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
|
/*
* Copyright © 2008-2015 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>
*
*/
#include <drm/drm_vma_manager.h>
#include <drm/i915_drm.h>
#include <linux/dma-fence-array.h>
#include <linux/kthread.h>
#include <linux/reservation.h>
#include <linux/shmem_fs.h>
#include <linux/slab.h>
#include <linux/stop_machine.h>
#include <linux/swap.h>
#include <linux/pci.h>
#include <linux/dma-buf.h>
#include <linux/mman.h>
#include "display/intel_display.h"
#include "display/intel_frontbuffer.h"
#include "gem/i915_gem_clflush.h"
#include "gem/i915_gem_context.h"
#include "gem/i915_gem_ioctls.h"
#include "gem/i915_gem_pm.h"
#include "gem/i915_gemfs.h"
#include "gt/intel_engine_user.h"
#include "gt/intel_gt.h"
#include "gt/intel_gt_pm.h"
#include "gt/intel_mocs.h"
#include "gt/intel_reset.h"
#include "gt/intel_renderstate.h"
#include "gt/intel_workarounds.h"
#include "i915_drv.h"
#include "i915_scatterlist.h"
#include "i915_trace.h"
#include "i915_vgpu.h"
#include "intel_pm.h"
static int
insert_mappable_node(struct i915_ggtt *ggtt,
struct drm_mm_node *node, u32 size)
{
memset(node, 0, sizeof(*node));
return drm_mm_insert_node_in_range(&ggtt->vm.mm, node,
size, 0, I915_COLOR_UNEVICTABLE,
0, ggtt->mappable_end,
DRM_MM_INSERT_LOW);
}
static void
remove_mappable_node(struct drm_mm_node *node)
{
drm_mm_remove_node(node);
}
int
i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
struct drm_file *file)
{
struct i915_ggtt *ggtt = &to_i915(dev)->ggtt;
struct drm_i915_gem_get_aperture *args = data;
struct i915_vma *vma;
u64 pinned;
mutex_lock(&ggtt->vm.mutex);
pinned = ggtt->vm.reserved;
list_for_each_entry(vma, &ggtt->vm.bound_list, vm_link)
if (i915_vma_is_pinned(vma))
pinned += vma->node.size;
mutex_unlock(&ggtt->vm.mutex);
args->aper_size = ggtt->vm.total;
args->aper_available_size = args->aper_size - pinned;
return 0;
}
int i915_gem_object_unbind(struct drm_i915_gem_object *obj,
unsigned long flags)
{
struct i915_vma *vma;
LIST_HEAD(still_in_list);
int ret = 0;
lockdep_assert_held(&obj->base.dev->struct_mutex);
spin_lock(&obj->vma.lock);
while (!ret && (vma = list_first_entry_or_null(&obj->vma.list,
struct i915_vma,
obj_link))) {
list_move_tail(&vma->obj_link, &still_in_list);
spin_unlock(&obj->vma.lock);
ret = -EBUSY;
if (flags & I915_GEM_OBJECT_UNBIND_ACTIVE ||
!i915_vma_is_active(vma))
ret = i915_vma_unbind(vma);
spin_lock(&obj->vma.lock);
}
list_splice(&still_in_list, &obj->vma.list);
spin_unlock(&obj->vma.lock);
return ret;
}
static int
i915_gem_phys_pwrite(struct drm_i915_gem_object *obj,
struct drm_i915_gem_pwrite *args,
struct drm_file *file)
{
void *vaddr = obj->phys_handle->vaddr + args->offset;
char __user *user_data = u64_to_user_ptr(args->data_ptr);
/*
* We manually control the domain here and pretend that it
* remains coherent i.e. in the GTT domain, like shmem_pwrite.
*/
intel_frontbuffer_invalidate(obj->frontbuffer, ORIGIN_CPU);
if (copy_from_user(vaddr, user_data, args->size))
return -EFAULT;
drm_clflush_virt_range(vaddr, args->size);
intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt);
intel_frontbuffer_flush(obj->frontbuffer, ORIGIN_CPU);
return 0;
}
static int
i915_gem_create(struct drm_file *file,
struct drm_i915_private *dev_priv,
u64 *size_p,
u32 *handle_p)
{
struct drm_i915_gem_object *obj;
u32 handle;
u64 size;
int ret;
size = round_up(*size_p, PAGE_SIZE);
if (size == 0)
return -EINVAL;
/* Allocate the new object */
obj = i915_gem_object_create_shmem(dev_priv, size);
if (IS_ERR(obj))
return PTR_ERR(obj);
ret = drm_gem_handle_create(file, &obj->base, &handle);
/* drop reference from allocate - handle holds it now */
i915_gem_object_put(obj);
if (ret)
return ret;
*handle_p = handle;
*size_p = size;
return 0;
}
int
i915_gem_dumb_create(struct drm_file *file,
struct drm_device *dev,
struct drm_mode_create_dumb *args)
{
int cpp = DIV_ROUND_UP(args->bpp, 8);
u32 format;
switch (cpp) {
case 1:
format = DRM_FORMAT_C8;
break;
case 2:
format = DRM_FORMAT_RGB565;
break;
case 4:
format = DRM_FORMAT_XRGB8888;
break;
default:
return -EINVAL;
}
/* have to work out size/pitch and return them */
args->pitch = ALIGN(args->width * cpp, 64);
/* align stride to page size so that we can remap */
if (args->pitch > intel_plane_fb_max_stride(to_i915(dev), format,
DRM_FORMAT_MOD_LINEAR))
args->pitch = ALIGN(args->pitch, 4096);
args->size = args->pitch * args->height;
return i915_gem_create(file, to_i915(dev),
&args->size, &args->handle);
}
/**
* Creates a new mm object and returns a handle to it.
