summaryrefslogtreecommitdiff
path: root/sys/net/rtsock.c
blob: 1a94cba0eab67973fccc74e96329326ccb22553c (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
/*	$OpenBSD: rtsock.c,v 1.29 2003/06/24 09:09:25 itojun Exp $	*/
/*	$NetBSD: rtsock.c,v 1.18 1996/03/29 00:32:10 cgd 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	8.6 (Berkeley) 2/11/95
 */

#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 <uvm/uvm_extern.h>
#include <sys/sysctl.h>

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

#include <machine/stdarg.h>

struct	sockaddr route_dst = { 2, PF_ROUTE, };
struct	sockaddr route_src = { 2, PF_ROUTE, };
struct	sockproto route_proto = { PF_ROUTE, };

struct walkarg {
	int	w_op, w_arg, w_given, w_needed, w_tmemsize;
	caddr_t	w_where, w_tmem;
};

static struct mbuf *
		rt_msg1(int, struct rt_addrinfo *);
static int	rt_msg2(int,
		    struct rt_addrinfo *, caddr_t, struct walkarg *);
static void	rt_xaddrs(caddr_t, caddr_t, struct rt_addrinfo *);

/* Sleazy use of local variables throughout file, warning!!!! */
#define dst	info.rti_info[RTAX_DST]
#define gate	info.rti_info[RTAX_GATEWAY]
#define netmask	info.rti_info[RTAX_NETMASK]
#define genmask	info.rti_info[RTAX_GENMASK]
#define ifpaddr	info.rti_info[RTAX_IFP]
#define ifaaddr	info.rti_info[RTAX_IFA]
#define brdaddr	info.rti_info[RTAX_BRD]

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

	if (req == PRU_ATTACH) {
		MALLOC(rp, struct rawcb *, sizeof(*rp), M_PCB, M_WAITOK);
		so->so_pcb = rp;
		bzero(so->so_pcb, sizeof(*rp));
	}
	if (req == PRU_DETACH && rp) {
		int af = rp->rcb_proto.sp_protocol;
		if (af == AF_INET)
			route_cb.ip_count--;
		else if (af == AF_INET6)
			route_cb.ip6_count--;
		else if (af == AF_NS)
			route_cb.ns_count--;
		else if (af == AF_ISO)
			route_cb.iso_count--;
		route_cb.any_count--;
	}
	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 (curproc == 0)
			error = EACCES;
		else
			error = raw_attach(so, (int)(long)nam);
	} else
		error = raw_usrreq(so, req, m, nam, control);

	rp = sotorawcb(so);
	if (req == PRU_ATTACH && rp) {
		int af = rp->rcb_proto.sp_protocol;
		if (error) {
			free((caddr_t)rp, M_PCB);
			splx(s);
			return (error);
		}
		if (af == AF_INET)
			route_cb.ip_count++;
		else if (af == AF_INET6)
			route_cb.ip6_count++;
		else if (af == AF_NS)
			route_cb.ns_count++;
		else if (af == AF_ISO)
			route_cb.iso_count++;
		rp->rcb_faddr = &route_src;
		route_cb.any_count++;
		soisconnected(so);
		so->so_options |= SO_USELOOPBACK;
	}
	splx(s);
	return (error);
}

/*ARGSUSED*/
int
route_output(struct mbuf *m, ...)
{
	register struct rt_msghdr *rtm = 0;
	register struct radix_node *rn = 0;
	register struct rtentry *rt = 0;
	struct rtentry *saved_nrt = 0;
	struct radix_node_head *rnh;
	struct rt_addrinfo info;
	int len, error = 0;
	struct ifnet *ifp = 0;
	struct ifaddr *ifa = 0;
	struct socket *so;
	va_list ap;

