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.
Signed-off-by: Andrey Grodzovsky andrey.grodzovsky@amd.com --- drivers/gpu/drm/scheduler/sched_main.c | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+)
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 908b0b5..11abf5d 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -897,9 +897,40 @@ EXPORT_SYMBOL(drm_sched_init); */ void drm_sched_fini(struct drm_gpu_scheduler *sched) { + int i; + struct drm_sched_entity *s_entity; if (sched->thread) kthread_stop(sched->thread);
+ /* Detach all sched_entites from this scheduler once it's stopped */ + 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; + + /* Loop this way because rq->lock is taken in drm_sched_rq_remove_entity */ + spin_lock(&rq->lock); + while ((s_entity = list_first_entry_or_null(&rq->entities, + struct drm_sched_entity, + list))) { + spin_unlock(&rq->lock); + drm_sched_rq_remove_entity(rq, s_entity); + + /* Mark as stopped to reject adding to any new rq */ + spin_lock(&s_entity->rq_lock); + s_entity->stopped = true; + spin_unlock(&s_entity->rq_lock); + + spin_lock(&rq->lock); + } + 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);
Ping
Andrey
On 2/16/21 12:07 PM, Andrey Grodzovsky wrote:
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.
Signed-off-by: Andrey Grodzovsky andrey.grodzovsky@amd.com
drivers/gpu/drm/scheduler/sched_main.c | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+)
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 908b0b5..11abf5d 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -897,9 +897,40 @@ EXPORT_SYMBOL(drm_sched_init); */ void drm_sched_fini(struct drm_gpu_scheduler *sched) {
int i;
struct drm_sched_entity *s_entity; if (sched->thread) kthread_stop(sched->thread);
/* Detach all sched_entites from this scheduler once it's stopped */
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;/* Loop this way because rq->lock is taken in drm_sched_rq_remove_entity */spin_lock(&rq->lock);while ((s_entity = list_first_entry_or_null(&rq->entities,struct drm_sched_entity,list))) {spin_unlock(&rq->lock);drm_sched_rq_remove_entity(rq, s_entity);/* Mark as stopped to reject adding to any new rq */spin_lock(&s_entity->rq_lock);s_entity->stopped = true;spin_unlock(&s_entity->rq_lock);spin_lock(&rq->lock);}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);
Am 16.02.21 um 18:07 schrieb Andrey Grodzovsky:
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.
Signed-off-by: Andrey Grodzovsky andrey.grodzovsky@amd.com
drivers/gpu/drm/scheduler/sched_main.c | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+)
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 908b0b5..11abf5d 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -897,9 +897,40 @@ EXPORT_SYMBOL(drm_sched_init); */ void drm_sched_fini(struct drm_gpu_scheduler *sched) {
int i;
struct drm_sched_entity *s_entity; if (sched->thread) kthread_stop(sched->thread);
/* Detach all sched_entites from this scheduler once it's stopped */
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;/* Loop this way because rq->lock is taken in drm_sched_rq_remove_entity */spin_lock(&rq->lock);while ((s_entity = list_first_entry_or_null(&rq->entities,struct drm_sched_entity,list))) {spin_unlock(&rq->lock);drm_sched_rq_remove_entity(rq, s_entity);/* Mark as stopped to reject adding to any new rq */spin_lock(&s_entity->rq_lock);s_entity->stopped = true;
Why not marking it as stopped and then removing it?
Regards, Christian.
spin_unlock(&s_entity->rq_lock);spin_lock(&rq->lock);}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);
On 2/17/21 4:32 PM, Christian König wrote:
Am 16.02.21 um 18:07 schrieb Andrey Grodzovsky:
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.
