[PATCH 1/9] drm: fix syncobj null_fence_enable_signaling

[PATCH 1/9] drm: fix syncobj null_fence_enable_signaling

[Chunming Zhou]

That is certainly totally nonsense. dma_fence_enable_sw_signaling()
is the function who is calling this callback.

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Cc: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Christian König <christian.koenig@amd.com>
Acked-by: Daniel Vetter <daniel@ffwll.ch>
---
 drivers/gpu/drm/drm_syncobj.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index 3a8837c49639..d17ed75ac7e2 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -184,7 +184,6 @@ static const char *drm_syncobj_null_fence_get_name(struct dma_fence *fence)
 
 static bool drm_syncobj_null_fence_enable_signaling(struct dma_fence *fence)
 {
-    dma_fence_enable_sw_signaling(fence);
     return !dma_fence_is_signaled(fence);
 }
 
-- 
2.17.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH 2/9] drm: rename null fence to stub fence in syncobj v2

[Chunming Zhou]

moved to front of file.
stub fence will be used by timeline syncobj as well.

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Cc: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/drm_syncobj.c | 53 +++++++++++++++++++----------------
 1 file changed, 29 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index d17ed75ac7e2..abbb22c97f7a 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -56,6 +56,33 @@
 #include "drm_internal.h"
 #include <drm/drm_syncobj.h>
 
+struct drm_syncobj_stub_fence {
+	struct dma_fence base;
+	spinlock_t lock;
+};
+
+static const char *drm_syncobj_stub_fence_get_name(struct dma_fence *fence)
+{
+        return "syncobjstub";
+}
+
+static bool drm_syncobj_stub_fence_enable_signaling(struct dma_fence *fence)
+{
+    return !dma_fence_is_signaled(fence);
+}
+
+static void drm_syncobj_stub_fence_release(struct dma_fence *f)
+{
+	kfree(f);
+}
+static const struct dma_fence_ops drm_syncobj_stub_fence_ops = {
+	.get_driver_name = drm_syncobj_stub_fence_get_name,
+	.get_timeline_name = drm_syncobj_stub_fence_get_name,
+	.enable_signaling = drm_syncobj_stub_fence_enable_signaling,
+	.release = drm_syncobj_stub_fence_release,
+};
+
+
 /**
  * drm_syncobj_find - lookup and reference a sync object.
  * @file_private: drm file private pointer
@@ -172,37 +199,15 @@ void drm_syncobj_replace_fence(struct drm_syncobj *syncobj,
 }
 EXPORT_SYMBOL(drm_syncobj_replace_fence);
 
-struct drm_syncobj_null_fence {
-	struct dma_fence base;
-	spinlock_t lock;
-};
-
-static const char *drm_syncobj_null_fence_get_name(struct dma_fence *fence)
-{
-        return "syncobjnull";
-}
-
-static bool drm_syncobj_null_fence_enable_signaling(struct dma_fence *fence)
-{
-    return !dma_fence_is_signaled(fence);
-}
-
-static const struct dma_fence_ops drm_syncobj_null_fence_ops = {
-	.get_driver_name = drm_syncobj_null_fence_get_name,
-	.get_timeline_name = drm_syncobj_null_fence_get_name,
-	.enable_signaling = drm_syncobj_null_fence_enable_signaling,
-	.release = NULL,
-};
-
 static int drm_syncobj_assign_null_handle(struct drm_syncobj *syncobj)
 {
-	struct drm_syncobj_null_fence *fence;
+	struct drm_syncobj_stub_fence *fence;
 	fence = kzalloc(sizeof(*fence), GFP_KERNEL);
 	if (fence == NULL)
 		return -ENOMEM;
 
 	spin_lock_init(&fence->lock);
-	dma_fence_init(&fence->base, &drm_syncobj_null_fence_ops,
+	dma_fence_init(&fence->base, &drm_syncobj_stub_fence_ops,
 		       &fence->lock, 0, 0);
 	dma_fence_signal(&fence->base);
 
-- 
2.17.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 3/9] drm: expand drm_syncobj_find_fence to support timeline point v2

[Chunming Zhou]

we can fetch timeline point fence after expanded.
v2: The parameter fence is the result of the function and should come last.

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 2 +-
 drivers/gpu/drm/drm_syncobj.c          | 5 +++--
 drivers/gpu/drm/v3d/v3d_gem.c          | 4 ++--
 drivers/gpu/drm/vc4/vc4_gem.c          | 2 +-
 include/drm/drm_syncobj.h              | 2 +-
 5 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 502b94fb116a..5db7b1b460da 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1102,7 +1102,7 @@ static int amdgpu_syncobj_lookup_and_add_to_sync(struct amdgpu_cs_parser *p,
 {
 	int r;
 	struct dma_fence *fence;
-	r = drm_syncobj_find_fence(p->filp, handle, &fence);
+	r = drm_syncobj_find_fence(p->filp, handle, 0, &fence);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index abbb22c97f7a..e04b0f336af0 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -222,6 +222,7 @@ static int drm_syncobj_assign_null_handle(struct drm_syncobj *syncobj)
  * drm_syncobj_find_fence - lookup and reference the fence in a sync object
  * @file_private: drm file private pointer
  * @handle: sync object handle to lookup.
+ * @point: timeline point
  * @fence: out parameter for the fence
  *
  * This is just a convenience function that combines drm_syncobj_find() and
@@ -232,7 +233,7 @@ static int drm_syncobj_assign_null_handle(struct drm_syncobj *syncobj)
  * dma_fence_put().
  */
 int drm_syncobj_find_fence(struct drm_file *file_private,
-			   u32 handle,
+			   u32 handle, u64 point,
 			   struct dma_fence **fence)
 {
 	struct drm_syncobj *syncobj = drm_syncobj_find(file_private, handle);
@@ -503,7 +504,7 @@ static int drm_syncobj_export_sync_file(struct drm_file *file_private,
 	if (fd < 0)
 		return fd;
 
-	ret = drm_syncobj_find_fence(file_private, handle, &fence);
+	ret = drm_syncobj_find_fence(file_private, handle, 0, &fence);
 	if (ret)
 		goto err_put_fd;
 
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index 5ce24098a5fd..9b9ab34fb461 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -521,12 +521,12 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 	kref_init(&exec->refcount);
 
 	ret = drm_syncobj_find_fence(file_priv, args->in_sync_bcl,
-				     &exec->bin.in_fence);
+				     0, &exec->bin.in_fence);
 	if (ret == -EINVAL)
 		goto fail;
 
 	ret = drm_syncobj_find_fence(file_priv, args->in_sync_rcl,
-				     &exec->render.in_fence);
+				     0, &exec->render.in_fence);
 	if (ret == -EINVAL)
 		goto fail;
 
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index 7910b9acedd6..928718b467bd 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -1173,7 +1173,7 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 
 	if (args->in_sync) {
 		ret = drm_syncobj_find_fence(file_priv, args->in_sync,
-					     &in_fence);
+					     0, &in_fence);
 		if (ret)
 			goto fail;
 
diff --git a/include/drm/drm_syncobj.h b/include/drm/drm_syncobj.h
index e419c79ba94d..ab9055f943c7 100644
--- a/include/drm/drm_syncobj.h
+++ b/include/drm/drm_syncobj.h
@@ -134,7 +134,7 @@ struct drm_syncobj *drm_syncobj_find(struct drm_file *file_private,
 void drm_syncobj_replace_fence(struct drm_syncobj *syncobj,
 			       struct dma_fence *fence);
 int drm_syncobj_find_fence(struct drm_file *file_private,
-			   u32 handle,
+			   u32 handle, u64 point,
 			   struct dma_fence **fence);
 void drm_syncobj_free(struct kref *kref);
 int drm_syncobj_create(struct drm_syncobj **out_syncobj, uint32_t flags,
-- 
2.17.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 4/9] drm: expand replace_fence to support timeline point v2

[Chunming Zhou]

we can place a fence to a timeline point after expanded.
v2: change func parameter order

