drm/sched: Add boolean to mark if sched is ready to work v5

Problem:
A particular scheduler may become unsuable (underlying HW) after
some event (e.g. GPU reset). If it's later chosen by
the get free sched. policy a command will fail to be
submitted.

Fix:
Add a driver specific callback to report the sched status so
rq with bad sched can be avoided in favor of working one or
none in which case job init will fail.

v2: Switch from driver callback to flag in scheduler.

v3: rebase

v4: Remove ready paramter from drm_sched_init, set
uncoditionally to true once init done.

v5: fix missed change in v3d in v4 (Alex)
Signed-off-by: NAndrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/scheduler/sched_entity.c

@@ -130,7 +130,14 @@ drm_sched_entity_get_free_sched(struct drm_sched_entity *entity)
 	int i;
 
 	for (i = 0; i < entity->num_rq_list; ++i) {
-		num_jobs = atomic_read(&entity->rq_list[i]->sched->num_jobs);
+		struct drm_gpu_scheduler *sched = entity->rq_list[i]->sched;
+
+		if (!entity->rq_list[i]->sched->ready) {
+			DRM_WARN("sched%s is not ready, skipping", sched->name);
+			continue;
+		}
+
+		num_jobs = atomic_read(&sched->num_jobs);
 		if (num_jobs < min_jobs) {
 			min_jobs = num_jobs;
 			rq = entity->rq_list[i];

drivers/gpu/drm/scheduler/sched_main.c

@@ -420,6 +420,9 @@ int drm_sched_job_init(struct drm_sched_job *job,
 	struct drm_gpu_scheduler *sched;
 
 	drm_sched_entity_select_rq(entity);
+	if (!entity->rq)
+		return -ENOENT;
+
 	sched = entity->rq->sched;
 
 	job->sched = sched;
@@ -633,6 +636,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 		return PTR_ERR(sched->thread);
 	}
 
+	sched->ready = true;
 	return 0;
 }
 EXPORT_SYMBOL(drm_sched_init);
@@ -648,5 +652,7 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched)
 {
 	if (sched->thread)
 		kthread_stop(sched->thread);
+
+	sched->ready = false;
 }
 EXPORT_SYMBOL(drm_sched_fini);

include/drm/gpu_scheduler.h

@@ -264,6 +264,7 @@ struct drm_sched_backend_ops {
  * @hang_limit: once the hangs by a job crosses this limit then it is marked
  *              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
  *
  * One scheduler is implemented for each hardware ring.
  */
@@ -283,12 +284,14 @@ struct drm_gpu_scheduler {
 	spinlock_t			job_list_lock;
 	int				hang_limit;
 	atomic_t                        num_jobs;
+	bool			ready;
 };
 
 int drm_sched_init(struct drm_gpu_scheduler *sched,
 		   const struct drm_sched_backend_ops *ops,
 		   uint32_t hw_submission, unsigned hang_limit, long timeout,
 		   const char *name);
+
 void drm_sched_fini(struct drm_gpu_scheduler *sched);
 int drm_sched_job_init(struct drm_sched_job *job,
 		       struct drm_sched_entity *entity,