summaryrefslogtreecommitdiffstats
path: root/drivers/vfio/vfio_main.c
blob: e053998baffd8065aca04d959aba6221445e0056 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * VFIO core
 *
 * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
 *     Author: Alex Williamson <alex.williamson@redhat.com>
 *
 * Derived from original vfio:
 * Copyright 2010 Cisco Systems, Inc.  All rights reserved.
 * Author: Tom Lyon, pugs@cisco.com
 */

#include <linux/cdev.h>
#include <linux/compat.h>
#include <linux/device.h>
#include <linux/file.h>
#include <linux/anon_inodes.h>
#include <linux/fs.h>
#include <linux/idr.h>
#include <linux/iommu.h>
#include <linux/list.h>
#include <linux/miscdevice.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/pci.h>
#include <linux/rwsem.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/uaccess.h>
#include <linux/vfio.h>
#include <linux/wait.h>
#include <linux/sched/signal.h>
#include <linux/pm_runtime.h>
#include <linux/interval_tree.h>
#include <linux/iova_bitmap.h>
#include <linux/iommufd.h>
#include "vfio.h"

#define DRIVER_VERSION	"0.3"
#define DRIVER_AUTHOR	"Alex Williamson <alex.williamson@redhat.com>"
#define DRIVER_DESC	"VFIO - User Level meta-driver"

static struct vfio {
	struct class			*class;
	struct list_head		group_list;
	struct mutex			group_lock; /* locks group_list */
	struct ida			group_ida;
	dev_t				group_devt;
	struct class			*device_class;
	struct ida			device_ida;
} vfio;

static DEFINE_XARRAY(vfio_device_set_xa);
static const struct file_operations vfio_group_fops;

int vfio_assign_device_set(struct vfio_device *device, void *set_id)
{
	unsigned long idx = (unsigned long)set_id;
	struct vfio_device_set *new_dev_set;
	struct vfio_device_set *dev_set;

	if (WARN_ON(!set_id))
		return -EINVAL;

	/*
	 * Atomically acquire a singleton object in the xarray for this set_id
	 */
	xa_lock(&vfio_device_set_xa);
	dev_set = xa_load(&vfio_device_set_xa, idx);
	if (dev_set)
		goto found_get_ref;
	xa_unlock(&vfio_device_set_xa);

	new_dev_set = kzalloc(sizeof(*new_dev_set), GFP_KERNEL);
	if (!new_dev_set)
		return -ENOMEM;
	mutex_init(&new_dev_set->lock);
	INIT_LIST_HEAD(&new_dev_set->device_list);
	new_dev_set->set_id = set_id;

	xa_lock(&vfio_device_set_xa);
	dev_set = __xa_cmpxchg(&vfio_device_set_xa, idx, NULL, new_dev_set,
			       GFP_KERNEL);
	if (!dev_set) {
		dev_set = new_dev_set;
		goto found_get_ref;
	}

	kfree(new_dev_set);
	if (xa_is_err(dev_set)) {
		xa_unlock(&vfio_device_set_xa);
		return xa_err(dev_set);
	}

found_get_ref:
	dev_set->device_count++;
	xa_unlock(&vfio_device_set_xa);
	mutex_lock(&dev_set->lock);
	device->dev_set = dev_set;
	list_add_tail(&device->dev_set_list, &dev_set->device_list);
	mutex_unlock(&dev_set->lock);
	return 0;
}
EXPORT_SYMBOL_GPL(vfio_assign_device_set);

static void vfio_release_device_set(struct vfio_device *device)
{
	struct vfio_device_set *dev_set = device->dev_set;

	if (!dev_set)
		return;

	mutex_lock(&dev_set->lock);
	list_del(&device->dev_set_list);
	mutex_unlock(&dev_set->lock);

	xa_lock(&vfio_device_set_xa);
	if (!--dev_set->device_count) {
		__xa_erase(&vfio_device_set_xa,
			   (unsigned long)dev_set->set_id);
		mutex_destroy(&dev_set->lock);
		kfree(dev_set);
	}
	xa_unlock(&vfio_device_set_xa);
}

unsigned int vfio_device_set_open_count(struct vfio_device_set *dev_set)
{
	struct vfio_device *cur;
	unsigned int open_count = 0;

	lockdep_assert_held(&dev_set->lock);

	list_for_each_entry(cur, &dev_set->device_list, dev_set_list)
		open_count += cur->open_count;
	return open_count;
}
EXPORT_SYMBOL_GPL(vfio_device_set_open_count);

/*
 * Group objects - create, release, get, put, search
 */
static struct vfio_group *
vfio_group_find_from_iommu(struct iommu_group *iommu_group)
{
	struct vfio_group *group;

	lockdep_assert_held(&vfio.group_lock);

	/*
	 * group->iommu_group from the vfio.group_list cannot be NULL
	 * under the vfio.group_lock.
	 */
	list_for_each_entry(group, &vfio.group_list, vfio_next) {
		if (group->iommu_group == iommu_group)
			return group;
	}
	return NULL;
}

static void vfio_group_release(struct device *dev)
{
	struct vfio_group *group = container_of(dev, struct vfio_group, dev);

	mutex_destroy(&group->device_lock);
	mutex_destroy(&group->group_lock);
	WARN_ON(group->iommu_group);
	ida_free(&vfio.group_ida, MINOR(group->dev.devt));
	kfree(group);
}

static struct vfio_group *vfio_group_alloc(struct iommu_group *iommu_group,
					   enum vfio_group_type type)
{
	struct vfio_group *group;
	int minor;

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

	minor = ida_alloc_max(&vfio.group_ida, MINORMASK, GFP_KERNEL);
	if (minor < 0) {
		kfree(group);
		return ERR_PTR(minor);
	}

	device_initialize(&group->dev);
	group->dev.devt = MKDEV(MAJOR(vfio.group_devt), minor);
	group->dev.class = vfio.class;
	group->dev.release = vfio_group_release;
	cdev_init(&group->cdev, &vfio_group_fops);
	group->cdev.owner = THIS_MODULE;

	refcount_set(&group->drivers, 1);
	mutex_init(&group->group_lock);
	INIT_LIST_HEAD(&group->device_list);
	mutex_init(&group->device_lock);
	group->iommu_group = iommu_group;
	/* put in vfio_group_release() */
	iommu_group_ref_get(iommu_group);
	group->type = type;
	BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier);

	return group;
}

static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group,
		enum vfio_group_type type)
{
	struct vfio_group *group;
	struct vfio_group *ret;
	int err;

	lockdep_assert_held(&vfio.group_lock);

	group = vfio_group_alloc(iommu_group, type);
	if (IS_ERR(group))
		return group;

	err = dev_set_name(&group->dev, "%s%d",
			   group->type == VFIO_NO_IOMMU ? "noiommu-" : "",
			   iommu_group_id(iommu_group));
	if (err) {
		ret = ERR_PTR(err);
		goto err_put;
	}

	err = cdev_device_add(&group->cdev, &group->dev);
	if (err) {
		ret = ERR_PTR(err);
		goto err_put;
	}

	list_add(&group->vfio_next, &vfio.group_list);

	return group;

err_put:
	put_device(&group->dev);
	return ret;
}

static void vfio_device_remove_group(struct vfio_device *device)
{
	struct vfio_group *group = device->group;
	struct iommu_group *iommu_group;

	if (group->type == VFIO_NO_IOMMU || group->type == VFIO_EMULATED_IOMMU)
		iommu_group_remove_device(device->dev);

	/* Pairs with vfio_create_group() / vfio_group_get_from_iommu() */
	if (!refcount_dec_and_mutex_lock(&group->drivers, &vfio.group_lock))
		return;
	list_del(&group->vfio_next);

	/*
	 * We could concurrently probe another driver in the group that might
	 * race vfio_device_remove_group() with vfio_get_group(), so we have to
	 * ensure that the sysfs is all cleaned up under lock otherwise the
	 * cdev_device_add() will fail due to the name aready existing.
	 */
	cdev_device_del(&group->cdev, &group->dev);

	mutex_lock(&group->group_lock);
	/*
	 * These data structures all have paired operations that can only be
	 * undone when the caller holds a live reference on the device. Since
	 * all pairs must be undone these WARN_ON's indicate some caller did not
	 * properly hold the group reference.
	 */
	WARN_ON(!list_empty(&group->device_list));
	WARN_ON(group->notifier.head);

