summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
blob: 82823d9a8ba8874e33959ef389465210a91f46f2 (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
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
/*
 * Copyright 2008 Jerome Glisse.
 * All Rights Reserved.
 *
 * 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 (including the next
 * paragraph) 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
 * PRECISION INSIGHT AND/OR ITS SUPPLIERS 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.
 *
 * Authors:
 *    Jerome Glisse <glisse@freedesktop.org>
 */

#include <linux/file.h>
#include <linux/pagemap.h>
#include <linux/sync_file.h>

#include <drm/amdgpu_drm.h>
#include <drm/drm_syncobj.h>
#include "amdgpu.h"
#include "amdgpu_trace.h"
#include "amdgpu_gmc.h"
#include "amdgpu_gem.h"

static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p,
				      struct drm_amdgpu_cs_chunk_fence *data,
				      uint32_t *offset)
{
	struct drm_gem_object *gobj;
	struct amdgpu_bo *bo;
	unsigned long size;
	int r;

	gobj = drm_gem_object_lookup(p->filp, data->handle);
	if (gobj == NULL)
		return -EINVAL;

	bo = amdgpu_bo_ref(gem_to_amdgpu_bo(gobj));
	p->uf_entry.priority = 0;
	p->uf_entry.tv.bo = &bo->tbo;
	/* One for TTM and one for the CS job */
	p->uf_entry.tv.num_shared = 2;

	drm_gem_object_put_unlocked(gobj);

	size = amdgpu_bo_size(bo);
	if (size != PAGE_SIZE || (data->offset + 8) > size) {
		r = -EINVAL;
		goto error_unref;
	}

	if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm)) {
		r = -EINVAL;
		goto error_unref;
	}

	*offset = data->offset;

	return 0;

error_unref:
	amdgpu_bo_unref(&bo);
	return r;
}

static int amdgpu_cs_bo_handles_chunk(struct amdgpu_cs_parser *p,
				      struct drm_amdgpu_bo_list_in *data)
{
	int r;
	struct drm_amdgpu_bo_list_entry *info = NULL;

	r = amdgpu_bo_create_list_entry_array(data, &info);
	if (r)
		return r;

	r = amdgpu_bo_list_create(p->adev, p->filp, info, data->bo_number,
				  &p->bo_list);
	if (r)
		goto error_free;

	kvfree(info);
	return 0;

error_free:
	if (info)
		kvfree(info);

	return r;
}

static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs *cs)
{
	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
	struct amdgpu_vm *vm = &fpriv->vm;
	uint64_t *chunk_array_user;
	uint64_t *chunk_array;
	unsigned size, num_ibs = 0;
	uint32_t uf_offset = 0;
	int i;
	int ret;

	if (cs->in.num_chunks == 0)
		return 0;

	chunk_array = kmalloc_array(cs->in.num_chunks, sizeof(uint64_t), GFP_KERNEL);
	if (!chunk_array)
		return -ENOMEM;

	p->ctx = amdgpu_ctx_get(fpriv, cs->in.ctx_id);
	if (!p->ctx) {
		ret = -EINVAL;
		goto free_chunk;
	}

	mutex_lock(&p->ctx->lock);

	/* skip guilty context job */
	if (atomic_read(&p->ctx->guilty) == 1) {
		ret = -ECANCELED;
		goto free_chunk;
	}

	/* get chunks */
	chunk_array_user = u64_to_user_ptr(cs->in.chunks);
	if (copy_from_user(chunk_array, chunk_array_user,
			   sizeof(uint64_t)*cs->in.num_chunks)) {
		ret = -EFAULT;
		goto free_chunk;
	}

	p->nchunks = cs->in.num_chunks;
	p->chunks = kmalloc_array(p->nchunks, sizeof(struct amdgpu_cs_chunk),
			    GFP_KERNEL);
	if (!p->chunks) {
		ret = -ENOMEM;
		goto free_chunk;
	}

	for (i = 0; i < p->nchunks; i++) {
		struct drm_amdgpu_cs_chunk __user **chunk_ptr = NULL;
		struct drm_amdgpu_cs_chunk user_chunk;
		uint32_t __user *cdata;

		chunk_ptr = u64_to_user_ptr(chunk_array[i]);
		if (copy_from_user(&user_chunk, chunk_ptr,
				       sizeof(struct drm_amdgpu_cs_chunk))) {
			ret = -EFAULT;
			i--;
			goto free_partial_kdata;
		}
		p->chunks[i].chunk_id = user_chunk.chunk_id;
		p->chunks[i].length_dw = user_chunk.length_dw;

		size = p->chunks[i].length_dw;
		cdata = u64_to_user_ptr(user_chunk.chunk_data);

		p->chunks[i].kdata = kvmalloc_array(size, sizeof(uint32_t), GFP_KERNEL);
		if (p->chunks[i].kdata == NULL) {
			ret = -ENOMEM;
			i--;
			goto free_partial_kdata;
		}
		size *= sizeof(uint32_t);
		if (copy_from_user(p->chunks[i].kdata, cdata, size)) {
			ret = -EFAULT;
			goto free_partial_kdata;
		}

		switch (p->chunks[i].chunk_id) {
		case AMDGPU_CHUNK_ID_IB:
			++num_ibs;
			break;

		case AMDGPU_CHUNK_ID_FENCE:
			size = sizeof(struct drm_amdgpu_cs_chunk_fence);
			if (p->chunks[i].length_dw * sizeof(uint32_t) < size) {
				ret = -EINVAL;
				goto free_partial_kdata;
			}

			ret = amdgpu_cs_user_fence_chunk(p, p->chunks[i].kdata,
							 &uf_offset);
			if (ret)
				goto free_partial_kdata;

			break;

		case AMDGPU_CHUNK_ID_BO_HANDLES:
			size = sizeof(struct drm_amdgpu_bo_list_in);
			if (p->chunks[i].length_dw * sizeof(uint32_t) < size) {
				ret = -EINVAL;
				goto free_partial_kdata;
			}

			ret = amdgpu_cs_bo_handles_chunk(p, p->chunks[i].kdata);
			if (ret)
				goto free_partial_kdata;

			break;

		case AMDGPU_CHUNK_ID_DEPENDENCIES:
		case AMDGPU_CHUNK_ID_SYNCOBJ_IN:
		case AMDGPU_CHUNK_ID_SYNCOBJ_OUT:
		case AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES:
		case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT:
		case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL:
			break;

		default:
			ret = -EINVAL;
			goto free_partial_kdata;
		}
	}

	ret = amdgpu_job_alloc(p->adev, num_ibs, &p->job, vm);
	if (ret)
		goto free_all_kdata;

	if (p->ctx->vram_lost_counter != p->job->vram_lost_counter) {
		ret = -ECANCELED;
		goto free_all_kdata;
	}

	if (p->uf_entry.tv.bo)
		p->job->uf_addr = uf_offset;
	kfree(chunk_array);

