/
rtsock.c
2073 lines (1855 loc) · 50.3 KB
/
rtsock.c
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
/* $OpenBSD: rtsock.c,v 1.283 2019/02/08 16:52:54 bluhm 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/sysctl.h>
#include <sys/mbuf.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/domain.h>
#include <sys/protosw.h>
#include <sys/srp.h>
#include <net/if.h>
#include <net/if_dl.h>
#include <net/if_var.h>
#include <net/route.h>
#include <netinet/in.h>
#ifdef MPLS
#include <netmpls/mpls.h>
#endif
#ifdef IPSEC
#include <netinet/ip_ipsp.h>
#include <net/if_enc.h>
#endif
#ifdef BFD
#include <net/bfd.h>
#endif
#include <sys/stdarg.h>
#include <sys/kernel.h>
#include <sys/timeout.h>
#define ROUTESNDQ 8192
#define ROUTERCVQ 8192
const struct sockaddr route_src = { 2, PF_ROUTE, };
struct walkarg {
int w_op, w_arg, w_given, w_needed, w_tmemsize;
caddr_t w_where, w_tmem;
};
void route_prinit(void);
void rcb_ref(void *, void *);
void rcb_unref(void *, void *);
int route_output(struct mbuf *, struct socket *, struct sockaddr *,
struct mbuf *);
int route_ctloutput(int, struct socket *, int, int, struct mbuf *);
int route_usrreq(struct socket *, int, struct mbuf *, struct mbuf *,
struct mbuf *, struct proc *);
void route_input(struct mbuf *m0, struct socket *, sa_family_t);
int route_arp_conflict(struct rtentry *, struct rt_addrinfo *);
int route_cleargateway(struct rtentry *, void *, unsigned int);
void rtm_senddesync_timer(void *);
void rtm_senddesync(struct socket *);
int rtm_sendup(struct socket *, struct mbuf *, int);
int rtm_getifa(struct rt_addrinfo *, unsigned int);
int rtm_output(struct rt_msghdr *, struct rtentry **, struct rt_addrinfo *,
uint8_t, unsigned int);
struct rt_msghdr *rtm_report(struct rtentry *, u_char, int, int);
struct mbuf *rtm_msg1(int, struct rt_addrinfo *);
int rtm_msg2(int, int, struct rt_addrinfo *, caddr_t,
struct walkarg *);
void rtm_xaddrs(caddr_t, caddr_t, struct rt_addrinfo *);
int rtm_validate_proposal(struct rt_addrinfo *);
void rtm_setmetrics(u_long, const struct rt_metrics *,
struct rt_kmetrics *);
void rtm_getmetrics(const struct rt_kmetrics *,
struct rt_metrics *);
int sysctl_iflist(int, struct walkarg *);
int sysctl_ifnames(struct walkarg *);
int sysctl_rtable_rtstat(void *, size_t *, void *);
struct rtpcb {
struct socket *rop_socket;
SRPL_ENTRY(rtpcb) rop_list;
struct refcnt rop_refcnt;
struct timeout rop_timeout;
unsigned int rop_msgfilter;
unsigned int rop_flags;
u_int rop_rtableid;
unsigned short rop_proto;
u_char rop_priority;
};
#define sotortpcb(so) ((struct rtpcb *)(so)->so_pcb)
struct rtptable {
SRPL_HEAD(, rtpcb) rtp_list;
struct srpl_rc rtp_rc;
struct rwlock rtp_lk;
unsigned int rtp_count;
};
struct rtptable rtptable;
/*
* These flags and timeout are used for indicating to userland (via a
* RTM_DESYNC msg) when the route socket has overflowed and messages
* have been lost.
