Bootlin logo

Elixir Cross Referencer

   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
/*
 * Copyright 2014-2018 Advanced Micro Devices, Inc.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
 * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
 * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
 * OTHER DEALINGS IN THE SOFTWARE.
 */

#define pr_fmt(fmt) "kfd2kgd: " fmt

#include <linux/list.h>
#include <linux/pagemap.h>
#include <linux/sched/mm.h>
#include <drm/drmP.h>
#include "amdgpu_object.h"
#include "amdgpu_vm.h"
#include "amdgpu_amdkfd.h"

/* Special VM and GART address alignment needed for VI pre-Fiji due to
 * a HW bug.
 */
#define VI_BO_SIZE_ALIGN (0x8000)

/* BO flag to indicate a KFD userptr BO */
#define AMDGPU_AMDKFD_USERPTR_BO (1ULL << 63)

/* Userptr restore delay, just long enough to allow consecutive VM
 * changes to accumulate
 */
#define AMDGPU_USERPTR_RESTORE_DELAY_MS 1

/* Impose limit on how much memory KFD can use */
static struct {
	uint64_t max_system_mem_limit;
	uint64_t max_userptr_mem_limit;
	int64_t system_mem_used;
	int64_t userptr_mem_used;
	spinlock_t mem_limit_lock;
} kfd_mem_limit;

/* Struct used for amdgpu_amdkfd_bo_validate */
struct amdgpu_vm_parser {
	uint32_t        domain;
	bool            wait;
};

static const char * const domain_bit_to_string[] = {
		"CPU",
		"GTT",
		"VRAM",
		"GDS",
		"GWS",
		"OA"
};

#define domain_string(domain) domain_bit_to_string[ffs(domain)-1]

static void amdgpu_amdkfd_restore_userptr_worker(struct work_struct *work);


static inline struct amdgpu_device *get_amdgpu_device(struct kgd_dev *kgd)
{
	return (struct amdgpu_device *)kgd;
}

static bool check_if_add_bo_to_vm(struct amdgpu_vm *avm,
		struct kgd_mem *mem)
{
	struct kfd_bo_va_list *entry;

	list_for_each_entry(entry, &mem->bo_va_list, bo_list)
		if (entry->bo_va->base.vm == avm)
			return false;

	return true;
}

/* Set memory usage limits. Current, limits are
 *  System (kernel) memory - 3/8th System RAM
 *  Userptr memory - 3/4th System RAM
 */
void amdgpu_amdkfd_gpuvm_init_mem_limits(void)
{
	struct sysinfo si;
	uint64_t mem;

	si_meminfo(&si);
	mem = si.totalram - si.totalhigh;
	mem *= si.mem_unit;

	spin_lock_init(&kfd_mem_limit.mem_limit_lock);
	kfd_mem_limit.max_system_mem_limit = (mem >> 1) - (mem >> 3);
	kfd_mem_limit.max_userptr_mem_limit = mem - (mem >> 2);
	pr_debug("Kernel memory limit %lluM, userptr limit %lluM\n",
		(kfd_mem_limit.max_system_mem_limit >> 20),
		(kfd_mem_limit.max_userptr_mem_limit >> 20));
}

static int amdgpu_amdkfd_reserve_system_mem_limit(struct amdgpu_device *adev,
					      uint64_t size, u32 domain)
{
	size_t acc_size;
	int ret = 0;

	acc_size = ttm_bo_dma_acc_size(&adev->mman.bdev, size,
				       sizeof(struct amdgpu_bo));

	spin_lock(&kfd_mem_limit.mem_limit_lock);
	if (domain == AMDGPU_GEM_DOMAIN_GTT) {
		if (kfd_mem_limit.system_mem_used + (acc_size + size) >
			kfd_mem_limit.max_system_mem_limit) {
			ret = -ENOMEM;
			goto err_no_mem;
		}
		kfd_mem_limit.system_mem_used += (acc_size + size);
	} else if (domain == AMDGPU_GEM_DOMAIN_CPU) {
		if ((kfd_mem_limit.system_mem_used + acc_size >
			kfd_mem_limit.max_system_mem_limit) ||
			(kfd_mem_limit.userptr_mem_used + (size + acc_size) >
			kfd_mem_limit.max_userptr_mem_limit)) {
			ret = -ENOMEM;
			goto err_no_mem;
		}
		kfd_mem_limit.system_mem_used += acc_size;
		kfd_mem_limit.userptr_mem_used += size;
	}
err_no_mem:
	spin_unlock(&kfd_mem_limit.mem_limit_lock);
	return ret;
}

static void unreserve_system_mem_limit(struct amdgpu_device *adev,
				       uint64_t size, u32 domain)
{
	size_t acc_size;

	acc_size = ttm_bo_dma_acc_size(&adev->mman.bdev, size,
				       sizeof(struct amdgpu_bo));

	spin_lock(&kfd_mem_limit.mem_limit_lock);
	if (domain == AMDGPU_GEM_DOMAIN_GTT) {
		kfd_mem_limit.system_mem_used -= (acc_size + size);
	} else if (domain == AMDGPU_GEM_DOMAIN_CPU) {
		kfd_mem_limit.system_mem_used -= acc_size;
		kfd_mem_limit.userptr_mem_used -= size;
	}
	WARN_ONCE(kfd_mem_limit.system_mem_used < 0,
		  "kfd system memory accounting unbalanced");
	WARN_ONCE(kfd_mem_limit.userptr_mem_used < 0,
		  "kfd userptr memory accounting unbalanced");

	spin_unlock(&kfd_mem_limit.mem_limit_lock);
}

void amdgpu_amdkfd_unreserve_system_memory_limit(struct amdgpu_bo *bo)
{
	spin_lock(&kfd_mem_limit.mem_limit_lock);

	if (bo->flags & AMDGPU_AMDKFD_USERPTR_BO) {
		kfd_mem_limit.system_mem_used -= bo->tbo.acc_size;
		kfd_mem_limit.userptr_mem_used -= amdgpu_bo_size(bo);
	} else if (bo->preferred_domains == AMDGPU_GEM_DOMAIN_GTT) {
		kfd_mem_limit.system_mem_used -=
			(bo->tbo.acc_size + amdgpu_bo_size(bo));
	}
	WARN_ONCE(kfd_mem_limit.system_mem_used < 0,
		  "kfd system memory accounting unbalanced");
	WARN_ONCE(kfd_mem_limit.userptr_mem_used < 0,
		  "kfd userptr memory accounting unbalanced");

	spin_unlock(&kfd_mem_limit.mem_limit_lock);
}


/* amdgpu_amdkfd_remove_eviction_fence - Removes eviction fence(s) from BO's
 *  reservation object.
 *
 * @bo: [IN] Remove eviction fence(s) from this BO
 * @ef: [IN] If ef is specified, then this eviction fence is removed if it
 *  is present in the shared list.
 * @ef_list: [OUT] Returns list of eviction fences. These fences are removed
 *  from BO's reservation object shared list.
 * @ef_count: [OUT] Number of fences in ef_list.
 *
 * NOTE: If called with ef_list, then amdgpu_amdkfd_add_eviction_fence must be
 *  called to restore the eviction fences and to avoid memory leak. This is
 *  useful for shared BOs.
 * NOTE: Must be called with BO reserved i.e. bo->tbo.resv->lock held.
 */
static int amdgpu_amdkfd_remove_eviction_fence(struct amdgpu_bo *bo,
					struct amdgpu_amdkfd_fence *ef,
					struct amdgpu_amdkfd_fence ***ef_list,
					unsigned int *ef_count)
{
	struct reservation_object *resv = bo->tbo.resv;
	struct reservation_object_list *old, *new;
	unsigned int i, j, k;

	if (!ef && !ef_list)
		return -EINVAL;

	if (ef_list) {
		*ef_list = NULL;
		*ef_count = 0;
	}

	old = reservation_object_get_list(resv);
	if (!old)
		return 0;

	new = kmalloc(offsetof(typeof(*new), shared[old->shared_max]),
		      GFP_KERNEL);
	if (!new)
		return -ENOMEM;

	/* Go through all the shared fences in the resevation object and sort
	 * the interesting ones to the end of the list.
	 */
	for (i = 0, j = old->shared_count, k = 0; i < old->shared_count; ++i) {
		struct dma_fence *f;

		f = rcu_dereference_protected(old->shared[i],
					      reservation_object_held(resv));

		if ((ef && f->context == ef->base.context) ||
		    (!ef && to_amdgpu_amdkfd_fence(f)))
			RCU_INIT_POINTER(new->shared[--j], f);
		else
			RCU_INIT_POINTER(new->shared[k++], f);
	}
	new->shared_max = old->shared_max;
	new->shared_count = k;

	if (!ef) {
		unsigned int count = old->shared_count - j;

		/* Alloc memory for count number of eviction fence pointers.
		 * Fill the ef_list array and ef_count
		 */
		*ef_list = kcalloc(count, sizeof(**ef_list), GFP_KERNEL);
		*ef_count = count;

		if (!*ef_list) {
			kfree(new);
			return -ENOMEM;
		}
	}

	/* Install the new fence list, seqcount provides the barriers */
	preempt_disable();
	write_seqcount_begin(&resv->seq);
	RCU_INIT_POINTER(resv->fence, new);
	write_seqcount_end(&resv->seq);
	preempt_enable();

