aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4/devinet.c
blob: cd71a39083910f21580275fd2ee2b6803c115c6c (plain) (blame)
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
/*
 *	NET3	IP device support routines.
 *
 *		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.
 *
 *	Derived from the IP parts of dev.c 1.0.19
 * 		Authors:	Ross Biro
 *				Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *				Mark Evans, <evansmp@uhura.aston.ac.uk>
 *
 *	Additional Authors:
 *		Alan Cox, <gw4pts@gw4pts.ampr.org>
 *		Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
 *
 *	Changes:
 *		Alexey Kuznetsov:	pa_* fields are replaced with ifaddr
 *					lists.
 *		Cyrus Durgin:		updated for kmod
 *		Matthias Andree:	in devinet_ioctl, compare label and
 *					address (4.4BSD alias style support),
 *					fall back to comparing just the label
 *					if no match found.
 */


#include <asm/uaccess.h>
#include <asm/system.h>
#include <linux/bitops.h>
#include <linux/capability.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/in.h>
#include <linux/errno.h>
#include <linux/interrupt.h>
#include <linux/if_addr.h>
#include <linux/if_ether.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/notifier.h>
#include <linux/inetdevice.h>
#include <linux/igmp.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
#include <linux/kmod.h>

#include <net/arp.h>
#include <net/ip.h>
#include <net/route.h>
#include <net/ip_fib.h>
#include <net/rtnetlink.h>
#include <net/net_namespace.h>

static struct ipv4_devconf ipv4_devconf = {
	.data = {
		[NET_IPV4_CONF_ACCEPT_REDIRECTS - 1] = 1,
		[NET_IPV4_CONF_SEND_REDIRECTS - 1] = 1,
		[NET_IPV4_CONF_SECURE_REDIRECTS - 1] = 1,
		[NET_IPV4_CONF_SHARED_MEDIA - 1] = 1,
	},
};

static struct ipv4_devconf ipv4_devconf_dflt = {
	.data = {
		[NET_IPV4_CONF_ACCEPT_REDIRECTS - 1] = 1,
		[NET_IPV4_CONF_SEND_REDIRECTS - 1] = 1,
		[NET_IPV4_CONF_SECURE_REDIRECTS - 1] = 1,
		[NET_IPV4_CONF_SHARED_MEDIA - 1] = 1,
		[NET_IPV4_CONF_ACCEPT_SOURCE_ROUTE - 1] = 1,
	},
};

#define IPV4_DEVCONF_DFLT(net, attr) \
	IPV4_DEVCONF((*net->ipv4.devconf_dflt), attr)

static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = {
	[IFA_LOCAL]     	= { .type = NLA_U32 },
	[IFA_ADDRESS]   	= { .type = NLA_U32 },
	[IFA_BROADCAST] 	= { .type = NLA_U32 },
	[IFA_LABEL]     	= { .type = NLA_STRING, .len = IFNAMSIZ - 1 },
};

static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32);

static BLOCKING_NOTIFIER_HEAD(inetaddr_chain);
static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
			 int destroy);
#ifdef CONFIG_SYSCTL
static void devinet_sysctl_register(struct in_device *idev);
static void devinet_sysctl_unregister(struct in_device *idev);
#else
static inline void devinet_sysctl_register(struct in_device *idev)
{
}
static inline void devinet_sysctl_unregister(struct in_device *idev)
{
}
#endif

/* Locks all the inet devices. */

static struct in_ifaddr *inet_alloc_ifa(void)
{
	return kzalloc(sizeof(struct in_ifaddr), GFP_KERNEL);
}

static void inet_rcu_free_ifa(struct rcu_head *head)
{
	struct in_ifaddr *ifa = container_of(head, struct in_ifaddr, rcu_head);
	if (ifa->ifa_dev)
		in_dev_put(ifa->ifa_dev);
	kfree(ifa);
}

static inline void inet_free_ifa(struct in_ifaddr *ifa)
{
	call_rcu(&ifa->rcu_head, inet_rcu_free_ifa);
}

void in_dev_finish_destroy(struct in_device *idev)
{
	struct net_device *dev = idev->dev;

	WARN_ON(idev->ifa_list);
	WARN_ON(idev->mc_list);
#ifdef NET_REFCNT_DEBUG
	printk(KERN_DEBUG "in_dev_finish_destroy: %p=%s\n",
	       idev, dev ? dev->name : "NIL");
#endif
	dev_put(dev);
	if (!idev->dead)
		pr_err("Freeing alive in_device %p\n", idev);
	else
		kfree(idev);
}
EXPORT_SYMBOL(in_dev_finish_destroy);

static struct in_device *inetdev_init(struct net_device *dev)
{
	struct in_device *in_dev;

	ASSERT_RTNL();

	in_dev = kzalloc(sizeof(*in_dev), GFP_KERNEL);
	if (!in_dev)
		goto out;
	memcpy(&in_dev->cnf, dev_net(dev)->ipv4.devconf_dflt,
			sizeof(in_dev->cnf));
	in_dev->cnf.sysctl = NULL;
	in_dev->dev = dev;
	in_dev->arp_parms = neigh_parms_alloc(dev, &arp_tbl);
	if (!in_dev->arp_parms)
		goto out_kfree;
	if (IPV4_DEVCONF(in_dev->cnf, FORWARDING))
		dev_disable_lro(dev);
	/* Reference in_dev->dev */
	dev_hold(dev);
	/* Account for reference dev->ip_ptr (below) */
	in_dev_hold(in_dev);

	devinet_sysctl_register(in_dev);
	ip_mc_init_dev(in_dev);
	if (dev->flags & IFF_UP)
		ip_mc_up(in_dev);

	/* we can receive as soon as ip_ptr is set -- do this last */
	rcu_assign_pointer(dev->ip_ptr, in_dev);
out:
	return in_dev;
out_kfree:
	kfree(in_dev);
	in_dev = NULL;
	goto out;
}

static void in_dev_rcu_put(struct rcu_head *head)
{
	struct in_device *idev = container_of(head, struct in_device, rcu_head);
	in_dev_put(idev);
}

static void inetdev_destroy(struct in_device *in_dev)
{
	struct in_ifaddr *ifa;
	struct net_device *dev;

