summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/drm_gpuva_mgr.c
blob: f86bfad74ff8a2aef4324ef72bbe6f18527f0dc4 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (c) 2022 Red Hat.
 *
 * 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:
 *     Danilo Krummrich <dakr@redhat.com>
 *
 */

#include <drm/drm_gpuva_mgr.h>

#include <linux/interval_tree_generic.h>
#include <linux/mm.h>

/**
 * DOC: Overview
 *
 * The DRM GPU VA Manager, represented by struct drm_gpuva_manager keeps track
 * of a GPU's virtual address (VA) space and manages the corresponding virtual
 * mappings represented by &drm_gpuva objects. It also keeps track of the
 * mapping's backing &drm_gem_object buffers.
 *
 * &drm_gem_object buffers maintain a list of &drm_gpuva objects representing
 * all existent GPU VA mappings using this &drm_gem_object as backing buffer.
 *
 * GPU VAs can be flagged as sparse, such that drivers may use GPU VAs to also
 * keep track of sparse PTEs in order to support Vulkan 'Sparse Resources'.
 *
 * The GPU VA manager internally uses a rb-tree to manage the
 * &drm_gpuva mappings within a GPU's virtual address space.
 *
 * The &drm_gpuva_manager contains a special &drm_gpuva representing the
 * portion of VA space reserved by the kernel. This node is initialized together
 * with the GPU VA manager instance and removed when the GPU VA manager is
 * destroyed.
 *
 * In a typical application drivers would embed struct drm_gpuva_manager and
 * struct drm_gpuva within their own driver specific structures, there won't be
 * any memory allocations of its own nor memory allocations of &drm_gpuva
 * entries.
 *
 * The data structures needed to store &drm_gpuvas within the &drm_gpuva_manager
 * are contained within struct drm_gpuva already. Hence, for inserting
 * &drm_gpuva entries from within dma-fence signalling critical sections it is
 * enough to pre-allocate the &drm_gpuva structures.
 */

