summaryrefslogtreecommitdiffstats
path: root/sys/net/rtsock.c
blob: de6548228eaa784b8061a2fdd71eb9e47b437246 (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
/*-
 * Copyright (c) 1988, 1991, 1993
 *	The Regents of the University of California.  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.
 *
 *	@(#)rtsock.c	8.7 (Berkeley) 10/12/95
 * $FreeBSD$
 */
#include "opt_compat.h"
#include "opt_sctp.h"
#include "opt_mpath.h"
#include "opt_inet.h"
#include "opt_inet6.h"

#include <sys/param.h>
#include <sys/jail.h>
#include <sys/kernel.h>
#include <sys/domain.h>
#include <sys/lock.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/priv.h>
#include <sys/proc.h>
#include <sys/protosw.h>
#include <sys/rwlock.h>
#include <sys/signalvar.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/sysctl.h>
#include <sys/systm.h>

#include <net/if.h>
#include <net/if_dl.h>
#include <net/if_llatbl.h>
#include <net/netisr.h>
#include <net/raw_cb.h>
#include <net/route.h>
#include <net/vnet.h>

#include <netinet/in.h>
#include <netinet/if_ether.h>
#ifdef INET6
#include <netinet6/scope6_var.h>
#endif

#if defined(INET) || defined(INET6)
#ifdef SCTP
extern void sctp_addr_change(struct ifaddr *ifa, int cmd);
#endif /* SCTP */
#endif

#ifdef COMPAT_FREEBSD32
#include <sys/mount.h>
#include <compat/freebsd32/freebsd32.h>

struct if_data32 {
	uint8_t	ifi_type;
	uint8_t	ifi_physical;
	uint8_t	ifi_addrlen;
	uint8_t	ifi_hdrlen;
	uint8_t	ifi_link_state;
	uint8_t	ifi_spare_char1;
	uint8_t	ifi_spare_char2;
	uint8_t	ifi_datalen;
	uint32_t ifi_mtu;
	uint32_t ifi_metric;
	uint32_t ifi_baudrate;
	uint32_t ifi_ipackets;
	uint32_t ifi_ierrors;
	uint32_t ifi_opackets;
	uint32_t ifi_oerrors;
	uint32_t ifi_collisions;
	uint32_t ifi_ibytes;
	uint32_t ifi_obytes;
	uint32_t ifi_imcasts;
	uint32_t ifi_omcasts;
	uint32_t ifi_iqdrops;
	uint32_t ifi_noproto;
	uint32_t ifi_hwassist;
	int32_t	ifi_epoch;
	struct	timeval32 ifi_lastchange;
};

struct if_msghdr32 {
	uint16_t ifm_msglen;
	uint8_t	ifm_version;
	uint8_t	ifm_type;
	int32_t	ifm_addrs;
	int32_t	ifm_flags;
	uint16_t ifm_index;
	struct	if_data32 ifm_data;
};
#endif

MALLOC_DEFINE(M_RTABLE, "routetbl", "routing tables");

/* NB: these are not modified */
static struct	sockaddr route_src = { 2, PF_ROUTE, };
static struct	sockaddr sa_zero   = { sizeof(sa_zero), AF_INET, };

static struct {
	int	ip_count;	/* attached w/ AF_INET */
	int	ip6_count;	/* attached w/ AF_INET6 */
	int	ipx_count;	/* attached w/ AF_IPX */
	int	any_count;	/* total attached */
} route_cb;

struct mtx rtsock_mtx;
MTX_SYSINIT(rtsock, &rtsock_mtx, "rtsock route_cb lock", MTX_DEF);

#define	RTSOCK_LOCK()	mtx_lock(&rtsock_mtx)
#define	RTSOCK_UNLOCK()	mtx_unlock(&rtsock_mtx)
#define	RTSOCK_LOCK_ASSERT()	mtx_assert(&rtsock_mtx, MA_OWNED)

SYSCTL_NODE(_net, OID_AUTO, route, CTLFLAG_RD, 0, "");

struct walkarg {
	int	w_tmemsize;
	int	w_op, w_arg;
	caddr_t	w_tmem;
	struct sysctl_req *w_req;
};

static void	rts_input(struct mbuf *m);
static struct mbuf *rt_msg1(int type, struct rt_addrinfo *rtinfo);
static int	rt_msg2(int type, struct rt_addrinfo *rtinfo,
			caddr_t cp, struct walkarg *w);
static int	rt_xaddrs(caddr_t cp, caddr_t cplim,
			struct rt_addrinfo *rtinfo);
static int	sysctl_dumpentry(struct radix_node *rn, void *vw);
static int	sysctl_iflist(int af, struct walkarg *w);
static int	sysctl_ifmalist(int af, struct walkarg *w);
static int	route_output(struct mbuf *m, struct socket *so);
static void	rt_setmetrics(u_long which, const struct rt_metrics *in,
			struct rt_metrics_lite *out);
static void	rt_getmetrics(const struct rt_metrics_lite *in,
			struct rt_metrics *out);
static void	rt_dispatch(struct mbuf *, const struct sockaddr *);

static struct netisr_handler rtsock_nh = {
	.nh_name = "rtsock",
	.nh_handler = rts_input,
	.nh_proto = NETISR_ROUTE,
	.nh_policy = NETISR_POLICY_SOURCE,
};

static int
sysctl_route_netisr_maxqlen(SYSCTL_HANDLER_ARGS)
{
	int error, qlimit;

	netisr_getqlimit(&rtsock_nh, &qlimit);
	error = sysctl_handle_int(oidp, &qlimit, 0, req);
        if (error || !req->newptr)
                return (error);
	if (qlimit < 1)
		return (EINVAL);
	return (netisr_setqlimit(&rtsock_nh, qlimit));
}
SYSCTL_PROC(_net_route, OID_AUTO, netisr_maxqlen, CTLTYPE_INT|CTLFLAG_RW,
    0, 0, sysctl_route_netisr_maxqlen, "I",
    "maximum routing socket dispatch queue length");

static void
rts_init(void)
{
	int tmp;

	if (TUNABLE_INT_FETCH("net.route.netisr_maxqlen", &tmp))
		rtsock_nh.nh_qlimit = tmp;
	netisr_register(&rtsock_nh);
}
SYSINIT(rtsock, SI_SUB_PROTO_DOMAIN, SI_ORDER_THIRD, rts_init, 0);

static void
rts_input(struct mbuf *m)
{
	struct sockproto route_proto;
	unsigned short *family;
	struct m_tag *tag;

	route_proto.sp_family = PF_ROUTE;
	tag = m_tag_find(m, PACKET_TAG_RTSOCKFAM, NULL);
	if (tag != NULL) {
		family = (unsigned short *)(tag + 1);
		route_proto.sp_protocol = *family;
		m_tag_delete(m, tag);
	} else
		route_proto.sp_protocol = 0;

	raw_input(m, &route_proto, &route_src);
}

/*
 * It really doesn't make any sense at all for this code to share much
 * with raw_usrreq.c, since its functionality is so restricted.  XXX
 */
static void
rts_abort(struct socket *so)
{

	raw_usrreqs.pru_abort(so);
}

static void
rts_close(struct socket *so)
{

	raw_usrreqs.pru_close(so);
}

/* pru_accept is EOPNOTSUPP */

static int
rts_attach(struct socket *so, int proto, struct thread *td)
{
	struct rawcb *rp;
	int s, error;

