summaryrefslogtreecommitdiff
path: root/sys/net/rtsock.c
blob: fabc5e377745ca20ac965ec73322f78a145480b1 (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
/*	$NetBSD: rtsock.c,v 1.143 2014/02/25 18:30:12 pooka Exp $	*/

/*
 * Copyright (C) 1995, 1996, 1997, and 1998 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.
 * 3. Neither the name of the project 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 PROJECT 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 PROJECT 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.
 */

/*
 * 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.
 * 3. 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
 */

#include <sys/cdefs.h>
__KERNEL_RCSID(0, "$NetBSD: rtsock.c,v 1.143 2014/02/25 18:30:12 pooka Exp $");

#ifdef _KERNEL_OPT
#include "opt_inet.h"
#include "opt_mpls.h"
#include "opt_compat_netbsd.h"
#endif

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/proc.h>
#include <sys/mbuf.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/domain.h>
#include <sys/protosw.h>
#include <sys/sysctl.h>
#include <sys/kauth.h>
#include <sys/intr.h>
#ifdef RTSOCK_DEBUG
#include <netinet/in.h>
#endif /* RTSOCK_DEBUG */

#include <net/if.h>
#include <net/route.h>
#include <net/raw_cb.h>

#include <netmpls/mpls.h>

#if defined(COMPAT_14) || defined(COMPAT_50)
#include <compat/net/if.h>
#include <compat/net/route.h>
#endif
#ifdef COMPAT_RTSOCK
#define	RTM_XVERSION	RTM_OVERSION
#define	RT_XADVANCE(a,b) RT_OADVANCE(a,b)
#define	RT_XROUNDUP(n)	RT_OROUNDUP(n)
#define	PF_XROUTE	PF_OROUTE
#define	rt_xmsghdr	rt_msghdr50
#define	if_xmsghdr	if_msghdr	/* if_msghdr50 is for RTM_OIFINFO */
#define	ifa_xmsghdr	ifa_msghdr50
#define	if_xannouncemsghdr	if_announcemsghdr50
#define	COMPATNAME(x)	compat_50_ ## x
#define	DOMAINNAME	"oroute"
CTASSERT(sizeof(struct ifa_xmsghdr) == 20);
DOMAIN_DEFINE(compat_50_routedomain); /* forward declare and add to link set */
#else
#define	RTM_XVERSION	RTM_VERSION
#define	RT_XADVANCE(a,b) RT_ADVANCE(a,b)
#define	RT_XROUNDUP(n)	RT_ROUNDUP(n)
#define	PF_XROUTE	PF_ROUTE
#define	rt_xmsghdr	rt_msghdr
#define	if_xmsghdr	if_msghdr
#define	ifa_xmsghdr	ifa_msghdr
#define	if_xannouncemsghdr	if_announcemsghdr
#define	COMPATNAME(x)	x
#define	DOMAINNAME	"route"
CTASSERT(sizeof(struct ifa_xmsghdr) == 24);
#ifdef COMPAT_50
#define	COMPATCALL(name, args)	compat_50_ ## name args
#endif
DOMAIN_DEFINE(routedomain); /* forward declare and add to link set */
#undef COMPAT_50
#undef COMPAT_14
#endif

#ifndef COMPATCALL
#define	COMPATCALL(name, args)	do { } while (/*CONSTCOND*/ 0)
#endif

struct route_info COMPATNAME(route_info) = {
	.ri_dst = { .sa_len = 2, .sa_family = PF_XROUTE, },
	.ri_src = { .sa_len = 2, .sa_family = PF_XROUTE, },
	.ri_maxqlen = IFQ_MAXLEN,
};

#define	PRESERVED_RTF	(RTF_UP | RTF_GATEWAY | RTF_HOST | RTF_DONE | RTF_MASK)

static void COMPATNAME(route_init)(void);
static int COMPATNAME(route_output)(struct mbuf *, ...);
static int COMPATNAME(route_usrreq)(struct socket *,
	    int, struct mbuf *, struct mbuf *, struct mbuf *, struct lwp *);

static int rt_msg2(int, struct rt_addrinfo *, void *, struct rt_walkarg *, int *);
static int rt_xaddrs(u_char, const char *, const char *, struct rt_addrinfo *);
static struct mbuf *rt_makeifannouncemsg(struct ifnet *, int, int,
    struct rt_addrinfo *);
static void rt_setmetrics(int, const struct rt_xmsghdr *, struct rtentry *);
static void rtm_setmetrics(const struct rtentry *, struct rt_xmsghdr *);
static void sysctl_net_route_setup(struct sysctllog **);
static int sysctl_dumpentry(struct rtentry *, void *);
static int sysctl_iflist(int, struct rt_walkarg *, int);
static int sysctl_rtable(SYSCTLFN_PROTO);
static void rt_adjustcount(int, int);

static void
rt_adjustcount(int af, int cnt)
{
	struct route_cb * const cb = &COMPATNAME(route_info).ri_cb;

	cb->any_count += cnt;

	switch (af) {
	case AF_INET:
		cb->ip_count += cnt;
		return;
#ifdef INET6
	case AF_INET6:
		cb->ip6_count += cnt;
		return;
#endif
	case AF_MPLS:
		cb->mpls_count += cnt;
		return;
	}
}

/*ARGSUSED*/
int
COMPATNAME(route_usrreq)(struct socket *so, int req, struct mbuf *m, struct mbuf *nam,
	struct mbuf *control, struct lwp *l)
{
	int error = 0;
	struct rawcb *rp = sotorawcb(so);
	int s;

	if (req == PRU_ATTACH) {
		sosetlock(so);
		rp = malloc(sizeof(*rp), M_PCB, M_WAITOK|M_ZERO);
		so->so_pcb = rp;
	}
	if (req == PRU_DETACH && rp)
		rt_adjustcount(rp->rcb_proto.sp_protocol, -1);
	s = splsoftnet();

