summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
blob: 97c94f9683fa047392ba62f128586e0b7e4492bc (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
/*
 * Copyright 2015 Advanced Micro Devices, Inc.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
 * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
 * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
 * OTHER DEALINGS IN THE SOFTWARE.
 *
 *
 */
#include <linux/kthread.h>
#include <linux/wait.h>
#include <linux/sched.h>
#include <uapi/linux/sched/types.h>
#include <drm/drmP.h>
#include "gpu_scheduler.h"

#define CREATE_TRACE_POINTS
#include "gpu_sched_trace.h"

static bool amd_sched_entity_is_ready(struct amd_sched_entity *entity);
static void amd_sched_wakeup(struct amd_gpu_scheduler *sched);
static void amd_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb);

/* Initialize a given run queue struct */
static void amd_sched_rq_init(struct amd_sched_rq *rq)
{
	spin_lock_init(&rq->lock);
	INIT_LIST_HEAD(&rq->entities);
	rq->current_entity = NULL;
}

static void amd_sched_rq_add_entity(struct amd_sched_rq *rq,
				    struct amd_sched_entity *entity)
{
	if (!list_empty(&entity->list))
		return;
	spin_lock(&rq->lock);
	list_add_tail(&entity->list, &rq->entities);
	spin_unlock(&rq->lock);
}

static void amd_sched_rq_remove_entity(struct amd_sched_rq *rq,
				       struct amd_sched_entity *entity)
{
	if (list_empty(&entity->list))
		return;
	spin_lock(&rq->lock);
	list_del_init(&entity->list);
	if (rq->current_entity == entity)
		rq->current_entity = NULL;
	spin_unlock(&rq->lock);
}

/**
 * Select an entity which could provide a job to run
 *
 * @rq		The run queue to check.
 *
 * Try to find a ready entity, returns NULL if none found.
 */
static struct amd_sched_entity *
amd_sched_rq_select_entity(struct amd_sched_rq *rq)
{
	struct amd_sched_entity *entity;

	spin_lock(&rq->lock);

	entity = rq->current_entity;
	if (entity) {
		list_for_each_entry_continue(entity, &rq->entities, list) {
			if (amd_sched_entity_is_ready(entity)) {
				rq->current_entity = entity;
				spin_unlock(&rq->lock);
				return entity;
			}
		}
	}

	list_for_each_entry(entity, &rq->entities, list) {

		if (amd_sched_entity_is_ready(entity)) {
			rq->current_entity = entity;
			spin_unlock(&rq->lock);
			return entity;
		}

		if (entity == rq->current_entity)
			break;
	}

	spin_unlock(&rq->lock);

	return NULL;
}

/**
 * Init a context entity used by scheduler when submit to HW ring.
 *
 * @sched	The pointer to the scheduler
 * @entity	The pointer to a valid amd_sched_entity
 * @rq		The run queue this entity belongs
 * @kernel	If this is an entity for the kernel
 * @jobs	The max number of jobs in the job queue
 *
 * return 0 if succeed. negative error code on failure
*/
int amd_sched_entity_init(struct amd_gpu_scheduler *sched,
			  struct amd_sched_entity *entity,
			  struct amd_sched_rq *rq,
			  uint32_t jobs)
{
	int r;

	if (!(sched && entity && rq))
		return -EINVAL;

	memset(entity, 0, sizeof(struct amd_sched_entity));
	INIT_LIST_HEAD(&entity->list);
	entity->rq = rq;
	entity->sched = sched;

	spin_lock_init(&entity->queue_lock);
	r = kfifo_alloc(&entity->job_queue, jobs * sizeof(void *), GFP_KERNEL);
	if (r)
		return r;

	atomic_set(&entity->fence_seq, 0);
	entity->fence_context = dma_fence_context_alloc(2);

	return 0;
}

/**
 * Query if entity is initialized
 *
 * @sched       Pointer to scheduler instance
 * @entity	The pointer to a valid scheduler entity
 *
 * return true if entity is initialized, false otherwise
*/
static bool amd_sched_entity_is_initialized(struct amd_gpu_scheduler *sched,
					    struct amd_sched_entity *entity)
{
	return entity->sched == sched &&
		entity->rq != NULL;
}

