summaryrefslogtreecommitdiffstats
path: root/net/ipv4/af_inet.c
blob: d99e7e020189144fc37da21618ee5c03f67ed203 (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
/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		PF_INET protocol family socket handler.
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Florian La Roche, <flla@stud.uni-sb.de>
 *		Alan Cox, <A.Cox@swansea.ac.uk>
 *
 * Changes (see also sock.c)
 *
 *		piggy,
 *		Karl Knutson	:	Socket protocol table
 *		A.N.Kuznetsov	:	Socket death error in accept().
 *		John Richardson :	Fix non blocking error in connect()
 *					so sockets that fail to connect
 *					don't return -EINPROGRESS.
 *		Alan Cox	:	Asynchronous I/O support
 *		Alan Cox	:	Keep correct socket pointer on sock
 *					structures
 *					when accept() ed
 *		Alan Cox	:	Semantics of SO_LINGER aren't state
 *					moved to close when you look carefully.
 *					With this fixed and the accept bug fixed
 *					some RPC stuff seems happier.
 *		Niibe Yutaka	:	4.4BSD style write async I/O
 *		Alan Cox,
 *		Tony Gale 	:	Fixed reuse semantics.
 *		Alan Cox	:	bind() shouldn't abort existing but dead
 *					sockets. Stops FTP netin:.. I hope.
 *		Alan Cox	:	bind() works correctly for RAW sockets.
 *					Note that FreeBSD at least was broken
 *					in this respect so be careful with
 *					compatibility tests...
 *		Alan Cox	:	routing cache support
 *		Alan Cox	:	memzero the socket structure for
 *					compactness.
 *		Matt Day	:	nonblock connect error handler
 *		Alan Cox	:	Allow large numbers of pending sockets
 *					(eg for big web sites), but only if
 *					specifically application requested.
 *		Alan Cox	:	New buffering throughout IP. Used
 *					dumbly.
 *		Alan Cox	:	New buffering now used smartly.
 *		Alan Cox	:	BSD rather than common sense
 *					interpretation of listen.
 *		Germano Caronni	:	Assorted small races.
 *		Alan Cox	:	sendmsg/recvmsg basic support.
 *		Alan Cox	:	Only sendmsg/recvmsg now supported.
 *		Alan Cox	:	Locked down bind (see security list).
 *		Alan Cox	:	Loosened bind a little.
 *		Mike McLagan	:	ADD/DEL DLCI Ioctls
 *	Willy Konynenberg	:	Transparent proxying support.
 *		David S. Miller	:	New socket lookup architecture.
 *					Some other random speedups.
 *		Cyrus Durgin	:	Cleaned up file for kmod hacks.
 *		Andi Kleen	:	Fix inet_stream_connect TCP race.
 *
 *		This program is free software; you can redistribute it and/or
 *		modify it under the terms of the GNU General Public License
 *		as published by the Free Software Foundation; either version
 *		2 of the License, or (at your option) any later version.
 */

#include <linux/err.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/capability.h>
#include <linux/fcntl.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/stat.h>
#include <linux/init.h>
#include <linux/poll.h>
#include <linux/netfilter_ipv4.h>
#include <linux/random.h>
#include <linux/slab.h>

#include <asm/uaccess.h>
#include <asm/system.h>

#include <linux/inet.h>
#include <linux/igmp.h>
#include <linux/inetdevice.h>
#include <linux/netdevice.h>
#include <net/checksum.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/arp.h>
#include <net/route.h>
#include <net/ip_fib.h>
#include <net/inet_connection_sock.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/udplite.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/raw.h>
#include <net/icmp.h>
#include <net/ipip.h>
#include <net/inet_common.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#ifdef CONFIG_IP_MROUTE
#include <linux/mroute.h>
#endif


/* The inetsw table contains everything that inet_create needs to
 * build a new socket.
 */
static struct list_head inetsw[SOCK_MAX];
static DEFINE_SPINLOCK(inetsw_lock);

struct ipv4_config ipv4_config;
EXPORT_SYMBOL(ipv4_config);

/* New destruction routine */

void inet_sock_destruct(struct sock *sk)
{
	struct inet_sock *inet = inet_sk(sk);

	__skb_queue_purge(&sk->sk_receive_queue);
	__skb_queue_purge(&sk->sk_error_queue);

	sk_mem_reclaim(sk);

	if (sk->sk_type == SOCK_STREAM && sk->sk_state != TCP_CLOSE) {
		pr_err("Attempt to release TCP socket in state %d %p\n",
		       sk->sk_state, sk);
		return;
	}
	if (!sock_flag(sk, SOCK_DEAD)) {
		pr_err("Attempt to release alive inet socket %p\n", sk);
		return;
	}

	WARN_ON(atomic_read(&sk->sk_rmem_alloc));
	WARN_ON(atomic_read(&sk->sk_wmem_alloc));
	WARN_ON(sk->sk_wmem_queued);
	WARN_ON(sk->sk_forward_alloc);

	kfree(inet->opt);
	dst_release(rcu_dereference_check(sk->sk_dst_cache, 1));
	sk_refcnt_debug_dec(sk);
}
EXPORT_SYMBOL(inet_sock_destruct);

/*
 *	The routines beyond this point handle the behaviour of an AF_INET
 *	socket object. Mostly it punts to the subprotocols of IP to do
 *	the work.
 */

/*
 *	Automatically bind an unbound socket.
 */

static int inet_autobind(struct sock *sk)
{
	struct inet_sock *inet;
	/* We may need to bind the socket. */
	lock_sock(sk);
	inet = inet_sk(sk);
	if (!inet->inet_num) {
		if (sk->sk_prot->get_port(sk, 0)) {
			release_sock(sk);
			return -EAGAIN;
		}
		inet->inet_sport = htons(inet->inet_num);
	}
	release_sock(sk);
	return 0;
}

/*
 *	Move a socket into listening state.
 */
int inet_listen(struct socket *sock, int backlog)
{
	struct sock *sk = sock->sk;
	unsigned char old_state;
	int err;

	lock_sock(sk);

	err = -EINVAL;
	if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM)
		goto out;

	old_state = sk->sk_state;
	if (!((1 << old_state) & (TCPF_CLOSE | TCPF_LISTEN)))
		goto out;

