summaryrefslogtreecommitdiff
path: root/net/sctp/protocol.c
blob: 274d07bd774f0e9b9de3886ba902c3c205991050 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/* SCTP kernel implementation
 * (C) Copyright IBM Corp. 2001, 2004
 * Copyright (c) 1999-2000 Cisco, Inc.
 * Copyright (c) 1999-2001 Motorola, Inc.
 * Copyright (c) 2001 Intel Corp.
 * Copyright (c) 2001 Nokia, Inc.
 * Copyright (c) 2001 La Monte H.P. Yarroll
 *
 * This file is part of the SCTP kernel implementation
 *
 * Initialization/cleanup for SCTP protocol support.
 *
 * Please send any bug reports or fixes you make to the
 * email address(es):
 *    lksctp developers <linux-sctp@vger.kernel.org>
 *
 * Written or modified by:
 *    La Monte H.P. Yarroll <piggy@acm.org>
 *    Karl Knutson <karl@athena.chicago.il.us>
 *    Jon Grimm <jgrimm@us.ibm.com>
 *    Sridhar Samudrala <sri@us.ibm.com>
 *    Daisy Chang <daisyc@us.ibm.com>
 *    Ardelle Fan <ardelle.fan@intel.com>
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/module.h>
#include <linux/init.h>
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/seq_file.h>
#include <linux/memblock.h>
#include <linux/highmem.h>
#include <linux/slab.h>
#include <net/net_namespace.h>
#include <net/protocol.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/route.h>
#include <net/sctp/sctp.h>
#include <net/addrconf.h>
#include <net/inet_common.h>
#include <net/inet_ecn.h>
#include <net/udp_tunnel.h>

#define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024)

/* Global data structures. */
struct sctp_globals sctp_globals __read_mostly;

struct idr sctp_assocs_id;
DEFINE_SPINLOCK(sctp_assocs_id_lock);

static struct sctp_pf *sctp_pf_inet6_specific;
static struct sctp_pf *sctp_pf_inet_specific;
static struct sctp_af *sctp_af_v4_specific;
static struct sctp_af *sctp_af_v6_specific;

struct kmem_cache *sctp_chunk_cachep __read_mostly;
struct kmem_cache *sctp_bucket_cachep __read_mostly;

long sysctl_sctp_mem[3];
int sysctl_sctp_rmem[3];
int sysctl_sctp_wmem[3];

/* Private helper to extract ipv4 address and stash them in
 * the protocol structure.
 */
static void sctp_v4_copy_addrlist(struct list_head *addrlist,
				  struct net_device *dev)
{
	struct in_device *in_dev;
	struct in_ifaddr *ifa;
	struct sctp_sockaddr_entry *addr;

	rcu_read_lock();
	if ((in_dev = __in_dev_get_rcu(dev)) == NULL) {
		rcu_read_unlock();
		return;
	}

	in_dev_for_each_ifa_rcu(ifa, in_dev) {
		/* Add the address to the local list.  */
		addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
		if (addr) {
			addr->a.v4.sin_family = AF_INET;
			addr->a.v4.sin_addr.s_addr = ifa->ifa_local;
			addr->valid = 1;
			INIT_LIST_HEAD(&addr->list);
			list_add_tail(&addr->list, addrlist);
		}
	}

	rcu_read_unlock();
}

/* Extract our IP addresses from the system and stash them in the
 * protocol structure.
 */
static void sctp_get_local_addr_list(struct net *net)
{
	struct net_device *dev;
	struct list_head *pos;
	struct sctp_af *af;

	rcu_read_lock();
	for_each_netdev_rcu(net, dev) {
		list_for_each(pos, &sctp_address_families) {
			af = list_entry(pos, struct sctp_af, list);
			af->copy_addrlist(&net->sctp.local_addr_list, dev);
		}
	}
	rcu_read_unlock();
}

/* Free the existing local addresses.  */
static void sctp_free_local_addr_list(struct net *net)
{
	struct sctp_sockaddr_entry *addr;
	struct list_head *pos, *temp;

	list_for_each_safe(pos, temp, &net->sctp.local_addr_list) {
		addr = list_entry(pos, struct sctp_sockaddr_entry, list);
		list_del(pos);
		kfree(addr);
	}
}

/* Copy the local addresses which are valid for 'scope' into 'bp'.  */
int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp,
			      enum sctp_scope scope, gfp_t gfp, int copy_flags)
{
	struct sctp_sockaddr_entry *addr;
	union sctp_addr laddr;
	int error = 0;

	rcu_read_lock();
	list_for_each_entry_rcu(addr, &net->sctp.local_addr_list, list) {
		if (!addr->valid)
			continue;
		if (!sctp_in_scope(net, &addr->a, scope))
			continue;

		/* Now that the address is in scope, check to see if
		 * the address type is really supported by the local
		 * sock as well as the remote peer.
		 */
		if (addr->a.sa.sa_family == AF_INET &&
		    (!(copy_flags & SCTP_ADDR4_ALLOWED) ||
		     !(copy_flags & SCTP_ADDR4_PEERSUPP)))
			continue;
		if (addr->a.sa.sa_family == AF_INET6 &&
		    (!(copy_flags & SCTP_ADDR6_ALLOWED) ||
		     !(copy_flags & SCTP_ADDR6_PEERSUPP)))
			continue;

		laddr = addr->a;
		/* also works for setting ipv6 address port */
		laddr.v4.sin_port = htons(bp->port);
		if (sctp_bind_addr_state(bp, &laddr) != -1)
			continue;

		error = sctp_add_bind_addr(bp, &addr->a, sizeof(addr->a),
					   SCTP_ADDR_SRC, GFP_ATOMIC);
		if (error)
			break;
	}

	rcu_read_unlock();
	return error;
}

/* Copy over any ip options */
static void sctp_v4_copy_ip_options(struct sock *sk, struct sock *newsk)
{
	struct inet_sock *newinet, *inet = inet_sk(sk);
	struct ip_options_rcu *inet_opt, *newopt = NULL;

	newinet = inet_sk(newsk);

	rcu_read_lock();
	inet_opt = rcu_dereference(inet->inet_opt);
	if (inet_opt) {
		newopt = sock_kmalloc(newsk, sizeof(*inet_opt) +
				      inet_opt->opt.optlen, GFP_ATOMIC);
		if (newopt)
			memcpy(newopt, inet_opt, sizeof(*inet_opt) +
			       inet_opt->opt.optlen);
		else
			pr_err("%s: Failed to copy ip options\n", __func__);
	}
	RCU_INIT_POINTER(newinet->inet_opt, newopt);
	rcu_read_unlock();
}

/* Account for the IP options */
static int sctp_v4_ip_options_len(struct sock *sk)
{
	struct inet_sock *inet = inet_sk(sk);
	struct ip_options_rcu *inet_opt;
	int len = 0;

	rcu_read_lock();
	inet_opt = rcu_dereference(inet->inet_opt);
	if (inet_opt)
		len = inet_opt->opt.optlen;

	rcu_read_unlock();
	return len;
}

/* Initialize a sctp_addr from in incoming skb.  */
static void sctp_v4_from_skb(union sctp_addr *addr, struct sk_buff *skb,
			     int is_saddr)
{
	/* Always called on head skb, so this is safe */
	struct sctphdr *sh = sctp_hdr(skb);
	struct sockaddr_in *sa = &addr->v4;

	addr->v4.sin_family = AF_INET;

	if (is_saddr) {
		sa->sin_port = sh->source;
		sa->sin_addr.s_addr = ip_hdr(skb)->saddr;
	} else {
		sa->sin_port = sh->dest;
		sa->sin_addr.s_addr = ip_hdr(skb)->daddr;
	}
	memset(sa->sin_zero, 0, sizeof(sa->sin_zero));
}

