summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
blob: 94089069c9ada61aa61b7c2b28601b764d47c172 (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
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
/*
 * Copyright 2008 Advanced Micro Devices, Inc.
 * Copyright 2008 Red Hat Inc.
 * Copyright 2009 Jerome Glisse.
 *
 * 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.
 *
 * Authors: Dave Airlie
 *          Alex Deucher
 *          Jerome Glisse
 */

#include <linux/dma-fence-array.h>
#include <linux/interval_tree_generic.h>
#include <linux/idr.h>
#include <linux/dma-buf.h>

#include <drm/amdgpu_drm.h>
#include <drm/drm_drv.h>
#include <drm/ttm/ttm_tt.h>
#include <drm/drm_exec.h>
#include "amdgpu.h"
#include "amdgpu_trace.h"
#include "amdgpu_amdkfd.h"
#include "amdgpu_gmc.h"
#include "amdgpu_xgmi.h"
#include "amdgpu_dma_buf.h"
#include "amdgpu_res_cursor.h"
#include "kfd_svm.h"

/**
 * DOC: GPUVM
 *
 * GPUVM is the MMU functionality provided on the GPU.
 * GPUVM is similar to the legacy GART on older asics, however
 * rather than there being a single global GART table
 * for the entire GPU, there can be multiple GPUVM page tables active
 * at any given time.  The GPUVM page tables can contain a mix
 * VRAM pages and system pages (both memory and MMIO) and system pages
 * can be mapped as snooped (cached system pages) or unsnooped
 * (uncached system pages).
 *
 * Each active GPUVM has an ID associated with it and there is a page table
 * linked with each VMID.  When executing a command buffer,
 * the kernel tells the engine what VMID to use for that command
 * buffer.  VMIDs are allocated dynamically as commands are submitted.
 * The userspace drivers maintain their own address space and the kernel
 * sets up their pages tables accordingly when they submit their
 * command buffers and a VMID is assigned.
 * The hardware supports up to 16 active GPUVMs at any given time.
 *
 * Each GPUVM is represented by a 1-2 or 1-5 level page table, depending
 * on the ASIC family.  GPUVM supports RWX attributes on each page as well
 * as other features such as encryption and caching attributes.
 *
 * VMID 0 is special.  It is the GPUVM used for the kernel driver.  In
 * addition to an aperture managed by a page table, VMID 0 also has
 * several other apertures.  There is an aperture for direct access to VRAM
 * and there is a legacy AGP aperture which just forwards accesses directly
 * to the matching system physical addresses (or IOVAs when an IOMMU is
 * present).  These apertures provide direct access to these memories without
 * incurring the overhead of a page table.  VMID 0 is used by the kernel
 * driver for tasks like memory management.
 *
 * GPU clients (i.e., engines on the GPU) use GPUVM VMIDs to access memory.
 * For user applications, each application can have their own unique GPUVM
 * address space.  The application manages the address space and the kernel
 * driver manages the GPUVM page tables for each process.  If an GPU client
 * accesses an invalid page, it will generate a GPU page fault, similar to
 * accessing an invalid page on a CPU.
 */

#define START(node) ((node)->start)
#define LAST(node) ((node)->last)

INTERVAL_TREE_DEFINE(struct amdgpu_bo_va_mapping, rb, uint64_t, __subtree_last,
		     START, LAST, static, amdgpu_vm_it)

#undef START
#undef LAST

/**
 * struct amdgpu_prt_cb - Helper to disable partial resident texture feature from a fence callback
 */
struct amdgpu_prt_cb {

	/**
	 * @adev: amdgpu device
	 */
	struct amdgpu_device *adev;

	/**
	 * @cb: callback
	 */
	struct dma_fence_cb cb;
};

/**
 * struct amdgpu_vm_tlb_seq_struct - Helper to increment the TLB flush sequence
 */
struct amdgpu_vm_tlb_seq_struct {
	/**
	 * @vm: pointer to the amdgpu_vm structure to set the fence sequence on
	 */
	struct amdgpu_vm *vm;

	/**
	 * @cb: callback
	 */
	struct dma_fence_cb cb;
};

/**
 * amdgpu_vm_set_pasid - manage pasid and vm ptr mapping
 *
 * @adev: amdgpu_device pointer
 * @vm: amdgpu_vm pointer
 * @pasid: the pasid the VM is using on this GPU
 *
 * Set the pasid this VM is using on this GPU, can also be used to remove the
 * pasid by passing in zero.
 *
 */
int amdgpu_vm_set_pasid(struct amdgpu_device *adev, struct amdgpu_vm *vm,
			u32 pasid)
{
	int r;

	if (vm->pasid == pasid)
		return 0;

	if (vm->pasid) {
		r = xa_err(xa_erase_irq(&adev->vm_manager.pasids, vm->pasid));
		if (r < 0)
			return r;

		vm->pasid = 0;
	}

	if (pasid) {
		r = xa_err(xa_store_irq(&adev->vm_manager.pasids, pasid, vm,
					GFP_KERNEL));
		if (r < 0)
			return r;

		vm->pasid = pasid;
	}


	return 0;
}

/**
 * amdgpu_vm_bo_evicted - vm_bo is evicted
 *
 * @vm_bo: vm_bo which is evicted
 *
 * State for PDs/PTs and per VM BOs which are not at the location they should
 * be.
 */
static void amdgpu_vm_bo_evicted(struct amdgpu_vm_bo_base *vm_bo)
{
	struct amdgpu_vm *vm = vm_bo->vm;
	struct amdgpu_bo *bo = vm_bo->bo;

	vm_bo->moved = true;
	spin_lock(&vm_bo->vm->status_lock);
	if (bo->tbo.type == ttm_bo_type_kernel)
		list_move(&vm_bo->vm_status, &vm->evicted);
	else
		list_move_tail(&vm_bo->vm_status, &vm->evicted);
	spin_unlock(&vm_bo->vm->status_lock);
}
/**
 * amdgpu_vm_bo_moved - vm_bo is moved
 *
 * @vm_bo: vm_bo which is moved
 *
 * State for per VM BOs which are moved, but that change is not yet reflected
 * in the page tables.
 */
static void amdgpu_vm_bo_moved(struct amdgpu_vm_bo_base *vm_bo)
{
	spin_lock(&vm_bo->vm->status_lock);
	list_move(&vm_bo->vm_status, &vm_bo->vm->moved);
	spin_unlock(&vm_bo->vm->status_lock);
}

/**
 * amdgpu_vm_bo_idle - vm_bo is idle
 *
 * @vm_bo: vm_bo which is now idle
 *
 * State for PDs/PTs and per VM BOs which have gone through the state machine
 * and are now idle.
 */
static void amdgpu_vm_bo_idle(struct amdgpu_vm_bo_base *vm_bo)
{
	spin_lock(&vm_bo->vm->status_lock);
	list_move(&vm_bo->vm_status, &vm_bo->vm->idle);
	spin_unlock(&vm_bo->vm->status_lock);
	vm_bo->moved = false;
}

/**
 * amdgpu_vm_bo_invalidated - vm_bo is invalidated
 *
 * @vm_bo: vm_bo which is now invalidated
 *
 * State for normal BOs which are invalidated and that change not yet reflected
 * in the PTs.
 */
static void amdgpu_vm_bo_invalidated(struct amdgpu_vm_bo_base *vm_bo)
{
	spin_lock(&vm_bo->vm->status_lock);
	list_move(&vm_bo->vm_status, &vm_bo->vm->invalidated);
	spin_unlock(&vm_bo->vm->status_lock);
}

/**
 * amdgpu_vm_bo_evicted_user - vm_bo is evicted
 *
 * @vm_bo: vm_bo which is evicted
 *
 * State for BOs used by user mode queues which are not at the location they
 * should be.
 */
static void amdgpu_vm_bo_evicted_user(struct amdgpu_vm_bo_base *vm_bo)
{
	vm_bo->moved = true;
	spin_lock(&vm_bo->vm->status_lock);
	list_move(&vm_bo->vm_status, &vm_bo->vm->evicted_user);
	spin_unlock(&vm_bo->vm->status_lock);
}

/**
 * amdgpu_vm_bo_relocated - vm_bo is reloacted
 *
 * @vm_bo: vm_bo which is relocated
 *
 * State for PDs/PTs which needs to update their parent PD.
 * For the root PD, just move to idle state.
 */
static void amdgpu_vm_bo_relocated(struct amdgpu_vm_bo_base *vm_bo)
{
	if (vm_bo->bo->parent) {
		spin_lock(&vm_bo->vm->status_lock);
		list_move(&vm_bo->vm_status, &vm_bo->vm->relocated);
		spin_unlock(&vm_bo->vm->status_lock);
	} else {
		amdgpu_vm_bo_idle(vm_bo);
	}
}

/**
 * amdgpu_vm_bo_done - vm_bo is done
 *
 * @vm_bo: vm_bo which is now done
 *
 * State for normal BOs which are invalidated and that change has been updated
 * in the PTs.
 */
static void amdgpu_vm_bo_done(struct amdgpu_vm_bo_base *vm_bo)
{
	spin_lock(&vm_bo->vm->status_lock);
	list_move(&vm_bo->vm_status, &vm_bo->vm->done);
	spin_unlock(&vm_bo->vm->status_lock);
}

/**
 * amdgpu_vm_bo_reset_state_machine - reset the vm_bo state machine
 * @vm: the VM which state machine to reset
 *
 * Move all vm_bo object in the VM into a state where they will be updated
 * again during validation.
 */
static void amdgpu_vm_bo_reset_state_machine(struct amdgpu_vm *vm)
{
	struct amdgpu_vm_bo_base *vm_bo, *tmp;

	spin_lock(&vm->status_lock);
	list_splice_init(&vm->done, &vm->invalidated);
	list_for_each_entry(vm_bo, &vm->invalidated, vm_status)
		vm_bo->moved = true;
	list_for_each_entry_safe(vm_bo, tmp, &vm->idle, vm_status) {
		struct amdgpu_bo *bo = vm_bo->bo;

		vm_bo->moved = true;
		if (!bo || bo->tbo.type != ttm_bo_type_kernel)
			list_move(&vm_bo->vm_status, &vm_bo->vm->moved);
		else if (bo->parent)
			list_move(&vm_bo->vm_status, &vm_bo->vm->relocated);
	}
	spin_unlock(&vm->status_lock);
}

/**
 * amdgpu_vm_bo_base_init - Adds bo to the list of bos associated with the vm
 *
 * @base: base structure for tracking BO usage in a VM
 * @vm: vm to which bo is to be added
 * @bo: amdgpu buffer object
 *
 * Initialize a bo_va_base structure and add it to the appropriate lists
 *
 */
void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base,
			    struct amdgpu_vm *vm, struct amdgpu_bo *bo)
{
	base->vm = vm;
	base->bo = bo;
	base->next = NULL;
	INIT_LIST_HEAD(&base->vm_status);

	if (!bo)
		return;
	base->next = bo->vm_bo;
	bo->vm_bo = base;

	if (bo->tbo.base.resv != vm->root.bo->tbo.base.resv)
		return;

	dma_resv_assert_held(vm->root.bo->tbo.base.resv);

	ttm_bo_set_bulk_move(&bo->tbo, &vm->lru_bulk_move);
	if (bo->tbo.type == ttm_bo_type_kernel && bo->parent)
		amdgpu_vm_bo_relocated(base);
	else
		amdgpu_vm_bo_idle(base);

	if (bo->preferred_domains &
	    amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type))
		return;

	/*
	 * we checked all the prerequisites, but it looks like this per vm bo
	 * is currently evicted. add the bo to the evicted list to make sure it
	 * is validated on next vm use to avoid fault.
	 * */
	amdgpu_vm_bo_evicted(base);
}

/**
 * amdgpu_vm_lock_pd - lock PD in drm_exec
 *
 * @vm: vm providing the BOs
 * @exec: drm execution context
 * @num_fences: number of extra fences to reserve
 *
 * Lock the VM root PD in the DRM execution context.
 */
int amdgpu_vm_lock_pd(struct amdgpu_vm *vm, struct drm_exec *exec,
		      unsigned int num_fences)
{
	/* We need at least two fences for the VM PD/PT updates */
	return drm_exec_prepare_obj(exec, &vm->root.bo->tbo.base,
				    2 + num_fences);
}

