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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
|
/* $NetBSD: udp_usrreq.c,v 1.258 2018/12/27 16:59:17 maxv 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) 1982, 1986, 1988, 1990, 1993, 1995
* 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.
*
* @(#)udp_usrreq.c 8.6 (Berkeley) 5/23/95
*/
/*
* UDP protocol implementation.
* Per RFC 768, August, 1980.
*/
#include <sys/cdefs.h>
__KERNEL_RCSID(0, "$NetBSD: udp_usrreq.c,v 1.258 2018/12/27 16:59:17 maxv Exp $");
#ifdef _KERNEL_OPT
#include "opt_inet.h"
#include "opt_ipsec.h"
#include "opt_inet_csum.h"
#include "opt_mbuftrace.h"
#include "opt_net_mpsafe.h"
#endif
#include <sys/param.h>
#include <sys/mbuf.h>
#include <sys/once.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/systm.h>
#include <sys/proc.h>
#include <sys/domain.h>
#include <sys/sysctl.h>
#include <net/if.h>
#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/in_var.h>
#include <netinet/ip.h>
#include <netinet/in_pcb.h>
#include <netinet/ip_var.h>
#include <netinet/ip_icmp.h>
#include <netinet/udp.h>
#include <netinet/udp_var.h>
#include <netinet/udp_private.h>
#ifdef INET6
#include <netinet/ip6.h>
#include <netinet6/ip6_var.h>
#include <netinet6/ip6_private.h>
#include <netinet6/in6_pcb.h>
#include <netinet6/udp6_var.h>
#include <netinet6/udp6_private.h>
#endif
#ifndef INET6
#include <netinet/ip6.h>
#endif
#ifdef IPSEC
#include <netipsec/ipsec.h>
#include <netipsec/esp.h>
#endif
int udpcksum = 1;
int udp_do_loopback_cksum = 0;
struct inpcbtable udbtable;
percpu_t *udpstat_percpu;
#ifdef INET
#ifdef IPSEC
static int udp4_espinudp(struct mbuf **, int);
#endif
static void udp4_sendup(struct mbuf *, int, struct sockaddr *,
struct socket *);
static int udp4_realinput(struct sockaddr_in *, struct sockaddr_in *,
struct mbuf **, int);
static int udp4_input_checksum(struct mbuf *, const struct udphdr *, int, int);
#endif
#ifdef INET
static void udp_notify (struct inpcb *, int);
#endif
#ifndef UDBHASHSIZE
#define UDBHASHSIZE 128
#endif
int udbhashsize = UDBHASHSIZE;
/*
* For send - really max datagram size; for receive - 40 1K datagrams.
*/
static int udp_sendspace = 9216;
static int udp_recvspace = 40 * (1024 + sizeof(struct sockaddr_in));
#ifdef MBUFTRACE
struct mowner udp_mowner = MOWNER_INIT("udp", "");
struct mowner udp_rx_mowner = MOWNER_INIT("udp", "rx");
struct mowner udp_tx_mowner = MOWNER_INIT("udp", "tx");
#endif
#ifdef UDP_CSUM_COUNTERS
#include <sys/device.h>
#if defined(INET)
struct evcnt udp_hwcsum_bad = EVCNT_INITIALIZER(EVCNT_TYPE_MISC,
NULL, "udp", "hwcsum bad");
struct evcnt udp_hwcsum_ok = EVCNT_INITIALIZER(EVCNT_TYPE_MISC,
NULL, "udp", "hwcsum ok");
struct evcnt udp_hwcsum_data = EVCNT_INITIALIZER(EVCNT_TYPE_MISC,
NULL, "udp", "hwcsum data");
struct evcnt udp_swcsum = EVCNT_INITIALIZER(EVCNT_TYPE_MISC,
NULL, "udp", "swcsum");
EVCNT_ATTACH_STATIC(udp_hwcsum_bad);
EVCNT_ATTACH_STATIC(udp_hwcsum_ok);
EVCNT_ATTACH_STATIC(udp_hwcsum_data);
EVCNT_ATTACH_STATIC(udp_swcsum);
#endif /* defined(INET) */
#define UDP_CSUM_COUNTER_INCR(ev) (ev)->ev_count++
#else
#define UDP_CSUM_COUNTER_INCR(ev) /* nothing */
#endif /* UDP_CSUM_COUNTERS */
static void sysctl_net_inet_udp_setup(struct sysctllog **);
static int
do_udpinit(void)
{
in_pcbinit(&udbtable, udbhashsize, udbhashsize);
udpstat_percpu = percpu_alloc(sizeof(uint64_t) * UDP_NSTATS);
MOWNER_ATTACH(&udp_tx_mowner);
MOWNER_ATTACH(&udp_rx_mowner);
MOWNER_ATTACH(&udp_mowner);
return 0;
}
void
udp_init_common(void)
{
static ONCE_DECL(doudpinit);
RUN_ONCE(&doudpinit, do_udpinit);
}
void
udp_init(void)
{
sysctl_net_inet_udp_setup(NULL);
udp_init_common();
}
/*
* Checksum extended UDP header and data.