	/*
	 * Revoke all users of group->iommu_group. At this point we know there
	 * are no devices active because we are unplugging the last one. Setting
	 * iommu_group to NULL blocks all new users.
	 */
	if (group->container)
		vfio_group_detach_container(group);
	iommu_group = group->iommu_group;
	group->iommu_group = NULL;
	mutex_unlock(&group->group_lock);
	mutex_unlock(&vfio.group_lock);

	iommu_group_put(iommu_group);
	put_device(&group->dev);
}

/*
 * Device objects - create, release, get, put, search
 */
/* Device reference always implies a group reference */
static void vfio_device_put_registration(struct vfio_device *device)
{
	if (refcount_dec_and_test(&device->refcount))
		complete(&device->comp);
}

static bool vfio_device_try_get_registration(struct vfio_device *device)
{
	return refcount_inc_not_zero(&device->refcount);
}

/*
 * VFIO driver API
 */
/* Release helper called by vfio_put_device() */
static void vfio_device_release(struct device *dev)
{
	struct vfio_device *device =
			container_of(dev, struct vfio_device, device);

	vfio_release_device_set(device);
	ida_free(&vfio.device_ida, device->index);

	/*
	 * kvfree() cannot be done here due to a life cycle mess in
	 * vfio-ccw. Before the ccw part is fixed all drivers are
	 * required to support @release and call vfio_free_device()
	 * from there.
	 */
	device->ops->release(device);
}

/*
 * Allocate and initialize vfio_device so it can be registered to vfio
 * core.
 *
 * Drivers should use the wrapper vfio_alloc_device() for allocation.
 * @size is the size of the structure to be allocated, including any
 * private data used by the driver.
 *
 * Driver may provide an @init callback to cover device private data.
 *
 * Use vfio_put_device() to release the structure after success return.
 */
struct vfio_device *_vfio_alloc_device(size_t size, struct device *dev,
				       const struct vfio_device_ops *ops)
{
	struct vfio_device *device;
	int ret;

	if (WARN_ON(size < sizeof(struct vfio_device)))
		return ERR_PTR(-EINVAL);

	device = kvzalloc(size, GFP_KERNEL);
	if (!device)
		return ERR_PTR(-ENOMEM);

	ret = vfio_init_device(device, dev, ops);
	if (ret)
		goto out_free;
	return device;

out_free:
	kvfree(device);
	return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(_vfio_alloc_device);

/*
 * Initialize a vfio_device so it can be registered to vfio core.
 *
 * Only vfio-ccw driver should call this interface.
 */
int vfio_init_device(struct vfio_device *device, struct device *dev,
		     const struct vfio_device_ops *ops)
{
	int ret;

	ret = ida_alloc_max(&vfio.device_ida, MINORMASK, GFP_KERNEL);
	if (ret < 0) {
		dev_dbg(dev, "Error to alloc index\n");
		return ret;
	}

	device->index = ret;
	init_completion(&device->comp);
	device->dev = dev;
	device->ops = ops;

	if (ops->init) {
		ret = ops->init(device);
		if (ret)
			goto out_uninit;
	}

	device_initialize(&device->device);
	device->device.release = vfio_device_release;
	device->device.class = vfio.device_class;
	device->device.parent = device->dev;
	return 0;

out_uninit:
	vfio_release_device_set(device);
	ida_free(&vfio.device_ida, device->index);
	return ret;
}
EXPORT_SYMBOL_GPL(vfio_init_device);

/*
 * The helper called by driver @release callback to free the device
 * structure. Drivers which don't have private data to clean can
 * simply use this helper as its @release.
 */
void vfio_free_device(struct vfio_device *device)
{
	kvfree(device);
}
EXPORT_SYMBOL_GPL(vfio_free_device);

static struct vfio_group *vfio_noiommu_group_alloc(struct device *dev,
		enum vfio_group_type type)
{
	struct iommu_group *iommu_group;
	struct vfio_group *group;
	int ret;

	iommu_group = iommu_group_alloc();
	if (IS_ERR(iommu_group))
		return ERR_CAST(iommu_group);

	ret = iommu_group_set_name(iommu_group, "vfio-noiommu");
	if (ret)
		goto out_put_group;
	ret = iommu_group_add_device(iommu_group, dev);
	if (ret)
		goto out_put_group;

	mutex_lock(&vfio.group_lock);
	group = vfio_create_group(iommu_group, type);
	mutex_unlock(&vfio.group_lock);
	if (IS_ERR(group)) {
		ret = PTR_ERR(group);
		goto out_remove_device;
	}
	iommu_group_put(iommu_group);
	return group;

out_remove_device:
	iommu_group_remove_device(dev);
out_put_group:
	iommu_group_put(iommu_group);
	return ERR_PTR(ret);
}

static bool vfio_group_has_device(struct vfio_group *group, struct device *dev)
{
	struct vfio_device *device;

	mutex_lock(&group->device_lock);
	list_for_each_entry(device, &group->device_list, group_next) {
		if (device->dev == dev) {
			mutex_unlock(&group->device_lock);
			return true;
		}
	}
	mutex_unlock(&group->device_lock);
	return false;
}

static struct vfio_group *vfio_group_find_or_alloc(struct device *dev)
{
	struct iommu_group *iommu_group;
	struct vfio_group *group;

	iommu_group = iommu_group_get(dev);
	if (!iommu_group && vfio_noiommu) {
		/*
		 * With noiommu enabled, create an IOMMU group for devices that
		 * don't already have one, implying no IOMMU hardware/driver
		 * exists.  Taint the kernel because we're about to give a DMA
		 * capable device to a user without IOMMU protection.
		 */
		group = vfio_noiommu_group_alloc(dev, VFIO_NO_IOMMU);
		if (!IS_ERR(group)) {
			add_taint(TAINT_USER, LOCKDEP_STILL_OK);
			dev_warn(dev, "Adding kernel taint for vfio-noiommu group on device\n");
		}
		return group;
	}

	if (!iommu_group)
		return ERR_PTR(-EINVAL);

	/*
	 * VFIO always sets IOMMU_CACHE because we offer no way for userspace to
	 * restore cache coherency. It has to be checked here because it is only
	 * valid for cases where we are using iommu groups.
	 */
	if (!device_iommu_capable(dev, IOMMU_CAP_CACHE_COHERENCY)) {
		iommu_group_put(iommu_group);
		return ERR_PTR(-EINVAL);
	}

	mutex_lock(&vfio.group_lock);
	group = vfio_group_find_from_iommu(iommu_group);
	if (group) {
		if (WARN_ON(vfio_group_has_device(group, dev)))
			group = ERR_PTR(-EINVAL);
		else
			refcount_inc(&group->drivers);
	} else {
		group = vfio_create_group(iommu_group, VFIO_IOMMU);
	}
	mutex_unlock(&vfio.group_lock);

	/* The vfio_group holds a reference to the iommu_group */
	iommu_group_put(iommu_group);
	return group;
}

static void vfio_device_group_register(struct vfio_device *device)
{
	mutex_lock(&device->group->device_lock);
	list_add(&device->group_next, &device->group->device_list);
	mutex_unlock(&device->group->device_lock);
}

static void vfio_device_group_unregister(struct vfio_device *device)
{
	mutex_lock(&device->group->device_lock);
	list_del(&device->group_next);
	mutex_unlock(&device->group->device_lock);
}

static int vfio_device_set_group(struct vfio_device *device,
				 enum vfio_group_type type)
{
	struct vfio_group *group;

	if (type == VFIO_IOMMU)
		group = vfio_group_find_or_alloc(device->dev);
	else
		group = vfio_noiommu_group_alloc(device->dev, type);

	if (IS_ERR(group))
		return PTR_ERR(group);

