-
Notifications
You must be signed in to change notification settings - Fork 34
/
raw_ip.c
1130 lines (1001 loc) · 27.1 KB
/
raw_ip.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) 1982, 1986, 1988, 1993
* The Regents of the University of California.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* @(#)raw_ip.c 8.7 (Berkeley) 5/15/95
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include "opt_inet.h"
#include "opt_inet6.h"
#include "opt_ipsec.h"
#include <sys/param.h>
#include <sys/jail.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/priv.h>
#include <sys/proc.h>
#include <sys/protosw.h>
#include <sys/rwlock.h>
#include <sys/signalvar.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/sx.h>
#include <sys/sysctl.h>
#include <sys/systm.h>
#include <vm/uma.h>
#include <net/if.h>
#include <net/route.h>
#include <net/vnet.h>
#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/in_pcb.h>
#include <netinet/in_var.h>
#include <netinet/if_ether.h>
#include <netinet/ip.h>
#include <netinet/ip_var.h>
#include <netinet/ip_mroute.h>
#ifdef IPSEC
#include <netipsec/ipsec.h>
#endif /*IPSEC*/
#include <security/mac/mac_framework.h>
VNET_DEFINE(int, ip_defttl) = IPDEFTTL;
SYSCTL_VNET_INT(_net_inet_ip, IPCTL_DEFTTL, ttl, CTLFLAG_RW,
&VNET_NAME(ip_defttl), 0,
"Maximum TTL on IP packets");
VNET_DEFINE(struct inpcbhead, ripcb);
VNET_DEFINE(struct inpcbinfo, ripcbinfo);
#define V_ripcb VNET(ripcb)
#define V_ripcbinfo VNET(ripcbinfo)
/*
* Control and data hooks for ipfw, dummynet, divert and so on.
* The data hooks are not used here but it is convenient
* to keep them all in one place.
*/
VNET_DEFINE(ip_fw_chk_ptr_t, ip_fw_chk_ptr) = NULL;
VNET_DEFINE(ip_fw_ctl_ptr_t, ip_fw_ctl_ptr) = NULL;
int (*ip_dn_ctl_ptr)(struct sockopt *);
int (*ip_dn_io_ptr)(struct mbuf **, int, struct ip_fw_args *);
void (*ip_divert_ptr)(struct mbuf *, int);
int (*ng_ipfw_input_p)(struct mbuf **, int,
struct ip_fw_args *, int);
#ifdef INET
/*
* Hooks for multicast routing. They all default to NULL, so leave them not
* initialized and rely on BSS being set to 0.
*/
/*
* The socket used to communicate with the multicast routing daemon.
*/
VNET_DEFINE(struct socket *, ip_mrouter);
/*
* The various mrouter and rsvp functions.
*/
int (*ip_mrouter_set)(struct socket *, struct sockopt *);
int (*ip_mrouter_get)(struct socket *, struct sockopt *);
int (*ip_mrouter_done)(void);
int (*ip_mforward)(struct ip *, struct ifnet *, struct mbuf *,
struct ip_moptions *);
int (*mrt_ioctl)(u_long, caddr_t, int);
int (*legal_vif_num)(int);
u_long (*ip_mcast_src)(int);
void (*rsvp_input_p)(struct mbuf *m, int off);
int (*ip_rsvp_vif)(struct socket *, struct sockopt *);
void (*ip_rsvp_force_done)(struct socket *);
#endif /* INET */
u_long rip_sendspace = 9216;
SYSCTL_ULONG(_net_inet_raw, OID_AUTO, maxdgram, CTLFLAG_RW,
&rip_sendspace, 0, "Maximum outgoing raw IP datagram size");
u_long rip_recvspace = 9216;
SYSCTL_ULONG(_net_inet_raw, OID_AUTO, recvspace, CTLFLAG_RW,
&rip_recvspace, 0, "Maximum space for incoming raw IP datagrams");
/*
* Hash functions
*/
#define INP_PCBHASH_RAW_SIZE 256
#define INP_PCBHASH_RAW(proto, laddr, faddr, mask) \
(((proto) + (laddr) + (faddr)) % (mask) + 1)
#ifdef INET
static void
rip_inshash(struct inpcb *inp)
{
struct inpcbinfo *pcbinfo = inp->inp_pcbinfo;
struct inpcbhead *pcbhash;
int hash;
INP_INFO_WLOCK_ASSERT(pcbinfo);
INP_WLOCK_ASSERT(inp);
if (inp->inp_ip_p != 0 &&
inp->inp_laddr.s_addr != INADDR_ANY &&
inp->inp_faddr.s_addr != INADDR_ANY) {
hash = INP_PCBHASH_RAW(inp->inp_ip_p, inp->inp_laddr.s_addr,
inp->inp_faddr.s_addr, pcbinfo->ipi_hashmask);
} else
hash = 0;
pcbhash = &pcbinfo->ipi_hashbase[hash];
LIST_INSERT_HEAD(pcbhash, inp, inp_hash);
}
static void
rip_delhash(struct inpcb *inp)
{
INP_INFO_WLOCK_ASSERT(inp->inp_pcbinfo);
INP_WLOCK_ASSERT(inp);
LIST_REMOVE(inp, inp_hash);
}
#endif /* INET */
/*
* Raw interface to IP protocol.