	/* Use this opportunity to fill in task info for the vm */
	amdgpu_vm_set_task_info(vm);

	return 0;

free_all_kdata:
	i = p->nchunks - 1;
free_partial_kdata:
	for (; i >= 0; i--)
		kvfree(p->chunks[i].kdata);
	kfree(p->chunks);
	p->chunks = NULL;
	p->nchunks = 0;
free_chunk:
	kfree(chunk_array);

	return ret;
}

/* Convert microseconds to bytes. */
static u64 us_to_bytes(struct amdgpu_device *adev, s64 us)
{
	if (us <= 0 || !adev->mm_stats.log2_max_MBps)
		return 0;

	/* Since accum_us is incremented by a million per second, just
	 * multiply it by the number of MB/s to get the number of bytes.
	 */
	return us << adev->mm_stats.log2_max_MBps;
}

static s64 bytes_to_us(struct amdgpu_device *adev, u64 bytes)
{
	if (!adev->mm_stats.log2_max_MBps)
		return 0;

	return bytes >> adev->mm_stats.log2_max_MBps;
}

/* Returns how many bytes TTM can move right now. If no bytes can be moved,
 * it returns 0. If it returns non-zero, it's OK to move at least one buffer,
 * which means it can go over the threshold once. If that happens, the driver
 * will be in debt and no other buffer migrations can be done until that debt
 * is repaid.
 *
 * This approach allows moving a buffer of any size (it's important to allow
 * that).
 *
 * The currency is simply time in microseconds and it increases as the clock
 * ticks. The accumulated microseconds (us) are converted to bytes and
 * returned.
 */
static void amdgpu_cs_get_threshold_for_moves(struct amdgpu_device *adev,
					      u64 *max_bytes,
					      u64 *max_vis_bytes)
{
	s64 time_us, increment_us;
	u64 free_vram, total_vram, used_vram;

	/* Allow a maximum of 200 accumulated ms. This is basically per-IB
	 * throttling.
	 *
	 * It means that in order to get full max MBps, at least 5 IBs per
	 * second must be submitted and not more than 200ms apart from each
	 * other.
	 */
	const s64 us_upper_bound = 200000;

	if (!adev->mm_stats.log2_max_MBps) {
		*max_bytes = 0;
		*max_vis_bytes = 0;
		return;
	}

	total_vram = adev->gmc.real_vram_size - atomic64_read(&adev->vram_pin_size);
	used_vram = amdgpu_vram_mgr_usage(&adev->mman.bdev.man[TTM_PL_VRAM]);
	free_vram = used_vram >= total_vram ? 0 : total_vram - used_vram;

	spin_lock(&adev->mm_stats.lock);

	/* Increase the amount of accumulated us. */
	time_us = ktime_to_us(ktime_get());
	increment_us = time_us - adev->mm_stats.last_update_us;
	adev->mm_stats.last_update_us = time_us;
	adev->mm_stats.accum_us = min(adev->mm_stats.accum_us + increment_us,
                                      us_upper_bound);

	/* This prevents the short period of low performance when the VRAM
	 * usage is low and the driver is in debt or doesn't have enough
	 * accumulated us to fill VRAM quickly.
	 *
	 * The situation can occur in these cases:
	 * - a lot of VRAM is freed by userspace
	 * - the presence of a big buffer causes a lot of evictions
	 *   (solution: split buffers into smaller ones)
	 *
	 * If 128 MB or 1/8th of VRAM is free, start filling it now by setting
	 * accum_us to a positive number.
	 */
	if (free_vram >= 128 * 1024 * 1024 || free_vram >= total_vram / 8) {
		s64 min_us;

		/* Be more aggresive on dGPUs. Try to fill a portion of free
		 * VRAM now.
		 */
		if (!(adev->flags & AMD_IS_APU))
			min_us = bytes_to_us(adev, free_vram / 4);
		else
			min_us = 0; /* Reset accum_us on APUs. */

		adev->mm_stats.accum_us = max(min_us, adev->mm_stats.accum_us);
	}

	/* This is set to 0 if the driver is in debt to disallow (optional)
	 * buffer moves.
	 */
	*max_bytes = us_to_bytes(adev, adev->mm_stats.accum_us);

	/* Do the same for visible VRAM if half of it is free */
	if (!amdgpu_gmc_vram_full_visible(&adev->gmc)) {
		u64 total_vis_vram = adev->gmc.visible_vram_size;
		u64 used_vis_vram =
			amdgpu_vram_mgr_vis_usage(&adev->mman.bdev.man[TTM_PL_VRAM]);

		if (used_vis_vram < total_vis_vram) {
			u64 free_vis_vram = total_vis_vram - used_vis_vram;
			adev->mm_stats.accum_us_vis = min(adev->mm_stats.accum_us_vis +
							  increment_us, us_upper_bound);

			if (free_vis_vram >= total_vis_vram / 2)
				adev->mm_stats.accum_us_vis =
					max(bytes_to_us(adev, free_vis_vram / 2),
					    adev->mm_stats.accum_us_vis);
		}

		*max_vis_bytes = us_to_bytes(adev, adev->mm_stats.accum_us_vis);
	} else {
		*max_vis_bytes = 0;
	}

	spin_unlock(&adev->mm_stats.lock);
}

/* Report how many bytes have really been moved for the last command
 * submission. This can result in a debt that can stop buffer migrations
 * temporarily.
 */
void amdgpu_cs_report_moved_bytes(struct amdgpu_device *adev, u64 num_bytes,
				  u64 num_vis_bytes)
{
	spin_lock(&adev->mm_stats.lock);
	adev->mm_stats.accum_us -= bytes_to_us(adev, num_bytes);
	adev->mm_stats.accum_us_vis -= bytes_to_us(adev, num_vis_bytes);
	spin_unlock(&adev->mm_stats.lock);
}

static int amdgpu_cs_bo_validate(struct amdgpu_cs_parser *p,
				 struct amdgpu_bo *bo)
{
	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
	struct ttm_operation_ctx ctx = {
		.interruptible = true,
		.no_wait_gpu = false,
		.resv = bo->tbo.base.resv,
		.flags = 0
	};
	uint32_t domain;
	int r;

	if (bo->pin_count)
		return 0;

