summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/xe/xe_bo.c
blob: 4d3b80ec906d0a6f44793df496ef776a90d84596 (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
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
// SPDX-License-Identifier: MIT
/*
 * Copyright © 2021 Intel Corporation
 */

#include "xe_bo.h"

#include <linux/dma-buf.h>

#include <drm/drm_drv.h>
#include <drm/drm_gem_ttm_helper.h>
#include <drm/drm_managed.h>
#include <drm/ttm/ttm_device.h>
#include <drm/ttm/ttm_placement.h>
#include <drm/ttm/ttm_tt.h>
#include <drm/xe_drm.h>

#include "xe_device.h"
#include "xe_dma_buf.h"
#include "xe_drm_client.h"
#include "xe_ggtt.h"
#include "xe_gt.h"
#include "xe_map.h"
#include "xe_migrate.h"
#include "xe_preempt_fence.h"
#include "xe_res_cursor.h"
#include "xe_trace.h"
#include "xe_ttm_stolen_mgr.h"
#include "xe_vm.h"

const char *const xe_mem_type_to_name[TTM_NUM_MEM_TYPES]  = {
	[XE_PL_SYSTEM] = "system",
	[XE_PL_TT] = "gtt",
	[XE_PL_VRAM0] = "vram0",
	[XE_PL_VRAM1] = "vram1",
	[XE_PL_STOLEN] = "stolen"
};

static const struct ttm_place sys_placement_flags = {
	.fpfn = 0,
	.lpfn = 0,
	.mem_type = XE_PL_SYSTEM,
	.flags = 0,
};

static struct ttm_placement sys_placement = {
	.num_placement = 1,
	.placement = &sys_placement_flags,
	.num_busy_placement = 1,
	.busy_placement = &sys_placement_flags,
};

static const struct ttm_place tt_placement_flags = {
	.fpfn = 0,
	.lpfn = 0,
	.mem_type = XE_PL_TT,
	.flags = 0,
};

static struct ttm_placement tt_placement = {
	.num_placement = 1,
	.placement = &tt_placement_flags,
	.num_busy_placement = 1,
	.busy_placement = &sys_placement_flags,
};

bool mem_type_is_vram(u32 mem_type)
{
	return mem_type >= XE_PL_VRAM0 && mem_type != XE_PL_STOLEN;
}

static bool resource_is_stolen_vram(struct xe_device *xe, struct ttm_resource *res)
{
	return res->mem_type == XE_PL_STOLEN && IS_DGFX(xe);
}

static bool resource_is_vram(struct ttm_resource *res)
{
	return mem_type_is_vram(res->mem_type);
}

bool xe_bo_is_vram(struct xe_bo *bo)
{
	return resource_is_vram(bo->ttm.resource) ||
		resource_is_stolen_vram(xe_bo_device(bo), bo->ttm.resource);
}

bool xe_bo_is_stolen(struct xe_bo *bo)
{
	return bo->ttm.resource->mem_type == XE_PL_STOLEN;
}

/**
 * xe_bo_is_stolen_devmem - check if BO is of stolen type accessed via PCI BAR
 * @bo: The BO
 *
 * The stolen memory is accessed through the PCI BAR for both DGFX and some
 * integrated platforms that have a dedicated bit in the PTE for devmem (DM).
 *
 * Returns: true if it's stolen memory accessed via PCI BAR, false otherwise.
 */
bool xe_bo_is_stolen_devmem(struct xe_bo *bo)
{
	return xe_bo_is_stolen(bo) &&
		GRAPHICS_VERx100(xe_bo_device(bo)) >= 1270;
}

static bool xe_bo_is_user(struct xe_bo *bo)
{
	return bo->flags & XE_BO_CREATE_USER_BIT;
}

static struct xe_migrate *
mem_type_to_migrate(struct xe_device *xe, u32 mem_type)
{
	struct xe_tile *tile;

	xe_assert(xe, mem_type == XE_PL_STOLEN || mem_type_is_vram(mem_type));
	tile = &xe->tiles[mem_type == XE_PL_STOLEN ? 0 : (mem_type - XE_PL_VRAM0)];
	return tile->migrate;
}

static struct xe_mem_region *res_to_mem_region(struct ttm_resource *res)
{
	struct xe_device *xe = ttm_to_xe_device(res->bo->bdev);
	struct ttm_resource_manager *mgr;

	xe_assert(xe, resource_is_vram(res));
	mgr = ttm_manager_type(&xe->ttm, res->mem_type);
	return to_xe_ttm_vram_mgr(mgr)->vram;
}

static void try_add_system(struct xe_device *xe, struct xe_bo *bo,
			   u32 bo_flags, u32 *c)
{
	if (bo_flags & XE_BO_CREATE_SYSTEM_BIT) {
		xe_assert(xe, *c < ARRAY_SIZE(bo->placements));

		bo->placements[*c] = (struct ttm_place) {
			.mem_type = XE_PL_TT,
		};
		*c += 1;

		if (bo->props.preferred_mem_type == XE_BO_PROPS_INVALID)
			bo->props.preferred_mem_type = XE_PL_TT;
	}
}

static void add_vram(struct xe_device *xe, struct xe_bo *bo,
		     struct ttm_place *places, u32 bo_flags, u32 mem_type, u32 *c)
{
	struct ttm_place place = { .mem_type = mem_type };
	struct xe_mem_region *vram;
	u64 io_size;

	xe_assert(xe, *c < ARRAY_SIZE(bo->placements));

	vram = to_xe_ttm_vram_mgr(ttm_manager_type(&xe->ttm, mem_type))->vram;
	xe_assert(xe, vram && vram->usable_size);
	io_size = vram->io_size;

	/*
	 * For eviction / restore on suspend / resume objects
	 * pinned in VRAM must be contiguous
	 */
	if (bo_flags & (XE_BO_CREATE_PINNED_BIT |
			XE_BO_CREATE_GGTT_BIT))
		place.flags |= TTM_PL_FLAG_CONTIGUOUS;

	if (io_size < vram->usable_size) {
		if (bo_flags & XE_BO_NEEDS_CPU_ACCESS) {
			place.fpfn = 0;
			place.lpfn = io_size >> PAGE_SHIFT;
		} else {
			place.flags |= TTM_PL_FLAG_TOPDOWN;
		}
	}
	places[*c] = place;
	*c += 1;

	if (bo->props.preferred_mem_type == XE_BO_PROPS_INVALID)
		bo->props.preferred_mem_type = mem_type;
}

static void try_add_vram(struct xe_device *xe, struct xe_bo *bo,
			 u32 bo_flags, u32 *c)
{
	if (bo->props.preferred_gt == XE_GT1) {
		if (bo_flags & XE_BO_CREATE_VRAM1_BIT)
			add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM1, c);
		if (bo_flags & XE_BO_CREATE_VRAM0_BIT)
			add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM0, c);
	} else {
		if (bo_flags & XE_BO_CREATE_VRAM0_BIT)
			add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM0, c);
		if (bo_flags & XE_BO_CREATE_VRAM1_BIT)
			add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM1, c);
	}
}

static void try_add_stolen(struct xe_device *xe, struct xe_bo *bo,
			   u32 bo_flags, u32 *c)
{
	if (bo_flags & XE_BO_CREATE_STOLEN_BIT) {
		xe_assert(xe, *c < ARRAY_SIZE(bo->placements));

		bo->placements[*c] = (struct ttm_place) {
			.mem_type = XE_PL_STOLEN,
			.flags = bo_flags & (XE_BO_CREATE_PINNED_BIT |
					     XE_BO_CREATE_GGTT_BIT) ?
				TTM_PL_FLAG_CONTIGUOUS : 0,
		};
		*c += 1;
	}
}

static int __xe_bo_placement_for_flags(struct xe_device *xe, struct xe_bo *bo,
				       u32 bo_flags)
{
	u32 c = 0;

	bo->props.preferred_mem_type = XE_BO_PROPS_INVALID;

	/* The order of placements should indicate preferred location */

	if (bo->props.preferred_mem_class == DRM_XE_MEM_REGION_CLASS_SYSMEM) {
		try_add_system(xe, bo, bo_flags, &c);
		try_add_vram(xe, bo, bo_flags, &c);
	} else {
		try_add_vram(xe, bo, bo_flags, &c);
		try_add_system(xe, bo, bo_flags, &c);
	}
	try_add_stolen(xe, bo, bo_flags, &c);

	if (!c)
		return -EINVAL;

	bo->placement = (struct ttm_placement) {
		.num_placement = c,
		.placement = bo->placements,
		.num_busy_placement = c,
		.busy_placement = bo->placements,
	};

	return 0;
}

int xe_bo_placement_for_flags(struct xe_device *xe, struct xe_bo *bo,
			      u32 bo_flags)
{
	xe_bo_assert_held(bo);
	return __xe_bo_placement_for_flags(xe, bo, bo_flags);
}

static void xe_evict_flags(struct ttm_buffer_object *tbo,
			   struct ttm_placement *placement)
{
	if (!xe_bo_is_xe_bo(tbo)) {
		/* Don't handle scatter gather BOs */
		if (tbo->type == ttm_bo_type_sg) {
			placement->num_placement = 0;
			placement->num_busy_placement = 0;
			return;
		}

		*placement = sys_placement;
		return;
	}

	/*
	 * For xe, sg bos that are evicted to system just triggers a
	 * rebind of the sg list upon subsequent validation to XE_PL_TT.
	 */
	switch (tbo->resource->mem_type) {
	case XE_PL_VRAM0:
	case XE_PL_VRAM1:
	case XE_PL_STOLEN:
		*placement = tt_placement;
		break;
	case XE_PL_TT:
	default:
		*placement = sys_placement;
		break;
	}
}

struct xe_ttm_tt {
	struct ttm_tt ttm;
	struct device *dev;
	struct sg_table sgt;
	struct sg_table *sg;
};

static int xe_tt_map_sg(struct ttm_tt *tt)
{
	struct xe_ttm_tt *xe_tt = container_of(tt, struct xe_ttm_tt, ttm);
	unsigned long num_pages = tt->num_pages;
	int ret;