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c     |  2 +-
 drivers/gpu/drm/drm_syncobj.c              | 14 ++++++++------
 drivers/gpu/drm/i915/i915_gem_execbuffer.c |  2 +-
 drivers/gpu/drm/v3d/v3d_gem.c              |  2 +-
 drivers/gpu/drm/vc4/vc4_gem.c              |  2 +-
 include/drm/drm_syncobj.h                  |  2 +-
 6 files changed, 13 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 5db7b1b460da..d68b73ff92d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1191,7 +1191,7 @@ static void amdgpu_cs_post_dependencies(struct amdgpu_cs_parser *p)
 	int i;
 
 	for (i = 0; i < p->num_post_dep_syncobjs; ++i)
-		drm_syncobj_replace_fence(p->post_dep_syncobjs[i], p->fence);
+		drm_syncobj_replace_fence(p->post_dep_syncobjs[i], 0, p->fence);
 }
 
 static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index e04b0f336af0..e9ce623d049e 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -167,11 +167,13 @@ void drm_syncobj_remove_callback(struct drm_syncobj *syncobj,
 /**
  * drm_syncobj_replace_fence - replace fence in a sync object.
  * @syncobj: Sync object to replace fence in
+ * @point: timeline point
  * @fence: fence to install in sync file.
  *
- * This replaces the fence on a sync object.
+ * This replaces the fence on a sync object, or a timeline point fence.
  */
 void drm_syncobj_replace_fence(struct drm_syncobj *syncobj,
+			       u64 point,
 			       struct dma_fence *fence)
 {
 	struct dma_fence *old_fence;
@@ -211,7 +213,7 @@ static int drm_syncobj_assign_null_handle(struct drm_syncobj *syncobj)
 		       &fence->lock, 0, 0);
 	dma_fence_signal(&fence->base);
 
-	drm_syncobj_replace_fence(syncobj, &fence->base);
+	drm_syncobj_replace_fence(syncobj, 0, &fence->base);
 
 	dma_fence_put(&fence->base);
 
@@ -262,7 +264,7 @@ void drm_syncobj_free(struct kref *kref)
 	struct drm_syncobj *syncobj = container_of(kref,
 						   struct drm_syncobj,
 						   refcount);
-	drm_syncobj_replace_fence(syncobj, NULL);
+	drm_syncobj_replace_fence(syncobj, 0, NULL);
 	kfree(syncobj);
 }
 EXPORT_SYMBOL(drm_syncobj_free);
@@ -302,7 +304,7 @@ int drm_syncobj_create(struct drm_syncobj **out_syncobj, uint32_t flags,
 	}
 
 	if (fence)
-		drm_syncobj_replace_fence(syncobj, fence);
+		drm_syncobj_replace_fence(syncobj, 0, fence);
 
 	*out_syncobj = syncobj;
 	return 0;
@@ -487,7 +489,7 @@ static int drm_syncobj_import_sync_file_fence(struct drm_file *file_private,
 		return -ENOENT;
 	}
 
-	drm_syncobj_replace_fence(syncobj, fence);
+	drm_syncobj_replace_fence(syncobj, 0, fence);
 	dma_fence_put(fence);
 	drm_syncobj_put(syncobj);
 	return 0;
@@ -969,7 +971,7 @@ drm_syncobj_reset_ioctl(struct drm_device *dev, void *data,
 		return ret;
 
 	for (i = 0; i < args->count_handles; i++)
-		drm_syncobj_replace_fence(syncobjs[i], NULL);
+		drm_syncobj_replace_fence(syncobjs[i], 0, NULL);
 
 	drm_syncobj_array_free(syncobjs, args->count_handles);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 3f0c612d42e7..0a8d2d64f380 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -2166,7 +2166,7 @@ signal_fence_array(struct i915_execbuffer *eb,
 		if (!(flags & I915_EXEC_FENCE_SIGNAL))
 			continue;
 
-		drm_syncobj_replace_fence(syncobj, fence);
+		drm_syncobj_replace_fence(syncobj, 0, fence);
 	}
 }
 
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index 9b9ab34fb461..70c54774400b 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -584,7 +584,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 	/* Update the return sync object for the */
 	sync_out = drm_syncobj_find(file_priv, args->out_sync);
 	if (sync_out) {
-		drm_syncobj_replace_fence(sync_out,
+		drm_syncobj_replace_fence(sync_out, 0,
 					  &exec->render.base.s_fence->finished);
 		drm_syncobj_put(sync_out);
 	}
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index 928718b467bd..5b22e996af6c 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -681,7 +681,7 @@ vc4_queue_submit(struct drm_device *dev, struct vc4_exec_info *exec,
 	exec->fence = &fence->base;
 
 	if (out_sync)
-		drm_syncobj_replace_fence(out_sync, exec->fence);
+		drm_syncobj_replace_fence(out_sync, 0, exec->fence);
 
 	vc4_update_bo_seqnos(exec, seqno);
 
diff --git a/include/drm/drm_syncobj.h b/include/drm/drm_syncobj.h
index ab9055f943c7..425432b85a87 100644
--- a/include/drm/drm_syncobj.h
+++ b/include/drm/drm_syncobj.h
@@ -131,7 +131,7 @@ drm_syncobj_fence_get(struct drm_syncobj *syncobj)
 
 struct drm_syncobj *drm_syncobj_find(struct drm_file *file_private,
 				     u32 handle);
-void drm_syncobj_replace_fence(struct drm_syncobj *syncobj,
+void drm_syncobj_replace_fence(struct drm_syncobj *syncobj, u64 point,
 			       struct dma_fence *fence);
 int drm_syncobj_find_fence(struct drm_file *file_private,
 			   u32 handle, u64 point,
-- 
2.17.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 5/9] [RFC]drm: add syncobj timeline support v4

[Chunming Zhou]

VK_KHR_timeline_semaphore:
This extension introduces a new type of semaphore that has an integer payload
identifying a point in a timeline. Such timeline semaphores support the
following operations:
   * CPU query - A host operation that allows querying the payload of the
     timeline semaphore.
   * CPU wait - A host operation that allows a blocking wait for a
     timeline semaphore to reach a specified value.
   * Device wait - A device operation that allows waiting for a
     timeline semaphore to reach a specified value.
   * Device signal - A device operation that allows advancing the
     timeline semaphore to a specified value.

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. semaphore 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

normal syncobj is tested by ./deqp-vk -n dEQP-VK*semaphore*
timeline syncobj is tested by ./amdgpu_test -s 9

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Cc: Christian Konig <christian.koenig@amd.com>
Cc: Dave Airlie <airlied@redhat.com>
Cc: Daniel Rakos <Daniel.Rakos@amd.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
---
 drivers/gpu/drm/drm_syncobj.c              | 494 ++++++++++++++++-----
 drivers/gpu/drm/i915/i915_gem_execbuffer.c |   4 +-
 include/drm/drm_syncobj.h                  |  78 ++--
 include/uapi/drm/drm.h                     |   1 +
 4 files changed, 425 insertions(+), 152 deletions(-)

diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index e9ce623d049e..502cdf313aea 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -56,6 +56,9 @@
 #include "drm_internal.h"
 #include <drm/drm_syncobj.h>
 
+/* merge normal syncobj to timeline syncobj, the point interval is 1 */
+#define DRM_SYNCOBJ_NORMAL_POINT 1
+
 struct drm_syncobj_stub_fence {
 	struct dma_fence base;
 	spinlock_t lock;
@@ -82,6 +85,18 @@ static const struct dma_fence_ops drm_syncobj_stub_fence_ops = {
 	.release = drm_syncobj_stub_fence_release,
 };
 
+struct drm_syncobj_signal_pt {
+	struct dma_fence_array *base;
+	u64    value;
+	struct list_head list;
+};
+struct drm_syncobj_wait_pt {
+	struct drm_syncobj_stub_fence base;
+	struct dma_fence *signal_pt_fence;
+	struct dma_fence_cb wait_cb;
+	struct rb_node   node;
+	u64    value;
+};
 
