summaryrefslogtreecommitdiff
path: root/drivers/vfio/vfio.c
blob: 15d8e678e5563ae0bb5cc002295f19e58f59f357 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
// 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>

#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		iommu_drivers_list;
	struct mutex			iommu_drivers_lock;
	struct list_head		group_list;
	struct idr			group_idr;
	struct mutex			group_lock;
	struct cdev			group_cdev;
	dev_t				group_devt;
	wait_queue_head_t		release_q;
} vfio;

struct vfio_iommu_driver {
	const struct vfio_iommu_driver_ops	*ops;
	struct list_head			vfio_next;
};

struct vfio_container {
	struct kref			kref;
	struct list_head		group_list;
	struct rw_semaphore		group_lock;
	struct vfio_iommu_driver	*iommu_driver;
	void				*iommu_data;
	bool				noiommu;
};

struct vfio_unbound_dev {
	struct device			*dev;
	struct list_head		unbound_next;
};

struct vfio_group {
	struct kref			kref;
	int				minor;
	atomic_t			container_users;
	struct iommu_group		*iommu_group;
	struct vfio_container		*container;
	struct list_head		device_list;
	struct mutex			device_lock;
	struct device			*dev;
	struct notifier_block		nb;
	struct list_head		vfio_next;
	struct list_head		container_next;
	struct list_head		unbound_list;
	struct mutex			unbound_lock;
	atomic_t			opened;
	wait_queue_head_t		container_q;
	bool				noiommu;
	unsigned int			dev_counter;
	struct kvm			*kvm;
	struct blocking_notifier_head	notifier;
};

struct vfio_device {
	struct kref			kref;
	struct device			*dev;
	const struct vfio_device_ops	*ops;
	struct vfio_group		*group;
	struct list_head		group_next;
	void				*device_data;
};

#ifdef CONFIG_VFIO_NOIOMMU
static bool noiommu __read_mostly;
module_param_named(enable_unsafe_noiommu_mode,
		   noiommu, bool, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(enable_unsafe_noiommu_mode, "Enable UNSAFE, no-IOMMU mode.  This mode provides no device isolation, no DMA translation, no host kernel protection, cannot be used for device assignment to virtual machines, requires RAWIO permissions, and will taint the kernel.  If you do not know what this is for, step away. (default: false)");
#endif

/*
 * vfio_iommu_group_{get,put} are only intended for VFIO bus driver probe
 * and remove functions, any use cases other than acquiring the first
 * reference for the purpose of calling vfio_add_group_dev() or removing
 * that symmetric reference after vfio_del_group_dev() should use the raw
 * iommu_group_{get,put} functions.  In particular, vfio_iommu_group_put()
 * removes the device from the dummy group and cannot be nested.
 */
struct iommu_group *vfio_iommu_group_get(struct device *dev)
{
	struct iommu_group *group;
	int __maybe_unused ret;

	group = iommu_group_get(dev);

#ifdef CONFIG_VFIO_NOIOMMU
	/*
	 * With noiommu enabled, an IOMMU group will be created for a device
	 * that doesn't already have one and doesn't have an iommu_ops on their
	 * bus.  We set iommudata simply to be able to identify these groups
	 * as special use and for reclamation later.
	 */
	if (group || !noiommu || iommu_present(dev->bus))
		return group;

	group = iommu_group_alloc();
	if (IS_ERR(group))
		return NULL;

	iommu_group_set_name(group, "vfio-noiommu");
	iommu_group_set_iommudata(group, &noiommu, NULL);
	ret = iommu_group_add_device(group, dev);
	if (ret) {
		iommu_group_put(group);
		return NULL;
	}

	/*
	 * Where to taint?  At this point we've added an IOMMU group for a
	 * device that is not backed by iommu_ops, therefore any iommu_
	 * callback using iommu_ops can legitimately Oops.  So, while we may
	 * be about to give a DMA capable device to a user without IOMMU
	 * protection, which is clearly taint-worthy, let's go ahead and do
	 * it here.
	 */
	add_taint(TAINT_USER, LOCKDEP_STILL_OK);
	dev_warn(dev, "Adding kernel taint for vfio-noiommu group on device\n");
#endif

	return group;
}
EXPORT_SYMBOL_GPL(vfio_iommu_group_get);

void vfio_iommu_group_put(struct iommu_group *group, struct device *dev)
{
#ifdef CONFIG_VFIO_NOIOMMU
	if (iommu_group_get_iommudata(group) == &noiommu)
		iommu_group_remove_device(dev);
#endif

	iommu_group_put(group);
}
EXPORT_SYMBOL_GPL(vfio_iommu_group_put);

#ifdef CONFIG_VFIO_NOIOMMU
static void *vfio_noiommu_open(unsigned long arg)
{
	if (arg != VFIO_NOIOMMU_IOMMU)
		return ERR_PTR(-EINVAL);
	if (!capable(CAP_SYS_RAWIO))
		return ERR_PTR(-EPERM);

	return NULL;
}

static void vfio_noiommu_release(void *iommu_data)
{
}

static long vfio_noiommu_ioctl(void *iommu_data,
			       unsigned int cmd, unsigned long arg)
{
	if (cmd == VFIO_CHECK_EXTENSION)
		return noiommu && (arg == VFIO_NOIOMMU_IOMMU) ? 1 : 0;

	return -ENOTTY;
}

static int vfio_noiommu_attach_group(void *iommu_data,
				     struct iommu_group *iommu_group)
{
	return iommu_group_get_iommudata(iommu_group) == &noiommu ? 0 : -EINVAL;
}

static void vfio_noiommu_detach_group(void *iommu_data,
				      struct iommu_group *iommu_group)
{
}

static const struct vfio_iommu_driver_ops vfio_noiommu_ops = {
	.name = "vfio-noiommu",
	.owner = THIS_MODULE,
	.open = vfio_noiommu_open,
	.release = vfio_noiommu_release,
	.ioctl = vfio_noiommu_ioctl,
	.attach_group = vfio_noiommu_attach_group,
	.detach_group = vfio_noiommu_detach_group,
};
#endif


/**
 * IOMMU driver registration
 */
int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops)
{
	struct vfio_iommu_driver *driver, *tmp;

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

	driver->ops = ops;

	mutex_lock(&vfio.iommu_drivers_lock);

	/* Check for duplicates */
	list_for_each_entry(tmp, &vfio.iommu_drivers_list, vfio_next) {
		if (tmp->ops == ops) {
			mutex_unlock(&vfio.iommu_drivers_lock);
			kfree(driver);
			return -EINVAL;
		}
	}

	list_add(&driver->vfio_next, &vfio.iommu_drivers_list);

	mutex_unlock(&vfio.iommu_drivers_lock);

	return 0;
}
EXPORT_SYMBOL_GPL(vfio_register_iommu_driver);

void vfio_unregister_iommu_driver(const struct vfio_iommu_driver_ops *ops)
{
	struct vfio_iommu_driver *driver;

	mutex_lock(&vfio.iommu_drivers_lock);
	list_for_each_entry(driver, &vfio.iommu_drivers_list, vfio_next) {
		if (driver->ops == ops) {
			list_del(&driver->vfio_next);
			mutex_unlock(&vfio.iommu_drivers_lock);
			kfree(driver);
			return;
		}
	}
	mutex_unlock(&vfio.iommu_drivers_lock);
}
EXPORT_SYMBOL_GPL(vfio_unregister_iommu_driver);

/**
 * Group minor allocation/free - both called with vfio.group_lock held
 */
static int vfio_alloc_group_minor(struct vfio_group *group)
{
	return idr_alloc(&vfio.group_idr, group, 0, MINORMASK + 1, GFP_KERNEL);
}

static void vfio_free_group_minor(int minor)
{
	idr_remove(&vfio.group_idr, minor);
}

static int vfio_iommu_group_notifier(struct notifier_block *nb,
				     unsigned long action, void *data);
static void vfio_group_get(struct vfio_group *group);