	XE_WARN_ON(tt->page_flags & TTM_TT_FLAG_EXTERNAL);

	if (xe_tt->sg)
		return 0;

	ret = sg_alloc_table_from_pages_segment(&xe_tt->sgt, tt->pages,
						num_pages, 0,
						(u64)num_pages << PAGE_SHIFT,
						xe_sg_segment_size(xe_tt->dev),
						GFP_KERNEL);
	if (ret)
		return ret;

	xe_tt->sg = &xe_tt->sgt;
	ret = dma_map_sgtable(xe_tt->dev, xe_tt->sg, DMA_BIDIRECTIONAL,
			      DMA_ATTR_SKIP_CPU_SYNC);
	if (ret) {
		sg_free_table(xe_tt->sg);
		xe_tt->sg = NULL;
		return ret;
	}

	return 0;
}

struct sg_table *xe_bo_sg(struct xe_bo *bo)
{
	struct ttm_tt *tt = bo->ttm.ttm;
	struct xe_ttm_tt *xe_tt = container_of(tt, struct xe_ttm_tt, ttm);

	return xe_tt->sg;
}

static struct ttm_tt *xe_ttm_tt_create(struct ttm_buffer_object *ttm_bo,
				       u32 page_flags)
{
	struct xe_bo *bo = ttm_to_xe_bo(ttm_bo);
	struct xe_device *xe = xe_bo_device(bo);
	struct xe_ttm_tt *tt;
	unsigned long extra_pages;
	enum ttm_caching caching;
	int err;

	tt = kzalloc(sizeof(*tt), GFP_KERNEL);
	if (!tt)
		return NULL;

	tt->dev = xe->drm.dev;

	extra_pages = 0;
	if (xe_bo_needs_ccs_pages(bo))
		extra_pages = DIV_ROUND_UP(xe_device_ccs_bytes(xe, bo->size),
					   PAGE_SIZE);

	switch (bo->cpu_caching) {
	case DRM_XE_GEM_CPU_CACHING_WC:
		caching = ttm_write_combined;
		break;
	default:
		caching = ttm_cached;
		break;
	}

	WARN_ON((bo->flags & XE_BO_CREATE_USER_BIT) && !bo->cpu_caching);

	/*
	 * Display scanout is always non-coherent with the CPU cache.
	 *
	 * For Xe_LPG and beyond, PPGTT PTE lookups are also non-coherent and
	 * require a CPU:WC mapping.
	 */
	if ((!bo->cpu_caching && bo->flags & XE_BO_SCANOUT_BIT) ||
	    (xe->info.graphics_verx100 >= 1270 && bo->flags & XE_BO_PAGETABLE))
		caching = ttm_write_combined;

	err = ttm_tt_init(&tt->ttm, &bo->ttm, page_flags, caching, extra_pages);
	if (err) {
		kfree(tt);
		return NULL;
	}

	return &tt->ttm;
}

static int xe_ttm_tt_populate(struct ttm_device *ttm_dev, struct ttm_tt *tt,
			      struct ttm_operation_ctx *ctx)
{
	int err;

	/*
	 * dma-bufs are not populated with pages, and the dma-
	 * addresses are set up when moved to XE_PL_TT.
	 */
	if (tt->page_flags & TTM_TT_FLAG_EXTERNAL)
		return 0;

	err = ttm_pool_alloc(&ttm_dev->pool, tt, ctx);
	if (err)
		return err;

	/* A follow up may move this xe_bo_move when BO is moved to XE_PL_TT */
	err = xe_tt_map_sg(tt);
	if (err)
		ttm_pool_free(&ttm_dev->pool, tt);

	return err;
}

static void xe_ttm_tt_unpopulate(struct ttm_device *ttm_dev, struct ttm_tt *tt)
{
	struct xe_ttm_tt *xe_tt = container_of(tt, struct xe_ttm_tt, ttm);

	if (tt->page_flags & TTM_TT_FLAG_EXTERNAL)
		return;

	if (xe_tt->sg) {
		dma_unmap_sgtable(xe_tt->dev, xe_tt->sg,
				  DMA_BIDIRECTIONAL, 0);
		sg_free_table(xe_tt->sg);
		xe_tt->sg = NULL;
	}

	return ttm_pool_free(&ttm_dev->pool, tt);
}

static void xe_ttm_tt_destroy(struct ttm_device *ttm_dev, struct ttm_tt *tt)
{
	ttm_tt_fini(tt);
	kfree(tt);
}

static int xe_ttm_io_mem_reserve(struct ttm_device *bdev,
				 struct ttm_resource *mem)
{
	struct xe_device *xe = ttm_to_xe_device(bdev);

	switch (mem->mem_type) {
	case XE_PL_SYSTEM:
	case XE_PL_TT:
		return 0;
	case XE_PL_VRAM0:
	case XE_PL_VRAM1: {
		struct xe_ttm_vram_mgr_resource *vres =
			to_xe_ttm_vram_mgr_resource(mem);
		struct xe_mem_region *vram = res_to_mem_region(mem);

		if (vres->used_visible_size < mem->size)
			return -EINVAL;

		mem->bus.offset = mem->start << PAGE_SHIFT;

		if (vram->mapping &&
		    mem->placement & TTM_PL_FLAG_CONTIGUOUS)
			mem->bus.addr = (u8 __force *)vram->mapping +
				mem->bus.offset;

		mem->bus.offset += vram->io_start;
		mem->bus.is_iomem = true;

#if  !defined(CONFIG_X86)
		mem->bus.caching = ttm_write_combined;
#endif
		return 0;
	} case XE_PL_STOLEN:
		return xe_ttm_stolen_io_mem_reserve(xe, mem);
	default:
		return -EINVAL;
	}
}

static int xe_bo_trigger_rebind(struct xe_device *xe, struct xe_bo *bo,
				const struct ttm_operation_ctx *ctx)
{
	struct dma_resv_iter cursor;
	struct dma_fence *fence;
	struct drm_gem_object *obj = &bo->ttm.base;
	struct drm_gpuvm_bo *vm_bo;
	bool idle = false;
	int ret = 0;

	dma_resv_assert_held(bo->ttm.base.resv);

	if (!list_empty(&bo->ttm.base.gpuva.list)) {
		dma_resv_iter_begin(&cursor, bo->ttm.base.resv,
				    DMA_RESV_USAGE_BOOKKEEP);
		dma_resv_for_each_fence_unlocked(&cursor, fence)
			dma_fence_enable_sw_signaling(fence);
		dma_resv_iter_end(&cursor);
	}

	drm_gem_for_each_gpuvm_bo(vm_bo, obj) {
		struct xe_vm *vm = gpuvm_to_vm(vm_bo->vm);
		struct drm_gpuva *gpuva;

		if (!xe_vm_in_fault_mode(vm)) {
			drm_gpuvm_bo_evict(vm_bo, true);
			continue;
		}

		if (!idle) {
			long timeout;

			if (ctx->no_wait_gpu &&
			    !dma_resv_test_signaled(bo->ttm.base.resv,
						    DMA_RESV_USAGE_BOOKKEEP))
				return -EBUSY;

			timeout = dma_resv_wait_timeout(bo->ttm.base.resv,
							DMA_RESV_USAGE_BOOKKEEP,
							ctx->interruptible,
							MAX_SCHEDULE_TIMEOUT);
			if (!timeout)
				return -ETIME;
			if (timeout < 0)
				return timeout;

			idle = true;
		}

		drm_gpuvm_bo_for_each_va(gpuva, vm_bo) {
			struct xe_vma *vma = gpuva_to_vma(gpuva);

			trace_xe_vma_evict(vma);
			ret = xe_vm_invalidate_vma(vma);
			if (XE_WARN_ON(ret))
				return ret;
		}
	}

	return ret;
}

/*
 * The dma-buf map_attachment() / unmap_attachment() is hooked up here.
 * Note that unmapping the attachment is deferred to the next
 * map_attachment time, or to bo destroy (after idling) whichever comes first.
 * This is to avoid syncing before unmap_attachment(), assuming that the
 * caller relies on idling the reservation object before moving the
 * backing store out. Should that assumption not hold, then we will be able
 * to unconditionally call unmap_attachment() when moving out to system.
 */
static int xe_bo_move_dmabuf(struct ttm_buffer_object *ttm_bo,
			     struct ttm_resource *new_res)
{
	struct dma_buf_attachment *attach = ttm_bo->base.import_attach;
	struct xe_ttm_tt *xe_tt = container_of(ttm_bo->ttm, struct xe_ttm_tt,
					       ttm);
	struct xe_device *xe = ttm_to_xe_device(ttm_bo->bdev);
	struct sg_table *sg;

	xe_assert(xe, attach);
	xe_assert(xe, ttm_bo->ttm);

	if (new_res->mem_type == XE_PL_SYSTEM)
		goto out;

	if (ttm_bo->sg) {
		dma_buf_unmap_attachment(attach, ttm_bo->sg, DMA_BIDIRECTIONAL);
		ttm_bo->sg = NULL;
	}

	sg = dma_buf_map_attachment(attach, DMA_BIDIRECTIONAL);
	if (IS_ERR(sg))
		return PTR_ERR(sg);

	ttm_bo->sg = sg;
	xe_tt->sg = sg;

out:
	ttm_bo_move_null(ttm_bo, new_res);

	return 0;
}

/**
 * xe_bo_move_notify - Notify subsystems of a pending move
 * @bo: The buffer object
 * @ctx: The struct ttm_operation_ctx controlling locking and waits.
 *
 * This function notifies subsystems of an upcoming buffer move.
 * Upon receiving such a notification, subsystems should schedule
 * halting access to the underlying pages and optionally add a fence
 * to the buffer object's dma_resv object, that signals when access is
 * stopped. The caller will wait on all dma_resv fences before
 * starting the move.
 *
 * A subsystem may commence access to the object after obtaining
 * bindings to the new backing memory under the object lock.
 *
 * Return: 0 on success, -EINTR or -ERESTARTSYS if interrupted in fault mode,
 * negative error code on error.
 */
static int xe_bo_move_notify(struct xe_bo *bo,
			     const struct ttm_operation_ctx *ctx)
{
	struct ttm_buffer_object *ttm_bo = &bo->ttm;
	struct xe_device *xe = ttm_to_xe_device(ttm_bo->bdev);
	int ret;

