summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/scheduler/sched_main.c
blob: ab53ab486fe69daca7e9537afd8bd0445dd4498e (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
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
/*
 * 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.
 *
 */

/**
 * DOC: Overview
 *
 * The GPU scheduler provides entities which allow userspace to push jobs
 * into software queues which are then scheduled on a hardware run queue.
 * The software queues have a priority among them. The scheduler selects the entities
 * from the run queue using a FIFO. The scheduler provides dependency handling
 * features among jobs. The driver is supposed to provide callback functions for
 * backend operations to the scheduler like submitting a job to hardware run queue,
 * returning the dependencies of a job etc.
 *
 * The organisation of the scheduler is the following:
 *
 * 1. Each hw run queue has one scheduler
 * 2. Each scheduler has multiple run queues with different priorities
 *    (e.g., HIGH_HW,HIGH_SW, KERNEL, NORMAL)
 * 3. Each scheduler run queue has a queue of entities to schedule
 * 4. Entities themselves maintain a queue of jobs that will be scheduled on
 *    the hardware.
 *
 * The jobs in a entity are always scheduled in the order that they were pushed.
 *
 * Note that once a job was taken from the entities queue and pushed to the
 * hardware, i.e. the pending queue, the entity must not be referenced anymore
 * through the jobs entity pointer.
 */

/**
 * DOC: Flow Control
 *
 * The DRM GPU scheduler provides a flow control mechanism to regulate the rate
 * in which the jobs fetched from scheduler entities are executed.
 *
 * In this context the &drm_gpu_scheduler keeps track of a driver specified
 * credit limit representing the capacity of this scheduler and a credit count;
 * every &drm_sched_job carries a driver specified number of credits.
 *
 * Once a job is executed (but not yet finished), the job's credits contribute
 * to the scheduler's credit count until the job is finished. If by executing
 * one more job the scheduler's credit count would exceed the scheduler's
 * credit limit, the job won't be executed. Instead, the scheduler will wait
 * until the credit count has decreased enough to not overflow its credit limit.
 * This implies waiting for previously executed jobs.
 *
 * Optionally, drivers may register a callback (update_job_credits) provided by
 * struct drm_sched_backend_ops to update the job's credits dynamically. The
 * scheduler executes this callback every time the scheduler considers a job for
 * execution and subsequently checks whether the job fits the scheduler's credit
 * limit.
 */

#include <linux/wait.h>
#include <linux/sched.h>
#include <linux/completion.h>
#include <linux/dma-resv.h>
#include <uapi/linux/sched/types.h>

#include <drm/drm_print.h>
#include <drm/drm_gem.h>
#include <drm/drm_syncobj.h>
#include <drm/gpu_scheduler.h>
#include <drm/spsc_queue.h>

#define CREATE_TRACE_POINTS
#include "gpu_scheduler_trace.h"

#define to_drm_sched_job(sched_job)		\
		container_of((sched_job), struct drm_sched_job, queue_node)

int drm_sched_policy = DRM_SCHED_POLICY_FIFO;

/**
 * DOC: sched_policy (int)
 * Used to override default entities scheduling policy in a run queue.
 */
MODULE_PARM_DESC(sched_policy, "Specify the scheduling policy for entities on a run-queue, " __stringify(DRM_SCHED_POLICY_RR) " = Round Robin, " __stringify(DRM_SCHED_POLICY_FIFO) " = FIFO (default).");
module_param_named(sched_policy, drm_sched_policy, int, 0444);

static u32 drm_sched_available_credits(struct drm_gpu_scheduler *sched)
{
	u32 credits;

	drm_WARN_ON(sched, check_sub_overflow(sched->credit_limit,
					      atomic_read(&sched->credit_count),
					      &credits));

	return credits;
}

/**
 * drm_sched_can_queue -- Can we queue more to the hardware?
 * @sched: scheduler instance
 * @entity: the scheduler entity
 *
 * Return true if we can push at least one more job from @entity, false
 * otherwise.
 */
static bool drm_sched_can_queue(struct drm_gpu_scheduler *sched,
				struct drm_sched_entity *entity)
{
	struct drm_sched_job *s_job;

	s_job = to_drm_sched_job(spsc_queue_peek(&entity->job_queue));
	if (!s_job)
		return false;

	if (sched->ops->update_job_credits) {
		s_job->credits = sched->ops->update_job_credits(s_job);

		drm_WARN(sched, !s_job->credits,
			 "Jobs with zero credits bypass job-flow control.\n");
	}

	/* If a job exceeds the credit limit, truncate it to the credit limit
	 * itself to guarantee forward progress.
	 */
	if (drm_WARN(sched, s_job->credits > sched->credit_limit,
		     "Jobs may not exceed the credit limit, truncate.\n"))
		s_job->credits = sched->credit_limit;

	return drm_sched_available_credits(sched) >= s_job->credits;
}

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
 *
 * @sched: scheduler instance to associate with this run queue
 * @rq: scheduler run queue
 *
 * Initializes a scheduler runqueue.
 */
static void drm_sched_rq_init(struct drm_gpu_scheduler *sched,
			      struct drm_sched_rq *rq)
{
	spin_lock_init(&rq->lock);
	INIT_LIST_HEAD(&rq->entities);
	rq->rb_tree_root = RB_ROOT_CACHED;
	rq->current_entity = NULL;
	rq->sched = sched;
}