	KASSERT(so->so_pcb == NULL, ("rts_attach: so_pcb != NULL"));

	/* XXX */
	rp = malloc(sizeof *rp, M_PCB, M_WAITOK | M_ZERO);
	if (rp == NULL)
		return ENOBUFS;

	/*
	 * The splnet() is necessary to block protocols from sending
	 * error notifications (like RTM_REDIRECT or RTM_LOSING) while
	 * this PCB is extant but incompletely initialized.
	 * Probably we should try to do more of this work beforehand and
	 * eliminate the spl.
	 */
	s = splnet();
	so->so_pcb = (caddr_t)rp;
	so->so_fibnum = td->td_proc->p_fibnum;
	error = raw_attach(so, proto);
	rp = sotorawcb(so);
	if (error) {
		splx(s);
		so->so_pcb = NULL;
		free(rp, M_PCB);
		return error;
	}
	RTSOCK_LOCK();
	switch(rp->rcb_proto.sp_protocol) {
	case AF_INET:
		route_cb.ip_count++;
		break;
	case AF_INET6:
		route_cb.ip6_count++;
		break;
	case AF_IPX:
		route_cb.ipx_count++;
		break;
	}
	route_cb.any_count++;
	RTSOCK_UNLOCK();
	soisconnected(so);
	so->so_options |= SO_USELOOPBACK;
	splx(s);
	return 0;
}

static int
rts_bind(struct socket *so, struct sockaddr *nam, struct thread *td)
{

	return (raw_usrreqs.pru_bind(so, nam, td)); /* xxx just EINVAL */
}

static int
rts_connect(struct socket *so, struct sockaddr *nam, struct thread *td)
{

	return (raw_usrreqs.pru_connect(so, nam, td)); /* XXX just EINVAL */
}

/* pru_connect2 is EOPNOTSUPP */
/* pru_control is EOPNOTSUPP */

static void
rts_detach(struct socket *so)
{
	struct rawcb *rp = sotorawcb(so);

	KASSERT(rp != NULL, ("rts_detach: rp == NULL"));

	RTSOCK_LOCK();
	switch(rp->rcb_proto.sp_protocol) {
	case AF_INET:
		route_cb.ip_count--;
		break;
	case AF_INET6:
		route_cb.ip6_count--;
		break;
	case AF_IPX:
		route_cb.ipx_count--;
		break;
	}
	route_cb.any_count--;
	RTSOCK_UNLOCK();
	raw_usrreqs.pru_detach(so);
}

static int
rts_disconnect(struct socket *so)
{

	return (raw_usrreqs.pru_disconnect(so));
}

/* pru_listen is EOPNOTSUPP */

static int
rts_peeraddr(struct socket *so, struct sockaddr **nam)
{

	return (raw_usrreqs.pru_peeraddr(so, nam));
}

/* pru_rcvd is EOPNOTSUPP */
/* pru_rcvoob is EOPNOTSUPP */

static int
rts_send(struct socket *so, int flags, struct mbuf *m, struct sockaddr *nam,
	 struct mbuf *control, struct thread *td)
{

	return (raw_usrreqs.pru_send(so, flags, m, nam, control, td));
}

/* pru_sense is null */

static int
rts_shutdown(struct socket *so)
{

	return (raw_usrreqs.pru_shutdown(so));
}

static int
rts_sockaddr(struct socket *so, struct sockaddr **nam)
{

	return (raw_usrreqs.pru_sockaddr(so, nam));
}

static struct pr_usrreqs route_usrreqs = {
	.pru_abort =		rts_abort,
	.pru_attach =		rts_attach,
	.pru_bind =		rts_bind,
	.pru_connect =		rts_connect,
	.pru_detach =		rts_detach,
	.pru_disconnect =	rts_disconnect,
	.pru_peeraddr =		rts_peeraddr,
	.pru_send =		rts_send,
	.pru_shutdown =		rts_shutdown,
	.pru_sockaddr =		rts_sockaddr,
	.pru_close =		rts_close,
};

#ifndef _SOCKADDR_UNION_DEFINED
#define	_SOCKADDR_UNION_DEFINED
/*
 * The union of all possible address formats we handle.
 */
union sockaddr_union {
	struct sockaddr		sa;
	struct sockaddr_in	sin;
	struct sockaddr_in6	sin6;
};
#endif /* _SOCKADDR_UNION_DEFINED */

static int
rtm_get_jailed(struct rt_addrinfo *info, struct ifnet *ifp,
    struct rtentry *rt, union sockaddr_union *saun, struct ucred *cred)
{

	/* First, see if the returned address is part of the jail. */
	if (prison_if(cred, rt->rt_ifa->ifa_addr) == 0) {
		info->rti_info[RTAX_IFA] = rt->rt_ifa->ifa_addr;
		return (0);
	}

	switch (info->rti_info[RTAX_DST]->sa_family) {
#ifdef INET
	case AF_INET:
	{
		struct in_addr ia;
		struct ifaddr *ifa;
		int found;

		found = 0;
		/*
		 * Try to find an address on the given outgoing interface
		 * that belongs to the jail.
		 */
		IF_ADDR_LOCK(ifp);
		TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
			struct sockaddr *sa;
			sa = ifa->ifa_addr;
			if (sa->sa_family != AF_INET)
				continue;
			ia = ((struct sockaddr_in *)sa)->sin_addr;
			if (prison_check_ip4(cred, &ia) == 0) {
				found = 1;
				break;
			}
		}
		IF_ADDR_UNLOCK(ifp);
		if (!found) {
			/*
			 * As a last resort return the 'default' jail address.
			 */
			ia = ((struct sockaddr_in *)rt->rt_ifa->ifa_addr)->
			    sin_addr;
			if (prison_get_ip4(cred, &ia) != 0)
				return (ESRCH);
		}
		bzero(&saun->sin, sizeof(struct sockaddr_in));
		saun->sin.sin_len = sizeof(struct sockaddr_in);
		saun->sin.sin_family = AF_INET;
		saun->sin.sin_addr.s_addr = ia.s_addr;
		info->rti_info[RTAX_IFA] = (struct sockaddr *)&saun->sin;
		break;
	}
#endif
#ifdef INET6
	case AF_INET6:
	{
		struct in6_addr ia6;
		struct ifaddr *ifa;
		int found;

		found = 0;
		/*
		 * Try to find an address on the given outgoing interface
		 * that belongs to the jail.
		 */
		IF_ADDR_LOCK(ifp);
		TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
			struct sockaddr *sa;
			sa = ifa->ifa_addr;
			if (sa->sa_family != AF_INET6)
				continue;
			bcopy(&((struct sockaddr_in6 *)sa)->sin6_addr,
			    &ia6, sizeof(struct in6_addr));
			if (prison_check_ip6(cred, &ia6) == 0) {
				found = 1;
				break;
			}
		}
		IF_ADDR_UNLOCK(ifp);
		if (!found) {
			/*
			 * As a last resort return the 'default' jail address.
			 */
			ia6 = ((struct sockaddr_in6 *)rt->rt_ifa->ifa_addr)->
			    sin6_addr;
			if (prison_get_ip6(cred, &ia6) != 0)
				return (ESRCH);
		}
		bzero(&saun->sin6, sizeof(struct sockaddr_in6));
		saun->sin6.sin6_len = sizeof(struct sockaddr_in6);
		saun->sin6.sin6_family = AF_INET6;
		bcopy(&ia6, &saun->sin6.sin6_addr, sizeof(struct in6_addr));
		if (sa6_recoverscope(&saun->sin6) != 0)
			return (ESRCH);
		info->rti_info[RTAX_IFA] = (struct sockaddr *)&saun->sin6;
		break;
	}
#endif
	default:
		return (ESRCH);
	}
	return (0);
}

