summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/i915_gem_execbuffer.c
blob: b845f468dd74f3b2500d3f1fb059662b6432664d (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
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
/*
 * Copyright © 2008,2010 Intel Corporation
 *
 * 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
 * THE AUTHORS OR COPYRIGHT HOLDERS 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:
 *    Eric Anholt <eric@anholt.net>
 *    Chris Wilson <chris@chris-wilson.co.uk>
 *
 */

#include <drm/drmP.h>
#include <drm/i915_drm.h>
#include "i915_drv.h"
#include "i915_trace.h"
#include "intel_drv.h"
#include <linux/dma_remapping.h>
#include <linux/uaccess.h>

#define  __EXEC_OBJECT_HAS_PIN (1<<31)
#define  __EXEC_OBJECT_HAS_FENCE (1<<30)
#define  __EXEC_OBJECT_NEEDS_MAP (1<<29)
#define  __EXEC_OBJECT_NEEDS_BIAS (1<<28)

#define BATCH_OFFSET_BIAS (256*1024)

struct eb_vmas {
	struct list_head vmas;
	int and;
	union {
		struct i915_vma *lut[0];
		struct hlist_head buckets[0];
	};
};

static struct eb_vmas *
eb_create(struct drm_i915_gem_execbuffer2 *args)
{
	struct eb_vmas *eb = NULL;

	if (args->flags & I915_EXEC_HANDLE_LUT) {
		unsigned size = args->buffer_count;
		size *= sizeof(struct i915_vma *);
		size += sizeof(struct eb_vmas);
		eb = kmalloc(size, GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY);
	}

	if (eb == NULL) {
		unsigned size = args->buffer_count;
		unsigned count = PAGE_SIZE / sizeof(struct hlist_head) / 2;
		BUILD_BUG_ON_NOT_POWER_OF_2(PAGE_SIZE / sizeof(struct hlist_head));
		while (count > 2*size)
			count >>= 1;
		eb = kzalloc(count*sizeof(struct hlist_head) +
			     sizeof(struct eb_vmas),
			     GFP_TEMPORARY);
		if (eb == NULL)
			return eb;

		eb->and = count - 1;
	} else
		eb->and = -args->buffer_count;

	INIT_LIST_HEAD(&eb->vmas);
	return eb;
}

static void
eb_reset(struct eb_vmas *eb)
{
	if (eb->and >= 0)
		memset(eb->buckets, 0, (eb->and+1)*sizeof(struct hlist_head));
}

static int
eb_lookup_vmas(struct eb_vmas *eb,
	       struct drm_i915_gem_exec_object2 *exec,
	       const struct drm_i915_gem_execbuffer2 *args,
	       struct i915_address_space *vm,
	       struct drm_file *file)
{
	struct drm_i915_gem_object *obj;
	struct list_head objects;
	int i, ret;

	INIT_LIST_HEAD(&objects);
	spin_lock(&file->table_lock);
	/* Grab a reference to the object and release the lock so we can lookup
	 * or create the VMA without using GFP_ATOMIC */
	for (i = 0; i < args->buffer_count; i++) {
		obj = to_intel_bo(idr_find(&file->object_idr, exec[i].handle));
		if (obj == NULL) {
			spin_unlock(&file->table_lock);
			DRM_DEBUG("Invalid object handle %d at index %d\n",
				   exec[i].handle, i);
			ret = -ENOENT;
			goto err;
		}

		if (!list_empty(&obj->obj_exec_link)) {
			spin_unlock(&file->table_lock);
			DRM_DEBUG("Object %p [handle %d, index %d] appears more than once in object list\n",
				   obj, exec[i].handle, i);
			ret = -EINVAL;
			goto err;
		}

		drm_gem_object_reference(&obj->base);
		list_add_tail(&obj->obj_exec_link, &objects);
	}
	spin_unlock(&file->table_lock);

	i = 0;
	while (!list_empty(&objects)) {
		struct i915_vma *vma;

		obj = list_first_entry(&objects,
				       struct drm_i915_gem_object,
				       obj_exec_link);

		/*
		 * NOTE: We can leak any vmas created here when something fails
		 * later on. But that's no issue since vma_unbind can deal with
		 * vmas which are not actually bound. And since only
		 * lookup_or_create exists as an interface to get at the vma
		 * from the (obj, vm) we don't run the risk of creating
		 * duplicated vmas for the same vm.
		 */
		vma = i915_gem_obj_lookup_or_create_vma(obj, vm);
		if (IS_ERR(vma)) {
			DRM_DEBUG("Failed to lookup VMA\n");
			ret = PTR_ERR(vma);
			goto err;
		}

		/* Transfer ownership from the objects list to the vmas list. */
		list_add_tail(&vma->exec_list, &eb->vmas);
		list_del_init(&obj->obj_exec_link);

		vma->exec_entry = &exec[i];
		if (eb->and < 0) {
			eb->lut[i] = vma;
		} else {
			uint32_t handle = args->flags & I915_EXEC_HANDLE_LUT ? i : exec[i].handle;
			vma->exec_handle = handle;
			hlist_add_head(&vma->exec_node,
				       &eb->buckets[handle & eb->and]);
		}
		++i;
	}

	return 0;


err:
	while (!list_empty(&objects)) {
		obj = list_first_entry(&objects,
				       struct drm_i915_gem_object,
				       obj_exec_link);
		list_del_init(&obj->obj_exec_link);
		drm_gem_object_unreference(&obj->base);
	}
	/*
	 * Objects already transfered to the vmas list will be unreferenced by
	 * eb_destroy.
	 */

	return ret;
}

static struct i915_vma *eb_get_vma(struct eb_vmas *eb, unsigned long handle)
{
	if (eb->and < 0) {
		if (handle >= -eb->and)
			return NULL;
		return eb->lut[handle];
	} else {
		struct hlist_head *head;
		struct i915_vma *vma;

		head = &eb->buckets[handle & eb->and];
		hlist_for_each_entry(vma, head, exec_node) {
			if (vma->exec_handle == handle)
				return vma;
		}
		return NULL;
	}
}

static void
i915_gem_execbuffer_unreserve_vma(struct i915_vma *vma)
{
	struct drm_i915_gem_exec_object2 *entry;
	struct drm_i915_gem_object *obj = vma->obj;

	if (!drm_mm_node_allocated(&vma->node))
		return;

	entry = vma->exec_entry;

	if (entry->flags & __EXEC_OBJECT_HAS_FENCE)
		i915_gem_object_unpin_fence(obj);

	if (entry->flags & __EXEC_OBJECT_HAS_PIN)
		vma->pin_count--;

	entry->flags &= ~(__EXEC_OBJECT_HAS_FENCE | __EXEC_OBJECT_HAS_PIN);
}

static void eb_destroy(struct eb_vmas *eb)
{
	while (!list_empty(&eb->vmas)) {
		struct i915_vma *vma;

		vma = list_first_entry(&eb->vmas,
				       struct i915_vma,
				       exec_list);
		list_del_init(&vma->exec_list);
		i915_gem_execbuffer_unreserve_vma(vma);
		drm_gem_object_unreference(&vma->obj->base);
	}
	kfree(eb);
}

static inline int use_cpu_reloc(struct drm_i915_gem_object *obj)
{
	return (HAS_LLC(obj->base.dev) ||
		obj->base.write_domain == I915_GEM_DOMAIN_CPU ||
		obj->cache_level != I915_CACHE_NONE);
}