/**
 * drm_sched_rq_add_entity - add an entity
 *
 * @rq: scheduler run queue
 * @entity: scheduler entity
 *
 * Adds a scheduler entity to the run queue.
 */
void drm_sched_rq_add_entity(struct drm_sched_rq *rq,
			     struct drm_sched_entity *entity)
{
	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);
}

/**
 * drm_sched_rq_remove_entity - remove an entity
 *
 * @rq: scheduler run queue
 * @entity: scheduler entity
 *
 * Removes a scheduler entity from the run queue.
 */
void drm_sched_rq_remove_entity(struct drm_sched_rq *rq,
				struct drm_sched_entity *entity)
{
	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_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.
 */
static 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)) {
				/* If we can't queue yet, preserve the current
				 * entity in terms of fairness.
				 */
				if (!drm_sched_can_queue(sched, entity)) {
					spin_unlock(&rq->lock);
					return ERR_PTR(-ENOSPC);
				}

				rq->current_entity = entity;
				reinit_completion(&entity->entity_idle);
				spin_unlock(&rq->lock);
				return entity;
			}
		}
	}

	list_for_each_entry(entity, &rq->entities, list) {
		if (drm_sched_entity_is_ready(entity)) {
			/* If we can't queue yet, preserve the current entity in
			 * terms of fairness.
			 */
			if (!drm_sched_can_queue(sched, entity)) {
				spin_unlock(&rq->lock);
				return ERR_PTR(-ENOSPC);
			}

			rq->current_entity = entity;
			reinit_completion(&entity->entity_idle);
			spin_unlock(&rq->lock);
			return entity;
		}

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

	spin_unlock(&rq->lock);

	return NULL;
}

/**
 * drm_sched_rq_select_entity_fifo - Select an entity which provides a job to run
 *
 * @sched: the gpu scheduler
 * @rq: scheduler run queue to check.
 *
 * Find oldest waiting 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.
 */
static struct drm_sched_entity *
drm_sched_rq_select_entity_fifo(struct drm_gpu_scheduler *sched,
				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)) {
			/* If we can't queue yet, preserve the current entity in
			 * terms of fairness.
			 */
			if (!drm_sched_can_queue(sched, entity)) {
				spin_unlock(&rq->lock);
				return ERR_PTR(-ENOSPC);
			}

			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_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_run_free_queue - enqueue free-job work
 * @sched: scheduler instance
 */
static void __drm_sched_run_free_queue(struct drm_gpu_scheduler *sched)
{
	if (!READ_ONCE(sched->pause_submit))
		queue_work(sched->submit_wq, &sched->work_free_job);
}

/**
 * drm_sched_run_free_queue - enqueue free-job work if ready
 * @sched: scheduler instance
 */
static void drm_sched_run_free_queue(struct drm_gpu_scheduler *sched)
{
	struct drm_sched_job *job;

	spin_lock(&sched->job_list_lock);
	job = list_first_entry_or_null(&sched->pending_list,
				       struct drm_sched_job, list);
	if (job && dma_fence_is_signaled(&job->s_fence->finished))
		__drm_sched_run_free_queue(sched);
	spin_unlock(&sched->job_list_lock);
}

/**
 * drm_sched_job_done - complete a job
 * @s_job: pointer to the job which is done
 *
 * Finish the job's fence and wake up the worker thread.
 */
static void drm_sched_job_done(struct drm_sched_job *s_job, int result)
{
	struct drm_sched_fence *s_fence = s_job->s_fence;
	struct drm_gpu_scheduler *sched = s_fence->sched;

	atomic_sub(s_job->credits, &sched->credit_count);
	atomic_dec(sched->score);

	trace_drm_sched_process_job(s_fence);

	dma_fence_get(&s_fence->finished);
	drm_sched_fence_finished(s_fence, result);
	dma_fence_put(&s_fence->finished);
	__drm_sched_run_free_queue(sched);
}

/**
 * drm_sched_job_done_cb - the callback for a done job
 * @f: fence
 * @cb: fence callbacks
 */
static void drm_sched_job_done_cb(struct dma_fence *f, struct dma_fence_cb *cb)
{
	struct drm_sched_job *s_job = container_of(cb, struct drm_sched_job, cb);

	drm_sched_job_done(s_job, f->error);
}

/**
 * drm_sched_start_timeout - start timeout for reset worker
 *
 * @sched: scheduler instance to start the worker for
 *
 * Start the timeout for the given scheduler.
 */
static void drm_sched_start_timeout(struct drm_gpu_scheduler *sched)
{
	lockdep_assert_held(&sched->job_list_lock);

	if (sched->timeout != MAX_SCHEDULE_TIMEOUT &&
	    !list_empty(&sched->pending_list))
		mod_delayed_work(sched->timeout_wq, &sched->work_tdr, sched->timeout);
}

static void drm_sched_start_timeout_unlocked(struct drm_gpu_scheduler *sched)
{
	spin_lock(&sched->job_list_lock);
	drm_sched_start_timeout(sched);
	spin_unlock(&sched->job_list_lock);
}