	/*
	 * If this starts to call into many components, consider
	 * using a notification chain here.
	 */

	if (xe_bo_is_pinned(bo))
		return -EINVAL;

	xe_bo_vunmap(bo);
	ret = xe_bo_trigger_rebind(xe, bo, ctx);
	if (ret)
		return ret;

	/* Don't call move_notify() for imported dma-bufs. */
	if (ttm_bo->base.dma_buf && !ttm_bo->base.import_attach)
		dma_buf_move_notify(ttm_bo->base.dma_buf);

	return 0;
}

static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
		      struct ttm_operation_ctx *ctx,
		      struct ttm_resource *new_mem,
		      struct ttm_place *hop)
{
	struct xe_device *xe = ttm_to_xe_device(ttm_bo->bdev);
	struct xe_bo *bo = ttm_to_xe_bo(ttm_bo);
	struct ttm_resource *old_mem = ttm_bo->resource;
	u32 old_mem_type = old_mem ? old_mem->mem_type : XE_PL_SYSTEM;
	struct ttm_tt *ttm = ttm_bo->ttm;
	struct xe_migrate *migrate = NULL;
	struct dma_fence *fence;
	bool move_lacks_source;
	bool tt_has_data;
	bool needs_clear;
	bool handle_system_ccs = (!IS_DGFX(xe) && xe_bo_needs_ccs_pages(bo) &&
				  ttm && ttm_tt_is_populated(ttm)) ? true : false;
	int ret = 0;
	/* Bo creation path, moving to system or TT. */
	if ((!old_mem && ttm) && !handle_system_ccs) {
		ttm_bo_move_null(ttm_bo, new_mem);
		return 0;
	}

	if (ttm_bo->type == ttm_bo_type_sg) {
		ret = xe_bo_move_notify(bo, ctx);
		if (!ret)
			ret = xe_bo_move_dmabuf(ttm_bo, new_mem);
		goto out;
	}

	tt_has_data = ttm && (ttm_tt_is_populated(ttm) ||
			      (ttm->page_flags & TTM_TT_FLAG_SWAPPED));

	move_lacks_source = handle_system_ccs ? (!bo->ccs_cleared)  :
						(!mem_type_is_vram(old_mem_type) && !tt_has_data);

	needs_clear = (ttm && ttm->page_flags & TTM_TT_FLAG_ZERO_ALLOC) ||
		(!ttm && ttm_bo->type == ttm_bo_type_device);

	if ((move_lacks_source && !needs_clear)) {
		ttm_bo_move_null(ttm_bo, new_mem);
		goto out;
	}

	if (old_mem_type == XE_PL_SYSTEM && new_mem->mem_type == XE_PL_TT && !handle_system_ccs) {
		ttm_bo_move_null(ttm_bo, new_mem);
		goto out;
	}

	/*
	 * Failed multi-hop where the old_mem is still marked as
	 * TTM_PL_FLAG_TEMPORARY, should just be a dummy move.
	 */
	if (old_mem_type == XE_PL_TT &&
	    new_mem->mem_type == XE_PL_TT) {
		ttm_bo_move_null(ttm_bo, new_mem);
		goto out;
	}

	if (!move_lacks_source && !xe_bo_is_pinned(bo)) {
		ret = xe_bo_move_notify(bo, ctx);
		if (ret)
			goto out;
	}

	if (old_mem_type == XE_PL_TT &&
	    new_mem->mem_type == XE_PL_SYSTEM) {
		long timeout = dma_resv_wait_timeout(ttm_bo->base.resv,
						     DMA_RESV_USAGE_BOOKKEEP,
						     true,
						     MAX_SCHEDULE_TIMEOUT);
		if (timeout < 0) {
			ret = timeout;
			goto out;
		}

		if (!handle_system_ccs) {
			ttm_bo_move_null(ttm_bo, new_mem);
			goto out;
		}
	}

	if (!move_lacks_source &&
	    ((old_mem_type == XE_PL_SYSTEM && resource_is_vram(new_mem)) ||
	     (mem_type_is_vram(old_mem_type) &&
	      new_mem->mem_type == XE_PL_SYSTEM))) {
		hop->fpfn = 0;
		hop->lpfn = 0;
		hop->mem_type = XE_PL_TT;
		hop->flags = TTM_PL_FLAG_TEMPORARY;
		ret = -EMULTIHOP;
		goto out;
	}

	if (bo->tile)
		migrate = bo->tile->migrate;
	else if (resource_is_vram(new_mem))
		migrate = mem_type_to_migrate(xe, new_mem->mem_type);
	else if (mem_type_is_vram(old_mem_type))
		migrate = mem_type_to_migrate(xe, old_mem_type);
	else
		migrate = xe->tiles[0].migrate;

	xe_assert(xe, migrate);
	trace_xe_bo_move(bo, new_mem->mem_type, old_mem_type, move_lacks_source);
	xe_device_mem_access_get(xe);

	if (xe_bo_is_pinned(bo) && !xe_bo_is_user(bo)) {
		/*
		 * Kernel memory that is pinned should only be moved on suspend
		 * / resume, some of the pinned memory is required for the
		 * device to resume / use the GPU to move other evicted memory
		 * (user memory) around. This likely could be optimized a bit
		 * futher where we find the minimum set of pinned memory
		 * required for resume but for simplity doing a memcpy for all
		 * pinned memory.
		 */
		ret = xe_bo_vmap(bo);
		if (!ret) {
			ret = ttm_bo_move_memcpy(ttm_bo, ctx, new_mem);

			/* Create a new VMAP once kernel BO back in VRAM */
			if (!ret && resource_is_vram(new_mem)) {
				struct xe_mem_region *vram = res_to_mem_region(new_mem);
				void __iomem *new_addr = vram->mapping +
					(new_mem->start << PAGE_SHIFT);

				if (XE_WARN_ON(new_mem->start == XE_BO_INVALID_OFFSET)) {
					ret = -EINVAL;
					xe_device_mem_access_put(xe);
					goto out;
				}

				xe_assert(xe, new_mem->start ==
					  bo->placements->fpfn);

				iosys_map_set_vaddr_iomem(&bo->vmap, new_addr);
			}
		}
	} else {
		if (move_lacks_source)
			fence = xe_migrate_clear(migrate, bo, new_mem);
		else
			fence = xe_migrate_copy(migrate, bo, bo, old_mem,
						new_mem, handle_system_ccs);
		if (IS_ERR(fence)) {
			ret = PTR_ERR(fence);
			xe_device_mem_access_put(xe);
			goto out;
		}
		if (!move_lacks_source) {
			ret = ttm_bo_move_accel_cleanup(ttm_bo, fence, evict,
							true, new_mem);
			if (ret) {
				dma_fence_wait(fence, false);
				ttm_bo_move_null(ttm_bo, new_mem);
				ret = 0;
			}
		} else {
			/*
			 * ttm_bo_move_accel_cleanup() may blow up if
			 * bo->resource == NULL, so just attach the
			 * fence and set the new resource.
			 */
			dma_resv_add_fence(ttm_bo->base.resv, fence,
					   DMA_RESV_USAGE_KERNEL);
			ttm_bo_move_null(ttm_bo, new_mem);
		}

		dma_fence_put(fence);
	}

	xe_device_mem_access_put(xe);

out:
	return ret;

}

/**
 * xe_bo_evict_pinned() - Evict a pinned VRAM object to system memory
 * @bo: The buffer object to move.
 *
 * On successful completion, the object memory will be moved to sytem memory.
 * This function blocks until the object has been fully moved.
 *
 * This is needed to for special handling of pinned VRAM object during
 * suspend-resume.
 *
 * Return: 0 on success. Negative error code on failure.
 */
int xe_bo_evict_pinned(struct xe_bo *bo)
{
	struct ttm_place place = {
		.mem_type = XE_PL_TT,
	};
	struct ttm_placement placement = {
		.placement = &place,
		.num_placement = 1,
	};
	struct ttm_operation_ctx ctx = {
		.interruptible = false,
	};
	struct ttm_resource *new_mem;
	int ret;

	xe_bo_assert_held(bo);

	if (WARN_ON(!bo->ttm.resource))
		return -EINVAL;

	if (WARN_ON(!xe_bo_is_pinned(bo)))
		return -EINVAL;

	if (WARN_ON(!xe_bo_is_vram(bo)))
		return -EINVAL;

	ret = ttm_bo_mem_space(&bo->ttm, &placement, &new_mem, &ctx);
	if (ret)
		return ret;

	if (!bo->ttm.ttm) {
		bo->ttm.ttm = xe_ttm_tt_create(&bo->ttm, 0);
		if (!bo->ttm.ttm) {
			ret = -ENOMEM;
			goto err_res_free;
		}
	}

	ret = ttm_tt_populate(bo->ttm.bdev, bo->ttm.ttm, &ctx);
	if (ret)
		goto err_res_free;

	ret = dma_resv_reserve_fences(bo->ttm.base.resv, 1);
	if (ret)
		goto err_res_free;

	ret = xe_bo_move(&bo->ttm, false, &ctx, new_mem, NULL);
	if (ret)
		goto err_res_free;

