drm/scheduler: remove timeout work_struct from drm_sched_job (v3)

having a delayed work item per job is redundant as we only need one
per scheduler to track the time out the currently executing job.

v2: the first element of the ring mirror list is the currently
executing job so we don't need a additional variable for it

v3: squash in fixes for v3d and etnaviv
Signed-off-by: Nayan Deshmukh <nayan26deshmukh@gmail.com>
Suggested-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/etnaviv/etnaviv_sched.c

@@ -105,7 +105,7 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job)
 	change = dma_addr - gpu->hangcheck_dma_addr;
 	if (change < 0 || change > 16) {
 		gpu->hangcheck_dma_addr = dma_addr;
-		schedule_delayed_work(&sched_job->work_tdr,
+		schedule_delayed_work(&sched_job->sched->work_tdr,
 				      sched_job->sched->timeout);
 		return;
 	}

drivers/gpu/drm/scheduler/sched_main.c

@@ -197,19 +197,15 @@ static void drm_sched_job_finish(struct work_struct *work)
 	 * manages to find this job as the next job in the list, the fence
 	 * signaled check below will prevent the timeout to be restarted.
 	 */
-	cancel_delayed_work_sync(&s_job->work_tdr);
+	cancel_delayed_work_sync(&sched->work_tdr);
 
 	spin_lock(&sched->job_list_lock);
-	/* queue TDR for next job */
-	if (sched->timeout != MAX_SCHEDULE_TIMEOUT &&
-	    !list_is_last(&s_job->node, &sched->ring_mirror_list)) {
-		struct drm_sched_job *next = list_next_entry(s_job, node);
-
-		if (!dma_fence_is_signaled(&next->s_fence->finished))
-			schedule_delayed_work(&next->work_tdr, sched->timeout);
-	}
 	/* remove job from ring_mirror_list */
 	list_del(&s_job->node);
+	/* queue TDR for next job */
+	if (sched->timeout != MAX_SCHEDULE_TIMEOUT &&
+	    !list_empty(&sched->ring_mirror_list))
+		schedule_delayed_work(&sched->work_tdr, sched->timeout);
 	spin_unlock(&sched->job_list_lock);
 
 	dma_fence_put(&s_job->s_fence->finished);
@@ -236,16 +232,21 @@ static void drm_sched_job_begin(struct drm_sched_job *s_job)
 	if (sched->timeout != MAX_SCHEDULE_TIMEOUT &&
 	    list_first_entry_or_null(&sched->ring_mirror_list,
 				     struct drm_sched_job, node) == s_job)
-		schedule_delayed_work(&s_job->work_tdr, sched->timeout);
+		schedule_delayed_work(&sched->work_tdr, sched->timeout);
 	spin_unlock(&sched->job_list_lock);
 }
 
 static void drm_sched_job_timedout(struct work_struct *work)
 {
-	struct drm_sched_job *job = container_of(work, struct drm_sched_job,
-						 work_tdr.work);
+	struct drm_gpu_scheduler *sched;
+	struct drm_sched_job *job;
+
+	sched = container_of(work, struct drm_gpu_scheduler, work_tdr.work);
+	job = list_first_entry_or_null(&sched->ring_mirror_list,
+				       struct drm_sched_job, node);
 
-	job->sched->ops->timedout_job(job);
+	if (job)
+		job->sched->ops->timedout_job(job);
 }
 
 /**
@@ -315,7 +316,7 @@ void drm_sched_job_recovery(struct drm_gpu_scheduler *sched)
 	s_job = list_first_entry_or_null(&sched->ring_mirror_list,
 					 struct drm_sched_job, node);
 	if (s_job && sched->timeout != MAX_SCHEDULE_TIMEOUT)
-		schedule_delayed_work(&s_job->work_tdr, sched->timeout);
+		schedule_delayed_work(&sched->work_tdr, sched->timeout);
 
 	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
 		struct drm_sched_fence *s_fence = s_job->s_fence;
@@ -384,7 +385,6 @@ int drm_sched_job_init(struct drm_sched_job *job,
 
 	INIT_WORK(&job->finish_work, drm_sched_job_finish);
 	INIT_LIST_HEAD(&job->node);
-	INIT_DELAYED_WORK(&job->work_tdr, drm_sched_job_timedout);
 
 	return 0;
 }
@@ -575,6 +575,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 	INIT_LIST_HEAD(&sched->ring_mirror_list);
 	spin_lock_init(&sched->job_list_lock);
 	atomic_set(&sched->hw_rq_count, 0);
+	INIT_DELAYED_WORK(&sched->work_tdr, drm_sched_job_timedout);
 	atomic_set(&sched->num_jobs, 0);
 	atomic64_set(&sched->job_id_count, 0);
 

drivers/gpu/drm/v3d/v3d_sched.c

@@ -168,7 +168,7 @@ v3d_job_timedout(struct drm_sched_job *sched_job)
 		job->timedout_ctca = ctca;
 		job->timedout_ctra = ctra;
 
-		schedule_delayed_work(&job->base.work_tdr,
+		schedule_delayed_work(&job->base.sched->work_tdr,
 				      job->base.sched->timeout);
 		return;
 	}

include/drm/gpu_scheduler.h

@@ -175,8 +175,6 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f);
  *               finished to remove the job from the
  *               @drm_gpu_scheduler.ring_mirror_list.
  * @node: used to append this struct to the @drm_gpu_scheduler.ring_mirror_list.
- * @work_tdr: schedules a delayed call to @drm_sched_job_timedout after the timeout
- *            interval is over.
  * @id: a unique id assigned to each job scheduled on the scheduler.
  * @karma: increment on every hang caused by this job. If this exceeds the hang
  *         limit of the scheduler then the job is marked guilty and will not
@@ -195,7 +193,6 @@ struct drm_sched_job {
 	struct dma_fence_cb		finish_cb;
 	struct work_struct		finish_work;
 	struct list_head		node;
-	struct delayed_work		work_tdr;
 	uint64_t			id;
 	atomic_t			karma;
 	enum drm_sched_priority		s_priority;
@@ -259,6 +256,8 @@ struct drm_sched_backend_ops {
  *                 finished.
  * @hw_rq_count: the number of jobs currently in the hardware queue.
  * @job_id_count: used to assign unique id to the each job.
+ * @work_tdr: schedules a delayed call to @drm_sched_job_timedout after the
+ *            timeout interval is over.
  * @thread: the kthread on which the scheduler which run.
  * @ring_mirror_list: the list of jobs which are currently in the job queue.
  * @job_list_lock: lock to protect the ring_mirror_list.
@@ -278,6 +277,7 @@ struct drm_gpu_scheduler {
 	wait_queue_head_t		job_scheduled;
 	atomic_t			hw_rq_count;
 	atomic64_t			job_id_count;
+	struct delayed_work		work_tdr;
 	struct task_struct		*thread;
 	struct list_head		ring_mirror_list;
 	spinlock_t			job_list_lock;