/*ARGSUSED*/
static int
route_output(struct mbuf *m, struct socket *so)
{
#define	sa_equal(a1, a2) (bcmp((a1), (a2), (a1)->sa_len) == 0)
	struct rt_msghdr *rtm = NULL;
	struct rtentry *rt = NULL;
	struct radix_node_head *rnh;
	struct rt_addrinfo info;
	int len, error = 0;
	struct ifnet *ifp = NULL;
	union sockaddr_union saun;

#define senderr(e) { error = e; goto flush;}
	if (m == NULL || ((m->m_len < sizeof(long)) &&
		       (m = m_pullup(m, sizeof(long))) == NULL))
		return (ENOBUFS);
	if ((m->m_flags & M_PKTHDR) == 0)
		panic("route_output");
	len = m->m_pkthdr.len;
	if (len < sizeof(*rtm) ||
	    len != mtod(m, struct rt_msghdr *)->rtm_msglen) {
		info.rti_info[RTAX_DST] = NULL;
		senderr(EINVAL);
	}
	R_Malloc(rtm, struct rt_msghdr *, len);
	if (rtm == NULL) {
		info.rti_info[RTAX_DST] = NULL;
		senderr(ENOBUFS);
	}
	m_copydata(m, 0, len, (caddr_t)rtm);
	if (rtm->rtm_version != RTM_VERSION) {
		info.rti_info[RTAX_DST] = NULL;
		senderr(EPROTONOSUPPORT);
	}
	rtm->rtm_pid = curproc->p_pid;
	bzero(&info, sizeof(info));
	info.rti_addrs = rtm->rtm_addrs;
	if (rt_xaddrs((caddr_t)(rtm + 1), len + (caddr_t)rtm, &info)) {
		info.rti_info[RTAX_DST] = NULL;
		senderr(EINVAL);
	}
	info.rti_flags = rtm->rtm_flags;
	if (info.rti_info[RTAX_DST] == NULL ||
	    info.rti_info[RTAX_DST]->sa_family >= AF_MAX ||
	    (info.rti_info[RTAX_GATEWAY] != NULL &&
	     info.rti_info[RTAX_GATEWAY]->sa_family >= AF_MAX))
		senderr(EINVAL);
	/*
	 * Verify that the caller has the appropriate privilege; RTM_GET
	 * is the only operation the non-superuser is allowed.
	 */
	if (rtm->rtm_type != RTM_GET) {
		error = priv_check(curthread, PRIV_NET_ROUTE);
		if (error)
			senderr(error);
	}

	/*
	 * The given gateway address may be an interface address.
	 * For example, issuing a "route change" command on a route
	 * entry that was created from a tunnel, and the gateway
	 * address given is the local end point. In this case the 
	 * RTF_GATEWAY flag must be cleared or the destination will
	 * not be reachable even though there is no error message.
	 */
	if (info.rti_info[RTAX_GATEWAY] != NULL &&
	    info.rti_info[RTAX_GATEWAY]->sa_family != AF_LINK) {
		struct route gw_ro;

		bzero(&gw_ro, sizeof(gw_ro));
		gw_ro.ro_dst = *info.rti_info[RTAX_GATEWAY];
		rtalloc_ign_fib(&gw_ro, 0, so->so_fibnum);
		/* 
		 * A host route through the loopback interface is 
		 * installed for each interface adddress. In pre 8.0
		 * releases the interface address of a PPP link type
		 * is not reachable locally. This behavior is fixed as 
		 * part of the new L2/L3 redesign and rewrite work. The
		 * signature of this interface address route is the
		 * AF_LINK sa_family type of the rt_gateway, and the
		 * rt_ifp has the IFF_LOOPBACK flag set.
		 */
		if (gw_ro.ro_rt != NULL &&
		    gw_ro.ro_rt->rt_gateway->sa_family == AF_LINK &&
		    gw_ro.ro_rt->rt_ifp->if_flags & IFF_LOOPBACK)
			info.rti_flags &= ~RTF_GATEWAY;
		if (gw_ro.ro_rt != NULL)
			RTFREE(gw_ro.ro_rt);
	}

	switch (rtm->rtm_type) {
		struct rtentry *saved_nrt;

	case RTM_ADD:
		if (info.rti_info[RTAX_GATEWAY] == NULL)
			senderr(EINVAL);
		saved_nrt = NULL;

		/* support for new ARP code */
		if (info.rti_info[RTAX_GATEWAY]->sa_family == AF_LINK &&
		    (rtm->rtm_flags & RTF_LLDATA) != 0) {
			error = lla_rt_output(rtm, &info);
			break;
		}
		error = rtrequest1_fib(RTM_ADD, &info, &saved_nrt,
		    so->so_fibnum);
		if (error == 0 && saved_nrt) {
			RT_LOCK(saved_nrt);
			rt_setmetrics(rtm->rtm_inits,
				&rtm->rtm_rmx, &saved_nrt->rt_rmx);
			rtm->rtm_index = saved_nrt->rt_ifp->if_index;
			RT_REMREF(saved_nrt);
			RT_UNLOCK(saved_nrt);
		}
		break;

	case RTM_DELETE:
		saved_nrt = NULL;
		/* support for new ARP code */
		if (info.rti_info[RTAX_GATEWAY] && 
		    (info.rti_info[RTAX_GATEWAY]->sa_family == AF_LINK) &&
		    (rtm->rtm_flags & RTF_LLDATA) != 0) {
			error = lla_rt_output(rtm, &info);
			break;
		}
		error = rtrequest1_fib(RTM_DELETE, &info, &saved_nrt,
		    so->so_fibnum);
		if (error == 0) {
			RT_LOCK(saved_nrt);
			rt = saved_nrt;
			goto report;
		}
		break;