/**
 * Container objects - containers are created when /dev/vfio/vfio is
 * opened, but their lifecycle extends until the last user is done, so
 * it's freed via kref.  Must support container/group/device being
 * closed in any order.
 */
static void vfio_container_get(struct vfio_container *container)
{
	kref_get(&container->kref);
}

static void vfio_container_release(struct kref *kref)
{
	struct vfio_container *container;
	container = container_of(kref, struct vfio_container, kref);

	kfree(container);
}

static void vfio_container_put(struct vfio_container *container)
{
	kref_put(&container->kref, vfio_container_release);
}

static void vfio_group_unlock_and_free(struct vfio_group *group)
{
	mutex_unlock(&vfio.group_lock);
	/*
	 * Unregister outside of lock.  A spurious callback is harmless now
	 * that the group is no longer in vfio.group_list.
	 */
	iommu_group_unregister_notifier(group->iommu_group, &group->nb);
	kfree(group);
}

/**
 * Group objects - create, release, get, put, search
 */
static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group)
{
	struct vfio_group *group, *tmp;
	struct device *dev;
	int ret, minor;

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

	kref_init(&group->kref);
	INIT_LIST_HEAD(&group->device_list);
	mutex_init(&group->device_lock);
	INIT_LIST_HEAD(&group->unbound_list);
	mutex_init(&group->unbound_lock);
	atomic_set(&group->container_users, 0);
	atomic_set(&group->opened, 0);
	init_waitqueue_head(&group->container_q);
	group->iommu_group = iommu_group;
#ifdef CONFIG_VFIO_NOIOMMU
	group->noiommu = (iommu_group_get_iommudata(iommu_group) == &noiommu);
#endif
	BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier);

	group->nb.notifier_call = vfio_iommu_group_notifier;

	/*
	 * blocking notifiers acquire a rwsem around registering and hold
	 * it around callback.  Therefore, need to register outside of
	 * vfio.group_lock to avoid A-B/B-A contention.  Our callback won't
	 * do anything unless it can find the group in vfio.group_list, so
	 * no harm in registering early.
	 */
	ret = iommu_group_register_notifier(iommu_group, &group->nb);
	if (ret) {
		kfree(group);
		return ERR_PTR(ret);
	}

	mutex_lock(&vfio.group_lock);

	/* Did we race creating this group? */
	list_for_each_entry(tmp, &vfio.group_list, vfio_next) {
		if (tmp->iommu_group == iommu_group) {
			vfio_group_get(tmp);
			vfio_group_unlock_and_free(group);
			return tmp;
		}
	}

	minor = vfio_alloc_group_minor(group);
	if (minor < 0) {
		vfio_group_unlock_and_free(group);
		return ERR_PTR(minor);
	}

	dev = device_create(vfio.class, NULL,
			    MKDEV(MAJOR(vfio.group_devt), minor),
			    group, "%s%d", group->noiommu ? "noiommu-" : "",
			    iommu_group_id(iommu_group));
	if (IS_ERR(dev)) {
		vfio_free_group_minor(minor);
		vfio_group_unlock_and_free(group);
		return ERR_CAST(dev);
	}

	group->minor = minor;
	group->dev = dev;

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

	mutex_unlock(&vfio.group_lock);

	return group;
}

/* called with vfio.group_lock held */
static void vfio_group_release(struct kref *kref)
{
	struct vfio_group *group = container_of(kref, struct vfio_group, kref);
	struct vfio_unbound_dev *unbound, *tmp;
	struct iommu_group *iommu_group = group->iommu_group;

	WARN_ON(!list_empty(&group->device_list));
	WARN_ON(group->notifier.head);

	list_for_each_entry_safe(unbound, tmp,
				 &group->unbound_list, unbound_next) {
		list_del(&unbound->unbound_next);
		kfree(unbound);
	}

	device_destroy(vfio.class, MKDEV(MAJOR(vfio.group_devt), group->minor));
	list_del(&group->vfio_next);
	vfio_free_group_minor(group->minor);
	vfio_group_unlock_and_free(group);
	iommu_group_put(iommu_group);
}

static void vfio_group_put(struct vfio_group *group)
{
	kref_put_mutex(&group->kref, vfio_group_release, &vfio.group_lock);
}

struct vfio_group_put_work {
	struct work_struct work;
	struct vfio_group *group;
};

static void vfio_group_put_bg(struct work_struct *work)
{
	struct vfio_group_put_work *do_work;

	do_work = container_of(work, struct vfio_group_put_work, work);

	vfio_group_put(do_work->group);
	kfree(do_work);
}

static void vfio_group_schedule_put(struct vfio_group *group)
{
	struct vfio_group_put_work *do_work;

	do_work = kmalloc(sizeof(*do_work), GFP_KERNEL);
	if (WARN_ON(!do_work))
		return;

	INIT_WORK(&do_work->work, vfio_group_put_bg);
	do_work->group = group;
	schedule_work(&do_work->work);
}

/* Assume group_lock or group reference is held */
static void vfio_group_get(struct vfio_group *group)
{
	kref_get(&group->kref);
}

/*
 * Not really a try as we will sleep for mutex, but we need to make
 * sure the group pointer is valid under lock and get a reference.
 */
static struct vfio_group *vfio_group_try_get(struct vfio_group *group)
{
	struct vfio_group *target = group;

	mutex_lock(&vfio.group_lock);
	list_for_each_entry(group, &vfio.group_list, vfio_next) {
		if (group == target) {
			vfio_group_get(group);
			mutex_unlock(&vfio.group_lock);
			return group;
		}
	}
	mutex_unlock(&vfio.group_lock);

	return NULL;
}

static
struct vfio_group *vfio_group_get_from_iommu(struct iommu_group *iommu_group)
{
	struct vfio_group *group;

	mutex_lock(&vfio.group_lock);
	list_for_each_entry(group, &vfio.group_list, vfio_next) {
		if (group->iommu_group == iommu_group) {
			vfio_group_get(group);
			mutex_unlock(&vfio.group_lock);
			return group;
		}
	}
	mutex_unlock(&vfio.group_lock);

	return NULL;
}

static struct vfio_group *vfio_group_get_from_minor(int minor)
{
	struct vfio_group *group;

	mutex_lock(&vfio.group_lock);
	group = idr_find(&vfio.group_idr, minor);
	if (!group) {
		mutex_unlock(&vfio.group_lock);
		return NULL;
	}
	vfio_group_get(group);
	mutex_unlock(&vfio.group_lock);

	return group;
}

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

	iommu_group = iommu_group_get(dev);
	if (!iommu_group)
		return NULL;

	group = vfio_group_get_from_iommu(iommu_group);
	iommu_group_put(iommu_group);

	return group;
}

/**
 * Device objects - create, release, get, put, search
 */
static
struct vfio_device *vfio_group_create_device(struct vfio_group *group,
					     struct device *dev,
					     const struct vfio_device_ops *ops,
					     void *device_data)
{
	struct vfio_device *device;

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

	kref_init(&device->kref);
	device->dev = dev;
	/* Our reference on group is moved to the device */
	device->group = group;
	device->ops = ops;
	device->device_data = device_data;
	dev_set_drvdata(dev, device);

	mutex_lock(&group->device_lock);
	list_add(&device->group_next, &group->device_list);
	group->dev_counter++;
	mutex_unlock(&group->device_lock);

	return device;
}

static void vfio_device_release(struct kref *kref)
{
	struct vfio_device *device = container_of(kref,
						  struct vfio_device, kref);
	struct vfio_group *group = device->group;

	list_del(&device->group_next);
	group->dev_counter--;
	mutex_unlock(&group->device_lock);

	dev_set_drvdata(device->dev, NULL);

	kfree(device);

