Linaro-mm-sig

linaro-mm-sig@lists.linaro.org

15 participants
3025 discussions

Re: [Linaro-mm-sig] [PATCH 08/10] dma-buf/resv: replace shared fence with new fences container

by Chris Wilson

Quoting Christian König (2019-08-21 13:31:45) > @@ -117,17 +120,10 @@ i915_gem_busy_ioctl(struct drm_device *dev, void *data, > busy_check_writer(rcu_dereference(obj->base.resv->fence_excl)); > > /* Translate shared fences to READ set of engines */ > - list = rcu_dereference(obj->base.resv->fence); > - if (list) { > - unsigned int shared_count = list->shared_count, i; > - > - for (i = 0; i < shared_count; ++i) { > - struct dma_fence *fence = > - rcu_dereference(list->shared[i]); > - > - args->busy |= busy_check_reader(fence); > - } > - } > + readers = dma_resv_fences_get_rcu(&obj->base.resv->readers); > + dma_fence_array_for_each(fence, cursor, readers) > + args->busy |= busy_check_reader(fence); > + dma_fence_put(readers); That's underwhelming, the full-mb shows up in scaling tests (I'll test the impact of this series later). Something like, do { read = 0; fences = dma_resv_fences_get_deref(&obj->base.resv->readers); dma_fence_array_for_each(fence, cursor, fences) read |= busy_check_reader(fence); smp_rmb(); } while (dma_resv_fences_get_deref(obj->readers) != fences) do { fences = dma_resv_fences_get_deref(&obj->base.resv->fences); write = busy_check_writer(fences); smp_rmb(); } while (dma_resv_fences_get_deref(obj->writes) != fences) args->busy = write | read; Perhaps? -Chris

6 years

Re: [Linaro-mm-sig] [PATCH 08/10] dma-buf/resv: replace shared fence with new fences container

by Chris Wilson

Quoting Christian König (2019-08-21 13:31:45) > @@ -528,20 +352,9 @@ void dma_resv_prune_fences(struct dma_resv *obj) > dma_fence_put(fence); > } > > - list = dma_resv_get_list(obj); > - if (!list) > - return; > - > - for (i = 0; i < list->shared_count; ++i) { > - fence = rcu_dereference_protected(list->shared[i], > - dma_resv_held(obj)); > - > - if (!dma_fence_is_signaled(fence)) > - continue; > - > - RCU_INIT_POINTER(list->shared[i], dma_fence_get_stub()); > - dma_fence_put(fence); > - } > + fence = dma_resv_fences_deref(obj, &obj->readers); > + if (dma_fence_is_signaled(fence)) > + dma_resv_fences_set(obj, &obj->readers, NULL); Needs fence==NULL safeguards. It's not as pruny as it was before. Or did you add some magic to fence-array? -Chris