 /**
  * drm_syncobj_find - lookup and reference a sync object.
@@ -109,61 +124,213 @@ struct drm_syncobj *drm_syncobj_find(struct drm_file *file_private,
 }
 EXPORT_SYMBOL(drm_syncobj_find);
 
-static void drm_syncobj_add_callback_locked(struct drm_syncobj *syncobj,
-					    struct drm_syncobj_cb *cb,
-					    drm_syncobj_func_t func)
+static void drm_syncobj_timeline_init(struct drm_syncobj *syncobj,
+				      struct drm_syncobj_timeline *syncobj_timeline)
 {
-	cb->func = func;
-	list_add_tail(&cb->node, &syncobj->cb_list);
+	spin_lock(&syncobj->lock);
+	syncobj_timeline->timeline_context = dma_fence_context_alloc(1);
+	syncobj_timeline->timeline = 0;
+	syncobj_timeline->signal_point = 0;
+	init_waitqueue_head(&syncobj_timeline->wq);
+
+	syncobj_timeline->wait_pt_tree = RB_ROOT;
+	INIT_LIST_HEAD(&syncobj_timeline->signal_pt_list);
+	spin_unlock(&syncobj->lock);
 }
 
-static int drm_syncobj_fence_get_or_add_callback(struct drm_syncobj *syncobj,
-						 struct dma_fence **fence,
-						 struct drm_syncobj_cb *cb,
-						 drm_syncobj_func_t func)
+static void drm_syncobj_timeline_fini(struct drm_syncobj *syncobj,
+				      struct drm_syncobj_timeline *syncobj_timeline)
 {
-	int ret;
-
-	*fence = drm_syncobj_fence_get(syncobj);
-	if (*fence)
-		return 1;
+	struct rb_node *node = NULL;
+	struct drm_syncobj_wait_pt *wait_pt = NULL;
+	struct drm_syncobj_signal_pt *signal_pt = NULL, *tmp;
 
 	spin_lock(&syncobj->lock);
-	/* We've already tried once to get a fence and failed.  Now that we
-	 * 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;
-	} else {
-		*fence = NULL;
-		drm_syncobj_add_callback_locked(syncobj, cb, func);
-		ret = 0;
+	if (!RB_EMPTY_ROOT(&syncobj_timeline->wait_pt_tree))
+		DRM_ERROR("There still are advanced wait_pts! pls check!");
+	while ((node = rb_first(&syncobj_timeline->wait_pt_tree))) {
+		wait_pt = rb_entry(node, struct drm_syncobj_wait_pt, node);
+		rb_erase(&wait_pt->node,
+			 &syncobj_timeline->wait_pt_tree);
+		RB_CLEAR_NODE(&wait_pt->node);
+		if (!wait_pt->signal_pt_fence) {
+			/* if wait_pt still is advanced, fake signal it.
+			 * generally shouldn't happens */
+			dma_fence_set_error(&wait_pt->base.base, -ENOENT);
+			dma_fence_signal(&wait_pt->base.base);
+		}
+		/* kfree(wait_pt) is excuted by fence put */
+		dma_fence_put(&wait_pt->base.base);
+	}
+	list_for_each_entry_safe(signal_pt, tmp,
+				 &syncobj_timeline->signal_pt_list, list) {
+		list_del(&signal_pt->list);
+		dma_fence_put(&signal_pt->base->base);
+		kfree(signal_pt);
 	}
 	spin_unlock(&syncobj->lock);
+}
 
-	return ret;
+static void wait_pt_func(struct dma_fence *fence, struct dma_fence_cb *cb)
+{
+	struct drm_syncobj_wait_pt *wait_pt =
+		container_of(cb, struct drm_syncobj_wait_pt, wait_cb);
+
+	dma_fence_signal(&wait_pt->base.base);
+	dma_fence_put(wait_pt->signal_pt_fence);
+	wait_pt->signal_pt_fence = NULL;
+	dma_fence_put(&wait_pt->base.base);
+}
+
+static void drm_syncobj_find_signal_pt_for_wait_pt(struct drm_syncobj *syncobj,
+						   struct drm_syncobj_wait_pt *wait_pt)
+{
+	struct drm_syncobj_timeline *timeline = &syncobj->syncobj_timeline;
+	struct drm_syncobj_signal_pt *signal_pt;
+	int ret;
+
+	if (wait_pt->signal_pt_fence) {
+		return;
+	} else if ((syncobj->type == DRM_SYNCOBJ_TYPE_TIMELINE) &&
+		   (wait_pt->value <= timeline->timeline)) {
+		dma_fence_signal(&wait_pt->base.base);
+		rb_erase(&wait_pt->node,
+			 &timeline->wait_pt_tree);
+		RB_CLEAR_NODE(&wait_pt->node);
+		dma_fence_put(&wait_pt->base.base);
+		return;
+	}
+
+	list_for_each_entry(signal_pt, &timeline->signal_pt_list, list) {
+		if (wait_pt->value > signal_pt->value)
+			continue;
+		if ((syncobj->type == DRM_SYNCOBJ_TYPE_NORMAL) &&
+		    (wait_pt->value != signal_pt->value))
+			continue;
+		wait_pt->signal_pt_fence = dma_fence_get(&signal_pt->base->base);
+		ret = dma_fence_add_callback(wait_pt->signal_pt_fence,
+					     &wait_pt->wait_cb,
+					     wait_pt_func);
+		if (ret == -ENOENT) {
+			dma_fence_signal(&wait_pt->base.base);
+			dma_fence_put(wait_pt->signal_pt_fence);
+			wait_pt->signal_pt_fence = NULL;
+			rb_erase(&wait_pt->node,
+				 &timeline->wait_pt_tree);
+			RB_CLEAR_NODE(&wait_pt->node);
+			dma_fence_put(&wait_pt->base.base);
+		} else if (ret < 0) {
+			dma_fence_put(wait_pt->signal_pt_fence);
+			DRM_ERROR("add callback error!");
+		} else {
+			/* after adding callback, remove from rb tree */
+			rb_erase(&wait_pt->node,
+				 &timeline->wait_pt_tree);
+			RB_CLEAR_NODE(&wait_pt->node);
+		}
+		return;
+	}
 }
 
-void drm_syncobj_add_callback(struct drm_syncobj *syncobj,
-			      struct drm_syncobj_cb *cb,
-			      drm_syncobj_func_t func)
+static int drm_syncobj_timeline_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;
+	struct rb_node *node;
+	struct drm_syncobj_wait_pt *tail_wait_pt = NULL;
+	int num_fences = 0;
+	int ret = 0, i;
+
+	if (!signal_pt)
+		return -ENOMEM;
+	if (syncobj->syncobj_timeline.signal_point >= point) {
+		DRM_WARN("A later signal is ready!");
+		goto out;
+	}
+	if (!fence)
+		goto out;
+
+	fences = kmalloc_array(sizeof(void *), 2, GFP_KERNEL);
+	if (!fences)
+		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->syncobj_timeline.signal_pt_list)) {
+			tail_pt = list_last_entry(&syncobj->syncobj_timeline.signal_pt_list,
+						  struct drm_syncobj_signal_pt, list);
+			fences[num_fences++] = dma_fence_get(&tail_pt->base->base);
+		}
+		spin_unlock(&syncobj->lock);
+	}
+	signal_pt->base = dma_fence_array_create(num_fences, fences,
+						 syncobj->syncobj_timeline.timeline_context,
+						 point, false);
+	if (!signal_pt->base)
+		goto fail;
+
 	spin_lock(&syncobj->lock);
-	drm_syncobj_add_callback_locked(syncobj, cb, func);
+	signal_pt->value = point;
+	INIT_LIST_HEAD(&signal_pt->list);
+	list_add_tail(&signal_pt->list, &syncobj->syncobj_timeline.signal_pt_list);
+	syncobj->syncobj_timeline.signal_point = point;
+
+	/* check if there is advanced wait */
+	node = rb_last(&syncobj->syncobj_timeline.wait_pt_tree);
+	if (node)
+		tail_wait_pt = rb_entry(node, struct drm_syncobj_wait_pt, node);
+	if (tail_wait_pt && !tail_wait_pt->signal_pt_fence) {
+		for (node = rb_first(&syncobj->syncobj_timeline.wait_pt_tree);
+		     node != NULL; node = rb_next(node)) {
+			struct drm_syncobj_wait_pt *wait_pt =
+				rb_entry(node, struct drm_syncobj_wait_pt,
+					 node);
+
+			drm_syncobj_find_signal_pt_for_wait_pt(syncobj,
+							       wait_pt);
+		}
+	}
+
 	spin_unlock(&syncobj->lock);
+	wake_up_all(&syncobj->syncobj_timeline.wq);
+
+	return 0;
+fail:
+	for (i = 0; i < num_fences; i++)
+		dma_fence_put(fences[i]);
+	kfree(fences);
+out:
+	kfree(signal_pt);
+	return ret;
 }
 