	/* vfio_del_group_dev may be waiting for this device */
	wake_up(&vfio.release_q);
}

/* Device reference always implies a group reference */
void vfio_device_put(struct vfio_device *device)
{
	struct vfio_group *group = device->group;
	kref_put_mutex(&device->kref, vfio_device_release, &group->device_lock);
}
EXPORT_SYMBOL_GPL(vfio_device_put);

static void vfio_device_get(struct vfio_device *device)
{
	kref_get(&device->kref);
}

static struct vfio_device *vfio_group_get_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) {
			vfio_device_get(device);
			mutex_unlock(&group->device_lock);
			return device;
		}
	}
	mutex_unlock(&group->device_lock);
	return NULL;
}

/*
 * Some drivers, like pci-stub, are only used to prevent other drivers from
 * claiming a device and are therefore perfectly legitimate for a user owned
 * group.  The pci-stub driver has no dependencies on DMA or the IOVA mapping
 * of the device, but it does prevent the user from having direct access to
 * the device, which is useful in some circumstances.
 *
 * We also assume that we can include PCI interconnect devices, ie. bridges.
 * IOMMU grouping on PCI necessitates that if we lack isolation on a bridge
 * then all of the downstream devices will be part of the same IOMMU group as
 * the bridge.  Thus, if placing the bridge into the user owned IOVA space
 * breaks anything, it only does so for user owned devices downstream.  Note
 * that error notification via MSI can be affected for platforms that handle
 * MSI within the same IOVA space as DMA.
 */
static const char * const vfio_driver_allowed[] = { "pci-stub" };

static bool vfio_dev_driver_allowed(struct device *dev,
				    struct device_driver *drv)
{
	if (dev_is_pci(dev)) {
		struct pci_dev *pdev = to_pci_dev(dev);

		if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL)
			return true;
	}

	return match_string(vfio_driver_allowed,
			    ARRAY_SIZE(vfio_driver_allowed),
			    drv->name) >= 0;
}

/*
 * A vfio group is viable for use by userspace if all devices are in
 * one of the following states:
 *  - driver-less
 *  - bound to a vfio driver
 *  - bound to an otherwise allowed driver
 *  - a PCI interconnect device
 *
 * We use two methods to determine whether a device is bound to a vfio
 * driver.  The first is to test whether the device exists in the vfio
 * group.  The second is to test if the device exists on the group
 * unbound_list, indicating it's in the middle of transitioning from
 * a vfio driver to driver-less.
 */
static int vfio_dev_viable(struct device *dev, void *data)
{
	struct vfio_group *group = data;
	struct vfio_device *device;
	struct device_driver *drv = READ_ONCE(dev->driver);
	struct vfio_unbound_dev *unbound;
	int ret = -EINVAL;

	mutex_lock(&group->unbound_lock);
	list_for_each_entry(unbound, &group->unbound_list, unbound_next) {
		if (dev == unbound->dev) {
			ret = 0;
			break;
		}
	}
	mutex_unlock(&group->unbound_lock);

	if (!ret || !drv || vfio_dev_driver_allowed(dev, drv))
		return 0;

	device = vfio_group_get_device(group, dev);
	if (device) {
		vfio_device_put(device);
		return 0;
	}

	return ret;
}

/**
 * Async device support
 */
static int vfio_group_nb_add_dev(struct vfio_group *group, struct device *dev)
{
	struct vfio_device *device;

	/* Do we already know about it?  We shouldn't */
	device = vfio_group_get_device(group, dev);
	if (WARN_ON_ONCE(device)) {
		vfio_device_put(device);
		return 0;
	}

	/* Nothing to do for idle groups */
	if (!atomic_read(&group->container_users))
		return 0;

	/* TODO Prevent device auto probing */
	dev_WARN(dev, "Device added to live group %d!\n",
		 iommu_group_id(group->iommu_group));

	return 0;
}

static int vfio_group_nb_verify(struct vfio_group *group, struct device *dev)
{
	/* We don't care what happens when the group isn't in use */
	if (!atomic_read(&group->container_users))
		return 0;

	return vfio_dev_viable(dev, group);
}

static int vfio_iommu_group_notifier(struct notifier_block *nb,
				     unsigned long action, void *data)
{
	struct vfio_group *group = container_of(nb, struct vfio_group, nb);
	struct device *dev = data;
	struct vfio_unbound_dev *unbound;

	/*
	 * Need to go through a group_lock lookup to get a reference or we
	 * risk racing a group being removed.  Ignore spurious notifies.
	 */
	group = vfio_group_try_get(group);
	if (!group)
		return NOTIFY_OK;

	switch (action) {
	case IOMMU_GROUP_NOTIFY_ADD_DEVICE:
		vfio_group_nb_add_dev(group, dev);
		break;
	case IOMMU_GROUP_NOTIFY_DEL_DEVICE:
		/*
		 * Nothing to do here.  If the device is in use, then the
		 * vfio sub-driver should block the remove callback until
		 * it is unused.  If the device is unused or attached to a
		 * stub driver, then it should be released and we don't
		 * care that it will be going away.
		 */
		break;
	case IOMMU_GROUP_NOTIFY_BIND_DRIVER:
		dev_dbg(dev, "%s: group %d binding to driver\n", __func__,
			iommu_group_id(group->iommu_group));
		break;
	case IOMMU_GROUP_NOTIFY_BOUND_DRIVER:
		dev_dbg(dev, "%s: group %d bound to driver %s\n", __func__,
			iommu_group_id(group->iommu_group), dev->driver->name);
		BUG_ON(vfio_group_nb_verify(group, dev));
		break;
	case IOMMU_GROUP_NOTIFY_UNBIND_DRIVER:
		dev_dbg(dev, "%s: group %d unbinding from driver %s\n",
			__func__, iommu_group_id(group->iommu_group),
			dev->driver->name);
		break;
	case IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER:
		dev_dbg(dev, "%s: group %d unbound from driver\n", __func__,
			iommu_group_id(group->iommu_group));
		/*
		 * XXX An unbound device in a live group is ok, but we'd
		 * really like to avoid the above BUG_ON by preventing other
		 * drivers from binding to it.  Once that occurs, we have to
		 * stop the system to maintain isolation.  At a minimum, we'd
		 * want a toggle to disable driver auto probe for this device.
		 */

		mutex_lock(&group->unbound_lock);
		list_for_each_entry(unbound,
				    &group->unbound_list, unbound_next) {
			if (dev == unbound->dev) {
				list_del(&unbound->unbound_next);
				kfree(unbound);
				break;
			}
		}
		mutex_unlock(&group->unbound_lock);
		break;
	}

	/*
	 * If we're the last reference to the group, the group will be
	 * released, which includes unregistering the iommu group notifier.
	 * We hold a read-lock on that notifier list, unregistering needs
	 * a write-lock... deadlock.  Release our reference asynchronously
	 * to avoid that situation.
	 */
	vfio_group_schedule_put(group);
	return NOTIFY_OK;
}