6 years

[PATCH 1/4] dma-buf: add reservation_object_fences helper

by Christian König

Add a new helper to get a consistent set of pointers from the reservation object. While at it group all access helpers together in the header file. v2: correctly return shared_count as well Signed-off-by: Christian König <christian.koenig(a)amd.com> --- drivers/dma-buf/dma-buf.c | 31 ++------- drivers/dma-buf/reservation.c | 82 ++++++++---------------- include/linux/reservation.h | 115 +++++++++++++++++++++------------- 3 files changed, 101 insertions(+), 127 deletions(-) diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index f45bfb29ef96..67510f2be8bc 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -199,7 +199,7 @@ static __poll_t dma_buf_poll(struct file *file, poll_table *poll) struct reservation_object_list *fobj; struct dma_fence *fence_excl; __poll_t events; - unsigned shared_count, seq; + unsigned shared_count; dmabuf = file->private_data; if (!dmabuf || !dmabuf->resv) @@ -213,21 +213,8 @@ static __poll_t dma_buf_poll(struct file *file, poll_table *poll) if (!events) return 0; -retry: - seq = read_seqcount_begin(&resv->seq); rcu_read_lock(); - - fobj = rcu_dereference(resv->fence); - if (fobj) - shared_count = fobj->shared_count; - else - shared_count = 0; - fence_excl = rcu_dereference(resv->fence_excl); - if (read_seqcount_retry(&resv->seq, seq)) { - rcu_read_unlock(); - goto retry; - } - + reservation_object_fences(resv, &fence_excl, &fobj, &shared_count); if (fence_excl && (!(events & EPOLLOUT) || shared_count == 0)) { struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_excl; __poll_t pevents = EPOLLIN; @@ -1157,7 +1144,6 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused) struct reservation_object *robj; struct reservation_object_list *fobj; struct dma_fence *fence; - unsigned seq; int count = 0, attach_count, shared_count, i; size_t size = 0; @@ -1188,16 +1174,9 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused) buf_obj->name ?: ""); robj = buf_obj->resv; - while (true) { - seq = read_seqcount_begin(&robj->seq); - rcu_read_lock(); - fobj = rcu_dereference(robj->fence); - shared_count = fobj ? fobj->shared_count : 0; - fence = rcu_dereference(robj->fence_excl); - if (!read_seqcount_retry(&robj->seq, seq)) - break; - rcu_read_unlock(); - } + rcu_read_lock(); + reservation_object_fences(robj, &fence, &fobj, &shared_count); + rcu_read_unlock(); if (fence) seq_printf(s, "\tExclusive fence: %s %s %ssignalled\n", diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c index ad6775b32a73..8fcaddffd5d4 100644 --- a/drivers/dma-buf/reservation.c +++ b/drivers/dma-buf/reservation.c @@ -317,17 +317,15 @@ int reservation_object_copy_fences(struct reservation_object *dst, { struct reservation_object_list *src_list, *dst_list; struct dma_fence *old, *new; - unsigned i; + unsigned int i, shared_count; reservation_object_assert_held(dst); rcu_read_lock(); - src_list = rcu_dereference(src->fence); retry: - if (src_list) { - unsigned shared_count = src_list->shared_count; - + reservation_object_fences(src, &new, &src_list, &shared_count); + if (shared_count) { rcu_read_unlock(); dst_list = reservation_object_list_alloc(shared_count); @@ -335,14 +333,14 @@ int reservation_object_copy_fences(struct reservation_object *dst, return -ENOMEM; rcu_read_lock(); - src_list = rcu_dereference(src->fence); - if (!src_list || src_list->shared_count > shared_count) { + reservation_object_fences(src, &new, &src_list, &shared_count); + if (!src_list || shared_count > dst_list->shared_max) { kfree(dst_list); goto retry; } dst_list->shared_count = 0; - for (i = 0; i < src_list->shared_count; ++i) { + for (i = 0; i < shared_count; ++i) { struct dma_fence *fence; fence = rcu_dereference(src_list->shared[i]); @@ -352,7 +350,6 @@ int reservation_object_copy_fences(struct reservation_object *dst, if (!dma_fence_get_rcu(fence)) { reservation_object_list_free(dst_list); - src_list = rcu_dereference(src->fence); goto retry; } @@ -367,7 +364,10 @@ int reservation_object_copy_fences(struct reservation_object *dst, dst_list = NULL; } - new = dma_fence_get_rcu_safe(&src->fence_excl); + if (new && !dma_fence_get_rcu(new)) { + reservation_object_list_free(dst_list); + goto retry; + } rcu_read_unlock(); src_list = reservation_object_get_list(dst); @@ -413,19 +413,18 @@ int reservation_object_get_fences_rcu(struct reservation_object *obj, do { struct reservation_object_list *fobj; - unsigned int i, seq; + unsigned int i; size_t sz = 0; - shared_count = i = 0; + i = 0; rcu_read_lock(); - seq = read_seqcount_begin(&obj->seq); + reservation_object_fences(obj, &fence_excl, &fobj, + &shared_count); - fence_excl = rcu_dereference(obj->fence_excl); if (fence_excl && !dma_fence_get_rcu(fence_excl)) goto unlock; - fobj = rcu_dereference(obj->fence); if (fobj) sz += sizeof(*shared) * fobj->shared_max; @@ -453,7 +452,6 @@ int reservation_object_get_fences_rcu(struct reservation_object *obj, break; } shared = nshared; - shared_count = fobj ? fobj->shared_count : 0; for (i = 0; i < shared_count; ++i) { shared[i] = rcu_dereference(fobj->shared[i]); if (!dma_fence_get_rcu(shared[i])) @@ -461,7 +459,7 @@ int reservation_object_get_fences_rcu(struct reservation_object *obj, } } - if (i != shared_count || read_seqcount_retry(&obj->seq, seq)) { + if (i != shared_count) { while (i--) dma_fence_put(shared[i]); dma_fence_put(fence_excl); @@ -505,18 +503,17 @@ long reservation_object_wait_timeout_rcu(struct reservation_object *obj, bool wait_all, bool intr, unsigned long timeout) { + struct reservation_object_list *fobj; struct dma_fence *fence; - unsigned seq, shared_count; + unsigned shared_count; long ret = timeout ? timeout : 1; int i; retry: - shared_count = 0; - seq = read_seqcount_begin(&obj->seq); rcu_read_lock(); i = -1; - fence = rcu_dereference(obj->fence_excl); + reservation_object_fences(obj, &fence, &fobj, &shared_count); if (fence && !