*/
int
udp_input_checksum(int af, struct mbuf *m, const struct udphdr *uh,
int iphlen, int len)
{
switch (af) {
#ifdef INET
case AF_INET:
return udp4_input_checksum(m, uh, iphlen, len);
#endif
#ifdef INET6
case AF_INET6:
return udp6_input_checksum(m, uh, iphlen, len);
#endif
}
#ifdef DIAGNOSTIC
panic("udp_input_checksum: unknown af %d", af);
#endif
/* NOTREACHED */
return -1;
}
#ifdef INET
/*
* Checksum extended UDP header and data.
*/
static int
udp4_input_checksum(struct mbuf *m, const struct udphdr *uh,
int iphlen, int len)
{
/*
* XXX it's better to record and check if this mbuf is
* already checked.
*/
if (uh->uh_sum == 0)
return 0;
switch (m->m_pkthdr.csum_flags &
((m_get_rcvif_NOMPSAFE(m)->if_csum_flags_rx & M_CSUM_UDPv4) |
M_CSUM_TCP_UDP_BAD | M_CSUM_DATA)) {
case M_CSUM_UDPv4|M_CSUM_TCP_UDP_BAD:
UDP_CSUM_COUNTER_INCR(&udp_hwcsum_bad);
goto badcsum;
case M_CSUM_UDPv4|M_CSUM_DATA: {
u_int32_t hw_csum = m->m_pkthdr.csum_data;
UDP_CSUM_COUNTER_INCR(&udp_hwcsum_data);
if (m->m_pkthdr.csum_flags & M_CSUM_NO_PSEUDOHDR) {
const struct ip *ip =
mtod(m, const struct ip *);
hw_csum = in_cksum_phdr(ip->ip_src.s_addr,
ip->ip_dst.s_addr,
htons(hw_csum + len + IPPROTO_UDP));
}
if ((hw_csum ^ 0xffff) != 0)
goto badcsum;
break;
}
case M_CSUM_UDPv4:
/* Checksum was okay. */
UDP_CSUM_COUNTER_INCR(&udp_hwcsum_ok);
break;
default:
/*
* Need to compute it ourselves. Maybe skip checksum
* on loopback interfaces.
*/
if (__predict_true(!(m_get_rcvif_NOMPSAFE(m)->if_flags &
IFF_LOOPBACK) ||
udp_do_loopback_cksum)) {
UDP_CSUM_COUNTER_INCR(&udp_swcsum);
if (in4_cksum(m, IPPROTO_UDP, iphlen, len) != 0)
goto badcsum;
}
break;
}
return 0;
badcsum:
UDP_STATINC(UDP_STAT_BADSUM);
return -1;
}
void
udp_input(struct mbuf *m, int off, int proto)
{
struct sockaddr_in src, dst;
struct ip *ip;
struct udphdr *uh;
int iphlen = off;
int len;
int n;
u_int16_t ip_len;
MCLAIM(m, &udp_rx_mowner);
UDP_STATINC(UDP_STAT_IPACKETS);
/*
* Get IP and UDP header together in first mbuf.
*/
ip = mtod(m, struct ip *);
M_REGION_GET(uh, struct udphdr *, m, iphlen, sizeof(struct udphdr));
if (uh == NULL) {
UDP_STATINC(UDP_STAT_HDROPS);
return;
}
/*
* Enforce alignment requirements that are violated in
* some cases, see kern/50766 for details.
*/
if (UDP_HDR_ALIGNED_P(uh) == 0) {
m = m_copyup(m, iphlen + sizeof(struct udphdr), 0);
if (m == NULL) {
UDP_STATINC(UDP_STAT_HDROPS);
return;
}
ip = mtod(m, struct ip *);
uh = (struct udphdr *)(mtod(m, char *) + iphlen);
}
KASSERT(UDP_HDR_ALIGNED_P(uh));
/* destination port of 0 is illegal, based on RFC768. */
if (uh->uh_dport == 0)
goto bad;
/*
* Make mbuf data length reflect UDP length.
* If not enough data to reflect UDP length, drop.
*/
ip_len = ntohs(ip->ip_len);
len = ntohs((u_int16_t)uh->uh_ulen);
if (len < sizeof(struct udphdr)) {
UDP_STATINC(UDP_STAT_BADLEN);
goto bad;
}
if (ip_len != iphlen + len) {
if (ip_len < iphlen + len) {
UDP_STATINC(UDP_STAT_BADLEN);
goto bad;
}
m_adj(m, iphlen + len - ip_len);
}
/*
* Checksum extended UDP header and data.