*/
#define ROUTECB_FLAG_DESYNC 0x1 /* Route socket out of memory */
#define ROUTECB_FLAG_FLUSH 0x2 /* Wait until socket is empty before
queueing more packets */
#define ROUTE_DESYNC_RESEND_TIMEOUT 200 /* In ms */
void
route_prinit(void)
{
srpl_rc_init(&rtptable.rtp_rc, rcb_ref, rcb_unref, NULL);
rw_init(&rtptable.rtp_lk, "rtsock");
SRPL_INIT(&rtptable.rtp_list);
}
void
rcb_ref(void *null, void *v)
{
struct rtpcb *rop = v;
refcnt_take(&rop->rop_refcnt);
}
void
rcb_unref(void *null, void *v)
{
struct rtpcb *rop = v;
refcnt_rele_wake(&rop->rop_refcnt);
}
int
route_usrreq(struct socket *so, int req, struct mbuf *m, struct mbuf *nam,
struct mbuf *control, struct proc *p)
{
struct rtpcb *rop;
int error = 0;
if (req == PRU_CONTROL)
return (EOPNOTSUPP);
soassertlocked(so);
if (control && control->m_len) {
error = EOPNOTSUPP;
goto release;
}
rop = sotortpcb(so);
if (rop == NULL) {
error = EINVAL;
goto release;
}
switch (req) {
/* no connect, bind, accept. Socket is connected from the start */
case PRU_CONNECT:
case PRU_BIND:
case PRU_CONNECT2:
case PRU_LISTEN:
case PRU_ACCEPT:
error = EOPNOTSUPP;
break;
case PRU_DISCONNECT:
case PRU_ABORT:
soisdisconnected(so);
break;
case PRU_SHUTDOWN:
socantsendmore(so);
break;
case PRU_SENSE:
/* stat: don't bother with a blocksize. */
break;
/* minimal support, just implement a fake peer address */
case PRU_SOCKADDR:
error = EINVAL;
break;
case PRU_PEERADDR:
bcopy(&route_src, mtod(nam, caddr_t), route_src.sa_len);
nam->m_len = route_src.sa_len;
break;
case PRU_RCVD:
/*
* If we are in a FLUSH state, check if the buffer is
* empty so that we can clear the flag.
*/
if (((rop->rop_flags & ROUTECB_FLAG_FLUSH) != 0) &&
((sbspace(rop->rop_socket, &rop->rop_socket->so_rcv) ==
rop->rop_socket->so_rcv.sb_hiwat)))
rop->rop_flags &= ~ROUTECB_FLAG_FLUSH;
break;
case PRU_RCVOOB:
case PRU_SENDOOB:
error = EOPNOTSUPP;
break;
case PRU_SEND:
if (nam) {
error = EISCONN;
break;
}
error = (*so->so_proto->pr_output)(m, so, NULL, NULL);
m = NULL;
break;
default:
panic("route_usrreq");
}
release:
if (req != PRU_RCVD && req != PRU_RCVOOB && req != PRU_SENSE) {
m_freem(control);
m_freem(m);
}
return (error);
}
int
route_attach(struct socket *so, int proto)
{
struct rtpcb *rop;
int error;
/*
* use the rawcb but allocate a rtpcb, this
* code does not care about the additional fields
* and works directly on the raw socket.