/* Used to convert any address to canonical form.
 * Starting from gen8, some commands (e.g. STATE_BASE_ADDRESS,
 * MI_LOAD_REGISTER_MEM and others, see Broadwell PRM Vol2a) require the
 * addresses to be in a canonical form:
 * "GraphicsAddress[63:48] are ignored by the HW and assumed to be in correct
 * canonical form [63:48] == [47]."
 */
#define GEN8_HIGH_ADDRESS_BIT 47
static inline uint64_t gen8_canonical_addr(uint64_t address)
{
	return sign_extend64(address, GEN8_HIGH_ADDRESS_BIT);
}

static inline uint64_t gen8_noncanonical_addr(uint64_t address)
{
	return address & ((1ULL << (GEN8_HIGH_ADDRESS_BIT + 1)) - 1);
}

static inline uint64_t
relocation_target(struct drm_i915_gem_relocation_entry *reloc,
		  uint64_t target_offset)
{
	return gen8_canonical_addr((int)reloc->delta + target_offset);
}

static int
relocate_entry_cpu(struct drm_i915_gem_object *obj,
		   struct drm_i915_gem_relocation_entry *reloc,
		   uint64_t target_offset)
{
	struct drm_device *dev = obj->base.dev;
	uint32_t page_offset = offset_in_page(reloc->offset);
	uint64_t delta = relocation_target(reloc, target_offset);
	char *vaddr;
	int ret;

	ret = i915_gem_object_set_to_cpu_domain(obj, true);
	if (ret)
		return ret;

	vaddr = kmap_atomic(i915_gem_object_get_dirty_page(obj,
				reloc->offset >> PAGE_SHIFT));
	*(uint32_t *)(vaddr + page_offset) = lower_32_bits(delta);

	if (INTEL_INFO(dev)->gen >= 8) {
		page_offset = offset_in_page(page_offset + sizeof(uint32_t));

		if (page_offset == 0) {
			kunmap_atomic(vaddr);
			vaddr = kmap_atomic(i915_gem_object_get_dirty_page(obj,
			    (reloc->offset + sizeof(uint32_t)) >> PAGE_SHIFT));
		}

		*(uint32_t *)(vaddr + page_offset) = upper_32_bits(delta);
	}

	kunmap_atomic(vaddr);

	return 0;
}

static int
relocate_entry_gtt(struct drm_i915_gem_object *obj,
		   struct drm_i915_gem_relocation_entry *reloc,
		   uint64_t target_offset)
{
	struct drm_device *dev = obj->base.dev;
	struct drm_i915_private *dev_priv = dev->dev_private;
	uint64_t delta = relocation_target(reloc, target_offset);
	uint64_t offset;
	void __iomem *reloc_page;
	int ret;

	ret = i915_gem_object_set_to_gtt_domain(obj, true);
	if (ret)
		return ret;

	ret = i915_gem_object_put_fence(obj);
	if (ret)
		return ret;

	/* Map the page containing the relocation we're going to perform.  */
	offset = i915_gem_obj_ggtt_offset(obj);
	offset += reloc->offset;
	reloc_page = io_mapping_map_atomic_wc(dev_priv->gtt.mappable,
					      offset & PAGE_MASK);
	iowrite32(lower_32_bits(delta), reloc_page + offset_in_page(offset));

	if (INTEL_INFO(dev)->gen >= 8) {
		offset += sizeof(uint32_t);

		if (offset_in_page(offset) == 0) {
			io_mapping_unmap_atomic(reloc_page);
			reloc_page =
				io_mapping_map_atomic_wc(dev_priv->gtt.mappable,
							 offset);
		}

		iowrite32(upper_32_bits(delta),
			  reloc_page + offset_in_page(offset));
	}

	io_mapping_unmap_atomic(reloc_page);

	return 0;
}

static void
clflush_write32(void *addr, uint32_t value)
{
	/* This is not a fast path, so KISS. */
	drm_clflush_virt_range(addr, sizeof(uint32_t));
	*(uint32_t *)addr = value;
	drm_clflush_virt_range(addr, sizeof(uint32_t));
}

static int
relocate_entry_clflush(struct drm_i915_gem_object *obj,
		       struct drm_i915_gem_relocation_entry *reloc,
		       uint64_t target_offset)
{
	struct drm_device *dev = obj->base.dev;
	uint32_t page_offset = offset_in_page(reloc->offset);
	uint64_t delta = relocation_target(reloc, target_offset);
	char *vaddr;
	int ret;

	ret = i915_gem_object_set_to_gtt_domain(obj, true);
	if (ret)
		return ret;

	vaddr = kmap_atomic(i915_gem_object_get_dirty_page(obj,
				reloc->offset >> PAGE_SHIFT));
	clflush_write32(vaddr + page_offset, lower_32_bits(delta));

	if (INTEL_INFO(dev)->gen >= 8) {
		page_offset = offset_in_page(page_offset + sizeof(uint32_t));

		if (page_offset == 0) {
			kunmap_atomic(vaddr);
			vaddr = kmap_atomic(i915_gem_object_get_dirty_page(obj,
			    (reloc->offset + sizeof(uint32_t)) >> PAGE_SHIFT));
		}

		clflush_write32(vaddr + page_offset, upper_32_bits(delta));
	}

	kunmap_atomic(vaddr);

	return 0;
}

static int
i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
				   struct eb_vmas *eb,
				   struct drm_i915_gem_relocation_entry *reloc)
{
	struct drm_device *dev = obj->base.dev;
	struct drm_gem_object *target_obj;
	struct drm_i915_gem_object *target_i915_obj;
	struct i915_vma *target_vma;
	uint64_t target_offset;
	int ret;

	/* we've already hold a reference to all valid objects */
	target_vma = eb_get_vma(eb, reloc->target_handle);
	if (unlikely(target_vma == NULL))
		return -ENOENT;
	target_i915_obj = target_vma->obj;
	target_obj = &target_vma->obj->base;

	target_offset = gen8_canonical_addr(target_vma->node.start);

	/* Sandybridge PPGTT errata: We need a global gtt mapping for MI and
	 * pipe_control writes because the gpu doesn't properly redirect them
	 * through the ppgtt for non_secure batchbuffers. */
	if (unlikely(IS_GEN6(dev) &&
	    reloc->write_domain == I915_GEM_DOMAIN_INSTRUCTION)) {
		ret = i915_vma_bind(target_vma, target_i915_obj->cache_level,
				    PIN_GLOBAL);
		if (WARN_ONCE(ret, "Unexpected failure to bind target VMA!"))
			return ret;
	}

	/* Validate that the target is in a valid r/w GPU domain */
	if (unlikely(reloc->write_domain & (reloc->write_domain - 1))) {
		DRM_DEBUG("reloc with multiple write domains: "
			  "obj %p target %d offset %d "
			  "read %08x write %08x",
			  obj, reloc->target_handle,
			  (int) reloc->offset,
			  reloc->read_domains,
			  reloc->write_domain);
		return -EINVAL;
	}
	if (unlikely((reloc->write_domain | reloc->read_domains)
		     & ~I915_GEM_GPU_DOMAINS)) {
		DRM_DEBUG("reloc with read/write non-GPU domains: "
			  "obj %p target %d offset %d "
			  "read %08x write %08x",
			  obj, reloc->target_handle,
			  (int) reloc->offset,
			  reloc->read_domains,
			  reloc->write_domain);
		return -EINVAL;
	}

	target_obj->pending_read_domains |= reloc->read_domains;
	target_obj->pending_write_domain |= reloc->write_domain;

	/* If the relocation already has the right value in it, no
	 * more work needs to be done.
	 */
	if (target_offset == reloc->presumed_offset)
		return 0;

	/* Check that the relocation address is valid... */
	if (unlikely(reloc->offset >
		obj->base.size - (INTEL_INFO(dev)->gen >= 8 ? 8 : 4))) {
		DRM_DEBUG("Relocation beyond object bounds: "
			  "obj %p target %d offset %d size %d.\n",
			  obj, reloc->target_handle,
			  (int) reloc->offset,
			  (int) obj->base.size);
		return -EINVAL;
	}
	if (unlikely(reloc->offset & 3)) {
		DRM_DEBUG("Relocation not 4-byte aligned: "
			  "obj %p target %d offset %d.\n",
			  obj, reloc->target_handle,
			  (int) reloc->offset);
		return -EINVAL;
	}