	ASSERT_RTNL();

	dev = in_dev->dev;

	in_dev->dead = 1;

	ip_mc_destroy_dev(in_dev);

	while ((ifa = in_dev->ifa_list) != NULL) {
		inet_del_ifa(in_dev, &in_dev->ifa_list, 0);
		inet_free_ifa(ifa);
	}

	dev->ip_ptr = NULL;

	devinet_sysctl_unregister(in_dev);
	neigh_parms_release(&arp_tbl, in_dev->arp_parms);
	arp_ifdown(dev);

	call_rcu(&in_dev->rcu_head, in_dev_rcu_put);
}

int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b)
{
	rcu_read_lock();
	for_primary_ifa(in_dev) {
		if (inet_ifa_match(a, ifa)) {
			if (!b || inet_ifa_match(b, ifa)) {
				rcu_read_unlock();
				return 1;
			}
		}
	} endfor_ifa(in_dev);
	rcu_read_unlock();
	return 0;
}

static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
			 int destroy, struct nlmsghdr *nlh, u32 pid)
{
	struct in_ifaddr *promote = NULL;
	struct in_ifaddr *ifa, *ifa1 = *ifap;
	struct in_ifaddr *last_prim = in_dev->ifa_list;
	struct in_ifaddr *prev_prom = NULL;
	int do_promote = IN_DEV_PROMOTE_SECONDARIES(in_dev);

	ASSERT_RTNL();

	/* 1. Deleting primary ifaddr forces deletion all secondaries
	 * unless alias promotion is set
	 **/

	if (!(ifa1->ifa_flags & IFA_F_SECONDARY)) {
		struct in_ifaddr **ifap1 = &ifa1->ifa_next;

		while ((ifa = *ifap1) != NULL) {
			if (!(ifa->ifa_flags & IFA_F_SECONDARY) &&
			    ifa1->ifa_scope <= ifa->ifa_scope)
				last_prim = ifa;

			if (!(ifa->ifa_flags & IFA_F_SECONDARY) ||
			    ifa1->ifa_mask != ifa->ifa_mask ||
			    !inet_ifa_match(ifa1->ifa_address, ifa)) {
				ifap1 = &ifa->ifa_next;
				prev_prom = ifa;
				continue;
			}

			if (!do_promote) {
				*ifap1 = ifa->ifa_next;

				rtmsg_ifa(RTM_DELADDR, ifa, nlh, pid);
				blocking_notifier_call_chain(&inetaddr_chain,
						NETDEV_DOWN, ifa);
				inet_free_ifa(ifa);
			} else {
				promote = ifa;
				break;
			}
		}
	}

	/* 2. Unlink it */

	*ifap = ifa1->ifa_next;

	/* 3. Announce address deletion */

	/* Send message first, then call notifier.
	   At first sight, FIB update triggered by notifier
	   will refer to already deleted ifaddr, that could confuse
	   netlink listeners. It is not true: look, gated sees
	   that route deleted and if it still thinks that ifaddr
	   is valid, it will try to restore deleted routes... Grr.
	   So that, this order is correct.
	 */
	rtmsg_ifa(RTM_DELADDR, ifa1, nlh, pid);
	blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa1);

	if (promote) {

		if (prev_prom) {
			prev_prom->ifa_next = promote->ifa_next;
			promote->ifa_next = last_prim->ifa_next;
			last_prim->ifa_next = promote;
		}

		promote->ifa_flags &= ~IFA_F_SECONDARY;
		rtmsg_ifa(RTM_NEWADDR, promote, nlh, pid);
		blocking_notifier_call_chain(&inetaddr_chain,
				NETDEV_UP, promote);
		for (ifa = promote->ifa_next; ifa; ifa = ifa->ifa_next) {
			if (ifa1->ifa_mask != ifa->ifa_mask ||
			    !inet_ifa_match(ifa1->ifa_address, ifa))
					continue;
			fib_add_ifaddr(ifa);
		}

	}
	if (destroy)
		inet_free_ifa(ifa1);
}

static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
			 int destroy)
{
	__inet_del_ifa(in_dev, ifap, destroy, NULL, 0);
}

static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
			     u32 pid)
{
	struct in_device *in_dev = ifa->ifa_dev;
	struct in_ifaddr *ifa1, **ifap, **last_primary;

	ASSERT_RTNL();

	if (!ifa->ifa_local) {
		inet_free_ifa(ifa);
		return 0;
	}

	ifa->ifa_flags &= ~IFA_F_SECONDARY;
	last_primary = &in_dev->ifa_list;

	for (ifap = &in_dev->ifa_list; (ifa1 = *ifap) != NULL;
	     ifap = &ifa1->ifa_next) {
		if (!(ifa1->ifa_flags & IFA_F_SECONDARY) &&
		    ifa->ifa_scope <= ifa1->ifa_scope)
			last_primary = &ifa1->ifa_next;
		if (ifa1->ifa_mask == ifa->ifa_mask &&
		    inet_ifa_match(ifa1->ifa_address, ifa)) {
			if (ifa1->ifa_local == ifa->ifa_local) {
				inet_free_ifa(ifa);
				return -EEXIST;
			}
			if (ifa1->ifa_scope != ifa->ifa_scope) {
				inet_free_ifa(ifa);
				return -EINVAL;
			}
			ifa->ifa_flags |= IFA_F_SECONDARY;
		}
	}

	if (!(ifa->ifa_flags & IFA_F_SECONDARY)) {
		net_srandom(ifa->ifa_local);
		ifap = last_primary;
	}

	ifa->ifa_next = *ifap;
	*ifap = ifa;

	/* Send message first, then call notifier.
	   Notifier will trigger FIB update, so that
	   listeners of netlink will know about new ifaddr */
	rtmsg_ifa(RTM_NEWADDR, ifa, nlh, pid);
	blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa);

	return 0;
}

static int inet_insert_ifa(struct in_ifaddr *ifa)
{
	return __inet_insert_ifa(ifa, NULL, 0);
}

static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa)
{
	struct in_device *in_dev = __in_dev_get_rtnl(dev);

	ASSERT_RTNL();

	if (!in_dev) {
		inet_free_ifa(ifa);
		return -ENOBUFS;
	}
	ipv4_devconf_setall(in_dev);
	if (ifa->ifa_dev != in_dev) {
		WARN_ON(ifa->ifa_dev);
		in_dev_hold(in_dev);
		ifa->ifa_dev = in_dev;
	}
	if (ipv4_is_loopback(ifa->ifa_local))
		ifa->ifa_scope = RT_SCOPE_HOST;
	return inet_insert_ifa(ifa);
}

struct in_device *inetdev_by_index(struct net *net, int ifindex)
{
	struct net_device *dev;
	struct in_device *in_dev = NULL;

	rcu_read_lock();
	dev = dev_get_by_index_rcu(net, ifindex);
	if (dev)
		in_dev = in_dev_get(dev);
	rcu_read_unlock();
	return in_dev;
}
EXPORT_SYMBOL(inetdev_by_index);

