| Message ID | 20210519141407.88444-1-andrey.grodzovsky@amd.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | drm/sched: Avoid data corruptions | expand |
Am 19.05.21 um 16:14 schrieb Andrey Grodzovsky: > Wait for all dependencies of a job to complete before > killing it to avoid data corruptions. > > Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> > --- > drivers/gpu/drm/scheduler/sched_entity.c | 5 +++++ > 1 file changed, 5 insertions(+) > > diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c > index 2e93e881b65f..d5cf61972558 100644 > --- a/drivers/gpu/drm/scheduler/sched_entity.c > +++ b/drivers/gpu/drm/scheduler/sched_entity.c > @@ -222,11 +222,16 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, > static void drm_sched_entity_kill_jobs(struct drm_sched_entity *entity) > { > struct drm_sched_job *job; > + struct dma_fence *f; > int r; > > while ((job = to_drm_sched_job(spsc_queue_pop(&entity->job_queue)))) { > struct drm_sched_fence *s_fence = job->s_fence; > > + /* Wait for all dependencies to avoid data corruptions */ > + while ((f = job->sched->ops->dependency(job, entity))) > + dma_fence_wait(f); > + > drm_sched_fence_scheduled(s_fence); > dma_fence_set_error(&s_fence->finished, -ESRCH); >
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 2e93e881b65f..d5cf61972558 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -222,11 +222,16 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, static void drm_sched_entity_kill_jobs(struct drm_sched_entity *entity) { struct drm_sched_job *job; + struct dma_fence *f; int r; while ((job = to_drm_sched_job(spsc_queue_pop(&entity->job_queue)))) { struct drm_sched_fence *s_fence = job->s_fence; + /* Wait for all dependencies to avoid data corruptions */ + while ((f = job->sched->ops->dependency(job, entity))) + dma_fence_wait(f); + drm_sched_fence_scheduled(s_fence); dma_fence_set_error(&s_fence->finished, -ESRCH);
Wait for all dependencies of a job to complete before killing it to avoid data corruptions. Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> --- drivers/gpu/drm/scheduler/sched_entity.c | 5 +++++ 1 file changed, 5 insertions(+)