Adding upstream version 6.7.7.upstream/6.7.7

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

2 files changed, 78 insertions, 17 deletions

diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index a42763e14..0a7a7e4ad 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -75,8 +75,23 @@ int drm_sched_entity_init(struct drm_sched_entity *entity,
 	RCU_INIT_POINTER(entity->last_scheduled, NULL);
 	RB_CLEAR_NODE(&entity->rb_tree_node);
 
-	if(num_sched_list)
-		entity->rq = &sched_list[0]->sched_rq[entity->priority];
+	if (!sched_list[0]->sched_rq) {
+		/* Warn drivers not to do this and to fix their DRM
+		 * calling order.
+		 */
+		pr_warn("%s: called with uninitialized scheduler\n", __func__);
+	} else if (num_sched_list) {
+		/* The "priority" of an entity cannot exceed the number of run-queues of a
+		 * scheduler. Protect against num_rqs being 0, by converting to signed.
+		 */
+		if (entity->priority >= sched_list[0]->num_rqs) {
+			drm_err(sched_list[0], "entity with out-of-bounds priority:%u num_rqs:%u\n",
+				entity->priority, sched_list[0]->num_rqs);
+			entity->priority = max_t(s32, (s32) sched_list[0]->num_rqs - 1,
+						 (s32) DRM_SCHED_PRIORITY_MIN);
+		}
+		entity->rq = sched_list[0]->sched_rq[entity->priority];
+	}
 
 	init_completion(&entity->entity_idle);
 
@@ -533,7 +548,7 @@ void drm_sched_entity_select_rq(struct drm_sched_entity *entity)
 
 	spin_lock(&entity->rq_lock);
 	sched = drm_sched_pick_best(entity->sched_list, entity->num_sched_list);
-	rq = sched ? &sched->sched_rq[entity->priority] : NULL;
+	rq = sched ? sched->sched_rq[entity->priority] : NULL;
 	if (rq != entity->rq) {
 		drm_sched_rq_remove_entity(entity->rq, entity);
 		entity->rq = rq;
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 5a3a622fc..99797a8c8 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -632,8 +632,14 @@ int drm_sched_job_init(struct drm_sched_job *job,
 		       struct drm_sched_entity *entity,
 		       void *owner)
 {
-	if (!entity->rq)
+	if (!entity->rq) {
+		/* This will most likely be followed by missing frames
+		 * or worse--a blank screen--leave a trail in the
+		 * logs, so this can be debugged easier.
+		 */
+		drm_err(job->sched, "%s: entity has no rq!\n", __func__);
 		return -ENOENT;
+	}
 
 	job->entity = entity;
 	job->s_fence = drm_sched_fence_alloc(entity, owner);
@@ -671,7 +677,7 @@ void drm_sched_job_arm(struct drm_sched_job *job)
 	sched = entity->rq->sched;
 
 	job->sched = sched;
-	job->s_priority = entity->rq - sched->sched_rq;
+	job->s_priority = entity->priority;
 	job->id = atomic64_inc_return(&sched->job_id_count);
 
 	drm_sched_fence_init(job->s_fence, job->entity);
@@ -888,10 +894,10 @@ drm_sched_select_entity(struct drm_gpu_scheduler *sched)
 		return NULL;
 
