summaryrefslogtreecommitdiff
path: root/drivers/vhost/vhost.c
blob: 266354390c8fae0490ef9ee24919e3ec72f1cb2a (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
/* Copyright (C) 2009 Red Hat, Inc.
 * Copyright (C) 2006 Rusty Russell IBM Corporation
 *
 * Author: Michael S. Tsirkin <mst@redhat.com>
 *
 * Inspiration, some code, and most witty comments come from
 * Documentation/virtual/lguest/lguest.c, by Rusty Russell
 *
 * This work is licensed under the terms of the GNU GPL, version 2.
 *
 * Generic code for virtio server in host kernel.
 */

#include <linux/eventfd.h>
#include <linux/vhost.h>
#include <linux/uio.h>
#include <linux/mm.h>
#include <linux/mmu_context.h>
#include <linux/miscdevice.h>
#include <linux/mutex.h>
#include <linux/poll.h>
#include <linux/file.h>
#include <linux/highmem.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/kthread.h>
#include <linux/cgroup.h>
#include <linux/module.h>
#include <linux/sort.h>
#include <linux/interval_tree_generic.h>

#include "vhost.h"

static ushort max_mem_regions = 64;
module_param(max_mem_regions, ushort, 0444);
MODULE_PARM_DESC(max_mem_regions,
	"Maximum number of memory regions in memory map. (default: 64)");
static int max_iotlb_entries = 2048;
module_param(max_iotlb_entries, int, 0444);
MODULE_PARM_DESC(max_iotlb_entries,
	"Maximum number of iotlb entries. (default: 2048)");

enum {
	VHOST_MEMORY_F_LOG = 0x1,
};

#define vhost_used_event(vq) ((__virtio16 __user *)&vq->avail->ring[vq->num])
#define vhost_avail_event(vq) ((__virtio16 __user *)&vq->used->ring[vq->num])

INTERVAL_TREE_DEFINE(struct vhost_umem_node,
		     rb, __u64, __subtree_last,
		     START, LAST, , vhost_umem_interval_tree);

#ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY
static void vhost_disable_cross_endian(struct vhost_virtqueue *vq)
{
	vq->user_be = !virtio_legacy_is_little_endian();
}

static void vhost_enable_cross_endian_big(struct vhost_virtqueue *vq)
{
	vq->user_be = true;
}

static void vhost_enable_cross_endian_little(struct vhost_virtqueue *vq)
{
	vq->user_be = false;
}

static long vhost_set_vring_endian(struct vhost_virtqueue *vq, int __user *argp)
{
	struct vhost_vring_state s;

	if (vq->private_data)
		return -EBUSY;

	if (copy_from_user(&s, argp, sizeof(s)))
		return -EFAULT;

	if (s.num != VHOST_VRING_LITTLE_ENDIAN &&
	    s.num != VHOST_VRING_BIG_ENDIAN)
		return -EINVAL;

	if (s.num == VHOST_VRING_BIG_ENDIAN)
		vhost_enable_cross_endian_big(vq);
	else
		vhost_enable_cross_endian_little(vq);

	return 0;
}

static long vhost_get_vring_endian(struct vhost_virtqueue *vq, u32 idx,
				   int __user *argp)
{
	struct vhost_vring_state s = {
		.index = idx,
		.num = vq->user_be
	};

	if (copy_to_user(argp, &s, sizeof(s)))
		return -EFAULT;

	return 0;
}

static void vhost_init_is_le(struct vhost_virtqueue *vq)
{
	/* Note for legacy virtio: user_be is initialized at reset time
	 * according to the host endianness. If userspace does not set an
	 * explicit endianness, the default behavior is native endian, as
	 * expected by legacy virtio.
	 */
	vq->is_le = vhost_has_feature(vq, VIRTIO_F_VERSION_1) || !vq->user_be;
}
#else
static void vhost_disable_cross_endian(struct vhost_virtqueue *vq)
{
}

static long vhost_set_vring_endian(struct vhost_virtqueue *vq, int __user *argp)
{
	return -ENOIOCTLCMD;
}

static long vhost_get_vring_endian(struct vhost_virtqueue *vq, u32 idx,
				   int __user *argp)
{
	return -ENOIOCTLCMD;
}

static void vhost_init_is_le(struct vhost_virtqueue *vq)
{
	if (vhost_has_feature(vq, VIRTIO_F_VERSION_1))
		vq->is_le = true;
}
#endif /* CONFIG_VHOST_CROSS_ENDIAN_LEGACY */

static void vhost_reset_is_le(struct vhost_virtqueue *vq)
{
	vq->is_le = virtio_legacy_is_little_endian();
}

struct vhost_flush_struct {
	struct vhost_work work;
	struct completion wait_event;
};

static void vhost_flush_work(struct vhost_work *work)
{
	struct vhost_flush_struct *s;

	s = container_of(work, struct vhost_flush_struct, work);
	complete(&s->wait_event);
}

static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
			    poll_table *pt)
{
	struct vhost_poll *poll;

	poll = container_of(pt, struct vhost_poll, table);
	poll->wqh = wqh;
	add_wait_queue(wqh, &poll->wait);
}

static int vhost_poll_wakeup(wait_queue_t *wait, unsigned mode, int sync,
			     void *key)
{
	struct vhost_poll *poll = container_of(wait, struct vhost_poll, wait);

	if (!((unsigned long)key & poll->mask))
		return 0;

	vhost_poll_queue(poll);
	return 0;
}

void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn)
{
	clear_bit(VHOST_WORK_QUEUED, &work->flags);
	work->fn = fn;
	init_waitqueue_head(&work->done);
}
EXPORT_SYMBOL_GPL(vhost_work_init);

/* Init poll structure */
void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn,
		     unsigned long mask, struct vhost_dev *dev)
{
	init_waitqueue_func_entry(&poll->wait, vhost_poll_wakeup);
	init_poll_funcptr(&poll->table, vhost_poll_func);
	poll->mask = mask;
	poll->dev = dev;
	poll->wqh = NULL;

	vhost_work_init(&poll->work, fn);
}
EXPORT_SYMBOL_GPL(vhost_poll_init);

/* Start polling a file. We add ourselves to file's wait queue. The caller must
 * keep a reference to a file until after vhost_poll_stop is called. */
int vhost_poll_start(struct vhost_poll *poll, struct file *file)
{
	unsigned long mask;
	int ret = 0;

	if (poll->wqh)
		return 0;

	mask = file->f_op->poll(file, &poll->table);
	if (mask)
		vhost_poll_wakeup(&poll->wait, 0, 0, (void *)mask);
	if (mask & POLLERR) {
		if (poll->wqh)
			remove_wait_queue(poll->wqh, &poll->wait);
		ret = -EINVAL;
	}

	return ret;
}
EXPORT_SYMBOL_GPL(vhost_poll_start);

/* Stop polling a file. After this function returns, it becomes safe to drop the
 * file reference. You must also flush afterwards. */
void vhost_poll_stop(struct vhost_poll *poll)
{
	if (poll->wqh) {
		remove_wait_queue(poll->wqh, &poll->wait);
		poll->wqh = NULL;
	}
}
EXPORT_SYMBOL_GPL(vhost_poll_stop);

void vhost_work_flush(struct vhost_dev *dev, struct vhost_work *work)
{
	struct vhost_flush_struct flush;

	if (dev->worker) {
		init_completion(&flush.wait_event);
		vhost_work_init(&flush.work, vhost_flush_work);

		vhost_work_queue(dev, &flush.work);
		wait_for_completion(&flush.wait_event);
	}
}
EXPORT_SYMBOL_GPL(vhost_work_flush);

/* Flush any work that has been scheduled. When calling this, don't hold any
 * locks that are also used by the callback. */
void vhost_poll_flush(struct vhost_poll *poll)
{
	vhost_work_flush(poll->dev, &poll->work);
}
EXPORT_SYMBOL_GPL(vhost_poll_flush);

void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work)
{
	if (!dev->worker)
		return;

	if (!test_and_set_bit(VHOST_WORK_QUEUED, &work->flags)) {
		/* We can only add the work to the list after we're
		 * sure it was not in the list.
		 * test_and_set_bit() implies a memory barrier.
		 */
		llist_add(&work->node, &dev->work_list);
		wake_up_process(dev->worker);
	}
}
EXPORT_SYMBOL_GPL(vhost_work_queue);