/**
 * VFIO driver API
 */
int vfio_add_group_dev(struct device *dev,
		       const struct vfio_device_ops *ops, void *device_data)
{
	struct iommu_group *iommu_group;
	struct vfio_group *group;
	struct vfio_device *device;

	iommu_group = iommu_group_get(dev);
	if (!iommu_group)
		return -EINVAL;

	group = vfio_group_get_from_iommu(iommu_group);
	if (!group) {
		group = vfio_create_group(iommu_group);
		if (IS_ERR(group)) {
			iommu_group_put(iommu_group);
			return PTR_ERR(group);
		}
	} else {
		/*
		 * A found vfio_group already holds a reference to the
		 * iommu_group.  A created vfio_group keeps the reference.
		 */
		iommu_group_put(iommu_group);
	}

	device = vfio_group_get_device(group, dev);
	if (device) {
		dev_WARN(dev, "Device already exists on group %d\n",
			 iommu_group_id(iommu_group));
		vfio_device_put(device);
		vfio_group_put(group);
		return -EBUSY;
	}

	device = vfio_group_create_device(group, dev, ops, device_data);
	if (IS_ERR(device)) {
		vfio_group_put(group);
		return PTR_ERR(device);
	}
	return 0;
}
EXPORT_SYMBOL_GPL(vfio_add_group_dev);

/**
 * Get a reference to the vfio_device for a device.  Even if the
 * caller thinks they own the device, they could be racing with a
 * release call path, so we can't trust drvdata for the shortcut.
 * Go the long way around, from the iommu_group to the vfio_group
 * to the vfio_device.
 */
struct vfio_device *vfio_device_get_from_dev(struct device *dev)
{
	struct vfio_group *group;
	struct vfio_device *device;

	group = vfio_group_get_from_dev(dev);
	if (!group)
		return NULL;

	device = vfio_group_get_device(group, dev);
	vfio_group_put(group);

	return device;
}
EXPORT_SYMBOL_GPL(vfio_device_get_from_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->device_data, buf);
			if (ret < 0) {
				device = ERR_PTR(ret);
				break;
			}
		} else {
			ret = !strcmp(dev_name(it->dev), buf);
		}

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

	return device;
}

/*
 * Caller must hold a reference to the vfio_device
 */
void *vfio_device_data(struct vfio_device *device)
{
	return device->device_data;
}
EXPORT_SYMBOL_GPL(vfio_device_data);

/*
 * Decrement the device reference count and wait for the device to be
 * removed.  Open file descriptors for the device... */
void *vfio_del_group_dev(struct device *dev)
{
	DEFINE_WAIT_FUNC(wait, woken_wake_function);
	struct vfio_device *device = dev_get_drvdata(dev);
	struct vfio_group *group = device->group;
	void *device_data = device->device_data;
	struct vfio_unbound_dev *unbound;
	unsigned int i = 0;
	bool interrupted = false;

	/*
	 * When the device is removed from the group, the group suddenly
	 * becomes non-viable; the device has a driver (until the unbind
	 * completes), but it's not present in the group.  This is bad news
	 * for any external users that need to re-acquire a group reference
	 * in order to match and release their existing reference.  To
	 * solve this, we track such devices on the unbound_list to bridge
	 * the gap until they're fully unbound.
	 */
	unbound = kzalloc(sizeof(*unbound), GFP_KERNEL);
	if (unbound) {
		unbound->dev = dev;
		mutex_lock(&group->unbound_lock);
		list_add(&unbound->unbound_next, &group->unbound_list);
		mutex_unlock(&group->unbound_lock);
	}
	WARN_ON(!unbound);

	vfio_device_put(device);

	/*
	 * If the device is still present in the group after the above
	 * 'put', then it is in use and we need to request it from the
	 * bus driver.  The driver may in turn need to request the
	 * device from the user.  We send the request on an arbitrary
	 * interval with counter to allow the driver to take escalating
	 * measures to release the device if it has the ability to do so.
	 */
	add_wait_queue(&vfio.release_q, &wait);

	do {
		device = vfio_group_get_device(group, dev);
		if (!device)
			break;

		if (device->ops->request)
			device->ops->request(device_data, i++);

		vfio_device_put(device);

		if (interrupted) {
			wait_woken(&wait, TASK_UNINTERRUPTIBLE, HZ * 10);
		} else {
			wait_woken(&wait, TASK_INTERRUPTIBLE, HZ * 10);
			if (signal_pending(current)) {
				interrupted = true;
				dev_warn(dev,
					 "Device is currently in use, task"
					 " \"%s\" (%d) "
					 "blocked until device is released",
					 current->comm, task_pid_nr(current));
			}
		}

	} while (1);

	remove_wait_queue(&vfio.release_q, &wait);
	/*
	 * In order to support multiple devices per group, devices can be
	 * plucked from the group while other devices in the group are still
	 * in use.  The container persists with this group and those remaining
	 * devices still attached.  If the user creates an isolation violation
	 * by binding this device to another driver while the group is still in
	 * use, that's their fault.  However, in the case of removing the last,
	 * or potentially the only, device in the group there can be no other
	 * in-use devices in the group.  The user has done their due diligence
	 * and we should lay no claims to those devices.  In order to do that,
	 * we need to make sure the group is detached from the container.
	 * Without this stall, we're potentially racing with a user process
	 * that may attempt to immediately bind this device to another driver.
	 */
	if (list_empty(&group->device_list))
		wait_event(group->container_q, !group->container);

	/* Matches the get in vfio_group_create_device() */
	vfio_group_put(group);

	return device_data;
}
EXPORT_SYMBOL_GPL(vfio_del_group_dev);

/**
 * VFIO base fd, /dev/vfio/vfio
 */
static long vfio_ioctl_check_extension(struct vfio_container *container,
				       unsigned long arg)
{
	struct vfio_iommu_driver *driver;
	long ret = 0;

	down_read(&container->group_lock);

	driver = container->iommu_driver;

	switch (arg) {
		/* No base extensions yet */
	default:
		/*
		 * If no driver is set, poll all registered drivers for
		 * extensions and return the first positive result.  If
		 * a driver is already set, further queries will be passed
		 * only to that driver.
		 */
		if (!driver) {
			mutex_lock(&vfio.iommu_drivers_lock);
			list_for_each_entry(driver, &vfio.iommu_drivers_list,
					    vfio_next) {

#ifdef CONFIG_VFIO_NOIOMMU
				if (!list_empty(&container->group_list) &&
				    (container->noiommu !=
				     (driver->ops == &vfio_noiommu_ops)))
					continue;
#endif

				if (!try_module_get(driver->ops->owner))
					continue;

				ret = driver->ops->ioctl(NULL,
							 VFIO_CHECK_EXTENSION,
							 arg);
				module_put(driver->ops->owner);
				if (ret > 0)
					break;
			}
			mutex_unlock(&vfio.iommu_drivers_lock);
		} else
			ret = driver->ops->ioctl(container->iommu_data,
						 VFIO_CHECK_EXTENSION, arg);
	}

	up_read(&container->group_lock);

	return ret;
}

/* hold write lock on container->group_lock */
static int __vfio_container_attach_groups(struct vfio_container *container,
					  struct vfio_iommu_driver *driver,
					  void *data)
{
	struct vfio_group *group;
	int ret = -ENODEV;

	list_for_each_entry(group, &container->group_list, container_next) {
		ret = driver->ops->attach_group(data, group->iommu_group);
		if (ret)
			goto unwind;
	}

	return ret;

unwind:
	list_for_each_entry_continue_reverse(group, &container->group_list,
					     container_next) {
		driver->ops->detach_group(data, group->iommu_group);
	}

	return ret;
}

static long vfio_ioctl_set_iommu(struct vfio_container *container,
				 unsigned long arg)
{
	struct vfio_iommu_driver *driver;
	long ret = -ENODEV;

	down_write(&container->group_lock);