	/*
	 * Don't call raw_usrreq() in the attach case, because
	 * we want to allow non-privileged processes to listen on
	 * and send "safe" commands to the routing socket.
	 */
	if (req == PRU_ATTACH) {
		if (l == NULL)
			error = EACCES;
		else
			error = raw_attach(so, (int)(long)nam);
	} else
		error = raw_usrreq(so, req, m, nam, control, l);

	rp = sotorawcb(so);
	if (req == PRU_ATTACH && rp) {
		if (error) {
			free(rp, M_PCB);
			splx(s);
			return error;
		}
		rt_adjustcount(rp->rcb_proto.sp_protocol, 1);
		rp->rcb_laddr = &COMPATNAME(route_info).ri_src;
		rp->rcb_faddr = &COMPATNAME(route_info).ri_dst;
		soisconnected(so);
		so->so_options |= SO_USELOOPBACK;
	}
	splx(s);
	return error;
}

/*ARGSUSED*/
int
COMPATNAME(route_output)(struct mbuf *m, ...)
{
	struct sockproto proto = { .sp_family = PF_XROUTE, };
	struct rt_xmsghdr *rtm = NULL;
	struct rt_xmsghdr *old_rtm = NULL;
	struct rtentry *rt = NULL;
	struct rtentry *saved_nrt = NULL;
	struct rt_addrinfo info;
	int len, error = 0;
	struct ifnet *ifp = NULL;
	struct ifaddr *ifa = NULL;
	struct socket *so;
	va_list ap;
	sa_family_t family;

	va_start(ap, m);
	so = va_arg(ap, struct socket *);
	va_end(ap);

#define senderr(e) do { error = e; goto flush;} while (/*CONSTCOND*/ 0)
	if (m == NULL || ((m->m_len < sizeof(int32_t)) &&
	   (m = m_pullup(m, sizeof(int32_t))) == NULL))
		return ENOBUFS;
	if ((m->m_flags & M_PKTHDR) == 0)
		panic("%s", __func__);
	len = m->m_pkthdr.len;
	if (len < sizeof(*rtm) ||
	    len != mtod(m, struct rt_xmsghdr *)->rtm_msglen) {
		info.rti_info[RTAX_DST] = NULL;
		senderr(EINVAL);
	}
	R_Malloc(rtm, struct rt_xmsghdr *, len);
	if (rtm == NULL) {
		info.rti_info[RTAX_DST] = NULL;
		senderr(ENOBUFS);
	}
	m_copydata(m, 0, len, rtm);
	if (rtm->rtm_version != RTM_XVERSION) {
		info.rti_info[RTAX_DST] = NULL;
		senderr(EPROTONOSUPPORT);
	}
	rtm->rtm_pid = curproc->p_pid;
	memset(&info, 0, sizeof(info));
	info.rti_addrs = rtm->rtm_addrs;
	if (rt_xaddrs(rtm->rtm_type, (const char *)(rtm + 1), len + (char *)rtm,
	    &info)) {
		senderr(EINVAL);
	}
	info.rti_flags = rtm->rtm_flags;
#ifdef RTSOCK_DEBUG
	if (info.rti_info[RTAX_DST]->sa_family == AF_INET) {
		printf("%s: extracted info.rti_info[RTAX_DST] %s\n", __func__,
		    inet_ntoa(((const struct sockaddr_in *)
		    info.rti_info[RTAX_DST])->sin_addr));
	}
#endif /* RTSOCK_DEBUG */
	if (info.rti_info[RTAX_DST] == NULL ||
	    (info.rti_info[RTAX_DST]->sa_family >= AF_MAX)) {
		senderr(EINVAL);
	}
	if (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 (kauth_authorize_network(curlwp->l_cred, KAUTH_NETWORK_ROUTE,
	    0, rtm, NULL, NULL) != 0)
		senderr(EACCES);

	switch (rtm->rtm_type) {

	case RTM_ADD:
		if (info.rti_info[RTAX_GATEWAY] == NULL) {
			senderr(EINVAL);
		}
		error = rtrequest1(rtm->rtm_type, &info, &saved_nrt);
		if (error == 0 && saved_nrt) {
			rt_setmetrics(rtm->rtm_inits, rtm, saved_nrt);
			saved_nrt->rt_refcnt--;
		}
		break;

	case RTM_DELETE:
		error = rtrequest1(rtm->rtm_type, &info, &saved_nrt);
		if (error == 0) {
			(rt = saved_nrt)->rt_refcnt++;
			goto report;
		}
		break;

	case RTM_GET:
	case RTM_CHANGE:
	case RTM_LOCK:
                /* XXX This will mask info.rti_info[RTAX_DST] with
		 * info.rti_info[RTAX_NETMASK] before
                 * searching.  It did not used to do that.  --dyoung
		 */
		error = rtrequest1(RTM_GET, &info, &rt);
		if (error != 0)
			senderr(error);
		if (rtm->rtm_type != RTM_GET) {/* XXX: too grotty */
			if (memcmp(info.rti_info[RTAX_DST], rt_getkey(rt),
			    info.rti_info[RTAX_DST]->sa_len) != 0)
				senderr(ESRCH);
			if (info.rti_info[RTAX_NETMASK] == NULL &&
			    rt_mask(rt) != NULL)
				senderr(ETOOMANYREFS);
		}