/**
 * drm_sched_tdr_queue_imm: - immediately start job timeout handler
 *
 * @sched: scheduler for which the timeout handling should be started.
 *
 * Start timeout handling immediately for the named scheduler.
 */
void drm_sched_tdr_queue_imm(struct drm_gpu_scheduler *sched)
{
	spin_lock(&sched->job_list_lock);
	sched->timeout = 0;
	drm_sched_start_timeout(sched);
	spin_unlock(&sched->job_list_lock);
}
EXPORT_SYMBOL(drm_sched_tdr_queue_imm);

/**
 * drm_sched_fault - immediately start timeout handler
 *
 * @sched: scheduler where the timeout handling should be started.
 *
 * Start timeout handling immediately when the driver detects a hardware fault.
 */
void drm_sched_fault(struct drm_gpu_scheduler *sched)
{
	if (sched->timeout_wq)
		mod_delayed_work(sched->timeout_wq, &sched->work_tdr, 0);
}
EXPORT_SYMBOL(drm_sched_fault);

/**
 * drm_sched_suspend_timeout - Suspend scheduler job timeout
 *
 * @sched: scheduler instance for which to suspend the timeout
 *
 * Suspend the delayed work timeout for the scheduler. This is done by
 * modifying the delayed work timeout to an arbitrary large value,
 * MAX_SCHEDULE_TIMEOUT in this case.
 *
 * Returns the timeout remaining
 *
 */
unsigned long drm_sched_suspend_timeout(struct drm_gpu_scheduler *sched)
{
	unsigned long sched_timeout, now = jiffies;

	sched_timeout = sched->work_tdr.timer.expires;

	/*
	 * Modify the timeout to an arbitrarily large value. This also prevents
	 * the timeout to be restarted when new submissions arrive
	 */
	if (mod_delayed_work(sched->timeout_wq, &sched->work_tdr, MAX_SCHEDULE_TIMEOUT)
			&& time_after(sched_timeout, now))
		return sched_timeout - now;
	else
		return sched->timeout;
}
EXPORT_SYMBOL(drm_sched_suspend_timeout);

/**
 * drm_sched_resume_timeout - Resume scheduler job timeout
 *
 * @sched: scheduler instance for which to resume the timeout
 * @remaining: remaining timeout
 *
 * Resume the delayed work timeout for the scheduler.
 */
void drm_sched_resume_timeout(struct drm_gpu_scheduler *sched,
		unsigned long remaining)
{
	spin_lock(&sched->job_list_lock);

	if (list_empty(&sched->pending_list))
		cancel_delayed_work(&sched->work_tdr);
	else
		mod_delayed_work(sched->timeout_wq, &sched->work_tdr, remaining);

	spin_unlock(&sched->job_list_lock);
}
EXPORT_SYMBOL(drm_sched_resume_timeout);

static void drm_sched_job_begin(struct drm_sched_job *s_job)
{
	struct drm_gpu_scheduler *sched = s_job->sched;

	spin_lock(&sched->job_list_lock);
	list_add_tail(&s_job->list, &sched->pending_list);
	drm_sched_start_timeout(sched);
	spin_unlock(&sched->job_list_lock);
}

static void drm_sched_job_timedout(struct work_struct *work)
{
	struct drm_gpu_scheduler *sched;
	struct drm_sched_job *job;
	enum drm_gpu_sched_stat status = DRM_GPU_SCHED_STAT_NOMINAL;

	sched = container_of(work, struct drm_gpu_scheduler, work_tdr.work);

	/* Protects against concurrent deletion in drm_sched_get_finished_job */
	spin_lock(&sched->job_list_lock);
	job = list_first_entry_or_null(&sched->pending_list,
				       struct drm_sched_job, list);

	if (job) {
		/*
		 * Remove the bad job so it cannot be freed by concurrent
		 * drm_sched_cleanup_jobs. It will be reinserted back after sched->thread
		 * is parked at which point it's safe.
		 */
		list_del_init(&job->list);
		spin_unlock(&sched->job_list_lock);

		status = job->sched->ops->timedout_job(job);

		/*
		 * Guilty job did complete and hence needs to be manually removed
		 * See drm_sched_stop doc.
		 */
		if (sched->free_guilty) {
			job->sched->ops->free_job(job);
			sched->free_guilty = false;
		}
	} else {
		spin_unlock(&sched->job_list_lock);
	}

	if (status != DRM_GPU_SCHED_STAT_ENODEV)
		drm_sched_start_timeout_unlocked(sched);
}

/**
 * drm_sched_stop - stop the scheduler
 *
 * @sched: scheduler instance
 * @bad: job which caused the time out
 *
 * Stop the scheduler and also removes and frees all completed jobs.
 * Note: bad job will not be freed as it might be used later and so it's
 * callers responsibility to release it manually if it's not part of the
 * pending list any more.
 *
 */
void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad)
{
	struct drm_sched_job *s_job, *tmp;

	drm_sched_wqueue_stop(sched);

