/
udp_usrreq.c
1718 lines (1559 loc) · 43.7 KB
/
udp_usrreq.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
/*-
* SPDX-License-Identifier: BSD-3-Clause
*
* Copyright (c) 1982, 1986, 1988, 1990, 1993, 1995
* The Regents of the University of California.
* Copyright (c) 2008 Robert N. M. Watson
* Copyright (c) 2010-2011 Juniper Networks, Inc.
* Copyright (c) 2014 Kevin Lo
* All rights reserved.
*
* Portions of this software were developed by Robert N. M. Watson under
* contract to Juniper Networks, Inc.
*
* 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.
*
* @(#)udp_usrreq.c 8.6 (Berkeley) 5/23/95
*/
#include <sys/cdefs.h>
#include "opt_inet.h"
#include "opt_inet6.h"
#include "opt_ipsec.h"
#include "opt_route.h"
#include "opt_rss.h"
#include <sys/param.h>
#include <sys/domain.h>
#include <sys/eventhandler.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/sdt.h>
#include <sys/signalvar.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/sx.h>
#include <sys/sysctl.h>
#include <sys/syslog.h>
#include <sys/systm.h>
#include <vm/uma.h>
#include <net/if.h>
#include <net/if_var.h>
#include <net/route.h>
#include <net/route/nhop.h>
#include <net/rss_config.h>
#include <netinet/in.h>
#include <netinet/in_kdtrace.h>
#include <netinet/in_fib.h>
#include <netinet/in_pcb.h>
#include <netinet/in_systm.h>
#include <netinet/in_var.h>
#include <netinet/ip.h>
#ifdef INET6
#include <netinet/ip6.h>
#endif
#include <netinet/ip_icmp.h>
#include <netinet/icmp_var.h>
#include <netinet/ip_var.h>
#include <netinet/ip_options.h>
#ifdef INET6
#include <netinet6/ip6_var.h>
#endif
#include <netinet/udp.h>
#include <netinet/udp_var.h>
#include <netinet/udplite.h>
#include <netinet/in_rss.h>
#include <netipsec/ipsec_support.h>
#include <machine/in_cksum.h>
#include <security/mac/mac_framework.h>
/*
* UDP and UDP-Lite protocols implementation.
* Per RFC 768, August, 1980.
* Per RFC 3828, July, 2004.
*/
/*
* BSD 4.2 defaulted the udp checksum to be off. Turning off udp checksums
* removes the only data integrity mechanism for packets and malformed
* packets that would otherwise be discarded due to bad checksums, and may
* cause problems (especially for NFS data blocks).
*/
VNET_DEFINE(int, udp_cksum) = 1;
SYSCTL_INT(_net_inet_udp, UDPCTL_CHECKSUM, checksum, CTLFLAG_VNET | CTLFLAG_RW,
&VNET_NAME(udp_cksum), 0, "compute udp checksum");
VNET_DEFINE(int, udp_log_in_vain) = 0;
SYSCTL_INT(_net_inet_udp, OID_AUTO, log_in_vain, CTLFLAG_VNET | CTLFLAG_RW,
&VNET_NAME(udp_log_in_vain), 0, "Log all incoming UDP packets");
VNET_DEFINE(int, udp_blackhole) = 0;
SYSCTL_INT(_net_inet_udp, OID_AUTO, blackhole, CTLFLAG_VNET | CTLFLAG_RW,
&VNET_NAME(udp_blackhole), 0,
"Do not send port unreachables for refused connects");
VNET_DEFINE(bool, udp_blackhole_local) = false;
SYSCTL_BOOL(_net_inet_udp, OID_AUTO, blackhole_local, CTLFLAG_VNET |
CTLFLAG_RW, &VNET_NAME(udp_blackhole_local), false,
"Enforce net.inet.udp.blackhole for locally originated packets");
u_long udp_sendspace = 9216; /* really max datagram size */
SYSCTL_ULONG(_net_inet_udp, UDPCTL_MAXDGRAM, maxdgram, CTLFLAG_RW,
&udp_sendspace, 0, "Maximum outgoing UDP datagram size");
u_long udp_recvspace = 40 * (1024 +
#ifdef INET6
sizeof(struct sockaddr_in6)
#else
sizeof(struct sockaddr_in)
