From 4fa825bf405082a342b3a8717337ba58c7260c3f Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Fri, 28 Sep 2018 16:21:25 -0700 Subject: drm/v3d: Add some better documentation of the in_sync arguments. Since this is UAPI, it's good to document what exactly the guarantees we're providing are. Signed-off-by: Eric Anholt Link: https://patchwork.freedesktop.org/patch/msgid/20180928232126.4332-3-eric@anholt.net Reviewed-by: Boris Brezillon --- include/uapi/drm/v3d_drm.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/uapi/drm') diff --git a/include/uapi/drm/v3d_drm.h b/include/uapi/drm/v3d_drm.h index 7b6627783608..f446656d00b1 100644 --- a/include/uapi/drm/v3d_drm.h +++ b/include/uapi/drm/v3d_drm.h @@ -58,6 +58,11 @@ struct drm_v3d_submit_cl { * coordinate shader to determine where primitives land on the screen, * then writes out the state updates and draw calls necessary per tile * to the tile allocation BO. + * + * This BCL will block on any previous BCL submitted on the + * same FD, but not on any RCL or BCLs submitted by other + * clients -- that is left up to the submitter to control + * using in_sync_bcl if necessary. */ __u32 bcl_start; @@ -69,6 +74,11 @@ struct drm_v3d_submit_cl { * This is the second set of commands executed, which will either * execute the tiles that have been set up by the BCL, or a fixed set * of tiles (in the case of RCL-only blits). + * + * This RCL will block on this submit's BCL, and any previous + * RCL submitted on the same FD, but not on any RCL or BCLs + * submitted by other clients -- that is left up to the + * submitter to control using in_sync_rcl if necessary. */ __u32 rcl_start; -- cgit v1.2.3 From 48197bc564c7a1888c86024a1ba4f956e0ec2300 Mon Sep 17 00:00:00 2001 From: Chunming Zhou Date: Thu, 18 Oct 2018 14:18:36 +0800 Subject: drm: add syncobj timeline support v9 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch is for VK_KHR_timeline_semaphore extension, semaphore is called syncobj in kernel side: This extension introduces a new type of syncobj that has an integer payload identifying a point in a timeline. Such timeline syncobjs support the following operations: * CPU query - A host operation that allows querying the payload of the timeline syncobj. * CPU wait - A host operation that allows a blocking wait for a timeline syncobj to reach a specified value. * Device wait - A device operation that allows waiting for a timeline syncobj to reach a specified value. * Device signal - A device operation that allows advancing the timeline syncobj to a specified value. v1: Since it's a timeline, that means the front time point(PT) always is signaled before the late PT. a. signal PT design: Signal PT fence N depends on PT[N-1] fence and signal opertion fence, when PT[N] fence is signaled, the timeline will increase to value of PT[N]. b. wait PT design: Wait PT fence is signaled by reaching timeline point value, when timeline is increasing, will compare wait PTs value with new timeline value, if PT value is lower than timeline value, then wait PT will be signaled, otherwise keep in list. syncobj wait operation can wait on any point of timeline, so need a RB tree to order them. And wait PT could ahead of signal PT, we need a sumission fence to perform that. v2: 1. remove unused DRM_SYNCOBJ_CREATE_TYPE_NORMAL. (Christian) 2. move unexposed denitions to .c file. (Daniel Vetter) 3. split up the change to drm_syncobj_find_fence() in a separate patch. (Christian) 4. split up the change to drm_syncobj_replace_fence() in a separate patch. 