	/* Really, if the socket is already in listen state
	 * we can only allow the backlog to be adjusted.
	 */
	if (old_state != TCP_LISTEN) {
		err = inet_csk_listen_start(sk, backlog);
		if (err)
			goto out;
	}
	sk->sk_max_ack_backlog = backlog;
	err = 0;

out:
	release_sock(sk);
	return err;
}
EXPORT_SYMBOL(inet_listen);

u32 inet_ehash_secret __read_mostly;
EXPORT_SYMBOL(inet_ehash_secret);

/*
 * inet_ehash_secret must be set exactly once
 * Instead of using a dedicated spinlock, we (ab)use inetsw_lock
 */
void build_ehash_secret(void)
{
	u32 rnd;
	do {
		get_random_bytes(&rnd, sizeof(rnd));
	} while (rnd == 0);
	spin_lock_bh(&inetsw_lock);
	if (!inet_ehash_secret)
		inet_ehash_secret = rnd;
	spin_unlock_bh(&inetsw_lock);
}
EXPORT_SYMBOL(build_ehash_secret);

static inline int inet_netns_ok(struct net *net, int protocol)
{
	int hash;
	const struct net_protocol *ipprot;

	if (net_eq(net, &init_net))
		return 1;

	hash = protocol & (MAX_INET_PROTOS - 1);
	ipprot = rcu_dereference(inet_protos[hash]);

	if (ipprot == NULL)
		/* raw IP is OK */
		return 1;
	return ipprot->netns_ok;
}

/*
 *	Create an inet socket.
 */

static int inet_create(struct net *net, struct socket *sock, int protocol,
		       int kern)
{
	struct sock *sk;
	struct inet_protosw *answer;
	struct inet_sock *inet;
	struct proto *answer_prot;
	unsigned char answer_flags;
	char answer_no_check;
	int try_loading_module = 0;
	int err;

	if (unlikely(!inet_ehash_secret))
		if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM)
			build_ehash_secret();

	sock->state = SS_UNCONNECTED;

	/* Look for the requested type/protocol pair. */
lookup_protocol:
	err = -ESOCKTNOSUPPORT;
	rcu_read_lock();
	list_for_each_entry_rcu(answer, &inetsw[sock->type], list) {

		err = 0;
		/* Check the non-wild match. */
		if (protocol == answer->protocol) {
			if (protocol != IPPROTO_IP)
				break;
		} else {
			/* Check for the two wild cases. */
			if (IPPROTO_IP == protocol) {
				protocol = answer->protocol;
				break;
			}
			if (IPPROTO_IP == answer->protocol)
				break;
		}
		err = -EPROTONOSUPPORT;
	}

	if (unlikely(err)) {
		if (try_loading_module < 2) {
			rcu_read_unlock();
			/*
			 * Be more specific, e.g. net-pf-2-proto-132-type-1
			 * (net-pf-PF_INET-proto-IPPROTO_SCTP-type-SOCK_STREAM)
			 */
			if (++try_loading_module == 1)
				request_module("net-pf-%d-proto-%d-type-%d",
					       PF_INET, protocol, sock->type);
			/*
			 * Fall back to generic, e.g. net-pf-2-proto-132
			 * (net-pf-PF_INET-proto-IPPROTO_SCTP)
			 */
			else
				request_module("net-pf-%d-proto-%d",
					       PF_INET, protocol);
			goto lookup_protocol;
		} else
			goto out_rcu_unlock;
	}

	err = -EPERM;
	if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW))
		goto out_rcu_unlock;

	err = -EAFNOSUPPORT;
	if (!inet_netns_ok(net, protocol))
		goto out_rcu_unlock;

	sock->ops = answer->ops;
	answer_prot = answer->prot;
	answer_no_check = answer->no_check;
	answer_flags = answer->flags;
	rcu_read_unlock();

	WARN_ON(answer_prot->slab == NULL);

	err = -ENOBUFS;
	sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot);
	if (sk == NULL)
		goto out;

	err = 0;
	sk->sk_no_check = answer_no_check;
	if (INET_PROTOSW_REUSE & answer_flags)
		sk->sk_reuse = 1;

	inet = inet_sk(sk);
	inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0;

	if (SOCK_RAW == sock->type) {
		inet->inet_num = protocol;
		if (IPPROTO_RAW == protocol)
			inet->hdrincl = 1;
	}

	if (ipv4_config.no_pmtu_disc)
		inet->pmtudisc = IP_PMTUDISC_DONT;
	else
		inet->pmtudisc = IP_PMTUDISC_WANT;

	inet->inet_id = 0;

	sock_init_data(sock, sk);

	sk->sk_destruct	   = inet_sock_destruct;
	sk->sk_protocol	   = protocol;
	sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;

	inet->uc_ttl	= -1;
	inet->mc_loop	= 1;
	inet->mc_ttl	= 1;
	inet->mc_all	= 1;
	inet->mc_index	= 0;
	inet->mc_list	= NULL;

	sk_refcnt_debug_inc(sk);

	if (inet->inet_num) {
		/* It assumes that any protocol which allows
		 * the user to assign a number at socket
		 * creation time automatically
		 * shares.
		 */
		inet->inet_sport = htons(inet->inet_num);
		/* Add to protocol hash chains. */
		sk->sk_prot->hash(sk);
	}

	if (sk->sk_prot->init) {
		err = sk->sk_prot->init(sk);
		if (err)
			sk_common_release(sk);
	}
out:
	return err;
out_rcu_unlock:
	rcu_read_unlock();
	goto out;
}


/*
 *	The peer socket should always be NULL (or else). When we call this
 *	function we are destroying the object and from then on nobody
 *	should refer to it.
 */
int inet_release(struct socket *sock)
{
	struct sock *sk = sock->sk;

	if (sk) {
		long timeout;

		sock_rps_reset_flow(sk);

		/* Applications forget to leave groups before exiting */
		ip_mc_drop_socket(sk);

		/* If linger is set, we don't return until the close
		 * is complete.  Otherwise we return immediately. The
		 * actually closing is done the same either way.
		 *
		 * If the close is due to the process exiting, we never
		 * linger..
		 */
		timeout = 0;
		if (sock_flag(sk, SOCK_LINGER) &&
		    !(current->flags & PF_EXITING))
			timeout = sk->sk_lingertime;
		sock->sk = NULL;
		sk->sk_prot->close(sk, timeout);
	}
	return 0;
}
EXPORT_SYMBOL(inet_release);

/* It is off by default, see below. */
int sysctl_ip_nonlocal_bind __read_mostly;
EXPORT_SYMBOL(sysctl_ip_nonlocal_bind);

int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
	struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
	struct sock *sk = sock->sk;
	struct inet_sock *inet = inet_sk(sk);
	unsigned short snum;
	int chk_addr_ret;
	int err;

