drm/sched: Convert drm scheduler to use a work queue rather than kthread

In Xe, the new Intel GPU driver, a choice has made to have a 1 to 1
mapping between a drm_gpu_scheduler and drm_sched_entity. At first this
seems a bit odd but let us explain the reasoning below.

1. In Xe the submission order from multiple drm_sched_entity is not
guaranteed to be the same completion even if targeting the same hardware
engine. This is because in Xe we have a firmware scheduler, the GuC,
which allowed to reorder, timeslice, and preempt submissions. If a using
shared drm_gpu_scheduler across multiple drm_sched_entity, the TDR falls
apart as the TDR expects submission order == completion order. Using a
dedicated drm_gpu_scheduler per drm_sched_entity solve this problem.

2. In Xe submissions are done via programming a ring buffer (circular
buffer), a drm_gpu_scheduler provides a limit on number of jobs, if the
limit of number jobs is set to RING_SIZE / MAX_SIZE_PER_JOB we get flow
control on the ring for free.

A problem with this design is currently a drm_gpu_scheduler uses a
kthread for submission / job cleanup. This doesn't scale if a large
number of drm_gpu_scheduler are used. To work around the scaling issue,
use a worker rather than kthread for submission / job cleanup.

v2:
  - (Rob Clark) Fix msm build
  - Pass in run work queue
v3:
  - (Boris) don't have loop in worker
v4:
  - (Tvrtko) break out submit ready, stop, start helpers into own patch
v5:
  - (Boris) default to ordered work queue
v6:
  - (Luben / checkpatch) fix alignment in msm_ringbuffer.c
  - (Luben) s/drm_sched_submit_queue/drm_sched_wqueue_enqueue
  - (Luben) Update comment for drm_sched_wqueue_enqueue
  - (Luben) Positive check for submit_wq in drm_sched_init
  - (Luben) s/alloc_submit_wq/own_submit_wq
v7:
  - (Luben) s/drm_sched_wqueue_enqueue/drm_sched_run_job_queue
v8:
  - (Luben) Adjust var names / comments

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Luben Tuikov <luben.tuikov@amd.com>
Link: https://lore.kernel.org/r/20231031032439.1558703-3-matthew.brost@intel.com
Signed-off-by: Luben Tuikov <ltuikov89@gmail.com>

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

@@ -2279,7 +2279,7 @@ static int amdgpu_device_init_schedulers(struct amdgpu_device *adev)
 			break;
 		}
 
-		r = drm_sched_init(&ring->sched, &amdgpu_sched_ops,
+		r = drm_sched_init(&ring->sched, &amdgpu_sched_ops, NULL,
 				   DRM_SCHED_PRIORITY_COUNT,
 				   ring->num_hw_submission, 0,
 				   timeout, adev->reset_domain->wq,

drivers/gpu/drm/etnaviv/etnaviv_sched.c

@@ -134,7 +134,7 @@ int etnaviv_sched_init(struct etnaviv_gpu *gpu)
 {
 	int ret;
 
-	ret = drm_sched_init(&gpu->sched, &etnaviv_sched_ops,
+	ret = drm_sched_init(&gpu->sched, &etnaviv_sched_ops, NULL,
 			     DRM_SCHED_PRIORITY_COUNT,
 			     etnaviv_hw_jobs_limit, etnaviv_job_hang_limit,
 			     msecs_to_jiffies(500), NULL, NULL,

drivers/gpu/drm/lima/lima_sched.c

@@ -488,7 +488,7 @@ 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,
+	return drm_sched_init(&pipe->base, &lima_sched_ops, NULL,
 			      DRM_SCHED_PRIORITY_COUNT,
 			      1,
 			      lima_job_hang_limit,

drivers/gpu/drm/msm/msm_ringbuffer.c

@@ -94,7 +94,7 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id,
 	 /* currently managing hangcheck ourselves: */
 	sched_timeout = MAX_SCHEDULE_TIMEOUT;
 