*/
/*
* Initialize raw connection block q.
*/
static void
rip_zone_change(void *tag)
{
uma_zone_set_max(V_ripcbinfo.ipi_zone, maxsockets);
}
static int
rip_inpcb_init(void *mem, int size, int flags)
{
struct inpcb *inp = mem;
INP_LOCK_INIT(inp, "inp", "rawinp");
return (0);
}
void
rip_init(void)
{
in_pcbinfo_init(&V_ripcbinfo, "rip", &V_ripcb, INP_PCBHASH_RAW_SIZE,
1, "ripcb", rip_inpcb_init, NULL, UMA_ZONE_NOFREE,
IPI_HASHFIELDS_NONE);
EVENTHANDLER_REGISTER(maxsockets_change, rip_zone_change, NULL,
EVENTHANDLER_PRI_ANY);
}
#ifdef VIMAGE
void
rip_destroy(void)
{
in_pcbinfo_destroy(&V_ripcbinfo);
}
#endif
#ifdef INET
static int
rip_append(struct inpcb *last, struct ip *ip, struct mbuf *n,
struct sockaddr_in *ripsrc)
{
int policyfail = 0;
INP_LOCK_ASSERT(last);
#ifdef IPSEC
/* check AH/ESP integrity. */
if (ipsec4_in_reject(n, last)) {
policyfail = 1;
}
#endif /* IPSEC */
#ifdef MAC
if (!policyfail && mac_inpcb_check_deliver(last, n) != 0)
policyfail = 1;
#endif
/* Check the minimum TTL for socket. */
if (last->inp_ip_minttl && last->inp_ip_minttl > ip->ip_ttl)
policyfail = 1;
if (!policyfail) {
struct mbuf *opts = NULL;
struct socket *so;
so = last->inp_socket;
if ((last->inp_flags & INP_CONTROLOPTS) ||
(so->so_options & (SO_TIMESTAMP | SO_BINTIME)))
ip_savecontrol(last, &opts, ip, n);
SOCKBUF_LOCK(&so->so_rcv);
if (sbappendaddr_locked(&so->so_rcv,
(struct sockaddr *)ripsrc, n, opts) == 0) {
/* should notify about lost packet */
m_freem(n);
if (opts)
m_freem(opts);
SOCKBUF_UNLOCK(&so->so_rcv);
} else
sorwakeup_locked(so);
} else
m_freem(n);
return (policyfail);
}
/*
* Setup generic address and protocol structures for raw_input routine, then
* pass them along with mbuf chain.
*/
void
rip_input(struct mbuf *m, int off)
{
struct ifnet *ifp;
struct ip *ip = mtod(m, struct ip *);
int proto = ip->ip_p;
struct inpcb *inp, *last;
struct sockaddr_in ripsrc;
int hash;
bzero(&ripsrc, sizeof(ripsrc));
ripsrc.sin_len = sizeof(ripsrc);
ripsrc.sin_family = AF_INET;
ripsrc.sin_addr = ip->ip_src;
last = NULL;
ifp = m->m_pkthdr.rcvif;
/*
* Applications on raw sockets expect host byte order.
