summaryrefslogtreecommitdiffstats
path: root/sys/netinet/in.c
blob: 15d38b191b5c22fff9df3cc58de26b609bdf1c98 (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
/*-
 * Copyright (c) 1982, 1986, 1991, 1993
 *	The Regents of the University of California.  All rights reserved.
 * Copyright (C) 2001 WIDE Project.  All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 *	@(#)in.c	8.4 (Berkeley) 1/9/95
 */

#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");

#include "opt_carp.h"

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/sockio.h>
#include <sys/malloc.h>
#include <sys/priv.h>
#include <sys/socket.h>
#include <sys/jail.h>
#include <sys/kernel.h>
#include <sys/proc.h>
#include <sys/sysctl.h>
#include <sys/syslog.h>

#include <net/if.h>
#include <net/if_var.h>
#include <net/if_dl.h>
#include <net/if_llatbl.h>
#include <net/if_types.h>
#include <net/route.h>
#include <net/vnet.h>

#include <netinet/in.h>
#include <netinet/in_var.h>
#include <netinet/in_pcb.h>
#include <netinet/ip_var.h>
#include <netinet/igmp_var.h>
#include <netinet/udp.h>
#include <netinet/udp_var.h>

static int in_mask2len(struct in_addr *);
static void in_len2mask(struct in_addr *, int);
static int in_lifaddr_ioctl(struct socket *, u_long, caddr_t,
	struct ifnet *, struct thread *);

static int	in_addprefix(struct in_ifaddr *, int);
static int	in_scrubprefix(struct in_ifaddr *);
static void	in_socktrim(struct sockaddr_in *);
static int	in_ifinit(struct ifnet *,
	    struct in_ifaddr *, struct sockaddr_in *, int);
static void	in_purgemaddrs(struct ifnet *);

static VNET_DEFINE(int, subnetsarelocal);
static VNET_DEFINE(int, sameprefixcarponly);
VNET_DECLARE(struct inpcbinfo, ripcbinfo);

#define	V_subnetsarelocal		VNET(subnetsarelocal)
#define	V_sameprefixcarponly		VNET(sameprefixcarponly)
#define	V_ripcbinfo			VNET(ripcbinfo)

SYSCTL_VNET_INT(_net_inet_ip, OID_AUTO, subnets_are_local, CTLFLAG_RW,
	&VNET_NAME(subnetsarelocal), 0,
	"Treat all subnets as directly connected");
SYSCTL_VNET_INT(_net_inet_ip, OID_AUTO, same_prefix_carp_only, CTLFLAG_RW,
	&VNET_NAME(sameprefixcarponly), 0,
	"Refuse to create same prefixes on different interfaces");

/*
 * Return 1 if an internet address is for a ``local'' host
 * (one to which we have a connection).  If subnetsarelocal
 * is true, this includes other subnets of the local net.
 * Otherwise, it includes only the directly-connected (sub)nets.
 */
int
in_localaddr(struct in_addr in)
{
	register u_long i = ntohl(in.s_addr);
	register struct in_ifaddr *ia;

	IN_IFADDR_RLOCK();
	if (V_subnetsarelocal) {
		TAILQ_FOREACH(ia, &V_in_ifaddrhead, ia_link) {
			if ((i & ia->ia_netmask) == ia->ia_net) {
				IN_IFADDR_RUNLOCK();
				return (1);
			}
		}
	} else {
		TAILQ_FOREACH(ia, &V_in_ifaddrhead, ia_link) {
			if ((i & ia->ia_subnetmask) == ia->ia_subnet) {
				IN_IFADDR_RUNLOCK();
				return (1);
			}
		}
	}
	IN_IFADDR_RUNLOCK();
	return (0);
}

/*
 * Return 1 if an internet address is for the local host and configured
 * on one of its interfaces.
 */
int
in_localip(struct in_addr in)
{
	struct in_ifaddr *ia;

	IN_IFADDR_RLOCK();
	LIST_FOREACH(ia, INADDR_HASH(in.s_addr), ia_hash) {
		if (IA_SIN(ia)->sin_addr.s_addr == in.s_addr) {
			IN_IFADDR_RUNLOCK();
			return (1);
		}
	}
	IN_IFADDR_RUNLOCK();
	return (0);
}

/*
 * Determine whether an IP address is in a reserved set of addresses
 * that may not be forwarded, or whether datagrams to that destination
 * may be forwarded.
 */
int
in_canforward(struct in_addr in)
{
	register u_long i = ntohl(in.s_addr);
	register u_long net;

	if (IN_EXPERIMENTAL(i) || IN_MULTICAST(i) || IN_LINKLOCAL(i))
		return (0);
	if (IN_CLASSA(i)) {
		net = i & IN_CLASSA_NET;
		if (net == 0 || net == (IN_LOOPBACKNET << IN_CLASSA_NSHIFT))
			return (0);
	}
	return (1);
}

/*
 * Trim a mask in a sockaddr
 */
static void
in_socktrim(struct sockaddr_in *ap)
{
    register char *cplim = (char *) &ap->sin_addr;
    register char *cp = (char *) (&ap->sin_addr + 1);

    ap->sin_len = 0;
    while (--cp >= cplim)
	if (*cp) {
	    (ap)->sin_len = cp - (char *) (ap) + 1;
	    break;
	}
}

static int
in_mask2len(mask)
	struct in_addr *mask;
{
	int x, y;
	u_char *p;

	p = (u_char *)mask;
	for (x = 0; x < sizeof(*mask); x++) {
		if (p[x] != 0xff)
			break;
	}
	y = 0;
	if (x < sizeof(*mask)) {
		for (y = 0; y < 8; y++) {
			if ((p[x] & (0x80 >> y)) == 0)
				break;
		}
	}
	return (x * 8 + y);
}

static void
in_len2mask(struct in_addr *mask, int len)
{
	int i;
	u_char *p;

	p = (u_char *)mask;
	bzero(mask, sizeof(*mask));
	for (i = 0; i < len / 8; i++)
		p[i] = 0xff;
	if (len % 8)
		p[i] = (0xff00 >> (len % 8)) & 0xff;
}

/*
 * Generic internet control operations (ioctl's).
 *
 * ifp is NULL if not an interface-specific ioctl.
 */
/* ARGSUSED */
int
in_control(struct socket *so, u_long cmd, caddr_t data, struct ifnet *ifp,
    struct thread *td)
{
	register struct ifreq *ifr = (struct ifreq *)data;
	register struct in_ifaddr *ia, *iap;
	register struct ifaddr *ifa;
	struct in_addr allhosts_addr;
	struct in_addr dst;
	struct in_ifinfo *ii;
	struct in_aliasreq *ifra = (struct in_aliasreq *)data;
	struct sockaddr_in oldaddr;
	int error, hostIsNew, iaIsNew, maskIsNew;
	int iaIsFirst;

	ia = NULL;
	iaIsFirst = 0;
	iaIsNew = 0;
	allhosts_addr.s_addr = htonl(INADDR_ALLHOSTS_GROUP);