-	ret = drm_sched_init(&ring->sched, &msm_sched_ops,
+	ret = drm_sched_init(&ring->sched, &msm_sched_ops, NULL,
 			     DRM_SCHED_PRIORITY_COUNT,
 			     num_hw_submissions, 0, sched_timeout,
 			     NULL, NULL, to_msm_bo(ring->bo)->name, gpu->dev->dev);

drivers/gpu/drm/nouveau/nouveau_sched.c

@@ -429,7 +429,7 @@ int nouveau_sched_init(struct nouveau_drm *drm)
 	if (!drm->sched_wq)
 		return -ENOMEM;
 
-	return drm_sched_init(sched, &nouveau_sched_ops,
+	return drm_sched_init(sched, &nouveau_sched_ops, NULL,
 			      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

@@ -852,7 +852,7 @@ int panfrost_job_init(struct panfrost_device *pfdev)
 		js->queue[j].fence_context = dma_fence_context_alloc(1);
 
 		ret = drm_sched_init(&js->queue[j].sched,
-				     &panfrost_sched_ops,
+				     &panfrost_sched_ops, NULL,
 				     DRM_SCHED_PRIORITY_COUNT,
 				     nentries, 0,
 				     msecs_to_jiffies(JOB_TIMEOUT_MS),

drivers/gpu/drm/scheduler/sched_main.c

@@ -48,7 +48,6 @@
  * through the jobs entity pointer.
  */
 
-#include <linux/kthread.h>
 #include <linux/wait.h>
 #include <linux/sched.h>
 #include <linux/completion.h>
@@ -256,6 +255,16 @@ drm_sched_rq_select_entity_fifo(struct drm_sched_rq *rq)
 	return rb ? rb_entry(rb, struct drm_sched_entity, rb_tree_node) : NULL;
 }
 
+/**
+ * drm_sched_run_job_queue - enqueue run-job work
+ * @sched: scheduler instance
+ */
+static void drm_sched_run_job_queue(struct drm_gpu_scheduler *sched)
+{
+	if (!READ_ONCE(sched->pause_submit))
+		queue_work(sched->submit_wq, &sched->work_run_job);
+}
+
 /**
  * drm_sched_job_done - complete a job
  * @s_job: pointer to the job which is done
@@ -275,7 +284,7 @@ static void drm_sched_job_done(struct drm_sched_job *s_job, int result)
 	dma_fence_get(&s_fence->finished);
 	drm_sched_fence_finished(s_fence, result);
 	dma_fence_put(&s_fence->finished);
-	wake_up_interruptible(&sched->wake_up_worker);
+	drm_sched_run_job_queue(sched);
 }
 
 /**
@@ -874,7 +883,7 @@ static bool drm_sched_can_queue(struct drm_gpu_scheduler *sched)
 void drm_sched_wakeup_if_can_queue(struct drm_gpu_scheduler *sched)
 {
 	if (drm_sched_can_queue(sched))
-		wake_up_interruptible(&sched->wake_up_worker);
+		drm_sched_run_job_queue(sched);
 }
 
 /**
@@ -985,60 +994,41 @@ drm_sched_pick_best(struct drm_gpu_scheduler **sched_list,
 EXPORT_SYMBOL(drm_sched_pick_best);
 
 /**
- * drm_sched_blocked - check if the scheduler is blocked
+ * drm_sched_run_job_work - main scheduler thread
  *
- * @sched: scheduler instance
- *
- * Returns true if blocked, otherwise false.
+ * @w: run job work
  */
-static bool drm_sched_blocked(struct drm_gpu_scheduler *sched)
+static void drm_sched_run_job_work(struct work_struct *w)
 {
-	if (kthread_should_park()) {
-		kthread_parkme();
-		return true;
-	}
-
-	return false;
-}
-
-/**
- * drm_sched_main - main scheduler thread
- *
- * @param: scheduler instance
- *
- * Returns 0.
- */
-static int drm_sched_main(void *param)
-{
-	struct drm_gpu_scheduler *sched = (struct drm_gpu_scheduler *)param;
+	struct drm_gpu_scheduler *sched =
+		container_of(w, struct drm_gpu_scheduler, work_run_job);
+	struct drm_sched_entity *entity;
+	struct drm_sched_job *cleanup_job;
 	int r;
 
-	sched_set_fifo_low(current);
+	if (READ_ONCE(sched->pause_submit))
+		return;
 