*/
ip->ip_len = ntohs(ip->ip_len);
ip->ip_off = ntohs(ip->ip_off);
hash = INP_PCBHASH_RAW(proto, ip->ip_src.s_addr,
ip->ip_dst.s_addr, V_ripcbinfo.ipi_hashmask);
INP_INFO_RLOCK(&V_ripcbinfo);
LIST_FOREACH(inp, &V_ripcbinfo.ipi_hashbase[hash], inp_hash) {
if (inp->inp_ip_p != proto)
continue;
#ifdef INET6
/* XXX inp locking */
if ((inp->inp_vflag & INP_IPV4) == 0)
continue;
#endif
if (inp->inp_laddr.s_addr != ip->ip_dst.s_addr)
continue;
if (inp->inp_faddr.s_addr != ip->ip_src.s_addr)
continue;
if (jailed_without_vnet(inp->inp_cred)) {
/*
* XXX: If faddr was bound to multicast group,
* jailed raw socket will drop datagram.
*/
if (prison_check_ip4(inp->inp_cred, &ip->ip_dst) != 0)
continue;
}
if (last != NULL) {
struct mbuf *n;
n = m_copy(m, 0, (int)M_COPYALL);
if (n != NULL)
(void) rip_append(last, ip, n, &ripsrc);
/* XXX count dropped packet */
INP_RUNLOCK(last);
}
INP_RLOCK(inp);
last = inp;
}
LIST_FOREACH(inp, &V_ripcbinfo.ipi_hashbase[0], inp_hash) {
if (inp->inp_ip_p && inp->inp_ip_p != proto)
continue;
#ifdef INET6
/* XXX inp locking */
if ((inp->inp_vflag & INP_IPV4) == 0)
continue;
#endif
if (!in_nullhost(inp->inp_laddr) &&
!in_hosteq(inp->inp_laddr, ip->ip_dst))
continue;
if (!in_nullhost(inp->inp_faddr) &&
!in_hosteq(inp->inp_faddr, ip->ip_src))
continue;
if (jailed_without_vnet(inp->inp_cred)) {
/*
* Allow raw socket in jail to receive multicast;
* assume process had PRIV_NETINET_RAW at attach,
* and fall through into normal filter path if so.
*/
if (!IN_MULTICAST(ntohl(ip->ip_dst.s_addr)) &&
prison_check_ip4(inp->inp_cred, &ip->ip_dst) != 0)
continue;
}
/*
* If this raw socket has multicast state, and we
* have received a multicast, check if this socket
* should receive it, as multicast filtering is now
* the responsibility of the transport layer.
*/
if (inp->inp_moptions != NULL &&
IN_MULTICAST(ntohl(ip->ip_dst.s_addr))) {
/*
* If the incoming datagram is for IGMP, allow it
* through unconditionally to the raw socket.
*
* In the case of IGMPv2, we may not have explicitly
* joined the group, and may have set IFF_ALLMULTI
* on the interface. imo_multi_filter() may discard
* control traffic we actually need to see.
*
* Userland multicast routing daemons should continue
* filter the control traffic appropriately.
*/
int blocked;
blocked = MCAST_PASS;
if (proto != IPPROTO_IGMP) {
struct sockaddr_in group;
bzero(&group, sizeof(struct sockaddr_in));
group.sin_len = sizeof(struct sockaddr_in);
group.sin_family = AF_INET;
group.sin_addr = ip->ip_dst;
blocked = imo_multi_filter(inp->inp_moptions,
ifp,
(struct sockaddr *)&group,
(struct sockaddr *)&ripsrc);
}
if (blocked != MCAST_PASS) {
IPSTAT_INC(ips_notmember);
continue;
}
}
if (last != NULL) {
struct mbuf *n;
n = m_copy(m, 0, (int)M_COPYALL);
if (n != NULL)
(void) rip_append(last, ip, n, &ripsrc);
/* XXX count dropped packet */
INP_RUNLOCK(last);
}
INP_RLOCK(inp);
last = inp;
}
INP_INFO_RUNLOCK(&V_ripcbinfo);
if (last != NULL) {
if (rip_append(last, ip, m, &ripsrc) != 0)
IPSTAT_INC(ips_delivered);
INP_RUNLOCK(last);
} else {
m_freem(m);
IPSTAT_INC(ips_noproto);
IPSTAT_DEC(ips_delivered);
}
}
/*
* Generate IP header and pass packet to ip_output. Tack on options user may
* have setup with control call.