/**
 * Check if entity is idle
 *
 * @entity	The pointer to a valid scheduler entity
 *
 * Return true if entity don't has any unscheduled jobs.
 */
static bool amd_sched_entity_is_idle(struct amd_sched_entity *entity)
{
	rmb();
	if (kfifo_is_empty(&entity->job_queue))
		return true;

	return false;
}

/**
 * Check if entity is ready
 *
 * @entity	The pointer to a valid scheduler entity
 *
 * Return true if entity could provide a job.
 */
static bool amd_sched_entity_is_ready(struct amd_sched_entity *entity)
{
	if (kfifo_is_empty(&entity->job_queue))
		return false;

	if (ACCESS_ONCE(entity->dependency))
		return false;

	return true;
}

/**
 * Destroy a context entity
 *
 * @sched       Pointer to scheduler instance
 * @entity	The pointer to a valid scheduler entity
 *
 * Cleanup and free the allocated resources.
 */
void amd_sched_entity_fini(struct amd_gpu_scheduler *sched,
			   struct amd_sched_entity *entity)
{
	struct amd_sched_rq *rq = entity->rq;
	int r;

	if (!amd_sched_entity_is_initialized(sched, entity))
		return;
	/**
	 * The client will not queue more IBs during this fini, consume existing
	 * queued IBs or discard them on SIGKILL
	*/
	if ((current->flags & PF_SIGNALED) && current->exit_code == SIGKILL)
		r = -ERESTARTSYS;
	else
		r = wait_event_killable(sched->job_scheduled,
					amd_sched_entity_is_idle(entity));
	amd_sched_rq_remove_entity(rq, entity);
	if (r) {
		struct amd_sched_job *job;

		/* Park the kernel for a moment to make sure it isn't processing
		 * our enity.
		 */
		kthread_park(sched->thread);
		kthread_unpark(sched->thread);
		while (kfifo_out(&entity->job_queue, &job, sizeof(job)))
			sched->ops->free_job(job);

	}
	kfifo_free(&entity->job_queue);
}

static void amd_sched_entity_wakeup(struct dma_fence *f, struct dma_fence_cb *cb)
{
	struct amd_sched_entity *entity =
		container_of(cb, struct amd_sched_entity, cb);
	entity->dependency = NULL;
	dma_fence_put(f);
	amd_sched_wakeup(entity->sched);
}

static void amd_sched_entity_clear_dep(struct dma_fence *f, struct dma_fence_cb *cb)
{
	struct amd_sched_entity *entity =
		container_of(cb, struct amd_sched_entity, cb);
	entity->dependency = NULL;
	dma_fence_put(f);
}

bool amd_sched_dependency_optimized(struct dma_fence* fence,
				    struct amd_sched_entity *entity)
{
	struct amd_gpu_scheduler *sched = entity->sched;
	struct amd_sched_fence *s_fence;

	if (!fence || dma_fence_is_signaled(fence))
		return false;
	if (fence->context == entity->fence_context)
		return true;
	s_fence = to_amd_sched_fence(fence);
	if (s_fence && s_fence->sched == sched)
		return true;

	return false;
}

static bool amd_sched_entity_add_dependency_cb(struct amd_sched_entity *entity)
{
	struct amd_gpu_scheduler *sched = entity->sched;
	struct dma_fence * fence = entity->dependency;
	struct amd_sched_fence *s_fence;

	if (fence->context == entity->fence_context) {
		/* We can ignore fences from ourself */
		dma_fence_put(entity->dependency);
		return false;
	}

	s_fence = to_amd_sched_fence(fence);
	if (s_fence && s_fence->sched == sched) {

		/*
		 * Fence is from the same scheduler, only need to wait for
		 * it to be scheduled
		 */
		fence = dma_fence_get(&s_fence->scheduled);
		dma_fence_put(entity->dependency);
		entity->dependency = fence;
		if (!dma_fence_add_callback(fence, &entity->cb,
					    amd_sched_entity_clear_dep))
			return true;

