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
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
|
/*
* 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. 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.
*
* @(#)tcp_subr.c 8.2 (Berkeley) 5/24/95
* $FreeBSD$
*/
#include "opt_compat.h"
#include "opt_inet6.h"
#include "opt_ipsec.h"
#include "opt_tcpdebug.h"
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/callout.h>
#include <sys/kernel.h>
#include <sys/sysctl.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#ifdef INET6
#include <sys/domain.h>
#endif
#include <sys/proc.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/protosw.h>
#include <vm/vm_zone.h>
#include <net/route.h>
#include <net/if.h>
#define _IP_VHL
#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/ip.h>
#ifdef INET6
#include <netinet/ip6.h>
#endif
#include <netinet/in_pcb.h>
#ifdef INET6
#include <netinet6/in6_pcb.h>
#endif
#include <netinet/in_var.h>
#include <netinet/ip_var.h>
#ifdef INET6
#include <netinet6/ip6_var.h>
#endif
#include <netinet/tcp.h>
#include <netinet/tcp_fsm.h>
#include <netinet/tcp_seq.h>
#include <netinet/tcp_timer.h>
#include <netinet/tcp_var.h>
#ifdef INET6
#include <netinet6/tcp6_var.h>
#endif
#include <netinet/tcpip.h>
#ifdef TCPDEBUG
#include <netinet/tcp_debug.h>
#endif
#include <netinet6/ip6protosw.h>
#ifdef IPSEC
#include <netinet6/ipsec.h>
#ifdef INET6
#include <netinet6/ipsec6.h>
#endif
#endif /*IPSEC*/
#include <machine/in_cksum.h>
int tcp_mssdflt = TCP_MSS;
SYSCTL_INT(_net_inet_tcp, TCPCTL_MSSDFLT, mssdflt, CTLFLAG_RW,
&tcp_mssdflt , 0, "Default TCP Maximum Segment Size");
#ifdef INET6
int tcp_v6mssdflt = TCP6_MSS;
SYSCTL_INT(_net_inet_tcp, TCPCTL_V6MSSDFLT, v6mssdflt,
CTLFLAG_RW, &tcp_v6mssdflt , 0,
"Default TCP Maximum Segment Size for IPv6");
#endif
#if 0
static int tcp_rttdflt = TCPTV_SRTTDFLT / PR_SLOWHZ;
SYSCTL_INT(_net_inet_tcp, TCPCTL_RTTDFLT, rttdflt, CTLFLAG_RW,
&tcp_rttdflt , 0, "Default maximum TCP Round Trip Time");
#endif
static int tcp_do_rfc1323 = 1;
SYSCTL_INT(_net_inet_tcp, TCPCTL_DO_RFC1323, rfc1323, CTLFLAG_RW,
&tcp_do_rfc1323 , 0, "Enable rfc1323 (high performance TCP) extensions");
static int tcp_do_rfc1644 = 0;
SYSCTL_INT(_net_inet_tcp, TCPCTL_DO_RFC1644, rfc1644, CTLFLAG_RW,
&tcp_do_rfc1644 , 0, "Enable rfc1644 (TTCP) extensions");
static int tcp_tcbhashsize = 0;
SYSCTL_INT(_net_inet_tcp, OID_AUTO, tcbhashsize, CTLFLAG_RD,
&tcp_tcbhashsize, 0, "Size of TCP control-block hashtable");
static int do_tcpdrain = 1;
SYSCTL_INT(_net_inet_tcp, OID_AUTO, do_tcpdrain, CTLFLAG_RW, &do_tcpdrain, 0,
"Enable tcp_drain routine for extra help when low on mbufs");
SYSCTL_INT(_net_inet_tcp, OID_AUTO, pcbcount, CTLFLAG_RD,
&tcbinfo.ipi_count, 0, "Number of active PCBs");
/*
* Treat ICMP administratively prohibited like a TCP RST
* as required by rfc1122 section 3.2.2.1
*/
static int icmp_admin_prohib_like_rst = 1;
SYSCTL_INT(_net_inet_tcp, OID_AUTO, icmp_admin_prohib_like_rst, CTLFLAG_RW,
&icmp_admin_prohib_like_rst, 0,
"Treat ICMP administratively prohibited messages like TCP RST, rfc1122 section 3.2.2.1");
/*
* When icmp_admin_prohib_like_rst is enabled, only act on
* sessions in SYN-SENT state
*/
static int icmp_like_rst_syn_sent_only = 1;
SYSCTL_INT(_net_inet_tcp, OID_AUTO, icmp_like_rst_syn_sent_only, CTLFLAG_RW,
&icmp_like_rst_syn_sent_only, 0,
"When icmp_admin_prohib_like_rst is enabled, only act on sessions in SYN-SENT state");
static void tcp_cleartaocache __P((void));
static void tcp_notify __P((struct inpcb *, int));
/*
* Target size of TCP PCB hash tables. Must be a power of two.