*/
rop = malloc(sizeof(struct rtpcb), M_PCB, M_WAITOK|M_ZERO);
so->so_pcb = rop;
/* Init the timeout structure */
timeout_set(&rop->rop_timeout, rtm_senddesync_timer, so);
refcnt_init(&rop->rop_refcnt);
if (curproc == NULL)
error = EACCES;
else
error = soreserve(so, ROUTESNDQ, ROUTERCVQ);
if (error) {
free(rop, M_PCB, sizeof(struct rtpcb));
return (error);
}
rop->rop_socket = so;
rop->rop_proto = proto;
rop->rop_rtableid = curproc->p_p->ps_rtableid;
soisconnected(so);
so->so_options |= SO_USELOOPBACK;
rw_enter(&rtptable.rtp_lk, RW_WRITE);
SRPL_INSERT_HEAD_LOCKED(&rtptable.rtp_rc, &rtptable.rtp_list, rop, rop_list);
rtptable.rtp_count++;
rw_exit(&rtptable.rtp_lk);
return (0);
}
int
route_detach(struct socket *so)
{
struct rtpcb *rop;
soassertlocked(so);
rop = sotortpcb(so);
if (rop == NULL)
return (EINVAL);
rw_enter(&rtptable.rtp_lk, RW_WRITE);
timeout_del(&rop->rop_timeout);
rtptable.rtp_count--;
SRPL_REMOVE_LOCKED(&rtptable.rtp_rc, &rtptable.rtp_list, rop, rtpcb,
rop_list);
rw_exit(&rtptable.rtp_lk);
/* wait for all references to drop */
refcnt_finalize(&rop->rop_refcnt, "rtsockrefs");
so->so_pcb = NULL;
KASSERT((so->so_state & SS_NOFDREF) == 0);
free(rop, M_PCB, sizeof(struct rtpcb));
return (0);
}
int
route_ctloutput(int op, struct socket *so, int level, int optname,
struct mbuf *m)
{
struct rtpcb *rop = sotortpcb(so);
int error = 0;
unsigned int tid, prio;
if (level != AF_ROUTE)
return (EINVAL);
switch (op) {
case PRCO_SETOPT:
switch (optname) {
case ROUTE_MSGFILTER:
if (m == NULL || m->m_len != sizeof(unsigned int))
error = EINVAL;
else
rop->rop_msgfilter = *mtod(m, unsigned int *);
break;
case ROUTE_TABLEFILTER:
if (m == NULL || m->m_len != sizeof(unsigned int)) {
error = EINVAL;
break;
}
tid = *mtod(m, unsigned int *);
if (tid != RTABLE_ANY && !rtable_exists(tid))
error = ENOENT;
else
rop->rop_rtableid = tid;
break;
case ROUTE_PRIOFILTER:
if (m == NULL || m->m_len != sizeof(unsigned int)) {
error = EINVAL;
break;
}
prio = *mtod(m, unsigned int *);
if (prio > RTP_MAX)
error = EINVAL;
else
rop->rop_priority = prio;
break;
default:
error = ENOPROTOOPT;
break;
}
break;
case PRCO_GETOPT:
switch (optname) {
case ROUTE_MSGFILTER:
m->m_len = sizeof(unsigned int);
*mtod(m, unsigned int *) = rop->rop_msgfilter;
break;
case ROUTE_TABLEFILTER:
m->m_len = sizeof(unsigned int);
*mtod(m, unsigned int *) = rop->rop_rtableid;
break;
case ROUTE_PRIOFILTER:
m->m_len = sizeof(unsigned int);
*mtod(m, unsigned int *) = rop->rop_priority;
break;
default:
error = ENOPROTOOPT;
break;
}
}
return (error);
}
void
rtm_senddesync_timer(void *xso)
{
struct socket *so = xso;
int s;
s = solock(so);
rtm_senddesync(so);
sounlock(so, s);
}
void
rtm_senddesync(struct socket *so)
{
struct rtpcb *rop = sotortpcb(so);
struct mbuf *desync_mbuf;
soassertlocked(so);
/* If we are in a DESYNC state, try to send a RTM_DESYNC packet */
if ((rop->rop_flags & ROUTECB_FLAG_DESYNC) == 0)
return;
/*
* If we fail to alloc memory or if sbappendaddr()
* fails, re-add timeout and try again.
*/
desync_mbuf = rtm_msg1(RTM_DESYNC, NULL);
if (desync_mbuf != NULL) {
if (sbappendaddr(so, &so->so_rcv, &route_src,
desync_mbuf, NULL) != 0) {
rop->rop_flags &= ~ROUTECB_FLAG_DESYNC;
sorwakeup(rop->rop_socket);
return;
}
m_freem(desync_mbuf);
}
/* Re-add timeout to try sending msg again */
timeout_add_msec(&rop->rop_timeout, ROUTE_DESYNC_RESEND_TIMEOUT);
}
void
route_input(struct mbuf *m0, struct socket *so0, sa_family_t sa_family)
{
struct socket *so;
struct rtpcb *rop;
struct rt_msghdr *rtm;
struct mbuf *m = m0;
struct socket *last = NULL;
struct srp_ref sr;
int s;
/* ensure that we can access the rtm_type via mtod() */
if (m->m_len < offsetof(struct rt_msghdr, rtm_type) + 1) {
m_freem(m);
return;
}
SRPL_FOREACH(rop, &sr, &rtptable.rtp_list, rop_list) {
/*
* If route socket is bound to an address family only send
* messages that match the address family. Address family
* agnostic messages are always sent.