/* Called only from RTNL semaphored context. No locks. */

struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix,
				    __be32 mask)
{
	ASSERT_RTNL();

	for_primary_ifa(in_dev) {
		if (ifa->ifa_mask == mask && inet_ifa_match(prefix, ifa))
			return ifa;
	} endfor_ifa(in_dev);
	return NULL;
}

static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
	struct net *net = sock_net(skb->sk);
	struct nlattr *tb[IFA_MAX+1];
	struct in_device *in_dev;
	struct ifaddrmsg *ifm;
	struct in_ifaddr *ifa, **ifap;
	int err = -EINVAL;

	ASSERT_RTNL();

	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy);
	if (err < 0)
		goto errout;

	ifm = nlmsg_data(nlh);
	in_dev = inetdev_by_index(net, ifm->ifa_index);
	if (in_dev == NULL) {
		err = -ENODEV;
		goto errout;
	}

	__in_dev_put(in_dev);

	for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL;
	     ifap = &ifa->ifa_next) {
		if (tb[IFA_LOCAL] &&
		    ifa->ifa_local != nla_get_be32(tb[IFA_LOCAL]))
			continue;

		if (tb[IFA_LABEL] && nla_strcmp(tb[IFA_LABEL], ifa->ifa_label))
			continue;

		if (tb[IFA_ADDRESS] &&
		    (ifm->ifa_prefixlen != ifa->ifa_prefixlen ||
		    !inet_ifa_match(nla_get_be32(tb[IFA_ADDRESS]), ifa)))
			continue;

		__inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).pid);
		return 0;
	}

	err = -EADDRNOTAVAIL;
errout:
	return err;
}

static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh)
{
	struct nlattr *tb[IFA_MAX+1];
	struct in_ifaddr *ifa;
	struct ifaddrmsg *ifm;
	struct net_device *dev;
	struct in_device *in_dev;
	int err;

	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy);
	if (err < 0)
		goto errout;

	ifm = nlmsg_data(nlh);
	err = -EINVAL;
	if (ifm->ifa_prefixlen > 32 || tb[IFA_LOCAL] == NULL)
		goto errout;

	dev = __dev_get_by_index(net, ifm->ifa_index);
	err = -ENODEV;
	if (dev == NULL)
		goto errout;

	in_dev = __in_dev_get_rtnl(dev);
	err = -ENOBUFS;
	if (in_dev == NULL)
		goto errout;

	ifa = inet_alloc_ifa();
	if (ifa == NULL)
		/*
		 * A potential indev allocation can be left alive, it stays
		 * assigned to its device and is destroy with it.
		 */
		goto errout;

	ipv4_devconf_setall(in_dev);
	in_dev_hold(in_dev);

	if (tb[IFA_ADDRESS] == NULL)
		tb[IFA_ADDRESS] = tb[IFA_LOCAL];

	ifa->ifa_prefixlen = ifm->ifa_prefixlen;
	ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen);
	ifa->ifa_flags = ifm->ifa_flags;
	ifa->ifa_scope = ifm->ifa_scope;
	ifa->ifa_dev = in_dev;

	ifa->ifa_local = nla_get_be32(tb[IFA_LOCAL]);
	ifa->ifa_address = nla_get_be32(tb[IFA_ADDRESS]);

	if (tb[IFA_BROADCAST])
		ifa->ifa_broadcast = nla_get_be32(tb[IFA_BROADCAST]);

	if (tb[IFA_LABEL])
		nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
	else
		memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);

	return ifa;

errout:
	return ERR_PTR(err);
}

static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
	struct net *net = sock_net(skb->sk);
	struct in_ifaddr *ifa;

	ASSERT_RTNL();

	ifa = rtm_to_ifaddr(net, nlh);
	if (IS_ERR(ifa))
		return PTR_ERR(ifa);

	return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).pid);
}

/*
 *	Determine a default network mask, based on the IP address.
 */

static inline int inet_abc_len(__be32 addr)
{
	int rc = -1;	/* Something else, probably a multicast. */

	if (ipv4_is_zeronet(addr))
		rc = 0;
	else {
		__u32 haddr = ntohl(addr);

		if (IN_CLASSA(haddr))
			rc = 8;
		else if (IN_CLASSB(haddr))
			rc = 16;
		else if (IN_CLASSC(haddr))
			rc = 24;
	}

	return rc;
}


int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
{
	struct ifreq ifr;
	struct sockaddr_in sin_orig;
	struct sockaddr_in *sin = (struct sockaddr_in *)&ifr.ifr_addr;
	struct in_device *in_dev;
	struct in_ifaddr **ifap = NULL;
	struct in_ifaddr *ifa = NULL;
	struct net_device *dev;
	char *colon;
	int ret = -EFAULT;
	int tryaddrmatch = 0;

	/*
	 *	Fetch the caller's info block into kernel space
	 */

	if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
		goto out;
	ifr.ifr_name[IFNAMSIZ - 1] = 0;

	/* save original address for comparison */
	memcpy(&sin_orig, sin, sizeof(*sin));

	colon = strchr(ifr.ifr_name, ':');
	if (colon)
		*colon = 0;

	dev_load(net, ifr.ifr_name);

	switch (cmd) {
	case SIOCGIFADDR:	/* Get interface address */
	case SIOCGIFBRDADDR:	/* Get the broadcast address */
	case SIOCGIFDSTADDR:	/* Get the destination address */
	case SIOCGIFNETMASK:	/* Get the netmask for the interface */
		/* Note that these ioctls will not sleep,
		   so that we do not impose a lock.
		   One day we will be forced to put shlock here (I mean SMP)
		 */
		tryaddrmatch = (sin_orig.sin_family == AF_INET);
		memset(sin, 0, sizeof(*sin));
		sin->sin_family = AF_INET;
		break;

	case SIOCSIFFLAGS:
		ret = -EACCES;
		if (!capable(CAP_NET_ADMIN))
			goto out;
		break;
	case SIOCSIFADDR:	/* Set interface address (and family) */
	case SIOCSIFBRDADDR:	/* Set the broadcast address */
	case SIOCSIFDSTADDR:	/* Set the destination address */
	case SIOCSIFNETMASK: 	/* Set the netmask for the interface */
		ret = -EACCES;
		if (!capable(CAP_NET_ADMIN))
			goto out;
		ret = -EINVAL;
		if (sin->sin_family != AF_INET)
			goto out;
		break;
	default:
		ret = -EINVAL;
		goto out;
	}