	/* Our reference on group is moved to the device */
	device->group = group;
	return 0;
}

static int __vfio_register_dev(struct vfio_device *device,
			       enum vfio_group_type type)
{
	int ret;

	if (WARN_ON(device->ops->bind_iommufd &&
		    (!device->ops->unbind_iommufd ||
		     !device->ops->attach_ioas)))
		return -EINVAL;

	/*
	 * If the driver doesn't specify a set then the device is added to a
	 * singleton set just for itself.
	 */
	if (!device->dev_set)
		vfio_assign_device_set(device, device);

	ret = dev_set_name(&device->device, "vfio%d", device->index);
	if (ret)
		return ret;

	ret = vfio_device_set_group(device, type);
	if (ret)
		return ret;

	ret = device_add(&device->device);
	if (ret)
		goto err_out;

	/* Refcounting can't start until the driver calls register */
	refcount_set(&device->refcount, 1);

	vfio_device_group_register(device);

	return 0;
err_out:
	vfio_device_remove_group(device);
	return ret;
}

int vfio_register_group_dev(struct vfio_device *device)
{
	return __vfio_register_dev(device, VFIO_IOMMU);
}
EXPORT_SYMBOL_GPL(vfio_register_group_dev);

/*
 * Register a virtual device without IOMMU backing.  The user of this
 * device must not be able to directly trigger unmediated DMA.
 */
int vfio_register_emulated_iommu_dev(struct vfio_device *device)
{
	return __vfio_register_dev(device, VFIO_EMULATED_IOMMU);
}
EXPORT_SYMBOL_GPL(vfio_register_emulated_iommu_dev);

static struct vfio_device *vfio_device_get_from_name(struct vfio_group *group,
						     char *buf)
{
	struct vfio_device *it, *device = ERR_PTR(-ENODEV);

	mutex_lock(&group->device_lock);
	list_for_each_entry(it, &group->device_list, group_next) {
		int ret;

		if (it->ops->match) {
			ret = it->ops->match(it, buf);
			if (ret < 0) {
				device = ERR_PTR(ret);
				break;
			}
		} else {
			ret = !strcmp(dev_name(it->dev), buf);
		}

		if (ret && vfio_device_try_get_registration(it)) {
			device = it;
			break;
		}
	}
	mutex_unlock(&group->device_lock);

	return device;
}

/*
 * Decrement the device reference count and wait for the device to be
 * removed.  Open file descriptors for the device... */
void vfio_unregister_group_dev(struct vfio_device *device)
{
	unsigned int i = 0;
	bool interrupted = false;
	long rc;

	vfio_device_put_registration(device);
	rc = try_wait_for_completion(&device->comp);
	while (rc <= 0) {
		if (device->ops->request)
			device->ops->request(device, i++);

		if (interrupted) {
			rc = wait_for_completion_timeout(&device->comp,
							 HZ * 10);
		} else {
			rc = wait_for_completion_interruptible_timeout(
				&device->comp, HZ * 10);
			if (rc < 0) {
				interrupted = true;
				dev_warn(device->dev,
					 "Device is currently in use, task"
					 " \"%s\" (%d) "
					 "blocked until device is released",
					 current->comm, task_pid_nr(current));
			}
		}
	}

	vfio_device_group_unregister(device);

	/* Balances device_add in register path */
	device_del(&device->device);

	/* Balances vfio_device_set_group in register path */
	vfio_device_remove_group(device);
}
EXPORT_SYMBOL_GPL(vfio_unregister_group_dev);

/*
 * VFIO Group fd, /dev/vfio/$GROUP
 */
static bool vfio_group_has_iommu(struct vfio_group *group)
{
	lockdep_assert_held(&group->group_lock);
	/*
	 * There can only be users if there is a container, and if there is a
	 * container there must be users.
	 */
	WARN_ON(!group->container != !group->container_users);

	return group->container || group->iommufd;
}

/*
 * VFIO_GROUP_UNSET_CONTAINER should fail if there are other users or
 * if there was no container to unset.  Since the ioctl is called on
 * the group, we know that still exists, therefore the only valid
 * transition here is 1->0.
 */
static int vfio_group_ioctl_unset_container(struct vfio_group *group)
{
	int ret = 0;

	mutex_lock(&group->group_lock);
	if (!vfio_group_has_iommu(group)) {
		ret = -EINVAL;
		goto out_unlock;
	}
	if (group->container) {
		if (group->container_users != 1) {
			ret = -EBUSY;
			goto out_unlock;
		}
		vfio_group_detach_container(group);
	}
	if (group->iommufd) {
		iommufd_ctx_put(group->iommufd);
		group->iommufd = NULL;
	}

out_unlock:
	mutex_unlock(&group->group_lock);
	return ret;
}

static int vfio_group_ioctl_set_container(struct vfio_group *group,
					  int __user *arg)
{
	struct vfio_container *container;
	struct iommufd_ctx *iommufd;
	struct fd f;
	int ret;
	int fd;

	if (get_user(fd, arg))
		return -EFAULT;

	f = fdget(fd);
	if (!f.file)
		return -EBADF;

	mutex_lock(&group->group_lock);
	if (vfio_group_has_iommu(group)) {
		ret = -EINVAL;
		goto out_unlock;
	}
	if (!group->iommu_group) {
		ret = -ENODEV;
		goto out_unlock;
	}

	container = vfio_container_from_file(f.file);
	if (container) {
		ret = vfio_container_attach_group(container, group);
		goto out_unlock;
	}

	iommufd = iommufd_ctx_from_file(f.file);
	if (!IS_ERR(iommufd)) {
		u32 ioas_id;

		ret = iommufd_vfio_compat_ioas_id(iommufd, &ioas_id);
		if (ret) {
			iommufd_ctx_put(group->iommufd);
			goto out_unlock;
		}

		group->iommufd = iommufd;
		goto out_unlock;
	}

	/* The FD passed is not recognized. */
	ret = -EBADFD;

out_unlock:
	mutex_unlock(&group->group_lock);
	fdput(f);
	return ret;
}

static const struct file_operations vfio_device_fops;

/* true if the vfio_device has open_device() called but not close_device() */
static bool vfio_assert_device_open(struct vfio_device *device)
{
	return !WARN_ON_ONCE(!READ_ONCE(device->open_count));
}

static int vfio_device_group_use_iommu(struct vfio_device *device)
{
	struct vfio_group *group = device->group;
	int ret = 0;

	lockdep_assert_held(&group->group_lock);

	if (WARN_ON(!group->container))
		return -EINVAL;

	ret = vfio_group_use_container(group);
	if (ret)
		return ret;
	vfio_device_container_register(device);
	return 0;
}

static void vfio_device_group_unuse_iommu(struct vfio_device *device)
{
	struct vfio_group *group = device->group;

	lockdep_assert_held(&group->group_lock);

	if (WARN_ON(!group->container))
		return;

	vfio_device_container_unregister(device);
	vfio_group_unuse_container(group);
}

static int vfio_device_first_open(struct vfio_device *device,
				  struct iommufd_ctx *iommufd, struct kvm *kvm)
{
	int ret;

	lockdep_assert_held(&device->dev_set->lock);

	if (!try_module_get(device->dev->driver->owner))
		return -ENODEV;

	if (iommufd)
		ret = vfio_iommufd_bind(device, iommufd);
	else
		ret = vfio_device_group_use_iommu(device);
	if (ret)
		goto err_module_put;

	device->kvm = kvm;
	if (device->ops->open_device) {
		ret = device->ops->open_device(device);
		if (ret)
			goto err_unuse_iommu;
	}
	return 0;

err_unuse_iommu:
	device->kvm = NULL;
	if (iommufd)
		vfio_iommufd_unbind(device);
	else
		vfio_device_group_unuse_iommu(device);
err_module_put:
	module_put(device->dev->driver->owner);
	return ret;
}

static void vfio_device_last_close(struct vfio_device *device,
				   struct iommufd_ctx *iommufd)
{
	lockdep_assert_held(&device->dev_set->lock);

	if (device->ops->close_device)
		device->ops->close_device(device);
	device->kvm = NULL;
	if (iommufd)
		vfio_iommufd_unbind(device);
	else
		vfio_device_group_unuse_iommu(device);
	module_put(device->dev->driver->owner);
}

static int vfio_device_open(struct vfio_device *device,
			    struct iommufd_ctx *iommufd, struct kvm *kvm)
{
	int ret = 0;

	mutex_lock(&device->dev_set->lock);
	device->open_count++;
	if (device->open_count == 1) {
		ret = vfio_device_first_open(device, iommufd, kvm);
		if (ret)
			device->open_count--;
	}
	mutex_unlock(&device->dev_set->lock);

	return ret;
}

static void vfio_device_close(struct vfio_device *device,
			      struct iommufd_ctx *iommufd)
{
	mutex_lock(&device->dev_set->lock);
	vfio_assert_device_open(device);
	if (device->open_count == 1)
		vfio_device_last_close(device, iommufd);
	device->open_count--;
	mutex_unlock(&device->dev_set->lock);
}

static int vfio_device_group_open(struct vfio_device *device)
{
	int ret;

	mutex_lock(&device->group->group_lock);
	if (!vfio_group_has_iommu(device->group)) {
		ret = -EINVAL;
		goto out_unlock;
	}