/* Initialize an sctp_addr from a socket. */
static void sctp_v4_from_sk(union sctp_addr *addr, struct sock *sk)
{
	addr->v4.sin_family = AF_INET;
	addr->v4.sin_port = 0;
	addr->v4.sin_addr.s_addr = inet_sk(sk)->inet_rcv_saddr;
	memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
}

/* Initialize sk->sk_rcv_saddr from sctp_addr. */
static void sctp_v4_to_sk_saddr(union sctp_addr *addr, struct sock *sk)
{
	inet_sk(sk)->inet_rcv_saddr = addr->v4.sin_addr.s_addr;
}

/* Initialize sk->sk_daddr from sctp_addr. */
static void sctp_v4_to_sk_daddr(union sctp_addr *addr, struct sock *sk)
{
	inet_sk(sk)->inet_daddr = addr->v4.sin_addr.s_addr;
}

/* Initialize a sctp_addr from an address parameter. */
static bool sctp_v4_from_addr_param(union sctp_addr *addr,
				    union sctp_addr_param *param,
				    __be16 port, int iif)
{
	if (ntohs(param->v4.param_hdr.length) < sizeof(struct sctp_ipv4addr_param))
		return false;

	addr->v4.sin_family = AF_INET;
	addr->v4.sin_port = port;
	addr->v4.sin_addr.s_addr = param->v4.addr.s_addr;
	memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));

	return true;
}

/* Initialize an address parameter from a sctp_addr and return the length
 * of the address parameter.
 */
static int sctp_v4_to_addr_param(const union sctp_addr *addr,
				 union sctp_addr_param *param)
{
	int length = sizeof(struct sctp_ipv4addr_param);

	param->v4.param_hdr.type = SCTP_PARAM_IPV4_ADDRESS;
	param->v4.param_hdr.length = htons(length);
	param->v4.addr.s_addr = addr->v4.sin_addr.s_addr;

	return length;
}

/* Initialize a sctp_addr from a dst_entry. */
static void sctp_v4_dst_saddr(union sctp_addr *saddr, struct flowi4 *fl4,
			      __be16 port)
{
	saddr->v4.sin_family = AF_INET;
	saddr->v4.sin_port = port;
	saddr->v4.sin_addr.s_addr = fl4->saddr;
	memset(saddr->v4.sin_zero, 0, sizeof(saddr->v4.sin_zero));
}

/* Compare two addresses exactly. */
static int sctp_v4_cmp_addr(const union sctp_addr *addr1,
			    const union sctp_addr *addr2)
{
	if (addr1->sa.sa_family != addr2->sa.sa_family)
		return 0;
	if (addr1->v4.sin_port != addr2->v4.sin_port)
		return 0;
	if (addr1->v4.sin_addr.s_addr != addr2->v4.sin_addr.s_addr)
		return 0;

	return 1;
}

/* Initialize addr struct to INADDR_ANY. */
static void sctp_v4_inaddr_any(union sctp_addr *addr, __be16 port)
{
	addr->v4.sin_family = AF_INET;
	addr->v4.sin_addr.s_addr = htonl(INADDR_ANY);
	addr->v4.sin_port = port;
	memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
}

/* Is this a wildcard address? */
static int sctp_v4_is_any(const union sctp_addr *addr)
{
	return htonl(INADDR_ANY) == addr->v4.sin_addr.s_addr;
}

/* This function checks if the address is a valid address to be used for
 * SCTP binding.
 *
 * Output:
 * Return 0 - If the address is a non-unicast or an illegal address.
 * Return 1 - If the address is a unicast.
 */
static int sctp_v4_addr_valid(union sctp_addr *addr,
			      struct sctp_sock *sp,
			      const struct sk_buff *skb)
{
	/* IPv4 addresses not allowed */
	if (sp && ipv6_only_sock(sctp_opt2sk(sp)))
		return 0;

	/* Is this a non-unicast address or a unusable SCTP address? */
	if (IS_IPV4_UNUSABLE_ADDRESS(addr->v4.sin_addr.s_addr))
		return 0;

	/* Is this a broadcast address? */
	if (skb && skb_rtable(skb)->rt_flags & RTCF_BROADCAST)
		return 0;

	return 1;
}

/* Should this be available for binding?   */
static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp)
{
	struct sock *sk = &sp->inet.sk;
	struct net *net = sock_net(sk);
	int tb_id = RT_TABLE_LOCAL;
	int ret;

	tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ?: tb_id;
	ret = inet_addr_type_table(net, addr->v4.sin_addr.s_addr, tb_id);
	if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) &&
	   ret != RTN_LOCAL &&
	   !sp->inet.freebind &&
	    !READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind))
		return 0;

	if (ipv6_only_sock(sctp_opt2sk(sp)))
		return 0;

	return 1;
}

/* Checking the loopback, private and other address scopes as defined in
 * RFC 1918.   The IPv4 scoping is based on the draft for SCTP IPv4
 * scoping <draft-stewart-tsvwg-sctp-ipv4-00.txt>.
 *
 * Level 0 - unusable SCTP addresses
 * Level 1 - loopback address
 * Level 2 - link-local addresses
 * Level 3 - private addresses.
 * Level 4 - global addresses
 * For INIT and INIT-ACK address list, let L be the level of
 * requested destination address, sender and receiver
 * SHOULD include all of its addresses with level greater
 * than or equal to L.
 *
 * IPv4 scoping can be controlled through sysctl option
 * net.sctp.addr_scope_policy
 */
static enum sctp_scope sctp_v4_scope(union sctp_addr *addr)
{
	enum sctp_scope retval;

	/* Check for unusable SCTP addresses. */
	if (IS_IPV4_UNUSABLE_ADDRESS(addr->v4.sin_addr.s_addr)) {
		retval =  SCTP_SCOPE_UNUSABLE;
	} else if (ipv4_is_loopback(addr->v4.sin_addr.s_addr)) {
		retval = SCTP_SCOPE_LOOPBACK;
	} else if (ipv4_is_linklocal_169(addr->v4.sin_addr.s_addr)) {
		retval = SCTP_SCOPE_LINK;
	} else if (ipv4_is_private_10(addr->v4.sin_addr.s_addr) ||
		   ipv4_is_private_172(addr->v4.sin_addr.s_addr) ||
		   ipv4_is_private_192(addr->v4.sin_addr.s_addr) ||
		   ipv4_is_test_198(addr->v4.sin_addr.s_addr)) {
		retval = SCTP_SCOPE_PRIVATE;
	} else {
		retval = SCTP_SCOPE_GLOBAL;
	}

	return retval;
}

/* Returns a valid dst cache entry for the given source and destination ip
 * addresses. If an association is passed, trys to get a dst entry with a
 * source address that matches an address in the bind address list.
 */
static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
				struct flowi *fl, struct sock *sk)
{
	struct sctp_association *asoc = t->asoc;
	struct rtable *rt;
	struct flowi _fl;
	struct flowi4 *fl4 = &_fl.u.ip4;
	struct sctp_bind_addr *bp;
	struct sctp_sockaddr_entry *laddr;
	struct dst_entry *dst = NULL;
	union sctp_addr *daddr = &t->ipaddr;
	union sctp_addr dst_saddr;
	__u8 tos = inet_sk(sk)->tos;

	if (t->dscp & SCTP_DSCP_SET_MASK)
		tos = t->dscp & SCTP_DSCP_VAL_MASK;
	memset(&_fl, 0x0, sizeof(_fl));
	fl4->daddr  = daddr->v4.sin_addr.s_addr;
	fl4->fl4_dport = daddr->v4.sin_port;
	fl4->flowi4_proto = IPPROTO_SCTP;
	if (asoc) {
		fl4->flowi4_tos = RT_CONN_FLAGS_TOS(asoc->base.sk, tos);
		fl4->flowi4_oif = asoc->base.sk->sk_bound_dev_if;
		fl4->fl4_sport = htons(asoc->base.bind_addr.port);
	}
	if (saddr) {
		fl4->saddr = saddr->v4.sin_addr.s_addr;
		if (!fl4->fl4_sport)
			fl4->fl4_sport = saddr->v4.sin_port;
	}

	pr_debug("%s: dst:%pI4, src:%pI4 - ", __func__, &fl4->daddr,
		 &fl4->saddr);

	rt = ip_route_output_key(sock_net(sk), fl4);
	if (!IS_ERR(rt)) {
		dst = &rt->dst;
		t->dst = dst;
		memcpy(fl, &_fl, sizeof(_fl));
	}