	/* Don't move this buffer if we have depleted our allowance
	 * to move it. Don't move anything if the threshold is zero.
	 */
	if (p->bytes_moved < p->bytes_moved_threshold) {
		if (!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
		    (bo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED)) {
			/* And don't move a CPU_ACCESS_REQUIRED BO to limited
			 * visible VRAM if we've depleted our allowance to do
			 * that.
			 */
			if (p->bytes_moved_vis < p->bytes_moved_vis_threshold)
				domain = bo->preferred_domains;
			else
				domain = bo->allowed_domains;
		} else {
			domain = bo->preferred_domains;
		}
	} else {
		domain = bo->allowed_domains;
	}

retry:
	amdgpu_bo_placement_from_domain(bo, domain);
	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);

	p->bytes_moved += ctx.bytes_moved;
	if (!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
	    amdgpu_bo_in_cpu_visible_vram(bo))
		p->bytes_moved_vis += ctx.bytes_moved;

	if (unlikely(r == -ENOMEM) && domain != bo->allowed_domains) {
		domain = bo->allowed_domains;
		goto retry;
	}

	return r;
}

/* Last resort, try to evict something from the current working set */
static bool amdgpu_cs_try_evict(struct amdgpu_cs_parser *p,
				struct amdgpu_bo *validated)
{
	uint32_t domain = validated->allowed_domains;
	struct ttm_operation_ctx ctx = { true, false };
	int r;

	if (!p->evictable)
		return false;

	for (;&p->evictable->tv.head != &p->validated;
	     p->evictable = list_prev_entry(p->evictable, tv.head)) {

		struct amdgpu_bo_list_entry *candidate = p->evictable;
		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(candidate->tv.bo);
		struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
		bool update_bytes_moved_vis;
		uint32_t other;

		/* If we reached our current BO we can forget it */
		if (bo == validated)
			break;

		/* We can't move pinned BOs here */
		if (bo->pin_count)
			continue;

		other = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type);

		/* Check if this BO is in one of the domains we need space for */
		if (!(other & domain))
			continue;

		/* Check if we can move this BO somewhere else */
		other = bo->allowed_domains & ~domain;
		if (!other)
			continue;

		/* Good we can try to move this BO somewhere else */
		update_bytes_moved_vis =
				!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
				amdgpu_bo_in_cpu_visible_vram(bo);
		amdgpu_bo_placement_from_domain(bo, other);
		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
		p->bytes_moved += ctx.bytes_moved;
		if (update_bytes_moved_vis)
			p->bytes_moved_vis += ctx.bytes_moved;

		if (unlikely(r))
			break;

		p->evictable = list_prev_entry(p->evictable, tv.head);
		list_move(&candidate->tv.head, &p->validated);

		return true;
	}

	return false;
}

static int amdgpu_cs_validate(void *param, struct amdgpu_bo *bo)
{
	struct amdgpu_cs_parser *p = param;
	int r;

	do {
		r = amdgpu_cs_bo_validate(p, bo);
	} while (r == -ENOMEM && amdgpu_cs_try_evict(p, bo));
	if (r)
		return r;

	if (bo->shadow)
		r = amdgpu_cs_bo_validate(p, bo->shadow);

	return r;
}

static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p,
			    struct list_head *validated)
{
	struct ttm_operation_ctx ctx = { true, false };
	struct amdgpu_bo_list_entry *lobj;
	int r;

	list_for_each_entry(lobj, validated, tv.head) {
		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(lobj->tv.bo);
		struct mm_struct *usermm;

		usermm = amdgpu_ttm_tt_get_usermm(bo->tbo.ttm);
		if (usermm && usermm != current->mm)
			return -EPERM;

		if (amdgpu_ttm_tt_is_userptr(bo->tbo.ttm) &&
		    lobj->user_invalidated && lobj->user_pages) {
			amdgpu_bo_placement_from_domain(bo,
							AMDGPU_GEM_DOMAIN_CPU);
			r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
			if (r)
				return r;

			amdgpu_ttm_tt_set_user_pages(bo->tbo.ttm,
						     lobj->user_pages);
		}

		if (p->evictable == lobj)
			p->evictable = NULL;

		r = amdgpu_cs_validate(p, bo);
		if (r)
			return r;

		kvfree(lobj->user_pages);
		lobj->user_pages = NULL;
	}
	return 0;
}

static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
				union drm_amdgpu_cs *cs)
{
	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
	struct amdgpu_vm *vm = &fpriv->vm;
	struct amdgpu_bo_list_entry *e;
	struct list_head duplicates;
	struct amdgpu_bo *gds;
	struct amdgpu_bo *gws;
	struct amdgpu_bo *oa;
	int r;

	INIT_LIST_HEAD(&p->validated);

	/* p->bo_list could already be assigned if AMDGPU_CHUNK_ID_BO_HANDLES is present */
	if (cs->in.bo_list_handle) {
		if (p->bo_list)
			return -EINVAL;

		r = amdgpu_bo_list_get(fpriv, cs->in.bo_list_handle,
				       &p->bo_list);
		if (r)
			return r;
	} else if (!p->bo_list) {
		/* Create a empty bo_list when no handle is provided */
		r = amdgpu_bo_list_create(p->adev, p->filp, NULL, 0,
					  &p->bo_list);
		if (r)
			return r;
	}

	/* One for TTM and one for the CS job */
	amdgpu_bo_list_for_each_entry(e, p->bo_list)
		e->tv.num_shared = 2;

	amdgpu_bo_list_get_list(p->bo_list, &p->validated);
	if (p->bo_list->first_userptr != p->bo_list->num_entries)
		p->mn = amdgpu_mn_get(p->adev, AMDGPU_MN_TYPE_GFX);

	INIT_LIST_HEAD(&duplicates);
	amdgpu_vm_get_pd_bo(&fpriv->vm, &p->validated, &p->vm_pd);

	if (p->uf_entry.tv.bo && !ttm_to_amdgpu_bo(p->uf_entry.tv.bo)->parent)
		list_add(&p->uf_entry.tv.head, &p->validated);

	/* Get userptr backing pages. If pages are updated after registered
	 * in amdgpu_gem_userptr_ioctl(), amdgpu_cs_list_validate() will do
	 * amdgpu_ttm_backend_bind() to flush and invalidate new pages
	 */
	amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) {
		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo);
		bool userpage_invalidated = false;
		int i;

		e->user_pages = kvmalloc_array(bo->tbo.ttm->num_pages,
					sizeof(struct page *),
					GFP_KERNEL | __GFP_ZERO);
		if (!e->user_pages) {
			DRM_ERROR("calloc failure\n");
			return -ENOMEM;
		}

		r = amdgpu_ttm_tt_get_user_pages(bo, e->user_pages);
		if (r) {
			kvfree(e->user_pages);
			e->user_pages = NULL;
			return r;
		}

		for (i = 0; i < bo->tbo.ttm->num_pages; i++) {
			if (bo->tbo.ttm->pages[i] != e->user_pages[i]) {
				userpage_invalidated = true;
				break;
			}
		}
		e->user_invalidated = userpage_invalidated;
	}

	r = ttm_eu_reserve_buffers(&p->ticket, &p->validated, true,
				   &duplicates, false);
	if (unlikely(r != 0)) {
		if (r != -ERESTARTSYS)
			DRM_ERROR("ttm_eu_reserve_buffers failed.\n");
		goto out;
	}