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { if (!dma_fence_get_rcu(fence)) goto unlock_retry; @@ -531,12 +528,6 @@ long reservation_object_wait_timeout_rcu(struct reservation_object *obj, } if (wait_all) { - struct reservation_object_list *fobj = - rcu_dereference(obj->fence); - - if (fobj) - shared_count = fobj->shared_count; - for (i = 0; !fence && i < shared_count; ++i) { struct dma_fence *lfence = rcu_dereference(fobj->shared[i]); @@ -559,11 +550,6 @@ long reservation_object_wait_timeout_rcu(struct reservation_object *obj, rcu_read_unlock(); if (fence) { - if (read_seqcount_retry(&obj->seq, seq)) { - dma_fence_put(fence); - goto retry; - } - ret = dma_fence_wait_timeout(fence, intr, ret); dma_fence_put(fence); if (ret > 0 && wait_all && (i + 1 < shared_count)) @@ -608,24 +594,19 @@ reservation_object_test_signaled_single(struct dma_fence *passed_fence) bool reservation_object_test_signaled_rcu(struct reservation_object *obj, bool test_all) { - unsigned seq, shared_count; + struct reservation_object_list *fobj; + struct dma_fence *fence_excl; + unsigned shared_count; int ret; rcu_read_lock(); retry: ret = true; - shared_count = 0; - seq = read_seqcount_begin(&obj->seq); + reservation_object_fences(obj, &fence_excl, &fobj, &shared_count); if (test_all) { unsigned i; - struct reservation_object_list *fobj = - rcu_dereference(obj->fence); - - if (fobj) - shared_count = fobj->shared_count; - for (i = 0; i < shared_count; ++i) { struct dma_fence *fence = rcu_dereference(fobj->shared[i]); @@ -635,23 +616,12 @@ bool reservation_object_test_signaled_rcu(struct reservation_object *obj, else if (!ret) break; } - - if (read_seqcount_retry(&obj->seq, seq)) - goto retry; } - if (!shared_count) { - struct dma_fence *fence_excl = rcu_dereference(obj->fence_excl); - - if (fence_excl) { - ret = reservation_object_test_signaled_single( - fence_excl); - if (ret < 0) - goto retry; - - if (read_seqcount_retry(&obj->seq, seq)) - goto retry; - } + if (!shared_count && fence_excl) { + ret = reservation_object_test_signaled_single(fence_excl); + if (ret < 0) + goto retry; } rcu_read_unlock(); diff --git a/include/linux/reservation.h b/include/linux/reservation.h index 56b782fec49b..044a5cd4af50 100644 --- a/include/linux/reservation.h +++ b/include/linux/reservation.h @@ -81,6 +81,51 @@ struct reservation_object { #define reservation_object_assert_held(obj) \ lockdep_assert_held(&(obj)->lock.base) +/** + * reservation_object_get_excl - get the reservation object's + * exclusive fence, with update-side lock held + * @obj: the reservation object + * + * Returns the exclusive fence (if any). Does NOT take a + * reference. Writers must hold obj->lock, readers may only + * hold a RCU read side lock. + * + * RETURNS + * The exclusive fence or NULL + */ +static inline struct dma_fence * +reservation_object_get_excl(struct reservation_object *obj) +{ + return rcu_dereference_protected(obj->fence_excl, + reservation_object_held(obj)); +} + +/** + * reservation_object_get_excl_rcu - get the reservation object's + * exclusive fence, without lock held. + * @obj: the reservation object + * + * If there is an exclusive fence, this atomically increments it's + * reference count and returns it. + * + * RETURNS + * The exclusive fence or NULL if none + */ +static inline struct dma_fence * +reservation_object_get_excl_rcu(struct reservation_object *obj) +{ + struct dma_fence *fence; + + if (!rcu_access_pointer(obj->fence_excl)) + return NULL; + + rcu_read_lock(); + fence = dma_fence_get_rcu_safe(&obj->fence_excl); + rcu_read_unlock(); + + return fence; +} + /** * reservation_object_get_list - get the reservation object's * shared fence list, with update-side lock held @@ -96,6 +141,31 @@ reservation_object_get_list(struct reservation_object *obj) reservation_object_held(obj)); } +/** + * reservation_object_fences - read consistent fence pointers + * @obj: reservation object where we get the fences from + * @excl: pointer for the exclusive fence + * @list: pointer for the shared fence list + * + * Make sure we have a consisten exclusive fence and shared fence list. + * Must be called with rcu read side lock held. + */ +static inline void +reservation_object_fences(struct reservation_object *obj, + struct dma_fence **excl, + struct reservation_object_list **list, + u32 *shared_count) +{ + unsigned int seq; + + do { + seq = read_seqcount_begin(&obj->seq); + *excl = rcu_dereference(obj->fence_excl); + *list = rcu_dereference(obj->fence); + *shared_count = *list ? (*list)->shared_count : 0; + } while (read_seqcount_retry(&obj->seq, seq)); +} + /** * reservation_object_lock - lock the reservation object * @obj: the reservation object @@ -239,51 +309,6 @@ reservation_object_unlock(struct reservation_object *obj) ww_mutex_unlock(&obj->lock); } -/** - * reservation_object_get_excl - get the reservation object's - * exclusive fence, with update-side lock held - * @obj: the reservation object - * - * Returns the exclusive fence (if any). Does NOT take a - * reference. Writers must hold obj->lock, readers may only - * hold a RCU read side lock. - * - * RETURNS - * The exclusive fence or NULL - */ -static inline struct dma_fence * -reservation_object_get_excl(struct reservation_object *obj) -{ - return rcu_dereference_protected(obj->fence_excl, - reservation_object_held(obj)); -} - -/** - * reservation_object_get_excl_rcu - get the reservation object's - * exclusive fence, without lock held. - * @obj: the reservation object - * - * If there is an exclusive fence, this atomically increments it's - * reference count and returns it. - * - * RETURNS - * The exclusive fence or NULL if none - */ -static inline struct dma_fence * -reservation_object_get_excl_rcu(struct reservation_object *obj) -{ - struct dma_fence *fence; - - if (!rcu_access_pointer(obj->fence_excl)) - return NULL; - - rcu_read_lock(); - fence = dma_fence_get_rcu_safe(&obj->fence_excl); - rcu_read_unlock(); - - return fence; -} - void reservation_object_init(struct reservation_object *obj); void reservation_object_fini(struct reservation_object *obj); int reservation_object_reserve_shared(struct reservation_object *obj, -- 2.17.1