		/* Ignore it when it is already scheduled */
		dma_fence_put(fence);
		return false;
	}

	if (!dma_fence_add_callback(entity->dependency, &entity->cb,
				    amd_sched_entity_wakeup))
		return true;

	dma_fence_put(entity->dependency);
	return false;
}

static struct amd_sched_job *
amd_sched_entity_pop_job(struct amd_sched_entity *entity)
{
	struct amd_gpu_scheduler *sched = entity->sched;
	struct amd_sched_job *sched_job;

	if (!kfifo_out_peek(&entity->job_queue, &sched_job, sizeof(sched_job)))
		return NULL;

	while ((entity->dependency = sched->ops->dependency(sched_job)))
		if (amd_sched_entity_add_dependency_cb(entity))
			return NULL;

	return sched_job;
}

/**
 * Helper to submit a job to the job queue
 *
 * @sched_job		The pointer to job required to submit
 *
 * Returns true if we could submit the job.
 */
static bool amd_sched_entity_in(struct amd_sched_job *sched_job)
{
	struct amd_gpu_scheduler *sched = sched_job->sched;
	struct amd_sched_entity *entity = sched_job->s_entity;
	bool added, first = false;

	spin_lock(&entity->queue_lock);
	added = kfifo_in(&entity->job_queue, &sched_job,
			sizeof(sched_job)) == sizeof(sched_job);

	if (added && kfifo_len(&entity->job_queue) == sizeof(sched_job))
		first = true;

	spin_unlock(&entity->queue_lock);

	/* first job wakes up scheduler */
	if (first) {
		/* Add the entity to the run queue */
		amd_sched_rq_add_entity(entity->rq, entity);
		amd_sched_wakeup(sched);
	}
	return added;
}

/* job_finish is called after hw fence signaled, and
 * the job had already been deleted from ring_mirror_list
 */
static void amd_sched_job_finish(struct work_struct *work)
{
	struct amd_sched_job *s_job = container_of(work, struct amd_sched_job,
						   finish_work);
	struct amd_gpu_scheduler *sched = s_job->sched;

	/* remove job from ring_mirror_list */
	spin_lock(&sched->job_list_lock);
	list_del_init(&s_job->node);
	if (sched->timeout != MAX_SCHEDULE_TIMEOUT) {
		struct amd_sched_job *next;

		spin_unlock(&sched->job_list_lock);
		cancel_delayed_work_sync(&s_job->work_tdr);
		spin_lock(&sched->job_list_lock);

		/* queue TDR for next job */
		next = list_first_entry_or_null(&sched->ring_mirror_list,
						struct amd_sched_job, node);

		if (next)
			schedule_delayed_work(&next->work_tdr, sched->timeout);
	}
	spin_unlock(&sched->job_list_lock);
	sched->ops->free_job(s_job);
}

static void amd_sched_job_finish_cb(struct dma_fence *f,
				    struct dma_fence_cb *cb)
{
	struct amd_sched_job *job = container_of(cb, struct amd_sched_job,
						 finish_cb);
	schedule_work(&job->finish_work);
}

static void amd_sched_job_begin(struct amd_sched_job *s_job)
{
	struct amd_gpu_scheduler *sched = s_job->sched;

	spin_lock(&sched->job_list_lock);
	list_add_tail(&s_job->node, &sched->ring_mirror_list);
	if (sched->timeout != MAX_SCHEDULE_TIMEOUT &&
	    list_first_entry_or_null(&sched->ring_mirror_list,
				     struct amd_sched_job, node) == s_job)
		schedule_delayed_work(&s_job->work_tdr, sched->timeout);
	spin_unlock(&sched->job_list_lock);
}

static void amd_sched_job_timedout(struct work_struct *work)
{
	struct amd_sched_job *job = container_of(work, struct amd_sched_job,
						 work_tdr.work);

	job->sched->ops->timedout_job(job);
}

void amd_sched_hw_job_reset(struct amd_gpu_scheduler *sched)
{
	struct amd_sched_job *s_job;

	spin_lock(&sched->job_list_lock);
	list_for_each_entry_reverse(s_job, &sched->ring_mirror_list, node) {
		if (s_job->s_fence->parent &&
		    dma_fence_remove_callback(s_job->s_fence->parent,
					      &s_job->s_fence->cb)) {
			dma_fence_put(s_job->s_fence->parent);
			s_job->s_fence->parent = NULL;
			atomic_dec(&sched->hw_rq_count);
		}
	}
	spin_unlock(&sched->job_list_lock);
}

