aboutsummaryrefslogtreecommitdiff
path: root/net/tipc/socket.c
blob: e741416d1d24d4655cd4096b07f84cd978c90cc7 (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
/*
 * net/tipc/socket.c: TIPC socket API
 *
 * Copyright (c) 2001-2007, 2012 Ericsson AB
 * Copyright (c) 2004-2008, 2010-2013, Wind River Systems
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. Neither the names of the copyright holders nor the names of its
 *    contributors may be used to endorse or promote products derived from
 *    this software without specific prior written permission.
 *
 * Alternatively, this software may be distributed under the terms of the
 * GNU General Public License ("GPL") version 2 as published by the Free
 * Software Foundation.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
 * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
 * POSSIBILITY OF SUCH DAMAGE.
 */

#include "core.h"
#include "port.h"

#include <linux/export.h>
#include <net/sock.h>

#define SS_LISTENING	-1	/* socket is listening */
#define SS_READY	-2	/* socket is connectionless */

#define CONN_TIMEOUT_DEFAULT	8000	/* default connect timeout = 8s */

struct tipc_sock {
	struct sock sk;
	struct tipc_port *p;
	struct tipc_portid peer_name;
	unsigned int conn_timeout;
};

#define tipc_sk(sk) ((struct tipc_sock *)(sk))
#define tipc_sk_port(sk) (tipc_sk(sk)->p)

#define tipc_rx_ready(sock) (!skb_queue_empty(&sock->sk->sk_receive_queue) || \
			(sock->state == SS_DISCONNECTING))

static int backlog_rcv(struct sock *sk, struct sk_buff *skb);
static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf);
static void wakeupdispatch(struct tipc_port *tport);
static void tipc_data_ready(struct sock *sk, int len);
static void tipc_write_space(struct sock *sk);
static int release(struct socket *sock);
static int accept(struct socket *sock, struct socket *new_sock, int flags);

static const struct proto_ops packet_ops;
static const struct proto_ops stream_ops;
static const struct proto_ops msg_ops;

static struct proto tipc_proto;
static struct proto tipc_proto_kern;

static int sockets_enabled;

/*
 * Revised TIPC socket locking policy:
 *
 * Most socket operations take the standard socket lock when they start
 * and hold it until they finish (or until they need to sleep).  Acquiring
 * this lock grants the owner exclusive access to the fields of the socket
 * data structures, with the exception of the backlog queue.  A few socket
 * operations can be done without taking the socket lock because they only
 * read socket information that never changes during the life of the socket.
 *
 * Socket operations may acquire the lock for the associated TIPC port if they
 * need to perform an operation on the port.  If any routine needs to acquire
 * both the socket lock and the port lock it must take the socket lock first
 * to avoid the risk of deadlock.
 *
 * The dispatcher handling incoming messages cannot grab the socket lock in
 * the standard fashion, since invoked it runs at the BH level and cannot block.
 * Instead, it checks to see if the socket lock is currently owned by someone,
 * and either handles the message itself or adds it to the socket's backlog
 * queue; in the latter case the queued message is processed once the process
 * owning the socket lock releases it.
 *
 * NOTE: Releasing the socket lock while an operation is sleeping overcomes
 * the problem of a blocked socket operation preventing any other operations
 * from occurring.  However, applications must be careful if they have
 * multiple threads trying to send (or receive) on the same socket, as these
 * operations might interfere with each other.  For example, doing a connect
 * and a receive at the same time might allow the receive to consume the
 * ACK message meant for the connect.  While additional work could be done
 * to try and overcome this, it doesn't seem to be worthwhile at the present.
 *
 * NOTE: Releasing the socket lock while an operation is sleeping also ensures
 * that another operation that must be performed in a non-blocking manner is
 * not delayed for very long because the lock has already been taken.
 *
 * NOTE: This code assumes that certain fields of a port/socket pair are
 * constant over its lifetime; such fields can be examined without taking
 * the socket lock and/or port lock, and do not need to be re-read even
 * after resuming processing after waiting.  These fields include:
 *   - socket type
 *   - pointer to socket sk structure (aka tipc_sock structure)
 *   - pointer to port structure
 *   - port reference
 */

/**
 * advance_rx_queue - discard first buffer in socket receive queue
 *
 * Caller must hold socket lock
 */
static void advance_rx_queue(struct sock *sk)
{
	kfree_skb(__skb_dequeue(&sk->sk_receive_queue));
}

/**
 * reject_rx_queue - reject all buffers in socket receive queue
 *
 * Caller must hold socket lock
 */
static void reject_rx_queue(struct sock *sk)
{
	struct sk_buff *buf;

	while ((buf = __skb_dequeue(&sk->sk_receive_queue)))
		tipc_reject_msg(buf, TIPC_ERR_NO_PORT);
}

/**
 * tipc_sk_create - create a TIPC socket
 * @net: network namespace (must be default network)
 * @sock: pre-allocated socket structure
 * @protocol: protocol indicator (must be 0)
 * @kern: caused by kernel or by userspace?
 *
 * This routine creates additional data structures used by the TIPC socket,
 * initializes them, and links them together.
 *
 * Returns 0 on success, errno otherwise
 */
static int tipc_sk_create(struct net *net, struct socket *sock, int protocol,
			  int kern)
{
	const struct proto_ops *ops;
	socket_state state;
	struct sock *sk;
	struct tipc_port *tp_ptr;

	/* Validate arguments */
	if (unlikely(protocol != 0))
		return -EPROTONOSUPPORT;

	switch (sock->type) {
	case SOCK_STREAM:
		ops = &stream_ops;
		state = SS_UNCONNECTED;
		break;
	case SOCK_SEQPACKET:
		ops = &packet_ops;
		state = SS_UNCONNECTED;
		break;
	case SOCK_DGRAM:
	case SOCK_RDM:
		ops = &msg_ops;
		state = SS_READY;
		break;
	default:
		return -EPROTOTYPE;
	}

	/* Allocate socket's protocol area */
	if (!kern)
		sk = sk_alloc(net, AF_TIPC, GFP_KERNEL, &tipc_proto);
	else
		sk = sk_alloc(net, AF_TIPC, GFP_KERNEL, &tipc_proto_kern);

	if (sk == NULL)
		return -ENOMEM;

	/* Allocate TIPC port for socket to use */
	tp_ptr = tipc_createport(sk, &dispatch, &wakeupdispatch,
				 TIPC_LOW_IMPORTANCE);
	if (unlikely(!tp_ptr)) {
		sk_free(sk);
		return -ENOMEM;
	}