	amdgpu_cs_get_threshold_for_moves(p->adev, &p->bytes_moved_threshold,
					  &p->bytes_moved_vis_threshold);
	p->bytes_moved = 0;
	p->bytes_moved_vis = 0;
	p->evictable = list_last_entry(&p->validated,
				       struct amdgpu_bo_list_entry,
				       tv.head);

	r = amdgpu_vm_validate_pt_bos(p->adev, &fpriv->vm,
				      amdgpu_cs_validate, p);
	if (r) {
		DRM_ERROR("amdgpu_vm_validate_pt_bos() failed.\n");
		goto error_validate;
	}

	r = amdgpu_cs_list_validate(p, &duplicates);
	if (r)
		goto error_validate;

	r = amdgpu_cs_list_validate(p, &p->validated);
	if (r)
		goto error_validate;

	amdgpu_cs_report_moved_bytes(p->adev, p->bytes_moved,
				     p->bytes_moved_vis);

	gds = p->bo_list->gds_obj;
	gws = p->bo_list->gws_obj;
	oa = p->bo_list->oa_obj;

	amdgpu_bo_list_for_each_entry(e, p->bo_list) {
		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo);

		/* Make sure we use the exclusive slot for shared BOs */
		if (bo->prime_shared_count)
			e->tv.num_shared = 0;
		e->bo_va = amdgpu_vm_bo_find(vm, bo);
	}

	if (gds) {
		p->job->gds_base = amdgpu_bo_gpu_offset(gds) >> PAGE_SHIFT;
		p->job->gds_size = amdgpu_bo_size(gds) >> PAGE_SHIFT;
	}
	if (gws) {
		p->job->gws_base = amdgpu_bo_gpu_offset(gws) >> PAGE_SHIFT;
		p->job->gws_size = amdgpu_bo_size(gws) >> PAGE_SHIFT;
	}
	if (oa) {
		p->job->oa_base = amdgpu_bo_gpu_offset(oa) >> PAGE_SHIFT;
		p->job->oa_size = amdgpu_bo_size(oa) >> PAGE_SHIFT;
	}

	if (!r && p->uf_entry.tv.bo) {
		struct amdgpu_bo *uf = ttm_to_amdgpu_bo(p->uf_entry.tv.bo);

		r = amdgpu_ttm_alloc_gart(&uf->tbo);
		p->job->uf_addr += amdgpu_bo_gpu_offset(uf);
	}

error_validate:
	if (r)
		ttm_eu_backoff_reservation(&p->ticket, &p->validated);
out:
	return r;
}

static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p)
{
	struct amdgpu_bo_list_entry *e;
	int r;

	list_for_each_entry(e, &p->validated, tv.head) {
		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo);
		struct dma_resv *resv = bo->tbo.base.resv;

		r = amdgpu_sync_resv(p->adev, &p->job->sync, resv, p->filp,
				     amdgpu_bo_explicit_sync(bo));

		if (r)
			return r;
	}
	return 0;
}

/**
 * cs_parser_fini() - clean parser states
 * @parser:	parser structure holding parsing context.
 * @error:	error number
 *
 * If error is set than unvalidate buffer, otherwise just free memory
 * used by parsing context.
 **/
static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error,
				  bool backoff)
{
	unsigned i;

	if (error && backoff)
		ttm_eu_backoff_reservation(&parser->ticket,
					   &parser->validated);

	for (i = 0; i < parser->num_post_deps; i++) {
		drm_syncobj_put(parser->post_deps[i].syncobj);
		kfree(parser->post_deps[i].chain);
	}
	kfree(parser->post_deps);

	dma_fence_put(parser->fence);

	if (parser->ctx) {
		mutex_unlock(&parser->ctx->lock);
		amdgpu_ctx_put(parser->ctx);
	}
	if (parser->bo_list)
		amdgpu_bo_list_put(parser->bo_list);

	for (i = 0; i < parser->nchunks; i++)
		kvfree(parser->chunks[i].kdata);
	kfree(parser->chunks);
	if (parser->job)
		amdgpu_job_free(parser->job);
	if (parser->uf_entry.tv.bo) {
		struct amdgpu_bo *uf = ttm_to_amdgpu_bo(parser->uf_entry.tv.bo);

		amdgpu_bo_unref(&uf);
	}
}

static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
{
	struct amdgpu_ring *ring = to_amdgpu_ring(p->entity->rq->sched);
	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
	struct amdgpu_device *adev = p->adev;
	struct amdgpu_vm *vm = &fpriv->vm;
	struct amdgpu_bo_list_entry *e;
	struct amdgpu_bo_va *bo_va;
	struct amdgpu_bo *bo;
	int r;

	/* Only for UVD/VCE VM emulation */
	if (ring->funcs->parse_cs || ring->funcs->patch_cs_in_place) {
		unsigned i, j;

		for (i = 0, j = 0; i < p->nchunks && j < p->job->num_ibs; i++) {
			struct drm_amdgpu_cs_chunk_ib *chunk_ib;
			struct amdgpu_bo_va_mapping *m;
			struct amdgpu_bo *aobj = NULL;
			struct amdgpu_cs_chunk *chunk;
			uint64_t offset, va_start;
			struct amdgpu_ib *ib;
			uint8_t *kptr;

			chunk = &p->chunks[i];
			ib = &p->job->ibs[j];
			chunk_ib = chunk->kdata;

			if (chunk->chunk_id != AMDGPU_CHUNK_ID_IB)
				continue;

			va_start = chunk_ib->va_start & AMDGPU_GMC_HOLE_MASK;
			r = amdgpu_cs_find_mapping(p, va_start, &aobj, &m);
			if (r) {
				DRM_ERROR("IB va_start is invalid\n");
				return r;
			}

			if ((va_start + chunk_ib->ib_bytes) >
			    (m->last + 1) * AMDGPU_GPU_PAGE_SIZE) {
				DRM_ERROR("IB va_start+ib_bytes is invalid\n");
				return -EINVAL;
			}

			/* the IB should be reserved at this point */
			r = amdgpu_bo_kmap(aobj, (void **)&kptr);
			if (r) {
				return r;
			}

			offset = m->start * AMDGPU_GPU_PAGE_SIZE;
			kptr += va_start - offset;

			if (ring->funcs->parse_cs) {
				memcpy(ib->ptr, kptr, chunk_ib->ib_bytes);
				amdgpu_bo_kunmap(aobj);

				r = amdgpu_ring_parse_cs(ring, p, j);
				if (r)
					return r;
			} else {
				ib->ptr = (uint32_t *)kptr;
				r = amdgpu_ring_patch_cs_in_place(ring, p, j);
				amdgpu_bo_kunmap(aobj);
				if (r)
					return r;
			}

			j++;
		}
	}

	if (!p->job->vm)
		return amdgpu_cs_sync_rings(p);


	r = amdgpu_vm_clear_freed(adev, vm, NULL);
	if (r)
		return r;

	r = amdgpu_vm_bo_update(adev, fpriv->prt_va, false);
	if (r)
		return r;

	r = amdgpu_sync_fence(adev, &p->job->sync,
			      fpriv->prt_va->last_pt_update, false);
	if (r)
		return r;

	if (amdgpu_mcbp || amdgpu_sriov_vf(adev)) {
		struct dma_fence *f;

		bo_va = fpriv->csa_va;
		BUG_ON(!bo_va);
		r = amdgpu_vm_bo_update(adev, bo_va, false);
		if (r)
			return r;

		f = bo_va->last_pt_update;
		r = amdgpu_sync_fence(adev, &p->job->sync, f, false);
		if (r)
			return r;
	}

	amdgpu_bo_list_for_each_entry(e, p->bo_list) {
		struct dma_fence *f;

