drm/sched: Optimise drm_sched_entity_push_job

In FIFO mode (which is the default), both drm_sched_entity_push_job() and
drm_sched_rq_update_fifo(), where the latter calls the former, are
currently taking and releasing the same entity->rq_lock.

We can avoid that design inelegance, and also have a miniscule
efficiency improvement on the submit from idle path, by introducing a new
drm_sched_rq_update_fifo_locked() helper and pulling up the lock taking to
its callers.

v2:
 * Remove drm_sched_rq_update_fifo() altogether. (Christian)

v3:
 * Improved commit message. (Philipp)

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>
Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241016122013.7857-2-tursulin@igalia.com

drivers/gpu/drm/scheduler/sched_entity.c

@@ -514,8 +514,12 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity)
 		struct drm_sched_job *next;
 
 		next = to_drm_sched_job(spsc_queue_peek(&entity->job_queue));
-		if (next)
-			drm_sched_rq_update_fifo(entity, next->submit_ts);
+		if (next) {
+			spin_lock(&entity->rq_lock);
+			drm_sched_rq_update_fifo_locked(entity,
+							next->submit_ts);
+			spin_unlock(&entity->rq_lock);
+		}
 	}
 
 	/* Jobs and entities might have different lifecycles. Since we're
@@ -613,10 +617,11 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job)
 		sched = rq->sched;
 
 		drm_sched_rq_add_entity(rq, entity);
-		spin_unlock(&entity->rq_lock);
 
 		if (drm_sched_policy == DRM_SCHED_POLICY_FIFO)
-			drm_sched_rq_update_fifo(entity, submit_ts);
+			drm_sched_rq_update_fifo_locked(entity, submit_ts);
+
+		spin_unlock(&entity->rq_lock);
 
 		drm_sched_wakeup(sched);
 	}

drivers/gpu/drm/scheduler/sched_main.c

@@ -163,14 +163,15 @@ static inline void drm_sched_rq_remove_fifo_locked(struct drm_sched_entity *enti
 	}
 }
 
-void drm_sched_rq_update_fifo(struct drm_sched_entity *entity, ktime_t ts)
+void drm_sched_rq_update_fifo_locked(struct drm_sched_entity *entity, 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.
 	 */
-	spin_lock(&entity->rq_lock);
+	lockdep_assert_held(&entity->rq_lock);
+
 	spin_lock(&entity->rq->lock);
 
 	drm_sched_rq_remove_fifo_locked(entity);
@@ -181,7 +182,6 @@ void drm_sched_rq_update_fifo(struct drm_sched_entity *entity, ktime_t ts)
 		      drm_sched_entity_compare_before);
 
 	spin_unlock(&entity->rq->lock);
-	spin_unlock(&entity->rq_lock);
 }
 
 /**

include/drm/gpu_scheduler.h

@@ -593,7 +593,7 @@ 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(struct drm_sched_entity *entity, ktime_t ts);
+void drm_sched_rq_update_fifo_locked(struct drm_sched_entity *entity, ktime_t ts);
 
 int drm_sched_entity_init(struct drm_sched_entity *entity,
 			  enum drm_sched_priority priority,