*/
if (udp4_input_checksum(m, uh, iphlen, len))
goto badcsum;
/* construct source and dst sockaddrs. */
sockaddr_in_init(&src, &ip->ip_src, uh->uh_sport);
sockaddr_in_init(&dst, &ip->ip_dst, uh->uh_dport);
if ((n = udp4_realinput(&src, &dst, &m, iphlen)) == -1) {
UDP_STATINC(UDP_STAT_HDROPS);
return;
}
if (m == NULL) {
/*
* packet has been processed by ESP stuff -
* e.g. dropped NAT-T-keep-alive-packet ...
*/
return;
}
ip = mtod(m, struct ip *);
M_REGION_GET(uh, struct udphdr *, m, iphlen, sizeof(struct udphdr));
if (uh == NULL) {
UDP_STATINC(UDP_STAT_HDROPS);
return;
}
/* XXX Re-enforce alignment? */
#ifdef INET6
if (IN_MULTICAST(ip->ip_dst.s_addr) || n == 0) {
struct sockaddr_in6 src6, dst6;
memset(&src6, 0, sizeof(src6));
src6.sin6_family = AF_INET6;
src6.sin6_len = sizeof(struct sockaddr_in6);
in6_in_2_v4mapin6(&ip->ip_src, &src6.sin6_addr);
src6.sin6_port = uh->uh_sport;
memset(&dst6, 0, sizeof(dst6));
dst6.sin6_family = AF_INET6;
dst6.sin6_len = sizeof(struct sockaddr_in6);
in6_in_2_v4mapin6(&ip->ip_dst, &dst6.sin6_addr);
dst6.sin6_port = uh->uh_dport;
n += udp6_realinput(AF_INET, &src6, &dst6, &m, iphlen);
}
#endif
if (n == 0) {
if (m->m_flags & (M_BCAST | M_MCAST)) {
UDP_STATINC(UDP_STAT_NOPORTBCAST);
goto bad;
}
UDP_STATINC(UDP_STAT_NOPORT);
icmp_error(m, ICMP_UNREACH, ICMP_UNREACH_PORT, 0, 0);
m = NULL;
}
bad:
if (m)
m_freem(m);
return;
badcsum:
m_freem(m);
}
#endif
#ifdef INET
static void
udp4_sendup(struct mbuf *m, int off /* offset of data portion */,
struct sockaddr *src, struct socket *so)
{
struct mbuf *opts = NULL;
struct mbuf *n;
struct inpcb *inp;
KASSERT(so != NULL);
KASSERT(so->so_proto->pr_domain->dom_family == AF_INET);
inp = sotoinpcb(so);
KASSERT(inp != NULL);
#if defined(IPSEC)
if (ipsec_used && ipsec_in_reject(m, inp)) {
if ((n = m_copypacket(m, M_DONTWAIT)) != NULL)
icmp_error(n, ICMP_UNREACH, ICMP_UNREACH_ADMIN_PROHIBIT,
0, 0);
return;
}
#endif
if ((n = m_copypacket(m, M_DONTWAIT)) != NULL) {
if (inp->inp_flags & INP_CONTROLOPTS ||
SOOPT_TIMESTAMP(so->so_options)) {
struct ip *ip = mtod(n, struct ip *);
ip_savecontrol(inp, &opts, ip, n);
}
m_adj(n, off);
if (sbappendaddr(&so->so_rcv, src, n, opts) == 0) {
m_freem(n);
if (opts)
m_freem(opts);
UDP_STATINC(UDP_STAT_FULLSOCK);
soroverflow(so);
} else
sorwakeup(so);
}
}
#endif
#ifdef INET
static int
udp4_realinput(struct sockaddr_in *src, struct sockaddr_in *dst,
struct mbuf **mp, int off /* offset of udphdr */)
{
u_int16_t *sport, *dport;
int rcvcnt;
struct in_addr *src4, *dst4;
struct inpcb_hdr *inph;
struct inpcb *inp;
struct mbuf *m = *mp;
rcvcnt = 0;
off += sizeof(struct udphdr); /* now, offset of payload */
if (src->sin_family != AF_INET || dst->sin_family != AF_INET)
goto bad;
src4 = &src->sin_addr;
sport = &src->sin_port;
dst4 = &dst->sin_addr;
dport = &dst->sin_port;
if (IN_MULTICAST(dst4->s_addr) ||
in_broadcast(*dst4, m_get_rcvif_NOMPSAFE(m))) {
/*
* Deliver a multicast or broadcast datagram to *all* sockets
* for which the local and remote addresses and ports match
* those of the incoming datagram. This allows more than
* one process to receive multi/broadcasts on the same port.