	/* Drop the references to the removed fences or move them to ef_list */
	for (i = j, k = 0; i < old->shared_count; ++i) {
		struct dma_fence *f;

		f = rcu_dereference_protected(new->shared[i],
					      reservation_object_held(resv));
		if (!ef)
			(*ef_list)[k++] = to_amdgpu_amdkfd_fence(f);
		else
			dma_fence_put(f);
	}
	kfree_rcu(old, rcu);

	return 0;
}

/* amdgpu_amdkfd_add_eviction_fence - Adds eviction fence(s) back into BO's
 *  reservation object.
 *
 * @bo: [IN] Add eviction fences to this BO
 * @ef_list: [IN] List of eviction fences to be added
 * @ef_count: [IN] Number of fences in ef_list.
 *
 * NOTE: Must call amdgpu_amdkfd_remove_eviction_fence before calling this
 *  function.
 */
static void amdgpu_amdkfd_add_eviction_fence(struct amdgpu_bo *bo,
				struct amdgpu_amdkfd_fence **ef_list,
				unsigned int ef_count)
{
	int i;

	if (!ef_list || !ef_count)
		return;

	for (i = 0; i < ef_count; i++) {
		amdgpu_bo_fence(bo, &ef_list[i]->base, true);
		/* Re-adding the fence takes an additional reference. Drop that
		 * reference.
		 */
		dma_fence_put(&ef_list[i]->base);
	}

	kfree(ef_list);
}

static int amdgpu_amdkfd_bo_validate(struct amdgpu_bo *bo, uint32_t domain,
				     bool wait)
{
	struct ttm_operation_ctx ctx = { false, false };
	int ret;

	if (WARN(amdgpu_ttm_tt_get_usermm(bo->tbo.ttm),
		 "Called with userptr BO"))
		return -EINVAL;

	amdgpu_bo_placement_from_domain(bo, domain);

	ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
	if (ret)
		goto validate_fail;
	if (wait) {
		struct amdgpu_amdkfd_fence **ef_list;
		unsigned int ef_count;

		ret = amdgpu_amdkfd_remove_eviction_fence(bo, NULL, &ef_list,
							  &ef_count);
		if (ret)
			goto validate_fail;

		ttm_bo_wait(&bo->tbo, false, false);
		amdgpu_amdkfd_add_eviction_fence(bo, ef_list, ef_count);
	}

validate_fail:
	return ret;
}

static int amdgpu_amdkfd_validate(void *param, struct amdgpu_bo *bo)
{
	struct amdgpu_vm_parser *p = param;

	return amdgpu_amdkfd_bo_validate(bo, p->domain, p->wait);
}

/* vm_validate_pt_pd_bos - Validate page table and directory BOs
 *
 * Page directories are not updated here because huge page handling
 * during page table updates can invalidate page directory entries
 * again. Page directories are only updated after updating page
 * tables.
 */
static int vm_validate_pt_pd_bos(struct amdgpu_vm *vm)
{
	struct amdgpu_bo *pd = vm->root.base.bo;
	struct amdgpu_device *adev = amdgpu_ttm_adev(pd->tbo.bdev);
	struct amdgpu_vm_parser param;
	int ret;

	param.domain = AMDGPU_GEM_DOMAIN_VRAM;
	param.wait = false;

	ret = amdgpu_vm_validate_pt_bos(adev, vm, amdgpu_amdkfd_validate,
					&param);
	if (ret) {
		pr_err("amdgpu: failed to validate PT BOs\n");
		return ret;
	}

	ret = amdgpu_amdkfd_validate(&param, pd);
	if (ret) {
		pr_err("amdgpu: failed to validate PD\n");
		return ret;
	}

	vm->pd_phys_addr = amdgpu_gmc_pd_addr(vm->root.base.bo);

	if (vm->use_cpu_for_update) {
		ret = amdgpu_bo_kmap(pd, NULL);
		if (ret) {
			pr_err("amdgpu: failed to kmap PD, ret=%d\n", ret);
			return ret;
		}
	}

	return 0;
}

static int sync_vm_fence(struct amdgpu_device *adev, struct amdgpu_sync *sync,
			 struct dma_fence *f)
{
	int ret = amdgpu_sync_fence(adev, sync, f, false);

	/* Sync objects can't handle multiple GPUs (contexts) updating
	 * sync->last_vm_update. Fortunately we don't need it for
	 * KFD's purposes, so we can just drop that fence.
	 */
	if (sync->last_vm_update) {
		dma_fence_put(sync->last_vm_update);
		sync->last_vm_update = NULL;
	}

	return ret;
}

static int vm_update_pds(struct amdgpu_vm *vm, struct amdgpu_sync *sync)
{
	struct amdgpu_bo *pd = vm->root.base.bo;
	struct amdgpu_device *adev = amdgpu_ttm_adev(pd->tbo.bdev);
	int ret;

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

	return sync_vm_fence(adev, sync, vm->last_update);
}

/* add_bo_to_vm - Add a BO to a VM
 *
 * Everything that needs to bo done only once when a BO is first added
 * to a VM. It can later be mapped and unmapped many times without
 * repeating these steps.
 *
 * 1. Allocate and initialize BO VA entry data structure
 * 2. Add BO to the VM
 * 3. Determine ASIC-specific PTE flags
 * 4. Alloc page tables and directories if needed
 * 4a.  Validate new page tables and directories
 */
static int add_bo_to_vm(struct amdgpu_device *adev, struct kgd_mem *mem,
		struct amdgpu_vm *vm, bool is_aql,
		struct kfd_bo_va_list **p_bo_va_entry)
{
	int ret;
	struct kfd_bo_va_list *bo_va_entry;
	struct amdgpu_bo *pd = vm->root.base.bo;
	struct amdgpu_bo *bo = mem->bo;
	uint64_t va = mem->va;
	struct list_head *list_bo_va = &mem->bo_va_list;
	unsigned long bo_size = bo->tbo.mem.size;

	if (!va) {
		pr_err("Invalid VA when adding BO to VM\n");
		return -EINVAL;
	}

	if (is_aql)
		va += bo_size;

	bo_va_entry = kzalloc(sizeof(*bo_va_entry), GFP_KERNEL);
	if (!bo_va_entry)
		return -ENOMEM;

	pr_debug("\t add VA 0x%llx - 0x%llx to vm %p\n", va,
			va + bo_size, vm);

	/* Add BO to VM internal data structures*/
	bo_va_entry->bo_va = amdgpu_vm_bo_add(adev, vm, bo);
	if (!bo_va_entry->bo_va) {
		ret = -EINVAL;
		pr_err("Failed to add BO object to VM. ret == %d\n",
				ret);
		goto err_vmadd;
	}

	bo_va_entry->va = va;
	bo_va_entry->pte_flags = amdgpu_gmc_get_pte_flags(adev,
							 mem->mapping_flags);
	bo_va_entry->kgd_dev = (void *)adev;
	list_add(&bo_va_entry->bo_list, list_bo_va);

	if (p_bo_va_entry)
		*p_bo_va_entry = bo_va_entry;

	/* Allocate new page tables if needed and validate
	 * them. Clearing of new page tables and validate need to wait
	 * on move fences. We don't want that to trigger the eviction
	 * fence, so remove it temporarily.
	 */
	amdgpu_amdkfd_remove_eviction_fence(pd,
					vm->process_info->eviction_fence,
					NULL, NULL);

	ret = amdgpu_vm_alloc_pts(adev, vm, va, amdgpu_bo_size(bo));
	if (ret) {
		pr_err("Failed to allocate pts, err=%d\n", ret);
		goto err_alloc_pts;
	}

	ret = vm_validate_pt_pd_bos(vm);
	if (ret) {
		pr_err("validate_pt_pd_bos() failed\n");
		goto err_alloc_pts;
	}

	/* Add the eviction fence back */
	amdgpu_bo_fence(pd, &vm->process_info->eviction_fence->base, true);

	return 0;

err_alloc_pts:
	amdgpu_bo_fence(pd, &vm->process_info->eviction_fence->base, true);
	amdgpu_vm_bo_rmv(adev, bo_va_entry->bo_va);
	list_del(&bo_va_entry->bo_list);
err_vmadd:
	kfree(bo_va_entry);
	return ret;
}

static void remove_bo_from_vm(struct amdgpu_device *adev,
		struct kfd_bo_va_list *entry, unsigned long size)
{
	pr_debug("\t remove VA 0x%llx - 0x%llx in entry %p\n",
			entry->va,
			entry->va + size, entry);
	amdgpu_vm_bo_rmv(adev, entry->bo_va);
	list_del(&entry->bo_list);
	kfree(entry);
}

static void add_kgd_mem_to_kfd_bo_list(struct kgd_mem *mem,
				struct amdkfd_process_info *process_info,
				bool userptr)
{
	struct ttm_validate_buffer *entry = &mem->validate_list;
	struct amdgpu_bo *bo = mem->bo;