void amd_sched_job_kickout(struct amd_sched_job *s_job)
{
	struct amd_gpu_scheduler *sched = s_job->sched;

	spin_lock(&sched->job_list_lock);
	list_del_init(&s_job->node);
	spin_unlock(&sched->job_list_lock);
}

void amd_sched_job_recovery(struct amd_gpu_scheduler *sched)
{
	struct amd_sched_job *s_job, *tmp;
	int r;

	spin_lock(&sched->job_list_lock);
	s_job = list_first_entry_or_null(&sched->ring_mirror_list,
					 struct amd_sched_job, node);
	if (s_job && sched->timeout != MAX_SCHEDULE_TIMEOUT)
		schedule_delayed_work(&s_job->work_tdr, sched->timeout);

	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
		struct amd_sched_fence *s_fence = s_job->s_fence;
		struct dma_fence *fence;

		spin_unlock(&sched->job_list_lock);
		fence = sched->ops->run_job(s_job);
		atomic_inc(&sched->hw_rq_count);
		if (fence) {
			s_fence->parent = dma_fence_get(fence);
			r = dma_fence_add_callback(fence, &s_fence->cb,
						   amd_sched_process_job);
			if (r == -ENOENT)
				amd_sched_process_job(fence, &s_fence->cb);
			else if (r)
				DRM_ERROR("fence add callback failed (%d)\n",
					  r);
			dma_fence_put(fence);
		} else {
			DRM_ERROR("Failed to run job!\n");
			amd_sched_process_job(NULL, &s_fence->cb);
		}
		spin_lock(&sched->job_list_lock);
	}
	spin_unlock(&sched->job_list_lock);
}

/**
 * Submit a job to the job queue
 *
 * @sched_job		The pointer to job required to submit
 *
 * Returns 0 for success, negative error code otherwise.
 */
void amd_sched_entity_push_job(struct amd_sched_job *sched_job)
{
	struct amd_sched_entity *entity = sched_job->s_entity;

	trace_amd_sched_job(sched_job);
	dma_fence_add_callback(&sched_job->s_fence->finished, &sched_job->finish_cb,
			       amd_sched_job_finish_cb);
	wait_event(entity->sched->job_scheduled,
		   amd_sched_entity_in(sched_job));
}

/* init a sched_job with basic field */
int amd_sched_job_init(struct amd_sched_job *job,
		       struct amd_gpu_scheduler *sched,
		       struct amd_sched_entity *entity,
		       void *owner)
{
	job->sched = sched;
	job->s_entity = entity;
	job->s_fence = amd_sched_fence_create(entity, owner);
	if (!job->s_fence)
		return -ENOMEM;
	job->id = atomic64_inc_return(&sched->job_id_count);

	INIT_WORK(&job->finish_work, amd_sched_job_finish);
	INIT_LIST_HEAD(&job->node);
	INIT_DELAYED_WORK(&job->work_tdr, amd_sched_job_timedout);

	return 0;
}

/**
 * Return ture if we can push more jobs to the hw.
 */
static bool amd_sched_ready(struct amd_gpu_scheduler *sched)
{
	return atomic_read(&sched->hw_rq_count) <
		sched->hw_submission_limit;
}

/**
 * Wake up the scheduler when it is ready
 */
static void amd_sched_wakeup(struct amd_gpu_scheduler *sched)
{
	if (amd_sched_ready(sched))
		wake_up_interruptible(&sched->wake_up_worker);
}

/**
 * Select next entity to process
*/
static struct amd_sched_entity *
amd_sched_select_entity(struct amd_gpu_scheduler *sched)
{
	struct amd_sched_entity *entity;
	int i;

	if (!amd_sched_ready(sched))
		return NULL;