	/*
	 * Filter out ioctls we implement directly; forward the rest on to
	 * in_lifaddr_ioctl() and ifp->if_ioctl().
	 */
	switch (cmd) {
	case SIOCAIFADDR:
	case SIOCDIFADDR:
	case SIOCGIFADDR:
	case SIOCGIFBRDADDR:
	case SIOCGIFDSTADDR:
	case SIOCGIFNETMASK:
	case SIOCSIFADDR:
	case SIOCSIFBRDADDR:
	case SIOCSIFDSTADDR:
	case SIOCSIFNETMASK:
		break;

	case SIOCALIFADDR:
		if (td != NULL) {
			error = priv_check(td, PRIV_NET_ADDIFADDR);
			if (error)
				return (error);
		}
		if (ifp == NULL)
			return (EINVAL);
		return in_lifaddr_ioctl(so, cmd, data, ifp, td);

	case SIOCDLIFADDR:
		if (td != NULL) {
			error = priv_check(td, PRIV_NET_DELIFADDR);
			if (error)
				return (error);
		}
		if (ifp == NULL)
			return (EINVAL);
		return in_lifaddr_ioctl(so, cmd, data, ifp, td);

	case SIOCGLIFADDR:
		if (ifp == NULL)
			return (EINVAL);
		return in_lifaddr_ioctl(so, cmd, data, ifp, td);

	default:
		if (ifp == NULL || ifp->if_ioctl == NULL)
			return (EOPNOTSUPP);
		return ((*ifp->if_ioctl)(ifp, cmd, data));
	}

	if (ifp == NULL)
		return (EADDRNOTAVAIL);

	/*
	 * Security checks before we get involved in any work.
	 */
	switch (cmd) {
	case SIOCAIFADDR:
	case SIOCSIFADDR:
	case SIOCSIFBRDADDR:
	case SIOCSIFNETMASK:
	case SIOCSIFDSTADDR:
		if (td != NULL) {
			error = priv_check(td, PRIV_NET_ADDIFADDR);
			if (error)
				return (error);
		}
		break;

	case SIOCDIFADDR:
		if (td != NULL) {
			error = priv_check(td, PRIV_NET_DELIFADDR);
			if (error)
				return (error);
		}
		break;
	}

	/*
	 * Find address for this interface, if it exists.
	 *
	 * If an alias address was specified, find that one instead of the
	 * first one on the interface, if possible.
	 */
	dst = ((struct sockaddr_in *)&ifr->ifr_addr)->sin_addr;
	IN_IFADDR_RLOCK();
	LIST_FOREACH(iap, INADDR_HASH(dst.s_addr), ia_hash) {
		if (iap->ia_ifp == ifp &&
		    iap->ia_addr.sin_addr.s_addr == dst.s_addr) {
			if (td == NULL || prison_check_ip4(td->td_ucred,
			    &dst) == 0)
				ia = iap;
			break;
		}
	}
	if (ia != NULL)
		ifa_ref(&ia->ia_ifa);
	IN_IFADDR_RUNLOCK();
	if (ia == NULL) {
		IF_ADDR_LOCK(ifp);
		TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
			iap = ifatoia(ifa);
			if (iap->ia_addr.sin_family == AF_INET) {
				if (td != NULL &&
				    prison_check_ip4(td->td_ucred,
				    &iap->ia_addr.sin_addr) != 0)
					continue;
				ia = iap;
				break;
			}
		}
		if (ia != NULL)
			ifa_ref(&ia->ia_ifa);
		IF_ADDR_UNLOCK(ifp);
	}
	if (ia == NULL)
		iaIsFirst = 1;

	error = 0;
	switch (cmd) {
	case SIOCAIFADDR:
	case SIOCDIFADDR:
		if (ifra->ifra_addr.sin_family == AF_INET) {
			struct in_ifaddr *oia;

			IN_IFADDR_RLOCK();
			for (oia = ia; ia; ia = TAILQ_NEXT(ia, ia_link)) {
				if (ia->ia_ifp == ifp  &&
				    ia->ia_addr.sin_addr.s_addr ==
				    ifra->ifra_addr.sin_addr.s_addr)
					break;
			}
			if (ia != NULL && ia != oia)
				ifa_ref(&ia->ia_ifa);
			if (oia != NULL && ia != oia)
				ifa_free(&oia->ia_ifa);
			IN_IFADDR_RUNLOCK();
			if ((ifp->if_flags & IFF_POINTOPOINT)
			    && (cmd == SIOCAIFADDR)
			    && (ifra->ifra_dstaddr.sin_addr.s_addr
				== INADDR_ANY)) {
				error = EDESTADDRREQ;
				goto out;
			}
		}
		if (cmd == SIOCDIFADDR && ia == NULL) {
			error = EADDRNOTAVAIL;
			goto out;
		}
		/* FALLTHROUGH */
	case SIOCSIFADDR:
	case SIOCSIFNETMASK:
	case SIOCSIFDSTADDR:
		if (ia == NULL) {
			ia = (struct in_ifaddr *)
				malloc(sizeof *ia, M_IFADDR, M_NOWAIT |
				    M_ZERO);
			if (ia == NULL) {
				error = ENOBUFS;
				goto out;
			}

			ifa = &ia->ia_ifa;
			ifa_init(ifa);
			ifa->ifa_addr = (struct sockaddr *)&ia->ia_addr;
			ifa->ifa_dstaddr = (struct sockaddr *)&ia->ia_dstaddr;
			ifa->ifa_netmask = (struct sockaddr *)&ia->ia_sockmask;

			ia->ia_sockmask.sin_len = 8;
			ia->ia_sockmask.sin_family = AF_INET;
			if (ifp->if_flags & IFF_BROADCAST) {
				ia->ia_broadaddr.sin_len = sizeof(ia->ia_addr);
				ia->ia_broadaddr.sin_family = AF_INET;
			}
			ia->ia_ifp = ifp;

			ifa_ref(ifa);			/* if_addrhead */
			IF_ADDR_LOCK(ifp);
			TAILQ_INSERT_TAIL(&ifp->if_addrhead, ifa, ifa_link);
			IF_ADDR_UNLOCK(ifp);
			ifa_ref(ifa);			/* in_ifaddrhead */
			IN_IFADDR_WLOCK();
			TAILQ_INSERT_TAIL(&V_in_ifaddrhead, ia, ia_link);
			IN_IFADDR_WUNLOCK();
			iaIsNew = 1;
		}
		break;

	case SIOCSIFBRDADDR:
	case SIOCGIFADDR:
	case SIOCGIFNETMASK:
	case SIOCGIFDSTADDR:
	case SIOCGIFBRDADDR:
		if (ia == NULL) {
			error = EADDRNOTAVAIL;
			goto out;
		}
		break;
	}