		switch (rtm->rtm_type) {
		case RTM_GET:
		report:
			info.rti_info[RTAX_DST] = rt_getkey(rt);
			info.rti_info[RTAX_GATEWAY] = rt->rt_gateway;
			info.rti_info[RTAX_NETMASK] = rt_mask(rt);
			info.rti_info[RTAX_TAG] = rt_gettag(rt);
			if ((rtm->rtm_addrs & (RTA_IFP | RTA_IFA)) == 0)
				;
			else if ((ifp = rt->rt_ifp) != NULL) {
				const struct ifaddr *rtifa;
				info.rti_info[RTAX_IFP] = ifp->if_dl->ifa_addr;
                                /* rtifa used to be simply rt->rt_ifa.
                                 * If rt->rt_ifa != NULL, then
                                 * rt_get_ifa() != NULL.  So this
                                 * ought to still be safe. --dyoung
				 */
				rtifa = rt_get_ifa(rt);
				info.rti_info[RTAX_IFA] = rtifa->ifa_addr;
#ifdef RTSOCK_DEBUG
				if (info.rti_info[RTAX_IFA]->sa_family ==
				    AF_INET) {
					printf("%s: copying out RTAX_IFA %s ",
					    __func__, inet_ntoa(
					    ((const struct sockaddr_in *)
					    info.rti_info[RTAX_IFA])->sin_addr)
					    );
					printf("for info.rti_info[RTAX_DST] %s "
					    "ifa_getifa %p ifa_seqno %p\n",
					    inet_ntoa(
					    ((const struct sockaddr_in *)
					    info.rti_info[RTAX_DST])->sin_addr),
					    (void *)rtifa->ifa_getifa,
					    rtifa->ifa_seqno);
				}
#endif /* RTSOCK_DEBUG */
				if (ifp->if_flags & IFF_POINTOPOINT) {
					info.rti_info[RTAX_BRD] =
					    rtifa->ifa_dstaddr;
				} else
					info.rti_info[RTAX_BRD] = NULL;
				rtm->rtm_index = ifp->if_index;
			} else {
				info.rti_info[RTAX_IFP] = NULL;
				info.rti_info[RTAX_IFA] = NULL;
			}
			(void)rt_msg2(rtm->rtm_type, &info, NULL, NULL, &len);
			if (len > rtm->rtm_msglen) {
				old_rtm = rtm;
				R_Malloc(rtm, struct rt_xmsghdr *, len);
				if (rtm == NULL)
					senderr(ENOBUFS);
				(void)memcpy(rtm, old_rtm, old_rtm->rtm_msglen);
			}
			(void)rt_msg2(rtm->rtm_type, &info, rtm, NULL, 0);
			rtm->rtm_flags = rt->rt_flags;
			rtm_setmetrics(rt, rtm);
			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 ((error = rt_getifa(&info)) != 0)
				senderr(error);
			if (info.rti_info[RTAX_GATEWAY] &&
			    rt_setgate(rt, info.rti_info[RTAX_GATEWAY]))
				senderr(EDQUOT);
			if (info.rti_info[RTAX_TAG])
				rt_settag(rt, info.rti_info[RTAX_TAG]);
			/* 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 (info.rti_info[RTAX_IFP] &&
			    (ifa = ifa_ifwithnet(info.rti_info[RTAX_IFP])) &&
			    (ifp = ifa->ifa_ifp) && (info.rti_info[RTAX_IFA] ||
			    info.rti_info[RTAX_GATEWAY])) {
				if (info.rti_info[RTAX_IFA] == NULL ||
				    (ifa = ifa_ifwithaddr(
				    info.rti_info[RTAX_IFA])) == NULL)
					ifa = ifaof_ifpforaddr(
					    info.rti_info[RTAX_IFA] ?
					    info.rti_info[RTAX_IFA] :
					    info.rti_info[RTAX_GATEWAY], ifp);
			} else if ((info.rti_info[RTAX_IFA] &&
			    (ifa = ifa_ifwithaddr(info.rti_info[RTAX_IFA]))) ||
			    (info.rti_info[RTAX_GATEWAY] &&
			    (ifa = ifa_ifwithroute(rt->rt_flags,
			    rt_getkey(rt), info.rti_info[RTAX_GATEWAY])))) {
				ifp = ifa->ifa_ifp;
			}
			if (ifa) {
				struct ifaddr *oifa = rt->rt_ifa;
				if (oifa != ifa) {
					if (oifa && oifa->ifa_rtrequest) {
						oifa->ifa_rtrequest(RTM_DELETE,
						    rt, &info);
					}
					rt_replace_ifa(rt, ifa);
					rt->rt_ifp = ifp;
				}
			}
			if (ifp && rt->rt_ifp != ifp)
				rt->rt_ifp = ifp;
			rt_setmetrics(rtm->rtm_inits, rtm, rt);
			if (rt->rt_flags != info.rti_flags)
				rt->rt_flags = (info.rti_flags & ~PRESERVED_RTF)
				    | (rt->rt_flags & PRESERVED_RTF);
			if (rt->rt_ifa && rt->rt_ifa->ifa_rtrequest)
				rt->rt_ifa->ifa_rtrequest(RTM_ADD, rt, &info);
			/*FALLTHROUGH*/
		case RTM_LOCK:
			rt->rt_rmx.rmx_locks &= ~(rtm->rtm_inits);
			rt->rt_rmx.rmx_locks |=
			    (rtm->rtm_inits & rtm->rtm_rmx.rmx_locks);
			break;
		}
		break;