/**
 * DOC: Split and Merge
 *
 * Besides its capability to manage and represent a GPU VA space, the
 * &drm_gpuva_manager also provides functions to let the &drm_gpuva_manager
 * calculate a sequence of operations to satisfy a given map or unmap request.
 *
 * Therefore the DRM GPU VA manager provides an algorithm implementing splitting
 * and merging of existent GPU VA mappings with the ones that are requested to
 * be mapped or unmapped. This feature is required by the Vulkan API to
 * implement Vulkan 'Sparse Memory Bindings' - drivers UAPIs often refer to this
 * as VM BIND.
 *
 * Drivers can call drm_gpuva_sm_map() to receive a sequence of callbacks
 * containing map, unmap and remap operations for a given newly requested
 * mapping. The sequence of callbacks represents the set of operations to
 * execute in order to integrate the new mapping cleanly into the current state
 * of the GPU VA space.
 *
 * Depending on how the new GPU VA mapping intersects with the existent mappings
 * of the GPU VA space the &drm_gpuva_fn_ops callbacks contain an arbitrary
 * amount of unmap operations, a maximum of two remap operations and a single
 * map operation. The caller might receive no callback at all if no operation is
 * required, e.g. if the requested mapping already exists in the exact same way.
 *
 * The single map operation represents the original map operation requested by
 * the caller.
 *
 * &drm_gpuva_op_unmap contains a 'keep' field, which indicates whether the
 * &drm_gpuva to unmap is physically contiguous with the original mapping
 * request. Optionally, if 'keep' is set, drivers may keep the actual page table
 * entries for this &drm_gpuva, adding the missing page table entries only and
 * update the &drm_gpuva_manager's view of things accordingly.
 *
 * Drivers may do the same optimization, namely delta page table updates, also
 * for remap operations. This is possible since &drm_gpuva_op_remap consists of
 * one unmap operation and one or two map operations, such that drivers can
 * derive the page table update delta accordingly.
 *
 * Note that there can't be more than two existent mappings to split up, one at
 * the beginning and one at the end of the new mapping, hence there is a
 * maximum of two remap operations.
 *
 * Analogous to drm_gpuva_sm_map() drm_gpuva_sm_unmap() uses &drm_gpuva_fn_ops
 * to call back into the driver in order to unmap a range of GPU VA space. The
 * logic behind this function is way simpler though: For all existent mappings
 * enclosed by the given range unmap operations are created. For mappings which
 * are only partically located within the given range, remap operations are
 * created such that those mappings are split up and re-mapped partically.
 *
 * As an alternative to drm_gpuva_sm_map() and drm_gpuva_sm_unmap(),
 * drm_gpuva_sm_map_ops_create() and drm_gpuva_sm_unmap_ops_create() can be used
 * to directly obtain an instance of struct drm_gpuva_ops containing a list of
 * &drm_gpuva_op, which can be iterated with drm_gpuva_for_each_op(). This list
 * contains the &drm_gpuva_ops analogous to the callbacks one would receive when
 * calling drm_gpuva_sm_map() or drm_gpuva_sm_unmap(). While this way requires
 * more memory (to allocate the &drm_gpuva_ops), it provides drivers a way to
 * iterate the &drm_gpuva_op multiple times, e.g. once in a context where memory
 * allocations are possible (e.g. to allocate GPU page tables) and once in the
 * dma-fence signalling critical path.
 *
 * To update the &drm_gpuva_manager's view of the GPU VA space
 * drm_gpuva_insert() and drm_gpuva_remove() may be used. These functions can
 * safely be used from &drm_gpuva_fn_ops callbacks originating from
 * drm_gpuva_sm_map() or drm_gpuva_sm_unmap(). However, it might be more
 * convenient to use the provided helper functions drm_gpuva_map(),
 * drm_gpuva_remap() and drm_gpuva_unmap() instead.
 *
 * The following diagram depicts the basic relationships of existent GPU VA
 * mappings, a newly requested mapping and the resulting mappings as implemented
 * by drm_gpuva_sm_map() - it doesn't cover any arbitrary combinations of these.
 *
 * 1) Requested mapping is identical. Replace it, but indicate the backing PTEs
 *    could be kept.
 *
 *    ::
 *
 *	     0     a     1
 *	old: |-----------| (bo_offset=n)
 *
 *	     0     a     1
 *	req: |-----------| (bo_offset=n)
 *
 *	     0     a     1
 *	new: |-----------| (bo_offset=n)
 *
 *
 * 2) Requested mapping is identical, except for the BO offset, hence replace
 *    the mapping.
 *
 *    ::
 *
 *	     0     a     1
 *	old: |-----------| (bo_offset=n)
 *
 *	     0     a     1
 *	req: |-----------| (bo_offset=m)
 *
 *	     0     a     1
 *	new: |-----------| (bo_offset=m)
 *
 *
 * 3) Requested mapping is identical, except for the backing BO, hence replace
 *    the mapping.
 *
 *    ::
 *
 *	     0     a     1
 *	old: |-----------| (bo_offset=n)
 *
 *	     0     b     1
 *	req: |-----------| (bo_offset=n)
 *
 *	     0     b     1
 *	new: |-----------| (bo_offset=n)
 *
 *
 * 4) Existent mapping is a left aligned subset of the requested one, hence
 *    replace the existent one.
 *
 *    ::
 *
 *	     0  a  1
 *	old: |-----|       (bo_offset=n)
 *
 *	     0     a     2
 *	req: |-----------| (bo_offset=n)
 *
 *	     0     a     2
 *	new: |-----------| (bo_offset=n)
 *
 *    .. note::
 *       We expect to see the same result for a request with a different BO
 *       and/or non-contiguous BO offset.
 *
 *
 * 5) Requested mapping's range is a left aligned subset of the existent one,
 *    but backed by a different BO. Hence, map the requested mapping and split
 *    the existent one adjusting its BO offset.
 *
 *    ::
 *
 *	     0     a     2
 *	old: |-----------| (bo_offset=n)
 *
 *	     0  b  1
 *	req: |-----|       (bo_offset=n)
 *
 *	     0  b  1  a' 2
 *	new: |-----|-----| (b.bo_offset=n, a.bo_offset=n+1)
 *
 *    .. note::
 *       We expect to see the same result for a request with a different BO
 *       and/or non-contiguous BO offset.
 *
 *
 * 6) Existent mapping is a superset of the requested mapping. Split it up, but
 *    indicate that the backing PTEs could be kept.
 *
 *    ::
 *
 *	     0     a     2
 *	old: |-----------| (bo_offset=n)
 *
 *	     0  a  1
 *	req: |-----|       (bo_offset=n)
 *
 *	     0  a  1  a' 2
 *	new: |-----|-----| (a.bo_offset=n, a'.bo_offset=n+1)
 *
 *
 * 7) Requested mapping's range is a right aligned subset of the existent one,
 *    but backed by a different BO. Hence, map the requested mapping and split
 *    the existent one, without adjusting the BO offset.
 *
 *    ::
 *
 *	     0     a     2
 *	old: |-----------| (bo_offset=n)
 *
 *	           1  b  2
 *	req:       |-----| (bo_offset=m)
 *
 *	     0  a  1  b  2
 *	new: |-----|-----| (a.bo_offset=n,b.bo_offset=m)
 *
 *
 * 8) Existent mapping is a superset of the requested mapping. Split it up, but
 *    indicate that the backing PTEs could be kept.
 *
 *    ::
 *
 *	      0     a     2
 *	old: |-----------| (bo_offset=n)
 *
 *	           1  a  2
 *	req:       |-----| (bo_offset=n+1)
 *
 *	     0  a' 1  a  2
 *	new: |-----|-----| (a'.bo_offset=n, a.bo_offset=n+1)
 *
 *
 * 9) Existent mapping is overlapped at the end by the requested mapping backed
 *    by a different BO. Hence, map the requested mapping and split up the
 *    existent one, without adjusting the BO offset.
 *
 *    ::
 *
 *	     0     a     2
 *	old: |-----------|       (bo_offset=n)
 *
 *	           1     b     3
 *	req:       |-----------| (bo_offset=m)
 *
 *	     0  a  1     b     3
 *	new: |-----|-----------| (a.bo_offset=n,b.bo_offset=m)
 *
 *
 * 10) Existent mapping is overlapped by the requested mapping, both having the
 *     same backing BO with a contiguous offset. Indicate the backing PTEs of
 *     the old mapping could be kept.
 *
 *     ::
 *
 *	      0     a     2
 *	 old: |-----------|       (bo_offset=n)
 *
 *	            1     a     3
 *	 req:       |-----------| (bo_offset=n+1)
 *
 *	      0  a' 1     a     3
 *	 new: |-----|-----------| (a'.bo_offset=n, a.bo_offset=n+1)
 *
 *
 * 11) Requested mapping's range is a centered subset of the existent one
 *     having a different backing BO. Hence, map the requested mapping and split
 *     up the existent one in two mappings, adjusting the BO offset of the right
 *     one accordingly.
 *
 *     ::
 *
 *	      0        a        3
 *	 old: |-----------------| (bo_offset=n)
 *
 *	            1  b  2
 *	 req:       |-----|       (bo_offset=m)
 *
 *	      0  a  1  b  2  a' 3
 *	 new: |-----|-----|-----| (a.bo_offset=n,b.bo_offset=m,a'.bo_offset=n+2)
 *
 *
 * 12) Requested mapping is a contiguous subset of the existent one. Split it
 *     up, but indicate that the backing PTEs could be kept.
 *
 *     ::
 *
 *	      0        a        3
 *	 old: |-----------------| (bo_offset=n)
 *
 *	            1  a  2
 *	 req:       |-----|       (bo_offset=n+1)
 *
 *	      0  a' 1  a  2 a'' 3
 *	 old: |-----|-----|-----| (a'.bo_offset=n, a.bo_offset=n+1, a''.bo_offset=n+2)
 *
 *
 * 13) Existent mapping is a right aligned subset of the requested one, hence
 *     replace the existent one.
 *
 *     ::
 *
 *	            1  a  2
 *	 old:       |-----| (bo_offset=n+1)
 *
 *	      0     a     2
 *	 req: |-----------| (bo_offset=n)
 *
 *	      0     a     2
 *	 new: |-----------| (bo_offset=n)
 *
 *     .. note::
 *        We expect to see the same result for a request with a different bo
 *        and/or non-contiguous bo_offset.
 *
 *
 * 14) Existent mapping is a centered subset of the requested one, hence
 *     replace the existent one.
 *
 *     ::
 *
 *	            1  a  2
 *	 old:       |-----| (bo_offset=n+1)
 *
 *	      0        a       3
 *	 req: |----------------| (bo_offset=n)
 *
 *	      0        a       3
 *	 new: |----------------| (bo_offset=n)
 *
 *     .. note::
 *        We expect to see the same result for a request with a different bo
 *        and/or non-contiguous bo_offset.
 *
 *
 * 15) Existent mappings is overlapped at the beginning by the requested mapping
 *     backed by a different BO. Hence, map the requested mapping and split up
 *     the existent one, adjusting its BO offset accordingly.
 *
 *     ::
 *
 *	            1     a     3
 *	 old:       |-----------| (bo_offset=n)
 *
 *	      0     b     2
 *	 req: |-----------|       (bo_offset=m)
 *
 *	      0     b     2  a' 3
 *	 new: |-----------|-----| (b.bo_offset=m,a.bo_offset=n+2)
 */

/**
 * DOC: Locking
 *
 * Generally, the GPU VA manager does not take care of locking itself, it is
 * the drivers responsibility to take care about locking. Drivers might want to
 * protect the following operations: inserting, removing and iterating
 * &drm_gpuva objects as well as generating all kinds of operations, such as
 * split / merge or prefetch.
 *
 * The GPU VA manager also does not take care of the locking of the backing
 * &drm_gem_object buffers GPU VA lists by itself; drivers are responsible to
 * enforce mutual exclusion using either the GEMs dma_resv lock or alternatively
 * a driver specific external lock. For the latter see also
 * drm_gem_gpuva_set_lock().
 *
 * However, the GPU VA manager contains lockdep checks to ensure callers of its
 * API hold the corresponding lock whenever the &drm_gem_objects GPU VA list is
 * accessed by functions such as drm_gpuva_link() or drm_gpuva_unlink().
 */