	INIT_LIST_HEAD(&entry->head);
	entry->shared = true;
	entry->bo = &bo->tbo;
	mutex_lock(&process_info->lock);
	if (userptr)
		list_add_tail(&entry->head, &process_info->userptr_valid_list);
	else
		list_add_tail(&entry->head, &process_info->kfd_bo_list);
	mutex_unlock(&process_info->lock);
}

/* Initializes user pages. It registers the MMU notifier and validates
 * the userptr BO in the GTT domain.
 *
 * The BO must already be on the userptr_valid_list. Otherwise an
 * eviction and restore may happen that leaves the new BO unmapped
 * with the user mode queues running.
 *
 * Takes the process_info->lock to protect against concurrent restore
 * workers.
 *
 * Returns 0 for success, negative errno for errors.
 */
static int init_user_pages(struct kgd_mem *mem, struct mm_struct *mm,
			   uint64_t user_addr)
{
	struct amdkfd_process_info *process_info = mem->process_info;
	struct amdgpu_bo *bo = mem->bo;
	struct ttm_operation_ctx ctx = { true, false };
	int ret = 0;

	mutex_lock(&process_info->lock);

	ret = amdgpu_ttm_tt_set_userptr(bo->tbo.ttm, user_addr, 0);
	if (ret) {
		pr_err("%s: Failed to set userptr: %d\n", __func__, ret);
		goto out;
	}

	ret = amdgpu_mn_register(bo, user_addr);
	if (ret) {
		pr_err("%s: Failed to register MMU notifier: %d\n",
		       __func__, ret);
		goto out;
	}

	/* If no restore worker is running concurrently, user_pages
	 * should not be allocated
	 */
	WARN(mem->user_pages, "Leaking user_pages array");

	mem->user_pages = kvmalloc_array(bo->tbo.ttm->num_pages,
					   sizeof(struct page *),
					   GFP_KERNEL | __GFP_ZERO);
	if (!mem->user_pages) {
		pr_err("%s: Failed to allocate pages array\n", __func__);
		ret = -ENOMEM;
		goto unregister_out;
	}

	ret = amdgpu_ttm_tt_get_user_pages(bo->tbo.ttm, mem->user_pages);
	if (ret) {
		pr_err("%s: Failed to get user pages: %d\n", __func__, ret);
		goto free_out;
	}

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

	ret = amdgpu_bo_reserve(bo, true);
	if (ret) {
		pr_err("%s: Failed to reserve BO\n", __func__);
		goto release_out;
	}
	amdgpu_bo_placement_from_domain(bo, mem->domain);
	ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
	if (ret)
		pr_err("%s: failed to validate BO\n", __func__);
	amdgpu_bo_unreserve(bo);

release_out:
	if (ret)
		release_pages(mem->user_pages, bo->tbo.ttm->num_pages);
free_out:
	kvfree(mem->user_pages);
	mem->user_pages = NULL;
unregister_out:
	if (ret)
		amdgpu_mn_unregister(bo);
out:
	mutex_unlock(&process_info->lock);
	return ret;
}

/* Reserving a BO and its page table BOs must happen atomically to
 * avoid deadlocks. Some operations update multiple VMs at once. Track
 * all the reservation info in a context structure. Optionally a sync
 * object can track VM updates.
 */
struct bo_vm_reservation_context {
	struct amdgpu_bo_list_entry kfd_bo; /* BO list entry for the KFD BO */
	unsigned int n_vms;		    /* Number of VMs reserved	    */
	struct amdgpu_bo_list_entry *vm_pd; /* Array of VM BO list entries  */
	struct ww_acquire_ctx ticket;	    /* Reservation ticket	    */
	struct list_head list, duplicates;  /* BO lists			    */
	struct amdgpu_sync *sync;	    /* Pointer to sync object	    */
	bool reserved;			    /* Whether BOs are reserved	    */
};

enum bo_vm_match {
	BO_VM_NOT_MAPPED = 0,	/* Match VMs where a BO is not mapped */
	BO_VM_MAPPED,		/* Match VMs where a BO is mapped     */
	BO_VM_ALL,		/* Match all VMs a BO was added to    */
};

/**
 * reserve_bo_and_vm - reserve a BO and a VM unconditionally.
 * @mem: KFD BO structure.
 * @vm: the VM to reserve.
 * @ctx: the struct that will be used in unreserve_bo_and_vms().
 */
static int reserve_bo_and_vm(struct kgd_mem *mem,
			      struct amdgpu_vm *vm,
			      struct bo_vm_reservation_context *ctx)
{
	struct amdgpu_bo *bo = mem->bo;
	int ret;

	WARN_ON(!vm);

	ctx->reserved = false;
	ctx->n_vms = 1;
	ctx->sync = &mem->sync;

	INIT_LIST_HEAD(&ctx->list);
	INIT_LIST_HEAD(&ctx->duplicates);

	ctx->vm_pd = kcalloc(ctx->n_vms, sizeof(*ctx->vm_pd), GFP_KERNEL);
	if (!ctx->vm_pd)
		return -ENOMEM;

	ctx->kfd_bo.priority = 0;
	ctx->kfd_bo.tv.bo = &bo->tbo;
	ctx->kfd_bo.tv.shared = true;
	ctx->kfd_bo.user_pages = NULL;
	list_add(&ctx->kfd_bo.tv.head, &ctx->list);

	amdgpu_vm_get_pd_bo(vm, &ctx->list, &ctx->vm_pd[0]);

	ret = ttm_eu_reserve_buffers(&ctx->ticket, &ctx->list,
				     false, &ctx->duplicates);
	if (!ret)
		ctx->reserved = true;
	else {
		pr_err("Failed to reserve buffers in ttm\n");
		kfree(ctx->vm_pd);
		ctx->vm_pd = NULL;
	}

	return ret;
}

/**
 * reserve_bo_and_cond_vms - reserve a BO and some VMs conditionally
 * @mem: KFD BO structure.
 * @vm: the VM to reserve. If NULL, then all VMs associated with the BO
 * is used. Otherwise, a single VM associated with the BO.
 * @map_type: the mapping status that will be used to filter the VMs.
 * @ctx: the struct that will be used in unreserve_bo_and_vms().
 *
 * Returns 0 for success, negative for failure.
 */
static int reserve_bo_and_cond_vms(struct kgd_mem *mem,
				struct amdgpu_vm *vm, enum bo_vm_match map_type,
				struct bo_vm_reservation_context *ctx)
{
	struct amdgpu_bo *bo = mem->bo;
	struct kfd_bo_va_list *entry;
	unsigned int i;
	int ret;

	ctx->reserved = false;
	ctx->n_vms = 0;
	ctx->vm_pd = NULL;
	ctx->sync = &mem->sync;

	INIT_LIST_HEAD(&ctx->list);
	INIT_LIST_HEAD(&ctx->duplicates);

	list_for_each_entry(entry, &mem->bo_va_list, bo_list) {
		if ((vm && vm != entry->bo_va->base.vm) ||
			(entry->is_mapped != map_type
			&& map_type != BO_VM_ALL))
			continue;

		ctx->n_vms++;
	}

	if (ctx->n_vms != 0) {
		ctx->vm_pd = kcalloc(ctx->n_vms, sizeof(*ctx->vm_pd),
				     GFP_KERNEL);
		if (!ctx->vm_pd)
			return -ENOMEM;
	}

	ctx->kfd_bo.priority = 0;
	ctx->kfd_bo.tv.bo = &bo->tbo;
	ctx->kfd_bo.tv.shared = true;
	ctx->kfd_bo.user_pages = NULL;
	list_add(&ctx->kfd_bo.tv.head, &ctx->list);

	i = 0;
	list_for_each_entry(entry, &mem->bo_va_list, bo_list) {
		if ((vm && vm != entry->bo_va->base.vm) ||
			(entry->is_mapped != map_type
			&& map_type != BO_VM_ALL))
			continue;

		amdgpu_vm_get_pd_bo(entry->bo_va->base.vm, &ctx->list,
				&ctx->vm_pd[i]);
		i++;
	}

	ret = ttm_eu_reserve_buffers(&ctx->ticket, &ctx->list,
				     false, &ctx->duplicates);
	if (!ret)
		ctx->reserved = true;
	else
		pr_err("Failed to reserve buffers in ttm.\n");

	if (ret) {
		kfree(ctx->vm_pd);
		ctx->vm_pd = NULL;
	}

	return ret;
}

/**
 * unreserve_bo_and_vms - Unreserve BO and VMs from a reservation context
 * @ctx: Reservation context to unreserve
 * @wait: Optionally wait for a sync object representing pending VM updates
 * @intr: Whether the wait is interruptible
 *
 * Also frees any resources allocated in
 * reserve_bo_and_(cond_)vm(s). Returns the status from
 * amdgpu_sync_wait.
 */
static int unreserve_bo_and_vms(struct bo_vm_reservation_context *ctx,
				 bool wait, bool intr)
{
	int ret = 0;

	if (wait)
		ret = amdgpu_sync_wait(ctx->sync, intr);

	if (ctx->reserved)
		ttm_eu_backoff_reservation(&ctx->ticket, &ctx->list);
	kfree(ctx->vm_pd);

	ctx->sync = NULL;

	ctx->reserved = false;
	ctx->vm_pd = NULL;

	return ret;
}

static int unmap_bo_from_gpuvm(struct amdgpu_device *adev,
				struct kfd_bo_va_list *entry,
				struct amdgpu_sync *sync)
{
	struct amdgpu_bo_va *bo_va = entry->bo_va;
	struct amdgpu_vm *vm = bo_va->base.vm;
	struct amdgpu_bo *pd = vm->root.base.bo;

