-
Notifications
You must be signed in to change notification settings - Fork 3
/
rtsock.c
2253 lines (2051 loc) · 58.1 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
/*
* Copyright (c) 2000-2020 Apple Inc. All rights reserved.
*
* @APPLE_OSREFERENCE_LICENSE_HEADER_START@
*
* This file contains Original Code and/or Modifications of Original Code
* as defined in and that are subject to the Apple Public Source License
* Version 2.0 (the 'License'). You may not use this file except in
* compliance with the License. The rights granted to you under the License
* may not be used to create, or enable the creation or redistribution of,
* unlawful or unlicensed copies of an Apple operating system, or to
* circumvent, violate, or enable the circumvention or violation of, any
* terms of an Apple operating system software license agreement.
*
* Please obtain a copy of the License at
* http://www.opensource.apple.com/apsl/ and read it before using this file.
*
* The Original Code and all software distributed under the License are
* distributed on an 'AS IS' basis, WITHOUT WARRANTY OF ANY KIND, EITHER
* EXPRESS OR IMPLIED, AND APPLE HEREBY DISCLAIMS ALL SUCH WARRANTIES,
* INCLUDING WITHOUT LIMITATION, ANY WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE, QUIET ENJOYMENT OR NON-INFRINGEMENT.
* Please see the License for the specific language governing rights and
* limitations under the License.
*
* @APPLE_OSREFERENCE_LICENSE_HEADER_END@
*/
/*
* 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. All advertising materials mentioning features or use of this software
* must display the following acknowledgement:
* This product includes software developed by the University of
* California, Berkeley and its contributors.
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* @(#)rtsock.c 8.5 (Berkeley) 11/2/94
*/
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kauth.h>
#include <sys/kernel.h>
#include <sys/sysctl.h>
#include <sys/proc.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/domain.h>
#include <sys/protosw.h>
#include <sys/syslog.h>
#include <sys/mcache.h>
#include <kern/locks.h>
#include <sys/codesign.h>
#include <net/if.h>
#include <net/route.h>
#include <net/dlil.h>
#include <net/raw_cb.h>
#include <netinet/in.h>
#include <netinet/in_var.h>
#include <netinet/in_arp.h>
#include <netinet/ip.h>
#include <netinet/ip6.h>
#include <netinet6/nd6.h>
extern struct rtstat rtstat;
extern struct domain routedomain_s;
static struct domain *routedomain = NULL;
MALLOC_DEFINE(M_RTABLE, "routetbl", "routing tables");
static struct sockaddr route_dst = { .sa_len = 2, .sa_family = PF_ROUTE, .sa_data = { 0, } };
static struct sockaddr route_src = { .sa_len = 2, .sa_family = PF_ROUTE, .sa_data = { 0, } };
static struct sockaddr sa_zero = { .sa_len = sizeof(sa_zero), .sa_family = AF_INET, .sa_data = { 0, } };
struct route_cb {
u_int32_t ip_count; /* attached w/ AF_INET */
u_int32_t ip6_count; /* attached w/ AF_INET6 */
u_int32_t any_count; /* total attached */
};
static struct route_cb route_cb;
struct walkarg {
int w_tmemsize;
int w_op, w_arg;
caddr_t w_tmem;
struct sysctl_req *w_req;