*/
if (sa_family != AF_UNSPEC && rop->rop_proto != AF_UNSPEC &&
rop->rop_proto != sa_family)
continue;
so = rop->rop_socket;
s = solock(so);
/*
* Check to see if we don't want our own messages and
* if we can receive anything.
*/
if ((so0 == so && !(so0->so_options & SO_USELOOPBACK)) ||
!(so->so_state & SS_ISCONNECTED) ||
(so->so_state & SS_CANTRCVMORE)) {
next:
sounlock(so, s);
continue;
}
/* filter messages that the process does not want */
rtm = mtod(m, struct rt_msghdr *);
/* but RTM_DESYNC can't be filtered */
if (rtm->rtm_type != RTM_DESYNC && rop->rop_msgfilter != 0 &&
!(rop->rop_msgfilter & (1 << rtm->rtm_type)))
goto next;
switch (rtm->rtm_type) {
case RTM_IFANNOUNCE:
case RTM_DESYNC:
/* no tableid */
break;
case RTM_RESOLVE:
case RTM_NEWADDR:
case RTM_DELADDR:
case RTM_IFINFO:
case RTM_80211INFO:
case RTM_BFD:
/* check against rdomain id */
if (rop->rop_rtableid != RTABLE_ANY &&
rtable_l2(rop->rop_rtableid) != rtm->rtm_tableid)
goto next;
break;
default:
if (rop->rop_priority != 0 &&
rop->rop_priority < rtm->rtm_priority)
goto next;
/* check against rtable id */
if (rop->rop_rtableid != RTABLE_ANY &&
rop->rop_rtableid != rtm->rtm_tableid)
goto next;
break;
}
/*
* Check to see if the flush flag is set. If so, don't queue
* any more messages until the flag is cleared.
*/
if ((rop->rop_flags & ROUTECB_FLAG_FLUSH) != 0)
goto next;
sounlock(so, s);
if (last) {
s = solock(last);
rtm_sendup(last, m, 1);
sounlock(last, s);
refcnt_rele_wake(&sotortpcb(last)->rop_refcnt);
}
/* keep a reference for last */
refcnt_take(&rop->rop_refcnt);
last = rop->rop_socket;
}
SRPL_LEAVE(&sr);
if (last) {
s = solock(last);
rtm_sendup(last, m, 0);
sounlock(last, s);
refcnt_rele_wake(&sotortpcb(last)->rop_refcnt);
} else
m_freem(m);
}
int
rtm_sendup(struct socket *so, struct mbuf *m0, int more)
{
struct rtpcb *rop = sotortpcb(so);
struct mbuf *m;
soassertlocked(so);
if (more) {
m = m_copym(m0, 0, M_COPYALL, M_NOWAIT);
if (m == NULL)
return (ENOMEM);
} else
m = m0;
if (sbspace(so, &so->so_rcv) < (2 * MSIZE) ||
sbappendaddr(so, &so->so_rcv, &route_src, m, NULL) == 0) {
/* Flag socket as desync'ed and flush required */
rop->rop_flags |= ROUTECB_FLAG_DESYNC | ROUTECB_FLAG_FLUSH;
rtm_senddesync(so);
m_freem(m);
return (ENOBUFS);
}
sorwakeup(so);
return (0);
}
struct rt_msghdr *
rtm_report(struct rtentry *rt, u_char type, int seq, int tableid)
{
struct rt_msghdr *rtm;
struct rt_addrinfo info;
struct sockaddr_rtlabel sa_rl;
struct sockaddr_in6 sa_mask;
#ifdef BFD
struct sockaddr_bfd sa_bfd;
#endif
struct ifnet *ifp = NULL;
int len;
bzero(&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_plen2mask(rt, &sa_mask);
info.rti_info[RTAX_LABEL] = rtlabel_id2sa(rt->rt_labelid, &sa_rl);
#ifdef BFD
if (rt->rt_flags & RTF_BFD)