	default:
		senderr(EOPNOTSUPP);
	}

flush:
	if (rtm) {
		if (error)
			rtm->rtm_errno = error;
		else
			rtm->rtm_flags |= RTF_DONE;
	}
	family = info.rti_info[RTAX_DST] ? info.rti_info[RTAX_DST]->sa_family :
	    0;
	/* We cannot free old_rtm until we have stopped using the
	 * pointers in info, some of which may point to sockaddrs
	 * in old_rtm.
	 */
	if (old_rtm != NULL)
		Free(old_rtm);
	if (rt)
		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 (COMPATNAME(route_info).ri_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, 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 (rp)
		rp->rcb_proto.sp_family = 0; /* Avoid us */
	if (family)
		proto.sp_protocol = family;
	if (m)
		raw_input(m, &proto, &COMPATNAME(route_info).ri_src,
		    &COMPATNAME(route_info).ri_dst);
	if (rp)
		rp->rcb_proto.sp_family = PF_XROUTE;
    }
	return error;
}

static void
rt_setmetrics(int which, const struct rt_xmsghdr *in, struct rtentry *out)
{
#define metric(f, e) if (which & (f)) out->rt_rmx.e = in->rtm_rmx.e;
	metric(RTV_RPIPE, rmx_recvpipe);
	metric(RTV_SPIPE, rmx_sendpipe);
	metric(RTV_SSTHRESH, rmx_ssthresh);
	metric(RTV_RTT, rmx_rtt);
	metric(RTV_RTTVAR, rmx_rttvar);
	metric(RTV_HOPCOUNT, rmx_hopcount);
	metric(RTV_MTU, rmx_mtu);
	metric(RTV_EXPIRE, rmx_expire);
#undef metric
}

static void
rtm_setmetrics(const struct rtentry *in, struct rt_xmsghdr *out)
{
#define metric(e) out->rtm_rmx.e = in->rt_rmx.e;
	metric(rmx_recvpipe);
	metric(rmx_sendpipe);
	metric(rmx_ssthresh);
	metric(rmx_rtt);
	metric(rmx_rttvar);
	metric(rmx_hopcount);
	metric(rmx_mtu);
	metric(rmx_expire);
#undef metric
}

static int
rt_xaddrs(u_char rtmtype, const char *cp, const char *cplim,
    struct rt_addrinfo *rtinfo)
{
	const struct sockaddr *sa = NULL;	/* Quell compiler warning */
	int i;

	for (i = 0; i < RTAX_MAX && cp < cplim; i++) {
		if ((rtinfo->rti_addrs & (1 << i)) == 0)
			continue;
		rtinfo->rti_info[i] = sa = (const struct sockaddr *)cp;
		RT_XADVANCE(cp, sa);
	}

	/*
	 * Check for extra addresses specified, except RTM_GET asking
	 * for interface info.
	 */
	if (rtmtype == RTM_GET) {
		if (((rtinfo->rti_addrs &
		    (~((1 << RTAX_IFP) | (1 << RTAX_IFA)))) & (~0 << i)) != 0)
			return 1;
	} else if ((rtinfo->rti_addrs & (~0 << i)) != 0)
		return 1;
	/* Check for bad data length.  */
	if (cp != cplim) {
		if (i == RTAX_NETMASK + 1 && sa != NULL &&
		    cp - RT_XROUNDUP(sa->sa_len) + sa->sa_len == cplim)
			/*
			 * The last sockaddr was info.rti_info[RTAX_NETMASK].
			 * We accept this for now for the sake of old
			 * binaries or third party softwares.
			 */
			;
		else
			return 1;
	}
	return 0;
}

static int
rt_getlen(int type)
{
#ifndef COMPAT_RTSOCK
	CTASSERT(__alignof(struct ifa_msghdr) >= sizeof(uint64_t));
	CTASSERT(__alignof(struct if_msghdr) >= sizeof(uint64_t));
	CTASSERT(__alignof(struct if_announcemsghdr) >= sizeof(uint64_t));
	CTASSERT(__alignof(struct rt_msghdr) >= sizeof(uint64_t));
#endif

	switch (type) {
	case RTM_DELADDR:
	case RTM_NEWADDR:
	case RTM_CHGADDR:
		return sizeof(struct ifa_xmsghdr);

	case RTM_OOIFINFO:
#ifdef COMPAT_14
		return sizeof(struct if_msghdr14);
#else
#ifdef DIAGNOSTIC
		printf("RTM_OOIFINFO\n");
#endif
		return -1;
#endif
	case RTM_OIFINFO:
#ifdef COMPAT_50
		return sizeof(struct if_msghdr50);
#else
#ifdef DIAGNOSTIC
		printf("RTM_OIFINFO\n");
#endif
		return -1;
#endif

	case RTM_IFINFO:
		return sizeof(struct if_xmsghdr);

	case RTM_IFANNOUNCE:
	case RTM_IEEE80211:
		return sizeof(struct if_xannouncemsghdr);

	default:
		return sizeof(struct rt_xmsghdr);
	}
}


struct mbuf *
COMPATNAME(rt_msg1)(int type, struct rt_addrinfo *rtinfo, void *data, int datalen)
{
	struct rt_xmsghdr *rtm;
	struct mbuf *m;
	int i;
	const struct sockaddr *sa;
	int len, dlen;

	m = m_gethdr(M_DONTWAIT, MT_DATA);
	if (m == NULL)
		return m;
	MCLAIM(m, &COMPATNAME(routedomain).dom_mowner);