		/* ignore duplicates */
		bo = ttm_to_amdgpu_bo(e->tv.bo);
		if (!bo)
			continue;

		bo_va = e->bo_va;
		if (bo_va == NULL)
			continue;

		r = amdgpu_vm_bo_update(adev, bo_va, false);
		if (r)
			return r;

		f = bo_va->last_pt_update;
		r = amdgpu_sync_fence(adev, &p->job->sync, f, false);
		if (r)
			return r;
	}

	r = amdgpu_vm_handle_moved(adev, vm);
	if (r)
		return r;

	r = amdgpu_vm_update_directories(adev, vm);
	if (r)
		return r;

	r = amdgpu_sync_fence(adev, &p->job->sync, vm->last_update, false);
	if (r)
		return r;

	p->job->vm_pd_addr = amdgpu_gmc_pd_addr(vm->root.base.bo);

	if (amdgpu_vm_debug) {
		/* Invalidate all BOs to test for userspace bugs */
		amdgpu_bo_list_for_each_entry(e, p->bo_list) {
			struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo);

			/* ignore duplicates */
			if (!bo)
				continue;

			amdgpu_vm_bo_invalidate(adev, bo, false);
		}
	}

	return amdgpu_cs_sync_rings(p);
}

static int amdgpu_cs_ib_fill(struct amdgpu_device *adev,
			     struct amdgpu_cs_parser *parser)
{
	struct amdgpu_fpriv *fpriv = parser->filp->driver_priv;
	struct amdgpu_vm *vm = &fpriv->vm;
	int r, ce_preempt = 0, de_preempt = 0;
	struct amdgpu_ring *ring;
	int i, j;

	for (i = 0, j = 0; i < parser->nchunks && j < parser->job->num_ibs; i++) {
		struct amdgpu_cs_chunk *chunk;
		struct amdgpu_ib *ib;
		struct drm_amdgpu_cs_chunk_ib *chunk_ib;
		struct drm_sched_entity *entity;

		chunk = &parser->chunks[i];
		ib = &parser->job->ibs[j];
		chunk_ib = (struct drm_amdgpu_cs_chunk_ib *)chunk->kdata;

		if (chunk->chunk_id != AMDGPU_CHUNK_ID_IB)
			continue;

		if (chunk_ib->ip_type == AMDGPU_HW_IP_GFX &&
		    (amdgpu_mcbp || amdgpu_sriov_vf(adev))) {
			if (chunk_ib->flags & AMDGPU_IB_FLAG_PREEMPT) {
				if (chunk_ib->flags & AMDGPU_IB_FLAG_CE)
					ce_preempt++;
				else
					de_preempt++;
			}

			/* each GFX command submit allows 0 or 1 IB preemptible for CE & DE */
			if (ce_preempt > 1 || de_preempt > 1)
				return -EINVAL;
		}

		r = amdgpu_ctx_get_entity(parser->ctx, chunk_ib->ip_type,
					  chunk_ib->ip_instance, chunk_ib->ring,
					  &entity);
		if (r)
			return r;

		if (chunk_ib->flags & AMDGPU_IB_FLAG_PREAMBLE)
			parser->job->preamble_status |=
				AMDGPU_PREAMBLE_IB_PRESENT;

		if (parser->entity && parser->entity != entity)
			return -EINVAL;

		parser->entity = entity;

		ring = to_amdgpu_ring(entity->rq->sched);
		r =  amdgpu_ib_get(adev, vm, ring->funcs->parse_cs ?
				   chunk_ib->ib_bytes : 0, ib);
		if (r) {
			DRM_ERROR("Failed to get ib !\n");
			return r;
		}

		ib->gpu_addr = chunk_ib->va_start;
		ib->length_dw = chunk_ib->ib_bytes / 4;
		ib->flags = chunk_ib->flags;

		j++;
	}

	/* MM engine doesn't support user fences */
	ring = to_amdgpu_ring(parser->entity->rq->sched);
	if (parser->job->uf_addr && ring->funcs->no_user_fence)
		return -EINVAL;

	return amdgpu_ctx_wait_prev_fence(parser->ctx, parser->entity);
}

static int amdgpu_cs_process_fence_dep(struct amdgpu_cs_parser *p,
				       struct amdgpu_cs_chunk *chunk)
{
	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
	unsigned num_deps;
	int i, r;
	struct drm_amdgpu_cs_chunk_dep *deps;

	deps = (struct drm_amdgpu_cs_chunk_dep *)chunk->kdata;
	num_deps = chunk->length_dw * 4 /
		sizeof(struct drm_amdgpu_cs_chunk_dep);

	for (i = 0; i < num_deps; ++i) {
		struct amdgpu_ctx *ctx;
		struct drm_sched_entity *entity;
		struct dma_fence *fence;

		ctx = amdgpu_ctx_get(fpriv, deps[i].ctx_id);
		if (ctx == NULL)
			return -EINVAL;

		r = amdgpu_ctx_get_entity(ctx, deps[i].ip_type,
					  deps[i].ip_instance,
					  deps[i].ring, &entity);
		if (r) {
			amdgpu_ctx_put(ctx);
			return r;
		}

		fence = amdgpu_ctx_get_fence(ctx, entity, deps[i].handle);
		amdgpu_ctx_put(ctx);

		if (IS_ERR(fence))
			return PTR_ERR(fence);
		else if (!fence)
			continue;

		if (chunk->chunk_id == AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES) {
			struct drm_sched_fence *s_fence;
			struct dma_fence *old = fence;

			s_fence = to_drm_sched_fence(fence);
			fence = dma_fence_get(&s_fence->scheduled);
			dma_fence_put(old);
		}

		r = amdgpu_sync_fence(p->adev, &p->job->sync, fence, true);
		dma_fence_put(fence);
		if (r)
			return r;
	}
	return 0;
}

static int amdgpu_syncobj_lookup_and_add_to_sync(struct amdgpu_cs_parser *p,
						 uint32_t handle, u64 point,
						 u64 flags)
{
	struct dma_fence *fence;
	int r;