*
* Note that this can be overridden by the kernel environment
* variable net.inet.tcp.tcbhashsize
*/
#ifndef TCBHASHSIZE
#define TCBHASHSIZE 512
#endif
/*
* This is the actual shape of what we allocate using the zone
* allocator. Doing it this way allows us to protect both structures
* using the same generation count, and also eliminates the overhead
* of allocating tcpcbs separately. By hiding the structure here,
* we avoid changing most of the rest of the code (although it needs
* to be changed, eventually, for greater efficiency).
*/
#define ALIGNMENT 32
#define ALIGNM1 (ALIGNMENT - 1)
struct inp_tp {
union {
struct inpcb inp;
char align[(sizeof(struct inpcb) + ALIGNM1) & ~ALIGNM1];
} inp_tp_u;
struct tcpcb tcb;
struct callout inp_tp_rexmt, inp_tp_persist, inp_tp_keep, inp_tp_2msl;
struct callout inp_tp_delack;
};
#undef ALIGNMENT
#undef ALIGNM1
/*
* Tcp initialization
*/
void
tcp_init()
{
int hashsize;
tcp_iss = arc4random(); /* wrong, but better than a constant */
tcp_ccgen = 1;
tcp_cleartaocache();
tcp_delacktime = TCPTV_DELACK;
tcp_keepinit = TCPTV_KEEP_INIT;
tcp_keepidle = TCPTV_KEEP_IDLE;
tcp_keepintvl = TCPTV_KEEPINTVL;
tcp_maxpersistidle = TCPTV_KEEP_IDLE;
tcp_msl = TCPTV_MSL;
LIST_INIT(&tcb);
tcbinfo.listhead = &tcb;
TUNABLE_INT_FETCH("net.inet.tcp.tcbhashsize", TCBHASHSIZE, hashsize);
if (!powerof2(hashsize)) {
printf("WARNING: TCB hash size not a power of 2\n");
hashsize = 512; /* safe default */
}
tcp_tcbhashsize = hashsize;
tcbinfo.hashbase = hashinit(hashsize, M_PCB, &tcbinfo.hashmask);
tcbinfo.porthashbase = hashinit(hashsize, M_PCB,
&tcbinfo.porthashmask);
tcbinfo.ipi_zone = zinit("tcpcb", sizeof(struct inp_tp), maxsockets,
ZONE_INTERRUPT, 0);
#ifdef INET6
#define TCP_MINPROTOHDR (sizeof(struct ip6_hdr) + sizeof(struct tcphdr))
#else /* INET6 */
#define TCP_MINPROTOHDR (sizeof(struct tcpiphdr))
#endif /* INET6 */
if (max_protohdr < TCP_MINPROTOHDR)
max_protohdr = TCP_MINPROTOHDR;
if (max_linkhdr + TCP_MINPROTOHDR > MHLEN)
panic("tcp_init");
#undef TCP_MINPROTOHDR
}
/*
* Create template to be used to send tcp packets on a connection.