#endif
); /* 40 1K datagrams */
SYSCTL_ULONG(_net_inet_udp, UDPCTL_RECVSPACE, recvspace, CTLFLAG_RW,
&udp_recvspace, 0, "Maximum space for incoming UDP datagrams");
VNET_DEFINE(struct inpcbinfo, udbinfo);
VNET_DEFINE(struct inpcbinfo, ulitecbinfo);
#ifndef UDBHASHSIZE
#define UDBHASHSIZE 128
#endif
VNET_PCPUSTAT_DEFINE(struct udpstat, udpstat); /* from udp_var.h */
VNET_PCPUSTAT_SYSINIT(udpstat);
SYSCTL_VNET_PCPUSTAT(_net_inet_udp, UDPCTL_STATS, stats, struct udpstat,
udpstat, "UDP statistics (struct udpstat, netinet/udp_var.h)");
#ifdef VIMAGE
VNET_PCPUSTAT_SYSUNINIT(udpstat);
#endif /* VIMAGE */
#ifdef INET
static void udp_detach(struct socket *so);
#endif
INPCBSTORAGE_DEFINE(udpcbstor, udpcb, "udpinp", "udp_inpcb", "udp", "udphash");
INPCBSTORAGE_DEFINE(udplitecbstor, udpcb, "udpliteinp", "udplite_inpcb",
"udplite", "udplitehash");
static void
udp_vnet_init(void *arg __unused)
{
/*
* For now default to 2-tuple UDP hashing - until the fragment
* reassembly code can also update the flowid.
*
* Once we can calculate the flowid that way and re-establish
* a 4-tuple, flip this to 4-tuple.
*/
in_pcbinfo_init(&V_udbinfo, &udpcbstor, UDBHASHSIZE, UDBHASHSIZE);
/* Additional pcbinfo for UDP-Lite */
in_pcbinfo_init(&V_ulitecbinfo, &udplitecbstor, UDBHASHSIZE,
UDBHASHSIZE);
}
VNET_SYSINIT(udp_vnet_init, SI_SUB_PROTO_DOMAIN, SI_ORDER_FOURTH,
udp_vnet_init, NULL);
/*
* Kernel module interface for updating udpstat. The argument is an index
* into udpstat treated as an array of u_long. While this encodes the
* general layout of udpstat into the caller, it doesn't encode its location,
* so that future changes to add, for example, per-CPU stats support won't
* cause binary compatibility problems for kernel modules.
*/
void
kmod_udpstat_inc(int statnum)
{
counter_u64_add(VNET(udpstat)[statnum], 1);
}
#ifdef VIMAGE
static void
udp_destroy(void *unused __unused)
{
in_pcbinfo_destroy(&V_udbinfo);
in_pcbinfo_destroy(&V_ulitecbinfo);
}
VNET_SYSUNINIT(udp, SI_SUB_PROTO_DOMAIN, SI_ORDER_FOURTH, udp_destroy, NULL);
#endif
#ifdef INET
/*
* Subroutine of udp_input(), which appends the provided mbuf chain to the
* passed pcb/socket. The caller must provide a sockaddr_in via udp_in that
* contains the source address. If the socket ends up being an IPv6 socket,
* udp_append() will convert to a sockaddr_in6 before passing the address
* into the socket code.
*
* In the normal case udp_append() will return 0, indicating that you
* must unlock the inp. However if a tunneling protocol is in place we increment
* the inpcb refcnt and unlock the inp, on return from the tunneling protocol we
* then decrement the reference count. If the inp_rele returns 1, indicating the
* inp is gone, we return that to the caller to tell them *not* to unlock
* the inp. In the case of multi-cast this will cause the distribution
* to stop (though most tunneling protocols known currently do *not* use
* multicast).
*/
static int
udp_append(struct inpcb *inp, struct ip *ip, struct mbuf *n, int off,
struct sockaddr_in *udp_in)
{
struct sockaddr *append_sa;
struct socket *so;
struct mbuf *tmpopts, *opts = NULL;
#ifdef INET6
struct sockaddr_in6 udp_in6;
#endif
struct udpcb *up;
bool filtered;
INP_LOCK_ASSERT(inp);
/*
* Engage the tunneling protocol.