/**
 * amdgpu_vm_move_to_lru_tail - move all BOs to the end of LRU
 *
 * @adev: amdgpu device pointer
 * @vm: vm providing the BOs
 *
 * Move all BOs to the end of LRU and remember their positions to put them
 * together.
 */
void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev,
				struct amdgpu_vm *vm)
{
	spin_lock(&adev->mman.bdev.lru_lock);
	ttm_lru_bulk_move_tail(&vm->lru_bulk_move);
	spin_unlock(&adev->mman.bdev.lru_lock);
}

/* Create scheduler entities for page table updates */
static int amdgpu_vm_init_entities(struct amdgpu_device *adev,
				   struct amdgpu_vm *vm)
{
	int r;

	r = drm_sched_entity_init(&vm->immediate, DRM_SCHED_PRIORITY_NORMAL,
				  adev->vm_manager.vm_pte_scheds,
				  adev->vm_manager.vm_pte_num_scheds, NULL);
	if (r)
		goto error;

	return drm_sched_entity_init(&vm->delayed, DRM_SCHED_PRIORITY_NORMAL,
				     adev->vm_manager.vm_pte_scheds,
				     adev->vm_manager.vm_pte_num_scheds, NULL);

error:
	drm_sched_entity_destroy(&vm->immediate);
	return r;
}

/* Destroy the entities for page table updates again */
static void amdgpu_vm_fini_entities(struct amdgpu_vm *vm)
{
	drm_sched_entity_destroy(&vm->immediate);
	drm_sched_entity_destroy(&vm->delayed);
}

/**
 * amdgpu_vm_generation - return the page table re-generation counter
 * @adev: the amdgpu_device
 * @vm: optional VM to check, might be NULL
 *
 * Returns a page table re-generation token to allow checking if submissions
 * are still valid to use this VM. The VM parameter might be NULL in which case
 * just the VRAM lost counter will be used.
 */
uint64_t amdgpu_vm_generation(struct amdgpu_device *adev, struct amdgpu_vm *vm)
{
	uint64_t result = (u64)atomic_read(&adev->vram_lost_counter) << 32;

	if (!vm)
		return result;

	result += vm->generation;
	/* Add one if the page tables will be re-generated on next CS */
	if (drm_sched_entity_error(&vm->delayed))
		++result;

	return result;
}

/**
 * amdgpu_vm_validate - validate evicted BOs tracked in the VM
 *
 * @adev: amdgpu device pointer
 * @vm: vm providing the BOs
 * @ticket: optional reservation ticket used to reserve the VM
 * @validate: callback to do the validation
 * @param: parameter for the validation callback
 *
 * Validate the page table BOs and per-VM BOs on command submission if
 * necessary. If a ticket is given, also try to validate evicted user queue
 * BOs. They must already be reserved with the given ticket.
 *
 * Returns:
 * Validation result.
 */
int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm,
		       struct ww_acquire_ctx *ticket,
		       int (*validate)(void *p, struct amdgpu_bo *bo),
		       void *param)
{
	struct amdgpu_vm_bo_base *bo_base;
	struct amdgpu_bo *shadow;
	struct amdgpu_bo *bo;
	int r;

	if (drm_sched_entity_error(&vm->delayed)) {
		++vm->generation;
		amdgpu_vm_bo_reset_state_machine(vm);
		amdgpu_vm_fini_entities(vm);
		r = amdgpu_vm_init_entities(adev, vm);
		if (r)
			return r;
	}

	spin_lock(&vm->status_lock);
	while (!list_empty(&vm->evicted)) {
		bo_base = list_first_entry(&vm->evicted,
					   struct amdgpu_vm_bo_base,
					   vm_status);
		spin_unlock(&vm->status_lock);

		bo = bo_base->bo;
		shadow = amdgpu_bo_shadowed(bo);

		r = validate(param, bo);
		if (r)
			return r;
		if (shadow) {
			r = validate(param, shadow);
			if (r)
				return r;
		}

		if (bo->tbo.type != ttm_bo_type_kernel) {
			amdgpu_vm_bo_moved(bo_base);
		} else {
			vm->update_funcs->map_table(to_amdgpu_bo_vm(bo));
			amdgpu_vm_bo_relocated(bo_base);
		}
		spin_lock(&vm->status_lock);
	}
	while (ticket && !list_empty(&vm->evicted_user)) {
		bo_base = list_first_entry(&vm->evicted_user,
					   struct amdgpu_vm_bo_base,
					   vm_status);
		spin_unlock(&vm->status_lock);

		bo = bo_base->bo;

		if (dma_resv_locking_ctx(bo->tbo.base.resv) != ticket) {
			struct amdgpu_task_info *ti = amdgpu_vm_get_task_info_vm(vm);

			pr_warn_ratelimited("Evicted user BO is not reserved\n");
			if (ti) {
				pr_warn_ratelimited("pid %d\n", ti->pid);
				amdgpu_vm_put_task_info(ti);
			}

			return -EINVAL;
		}

		r = validate(param, bo);
		if (r)
			return r;

		amdgpu_vm_bo_invalidated(bo_base);

		spin_lock(&vm->status_lock);
	}
	spin_unlock(&vm->status_lock);

	amdgpu_vm_eviction_lock(vm);
	vm->evicting = false;
	amdgpu_vm_eviction_unlock(vm);

	return 0;
}

/**
 * amdgpu_vm_ready - check VM is ready for updates
 *
 * @vm: VM to check
 *
 * Check if all VM PDs/PTs are ready for updates
 *
 * Returns:
 * True if VM is not evicting.
 */
bool amdgpu_vm_ready(struct amdgpu_vm *vm)
{
	bool empty;
	bool ret;

	amdgpu_vm_eviction_lock(vm);
	ret = !vm->evicting;
	amdgpu_vm_eviction_unlock(vm);

	spin_lock(&vm->status_lock);
	empty = list_empty(&vm->evicted);
	spin_unlock(&vm->status_lock);

	return ret && empty;
}

/**
 * amdgpu_vm_check_compute_bug - check whether asic has compute vm bug
 *
 * @adev: amdgpu_device pointer
 */
void amdgpu_vm_check_compute_bug(struct amdgpu_device *adev)
{
	const struct amdgpu_ip_block *ip_block;
	bool has_compute_vm_bug;
	struct amdgpu_ring *ring;
	int i;

	has_compute_vm_bug = false;

	ip_block = amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_GFX);
	if (ip_block) {
		/* Compute has a VM bug for GFX version < 7.
		   Compute has a VM bug for GFX 8 MEC firmware version < 673.*/
		if (ip_block->version->major <= 7)
			has_compute_vm_bug = true;
		else if (ip_block->version->major == 8)
			if (adev->gfx.mec_fw_version < 673)
				has_compute_vm_bug = true;
	}

	for (i = 0; i < adev->num_rings; i++) {
		ring = adev->rings[i];
		if (ring->funcs->type == AMDGPU_RING_TYPE_COMPUTE)
			/* only compute rings */
			ring->has_compute_vm_bug = has_compute_vm_bug;
		else
			ring->has_compute_vm_bug = false;
	}
}

/**
 * amdgpu_vm_need_pipeline_sync - Check if pipe sync is needed for job.
 *
 * @ring: ring on which the job will be submitted
 * @job: job to submit
 *
 * Returns:
 * True if sync is needed.
 */
bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
				  struct amdgpu_job *job)
{
	struct amdgpu_device *adev = ring->adev;
	unsigned vmhub = ring->vm_hub;
	struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub];

	if (job->vmid == 0)
		return false;

	if (job->vm_needs_flush || ring->has_compute_vm_bug)
		return true;

	if (ring->funcs->emit_gds_switch && job->gds_switch_needed)
		return true;

	if (amdgpu_vmid_had_gpu_reset(adev, &id_mgr->ids[job->vmid]))
		return true;

	return false;
}

/**
 * amdgpu_vm_flush - hardware flush the vm
 *
 * @ring: ring to use for flush
 * @job:  related job
 * @need_pipe_sync: is pipe sync needed
 *
 * Emit a VM flush when it is necessary.
 *
 * Returns:
 * 0 on success, errno otherwise.
 */
int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,
		    bool need_pipe_sync)
{
	struct amdgpu_device *adev = ring->adev;
	unsigned vmhub = ring->vm_hub;
	struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub];
	struct amdgpu_vmid *id = &id_mgr->ids[job->vmid];
	bool spm_update_needed = job->spm_update_needed;
	bool gds_switch_needed = ring->funcs->emit_gds_switch &&
		job->gds_switch_needed;
	bool vm_flush_needed = job->vm_needs_flush;
	struct dma_fence *fence = NULL;
	bool pasid_mapping_needed = false;
	unsigned int patch;
	int r;

	if (amdgpu_vmid_had_gpu_reset(adev, id)) {
		gds_switch_needed = true;
		vm_flush_needed = true;
		pasid_mapping_needed = true;
		spm_update_needed = true;
	}

	mutex_lock(&id_mgr->lock);
	if (id->pasid != job->pasid || !id->pasid_mapping ||
	    !dma_fence_is_signaled(id->pasid_mapping))
		pasid_mapping_needed = true;
	mutex_unlock(&id_mgr->lock);

	gds_switch_needed &= !!ring->funcs->emit_gds_switch;
	vm_flush_needed &= !!ring->funcs->emit_vm_flush  &&
			job->vm_pd_addr != AMDGPU_BO_INVALID_OFFSET;
	pasid_mapping_needed &= adev->gmc.gmc_funcs->emit_pasid_mapping &&
		ring->funcs->emit_wreg;

	if (!vm_flush_needed && !gds_switch_needed && !need_pipe_sync)
		return 0;

	amdgpu_ring_ib_begin(ring);
	if (ring->funcs->init_cond_exec)
		patch = amdgpu_ring_init_cond_exec(ring,
						   ring->cond_exe_gpu_addr);

	if (need_pipe_sync)
		amdgpu_ring_emit_pipeline_sync(ring);

	if (vm_flush_needed) {
		trace_amdgpu_vm_flush(ring, job->vmid, job->vm_pd_addr);
		amdgpu_ring_emit_vm_flush(ring, job->vmid, job->vm_pd_addr);
	}

	if (pasid_mapping_needed)
		amdgpu_gmc_emit_pasid_mapping(ring, job->vmid, job->pasid);

	if (spm_update_needed && adev->gfx.rlc.funcs->update_spm_vmid)
		adev->gfx.rlc.funcs->update_spm_vmid(adev, ring, job->vmid);

	if (!ring->is_mes_queue && ring->funcs->emit_gds_switch &&
	    gds_switch_needed) {
		amdgpu_ring_emit_gds_switch(ring, job->vmid, job->gds_base,
					    job->gds_size, job->gws_base,
					    job->gws_size, job->oa_base,
					    job->oa_size);
	}

	if (vm_flush_needed || pasid_mapping_needed) {
		r = amdgpu_fence_emit(ring, &fence, NULL, 0);
		if (r)
			return r;
	}

	if (vm_flush_needed) {
		mutex_lock(&id_mgr->lock);
		dma_fence_put(id->last_flush);
		id->last_flush = dma_fence_get(fence);
		id->current_gpu_reset_count =
			atomic_read(&adev->gpu_reset_counter);
		mutex_unlock(&id_mgr->lock);
	}

	if (pasid_mapping_needed) {
		mutex_lock(&id_mgr->lock);
		id->pasid = job->pasid;
		dma_fence_put(id->pasid_mapping);
		id->pasid_mapping = dma_fence_get(fence);
		mutex_unlock(&id_mgr->lock);
	}
	dma_fence_put(fence);

	amdgpu_ring_patch_cond_exec(ring, patch);

	/* the double SWITCH_BUFFER here *cannot* be skipped by COND_EXEC */
	if (ring->funcs->emit_switch_buffer) {
		amdgpu_ring_emit_switch_buffer(ring);
		amdgpu_ring_emit_switch_buffer(ring);
	}
	amdgpu_ring_ib_end(ring);
	return 0;
}