	/* If there is no association or if a source address is passed, no
	 * more validation is required.
	 */
	if (!asoc || saddr)
		goto out;

	bp = &asoc->base.bind_addr;

	if (dst) {
		/* Walk through the bind address list and look for a bind
		 * address that matches the source address of the returned dst.
		 */
		sctp_v4_dst_saddr(&dst_saddr, fl4, htons(bp->port));
		rcu_read_lock();
		list_for_each_entry_rcu(laddr, &bp->address_list, list) {
			if (!laddr->valid || (laddr->state == SCTP_ADDR_DEL) ||
			    (laddr->state != SCTP_ADDR_SRC &&
			    !asoc->src_out_of_asoc_ok))
				continue;
			if (sctp_v4_cmp_addr(&dst_saddr, &laddr->a))
				goto out_unlock;
		}
		rcu_read_unlock();

		/* None of the bound addresses match the source address of the
		 * dst. So release it.
		 */
		dst_release(dst);
		dst = NULL;
	}

	/* Walk through the bind address list and try to get a dst that
	 * matches a bind address as the source address.
	 */
	rcu_read_lock();
	list_for_each_entry_rcu(laddr, &bp->address_list, list) {
		struct net_device *odev;

		if (!laddr->valid)
			continue;
		if (laddr->state != SCTP_ADDR_SRC ||
		    AF_INET != laddr->a.sa.sa_family)
			continue;

		fl4->fl4_sport = laddr->a.v4.sin_port;
		flowi4_update_output(fl4, asoc->base.sk->sk_bound_dev_if,
				     daddr->v4.sin_addr.s_addr,
				     laddr->a.v4.sin_addr.s_addr);

		rt = ip_route_output_key(sock_net(sk), fl4);
		if (IS_ERR(rt))
			continue;

		/* Ensure the src address belongs to the output
		 * interface.
		 */
		odev = __ip_dev_find(sock_net(sk), laddr->a.v4.sin_addr.s_addr,
				     false);
		if (!odev || odev->ifindex != fl4->flowi4_oif) {
			if (!dst) {
				dst = &rt->dst;
				t->dst = dst;
				memcpy(fl, &_fl, sizeof(_fl));
			} else {
				dst_release(&rt->dst);
			}
			continue;
		}

		dst_release(dst);
		dst = &rt->dst;
		t->dst = dst;
		memcpy(fl, &_fl, sizeof(_fl));
		break;
	}

out_unlock:
	rcu_read_unlock();
out:
	if (dst) {
		pr_debug("rt_dst:%pI4, rt_src:%pI4\n",
			 &fl->u.ip4.daddr, &fl->u.ip4.saddr);
	} else {
		t->dst = NULL;
		pr_debug("no route\n");
	}
}

/* For v4, the source address is cached in the route entry(dst). So no need
 * to cache it separately and hence this is an empty routine.
 */
static void sctp_v4_get_saddr(struct sctp_sock *sk,
			      struct sctp_transport *t,
			      struct flowi *fl)
{
	union sctp_addr *saddr = &t->saddr;
	struct rtable *rt = (struct rtable *)t->dst;

	if (rt) {
		saddr->v4.sin_family = AF_INET;
		saddr->v4.sin_addr.s_addr = fl->u.ip4.saddr;
	}
}

/* What interface did this skb arrive on? */
static int sctp_v4_skb_iif(const struct sk_buff *skb)
{
	return inet_iif(skb);
}

static int sctp_v4_skb_sdif(const struct sk_buff *skb)
{
	return inet_sdif(skb);
}

/* Was this packet marked by Explicit Congestion Notification? */
static int sctp_v4_is_ce(const struct sk_buff *skb)
{
	return INET_ECN_is_ce(ip_hdr(skb)->tos);
}

/* Create and initialize a new sk for the socket returned by accept(). */
static struct sock *sctp_v4_create_accept_sk(struct sock *sk,
					     struct sctp_association *asoc,
					     bool kern)
{
	struct sock *newsk = sk_alloc(sock_net(sk), PF_INET, GFP_KERNEL,
			sk->sk_prot, kern);
	struct inet_sock *newinet;

	if (!newsk)
		goto out;

	sock_init_data(NULL, newsk);

	sctp_copy_sock(newsk, sk, asoc);
	sock_reset_flag(newsk, SOCK_ZAPPED);

	sctp_v4_copy_ip_options(sk, newsk);

	newinet = inet_sk(newsk);

	newinet->inet_daddr = asoc->peer.primary_addr.v4.sin_addr.s_addr;

	if (newsk->sk_prot->init(newsk)) {
		sk_common_release(newsk);
		newsk = NULL;
	}

out:
	return newsk;
}

static int sctp_v4_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr)
{
	/* No address mapping for V4 sockets */
	memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
	return sizeof(struct sockaddr_in);
}

/* Dump the v4 addr to the seq file. */
static void sctp_v4_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr)
{
	seq_printf(seq, "%pI4 ", &addr->v4.sin_addr);
}

static void sctp_v4_ecn_capable(struct sock *sk)
{
	INET_ECN_xmit(sk);
}

static void sctp_addr_wq_timeout_handler(struct timer_list *t)
{
	struct net *net = from_timer(net, t, sctp.addr_wq_timer);
	struct sctp_sockaddr_entry *addrw, *temp;
	struct sctp_sock *sp;

	spin_lock_bh(&net->sctp.addr_wq_lock);

	list_for_each_entry_safe(addrw, temp, &net->sctp.addr_waitq, list) {
		pr_debug("%s: the first ent in wq:%p is addr:%pISc for cmd:%d at "
			 "entry:%p\n", __func__, &net->sctp.addr_waitq, &addrw->a.sa,
			 addrw->state, addrw);