};
static void route_dinit(struct domain *);
static int rts_abort(struct socket *);
static int rts_attach(struct socket *, int, struct proc *);
static int rts_bind(struct socket *, struct sockaddr *, struct proc *);
static int rts_connect(struct socket *, struct sockaddr *, struct proc *);
static int rts_detach(struct socket *);
static int rts_disconnect(struct socket *);
static int rts_peeraddr(struct socket *, struct sockaddr **);
static int rts_send(struct socket *, int, struct mbuf *, struct sockaddr *,
struct mbuf *, struct proc *);
static int rts_shutdown(struct socket *);
static int rts_sockaddr(struct socket *, struct sockaddr **);
static int route_output(struct mbuf *, struct socket *);
static int rt_setmetrics(u_int32_t, struct rt_metrics *, struct rtentry *);
static void rt_getmetrics(struct rtentry *, struct rt_metrics *);
static void rt_setif(struct rtentry *, struct sockaddr *, struct sockaddr *,
struct sockaddr *, unsigned int);
static int rt_xaddrs(caddr_t, caddr_t, struct rt_addrinfo *);
static struct mbuf *rt_msg1(u_char, struct rt_addrinfo *);
static int rt_msg2(u_char, struct rt_addrinfo *, caddr_t, struct walkarg *,
kauth_cred_t *);
static int sysctl_dumpentry(struct radix_node *rn, void *vw);
static int sysctl_dumpentry_ext(struct radix_node *rn, void *vw);
static int sysctl_iflist(int af, struct walkarg *w);
static int sysctl_iflist2(int af, struct walkarg *w);
static int sysctl_rtstat(struct sysctl_req *);
static int sysctl_rttrash(struct sysctl_req *);
static int sysctl_rtsock SYSCTL_HANDLER_ARGS;
SYSCTL_NODE(_net, PF_ROUTE, routetable, CTLFLAG_RD | CTLFLAG_LOCKED,
sysctl_rtsock, "");
SYSCTL_NODE(_net, OID_AUTO, route, CTLFLAG_RW | CTLFLAG_LOCKED, 0, "routing");
/* Align x to 1024 (only power of 2) assuming x is positive */
#define ALIGN_BYTES(x) do { \
x = (uint32_t)P2ALIGN(x, 1024); \
} while(0)
#define ROUNDUP32(a) \
((a) > 0 ? (1 + (((a) - 1) | (sizeof (uint32_t) - 1))) : \
sizeof (uint32_t))
#define ADVANCE32(x, n) \
(x += ROUNDUP32((n)->sa_len))
#define RT_HAS_IFADDR(rt) \
((rt)->rt_ifa != NULL && (rt)->rt_ifa->ifa_addr != NULL)
/*
* It really doesn't make any sense at all for this code to share much
* with raw_usrreq.c, since its functionality is so restricted. XXX
*/
static int
rts_abort(struct socket *so)
{
return raw_usrreqs.pru_abort(so);
}
/* pru_accept is EOPNOTSUPP */
static int
rts_attach(struct socket *so, int proto, struct proc *p)
{
#pragma unused(p)
struct rawcb *rp;
int error;
VERIFY(so->so_pcb == NULL);
MALLOC(rp, struct rawcb *, sizeof(*rp), M_PCB, M_WAITOK | M_ZERO);
if (rp == NULL) {
return ENOBUFS;
}
so->so_pcb = (caddr_t)rp;
/* don't use raw_usrreqs.pru_attach, it checks for SS_PRIV */
error = raw_attach(so, proto);
rp = sotorawcb(so);
if (error) {
FREE(rp, M_PCB);
so->so_pcb = NULL;
so->so_flags |= SOF_PCBCLEARING;
return error;
}
switch (rp->rcb_proto.sp_protocol) {
case AF_INET:
atomic_add_32(&route_cb.ip_count, 1);
break;
case AF_INET6:
atomic_add_32(&route_cb.ip6_count, 1);
break;
}
rp->rcb_faddr = &route_src;
atomic_add_32(&route_cb.any_count, 1);
/* the socket is already locked when we enter rts_attach */
soisconnected(so);