* (This really ought to be done for unicast datagrams as
* well, but that would cause problems with existing
* applications that open both address-specific sockets and
* a wildcard socket listening to the same port -- they would
* end up receiving duplicates of every unicast datagram.
* Those applications open the multiple sockets to overcome an
* inadequacy of the UDP socket interface, but for backwards
* compatibility we avoid the problem here rather than
* fixing the interface. Maybe 4.5BSD will remedy this?)
*/
/*
* KAME note: traditionally we dropped udpiphdr from mbuf here.
* we need udpiphdr for IPsec processing so we do that later.
*/
/*
* Locate pcb(s) for datagram.
*/
TAILQ_FOREACH(inph, &udbtable.inpt_queue, inph_queue) {
inp = (struct inpcb *)inph;
if (inp->inp_af != AF_INET)
continue;
if (inp->inp_lport != *dport)
continue;
if (!in_nullhost(inp->inp_laddr)) {
if (!in_hosteq(inp->inp_laddr, *dst4))
continue;
}
if (!in_nullhost(inp->inp_faddr)) {
if (!in_hosteq(inp->inp_faddr, *src4) ||
inp->inp_fport != *sport)
continue;
}
udp4_sendup(m, off, (struct sockaddr *)src,
inp->inp_socket);
rcvcnt++;
/*
* 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_REUSEADDR)) == 0)
break;
}
} else {
/*
* Locate pcb for datagram.
*/
inp = in_pcblookup_connect(&udbtable, *src4, *sport, *dst4,
*dport, 0);
if (inp == 0) {
UDP_STATINC(UDP_STAT_PCBHASHMISS);
inp = in_pcblookup_bind(&udbtable, *dst4, *dport);
if (inp == 0)
return rcvcnt;
}
#ifdef IPSEC
/* Handle ESP over UDP */
if (inp->inp_flags & INP_ESPINUDP) {
switch (udp4_espinudp(mp, off)) {
case -1: /* Error, m was freed */
rcvcnt = -1;
goto bad;
case 1: /* ESP over UDP */
rcvcnt++;
goto bad;
case 0: /* plain UDP */
default: /* Unexpected */
/*
* Normal UDP processing will take place,
* m may have changed.
*/
m = *mp;
break;
}
}
#endif
/*
* Check the minimum TTL for socket.
*/
if (mtod(m, struct ip *)->ip_ttl < inp->inp_ip_minttl)
goto bad;
udp4_sendup(m, off, (struct sockaddr *)src, inp->inp_socket);
rcvcnt++;
}
bad:
return rcvcnt;
}
#endif
#ifdef INET
/*
* Notify a udp user of an asynchronous error;
* just wake up so that he can collect error status.
*/
static void
udp_notify(struct inpcb *inp, int errno)
{
inp->inp_socket->so_error = errno;
sorwakeup(inp->inp_socket);
sowwakeup(inp->inp_socket);
}
void *
udp_ctlinput(int cmd, const struct sockaddr *sa, void *v)
{
struct ip *ip = v;
struct udphdr *uh;
void (*notify)(struct inpcb *, int) = udp_notify;
int errno;
if (sa->sa_family != AF_INET ||
sa->sa_len != sizeof(struct sockaddr_in))
return NULL;
if ((unsigned)cmd >= PRC_NCMDS)
return NULL;
errno = inetctlerrmap[cmd];
if (PRC_IS_REDIRECT(cmd)) {
notify = in_rtchange;
ip = NULL;
} else if (cmd == PRC_HOSTDEAD) {
ip = NULL;
} else if (errno == 0) {
return NULL;
}
if (ip) {
uh = (struct udphdr *)((char *)ip + (ip->ip_hl << 2));
in_pcbnotify(&udbtable, satocsin(sa)->sin_addr, uh->uh_dport,
ip->ip_src, uh->uh_sport, errno, notify);
/* XXX mapped address case */
} else {
in_pcbnotifyall(&udbtable, satocsin(sa)->sin_addr, errno,
notify);
}
return NULL;
}
int
udp_ctloutput(int op, struct socket *so, struct sockopt *sopt)
{
int s;
int error = 0;
struct inpcb *inp;
int family;
int optval;
family = so->so_proto->pr_domain->dom_family;
s = splsoftnet();
switch (family) {
#ifdef INET
case PF_INET:
if (sopt->sopt_level != IPPROTO_UDP) {
error = ip_ctloutput(op, so, sopt);
goto end;
}
break;
#endif
#ifdef INET6
case PF_INET6:
if (sopt->sopt_level != IPPROTO_UDP) {
error = ip6_ctloutput(op, so, sopt);
goto end;
}
break;
#endif
default:
error = EAFNOSUPPORT;
goto end;
}
switch (op) {
case PRCO_SETOPT:
inp = sotoinpcb(so);
switch (sopt->sopt_name) {
case UDP_ENCAP:
error = sockopt_getint(sopt, &optval);
if (error)
break;
switch(optval) {
case 0:
inp->inp_flags &= ~INP_ESPINUDP;
break;
case UDP_ENCAP_ESPINUDP:
inp->inp_flags |= INP_ESPINUDP;
break;
default:
error = EINVAL;
break;
}
break;
default:
error = ENOPROTOOPT;
break;
}
break;
default:
error = EINVAL;
break;
}
end:
splx(s);
return error;
}
int
udp_output(struct mbuf *m, struct inpcb *inp, struct mbuf *control,
struct lwp *l)
{
struct udpiphdr *ui;
struct route *ro;
struct ip_pktopts pktopts;
kauth_cred_t cred;
int len = m->m_pkthdr.len;
int error, flags = 0;
MCLAIM(m, &udp_tx_mowner);
/*
* Calculate data length and get a mbuf
* for UDP and IP headers.