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

#define senderr(e) do { error = e; goto flush;} while (0)
	if (m == 0 || ((m->m_len < sizeof(int32_t)) &&
		       (m = m_pullup(m, sizeof(int32_t))) == 0))
		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) {
		dst = 0;
		senderr(EINVAL);
	}
	R_Malloc(rtm, struct rt_msghdr *, len);
	if (rtm == 0) {
		dst = 0;
		senderr(ENOBUFS);
	}
	m_copydata(m, 0, len, (caddr_t)rtm);
	if (rtm->rtm_version != RTM_VERSION) {
		dst = 0;
		senderr(EPROTONOSUPPORT);
	}
	rtm->rtm_pid = curproc->p_pid;
	bzero(&info, sizeof(info));
	info.rti_addrs = rtm->rtm_addrs;
	rt_xaddrs((caddr_t)(rtm + 1), len + (caddr_t)rtm, &info);
	info.rti_flags = rtm->rtm_flags;
	if (dst == 0 || (dst->sa_family >= AF_MAX))
		senderr(EINVAL);
	if (gate != 0 && (gate->sa_family >= AF_MAX))
		senderr(EINVAL);
	if (genmask) {
		struct radix_node *t;
		t = rn_addmask((caddr_t)genmask, 0, 1);
		if (t && genmask->sa_len >= ((struct sockaddr *)t->rn_key)->sa_len &&
		    Bcmp((caddr_t *)genmask + 1, (caddr_t *)t->rn_key + 1,
		    ((struct sockaddr *)t->rn_key)->sa_len) - 1)
			genmask = (struct sockaddr *)(t->rn_key);
		else
			senderr(ENOBUFS);
	}

	/*
	 * 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 &&
	    suser(curproc->p_ucred, &curproc->p_acflag) != 0)
		senderr(EACCES);
	switch (rtm->rtm_type) {

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

	case RTM_ADD:
		if (gate == 0)
			senderr(EINVAL);
		error = rtrequest1(rtm->rtm_type, &info, &saved_nrt);
		if (error == 0 && saved_nrt) {
			rt_setmetrics(rtm->rtm_inits,
				&rtm->rtm_rmx, &saved_nrt->rt_rmx);
			saved_nrt->rt_refcnt--;
			saved_nrt->rt_genmask = genmask;
		}
		/* FALLTHROUGH */
	case RTM_GET:
	case RTM_CHANGE:
	case RTM_LOCK:
		if ((rnh = rt_tables[dst->sa_family]) == 0) {
			senderr(EAFNOSUPPORT);
		}
		rn = rnh->rnh_lookup(dst, netmask, rnh);
		if (rn == NULL || (rn->rn_flags & RNF_ROOT) != 0) {
			senderr(ESRCH);
		}
		rt = (struct rtentry *)rn;
		rt->rt_refcnt++;
		if (rtm->rtm_type != RTM_GET) {/* XXX: too grotty */
			struct radix_node *rn;
			extern struct radix_node_head *mask_rnhead;

			if (Bcmp(dst, rt_key(rt), dst->sa_len) != 0)
				senderr(ESRCH);
			if (netmask && (rn = rn_search(netmask,
					    mask_rnhead->rnh_treetop)))
				netmask = (struct sockaddr *)rn->rn_key;
			for (rn = rt->rt_nodes; rn; rn = rn->rn_dupedkey)
				if (netmask == (struct sockaddr *)rn->rn_mask)
					break;
			if (rn == 0)
				senderr(ETOOMANYREFS);
			rt = (struct rtentry *)rn;
		}