/**
 * amdgpu_vm_bo_find - find the bo_va for a specific vm & bo
 *
 * @vm: requested vm
 * @bo: requested buffer object
 *
 * Find @bo inside the requested vm.
 * Search inside the @bos vm list for the requested vm
 * Returns the found bo_va or NULL if none is found
 *
 * Object has to be reserved!
 *
 * Returns:
 * Found bo_va or NULL.
 */
struct amdgpu_bo_va *amdgpu_vm_bo_find(struct amdgpu_vm *vm,
				       struct amdgpu_bo *bo)
{
	struct amdgpu_vm_bo_base *base;

	for (base = bo->vm_bo; base; base = base->next) {
		if (base->vm != vm)
			continue;

		return container_of(base, struct amdgpu_bo_va, base);
	}
	return NULL;
}

/**
 * amdgpu_vm_map_gart - Resolve gart mapping of addr
 *
 * @pages_addr: optional DMA address to use for lookup
 * @addr: the unmapped addr
 *
 * Look up the physical address of the page that the pte resolves
 * to.
 *
 * Returns:
 * The pointer for the page table entry.
 */
uint64_t amdgpu_vm_map_gart(const dma_addr_t *pages_addr, uint64_t addr)
{
	uint64_t result;

	/* page table offset */
	result = pages_addr[addr >> PAGE_SHIFT];

	/* in case cpu page size != gpu page size*/
	result |= addr & (~PAGE_MASK);

	result &= 0xFFFFFFFFFFFFF000ULL;

	return result;
}

/**
 * amdgpu_vm_update_pdes - make sure that all directories are valid
 *
 * @adev: amdgpu_device pointer
 * @vm: requested vm
 * @immediate: submit immediately to the paging queue
 *
 * Makes sure all directories are up to date.
 *
 * Returns:
 * 0 for success, error for failure.
 */
int amdgpu_vm_update_pdes(struct amdgpu_device *adev,
			  struct amdgpu_vm *vm, bool immediate)
{
	struct amdgpu_vm_update_params params;
	struct amdgpu_vm_bo_base *entry;
	bool flush_tlb_needed = false;
	LIST_HEAD(relocated);
	int r, idx;

	spin_lock(&vm->status_lock);
	list_splice_init(&vm->relocated, &relocated);
	spin_unlock(&vm->status_lock);

	if (list_empty(&relocated))
		return 0;

	if (!drm_dev_enter(adev_to_drm(adev), &idx))
		return -ENODEV;

	memset(&params, 0, sizeof(params));
	params.adev = adev;
	params.vm = vm;
	params.immediate = immediate;

	r = vm->update_funcs->prepare(&params, NULL, AMDGPU_SYNC_EXPLICIT);
	if (r)
		goto error;

	list_for_each_entry(entry, &relocated, vm_status) {
		/* vm_flush_needed after updating moved PDEs */
		flush_tlb_needed |= entry->moved;

		r = amdgpu_vm_pde_update(&params, entry);
		if (r)
			goto error;
	}

	r = vm->update_funcs->commit(&params, &vm->last_update);
	if (r)
		goto error;

	if (flush_tlb_needed)
		atomic64_inc(&vm->tlb_seq);

	while (!list_empty(&relocated)) {
		entry = list_first_entry(&relocated, struct amdgpu_vm_bo_base,
					 vm_status);
		amdgpu_vm_bo_idle(entry);
	}

error:
	drm_dev_exit(idx);
	return r;
}

/**
 * amdgpu_vm_tlb_seq_cb - make sure to increment tlb sequence
 * @fence: unused
 * @cb: the callback structure
 *
 * Increments the tlb sequence to make sure that future CS execute a VM flush.
 */
static void amdgpu_vm_tlb_seq_cb(struct dma_fence *fence,
				 struct dma_fence_cb *cb)
{
	struct amdgpu_vm_tlb_seq_struct *tlb_cb;

	tlb_cb = container_of(cb, typeof(*tlb_cb), cb);
	atomic64_inc(&tlb_cb->vm->tlb_seq);
	kfree(tlb_cb);
}

/**
 * amdgpu_vm_update_range - update a range in the vm page table
 *
 * @adev: amdgpu_device pointer to use for commands
 * @vm: the VM to update the range
 * @immediate: immediate submission in a page fault
 * @unlocked: unlocked invalidation during MM callback
 * @flush_tlb: trigger tlb invalidation after update completed
 * @allow_override: change MTYPE for local NUMA nodes
 * @resv: fences we need to sync to
 * @start: start of mapped range
 * @last: last mapped entry
 * @flags: flags for the entries
 * @offset: offset into nodes and pages_addr
 * @vram_base: base for vram mappings
 * @res: ttm_resource to map
 * @pages_addr: DMA addresses to use for mapping
 * @fence: optional resulting fence
 *
 * Fill in the page table entries between @start and @last.
 *
 * Returns:
 * 0 for success, negative erro code for failure.
 */
int amdgpu_vm_update_range(struct amdgpu_device *adev, struct amdgpu_vm *vm,
			   bool immediate, bool unlocked, bool flush_tlb, bool allow_override,
			   struct dma_resv *resv, uint64_t start, uint64_t last,
			   uint64_t flags, uint64_t offset, uint64_t vram_base,
			   struct ttm_resource *res, dma_addr_t *pages_addr,
			   struct dma_fence **fence)
{
	struct amdgpu_vm_update_params params;
	struct amdgpu_vm_tlb_seq_struct *tlb_cb;
	struct amdgpu_res_cursor cursor;
	enum amdgpu_sync_mode sync_mode;
	int r, idx;

	if (!drm_dev_enter(adev_to_drm(adev), &idx))
		return -ENODEV;

	tlb_cb = kmalloc(sizeof(*tlb_cb), GFP_KERNEL);
	if (!tlb_cb) {
		r = -ENOMEM;
		goto error_unlock;
	}

	/* Vega20+XGMI where PTEs get inadvertently cached in L2 texture cache,
	 * heavy-weight flush TLB unconditionally.
	 */
	flush_tlb |= adev->gmc.xgmi.num_physical_nodes &&
		     amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 0);

	/*
	 * On GFX8 and older any 8 PTE block with a valid bit set enters the TLB
	 */
	flush_tlb |= amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(9, 0, 0);

	memset(&params, 0, sizeof(params));
	params.adev = adev;
	params.vm = vm;
	params.immediate = immediate;
	params.pages_addr = pages_addr;
	params.unlocked = unlocked;
	params.allow_override = allow_override;

	/* Implicitly sync to command submissions in the same VM before
	 * unmapping. Sync to moving fences before mapping.
	 */
	if (!(flags & AMDGPU_PTE_VALID))
		sync_mode = AMDGPU_SYNC_EQ_OWNER;
	else
		sync_mode = AMDGPU_SYNC_EXPLICIT;

	amdgpu_vm_eviction_lock(vm);
	if (vm->evicting) {
		r = -EBUSY;
		goto error_free;
	}

	if (!unlocked && !dma_fence_is_signaled(vm->last_unlocked)) {
		struct dma_fence *tmp = dma_fence_get_stub();

		amdgpu_bo_fence(vm->root.bo, vm->last_unlocked, true);
		swap(vm->last_unlocked, tmp);
		dma_fence_put(tmp);
	}

	r = vm->update_funcs->prepare(&params, resv, sync_mode);
	if (r)
		goto error_free;

	amdgpu_res_first(pages_addr ? NULL : res, offset,
			 (last - start + 1) * AMDGPU_GPU_PAGE_SIZE, &cursor);
	while (cursor.remaining) {
		uint64_t tmp, num_entries, addr;

		num_entries = cursor.size >> AMDGPU_GPU_PAGE_SHIFT;
		if (pages_addr) {
			bool contiguous = true;

			if (num_entries > AMDGPU_GPU_PAGES_IN_CPU_PAGE) {
				uint64_t pfn = cursor.start >> PAGE_SHIFT;
				uint64_t count;

				contiguous = pages_addr[pfn + 1] ==
					pages_addr[pfn] + PAGE_SIZE;

				tmp = num_entries /
					AMDGPU_GPU_PAGES_IN_CPU_PAGE;
				for (count = 2; count < tmp; ++count) {
					uint64_t idx = pfn + count;

					if (contiguous != (pages_addr[idx] ==
					    pages_addr[idx - 1] + PAGE_SIZE))
						break;
				}
				if (!contiguous)
					count--;
				num_entries = count *
					AMDGPU_GPU_PAGES_IN_CPU_PAGE;
			}

			if (!contiguous) {
				addr = cursor.start;
				params.pages_addr = pages_addr;
			} else {
				addr = pages_addr[cursor.start >> PAGE_SHIFT];
				params.pages_addr = NULL;
			}

		} else if (flags & (AMDGPU_PTE_VALID | AMDGPU_PTE_PRT)) {
			addr = vram_base + cursor.start;
		} else {
			addr = 0;
		}

		tmp = start + num_entries;
		r = amdgpu_vm_ptes_update(&params, start, tmp, addr, flags);
		if (r)
			goto error_free;

		amdgpu_res_next(&cursor, num_entries * AMDGPU_GPU_PAGE_SIZE);
		start = tmp;
	}

	r = vm->update_funcs->commit(&params, fence);

	if (flush_tlb || params.table_freed) {
		tlb_cb->vm = vm;
		if (fence && *fence &&
		    !dma_fence_add_callback(*fence, &tlb_cb->cb,
					   amdgpu_vm_tlb_seq_cb)) {
			dma_fence_put(vm->last_tlb_flush);
			vm->last_tlb_flush = dma_fence_get(*fence);
		} else {
			amdgpu_vm_tlb_seq_cb(NULL, &tlb_cb->cb);
		}
		tlb_cb = NULL;
	}

error_free:
	kfree(tlb_cb);

error_unlock:
	amdgpu_vm_eviction_unlock(vm);
	drm_dev_exit(idx);
	return r;
}

static void amdgpu_vm_bo_get_memory(struct amdgpu_bo_va *bo_va,
				    struct amdgpu_mem_stats *stats)
{
	struct amdgpu_vm *vm = bo_va->base.vm;
	struct amdgpu_bo *bo = bo_va->base.bo;

	if (!bo)
		return;

	/*
	 * For now ignore BOs which are currently locked and potentially
	 * changing their location.
	 */
	if (bo->tbo.base.resv != vm->root.bo->tbo.base.resv &&
	    !dma_resv_trylock(bo->tbo.base.resv))
		return;

	amdgpu_bo_get_memory(bo, stats);
	if (bo->tbo.base.resv != vm->root.bo->tbo.base.resv)
	    dma_resv_unlock(bo->tbo.base.resv);
}

void amdgpu_vm_get_memory(struct amdgpu_vm *vm,
			  struct amdgpu_mem_stats *stats)
{
	struct amdgpu_bo_va *bo_va, *tmp;

	spin_lock(&vm->status_lock);
	list_for_each_entry_safe(bo_va, tmp, &vm->idle, base.vm_status)
		amdgpu_vm_bo_get_memory(bo_va, stats);

	list_for_each_entry_safe(bo_va, tmp, &vm->evicted, base.vm_status)
		amdgpu_vm_bo_get_memory(bo_va, stats);

	list_for_each_entry_safe(bo_va, tmp, &vm->relocated, base.vm_status)
		amdgpu_vm_bo_get_memory(bo_va, stats);

	list_for_each_entry_safe(bo_va, tmp, &vm->moved, base.vm_status)
		amdgpu_vm_bo_get_memory(bo_va, stats);

	list_for_each_entry_safe(bo_va, tmp, &vm->invalidated, base.vm_status)
		amdgpu_vm_bo_get_memory(bo_va, stats);

	list_for_each_entry_safe(bo_va, tmp, &vm->done, base.vm_status)
		amdgpu_vm_bo_get_memory(bo_va, stats);
	spin_unlock(&vm->status_lock);
}