*/
M_PREPEND(m, sizeof(struct udpiphdr), M_DONTWAIT);
if (m == NULL) {
error = ENOBUFS;
goto release;
}
/*
* Compute the packet length of the IP header, and
* punt if the length looks bogus.
*/
if (len + sizeof(struct udpiphdr) > IP_MAXPACKET) {
error = EMSGSIZE;
goto release;
}
if (l == NULL)
cred = NULL;
else
cred = l->l_cred;
/* Setup IP outgoing packet options */
memset(&pktopts, 0, sizeof(pktopts));
error = ip_setpktopts(control, &pktopts, &flags, inp, cred);
if (error != 0)
goto release;
if (control != NULL) {
m_freem(control);
control = NULL;
}
/*
* Fill in mbuf with extended UDP header
* and addresses and length put into network format.
*/
ui = mtod(m, struct udpiphdr *);
ui->ui_pr = IPPROTO_UDP;
ui->ui_src = pktopts.ippo_laddr.sin_addr;
ui->ui_dst = inp->inp_faddr;
ui->ui_sport = inp->inp_lport;
ui->ui_dport = inp->inp_fport;
ui->ui_ulen = htons((u_int16_t)len + sizeof(struct udphdr));
ro = &inp->inp_route;
/*
* Set up checksum and output datagram.
*/
if (udpcksum) {
/*
* XXX Cache pseudo-header checksum part for
* XXX "connected" UDP sockets.
*/
ui->ui_sum = in_cksum_phdr(ui->ui_src.s_addr,
ui->ui_dst.s_addr, htons((u_int16_t)len +
sizeof(struct udphdr) + IPPROTO_UDP));
m->m_pkthdr.csum_flags = M_CSUM_UDPv4;
m->m_pkthdr.csum_data = offsetof(struct udphdr, uh_sum);
} else
ui->ui_sum = 0;
((struct ip *)ui)->ip_len = htons(sizeof(struct udpiphdr) + len);
((struct ip *)ui)->ip_ttl = inp->inp_ip.ip_ttl; /* XXX */
((struct ip *)ui)->ip_tos = inp->inp_ip.ip_tos; /* XXX */
UDP_STATINC(UDP_STAT_OPACKETS);
flags |= inp->inp_socket->so_options & (SO_DONTROUTE|SO_BROADCAST);
return ip_output(m, inp->inp_options, ro, flags, pktopts.ippo_imo, inp);
release:
if (control != NULL)
m_freem(control);
m_freem(m);
return error;
}
static int
udp_attach(struct socket *so, int proto)
{
struct inpcb *inp;
int error;
KASSERT(sotoinpcb(so) == NULL);
/* Assign the lock (must happen even if we will error out). */
sosetlock(so);
#ifdef MBUFTRACE
so->so_mowner = &udp_mowner;
so->so_rcv.sb_mowner = &udp_rx_mowner;
so->so_snd.sb_mowner = &udp_tx_mowner;
#endif
if (so->so_snd.sb_hiwat == 0 || so->so_rcv.sb_hiwat == 0) {
error = soreserve(so, udp_sendspace, udp_recvspace);
if (error) {
return error;
}
}
error = in_pcballoc(so, &udbtable);
if (error) {
return error;
}
inp = sotoinpcb(so);
inp->inp_ip.ip_ttl = ip_defttl;
KASSERT(solocked(so));
return error;
}
static void
udp_detach(struct socket *so)
{
struct inpcb *inp;
KASSERT(solocked(so));
inp = sotoinpcb(so);
KASSERT(inp != NULL);
in_pcbdetach(inp);
}
static int
udp_accept(struct socket *so, struct sockaddr *nam)
{
KASSERT(solocked(so));
panic("udp_accept");
return EOPNOTSUPP;
}
static int
udp_bind(struct socket *so, struct sockaddr *nam, struct lwp *l)
{
struct inpcb *inp = sotoinpcb(so);
struct sockaddr_in *sin = (struct sockaddr_in *)nam;
int error = 0;
int s;
KASSERT(solocked(so));
KASSERT(inp != NULL);
KASSERT(nam != NULL);
s = splsoftnet();
error = in_pcbbind(inp, sin, l);
splx(s);
return error;
}
static int
udp_listen(struct socket *so, struct lwp *l)
{
KASSERT(solocked(so));
return EOPNOTSUPP;
}
static int
udp_connect(struct socket *so, struct sockaddr *nam, struct lwp *l)
{
struct inpcb *inp = sotoinpcb(so);
int error = 0;
int s;
KASSERT(solocked(so));
KASSERT(inp != NULL);
KASSERT(nam != NULL);
s = splsoftnet();