/**
 * DOC: Examples
 *
 * This section gives two examples on how to let the DRM GPUVA Manager generate
 * &drm_gpuva_op in order to satisfy a given map or unmap request and how to
 * make use of them.
 *
 * The below code is strictly limited to illustrate the generic usage pattern.
 * To maintain simplicitly, it doesn't make use of any abstractions for common
 * code, different (asyncronous) stages with fence signalling critical paths,
 * any other helpers or error handling in terms of freeing memory and dropping
 * previously taken locks.
 *
 * 1) Obtain a list of &drm_gpuva_op to create a new mapping::
 *
 *	// Allocates a new &drm_gpuva.
 *	struct drm_gpuva * driver_gpuva_alloc(void);
 *
 *	// Typically drivers would embedd the &drm_gpuva_manager and &drm_gpuva
 *	// structure in individual driver structures and lock the dma-resv with
 *	// drm_exec or similar helpers.
 *	int driver_mapping_create(struct drm_gpuva_manager *mgr,
 *				  u64 addr, u64 range,
 *				  struct drm_gem_object *obj, u64 offset)
 *	{
 *		struct drm_gpuva_ops *ops;
 *		struct drm_gpuva_op *op
 *
 *		driver_lock_va_space();
 *		ops = drm_gpuva_sm_map_ops_create(mgr, addr, range,
 *						  obj, offset);
 *		if (IS_ERR(ops))
 *			return PTR_ERR(ops);
 *
 *		drm_gpuva_for_each_op(op, ops) {
 *			struct drm_gpuva *va;
 *
 *			switch (op->op) {
 *			case DRM_GPUVA_OP_MAP:
 *				va = driver_gpuva_alloc();
 *				if (!va)
 *					; // unwind previous VA space updates,
 *					  // free memory and unlock
 *
 *				driver_vm_map();
 *				drm_gpuva_map(mgr, va, &op->map);
 *				drm_gpuva_link(va);
 *
 *				break;
 *			case DRM_GPUVA_OP_REMAP: {
 *				struct drm_gpuva *prev = NULL, *next = NULL;
 *
 *				va = op->remap.unmap->va;
 *
 *				if (op->remap.prev) {
 *					prev = driver_gpuva_alloc();
 *					if (!prev)
 *						; // unwind previous VA space
 *						  // updates, free memory and
 *						  // unlock
 *				}
 *
 *				if (op->remap.next) {
 *					next = driver_gpuva_alloc();
 *					if (!next)
 *						; // unwind previous VA space
 *						  // updates, free memory and
 *						  // unlock
 *				}
 *
 *				driver_vm_remap();
 *				drm_gpuva_remap(prev, next, &op->remap);
 *
 *				drm_gpuva_unlink(va);
 *				if (prev)
 *					drm_gpuva_link(prev);
 *				if (next)
 *					drm_gpuva_link(next);
 *
 *				break;
 *			}
 *			case DRM_GPUVA_OP_UNMAP:
 *				va = op->unmap->va;
 *
 *				driver_vm_unmap();
 *				drm_gpuva_unlink(va);
 *				drm_gpuva_unmap(&op->unmap);
 *
 *				break;
 *			default:
 *				break;
 *			}
 *		}
 *		driver_unlock_va_space();
 *
 *		return 0;
 *	}
 *
 * 2) Receive a callback for each &drm_gpuva_op to create a new mapping::
 *
 *	struct driver_context {
 *		struct drm_gpuva_manager *mgr;
 *		struct drm_gpuva *new_va;
 *		struct drm_gpuva *prev_va;
 *		struct drm_gpuva *next_va;
 *	};
 *
 *	// ops to pass to drm_gpuva_manager_init()
 *	static const struct drm_gpuva_fn_ops driver_gpuva_ops = {
 *		.sm_step_map = driver_gpuva_map,
 *		.sm_step_remap = driver_gpuva_remap,
 *		.sm_step_unmap = driver_gpuva_unmap,
 *	};
 *
 *	// Typically drivers would embedd the &drm_gpuva_manager and &drm_gpuva
 *	// structure in individual driver structures and lock the dma-resv with
 *	// drm_exec or similar helpers.
 *	int driver_mapping_create(struct drm_gpuva_manager *mgr,
 *				  u64 addr, u64 range,
 *				  struct drm_gem_object *obj, u64 offset)
 *	{
 *		struct driver_context ctx;
 *		struct drm_gpuva_ops *ops;
 *		struct drm_gpuva_op *op;
 *		int ret = 0;
 *
 *		ctx.mgr = mgr;
 *
 *		ctx.new_va = kzalloc(sizeof(*ctx.new_va), GFP_KERNEL);
 *		ctx.prev_va = kzalloc(sizeof(*ctx.prev_va), GFP_KERNEL);
 *		ctx.next_va = kzalloc(sizeof(*ctx.next_va), GFP_KERNEL);
 *		if (!ctx.new_va || !ctx.prev_va || !ctx.next_va) {
 *			ret = -ENOMEM;
 *			goto out;
 *		}
 *
 *		driver_lock_va_space();
 *		ret = drm_gpuva_sm_map(mgr, &ctx, addr, range, obj, offset);
 *		driver_unlock_va_space();
 *
 *	out:
 *		kfree(ctx.new_va);
 *		kfree(ctx.prev_va);
 *		kfree(ctx.next_va);
 *		return ret;
 *	}
 *
 *	int driver_gpuva_map(struct drm_gpuva_op *op, void *__ctx)
 *	{
 *		struct driver_context *ctx = __ctx;
 *
 *		drm_gpuva_map(ctx->mgr, ctx->new_va, &op->map);
 *
 *		drm_gpuva_link(ctx->new_va);
 *
 *		// prevent the new GPUVA from being freed in
 *		// driver_mapping_create()
 *		ctx->new_va = NULL;
 *
 *		return 0;
 *	}
 *
 *	int driver_gpuva_remap(struct drm_gpuva_op *op, void *__ctx)
 *	{
 *		struct driver_context *ctx = __ctx;
 *
 *		drm_gpuva_remap(ctx->prev_va, ctx->next_va, &op->remap);
 *
 *		drm_gpuva_unlink(op->remap.unmap->va);
 *		kfree(op->remap.unmap->va);
 *
 *		if (op->remap.prev) {
 *			drm_gpuva_link(ctx->prev_va);
 *			ctx->prev_va = NULL;
 *		}
 *
 *		if (op->remap.next) {
 *			drm_gpuva_link(ctx->next_va);
 *			ctx->next_va = NULL;
 *		}
 *
 *		return 0;
 *	}
 *
 *	int driver_gpuva_unmap(struct drm_gpuva_op *op, void *__ctx)
 *	{
 *		drm_gpuva_unlink(op->unmap.va);
 *		drm_gpuva_unmap(&op->unmap);
 *		kfree(op->unmap.va);
 *
 *		return 0;
 *	}
 */

#define to_drm_gpuva(__node)	container_of((__node), struct drm_gpuva, rb.node)

#define GPUVA_START(node) ((node)->va.addr)
#define GPUVA_LAST(node) ((node)->va.addr + (node)->va.range - 1)

