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: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210512142648.666476-14-andrey.grodzovsky@amd.com

diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 0249c745018882d1089ff31f2e42560fdaa7b3a5..2e93e881b65f7b5f15037d9f2e2d196d8effe1d8 100644 (file)
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -116,7 +116,8 @@ static bool drm_sched_entity_is_idle(struct drm_sched_entity *entity)
        rmb(); /* for list_empty to work without lock */
 
        if (list_empty(&entity->list) ||
-           spsc_queue_count(&entity->job_queue) == 0)
+           spsc_queue_count(&entity->job_queue) == 0 ||
+           entity->stopped)
                return true;
 
        return false;

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 8d1211e87101122778e3a52e1e43566df264fe25..a2a953693b4508cf89d6e6d95a64231b15f4bcdb 100644 (file)
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -898,9 +898,33 @@ EXPORT_SYMBOL(drm_sched_init);
  */
 void drm_sched_fini(struct drm_gpu_scheduler *sched)
 {
+       struct drm_sched_entity *s_entity;
+       int i;
+
        if (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 */
        cancel_delayed_work_sync(&sched->work_tdr);