error = in_pcbconnect(inp, (struct sockaddr_in *)nam, l);
if (! error)
soisconnected(so);
splx(s);
return error;
}
static int
udp_connect2(struct socket *so, struct socket *so2)
{
KASSERT(solocked(so));
return EOPNOTSUPP;
}
static int
udp_disconnect(struct socket *so)
{
struct inpcb *inp = sotoinpcb(so);
int s;
KASSERT(solocked(so));
KASSERT(inp != NULL);
s = splsoftnet();
/*soisdisconnected(so);*/
so->so_state &= ~SS_ISCONNECTED; /* XXX */
in_pcbdisconnect(inp);
inp->inp_laddr = zeroin_addr; /* XXX */
in_pcbstate(inp, INP_BOUND); /* XXX */
splx(s);
return 0;
}
static int
udp_shutdown(struct socket *so)
{
int s;
KASSERT(solocked(so));
s = splsoftnet();
socantsendmore(so);
splx(s);
return 0;
}
static int
udp_abort(struct socket *so)
{
KASSERT(solocked(so));
panic("udp_abort");
return EOPNOTSUPP;
}
static int
udp_ioctl(struct socket *so, u_long cmd, void *nam, struct ifnet *ifp)
{
return in_control(so, cmd, nam, ifp);
}
static int
udp_stat(struct socket *so, struct stat *ub)
{
KASSERT(solocked(so));
/* stat: don't bother with a blocksize. */
return 0;
}
static int
udp_peeraddr(struct socket *so, struct sockaddr *nam)
{
int s;
KASSERT(solocked(so));
KASSERT(sotoinpcb(so) != NULL);
KASSERT(nam != NULL);
s = splsoftnet();
in_setpeeraddr(sotoinpcb(so), (struct sockaddr_in *)nam);
splx(s);
return 0;
}
static int
udp_sockaddr(struct socket *so, struct sockaddr *nam)
{
int s;
KASSERT(solocked(so));
KASSERT(sotoinpcb(so) != NULL);
KASSERT(nam != NULL);
s = splsoftnet();
in_setsockaddr(sotoinpcb(so), (struct sockaddr_in *)nam);
splx(s);
return 0;
}
static int
udp_rcvd(struct socket *so, int flags, struct lwp *l)
{
KASSERT(solocked(so));
return EOPNOTSUPP;
}
static int
udp_recvoob(struct socket *so, struct mbuf *m, int flags)
{
KASSERT(solocked(so));
return EOPNOTSUPP;
}
static int
udp_send(struct socket *so, struct mbuf *m, struct sockaddr *nam,
struct mbuf *control, struct lwp *l)
{
struct inpcb *inp = sotoinpcb(so);
int error = 0;
struct in_addr laddr; /* XXX */
int s;
KASSERT(solocked(so));
KASSERT(inp != NULL);
KASSERT(m != NULL);
memset(&laddr, 0, sizeof laddr);
s = splsoftnet();
if (nam) {
laddr = inp->inp_laddr; /* XXX */
if ((so->so_state & SS_ISCONNECTED) != 0) {
error = EISCONN;
goto die;
}
error = in_pcbconnect(inp, (struct sockaddr_in *)nam, l);
if (error)
goto die;
} else {
if ((so->so_state & SS_ISCONNECTED) == 0) {
error = ENOTCONN;
goto die;
}
}
error = udp_output(m, inp, control, l);
m = NULL;
control = NULL;
if (nam) {
in_pcbdisconnect(inp);
inp->inp_laddr = laddr; /* XXX */
in_pcbstate(inp, INP_BOUND); /* XXX */
}
die:
if (m != NULL)
m_freem(m);
if (control != NULL)
m_freem(control);
splx(s);
return error;
}
static int
udp_sendoob(struct socket *so, struct mbuf *m, struct mbuf *control)
{
KASSERT(solocked(so));
m_freem(m);
m_freem(control);
return EOPNOTSUPP;
}
static int
udp_purgeif(struct socket *so, struct ifnet *ifp)
{
int s;
s = splsoftnet();
mutex_enter(softnet_lock);
in_pcbpurgeif0(&udbtable, ifp);
#ifdef NET_MPSAFE
mutex_exit(softnet_lock);
#endif
in_purgeif(ifp);
#ifdef NET_MPSAFE
mutex_enter(softnet_lock);
#endif
in_pcbpurgeif(&udbtable, ifp);
mutex_exit(softnet_lock);
splx(s);
return 0;
}
static int
sysctl_net_inet_udp_stats(SYSCTLFN_ARGS)
{
return (NETSTAT_SYSCTL(udpstat_percpu, UDP_NSTATS));
}
/*
* Sysctl for udp variables.