info.rti_info[RTAX_BFD] = bfd2sa(rt, &sa_bfd);
#endif
#ifdef MPLS
if (rt->rt_flags & RTF_MPLS) {
struct sockaddr_mpls sa_mpls;
bzero(&sa_mpls, sizeof(sa_mpls));
sa_mpls.smpls_family = AF_MPLS;
sa_mpls.smpls_len = sizeof(sa_mpls);
sa_mpls.smpls_label = ((struct rt_mpls *)
rt->rt_llinfo)->mpls_label;
info.rti_info[RTAX_SRC] = (struct sockaddr *)&sa_mpls;
info.rti_mpls = ((struct rt_mpls *)
rt->rt_llinfo)->mpls_operation;
}
#endif
ifp = if_get(rt->rt_ifidx);
if (ifp != NULL) {
info.rti_info[RTAX_IFP] = sdltosa(ifp->if_sadl);
info.rti_info[RTAX_IFA] = rt->rt_ifa->ifa_addr;
if (ifp->if_flags & IFF_POINTOPOINT)
info.rti_info[RTAX_BRD] = rt->rt_ifa->ifa_dstaddr;
}
if_put(ifp);
/* RTAX_GENMASK, RTAX_AUTHOR, RTAX_SRCMASK ignored */
/* build new route message */
len = rtm_msg2(type, RTM_VERSION, &info, NULL, NULL);
rtm = malloc(len, M_RTABLE, M_WAITOK | M_ZERO);
rtm_msg2(type, RTM_VERSION, &info, (caddr_t)rtm, NULL);
rtm->rtm_type = type;
rtm->rtm_index = rt->rt_ifidx;
rtm->rtm_tableid = tableid;
rtm->rtm_priority = rt->rt_priority & RTP_MASK;
rtm->rtm_flags = rt->rt_flags;
rtm->rtm_pid = curproc->p_p->ps_pid;
rtm->rtm_seq = seq;
rtm_getmetrics(&rt->rt_rmx, &rtm->rtm_rmx);
rtm->rtm_addrs = info.rti_addrs;
#ifdef MPLS
rtm->rtm_mpls = info.rti_mpls;
#endif
return rtm;
}
int
route_output(struct mbuf *m, struct socket *so, struct sockaddr *dstaddr,
struct mbuf *control)
{
struct rt_msghdr *rtm = NULL;
struct rtentry *rt = NULL;
struct rt_addrinfo info;
int len, seq, error = 0;
u_int tableid;
u_int8_t prio;
u_char vers, type;
if (m == NULL || ((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 < offsetof(struct rt_msghdr, rtm_type) + 1 ||
len != mtod(m, struct rt_msghdr *)->rtm_msglen) {
error = EINVAL;
goto fail;
}
vers = mtod(m, struct rt_msghdr *)->rtm_version;
switch (vers) {
case RTM_VERSION:
if (len < sizeof(struct rt_msghdr)) {
error = EINVAL;
goto fail;
}
if (len > RTM_MAXSIZE) {
error = EMSGSIZE;
goto fail;
}
rtm = malloc(len, M_RTABLE, M_WAITOK);
m_copydata(m, 0, len, (caddr_t)rtm);
break;
default:
error = EPROTONOSUPPORT;
goto fail;
}
rtm->rtm_pid = curproc->p_p->ps_pid;
if (rtm->rtm_hdrlen == 0) /* old client */
rtm->rtm_hdrlen = sizeof(struct rt_msghdr);
if (len < rtm->rtm_hdrlen) {
error = EINVAL;
goto fail;
}
/* Verify that the caller is sending an appropriate message early */
switch (rtm->rtm_type) {
case RTM_ADD:
case RTM_DELETE:
case RTM_GET:
case RTM_CHANGE:
case RTM_PROPOSAL:
break;
default:
error = EOPNOTSUPP;
goto fail;
}
/*
* 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) != 0) {
error = EACCES;
goto fail;
}
tableid = rtm->rtm_tableid;
if (!rtable_exists(tableid)) {
if (rtm->rtm_type == RTM_ADD) {
if ((error = rtable_add(tableid)) != 0)
goto fail;
} else {
error = EINVAL;
goto fail;
}
}