-	while (!kthread_should_stop()) {
-		struct drm_sched_entity *entity = NULL;
-		struct drm_sched_fence *s_fence;
-		struct drm_sched_job *sched_job;
-		struct dma_fence *fence;
-		struct drm_sched_job *cleanup_job = NULL;
+	cleanup_job = drm_sched_get_cleanup_job(sched);
+	entity = drm_sched_select_entity(sched);
 
-		wait_event_interruptible(sched->wake_up_worker,
-					 (cleanup_job = drm_sched_get_cleanup_job(sched)) ||
-					 (!drm_sched_blocked(sched) &&
-					  (entity = drm_sched_select_entity(sched))) ||
-					 kthread_should_stop());
+	if (!entity && !cleanup_job)
+		return;	/* No more work */
 
-		if (cleanup_job)
-			sched->ops->free_job(cleanup_job);
+	if (cleanup_job)
+		sched->ops->free_job(cleanup_job);
 
-		if (!entity)
-			continue;
+	if (entity) {
+		struct dma_fence *fence;
+		struct drm_sched_fence *s_fence;
+		struct drm_sched_job *sched_job;
 
 		sched_job = drm_sched_entity_pop_job(entity);
-
 		if (!sched_job) {
 			complete_all(&entity->entity_idle);
-			continue;
+			if (!cleanup_job)
+				return;	/* No more work */
+			goto again;
 		}
 
 		s_fence = sched_job->s_fence;
@@ -1069,14 +1059,18 @@ static int drm_sched_main(void *param)
 
 		wake_up(&sched->job_scheduled);
 	}
-	return 0;
+
+again:
+	drm_sched_run_job_queue(sched);
 }
 
 /**
  * drm_sched_init - Init a gpu scheduler instance
  *
  * @sched: scheduler instance
  * @ops: backend operations for this scheduler
+ * @submit_wq: workqueue to use for submission. If NULL, an ordered wq is
+ *	       allocated and used
  * @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
@@ -1091,6 +1085,7 @@ static int drm_sched_main(void *param)
  */
 int drm_sched_init(struct drm_gpu_scheduler *sched,
 		   const struct drm_sched_backend_ops *ops,
+		   struct workqueue_struct *submit_wq,
 		   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)
@@ -1121,46 +1116,49 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 		return 0;
 	}
 
+	if (submit_wq) {
+		sched->submit_wq = submit_wq;
+		sched->own_submit_wq = false;
+	} else {
+		sched->submit_wq = alloc_ordered_workqueue(name, 0);
+		if (!sched->submit_wq)
+			return -ENOMEM;
+
+		sched->own_submit_wq = true;
+	}
+	ret = -ENOMEM;
 	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;
-	}
+	if (!sched->sched_rq)
+		goto Out_free;
 	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);
 	INIT_LIST_HEAD(&sched->pending_list);
 	spin_lock_init(&sched->job_list_lock);
 	atomic_set(&sched->hw_rq_count, 0);
 	INIT_DELAYED_WORK(&sched->work_tdr, drm_sched_job_timedout);
+	INIT_WORK(&sched->work_run_job, drm_sched_run_job_work);
 	atomic_set(&sched->_score, 0);
 	atomic64_set(&sched->job_id_count, 0);
-
-	/* Each scheduler will run on a seperate kernel thread */
-	sched->thread = kthread_run(drm_sched_main, sched, sched->name);
-	if (IS_ERR(sched->thread)) {
-		ret = PTR_ERR(sched->thread);
-		sched->thread = NULL;
-		DRM_DEV_ERROR(sched->dev, "Failed to create scheduler for %s.\n", name);
-		goto Out_unroll;
-	}
+	sched->pause_submit = false;
 
 	sched->ready = true;
 	return 0;
 Out_unroll:
 	for (--i ; i >= DRM_SCHED_PRIORITY_MIN; i--)
 		kfree(sched->sched_rq[i]);
+Out_free:
 	kfree(sched->sched_rq);
 	sched->sched_rq = NULL;
+	if (sched->own_submit_wq)
+		destroy_workqueue(sched->submit_wq);
 	drm_err(sched, "%s: Failed to setup GPU scheduler--out of memory\n", __func__);
 	return ret;
 }
@@ -1178,8 +1176,7 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched)
 	struct drm_sched_entity *s_entity;
 	int i;
 