	/*
	 * The container is designed to be an unprivileged interface while
	 * the group can be assigned to specific users.  Therefore, only by
	 * adding a group to a container does the user get the privilege of
	 * enabling the iommu, which may allocate finite resources.  There
	 * is no unset_iommu, but by removing all the groups from a container,
	 * the container is deprivileged and returns to an unset state.
	 */
	if (list_empty(&container->group_list) || container->iommu_driver) {
		up_write(&container->group_lock);
		return -EINVAL;
	}

	mutex_lock(&vfio.iommu_drivers_lock);
	list_for_each_entry(driver, &vfio.iommu_drivers_list, vfio_next) {
		void *data;

#ifdef CONFIG_VFIO_NOIOMMU
		/*
		 * Only noiommu containers can use vfio-noiommu and noiommu
		 * containers can only use vfio-noiommu.
		 */
		if (container->noiommu != (driver->ops == &vfio_noiommu_ops))
			continue;
#endif

		if (!try_module_get(driver->ops->owner))
			continue;

		/*
		 * The arg magic for SET_IOMMU is the same as CHECK_EXTENSION,
		 * so test which iommu driver reported support for this
		 * extension and call open on them.  We also pass them the
		 * magic, allowing a single driver to support multiple
		 * interfaces if they'd like.
		 */
		if (driver->ops->ioctl(NULL, VFIO_CHECK_EXTENSION, arg) <= 0) {
			module_put(driver->ops->owner);
			continue;
		}

		data = driver->ops->open(arg);
		if (IS_ERR(data)) {
			ret = PTR_ERR(data);
			module_put(driver->ops->owner);
			continue;
		}

		ret = __vfio_container_attach_groups(container, driver, data);
		if (ret) {
			driver->ops->release(data);
			module_put(driver->ops->owner);
			continue;
		}

		container->iommu_driver = driver;
		container->iommu_data = data;
		break;
	}

	mutex_unlock(&vfio.iommu_drivers_lock);
	up_write(&container->group_lock);

	return ret;
}

static long vfio_fops_unl_ioctl(struct file *filep,
				unsigned int cmd, unsigned long arg)
{
	struct vfio_container *container = filep->private_data;
	struct vfio_iommu_driver *driver;
	void *data;
	long ret = -EINVAL;

	if (!container)
		return ret;

	switch (cmd) {
	case VFIO_GET_API_VERSION:
		ret = VFIO_API_VERSION;
		break;
	case VFIO_CHECK_EXTENSION:
		ret = vfio_ioctl_check_extension(container, arg);
		break;
	case VFIO_SET_IOMMU:
		ret = vfio_ioctl_set_iommu(container, arg);
		break;
	default:
		driver = container->iommu_driver;
		data = container->iommu_data;

		if (driver) /* passthrough all unrecognized ioctls */
			ret = driver->ops->ioctl(data, cmd, arg);
	}

	return ret;
}

static int vfio_fops_open(struct inode *inode, struct file *filep)
{
	struct vfio_container *container;

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

	INIT_LIST_HEAD(&container->group_list);
	init_rwsem(&container->group_lock);
	kref_init(&container->kref);

	filep->private_data = container;

	return 0;
}

static int vfio_fops_release(struct inode *inode, struct file *filep)
{
	struct vfio_container *container = filep->private_data;
	struct vfio_iommu_driver *driver = container->iommu_driver;

	if (driver && driver->ops->notify)
		driver->ops->notify(container->iommu_data,
				    VFIO_IOMMU_CONTAINER_CLOSE);

	filep->private_data = NULL;

	vfio_container_put(container);

	return 0;
}

/*
 * Once an iommu driver is set, we optionally pass read/write/mmap
 * on to the driver, allowing management interfaces beyond ioctl.
 */
static ssize_t vfio_fops_read(struct file *filep, char __user *buf,
			      size_t count, loff_t *ppos)
{
	struct vfio_container *container = filep->private_data;
	struct vfio_iommu_driver *driver;
	ssize_t ret = -EINVAL;

	driver = container->iommu_driver;
	if (likely(driver && driver->ops->read))
		ret = driver->ops->read(container->iommu_data,
					buf, count, ppos);

	return ret;
}

static ssize_t vfio_fops_write(struct file *filep, const char __user *buf,
			       size_t count, loff_t *ppos)
{
	struct vfio_container *container = filep->private_data;
	struct vfio_iommu_driver *driver;
	ssize_t ret = -EINVAL;

	driver = container->iommu_driver;
	if (likely(driver && driver->ops->write))
		ret = driver->ops->write(container->iommu_data,
					 buf, count, ppos);

	return ret;
}

static int vfio_fops_mmap(struct file *filep, struct vm_area_struct *vma)
{
	struct vfio_container *container = filep->private_data;
	struct vfio_iommu_driver *driver;
	int ret = -EINVAL;

	driver = container->iommu_driver;
	if (likely(driver && driver->ops->mmap))
		ret = driver->ops->mmap(container->iommu_data, vma);

	return ret;
}

static const struct file_operations vfio_fops = {
	.owner		= THIS_MODULE,
	.open		= vfio_fops_open,
	.release	= vfio_fops_release,
	.read		= vfio_fops_read,
	.write		= vfio_fops_write,
	.unlocked_ioctl	= vfio_fops_unl_ioctl,
	.compat_ioctl	= compat_ptr_ioctl,
	.mmap		= vfio_fops_mmap,
};

/**
 * VFIO Group fd, /dev/vfio/$GROUP
 */
static void __vfio_group_unset_container(struct vfio_group *group)
{
	struct vfio_container *container = group->container;
	struct vfio_iommu_driver *driver;

	down_write(&container->group_lock);

	driver = container->iommu_driver;
	if (driver)
		driver->ops->detach_group(container->iommu_data,
					  group->iommu_group);

	group->container = NULL;
	wake_up(&group->container_q);
	list_del(&group->container_next);

	/* Detaching the last group deprivileges a container, remove iommu */
	if (driver && list_empty(&container->group_list)) {
		driver->ops->release(container->iommu_data);
		module_put(driver->ops->owner);
		container->iommu_driver = NULL;
		container->iommu_data = NULL;
	}

	up_write(&container->group_lock);

	vfio_container_put(container);
}

/*
 * 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_unset_container(struct vfio_group *group)
{
	int users = atomic_cmpxchg(&group->container_users, 1, 0);

	if (!users)
		return -EINVAL;
	if (users != 1)
		return -EBUSY;

	__vfio_group_unset_container(group);

	return 0;
}

/*
 * When removing container users, anything that removes the last user
 * implicitly removes the group from the container.  That is, if the
 * group file descriptor is closed, as well as any device file descriptors,
 * the group is free.
 */
static void vfio_group_try_dissolve_container(struct vfio_group *group)
{
	if (0 == atomic_dec_if_positive(&group->container_users))
		__vfio_group_unset_container(group);
}

static int vfio_group_set_container(struct vfio_group *group, int container_fd)
{
	struct fd f;
	struct vfio_container *container;
	struct vfio_iommu_driver *driver;
	int ret = 0;

	if (atomic_read(&group->container_users))
		return -EINVAL;

	if (group->noiommu && !capable(CAP_SYS_RAWIO))
		return -EPERM;

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

	/* Sanity check, is this really our fd? */
	if (f.file->f_op != &vfio_fops) {
		fdput(f);
		return -EINVAL;
	}

	container = f.file->private_data;
	WARN_ON(!container); /* fget ensures we don't race vfio_release */

	down_write(&container->group_lock);

	/* Real groups and fake groups cannot mix */
	if (!list_empty(&container->group_list) &&
	    container->noiommu != group->noiommu) {
		ret = -EPERM;
		goto unlock_out;
	}

	driver = container->iommu_driver;
	if (driver) {
		ret = driver->ops->attach_group(container->iommu_data,
						group->iommu_group);
		if (ret)
			goto unlock_out;
	}

	group->container = container;
	container->noiommu = group->noiommu;
	list_add(&group->container_next, &container->group_list);