	/*
	 * Most paths in this switch return directly or via out.  Only paths
	 * that remove the address break in order to hit common removal code.
	 */
	switch (cmd) {
	case SIOCGIFADDR:
		*((struct sockaddr_in *)&ifr->ifr_addr) = ia->ia_addr;
		goto out;

	case SIOCGIFBRDADDR:
		if ((ifp->if_flags & IFF_BROADCAST) == 0) {
			error = EINVAL;
			goto out;
		}
		*((struct sockaddr_in *)&ifr->ifr_dstaddr) = ia->ia_broadaddr;
		goto out;

	case SIOCGIFDSTADDR:
		if ((ifp->if_flags & IFF_POINTOPOINT) == 0) {
			error = EINVAL;
			goto out;
		}
		*((struct sockaddr_in *)&ifr->ifr_dstaddr) = ia->ia_dstaddr;
		goto out;

	case SIOCGIFNETMASK:
		*((struct sockaddr_in *)&ifr->ifr_addr) = ia->ia_sockmask;
		goto out;

	case SIOCSIFDSTADDR:
		if ((ifp->if_flags & IFF_POINTOPOINT) == 0) {
			error = EINVAL;
			goto out;
		}
		oldaddr = ia->ia_dstaddr;
		ia->ia_dstaddr = *(struct sockaddr_in *)&ifr->ifr_dstaddr;
		if (ifp->if_ioctl != NULL) {
			error = (*ifp->if_ioctl)(ifp, SIOCSIFDSTADDR,
			    (caddr_t)ia);
			if (error) {
				ia->ia_dstaddr = oldaddr;
				goto out;
			}
		}
		if (ia->ia_flags & IFA_ROUTE) {
			ia->ia_ifa.ifa_dstaddr = (struct sockaddr *)&oldaddr;
			rtinit(&(ia->ia_ifa), (int)RTM_DELETE, RTF_HOST);
			ia->ia_ifa.ifa_dstaddr =
					(struct sockaddr *)&ia->ia_dstaddr;
			rtinit(&(ia->ia_ifa), (int)RTM_ADD, RTF_HOST|RTF_UP);
		}
		goto out;

	case SIOCSIFBRDADDR:
		if ((ifp->if_flags & IFF_BROADCAST) == 0) {
			error = EINVAL;
			goto out;
		}
		ia->ia_broadaddr = *(struct sockaddr_in *)&ifr->ifr_broadaddr;
		goto out;

	case SIOCSIFADDR:
		error = in_ifinit(ifp, ia,
		    (struct sockaddr_in *) &ifr->ifr_addr, 1);
		if (error != 0 && iaIsNew)
			break;
		if (error == 0) {
			ii = ((struct in_ifinfo *)ifp->if_afdata[AF_INET]);
			if (iaIsFirst &&
			    (ifp->if_flags & IFF_MULTICAST) != 0) {
				error = in_joingroup(ifp, &allhosts_addr,
				    NULL, &ii->ii_allhosts);
			}
			EVENTHANDLER_INVOKE(ifaddr_event, ifp);
		}
		error = 0;
		goto out;

	case SIOCSIFNETMASK:
		ia->ia_sockmask.sin_addr = ifra->ifra_addr.sin_addr;
		ia->ia_subnetmask = ntohl(ia->ia_sockmask.sin_addr.s_addr);
		goto out;

	case SIOCAIFADDR:
		maskIsNew = 0;
		hostIsNew = 1;
		error = 0;
		if (ia->ia_addr.sin_family == AF_INET) {
			if (ifra->ifra_addr.sin_len == 0) {
				ifra->ifra_addr = ia->ia_addr;
				hostIsNew = 0;
			} else if (ifra->ifra_addr.sin_addr.s_addr ==
					       ia->ia_addr.sin_addr.s_addr)
				hostIsNew = 0;
		}
		if (ifra->ifra_mask.sin_len) {
			in_ifscrub(ifp, ia);
			ia->ia_sockmask = ifra->ifra_mask;
			ia->ia_sockmask.sin_family = AF_INET;
			ia->ia_subnetmask =
			     ntohl(ia->ia_sockmask.sin_addr.s_addr);
			maskIsNew = 1;
		}
		if ((ifp->if_flags & IFF_POINTOPOINT) &&
		    (ifra->ifra_dstaddr.sin_family == AF_INET)) {
			in_ifscrub(ifp, ia);
			ia->ia_dstaddr = ifra->ifra_dstaddr;
			maskIsNew  = 1; /* We lie; but the effect's the same */
		}
		if (ifra->ifra_addr.sin_family == AF_INET &&
		    (hostIsNew || maskIsNew))
			error = in_ifinit(ifp, ia, &ifra->ifra_addr, 0);
		if (error != 0 && iaIsNew)
			goto out;

		if ((ifp->if_flags & IFF_BROADCAST) &&
		    (ifra->ifra_broadaddr.sin_family == AF_INET))
			ia->ia_broadaddr = ifra->ifra_broadaddr;
		if (error == 0) {
			ii = ((struct in_ifinfo *)ifp->if_afdata[AF_INET]);
			if (iaIsFirst &&
			    (ifp->if_flags & IFF_MULTICAST) != 0) {
				error = in_joingroup(ifp, &allhosts_addr,
				    NULL, &ii->ii_allhosts);
			}
			EVENTHANDLER_INVOKE(ifaddr_event, ifp);
		}
		goto out;

	case SIOCDIFADDR:
		/*
		 * in_ifscrub kills the interface route.
		 */
		in_ifscrub(ifp, ia);

		/*
		 * in_ifadown gets rid of all the rest of
		 * the routes.  This is not quite the right
		 * thing to do, but at least if we are running
		 * a routing process they will come back.
		 */
		in_ifadown(&ia->ia_ifa, 1);
		EVENTHANDLER_INVOKE(ifaddr_event, ifp);
		error = 0;
		break;

	default:
		panic("in_control: unsupported ioctl");
	}

	IF_ADDR_LOCK(ifp);
	TAILQ_REMOVE(&ifp->if_addrhead, &ia->ia_ifa, ifa_link);
	IF_ADDR_UNLOCK(ifp);
	ifa_free(&ia->ia_ifa);				/* if_addrhead */

	IN_IFADDR_WLOCK();
	TAILQ_REMOVE(&V_in_ifaddrhead, ia, ia_link);
	if (ia->ia_addr.sin_family == AF_INET) {
		struct in_ifaddr *if_ia;