* Call after host entry created, allocates an mbuf and fills
* in a skeletal tcp/ip header, minimizing the amount of work
* necessary when the connection is used.
*/
struct tcptemp *
tcp_template(tp)
struct tcpcb *tp;
{
register struct inpcb *inp = tp->t_inpcb;
register struct mbuf *m;
register struct tcptemp *n;
if ((n = tp->t_template) == 0) {
m = m_get(M_DONTWAIT, MT_HEADER);
if (m == NULL)
return (0);
m->m_len = sizeof (struct tcptemp);
n = mtod(m, struct tcptemp *);
}
#ifdef INET6
if ((inp->inp_vflag & INP_IPV6) != 0) {
register struct ip6_hdr *ip6;
ip6 = (struct ip6_hdr *)n->tt_ipgen;
ip6->ip6_flow = (ip6->ip6_flow & ~IPV6_FLOWINFO_MASK) |
(inp->in6p_flowinfo & IPV6_FLOWINFO_MASK);
ip6->ip6_vfc = (ip6->ip6_vfc & ~IPV6_VERSION_MASK) |
(IPV6_VERSION & IPV6_VERSION_MASK);
ip6->ip6_nxt = IPPROTO_TCP;
ip6->ip6_plen = sizeof(struct tcphdr);
ip6->ip6_src = inp->in6p_laddr;
ip6->ip6_dst = inp->in6p_faddr;
n->tt_t.th_sum = 0;
} else
#endif
{
struct ip *ip = (struct ip *)n->tt_ipgen;
bzero(ip, sizeof(struct ip)); /* XXX overkill? */
ip->ip_vhl = IP_VHL_BORING;
ip->ip_p = IPPROTO_TCP;
ip->ip_src = inp->inp_laddr;
ip->ip_dst = inp->inp_faddr;
n->tt_t.th_sum = in_pseudo(ip->ip_src.s_addr, ip->ip_dst.s_addr,
htons(sizeof(struct tcphdr) + IPPROTO_TCP));
}
n->tt_t.th_sport = inp->inp_lport;
n->tt_t.th_dport = inp->inp_fport;
n->tt_t.th_seq = 0;
n->tt_t.th_ack = 0;
n->tt_t.th_x2 = 0;
n->tt_t.th_off = 5;
n->tt_t.th_flags = 0;
n->tt_t.th_win = 0;
n->tt_t.th_urp = 0;
return (n);
}
/*
* Send a single message to the TCP at address specified by
* the given TCP/IP header. If m == 0, then we make a copy
* of the tcpiphdr at ti and send directly to the addressed host.
* This is used to force keep alive messages out using the TCP
* template for a connection tp->t_template. If flags are given
* then we send a message back to the TCP which originated the
* segment ti, and discard the mbuf containing it and any other
* attached mbufs.
*
* In any case the ack and sequence number of the transmitted
* segment are as specified by the parameters.
*
* NOTE: If m != NULL, then ti must point to *inside* the mbuf.