		switch (rtm->rtm_type) {

		case RTM_GET:
		report:
			dst = rt_key(rt);
			gate = rt->rt_gateway;
			netmask = rt_mask(rt);
			genmask = rt->rt_genmask;
			if (rtm->rtm_addrs & (RTA_IFP | RTA_IFA)) {
				if ((ifp = rt->rt_ifp) != NULL) {
					ifpaddr =
					    TAILQ_FIRST(&ifp->if_addrlist)->ifa_addr;
					ifaaddr = rt->rt_ifa->ifa_addr;
					if (ifp->if_flags & IFF_POINTOPOINT)
						brdaddr = rt->rt_ifa->ifa_dstaddr;
					else
						brdaddr = 0;
					rtm->rtm_index = ifp->if_index;
				} else {
					ifpaddr = 0;
					ifaaddr = 0;
				}
			}
			len = rt_msg2(rtm->rtm_type, &info, (caddr_t)0,
				(struct walkarg *)0);
			if (len > rtm->rtm_msglen) {
				struct rt_msghdr *new_rtm;
				R_Malloc(new_rtm, struct rt_msghdr *, len);
				if (new_rtm == 0)
					senderr(ENOBUFS);
				Bcopy(rtm, new_rtm, rtm->rtm_msglen);
				Free(rtm); rtm = new_rtm;
			}
			(void)rt_msg2(rtm->rtm_type, &info, (caddr_t)rtm,
				(struct walkarg *)0);
			rtm->rtm_flags = rt->rt_flags;
			rtm->rtm_rmx = rt->rt_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 ((error = rt_getifa(&info)) != 0)
				senderr(error);
			if (gate && rt_setgate(rt, rt_key(rt), gate))
				senderr(EDQUOT);
			if (ifpaddr && (ifa = ifa_ifwithnet(ifpaddr)) &&
			    (ifp = ifa->ifa_ifp) && (ifaaddr || gate))
				ifa = ifaof_ifpforaddr(ifaaddr ? ifaaddr : gate,
							ifp);
			else if ((ifaaddr && (ifa = ifa_ifwithaddr(ifaaddr))) ||
				 (gate && (ifa = ifa_ifwithroute(rt->rt_flags,
							rt_key(rt), gate))))
				ifp = ifa->ifa_ifp;
			if (ifa) {
				register struct ifaddr *oifa = rt->rt_ifa;
				if (oifa != ifa) {
				    if (oifa && oifa->ifa_rtrequest)
					oifa->ifa_rtrequest(RTM_DELETE, rt,
					    &info);
				    IFAFREE(rt->rt_ifa);
				    rt->rt_ifa = ifa;
				    ifa->ifa_refcnt++;
				    rt->rt_ifp = ifp;
				}
			}
			rt_setmetrics(rtm->rtm_inits, &rtm->rtm_rmx,
					&rt->rt_rmx);
			if (rt->rt_ifa && rt->rt_ifa->ifa_rtrequest)
			       rt->rt_ifa->ifa_rtrequest(RTM_ADD, rt, &info);
			if (genmask)
				rt->rt_genmask = genmask;
			/*
			 * Fall into
			 */
		case RTM_ADD:
		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;
	}
	if (rt)
		rtfree(rt);
    {
	register struct rawcb *rp = 0;
	/*
	 * 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 (rp)
		rp->rcb_proto.sp_family = 0; /* Avoid us */
	if (dst)
		route_proto.sp_protocol = dst->sa_family;
	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)
		raw_input(m, &route_proto, &route_src, &route_dst);
	if (rp)
		rp->rcb_proto.sp_family = PF_ROUTE;
    }
	return (error);
}

void
rt_setmetrics(which, in, out)
	u_long which;
	register struct rt_metrics *in, *out;
{
#define metric(f, e) if (which & (f)) out->e = in->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
}

#define ROUNDUP(a) \
	((a) > 0 ? (1 + (((a) - 1) | (sizeof(long) - 1))) : sizeof(long))
#define ADVANCE(x, n) (x += ROUNDUP((n)->sa_len))

static void
rt_xaddrs(cp, cplim, rtinfo)
	register caddr_t cp, cplim;
	register struct rt_addrinfo *rtinfo;
{
	register struct sockaddr *sa;
	register int i;