	/* Get a reference on the container and mark a user within the group */
	vfio_container_get(container);
	atomic_inc(&group->container_users);

unlock_out:
	up_write(&container->group_lock);
	fdput(f);
	return ret;
}

static bool vfio_group_viable(struct vfio_group *group)
{
	return (iommu_group_for_each_dev(group->iommu_group,
					 group, vfio_dev_viable) == 0);
}

static int vfio_group_add_container_user(struct vfio_group *group)
{
	if (!atomic_inc_not_zero(&group->container_users))
		return -EINVAL;

	if (group->noiommu) {
		atomic_dec(&group->container_users);
		return -EPERM;
	}
	if (!group->container->iommu_driver || !vfio_group_viable(group)) {
		atomic_dec(&group->container_users);
		return -EINVAL;
	}

	return 0;
}

static const struct file_operations vfio_device_fops;

static int vfio_group_get_device_fd(struct vfio_group *group, char *buf)
{
	struct vfio_device *device;
	struct file *filep;
	int ret;

	if (0 == atomic_read(&group->container_users) ||
	    !group->container->iommu_driver || !vfio_group_viable(group))
		return -EINVAL;

	if (group->noiommu && !capable(CAP_SYS_RAWIO))
		return -EPERM;

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

	ret = device->ops->open(device->device_data);
	if (ret) {
		vfio_device_put(device);
		return ret;
	}

	/*
	 * We can't use anon_inode_getfd() because we need to modify
	 * the f_mode flags directly to allow more than just ioctls
	 */
	ret = get_unused_fd_flags(O_CLOEXEC);
	if (ret < 0) {
		device->ops->release(device->device_data);
		vfio_device_put(device);
		return ret;
	}

	filep = anon_inode_getfile("[vfio-device]", &vfio_device_fops,
				   device, O_RDWR);
	if (IS_ERR(filep)) {
		put_unused_fd(ret);
		ret = PTR_ERR(filep);
		device->ops->release(device->device_data);
		vfio_device_put(device);
		return ret;
	}

	/*
	 * 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_LSEEK | FMODE_PREAD | FMODE_PWRITE);

	atomic_inc(&group->container_users);

	fd_install(ret, filep);

	if (group->noiommu)
		dev_warn(device->dev, "vfio-noiommu device opened by user "
			 "(%s:%d)\n", current->comm, task_pid_nr(current));

	return ret;
}

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

	switch (cmd) {
	case VFIO_GROUP_GET_STATUS:
	{
		struct vfio_group_status status;
		unsigned long minsz;

		minsz = offsetofend(struct vfio_group_status, flags);

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

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

		status.flags = 0;

		if (vfio_group_viable(group))
			status.flags |= VFIO_GROUP_FLAGS_VIABLE;

		if (group->container)
			status.flags |= VFIO_GROUP_FLAGS_CONTAINER_SET;

		if (copy_to_user((void __user *)arg, &status, minsz))
			return -EFAULT;

		ret = 0;
		break;
	}
	case VFIO_GROUP_SET_CONTAINER:
	{
		int fd;

		if (get_user(fd, (int __user *)arg))
			return -EFAULT;

		if (fd < 0)
			return -EINVAL;

		ret = vfio_group_set_container(group, fd);
		break;
	}
	case VFIO_GROUP_UNSET_CONTAINER:
		ret = vfio_group_unset_container(group);
		break;
	case VFIO_GROUP_GET_DEVICE_FD:
	{
		char *buf;

		buf = strndup_user((const char __user *)arg, PAGE_SIZE);
		if (IS_ERR(buf))
			return PTR_ERR(buf);

		ret = vfio_group_get_device_fd(group, buf);
		kfree(buf);
		break;
	}
	}

	return ret;
}

static int vfio_group_fops_open(struct inode *inode, struct file *filep)
{
	struct vfio_group *group;
	int opened;

	group = vfio_group_get_from_minor(iminor(inode));
	if (!group)
		return -ENODEV;

	if (group->noiommu && !capable(CAP_SYS_RAWIO)) {
		vfio_group_put(group);
		return -EPERM;
	}

	/* Do we need multiple instances of the group open?  Seems not. */
	opened = atomic_cmpxchg(&group->opened, 0, 1);
	if (opened) {
		vfio_group_put(group);
		return -EBUSY;
	}

	/* Is something still in use from a previous open? */
	if (group->container) {
		atomic_dec(&group->opened);
		vfio_group_put(group);
		return -EBUSY;
	}

	/* Warn if previous user didn't cleanup and re-init to drop them */
	if (WARN_ON(group->notifier.head))
		BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier);

	filep->private_data = group;

	return 0;
}

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

	filep->private_data = NULL;

	vfio_group_try_dissolve_container(group);

	atomic_dec(&group->opened);

	vfio_group_put(group);

	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,
};

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

	device->ops->release(device->device_data);

	vfio_group_try_dissolve_container(device->group);

	vfio_device_put(device);

	return 0;
}

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

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

	return device->ops->ioctl(device->device_data, cmd, arg);
}

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->device_data, 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->device_data, 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->device_data, 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,
};

/**
 * External user API, exported by symbols to be linked dynamically.
 *
 * The protocol includes:
 *  1. do normal VFIO init operation:
 *	- opening a new container;
 *	- attaching group(s) to it;
 *	- setting an IOMMU driver for a container.
 * When IOMMU is set for a container, all groups in it are
 * considered ready to use by an external user.
 *
 * 2. User space passes a group fd to an external user.
 * The external user calls vfio_group_get_external_user()
 * to verify that:
 *	- the group is initialized;
 *	- IOMMU is set for it.
 * If both checks passed, vfio_group_get_external_user()
 * increments the container user counter to prevent
 * the VFIO group from disposal before KVM exits.
 *
 * 3. The external user calls vfio_external_user_iommu_id()
 * to know an IOMMU ID.
 *
 * 4. When the external KVM finishes, it calls
 * vfio_group_put_external_user() to release the VFIO group.
 * This call decrements the container user counter.
 */
struct vfio_group *vfio_group_get_external_user(struct file *filep)
{
	struct vfio_group *group = filep->private_data;
	int ret;

	if (filep->f_op != &vfio_group_fops)
		return ERR_PTR(-EINVAL);

	ret = vfio_group_add_container_user(group);
	if (ret)
		return ERR_PTR(ret);

	vfio_group_get(group);

	return group;
}
EXPORT_SYMBOL_GPL(vfio_group_get_external_user);

/**
 * External user API, exported by symbols to be linked dynamically.
 * The external user passes in a device pointer
 * to verify that:
 *	- A VFIO group is assiciated with the device;
 *	- IOMMU is set for the group.
 * If both checks passed, vfio_group_get_external_user_from_dev()
 * increments the container user counter to prevent the VFIO group
 * from disposal before external user exits and returns the pointer
 * to the VFIO group.
 *
 * When the external user finishes using the VFIO group, it calls
 * vfio_group_put_external_user() to release the VFIO group and
 * decrement the container user counter.
 *
 * @dev [in]	: device
 * Return error PTR or pointer to VFIO group.
 */

struct vfio_group *vfio_group_get_external_user_from_dev(struct device *dev)
{
	struct vfio_group *group;
	int ret;

	group = vfio_group_get_from_dev(dev);
	if (!group)
		return ERR_PTR(-ENODEV);

	ret = vfio_group_add_container_user(group);
	if (ret) {
		vfio_group_put(group);
		return ERR_PTR(ret);
	}

	return group;
}
EXPORT_SYMBOL_GPL(vfio_group_get_external_user_from_dev);

void vfio_group_put_external_user(struct vfio_group *group)
{
	vfio_group_try_dissolve_container(group);
	vfio_group_put(group);
}
EXPORT_SYMBOL_GPL(vfio_group_put_external_user);

bool vfio_external_group_match_file(struct vfio_group *test_group,
				    struct file *filep)
{
	struct vfio_group *group = filep->private_data;

	return (filep->f_op == &vfio_group_fops) && (group == test_group);
}
EXPORT_SYMBOL_GPL(vfio_external_group_match_file);

int vfio_external_user_iommu_id(struct vfio_group *group)
{
	return iommu_group_id(group->iommu_group);
}
EXPORT_SYMBOL_GPL(vfio_external_user_iommu_id);

long vfio_external_check_extension(struct vfio_group *group, unsigned long arg)
{
	return vfio_ioctl_check_extension(group->container, arg);
}
EXPORT_SYMBOL_GPL(vfio_external_check_extension);

