drm/scheduler: Add flag to hint the release of guilty job.

Problem:
Sched thread's cleanup function races against TO handler
and removes the guilty job from mirror list and we
have no way of differentiating if the job was removed from within the
TO handler or from the sched thread's clean-up function.

Fix:
Add a flag to scheduler to hint the TO handler that the guilty job needs
to be explicitly released.

v2: whitespace fix

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1555599624-12285-5-git-send-email-andrey.grodzovsky@amd.com

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 03e6bd8a1a42af46baa74fa4ed69eb8d0b92c67b..f8f0e1c190020696e08e62329c41d32e72b932f8 100644 (file)
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -293,8 +293,10 @@ static void drm_sched_job_timedout(struct work_struct *work)
         * Guilty job did complete and hence needs to be manually removed
         * See drm_sched_stop doc.
         */
-       if (list_empty(&job->node))
+       if (sched->free_guilty) {
                job->sched->ops->free_job(job);
+               sched->free_guilty = false;
+       }
 
        spin_lock_irqsave(&sched->job_list_lock, flags);
        drm_sched_start_timeout(sched);
@@ -395,10 +397,13 @@ void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad)
 
                        /*
                         * We must keep bad job alive for later use during
-                        * recovery by some of the drivers
+                        * recovery by some of the drivers but leave a hint
+                        * that the guilty job must be released.
                         */
                        if (bad != s_job)
                                sched->ops->free_job(s_job);
+                       else
+                               sched->free_guilty = true;
                }
        }
 

diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 9ee0f2735d712e760cc36680b1505053f2ac2df8..57b4121c750ae768351900a8a3a6b4899e5628a1 100644 (file)
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -259,6 +259,7 @@ struct drm_sched_backend_ops {
  *              guilty and it will be considered for scheduling further.
  * @num_jobs: the number of jobs in queue in the scheduler
  * @ready: marks if the underlying HW is ready to work
+ * @free_guilty: A hit to time out handler to free the guilty job.
  *
  * One scheduler is implemented for each hardware ring.
  */
@@ -279,6 +280,7 @@ struct drm_gpu_scheduler {
        int                             hang_limit;
        atomic_t                        num_jobs;
        bool                    ready;
+       bool                            free_guilty;
 };
 
 int drm_sched_init(struct drm_gpu_scheduler *sched,