5. drop the submission_fence implementation and instead use wait_event() for that. (Christian) 6. WARN_ON(point != 0) for NORMAL type syncobj case. (Daniel Vetter) v3: 1. replace normal syncobj with timeline implemenation. (Vetter and Christian) a. normal syncobj signal op will create a signal PT to tail of signal pt list. b. normal syncobj wait op will create a wait pt with last signal point, and this wait PT is only signaled by related signal point PT. 2. many bug fix and clean up 3. stub fence moving is moved to other patch. v4： 1. fix RB tree loop with while(node=rb_first(...)). (Christian) 2. fix syncobj lifecycle. (Christian) 3. only enable_signaling when there is wait_pt. (Christian) 4. fix timeline path issues. 5. write a timeline test in libdrm v5: (Christian) 1. semaphore is called syncobj in kernel side. 2. don't need 'timeline' characters in some function name. 3. keep syncobj cb. v6: (Christian) 1. merge syncobj_timeline to syncobj structure. 2. simplify some check sentences. 3. some misc change. 4. fix CTS failed issue. v7: (Christian) 1. error handling when creating signal pt. 2. remove timeline naming in func. 3. export flags in find_fence. 4. allow reset timeline. v8: 1. use wait_event_interruptible without timeout 2. rename _TYPE_INDIVIDUAL to _TYPE_BINARY v9: 1. rename signal_pt->base to signal_pt->fence_array to avoid misleading 2. improve kerneldoc individual syncobj is tested by ./deqp-vk -n dEQP-VK*semaphore* timeline syncobj is tested by ./amdgpu_test -s 9 Signed-off-by: Chunming Zhou Signed-off-by: Christian König Cc: Christian Konig Cc: Dave Airlie Cc: Daniel Rakos Cc: Daniel Vetter Cc: Bas Nieuwenhuizen Cc: Jason Ekstrand Reviewed-by: Christian König Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/257258/ --- drivers/gpu/drm/drm_syncobj.c | 306 +++++++++++++++++++++++++---- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 +- include/drm/drm_syncobj.h | 67 +++---- include/uapi/drm/drm.h | 1 + 4 files changed, 301 insertions(+), 75 deletions(-) (limited to 'include/uapi/drm') diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index e2c5b3ca4824..57bf6006394d 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -56,6 +56,9 @@ #include "drm_internal.h" #include +/* merge normal syncobj to timeline syncobj, the point interval is 1 */ +#define DRM_SYNCOBJ_BINARY_POINT 1 + struct drm_syncobj_stub_fence { struct dma_fence base; spinlock_t lock; @@ -71,6 +74,11 @@ static const struct dma_fence_ops drm_syncobj_stub_fence_ops = { .get_timeline_name = drm_syncobj_stub_fence_get_name, }; +struct drm_syncobj_signal_pt { + struct dma_fence_array *fence_array; + u64 value; + struct list_head list; +}; /** * drm_syncobj_find - lookup and reference a sync object. @@ -113,8 +121,8 @@ static int drm_syncobj_fence_get_or_add_callback(struct drm_syncobj *syncobj, { int ret; - *fence = drm_syncobj_fence_get(syncobj); - if (*fence) + ret = drm_syncobj_search_fence(syncobj, 0, 0, fence); + if (!ret) return 1; spin_lock(&syncobj->lock); @@ -122,10 +130,12 @@ static int drm_syncobj_fence_get_or_add_callback(struct drm_syncobj *syncobj, * have