	/* If the socket has its own bind function then use it. (RAW) */
	if (sk->sk_prot->bind) {
		err = sk->sk_prot->bind(sk, uaddr, addr_len);
		goto out;
	}
	err = -EINVAL;
	if (addr_len < sizeof(struct sockaddr_in))
		goto out;

	chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr);

	/* Not specified by any standard per-se, however it breaks too
	 * many applications when removed.  It is unfortunate since
	 * allowing applications to make a non-local bind solves
	 * several problems with systems using dynamic addressing.
	 * (ie. your servers still start up even if your ISDN link
	 *  is temporarily down)
	 */
	err = -EADDRNOTAVAIL;
	if (!sysctl_ip_nonlocal_bind &&
	    !(inet->freebind || inet->transparent) &&
	    addr->sin_addr.s_addr != htonl(INADDR_ANY) &&
	    chk_addr_ret != RTN_LOCAL &&
	    chk_addr_ret != RTN_MULTICAST &&
	    chk_addr_ret != RTN_BROADCAST)
		goto out;

	snum = ntohs(addr->sin_port);
	err = -EACCES;
	if (snum && snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
		goto out;

	/*      We keep a pair of addresses. rcv_saddr is the one
	 *      used by hash lookups, and saddr is used for transmit.
	 *
	 *      In the BSD API these are the same except where it
	 *      would be illegal to use them (multicast/broadcast) in
	 *      which case the sending device address is used.
	 */
	lock_sock(sk);

	/* Check these errors (active socket, double bind). */
	err = -EINVAL;
	if (sk->sk_state != TCP_CLOSE || inet->inet_num)
		goto out_release_sock;

	inet->inet_rcv_saddr = inet->inet_saddr = addr->sin_addr.s_addr;
	if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST)
		inet->inet_saddr = 0;  /* Use device */

	/* Make sure we are allowed to bind here. */
	if (sk->sk_prot->get_port(sk, snum)) {
		inet->inet_saddr = inet->inet_rcv_saddr = 0;
		err = -EADDRINUSE;
		goto out_release_sock;
	}

	if (inet->inet_rcv_saddr)
		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
	if (snum)
		sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
	inet->inet_sport = htons(inet->inet_num);
	inet->inet_daddr = 0;
	inet->inet_dport = 0;
	sk_dst_reset(sk);
	err = 0;
out_release_sock:
	release_sock(sk);
out:
	return err;
}
EXPORT_SYMBOL(inet_bind);

int inet_dgram_connect(struct socket *sock, struct sockaddr * uaddr,
		       int addr_len, int flags)
{
	struct sock *sk = sock->sk;

	if (addr_len < sizeof(uaddr->sa_family))
		return -EINVAL;
	if (uaddr->sa_family == AF_UNSPEC)
		return sk->sk_prot->disconnect(sk, flags);

	if (!inet_sk(sk)->inet_num && inet_autobind(sk))
		return -EAGAIN;
	return sk->sk_prot->connect(sk, (struct sockaddr *)uaddr, addr_len);
}
EXPORT_SYMBOL(inet_dgram_connect);

static long inet_wait_for_connect(struct sock *sk, long timeo)
{
	DEFINE_WAIT(wait);

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

	/* Basic assumption: if someone sets sk->sk_err, he _must_
	 * change state of the socket from TCP_SYN_*.
	 * Connect() does not allow to get error notifications
	 * without closing the socket.
	 */
	while ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
		release_sock(sk);
		timeo = schedule_timeout(timeo);
		lock_sock(sk);
		if (signal_pending(current) || !timeo)
			break;
		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
	}
	finish_wait(sk_sleep(sk), &wait);
	return timeo;
}

/*
 *	Connect to a remote host. There is regrettably still a little
 *	TCP 'magic' in here.
 */
int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
			int addr_len, int flags)
{
	struct sock *sk = sock->sk;
	int err;
	long timeo;

	if (addr_len < sizeof(uaddr->sa_family))
		return -EINVAL;

	lock_sock(sk);

	if (uaddr->sa_family == AF_UNSPEC) {
		err = sk->sk_prot->disconnect(sk, flags);
		sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
		goto out;
	}

	switch (sock->state) {
	default:
		err = -EINVAL;
		goto out;
	case SS_CONNECTED:
		err = -EISCONN;
		goto out;
	case SS_CONNECTING:
		err = -EALREADY;
		/* Fall out of switch with err, set for this state */
		break;
	case SS_UNCONNECTED:
		err = -EISCONN;
		if (sk->sk_state != TCP_CLOSE)
			goto out;

		err = sk->sk_prot->connect(sk, uaddr, addr_len);
		if (err < 0)
			goto out;

		sock->state = SS_CONNECTING;

		/* Just entered SS_CONNECTING state; the only
		 * difference is that return value in non-blocking
		 * case is EINPROGRESS, rather than EALREADY.
		 */
		err = -EINPROGRESS;
		break;
	}

	timeo = sock_sndtimeo(sk, flags & O_NONBLOCK);

	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
		/* Error code is set above */
		if (!timeo || !inet_wait_for_connect(sk, timeo))
			goto out;

		err = sock_intr_errno(timeo);
		if (signal_pending(current))
			goto out;
	}

	/* Connection was closed by RST, timeout, ICMP error
	 * or another process disconnected us.
	 */
	if (sk->sk_state == TCP_CLOSE)
		goto sock_error;

	/* sk->sk_err may be not zero now, if RECVERR was ordered by user
	 * and error was received after socket entered established state.
	 * Hence, it is handled normally after connect() return successfully.
	 */

	sock->state = SS_CONNECTED;
	err = 0;
out:
	release_sock(sk);
	return err;

sock_error:
	err = sock_error(sk) ? : -ECONNABORTED;
	sock->state = SS_UNCONNECTED;
	if (sk->sk_prot->disconnect(sk, flags))
		sock->state = SS_DISCONNECTING;
	goto out;
}
EXPORT_SYMBOL(inet_stream_connect);

/*
 *	Accept a pending connection. The TCP layer now gives BSD semantics.
 */

int inet_accept(struct socket *sock, struct socket *newsock, int flags)
{
	struct sock *sk1 = sock->sk;
	int err = -EINVAL;
	struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err);

	if (!sk2)
		goto do_err;

	lock_sock(sk2);