	case RTM_GET:
	case RTM_CHANGE:
	case RTM_LOCK:
		rnh = rt_tables_get_rnh(so->so_fibnum,
		    info.rti_info[RTAX_DST]->sa_family);
		if (rnh == NULL)
			senderr(EAFNOSUPPORT);
		RADIX_NODE_HEAD_RLOCK(rnh);
		rt = (struct rtentry *) rnh->rnh_lookup(info.rti_info[RTAX_DST],
			info.rti_info[RTAX_NETMASK], rnh);
		if (rt == NULL) {	/* XXX looks bogus */
			RADIX_NODE_HEAD_RUNLOCK(rnh);
			senderr(ESRCH);
		}
#ifdef RADIX_MPATH
		/*
		 * for RTM_CHANGE/LOCK, if we got multipath routes,
		 * we require users to specify a matching RTAX_GATEWAY.
		 *
		 * for RTM_GET, gate is optional even with multipath.
		 * if gate == NULL the first match is returned.
		 * (no need to call rt_mpath_matchgate if gate == NULL)
		 */
		if (rn_mpath_capable(rnh) &&
		    (rtm->rtm_type != RTM_GET || info.rti_info[RTAX_GATEWAY])) {
			rt = rt_mpath_matchgate(rt, info.rti_info[RTAX_GATEWAY]);
			if (!rt) {
				RADIX_NODE_HEAD_RUNLOCK(rnh);
				senderr(ESRCH);
			}
		}
#endif
		/*
		 * If performing proxied L2 entry insertion, and
		 * the actual PPP host entry is found, perform
		 * another search to retrieve the prefix route of
		 * the local end point of the PPP link.
		 */
		if ((rtm->rtm_flags & RTF_ANNOUNCE) &&
		    (rt->rt_ifp->if_flags & IFF_POINTOPOINT)) {
			struct sockaddr laddr;
			rt_maskedcopy(rt->rt_ifa->ifa_addr,
				      &laddr,
				      rt->rt_ifa->ifa_netmask);
			/* 
			 * refactor rt and no lock operation necessary
			 */
			rt = (struct rtentry *)rnh->rnh_matchaddr(&laddr, rnh);
			if (rt == NULL) {
				RADIX_NODE_HEAD_RUNLOCK(rnh);
				senderr(ESRCH);
			}
		} 
		RT_LOCK(rt);
		RT_ADDREF(rt);
		RADIX_NODE_HEAD_RUNLOCK(rnh);

		/* 
		 * Fix for PR: 82974
		 *
		 * RTM_CHANGE/LOCK need a perfect match, rn_lookup()
		 * returns a perfect match in case a netmask is
		 * specified.  For host routes only a longest prefix
		 * match is returned so it is necessary to compare the
		 * existence of the netmask.  If both have a netmask
		 * rnh_lookup() did a perfect match and if none of them
		 * have a netmask both are host routes which is also a
		 * perfect match.
		 */

		if (rtm->rtm_type != RTM_GET && 
		    (!rt_mask(rt) != !info.rti_info[RTAX_NETMASK])) {
			RT_UNLOCK(rt);
			senderr(ESRCH);
		}

		switch(rtm->rtm_type) {

		case RTM_GET:
		report:
			RT_LOCK_ASSERT(rt);
			if ((rt->rt_flags & RTF_HOST) == 0
			    ? jailed_without_vnet(curthread->td_ucred)
			    : prison_if(curthread->td_ucred,
			    rt_key(rt)) != 0) {
				RT_UNLOCK(rt);
				senderr(ESRCH);
			}
			info.rti_info[RTAX_DST] = rt_key(rt);
			info.rti_info[RTAX_GATEWAY] = rt->rt_gateway;
			info.rti_info[RTAX_NETMASK] = rt_mask(rt);
			info.rti_info[RTAX_GENMASK] = 0;
			if (rtm->rtm_addrs & (RTA_IFP | RTA_IFA)) {
				ifp = rt->rt_ifp;
				if (ifp) {
					info.rti_info[RTAX_IFP] =
					    ifp->if_addr->ifa_addr;
					error = rtm_get_jailed(&info, ifp, rt,
					    &saun, curthread->td_ucred);
					if (error != 0) {
						RT_UNLOCK(rt);
						senderr(error);
					}
					if (ifp->if_flags & IFF_POINTOPOINT)
						info.rti_info[RTAX_BRD] =
						    rt->rt_ifa->ifa_dstaddr;
					rtm->rtm_index = ifp->if_index;
				} else {
					info.rti_info[RTAX_IFP] = NULL;
					info.rti_info[RTAX_IFA] = NULL;
				}
			} else if ((ifp = rt->rt_ifp) != NULL) {
				rtm->rtm_index = ifp->if_index;
			}
			len = rt_msg2(rtm->rtm_type, &info, NULL, NULL);
			if (len > rtm->rtm_msglen) {
				struct rt_msghdr *new_rtm;
				R_Malloc(new_rtm, struct rt_msghdr *, len);
				if (new_rtm == NULL) {
					RT_UNLOCK(rt);
					senderr(ENOBUFS);
				}
				bcopy(rtm, new_rtm, rtm->rtm_msglen);
				Free(rtm); rtm = new_rtm;
			}
			(void)rt_msg2(rtm->rtm_type, &info, (caddr_t)rtm, NULL);
			rtm->rtm_flags = rt->rt_flags;
			rt_getmetrics(&rt->rt_rmx, &rtm->rtm_rmx);
			rtm->rtm_addrs = info.rti_addrs;
			break;

		case RTM_CHANGE:
			/*
			 * New gateway could require new ifaddr, ifp;
			 * flags may also be different; ifp may be specified
			 * by ll sockaddr when protocol address is ambiguous
			 */
			if (((rt->rt_flags & RTF_GATEWAY) &&
			     info.rti_info[RTAX_GATEWAY] != NULL) ||
			    info.rti_info[RTAX_IFP] != NULL ||
			    (info.rti_info[RTAX_IFA] != NULL &&
			     !sa_equal(info.rti_info[RTAX_IFA],
				       rt->rt_ifa->ifa_addr))) {
				RT_UNLOCK(rt);
				RADIX_NODE_HEAD_LOCK(rnh);
				error = rt_getifa_fib(&info, rt->rt_fibnum);
				/*
				 * XXXRW: Really we should release this
				 * reference later, but this maintains
				 * historical behavior.
				 */
				if (info.rti_ifa != NULL)
					ifa_free(info.rti_ifa);
				RADIX_NODE_HEAD_UNLOCK(rnh);
				if (error != 0)
					senderr(error);
				RT_LOCK(rt);
			}
			if (info.rti_ifa != NULL &&
			    info.rti_ifa != rt->rt_ifa &&
			    rt->rt_ifa != NULL &&
			    rt->rt_ifa->ifa_rtrequest != NULL) {
				rt->rt_ifa->ifa_rtrequest(RTM_DELETE, rt,
				    &info);
				ifa_free(rt->rt_ifa);
			}
			if (info.rti_info[RTAX_GATEWAY] != NULL) {
				RT_UNLOCK(rt);
				RADIX_NODE_HEAD_LOCK(rnh);
				RT_LOCK(rt);
				
				error = rt_setgate(rt, rt_key(rt),
				    info.rti_info[RTAX_GATEWAY]);
				RADIX_NODE_HEAD_UNLOCK(rnh);
				if (error != 0) {
					RT_UNLOCK(rt);
					senderr(error);
				}
				rt->rt_flags |= (RTF_GATEWAY & info.rti_flags);
			}
			if (info.rti_ifa != NULL &&
			    info.rti_ifa != rt->rt_ifa) {
				ifa_ref(info.rti_ifa);
				rt->rt_ifa = info.rti_ifa;
				rt->rt_ifp = info.rti_ifp;
			}
			/* Allow some flags to be toggled on change. */
			rt->rt_flags = (rt->rt_flags & ~RTF_FMASK) |
				    (rtm->rtm_flags & RTF_FMASK);
			rt_setmetrics(rtm->rtm_inits, &rtm->rtm_rmx,
					&rt->rt_rmx);
			rtm->rtm_index = rt->rt_ifp->if_index;
			if (rt->rt_ifa && rt->rt_ifa->ifa_rtrequest)
			       rt->rt_ifa->ifa_rtrequest(RTM_ADD, rt, &info);
			/* FALLTHROUGH */
		case RTM_LOCK:
			/* We don't support locks anymore */
			break;
		}
		RT_UNLOCK(rt);
		break;