		LIST_REMOVE(ia, ia_hash);
		IN_IFADDR_WUNLOCK();
		/*
		 * If this is the last IPv4 address configured on this
		 * interface, leave the all-hosts group.
		 * No state-change report need be transmitted.
		 */
		if_ia = NULL;
		IFP_TO_IA(ifp, if_ia);
		if (if_ia == NULL) {
			ii = ((struct in_ifinfo *)ifp->if_afdata[AF_INET]);
			IN_MULTI_LOCK();
			if (ii->ii_allhosts) {
				(void)in_leavegroup_locked(ii->ii_allhosts,
				    NULL);
				ii->ii_allhosts = NULL;
			}
			IN_MULTI_UNLOCK();
		} else
			ifa_free(&if_ia->ia_ifa);
	} else
		IN_IFADDR_WUNLOCK();
	ifa_free(&ia->ia_ifa);				/* in_ifaddrhead */
out:
	if (ia != NULL)
		ifa_free(&ia->ia_ifa);
	return (error);
}

/*
 * SIOC[GAD]LIFADDR.
 *	SIOCGLIFADDR: get first address. (?!?)
 *	SIOCGLIFADDR with IFLR_PREFIX:
 *		get first address that matches the specified prefix.
 *	SIOCALIFADDR: add the specified address.
 *	SIOCALIFADDR with IFLR_PREFIX:
 *		EINVAL since we can't deduce hostid part of the address.
 *	SIOCDLIFADDR: delete the specified address.
 *	SIOCDLIFADDR with IFLR_PREFIX:
 *		delete the first address that matches the specified prefix.
 * return values:
 *	EINVAL on invalid parameters
 *	EADDRNOTAVAIL on prefix match failed/specified address not found
 *	other values may be returned from in_ioctl()
 */
static int
in_lifaddr_ioctl(struct socket *so, u_long cmd, caddr_t data,
    struct ifnet *ifp, struct thread *td)
{
	struct if_laddrreq *iflr = (struct if_laddrreq *)data;
	struct ifaddr *ifa;

	/* sanity checks */
	if (data == NULL || ifp == NULL) {
		panic("invalid argument to in_lifaddr_ioctl");
		/*NOTRECHED*/
	}

	switch (cmd) {
	case SIOCGLIFADDR:
		/* address must be specified on GET with IFLR_PREFIX */
		if ((iflr->flags & IFLR_PREFIX) == 0)
			break;
		/*FALLTHROUGH*/
	case SIOCALIFADDR:
	case SIOCDLIFADDR:
		/* address must be specified on ADD and DELETE */
		if (iflr->addr.ss_family != AF_INET)
			return (EINVAL);
		if (iflr->addr.ss_len != sizeof(struct sockaddr_in))
			return (EINVAL);
		/* XXX need improvement */
		if (iflr->dstaddr.ss_family
		 && iflr->dstaddr.ss_family != AF_INET)
			return (EINVAL);
		if (iflr->dstaddr.ss_family
		 && iflr->dstaddr.ss_len != sizeof(struct sockaddr_in))
			return (EINVAL);
		break;
	default: /*shouldn't happen*/
		return (EOPNOTSUPP);
	}
	if (sizeof(struct in_addr) * 8 < iflr->prefixlen)
		return (EINVAL);

	switch (cmd) {
	case SIOCALIFADDR:
	    {
		struct in_aliasreq ifra;

		if (iflr->flags & IFLR_PREFIX)
			return (EINVAL);

		/* copy args to in_aliasreq, perform ioctl(SIOCAIFADDR_IN6). */
		bzero(&ifra, sizeof(ifra));
		bcopy(iflr->iflr_name, ifra.ifra_name,
			sizeof(ifra.ifra_name));

		bcopy(&iflr->addr, &ifra.ifra_addr, iflr->addr.ss_len);

		if (iflr->dstaddr.ss_family) {	/*XXX*/
			bcopy(&iflr->dstaddr, &ifra.ifra_dstaddr,
				iflr->dstaddr.ss_len);
		}

		ifra.ifra_mask.sin_family = AF_INET;
		ifra.ifra_mask.sin_len = sizeof(struct sockaddr_in);
		in_len2mask(&ifra.ifra_mask.sin_addr, iflr->prefixlen);

		return (in_control(so, SIOCAIFADDR, (caddr_t)&ifra, ifp, td));
	    }
	case SIOCGLIFADDR:
	case SIOCDLIFADDR:
	    {
		struct in_ifaddr *ia;
		struct in_addr mask, candidate, match;
		struct sockaddr_in *sin;

		bzero(&mask, sizeof(mask));
		bzero(&match, sizeof(match));
		if (iflr->flags & IFLR_PREFIX) {
			/* lookup a prefix rather than address. */
			in_len2mask(&mask, iflr->prefixlen);

			sin = (struct sockaddr_in *)&iflr->addr;
			match.s_addr = sin->sin_addr.s_addr;
			match.s_addr &= mask.s_addr;

			/* if you set extra bits, that's wrong */
			if (match.s_addr != sin->sin_addr.s_addr)
				return (EINVAL);

		} else {
			/* on getting an address, take the 1st match */
			/* on deleting an address, do exact match */
			if (cmd != SIOCGLIFADDR) {
				in_len2mask(&mask, 32);
				sin = (struct sockaddr_in *)&iflr->addr;
				match.s_addr = sin->sin_addr.s_addr;
			}
		}

		TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link)	{
			if (ifa->ifa_addr->sa_family != AF_INET6)
				continue;
			if (match.s_addr == 0)
				break;
			candidate.s_addr = ((struct sockaddr_in *)&ifa->ifa_addr)->sin_addr.s_addr;
			candidate.s_addr &= mask.s_addr;
			if (candidate.s_addr == match.s_addr)
				break;
		}
		if (ifa == NULL)
			return (EADDRNOTAVAIL);
		ia = (struct in_ifaddr *)ifa;

		if (cmd == SIOCGLIFADDR) {
			/* fill in the if_laddrreq structure */
			bcopy(&ia->ia_addr, &iflr->addr, ia->ia_addr.sin_len);

			if ((ifp->if_flags & IFF_POINTOPOINT) != 0) {
				bcopy(&ia->ia_dstaddr, &iflr->dstaddr,
					ia->ia_dstaddr.sin_len);
			} else
				bzero(&iflr->dstaddr, sizeof(iflr->dstaddr));

			iflr->prefixlen =
				in_mask2len(&ia->ia_sockmask.sin_addr);

			iflr->flags = 0;	/*XXX*/

			return (0);
		} else {
			struct in_aliasreq ifra;