so->so_options |= SO_USELOOPBACK;
return 0;
}
static int
rts_bind(struct socket *so, struct sockaddr *nam, struct proc *p)
{
return raw_usrreqs.pru_bind(so, nam, p); /* xxx just EINVAL */
}
static int
rts_connect(struct socket *so, struct sockaddr *nam, struct proc *p)
{
return raw_usrreqs.pru_connect(so, nam, p); /* XXX just EINVAL */
}
/* pru_connect2 is EOPNOTSUPP */
/* pru_control is EOPNOTSUPP */
static int
rts_detach(struct socket *so)
{
struct rawcb *rp = sotorawcb(so);
VERIFY(rp != NULL);
switch (rp->rcb_proto.sp_protocol) {
case AF_INET:
atomic_add_32(&route_cb.ip_count, -1);
break;
case AF_INET6:
atomic_add_32(&route_cb.ip6_count, -1);
break;
}
atomic_add_32(&route_cb.any_count, -1);
return raw_usrreqs.pru_detach(so);
}
static int
rts_disconnect(struct socket *so)
{
return raw_usrreqs.pru_disconnect(so);
}
/* pru_listen is EOPNOTSUPP */
static int
rts_peeraddr(struct socket *so, struct sockaddr **nam)
{
return raw_usrreqs.pru_peeraddr(so, nam);
}
/* pru_rcvd is EOPNOTSUPP */
/* pru_rcvoob is EOPNOTSUPP */
static int
rts_send(struct socket *so, int flags, struct mbuf *m, struct sockaddr *nam,
struct mbuf *control, struct proc *p)
{
return raw_usrreqs.pru_send(so, flags, m, nam, control, p);
}
/* pru_sense is null */
static int
rts_shutdown(struct socket *so)
{
return raw_usrreqs.pru_shutdown(so);
}
static int
rts_sockaddr(struct socket *so, struct sockaddr **nam)
{
return raw_usrreqs.pru_sockaddr(so, nam);
}
static struct pr_usrreqs route_usrreqs = {
.pru_abort = rts_abort,
.pru_attach = rts_attach,
.pru_bind = rts_bind,
.pru_connect = rts_connect,
.pru_detach = rts_detach,
.pru_disconnect = rts_disconnect,
.pru_peeraddr = rts_peeraddr,
.pru_send = rts_send,
.pru_shutdown = rts_shutdown,
.pru_sockaddr = rts_sockaddr,
.pru_sosend = sosend,
.pru_soreceive = soreceive,
};
/*ARGSUSED*/
static int
route_output(struct mbuf *m, struct socket *so)
{
struct rt_msghdr *rtm = NULL;
struct rtentry *rt = NULL;
struct rtentry *saved_nrt = NULL;
struct radix_node_head *rnh;
struct rt_addrinfo info;
int len, error = 0;
sa_family_t dst_sa_family = 0;
struct ifnet *ifp = NULL;
struct sockaddr_in dst_in, gate_in;
int sendonlytoself = 0;
unsigned int ifscope = IFSCOPE_NONE;
struct rawcb *rp = NULL;
boolean_t is_router = FALSE;
#define senderr(e) { error = (e); goto flush; }
if (m == NULL || ((m->m_len < sizeof(intptr_t)) &&
(m = m_pullup(m, sizeof(intptr_t))) == NULL)) {
return ENOBUFS;
}
VERIFY(m->m_flags & M_PKTHDR);
/*
* Unlock the socket (but keep a reference) it won't be
* accessed until raw_input appends to it.
*/
socket_unlock(so, 0);
lck_mtx_lock(rnh_lock);
len = m->m_pkthdr.len;
if (len < sizeof(*rtm) ||
len != mtod(m, struct rt_msghdr *)->rtm_msglen) {
info.rti_info[RTAX_DST] = NULL;
senderr(EINVAL);
}
R_Malloc(rtm, struct rt_msghdr *, len);
if (rtm == NULL) {
info.rti_info[RTAX_DST] = NULL;
senderr(ENOBUFS);
}
m_copydata(m, 0, len, (caddr_t)rtm);
if (rtm->rtm_version != RTM_VERSION) {
info.rti_info[RTAX_DST] = NULL;
senderr(EPROTONOSUPPORT);
}
/*
* Silent version of RTM_GET for Reachabiltiy APIs. We may change
* all RTM_GETs to be silent in the future, so this is private for now.