/**
 * amdgpu_vm_bo_update - update all BO mappings in the vm page table
 *
 * @adev: amdgpu_device pointer
 * @bo_va: requested BO and VM object
 * @clear: if true clear the entries
 *
 * Fill in the page table entries for @bo_va.
 *
 * Returns:
 * 0 for success, -EINVAL for failure.
 */
int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
			bool clear)
{
	struct amdgpu_bo *bo = bo_va->base.bo;
	struct amdgpu_vm *vm = bo_va->base.vm;
	struct amdgpu_bo_va_mapping *mapping;
	dma_addr_t *pages_addr = NULL;
	struct ttm_resource *mem;
	struct dma_fence **last_update;
	bool flush_tlb = clear;
	bool uncached;
	struct dma_resv *resv;
	uint64_t vram_base;
	uint64_t flags;
	int r;

	if (clear || !bo) {
		mem = NULL;
		resv = vm->root.bo->tbo.base.resv;
	} else {
		struct drm_gem_object *obj = &bo->tbo.base;

		resv = bo->tbo.base.resv;
		if (obj->import_attach && bo_va->is_xgmi) {
			struct dma_buf *dma_buf = obj->import_attach->dmabuf;
			struct drm_gem_object *gobj = dma_buf->priv;
			struct amdgpu_bo *abo = gem_to_amdgpu_bo(gobj);

			if (abo->tbo.resource &&
			    abo->tbo.resource->mem_type == TTM_PL_VRAM)
				bo = gem_to_amdgpu_bo(gobj);
		}
		mem = bo->tbo.resource;
		if (mem && (mem->mem_type == TTM_PL_TT ||
			    mem->mem_type == AMDGPU_PL_PREEMPT))
			pages_addr = bo->tbo.ttm->dma_address;
	}

	if (bo) {
		struct amdgpu_device *bo_adev;

		flags = amdgpu_ttm_tt_pte_flags(adev, bo->tbo.ttm, mem);

		if (amdgpu_bo_encrypted(bo))
			flags |= AMDGPU_PTE_TMZ;

		bo_adev = amdgpu_ttm_adev(bo->tbo.bdev);
		vram_base = bo_adev->vm_manager.vram_base_offset;
		uncached = (bo->flags & AMDGPU_GEM_CREATE_UNCACHED) != 0;
	} else {
		flags = 0x0;
		vram_base = 0;
		uncached = false;
	}

	if (clear || (bo && bo->tbo.base.resv ==
		      vm->root.bo->tbo.base.resv))
		last_update = &vm->last_update;
	else
		last_update = &bo_va->last_pt_update;

	if (!clear && bo_va->base.moved) {
		flush_tlb = true;
		list_splice_init(&bo_va->valids, &bo_va->invalids);

	} else if (bo_va->cleared != clear) {
		list_splice_init(&bo_va->valids, &bo_va->invalids);
	}

	list_for_each_entry(mapping, &bo_va->invalids, list) {
		uint64_t update_flags = flags;

		/* normally,bo_va->flags only contians READABLE and WIRTEABLE bit go here
		 * but in case of something, we filter the flags in first place
		 */
		if (!(mapping->flags & AMDGPU_PTE_READABLE))
			update_flags &= ~AMDGPU_PTE_READABLE;
		if (!(mapping->flags & AMDGPU_PTE_WRITEABLE))
			update_flags &= ~AMDGPU_PTE_WRITEABLE;

		/* Apply ASIC specific mapping flags */
		amdgpu_gmc_get_vm_pte(adev, mapping, &update_flags);

		trace_amdgpu_vm_bo_update(mapping);

		r = amdgpu_vm_update_range(adev, vm, false, false, flush_tlb,
					   !uncached, resv, mapping->start, mapping->last,
					   update_flags, mapping->offset,
					   vram_base, mem, pages_addr,
					   last_update);
		if (r)
			return r;
	}

	/* If the BO is not in its preferred location add it back to
	 * the evicted list so that it gets validated again on the
	 * next command submission.
	 */
	if (bo && bo->tbo.base.resv == vm->root.bo->tbo.base.resv) {
		uint32_t mem_type = bo->tbo.resource->mem_type;

		if (!(bo->preferred_domains &
		      amdgpu_mem_type_to_domain(mem_type)))
			amdgpu_vm_bo_evicted(&bo_va->base);
		else
			amdgpu_vm_bo_idle(&bo_va->base);
	} else {
		amdgpu_vm_bo_done(&bo_va->base);
	}

	list_splice_init(&bo_va->invalids, &bo_va->valids);
	bo_va->cleared = clear;
	bo_va->base.moved = false;

	if (trace_amdgpu_vm_bo_mapping_enabled()) {
		list_for_each_entry(mapping, &bo_va->valids, list)
			trace_amdgpu_vm_bo_mapping(mapping);
	}

	return 0;
}

/**
 * amdgpu_vm_update_prt_state - update the global PRT state
 *
 * @adev: amdgpu_device pointer
 */
static void amdgpu_vm_update_prt_state(struct amdgpu_device *adev)
{
	unsigned long flags;
	bool enable;

	spin_lock_irqsave(&adev->vm_manager.prt_lock, flags);
	enable = !!atomic_read(&adev->vm_manager.num_prt_users);
	adev->gmc.gmc_funcs->set_prt(adev, enable);
	spin_unlock_irqrestore(&adev->vm_manager.prt_lock, flags);
}

/**
 * amdgpu_vm_prt_get - add a PRT user
 *
 * @adev: amdgpu_device pointer
 */
static void amdgpu_vm_prt_get(struct amdgpu_device *adev)
{
	if (!adev->gmc.gmc_funcs->set_prt)
		return;

	if (atomic_inc_return(&adev->vm_manager.num_prt_users) == 1)
		amdgpu_vm_update_prt_state(adev);
}

/**
 * amdgpu_vm_prt_put - drop a PRT user
 *
 * @adev: amdgpu_device pointer
 */
static void amdgpu_vm_prt_put(struct amdgpu_device *adev)
{
	if (atomic_dec_return(&adev->vm_manager.num_prt_users) == 0)
		amdgpu_vm_update_prt_state(adev);
}

/**
 * amdgpu_vm_prt_cb - callback for updating the PRT status
 *
 * @fence: fence for the callback
 * @_cb: the callback function
 */
static void amdgpu_vm_prt_cb(struct dma_fence *fence, struct dma_fence_cb *_cb)
{
	struct amdgpu_prt_cb *cb = container_of(_cb, struct amdgpu_prt_cb, cb);

	amdgpu_vm_prt_put(cb->adev);
	kfree(cb);
}

/**
 * amdgpu_vm_add_prt_cb - add callback for updating the PRT status
 *
 * @adev: amdgpu_device pointer
 * @fence: fence for the callback
 */
static void amdgpu_vm_add_prt_cb(struct amdgpu_device *adev,
				 struct dma_fence *fence)
{
	struct amdgpu_prt_cb *cb;

	if (!adev->gmc.gmc_funcs->set_prt)
		return;

	cb = kmalloc(sizeof(struct amdgpu_prt_cb), GFP_KERNEL);
	if (!cb) {
		/* Last resort when we are OOM */
		if (fence)
			dma_fence_wait(fence, false);

		amdgpu_vm_prt_put(adev);
	} else {
		cb->adev = adev;
		if (!fence || dma_fence_add_callback(fence, &cb->cb,
						     amdgpu_vm_prt_cb))
			amdgpu_vm_prt_cb(fence, &cb->cb);
	}
}

/**
 * amdgpu_vm_free_mapping - free a mapping
 *
 * @adev: amdgpu_device pointer
 * @vm: requested vm
 * @mapping: mapping to be freed
 * @fence: fence of the unmap operation
 *
 * Free a mapping and make sure we decrease the PRT usage count if applicable.
 */
static void amdgpu_vm_free_mapping(struct amdgpu_device *adev,
				   struct amdgpu_vm *vm,
				   struct amdgpu_bo_va_mapping *mapping,
				   struct dma_fence *fence)
{
	if (mapping->flags & AMDGPU_PTE_PRT)
		amdgpu_vm_add_prt_cb(adev, fence);
	kfree(mapping);
}

/**
 * amdgpu_vm_prt_fini - finish all prt mappings
 *
 * @adev: amdgpu_device pointer
 * @vm: requested vm
 *
 * Register a cleanup callback to disable PRT support after VM dies.
 */
static void amdgpu_vm_prt_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
{
	struct dma_resv *resv = vm->root.bo->tbo.base.resv;
	struct dma_resv_iter cursor;
	struct dma_fence *fence;

	dma_resv_for_each_fence(&cursor, resv, DMA_RESV_USAGE_BOOKKEEP, fence) {
		/* Add a callback for each fence in the reservation object */
		amdgpu_vm_prt_get(adev);
		amdgpu_vm_add_prt_cb(adev, fence);
	}
}

/**
 * amdgpu_vm_clear_freed - clear freed BOs in the PT
 *
 * @adev: amdgpu_device pointer
 * @vm: requested vm
 * @fence: optional resulting fence (unchanged if no work needed to be done
 * or if an error occurred)
 *
 * Make sure all freed BOs are cleared in the PT.
 * PTs have to be reserved and mutex must be locked!
 *
 * Returns:
 * 0 for success.
 *
 */
int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
			  struct amdgpu_vm *vm,
			  struct dma_fence **fence)
{
	struct dma_resv *resv = vm->root.bo->tbo.base.resv;
	struct amdgpu_bo_va_mapping *mapping;
	uint64_t init_pte_value = 0;
	struct dma_fence *f = NULL;
	int r;

	while (!list_empty(&vm->freed)) {
		mapping = list_first_entry(&vm->freed,
			struct amdgpu_bo_va_mapping, list);
		list_del(&mapping->list);

		r = amdgpu_vm_update_range(adev, vm, false, false, true, false,
					   resv, mapping->start, mapping->last,
					   init_pte_value, 0, 0, NULL, NULL,
					   &f);
		amdgpu_vm_free_mapping(adev, vm, mapping, f);
		if (r) {
			dma_fence_put(f);
			return r;
		}
	}

	if (fence && f) {
		dma_fence_put(*fence);
		*fence = f;
	} else {
		dma_fence_put(f);
	}

	return 0;

}

/**
 * amdgpu_vm_handle_moved - handle moved BOs in the PT
 *
 * @adev: amdgpu_device pointer
 * @vm: requested vm
 * @ticket: optional reservation ticket used to reserve the VM
 *
 * Make sure all BOs which are moved are updated in the PTs.
 *
 * Returns:
 * 0 for success.
 *
 * PTs have to be reserved!
 */
int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
			   struct amdgpu_vm *vm,
			   struct ww_acquire_ctx *ticket)
{
	struct amdgpu_bo_va *bo_va;
	struct dma_resv *resv;
	bool clear, unlock;
	int r;

	spin_lock(&vm->status_lock);
	while (!list_empty(&vm->moved)) {
		bo_va = list_first_entry(&vm->moved, struct amdgpu_bo_va,
					 base.vm_status);
		spin_unlock(&vm->status_lock);

		/* Per VM BOs never need to bo cleared in the page tables */
		r = amdgpu_vm_bo_update(adev, bo_va, false);
		if (r)
			return r;
		spin_lock(&vm->status_lock);
	}

	while (!list_empty(&vm->invalidated)) {
		bo_va = list_first_entry(&vm->invalidated, struct amdgpu_bo_va,
					 base.vm_status);
		resv = bo_va->base.bo->tbo.base.resv;
		spin_unlock(&vm->status_lock);

		/* Try to reserve the BO to avoid clearing its ptes */
		if (!adev->debug_vm && dma_resv_trylock(resv)) {
			clear = false;
			unlock = true;
		/* The caller is already holding the reservation lock */
		} else if (ticket && dma_resv_locking_ctx(resv) == ticket) {
			clear = false;
			unlock = false;
		/* Somebody else is using the BO right now */
		} else {
			clear = true;
			unlock = false;
		}

		r = amdgpu_vm_bo_update(adev, bo_va, clear);

		if (unlock)
			dma_resv_unlock(resv);
		if (r)
			return r;

		/* Remember evicted DMABuf imports in compute VMs for later
		 * validation
		 */
		if (vm->is_compute_context &&
		    bo_va->base.bo->tbo.base.import_attach &&
		    (!bo_va->base.bo->tbo.resource ||
		     bo_va->base.bo->tbo.resource->mem_type == TTM_PL_SYSTEM))
			amdgpu_vm_bo_evicted_user(&bo_va->base);

		spin_lock(&vm->status_lock);
	}
	spin_unlock(&vm->status_lock);

	return 0;
}

/**
 * amdgpu_vm_flush_compute_tlb - Flush TLB on compute VM
 *
 * @adev: amdgpu_device pointer
 * @vm: requested vm
 * @flush_type: flush type
 * @xcc_mask: mask of XCCs that belong to the compute partition in need of a TLB flush.
 *
 * Flush TLB if needed for a compute VM.
 *
 * Returns:
 * 0 for success.
 */
int amdgpu_vm_flush_compute_tlb(struct amdgpu_device *adev,
				struct amdgpu_vm *vm,
				uint32_t flush_type,
				uint32_t xcc_mask)
{
	uint64_t tlb_seq = amdgpu_vm_tlb_seq(vm);
	bool all_hub = false;
	int xcc = 0, r = 0;