	/*
	 * Here we pass the KVM pointer with the group under the lock.  If the
	 * device driver will use it, it must obtain a reference and release it
	 * during close_device.
	 */
	ret = vfio_device_open(device, device->group->iommufd,
			       device->group->kvm);

out_unlock:
	mutex_unlock(&device->group->group_lock);
	return ret;
}

static void vfio_device_group_close(struct vfio_device *device)
{
	mutex_lock(&device->group->group_lock);
	vfio_device_close(device, device->group->iommufd);
	mutex_unlock(&device->group->group_lock);
}

static struct file *vfio_device_open_file(struct vfio_device *device)
{
	struct file *filep;
	int ret;

	ret = vfio_device_group_open(device);
	if (ret)
		goto err_out;

	/*
	 * We can't use anon_inode_getfd() because we need to modify
	 * the f_mode flags directly to allow more than just ioctls
	 */
	filep = anon_inode_getfile("[vfio-device]", &vfio_device_fops,
				   device, O_RDWR);
	if (IS_ERR(filep)) {
		ret = PTR_ERR(filep);
		goto err_close_device;
	}

	/*
	 * TODO: add an anon_inode interface to do this.
	 * Appears to be missing by lack of need rather than
	 * explicitly prevented.  Now there's need.
	 */
	filep->f_mode |= (FMODE_PREAD | FMODE_PWRITE);

	if (device->group->type == VFIO_NO_IOMMU)
		dev_warn(device->dev, "vfio-noiommu device opened by user "
			 "(%s:%d)\n", current->comm, task_pid_nr(current));
	/*
	 * On success the ref of device is moved to the file and
	 * put in vfio_device_fops_release()
	 */
	return filep;

err_close_device:
	vfio_device_group_close(device);
err_out:
	return ERR_PTR(ret);
}

static int vfio_group_ioctl_get_device_fd(struct vfio_group *group,
					  char __user *arg)
{
	struct vfio_device *device;
	struct file *filep;
	char *buf;
	int fdno;
	int ret;

	buf = strndup_user(arg, PAGE_SIZE);
	if (IS_ERR(buf))
		return PTR_ERR(buf);

	device = vfio_device_get_from_name(group, buf);
	kfree(buf);
	if (IS_ERR(device))
		return PTR_ERR(device);

	fdno = get_unused_fd_flags(O_CLOEXEC);
	if (fdno < 0) {
		ret = fdno;
		goto err_put_device;
	}

	filep = vfio_device_open_file(device);
	if (IS_ERR(filep)) {
		ret = PTR_ERR(filep);
		goto err_put_fdno;
	}

	fd_install(fdno, filep);
	return fdno;

err_put_fdno:
	put_unused_fd(fdno);
err_put_device:
	vfio_device_put_registration(device);
	return ret;
}

static int vfio_group_ioctl_get_status(struct vfio_group *group,
				       struct vfio_group_status __user *arg)
{
	unsigned long minsz = offsetofend(struct vfio_group_status, flags);
	struct vfio_group_status status;

	if (copy_from_user(&status, arg, minsz))
		return -EFAULT;

	if (status.argsz < minsz)
		return -EINVAL;

	status.flags = 0;

	mutex_lock(&group->group_lock);
	if (!group->iommu_group) {
		mutex_unlock(&group->group_lock);
		return -ENODEV;
	}

	/*
	 * With the container FD the iommu_group_claim_dma_owner() is done
	 * during SET_CONTAINER but for IOMMFD this is done during
	 * VFIO_GROUP_GET_DEVICE_FD. Meaning that with iommufd
	 * VFIO_GROUP_FLAGS_VIABLE could be set but GET_DEVICE_FD will fail due
	 * to viability.
	 */
	if (vfio_group_has_iommu(group))
		status.flags |= VFIO_GROUP_FLAGS_CONTAINER_SET |
				VFIO_GROUP_FLAGS_VIABLE;
	else if (!iommu_group_dma_owner_claimed(group->iommu_group))
		status.flags |= VFIO_GROUP_FLAGS_VIABLE;
	mutex_unlock(&group->group_lock);

	if (copy_to_user(arg, &status, minsz))
		return -EFAULT;
	return 0;
}

static long vfio_group_fops_unl_ioctl(struct file *filep,
				      unsigned int cmd, unsigned long arg)
{
	struct vfio_group *group = filep->private_data;
	void __user *uarg = (void __user *)arg;

	switch (cmd) {
	case VFIO_GROUP_GET_DEVICE_FD:
		return vfio_group_ioctl_get_device_fd(group, uarg);
	case VFIO_GROUP_GET_STATUS:
		return vfio_group_ioctl_get_status(group, uarg);
	case VFIO_GROUP_SET_CONTAINER:
		return vfio_group_ioctl_set_container(group, uarg);
	case VFIO_GROUP_UNSET_CONTAINER:
		return vfio_group_ioctl_unset_container(group);
	default:
		return -ENOTTY;
	}
}

static int vfio_group_fops_open(struct inode *inode, struct file *filep)
{
	struct vfio_group *group =
		container_of(inode->i_cdev, struct vfio_group, cdev);
	int ret;

	mutex_lock(&group->group_lock);

	/*
	 * drivers can be zero if this races with vfio_device_remove_group(), it
	 * will be stable at 0 under the group rwsem
	 */
	if (refcount_read(&group->drivers) == 0) {
		ret = -ENODEV;
		goto out_unlock;
	}

	if (group->type == VFIO_NO_IOMMU && !capable(CAP_SYS_RAWIO)) {
		ret = -EPERM;
		goto out_unlock;
	}

	/*
	 * Do we need multiple instances of the group open?  Seems not.
	 */
	if (group->opened_file) {
		ret = -EBUSY;
		goto out_unlock;
	}
	group->opened_file = filep;
	filep->private_data = group;
	ret = 0;
out_unlock:
	mutex_unlock(&group->group_lock);
	return ret;
}

static int vfio_group_fops_release(struct inode *inode, struct file *filep)
{
	struct vfio_group *group = filep->private_data;

	filep->private_data = NULL;

	mutex_lock(&group->group_lock);
	/*
	 * Device FDs hold a group file reference, therefore the group release
	 * is only called when there are no open devices.
	 */
	WARN_ON(group->notifier.head);
	if (group->container)
		vfio_group_detach_container(group);
	if (group->iommufd) {
		iommufd_ctx_put(group->iommufd);
		group->iommufd = NULL;
	}
	group->opened_file = NULL;
	mutex_unlock(&group->group_lock);
	return 0;
}

static const struct file_operations vfio_group_fops = {
	.owner		= THIS_MODULE,
	.unlocked_ioctl	= vfio_group_fops_unl_ioctl,
	.compat_ioctl	= compat_ptr_ioctl,
	.open		= vfio_group_fops_open,
	.release	= vfio_group_fops_release,
};