	/* Finish initializing socket data structures */
	sock->ops = ops;
	sock->state = state;

	sock_init_data(sock, sk);
	sk->sk_backlog_rcv = backlog_rcv;
	sk->sk_rcvbuf = sysctl_tipc_rmem[1];
	sk->sk_data_ready = tipc_data_ready;
	sk->sk_write_space = tipc_write_space;
	tipc_sk(sk)->p = tp_ptr;
	tipc_sk(sk)->conn_timeout = CONN_TIMEOUT_DEFAULT;

	spin_unlock_bh(tp_ptr->lock);

	if (sock->state == SS_READY) {
		tipc_set_portunreturnable(tp_ptr->ref, 1);
		if (sock->type == SOCK_DGRAM)
			tipc_set_portunreliable(tp_ptr->ref, 1);
	}

	return 0;
}

/**
 * tipc_sock_create_local - create TIPC socket from inside TIPC module
 * @type: socket type - SOCK_RDM or SOCK_SEQPACKET
 *
 * We cannot use sock_creat_kern here because it bumps module user count.
 * Since socket owner and creator is the same module we must make sure
 * that module count remains zero for module local sockets, otherwise
 * we cannot do rmmod.
 *
 * Returns 0 on success, errno otherwise
 */
int tipc_sock_create_local(int type, struct socket **res)
{
	int rc;
	struct sock *sk;

	rc = sock_create_lite(AF_TIPC, type, 0, res);
	if (rc < 0) {
		pr_err("Failed to create kernel socket\n");
		return rc;
	}
	tipc_sk_create(&init_net, *res, 0, 1);

	sk = (*res)->sk;

	return 0;
}

/**
 * tipc_sock_release_local - release socket created by tipc_sock_create_local
 * @sock: the socket to be released.
 *
 * Module reference count is not incremented when such sockets are created,
 * so we must keep it from being decremented when they are released.
 */
void tipc_sock_release_local(struct socket *sock)
{
	release(sock);
	sock->ops = NULL;
	sock_release(sock);
}

/**
 * tipc_sock_accept_local - accept a connection on a socket created
 * with tipc_sock_create_local. Use this function to avoid that
 * module reference count is inadvertently incremented.
 *
 * @sock:    the accepting socket
 * @newsock: reference to the new socket to be created
 * @flags:   socket flags
 */

int tipc_sock_accept_local(struct socket *sock, struct socket **newsock,
			   int flags)
{
	struct sock *sk = sock->sk;
	int ret;

	ret = sock_create_lite(sk->sk_family, sk->sk_type,
			       sk->sk_protocol, newsock);
	if (ret < 0)
		return ret;

	ret = accept(sock, *newsock, flags);
	if (ret < 0) {
		sock_release(*newsock);
		return ret;
	}
	(*newsock)->ops = sock->ops;
	return ret;
}

/**
 * release - destroy a TIPC socket
 * @sock: socket to destroy
 *
 * This routine cleans up any messages that are still queued on the socket.
 * For DGRAM and RDM socket types, all queued messages are rejected.
 * For SEQPACKET and STREAM socket types, the first message is rejected
 * and any others are discarded.  (If the first message on a STREAM socket
 * is partially-read, it is discarded and the next one is rejected instead.)
 *
 * NOTE: Rejected messages are not necessarily returned to the sender!  They
 * are returned or discarded according to the "destination droppable" setting
 * specified for the message by the sender.
 *
 * Returns 0 on success, errno otherwise
 */
static int release(struct socket *sock)
{
	struct sock *sk = sock->sk;
	struct tipc_port *tport;
	struct sk_buff *buf;
	int res;

	/*
	 * Exit if socket isn't fully initialized (occurs when a failed accept()
	 * releases a pre-allocated child socket that was never used)
	 */
	if (sk == NULL)
		return 0;

	tport = tipc_sk_port(sk);
	lock_sock(sk);

	/*
	 * Reject all unreceived messages, except on an active connection
	 * (which disconnects locally & sends a 'FIN+' to peer)
	 */
	while (sock->state != SS_DISCONNECTING) {
		buf = __skb_dequeue(&sk->sk_receive_queue);
		if (buf == NULL)
			break;
		if (TIPC_SKB_CB(buf)->handle != NULL)
			kfree_skb(buf);
		else {
			if ((sock->state == SS_CONNECTING) ||
			    (sock->state == SS_CONNECTED)) {
				sock->state = SS_DISCONNECTING;
				tipc_disconnect(tport->ref);
			}
			tipc_reject_msg(buf, TIPC_ERR_NO_PORT);
		}
	}

	/*
	 * Delete TIPC port; this ensures no more messages are queued
	 * (also disconnects an active connection & sends a 'FIN-' to peer)
	 */
	res = tipc_deleteport(tport);

	/* Discard any remaining (connection-based) messages in receive queue */
	__skb_queue_purge(&sk->sk_receive_queue);

	/* Reject any messages that accumulated in backlog queue */
	sock->state = SS_DISCONNECTING;
	release_sock(sk);

	sock_put(sk);
	sock->sk = NULL;

	return res;
}

/**
 * bind - associate or disassocate TIPC name(s) with a socket
 * @sock: socket structure
 * @uaddr: socket address describing name(s) and desired operation
 * @uaddr_len: size of socket address data structure
 *
 * Name and name sequence binding is indicated using a positive scope value;
 * a negative scope value unbinds the specified name.  Specifying no name
 * (i.e. a socket address length of 0) unbinds all names from the socket.
 *
 * Returns 0 on success, errno otherwise
 *
 * NOTE: This routine doesn't need to take the socket lock since it doesn't
 *       access any non-constant socket information.
 */
static int bind(struct socket *sock, struct sockaddr *uaddr, int uaddr_len)
{
	struct sock *sk = sock->sk;
	struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr;
	struct tipc_port *tport = tipc_sk_port(sock->sk);
	int res = -EINVAL;

	lock_sock(sk);
	if (unlikely(!uaddr_len)) {
		res = tipc_withdraw(tport, 0, NULL);
		goto exit;
	}

	if (uaddr_len < sizeof(struct sockaddr_tipc)) {
		res = -EINVAL;
		goto exit;
	}
	if (addr->family != AF_TIPC) {
		res = -EAFNOSUPPORT;
		goto exit;
	}

	if (addr->addrtype == TIPC_ADDR_NAME)
		addr->addr.nameseq.upper = addr->addr.nameseq.lower;
	else if (addr->addrtype != TIPC_ADDR_NAMESEQ) {
		res = -EAFNOSUPPORT;
		goto exit;
	}

	if ((addr->addr.nameseq.type < TIPC_RESERVED_TYPES) &&
	    (addr->addr.nameseq.type != TIPC_TOP_SRV) &&
	    (addr->addr.nameseq.type != TIPC_CFG_SRV)) {
		res = -EACCES;
		goto exit;
	}

	res = (addr->scope > 0) ?
		tipc_publish(tport, addr->scope, &addr->addr.nameseq) :
		tipc_withdraw(tport, -addr->scope, &addr->addr.nameseq);
exit:
	release_sock(sk);
	return res;
}

/**
 * get_name - get port ID of socket or peer socket
 * @sock: socket structure
 * @uaddr: area for returned socket address
 * @uaddr_len: area for returned length of socket address
 * @peer: 0 = own ID, 1 = current peer ID, 2 = current/former peer ID
 *
 * Returns 0 on success, errno otherwise
 *
 * NOTE: This routine doesn't need to take the socket lock since it only
 *       accesses socket information that is unchanging (or which changes in
 *       a completely predictable manner).
 */
static int get_name(struct socket *sock, struct sockaddr *uaddr,
		    int *uaddr_len, int peer)
{
	struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr;
	struct tipc_sock *tsock = tipc_sk(sock->sk);

	memset(addr, 0, sizeof(*addr));
	if (peer) {
		if ((sock->state != SS_CONNECTED) &&
			((peer != 2) || (sock->state != SS_DISCONNECTING)))
			return -ENOTCONN;
		addr->addr.id.ref = tsock->peer_name.ref;
		addr->addr.id.node = tsock->peer_name.node;
	} else {
		addr->addr.id.ref = tsock->p->ref;
		addr->addr.id.node = tipc_own_addr;
	}