-void drm_syncobj_remove_callback(struct drm_syncobj *syncobj,
-				 struct drm_syncobj_cb *cb)
+static void drm_syncobj_timeline_garbage_collection(struct drm_syncobj *syncobj)
 {
+	struct drm_syncobj_timeline *timeline = &syncobj->syncobj_timeline;
+	struct drm_syncobj_signal_pt *signal_pt, *tmp;
+
 	spin_lock(&syncobj->lock);
-	list_del_init(&cb->node);
+	list_for_each_entry_safe(signal_pt, tmp,
+				 &timeline->signal_pt_list, list) {
+		if (dma_fence_is_signaled(&signal_pt->base->base)) {
+			timeline->timeline = signal_pt->value;
+			list_del(&signal_pt->list);
+			dma_fence_put(&signal_pt->base->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
@@ -176,28 +343,29 @@ 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);
-
-	if (fence != old_fence) {
-		list_for_each_entry_safe(cur, tmp, &syncobj->cb_list, node) {
-			list_del_init(&cur->node);
-			cur->func(syncobj, cur);
+	drm_syncobj_timeline_garbage_collection(syncobj);
+	if (syncobj->type == DRM_SYNCOBJ_TYPE_TIMELINE) {
+		if (fence)
+			drm_syncobj_timeline_create_signal_pt(syncobj, fence,
+							      point);
+		return;
+	} else if (syncobj->type == DRM_SYNCOBJ_TYPE_NORMAL) {
+		u64 pt_value;
+
+		if (!fence) {
+			drm_syncobj_timeline_fini(syncobj,
+						  &syncobj->syncobj_timeline);
+			drm_syncobj_timeline_init(syncobj,
+						  &syncobj->syncobj_timeline);
+			return;
 		}
+		pt_value = syncobj->syncobj_timeline.signal_point +
+			DRM_SYNCOBJ_NORMAL_POINT;
+		drm_syncobj_timeline_create_signal_pt(syncobj, fence, pt_value);
+		return;
+	} else {
+		DRM_ERROR("the syncobj type isn't support\n");
 	}
-
-	spin_unlock(&syncobj->lock);
-
-	dma_fence_put(old_fence);
 }
 EXPORT_SYMBOL(drm_syncobj_replace_fence);
 
@@ -220,6 +388,120 @@ static int drm_syncobj_assign_null_handle(struct drm_syncobj *syncobj)
 	return 0;
 }
 
+static struct drm_syncobj_wait_pt *
+drm_syncobj_timeline_lookup_wait_pt_fence(struct drm_syncobj *syncobj,
+					  u64 point,
+					  struct dma_fence **fence)
+{
+	struct rb_node *node = syncobj->syncobj_timeline.wait_pt_tree.rb_node;
+	struct drm_syncobj_wait_pt *wait_pt = NULL;
+
+	spin_lock(&syncobj->lock);
+	while(node) {
+		int result;
+
+		wait_pt = rb_entry(node, struct drm_syncobj_wait_pt, node);
+		result = point - wait_pt->value;
+		if (result < 0) {
+			node = node->rb_left;
+		} else if (result > 0) {
+			node = node->rb_right;
+		} else {
+			if (fence)
+				*fence = dma_fence_get(&wait_pt->base.base);
+			break;
+		}
+	}
+	spin_unlock(&syncobj->lock);
+
+	return wait_pt;
+}
+
+static struct drm_syncobj_wait_pt *
+drm_syncobj_timeline_create_wait_pt_and_return_fence(struct drm_syncobj *syncobj,
+						     u64 point,
+						     struct dma_fence **fence)
+{
+	struct drm_syncobj_wait_pt *wait_pt = kzalloc(sizeof(*wait_pt),
+						      GFP_KERNEL);
+	struct drm_syncobj_stub_fence *base;
+	struct rb_node **new = &(syncobj->syncobj_timeline.wait_pt_tree.rb_node), *parent = NULL;
+
+	if (!wait_pt)
+		return NULL;
+	base = &wait_pt->base;
+	spin_lock_init(&base->lock);
+	dma_fence_init(&base->base,
+		       &drm_syncobj_stub_fence_ops,
+		       &base->lock,
+		       syncobj->syncobj_timeline.timeline_context, point);
+	wait_pt->value = point;
+	wait_pt->signal_pt_fence = NULL;
+
+	/* wait pt must be in an order, so that we can easily lookup and signal
+	 * it */
+	spin_lock(&syncobj->lock);
+	while(*new) {
+		struct drm_syncobj_wait_pt *this =
+			rb_entry(*new, struct drm_syncobj_wait_pt, node);
+		int result = wait_pt->value - this->value;
+
+		parent = *new;
+		if (result < 0)
+			new = &((*new)->rb_left);
+		else if (result > 0)
+			new = &((*new)->rb_right);
+		else
+			goto exist;
+	}
+	if (fence)
+		*fence = dma_fence_get(&wait_pt->base.base);
+	rb_link_node(&wait_pt->node, parent, new);
+	rb_insert_color(&wait_pt->node, &syncobj->syncobj_timeline.wait_pt_tree);
+	spin_unlock(&syncobj->lock);
+	return wait_pt;
+exist:
+	spin_unlock(&syncobj->lock);
+	dma_fence_put(&wait_pt->base.base);
+	wait_pt = drm_syncobj_timeline_lookup_wait_pt_fence(syncobj, point,
+							    fence);
+	return wait_pt;
+}
+
+static struct dma_fence *
+drm_syncobj_timeline_point_get(struct drm_syncobj *syncobj, u64 point, u64 flags)
+{
+	struct drm_syncobj_wait_pt *wait_pt;
+	struct dma_fence *fence = NULL;
+
+	/* check if the wait pt exists */
+	wait_pt = drm_syncobj_timeline_lookup_wait_pt_fence(syncobj, point,
+							    &fence);
+	if (!fence) {
+		/* This is a new wait pt, so create it */
+		wait_pt = drm_syncobj_timeline_create_wait_pt_and_return_fence(syncobj, point,
+							      &fence);
+		if (!fence)
+			return NULL;
+	}
+	if (wait_pt) {
+		int ret = 0;
+
+		if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) {
+			ret = wait_event_timeout(syncobj->syncobj_timeline.wq,
+							       wait_pt->value <= syncobj->syncobj_timeline.signal_point,
+							       msecs_to_jiffies(10000)); /* wait 10s */
+			if (ret <= 0)
+				return NULL;
+		}
+		spin_lock(&syncobj->lock);
+		drm_syncobj_find_signal_pt_for_wait_pt(syncobj, wait_pt);
+		spin_unlock(&syncobj->lock);
+		return fence;
+	}
+	return NULL;
+}
+
 /**
  * drm_syncobj_find_fence - lookup and reference the fence in a sync object
  * @file_private: drm file private pointer
@@ -234,20 +516,46 @@ static int drm_syncobj_assign_null_handle(struct drm_syncobj *syncobj)
  * contains a reference to the fence, which must be released by calling
  * dma_fence_put().
  */
-int drm_syncobj_find_fence(struct drm_file *file_private,
-			   u32 handle, u64 point,
-			   struct dma_fence **fence)
+int drm_syncobj_search_fence(struct drm_syncobj *syncobj, u64 point,
+			     u64 flags, struct dma_fence **fence)
 {
-	struct drm_syncobj *syncobj = drm_syncobj_find(file_private, handle);
 	int ret = 0;
 
 	if (!syncobj)
 		return -ENOENT;
 