/**
 * 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->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 a set of guest PFNs and return their associated host PFNs for local
 * domain only.
 * @dev [in]     : device
 * @user_pfn [in]: array of user/guest PFNs to be pinned.
 * @npage [in]   : count of elements in user_pfn array.  This count should not
 *		   be greater VFIO_PIN_PAGES_MAX_ENTRIES.
 * @prot [in]    : protection flags
 * @phys_pfn[out]: array of host PFNs
 * Return error or number of pages pinned.
 */
int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, int npage,
		   int prot, unsigned long *phys_pfn)
{
	struct vfio_container *container;
	struct vfio_group *group;
	struct vfio_iommu_driver *driver;
	int ret;

	if (!dev || !user_pfn || !phys_pfn || !npage)
		return -EINVAL;

	if (npage > VFIO_PIN_PAGES_MAX_ENTRIES)
		return -E2BIG;

	group = vfio_group_get_from_dev(dev);
	if (!group)
		return -ENODEV;

	if (group->dev_counter > 1) {
		ret = -EINVAL;
		goto err_pin_pages;
	}

	ret = vfio_group_add_container_user(group);
	if (ret)
		goto err_pin_pages;

	container = group->container;
	driver = container->iommu_driver;
	if (likely(driver && driver->ops->pin_pages))
		ret = driver->ops->pin_pages(container->iommu_data,
					     group->iommu_group, user_pfn,
					     npage, prot, phys_pfn);
	else
		ret = -ENOTTY;

	vfio_group_try_dissolve_container(group);

err_pin_pages:
	vfio_group_put(group);
	return ret;
}
EXPORT_SYMBOL(vfio_pin_pages);

/*
 * Unpin set of host PFNs for local domain only.
 * @dev [in]     : device
 * @user_pfn [in]: array of user/guest PFNs to be unpinned. Number of user/guest
 *		   PFNs should not be greater than VFIO_PIN_PAGES_MAX_ENTRIES.
 * @npage [in]   : count of elements in user_pfn array.  This count should not
 *                 be greater than VFIO_PIN_PAGES_MAX_ENTRIES.
 * Return error or number of pages unpinned.
 */
int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn, int npage)
{
	struct vfio_container *container;
	struct vfio_group *group;
	struct vfio_iommu_driver *driver;
	int ret;

	if (!dev || !user_pfn || !npage)
		return -EINVAL;

	if (npage > VFIO_PIN_PAGES_MAX_ENTRIES)
		return -E2BIG;

	group = vfio_group_get_from_dev(dev);
	if (!group)
		return -ENODEV;

	ret = vfio_group_add_container_user(group);
	if (ret)
		goto err_unpin_pages;

	container = group->container;
	driver = container->iommu_driver;
	if (likely(driver && driver->ops->unpin_pages))
		ret = driver->ops->unpin_pages(container->iommu_data, user_pfn,
					       npage);
	else
		ret = -ENOTTY;

	vfio_group_try_dissolve_container(group);

err_unpin_pages:
	vfio_group_put(group);
	return ret;
}
EXPORT_SYMBOL(vfio_unpin_pages);

/*
 * Pin a set of guest IOVA PFNs and return their associated host PFNs for a
 * VFIO group.
 *
 * The caller needs to call vfio_group_get_external_user() or
 * vfio_group_get_external_user_from_dev() prior to calling this interface,
 * so as to prevent the VFIO group from disposal in the middle of the call.
 * But it can keep the reference to the VFIO group for several calls into
 * this interface.
 * After finishing using of the VFIO group, the caller needs to release the
 * VFIO group by calling vfio_group_put_external_user().
 *
 * @group [in]		: VFIO group
 * @user_iova_pfn [in]	: array of user/guest IOVA PFNs to be pinned.
 * @npage [in]		: count of elements in user_iova_pfn array.
 *			  This count should not be greater
 *			  VFIO_PIN_PAGES_MAX_ENTRIES.
 * @prot [in]		: protection flags
 * @phys_pfn [out]	: array of host PFNs
 * Return error or number of pages pinned.
 */
int vfio_group_pin_pages(struct vfio_group *group,
			 unsigned long *user_iova_pfn, int npage,
			 int prot, unsigned long *phys_pfn)
{
	struct vfio_container *container;
	struct vfio_iommu_driver *driver;
	int ret;

	if (!group || !user_iova_pfn || !phys_pfn || !npage)
		return -EINVAL;

	if (group->dev_counter > 1)
		return -EINVAL;

	if (npage > VFIO_PIN_PAGES_MAX_ENTRIES)
		return -E2BIG;

	container = group->container;
	driver = container->iommu_driver;
	if (likely(driver && driver->ops->pin_pages))
		ret = driver->ops->pin_pages(container->iommu_data,
					     group->iommu_group, user_iova_pfn,
					     npage, prot, phys_pfn);
	else
		ret = -ENOTTY;

	return ret;
}
EXPORT_SYMBOL(vfio_group_pin_pages);

/*
 * Unpin a set of guest IOVA PFNs for a VFIO group.
 *
 * The caller needs to call vfio_group_get_external_user() or
 * vfio_group_get_external_user_from_dev() prior to calling this interface,
 * so as to prevent the VFIO group from disposal in the middle of the call.
 * But it can keep the reference to the VFIO group for several calls into
 * this interface.
 * After finishing using of the VFIO group, the caller needs to release the
 * VFIO group by calling vfio_group_put_external_user().
 *
 * @group [in]		: vfio group
 * @user_iova_pfn [in]	: array of user/guest IOVA PFNs to be unpinned.
 * @npage [in]		: count of elements in user_iova_pfn array.
 *			  This count should not be greater than
 *			  VFIO_PIN_PAGES_MAX_ENTRIES.
 * Return error or number of pages unpinned.
 */
int vfio_group_unpin_pages(struct vfio_group *group,
			   unsigned long *user_iova_pfn, int npage)
{
	struct vfio_container *container;
	struct vfio_iommu_driver *driver;
	int ret;

	if (!group || !user_iova_pfn || !npage)
		return -EINVAL;

	if (npage > VFIO_PIN_PAGES_MAX_ENTRIES)
		return -E2BIG;

	container = group->container;
	driver = container->iommu_driver;
	if (likely(driver && driver->ops->unpin_pages))
		ret = driver->ops->unpin_pages(container->iommu_data,
					       user_iova_pfn, npage);
	else
		ret = -ENOTTY;

	return ret;
}
EXPORT_SYMBOL(vfio_group_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.
 *
 * The caller needs to call vfio_group_get_external_user() or
 * vfio_group_get_external_user_from_dev() prior to calling this interface,
 * so as to prevent the VFIO group from disposal in the middle of the call.
 * But it can keep the reference to the VFIO group for several calls into
 * this interface.
 * After finishing using of the VFIO group, the caller needs to release the
 * VFIO group by calling vfio_group_put_external_user().
 *
 * @group [in]		: VFIO group
 * @user_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_group *group, dma_addr_t user_iova,
		void *data, size_t len, bool write)
{
	struct vfio_container *container;
	struct vfio_iommu_driver *driver;
	int ret = 0;