	*uaddr_len = sizeof(*addr);
	addr->addrtype = TIPC_ADDR_ID;
	addr->family = AF_TIPC;
	addr->scope = 0;
	addr->addr.name.domain = 0;

	return 0;
}

/**
 * poll - read and possibly block on pollmask
 * @file: file structure associated with the socket
 * @sock: socket for which to calculate the poll bits
 * @wait: ???
 *
 * Returns pollmask value
 *
 * COMMENTARY:
 * It appears that the usual socket locking mechanisms are not useful here
 * since the pollmask info is potentially out-of-date the moment this routine
 * exits.  TCP and other protocols seem to rely on higher level poll routines
 * to handle any preventable race conditions, so TIPC will do the same ...
 *
 * TIPC sets the returned events as follows:
 *
 * socket state		flags set
 * ------------		---------
 * unconnected		no read flags
 *			POLLOUT if port is not congested
 *
 * connecting		POLLIN/POLLRDNORM if ACK/NACK in rx queue
 *			no write flags
 *
 * connected		POLLIN/POLLRDNORM if data in rx queue
 *			POLLOUT if port is not congested
 *
 * disconnecting	POLLIN/POLLRDNORM/POLLHUP
 *			no write flags
 *
 * listening		POLLIN if SYN in rx queue
 *			no write flags
 *
 * ready		POLLIN/POLLRDNORM if data in rx queue
 * [connectionless]	POLLOUT (since port cannot be congested)
 *
 * IMPORTANT: The fact that a read or write operation is indicated does NOT
 * imply that the operation will succeed, merely that it should be performed
 * and will not block.
 */
static unsigned int poll(struct file *file, struct socket *sock,
			 poll_table *wait)
{
	struct sock *sk = sock->sk;
	u32 mask = 0;

	sock_poll_wait(file, sk_sleep(sk), wait);

	switch ((int)sock->state) {
	case SS_UNCONNECTED:
		if (!tipc_sk_port(sk)->congested)
			mask |= POLLOUT;
		break;
	case SS_READY:
	case SS_CONNECTED:
		if (!tipc_sk_port(sk)->congested)
			mask |= POLLOUT;
		/* fall thru' */
	case SS_CONNECTING:
	case SS_LISTENING:
		if (!skb_queue_empty(&sk->sk_receive_queue))
			mask |= (POLLIN | POLLRDNORM);
		break;
	case SS_DISCONNECTING:
		mask = (POLLIN | POLLRDNORM | POLLHUP);
		break;
	}

	return mask;
}

/**
 * dest_name_check - verify user is permitted to send to specified port name
 * @dest: destination address
 * @m: descriptor for message to be sent
 *
 * Prevents restricted configuration commands from being issued by
 * unauthorized users.
 *
 * Returns 0 if permission is granted, otherwise errno
 */
static int dest_name_check(struct sockaddr_tipc *dest, struct msghdr *m)
{
	struct tipc_cfg_msg_hdr hdr;

	if (likely(dest->addr.name.name.type >= TIPC_RESERVED_TYPES))
		return 0;
	if (likely(dest->addr.name.name.type == TIPC_TOP_SRV))
		return 0;
	if (likely(dest->addr.name.name.type != TIPC_CFG_SRV))
		return -EACCES;

	if (!m->msg_iovlen || (m->msg_iov[0].iov_len < sizeof(hdr)))
		return -EMSGSIZE;
	if (copy_from_user(&hdr, m->msg_iov[0].iov_base, sizeof(hdr)))
		return -EFAULT;
	if ((ntohs(hdr.tcm_type) & 0xC000) && (!capable(CAP_NET_ADMIN)))
		return -EACCES;

	return 0;
}

/**
 * send_msg - send message in connectionless manner
 * @iocb: if NULL, indicates that socket lock is already held
 * @sock: socket structure
 * @m: message to send
 * @total_len: length of message
 *
 * Message must have an destination specified explicitly.
 * Used for SOCK_RDM and SOCK_DGRAM messages,
 * and for 'SYN' messages on SOCK_SEQPACKET and SOCK_STREAM connections.
 * (Note: 'SYN+' is prohibited on SOCK_STREAM.)
 *
 * Returns the number of bytes sent on success, or errno otherwise
 */
static int send_msg(struct kiocb *iocb, struct socket *sock,
		    struct msghdr *m, size_t total_len)
{
	struct sock *sk = sock->sk;
	struct tipc_port *tport = tipc_sk_port(sk);
	struct sockaddr_tipc *dest = (struct sockaddr_tipc *)m->msg_name;
	int needs_conn;
	long timeout_val;
	int res = -EINVAL;

	if (unlikely(!dest))
		return -EDESTADDRREQ;
	if (unlikely((m->msg_namelen < sizeof(*dest)) ||
		     (dest->family != AF_TIPC)))
		return -EINVAL;
	if (total_len > TIPC_MAX_USER_MSG_SIZE)
		return -EMSGSIZE;

	if (iocb)
		lock_sock(sk);

	needs_conn = (sock->state != SS_READY);
	if (unlikely(needs_conn)) {
		if (sock->state == SS_LISTENING) {
			res = -EPIPE;
			goto exit;
		}
		if (sock->state != SS_UNCONNECTED) {
			res = -EISCONN;
			goto exit;
		}
		if (tport->published) {
			res = -EOPNOTSUPP;
			goto exit;
		}
		if (dest->addrtype == TIPC_ADDR_NAME) {
			tport->conn_type = dest->addr.name.name.type;
			tport->conn_instance = dest->addr.name.name.instance;
		}

		/* Abort any pending connection attempts (very unlikely) */
		reject_rx_queue(sk);
	}

	timeout_val = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);

	do {
		if (dest->addrtype == TIPC_ADDR_NAME) {
			res = dest_name_check(dest, m);
			if (res)
				break;
			res = tipc_send2name(tport->ref,
					     &dest->addr.name.name,
					     dest->addr.name.domain,
					     m->msg_iov,
					     total_len);
		} else if (dest->addrtype == TIPC_ADDR_ID) {
			res = tipc_send2port(tport->ref,
					     &dest->addr.id,
					     m->msg_iov,
					     total_len);
		} else if (dest->addrtype == TIPC_ADDR_MCAST) {
			if (needs_conn) {
				res = -EOPNOTSUPP;
				break;
			}
			res = dest_name_check(dest, m);
			if (res)
				break;
			res = tipc_multicast(tport->ref,
					     &dest->addr.nameseq,
					     m->msg_iov,
					     total_len);
		}
		if (likely(res != -ELINKCONG)) {
			if (needs_conn && (res >= 0))
				sock->state = SS_CONNECTING;
			break;
		}
		if (timeout_val <= 0L) {
			res = timeout_val ? timeout_val : -EWOULDBLOCK;
			break;
		}
		release_sock(sk);
		timeout_val = wait_event_interruptible_timeout(*sk_sleep(sk),
					       !tport->congested, timeout_val);
		lock_sock(sk);
	} while (1);

exit:
	if (iocb)
		release_sock(sk);
	return res;
}

/**
 * send_packet - send a connection-oriented message
 * @iocb: if NULL, indicates that socket lock is already held
 * @sock: socket structure
 * @m: message to send
 * @total_len: length of message
 *
 * Used for SOCK_SEQPACKET messages and SOCK_STREAM data.
 *
 * Returns the number of bytes sent on success, or errno otherwise
 */
static int send_packet(struct kiocb *iocb, struct socket *sock,
		       struct msghdr *m, size_t total_len)
{
	struct sock *sk = sock->sk;
	struct tipc_port *tport = tipc_sk_port(sk);
	struct sockaddr_tipc *dest = (struct sockaddr_tipc *)m->msg_name;
	long timeout_val;
	int res;