*/
void
tcp_respond(tp, ipgen, th, m, ack, seq, flags)
struct tcpcb *tp;
void *ipgen;
register struct tcphdr *th;
register struct mbuf *m;
tcp_seq ack, seq;
int flags;
{
register int tlen;
int win = 0;
struct route *ro = 0;
struct route sro;
struct ip *ip;
struct tcphdr *nth;
#ifdef INET6
struct route_in6 *ro6 = 0;
struct route_in6 sro6;
struct ip6_hdr *ip6;
int isipv6;
#endif /* INET6 */
int ipflags = 0;
#ifdef INET6
isipv6 = IP_VHL_V(((struct ip *)ipgen)->ip_vhl) == 6;
ip6 = ipgen;
#endif /* INET6 */
ip = ipgen;
if (tp) {
if (!(flags & TH_RST)) {
win = sbspace(&tp->t_inpcb->inp_socket->so_rcv);
if (win > (long)TCP_MAXWIN << tp->rcv_scale)
win = (long)TCP_MAXWIN << tp->rcv_scale;
}
#ifdef INET6
if (isipv6)
ro6 = &tp->t_inpcb->in6p_route;
else
#endif /* INET6 */
ro = &tp->t_inpcb->inp_route;
} else {
#ifdef INET6
if (isipv6) {
ro6 = &sro6;
bzero(ro6, sizeof *ro6);
} else
#endif /* INET6 */
{
ro = &sro;
bzero(ro, sizeof *ro);
}
}
if (m == 0) {
m = m_gethdr(M_DONTWAIT, MT_HEADER);
if (m == NULL)
return;
#ifdef TCP_COMPAT_42
tlen = 1;
#else
tlen = 0;
#endif
m->m_data += max_linkhdr;
#ifdef INET6
if (isipv6) {
bcopy((caddr_t)ip6, mtod(m, caddr_t),
sizeof(struct ip6_hdr));
ip6 = mtod(m, struct ip6_hdr *);
nth = (struct tcphdr *)(ip6 + 1);
} else
#endif /* INET6 */
{
bcopy((caddr_t)ip, mtod(m, caddr_t), sizeof(struct ip));
ip = mtod(m, struct ip *);
nth = (struct tcphdr *)(ip + 1);
}
bcopy((caddr_t)th, (caddr_t)nth, sizeof(struct tcphdr));
flags = TH_ACK;
} else {
m_freem(m->m_next);
m->m_next = 0;
m->m_data = (caddr_t)ipgen;
/* m_len is set later */
tlen = 0;
#define xchg(a,b,type) { type t; t=a; a=b; b=t; }
#ifdef INET6
if (isipv6) {
xchg(ip6->ip6_dst, ip6->ip6_src, struct in6_addr);
nth = (struct tcphdr *)(ip6 + 1);
} else
#endif /* INET6 */
{
xchg(ip->ip_dst.s_addr, ip->ip_src.s_addr, n_long);
nth = (struct tcphdr *)(ip + 1);
}
if (th != nth) {
/*
* this is usually a case when an extension header
* exists between the IPv6 header and the
* TCP header.
*/
nth->th_sport = th->th_sport;
nth->th_dport = th->th_dport;
}
xchg(nth->th_dport, nth->th_sport, n_short);
#undef xchg
}
#ifdef INET6
if (isipv6) {
ip6->ip6_plen = htons((u_short)(sizeof (struct tcphdr) +
tlen));
tlen += sizeof (struct ip6_hdr) + sizeof (struct tcphdr);
} else
#endif
{
tlen += sizeof (struct tcpiphdr);
ip->ip_len = tlen;
ip->ip_ttl = ip_defttl;
}
m->m_len = tlen;
m->m_pkthdr.len = tlen;
m->m_pkthdr.rcvif = (struct ifnet *) 0;
nth->th_seq = htonl(seq);
nth->th_ack = htonl(ack);
nth->th_x2 = 0;
nth->th_off = sizeof (struct tcphdr) >> 2;
nth->th_flags = flags;
if (tp)
nth->th_win = htons((u_short) (win >> tp->rcv_scale));
else
nth->th_win = htons((u_short)win);
nth->th_urp = 0;
#ifdef INET6
if (isipv6) {
nth->th_sum = 0;
nth->th_sum = in6_cksum(m, IPPROTO_TCP,
sizeof(struct ip6_hdr),
tlen - sizeof(struct ip6_hdr));
ip6->ip6_hlim = in6_selecthlim(tp ? tp->t_inpcb : NULL,
ro6 && ro6->ro_rt ?