-	*fence = drm_syncobj_fence_get(syncobj);
+	drm_syncobj_timeline_garbage_collection(syncobj);
+	if (syncobj->type == DRM_SYNCOBJ_TYPE_NORMAL) {
+		/*NORMAL syncobj always wait on last pt */
+		u64 tail_pt_value = syncobj->syncobj_timeline.signal_point;
+
+		if (tail_pt_value == 0)
+			tail_pt_value += DRM_SYNCOBJ_NORMAL_POINT;
+		/* NORMAL syncobj doesn't care point value */
+		WARN_ON(point != 0);
+		*fence = drm_syncobj_timeline_point_get(syncobj, tail_pt_value,
+							flags);
+	} else if (syncobj->type == DRM_SYNCOBJ_TYPE_TIMELINE) {
+		*fence = drm_syncobj_timeline_point_get(syncobj, point,
+							flags);
+	} else {
+		DRM_ERROR("Don't support this type syncobj\n");
+		*fence = NULL;
+	}
 	if (!*fence) {
 		ret = -EINVAL;
 	}
+	return ret;
+}
+EXPORT_SYMBOL(drm_syncobj_search_fence);
+int drm_syncobj_find_fence(struct drm_file *file_private,
+			   u32 handle, u64 point,
+			   struct dma_fence **fence) {
+	struct drm_syncobj *syncobj = drm_syncobj_find(file_private, handle);
+
+	int ret = drm_syncobj_search_fence(syncobj, point,
+					DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT,
+					fence);
 	drm_syncobj_put(syncobj);
 	return ret;
 }
@@ -264,7 +572,7 @@ 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_timeline_fini(syncobj, &syncobj->syncobj_timeline);
 	kfree(syncobj);
 }
 EXPORT_SYMBOL(drm_syncobj_free);
@@ -292,8 +600,12 @@ int drm_syncobj_create(struct drm_syncobj **out_syncobj, uint32_t flags,
 		return -ENOMEM;
 
 	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_NORMAL;
+	drm_syncobj_timeline_init(syncobj, &syncobj->syncobj_timeline);
 
 	if (flags & DRM_SYNCOBJ_CREATE_SIGNALED) {
 		ret = drm_syncobj_assign_null_handle(syncobj);
@@ -576,7 +888,8 @@ drm_syncobj_create_ioctl(struct drm_device *dev, void *data,
 		return -ENODEV;
 
 	/* 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,
@@ -651,7 +964,6 @@ struct syncobj_wait_entry {
 	struct task_struct *task;
 	struct dma_fence *fence;
 	struct dma_fence_cb fence_cb;
-	struct drm_syncobj_cb syncobj_cb;
 };
 
 static void syncobj_wait_fence_func(struct dma_fence *fence,
@@ -663,18 +975,6 @@ static void syncobj_wait_fence_func(struct dma_fence *fence,
 	wake_up_process(wait->task);
 }
 
-static void syncobj_wait_syncobj_func(struct drm_syncobj *syncobj,
-				      struct drm_syncobj_cb *cb)
-{
-	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)));
-	wake_up_process(wait->task);
-}
-
 static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
 						  uint32_t count,
 						  uint32_t flags,
@@ -698,14 +998,11 @@ 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]);
+		ret = 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;
-			} else {
-				ret = -EINVAL;
-				goto cleanup_entries;
-			}
+			ret = -EINVAL;
+			goto cleanup_entries;
 		}
 
 		if (dma_fence_is_signaled(entries[i].fence)) {
@@ -733,15 +1030,6 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
 	 * fallthough and try a 0 timeout wait!
 	 */
 
-	if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) {
-		for (i = 0; i < count; ++i) {
-			drm_syncobj_fence_get_or_add_callback(syncobjs[i],
-							      &entries[i].fence,
-							      &entries[i].syncobj_cb,
-							      syncobj_wait_syncobj_func);
-		}
-	}
-
 	do {
 		set_current_state(TASK_INTERRUPTIBLE);
 
@@ -789,13 +1077,10 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
 
 cleanup_entries:
 	for (i = 0; i < count; ++i) {
-		if (entries[i].syncobj_cb.func)
-			drm_syncobj_remove_callback(syncobjs[i],
-						    &entries[i].syncobj_cb);
+		dma_fence_put(entries[i].fence);
 		if (entries[i].fence_cb.func)
 			dma_fence_remove_callback(entries[i].fence,
 						  &entries[i].fence_cb);
-		dma_fence_put(entries[i].fence);
 	}
 	kfree(entries);
 
@@ -970,12 +1255,21 @@ 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++) {
+		if (syncobjs[i]->type == DRM_SYNCOBJ_TYPE_TIMELINE) {
+			DRM_ERROR("timeline syncobj cannot reset!\n");
+			ret = -EINVAL;
+			goto out;
+		}
+		drm_syncobj_timeline_fini(syncobjs[i],
+					  &syncobjs[i]->syncobj_timeline);
+		drm_syncobj_timeline_init(syncobjs[i],
+					  &syncobjs[i]->syncobj_timeline);
+	}
+out:
 	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 0a8d2d64f380..579e91a5858b 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -2137,7 +2137,9 @@ 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,
+					 DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT,
+					 &fence);
 		if (!fence)
 			return -EINVAL;
 
diff --git a/include/drm/drm_syncobj.h b/include/drm/drm_syncobj.h
index 425432b85a87..657c97dc25ec 100644
--- a/include/drm/drm_syncobj.h
+++ b/include/drm/drm_syncobj.h
@@ -30,6 +30,25 @@
 
 struct drm_syncobj_cb;
 
+enum drm_syncobj_type {
+	DRM_SYNCOBJ_TYPE_NORMAL,
+	DRM_SYNCOBJ_TYPE_TIMELINE
+};
+
+struct drm_syncobj_timeline {
+	wait_queue_head_t	wq;
+	u64 timeline_context;
+	/**
+	 * @timeline: syncobj timeline
+	 */
+	u64 timeline;
+	u64 signal_point;
+
+
+	struct rb_root wait_pt_tree;
+	struct list_head signal_pt_list;
+};
+
 /**
  * struct drm_syncobj - sync object.
  *
@@ -41,19 +60,16 @@ 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
 	 */
-	struct dma_fence __rcu *fence;
+	enum drm_syncobj_type type;
 	/**
-	 * @cb_list: List of callbacks to call when the &fence gets replaced.
+	 * @syncobj_timeline: timeline
 	 */
-	struct list_head cb_list;
+	struct drm_syncobj_timeline syncobj_timeline;
+
 	/**
-	 * @lock: Protects &cb_list and write-locks &fence.
+	 * @lock: Protects timeline list and write-locks &fence.
 	 */
 	spinlock_t lock;
 	/**
@@ -62,25 +78,6 @@ struct drm_syncobj {
 	struct file *file;
 };
 
-typedef void (*drm_syncobj_func_t)(struct drm_syncobj *syncobj,
-				   struct drm_syncobj_cb *cb);
-
-/**
- * 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
- * @func: drm_syncobj_func_t to call
- *
- * This struct will be initialized by drm_syncobj_add_callback, additional
- * data can be passed along by embedding drm_syncobj_cb in another struct.
- * The callback will get called the next time drm_syncobj_replace_fence is
- * called.
- */
-struct drm_syncobj_cb {
-	struct list_head node;
-	drm_syncobj_func_t func;
-};
-
 void drm_syncobj_free(struct kref *kref);
 
 /**
@@ -106,29 +103,6 @@ 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 +116,7 @@ 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;
 };
 
-- 
2.17.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 6/9] drm: add support of syncobj timeline point wait v2

[Chunming Zhou]

points array is one-to-one match with syncobjs array.
v2:
add seperate ioctl for timeline point wait, otherwise break uapi.