	WARN_ON(!((1 << sk2->sk_state) &
		  (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_CLOSE)));

	sock_graft(sk2, newsock);

	newsock->state = SS_CONNECTED;
	err = 0;
	release_sock(sk2);
do_err:
	return err;
}
EXPORT_SYMBOL(inet_accept);


/*
 *	This does both peername and sockname.
 */
int inet_getname(struct socket *sock, struct sockaddr *uaddr,
			int *uaddr_len, int peer)
{
	struct sock *sk		= sock->sk;
	struct inet_sock *inet	= inet_sk(sk);
	DECLARE_SOCKADDR(struct sockaddr_in *, sin, uaddr);

	sin->sin_family = AF_INET;
	if (peer) {
		if (!inet->inet_dport ||
		    (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) &&
		     peer == 1))
			return -ENOTCONN;
		sin->sin_port = inet->inet_dport;
		sin->sin_addr.s_addr = inet->inet_daddr;
	} else {
		__be32 addr = inet->inet_rcv_saddr;
		if (!addr)
			addr = inet->inet_saddr;
		sin->sin_port = inet->inet_sport;
		sin->sin_addr.s_addr = addr;
	}
	memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
	*uaddr_len = sizeof(*sin);
	return 0;
}
EXPORT_SYMBOL(inet_getname);

int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
		 size_t size)
{
	struct sock *sk = sock->sk;

	sock_rps_record_flow(sk);

	/* We may need to bind the socket. */
	if (!inet_sk(sk)->inet_num && inet_autobind(sk))
		return -EAGAIN;

	return sk->sk_prot->sendmsg(iocb, sk, msg, size);
}
EXPORT_SYMBOL(inet_sendmsg);

static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
			     size_t size, int flags)
{
	struct sock *sk = sock->sk;

	sock_rps_record_flow(sk);

	/* We may need to bind the socket. */
	if (!inet_sk(sk)->inet_num && inet_autobind(sk))
		return -EAGAIN;

	if (sk->sk_prot->sendpage)
		return sk->sk_prot->sendpage(sk, page, offset, size, flags);
	return sock_no_sendpage(sock, page, offset, size, flags);
}

int inet_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
		 size_t size, int flags)
{
	struct sock *sk = sock->sk;
	int addr_len = 0;
	int err;

	sock_rps_record_flow(sk);

	err = sk->sk_prot->recvmsg(iocb, sk, msg, size, flags & MSG_DONTWAIT,
				   flags & ~MSG_DONTWAIT, &addr_len);
	if (err >= 0)
		msg->msg_namelen = addr_len;
	return err;
}
EXPORT_SYMBOL(inet_recvmsg);

int inet_shutdown(struct socket *sock, int how)
{
	struct sock *sk = sock->sk;
	int err = 0;

	/* This should really check to make sure
	 * the socket is a TCP socket. (WHY AC...)
	 */
	how++; /* maps 0->1 has the advantage of making bit 1 rcvs and
		       1->2 bit 2 snds.
		       2->3 */
	if ((how & ~SHUTDOWN_MASK) || !how)	/* MAXINT->0 */
		return -EINVAL;

	lock_sock(sk);
	if (sock->state == SS_CONNECTING) {
		if ((1 << sk->sk_state) &
		    (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE))
			sock->state = SS_DISCONNECTING;
		else
			sock->state = SS_CONNECTED;
	}

	switch (sk->sk_state) {
	case TCP_CLOSE:
		err = -ENOTCONN;
		/* Hack to wake up other listeners, who can poll for
		   POLLHUP, even on eg. unconnected UDP sockets -- RR */
	default:
		sk->sk_shutdown |= how;
		if (sk->sk_prot->shutdown)
			sk->sk_prot->shutdown(sk, how);
		break;

	/* Remaining two branches are temporary solution for missing
	 * close() in multithreaded environment. It is _not_ a good idea,
	 * but we have no choice until close() is repaired at VFS level.
	 */
	case TCP_LISTEN:
		if (!(how & RCV_SHUTDOWN))
			break;
		/* Fall through */
	case TCP_SYN_SENT:
		err = sk->sk_prot->disconnect(sk, O_NONBLOCK);
		sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
		break;
	}

	/* Wake up anyone sleeping in poll. */
	sk->sk_state_change(sk);
	release_sock(sk);
	return err;
}
EXPORT_SYMBOL(inet_shutdown);

/*
 *	ioctl() calls you can issue on an INET socket. Most of these are
 *	device configuration and stuff and very rarely used. Some ioctls
 *	pass on to the socket itself.
 *
 *	NOTE: I like the idea of a module for the config stuff. ie ifconfig
 *	loads the devconfigure module does its configuring and unloads it.
 *	There's a good 20K of config code hanging around the kernel.
 */

int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
	struct sock *sk = sock->sk;
	int err = 0;
	struct net *net = sock_net(sk);

	switch (cmd) {
	case SIOCGSTAMP:
		err = sock_get_timestamp(sk, (struct timeval __user *)arg);
		break;
	case SIOCGSTAMPNS:
		err = sock_get_timestampns(sk, (struct timespec __user *)arg);
		break;
	case SIOCADDRT:
	case SIOCDELRT:
	case SIOCRTMSG:
		err = ip_rt_ioctl(net, cmd, (void __user *)arg);
		break;
	case SIOCDARP:
	case SIOCGARP:
	case SIOCSARP:
		err = arp_ioctl(net, cmd, (void __user *)arg);
		break;
	case SIOCGIFADDR:
	case SIOCSIFADDR:
	case SIOCGIFBRDADDR:
	case SIOCSIFBRDADDR:
	case SIOCGIFNETMASK:
	case SIOCSIFNETMASK:
	case SIOCGIFDSTADDR:
	case SIOCSIFDSTADDR:
	case SIOCSIFPFLAGS:
	case SIOCGIFPFLAGS:
	case SIOCSIFFLAGS:
		err = devinet_ioctl(net, cmd, (void __user *)arg);
		break;
	default:
		if (sk->sk_prot->ioctl)
			err = sk->sk_prot->ioctl(sk, cmd, arg);
		else
			err = -ENOIOCTLCMD;
		break;
	}
	return err;
}
EXPORT_SYMBOL(inet_ioctl);