ro6->ro_rt->rt_ifp :
NULL);
} else
#endif /* INET6 */
{
nth->th_sum = in_pseudo(ip->ip_src.s_addr, ip->ip_dst.s_addr,
htons((u_short)(tlen - sizeof(struct ip) + ip->ip_p)));
m->m_pkthdr.csum_flags = CSUM_TCP;
m->m_pkthdr.csum_data = offsetof(struct tcphdr, th_sum);
}
#ifdef TCPDEBUG
if (tp == NULL || (tp->t_inpcb->inp_socket->so_options & SO_DEBUG))
tcp_trace(TA_OUTPUT, 0, tp, mtod(m, void *), th, 0);
#endif
#ifdef IPSEC
ipsec_setsocket(m, tp ? tp->t_inpcb->inp_socket : NULL);
#endif
#ifdef INET6
if (isipv6) {
(void)ip6_output(m, NULL, ro6, ipflags, NULL, NULL);
if (ro6 == &sro6 && ro6->ro_rt) {
RTFREE(ro6->ro_rt);
ro6->ro_rt = NULL;
}
} else
#endif /* INET6 */
{
(void) ip_output(m, NULL, ro, ipflags, NULL);
if (ro == &sro && ro->ro_rt) {
RTFREE(ro->ro_rt);
ro->ro_rt = NULL;
}
}
}
/*
* Create a new TCP control block, making an
* empty reassembly queue and hooking it to the argument
* protocol control block. The `inp' parameter must have
* come from the zone allocator set up in tcp_init().
*/
struct tcpcb *
tcp_newtcpcb(inp)
struct inpcb *inp;
{
struct inp_tp *it;
register struct tcpcb *tp;
#ifdef INET6
int isipv6 = (inp->inp_vflag & INP_IPV6) != 0;
#endif /* INET6 */
it = (struct inp_tp *)inp;
tp = &it->tcb;
bzero((char *) tp, sizeof(struct tcpcb));
LIST_INIT(&tp->t_segq);
tp->t_maxseg = tp->t_maxopd =
#ifdef INET6
isipv6 ? tcp_v6mssdflt :
#endif /* INET6 */
tcp_mssdflt;
/* Set up our timeouts. */
callout_init(tp->tt_rexmt = &it->inp_tp_rexmt, 0);
callout_init(tp->tt_persist = &it->inp_tp_persist, 0);
callout_init(tp->tt_keep = &it->inp_tp_keep, 0);
callout_init(tp->tt_2msl = &it->inp_tp_2msl, 0);
callout_init(tp->tt_delack = &it->inp_tp_delack, 0);
if (tcp_do_rfc1323)
tp->t_flags = (TF_REQ_SCALE|TF_REQ_TSTMP);
if (tcp_do_rfc1644)
tp->t_flags |= TF_REQ_CC;
tp->t_inpcb = inp; /* XXX */
/*
* Init srtt to TCPTV_SRTTBASE (0), so we can tell that we have no
* rtt estimate. Set rttvar so that srtt + 4 * rttvar gives
* reasonable initial retransmit time.
*/
tp->t_srtt = TCPTV_SRTTBASE;
tp->t_rttvar = ((TCPTV_RTOBASE - TCPTV_SRTTBASE) << TCP_RTTVAR_SHIFT) / 4;
tp->t_rttmin = TCPTV_MIN;
tp->t_rxtcur = TCPTV_RTOBASE;
tp->snd_cwnd = TCP_MAXWIN << TCP_MAX_WINSHIFT;
tp->snd_ssthresh = TCP_MAXWIN << TCP_MAX_WINSHIFT;
tp->t_rcvtime = ticks;
/*
* IPv4 TTL initialization is necessary for an IPv6 socket as well,
* because the socket may be bound to an IPv6 wildcard address,
* which may match an IPv4-mapped IPv6 address.
*/
inp->inp_ip_ttl = ip_defttl;
inp->inp_ppcb = (caddr_t)tp;
return (tp); /* XXX */
}
/*
* Drop a TCP connection, reporting
* the specified error. If connection is synchronized,
* then send a RST to peer.