* @dev: drm device pointer
* @data: ioctl data blob
* @file: drm file pointer
*/
int
i915_gem_create_ioctl(struct drm_device *dev, void *data,
struct drm_file *file)
{
struct drm_i915_private *dev_priv = to_i915(dev);
struct drm_i915_gem_create *args = data;
i915_gem_flush_free_objects(dev_priv);
return i915_gem_create(file, dev_priv,
&args->size, &args->handle);
}
static int
shmem_pread(struct page *page, int offset, int len, char __user *user_data,
bool needs_clflush)
{
char *vaddr;
int ret;
vaddr = kmap(page);
if (needs_clflush)
drm_clflush_virt_range(vaddr + offset, len);
ret = __copy_to_user(user_data, vaddr + offset, len);
kunmap(page);
return ret ? -EFAULT : 0;
}
static int
i915_gem_shmem_pread(struct drm_i915_gem_object *obj,
struct drm_i915_gem_pread *args)
{
unsigned int needs_clflush;
unsigned int idx, offset;
struct dma_fence *fence;
char __user *user_data;
u64 remain;
int ret;
ret = i915_gem_object_prepare_read(obj, &needs_clflush);
if (ret)
return ret;
fence = i915_gem_object_lock_fence(obj);
i915_gem_object_finish_access(obj);
if (!fence)
return -ENOMEM;
remain = args->size;
user_data = u64_to_user_ptr(args->data_ptr);
offset = offset_in_page(args->offset);
for (idx = args->offset >> PAGE_SHIFT; remain; idx++) {
struct page *page = i915_gem_object_get_page(obj, idx);
unsigned int length = min_t(u64, remain, PAGE_SIZE - offset);
ret = shmem_pread(page, offset, length, user_data,
needs_clflush);
if (ret)
break;
remain -= length;
user_data += length;
offset = 0;
}
i915_gem_object_unlock_fence(obj, fence);
return ret;
}
static inline bool
gtt_user_read(struct io_mapping *mapping,
loff_t base, int offset,
char __user *user_data, int length)
{
void __iomem *vaddr;
unsigned long unwritten;
/* We can use the cpu mem copy function because this is X86. */
vaddr = io_mapping_map_atomic_wc(mapping, base);
unwritten = __copy_to_user_inatomic(user_data,
(void __force *)vaddr + offset,
length);
io_mapping_unmap_atomic(vaddr);
if (unwritten) {
vaddr = io_mapping_map_wc(mapping, base, PAGE_SIZE);
unwritten = copy_to_user(user_data,
(void __force *)vaddr + offset,
length);
io_mapping_unmap(vaddr);
}
return unwritten;
}
static int
i915_gem_gtt_pread(struct drm_i915_gem_object *obj,
const struct drm_i915_gem_pread *args)
{
struct drm_i915_private *i915 = to_i915(obj->base.dev);
struct i915_ggtt *ggtt = &i915->ggtt;
intel_wakeref_t wakeref;
struct drm_mm_node node;
struct dma_fence *fence;
void __user *user_data;
struct i915_vma *vma;
u64 remain, offset;
int ret;
ret = mutex_lock_interruptible(&i915->drm.struct_mutex);
if (ret)
return ret;
wakeref = intel_runtime_pm_get(&i915->runtime_pm);
vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0,
PIN_MAPPABLE |
PIN_NONBLOCK /* NOWARN */ |
PIN_NOEVICT);
if (!IS_ERR(vma)) {
node.start = i915_ggtt_offset(vma);
node.allocated = false;
ret = i915_vma_put_fence(vma);
if (ret) {
i915_vma_unpin(vma);
vma = ERR_PTR(ret);
}
}
if (IS_ERR(vma)) {
ret = insert_mappable_node(ggtt, &node, PAGE_SIZE);
if (ret)
goto out_unlock;
GEM_BUG_ON(!node.allocated);
}
mutex_unlock(&i915->drm.struct_mutex);
ret = i915_gem_object_lock_interruptible(obj);
if (ret)
goto out_unpin;
ret = i915_gem_object_set_to_gtt_domain(obj, false);
if (ret) {
i915_gem_object_unlock(obj);
goto out_unpin;
}
fence = i915_gem_object_lock_fence(obj);
i915_gem_object_unlock(obj);
if (!fence) {
ret = -ENOMEM;
goto out_unpin;
}
user_data = u64_to_user_ptr(args->data_ptr);
remain = args->size;
offset = args->offset;
while (remain > 0) {
/* Operation in this page
*
* page_base = page offset within aperture
* page_offset = offset within page
* page_length = bytes to copy for this page
*/
u32 page_base = node.start;
unsigned page_offset = offset_in_page(offset);
unsigned page_length = PAGE_SIZE - page_offset;
page_length = remain < page_length ? remain : page_length;
if (node.allocated) {
ggtt->vm.insert_page(&ggtt->vm,
i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT),
node.start, I915_CACHE_NONE, 0);
} else {
page_base += offset & PAGE_MASK;
}
if (gtt_user_read(&ggtt->iomap, page_base, page_offset,
user_data, page_length)) {
ret = -EFAULT;
break;
}
remain -= page_length;
user_data += page_length;
offset += page_length;
}
i915_gem_object_unlock_fence(obj, fence);
out_unpin:
mutex_lock(&i915->drm.struct_mutex);
if (node.allocated) {
ggtt->vm.clear_range(&ggtt->vm, node.start, node.size);
remove_mappable_node(&node);
} else {
i915_vma_unpin(vma);
}
out_unlock:
intel_runtime_pm_put(&i915->runtime_pm, wakeref);
mutex_unlock(&i915->drm.struct_mutex);
return ret;
}
/**
* Reads data from the object referenced by handle.
* @dev: drm device pointer
* @data: ioctl data blob
* @file: drm file pointer
*
* On error, the contents of *data are undefined.
*/
int
i915_gem_pread_ioctl(struct drm_device *dev, void *data,
struct drm_file *file)
{
struct drm_i915_gem_pread *args = data;
struct drm_i915_gem_object *obj;
int ret;
if (args->size == 0)
return 0;
if (!access_ok(u64_to_user_ptr(args->data_ptr),
args->size))
return -EFAULT;
obj = i915_gem_object_lookup(file, args->handle);
if (!obj)
return -ENOENT;
/* Bounds check source. */
if (range_overflows_t(u64, args->offset, args->size, obj->base.size)) {
ret = -EINVAL;
goto out;
}
trace_i915_gem_object_pread(obj, args->offset, args->size);
ret = i915_gem_object_wait(obj,
I915_WAIT_INTERRUPTIBLE,
MAX_SCHEDULE_TIMEOUT);
if (ret)
goto out;
ret = i915_gem_object_pin_pages(obj);
if (ret)
goto out;
ret = i915_gem_shmem_pread(obj, args);
if (ret == -EFAULT || ret == -ENODEV)
ret = i915_gem_gtt_pread(obj, args);
i915_gem_object_unpin_pages(obj);
out:
i915_gem_object_put(obj);
return ret;
}
/* This is the fast write path which cannot handle
* page faults in the source data
*/
static inline bool
ggtt_write(struct io_mapping *mapping,
loff_t base, int offset,
char __user *user_data, int length)
{
void __iomem *vaddr;
unsigned long unwritten;
/* We can use the cpu mem copy function because this is X86. */
vaddr = io_mapping_map_atomic_wc(mapping, base);
unwritten = __copy_from_user_inatomic_nocache((void __force *)vaddr + offset,
user_data, length);
io_mapping_unmap_atomic(vaddr);
if (unwritten) {
vaddr = io_mapping_map_wc(mapping, base, PAGE_SIZE);
unwritten = copy_from_user((void __force *)vaddr + offset,
user_data, length);
io_mapping_unmap(vaddr);
}
return unwritten;
}
/**
* This is the fast pwrite path, where we copy the data directly from the
* user into the GTT, uncached.