*/
int
rip_output(struct mbuf *m, struct socket *so, u_long dst)
{
struct ip *ip;
int error;
struct inpcb *inp = sotoinpcb(so);
int flags = ((so->so_options & SO_DONTROUTE) ? IP_ROUTETOIF : 0) |
IP_ALLOWBROADCAST;
/*
* If the user handed us a complete IP packet, use it. Otherwise,
* allocate an mbuf for a header and fill it in.
*/
if ((inp->inp_flags & INP_HDRINCL) == 0) {
if (m->m_pkthdr.len + sizeof(struct ip) > IP_MAXPACKET) {
m_freem(m);
return(EMSGSIZE);
}
M_PREPEND(m, sizeof(struct ip), M_NOWAIT);
if (m == NULL)
return(ENOBUFS);
INP_RLOCK(inp);
ip = mtod(m, struct ip *);
ip->ip_tos = inp->inp_ip_tos;
if (inp->inp_flags & INP_DONTFRAG)
ip->ip_off = htons(IP_DF);
else
ip->ip_off = htons(0);
ip->ip_p = inp->inp_ip_p;
ip->ip_len = htons(m->m_pkthdr.len);
ip->ip_src = inp->inp_laddr;
if (jailed(inp->inp_cred)) {
/*
* prison_local_ip4() would be good enough but would
* let a source of INADDR_ANY pass, which we do not
* want to see from jails. We do not go through the
* pain of in_pcbladdr() for raw sockets.
*/
if (ip->ip_src.s_addr == INADDR_ANY)
error = prison_get_ip4(inp->inp_cred,
&ip->ip_src);
else
error = prison_local_ip4(inp->inp_cred,
&ip->ip_src);
if (error != 0) {
INP_RUNLOCK(inp);
m_freem(m);
return (error);
}
}
ip->ip_dst.s_addr = dst;
ip->ip_ttl = inp->inp_ip_ttl;
} else {
if (m->m_pkthdr.len > IP_MAXPACKET) {
m_freem(m);
return(EMSGSIZE);
}
INP_RLOCK(inp);
ip = mtod(m, struct ip *);
error = prison_check_ip4(inp->inp_cred, &ip->ip_src);
if (error != 0) {
INP_RUNLOCK(inp);
m_freem(m);
return (error);
}
/*
* Don't allow both user specified and setsockopt options,
* and don't allow packet length sizes that will crash.
*/
if (((ip->ip_hl != (sizeof (*ip) >> 2)) && inp->inp_options)
|| (ip->ip_len > m->m_pkthdr.len)
|| (ip->ip_len < (ip->ip_hl << 2))) {
INP_RUNLOCK(inp);
m_freem(m);
return (EINVAL);
}
if (ip->ip_id == 0)
ip->ip_id = ip_newid();
/*
* Applications on raw sockets pass us packets
* in host byte order.
*/
ip->ip_len = htons(ip->ip_len);
ip->ip_off = htons(ip->ip_off);
/*
* XXX prevent ip_output from overwriting header fields.
*/
flags |= IP_RAWOUTPUT;
IPSTAT_INC(ips_rawout);
}
if (inp->inp_flags & INP_ONESBCAST)
flags |= IP_SENDONES;
#ifdef MAC
mac_inpcb_create_mbuf(inp, m);
#endif
error = ip_output(m, inp->inp_options, NULL, flags,
inp->inp_moptions, inp);
INP_RUNLOCK(inp);
return (error);
}
/*
* Raw IP socket option processing.
*
* IMPORTANT NOTE regarding access control: Traditionally, raw sockets could
* only be created by a privileged process, and as such, socket option
* operations to manage system properties on any raw socket were allowed to
* take place without explicit additional access control checks. However,
* raw sockets can now also be created in jail(), and therefore explicit
* checks are now required. Likewise, raw sockets can be used by a process
* after it gives up privilege, so some caution is required. For options
* passed down to the IP layer via ip_ctloutput(), checks are assumed to be
* performed in ip_ctloutput() and therefore no check occurs here.
* Unilaterally checking priv_check() here breaks normal IP socket option
* operations on raw sockets.
*
* When adding new socket options here, make sure to add access control
* checks here as necessary.
*
* XXX-BZ inp locking?