*/
up = intoudpcb(inp);
if (up->u_tun_func != NULL) {
in_pcbref(inp);
INP_RUNLOCK(inp);
filtered = (*up->u_tun_func)(n, off, inp, (struct sockaddr *)&udp_in[0],
up->u_tun_ctx);
INP_RLOCK(inp);
if (filtered)
return (in_pcbrele_rlocked(inp));
}
off += sizeof(struct udphdr);
#if defined(IPSEC) || defined(IPSEC_SUPPORT)
/* Check AH/ESP integrity. */
if (IPSEC_ENABLED(ipv4) &&
IPSEC_CHECK_POLICY(ipv4, n, inp) != 0) {
m_freem(n);
return (0);
}
if (up->u_flags & UF_ESPINUDP) {/* IPSec UDP encaps. */
if (IPSEC_ENABLED(ipv4) &&
UDPENCAP_INPUT(n, off, AF_INET) != 0)
return (0); /* Consumed. */
}
#endif /* IPSEC */
#ifdef MAC
if (mac_inpcb_check_deliver(inp, n) != 0) {
m_freem(n);
return (0);
}
#endif /* MAC */
if (inp->inp_flags & INP_CONTROLOPTS ||
inp->inp_socket->so_options & (SO_TIMESTAMP | SO_BINTIME)) {
#ifdef INET6
if (inp->inp_vflag & INP_IPV6)
(void)ip6_savecontrol_v4(inp, n, &opts, NULL);
else
#endif /* INET6 */
ip_savecontrol(inp, &opts, ip, n);
}
if ((inp->inp_vflag & INP_IPV4) && (inp->inp_flags2 & INP_ORIGDSTADDR)) {
tmpopts = sbcreatecontrol(&udp_in[1],
sizeof(struct sockaddr_in), IP_ORIGDSTADDR, IPPROTO_IP,
M_NOWAIT);
if (tmpopts) {
if (opts) {
tmpopts->m_next = opts;
opts = tmpopts;
} else
opts = tmpopts;
}
}
#ifdef INET6
if (inp->inp_vflag & INP_IPV6) {
bzero(&udp_in6, sizeof(udp_in6));
udp_in6.sin6_len = sizeof(udp_in6);
udp_in6.sin6_family = AF_INET6;
in6_sin_2_v4mapsin6(&udp_in[0], &udp_in6);
append_sa = (struct sockaddr *)&udp_in6;
} else
#endif /* INET6 */
append_sa = (struct sockaddr *)&udp_in[0];
m_adj(n, off);
so = inp->inp_socket;
SOCKBUF_LOCK(&so->so_rcv);
if (sbappendaddr_locked(&so->so_rcv, append_sa, n, opts) == 0) {
soroverflow_locked(so);
m_freem(n);
if (opts)
m_freem(opts);
UDPSTAT_INC(udps_fullsock);
} else
sorwakeup_locked(so);
return (0);
}
static bool
udp_multi_match(const struct inpcb *inp, void *v)
{
struct ip *ip = v;
struct udphdr *uh = (struct udphdr *)(ip + 1);
if (inp->inp_lport != uh->uh_dport)
return (false);
#ifdef INET6
if ((inp->inp_vflag & INP_IPV4) == 0)
return (false);
#endif
if (inp->inp_laddr.s_addr != INADDR_ANY &&
inp->inp_laddr.s_addr != ip->ip_dst.s_addr)
return (false);
if (inp->inp_faddr.s_addr != INADDR_ANY &&
inp->inp_faddr.s_addr != ip->ip_src.s_addr)
return (false);
if (inp->inp_fport != 0 &&
inp->inp_fport != uh->uh_sport)
return (false);
return (true);
}
static int
udp_multi_input(struct mbuf *m, int proto, struct sockaddr_in *udp_in)
{
struct ip *ip = mtod(m, struct ip *);
struct inpcb_iterator inpi = INP_ITERATOR(udp_get_inpcbinfo(proto),
INPLOOKUP_RLOCKPCB, udp_multi_match, ip);
#ifdef KDTRACE_HOOKS
struct udphdr *uh = (struct udphdr *)(ip + 1);
#endif
struct inpcb *inp;
struct mbuf *n;
int appends = 0;
MPASS(ip->ip_hl == sizeof(struct ip) >> 2);
while ((inp = inp_next(&inpi)) != NULL) {
/*
* XXXRW: Because we weren't holding either the inpcb
* or the hash lock when we checked for a match
* before, we should probably recheck now that the
* inpcb lock is held.