/* We do not actually use drm_gpuva_it_next(), tell the compiler to not complain
 * about this.
 */
INTERVAL_TREE_DEFINE(struct drm_gpuva, rb.node, u64, rb.__subtree_last,
		     GPUVA_START, GPUVA_LAST, static __maybe_unused,
		     drm_gpuva_it)

static int __drm_gpuva_insert(struct drm_gpuva_manager *mgr,
			      struct drm_gpuva *va);
static void __drm_gpuva_remove(struct drm_gpuva *va);

static bool
drm_gpuva_check_overflow(u64 addr, u64 range)
{
	u64 end;

	return WARN(check_add_overflow(addr, range, &end),
		    "GPUVA address limited to %zu bytes.\n", sizeof(end));
}

static bool
drm_gpuva_in_mm_range(struct drm_gpuva_manager *mgr, u64 addr, u64 range)
{
	u64 end = addr + range;
	u64 mm_start = mgr->mm_start;
	u64 mm_end = mm_start + mgr->mm_range;

	return addr >= mm_start && end <= mm_end;
}

static bool
drm_gpuva_in_kernel_node(struct drm_gpuva_manager *mgr, u64 addr, u64 range)
{
	u64 end = addr + range;
	u64 kstart = mgr->kernel_alloc_node.va.addr;
	u64 krange = mgr->kernel_alloc_node.va.range;
	u64 kend = kstart + krange;

	return krange && addr < kend && kstart < end;
}

static bool
drm_gpuva_range_valid(struct drm_gpuva_manager *mgr,
		      u64 addr, u64 range)
{
	return !drm_gpuva_check_overflow(addr, range) &&
	       drm_gpuva_in_mm_range(mgr, addr, range) &&
	       !drm_gpuva_in_kernel_node(mgr, addr, range);
}

/**
 * drm_gpuva_manager_init() - initialize a &drm_gpuva_manager
 * @mgr: pointer to the &drm_gpuva_manager to initialize
 * @name: the name of the GPU VA space
 * @start_offset: the start offset of the GPU VA space
 * @range: the size of the GPU VA space
 * @reserve_offset: the start of the kernel reserved GPU VA area
 * @reserve_range: the size of the kernel reserved GPU VA area
 * @ops: &drm_gpuva_fn_ops called on &drm_gpuva_sm_map / &drm_gpuva_sm_unmap
 *
 * The &drm_gpuva_manager must be initialized with this function before use.
 *
 * Note that @mgr must be cleared to 0 before calling this function. The given
 * &name is expected to be managed by the surrounding driver structures.
 */
void
drm_gpuva_manager_init(struct drm_gpuva_manager *mgr,
		       const char *name,
		       u64 start_offset, u64 range,
		       u64 reserve_offset, u64 reserve_range,
		       const struct drm_gpuva_fn_ops *ops)
{
	mgr->rb.tree = RB_ROOT_CACHED;
	INIT_LIST_HEAD(&mgr->rb.list);

	drm_gpuva_check_overflow(start_offset, range);
	mgr->mm_start = start_offset;
	mgr->mm_range = range;

	mgr->name = name ? name : "unknown";
	mgr->ops = ops;

	memset(&mgr->kernel_alloc_node, 0, sizeof(struct drm_gpuva));

	if (reserve_range) {
		mgr->kernel_alloc_node.va.addr = reserve_offset;
		mgr->kernel_alloc_node.va.range = reserve_range;

		if (likely(!drm_gpuva_check_overflow(reserve_offset,
						     reserve_range)))
			__drm_gpuva_insert(mgr, &mgr->kernel_alloc_node);
	}
}
EXPORT_SYMBOL_GPL(drm_gpuva_manager_init);

/**
 * drm_gpuva_manager_destroy() - cleanup a &drm_gpuva_manager
 * @mgr: pointer to the &drm_gpuva_manager to clean up
 *
 * Note that it is a bug to call this function on a manager that still
 * holds GPU VA mappings.
 */
void
drm_gpuva_manager_destroy(struct drm_gpuva_manager *mgr)
{
	mgr->name = NULL;

	if (mgr->kernel_alloc_node.va.range)
		__drm_gpuva_remove(&mgr->kernel_alloc_node);

	WARN(!RB_EMPTY_ROOT(&mgr->rb.tree.rb_root),
	     "GPUVA tree is not empty, potentially leaking memory.");
}
EXPORT_SYMBOL_GPL(drm_gpuva_manager_destroy);

static int
__drm_gpuva_insert(struct drm_gpuva_manager *mgr,
		   struct drm_gpuva *va)
{
	struct rb_node *node;
	struct list_head *head;

	if (drm_gpuva_it_iter_first(&mgr->rb.tree,
				    GPUVA_START(va),
				    GPUVA_LAST(va)))
		return -EEXIST;

	va->mgr = mgr;

	drm_gpuva_it_insert(va, &mgr->rb.tree);

	node = rb_prev(&va->rb.node);
	if (node)
		head = &(to_drm_gpuva(node))->rb.entry;
	else
		head = &mgr->rb.list;

	list_add(&va->rb.entry, head);

	return 0;
}

/**
 * drm_gpuva_insert() - insert a &drm_gpuva
 * @mgr: the &drm_gpuva_manager to insert the &drm_gpuva in
 * @va: the &drm_gpuva to insert
 *
 * Insert a &drm_gpuva with a given address and range into a
 * &drm_gpuva_manager.
 *
 * It is safe to use this function using the safe versions of iterating the GPU
 * VA space, such as drm_gpuva_for_each_va_safe() and
 * drm_gpuva_for_each_va_range_safe().
 *
 * Returns: 0 on success, negative error code on failure.
 */
int
drm_gpuva_insert(struct drm_gpuva_manager *mgr,
		 struct drm_gpuva *va)
{
	u64 addr = va->va.addr;
	u64 range = va->va.range;

	if (unlikely(!drm_gpuva_range_valid(mgr, addr, range)))
		return -EINVAL;

	return __drm_gpuva_insert(mgr, va);
}
EXPORT_SYMBOL_GPL(drm_gpuva_insert);

static void
__drm_gpuva_remove(struct drm_gpuva *va)
{
	drm_gpuva_it_remove(va, &va->mgr->rb.tree);
	list_del_init(&va->rb.entry);
}

/**
 * drm_gpuva_remove() - remove a &drm_gpuva
 * @va: the &drm_gpuva to remove
 *
 * This removes the given &va from the underlaying tree.
 *
 * It is safe to use this function using the safe versions of iterating the GPU
 * VA space, such as drm_gpuva_for_each_va_safe() and
 * drm_gpuva_for_each_va_range_safe().
 */
void
drm_gpuva_remove(struct drm_gpuva *va)
{
	struct drm_gpuva_manager *mgr = va->mgr;

	if (unlikely(va == &mgr->kernel_alloc_node)) {
		WARN(1, "Can't destroy kernel reserved node.\n");
		return;
	}

	__drm_gpuva_remove(va);
}
EXPORT_SYMBOL_GPL(drm_gpuva_remove);

/**
 * drm_gpuva_link() - link a &drm_gpuva
 * @va: the &drm_gpuva to link
 *
 * This adds the given &va to the GPU VA list of the &drm_gem_object it is
 * associated with.
 *
 * This function expects the caller to protect the GEM's GPUVA list against
 * concurrent access using the GEMs dma_resv lock.
 */
void
drm_gpuva_link(struct drm_gpuva *va)
{
	struct drm_gem_object *obj = va->gem.obj;

	if (unlikely(!obj))
		return;

	drm_gem_gpuva_assert_lock_held(obj);

	list_add_tail(&va->gem.entry, &obj->gpuva.list);
}
EXPORT_SYMBOL_GPL(drm_gpuva_link);