	/* Handle implied connection establishment */
	if (unlikely(dest))
		return send_msg(iocb, sock, m, total_len);

	if (total_len > TIPC_MAX_USER_MSG_SIZE)
		return -EMSGSIZE;

	if (iocb)
		lock_sock(sk);

	timeout_val = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);

	do {
		if (unlikely(sock->state != SS_CONNECTED)) {
			if (sock->state == SS_DISCONNECTING)
				res = -EPIPE;
			else
				res = -ENOTCONN;
			break;
		}

		res = tipc_send(tport->ref, m->msg_iov, total_len);
		if (likely(res != -ELINKCONG))
			break;
		if (timeout_val <= 0L) {
			res = timeout_val ? timeout_val : -EWOULDBLOCK;
			break;
		}
		release_sock(sk);
		timeout_val = wait_event_interruptible_timeout(*sk_sleep(sk),
			(!tport->congested || !tport->connected), timeout_val);
		lock_sock(sk);
	} while (1);

	if (iocb)
		release_sock(sk);
	return res;
}

/**
 * send_stream - send stream-oriented data
 * @iocb: (unused)
 * @sock: socket structure
 * @m: data to send
 * @total_len: total length of data to be sent
 *
 * Used for SOCK_STREAM data.
 *
 * Returns the number of bytes sent on success (or partial success),
 * or errno if no data sent
 */
static int send_stream(struct kiocb *iocb, struct socket *sock,
		       struct msghdr *m, size_t total_len)
{
	struct sock *sk = sock->sk;
	struct tipc_port *tport = tipc_sk_port(sk);
	struct msghdr my_msg;
	struct iovec my_iov;
	struct iovec *curr_iov;
	int curr_iovlen;
	char __user *curr_start;
	u32 hdr_size;
	int curr_left;
	int bytes_to_send;
	int bytes_sent;
	int res;

	lock_sock(sk);

	/* Handle special cases where there is no connection */
	if (unlikely(sock->state != SS_CONNECTED)) {
		if (sock->state == SS_UNCONNECTED) {
			res = send_packet(NULL, sock, m, total_len);
			goto exit;
		} else if (sock->state == SS_DISCONNECTING) {
			res = -EPIPE;
			goto exit;
		} else {
			res = -ENOTCONN;
			goto exit;
		}
	}

	if (unlikely(m->msg_name)) {
		res = -EISCONN;
		goto exit;
	}

	if (total_len > (unsigned int)INT_MAX) {
		res = -EMSGSIZE;
		goto exit;
	}

	/*
	 * Send each iovec entry using one or more messages
	 *
	 * Note: This algorithm is good for the most likely case
	 * (i.e. one large iovec entry), but could be improved to pass sets
	 * of small iovec entries into send_packet().
	 */
	curr_iov = m->msg_iov;
	curr_iovlen = m->msg_iovlen;
	my_msg.msg_iov = &my_iov;
	my_msg.msg_iovlen = 1;
	my_msg.msg_flags = m->msg_flags;
	my_msg.msg_name = NULL;
	bytes_sent = 0;

	hdr_size = msg_hdr_sz(&tport->phdr);

	while (curr_iovlen--) {
		curr_start = curr_iov->iov_base;
		curr_left = curr_iov->iov_len;

		while (curr_left) {
			bytes_to_send = tport->max_pkt - hdr_size;
			if (bytes_to_send > TIPC_MAX_USER_MSG_SIZE)
				bytes_to_send = TIPC_MAX_USER_MSG_SIZE;
			if (curr_left < bytes_to_send)
				bytes_to_send = curr_left;
			my_iov.iov_base = curr_start;
			my_iov.iov_len = bytes_to_send;
			res = send_packet(NULL, sock, &my_msg, bytes_to_send);
			if (res < 0) {
				if (bytes_sent)
					res = bytes_sent;
				goto exit;
			}
			curr_left -= bytes_to_send;
			curr_start += bytes_to_send;
			bytes_sent += bytes_to_send;
		}

		curr_iov++;
	}
	res = bytes_sent;
exit:
	release_sock(sk);
	return res;
}

/**
 * auto_connect - complete connection setup to a remote port
 * @sock: socket structure
 * @msg: peer's response message
 *
 * Returns 0 on success, errno otherwise
 */
static int auto_connect(struct socket *sock, struct tipc_msg *msg)
{
	struct tipc_sock *tsock = tipc_sk(sock->sk);
	struct tipc_port *p_ptr;

	tsock->peer_name.ref = msg_origport(msg);
	tsock->peer_name.node = msg_orignode(msg);
	p_ptr = tipc_port_deref(tsock->p->ref);
	if (!p_ptr)
		return -EINVAL;

	__tipc_connect(tsock->p->ref, p_ptr, &tsock->peer_name);

	if (msg_importance(msg) > TIPC_CRITICAL_IMPORTANCE)
		return -EINVAL;
	msg_set_importance(&p_ptr->phdr, (u32)msg_importance(msg));
	sock->state = SS_CONNECTED;
	return 0;
}

/**
 * set_orig_addr - capture sender's address for received message
 * @m: descriptor for message info
 * @msg: received message header
 *
 * Note: Address is not captured if not requested by receiver.
 */
static void set_orig_addr(struct msghdr *m, struct tipc_msg *msg)
{
	struct sockaddr_tipc *addr = (struct sockaddr_tipc *)m->msg_name;

	if (addr) {
		addr->family = AF_TIPC;
		addr->addrtype = TIPC_ADDR_ID;
		memset(&addr->addr, 0, sizeof(addr->addr));
		addr->addr.id.ref = msg_origport(msg);
		addr->addr.id.node = msg_orignode(msg);
		addr->addr.name.domain = 0;	/* could leave uninitialized */
		addr->scope = 0;		/* could leave uninitialized */
		m->msg_namelen = sizeof(struct sockaddr_tipc);
	}
}

/**
 * anc_data_recv - optionally capture ancillary data for received message
 * @m: descriptor for message info
 * @msg: received message header
 * @tport: TIPC port associated with message
 *
 * Note: Ancillary data is not captured if not requested by receiver.
 *
 * Returns 0 if successful, otherwise errno
 */
static int anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
			 struct tipc_port *tport)
{
	u32 anc_data[3];
	u32 err;
	u32 dest_type;
	int has_name;
	int res;

	if (likely(m->msg_controllen == 0))
		return 0;

	/* Optionally capture errored message object(s) */
	err = msg ? msg_errcode(msg) : 0;
	if (unlikely(err)) {
		anc_data[0] = err;
		anc_data[1] = msg_data_sz(msg);
		res = put_cmsg(m, SOL_TIPC, TIPC_ERRINFO, 8, anc_data);
		if (res)
			return res;
		if (anc_data[1]) {
			res = put_cmsg(m, SOL_TIPC, TIPC_RETDATA, anc_data[1],
				       msg_data(msg));
			if (res)
				return res;
		}
	}