			/* fill in_aliasreq and do ioctl(SIOCDIFADDR_IN6) */
			bzero(&ifra, sizeof(ifra));
			bcopy(iflr->iflr_name, ifra.ifra_name,
				sizeof(ifra.ifra_name));

			bcopy(&ia->ia_addr, &ifra.ifra_addr,
				ia->ia_addr.sin_len);
			if ((ifp->if_flags & IFF_POINTOPOINT) != 0) {
				bcopy(&ia->ia_dstaddr, &ifra.ifra_dstaddr,
					ia->ia_dstaddr.sin_len);
			}
			bcopy(&ia->ia_sockmask, &ifra.ifra_dstaddr,
				ia->ia_sockmask.sin_len);

			return (in_control(so, SIOCDIFADDR, (caddr_t)&ifra,
			    ifp, td));
		}
	    }
	}

	return (EOPNOTSUPP);	/*just for safety*/
}

/*
 * Delete any existing route for an interface.
 */
void
in_ifscrub(struct ifnet *ifp, struct in_ifaddr *ia)
{

	in_scrubprefix(ia);
}

/*
 * Initialize an interface's internet address
 * and routing table entry.
 */
static int
in_ifinit(struct ifnet *ifp, struct in_ifaddr *ia, struct sockaddr_in *sin,
    int scrub)
{
	register u_long i = ntohl(sin->sin_addr.s_addr);
	struct sockaddr_in oldaddr;
	struct rtentry *rt = NULL;
	struct rt_addrinfo info;
	static struct sockaddr_dl null_sdl = {sizeof(null_sdl), AF_LINK};
	int s = splimp(), flags = RTF_UP, error = 0;

	oldaddr = ia->ia_addr;
	if (oldaddr.sin_family == AF_INET)
		LIST_REMOVE(ia, ia_hash);
	ia->ia_addr = *sin;
	if (ia->ia_addr.sin_family == AF_INET) {
		IN_IFADDR_WLOCK();
		LIST_INSERT_HEAD(INADDR_HASH(ia->ia_addr.sin_addr.s_addr),
		    ia, ia_hash);
		IN_IFADDR_WUNLOCK();
	}
	/*
	 * Give the interface a chance to initialize
	 * if this is its first address,
	 * and to validate the address if necessary.
	 */
	if (ifp->if_ioctl != NULL) {
		error = (*ifp->if_ioctl)(ifp, SIOCSIFADDR, (caddr_t)ia);
		if (error) {
			splx(s);
			/* LIST_REMOVE(ia, ia_hash) is done in in_control */
			ia->ia_addr = oldaddr;
			IN_IFADDR_WLOCK();
			if (ia->ia_addr.sin_family == AF_INET)
				LIST_INSERT_HEAD(INADDR_HASH(
				    ia->ia_addr.sin_addr.s_addr), ia, ia_hash);
			else 
				/* 
				 * If oldaddr family is not AF_INET (e.g. 
				 * interface has been just created) in_control 
				 * does not call LIST_REMOVE, and we end up 
				 * with bogus ia entries in hash
				 */
				LIST_REMOVE(ia, ia_hash);
			IN_IFADDR_WUNLOCK();
			return (error);
		}
	}
	splx(s);
	if (scrub) {
		ia->ia_ifa.ifa_addr = (struct sockaddr *)&oldaddr;
		in_ifscrub(ifp, ia);
		ia->ia_ifa.ifa_addr = (struct sockaddr *)&ia->ia_addr;
	}
	if (IN_CLASSA(i))
		ia->ia_netmask = IN_CLASSA_NET;
	else if (IN_CLASSB(i))
		ia->ia_netmask = IN_CLASSB_NET;
	else
		ia->ia_netmask = IN_CLASSC_NET;
	/*
	 * The subnet mask usually includes at least the standard network part,
	 * but may may be smaller in the case of supernetting.
	 * If it is set, we believe it.
	 */
	if (ia->ia_subnetmask == 0) {
		ia->ia_subnetmask = ia->ia_netmask;
		ia->ia_sockmask.sin_addr.s_addr = htonl(ia->ia_subnetmask);
	} else
		ia->ia_netmask &= ia->ia_subnetmask;
	ia->ia_net = i & ia->ia_netmask;
	ia->ia_subnet = i & ia->ia_subnetmask;
	in_socktrim(&ia->ia_sockmask);
#ifdef DEV_CARP
	/*
	 * XXX: carp(4) does not have interface route
	 */
	if (ifp->if_type == IFT_CARP)
		return (0);
#endif
	/*
	 * Add route for the network.
	 */
	ia->ia_ifa.ifa_metric = ifp->if_metric;
	if (ifp->if_flags & IFF_BROADCAST) {
		ia->ia_broadaddr.sin_addr.s_addr =
			htonl(ia->ia_subnet | ~ia->ia_subnetmask);
		ia->ia_netbroadcast.s_addr =
			htonl(ia->ia_net | ~ ia->ia_netmask);
	} else if (ifp->if_flags & IFF_LOOPBACK) {
		ia->ia_dstaddr = ia->ia_addr;
		flags |= RTF_HOST;
	} else if (ifp->if_flags & IFF_POINTOPOINT) {
		if (ia->ia_dstaddr.sin_family != AF_INET)
			return (0);
		flags |= RTF_HOST;
	}
	if ((error = in_addprefix(ia, flags)) != 0)
		return (error);

	if (ia->ia_addr.sin_addr.s_addr == INADDR_ANY)
		return (0);

	/*
	 * add a loopback route to self
	 */
	if (V_useloopback && !(ifp->if_flags & IFF_LOOPBACK)) {
		bzero(&info, sizeof(info));
		info.rti_ifp = V_loif;
		info.rti_flags = ia->ia_flags | RTF_HOST | RTF_STATIC;
		info.rti_info[RTAX_DST] = (struct sockaddr *)&ia->ia_addr;
		info.rti_info[RTAX_GATEWAY] = (struct sockaddr *)&null_sdl;
		error = rtrequest1_fib(RTM_ADD, &info, &rt, 0);

		if (error == 0 && rt != NULL) {
			RT_LOCK(rt);
			((struct sockaddr_dl *)rt->rt_gateway)->sdl_type  =
				rt->rt_ifp->if_type;
			((struct sockaddr_dl *)rt->rt_gateway)->sdl_index =
				rt->rt_ifp->if_index;
			RT_REMREF(rt);
			RT_UNLOCK(rt);
		} else if (error != 0)
			log(LOG_INFO, "in_ifinit: insertion failed\n");
	}

	return (error);
}

#define rtinitflags(x) \
	((((x)->ia_ifp->if_flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) != 0) \
	    ? RTF_HOST : 0)
/*
 * Check if we have a route for the given prefix already or add one accordingly.
 */
static int
in_addprefix(struct in_ifaddr *target, int flags)
{
	struct in_ifaddr *ia;
	struct in_addr prefix, mask, p, m;
	int error;

	if ((flags & RTF_HOST) != 0) {
		prefix = target->ia_dstaddr.sin_addr;
		mask.s_addr = 0;
	} else {
		prefix = target->ia_addr.sin_addr;
		mask = target->ia_sockmask.sin_addr;
		prefix.s_addr &= mask.s_addr;
	}