the lock, try one more time just to be sure we don't add a * callback when a fence has already been set. */ - if (syncobj->fence) { - *fence = dma_fence_get(rcu_dereference_protected(syncobj->fence, - lockdep_is_held(&syncobj->lock))); - ret = 1; + if (!list_empty(&syncobj->signal_pt_list)) { + spin_unlock(&syncobj->lock); + drm_syncobj_search_fence(syncobj, 0, 0, fence); + if (*fence) + return 1; + spin_lock(&syncobj->lock); } else { *fence = NULL; drm_syncobj_add_callback_locked(syncobj, cb, func); @@ -153,6 +163,160 @@ void drm_syncobj_remove_callback(struct drm_syncobj *syncobj, spin_unlock(&syncobj->lock); } +static void drm_syncobj_init(struct drm_syncobj *syncobj) +{ + spin_lock(&syncobj->lock); + syncobj->timeline_context = dma_fence_context_alloc(1); + syncobj->timeline = 0; + syncobj->signal_point = 0; + init_waitqueue_head(&syncobj->wq); + + INIT_LIST_HEAD(&syncobj->signal_pt_list); + spin_unlock(&syncobj->lock); +} + +static void drm_syncobj_fini(struct drm_syncobj *syncobj) +{ + struct drm_syncobj_signal_pt *signal_pt = NULL, *tmp; + + spin_lock(&syncobj->lock); + list_for_each_entry_safe(signal_pt, tmp, + &syncobj->signal_pt_list, list) { + list_del(&signal_pt->list); + dma_fence_put(&signal_pt->fence_array->base); + kfree(signal_pt); + } + spin_unlock(&syncobj->lock); +} + +static struct dma_fence +*drm_syncobj_find_signal_pt_for_point(struct drm_syncobj *syncobj, + uint64_t point) +{ + struct drm_syncobj_signal_pt *signal_pt; + + if ((syncobj->type == DRM_SYNCOBJ_TYPE_TIMELINE) && + (point <= syncobj->timeline)) { + struct drm_syncobj_stub_fence *fence = + kzalloc(sizeof(struct drm_syncobj_stub_fence), + GFP_KERNEL); + + if (!fence) + return NULL; + spin_lock_init(&fence->lock); + dma_fence_init(&fence->base, + &drm_syncobj_stub_fence_ops, + &fence->lock, + syncobj->timeline_context, + point); + + dma_fence_signal(&fence->base); + return &fence->base; + } + + list_for_each_entry(signal_pt, &syncobj->signal_pt_list, list) { + if (point > signal_pt->value) + continue; + if ((syncobj->type == DRM_SYNCOBJ_TYPE_BINARY) && + (point != signal_pt->value)) + continue; + return dma_fence_get(&signal_pt->fence_array->base); + } + return NULL; +} + +static int drm_syncobj_create_signal_pt(struct drm_syncobj *syncobj, + struct dma_fence *fence, + u64 point) +{ + struct drm_syncobj_signal_pt *signal_pt = + kzalloc(sizeof(struct drm_syncobj_signal_pt), GFP_KERNEL); + struct drm_syncobj_signal_pt *tail_pt; + struct dma_fence **fences; + int num_fences = 0; + int ret = 0, i; + + if (!signal_pt) + return -ENOMEM; + if (!fence) + goto out; + + fences = kmalloc_array(sizeof(void *), 2, GFP_KERNEL); + if (!fences) { + ret = -ENOMEM; + goto out; + } + fences[num_fences++] = dma_fence_get(fence); + /* timeline syncobj must take this dependency */ + if (syncobj->type == DRM_SYNCOBJ_TYPE_TIMELINE) { + spin_lock(&syncobj->lock); + if (!list_empty(&syncobj->signal_pt_list)) { + tail_pt = list_last_entry(&syncobj->signal_pt_list, + struct drm_syncobj_signal_pt, list); + fences[num_fences++] = + dma_fence_get(&tail_pt->fence_array->base); + } + spin_unlock(&syncobj->lock); + } + signal_pt->fence_array = dma_fence_array_create(num_fences, fences, + syncobj->timeline_context, + point, false); + if (!signal_pt->fence_array) { + ret = -ENOMEM; + goto fail; + } + + spin_lock(&syncobj->lock); + if (syncobj->signal_point >= point) { + DRM_WARN("A later signal is ready!"); + spin_unlock(&syncobj->lock); + goto exist; + } + signal_pt->value = point; + list_add_tail(&signal_pt->list, &syncobj->signal_pt_list); + syncobj->signal_point = point; + spin_unlock(&syncobj->lock); + wake_up_all(&syncobj->wq); + + return 0; +exist: + dma_fence_put(&signal_pt->fence_array->base); +fail: + for (i = 0; i < num_fences; i++) + dma_fence_put(fences[i]); + kfree(fences); +out: + kfree(signal_pt); + return ret; +} + +static void drm_syncobj_garbage_collection(struct drm_syncobj *syncobj) +{ + struct drm_syncobj_signal_pt *signal_pt, *tmp, *tail_pt; + + spin_lock(&syncobj->lock); + tail_pt = list_last_entry(&syncobj->signal_pt_list, + struct drm_syncobj_signal_pt, + list); + list_for_each_entry_safe(signal_pt, tmp, + &syncobj->signal_pt_list, list) { + if (syncobj->type == DRM_SYNCOBJ_TYPE_BINARY && + signal_pt == tail_pt) + continue; + if (dma_fence_is_signaled(&signal_pt->fence_array->base)) { + syncobj->timeline = signal_pt->value; + list_del(&signal_pt->list); + dma_fence_put(&signal_pt->fence_array->base); + kfree(signal_pt); + } else { + /*signal_pt is in order in list, from small to big, so + * the later must not be signal either */ + break; + } + } + + spin_unlock(&syncobj->lock); +} /** * drm_syncobj_replace_fence - replace fence in a sync object. * @syncobj: Sync object to replace fence in @@ -165,28 +329,29 @@ void drm_syncobj_replace_fence(struct drm_syncobj *syncobj, u64 point, struct dma_fence *fence) { - struct dma_fence *old_fence; - struct drm_syncobj_cb *cur, *tmp; - - if (fence) - dma_fence_get(fence); - - spin_lock(&syncobj->lock); - - old_fence = rcu_dereference_protected(syncobj->fence, - lockdep_is_held(&syncobj->lock)); - rcu_assign_pointer(syncobj->fence, fence); + u64 pt_value = point; + + drm_syncobj_garbage_collection(syncobj); + if (syncobj->type == DRM_SYNCOBJ_TYPE_BINARY) { + if (!fence) { + drm_syncobj_fini(syncobj); + drm_syncobj_init(syncobj); + return; + } + pt_value = syncobj->signal_point + + DRM_SYNCOBJ_BINARY_POINT; + } + drm_syncobj_create_signal_pt(syncobj, fence, pt_value); + if (fence) { + struct drm_syncobj_cb *cur, *tmp; - if (fence != old_fence) { + spin_lock(&syncobj->lock); list_for_each_entry_safe(cur, tmp, &syncobj->cb_list, node) { list_del_init(&cur->node); cur->func(syncobj, cur); } + spin_unlock(&syncobj->lock); } - - spin_unlock(&syncobj->lock); - - dma_fence_put(old_fence); } EXPORT_SYMBOL(drm_syncobj_replace_fence); @@ -209,6 +374,64 @@ static int drm_syncobj_assign_null_handle(struct drm_syncobj *syncobj) return 0; } +static int +drm_syncobj_point_get(struct drm_syncobj *syncobj, u64 point, u64 flags, + struct dma_fence **fence) +{ + int ret = 0; + + if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) { + ret = wait_event_interruptible(syncobj->wq, + point <= syncobj->signal_point); + if (ret < 0) + return ret; + } + spin_lock(&syncobj->lock); + *fence = drm_syncobj_find_signal_pt_for_point(syncobj, point); + if (!