/**
 * drm_gpuva_unlink() - unlink a &drm_gpuva
 * @va: the &drm_gpuva to unlink
 *
 * This removes the given &va from the GPU VA list of the &drm_gem_object it is
 * associated with.
 *
 * This function expects the caller to protect the GEM's GPUVA list against
 * concurrent access using the GEMs dma_resv lock.
 */
void
drm_gpuva_unlink(struct drm_gpuva *va)
{
	struct drm_gem_object *obj = va->gem.obj;

	if (unlikely(!obj))
		return;

	drm_gem_gpuva_assert_lock_held(obj);

	list_del_init(&va->gem.entry);
}
EXPORT_SYMBOL_GPL(drm_gpuva_unlink);

/**
 * drm_gpuva_find_first() - find the first &drm_gpuva in the given range
 * @mgr: the &drm_gpuva_manager to search in
 * @addr: the &drm_gpuvas address
 * @range: the &drm_gpuvas range
 *
 * Returns: the first &drm_gpuva within the given range
 */
struct drm_gpuva *
drm_gpuva_find_first(struct drm_gpuva_manager *mgr,
		     u64 addr, u64 range)
{
	u64 last = addr + range - 1;

	return drm_gpuva_it_iter_first(&mgr->rb.tree, addr, last);
}
EXPORT_SYMBOL_GPL(drm_gpuva_find_first);

/**
 * drm_gpuva_find() - find a &drm_gpuva
 * @mgr: the &drm_gpuva_manager to search in
 * @addr: the &drm_gpuvas address
 * @range: the &drm_gpuvas range
 *
 * Returns: the &drm_gpuva at a given &addr and with a given &range
 */
struct drm_gpuva *
drm_gpuva_find(struct drm_gpuva_manager *mgr,
	       u64 addr, u64 range)
{
	struct drm_gpuva *va;

	va = drm_gpuva_find_first(mgr, addr, range);
	if (!va)
		goto out;

	if (va->va.addr != addr ||
	    va->va.range != range)
		goto out;

	return va;

out:
	return NULL;
}
EXPORT_SYMBOL_GPL(drm_gpuva_find);

/**
 * drm_gpuva_find_prev() - find the &drm_gpuva before the given address
 * @mgr: the &drm_gpuva_manager to search in
 * @start: the given GPU VA's start address
 *
 * Find the adjacent &drm_gpuva before the GPU VA with given &start address.
 *
 * Note that if there is any free space between the GPU VA mappings no mapping
 * is returned.
 *
 * Returns: a pointer to the found &drm_gpuva or NULL if none was found
 */
struct drm_gpuva *
drm_gpuva_find_prev(struct drm_gpuva_manager *mgr, u64 start)
{
	if (!drm_gpuva_range_valid(mgr, start - 1, 1))
		return NULL;

	return drm_gpuva_it_iter_first(&mgr->rb.tree, start - 1, start);
}
EXPORT_SYMBOL_GPL(drm_gpuva_find_prev);

/**
 * drm_gpuva_find_next() - find the &drm_gpuva after the given address
 * @mgr: the &drm_gpuva_manager to search in
 * @end: the given GPU VA's end address
 *
 * Find the adjacent &drm_gpuva after the GPU VA with given &end address.
 *
 * Note that if there is any free space between the GPU VA mappings no mapping
 * is returned.
 *
 * Returns: a pointer to the found &drm_gpuva or NULL if none was found
 */
struct drm_gpuva *
drm_gpuva_find_next(struct drm_gpuva_manager *mgr, u64 end)
{
	if (!drm_gpuva_range_valid(mgr, end, 1))
		return NULL;

	return drm_gpuva_it_iter_first(&mgr->rb.tree, end, end + 1);
}
EXPORT_SYMBOL_GPL(drm_gpuva_find_next);

/**
 * drm_gpuva_interval_empty() - indicate whether a given interval of the VA space
 * is empty
 * @mgr: the &drm_gpuva_manager to check the range for
 * @addr: the start address of the range
 * @range: the range of the interval
 *
 * Returns: true if the interval is empty, false otherwise
 */
bool
drm_gpuva_interval_empty(struct drm_gpuva_manager *mgr, u64 addr, u64 range)
{
	return !drm_gpuva_find_first(mgr, addr, range);
}
EXPORT_SYMBOL_GPL(drm_gpuva_interval_empty);

/**
 * drm_gpuva_map() - helper to insert a &drm_gpuva according to a
 * &drm_gpuva_op_map
 * @mgr: the &drm_gpuva_manager
 * @va: the &drm_gpuva to insert
 * @op: the &drm_gpuva_op_map to initialize @va with
 *
 * Initializes the @va from the @op and inserts it into the given @mgr.
 */
void
drm_gpuva_map(struct drm_gpuva_manager *mgr,
	      struct drm_gpuva *va,
	      struct drm_gpuva_op_map *op)
{
	drm_gpuva_init_from_op(va, op);
	drm_gpuva_insert(mgr, va);
}
EXPORT_SYMBOL_GPL(drm_gpuva_map);

/**
 * drm_gpuva_remap() - helper to remap a &drm_gpuva according to a
 * &drm_gpuva_op_remap
 * @prev: the &drm_gpuva to remap when keeping the start of a mapping
 * @next: the &drm_gpuva to remap when keeping the end of a mapping
 * @op: the &drm_gpuva_op_remap to initialize @prev and @next with
 *
 * Removes the currently mapped &drm_gpuva and remaps it using @prev and/or
 * @next.
 */
void
drm_gpuva_remap(struct drm_gpuva *prev,
		struct drm_gpuva *next,
		struct drm_gpuva_op_remap *op)
{
	struct drm_gpuva *curr = op->unmap->va;
	struct drm_gpuva_manager *mgr = curr->mgr;

	drm_gpuva_remove(curr);

	if (op->prev) {
		drm_gpuva_init_from_op(prev, op->prev);
		drm_gpuva_insert(mgr, prev);
	}

	if (op->next) {
		drm_gpuva_init_from_op(next, op->next);
		drm_gpuva_insert(mgr, next);
	}
}
EXPORT_SYMBOL_GPL(drm_gpuva_remap);

/**
 * drm_gpuva_unmap() - helper to remove a &drm_gpuva according to a
 * &drm_gpuva_op_unmap
 * @op: the &drm_gpuva_op_unmap specifying the &drm_gpuva to remove
 *
 * Removes the &drm_gpuva associated with the &drm_gpuva_op_unmap.
 */
void
drm_gpuva_unmap(struct drm_gpuva_op_unmap *op)
{
	drm_gpuva_remove(op->va);
}
EXPORT_SYMBOL_GPL(drm_gpuva_unmap);

static int
op_map_cb(const struct drm_gpuva_fn_ops *fn, void *priv,
	  u64 addr, u64 range,
	  struct drm_gem_object *obj, u64 offset)
{
	struct drm_gpuva_op op = {};

	op.op = DRM_GPUVA_OP_MAP;
	op.map.va.addr = addr;
	op.map.va.range = range;
	op.map.gem.obj = obj;
	op.map.gem.offset = offset;

