Linaro-mm-sig

linaro-mm-sig@lists.linaro.org

27 participants
3087 discussions

[PATCH 2/3] udmabuf: check that __pad is zero

by Gerd Hoffmann

Reported-by: Yann Droneaud <ydroneaud(a)opteya.com> Signed-off-by: Gerd Hoffmann <kraxel(a)redhat.com> --- drivers/dma-buf/udmabuf.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c index 9635897458a0..6c3ec8fcef01 100644 --- a/drivers/dma-buf/udmabuf.c +++ b/drivers/dma-buf/udmabuf.c @@ -137,6 +137,8 @@ static long udmabuf_create(const struct udmabuf_create_list *head, pglimit = (size_limit_mb * 1024 * 1024) >> PAGE_SHIFT; for (i = 0; i < head->count; i++) { + if (list[i].__pad) + goto err; if (!IS_ALIGNED(list[i].offset, PAGE_SIZE)) goto err; if (!IS_ALIGNED(list[i].size, PAGE_SIZE)) -- 2.18.1

6 years, 2 months

[PATCH 1/3] udmabuf: add documentation

by Gerd Hoffmann

Signed-off-by: Gerd Hoffmann <kraxel(a)redhat.com> --- include/uapi/linux/udmabuf.h | 52 ++++++++++++++++++++++++++-- Documentation/driver-api/dma-buf.rst | 8 +++++ 2 files changed, 57 insertions(+), 3 deletions(-) diff --git a/include/uapi/linux/udmabuf.h b/include/uapi/linux/udmabuf.h index 46b6532ed855..9fe440abf2f9 100644 --- a/include/uapi/linux/udmabuf.h +++ b/include/uapi/linux/udmabuf.h @@ -5,8 +5,39 @@ #include <linux/types.h> #include <linux/ioctl.h> +/** + * DOC: udmabuf + * + * udmabuf is a device driver which allows userspace to create + * dmabufs. The memory used for these dmabufs must be backed by + * memfd. The memfd must have F_SEAL_SHRINK and it must not have + * F_SEAL_WRITE. + * + * The driver has two ioctls, one to create a dmabuf from a single + * memory block and one to create a dmabuf from a list of memory + * blocks. + * + * UDMABUF_CREATE - _IOW('u', 0x42, udmabuf_create) + * + * UDMABUF_CREATE_LIST - _IOW('u', 0x43, udmabuf_create_list) + */ + +#define UDMABUF_CREATE _IOW('u', 0x42, struct udmabuf_create) +#define UDMABUF_CREATE_LIST _IOW('u', 0x43, struct udmabuf_create_list) + #define UDMABUF_FLAGS_CLOEXEC 0x01 +/** + * struct udmabuf_create - create a dmabuf from a single memory block. + * + * @memfd: The file handle. + * @offset: Start of the buffer (from memfd start). + * Must be page aligned. + * @size: Size of the buffer. Must be rounded to page size. + * + * @flags: + * UDMABUF_FLAGS_CLOEXEC: set CLOEXEC flag for the dmabuf. + */ struct udmabuf_create { __u32 memfd; __u32 flags; @@ -14,6 +45,15 @@ struct udmabuf_create { __u64 size; }; +/** + * struct udmabuf_create_item - one memory block list item. + * + * @memfd: The file handle. + * @__pad: Padding field (unused). + * @offset: Start of the buffer (from memfd start). + * Must be page aligned. + * @size: Size of the buffer. Must be rounded to page size. + */ struct udmabuf_create_item { __u32 memfd; __u32 __pad; @@ -21,13 +61,19 @@ struct udmabuf_create_item { __u64 size; }; +/** + * struct udmabuf_create_list - create a dmabuf from a memory block list. + * + * @count: The number of list elements. + * @list: The memory block list + * + * @flags: + * UDMABUF_FLAGS_CLOEXEC: set CLOEXEC flag for the dmabuf. + */ struct udmabuf_create_list { __u32 flags; __u32 count; struct udmabuf_create_item list[]; }; -#define UDMABUF_CREATE _IOW('u', 0x42, struct udmabuf_create) -#define UDMABUF_CREATE_LIST _IOW('u', 0x43, struct udmabuf_create_list) - #endif /* _UAPI_LINUX_UDMABUF_H */ diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst index b541e97c7ab1..1f62c30a14b0 100644 --- a/Documentation/driver-api/dma-buf.rst +++ b/Documentation/driver-api/dma-buf.rst @@ -166,3 +166,11 @@ DMA Fence uABI/Sync File .. kernel-doc:: include/linux/sync_file.h :internal: +Userspace DMA Buffer driver +~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +.. kernel-doc:: include/uapi/linux/udmabuf.h + :doc: udmabuf + +.. kernel-doc:: include/uapi/linux/udmabuf.h + :internal: -- 2.18.1

6 years, 2 months

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, 2 months

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, 2 months

[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, 2 months

[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, 2 months

[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, 2 months

[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, 2 months

[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, 2 months

[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, 2 months

Jump to page:

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

Linaro-mm-sig