*/
if (rtm->rtm_type == RTM_GET_SILENT) {
if (!(so->so_options & SO_USELOOPBACK)) {
senderr(EINVAL);
}
sendonlytoself = 1;
rtm->rtm_type = RTM_GET;
}
/*
* Perform permission checking, only privileged sockets
* may perform operations other than RTM_GET
*/
if (rtm->rtm_type != RTM_GET && !(so->so_state & SS_PRIV)) {
info.rti_info[RTAX_DST] = NULL;
senderr(EPERM);
}
rtm->rtm_pid = proc_selfpid();
info.rti_addrs = rtm->rtm_addrs;
if (rt_xaddrs((caddr_t)(rtm + 1), len + (caddr_t)rtm, &info)) {
info.rti_info[RTAX_DST] = NULL;
senderr(EINVAL);
}
if (info.rti_info[RTAX_DST] == NULL ||
info.rti_info[RTAX_DST]->sa_family >= AF_MAX ||
(info.rti_info[RTAX_GATEWAY] != NULL &&
info.rti_info[RTAX_GATEWAY]->sa_family >= AF_MAX)) {
senderr(EINVAL);
}
if (info.rti_info[RTAX_DST]->sa_family == AF_INET &&
info.rti_info[RTAX_DST]->sa_len != sizeof(struct sockaddr_in)) {
/* At minimum, we need up to sin_addr */
if (info.rti_info[RTAX_DST]->sa_len <
offsetof(struct sockaddr_in, sin_zero)) {
senderr(EINVAL);
}
bzero(&dst_in, sizeof(dst_in));
dst_in.sin_len = sizeof(dst_in);
dst_in.sin_family = AF_INET;
dst_in.sin_port = SIN(info.rti_info[RTAX_DST])->sin_port;
dst_in.sin_addr = SIN(info.rti_info[RTAX_DST])->sin_addr;
info.rti_info[RTAX_DST] = (struct sockaddr *)&dst_in;
dst_sa_family = info.rti_info[RTAX_DST]->sa_family;
} else if (info.rti_info[RTAX_DST]->sa_family == AF_INET6 &&
info.rti_info[RTAX_DST]->sa_len < sizeof(struct sockaddr_in6)) {
senderr(EINVAL);
}
if (info.rti_info[RTAX_GATEWAY] != NULL) {
if (info.rti_info[RTAX_GATEWAY]->sa_family == AF_INET &&
info.rti_info[RTAX_GATEWAY]->sa_len != sizeof(struct sockaddr_in)) {
/* At minimum, we need up to sin_addr */
if (info.rti_info[RTAX_GATEWAY]->sa_len <
offsetof(struct sockaddr_in, sin_zero)) {
senderr(EINVAL);
}
bzero(&gate_in, sizeof(gate_in));
gate_in.sin_len = sizeof(gate_in);
gate_in.sin_family = AF_INET;
gate_in.sin_port = SIN(info.rti_info[RTAX_GATEWAY])->sin_port;
gate_in.sin_addr = SIN(info.rti_info[RTAX_GATEWAY])->sin_addr;
info.rti_info[RTAX_GATEWAY] = (struct sockaddr *)&gate_in;
} else if (info.rti_info[RTAX_GATEWAY]->sa_family == AF_INET6 &&
info.rti_info[RTAX_GATEWAY]->sa_len < sizeof(struct sockaddr_in6)) {
senderr(EINVAL);
}
}
if (info.rti_info[RTAX_GENMASK]) {
struct radix_node *t;
t = rn_addmask((caddr_t)info.rti_info[RTAX_GENMASK], 0, 1);
if (t != NULL && Bcmp(info.rti_info[RTAX_GENMASK],
t->rn_key, *(u_char *)info.rti_info[RTAX_GENMASK]) == 0) {
info.rti_info[RTAX_GENMASK] =
(struct sockaddr *)(t->rn_key);
} else {
senderr(ENOBUFS);
}
}
/*
* If RTF_IFSCOPE flag is set, then rtm_index specifies the scope.
*/
if (rtm->rtm_flags & RTF_IFSCOPE) {
if (info.rti_info[RTAX_DST]->sa_family != AF_INET &&
info.rti_info[RTAX_DST]->sa_family != AF_INET6) {
senderr(EINVAL);
}
ifscope = rtm->rtm_index;
}
/*
* Block changes on INTCOPROC interfaces.
*/
if (ifscope) {
unsigned int intcoproc_scope = 0;
ifnet_head_lock_shared();
TAILQ_FOREACH(ifp, &ifnet_head, if_link) {
if (IFNET_IS_INTCOPROC(ifp)) {
intcoproc_scope = ifp->if_index;
break;
}
}
ifnet_head_done();
if (intcoproc_scope == ifscope && current_proc()->p_pid != 0) {
senderr(EINVAL);
}
}
/*
* RTF_PROXY can only be set internally from within the kernel.
*/
if (rtm->rtm_flags & RTF_PROXY) {
senderr(EINVAL);
}
/*
* For AF_INET, always zero out the embedded scope ID. If this is
* a scoped request, it must be done explicitly by setting RTF_IFSCOPE
* flag and the corresponding rtm_index value. This is to prevent
* false interpretation of the scope ID because it's using the sin_zero
* field, which might not be properly cleared by the requestor.