/*
 * Wrapper around pm_runtime_resume_and_get().
 * Return error code on failure or 0 on success.
 */
static inline int vfio_device_pm_runtime_get(struct vfio_device *device)
{
	struct device *dev = device->dev;

	if (dev->driver && dev->driver->pm) {
		int ret;

		ret = pm_runtime_resume_and_get(dev);
		if (ret) {
			dev_info_ratelimited(dev,
				"vfio: runtime resume failed %d\n", ret);
			return -EIO;
		}
	}

	return 0;
}

/*
 * Wrapper around pm_runtime_put().
 */
static inline void vfio_device_pm_runtime_put(struct vfio_device *device)
{
	struct device *dev = device->dev;

	if (dev->driver && dev->driver->pm)
		pm_runtime_put(dev);
}

/*
 * VFIO Device fd
 */
static int vfio_device_fops_release(struct inode *inode, struct file *filep)
{
	struct vfio_device *device = filep->private_data;

	vfio_device_group_close(device);

	vfio_device_put_registration(device);

	return 0;
}

/*
 * vfio_mig_get_next_state - Compute the next step in the FSM
 * @cur_fsm - The current state the device is in
 * @new_fsm - The target state to reach
 * @next_fsm - Pointer to the next step to get to new_fsm
 *
 * Return 0 upon success, otherwise -errno
 * Upon success the next step in the state progression between cur_fsm and
 * new_fsm will be set in next_fsm.
 *
 * This breaks down requests for combination transitions into smaller steps and
 * returns the next step to get to new_fsm. The function may need to be called
 * multiple times before reaching new_fsm.
 *
 */
int vfio_mig_get_next_state(struct vfio_device *device,
			    enum vfio_device_mig_state cur_fsm,
			    enum vfio_device_mig_state new_fsm,
			    enum vfio_device_mig_state *next_fsm)
{
	enum { VFIO_DEVICE_NUM_STATES = VFIO_DEVICE_STATE_RUNNING_P2P + 1 };
	/*
	 * The coding in this table requires the driver to implement the
	 * following FSM arcs:
	 *         RESUMING -> STOP
	 *         STOP -> RESUMING
	 *         STOP -> STOP_COPY
	 *         STOP_COPY -> STOP
	 *
	 * If P2P is supported then the driver must also implement these FSM
	 * arcs:
	 *         RUNNING -> RUNNING_P2P
	 *         RUNNING_P2P -> RUNNING
	 *         RUNNING_P2P -> STOP
	 *         STOP -> RUNNING_P2P
	 * Without P2P the driver must implement:
	 *         RUNNING -> STOP
	 *         STOP -> RUNNING
	 *
	 * The coding will step through multiple states for some combination
	 * transitions; if all optional features are supported, this means the
	 * following ones:
	 *         RESUMING -> STOP -> RUNNING_P2P
	 *         RESUMING -> STOP -> RUNNING_P2P -> RUNNING
	 *         RESUMING -> STOP -> STOP_COPY
	 *         RUNNING -> RUNNING_P2P -> STOP
	 *         RUNNING -> RUNNING_P2P -> STOP -> RESUMING
	 *         RUNNING -> RUNNING_P2P -> STOP -> STOP_COPY
	 *         RUNNING_P2P -> STOP -> RESUMING
	 *         RUNNING_P2P -> STOP -> STOP_COPY
	 *         STOP -> RUNNING_P2P -> RUNNING
	 *         STOP_COPY -> STOP -> RESUMING
	 *         STOP_COPY -> STOP -> RUNNING_P2P
	 *         STOP_COPY -> STOP -> RUNNING_P2P -> RUNNING
	 */
	static const u8 vfio_from_fsm_table[VFIO_DEVICE_NUM_STATES][VFIO_DEVICE_NUM_STATES] = {
		[VFIO_DEVICE_STATE_STOP] = {
			[VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP,
			[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING_P2P,
			[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP_COPY,
			[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RESUMING,
			[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P,
			[VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR,
		},
		[VFIO_DEVICE_STATE_RUNNING] = {
			[VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_RUNNING_P2P,
			[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING,
			[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_RUNNING_P2P,
			[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RUNNING_P2P,
			[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P,
			[VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR,
		},
		[VFIO_DEVICE_STATE_STOP_COPY] = {
			[VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP,
			[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_STOP,
			[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP_COPY,
			[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_STOP,
			[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_STOP,
			[VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR,
		},
		[VFIO_DEVICE_STATE_RESUMING] = {
			[VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP,
			[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_STOP,
			[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP,
			[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RESUMING,
			[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_STOP,
			[VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR,
		},
		[VFIO_DEVICE_STATE_RUNNING_P2P] = {
			[VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP,
			[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING,
			[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP,
			[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_STOP,
			[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P,
			[VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR,
		},
		[VFIO_DEVICE_STATE_ERROR] = {
			[VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_ERROR,
			[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_ERROR,
			[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_ERROR,
			[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_ERROR,
			[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_ERROR,
			[VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR,
		},
	};

	static const unsigned int state_flags_table[VFIO_DEVICE_NUM_STATES] = {
		[VFIO_DEVICE_STATE_STOP] = VFIO_MIGRATION_STOP_COPY,
		[VFIO_DEVICE_STATE_RUNNING] = VFIO_MIGRATION_STOP_COPY,
		[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_MIGRATION_STOP_COPY,
		[VFIO_DEVICE_STATE_RESUMING] = VFIO_MIGRATION_STOP_COPY,
		[VFIO_DEVICE_STATE_RUNNING_P2P] =
			VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P,
		[VFIO_DEVICE_STATE_ERROR] = ~0U,
	};

	if (WARN_ON(cur_fsm >= ARRAY_SIZE(vfio_from_fsm_table) ||
		    (state_flags_table[cur_fsm] & device->migration_flags) !=
			state_flags_table[cur_fsm]))
		return -EINVAL;

	if (new_fsm >= ARRAY_SIZE(vfio_from_fsm_table) ||
	   (state_flags_table[new_fsm] & device->migration_flags) !=
			state_flags_table[new_fsm])
		return -EINVAL;

	/*
	 * Arcs touching optional and unsupported states are skipped over. The
	 * driver will instead see an arc from the original state to the next
	 * logical state, as per the above comment.
	 */
	*next_fsm = vfio_from_fsm_table[cur_fsm][new_fsm];
	while ((state_flags_table[*next_fsm] & device->migration_flags) !=
			state_flags_table[*next_fsm])
		*next_fsm = vfio_from_fsm_table[*next_fsm][new_fsm];

	return (*next_fsm != VFIO_DEVICE_STATE_ERROR) ? 0 : -EINVAL;
}
EXPORT_SYMBOL_GPL(vfio_mig_get_next_state);

/*
 * Convert the drivers's struct file into a FD number and return it to userspace
 */
static int vfio_ioct_mig_return_fd(struct file *filp, void __user *arg,
				   struct vfio_device_feature_mig_state *mig)
{
	int ret;
	int fd;

	fd = get_unused_fd_flags(O_CLOEXEC);
	if (fd < 0) {
		ret = fd;
		goto out_fput;
	}

	mig->data_fd = fd;
	if (copy_to_user(arg, mig, sizeof(*mig))) {
		ret = -EFAULT;
		goto out_put_unused;
	}
	fd_install(fd, filp);
	return 0;

out_put_unused:
	put_unused_fd(fd);
out_fput:
	fput(filp);
	return ret;
}

static int
vfio_ioctl_device_feature_mig_device_state(struct vfio_device *device,
					   u32 flags, void __user *arg,
					   size_t argsz)
{
	size_t minsz =
		offsetofend(struct vfio_device_feature_mig_state, data_fd);
	struct vfio_device_feature_mig_state mig;
	struct file *filp = NULL;
	int ret;

	if (!device->mig_ops)
		return -ENOTTY;

	ret = vfio_check_feature(flags, argsz,
				 VFIO_DEVICE_FEATURE_SET |
				 VFIO_DEVICE_FEATURE_GET,
				 sizeof(mig));
	if (ret != 1)
		return ret;

	if (copy_from_user(&mig, arg, minsz))
		return -EFAULT;

	if (flags & VFIO_DEVICE_FEATURE_GET) {
		enum vfio_device_mig_state curr_state;

		ret = device->mig_ops->migration_get_state(device,
							   &curr_state);
		if (ret)
			return ret;
		mig.device_state = curr_state;
		goto out_copy;
	}