*fence) + ret = -EINVAL; + spin_unlock(&syncobj->lock); + return ret; +} + +/** + * drm_syncobj_search_fence - lookup and reference the fence in a sync object or + * in a timeline point + * @syncobj: sync object pointer + * @point: timeline point + * @flags: DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT or not + * @fence: out parameter for the fence + * + * if flags is DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT, the function will block + * here until specific timeline points is reached. + * if not, you need a submit thread and block in userspace until all future + * timeline points have materialized, only then you can submit to the kernel, + * otherwise, function will fail to return fence. + * + * Returns 0 on success or a negative error value on failure. On success @fence + * contains a reference to the fence, which must be released by calling + * dma_fence_put(). + */ +int drm_syncobj_search_fence(struct drm_syncobj *syncobj, u64 point, + u64 flags, struct dma_fence **fence) +{ + u64 pt_value = point; + + if (!syncobj) + return -ENOENT; + + drm_syncobj_garbage_collection(syncobj); + if (syncobj->type == DRM_SYNCOBJ_TYPE_BINARY) { + /*BINARY syncobj always wait on last pt */ + pt_value = syncobj->signal_point; + + if (pt_value == 0) + pt_value += DRM_SYNCOBJ_BINARY_POINT; + } + return drm_syncobj_point_get(syncobj, pt_value, flags, fence); +} +EXPORT_SYMBOL(drm_syncobj_search_fence); + /** * drm_syncobj_find_fence - lookup and reference the fence in a sync object * @file_private: drm file private pointer @@ -218,7 +441,7 @@ static int drm_syncobj_assign_null_handle(struct drm_syncobj *syncobj) * @fence: out parameter for the fence * * This is just a convenience function that combines drm_syncobj_find() and - * drm_syncobj_fence_get(). + * drm_syncobj_lookup_fence(). * * Returns 0 on success or a negative error value on failure. On success @fence * contains a reference to the fence, which must be released by calling @@ -229,15 +452,9 @@ int drm_syncobj_find_fence(struct drm_file *file_private, struct dma_fence **fence) { struct drm_syncobj *syncobj = drm_syncobj_find(file_private, handle); - int ret = 0; - - if (!syncobj) - return -ENOENT; + int ret; - *fence = drm_syncobj_fence_get(syncobj); - if (!*fence) { - ret = -EINVAL; - } + ret = drm_syncobj_search_fence(syncobj, point, flags, fence); drm_syncobj_put(syncobj); return ret; } @@ -254,7 +471,7 @@ void drm_syncobj_free(struct kref *kref) struct drm_syncobj *syncobj = container_of(kref, struct drm_syncobj, refcount); - drm_syncobj_replace_fence(syncobj, 0, NULL); + drm_syncobj_fini(syncobj); kfree(syncobj); } EXPORT_SYMBOL(drm_syncobj_free); @@ -284,6 +501,11 @@ int drm_syncobj_create(struct drm_syncobj **out_syncobj, uint32_t flags, kref_init(&syncobj->refcount); INIT_LIST_HEAD(&syncobj->cb_list); spin_lock_init(&syncobj->lock); + if (flags & DRM_SYNCOBJ_CREATE_TYPE_TIMELINE) + syncobj->type = DRM_SYNCOBJ_TYPE_TIMELINE; + else + syncobj->type = DRM_SYNCOBJ_TYPE_BINARY; + drm_syncobj_init(syncobj); if (flags & DRM_SYNCOBJ_CREATE_SIGNALED) { ret = drm_syncobj_assign_null_handle(syncobj); @@ -566,7 +788,8 @@ drm_syncobj_create_ioctl(struct drm_device *dev, void *data, return -EOPNOTSUPP; /* no valid flags yet */ - if (args->flags & ~DRM_SYNCOBJ_CREATE_SIGNALED) + if (args->flags & ~(DRM_SYNCOBJ_CREATE_SIGNALED | + DRM_SYNCOBJ_CREATE_TYPE_TIMELINE)) return -EINVAL; return drm_syncobj_create_as_handle(file_private, @@ -659,9 +882,8 @@ static void syncobj_wait_syncobj_func(struct drm_syncobj *syncobj, struct syncobj_wait_entry *wait = container_of(cb, struct