	IN_IFADDR_RLOCK();
	TAILQ_FOREACH(ia, &V_in_ifaddrhead, ia_link) {
		if (rtinitflags(ia)) {
			p = ia->ia_addr.sin_addr;

			if (prefix.s_addr != p.s_addr)
				continue;
		} else {
			p = ia->ia_addr.sin_addr;
			m = ia->ia_sockmask.sin_addr;
			p.s_addr &= m.s_addr;

			if (prefix.s_addr != p.s_addr ||
			    mask.s_addr != m.s_addr)
				continue;
		}

		/*
		 * If we got a matching prefix route inserted by other
		 * interface address, we are done here.
		 */
		if (ia->ia_flags & IFA_ROUTE) {
			if (V_sameprefixcarponly &&
			    target->ia_ifp->if_type != IFT_CARP &&
			    ia->ia_ifp->if_type != IFT_CARP) {
				IN_IFADDR_RUNLOCK();
				return (EEXIST);
			} else {
				IN_IFADDR_RUNLOCK();
				return (0);
			}
		}
	}
	IN_IFADDR_RUNLOCK();

	/*
	 * No-one seem to have this prefix route, so we try to insert it.
	 */
	error = rtinit(&target->ia_ifa, (int)RTM_ADD, flags);
	if (!error)
		target->ia_flags |= IFA_ROUTE;
	return (error);
}

extern void arp_ifscrub(struct ifnet *ifp, uint32_t addr);

/*
 * If there is no other address in the system that can serve a route to the
 * same prefix, remove the route.  Hand over the route to the new address
 * otherwise.
 */
static int
in_scrubprefix(struct in_ifaddr *target)
{
	struct in_ifaddr *ia;
	struct in_addr prefix, mask, p;
	int error;
	struct sockaddr_in prefix0, mask0;
	struct rt_addrinfo info;
	struct sockaddr_dl null_sdl;

	if ((target->ia_flags & IFA_ROUTE) == 0)
		return (0);

	/*
	 * Remove the loopback route to the interface address.
	 * The "useloopback" setting is not consulted because if the
	 * user configures an interface address, turns off this
	 * setting, and then tries to delete that interface address,
	 * checking the current setting of "useloopback" would leave
	 * that interface address loopback route untouched, which
	 * would be wrong. Therefore the interface address loopback route
	 * deletion is unconditional.
	 */
	if ((target->ia_addr.sin_addr.s_addr != INADDR_ANY) &&
	    !(target->ia_ifp->if_flags & IFF_LOOPBACK)) {
		bzero(&null_sdl, sizeof(null_sdl));
		null_sdl.sdl_len = sizeof(null_sdl);
		null_sdl.sdl_family = AF_LINK;
		null_sdl.sdl_type = V_loif->if_type;
		null_sdl.sdl_index = V_loif->if_index;
		bzero(&info, sizeof(info));
		info.rti_flags = target->ia_flags | RTF_HOST | RTF_STATIC;
		info.rti_info[RTAX_DST] = (struct sockaddr *)&target->ia_addr;
		info.rti_info[RTAX_GATEWAY] = (struct sockaddr *)&null_sdl;
		error = rtrequest1_fib(RTM_DELETE, &info, NULL, 0);

		if (error != 0)
			log(LOG_INFO, "in_scrubprefix: deletion failed\n");
	}

	if (rtinitflags(target))
		prefix = target->ia_dstaddr.sin_addr;
	else {
		prefix = target->ia_addr.sin_addr;
		mask = target->ia_sockmask.sin_addr;
		prefix.s_addr &= mask.s_addr;
		/* remove arp cache */
		arp_ifscrub(target->ia_ifp, IA_SIN(target)->sin_addr.s_addr);
	}

	IN_IFADDR_RLOCK();
	TAILQ_FOREACH(ia, &V_in_ifaddrhead, ia_link) {
		if (rtinitflags(ia))
			p = ia->ia_dstaddr.sin_addr;
		else {
			p = ia->ia_addr.sin_addr;
			p.s_addr &= ia->ia_sockmask.sin_addr.s_addr;
		}

		if (prefix.s_addr != p.s_addr)
			continue;

		/*
		 * If we got a matching prefix address, move IFA_ROUTE and
		 * the route itself to it.  Make sure that routing daemons
		 * get a heads-up.
		 *
		 * XXX: a special case for carp(4) interface
		 */
		if ((ia->ia_flags & IFA_ROUTE) == 0
#ifdef DEV_CARP
		    && (ia->ia_ifp->if_type != IFT_CARP)
#endif
							) {
			IN_IFADDR_RUNLOCK();
			rtinit(&(target->ia_ifa), (int)RTM_DELETE,
			    rtinitflags(target));
			target->ia_flags &= ~IFA_ROUTE;

			error = rtinit(&ia->ia_ifa, (int)RTM_ADD,
			    rtinitflags(ia) | RTF_UP);
			if (error == 0)
				ia->ia_flags |= IFA_ROUTE;
			return (error);
		}
	}
	IN_IFADDR_RUNLOCK();

	/*
	 * remove all L2 entries on the given prefix
	 */
	bzero(&prefix0, sizeof(prefix0));
	prefix0.sin_len = sizeof(prefix0);
	prefix0.sin_family = AF_INET;
	prefix0.sin_addr.s_addr = target->ia_subnet;
	bzero(&mask0, sizeof(mask0));
	mask0.sin_len = sizeof(mask0);
	mask0.sin_family = AF_INET;
	mask0.sin_addr.s_addr = target->ia_subnetmask;
	lltable_prefix_free(AF_INET, (struct sockaddr *)&prefix0, 
			    (struct sockaddr *)&mask0);

	/*
	 * As no-one seem to have this prefix, we can remove the route.
	 */
	rtinit(&(target->ia_ifa), (int)RTM_DELETE, rtinitflags(target));
	target->ia_flags &= ~IFA_ROUTE;
	return (0);
}

