3 files changed, 87 insertions, 10 deletions

diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 15d04a0ec623..e0a8890a62e2 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -507,12 +507,19 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job)
 {
 	struct drm_sched_entity *entity = sched_job->entity;
 	bool first;
+	ktime_t submit_ts;
 
 	trace_drm_sched_job(sched_job, entity);
 	atomic_inc(entity->rq->sched->score);
 	WRITE_ONCE(entity->last_user, current->group_leader);
+
+	/*
+	 * After the sched_job is pushed into the entity queue, it may be
+	 * completed and freed up at any time. We can no longer access it.
+	 * Make sure to set the submit_ts first, to avoid a race.
+	 */
+	sched_job->submit_ts = submit_ts = ktime_get();
 	first = spsc_queue_push(&entity->job_queue, &sched_job->queue_node);
-	sched_job->submit_ts = ktime_get();
 
 	/* first job wakes up scheduler */
 	if (first) {
@@ -529,7 +536,7 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job)
 		spin_unlock(&entity->rq_lock);
 
 		if (drm_sched_policy == DRM_SCHED_POLICY_FIFO)
-			drm_sched_rq_update_fifo(entity, sched_job->submit_ts);
+			drm_sched_rq_update_fifo(entity, submit_ts);
 
 		drm_sched_wakeup(entity->rq->sched);
 	}
diff --git a/drivers/gpu/drm/scheduler/sched_fence.c b/drivers/gpu/drm/scheduler/sched_fence.c
index 7fd869520ef2..fe9c6468e440 100644
--- a/drivers/gpu/drm/scheduler/sched_fence.c
+++ b/drivers/gpu/drm/scheduler/sched_fence.c
@@ -123,6 +123,37 @@ static void drm_sched_fence_release_finished(struct dma_fence *f)
 	dma_fence_put(&fence->scheduled);
 }
 
+static void drm_sched_fence_set_deadline_finished(struct dma_fence *f,
+						  ktime_t deadline)
+{
+	struct drm_sched_fence *fence = to_drm_sched_fence(f);
+	struct dma_fence *parent;
+	unsigned long flags;
+
+	spin_lock_irqsave(&fence->lock, flags);
+
+	/* If we already have an earlier deadline, keep it: */
+	if (test_bit(DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT, &f->flags) &&
+	    ktime_before(fence->deadline, deadline)) {
+		spin_unlock_irqrestore(&fence->lock, flags);
+		return;
+	}
+
+	fence->deadline = deadline;
+	set_bit(DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT, &f->flags);
+
+	spin_unlock_irqrestore(&fence->lock, flags);
+
+	/*
+	 * smp_load_aquire() to ensure that if we are racing another
+	 * thread calling drm_sched_fence_set_parent(), that we see
+	 * the parent set before it calls test_bit(HAS_DEADLINE_BIT)
+	 */
+	parent = smp_load_acquire(&fence->parent);
+	if (parent)
+		dma_fence_set_deadline(parent, deadline);
+}
+
 static const struct dma_fence_ops drm_sched_fence_ops_scheduled = {
 	.get_driver_name = drm_sched_fence_get_driver_name,
 	.get_timeline_name = drm_sched_fence_get_timeline_name,
@@ -133,6 +164,7 @@ static const struct dma_fence_ops drm_sched_fence_ops_finished = {
 	.get_driver_name = drm_sched_fence_get_driver_name,
 	.get_timeline_name = drm_sched_fence_get_timeline_name,
 	.release = drm_sched_fence_release_finished,
+	.set_deadline = drm_sched_fence_set_deadline_finished,
 };
 
 struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f)
@@ -147,6 +179,20 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f)
 }
 EXPORT_SYMBOL(to_drm_sched_fence);
 
+void drm_sched_fence_set_parent(struct drm_sched_fence *s_fence,
+				struct dma_fence *fence)
+{
+	/*
+	 * smp_store_release() to ensure another thread racing us
+	 * in drm_sched_fence_set_deadline_finished() sees the
+	 * fence's parent set before test_bit()
+	 */
+	smp_store_release(&s_fence->parent, dma_fence_get(fence));
+	if (test_bit(DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT,
+		     &s_fence->finished.flags))
+		dma_fence_set_deadline(fence, s_fence->deadline);
+}
+
 struct drm_sched_fence *drm_sched_fence_alloc(struct drm_sched_entity *entity,
 					      void *owner)
 {
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 4e6ad6e122bc..fcd5bd7e5e8e 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -53,6 +53,7 @@
 
 #include <drm/drm_print.h>
 #include <drm/drm_gem.h>
+#include <drm/drm_syncobj.h>
 #include <drm/gpu_scheduler.h>
 #include <drm/spsc_queue.h>
 
@@ -308,7 +309,8 @@ static void drm_sched_start_timeout(struct drm_gpu_scheduler *sched)
  */
 void drm_sched_fault(struct drm_gpu_scheduler *sched)
 {
-	mod_delayed_work(sched->timeout_wq, &sched->work_tdr, 0);
+	if (sched->ready)
+		mod_delayed_work(sched->timeout_wq, &sched->work_tdr, 0);
 }
 EXPORT_SYMBOL(drm_sched_fault);
 
@@ -719,6 +721,34 @@ int drm_sched_job_add_dependency(struct drm_sched_job *job,
 EXPORT_SYMBOL(drm_sched_job_add_dependency);
 
 /**
+ * drm_sched_job_add_syncobj_dependency - adds a syncobj's fence as a job dependency
+ * @job: scheduler job to add the dependencies to
+ * @file: drm file private pointer
+ * @handle: syncobj handle to lookup
+ * @point: timeline point
+ *
+ * This adds the fence matching the given syncobj to @job.
+ *
+ * Returns:
+ * 0 on success, or an error on failing to expand the array.
+ */
+int drm_sched_job_add_syncobj_dependency(struct drm_sched_job *job,
+					 struct drm_file *file,
+					 u32 handle,
+					 u32 point)
+{
+	struct dma_fence *fence;
+	int ret;
+
+	ret = drm_syncobj_find_fence(file, handle, point, 0, &fence);
+	if (ret)
+		return ret;
+
+	return drm_sched_job_add_dependency(job, fence);
+}
+EXPORT_SYMBOL(drm_sched_job_add_syncobj_dependency);
+
+/**
  * drm_sched_job_add_resv_dependencies - add all fences from the resv to the job
  * @job: scheduler job to add the dependencies to
  * @resv: the dma_resv object to get the fences from
@@ -906,12 +936,6 @@ drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched)
 
 	spin_unlock(&sched->job_list_lock);
 
-	if (job) {
-		job->entity->elapsed_ns += ktime_to_ns(
-			ktime_sub(job->s_fence->finished.timestamp,
-				  job->s_fence->scheduled.timestamp));
-	}
-
 	return job;
 }
 
@@ -1019,7 +1043,7 @@ static int drm_sched_main(void *param)
 		drm_sched_fence_scheduled(s_fence);
 
 		if (!IS_ERR_OR_NULL(fence)) {
-			s_fence->parent = dma_fence_get(fence);
+			drm_sched_fence_set_parent(s_fence, fence);
 			/* Drop for original kref_init of the fence */
 			dma_fence_put(fence);