syncobj_wait_entry, syncobj_cb); - /* This happens inside the syncobj lock */ - wait->fence = dma_fence_get(rcu_dereference_protected(syncobj->fence, - lockdep_is_held(&syncobj->lock))); + drm_syncobj_search_fence(syncobj, 0, 0, &wait->fence); + wake_up_process(wait->task); } @@ -687,7 +909,8 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, signaled_count = 0; for (i = 0; i < count; ++i) { entries[i].task = current; - entries[i].fence = drm_syncobj_fence_get(syncobjs[i]); + drm_syncobj_search_fence(syncobjs[i], 0, 0, + &entries[i].fence); if (!entries[i].fence) { if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) { continue; @@ -949,12 +1172,13 @@ drm_syncobj_reset_ioctl(struct drm_device *dev, void *data, if (ret < 0) return ret; - for (i = 0; i < args->count_handles; i++) - drm_syncobj_replace_fence(syncobjs[i], 0, NULL); - + for (i = 0; i < args->count_handles; i++) { + drm_syncobj_fini(syncobjs[i]); + drm_syncobj_init(syncobjs[i]); + } drm_syncobj_array_free(syncobjs, args->count_handles); - return 0; + return ret; } int diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 22b4cb775576..6d99651c6c4b 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -2152,7 +2152,7 @@ await_fence_array(struct i915_execbuffer *eb, if (!(flags & I915_EXEC_FENCE_WAIT)) continue; - fence = drm_syncobj_fence_get(syncobj); + drm_syncobj_search_fence(syncobj, 0, 0, &fence); if (!fence) return -EINVAL; diff --git a/include/drm/drm_syncobj.h b/include/drm/drm_syncobj.h index 2eda44def639..5e8c5c027e09 100644 --- a/include/drm/drm_syncobj.h +++ b/include/drm/drm_syncobj.h @@ -30,10 +30,15 @@ struct drm_syncobj_cb; +enum drm_syncobj_type { + DRM_SYNCOBJ_TYPE_BINARY, + DRM_SYNCOBJ_TYPE_TIMELINE +}; + /** * struct drm_syncobj - sync object. * - * This structure defines a generic sync object which wraps a &dma_fence. + * This structure defines a generic sync object which is timeline based. */ struct drm_syncobj { /** @@ -41,19 +46,36 @@ struct drm_syncobj { */ struct kref refcount; /** - * @fence: - * NULL or a pointer to the fence bound to this object. - * - * This field should not be used directly. Use drm_syncobj_fence_get() - * and drm_syncobj_replace_fence() instead. + * @type: indicate syncobj type + */ + enum drm_syncobj_type type; + /** + * @wq: wait signal operation work queue + */ + wait_queue_head_t wq; + /** + * @timeline_context: fence context used by timeline */ - struct dma_fence __rcu *fence; + u64 timeline_context; /** - * @cb_list: List of callbacks to call when the &fence gets replaced. + * @timeline: syncobj timeline value, which indicates point is signaled. */ + u64 timeline; + /** + * @signal_point: which indicates the latest signaler point. + */ + u64 signal_point; + /** + * @signal_pt_list: signaler point list. + */ + struct list_head signal_pt_list; + + /** + * @cb_list: List of callbacks to call when the &fence gets replaced. + */ struct list_head cb_list; /** - * @lock: Protects &cb_list and write-locks &fence. + * @lock: Protects syncobj list and write-locks &fence. */ spinlock_t lock; /** @@ -68,7 +90,7 @@ typedef void (*drm_syncobj_func_t)(struct drm_syncobj *syncobj, /** * struct drm_syncobj_cb - callback for drm_syncobj_add_callback * @node: used by drm_syncob_add_callback to append this struct to - * &drm_syncobj.cb_list + * &drm_syncobj.cb_list * @func: drm_syncobj_func_t to call * * This struct will be initialized by drm_syncobj_add_callback, additional @@ -106,29 +128,6 @@ drm_syncobj_put(struct drm_syncobj *obj) kref_put(&obj->refcount, drm_syncobj_free); } -/** - * drm_syncobj_fence_get - get a reference to a fence in a sync object - * @syncobj: sync object. - * - * This acquires additional reference to &drm_syncobj.fence contained in @obj, - * if not NULL. It is illegal to call this without already holding a reference. - * No locks required. - * - * Returns: - * Either the fence of @obj or NULL if there's none. - */ -static inline struct dma_fence * -drm_syncobj_fence_get(struct drm_syncobj *syncobj) -{ - struct dma_fence *fence; - - rcu_read_lock(); - fence = dma_fence_get_rcu_safe(&syncobj->fence); - rcu_read_unlock(); - - return fence; -} - struct drm_syncobj *drm_syncobj_find(struct drm_file *file_private, u32 handle); void drm_syncobj_replace_fence(struct drm_syncobj *syncobj, u64 point, @@ -142,5 +141,7 @@ int drm_syncobj_create(struct drm_syncobj **out_syncobj, uint32_t flags, int drm_syncobj_get_handle(struct drm_file *file_private, struct drm_syncobj *syncobj, u32 *handle); int drm_syncobj_get_fd(struct drm_syncobj *syncobj, int *p_fd); +int drm_syncobj_search_fence(struct drm_syncobj *syncobj, u64 point, u64 flags, + struct dma_fence **fence); #endif diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h index 300f336633f2..cebdb2541eb7 100644 --- a/include/uapi/drm/drm.h +++ b/include/uapi/drm/drm.h @@ -717,6 +717,7 @@ struct drm_prime_handle { struct drm_syncobj_create { __u32 handle; #define DRM_SYNCOBJ_CREATE_SIGNALED (1 << 0) +#define DRM_SYNCOBJ_CREATE_TYPE_TIMELINE (1 << 1) __u32 flags; }; -- cgit v1.2.3 From 697b6b85042ef0fb9838e3100700eed727c211e9 Mon Sep 17 00:00:00 2001 From: Alexandru Gheorghe Date: Thu, 1 Nov 2018 15:11:30 +0000 Subject: drm/fourcc: Add fourcc for Mali linear tiled formats Mali-DP implements a number of tiled yuv formats which are not currently described in drm_fourcc.h. This adds those definitions and describes their memory layout by using the newly added char_per_block, block_w, block_h. Reviewed-by: Brian Starkey Reviewed-by: Daniel Vetter Signed-off-by: Alexandru Gheorghe Link: https://patchwork.freedesktop.org/patch/msgid/20181101151051.1509-3-alexandru-cosmin.gheorghe@arm.com --- drivers/gpu/drm/drm_fourcc.c | 12 ++++++++++++ include/uapi/drm/drm_fourcc.h | 14 ++++++++++++++ 2 files changed, 26 insertions(+) (limited to 'include/uapi/drm') diff --git a/drivers/gpu/drm/drm_fourcc.c b/drivers/gpu/drm/drm_fourcc.c index 8c4a79b3a4ad..f523948c82b1 100644 --- a/drivers/gpu/drm/drm_fourcc.c +++ b/drivers/gpu/drm/drm_fourcc.c @@ -225,6 +225,18 @@ const struct drm_format_info *__drm_format_info(u32 format) { .format = DRM_FORMAT_UYVY, .depth = 0, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true }, { .format = DRM_FORMAT_VYUY, .depth = 0, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true }, { .format = DRM_FORMAT_AYUV, .depth = 0, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true, .is_yuv = true }, + { .format = DRM_FORMAT_Y0L0, .depth = 0, .num_planes = 1, + .char_per_block = { 8, 0, 0 }, .block_w = { 2, 0, 0 }, .block_h = { 2, 0, 0 }, + .hsub = 2, .vsub = 2, .has_alpha = true, .is_yuv = true }, + { .format = DRM_FORMAT_X0L0, .depth = 