[PATCH v2] drm/sched: Avoid double re-lock on the job free path

[Tvrtko Ursulin]

Currently the job free work item will lock sched->job_list_lock first time
to see if there are any jobs, free a single job, and then lock again to
decide whether to re-queue itself if there are more finished jobs.

Since drm_sched_get_finished_job() already looks at the second job in the
queue we can simply extend the timestamp check with the full signaled
check and have it return the presence of more jobs to free to the caller.
That way the work item does not have to lock the list again and repeat the
very similar check.

v2:
 * Consolidate to single dma_fence_is_signaled check.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at igalia.com>
Cc: Christian König <christian.koenig at amd.com>
Cc: Danilo Krummrich <dakr at kernel.org>
Cc: Matthew Brost <matthew.brost at intel.com>
Cc: Philipp Stanner <phasta at kernel.org>
---
 drivers/gpu/drm/scheduler/sched_main.c | 40 ++++++++++----------------
 1 file changed, 15 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index d172e3158880..af63a14f5001 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -370,22 +370,6 @@ static void __drm_sched_run_free_queue(struct drm_gpu_scheduler *sched)
 		queue_work(sched->submit_wq, &sched->work_free_job);
 }
 
-/**
- * drm_sched_run_free_queue - enqueue free-job work if ready
- * @sched: scheduler instance
- */
-static void drm_sched_run_free_queue(struct drm_gpu_scheduler *sched)
-{
-	struct drm_sched_job *job;
-
-	spin_lock(&sched->job_list_lock);
-	job = list_first_entry_or_null(&sched->pending_list,
-				       struct drm_sched_job, list);
-	if (job && dma_fence_is_signaled(&job->s_fence->finished))
-		__drm_sched_run_free_queue(sched);
-	spin_unlock(&sched->job_list_lock);
-}
-
 /**
  * drm_sched_job_done - complete a job
  * @s_job: pointer to the job which is done
@@ -1065,12 +1049,13 @@ drm_sched_select_entity(struct drm_gpu_scheduler *sched)
  * drm_sched_get_finished_job - fetch the next finished job to be destroyed
  *
  * @sched: scheduler instance
+ * @have_more: are there more finished jobs on the list
  *
  * Returns the next finished job from the pending list (if there is one)
  * ready for it to be destroyed.
  */
 static struct drm_sched_job *
-drm_sched_get_finished_job(struct drm_gpu_scheduler *sched)
+drm_sched_get_finished_job(struct drm_gpu_scheduler *sched, bool *have_more)
 {
 	struct drm_sched_job *job, *next;
 
@@ -1078,22 +1063,24 @@ drm_sched_get_finished_job(struct drm_gpu_scheduler *sched)
 
 	job = list_first_entry_or_null(&sched->pending_list,
 				       struct drm_sched_job, list);
-
 	if (job && dma_fence_is_signaled(&job->s_fence->finished)) {
 		/* remove job from pending_list */
 		list_del_init(&job->list);
 
 		/* cancel this job's TO timer */
 		cancel_delayed_work(&sched->work_tdr);
-		/* make the scheduled timestamp more accurate */
+
+		*have_more = false;
 		next = list_first_entry_or_null(&sched->pending_list,
 						typeof(*next), list);
-
 		if (next) {
-			if (test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT,
-				     &next->s_fence->scheduled.flags))
+			if (dma_fence_is_signaled(&next->s_fence->finished)) {
+				*have_more = true;
+				/* make the scheduled timestamp more accurate */
 				next->s_fence->scheduled.timestamp =
 					dma_fence_timestamp(&job->s_fence->finished);
+			}
+
 			/* start TO timer for next job */
 			drm_sched_start_timeout(sched);
 		}
@@ -1152,12 +1139,15 @@ static void drm_sched_free_job_work(struct work_struct *w)
 	struct drm_gpu_scheduler *sched =
 		container_of(w, struct drm_gpu_scheduler, work_free_job);
 	struct drm_sched_job *job;
+	bool have_more;
 
-	job = drm_sched_get_finished_job(sched);
-	if (job)
+	job = drm_sched_get_finished_job(sched, &have_more);
+	if (job) {
 		sched->ops->free_job(job);
+		if (have_more)
+			__drm_sched_run_free_queue(sched);
+	}
 
-	drm_sched_run_free_queue(sched);
 	drm_sched_run_job_queue(sched);
 }
 
-- 
2.47.1