Commit c61cdbdb authored by Andrey Grodzovsky's avatar Andrey Grodzovsky
Browse files

drm/scheduler: Fix hang when sched_entity released 



Problem: If scheduler is already stopped by the time sched_entity
is released and entity's job_queue not empty I encountred
a hang in drm_sched_entity_flush. This is because drm_sched_entity_is_idle
never becomes false.

Fix: In drm_sched_fini detach all sched_entities from the
scheduler's run queues. This will satisfy drm_sched_entity_is_idle.
Also wakeup all those processes stuck in sched_entity flushing
as the scheduler main thread which wakes them up is stopped by now.

v2:
Reverse order of drm_sched_rq_remove_entity and marking
s_entity as stopped to prevent reinserion back to rq due
to race.

v3:
Drop drm_sched_rq_remove_entity, only modify entity->stopped
and check for it in drm_sched_entity_is_idle

Signed-off-by: default avatarAndrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: default avatarChristian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210512142648.666476-14-andrey.grodzovsky@amd.com
parent 54a85db8

drivers/gpu/drm/scheduler/sched_entity.c

+2 −1
Original line number Original line Diff line number Diff line
@@ -116,7 +116,8 @@ static bool drm_sched_entity_is_idle(struct drm_sched_entity *entity) 
	rmb(); /* for list_empty to work without lock */

	rmb(); /* for list_empty to work without lock */





	if (list_empty(&entity->list) ||

	if (list_empty(&entity->list) ||

	    spsc_queue_count(&entity->job_queue) == 0)

	    spsc_queue_count(&entity->job_queue) == 0 ||

	    entity->stopped)

		return true;

		return true;





	return false;

	return false;

drivers/gpu/drm/scheduler/sched_main.c

+24 −0
Original line number Original line Diff line number Diff line
@@ -898,9 +898,33 @@ EXPORT_SYMBOL(drm_sched_init); 
 */

 */

void drm_sched_fini(struct drm_gpu_scheduler *sched)

void drm_sched_fini(struct drm_gpu_scheduler *sched)

{

{

	struct drm_sched_entity *s_entity;

	int i;



	if (sched->thread)

	if (sched->thread)

		kthread_stop(sched->thread);

		kthread_stop(sched->thread);





	for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {

		struct drm_sched_rq *rq = &sched->sched_rq[i];



		if (!rq)

			continue;



		spin_lock(&rq->lock);

		list_for_each_entry(s_entity, &rq->entities, list)

			/*

			 * Prevents reinsertion and marks job_queue as idle,

			 * it will removed from rq in drm_sched_entity_fini

			 * eventually

			 */

			s_entity->stopped = true;

		spin_unlock(&rq->lock);



	}



	/* Wakeup everyone stuck in drm_sched_entity_flush for this scheduler */

	wake_up_all(&sched->job_scheduled);



	/* Confirm no work left behind accessing device structures */

	/* Confirm no work left behind accessing device structures */

	cancel_delayed_work_sync(&sched->work_tdr);

	cancel_delayed_work_sync(&sched->work_tdr);