	/* Optionally capture message destination object */
	dest_type = msg ? msg_type(msg) : TIPC_DIRECT_MSG;
	switch (dest_type) {
	case TIPC_NAMED_MSG:
		has_name = 1;
		anc_data[0] = msg_nametype(msg);
		anc_data[1] = msg_namelower(msg);
		anc_data[2] = msg_namelower(msg);
		break;
	case TIPC_MCAST_MSG:
		has_name = 1;
		anc_data[0] = msg_nametype(msg);
		anc_data[1] = msg_namelower(msg);
		anc_data[2] = msg_nameupper(msg);
		break;
	case TIPC_CONN_MSG:
		has_name = (tport->conn_type != 0);
		anc_data[0] = tport->conn_type;
		anc_data[1] = tport->conn_instance;
		anc_data[2] = tport->conn_instance;
		break;
	default:
		has_name = 0;
	}
	if (has_name) {
		res = put_cmsg(m, SOL_TIPC, TIPC_DESTNAME, 12, anc_data);
		if (res)
			return res;
	}

	return 0;
}

/**
 * recv_msg - receive packet-oriented message
 * @iocb: (unused)
 * @m: descriptor for message info
 * @buf_len: total size of user buffer area
 * @flags: receive flags
 *
 * Used for SOCK_DGRAM, SOCK_RDM, and SOCK_SEQPACKET messages.
 * If the complete message doesn't fit in user area, truncate it.
 *
 * Returns size of returned message data, errno otherwise
 */
static int recv_msg(struct kiocb *iocb, struct socket *sock,
		    struct msghdr *m, size_t buf_len, int flags)
{
	struct sock *sk = sock->sk;
	struct tipc_port *tport = tipc_sk_port(sk);
	struct sk_buff *buf;
	struct tipc_msg *msg;
	long timeout;
	unsigned int sz;
	u32 err;
	int res;

	/* Catch invalid receive requests */
	if (unlikely(!buf_len))
		return -EINVAL;

	lock_sock(sk);

	if (unlikely(sock->state == SS_UNCONNECTED)) {
		res = -ENOTCONN;
		goto exit;
	}

	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
restart:

	/* Look for a message in receive queue; wait if necessary */
	while (skb_queue_empty(&sk->sk_receive_queue)) {
		if (sock->state == SS_DISCONNECTING) {
			res = -ENOTCONN;
			goto exit;
		}
		if (timeout <= 0L) {
			res = timeout ? timeout : -EWOULDBLOCK;
			goto exit;
		}
		release_sock(sk);
		timeout = wait_event_interruptible_timeout(*sk_sleep(sk),
							   tipc_rx_ready(sock),
							   timeout);
		lock_sock(sk);
	}

	/* Look at first message in receive queue */
	buf = skb_peek(&sk->sk_receive_queue);
	msg = buf_msg(buf);
	sz = msg_data_sz(msg);
	err = msg_errcode(msg);

	/* Discard an empty non-errored message & try again */
	if ((!sz) && (!err)) {
		advance_rx_queue(sk);
		goto restart;
	}

	/* Capture sender's address (optional) */
	set_orig_addr(m, msg);

	/* Capture ancillary data (optional) */
	res = anc_data_recv(m, msg, tport);
	if (res)
		goto exit;

	/* Capture message data (if valid) & compute return value (always) */
	if (!err) {
		if (unlikely(buf_len < sz)) {
			sz = buf_len;
			m->msg_flags |= MSG_TRUNC;
		}
		res = skb_copy_datagram_iovec(buf, msg_hdr_sz(msg),
					      m->msg_iov, sz);
		if (res)
			goto exit;
		res = sz;
	} else {
		if ((sock->state == SS_READY) ||
		    ((err == TIPC_CONN_SHUTDOWN) || m->msg_control))
			res = 0;
		else
			res = -ECONNRESET;
	}

	/* Consume received message (optional) */
	if (likely(!(flags & MSG_PEEK))) {
		if ((sock->state != SS_READY) &&
		    (++tport->conn_unacked >= TIPC_FLOW_CONTROL_WIN))
			tipc_acknowledge(tport->ref, tport->conn_unacked);
		advance_rx_queue(sk);
	}
exit:
	release_sock(sk);
	return res;
}

/**
 * recv_stream - receive stream-oriented data
 * @iocb: (unused)
 * @m: descriptor for message info
 * @buf_len: total size of user buffer area
 * @flags: receive flags
 *
 * Used for SOCK_STREAM messages only.  If not enough data is available
 * will optionally wait for more; never truncates data.
 *
 * Returns size of returned message data, errno otherwise
 */
static int recv_stream(struct kiocb *iocb, struct socket *sock,
		       struct msghdr *m, size_t buf_len, int flags)
{
	struct sock *sk = sock->sk;
	struct tipc_port *tport = tipc_sk_port(sk);
	struct sk_buff *buf;
	struct tipc_msg *msg;
	long timeout;
	unsigned int sz;
	int sz_to_copy, target, needed;
	int sz_copied = 0;
	u32 err;
	int res = 0;

	/* Catch invalid receive attempts */
	if (unlikely(!buf_len))
		return -EINVAL;

	lock_sock(sk);

	if (unlikely((sock->state == SS_UNCONNECTED))) {
		res = -ENOTCONN;
		goto exit;
	}

	target = sock_rcvlowat(sk, flags & MSG_WAITALL, buf_len);
	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);

restart:
	/* Look for a message in receive queue; wait if necessary */
	while (skb_queue_empty(&sk->sk_receive_queue)) {
		if (sock->state == SS_DISCONNECTING) {
			res = -ENOTCONN;
			goto exit;
		}
		if (timeout <= 0L) {
			res = timeout ? timeout : -EWOULDBLOCK;
			goto exit;
		}
		release_sock(sk);
		timeout = wait_event_interruptible_timeout(*sk_sleep(sk),
							   tipc_rx_ready(sock),
							   timeout);
		lock_sock(sk);
	}

	/* Look at first message in receive queue */
	buf = skb_peek(&sk->sk_receive_queue);
	msg = buf_msg(buf);
	sz = msg_data_sz(msg);
	err = msg_errcode(msg);

	/* Discard an empty non-errored message & try again */
	if ((!sz) && (!err)) {
		advance_rx_queue(sk);
		goto restart;
	}

	/* Optionally capture sender's address & ancillary data of first msg */
	if (sz_copied == 0) {
		set_orig_addr(m, msg);
		res = anc_data_recv(m, msg, tport);
		if (res)
			goto exit;
	}

	/* Capture message data (if valid) & compute return value (always) */
	if (!err) {
		u32 offset = (u32)(unsigned long)(TIPC_SKB_CB(buf)->handle);

		sz -= offset;
		needed = (buf_len - sz_copied);
		sz_to_copy = (sz <= needed) ? sz : needed;

		res = skb_copy_datagram_iovec(buf, msg_hdr_sz(msg) + offset,
					      m->msg_iov, sz_to_copy);
		if (res)
			goto exit;

		sz_copied += sz_to_copy;

		if (sz_to_copy < sz) {
			if (!(flags & MSG_PEEK))
				TIPC_SKB_CB(buf)->handle =
				(void *)(unsigned long)(offset + sz_to_copy);
			goto exit;
		}
	} else {
		if (sz_copied != 0)
			goto exit; /* can't add error msg to valid data */

		if ((err == TIPC_CONN_SHUTDOWN) || m->msg_control)
			res = 0;
		else
			res = -ECONNRESET;
	}

	/* Consume received message (optional) */
	if (likely(!(flags & MSG_PEEK))) {
		if (unlikely(++tport->conn_unacked >= TIPC_FLOW_CONTROL_WIN))
			tipc_acknowledge(tport->ref, tport->conn_unacked);
		advance_rx_queue(sk);
	}