*/
int
rip_ctloutput(struct socket *so, struct sockopt *sopt)
{
struct inpcb *inp = sotoinpcb(so);
int error, optval;
if (sopt->sopt_level != IPPROTO_IP) {
if ((sopt->sopt_level == SOL_SOCKET) &&
(sopt->sopt_name == SO_SETFIB)) {
inp->inp_inc.inc_fibnum = so->so_fibnum;
return (0);
}
return (EINVAL);
}
error = 0;
switch (sopt->sopt_dir) {
case SOPT_GET:
switch (sopt->sopt_name) {
case IP_HDRINCL:
optval = inp->inp_flags & INP_HDRINCL;
error = sooptcopyout(sopt, &optval, sizeof optval);
break;
case IP_FW3: /* generic ipfw v.3 functions */
case IP_FW_ADD: /* ADD actually returns the body... */
case IP_FW_GET:
case IP_FW_TABLE_GETSIZE:
case IP_FW_TABLE_LIST:
case IP_FW_NAT_GET_CONFIG:
case IP_FW_NAT_GET_LOG:
if (V_ip_fw_ctl_ptr != NULL)
error = V_ip_fw_ctl_ptr(sopt);
else
error = ENOPROTOOPT;
break;
case IP_DUMMYNET3: /* generic dummynet v.3 functions */
case IP_DUMMYNET_GET:
if (ip_dn_ctl_ptr != NULL)
error = ip_dn_ctl_ptr(sopt);
else
error = ENOPROTOOPT;
break ;
case MRT_INIT:
case MRT_DONE:
case MRT_ADD_VIF:
case MRT_DEL_VIF:
case MRT_ADD_MFC:
case MRT_DEL_MFC:
case MRT_VERSION:
case MRT_ASSERT:
case MRT_API_SUPPORT:
case MRT_API_CONFIG:
case MRT_ADD_BW_UPCALL:
case MRT_DEL_BW_UPCALL:
error = priv_check(curthread, PRIV_NETINET_MROUTE);
if (error != 0)
return (error);
error = ip_mrouter_get ? ip_mrouter_get(so, sopt) :
EOPNOTSUPP;
break;
default:
error = ip_ctloutput(so, sopt);
break;
}
break;
case SOPT_SET:
switch (sopt->sopt_name) {
case IP_HDRINCL:
error = sooptcopyin(sopt, &optval, sizeof optval,
sizeof optval);
if (error)
break;
if (optval)
inp->inp_flags |= INP_HDRINCL;
else
inp->inp_flags &= ~INP_HDRINCL;
break;
case IP_FW3: /* generic ipfw v.3 functions */
case IP_FW_ADD:
case IP_FW_DEL:
case IP_FW_FLUSH:
case IP_FW_ZERO:
case IP_FW_RESETLOG:
case IP_FW_TABLE_ADD:
case IP_FW_TABLE_DEL:
case IP_FW_TABLE_FLUSH:
case IP_FW_NAT_CFG:
case IP_FW_NAT_DEL:
if (V_ip_fw_ctl_ptr != NULL)
error = V_ip_fw_ctl_ptr(sopt);
else
error = ENOPROTOOPT;
break;
case IP_DUMMYNET3: /* generic dummynet v.3 functions */
case IP_DUMMYNET_CONFIGURE:
case IP_DUMMYNET_DEL:
case IP_DUMMYNET_FLUSH:
if (ip_dn_ctl_ptr != NULL)
error = ip_dn_ctl_ptr(sopt);
else
error = ENOPROTOOPT ;
break ;
case IP_RSVP_ON:
error = priv_check(curthread, PRIV_NETINET_MROUTE);
if (error != 0)
return (error);
error = ip_rsvp_init(so);
break;
case IP_RSVP_OFF:
error = priv_check(curthread, PRIV_NETINET_MROUTE);
if (error != 0)
return (error);
error = ip_rsvp_done();
break;
case IP_RSVP_VIF_ON:
case IP_RSVP_VIF_OFF:
error = priv_check(curthread, PRIV_NETINET_MROUTE);
if (error != 0)
return (error);
error = ip_rsvp_vif ?
ip_rsvp_vif(so, sopt) : EINVAL;
break;
case MRT_INIT:
case MRT_DONE:
case MRT_ADD_VIF:
case MRT_DEL_VIF:
case MRT_ADD_MFC:
case MRT_DEL_MFC:
case MRT_VERSION:
case MRT_ASSERT:
case MRT_API_SUPPORT:
case MRT_API_CONFIG:
case MRT_ADD_BW_UPCALL:
case MRT_DEL_BW_UPCALL:
error = priv_check(curthread, PRIV_NETINET_MROUTE);
if (error != 0)
return (error);
error = ip_mrouter_set ? ip_mrouter_set(so, sopt) :
EOPNOTSUPP;
break;
default:
error = ip_ctloutput(so, sopt);
break;
}
break;
}
return (error);
}
/*
* This function exists solely to receive the PRC_IFDOWN messages which are
* sent by if_down(). It looks for an ifaddr whose ifa_addr is sa, and calls
* in_ifadown() to remove all routes corresponding to that address. It also
* receives the PRC_IFUP messages from if_up() and reinstalls the interface
* routes.