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

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

	switch (type) {

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

	case RTM_IFINFO:
		len = sizeof(struct if_msghdr);
		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 == 0)
		return (m);
	m->m_pkthdr.len = m->m_len = len;
	m->m_pkthdr.rcvif = 0;
	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 = ROUNDUP(sa->sa_len);
		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(type, rtinfo, cp, w)
	int type;
	register struct rt_addrinfo *rtinfo;
	caddr_t cp;
	struct walkarg *w;
{
	register 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:
		len = sizeof(struct if_msghdr);
		break;

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

		if ((sa = rtinfo->rti_info[i]) == 0)
			continue;
		rtinfo->rti_addrs |= (1 << i);
		dlen = ROUNDUP(sa->sa_len);
		if (cp) {
			bcopy((caddr_t)sa, cp, (unsigned)dlen);
			cp += dlen;
		}
		len += dlen;
	}
	if (cp == 0 && w != NULL && !second_time) {
		register struct 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 = (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;
			} else
				rw->w_where = 0;
		}
	}
	if (cp) {
		register 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 occurred, a routing lookup
 * has failed, or that a protocol has detected timeouts to a particular
 * destination.
 */
void
rt_missmsg(type, rtinfo, flags, error)
	int type, flags, error;
	register struct rt_addrinfo *rtinfo;
{
	register struct rt_msghdr *rtm;
	register 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 == 0)
		return;
	rtm = mtod(m, struct rt_msghdr *);
	rtm->rtm_flags = RTF_DONE | flags;
	rtm->rtm_errno = error;
	rtm->rtm_addrs = rtinfo->rti_addrs;
	route_proto.sp_protocol = sa ? sa->sa_family : 0;
	raw_input(m, &route_proto, &route_src, &route_dst);
}

/*
 * 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(ifp)
	register struct ifnet *ifp;
{
	register 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 == 0)
		return;
	ifm = mtod(m, struct if_msghdr *);
	ifm->ifm_index = ifp->if_index;
	ifm->ifm_flags = ifp->if_flags;
	ifm->ifm_data = ifp->if_data;
	ifm->ifm_addrs = 0;
	route_proto.sp_protocol = 0;
	raw_input(m, &route_proto, &route_src, &route_dst);
}

/*
 * 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(cmd, ifa, error, rt)
	int cmd, error;
	register struct ifaddr *ifa;
	register struct rtentry *rt;
{
	struct rt_addrinfo info;
	struct sockaddr *sa = NULL;
	int pass;
	struct mbuf *m = NULL;
	struct ifnet *ifp = ifa->ifa_ifp;

	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)) {
			register struct ifa_msghdr *ifam;
			int ncmd = cmd == RTM_ADD ? RTM_NEWADDR : RTM_DELADDR;

			ifaaddr = sa = ifa->ifa_addr;
			ifpaddr = TAILQ_FIRST(&ifp->if_addrlist)->ifa_addr;
			netmask = ifa->ifa_netmask;
			brdaddr = 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)) {
			register struct rt_msghdr *rtm;
			
			if (rt == 0)
				continue;
			netmask = rt_mask(rt);
			dst = sa = rt_key(rt);
			gate = 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;
		}
		route_proto.sp_protocol = sa ? sa->sa_family : 0;
		raw_input(m, &route_proto, &route_src, &route_dst);
	}
}

/*
 * This is used in dumping the kernel table via sysctl().
 */
int
sysctl_dumpentry(rn, v)
	struct radix_node *rn;
	register void *v;
{
	register struct walkarg *w = v;
	register 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;
	bzero((caddr_t)&info, sizeof(info));
	dst = rt_key(rt);
	gate = rt->rt_gateway;
	netmask = rt_mask(rt);
	genmask = rt->rt_genmask;
	if (rt->rt_ifp) {
		ifpaddr = TAILQ_FIRST(&rt->rt_ifp->if_addrlist)->ifa_addr;
		ifaaddr = rt->rt_ifa->ifa_addr;
		if (rt->rt_ifp->if_flags & IFF_POINTOPOINT)
			brdaddr = rt->rt_ifa->ifa_dstaddr;
	}
	size = rt_msg2(RTM_GET, &info, 0, w);
	if (w->w_where && w->w_tmem && w->w_needed <= 0) {
		register struct rt_msghdr *rtm = (struct rt_msghdr *)w->w_tmem;

		rtm->rtm_flags = rt->rt_flags;
		rtm->rtm_use = rt->rt_use;
		rtm->rtm_rmx = rt->rt_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;
		if ((error = copyout((caddr_t)rtm, w->w_where, size)) != 0)
			w->w_where = NULL;
		else
			w->w_where += size;
	}
	return (error);
}