	/* Loop around if more data is required */
	if ((sz_copied < buf_len) &&	/* didn't get all requested data */
	    (!skb_queue_empty(&sk->sk_receive_queue) ||
	    (sz_copied < target)) &&	/* and more is ready or required */
	    (!(flags & MSG_PEEK)) &&	/* and aren't just peeking at data */
	    (!err))			/* and haven't reached a FIN */
		goto restart;

exit:
	release_sock(sk);
	return sz_copied ? sz_copied : res;
}

/**
 * tipc_write_space - wake up thread if port congestion is released
 * @sk: socket
 */
static void tipc_write_space(struct sock *sk)
{
	struct socket_wq *wq;

	rcu_read_lock();
	wq = rcu_dereference(sk->sk_wq);
	if (wq_has_sleeper(wq))
		wake_up_interruptible_sync_poll(&wq->wait, POLLOUT |
						POLLWRNORM | POLLWRBAND);
	rcu_read_unlock();
}

/**
 * tipc_data_ready - wake up threads to indicate messages have been received
 * @sk: socket
 * @len: the length of messages
 */
static void tipc_data_ready(struct sock *sk, int len)
{
	struct socket_wq *wq;

	rcu_read_lock();
	wq = rcu_dereference(sk->sk_wq);
	if (wq_has_sleeper(wq))
		wake_up_interruptible_sync_poll(&wq->wait, POLLIN |
						POLLRDNORM | POLLRDBAND);
	rcu_read_unlock();
}

/**
 * filter_connect - Handle all incoming messages for a connection-based socket
 * @tsock: TIPC socket
 * @msg: message
 *
 * Returns TIPC error status code and socket error status code
 * once it encounters some errors
 */
static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf)
{
	struct socket *sock = tsock->sk.sk_socket;
	struct tipc_msg *msg = buf_msg(*buf);
	struct sock *sk = &tsock->sk;
	u32 retval = TIPC_ERR_NO_PORT;
	int res;

	if (msg_mcast(msg))
		return retval;

	switch ((int)sock->state) {
	case SS_CONNECTED:
		/* Accept only connection-based messages sent by peer */
		if (msg_connected(msg) && tipc_port_peer_msg(tsock->p, msg)) {
			if (unlikely(msg_errcode(msg))) {
				sock->state = SS_DISCONNECTING;
				__tipc_disconnect(tsock->p);
			}
			retval = TIPC_OK;
		}
		break;
	case SS_CONNECTING:
		/* Accept only ACK or NACK message */
		if (unlikely(msg_errcode(msg))) {
			sock->state = SS_DISCONNECTING;
			sk->sk_err = ECONNREFUSED;
			retval = TIPC_OK;
			break;
		}

		if (unlikely(!msg_connected(msg)))
			break;

		res = auto_connect(sock, msg);
		if (res) {
			sock->state = SS_DISCONNECTING;
			sk->sk_err = -res;
			retval = TIPC_OK;
			break;
		}

		/* If an incoming message is an 'ACK-', it should be
		 * discarded here because it doesn't contain useful
		 * data. In addition, we should try to wake up
		 * connect() routine if sleeping.
		 */
		if (msg_data_sz(msg) == 0) {
			kfree_skb(*buf);
			*buf = NULL;
			if (waitqueue_active(sk_sleep(sk)))
				wake_up_interruptible(sk_sleep(sk));
		}
		retval = TIPC_OK;
		break;
	case SS_LISTENING:
	case SS_UNCONNECTED:
		/* Accept only SYN message */
		if (!msg_connected(msg) && !(msg_errcode(msg)))
			retval = TIPC_OK;
		break;
	case SS_DISCONNECTING:
		break;
	default:
		pr_err("Unknown socket state %u\n", sock->state);
	}
	return retval;
}

/**
 * rcvbuf_limit - get proper overload limit of socket receive queue
 * @sk: socket
 * @buf: message
 *
 * For all connection oriented messages, irrespective of importance,
 * the default overload value (i.e. 67MB) is set as limit.
 *
 * For all connectionless messages, by default new queue limits are
 * as belows:
 *
 * TIPC_LOW_IMPORTANCE       (4 MB)
 * TIPC_MEDIUM_IMPORTANCE    (8 MB)
 * TIPC_HIGH_IMPORTANCE      (16 MB)
 * TIPC_CRITICAL_IMPORTANCE  (32 MB)
 *
 * Returns overload limit according to corresponding message importance
 */
static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *buf)
{
	struct tipc_msg *msg = buf_msg(buf);
	unsigned int limit;

	if (msg_connected(msg))
		limit = sysctl_tipc_rmem[2];
	else
		limit = sk->sk_rcvbuf >> TIPC_CRITICAL_IMPORTANCE <<
			msg_importance(msg);
	return limit;
}

/**
 * filter_rcv - validate incoming message
 * @sk: socket
 * @buf: message
 *
 * Enqueues message on receive queue if acceptable; optionally handles
 * disconnect indication for a connected socket.
 *
 * Called with socket lock already taken; port lock may also be taken.
 *
 * Returns TIPC error status code (TIPC_OK if message is not to be rejected)
 */
static u32 filter_rcv(struct sock *sk, struct sk_buff *buf)
{
	struct socket *sock = sk->sk_socket;
	struct tipc_msg *msg = buf_msg(buf);
	unsigned int limit = rcvbuf_limit(sk, buf);
	u32 res = TIPC_OK;

	/* Reject message if it is wrong sort of message for socket */
	if (msg_type(msg) > TIPC_DIRECT_MSG)
		return TIPC_ERR_NO_PORT;

	if (sock->state == SS_READY) {
		if (msg_connected(msg))
			return TIPC_ERR_NO_PORT;
	} else {
		res = filter_connect(tipc_sk(sk), &buf);
		if (res != TIPC_OK || buf == NULL)
			return res;
	}

	/* Reject message if there isn't room to queue it */
	if (sk_rmem_alloc_get(sk) + buf->truesize >= limit)
		return TIPC_ERR_OVERLOAD;

	/* Enqueue message */
	TIPC_SKB_CB(buf)->handle = NULL;
	__skb_queue_tail(&sk->sk_receive_queue, buf);
	skb_set_owner_r(buf, sk);

	sk->sk_data_ready(sk, 0);
	return TIPC_OK;
}

/**
 * backlog_rcv - handle incoming message from backlog queue
 * @sk: socket
 * @buf: message
 *
 * Caller must hold socket lock, but not port lock.
 *
 * Returns 0
 */
static int backlog_rcv(struct sock *sk, struct sk_buff *buf)
{
	u32 res;

	res = filter_rcv(sk, buf);
	if (res)
		tipc_reject_msg(buf, res);
	return 0;
}

/**
 * dispatch - handle incoming message
 * @tport: TIPC port that received message
 * @buf: message
 *
 * Called with port lock already taken.
 *
 * Returns TIPC error status code (TIPC_OK if message is not to be rejected)
 */
static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf)
{
	struct sock *sk = tport->sk;
	u32 res;

	/*
	 * Process message if socket is unlocked; otherwise add to backlog queue
	 *
	 * This code is based on sk_receive_skb(), but must be distinct from it
	 * since a TIPC-specific filter/reject mechanism is utilized
	 */
	bh_lock_sock(sk);
	if (!sock_owned_by_user(sk)) {
		res = filter_rcv(sk, buf);
	} else {
		if (sk_add_backlog(sk, buf, rcvbuf_limit(sk, buf)))
			res = TIPC_ERR_OVERLOAD;
		else
			res = TIPC_OK;
	}
	bh_unlock_sock(sk);

	return res;
}

/**
 * wakeupdispatch - wake up port after congestion
 * @tport: port to wakeup
 *
 * Called with port lock already taken.
 */
static void wakeupdispatch(struct tipc_port *tport)
{
	struct sock *sk = tport->sk;

	sk->sk_write_space(sk);
}

/**
 * connect - establish a connection to another TIPC port
 * @sock: socket structure
 * @dest: socket address for destination port
 * @destlen: size of socket address data structure
 * @flags: file-related flags associated with socket
 *
 * Returns 0 on success, errno otherwise
 */
static int connect(struct socket *sock, struct sockaddr *dest, int destlen,
		   int flags)
{
	struct sock *sk = sock->sk;
	struct sockaddr_tipc *dst = (struct sockaddr_tipc *)dest;
	struct msghdr m = {NULL,};
	unsigned int timeout;
	int res;

	lock_sock(sk);