const struct proto_ops inet_stream_ops = {
	.family		   = PF_INET,
	.owner		   = THIS_MODULE,
	.release	   = inet_release,
	.bind		   = inet_bind,
	.connect	   = inet_stream_connect,
	.socketpair	   = sock_no_socketpair,
	.accept		   = inet_accept,
	.getname	   = inet_getname,
	.poll		   = tcp_poll,
	.ioctl		   = inet_ioctl,
	.listen		   = inet_listen,
	.shutdown	   = inet_shutdown,
	.setsockopt	   = sock_common_setsockopt,
	.getsockopt	   = sock_common_getsockopt,
	.sendmsg	   = tcp_sendmsg,
	.recvmsg	   = inet_recvmsg,
	.mmap		   = sock_no_mmap,
	.sendpage	   = tcp_sendpage,
	.splice_read	   = tcp_splice_read,
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_sock_common_setsockopt,
	.compat_getsockopt = compat_sock_common_getsockopt,
#endif
};
EXPORT_SYMBOL(inet_stream_ops);

const struct proto_ops inet_dgram_ops = {
	.family		   = PF_INET,
	.owner		   = THIS_MODULE,
	.release	   = inet_release,
	.bind		   = inet_bind,
	.connect	   = inet_dgram_connect,
	.socketpair	   = sock_no_socketpair,
	.accept		   = sock_no_accept,
	.getname	   = inet_getname,
	.poll		   = udp_poll,
	.ioctl		   = inet_ioctl,
	.listen		   = sock_no_listen,
	.shutdown	   = inet_shutdown,
	.setsockopt	   = sock_common_setsockopt,
	.getsockopt	   = sock_common_getsockopt,
	.sendmsg	   = inet_sendmsg,
	.recvmsg	   = inet_recvmsg,
	.mmap		   = sock_no_mmap,
	.sendpage	   = inet_sendpage,
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_sock_common_setsockopt,
	.compat_getsockopt = compat_sock_common_getsockopt,
#endif
};
EXPORT_SYMBOL(inet_dgram_ops);

/*
 * For SOCK_RAW sockets; should be the same as inet_dgram_ops but without
 * udp_poll
 */
static const struct proto_ops inet_sockraw_ops = {
	.family		   = PF_INET,
	.owner		   = THIS_MODULE,
	.release	   = inet_release,
	.bind		   = inet_bind,
	.connect	   = inet_dgram_connect,
	.socketpair	   = sock_no_socketpair,
	.accept		   = sock_no_accept,
	.getname	   = inet_getname,
	.poll		   = datagram_poll,
	.ioctl		   = inet_ioctl,
	.listen		   = sock_no_listen,
	.shutdown	   = inet_shutdown,
	.setsockopt	   = sock_common_setsockopt,
	.getsockopt	   = sock_common_getsockopt,
	.sendmsg	   = inet_sendmsg,
	.recvmsg	   = inet_recvmsg,
	.mmap		   = sock_no_mmap,
	.sendpage	   = inet_sendpage,
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_sock_common_setsockopt,
	.compat_getsockopt = compat_sock_common_getsockopt,
#endif
};

static const struct net_proto_family inet_family_ops = {
	.family = PF_INET,
	.create = inet_create,
	.owner	= THIS_MODULE,
};

/* Upon startup we insert all the elements in inetsw_array[] into
 * the linked list inetsw.
 */
static struct inet_protosw inetsw_array[] =
{
	{
		.type =       SOCK_STREAM,
		.protocol =   IPPROTO_TCP,
		.prot =       &tcp_prot,
		.ops =        &inet_stream_ops,
		.no_check =   0,
		.flags =      INET_PROTOSW_PERMANENT |
			      INET_PROTOSW_ICSK,
	},

	{
		.type =       SOCK_DGRAM,
		.protocol =   IPPROTO_UDP,
		.prot =       &udp_prot,
		.ops =        &inet_dgram_ops,
		.no_check =   UDP_CSUM_DEFAULT,
		.flags =      INET_PROTOSW_PERMANENT,
       },


       {
	       .type =       SOCK_RAW,
	       .protocol =   IPPROTO_IP,	/* wild card */
	       .prot =       &raw_prot,
	       .ops =        &inet_sockraw_ops,
	       .no_check =   UDP_CSUM_DEFAULT,
	       .flags =      INET_PROTOSW_REUSE,
       }
};

#define INETSW_ARRAY_LEN ARRAY_SIZE(inetsw_array)

void inet_register_protosw(struct inet_protosw *p)
{
	struct list_head *lh;
	struct inet_protosw *answer;
	int protocol = p->protocol;
	struct list_head *last_perm;

	spin_lock_bh(&inetsw_lock);

	if (p->type >= SOCK_MAX)
		goto out_illegal;

	/* If we are trying to override a permanent protocol, bail. */
	answer = NULL;
	last_perm = &inetsw[p->type];
	list_for_each(lh, &inetsw[p->type]) {
		answer = list_entry(lh, struct inet_protosw, list);

		/* Check only the non-wild match. */
		if (INET_PROTOSW_PERMANENT & answer->flags) {
			if (protocol == answer->protocol)
				break;
			last_perm = lh;
		}

		answer = NULL;
	}
	if (answer)
		goto out_permanent;

	/* Add the new entry after the last permanent entry if any, so that
	 * the new entry does not override a permanent entry when matched with
	 * a wild-card protocol. But it is allowed to override any existing
	 * non-permanent entry.  This means that when we remove this entry, the
	 * system automatically returns to the old behavior.
	 */
	list_add_rcu(&p->list, last_perm);
out:
	spin_unlock_bh(&inetsw_lock);

	return;

out_permanent:
	printk(KERN_ERR "Attempt to override permanent protocol %d.\n",
	       protocol);
	goto out;

out_illegal:
	printk(KERN_ERR
	       "Ignoring attempt to register invalid socket type %d.\n",
	       p->type);
	goto out;
}
EXPORT_SYMBOL(inet_register_protosw);

void inet_unregister_protosw(struct inet_protosw *p)
{
	if (INET_PROTOSW_PERMANENT & p->flags) {
		printk(KERN_ERR
		       "Attempt to unregister permanent protocol %d.\n",
		       p->protocol);
	} else {
		spin_lock_bh(&inetsw_lock);
		list_del_rcu(&p->list);
		spin_unlock_bh(&inetsw_lock);

		synchronize_net();
	}
}
EXPORT_SYMBOL(inet_unregister_protosw);

/*
 *      Shall we try to damage output packets if routing dev changes?
 */

int sysctl_ip_dynaddr __read_mostly;

static int inet_sk_reselect_saddr(struct sock *sk)
{
	struct inet_sock *inet = inet_sk(sk);
	int err;
	struct rtable *rt;
	__be32 old_saddr = inet->inet_saddr;
	__be32 new_saddr;
	__be32 daddr = inet->inet_daddr;

	if (inet->opt && inet->opt->srr)
		daddr = inet->opt->faddr;