	return fn->sm_step_map(&op, priv);
}

static int
op_remap_cb(const struct drm_gpuva_fn_ops *fn, void *priv,
	    struct drm_gpuva_op_map *prev,
	    struct drm_gpuva_op_map *next,
	    struct drm_gpuva_op_unmap *unmap)
{
	struct drm_gpuva_op op = {};
	struct drm_gpuva_op_remap *r;

	op.op = DRM_GPUVA_OP_REMAP;
	r = &op.remap;
	r->prev = prev;
	r->next = next;
	r->unmap = unmap;

	return fn->sm_step_remap(&op, priv);
}

static int
op_unmap_cb(const struct drm_gpuva_fn_ops *fn, void *priv,
	    struct drm_gpuva *va, bool merge)
{
	struct drm_gpuva_op op = {};

	op.op = DRM_GPUVA_OP_UNMAP;
	op.unmap.va = va;
	op.unmap.keep = merge;

	return fn->sm_step_unmap(&op, priv);
}

static int
__drm_gpuva_sm_map(struct drm_gpuva_manager *mgr,
		   const struct drm_gpuva_fn_ops *ops, void *priv,
		   u64 req_addr, u64 req_range,
		   struct drm_gem_object *req_obj, u64 req_offset)
{
	struct drm_gpuva *va, *next, *prev = NULL;
	u64 req_end = req_addr + req_range;
	int ret;

	if (unlikely(!drm_gpuva_range_valid(mgr, req_addr, req_range)))
		return -EINVAL;

	drm_gpuva_for_each_va_range_safe(va, next, mgr, req_addr, req_end) {
		struct drm_gem_object *obj = va->gem.obj;
		u64 offset = va->gem.offset;
		u64 addr = va->va.addr;
		u64 range = va->va.range;
		u64 end = addr + range;
		bool merge = !!va->gem.obj;

		if (addr == req_addr) {
			merge &= obj == req_obj &&
				 offset == req_offset;

			if (end == req_end) {
				ret = op_unmap_cb(ops, priv, va, merge);
				if (ret)
					return ret;
				break;
			}

			if (end < req_end) {
				ret = op_unmap_cb(ops, priv, va, merge);
				if (ret)
					return ret;
				goto next;
			}

			if (end > req_end) {
				struct drm_gpuva_op_map n = {
					.va.addr = req_end,
					.va.range = range - req_range,
					.gem.obj = obj,
					.gem.offset = offset + req_range,
				};
				struct drm_gpuva_op_unmap u = {
					.va = va,
					.keep = merge,
				};

				ret = op_remap_cb(ops, priv, NULL, &n, &u);
				if (ret)
					return ret;
				break;
			}
		} else if (addr < req_addr) {
			u64 ls_range = req_addr - addr;
			struct drm_gpuva_op_map p = {
				.va.addr = addr,
				.va.range = ls_range,
				.gem.obj = obj,
				.gem.offset = offset,
			};
			struct drm_gpuva_op_unmap u = { .va = va };

			merge &= obj == req_obj &&
				 offset + ls_range == req_offset;
			u.keep = merge;

			if (end == req_end) {
				ret = op_remap_cb(ops, priv, &p, NULL, &u);
				if (ret)
					return ret;
				break;
			}

			if (end < req_end) {
				ret = op_remap_cb(ops, priv, &p, NULL, &u);
				if (ret)
					return ret;
				goto next;
			}

			if (end > req_end) {
				struct drm_gpuva_op_map n = {
					.va.addr = req_end,
					.va.range = end - req_end,
					.gem.obj = obj,
					.gem.offset = offset + ls_range +
						      req_range,
				};

				ret = op_remap_cb(ops, priv, &p, &n, &u);
				if (ret)
					return ret;
				break;
			}
		} else if (addr > req_addr) {
			merge &= obj == req_obj &&
				 offset == req_offset +
					   (addr - req_addr);

			if (end == req_end) {
				ret = op_unmap_cb(ops, priv, va, merge);
				if (ret)
					return ret;
				break;
			}

			if (end < req_end) {
				ret = op_unmap_cb(ops, priv, va, merge);
				if (ret)
					return ret;
				goto next;
			}

			if (end > req_end) {
				struct drm_gpuva_op_map n = {
					.va.addr = req_end,
					.va.range = end - req_end,
					.gem.obj = obj,
					.gem.offset = offset + req_end - addr,
				};
				struct drm_gpuva_op_unmap u = {
					.va = va,
					.keep = merge,
				};

				ret = op_remap_cb(ops, priv, NULL, &n, &u);
				if (ret)
					return ret;
				break;
			}
		}
next:
		prev = va;
	}

	return op_map_cb(ops, priv,
			 req_addr, req_range,
			 req_obj, req_offset);
}

static int
__drm_gpuva_sm_unmap(struct drm_gpuva_manager *mgr,
		     const struct drm_gpuva_fn_ops *ops, void *priv,
		     u64 req_addr, u64 req_range)
{
	struct drm_gpuva *va, *next;
	u64 req_end = req_addr + req_range;
	int ret;

	if (unlikely(!drm_gpuva_range_valid(mgr, req_addr, req_range)))
		return -EINVAL;

	drm_gpuva_for_each_va_range_safe(va, next, mgr, req_addr, req_end) {
		struct drm_gpuva_op_map prev = {}, next = {};
		bool prev_split = false, next_split = false;
		struct drm_gem_object *obj = va->gem.obj;
		u64 offset = va->gem.offset;
		u64 addr = va->va.addr;
		u64 range = va->va.range;
		u64 end = addr + range;

		if (addr < req_addr) {
			prev.va.addr = addr;
			prev.va.range = req_addr - addr;
			prev.gem.obj = obj;
			prev.gem.offset = offset;

			prev_split = true;
		}

		if (end > req_end) {
			next.va.addr = req_end;
			next.va.range = end - req_end;
			next.gem.obj = obj;
			next.gem.offset = offset + (req_end - addr);

			next_split = true;
		}

		if (prev_split || next_split) {
			struct drm_gpuva_op_unmap unmap = { .va = va };

			ret = op_remap_cb(ops, priv,
					  prev_split ? &prev : NULL,
					  next_split ? &next : NULL,
					  &unmap);
			if (ret)
				return ret;
		} else {
			ret = op_unmap_cb(ops, priv, va, false);
			if (ret)
				return ret;
		}
	}

	return 0;
}

/**
 * drm_gpuva_sm_map() - creates the &drm_gpuva_op split/merge steps
 * @mgr: the &drm_gpuva_manager representing the GPU VA space
 * @req_addr: the start address of the new mapping
 * @req_range: the range of the new mapping
 * @req_obj: the &drm_gem_object to map
 * @req_offset: the offset within the &drm_gem_object
 * @priv: pointer to a driver private data structure
 *
 * This function iterates the given range of the GPU VA space. It utilizes the
 * &drm_gpuva_fn_ops to call back into the driver providing the split and merge
 * steps.
 *
 * Drivers may use these callbacks to update the GPU VA space right away within
 * the callback. In case the driver decides to copy and store the operations for
 * later processing neither this function nor &drm_gpuva_sm_unmap is allowed to
 * be called before the &drm_gpuva_manager's view of the GPU VA space was
 * updated with the previous set of operations. To update the
 * &drm_gpuva_manager's view of the GPU VA space drm_gpuva_insert(),
 * drm_gpuva_destroy_locked() and/or drm_gpuva_destroy_unlocked() should be
 * used.
 *
 * A sequence of callbacks can contain map, unmap and remap operations, but
 * the sequence of callbacks might also be empty if no operation is required,
 * e.g. if the requested mapping already exists in the exact same way.
 *
 * There can be an arbitrary amount of unmap operations, a maximum of two remap
 * operations and a single map operation. The latter one represents the original
 * map operation requested by the caller.
 *
 * Returns: 0 on success or a negative error code
 */
int
drm_gpuva_sm_map(struct drm_gpuva_manager *mgr, void *priv,
		 u64 req_addr, u64 req_range,
		 struct drm_gem_object *req_obj, u64 req_offset)
{
	const struct drm_gpuva_fn_ops *ops = mgr->ops;

	if (unlikely(!(ops && ops->sm_step_map &&
		       ops->sm_step_remap &&
		       ops->sm_step_unmap)))
		return -EINVAL;

	return __drm_gpuva_sm_map(mgr, ops, priv,
				  req_addr, req_range,
				  req_obj, req_offset);
}
EXPORT_SYMBOL_GPL(drm_gpuva_sm_map);