/* A lockless hint for busy polling code to exit the loop */
bool vhost_has_work(struct vhost_dev *dev)
{
	return !llist_empty(&dev->work_list);
}
EXPORT_SYMBOL_GPL(vhost_has_work);

void vhost_poll_queue(struct vhost_poll *poll)
{
	vhost_work_queue(poll->dev, &poll->work);
}
EXPORT_SYMBOL_GPL(vhost_poll_queue);

static void vhost_vq_reset(struct vhost_dev *dev,
			   struct vhost_virtqueue *vq)
{
	vq->num = 1;
	vq->desc = NULL;
	vq->avail = NULL;
	vq->used = NULL;
	vq->last_avail_idx = 0;
	vq->avail_idx = 0;
	vq->last_used_idx = 0;
	vq->signalled_used = 0;
	vq->signalled_used_valid = false;
	vq->used_flags = 0;
	vq->log_used = false;
	vq->log_addr = -1ull;
	vq->private_data = NULL;
	vq->acked_features = 0;
	vq->log_base = NULL;
	vq->error_ctx = NULL;
	vq->error = NULL;
	vq->kick = NULL;
	vq->call_ctx = NULL;
	vq->call = NULL;
	vq->log_ctx = NULL;
	vhost_reset_is_le(vq);
	vhost_disable_cross_endian(vq);
	vq->busyloop_timeout = 0;
	vq->umem = NULL;
	vq->iotlb = NULL;
}

static int vhost_worker(void *data)
{
	struct vhost_dev *dev = data;
	struct vhost_work *work, *work_next;
	struct llist_node *node;
	mm_segment_t oldfs = get_fs();

	set_fs(USER_DS);
	use_mm(dev->mm);

	for (;;) {
		/* mb paired w/ kthread_stop */
		set_current_state(TASK_INTERRUPTIBLE);

		if (kthread_should_stop()) {
			__set_current_state(TASK_RUNNING);
			break;
		}

		node = llist_del_all(&dev->work_list);
		if (!node)
			schedule();

		node = llist_reverse_order(node);
		/* make sure flag is seen after deletion */
		smp_wmb();
		llist_for_each_entry_safe(work, work_next, node, node) {
			clear_bit(VHOST_WORK_QUEUED, &work->flags);
			__set_current_state(TASK_RUNNING);
			work->fn(work);
			if (need_resched())
				schedule();
		}
	}
	unuse_mm(dev->mm);
	set_fs(oldfs);
	return 0;
}

static void vhost_vq_free_iovecs(struct vhost_virtqueue *vq)
{
	kfree(vq->indirect);
	vq->indirect = NULL;
	kfree(vq->log);
	vq->log = NULL;
	kfree(vq->heads);
	vq->heads = NULL;
}

/* Helper to allocate iovec buffers for all vqs. */
static long vhost_dev_alloc_iovecs(struct vhost_dev *dev)
{
	struct vhost_virtqueue *vq;
	int i;

	for (i = 0; i < dev->nvqs; ++i) {
		vq = dev->vqs[i];
		vq->indirect = kmalloc(sizeof *vq->indirect * UIO_MAXIOV,
				       GFP_KERNEL);
		vq->log = kmalloc(sizeof *vq->log * UIO_MAXIOV, GFP_KERNEL);
		vq->heads = kmalloc(sizeof *vq->heads * UIO_MAXIOV, GFP_KERNEL);
		if (!vq->indirect || !vq->log || !vq->heads)
			goto err_nomem;
	}
	return 0;

err_nomem:
	for (; i >= 0; --i)
		vhost_vq_free_iovecs(dev->vqs[i]);
	return -ENOMEM;
}

static void vhost_dev_free_iovecs(struct vhost_dev *dev)
{
	int i;

	for (i = 0; i < dev->nvqs; ++i)
		vhost_vq_free_iovecs(dev->vqs[i]);
}

void vhost_dev_init(struct vhost_dev *dev,
		    struct vhost_virtqueue **vqs, int nvqs)
{
	struct vhost_virtqueue *vq;
	int i;

	dev->vqs = vqs;
	dev->nvqs = nvqs;
	mutex_init(&dev->mutex);
	dev->log_ctx = NULL;
	dev->log_file = NULL;
	dev->umem = NULL;
	dev->iotlb = NULL;
	dev->mm = NULL;
	dev->worker = NULL;
	init_llist_head(&dev->work_list);
	init_waitqueue_head(&dev->wait);
	INIT_LIST_HEAD(&dev->read_list);
	INIT_LIST_HEAD(&dev->pending_list);
	spin_lock_init(&dev->iotlb_lock);


	for (i = 0; i < dev->nvqs; ++i) {
		vq = dev->vqs[i];
		vq->log = NULL;
		vq->indirect = NULL;
		vq->heads = NULL;
		vq->dev = dev;
		mutex_init(&vq->mutex);
		vhost_vq_reset(dev, vq);
		if (vq->handle_kick)
			vhost_poll_init(&vq->poll, vq->handle_kick,
					POLLIN, dev);
	}
}
EXPORT_SYMBOL_GPL(vhost_dev_init);

/* Caller should have device mutex */
long vhost_dev_check_owner(struct vhost_dev *dev)
{
	/* Are you the owner? If not, I don't think you mean to do that */
	return dev->mm == current->mm ? 0 : -EPERM;
}
EXPORT_SYMBOL_GPL(vhost_dev_check_owner);

struct vhost_attach_cgroups_struct {
	struct vhost_work work;
	struct task_struct *owner;
	int ret;
};

static void vhost_attach_cgroups_work(struct vhost_work *work)
{
	struct vhost_attach_cgroups_struct *s;

	s = container_of(work, struct vhost_attach_cgroups_struct, work);
	s->ret = cgroup_attach_task_all(s->owner, current);
}

static int vhost_attach_cgroups(struct vhost_dev *dev)
{
	struct vhost_attach_cgroups_struct attach;

	attach.owner = current;
	vhost_work_init(&attach.work, vhost_attach_cgroups_work);
	vhost_work_queue(dev, &attach.work);
	vhost_work_flush(dev, &attach.work);
	return attach.ret;
}

/* Caller should have device mutex */
bool vhost_dev_has_owner(struct vhost_dev *dev)
{
	return dev->mm;
}
EXPORT_SYMBOL_GPL(vhost_dev_has_owner);

/* Caller should have device mutex */
long vhost_dev_set_owner(struct vhost_dev *dev)
{
	struct task_struct *worker;
	int err;

	/* Is there an owner already? */
	if (vhost_dev_has_owner(dev)) {
		err = -EBUSY;
		goto err_mm;
	}

	/* No owner, become one */
	dev->mm = get_task_mm(current);
	worker = kthread_create(vhost_worker, dev, "vhost-%d", current->pid);
	if (IS_ERR(worker)) {
		err = PTR_ERR(worker);
		goto err_worker;
	}

	dev->worker = worker;
	wake_up_process(worker);	/* avoid contributing to loadavg */

	err = vhost_attach_cgroups(dev);
	if (err)
		goto err_cgroup;

	err = vhost_dev_alloc_iovecs(dev);
	if (err)
		goto err_cgroup;

	return 0;
err_cgroup:
	kthread_stop(worker);
	dev->worker = NULL;
err_worker:
	if (dev->mm)
		mmput(dev->mm);
	dev->mm = NULL;
err_mm:
	return err;
}
EXPORT_SYMBOL_GPL(vhost_dev_set_owner);

static void *vhost_kvzalloc(unsigned long size)
{
	void *n = kzalloc(size, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);

	if (!n)
		n = vzalloc(size);
	return n;
}

struct vhost_umem *vhost_dev_reset_owner_prepare(void)
{
	return vhost_kvzalloc(sizeof(struct vhost_umem));
}
EXPORT_SYMBOL_GPL(vhost_dev_reset_owner_prepare);

/* Caller should have device mutex */
void vhost_dev_reset_owner(struct vhost_dev *dev, struct vhost_umem *umem)
{
	int i;

	vhost_dev_cleanup(dev, true);

	/* Restore memory to default empty mapping. */
	INIT_LIST_HEAD(&umem->umem_list);
	dev->umem = umem;
	/* We don't need VQ locks below since vhost_dev_cleanup makes sure
	 * VQs aren't running.
	 */
	for (i = 0; i < dev->nvqs; ++i)
		dev->vqs[i]->umem = umem;
}
EXPORT_SYMBOL_GPL(vhost_dev_reset_owner);

void vhost_dev_stop(struct vhost_dev *dev)
{
	int i;

	for (i = 0; i < dev->nvqs; ++i) {
		if (dev->vqs[i]->kick && dev->vqs[i]->handle_kick) {
			vhost_poll_stop(&dev->vqs[i]->poll);
			vhost_poll_flush(&dev->vqs[i]->poll);
		}
	}
}
EXPORT_SYMBOL_GPL(vhost_dev_stop);

static void vhost_umem_free(struct vhost_umem *umem,
			    struct vhost_umem_node *node)
{
	vhost_umem_interval_tree_remove(node, &umem->umem_tree);
	list_del(&node->link);
	kfree(node);
	umem->numem--;
}

static void vhost_umem_clean(struct vhost_umem *umem)
{
	struct vhost_umem_node *node, *tmp;

	if (!umem)
		return;

	list_for_each_entry_safe(node, tmp, &umem->umem_list, link)
		vhost_umem_free(umem, node);

	kvfree(umem);
}

static void vhost_clear_msg(struct vhost_dev *dev)
{
	struct vhost_msg_node *node, *n;

	spin_lock(&dev->iotlb_lock);

	list_for_each_entry_safe(node, n, &dev->read_list, node) {
		list_del(&node->node);
		kfree(node);
	}

	list_for_each_entry_safe(node, n, &dev->pending_list, node) {
		list_del(&node->node);
		kfree(node);
	}

	spin_unlock(&dev->iotlb_lock);
}

/* Caller should have device mutex if and only if locked is set */
void vhost_dev_cleanup(struct vhost_dev *dev, bool locked)
{
	int i;

