drm/sched: Refactor ring mirror list handling.

Decauple sched threads stop and start and ring mirror
list handling from the policy of what to do about the
guilty jobs.
When stoppping the sched thread and detaching sched fences
from non signaled HW fenes wait for all signaled HW fences
to complete before rerunning the jobs.

v2: Fix resubmission of guilty job into HW after refactoring.

v4:
Full restart for all the jobs, not only from guilty ring.
Extract karma increase into standalone function.

v5:
Rework waiting for signaled jobs without relying on the job
struct itself as those might already be freed for non 'guilty'
job's schedulers.
Expose karma increase to drivers.

v6:
Use list_for_each_entry_safe_continue and drm_sched_process_job
in case fence already signaled.
Call drm_sched_increase_karma only once for amdgpu and add documentation.

v7:
Wait only for the latest job's fence.

Suggested-by: Christian Koenig <Christian.Koenig@amd.com>
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 105 insertions, 65 deletions

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index dbb69063b3d5..4bb18511ac75 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -60,8 +60,6 @@
 
 static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb);
 
-static void drm_sched_expel_job_unlocked(struct drm_sched_job *s_job);
-
 /**
  * drm_sched_rq_init - initialize a given run queue struct
  *
@@ -335,6 +333,51 @@ static void drm_sched_job_timedout(struct work_struct *work)
 	spin_unlock_irqrestore(&sched->job_list_lock, flags);
 }
 
+ /**
+  * drm_sched_increase_karma - Update sched_entity guilty flag
+  *
+  * @bad: The job guilty of time out
+  *
+  * Increment on every hang caused by the 'bad' job. If this exceeds the hang
+  * limit of the scheduler then the respective sched entity is marked guilty and
+  * jobs from it will not be scheduled further
+  */
+void drm_sched_increase_karma(struct drm_sched_job *bad)
+{
+	int i;
+	struct drm_sched_entity *tmp;
+	struct drm_sched_entity *entity;
+	struct drm_gpu_scheduler *sched = bad->sched;
+
+	/* don't increase @bad's karma if it's from KERNEL RQ,
+	 * because sometimes GPU hang would cause kernel jobs (like VM updating jobs)
+	 * corrupt but keep in mind that kernel jobs always considered good.
+	 */
+	if (bad->s_priority != DRM_SCHED_PRIORITY_KERNEL) {
+		atomic_inc(&bad->karma);
+		for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_KERNEL;
+		     i++) {
+			struct drm_sched_rq *rq = &sched->sched_rq[i];
+
+			spin_lock(&rq->lock);
+			list_for_each_entry_safe(entity, tmp, &rq->entities, list) {
+				if (bad->s_fence->scheduled.context ==
+				    entity->fence_context) {
+					if (atomic_read(&bad->karma) >
+					    bad->sched->hang_limit)
+						if (entity->guilty)
+							atomic_set(entity->guilty, 1);
+					break;
+				}
+			}
+			spin_unlock(&rq->lock);
+			if (&entity->list != &rq->entities)
+				break;
+		}
+	}
+}
+EXPORT_SYMBOL(drm_sched_increase_karma);
+
 /**
  * drm_sched_hw_job_reset - stop the scheduler if it contains the bad job
  *
@@ -342,13 +385,20 @@ static void drm_sched_job_timedout(struct work_struct *work)
  * @bad: bad scheduler job
  *
  */
-void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad)
+void drm_sched_stop(struct drm_gpu_scheduler *sched)
 {
 	struct drm_sched_job *s_job;
-	struct drm_sched_entity *entity, *tmp;
 	unsigned long flags;
-	int i;
+	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.
+	 */
 	spin_lock_irqsave(&sched->job_list_lock, flags);
 	list_for_each_entry_reverse(s_job, &sched->ring_mirror_list, node) {
 		if (s_job->s_fence->parent &&
@@ -357,35 +407,20 @@ void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched, struct drm_sched_jo
 			dma_fence_put(s_job->s_fence->parent);
 			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);
 