	default:
		senderr(EOPNOTSUPP);
	}

flush:
	if (rtm) {
		if (error)
			rtm->rtm_errno = error;
		else
			rtm->rtm_flags |= RTF_DONE;
	}
	if (rt)		/* XXX can this be true? */
		RTFREE(rt);
    {
	struct rawcb *rp = NULL;
	/*
	 * Check to see if we don't want our own messages.
	 */
	if ((so->so_options & SO_USELOOPBACK) == 0) {
		if (route_cb.any_count <= 1) {
			if (rtm)
				Free(rtm);
			m_freem(m);
			return (error);
		}
		/* There is another listener, so construct message */
		rp = sotorawcb(so);
	}
	if (rtm) {
		m_copyback(m, 0, rtm->rtm_msglen, (caddr_t)rtm);
		if (m->m_pkthdr.len < rtm->rtm_msglen) {
			m_freem(m);
			m = NULL;
		} else if (m->m_pkthdr.len > rtm->rtm_msglen)
			m_adj(m, rtm->rtm_msglen - m->m_pkthdr.len);
		Free(rtm);
	}
	if (m) {
		if (rp) {
			/*
			 * XXX insure we don't get a copy by
			 * invalidating our protocol
			 */
			unsigned short family = rp->rcb_proto.sp_family;
			rp->rcb_proto.sp_family = 0;
			rt_dispatch(m, info.rti_info[RTAX_DST]);
			rp->rcb_proto.sp_family = family;
		} else
			rt_dispatch(m, info.rti_info[RTAX_DST]);
	}
    }
	return (error);
#undef	sa_equal
}

static void
rt_setmetrics(u_long which, const struct rt_metrics *in,
	struct rt_metrics_lite *out)
{
#define metric(f, e) if (which & (f)) out->e = in->e;
	/*
	 * Only these are stored in the routing entry since introduction
	 * of tcp hostcache. The rest is ignored.
	 */
	metric(RTV_MTU, rmx_mtu);
	metric(RTV_WEIGHT, rmx_weight);
	/* Userland -> kernel timebase conversion. */
	if (which & RTV_EXPIRE)
		out->rmx_expire = in->rmx_expire ?
		    in->rmx_expire - time_second + time_uptime : 0;
#undef metric
}

static void
rt_getmetrics(const struct rt_metrics_lite *in, struct rt_metrics *out)
{
#define metric(e) out->e = in->e;
	bzero(out, sizeof(*out));
	metric(rmx_mtu);
	metric(rmx_weight);
	/* Kernel -> userland timebase conversion. */
	out->rmx_expire = in->rmx_expire ?
	    in->rmx_expire - time_uptime + time_second : 0;
#undef metric
}

/*
 * Extract the addresses of the passed sockaddrs.
 * Do a little sanity checking so as to avoid bad memory references.
 * This data is derived straight from userland.
 */
static int
rt_xaddrs(caddr_t cp, caddr_t cplim, struct rt_addrinfo *rtinfo)
{
	struct sockaddr *sa;
	int i;

	for (i = 0; i < RTAX_MAX && cp < cplim; i++) {
		if ((rtinfo->rti_addrs & (1 << i)) == 0)
			continue;
		sa = (struct sockaddr *)cp;
		/*
		 * It won't fit.
		 */
		if (cp + sa->sa_len > cplim)
			return (EINVAL);
		/*
		 * there are no more.. quit now
		 * If there are more bits, they are in error.
		 * I've seen this. route(1) can evidently generate these. 
		 * This causes kernel to core dump.
		 * for compatibility, If we see this, point to a safe address.
		 */
		if (sa->sa_len == 0) {
			rtinfo->rti_info[i] = &sa_zero;
			return (0); /* should be EINVAL but for compat */
		}
		/* accept it */
		rtinfo->rti_info[i] = sa;
		cp += SA_SIZE(sa);
	}
	return (0);
}

static struct mbuf *
rt_msg1(int type, struct rt_addrinfo *rtinfo)
{
	struct rt_msghdr *rtm;
	struct mbuf *m;
	int i;
	struct sockaddr *sa;
	int len, dlen;

	switch (type) {

	case RTM_DELADDR:
	case RTM_NEWADDR:
		len = sizeof(struct ifa_msghdr);
		break;

	case RTM_DELMADDR:
	case RTM_NEWMADDR:
		len = sizeof(struct ifma_msghdr);
		break;

	case RTM_IFINFO:
		len = sizeof(struct if_msghdr);
		break;

	case RTM_IFANNOUNCE:
	case RTM_IEEE80211:
		len = sizeof(struct if_announcemsghdr);
		break;

	default:
		len = sizeof(struct rt_msghdr);
	}
	if (len > MCLBYTES)
		panic("rt_msg1");
	m = m_gethdr(M_DONTWAIT, MT_DATA);
	if (m && len > MHLEN) {
		MCLGET(m, M_DONTWAIT);
		if ((m->m_flags & M_EXT) == 0) {
			m_free(m);
			m = NULL;
		}
	}
	if (m == NULL)
		return (m);
	m->m_pkthdr.len = m->m_len = len;
	m->m_pkthdr.rcvif = NULL;
	rtm = mtod(m, struct rt_msghdr *);
	bzero((caddr_t)rtm, len);
	for (i = 0; i < RTAX_MAX; i++) {
		if ((sa = rtinfo->rti_info[i]) == NULL)
			continue;
		rtinfo->rti_addrs |= (1 << i);
		dlen = SA_SIZE(sa);
		m_copyback(m, len, dlen, (caddr_t)sa);
		len += dlen;
	}
	if (m->m_pkthdr.len != len) {
		m_freem(m);
		return (NULL);
	}
	rtm->rtm_msglen = len;
	rtm->rtm_version = RTM_VERSION;
	rtm->rtm_type = type;
	return (m);
}

static int
rt_msg2(int type, struct rt_addrinfo *rtinfo, caddr_t cp, struct walkarg *w)
{
	int i;
	int len, dlen, second_time = 0;
	caddr_t cp0;

	rtinfo->rti_addrs = 0;
again:
	switch (type) {

	case RTM_DELADDR:
	case RTM_NEWADDR:
		len = sizeof(struct ifa_msghdr);
		break;

	case RTM_IFINFO:
#ifdef COMPAT_FREEBSD32
		if (w != NULL && w->w_req->flags & SCTL_MASK32) {
			len = sizeof(struct if_msghdr32);
			break;
		}
#endif
		len = sizeof(struct if_msghdr);
		break;

	case RTM_NEWMADDR:
		len = sizeof(struct ifma_msghdr);
		break;

	default:
		len = sizeof(struct rt_msghdr);
	}
	cp0 = cp;
	if (cp0)
		cp += len;
	for (i = 0; i < RTAX_MAX; i++) {
		struct sockaddr *sa;

		if ((sa = rtinfo->rti_info[i]) == NULL)
			continue;
		rtinfo->rti_addrs |= (1 << i);
		dlen = SA_SIZE(sa);
		if (cp) {
			bcopy((caddr_t)sa, cp, (unsigned)dlen);
			cp += dlen;
		}
		len += dlen;
	}
	len = ALIGN(len);
	if (cp == NULL && w != NULL && !second_time) {
		struct walkarg *rw = w;

		if (rw->w_req) {
			if (rw->w_tmemsize < len) {
				if (rw->w_tmem)
					free(rw->w_tmem, M_RTABLE);
				rw->w_tmem = (caddr_t)
					malloc(len, M_RTABLE, M_NOWAIT);
				if (rw->w_tmem)
					rw->w_tmemsize = len;
			}
			if (rw->w_tmem) {
				cp = rw->w_tmem;
				second_time = 1;
				goto again;
			}
		}
	}
	if (cp) {
		struct rt_msghdr *rtm = (struct rt_msghdr *)cp0;

		rtm->rtm_version = RTM_VERSION;
		rtm->rtm_type = type;
		rtm->rtm_msglen = len;
	}
	return (len);
}