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
---
 drivers/gpu/drm/drm_internal.h |  2 +
 drivers/gpu/drm/drm_ioctl.c    |  2 +
 drivers/gpu/drm/drm_syncobj.c  | 87 +++++++++++++++++++++++++++++-----
 include/uapi/drm/drm.h         | 14 ++++++
 4 files changed, 94 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index 40179c5fc6b8..1bdbf2273b49 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -178,6 +178,8 @@ int drm_syncobj_fd_to_handle_ioctl(struct drm_device *dev, void *data,
 				   struct drm_file *file_private);
 int drm_syncobj_wait_ioctl(struct drm_device *dev, void *data,
 			   struct drm_file *file_private);
+int drm_syncobj_timeline_wait_ioctl(struct drm_device *dev, void *data,
+				    struct drm_file *file_private);
 int drm_syncobj_reset_ioctl(struct drm_device *dev, void *data,
 			    struct drm_file *file_private);
 int drm_syncobj_signal_ioctl(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index ea10e9a26aad..92d94867746b 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -669,6 +669,8 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 		      DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_WAIT, drm_syncobj_wait_ioctl,
 		      DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_TIMELINE_WAIT, drm_syncobj_timeline_wait_ioctl,
+		      DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_RESET, drm_syncobj_reset_ioctl,
 		      DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_SIGNAL, drm_syncobj_signal_ioctl,
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index 502cdf313aea..bcb3ba002985 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -976,6 +976,7 @@ static void syncobj_wait_fence_func(struct dma_fence *fence,
 }
 
 static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
+						  void __user *user_points,
 						  uint32_t count,
 						  uint32_t flags,
 						  signed long timeout,
@@ -983,13 +984,27 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
 {
 	struct syncobj_wait_entry *entries;
 	struct dma_fence *fence;
+	uint64_t *points;
 	signed long ret;
 	uint32_t signaled_count, i;
 
-	entries = kcalloc(count, sizeof(*entries), GFP_KERNEL);
-	if (!entries)
+	points = kmalloc_array(count, sizeof(*points), GFP_KERNEL);
+	if (points == NULL)
 		return -ENOMEM;
 
+	if (!user_points) {
+		memset(points, 0, count * sizeof(uint64_t));
+	} else if (copy_from_user(points, user_points, sizeof(uint64_t) * count)) {
+		ret = -EFAULT;
+		goto err_free_points;
+	}
+
+
+	entries = kcalloc(count, sizeof(*entries), GFP_KERNEL);
+	if (!entries) {
+		ret = -ENOMEM;
+		goto err_free_points;
+	}
 	/* Walk the list of sync objects and initialize entries.  We do
 	 * this up-front so that we can properly return -EINVAL if there is
 	 * a syncobj with a missing fence and then never have the chance of
@@ -998,7 +1013,7 @@ 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;
-		ret = drm_syncobj_search_fence(syncobjs[i], 0, 0,
+		ret = drm_syncobj_search_fence(syncobjs[i], points[i], 0,
 					       &entries[i].fence);
 		if (!entries[i].fence) {
 			ret = -EINVAL;
@@ -1084,6 +1099,9 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
 	}
 	kfree(entries);
 
+err_free_points:
+	kfree(points);
+
 	return ret;
 }
 
@@ -1122,20 +1140,33 @@ static signed long drm_timeout_abs_to_jiffies(int64_t timeout_nsec)
 static int drm_syncobj_array_wait(struct drm_device *dev,
 				  struct drm_file *file_private,
 				  struct drm_syncobj_wait *wait,
-				  struct drm_syncobj **syncobjs)
+				  struct drm_syncobj_timeline_wait *timeline_wait,
+				  struct drm_syncobj **syncobjs, bool timeline)
 {
-	signed long timeout = drm_timeout_abs_to_jiffies(wait->timeout_nsec);
+	signed long timeout = 0;
 	signed long ret = 0;
 	uint32_t first = ~0;
 
-	ret = drm_syncobj_array_wait_timeout(syncobjs,
-					     wait->count_handles,
-					     wait->flags,
-					     timeout, &first);
+	if (!timeline) {
+		timeout = drm_timeout_abs_to_jiffies(wait->timeout_nsec);
+		ret = drm_syncobj_array_wait_timeout(syncobjs,
+						     NULL,
+						     wait->count_handles,
+						     wait->flags,
+						     timeout, &first);
+		wait->first_signaled = first;
+	} else {
+		timeout = drm_timeout_abs_to_jiffies(timeline_wait->timeout_nsec);
+		ret = drm_syncobj_array_wait_timeout(syncobjs,
+						     u64_to_user_ptr(timeline_wait->points),
+						     timeline_wait->count_handles,
+						     timeline_wait->flags,
+						     timeout, &first);
+		timeline_wait->first_signaled = first;
+	}
 	if (ret < 0)
 		return ret;
 
-	wait->first_signaled = first;
 	if (ret == 0)
 		return -ETIME;
 	return 0;
@@ -1223,13 +1254,47 @@ drm_syncobj_wait_ioctl(struct drm_device *dev, void *data,
 		return ret;
 
 	ret = drm_syncobj_array_wait(dev, file_private,
-				     args, syncobjs);
+				     args, NULL, syncobjs, false);
 
 	drm_syncobj_array_free(syncobjs, args->count_handles);
 
 	return ret;
 }
 
+int
+drm_syncobj_timeline_wait_ioctl(struct drm_device *dev, void *data,
+				struct drm_file *file_private)
+{
+	struct drm_syncobj_timeline_wait *args = data;
+	struct drm_syncobj **syncobjs;
+	int ret = 0;
+
+	if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ))
+		return -ENODEV;
+
+	if (args->flags & ~(DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL |
+			    DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT))
+		return -EINVAL;
+
+	if (args->count_handles == 0)
+		return -EINVAL;
+
+	ret = drm_syncobj_array_find(file_private,
+				     u64_to_user_ptr(args->handles),
+				     args->count_handles,
+				     &syncobjs);
+	if (ret < 0)
+		return ret;
+
+	ret = drm_syncobj_array_wait(dev, file_private,
+				     NULL, args, syncobjs, true);
+
+	drm_syncobj_array_free(syncobjs, args->count_handles);
+
+	return ret;
+}
+
+
 int
 drm_syncobj_reset_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file_private)
diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
index cebdb2541eb7..501e86d81f47 100644
--- a/include/uapi/drm/drm.h
+++ b/include/uapi/drm/drm.h
@@ -748,6 +748,19 @@ struct drm_syncobj_wait {
 	__u32 pad;
 };
 
+struct drm_syncobj_timeline_wait {
+	__u64 handles;
+	/* wait on specific timeline point for every handles*/
+	__u64 points;
+	/* absolute timeout */
+	__s64 timeout_nsec;
+	__u32 count_handles;
+	__u32 flags;
+	__u32 first_signaled; /* only valid when not waiting all */
+	__u32 pad;
+};
+
+
 struct drm_syncobj_array {
 	__u64 handles;
 	__u32 count_handles;
@@ -910,6 +923,7 @@ extern "C" {
 #define DRM_IOCTL_MODE_GET_LEASE	DRM_IOWR(0xC8, struct drm_mode_get_lease)
 #define DRM_IOCTL_MODE_REVOKE_LEASE	DRM_IOWR(0xC9, struct drm_mode_revoke_lease)
 
+#define DRM_IOCTL_SYNCOBJ_TIMELINE_WAIT	DRM_IOWR(0xCA, struct drm_syncobj_timeline_wait)
 /**
  * Device specific ioctls should only be in their respective headers
  * The device specific ioctl range is from 0x40 to 0x9f.
-- 
2.17.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 7/9] drm: add timeline syncobj payload query ioctl

[Chunming Zhou]

user mode can query timeline payload.