	if ((len = rt_getlen(type)) == -1)
		goto out;
	if (len > MHLEN + MLEN)
		panic("%s: message too long", __func__);
	else if (len > MHLEN) {
		m->m_next = m_get(M_DONTWAIT, MT_DATA);
		if (m->m_next == NULL)
			goto out;
		MCLAIM(m->m_next, m->m_owner);
		m->m_pkthdr.len = len;
		m->m_len = MHLEN;
		m->m_next->m_len = len - MHLEN;
	} else {
		m->m_pkthdr.len = m->m_len = len;
	}
	m->m_pkthdr.rcvif = NULL;
	m_copyback(m, 0, datalen, data);
	if (len > datalen)
		(void)memset(mtod(m, char *) + datalen, 0, len - datalen);
	rtm = mtod(m, struct rt_xmsghdr *);
	for (i = 0; i < RTAX_MAX; i++) {
		if ((sa = rtinfo->rti_info[i]) == NULL)
			continue;
		rtinfo->rti_addrs |= (1 << i);
		dlen = RT_XROUNDUP(sa->sa_len);
		m_copyback(m, len, sa->sa_len, sa);
		if (dlen != sa->sa_len) {
			/*
			 * Up to 6 + 1 nul's since roundup is to
			 * sizeof(uint64_t) (8 bytes)
			 */
			m_copyback(m, len + sa->sa_len,
			    dlen - sa->sa_len, "\0\0\0\0\0\0");
		}
		len += dlen;
	}
	if (m->m_pkthdr.len != len)
		goto out;
	rtm->rtm_msglen = len;
	rtm->rtm_version = RTM_XVERSION;
	rtm->rtm_type = type;
	return m;
out:
	m_freem(m);
	return NULL;
}

/*
 * rt_msg2
 *
 *	 fills 'cp' or 'w'.w_tmem with the routing socket message and
 *		returns the length of the message in 'lenp'.
 *
 * if walkarg is 0, cp is expected to be 0 or a buffer large enough to hold
 *	the message
 * otherwise walkarg's w_needed is updated and if the user buffer is
 *	specified and w_needed indicates space exists the information is copied
 *	into the temp space (w_tmem). w_tmem is [re]allocated if necessary,
 *	if the allocation fails ENOBUFS is returned.
 */
static int
rt_msg2(int type, struct rt_addrinfo *rtinfo, void *cpv, struct rt_walkarg *w,
	int *lenp)
{
	int i;
	int len, dlen, second_time = 0;
	char *cp0, *cp = cpv;

	rtinfo->rti_addrs = 0;
again:
	if ((len = rt_getlen(type)) == -1)
		return EINVAL;

	if ((cp0 = cp) != NULL)
		cp += len;
	for (i = 0; i < RTAX_MAX; i++) {
		const struct sockaddr *sa;

		if ((sa = rtinfo->rti_info[i]) == NULL)
			continue;
		rtinfo->rti_addrs |= (1 << i);
		dlen = RT_XROUNDUP(sa->sa_len);
		if (cp) {
			int diff = dlen - sa->sa_len;
			(void)memcpy(cp, sa, (size_t)sa->sa_len);
			cp += sa->sa_len;
			if (diff > 0) {
				(void)memset(cp, 0, (size_t)diff);
				cp += diff;
			}
		}
		len += dlen;
	}
	if (cp == NULL && w != NULL && !second_time) {
		struct rt_walkarg *rw = w;

		rw->w_needed += len;
		if (rw->w_needed <= 0 && rw->w_where) {
			if (rw->w_tmemsize < len) {
				if (rw->w_tmem)
					free(rw->w_tmem, M_RTABLE);
				rw->w_tmem = malloc(len, M_RTABLE, M_NOWAIT);
				if (rw->w_tmem)
					rw->w_tmemsize = len;
				else
					rw->w_tmemsize = 0;
			}
			if (rw->w_tmem) {
				cp = rw->w_tmem;
				second_time = 1;
				goto again;
			} else {
				rw->w_tmemneeded = len;
				return ENOBUFS;
			}
		}
	}
	if (cp) {
		struct rt_xmsghdr *rtm = (struct rt_xmsghdr *)cp0;

		rtm->rtm_version = RTM_XVERSION;
		rtm->rtm_type = type;
		rtm->rtm_msglen = len;
	}
	if (lenp)
		*lenp = len;
	return 0;
}

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

	COMPATCALL(rt_missmsg, (type, rtinfo, flags, error));
	if (COMPATNAME(route_info).ri_cb.any_count == 0)
		return;
	memset(&rtm, 0, sizeof(rtm));
	rtm.rtm_flags = RTF_DONE | flags;
	rtm.rtm_errno = error;
	m = COMPATNAME(rt_msg1)(type, &info, &rtm, sizeof(rtm));
	if (m == NULL)
		return;
	mtod(m, struct rt_xmsghdr *)->rtm_addrs = info.rti_addrs;
	COMPATNAME(route_enqueue)(m, sa ? sa->sa_family : 0);
}

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

	COMPATCALL(rt_ifmsg, (ifp));
	if (COMPATNAME(route_info).ri_cb.any_count == 0)
		return;
	(void)memset(&info, 0, sizeof(info));
	(void)memset(&ifm, 0, sizeof(ifm));
	ifm.ifm_index = ifp->if_index;
	ifm.ifm_flags = ifp->if_flags;
	ifm.ifm_data = ifp->if_data;
	ifm.ifm_addrs = 0;
	m = COMPATNAME(rt_msg1)(RTM_IFINFO, &info, &ifm, sizeof(ifm));
	if (m == NULL)
		return;
	COMPATNAME(route_enqueue)(m, 0);
#ifdef COMPAT_14
	compat_14_rt_oifmsg(ifp);
#endif
#ifdef COMPAT_50
	compat_50_rt_oifmsg(ifp);
#endif
}