-	if (sched->thread)
-		kthread_stop(sched->thread);
+	drm_sched_wqueue_stop(sched);
 
 	for (i = sched->num_rqs - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
 		struct drm_sched_rq *rq = sched->sched_rq[i];
@@ -1202,6 +1199,8 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched)
 	/* Confirm no work left behind accessing device structures */
 	cancel_delayed_work_sync(&sched->work_tdr);
 
+	if (sched->own_submit_wq)
+		destroy_workqueue(sched->submit_wq);
 	sched->ready = false;
 	kfree(sched->sched_rq);
 	sched->sched_rq = NULL;
@@ -1262,7 +1261,7 @@ EXPORT_SYMBOL(drm_sched_increase_karma);
  */
 bool drm_sched_wqueue_ready(struct drm_gpu_scheduler *sched)
 {
-	return !!sched->thread;
+	return sched->ready;
 }
 EXPORT_SYMBOL(drm_sched_wqueue_ready);
 
@@ -1273,7 +1272,8 @@ EXPORT_SYMBOL(drm_sched_wqueue_ready);
  */
 void drm_sched_wqueue_stop(struct drm_gpu_scheduler *sched)
 {
-	kthread_park(sched->thread);
+	WRITE_ONCE(sched->pause_submit, true);
+	cancel_work_sync(&sched->work_run_job);
 }
 EXPORT_SYMBOL(drm_sched_wqueue_stop);
 
@@ -1284,6 +1284,7 @@ EXPORT_SYMBOL(drm_sched_wqueue_stop);
  */
 void drm_sched_wqueue_start(struct drm_gpu_scheduler *sched)
 {
-	kthread_unpark(sched->thread);
+	WRITE_ONCE(sched->pause_submit, false);
+	queue_work(sched->submit_wq, &sched->work_run_job);
 }
 EXPORT_SYMBOL(drm_sched_wqueue_start);

drivers/gpu/drm/v3d/v3d_sched.c

@@ -388,7 +388,7 @@ v3d_sched_init(struct v3d_dev *v3d)
 	int ret;
 
 	ret = drm_sched_init(&v3d->queue[V3D_BIN].sched,
-			     &v3d_bin_sched_ops,
+			     &v3d_bin_sched_ops, NULL,
 			     DRM_SCHED_PRIORITY_COUNT,
 			     hw_jobs_limit, job_hang_limit,
 			     msecs_to_jiffies(hang_limit_ms), NULL,
@@ -397,7 +397,7 @@ v3d_sched_init(struct v3d_dev *v3d)
 		return ret;
 
 	ret = drm_sched_init(&v3d->queue[V3D_RENDER].sched,
-			     &v3d_render_sched_ops,
+			     &v3d_render_sched_ops, NULL,
 			     DRM_SCHED_PRIORITY_COUNT,
 			     hw_jobs_limit, job_hang_limit,
 			     msecs_to_jiffies(hang_limit_ms), NULL,
@@ -406,7 +406,7 @@ v3d_sched_init(struct v3d_dev *v3d)
 		goto fail;
 
 	ret = drm_sched_init(&v3d->queue[V3D_TFU].sched,
-			     &v3d_tfu_sched_ops,
+			     &v3d_tfu_sched_ops, NULL,
 			     DRM_SCHED_PRIORITY_COUNT,
 			     hw_jobs_limit, job_hang_limit,
 			     msecs_to_jiffies(hang_limit_ms), NULL,
@@ -416,7 +416,7 @@ 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,
+				     &v3d_csd_sched_ops, NULL,
 				     DRM_SCHED_PRIORITY_COUNT,
 				     hw_jobs_limit, job_hang_limit,
 				     msecs_to_jiffies(hang_limit_ms), NULL,
@@ -425,7 +425,7 @@ v3d_sched_init(struct v3d_dev *v3d)
 			goto fail;
 
 		ret = drm_sched_init(&v3d->queue[V3D_CACHE_CLEAN].sched,
-				     &v3d_cache_clean_sched_ops,
+				     &v3d_cache_clean_sched_ops, NULL,
 				     DRM_SCHED_PRIORITY_COUNT,
 				     hw_jobs_limit, job_hang_limit,
 				     msecs_to_jiffies(hang_limit_ms), NULL,