/**
 * drm_gpuva_sm_unmap() - creates the &drm_gpuva_ops to split on unmap
 * @mgr: the &drm_gpuva_manager representing the GPU VA space
 * @priv: pointer to a driver private data structure
 * @req_addr: the start address of the range to unmap
 * @req_range: the range of the mappings to unmap
 *
 * This function iterates the given range of the GPU VA space. It utilizes the
 * &drm_gpuva_fn_ops to call back into the driver providing the operations to
 * unmap and, if required, split existent mappings.
 *
 * Drivers may use these callbacks to update the GPU VA space right away within
 * the callback. In case the driver decides to copy and store the operations for
 * later processing neither this function nor &drm_gpuva_sm_map is allowed to be
 * called before the &drm_gpuva_manager's view of the GPU VA space was updated
 * with the previous set of operations. To update the &drm_gpuva_manager's view
 * of the GPU VA space drm_gpuva_insert(), drm_gpuva_destroy_locked() and/or
 * drm_gpuva_destroy_unlocked() should be used.
 *
 * A sequence of callbacks can contain unmap and remap operations, depending on
 * whether there are actual overlapping mappings to split.
 *
 * There can be an arbitrary amount of unmap operations and a maximum of two
 * remap operations.
 *
 * Returns: 0 on success or a negative error code
 */
int
drm_gpuva_sm_unmap(struct drm_gpuva_manager *mgr, void *priv,
		   u64 req_addr, u64 req_range)
{
	const struct drm_gpuva_fn_ops *ops = mgr->ops;

	if (unlikely(!(ops && ops->sm_step_remap &&
		       ops->sm_step_unmap)))
		return -EINVAL;

	return __drm_gpuva_sm_unmap(mgr, ops, priv,
				    req_addr, req_range);
}
EXPORT_SYMBOL_GPL(drm_gpuva_sm_unmap);

static struct drm_gpuva_op *
gpuva_op_alloc(struct drm_gpuva_manager *mgr)
{
	const struct drm_gpuva_fn_ops *fn = mgr->ops;
	struct drm_gpuva_op *op;

	if (fn && fn->op_alloc)
		op = fn->op_alloc();
	else
		op = kzalloc(sizeof(*op), GFP_KERNEL);

	if (unlikely(!op))
		return NULL;

	return op;
}

static void
gpuva_op_free(struct drm_gpuva_manager *mgr,
	      struct drm_gpuva_op *op)
{
	const struct drm_gpuva_fn_ops *fn = mgr->ops;

	if (fn && fn->op_free)
		fn->op_free(op);
	else
		kfree(op);
}

static int
drm_gpuva_sm_step(struct drm_gpuva_op *__op,
		  void *priv)
{
	struct {
		struct drm_gpuva_manager *mgr;
		struct drm_gpuva_ops *ops;
	} *args = priv;
	struct drm_gpuva_manager *mgr = args->mgr;
	struct drm_gpuva_ops *ops = args->ops;
	struct drm_gpuva_op *op;

	op = gpuva_op_alloc(mgr);
	if (unlikely(!op))
		goto err;

	memcpy(op, __op, sizeof(*op));

	if (op->op == DRM_GPUVA_OP_REMAP) {
		struct drm_gpuva_op_remap *__r = &__op->remap;
		struct drm_gpuva_op_remap *r = &op->remap;

		r->unmap = kmemdup(__r->unmap, sizeof(*r->unmap),
				   GFP_KERNEL);
		if (unlikely(!r->unmap))
			goto err_free_op;

		if (__r->prev) {
			r->prev = kmemdup(__r->prev, sizeof(*r->prev),
					  GFP_KERNEL);
			if (unlikely(!r->prev))
				goto err_free_unmap;
		}

		if (__r->next) {
			r->next = kmemdup(__r->next, sizeof(*r->next),
					  GFP_KERNEL);
			if (unlikely(!r->next))
				goto err_free_prev;
		}
	}

	list_add_tail(&op->entry, &ops->list);

	return 0;

err_free_unmap:
	kfree(op->remap.unmap);
err_free_prev:
	kfree(op->remap.prev);
err_free_op:
	gpuva_op_free(mgr, op);
err:
	return -ENOMEM;
}

static const struct drm_gpuva_fn_ops gpuva_list_ops = {
	.sm_step_map = drm_gpuva_sm_step,
	.sm_step_remap = drm_gpuva_sm_step,
	.sm_step_unmap = drm_gpuva_sm_step,
};

/**
 * drm_gpuva_sm_map_ops_create() - creates the &drm_gpuva_ops to split and merge
 * @mgr: the &drm_gpuva_manager representing the GPU VA space
 * @req_addr: the start address of the new mapping
 * @req_range: the range of the new mapping
 * @req_obj: the &drm_gem_object to map
 * @req_offset: the offset within the &drm_gem_object
 *
 * This function creates a list of operations to perform splitting and merging
 * of existent mapping(s) with the newly requested one.
 *
 * The list can be iterated with &drm_gpuva_for_each_op and must be processed
 * in the given order. It can contain map, unmap and remap operations, but it
 * also can be empty if no operation is required, e.g. if the requested mapping
 * already exists is the exact same way.
 *
 * There can be an arbitrary amount of unmap operations, a maximum of two remap
 * operations and a single map operation. The latter one represents the original
 * map operation requested by the caller.
 *
 * Note that before calling this function again with another mapping request it
 * is necessary to update the &drm_gpuva_manager's view of the GPU VA space. The
 * previously obtained operations must be either processed or abandoned. To
 * update the &drm_gpuva_manager's view of the GPU VA space drm_gpuva_insert(),
 * drm_gpuva_destroy_locked() and/or drm_gpuva_destroy_unlocked() should be
 * used.
 *
 * After the caller finished processing the returned &drm_gpuva_ops, they must
 * be freed with &drm_gpuva_ops_free.
 *
 * Returns: a pointer to the &drm_gpuva_ops on success, an ERR_PTR on failure
 */
struct drm_gpuva_ops *
drm_gpuva_sm_map_ops_create(struct drm_gpuva_manager *mgr,
			    u64 req_addr, u64 req_range,
			    struct drm_gem_object *req_obj, u64 req_offset)
{
	struct drm_gpuva_ops *ops;
	struct {
		struct drm_gpuva_manager *mgr;
		struct drm_gpuva_ops *ops;
	} args;
	int ret;

	ops = kzalloc(sizeof(*ops), GFP_KERNEL);
	if (unlikely(!ops))
		return ERR_PTR(-ENOMEM);