*/
/*
* Handle socket delivery policy for any-source
* and source-specific multicast. [RFC3678]
*/
if (IN_MULTICAST(ntohl(ip->ip_dst.s_addr))) {
struct ip_moptions *imo;
struct sockaddr_in group;
int blocked;
imo = inp->inp_moptions;
if (imo == NULL)
continue;
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(imo, m->m_pkthdr.rcvif,
(struct sockaddr *)&group,
(struct sockaddr *)&udp_in[0]);
if (blocked != MCAST_PASS) {
if (blocked == MCAST_NOTGMEMBER)
IPSTAT_INC(ips_notmember);
if (blocked == MCAST_NOTSMEMBER ||
blocked == MCAST_MUTED)
UDPSTAT_INC(udps_filtermcast);
continue;
}
}
if ((n = m_copym(m, 0, M_COPYALL, M_NOWAIT)) != NULL) {
if (proto == IPPROTO_UDPLITE)
UDPLITE_PROBE(receive, NULL, inp, ip, inp, uh);
else
UDP_PROBE(receive, NULL, inp, ip, inp, uh);
if (udp_append(inp, ip, n, sizeof(struct ip), udp_in)) {
break;
} else
appends++;
}
/*
* Don't look for additional matches if this one does
* not have either the SO_REUSEPORT or SO_REUSEADDR
* socket options set. This heuristic avoids
* searching through all pcbs in the common case of a
* non-shared port. It assumes that an application
* will never clear these options after setting them.
*/
if ((inp->inp_socket->so_options &
(SO_REUSEPORT|SO_REUSEPORT_LB|SO_REUSEADDR)) == 0) {
INP_RUNLOCK(inp);
break;
}
}
if (appends == 0) {
/*
* No matching pcb found; discard datagram. (No need
* to send an ICMP Port Unreachable for a broadcast
* or multicast datgram.)
*/
UDPSTAT_INC(udps_noport);
if (IN_MULTICAST(ntohl(ip->ip_dst.s_addr)))
UDPSTAT_INC(udps_noportmcast);
else
UDPSTAT_INC(udps_noportbcast);
}
m_freem(m);
return (IPPROTO_DONE);
}
static int
udp_input(struct mbuf **mp, int *offp, int proto)
{
struct ip *ip;
struct udphdr *uh;
struct ifnet *ifp;
struct inpcb *inp;
uint16_t len, ip_len;
struct inpcbinfo *pcbinfo;
struct sockaddr_in udp_in[2];
struct mbuf *m;
struct m_tag *fwd_tag;
int cscov_partial, iphlen;
m = *mp;
iphlen = *offp;
ifp = m->m_pkthdr.rcvif;
*mp = NULL;
UDPSTAT_INC(udps_ipackets);
/*
* Strip IP options, if any; should skip this, make available to
* user, and use on returned packets, but we don't yet have a way to
* check the checksum with options still present.
*/
if (iphlen > sizeof (struct ip)) {
ip_stripoptions(m);
iphlen = sizeof(struct ip);
}
/*
* Get IP and UDP header together in first mbuf.
*/
if (m->m_len < iphlen + sizeof(struct udphdr)) {
if ((m = m_pullup(m, iphlen + sizeof(struct udphdr))) == NULL) {
UDPSTAT_INC(udps_hdrops);
return (IPPROTO_DONE);
}
}
ip = mtod(m, struct ip *);
uh = (struct udphdr *)((caddr_t)ip + iphlen);
cscov_partial = (proto == IPPROTO_UDPLITE) ? 1 : 0;
/*
* Destination port of 0 is illegal, based on RFC768.
*/
if (uh->uh_dport == 0)
goto badunlocked;
/*
* Construct sockaddr format source address. Stuff source address
* and datagram in user buffer.