* @obj: i915 GEM object
* @args: pwrite arguments structure
*/
static int
i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj,
const struct drm_i915_gem_pwrite *args)
{
struct drm_i915_private *i915 = to_i915(obj->base.dev);
struct i915_ggtt *ggtt = &i915->ggtt;
struct intel_runtime_pm *rpm = &i915->runtime_pm;
intel_wakeref_t wakeref;
struct drm_mm_node node;
struct dma_fence *fence;
struct i915_vma *vma;
u64 remain, offset;
void __user *user_data;
int ret;
ret = mutex_lock_interruptible(&i915->drm.struct_mutex);
if (ret)
return ret;
if (i915_gem_object_has_struct_page(obj)) {
/*
* Avoid waking the device up if we can fallback, as
* waking/resuming is very slow (worst-case 10-100 ms
* depending on PCI sleeps and our own resume time).
* This easily dwarfs any performance advantage from
* using the cache bypass of indirect GGTT access.
*/
wakeref = intel_runtime_pm_get_if_in_use(rpm);
if (!wakeref) {
ret = -EFAULT;
goto out_unlock;
}
} else {
/* No backing pages, no fallback, we must force GGTT access */
wakeref = intel_runtime_pm_get(rpm);
}
vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0,
PIN_MAPPABLE |
PIN_NONBLOCK /* NOWARN */ |
PIN_NOEVICT);
if (!IS_ERR(vma)) {
node.start = i915_ggtt_offset(vma);
node.allocated = false;
ret = i915_vma_put_fence(vma);
if (ret) {
i915_vma_unpin(vma);
vma = ERR_PTR(ret);
}
}
if (IS_ERR(vma)) {
ret = insert_mappable_node(ggtt, &node, PAGE_SIZE);
if (ret)
goto out_rpm;
GEM_BUG_ON(!node.allocated);
}
mutex_unlock(&i915->drm.struct_mutex);
ret = i915_gem_object_lock_interruptible(obj);
if (ret)
goto out_unpin;
ret = i915_gem_object_set_to_gtt_domain(obj, true);
if (ret) {
i915_gem_object_unlock(obj);
goto out_unpin;
}
fence = i915_gem_object_lock_fence(obj);
i915_gem_object_unlock(obj);
if (!fence) {
ret = -ENOMEM;
goto out_unpin;
}
intel_frontbuffer_invalidate(obj->frontbuffer, ORIGIN_CPU);
user_data = u64_to_user_ptr(args->data_ptr);
offset = args->offset;
remain = args->size;
while (remain) {
/* Operation in this page
*
* page_base = page offset within aperture
* page_offset = offset within page
* page_length = bytes to copy for this page
*/
u32 page_base = node.start;
unsigned int page_offset = offset_in_page(offset);
unsigned int page_length = PAGE_SIZE - page_offset;
page_length = remain < page_length ? remain : page_length;
if (node.allocated) {
/* flush the write before we modify the GGTT */
intel_gt_flush_ggtt_writes(ggtt->vm.gt);
ggtt->vm.insert_page(&ggtt->vm,
i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT),
node.start, I915_CACHE_NONE, 0);
wmb(); /* flush modifications to the GGTT (insert_page) */
} else {
page_base += offset & PAGE_MASK;
}
/* If we get a fault while copying data, then (presumably) our
* source page isn't available. Return the error and we'll
* retry in the slow path.
* If the object is non-shmem backed, we retry again with the
* path that handles page fault.
*/
if (ggtt_write(&ggtt->iomap, page_base, page_offset,
user_data, page_length)) {
ret = -EFAULT;
break;
}
remain -= page_length;
user_data += page_length;
offset += page_length;
}
intel_frontbuffer_flush(obj->frontbuffer, ORIGIN_CPU);
i915_gem_object_unlock_fence(obj, fence);
out_unpin:
mutex_lock(&i915->drm.struct_mutex);
intel_gt_flush_ggtt_writes(ggtt->vm.gt);
if (node.allocated) {
ggtt->vm.clear_range(&ggtt->vm, node.start, node.size);
remove_mappable_node(&node);
} else {
i915_vma_unpin(vma);
}
out_rpm:
intel_runtime_pm_put(rpm, wakeref);
out_unlock:
mutex_unlock(&i915->drm.struct_mutex);
return ret;
}
/* Per-page copy function for the shmem pwrite fastpath.
* Flushes invalid cachelines before writing to the target if
* needs_clflush_before is set and flushes out any written cachelines after
* writing if needs_clflush is set.
*/
static int
shmem_pwrite(struct page *page, int offset, int len, char __user *user_data,
bool needs_clflush_before,
bool needs_clflush_after)
{
char *vaddr;
int ret;
vaddr = kmap(page);
if (needs_clflush_before)
drm_clflush_virt_range(vaddr + offset, len);
ret = __copy_from_user(vaddr + offset, user_data, len);
if (!ret && needs_clflush_after)
drm_clflush_virt_range(vaddr + offset, len);
kunmap(page);
return ret ? -EFAULT : 0;
}
static int
i915_gem_shmem_pwrite(struct drm_i915_gem_object *obj,
const struct drm_i915_gem_pwrite *args)
{
unsigned int partial_cacheline_write;
unsigned int needs_clflush;
unsigned int offset, idx;
struct dma_fence *fence;
void __user *user_data;
u64 remain;
int ret;
ret = i915_gem_object_prepare_write(obj, &needs_clflush);
if (ret)
return ret;
fence = i915_gem_object_lock_fence(obj);
i915_gem_object_finish_access(obj);
if (!fence)
return -ENOMEM;
/* If we don't overwrite a cacheline completely we need to be
* careful to have up-to-date data by first clflushing. Don't
* overcomplicate things and flush the entire patch.