	rtnl_lock();

	ret = -ENODEV;
	dev = __dev_get_by_name(net, ifr.ifr_name);
	if (!dev)
		goto done;

	if (colon)
		*colon = ':';

	in_dev = __in_dev_get_rtnl(dev);
	if (in_dev) {
		if (tryaddrmatch) {
			/* Matthias Andree */
			/* compare label and address (4.4BSD style) */
			/* note: we only do this for a limited set of ioctls
			   and only if the original address family was AF_INET.
			   This is checked above. */
			for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL;
			     ifap = &ifa->ifa_next) {
				if (!strcmp(ifr.ifr_name, ifa->ifa_label) &&
				    sin_orig.sin_addr.s_addr ==
							ifa->ifa_address) {
					break; /* found */
				}
			}
		}
		/* we didn't get a match, maybe the application is
		   4.3BSD-style and passed in junk so we fall back to
		   comparing just the label */
		if (!ifa) {
			for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL;
			     ifap = &ifa->ifa_next)
				if (!strcmp(ifr.ifr_name, ifa->ifa_label))
					break;
		}
	}

	ret = -EADDRNOTAVAIL;
	if (!ifa && cmd != SIOCSIFADDR && cmd != SIOCSIFFLAGS)
		goto done;

	switch (cmd) {
	case SIOCGIFADDR:	/* Get interface address */
		sin->sin_addr.s_addr = ifa->ifa_local;
		goto rarok;

	case SIOCGIFBRDADDR:	/* Get the broadcast address */
		sin->sin_addr.s_addr = ifa->ifa_broadcast;
		goto rarok;

	case SIOCGIFDSTADDR:	/* Get the destination address */
		sin->sin_addr.s_addr = ifa->ifa_address;
		goto rarok;

	case SIOCGIFNETMASK:	/* Get the netmask for the interface */
		sin->sin_addr.s_addr = ifa->ifa_mask;
		goto rarok;

	case SIOCSIFFLAGS:
		if (colon) {
			ret = -EADDRNOTAVAIL;
			if (!ifa)
				break;
			ret = 0;
			if (!(ifr.ifr_flags & IFF_UP))
				inet_del_ifa(in_dev, ifap, 1);
			break;
		}
		ret = dev_change_flags(dev, ifr.ifr_flags);
		break;

	case SIOCSIFADDR:	/* Set interface address (and family) */
		ret = -EINVAL;
		if (inet_abc_len(sin->sin_addr.s_addr) < 0)
			break;

		if (!ifa) {
			ret = -ENOBUFS;
			ifa = inet_alloc_ifa();
			if (!ifa)
				break;
			if (colon)
				memcpy(ifa->ifa_label, ifr.ifr_name, IFNAMSIZ);
			else
				memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
		} else {
			ret = 0;
			if (ifa->ifa_local == sin->sin_addr.s_addr)
				break;
			inet_del_ifa(in_dev, ifap, 0);
			ifa->ifa_broadcast = 0;
			ifa->ifa_scope = 0;
		}

		ifa->ifa_address = ifa->ifa_local = sin->sin_addr.s_addr;

		if (!(dev->flags & IFF_POINTOPOINT)) {
			ifa->ifa_prefixlen = inet_abc_len(ifa->ifa_address);
			ifa->ifa_mask = inet_make_mask(ifa->ifa_prefixlen);
			if ((dev->flags & IFF_BROADCAST) &&
			    ifa->ifa_prefixlen < 31)
				ifa->ifa_broadcast = ifa->ifa_address |
						     ~ifa->ifa_mask;
		} else {
			ifa->ifa_prefixlen = 32;
			ifa->ifa_mask = inet_make_mask(32);
		}
		ret = inet_set_ifa(dev, ifa);
		break;

	case SIOCSIFBRDADDR:	/* Set the broadcast address */
		ret = 0;
		if (ifa->ifa_broadcast != sin->sin_addr.s_addr) {
			inet_del_ifa(in_dev, ifap, 0);
			ifa->ifa_broadcast = sin->sin_addr.s_addr;
			inet_insert_ifa(ifa);
		}
		break;

	case SIOCSIFDSTADDR:	/* Set the destination address */
		ret = 0;
		if (ifa->ifa_address == sin->sin_addr.s_addr)
			break;
		ret = -EINVAL;
		if (inet_abc_len(sin->sin_addr.s_addr) < 0)
			break;
		ret = 0;
		inet_del_ifa(in_dev, ifap, 0);
		ifa->ifa_address = sin->sin_addr.s_addr;
		inet_insert_ifa(ifa);
		break;

	case SIOCSIFNETMASK: 	/* Set the netmask for the interface */

		/*
		 *	The mask we set must be legal.
		 */
		ret = -EINVAL;
		if (bad_mask(sin->sin_addr.s_addr, 0))
			break;
		ret = 0;
		if (ifa->ifa_mask != sin->sin_addr.s_addr) {
			__be32 old_mask = ifa->ifa_mask;
			inet_del_ifa(in_dev, ifap, 0);
			ifa->ifa_mask = sin->sin_addr.s_addr;
			ifa->ifa_prefixlen = inet_mask_len(ifa->ifa_mask);

			/* See if current broadcast address matches
			 * with current netmask, then recalculate
			 * the broadcast address. Otherwise it's a
			 * funny address, so don't touch it since
			 * the user seems to know what (s)he's doing...
			 */
			if ((dev->flags & IFF_BROADCAST) &&
			    (ifa->ifa_prefixlen < 31) &&
			    (ifa->ifa_broadcast ==
			     (ifa->ifa_local|~old_mask))) {
				ifa->ifa_broadcast = (ifa->ifa_local |
						      ~sin->sin_addr.s_addr);
			}
			inet_insert_ifa(ifa);
		}
		break;
	}
done:
	rtnl_unlock();
out:
	return ret;
rarok:
	rtnl_unlock();
	ret = copy_to_user(arg, &ifr, sizeof(struct ifreq)) ? -EFAULT : 0;
	goto out;
}

static int inet_gifconf(struct net_device *dev, char __user *buf, int len)
{
	struct in_device *in_dev = __in_dev_get_rtnl(dev);
	struct in_ifaddr *ifa;
	struct ifreq ifr;
	int done = 0;

	if (!in_dev)
		goto out;

	for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
		if (!buf) {
			done += sizeof(ifr);
			continue;
		}
		if (len < (int) sizeof(ifr))
			break;
		memset(&ifr, 0, sizeof(struct ifreq));
		if (ifa->ifa_label)
			strcpy(ifr.ifr_name, ifa->ifa_label);
		else
			strcpy(ifr.ifr_name, dev->name);