	INIT_LIST_HEAD(&ops->list);

	args.mgr = mgr;
	args.ops = ops;

	ret = __drm_gpuva_sm_map(mgr, &gpuva_list_ops, &args,
				 req_addr, req_range,
				 req_obj, req_offset);
	if (ret)
		goto err_free_ops;

	return ops;

err_free_ops:
	drm_gpuva_ops_free(mgr, ops);
	return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(drm_gpuva_sm_map_ops_create);

/**
 * drm_gpuva_sm_unmap_ops_create() - creates the &drm_gpuva_ops to split on
 * unmap
 * @mgr: the &drm_gpuva_manager representing the GPU VA space
 * @req_addr: the start address of the range to unmap
 * @req_range: the range of the mappings to unmap
 *
 * This function creates a list of operations to perform unmapping and, if
 * required, splitting of the mappings overlapping the unmap range.
 *
 * The list can be iterated with &drm_gpuva_for_each_op and must be processed
 * in the given order. It can contain unmap and remap operations, depending on
 * whether there are actual overlapping mappings to split.
 *
 * There can be an arbitrary amount of unmap operations and a maximum of two
 * remap operations.
 *
 * Note that before calling this function again with another range to unmap it
 * is necessary to update the &drm_gpuva_manager's view of the GPU VA space. The
 * previously obtained operations must be processed or abandoned. To update the
 * &drm_gpuva_manager's view of the GPU VA space drm_gpuva_insert(),
 * drm_gpuva_destroy_locked() and/or drm_gpuva_destroy_unlocked() should be
 * used.
 *
 * After the caller finished processing the returned &drm_gpuva_ops, they must
 * be freed with &drm_gpuva_ops_free.
 *
 * Returns: a pointer to the &drm_gpuva_ops on success, an ERR_PTR on failure
 */
struct drm_gpuva_ops *
drm_gpuva_sm_unmap_ops_create(struct drm_gpuva_manager *mgr,
			      u64 req_addr, u64 req_range)
{
	struct drm_gpuva_ops *ops;
	struct {
		struct drm_gpuva_manager *mgr;
		struct drm_gpuva_ops *ops;
	} args;
	int ret;

	ops = kzalloc(sizeof(*ops), GFP_KERNEL);
	if (unlikely(!ops))
		return ERR_PTR(-ENOMEM);

	INIT_LIST_HEAD(&ops->list);

	args.mgr = mgr;
	args.ops = ops;

	ret = __drm_gpuva_sm_unmap(mgr, &gpuva_list_ops, &args,
				   req_addr, req_range);
	if (ret)
		goto err_free_ops;

	return ops;

err_free_ops:
	drm_gpuva_ops_free(mgr, ops);
	return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(drm_gpuva_sm_unmap_ops_create);

/**
 * drm_gpuva_prefetch_ops_create() - creates the &drm_gpuva_ops to prefetch
 * @mgr: the &drm_gpuva_manager representing the GPU VA space
 * @addr: the start address of the range to prefetch
 * @range: the range of the mappings to prefetch
 *
 * This function creates a list of operations to perform prefetching.
 *
 * The list can be iterated with &drm_gpuva_for_each_op and must be processed
 * in the given order. It can contain prefetch operations.
 *
 * There can be an arbitrary amount of prefetch operations.
 *
 * After the caller finished processing the returned &drm_gpuva_ops, they must
 * be freed with &drm_gpuva_ops_free.
 *
 * Returns: a pointer to the &drm_gpuva_ops on success, an ERR_PTR on failure
 */
struct drm_gpuva_ops *
drm_gpuva_prefetch_ops_create(struct drm_gpuva_manager *mgr,
			      u64 addr, u64 range)
{
	struct drm_gpuva_ops *ops;
	struct drm_gpuva_op *op;
	struct drm_gpuva *va;
	u64 end = addr + range;
	int ret;

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

	INIT_LIST_HEAD(&ops->list);

	drm_gpuva_for_each_va_range(va, mgr, addr, end) {
		op = gpuva_op_alloc(mgr);
		if (!op) {
			ret = -ENOMEM;
			goto err_free_ops;
		}

		op->op = DRM_GPUVA_OP_PREFETCH;
		op->prefetch.va = va;
		list_add_tail(&op->entry, &ops->list);
	}

	return ops;

err_free_ops:
	drm_gpuva_ops_free(mgr, ops);
	return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(drm_gpuva_prefetch_ops_create);

/**
 * drm_gpuva_gem_unmap_ops_create() - creates the &drm_gpuva_ops to unmap a GEM
 * @mgr: the &drm_gpuva_manager representing the GPU VA space
 * @obj: the &drm_gem_object to unmap
 *
 * This function creates a list of operations to perform unmapping for every
 * GPUVA attached to a GEM.
 *
 * The list can be iterated with &drm_gpuva_for_each_op and consists out of an
 * arbitrary amount of unmap operations.
 *
 * After the caller finished processing the returned &drm_gpuva_ops, they must
 * be freed with &drm_gpuva_ops_free.
 *
 * It is the callers responsibility to protect the GEMs GPUVA list against
 * concurrent access using the GEMs dma_resv lock.
 *
 * Returns: a pointer to the &drm_gpuva_ops on success, an ERR_PTR on failure
 */
struct drm_gpuva_ops *
drm_gpuva_gem_unmap_ops_create(struct drm_gpuva_manager *mgr,
			       struct drm_gem_object *obj)
{
	struct drm_gpuva_ops *ops;
	struct drm_gpuva_op *op;
	struct drm_gpuva *va;
	int ret;

	drm_gem_gpuva_assert_lock_held(obj);

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

	INIT_LIST_HEAD(&ops->list);

	drm_gem_for_each_gpuva(va, obj) {
		op = gpuva_op_alloc(mgr);
		if (!op) {
			ret = -ENOMEM;
			goto err_free_ops;
		}

		op->op = DRM_GPUVA_OP_UNMAP;
		op->unmap.va = va;
		list_add_tail(&op->entry, &ops->list);
	}

	return ops;

err_free_ops:
	drm_gpuva_ops_free(mgr, ops);
	return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(drm_gpuva_gem_unmap_ops_create);

/**
 * drm_gpuva_ops_free() - free the given &drm_gpuva_ops
 * @mgr: the &drm_gpuva_manager the ops were created for
 * @ops: the &drm_gpuva_ops to free
 *
 * Frees the given &drm_gpuva_ops structure including all the ops associated
 * with it.
 */
void
drm_gpuva_ops_free(struct drm_gpuva_manager *mgr,
		   struct drm_gpuva_ops *ops)
{
	struct drm_gpuva_op *op, *next;

	drm_gpuva_for_each_op_safe(op, next, ops) {
		list_del(&op->entry);

		if (op->op == DRM_GPUVA_OP_REMAP) {
			kfree(op->remap.prev);
			kfree(op->remap.next);
			kfree(op->remap.unmap);
		}

		gpuva_op_free(mgr, op);
	}

	kfree(ops);
}
EXPORT_SYMBOL_GPL(drm_gpuva_ops_free);