	for (i = 0; i < dev->nvqs; ++i) {
		if (dev->vqs[i]->error_ctx)
			eventfd_ctx_put(dev->vqs[i]->error_ctx);
		if (dev->vqs[i]->error)
			fput(dev->vqs[i]->error);
		if (dev->vqs[i]->kick)
			fput(dev->vqs[i]->kick);
		if (dev->vqs[i]->call_ctx)
			eventfd_ctx_put(dev->vqs[i]->call_ctx);
		if (dev->vqs[i]->call)
			fput(dev->vqs[i]->call);
		vhost_vq_reset(dev, dev->vqs[i]);
	}
	vhost_dev_free_iovecs(dev);
	if (dev->log_ctx)
		eventfd_ctx_put(dev->log_ctx);
	dev->log_ctx = NULL;
	if (dev->log_file)
		fput(dev->log_file);
	dev->log_file = NULL;
	/* No one will access memory at this point */
	vhost_umem_clean(dev->umem);
	dev->umem = NULL;
	vhost_umem_clean(dev->iotlb);
	dev->iotlb = NULL;
	vhost_clear_msg(dev);
	wake_up_interruptible_poll(&dev->wait, POLLIN | POLLRDNORM);
	WARN_ON(!llist_empty(&dev->work_list));
	if (dev->worker) {
		kthread_stop(dev->worker);
		dev->worker = NULL;
	}
	if (dev->mm)
		mmput(dev->mm);
	dev->mm = NULL;
}
EXPORT_SYMBOL_GPL(vhost_dev_cleanup);

static int log_access_ok(void __user *log_base, u64 addr, unsigned long sz)
{
	u64 a = addr / VHOST_PAGE_SIZE / 8;

	/* Make sure 64 bit math will not overflow. */
	if (a > ULONG_MAX - (unsigned long)log_base ||
	    a + (unsigned long)log_base > ULONG_MAX)
		return 0;

	return access_ok(VERIFY_WRITE, log_base + a,
			 (sz + VHOST_PAGE_SIZE * 8 - 1) / VHOST_PAGE_SIZE / 8);
}

static bool vhost_overflow(u64 uaddr, u64 size)
{
	/* Make sure 64 bit math will not overflow. */
	return uaddr > ULONG_MAX || size > ULONG_MAX || uaddr > ULONG_MAX - size;
}

/* Caller should have vq mutex and device mutex. */
static int vq_memory_access_ok(void __user *log_base, struct vhost_umem *umem,
			       int log_all)
{
	struct vhost_umem_node *node;

	if (!umem)
		return 0;

	list_for_each_entry(node, &umem->umem_list, link) {
		unsigned long a = node->userspace_addr;

		if (vhost_overflow(node->userspace_addr, node->size))
			return 0;


		if (!access_ok(VERIFY_WRITE, (void __user *)a,
				    node->size))
			return 0;
		else if (log_all && !log_access_ok(log_base,
						   node->start,
						   node->size))
			return 0;
	}
	return 1;
}

/* Can we switch to this memory table? */
/* Caller should have device mutex but not vq mutex */
static int memory_access_ok(struct vhost_dev *d, struct vhost_umem *umem,
			    int log_all)
{
	int i;

	for (i = 0; i < d->nvqs; ++i) {
		int ok;
		bool log;

		mutex_lock(&d->vqs[i]->mutex);
		log = log_all || vhost_has_feature(d->vqs[i], VHOST_F_LOG_ALL);
		/* If ring is inactive, will check when it's enabled. */
		if (d->vqs[i]->private_data)
			ok = vq_memory_access_ok(d->vqs[i]->log_base,
						 umem, log);
		else
			ok = 1;
		mutex_unlock(&d->vqs[i]->mutex);
		if (!ok)
			return 0;
	}
	return 1;
}

static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len,
			  struct iovec iov[], int iov_size, int access);

static int vhost_copy_to_user(struct vhost_virtqueue *vq, void *to,
			      const void *from, unsigned size)
{
	int ret;

	if (!vq->iotlb)
		return __copy_to_user(to, from, size);
	else {
		/* This function should be called after iotlb
		 * prefetch, which means we're sure that all vq
		 * could be access through iotlb. So -EAGAIN should
		 * not happen in this case.
		 */
		/* TODO: more fast path */
		struct iov_iter t;
		ret = translate_desc(vq, (u64)(uintptr_t)to, size, vq->iotlb_iov,
				     ARRAY_SIZE(vq->iotlb_iov),
				     VHOST_ACCESS_WO);
		if (ret < 0)
			goto out;
		iov_iter_init(&t, WRITE, vq->iotlb_iov, ret, size);
		ret = copy_to_iter(from, size, &t);
		if (ret == size)
			ret = 0;
	}
out:
	return ret;
}

static int vhost_copy_from_user(struct vhost_virtqueue *vq, void *to,
				void *from, unsigned size)
{
	int ret;

	if (!vq->iotlb)
		return __copy_from_user(to, from, size);
	else {
		/* This function should be called after iotlb
		 * prefetch, which means we're sure that vq
		 * could be access through iotlb. So -EAGAIN should
		 * not happen in this case.
		 */
		/* TODO: more fast path */
		struct iov_iter f;
		ret = translate_desc(vq, (u64)(uintptr_t)from, size, vq->iotlb_iov,
				     ARRAY_SIZE(vq->iotlb_iov),
				     VHOST_ACCESS_RO);
		if (ret < 0) {
			vq_err(vq, "IOTLB translation failure: uaddr "
			       "%p size 0x%llx\n", from,
			       (unsigned long long) size);
			goto out;
		}
		iov_iter_init(&f, READ, vq->iotlb_iov, ret, size);
		ret = copy_from_iter(to, size, &f);
		if (ret == size)
			ret = 0;
	}

out:
	return ret;
}

static void __user *__vhost_get_user(struct vhost_virtqueue *vq,
				     void *addr, unsigned size)
{
	int ret;

	/* This function should be called after iotlb
	 * prefetch, which means we're sure that vq
	 * could be access through iotlb. So -EAGAIN should
	 * not happen in this case.
	 */
	/* TODO: more fast path */
	ret = translate_desc(vq, (u64)(uintptr_t)addr, size, vq->iotlb_iov,
			     ARRAY_SIZE(vq->iotlb_iov),
			     VHOST_ACCESS_RO);
	if (ret < 0) {
		vq_err(vq, "IOTLB translation failure: uaddr "
			"%p size 0x%llx\n", addr,
			(unsigned long long) size);
		return NULL;
	}

	if (ret != 1 || vq->iotlb_iov[0].iov_len != size) {
		vq_err(vq, "Non atomic userspace memory access: uaddr "
			"%p size 0x%llx\n", addr,
			(unsigned long long) size);
		return NULL;
	}

	return vq->iotlb_iov[0].iov_base;
}

#define vhost_put_user(vq, x, ptr) \
({ \
	int ret = -EFAULT; \
	if (!vq->iotlb) { \
		ret = __put_user(x, ptr); \
	} else { \
		__typeof__(ptr) to = \
			(__typeof__(ptr)) __vhost_get_user(vq, ptr, sizeof(*ptr)); \
		if (to != NULL) \
			ret = __put_user(x, to); \
		else \
			ret = -EFAULT;	\
	} \
	ret; \
})

#define vhost_get_user(vq, x, ptr) \
({ \
	int ret; \
	if (!vq->iotlb) { \
		ret = __get_user(x, ptr); \
	} else { \
		__typeof__(ptr) from = \
			(__typeof__(ptr)) __vhost_get_user(vq, ptr, sizeof(*ptr)); \
		if (from != NULL) \
			ret = __get_user(x, from); \
		else \
			ret = -EFAULT; \
	} \
	ret; \
})

static void vhost_dev_lock_vqs(struct vhost_dev *d)
{
	int i = 0;
	for (i = 0; i < d->nvqs; ++i)
		mutex_lock(&d->vqs[i]->mutex);
}

static void vhost_dev_unlock_vqs(struct vhost_dev *d)
{
	int i = 0;
	for (i = 0; i < d->nvqs; ++i)
		mutex_unlock(&d->vqs[i]->mutex);
}

static int vhost_new_umem_range(struct vhost_umem *umem,
				u64 start, u64 size, u64 end,
				u64 userspace_addr, int perm)
{
	struct vhost_umem_node *tmp, *node = kmalloc(sizeof(*node), GFP_ATOMIC);

	if (!node)
		return -ENOMEM;

	if (umem->numem == max_iotlb_entries) {
		tmp = list_first_entry(&umem->umem_list, typeof(*tmp), link);
		vhost_umem_free(umem, tmp);
	}

	node->start = start;
	node->size = size;
	node->last = end;
	node->userspace_addr = userspace_addr;
	node->perm = perm;
	INIT_LIST_HEAD(&node->link);
	list_add_tail(&node->link, &umem->umem_list);
	vhost_umem_interval_tree_insert(node, &umem->umem_tree);
	umem->numem++;

	return 0;
}

static void vhost_del_umem_range(struct vhost_umem *umem,
				 u64 start, u64 end)
{
	struct vhost_umem_node *node;

	while ((node = vhost_umem_interval_tree_iter_first(&umem->umem_tree,
							   start, end)))
		vhost_umem_free(umem, node);
}

static void vhost_iotlb_notify_vq(struct vhost_dev *d,
				  struct vhost_iotlb_msg *msg)
{
	struct vhost_msg_node *node, *n;

	spin_lock(&d->iotlb_lock);

	list_for_each_entry_safe(node, n, &d->pending_list, node) {
		struct vhost_iotlb_msg *vq_msg = &node->msg.iotlb;
		if (msg->iova <= vq_msg->iova &&
		    msg->iova + msg->size - 1 > vq_msg->iova &&
		    vq_msg->type == VHOST_IOTLB_MISS) {
			vhost_poll_queue(&node->vq->poll);
			list_del(&node->node);
			kfree(node);
		}
	}

	spin_unlock(&d->iotlb_lock);
}

static int umem_access_ok(u64 uaddr, u64 size, int access)
{
	unsigned long a = uaddr;