*/
static void
sysctl_net_inet_udp_setup(struct sysctllog **clog)
{
sysctl_createv(clog, 0, NULL, NULL,
CTLFLAG_PERMANENT,
CTLTYPE_NODE, "inet", NULL,
NULL, 0, NULL, 0,
CTL_NET, PF_INET, CTL_EOL);
sysctl_createv(clog, 0, NULL, NULL,
CTLFLAG_PERMANENT,
CTLTYPE_NODE, "udp",
SYSCTL_DESCR("UDPv4 related settings"),
NULL, 0, NULL, 0,
CTL_NET, PF_INET, IPPROTO_UDP, CTL_EOL);
sysctl_createv(clog, 0, NULL, NULL,
CTLFLAG_PERMANENT|CTLFLAG_READWRITE,
CTLTYPE_INT, "checksum",
SYSCTL_DESCR("Compute UDP checksums"),
NULL, 0, &udpcksum, 0,
CTL_NET, PF_INET, IPPROTO_UDP, UDPCTL_CHECKSUM,
CTL_EOL);
sysctl_createv(clog, 0, NULL, NULL,
CTLFLAG_PERMANENT|CTLFLAG_READWRITE,
CTLTYPE_INT, "sendspace",
SYSCTL_DESCR("Default UDP send buffer size"),
NULL, 0, &udp_sendspace, 0,
CTL_NET, PF_INET, IPPROTO_UDP, UDPCTL_SENDSPACE,
CTL_EOL);
sysctl_createv(clog, 0, NULL, NULL,
CTLFLAG_PERMANENT|CTLFLAG_READWRITE,
CTLTYPE_INT, "recvspace",
SYSCTL_DESCR("Default UDP receive buffer size"),
NULL, 0, &udp_recvspace, 0,
CTL_NET, PF_INET, IPPROTO_UDP, UDPCTL_RECVSPACE,
CTL_EOL);
sysctl_createv(clog, 0, NULL, NULL,
CTLFLAG_PERMANENT|CTLFLAG_READWRITE,
CTLTYPE_INT, "do_loopback_cksum",
SYSCTL_DESCR("Perform UDP checksum on loopback"),
NULL, 0, &udp_do_loopback_cksum, 0,
CTL_NET, PF_INET, IPPROTO_UDP, UDPCTL_LOOPBACKCKSUM,
CTL_EOL);
sysctl_createv(clog, 0, NULL, NULL,
CTLFLAG_PERMANENT,
CTLTYPE_STRUCT, "pcblist",
SYSCTL_DESCR("UDP protocol control block list"),
sysctl_inpcblist, 0, &udbtable, 0,
CTL_NET, PF_INET, IPPROTO_UDP, CTL_CREATE,
CTL_EOL);
sysctl_createv(clog, 0, NULL, NULL,
CTLFLAG_PERMANENT,
CTLTYPE_STRUCT, "stats",
SYSCTL_DESCR("UDP statistics"),
sysctl_net_inet_udp_stats, 0, NULL, 0,
CTL_NET, PF_INET, IPPROTO_UDP, UDPCTL_STATS,
CTL_EOL);
}
#endif
void
udp_statinc(u_int stat)
{
KASSERT(stat < UDP_NSTATS);
UDP_STATINC(stat);
}
#if defined(INET) && defined(IPSEC)
/*
* Handle ESP-in-UDP packets (RFC3948).
*
* We need to distinguish between ESP packets and IKE packets. We do so by
* looking at the Non-ESP marker. If IKE, we process the UDP packet as usual.
* Otherwise, ESP, we invoke IPsec.