*/
struct tcpcb *
tcp_drop(tp, errno)
register struct tcpcb *tp;
int errno;
{
struct socket *so = tp->t_inpcb->inp_socket;
if (TCPS_HAVERCVDSYN(tp->t_state)) {
tp->t_state = TCPS_CLOSED;
(void) tcp_output(tp);
tcpstat.tcps_drops++;
} else
tcpstat.tcps_conndrops++;
if (errno == ETIMEDOUT && tp->t_softerror)
errno = tp->t_softerror;
so->so_error = errno;
return (tcp_close(tp));
}
/*
* Close a TCP control block:
* discard all space held by the tcp
* discard internet protocol block
* wake up any sleepers
*/
struct tcpcb *
tcp_close(tp)
register struct tcpcb *tp;
{
register struct tseg_qent *q;
struct inpcb *inp = tp->t_inpcb;
struct socket *so = inp->inp_socket;
#ifdef INET6
int isipv6 = (inp->inp_vflag & INP_IPV6) != 0;
#endif /* INET6 */
register struct rtentry *rt;
int dosavessthresh;
/*
* Make sure that all of our timers are stopped before we
* delete the PCB.
*/
callout_stop(tp->tt_rexmt);
callout_stop(tp->tt_persist);
callout_stop(tp->tt_keep);
callout_stop(tp->tt_2msl);
callout_stop(tp->tt_delack);
/*
* If we got enough samples through the srtt filter,
* save the rtt and rttvar in the routing entry.
* 'Enough' is arbitrarily defined as the 16 samples.
* 16 samples is enough for the srtt filter to converge
* to within 5% of the correct value; fewer samples and
* we could save a very bogus rtt.
*
* Don't update the default route's characteristics and don't
* update anything that the user "locked".
*/
if (tp->t_rttupdated >= 16) {
register u_long i = 0;
#ifdef INET6
if (isipv6) {
struct sockaddr_in6 *sin6;
if ((rt = inp->in6p_route.ro_rt) == NULL)
goto no_valid_rt;
sin6 = (struct sockaddr_in6 *)rt_key(rt);
if (IN6_IS_ADDR_UNSPECIFIED(&sin6->sin6_addr))
goto no_valid_rt;
}
else
#endif /* INET6 */
if ((rt = inp->inp_route.ro_rt) == NULL ||
((struct sockaddr_in *)rt_key(rt))->sin_addr.s_addr
== INADDR_ANY)
goto no_valid_rt;
if ((rt->rt_rmx.rmx_locks & RTV_RTT) == 0) {
i = tp->t_srtt *
(RTM_RTTUNIT / (hz * TCP_RTT_SCALE));
if (rt->rt_rmx.rmx_rtt && i)
/*
* filter this update to half the old & half
* the new values, converting scale.
* See route.h and tcp_var.h for a
* description of the scaling constants.
*/
rt->rt_rmx.rmx_rtt =
(rt->rt_rmx.rmx_rtt + i) / 2;
else
rt->rt_rmx.rmx_rtt = i;
tcpstat.tcps_cachedrtt++;
}
if ((rt->rt_rmx.rmx_locks & RTV_RTTVAR) == 0) {
i = tp->t_rttvar *
(RTM_RTTUNIT / (hz * TCP_RTTVAR_SCALE));
if (rt->rt_rmx.rmx_rttvar && i)
rt->rt_rmx.rmx_rttvar =
(rt->rt_rmx.rmx_rttvar + i) / 2;
else
rt->rt_rmx.rmx_rttvar = i;
tcpstat.tcps_cachedrttvar++;
}
/*
* The old comment here said:
* update the pipelimit (ssthresh) if it has been updated
* already or if a pipesize was specified & the threshhold
* got below half the pipesize. I.e., wait for bad news
* before we start updating, then update on both good
* and bad news.
*
* But we want to save the ssthresh even if no pipesize is
* specified explicitly in the route, because such
* connections still have an implicit pipesize specified
* by the global tcp_sendspace. In the absence of a reliable
* way to calculate the pipesize, it will have to do.