*/
if (info.rti_info[RTAX_DST]->sa_family == AF_INET) {
sin_set_ifscope(info.rti_info[RTAX_DST], IFSCOPE_NONE);
}
if (info.rti_info[RTAX_GATEWAY] != NULL &&
info.rti_info[RTAX_GATEWAY]->sa_family == AF_INET) {
sin_set_ifscope(info.rti_info[RTAX_GATEWAY], IFSCOPE_NONE);
}
switch (rtm->rtm_type) {
case RTM_ADD:
if (info.rti_info[RTAX_GATEWAY] == NULL) {
senderr(EINVAL);
}
error = rtrequest_scoped_locked(RTM_ADD,
info.rti_info[RTAX_DST], info.rti_info[RTAX_GATEWAY],
info.rti_info[RTAX_NETMASK], rtm->rtm_flags, &saved_nrt,
ifscope);
if (error == 0 && saved_nrt != NULL) {
RT_LOCK(saved_nrt);
/*
* If the route request specified an interface with
* IFA and/or IFP, we set the requested interface on
* the route with rt_setif. It would be much better
* to do this inside rtrequest, but that would
* require passing the desired interface, in some
* form, to rtrequest. Since rtrequest is called in
* so many places (roughly 40 in our source), adding
* a parameter is to much for us to swallow; this is
* something for the FreeBSD developers to tackle.
* Instead, we let rtrequest compute whatever
* interface it wants, then come in behind it and
* stick in the interface that we really want. This
* works reasonably well except when rtrequest can't
* figure out what interface to use (with
* ifa_withroute) and returns ENETUNREACH. Ideally
* it shouldn't matter if rtrequest can't figure out
* the interface if we're going to explicitly set it
* ourselves anyway. But practically we can't
* recover here because rtrequest will not do any of
* the work necessary to add the route if it can't
* find an interface. As long as there is a default
* route that leads to some interface, rtrequest will
* find an interface, so this problem should be
* rarely encountered.
* dwiggins@bbn.com
*/
rt_setif(saved_nrt,
info.rti_info[RTAX_IFP], info.rti_info[RTAX_IFA],
info.rti_info[RTAX_GATEWAY], ifscope);
(void)rt_setmetrics(rtm->rtm_inits, &rtm->rtm_rmx, saved_nrt);
saved_nrt->rt_rmx.rmx_locks &= ~(rtm->rtm_inits);
saved_nrt->rt_rmx.rmx_locks |=
(rtm->rtm_inits & rtm->rtm_rmx.rmx_locks);
saved_nrt->rt_genmask = info.rti_info[RTAX_GENMASK];
RT_REMREF_LOCKED(saved_nrt);
RT_UNLOCK(saved_nrt);
}
break;
case RTM_DELETE:
error = rtrequest_scoped_locked(RTM_DELETE,
info.rti_info[RTAX_DST], info.rti_info[RTAX_GATEWAY],
info.rti_info[RTAX_NETMASK], rtm->rtm_flags, &saved_nrt,
ifscope);
if (error == 0) {
rt = saved_nrt;
RT_LOCK(rt);
goto report;
}
break;
case RTM_GET:
case RTM_CHANGE:
case RTM_LOCK:
rnh = rt_tables[info.rti_info[RTAX_DST]->sa_family];
if (rnh == NULL) {
senderr(EAFNOSUPPORT);
}
/*
* Lookup the best match based on the key-mask pair;
* callee adds a reference and checks for root node.
*/
rt = rt_lookup(TRUE, info.rti_info[RTAX_DST],
info.rti_info[RTAX_NETMASK], rnh, ifscope);
if (rt == NULL) {
senderr(ESRCH);
}
RT_LOCK(rt);
/*
* Holding rnh_lock here prevents the possibility of
* ifa from changing (e.g. in_ifinit), so it is safe
* to access its ifa_addr (down below) without locking.