	/*
	 * Reinsert back the bad job here - now it's safe as
	 * drm_sched_get_finished_job cannot race against us and release the
	 * bad job at this point - we parked (waited for) any in progress
	 * (earlier) cleanups and drm_sched_get_finished_job will not be called
	 * now until the scheduler thread is unparked.
	 */
	if (bad && bad->sched == sched)
		/*
		 * Add at the head of the queue to reflect it was the earliest
		 * job extracted.
		 */
		list_add(&bad->list, &sched->pending_list);

	/*
	 * Iterate the job list from later to  earlier one and either deactive
	 * their HW callbacks or remove them from pending list if they already
	 * signaled.
	 * This iteration is thread safe as sched thread is stopped.
	 */
	list_for_each_entry_safe_reverse(s_job, tmp, &sched->pending_list,
					 list) {
		if (s_job->s_fence->parent &&
		    dma_fence_remove_callback(s_job->s_fence->parent,
					      &s_job->cb)) {
			dma_fence_put(s_job->s_fence->parent);
			s_job->s_fence->parent = NULL;
			atomic_sub(s_job->credits, &sched->credit_count);
		} else {
			/*
			 * remove job from pending_list.
			 * Locking here is for concurrent resume timeout
			 */
			spin_lock(&sched->job_list_lock);
			list_del_init(&s_job->list);
			spin_unlock(&sched->job_list_lock);

			/*
			 * Wait for job's HW fence callback to finish using s_job
			 * before releasing it.
			 *
			 * Job is still alive so fence refcount at least 1
			 */
			dma_fence_wait(&s_job->s_fence->finished, false);

			/*
			 * We must keep bad job alive for later use during
			 * recovery by some of the drivers but leave a hint
			 * that the guilty job must be released.
			 */
			if (bad != s_job)
				sched->ops->free_job(s_job);
			else
				sched->free_guilty = true;
		}
	}

	/*
	 * Stop pending timer in flight as we rearm it in  drm_sched_start. This
	 * avoids the pending timeout work in progress to fire right away after
	 * this TDR finished and before the newly restarted jobs had a
	 * chance to complete.
	 */
	cancel_delayed_work(&sched->work_tdr);
}

EXPORT_SYMBOL(drm_sched_stop);

/**
 * drm_sched_start - recover jobs after a reset
 *
 * @sched: scheduler instance
 *
 */
void drm_sched_start(struct drm_gpu_scheduler *sched)
{
	struct drm_sched_job *s_job, *tmp;

	/*
	 * Locking the list is not required here as the sched thread is parked
	 * so no new jobs are being inserted or removed. Also concurrent
	 * GPU recovers can't run in parallel.
	 */
	list_for_each_entry_safe(s_job, tmp, &sched->pending_list, list) {
		struct dma_fence *fence = s_job->s_fence->parent;

		atomic_add(s_job->credits, &sched->credit_count);

		if (!fence) {
			drm_sched_job_done(s_job, -ECANCELED);
			continue;
		}

		if (dma_fence_add_callback(fence, &s_job->cb,
					   drm_sched_job_done_cb))
			drm_sched_job_done(s_job, fence->error);
	}

	drm_sched_start_timeout_unlocked(sched);
	drm_sched_wqueue_start(sched);
}
EXPORT_SYMBOL(drm_sched_start);

/**
 * drm_sched_resubmit_jobs - Deprecated, don't use in new code!
 *
 * @sched: scheduler instance
 *
 * Re-submitting jobs was a concept AMD came up as cheap way to implement
 * recovery after a job timeout.
 *
 * This turned out to be not working very well. First of all there are many
 * problem with the dma_fence implementation and requirements. Either the
 * implementation is risking deadlocks with core memory management or violating
 * documented implementation details of the dma_fence object.
 *
 * Drivers can still save and restore their state for recovery operations, but
 * we shouldn't make this a general scheduler feature around the dma_fence
 * interface.
 */
void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
{
	struct drm_sched_job *s_job, *tmp;
	uint64_t guilty_context;
	bool found_guilty = false;
	struct dma_fence *fence;

	list_for_each_entry_safe(s_job, tmp, &sched->pending_list, list) {
		struct drm_sched_fence *s_fence = s_job->s_fence;

		if (!found_guilty && atomic_read(&s_job->karma) > sched->hang_limit) {
			found_guilty = true;
			guilty_context = s_job->s_fence->scheduled.context;
		}

		if (found_guilty && s_job->s_fence->scheduled.context == guilty_context)
			dma_fence_set_error(&s_fence->finished, -ECANCELED);

		fence = sched->ops->run_job(s_job);

		if (IS_ERR_OR_NULL(fence)) {
			if (IS_ERR(fence))
				dma_fence_set_error(&s_fence->finished, PTR_ERR(fence));

			s_job->s_fence->parent = NULL;
		} else {

			s_job->s_fence->parent = dma_fence_get(fence);