	/* For now, TIPC does not allow use of connect() with DGRAM/RDM types */
	if (sock->state == SS_READY) {
		res = -EOPNOTSUPP;
		goto exit;
	}

	/*
	 * Reject connection attempt using multicast address
	 *
	 * Note: send_msg() validates the rest of the address fields,
	 *       so there's no need to do it here
	 */
	if (dst->addrtype == TIPC_ADDR_MCAST) {
		res = -EINVAL;
		goto exit;
	}

	timeout = (flags & O_NONBLOCK) ? 0 : tipc_sk(sk)->conn_timeout;

	switch (sock->state) {
	case SS_UNCONNECTED:
		/* Send a 'SYN-' to destination */
		m.msg_name = dest;
		m.msg_namelen = destlen;

		/* If connect is in non-blocking case, set MSG_DONTWAIT to
		 * indicate send_msg() is never blocked.
		 */
		if (!timeout)
			m.msg_flags = MSG_DONTWAIT;

		res = send_msg(NULL, sock, &m, 0);
		if ((res < 0) && (res != -EWOULDBLOCK))
			goto exit;

		/* Just entered SS_CONNECTING state; the only
		 * difference is that return value in non-blocking
		 * case is EINPROGRESS, rather than EALREADY.
		 */
		res = -EINPROGRESS;
		break;
	case SS_CONNECTING:
		res = -EALREADY;
		break;
	case SS_CONNECTED:
		res = -EISCONN;
		break;
	default:
		res = -EINVAL;
		goto exit;
	}

	if (sock->state == SS_CONNECTING) {
		if (!timeout)
			goto exit;

		/* Wait until an 'ACK' or 'RST' arrives, or a timeout occurs */
		release_sock(sk);
		res = wait_event_interruptible_timeout(*sk_sleep(sk),
				sock->state != SS_CONNECTING,
				timeout ? (long)msecs_to_jiffies(timeout)
					: MAX_SCHEDULE_TIMEOUT);
		lock_sock(sk);
		if (res <= 0) {
			if (res == 0)
				res = -ETIMEDOUT;
			else
				; /* leave "res" unchanged */
			goto exit;
		}
	}

	if (unlikely(sock->state == SS_DISCONNECTING))
		res = sock_error(sk);
	else
		res = 0;

exit:
	release_sock(sk);
	return res;
}

/**
 * listen - allow socket to listen for incoming connections
 * @sock: socket structure
 * @len: (unused)
 *
 * Returns 0 on success, errno otherwise
 */
static int listen(struct socket *sock, int len)
{
	struct sock *sk = sock->sk;
	int res;

	lock_sock(sk);

	if (sock->state != SS_UNCONNECTED)
		res = -EINVAL;
	else {
		sock->state = SS_LISTENING;
		res = 0;
	}

	release_sock(sk);
	return res;
}

/**
 * accept - wait for connection request
 * @sock: listening socket
 * @newsock: new socket that is to be connected
 * @flags: file-related flags associated with socket
 *
 * Returns 0 on success, errno otherwise
 */
static int accept(struct socket *sock, struct socket *new_sock, int flags)
{
	struct sock *new_sk, *sk = sock->sk;
	struct sk_buff *buf;
	struct tipc_sock *new_tsock;
	struct tipc_port *new_tport;
	struct tipc_msg *msg;
	u32 new_ref;

	int res;

	lock_sock(sk);

	if (sock->state != SS_LISTENING) {
		res = -EINVAL;
		goto exit;
	}

	while (skb_queue_empty(&sk->sk_receive_queue)) {
		if (flags & O_NONBLOCK) {
			res = -EWOULDBLOCK;
			goto exit;
		}
		release_sock(sk);
		res = wait_event_interruptible(*sk_sleep(sk),
				(!skb_queue_empty(&sk->sk_receive_queue)));
		lock_sock(sk);
		if (res)
			goto exit;
	}

	buf = skb_peek(&sk->sk_receive_queue);

	res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, 1);
	if (res)
		goto exit;

	new_sk = new_sock->sk;
	new_tsock = tipc_sk(new_sk);
	new_tport = new_tsock->p;
	new_ref = new_tport->ref;
	msg = buf_msg(buf);

	/* we lock on new_sk; but lockdep sees the lock on sk */
	lock_sock_nested(new_sk, SINGLE_DEPTH_NESTING);

	/*
	 * Reject any stray messages received by new socket
	 * before the socket lock was taken (very, very unlikely)
	 */
	reject_rx_queue(new_sk);

	/* Connect new socket to it's peer */
	new_tsock->peer_name.ref = msg_origport(msg);
	new_tsock->peer_name.node = msg_orignode(msg);
	tipc_connect(new_ref, &new_tsock->peer_name);
	new_sock->state = SS_CONNECTED;

	tipc_set_portimportance(new_ref, msg_importance(msg));
	if (msg_named(msg)) {
		new_tport->conn_type = msg_nametype(msg);
		new_tport->conn_instance = msg_nameinst(msg);
	}

	/*
	 * Respond to 'SYN-' by discarding it & returning 'ACK'-.
	 * Respond to 'SYN+' by queuing it on new socket.
	 */
	if (!msg_data_sz(msg)) {
		struct msghdr m = {NULL,};

		advance_rx_queue(sk);
		send_packet(NULL, new_sock, &m, 0);
	} else {
		__skb_dequeue(&sk->sk_receive_queue);
		__skb_queue_head(&new_sk->sk_receive_queue, buf);
		skb_set_owner_r(buf, new_sk);
	}
	release_sock(new_sk);

exit:
	release_sock(sk);
	return res;
}

/**
 * shutdown - shutdown socket connection
 * @sock: socket structure
 * @how: direction to close (must be SHUT_RDWR)
 *
 * Terminates connection (if necessary), then purges socket's receive queue.
 *
 * Returns 0 on success, errno otherwise
 */
static int shutdown(struct socket *sock, int how)
{
	struct sock *sk = sock->sk;
	struct tipc_port *tport = tipc_sk_port(sk);
	struct sk_buff *buf;
	int res;

	if (how != SHUT_RDWR)
		return -EINVAL;

	lock_sock(sk);

	switch (sock->state) {
	case SS_CONNECTING:
	case SS_CONNECTED:

restart:
		/* Disconnect and send a 'FIN+' or 'FIN-' message to peer */
		buf = __skb_dequeue(&sk->sk_receive_queue);
		if (buf) {
			if (TIPC_SKB_CB(buf)->handle != NULL) {
				kfree_skb(buf);
				goto restart;
			}
			tipc_disconnect(tport->ref);
			tipc_reject_msg(buf, TIPC_CONN_SHUTDOWN);
		} else {
			tipc_shutdown(tport->ref);
		}

		sock->state = SS_DISCONNECTING;

		/* fall through */

	case SS_DISCONNECTING:

		/* Discard any unreceived messages */
		__skb_queue_purge(&sk->sk_receive_queue);

		/* Wake up anyone sleeping in poll */
		sk->sk_state_change(sk);
		res = 0;
		break;

	default:
		res = -ENOTCONN;
	}

	release_sock(sk);
	return res;
}

/**
 * setsockopt - set socket option
 * @sock: socket structure
 * @lvl: option level
 * @opt: option identifier
 * @ov: pointer to new option value
 * @ol: length of option value
 *
 * For stream sockets only, accepts and ignores all IPPROTO_TCP options
 * (to ease compatibility).
 *
 * Returns 0 on success, errno otherwise
 */
static int setsockopt(struct socket *sock, int lvl, int opt, char __user *ov,
		      unsigned int ol)
{
	struct sock *sk = sock->sk;
	struct tipc_port *tport = tipc_sk_port(sk);
	u32 value;
	int res;

	if ((lvl == IPPROTO_TCP) && (sock->type == SOCK_STREAM))
		return 0;
	if (lvl != SOL_TIPC)
		return -ENOPROTOOPT;
	if (ol < sizeof(value))
		return -EINVAL;
	res = get_user(value, (u32 __user *)ov);
	if (res)
		return res;

	lock_sock(sk);

	switch (opt) {
	case TIPC_IMPORTANCE:
		res = tipc_set_portimportance(tport->ref, value);
		break;
	case TIPC_SRC_DROPPABLE:
		if (sock->type != SOCK_STREAM)
			res = tipc_set_portunreliable(tport->ref, value);
		else
			res = -ENOPROTOOPT;
		break;
	case TIPC_DEST_DROPPABLE:
		res = tipc_set_portunreturnable(tport->ref, value);
		break;
	case TIPC_CONN_TIMEOUT:
		tipc_sk(sk)->conn_timeout = value;
		/* no need to set "res", since already 0 at this point */
		break;
	default:
		res = -EINVAL;
	}

	release_sock(sk);

	return res;
}

/**
 * getsockopt - get socket option
 * @sock: socket structure
 * @lvl: option level
 * @opt: option identifier
 * @ov: receptacle for option value
 * @ol: receptacle for length of option value
 *
 * For stream sockets only, returns 0 length result for all IPPROTO_TCP options
 * (to ease compatibility).
 *
 * Returns 0 on success, errno otherwise
 */
static int getsockopt(struct socket *sock, int lvl, int opt, char __user *ov,
		      int __user *ol)
{
	struct sock *sk = sock->sk;
	struct tipc_port *tport = tipc_sk_port(sk);
	int len;
	u32 value;
	int res;

	if ((lvl == IPPROTO_TCP) && (sock->type == SOCK_STREAM))
		return put_user(0, ol);
	if (lvl != SOL_TIPC)
		return -ENOPROTOOPT;
	res = get_user(len, ol);
	if (res)
		return res;

	lock_sock(sk);

	switch (opt) {
	case TIPC_IMPORTANCE:
		res = tipc_portimportance(tport->ref, &value);
		break;
	case TIPC_SRC_DROPPABLE:
		res = tipc_portunreliable(tport->ref, &value);
		break;
	case TIPC_DEST_DROPPABLE:
		res = tipc_portunreturnable(tport->ref, &value);
		break;
	case TIPC_CONN_TIMEOUT:
		value = tipc_sk(sk)->conn_timeout;
		/* no need to set "res", since already 0 at this point */
		break;
	case TIPC_NODE_RECVQ_DEPTH:
		value = 0; /* was tipc_queue_size, now obsolete */
		break;
	case TIPC_SOCK_RECVQ_DEPTH:
		value = skb_queue_len(&sk->sk_receive_queue);
		break;
	default:
		res = -EINVAL;
	}

	release_sock(sk);

	if (res)
		return res;	/* "get" failed */

	if (len < sizeof(value))
		return -EINVAL;

	if (copy_to_user(ov, &value, sizeof(value)))
		return -EFAULT;

	return put_user(sizeof(value), ol);
}

/* Protocol switches for the various types of TIPC sockets */

static const struct proto_ops msg_ops = {
	.owner		= THIS_MODULE,
	.family		= AF_TIPC,
	.release	= release,
	.bind		= bind,
	.connect	= connect,
	.socketpair	= sock_no_socketpair,
	.accept		= sock_no_accept,
	.getname	= get_name,
	.poll		= poll,
	.ioctl		= sock_no_ioctl,
	.listen		= sock_no_listen,
	.shutdown	= shutdown,
	.setsockopt	= setsockopt,
	.getsockopt	= getsockopt,
	.sendmsg	= send_msg,
	.recvmsg	= recv_msg,
	.mmap		= sock_no_mmap,
	.sendpage	= sock_no_sendpage
};

static const struct proto_ops packet_ops = {
	.owner		= THIS_MODULE,
	.family		= AF_TIPC,
	.release	= release,
	.bind		= bind,
	.connect	= connect,
	.socketpair	= sock_no_socketpair,
	.accept		= accept,
	.getname	= get_name,
	.poll		= poll,
	.ioctl		= sock_no_ioctl,
	.listen		= listen,
	.shutdown	= shutdown,
	.setsockopt	= setsockopt,
	.getsockopt	= getsockopt,
	.sendmsg	= send_packet,
	.recvmsg	= recv_msg,
	.mmap		= sock_no_mmap,
	.sendpage	= sock_no_sendpage
};

static const struct proto_ops stream_ops = {
	.owner		= THIS_MODULE,
	.family		= AF_TIPC,
	.release	= release,
	.bind		= bind,
	.connect	= connect,
	.socketpair	= sock_no_socketpair,
	.accept		= accept,
	.getname	= get_name,
	.poll		= poll,
	.ioctl		= sock_no_ioctl,
	.listen		= listen,
	.shutdown	= shutdown,
	.setsockopt	= setsockopt,
	.getsockopt	= getsockopt,
	.sendmsg	= send_stream,
	.recvmsg	= recv_stream,
	.mmap		= sock_no_mmap,
	.sendpage	= sock_no_sendpage
};

static const struct net_proto_family tipc_family_ops = {
	.owner		= THIS_MODULE,
	.family		= AF_TIPC,
	.create		= tipc_sk_create
};

static struct proto tipc_proto = {
	.name		= "TIPC",
	.owner		= THIS_MODULE,
	.obj_size	= sizeof(struct tipc_sock),
	.sysctl_rmem	= sysctl_tipc_rmem
};

static struct proto tipc_proto_kern = {
	.name		= "TIPC",
	.obj_size	= sizeof(struct tipc_sock),
	.sysctl_rmem	= sysctl_tipc_rmem
};

/**
 * tipc_socket_init - initialize TIPC socket interface
 *
 * Returns 0 on success, errno otherwise
 */
int tipc_socket_init(void)
{
	int res;

	res = proto_register(&tipc_proto, 1);
	if (res) {
		pr_err("Failed to register TIPC protocol type\n");
		goto out;
	}

	res = sock_register(&tipc_family_ops);
	if (res) {
		pr_err("Failed to register TIPC socket type\n");
		proto_unregister(&tipc_proto);
		goto out;
	}

	sockets_enabled = 1;
 out:
	return res;
}

/**
 * tipc_socket_stop - stop TIPC socket interface
 */
void tipc_socket_stop(void)
{
	if (!sockets_enabled)
		return;

	sockets_enabled = 0;
	sock_unregister(tipc_family_ops.family);
	proto_unregister(&tipc_proto);
}