#if IS_ENABLED(CONFIG_IPV6)
		/* Now we send an ASCONF for each association */
		/* Note. we currently don't handle link local IPv6 addressees */
		if (addrw->a.sa.sa_family == AF_INET6) {
			struct in6_addr *in6;

			if (ipv6_addr_type(&addrw->a.v6.sin6_addr) &
			    IPV6_ADDR_LINKLOCAL)
				goto free_next;

			in6 = (struct in6_addr *)&addrw->a.v6.sin6_addr;
			if (ipv6_chk_addr(net, in6, NULL, 0) == 0 &&
			    addrw->state == SCTP_ADDR_NEW) {
				unsigned long timeo_val;

				pr_debug("%s: this is on DAD, trying %d sec "
					 "later\n", __func__,
					 SCTP_ADDRESS_TICK_DELAY);

				timeo_val = jiffies;
				timeo_val += msecs_to_jiffies(SCTP_ADDRESS_TICK_DELAY);
				mod_timer(&net->sctp.addr_wq_timer, timeo_val);
				break;
			}
		}
#endif
		list_for_each_entry(sp, &net->sctp.auto_asconf_splist, auto_asconf_list) {
			struct sock *sk;

			sk = sctp_opt2sk(sp);
			/* ignore bound-specific endpoints */
			if (!sctp_is_ep_boundall(sk))
				continue;
			bh_lock_sock(sk);
			if (sctp_asconf_mgmt(sp, addrw) < 0)
				pr_debug("%s: sctp_asconf_mgmt failed\n", __func__);
			bh_unlock_sock(sk);
		}
#if IS_ENABLED(CONFIG_IPV6)
free_next:
#endif
		list_del(&addrw->list);
		kfree(addrw);
	}
	spin_unlock_bh(&net->sctp.addr_wq_lock);
}

static void sctp_free_addr_wq(struct net *net)
{
	struct sctp_sockaddr_entry *addrw;
	struct sctp_sockaddr_entry *temp;

	spin_lock_bh(&net->sctp.addr_wq_lock);
	del_timer(&net->sctp.addr_wq_timer);
	list_for_each_entry_safe(addrw, temp, &net->sctp.addr_waitq, list) {
		list_del(&addrw->list);
		kfree(addrw);
	}
	spin_unlock_bh(&net->sctp.addr_wq_lock);
}

/* lookup the entry for the same address in the addr_waitq
 * sctp_addr_wq MUST be locked
 */
static struct sctp_sockaddr_entry *sctp_addr_wq_lookup(struct net *net,
					struct sctp_sockaddr_entry *addr)
{
	struct sctp_sockaddr_entry *addrw;

	list_for_each_entry(addrw, &net->sctp.addr_waitq, list) {
		if (addrw->a.sa.sa_family != addr->a.sa.sa_family)
			continue;
		if (addrw->a.sa.sa_family == AF_INET) {
			if (addrw->a.v4.sin_addr.s_addr ==
			    addr->a.v4.sin_addr.s_addr)
				return addrw;
		} else if (addrw->a.sa.sa_family == AF_INET6) {
			if (ipv6_addr_equal(&addrw->a.v6.sin6_addr,
			    &addr->a.v6.sin6_addr))
				return addrw;
		}
	}
	return NULL;
}

void sctp_addr_wq_mgmt(struct net *net, struct sctp_sockaddr_entry *addr, int cmd)
{
	struct sctp_sockaddr_entry *addrw;
	unsigned long timeo_val;

	/* first, we check if an opposite message already exist in the queue.
	 * If we found such message, it is removed.
	 * This operation is a bit stupid, but the DHCP client attaches the
	 * new address after a couple of addition and deletion of that address
	 */

	spin_lock_bh(&net->sctp.addr_wq_lock);
	/* Offsets existing events in addr_wq */
	addrw = sctp_addr_wq_lookup(net, addr);
	if (addrw) {
		if (addrw->state != cmd) {
			pr_debug("%s: offsets existing entry for %d, addr:%pISc "
				 "in wq:%p\n", __func__, addrw->state, &addrw->a.sa,
				 &net->sctp.addr_waitq);

			list_del(&addrw->list);
			kfree(addrw);
		}
		spin_unlock_bh(&net->sctp.addr_wq_lock);
		return;
	}

	/* OK, we have to add the new address to the wait queue */
	addrw = kmemdup(addr, sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC);
	if (addrw == NULL) {
		spin_unlock_bh(&net->sctp.addr_wq_lock);
		return;
	}
	addrw->state = cmd;
	list_add_tail(&addrw->list, &net->sctp.addr_waitq);

	pr_debug("%s: add new entry for cmd:%d, addr:%pISc in wq:%p\n",
		 __func__, addrw->state, &addrw->a.sa, &net->sctp.addr_waitq);

	if (!timer_pending(&net->sctp.addr_wq_timer)) {
		timeo_val = jiffies;
		timeo_val += msecs_to_jiffies(SCTP_ADDRESS_TICK_DELAY);
		mod_timer(&net->sctp.addr_wq_timer, timeo_val);
	}
	spin_unlock_bh(&net->sctp.addr_wq_lock);
}

/* Event handler for inet address addition/deletion events.
 * The sctp_local_addr_list needs to be protocted by a spin lock since
 * multiple notifiers (say IPv4 and IPv6) may be running at the same
 * time and thus corrupt the list.
 * The reader side is protected with RCU.
 */
static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev,
			       void *ptr)
{
	struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
	struct sctp_sockaddr_entry *addr = NULL;
	struct sctp_sockaddr_entry *temp;
	struct net *net = dev_net(ifa->ifa_dev->dev);
	int found = 0;

	switch (ev) {
	case NETDEV_UP:
		addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
		if (addr) {
			addr->a.v4.sin_family = AF_INET;
			addr->a.v4.sin_addr.s_addr = ifa->ifa_local;
			addr->valid = 1;
			spin_lock_bh(&net->sctp.local_addr_lock);
			list_add_tail_rcu(&addr->list, &net->sctp.local_addr_list);
			sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_NEW);
			spin_unlock_bh(&net->sctp.local_addr_lock);
		}
		break;
	case NETDEV_DOWN:
		spin_lock_bh(&net->sctp.local_addr_lock);
		list_for_each_entry_safe(addr, temp,
					&net->sctp.local_addr_list, list) {
			if (addr->a.sa.sa_family == AF_INET &&
					addr->a.v4.sin_addr.s_addr ==
					ifa->ifa_local) {
				sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL);
				found = 1;
				addr->valid = 0;
				list_del_rcu(&addr->list);
				break;
			}
		}
		spin_unlock_bh(&net->sctp.local_addr_lock);
		if (found)
			kfree_rcu(addr, rcu);
		break;
	}

	return NOTIFY_DONE;
}

/*
 * Initialize the control inode/socket with a control endpoint data
 * structure.  This endpoint is reserved exclusively for the OOTB processing.
 */
static int sctp_ctl_sock_init(struct net *net)
{
	int err;
	sa_family_t family = PF_INET;

	if (sctp_get_pf_specific(PF_INET6))
		family = PF_INET6;

	err = inet_ctl_sock_create(&net->sctp.ctl_sock, family,
				   SOCK_SEQPACKET, IPPROTO_SCTP, net);

	/* If IPv6 socket could not be created, try the IPv4 socket */
	if (err < 0 && family == PF_INET6)
		err = inet_ctl_sock_create(&net->sctp.ctl_sock, AF_INET,
					   SOCK_SEQPACKET, IPPROTO_SCTP,
					   net);

	if (err < 0) {
		pr_err("Failed to create the SCTP control socket\n");
		return err;
	}
	return 0;
}

static int sctp_udp_rcv(struct sock *sk, struct sk_buff *skb)
{
	SCTP_INPUT_CB(skb)->encap_port = udp_hdr(skb)->source;

	skb_set_transport_header(skb, sizeof(struct udphdr));
	sctp_rcv(skb);
	return 0;
}

int sctp_udp_sock_start(struct net *net)
{
	struct udp_tunnel_sock_cfg tuncfg = {NULL};
	struct udp_port_cfg udp_conf = {0};
	struct socket *sock;
	int err;

	udp_conf.family = AF_INET;
	udp_conf.local_ip.s_addr = htonl(INADDR_ANY);
	udp_conf.local_udp_port = htons(net->sctp.udp_port);
	err = udp_sock_create(net, &udp_conf, &sock);
	if (err) {
		pr_err("Failed to create the SCTP UDP tunneling v4 sock\n");
		return err;
	}

	tuncfg.encap_type = 1;
	tuncfg.encap_rcv = sctp_udp_rcv;
	tuncfg.encap_err_lookup = sctp_udp_v4_err;
	setup_udp_tunnel_sock(net, sock, &tuncfg);
	net->sctp.udp4_sock = sock->sk;