			/* Drop for orignal kref_init */
			dma_fence_put(fence);
		}
	}
}
EXPORT_SYMBOL(drm_sched_resubmit_jobs);

/**
 * drm_sched_job_init - init a scheduler job
 * @job: scheduler job to init
 * @entity: scheduler entity to use
 * @credits: the number of credits this job contributes to the schedulers
 * credit limit
 * @owner: job owner for debugging
 *
 * Refer to drm_sched_entity_push_job() documentation
 * for locking considerations.
 *
 * Drivers must make sure drm_sched_job_cleanup() if this function returns
 * successfully, even when @job is aborted before drm_sched_job_arm() is called.
 *
 * WARNING: amdgpu abuses &drm_sched.ready to signal when the hardware
 * has died, which can mean that there's no valid runqueue for a @entity.
 * This function returns -ENOENT in this case (which probably should be -EIO as
 * a more meanigful return value).
 *
 * Returns 0 for success, negative error code otherwise.
 */
int drm_sched_job_init(struct drm_sched_job *job,
		       struct drm_sched_entity *entity,
		       u32 credits, void *owner)
{
	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;
	}

	if (unlikely(!credits)) {
		pr_err("*ERROR* %s: credits cannot be 0!\n", __func__);
		return -EINVAL;
	}

	job->entity = entity;
	job->credits = credits;
	job->s_fence = drm_sched_fence_alloc(entity, owner);
	if (!job->s_fence)
		return -ENOMEM;

	INIT_LIST_HEAD(&job->list);

	xa_init_flags(&job->dependencies, XA_FLAGS_ALLOC);

	return 0;
}
EXPORT_SYMBOL(drm_sched_job_init);

/**
 * drm_sched_job_arm - arm a scheduler job for execution
 * @job: scheduler job to arm
 *
 * This arms a scheduler job for execution. Specifically it initializes the
 * &drm_sched_job.s_fence of @job, so that it can be attached to struct dma_resv
 * or other places that need to track the completion of this job.
 *
 * Refer to drm_sched_entity_push_job() documentation for locking
 * considerations.
 *
 * This can only be called if drm_sched_job_init() succeeded.
 */
void drm_sched_job_arm(struct drm_sched_job *job)
{
	struct drm_gpu_scheduler *sched;
	struct drm_sched_entity *entity = job->entity;

	BUG_ON(!entity);
	drm_sched_entity_select_rq(entity);
	sched = entity->rq->sched;

	job->sched = sched;
	job->s_priority = entity->priority;
	job->id = atomic64_inc_return(&sched->job_id_count);

	drm_sched_fence_init(job->s_fence, job->entity);
}
EXPORT_SYMBOL(drm_sched_job_arm);

/**
 * drm_sched_job_add_dependency - adds the fence as a job dependency
 * @job: scheduler job to add the dependencies to
 * @fence: the dma_fence to add to the list of dependencies.
 *
 * Note that @fence is consumed in both the success and error cases.
 *
 * Returns:
 * 0 on success, or an error on failing to expand the array.
 */
int drm_sched_job_add_dependency(struct drm_sched_job *job,
				 struct dma_fence *fence)
{
	struct dma_fence *entry;
	unsigned long index;
	u32 id = 0;
	int ret;

	if (!fence)
		return 0;

	/* Deduplicate if we already depend on a fence from the same context.
	 * This lets the size of the array of deps scale with the number of
	 * engines involved, rather than the number of BOs.
	 */
	xa_for_each(&job->dependencies, index, entry) {
		if (entry->context != fence->context)
			continue;

		if (dma_fence_is_later(fence, entry)) {
			dma_fence_put(entry);
			xa_store(&job->dependencies, index, fence, GFP_KERNEL);
		} else {
			dma_fence_put(fence);
		}
		return 0;
	}

	ret = xa_alloc(&job->dependencies, &id, fence, xa_limit_32b, GFP_KERNEL);
	if (ret != 0)
		dma_fence_put(fence);

	return ret;
}
EXPORT_SYMBOL(drm_sched_job_add_dependency);

/**
 * drm_sched_job_add_syncobj_dependency - adds a syncobj's fence as a job dependency
 * @job: scheduler job to add the dependencies to
 * @file: drm file private pointer
 * @handle: syncobj handle to lookup
 * @point: timeline point
 *
 * This adds the fence matching the given syncobj to @job.
 *
 * Returns:
 * 0 on success, or an error on failing to expand the array.
 */
int drm_sched_job_add_syncobj_dependency(struct drm_sched_job *job,
					 struct drm_file *file,
					 u32 handle,
					 u32 point)
{
	struct dma_fence *fence;
	int ret;

	ret = drm_syncobj_find_fence(file, handle, point, 0, &fence);
	if (ret)
		return ret;

	return drm_sched_job_add_dependency(job, fence);
}
EXPORT_SYMBOL(drm_sched_job_add_syncobj_dependency);