*/
bzero(&udp_in[0], sizeof(struct sockaddr_in) * 2);
udp_in[0].sin_len = sizeof(struct sockaddr_in);
udp_in[0].sin_family = AF_INET;
udp_in[0].sin_port = uh->uh_sport;
udp_in[0].sin_addr = ip->ip_src;
udp_in[1].sin_len = sizeof(struct sockaddr_in);
udp_in[1].sin_family = AF_INET;
udp_in[1].sin_port = uh->uh_dport;
udp_in[1].sin_addr = ip->ip_dst;
/*
* Make mbuf data length reflect UDP length. If not enough data to
* reflect UDP length, drop.
*/
len = ntohs((u_short)uh->uh_ulen);
ip_len = ntohs(ip->ip_len) - iphlen;
if (proto == IPPROTO_UDPLITE && (len == 0 || len == ip_len)) {
/* Zero means checksum over the complete packet. */
if (len == 0)
len = ip_len;
cscov_partial = 0;
}
if (ip_len != len) {
if (len > ip_len || len < sizeof(struct udphdr)) {
UDPSTAT_INC(udps_badlen);
goto badunlocked;
}
if (proto == IPPROTO_UDP)
m_adj(m, len - ip_len);
}
/*
* Checksum extended UDP header and data.
*/
if (uh->uh_sum) {
u_short uh_sum;
if ((m->m_pkthdr.csum_flags & CSUM_DATA_VALID) &&
!cscov_partial) {
if (m->m_pkthdr.csum_flags & CSUM_PSEUDO_HDR)
uh_sum = m->m_pkthdr.csum_data;
else
uh_sum = in_pseudo(ip->ip_src.s_addr,
ip->ip_dst.s_addr, htonl((u_short)len +
m->m_pkthdr.csum_data + proto));
uh_sum ^= 0xffff;
} else {
char b[offsetof(struct ipovly, ih_src)];
struct ipovly *ipov = (struct ipovly *)ip;
bcopy(ipov, b, sizeof(b));
bzero(ipov, sizeof(ipov->ih_x1));
ipov->ih_len = (proto == IPPROTO_UDP) ?
uh->uh_ulen : htons(ip_len);
uh_sum = in_cksum(m, len + sizeof (struct ip));
bcopy(b, ipov, sizeof(b));
}
if (uh_sum) {
UDPSTAT_INC(udps_badsum);
m_freem(m);
return (IPPROTO_DONE);
}
} else {
if (proto == IPPROTO_UDP) {
UDPSTAT_INC(udps_nosum);
} else {
/* UDPLite requires a checksum */
/* XXX: What is the right UDPLite MIB counter here? */
m_freem(m);
return (IPPROTO_DONE);
}
}
if (IN_MULTICAST(ntohl(ip->ip_dst.s_addr)) ||
in_broadcast(ip->ip_dst, ifp))
return (udp_multi_input(m, proto, udp_in));
pcbinfo = udp_get_inpcbinfo(proto);
/*
* Locate pcb for datagram.
*
* Grab info from PACKET_TAG_IPFORWARD tag prepended to the chain.
*/
if ((m->m_flags & M_IP_NEXTHOP) &&
(fwd_tag = m_tag_find(m, PACKET_TAG_IPFORWARD, NULL)) != NULL) {
struct sockaddr_in *next_hop;
next_hop = (struct sockaddr_in *)(fwd_tag + 1);
/*
* Transparently forwarded. Pretend to be the destination.
* Already got one like this?
*/
inp = in_pcblookup_mbuf(pcbinfo, ip->ip_src, uh->uh_sport,
ip->ip_dst, uh->uh_dport, INPLOOKUP_RLOCKPCB, ifp, m);
if (!inp) {
/*
* It's new. Try to find the ambushing socket.
* Because we've rewritten the destination address,
* any hardware-generated hash is ignored.