	/* We can't wait for rendering with pagefaults disabled */
	if (obj->active && pagefault_disabled())
		return -EFAULT;

	if (use_cpu_reloc(obj))
		ret = relocate_entry_cpu(obj, reloc, target_offset);
	else if (obj->map_and_fenceable)
		ret = relocate_entry_gtt(obj, reloc, target_offset);
	else if (static_cpu_has(X86_FEATURE_CLFLUSH))
		ret = relocate_entry_clflush(obj, reloc, target_offset);
	else {
		WARN_ONCE(1, "Impossible case in relocation handling\n");
		ret = -ENODEV;
	}

	if (ret)
		return ret;

	/* and update the user's relocation entry */
	reloc->presumed_offset = target_offset;

	return 0;
}

static int
i915_gem_execbuffer_relocate_vma(struct i915_vma *vma,
				 struct eb_vmas *eb)
{
#define N_RELOC(x) ((x) / sizeof(struct drm_i915_gem_relocation_entry))
	struct drm_i915_gem_relocation_entry stack_reloc[N_RELOC(512)];
	struct drm_i915_gem_relocation_entry __user *user_relocs;
	struct drm_i915_gem_exec_object2 *entry = vma->exec_entry;
	int remain, ret;

	user_relocs = to_user_ptr(entry->relocs_ptr);

	remain = entry->relocation_count;
	while (remain) {
		struct drm_i915_gem_relocation_entry *r = stack_reloc;
		int count = remain;
		if (count > ARRAY_SIZE(stack_reloc))
			count = ARRAY_SIZE(stack_reloc);
		remain -= count;

		if (__copy_from_user_inatomic(r, user_relocs, count*sizeof(r[0])))
			return -EFAULT;

		do {
			u64 offset = r->presumed_offset;

			ret = i915_gem_execbuffer_relocate_entry(vma->obj, eb, r);
			if (ret)
				return ret;

			if (r->presumed_offset != offset &&
			    __copy_to_user_inatomic(&user_relocs->presumed_offset,
						    &r->presumed_offset,
						    sizeof(r->presumed_offset))) {
				return -EFAULT;
			}

			user_relocs++;
			r++;
		} while (--count);
	}

	return 0;
#undef N_RELOC
}

static int
i915_gem_execbuffer_relocate_vma_slow(struct i915_vma *vma,
				      struct eb_vmas *eb,
				      struct drm_i915_gem_relocation_entry *relocs)
{
	const struct drm_i915_gem_exec_object2 *entry = vma->exec_entry;
	int i, ret;

	for (i = 0; i < entry->relocation_count; i++) {
		ret = i915_gem_execbuffer_relocate_entry(vma->obj, eb, &relocs[i]);
		if (ret)
			return ret;
	}

	return 0;
}

static int
i915_gem_execbuffer_relocate(struct eb_vmas *eb)
{
	struct i915_vma *vma;
	int ret = 0;

	/* This is the fast path and we cannot handle a pagefault whilst
	 * holding the struct mutex lest the user pass in the relocations
	 * contained within a mmaped bo. For in such a case we, the page
	 * fault handler would call i915_gem_fault() and we would try to
	 * acquire the struct mutex again. Obviously this is bad and so
	 * lockdep complains vehemently.
	 */
	pagefault_disable();
	list_for_each_entry(vma, &eb->vmas, exec_list) {
		ret = i915_gem_execbuffer_relocate_vma(vma, eb);
		if (ret)
			break;
	}
	pagefault_enable();

	return ret;
}

static bool only_mappable_for_reloc(unsigned int flags)
{
	return (flags & (EXEC_OBJECT_NEEDS_FENCE | __EXEC_OBJECT_NEEDS_MAP)) ==
		__EXEC_OBJECT_NEEDS_MAP;
}

static int
i915_gem_execbuffer_reserve_vma(struct i915_vma *vma,
				struct intel_engine_cs *ring,
				bool *need_reloc)
{
	struct drm_i915_gem_object *obj = vma->obj;
	struct drm_i915_gem_exec_object2 *entry = vma->exec_entry;
	uint64_t flags;
	int ret;

	flags = PIN_USER;
	if (entry->flags & EXEC_OBJECT_NEEDS_GTT)
		flags |= PIN_GLOBAL;

	if (!drm_mm_node_allocated(&vma->node)) {
		/* Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset,
		 * limit address to the first 4GBs for unflagged objects.
		 */
		if ((entry->flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS) == 0)
			flags |= PIN_ZONE_4G;
		if (entry->flags & __EXEC_OBJECT_NEEDS_MAP)
			flags |= PIN_GLOBAL | PIN_MAPPABLE;
		if (entry->flags & __EXEC_OBJECT_NEEDS_BIAS)
			flags |= BATCH_OFFSET_BIAS | PIN_OFFSET_BIAS;
		if (entry->flags & EXEC_OBJECT_PINNED)
			flags |= entry->offset | PIN_OFFSET_FIXED;
		if ((flags & PIN_MAPPABLE) == 0)
			flags |= PIN_HIGH;
	}

	ret = i915_gem_object_pin(obj, vma->vm, entry->alignment, flags);
	if ((ret == -ENOSPC  || ret == -E2BIG) &&
	    only_mappable_for_reloc(entry->flags))
		ret = i915_gem_object_pin(obj, vma->vm,
					  entry->alignment,
					  flags & ~PIN_MAPPABLE);
	if (ret)
		return ret;

	entry->flags |= __EXEC_OBJECT_HAS_PIN;

	if (entry->flags & EXEC_OBJECT_NEEDS_FENCE) {
		ret = i915_gem_object_get_fence(obj);
		if (ret)
			return ret;

		if (i915_gem_object_pin_fence(obj))
			entry->flags |= __EXEC_OBJECT_HAS_FENCE;
	}

	if (entry->offset != vma->node.start) {
		entry->offset = vma->node.start;
		*need_reloc = true;
	}

	if (entry->flags & EXEC_OBJECT_WRITE) {
		obj->base.pending_read_domains = I915_GEM_DOMAIN_RENDER;
		obj->base.pending_write_domain = I915_GEM_DOMAIN_RENDER;
	}

	return 0;
}

static bool
need_reloc_mappable(struct i915_vma *vma)
{
	struct drm_i915_gem_exec_object2 *entry = vma->exec_entry;

	if (entry->relocation_count == 0)
		return false;

	if (!vma->is_ggtt)
		return false;

	/* See also use_cpu_reloc() */
	if (HAS_LLC(vma->obj->base.dev))
		return false;

	if (vma->obj->base.write_domain == I915_GEM_DOMAIN_CPU)
		return false;

	return true;
}

static bool
eb_vma_misplaced(struct i915_vma *vma)
{
	struct drm_i915_gem_exec_object2 *entry = vma->exec_entry;
	struct drm_i915_gem_object *obj = vma->obj;

	WARN_ON(entry->flags & __EXEC_OBJECT_NEEDS_MAP && !vma->is_ggtt);

	if (entry->alignment &&
	    vma->node.start & (entry->alignment - 1))
		return true;

	if (entry->flags & EXEC_OBJECT_PINNED &&
	    vma->node.start != entry->offset)
		return true;

	if (entry->flags & __EXEC_OBJECT_NEEDS_BIAS &&
	    vma->node.start < BATCH_OFFSET_BIAS)
		return true;