	r = drm_syncobj_find_fence(p->filp, handle, point, flags, &fence);
	if (r) {
		DRM_ERROR("syncobj %u failed to find fence @ %llu (%d)!\n",
			  handle, point, r);
		return r;
	}

	r = amdgpu_sync_fence(p->adev, &p->job->sync, fence, true);
	dma_fence_put(fence);

	return r;
}

static int amdgpu_cs_process_syncobj_in_dep(struct amdgpu_cs_parser *p,
					    struct amdgpu_cs_chunk *chunk)
{
	struct drm_amdgpu_cs_chunk_sem *deps;
	unsigned num_deps;
	int i, r;

	deps = (struct drm_amdgpu_cs_chunk_sem *)chunk->kdata;
	num_deps = chunk->length_dw * 4 /
		sizeof(struct drm_amdgpu_cs_chunk_sem);
	for (i = 0; i < num_deps; ++i) {
		r = amdgpu_syncobj_lookup_and_add_to_sync(p, deps[i].handle,
							  0, 0);
		if (r)
			return r;
	}

	return 0;
}


static int amdgpu_cs_process_syncobj_timeline_in_dep(struct amdgpu_cs_parser *p,
						     struct amdgpu_cs_chunk *chunk)
{
	struct drm_amdgpu_cs_chunk_syncobj *syncobj_deps;
	unsigned num_deps;
	int i, r;

	syncobj_deps = (struct drm_amdgpu_cs_chunk_syncobj *)chunk->kdata;
	num_deps = chunk->length_dw * 4 /
		sizeof(struct drm_amdgpu_cs_chunk_syncobj);
	for (i = 0; i < num_deps; ++i) {
		r = amdgpu_syncobj_lookup_and_add_to_sync(p,
							  syncobj_deps[i].handle,
							  syncobj_deps[i].point,
							  syncobj_deps[i].flags);
		if (r)
			return r;
	}

	return 0;
}

static int amdgpu_cs_process_syncobj_out_dep(struct amdgpu_cs_parser *p,
					     struct amdgpu_cs_chunk *chunk)
{
	struct drm_amdgpu_cs_chunk_sem *deps;
	unsigned num_deps;
	int i;

	deps = (struct drm_amdgpu_cs_chunk_sem *)chunk->kdata;
	num_deps = chunk->length_dw * 4 /
		sizeof(struct drm_amdgpu_cs_chunk_sem);

	if (p->post_deps)
		return -EINVAL;

	p->post_deps = kmalloc_array(num_deps, sizeof(*p->post_deps),
				     GFP_KERNEL);
	p->num_post_deps = 0;

	if (!p->post_deps)
		return -ENOMEM;


	for (i = 0; i < num_deps; ++i) {
		p->post_deps[i].syncobj =
			drm_syncobj_find(p->filp, deps[i].handle);
		if (!p->post_deps[i].syncobj)
			return -EINVAL;
		p->post_deps[i].chain = NULL;
		p->post_deps[i].point = 0;
		p->num_post_deps++;
	}

	return 0;
}


static int amdgpu_cs_process_syncobj_timeline_out_dep(struct amdgpu_cs_parser *p,
						      struct amdgpu_cs_chunk *chunk)
{
	struct drm_amdgpu_cs_chunk_syncobj *syncobj_deps;
	unsigned num_deps;
	int i;

	syncobj_deps = (struct drm_amdgpu_cs_chunk_syncobj *)chunk->kdata;
	num_deps = chunk->length_dw * 4 /
		sizeof(struct drm_amdgpu_cs_chunk_syncobj);

	if (p->post_deps)
		return -EINVAL;

	p->post_deps = kmalloc_array(num_deps, sizeof(*p->post_deps),
				     GFP_KERNEL);
	p->num_post_deps = 0;

	if (!p->post_deps)
		return -ENOMEM;

	for (i = 0; i < num_deps; ++i) {
		struct amdgpu_cs_post_dep *dep = &p->post_deps[i];

		dep->chain = NULL;
		if (syncobj_deps[i].point) {
			dep->chain = kmalloc(sizeof(*dep->chain), GFP_KERNEL);
			if (!dep->chain)
				return -ENOMEM;
		}

		dep->syncobj = drm_syncobj_find(p->filp,
						syncobj_deps[i].handle);
		if (!dep->syncobj) {
			kfree(dep->chain);
			return -EINVAL;
		}
		dep->point = syncobj_deps[i].point;
		p->num_post_deps++;
	}

	return 0;
}

static int amdgpu_cs_dependencies(struct amdgpu_device *adev,
				  struct amdgpu_cs_parser *p)
{
	int i, r;

	for (i = 0; i < p->nchunks; ++i) {
		struct amdgpu_cs_chunk *chunk;

		chunk = &p->chunks[i];

		switch (chunk->chunk_id) {
		case AMDGPU_CHUNK_ID_DEPENDENCIES:
		case AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES:
			r = amdgpu_cs_process_fence_dep(p, chunk);
			if (r)
				return r;
			break;
		case AMDGPU_CHUNK_ID_SYNCOBJ_IN:
			r = amdgpu_cs_process_syncobj_in_dep(p, chunk);
			if (r)
				return r;
			break;
		case AMDGPU_CHUNK_ID_SYNCOBJ_OUT:
			r = amdgpu_cs_process_syncobj_out_dep(p, chunk);
			if (r)
				return r;
			break;
		case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT:
			r = amdgpu_cs_process_syncobj_timeline_in_dep(p, chunk);
			if (r)
				return r;
			break;
		case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL:
			r = amdgpu_cs_process_syncobj_timeline_out_dep(p, chunk);
			if (r)
				return r;
			break;
		}
	}

	return 0;
}

static void amdgpu_cs_post_dependencies(struct amdgpu_cs_parser *p)
{
	int i;

	for (i = 0; i < p->num_post_deps; ++i) {
		if (p->post_deps[i].chain && p->post_deps[i].point) {
			drm_syncobj_add_point(p->post_deps[i].syncobj,
					      p->post_deps[i].chain,
					      p->fence, p->post_deps[i].point);
			p->post_deps[i].chain = NULL;
		} else {
			drm_syncobj_replace_fence(p->post_deps[i].syncobj,
						  p->fence);
		}
	}
}

static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
			    union drm_amdgpu_cs *cs)
{
	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
	struct drm_sched_entity *entity = p->entity;
	enum drm_sched_priority priority;
	struct amdgpu_ring *ring;
	struct amdgpu_bo_list_entry *e;
	struct amdgpu_job *job;
	uint64_t seq;
	int r;

	job = p->job;
	p->job = NULL;

	r = drm_sched_job_init(&job->base, entity, p->filp);
	if (r)
		goto error_unlock;

	/* No memory allocation is allowed while holding the mn lock.
	 * p->mn is hold until amdgpu_cs_submit is finished and fence is added
	 * to BOs.
	 */
	amdgpu_mn_lock(p->mn);