/*
 * 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
COMPATNAME(rt_newaddrmsg)(int cmd, struct ifaddr *ifa, int error,
    struct rtentry *rt)
{
#define	cmdpass(__cmd, __pass)	(((__cmd) << 2) | (__pass))
	struct rt_addrinfo info;
	const struct sockaddr *sa;
	int pass;
	struct mbuf *m;
	struct ifnet *ifp;
	struct rt_xmsghdr rtm;
	struct ifa_xmsghdr ifam;
	int ncmd;

	KASSERT(ifa != NULL);
	ifp = ifa->ifa_ifp;
	COMPATCALL(rt_newaddrmsg, (cmd, ifa, error, rt));
	if (COMPATNAME(route_info).ri_cb.any_count == 0)
		return;
	for (pass = 1; pass < 3; pass++) {
		memset(&info, 0, sizeof(info));
		switch (cmdpass(cmd, pass)) {
		case cmdpass(RTM_ADD, 1):
		case cmdpass(RTM_CHANGE, 1):
		case cmdpass(RTM_DELETE, 2):
		case cmdpass(RTM_NEWADDR, 1):
		case cmdpass(RTM_DELADDR, 1):
		case cmdpass(RTM_CHGADDR, 1):
			switch (cmd) {
			case RTM_ADD:
				ncmd = RTM_NEWADDR;
				break;
			case RTM_DELETE:
				ncmd = RTM_DELADDR;
				break;
			case RTM_CHANGE:
				ncmd = RTM_CHGADDR;
				break;
			default:
				ncmd = cmd;
			}
			info.rti_info[RTAX_IFA] = sa = ifa->ifa_addr;
			KASSERT(ifp->if_dl != NULL);
			info.rti_info[RTAX_IFP] = ifp->if_dl->ifa_addr;
			info.rti_info[RTAX_NETMASK] = ifa->ifa_netmask;
			info.rti_info[RTAX_BRD] = ifa->ifa_dstaddr;
			memset(&ifam, 0, sizeof(ifam));
			ifam.ifam_index = ifp->if_index;
			ifam.ifam_metric = ifa->ifa_metric;
			ifam.ifam_flags = ifa->ifa_flags;
			m = COMPATNAME(rt_msg1)(ncmd, &info, &ifam, sizeof(ifam));
			if (m == NULL)
				continue;
			mtod(m, struct ifa_xmsghdr *)->ifam_addrs =
			    info.rti_addrs;
			break;
		case cmdpass(RTM_ADD, 2):
		case cmdpass(RTM_CHANGE, 2):
		case cmdpass(RTM_DELETE, 1):
			if (rt == NULL)
				continue;
			info.rti_info[RTAX_NETMASK] = rt_mask(rt);
			info.rti_info[RTAX_DST] = sa = rt_getkey(rt);
			info.rti_info[RTAX_GATEWAY] = rt->rt_gateway;
			memset(&rtm, 0, sizeof(rtm));
			rtm.rtm_index = ifp->if_index;
			rtm.rtm_flags |= rt->rt_flags;
			rtm.rtm_errno = error;
			m = COMPATNAME(rt_msg1)(cmd, &info, &rtm, sizeof(rtm));
			if (m == NULL)
				continue;
			mtod(m, struct rt_xmsghdr *)->rtm_addrs = info.rti_addrs;
			break;
		default:
			continue;
		}
#ifdef DIAGNOSTIC
		if (m == NULL)
			panic("%s: called with wrong command", __func__);
#endif
		COMPATNAME(route_enqueue)(m, sa ? sa->sa_family : 0);
	}
#undef cmdpass
}

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

	memset(info, 0, sizeof(*info));
	memset(&ifan, 0, sizeof(ifan));
	ifan.ifan_index = ifp->if_index;
	strlcpy(ifan.ifan_name, ifp->if_xname, sizeof(ifan.ifan_name));
	ifan.ifan_what = what;
	return COMPATNAME(rt_msg1)(type, info, &ifan, sizeof(ifan));
}

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

	COMPATCALL(rt_ifannouncemsg, (ifp, what));
	if (COMPATNAME(route_info).ri_cb.any_count == 0)
		return;
	m = rt_makeifannouncemsg(ifp, RTM_IFANNOUNCE, what, &info);
	if (m == NULL)
		return;
	COMPATNAME(route_enqueue)(m, 0);
}

/*
 * 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
COMPATNAME(rt_ieee80211msg)(struct ifnet *ifp, int what, void *data,
	size_t data_len)
{
	struct mbuf *m;
	struct rt_addrinfo info;

	COMPATCALL(rt_ieee80211msg, (ifp, what, data, data_len));
	if (COMPATNAME(route_info).ri_cb.any_count == 0)
		return;
	m = rt_makeifannouncemsg(ifp, RTM_IEEE80211, what, &info);
	if (m == NULL)
		return;
	/*
	 * 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;
		}
		(void)memcpy(mtod(n, void *), data, data_len);
		n->m_len = data_len;
		m->m_next = n;
	} else if (data_len > 0) {
		(void)memcpy(mtod(m, uint8_t *) + m->m_len, data, data_len);
		m->m_len += data_len;
	}
	if (m->m_flags & M_PKTHDR)
		m->m_pkthdr.len += data_len;
	mtod(m, struct if_xannouncemsghdr *)->ifan_msglen += data_len;
	COMPATNAME(route_enqueue)(m, 0);
}