	/* Remove eviction fence from PD (and thereby from PTs too as
	 * they share the resv. object). Otherwise during PT update
	 * job (see amdgpu_vm_bo_update_mapping), eviction fence would
	 * get added to job->sync object and job execution would
	 * trigger the eviction fence.
	 */
	amdgpu_amdkfd_remove_eviction_fence(pd,
					    vm->process_info->eviction_fence,
					    NULL, NULL);
	amdgpu_vm_bo_unmap(adev, bo_va, entry->va);

	amdgpu_vm_clear_freed(adev, vm, &bo_va->last_pt_update);

	/* Add the eviction fence back */
	amdgpu_bo_fence(pd, &vm->process_info->eviction_fence->base, true);

	sync_vm_fence(adev, sync, bo_va->last_pt_update);

	return 0;
}

static int update_gpuvm_pte(struct amdgpu_device *adev,
		struct kfd_bo_va_list *entry,
		struct amdgpu_sync *sync)
{
	int ret;
	struct amdgpu_vm *vm;
	struct amdgpu_bo_va *bo_va;
	struct amdgpu_bo *bo;

	bo_va = entry->bo_va;
	vm = bo_va->base.vm;
	bo = bo_va->base.bo;

	/* Update the page tables  */
	ret = amdgpu_vm_bo_update(adev, bo_va, false);
	if (ret) {
		pr_err("amdgpu_vm_bo_update failed\n");
		return ret;
	}

	return sync_vm_fence(adev, sync, bo_va->last_pt_update);
}

static int map_bo_to_gpuvm(struct amdgpu_device *adev,
		struct kfd_bo_va_list *entry, struct amdgpu_sync *sync,
		bool no_update_pte)
{
	int ret;

	/* Set virtual address for the allocation */
	ret = amdgpu_vm_bo_map(adev, entry->bo_va, entry->va, 0,
			       amdgpu_bo_size(entry->bo_va->base.bo),
			       entry->pte_flags);
	if (ret) {
		pr_err("Failed to map VA 0x%llx in vm. ret %d\n",
				entry->va, ret);
		return ret;
	}

	if (no_update_pte)
		return 0;

	ret = update_gpuvm_pte(adev, entry, sync);
	if (ret) {
		pr_err("update_gpuvm_pte() failed\n");
		goto update_gpuvm_pte_failed;
	}

	return 0;

update_gpuvm_pte_failed:
	unmap_bo_from_gpuvm(adev, entry, sync);
	return ret;
}

static int process_validate_vms(struct amdkfd_process_info *process_info)
{
	struct amdgpu_vm *peer_vm;
	int ret;

	list_for_each_entry(peer_vm, &process_info->vm_list_head,
			    vm_list_node) {
		ret = vm_validate_pt_pd_bos(peer_vm);
		if (ret)
			return ret;
	}

	return 0;
}

static int process_update_pds(struct amdkfd_process_info *process_info,
			      struct amdgpu_sync *sync)
{
	struct amdgpu_vm *peer_vm;
	int ret;

	list_for_each_entry(peer_vm, &process_info->vm_list_head,
			    vm_list_node) {
		ret = vm_update_pds(peer_vm, sync);
		if (ret)
			return ret;
	}

	return 0;
}

static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info,
		       struct dma_fence **ef)
{
	struct amdkfd_process_info *info = NULL;
	int ret;

	if (!*process_info) {
		info = kzalloc(sizeof(*info), GFP_KERNEL);
		if (!info)
			return -ENOMEM;

		mutex_init(&info->lock);
		INIT_LIST_HEAD(&info->vm_list_head);
		INIT_LIST_HEAD(&info->kfd_bo_list);
		INIT_LIST_HEAD(&info->userptr_valid_list);
		INIT_LIST_HEAD(&info->userptr_inval_list);

		info->eviction_fence =
			amdgpu_amdkfd_fence_create(dma_fence_context_alloc(1),
						   current->mm);
		if (!info->eviction_fence) {
			pr_err("Failed to create eviction fence\n");
			ret = -ENOMEM;
			goto create_evict_fence_fail;
		}

		info->pid = get_task_pid(current->group_leader, PIDTYPE_PID);
		atomic_set(&info->evicted_bos, 0);
		INIT_DELAYED_WORK(&info->restore_userptr_work,
				  amdgpu_amdkfd_restore_userptr_worker);

		*process_info = info;
		*ef = dma_fence_get(&info->eviction_fence->base);
	}

	vm->process_info = *process_info;

	/* Validate page directory and attach eviction fence */
	ret = amdgpu_bo_reserve(vm->root.base.bo, true);
	if (ret)
		goto reserve_pd_fail;
	ret = vm_validate_pt_pd_bos(vm);
	if (ret) {
		pr_err("validate_pt_pd_bos() failed\n");
		goto validate_pd_fail;
	}
	ret = ttm_bo_wait(&vm->root.base.bo->tbo, false, false);
	if (ret)
		goto wait_pd_fail;
	amdgpu_bo_fence(vm->root.base.bo,
			&vm->process_info->eviction_fence->base, true);
	amdgpu_bo_unreserve(vm->root.base.bo);

	/* Update process info */
	mutex_lock(&vm->process_info->lock);
	list_add_tail(&vm->vm_list_node,
			&(vm->process_info->vm_list_head));
	vm->process_info->n_vms++;
	mutex_unlock(&vm->process_info->lock);

	return 0;

wait_pd_fail:
validate_pd_fail:
	amdgpu_bo_unreserve(vm->root.base.bo);
reserve_pd_fail:
	vm->process_info = NULL;
	if (info) {
		/* Two fence references: one in info and one in *ef */
		dma_fence_put(&info->eviction_fence->base);
		dma_fence_put(*ef);
		*ef = NULL;
		*process_info = NULL;
		put_pid(info->pid);
create_evict_fence_fail:
		mutex_destroy(&info->lock);
		kfree(info);
	}
	return ret;
}

int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, unsigned int pasid,
					  void **vm, void **process_info,
					  struct dma_fence **ef)
{
	struct amdgpu_device *adev = get_amdgpu_device(kgd);
	struct amdgpu_vm *new_vm;
	int ret;

	new_vm = kzalloc(sizeof(*new_vm), GFP_KERNEL);
	if (!new_vm)
		return -ENOMEM;

	/* Initialize AMDGPU part of the VM */
	ret = amdgpu_vm_init(adev, new_vm, AMDGPU_VM_CONTEXT_COMPUTE, pasid);
	if (ret) {
		pr_err("Failed init vm ret %d\n", ret);
		goto amdgpu_vm_init_fail;
	}

	/* Initialize KFD part of the VM and process info */
	ret = init_kfd_vm(new_vm, process_info, ef);
	if (ret)
		goto init_kfd_vm_fail;

	*vm = (void *) new_vm;

	return 0;

init_kfd_vm_fail:
	amdgpu_vm_fini(adev, new_vm);
amdgpu_vm_init_fail:
	kfree(new_vm);
	return ret;
}

int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd,
					   struct file *filp, unsigned int pasid,
					   void **vm, void **process_info,
					   struct dma_fence **ef)
{
	struct amdgpu_device *adev = get_amdgpu_device(kgd);
	struct drm_file *drm_priv = filp->private_data;
	struct amdgpu_fpriv *drv_priv = drm_priv->driver_priv;
	struct amdgpu_vm *avm = &drv_priv->vm;
	int ret;

	/* Already a compute VM? */
	if (avm->process_info)
		return -EINVAL;

	/* Convert VM into a compute VM */
	ret = amdgpu_vm_make_compute(adev, avm, pasid);
	if (ret)
		return ret;

	/* Initialize KFD part of the VM and process info */
	ret = init_kfd_vm(avm, process_info, ef);
	if (ret)
		return ret;

	*vm = (void *)avm;

	return 0;
}

void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
				    struct amdgpu_vm *vm)
{
	struct amdkfd_process_info *process_info = vm->process_info;
	struct amdgpu_bo *pd = vm->root.base.bo;

	if (!process_info)
		return;

	/* Release eviction fence from PD */
	amdgpu_bo_reserve(pd, false);
	amdgpu_bo_fence(pd, NULL, false);
	amdgpu_bo_unreserve(pd);

	/* Update process info */
	mutex_lock(&process_info->lock);
	process_info->n_vms--;
	list_del(&vm->vm_list_node);
	mutex_unlock(&process_info->lock);

	/* Release per-process resources when last compute VM is destroyed */
	if (!process_info->n_vms) {
		WARN_ON(!list_empty(&process_info->kfd_bo_list));
		WARN_ON(!list_empty(&process_info->userptr_valid_list));
		WARN_ON(!list_empty(&process_info->userptr_inval_list));

		dma_fence_put(&process_info->eviction_fence->base);
		cancel_delayed_work_sync(&process_info->restore_userptr_work);
		put_pid(process_info->pid);
		mutex_destroy(&process_info->lock);
		kfree(process_info);
	}
}

void amdgpu_amdkfd_gpuvm_destroy_process_vm(struct kgd_dev *kgd, void *vm)
{
	struct amdgpu_device *adev = get_amdgpu_device(kgd);
	struct amdgpu_vm *avm = (struct amdgpu_vm *)vm;

	if (WARN_ON(!kgd || !vm))
		return;

	pr_debug("Destroying process vm %p\n", vm);