	/* avoid costly ping-pong once a batch bo ended up non-mappable */
	if (entry->flags & __EXEC_OBJECT_NEEDS_MAP && !obj->map_and_fenceable)
		return !only_mappable_for_reloc(entry->flags);

	if ((entry->flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS) == 0 &&
	    (vma->node.start + vma->node.size - 1) >> 32)
		return true;

	return false;
}

static int
i915_gem_execbuffer_reserve(struct intel_engine_cs *ring,
			    struct list_head *vmas,
			    struct intel_context *ctx,
			    bool *need_relocs)
{
	struct drm_i915_gem_object *obj;
	struct i915_vma *vma;
	struct i915_address_space *vm;
	struct list_head ordered_vmas;
	struct list_head pinned_vmas;
	bool has_fenced_gpu_access = INTEL_INFO(ring->dev)->gen < 4;
	int retry;

	i915_gem_retire_requests_ring(ring);

	vm = list_first_entry(vmas, struct i915_vma, exec_list)->vm;

	INIT_LIST_HEAD(&ordered_vmas);
	INIT_LIST_HEAD(&pinned_vmas);
	while (!list_empty(vmas)) {
		struct drm_i915_gem_exec_object2 *entry;
		bool need_fence, need_mappable;

		vma = list_first_entry(vmas, struct i915_vma, exec_list);
		obj = vma->obj;
		entry = vma->exec_entry;

		if (ctx->flags & CONTEXT_NO_ZEROMAP)
			entry->flags |= __EXEC_OBJECT_NEEDS_BIAS;

		if (!has_fenced_gpu_access)
			entry->flags &= ~EXEC_OBJECT_NEEDS_FENCE;
		need_fence =
			entry->flags & EXEC_OBJECT_NEEDS_FENCE &&
			obj->tiling_mode != I915_TILING_NONE;
		need_mappable = need_fence || need_reloc_mappable(vma);

		if (entry->flags & EXEC_OBJECT_PINNED)
			list_move_tail(&vma->exec_list, &pinned_vmas);
		else if (need_mappable) {
			entry->flags |= __EXEC_OBJECT_NEEDS_MAP;
			list_move(&vma->exec_list, &ordered_vmas);
		} else
			list_move_tail(&vma->exec_list, &ordered_vmas);

		obj->base.pending_read_domains = I915_GEM_GPU_DOMAINS & ~I915_GEM_DOMAIN_COMMAND;
		obj->base.pending_write_domain = 0;
	}
	list_splice(&ordered_vmas, vmas);
	list_splice(&pinned_vmas, vmas);

	/* Attempt to pin all of the buffers into the GTT.
	 * This is done in 3 phases:
	 *
	 * 1a. Unbind all objects that do not match the GTT constraints for
	 *     the execbuffer (fenceable, mappable, alignment etc).
	 * 1b. Increment pin count for already bound objects.
	 * 2.  Bind new objects.
	 * 3.  Decrement pin count.
	 *
	 * This avoid unnecessary unbinding of later objects in order to make
	 * room for the earlier objects *unless* we need to defragment.
	 */
	retry = 0;
	do {
		int ret = 0;

		/* Unbind any ill-fitting objects or pin. */
		list_for_each_entry(vma, vmas, exec_list) {
			if (!drm_mm_node_allocated(&vma->node))
				continue;

			if (eb_vma_misplaced(vma))
				ret = i915_vma_unbind(vma);
			else
				ret = i915_gem_execbuffer_reserve_vma(vma, ring, need_relocs);
			if (ret)
				goto err;
		}

		/* Bind fresh objects */
		list_for_each_entry(vma, vmas, exec_list) {
			if (drm_mm_node_allocated(&vma->node))
				continue;

			ret = i915_gem_execbuffer_reserve_vma(vma, ring, need_relocs);
			if (ret)
				goto err;
		}

err:
		if (ret != -ENOSPC || retry++)
			return ret;

		/* Decrement pin count for bound objects */
		list_for_each_entry(vma, vmas, exec_list)
			i915_gem_execbuffer_unreserve_vma(vma);

		ret = i915_gem_evict_vm(vm, true);
		if (ret)
			return ret;
	} while (1);
}

static int
i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
				  struct drm_i915_gem_execbuffer2 *args,
				  struct drm_file *file,
				  struct intel_engine_cs *ring,
				  struct eb_vmas *eb,
				  struct drm_i915_gem_exec_object2 *exec,
				  struct intel_context *ctx)
{
	struct drm_i915_gem_relocation_entry *reloc;
	struct i915_address_space *vm;
	struct i915_vma *vma;
	bool need_relocs;
	int *reloc_offset;
	int i, total, ret;
	unsigned count = args->buffer_count;

	vm = list_first_entry(&eb->vmas, struct i915_vma, exec_list)->vm;

	/* We may process another execbuffer during the unlock... */
	while (!list_empty(&eb->vmas)) {
		vma = list_first_entry(&eb->vmas, struct i915_vma, exec_list);
		list_del_init(&vma->exec_list);
		i915_gem_execbuffer_unreserve_vma(vma);
		drm_gem_object_unreference(&vma->obj->base);
	}

	mutex_unlock(&dev->struct_mutex);

	total = 0;
	for (i = 0; i < count; i++)
		total += exec[i].relocation_count;

	reloc_offset = drm_malloc_ab(count, sizeof(*reloc_offset));
	reloc = drm_malloc_ab(total, sizeof(*reloc));
	if (reloc == NULL || reloc_offset == NULL) {
		drm_free_large(reloc);
		drm_free_large(reloc_offset);
		mutex_lock(&dev->struct_mutex);
		return -ENOMEM;
	}

	total = 0;
	for (i = 0; i < count; i++) {
		struct drm_i915_gem_relocation_entry __user *user_relocs;
		u64 invalid_offset = (u64)-1;
		int j;

		user_relocs = to_user_ptr(exec[i].relocs_ptr);

		if (copy_from_user(reloc+total, user_relocs,
				   exec[i].relocation_count * sizeof(*reloc))) {
			ret = -EFAULT;
			mutex_lock(&dev->struct_mutex);
			goto err;
		}

		/* As we do not update the known relocation offsets after
		 * relocating (due to the complexities in lock handling),
		 * we need to mark them as invalid now so that we force the
		 * relocation processing next time. Just in case the target
		 * object is evicted and then rebound into its old
		 * presumed_offset before the next execbuffer - if that
		 * happened we would make the mistake of assuming that the
		 * relocations were valid.
		 */
		for (j = 0; j < exec[i].relocation_count; j++) {
			if (__copy_to_user(&user_relocs[j].presumed_offset,
					   &invalid_offset,
					   sizeof(invalid_offset))) {
				ret = -EFAULT;
				mutex_lock(&dev->struct_mutex);
				goto err;
			}
		}

		reloc_offset[i] = total;
		total += exec[i].relocation_count;
	}

	ret = i915_mutex_lock_interruptible(dev);
	if (ret) {
		mutex_lock(&dev->struct_mutex);
		goto err;
	}

	/* reacquire the objects */
	eb_reset(eb);
	ret = eb_lookup_vmas(eb, exec, args, vm, file);
	if (ret)
		goto err;

	need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0;
	ret = i915_gem_execbuffer_reserve(ring, &eb->vmas, ctx, &need_relocs);
	if (ret)
		goto err;

	list_for_each_entry(vma, &eb->vmas, exec_list) {
		int offset = vma->exec_entry - exec;
		ret = i915_gem_execbuffer_relocate_vma_slow(vma, eb,
							    reloc + reloc_offset[offset]);
		if (ret)
			goto err;
	}