	/* If userptr are invalidated after amdgpu_cs_parser_bos(), return
	 * -EAGAIN, drmIoctl in libdrm will restart the amdgpu_cs_ioctl.
	 */
	amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) {
		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo);

		r |= !amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm);
	}
	if (r) {
		r = -EAGAIN;
		goto error_abort;
	}

	job->owner = p->filp;
	p->fence = dma_fence_get(&job->base.s_fence->finished);

	amdgpu_ctx_add_fence(p->ctx, entity, p->fence, &seq);
	amdgpu_cs_post_dependencies(p);

	if ((job->preamble_status & AMDGPU_PREAMBLE_IB_PRESENT) &&
	    !p->ctx->preamble_presented) {
		job->preamble_status |= AMDGPU_PREAMBLE_IB_PRESENT_FIRST;
		p->ctx->preamble_presented = true;
	}

	cs->out.handle = seq;
	job->uf_sequence = seq;

	amdgpu_job_free_resources(job);

	trace_amdgpu_cs_ioctl(job);
	amdgpu_vm_bo_trace_cs(&fpriv->vm, &p->ticket);
	priority = job->base.s_priority;
	drm_sched_entity_push_job(&job->base, entity);

	ring = to_amdgpu_ring(entity->rq->sched);
	amdgpu_ring_priority_get(ring, priority);

	amdgpu_vm_move_to_lru_tail(p->adev, &fpriv->vm);

	ttm_eu_fence_buffer_objects(&p->ticket, &p->validated, p->fence);
	amdgpu_mn_unlock(p->mn);

	return 0;

error_abort:
	drm_sched_job_cleanup(&job->base);
	amdgpu_mn_unlock(p->mn);

error_unlock:
	amdgpu_job_free(job);
	return r;
}

int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
{
	struct amdgpu_device *adev = dev->dev_private;
	union drm_amdgpu_cs *cs = data;
	struct amdgpu_cs_parser parser = {};
	bool reserved_buffers = false;
	int i, r;

	if (!adev->accel_working)
		return -EBUSY;

	parser.adev = adev;
	parser.filp = filp;

	r = amdgpu_cs_parser_init(&parser, data);
	if (r) {
		DRM_ERROR("Failed to initialize parser %d!\n", r);
		goto out;
	}

	r = amdgpu_cs_ib_fill(adev, &parser);
	if (r)
		goto out;

	r = amdgpu_cs_dependencies(adev, &parser);
	if (r) {
		DRM_ERROR("Failed in the dependencies handling %d!\n", r);
		goto out;
	}

	r = amdgpu_cs_parser_bos(&parser, data);
	if (r) {
		if (r == -ENOMEM)
			DRM_ERROR("Not enough memory for command submission!\n");
		else if (r != -ERESTARTSYS && r != -EAGAIN)
			DRM_ERROR("Failed to process the buffer list %d!\n", r);
		goto out;
	}

	reserved_buffers = true;

	for (i = 0; i < parser.job->num_ibs; i++)
		trace_amdgpu_cs(&parser, i);

	r = amdgpu_cs_vm_handling(&parser);
	if (r)
		goto out;

	r = amdgpu_cs_submit(&parser, cs);

out:
	amdgpu_cs_parser_fini(&parser, r, reserved_buffers);

	return r;
}

/**
 * amdgpu_cs_wait_ioctl - wait for a command submission to finish
 *
 * @dev: drm device
 * @data: data from userspace
 * @filp: file private
 *
 * Wait for the command submission identified by handle to finish.
 */
int amdgpu_cs_wait_ioctl(struct drm_device *dev, void *data,
			 struct drm_file *filp)
{
	union drm_amdgpu_wait_cs *wait = data;
	unsigned long timeout = amdgpu_gem_timeout(wait->in.timeout);
	struct drm_sched_entity *entity;
	struct amdgpu_ctx *ctx;
	struct dma_fence *fence;
	long r;

	ctx = amdgpu_ctx_get(filp->driver_priv, wait->in.ctx_id);
	if (ctx == NULL)
		return -EINVAL;

	r = amdgpu_ctx_get_entity(ctx, wait->in.ip_type, wait->in.ip_instance,
				  wait->in.ring, &entity);
	if (r) {
		amdgpu_ctx_put(ctx);
		return r;
	}

	fence = amdgpu_ctx_get_fence(ctx, entity, wait->in.handle);
	if (IS_ERR(fence))
		r = PTR_ERR(fence);
	else if (fence) {
		r = dma_fence_wait_timeout(fence, true, timeout);
		if (r > 0 && fence->error)
			r = fence->error;
		dma_fence_put(fence);
	} else
		r = 1;

	amdgpu_ctx_put(ctx);
	if (r < 0)
		return r;

	memset(wait, 0, sizeof(*wait));
	wait->out.status = (r == 0);

	return 0;
}

/**
 * amdgpu_cs_get_fence - helper to get fence from drm_amdgpu_fence
 *
 * @adev: amdgpu device
 * @filp: file private
 * @user: drm_amdgpu_fence copied from user space
 */
static struct dma_fence *amdgpu_cs_get_fence(struct amdgpu_device *adev,
					     struct drm_file *filp,
					     struct drm_amdgpu_fence *user)
{
	struct drm_sched_entity *entity;
	struct amdgpu_ctx *ctx;
	struct dma_fence *fence;
	int r;

	ctx = amdgpu_ctx_get(filp->driver_priv, user->ctx_id);
	if (ctx == NULL)
		return ERR_PTR(-EINVAL);

	r = amdgpu_ctx_get_entity(ctx, user->ip_type, user->ip_instance,
				  user->ring, &entity);
	if (r) {
		amdgpu_ctx_put(ctx);
		return ERR_PTR(r);
	}

	fence = amdgpu_ctx_get_fence(ctx, entity, user->seq_no);
	amdgpu_ctx_put(ctx);

	return fence;
}

int amdgpu_cs_fence_to_handle_ioctl(struct drm_device *dev, void *data,
				    struct drm_file *filp)
{
	struct amdgpu_device *adev = dev->dev_private;
	union drm_amdgpu_fence_to_handle *info = data;
	struct dma_fence *fence;
	struct drm_syncobj *syncobj;
	struct sync_file *sync_file;
	int fd, r;

	fence = amdgpu_cs_get_fence(adev, filp, &info->in.fence);
	if (IS_ERR(fence))
		return PTR_ERR(fence);

	if (!fence)
		fence = dma_fence_get_stub();

	switch (info->in.what) {
	case AMDGPU_FENCE_TO_HANDLE_GET_SYNCOBJ:
		r = drm_syncobj_create(&syncobj, 0, fence);
		dma_fence_put(fence);
		if (r)
			return r;
		r = drm_syncobj_get_handle(filp, syncobj, &info->out.handle);
		drm_syncobj_put(syncobj);
		return r;