	/* Release the VM context */
	amdgpu_vm_fini(adev, avm);
	kfree(vm);
}

void amdgpu_amdkfd_gpuvm_release_process_vm(struct kgd_dev *kgd, void *vm)
{
	struct amdgpu_device *adev = get_amdgpu_device(kgd);
        struct amdgpu_vm *avm = (struct amdgpu_vm *)vm;

	if (WARN_ON(!kgd || !vm))
                return;

        pr_debug("Releasing process vm %p\n", vm);

        /* The original pasid of amdgpu vm has already been
         * released during making a amdgpu vm to a compute vm
         * The current pasid is managed by kfd and will be
         * released on kfd process destroy. Set amdgpu pasid
         * to 0 to avoid duplicate release.
         */
	amdgpu_vm_release_compute(adev, avm);
}

uint64_t amdgpu_amdkfd_gpuvm_get_process_page_dir(void *vm)
{
	struct amdgpu_vm *avm = (struct amdgpu_vm *)vm;
	struct amdgpu_bo *pd = avm->root.base.bo;
	struct amdgpu_device *adev = amdgpu_ttm_adev(pd->tbo.bdev);

	if (adev->asic_type < CHIP_VEGA10)
		return avm->pd_phys_addr >> AMDGPU_GPU_PAGE_SHIFT;
	return avm->pd_phys_addr;
}

int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
		struct kgd_dev *kgd, uint64_t va, uint64_t size,
		void *vm, struct kgd_mem **mem,
		uint64_t *offset, uint32_t flags)
{
	struct amdgpu_device *adev = get_amdgpu_device(kgd);
	struct amdgpu_vm *avm = (struct amdgpu_vm *)vm;
	uint64_t user_addr = 0;
	struct amdgpu_bo *bo;
	struct amdgpu_bo_param bp;
	int byte_align;
	u32 domain, alloc_domain;
	u64 alloc_flags;
	uint32_t mapping_flags;
	int ret;

	/*
	 * Check on which domain to allocate BO
	 */
	if (flags & ALLOC_MEM_FLAGS_VRAM) {
		domain = alloc_domain = AMDGPU_GEM_DOMAIN_VRAM;
		alloc_flags = AMDGPU_GEM_CREATE_VRAM_CLEARED;
		alloc_flags |= (flags & ALLOC_MEM_FLAGS_PUBLIC) ?
			AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED :
			AMDGPU_GEM_CREATE_NO_CPU_ACCESS;
	} else if (flags & ALLOC_MEM_FLAGS_GTT) {
		domain = alloc_domain = AMDGPU_GEM_DOMAIN_GTT;
		alloc_flags = 0;
	} else if (flags & ALLOC_MEM_FLAGS_USERPTR) {
		domain = AMDGPU_GEM_DOMAIN_GTT;
		alloc_domain = AMDGPU_GEM_DOMAIN_CPU;
		alloc_flags = 0;
		if (!offset || !*offset)
			return -EINVAL;
		user_addr = *offset;
	} else {
		return -EINVAL;
	}

	*mem = kzalloc(sizeof(struct kgd_mem), GFP_KERNEL);
	if (!*mem)
		return -ENOMEM;
	INIT_LIST_HEAD(&(*mem)->bo_va_list);
	mutex_init(&(*mem)->lock);
	(*mem)->aql_queue = !!(flags & ALLOC_MEM_FLAGS_AQL_QUEUE_MEM);

	/* Workaround for AQL queue wraparound bug. Map the same
	 * memory twice. That means we only actually allocate half
	 * the memory.
	 */
	if ((*mem)->aql_queue)
		size = size >> 1;

	/* Workaround for TLB bug on older VI chips */
	byte_align = (adev->family == AMDGPU_FAMILY_VI &&
			adev->asic_type != CHIP_FIJI &&
			adev->asic_type != CHIP_POLARIS10 &&
			adev->asic_type != CHIP_POLARIS11) ?
			VI_BO_SIZE_ALIGN : 1;

	mapping_flags = AMDGPU_VM_PAGE_READABLE;
	if (flags & ALLOC_MEM_FLAGS_WRITABLE)
		mapping_flags |= AMDGPU_VM_PAGE_WRITEABLE;
	if (flags & ALLOC_MEM_FLAGS_EXECUTABLE)
		mapping_flags |= AMDGPU_VM_PAGE_EXECUTABLE;
	if (flags & ALLOC_MEM_FLAGS_COHERENT)
		mapping_flags |= AMDGPU_VM_MTYPE_UC;
	else
		mapping_flags |= AMDGPU_VM_MTYPE_NC;
	(*mem)->mapping_flags = mapping_flags;

	amdgpu_sync_create(&(*mem)->sync);

	ret = amdgpu_amdkfd_reserve_system_mem_limit(adev, size, alloc_domain);
	if (ret) {
		pr_debug("Insufficient system memory\n");
		goto err_reserve_system_mem;
	}

	pr_debug("\tcreate BO VA 0x%llx size 0x%llx domain %s\n",
			va, size, domain_string(alloc_domain));

	memset(&bp, 0, sizeof(bp));
	bp.size = size;
	bp.byte_align = byte_align;
	bp.domain = alloc_domain;
	bp.flags = alloc_flags;
	bp.type = ttm_bo_type_device;
	bp.resv = NULL;
	ret = amdgpu_bo_create(adev, &bp, &bo);
	if (ret) {
		pr_debug("Failed to create BO on domain %s. ret %d\n",
				domain_string(alloc_domain), ret);
		goto err_bo_create;
	}
	bo->kfd_bo = *mem;
	(*mem)->bo = bo;
	if (user_addr)
		bo->flags |= AMDGPU_AMDKFD_USERPTR_BO;

	(*mem)->va = va;
	(*mem)->domain = domain;
	(*mem)->mapped_to_gpu_memory = 0;
	(*mem)->process_info = avm->process_info;
	add_kgd_mem_to_kfd_bo_list(*mem, avm->process_info, user_addr);

	if (user_addr) {
		ret = init_user_pages(*mem, current->mm, user_addr);
		if (ret) {
			mutex_lock(&avm->process_info->lock);
			list_del(&(*mem)->validate_list.head);
			mutex_unlock(&avm->process_info->lock);
			goto allocate_init_user_pages_failed;
		}
	}

	if (offset)
		*offset = amdgpu_bo_mmap_offset(bo);

	return 0;

allocate_init_user_pages_failed:
	amdgpu_bo_unref(&bo);
	/* Don't unreserve system mem limit twice */
	goto err_reserve_system_mem;
err_bo_create:
	unreserve_system_mem_limit(adev, size, alloc_domain);
err_reserve_system_mem:
	mutex_destroy(&(*mem)->lock);
	kfree(*mem);
	return ret;
}

int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
		struct kgd_dev *kgd, struct kgd_mem *mem)
{
	struct amdkfd_process_info *process_info = mem->process_info;
	unsigned long bo_size = mem->bo->tbo.mem.size;
	struct kfd_bo_va_list *entry, *tmp;
	struct bo_vm_reservation_context ctx;
	struct ttm_validate_buffer *bo_list_entry;
	int ret;

	mutex_lock(&mem->lock);

	if (mem->mapped_to_gpu_memory > 0) {
		pr_debug("BO VA 0x%llx size 0x%lx is still mapped.\n",
				mem->va, bo_size);
		mutex_unlock(&mem->lock);
		return -EBUSY;
	}

	mutex_unlock(&mem->lock);
	/* lock is not needed after this, since mem is unused and will
	 * be freed anyway
	 */

	/* No more MMU notifiers */
	amdgpu_mn_unregister(mem->bo);

	/* Make sure restore workers don't access the BO any more */
	bo_list_entry = &mem->validate_list;
	mutex_lock(&process_info->lock);
	list_del(&bo_list_entry->head);
	mutex_unlock(&process_info->lock);

	/* Free user pages if necessary */
	if (mem->user_pages) {
		pr_debug("%s: Freeing user_pages array\n", __func__);
		if (mem->user_pages[0])
			release_pages(mem->user_pages,
					mem->bo->tbo.ttm->num_pages);
		kvfree(mem->user_pages);
	}

	ret = reserve_bo_and_cond_vms(mem, NULL, BO_VM_ALL, &ctx);
	if (unlikely(ret))
		return ret;

	/* The eviction fence should be removed by the last unmap.
	 * TODO: Log an error condition if the bo still has the eviction fence
	 * attached
	 */
	amdgpu_amdkfd_remove_eviction_fence(mem->bo,
					process_info->eviction_fence,
					NULL, NULL);
	pr_debug("Release VA 0x%llx - 0x%llx\n", mem->va,
		mem->va + bo_size * (1 + mem->aql_queue));