	/* Leave the user relocations as are, this is the painfully slow path,
	 * and we want to avoid the complication of dropping the lock whilst
	 * having buffers reserved in the aperture and so causing spurious
	 * ENOSPC for random operations.
	 */

err:
	drm_free_large(reloc);
	drm_free_large(reloc_offset);
	return ret;
}

static int
i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req,
				struct list_head *vmas)
{
	const unsigned other_rings = ~intel_ring_flag(req->ring);
	struct i915_vma *vma;
	uint32_t flush_domains = 0;
	bool flush_chipset = false;
	int ret;

	list_for_each_entry(vma, vmas, exec_list) {
		struct drm_i915_gem_object *obj = vma->obj;

		if (obj->active & other_rings) {
			ret = i915_gem_object_sync(obj, req->ring, &req);
			if (ret)
				return ret;
		}

		if (obj->base.write_domain & I915_GEM_DOMAIN_CPU)
			flush_chipset |= i915_gem_clflush_object(obj, false);

		flush_domains |= obj->base.write_domain;
	}

	if (flush_chipset)
		i915_gem_chipset_flush(req->ring->dev);

	if (flush_domains & I915_GEM_DOMAIN_GTT)
		wmb();

	/* Unconditionally invalidate gpu caches and ensure that we do flush
	 * any residual writes from the previous batch.
	 */
	return intel_ring_invalidate_all_caches(req);
}

static bool
i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec)
{
	if (exec->flags & __I915_EXEC_UNKNOWN_FLAGS)
		return false;

	/* Kernel clipping was a DRI1 misfeature */
	if (exec->num_cliprects || exec->cliprects_ptr)
		return false;

	if (exec->DR4 == 0xffffffff) {
		DRM_DEBUG("UXA submitting garbage DR4, fixing up\n");
		exec->DR4 = 0;
	}
	if (exec->DR1 || exec->DR4)
		return false;

	if ((exec->batch_start_offset | exec->batch_len) & 0x7)
		return false;

	return true;
}

static int
validate_exec_list(struct drm_device *dev,
		   struct drm_i915_gem_exec_object2 *exec,
		   int count)
{
	unsigned relocs_total = 0;
	unsigned relocs_max = UINT_MAX / sizeof(struct drm_i915_gem_relocation_entry);
	unsigned invalid_flags;
	int i;

	invalid_flags = __EXEC_OBJECT_UNKNOWN_FLAGS;
	if (USES_FULL_PPGTT(dev))
		invalid_flags |= EXEC_OBJECT_NEEDS_GTT;

	for (i = 0; i < count; i++) {
		char __user *ptr = to_user_ptr(exec[i].relocs_ptr);
		int length; /* limited by fault_in_pages_readable() */

		if (exec[i].flags & invalid_flags)
			return -EINVAL;

		/* Offset can be used as input (EXEC_OBJECT_PINNED), reject
		 * any non-page-aligned or non-canonical addresses.
		 */
		if (exec[i].flags & EXEC_OBJECT_PINNED) {
			if (exec[i].offset !=
			    gen8_canonical_addr(exec[i].offset & PAGE_MASK))
				return -EINVAL;

			/* From drm_mm perspective address space is continuous,
			 * so from this point we're always using non-canonical
			 * form internally.
			 */
			exec[i].offset = gen8_noncanonical_addr(exec[i].offset);
		}

		if (exec[i].alignment && !is_power_of_2(exec[i].alignment))
			return -EINVAL;

		/* First check for malicious input causing overflow in
		 * the worst case where we need to allocate the entire
		 * relocation tree as a single array.
		 */
		if (exec[i].relocation_count > relocs_max - relocs_total)
			return -EINVAL;
		relocs_total += exec[i].relocation_count;

		length = exec[i].relocation_count *
			sizeof(struct drm_i915_gem_relocation_entry);
		/*
		 * We must check that the entire relocation array is safe
		 * to read, but since we may need to update the presumed
		 * offsets during execution, check for full write access.
		 */
		if (!access_ok(VERIFY_WRITE, ptr, length))
			return -EFAULT;

		if (likely(!i915.prefault_disable)) {
			if (fault_in_multipages_readable(ptr, length))
				return -EFAULT;
		}
	}

	return 0;
}

static struct intel_context *
i915_gem_validate_context(struct drm_device *dev, struct drm_file *file,
			  struct intel_engine_cs *ring, const u32 ctx_id)
{
	struct intel_context *ctx = NULL;
	struct i915_ctx_hang_stats *hs;

	if (ring->id != RCS && ctx_id != DEFAULT_CONTEXT_HANDLE)
		return ERR_PTR(-EINVAL);

	ctx = i915_gem_context_get(file->driver_priv, ctx_id);
	if (IS_ERR(ctx))
		return ctx;

	hs = &ctx->hang_stats;
	if (hs->banned) {
		DRM_DEBUG("Context %u tried to submit while banned\n", ctx_id);
		return ERR_PTR(-EIO);
	}

	if (i915.enable_execlists && !ctx->engine[ring->id].state) {
		int ret = intel_lr_context_deferred_alloc(ctx, ring);
		if (ret) {
			DRM_DEBUG("Could not create LRC %u: %d\n", ctx_id, ret);
			return ERR_PTR(ret);
		}
	}

	return ctx;
}

void
i915_gem_execbuffer_move_to_active(struct list_head *vmas,
				   struct drm_i915_gem_request *req)
{
	struct intel_engine_cs *ring = i915_gem_request_get_ring(req);
	struct i915_vma *vma;

	list_for_each_entry(vma, vmas, exec_list) {
		struct drm_i915_gem_exec_object2 *entry = vma->exec_entry;
		struct drm_i915_gem_object *obj = vma->obj;
		u32 old_read = obj->base.read_domains;
		u32 old_write = obj->base.write_domain;

		obj->dirty = 1; /* be paranoid  */
		obj->base.write_domain = obj->base.pending_write_domain;
		if (obj->base.write_domain == 0)
			obj->base.pending_read_domains |= obj->base.read_domains;
		obj->base.read_domains = obj->base.pending_read_domains;

		i915_vma_move_to_active(vma, req);
		if (obj->base.write_domain) {
			i915_gem_request_assign(&obj->last_write_req, req);

			intel_fb_obj_invalidate(obj, ORIGIN_CS);

			/* update for the implicit flush after a batch */
			obj->base.write_domain &= ~I915_GEM_GPU_DOMAINS;
		}
		if (entry->flags & EXEC_OBJECT_NEEDS_FENCE) {
			i915_gem_request_assign(&obj->last_fenced_req, req);
			if (entry->flags & __EXEC_OBJECT_HAS_FENCE) {
				struct drm_i915_private *dev_priv = to_i915(ring->dev);
				list_move_tail(&dev_priv->fence_regs[obj->fence_reg].lru_list,
					       &dev_priv->mm.fence_list);
			}
		}

		trace_i915_gem_object_change_domain(obj, old_read, old_write);
	}
}

void
i915_gem_execbuffer_retire_commands(struct i915_execbuffer_params *params)
{
	/* Unconditionally force add_request to emit a full flush. */
	params->ring->gpu_caches_dirty = true;