6 years, 1 month

[PATCH] dma-buf: make dma_fence structure a bit smaller v2

by Christian König

We clear the callback list on kref_put so that by the time we release the fence it is unused. No one should be adding to the cb_list that they don't themselves hold a reference for. This small change is actually making the structure 16% smaller. v2: add the comment to the code as well. Signed-off-by: Christian König <christian.koenig(a)amd.com> Reviewed-by: Chris Wilson <chris(a)chris-wilson.co.uk> --- include/linux/dma-fence.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 05d29dbc7e62..bea1d05cf51e 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -65,8 +65,14 @@ struct dma_fence_cb; struct dma_fence { struct kref refcount; const struct dma_fence_ops *ops; - struct rcu_head rcu; - struct list_head cb_list; + /* We clear the callback list on kref_put so that by the time we + * release the fence it is unused. No one should be adding to the cb_list + * that they don't themselves hold a reference for. + */ + union { + struct rcu_head rcu; + struct list_head cb_list; + }; spinlock_t *lock; u64 context; u64 seqno; -- 2.17.1

6 years, 1 month

[PATCH] dma-buf: make dma_fence structure a bit smaller

by Christian König

We clear the callback list on kref_put so that by the time we release the fence it is unused. No one should be adding to the cb_list that they don't themselves hold a reference for. This small change is actually making the structure 16% smaller. Signed-off-by: Christian König <christian.koenig(a)amd.com> Reviewed-by: Chris Wilson <chris(a)chris-wilson.co.uk> --- include/linux/dma-fence.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 05d29dbc7e62..3985c72cd0c2 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -65,8 +65,10 @@ struct dma_fence_cb; struct dma_fence { struct kref refcount; const struct dma_fence_ops *ops; - struct rcu_head rcu; - struct list_head cb_list; + union { + struct rcu_head rcu; + struct list_head cb_list; + }; spinlock_t *lock; u64 context; u64 seqno; -- 2.17.1

6 years, 1 month

[PATCH] dma-buf: make dma_fence structure a bit smaller

by Christian König

The ruc and cb_list are never used at the same time. This smal change is actually making the structure 16% smaller. Signed-off-by: Christian König <christian.koenig(a)amd.com> --- include/linux/dma-fence.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 05d29dbc7e62..3985c72cd0c2 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -65,8 +65,10 @@ struct dma_fence_cb; struct dma_fence { struct kref refcount; const struct dma_fence_ops *ops; - struct rcu_head rcu; - struct list_head cb_list; + union { + struct rcu_head rcu; + struct list_head cb_list; + }; spinlock_t *lock; u64 context; u64 seqno; -- 2.17.1

6 years, 1 month

[PATCH 1/8] dma-buf: fix busy wait for new shared fences

by Christian König

When reservation_object_add_shared_fence is replacing an old fence with a new one we should not drop the old one before the new one is in place. Otherwise other cores can busy wait for the new one to appear. Signed-off-by: Christian König <christian.koenig(a)amd.com> --- drivers/dma-buf/reservation.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c index c71b85c8c159..d59207ca72d2 100644 --- a/drivers/dma-buf/reservation.c +++ b/drivers/dma-buf/reservation.c @@ -196,6 +196,7 @@ void reservation_object_add_shared_fence(struct reservation_object *obj, struct dma_fence *fence) { struct reservation_object_list *fobj; + struct dma_fence *old; unsigned int i, count; dma_fence_get(fence); @@ -209,18 +210,16 @@ void reservation_object_add_shared_fence(struct reservation_object *obj, write_seqcount_begin(&obj->seq); for (i = 0; i < count; ++i) { - struct dma_fence *old_fence; - old_fence = rcu_dereference_protected(fobj->shared[i], - reservation_object_held(obj)); - if (old_fence->context == fence->context || - dma_fence_is_signaled(old_fence)) { - dma_fence_put(old_fence); + old = rcu_dereference_protected(fobj->shared[i], + reservation_object_held(obj)); + if (old->context == fence->context || + dma_fence_is_signaled(old)) goto replace; - } } BUG_ON(fobj->shared_count >= fobj->shared_max); + old = NULL; count++; replace: @@ -230,6 +229,7 @@ void reservation_object_add_shared_fence(struct reservation_object *obj, write_seqcount_end(&obj->seq); preempt_enable(); + dma_fence_put(old); } EXPORT_SYMBOL(reservation_object_add_shared_fence); -- 2.17.1