	/* Query new route. */
	err = ip_route_connect(&rt, daddr, 0,
			       RT_CONN_FLAGS(sk),
			       sk->sk_bound_dev_if,
			       sk->sk_protocol,
			       inet->inet_sport, inet->inet_dport, sk, 0);
	if (err)
		return err;

	sk_setup_caps(sk, &rt->dst);

	new_saddr = rt->rt_src;

	if (new_saddr == old_saddr)
		return 0;

	if (sysctl_ip_dynaddr > 1) {
		printk(KERN_INFO "%s(): shifting inet->saddr from %pI4 to %pI4\n",
		       __func__, &old_saddr, &new_saddr);
	}

	inet->inet_saddr = inet->inet_rcv_saddr = new_saddr;

	/*
	 * XXX The only one ugly spot where we need to
	 * XXX really change the sockets identity after
	 * XXX it has entered the hashes. -DaveM
	 *
	 * Besides that, it does not check for connection
	 * uniqueness. Wait for troubles.
	 */
	__sk_prot_rehash(sk);
	return 0;
}

int inet_sk_rebuild_header(struct sock *sk)
{
	struct inet_sock *inet = inet_sk(sk);
	struct rtable *rt = (struct rtable *)__sk_dst_check(sk, 0);
	__be32 daddr;
	int err;

	/* Route is OK, nothing to do. */
	if (rt)
		return 0;

	/* Reroute. */
	daddr = inet->inet_daddr;
	if (inet->opt && inet->opt->srr)
		daddr = inet->opt->faddr;
{
	struct flowi fl = {
		.oif = sk->sk_bound_dev_if,
		.mark = sk->sk_mark,
		.nl_u = {
			.ip4_u = {
				.daddr	= daddr,
				.saddr	= inet->inet_saddr,
				.tos	= RT_CONN_FLAGS(sk),
			},
		},
		.proto = sk->sk_protocol,
		.flags = inet_sk_flowi_flags(sk),
		.uli_u = {
			.ports = {
				.sport = inet->inet_sport,
				.dport = inet->inet_dport,
			},
		},
	};

	security_sk_classify_flow(sk, &fl);
	err = ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 0);
}
	if (!err)
		sk_setup_caps(sk, &rt->dst);
	else {
		/* Routing failed... */
		sk->sk_route_caps = 0;
		/*
		 * Other protocols have to map its equivalent state to TCP_SYN_SENT.
		 * DCCP maps its DCCP_REQUESTING state to TCP_SYN_SENT. -acme
		 */
		if (!sysctl_ip_dynaddr ||
		    sk->sk_state != TCP_SYN_SENT ||
		    (sk->sk_userlocks & SOCK_BINDADDR_LOCK) ||
		    (err = inet_sk_reselect_saddr(sk)) != 0)
			sk->sk_err_soft = -err;
	}

	return err;
}
EXPORT_SYMBOL(inet_sk_rebuild_header);

static int inet_gso_send_check(struct sk_buff *skb)
{
	struct iphdr *iph;
	const struct net_protocol *ops;
	int proto;
	int ihl;
	int err = -EINVAL;

	if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
		goto out;

	iph = ip_hdr(skb);
	ihl = iph->ihl * 4;
	if (ihl < sizeof(*iph))
		goto out;

	if (unlikely(!pskb_may_pull(skb, ihl)))
		goto out;

	__skb_pull(skb, ihl);
	skb_reset_transport_header(skb);
	iph = ip_hdr(skb);
	proto = iph->protocol & (MAX_INET_PROTOS - 1);
	err = -EPROTONOSUPPORT;

	rcu_read_lock();
	ops = rcu_dereference(inet_protos[proto]);
	if (likely(ops && ops->gso_send_check))
		err = ops->gso_send_check(skb);
	rcu_read_unlock();

out:
	return err;
}

static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int features)
{
	struct sk_buff *segs = ERR_PTR(-EINVAL);
	struct iphdr *iph;
	const struct net_protocol *ops;
	int proto;
	int ihl;
	int id;
	unsigned int offset = 0;

	if (!(features & NETIF_F_V4_CSUM))
		features &= ~NETIF_F_SG;

	if (unlikely(skb_shinfo(skb)->gso_type &
		     ~(SKB_GSO_TCPV4 |
		       SKB_GSO_UDP |
		       SKB_GSO_DODGY |
		       SKB_GSO_TCP_ECN |
		       0)))
		goto out;

	if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
		goto out;

	iph = ip_hdr(skb);
	ihl = iph->ihl * 4;
	if (ihl < sizeof(*iph))
		goto out;

	if (unlikely(!pskb_may_pull(skb, ihl)))
		goto out;

	__skb_pull(skb, ihl);
	skb_reset_transport_header(skb);
	iph = ip_hdr(skb);
	id = ntohs(iph->id);
	proto = iph->protocol & (MAX_INET_PROTOS - 1);
	segs = ERR_PTR(-EPROTONOSUPPORT);

	rcu_read_lock();
	ops = rcu_dereference(inet_protos[proto]);
	if (likely(ops && ops->gso_segment))
		segs = ops->gso_segment(skb, features);
	rcu_read_unlock();

	if (!segs || IS_ERR(segs))
		goto out;

	skb = segs;
	do {
		iph = ip_hdr(skb);
		if (proto == IPPROTO_UDP) {
			iph->id = htons(id);
			iph->frag_off = htons(offset >> 3);
			if (skb->next != NULL)
				iph->frag_off |= htons(IP_MF);
			offset += (skb->len - skb->mac_len - iph->ihl * 4);
		} else
			iph->id = htons(id++);
		iph->tot_len = htons(skb->len - skb->mac_len);
		iph->check = 0;
		iph->check = ip_fast_csum(skb_network_header(skb), iph->ihl);
	} while ((skb = skb->next));

out:
	return segs;
}

static struct sk_buff **inet_gro_receive(struct sk_buff **head,
					 struct sk_buff *skb)
{
	const struct net_protocol *ops;
	struct sk_buff **pp = NULL;
	struct sk_buff *p;
	struct iphdr *iph;
	unsigned int hlen;
	unsigned int off;
	unsigned int id;
	int flush = 1;
	int proto;

	off = skb_gro_offset(skb);
	hlen = off + sizeof(*iph);
	iph = skb_gro_header_fast(skb, off);
	if (skb_gro_header_hard(skb, hlen)) {
		iph = skb_gro_header_slow(skb, hlen, off);
		if (unlikely(!iph))
			goto out;
	}