*/
partial_cacheline_write = 0;
if (needs_clflush & CLFLUSH_BEFORE)
partial_cacheline_write = boot_cpu_data.x86_clflush_size - 1;
user_data = u64_to_user_ptr(args->data_ptr);
remain = args->size;
offset = offset_in_page(args->offset);
for (idx = args->offset >> PAGE_SHIFT; remain; idx++) {
struct page *page = i915_gem_object_get_page(obj, idx);
unsigned int length = min_t(u64, remain, PAGE_SIZE - offset);
ret = shmem_pwrite(page, offset, length, user_data,
(offset | length) & partial_cacheline_write,
needs_clflush & CLFLUSH_AFTER);
if (ret)
break;
remain -= length;
user_data += length;
offset = 0;
}
intel_frontbuffer_flush(obj->frontbuffer, ORIGIN_CPU);
i915_gem_object_unlock_fence(obj, fence);
return ret;
}
/**
* Writes data to the object referenced by handle.
* @dev: drm device
* @data: ioctl data blob
* @file: drm file
*
* On error, the contents of the buffer that were to be modified are undefined.
*/
int
i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
struct drm_file *file)
{
struct drm_i915_gem_pwrite *args = data;
struct drm_i915_gem_object *obj;
int ret;
if (args->size == 0)
return 0;
if (!access_ok(u64_to_user_ptr(args->data_ptr), args->size))
return -EFAULT;
obj = i915_gem_object_lookup(file, args->handle);
if (!obj)
return -ENOENT;
/* Bounds check destination. */
if (range_overflows_t(u64, args->offset, args->size, obj->base.size)) {
ret = -EINVAL;
goto err;
}
/* Writes not allowed into this read-only object */
if (i915_gem_object_is_readonly(obj)) {
ret = -EINVAL;
goto err;
}
trace_i915_gem_object_pwrite(obj, args->offset, args->size);
ret = -ENODEV;
if (obj->ops->pwrite)
ret = obj->ops->pwrite(obj, args);
if (ret != -ENODEV)
goto err;
ret = i915_gem_object_wait(obj,
I915_WAIT_INTERRUPTIBLE |
I915_WAIT_ALL,
MAX_SCHEDULE_TIMEOUT);
if (ret)
goto err;
ret = i915_gem_object_pin_pages(obj);
if (ret)
goto err;
ret = -EFAULT;
/* We can only do the GTT pwrite on untiled buffers, as otherwise
* it would end up going through the fenced access, and we'll get
* different detiling behavior between reading and writing.
* pread/pwrite currently are reading and writing from the CPU
* perspective, requiring manual detiling by the client.
*/
if (!i915_gem_object_has_struct_page(obj) ||
cpu_write_needs_clflush(obj))
/* Note that the gtt paths might fail with non-page-backed user
* pointers (e.g. gtt mappings when moving data between
* textures). Fallback to the shmem path in that case.
*/
ret = i915_gem_gtt_pwrite_fast(obj, args);
if (ret == -EFAULT || ret == -ENOSPC) {
if (obj->phys_handle)
ret = i915_gem_phys_pwrite(obj, args, file);
else
ret = i915_gem_shmem_pwrite(obj, args);
}
i915_gem_object_unpin_pages(obj);
err:
i915_gem_object_put(obj);
return ret;
}
/**
* Called when user space has done writes to this buffer
* @dev: drm device
* @data: ioctl data blob
* @file: drm file
*/
int
i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data,
struct drm_file *file)
{
struct drm_i915_gem_sw_finish *args = data;
struct drm_i915_gem_object *obj;
obj = i915_gem_object_lookup(file, args->handle);
if (!obj)
return -ENOENT;
/*
* Proxy objects are barred from CPU access, so there is no
* need to ban sw_finish as it is a nop.
*/
/* Pinned buffers may be scanout, so flush the cache */
i915_gem_object_flush_if_display(obj);
i915_gem_object_put(obj);
return 0;
}
void i915_gem_runtime_suspend(struct drm_i915_private *i915)
{
struct drm_i915_gem_object *obj, *on;
int i;
/*
* Only called during RPM suspend. All users of the userfault_list
* must be holding an RPM wakeref to ensure that this can not
* run concurrently with themselves (and use the struct_mutex for
* protection between themselves).
*/
list_for_each_entry_safe(obj, on,
&i915->ggtt.userfault_list, userfault_link)
__i915_gem_object_release_mmap(obj);
/*
* The fence will be lost when the device powers down. If any were
* in use by hardware (i.e. they are pinned), we should not be powering
* down! All other fences will be reacquired by the user upon waking.
*/
for (i = 0; i < i915->ggtt.num_fences; i++) {
struct i915_fence_reg *reg = &i915->ggtt.fence_regs[i];
/*
* Ideally we want to assert that the fence register is not
* live at this point (i.e. that no piece of code will be
* trying to write through fence + GTT, as that both violates
* our tracking of activity and associated locking/barriers,
* but also is illegal given that the hw is powered down).
*
* Previously we used reg->pin_count as a "liveness" indicator.
* That is not sufficient, and we need a more fine-grained
* tool if we want to have a sanity check here.
*/
if (!reg->vma)
continue;
GEM_BUG_ON(i915_vma_has_userfault(reg->vma));
reg->dirty = true;
}
}
static long
wait_for_timelines(struct drm_i915_private *i915,
unsigned int flags, long timeout)
{
struct intel_gt_timelines *timelines = &i915->gt.timelines;
struct intel_timeline *tl;
spin_lock(&timelines->lock);
list_for_each_entry(tl, &timelines->active_list, link) {
struct i915_request *rq;
rq = i915_active_request_get_unlocked(&tl->last_request);
if (!rq)
continue;
spin_unlock(&timelines->lock);
/*
* "Race-to-idle".
*
* Switching to the kernel context is often used a synchronous
* step prior to idling, e.g. in suspend for flushing all
* current operations to memory before sleeping. These we
* want to complete as quickly as possible to avoid prolonged
* stalls, so allow the gpu to boost to maximum clocks.