*/
i = tp->snd_ssthresh;
if (rt->rt_rmx.rmx_sendpipe != 0)
dosavessthresh = (i < rt->rt_rmx.rmx_sendpipe / 2);
else
dosavessthresh = (i < so->so_snd.sb_hiwat / 2);
if (((rt->rt_rmx.rmx_locks & RTV_SSTHRESH) == 0 &&
i != 0 && rt->rt_rmx.rmx_ssthresh != 0)
|| dosavessthresh) {
/*
* convert the limit from user data bytes to
* packets then to packet data bytes.
*/
i = (i + tp->t_maxseg / 2) / tp->t_maxseg;
if (i < 2)
i = 2;
i *= (u_long)(tp->t_maxseg +
#ifdef INET6
(isipv6 ? sizeof (struct ip6_hdr) +
sizeof (struct tcphdr) :
#endif
sizeof (struct tcpiphdr)
#ifdef INET6
)
#endif
);
if (rt->rt_rmx.rmx_ssthresh)
rt->rt_rmx.rmx_ssthresh =
(rt->rt_rmx.rmx_ssthresh + i) / 2;
else
rt->rt_rmx.rmx_ssthresh = i;
tcpstat.tcps_cachedssthresh++;
}
}
rt = inp->inp_route.ro_rt;
if (rt) {
/*
* mark route for deletion if no information is
* cached.
*/
if ((tp->t_flags & TF_LQ_OVERFLOW) &&
((rt->rt_rmx.rmx_locks & RTV_RTT) == 0)){
if (rt->rt_rmx.rmx_rtt == 0)
rt->rt_flags |= RTF_DELCLONE;
}
}
no_valid_rt:
/* free the reassembly queue, if any */
while((q = LIST_FIRST(&tp->t_segq)) != NULL) {
LIST_REMOVE(q, tqe_q);
m_freem(q->tqe_m);
FREE(q, M_TSEGQ);
}
if (tp->t_template)
(void) m_free(dtom(tp->t_template));
inp->inp_ppcb = NULL;
soisdisconnected(so);
#ifdef INET6
if (INP_CHECK_SOCKAF(so, AF_INET6))
in6_pcbdetach(inp);
else
#endif /* INET6 */
in_pcbdetach(inp);
tcpstat.tcps_closed++;
return ((struct tcpcb *)0);
}
void
tcp_drain()
{
if (do_tcpdrain)
{
struct inpcb *inpb;
struct tcpcb *tcpb;
struct tseg_qent *te;
/*
* Walk the tcpbs, if existing, and flush the reassembly queue,
* if there is one...
* XXX: The "Net/3" implementation doesn't imply that the TCP
* reassembly queue should be flushed, but in a situation
* where we're really low on mbufs, this is potentially
* usefull.
*/
for (inpb = LIST_FIRST(tcbinfo.listhead); inpb;
inpb = LIST_NEXT(inpb, inp_list)) {
if ((tcpb = intotcpcb(inpb))) {
while ((te = LIST_FIRST(&tcpb->t_segq))
!= NULL) {
LIST_REMOVE(te, tqe_q);
m_freem(te->tqe_m);
FREE(te, M_TSEGQ);
}
}
}
}
}
/*
* Notify a tcp user of an asynchronous error;
* store error as soft error, but wake up user
* (for now, won't do anything until can select for soft error).
*/
static void
tcp_notify(inp, error)
struct inpcb *inp;
int error;
{
register struct tcpcb *tp = (struct tcpcb *)inp->inp_ppcb;
register struct socket *so = inp->inp_socket;
/*
* Ignore some errors if we are hooked up.
* If connection hasn't completed, has retransmitted several times,
* and receives a second error, give up now. This is better
* than waiting a long time to establish a connection that
* can never complete.