	if (!group || !data || len <= 0)
		return -EINVAL;

	container = group->container;
	driver = container->iommu_driver;

	if (likely(driver && driver->ops->dma_rw))
		ret = driver->ops->dma_rw(container->iommu_data,
					  user_iova, data, len, write);
	else
		ret = -ENOTTY;

	return ret;
}
EXPORT_SYMBOL(vfio_dma_rw);

static int vfio_register_iommu_notifier(struct vfio_group *group,
					unsigned long *events,
					struct notifier_block *nb)
{
	struct vfio_container *container;
	struct vfio_iommu_driver *driver;
	int ret;

	ret = vfio_group_add_container_user(group);
	if (ret)
		return -EINVAL;

	container = group->container;
	driver = container->iommu_driver;
	if (likely(driver && driver->ops->register_notifier))
		ret = driver->ops->register_notifier(container->iommu_data,
						     events, nb);
	else
		ret = -ENOTTY;

	vfio_group_try_dissolve_container(group);

	return ret;
}

static int vfio_unregister_iommu_notifier(struct vfio_group *group,
					  struct notifier_block *nb)
{
	struct vfio_container *container;
	struct vfio_iommu_driver *driver;
	int ret;

	ret = vfio_group_add_container_user(group);
	if (ret)
		return -EINVAL;

	container = group->container;
	driver = container->iommu_driver;
	if (likely(driver && driver->ops->unregister_notifier))
		ret = driver->ops->unregister_notifier(container->iommu_data,
						       nb);
	else
		ret = -ENOTTY;

	vfio_group_try_dissolve_container(group);

	return ret;
}

void vfio_group_set_kvm(struct vfio_group *group, struct kvm *kvm)
{
	group->kvm = kvm;
	blocking_notifier_call_chain(&group->notifier,
				VFIO_GROUP_NOTIFY_SET_KVM, kvm);
}
EXPORT_SYMBOL_GPL(vfio_group_set_kvm);

static int vfio_register_group_notifier(struct vfio_group *group,
					unsigned long *events,
					struct notifier_block *nb)
{
	int ret;
	bool set_kvm = false;

	if (*events & VFIO_GROUP_NOTIFY_SET_KVM)
		set_kvm = true;

	/* clear known events */
	*events &= ~VFIO_GROUP_NOTIFY_SET_KVM;

	/* refuse to continue if still events remaining */
	if (*events)
		return -EINVAL;

	ret = vfio_group_add_container_user(group);
	if (ret)
		return -EINVAL;

	ret = blocking_notifier_chain_register(&group->notifier, nb);

	/*
	 * The attaching of kvm and vfio_group might already happen, so
	 * here we replay once upon registration.
	 */
	if (!ret && set_kvm && group->kvm)
		blocking_notifier_call_chain(&group->notifier,
					VFIO_GROUP_NOTIFY_SET_KVM, group->kvm);

	vfio_group_try_dissolve_container(group);

	return ret;
}

static int vfio_unregister_group_notifier(struct vfio_group *group,
					 struct notifier_block *nb)
{
	int ret;

	ret = vfio_group_add_container_user(group);
	if (ret)
		return -EINVAL;

	ret = blocking_notifier_chain_unregister(&group->notifier, nb);

	vfio_group_try_dissolve_container(group);

	return ret;
}

int vfio_register_notifier(struct device *dev, enum vfio_notify_type type,
			   unsigned long *events, struct notifier_block *nb)
{
	struct vfio_group *group;
	int ret;

	if (!dev || !nb || !events || (*events == 0))
		return -EINVAL;

	group = vfio_group_get_from_dev(dev);
	if (!group)
		return -ENODEV;

	switch (type) {
	case VFIO_IOMMU_NOTIFY:
		ret = vfio_register_iommu_notifier(group, events, nb);
		break;
	case VFIO_GROUP_NOTIFY:
		ret = vfio_register_group_notifier(group, events, nb);
		break;
	default:
		ret = -EINVAL;
	}

	vfio_group_put(group);
	return ret;
}
EXPORT_SYMBOL(vfio_register_notifier);

int vfio_unregister_notifier(struct device *dev, enum vfio_notify_type type,
			     struct notifier_block *nb)
{
	struct vfio_group *group;
	int ret;

	if (!dev || !nb)
		return -EINVAL;

	group = vfio_group_get_from_dev(dev);
	if (!group)
		return -ENODEV;

	switch (type) {
	case VFIO_IOMMU_NOTIFY:
		ret = vfio_unregister_iommu_notifier(group, nb);
		break;
	case VFIO_GROUP_NOTIFY:
		ret = vfio_unregister_group_notifier(group, nb);
		break;
	default:
		ret = -EINVAL;
	}

	vfio_group_put(group);
	return ret;
}
EXPORT_SYMBOL(vfio_unregister_notifier);

struct iommu_domain *vfio_group_iommu_domain(struct vfio_group *group)
{
	struct vfio_container *container;
	struct vfio_iommu_driver *driver;

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

	container = group->container;
	driver = container->iommu_driver;
	if (likely(driver && driver->ops->group_iommu_domain))
		return driver->ops->group_iommu_domain(container->iommu_data,
						       group->iommu_group);

	return ERR_PTR(-ENOTTY);
}
EXPORT_SYMBOL_GPL(vfio_group_iommu_domain);

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

static struct miscdevice vfio_dev = {
	.minor = VFIO_MINOR,
	.name = "vfio",
	.fops = &vfio_fops,
	.nodename = "vfio/vfio",
	.mode = S_IRUGO | S_IWUGO,
};

static int __init vfio_init(void)
{
	int ret;

	idr_init(&vfio.group_idr);
	mutex_init(&vfio.group_lock);
	mutex_init(&vfio.iommu_drivers_lock);
	INIT_LIST_HEAD(&vfio.group_list);
	INIT_LIST_HEAD(&vfio.iommu_drivers_list);
	init_waitqueue_head(&vfio.release_q);

	ret = misc_register(&vfio_dev);
	if (ret) {
		pr_err("vfio: misc device register failed\n");
		return ret;
	}

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

	vfio.class->devnode = vfio_devnode;

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

	cdev_init(&vfio.group_cdev, &vfio_group_fops);
	ret = cdev_add(&vfio.group_cdev, vfio.group_devt, MINORMASK + 1);
	if (ret)
		goto err_cdev_add;

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

#ifdef CONFIG_VFIO_NOIOMMU
	vfio_register_iommu_driver(&vfio_noiommu_ops);
#endif
	return 0;

err_cdev_add:
	unregister_chrdev_region(vfio.group_devt, MINORMASK + 1);
err_alloc_chrdev:
	class_destroy(vfio.class);
	vfio.class = NULL;
err_class:
	misc_deregister(&vfio_dev);
	return ret;
}

static void __exit vfio_cleanup(void)
{
	WARN_ON(!list_empty(&vfio.group_list));

#ifdef CONFIG_VFIO_NOIOMMU
	vfio_unregister_iommu_driver(&vfio_noiommu_ops);
#endif
	idr_destroy(&vfio.group_idr);
	cdev_del(&vfio.group_cdev);
	unregister_chrdev_region(vfio.group_devt, MINORMASK + 1);
	class_destroy(vfio.class);
	vfio.class = NULL;
	misc_deregister(&vfio_dev);
}

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_ALIAS_MISCDEV(VFIO_MINOR);
MODULE_ALIAS("devname:vfio/vfio");
MODULE_SOFTDEP("post: vfio_iommu_type1 vfio_iommu_spapr_tce");