	/* Handle the VFIO_DEVICE_FEATURE_SET */
	filp = device->mig_ops->migration_set_state(device, mig.device_state);
	if (IS_ERR(filp) || !filp)
		goto out_copy;

	return vfio_ioct_mig_return_fd(filp, arg, &mig);
out_copy:
	mig.data_fd = -1;
	if (copy_to_user(arg, &mig, sizeof(mig)))
		return -EFAULT;
	if (IS_ERR(filp))
		return PTR_ERR(filp);
	return 0;
}

static int vfio_ioctl_device_feature_migration(struct vfio_device *device,
					       u32 flags, void __user *arg,
					       size_t argsz)
{
	struct vfio_device_feature_migration mig = {
		.flags = device->migration_flags,
	};
	int ret;

	if (!device->mig_ops)
		return -ENOTTY;

	ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_GET,
				 sizeof(mig));
	if (ret != 1)
		return ret;
	if (copy_to_user(arg, &mig, sizeof(mig)))
		return -EFAULT;
	return 0;
}

/* Ranges should fit into a single kernel page */
#define LOG_MAX_RANGES \
	(PAGE_SIZE / sizeof(struct vfio_device_feature_dma_logging_range))

static int
vfio_ioctl_device_feature_logging_start(struct vfio_device *device,
					u32 flags, void __user *arg,
					size_t argsz)
{
	size_t minsz =
		offsetofend(struct vfio_device_feature_dma_logging_control,
			    ranges);
	struct vfio_device_feature_dma_logging_range __user *ranges;
	struct vfio_device_feature_dma_logging_control control;
	struct vfio_device_feature_dma_logging_range range;
	struct rb_root_cached root = RB_ROOT_CACHED;
	struct interval_tree_node *nodes;
	u64 iova_end;
	u32 nnodes;
	int i, ret;

	if (!device->log_ops)
		return -ENOTTY;

	ret = vfio_check_feature(flags, argsz,
				 VFIO_DEVICE_FEATURE_SET,
				 sizeof(control));
	if (ret != 1)
		return ret;

	if (copy_from_user(&control, arg, minsz))
		return -EFAULT;

	nnodes = control.num_ranges;
	if (!nnodes)
		return -EINVAL;

	if (nnodes > LOG_MAX_RANGES)
		return -E2BIG;

	ranges = u64_to_user_ptr(control.ranges);
	nodes = kmalloc_array(nnodes, sizeof(struct interval_tree_node),
			      GFP_KERNEL);
	if (!nodes)
		return -ENOMEM;

	for (i = 0; i < nnodes; i++) {
		if (copy_from_user(&range, &ranges[i], sizeof(range))) {
			ret = -EFAULT;
			goto end;
		}
		if (!IS_ALIGNED(range.iova, control.page_size) ||
		    !IS_ALIGNED(range.length, control.page_size)) {
			ret = -EINVAL;
			goto end;
		}

		if (check_add_overflow(range.iova, range.length, &iova_end) ||
		    iova_end > ULONG_MAX) {
			ret = -EOVERFLOW;
			goto end;
		}

		nodes[i].start = range.iova;
		nodes[i].last = range.iova + range.length - 1;
		if (interval_tree_iter_first(&root, nodes[i].start,
					     nodes[i].last)) {
			/* Range overlapping */
			ret = -EINVAL;
			goto end;
		}
		interval_tree_insert(nodes + i, &root);
	}

	ret = device->log_ops->log_start(device, &root, nnodes,
					 &control.page_size);
	if (ret)
		goto end;

	if (copy_to_user(arg, &control, sizeof(control))) {
		ret = -EFAULT;
		device->log_ops->log_stop(device);
	}

end:
	kfree(nodes);
	return ret;
}

static int
vfio_ioctl_device_feature_logging_stop(struct vfio_device *device,
				       u32 flags, void __user *arg,
				       size_t argsz)
{
	int ret;

	if (!device->log_ops)
		return -ENOTTY;

	ret = vfio_check_feature(flags, argsz,
				 VFIO_DEVICE_FEATURE_SET, 0);
	if (ret != 1)
		return ret;

	return device->log_ops->log_stop(device);
}

static int vfio_device_log_read_and_clear(struct iova_bitmap *iter,
					  unsigned long iova, size_t length,
					  void *opaque)
{
	struct vfio_device *device = opaque;

	return device->log_ops->log_read_and_clear(device, iova, length, iter);
}

static int
vfio_ioctl_device_feature_logging_report(struct vfio_device *device,
					 u32 flags, void __user *arg,
					 size_t argsz)
{
	size_t minsz =
		offsetofend(struct vfio_device_feature_dma_logging_report,
			    bitmap);
	struct vfio_device_feature_dma_logging_report report;
	struct iova_bitmap *iter;
	u64 iova_end;
	int ret;

	if (!device->log_ops)
		return -ENOTTY;

	ret = vfio_check_feature(flags, argsz,
				 VFIO_DEVICE_FEATURE_GET,
				 sizeof(report));
	if (ret != 1)
		return ret;

	if (copy_from_user(&report, arg, minsz))
		return -EFAULT;

	if (report.page_size < SZ_4K || !is_power_of_2(report.page_size))
		return -EINVAL;

	if (check_add_overflow(report.iova, report.length, &iova_end) ||
	    iova_end > ULONG_MAX)
		return -EOVERFLOW;

	iter = iova_bitmap_alloc(report.iova, report.length,
				 report.page_size,
				 u64_to_user_ptr(report.bitmap));
	if (IS_ERR(iter))
		return PTR_ERR(iter);

	ret = iova_bitmap_for_each(iter, device,
				   vfio_device_log_read_and_clear);

	iova_bitmap_free(iter);
	return ret;
}

static int vfio_ioctl_device_feature(struct vfio_device *device,
				     struct vfio_device_feature __user *arg)
{
	size_t minsz = offsetofend(struct vfio_device_feature, flags);
	struct vfio_device_feature feature;

	if (copy_from_user(&feature, arg, minsz))
		return -EFAULT;

	if (feature.argsz < minsz)
		return -EINVAL;

	/* Check unknown flags */
	if (feature.flags &
	    ~(VFIO_DEVICE_FEATURE_MASK | VFIO_DEVICE_FEATURE_SET |
	      VFIO_DEVICE_FEATURE_GET | VFIO_DEVICE_FEATURE_PROBE))
		return -EINVAL;

	/* GET & SET are mutually exclusive except with PROBE */
	if (!(feature.flags & VFIO_DEVICE_FEATURE_PROBE) &&
	    (feature.flags & VFIO_DEVICE_FEATURE_SET) &&
	    (feature.flags & VFIO_DEVICE_FEATURE_GET))
		return -EINVAL;

	switch (feature.flags & VFIO_DEVICE_FEATURE_MASK) {
	case VFIO_DEVICE_FEATURE_MIGRATION:
		return vfio_ioctl_device_feature_migration(
			device, feature.flags, arg->data,
			feature.argsz - minsz);
	case VFIO_DEVICE_FEATURE_MIG_DEVICE_STATE:
		return vfio_ioctl_device_feature_mig_device_state(
			device, feature.flags, arg->data,
			feature.argsz - minsz);
	case VFIO_DEVICE_FEATURE_DMA_LOGGING_START:
		return vfio_ioctl_device_feature_logging_start(
			device, feature.flags, arg->data,
			feature.argsz - minsz);
	case VFIO_DEVICE_FEATURE_DMA_LOGGING_STOP:
		return vfio_ioctl_device_feature_logging_stop(
			device, feature.flags, arg->data,
			feature.argsz - minsz);
	case VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT:
		return vfio_ioctl_device_feature_logging_report(
			device, feature.flags, arg->data,
			feature.argsz - minsz);
	default:
		if (unlikely(!device->ops->device_feature))
			return -EINVAL;
		return device->ops->device_feature(device, feature.flags,
						   arg->data,
						   feature.argsz - minsz);
	}
}