/* Do not let userland play with kernel-only flags. */
if ((rtm->rtm_flags & (RTF_LOCAL|RTF_BROADCAST)) != 0) {
error = EINVAL;
goto fail;
}
/* make sure that kernel-only bits are not set */
rtm->rtm_priority &= RTP_MASK;
rtm->rtm_flags &= ~(RTF_DONE|RTF_CLONED|RTF_CACHED);
rtm->rtm_fmask &= RTF_FMASK;
if (rtm->rtm_priority != 0) {
if (rtm->rtm_priority > RTP_MAX ||
rtm->rtm_priority == RTP_LOCAL) {
error = EINVAL;
goto fail;
}
prio = rtm->rtm_priority;
} else if (rtm->rtm_type != RTM_ADD)
prio = RTP_ANY;
else if (rtm->rtm_flags & RTF_STATIC)
prio = 0;
else
prio = RTP_DEFAULT;
bzero(&info, sizeof(info));
info.rti_addrs = rtm->rtm_addrs;
rtm_xaddrs(rtm->rtm_hdrlen + (caddr_t)rtm, len + (caddr_t)rtm, &info);
info.rti_flags = rtm->rtm_flags;
if (rtm->rtm_type != RTM_PROPOSAL &&
(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) ||
info.rti_info[RTAX_GENMASK] != NULL)) {
error = EINVAL;
goto fail;
}
#ifdef MPLS
info.rti_mpls = rtm->rtm_mpls;
#endif
if (info.rti_info[RTAX_GATEWAY] != NULL &&
info.rti_info[RTAX_GATEWAY]->sa_family == AF_LINK &&
(info.rti_flags & RTF_CLONING) == 0) {
info.rti_flags |= RTF_LLINFO;
}
/*
* Validate RTM_PROPOSAL and pass it along or error out.
*/
if (rtm->rtm_type == RTM_PROPOSAL) {
if (rtm_validate_proposal(&info) == -1) {
error = EINVAL;
goto fail;
}
} else {
error = rtm_output(rtm, &rt, &info, prio, tableid);
if (!error) {
type = rtm->rtm_type;
seq = rtm->rtm_seq;
free(rtm, M_RTABLE, len);
rtm = rtm_report(rt, type, seq, tableid);
len = rtm->rtm_msglen;
}
}
rtfree(rt);
if (error) {
rtm->rtm_errno = error;
} else {
rtm->rtm_flags |= RTF_DONE;
}
/*
* Check to see if we don't want our own messages.
*/
if (!(so->so_options & SO_USELOOPBACK)) {
if (rtptable.rtp_count <= 1) {
/* no other listener and no loopback of messages */
fail:
free(rtm, M_RTABLE, len);
m_freem(m);
return (error);
}
}
if (rtm) {
if (m_copyback(m, 0, len, rtm, M_NOWAIT)) {
m_freem(m);
m = NULL;
} else if (m->m_pkthdr.len > len)
m_adj(m, len - m->m_pkthdr.len);
free(rtm, M_RTABLE, len);
}
if (m)
route_input(m, so, info.rti_info[RTAX_DST] ?
info.rti_info[RTAX_DST]->sa_family : AF_UNSPEC);
return (error);
}
int
rtm_output(struct rt_msghdr *rtm, struct rtentry **prt,
struct rt_addrinfo *info, uint8_t prio, unsigned int tableid)
{
struct rtentry *rt = *prt;
struct ifnet *ifp = NULL;
int plen, newgate = 0, error = 0;
switch (rtm->rtm_type) {
case RTM_ADD:
if (info->rti_info[RTAX_GATEWAY] == NULL) {
error = EINVAL;
break;
}
rt = rtable_match(tableid, info->rti_info[RTAX_DST], NULL);
if ((error = route_arp_conflict(rt, info))) {
rtfree(rt);
rt = NULL;
break;
}
/*
* We cannot go through a delete/create/insert cycle for
* cached route because this can lead to races in the
* receive path. Instead we update the L2 cache.