*/
if (flags & I915_WAIT_FOR_IDLE_BOOST)
gen6_rps_boost(rq);
timeout = i915_request_wait(rq, flags, timeout);
i915_request_put(rq);
if (timeout < 0)
return timeout;
/* restart after reacquiring the lock */
spin_lock(&timelines->lock);
tl = list_entry(&timelines->active_list, typeof(*tl), link);
}
spin_unlock(&timelines->lock);
return timeout;
}
int i915_gem_wait_for_idle(struct drm_i915_private *i915,
unsigned int flags, long timeout)
{
/* If the device is asleep, we have no requests outstanding */
if (!intel_gt_pm_is_awake(&i915->gt))
return 0;
GEM_TRACE("flags=%x (%s), timeout=%ld%s\n",
flags, flags & I915_WAIT_LOCKED ? "locked" : "unlocked",
timeout, timeout == MAX_SCHEDULE_TIMEOUT ? " (forever)" : "");
timeout = wait_for_timelines(i915, flags, timeout);
if (timeout < 0)
return timeout;
if (flags & I915_WAIT_LOCKED) {
lockdep_assert_held(&i915->drm.struct_mutex);
i915_retire_requests(i915);
}
return 0;
}
struct i915_vma *
i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
const struct i915_ggtt_view *view,
u64 size,
u64 alignment,
u64 flags)
{
struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
struct i915_address_space *vm = &dev_priv->ggtt.vm;
struct i915_vma *vma;
int ret;
lockdep_assert_held(&obj->base.dev->struct_mutex);
if (flags & PIN_MAPPABLE &&
(!view || view->type == I915_GGTT_VIEW_NORMAL)) {
/* If the required space is larger than the available
* aperture, we will not able to find a slot for the
* object and unbinding the object now will be in
* vain. Worse, doing so may cause us to ping-pong
* the object in and out of the Global GTT and
* waste a lot of cycles under the mutex.
*/
if (obj->base.size > dev_priv->ggtt.mappable_end)
return ERR_PTR(-E2BIG);
/* If NONBLOCK is set the caller is optimistically
* trying to cache the full object within the mappable
* aperture, and *must* have a fallback in place for
* situations where we cannot bind the object. We
* can be a little more lax here and use the fallback
* more often to avoid costly migrations of ourselves
* and other objects within the aperture.
*
* Half-the-aperture is used as a simple heuristic.
* More interesting would to do search for a free
* block prior to making the commitment to unbind.
* That caters for the self-harm case, and with a
* little more heuristics (e.g. NOFAULT, NOEVICT)
* we could try to minimise harm to others.
*/
if (flags & PIN_NONBLOCK &&
obj->base.size > dev_priv->ggtt.mappable_end / 2)
return ERR_PTR(-ENOSPC);
}
vma = i915_vma_instance(obj, vm, view);
if (IS_ERR(vma))
return vma;
if (i915_vma_misplaced(vma, size, alignment, flags)) {
if (flags & PIN_NONBLOCK) {
if (i915_vma_is_pinned(vma) || i915_vma_is_active(vma))
return ERR_PTR(-ENOSPC);
if (flags & PIN_MAPPABLE &&
vma->fence_size > dev_priv->ggtt.mappable_end / 2)
return ERR_PTR(-ENOSPC);
}
WARN(i915_vma_is_pinned(vma),
"bo is already pinned in ggtt with incorrect alignment:"
" offset=%08x, req.alignment=%llx,"
" req.map_and_fenceable=%d, vma->map_and_fenceable=%d\n",
i915_ggtt_offset(vma), alignment,
!!(flags & PIN_MAPPABLE),
i915_vma_is_map_and_fenceable(vma));
ret = i915_vma_unbind(vma);
if (ret)
return ERR_PTR(ret);
}
ret = i915_vma_pin(vma, size, alignment, flags | PIN_GLOBAL);
if (ret)
return ERR_PTR(ret);
return vma;
}
int
i915_gem_madvise_ioctl(struct drm_device *dev, void *data,
struct drm_file *file_priv)
{
struct drm_i915_private *i915 = to_i915(dev);
struct drm_i915_gem_madvise *args = data;
struct drm_i915_gem_object *obj;
int err;
switch (args->madv) {
case I915_MADV_DONTNEED:
case I915_MADV_WILLNEED:
break;
default:
return -EINVAL;
}
obj = i915_gem_object_lookup(file_priv, args->handle);
if (!obj)
return -ENOENT;
err = mutex_lock_interruptible(&obj->mm.lock);
if (err)
goto out;
if (i915_gem_object_has_pages(obj) &&
i915_gem_object_is_tiled(obj) &&
i915->quirks & QUIRK_PIN_SWIZZLED_PAGES) {
if (obj->mm.madv == I915_MADV_WILLNEED) {
GEM_BUG_ON(!obj->mm.quirked);
__i915_gem_object_unpin_pages(obj);
obj->mm.quirked = false;
}
if (args->madv == I915_MADV_WILLNEED) {
GEM_BUG_ON(obj->mm.quirked);
__i915_gem_object_pin_pages(obj);
obj->mm.quirked = true;
}
}
if (obj->mm.madv != __I915_MADV_PURGED)
obj->mm.madv = args->madv;
if (i915_gem_object_has_pages(obj)) {
struct list_head *list;
if (i915_gem_object_is_shrinkable(obj)) {
unsigned long flags;
spin_lock_irqsave(&i915->mm.obj_lock, flags);
if (obj->mm.madv != I915_MADV_WILLNEED)
list = &i915->mm.purge_list;
else
list = &i915->mm.shrink_list;
list_move_tail(&obj->mm.link, list);
spin_unlock_irqrestore(&i915->mm.obj_lock, flags);
}
}
/* if the object is no longer attached, discard its backing storage */
if (obj->mm.madv == I915_MADV_DONTNEED &&
!i915_gem_object_has_pages(obj))
i915_gem_object_truncate(obj);
args->retained = obj->mm.madv != __I915_MADV_PURGED;
mutex_unlock(&obj->mm.lock);
out:
i915_gem_object_put(obj);
return err;
}
void i915_gem_sanitize(struct drm_i915_private *i915)
{
intel_wakeref_t wakeref;
GEM_TRACE("\n");
wakeref = intel_runtime_pm_get(&i915->runtime_pm);
intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL);
/*
* As we have just resumed the machine and woken the device up from
* deep PCI sleep (presumably D3_cold), assume the HW has been reset
* back to defaults, recovering from whatever wedged state we left it
* in and so worth trying to use the device once more.