	/* Add a breadcrumb for the completion of the batch buffer */
	__i915_add_request(params->request, params->batch_obj, true);
}

static int
i915_reset_gen7_sol_offsets(struct drm_device *dev,
			    struct drm_i915_gem_request *req)
{
	struct intel_engine_cs *ring = req->ring;
	struct drm_i915_private *dev_priv = dev->dev_private;
	int ret, i;

	if (!IS_GEN7(dev) || ring != &dev_priv->ring[RCS]) {
		DRM_DEBUG("sol reset is gen7/rcs only\n");
		return -EINVAL;
	}

	ret = intel_ring_begin(req, 4 * 3);
	if (ret)
		return ret;

	for (i = 0; i < 4; i++) {
		intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
		intel_ring_emit_reg(ring, GEN7_SO_WRITE_OFFSET(i));
		intel_ring_emit(ring, 0);
	}

	intel_ring_advance(ring);

	return 0;
}

static struct drm_i915_gem_object*
i915_gem_execbuffer_parse(struct intel_engine_cs *ring,
			  struct drm_i915_gem_exec_object2 *shadow_exec_entry,
			  struct eb_vmas *eb,
			  struct drm_i915_gem_object *batch_obj,
			  u32 batch_start_offset,
			  u32 batch_len,
			  bool is_master)
{
	struct drm_i915_gem_object *shadow_batch_obj;
	struct i915_vma *vma;
	int ret;

	shadow_batch_obj = i915_gem_batch_pool_get(&ring->batch_pool,
						   PAGE_ALIGN(batch_len));
	if (IS_ERR(shadow_batch_obj))
		return shadow_batch_obj;

	ret = i915_parse_cmds(ring,
			      batch_obj,
			      shadow_batch_obj,
			      batch_start_offset,
			      batch_len,
			      is_master);
	if (ret)
		goto err;

	ret = i915_gem_obj_ggtt_pin(shadow_batch_obj, 0, 0);
	if (ret)
		goto err;

	i915_gem_object_unpin_pages(shadow_batch_obj);

	memset(shadow_exec_entry, 0, sizeof(*shadow_exec_entry));

	vma = i915_gem_obj_to_ggtt(shadow_batch_obj);
	vma->exec_entry = shadow_exec_entry;
	vma->exec_entry->flags = __EXEC_OBJECT_HAS_PIN;
	drm_gem_object_reference(&shadow_batch_obj->base);
	list_add_tail(&vma->exec_list, &eb->vmas);

	shadow_batch_obj->base.pending_read_domains = I915_GEM_DOMAIN_COMMAND;

	return shadow_batch_obj;

err:
	i915_gem_object_unpin_pages(shadow_batch_obj);
	if (ret == -EACCES) /* unhandled chained batch */
		return batch_obj;
	else
		return ERR_PTR(ret);
}

int
i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
			       struct drm_i915_gem_execbuffer2 *args,
			       struct list_head *vmas)
{
	struct drm_device *dev = params->dev;
	struct intel_engine_cs *ring = params->ring;
	struct drm_i915_private *dev_priv = dev->dev_private;
	u64 exec_start, exec_len;
	int instp_mode;
	u32 instp_mask;
	int ret;

	ret = i915_gem_execbuffer_move_to_gpu(params->request, vmas);
	if (ret)
		return ret;

	ret = i915_switch_context(params->request);
	if (ret)
		return ret;

	WARN(params->ctx->ppgtt && params->ctx->ppgtt->pd_dirty_rings & (1<<ring->id),
	     "%s didn't clear reload\n", ring->name);

	instp_mode = args->flags & I915_EXEC_CONSTANTS_MASK;
	instp_mask = I915_EXEC_CONSTANTS_MASK;
	switch (instp_mode) {
	case I915_EXEC_CONSTANTS_REL_GENERAL:
	case I915_EXEC_CONSTANTS_ABSOLUTE:
	case I915_EXEC_CONSTANTS_REL_SURFACE:
		if (instp_mode != 0 && ring != &dev_priv->ring[RCS]) {
			DRM_DEBUG("non-0 rel constants mode on non-RCS\n");
			return -EINVAL;
		}

		if (instp_mode != dev_priv->relative_constants_mode) {
			if (INTEL_INFO(dev)->gen < 4) {
				DRM_DEBUG("no rel constants on pre-gen4\n");
				return -EINVAL;
			}

			if (INTEL_INFO(dev)->gen > 5 &&
			    instp_mode == I915_EXEC_CONSTANTS_REL_SURFACE) {
				DRM_DEBUG("rel surface constants mode invalid on gen5+\n");
				return -EINVAL;
			}

			/* The HW changed the meaning on this bit on gen6 */
			if (INTEL_INFO(dev)->gen >= 6)
				instp_mask &= ~I915_EXEC_CONSTANTS_REL_SURFACE;
		}
		break;
	default:
		DRM_DEBUG("execbuf with unknown constants: %d\n", instp_mode);
		return -EINVAL;
	}

	if (ring == &dev_priv->ring[RCS] &&
	    instp_mode != dev_priv->relative_constants_mode) {
		ret = intel_ring_begin(params->request, 4);
		if (ret)
			return ret;

		intel_ring_emit(ring, MI_NOOP);
		intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
		intel_ring_emit_reg(ring, INSTPM);
		intel_ring_emit(ring, instp_mask << 16 | instp_mode);
		intel_ring_advance(ring);

		dev_priv->relative_constants_mode = instp_mode;
	}

	if (args->flags & I915_EXEC_GEN7_SOL_RESET) {
		ret = i915_reset_gen7_sol_offsets(dev, params->request);
		if (ret)
			return ret;
	}

	exec_len   = args->batch_len;
	exec_start = params->batch_obj_vm_offset +
		     params->args_batch_start_offset;

	if (exec_len == 0)
		exec_len = params->batch_obj->base.size;

	ret = ring->dispatch_execbuffer(params->request,
					exec_start, exec_len,
					params->dispatch_flags);
	if (ret)
		return ret;

	trace_i915_gem_ring_dispatch(params->request, params->dispatch_flags);

	i915_gem_execbuffer_move_to_active(vmas, params->request);
	i915_gem_execbuffer_retire_commands(params);

	return 0;
}

/**
 * Find one BSD ring to dispatch the corresponding BSD command.
 * The ring index is returned.
 */
static unsigned int
gen8_dispatch_bsd_ring(struct drm_i915_private *dev_priv, struct drm_file *file)
{
	struct drm_i915_file_private *file_priv = file->driver_priv;

	/* Check whether the file_priv has already selected one ring. */
	if ((int)file_priv->bsd_ring < 0) {
		/* If not, use the ping-pong mechanism to select one. */
		mutex_lock(&dev_priv->dev->struct_mutex);
		file_priv->bsd_ring = dev_priv->mm.bsd_ring_dispatch_index;
		dev_priv->mm.bsd_ring_dispatch_index ^= 1;
		mutex_unlock(&dev_priv->dev->struct_mutex);
	}

	return file_priv->bsd_ring;
}

static struct drm_i915_gem_object *
eb_get_batch(struct eb_vmas *eb)
{
	struct i915_vma *vma = list_entry(eb->vmas.prev, typeof(*vma), exec_list);

	/*
	 * SNA is doing fancy tricks with compressing batch buffers, which leads
	 * to negative relocation deltas. Usually that works out ok since the
	 * relocate address is still positive, except when the batch is placed
	 * very low in the GTT. Ensure this doesn't happen.
	 *
	 * Note that actual hangs have only been observed on gen7, but for
	 * paranoia do it everywhere.
	 */
	if ((vma->exec_entry->flags & EXEC_OBJECT_PINNED) == 0)
		vma->exec_entry->flags |= __EXEC_OBJECT_NEEDS_BIAS;

	return vma->obj;
}

#define I915_USER_RINGS (4)

static const enum intel_ring_id user_ring_map[I915_USER_RINGS + 1] = {
	[I915_EXEC_DEFAULT]	= RCS,
	[I915_EXEC_RENDER]	= RCS,
	[I915_EXEC_BLT]		= BCS,
	[I915_EXEC_BSD]		= VCS,
	[I915_EXEC_VEBOX]	= VECS
};

static int
eb_select_ring(struct drm_i915_private *dev_priv,
	       struct drm_file *file,
	       struct drm_i915_gem_execbuffer2 *args,
	       struct intel_engine_cs **ring)
{
	unsigned int user_ring_id = args->flags & I915_EXEC_RING_MASK;

	if (user_ring_id > I915_USER_RINGS) {
		DRM_DEBUG("execbuf with unknown ring: %u\n", user_ring_id);
		return -EINVAL;
	}

	if ((user_ring_id != I915_EXEC_BSD) &&
	    ((args->flags & I915_EXEC_BSD_MASK) != 0)) {
		DRM_DEBUG("execbuf with non bsd ring but with invalid "
			  "bsd dispatch flags: %d\n", (int)(args->flags));
		return -EINVAL;
	}

	if (user_ring_id == I915_EXEC_BSD && HAS_BSD2(dev_priv)) {
		unsigned int bsd_idx = args->flags & I915_EXEC_BSD_MASK;

		if (bsd_idx == I915_EXEC_BSD_DEFAULT) {
			bsd_idx = gen8_dispatch_bsd_ring(dev_priv, file);
		} else if (bsd_idx >= I915_EXEC_BSD_RING1 &&
			   bsd_idx <= I915_EXEC_BSD_RING2) {
			bsd_idx >>= I915_EXEC_BSD_SHIFT;
			bsd_idx--;
		} else {
			DRM_DEBUG("execbuf with unknown bsd ring: %u\n",
				  bsd_idx);
			return -EINVAL;
		}