/**
 * drm_sched_job_add_resv_dependencies - add all fences from the resv to the job
 * @job: scheduler job to add the dependencies to
 * @resv: the dma_resv object to get the fences from
 * @usage: the dma_resv_usage to use to filter the fences
 *
 * This adds all fences matching the given usage from @resv to @job.
 * Must be called with the @resv lock held.
 *
 * Returns:
 * 0 on success, or an error on failing to expand the array.
 */
int drm_sched_job_add_resv_dependencies(struct drm_sched_job *job,
					struct dma_resv *resv,
					enum dma_resv_usage usage)
{
	struct dma_resv_iter cursor;
	struct dma_fence *fence;
	int ret;

	dma_resv_assert_held(resv);

	dma_resv_for_each_fence(&cursor, resv, usage, fence) {
		/* Make sure to grab an additional ref on the added fence */
		dma_fence_get(fence);
		ret = drm_sched_job_add_dependency(job, fence);
		if (ret) {
			dma_fence_put(fence);
			return ret;
		}
	}
	return 0;
}
EXPORT_SYMBOL(drm_sched_job_add_resv_dependencies);

/**
 * drm_sched_job_add_implicit_dependencies - adds implicit dependencies as job
 *   dependencies
 * @job: scheduler job to add the dependencies to
 * @obj: the gem object to add new dependencies from.
 * @write: whether the job might write the object (so we need to depend on
 * shared fences in the reservation object).
 *
 * This should be called after drm_gem_lock_reservations() on your array of
 * GEM objects used in the job but before updating the reservations with your
 * own fences.
 *
 * Returns:
 * 0 on success, or an error on failing to expand the array.
 */
int drm_sched_job_add_implicit_dependencies(struct drm_sched_job *job,
					    struct drm_gem_object *obj,
					    bool write)
{
	return drm_sched_job_add_resv_dependencies(job, obj->resv,
						   dma_resv_usage_rw(write));
}
EXPORT_SYMBOL(drm_sched_job_add_implicit_dependencies);

/**
 * drm_sched_job_cleanup - clean up scheduler job resources
 * @job: scheduler job to clean up
 *
 * Cleans up the resources allocated with drm_sched_job_init().
 *
 * Drivers should call this from their error unwind code if @job is aborted
 * before drm_sched_job_arm() is called.
 *
 * After that point of no return @job is committed to be executed by the
 * scheduler, and this function should be called from the
 * &drm_sched_backend_ops.free_job callback.
 */
void drm_sched_job_cleanup(struct drm_sched_job *job)
{
	struct dma_fence *fence;
	unsigned long index;

	if (kref_read(&job->s_fence->finished.refcount)) {
		/* drm_sched_job_arm() has been called */
		dma_fence_put(&job->s_fence->finished);
	} else {
		/* aborted job before committing to run it */
		drm_sched_fence_free(job->s_fence);
	}

	job->s_fence = NULL;

	xa_for_each(&job->dependencies, index, fence) {
		dma_fence_put(fence);
	}
	xa_destroy(&job->dependencies);

}
EXPORT_SYMBOL(drm_sched_job_cleanup);

/**
 * drm_sched_wakeup - Wake up the scheduler if it is ready to queue
 * @sched: scheduler instance
 * @entity: the scheduler entity
 *
 * Wake up the scheduler if we can queue jobs.
 */
void drm_sched_wakeup(struct drm_gpu_scheduler *sched,
		      struct drm_sched_entity *entity)
{
	if (drm_sched_can_queue(sched, entity))
		drm_sched_run_job_queue(sched);
}

/**
 * drm_sched_select_entity - Select next entity to process
 *
 * @sched: scheduler instance
 *
 * Return an entity to process or NULL if none are found.
 *
 * Note, that we break out of the for-loop when "entity" is non-null, which can
 * also be an error-pointer--this assures we don't process lower priority
 * run-queues. See comments in the respectively called functions.
 */
static struct drm_sched_entity *
drm_sched_select_entity(struct drm_gpu_scheduler *sched)
{
	struct drm_sched_entity *entity;
	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]);
		if (entity)
			break;
	}

	return IS_ERR(entity) ? NULL : entity;
}

/**
 * drm_sched_get_finished_job - fetch the next finished job to be destroyed
 *
 * @sched: scheduler instance
 *
 * Returns the next finished job from the pending list (if there is one)
 * ready for it to be destroyed.
 */
static struct drm_sched_job *
drm_sched_get_finished_job(struct drm_gpu_scheduler *sched)
{
	struct drm_sched_job *job, *next;

	spin_lock(&sched->job_list_lock);

	job = list_first_entry_or_null(&sched->pending_list,
				       struct drm_sched_job, list);

	if (job && dma_fence_is_signaled(&job->s_fence->finished)) {
		/* remove job from pending_list */
		list_del_init(&job->list);