#undef rtinitflags

/*
 * Return 1 if the address might be a local broadcast address.
 */
int
in_broadcast(struct in_addr in, struct ifnet *ifp)
{
	register struct ifaddr *ifa;
	u_long t;

	if (in.s_addr == INADDR_BROADCAST ||
	    in.s_addr == INADDR_ANY)
		return (1);
	if ((ifp->if_flags & IFF_BROADCAST) == 0)
		return (0);
	t = ntohl(in.s_addr);
	/*
	 * Look through the list of addresses for a match
	 * with a broadcast address.
	 */
#define ia ((struct in_ifaddr *)ifa)
	TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link)
		if (ifa->ifa_addr->sa_family == AF_INET &&
		    (in.s_addr == ia->ia_broadaddr.sin_addr.s_addr ||
		     in.s_addr == ia->ia_netbroadcast.s_addr ||
		     /*
		      * Check for old-style (host 0) broadcast.
		      */
		     t == ia->ia_subnet || t == ia->ia_net) &&
		     /*
		      * Check for an all one subnetmask. These
		      * only exist when an interface gets a secondary
		      * address.
		      */
		     ia->ia_subnetmask != (u_long)0xffffffff)
			    return (1);
	return (0);
#undef ia
}

/*
 * On interface removal, clean up IPv4 data structures hung off of the ifnet.
 */
void
in_ifdetach(struct ifnet *ifp)
{

	in_pcbpurgeif0(&V_ripcbinfo, ifp);
	in_pcbpurgeif0(&V_udbinfo, ifp);
	in_purgemaddrs(ifp);
}

/*
 * Delete all IPv4 multicast address records, and associated link-layer
 * multicast address records, associated with ifp.
 * XXX It looks like domifdetach runs AFTER the link layer cleanup.
 * XXX This should not race with ifma_protospec being set during
 * a new allocation, if it does, we have bigger problems.
 */
static void
in_purgemaddrs(struct ifnet *ifp)
{
	LIST_HEAD(,in_multi) purgeinms;
	struct in_multi		*inm, *tinm;
	struct ifmultiaddr	*ifma;

	LIST_INIT(&purgeinms);
	IN_MULTI_LOCK();

	/*
	 * Extract list of in_multi associated with the detaching ifp
	 * which the PF_INET layer is about to release.
	 * We need to do this as IF_ADDR_LOCK() may be re-acquired
	 * by code further down.
	 */
	IF_ADDR_LOCK(ifp);
	TAILQ_FOREACH(ifma, &ifp->if_multiaddrs, ifma_link) {
		if (ifma->ifma_addr->sa_family != AF_INET ||
		    ifma->ifma_protospec == NULL)
			continue;
#if 0
		KASSERT(ifma->ifma_protospec != NULL,
		    ("%s: ifma_protospec is NULL", __func__));
#endif
		inm = (struct in_multi *)ifma->ifma_protospec;
		LIST_INSERT_HEAD(&purgeinms, inm, inm_link);
	}
	IF_ADDR_UNLOCK(ifp);

	LIST_FOREACH_SAFE(inm, &purgeinms, inm_link, tinm) {
		LIST_REMOVE(inm, inm_link);
		inm_release_locked(inm);
	}
	igmp_ifdetach(ifp);

	IN_MULTI_UNLOCK();
}

#include <net/if_dl.h>
#include <netinet/if_ether.h>

struct in_llentry {
	struct llentry		base;
	struct sockaddr_in	l3_addr4;
};

static struct llentry *
in_lltable_new(const struct sockaddr *l3addr, u_int flags)
{
	struct in_llentry *lle;

	lle = malloc(sizeof(struct in_llentry), M_LLTABLE, M_DONTWAIT | M_ZERO);
	if (lle == NULL)		/* NB: caller generates msg */
		return NULL;

	callout_init(&lle->base.la_timer, CALLOUT_MPSAFE);
	/*
	 * For IPv4 this will trigger "arpresolve" to generate
	 * an ARP request.
	 */
	lle->base.la_expire = time_second; /* mark expired */
	lle->l3_addr4 = *(const struct sockaddr_in *)l3addr;
	lle->base.lle_refcnt = 1;
	LLE_LOCK_INIT(&lle->base);
	return &lle->base;
}

/*
 * Deletes an address from the address table.
 * This function is called by the timer functions
 * such as arptimer() and nd6_llinfo_timer(), and
 * the caller does the locking.
 */
static void
in_lltable_free(struct lltable *llt, struct llentry *lle)
{
	LLE_WUNLOCK(lle);
	LLE_LOCK_DESTROY(lle);
	free(lle, M_LLTABLE);
}


#define IN_ARE_MASKED_ADDR_EQUAL(d, a, m)	(			\
	    (((ntohl((d)->sin_addr.s_addr) ^ (a)->sin_addr.s_addr) & (m)->sin_addr.s_addr)) == 0 )

static void
in_lltable_prefix_free(struct lltable *llt, 
		       const struct sockaddr *prefix,
		       const struct sockaddr *mask)
{
	const struct sockaddr_in *pfx = (const struct sockaddr_in *)prefix;
	const struct sockaddr_in *msk = (const struct sockaddr_in *)mask;
	struct llentry *lle, *next;
	register int i;

	for (i=0; i < LLTBL_HASHTBL_SIZE; i++) {
		LIST_FOREACH_SAFE(lle, &llt->lle_head[i], lle_next, next) {

			if (IN_ARE_MASKED_ADDR_EQUAL((struct sockaddr_in *)L3_ADDR(lle), 
						     pfx, msk)) {
				callout_drain(&lle->la_timer);
				LLE_WLOCK(lle);
				llentry_free(lle);
			}
		}
	}
}


static int
in_lltable_rtcheck(struct ifnet *ifp, const struct sockaddr *l3addr)
{
	struct rtentry *rt;

	KASSERT(l3addr->sa_family == AF_INET,
	    ("sin_family %d", l3addr->sa_family));

	/* XXX rtalloc1 should take a const param */
	rt = rtalloc1(__DECONST(struct sockaddr *, l3addr), 0, 0);
	if (rt == NULL || (rt->rt_flags & RTF_GATEWAY) || rt->rt_ifp != ifp) {
		log(LOG_INFO, "IPv4 address: \"%s\" is not on the network\n",
		    inet_ntoa(((const struct sockaddr_in *)l3addr)->sin_addr));
		if (rt != NULL)
			RTFREE_LOCKED(rt);
		return (EINVAL);
	}
	RTFREE_LOCKED(rt);
	return 0;
}

/*
 * Return NULL if not found or marked for deletion.
 * If found return lle read locked.
 */
static struct llentry *
in_lltable_lookup(struct lltable *llt, u_int flags, const struct sockaddr *l3addr)
{
	const struct sockaddr_in *sin = (const struct sockaddr_in *)l3addr;
	struct ifnet *ifp = llt->llt_ifp;
	struct llentry *lle;
	struct llentries *lleh;
	u_int hashkey;