	dma_resv_wait_timeout(bo->ttm.base.resv, DMA_RESV_USAGE_KERNEL,
			      false, MAX_SCHEDULE_TIMEOUT);

	return 0;

err_res_free:
	ttm_resource_free(&bo->ttm, &new_mem);
	return ret;
}

/**
 * xe_bo_restore_pinned() - Restore a pinned VRAM object
 * @bo: The buffer object to move.
 *
 * On successful completion, the object memory will be moved back to VRAM.
 * This function blocks until the object has been fully moved.
 *
 * This is needed to for special handling of pinned VRAM object during
 * suspend-resume.
 *
 * Return: 0 on success. Negative error code on failure.
 */
int xe_bo_restore_pinned(struct xe_bo *bo)
{
	struct ttm_operation_ctx ctx = {
		.interruptible = false,
	};
	struct ttm_resource *new_mem;
	int ret;

	xe_bo_assert_held(bo);

	if (WARN_ON(!bo->ttm.resource))
		return -EINVAL;

	if (WARN_ON(!xe_bo_is_pinned(bo)))
		return -EINVAL;

	if (WARN_ON(xe_bo_is_vram(bo) || !bo->ttm.ttm))
		return -EINVAL;

	ret = ttm_bo_mem_space(&bo->ttm, &bo->placement, &new_mem, &ctx);
	if (ret)
		return ret;

	ret = ttm_tt_populate(bo->ttm.bdev, bo->ttm.ttm, &ctx);
	if (ret)
		goto err_res_free;

	ret = dma_resv_reserve_fences(bo->ttm.base.resv, 1);
	if (ret)
		goto err_res_free;

	ret = xe_bo_move(&bo->ttm, false, &ctx, new_mem, NULL);
	if (ret)
		goto err_res_free;

	dma_resv_wait_timeout(bo->ttm.base.resv, DMA_RESV_USAGE_KERNEL,
			      false, MAX_SCHEDULE_TIMEOUT);

	return 0;

err_res_free:
	ttm_resource_free(&bo->ttm, &new_mem);
	return ret;
}

static unsigned long xe_ttm_io_mem_pfn(struct ttm_buffer_object *ttm_bo,
				       unsigned long page_offset)
{
	struct xe_bo *bo = ttm_to_xe_bo(ttm_bo);
	struct xe_res_cursor cursor;
	struct xe_mem_region *vram;

	if (ttm_bo->resource->mem_type == XE_PL_STOLEN)
		return xe_ttm_stolen_io_offset(bo, page_offset << PAGE_SHIFT) >> PAGE_SHIFT;

	vram = res_to_mem_region(ttm_bo->resource);
	xe_res_first(ttm_bo->resource, (u64)page_offset << PAGE_SHIFT, 0, &cursor);
	return (vram->io_start + cursor.start) >> PAGE_SHIFT;
}

static void __xe_bo_vunmap(struct xe_bo *bo);

/*
 * TODO: Move this function to TTM so we don't rely on how TTM does its
 * locking, thereby abusing TTM internals.
 */
static bool xe_ttm_bo_lock_in_destructor(struct ttm_buffer_object *ttm_bo)
{
	struct xe_device *xe = ttm_to_xe_device(ttm_bo->bdev);
	bool locked;

	xe_assert(xe, !kref_read(&ttm_bo->kref));

	/*
	 * We can typically only race with TTM trylocking under the
	 * lru_lock, which will immediately be unlocked again since
	 * the ttm_bo refcount is zero at this point. So trylocking *should*
	 * always succeed here, as long as we hold the lru lock.
	 */
	spin_lock(&ttm_bo->bdev->lru_lock);
	locked = dma_resv_trylock(ttm_bo->base.resv);
	spin_unlock(&ttm_bo->bdev->lru_lock);
	xe_assert(xe, locked);

	return locked;
}

static void xe_ttm_bo_release_notify(struct ttm_buffer_object *ttm_bo)
{
	struct dma_resv_iter cursor;
	struct dma_fence *fence;
	struct dma_fence *replacement = NULL;
	struct xe_bo *bo;

	if (!xe_bo_is_xe_bo(ttm_bo))
		return;

	bo = ttm_to_xe_bo(ttm_bo);
	xe_assert(xe_bo_device(bo), !(bo->created && kref_read(&ttm_bo->base.refcount)));

	/*
	 * Corner case where TTM fails to allocate memory and this BOs resv
	 * still points the VMs resv
	 */
	if (ttm_bo->base.resv != &ttm_bo->base._resv)
		return;

	if (!xe_ttm_bo_lock_in_destructor(ttm_bo))
		return;

	/*
	 * Scrub the preempt fences if any. The unbind fence is already
	 * attached to the resv.
	 * TODO: Don't do this for external bos once we scrub them after
	 * unbind.
	 */
	dma_resv_for_each_fence(&cursor, ttm_bo->base.resv,
				DMA_RESV_USAGE_BOOKKEEP, fence) {
		if (xe_fence_is_xe_preempt(fence) &&
		    !dma_fence_is_signaled(fence)) {
			if (!replacement)
				replacement = dma_fence_get_stub();

			dma_resv_replace_fences(ttm_bo->base.resv,
						fence->context,
						replacement,
						DMA_RESV_USAGE_BOOKKEEP);
		}
	}
	dma_fence_put(replacement);

	dma_resv_unlock(ttm_bo->base.resv);
}

static void xe_ttm_bo_delete_mem_notify(struct ttm_buffer_object *ttm_bo)
{
	if (!xe_bo_is_xe_bo(ttm_bo))
		return;

	/*
	 * Object is idle and about to be destroyed. Release the
	 * dma-buf attachment.
	 */
	if (ttm_bo->type == ttm_bo_type_sg && ttm_bo->sg) {
		struct xe_ttm_tt *xe_tt = container_of(ttm_bo->ttm,
						       struct xe_ttm_tt, ttm);

		dma_buf_unmap_attachment(ttm_bo->base.import_attach, ttm_bo->sg,
					 DMA_BIDIRECTIONAL);
		ttm_bo->sg = NULL;
		xe_tt->sg = NULL;
	}
}

struct ttm_device_funcs xe_ttm_funcs = {
	.ttm_tt_create = xe_ttm_tt_create,
	.ttm_tt_populate = xe_ttm_tt_populate,
	.ttm_tt_unpopulate = xe_ttm_tt_unpopulate,
	.ttm_tt_destroy = xe_ttm_tt_destroy,
	.evict_flags = xe_evict_flags,
	.move = xe_bo_move,
	.io_mem_reserve = xe_ttm_io_mem_reserve,
	.io_mem_pfn = xe_ttm_io_mem_pfn,
	.release_notify = xe_ttm_bo_release_notify,
	.eviction_valuable = ttm_bo_eviction_valuable,
	.delete_mem_notify = xe_ttm_bo_delete_mem_notify,
};

static void xe_ttm_bo_destroy(struct ttm_buffer_object *ttm_bo)
{
	struct xe_bo *bo = ttm_to_xe_bo(ttm_bo);
	struct xe_device *xe = ttm_to_xe_device(ttm_bo->bdev);

	if (bo->ttm.base.import_attach)
		drm_prime_gem_destroy(&bo->ttm.base, NULL);
	drm_gem_object_release(&bo->ttm.base);

	xe_assert(xe, list_empty(&ttm_bo->base.gpuva.list));

	if (bo->ggtt_node.size)
		xe_ggtt_remove_bo(bo->tile->mem.ggtt, bo);

#ifdef CONFIG_PROC_FS
	if (bo->client)
		xe_drm_client_remove_bo(bo);
#endif

	if (bo->vm && xe_bo_is_user(bo))
		xe_vm_put(bo->vm);

	kfree(bo);
}

static void xe_gem_object_free(struct drm_gem_object *obj)
{
	/* Our BO reference counting scheme works as follows:
	 *
	 * The gem object kref is typically used throughout the driver,
	 * and the gem object holds a ttm_buffer_object refcount, so
	 * that when the last gem object reference is put, which is when
	 * we end up in this function, we put also that ttm_buffer_object
	 * refcount. Anything using gem interfaces is then no longer
	 * allowed to access the object in a way that requires a gem
	 * refcount, including locking the object.
	 *
	 * driver ttm callbacks is allowed to use the ttm_buffer_object
	 * refcount directly if needed.
	 */
	__xe_bo_vunmap(gem_to_xe_bo(obj));
	ttm_bo_put(container_of(obj, struct ttm_buffer_object, base));
}

static void xe_gem_object_close(struct drm_gem_object *obj,
				struct drm_file *file_priv)
{
	struct xe_bo *bo = gem_to_xe_bo(obj);

	if (bo->vm && !xe_vm_in_fault_mode(bo->vm)) {
		xe_assert(xe_bo_device(bo), xe_bo_is_user(bo));

		xe_bo_lock(bo, false);
		ttm_bo_set_bulk_move(&bo->ttm, NULL);
		xe_bo_unlock(bo);
	}
}

static bool should_migrate_to_system(struct xe_bo *bo)
{
	struct xe_device *xe = xe_bo_device(bo);

	return xe_device_in_fault_mode(xe) && bo->props.cpu_atomic;
}

static vm_fault_t xe_gem_fault(struct vm_fault *vmf)
{
	struct ttm_buffer_object *tbo = vmf->vma->vm_private_data;
	struct drm_device *ddev = tbo->base.dev;
	vm_fault_t ret;
	int idx, r = 0;

	ret = ttm_bo_vm_reserve(tbo, vmf);
	if (ret)
		return ret;

	if (drm_dev_enter(ddev, &idx)) {
		struct xe_bo *bo = ttm_to_xe_bo(tbo);

		trace_xe_bo_cpu_fault(bo);

		if (should_migrate_to_system(bo)) {
			r = xe_bo_migrate(bo, XE_PL_TT);
			if (r == -EBUSY || r == -ERESTARTSYS || r == -EINTR)
				ret = VM_FAULT_NOPAGE;
			else if (r)
				ret = VM_FAULT_SIGBUS;
		}
		if (!ret)
			ret = ttm_bo_vm_fault_reserved(vmf,
						       vmf->vma->vm_page_prot,
						       TTM_BO_VM_NUM_PREFAULT);
		drm_dev_exit(idx);
	} else {
		ret = ttm_bo_vm_dummy_page(vmf, vmf->vma->vm_page_prot);
	}
	if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
		return ret;

	dma_resv_unlock(tbo->base.resv);
	return ret;
}

static const struct vm_operations_struct xe_gem_vm_ops = {
	.fault = xe_gem_fault,
	.open = ttm_bo_vm_open,
	.close = ttm_bo_vm_close,
	.access = ttm_bo_vm_access
};

static const struct drm_gem_object_funcs xe_gem_object_funcs = {
	.free = xe_gem_object_free,
	.close = xe_gem_object_close,
	.mmap = drm_gem_ttm_mmap,
	.export = xe_gem_prime_export,
	.vm_ops = &xe_gem_vm_ops,
};