		(*(struct sockaddr_in *)&ifr.ifr_addr).sin_family = AF_INET;
		(*(struct sockaddr_in *)&ifr.ifr_addr).sin_addr.s_addr =
								ifa->ifa_local;

		if (copy_to_user(buf, &ifr, sizeof(struct ifreq))) {
			done = -EFAULT;
			break;
		}
		buf  += sizeof(struct ifreq);
		len  -= sizeof(struct ifreq);
		done += sizeof(struct ifreq);
	}
out:
	return done;
}

__be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope)
{
	__be32 addr = 0;
	struct in_device *in_dev;
	struct net *net = dev_net(dev);

	rcu_read_lock();
	in_dev = __in_dev_get_rcu(dev);
	if (!in_dev)
		goto no_in_dev;

	for_primary_ifa(in_dev) {
		if (ifa->ifa_scope > scope)
			continue;
		if (!dst || inet_ifa_match(dst, ifa)) {
			addr = ifa->ifa_local;
			break;
		}
		if (!addr)
			addr = ifa->ifa_local;
	} endfor_ifa(in_dev);

	if (addr)
		goto out_unlock;
no_in_dev:

	/* Not loopback addresses on loopback should be preferred
	   in this case. It is importnat that lo is the first interface
	   in dev_base list.
	 */
	for_each_netdev_rcu(net, dev) {
		in_dev = __in_dev_get_rcu(dev);
		if (!in_dev)
			continue;

		for_primary_ifa(in_dev) {
			if (ifa->ifa_scope != RT_SCOPE_LINK &&
			    ifa->ifa_scope <= scope) {
				addr = ifa->ifa_local;
				goto out_unlock;
			}
		} endfor_ifa(in_dev);
	}
out_unlock:
	rcu_read_unlock();
	return addr;
}
EXPORT_SYMBOL(inet_select_addr);

static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst,
			      __be32 local, int scope)
{
	int same = 0;
	__be32 addr = 0;

	for_ifa(in_dev) {
		if (!addr &&
		    (local == ifa->ifa_local || !local) &&
		    ifa->ifa_scope <= scope) {
			addr = ifa->ifa_local;
			if (same)
				break;
		}
		if (!same) {
			same = (!local || inet_ifa_match(local, ifa)) &&
				(!dst || inet_ifa_match(dst, ifa));
			if (same && addr) {
				if (local || !dst)
					break;
				/* Is the selected addr into dst subnet? */
				if (inet_ifa_match(addr, ifa))
					break;
				/* No, then can we use new local src? */
				if (ifa->ifa_scope <= scope) {
					addr = ifa->ifa_local;
					break;
				}
				/* search for large dst subnet for addr */
				same = 0;
			}
		}
	} endfor_ifa(in_dev);

	return same ? addr : 0;
}

/*
 * Confirm that local IP address exists using wildcards:
 * - in_dev: only on this interface, 0=any interface
 * - dst: only in the same subnet as dst, 0=any dst
 * - local: address, 0=autoselect the local address
 * - scope: maximum allowed scope value for the local address
 */
__be32 inet_confirm_addr(struct in_device *in_dev,
			 __be32 dst, __be32 local, int scope)
{
	__be32 addr = 0;
	struct net_device *dev;
	struct net *net;

	if (scope != RT_SCOPE_LINK)
		return confirm_addr_indev(in_dev, dst, local, scope);

	net = dev_net(in_dev->dev);
	rcu_read_lock();
	for_each_netdev_rcu(net, dev) {
		in_dev = __in_dev_get_rcu(dev);
		if (in_dev) {
			addr = confirm_addr_indev(in_dev, dst, local, scope);
			if (addr)
				break;
		}
	}
	rcu_read_unlock();

	return addr;
}

/*
 *	Device notifier
 */

int register_inetaddr_notifier(struct notifier_block *nb)
{
	return blocking_notifier_chain_register(&inetaddr_chain, nb);
}
EXPORT_SYMBOL(register_inetaddr_notifier);

int unregister_inetaddr_notifier(struct notifier_block *nb)
{
	return blocking_notifier_chain_unregister(&inetaddr_chain, nb);
}
EXPORT_SYMBOL(unregister_inetaddr_notifier);

/* Rename ifa_labels for a device name change. Make some effort to preserve
 * existing alias numbering and to create unique labels if possible.
*/
static void inetdev_changename(struct net_device *dev, struct in_device *in_dev)
{
	struct in_ifaddr *ifa;
	int named = 0;

	for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
		char old[IFNAMSIZ], *dot;

		memcpy(old, ifa->ifa_label, IFNAMSIZ);
		memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
		if (named++ == 0)
			goto skip;
		dot = strchr(old, ':');
		if (dot == NULL) {
			sprintf(old, ":%d", named);
			dot = old;
		}
		if (strlen(dot) + strlen(dev->name) < IFNAMSIZ)
			strcat(ifa->ifa_label, dot);
		else
			strcpy(ifa->ifa_label + (IFNAMSIZ - strlen(dot) - 1), dot);
skip:
		rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0);
	}
}

static inline bool inetdev_valid_mtu(unsigned mtu)
{
	return mtu >= 68;
}

/* Called only under RTNL semaphore */

static int inetdev_event(struct notifier_block *this, unsigned long event,
			 void *ptr)
{
	struct net_device *dev = ptr;
	struct in_device *in_dev = __in_dev_get_rtnl(dev);

