[PATCH 08/11] drm/amd: use scheduler to recover hw jobs

[Chunming Zhou]

The old way is trying to recover hw jobs directly, which will conflict
with scheduler thread.

Change-Id: I9e45abd43ae280a675b0b0d88a820106dea2716c
Signed-off-by: Chunming Zhou <David1.Zhou at amd.com>
---
 drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 48 +++++++++------------------
 1 file changed, 16 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
index 36f5805..9f4fa6e 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
@@ -324,10 +324,12 @@ amd_sched_entity_pop_job(struct amd_sched_entity *entity)
  *
  * Returns true if we could submit the job.
  */
-static bool amd_sched_entity_in(struct amd_sched_job *sched_job)
+static bool amd_sched_entity_in_or_recover(struct amd_sched_job *sched_job,
+					   bool recover)
 {
 	struct amd_gpu_scheduler *sched = sched_job->sched;
-	struct amd_sched_entity *entity = sched_job->s_entity;
+	struct amd_sched_entity *entity = recover ? &sched->recover_entity :
+		sched_job->s_entity;
 	bool added, first = false;
 
 	spin_lock(&entity->queue_lock);
@@ -348,6 +350,15 @@ static bool amd_sched_entity_in(struct amd_sched_job *sched_job)
 	return added;
 }
 
+static void amd_sched_entity_push_job_recover(struct amd_sched_job *sched_job)
+{
+	struct amd_sched_entity *entity = sched_job->s_entity;
+
+	trace_amd_sched_job(sched_job);
+	wait_event(entity->sched->job_scheduled,
+		   amd_sched_entity_in_or_recover(sched_job, true));
+}
+
 /* job_finish is called after hw fence signaled, and
  * the job had already been deleted from ring_mirror_list
  */
@@ -426,39 +437,12 @@ void amd_sched_hw_job_reset(struct amd_gpu_scheduler *sched)
 void amd_sched_job_recovery(struct amd_gpu_scheduler *sched)
 {
 	struct amd_sched_job *s_job, *tmp;
-	int r;
 
 	spin_lock(&sched->job_list_lock);
-	s_job = list_first_entry_or_null(&sched->ring_mirror_list,
-					 struct amd_sched_job, node);
-	if (s_job)
-		schedule_delayed_work(&s_job->work_tdr, sched->timeout);
-
 	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
-		struct amd_sched_fence *s_fence = s_job->s_fence;
-		struct fence *fence, *dependency;
-
+		list_del_init(&s_job->node);
 		spin_unlock(&sched->job_list_lock);
-		while ((dependency = sched->ops->dependency(s_job))) {
-		       fence_wait(dependency, false);
-		       fence_put(dependency);
-		}
-		fence = sched->ops->run_job(s_job);
-		atomic_inc(&sched->hw_rq_count);
-		if (fence) {
-			s_fence->parent = fence_get(fence);
-			r = fence_add_callback(fence, &s_fence->cb,
-					       amd_sched_process_job);
-			if (r == -ENOENT)
-				amd_sched_process_job(fence, &s_fence->cb);
-			else if (r)
-				DRM_ERROR("fence add callback failed (%d)\n",
-					  r);
-			fence_put(fence);
-		} else {
-			DRM_ERROR("Failed to run job!\n");
-			amd_sched_process_job(NULL, &s_fence->cb);
-		}
+		amd_sched_entity_push_job_recover(s_job);
 		spin_lock(&sched->job_list_lock);
 	}
 	spin_unlock(&sched->job_list_lock);
@@ -479,7 +463,7 @@ void amd_sched_entity_push_job(struct amd_sched_job *sched_job)
 	fence_add_callback(&sched_job->s_fence->finished, &sched_job->finish_cb,
 			   amd_sched_job_finish_cb);
 	wait_event(entity->sched->job_scheduled,
-		   amd_sched_entity_in(sched_job));
+		   amd_sched_entity_in_or_recover(sched_job, false));
 }
 
 /* init a sched_job with basic field */
-- 
1.9.1