Note which task is using the entity and only kill it if the last user of the entity is killed. This should prevent problems when entities are leaked to child processes.
Signed-off-by: Christian König christian.koenig@amd.com --- drivers/gpu/drm/scheduler/gpu_scheduler.c | 6 +++++- include/drm/gpu_scheduler.h | 1 + 2 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c index 3f2fc5e8242a..f563e4fbb4b6 100644 --- a/drivers/gpu/drm/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c @@ -275,6 +275,7 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout) { struct drm_gpu_scheduler *sched; + struct task_struct *last_user; long ret = timeout;
sched = entity->rq->sched; @@ -295,7 +296,9 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout)
/* For killed process disable any more IBs enqueue right now */ - if ((current->flags & PF_EXITING) && (current->exit_code == SIGKILL)) + last_user = cmpxchg(&entity->last_user, current->group_leader, NULL); + if ((!last_user || last_user == current->group_leader) && + (current->flags & PF_EXITING) && (current->exit_code == SIGKILL)) drm_sched_entity_set_rq(entity, NULL);
return ret; @@ -541,6 +544,7 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job,
trace_drm_sched_job(sched_job, entity);
+ WRITE_ONCE(entity->last_user, current->group_leader); first = spsc_queue_push(&entity->job_queue, &sched_job->queue_node);
/* first job wakes up scheduler */ diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 091b9afcd184..64016446a103 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -85,6 +85,7 @@ struct drm_sched_entity { struct dma_fence_cb cb; atomic_t *guilty; struct dma_fence *last_scheduled; + struct task_struct *last_user; };
/**
On Thu, Jul 26, 2018 at 01:45:54PM +0200, Christian König wrote:
Note which task is using the entity and only kill it if the last user of the entity is killed. This should prevent problems when entities are leaked to child processes.
Signed-off-by: Christian König christian.koenig@amd.com
I am not very familiar with scheduler yet. From code logic, it looks fine for me.
Reviewed-by: Huang Rui ray.huang@amd.com
drivers/gpu/drm/scheduler/gpu_scheduler.c | 6 +++++- include/drm/gpu_scheduler.h | 1 + 2 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c index 3f2fc5e8242a..f563e4fbb4b6 100644 --- a/drivers/gpu/drm/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c @@ -275,6 +275,7 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout) { struct drm_gpu_scheduler *sched;
struct task_struct *last_user; long ret = timeout;
sched = entity->rq->sched;
@@ -295,7 +296,9 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout)
/* For killed process disable any more IBs enqueue right now */
- if ((current->flags & PF_EXITING) && (current->exit_code == SIGKILL))
last_user = cmpxchg(&entity->last_user, current->group_leader, NULL);
if ((!last_user || last_user == current->group_leader) &&
(current->flags & PF_EXITING) && (current->exit_code == SIGKILL))drm_sched_entity_set_rq(entity, NULL);
return ret;
@@ -541,6 +544,7 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job,
trace_drm_sched_job(sched_job, entity);
WRITE_ONCE(entity->last_user, current->group_leader); first = spsc_queue_push(&entity->job_queue, &sched_job->queue_node);
/* first job wakes up scheduler */
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 091b9afcd184..64016446a103 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -85,6 +85,7 @@ struct drm_sched_entity { struct dma_fence_cb cb; atomic_t *guilty; struct dma_fence *last_scheduled;
- struct task_struct *last_user;
};
/**
2.14.1
amd-gfx mailing list amd-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/amd-gfx
On Thu, Jul 26, 2018 at 5:16 PM Christian König < ckoenig.leichtzumerken@gmail.com> wrote:
Note which task is using the entity and only kill it if the last user of the entity is killed. This should prevent problems when entities are leaked to child processes.
Signed-off-by: Christian König christian.koenig@amd.com
drivers/gpu/drm/scheduler/gpu_scheduler.c | 6 +++++- include/drm/gpu_scheduler.h | 1 + 2 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c index 3f2fc5e8242a..f563e4fbb4b6 100644 --- a/drivers/gpu/drm/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c @@ -275,6 +275,7 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout) { struct drm_gpu_scheduler *sched;
struct task_struct *last_user; long ret = timeout; sched = entity->rq->sched;@@ -295,7 +296,9 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout)
/* For killed process disable any more IBs enqueue right now */
if ((current->flags & PF_EXITING) && (current->exit_code ==SIGKILL))
last_user = cmpxchg(&entity->last_user, current->group_leader,NULL);
if ((!last_user || last_user == current->group_leader) &&(current->flags & PF_EXITING) && (current->exit_code ==SIGKILL)) drm_sched_entity_set_rq(entity, NULL);
return ret;@@ -541,6 +544,7 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job,
trace_drm_sched_job(sched_job, entity);
WRITE_ONCE(entity->last_user, current->group_leader); first = spsc_queue_push(&entity->job_queue,&sched_job->queue_node);
/* first job wakes up scheduler */diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 091b9afcd184..64016446a103 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -85,6 +85,7 @@ struct drm_sched_entity { struct dma_fence_cb cb; atomic_t *guilty; struct dma_fence *last_scheduled;
struct task_struct *last_user;
Please add a line regarding this field in the kernel doc comments.
Regards, Nayan
};
/**
2.14.1
dri-devel mailing list dri-devel@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/dri-devel
dri-devel@lists.freedesktop.org
-
Christian König -
Huang Rui -
Nayan Deshmukh