	/* Remove from VM internal data structures */
	list_for_each_entry_safe(entry, tmp, &mem->bo_va_list, bo_list)
		remove_bo_from_vm((struct amdgpu_device *)entry->kgd_dev,
				entry, bo_size);

	ret = unreserve_bo_and_vms(&ctx, false, false);

	/* Free the sync object */
	amdgpu_sync_free(&mem->sync);

	/* Free the BO*/
	amdgpu_bo_unref(&mem->bo);
	mutex_destroy(&mem->lock);
	kfree(mem);

	return ret;
}

int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
		struct kgd_dev *kgd, struct kgd_mem *mem, void *vm)
{
	struct amdgpu_device *adev = get_amdgpu_device(kgd);
	struct amdgpu_vm *avm = (struct amdgpu_vm *)vm;
	int ret;
	struct amdgpu_bo *bo;
	uint32_t domain;
	struct kfd_bo_va_list *entry;
	struct bo_vm_reservation_context ctx;
	struct kfd_bo_va_list *bo_va_entry = NULL;
	struct kfd_bo_va_list *bo_va_entry_aql = NULL;
	unsigned long bo_size;
	bool is_invalid_userptr = false;

	bo = mem->bo;
	if (!bo) {
		pr_err("Invalid BO when mapping memory to GPU\n");
		return -EINVAL;
	}

	/* Make sure restore is not running concurrently. Since we
	 * don't map invalid userptr BOs, we rely on the next restore
	 * worker to do the mapping
	 */
	mutex_lock(&mem->process_info->lock);

	/* Lock mmap-sem. If we find an invalid userptr BO, we can be
	 * sure that the MMU notifier is no longer running
	 * concurrently and the queues are actually stopped
	 */
	if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm)) {
		down_write(&current->mm->mmap_sem);
		is_invalid_userptr = atomic_read(&mem->invalid);
		up_write(&current->mm->mmap_sem);
	}

	mutex_lock(&mem->lock);

	domain = mem->domain;
	bo_size = bo->tbo.mem.size;

	pr_debug("Map VA 0x%llx - 0x%llx to vm %p domain %s\n",
			mem->va,
			mem->va + bo_size * (1 + mem->aql_queue),
			vm, domain_string(domain));

	ret = reserve_bo_and_vm(mem, vm, &ctx);
	if (unlikely(ret))
		goto out;

	/* Userptr can be marked as "not invalid", but not actually be
	 * validated yet (still in the system domain). In that case
	 * the queues are still stopped and we can leave mapping for
	 * the next restore worker
	 */
	if (bo->tbo.mem.mem_type == TTM_PL_SYSTEM)
		is_invalid_userptr = true;

	if (check_if_add_bo_to_vm(avm, mem)) {
		ret = add_bo_to_vm(adev, mem, avm, false,
				&bo_va_entry);
		if (ret)
			goto add_bo_to_vm_failed;
		if (mem->aql_queue) {
			ret = add_bo_to_vm(adev, mem, avm,
					true, &bo_va_entry_aql);
			if (ret)
				goto add_bo_to_vm_failed_aql;
		}
	} else {
		ret = vm_validate_pt_pd_bos(avm);
		if (unlikely(ret))
			goto add_bo_to_vm_failed;
	}

	if (mem->mapped_to_gpu_memory == 0 &&
	    !amdgpu_ttm_tt_get_usermm(bo->tbo.ttm)) {
		/* Validate BO only once. The eviction fence gets added to BO
		 * the first time it is mapped. Validate will wait for all
		 * background evictions to complete.
		 */
		ret = amdgpu_amdkfd_bo_validate(bo, domain, true);
		if (ret) {
			pr_debug("Validate failed\n");
			goto map_bo_to_gpuvm_failed;
		}
	}

	list_for_each_entry(entry, &mem->bo_va_list, bo_list) {
		if (entry->bo_va->base.vm == vm && !entry->is_mapped) {
			pr_debug("\t map VA 0x%llx - 0x%llx in entry %p\n",
					entry->va, entry->va + bo_size,
					entry);

			ret = map_bo_to_gpuvm(adev, entry, ctx.sync,
					      is_invalid_userptr);
			if (ret) {
				pr_err("Failed to map radeon bo to gpuvm\n");
				goto map_bo_to_gpuvm_failed;
			}

			ret = vm_update_pds(vm, ctx.sync);
			if (ret) {
				pr_err("Failed to update page directories\n");
				goto map_bo_to_gpuvm_failed;
			}

			entry->is_mapped = true;
			mem->mapped_to_gpu_memory++;
			pr_debug("\t INC mapping count %d\n",
					mem->mapped_to_gpu_memory);
		}
	}

	if (!amdgpu_ttm_tt_get_usermm(bo->tbo.ttm) && !bo->pin_count)
		amdgpu_bo_fence(bo,
				&avm->process_info->eviction_fence->base,
				true);
	ret = unreserve_bo_and_vms(&ctx, false, false);

	goto out;

map_bo_to_gpuvm_failed:
	if (bo_va_entry_aql)
		remove_bo_from_vm(adev, bo_va_entry_aql, bo_size);
add_bo_to_vm_failed_aql:
	if (bo_va_entry)
		remove_bo_from_vm(adev, bo_va_entry, bo_size);
add_bo_to_vm_failed:
	unreserve_bo_and_vms(&ctx, false, false);
out:
	mutex_unlock(&mem->process_info->lock);
	mutex_unlock(&mem->lock);
	return ret;
}

int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
		struct kgd_dev *kgd, struct kgd_mem *mem, void *vm)
{
	struct amdgpu_device *adev = get_amdgpu_device(kgd);
	struct amdkfd_process_info *process_info =
		((struct amdgpu_vm *)vm)->process_info;
	unsigned long bo_size = mem->bo->tbo.mem.size;
	struct kfd_bo_va_list *entry;
	struct bo_vm_reservation_context ctx;
	int ret;

	mutex_lock(&mem->lock);

	ret = reserve_bo_and_cond_vms(mem, vm, BO_VM_MAPPED, &ctx);
	if (unlikely(ret))
		goto out;
	/* If no VMs were reserved, it means the BO wasn't actually mapped */
	if (ctx.n_vms == 0) {
		ret = -EINVAL;
		goto unreserve_out;
	}

	ret = vm_validate_pt_pd_bos((struct amdgpu_vm *)vm);
	if (unlikely(ret))
		goto unreserve_out;

	pr_debug("Unmap VA 0x%llx - 0x%llx from vm %p\n",
		mem->va,
		mem->va + bo_size * (1 + mem->aql_queue),
		vm);

	list_for_each_entry(entry, &mem->bo_va_list, bo_list) {
		if (entry->bo_va->base.vm == vm && entry->is_mapped) {
			pr_debug("\t unmap VA 0x%llx - 0x%llx from entry %p\n",
					entry->va,
					entry->va + bo_size,
					entry);

			ret = unmap_bo_from_gpuvm(adev, entry, ctx.sync);
			if (ret == 0) {
				entry->is_mapped = false;
			} else {
				pr_err("failed to unmap VA 0x%llx\n",
						mem->va);
				goto unreserve_out;
			}

			mem->mapped_to_gpu_memory--;
			pr_debug("\t DEC mapping count %d\n",
					mem->mapped_to_gpu_memory);
		}
	}

	/* If BO is unmapped from all VMs, unfence it. It can be evicted if
	 * required.
	 */
	if (mem->mapped_to_gpu_memory == 0 &&
	    !amdgpu_ttm_tt_get_usermm(mem->bo->tbo.ttm) && !mem->bo->pin_count)
		amdgpu_amdkfd_remove_eviction_fence(mem->bo,
						process_info->eviction_fence,
						    NULL, NULL);

unreserve_out:
	unreserve_bo_and_vms(&ctx, false, false);
out:
	mutex_unlock(&mem->lock);
	return ret;
}

int amdgpu_amdkfd_gpuvm_sync_memory(
		struct kgd_dev *kgd, struct kgd_mem *mem, bool intr)
{
	struct amdgpu_sync sync;
	int ret;

	amdgpu_sync_create(&sync);

	mutex_lock(&mem->lock);
	amdgpu_sync_clone(&mem->sync, &sync);
	mutex_unlock(&mem->lock);

	ret = amdgpu_sync_wait(&sync, intr);
	amdgpu_sync_free(&sync);
	return ret;
}

int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_dev *kgd,
		struct kgd_mem *mem, void **kptr, uint64_t *size)
{
	int ret;
	struct amdgpu_bo *bo = mem->bo;

	if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm)) {
		pr_err("userptr can't be mapped to kernel\n");
		return -EINVAL;
	}