#if IS_ENABLED(CONFIG_IPV6)
	memset(&udp_conf, 0, sizeof(udp_conf));

	udp_conf.family = AF_INET6;
	udp_conf.local_ip6 = in6addr_any;
	udp_conf.local_udp_port = htons(net->sctp.udp_port);
	udp_conf.use_udp6_rx_checksums = true;
	udp_conf.ipv6_v6only = true;
	err = udp_sock_create(net, &udp_conf, &sock);
	if (err) {
		pr_err("Failed to create the SCTP UDP tunneling v6 sock\n");
		udp_tunnel_sock_release(net->sctp.udp4_sock->sk_socket);
		net->sctp.udp4_sock = NULL;
		return err;
	}

	tuncfg.encap_type = 1;
	tuncfg.encap_rcv = sctp_udp_rcv;
	tuncfg.encap_err_lookup = sctp_udp_v6_err;
	setup_udp_tunnel_sock(net, sock, &tuncfg);
	net->sctp.udp6_sock = sock->sk;
#endif

	return 0;
}

void sctp_udp_sock_stop(struct net *net)
{
	if (net->sctp.udp4_sock) {
		udp_tunnel_sock_release(net->sctp.udp4_sock->sk_socket);
		net->sctp.udp4_sock = NULL;
	}
	if (net->sctp.udp6_sock) {
		udp_tunnel_sock_release(net->sctp.udp6_sock->sk_socket);
		net->sctp.udp6_sock = NULL;
	}
}

/* Register address family specific functions. */
int sctp_register_af(struct sctp_af *af)
{
	switch (af->sa_family) {
	case AF_INET:
		if (sctp_af_v4_specific)
			return 0;
		sctp_af_v4_specific = af;
		break;
	case AF_INET6:
		if (sctp_af_v6_specific)
			return 0;
		sctp_af_v6_specific = af;
		break;
	default:
		return 0;
	}

	INIT_LIST_HEAD(&af->list);
	list_add_tail(&af->list, &sctp_address_families);
	return 1;
}

/* Get the table of functions for manipulating a particular address
 * family.
 */
struct sctp_af *sctp_get_af_specific(sa_family_t family)
{
	switch (family) {
	case AF_INET:
		return sctp_af_v4_specific;
	case AF_INET6:
		return sctp_af_v6_specific;
	default:
		return NULL;
	}
}

/* Common code to initialize a AF_INET msg_name. */
static void sctp_inet_msgname(char *msgname, int *addr_len)
{
	struct sockaddr_in *sin;

	sin = (struct sockaddr_in *)msgname;
	*addr_len = sizeof(struct sockaddr_in);
	sin->sin_family = AF_INET;
	memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
}

/* Copy the primary address of the peer primary address as the msg_name. */
static void sctp_inet_event_msgname(struct sctp_ulpevent *event, char *msgname,
				    int *addr_len)
{
	struct sockaddr_in *sin, *sinfrom;

	if (msgname) {
		struct sctp_association *asoc;

		asoc = event->asoc;
		sctp_inet_msgname(msgname, addr_len);
		sin = (struct sockaddr_in *)msgname;
		sinfrom = &asoc->peer.primary_addr.v4;
		sin->sin_port = htons(asoc->peer.port);
		sin->sin_addr.s_addr = sinfrom->sin_addr.s_addr;
	}
}

/* Initialize and copy out a msgname from an inbound skb. */
static void sctp_inet_skb_msgname(struct sk_buff *skb, char *msgname, int *len)
{
	if (msgname) {
		struct sctphdr *sh = sctp_hdr(skb);
		struct sockaddr_in *sin = (struct sockaddr_in *)msgname;

		sctp_inet_msgname(msgname, len);
		sin->sin_port = sh->source;
		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
	}
}

/* Do we support this AF? */
static int sctp_inet_af_supported(sa_family_t family, struct sctp_sock *sp)
{
	/* PF_INET only supports AF_INET addresses. */
	return AF_INET == family;
}

/* Address matching with wildcards allowed. */
static int sctp_inet_cmp_addr(const union sctp_addr *addr1,
			      const union sctp_addr *addr2,
			      struct sctp_sock *opt)
{
	/* PF_INET only supports AF_INET addresses. */
	if (addr1->sa.sa_family != addr2->sa.sa_family)
		return 0;
	if (htonl(INADDR_ANY) == addr1->v4.sin_addr.s_addr ||
	    htonl(INADDR_ANY) == addr2->v4.sin_addr.s_addr)
		return 1;
	if (addr1->v4.sin_addr.s_addr == addr2->v4.sin_addr.s_addr)
		return 1;

	return 0;
}

/* Verify that provided sockaddr looks bindable.  Common verification has
 * already been taken care of.
 */
static int sctp_inet_bind_verify(struct sctp_sock *opt, union sctp_addr *addr)
{
	return sctp_v4_available(addr, opt);
}

/* Verify that sockaddr looks sendable.  Common verification has already
 * been taken care of.
 */
static int sctp_inet_send_verify(struct sctp_sock *opt, union sctp_addr *addr)
{
	return 1;
}

/* Fill in Supported Address Type information for INIT and INIT-ACK
 * chunks.  Returns number of addresses supported.
 */
static int sctp_inet_supported_addrs(const struct sctp_sock *opt,
				     __be16 *types)
{
	types[0] = SCTP_PARAM_IPV4_ADDRESS;
	return 1;
}

/* Wrapper routine that calls the ip transmit routine. */
static inline int sctp_v4_xmit(struct sk_buff *skb, struct sctp_transport *t)
{
	struct dst_entry *dst = dst_clone(t->dst);
	struct flowi4 *fl4 = &t->fl.u.ip4;
	struct sock *sk = skb->sk;
	struct inet_sock *inet = inet_sk(sk);
	__u8 dscp = inet->tos;
	__be16 df = 0;

	pr_debug("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", __func__, skb,
		 skb->len, &fl4->saddr, &fl4->daddr);

	if (t->dscp & SCTP_DSCP_SET_MASK)
		dscp = t->dscp & SCTP_DSCP_VAL_MASK;

	inet->pmtudisc = t->param_flags & SPP_PMTUD_ENABLE ? IP_PMTUDISC_DO
							   : IP_PMTUDISC_DONT;
	SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS);

	if (!t->encap_port || !sctp_sk(sk)->udp_port) {
		skb_dst_set(skb, dst);
		return __ip_queue_xmit(sk, skb, &t->fl, dscp);
	}

	if (skb_is_gso(skb))
		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;

	if (ip_dont_fragment(sk, dst) && !skb->ignore_df)
		df = htons(IP_DF);

	skb->encapsulation = 1;
	skb_reset_inner_mac_header(skb);
	skb_reset_inner_transport_header(skb);
	skb_set_inner_ipproto(skb, IPPROTO_SCTP);
	udp_tunnel_xmit_skb((struct rtable *)dst, sk, skb, fl4->saddr,
			    fl4->daddr, dscp, ip4_dst_hoplimit(dst), df,
			    sctp_sk(sk)->udp_port, t->encap_port, false, false);
	return 0;
}

static struct sctp_af sctp_af_inet;

static struct sctp_pf sctp_pf_inet = {
	.event_msgname = sctp_inet_event_msgname,
	.skb_msgname   = sctp_inet_skb_msgname,
	.af_supported  = sctp_inet_af_supported,
	.cmp_addr      = sctp_inet_cmp_addr,
	.bind_verify   = sctp_inet_bind_verify,
	.send_verify   = sctp_inet_send_verify,
	.supported_addrs = sctp_inet_supported_addrs,
	.create_accept_sk = sctp_v4_create_accept_sk,
	.addr_to_user  = sctp_v4_addr_to_user,
	.to_sk_saddr   = sctp_v4_to_sk_saddr,
	.to_sk_daddr   = sctp_v4_to_sk_daddr,
	.copy_ip_options = sctp_v4_copy_ip_options,
	.af            = &sctp_af_inet
};