*/
if (intel_gt_is_wedged(&i915->gt))
intel_gt_unset_wedged(&i915->gt);
/*
* If we inherit context state from the BIOS or earlier occupants
* of the GPU, the GPU may be in an inconsistent state when we
* try to take over. The only way to remove the earlier state
* is by resetting. However, resetting on earlier gen is tricky as
* it may impact the display and we are uncertain about the stability
* of the reset, so this could be applied to even earlier gen.
*/
intel_gt_sanitize(&i915->gt, false);
intel_uncore_forcewake_put(&i915->uncore, FORCEWAKE_ALL);
intel_runtime_pm_put(&i915->runtime_pm, wakeref);
}
static void init_unused_ring(struct intel_gt *gt, u32 base)
{
struct intel_uncore *uncore = gt->uncore;
intel_uncore_write(uncore, RING_CTL(base), 0);
intel_uncore_write(uncore, RING_HEAD(base), 0);
intel_uncore_write(uncore, RING_TAIL(base), 0);
intel_uncore_write(uncore, RING_START(base), 0);
}
static void init_unused_rings(struct intel_gt *gt)
{
struct drm_i915_private *i915 = gt->i915;
if (IS_I830(i915)) {
init_unused_ring(gt, PRB1_BASE);
init_unused_ring(gt, SRB0_BASE);
init_unused_ring(gt, SRB1_BASE);
init_unused_ring(gt, SRB2_BASE);
init_unused_ring(gt, SRB3_BASE);
} else if (IS_GEN(i915, 2)) {
init_unused_ring(gt, SRB0_BASE);
init_unused_ring(gt, SRB1_BASE);
} else if (IS_GEN(i915, 3)) {
init_unused_ring(gt, PRB1_BASE);
init_unused_ring(gt, PRB2_BASE);
}
}
int i915_gem_init_hw(struct drm_i915_private *i915)
{
struct intel_uncore *uncore = &i915->uncore;
struct intel_gt *gt = &i915->gt;
int ret;
BUG_ON(!i915->kernel_context);
ret = intel_gt_terminally_wedged(gt);
if (ret)
return ret;
gt->last_init_time = ktime_get();
/* Double layer security blanket, see i915_gem_init() */
intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
if (HAS_EDRAM(i915) && INTEL_GEN(i915) < 9)
intel_uncore_rmw(uncore, HSW_IDICR, 0, IDIHASHMSK(0xf));
if (IS_HASWELL(i915))
intel_uncore_write(uncore,
MI_PREDICATE_RESULT_2,
IS_HSW_GT3(i915) ?
LOWER_SLICE_ENABLED : LOWER_SLICE_DISABLED);
/* Apply the GT workarounds... */
intel_gt_apply_workarounds(gt);
/* ...and determine whether they are sticking. */
intel_gt_verify_workarounds(gt, "init");
intel_gt_init_swizzling(gt);
/*
* At least 830 can leave some of the unused rings
* "active" (ie. head != tail) after resume which
* will prevent c3 entry. Makes sure all unused rings
* are totally idle.
*/
init_unused_rings(gt);
ret = i915_ppgtt_init_hw(gt);
if (ret) {
DRM_ERROR("Enabling PPGTT failed (%d)\n", ret);
goto out;
}
/* We can't enable contexts until all firmware is loaded */
ret = intel_uc_init_hw(>->uc);
if (ret) {
i915_probe_error(i915, "Enabling uc failed (%d)\n", ret);
goto out;
}
intel_mocs_init(gt);
out:
intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL);
return ret;
}
static int __intel_engines_record_defaults(struct drm_i915_private *i915)
{
struct i915_request *requests[I915_NUM_ENGINES] = {};
struct intel_engine_cs *engine;
enum intel_engine_id id;
int err = 0;
/*
* As we reset the gpu during very early sanitisation, the current
* register state on the GPU should reflect its defaults values.
* We load a context onto the hw (with restore-inhibit), then switch
* over to a second context to save that default register state. We
* can then prime every new context with that state so they all start
* from the same default HW values.
*/
for_each_engine(engine, i915, id) {
struct intel_context *ce;
struct i915_request *rq;
/* We must be able to switch to something! */
GEM_BUG_ON(!engine->kernel_context);
engine->serial++; /* force the kernel context switch */
ce = intel_context_create(i915->kernel_context, engine);
if (IS_ERR(ce)) {
err = PTR_ERR(ce);
goto out;
}
rq = intel_context_create_request(ce);
if (IS_ERR(rq)) {
err = PTR_ERR(rq);
intel_context_put(ce);
goto out;
}
err = intel_engine_emit_ctx_wa(rq);
if (err)
goto err_rq;
/*
* Failing to program the MOCS is non-fatal.The system will not
* run at peak performance. So warn the user and carry on.
*/
err = intel_mocs_emit(rq);
if (err)
dev_notice(i915->drm.dev,
"Failed to program MOCS registers; expect performance issues.\n");
err = intel_renderstate_emit(rq);
if (err)
goto err_rq;
err_rq:
requests[id] = i915_request_get(rq);
i915_request_add(rq);
if (err)
goto out;
}
/* Flush the default context image to memory, and enable powersaving. */
if (!i915_gem_load_power_context(i915)) {
err = -EIO;
goto out;
}
for (id = 0; id < ARRAY_SIZE(requests); id++) {
struct i915_request *rq;
struct i915_vma *state;
void *vaddr;
rq = requests[id];
if (!rq)
continue;
/* We want to be able to unbind the state from the GGTT */
GEM_BUG_ON(intel_context_is_pinned(rq->hw_context));
state = rq->hw_context->state;
if (!state)
continue;
/*
* As we will hold a reference to the logical state, it will
* not be torn down with the context, and importantly the
* object will hold onto its vma (making it possible for a
* stray GTT write to corrupt our defaults). Unmap the vma
* from the GTT to prevent such accidents and reclaim the
* space.