*/
void
rip_ctlinput(int cmd, struct sockaddr *sa, void *vip)
{
struct in_ifaddr *ia;
struct ifnet *ifp;
int err;
int flags;
switch (cmd) {
case PRC_IFDOWN:
IN_IFADDR_RLOCK();
TAILQ_FOREACH(ia, &V_in_ifaddrhead, ia_link) {
if (ia->ia_ifa.ifa_addr == sa
&& (ia->ia_flags & IFA_ROUTE)) {
ifa_ref(&ia->ia_ifa);
IN_IFADDR_RUNLOCK();
/*
* in_ifscrub kills the interface route.
*/
in_ifscrub(ia->ia_ifp, ia, 0);
/*
* in_ifadown gets rid of all the rest of the
* routes. This is not quite the right thing
* to do, but at least if we are running a
* routing process they will come back.
*/
in_ifadown(&ia->ia_ifa, 0);
ifa_free(&ia->ia_ifa);
break;
}
}
if (ia == NULL) /* If ia matched, already unlocked. */
IN_IFADDR_RUNLOCK();
break;
case PRC_IFUP:
IN_IFADDR_RLOCK();
TAILQ_FOREACH(ia, &V_in_ifaddrhead, ia_link) {
if (ia->ia_ifa.ifa_addr == sa)
break;
}
if (ia == NULL || (ia->ia_flags & IFA_ROUTE)) {
IN_IFADDR_RUNLOCK();
return;
}
ifa_ref(&ia->ia_ifa);
IN_IFADDR_RUNLOCK();
flags = RTF_UP;
ifp = ia->ia_ifa.ifa_ifp;
if ((ifp->if_flags & IFF_LOOPBACK)
|| (ifp->if_flags & IFF_POINTOPOINT))
flags |= RTF_HOST;
err = ifa_del_loopback_route((struct ifaddr *)ia, sa);
if (err == 0)
ia->ia_flags &= ~IFA_RTSELF;
err = rtinit(&ia->ia_ifa, RTM_ADD, flags);
if (err == 0)
ia->ia_flags |= IFA_ROUTE;
err = ifa_add_loopback_route((struct ifaddr *)ia, sa);
if (err == 0)
ia->ia_flags |= IFA_RTSELF;
ifa_free(&ia->ia_ifa);
break;
}
}
static int
rip_attach(struct socket *so, int proto, struct thread *td)
{
struct inpcb *inp;
int error;
inp = sotoinpcb(so);
KASSERT(inp == NULL, ("rip_attach: inp != NULL"));
error = priv_check(td, PRIV_NETINET_RAW);
if (error)
return (error);
if (proto >= IPPROTO_MAX || proto < 0)
return EPROTONOSUPPORT;
error = soreserve(so, rip_sendspace, rip_recvspace);
if (error)
return (error);
INP_INFO_WLOCK(&V_ripcbinfo);
error = in_pcballoc(so, &V_ripcbinfo);
if (error) {
INP_INFO_WUNLOCK(&V_ripcbinfo);
return (error);
}
inp = (struct inpcb *)so->so_pcb;
inp->inp_vflag |= INP_IPV4;
inp->inp_ip_p = proto;
inp->inp_ip_ttl = V_ip_defttl;
rip_inshash(inp);
INP_INFO_WUNLOCK(&V_ripcbinfo);
INP_WUNLOCK(inp);
return (0);
}
static void
rip_detach(struct socket *so)
{
struct inpcb *inp;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_detach: inp == NULL"));
KASSERT(inp->inp_faddr.s_addr == INADDR_ANY,
("rip_detach: not closed"));
INP_INFO_WLOCK(&V_ripcbinfo);
INP_WLOCK(inp);
rip_delhash(inp);
if (so == V_ip_mrouter && ip_mrouter_done)
ip_mrouter_done();
if (ip_rsvp_force_done)
ip_rsvp_force_done(so);
if (so == V_ip_rsvpd)
ip_rsvp_done();
in_pcbdetach(inp);
in_pcbfree(inp);
INP_INFO_WUNLOCK(&V_ripcbinfo);
}
static void
rip_dodisconnect(struct socket *so, struct inpcb *inp)
{
struct inpcbinfo *pcbinfo;
pcbinfo = inp->inp_pcbinfo;
INP_INFO_WLOCK(pcbinfo);
INP_WLOCK(inp);
rip_delhash(inp);