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

	if (w->w_op == NET_RT_FLAGS && !(rt->rt_flags & w->w_arg))
		return 0;
	memset(&info, 0, sizeof(info));
	info.rti_info[RTAX_DST] = rt_getkey(rt);
	info.rti_info[RTAX_GATEWAY] = rt->rt_gateway;
	info.rti_info[RTAX_NETMASK] = rt_mask(rt);
	info.rti_info[RTAX_TAG] = rt_gettag(rt);
	if (rt->rt_ifp) {
		const struct ifaddr *rtifa;
		info.rti_info[RTAX_IFP] = rt->rt_ifp->if_dl->ifa_addr;
		/* rtifa used to be simply rt->rt_ifa.  If rt->rt_ifa != NULL,
		 * then rt_get_ifa() != NULL.  So this ought to still be safe.
		 * --dyoung
		 */
		rtifa = rt_get_ifa(rt);
		info.rti_info[RTAX_IFA] = rtifa->ifa_addr;
		if (rt->rt_ifp->if_flags & IFF_POINTOPOINT)
			info.rti_info[RTAX_BRD] = rtifa->ifa_dstaddr;
	}
	if ((error = rt_msg2(RTM_GET, &info, 0, w, &size)))
		return error;
	if (w->w_where && w->w_tmem && w->w_needed <= 0) {
		struct rt_xmsghdr *rtm = (struct rt_xmsghdr *)w->w_tmem;

		rtm->rtm_flags = rt->rt_flags;
		rtm->rtm_use = rt->rt_use;
		rtm_setmetrics(rt, rtm);
		KASSERT(rt->rt_ifp != NULL);
		rtm->rtm_index = rt->rt_ifp->if_index;
		rtm->rtm_errno = rtm->rtm_pid = rtm->rtm_seq = 0;
		rtm->rtm_addrs = info.rti_addrs;
		if ((error = copyout(rtm, w->w_where, size)) != 0)
			w->w_where = NULL;
		else
			w->w_where = (char *)w->w_where + size;
	}
	return error;
}

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

	memset(&info, 0, sizeof(info));
	IFNET_FOREACH(ifp) {
		if (w->w_arg && w->w_arg != ifp->if_index)
			continue;
		if (IFADDR_EMPTY(ifp))
			continue;
		info.rti_info[RTAX_IFP] = ifp->if_dl->ifa_addr;
		switch (type) {
		case NET_RT_IFLIST:
			error = rt_msg2(RTM_IFINFO, &info, NULL, w, &len);
			break;
#ifdef COMPAT_14
		case NET_RT_OOIFLIST:
			error = rt_msg2(RTM_OOIFINFO, &info, NULL, w, &len);
			break;
#endif
#ifdef COMPAT_50
		case NET_RT_OIFLIST:
			error = rt_msg2(RTM_OIFINFO, &info, NULL, w, &len);
			break;
#endif
		default:
			panic("sysctl_iflist(1)");
		}
		if (error)
			return error;
		info.rti_info[RTAX_IFP] = NULL;
		if (w->w_where && w->w_tmem && w->w_needed <= 0) {
			switch (type) {
			case NET_RT_IFLIST: {
				struct if_xmsghdr *ifm;

				ifm = (struct if_xmsghdr *)w->w_tmem;
				ifm->ifm_index = ifp->if_index;
				ifm->ifm_flags = ifp->if_flags;
				ifm->ifm_data = ifp->if_data;
				ifm->ifm_addrs = info.rti_addrs;
				error = copyout(ifm, w->w_where, len);
				if (error)
					return error;
				w->w_where = (char *)w->w_where + len;
				break;
			}

#ifdef COMPAT_14
			case NET_RT_OOIFLIST:
				error = compat_14_iflist(ifp, w, &info, len);
				if (error)
					return error;
				break;
#endif
#ifdef COMPAT_50
			case NET_RT_OIFLIST:
				error = compat_50_iflist(ifp, w, &info, len);
				if (error)
					return error;
				break;
#endif
			default:
				panic("sysctl_iflist(2)");
			}
		}
		IFADDR_FOREACH(ifa, ifp) {
			if (af && af != ifa->ifa_addr->sa_family)
				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;
			if ((error = rt_msg2(RTM_NEWADDR, &info, 0, w, &len)))
				return error;
			if (w->w_where && w->w_tmem && w->w_needed <= 0) {
				struct ifa_xmsghdr *ifam;

				ifam = (struct ifa_xmsghdr *)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 = copyout(w->w_tmem, w->w_where, len);
				if (error)
					return error;
				w->w_where = (char *)w->w_where + len;
			}
		}
		info.rti_info[RTAX_IFA] = info.rti_info[RTAX_NETMASK] =
		    info.rti_info[RTAX_BRD] = NULL;
	}
	return 0;
}

static int
sysctl_rtable(SYSCTLFN_ARGS)
{
	void 	*where = oldp;
	size_t	*given = oldlenp;
	const void *new = newp;
	int	i, s, error = EINVAL;
	u_char  af;
	struct	rt_walkarg w;

	if (namelen == 1 && name[0] == CTL_QUERY)
		return sysctl_query(SYSCTLFN_CALL(rnode));

	if (new)
		return EPERM;
	if (namelen != 3)
		return EINVAL;
	af = name[0];
	w.w_tmemneeded = 0;
	w.w_tmemsize = 0;
	w.w_tmem = NULL;
again:
	/* we may return here if a later [re]alloc of the t_mem buffer fails */
	if (w.w_tmemneeded) {
		w.w_tmem = malloc(w.w_tmemneeded, M_RTABLE, M_WAITOK);
		w.w_tmemsize = w.w_tmemneeded;
		w.w_tmemneeded = 0;
	}
	w.w_op = name[1];
	w.w_arg = name[2];
	w.w_given = *given;
	w.w_needed = 0 - w.w_given;
	w.w_where = where;

	s = splsoftnet();
	switch (w.w_op) {

	case NET_RT_DUMP:
	case NET_RT_FLAGS:
		for (i = 1; i <= AF_MAX; i++)
			if ((af == 0 || af == i) &&
			    (error = rt_walktree(i, sysctl_dumpentry, &w)))
				break;
		break;

