drm/sched: Implement RR via FIFO

Round-robin being the non-default policy and unclear how much it is used,
we can notice that it can be implemented using the FIFO data structures if
we only invent a fake submit timestamp which is monotonically increasing
inside drm_sched_rq instances.

So instead of remembering which was the last entity the scheduler worker
picked we can simply bump the picked one to the bottom of the tree, which
ensures round-robin behaviour between all active queued jobs.

If the picked job was the last from a given entity, we remember the
assigned fake timestamp and use it to re-insert the job once it re-joins
the queue. This ensures the job neither overtakes all already queued jobs,
neither it goes last. Instead it keeps the position after the currently
queued jobs and before the ones which haven't yet been queued at the point
the entity left the queue.

Advantage is that we can consolidate to a single code path and remove a
bunch of code. Downside is round-robin mode now needs to lock on the job
pop path but that should not have a measurable performance impact.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Danilo Krummrich <dakr@kernel.org>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Philipp Stanner <phasta@kernel.org>
Acked-by: Danilo Krummrich <dakr@kernel.org>
Tested-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Signed-off-by: Philipp Stanner <phasta@kernel.org>
Link: https://patch.msgid.link/20260417103744.76020-7-tvrtko.ursulin@igalia.com

diff --git a/drivers/gpu/drm/scheduler/sched_internal.h b/drivers/gpu/drm/scheduler/sched_internal.h
index aab63a8721d94f86115880474acb3e1b6af0450c..b683cf8134691a17df03e86a25a4c921cd9e1320 100644 (file)
--- a/drivers/gpu/drm/scheduler/sched_internal.h
+++ b/drivers/gpu/drm/scheduler/sched_internal.h
@@ -24,11 +24,8 @@ void drm_sched_rq_remove_entity(struct drm_sched_rq *rq,
 void drm_sched_rq_pop_entity(struct drm_sched_entity *entity);
 
 struct drm_sched_entity *
-drm_sched_rq_select_entity_rr(struct drm_gpu_scheduler *sched,
-                             struct drm_sched_rq *rq);
-struct drm_sched_entity *
-drm_sched_rq_select_entity_fifo(struct drm_gpu_scheduler *sched,
-                               struct drm_sched_rq *rq);
+drm_sched_rq_select_entity(struct drm_gpu_scheduler *sched,
+                          struct drm_sched_rq *rq);
 
 void drm_sched_entity_select_rq(struct drm_sched_entity *entity);
 struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity);

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 298509e40d695a05d98a6f5c8c472d20579efcdd..097ea187d08e05527fe58932388b993ec8623d7b 100644 (file)
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -892,15 +892,13 @@ void drm_sched_wakeup(struct drm_gpu_scheduler *sched)
 static struct drm_sched_entity *
 drm_sched_select_entity(struct drm_gpu_scheduler *sched)
 {
-       struct drm_sched_entity *entity;
+       struct drm_sched_entity *entity = NULL;
        int i;
 
        /* Start with the highest priority.
         */
        for (i = DRM_SCHED_PRIORITY_KERNEL; i < sched->num_rqs; i++) {
-               entity = drm_sched_policy == DRM_SCHED_POLICY_FIFO ?
-                       drm_sched_rq_select_entity_fifo(sched, sched->sched_rq[i]) :
-                       drm_sched_rq_select_entity_rr(sched, sched->sched_rq[i]);
+               entity = drm_sched_rq_select_entity(sched, sched->sched_rq[i]);
                if (entity)
                        break;
        }

diff --git a/drivers/gpu/drm/scheduler/sched_rq.c b/drivers/gpu/drm/scheduler/sched_rq.c
index a525bb579c4de9c68ed0a6827b5aab7c62a34a93..6948b342d26a7f834d978b0e48915b20a4a47c76 100644 (file)
--- a/drivers/gpu/drm/scheduler/sched_rq.c
+++ b/drivers/gpu/drm/scheduler/sched_rq.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: MIT
 /* Copyright 2015 Advanced Micro Devices, Inc. */
+/* Copyright (c) 2025 Valve Corporation */
 
 #include <linux/rbtree.h>
 
@@ -98,8 +99,9 @@ drm_sched_rq_add_entity(struct drm_sched_entity *entity, ktime_t ts)
                list_add_tail(&entity->list, &rq->entities);
        }
 
-       if (drm_sched_policy == DRM_SCHED_POLICY_FIFO)
-               drm_sched_rq_update_fifo_locked(entity, rq, ts);
+       if (drm_sched_policy == DRM_SCHED_POLICY_RR)
+               ts = entity->rr_ts;
+       drm_sched_rq_update_fifo_locked(entity, rq, ts);
 
        spin_unlock(&rq->lock);
        spin_unlock(&entity->lock);
@@ -127,15 +129,27 @@ void drm_sched_rq_remove_entity(struct drm_sched_rq *rq,
        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, rq);
+       drm_sched_rq_remove_fifo_locked(entity, rq);
 