static long vfio_device_fops_unl_ioctl(struct file *filep,
				       unsigned int cmd, unsigned long arg)
{
	struct vfio_device *device = filep->private_data;
	int ret;

	ret = vfio_device_pm_runtime_get(device);
	if (ret)
		return ret;

	switch (cmd) {
	case VFIO_DEVICE_FEATURE:
		ret = vfio_ioctl_device_feature(device, (void __user *)arg);
		break;

	default:
		if (unlikely(!device->ops->ioctl))
			ret = -EINVAL;
		else
			ret = device->ops->ioctl(device, cmd, arg);
		break;
	}

	vfio_device_pm_runtime_put(device);
	return ret;
}

static ssize_t vfio_device_fops_read(struct file *filep, char __user *buf,
				     size_t count, loff_t *ppos)
{
	struct vfio_device *device = filep->private_data;

	if (unlikely(!device->ops->read))
		return -EINVAL;

	return device->ops->read(device, buf, count, ppos);
}

static ssize_t vfio_device_fops_write(struct file *filep,
				      const char __user *buf,
				      size_t count, loff_t *ppos)
{
	struct vfio_device *device = filep->private_data;

	if (unlikely(!device->ops->write))
		return -EINVAL;

	return device->ops->write(device, buf, count, ppos);
}

static int vfio_device_fops_mmap(struct file *filep, struct vm_area_struct *vma)
{
	struct vfio_device *device = filep->private_data;

	if (unlikely(!device->ops->mmap))
		return -EINVAL;

	return device->ops->mmap(device, vma);
}

static const struct file_operations vfio_device_fops = {
	.owner		= THIS_MODULE,
	.release	= vfio_device_fops_release,
	.read		= vfio_device_fops_read,
	.write		= vfio_device_fops_write,
	.unlocked_ioctl	= vfio_device_fops_unl_ioctl,
	.compat_ioctl	= compat_ptr_ioctl,
	.mmap		= vfio_device_fops_mmap,
};

/**
 * vfio_file_iommu_group - Return the struct iommu_group for the vfio group file
 * @file: VFIO group file
 *
 * The returned iommu_group is valid as long as a ref is held on the file. This
 * returns a reference on the group. This function is deprecated, only the SPAPR
 * path in kvm should call it.
 */
struct iommu_group *vfio_file_iommu_group(struct file *file)
{
	struct vfio_group *group = file->private_data;
	struct iommu_group *iommu_group = NULL;

	if (!IS_ENABLED(CONFIG_SPAPR_TCE_IOMMU))
		return NULL;

	if (!vfio_file_is_group(file))
		return NULL;

	mutex_lock(&group->group_lock);
	if (group->iommu_group) {
		iommu_group = group->iommu_group;
		iommu_group_ref_get(iommu_group);
	}
	mutex_unlock(&group->group_lock);
	return iommu_group;
}
EXPORT_SYMBOL_GPL(vfio_file_iommu_group);

/**
 * vfio_file_is_group - True if the file is usable with VFIO aPIS
 * @file: VFIO group file
 */
bool vfio_file_is_group(struct file *file)
{
	return file->f_op == &vfio_group_fops;
}
EXPORT_SYMBOL_GPL(vfio_file_is_group);

/**
 * vfio_file_enforced_coherent - True if the DMA associated with the VFIO file
 *        is always CPU cache coherent
 * @file: VFIO group file
 *
 * Enforced coherency means that the IOMMU ignores things like the PCIe no-snoop
 * bit in DMA transactions. A return of false indicates that the user has
 * rights to access additional instructions such as wbinvd on x86.
 */
bool vfio_file_enforced_coherent(struct file *file)
{
	struct vfio_group *group = file->private_data;
	struct vfio_device *device;
	bool ret = true;

	if (!vfio_file_is_group(file))
		return true;

	/*
	 * If the device does not have IOMMU_CAP_ENFORCE_CACHE_COHERENCY then
	 * any domain later attached to it will also not support it. If the cap
	 * is set then the iommu_domain eventually attached to the device/group
	 * must use a domain with enforce_cache_coherency().
	 */
	mutex_lock(&group->device_lock);
	list_for_each_entry(device, &group->device_list, group_next) {
		if (!device_iommu_capable(device->dev,
					  IOMMU_CAP_ENFORCE_CACHE_COHERENCY)) {
			ret = false;
			break;
		}
	}
	mutex_unlock(&group->device_lock);
	return ret;
}
EXPORT_SYMBOL_GPL(vfio_file_enforced_coherent);

/**
 * vfio_file_set_kvm - Link a kvm with VFIO drivers
 * @file: VFIO group file
 * @kvm: KVM to link
 *
 * When a VFIO device is first opened the KVM will be available in
 * device->kvm if one was associated with the group.
 */
void vfio_file_set_kvm(struct file *file, struct kvm *kvm)
{
	struct vfio_group *group = file->private_data;

	if (!vfio_file_is_group(file))
		return;

	mutex_lock(&group->group_lock);
	group->kvm = kvm;
	mutex_unlock(&group->group_lock);
}
EXPORT_SYMBOL_GPL(vfio_file_set_kvm);

/**
 * vfio_file_has_dev - True if the VFIO file is a handle for device
 * @file: VFIO file to check
 * @device: Device that must be part of the file
 *
 * Returns true if given file has permission to manipulate the given device.
 */
bool vfio_file_has_dev(struct file *file, struct vfio_device *device)
{
	struct vfio_group *group = file->private_data;

	if (!vfio_file_is_group(file))
		return false;

	return group == device->group;
}
EXPORT_SYMBOL_GPL(vfio_file_has_dev);

/*
 * Sub-module support
 */
/*
 * Helper for managing a buffer of info chain capabilities, allocate or
 * reallocate a buffer with additional @size, filling in @id and @version
 * of the capability.  A pointer to the new capability is returned.
 *
 * NB. The chain is based at the head of the buffer, so new entries are
 * added to the tail, vfio_info_cap_shift() should be called to fixup the
 * next offsets prior to copying to the user buffer.
 */
struct vfio_info_cap_header *vfio_info_cap_add(struct vfio_info_cap *caps,
					       size_t size, u16 id, u16 version)
{
	void *buf;
	struct vfio_info_cap_header *header, *tmp;

	buf = krealloc(caps->buf, caps->size + size, GFP_KERNEL);
	if (!buf) {
		kfree(caps->buf);
		caps->buf = NULL;
		caps->size = 0;
		return ERR_PTR(-ENOMEM);
	}

	caps->buf = buf;
	header = buf + caps->size;

	/* Eventually copied to user buffer, zero */
	memset(header, 0, size);

	header->id = id;
	header->version = version;

	/* Add to the end of the capability chain */
	for (tmp = buf; tmp->next; tmp = buf + tmp->next)
		; /* nothing */

	tmp->next = caps->size;
	caps->size += size;

	return header;
}
EXPORT_SYMBOL_GPL(vfio_info_cap_add);

void vfio_info_cap_shift(struct vfio_info_cap *caps, size_t offset)
{
	struct vfio_info_cap_header *tmp;
	void *buf = (void *)caps->buf;

	for (tmp = buf; tmp->next; tmp = buf + tmp->next - offset)
		tmp->next += offset;
}
EXPORT_SYMBOL(vfio_info_cap_shift);

int vfio_info_add_capability(struct vfio_info_cap *caps,
			     struct vfio_info_cap_header *cap, size_t size)
{
	struct vfio_info_cap_header *header;

	header = vfio_info_cap_add(caps, size, cap->id, cap->version);
	if (IS_ERR(header))
		return PTR_ERR(header);

	memcpy(header + 1, cap + 1, size - sizeof(*header));

	return 0;
}
EXPORT_SYMBOL(vfio_info_add_capability);

int vfio_set_irqs_validate_and_prepare(struct vfio_irq_set *hdr, int num_irqs,
				       int max_irq_type, size_t *data_size)
{
	unsigned long minsz;
	size_t size;

	minsz = offsetofend(struct vfio_irq_set, count);

	if ((hdr->argsz < minsz) || (hdr->index >= max_irq_type) ||
	    (hdr->count >= (U32_MAX - hdr->start)) ||
	    (hdr->flags & ~(VFIO_IRQ_SET_DATA_TYPE_MASK |
				VFIO_IRQ_SET_ACTION_TYPE_MASK)))
		return -EINVAL;

	if (data_size)
		*data_size = 0;

	if (hdr->start >= num_irqs || hdr->start + hdr->count > num_irqs)
		return -EINVAL;

	switch (hdr->flags & VFIO_IRQ_SET_DATA_TYPE_MASK) {
	case VFIO_IRQ_SET_DATA_NONE:
		size = 0;
		break;
	case VFIO_IRQ_SET_DATA_BOOL:
		size = sizeof(uint8_t);
		break;
	case VFIO_IRQ_SET_DATA_EVENTFD:
		size = sizeof(int32_t);
		break;
	default:
		return -EINVAL;
	}

	if (size) {
		if (hdr->argsz - minsz < hdr->count * size)
			return -EINVAL;

		if (!data_size)
			return -EINVAL;