	WARN_ON_ONCE(!vm->is_compute_context);

	/*
	 * It can be that we race and lose here, but that is extremely unlikely
	 * and the worst thing which could happen is that we flush the changes
	 * into the TLB once more which is harmless.
	 */
	if (atomic64_xchg(&vm->kfd_last_flushed_seq, tlb_seq) == tlb_seq)
		return 0;

	if (adev->family == AMDGPU_FAMILY_AI ||
	    adev->family == AMDGPU_FAMILY_RV)
		all_hub = true;

	for_each_inst(xcc, xcc_mask) {
		r = amdgpu_gmc_flush_gpu_tlb_pasid(adev, vm->pasid, flush_type,
						   all_hub, xcc);
		if (r)
			break;
	}
	return r;
}

/**
 * amdgpu_vm_bo_add - add a bo to a specific vm
 *
 * @adev: amdgpu_device pointer
 * @vm: requested vm
 * @bo: amdgpu buffer object
 *
 * Add @bo into the requested vm.
 * Add @bo to the list of bos associated with the vm
 *
 * Returns:
 * Newly added bo_va or NULL for failure
 *
 * Object has to be reserved!
 */
struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev,
				      struct amdgpu_vm *vm,
				      struct amdgpu_bo *bo)
{
	struct amdgpu_bo_va *bo_va;

	bo_va = kzalloc(sizeof(struct amdgpu_bo_va), GFP_KERNEL);
	if (bo_va == NULL) {
		return NULL;
	}
	amdgpu_vm_bo_base_init(&bo_va->base, vm, bo);

	bo_va->ref_count = 1;
	bo_va->last_pt_update = dma_fence_get_stub();
	INIT_LIST_HEAD(&bo_va->valids);
	INIT_LIST_HEAD(&bo_va->invalids);

	if (!bo)
		return bo_va;

	dma_resv_assert_held(bo->tbo.base.resv);
	if (amdgpu_dmabuf_is_xgmi_accessible(adev, bo)) {
		bo_va->is_xgmi = true;
		/* Power up XGMI if it can be potentially used */
		amdgpu_xgmi_set_pstate(adev, AMDGPU_XGMI_PSTATE_MAX_VEGA20);
	}

	return bo_va;
}


/**
 * amdgpu_vm_bo_insert_map - insert a new mapping
 *
 * @adev: amdgpu_device pointer
 * @bo_va: bo_va to store the address
 * @mapping: the mapping to insert
 *
 * Insert a new mapping into all structures.
 */
static void amdgpu_vm_bo_insert_map(struct amdgpu_device *adev,
				    struct amdgpu_bo_va *bo_va,
				    struct amdgpu_bo_va_mapping *mapping)
{
	struct amdgpu_vm *vm = bo_va->base.vm;
	struct amdgpu_bo *bo = bo_va->base.bo;

	mapping->bo_va = bo_va;
	list_add(&mapping->list, &bo_va->invalids);
	amdgpu_vm_it_insert(mapping, &vm->va);

	if (mapping->flags & AMDGPU_PTE_PRT)
		amdgpu_vm_prt_get(adev);

	if (bo && bo->tbo.base.resv == vm->root.bo->tbo.base.resv &&
	    !bo_va->base.moved) {
		amdgpu_vm_bo_moved(&bo_va->base);
	}
	trace_amdgpu_vm_bo_map(bo_va, mapping);
}

/* Validate operation parameters to prevent potential abuse */
static int amdgpu_vm_verify_parameters(struct amdgpu_device *adev,
					  struct amdgpu_bo *bo,
					  uint64_t saddr,
					  uint64_t offset,
					  uint64_t size)
{
	uint64_t tmp, lpfn;

	if (saddr & AMDGPU_GPU_PAGE_MASK
	    || offset & AMDGPU_GPU_PAGE_MASK
	    || size & AMDGPU_GPU_PAGE_MASK)
		return -EINVAL;

	if (check_add_overflow(saddr, size, &tmp)
	    || check_add_overflow(offset, size, &tmp)
	    || size == 0 /* which also leads to end < begin */)
		return -EINVAL;

	/* make sure object fit at this offset */
	if (bo && offset + size > amdgpu_bo_size(bo))
		return -EINVAL;

	/* Ensure last pfn not exceed max_pfn */
	lpfn = (saddr + size - 1) >> AMDGPU_GPU_PAGE_SHIFT;
	if (lpfn >= adev->vm_manager.max_pfn)
		return -EINVAL;

	return 0;
}

/**
 * amdgpu_vm_bo_map - map bo inside a vm
 *
 * @adev: amdgpu_device pointer
 * @bo_va: bo_va to store the address
 * @saddr: where to map the BO
 * @offset: requested offset in the BO
 * @size: BO size in bytes
 * @flags: attributes of pages (read/write/valid/etc.)
 *
 * Add a mapping of the BO at the specefied addr into the VM.
 *
 * Returns:
 * 0 for success, error for failure.
 *
 * Object has to be reserved and unreserved outside!
 */
int amdgpu_vm_bo_map(struct amdgpu_device *adev,
		     struct amdgpu_bo_va *bo_va,
		     uint64_t saddr, uint64_t offset,
		     uint64_t size, uint64_t flags)
{
	struct amdgpu_bo_va_mapping *mapping, *tmp;
	struct amdgpu_bo *bo = bo_va->base.bo;
	struct amdgpu_vm *vm = bo_va->base.vm;
	uint64_t eaddr;
	int r;

	r = amdgpu_vm_verify_parameters(adev, bo, saddr, offset, size);
	if (r)
		return r;

	saddr /= AMDGPU_GPU_PAGE_SIZE;
	eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE;

	tmp = amdgpu_vm_it_iter_first(&vm->va, saddr, eaddr);
	if (tmp) {
		/* bo and tmp overlap, invalid addr */
		dev_err(adev->dev, "bo %p va 0x%010Lx-0x%010Lx conflict with "
			"0x%010Lx-0x%010Lx\n", bo, saddr, eaddr,
			tmp->start, tmp->last + 1);
		return -EINVAL;
	}

	mapping = kmalloc(sizeof(*mapping), GFP_KERNEL);
	if (!mapping)
		return -ENOMEM;

	mapping->start = saddr;
	mapping->last = eaddr;
	mapping->offset = offset;
	mapping->flags = flags;

	amdgpu_vm_bo_insert_map(adev, bo_va, mapping);

	return 0;
}

/**
 * amdgpu_vm_bo_replace_map - map bo inside a vm, replacing existing mappings
 *
 * @adev: amdgpu_device pointer
 * @bo_va: bo_va to store the address
 * @saddr: where to map the BO
 * @offset: requested offset in the BO
 * @size: BO size in bytes
 * @flags: attributes of pages (read/write/valid/etc.)
 *
 * Add a mapping of the BO at the specefied addr into the VM. Replace existing
 * mappings as we do so.
 *
 * Returns:
 * 0 for success, error for failure.
 *
 * Object has to be reserved and unreserved outside!
 */
int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev,
			     struct amdgpu_bo_va *bo_va,
			     uint64_t saddr, uint64_t offset,
			     uint64_t size, uint64_t flags)
{
	struct amdgpu_bo_va_mapping *mapping;
	struct amdgpu_bo *bo = bo_va->base.bo;
	uint64_t eaddr;
	int r;

	r = amdgpu_vm_verify_parameters(adev, bo, saddr, offset, size);
	if (r)
		return r;

	/* Allocate all the needed memory */
	mapping = kmalloc(sizeof(*mapping), GFP_KERNEL);
	if (!mapping)
		return -ENOMEM;

	r = amdgpu_vm_bo_clear_mappings(adev, bo_va->base.vm, saddr, size);
	if (r) {
		kfree(mapping);
		return r;
	}

	saddr /= AMDGPU_GPU_PAGE_SIZE;
	eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE;

	mapping->start = saddr;
	mapping->last = eaddr;
	mapping->offset = offset;
	mapping->flags = flags;

	amdgpu_vm_bo_insert_map(adev, bo_va, mapping);

	return 0;
}

/**
 * amdgpu_vm_bo_unmap - remove bo mapping from vm
 *
 * @adev: amdgpu_device pointer
 * @bo_va: bo_va to remove the address from
 * @saddr: where to the BO is mapped
 *
 * Remove a mapping of the BO at the specefied addr from the VM.
 *
 * Returns:
 * 0 for success, error for failure.
 *
 * Object has to be reserved and unreserved outside!
 */
int amdgpu_vm_bo_unmap(struct amdgpu_device *adev,
		       struct amdgpu_bo_va *bo_va,
		       uint64_t saddr)
{
	struct amdgpu_bo_va_mapping *mapping;
	struct amdgpu_vm *vm = bo_va->base.vm;
	bool valid = true;

	saddr /= AMDGPU_GPU_PAGE_SIZE;

	list_for_each_entry(mapping, &bo_va->valids, list) {
		if (mapping->start == saddr)
			break;
	}

	if (&mapping->list == &bo_va->valids) {
		valid = false;

		list_for_each_entry(mapping, &bo_va->invalids, list) {
			if (mapping->start == saddr)
				break;
		}

		if (&mapping->list == &bo_va->invalids)
			return -ENOENT;
	}

	list_del(&mapping->list);
	amdgpu_vm_it_remove(mapping, &vm->va);
	mapping->bo_va = NULL;
	trace_amdgpu_vm_bo_unmap(bo_va, mapping);

	if (valid)
		list_add(&mapping->list, &vm->freed);
	else
		amdgpu_vm_free_mapping(adev, vm, mapping,
				       bo_va->last_pt_update);

	return 0;
}

/**
 * amdgpu_vm_bo_clear_mappings - remove all mappings in a specific range
 *
 * @adev: amdgpu_device pointer
 * @vm: VM structure to use
 * @saddr: start of the range
 * @size: size of the range
 *
 * Remove all mappings in a range, split them as appropriate.
 *
 * Returns:
 * 0 for success, error for failure.
 */
int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev,
				struct amdgpu_vm *vm,
				uint64_t saddr, uint64_t size)
{
	struct amdgpu_bo_va_mapping *before, *after, *tmp, *next;
	LIST_HEAD(removed);
	uint64_t eaddr;
	int r;

	r = amdgpu_vm_verify_parameters(adev, NULL, saddr, 0, size);
	if (r)
		return r;

	saddr /= AMDGPU_GPU_PAGE_SIZE;
	eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE;

	/* Allocate all the needed memory */
	before = kzalloc(sizeof(*before), GFP_KERNEL);
	if (!before)
		return -ENOMEM;
	INIT_LIST_HEAD(&before->list);

	after = kzalloc(sizeof(*after), GFP_KERNEL);
	if (!after) {
		kfree(before);
		return -ENOMEM;
	}
	INIT_LIST_HEAD(&after->list);

	/* Now gather all removed mappings */
	tmp = amdgpu_vm_it_iter_first(&vm->va, saddr, eaddr);
	while (tmp) {
		/* Remember mapping split at the start */
		if (tmp->start < saddr) {
			before->start = tmp->start;
			before->last = saddr - 1;
			before->offset = tmp->offset;
			before->flags = tmp->flags;
			before->bo_va = tmp->bo_va;
			list_add(&before->list, &tmp->bo_va->invalids);
		}

		/* Remember mapping split at the end */
		if (tmp->last > eaddr) {
			after->start = eaddr + 1;
			after->last = tmp->last;
			after->offset = tmp->offset;
			after->offset += (after->start - tmp->start) << PAGE_SHIFT;
			after->flags = tmp->flags;
			after->bo_va = tmp->bo_va;
			list_add(&after->list, &tmp->bo_va->invalids);
		}

		list_del(&tmp->list);
		list_add(&tmp->list, &removed);

		tmp = amdgpu_vm_it_iter_next(tmp, saddr, eaddr);
	}

	/* And free them up */
	list_for_each_entry_safe(tmp, next, &removed, list) {
		amdgpu_vm_it_remove(tmp, &vm->va);
		list_del(&tmp->list);

		if (tmp->start < saddr)
		    tmp->start = saddr;
		if (tmp->last > eaddr)
		    tmp->last = eaddr;

		tmp->bo_va = NULL;
		list_add(&tmp->list, &vm->freed);
		trace_amdgpu_vm_bo_unmap(NULL, tmp);
	}