/*
 * This routine is called to generate a message from the routing
 * socket indicating that a redirect has occured, a routing lookup
 * has failed, or that a protocol has detected timeouts to a particular
 * destination.
 */
void
rt_missmsg(int type, struct rt_addrinfo *rtinfo, int flags, int error)
{
	struct rt_msghdr *rtm;
	struct mbuf *m;
	struct sockaddr *sa = rtinfo->rti_info[RTAX_DST];

	if (route_cb.any_count == 0)
		return;
	m = rt_msg1(type, rtinfo);
	if (m == NULL)
		return;
	rtm = mtod(m, struct rt_msghdr *);
	rtm->rtm_flags = RTF_DONE | flags;
	rtm->rtm_errno = error;
	rtm->rtm_addrs = rtinfo->rti_addrs;
	rt_dispatch(m, sa);
}

/*
 * This routine is called to generate a message from the routing
 * socket indicating that the status of a network interface has changed.
 */
void
rt_ifmsg(struct ifnet *ifp)
{
	struct if_msghdr *ifm;
	struct mbuf *m;
	struct rt_addrinfo info;

	if (route_cb.any_count == 0)
		return;
	bzero((caddr_t)&info, sizeof(info));
	m = rt_msg1(RTM_IFINFO, &info);
	if (m == NULL)
		return;
	ifm = mtod(m, struct if_msghdr *);
	ifm->ifm_index = ifp->if_index;
	ifm->ifm_flags = ifp->if_flags | ifp->if_drv_flags;
	ifm->ifm_data = ifp->if_data;
	ifm->ifm_addrs = 0;
	rt_dispatch(m, NULL);
}

/*
 * This is called to generate messages from the routing socket
 * indicating a network interface has had addresses associated with it.
 * if we ever reverse the logic and replace messages TO the routing
 * socket indicate a request to configure interfaces, then it will
 * be unnecessary as the routing socket will automatically generate
 * copies of it.
 */
void
rt_newaddrmsg(int cmd, struct ifaddr *ifa, int error, struct rtentry *rt)
{
	struct rt_addrinfo info;
	struct sockaddr *sa = NULL;
	int pass;
	struct mbuf *m = NULL;
	struct ifnet *ifp = ifa->ifa_ifp;

	KASSERT(cmd == RTM_ADD || cmd == RTM_DELETE,
		("unexpected cmd %u", cmd));
#if defined(INET) || defined(INET6)
#ifdef SCTP
	/*
	 * notify the SCTP stack
	 * this will only get called when an address is added/deleted
	 * XXX pass the ifaddr struct instead if ifa->ifa_addr...
	 */
	sctp_addr_change(ifa, cmd);
#endif /* SCTP */
#endif
	if (route_cb.any_count == 0)
		return;
	for (pass = 1; pass < 3; pass++) {
		bzero((caddr_t)&info, sizeof(info));
		if ((cmd == RTM_ADD && pass == 1) ||
		    (cmd == RTM_DELETE && pass == 2)) {
			struct ifa_msghdr *ifam;
			int ncmd = cmd == RTM_ADD ? RTM_NEWADDR : RTM_DELADDR;

			info.rti_info[RTAX_IFA] = sa = ifa->ifa_addr;
			info.rti_info[RTAX_IFP] = ifp->if_addr->ifa_addr;
			info.rti_info[RTAX_NETMASK] = ifa->ifa_netmask;
			info.rti_info[RTAX_BRD] = ifa->ifa_dstaddr;
			if ((m = rt_msg1(ncmd, &info)) == NULL)
				continue;
			ifam = mtod(m, struct ifa_msghdr *);
			ifam->ifam_index = ifp->if_index;
			ifam->ifam_metric = ifa->ifa_metric;
			ifam->ifam_flags = ifa->ifa_flags;
			ifam->ifam_addrs = info.rti_addrs;
		}
		if ((cmd == RTM_ADD && pass == 2) ||
		    (cmd == RTM_DELETE && pass == 1)) {
			struct rt_msghdr *rtm;

			if (rt == NULL)
				continue;
			info.rti_info[RTAX_NETMASK] = rt_mask(rt);
			info.rti_info[RTAX_DST] = sa = rt_key(rt);
			info.rti_info[RTAX_GATEWAY] = rt->rt_gateway;
			if ((m = rt_msg1(cmd, &info)) == NULL)
				continue;
			rtm = mtod(m, struct rt_msghdr *);
			rtm->rtm_index = ifp->if_index;
			rtm->rtm_flags |= rt->rt_flags;
			rtm->rtm_errno = error;
			rtm->rtm_addrs = info.rti_addrs;
		}
		rt_dispatch(m, sa);
	}
}

/*
 * This is the analogue to the rt_newaddrmsg which performs the same
 * function but for multicast group memberhips.  This is easier since
 * there is no route state to worry about.
 */
void
rt_newmaddrmsg(int cmd, struct ifmultiaddr *ifma)
{
	struct rt_addrinfo info;
	struct mbuf *m = NULL;
	struct ifnet *ifp = ifma->ifma_ifp;
	struct ifma_msghdr *ifmam;

	if (route_cb.any_count == 0)
		return;

	bzero((caddr_t)&info, sizeof(info));
	info.rti_info[RTAX_IFA] = ifma->ifma_addr;
	info.rti_info[RTAX_IFP] = ifp ? ifp->if_addr->ifa_addr : NULL;
	/*
	 * If a link-layer address is present, present it as a ``gateway''
	 * (similarly to how ARP entries, e.g., are presented).
	 */
	info.rti_info[RTAX_GATEWAY] = ifma->ifma_lladdr;
	m = rt_msg1(cmd, &info);
	if (m == NULL)
		return;
	ifmam = mtod(m, struct ifma_msghdr *);
	KASSERT(ifp != NULL, ("%s: link-layer multicast address w/o ifp\n",
	    __func__));
	ifmam->ifmam_index = ifp->if_index;
	ifmam->ifmam_addrs = info.rti_addrs;
	rt_dispatch(m, ifma->ifma_addr);
}

static struct mbuf *
rt_makeifannouncemsg(struct ifnet *ifp, int type, int what,
	struct rt_addrinfo *info)
{
	struct if_announcemsghdr *ifan;
	struct mbuf *m;

	if (route_cb.any_count == 0)
		return NULL;
	bzero((caddr_t)info, sizeof(*info));
	m = rt_msg1(type, info);
	if (m != NULL) {
		ifan = mtod(m, struct if_announcemsghdr *);
		ifan->ifan_index = ifp->if_index;
		strlcpy(ifan->ifan_name, ifp->if_xname,
			sizeof(ifan->ifan_name));
		ifan->ifan_what = what;
	}
	return m;
}