	/* Kernel run queue has higher priority than normal run queue*/
	for (i = AMD_SCHED_PRIORITY_MAX - 1; i >= AMD_SCHED_PRIORITY_MIN; i--) {
		entity = amd_sched_rq_select_entity(&sched->sched_rq[i]);
		if (entity)
			break;
	}

	return entity;
}

static void amd_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb)
{
	struct amd_sched_fence *s_fence =
		container_of(cb, struct amd_sched_fence, cb);
	struct amd_gpu_scheduler *sched = s_fence->sched;

	atomic_dec(&sched->hw_rq_count);
	amd_sched_fence_finished(s_fence);

	trace_amd_sched_process_job(s_fence);
	dma_fence_put(&s_fence->finished);
	wake_up_interruptible(&sched->wake_up_worker);
}

static bool amd_sched_blocked(struct amd_gpu_scheduler *sched)
{
	if (kthread_should_park()) {
		kthread_parkme();
		return true;
	}

	return false;
}

static int amd_sched_main(void *param)
{
	struct sched_param sparam = {.sched_priority = 1};
	struct amd_gpu_scheduler *sched = (struct amd_gpu_scheduler *)param;
	int r, count;

	sched_setscheduler(current, SCHED_FIFO, &sparam);

	while (!kthread_should_stop()) {
		struct amd_sched_entity *entity = NULL;
		struct amd_sched_fence *s_fence;
		struct amd_sched_job *sched_job;
		struct dma_fence *fence;

		wait_event_interruptible(sched->wake_up_worker,
					 (!amd_sched_blocked(sched) &&
					  (entity = amd_sched_select_entity(sched))) ||
					 kthread_should_stop());

		if (!entity)
			continue;

		sched_job = amd_sched_entity_pop_job(entity);
		if (!sched_job)
			continue;

		s_fence = sched_job->s_fence;

		atomic_inc(&sched->hw_rq_count);
		amd_sched_job_begin(sched_job);

		fence = sched->ops->run_job(sched_job);
		amd_sched_fence_scheduled(s_fence);
		if (fence) {
			s_fence->parent = dma_fence_get(fence);
			r = dma_fence_add_callback(fence, &s_fence->cb,
						   amd_sched_process_job);
			if (r == -ENOENT)
				amd_sched_process_job(fence, &s_fence->cb);
			else if (r)
				DRM_ERROR("fence add callback failed (%d)\n",
					  r);
			dma_fence_put(fence);
		} else {
			DRM_ERROR("Failed to run job!\n");
			amd_sched_process_job(NULL, &s_fence->cb);
		}

		count = kfifo_out(&entity->job_queue, &sched_job,
				sizeof(sched_job));
		WARN_ON(count != sizeof(sched_job));
		wake_up(&sched->job_scheduled);
	}
	return 0;
}

/**
 * Init a gpu scheduler instance
 *
 * @sched		The pointer to the scheduler
 * @ops			The backend operations for this scheduler.
 * @hw_submissions	Number of hw submissions to do.
 * @name		Name used for debugging
 *
 * Return 0 on success, otherwise error code.
*/
int amd_sched_init(struct amd_gpu_scheduler *sched,
		   const struct amd_sched_backend_ops *ops,
		   unsigned hw_submission, long timeout, const char *name)
{
	int i;
	sched->ops = ops;
	sched->hw_submission_limit = hw_submission;
	sched->name = name;
	sched->timeout = timeout;
	for (i = AMD_SCHED_PRIORITY_MIN; i < AMD_SCHED_PRIORITY_MAX; i++)
		amd_sched_rq_init(&sched->sched_rq[i]);

	init_waitqueue_head(&sched->wake_up_worker);
	init_waitqueue_head(&sched->job_scheduled);
	INIT_LIST_HEAD(&sched->ring_mirror_list);
	spin_lock_init(&sched->job_list_lock);
	atomic_set(&sched->hw_rq_count, 0);
	atomic64_set(&sched->job_id_count, 0);

	/* Each scheduler will run on a seperate kernel thread */
	sched->thread = kthread_run(amd_sched_main, sched, sched->name);
	if (IS_ERR(sched->thread)) {
		DRM_ERROR("Failed to create scheduler for %s.\n", name);
		return PTR_ERR(sched->thread);
	}

	return 0;
}

/**
 * Destroy a gpu scheduler
 *
 * @sched	The pointer to the scheduler
 */
void amd_sched_fini(struct amd_gpu_scheduler *sched)
{
	if (sched->thread)
		kthread_stop(sched->thread);
}