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
---
 drivers/gpu/drm/drm_internal.h |  2 ++
 drivers/gpu/drm/drm_ioctl.c    |  2 ++
 drivers/gpu/drm/drm_syncobj.c  | 53 ++++++++++++++++++++++++++++++++++
 include/uapi/drm/drm.h         | 11 +++++++
 4 files changed, 68 insertions(+)

diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index 1bdbf2273b49..3a176e11b4ff 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -184,6 +184,8 @@ int drm_syncobj_reset_ioctl(struct drm_device *dev, void *data,
 			    struct drm_file *file_private);
 int drm_syncobj_signal_ioctl(struct drm_device *dev, void *data,
 			     struct drm_file *file_private);
+int drm_syncobj_query_ioctl(struct drm_device *dev, void *data,
+			    struct drm_file *file_private);
 
 /* drm_framebuffer.c */
 void drm_framebuffer_print_info(struct drm_printer *p, unsigned int indent,
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 92d94867746b..cfd1de44a4cc 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -675,6 +675,8 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 		      DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_SIGNAL, drm_syncobj_signal_ioctl,
 		      DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_QUERY, drm_syncobj_query_ioctl,
+		      DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF(DRM_IOCTL_CRTC_GET_SEQUENCE, drm_crtc_get_sequence_ioctl, DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_CRTC_QUEUE_SEQUENCE, drm_crtc_queue_sequence_ioctl, DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CREATE_LEASE, drm_mode_create_lease_ioctl, DRM_MASTER|DRM_UNLOCKED),
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index bcb3ba002985..8466fb38fa19 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -1372,3 +1372,56 @@ drm_syncobj_signal_ioctl(struct drm_device *dev, void *data,
 
 	return ret;
 }
+
+static void drm_syncobj_timeline_query_payload(struct drm_syncobj *syncobj,
+					       uint64_t *point)
+{
+	if (syncobj->type != DRM_SYNCOBJ_TYPE_TIMELINE) {
+		DRM_ERROR("Normal syncobj cann't be queried!");
+		*point = 0;
+		return;
+	}
+	*point = syncobj->syncobj_timeline.signal_point;
+}
+
+int drm_syncobj_query_ioctl(struct drm_device *dev, void *data,
+			    struct drm_file *file_private)
+{
+	struct drm_syncobj_timeline_query *args = data;
+	struct drm_syncobj **syncobjs;
+	uint64_t *points;
+	uint32_t i;
+	int ret;
+
+	if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ))
+		return -ENODEV;
+
+	if (args->count_handles == 0)
+		return -EINVAL;
+
+	ret = drm_syncobj_array_find(file_private,
+				     u64_to_user_ptr(args->handles),
+				     args->count_handles,
+				     &syncobjs);
+	if (ret < 0)
+		return ret;
+
+
+	points = kmalloc_array(args->count_handles, sizeof(*points),
+			       GFP_KERNEL);
+	if (points == NULL) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	for (i = 0; i < args->count_handles; i++) {
+		drm_syncobj_timeline_query_payload(syncobjs[i], &points[i]);
+		copy_to_user(u64_to_user_ptr(args->points), points,
+			     sizeof(uint64_t) * args->count_handles);
+	}
+
+	kfree(points);
+out:
+	drm_syncobj_array_free(syncobjs, args->count_handles);
+
+	return ret;
+}
diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
index 501e86d81f47..188b63f1975b 100644
--- a/include/uapi/drm/drm.h
+++ b/include/uapi/drm/drm.h
@@ -767,6 +767,15 @@ struct drm_syncobj_array {
 	__u32 pad;
 };
 
+struct drm_syncobj_timeline_query {
+	__u64 handles;
+	/* points are timeline syncobjs payloads returned by query ioctl */
+	__u64 points;
+	__u32 count_handles;
+	__u32 pad;
+};
+
+
 /* Query current scanout sequence number */
 struct drm_crtc_get_sequence {
 	__u32 crtc_id;		/* requested crtc_id */
@@ -924,6 +933,8 @@ extern "C" {
 #define DRM_IOCTL_MODE_REVOKE_LEASE	DRM_IOWR(0xC9, struct drm_mode_revoke_lease)
 
 #define DRM_IOCTL_SYNCOBJ_TIMELINE_WAIT	DRM_IOWR(0xCA, struct drm_syncobj_timeline_wait)
+#define DRM_IOCTL_SYNCOBJ_QUERY		DRM_IOWR(0xCB, struct drm_syncobj_timeline_query)
+
 /**
  * Device specific ioctls should only be in their respective headers
  * The device specific ioctl range is from 0x40 to 0x9f.
-- 
2.17.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH 8/9] drm/amdgpu: add timeline support in amdgpu CS

[Chunming Zhou]

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h    |   8 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 111 +++++++++++++++++++------
 include/uapi/drm/amdgpu_drm.h          |   9 ++
 3 files changed, 100 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 447c4c7a36d6..6e4a3db56833 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -975,6 +975,11 @@ struct amdgpu_cs_chunk {
 	void			*kdata;
 };
 
+struct amdgpu_cs_syncobj_post_dep {
+	struct drm_syncobj *post_dep_syncobj;
+	u64 point;
+};
+
 struct amdgpu_cs_parser {
 	struct amdgpu_device	*adev;
 	struct drm_file		*filp;
@@ -1003,9 +1008,8 @@ struct amdgpu_cs_parser {
 
 	/* user fence */
 	struct amdgpu_bo_list_entry	uf_entry;
-
+	struct amdgpu_cs_syncobj_post_dep *post_dep_syncobjs;
 	unsigned num_post_dep_syncobjs;
-	struct drm_syncobj **post_dep_syncobjs;
 };
 
 static inline u32 amdgpu_get_ib_value(struct amdgpu_cs_parser *p,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index d68b73ff92d2..230e2357e249 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -204,6 +204,8 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs
 		case AMDGPU_CHUNK_ID_DEPENDENCIES:
 		case AMDGPU_CHUNK_ID_SYNCOBJ_IN:
 		case AMDGPU_CHUNK_ID_SYNCOBJ_OUT:
+		case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT:
+		case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL:
 			break;
 
 		default:
@@ -783,7 +785,7 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error,
 					   &parser->validated);
 
 	for (i = 0; i < parser->num_post_dep_syncobjs; i++)
-		drm_syncobj_put(parser->post_dep_syncobjs[i]);
+		drm_syncobj_put(parser->post_dep_syncobjs[i].post_dep_syncobj);
 	kfree(parser->post_dep_syncobjs);
 
 	dma_fence_put(parser->fence);
@@ -1098,11 +1100,11 @@ static int amdgpu_cs_process_fence_dep(struct amdgpu_cs_parser *p,
 }
 
 static int amdgpu_syncobj_lookup_and_add_to_sync(struct amdgpu_cs_parser *p,
-						 uint32_t handle)
+						 uint32_t handle, u64 point)
 {
 	int r;
 	struct dma_fence *fence;
-	r = drm_syncobj_find_fence(p->filp, handle, 0, &fence);
+	r = drm_syncobj_find_fence(p->filp, handle, point, &fence);
 	if (r)
 		return r;
 
@@ -1113,48 +1115,90 @@ static int amdgpu_syncobj_lookup_and_add_to_sync(struct amdgpu_cs_parser *p,
 }
 
 static int amdgpu_cs_process_syncobj_in_dep(struct amdgpu_cs_parser *p,
-					    struct amdgpu_cs_chunk *chunk)
+					    struct amdgpu_cs_chunk *chunk,
+					    bool timeline)
 {
 	unsigned num_deps;
 	int i, r;
-	struct drm_amdgpu_cs_chunk_sem *deps;
 
-	deps = (struct drm_amdgpu_cs_chunk_sem *)chunk->kdata;
-	num_deps = chunk->length_dw * 4 /
-		sizeof(struct drm_amdgpu_cs_chunk_sem);
+	if (!timeline) {
+		struct drm_amdgpu_cs_chunk_sem *deps;
 