	/* Make sure 64 bit math will not overflow. */
	if (vhost_overflow(uaddr, size))
		return -EFAULT;

	if ((access & VHOST_ACCESS_RO) &&
	    !access_ok(VERIFY_READ, (void __user *)a, size))
		return -EFAULT;
	if ((access & VHOST_ACCESS_WO) &&
	    !access_ok(VERIFY_WRITE, (void __user *)a, size))
		return -EFAULT;
	return 0;
}

int vhost_process_iotlb_msg(struct vhost_dev *dev,
			    struct vhost_iotlb_msg *msg)
{
	int ret = 0;

	vhost_dev_lock_vqs(dev);
	switch (msg->type) {
	case VHOST_IOTLB_UPDATE:
		if (!dev->iotlb) {
			ret = -EFAULT;
			break;
		}
		if (umem_access_ok(msg->uaddr, msg->size, msg->perm)) {
			ret = -EFAULT;
			break;
		}
		if (vhost_new_umem_range(dev->iotlb, msg->iova, msg->size,
					 msg->iova + msg->size - 1,
					 msg->uaddr, msg->perm)) {
			ret = -ENOMEM;
			break;
		}
		vhost_iotlb_notify_vq(dev, msg);
		break;
	case VHOST_IOTLB_INVALIDATE:
		vhost_del_umem_range(dev->iotlb, msg->iova,
				     msg->iova + msg->size - 1);
		break;
	default:
		ret = -EINVAL;
		break;
	}

	vhost_dev_unlock_vqs(dev);
	return ret;
}
ssize_t vhost_chr_write_iter(struct vhost_dev *dev,
			     struct iov_iter *from)
{
	struct vhost_msg_node node;
	unsigned size = sizeof(struct vhost_msg);
	size_t ret;
	int err;

	if (iov_iter_count(from) < size)
		return 0;
	ret = copy_from_iter(&node.msg, size, from);
	if (ret != size)
		goto done;

	switch (node.msg.type) {
	case VHOST_IOTLB_MSG:
		err = vhost_process_iotlb_msg(dev, &node.msg.iotlb);
		if (err)
			ret = err;
		break;
	default:
		ret = -EINVAL;
		break;
	}

done:
	return ret;
}
EXPORT_SYMBOL(vhost_chr_write_iter);

unsigned int vhost_chr_poll(struct file *file, struct vhost_dev *dev,
			    poll_table *wait)
{
	unsigned int mask = 0;

	poll_wait(file, &dev->wait, wait);

	if (!list_empty(&dev->read_list))
		mask |= POLLIN | POLLRDNORM;

	return mask;
}
EXPORT_SYMBOL(vhost_chr_poll);

ssize_t vhost_chr_read_iter(struct vhost_dev *dev, struct iov_iter *to,
			    int noblock)
{
	DEFINE_WAIT(wait);
	struct vhost_msg_node *node;
	ssize_t ret = 0;
	unsigned size = sizeof(struct vhost_msg);

	if (iov_iter_count(to) < size)
		return 0;

	while (1) {
		if (!noblock)
			prepare_to_wait(&dev->wait, &wait,
					TASK_INTERRUPTIBLE);

		node = vhost_dequeue_msg(dev, &dev->read_list);
		if (node)
			break;
		if (noblock) {
			ret = -EAGAIN;
			break;
		}
		if (signal_pending(current)) {
			ret = -ERESTARTSYS;
			break;
		}
		if (!dev->iotlb) {
			ret = -EBADFD;
			break;
		}

		schedule();
	}

	if (!noblock)
		finish_wait(&dev->wait, &wait);

	if (node) {
		ret = copy_to_iter(&node->msg, size, to);

		if (ret != size || node->msg.type != VHOST_IOTLB_MISS) {
			kfree(node);
			return ret;
		}

		vhost_enqueue_msg(dev, &dev->pending_list, node);
	}

	return ret;
}
EXPORT_SYMBOL_GPL(vhost_chr_read_iter);

static int vhost_iotlb_miss(struct vhost_virtqueue *vq, u64 iova, int access)
{
	struct vhost_dev *dev = vq->dev;
	struct vhost_msg_node *node;
	struct vhost_iotlb_msg *msg;

	node = vhost_new_msg(vq, VHOST_IOTLB_MISS);
	if (!node)
		return -ENOMEM;

	msg = &node->msg.iotlb;
	msg->type = VHOST_IOTLB_MISS;
	msg->iova = iova;
	msg->perm = access;

	vhost_enqueue_msg(dev, &dev->read_list, node);

	return 0;
}

static int vq_access_ok(struct vhost_virtqueue *vq, unsigned int num,
			struct vring_desc __user *desc,
			struct vring_avail __user *avail,
			struct vring_used __user *used)

{
	size_t s = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;

	return access_ok(VERIFY_READ, desc, num * sizeof *desc) &&
	       access_ok(VERIFY_READ, avail,
			 sizeof *avail + num * sizeof *avail->ring + s) &&
	       access_ok(VERIFY_WRITE, used,
			sizeof *used + num * sizeof *used->ring + s);
}

static int iotlb_access_ok(struct vhost_virtqueue *vq,
			   int access, u64 addr, u64 len)
{
	const struct vhost_umem_node *node;
	struct vhost_umem *umem = vq->iotlb;
	u64 s = 0, size;

	while (len > s) {
		node = vhost_umem_interval_tree_iter_first(&umem->umem_tree,
							   addr,
							   addr + len - 1);
		if (node == NULL || node->start > addr) {
			vhost_iotlb_miss(vq, addr, access);
			return false;
		} else if (!(node->perm & access)) {
			/* Report the possible access violation by
			 * request another translation from userspace.
			 */
			return false;
		}

		size = node->size - addr + node->start;
		s += size;
		addr += size;
	}

	return true;
}

int vq_iotlb_prefetch(struct vhost_virtqueue *vq)
{
	size_t s = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
	unsigned int num = vq->num;

	if (!vq->iotlb)
		return 1;

	return iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->desc,
			       num * sizeof *vq->desc) &&
	       iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->avail,
			       sizeof *vq->avail +
			       num * sizeof *vq->avail->ring + s) &&
	       iotlb_access_ok(vq, VHOST_ACCESS_WO, (u64)(uintptr_t)vq->used,
			       sizeof *vq->used +
			       num * sizeof *vq->used->ring + s);
}
EXPORT_SYMBOL_GPL(vq_iotlb_prefetch);

/* Can we log writes? */
/* Caller should have device mutex but not vq mutex */
int vhost_log_access_ok(struct vhost_dev *dev)
{
	return memory_access_ok(dev, dev->umem, 1);
}
EXPORT_SYMBOL_GPL(vhost_log_access_ok);

/* Verify access for write logging. */
/* Caller should have vq mutex and device mutex */
static int vq_log_access_ok(struct vhost_virtqueue *vq,
			    void __user *log_base)
{
	size_t s = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;

	return vq_memory_access_ok(log_base, vq->umem,
				   vhost_has_feature(vq, VHOST_F_LOG_ALL)) &&
		(!vq->log_used || log_access_ok(log_base, vq->log_addr,
					sizeof *vq->used +
					vq->num * sizeof *vq->used->ring + s));
}

/* Can we start vq? */
/* Caller should have vq mutex and device mutex */
int vhost_vq_access_ok(struct vhost_virtqueue *vq)
{
	if (vq->iotlb) {
		/* When device IOTLB was used, the access validation
		 * will be validated during prefetching.
		 */
		return 1;
	}
	return vq_access_ok(vq, vq->num, vq->desc, vq->avail, vq->used) &&
		vq_log_access_ok(vq, vq->log_base);
}
EXPORT_SYMBOL_GPL(vhost_vq_access_ok);

static struct vhost_umem *vhost_umem_alloc(void)
{
	struct vhost_umem *umem = vhost_kvzalloc(sizeof(*umem));

	if (!umem)
		return NULL;

	umem->umem_tree = RB_ROOT;
	umem->numem = 0;
	INIT_LIST_HEAD(&umem->umem_list);

	return umem;
}

static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
{
	struct vhost_memory mem, *newmem;
	struct vhost_memory_region *region;
	struct vhost_umem *newumem, *oldumem;
	unsigned long size = offsetof(struct vhost_memory, regions);
	int i;

	if (copy_from_user(&mem, m, size))
		return -EFAULT;
	if (mem.padding)
		return -EOPNOTSUPP;
	if (mem.nregions > max_mem_regions)
		return -E2BIG;
	newmem = vhost_kvzalloc(size + mem.nregions * sizeof(*m->regions));
	if (!newmem)
		return -ENOMEM;

	memcpy(newmem, &mem, size);
	if (copy_from_user(newmem->regions, m->regions,
			   mem.nregions * sizeof *m->regions)) {
		kvfree(newmem);
		return -EFAULT;
	}

	newumem = vhost_umem_alloc();
	if (!newumem) {
		kvfree(newmem);
		return -ENOMEM;
	}

	for (region = newmem->regions;
	     region < newmem->regions + mem.nregions;
	     region++) {
		if (vhost_new_umem_range(newumem,
					 region->guest_phys_addr,
					 region->memory_size,
					 region->guest_phys_addr +
					 region->memory_size - 1,
					 region->userspace_addr,
					 VHOST_ACCESS_RW))
			goto err;
	}

	if (!memory_access_ok(d, newumem, 0))
		goto err;

	oldumem = d->umem;
	d->umem = newumem;

	/* All memory accesses are done under some VQ mutex. */
	for (i = 0; i < d->nvqs; ++i) {
		mutex_lock(&d->vqs[i]->mutex);
		d->vqs[i]->umem = newumem;
		mutex_unlock(&d->vqs[i]->mutex);
	}

	kvfree(newmem);
	vhost_umem_clean(oldumem);
	return 0;

err:
	vhost_umem_clean(newumem);
	kvfree(newmem);
	return -EFAULT;
}

long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp)
{
	struct file *eventfp, *filep = NULL;
	bool pollstart = false, pollstop = false;
	struct eventfd_ctx *ctx = NULL;
	u32 __user *idxp = argp;
	struct vhost_virtqueue *vq;
	struct vhost_vring_state s;
	struct vhost_vring_file f;
	struct vhost_vring_addr a;
	u32 idx;
	long r;

	r = get_user(idx, idxp);
	if (r < 0)
		return r;
	if (idx >= d->nvqs)
		return -ENOBUFS;

	vq = d->vqs[idx];

	mutex_lock(&vq->mutex);

	switch (ioctl) {
	case VHOST_SET_VRING_NUM:
		/* Resizing ring with an active backend?
		 * You don't want to do that. */
		if (vq->private_data) {
			r = -EBUSY;
			break;
		}
		if (copy_from_user(&s, argp, sizeof s)) {
			r = -EFAULT;
			break;
		}
		if (!s.num || s.num > 0xffff || (s.num & (s.num - 1))) {
			r = -EINVAL;
			break;
		}
		vq->num = s.num;
		break;
	case VHOST_SET_VRING_BASE:
		/* Moving base with an active backend?
		 * You don't want to do that. */
		if (vq->private_data) {
			r = -EBUSY;
			break;
		}
		if (copy_from_user(&s, argp, sizeof s)) {
			r = -EFAULT;
			break;
		}
		if (s.num > 0xffff) {
			r = -EINVAL;
			break;
		}
		vq->last_avail_idx = s.num;
		/* Forget the cached index value. */
		vq->avail_idx = vq->last_avail_idx;
		break;
	case VHOST_GET_VRING_BASE:
		s.index = idx;
		s.num = vq->last_avail_idx;
		if (copy_to_user(argp, &s, sizeof s))
			r = -EFAULT;
		break;
	case VHOST_SET_VRING_ADDR:
		if (copy_from_user(&a, argp, sizeof a)) {
			r = -EFAULT;
			break;
		}
		if (a.flags & ~(0x1 << VHOST_VRING_F_LOG)) {
			r = -EOPNOTSUPP;
			break;
		}
		/* For 32bit, verify that the top 32bits of the user
		   data are set to zero. */
		if ((u64)(unsigned long)a.desc_user_addr != a.desc_user_addr ||
		    (u64)(unsigned long)a.used_user_addr != a.used_user_addr ||
		    (u64)(unsigned long)a.avail_user_addr != a.avail_user_addr) {
			r = -EFAULT;
			break;
		}

		/* Make sure it's safe to cast pointers to vring types. */
		BUILD_BUG_ON(__alignof__ *vq->avail > VRING_AVAIL_ALIGN_SIZE);
		BUILD_BUG_ON(__alignof__ *vq->used > VRING_USED_ALIGN_SIZE);
		if ((a.avail_user_addr & (VRING_AVAIL_ALIGN_SIZE - 1)) ||
		    (a.used_user_addr & (VRING_USED_ALIGN_SIZE - 1)) ||
		    (a.log_guest_addr & (VRING_USED_ALIGN_SIZE - 1))) {
			r = -EINVAL;
			break;
		}

		/* We only verify access here if backend is configured.
		 * If it is not, we don't as size might not have been setup.
		 * We will verify when backend is configured. */
		if (vq->private_data) {
			if (!vq_access_ok(vq, vq->num,
				(void __user *)(unsigned long)a.desc_user_addr,
				(void __user *)(unsigned long)a.avail_user_addr,
				(void __user *)(unsigned long)a.used_user_addr)) {
				r = -EINVAL;
				break;
			}

			/* Also validate log access for used ring if enabled. */
			if ((a.flags & (0x1 << VHOST_VRING_F_LOG)) &&
			    !log_access_ok(vq->log_base, a.log_guest_addr,
					   sizeof *vq->used +
					   vq->num * sizeof *vq->used->ring)) {
				r = -EINVAL;
				break;
			}
		}

		vq->log_used = !!(a.flags & (0x1 << VHOST_VRING_F_LOG));
		vq->desc = (void __user *)(unsigned long)a.desc_user_addr;
		vq->avail = (void __user *)(unsigned long)a.avail_user_addr;
		vq->log_addr = a.log_guest_addr;
		vq->used = (void __user *)(unsigned long)a.used_user_addr;
		break;
	case VHOST_SET_VRING_KICK:
		if (copy_from_user(&f, argp, sizeof f)) {
			r = -EFAULT;
			break;
		}
		eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd);
		if (IS_ERR(eventfp)) {
			r = PTR_ERR(eventfp);
			break;
		}
		if (eventfp != vq->kick) {
			pollstop = (filep = vq->kick) != NULL;
			pollstart = (vq->kick = eventfp) != NULL;
		} else
			filep = eventfp;
		break;
	case VHOST_SET_VRING_CALL:
		if (copy_from_user(&f, argp, sizeof f)) {
			r = -EFAULT;
			break;
		}
		eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd);
		if (IS_ERR(eventfp)) {
			r = PTR_ERR(eventfp);
			break;
		}
		if (eventfp != vq->call) {
			filep = vq->call;
			ctx = vq->call_ctx;
			vq->call = eventfp;
			vq->call_ctx = eventfp ?
				eventfd_ctx_fileget(eventfp) : NULL;
		} else
			filep = eventfp;
		break;
	case VHOST_SET_VRING_ERR:
		if (copy_from_user(&f, argp, sizeof f)) {
			r = -EFAULT;
			break;
		}
		eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd);
		if (IS_ERR(eventfp)) {
			r = PTR_ERR(eventfp);
			break;
		}
		if (eventfp != vq->error) {
			filep = vq->error;
			vq->error = eventfp;
			ctx = vq->error_ctx;
			vq->error_ctx = eventfp ?
				eventfd_ctx_fileget(eventfp) : NULL;
		} else
			filep = eventfp;
		break;
	case VHOST_SET_VRING_ENDIAN:
		r = vhost_set_vring_endian(vq, argp);
		break;
	case VHOST_GET_VRING_ENDIAN:
		r = vhost_get_vring_endian(vq, idx, argp);
		break;
	case VHOST_SET_VRING_BUSYLOOP_TIMEOUT:
		if (copy_from_user(&s, argp, sizeof(s))) {
			r = -EFAULT;
			break;
		}
		vq->busyloop_timeout = s.num;
		break;
	case VHOST_GET_VRING_BUSYLOOP_TIMEOUT:
		s.index = idx;
		s.num = vq->busyloop_timeout;
		if (copy_to_user(argp, &s, sizeof(s)))
			r = -EFAULT;
		break;
	default:
		r = -ENOIOCTLCMD;
	}

	if (pollstop && vq->handle_kick)
		vhost_poll_stop(&vq->poll);

	if (ctx)
		eventfd_ctx_put(ctx);
	if (filep)
		fput(filep);

	if (pollstart && vq->handle_kick)
		r = vhost_poll_start(&vq->poll, vq->kick);

	mutex_unlock(&vq->mutex);

	if (pollstop && vq->handle_kick)
		vhost_poll_flush(&vq->poll);
	return r;
}
EXPORT_SYMBOL_GPL(vhost_vring_ioctl);

int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled)
{
	struct vhost_umem *niotlb, *oiotlb;
	int i;

	niotlb = vhost_umem_alloc();
	if (!niotlb)
		return -ENOMEM;

	oiotlb = d->iotlb;
	d->iotlb = niotlb;

	for (i = 0; i < d->nvqs; ++i) {
		mutex_lock(&d->vqs[i]->mutex);
		d->vqs[i]->iotlb = niotlb;
		mutex_unlock(&d->vqs[i]->mutex);
	}

	vhost_umem_clean(oiotlb);

	return 0;
}
EXPORT_SYMBOL_GPL(vhost_init_device_iotlb);

/* Caller must have device mutex */
long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp)
{
	struct file *eventfp, *filep = NULL;
	struct eventfd_ctx *ctx = NULL;
	u64 p;
	long r;
	int i, fd;

	/* If you are not the owner, you can become one */
	if (ioctl == VHOST_SET_OWNER) {
		r = vhost_dev_set_owner(d);
		goto done;
	}

	/* You must be the owner to do anything else */
	r = vhost_dev_check_owner(d);
	if (r)
		goto done;

	switch (ioctl) {
	case VHOST_SET_MEM_TABLE:
		r = vhost_set_memory(d, argp);
		break;
	case VHOST_SET_LOG_BASE:
		if (copy_from_user(&p, argp, sizeof p)) {
			r = -EFAULT;
			break;
		}
		if ((u64)(unsigned long)p != p) {
			r = -EFAULT;
			break;
		}
		for (i = 0; i < d->nvqs; ++i) {
			struct vhost_virtqueue *vq;
			void __user *base = (void __user *)(unsigned long)p;
			vq = d->vqs[i];
			mutex_lock(&vq->mutex);
			/* If ring is inactive, will check when it's enabled. */
			if (vq->private_data && !vq_log_access_ok(vq, base))
				r = -EFAULT;
			else
				vq->log_base = base;
			mutex_unlock(&vq->mutex);
		}
		break;
	case VHOST_SET_LOG_FD:
		r = get_user(fd, (int __user *)argp);
		if (r < 0)
			break;
		eventfp = fd == -1 ? NULL : eventfd_fget(fd);
		if (IS_ERR(eventfp)) {
			r = PTR_ERR(eventfp);
			break;
		}
		if (eventfp != d->log_file) {
			filep = d->log_file;
			d->log_file = eventfp;
			ctx = d->log_ctx;
			d->log_ctx = eventfp ?
				eventfd_ctx_fileget(eventfp) : NULL;
		} else
			filep = eventfp;
		for (i = 0; i < d->nvqs; ++i) {
			mutex_lock(&d->vqs[i]->mutex);
			d->vqs[i]->log_ctx = d->log_ctx;
			mutex_unlock(&d->vqs[i]->mutex);
		}
		if (ctx)
			eventfd_ctx_put(ctx);
		if (filep)
			fput(filep);
		break;
	default:
		r = -ENOIOCTLCMD;
		break;
	}
done:
	return r;
}
EXPORT_SYMBOL_GPL(vhost_dev_ioctl);

/* TODO: This is really inefficient.  We need something like get_user()
 * (instruction directly accesses the data, with an exception table entry
 * returning -EFAULT). See Documentation/x86/exception-tables.txt.
 */
static int set_bit_to_user(int nr, void __user *addr)
{
	unsigned long log = (unsigned long)addr;
	struct page *page;
	void *base;
	int bit = nr + (log % PAGE_SIZE) * 8;
	int r;

	r = get_user_pages_fast(log, 1, 1, &page);
	if (r < 0)
		return r;
	BUG_ON(r != 1);
	base = kmap_atomic(page);
	set_bit(bit, base);
	kunmap_atomic(base);
	set_page_dirty_lock(page);
	put_page(page);
	return 0;
}

static int log_write(void __user *log_base,
		     u64 write_address, u64 write_length)
{
	u64 write_page = write_address / VHOST_PAGE_SIZE;
	int r;

	if (!write_length)
		return 0;
	write_length += write_address % VHOST_PAGE_SIZE;
	for (;;) {
		u64 base = (u64)(unsigned long)log_base;
		u64 log = base + write_page / 8;
		int bit = write_page % 8;
		if ((u64)(unsigned long)log != log)
			return -EFAULT;
		r = set_bit_to_user(bit, (void __user *)(unsigned long)log);
		if (r < 0)
			return r;
		if (write_length <= VHOST_PAGE_SIZE)
			break;
		write_length -= VHOST_PAGE_SIZE;
		write_page += 1;
	}
	return r;
}

int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
		    unsigned int log_num, u64 len)
{
	int i, r;

	/* Make sure data written is seen before log. */
	smp_wmb();
	for (i = 0; i < log_num; ++i) {
		u64 l = min(log[i].len, len);
		r = log_write(vq->log_base, log[i].addr, l);
		if (r < 0)
			return r;
		len -= l;
		if (!len) {
			if (vq->log_ctx)
				eventfd_signal(vq->log_ctx, 1);
			return 0;
		}
	}
	/* Length written exceeds what we have stored. This is a bug. */
	BUG();
	return 0;
}
EXPORT_SYMBOL_GPL(vhost_log_write);

static int vhost_update_used_flags(struct vhost_virtqueue *vq)
{
	void __user *used;
	if (vhost_put_user(vq, cpu_to_vhost16(vq, vq->used_flags),
			   &vq->used->flags) < 0)
		return -EFAULT;
	if (unlikely(vq->log_used)) {
		/* Make sure the flag is seen before log. */
		smp_wmb();
		/* Log used flag write. */
		used = &vq->used->flags;
		log_write(vq->log_base, vq->log_addr +
			  (used - (void __user *)vq->used),
			  sizeof vq->used->flags);
		if (vq->log_ctx)
			eventfd_signal(vq->log_ctx, 1);
	}
	return 0;
}

static int vhost_update_avail_event(struct vhost_virtqueue *vq, u16 avail_event)
{
	if (vhost_put_user(vq, cpu_to_vhost16(vq, vq->avail_idx),
			   vhost_avail_event(vq)))
		return -EFAULT;
	if (unlikely(vq->log_used)) {
		void __user *used;
		/* Make sure the event is seen before log. */
		smp_wmb();
		/* Log avail event write */
		used = vhost_avail_event(vq);
		log_write(vq->log_base, vq->log_addr +
			  (used - (void __user *)vq->used),
			  sizeof *vhost_avail_event(vq));
		if (vq->log_ctx)
			eventfd_signal(vq->log_ctx, 1);
	}
	return 0;
}

int vhost_vq_init_access(struct vhost_virtqueue *vq)
{
	__virtio16 last_used_idx;
	int r;
	bool is_le = vq->is_le;

	if (!vq->private_data) {
		vhost_reset_is_le(vq);
		return 0;
	}

	vhost_init_is_le(vq);

	r = vhost_update_used_flags(vq);
	if (r)
		goto err;
	vq->signalled_used_valid = false;
	if (!vq->iotlb &&
	    !access_ok(VERIFY_READ, &vq->used->idx, sizeof vq->used->idx)) {
		r = -EFAULT;
		goto err;
	}
	r = vhost_get_user(vq, last_used_idx, &vq->used->idx);
	if (r) {
		vq_err(vq, "Can't access used idx at %p\n",
		       &vq->used->idx);
		goto err;
	}
	vq->last_used_idx = vhost16_to_cpu(vq, last_used_idx);
	return 0;

err:
	vq->is_le = is_le;
	return r;
}
EXPORT_SYMBOL_GPL(vhost_vq_init_access);

static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len,
			  struct iovec iov[], int iov_size, int access)
{
	const struct vhost_umem_node *node;
	struct vhost_dev *dev = vq->dev;
	struct vhost_umem *umem = dev->iotlb ? dev->iotlb : dev->umem;
	struct iovec *_iov;
	u64 s = 0;
	int ret = 0;

	while ((u64)len > s) {
		u64 size;
		if (unlikely(ret >= iov_size)) {
			ret = -ENOBUFS;
			break;
		}

		node = vhost_umem_interval_tree_iter_first(&umem->umem_tree,
							addr, addr + len - 1);
		if (node == NULL || node->start > addr) {
			if (umem != dev->iotlb) {
				ret = -EFAULT;
				break;
			}
			ret = -EAGAIN;
			break;
		} else if (!(node->perm & access)) {
			ret = -EPERM;
			break;
		}

		_iov = iov + ret;
		size = node->size - addr + node->start;
		_iov->iov_len = min((u64)len - s, size);
		_iov->iov_base = (void __user *)(unsigned long)
			(node->userspace_addr + addr - node->start);
		s += size;
		addr += size;
		++ret;
	}

	if (ret == -EAGAIN)
		vhost_iotlb_miss(vq, addr, access);
	return ret;
}

/* Each buffer in the virtqueues is actually a chain of descriptors.  This
 * function returns the next descriptor in the chain,
 * or -1U if we're at the end. */
static unsigned next_desc(struct vhost_virtqueue *vq, struct vring_desc *desc)
{
	unsigned int next;

	/* If this descriptor says it doesn't chain, we're done. */
	if (!(desc->flags & cpu_to_vhost16(vq, VRING_DESC_F_NEXT)))
		return -1U;