*/
switch (rtm->rtm_type) {
case RTM_GET: {
kauth_cred_t cred;
kauth_cred_t* credp;
struct ifaddr *ifa2;
report:
cred = kauth_cred_proc_ref(current_proc());
credp = &cred;
ifa2 = NULL;
RT_LOCK_ASSERT_HELD(rt);
info.rti_info[RTAX_DST] = rt_key(rt);
dst_sa_family = info.rti_info[RTAX_DST]->sa_family;
info.rti_info[RTAX_GATEWAY] = rt->rt_gateway;
info.rti_info[RTAX_NETMASK] = rt_mask(rt);
info.rti_info[RTAX_GENMASK] = rt->rt_genmask;
if (rtm->rtm_addrs & (RTA_IFP | RTA_IFA)) {
ifp = rt->rt_ifp;
if (ifp != NULL) {
ifnet_lock_shared(ifp);
ifa2 = ifp->if_lladdr;
info.rti_info[RTAX_IFP] =
ifa2->ifa_addr;
IFA_ADDREF(ifa2);
ifnet_lock_done(ifp);
info.rti_info[RTAX_IFA] =
rt->rt_ifa->ifa_addr;
rtm->rtm_index = ifp->if_index;
} else {
info.rti_info[RTAX_IFP] = NULL;
info.rti_info[RTAX_IFA] = NULL;
}
} else if ((ifp = rt->rt_ifp) != NULL) {
rtm->rtm_index = ifp->if_index;
}
if (ifa2 != NULL) {
IFA_LOCK(ifa2);
}
len = rt_msg2(rtm->rtm_type, &info, NULL, NULL, credp);
if (ifa2 != NULL) {
IFA_UNLOCK(ifa2);
}
struct rt_msghdr *out_rtm;
R_Malloc(out_rtm, struct rt_msghdr *, len);
if (out_rtm == NULL) {
RT_UNLOCK(rt);
if (ifa2 != NULL) {
IFA_REMREF(ifa2);
}
senderr(ENOBUFS);
}
Bcopy(rtm, out_rtm, sizeof(struct rt_msghdr));
if (ifa2 != NULL) {
IFA_LOCK(ifa2);
}
(void) rt_msg2(out_rtm->rtm_type, &info, (caddr_t)out_rtm,
NULL, &cred);
if (ifa2 != NULL) {
IFA_UNLOCK(ifa2);
}
R_Free(rtm);
rtm = out_rtm;
rtm->rtm_flags = rt->rt_flags;
rt_getmetrics(rt, &rtm->rtm_rmx);
rtm->rtm_addrs = info.rti_addrs;
if (ifa2 != NULL) {
IFA_REMREF(ifa2);
}
kauth_cred_unref(&cred);
break;
}
case RTM_CHANGE:
is_router = (rt->rt_flags & RTF_ROUTER) ? TRUE : FALSE;
if (info.rti_info[RTAX_GATEWAY] != NULL &&
(error = rt_setgate(rt, rt_key(rt),
info.rti_info[RTAX_GATEWAY]))) {
int tmp = error;
RT_UNLOCK(rt);
senderr(tmp);
}
/*
* If they tried to change things but didn't specify
* the required gateway, then just use the old one.
* This can happen if the user tries to change the
* flags on the default route without changing the
* default gateway. Changing flags still doesn't work.
*/
if ((rt->rt_flags & RTF_GATEWAY) &&
info.rti_info[RTAX_GATEWAY] == NULL) {
info.rti_info[RTAX_GATEWAY] = rt->rt_gateway;
}
/*
* On Darwin, we call rt_setif which contains the
* equivalent to the code found at this very spot
* in BSD.
*/
rt_setif(rt,
info.rti_info[RTAX_IFP], info.rti_info[RTAX_IFA],
info.rti_info[RTAX_GATEWAY], ifscope);
if ((error = rt_setmetrics(rtm->rtm_inits,
&rtm->rtm_rmx, rt))) {
int tmp = error;
RT_UNLOCK(rt);
senderr(tmp);
}
if (info.rti_info[RTAX_GENMASK]) {
rt->rt_genmask = info.rti_info[RTAX_GENMASK];
}
/*
* Enqueue work item to invoke callback for this route entry
* This may not be needed always, but for now issue it anytime
* RTM_CHANGE gets called.