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

	bzero((caddr_t)&info, sizeof(info));
	TAILQ_FOREACH(ifp, &ifnet, if_list) {
		if (w->w_arg && w->w_arg != ifp->if_index)
			continue;
		ifa = TAILQ_FIRST(&ifp->if_addrlist);
		if (!ifa)
			continue;
		ifpaddr = ifa->ifa_addr;
		len = rt_msg2(RTM_IFINFO, &info, (caddr_t)0, w);
		ifpaddr = 0;
		if (w->w_where && w->w_tmem && w->w_needed <= 0) {
			register struct if_msghdr *ifm;

			ifm = (struct if_msghdr *)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((caddr_t)ifm, w->w_where, len);
			if (error)
				return (error);
			w->w_where += len;
		}
		while ((ifa = TAILQ_NEXT(ifa, ifa_list)) !=
		    TAILQ_END(&ifp->if_addrlist)) {
			if (af && af != ifa->ifa_addr->sa_family)
				continue;
			ifaaddr = ifa->ifa_addr;
			netmask = ifa->ifa_netmask;
			brdaddr = ifa->ifa_dstaddr;
			len = rt_msg2(RTM_NEWADDR, &info, 0, w);
			if (w->w_where && w->w_tmem && w->w_needed <= 0) {
				register 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 = copyout(w->w_tmem, w->w_where, len);
				if (error)
					return (error);
				w->w_where += len;
			}
		}
		ifaaddr = netmask = brdaddr = 0;
	}
	return (0);
}

int
sysctl_rtable(name, namelen, where, given, new, newlen)
	int	*name;
	u_int	namelen;
	void 	*where;
	size_t	*given;
	void	*new;
	size_t	newlen;
{
	register struct radix_node_head *rnh;
	int	i, s, error = EINVAL;
	u_char  af;
	struct	walkarg w;

	if (new)
		return (EPERM);
	if (namelen != 3)
		return (EINVAL);
	af = name[0];
	Bzero(&w, sizeof(w));
	w.w_where = where;
	w.w_given = *given;
	w.w_needed = 0 - w.w_given;
	w.w_op = name[1];
	w.w_arg = name[2];

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

	case NET_RT_DUMP:
	case NET_RT_FLAGS:
		for (i = 1; i <= AF_MAX; i++)
			if ((rnh = rt_tables[i]) && (af == 0 || af == i) &&
			    (error = (*rnh->rnh_walktree)(rnh,
							  sysctl_dumpentry,
							  &w)))
				break;
		break;

	case NET_RT_IFLIST:
		error = sysctl_iflist(af, &w);
	}
	splx(s);
	if (w.w_tmem)
		free(w.w_tmem, M_RTABLE);
	w.w_needed += w.w_given;
	if (where) {
		*given = w.w_where - (caddr_t) where;
		if (*given < w.w_needed)
			return (ENOMEM);
	} else {
		*given = (11 * w.w_needed) / 10;
	}
	return (error);
}

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

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

struct protosw routesw[] = {
{ SOCK_RAW,	&routedomain,	0,		PR_ATOMIC|PR_ADDR,
  raw_input,	route_output,	raw_ctlinput,	0,
  route_usrreq,
  raw_init,	0,		0,		0,
  sysctl_rtable,
}
};

struct domain routedomain =
    { PF_ROUTE, "route", route_init, 0, 0,
      routesw, &routesw[sizeof(routesw)/sizeof(routesw[0])] };