Signed-off-by: Andrey Grodzovsky andrey.grodzovsky@amd.com
drivers/gpu/drm/scheduler/sched_main.c | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+)
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 908b0b5..11abf5d 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -897,9 +897,40 @@ EXPORT_SYMBOL(drm_sched_init); */ void drm_sched_fini(struct drm_gpu_scheduler *sched) { + int i; + struct drm_sched_entity *s_entity; if (sched->thread) kthread_stop(sched->thread); + /* Detach all sched_entites from this scheduler once it's stopped */ + 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;
+ /* Loop this way because rq->lock is taken in drm_sched_rq_remove_entity */ + spin_lock(&rq->lock); + while ((s_entity = list_first_entry_or_null(&rq->entities, + struct drm_sched_entity, + list))) { + spin_unlock(&rq->lock); + drm_sched_rq_remove_entity(rq, s_entity);
+ /* Mark as stopped to reject adding to any new rq */ + spin_lock(&s_entity->rq_lock); + s_entity->stopped = true;
Why not marking it as stopped and then removing it?
Regards, Christian.
You mean just reverse the order of operations here to prevent a race where someone adding it again to rq before marking it as stopped ?
Andrey
- spin_unlock(&s_entity->rq_lock);
+ spin_lock(&rq->lock); + } + 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);
Am 17.02.21 um 22:36 schrieb Andrey Grodzovsky:
On 2/17/21 4:32 PM, Christian König wrote:
Am 16.02.21 um 18:07 schrieb Andrey Grodzovsky:
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.
Signed-off-by: Andrey Grodzovsky andrey.grodzovsky@amd.com
drivers/gpu/drm/scheduler/sched_main.c | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+)
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 908b0b5..11abf5d 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -897,9 +897,40 @@ EXPORT_SYMBOL(drm_sched_init); */ void drm_sched_fini(struct drm_gpu_scheduler *sched) { + int i; + struct drm_sched_entity *s_entity; if (sched->thread) kthread_stop(sched->thread); + /* Detach all sched_entites from this scheduler once it's stopped */ + 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;
+ /* Loop this way because rq->lock is taken in drm_sched_rq_remove_entity */ + spin_lock(&rq->lock); + while ((s_entity = list_first_entry_or_null(&rq->entities, + struct drm_sched_entity, + list))) { + spin_unlock(&rq->lock); + drm_sched_rq_remove_entity(rq, s_entity);
+ /* Mark as stopped to reject adding to any new rq */ + spin_lock(&s_entity->rq_lock); + s_entity->stopped = true;
Why not marking it as stopped and then removing it?
Regards, Christian.
You mean just reverse the order of operations here to prevent a race where someone adding it again to rq before marking it as stopped ?
Exactly that, yeah.
Christian.
Andrey
- spin_unlock(&s_entity->rq_lock);
+ spin_lock(&rq->lock); + } + 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);
Will do.
Andrey
On 2/17/21 4:37 PM, Christian König wrote:
Am 17.02.21 um 22:36 schrieb Andrey Grodzovsky:
On 2/17/21 4:32 PM, Christian König wrote:
Am 16.02.21 um 18:07 schrieb Andrey Grodzovsky:
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.
Signed-off-by: Andrey Grodzovsky andrey.grodzovsky@amd.com
drivers/gpu/drm/scheduler/sched_main.c | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+)
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 908b0b5..11abf5d 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -897,9 +897,40 @@ EXPORT_SYMBOL(drm_sched_init); */ void drm_sched_fini(struct drm_gpu_scheduler *sched) { + int i; + struct drm_sched_entity *s_entity; if (sched->thread) kthread_stop(sched->thread); + /* Detach all sched_entites from this scheduler once it's stopped */ + 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;
+ /* Loop this way because rq->lock is taken in drm_sched_rq_remove_entity */ + spin_lock(&rq->lock); + while ((s_entity = list_first_entry_or_null(&rq->entities, + struct drm_sched_entity, + list))) { + spin_unlock(&rq->lock); + drm_sched_rq_remove_entity(rq, s_entity);
+ /* Mark as stopped to reject adding to any new rq */ + spin_lock(&s_entity->rq_lock); + s_entity->stopped = true;
Why not marking it as stopped and then removing it?
Regards, Christian.
You mean just reverse the order of operations here to prevent a race where someone adding it again to rq before marking it as stopped ?
Exactly that, yeah.
Christian.
Andrey
- spin_unlock(&s_entity->rq_lock);
+ spin_lock(&rq->lock); + } + 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);
dri-devel@lists.freedesktop.org
-
Andrey Grodzovsky -
Andrey Grodzovsky
-
Christian König