-	for (i = 0; i < num_deps; ++i) {
-		r = amdgpu_syncobj_lookup_and_add_to_sync(p, deps[i].handle);
+		deps = (struct drm_amdgpu_cs_chunk_sem *)chunk->kdata;
+		num_deps = chunk->length_dw * 4 /
+			sizeof(struct drm_amdgpu_cs_chunk_sem);
+		for (i = 0; i < num_deps; ++i) {
+			r = amdgpu_syncobj_lookup_and_add_to_sync(p, deps[i].handle,
+								  0);
 		if (r)
 			return r;
+		}
+	} else {
+		struct drm_amdgpu_cs_chunk_syncobj *syncobj_deps;
+
+		syncobj_deps = (struct drm_amdgpu_cs_chunk_syncobj *)chunk->kdata;
+		num_deps = chunk->length_dw * 4 /
+			sizeof(struct drm_amdgpu_cs_chunk_syncobj);
+		for (i = 0; i < num_deps; ++i) {
+			r = amdgpu_syncobj_lookup_and_add_to_sync(p, syncobj_deps[i].handle,
+								  syncobj_deps[i].point);
+		if (r)
+			return r;
+		}
 	}
+
 	return 0;
 }
 
 static int amdgpu_cs_process_syncobj_out_dep(struct amdgpu_cs_parser *p,
-					     struct amdgpu_cs_chunk *chunk)
+					     struct amdgpu_cs_chunk *chunk,
+					     bool timeline)
 {
 	unsigned num_deps;
 	int i;
 	struct drm_amdgpu_cs_chunk_sem *deps;
-	deps = (struct drm_amdgpu_cs_chunk_sem *)chunk->kdata;
-	num_deps = chunk->length_dw * 4 /
-		sizeof(struct drm_amdgpu_cs_chunk_sem);
+	struct drm_amdgpu_cs_chunk_syncobj *syncobj_deps;
+
+	if (!timeline) {
+		deps = (struct drm_amdgpu_cs_chunk_sem *)chunk->kdata;
+		num_deps = chunk->length_dw * 4 /
+			sizeof(struct drm_amdgpu_cs_chunk_sem);
+	} else {
+		syncobj_deps = (struct drm_amdgpu_cs_chunk_syncobj *)chunk->kdata;
+		num_deps = chunk->length_dw * 4 /
+			sizeof(struct drm_amdgpu_cs_chunk_syncobj);
+	}
+
 
 	p->post_dep_syncobjs = kmalloc_array(num_deps,
-					     sizeof(struct drm_syncobj *),
+					     sizeof(struct amdgpu_cs_syncobj_post_dep),
 					     GFP_KERNEL);
 	p->num_post_dep_syncobjs = 0;
 
 	if (!p->post_dep_syncobjs)
 		return -ENOMEM;
 
-	for (i = 0; i < num_deps; ++i) {
-		p->post_dep_syncobjs[i] = drm_syncobj_find(p->filp, deps[i].handle);
-		if (!p->post_dep_syncobjs[i])
-			return -EINVAL;
-		p->num_post_dep_syncobjs++;
+
+	if (!timeline) {
+		for (i = 0; i < num_deps; ++i) {
+			p->post_dep_syncobjs[i].post_dep_syncobj =
+				drm_syncobj_find(p->filp, deps[i].handle);
+			if (!p->post_dep_syncobjs[i].post_dep_syncobj)
+				return -EINVAL;
+			p->post_dep_syncobjs[i].point = 0;
+			p->num_post_dep_syncobjs++;
+		}
+	} else {
+		for (i = 0; i < num_deps; ++i) {
+			p->post_dep_syncobjs[i].post_dep_syncobj =
+				drm_syncobj_find(p->filp, syncobj_deps[i].handle);
+			if (!p->post_dep_syncobjs[i].post_dep_syncobj)
+				return -EINVAL;
+			p->post_dep_syncobjs[i].point = syncobj_deps[i].point;
+			p->num_post_dep_syncobjs++;
+		}
 	}
+
 	return 0;
 }
 
@@ -1168,18 +1212,32 @@ static int amdgpu_cs_dependencies(struct amdgpu_device *adev,
 
 		chunk = &p->chunks[i];
 
-		if (chunk->chunk_id == AMDGPU_CHUNK_ID_DEPENDENCIES) {
+		switch (chunk->chunk_id) {
+		case AMDGPU_CHUNK_ID_DEPENDENCIES:
 			r = amdgpu_cs_process_fence_dep(p, chunk);
 			if (r)
 				return r;
-		} else if (chunk->chunk_id == AMDGPU_CHUNK_ID_SYNCOBJ_IN) {
-			r = amdgpu_cs_process_syncobj_in_dep(p, chunk);
+			break;
+		case AMDGPU_CHUNK_ID_SYNCOBJ_IN:
+			r = amdgpu_cs_process_syncobj_in_dep(p, chunk, false);
 			if (r)
 				return r;
-		} else if (chunk->chunk_id == AMDGPU_CHUNK_ID_SYNCOBJ_OUT) {
-			r = amdgpu_cs_process_syncobj_out_dep(p, chunk);
+			break;
+		case AMDGPU_CHUNK_ID_SYNCOBJ_OUT:
+			r = amdgpu_cs_process_syncobj_out_dep(p, chunk, false);
+			if (r)
+				return r;
+			break;
+		case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT:
+			r = amdgpu_cs_process_syncobj_in_dep(p, chunk, true);
 			if (r)
 				return r;
+			break;
+		case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL:
+			r = amdgpu_cs_process_syncobj_out_dep(p, chunk, true);
+			if (r)
+				return r;
+			break;
 		}
 	}
 
@@ -1191,7 +1249,8 @@ static void amdgpu_cs_post_dependencies(struct amdgpu_cs_parser *p)
 	int i;
 
 	for (i = 0; i < p->num_post_dep_syncobjs; ++i)
-		drm_syncobj_replace_fence(p->post_dep_syncobjs[i], 0, p->fence);
+		drm_syncobj_replace_fence(p->post_dep_syncobjs[i].post_dep_syncobj,
+					  p->post_dep_syncobjs[i].point, p->fence);
 }
 
 static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 1ceec56de015..0f3eecda676a 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -517,6 +517,8 @@ struct drm_amdgpu_gem_va {
 #define AMDGPU_CHUNK_ID_SYNCOBJ_IN      0x04
 #define AMDGPU_CHUNK_ID_SYNCOBJ_OUT     0x05
 #define AMDGPU_CHUNK_ID_BO_HANDLES      0x06
+#define AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT    0x07
+#define AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL  0x08
 
 struct drm_amdgpu_cs_chunk {
 	__u32		chunk_id;
@@ -592,6 +594,13 @@ struct drm_amdgpu_cs_chunk_sem {
 	__u32 handle;
 };
 
+struct drm_amdgpu_cs_chunk_syncobj {
+       __u32 handle;
+       __u32 pad;
+       __u64 point;
+};
+
+
 #define AMDGPU_FENCE_TO_HANDLE_GET_SYNCOBJ	0
 #define AMDGPU_FENCE_TO_HANDLE_GET_SYNCOBJ_FD	1
 #define AMDGPU_FENCE_TO_HANDLE_GET_SYNC_FILE_FD	2
-- 
2.17.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH 9/9] drm/amdgpu: move cs dependencies front a bit

[Chunming Zhou]

cs dependencies handling doesn't need in vm resv

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 230e2357e249..aa829c6ef08e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1343,6 +1343,12 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	if (r)
 		goto out;
 
+	r = amdgpu_cs_dependencies(adev, &parser);
+	if (r) {
+		DRM_ERROR("Failed in the dependencies handling %d!\n", r);
+		goto out;
+	}
+
 	r = amdgpu_cs_parser_bos(&parser, data);
 	if (r) {
 		if (r == -ENOMEM)
@@ -1354,12 +1360,6 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 
 	reserved_buffers = true;
 
-	r = amdgpu_cs_dependencies(adev, &parser);
-	if (r) {
-		DRM_ERROR("Failed in the dependencies handling %d!\n", r);
-		goto out;
-	}
-
 	for (i = 0; i < parser.job->num_ibs; i++)
 		trace_amdgpu_cs(&parser, i);
 
-- 
2.17.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx