summaryrefslogtreecommitdiff
path: root/net/vmw_vsock/af_vsock.c
blob: ca511c4f388a56cf1fdaf110d31aff7d30b5d0fb (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
/*
 * VMware vSockets Driver
 *
 * Copyright (C) 2007-2013 VMware, Inc. All rights reserved.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License as published by the Free
 * Software Foundation version 2 and no later version.
 *
 * This program is distributed in the hope that it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 */

/* Implementation notes:
 *
 * - There are two kinds of sockets: those created by user action (such as
 * calling socket(2)) and those created by incoming connection request packets.
 *
 * - There are two "global" tables, one for bound sockets (sockets that have
 * specified an address that they are responsible for) and one for connected
 * sockets (sockets that have established a connection with another socket).
 * These tables are "global" in that all sockets on the system are placed
 * within them. - Note, though, that the bound table contains an extra entry
 * for a list of unbound sockets and SOCK_DGRAM sockets will always remain in
 * that list. The bound table is used solely for lookup of sockets when packets
 * are received and that's not necessary for SOCK_DGRAM sockets since we create
 * a datagram handle for each and need not perform a lookup.  Keeping SOCK_DGRAM
 * sockets out of the bound hash buckets will reduce the chance of collisions
 * when looking for SOCK_STREAM sockets and prevents us from having to check the
 * socket type in the hash table lookups.
 *
 * - Sockets created by user action will either be "client" sockets that
 * initiate a connection or "server" sockets that listen for connections; we do
 * not support simultaneous connects (two "client" sockets connecting).
 *
 * - "Server" sockets are referred to as listener sockets throughout this
 * implementation because they are in the SS_LISTEN state.  When a connection
 * request is received (the second kind of socket mentioned above), we create a
 * new socket and refer to it as a pending socket.  These pending sockets are
 * placed on the pending connection list of the listener socket.  When future
 * packets are received for the address the listener socket is bound to, we
 * check if the source of the packet is from one that has an existing pending
 * connection.  If it does, we process the packet for the pending socket.  When
 * that socket reaches the connected state, it is removed from the listener
 * socket's pending list and enqueued in the listener socket's accept queue.
 * Callers of accept(2) will accept connected sockets from the listener socket's
 * accept queue.  If the socket cannot be accepted for some reason then it is
 * marked rejected.  Once the connection is accepted, it is owned by the user
 * process and the responsibility for cleanup falls with that user process.
 *
 * - It is possible that these pending sockets will never reach the connected
 * state; in fact, we may never receive another packet after the connection
 * request.  Because of this, we must schedule a cleanup function to run in the
 * future, after some amount of time passes where a connection should have been
 * established.  This function ensures that the socket is off all lists so it
 * cannot be retrieved, then drops all references to the socket so it is cleaned
 * up (sock_put() -> sk_free() -> our sk_destruct implementation).  Note this
 * function will also cleanup rejected sockets, those that reach the connected
 * state but leave it before they have been accepted.
 *
 * - Sockets created by user action will be cleaned up when the user process
 * calls close(2), causing our release implementation to be called. Our release
 * implementation will perform some cleanup then drop the last reference so our
 * sk_destruct implementation is invoked.  Our sk_destruct implementation will
 * perform additional cleanup that's common for both types of sockets.
 *
 * - A socket's reference count is what ensures that the structure won't be
 * freed.  Each entry in a list (such as the "global" bound and connected tables
 * and the listener socket's pending list and connected queue) ensures a
 * reference.  When we defer work until process context and pass a socket as our
 * argument, we must ensure the reference count is increased to ensure the
 * socket isn't freed before the function is run; the deferred function will
 * then drop the reference.
 */

#include <linux/types.h>
#include <linux/bitops.h>
#include <linux/cred.h>
#include <linux/init.h>
#include <linux/io.h>
#include <linux/kernel.h>
#include <linux/kmod.h>
#include <linux/list.h>
#include <linux/miscdevice.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/net.h>
#include <linux/poll.h>
#include <linux/skbuff.h>
#include <linux/smp.h>
#include <linux/socket.h>
#include <linux/stddef.h>
#include <linux/unistd.h>
#include <linux/wait.h>
#include <linux/workqueue.h>
#include <net/sock.h>

#include "af_vsock.h"

static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr);
static void vsock_sk_destruct(struct sock *sk);
static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);

/* Protocol family. */
static struct proto vsock_proto = {
	.name = "AF_VSOCK",
	.owner = THIS_MODULE,
	.obj_size = sizeof(struct vsock_sock),
};

/* The default peer timeout indicates how long we will wait for a peer response
 * to a control message.
 */
#define VSOCK_DEFAULT_CONNECT_TIMEOUT (2 * HZ)

#define SS_LISTEN 255

static const struct vsock_transport *transport;
static DEFINE_MUTEX(vsock_register_mutex);

/**** EXPORTS ****/

/* Get the ID of the local context.  This is transport dependent. */

int vm_sockets_get_local_cid(void)
{
	return transport->get_local_cid();
}
EXPORT_SYMBOL_GPL(vm_sockets_get_local_cid);

/**** UTILS ****/

/* Each bound VSocket is stored in the bind hash table and each connected
 * VSocket is stored in the connected hash table.
 *
 * Unbound sockets are all put on the same list attached to the end of the hash
 * table (vsock_unbound_sockets).  Bound sockets are added to the hash table in
 * the bucket that their local address hashes to (vsock_bound_sockets(addr)
 * represents the list that addr hashes to).
 *
 * Specifically, we initialize the vsock_bind_table array to a size of
 * VSOCK_HASH_SIZE + 1 so that vsock_bind_table[0] through
 * vsock_bind_table[VSOCK_HASH_SIZE - 1] are for bound sockets and
 * vsock_bind_table[VSOCK_HASH_SIZE] is for unbound sockets.  The hash function
 * mods with VSOCK_HASH_SIZE - 1 to ensure this.
 */
#define VSOCK_HASH_SIZE         251
#define MAX_PORT_RETRIES        24

#define VSOCK_HASH(addr)        ((addr)->svm_port % (VSOCK_HASH_SIZE - 1))
#define vsock_bound_sockets(addr) (&vsock_bind_table[VSOCK_HASH(addr)])
#define vsock_unbound_sockets     (&vsock_bind_table[VSOCK_HASH_SIZE])

/* XXX This can probably be implemented in a better way. */
#define VSOCK_CONN_HASH(src, dst)				\
	(((src)->svm_cid ^ (dst)->svm_port) % (VSOCK_HASH_SIZE - 1))
#define vsock_connected_sockets(src, dst)		\
	(&vsock_connected_table[VSOCK_CONN_HASH(src, dst)])
#define vsock_connected_sockets_vsk(vsk)				\
	vsock_connected_sockets(&(vsk)->remote_addr, &(vsk)->local_addr)

static struct list_head vsock_bind_table[VSOCK_HASH_SIZE + 1];
static struct list_head vsock_connected_table[VSOCK_HASH_SIZE];
static DEFINE_SPINLOCK(vsock_table_lock);

static __init void vsock_init_tables(void)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(vsock_bind_table); i++)
		INIT_LIST_HEAD(&vsock_bind_table[i]);

	for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++)
		INIT_LIST_HEAD(&vsock_connected_table[i]);
}

static void __vsock_insert_bound(struct list_head *list,
				 struct vsock_sock *vsk)
{
	sock_hold(&vsk->sk);
	list_add(&vsk->bound_table, list);
}

static void __vsock_insert_connected(struct list_head *list,
				     struct vsock_sock *vsk)
{
	sock_hold(&vsk->sk);
	list_add(&vsk->connected_table, list);
}

static void __vsock_remove_bound(struct vsock_sock *vsk)
{
	list_del_init(&vsk->bound_table);
	sock_put(&vsk->sk);
}

static void __vsock_remove_connected(struct vsock_sock *vsk)
{
	list_del_init(&vsk->connected_table);
	sock_put(&vsk->sk);
}

static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr)
{
	struct vsock_sock *vsk;

	list_for_each_entry(vsk, vsock_bound_sockets(addr), bound_table)
		if (vsock_addr_equals_addr_any(addr, &vsk->local_addr))
			return sk_vsock(vsk);

	return NULL;
}

static struct sock *__vsock_find_connected_socket(struct sockaddr_vm *src,
						  struct sockaddr_vm *dst)
{
	struct vsock_sock *vsk;

	list_for_each_entry(vsk, vsock_connected_sockets(src, dst),
			    connected_table) {
		if (vsock_addr_equals_addr(src, &vsk->remote_addr)
		    && vsock_addr_equals_addr(dst, &vsk->local_addr)) {
			return sk_vsock(vsk);
		}
	}

	return NULL;
}

static bool __vsock_in_bound_table(struct vsock_sock *vsk)
{
	return !list_empty(&vsk->bound_table);
}

static bool __vsock_in_connected_table(struct vsock_sock *vsk)
{
	return !list_empty(&vsk->connected_table);
}

static void vsock_insert_unbound(struct vsock_sock *vsk)
{
	spin_lock_bh(&vsock_table_lock);
	__vsock_insert_bound(vsock_unbound_sockets, vsk);
	spin_unlock_bh(&vsock_table_lock);
}

void vsock_insert_connected(struct vsock_sock *vsk)
{
	struct list_head *list = vsock_connected_sockets(
		&vsk->remote_addr, &vsk->local_addr);

	spin_lock_bh(&vsock_table_lock);
	__vsock_insert_connected(list, vsk);
	spin_unlock_bh(&vsock_table_lock);
}
EXPORT_SYMBOL_GPL(vsock_insert_connected);

void vsock_remove_bound(struct vsock_sock *vsk)
{
	spin_lock_bh(&vsock_table_lock);
	__vsock_remove_bound(vsk);
	spin_unlock_bh(&vsock_table_lock);
}
EXPORT_SYMBOL_GPL(vsock_remove_bound);

void vsock_remove_connected(struct vsock_sock *vsk)
{
	spin_lock_bh(&vsock_table_lock);
	__vsock_remove_connected(vsk);
	spin_unlock_bh(&vsock_table_lock);
}
EXPORT_SYMBOL_GPL(vsock_remove_connected);

struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr)
{
	struct sock *sk;

	spin_lock_bh(&vsock_table_lock);
	sk = __vsock_find_bound_socket(addr);
	if (sk)
		sock_hold(sk);

	spin_unlock_bh(&vsock_table_lock);

	return sk;
}
EXPORT_SYMBOL_GPL(vsock_find_bound_socket);

struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
					 struct sockaddr_vm *dst)
{
	struct sock *sk;

	spin_lock_bh(&vsock_table_lock);
	sk = __vsock_find_connected_socket(src, dst);
	if (sk)
		sock_hold(sk);

	spin_unlock_bh(&vsock_table_lock);

	return sk;
}
EXPORT_SYMBOL_GPL(vsock_find_connected_socket);

static bool vsock_in_bound_table(struct vsock_sock *vsk)
{
	bool ret;

	spin_lock_bh(&vsock_table_lock);
	ret = __vsock_in_bound_table(vsk);
	spin_unlock_bh(&vsock_table_lock);

	return ret;
}

static bool vsock_in_connected_table(struct vsock_sock *vsk)
{
	bool ret;

	spin_lock_bh(&vsock_table_lock);
	ret = __vsock_in_connected_table(vsk);
	spin_unlock_bh(&vsock_table_lock);

	return ret;
}

void vsock_for_each_connected_socket(void (*fn)(struct sock *sk))
{
	int i;

	spin_lock_bh(&vsock_table_lock);

	for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++) {
		struct vsock_sock *vsk;
		list_for_each_entry(vsk, &vsock_connected_table[i],
				    connected_table);
			fn(sk_vsock(vsk));
	}

	spin_unlock_bh(&vsock_table_lock);
}
EXPORT_SYMBOL_GPL(vsock_for_each_connected_socket);

void vsock_add_pending(struct sock *listener, struct sock *pending)
{
	struct vsock_sock *vlistener;
	struct vsock_sock *vpending;

	vlistener = vsock_sk(listener);
	vpending = vsock_sk(pending);

	sock_hold(pending);
	sock_hold(listener);
	list_add_tail(&vpending->pending_links, &vlistener->pending_links);
}
EXPORT_SYMBOL_GPL(vsock_add_pending);

void vsock_remove_pending(struct sock *listener, struct sock *pending)
{
	struct vsock_sock *vpending = vsock_sk(pending);

	list_del_init(&vpending->pending_links);
	sock_put(listener);
	sock_put(pending);
}
EXPORT_SYMBOL_GPL(vsock_remove_pending);

void vsock_enqueue_accept(struct sock *listener, struct sock *connected)
{
	struct vsock_sock *vlistener;
	struct vsock_sock *vconnected;

	vlistener = vsock_sk(listener);
	vconnected = vsock_sk(connected);

	sock_hold(connected);
	sock_hold(listener);
	list_add_tail(&vconnected->accept_queue, &vlistener->accept_queue);
}
EXPORT_SYMBOL_GPL(vsock_enqueue_accept);

static struct sock *vsock_dequeue_accept(struct sock *listener)
{
	struct vsock_sock *vlistener;
	struct vsock_sock *vconnected;

	vlistener = vsock_sk(listener);

	if (list_empty(&vlistener->accept_queue))
		return NULL;

	vconnected = list_entry(vlistener->accept_queue.next,
				struct vsock_sock, accept_queue);

	list_del_init(&vconnected->accept_queue);
	sock_put(listener);
	/* The caller will need a reference on the connected socket so we let
	 * it call sock_put().
	 */

	return sk_vsock(vconnected);
}

static bool vsock_is_accept_queue_empty(struct sock *sk)
{
	struct vsock_sock *vsk = vsock_sk(sk);
	return list_empty(&vsk->accept_queue);
}

static bool vsock_is_pending(struct sock *sk)
{
	struct vsock_sock *vsk = vsock_sk(sk);
	return !list_empty(&vsk->pending_links);
}

static int vsock_send_shutdown(struct sock *sk, int mode)
{
	return transport->shutdown(vsock_sk(sk), mode);
}

void vsock_pending_work(struct work_struct *work)
{
	struct sock *sk;
	struct sock *listener;
	struct vsock_sock *vsk;
	bool cleanup;

	vsk = container_of(work, struct vsock_sock, dwork.work);
	sk = sk_vsock(vsk);
	listener = vsk->listener;
	cleanup = true;

	lock_sock(listener);
	lock_sock(sk);

	if (vsock_is_pending(sk)) {
		vsock_remove_pending(listener, sk);
	} else if (!vsk->rejected) {
		/* We are not on the pending list and accept() did not reject
		 * us, so we must have been accepted by our user process.  We
		 * just need to drop our references to the sockets and be on
		 * our way.
		 */
		cleanup = false;
		goto out;
	}

	listener->sk_ack_backlog--;

	/* We need to remove ourself from the global connected sockets list so
	 * incoming packets can't find this socket, and to reduce the reference
	 * count.
	 */
	if (vsock_in_connected_table(vsk))
		vsock_remove_connected(vsk);

	sk->sk_state = SS_FREE;

out:
	release_sock(sk);
	release_sock(listener);
	if (cleanup)
		sock_put(sk);

	sock_put(sk);
	sock_put(listener);
}
EXPORT_SYMBOL_GPL(vsock_pending_work);

/**** SOCKET OPERATIONS ****/

static int __vsock_bind_stream(struct vsock_sock *vsk,
			       struct sockaddr_vm *addr)
{
	static u32 port = LAST_RESERVED_PORT + 1;
	struct sockaddr_vm new_addr;

	vsock_addr_init(&new_addr, addr->svm_cid, addr->svm_port);

	if (addr->svm_port == VMADDR_PORT_ANY) {
		bool found = false;
		unsigned int i;

		for (i = 0; i < MAX_PORT_RETRIES; i++) {
			if (port <= LAST_RESERVED_PORT)
				port = LAST_RESERVED_PORT + 1;

			new_addr.svm_port = port++;

			if (!__vsock_find_bound_socket(&new_addr)) {
				found = true;
				break;
			}
		}

		if (!found)
			return -EADDRNOTAVAIL;
	} else {
		/* If port is in reserved range, ensure caller
		 * has necessary privileges.
		 */
		if (addr->svm_port <= LAST_RESERVED_PORT &&
		    !capable(CAP_NET_BIND_SERVICE)) {
			return -EACCES;
		}

		if (__vsock_find_bound_socket(&new_addr))
			return -EADDRINUSE;
	}

	vsock_addr_init(&vsk->local_addr, new_addr.svm_cid, new_addr.svm_port);

	/* Remove stream sockets from the unbound list and add them to the hash
	 * table for easy lookup by its address.  The unbound list is simply an
	 * extra entry at the end of the hash table, a trick used by AF_UNIX.
	 */
	__vsock_remove_bound(vsk);
	__vsock_insert_bound(vsock_bound_sockets(&vsk->local_addr), vsk);

	return 0;
}

static int __vsock_bind_dgram(struct vsock_sock *vsk,
			      struct sockaddr_vm *addr)
{
	return transport->dgram_bind(vsk, addr);
}

static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr)
{
	struct vsock_sock *vsk = vsock_sk(sk);
	u32 cid;
	int retval;

	/* First ensure this socket isn't already bound. */
	if (vsock_addr_bound(&vsk->local_addr))
		return -EINVAL;

	/* Now bind to the provided address or select appropriate values if
	 * none are provided (VMADDR_CID_ANY and VMADDR_PORT_ANY).  Note that
	 * like AF_INET prevents binding to a non-local IP address (in most
	 * cases), we only allow binding to the local CID.
	 */
	cid = transport->get_local_cid();
	if (addr->svm_cid != cid && addr->svm_cid != VMADDR_CID_ANY)
		return -EADDRNOTAVAIL;

	switch (sk->sk_socket->type) {
	case SOCK_STREAM:
		spin_lock_bh(&vsock_table_lock);
		retval = __vsock_bind_stream(vsk, addr);
		spin_unlock_bh(&vsock_table_lock);
		break;

	case SOCK_DGRAM:
		retval = __vsock_bind_dgram(vsk, addr);
		break;

	default:
		retval = -EINVAL;
		break;
	}

	return retval;
}

struct sock *__vsock_create(struct net *net,
			    struct socket *sock,
			    struct sock *parent,
			    gfp_t priority,
			    unsigned short type)
{
	struct sock *sk;
	struct vsock_sock *psk;
	struct vsock_sock *vsk;

	sk = sk_alloc(net, AF_VSOCK, priority, &vsock_proto);
	if (!sk)
		return NULL;

	sock_init_data(sock, sk);

	/* sk->sk_type is normally set in sock_init_data, but only if sock is
	 * non-NULL. We make sure that our sockets always have a type by
	 * setting it here if needed.
	 */
	if (!sock)
		sk->sk_type = type;

	vsk = vsock_sk(sk);
	vsock_addr_init(&vsk->local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY);
	vsock_addr_init(&vsk->remote_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY);

	sk->sk_destruct = vsock_sk_destruct;
	sk->sk_backlog_rcv = vsock_queue_rcv_skb;
	sk->sk_state = 0;
	sock_reset_flag(sk, SOCK_DONE);

	INIT_LIST_HEAD(&vsk->bound_table);
	INIT_LIST_HEAD(&vsk->connected_table);
	vsk->listener = NULL;
	INIT_LIST_HEAD(&vsk->pending_links);
	INIT_LIST_HEAD(&vsk->accept_queue);
	vsk->rejected = false;
	vsk->sent_request = false;
	vsk->ignore_connecting_rst = false;
	vsk->peer_shutdown = 0;

	psk = parent ? vsock_sk(parent) : NULL;
	if (parent) {
		vsk->trusted = psk->trusted;
		vsk->owner = get_cred(psk->owner);
		vsk->connect_timeout = psk->connect_timeout;
	} else {
		vsk->trusted = capable(CAP_NET_ADMIN);
		vsk->owner = get_current_cred();
		vsk->connect_timeout = VSOCK_DEFAULT_CONNECT_TIMEOUT;
	}

	if (transport->init(vsk, psk) < 0) {
		sk_free(sk);
		return NULL;
	}

	if (sock)
		vsock_insert_unbound(vsk);

	return sk;
}
EXPORT_SYMBOL_GPL(__vsock_create);

static void __vsock_release(struct sock *sk)
{
	if (sk) {
		struct sk_buff *skb;
		struct sock *pending;
		struct vsock_sock *vsk;

		vsk = vsock_sk(sk);
		pending = NULL;	/* Compiler warning. */

		if (vsock_in_bound_table(vsk))
			vsock_remove_bound(vsk);

		if (vsock_in_connected_table(vsk))
			vsock_remove_connected(vsk);

		transport->release(vsk);

		lock_sock(sk);
		sock_orphan(sk);
		sk->sk_shutdown = SHUTDOWN_MASK;

		while ((skb = skb_dequeue(&sk->sk_receive_queue)))
			kfree_skb(skb);

		/* Clean up any sockets that never were accepted. */
		while ((pending = vsock_dequeue_accept(sk)) != NULL) {
			__vsock_release(pending);
			sock_put(pending);
		}

		release_sock(sk);
		sock_put(sk);
	}
}

static void vsock_sk_destruct(struct sock *sk)
{
	struct vsock_sock *vsk = vsock_sk(sk);

	transport->destruct(vsk);

	/* When clearing these addresses, there's no need to set the family and
	 * possibly register the address family with the kernel.
	 */
	vsock_addr_init(&vsk->local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY);
	vsock_addr_init(&vsk->remote_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY);

	put_cred(vsk->owner);
}

static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
	int err;

	err = sock_queue_rcv_skb(sk, skb);
	if (err)
		kfree_skb(skb);

	return err;
}

s64 vsock_stream_has_data(struct vsock_sock *vsk)
{
	return transport->stream_has_data(vsk);
}
EXPORT_SYMBOL_GPL(vsock_stream_has_data);

s64 vsock_stream_has_space(struct vsock_sock *vsk)
{
	return transport->stream_has_space(vsk);
}
EXPORT_SYMBOL_GPL(vsock_stream_has_space);

static int vsock_release(struct socket *sock)
{
	__vsock_release(sock->sk);
	sock->sk = NULL;
	sock->state = SS_FREE;

	return 0;
}

static int
vsock_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
{
	int err;
	struct sock *sk;
	struct sockaddr_vm *vm_addr;

	sk = sock->sk;

	if (vsock_addr_cast(addr, addr_len, &vm_addr) != 0)
		return -EINVAL;

	lock_sock(sk);
	err = __vsock_bind(sk, vm_addr);
	release_sock(sk);

	return err;
}

static int vsock_getname(struct socket *sock,
			 struct sockaddr *addr, int *addr_len, int peer)
{
	int err;
	struct sock *sk;
	struct vsock_sock *vsk;
	struct sockaddr_vm *vm_addr;

	sk = sock->sk;
	vsk = vsock_sk(sk);
	err = 0;

	lock_sock(sk);

	if (peer) {
		if (sock->state != SS_CONNECTED) {
			err = -ENOTCONN;
			goto out;
		}
		vm_addr = &vsk->remote_addr;
	} else {
		vm_addr = &vsk->local_addr;
	}

	if (!vm_addr) {
		err = -EINVAL;
		goto out;
	}

	/* sys_getsockname() and sys_getpeername() pass us a
	 * MAX_SOCK_ADDR-sized buffer and don't set addr_len.  Unfortunately
	 * that macro is defined in socket.c instead of .h, so we hardcode its
	 * value here.
	 */
	BUILD_BUG_ON(sizeof(*vm_addr) > 128);
	memcpy(addr, vm_addr, sizeof(*vm_addr));
	*addr_len = sizeof(*vm_addr);

out:
	release_sock(sk);
	return err;
}

static int vsock_shutdown(struct socket *sock, int mode)
{
	int err;
	struct sock *sk;

	/* User level uses SHUT_RD (0) and SHUT_WR (1), but the kernel uses
	 * RCV_SHUTDOWN (1) and SEND_SHUTDOWN (2), so we must increment mode
	 * here like the other address families do.  Note also that the
	 * increment makes SHUT_RDWR (2) into RCV_SHUTDOWN | SEND_SHUTDOWN (3),
	 * which is what we want.
	 */
	mode++;

	if ((mode & ~SHUTDOWN_MASK) || !mode)
		return -EINVAL;

	/* If this is a STREAM socket and it is not connected then bail out
	 * immediately.  If it is a DGRAM socket then we must first kick the
	 * socket so that it wakes up from any sleeping calls, for example
	 * recv(), and then afterwards return the error.
	 */

	sk = sock->sk;
	if (sock->state == SS_UNCONNECTED) {
		err = -ENOTCONN;
		if (sk->sk_type == SOCK_STREAM)
			return err;
	} else {
		sock->state = SS_DISCONNECTING;
		err = 0;
	}

	/* Receive and send shutdowns are treated alike. */
	mode = mode & (RCV_SHUTDOWN | SEND_SHUTDOWN);
	if (mode) {
		lock_sock(sk);
		sk->sk_shutdown |= mode;
		sk->sk_state_change(sk);
		release_sock(sk);

		if (sk->sk_type == SOCK_STREAM) {
			sock_reset_flag(sk, SOCK_DONE);
			vsock_send_shutdown(sk, mode);
		}
	}

	return err;
}

static unsigned int vsock_poll(struct file *file, struct socket *sock,
			       poll_table *wait)
{
	struct sock *sk;
	unsigned int mask;
	struct vsock_sock *vsk;

	sk = sock->sk;
	vsk = vsock_sk(sk);

	poll_wait(file, sk_sleep(sk), wait);
	mask = 0;

	if (sk->sk_err)
		/* Signify that there has been an error on this socket. */
		mask |= POLLERR;

	/* INET sockets treat local write shutdown and peer write shutdown as a
	 * case of POLLHUP set.
	 */
	if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
	    ((sk->sk_shutdown & SEND_SHUTDOWN) &&
	     (vsk->peer_shutdown & SEND_SHUTDOWN))) {
		mask |= POLLHUP;
	}

	if (sk->sk_shutdown & RCV_SHUTDOWN ||
	    vsk->peer_shutdown & SEND_SHUTDOWN) {
		mask |= POLLRDHUP;
	}

	if (sock->type == SOCK_DGRAM) {
		/* For datagram sockets we can read if there is something in
		 * the queue and write as long as the socket isn't shutdown for
		 * sending.
		 */
		if (!skb_queue_empty(&sk->sk_receive_queue) ||
		    (sk->sk_shutdown & RCV_SHUTDOWN)) {
			mask |= POLLIN | POLLRDNORM;
		}

		if (!(sk->sk_shutdown & SEND_SHUTDOWN))
			mask |= POLLOUT | POLLWRNORM | POLLWRBAND;

	} else if (sock->type == SOCK_STREAM) {
		lock_sock(sk);

		/* Listening sockets that have connections in their accept
		 * queue can be read.
		 */
		if (sk->sk_state == SS_LISTEN
		    && !vsock_is_accept_queue_empty(sk))
			mask |= POLLIN | POLLRDNORM;

		/* If there is something in the queue then we can read. */
		if (transport->stream_is_active(vsk) &&
		    !(sk->sk_shutdown & RCV_SHUTDOWN)) {
			bool data_ready_now = false;
			int ret = transport->notify_poll_in(
					vsk, 1, &data_ready_now);
			if (ret < 0) {
				mask |= POLLERR;
			} else {
				if (data_ready_now)
					mask |= POLLIN | POLLRDNORM;

			}
		}

		/* Sockets whose connections have been closed, reset, or
		 * terminated should also be considered read, and we check the
		 * shutdown flag for that.
		 */
		if (sk->sk_shutdown & RCV_SHUTDOWN ||
		    vsk->peer_shutdown & SEND_SHUTDOWN) {
			mask |= POLLIN | POLLRDNORM;
		}

		/* Connected sockets that can produce data can be written. */
		if (sk->sk_state == SS_CONNECTED) {
			if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
				bool space_avail_now = false;
				int ret = transport->notify_poll_out(
						vsk, 1, &space_avail_now);
				if (ret < 0) {
					mask |= POLLERR;
				} else {
					if (space_avail_now)
						/* Remove POLLWRBAND since INET
						 * sockets are not setting it.
						 */
						mask |= POLLOUT | POLLWRNORM;

				}
			}
		}

		/* Simulate INET socket poll behaviors, which sets
		 * POLLOUT|POLLWRNORM when peer is closed and nothing to read,
		 * but local send is not shutdown.
		 */
		if (sk->sk_state == SS_UNCONNECTED) {
			if (!(sk->sk_shutdown & SEND_SHUTDOWN))
				mask |= POLLOUT | POLLWRNORM;

		}

		release_sock(sk);
	}

	return mask;
}

static int vsock_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
			       struct msghdr *msg, size_t len)
{
	int err;
	struct sock *sk;
	struct vsock_sock *vsk;
	struct sockaddr_vm *remote_addr;

	if (msg->msg_flags & MSG_OOB)
		return -EOPNOTSUPP;

	/* For now, MSG_DONTWAIT is always assumed... */
	err = 0;
	sk = sock->sk;
	vsk = vsock_sk(sk);

	lock_sock(sk);

	if (!vsock_addr_bound(&vsk->local_addr)) {
		struct sockaddr_vm local_addr;

		vsock_addr_init(&local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY);
		err = __vsock_bind(sk, &local_addr);
		if (err != 0)
			goto out;

	}

	/* If the provided message contains an address, use that.  Otherwise
	 * fall back on the socket's remote handle (if it has been connected).
	 */
	if (msg->msg_name &&
	    vsock_addr_cast(msg->msg_name, msg->msg_namelen,
			    &remote_addr) == 0) {
		/* Ensure this address is of the right type and is a valid
		 * destination.
		 */

		if (remote_addr->svm_cid == VMADDR_CID_ANY)
			remote_addr->svm_cid = transport->get_local_cid();

		if (!vsock_addr_bound(remote_addr)) {
			err = -EINVAL;
			goto out;
		}
	} else if (sock->state == SS_CONNECTED) {
		remote_addr = &vsk->remote_addr;

		if (remote_addr->svm_cid == VMADDR_CID_ANY)
			remote_addr->svm_cid = transport->get_local_cid();

		/* XXX Should connect() or this function ensure remote_addr is
		 * bound?
		 */
		if (!vsock_addr_bound(&vsk->remote_addr)) {
			err = -EINVAL;
			goto out;
		}
	} else {
		err = -EINVAL;
		goto out;
	}

	if (!transport->dgram_allow(remote_addr->svm_cid,
				    remote_addr->svm_port)) {
		err = -EINVAL;
		goto out;
	}

	err = transport->dgram_enqueue(vsk, remote_addr, msg->msg_iov, len);

out:
	release_sock(sk);
	return err;
}

static int vsock_dgram_connect(struct socket *sock,
			       struct sockaddr *addr, int addr_len, int flags)
{
	int err;
	struct sock *sk;
	struct vsock_sock *vsk;
	struct sockaddr_vm *remote_addr;

	sk = sock->sk;
	vsk = vsock_sk(sk);

	err = vsock_addr_cast(addr, addr_len, &remote_addr);
	if (err == -EAFNOSUPPORT && remote_addr->svm_family == AF_UNSPEC) {
		lock_sock(sk);
		vsock_addr_init(&vsk->remote_addr, VMADDR_CID_ANY,
				VMADDR_PORT_ANY);
		sock->state = SS_UNCONNECTED;
		release_sock(sk);
		return 0;
	} else if (err != 0)
		return -EINVAL;

	lock_sock(sk);

	if (!vsock_addr_bound(&vsk->local_addr)) {
		struct sockaddr_vm local_addr;

		vsock_addr_init(&local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY);
		err = __vsock_bind(sk, &local_addr);
		if (err != 0)
			goto out;

	}

	if (!transport->dgram_allow(remote_addr->svm_cid,
				    remote_addr->svm_port)) {
		err = -EINVAL;
		goto out;
	}

	memcpy(&vsk->remote_addr, remote_addr, sizeof(vsk->remote_addr));
	sock->state = SS_CONNECTED;

out:
	release_sock(sk);
	return err;
}

static int vsock_dgram_recvmsg(struct kiocb *kiocb, struct socket *sock,
			       struct msghdr *msg, size_t len, int flags)
{
	return transport->dgram_dequeue(kiocb, vsock_sk(sock->sk), msg, len,
					flags);
}

static const struct proto_ops vsock_dgram_ops = {
	.family = PF_VSOCK,
	.owner = THIS_MODULE,
	.release = vsock_release,
	.bind = vsock_bind,
	.connect = vsock_dgram_connect,
	.socketpair = sock_no_socketpair,
	.accept = sock_no_accept,
	.getname = vsock_getname,
	.poll = vsock_poll,
	.ioctl = sock_no_ioctl,
	.listen = sock_no_listen,
	.shutdown = vsock_shutdown,
	.setsockopt = sock_no_setsockopt,
	.getsockopt = sock_no_getsockopt,
	.sendmsg = vsock_dgram_sendmsg,
	.recvmsg = vsock_dgram_recvmsg,
	.mmap = sock_no_mmap,
	.sendpage = sock_no_sendpage,
};

static void vsock_connect_timeout(struct work_struct *work)
{
	struct sock *sk;
	struct vsock_sock *vsk;

	vsk = container_of(work, struct vsock_sock, dwork.work);
	sk = sk_vsock(vsk);

	lock_sock(sk);
	if (sk->sk_state == SS_CONNECTING &&
	    (sk->sk_shutdown != SHUTDOWN_MASK)) {
		sk->sk_state = SS_UNCONNECTED;
		sk->sk_err = ETIMEDOUT;
		sk->sk_error_report(sk);
	}
	release_sock(sk);

	sock_put(sk);
}

static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
				int addr_len, int flags)
{
	int err;
	struct sock *sk;
	struct vsock_sock *vsk;
	struct sockaddr_vm *remote_addr;
	long timeout;
	DEFINE_WAIT(wait);

	err = 0;
	sk = sock->sk;
	vsk = vsock_sk(sk);

	lock_sock(sk);

	/* XXX AF_UNSPEC should make us disconnect like AF_INET. */
	switch (sock->state) {
	case SS_CONNECTED:
		err = -EISCONN;
		goto out;
	case SS_DISCONNECTING:
		err = -EINVAL;
		goto out;
	case SS_CONNECTING:
		/* This continues on so we can move sock into the SS_CONNECTED
		 * state once the connection has completed (at which point err
		 * will be set to zero also).  Otherwise, we will either wait
		 * for the connection or return -EALREADY should this be a
		 * non-blocking call.
		 */
		err = -EALREADY;
		break;
	default:
		if ((sk->sk_state == SS_LISTEN) ||
		    vsock_addr_cast(addr, addr_len, &remote_addr) != 0) {
			err = -EINVAL;
			goto out;
		}

		/* The hypervisor and well-known contexts do not have socket
		 * endpoints.
		 */
		if (!transport->stream_allow(remote_addr->svm_cid,
					     remote_addr->svm_port)) {
			err = -ENETUNREACH;
			goto out;
		}

		/* Set the remote address that we are connecting to. */
		memcpy(&vsk->remote_addr, remote_addr,
		       sizeof(vsk->remote_addr));

		/* Autobind this socket to the local address if necessary. */
		if (!vsock_addr_bound(&vsk->local_addr)) {
			struct sockaddr_vm local_addr;

			vsock_addr_init(&local_addr, VMADDR_CID_ANY,
					VMADDR_PORT_ANY);
			err = __vsock_bind(sk, &local_addr);
			if (err != 0)
				goto out;

		}

		sk->sk_state = SS_CONNECTING;

		err = transport->connect(vsk);
		if (err < 0)
			goto out;

		/* Mark sock as connecting and set the error code to in
		 * progress in case this is a non-blocking connect.
		 */
		sock->state = SS_CONNECTING;
		err = -EINPROGRESS;
	}

	/* The receive path will handle all communication until we are able to
	 * enter the connected state.  Here we wait for the connection to be
	 * completed or a notification of an error.
	 */
	timeout = vsk->connect_timeout;
	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);

	while (sk->sk_state != SS_CONNECTED && sk->sk_err == 0) {
		if (flags & O_NONBLOCK) {
			/* If we're not going to block, we schedule a timeout
			 * function to generate a timeout on the connection
			 * attempt, in case the peer doesn't respond in a
			 * timely manner. We hold on to the socket until the
			 * timeout fires.
			 */
			sock_hold(sk);
			INIT_DELAYED_WORK(&vsk->dwork,
					  vsock_connect_timeout);
			schedule_delayed_work(&vsk->dwork, timeout);

			/* Skip ahead to preserve error code set above. */
			goto out_wait;
		}

		release_sock(sk);
		timeout = schedule_timeout(timeout);
		lock_sock(sk);

		if (signal_pending(current)) {
			err = sock_intr_errno(timeout);
			goto out_wait_error;
		} else if (timeout == 0) {
			err = -ETIMEDOUT;
			goto out_wait_error;
		}

		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
	}

	if (sk->sk_err) {
		err = -sk->sk_err;
		goto out_wait_error;
	} else
		err = 0;

out_wait:
	finish_wait(sk_sleep(sk), &wait);
out:
	release_sock(sk);
	return err;

out_wait_error:
	sk->sk_state = SS_UNCONNECTED;
	sock->state = SS_UNCONNECTED;
	goto out_wait;
}

static int vsock_accept(struct socket *sock, struct socket *newsock, int flags)
{
	struct sock *listener;
	int err;
	struct sock *connected;
	struct vsock_sock *vconnected;
	long timeout;
	DEFINE_WAIT(wait);

	err = 0;
	listener = sock->sk;

	lock_sock(listener);

	if (sock->type != SOCK_STREAM) {
		err = -EOPNOTSUPP;
		goto out;
	}

	if (listener->sk_state != SS_LISTEN) {
		err = -EINVAL;
		goto out;
	}

	/* Wait for children sockets to appear; these are the new sockets
	 * created upon connection establishment.
	 */
	timeout = sock_sndtimeo(listener, flags & O_NONBLOCK);
	prepare_to_wait(sk_sleep(listener), &wait, TASK_INTERRUPTIBLE);

	while ((connected = vsock_dequeue_accept(listener)) == NULL &&
	       listener->sk_err == 0) {
		release_sock(listener);
		timeout = schedule_timeout(timeout);
		lock_sock(listener);

		if (signal_pending(current)) {
			err = sock_intr_errno(timeout);
			goto out_wait;
		} else if (timeout == 0) {
			err = -EAGAIN;
			goto out_wait;
		}

		prepare_to_wait(sk_sleep(listener), &wait, TASK_INTERRUPTIBLE);
	}

	if (listener->sk_err)
		err = -listener->sk_err;

	if (connected) {
		listener->sk_ack_backlog--;

		lock_sock(connected);
		vconnected = vsock_sk(connected);

		/* If the listener socket has received an error, then we should
		 * reject this socket and return.  Note that we simply mark the
		 * socket rejected, drop our reference, and let the cleanup
		 * function handle the cleanup; the fact that we found it in
		 * the listener's accept queue guarantees that the cleanup
		 * function hasn't run yet.
		 */
		if (err) {
			vconnected->rejected = true;
			release_sock(connected);
			sock_put(connected);
			goto out_wait;
		}

		newsock->state = SS_CONNECTED;
		sock_graft(connected, newsock);
		release_sock(connected);
		sock_put(connected);
	}

out_wait:
	finish_wait(sk_sleep(listener), &wait);
out:
	release_sock(listener);
	return err;
}

static int vsock_listen(struct socket *sock, int backlog)
{
	int err;
	struct sock *sk;
	struct vsock_sock *vsk;

	sk = sock->sk;

	lock_sock(sk);

	if (sock->type != SOCK_STREAM) {
		err = -EOPNOTSUPP;
		goto out;
	}

	if (sock->state != SS_UNCONNECTED) {
		err = -EINVAL;
		goto out;
	}

	vsk = vsock_sk(sk);

	if (!vsock_addr_bound(&vsk->local_addr)) {
		err = -EINVAL;
		goto out;
	}

	sk->sk_max_ack_backlog = backlog;
	sk->sk_state = SS_LISTEN;

	err = 0;

out:
	release_sock(sk);
	return err;
}

static int vsock_stream_setsockopt(struct socket *sock,
				   int level,
				   int optname,
				   char __user *optval,
				   unsigned int optlen)
{
	int err;
	struct sock *sk;
	struct vsock_sock *vsk;
	u64 val;

	if (level != AF_VSOCK)
		return -ENOPROTOOPT;

#define COPY_IN(_v)                                       \
	do {						  \
		if (optlen < sizeof(_v)) {		  \
			err = -EINVAL;			  \
			goto exit;			  \
		}					  \
		if (copy_from_user(&_v, optval, sizeof(_v)) != 0) {	\
			err = -EFAULT;					\
			goto exit;					\
		}							\
	} while (0)

	err = 0;
	sk = sock->sk;
	vsk = vsock_sk(sk);

	lock_sock(sk);

	switch (optname) {
	case SO_VM_SOCKETS_BUFFER_SIZE:
		COPY_IN(val);
		transport->set_buffer_size(vsk, val);
		break;

	case SO_VM_SOCKETS_BUFFER_MAX_SIZE:
		COPY_IN(val);
		transport->set_max_buffer_size(vsk, val);
		break;

	case SO_VM_SOCKETS_BUFFER_MIN_SIZE:
		COPY_IN(val);
		transport->set_min_buffer_size(vsk, val);
		break;

	case SO_VM_SOCKETS_CONNECT_TIMEOUT: {
		struct timeval tv;
		COPY_IN(tv);
		if (tv.tv_sec >= 0 && tv.tv_usec < USEC_PER_SEC &&
		    tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)) {
			vsk->connect_timeout = tv.tv_sec * HZ +
			    DIV_ROUND_UP(tv.tv_usec, (1000000 / HZ));
			if (vsk->connect_timeout == 0)
				vsk->connect_timeout =
				    VSOCK_DEFAULT_CONNECT_TIMEOUT;

		} else {
			err = -ERANGE;
		}
		break;
	}

	default:
		err = -ENOPROTOOPT;
		break;
	}

#undef COPY_IN

exit:
	release_sock(sk);
	return err;
}

static int vsock_stream_getsockopt(struct socket *sock,
				   int level, int optname,
				   char __user *optval,
				   int __user *optlen)
{
	int err;
	int len;
	struct sock *sk;
	struct vsock_sock *vsk;
	u64 val;

	if (level != AF_VSOCK)
		return -ENOPROTOOPT;

	err = get_user(len, optlen);
	if (err != 0)
		return err;

#define COPY_OUT(_v)                            \
	do {					\
		if (len < sizeof(_v))		\
			return -EINVAL;		\
						\
		len = sizeof(_v);		\
		if (copy_to_user(optval, &_v, len) != 0)	\
			return -EFAULT;				\
								\
	} while (0)

	err = 0;
	sk = sock->sk;
	vsk = vsock_sk(sk);

	switch (optname) {
	case SO_VM_SOCKETS_BUFFER_SIZE:
		val = transport->get_buffer_size(vsk);
		COPY_OUT(val);
		break;

	case SO_VM_SOCKETS_BUFFER_MAX_SIZE:
		val = transport->get_max_buffer_size(vsk);
		COPY_OUT(val);
		break;

	case SO_VM_SOCKETS_BUFFER_MIN_SIZE:
		val = transport->get_min_buffer_size(vsk);
		COPY_OUT(val);
		break;

	case SO_VM_SOCKETS_CONNECT_TIMEOUT: {
		struct timeval tv;
		tv.tv_sec = vsk->connect_timeout / HZ;
		tv.tv_usec =
		    (vsk->connect_timeout -
		     tv.tv_sec * HZ) * (1000000 / HZ);
		COPY_OUT(tv);
		break;
	}
	default:
		return -ENOPROTOOPT;
	}

	err = put_user(len, optlen);
	if (err != 0)
		return -EFAULT;

#undef COPY_OUT

	return 0;
}

static int vsock_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
				struct msghdr *msg, size_t len)
{
	struct sock *sk;
	struct vsock_sock *vsk;
	ssize_t total_written;
	long timeout;
	int err;
	struct vsock_transport_send_notify_data send_data;

	DEFINE_WAIT(wait);

	sk = sock->sk;
	vsk = vsock_sk(sk);
	total_written = 0;
	err = 0;

	if (msg->msg_flags & MSG_OOB)
		return -EOPNOTSUPP;

	lock_sock(sk);

	/* Callers should not provide a destination with stream sockets. */
	if (msg->msg_namelen) {
		err = sk->sk_state == SS_CONNECTED ? -EISCONN : -EOPNOTSUPP;
		goto out;
	}

	/* Send data only if both sides are not shutdown in the direction. */
	if (sk->sk_shutdown & SEND_SHUTDOWN ||
	    vsk->peer_shutdown & RCV_SHUTDOWN) {
		err = -EPIPE;
		goto out;
	}

	if (sk->sk_state != SS_CONNECTED ||
	    !vsock_addr_bound(&vsk->local_addr)) {
		err = -ENOTCONN;
		goto out;
	}

	if (!vsock_addr_bound(&vsk->remote_addr)) {
		err = -EDESTADDRREQ;
		goto out;
	}

	/* Wait for room in the produce queue to enqueue our user's data. */
	timeout = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);

	err = transport->notify_send_init(vsk, &send_data);
	if (err < 0)
		goto out;

	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);

	while (total_written < len) {
		ssize_t written;

		while (vsock_stream_has_space(vsk) == 0 &&
		       sk->sk_err == 0 &&
		       !(sk->sk_shutdown & SEND_SHUTDOWN) &&
		       !(vsk->peer_shutdown & RCV_SHUTDOWN)) {

			/* Don't wait for non-blocking sockets. */
			if (timeout == 0) {
				err = -EAGAIN;
				goto out_wait;
			}

			err = transport->notify_send_pre_block(vsk, &send_data);
			if (err < 0)
				goto out_wait;

			release_sock(sk);
			timeout = schedule_timeout(timeout);
			lock_sock(sk);
			if (signal_pending(current)) {
				err = sock_intr_errno(timeout);
				goto out_wait;
			} else if (timeout == 0) {
				err = -EAGAIN;
				goto out_wait;
			}

			prepare_to_wait(sk_sleep(sk), &wait,
					TASK_INTERRUPTIBLE);
		}

		/* These checks occur both as part of and after the loop
		 * conditional since we need to check before and after
		 * sleeping.
		 */
		if (sk->sk_err) {
			err = -sk->sk_err;
			goto out_wait;
		} else if ((sk->sk_shutdown & SEND_SHUTDOWN) ||
			   (vsk->peer_shutdown & RCV_SHUTDOWN)) {
			err = -EPIPE;
			goto out_wait;
		}

		err = transport->notify_send_pre_enqueue(vsk, &send_data);
		if (err < 0)
			goto out_wait;

		/* Note that enqueue will only write as many bytes as are free
		 * in the produce queue, so we don't need to ensure len is
		 * smaller than the queue size.  It is the caller's
		 * responsibility to check how many bytes we were able to send.
		 */

		written = transport->stream_enqueue(
				vsk, msg->msg_iov,
				len - total_written);
		if (written < 0) {
			err = -ENOMEM;
			goto out_wait;
		}

		total_written += written;

		err = transport->notify_send_post_enqueue(
				vsk, written, &send_data);
		if (err < 0)
			goto out_wait;

	}

out_wait:
	if (total_written > 0)
		err = total_written;
	finish_wait(sk_sleep(sk), &wait);
out:
	release_sock(sk);
	return err;
}


static int
vsock_stream_recvmsg(struct kiocb *kiocb,
		     struct socket *sock,
		     struct msghdr *msg, size_t len, int flags)
{
	struct sock *sk;
	struct vsock_sock *vsk;
	int err;
	size_t target;
	ssize_t copied;
	long timeout;
	struct vsock_transport_recv_notify_data recv_data;

	DEFINE_WAIT(wait);

	sk = sock->sk;
	vsk = vsock_sk(sk);
	err = 0;

	lock_sock(sk);

	if (sk->sk_state != SS_CONNECTED) {
		/* Recvmsg is supposed to return 0 if a peer performs an
		 * orderly shutdown. Differentiate between that case and when a
		 * peer has not connected or a local shutdown occured with the
		 * SOCK_DONE flag.
		 */
		if (sock_flag(sk, SOCK_DONE))
			err = 0;
		else
			err = -ENOTCONN;

		goto out;
	}

	if (flags & MSG_OOB) {
		err = -EOPNOTSUPP;
		goto out;
	}

	/* We don't check peer_shutdown flag here since peer may actually shut
	 * down, but there can be data in the queue that a local socket can
	 * receive.
	 */
	if (sk->sk_shutdown & RCV_SHUTDOWN) {
		err = 0;
		goto out;
	}

	/* It is valid on Linux to pass in a zero-length receive buffer.  This
	 * is not an error.  We may as well bail out now.
	 */
	if (!len) {
		err = 0;
		goto out;
	}

	/* We must not copy less than target bytes into the user's buffer
	 * before returning successfully, so we wait for the consume queue to
	 * have that much data to consume before dequeueing.  Note that this
	 * makes it impossible to handle cases where target is greater than the
	 * queue size.
	 */
	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
	if (target >= transport->stream_rcvhiwat(vsk)) {
		err = -ENOMEM;
		goto out;
	}
	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
	copied = 0;

	err = transport->notify_recv_init(vsk, target, &recv_data);
	if (err < 0)
		goto out;

	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);

	while (1) {
		s64 ready = vsock_stream_has_data(vsk);

		if (ready < 0) {
			/* Invalid queue pair content. XXX This should be
			 * changed to a connection reset in a later change.
			 */

			err = -ENOMEM;
			goto out_wait;
		} else if (ready > 0) {
			ssize_t read;

			err = transport->notify_recv_pre_dequeue(
					vsk, target, &recv_data);
			if (err < 0)
				break;

			read = transport->stream_dequeue(
					vsk, msg->msg_iov,
					len - copied, flags);
			if (read < 0) {
				err = -ENOMEM;
				break;
			}

			copied += read;

			err = transport->notify_recv_post_dequeue(
					vsk, target, read,
					!(flags & MSG_PEEK), &recv_data);
			if (err < 0)
				goto out_wait;

			if (read >= target || flags & MSG_PEEK)
				break;

			target -= read;
		} else {
			if (sk->sk_err != 0 || (sk->sk_shutdown & RCV_SHUTDOWN)
			    || (vsk->peer_shutdown & SEND_SHUTDOWN)) {
				break;
			}
			/* Don't wait for non-blocking sockets. */
			if (timeout == 0) {
				err = -EAGAIN;
				break;
			}

			err = transport->notify_recv_pre_block(
					vsk, target, &recv_data);
			if (err < 0)
				break;

			release_sock(sk);
			timeout = schedule_timeout(timeout);
			lock_sock(sk);

			if (signal_pending(current)) {
				err = sock_intr_errno(timeout);
				break;
			} else if (timeout == 0) {
				err = -EAGAIN;
				break;
			}

			prepare_to_wait(sk_sleep(sk), &wait,
					TASK_INTERRUPTIBLE);
		}
	}

	if (sk->sk_err)
		err = -sk->sk_err;
	else if (sk->sk_shutdown & RCV_SHUTDOWN)
		err = 0;

	if (copied > 0) {
		/* We only do these additional bookkeeping/notification steps
		 * if we actually copied something out of the queue pair
		 * instead of just peeking ahead.
		 */

		if (!(flags & MSG_PEEK)) {
			/* If the other side has shutdown for sending and there
			 * is nothing more to read, then modify the socket
			 * state.
			 */
			if (vsk->peer_shutdown & SEND_SHUTDOWN) {
				if (vsock_stream_has_data(vsk) <= 0) {
					sk->sk_state = SS_UNCONNECTED;
					sock_set_flag(sk, SOCK_DONE);
					sk->sk_state_change(sk);
				}
			}
		}
		err = copied;
	}

out_wait:
	finish_wait(sk_sleep(sk), &wait);
out:
	release_sock(sk);
	return err;
}

static const struct proto_ops vsock_stream_ops = {
	.family = PF_VSOCK,
	.owner = THIS_MODULE,
	.release = vsock_release,
	.bind = vsock_bind,
	.connect = vsock_stream_connect,
	.socketpair = sock_no_socketpair,
	.accept = vsock_accept,
	.getname = vsock_getname,
	.poll = vsock_poll,
	.ioctl = sock_no_ioctl,
	.listen = vsock_listen,
	.shutdown = vsock_shutdown,
	.setsockopt = vsock_stream_setsockopt,
	.getsockopt = vsock_stream_getsockopt,
	.sendmsg = vsock_stream_sendmsg,
	.recvmsg = vsock_stream_recvmsg,
	.mmap = sock_no_mmap,
	.sendpage = sock_no_sendpage,
};

static int vsock_create(struct net *net, struct socket *sock,
			int protocol, int kern)
{
	if (!sock)
		return -EINVAL;

	if (protocol && protocol != PF_VSOCK)
		return -EPROTONOSUPPORT;

	switch (sock->type) {
	case SOCK_DGRAM:
		sock->ops = &vsock_dgram_ops;
		break;
	case SOCK_STREAM:
		sock->ops = &vsock_stream_ops;
		break;
	default:
		return -ESOCKTNOSUPPORT;
	}

	sock->state = SS_UNCONNECTED;

	return __vsock_create(net, sock, NULL, GFP_KERNEL, 0) ? 0 : -ENOMEM;
}

static const struct net_proto_family vsock_family_ops = {
	.family = AF_VSOCK,
	.create = vsock_create,
	.owner = THIS_MODULE,
};

static long vsock_dev_do_ioctl(struct file *filp,
			       unsigned int cmd, void __user *ptr)
{
	u32 __user *p = ptr;
	int retval = 0;

	switch (cmd) {
	case IOCTL_VM_SOCKETS_GET_LOCAL_CID:
		if (put_user(transport->get_local_cid(), p) != 0)
			retval = -EFAULT;
		break;

	default:
		pr_err("Unknown ioctl %d\n", cmd);
		retval = -EINVAL;
	}

	return retval;
}

static long vsock_dev_ioctl(struct file *filp,
			    unsigned int cmd, unsigned long arg)
{
	return vsock_dev_do_ioctl(filp, cmd, (void __user *)arg);
}

#ifdef CONFIG_COMPAT
static long vsock_dev_compat_ioctl(struct file *filp,
				   unsigned int cmd, unsigned long arg)
{
	return vsock_dev_do_ioctl(filp, cmd, compat_ptr(arg));
}
#endif

static const struct file_operations vsock_device_ops = {
	.owner		= THIS_MODULE,
	.unlocked_ioctl	= vsock_dev_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= vsock_dev_compat_ioctl,
#endif
	.open		= nonseekable_open,
};

static struct miscdevice vsock_device = {
	.name		= "vsock",
	.minor		= MISC_DYNAMIC_MINOR,
	.fops		= &vsock_device_ops,
};

static int __vsock_core_init(void)
{
	int err;

	vsock_init_tables();

	err = misc_register(&vsock_device);
	if (err) {
		pr_err("Failed to register misc device\n");
		return -ENOENT;
	}

	err = proto_register(&vsock_proto, 1);	/* we want our slab */
	if (err) {
		pr_err("Cannot register vsock protocol\n");
		goto err_misc_deregister;
	}

	err = sock_register(&vsock_family_ops);
	if (err) {
		pr_err("could not register af_vsock (%d) address family: %d\n",
		       AF_VSOCK, err);
		goto err_unregister_proto;
	}

	return 0;

err_unregister_proto:
	proto_unregister(&vsock_proto);
err_misc_deregister:
	misc_deregister(&vsock_device);
	return err;
}

int vsock_core_init(const struct vsock_transport *t)
{
	int retval = mutex_lock_interruptible(&vsock_register_mutex);
	if (retval)
		return retval;

	if (transport) {
		retval = -EBUSY;
		goto out;
	}

	transport = t;
	retval = __vsock_core_init();
	if (retval)
		transport = NULL;

out:
	mutex_unlock(&vsock_register_mutex);
	return retval;
}
EXPORT_SYMBOL_GPL(vsock_core_init);

void vsock_core_exit(void)
{
	mutex_lock(&vsock_register_mutex);

	misc_deregister(&vsock_device);
	sock_unregister(AF_VSOCK);
	proto_unregister(&vsock_proto);

	/* We do not want the assignment below re-ordered. */
	mb();
	transport = NULL;

	mutex_unlock(&vsock_register_mutex);
}
EXPORT_SYMBOL_GPL(vsock_core_exit);

MODULE_AUTHOR("VMware, Inc.");
MODULE_DESCRIPTION("VMware Virtual Socket Family");
MODULE_VERSION("1.0.0.0-k");
MODULE_LICENSE("GPL v2");