*/
inp = in_pcblookup(pcbinfo, ip->ip_src,
uh->uh_sport, next_hop->sin_addr,
next_hop->sin_port ? htons(next_hop->sin_port) :
uh->uh_dport, INPLOOKUP_WILDCARD |
INPLOOKUP_RLOCKPCB, ifp);
}
/* Remove the tag from the packet. We don't need it anymore. */
m_tag_delete(m, fwd_tag);
m->m_flags &= ~M_IP_NEXTHOP;
} else
inp = in_pcblookup_mbuf(pcbinfo, ip->ip_src, uh->uh_sport,
ip->ip_dst, uh->uh_dport, INPLOOKUP_WILDCARD |
INPLOOKUP_RLOCKPCB, ifp, m);
if (inp == NULL) {
if (V_udp_log_in_vain) {
char src[INET_ADDRSTRLEN];
char dst[INET_ADDRSTRLEN];
log(LOG_INFO,
"Connection attempt to UDP %s:%d from %s:%d\n",
inet_ntoa_r(ip->ip_dst, dst), ntohs(uh->uh_dport),
inet_ntoa_r(ip->ip_src, src), ntohs(uh->uh_sport));
}
if (proto == IPPROTO_UDPLITE)
UDPLITE_PROBE(receive, NULL, NULL, ip, NULL, uh);
else
UDP_PROBE(receive, NULL, NULL, ip, NULL, uh);
UDPSTAT_INC(udps_noport);
if (m->m_flags & (M_BCAST | M_MCAST)) {
UDPSTAT_INC(udps_noportbcast);
goto badunlocked;
}
if (V_udp_blackhole && (V_udp_blackhole_local ||
!in_localip(ip->ip_src)))
goto badunlocked;
if (badport_bandlim(BANDLIM_ICMP_UNREACH) < 0)
goto badunlocked;
icmp_error(m, ICMP_UNREACH, ICMP_UNREACH_PORT, 0, 0);
return (IPPROTO_DONE);
}
/*
* Check the minimum TTL for socket.
*/
INP_RLOCK_ASSERT(inp);
if (inp->inp_ip_minttl && inp->inp_ip_minttl > ip->ip_ttl) {
if (proto == IPPROTO_UDPLITE)
UDPLITE_PROBE(receive, NULL, inp, ip, inp, uh);
else
UDP_PROBE(receive, NULL, inp, ip, inp, uh);
INP_RUNLOCK(inp);
m_freem(m);
return (IPPROTO_DONE);
}
if (cscov_partial) {
struct udpcb *up;
up = intoudpcb(inp);
if (up->u_rxcslen == 0 || up->u_rxcslen > len) {
INP_RUNLOCK(inp);
m_freem(m);
return (IPPROTO_DONE);
}
}
if (proto == IPPROTO_UDPLITE)
UDPLITE_PROBE(receive, NULL, inp, ip, inp, uh);
else
UDP_PROBE(receive, NULL, inp, ip, inp, uh);
if (udp_append(inp, ip, m, iphlen, udp_in) == 0)
INP_RUNLOCK(inp);
return (IPPROTO_DONE);
badunlocked:
m_freem(m);
return (IPPROTO_DONE);
}
#endif /* INET */
/*
* Notify a udp user of an asynchronous error; just wake up so that they can
* collect error status.
*/
struct inpcb *
udp_notify(struct inpcb *inp, int errno)
{
INP_WLOCK_ASSERT(inp);
if ((errno == EHOSTUNREACH || errno == ENETUNREACH ||
errno == EHOSTDOWN) && inp->inp_route.ro_nh) {
NH_FREE(inp->inp_route.ro_nh);
inp->inp_route.ro_nh = (struct nhop_object *)NULL;
}
inp->inp_socket->so_error = errno;
sorwakeup(inp->inp_socket);
sowwakeup(inp->inp_socket);
return (inp);
}
#ifdef INET
static void
udp_common_ctlinput(struct icmp *icmp, struct inpcbinfo *pcbinfo)
{
struct ip *ip = &icmp->icmp_ip;
struct udphdr *uh;
struct inpcb *inp;
if (icmp_errmap(icmp) == 0)
return;
uh = (struct udphdr *)((caddr_t)ip + (ip->ip_hl << 2));
inp = in_pcblookup(pcbinfo, ip->ip_dst, uh->uh_dport, ip->ip_src,
uh->uh_sport, INPLOOKUP_WLOCKPCB, NULL);
if (inp != NULL) {
INP_WLOCK_ASSERT(inp);
if (inp->inp_socket != NULL)
udp_notify(inp, icmp_errmap(icmp));