/*
 * This is called to generate routing socket messages indicating
 * IEEE80211 wireless events.
 * XXX we piggyback on the RTM_IFANNOUNCE msg format in a clumsy way.
 */
void
rt_ieee80211msg(struct ifnet *ifp, int what, void *data, size_t data_len)
{
	struct mbuf *m;
	struct rt_addrinfo info;

	m = rt_makeifannouncemsg(ifp, RTM_IEEE80211, what, &info);
	if (m != NULL) {
		/*
		 * Append the ieee80211 data.  Try to stick it in the
		 * mbuf containing the ifannounce msg; otherwise allocate
		 * a new mbuf and append.
		 *
		 * NB: we assume m is a single mbuf.
		 */
		if (data_len > M_TRAILINGSPACE(m)) {
			struct mbuf *n = m_get(M_NOWAIT, MT_DATA);
			if (n == NULL) {
				m_freem(m);
				return;
			}
			bcopy(data, mtod(n, void *), data_len);
			n->m_len = data_len;
			m->m_next = n;
		} else if (data_len > 0) {
			bcopy(data, mtod(m, u_int8_t *) + m->m_len, data_len);
			m->m_len += data_len;
		}
		if (m->m_flags & M_PKTHDR)
			m->m_pkthdr.len += data_len;
		mtod(m, struct if_announcemsghdr *)->ifan_msglen += data_len;
		rt_dispatch(m, NULL);
	}
}

/*
 * This is called to generate routing socket messages indicating
 * network interface arrival and departure.
 */
void
rt_ifannouncemsg(struct ifnet *ifp, int what)
{
	struct mbuf *m;
	struct rt_addrinfo info;

	m = rt_makeifannouncemsg(ifp, RTM_IFANNOUNCE, what, &info);
	if (m != NULL)
		rt_dispatch(m, NULL);
}

static void
rt_dispatch(struct mbuf *m, const struct sockaddr *sa)
{
	struct m_tag *tag;

	/*
	 * Preserve the family from the sockaddr, if any, in an m_tag for
	 * use when injecting the mbuf into the routing socket buffer from
	 * the netisr.
	 */
	if (sa != NULL) {
		tag = m_tag_get(PACKET_TAG_RTSOCKFAM, sizeof(unsigned short),
		    M_NOWAIT);
		if (tag == NULL) {
			m_freem(m);
			return;
		}
		*(unsigned short *)(tag + 1) = sa->sa_family;
		m_tag_prepend(m, tag);
	}
#ifdef VIMAGE
	if (V_loif)
		m->m_pkthdr.rcvif = V_loif;
	else {
		m_freem(m);
		return;
	}
#endif
	netisr_queue(NETISR_ROUTE, m);	/* mbuf is free'd on failure. */
}

/*
 * This is used in dumping the kernel table via sysctl().
 */
static int
sysctl_dumpentry(struct radix_node *rn, void *vw)
{
	struct walkarg *w = vw;
	struct rtentry *rt = (struct rtentry *)rn;
	int error = 0, size;
	struct rt_addrinfo info;

	if (w->w_op == NET_RT_FLAGS && !(rt->rt_flags & w->w_arg))
		return 0;
	if ((rt->rt_flags & RTF_HOST) == 0
	    ? jailed_without_vnet(w->w_req->td->td_ucred)
	    : prison_if(w->w_req->td->td_ucred, rt_key(rt)) != 0)
		return (0);
	bzero((caddr_t)&info, sizeof(info));
	info.rti_info[RTAX_DST] = rt_key(rt);
	info.rti_info[RTAX_GATEWAY] = rt->rt_gateway;
	info.rti_info[RTAX_NETMASK] = rt_mask(rt);
	info.rti_info[RTAX_GENMASK] = 0;
	if (rt->rt_ifp) {
		info.rti_info[RTAX_IFP] = rt->rt_ifp->if_addr->ifa_addr;
		info.rti_info[RTAX_IFA] = rt->rt_ifa->ifa_addr;
		if (rt->rt_ifp->if_flags & IFF_POINTOPOINT)
			info.rti_info[RTAX_BRD] = rt->rt_ifa->ifa_dstaddr;
	}
	size = rt_msg2(RTM_GET, &info, NULL, w);
	if (w->w_req && w->w_tmem) {
		struct rt_msghdr *rtm = (struct rt_msghdr *)w->w_tmem;

		rtm->rtm_flags = rt->rt_flags;
		/*
		 * let's be honest about this being a retarded hack
		 */
		rtm->rtm_fmask = rt->rt_rmx.rmx_pksent;
		rt_getmetrics(&rt->rt_rmx, &rtm->rtm_rmx);
		rtm->rtm_index = rt->rt_ifp->if_index;
		rtm->rtm_errno = rtm->rtm_pid = rtm->rtm_seq = 0;
		rtm->rtm_addrs = info.rti_addrs;
		error = SYSCTL_OUT(w->w_req, (caddr_t)rtm, size);
		return (error);
	}
	return (error);
}

#ifdef COMPAT_FREEBSD32
static void
copy_ifdata32(struct if_data *src, struct if_data32 *dst)
{

	bzero(dst, sizeof(*dst));
	CP(*src, *dst, ifi_type);
	CP(*src, *dst, ifi_physical);
	CP(*src, *dst, ifi_addrlen);
	CP(*src, *dst, ifi_hdrlen);
	CP(*src, *dst, ifi_link_state);
	CP(*src, *dst, ifi_datalen);
	CP(*src, *dst, ifi_mtu);
	CP(*src, *dst, ifi_metric);
	CP(*src, *dst, ifi_baudrate);
	CP(*src, *dst, ifi_ipackets);
	CP(*src, *dst, ifi_ierrors);
	CP(*src, *dst, ifi_opackets);
	CP(*src, *dst, ifi_oerrors);
	CP(*src, *dst, ifi_collisions);
	CP(*src, *dst, ifi_ibytes);
	CP(*src, *dst, ifi_obytes);
	CP(*src, *dst, ifi_imcasts);
	CP(*src, *dst, ifi_omcasts);
	CP(*src, *dst, ifi_iqdrops);
	CP(*src, *dst, ifi_noproto);
	CP(*src, *dst, ifi_hwassist);
	CP(*src, *dst, ifi_epoch);
	TV_CP(*src, *dst, ifi_lastchange);
}
#endif

static int
sysctl_iflist(int af, struct walkarg *w)
{
	struct ifnet *ifp;
	struct ifaddr *ifa;
	struct rt_addrinfo info;
	int len, error = 0;

	bzero((caddr_t)&info, sizeof(info));
	IFNET_RLOCK();
	TAILQ_FOREACH(ifp, &V_ifnet, if_link) {
		if (w->w_arg && w->w_arg != ifp->if_index)
			continue;
		ifa = ifp->if_addr;
		info.rti_info[RTAX_IFP] = ifa->ifa_addr;
		len = rt_msg2(RTM_IFINFO, &info, NULL, w);
		info.rti_info[RTAX_IFP] = NULL;
		if (w->w_req && w->w_tmem) {
			struct if_msghdr *ifm;

