drm/scheduler: rework job destruction

We now destroy finished jobs from the worker thread to make sure that
we never destroy a job currently in timeout processing.
By this we avoid holding lock around ring mirror list in drm_sched_stop
which should solve a deadlock reported by a user.

v2: Remove unused variable.
v4: Move guilty job free into sched code.
v5:
Move sched->hw_rq_count to drm_sched_start to account for counter
decrement in drm_sched_stop even when we don't call resubmit jobs
if guily job did signal.
v6: remove unused variable

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=109692

Acked-by: Chunming Zhou <[e-mail]>
Signed-off-by: Christian König <[e-mail]>
Signed-off-by: Andrey Grodzovsky <[e-mail]>
Signed-off-by: Alex Deucher <[e-mail]>
Link: https://patchwork.freedesktop.org/patch/msgid/[e-mail]

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

···
 		if (!ring || !ring->sched.thread)
 			continue;
 
-		drm_sched_stop(&ring->sched);
+		drm_sched_stop(&ring->sched, &job->base);
 
 		/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
 		amdgpu_fence_driver_force_completion(ring);
···
 
 	if(job)
 		drm_sched_increase_karma(&job->base);
-
-
 
 	if (!amdgpu_sriov_vf(adev)) {
 
···
 	return r;
 }
 
-static void amdgpu_device_post_asic_reset(struct amdgpu_device *adev,
-					  struct amdgpu_job *job)
+static void amdgpu_device_post_asic_reset(struct amdgpu_device *adev)
 {
 	int i;
 
···
 
 	/* Post ASIC reset for all devs .*/
 	list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
-		amdgpu_device_post_asic_reset(tmp_adev, tmp_adev == adev ? job : NULL);
+		amdgpu_device_post_asic_reset(tmp_adev);
 
 		if (r) {
 			/* bad news, how to tell it to userspace ? */

drivers/gpu/drm/etnaviv/etnaviv_dump.c

···
 	unsigned int n_obj, n_bomap_pages;
 	size_t file_size, mmu_size;
 	__le64 *bomap, *bomap_start;
-	unsigned long flags;
 
 	/* Only catch the first event, or when manually re-armed */
 	if (!etnaviv_dump_core)
···
 		    mmu_size + gpu->buffer.size;
 
 	/* Add in the active command buffers */
-	spin_lock_irqsave(&gpu->sched.job_list_lock, flags);
 	list_for_each_entry(s_job, &gpu->sched.ring_mirror_list, node) {
 		submit = to_etnaviv_submit(s_job);
 		file_size += submit->cmdbuf.size;
 		n_obj++;
 	}
-	spin_unlock_irqrestore(&gpu->sched.job_list_lock, flags);
 
 	/* Add in the active buffer objects */
 	list_for_each_entry(vram, &gpu->mmu->mappings, mmu_node) {
···
 			      gpu->buffer.size,
 			      etnaviv_cmdbuf_get_va(&gpu->buffer));
 
-	spin_lock_irqsave(&gpu->sched.job_list_lock, flags);
 	list_for_each_entry(s_job, &gpu->sched.ring_mirror_list, node) {
 		submit = to_etnaviv_submit(s_job);
 		etnaviv_core_dump_mem(&iter, ETDUMP_BUF_CMD,
 				      submit->cmdbuf.vaddr, submit->cmdbuf.size,
 				      etnaviv_cmdbuf_get_va(&submit->cmdbuf));
 	}
-	spin_unlock_irqrestore(&gpu->sched.job_list_lock, flags);
 
 	/* Reserve space for the bomap */
 	if (n_bomap_pages) {

drivers/gpu/drm/etnaviv/etnaviv_sched.c

···
 	}
 
 	/* block scheduler */
-	drm_sched_stop(&gpu->sched);
+	drm_sched_stop(&gpu->sched, sched_job);
 
 	if(sched_job)
 		drm_sched_increase_karma(sched_job);

drivers/gpu/drm/lima/lima_sched.c

···
 static void lima_sched_handle_error_task(struct lima_sched_pipe *pipe,
 					 struct lima_sched_task *task)
 {
-	drm_sched_stop(&pipe->base);
+	drm_sched_stop(&pipe->base, &task->base);
 
 	if (task)
 		drm_sched_increase_karma(&task->base);

drivers/gpu/drm/panfrost/panfrost_job.c

···
 	mutex_lock(&pfdev->reset_lock);
 
 	for (i = 0; i < NUM_JOB_SLOTS; i++)
-		drm_sched_stop(&pfdev->js->queue[i].sched);
+		drm_sched_stop(&pfdev->js->queue[i].sched, sched_job);
 
 	if (sched_job)
 		drm_sched_increase_karma(sched_job);

drivers/gpu/drm/scheduler/sched_main.c

···
 }
 EXPORT_SYMBOL(drm_sched_resume_timeout);
 