/* Notifier for inetaddr addition/deletion events.  */
static struct notifier_block sctp_inetaddr_notifier = {
	.notifier_call = sctp_inetaddr_event,
};

/* Socket operations.  */
static const struct proto_ops inet_seqpacket_ops = {
	.family		   = PF_INET,
	.owner		   = THIS_MODULE,
	.release	   = inet_release,	/* Needs to be wrapped... */
	.bind		   = inet_bind,
	.connect	   = sctp_inet_connect,
	.socketpair	   = sock_no_socketpair,
	.accept		   = inet_accept,
	.getname	   = inet_getname,	/* Semantics are different.  */
	.poll		   = sctp_poll,
	.ioctl		   = inet_ioctl,
	.gettstamp	   = sock_gettstamp,
	.listen		   = sctp_inet_listen,
	.shutdown	   = inet_shutdown,	/* Looks harmless.  */
	.setsockopt	   = sock_common_setsockopt, /* IP_SOL IP_OPTION is a problem */
	.getsockopt	   = sock_common_getsockopt,
	.sendmsg	   = inet_sendmsg,
	.recvmsg	   = inet_recvmsg,
	.mmap		   = sock_no_mmap,
};

/* Registration with AF_INET family.  */
static struct inet_protosw sctp_seqpacket_protosw = {
	.type       = SOCK_SEQPACKET,
	.protocol   = IPPROTO_SCTP,
	.prot       = &sctp_prot,
	.ops        = &inet_seqpacket_ops,
	.flags      = SCTP_PROTOSW_FLAG
};
static struct inet_protosw sctp_stream_protosw = {
	.type       = SOCK_STREAM,
	.protocol   = IPPROTO_SCTP,
	.prot       = &sctp_prot,
	.ops        = &inet_seqpacket_ops,
	.flags      = SCTP_PROTOSW_FLAG
};

static int sctp4_rcv(struct sk_buff *skb)
{
	SCTP_INPUT_CB(skb)->encap_port = 0;
	return sctp_rcv(skb);
}

/* Register with IP layer.  */
static const struct net_protocol sctp_protocol = {
	.handler     = sctp4_rcv,
	.err_handler = sctp_v4_err,
	.no_policy   = 1,
	.icmp_strict_tag_validation = 1,
};

/* IPv4 address related functions.  */
static struct sctp_af sctp_af_inet = {
	.sa_family	   = AF_INET,
	.sctp_xmit	   = sctp_v4_xmit,
	.setsockopt	   = ip_setsockopt,
	.getsockopt	   = ip_getsockopt,
	.get_dst	   = sctp_v4_get_dst,
	.get_saddr	   = sctp_v4_get_saddr,
	.copy_addrlist	   = sctp_v4_copy_addrlist,
	.from_skb	   = sctp_v4_from_skb,
	.from_sk	   = sctp_v4_from_sk,
	.from_addr_param   = sctp_v4_from_addr_param,
	.to_addr_param	   = sctp_v4_to_addr_param,
	.cmp_addr	   = sctp_v4_cmp_addr,
	.addr_valid	   = sctp_v4_addr_valid,
	.inaddr_any	   = sctp_v4_inaddr_any,
	.is_any		   = sctp_v4_is_any,
	.available	   = sctp_v4_available,
	.scope		   = sctp_v4_scope,
	.skb_iif	   = sctp_v4_skb_iif,
	.skb_sdif	   = sctp_v4_skb_sdif,
	.is_ce		   = sctp_v4_is_ce,
	.seq_dump_addr	   = sctp_v4_seq_dump_addr,
	.ecn_capable	   = sctp_v4_ecn_capable,
	.net_header_len	   = sizeof(struct iphdr),
	.sockaddr_len	   = sizeof(struct sockaddr_in),
	.ip_options_len	   = sctp_v4_ip_options_len,
};

struct sctp_pf *sctp_get_pf_specific(sa_family_t family)
{
	switch (family) {
	case PF_INET:
		return sctp_pf_inet_specific;
	case PF_INET6:
		return sctp_pf_inet6_specific;
	default:
		return NULL;
	}
}

/* Register the PF specific function table.  */
int sctp_register_pf(struct sctp_pf *pf, sa_family_t family)
{
	switch (family) {
	case PF_INET:
		if (sctp_pf_inet_specific)
			return 0;
		sctp_pf_inet_specific = pf;
		break;
	case PF_INET6:
		if (sctp_pf_inet6_specific)
			return 0;
		sctp_pf_inet6_specific = pf;
		break;
	default:
		return 0;
	}
	return 1;
}

static inline int init_sctp_mibs(struct net *net)
{
	net->sctp.sctp_statistics = alloc_percpu(struct sctp_mib);
	if (!net->sctp.sctp_statistics)
		return -ENOMEM;
	return 0;
}

static inline void cleanup_sctp_mibs(struct net *net)
{
	free_percpu(net->sctp.sctp_statistics);
}

static void sctp_v4_pf_init(void)
{
	/* Initialize the SCTP specific PF functions. */
	sctp_register_pf(&sctp_pf_inet, PF_INET);
	sctp_register_af(&sctp_af_inet);
}

static void sctp_v4_pf_exit(void)
{
	list_del(&sctp_af_inet.list);
}

static int sctp_v4_protosw_init(void)
{
	int rc;

	rc = proto_register(&sctp_prot, 1);
	if (rc)
		return rc;

	/* Register SCTP(UDP and TCP style) with socket layer.  */
	inet_register_protosw(&sctp_seqpacket_protosw);
	inet_register_protosw(&sctp_stream_protosw);

	return 0;
}

static void sctp_v4_protosw_exit(void)
{
	inet_unregister_protosw(&sctp_stream_protosw);
	inet_unregister_protosw(&sctp_seqpacket_protosw);
	proto_unregister(&sctp_prot);
}

static int sctp_v4_add_protocol(void)
{
	/* Register notifier for inet address additions/deletions. */
	register_inetaddr_notifier(&sctp_inetaddr_notifier);

	/* Register SCTP with inet layer.  */
	if (inet_add_protocol(&sctp_protocol, IPPROTO_SCTP) < 0)
		return -EAGAIN;

	return 0;
}

static void sctp_v4_del_protocol(void)
{
	inet_del_protocol(&sctp_protocol, IPPROTO_SCTP);
	unregister_inetaddr_notifier(&sctp_inetaddr_notifier);
}

static int __net_init sctp_defaults_init(struct net *net)
{
	int status;

	/*
	 * 14. Suggested SCTP Protocol Parameter Values
	 */
	/* The following protocol parameters are RECOMMENDED:  */
	/* RTO.Initial              - 3  seconds */
	net->sctp.rto_initial			= SCTP_RTO_INITIAL;
	/* RTO.Min                  - 1  second */
	net->sctp.rto_min	 		= SCTP_RTO_MIN;
	/* RTO.Max                 -  60 seconds */
	net->sctp.rto_max 			= SCTP_RTO_MAX;
	/* RTO.Alpha                - 1/8 */
	net->sctp.rto_alpha			= SCTP_RTO_ALPHA;
	/* RTO.Beta                 - 1/4 */
	net->sctp.rto_beta			= SCTP_RTO_BETA;