#ifdef COMPAT_FREEBSD32
			if (w->w_req->flags & SCTL_MASK32) {
				struct if_msghdr32 *ifm32;

				ifm32 = (struct if_msghdr32 *)w->w_tmem;
				ifm32->ifm_index = ifp->if_index;
				ifm32->ifm_flags = ifp->if_flags |
				    ifp->if_drv_flags;
				copy_ifdata32(&ifp->if_data, &ifm32->ifm_data);
				ifm32->ifm_addrs = info.rti_addrs;
				error = SYSCTL_OUT(w->w_req, (caddr_t)ifm32,
				    len);
				goto sysctl_out;
			}
#endif
			ifm = (struct if_msghdr *)w->w_tmem;
			ifm->ifm_index = ifp->if_index;
			ifm->ifm_flags = ifp->if_flags | ifp->if_drv_flags;
			ifm->ifm_data = ifp->if_data;
			ifm->ifm_addrs = info.rti_addrs;
			error = SYSCTL_OUT(w->w_req, (caddr_t)ifm, len);
#ifdef COMPAT_FREEBSD32
		sysctl_out:
#endif
			if (error)
				goto done;
		}
		while ((ifa = TAILQ_NEXT(ifa, ifa_link)) != NULL) {
			if (af && af != ifa->ifa_addr->sa_family)
				continue;
			if (prison_if(w->w_req->td->td_ucred,
			    ifa->ifa_addr) != 0)
				continue;
			info.rti_info[RTAX_IFA] = ifa->ifa_addr;
			info.rti_info[RTAX_NETMASK] = ifa->ifa_netmask;
			info.rti_info[RTAX_BRD] = ifa->ifa_dstaddr;
			len = rt_msg2(RTM_NEWADDR, &info, NULL, w);
			if (w->w_req && w->w_tmem) {
				struct ifa_msghdr *ifam;

				ifam = (struct ifa_msghdr *)w->w_tmem;
				ifam->ifam_index = ifa->ifa_ifp->if_index;
				ifam->ifam_flags = ifa->ifa_flags;
				ifam->ifam_metric = ifa->ifa_metric;
				ifam->ifam_addrs = info.rti_addrs;
				error = SYSCTL_OUT(w->w_req, w->w_tmem, len);
				if (error)
					goto done;
			}
		}
		info.rti_info[RTAX_IFA] = info.rti_info[RTAX_NETMASK] =
			info.rti_info[RTAX_BRD] = NULL;
	}
done:
	IFNET_RUNLOCK();
	return (error);
}

static int
sysctl_ifmalist(int af, struct walkarg *w)
{
	struct ifnet *ifp;
	struct ifmultiaddr *ifma;
	struct	rt_addrinfo info;
	int	len, error = 0;
	struct ifaddr *ifa;

	bzero((caddr_t)&info, sizeof(info));
	IFNET_RLOCK();
	TAILQ_FOREACH(ifp, &V_ifnet, if_link) {
		if (w->w_arg && w->w_arg != ifp->if_index)
			continue;
		ifa = ifp->if_addr;
		info.rti_info[RTAX_IFP] = ifa ? ifa->ifa_addr : NULL;
		IF_ADDR_LOCK(ifp);
		TAILQ_FOREACH(ifma, &ifp->if_multiaddrs, ifma_link) {
			if (af && af != ifma->ifma_addr->sa_family)
				continue;
			if (prison_if(w->w_req->td->td_ucred,
			    ifma->ifma_addr) != 0)
				continue;
			info.rti_info[RTAX_IFA] = ifma->ifma_addr;
			info.rti_info[RTAX_GATEWAY] =
			    (ifma->ifma_addr->sa_family != AF_LINK) ?
			    ifma->ifma_lladdr : NULL;
			len = rt_msg2(RTM_NEWMADDR, &info, NULL, w);
			if (w->w_req && w->w_tmem) {
				struct ifma_msghdr *ifmam;

				ifmam = (struct ifma_msghdr *)w->w_tmem;
				ifmam->ifmam_index = ifma->ifma_ifp->if_index;
				ifmam->ifmam_flags = 0;
				ifmam->ifmam_addrs = info.rti_addrs;
				error = SYSCTL_OUT(w->w_req, w->w_tmem, len);
				if (error) {
					IF_ADDR_UNLOCK(ifp);
					goto done;
				}
			}
		}
		IF_ADDR_UNLOCK(ifp);
	}
done:
	IFNET_RUNLOCK();
	return (error);
}

static int
sysctl_rtsock(SYSCTL_HANDLER_ARGS)
{
	int	*name = (int *)arg1;
	u_int	namelen = arg2;
	struct radix_node_head *rnh = NULL; /* silence compiler. */
	int	i, lim, error = EINVAL;
	u_char	af;
	struct	walkarg w;

	name ++;
	namelen--;
	if (req->newptr)
		return (EPERM);
	if (namelen != 3)
		return ((namelen < 3) ? EISDIR : ENOTDIR);
	af = name[0];
	if (af > AF_MAX)
		return (EINVAL);
	bzero(&w, sizeof(w));
	w.w_op = name[1];
	w.w_arg = name[2];
	w.w_req = req;

	error = sysctl_wire_old_buffer(req, 0);
	if (error)
		return (error);
	switch (w.w_op) {

	case NET_RT_DUMP:
	case NET_RT_FLAGS:
		if (af == 0) {			/* dump all tables */
			i = 1;
			lim = AF_MAX;
		} else				/* dump only one table */
			i = lim = af;

		/*
		 * take care of llinfo entries, the caller must
		 * specify an AF
		 */
		if (w.w_op == NET_RT_FLAGS &&
		    (w.w_arg == 0 || w.w_arg & RTF_LLINFO)) {
			if (af != 0)
				error = lltable_sysctl_dumparp(af, w.w_req);
			else
				error = EINVAL;
			break;
		}
		/*
		 * take care of routing entries
		 */
		for (error = 0; error == 0 && i <= lim; i++) {
			rnh = rt_tables_get_rnh(req->td->td_proc->p_fibnum, i);
			if (rnh != NULL) {
				RADIX_NODE_HEAD_LOCK(rnh); 
			    	error = rnh->rnh_walktree(rnh,
				    sysctl_dumpentry, &w);
				RADIX_NODE_HEAD_UNLOCK(rnh);
			} else if (af != 0)
				error = EAFNOSUPPORT;
		}
		break;

	case NET_RT_IFLIST:
		error = sysctl_iflist(af, &w);
		break;

	case NET_RT_IFMALIST:
		error = sysctl_ifmalist(af, &w);
		break;
	}
	if (w.w_tmem)
		free(w.w_tmem, M_RTABLE);
	return (error);
}

SYSCTL_NODE(_net, PF_ROUTE, routetable, CTLFLAG_RD, sysctl_rtsock, "");

/*
 * Definitions of protocols supported in the ROUTE domain.
 */

static struct domain routedomain;		/* or at least forward */

static struct protosw routesw[] = {
{
	.pr_type =		SOCK_RAW,
	.pr_domain =		&routedomain,
	.pr_flags =		PR_ATOMIC|PR_ADDR,
	.pr_output =		route_output,
	.pr_ctlinput =		raw_ctlinput,
	.pr_init =		raw_init,
	.pr_usrreqs =		&route_usrreqs
}
};

static struct domain routedomain = {
	.dom_family =		PF_ROUTE,
	.dom_name =		 "route",
	.dom_protosw =		routesw,
	.dom_protoswNPROTOSW =	&routesw[sizeof(routesw)/sizeof(routesw[0])]
};

VNET_DOMAIN_SET(route);
OpenPOWER on IntegriCloud