/**
 * xe_bo_alloc - Allocate storage for a struct xe_bo
 *
 * This funcition is intended to allocate storage to be used for input
 * to __xe_bo_create_locked(), in the case a pointer to the bo to be
 * created is needed before the call to __xe_bo_create_locked().
 * If __xe_bo_create_locked ends up never to be called, then the
 * storage allocated with this function needs to be freed using
 * xe_bo_free().
 *
 * Return: A pointer to an uninitialized struct xe_bo on success,
 * ERR_PTR(-ENOMEM) on error.
 */
struct xe_bo *xe_bo_alloc(void)
{
	struct xe_bo *bo = kzalloc(sizeof(*bo), GFP_KERNEL);

	if (!bo)
		return ERR_PTR(-ENOMEM);

	return bo;
}

/**
 * xe_bo_free - Free storage allocated using xe_bo_alloc()
 * @bo: The buffer object storage.
 *
 * Refer to xe_bo_alloc() documentation for valid use-cases.
 */
void xe_bo_free(struct xe_bo *bo)
{
	kfree(bo);
}

struct xe_bo *___xe_bo_create_locked(struct xe_device *xe, struct xe_bo *bo,
				     struct xe_tile *tile, struct dma_resv *resv,
				     struct ttm_lru_bulk_move *bulk, size_t size,
				     u16 cpu_caching, enum ttm_bo_type type,
				     u32 flags)
{
	struct ttm_operation_ctx ctx = {
		.interruptible = true,
		.no_wait_gpu = false,
	};
	struct ttm_placement *placement;
	uint32_t alignment;
	size_t aligned_size;
	int err;

	/* Only kernel objects should set GT */
	xe_assert(xe, !tile || type == ttm_bo_type_kernel);

	if (XE_WARN_ON(!size)) {
		xe_bo_free(bo);
		return ERR_PTR(-EINVAL);
	}

	if (flags & (XE_BO_CREATE_VRAM_MASK | XE_BO_CREATE_STOLEN_BIT) &&
	    !(flags & XE_BO_CREATE_IGNORE_MIN_PAGE_SIZE_BIT) &&
	    xe->info.vram_flags & XE_VRAM_FLAGS_NEED64K) {
		aligned_size = ALIGN(size, SZ_64K);
		if (type != ttm_bo_type_device)
			size = ALIGN(size, SZ_64K);
		flags |= XE_BO_INTERNAL_64K;
		alignment = SZ_64K >> PAGE_SHIFT;

	} else {
		aligned_size = ALIGN(size, SZ_4K);
		flags &= ~XE_BO_INTERNAL_64K;
		alignment = SZ_4K >> PAGE_SHIFT;
	}

	if (type == ttm_bo_type_device && aligned_size != size)
		return ERR_PTR(-EINVAL);

	if (!bo) {
		bo = xe_bo_alloc();
		if (IS_ERR(bo))
			return bo;
	}

	bo->ccs_cleared = false;
	bo->tile = tile;
	bo->size = size;
	bo->flags = flags;
	bo->cpu_caching = cpu_caching;
	bo->ttm.base.funcs = &xe_gem_object_funcs;
	bo->props.preferred_mem_class = XE_BO_PROPS_INVALID;
	bo->props.preferred_gt = XE_BO_PROPS_INVALID;
	bo->props.preferred_mem_type = XE_BO_PROPS_INVALID;
	bo->ttm.priority = XE_BO_PRIORITY_NORMAL;
	INIT_LIST_HEAD(&bo->pinned_link);
#ifdef CONFIG_PROC_FS
	INIT_LIST_HEAD(&bo->client_link);
#endif

	drm_gem_private_object_init(&xe->drm, &bo->ttm.base, size);

	if (resv) {
		ctx.allow_res_evict = !(flags & XE_BO_CREATE_NO_RESV_EVICT);
		ctx.resv = resv;
	}

	if (!(flags & XE_BO_FIXED_PLACEMENT_BIT)) {
		err = __xe_bo_placement_for_flags(xe, bo, bo->flags);
		if (WARN_ON(err)) {
			xe_ttm_bo_destroy(&bo->ttm);
			return ERR_PTR(err);
		}
	}

	/* Defer populating type_sg bos */
	placement = (type == ttm_bo_type_sg ||
		     bo->flags & XE_BO_DEFER_BACKING) ? &sys_placement :
		&bo->placement;
	err = ttm_bo_init_reserved(&xe->ttm, &bo->ttm, type,
				   placement, alignment,
				   &ctx, NULL, resv, xe_ttm_bo_destroy);
	if (err)
		return ERR_PTR(err);

	/*
	 * The VRAM pages underneath are potentially still being accessed by the
	 * GPU, as per async GPU clearing and async evictions. However TTM makes
	 * sure to add any corresponding move/clear fences into the objects
	 * dma-resv using the DMA_RESV_USAGE_KERNEL slot.
	 *
	 * For KMD internal buffers we don't care about GPU clearing, however we
	 * still need to handle async evictions, where the VRAM is still being
	 * accessed by the GPU. Most internal callers are not expecting this,
	 * since they are missing the required synchronisation before accessing
	 * the memory. To keep things simple just sync wait any kernel fences
	 * here, if the buffer is designated KMD internal.
	 *
	 * For normal userspace objects we should already have the required
	 * pipelining or sync waiting elsewhere, since we already have to deal
	 * with things like async GPU clearing.
	 */
	if (type == ttm_bo_type_kernel) {
		long timeout = dma_resv_wait_timeout(bo->ttm.base.resv,
						     DMA_RESV_USAGE_KERNEL,
						     ctx.interruptible,
						     MAX_SCHEDULE_TIMEOUT);

		if (timeout < 0) {
			if (!resv)
				dma_resv_unlock(bo->ttm.base.resv);
			xe_bo_put(bo);
			return ERR_PTR(timeout);
		}
	}

	bo->created = true;
	if (bulk)
		ttm_bo_set_bulk_move(&bo->ttm, bulk);
	else
		ttm_bo_move_to_lru_tail_unlocked(&bo->ttm);

	return bo;
}

static int __xe_bo_fixed_placement(struct xe_device *xe,
				   struct xe_bo *bo,
				   u32 flags,
				   u64 start, u64 end, u64 size)
{
	struct ttm_place *place = bo->placements;

	if (flags & (XE_BO_CREATE_USER_BIT|XE_BO_CREATE_SYSTEM_BIT))
		return -EINVAL;

	place->flags = TTM_PL_FLAG_CONTIGUOUS;
	place->fpfn = start >> PAGE_SHIFT;
	place->lpfn = end >> PAGE_SHIFT;

	switch (flags & (XE_BO_CREATE_STOLEN_BIT | XE_BO_CREATE_VRAM_MASK)) {
	case XE_BO_CREATE_VRAM0_BIT:
		place->mem_type = XE_PL_VRAM0;
		break;
	case XE_BO_CREATE_VRAM1_BIT:
		place->mem_type = XE_PL_VRAM1;
		break;
	case XE_BO_CREATE_STOLEN_BIT:
		place->mem_type = XE_PL_STOLEN;
		break;

	default:
		/* 0 or multiple of the above set */
		return -EINVAL;
	}

	bo->placement = (struct ttm_placement) {
		.num_placement = 1,
		.placement = place,
		.num_busy_placement = 1,
		.busy_placement = place,
	};

	return 0;
}

static struct xe_bo *
__xe_bo_create_locked(struct xe_device *xe,
		      struct xe_tile *tile, struct xe_vm *vm,
		      size_t size, u64 start, u64 end,
		      u16 cpu_caching, enum ttm_bo_type type, u32 flags)
{
	struct xe_bo *bo = NULL;
	int err;

	if (vm)
		xe_vm_assert_held(vm);

	if (start || end != ~0ULL) {
		bo = xe_bo_alloc();
		if (IS_ERR(bo))
			return bo;

		flags |= XE_BO_FIXED_PLACEMENT_BIT;
		err = __xe_bo_fixed_placement(xe, bo, flags, start, end, size);
		if (err) {
			xe_bo_free(bo);
			return ERR_PTR(err);
		}
	}

	bo = ___xe_bo_create_locked(xe, bo, tile, vm ? xe_vm_resv(vm) : NULL,
				    vm && !xe_vm_in_fault_mode(vm) &&
				    flags & XE_BO_CREATE_USER_BIT ?
				    &vm->lru_bulk_move : NULL, size,
				    cpu_caching, type, flags);
	if (IS_ERR(bo))
		return bo;