-	if (bad && bad->s_priority != DRM_SCHED_PRIORITY_KERNEL) {
-		atomic_inc(&bad->karma);
-		/* don't increase @bad's karma if it's from KERNEL RQ,
-		 * becuase sometimes GPU hang would cause kernel jobs (like VM updating jobs)
-		 * corrupt but keep in mind that kernel jobs always considered good.
-		 */
-		for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_KERNEL; i++ ) {
-			struct drm_sched_rq *rq = &sched->sched_rq[i];
-
-			spin_lock(&rq->lock);
-			list_for_each_entry_safe(entity, tmp, &rq->entities, list) {
-				if (bad->s_fence->scheduled.context == entity->fence_context) {
-				    if (atomic_read(&bad->karma) > bad->sched->hang_limit)
-						if (entity->guilty)
-							atomic_set(entity->guilty, 1);
-					break;
-				}
-			}
-			spin_unlock(&rq->lock);
-			if (&entity->list != &rq->entities)
-				break;
-		}
+	if (last_fence) {
+		dma_fence_wait(last_fence, false);
+		dma_fence_put(last_fence);
 	}
 }
-EXPORT_SYMBOL(drm_sched_hw_job_reset);
+
+EXPORT_SYMBOL(drm_sched_stop);
 
 /**
  * drm_sched_job_recovery - recover jobs after a reset
@@ -393,33 +428,21 @@ EXPORT_SYMBOL(drm_sched_hw_job_reset);
  * @sched: scheduler instance
  *
  */
-void drm_sched_job_recovery(struct drm_gpu_scheduler *sched)
+void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery)
 {
 	struct drm_sched_job *s_job, *tmp;
-	bool found_guilty = false;
 	unsigned long flags;
 	int r;
 
+	if (!full_recovery)
+		goto unpark;
+
 	spin_lock_irqsave(&sched->job_list_lock, flags);
 	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
 		struct drm_sched_fence *s_fence = s_job->s_fence;
-		struct dma_fence *fence;
-		uint64_t guilty_context;
-
-		if (!found_guilty && atomic_read(&s_job->karma) > sched->hang_limit) {
-			found_guilty = true;
-			guilty_context = s_job->s_fence->scheduled.context;
-		}
-
-		if (found_guilty && s_job->s_fence->scheduled.context == guilty_context)
-			dma_fence_set_error(&s_fence->finished, -ECANCELED);
-
-		spin_unlock_irqrestore(&sched->job_list_lock, flags);
-		fence = sched->ops->run_job(s_job);
-		atomic_inc(&sched->hw_rq_count);
+		struct dma_fence *fence = s_job->s_fence->parent;
 
 		if (fence) {
-			s_fence->parent = dma_fence_get(fence);
 			r = dma_fence_add_callback(fence, &s_fence->cb,
 						   drm_sched_process_job);
 			if (r == -ENOENT)
@@ -427,18 +450,47 @@ void drm_sched_job_recovery(struct drm_gpu_scheduler *sched)
 			else if (r)
 				DRM_ERROR("fence add callback failed (%d)\n",
 					  r);
-			dma_fence_put(fence);
-		} else {
-			if (s_fence->finished.error < 0)
-				drm_sched_expel_job_unlocked(s_job);
+		} else
 			drm_sched_process_job(NULL, &s_fence->cb);
-		}
-		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_job_recovery);
+EXPORT_SYMBOL(drm_sched_start);
+
+/**
+ * drm_sched_resubmit_jobs - helper to relunch job from mirror ring list
+ *
+ * @sched: scheduler instance
+ *
+ */
+void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
+{
+	struct drm_sched_job *s_job, *tmp;
+	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;
+
+		if (!found_guilty && atomic_read(&s_job->karma) > sched->hang_limit) {
+			found_guilty = true;
+			guilty_context = s_job->s_fence->scheduled.context;
+		}
+
+		if (found_guilty && s_job->s_fence->scheduled.context == guilty_context)
+			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);
 
 /**
  * drm_sched_job_init - init a scheduler job
@@ -634,26 +686,14 @@ static int drm_sched_main(void *param)
 				DRM_ERROR("fence add callback failed (%d)\n",
 					  r);
 			dma_fence_put(fence);
-		} else {
-			if (s_fence->finished.error < 0)
-				drm_sched_expel_job_unlocked(sched_job);
+		} else
 			drm_sched_process_job(NULL, &s_fence->cb);
-		}
 
 		wake_up(&sched->job_scheduled);
 	}
 	return 0;
 }
 
-static void drm_sched_expel_job_unlocked(struct drm_sched_job *s_job)
-{
-	struct drm_gpu_scheduler *sched = s_job->sched;
-
-	spin_lock(&sched->job_list_lock);
-	list_del_init(&s_job->node);
-	spin_unlock(&sched->job_list_lock);
-}
-
 /**
  * drm_sched_init - Init a gpu scheduler instance
  *