*/
err = i915_vma_unbind(state);
if (err)
goto out;
i915_gem_object_lock(state->obj);
err = i915_gem_object_set_to_cpu_domain(state->obj, false);
i915_gem_object_unlock(state->obj);
if (err)
goto out;
i915_gem_object_set_cache_coherency(state->obj, I915_CACHE_LLC);
/* Check we can acquire the image of the context state */
vaddr = i915_gem_object_pin_map(state->obj, I915_MAP_FORCE_WB);
if (IS_ERR(vaddr)) {
err = PTR_ERR(vaddr);
goto out;
}
rq->engine->default_state = i915_gem_object_get(state->obj);
i915_gem_object_unpin_map(state->obj);
}
out:
/*
* If we have to abandon now, we expect the engines to be idle
* and ready to be torn-down. The quickest way we can accomplish
* this is by declaring ourselves wedged.
*/
if (err)
intel_gt_set_wedged(&i915->gt);
for (id = 0; id < ARRAY_SIZE(requests); id++) {
struct intel_context *ce;
struct i915_request *rq;
rq = requests[id];
if (!rq)
continue;
ce = rq->hw_context;
i915_request_put(rq);
intel_context_put(ce);
}
return err;
}
static int
i915_gem_init_scratch(struct drm_i915_private *i915, unsigned int size)
{
return intel_gt_init_scratch(&i915->gt, size);
}
static void i915_gem_fini_scratch(struct drm_i915_private *i915)
{
intel_gt_fini_scratch(&i915->gt);
}
static int intel_engines_verify_workarounds(struct drm_i915_private *i915)
{
struct intel_engine_cs *engine;
enum intel_engine_id id;
int err = 0;
if (!IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
return 0;
for_each_engine(engine, i915, id) {
if (intel_engine_verify_workarounds(engine, "load"))
err = -EIO;
}
return err;
}
int i915_gem_init(struct drm_i915_private *dev_priv)
{
int ret;
/* We need to fallback to 4K pages if host doesn't support huge gtt. */
if (intel_vgpu_active(dev_priv) && !intel_vgpu_has_huge_gtt(dev_priv))
mkwrite_device_info(dev_priv)->page_sizes =
I915_GTT_PAGE_SIZE_4K;
intel_timelines_init(dev_priv);
ret = i915_gem_init_userptr(dev_priv);
if (ret)
return ret;
intel_uc_fetch_firmwares(&dev_priv->gt.uc);
intel_wopcm_init(&dev_priv->wopcm);
/* This is just a security blanket to placate dragons.
* On some systems, we very sporadically observe that the first TLBs
* used by the CS may be stale, despite us poking the TLB reset. If
* we hold the forcewake during initialisation these problems
* just magically go away.
*/
mutex_lock(&dev_priv->drm.struct_mutex);
intel_uncore_forcewake_get(&dev_priv->uncore, FORCEWAKE_ALL);
ret = i915_init_ggtt(dev_priv);
if (ret) {
GEM_BUG_ON(ret == -EIO);
goto err_unlock;
}
ret = i915_gem_init_scratch(dev_priv,
IS_GEN(dev_priv, 2) ? SZ_256K : PAGE_SIZE);
if (ret) {
GEM_BUG_ON(ret == -EIO);
goto err_ggtt;
}
ret = intel_engines_setup(dev_priv);
if (ret) {
GEM_BUG_ON(ret == -EIO);
goto err_unlock;
}
ret = i915_gem_contexts_init(dev_priv);
if (ret) {
GEM_BUG_ON(ret == -EIO);
goto err_scratch;
}
ret = intel_engines_init(dev_priv);
if (ret) {
GEM_BUG_ON(ret == -EIO);
goto err_context;
}
intel_init_gt_powersave(dev_priv);
intel_uc_init(&dev_priv->gt.uc);
ret = i915_gem_init_hw(dev_priv);
if (ret)
goto err_uc_init;
/* Only when the HW is re-initialised, can we replay the requests */
ret = intel_gt_resume(&dev_priv->gt);
if (ret)
goto err_init_hw;
/*
* Despite its name intel_init_clock_gating applies both display
* clock gating workarounds; GT mmio workarounds and the occasional
* GT power context workaround. Worse, sometimes it includes a context
* register workaround which we need to apply before we record the
* default HW state for all contexts.
*
* FIXME: break up the workarounds and apply them at the right time!
*/
intel_init_clock_gating(dev_priv);
ret = intel_engines_verify_workarounds(dev_priv);
if (ret)
goto err_gt;
ret = __intel_engines_record_defaults(dev_priv);
if (ret)
goto err_gt;
ret = i915_inject_load_error(dev_priv, -ENODEV);
if (ret)
goto err_gt;
ret = i915_inject_load_error(dev_priv, -EIO);
if (ret)
goto err_gt;
intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
mutex_unlock(&dev_priv->drm.struct_mutex);
return 0;
/*
* Unwinding is complicated by that we want to handle -EIO to mean
* disable GPU submission but keep KMS alive. We want to mark the
* HW as irrevisibly wedged, but keep enough state around that the
* driver doesn't explode during runtime.
*/
err_gt:
mutex_unlock(&dev_priv->drm.struct_mutex);
intel_gt_set_wedged(&dev_priv->gt);
i915_gem_suspend(dev_priv);
i915_gem_suspend_late(dev_priv);
i915_gem_drain_workqueue(dev_priv);
mutex_lock(&dev_priv->drm.struct_mutex);
err_init_hw:
intel_uc_fini_hw(&dev_priv->gt.uc);
err_uc_init:
if (ret != -EIO) {
intel_uc_fini(&dev_priv->gt.uc);
intel_cleanup_gt_powersave(dev_priv);
intel_engines_cleanup(dev_priv);
}
err_context:
if (ret != -EIO)
i915_gem_contexts_fini(dev_priv);
err_scratch:
i915_gem_fini_scratch(dev_priv);
err_ggtt:
err_unlock:
intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
mutex_unlock(&dev_priv->drm.struct_mutex);
if (ret != -EIO) {
intel_uc_cleanup_firmwares(&dev_priv->gt.uc);
i915_gem_cleanup_userptr(dev_priv);
intel_timelines_fini(dev_priv);
}
if (ret == -EIO) {
mutex_lock(&dev_priv->drm.struct_mutex);
/*
* Allow engines or uC initialisation to fail by marking the GPU
* as wedged. But we only want to do this when the GPU is angry,
* for all other failure, such as an allocation failure, bail.