		/* cancel this job's TO timer */
		cancel_delayed_work(&sched->work_tdr);
		/* make the scheduled timestamp more accurate */
		next = list_first_entry_or_null(&sched->pending_list,
						typeof(*next), list);

		if (next) {
			if (test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT,
				     &next->s_fence->scheduled.flags))
				next->s_fence->scheduled.timestamp =
					dma_fence_timestamp(&job->s_fence->finished);
			/* start TO timer for next job */
			drm_sched_start_timeout(sched);
		}
	} else {
		job = NULL;
	}

	spin_unlock(&sched->job_list_lock);

	return job;
}

/**
 * drm_sched_pick_best - Get a drm sched from a sched_list with the least load
 * @sched_list: list of drm_gpu_schedulers
 * @num_sched_list: number of drm_gpu_schedulers in the sched_list
 *
 * Returns pointer of the sched with the least load or NULL if none of the
 * drm_gpu_schedulers are ready
 */
struct drm_gpu_scheduler *
drm_sched_pick_best(struct drm_gpu_scheduler **sched_list,
		     unsigned int num_sched_list)
{
	struct drm_gpu_scheduler *sched, *picked_sched = NULL;
	int i;
	unsigned int min_score = UINT_MAX, num_score;

	for (i = 0; i < num_sched_list; ++i) {
		sched = sched_list[i];

		if (!sched->ready) {
			DRM_WARN("scheduler %s is not ready, skipping",
				 sched->name);
			continue;
		}

		num_score = atomic_read(sched->score);
		if (num_score < min_score) {
			min_score = num_score;
			picked_sched = sched;
		}
	}

	return picked_sched;
}
EXPORT_SYMBOL(drm_sched_pick_best);

/**
 * drm_sched_free_job_work - worker to call free_job
 *
 * @w: free job work
 */
static void drm_sched_free_job_work(struct work_struct *w)
{
	struct drm_gpu_scheduler *sched =
		container_of(w, struct drm_gpu_scheduler, work_free_job);
	struct drm_sched_job *job;

	if (READ_ONCE(sched->pause_submit))
		return;

	job = drm_sched_get_finished_job(sched);
	if (job)
		sched->ops->free_job(job);

	drm_sched_run_free_queue(sched);
	drm_sched_run_job_queue(sched);
}

/**
 * drm_sched_run_job_work - worker to call run_job
 *
 * @w: run job work
 */
static void drm_sched_run_job_work(struct work_struct *w)
{
	struct drm_gpu_scheduler *sched =
		container_of(w, struct drm_gpu_scheduler, work_run_job);
	struct drm_sched_entity *entity;
	struct dma_fence *fence;
	struct drm_sched_fence *s_fence;
	struct drm_sched_job *sched_job;
	int r;

	if (READ_ONCE(sched->pause_submit))
		return;

	/* Find entity with a ready job */
	entity = drm_sched_select_entity(sched);
	if (!entity)
		return;	/* No more work */

	sched_job = drm_sched_entity_pop_job(entity);
	if (!sched_job) {
		complete_all(&entity->entity_idle);
		drm_sched_run_job_queue(sched);
		return;
	}

	s_fence = sched_job->s_fence;

	atomic_add(sched_job->credits, &sched->credit_count);
	drm_sched_job_begin(sched_job);

	trace_drm_run_job(sched_job, entity);
	fence = sched->ops->run_job(sched_job);
	complete_all(&entity->entity_idle);
	drm_sched_fence_scheduled(s_fence, fence);

	if (!IS_ERR_OR_NULL(fence)) {
		/* Drop for original kref_init of the fence */
		dma_fence_put(fence);

		r = dma_fence_add_callback(fence, &sched_job->cb,
					   drm_sched_job_done_cb);
		if (r == -ENOENT)
			drm_sched_job_done(sched_job, fence->error);
		else if (r)
			DRM_DEV_ERROR(sched->dev, "fence add callback failed (%d)\n", r);
	} else {
		drm_sched_job_done(sched_job, IS_ERR(fence) ?
				   PTR_ERR(fence) : 0);
	}

	wake_up(&sched->job_scheduled);
	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
 * @credit_limit: the number of credits this scheduler can hold from all jobs
 * @hang_limit: number of times to allow a job to hang before dropping it
 * @timeout: timeout value in jiffies for the scheduler
 * @timeout_wq: workqueue to use for timeout work. If NULL, the system_wq is
 *		used
 * @score: optional score atomic shared with other schedulers
 * @name: name used for debugging
 * @dev: target &struct device
 *
 * Return 0 on success, otherwise error code.
 */
int drm_sched_init(struct drm_gpu_scheduler *sched,
		   const struct drm_sched_backend_ops *ops,
		   struct workqueue_struct *submit_wq,
		   u32 num_rqs, u32 credit_limit, unsigned int hang_limit,
		   long timeout, struct workqueue_struct *timeout_wq,
		   atomic_t *score, const char *name, struct device *dev)
{
	int i;

	sched->ops = ops;
	sched->credit_limit = credit_limit;
	sched->name = name;
	sched->timeout = timeout;
	sched->timeout_wq = timeout_wq ? : system_wq;
	sched->hang_limit = hang_limit;
	sched->score = score ? score : &sched->_score;
	sched->dev = dev;

