drm/sched: Convert the GPU scheduler to variable number of run-queues

The GPU scheduler has now a variable number of run-queues, which are set up at
drm_sched_init() time. This way, each driver announces how many run-queues it
requires (supports) per each GPU scheduler it creates. Note, that run-queues
correspond to scheduler "priorities", thus if the number of run-queues is set
to 1 at drm_sched_init(), then that scheduler supports a single run-queue,
i.e. single "priority". If a driver further sets a single entity per
run-queue, then this creates a 1-to-1 correspondence between a scheduler and
a scheduled entity.

Cc: Lucas Stach <l.stach@pengutronix.de>
Cc: Russell King <linux+etnaviv@armlinux.org.uk>
Cc: Qiang Yu <yuq825@gmail.com>
Cc: Rob Clark <robdclark@gmail.com>
Cc: Abhinav Kumar <quic_abhinavk@quicinc.com>
Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Cc: Danilo Krummrich <dakr@redhat.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Boris Brezillon <boris.brezillon@collabora.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Emma Anholt <emma@anholt.net>
Cc: etnaviv@lists.freedesktop.org
Cc: lima@lists.freedesktop.org
Cc: linux-arm-msm@vger.kernel.org
Cc: freedreno@lists.freedesktop.org
Cc: nouveau@lists.freedesktop.org
Cc: dri-devel@lists.freedesktop.org
Signed-off-by: Luben Tuikov <luben.tuikov@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Link: https://lore.kernel.org/r/20231023032251.164775-1-luben.tuikov@amd.com

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -2280,6 +2280,7 @@ static int amdgpu_device_init_schedulers(struct amdgpu_device *adev)
 		}
 
 		r = drm_sched_init(&ring->sched, &amdgpu_sched_ops,
+				   DRM_SCHED_PRIORITY_COUNT,
 				   ring->num_hw_submission, 0,
 				   timeout, adev->reset_domain->wq,
 				   ring->sched_score, ring->name,

drivers/gpu/drm/amd/amdgpu/amdgpu_job.c

@@ -325,8 +325,8 @@ void amdgpu_job_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched)
 	int i;
 
 	/* Signal all jobs not yet scheduled */
-	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) {
 			while ((s_job = to_drm_sched_job(spsc_queue_pop(&s_entity->job_queue)))) {

drivers/gpu/drm/etnaviv/etnaviv_sched.c

@@ -135,6 +135,7 @@ int etnaviv_sched_init(struct etnaviv_gpu *gpu)
 	int ret;
 
 	ret = drm_sched_init(&gpu->sched, &etnaviv_sched_ops,
+			     DRM_SCHED_PRIORITY_COUNT,
 			     etnaviv_hw_jobs_limit, etnaviv_job_hang_limit,
 			     msecs_to_jiffies(500), NULL, NULL,
 			     dev_name(gpu->dev), gpu->dev);

drivers/gpu/drm/lima/lima_sched.c

@@ -488,7 +488,9 @@ int lima_sched_pipe_init(struct lima_sched_pipe *pipe, const char *name)
 
 	INIT_WORK(&pipe->recover_work, lima_sched_recover_work);
 
-	return drm_sched_init(&pipe->base, &lima_sched_ops, 1,
+	return drm_sched_init(&pipe->base, &lima_sched_ops,
+			      DRM_SCHED_PRIORITY_COUNT,
+			      1,
 			      lima_job_hang_limit,
 			      msecs_to_jiffies(timeout), NULL,
 			      NULL, name, pipe->ldev->dev);

drivers/gpu/drm/msm/msm_ringbuffer.c

@@ -95,6 +95,7 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id,
 	sched_timeout = MAX_SCHEDULE_TIMEOUT;
 
 	ret = drm_sched_init(&ring->sched, &msm_sched_ops,
+			     DRM_SCHED_PRIORITY_COUNT,
 			     num_hw_submissions, 0, sched_timeout,
 			     NULL, NULL, to_msm_bo(ring->bo)->name, gpu->dev->dev);
 	if (ret) {

drivers/gpu/drm/nouveau/nouveau_sched.c

@@ -430,6 +430,7 @@ int nouveau_sched_init(struct nouveau_drm *drm)
 		return -ENOMEM;
 
 	return drm_sched_init(sched, &nouveau_sched_ops,
+			      DRM_SCHED_PRIORITY_COUNT,
 			      NOUVEAU_SCHED_HW_SUBMISSIONS, 0, job_hang_limit,
 			      NULL, NULL, "nouveau_sched", drm->dev->dev);
 }

drivers/gpu/drm/panfrost/panfrost_job.c

@@ -853,6 +853,7 @@ int panfrost_job_init(struct panfrost_device *pfdev)
 
 		ret = drm_sched_init(&js->queue[j].sched,
 				     &panfrost_sched_ops,
+				     DRM_SCHED_PRIORITY_COUNT,
 				     nentries, 0,
 				     msecs_to_jiffies(JOB_TIMEOUT_MS),
 				     pfdev->reset.wq,

drivers/gpu/drm/scheduler/sched_entity.c

@@ -75,8 +75,20 @@ 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.
+		 */
+		if (entity->priority >= sched_list[0]->num_rqs)
+			entity->priority = max_t(u32, sched_list[0]->num_rqs,
+						 DRM_SCHED_PRIORITY_MIN);
+		entity->rq = sched_list[0]->sched_rq[entity->priority];
+	}
 
 	init_completion(&entity->entity_idle);
 