	/* Insert partial mapping before the range */
	if (!list_empty(&before->list)) {
		struct amdgpu_bo *bo = before->bo_va->base.bo;

		amdgpu_vm_it_insert(before, &vm->va);
		if (before->flags & AMDGPU_PTE_PRT)
			amdgpu_vm_prt_get(adev);

		if (bo && bo->tbo.base.resv == vm->root.bo->tbo.base.resv &&
		    !before->bo_va->base.moved)
			amdgpu_vm_bo_moved(&before->bo_va->base);
	} else {
		kfree(before);
	}

	/* Insert partial mapping after the range */
	if (!list_empty(&after->list)) {
		struct amdgpu_bo *bo = after->bo_va->base.bo;

		amdgpu_vm_it_insert(after, &vm->va);
		if (after->flags & AMDGPU_PTE_PRT)
			amdgpu_vm_prt_get(adev);

		if (bo && bo->tbo.base.resv == vm->root.bo->tbo.base.resv &&
		    !after->bo_va->base.moved)
			amdgpu_vm_bo_moved(&after->bo_va->base);
	} else {
		kfree(after);
	}

	return 0;
}

/**
 * amdgpu_vm_bo_lookup_mapping - find mapping by address
 *
 * @vm: the requested VM
 * @addr: the address
 *
 * Find a mapping by it's address.
 *
 * Returns:
 * The amdgpu_bo_va_mapping matching for addr or NULL
 *
 */
struct amdgpu_bo_va_mapping *amdgpu_vm_bo_lookup_mapping(struct amdgpu_vm *vm,
							 uint64_t addr)
{
	return amdgpu_vm_it_iter_first(&vm->va, addr, addr);
}

/**
 * amdgpu_vm_bo_trace_cs - trace all reserved mappings
 *
 * @vm: the requested vm
 * @ticket: CS ticket
 *
 * Trace all mappings of BOs reserved during a command submission.
 */
void amdgpu_vm_bo_trace_cs(struct amdgpu_vm *vm, struct ww_acquire_ctx *ticket)
{
	struct amdgpu_bo_va_mapping *mapping;

	if (!trace_amdgpu_vm_bo_cs_enabled())
		return;

	for (mapping = amdgpu_vm_it_iter_first(&vm->va, 0, U64_MAX); mapping;
	     mapping = amdgpu_vm_it_iter_next(mapping, 0, U64_MAX)) {
		if (mapping->bo_va && mapping->bo_va->base.bo) {
			struct amdgpu_bo *bo;

			bo = mapping->bo_va->base.bo;
			if (dma_resv_locking_ctx(bo->tbo.base.resv) !=
			    ticket)
				continue;
		}

		trace_amdgpu_vm_bo_cs(mapping);
	}
}

/**
 * amdgpu_vm_bo_del - remove a bo from a specific vm
 *
 * @adev: amdgpu_device pointer
 * @bo_va: requested bo_va
 *
 * Remove @bo_va->bo from the requested vm.
 *
 * Object have to be reserved!
 */
void amdgpu_vm_bo_del(struct amdgpu_device *adev,
		      struct amdgpu_bo_va *bo_va)
{
	struct amdgpu_bo_va_mapping *mapping, *next;
	struct amdgpu_bo *bo = bo_va->base.bo;
	struct amdgpu_vm *vm = bo_va->base.vm;
	struct amdgpu_vm_bo_base **base;

	dma_resv_assert_held(vm->root.bo->tbo.base.resv);

	if (bo) {
		dma_resv_assert_held(bo->tbo.base.resv);
		if (bo->tbo.base.resv == vm->root.bo->tbo.base.resv)
			ttm_bo_set_bulk_move(&bo->tbo, NULL);

		for (base = &bo_va->base.bo->vm_bo; *base;
		     base = &(*base)->next) {
			if (*base != &bo_va->base)
				continue;

			*base = bo_va->base.next;
			break;
		}
	}

	spin_lock(&vm->status_lock);
	list_del(&bo_va->base.vm_status);
	spin_unlock(&vm->status_lock);

	list_for_each_entry_safe(mapping, next, &bo_va->valids, list) {
		list_del(&mapping->list);
		amdgpu_vm_it_remove(mapping, &vm->va);
		mapping->bo_va = NULL;
		trace_amdgpu_vm_bo_unmap(bo_va, mapping);
		list_add(&mapping->list, &vm->freed);
	}
	list_for_each_entry_safe(mapping, next, &bo_va->invalids, list) {
		list_del(&mapping->list);
		amdgpu_vm_it_remove(mapping, &vm->va);
		amdgpu_vm_free_mapping(adev, vm, mapping,
				       bo_va->last_pt_update);
	}

	dma_fence_put(bo_va->last_pt_update);

	if (bo && bo_va->is_xgmi)
		amdgpu_xgmi_set_pstate(adev, AMDGPU_XGMI_PSTATE_MIN);

	kfree(bo_va);
}

/**
 * amdgpu_vm_evictable - check if we can evict a VM
 *
 * @bo: A page table of the VM.
 *
 * Check if it is possible to evict a VM.
 */
bool amdgpu_vm_evictable(struct amdgpu_bo *bo)
{
	struct amdgpu_vm_bo_base *bo_base = bo->vm_bo;

	/* Page tables of a destroyed VM can go away immediately */
	if (!bo_base || !bo_base->vm)
		return true;

	/* Don't evict VM page tables while they are busy */
	if (!dma_resv_test_signaled(bo->tbo.base.resv, DMA_RESV_USAGE_BOOKKEEP))
		return false;

	/* Try to block ongoing updates */
	if (!amdgpu_vm_eviction_trylock(bo_base->vm))
		return false;

	/* Don't evict VM page tables while they are updated */
	if (!dma_fence_is_signaled(bo_base->vm->last_unlocked)) {
		amdgpu_vm_eviction_unlock(bo_base->vm);
		return false;
	}

	bo_base->vm->evicting = true;
	amdgpu_vm_eviction_unlock(bo_base->vm);
	return true;
}

/**
 * amdgpu_vm_bo_invalidate - mark the bo as invalid
 *
 * @adev: amdgpu_device pointer
 * @bo: amdgpu buffer object
 * @evicted: is the BO evicted
 *
 * Mark @bo as invalid.
 */
void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev,
			     struct amdgpu_bo *bo, bool evicted)
{
	struct amdgpu_vm_bo_base *bo_base;

	/* shadow bo doesn't have bo base, its validation needs its parent */
	if (bo->parent && (amdgpu_bo_shadowed(bo->parent) == bo))
		bo = bo->parent;

	for (bo_base = bo->vm_bo; bo_base; bo_base = bo_base->next) {
		struct amdgpu_vm *vm = bo_base->vm;

		if (evicted && bo->tbo.base.resv == vm->root.bo->tbo.base.resv) {
			amdgpu_vm_bo_evicted(bo_base);
			continue;
		}

		if (bo_base->moved)
			continue;
		bo_base->moved = true;

		if (bo->tbo.type == ttm_bo_type_kernel)
			amdgpu_vm_bo_relocated(bo_base);
		else if (bo->tbo.base.resv == vm->root.bo->tbo.base.resv)
			amdgpu_vm_bo_moved(bo_base);
		else
			amdgpu_vm_bo_invalidated(bo_base);
	}
}

/**
 * amdgpu_vm_get_block_size - calculate VM page table size as power of two
 *
 * @vm_size: VM size
 *
 * Returns:
 * VM page table as power of two
 */
static uint32_t amdgpu_vm_get_block_size(uint64_t vm_size)
{
	/* Total bits covered by PD + PTs */
	unsigned bits = ilog2(vm_size) + 18;

	/* Make sure the PD is 4K in size up to 8GB address space.
	   Above that split equal between PD and PTs */
	if (vm_size <= 8)
		return (bits - 9);
	else
		return ((bits + 3) / 2);
}

/**
 * amdgpu_vm_adjust_size - adjust vm size, block size and fragment size
 *
 * @adev: amdgpu_device pointer
 * @min_vm_size: the minimum vm size in GB if it's set auto
 * @fragment_size_default: Default PTE fragment size
 * @max_level: max VMPT level
 * @max_bits: max address space size in bits
 *
 */
void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t min_vm_size,
			   uint32_t fragment_size_default, unsigned max_level,
			   unsigned max_bits)
{
	unsigned int max_size = 1 << (max_bits - 30);
	unsigned int vm_size;
	uint64_t tmp;

	/* adjust vm size first */
	if (amdgpu_vm_size != -1) {
		vm_size = amdgpu_vm_size;
		if (vm_size > max_size) {
			dev_warn(adev->dev, "VM size (%d) too large, max is %u GB\n",
				 amdgpu_vm_size, max_size);
			vm_size = max_size;
		}
	} else {
		struct sysinfo si;
		unsigned int phys_ram_gb;

		/* Optimal VM size depends on the amount of physical
		 * RAM available. Underlying requirements and
		 * assumptions:
		 *
		 *  - Need to map system memory and VRAM from all GPUs
		 *     - VRAM from other GPUs not known here
		 *     - Assume VRAM <= system memory
		 *  - On GFX8 and older, VM space can be segmented for
		 *    different MTYPEs
		 *  - Need to allow room for fragmentation, guard pages etc.
		 *
		 * This adds up to a rough guess of system memory x3.
		 * Round up to power of two to maximize the available
		 * VM size with the given page table size.
		 */
		si_meminfo(&si);
		phys_ram_gb = ((uint64_t)si.totalram * si.mem_unit +
			       (1 << 30) - 1) >> 30;
		vm_size = roundup_pow_of_two(
			min(max(phys_ram_gb * 3, min_vm_size), max_size));
	}

	adev->vm_manager.max_pfn = (uint64_t)vm_size << 18;

	tmp = roundup_pow_of_two(adev->vm_manager.max_pfn);
	if (amdgpu_vm_block_size != -1)
		tmp >>= amdgpu_vm_block_size - 9;
	tmp = DIV_ROUND_UP(fls64(tmp) - 1, 9) - 1;
	adev->vm_manager.num_level = min_t(unsigned int, max_level, tmp);
	switch (adev->vm_manager.num_level) {
	case 3:
		adev->vm_manager.root_level = AMDGPU_VM_PDB2;
		break;
	case 2:
		adev->vm_manager.root_level = AMDGPU_VM_PDB1;
		break;
	case 1:
		adev->vm_manager.root_level = AMDGPU_VM_PDB0;
		break;
	default:
		dev_err(adev->dev, "VMPT only supports 2~4+1 levels\n");
	}
	/* block size depends on vm size and hw setup*/
	if (amdgpu_vm_block_size != -1)
		adev->vm_manager.block_size =
			min((unsigned)amdgpu_vm_block_size, max_bits
			    - AMDGPU_GPU_PAGE_SHIFT
			    - 9 * adev->vm_manager.num_level);
	else if (adev->vm_manager.num_level > 1)
		adev->vm_manager.block_size = 9;
	else
		adev->vm_manager.block_size = amdgpu_vm_get_block_size(tmp);

	if (amdgpu_vm_fragment_size == -1)
		adev->vm_manager.fragment_size = fragment_size_default;
	else
		adev->vm_manager.fragment_size = amdgpu_vm_fragment_size;

	DRM_INFO("vm size is %u GB, %u levels, block size is %u-bit, fragment size is %u-bit\n",
		 vm_size, adev->vm_manager.num_level + 1,
		 adev->vm_manager.block_size,
		 adev->vm_manager.fragment_size);
}

/**
 * amdgpu_vm_wait_idle - wait for the VM to become idle
 *
 * @vm: VM object to wait for
 * @timeout: timeout to wait for VM to become idle
 */
long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout)
{
	timeout = dma_resv_wait_timeout(vm->root.bo->tbo.base.resv,
					DMA_RESV_USAGE_BOOKKEEP,
					true, timeout);
	if (timeout <= 0)
		return timeout;

	return dma_fence_wait_timeout(vm->last_unlocked, true, timeout);
}

static void amdgpu_vm_destroy_task_info(struct kref *kref)
{
	struct amdgpu_task_info *ti = container_of(kref, struct amdgpu_task_info, refcount);

	kfree(ti);
}

static inline struct amdgpu_vm *
amdgpu_vm_get_vm_from_pasid(struct amdgpu_device *adev, u32 pasid)
{
	struct amdgpu_vm *vm;
	unsigned long flags;

	xa_lock_irqsave(&adev->vm_manager.pasids, flags);
	vm = xa_load(&adev->vm_manager.pasids, pasid);
	xa_unlock_irqrestore(&adev->vm_manager.pasids, flags);

	return vm;
}

/**
 * amdgpu_vm_put_task_info - reference down the vm task_info ptr
 *
 * @task_info: task_info struct under discussion.
 *
 * frees the vm task_info ptr at the last put
 */
void amdgpu_vm_put_task_info(struct amdgpu_task_info *task_info)
{
	kref_put(&task_info->refcount, amdgpu_vm_destroy_task_info);
}

