drm/sched: Further optimise drm_sched_entity_push_job

Having removed one re-lock cycle on the entity->lock in a patch titled
"drm/sched: Optimise drm_sched_entity_push_job", with only a tiny bit
larger refactoring we can do the same optimisation on the rq->lock.
(Currently both drm_sched_rq_add_entity() and
drm_sched_rq_update_fifo_locked() take and release the same lock.)

To achieve this we make drm_sched_rq_update_fifo_locked() and
drm_sched_rq_add_entity() expect the rq->lock to be held.

We also align drm_sched_rq_update_fifo_locked(),
drm_sched_rq_add_entity() and
drm_sched_rq_remove_fifo_locked() function signatures, by adding rq as a
parameter to the latter.

v2:
 * Fix after rebase of the series.
 * Avoid naming inconsistency between drm_sched_rq_add/remove. (Christian)

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Luben Tuikov <ltuikov89@gmail.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Philipp Stanner <pstanner@redhat.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Philipp Stanner <pstanner@redhat.com>
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241016122013.7857-6-tursulin@igalia.com

Author: Tvrtko Ursulin

drivers/gpu/drm/scheduler/sched_entity.c

@@ -515,9 +515,14 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity)
 
 		next = to_drm_sched_job(spsc_queue_peek(&entity->job_queue));
 		if (next) {
+			struct drm_sched_rq *rq;
+
 			spin_lock(&entity->lock);
-			drm_sched_rq_update_fifo_locked(entity,
+			rq = entity->rq;
+			spin_lock(&rq->lock);
+			drm_sched_rq_update_fifo_locked(entity, rq,
 							next->submit_ts);
+			spin_unlock(&rq->lock);
 			spin_unlock(&entity->lock);
 		}
 	}
@@ -616,11 +621,13 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job)
 		rq = entity->rq;
 		sched = rq->sched;
 
+		spin_lock(&rq->lock);
 		drm_sched_rq_add_entity(rq, entity);
 
 		if (drm_sched_policy == DRM_SCHED_POLICY_FIFO)
-			drm_sched_rq_update_fifo_locked(entity, submit_ts);
+			drm_sched_rq_update_fifo_locked(entity, rq, submit_ts);
 
+		spin_unlock(&rq->lock);
 		spin_unlock(&entity->lock);
 
 		drm_sched_wakeup(sched);

drivers/gpu/drm/scheduler/sched_main.c

@@ -153,35 +153,33 @@ static __always_inline bool drm_sched_entity_compare_before(struct rb_node *a,
 	return ktime_before(ent_a->oldest_job_waiting, ent_b->oldest_job_waiting);
 }
 
-static inline void drm_sched_rq_remove_fifo_locked(struct drm_sched_entity *entity)
+static void drm_sched_rq_remove_fifo_locked(struct drm_sched_entity *entity,
+					    struct drm_sched_rq *rq)
 {
-	struct drm_sched_rq *rq = entity->rq;
-
 	if (!RB_EMPTY_NODE(&entity->rb_tree_node)) {
 		rb_erase_cached(&entity->rb_tree_node, &rq->rb_tree_root);
 		RB_CLEAR_NODE(&entity->rb_tree_node);
 	}
 }
 
-void drm_sched_rq_update_fifo_locked(struct drm_sched_entity *entity, ktime_t ts)
+void drm_sched_rq_update_fifo_locked(struct drm_sched_entity *entity,
+				     struct drm_sched_rq *rq,
+				     ktime_t ts)
 {
 	/*
 	 * Both locks need to be grabbed, one to protect from entity->rq change
 	 * for entity from within concurrent drm_sched_entity_select_rq and the
 	 * other to update the rb tree structure.
 	 */
 	lockdep_assert_held(&entity->lock);
+	lockdep_assert_held(&rq->lock);
 
-	spin_lock(&entity->rq->lock);
-
-	drm_sched_rq_remove_fifo_locked(entity);
+	drm_sched_rq_remove_fifo_locked(entity, rq);
 
 	entity->oldest_job_waiting = ts;
 
-	rb_add_cached(&entity->rb_tree_node, &entity->rq->rb_tree_root,
+	rb_add_cached(&entity->rb_tree_node, &rq->rb_tree_root,
 		      drm_sched_entity_compare_before);
-
-	spin_unlock(&entity->rq->lock);
 }
 
 /**
@@ -213,15 +211,14 @@ static void drm_sched_rq_init(struct drm_gpu_scheduler *sched,
 void drm_sched_rq_add_entity(struct drm_sched_rq *rq,
 			     struct drm_sched_entity *entity)
 {
+	lockdep_assert_held(&entity->lock);
+	lockdep_assert_held(&rq->lock);
+
 	if (!list_empty(&entity->list))
 		return;
 
-	spin_lock(&rq->lock);
-
 	atomic_inc(rq->sched->score);
 	list_add_tail(&entity->list, &rq->entities);
-
-	spin_unlock(&rq->lock);
 }
 
 /**
@@ -235,6 +232,8 @@ void drm_sched_rq_add_entity(struct drm_sched_rq *rq,
 void drm_sched_rq_remove_entity(struct drm_sched_rq *rq,
 				struct drm_sched_entity *entity)
 {
+	lockdep_assert_held(&entity->lock);
+
 	if (list_empty(&entity->list))
 		return;
 
@@ -247,7 +246,7 @@ void drm_sched_rq_remove_entity(struct drm_sched_rq *rq,
 		rq->current_entity = NULL;
 
 	if (drm_sched_policy == DRM_SCHED_POLICY_FIFO)
-		drm_sched_rq_remove_fifo_locked(entity);
+		drm_sched_rq_remove_fifo_locked(entity, rq);
 
 	spin_unlock(&rq->lock);
 }

include/drm/gpu_scheduler.h

@@ -596,7 +596,8 @@ void drm_sched_rq_add_entity(struct drm_sched_rq *rq,
 void drm_sched_rq_remove_entity(struct drm_sched_rq *rq,
 				struct drm_sched_entity *entity);
 
-void drm_sched_rq_update_fifo_locked(struct drm_sched_entity *entity, ktime_t ts);
+void drm_sched_rq_update_fifo_locked(struct drm_sched_entity *entity,
+				     struct drm_sched_rq *rq, ktime_t ts);
 
 int drm_sched_entity_init(struct drm_sched_entity *entity,
 			  enum drm_sched_priority priority,