	ASSERT_RTNL();

	if (!in_dev) {
		if (event == NETDEV_REGISTER) {
			in_dev = inetdev_init(dev);
			if (!in_dev)
				return notifier_from_errno(-ENOMEM);
			if (dev->flags & IFF_LOOPBACK) {
				IN_DEV_CONF_SET(in_dev, NOXFRM, 1);
				IN_DEV_CONF_SET(in_dev, NOPOLICY, 1);
			}
		} else if (event == NETDEV_CHANGEMTU) {
			/* Re-enabling IP */
			if (inetdev_valid_mtu(dev->mtu))
				in_dev = inetdev_init(dev);
		}
		goto out;
	}

	switch (event) {
	case NETDEV_REGISTER:
		printk(KERN_DEBUG "inetdev_event: bug\n");
		dev->ip_ptr = NULL;
		break;
	case NETDEV_UP:
		if (!inetdev_valid_mtu(dev->mtu))
			break;
		if (dev->flags & IFF_LOOPBACK) {
			struct in_ifaddr *ifa = inet_alloc_ifa();

			if (ifa) {
				ifa->ifa_local =
				  ifa->ifa_address = htonl(INADDR_LOOPBACK);
				ifa->ifa_prefixlen = 8;
				ifa->ifa_mask = inet_make_mask(8);
				in_dev_hold(in_dev);
				ifa->ifa_dev = in_dev;
				ifa->ifa_scope = RT_SCOPE_HOST;
				memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
				inet_insert_ifa(ifa);
			}
		}
		ip_mc_up(in_dev);
		/* fall through */
	case NETDEV_CHANGEADDR:
		/* Send gratuitous ARP to notify of link change */
		if (IN_DEV_ARP_NOTIFY(in_dev)) {
			struct in_ifaddr *ifa = in_dev->ifa_list;

			if (ifa)
				arp_send(ARPOP_REQUEST, ETH_P_ARP,
					 ifa->ifa_address, dev,
					 ifa->ifa_address, NULL,
					 dev->dev_addr, NULL);
		}
		break;
	case NETDEV_DOWN:
		ip_mc_down(in_dev);
		break;
	case NETDEV_BONDING_OLDTYPE:
		ip_mc_unmap(in_dev);
		break;
	case NETDEV_BONDING_NEWTYPE:
		ip_mc_remap(in_dev);
		break;
	case NETDEV_CHANGEMTU:
		if (inetdev_valid_mtu(dev->mtu))
			break;
		/* disable IP when MTU is not enough */
	case NETDEV_UNREGISTER:
		inetdev_destroy(in_dev);
		break;
	case NETDEV_CHANGENAME:
		/* Do not notify about label change, this event is
		 * not interesting to applications using netlink.
		 */
		inetdev_changename(dev, in_dev);

		devinet_sysctl_unregister(in_dev);
		devinet_sysctl_register(in_dev);
		break;
	}
out:
	return NOTIFY_DONE;
}

static struct notifier_block ip_netdev_notifier = {
	.notifier_call = inetdev_event,
};

static inline size_t inet_nlmsg_size(void)
{
	return NLMSG_ALIGN(sizeof(struct ifaddrmsg))
	       + nla_total_size(4) /* IFA_ADDRESS */
	       + nla_total_size(4) /* IFA_LOCAL */
	       + nla_total_size(4) /* IFA_BROADCAST */
	       + nla_total_size(IFNAMSIZ); /* IFA_LABEL */
}

static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa,
			    u32 pid, u32 seq, int event, unsigned int flags)
{
	struct ifaddrmsg *ifm;
	struct nlmsghdr  *nlh;

	nlh = nlmsg_put(skb, pid, seq, event, sizeof(*ifm), flags);
	if (nlh == NULL)
		return -EMSGSIZE;

	ifm = nlmsg_data(nlh);
	ifm->ifa_family = AF_INET;
	ifm->ifa_prefixlen = ifa->ifa_prefixlen;
	ifm->ifa_flags = ifa->ifa_flags|IFA_F_PERMANENT;
	ifm->ifa_scope = ifa->ifa_scope;
	ifm->ifa_index = ifa->ifa_dev->dev->ifindex;

	if (ifa->ifa_address)
		NLA_PUT_BE32(skb, IFA_ADDRESS, ifa->ifa_address);

	if (ifa->ifa_local)
		NLA_PUT_BE32(skb, IFA_LOCAL, ifa->ifa_local);

	if (ifa->ifa_broadcast)
		NLA_PUT_BE32(skb, IFA_BROADCAST, ifa->ifa_broadcast);

	if (ifa->ifa_label[0])
		NLA_PUT_STRING(skb, IFA_LABEL, ifa->ifa_label);

	return nlmsg_end(skb, nlh);

nla_put_failure:
	nlmsg_cancel(skb, nlh);
	return -EMSGSIZE;
}

static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
{
	struct net *net = sock_net(skb->sk);
	int h, s_h;
	int idx, s_idx;
	int ip_idx, s_ip_idx;
	struct net_device *dev;
	struct in_device *in_dev;
	struct in_ifaddr *ifa;
	struct hlist_head *head;
	struct hlist_node *node;

	s_h = cb->args[0];
	s_idx = idx = cb->args[1];
	s_ip_idx = ip_idx = cb->args[2];

	for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
		idx = 0;
		head = &net->dev_index_head[h];
		rcu_read_lock();
		hlist_for_each_entry_rcu(dev, node, head, index_hlist) {
			if (idx < s_idx)
				goto cont;
			if (idx > s_idx)
				s_ip_idx = 0;
			in_dev = __in_dev_get_rcu(dev);
			if (!in_dev)
				goto cont;

			for (ifa = in_dev->ifa_list, ip_idx = 0; ifa;
			     ifa = ifa->ifa_next, ip_idx++) {
				if (ip_idx < s_ip_idx)
					continue;
				if (inet_fill_ifaddr(skb, ifa,
					     NETLINK_CB(cb->skb).pid,
					     cb->nlh->nlmsg_seq,
					     RTM_NEWADDR, NLM_F_MULTI) <= 0) {
					rcu_read_unlock();
					goto done;
				}
			}
cont:
			idx++;
		}
		rcu_read_unlock();
	}

done:
	cb->args[0] = h;
	cb->args[1] = idx;
	cb->args[2] = ip_idx;

	return skb->len;
}

static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh,
		      u32 pid)
{
	struct sk_buff *skb;
	u32 seq = nlh ? nlh->nlmsg_seq : 0;
	int err = -ENOBUFS;
	struct net *net;

	net = dev_net(ifa->ifa_dev->dev);
	skb = nlmsg_new(inet_nlmsg_size(), GFP_KERNEL);
	if (skb == NULL)
		goto errout;

	err = inet_fill_ifaddr(skb, ifa, pid, seq, event, 0);
	if (err < 0) {
		/* -EMSGSIZE implies BUG in inet_nlmsg_size() */
		WARN_ON(err == -EMSGSIZE);
		kfree_skb(skb);
		goto errout;
	}
	rtnl_notify(skb, net, pid, RTNLGRP_IPV4_IFADDR, nlh, GFP_KERNEL);
	return;
errout:
	if (err < 0)
		rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err);
}