/**
 * amdgpu_vm_get_task_info_vm - Extracts task info for a vm.
 *
 * @vm: VM to get info from
 *
 * Returns the reference counted task_info structure, which must be
 * referenced down with amdgpu_vm_put_task_info.
 */
struct amdgpu_task_info *
amdgpu_vm_get_task_info_vm(struct amdgpu_vm *vm)
{
	struct amdgpu_task_info *ti = NULL;

	if (vm) {
		ti = vm->task_info;
		kref_get(&vm->task_info->refcount);
	}

	return ti;
}

/**
 * amdgpu_vm_get_task_info_pasid - Extracts task info for a PASID.
 *
 * @adev: drm device pointer
 * @pasid: PASID identifier for VM
 *
 * Returns the reference counted task_info structure, which must be
 * referenced down with amdgpu_vm_put_task_info.
 */
struct amdgpu_task_info *
amdgpu_vm_get_task_info_pasid(struct amdgpu_device *adev, u32 pasid)
{
	return amdgpu_vm_get_task_info_vm(
			amdgpu_vm_get_vm_from_pasid(adev, pasid));
}

static int amdgpu_vm_create_task_info(struct amdgpu_vm *vm)
{
	vm->task_info = kzalloc(sizeof(struct amdgpu_task_info), GFP_KERNEL);
	if (!vm->task_info)
		return -ENOMEM;

	kref_init(&vm->task_info->refcount);
	return 0;
}

/**
 * amdgpu_vm_set_task_info - Sets VMs task info.
 *
 * @vm: vm for which to set the info
 */
void amdgpu_vm_set_task_info(struct amdgpu_vm *vm)
{
	if (!vm->task_info)
		return;

	if (vm->task_info->pid == current->pid)
		return;

	vm->task_info->pid = current->pid;
	get_task_comm(vm->task_info->task_name, current);

	if (current->group_leader->mm != current->mm)
		return;

	vm->task_info->tgid = current->group_leader->pid;
	get_task_comm(vm->task_info->process_name, current->group_leader);
}

/**
 * amdgpu_vm_init - initialize a vm instance
 *
 * @adev: amdgpu_device pointer
 * @vm: requested vm
 * @xcp_id: GPU partition selection id
 *
 * Init @vm fields.
 *
 * Returns:
 * 0 for success, error for failure.
 */
int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
		   int32_t xcp_id)
{
	struct amdgpu_bo *root_bo;
	struct amdgpu_bo_vm *root;
	int r, i;

	vm->va = RB_ROOT_CACHED;
	for (i = 0; i < AMDGPU_MAX_VMHUBS; i++)
		vm->reserved_vmid[i] = NULL;
	INIT_LIST_HEAD(&vm->evicted);
	INIT_LIST_HEAD(&vm->evicted_user);
	INIT_LIST_HEAD(&vm->relocated);
	INIT_LIST_HEAD(&vm->moved);
	INIT_LIST_HEAD(&vm->idle);
	INIT_LIST_HEAD(&vm->invalidated);
	spin_lock_init(&vm->status_lock);
	INIT_LIST_HEAD(&vm->freed);
	INIT_LIST_HEAD(&vm->done);
	INIT_LIST_HEAD(&vm->pt_freed);
	INIT_WORK(&vm->pt_free_work, amdgpu_vm_pt_free_work);
	INIT_KFIFO(vm->faults);

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

	vm->is_compute_context = false;

	vm->use_cpu_for_update = !!(adev->vm_manager.vm_update_mode &
				    AMDGPU_VM_USE_CPU_FOR_GFX);

	DRM_DEBUG_DRIVER("VM update mode is %s\n",
			 vm->use_cpu_for_update ? "CPU" : "SDMA");
	WARN_ONCE((vm->use_cpu_for_update &&
		   !amdgpu_gmc_vram_full_visible(&adev->gmc)),
		  "CPU update of VM recommended only for large BAR system\n");

	if (vm->use_cpu_for_update)
		vm->update_funcs = &amdgpu_vm_cpu_funcs;
	else
		vm->update_funcs = &amdgpu_vm_sdma_funcs;

	vm->last_update = dma_fence_get_stub();
	vm->last_unlocked = dma_fence_get_stub();
	vm->last_tlb_flush = dma_fence_get_stub();
	vm->generation = 0;

	mutex_init(&vm->eviction_lock);
	vm->evicting = false;

	r = amdgpu_vm_pt_create(adev, vm, adev->vm_manager.root_level,
				false, &root, xcp_id);
	if (r)
		goto error_free_delayed;

	root_bo = amdgpu_bo_ref(&root->bo);
	r = amdgpu_bo_reserve(root_bo, true);
	if (r) {
		amdgpu_bo_unref(&root->shadow);
		amdgpu_bo_unref(&root_bo);
		goto error_free_delayed;
	}

	amdgpu_vm_bo_base_init(&vm->root, vm, root_bo);
	r = dma_resv_reserve_fences(root_bo->tbo.base.resv, 1);
	if (r)
		goto error_free_root;

	r = amdgpu_vm_pt_clear(adev, vm, root, false);
	if (r)
		goto error_free_root;

	r = amdgpu_vm_create_task_info(vm);
	if (r)
		DRM_DEBUG("Failed to create task info for VM\n");

	amdgpu_bo_unreserve(vm->root.bo);
	amdgpu_bo_unref(&root_bo);

	return 0;

error_free_root:
	amdgpu_vm_pt_free_root(adev, vm);
	amdgpu_bo_unreserve(vm->root.bo);
	amdgpu_bo_unref(&root_bo);

error_free_delayed:
	dma_fence_put(vm->last_tlb_flush);
	dma_fence_put(vm->last_unlocked);
	amdgpu_vm_fini_entities(vm);

	return r;
}

/**
 * amdgpu_vm_make_compute - Turn a GFX VM into a compute VM
 *
 * @adev: amdgpu_device pointer
 * @vm: requested vm
 *
 * This only works on GFX VMs that don't have any BOs added and no
 * page tables allocated yet.
 *
 * Changes the following VM parameters:
 * - use_cpu_for_update
 * - pte_supports_ats
 *
 * Reinitializes the page directory to reflect the changed ATS
 * setting.
 *
 * Returns:
 * 0 for success, -errno for errors.
 */
int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm)
{
	int r;

	r = amdgpu_bo_reserve(vm->root.bo, true);
	if (r)
		return r;

	/* Update VM state */
	vm->use_cpu_for_update = !!(adev->vm_manager.vm_update_mode &
				    AMDGPU_VM_USE_CPU_FOR_COMPUTE);
	DRM_DEBUG_DRIVER("VM update mode is %s\n",
			 vm->use_cpu_for_update ? "CPU" : "SDMA");
	WARN_ONCE((vm->use_cpu_for_update &&
		   !amdgpu_gmc_vram_full_visible(&adev->gmc)),
		  "CPU update of VM recommended only for large BAR system\n");

	if (vm->use_cpu_for_update) {
		/* Sync with last SDMA update/clear before switching to CPU */
		r = amdgpu_bo_sync_wait(vm->root.bo,
					AMDGPU_FENCE_OWNER_UNDEFINED, true);
		if (r)
			goto unreserve_bo;

		vm->update_funcs = &amdgpu_vm_cpu_funcs;
		r = amdgpu_vm_pt_map_tables(adev, vm);
		if (r)
			goto unreserve_bo;

	} else {
		vm->update_funcs = &amdgpu_vm_sdma_funcs;
	}

	dma_fence_put(vm->last_update);
	vm->last_update = dma_fence_get_stub();
	vm->is_compute_context = true;

	/* Free the shadow bo for compute VM */
	amdgpu_bo_unref(&to_amdgpu_bo_vm(vm->root.bo)->shadow);

	goto unreserve_bo;

unreserve_bo:
	amdgpu_bo_unreserve(vm->root.bo);
	return r;
}

/**
 * amdgpu_vm_release_compute - release a compute vm
 * @adev: amdgpu_device pointer
 * @vm: a vm turned into compute vm by calling amdgpu_vm_make_compute
 *
 * This is a correspondant of amdgpu_vm_make_compute. It decouples compute
 * pasid from vm. Compute should stop use of vm after this call.
 */
void amdgpu_vm_release_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm)
{
	amdgpu_vm_set_pasid(adev, vm, 0);
	vm->is_compute_context = false;
}

/**
 * amdgpu_vm_fini - tear down a vm instance
 *
 * @adev: amdgpu_device pointer
 * @vm: requested vm
 *
 * Tear down @vm.
 * Unbind the VM and remove all bos from the vm bo list
 */
void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
{
	struct amdgpu_bo_va_mapping *mapping, *tmp;
	bool prt_fini_needed = !!adev->gmc.gmc_funcs->set_prt;
	struct amdgpu_bo *root;
	unsigned long flags;
	int i;

	amdgpu_amdkfd_gpuvm_destroy_cb(adev, vm);

	flush_work(&vm->pt_free_work);

	root = amdgpu_bo_ref(vm->root.bo);
	amdgpu_bo_reserve(root, true);
	amdgpu_vm_put_task_info(vm->task_info);
	amdgpu_vm_set_pasid(adev, vm, 0);
	dma_fence_wait(vm->last_unlocked, false);
	dma_fence_put(vm->last_unlocked);
	dma_fence_wait(vm->last_tlb_flush, false);
	/* Make sure that all fence callbacks have completed */
	spin_lock_irqsave(vm->last_tlb_flush->lock, flags);
	spin_unlock_irqrestore(vm->last_tlb_flush->lock, flags);
	dma_fence_put(vm->last_tlb_flush);

	list_for_each_entry_safe(mapping, tmp, &vm->freed, list) {
		if (mapping->flags & AMDGPU_PTE_PRT && prt_fini_needed) {
			amdgpu_vm_prt_fini(adev, vm);
			prt_fini_needed = false;
		}

		list_del(&mapping->list);
		amdgpu_vm_free_mapping(adev, vm, mapping, NULL);
	}

	amdgpu_vm_pt_free_root(adev, vm);
	amdgpu_bo_unreserve(root);
	amdgpu_bo_unref(&root);
	WARN_ON(vm->root.bo);

	amdgpu_vm_fini_entities(vm);

	if (!RB_EMPTY_ROOT(&vm->va.rb_root)) {
		dev_err(adev->dev, "still active bo inside vm\n");
	}
	rbtree_postorder_for_each_entry_safe(mapping, tmp,
					     &vm->va.rb_root, rb) {
		/* Don't remove the mapping here, we don't want to trigger a
		 * rebalance and the tree is about to be destroyed anyway.
		 */
		list_del(&mapping->list);
		kfree(mapping);
	}

	dma_fence_put(vm->last_update);

	for (i = 0; i < AMDGPU_MAX_VMHUBS; i++) {
		if (vm->reserved_vmid[i]) {
			amdgpu_vmid_free_reserved(adev, i);
			vm->reserved_vmid[i] = false;
		}
	}

}

/**
 * amdgpu_vm_manager_init - init the VM manager
 *
 * @adev: amdgpu_device pointer
 *
 * Initialize the VM manager structures
 */
void amdgpu_vm_manager_init(struct amdgpu_device *adev)
{
	unsigned i;

	/* Concurrent flushes are only possible starting with Vega10 and
	 * are broken on Navi10 and Navi14.
	 */
	adev->vm_manager.concurrent_flush = !(adev->asic_type < CHIP_VEGA10 ||
					      adev->asic_type == CHIP_NAVI10 ||
					      adev->asic_type == CHIP_NAVI14);
	amdgpu_vmid_mgr_init(adev);

	adev->vm_manager.fence_context =
		dma_fence_context_alloc(AMDGPU_MAX_RINGS);
	for (i = 0; i < AMDGPU_MAX_RINGS; ++i)
		adev->vm_manager.seqno[i] = 0;

	spin_lock_init(&adev->vm_manager.prt_lock);
	atomic_set(&adev->vm_manager.num_prt_users, 0);