6 years, 1 month

[PATCH 1/5] drm/i915: stop pruning reservation object after wait

by Christian König

The reservation object should be capable of handling its internal memory management itself. And since we search for a free slot to add the fence from the beginning this is actually a waste of time and only minimal helpful. Drop it to allow removal of the seqno handling in the reservation object. This essentially reverts commit "drm/i915: Remove completed fences after a wait". Signed-off-by: Christian König <christian.koenig(a)amd.com> --- drivers/gpu/drm/i915/gem/i915_gem_wait.c | 27 ------------------------ 1 file changed, 27 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_wait.c b/drivers/gpu/drm/i915/gem/i915_gem_wait.c index 26ec6579b7cd..bb64ec6bef8e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_wait.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_wait.c @@ -35,9 +35,7 @@ i915_gem_object_wait_reservation(struct reservation_object *resv, unsigned int flags, long timeout) { - unsigned int seq = __read_seqcount_begin(&resv->seq); struct dma_fence *excl; - bool prune_fences = false; if (flags & I915_WAIT_ALL) { struct dma_fence **shared; @@ -61,17 +59,6 @@ i915_gem_object_wait_reservation(struct reservation_object *resv, for (; i < count; i++) dma_fence_put(shared[i]); kfree(shared); - - /* - * If both shared fences and an exclusive fence exist, - * then by construction the shared fences must be later - * than the exclusive fence. If we successfully wait for - * all the shared fences, we know that the exclusive fence - * must all be signaled. If all the shared fences are - * signaled, we can prune the array and recover the - * floating references on the fences/requests. - */ - prune_fences = count && timeout >= 0; } else { excl = reservation_object_get_excl_rcu(resv); } @@ -80,20 +67,6 @@ i915_gem_object_wait_reservation(struct reservation_object *resv, timeout = i915_gem_object_wait_fence(excl, flags, timeout); dma_fence_put(excl); - - /* - * Opportunistically prune the fences iff we know they have *all* been - * signaled and that the reservation object has not been changed (i.e. - * no new fences have been added). - */ - if (prune_fences && !__read_seqcount_retry(&resv->seq, seq)) { - if (reservation_object_trylock(resv)) { - if (!__read_seqcount_retry(&resv->seq, seq)) - reservation_object_add_excl_fence(resv, NULL); - reservation_object_unlock(resv); - } - } - return timeout; } -- 2.17.1