		*ring = &dev_priv->ring[_VCS(bsd_idx)];
	} else {
		*ring = &dev_priv->ring[user_ring_map[user_ring_id]];
	}

	if (!intel_ring_initialized(*ring)) {
		DRM_DEBUG("execbuf with invalid ring: %u\n", user_ring_id);
		return -EINVAL;
	}

	return 0;
}

static int
i915_gem_do_execbuffer(struct drm_device *dev, void *data,
		       struct drm_file *file,
		       struct drm_i915_gem_execbuffer2 *args,
		       struct drm_i915_gem_exec_object2 *exec)
{
	struct drm_i915_private *dev_priv = dev->dev_private;
	struct drm_i915_gem_request *req = NULL;
	struct eb_vmas *eb;
	struct drm_i915_gem_object *batch_obj;
	struct drm_i915_gem_exec_object2 shadow_exec_entry;
	struct intel_engine_cs *ring;
	struct intel_context *ctx;
	struct i915_address_space *vm;
	struct i915_execbuffer_params params_master; /* XXX: will be removed later */
	struct i915_execbuffer_params *params = &params_master;
	const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
	u32 dispatch_flags;
	int ret;
	bool need_relocs;

	if (!i915_gem_check_execbuffer(args))
		return -EINVAL;

	ret = validate_exec_list(dev, exec, args->buffer_count);
	if (ret)
		return ret;

	dispatch_flags = 0;
	if (args->flags & I915_EXEC_SECURE) {
		if (!file->is_master || !capable(CAP_SYS_ADMIN))
		    return -EPERM;

		dispatch_flags |= I915_DISPATCH_SECURE;
	}
	if (args->flags & I915_EXEC_IS_PINNED)
		dispatch_flags |= I915_DISPATCH_PINNED;

	ret = eb_select_ring(dev_priv, file, args, &ring);
	if (ret)
		return ret;

	if (args->buffer_count < 1) {
		DRM_DEBUG("execbuf with %d buffers\n", args->buffer_count);
		return -EINVAL;
	}

	if (args->flags & I915_EXEC_RESOURCE_STREAMER) {
		if (!HAS_RESOURCE_STREAMER(dev)) {
			DRM_DEBUG("RS is only allowed for Haswell, Gen8 and above\n");
			return -EINVAL;
		}
		if (ring->id != RCS) {
			DRM_DEBUG("RS is not available on %s\n",
				 ring->name);
			return -EINVAL;
		}

		dispatch_flags |= I915_DISPATCH_RS;
	}

	intel_runtime_pm_get(dev_priv);

	ret = i915_mutex_lock_interruptible(dev);
	if (ret)
		goto pre_mutex_err;

	ctx = i915_gem_validate_context(dev, file, ring, ctx_id);
	if (IS_ERR(ctx)) {
		mutex_unlock(&dev->struct_mutex);
		ret = PTR_ERR(ctx);
		goto pre_mutex_err;
	}

	i915_gem_context_reference(ctx);

	if (ctx->ppgtt)
		vm = &ctx->ppgtt->base;
	else
		vm = &dev_priv->gtt.base;

	memset(&params_master, 0x00, sizeof(params_master));

	eb = eb_create(args);
	if (eb == NULL) {
		i915_gem_context_unreference(ctx);
		mutex_unlock(&dev->struct_mutex);
		ret = -ENOMEM;
		goto pre_mutex_err;
	}

	/* Look up object handles */
	ret = eb_lookup_vmas(eb, exec, args, vm, file);
	if (ret)
		goto err;

	/* take note of the batch buffer before we might reorder the lists */
	batch_obj = eb_get_batch(eb);

	/* Move the objects en-masse into the GTT, evicting if necessary. */
	need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0;
	ret = i915_gem_execbuffer_reserve(ring, &eb->vmas, ctx, &need_relocs);
	if (ret)
		goto err;

	/* The objects are in their final locations, apply the relocations. */
	if (need_relocs)
		ret = i915_gem_execbuffer_relocate(eb);
	if (ret) {
		if (ret == -EFAULT) {
			ret = i915_gem_execbuffer_relocate_slow(dev, args, file, ring,
								eb, exec, ctx);
			BUG_ON(!mutex_is_locked(&dev->struct_mutex));
		}
		if (ret)
			goto err;
	}

	/* Set the pending read domains for the batch buffer to COMMAND */
	if (batch_obj->base.pending_write_domain) {
		DRM_DEBUG("Attempting to use self-modifying batch buffer\n");
		ret = -EINVAL;
		goto err;
	}

	params->args_batch_start_offset = args->batch_start_offset;
	if (i915_needs_cmd_parser(ring) && args->batch_len) {
		struct drm_i915_gem_object *parsed_batch_obj;

		parsed_batch_obj = i915_gem_execbuffer_parse(ring,
						      &shadow_exec_entry,
						      eb,
						      batch_obj,
						      args->batch_start_offset,
						      args->batch_len,
						      file->is_master);
		if (IS_ERR(parsed_batch_obj)) {
			ret = PTR_ERR(parsed_batch_obj);
			goto err;
		}

		/*
		 * parsed_batch_obj == batch_obj means batch not fully parsed:
		 * Accept, but don't promote to secure.
		 */

		if (parsed_batch_obj != batch_obj) {
			/*
			 * Batch parsed and accepted:
			 *
			 * Set the DISPATCH_SECURE bit to remove the NON_SECURE
			 * bit from MI_BATCH_BUFFER_START commands issued in
			 * the dispatch_execbuffer implementations. We
			 * specifically don't want that set on batches the
			 * command parser has accepted.
			 */
			dispatch_flags |= I915_DISPATCH_SECURE;
			params->args_batch_start_offset = 0;
			batch_obj = parsed_batch_obj;
		}
	}

	batch_obj->base.pending_read_domains |= I915_GEM_DOMAIN_COMMAND;

	/* snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure
	 * batch" bit. Hence we need to pin secure batches into the global gtt.
	 * hsw should have this fixed, but bdw mucks it up again. */
	if (dispatch_flags & I915_DISPATCH_SECURE) {
		/*
		 * So on first glance it looks freaky that we pin the batch here
		 * outside of the reservation loop. But:
		 * - The batch is already pinned into the relevant ppgtt, so we
		 *   already have the backing storage fully allocated.
		 * - No other BO uses the global gtt (well contexts, but meh),
		 *   so we don't really have issues with multiple objects not
		 *   fitting due to fragmentation.
		 * So this is actually safe.
		 */
		ret = i915_gem_obj_ggtt_pin(batch_obj, 0, 0);
		if (ret)
			goto err;

		params->batch_obj_vm_offset = i915_gem_obj_ggtt_offset(batch_obj);
	} else
		params->batch_obj_vm_offset = i915_gem_obj_offset(batch_obj, vm);