#ifdef CONFIG_SYSCTL

static void devinet_copy_dflt_conf(struct net *net, int i)
{
	struct net_device *dev;

	rcu_read_lock();
	for_each_netdev_rcu(net, dev) {
		struct in_device *in_dev;

		in_dev = __in_dev_get_rcu(dev);
		if (in_dev && !test_bit(i, in_dev->cnf.state))
			in_dev->cnf.data[i] = net->ipv4.devconf_dflt->data[i];
	}
	rcu_read_unlock();
}

/* called with RTNL locked */
static void inet_forward_change(struct net *net)
{
	struct net_device *dev;
	int on = IPV4_DEVCONF_ALL(net, FORWARDING);

	IPV4_DEVCONF_ALL(net, ACCEPT_REDIRECTS) = !on;
	IPV4_DEVCONF_DFLT(net, FORWARDING) = on;

	for_each_netdev(net, dev) {
		struct in_device *in_dev;
		if (on)
			dev_disable_lro(dev);
		rcu_read_lock();
		in_dev = __in_dev_get_rcu(dev);
		if (in_dev)
			IN_DEV_CONF_SET(in_dev, FORWARDING, on);
		rcu_read_unlock();
	}
}

static int devinet_conf_proc(ctl_table *ctl, int write,
			     void __user *buffer,
			     size_t *lenp, loff_t *ppos)
{
	int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);

	if (write) {
		struct ipv4_devconf *cnf = ctl->extra1;
		struct net *net = ctl->extra2;
		int i = (int *)ctl->data - cnf->data;

		set_bit(i, cnf->state);

		if (cnf == net->ipv4.devconf_dflt)
			devinet_copy_dflt_conf(net, i);
	}

	return ret;
}

static int devinet_sysctl_forward(ctl_table *ctl, int write,
				  void __user *buffer,
				  size_t *lenp, loff_t *ppos)
{
	int *valp = ctl->data;
	int val = *valp;
	int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);

	if (write && *valp != val) {
		struct net *net = ctl->extra2;

		if (valp != &IPV4_DEVCONF_DFLT(net, FORWARDING)) {
			if (!rtnl_trylock())
				return restart_syscall();
			if (valp == &IPV4_DEVCONF_ALL(net, FORWARDING)) {
				inet_forward_change(net);
			} else if (*valp) {
				struct ipv4_devconf *cnf = ctl->extra1;
				struct in_device *idev =
					container_of(cnf, struct in_device, cnf);
				dev_disable_lro(idev->dev);
			}
			rtnl_unlock();
			rt_cache_flush(net, 0);
		}
	}

	return ret;
}

int ipv4_doint_and_flush(ctl_table *ctl, int write,
			 void __user *buffer,
			 size_t *lenp, loff_t *ppos)
{
	int *valp = ctl->data;
	int val = *valp;
	int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
	struct net *net = ctl->extra2;

	if (write && *valp != val)
		rt_cache_flush(net, 0);

	return ret;
}

#define DEVINET_SYSCTL_ENTRY(attr, name, mval, proc) \
	{ \
		.procname	= name, \
		.data		= ipv4_devconf.data + \
				  NET_IPV4_CONF_ ## attr - 1, \
		.maxlen		= sizeof(int), \
		.mode		= mval, \
		.proc_handler	= proc, \
		.extra1		= &ipv4_devconf, \
	}

#define DEVINET_SYSCTL_RW_ENTRY(attr, name) \
	DEVINET_SYSCTL_ENTRY(attr, name, 0644, devinet_conf_proc)

#define DEVINET_SYSCTL_RO_ENTRY(attr, name) \
	DEVINET_SYSCTL_ENTRY(attr, name, 0444, devinet_conf_proc)

#define DEVINET_SYSCTL_COMPLEX_ENTRY(attr, name, proc) \
	DEVINET_SYSCTL_ENTRY(attr, name, 0644, proc)

#define DEVINET_SYSCTL_FLUSHING_ENTRY(attr, name) \
	DEVINET_SYSCTL_COMPLEX_ENTRY(attr, name, ipv4_doint_and_flush)

static struct devinet_sysctl_table {
	struct ctl_table_header *sysctl_header;
	struct ctl_table devinet_vars[__NET_IPV4_CONF_MAX];
	char *dev_name;
} devinet_sysctl = {
	.devinet_vars = {
		DEVINET_SYSCTL_COMPLEX_ENTRY(FORWARDING, "forwarding",
					     devinet_sysctl_forward),
		DEVINET_SYSCTL_RO_ENTRY(MC_FORWARDING, "mc_forwarding"),

		DEVINET_SYSCTL_RW_ENTRY(ACCEPT_REDIRECTS, "accept_redirects"),
		DEVINET_SYSCTL_RW_ENTRY(SECURE_REDIRECTS, "secure_redirects"),
		DEVINET_SYSCTL_RW_ENTRY(SHARED_MEDIA, "shared_media"),
		DEVINET_SYSCTL_RW_ENTRY(RP_FILTER, "rp_filter"),
		DEVINET_SYSCTL_RW_ENTRY(SEND_REDIRECTS, "send_redirects"),
		DEVINET_SYSCTL_RW_ENTRY(ACCEPT_SOURCE_ROUTE,
					"accept_source_route"),
		DEVINET_SYSCTL_RW_ENTRY(ACCEPT_LOCAL, "accept_local"),
		DEVINET_SYSCTL_RW_ENTRY(SRC_VMARK, "src_valid_mark"),
		DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP, "proxy_arp"),
		DEVINET_SYSCTL_RW_ENTRY(MEDIUM_ID, "medium_id"),
		DEVINET_SYSCTL_RW_ENTRY(BOOTP_RELAY, "bootp_relay"),
		DEVINET_SYSCTL_RW_ENTRY(LOG_MARTIANS, "log_martians"),
		DEVINET_SYSCTL_RW_ENTRY(TAG, "tag"),
		DEVINET_SYSCTL_RW_ENTRY(ARPFILTER, "arp_filter"),
		DEVINET_SYSCTL_RW_ENTRY(ARP_ANNOUNCE, "arp_announce"),
		DEVINET_SYSCTL_RW_ENTRY(ARP_IGNORE, "arp_ignore"),
		DEVINET_SYSCTL_RW_ENTRY(ARP_ACCEPT, "arp_accept"),
		DEVINET_SYSCTL_RW_ENTRY(ARP_NOTIFY, "arp_notify"),
		DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP_PVLAN, "proxy_arp_pvlan"),