	/* Valid.Cookie.Life        - 60  seconds */
	net->sctp.valid_cookie_life		= SCTP_DEFAULT_COOKIE_LIFE;

	/* Whether Cookie Preservative is enabled(1) or not(0) */
	net->sctp.cookie_preserve_enable 	= 1;

	/* Default sctp sockets to use md5 as their hmac alg */
#if defined (CONFIG_SCTP_DEFAULT_COOKIE_HMAC_MD5)
	net->sctp.sctp_hmac_alg			= "md5";
#elif defined (CONFIG_SCTP_DEFAULT_COOKIE_HMAC_SHA1)
	net->sctp.sctp_hmac_alg			= "sha1";
#else
	net->sctp.sctp_hmac_alg			= NULL;
#endif

	/* Max.Burst		    - 4 */
	net->sctp.max_burst			= SCTP_DEFAULT_MAX_BURST;

	/* Disable of Primary Path Switchover by default */
	net->sctp.ps_retrans = SCTP_PS_RETRANS_MAX;

	/* Enable pf state by default */
	net->sctp.pf_enable = 1;

	/* Ignore pf exposure feature by default */
	net->sctp.pf_expose = SCTP_PF_EXPOSE_UNSET;

	/* Association.Max.Retrans  - 10 attempts
	 * Path.Max.Retrans         - 5  attempts (per destination address)
	 * Max.Init.Retransmits     - 8  attempts
	 */
	net->sctp.max_retrans_association	= 10;
	net->sctp.max_retrans_path		= 5;
	net->sctp.max_retrans_init		= 8;

	/* Sendbuffer growth	    - do per-socket accounting */
	net->sctp.sndbuf_policy			= 0;

	/* Rcvbuffer growth	    - do per-socket accounting */
	net->sctp.rcvbuf_policy			= 0;

	/* HB.interval              - 30 seconds */
	net->sctp.hb_interval			= SCTP_DEFAULT_TIMEOUT_HEARTBEAT;

	/* delayed SACK timeout */
	net->sctp.sack_timeout			= SCTP_DEFAULT_TIMEOUT_SACK;

	/* Disable ADDIP by default. */
	net->sctp.addip_enable = 0;
	net->sctp.addip_noauth = 0;
	net->sctp.default_auto_asconf = 0;

	/* Enable PR-SCTP by default. */
	net->sctp.prsctp_enable = 1;

	/* Disable RECONF by default. */
	net->sctp.reconf_enable = 0;

	/* Disable AUTH by default. */
	net->sctp.auth_enable = 0;

	/* Enable ECN by default. */
	net->sctp.ecn_enable = 1;

	/* Set UDP tunneling listening port to 0 by default */
	net->sctp.udp_port = 0;

	/* Set remote encap port to 0 by default */
	net->sctp.encap_port = 0;

	/* Set SCOPE policy to enabled */
	net->sctp.scope_policy = SCTP_SCOPE_POLICY_ENABLE;

	/* Set the default rwnd update threshold */
	net->sctp.rwnd_upd_shift = SCTP_DEFAULT_RWND_SHIFT;

	/* Initialize maximum autoclose timeout. */
	net->sctp.max_autoclose		= INT_MAX / HZ;

#ifdef CONFIG_NET_L3_MASTER_DEV
	net->sctp.l3mdev_accept = 1;
#endif

	status = sctp_sysctl_net_register(net);
	if (status)
		goto err_sysctl_register;

	/* Allocate and initialise sctp mibs.  */
	status = init_sctp_mibs(net);
	if (status)
		goto err_init_mibs;

#ifdef CONFIG_PROC_FS
	/* Initialize proc fs directory.  */
	status = sctp_proc_init(net);
	if (status)
		goto err_init_proc;
#endif

	sctp_dbg_objcnt_init(net);

	/* Initialize the local address list. */
	INIT_LIST_HEAD(&net->sctp.local_addr_list);
	spin_lock_init(&net->sctp.local_addr_lock);
	sctp_get_local_addr_list(net);

	/* Initialize the address event list */
	INIT_LIST_HEAD(&net->sctp.addr_waitq);
	INIT_LIST_HEAD(&net->sctp.auto_asconf_splist);
	spin_lock_init(&net->sctp.addr_wq_lock);
	net->sctp.addr_wq_timer.expires = 0;
	timer_setup(&net->sctp.addr_wq_timer, sctp_addr_wq_timeout_handler, 0);

	return 0;

#ifdef CONFIG_PROC_FS
err_init_proc:
	cleanup_sctp_mibs(net);
#endif
err_init_mibs:
	sctp_sysctl_net_unregister(net);
err_sysctl_register:
	return status;
}

static void __net_exit sctp_defaults_exit(struct net *net)
{
	/* Free the local address list */
	sctp_free_addr_wq(net);
	sctp_free_local_addr_list(net);

#ifdef CONFIG_PROC_FS
	remove_proc_subtree("sctp", net->proc_net);
	net->sctp.proc_net_sctp = NULL;
#endif
	cleanup_sctp_mibs(net);
	sctp_sysctl_net_unregister(net);
}

static struct pernet_operations sctp_defaults_ops = {
	.init = sctp_defaults_init,
	.exit = sctp_defaults_exit,
};

static int __net_init sctp_ctrlsock_init(struct net *net)
{
	int status;

	/* Initialize the control inode/socket for handling OOTB packets.  */
	status = sctp_ctl_sock_init(net);
	if (status)
		pr_err("Failed to initialize the SCTP control sock\n");

	return status;
}

static void __net_exit sctp_ctrlsock_exit(struct net *net)
{
	/* Free the control endpoint.  */
	inet_ctl_sock_destroy(net->sctp.ctl_sock);
}

static struct pernet_operations sctp_ctrlsock_ops = {
	.init = sctp_ctrlsock_init,
	.exit = sctp_ctrlsock_exit,
};

/* Initialize the universe into something sensible.  */
static __init int sctp_init(void)
{
	unsigned long nr_pages = totalram_pages();
	unsigned long limit;
	unsigned long goal;
	int max_entry_order;
	int num_entries;
	int max_share;
	int status;
	int order;
	int i;

	sock_skb_cb_check_size(sizeof(struct sctp_ulpevent));

	/* Allocate bind_bucket and chunk caches. */
	status = -ENOBUFS;
	sctp_bucket_cachep = kmem_cache_create("sctp_bind_bucket",
					       sizeof(struct sctp_bind_bucket),
					       0, SLAB_HWCACHE_ALIGN,
					       NULL);
	if (!sctp_bucket_cachep)
		goto out;

	sctp_chunk_cachep = kmem_cache_create("sctp_chunk",
					       sizeof(struct sctp_chunk),
					       0, SLAB_HWCACHE_ALIGN,
					       NULL);
	if (!sctp_chunk_cachep)
		goto err_chunk_cachep;

	status = percpu_counter_init(&sctp_sockets_allocated, 0, GFP_KERNEL);
	if (status)
		goto err_percpu_counter_init;

	/* Implementation specific variables. */

	/* Initialize default stream count setup information. */
	sctp_max_instreams    		= SCTP_DEFAULT_INSTREAMS;
	sctp_max_outstreams   		= SCTP_DEFAULT_OUTSTREAMS;

	/* Initialize handle used for association ids. */
	idr_init(&sctp_assocs_id);

	limit = nr_free_buffer_pages() / 8;
	limit = max(limit, 128UL);
	sysctl_sctp_mem[0] = limit / 4 * 3;
	sysctl_sctp_mem[1] = limit;
	sysctl_sctp_mem[2] = sysctl_sctp_mem[0] * 2;