	/*
	 * Note that instead of taking a reference no the drm_gpuvm_resv_bo(),
	 * to ensure the shared resv doesn't disappear under the bo, the bo
	 * will keep a reference to the vm, and avoid circular references
	 * by having all the vm's bo refereferences released at vm close
	 * time.
	 */
	if (vm && xe_bo_is_user(bo))
		xe_vm_get(vm);
	bo->vm = vm;

	if (bo->flags & XE_BO_CREATE_GGTT_BIT) {
		if (!tile && flags & XE_BO_CREATE_STOLEN_BIT)
			tile = xe_device_get_root_tile(xe);

		xe_assert(xe, tile);

		if (flags & XE_BO_FIXED_PLACEMENT_BIT) {
			err = xe_ggtt_insert_bo_at(tile->mem.ggtt, bo,
						   start + bo->size, U64_MAX);
		} else {
			err = xe_ggtt_insert_bo(tile->mem.ggtt, bo);
		}
		if (err)
			goto err_unlock_put_bo;
	}

	return bo;

err_unlock_put_bo:
	__xe_bo_unset_bulk_move(bo);
	xe_bo_unlock_vm_held(bo);
	xe_bo_put(bo);
	return ERR_PTR(err);
}

struct xe_bo *
xe_bo_create_locked_range(struct xe_device *xe,
			  struct xe_tile *tile, struct xe_vm *vm,
			  size_t size, u64 start, u64 end,
			  enum ttm_bo_type type, u32 flags)
{
	return __xe_bo_create_locked(xe, tile, vm, size, start, end, 0, type, flags);
}

struct xe_bo *xe_bo_create_locked(struct xe_device *xe, struct xe_tile *tile,
				  struct xe_vm *vm, size_t size,
				  enum ttm_bo_type type, u32 flags)
{
	return __xe_bo_create_locked(xe, tile, vm, size, 0, ~0ULL, 0, type, flags);
}

struct xe_bo *xe_bo_create_user(struct xe_device *xe, struct xe_tile *tile,
				struct xe_vm *vm, size_t size,
				u16 cpu_caching,
				enum ttm_bo_type type,
				u32 flags)
{
	struct xe_bo *bo = __xe_bo_create_locked(xe, tile, vm, size, 0, ~0ULL,
						 cpu_caching, type,
						 flags | XE_BO_CREATE_USER_BIT);
	if (!IS_ERR(bo))
		xe_bo_unlock_vm_held(bo);

	return bo;
}

struct xe_bo *xe_bo_create(struct xe_device *xe, struct xe_tile *tile,
			   struct xe_vm *vm, size_t size,
			   enum ttm_bo_type type, u32 flags)
{
	struct xe_bo *bo = xe_bo_create_locked(xe, tile, vm, size, type, flags);

	if (!IS_ERR(bo))
		xe_bo_unlock_vm_held(bo);

	return bo;
}

struct xe_bo *xe_bo_create_pin_map_at(struct xe_device *xe, struct xe_tile *tile,
				      struct xe_vm *vm,
				      size_t size, u64 offset,
				      enum ttm_bo_type type, u32 flags)
{
	struct xe_bo *bo;
	int err;
	u64 start = offset == ~0ull ? 0 : offset;
	u64 end = offset == ~0ull ? offset : start + size;

	if (flags & XE_BO_CREATE_STOLEN_BIT &&
	    xe_ttm_stolen_cpu_access_needs_ggtt(xe))
		flags |= XE_BO_CREATE_GGTT_BIT;

	bo = xe_bo_create_locked_range(xe, tile, vm, size, start, end, type,
				       flags | XE_BO_NEEDS_CPU_ACCESS);
	if (IS_ERR(bo))
		return bo;

	err = xe_bo_pin(bo);
	if (err)
		goto err_put;

	err = xe_bo_vmap(bo);
	if (err)
		goto err_unpin;

	xe_bo_unlock_vm_held(bo);

	return bo;

err_unpin:
	xe_bo_unpin(bo);
err_put:
	xe_bo_unlock_vm_held(bo);
	xe_bo_put(bo);
	return ERR_PTR(err);
}

struct xe_bo *xe_bo_create_pin_map(struct xe_device *xe, struct xe_tile *tile,
				   struct xe_vm *vm, size_t size,
				   enum ttm_bo_type type, u32 flags)
{
	return xe_bo_create_pin_map_at(xe, tile, vm, size, ~0ull, type, flags);
}

struct xe_bo *xe_bo_create_from_data(struct xe_device *xe, struct xe_tile *tile,
				     const void *data, size_t size,
				     enum ttm_bo_type type, u32 flags)
{
	struct xe_bo *bo = xe_bo_create_pin_map(xe, tile, NULL,
						ALIGN(size, PAGE_SIZE),
						type, flags);
	if (IS_ERR(bo))
		return bo;

	xe_map_memcpy_to(xe, &bo->vmap, 0, data, size);

	return bo;
}

static void __xe_bo_unpin_map_no_vm(struct drm_device *drm, void *arg)
{
	xe_bo_unpin_map_no_vm(arg);
}

struct xe_bo *xe_managed_bo_create_pin_map(struct xe_device *xe, struct xe_tile *tile,
					   size_t size, u32 flags)
{
	struct xe_bo *bo;
	int ret;

	bo = xe_bo_create_pin_map(xe, tile, NULL, size, ttm_bo_type_kernel, flags);
	if (IS_ERR(bo))
		return bo;

	ret = drmm_add_action_or_reset(&xe->drm, __xe_bo_unpin_map_no_vm, bo);
	if (ret)
		return ERR_PTR(ret);

	return bo;
}

struct xe_bo *xe_managed_bo_create_from_data(struct xe_device *xe, struct xe_tile *tile,
					     const void *data, size_t size, u32 flags)
{
	struct xe_bo *bo = xe_managed_bo_create_pin_map(xe, tile, ALIGN(size, PAGE_SIZE), flags);

	if (IS_ERR(bo))
		return bo;

	xe_map_memcpy_to(xe, &bo->vmap, 0, data, size);

	return bo;
}

/*
 * XXX: This is in the VM bind data path, likely should calculate this once and
 * store, with a recalculation if the BO is moved.
 */
uint64_t vram_region_gpu_offset(struct ttm_resource *res)
{
	struct xe_device *xe = ttm_to_xe_device(res->bo->bdev);

	if (res->mem_type == XE_PL_STOLEN)
		return xe_ttm_stolen_gpu_offset(xe);

	return res_to_mem_region(res)->dpa_base;
}

/**
 * xe_bo_pin_external - pin an external BO
 * @bo: buffer object to be pinned
 *
 * Pin an external (not tied to a VM, can be exported via dma-buf / prime FD)
 * BO. Unique call compared to xe_bo_pin as this function has it own set of
 * asserts and code to ensure evict / restore on suspend / resume.
 *
 * Returns 0 for success, negative error code otherwise.
 */
int xe_bo_pin_external(struct xe_bo *bo)
{
	struct xe_device *xe = xe_bo_device(bo);
	int err;

	xe_assert(xe, !bo->vm);
	xe_assert(xe, xe_bo_is_user(bo));

	if (!xe_bo_is_pinned(bo)) {
		err = xe_bo_validate(bo, NULL, false);
		if (err)
			return err;

		if (xe_bo_is_vram(bo)) {
			spin_lock(&xe->pinned.lock);
			list_add_tail(&bo->pinned_link,
				      &xe->pinned.external_vram);
			spin_unlock(&xe->pinned.lock);
		}
	}

	ttm_bo_pin(&bo->ttm);

	/*
	 * FIXME: If we always use the reserve / unreserve functions for locking
	 * we do not need this.
	 */
	ttm_bo_move_to_lru_tail_unlocked(&bo->ttm);

	return 0;
}

int xe_bo_pin(struct xe_bo *bo)
{
	struct xe_device *xe = xe_bo_device(bo);
	int err;

	/* We currently don't expect user BO to be pinned */
	xe_assert(xe, !xe_bo_is_user(bo));

	/* Pinned object must be in GGTT or have pinned flag */
	xe_assert(xe, bo->flags & (XE_BO_CREATE_PINNED_BIT |
				   XE_BO_CREATE_GGTT_BIT));

	/*
	 * No reason we can't support pinning imported dma-bufs we just don't
	 * expect to pin an imported dma-buf.
	 */
	xe_assert(xe, !bo->ttm.base.import_attach);

	/* We only expect at most 1 pin */
	xe_assert(xe, !xe_bo_is_pinned(bo));

	err = xe_bo_validate(bo, NULL, false);
	if (err)
		return err;

	/*
	 * For pinned objects in on DGFX, which are also in vram, we expect
	 * these to be in contiguous VRAM memory. Required eviction / restore
	 * during suspend / resume (force restore to same physical address).
	 */
	if (IS_DGFX(xe) && !(IS_ENABLED(CONFIG_DRM_XE_DEBUG) &&
	    bo->flags & XE_BO_INTERNAL_TEST)) {
		struct ttm_place *place = &(bo->placements[0]);

		if (mem_type_is_vram(place->mem_type)) {
			xe_assert(xe, place->flags & TTM_PL_FLAG_CONTIGUOUS);

			place->fpfn = (xe_bo_addr(bo, 0, PAGE_SIZE) -
				       vram_region_gpu_offset(bo->ttm.resource)) >> PAGE_SHIFT;
			place->lpfn = place->fpfn + (bo->size >> PAGE_SHIFT);

			spin_lock(&xe->pinned.lock);
			list_add_tail(&bo->pinned_link, &xe->pinned.kernel_bo_present);
			spin_unlock(&xe->pinned.lock);
		}
	}

	ttm_bo_pin(&bo->ttm);