		DEVINET_SYSCTL_FLUSHING_ENTRY(NOXFRM, "disable_xfrm"),
		DEVINET_SYSCTL_FLUSHING_ENTRY(NOPOLICY, "disable_policy"),
		DEVINET_SYSCTL_FLUSHING_ENTRY(FORCE_IGMP_VERSION,
					      "force_igmp_version"),
		DEVINET_SYSCTL_FLUSHING_ENTRY(PROMOTE_SECONDARIES,
					      "promote_secondaries"),
	},
};

static int __devinet_sysctl_register(struct net *net, char *dev_name,
					struct ipv4_devconf *p)
{
	int i;
	struct devinet_sysctl_table *t;

#define DEVINET_CTL_PATH_DEV	3

	struct ctl_path devinet_ctl_path[] = {
		{ .procname = "net",  },
		{ .procname = "ipv4", },
		{ .procname = "conf", },
		{ /* to be set */ },
		{ },
	};

	t = kmemdup(&devinet_sysctl, sizeof(*t), GFP_KERNEL);
	if (!t)
		goto out;

	for (i = 0; i < ARRAY_SIZE(t->devinet_vars) - 1; i++) {
		t->devinet_vars[i].data += (char *)p - (char *)&ipv4_devconf;
		t->devinet_vars[i].extra1 = p;
		t->devinet_vars[i].extra2 = net;
	}

	/*
	 * Make a copy of dev_name, because '.procname' is regarded as const
	 * by sysctl and we wouldn't want anyone to change it under our feet
	 * (see SIOCSIFNAME).
	 */
	t->dev_name = kstrdup(dev_name, GFP_KERNEL);
	if (!t->dev_name)
		goto free;

	devinet_ctl_path[DEVINET_CTL_PATH_DEV].procname = t->dev_name;

	t->sysctl_header = register_net_sysctl_table(net, devinet_ctl_path,
			t->devinet_vars);
	if (!t->sysctl_header)
		goto free_procname;

	p->sysctl = t;
	return 0;

free_procname:
	kfree(t->dev_name);
free:
	kfree(t);
out:
	return -ENOBUFS;
}

static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf)
{
	struct devinet_sysctl_table *t = cnf->sysctl;

	if (t == NULL)
		return;

	cnf->sysctl = NULL;
	unregister_sysctl_table(t->sysctl_header);
	kfree(t->dev_name);
	kfree(t);
}

static void devinet_sysctl_register(struct in_device *idev)
{
	neigh_sysctl_register(idev->dev, idev->arp_parms, NET_IPV4,
			NET_IPV4_NEIGH, "ipv4", NULL);
	__devinet_sysctl_register(dev_net(idev->dev), idev->dev->name,
					&idev->cnf);
}

static void devinet_sysctl_unregister(struct in_device *idev)
{
	__devinet_sysctl_unregister(&idev->cnf);
	neigh_sysctl_unregister(idev->arp_parms);
}

static struct ctl_table ctl_forward_entry[] = {
	{
		.procname	= "ip_forward",
		.data		= &ipv4_devconf.data[
					NET_IPV4_CONF_FORWARDING - 1],
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= devinet_sysctl_forward,
		.extra1		= &ipv4_devconf,
		.extra2		= &init_net,
	},
	{ },
};

static __net_initdata struct ctl_path net_ipv4_path[] = {
	{ .procname = "net", },
	{ .procname = "ipv4", },
	{ },
};
#endif

static __net_init int devinet_init_net(struct net *net)
{
	int err;
	struct ipv4_devconf *all, *dflt;
#ifdef CONFIG_SYSCTL
	struct ctl_table *tbl = ctl_forward_entry;
	struct ctl_table_header *forw_hdr;
#endif

	err = -ENOMEM;
	all = &ipv4_devconf;
	dflt = &ipv4_devconf_dflt;

	if (!net_eq(net, &init_net)) {
		all = kmemdup(all, sizeof(ipv4_devconf), GFP_KERNEL);
		if (all == NULL)
			goto err_alloc_all;

		dflt = kmemdup(dflt, sizeof(ipv4_devconf_dflt), GFP_KERNEL);
		if (dflt == NULL)
			goto err_alloc_dflt;

#ifdef CONFIG_SYSCTL
		tbl = kmemdup(tbl, sizeof(ctl_forward_entry), GFP_KERNEL);
		if (tbl == NULL)
			goto err_alloc_ctl;

		tbl[0].data = &all->data[NET_IPV4_CONF_FORWARDING - 1];
		tbl[0].extra1 = all;
		tbl[0].extra2 = net;
#endif
	}

#ifdef CONFIG_SYSCTL
	err = __devinet_sysctl_register(net, "all", all);
	if (err < 0)
		goto err_reg_all;

	err = __devinet_sysctl_register(net, "default", dflt);
	if (err < 0)
		goto err_reg_dflt;

	err = -ENOMEM;
	forw_hdr = register_net_sysctl_table(net, net_ipv4_path, tbl);
	if (forw_hdr == NULL)
		goto err_reg_ctl;
	net->ipv4.forw_hdr = forw_hdr;
#endif

	net->ipv4.devconf_all = all;
	net->ipv4.devconf_dflt = dflt;
	return 0;

#ifdef CONFIG_SYSCTL
err_reg_ctl:
	__devinet_sysctl_unregister(dflt);
err_reg_dflt:
	__devinet_sysctl_unregister(all);
err_reg_all:
	if (tbl != ctl_forward_entry)
		kfree(tbl);
err_alloc_ctl:
#endif
	if (dflt != &ipv4_devconf_dflt)
		kfree(dflt);
err_alloc_dflt:
	if (all != &ipv4_devconf)
		kfree(all);
err_alloc_all:
	return err;
}

static __net_exit void devinet_exit_net(struct net *net)
{
#ifdef CONFIG_SYSCTL
	struct ctl_table *tbl;

	tbl = net->ipv4.forw_hdr->ctl_table_arg;
	unregister_net_sysctl_table(net->ipv4.forw_hdr);
	__devinet_sysctl_unregister(net->ipv4.devconf_dflt);
	__devinet_sysctl_unregister(net->ipv4.devconf_all);
	kfree(tbl);
#endif
	kfree(net->ipv4.devconf_dflt);
	kfree(net->ipv4.devconf_all);
}

static __net_initdata struct pernet_operations devinet_ops = {
	.init = devinet_init_net,
	.exit = devinet_exit_net,
};

void __init devinet_init(void)
{
	register_pernet_subsys(&devinet_ops);

	register_gifconf(PF_INET, inet_gifconf);
	register_netdevice_notifier(&ip_netdev_notifier);

	rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL);
	rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL);
	rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr);
}