	/* delete kgd_mem from kfd_bo_list to avoid re-validating
	 * this BO in BO's restoring after eviction.
	 */
	mutex_lock(&mem->process_info->lock);

	ret = amdgpu_bo_reserve(bo, true);
	if (ret) {
		pr_err("Failed to reserve bo. ret %d\n", ret);
		goto bo_reserve_failed;
	}

	ret = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
	if (ret) {
		pr_err("Failed to pin bo. ret %d\n", ret);
		goto pin_failed;
	}

	ret = amdgpu_bo_kmap(bo, kptr);
	if (ret) {
		pr_err("Failed to map bo to kernel. ret %d\n", ret);
		goto kmap_failed;
	}

	amdgpu_amdkfd_remove_eviction_fence(
		bo, mem->process_info->eviction_fence, NULL, NULL);
	list_del_init(&mem->validate_list.head);

	if (size)
		*size = amdgpu_bo_size(bo);

	amdgpu_bo_unreserve(bo);

	mutex_unlock(&mem->process_info->lock);
	return 0;

kmap_failed:
	amdgpu_bo_unpin(bo);
pin_failed:
	amdgpu_bo_unreserve(bo);
bo_reserve_failed:
	mutex_unlock(&mem->process_info->lock);

	return ret;
}

int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd,
					      struct kfd_vm_fault_info *mem)
{
	struct amdgpu_device *adev;

	adev = (struct amdgpu_device *)kgd;
	if (atomic_read(&adev->gmc.vm_fault_info_updated) == 1) {
		*mem = *adev->gmc.vm_fault_info;
		mb();
		atomic_set(&adev->gmc.vm_fault_info_updated, 0);
	}
	return 0;
}

/* Evict a userptr BO by stopping the queues if necessary
 *
 * Runs in MMU notifier, may be in RECLAIM_FS context. This means it
 * cannot do any memory allocations, and cannot take any locks that
 * are held elsewhere while allocating memory. Therefore this is as
 * simple as possible, using atomic counters.
 *
 * It doesn't do anything to the BO itself. The real work happens in
 * restore, where we get updated page addresses. This function only
 * ensures that GPU access to the BO is stopped.
 */
int amdgpu_amdkfd_evict_userptr(struct kgd_mem *mem,
				struct mm_struct *mm)
{
	struct amdkfd_process_info *process_info = mem->process_info;
	int invalid, evicted_bos;
	int r = 0;

	invalid = atomic_inc_return(&mem->invalid);
	evicted_bos = atomic_inc_return(&process_info->evicted_bos);
	if (evicted_bos == 1) {
		/* First eviction, stop the queues */
		r = kgd2kfd->quiesce_mm(mm);
		if (r)
			pr_err("Failed to quiesce KFD\n");
		schedule_delayed_work(&process_info->restore_userptr_work,
			msecs_to_jiffies(AMDGPU_USERPTR_RESTORE_DELAY_MS));
	}

	return r;
}

/* Update invalid userptr BOs
 *
 * Moves invalidated (evicted) userptr BOs from userptr_valid_list to
 * userptr_inval_list and updates user pages for all BOs that have
 * been invalidated since their last update.
 */
static int update_invalid_user_pages(struct amdkfd_process_info *process_info,
				     struct mm_struct *mm)
{
	struct kgd_mem *mem, *tmp_mem;
	struct amdgpu_bo *bo;
	struct ttm_operation_ctx ctx = { false, false };
	int invalid, ret;

	/* Move all invalidated BOs to the userptr_inval_list and
	 * release their user pages by migration to the CPU domain
	 */
	list_for_each_entry_safe(mem, tmp_mem,
				 &process_info->userptr_valid_list,
				 validate_list.head) {
		if (!atomic_read(&mem->invalid))
			continue; /* BO is still valid */

		bo = mem->bo;

		if (amdgpu_bo_reserve(bo, true))
			return -EAGAIN;
		amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_CPU);
		ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
		amdgpu_bo_unreserve(bo);
		if (ret) {
			pr_err("%s: Failed to invalidate userptr BO\n",
			       __func__);
			return -EAGAIN;
		}

		list_move_tail(&mem->validate_list.head,
			       &process_info->userptr_inval_list);
	}

	if (list_empty(&process_info->userptr_inval_list))
		return 0; /* All evicted userptr BOs were freed */

	/* Go through userptr_inval_list and update any invalid user_pages */
	list_for_each_entry(mem, &process_info->userptr_inval_list,
			    validate_list.head) {
		invalid = atomic_read(&mem->invalid);
		if (!invalid)
			/* BO hasn't been invalidated since the last
			 * revalidation attempt. Keep its BO list.
			 */
			continue;

		bo = mem->bo;

		if (!mem->user_pages) {
			mem->user_pages =
				kvmalloc_array(bo->tbo.ttm->num_pages,
						 sizeof(struct page *),
						 GFP_KERNEL | __GFP_ZERO);
			if (!mem->user_pages) {
				pr_err("%s: Failed to allocate pages array\n",
				       __func__);
				return -ENOMEM;
			}
		} else if (mem->user_pages[0]) {
			release_pages(mem->user_pages, bo->tbo.ttm->num_pages);
		}

		/* Get updated user pages */
		ret = amdgpu_ttm_tt_get_user_pages(bo->tbo.ttm,
						   mem->user_pages);
		if (ret) {
			mem->user_pages[0] = NULL;
			pr_info("%s: Failed to get user pages: %d\n",
				__func__, ret);
			/* Pretend it succeeded. It will fail later
			 * with a VM fault if the GPU tries to access
			 * it. Better than hanging indefinitely with
			 * stalled user mode queues.
			 */
		}

		/* Mark the BO as valid unless it was invalidated
		 * again concurrently
		 */
		if (atomic_cmpxchg(&mem->invalid, invalid, 0) != invalid)
			return -EAGAIN;
	}

	return 0;
}

/* Validate invalid userptr BOs
 *
 * Validates BOs on the userptr_inval_list, and moves them back to the
 * userptr_valid_list. Also updates GPUVM page tables with new page
 * addresses and waits for the page table updates to complete.
 */
static int validate_invalid_user_pages(struct amdkfd_process_info *process_info)
{
	struct amdgpu_bo_list_entry *pd_bo_list_entries;
	struct list_head resv_list, duplicates;
	struct ww_acquire_ctx ticket;
	struct amdgpu_sync sync;

	struct amdgpu_vm *peer_vm;
	struct kgd_mem *mem, *tmp_mem;
	struct amdgpu_bo *bo;
	struct ttm_operation_ctx ctx = { false, false };
	int i, ret;

	pd_bo_list_entries = kcalloc(process_info->n_vms,
				     sizeof(struct amdgpu_bo_list_entry),
				     GFP_KERNEL);
	if (!pd_bo_list_entries) {
		pr_err("%s: Failed to allocate PD BO list entries\n", __func__);
		return -ENOMEM;
	}

	INIT_LIST_HEAD(&resv_list);
	INIT_LIST_HEAD(&duplicates);

	/* Get all the page directory BOs that need to be reserved */
	i = 0;
	list_for_each_entry(peer_vm, &process_info->vm_list_head,
			    vm_list_node)
		amdgpu_vm_get_pd_bo(peer_vm, &resv_list,
				    &pd_bo_list_entries[i++]);
	/* Add the userptr_inval_list entries to resv_list */
	list_for_each_entry(mem, &process_info->userptr_inval_list,
			    validate_list.head) {
		list_add_tail(&mem->resv_list.head, &resv_list);
		mem->resv_list.bo = mem->validate_list.bo;
		mem->resv_list.shared = mem->validate_list.shared;
	}

	/* Reserve all BOs and page tables for validation */
	ret = ttm_eu_reserve_buffers(&ticket, &resv_list, false, &duplicates);
	WARN(!list_empty(&duplicates), "Duplicates should be empty");
	if (ret)
		goto out;

	amdgpu_sync_create(&sync);

	/* Avoid triggering eviction fences when unmapping invalid
	 * userptr BOs (waits for all fences, doesn't use
	 * FENCE_OWNER_VM)
	 */
	list_for_each_entry(peer_vm, &process_info->vm_list_head,
			    vm_list_node)
		amdgpu_amdkfd_remove_eviction_fence(peer_vm->root.base.bo,
						process_info->eviction_fence,
						NULL, NULL);

	ret = process_validate_vms(process_info);
	if (ret)
		goto unreserve_out;

	/* Validate BOs and update GPUVM page tables */
	list_for_each_entry_safe(mem, tmp_mem,
				 &process_info->userptr_inval_list,
				 validate_list.head) {
		struct kfd_bo_va_list *bo_va_entry;

		bo = mem->bo;

		/* Copy pages array and validate the BO if we got user pages */
		if (mem->user_pages[0]) {
			amdgpu_ttm_tt_set_user_pages(bo->tbo.ttm,
						     mem->user_pages);
			amdgpu_bo_placement_from_domain(bo, mem->domain);
			ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
			if (ret) {
				pr_err("%s: failed to validate BO\n", __func__);
				goto unreserve_out;
			}
		}

		/* Validate succeeded, now the BO owns the pages, free
		 * our copy of the pointer array. Put this BO back on
		 * the userptr_valid_list. If we need to revalidate
		 * it, we need to start from scratch.
		 */
		kvfree(mem->user_pages);
		mem->user_pages = NULL;
		list_move_tail(&mem->validate_list.head,
			       &process_info->userptr_valid_list);

		/* Update mapping. If the BO was not validated
		 * (because we couldn't get user pages), this will
		 * clear the page table entries, which will result in
		 * VM faults if the GPU tries to access the invalid
		 * memory.
		 */
		list_for_each_entry(bo_va_entry, &mem->bo_va_list, bo_list) {
			if (!bo_va_entry->is_mapped)
				continue;

			ret = update_gpuvm_pte((struct amdgpu_device *)
					       bo_va_entry->kgd_dev,
					       bo_va_entry, &sync);
			if (ret) {
				pr_err("%s: update PTE failed\n", __func__);
				/* make sure this gets validated again */
				atomic_inc(&mem->invalid);
				goto unreserve_out;
			}
		}
	}