	/*
	 * FIXME: If we always use the reserve / unreserve functions for locking
	 * we do not need this.
	 */
	ttm_bo_move_to_lru_tail_unlocked(&bo->ttm);

	return 0;
}

/**
 * xe_bo_unpin_external - unpin an external BO
 * @bo: buffer object to be unpinned
 *
 * Unpin an external (not tied to a VM, can be exported via dma-buf / prime FD)
 * BO. Unique call compared to xe_bo_unpin as this function has it own set of
 * asserts and code to ensure evict / restore on suspend / resume.
 *
 * Returns 0 for success, negative error code otherwise.
 */
void xe_bo_unpin_external(struct xe_bo *bo)
{
	struct xe_device *xe = xe_bo_device(bo);

	xe_assert(xe, !bo->vm);
	xe_assert(xe, xe_bo_is_pinned(bo));
	xe_assert(xe, xe_bo_is_user(bo));

	if (bo->ttm.pin_count == 1 && !list_empty(&bo->pinned_link)) {
		spin_lock(&xe->pinned.lock);
		list_del_init(&bo->pinned_link);
		spin_unlock(&xe->pinned.lock);
	}

	ttm_bo_unpin(&bo->ttm);

	/*
	 * FIXME: If we always use the reserve / unreserve functions for locking
	 * we do not need this.
	 */
	ttm_bo_move_to_lru_tail_unlocked(&bo->ttm);
}

void xe_bo_unpin(struct xe_bo *bo)
{
	struct xe_device *xe = xe_bo_device(bo);

	xe_assert(xe, !bo->ttm.base.import_attach);
	xe_assert(xe, xe_bo_is_pinned(bo));

	if (IS_DGFX(xe) && !(IS_ENABLED(CONFIG_DRM_XE_DEBUG) &&
	    bo->flags & XE_BO_INTERNAL_TEST)) {
		struct ttm_place *place = &(bo->placements[0]);

		if (mem_type_is_vram(place->mem_type)) {
			xe_assert(xe, !list_empty(&bo->pinned_link));

			spin_lock(&xe->pinned.lock);
			list_del_init(&bo->pinned_link);
			spin_unlock(&xe->pinned.lock);
		}
	}

	ttm_bo_unpin(&bo->ttm);
}

/**
 * xe_bo_validate() - Make sure the bo is in an allowed placement
 * @bo: The bo,
 * @vm: Pointer to a the vm the bo shares a locked dma_resv object with, or
 *      NULL. Used together with @allow_res_evict.
 * @allow_res_evict: Whether it's allowed to evict bos sharing @vm's
 *                   reservation object.
 *
 * Make sure the bo is in allowed placement, migrating it if necessary. If
 * needed, other bos will be evicted. If bos selected for eviction shares
 * the @vm's reservation object, they can be evicted iff @allow_res_evict is
 * set to true, otherwise they will be bypassed.
 *
 * Return: 0 on success, negative error code on failure. May return
 * -EINTR or -ERESTARTSYS if internal waits are interrupted by a signal.
 */
int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict)
{
	struct ttm_operation_ctx ctx = {
		.interruptible = true,
		.no_wait_gpu = false,
	};

	if (vm) {
		lockdep_assert_held(&vm->lock);
		xe_vm_assert_held(vm);

		ctx.allow_res_evict = allow_res_evict;
		ctx.resv = xe_vm_resv(vm);
	}

	return ttm_bo_validate(&bo->ttm, &bo->placement, &ctx);
}

bool xe_bo_is_xe_bo(struct ttm_buffer_object *bo)
{
	if (bo->destroy == &xe_ttm_bo_destroy)
		return true;

	return false;
}

/*
 * Resolve a BO address. There is no assert to check if the proper lock is held
 * so it should only be used in cases where it is not fatal to get the wrong
 * address, such as printing debug information, but not in cases where memory is
 * written based on this result.
 */
dma_addr_t __xe_bo_addr(struct xe_bo *bo, u64 offset, size_t page_size)
{
	struct xe_device *xe = xe_bo_device(bo);
	struct xe_res_cursor cur;
	u64 page;

	xe_assert(xe, page_size <= PAGE_SIZE);
	page = offset >> PAGE_SHIFT;
	offset &= (PAGE_SIZE - 1);

	if (!xe_bo_is_vram(bo) && !xe_bo_is_stolen(bo)) {
		xe_assert(xe, bo->ttm.ttm);

		xe_res_first_sg(xe_bo_sg(bo), page << PAGE_SHIFT,
				page_size, &cur);
		return xe_res_dma(&cur) + offset;
	} else {
		struct xe_res_cursor cur;

		xe_res_first(bo->ttm.resource, page << PAGE_SHIFT,
			     page_size, &cur);
		return cur.start + offset + vram_region_gpu_offset(bo->ttm.resource);
	}
}

dma_addr_t xe_bo_addr(struct xe_bo *bo, u64 offset, size_t page_size)
{
	if (!READ_ONCE(bo->ttm.pin_count))
		xe_bo_assert_held(bo);
	return __xe_bo_addr(bo, offset, page_size);
}

int xe_bo_vmap(struct xe_bo *bo)
{
	void *virtual;
	bool is_iomem;
	int ret;

	xe_bo_assert_held(bo);

	if (!(bo->flags & XE_BO_NEEDS_CPU_ACCESS))
		return -EINVAL;

	if (!iosys_map_is_null(&bo->vmap))
		return 0;

	/*
	 * We use this more or less deprecated interface for now since
	 * ttm_bo_vmap() doesn't offer the optimization of kmapping
	 * single page bos, which is done here.
	 * TODO: Fix up ttm_bo_vmap to do that, or fix up ttm_bo_kmap
	 * to use struct iosys_map.
	 */
	ret = ttm_bo_kmap(&bo->ttm, 0, bo->size >> PAGE_SHIFT, &bo->kmap);
	if (ret)
		return ret;

	virtual = ttm_kmap_obj_virtual(&bo->kmap, &is_iomem);
	if (is_iomem)
		iosys_map_set_vaddr_iomem(&bo->vmap, (void __iomem *)virtual);
	else
		iosys_map_set_vaddr(&bo->vmap, virtual);

	return 0;
}

static void __xe_bo_vunmap(struct xe_bo *bo)
{
	if (!iosys_map_is_null(&bo->vmap)) {
		iosys_map_clear(&bo->vmap);
		ttm_bo_kunmap(&bo->kmap);
	}
}

void xe_bo_vunmap(struct xe_bo *bo)
{
	xe_bo_assert_held(bo);
	__xe_bo_vunmap(bo);
}

int xe_gem_create_ioctl(struct drm_device *dev, void *data,
			struct drm_file *file)
{
	struct xe_device *xe = to_xe_device(dev);
	struct xe_file *xef = to_xe_file(file);
	struct drm_xe_gem_create *args = data;
	struct xe_vm *vm = NULL;
	struct xe_bo *bo;
	unsigned int bo_flags;
	u32 handle;
	int err;

	if (XE_IOCTL_DBG(xe, args->extensions) ||
	    XE_IOCTL_DBG(xe, args->pad[0] || args->pad[1] || args->pad[2]) ||
	    XE_IOCTL_DBG(xe, args->reserved[0] || args->reserved[1]))
		return -EINVAL;

	/* at least one valid memory placement must be specified */
	if (XE_IOCTL_DBG(xe, (args->placement & ~xe->info.mem_region_mask) ||
			 !args->placement))
		return -EINVAL;

	if (XE_IOCTL_DBG(xe, args->flags &
			 ~(DRM_XE_GEM_CREATE_FLAG_DEFER_BACKING |
			   DRM_XE_GEM_CREATE_FLAG_SCANOUT |
			   DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM)))
		return -EINVAL;

	if (XE_IOCTL_DBG(xe, args->handle))
		return -EINVAL;

	if (XE_IOCTL_DBG(xe, !args->size))
		return -EINVAL;

	if (XE_IOCTL_DBG(xe, args->size > SIZE_MAX))
		return -EINVAL;

	if (XE_IOCTL_DBG(xe, args->size & ~PAGE_MASK))
		return -EINVAL;

	bo_flags = 0;
	if (args->flags & DRM_XE_GEM_CREATE_FLAG_DEFER_BACKING)
		bo_flags |= XE_BO_DEFER_BACKING;

	if (args->flags & DRM_XE_GEM_CREATE_FLAG_SCANOUT)
		bo_flags |= XE_BO_SCANOUT_BIT;

	bo_flags |= args->placement << (ffs(XE_BO_CREATE_SYSTEM_BIT) - 1);

	if (args->flags & DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM) {
		if (XE_IOCTL_DBG(xe, !(bo_flags & XE_BO_CREATE_VRAM_MASK)))
			return -EINVAL;

		bo_flags |= XE_BO_NEEDS_CPU_ACCESS;
	}

	if (XE_IOCTL_DBG(xe, !args->cpu_caching ||
			 args->cpu_caching > DRM_XE_GEM_CPU_CACHING_WC))
		return -EINVAL;

	if (XE_IOCTL_DBG(xe, bo_flags & XE_BO_CREATE_VRAM_MASK &&
			 args->cpu_caching != DRM_XE_GEM_CPU_CACHING_WC))
		return -EINVAL;

	if (XE_IOCTL_DBG(xe, bo_flags & XE_BO_SCANOUT_BIT &&
			 args->cpu_caching == DRM_XE_GEM_CPU_CACHING_WB))
		return -EINVAL;

	if (args->vm_id) {
		vm = xe_vm_lookup(xef, args->vm_id);
		if (XE_IOCTL_DBG(xe, !vm))
			return -ENOENT;
		err = xe_vm_lock(vm, true);
		if (err)
			goto out_vm;
	}

	bo = xe_bo_create_user(xe, NULL, vm, args->size, args->cpu_caching,
			       ttm_bo_type_device, bo_flags);

	if (vm)
		xe_vm_unlock(vm);

	if (IS_ERR(bo)) {
		err = PTR_ERR(bo);
		goto out_vm;
	}

	err = drm_gem_handle_create(file, &bo->ttm.base, &handle);
	if (err)
		goto out_bulk;

	args->handle = handle;
	goto out_put;

out_bulk:
	if (vm && !xe_vm_in_fault_mode(vm)) {
		xe_vm_lock(vm, false);
		__xe_bo_unset_bulk_move(bo);
		xe_vm_unlock(vm);
	}
out_put:
	xe_bo_put(bo);
out_vm:
	if (vm)
		xe_vm_put(vm);

	return err;
}

int xe_gem_mmap_offset_ioctl(struct drm_device *dev, void *data,
			     struct drm_file *file)
{
	struct xe_device *xe = to_xe_device(dev);
	struct drm_xe_gem_mmap_offset *args = data;
	struct drm_gem_object *gem_obj;

	if (XE_IOCTL_DBG(xe, args->extensions) ||
	    XE_IOCTL_DBG(xe, args->reserved[0] || args->reserved[1]))
		return -EINVAL;

	if (XE_IOCTL_DBG(xe, args->flags))
		return -EINVAL;

	gem_obj = drm_gem_object_lookup(file, args->handle);
	if (XE_IOCTL_DBG(xe, !gem_obj))
		return -ENOENT;