	/* Check they're not leading us off end of descriptors. */
	next = vhost16_to_cpu(vq, desc->next);
	/* Make sure compiler knows to grab that: we don't want it changing! */
	/* We will use the result as an index in an array, so most
	 * architectures only need a compiler barrier here. */
	read_barrier_depends();

	return next;
}

static int get_indirect(struct vhost_virtqueue *vq,
			struct iovec iov[], unsigned int iov_size,
			unsigned int *out_num, unsigned int *in_num,
			struct vhost_log *log, unsigned int *log_num,
			struct vring_desc *indirect)
{
	struct vring_desc desc;
	unsigned int i = 0, count, found = 0;
	u32 len = vhost32_to_cpu(vq, indirect->len);
	struct iov_iter from;
	int ret, access;

	/* Sanity check */
	if (unlikely(len % sizeof desc)) {
		vq_err(vq, "Invalid length in indirect descriptor: "
		       "len 0x%llx not multiple of 0x%zx\n",
		       (unsigned long long)len,
		       sizeof desc);
		return -EINVAL;
	}

	ret = translate_desc(vq, vhost64_to_cpu(vq, indirect->addr), len, vq->indirect,
			     UIO_MAXIOV, VHOST_ACCESS_RO);
	if (unlikely(ret < 0)) {
		if (ret != -EAGAIN)
			vq_err(vq, "Translation failure %d in indirect.\n", ret);
		return ret;
	}
	iov_iter_init(&from, READ, vq->indirect, ret, len);

	/* We will use the result as an address to read from, so most
	 * architectures only need a compiler barrier here. */
	read_barrier_depends();

	count = len / sizeof desc;
	/* Buffers are chained via a 16 bit next field, so
	 * we can have at most 2^16 of these. */
	if (unlikely(count > USHRT_MAX + 1)) {
		vq_err(vq, "Indirect buffer length too big: %d\n",
		       indirect->len);
		return -E2BIG;
	}

	do {
		unsigned iov_count = *in_num + *out_num;
		if (unlikely(++found > count)) {
			vq_err(vq, "Loop detected: last one at %u "
			       "indirect size %u\n",
			       i, count);
			return -EINVAL;
		}
		if (unlikely(copy_from_iter(&desc, sizeof(desc), &from) !=
			     sizeof(desc))) {
			vq_err(vq, "Failed indirect descriptor: idx %d, %zx\n",
			       i, (size_t)vhost64_to_cpu(vq, indirect->addr) + i * sizeof desc);
			return -EINVAL;
		}
		if (unlikely(desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_INDIRECT))) {
			vq_err(vq, "Nested indirect descriptor: idx %d, %zx\n",
			       i, (size_t)vhost64_to_cpu(vq, indirect->addr) + i * sizeof desc);
			return -EINVAL;
		}

		if (desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_WRITE))
			access = VHOST_ACCESS_WO;
		else
			access = VHOST_ACCESS_RO;

		ret = translate_desc(vq, vhost64_to_cpu(vq, desc.addr),
				     vhost32_to_cpu(vq, desc.len), iov + iov_count,
				     iov_size - iov_count, access);
		if (unlikely(ret < 0)) {
			if (ret != -EAGAIN)
				vq_err(vq, "Translation failure %d indirect idx %d\n",
					ret, i);
			return ret;
		}
		/* If this is an input descriptor, increment that count. */
		if (access == VHOST_ACCESS_WO) {
			*in_num += ret;
			if (unlikely(log)) {
				log[*log_num].addr = vhost64_to_cpu(vq, desc.addr);
				log[*log_num].len = vhost32_to_cpu(vq, desc.len);
				++*log_num;
			}
		} else {
			/* If it's an output descriptor, they're all supposed
			 * to come before any input descriptors. */
			if (unlikely(*in_num)) {
				vq_err(vq, "Indirect descriptor "
				       "has out after in: idx %d\n", i);
				return -EINVAL;
			}
			*out_num += ret;
		}
	} while ((i = next_desc(vq, &desc)) != -1);
	return 0;
}

/* This looks in the virtqueue and for the first available buffer, and converts
 * it to an iovec for convenient access.  Since descriptors consist of some
 * number of output then some number of input descriptors, it's actually two
 * iovecs, but we pack them into one and note how many of each there were.
 *
 * This function returns the descriptor number found, or vq->num (which is
 * never a valid descriptor number) if none was found.  A negative code is
 * returned on error. */
int vhost_get_vq_desc(struct vhost_virtqueue *vq,
		      struct iovec iov[], unsigned int iov_size,
		      unsigned int *out_num, unsigned int *in_num,
		      struct vhost_log *log, unsigned int *log_num)
{
	struct vring_desc desc;
	unsigned int i, head, found = 0;
	u16 last_avail_idx;
	__virtio16 avail_idx;
	__virtio16 ring_head;
	int ret, access;

	/* Check it isn't doing very strange things with descriptor numbers. */
	last_avail_idx = vq->last_avail_idx;
	if (unlikely(vhost_get_user(vq, avail_idx, &vq->avail->idx))) {
		vq_err(vq, "Failed to access avail idx at %p\n",
		       &vq->avail->idx);
		return -EFAULT;
	}
	vq->avail_idx = vhost16_to_cpu(vq, avail_idx);

	if (unlikely((u16)(vq->avail_idx - last_avail_idx) > vq->num)) {
		vq_err(vq, "Guest moved used index from %u to %u",
		       last_avail_idx, vq->avail_idx);
		return -EFAULT;
	}

	/* If there's nothing new since last we looked, return invalid. */
	if (vq->avail_idx == last_avail_idx)
		return vq->num;

	/* Only get avail ring entries after they have been exposed by guest. */
	smp_rmb();

	/* Grab the next descriptor number they're advertising, and increment
	 * the index we've seen. */
	if (unlikely(vhost_get_user(vq, ring_head,
		     &vq->avail->ring[last_avail_idx & (vq->num - 1)]))) {
		vq_err(vq, "Failed to read head: idx %d address %p\n",
		       last_avail_idx,
		       &vq->avail->ring[last_avail_idx % vq->num]);
		return -EFAULT;
	}

	head = vhost16_to_cpu(vq, ring_head);

	/* If their number is silly, that's an error. */
	if (unlikely(head >= vq->num)) {
		vq_err(vq, "Guest says index %u > %u is available",
		       head, vq->num);
		return -EINVAL;
	}

	/* When we start there are none of either input nor output. */
	*out_num = *in_num = 0;
	if (unlikely(log))
		*log_num = 0;

	i = head;
	do {
		unsigned iov_count = *in_num + *out_num;
		if (unlikely(i >= vq->num)) {
			vq_err(vq, "Desc index is %u > %u, head = %u",
			       i, vq->num, head);
			return -EINVAL;
		}
		if (unlikely(++found > vq->num)) {
			vq_err(vq, "Loop detected: last one at %u "
			       "vq size %u head %u\n",
			       i, vq->num, head);
			return -EINVAL;
		}
		ret = vhost_copy_from_user(vq, &desc, vq->desc + i,
					   sizeof desc);
		if (unlikely(ret)) {
			vq_err(vq, "Failed to get descriptor: idx %d addr %p\n",
			       i, vq->desc + i);
			return -EFAULT;
		}
		if (desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_INDIRECT)) {
			ret = get_indirect(vq, iov, iov_size,
					   out_num, in_num,
					   log, log_num, &desc);
			if (unlikely(ret < 0)) {
				if (ret != -EAGAIN)
					vq_err(vq, "Failure detected "
						"in indirect descriptor at idx %d\n", i);
				return ret;
			}
			continue;
		}

		if (desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_WRITE))
			access = VHOST_ACCESS_WO;
		else
			access = VHOST_ACCESS_RO;
		ret = translate_desc(vq, vhost64_to_cpu(vq, desc.addr),
				     vhost32_to_cpu(vq, desc.len), iov + iov_count,
				     iov_size - iov_count, access);
		if (unlikely(ret < 0)) {
			if (ret != -EAGAIN)
				vq_err(vq, "Translation failure %d descriptor idx %d\n",
					ret, i);
			return ret;
		}
		if (access == VHOST_ACCESS_WO) {
			/* If this is an input descriptor,
			 * increment that count. */
			*in_num += ret;
			if (unlikely(log)) {
				log[*log_num].addr = vhost64_to_cpu(vq, desc.addr);
				log[*log_num].len = vhost32_to_cpu(vq, desc.len);
				++*log_num;
			}
		} else {
			/* If it's an output descriptor, they're all supposed
			 * to come before any input descriptors. */
			if (unlikely(*in_num)) {
				vq_err(vq, "Descriptor has out after in: "
				       "idx %d\n", i);
				return -EINVAL;
			}
			*out_num += ret;
		}
	} while ((i = next_desc(vq, &desc)) != -1);

	/* On success, increment avail index. */
	vq->last_avail_idx++;

	/* Assume notifications from guest are disabled at this point,
	 * if they aren't we would need to update avail_event index. */
	BUG_ON(!(vq->used_flags & VRING_USED_F_NO_NOTIFY));
	return head;
}
EXPORT_SYMBOL_GPL(vhost_get_vq_desc);

/* Reverse the effect of vhost_get_vq_desc. Useful for error handling. */
void vhost_discard_vq_desc(struct vhost_virtqueue *vq, int n)
{
	vq->last_avail_idx -= n;
}
EXPORT_SYMBOL_GPL(vhost_discard_vq_desc);