inp->inp_faddr.s_addr = INADDR_ANY;
rip_inshash(inp);
SOCK_LOCK(so);
so->so_state &= ~SS_ISCONNECTED;
SOCK_UNLOCK(so);
INP_WUNLOCK(inp);
INP_INFO_WUNLOCK(pcbinfo);
}
static void
rip_abort(struct socket *so)
{
struct inpcb *inp;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_abort: inp == NULL"));
rip_dodisconnect(so, inp);
}
static void
rip_close(struct socket *so)
{
struct inpcb *inp;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_close: inp == NULL"));
rip_dodisconnect(so, inp);
}
static int
rip_disconnect(struct socket *so)
{
struct inpcb *inp;
if ((so->so_state & SS_ISCONNECTED) == 0)
return (ENOTCONN);
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_disconnect: inp == NULL"));
rip_dodisconnect(so, inp);
return (0);
}
static int
rip_bind(struct socket *so, struct sockaddr *nam, struct thread *td)
{
struct sockaddr_in *addr = (struct sockaddr_in *)nam;
struct inpcb *inp;
int error;
if (nam->sa_len != sizeof(*addr))
return (EINVAL);
error = prison_check_ip4(td->td_ucred, &addr->sin_addr);
if (error != 0)
return (error);
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_bind: inp == NULL"));
if (TAILQ_EMPTY(&V_ifnet) ||
(addr->sin_family != AF_INET && addr->sin_family != AF_IMPLINK) ||
(addr->sin_addr.s_addr &&
(inp->inp_flags & INP_BINDANY) == 0 &&
ifa_ifwithaddr_check((struct sockaddr *)addr) == 0))
return (EADDRNOTAVAIL);
INP_INFO_WLOCK(&V_ripcbinfo);
INP_WLOCK(inp);
rip_delhash(inp);
inp->inp_laddr = addr->sin_addr;
rip_inshash(inp);
INP_WUNLOCK(inp);
INP_INFO_WUNLOCK(&V_ripcbinfo);
return (0);
}
static int
rip_connect(struct socket *so, struct sockaddr *nam, struct thread *td)
{
struct sockaddr_in *addr = (struct sockaddr_in *)nam;
struct inpcb *inp;
if (nam->sa_len != sizeof(*addr))
return (EINVAL);
if (TAILQ_EMPTY(&V_ifnet))
return (EADDRNOTAVAIL);
if (addr->sin_family != AF_INET && addr->sin_family != AF_IMPLINK)
return (EAFNOSUPPORT);
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_connect: inp == NULL"));
INP_INFO_WLOCK(&V_ripcbinfo);
INP_WLOCK(inp);
rip_delhash(inp);
inp->inp_faddr = addr->sin_addr;
rip_inshash(inp);
soisconnected(so);
INP_WUNLOCK(inp);
INP_INFO_WUNLOCK(&V_ripcbinfo);
return (0);
}
static int
rip_shutdown(struct socket *so)
{
struct inpcb *inp;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_shutdown: inp == NULL"));
INP_WLOCK(inp);
socantsendmore(so);
INP_WUNLOCK(inp);
return (0);
}
static int
rip_send(struct socket *so, int flags, struct mbuf *m, struct sockaddr *nam,
struct mbuf *control, struct thread *td)
{
struct inpcb *inp;
u_long dst;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_send: inp == NULL"));
/*
* Note: 'dst' reads below are unlocked.
*/
if (so->so_state & SS_ISCONNECTED) {
if (nam) {
m_freem(m);
return (EISCONN);
}
dst = inp->inp_faddr.s_addr; /* Unlocked read. */
} else {
if (nam == NULL) {
m_freem(m);