INP_WUNLOCK(inp);
} else {
inp = in_pcblookup(pcbinfo, ip->ip_dst, uh->uh_dport,
ip->ip_src, uh->uh_sport,
INPLOOKUP_WILDCARD | INPLOOKUP_RLOCKPCB, NULL);
if (inp != NULL) {
struct udpcb *up;
udp_tun_icmp_t *func;
up = intoudpcb(inp);
func = up->u_icmp_func;
INP_RUNLOCK(inp);
if (func != NULL)
func(icmp);
}
}
}
static void
udp_ctlinput(struct icmp *icmp)
{
return (udp_common_ctlinput(icmp, &V_udbinfo));
}
static void
udplite_ctlinput(struct icmp *icmp)
{
return (udp_common_ctlinput(icmp, &V_ulitecbinfo));
}
#endif /* INET */
static int
udp_pcblist(SYSCTL_HANDLER_ARGS)
{
struct inpcb_iterator inpi = INP_ALL_ITERATOR(&V_udbinfo,
INPLOOKUP_RLOCKPCB);
struct xinpgen xig;
struct inpcb *inp;
int error;
if (req->newptr != 0)
return (EPERM);
if (req->oldptr == 0) {
int n;
n = V_udbinfo.ipi_count;
n += imax(n / 8, 10);
req->oldidx = 2 * (sizeof xig) + n * sizeof(struct xinpcb);
return (0);
}
if ((error = sysctl_wire_old_buffer(req, 0)) != 0)
return (error);
bzero(&xig, sizeof(xig));
xig.xig_len = sizeof xig;
xig.xig_count = V_udbinfo.ipi_count;
xig.xig_gen = V_udbinfo.ipi_gencnt;
xig.xig_sogen = so_gencnt;
error = SYSCTL_OUT(req, &xig, sizeof xig);
if (error)
return (error);
while ((inp = inp_next(&inpi)) != NULL) {
if (inp->inp_gencnt <= xig.xig_gen &&
cr_canseeinpcb(req->td->td_ucred, inp) == 0) {
struct xinpcb xi;
in_pcbtoxinpcb(inp, &xi);
error = SYSCTL_OUT(req, &xi, sizeof xi);
if (error) {
INP_RUNLOCK(inp);
break;
}
}
}
if (!error) {
/*
* Give the user an updated idea of our state. If the
* generation differs from what we told her before, she knows
* that something happened while we were processing this
* request, and it might be necessary to retry.
*/
xig.xig_gen = V_udbinfo.ipi_gencnt;
xig.xig_sogen = so_gencnt;
xig.xig_count = V_udbinfo.ipi_count;
error = SYSCTL_OUT(req, &xig, sizeof xig);
}
return (error);
}
SYSCTL_PROC(_net_inet_udp, UDPCTL_PCBLIST, pcblist,
CTLTYPE_OPAQUE | CTLFLAG_RD | CTLFLAG_MPSAFE, NULL, 0,
udp_pcblist, "S,xinpcb",
"List of active UDP sockets");
#ifdef INET
static int
udp_getcred(SYSCTL_HANDLER_ARGS)
{
struct xucred xuc;
struct sockaddr_in addrs[2];
struct epoch_tracker et;
struct inpcb *inp;
int error;
error = priv_check(req->td, PRIV_NETINET_GETCRED);
if (error)
return (error);
error = SYSCTL_IN(req, addrs, sizeof(addrs));
if (error)
return (error);
NET_EPOCH_ENTER(et);
inp = in_pcblookup(&V_udbinfo, addrs[1].sin_addr, addrs[1].sin_port,
addrs[0].sin_addr, addrs[0].sin_port,
INPLOOKUP_WILDCARD | INPLOOKUP_RLOCKPCB, NULL);
NET_EPOCH_EXIT(et);
if (inp != NULL) {
INP_RLOCK_ASSERT(inp);
if (inp->inp_socket == NULL)
error = ENOENT;
if (error == 0)
error = cr_canseeinpcb(req->td->td_ucred, inp);
if (error == 0)
cru2x(inp->inp_cred, &xuc);
INP_RUNLOCK(inp);
} else
error = ENOENT;
if (error == 0)
error = SYSCTL_OUT(req, &xuc, sizeof(struct xucred));
return (error);
}
SYSCTL_PROC(_net_inet_udp, OID_AUTO, getcred,