/* After we've used one of their buffers, we tell them about it.  We'll then
 * want to notify the guest, using eventfd. */
int vhost_add_used(struct vhost_virtqueue *vq, unsigned int head, int len)
{
	struct vring_used_elem heads = {
		cpu_to_vhost32(vq, head),
		cpu_to_vhost32(vq, len)
	};

	return vhost_add_used_n(vq, &heads, 1);
}
EXPORT_SYMBOL_GPL(vhost_add_used);

static int __vhost_add_used_n(struct vhost_virtqueue *vq,
			    struct vring_used_elem *heads,
			    unsigned count)
{
	struct vring_used_elem __user *used;
	u16 old, new;
	int start;

	start = vq->last_used_idx & (vq->num - 1);
	used = vq->used->ring + start;
	if (count == 1) {
		if (vhost_put_user(vq, heads[0].id, &used->id)) {
			vq_err(vq, "Failed to write used id");
			return -EFAULT;
		}
		if (vhost_put_user(vq, heads[0].len, &used->len)) {
			vq_err(vq, "Failed to write used len");
			return -EFAULT;
		}
	} else if (vhost_copy_to_user(vq, used, heads, count * sizeof *used)) {
		vq_err(vq, "Failed to write used");
		return -EFAULT;
	}
	if (unlikely(vq->log_used)) {
		/* Make sure data is seen before log. */
		smp_wmb();
		/* Log used ring entry write. */
		log_write(vq->log_base,
			  vq->log_addr +
			   ((void __user *)used - (void __user *)vq->used),
			  count * sizeof *used);
	}
	old = vq->last_used_idx;
	new = (vq->last_used_idx += count);
	/* If the driver never bothers to signal in a very long while,
	 * used index might wrap around. If that happens, invalidate
	 * signalled_used index we stored. TODO: make sure driver
	 * signals at least once in 2^16 and remove this. */
	if (unlikely((u16)(new - vq->signalled_used) < (u16)(new - old)))
		vq->signalled_used_valid = false;
	return 0;
}

/* After we've used one of their buffers, we tell them about it.  We'll then
 * want to notify the guest, using eventfd. */
int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
		     unsigned count)
{
	int start, n, r;

	start = vq->last_used_idx & (vq->num - 1);
	n = vq->num - start;
	if (n < count) {
		r = __vhost_add_used_n(vq, heads, n);
		if (r < 0)
			return r;
		heads += n;
		count -= n;
	}
	r = __vhost_add_used_n(vq, heads, count);

	/* Make sure buffer is written before we update index. */
	smp_wmb();
	if (vhost_put_user(vq, cpu_to_vhost16(vq, vq->last_used_idx),
			   &vq->used->idx)) {
		vq_err(vq, "Failed to increment used idx");
		return -EFAULT;
	}
	if (unlikely(vq->log_used)) {
		/* Log used index update. */
		log_write(vq->log_base,
			  vq->log_addr + offsetof(struct vring_used, idx),
			  sizeof vq->used->idx);
		if (vq->log_ctx)
			eventfd_signal(vq->log_ctx, 1);
	}
	return r;
}
EXPORT_SYMBOL_GPL(vhost_add_used_n);

static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
{
	__u16 old, new;
	__virtio16 event;
	bool v;
	/* Flush out used index updates. This is paired
	 * with the barrier that the Guest executes when enabling
	 * interrupts. */
	smp_mb();

	if (vhost_has_feature(vq, VIRTIO_F_NOTIFY_ON_EMPTY) &&
	    unlikely(vq->avail_idx == vq->last_avail_idx))
		return true;

	if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) {
		__virtio16 flags;
		if (vhost_get_user(vq, flags, &vq->avail->flags)) {
			vq_err(vq, "Failed to get flags");
			return true;
		}
		return !(flags & cpu_to_vhost16(vq, VRING_AVAIL_F_NO_INTERRUPT));
	}
	old = vq->signalled_used;
	v = vq->signalled_used_valid;
	new = vq->signalled_used = vq->last_used_idx;
	vq->signalled_used_valid = true;

	if (unlikely(!v))
		return true;

	if (vhost_get_user(vq, event, vhost_used_event(vq))) {
		vq_err(vq, "Failed to get used event idx");
		return true;
	}
	return vring_need_event(vhost16_to_cpu(vq, event), new, old);
}

/* This actually signals the guest, using eventfd. */
void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
{
	/* Signal the Guest tell them we used something up. */
	if (vq->call_ctx && vhost_notify(dev, vq))
		eventfd_signal(vq->call_ctx, 1);
}
EXPORT_SYMBOL_GPL(vhost_signal);

/* And here's the combo meal deal.  Supersize me! */
void vhost_add_used_and_signal(struct vhost_dev *dev,
			       struct vhost_virtqueue *vq,
			       unsigned int head, int len)
{
	vhost_add_used(vq, head, len);
	vhost_signal(dev, vq);
}
EXPORT_SYMBOL_GPL(vhost_add_used_and_signal);

/* multi-buffer version of vhost_add_used_and_signal */
void vhost_add_used_and_signal_n(struct vhost_dev *dev,
				 struct vhost_virtqueue *vq,
				 struct vring_used_elem *heads, unsigned count)
{
	vhost_add_used_n(vq, heads, count);
	vhost_signal(dev, vq);
}
EXPORT_SYMBOL_GPL(vhost_add_used_and_signal_n);

/* return true if we're sure that avaiable ring is empty */
bool vhost_vq_avail_empty(struct vhost_dev *dev, struct vhost_virtqueue *vq)
{
	__virtio16 avail_idx;
	int r;

	r = vhost_get_user(vq, avail_idx, &vq->avail->idx);
	if (r)
		return false;

	return vhost16_to_cpu(vq, avail_idx) == vq->avail_idx;
}
EXPORT_SYMBOL_GPL(vhost_vq_avail_empty);

/* OK, now we need to know about added descriptors. */
bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
{
	__virtio16 avail_idx;
	int r;

	if (!(vq->used_flags & VRING_USED_F_NO_NOTIFY))
		return false;
	vq->used_flags &= ~VRING_USED_F_NO_NOTIFY;
	if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) {
		r = vhost_update_used_flags(vq);
		if (r) {
			vq_err(vq, "Failed to enable notification at %p: %d\n",
			       &vq->used->flags, r);
			return false;
		}
	} else {
		r = vhost_update_avail_event(vq, vq->avail_idx);
		if (r) {
			vq_err(vq, "Failed to update avail event index at %p: %d\n",
			       vhost_avail_event(vq), r);
			return false;
		}
	}
	/* They could have slipped one in as we were doing that: make
	 * sure it's written, then check again. */
	smp_mb();
	r = vhost_get_user(vq, avail_idx, &vq->avail->idx);
	if (r) {
		vq_err(vq, "Failed to check avail idx at %p: %d\n",
		       &vq->avail->idx, r);
		return false;
	}

	return vhost16_to_cpu(vq, avail_idx) != vq->avail_idx;
}
EXPORT_SYMBOL_GPL(vhost_enable_notify);

/* We don't need to be notified again. */
void vhost_disable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
{
	int r;

	if (vq->used_flags & VRING_USED_F_NO_NOTIFY)
		return;
	vq->used_flags |= VRING_USED_F_NO_NOTIFY;
	if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) {
		r = vhost_update_used_flags(vq);
		if (r)
			vq_err(vq, "Failed to enable notification at %p: %d\n",
			       &vq->used->flags, r);
	}
}
EXPORT_SYMBOL_GPL(vhost_disable_notify);

/* Create a new message. */
struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type)
{
	struct vhost_msg_node *node = kmalloc(sizeof *node, GFP_KERNEL);
	if (!node)
		return NULL;
	node->vq = vq;
	node->msg.type = type;
	return node;
}
EXPORT_SYMBOL_GPL(vhost_new_msg);

void vhost_enqueue_msg(struct vhost_dev *dev, struct list_head *head,
		       struct vhost_msg_node *node)
{
	spin_lock(&dev->iotlb_lock);
	list_add_tail(&node->node, head);
	spin_unlock(&dev->iotlb_lock);

	wake_up_interruptible_poll(&dev->wait, POLLIN | POLLRDNORM);
}
EXPORT_SYMBOL_GPL(vhost_enqueue_msg);

struct vhost_msg_node *vhost_dequeue_msg(struct vhost_dev *dev,
					 struct list_head *head)
{
	struct vhost_msg_node *node = NULL;

	spin_lock(&dev->iotlb_lock);
	if (!list_empty(head)) {
		node = list_first_entry(head, struct vhost_msg_node,
					node);
		list_del(&node->node);
	}
	spin_unlock(&dev->iotlb_lock);

	return node;
}
EXPORT_SYMBOL_GPL(vhost_dequeue_msg);


static int __init vhost_init(void)
{
	return 0;
}

static void __exit vhost_exit(void)
{
}

module_init(vhost_init);
module_exit(vhost_exit);

MODULE_VERSION("0.0.1");
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Michael S. Tsirkin");
MODULE_DESCRIPTION("Host kernel accelerator for virtio");