		*data_size = hdr->count * size;
	}

	return 0;
}
EXPORT_SYMBOL(vfio_set_irqs_validate_and_prepare);

/*
 * Pin contiguous user pages and return their associated host pages for local
 * domain only.
 * @device [in]  : device
 * @iova [in]    : starting IOVA of user pages to be pinned.
 * @npage [in]   : count of pages to be pinned.  This count should not
 *		   be greater than VFIO_PIN_PAGES_MAX_ENTRIES.
 * @prot [in]    : protection flags
 * @pages[out]   : array of host pages
 * Return error or number of pages pinned.
 *
 * A driver may only call this function if the vfio_device was created
 * by vfio_register_emulated_iommu_dev() due to vfio_container_pin_pages().
 */
int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova,
		   int npage, int prot, struct page **pages)
{
	/* group->container cannot change while a vfio device is open */
	if (!pages || !npage || WARN_ON(!vfio_assert_device_open(device)))
		return -EINVAL;
	if (device->group->container)
		return vfio_container_pin_pages(device->group->container,
						device->group->iommu_group,
						iova, npage, prot, pages);
	if (device->iommufd_access) {
		int ret;

		if (iova > ULONG_MAX)
			return -EINVAL;
		/*
		 * VFIO ignores the sub page offset, npages is from the start of
		 * a PAGE_SIZE chunk of IOVA. The caller is expected to recover
		 * the sub page offset by doing:
		 *     pages[0] + (iova % PAGE_SIZE)
		 */
		ret = iommufd_access_pin_pages(
			device->iommufd_access, ALIGN_DOWN(iova, PAGE_SIZE),
			npage * PAGE_SIZE, pages,
			(prot & IOMMU_WRITE) ? IOMMUFD_ACCESS_RW_WRITE : 0);
		if (ret)
			return ret;
		return npage;
	}
	return -EINVAL;
}
EXPORT_SYMBOL(vfio_pin_pages);

/*
 * Unpin contiguous host pages for local domain only.
 * @device [in]  : device
 * @iova [in]    : starting address of user pages to be unpinned.
 * @npage [in]   : count of pages to be unpinned.  This count should not
 *                 be greater than VFIO_PIN_PAGES_MAX_ENTRIES.
 */
void vfio_unpin_pages(struct vfio_device *device, dma_addr_t iova, int npage)
{
	if (WARN_ON(!vfio_assert_device_open(device)))
		return;

	if (device->group->container) {
		vfio_container_unpin_pages(device->group->container, iova,
					   npage);
		return;
	}
	if (device->iommufd_access) {
		if (WARN_ON(iova > ULONG_MAX))
			return;
		iommufd_access_unpin_pages(device->iommufd_access,
					   ALIGN_DOWN(iova, PAGE_SIZE),
					   npage * PAGE_SIZE);
		return;
	}
}
EXPORT_SYMBOL(vfio_unpin_pages);

/*
 * This interface allows the CPUs to perform some sort of virtual DMA on
 * behalf of the device.
 *
 * CPUs read/write from/into a range of IOVAs pointing to user space memory
 * into/from a kernel buffer.
 *
 * As the read/write of user space memory is conducted via the CPUs and is
 * not a real device DMA, it is not necessary to pin the user space memory.
 *
 * @device [in]		: VFIO device
 * @iova [in]		: base IOVA of a user space buffer
 * @data [in]		: pointer to kernel buffer
 * @len [in]		: kernel buffer length
 * @write		: indicate read or write
 * Return error code on failure or 0 on success.
 */
int vfio_dma_rw(struct vfio_device *device, dma_addr_t iova, void *data,
		size_t len, bool write)
{
	if (!data || len <= 0 || !vfio_assert_device_open(device))
		return -EINVAL;

	if (device->group->container)
		return vfio_container_dma_rw(device->group->container, iova,
					     data, len, write);

	if (device->iommufd_access) {
		unsigned int flags = 0;

		if (iova > ULONG_MAX)
			return -EINVAL;

		/* VFIO historically tries to auto-detect a kthread */
		if (!current->mm)
			flags |= IOMMUFD_ACCESS_RW_KTHREAD;
		if (write)
			flags |= IOMMUFD_ACCESS_RW_WRITE;
		return iommufd_access_rw(device->iommufd_access, iova, data,
					 len, flags);
	}
	return -EINVAL;
}
EXPORT_SYMBOL(vfio_dma_rw);

/*
 * Module/class support
 */
static char *vfio_devnode(struct device *dev, umode_t *mode)
{
	return kasprintf(GFP_KERNEL, "vfio/%s", dev_name(dev));
}

static int __init vfio_group_init(void)
{
	int ret;

	ida_init(&vfio.group_ida);
	mutex_init(&vfio.group_lock);
	INIT_LIST_HEAD(&vfio.group_list);

	ret = vfio_container_init();
	if (ret)
		return ret;

	/* /dev/vfio/$GROUP */
	vfio.class = class_create(THIS_MODULE, "vfio");
	if (IS_ERR(vfio.class)) {
		ret = PTR_ERR(vfio.class);
		goto err_group_class;
	}

	vfio.class->devnode = vfio_devnode;

	ret = alloc_chrdev_region(&vfio.group_devt, 0, MINORMASK + 1, "vfio");
	if (ret)
		goto err_alloc_chrdev;
	return 0;

err_alloc_chrdev:
	class_destroy(vfio.class);
	vfio.class = NULL;
err_group_class:
	vfio_container_cleanup();
	return ret;
}

static void vfio_group_cleanup(void)
{
	WARN_ON(!list_empty(&vfio.group_list));
	ida_destroy(&vfio.group_ida);
	unregister_chrdev_region(vfio.group_devt, MINORMASK + 1);
	class_destroy(vfio.class);
	vfio.class = NULL;
	vfio_container_cleanup();
}

static int __init vfio_init(void)
{
	int ret;

	ida_init(&vfio.device_ida);

	ret = vfio_group_init();
	if (ret)
		return ret;

	/* /sys/class/vfio-dev/vfioX */
	vfio.device_class = class_create(THIS_MODULE, "vfio-dev");
	if (IS_ERR(vfio.device_class)) {
		ret = PTR_ERR(vfio.device_class);
		goto err_dev_class;
	}

	pr_info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
	return 0;

err_dev_class:
	vfio_group_cleanup();
	return ret;
}

static void __exit vfio_cleanup(void)
{
	ida_destroy(&vfio.device_ida);
	class_destroy(vfio.device_class);
	vfio.device_class = NULL;
	vfio_group_cleanup();
	xa_destroy(&vfio_device_set_xa);
}

module_init(vfio_init);
module_exit(vfio_cleanup);

MODULE_VERSION(DRIVER_VERSION);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR(DRIVER_AUTHOR);
MODULE_DESCRIPTION(DRIVER_DESC);
MODULE_SOFTDEP("post: vfio_iommu_type1 vfio_iommu_spapr_tce");