*/
route_event_enqueue_nwk_wq_entry(rt, NULL, ROUTE_ENTRY_REFRESH, NULL, TRUE);
/*
* If the route is for a router, walk the tree to send refresh
* event to protocol cloned entries
*/
if (is_router) {
struct route_event rt_ev;
route_event_init(&rt_ev, rt, NULL, ROUTE_ENTRY_REFRESH);
RT_UNLOCK(rt);
(void) rnh->rnh_walktree(rnh, route_event_walktree, (void *)&rt_ev);
RT_LOCK(rt);
}
OS_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;
}
RT_UNLOCK(rt);
break;
default:
senderr(EOPNOTSUPP);
}
flush:
if (rtm != NULL) {
if (error) {
rtm->rtm_errno = error;
} else {
rtm->rtm_flags |= RTF_DONE;
}
}
if (rt != NULL) {
RT_LOCK_ASSERT_NOTHELD(rt);
rtfree_locked(rt);
}
lck_mtx_unlock(rnh_lock);
/* relock the socket now */
socket_lock(so, 0);
/*
* Check to see if we don't want our own messages.
*/
if (!(so->so_options & SO_USELOOPBACK)) {
if (route_cb.any_count <= 1) {
if (rtm != NULL) {
R_Free(rtm);
}
m_freem(m);
return error;
}
/* There is another listener, so construct message */
rp = sotorawcb(so);
}
if (rtm != NULL) {
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);
}
R_Free(rtm);
}
if (sendonlytoself && m != NULL) {
error = 0;
if (sbappendaddr(&so->so_rcv, &route_src, m,
NULL, &error) != 0) {
sorwakeup(so);
}
if (error) {
return error;
}
} else {
struct sockproto route_proto = { .sp_family = PF_ROUTE, .sp_protocol = 0 };
if (rp != NULL) {
rp->rcb_proto.sp_family = 0; /* Avoid us */
}
if (dst_sa_family != 0) {
route_proto.sp_protocol = dst_sa_family;
}
if (m != NULL) {
socket_unlock(so, 0);
raw_input(m, &route_proto, &route_src, &route_dst);
socket_lock(so, 0);
}
if (rp != NULL) {
rp->rcb_proto.sp_family = PF_ROUTE;
}
}
return error;
}
void
rt_setexpire(struct rtentry *rt, uint64_t expiry)
{
/* set both rt_expire and rmx_expire */
rt->rt_expire = expiry;
if (expiry) {
rt->rt_rmx.rmx_expire =
(int32_t)(expiry + rt->base_calendartime -
rt->base_uptime);
} else {
rt->rt_rmx.rmx_expire = 0;
}
}
static int
rt_setmetrics(u_int32_t which, struct rt_metrics *in, struct rtentry *out)
{
if (!(which & RTV_REFRESH_HOST)) {
struct timeval caltime;
getmicrotime(&caltime);
#define metric(f, e) if (which & (f)) out->rt_rmx.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
if (out->rt_rmx.rmx_expire > 0) {
/* account for system time change */
getmicrotime(&caltime);
out->base_calendartime +=
NET_CALCULATE_CLOCKSKEW(caltime,
out->base_calendartime,
net_uptime(), out->base_uptime);
rt_setexpire(out,
out->rt_rmx.rmx_expire -
out->base_calendartime +
out->base_uptime);
} else {
rt_setexpire(out, 0);
}
VERIFY(out->rt_expire == 0 || out->rt_rmx.rmx_expire != 0);
VERIFY(out->rt_expire != 0 || out->rt_rmx.rmx_expire == 0);
} else {
/* Only RTV_REFRESH_HOST must be set */
if ((which & ~RTV_REFRESH_HOST) ||
(out->rt_flags & RTF_STATIC) ||
!(out->rt_flags & RTF_LLINFO)) {
return EINVAL;
}
if (out->rt_llinfo_refresh == NULL) {
return ENOTSUP;
}
out->rt_llinfo_refresh(out);
}
return 0;
}
static void
rt_getmetrics(struct rtentry *in, struct rt_metrics *out)
{
struct timeval caltime;
VERIFY(in->rt_expire == 0 || in->rt_rmx.rmx_expire != 0);
VERIFY(in->rt_expire != 0 || in->rt_rmx.rmx_expire == 0);
*out = in->rt_rmx;
if (in->rt_expire != 0) {
/* account for system time change */
getmicrotime(&caltime);
in->base_calendartime +=
NET_CALCULATE_CLOCKSKEW(caltime,
in->base_calendartime, net_uptime(), in->base_uptime);
out->rmx_expire = (int32_t)(in->base_calendartime +
in->rt_expire - in->base_uptime);
} else {
out->rmx_expire = 0;
}
}
/*
* Set route's interface given info.rti_info[RTAX_IFP],
* info.rti_info[RTAX_IFA], and gateway.