0, .num_planes = 1, + .char_per_block = { 8, 0, 0 }, .block_w = { 2, 0, 0 }, .block_h = { 2, 0, 0 }, + .hsub = 2, .vsub = 2, .is_yuv = true }, + { .format = DRM_FORMAT_Y0L2, .depth = 0, .num_planes = 1, + .char_per_block = { 8, 0, 0 }, .block_w = { 2, 0, 0 }, .block_h = { 2, 0, 0 }, + .hsub = 2, .vsub = 2, .has_alpha = true, .is_yuv = true }, + { .format = DRM_FORMAT_X0L2, .depth = 0, .num_planes = 1, + .char_per_block = { 8, 0, 0 }, .block_w = { 2, 0, 0 }, .block_h = { 2, 0, 0 }, + .hsub = 2, .vsub = 2, .is_yuv = true }, }; unsigned int i; diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index 0cd40ebfa1b1..e7e48f1f4a74 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -152,6 +152,20 @@ extern "C" { #define DRM_FORMAT_AYUV fourcc_code('A', 'Y', 'U', 'V') /* [31:0] A:Y:Cb:Cr 8:8:8:8 little endian */ +/* + * packed YCbCr420 2x2 tiled formats + * first 64 bits will contain Y,Cb,Cr components for a 2x2 tile + */ +/* [63:0] A3:A2:Y3:0:Cr0:0:Y2:0:A1:A0:Y1:0:Cb0:0:Y0:0 1:1:8:2:8:2:8:2:1:1:8:2:8:2:8:2 little endian */ +#define DRM_FORMAT_Y0L0 fourcc_code('Y', '0', 'L', '0') +/* [63:0] X3:X2:Y3:0:Cr0:0:Y2:0:X1:X0:Y1:0:Cb0:0:Y0:0 1:1:8:2:8:2:8:2:1:1:8:2:8:2:8:2 little endian */ +#define DRM_FORMAT_X0L0 fourcc_code('X', '0', 'L', '0') + +/* [63:0] A3:A2:Y3:Cr0:Y2:A1:A0:Y1:Cb0:Y0 1:1:10:10:10:1:1:10:10:10 little endian */ +#define DRM_FORMAT_Y0L2 fourcc_code('Y', '0', 'L', '2') +/* [63:0] X3:X2:Y3:Cr0:Y2:X1:X0:Y1:Cb0:Y0 1:1:10:10:10:1:1:10:10:10 little endian */ +#define DRM_FORMAT_X0L2 fourcc_code('X', '0', 'L', '2') + /* * 2 plane RGB + A * index 0 = RGB plane, same format as the corresponding non _A8 format has -- cgit v1.2.3 From ce331f8f7c04186b7b130550250d9c4e752b4f8f Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Tue, 23 Oct 2018 10:04:54 -0400 Subject: drm/amdgpu: Add DCC flags for GFX9 amdgpu_bo MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [Why] Hardware support for Delta Color Compression (DCC) decompression is available in DC for GFX9 but there's no way for userspace to enable the feature. Enabling the feature can provide improved GFX performance and power savings in many situations. [How] Extend the GFX9 tiling flags to include DCC parameters. These are logically grouped together with tiling flags even if they are technically distinct. This trivially maintains backwards compatibility with existing users of amdgpu_gem_metadata. No new IOCTls or data structures are needed to support DCC. This patch helps expose DCC attributes to both libdrm and amdgpu_dm. Signed-off-by: Nicholas Kazlauskas Reviewed-by: Marek Olšák Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi/drm') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 370e9a5536ef..be84e43c1e19 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -326,6 +326,12 @@ struct drm_amdgpu_gem_userptr { /* GFX9 and later: */ #define AMDGPU_TILING_SWIZZLE_MODE_SHIFT 0 #define AMDGPU_TILING_SWIZZLE_MODE_MASK 0x1f +#define AMDGPU_TILING_DCC_OFFSET_256B_SHIFT 5 +#define AMDGPU_TILING_DCC_OFFSET_256B_MASK 0xFFFFFF +#define AMDGPU_TILING_DCC_PITCH_MAX_SHIFT 29 +#define AMDGPU_TILING_DCC_PITCH_MAX_MASK 0x3FFF +#define AMDGPU_TILING_DCC_INDEPENDENT_64B_SHIFT 43 +#define AMDGPU_TILING_DCC_INDEPENDENT_64B_MASK 0x1 /* Set/Get helpers for tiling flags. */ #define AMDGPU_TILING_SET(field, value) \ -- cgit v1.2.3