	/* Update page directories */
	ret = process_update_pds(process_info, &sync);

unreserve_out:
	list_for_each_entry(peer_vm, &process_info->vm_list_head,
			    vm_list_node)
		amdgpu_bo_fence(peer_vm->root.base.bo,
				&process_info->eviction_fence->base, true);
	ttm_eu_backoff_reservation(&ticket, &resv_list);
	amdgpu_sync_wait(&sync, false);
	amdgpu_sync_free(&sync);
out:
	kfree(pd_bo_list_entries);

	return ret;
}

/* Worker callback to restore evicted userptr BOs
 *
 * Tries to update and validate all userptr BOs. If successful and no
 * concurrent evictions happened, the queues are restarted. Otherwise,
 * reschedule for another attempt later.
 */
static void amdgpu_amdkfd_restore_userptr_worker(struct work_struct *work)
{
	struct delayed_work *dwork = to_delayed_work(work);
	struct amdkfd_process_info *process_info =
		container_of(dwork, struct amdkfd_process_info,
			     restore_userptr_work);
	struct task_struct *usertask;
	struct mm_struct *mm;
	int evicted_bos;

	evicted_bos = atomic_read(&process_info->evicted_bos);
	if (!evicted_bos)
		return;

	/* Reference task and mm in case of concurrent process termination */
	usertask = get_pid_task(process_info->pid, PIDTYPE_PID);
	if (!usertask)
		return;
	mm = get_task_mm(usertask);
	if (!mm) {
		put_task_struct(usertask);
		return;
	}

	mutex_lock(&process_info->lock);

	if (update_invalid_user_pages(process_info, mm))
		goto unlock_out;
	/* userptr_inval_list can be empty if all evicted userptr BOs
	 * have been freed. In that case there is nothing to validate
	 * and we can just restart the queues.
	 */
	if (!list_empty(&process_info->userptr_inval_list)) {
		if (atomic_read(&process_info->evicted_bos) != evicted_bos)
			goto unlock_out; /* Concurrent eviction, try again */

		if (validate_invalid_user_pages(process_info))
			goto unlock_out;
	}
	/* Final check for concurrent evicton and atomic update. If
	 * another eviction happens after successful update, it will
	 * be a first eviction that calls quiesce_mm. The eviction
	 * reference counting inside KFD will handle this case.
	 */
	if (atomic_cmpxchg(&process_info->evicted_bos, evicted_bos, 0) !=
	    evicted_bos)
		goto unlock_out;
	evicted_bos = 0;
	if (kgd2kfd->resume_mm(mm)) {
		pr_err("%s: Failed to resume KFD\n", __func__);
		/* No recovery from this failure. Probably the CP is
		 * hanging. No point trying again.
		 */
	}
unlock_out:
	mutex_unlock(&process_info->lock);
	mmput(mm);
	put_task_struct(usertask);

	/* If validation failed, reschedule another attempt */
	if (evicted_bos)
		schedule_delayed_work(&process_info->restore_userptr_work,
			msecs_to_jiffies(AMDGPU_USERPTR_RESTORE_DELAY_MS));
}

/** amdgpu_amdkfd_gpuvm_restore_process_bos - Restore all BOs for the given
 *   KFD process identified by process_info
 *
 * @process_info: amdkfd_process_info of the KFD process
 *
 * After memory eviction, restore thread calls this function. The function
 * should be called when the Process is still valid. BO restore involves -
 *
 * 1.  Release old eviction fence and create new one
 * 2.  Get two copies of PD BO list from all the VMs. Keep one copy as pd_list.
 * 3   Use the second PD list and kfd_bo_list to create a list (ctx.list) of
 *     BOs that need to be reserved.
 * 4.  Reserve all the BOs
 * 5.  Validate of PD and PT BOs.
 * 6.  Validate all KFD BOs using kfd_bo_list and Map them and add new fence
 * 7.  Add fence to all PD and PT BOs.
 * 8.  Unreserve all BOs
 */
int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef)
{
	struct amdgpu_bo_list_entry *pd_bo_list;
	struct amdkfd_process_info *process_info = info;
	struct amdgpu_vm *peer_vm;
	struct kgd_mem *mem;
	struct bo_vm_reservation_context ctx;
	struct amdgpu_amdkfd_fence *new_fence;
	int ret = 0, i;
	struct list_head duplicate_save;
	struct amdgpu_sync sync_obj;

	INIT_LIST_HEAD(&duplicate_save);
	INIT_LIST_HEAD(&ctx.list);
	INIT_LIST_HEAD(&ctx.duplicates);

	pd_bo_list = kcalloc(process_info->n_vms,
			     sizeof(struct amdgpu_bo_list_entry),
			     GFP_KERNEL);
	if (!pd_bo_list)
		return -ENOMEM;

	i = 0;
	mutex_lock(&process_info->lock);
	list_for_each_entry(peer_vm, &process_info->vm_list_head,
			vm_list_node)
		amdgpu_vm_get_pd_bo(peer_vm, &ctx.list, &pd_bo_list[i++]);

	/* Reserve all BOs and page tables/directory. Add all BOs from
	 * kfd_bo_list to ctx.list
	 */
	list_for_each_entry(mem, &process_info->kfd_bo_list,
			    validate_list.head) {

		list_add_tail(&mem->resv_list.head, &ctx.list);
		mem->resv_list.bo = mem->validate_list.bo;
		mem->resv_list.shared = mem->validate_list.shared;
	}

	ret = ttm_eu_reserve_buffers(&ctx.ticket, &ctx.list,
				     false, &duplicate_save);
	if (ret) {
		pr_debug("Memory eviction: TTM Reserve Failed. Try again\n");
		goto ttm_reserve_fail;
	}

	amdgpu_sync_create(&sync_obj);

	/* Validate PDs and PTs */
	ret = process_validate_vms(process_info);
	if (ret)
		goto validate_map_fail;

	/* Wait for PD/PTs validate to finish */
	/* FIXME: I think this isn't needed */
	list_for_each_entry(peer_vm, &process_info->vm_list_head,
			    vm_list_node) {
		struct amdgpu_bo *bo = peer_vm->root.base.bo;

		ttm_bo_wait(&bo->tbo, false, false);
	}

	/* Validate BOs and map them to GPUVM (update VM page tables). */
	list_for_each_entry(mem, &process_info->kfd_bo_list,
			    validate_list.head) {

		struct amdgpu_bo *bo = mem->bo;
		uint32_t domain = mem->domain;
		struct kfd_bo_va_list *bo_va_entry;

		ret = amdgpu_amdkfd_bo_validate(bo, domain, false);
		if (ret) {
			pr_debug("Memory eviction: Validate BOs failed. Try again\n");
			goto validate_map_fail;
		}

		list_for_each_entry(bo_va_entry, &mem->bo_va_list,
				    bo_list) {
			ret = update_gpuvm_pte((struct amdgpu_device *)
					      bo_va_entry->kgd_dev,
					      bo_va_entry,
					      &sync_obj);
			if (ret) {
				pr_debug("Memory eviction: update PTE failed. Try again\n");
				goto validate_map_fail;
			}
		}
	}

	/* Update page directories */
	ret = process_update_pds(process_info, &sync_obj);
	if (ret) {
		pr_debug("Memory eviction: update PDs failed. Try again\n");
		goto validate_map_fail;
	}

	amdgpu_sync_wait(&sync_obj, false);

	/* Release old eviction fence and create new one, because fence only
	 * goes from unsignaled to signaled, fence cannot be reused.
	 * Use context and mm from the old fence.
	 */
	new_fence = amdgpu_amdkfd_fence_create(
				process_info->eviction_fence->base.context,
				process_info->eviction_fence->mm);
	if (!new_fence) {
		pr_err("Failed to create eviction fence\n");
		ret = -ENOMEM;
		goto validate_map_fail;
	}
	dma_fence_put(&process_info->eviction_fence->base);
	process_info->eviction_fence = new_fence;
	*ef = dma_fence_get(&new_fence->base);

	/* Wait for validate to finish and attach new eviction fence */
	list_for_each_entry(mem, &process_info->kfd_bo_list,
		validate_list.head)
		ttm_bo_wait(&mem->bo->tbo, false, false);
	list_for_each_entry(mem, &process_info->kfd_bo_list,
		validate_list.head)
		amdgpu_bo_fence(mem->bo,
			&process_info->eviction_fence->base, true);

	/* Attach eviction fence to PD / PT BOs */
	list_for_each_entry(peer_vm, &process_info->vm_list_head,
			    vm_list_node) {
		struct amdgpu_bo *bo = peer_vm->root.base.bo;

		amdgpu_bo_fence(bo, &process_info->eviction_fence->base, true);
	}

validate_map_fail:
	ttm_eu_backoff_reservation(&ctx.ticket, &ctx.list);
	amdgpu_sync_free(&sync_obj);
ttm_reserve_fail:
	mutex_unlock(&process_info->lock);
	kfree(pd_bo_list);
	return ret;
}