*/
if ((rt != NULL) && ISSET(rt->rt_flags, RTF_CACHED))
goto change;
rtfree(rt);
rt = NULL;
NET_LOCK();
if ((error = rtm_getifa(info, tableid)) != 0) {
NET_UNLOCK();
break;
}
error = rtrequest(RTM_ADD, info, prio, &rt, tableid);
NET_UNLOCK();
if (error == 0)
rtm_setmetrics(rtm->rtm_inits, &rtm->rtm_rmx,
&rt->rt_rmx);
break;
case RTM_DELETE:
rt = rtable_lookup(tableid, info->rti_info[RTAX_DST],
info->rti_info[RTAX_NETMASK], info->rti_info[RTAX_GATEWAY],
prio);
if (rt == NULL) {
error = ESRCH;
break;
}
/*
* If we got multipath routes, we require users to specify
* a matching gateway.
*/
if (ISSET(rt->rt_flags, RTF_MPATH) &&
info->rti_info[RTAX_GATEWAY] == NULL) {
error = ESRCH;
break;
}
/* Detaching an interface requires the KERNEL_LOCK(). */
ifp = if_get(rt->rt_ifidx);
KASSERT(ifp != NULL);
/*
* Invalidate the cache of automagically created and
* referenced L2 entries to make sure that ``rt_gwroute''
* pointer stays valid for other CPUs.
*/
if ((ISSET(rt->rt_flags, RTF_CACHED))) {
NET_LOCK();
ifp->if_rtrequest(ifp, RTM_INVALIDATE, rt);
/* Reset the MTU of the gateway route. */
rtable_walk(tableid, rt_key(rt)->sa_family,
route_cleargateway, rt);
NET_UNLOCK();
if_put(ifp);
break;
}
/*
* Make sure that local routes are only modified by the
* kernel.
*/
if (ISSET(rt->rt_flags, RTF_LOCAL|RTF_BROADCAST)) {
if_put(ifp);
error = EINVAL;
break;
}
rtfree(rt);
rt = NULL;
NET_LOCK();
error = rtrequest_delete(info, prio, ifp, &rt, tableid);
NET_UNLOCK();
if_put(ifp);
break;
case RTM_CHANGE:
rt = rtable_lookup(tableid, info->rti_info[RTAX_DST],
info->rti_info[RTAX_NETMASK], info->rti_info[RTAX_GATEWAY],
prio);
/*
* If we got multipath routes, we require users to specify
* a matching gateway.
*/
if ((rt != NULL) && ISSET(rt->rt_flags, RTF_MPATH) &&
(info->rti_info[RTAX_GATEWAY] == NULL)) {
rtfree(rt);
rt = NULL;
}
/*
* If RTAX_GATEWAY is the argument we're trying to
* change, try to find a compatible route.
*/
if ((rt == NULL) && (info->rti_info[RTAX_GATEWAY] != NULL) &&
(rtm->rtm_type == RTM_CHANGE)) {
rt = rtable_lookup(tableid, info->rti_info[RTAX_DST],
info->rti_info[RTAX_NETMASK], NULL, prio);
/* Ensure we don't pick a multipath one. */
if ((rt != NULL) && ISSET(rt->rt_flags, RTF_MPATH)) {
rtfree(rt);
rt = NULL;
}
}
if (rt == NULL) {
error = ESRCH;
break;
}
/*
* Make sure that local routes are only modified by the
* kernel.
*/
if (ISSET(rt->rt_flags, RTF_LOCAL|RTF_BROADCAST)) {
error = EINVAL;
break;
}
/*
* RTM_CHANGE/LOCK need a perfect match.
*/
plen = rtable_satoplen(info->rti_info[RTAX_DST]->sa_family,
info->rti_info[RTAX_NETMASK]);
if (rt_plen(rt) != plen) {
error = ESRCH;
break;