	/* Allocate a request for this batch buffer nice and early. */
	req = i915_gem_request_alloc(ring, ctx);
	if (IS_ERR(req)) {
		ret = PTR_ERR(req);
		goto err_batch_unpin;
	}

	ret = i915_gem_request_add_to_client(req, file);
	if (ret)
		goto err_batch_unpin;

	/*
	 * Save assorted stuff away to pass through to *_submission().
	 * NB: This data should be 'persistent' and not local as it will
	 * kept around beyond the duration of the IOCTL once the GPU
	 * scheduler arrives.
	 */
	params->dev                     = dev;
	params->file                    = file;
	params->ring                    = ring;
	params->dispatch_flags          = dispatch_flags;
	params->batch_obj               = batch_obj;
	params->ctx                     = ctx;
	params->request                 = req;

	ret = dev_priv->gt.execbuf_submit(params, args, &eb->vmas);

err_batch_unpin:
	/*
	 * FIXME: We crucially rely upon the active tracking for the (ppgtt)
	 * batch vma for correctness. For less ugly and less fragility this
	 * needs to be adjusted to also track the ggtt batch vma properly as
	 * active.
	 */
	if (dispatch_flags & I915_DISPATCH_SECURE)
		i915_gem_object_ggtt_unpin(batch_obj);

err:
	/* the request owns the ref now */
	i915_gem_context_unreference(ctx);
	eb_destroy(eb);

	/*
	 * If the request was created but not successfully submitted then it
	 * must be freed again. If it was submitted then it is being tracked
	 * on the active request list and no clean up is required here.
	 */
	if (ret && !IS_ERR_OR_NULL(req))
		i915_gem_request_cancel(req);

	mutex_unlock(&dev->struct_mutex);

pre_mutex_err:
	/* intel_gpu_busy should also get a ref, so it will free when the device
	 * is really idle. */
	intel_runtime_pm_put(dev_priv);
	return ret;
}

/*
 * Legacy execbuffer just creates an exec2 list from the original exec object
 * list array and passes it to the real function.
 */
int
i915_gem_execbuffer(struct drm_device *dev, void *data,
		    struct drm_file *file)
{
	struct drm_i915_gem_execbuffer *args = data;
	struct drm_i915_gem_execbuffer2 exec2;
	struct drm_i915_gem_exec_object *exec_list = NULL;
	struct drm_i915_gem_exec_object2 *exec2_list = NULL;
	int ret, i;

	if (args->buffer_count < 1) {
		DRM_DEBUG("execbuf with %d buffers\n", args->buffer_count);
		return -EINVAL;
	}

	/* Copy in the exec list from userland */
	exec_list = drm_malloc_ab(sizeof(*exec_list), args->buffer_count);
	exec2_list = drm_malloc_ab(sizeof(*exec2_list), args->buffer_count);
	if (exec_list == NULL || exec2_list == NULL) {
		DRM_DEBUG("Failed to allocate exec list for %d buffers\n",
			  args->buffer_count);
		drm_free_large(exec_list);
		drm_free_large(exec2_list);
		return -ENOMEM;
	}
	ret = copy_from_user(exec_list,
			     to_user_ptr(args->buffers_ptr),
			     sizeof(*exec_list) * args->buffer_count);
	if (ret != 0) {
		DRM_DEBUG("copy %d exec entries failed %d\n",
			  args->buffer_count, ret);
		drm_free_large(exec_list);
		drm_free_large(exec2_list);
		return -EFAULT;
	}

	for (i = 0; i < args->buffer_count; i++) {
		exec2_list[i].handle = exec_list[i].handle;
		exec2_list[i].relocation_count = exec_list[i].relocation_count;
		exec2_list[i].relocs_ptr = exec_list[i].relocs_ptr;
		exec2_list[i].alignment = exec_list[i].alignment;
		exec2_list[i].offset = exec_list[i].offset;
		if (INTEL_INFO(dev)->gen < 4)
			exec2_list[i].flags = EXEC_OBJECT_NEEDS_FENCE;
		else
			exec2_list[i].flags = 0;
	}

	exec2.buffers_ptr = args->buffers_ptr;
	exec2.buffer_count = args->buffer_count;
	exec2.batch_start_offset = args->batch_start_offset;
	exec2.batch_len = args->batch_len;
	exec2.DR1 = args->DR1;
	exec2.DR4 = args->DR4;
	exec2.num_cliprects = args->num_cliprects;
	exec2.cliprects_ptr = args->cliprects_ptr;
	exec2.flags = I915_EXEC_RENDER;
	i915_execbuffer2_set_context_id(exec2, 0);

	ret = i915_gem_do_execbuffer(dev, data, file, &exec2, exec2_list);
	if (!ret) {
		struct drm_i915_gem_exec_object __user *user_exec_list =
			to_user_ptr(args->buffers_ptr);

		/* Copy the new buffer offsets back to the user's exec list. */
		for (i = 0; i < args->buffer_count; i++) {
			exec2_list[i].offset =
				gen8_canonical_addr(exec2_list[i].offset);
			ret = __copy_to_user(&user_exec_list[i].offset,
					     &exec2_list[i].offset,
					     sizeof(user_exec_list[i].offset));
			if (ret) {
				ret = -EFAULT;
				DRM_DEBUG("failed to copy %d exec entries "
					  "back to user (%d)\n",
					  args->buffer_count, ret);
				break;
			}
		}
	}

	drm_free_large(exec_list);
	drm_free_large(exec2_list);
	return ret;
}

int
i915_gem_execbuffer2(struct drm_device *dev, void *data,
		     struct drm_file *file)
{
	struct drm_i915_gem_execbuffer2 *args = data;
	struct drm_i915_gem_exec_object2 *exec2_list = NULL;
	int ret;

	if (args->buffer_count < 1 ||
	    args->buffer_count > UINT_MAX / sizeof(*exec2_list)) {
		DRM_DEBUG("execbuf2 with %d buffers\n", args->buffer_count);
		return -EINVAL;
	}

	if (args->rsvd2 != 0) {
		DRM_DEBUG("dirty rvsd2 field\n");
		return -EINVAL;
	}

	exec2_list = kmalloc(sizeof(*exec2_list)*args->buffer_count,
			     GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY);
	if (exec2_list == NULL)
		exec2_list = drm_malloc_ab(sizeof(*exec2_list),
					   args->buffer_count);
	if (exec2_list == NULL) {
		DRM_DEBUG("Failed to allocate exec list for %d buffers\n",
			  args->buffer_count);
		return -ENOMEM;
	}
	ret = copy_from_user(exec2_list,
			     to_user_ptr(args->buffers_ptr),
			     sizeof(*exec2_list) * args->buffer_count);
	if (ret != 0) {
		DRM_DEBUG("copy %d exec entries failed %d\n",
			  args->buffer_count, ret);
		drm_free_large(exec2_list);
		return -EFAULT;
	}

	ret = i915_gem_do_execbuffer(dev, data, file, args, exec2_list);
	if (!ret) {
		/* Copy the new buffer offsets back to the user's exec list. */
		struct drm_i915_gem_exec_object2 __user *user_exec_list =
				   to_user_ptr(args->buffers_ptr);
		int i;

		for (i = 0; i < args->buffer_count; i++) {
			exec2_list[i].offset =
				gen8_canonical_addr(exec2_list[i].offset);
			ret = __copy_to_user(&user_exec_list[i].offset,
					     &exec2_list[i].offset,
					     sizeof(user_exec_list[i].offset));
			if (ret) {
				ret = -EFAULT;
				DRM_DEBUG("failed to copy %d exec entries "
					  "back to user\n",
					  args->buffer_count);
				break;
			}
		}
	}

	drm_free_large(exec2_list);
	return ret;
}