	case AMDGPU_FENCE_TO_HANDLE_GET_SYNCOBJ_FD:
		r = drm_syncobj_create(&syncobj, 0, fence);
		dma_fence_put(fence);
		if (r)
			return r;
		r = drm_syncobj_get_fd(syncobj, (int*)&info->out.handle);
		drm_syncobj_put(syncobj);
		return r;

	case AMDGPU_FENCE_TO_HANDLE_GET_SYNC_FILE_FD:
		fd = get_unused_fd_flags(O_CLOEXEC);
		if (fd < 0) {
			dma_fence_put(fence);
			return fd;
		}

		sync_file = sync_file_create(fence);
		dma_fence_put(fence);
		if (!sync_file) {
			put_unused_fd(fd);
			return -ENOMEM;
		}

		fd_install(fd, sync_file->file);
		info->out.handle = fd;
		return 0;

	default:
		return -EINVAL;
	}
}

/**
 * amdgpu_cs_wait_all_fence - wait on all fences to signal
 *
 * @adev: amdgpu device
 * @filp: file private
 * @wait: wait parameters
 * @fences: array of drm_amdgpu_fence
 */
static int amdgpu_cs_wait_all_fences(struct amdgpu_device *adev,
				     struct drm_file *filp,
				     union drm_amdgpu_wait_fences *wait,
				     struct drm_amdgpu_fence *fences)
{
	uint32_t fence_count = wait->in.fence_count;
	unsigned int i;
	long r = 1;

	for (i = 0; i < fence_count; i++) {
		struct dma_fence *fence;
		unsigned long timeout = amdgpu_gem_timeout(wait->in.timeout_ns);

		fence = amdgpu_cs_get_fence(adev, filp, &fences[i]);
		if (IS_ERR(fence))
			return PTR_ERR(fence);
		else if (!fence)
			continue;

		r = dma_fence_wait_timeout(fence, true, timeout);
		dma_fence_put(fence);
		if (r < 0)
			return r;

		if (r == 0)
			break;

		if (fence->error)
			return fence->error;
	}

	memset(wait, 0, sizeof(*wait));
	wait->out.status = (r > 0);

	return 0;
}

/**
 * amdgpu_cs_wait_any_fence - wait on any fence to signal
 *
 * @adev: amdgpu device
 * @filp: file private
 * @wait: wait parameters
 * @fences: array of drm_amdgpu_fence
 */
static int amdgpu_cs_wait_any_fence(struct amdgpu_device *adev,
				    struct drm_file *filp,
				    union drm_amdgpu_wait_fences *wait,
				    struct drm_amdgpu_fence *fences)
{
	unsigned long timeout = amdgpu_gem_timeout(wait->in.timeout_ns);
	uint32_t fence_count = wait->in.fence_count;
	uint32_t first = ~0;
	struct dma_fence **array;
	unsigned int i;
	long r;

	/* Prepare the fence array */
	array = kcalloc(fence_count, sizeof(struct dma_fence *), GFP_KERNEL);

	if (array == NULL)
		return -ENOMEM;

	for (i = 0; i < fence_count; i++) {
		struct dma_fence *fence;

		fence = amdgpu_cs_get_fence(adev, filp, &fences[i]);
		if (IS_ERR(fence)) {
			r = PTR_ERR(fence);
			goto err_free_fence_array;
		} else if (fence) {
			array[i] = fence;
		} else { /* NULL, the fence has been already signaled */
			r = 1;
			first = i;
			goto out;
		}
	}

	r = dma_fence_wait_any_timeout(array, fence_count, true, timeout,
				       &first);
	if (r < 0)
		goto err_free_fence_array;

out:
	memset(wait, 0, sizeof(*wait));
	wait->out.status = (r > 0);
	wait->out.first_signaled = first;

	if (first < fence_count && array[first])
		r = array[first]->error;
	else
		r = 0;

err_free_fence_array:
	for (i = 0; i < fence_count; i++)
		dma_fence_put(array[i]);
	kfree(array);

	return r;
}

/**
 * amdgpu_cs_wait_fences_ioctl - wait for multiple command submissions to finish
 *
 * @dev: drm device
 * @data: data from userspace
 * @filp: file private
 */
int amdgpu_cs_wait_fences_ioctl(struct drm_device *dev, void *data,
				struct drm_file *filp)
{
	struct amdgpu_device *adev = dev->dev_private;
	union drm_amdgpu_wait_fences *wait = data;
	uint32_t fence_count = wait->in.fence_count;
	struct drm_amdgpu_fence *fences_user;
	struct drm_amdgpu_fence *fences;
	int r;

	/* Get the fences from userspace */
	fences = kmalloc_array(fence_count, sizeof(struct drm_amdgpu_fence),
			GFP_KERNEL);
	if (fences == NULL)
		return -ENOMEM;

	fences_user = u64_to_user_ptr(wait->in.fences);
	if (copy_from_user(fences, fences_user,
		sizeof(struct drm_amdgpu_fence) * fence_count)) {
		r = -EFAULT;
		goto err_free_fences;
	}

	if (wait->in.wait_all)
		r = amdgpu_cs_wait_all_fences(adev, filp, wait, fences);
	else
		r = amdgpu_cs_wait_any_fence(adev, filp, wait, fences);

err_free_fences:
	kfree(fences);

	return r;
}

/**
 * amdgpu_cs_find_bo_va - find bo_va for VM address
 *
 * @parser: command submission parser context
 * @addr: VM address
 * @bo: resulting BO of the mapping found
 *
 * Search the buffer objects in the command submission context for a certain
 * virtual memory address. Returns allocation structure when found, NULL
 * otherwise.
 */
int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser,
			   uint64_t addr, struct amdgpu_bo **bo,
			   struct amdgpu_bo_va_mapping **map)
{
	struct amdgpu_fpriv *fpriv = parser->filp->driver_priv;
	struct ttm_operation_ctx ctx = { false, false };
	struct amdgpu_vm *vm = &fpriv->vm;
	struct amdgpu_bo_va_mapping *mapping;
	int r;

	addr /= AMDGPU_GPU_PAGE_SIZE;

	mapping = amdgpu_vm_bo_lookup_mapping(vm, addr);
	if (!mapping || !mapping->bo_va || !mapping->bo_va->base.bo)
		return -EINVAL;

	*bo = mapping->bo_va->base.bo;
	*map = mapping;

	/* Double check that the BO is reserved by this CS */
	if (dma_resv_locking_ctx((*bo)->tbo.base.resv) != &parser->ticket)
		return -EINVAL;

	if (!((*bo)->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)) {
		(*bo)->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
		amdgpu_bo_placement_from_domain(*bo, (*bo)->allowed_domains);
		r = ttm_bo_validate(&(*bo)->tbo, &(*bo)->placement, &ctx);
		if (r)
			return r;
	}

	return amdgpu_ttm_alloc_gart(&(*bo)->tbo);
}