*
* Returns:
* 1 if the packet was processed
* 0 if normal UDP processing should take place
* -1 if an error occurred and m was freed
*/
static int
udp4_espinudp(struct mbuf **mp, int off)
{
const size_t skip = sizeof(struct udphdr);
size_t len;
uint8_t *data;
size_t minlen;
size_t iphdrlen;
struct ip *ip;
struct m_tag *tag;
struct udphdr *udphdr;
u_int16_t sport, dport;
struct mbuf *m = *mp;
uint32_t *marker;
minlen = off + sizeof(struct esp);
if (minlen > m->m_pkthdr.len)
minlen = m->m_pkthdr.len;
if (m->m_len < minlen) {
if ((*mp = m_pullup(m, minlen)) == NULL) {
return -1;
}
m = *mp;
}
len = m->m_len - off;
data = mtod(m, uint8_t *) + off;
/* Ignore keepalive packets. */
if ((len == 1) && (*data == 0xff)) {
m_freem(m);
*mp = NULL; /* avoid any further processing by caller */
return 1;
}
/* Handle Non-ESP marker (32bit). If zero, then IKE. */
marker = (uint32_t *)data;
if (len <= sizeof(uint32_t))
return 0;
if (marker[0] == 0)
return 0;
/*
* Get the UDP ports. They are handled in network order
* everywhere in the IPSEC_NAT_T code.
*/
udphdr = (struct udphdr *)((char *)data - skip);
sport = udphdr->uh_sport;
dport = udphdr->uh_dport;
/*
* Remove the UDP header, plus a possible marker. IP header
* length is iphdrlen.
*
* Before:
* <--- off --->
* +----+------+-----+
* | IP | UDP | ESP |
* +----+------+-----+
* <-skip->
* After:
* +----+-----+
* | IP | ESP |
* +----+-----+
* <-skip->
*/
iphdrlen = off - sizeof(struct udphdr);
memmove(mtod(m, char *) + skip, mtod(m, void *), iphdrlen);
m_adj(m, skip);
ip = mtod(m, struct ip *);
ip->ip_len = htons(ntohs(ip->ip_len) - skip);
ip->ip_p = IPPROTO_ESP;
/*
* We have modified the packet - it is now ESP, so we should not
* return to UDP processing.
*
* Add a PACKET_TAG_IPSEC_NAT_T_PORTS tag to remember the source
* UDP port. This is required if we want to select the right SPD
* for multiple hosts behind same NAT.
*/
if ((tag = m_tag_get(PACKET_TAG_IPSEC_NAT_T_PORTS,
sizeof(sport) + sizeof(dport), M_DONTWAIT)) == NULL) {
m_freem(m);
return -1;
}
((u_int16_t *)(tag + 1))[0] = sport;
((u_int16_t *)(tag + 1))[1] = dport;
m_tag_prepend(m, tag);
if (ipsec_used)
ipsec4_common_input(m, iphdrlen, IPPROTO_ESP);
else
m_freem(m);
/* We handled it, it shouldn't be handled by UDP */
*mp = NULL; /* avoid free by caller ... */
return 1;
}
#endif
PR_WRAP_USRREQS(udp)
#define udp_attach udp_attach_wrapper
#define udp_detach udp_detach_wrapper
#define udp_accept udp_accept_wrapper
#define udp_bind udp_bind_wrapper
#define udp_listen udp_listen_wrapper
#define udp_connect udp_connect_wrapper
#define udp_connect2 udp_connect2_wrapper
#define udp_disconnect udp_disconnect_wrapper
#define udp_shutdown udp_shutdown_wrapper
#define udp_abort udp_abort_wrapper
#define udp_ioctl udp_ioctl_wrapper
#define udp_stat udp_stat_wrapper
#define udp_peeraddr udp_peeraddr_wrapper
#define udp_sockaddr udp_sockaddr_wrapper
#define udp_rcvd udp_rcvd_wrapper
#define udp_recvoob udp_recvoob_wrapper
#define udp_send udp_send_wrapper
#define udp_sendoob udp_sendoob_wrapper
#define udp_purgeif udp_purgeif_wrapper
const struct pr_usrreqs udp_usrreqs = {
.pr_attach = udp_attach,
.pr_detach = udp_detach,
.pr_accept = udp_accept,
.pr_bind = udp_bind,
.pr_listen = udp_listen,
.pr_connect = udp_connect,
.pr_connect2 = udp_connect2,
.pr_disconnect = udp_disconnect,
.pr_shutdown = udp_shutdown,
.pr_abort = udp_abort,
.pr_ioctl = udp_ioctl,
.pr_stat = udp_stat,
.pr_peeraddr = udp_peeraddr,
.pr_sockaddr = udp_sockaddr,
.pr_rcvd = udp_rcvd,
.pr_recvoob = udp_recvoob,
.pr_send = udp_send,
.pr_sendoob = udp_sendoob,
.pr_purgeif = udp_purgeif,
};
|