	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;
	}

	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;
	}

	sched->sched_rq = kmalloc_array(num_rqs, sizeof(*sched->sched_rq),
					GFP_KERNEL | __GFP_ZERO);
	if (!sched->sched_rq)
		goto Out_check_own;
	sched->num_rqs = num_rqs;
	for (i = DRM_SCHED_PRIORITY_KERNEL; 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->job_scheduled);
	INIT_LIST_HEAD(&sched->pending_list);
	spin_lock_init(&sched->job_list_lock);
	atomic_set(&sched->credit_count, 0);
	INIT_DELAYED_WORK(&sched->work_tdr, drm_sched_job_timedout);
	INIT_WORK(&sched->work_run_job, drm_sched_run_job_work);
	INIT_WORK(&sched->work_free_job, drm_sched_free_job_work);
	atomic_set(&sched->_score, 0);
	atomic64_set(&sched->job_id_count, 0);
	sched->pause_submit = false;

	sched->ready = true;
	return 0;
Out_unroll:
	for (--i ; i >= DRM_SCHED_PRIORITY_KERNEL; i--)
		kfree(sched->sched_rq[i]);

	kfree(sched->sched_rq);
	sched->sched_rq = NULL;
Out_check_own:
	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 -ENOMEM;
}
EXPORT_SYMBOL(drm_sched_init);

/**
 * drm_sched_fini - Destroy a gpu scheduler
 *
 * @sched: scheduler instance
 *
 * Tears down and cleans up the scheduler.
 */
void drm_sched_fini(struct drm_gpu_scheduler *sched)
{
	struct drm_sched_entity *s_entity;
	int i;

	drm_sched_wqueue_stop(sched);

	for (i = DRM_SCHED_PRIORITY_KERNEL; i < sched->num_rqs; i++) {
		struct drm_sched_rq *rq = sched->sched_rq[i];

		spin_lock(&rq->lock);
		list_for_each_entry(s_entity, &rq->entities, list)
			/*
			 * Prevents reinsertion and marks job_queue as idle,
			 * it will removed from rq in drm_sched_entity_fini
			 * eventually
			 */
			s_entity->stopped = true;
		spin_unlock(&rq->lock);
		kfree(sched->sched_rq[i]);
	}

	/* Wakeup everyone stuck in drm_sched_entity_flush for this scheduler */
	wake_up_all(&sched->job_scheduled);

	/* 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;
}
EXPORT_SYMBOL(drm_sched_fini);

/**
 * drm_sched_increase_karma - Update sched_entity guilty flag
 *
 * @bad: The job guilty of time out
 *
 * Increment on every hang caused by the 'bad' job. If this exceeds the hang
 * limit of the scheduler then the respective sched entity is marked guilty and
 * jobs from it will not be scheduled further
 */
void drm_sched_increase_karma(struct drm_sched_job *bad)
{
	int i;
	struct drm_sched_entity *tmp;
	struct drm_sched_entity *entity;
	struct drm_gpu_scheduler *sched = bad->sched;

	/* don't change @bad's karma if it's from KERNEL RQ,
	 * because sometimes GPU hang would cause kernel jobs (like VM updating jobs)
	 * corrupt but keep in mind that kernel jobs always considered good.
	 */
	if (bad->s_priority != DRM_SCHED_PRIORITY_KERNEL) {
		atomic_inc(&bad->karma);

		for (i = DRM_SCHED_PRIORITY_HIGH; i < sched->num_rqs; i++) {
			struct drm_sched_rq *rq = sched->sched_rq[i];

			spin_lock(&rq->lock);
			list_for_each_entry_safe(entity, tmp, &rq->entities, list) {
				if (bad->s_fence->scheduled.context ==
				    entity->fence_context) {
					if (entity->guilty)
						atomic_set(entity->guilty, 1);
					break;
				}
			}
			spin_unlock(&rq->lock);
			if (&entity->list != &rq->entities)
				break;
		}
	}
}
EXPORT_SYMBOL(drm_sched_increase_karma);

/**
 * drm_sched_wqueue_ready - Is the scheduler ready for submission
 *
 * @sched: scheduler instance
 *
 * Returns true if submission is ready
 */
bool drm_sched_wqueue_ready(struct drm_gpu_scheduler *sched)
{
	return sched->ready;
}
EXPORT_SYMBOL(drm_sched_wqueue_ready);

/**
 * drm_sched_wqueue_stop - stop scheduler submission
 *
 * @sched: scheduler instance
 */
void drm_sched_wqueue_stop(struct drm_gpu_scheduler *sched)
{
	WRITE_ONCE(sched->pause_submit, true);
	cancel_work_sync(&sched->work_run_job);
	cancel_work_sync(&sched->work_free_job);
}
EXPORT_SYMBOL(drm_sched_wqueue_stop);

/**
 * drm_sched_wqueue_start - start scheduler submission
 *
 * @sched: scheduler instance
 */
void drm_sched_wqueue_start(struct drm_gpu_scheduler *sched)
{
	WRITE_ONCE(sched->pause_submit, false);
	queue_work(sched->submit_wq, &sched->work_run_job);
	queue_work(sched->submit_wq, &sched->work_free_job);
}
EXPORT_SYMBOL(drm_sched_wqueue_start);