*/
if (!intel_gt_is_wedged(&dev_priv->gt)) {
i915_probe_error(dev_priv,
"Failed to initialize GPU, declaring it wedged!\n");
intel_gt_set_wedged(&dev_priv->gt);
}
/* Minimal basic recovery for KMS */
ret = i915_ggtt_enable_hw(dev_priv);
i915_gem_restore_gtt_mappings(dev_priv);
i915_gem_restore_fences(dev_priv);
intel_init_clock_gating(dev_priv);
mutex_unlock(&dev_priv->drm.struct_mutex);
}
i915_gem_drain_freed_objects(dev_priv);
return ret;
}
void i915_gem_driver_register(struct drm_i915_private *i915)
{
i915_gem_driver_register__shrinker(i915);
intel_engines_driver_register(i915);
}
void i915_gem_driver_unregister(struct drm_i915_private *i915)
{
i915_gem_driver_unregister__shrinker(i915);
}
void i915_gem_driver_remove(struct drm_i915_private *dev_priv)
{
GEM_BUG_ON(dev_priv->gt.awake);
intel_wakeref_auto_fini(&dev_priv->ggtt.userfault_wakeref);
i915_gem_suspend_late(dev_priv);
intel_disable_gt_powersave(dev_priv);
/* Flush any outstanding unpin_work. */
i915_gem_drain_workqueue(dev_priv);
mutex_lock(&dev_priv->drm.struct_mutex);
intel_uc_fini_hw(&dev_priv->gt.uc);
intel_uc_fini(&dev_priv->gt.uc);
mutex_unlock(&dev_priv->drm.struct_mutex);
i915_gem_drain_freed_objects(dev_priv);
}
void i915_gem_driver_release(struct drm_i915_private *dev_priv)
{
mutex_lock(&dev_priv->drm.struct_mutex);
intel_engines_cleanup(dev_priv);
i915_gem_contexts_fini(dev_priv);
i915_gem_fini_scratch(dev_priv);
mutex_unlock(&dev_priv->drm.struct_mutex);
intel_wa_list_free(&dev_priv->gt_wa_list);
intel_cleanup_gt_powersave(dev_priv);
intel_uc_cleanup_firmwares(&dev_priv->gt.uc);
i915_gem_cleanup_userptr(dev_priv);
intel_timelines_fini(dev_priv);
i915_gem_drain_freed_objects(dev_priv);
WARN_ON(!list_empty(&dev_priv->contexts.list));
}
void i915_gem_init_mmio(struct drm_i915_private *i915)
{
i915_gem_sanitize(i915);
}
static void i915_gem_init__mm(struct drm_i915_private *i915)
{
spin_lock_init(&i915->mm.obj_lock);
init_llist_head(&i915->mm.free_list);
INIT_LIST_HEAD(&i915->mm.purge_list);
INIT_LIST_HEAD(&i915->mm.shrink_list);
i915_gem_init__objects(i915);
}
int i915_gem_init_early(struct drm_i915_private *dev_priv)
{
int err;
i915_gem_init__mm(dev_priv);
i915_gem_init__pm(dev_priv);
spin_lock_init(&dev_priv->fb_tracking.lock);
err = i915_gemfs_init(dev_priv);
if (err)
DRM_NOTE("Unable to create a private tmpfs mount, hugepage support will be disabled(%d).\n", err);
return 0;
}
void i915_gem_cleanup_early(struct drm_i915_private *dev_priv)
{
i915_gem_drain_freed_objects(dev_priv);
GEM_BUG_ON(!llist_empty(&dev_priv->mm.free_list));
GEM_BUG_ON(atomic_read(&dev_priv->mm.free_count));
WARN_ON(dev_priv->mm.shrink_count);
i915_gemfs_fini(dev_priv);
}
int i915_gem_freeze(struct drm_i915_private *dev_priv)
{
/* Discard all purgeable objects, let userspace recover those as
* required after resuming.
*/
i915_gem_shrink_all(dev_priv);
return 0;
}
int i915_gem_freeze_late(struct drm_i915_private *i915)
{
struct drm_i915_gem_object *obj;
intel_wakeref_t wakeref;
/*
* Called just before we write the hibernation image.
*
* We need to update the domain tracking to reflect that the CPU
* will be accessing all the pages to create and restore from the
* hibernation, and so upon restoration those pages will be in the
* CPU domain.
*
* To make sure the hibernation image contains the latest state,
* we update that state just before writing out the image.
*
* To try and reduce the hibernation image, we manually shrink
* the objects as well, see i915_gem_freeze()
*/
wakeref = intel_runtime_pm_get(&i915->runtime_pm);
i915_gem_shrink(i915, -1UL, NULL, ~0);
i915_gem_drain_freed_objects(i915);
list_for_each_entry(obj, &i915->mm.shrink_list, mm.link) {
i915_gem_object_lock(obj);
WARN_ON(i915_gem_object_set_to_cpu_domain(obj, true));
i915_gem_object_unlock(obj);
}
intel_runtime_pm_put(&i915->runtime_pm, wakeref);
return 0;
}
void i915_gem_release(struct drm_device *dev, struct drm_file *file)
{
struct drm_i915_file_private *file_priv = file->driver_priv;
struct i915_request *request;
/* Clean up our request list when the client is going away, so that
* later retire_requests won't dereference our soon-to-be-gone
* file_priv.
*/
spin_lock(&file_priv->mm.lock);
list_for_each_entry(request, &file_priv->mm.request_list, client_link)
request->file_priv = NULL;
spin_unlock(&file_priv->mm.lock);
}
int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file)
{
struct drm_i915_file_private *file_priv;
int ret;
DRM_DEBUG("\n");
file_priv = kzalloc(sizeof(*file_priv), GFP_KERNEL);
if (!file_priv)
return -ENOMEM;
file->driver_priv = file_priv;
file_priv->dev_priv = i915;
file_priv->file = file;
spin_lock_init(&file_priv->mm.lock);
INIT_LIST_HEAD(&file_priv->mm.request_list);
file_priv->bsd_engine = -1;
file_priv->hang_timestamp = jiffies;
ret = i915_gem_context_open(i915, file);
if (ret)
kfree(file_priv);
return ret;
}
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
#include "selftests/mock_gem_device.c"
#include "selftests/i915_gem.c"
#endif
|