	IF_AFDATA_LOCK_ASSERT(ifp);
	KASSERT(l3addr->sa_family == AF_INET,
	    ("sin_family %d", l3addr->sa_family));

	hashkey = sin->sin_addr.s_addr;
	lleh = &llt->lle_head[LLATBL_HASH(hashkey, LLTBL_HASHMASK)];
	LIST_FOREACH(lle, lleh, lle_next) {
		struct sockaddr_in *sa2 = (struct sockaddr_in *)L3_ADDR(lle);
		if (lle->la_flags & LLE_DELETED)
			continue;
		if (sa2->sin_addr.s_addr == sin->sin_addr.s_addr)
			break;
	}
	if (lle == NULL) {
#ifdef DIAGNOSTICS
		if (flags & LLE_DELETE)
			log(LOG_INFO, "interface address is missing from cache = %p  in delete\n", lle);	
#endif
		if (!(flags & LLE_CREATE))
			return (NULL);
		/*
		 * A route that covers the given address must have
		 * been installed 1st because we are doing a resolution,
		 * verify this.
		 */
		if (!(flags & LLE_IFADDR) &&
		    in_lltable_rtcheck(ifp, l3addr) != 0)
			goto done;

		lle = in_lltable_new(l3addr, flags);
		if (lle == NULL) {
			log(LOG_INFO, "lla_lookup: new lle malloc failed\n");
			goto done;
		}
		lle->la_flags = flags & ~LLE_CREATE;
		if ((flags & (LLE_CREATE | LLE_IFADDR)) == (LLE_CREATE | LLE_IFADDR)) {
			bcopy(IF_LLADDR(ifp), &lle->ll_addr, ifp->if_addrlen);
			lle->la_flags |= (LLE_VALID | LLE_STATIC);
		}

		lle->lle_tbl  = llt;
		lle->lle_head = lleh;
		LIST_INSERT_HEAD(lleh, lle, lle_next);
	} else if (flags & LLE_DELETE) {
		if (!(lle->la_flags & LLE_IFADDR) || (flags & LLE_IFADDR)) {
			LLE_WLOCK(lle);
			lle->la_flags = LLE_DELETED;
			LLE_WUNLOCK(lle);
#ifdef DIAGNOSTICS
			log(LOG_INFO, "ifaddr cache = %p  is deleted\n", lle);	
#endif
		}
		lle = (void *)-1;
		
	}
	if (LLE_IS_VALID(lle)) {
		if (flags & LLE_EXCLUSIVE)
			LLE_WLOCK(lle);
		else
			LLE_RLOCK(lle);
	}
done:
	return (lle);
}

static int
in_lltable_dump(struct lltable *llt, struct sysctl_req *wr)
{
#define	SIN(lle)	((struct sockaddr_in *) L3_ADDR(lle))
	struct ifnet *ifp = llt->llt_ifp;
	struct llentry *lle;
	/* XXX stack use */
	struct {
		struct rt_msghdr	rtm;
		struct sockaddr_inarp	sin;
		struct sockaddr_dl	sdl;
	} arpc;
	int error, i;

	/* XXXXX
	 * current IFNET_RLOCK() is mapped to IFNET_WLOCK()
	 * so it is okay to use this ASSERT, change it when
	 * IFNET lock is finalized
	 */
	IFNET_WLOCK_ASSERT();

	error = 0;
	for (i = 0; i < LLTBL_HASHTBL_SIZE; i++) {
		LIST_FOREACH(lle, &llt->lle_head[i], lle_next) {
			struct sockaddr_dl *sdl;
			
			/* skip deleted entries */
			if ((lle->la_flags & (LLE_DELETED|LLE_VALID)) != LLE_VALID)
				continue;
			/* Skip if jailed and not a valid IP of the prison. */
			if (prison_if(wr->td->td_ucred, L3_ADDR(lle)) != 0)
				continue;
			/*
			 * produce a msg made of:
			 *  struct rt_msghdr;
			 *  struct sockaddr_inarp; (IPv4)
			 *  struct sockaddr_dl;
			 */
			bzero(&arpc, sizeof(arpc));
			arpc.rtm.rtm_msglen = sizeof(arpc);
			arpc.rtm.rtm_version = RTM_VERSION;
			arpc.rtm.rtm_type = RTM_GET;
			arpc.rtm.rtm_flags = RTF_UP;
			arpc.rtm.rtm_addrs = RTA_DST | RTA_GATEWAY;
			arpc.sin.sin_family = AF_INET;
			arpc.sin.sin_len = sizeof(arpc.sin);
			arpc.sin.sin_addr.s_addr = SIN(lle)->sin_addr.s_addr;

			/* publish */
			if (lle->la_flags & LLE_PUB) {
				arpc.rtm.rtm_flags |= RTF_ANNOUNCE;
				/* proxy only */
				if (lle->la_flags & LLE_PROXY)
					arpc.sin.sin_other = SIN_PROXY;
			}

			sdl = &arpc.sdl;
			sdl->sdl_family = AF_LINK;
			sdl->sdl_len = sizeof(*sdl);
			sdl->sdl_alen = ifp->if_addrlen;
			sdl->sdl_index = ifp->if_index;
			sdl->sdl_type = ifp->if_type;
			bcopy(&lle->ll_addr, LLADDR(sdl), ifp->if_addrlen);

			arpc.rtm.rtm_rmx.rmx_expire =
			    lle->la_flags & LLE_STATIC ? 0 : lle->la_expire;
			arpc.rtm.rtm_flags |= (RTF_HOST | RTF_LLDATA);
			if (lle->la_flags & LLE_STATIC)
				arpc.rtm.rtm_flags |= RTF_STATIC;
			arpc.rtm.rtm_index = ifp->if_index;
			error = SYSCTL_OUT(wr, &arpc, sizeof(arpc));
			if (error)
				break;
		}
	}
	return error;
#undef SIN
}

void *
in_domifattach(struct ifnet *ifp)
{
	struct in_ifinfo *ii;
	struct lltable *llt;

	ii = malloc(sizeof(struct in_ifinfo), M_IFADDR, M_WAITOK|M_ZERO);

	llt = lltable_init(ifp, AF_INET);
	if (llt != NULL) {
		llt->llt_new = in_lltable_new;
		llt->llt_free = in_lltable_free;
		llt->llt_prefix_free = in_lltable_prefix_free;
		llt->llt_rtcheck = in_lltable_rtcheck;
		llt->llt_lookup = in_lltable_lookup;
		llt->llt_dump = in_lltable_dump;
	}
	ii->ii_llt = llt;

	ii->ii_igmp = igmp_domifattach(ifp);

	return ii;
}

void
in_domifdetach(struct ifnet *ifp, void *aux)
{
	struct in_ifinfo *ii = (struct in_ifinfo *)aux;

	igmp_domifdetach(ifp);
	lltable_free(ii->ii_llt);
	free(ii, M_IFADDR);
}
OpenPOWER on IntegriCloud