	/* The mmap offset was set up at BO allocation time. */
	args->offset = drm_vma_node_offset_addr(&gem_obj->vma_node);

	xe_bo_put(gem_to_xe_bo(gem_obj));
	return 0;
}

/**
 * xe_bo_lock() - Lock the buffer object's dma_resv object
 * @bo: The struct xe_bo whose lock is to be taken
 * @intr: Whether to perform any wait interruptible
 *
 * Locks the buffer object's dma_resv object. If the buffer object is
 * pointing to a shared dma_resv object, that shared lock is locked.
 *
 * Return: 0 on success, -EINTR if @intr is true and the wait for a
 * contended lock was interrupted. If @intr is set to false, the
 * function always returns 0.
 */
int xe_bo_lock(struct xe_bo *bo, bool intr)
{
	if (intr)
		return dma_resv_lock_interruptible(bo->ttm.base.resv, NULL);

	dma_resv_lock(bo->ttm.base.resv, NULL);

	return 0;
}

/**
 * xe_bo_unlock() - Unlock the buffer object's dma_resv object
 * @bo: The struct xe_bo whose lock is to be released.
 *
 * Unlock a buffer object lock that was locked by xe_bo_lock().
 */
void xe_bo_unlock(struct xe_bo *bo)
{
	dma_resv_unlock(bo->ttm.base.resv);
}

/**
 * xe_bo_can_migrate - Whether a buffer object likely can be migrated
 * @bo: The buffer object to migrate
 * @mem_type: The TTM memory type intended to migrate to
 *
 * Check whether the buffer object supports migration to the
 * given memory type. Note that pinning may affect the ability to migrate as
 * returned by this function.
 *
 * This function is primarily intended as a helper for checking the
 * possibility to migrate buffer objects and can be called without
 * the object lock held.
 *
 * Return: true if migration is possible, false otherwise.
 */
bool xe_bo_can_migrate(struct xe_bo *bo, u32 mem_type)
{
	unsigned int cur_place;

	if (bo->ttm.type == ttm_bo_type_kernel)
		return true;

	if (bo->ttm.type == ttm_bo_type_sg)
		return false;

	for (cur_place = 0; cur_place < bo->placement.num_placement;
	     cur_place++) {
		if (bo->placements[cur_place].mem_type == mem_type)
			return true;
	}

	return false;
}

static void xe_place_from_ttm_type(u32 mem_type, struct ttm_place *place)
{
	memset(place, 0, sizeof(*place));
	place->mem_type = mem_type;
}

/**
 * xe_bo_migrate - Migrate an object to the desired region id
 * @bo: The buffer object to migrate.
 * @mem_type: The TTM region type to migrate to.
 *
 * Attempt to migrate the buffer object to the desired memory region. The
 * buffer object may not be pinned, and must be locked.
 * On successful completion, the object memory type will be updated,
 * but an async migration task may not have completed yet, and to
 * accomplish that, the object's kernel fences must be signaled with
 * the object lock held.
 *
 * Return: 0 on success. Negative error code on failure. In particular may
 * return -EINTR or -ERESTARTSYS if signal pending.
 */
int xe_bo_migrate(struct xe_bo *bo, u32 mem_type)
{
	struct xe_device *xe = ttm_to_xe_device(bo->ttm.bdev);
	struct ttm_operation_ctx ctx = {
		.interruptible = true,
		.no_wait_gpu = false,
	};
	struct ttm_placement placement;
	struct ttm_place requested;

	xe_bo_assert_held(bo);

	if (bo->ttm.resource->mem_type == mem_type)
		return 0;

	if (xe_bo_is_pinned(bo))
		return -EBUSY;

	if (!xe_bo_can_migrate(bo, mem_type))
		return -EINVAL;

	xe_place_from_ttm_type(mem_type, &requested);
	placement.num_placement = 1;
	placement.num_busy_placement = 1;
	placement.placement = &requested;
	placement.busy_placement = &requested;

	/*
	 * Stolen needs to be handled like below VRAM handling if we ever need
	 * to support it.
	 */
	drm_WARN_ON(&xe->drm, mem_type == XE_PL_STOLEN);

	if (mem_type_is_vram(mem_type)) {
		u32 c = 0;

		add_vram(xe, bo, &requested, bo->flags, mem_type, &c);
	}

	return ttm_bo_validate(&bo->ttm, &placement, &ctx);
}

/**
 * xe_bo_evict - Evict an object to evict placement
 * @bo: The buffer object to migrate.
 * @force_alloc: Set force_alloc in ttm_operation_ctx
 *
 * On successful completion, the object memory will be moved to evict
 * placement. Ths function blocks until the object has been fully moved.
 *
 * Return: 0 on success. Negative error code on failure.
 */
int xe_bo_evict(struct xe_bo *bo, bool force_alloc)
{
	struct ttm_operation_ctx ctx = {
		.interruptible = false,
		.no_wait_gpu = false,
		.force_alloc = force_alloc,
	};
	struct ttm_placement placement;
	int ret;

	xe_evict_flags(&bo->ttm, &placement);
	ret = ttm_bo_validate(&bo->ttm, &placement, &ctx);
	if (ret)
		return ret;

	dma_resv_wait_timeout(bo->ttm.base.resv, DMA_RESV_USAGE_KERNEL,
			      false, MAX_SCHEDULE_TIMEOUT);

	return 0;
}

/**
 * xe_bo_needs_ccs_pages - Whether a bo needs to back up CCS pages when
 * placed in system memory.
 * @bo: The xe_bo
 *
 * Return: true if extra pages need to be allocated, false otherwise.
 */
bool xe_bo_needs_ccs_pages(struct xe_bo *bo)
{
	struct xe_device *xe = xe_bo_device(bo);

	if (!xe_device_has_flat_ccs(xe) || bo->ttm.type != ttm_bo_type_device)
		return false;

	/* On discrete GPUs, if the GPU can access this buffer from
	 * system memory (i.e., it allows XE_PL_TT placement), FlatCCS
	 * can't be used since there's no CCS storage associated with
	 * non-VRAM addresses.
	 */
	if (IS_DGFX(xe) && (bo->flags & XE_BO_CREATE_SYSTEM_BIT))
		return false;

	return true;
}

/**
 * __xe_bo_release_dummy() - Dummy kref release function
 * @kref: The embedded struct kref.
 *
 * Dummy release function for xe_bo_put_deferred(). Keep off.
 */
void __xe_bo_release_dummy(struct kref *kref)
{
}

/**
 * xe_bo_put_commit() - Put bos whose put was deferred by xe_bo_put_deferred().
 * @deferred: The lockless list used for the call to xe_bo_put_deferred().
 *
 * Puts all bos whose put was deferred by xe_bo_put_deferred().
 * The @deferred list can be either an onstack local list or a global
 * shared list used by a workqueue.
 */
void xe_bo_put_commit(struct llist_head *deferred)
{
	struct llist_node *freed;
	struct xe_bo *bo, *next;

	if (!deferred)
		return;

	freed = llist_del_all(deferred);
	if (!freed)
		return;

	llist_for_each_entry_safe(bo, next, freed, freed)
		drm_gem_object_free(&bo->ttm.base.refcount);
}

/**
 * xe_bo_dumb_create - Create a dumb bo as backing for a fb
 * @file_priv: ...
 * @dev: ...
 * @args: ...
 *
 * See dumb_create() hook in include/drm/drm_drv.h
 *
 * Return: ...
 */
int xe_bo_dumb_create(struct drm_file *file_priv,
		      struct drm_device *dev,
		      struct drm_mode_create_dumb *args)
{
	struct xe_device *xe = to_xe_device(dev);
	struct xe_bo *bo;
	uint32_t handle;
	int cpp = DIV_ROUND_UP(args->bpp, 8);
	int err;
	u32 page_size = max_t(u32, PAGE_SIZE,
		xe->info.vram_flags & XE_VRAM_FLAGS_NEED64K ? SZ_64K : SZ_4K);

	args->pitch = ALIGN(args->width * cpp, 64);
	args->size = ALIGN(mul_u32_u32(args->pitch, args->height),
			   page_size);

	bo = xe_bo_create_user(xe, NULL, NULL, args->size,
			       DRM_XE_GEM_CPU_CACHING_WC,
			       ttm_bo_type_device,
			       XE_BO_CREATE_VRAM_IF_DGFX(xe_device_get_root_tile(xe)) |
			       XE_BO_CREATE_USER_BIT | XE_BO_SCANOUT_BIT |
			       XE_BO_NEEDS_CPU_ACCESS);
	if (IS_ERR(bo))
		return PTR_ERR(bo);

	err = drm_gem_handle_create(file_priv, &bo->ttm.base, &handle);
	/* drop reference from allocate - handle holds it now */
	drm_gem_object_put(&bo->ttm.base);
	if (!err)
		args->handle = handle;
	return err;
}

#if IS_ENABLED(CONFIG_DRM_XE_KUNIT_TEST)
#include "tests/xe_bo.c"
#endif