-/* job_finish is called after hw fence signaled
- */
-static void drm_sched_job_finish(struct work_struct *work)
-{
-	struct drm_sched_job *s_job = container_of(work, struct drm_sched_job,
-						   finish_work);
-	struct drm_gpu_scheduler *sched = s_job->sched;
-	unsigned long flags;
-
-	/*
-	 * Canceling the timeout without removing our job from the ring mirror
-	 * list is safe, as we will only end up in this worker if our jobs
-	 * finished fence has been signaled. So even if some another worker
-	 * 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(&sched->work_tdr);
-
-	spin_lock_irqsave(&sched->job_list_lock, flags);
-	/* queue TDR for next job */
-	drm_sched_start_timeout(sched);
-	spin_unlock_irqrestore(&sched->job_list_lock, flags);
-
-	sched->ops->free_job(s_job);
-}
-
 static void drm_sched_job_begin(struct drm_sched_job *s_job)
 {
 	struct drm_gpu_scheduler *sched = s_job->sched;
···
 
 	if (job)
 		job->sched->ops->timedout_job(job);
+
+	/*
+	 * Guilty job did complete and hence needs to be manually removed
+	 * See drm_sched_stop doc.
+	 */
+	if (list_empty(&job->node))
+		job->sched->ops->free_job(job);
 
 	spin_lock_irqsave(&sched->job_list_lock, flags);
 	drm_sched_start_timeout(sched);
···
  * @sched: scheduler instance
  * @bad: bad scheduler job
  *
+ * Stop the scheduler and also removes and frees all completed jobs.
+ * Note: bad job will not be freed as it might be used later and so it's
+ * callers responsibility to release it manually if it's not part of the
+ * mirror list any more.
+ *
  */
-void drm_sched_stop(struct drm_gpu_scheduler *sched)
+void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad)
 {
-	struct drm_sched_job *s_job;
+	struct drm_sched_job *s_job, *tmp;
 	unsigned long flags;
-	struct dma_fence *last_fence =  NULL;
 
 	kthread_park(sched->thread);
 
 	/*
-	 * Verify all the signaled jobs in mirror list are removed from the ring
-	 * by waiting for the latest job to enter the list. This should insure that
-	 * also all the previous jobs that were in flight also already singaled
-	 * and removed from the list.
+	 * Iterate the job list from later to  earlier one and either deactive
+	 * their HW callbacks or remove them from mirror list if they already
+	 * signaled.
+	 * This iteration is thread safe as sched thread is stopped.
 	 */
-	spin_lock_irqsave(&sched->job_list_lock, flags);
-	list_for_each_entry_reverse(s_job, &sched->ring_mirror_list, node) {
+	list_for_each_entry_safe_reverse(s_job, tmp, &sched->ring_mirror_list, node) {
 		if (s_job->s_fence->parent &&
 		    dma_fence_remove_callback(s_job->s_fence->parent,
 					      &s_job->cb)) {
···
 			s_job->s_fence->parent = NULL;
 			atomic_dec(&sched->hw_rq_count);
 		} else {
-			 last_fence = dma_fence_get(&s_job->s_fence->finished);
-			 break;
-		}
-	}
-	spin_unlock_irqrestore(&sched->job_list_lock, flags);
+			/*
+			 * remove job from ring_mirror_list.
+			 * Locking here is for concurrent resume timeout
+			 */
+			spin_lock_irqsave(&sched->job_list_lock, flags);
+			list_del_init(&s_job->node);
+			spin_unlock_irqrestore(&sched->job_list_lock, flags);
 
-	if (last_fence) {
-		dma_fence_wait(last_fence, false);
-		dma_fence_put(last_fence);
+			/*
+			 * Wait for job's HW fence callback to finish using s_job
+			 * before releasing it.
+			 *
+			 * Job is still alive so fence refcount at least 1
+			 */
+			dma_fence_wait(&s_job->s_fence->finished, false);
+
+			/*
+			 * We must keep bad job alive for later use during
+			 * recovery by some of the drivers
+			 */
+			if (bad != s_job)
+				sched->ops->free_job(s_job);
+		}
 	}
 }
 
···
 void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery)
 {
 	struct drm_sched_job *s_job, *tmp;
+	unsigned long flags;
 	int r;
-
-	if (!full_recovery)
-		goto unpark;
 
 	/*
 	 * Locking the list is not required here as the sched thread is parked
-	 * so no new jobs are being pushed in to HW and in drm_sched_stop we
-	 * flushed all the jobs who were still in mirror list but who already
-	 * signaled and removed them self from the list. Also concurrent
+	 * so no new jobs are being inserted or removed. Also concurrent
 	 * GPU recovers can't run in parallel.
 	 */
 	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
 		struct dma_fence *fence = s_job->s_fence->parent;
+
+		atomic_inc(&sched->hw_rq_count);
+
+		if (!full_recovery)
+			continue;
 
 		if (fence) {
 			r = dma_fence_add_callback(fence, &s_job->cb,
···
 			drm_sched_process_job(NULL, &s_job->cb);
 	}
 
-	drm_sched_start_timeout(sched);
+	if (full_recovery) {
+		spin_lock_irqsave(&sched->job_list_lock, flags);
+		drm_sched_start_timeout(sched);
+		spin_unlock_irqrestore(&sched->job_list_lock, flags);
+	}
 