CTLTYPE_OPAQUE | CTLFLAG_RW | CTLFLAG_PRISON | CTLFLAG_MPSAFE,
0, 0, udp_getcred, "S,xucred",
"Get the xucred of a UDP connection");
#endif /* INET */
int
udp_ctloutput(struct socket *so, struct sockopt *sopt)
{
struct inpcb *inp;
struct udpcb *up;
int isudplite, error, optval;
error = 0;
isudplite = (so->so_proto->pr_protocol == IPPROTO_UDPLITE) ? 1 : 0;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("%s: inp == NULL", __func__));
INP_WLOCK(inp);
if (sopt->sopt_level != so->so_proto->pr_protocol) {
#ifdef INET6
if (INP_CHECK_SOCKAF(so, AF_INET6)) {
INP_WUNLOCK(inp);
error = ip6_ctloutput(so, sopt);
}
#endif
#if defined(INET) && defined(INET6)
else
#endif
#ifdef INET
{
INP_WUNLOCK(inp);
error = ip_ctloutput(so, sopt);
}
#endif
return (error);
}
switch (sopt->sopt_dir) {
case SOPT_SET:
switch (sopt->sopt_name) {
#if defined(IPSEC) || defined(IPSEC_SUPPORT)
#ifdef INET
case UDP_ENCAP:
if (!IPSEC_ENABLED(ipv4)) {
INP_WUNLOCK(inp);
return (ENOPROTOOPT);
}
error = UDPENCAP_PCBCTL(inp, sopt);
break;
#endif /* INET */
#endif /* IPSEC */
case UDPLITE_SEND_CSCOV:
case UDPLITE_RECV_CSCOV:
if (!isudplite) {
INP_WUNLOCK(inp);
error = ENOPROTOOPT;
break;
}
INP_WUNLOCK(inp);
error = sooptcopyin(sopt, &optval, sizeof(optval),
sizeof(optval));
if (error != 0)
break;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("%s: inp == NULL", __func__));
INP_WLOCK(inp);
up = intoudpcb(inp);
KASSERT(up != NULL, ("%s: up == NULL", __func__));
if ((optval != 0 && optval < 8) || (optval > 65535)) {
INP_WUNLOCK(inp);
error = EINVAL;
break;
}
if (sopt->sopt_name == UDPLITE_SEND_CSCOV)
up->u_txcslen = optval;
else
up->u_rxcslen = optval;
INP_WUNLOCK(inp);
break;
default:
INP_WUNLOCK(inp);
error = ENOPROTOOPT;
break;
}
break;
case SOPT_GET:
switch (sopt->sopt_name) {
#if defined(IPSEC) || defined(IPSEC_SUPPORT)
#ifdef INET
case UDP_ENCAP:
if (!IPSEC_ENABLED(ipv4)) {
INP_WUNLOCK(inp);
return (ENOPROTOOPT);
}
error = UDPENCAP_PCBCTL(inp, sopt);
break;
#endif /* INET */
#endif /* IPSEC */
case UDPLITE_SEND_CSCOV:
case UDPLITE_RECV_CSCOV:
if (!isudplite) {
INP_WUNLOCK(inp);
error = ENOPROTOOPT;
break;
}
up = intoudpcb(inp);
KASSERT(up != NULL, ("%s: up == NULL", __func__));
if (sopt->sopt_name == UDPLITE_SEND_CSCOV)
optval = up->u_txcslen;
else
optval = up->u_rxcslen;
INP_WUNLOCK(inp);
error = sooptcopyout(sopt, &optval, sizeof(optval));
break;
default:
INP_WUNLOCK(inp);
error = ENOPROTOOPT;
break;
}
break;
}
return (error);
}
#ifdef INET
#ifdef INET6
/* The logic here is derived from ip6_setpktopt(). See comments there. */
static int
udp_v4mapped_pktinfo(struct cmsghdr *cm, struct sockaddr_in * src,
struct inpcb *inp, int flags)
{
struct ifnet *ifp;
struct in6_pktinfo *pktinfo;
struct in_addr ia;
if ((flags & PRUS_IPV6) == 0)
return (0);
if (cm->cmsg_level != IPPROTO_IPV6)
return (0);
if (cm->cmsg_type != IPV6_2292PKTINFO &&
cm->cmsg_type != IPV6_PKTINFO)
return (0);