	proto = iph->protocol & (MAX_INET_PROTOS - 1);

	rcu_read_lock();
	ops = rcu_dereference(inet_protos[proto]);
	if (!ops || !ops->gro_receive)
		goto out_unlock;

	if (*(u8 *)iph != 0x45)
		goto out_unlock;

	if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
		goto out_unlock;

	id = ntohl(*(__be32 *)&iph->id);
	flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id ^ IP_DF));
	id >>= 16;

	for (p = *head; p; p = p->next) {
		struct iphdr *iph2;

		if (!NAPI_GRO_CB(p)->same_flow)
			continue;

		iph2 = ip_hdr(p);

		if ((iph->protocol ^ iph2->protocol) |
		    (iph->tos ^ iph2->tos) |
		    ((__force u32)iph->saddr ^ (__force u32)iph2->saddr) |
		    ((__force u32)iph->daddr ^ (__force u32)iph2->daddr)) {
			NAPI_GRO_CB(p)->same_flow = 0;
			continue;
		}

		/* All fields must match except length and checksum. */
		NAPI_GRO_CB(p)->flush |=
			(iph->ttl ^ iph2->ttl) |
			((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id);

		NAPI_GRO_CB(p)->flush |= flush;
	}

	NAPI_GRO_CB(skb)->flush |= flush;
	skb_gro_pull(skb, sizeof(*iph));
	skb_set_transport_header(skb, skb_gro_offset(skb));

	pp = ops->gro_receive(head, skb);

out_unlock:
	rcu_read_unlock();

out:
	NAPI_GRO_CB(skb)->flush |= flush;

	return pp;
}

static int inet_gro_complete(struct sk_buff *skb)
{
	const struct net_protocol *ops;
	struct iphdr *iph = ip_hdr(skb);
	int proto = iph->protocol & (MAX_INET_PROTOS - 1);
	int err = -ENOSYS;
	__be16 newlen = htons(skb->len - skb_network_offset(skb));

	csum_replace2(&iph->check, iph->tot_len, newlen);
	iph->tot_len = newlen;

	rcu_read_lock();
	ops = rcu_dereference(inet_protos[proto]);
	if (WARN_ON(!ops || !ops->gro_complete))
		goto out_unlock;

	err = ops->gro_complete(skb);

out_unlock:
	rcu_read_unlock();

	return err;
}

int inet_ctl_sock_create(struct sock **sk, unsigned short family,
			 unsigned short type, unsigned char protocol,
			 struct net *net)
{
	struct socket *sock;
	int rc = sock_create_kern(family, type, protocol, &sock);

	if (rc == 0) {
		*sk = sock->sk;
		(*sk)->sk_allocation = GFP_ATOMIC;
		/*
		 * Unhash it so that IP input processing does not even see it,
		 * we do not wish this socket to see incoming packets.
		 */
		(*sk)->sk_prot->unhash(*sk);

		sk_change_net(*sk, net);
	}
	return rc;
}
EXPORT_SYMBOL_GPL(inet_ctl_sock_create);

unsigned long snmp_fold_field(void __percpu *mib[], int offt)
{
	unsigned long res = 0;
	int i;

	for_each_possible_cpu(i) {
		res += *(((unsigned long *) per_cpu_ptr(mib[0], i)) + offt);
		res += *(((unsigned long *) per_cpu_ptr(mib[1], i)) + offt);
	}
	return res;
}
EXPORT_SYMBOL_GPL(snmp_fold_field);

int snmp_mib_init(void __percpu *ptr[2], size_t mibsize)
{
	BUG_ON(ptr == NULL);
	ptr[0] = __alloc_percpu(mibsize, __alignof__(unsigned long));
	if (!ptr[0])
		goto err0;
	ptr[1] = __alloc_percpu(mibsize, __alignof__(unsigned long));
	if (!ptr[1])
		goto err1;
	return 0;
err1:
	free_percpu(ptr[0]);
	ptr[0] = NULL;
err0:
	return -ENOMEM;
}
EXPORT_SYMBOL_GPL(snmp_mib_init);

void snmp_mib_free(void __percpu *ptr[2])
{
	BUG_ON(ptr == NULL);
	free_percpu(ptr[0]);
	free_percpu(ptr[1]);
	ptr[0] = ptr[1] = NULL;
}
EXPORT_SYMBOL_GPL(snmp_mib_free);

#ifdef CONFIG_IP_MULTICAST
static const struct net_protocol igmp_protocol = {
	.handler =	igmp_rcv,
	.netns_ok =	1,
};
#endif

static const struct net_protocol tcp_protocol = {
	.handler =	tcp_v4_rcv,
	.err_handler =	tcp_v4_err,
	.gso_send_check = tcp_v4_gso_send_check,
	.gso_segment =	tcp_tso_segment,
	.gro_receive =	tcp4_gro_receive,
	.gro_complete =	tcp4_gro_complete,
	.no_policy =	1,
	.netns_ok =	1,
};

static const struct net_protocol udp_protocol = {
	.handler =	udp_rcv,
	.err_handler =	udp_err,
	.gso_send_check = udp4_ufo_send_check,
	.gso_segment = udp4_ufo_fragment,
	.no_policy =	1,
	.netns_ok =	1,
};

static const struct net_protocol icmp_protocol = {
	.handler =	icmp_rcv,
	.no_policy =	1,
	.netns_ok =	1,
};

static __net_init int ipv4_mib_init_net(struct net *net)
{
	if (snmp_mib_init((void __percpu **)net->mib.tcp_statistics,
			  sizeof(struct tcp_mib)) < 0)
		goto err_tcp_mib;
	if (snmp_mib_init((void __percpu **)net->mib.ip_statistics,
			  sizeof(struct ipstats_mib)) < 0)
		goto err_ip_mib;
	if (snmp_mib_init((void __percpu **)net->mib.net_statistics,
			  sizeof(struct linux_mib)) < 0)
		goto err_net_mib;
	if (snmp_mib_init((void __percpu **)net->mib.udp_statistics,
			  sizeof(struct udp_mib)) < 0)
		goto err_udp_mib;
	if (snmp_mib_init((void __percpu **)net->mib.udplite_statistics,
			  sizeof(struct udp_mib)) < 0)
		goto err_udplite_mib;
	if (snmp_mib_init((void __percpu **)net->mib.icmp_statistics,
			  sizeof(struct icmp_mib)) < 0)
		goto err_icmp_mib;
	if (snmp_mib_init((void __percpu **)net->mib.icmpmsg_statistics,
			  sizeof(struct icmpmsg_mib)) < 0)
		goto err_icmpmsg_mib;