        spin_unlock(&rq->lock);
 }
 
+static ktime_t
+drm_sched_rq_next_rr_ts(struct drm_sched_rq *rq,
+                       struct drm_sched_entity *entity)
+{
+       ktime_t ts;
+
+       lockdep_assert_held(&entity->lock);
+       lockdep_assert_held(&rq->lock);
+
+       ts = ktime_add_ns(rq->rr_ts, 1);
+       entity->rr_ts = ts;
+       rq->rr_ts = ts;
+
+       return ts;
+}
+
 /**
  * drm_sched_rq_pop_entity - pops an entity
  * @entity: scheduler entity
@@ -144,88 +158,32 @@ void drm_sched_rq_remove_entity(struct drm_sched_rq *rq,
  */
 void drm_sched_rq_pop_entity(struct drm_sched_entity *entity)
 {
+       struct drm_sched_job *next_job;
+
        /*
         * Update the entity's location in the min heap according to
         * the timestamp of the next job, if any.
         */
-       if (drm_sched_policy == DRM_SCHED_POLICY_FIFO) {
-               struct drm_sched_job *next;
-
-               next = drm_sched_entity_queue_peek(entity);
-               if (next) {
-                       struct drm_sched_rq *rq;
-
-                       spin_lock(&entity->lock);
-                       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);
-               }
-       }
-}
-
-/**
- * drm_sched_rq_select_entity_rr - Select an entity which could provide a job to run
- *
- * @sched: the gpu scheduler
- * @rq: scheduler run queue to check.
- *
- * Try to find the next ready entity.
- *
- * Return an entity if one is found; return an error-pointer (!NULL) if an
- * entity was ready, but the scheduler had insufficient credits to accommodate
- * its job; return NULL, if no ready entity was found.
- */
-struct drm_sched_entity *
-drm_sched_rq_select_entity_rr(struct drm_gpu_scheduler *sched,
-                             struct drm_sched_rq *rq)
-{
-       struct drm_sched_entity *entity;
-
-       spin_lock(&rq->lock);
-
-       entity = rq->current_entity;
-       if (entity) {
-               list_for_each_entry_continue(entity, &rq->entities, list) {
-                       if (drm_sched_entity_is_ready(entity))
-                               goto found;
-               }
-       }
-
-       list_for_each_entry(entity, &rq->entities, list) {
-               if (drm_sched_entity_is_ready(entity))
-                       goto found;
-
-               if (entity == rq->current_entity)
-                       break;
-       }
-
-       spin_unlock(&rq->lock);
-
-       return NULL;
-
-found:
-       if (!drm_sched_can_queue(sched, entity)) {
-               /*
-                * If scheduler cannot take more jobs signal the caller to not
-                * consider lower priority queues.
-                */
-               entity = ERR_PTR(-ENOSPC);
-       } else {
-               rq->current_entity = entity;
-               reinit_completion(&entity->entity_idle);
+       next_job = drm_sched_entity_queue_peek(entity);
+       if (next_job) {
+               struct drm_sched_rq *rq;
+               ktime_t ts;
+
+               spin_lock(&entity->lock);
+               rq = entity->rq;
+               spin_lock(&rq->lock);
+               if (drm_sched_policy == DRM_SCHED_POLICY_FIFO)
+                       ts = next_job->submit_ts;
+               else
+                       ts = drm_sched_rq_next_rr_ts(rq, entity);
+               drm_sched_rq_update_fifo_locked(entity, rq, ts);
+               spin_unlock(&rq->lock);
+               spin_unlock(&entity->lock);
        }
-
-       spin_unlock(&rq->lock);
-
-       return entity;
 }
 
 /**
- * drm_sched_rq_select_entity_fifo - Select an entity which provides a job to run
- *
+ * drm_sched_rq_select_entity - Select an entity which provides a job to run
  * @sched: the gpu scheduler
  * @rq: scheduler run queue to check.
  *
@@ -236,8 +194,8 @@ found:
  * its job; return NULL, if no ready entity was found.
  */
 struct drm_sched_entity *
-drm_sched_rq_select_entity_fifo(struct drm_gpu_scheduler *sched,
-                               struct drm_sched_rq *rq)
+drm_sched_rq_select_entity(struct drm_gpu_scheduler *sched,
+                          struct drm_sched_rq *rq)
 {
        struct rb_node *rb;
 

diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 609ebe389094f2c9fb414ce679e437f2f92e4b5a..772331067cc2863d9c79e20e7d6a3c807cc748da 100644 (file)
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -94,7 +94,8 @@ struct drm_sched_entity {
         * @lock:
         *
         * Lock protecting the run-queue (@rq) to which this entity belongs,
-        * @priority and the list of schedulers (@sched_list, @num_sched_list).
+        * @priority, the list of schedulers (@sched_list, @num_sched_list) and
+        * the @rr_ts field.
         */
        spinlock_t                      lock;
 
@@ -142,6 +143,13 @@ struct drm_sched_entity {
         */
        enum drm_sched_priority         priority;
 
+       /**
+        * @rr_ts:
+        *
+        * Fake timestamp of the last popped job from the entity.
+        */
+       ktime_t                         rr_ts;
+
        /**
         * @job_queue: the list of jobs of this entity.
         */
@@ -239,8 +247,8 @@ struct drm_sched_entity {
  * struct drm_sched_rq - queue of entities to be scheduled.
  *
  * @sched: the scheduler to which this rq belongs to.
- * @lock: protects @entities, @rb_tree_root and @current_entity.
- * @current_entity: the entity which is to be scheduled.
+ * @lock: protects @entities, @rb_tree_root and @rr_ts.
+ * @rr_ts: monotonically incrementing fake timestamp for RR mode.
  * @entities: list of the entities to be scheduled.
  * @rb_tree_root: root of time based priority queue of entities for FIFO scheduling
  *
@@ -253,7 +261,7 @@ struct drm_sched_rq {
 
        spinlock_t                      lock;
        /* Following members are protected by the @lock: */
-       struct drm_sched_entity         *current_entity;
+       ktime_t                         rr_ts;
        struct list_head                entities;
        struct rb_root_cached           rb_tree_root;
 };