*/
static void
rt_setif(struct rtentry *rt, struct sockaddr *Ifpaddr, struct sockaddr *Ifaaddr,
struct sockaddr *Gate, unsigned int ifscope)
{
struct ifaddr *ifa = NULL;
struct ifnet *ifp = NULL;
void (*ifa_rtrequest)(int, struct rtentry *, struct sockaddr *);
LCK_MTX_ASSERT(rnh_lock, LCK_MTX_ASSERT_OWNED);
RT_LOCK_ASSERT_HELD(rt);
/* Don't update a defunct route */
if (rt->rt_flags & RTF_CONDEMNED) {
return;
}
/* Add an extra ref for ourselves */
RT_ADDREF_LOCKED(rt);
/* Become a regular mutex, just in case */
RT_CONVERT_LOCK(rt);
/*
* 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 (Ifpaddr && (ifa = ifa_ifwithnet_scoped(Ifpaddr, ifscope)) &&
(ifp = ifa->ifa_ifp) && (Ifaaddr || Gate)) {
IFA_REMREF(ifa);
ifa = ifaof_ifpforaddr(Ifaaddr ? Ifaaddr : Gate, ifp);
} else {
if (ifa != NULL) {
IFA_REMREF(ifa);
ifa = NULL;
}
if (Ifpaddr && (ifp = if_withname(Ifpaddr))) {
if (Gate) {
ifa = ifaof_ifpforaddr(Gate, ifp);
} else {
ifnet_lock_shared(ifp);
ifa = TAILQ_FIRST(&ifp->if_addrhead);
if (ifa != NULL) {
IFA_ADDREF(ifa);
}
ifnet_lock_done(ifp);
}
} else if (Ifaaddr &&
(ifa = ifa_ifwithaddr_scoped(Ifaaddr, ifscope))) {
ifp = ifa->ifa_ifp;
} else if (Gate != NULL) {
/*
* Safe to drop rt_lock and use rt_key, since holding
* rnh_lock here prevents another thread from calling
* rt_setgate() on this route. We cannot hold the
* lock across ifa_ifwithroute since the lookup done
* by that routine may point to the same route.
*/
RT_UNLOCK(rt);
if ((ifa = ifa_ifwithroute_scoped_locked(rt->rt_flags,
rt_key(rt), Gate, ifscope)) != NULL) {
ifp = ifa->ifa_ifp;
}
RT_LOCK(rt);
/* Don't update a defunct route */
if (rt->rt_flags & RTF_CONDEMNED) {
if (ifa != NULL) {
IFA_REMREF(ifa);
}
/* Release extra ref */
RT_REMREF_LOCKED(rt);
return;
}
}
}
/* trigger route cache reevaluation */
if (rt_key(rt)->sa_family == AF_INET) {
routegenid_inet_update();
} else if (rt_key(rt)->sa_family == AF_INET6) {
routegenid_inet6_update();
}
if (ifa != NULL) {
struct ifaddr *oifa = rt->rt_ifa;
if (oifa != ifa) {
if (oifa != NULL) {
IFA_LOCK_SPIN(oifa);
ifa_rtrequest = oifa->ifa_rtrequest;
IFA_UNLOCK(oifa);
if (ifa_rtrequest != NULL) {
ifa_rtrequest(RTM_DELETE, rt, Gate);
}
}
rtsetifa(rt, ifa);
if (rt->rt_ifp != ifp) {
/*
* Purge any link-layer info caching.
*/
if (rt->rt_llinfo_purge != NULL) {
rt->rt_llinfo_purge(rt);
}
/*
* Adjust route ref count for the interfaces.
*/
if (rt->rt_if_ref_fn != NULL) {
rt->rt_if_ref_fn(ifp, 1);
rt->rt_if_ref_fn(rt->rt_ifp, -1);
}
}
rt->rt_ifp = ifp;
/*
* If this is the (non-scoped) default route, record
* the interface index used for the primary ifscope.
*/
if (rt_primary_default(rt, rt_key(rt))) {
set_primary_ifscope(rt_key(rt)->sa_family,
rt->rt_ifp->if_index);