 	/* Kernel run queue has higher priority than normal run queue*/
-	for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
+	for (i = sched->num_rqs - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
 		entity = drm_sched_policy == DRM_SCHED_POLICY_FIFO ?
-			drm_sched_rq_select_entity_fifo(&sched->sched_rq[i]) :
-			drm_sched_rq_select_entity_rr(&sched->sched_rq[i]);
+			drm_sched_rq_select_entity_fifo(sched->sched_rq[i]) :
+			drm_sched_rq_select_entity_rr(sched->sched_rq[i]);
 		if (entity)
 			break;
 	}
@@ -1071,6 +1077,7 @@ static int drm_sched_main(void *param)
  *
  * @sched: scheduler instance
  * @ops: backend operations for this scheduler
+ * @num_rqs: number of runqueues, one for each priority, up to DRM_SCHED_PRIORITY_COUNT
  * @hw_submission: number of hw submissions that can be in flight
  * @hang_limit: number of times to allow a job to hang before dropping it
  * @timeout: timeout value in jiffies for the scheduler
@@ -1084,11 +1091,12 @@ static int drm_sched_main(void *param)
  */
 int drm_sched_init(struct drm_gpu_scheduler *sched,
 		   const struct drm_sched_backend_ops *ops,
-		   unsigned hw_submission, unsigned hang_limit,
+		   u32 num_rqs, uint32_t hw_submission, unsigned int hang_limit,
 		   long timeout, struct workqueue_struct *timeout_wq,
 		   atomic_t *score, const char *name, struct device *dev)
 {
 	int i, ret;
+
 	sched->ops = ops;
 	sched->hw_submission_limit = hw_submission;
 	sched->name = name;
@@ -1097,8 +1105,36 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 	sched->hang_limit = hang_limit;
 	sched->score = score ? score : &sched->_score;
 	sched->dev = dev;
-	for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_COUNT; i++)
-		drm_sched_rq_init(sched, &sched->sched_rq[i]);
+
+	if (num_rqs > DRM_SCHED_PRIORITY_COUNT) {
+		/* This is a gross violation--tell drivers what the  problem is.
+		 */
+		drm_err(sched, "%s: num_rqs cannot be greater than DRM_SCHED_PRIORITY_COUNT\n",
+			__func__);
+		return -EINVAL;
+	} else if (sched->sched_rq) {
+		/* Not an error, but warn anyway so drivers can
+		 * fine-tune their DRM calling order, and return all
+		 * is good.
+		 */
+		drm_warn(sched, "%s: scheduler already initialized!\n", __func__);
+		return 0;
+	}
+
+	sched->sched_rq = kmalloc_array(num_rqs, sizeof(*sched->sched_rq),
+					GFP_KERNEL | __GFP_ZERO);
+	if (!sched->sched_rq) {
+		drm_err(sched, "%s: out of memory for sched_rq\n", __func__);
+		return -ENOMEM;
+	}
+	sched->num_rqs = num_rqs;
+	ret = -ENOMEM;
+	for (i = DRM_SCHED_PRIORITY_MIN; i < sched->num_rqs; i++) {
+		sched->sched_rq[i] = kzalloc(sizeof(*sched->sched_rq[i]), GFP_KERNEL);
+		if (!sched->sched_rq[i])
+			goto Out_unroll;
+		drm_sched_rq_init(sched, sched->sched_rq[i]);
+	}
 
 	init_waitqueue_head(&sched->wake_up_worker);
 	init_waitqueue_head(&sched->job_scheduled);
@@ -1115,11 +1151,18 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 		ret = PTR_ERR(sched->thread);
 		sched->thread = NULL;
 		DRM_DEV_ERROR(sched->dev, "Failed to create scheduler for %s.\n", name);
-		return ret;
+		goto Out_unroll;
 	}
 
 	sched->ready = true;
 	return 0;
+Out_unroll:
+	for (--i ; i >= DRM_SCHED_PRIORITY_MIN; i--)
+		kfree(sched->sched_rq[i]);
+	kfree(sched->sched_rq);
+	sched->sched_rq = NULL;
+	drm_err(sched, "%s: Failed to setup GPU scheduler--out of memory\n", __func__);
+	return ret;
 }
 EXPORT_SYMBOL(drm_sched_init);
 
@@ -1138,8 +1181,8 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched)
 	if (sched->thread)
 		kthread_stop(sched->thread);
 
-	for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
-		struct drm_sched_rq *rq = &sched->sched_rq[i];
+	for (i = sched->num_rqs - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
+		struct drm_sched_rq *rq = sched->sched_rq[i];
 
 		spin_lock(&rq->lock);
 		list_for_each_entry(s_entity, &rq->entities, list)
@@ -1150,7 +1193,7 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched)
 			 */
 			s_entity->stopped = true;
 		spin_unlock(&rq->lock);
-
+		kfree(sched->sched_rq[i]);
 	}
 
 	/* Wakeup everyone stuck in drm_sched_entity_flush for this scheduler */
@@ -1160,6 +1203,8 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched)
 	cancel_delayed_work_sync(&sched->work_tdr);
 
 	sched->ready = false;
+	kfree(sched->sched_rq);
+	sched->sched_rq = NULL;
 }
 EXPORT_SYMBOL(drm_sched_fini);
 
@@ -1186,9 +1231,10 @@ void drm_sched_increase_karma(struct drm_sched_job *bad)
 	if (bad->s_priority != DRM_SCHED_PRIORITY_KERNEL) {
 		atomic_inc(&bad->karma);
 
-		for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_KERNEL;
+		for (i = DRM_SCHED_PRIORITY_MIN;
+		     i < min_t(typeof(sched->num_rqs), sched->num_rqs, DRM_SCHED_PRIORITY_KERNEL);
 		     i++) {
-			struct drm_sched_rq *rq = &sched->sched_rq[i];
+			struct drm_sched_rq *rq = sched->sched_rq[i];
 
 			spin_lock(&rq->lock);
 			list_for_each_entry_safe(entity, tmp, &rq->entities, list) {