6 years, 1 month

[PATCH] dma-buf: add more reservation object locking wrappers

by Christian König

Complete the abstraction of the ww_mutex inside the reservation object. This allows us to add more handling and debugging to the reservation object in the future. Signed-off-by: Christian König <christian.koenig(a)amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 6 +-- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 6 +-- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 3 +- drivers/gpu/drm/drm_gem.c | 14 ++--- drivers/gpu/drm/nouveau/nouveau_prime.c | 4 +- drivers/gpu/drm/radeon/radeon_object.c | 6 +-- drivers/gpu/drm/radeon/radeon_prime.c | 4 +- drivers/gpu/drm/ttm/ttm_bo.c | 10 ++-- drivers/gpu/drm/ttm/ttm_execbuf_util.c | 6 +-- drivers/gpu/drm/vmwgfx/vmwgfx_blit.c | 4 +- drivers/gpu/drm/vmwgfx/vmwgfx_bo.c | 2 +- drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c | 4 +- drivers/gpu/drm/vmwgfx/vmwgfx_resource.c | 6 +-- include/drm/ttm/ttm_bo_driver.h | 6 +-- include/linux/reservation.h | 57 +++++++++++++++++++++ 16 files changed, 100 insertions(+), 40 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 4b1e4b321999..f486c23fa24c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1725,7 +1725,7 @@ int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser, *map = mapping; /* Double check that the BO is reserved by this CS */ - if (READ_ONCE((*bo)->tbo.resv->lock.ctx) != &parser->ticket) + if (reservation_object_locking_ctx((*bo)->tbo.resv) != &parser->ticket) return -EINVAL; if (!((*bo)->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 6770eb3967a6..e1d2c410bc33 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -398,7 +398,7 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev, bp.flags = 0; bp.type = ttm_bo_type_sg; bp.resv = resv; - ww_mutex_lock(&resv->lock, NULL); + reservation_object_lock(resv, NULL); ret = amdgpu_bo_create(adev, &bp, &bo); if (ret) goto error; @@ -410,11 +410,11 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev, if (attach->dmabuf->ops != &amdgpu_dmabuf_ops) bo->prime_shared_count = 1; - ww_mutex_unlock(&resv->lock); + reservation_object_unlock(resv); return &bo->gem_base; error: - ww_mutex_unlock(&resv->lock); + reservation_object_unlock(resv); return ERR_PTR(ret); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 87020628a66e..c31e96925892 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -553,7 +553,7 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev, fail_unreserve: if (!bp->resv) - ww_mutex_unlock(&bo->tbo.resv->lock); + reservation_object_unlock(bo->tbo.resv); amdgpu_bo_unref(&bo); return r; } @@ -1096,7 +1096,7 @@ int amdgpu_bo_set_tiling_flags(struct amdgpu_bo *bo, u64 tiling_flags) */ void amdgpu_bo_get_tiling_flags(struct amdgpu_bo *bo, u64 *tiling_flags) { - lockdep_assert_held(&bo->tbo.resv->lock.base); + reservation_object_assert_held(bo->tbo.resv); if (tiling_flags) *tiling_flags = bo->tiling_flags; @@ -1337,7 +1337,7 @@ int amdgpu_bo_sync_wait(struct amdgpu_bo *bo, void *owner, bool intr) u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo) { WARN_ON_ONCE(bo->tbo.mem.mem_type == TTM_PL_SYSTEM); - WARN_ON_ONCE(!ww_mutex_is_locked(&bo->tbo.resv->lock) && + WARN_ON_ONCE(!reservation_object_is_locked(bo->tbo.resv) && !bo->pin_count && bo->tbo.type != ttm_bo_type_kernel); WARN_ON_ONCE(bo->tbo.mem.start == AMDGPU_BO_INVALID_OFFSET); WARN_ON_ONCE(bo->tbo.mem.mem_type == TTM_PL_VRAM && diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index c1baf3d879b7..e9df0b10a37e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2416,7 +2416,8 @@ void amdgpu_vm_bo_trace_cs(struct amdgpu_vm *vm, struct ww_acquire_ctx *ticket) struct amdgpu_bo *bo; bo = mapping->bo_va->base.bo; - if (READ_ONCE(bo->tbo.resv->lock.ctx) != ticket) + if (reservation_object_locking_ctx(bo->tbo.resv) != + ticket) continue; } diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 50de138c89e0..04c0307ca54f 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -1316,8 +1316,8 @@ drm_gem_lock_reservations(struct drm_gem_object **objs, int count, if (contended != -1) { struct drm_gem_object *obj = objs[contended]; - ret = ww_mutex_lock_slow_interruptible(&obj->resv->lock, - acquire_ctx); + ret = reservation_object_lock_slow_interruptible(obj->resv, + acquire_ctx); if (ret) { ww_acquire_done(acquire_ctx); return ret; @@ -1328,16 +1328,16 @@ drm_gem_lock_reservations(struct drm_gem_object **objs, int count, if (i == contended) continue; - ret = ww_mutex_lock_interruptible(&objs[i]->resv->lock, - acquire_ctx); + ret = reservation_object_lock_interruptible(objs[i]->resv, + acquire_ctx); if (ret) { int j; for (j = 0; j < i; j++) - ww_mutex_unlock(&objs[j]->resv->lock); + reservation_object_unlock(objs[j]->resv); if (contended != -1 && contended >= i) - ww_mutex_unlock(&objs[contended]->resv->lock); + reservation_object_unlock(objs[contended]->resv); if (ret == -EDEADLK) { contended = i; @@ -1362,7 +1362,7 @@ drm_gem_unlock_reservations(struct drm_gem_object **objs, int count, int i; for (i = 0; i < count; i++) - ww_mutex_unlock(&objs[i]->resv->lock); + reservation_object_unlock(objs[i]->resv); ww_acquire_fini(acquire_ctx); } diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c index 1fefc93af1d7..38abdfa96af7 100644 --- a/drivers/gpu/drm/nouveau/nouveau_prime.c +++ b/drivers/gpu/drm/nouveau/nouveau_prime.c @@ -68,10 +68,10 @@ struct drm_gem_object *nouveau_gem_prime_import_sg_table(struct drm_device *dev, flags = TTM_PL_FLAG_TT; - ww_mutex_lock(&robj->lock, NULL); + reservation_object_lock(robj, NULL); ret = nouveau_bo_new(&drm->client, attach->dmabuf->size, 0, flags, 0, 0, sg, robj, &nvbo); - ww_mutex_unlock(&robj->lock); + reservation_object_unlock(robj); if (ret) return ERR_PTR(ret); diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index 36683de0300b..3210b1e090f8 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -607,7 +607,7 @@ int radeon_bo_get_surface_reg(struct radeon_bo *bo) int steal; int i; - lockdep_assert_held(&bo->tbo.resv->lock.base); + reservation_object_assert_held(bo->tbo.resv); if (!bo->tiling_flags) return 0; @@ -733,7 +733,7 @@ void radeon_bo_get_tiling_flags(struct radeon_bo *bo, uint32_t *tiling_flags, uint32_t *pitch) { - lockdep_assert_held(&bo->tbo.resv->lock.base); + reservation_object_assert_held(bo->tbo.resv); if (tiling_flags) *tiling_flags = bo->tiling_flags; @@ -745,7 +745,7 @@ int radeon_bo_check_tiling(struct radeon_bo *bo, bool has_moved, bool force_drop) { if (!force_drop) - lockdep_assert_held(&bo->tbo.resv->lock.base); + reservation_object_assert_held(bo->tbo.resv); if (!