@@ -533,7 +545,7 @@ 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;

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) {

drivers/gpu/drm/v3d/v3d_sched.c

@@ -389,6 +389,7 @@ v3d_sched_init(struct v3d_dev *v3d)
 
 	ret = drm_sched_init(&v3d->queue[V3D_BIN].sched,
 			     &v3d_bin_sched_ops,
+			     DRM_SCHED_PRIORITY_COUNT,
 			     hw_jobs_limit, job_hang_limit,
 			     msecs_to_jiffies(hang_limit_ms), NULL,
 			     NULL, "v3d_bin", v3d->drm.dev);
@@ -397,6 +398,7 @@ v3d_sched_init(struct v3d_dev *v3d)
 
 	ret = drm_sched_init(&v3d->queue[V3D_RENDER].sched,
 			     &v3d_render_sched_ops,
+			     DRM_SCHED_PRIORITY_COUNT,
 			     hw_jobs_limit, job_hang_limit,
 			     msecs_to_jiffies(hang_limit_ms), NULL,
 			     NULL, "v3d_render", v3d->drm.dev);
@@ -405,6 +407,7 @@ v3d_sched_init(struct v3d_dev *v3d)
 
 	ret = drm_sched_init(&v3d->queue[V3D_TFU].sched,
 			     &v3d_tfu_sched_ops,
+			     DRM_SCHED_PRIORITY_COUNT,
 			     hw_jobs_limit, job_hang_limit,
 			     msecs_to_jiffies(hang_limit_ms), NULL,
 			     NULL, "v3d_tfu", v3d->drm.dev);
@@ -414,6 +417,7 @@ v3d_sched_init(struct v3d_dev *v3d)
 	if (v3d_has_csd(v3d)) {
 		ret = drm_sched_init(&v3d->queue[V3D_CSD].sched,
 				     &v3d_csd_sched_ops,
+				     DRM_SCHED_PRIORITY_COUNT,
 				     hw_jobs_limit, job_hang_limit,
 				     msecs_to_jiffies(hang_limit_ms), NULL,
 				     NULL, "v3d_csd", v3d->drm.dev);
@@ -422,6 +426,7 @@ v3d_sched_init(struct v3d_dev *v3d)
 
 		ret = drm_sched_init(&v3d->queue[V3D_CACHE_CLEAN].sched,
 				     &v3d_cache_clean_sched_ops,
+				     DRM_SCHED_PRIORITY_COUNT,
 				     hw_jobs_limit, job_hang_limit,
 				     msecs_to_jiffies(hang_limit_ms), NULL,
 				     NULL, "v3d_cache_clean", v3d->drm.dev);

include/drm/gpu_scheduler.h

@@ -472,7 +472,9 @@ struct drm_sched_backend_ops {
  * @hw_submission_limit: the max size of the hardware queue.
  * @timeout: the time after which a job is removed from the scheduler.
  * @name: name of the ring for which this scheduler is being used.
- * @sched_rq: priority wise array of run queues.
+ * @num_rqs: Number of run-queues. This is at most DRM_SCHED_PRIORITY_COUNT,
+ *           as there's usually one run-queue per priority, but could be less.
+ * @sched_rq: An allocated array of run-queues of size @num_rqs;
  * @wake_up_worker: the wait queue on which the scheduler sleeps until a job
  *                  is ready to be scheduled.
  * @job_scheduled: once @drm_sched_entity_do_release is called the scheduler
@@ -501,7 +503,8 @@ struct drm_gpu_scheduler {
 	uint32_t			hw_submission_limit;
 	long				timeout;
 	const char			*name;
-	struct drm_sched_rq		sched_rq[DRM_SCHED_PRIORITY_COUNT];
+	u32                             num_rqs;
+	struct drm_sched_rq             **sched_rq;
 	wait_queue_head_t		wake_up_worker;
 	wait_queue_head_t		job_scheduled;
 	atomic_t			hw_rq_count;
@@ -521,7 +524,7 @@ struct drm_gpu_scheduler {
 
 int drm_sched_init(struct drm_gpu_scheduler *sched,
 		   const struct drm_sched_backend_ops *ops,
-		   uint32_t 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);