	/* If not overridden by the user, by default, only in large BAR systems
	 * Compute VM tables will be updated by CPU
	 */
#ifdef CONFIG_X86_64
	if (amdgpu_vm_update_mode == -1) {
		/* For asic with VF MMIO access protection
		 * avoid using CPU for VM table updates
		 */
		if (amdgpu_gmc_vram_full_visible(&adev->gmc) &&
		    !amdgpu_sriov_vf_mmio_access_protection(adev))
			adev->vm_manager.vm_update_mode =
				AMDGPU_VM_USE_CPU_FOR_COMPUTE;
		else
			adev->vm_manager.vm_update_mode = 0;
	} else
		adev->vm_manager.vm_update_mode = amdgpu_vm_update_mode;
#else
	adev->vm_manager.vm_update_mode = 0;
#endif

	xa_init_flags(&adev->vm_manager.pasids, XA_FLAGS_LOCK_IRQ);
}

/**
 * amdgpu_vm_manager_fini - cleanup VM manager
 *
 * @adev: amdgpu_device pointer
 *
 * Cleanup the VM manager and free resources.
 */
void amdgpu_vm_manager_fini(struct amdgpu_device *adev)
{
	WARN_ON(!xa_empty(&adev->vm_manager.pasids));
	xa_destroy(&adev->vm_manager.pasids);

	amdgpu_vmid_mgr_fini(adev);
}

/**
 * amdgpu_vm_ioctl - Manages VMID reservation for vm hubs.
 *
 * @dev: drm device pointer
 * @data: drm_amdgpu_vm
 * @filp: drm file pointer
 *
 * Returns:
 * 0 for success, -errno for errors.
 */
int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
{
	union drm_amdgpu_vm *args = data;
	struct amdgpu_device *adev = drm_to_adev(dev);
	struct amdgpu_fpriv *fpriv = filp->driver_priv;

	/* No valid flags defined yet */
	if (args->in.flags)
		return -EINVAL;

	switch (args->in.op) {
	case AMDGPU_VM_OP_RESERVE_VMID:
		/* We only have requirement to reserve vmid from gfxhub */
		if (!fpriv->vm.reserved_vmid[AMDGPU_GFXHUB(0)]) {
			amdgpu_vmid_alloc_reserved(adev, AMDGPU_GFXHUB(0));
			fpriv->vm.reserved_vmid[AMDGPU_GFXHUB(0)] = true;
		}

		break;
	case AMDGPU_VM_OP_UNRESERVE_VMID:
		if (fpriv->vm.reserved_vmid[AMDGPU_GFXHUB(0)]) {
			amdgpu_vmid_free_reserved(adev, AMDGPU_GFXHUB(0));
			fpriv->vm.reserved_vmid[AMDGPU_GFXHUB(0)] = false;
		}
		break;
	default:
		return -EINVAL;
	}

	return 0;
}

/**
 * amdgpu_vm_handle_fault - graceful handling of VM faults.
 * @adev: amdgpu device pointer
 * @pasid: PASID of the VM
 * @vmid: VMID, only used for GFX 9.4.3.
 * @node_id: Node_id received in IH cookie. Only applicable for
 *           GFX 9.4.3.
 * @addr: Address of the fault
 * @write_fault: true is write fault, false is read fault
 *
 * Try to gracefully handle a VM fault. Return true if the fault was handled and
 * shouldn't be reported any more.
 */
bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
			    u32 vmid, u32 node_id, uint64_t addr,
			    bool write_fault)
{
	bool is_compute_context = false;
	struct amdgpu_bo *root;
	unsigned long irqflags;
	uint64_t value, flags;
	struct amdgpu_vm *vm;
	int r;

	xa_lock_irqsave(&adev->vm_manager.pasids, irqflags);
	vm = xa_load(&adev->vm_manager.pasids, pasid);
	if (vm) {
		root = amdgpu_bo_ref(vm->root.bo);
		is_compute_context = vm->is_compute_context;
	} else {
		root = NULL;
	}
	xa_unlock_irqrestore(&adev->vm_manager.pasids, irqflags);

	if (!root)
		return false;

	addr /= AMDGPU_GPU_PAGE_SIZE;

	if (is_compute_context && !svm_range_restore_pages(adev, pasid, vmid,
	    node_id, addr, write_fault)) {
		amdgpu_bo_unref(&root);
		return true;
	}

	r = amdgpu_bo_reserve(root, true);
	if (r)
		goto error_unref;

	/* Double check that the VM still exists */
	xa_lock_irqsave(&adev->vm_manager.pasids, irqflags);
	vm = xa_load(&adev->vm_manager.pasids, pasid);
	if (vm && vm->root.bo != root)
		vm = NULL;
	xa_unlock_irqrestore(&adev->vm_manager.pasids, irqflags);
	if (!vm)
		goto error_unlock;

	flags = AMDGPU_PTE_VALID | AMDGPU_PTE_SNOOPED |
		AMDGPU_PTE_SYSTEM;

	if (is_compute_context) {
		/* Intentionally setting invalid PTE flag
		 * combination to force a no-retry-fault
		 */
		flags = AMDGPU_VM_NORETRY_FLAGS;
		value = 0;
	} else if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_NEVER) {
		/* Redirect the access to the dummy page */
		value = adev->dummy_page_addr;
		flags |= AMDGPU_PTE_EXECUTABLE | AMDGPU_PTE_READABLE |
			AMDGPU_PTE_WRITEABLE;

	} else {
		/* Let the hw retry silently on the PTE */
		value = 0;
	}

	r = dma_resv_reserve_fences(root->tbo.base.resv, 1);
	if (r) {
		pr_debug("failed %d to reserve fence slot\n", r);
		goto error_unlock;
	}

	r = amdgpu_vm_update_range(adev, vm, true, false, false, false,
				   NULL, addr, addr, flags, value, 0, NULL, NULL, NULL);
	if (r)
		goto error_unlock;

	r = amdgpu_vm_update_pdes(adev, vm, true);

error_unlock:
	amdgpu_bo_unreserve(root);
	if (r < 0)
		DRM_ERROR("Can't handle page fault (%d)\n", r);

error_unref:
	amdgpu_bo_unref(&root);

	return false;
}

#if defined(CONFIG_DEBUG_FS)
/**
 * amdgpu_debugfs_vm_bo_info  - print BO info for the VM
 *
 * @vm: Requested VM for printing BO info
 * @m: debugfs file
 *
 * Print BO information in debugfs file for the VM
 */
void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m)
{
	struct amdgpu_bo_va *bo_va, *tmp;
	u64 total_idle = 0;
	u64 total_evicted = 0;
	u64 total_relocated = 0;
	u64 total_moved = 0;
	u64 total_invalidated = 0;
	u64 total_done = 0;
	unsigned int total_idle_objs = 0;
	unsigned int total_evicted_objs = 0;
	unsigned int total_relocated_objs = 0;
	unsigned int total_moved_objs = 0;
	unsigned int total_invalidated_objs = 0;
	unsigned int total_done_objs = 0;
	unsigned int id = 0;

	spin_lock(&vm->status_lock);
	seq_puts(m, "\tIdle BOs:\n");
	list_for_each_entry_safe(bo_va, tmp, &vm->idle, base.vm_status) {
		if (!bo_va->base.bo)
			continue;
		total_idle += amdgpu_bo_print_info(id++, bo_va->base.bo, m);
	}
	total_idle_objs = id;
	id = 0;

	seq_puts(m, "\tEvicted BOs:\n");
	list_for_each_entry_safe(bo_va, tmp, &vm->evicted, base.vm_status) {
		if (!bo_va->base.bo)
			continue;
		total_evicted += amdgpu_bo_print_info(id++, bo_va->base.bo, m);
	}
	total_evicted_objs = id;
	id = 0;

	seq_puts(m, "\tRelocated BOs:\n");
	list_for_each_entry_safe(bo_va, tmp, &vm->relocated, base.vm_status) {
		if (!bo_va->base.bo)
			continue;
		total_relocated += amdgpu_bo_print_info(id++, bo_va->base.bo, m);
	}
	total_relocated_objs = id;
	id = 0;

	seq_puts(m, "\tMoved BOs:\n");
	list_for_each_entry_safe(bo_va, tmp, &vm->moved, base.vm_status) {
		if (!bo_va->base.bo)
			continue;
		total_moved += amdgpu_bo_print_info(id++, bo_va->base.bo, m);
	}
	total_moved_objs = id;
	id = 0;

	seq_puts(m, "\tInvalidated BOs:\n");
	list_for_each_entry_safe(bo_va, tmp, &vm->invalidated, base.vm_status) {
		if (!bo_va->base.bo)
			continue;
		total_invalidated += amdgpu_bo_print_info(id++,	bo_va->base.bo, m);
	}
	total_invalidated_objs = id;
	id = 0;

	seq_puts(m, "\tDone BOs:\n");
	list_for_each_entry_safe(bo_va, tmp, &vm->done, base.vm_status) {
		if (!bo_va->base.bo)
			continue;
		total_done += amdgpu_bo_print_info(id++, bo_va->base.bo, m);
	}
	spin_unlock(&vm->status_lock);
	total_done_objs = id;

	seq_printf(m, "\tTotal idle size:        %12lld\tobjs:\t%d\n", total_idle,
		   total_idle_objs);
	seq_printf(m, "\tTotal evicted size:     %12lld\tobjs:\t%d\n", total_evicted,
		   total_evicted_objs);
	seq_printf(m, "\tTotal relocated size:   %12lld\tobjs:\t%d\n", total_relocated,
		   total_relocated_objs);
	seq_printf(m, "\tTotal moved size:       %12lld\tobjs:\t%d\n", total_moved,
		   total_moved_objs);
	seq_printf(m, "\tTotal invalidated size: %12lld\tobjs:\t%d\n", total_invalidated,
		   total_invalidated_objs);
	seq_printf(m, "\tTotal done size:        %12lld\tobjs:\t%d\n", total_done,
		   total_done_objs);
}
#endif

/**
 * amdgpu_vm_update_fault_cache - update cached fault into.
 * @adev: amdgpu device pointer
 * @pasid: PASID of the VM
 * @addr: Address of the fault
 * @status: GPUVM fault status register
 * @vmhub: which vmhub got the fault
 *
 * Cache the fault info for later use by userspace in debugging.
 */
void amdgpu_vm_update_fault_cache(struct amdgpu_device *adev,
				  unsigned int pasid,
				  uint64_t addr,
				  uint32_t status,
				  unsigned int vmhub)
{
	struct amdgpu_vm *vm;
	unsigned long flags;

	xa_lock_irqsave(&adev->vm_manager.pasids, flags);

	vm = xa_load(&adev->vm_manager.pasids, pasid);
	/* Don't update the fault cache if status is 0.  In the multiple
	 * fault case, subsequent faults will return a 0 status which is
	 * useless for userspace and replaces the useful fault status, so
	 * only update if status is non-0.
	 */
	if (vm && status) {
		vm->fault_info.addr = addr;
		vm->fault_info.status = status;
		if (AMDGPU_IS_GFXHUB(vmhub)) {
			vm->fault_info.vmhub = AMDGPU_VMHUB_TYPE_GFX;
			vm->fault_info.vmhub |=
				(vmhub - AMDGPU_GFXHUB_START) << AMDGPU_VMHUB_IDX_SHIFT;
		} else if (AMDGPU_IS_MMHUB0(vmhub)) {
			vm->fault_info.vmhub = AMDGPU_VMHUB_TYPE_MM0;
			vm->fault_info.vmhub |=
				(vmhub - AMDGPU_MMHUB0_START) << AMDGPU_VMHUB_IDX_SHIFT;
		} else if (AMDGPU_IS_MMHUB1(vmhub)) {
			vm->fault_info.vmhub = AMDGPU_VMHUB_TYPE_MM1;
			vm->fault_info.vmhub |=
				(vmhub - AMDGPU_MMHUB1_START) << AMDGPU_VMHUB_IDX_SHIFT;
		} else {
			WARN_ONCE(1, "Invalid vmhub %u\n", vmhub);
		}
	}
	xa_unlock_irqrestore(&adev->vm_manager.pasids, flags);
}