#ifdef COMPAT_14
	case NET_RT_OOIFLIST:
		error = sysctl_iflist(af, &w, w.w_op);
		break;
#endif
#ifdef COMPAT_50
	case NET_RT_OIFLIST:
		error = sysctl_iflist(af, &w, w.w_op);
		break;
#endif
	case NET_RT_IFLIST:
		error = sysctl_iflist(af, &w, w.w_op);
		break;
	}
	splx(s);

	/* check to see if we couldn't allocate memory with NOWAIT */
	if (error == ENOBUFS && w.w_tmem == 0 && w.w_tmemneeded)
		goto again;

	if (w.w_tmem)
		free(w.w_tmem, M_RTABLE);
	w.w_needed += w.w_given;
	if (where) {
		*given = (char *)w.w_where - (char *)where;
		if (*given < w.w_needed)
			return ENOMEM;
	} else {
		*given = (11 * w.w_needed) / 10;
	}
	return error;
}

/*
 * Routing message software interrupt routine
 */
static void
COMPATNAME(route_intr)(void *cookie)
{
	struct sockproto proto = { .sp_family = PF_XROUTE, };
	struct route_info * const ri = &COMPATNAME(route_info);
	struct mbuf *m;
	int s;

	mutex_enter(softnet_lock);
	KERNEL_LOCK(1, NULL);
	while (!IF_IS_EMPTY(&ri->ri_intrq)) {
		s = splnet();
		IF_DEQUEUE(&ri->ri_intrq, m);
		splx(s);
		if (m == NULL)
			break;
		proto.sp_protocol = M_GETCTX(m, uintptr_t);
		raw_input(m, &proto, &ri->ri_src, &ri->ri_dst);
	}
	KERNEL_UNLOCK_ONE(NULL);
	mutex_exit(softnet_lock);
}

/*
 * Enqueue a message to the software interrupt routine.
 */
void
COMPATNAME(route_enqueue)(struct mbuf *m, int family)
{
	struct route_info * const ri = &COMPATNAME(route_info);
	int s, wasempty;

	s = splnet();
	if (IF_QFULL(&ri->ri_intrq)) {
		IF_DROP(&ri->ri_intrq);
		m_freem(m);
	} else {
		wasempty = IF_IS_EMPTY(&ri->ri_intrq);
		M_SETCTX(m, (uintptr_t)family);
		IF_ENQUEUE(&ri->ri_intrq, m);
		if (wasempty)
			softint_schedule(ri->ri_sih);
	}
	splx(s);
}

static void
COMPATNAME(route_init)(void)
{
	struct route_info * const ri = &COMPATNAME(route_info);

#ifndef COMPAT_RTSOCK
	rt_init();
#endif

	sysctl_net_route_setup(NULL);
	ri->ri_intrq.ifq_maxlen = ri->ri_maxqlen;
	ri->ri_sih = softint_establish(SOFTINT_NET | SOFTINT_MPSAFE,
	    COMPATNAME(route_intr), NULL);
}

/*
 * Definitions of protocols supported in the ROUTE domain.
 */
#ifndef COMPAT_RTSOCK
PR_WRAP_USRREQ(route_usrreq);
#else
PR_WRAP_USRREQ(compat_50_route_usrreq);
#endif

static const struct protosw COMPATNAME(route_protosw)[] = {
	{
		.pr_type = SOCK_RAW,
		.pr_domain = &COMPATNAME(routedomain),
		.pr_flags = PR_ATOMIC|PR_ADDR,
		.pr_input = raw_input,
		.pr_output = COMPATNAME(route_output),
		.pr_ctlinput = raw_ctlinput,
		.pr_usrreq = COMPATNAME(route_usrreq_wrapper),
		.pr_init = raw_init,
	},
};

struct domain COMPATNAME(routedomain) = {
	.dom_family = PF_XROUTE,
	.dom_name = DOMAINNAME,
	.dom_init = COMPATNAME(route_init),
	.dom_protosw = COMPATNAME(route_protosw),
	.dom_protoswNPROTOSW =
	    &COMPATNAME(route_protosw)[__arraycount(COMPATNAME(route_protosw))],
};

static void
sysctl_net_route_setup(struct sysctllog **clog)
{
	const struct sysctlnode *rnode = NULL;

	sysctl_createv(clog, 0, NULL, &rnode,
		       CTLFLAG_PERMANENT,
		       CTLTYPE_NODE, DOMAINNAME,
		       SYSCTL_DESCR("PF_ROUTE information"),
		       NULL, 0, NULL, 0,
		       CTL_NET, PF_XROUTE, CTL_EOL);

	sysctl_createv(clog, 0, NULL, NULL,
		       CTLFLAG_PERMANENT,
		       CTLTYPE_NODE, "rtable",
		       SYSCTL_DESCR("Routing table information"),
		       sysctl_rtable, 0, NULL, 0,
		       CTL_NET, PF_XROUTE, 0 /* any protocol */, CTL_EOL);

	sysctl_createv(clog, 0, &rnode, NULL,
		       CTLFLAG_PERMANENT,
		       CTLTYPE_STRUCT, "stats",
		       SYSCTL_DESCR("Routing statistics"),
		       NULL, 0, &rtstat, sizeof(rtstat),
		       CTL_CREATE, CTL_EOL);
}