* [PATCH] drm/scheduler: use job count instead of peek
@ 2019-08-09 15:31 Christian König
2019-08-12 15:53 ` Grodzovsky, Andrey
2019-08-13 7:58 ` Liu, Monk
0 siblings, 2 replies; 3+ messages in thread
From: Christian König @ 2019-08-09 15:31 UTC (permalink / raw)
To: andrey.grodzovsky, dri-devel, Monk.Liu, Emily.Deng
The spsc_queue_peek function is accessing queue->head which belongs to
the consumer thread and shouldn't be accessed by the producer
This is fixing a rare race condition when destroying entities.
Signed-off-by: Christian König <christian.koenig@amd.com>
---
drivers/gpu/drm/scheduler/sched_entity.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 35ddbec1375a..671c90f34ede 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -95,7 +95,7 @@ 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_peek(&entity->job_queue) == NULL)
+ spsc_queue_count(&entity->job_queue) == 0)
return true;
return false;
@@ -281,7 +281,7 @@ void drm_sched_entity_fini(struct drm_sched_entity *entity)
/* Consumption of existing IBs wasn't completed. Forcefully
* remove them here.
*/
- if (spsc_queue_peek(&entity->job_queue)) {
+ if (spsc_queue_count(&entity->job_queue)) {
if (sched) {
/* Park the kernel for a moment to make sure it isn't processing
* our enity.
--
2.17.1
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [PATCH] drm/scheduler: use job count instead of peek
2019-08-09 15:31 [PATCH] drm/scheduler: use job count instead of peek Christian König
@ 2019-08-12 15:53 ` Grodzovsky, Andrey
2019-08-13 7:58 ` Liu, Monk
1 sibling, 0 replies; 3+ messages in thread
From: Grodzovsky, Andrey @ 2019-08-12 15:53 UTC (permalink / raw)
To: Christian König, dri-devel, Liu, Monk, Deng, Emily
Acked-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Andrey
On 8/9/19 11:31 AM, Christian König wrote:
> The spsc_queue_peek function is accessing queue->head which belongs to
> the consumer thread and shouldn't be accessed by the producer
>
> This is fixing a rare race condition when destroying entities.
>
> Signed-off-by: Christian König <christian.koenig@amd.com>
> ---
> drivers/gpu/drm/scheduler/sched_entity.c | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
> index 35ddbec1375a..671c90f34ede 100644
> --- a/drivers/gpu/drm/scheduler/sched_entity.c
> +++ b/drivers/gpu/drm/scheduler/sched_entity.c
> @@ -95,7 +95,7 @@ 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_peek(&entity->job_queue) == NULL)
> + spsc_queue_count(&entity->job_queue) == 0)
> return true;
>
> return false;
> @@ -281,7 +281,7 @@ void drm_sched_entity_fini(struct drm_sched_entity *entity)
> /* Consumption of existing IBs wasn't completed. Forcefully
> * remove them here.
> */
> - if (spsc_queue_peek(&entity->job_queue)) {
> + if (spsc_queue_count(&entity->job_queue)) {
> if (sched) {
> /* Park the kernel for a moment to make sure it isn't processing
> * our enity.
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
^ permalink raw reply [flat|nested] 3+ messages in thread
* RE: [PATCH] drm/scheduler: use job count instead of peek
2019-08-09 15:31 [PATCH] drm/scheduler: use job count instead of peek Christian König
2019-08-12 15:53 ` Grodzovsky, Andrey
@ 2019-08-13 7:58 ` Liu, Monk
1 sibling, 0 replies; 3+ messages in thread
From: Liu, Monk @ 2019-08-13 7:58 UTC (permalink / raw)
To: Christian König, Grodzovsky, Andrey, dri-devel, Deng, Emily
Reviewed-by: Monk.liu@amd.com
_____________________________________
Monk Liu|GPU Virtualization Team |AMD
-----Original Message-----
From: Christian König <ckoenig.leichtzumerken@gmail.com>
Sent: Friday, August 9, 2019 11:31 PM
To: Grodzovsky, Andrey <Andrey.Grodzovsky@amd.com>; dri-devel@lists.freedesktop.org; Liu, Monk <Monk.Liu@amd.com>; Deng, Emily <Emily.Deng@amd.com>
Subject: [PATCH] drm/scheduler: use job count instead of peek
The spsc_queue_peek function is accessing queue->head which belongs to the consumer thread and shouldn't be accessed by the producer
This is fixing a rare race condition when destroying entities.
Signed-off-by: Christian König <christian.koenig@amd.com>
---
drivers/gpu/drm/scheduler/sched_entity.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 35ddbec1375a..671c90f34ede 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -95,7 +95,7 @@ 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_peek(&entity->job_queue) == NULL)
+ spsc_queue_count(&entity->job_queue) == 0)
return true;
return false;
@@ -281,7 +281,7 @@ void drm_sched_entity_fini(struct drm_sched_entity *entity)
/* Consumption of existing IBs wasn't completed. Forcefully
* remove them here.
*/
- if (spsc_queue_peek(&entity->job_queue)) {
+ if (spsc_queue_count(&entity->job_queue)) {
if (sched) {
/* Park the kernel for a moment to make sure it isn't processing
* our enity.
--
2.17.1
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
^ permalink raw reply related [flat|nested] 3+ messages in thread
end of thread, other threads:[~2019-08-13 7:58 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-08-09 15:31 [PATCH] drm/scheduler: use job count instead of peek Christian König
2019-08-12 15:53 ` Grodzovsky, Andrey
2019-08-13 7:58 ` Liu, Monk
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.