-unpark:
 	kthread_unpark(sched->thread);
 }
 EXPORT_SYMBOL(drm_sched_start);
···
 	uint64_t guilty_context;
 	bool found_guilty = false;
 
-	/*TODO DO we need spinlock here ? */
 	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
 		struct drm_sched_fence *s_fence = s_job->s_fence;
 
···
 			dma_fence_set_error(&s_fence->finished, -ECANCELED);
 
 		s_job->s_fence->parent = sched->ops->run_job(s_job);
-		atomic_inc(&sched->hw_rq_count);
 	}
 }
 EXPORT_SYMBOL(drm_sched_resubmit_jobs);
···
 		return -ENOMEM;
 	job->id = atomic64_inc_return(&sched->job_id_count);
 
-	INIT_WORK(&job->finish_work, drm_sched_job_finish);
 	INIT_LIST_HEAD(&job->node);
 
 	return 0;
···
 	struct drm_sched_job *s_job = container_of(cb, struct drm_sched_job, cb);
 	struct drm_sched_fence *s_fence = s_job->s_fence;
 	struct drm_gpu_scheduler *sched = s_fence->sched;
-	unsigned long flags;
-
-	cancel_delayed_work(&sched->work_tdr);
 
 	atomic_dec(&sched->hw_rq_count);
 	atomic_dec(&sched->num_jobs);
 
-	spin_lock_irqsave(&sched->job_list_lock, flags);
-	/* remove job from ring_mirror_list */
-	list_del_init(&s_job->node);
-	spin_unlock_irqrestore(&sched->job_list_lock, flags);
+	trace_drm_sched_process_job(s_fence);
 
 	drm_sched_fence_finished(s_fence);
-
-	trace_drm_sched_process_job(s_fence);
 	wake_up_interruptible(&sched->wake_up_worker);
+}
 
-	schedule_work(&s_job->finish_work);
+/**
+ * drm_sched_cleanup_jobs - destroy finished jobs
+ *
+ * @sched: scheduler instance
+ *
+ * Remove all finished jobs from the mirror list and destroy them.
+ */
+static void drm_sched_cleanup_jobs(struct drm_gpu_scheduler *sched)
+{
+	unsigned long flags;
+
+	/* Don't destroy jobs while the timeout worker is running */
+	if (!cancel_delayed_work(&sched->work_tdr))
+		return;
+
+
+	while (!list_empty(&sched->ring_mirror_list)) {
+		struct drm_sched_job *job;
+
+		job = list_first_entry(&sched->ring_mirror_list,
+				       struct drm_sched_job, node);
+		if (!dma_fence_is_signaled(&job->s_fence->finished))
+			break;
+
+		spin_lock_irqsave(&sched->job_list_lock, flags);
+		/* remove job from ring_mirror_list */
+		list_del_init(&job->node);
+		spin_unlock_irqrestore(&sched->job_list_lock, flags);
+
+		sched->ops->free_job(job);
+	}
+
+	/* queue timeout for next job */
+	spin_lock_irqsave(&sched->job_list_lock, flags);
+	drm_sched_start_timeout(sched);
+	spin_unlock_irqrestore(&sched->job_list_lock, flags);
+
 }
 
 /**
···
 		struct dma_fence *fence;
 
 		wait_event_interruptible(sched->wake_up_worker,
+					 (drm_sched_cleanup_jobs(sched),
 					 (!drm_sched_blocked(sched) &&
 					  (entity = drm_sched_select_entity(sched))) ||
-					 kthread_should_stop());
+					 kthread_should_stop()));
 
 		if (!entity)
 			continue;

drivers/gpu/drm/v3d/v3d_sched.c

···
 
 	/* block scheduler */
 	for (q = 0; q < V3D_MAX_QUEUES; q++)
-		drm_sched_stop(&v3d->queue[q].sched);
+		drm_sched_stop(&v3d->queue[q].sched, sched_job);
 
 	if (sched_job)
 		drm_sched_increase_karma(sched_job);

include/drm/gpu_scheduler.h

···
  * @sched: the scheduler instance on which this job is scheduled.
  * @s_fence: contains the fences for the scheduling of job.
  * @finish_cb: the callback for the finished fence.
- * @finish_work: schedules the function @drm_sched_job_finish once the job has
- *               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.
  * @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
···
 	struct drm_gpu_scheduler	*sched;
 	struct drm_sched_fence		*s_fence;
 	struct dma_fence_cb		finish_cb;
-	struct work_struct		finish_work;
 	struct list_head		node;
 	uint64_t			id;
 	atomic_t			karma;
···
 		       void *owner);
 void drm_sched_job_cleanup(struct drm_sched_job *job);
 void drm_sched_wakeup(struct drm_gpu_scheduler *sched);
-void drm_sched_stop(struct drm_gpu_scheduler *sched);
+void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad);
 void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery);
 void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched);
 void drm_sched_increase_karma(struct drm_sched_job *bad);