	tcp_mib_init(net);
	return 0;

err_icmpmsg_mib:
	snmp_mib_free((void __percpu **)net->mib.icmp_statistics);
err_icmp_mib:
	snmp_mib_free((void __percpu **)net->mib.udplite_statistics);
err_udplite_mib:
	snmp_mib_free((void __percpu **)net->mib.udp_statistics);
err_udp_mib:
	snmp_mib_free((void __percpu **)net->mib.net_statistics);
err_net_mib:
	snmp_mib_free((void __percpu **)net->mib.ip_statistics);
err_ip_mib:
	snmp_mib_free((void __percpu **)net->mib.tcp_statistics);
err_tcp_mib:
	return -ENOMEM;
}

static __net_exit void ipv4_mib_exit_net(struct net *net)
{
	snmp_mib_free((void __percpu **)net->mib.icmpmsg_statistics);
	snmp_mib_free((void __percpu **)net->mib.icmp_statistics);
	snmp_mib_free((void __percpu **)net->mib.udplite_statistics);
	snmp_mib_free((void __percpu **)net->mib.udp_statistics);
	snmp_mib_free((void __percpu **)net->mib.net_statistics);
	snmp_mib_free((void __percpu **)net->mib.ip_statistics);
	snmp_mib_free((void __percpu **)net->mib.tcp_statistics);
}

static __net_initdata struct pernet_operations ipv4_mib_ops = {
	.init = ipv4_mib_init_net,
	.exit = ipv4_mib_exit_net,
};

static int __init init_ipv4_mibs(void)
{
	return register_pernet_subsys(&ipv4_mib_ops);
}

static int ipv4_proc_init(void);

/*
 *	IP protocol layer initialiser
 */

static struct packet_type ip_packet_type __read_mostly = {
	.type = cpu_to_be16(ETH_P_IP),
	.func = ip_rcv,
	.gso_send_check = inet_gso_send_check,
	.gso_segment = inet_gso_segment,
	.gro_receive = inet_gro_receive,
	.gro_complete = inet_gro_complete,
};

static int __init inet_init(void)
{
	struct sk_buff *dummy_skb;
	struct inet_protosw *q;
	struct list_head *r;
	int rc = -EINVAL;

	BUILD_BUG_ON(sizeof(struct inet_skb_parm) > sizeof(dummy_skb->cb));

	sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL);
	if (!sysctl_local_reserved_ports)
		goto out;

	rc = proto_register(&tcp_prot, 1);
	if (rc)
		goto out_free_reserved_ports;

	rc = proto_register(&udp_prot, 1);
	if (rc)
		goto out_unregister_tcp_proto;

	rc = proto_register(&raw_prot, 1);
	if (rc)
		goto out_unregister_udp_proto;

	/*
	 *	Tell SOCKET that we are alive...
	 */

	(void)sock_register(&inet_family_ops);

#ifdef CONFIG_SYSCTL
	ip_static_sysctl_init();
#endif

	/*
	 *	Add all the base protocols.
	 */

	if (inet_add_protocol(&icmp_protocol, IPPROTO_ICMP) < 0)
		printk(KERN_CRIT "inet_init: Cannot add ICMP protocol\n");
	if (inet_add_protocol(&udp_protocol, IPPROTO_UDP) < 0)
		printk(KERN_CRIT "inet_init: Cannot add UDP protocol\n");
	if (inet_add_protocol(&tcp_protocol, IPPROTO_TCP) < 0)
		printk(KERN_CRIT "inet_init: Cannot add TCP protocol\n");
#ifdef CONFIG_IP_MULTICAST
	if (inet_add_protocol(&igmp_protocol, IPPROTO_IGMP) < 0)
		printk(KERN_CRIT "inet_init: Cannot add IGMP protocol\n");
#endif

	/* Register the socket-side information for inet_create. */
	for (r = &inetsw[0]; r < &inetsw[SOCK_MAX]; ++r)
		INIT_LIST_HEAD(r);

	for (q = inetsw_array; q < &inetsw_array[INETSW_ARRAY_LEN]; ++q)
		inet_register_protosw(q);

	/*
	 *	Set the ARP module up
	 */

	arp_init();

	/*
	 *	Set the IP module up
	 */

	ip_init();

	tcp_v4_init();

	/* Setup TCP slab cache for open requests. */
	tcp_init();

	/* Setup UDP memory threshold */
	udp_init();

	/* Add UDP-Lite (RFC 3828) */
	udplite4_register();

	/*
	 *	Set the ICMP layer up
	 */

	if (icmp_init() < 0)
		panic("Failed to create the ICMP control socket.\n");

	/*
	 *	Initialise the multicast router
	 */
#if defined(CONFIG_IP_MROUTE)
	if (ip_mr_init())
		printk(KERN_CRIT "inet_init: Cannot init ipv4 mroute\n");
#endif
	/*
	 *	Initialise per-cpu ipv4 mibs
	 */

	if (init_ipv4_mibs())
		printk(KERN_CRIT "inet_init: Cannot init ipv4 mibs\n");

	ipv4_proc_init();

	ipfrag_init();

	dev_add_pack(&ip_packet_type);

	rc = 0;
out:
	return rc;
out_unregister_udp_proto:
	proto_unregister(&udp_prot);
out_unregister_tcp_proto:
	proto_unregister(&tcp_prot);
out_free_reserved_ports:
	kfree(sysctl_local_reserved_ports);
	goto out;
}

fs_initcall(inet_init);

/* ------------------------------------------------------------------------ */

#ifdef CONFIG_PROC_FS
static int __init ipv4_proc_init(void)
{
	int rc = 0;

	if (raw_proc_init())
		goto out_raw;
	if (tcp4_proc_init())
		goto out_tcp;
	if (udp4_proc_init())
		goto out_udp;
	if (ip_misc_proc_init())
		goto out_misc;
out:
	return rc;
out_misc:
	udp4_proc_exit();
out_udp:
	tcp4_proc_exit();
out_tcp:
	raw_proc_exit();
out_raw:
	rc = -ENOMEM;
	goto out;
}

#else /* CONFIG_PROC_FS */
static int __init ipv4_proc_init(void)
{
	return 0;
}
#endif /* CONFIG_PROC_FS */

MODULE_ALIAS_NETPROTO(PF_INET);

OpenPOWER on IntegriCloud