drm/sched: Add FIFO sched policy to run queue

When many entities are competing for the same run queue
on the same scheduler, we observe an unusually long wait
times and some jobs get starved. This has been observed on GPUVis.

The issue is due to the Round Robin policy used by schedulers
to pick up the next entity's job queue for execution. Under stress
of many entities and long job queues within entity some
jobs could be stuck for very long time in it's entity's
queue before being popped from the queue and executed
while for other entities with smaller job queues a job
might execute earlier even though that job arrived later
then the job in the long queue.

Fix:
Add FIFO selection policy to entities in run queue, chose next entity
on run queue in such order that if job on one entity arrived
earlier then job on another entity the first job will start
executing earlier regardless of the length of the entity's job
queue.

v2:
Switch to rb tree structure for entities based on TS of
oldest job waiting in the job queue of an entity. Improves next
entity extraction to O(1). Entity TS update
O(log N) where N is the number of entities in the run-queue

Drop default option in module control parameter.

v3:
Various cosmetical fixes and minor refactoring of fifo update function. (Luben)

v4:
Switch drm_sched_rq_select_entity_fifo to in order search (Luben)

v5: Fix up drm_sched_rq_select_entity_fifo loop (Luben)

v6: Add missing drm_sched_rq_remove_fifo_locked

v7: Fix ts sampling bug and more cosmetic stuff (Luben)

v8: Fix module parameter string (Luben)

Cc: Luben Tuikov <luben.tuikov@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Direct Rendering Infrastructure - Development <dri-devel@lists.freedesktop.org>
Cc: AMD Graphics <amd-gfx@lists.freedesktop.org>
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Tested-by: Yunxiang Li (Teddy) <Yunxiang.Li@amd.com>
Signed-off-by: Luben Tuikov <luben.tuikov@amd.com>
Reviewed-by: Luben Tuikov <luben.tuikov@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220930041258.1050247-1-luben.tuikov@amd.com

1 files changed, 93 insertions, 3 deletions

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 4f2395d1a791..ce86b03e8386 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -62,6 +62,55 @@
 #define to_drm_sched_job(sched_job)		\
 		container_of((sched_job), struct drm_sched_job, queue_node)
 
+int drm_sched_policy = DRM_SCHED_POLICY_RR;
+
+/**
+ * DOC: sched_policy (int)
+ * Used to override default entities scheduling policy in a run queue.
+ */
+MODULE_PARM_DESC(sched_policy, "Specify schedule policy for entities on a runqueue, " __stringify(DRM_SCHED_POLICY_RR) " = Round Robin (default), " __stringify(DRM_SCHED_POLICY_FIFO) " = use FIFO.");
+module_param_named(sched_policy, drm_sched_policy, int, 0444);
+
+static __always_inline bool drm_sched_entity_compare_before(struct rb_node *a,
+							    const struct rb_node *b)
+{
+	struct drm_sched_entity *ent_a =  rb_entry((a), struct drm_sched_entity, rb_tree_node);
+	struct drm_sched_entity *ent_b =  rb_entry((b), struct drm_sched_entity, rb_tree_node);
+
+	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)
+{
+	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(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);
+	spin_lock(&entity->rq->lock);
+
+	drm_sched_rq_remove_fifo_locked(entity);
+
+	entity->oldest_job_waiting = ts;
+
+	rb_add_cached(&entity->rb_tree_node, &entity->rq->rb_tree_root,
+		      drm_sched_entity_compare_before);
+
+	spin_unlock(&entity->rq->lock);
+	spin_unlock(&entity->rq_lock);
+}
+
 /**
  * drm_sched_rq_init - initialize a given run queue struct
  *
@@ -75,6 +124,7 @@ static void drm_sched_rq_init(struct drm_gpu_scheduler *sched,
 {
 	spin_lock_init(&rq->lock);
 	INIT_LIST_HEAD(&rq->entities);
+	rq->rb_tree_root = RB_ROOT_CACHED;
 	rq->current_entity = NULL;
 	rq->sched = sched;
 }
@@ -92,9 +142,12 @@ void drm_sched_rq_add_entity(struct drm_sched_rq *rq,
 {
 	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);
 }
 
@@ -111,23 +164,30 @@ void drm_sched_rq_remove_entity(struct drm_sched_rq *rq,
 {
 	if (list_empty(&entity->list))
 		return;
+
 	spin_lock(&rq->lock);
+
 	atomic_dec(rq->sched->score);
 	list_del_init(&entity->list);
+
 	if (rq->current_entity == entity)
 		rq->current_entity = NULL;
+
+	if (drm_sched_policy == DRM_SCHED_POLICY_FIFO)
+		drm_sched_rq_remove_fifo_locked(entity);
+
 	spin_unlock(&rq->lock);
 }
 
 /**
- * drm_sched_rq_select_entity - Select an entity which could provide a job to run
+ * drm_sched_rq_select_entity_rr - Select an entity which could provide a job to run
  *
  * @rq: scheduler run queue to check.
  *
  * Try to find a ready entity, returns NULL if none found.
  */
 static struct drm_sched_entity *
-drm_sched_rq_select_entity(struct drm_sched_rq *rq)
+drm_sched_rq_select_entity_rr(struct drm_sched_rq *rq)
 {
 	struct drm_sched_entity *entity;
 
@@ -164,6 +224,34 @@ drm_sched_rq_select_entity(struct drm_sched_rq *rq)
 }
 
 /**
+ * drm_sched_rq_select_entity_fifo - Select an entity which provides a job to run
+ *
+ * @rq: scheduler run queue to check.
+ *
+ * Find oldest waiting ready entity, returns NULL if none found.
+ */
+static struct drm_sched_entity *
+drm_sched_rq_select_entity_fifo(struct drm_sched_rq *rq)
+{
+	struct rb_node *rb;
+
+	spin_lock(&rq->lock);
+	for (rb = rb_first_cached(&rq->rb_tree_root); rb; rb = rb_next(rb)) {
+		struct drm_sched_entity *entity;
+
+		entity = rb_entry(rb, struct drm_sched_entity, rb_tree_node);
+		if (drm_sched_entity_is_ready(entity)) {
+			rq->current_entity = entity;
+			reinit_completion(&entity->entity_idle);
+			break;
+		}
+	}
+	spin_unlock(&rq->lock);
+
+	return rb ? rb_entry(rb, struct drm_sched_entity, rb_tree_node) : NULL;
+}
+
+/**
  * drm_sched_job_done - complete a job
  * @s_job: pointer to the job which is done
  *
@@ -803,7 +891,9 @@ drm_sched_select_entity(struct drm_gpu_scheduler *sched)
 
 	/* Kernel run queue has higher priority than normal run queue*/
 	for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
-		entity = drm_sched_rq_select_entity(&sched->sched_rq[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]);
 		if (entity)
 			break;
 	}