(bo->tiling_flags & RADEON_TILING_SURFACE)) return 0; diff --git a/drivers/gpu/drm/radeon/radeon_prime.c b/drivers/gpu/drm/radeon/radeon_prime.c index 7110d403322c..f48bc87d0e4b 100644 --- a/drivers/gpu/drm/radeon/radeon_prime.c +++ b/drivers/gpu/drm/radeon/radeon_prime.c @@ -66,10 +66,10 @@ struct drm_gem_object *radeon_gem_prime_import_sg_table(struct drm_device *dev, struct radeon_bo *bo; int ret; - ww_mutex_lock(&resv->lock, NULL); + reservation_object_lock(resv, NULL); ret = radeon_bo_create(rdev, attach->dmabuf->size, PAGE_SIZE, false, RADEON_GEM_DOMAIN_GTT, 0, sg, resv, &bo); - ww_mutex_unlock(&resv->lock); + reservation_object_unlock(resv); if (ret) return ERR_PTR(ret); diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 58c403eda04e..40d3e547c78e 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -850,8 +850,8 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev, if (!ttm_bo_evict_swapout_allowable(bo, ctx, &locked, &busy)) { - if (busy && !busy_bo && - bo->resv->lock.ctx != ticket) + if (busy && !busy_bo && ticket != + reservation_object_locking_ctx(bo->resv)) busy_bo = bo; continue; } @@ -957,8 +957,10 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo, { struct ttm_bo_device *bdev = bo->bdev; struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type]; + struct ww_acquire_ctx *ticket; int ret; + ticket = reservation_object_locking_ctx(bo->resv); do { ret = (*man->func->get_node)(man, bo, place, mem); if (unlikely(ret != 0)) @@ -966,7 +968,7 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo, if (mem->mm_node) break; ret = ttm_mem_evict_first(bdev, mem->mem_type, place, ctx, - bo->resv->lock.ctx); + ticket); if (unlikely(ret != 0)) return ret; } while (1); @@ -1963,7 +1965,7 @@ int ttm_bo_wait_unreserved(struct ttm_buffer_object *bo) ret = mutex_lock_interruptible(&bo->wu_mutex); if (unlikely(ret != 0)) return -ERESTARTSYS; - if (!ww_mutex_is_locked(&bo->resv->lock)) + if (!reservation_object_is_locked(bo->resv)) goto out_unlock; ret = reservation_object_lock_interruptible(bo->resv, NULL); if (ret == -EINTR) diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c index 957ec375a4ba..723fb583fdda 100644 --- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c +++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c @@ -144,10 +144,10 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket, if (ret == -EDEADLK) { if (intr) { - ret = ww_mutex_lock_slow_interruptible(&bo->resv->lock, - ticket); + ret = reservation_object_lock_slow_interruptible(bo->resv, + ticket); } else { - ww_mutex_lock_slow(&bo->resv->lock, ticket); + reservation_object_lock_slow(bo->resv, ticket); ret = 0; } } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c index fc6673cde289..703786e3d579 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c @@ -459,9 +459,9 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst, /* Buffer objects need to be either pinned or reserved: */ if (!(dst->mem.placement & TTM_PL_FLAG_NO_EVICT)) - lockdep_assert_held(&dst->resv->lock.base); + reservation_object_assert_held(dst->resv); if (!(src->mem.placement & TTM_PL_FLAG_NO_EVICT)) - lockdep_assert_held(&src->resv->lock.base); + reservation_object_assert_held(src->resv); if (dst->ttm->state == tt_unpopulated) { ret = dst->ttm->bdev->driver->ttm_tt_populate(dst->ttm, &ctx); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index 5d5c2bce01f3..315da41a18b4 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -342,7 +342,7 @@ void vmw_bo_pin_reserved(struct vmw_buffer_object *vbo, bool pin) uint32_t old_mem_type = bo->mem.mem_type; int ret; - lockdep_assert_held(&bo->resv->lock.base); + reservation_object_assert_held(bo->resv); if (pin) { if (vbo->pin_count++ > 0) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c index b4f6e1217c9d..71e901bbed68 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c @@ -169,7 +169,7 @@ static int vmw_cotable_unscrub(struct vmw_resource *res) } *cmd; WARN_ON_ONCE(bo->mem.mem_type != VMW_PL_MOB); - lockdep_assert_held(&bo->resv->lock.base); + reservation_object_assert_held(bo->resv); cmd = VMW_FIFO_RESERVE(dev_priv, sizeof(*cmd)); if (!cmd) @@ -311,7 +311,7 @@ static int vmw_cotable_unbind(struct vmw_resource *res, return 0; WARN_ON_ONCE(bo->mem.mem_type != VMW_PL_MOB); - lockdep_assert_held(&bo->resv->lock.base); + reservation_object_assert_held(bo->resv); mutex_lock(&dev_priv->binding_mutex); if (!vcotbl->scrubbed) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index 1d38a8b2f2ec..303d2c7d9ab3 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -402,14 +402,14 @@ void vmw_resource_unreserve(struct vmw_resource *res, if (switch_backup && new_backup != res->backup) { if (res->backup) { - lockdep_assert_held(&res->backup->base.resv->lock.base); + reservation_object_assert_held(res->backup->base.resv); list_del_init(&res->mob_head); vmw_bo_unreference(&res->backup); } if (new_backup) { res->backup = vmw_bo_reference(new_backup); - lockdep_assert_held(&new_backup->base.resv->lock.base); + reservation_object_assert_held(new_backup->base.resv); list_add_tail(&res->mob_head, &new_backup->res_list); } else { res->backup = NULL; @@ -691,7 +691,7 @@ void vmw_resource_unbind_list(struct vmw_buffer_object *vbo) .num_shared = 0 }; - lockdep_assert_held(&vbo->base.resv->lock.base); + reservation_object_assert_held(vbo->base.resv); list_for_each_entry_safe(res, next, &vbo->res_list, mob_head) { if (!res->func->unbind) continue; diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index c9b8ba492f24..0e6a111bed0b 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -745,10 +745,10 @@ static inline int ttm_bo_reserve_slowpath(struct ttm_buffer_object *bo, WARN_ON(!kref_read(&bo->kref)); if (interruptible) - ret = ww_mutex_lock_slow_interruptible(&bo->resv->lock, - ticket); + ret = reservation_object_lock_slow_interruptible(bo->resv, + ticket); else - ww_mutex_lock_slow(&bo->resv->lock, ticket); + reservation_object_lock_slow(bo->resv, ticket); if (likely(ret == 0)) ttm_bo_del_sub_from_lru(bo); diff --git a/include/linux/reservation.h b/include/linux/reservation.h index f47e8196d039..d19de7a6af71 100644 --- a/include/linux/reservation.h +++ b/include/linux/reservation.h @@ -140,6 +140,38 @@ reservation_object_lock_interruptible(struct reservation_object *obj, return ww_mutex_lock_interruptible(&obj->lock, ctx); } +/** + * reservation_object_lock_slow - slowpath lock the reservation object + * @obj: the reservation object + * @ctx: the locking context + * + * Acquires the reservation object after a die case. This function + * will sleep until the lock becomes available. See reservation_object_lock() as + * well. + */ +static inline void +reservation_object_lock_slow(struct reservation_object *obj, + struct ww_acquire_ctx *ctx) +{ + ww_mutex_lock_slow(&obj->lock, ctx); +} + +/** + * reservation_object_lock_slow_interruptible - slowpath lock the reservation + * object, interruptible + * @obj: the reservation object + * @ctx: the locking context + * + * Acquires the reservation object interruptible after a die case. This function + * will sleep until the lock becomes available. See + * reservation_object_lock_interruptible() as well. + */ +static inline int +reservation_object_lock_slow_interruptible(struct reservation_object *obj, + struct ww_acquire_ctx *ctx) +{ + return ww_mutex_lock_slow_interruptible(&obj->lock, ctx); +} /** * reservation_object_trylock - trylock the reservation object @@ -161,6 +193,31 @@ reservation_object_trylock(struct reservation_object *obj) return ww_mutex_trylock(&obj->lock); } +/** + * reservation_object_is_locked - is the reservation object locked + * @obj: the reservation object + * + * Returns true if the mutex is locked, false if unlocked. + */ +static inline bool +reservation_object_is_locked(struct reservation_object *obj) +{ + return ww_mutex_is_locked(&obj->lock); +} + +/** + * reservation_object_locking_ctx - returns the context used to lock the object + * @obj: the reservation object + * + * Returns the context used to lock a reservation object or NULL if no context + * was used or the object is not locked at all. + */ +static inline struct ww_acquire_ctx * +reservation_object_locking_ctx(struct reservation_object *obj) +{ + return READ_ONCE(obj->lock.ctx); +} + /** * reservation_object_unlock - unlock the reservation object * @obj: the reservation object -- 2.17.1