	/* Set per-socket limits to no more than 1/128 the pressure threshold*/
	limit = (sysctl_sctp_mem[1]) << (PAGE_SHIFT - 7);
	max_share = min(4UL*1024*1024, limit);

	sysctl_sctp_rmem[0] = PAGE_SIZE; /* give each asoc 1 page min */
	sysctl_sctp_rmem[1] = 1500 * SKB_TRUESIZE(1);
	sysctl_sctp_rmem[2] = max(sysctl_sctp_rmem[1], max_share);

	sysctl_sctp_wmem[0] = PAGE_SIZE;
	sysctl_sctp_wmem[1] = 16*1024;
	sysctl_sctp_wmem[2] = max(64*1024, max_share);

	/* Size and allocate the association hash table.
	 * The methodology is similar to that of the tcp hash tables.
	 * Though not identical.  Start by getting a goal size
	 */
	if (nr_pages >= (128 * 1024))
		goal = nr_pages >> (22 - PAGE_SHIFT);
	else
		goal = nr_pages >> (24 - PAGE_SHIFT);

	/* Then compute the page order for said goal */
	order = get_order(goal);

	/* Now compute the required page order for the maximum sized table we
	 * want to create
	 */
	max_entry_order = get_order(MAX_SCTP_PORT_HASH_ENTRIES *
				    sizeof(struct sctp_bind_hashbucket));

	/* Limit the page order by that maximum hash table size */
	order = min(order, max_entry_order);

	/* Allocate and initialize the endpoint hash table.  */
	sctp_ep_hashsize = 64;
	sctp_ep_hashtable =
		kmalloc_array(64, sizeof(struct sctp_hashbucket), GFP_KERNEL);
	if (!sctp_ep_hashtable) {
		pr_err("Failed endpoint_hash alloc\n");
		status = -ENOMEM;
		goto err_ehash_alloc;
	}
	for (i = 0; i < sctp_ep_hashsize; i++) {
		rwlock_init(&sctp_ep_hashtable[i].lock);
		INIT_HLIST_HEAD(&sctp_ep_hashtable[i].chain);
	}

	/* Allocate and initialize the SCTP port hash table.
	 * Note that order is initalized to start at the max sized
	 * table we want to support.  If we can't get that many pages
	 * reduce the order and try again
	 */
	do {
		sctp_port_hashtable = (struct sctp_bind_hashbucket *)
			__get_free_pages(GFP_KERNEL | __GFP_NOWARN, order);
	} while (!sctp_port_hashtable && --order > 0);

	if (!sctp_port_hashtable) {
		pr_err("Failed bind hash alloc\n");
		status = -ENOMEM;
		goto err_bhash_alloc;
	}

	/* Now compute the number of entries that will fit in the
	 * port hash space we allocated
	 */
	num_entries = (1UL << order) * PAGE_SIZE /
		      sizeof(struct sctp_bind_hashbucket);

	/* And finish by rounding it down to the nearest power of two.
	 * This wastes some memory of course, but it's needed because
	 * the hash function operates based on the assumption that
	 * the number of entries is a power of two.
	 */
	sctp_port_hashsize = rounddown_pow_of_two(num_entries);

	for (i = 0; i < sctp_port_hashsize; i++) {
		spin_lock_init(&sctp_port_hashtable[i].lock);
		INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain);
	}

	status = sctp_transport_hashtable_init();
	if (status)
		goto err_thash_alloc;

	pr_info("Hash tables configured (bind %d/%d)\n", sctp_port_hashsize,
		num_entries);

	sctp_sysctl_register();

	INIT_LIST_HEAD(&sctp_address_families);
	sctp_v4_pf_init();
	sctp_v6_pf_init();
	sctp_sched_ops_init();

	status = register_pernet_subsys(&sctp_defaults_ops);
	if (status)
		goto err_register_defaults;

	status = sctp_v4_protosw_init();
	if (status)
		goto err_protosw_init;

	status = sctp_v6_protosw_init();
	if (status)
		goto err_v6_protosw_init;

	status = register_pernet_subsys(&sctp_ctrlsock_ops);
	if (status)
		goto err_register_ctrlsock;

	status = sctp_v4_add_protocol();
	if (status)
		goto err_add_protocol;

	/* Register SCTP with inet6 layer.  */
	status = sctp_v6_add_protocol();
	if (status)
		goto err_v6_add_protocol;

	if (sctp_offload_init() < 0)
		pr_crit("%s: Cannot add SCTP protocol offload\n", __func__);

out:
	return status;
err_v6_add_protocol:
	sctp_v4_del_protocol();
err_add_protocol:
	unregister_pernet_subsys(&sctp_ctrlsock_ops);
err_register_ctrlsock:
	sctp_v6_protosw_exit();
err_v6_protosw_init:
	sctp_v4_protosw_exit();
err_protosw_init:
	unregister_pernet_subsys(&sctp_defaults_ops);
err_register_defaults:
	sctp_v4_pf_exit();
	sctp_v6_pf_exit();
	sctp_sysctl_unregister();
	free_pages((unsigned long)sctp_port_hashtable,
		   get_order(sctp_port_hashsize *
			     sizeof(struct sctp_bind_hashbucket)));
err_bhash_alloc:
	sctp_transport_hashtable_destroy();
err_thash_alloc:
	kfree(sctp_ep_hashtable);
err_ehash_alloc:
	percpu_counter_destroy(&sctp_sockets_allocated);
err_percpu_counter_init:
	kmem_cache_destroy(sctp_chunk_cachep);
err_chunk_cachep:
	kmem_cache_destroy(sctp_bucket_cachep);
	goto out;
}

/* Exit handler for the SCTP protocol.  */
static __exit void sctp_exit(void)
{
	/* BUG.  This should probably do something useful like clean
	 * up all the remaining associations and all that memory.
	 */

	/* Unregister with inet6/inet layers. */
	sctp_v6_del_protocol();
	sctp_v4_del_protocol();

	unregister_pernet_subsys(&sctp_ctrlsock_ops);

	/* Free protosw registrations */
	sctp_v6_protosw_exit();
	sctp_v4_protosw_exit();

	unregister_pernet_subsys(&sctp_defaults_ops);

	/* Unregister with socket layer. */
	sctp_v6_pf_exit();
	sctp_v4_pf_exit();

	sctp_sysctl_unregister();

	free_pages((unsigned long)sctp_port_hashtable,
		   get_order(sctp_port_hashsize *
			     sizeof(struct sctp_bind_hashbucket)));
	kfree(sctp_ep_hashtable);
	sctp_transport_hashtable_destroy();

	percpu_counter_destroy(&sctp_sockets_allocated);

	rcu_barrier(); /* Wait for completion of call_rcu()'s */

	kmem_cache_destroy(sctp_chunk_cachep);
	kmem_cache_destroy(sctp_bucket_cachep);
}

module_init(sctp_init);
module_exit(sctp_exit);

/*
 * __stringify doesn't likes enums, so use IPPROTO_SCTP value (132) directly.
 */
MODULE_ALIAS("net-pf-" __stringify(PF_INET) "-proto-132");
MODULE_ALIAS("net-pf-" __stringify(PF_INET6) "-proto-132");
MODULE_AUTHOR("Linux Kernel SCTP developers <linux-sctp@vger.kernel.org>");
MODULE_DESCRIPTION("Support for the SCTP protocol (RFC2960)");
module_param_named(no_checksums, sctp_checksum_disable, bool, 0644);
MODULE_PARM_DESC(no_checksums, "Disable checksums computing and verification");
MODULE_LICENSE("GPL");