6 years, 1 month

[PATCH 4.14 205/293] dma-buf: balance refcount inbalance

by Greg Kroah-Hartman

From: Jérôme Glisse <jglisse(a)redhat.com> commit 5e383a9798990c69fc759a4930de224bb497e62c upstream. The debugfs take reference on fence without dropping them. Signed-off-by: Jérôme Glisse <jglisse(a)redhat.com> Cc: Christian König <christian.koenig(a)amd.com> Cc: Daniel Vetter <daniel.vetter(a)ffwll.ch> Cc: Sumit Semwal <sumit.semwal(a)linaro.org> Cc: linux-media(a)vger.kernel.org Cc: dri-devel(a)lists.freedesktop.org Cc: linaro-mm-sig(a)lists.linaro.org Cc: Stéphane Marchesin <marcheu(a)chromium.org> Cc: stable(a)vger.kernel.org Reviewed-by: Christian König <christian.koenig(a)amd.com> Signed-off-by: Sumit Semwal <sumit.semwal(a)linaro.org> Link: https://patchwork.freedesktop.org/patch/msgid/20181206161840.6578-1-jglisse… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/dma-buf/dma-buf.c | 1 + 1 file changed, 1 insertion(+) --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -1115,6 +1115,7 @@ static int dma_buf_debug_show(struct seq fence->ops->get_driver_name(fence), fence->ops->get_timeline_name(fence), dma_fence_is_signaled(fence) ? "" : "un"); + dma_fence_put(fence); } rcu_read_unlock();

6 years, 1 month

Jump to page:

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

Linaro-mm-sig