*/
if (tp->t_state == TCPS_ESTABLISHED &&
(error == EHOSTUNREACH || error == ENETUNREACH ||
error == EHOSTDOWN)) {
return;
} else if (tp->t_state < TCPS_ESTABLISHED && tp->t_rxtshift > 3 &&
tp->t_softerror)
so->so_error = error;
else
tp->t_softerror = error;
wakeup((caddr_t) &so->so_timeo);
sorwakeup(so);
sowwakeup(so);
}
static int
tcp_pcblist(SYSCTL_HANDLER_ARGS)
{
int error, i, n, s;
struct inpcb *inp, **inp_list;
inp_gen_t gencnt;
struct xinpgen xig;
/*
* The process of preparing the TCB list is too time-consuming and
* resource-intensive to repeat twice on every request.
*/
if (req->oldptr == 0) {
n = tcbinfo.ipi_count;
req->oldidx = 2 * (sizeof xig)
+ (n + n/8) * sizeof(struct xtcpcb);
return 0;
}
if (req->newptr != 0)
return EPERM;
/*
* OK, now we're committed to doing something.
*/
s = splnet();
gencnt = tcbinfo.ipi_gencnt;
n = tcbinfo.ipi_count;
splx(s);
xig.xig_len = sizeof xig;
xig.xig_count = n;
xig.xig_gen = gencnt;
xig.xig_sogen = so_gencnt;
error = SYSCTL_OUT(req, &xig, sizeof xig);
if (error)
return error;
inp_list = malloc(n * sizeof *inp_list, M_TEMP, M_WAITOK);
if (inp_list == 0)
return ENOMEM;
s = splnet();
for (inp = LIST_FIRST(tcbinfo.listhead), i = 0; inp && i < n;
inp = LIST_NEXT(inp, inp_list)) {
if (inp->inp_gencnt <= gencnt && !prison_xinpcb(req->p, inp))
inp_list[i++] = inp;
}
splx(s);
n = i;
error = 0;
for (i = 0; i < n; i++) {
inp = inp_list[i];
if (inp->inp_gencnt <= gencnt) {
struct xtcpcb xt;
caddr_t inp_ppcb;
xt.xt_len = sizeof xt;
/* XXX should avoid extra copy */
bcopy(inp, &xt.xt_inp, sizeof *inp);
inp_ppcb = inp->inp_ppcb;
if (inp_ppcb != NULL)
bcopy(inp_ppcb, &xt.xt_tp, sizeof xt.xt_tp);
else
bzero((char *) &xt.xt_tp, sizeof xt.xt_tp);
if (inp->inp_socket)
sotoxsocket(inp->inp_socket, &xt.xt_socket);
error = SYSCTL_OUT(req, &xt, sizeof xt);
}
}
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.
*/
s = splnet();
xig.xig_gen = tcbinfo.ipi_gencnt;
xig.xig_sogen = so_gencnt;
xig.xig_count = tcbinfo.ipi_count;
splx(s);
error = SYSCTL_OUT(req, &xig, sizeof xig);
}
free(inp_list, M_TEMP);
return error;
}
SYSCTL_PROC(_net_inet_tcp, TCPCTL_PCBLIST, pcblist, CTLFLAG_RD, 0, 0,
tcp_pcblist, "S,xtcpcb", "List of active TCP connections");
static int
tcp_getcred(SYSCTL_HANDLER_ARGS)
{
struct sockaddr_in addrs[2];
struct inpcb *inp;
int error, s;
error = suser(req->p);
if (error)
return (error);
error = SYSCTL_IN(req, addrs, sizeof(addrs));
if (error)
return (error);
s = splnet();
inp = in_pcblookup_hash(&tcbinfo, addrs[1].sin_addr, addrs[1].sin_port,
addrs[0].sin_addr, addrs[0].sin_port, 0, NULL);
if (inp == NULL || inp->inp_socket == NULL) {
error = ENOENT;
goto out;
}
error = SYSCTL_OUT(req, inp->inp_socket->so_cred, sizeof(struct ucred));
out:
splx(s);
return (error);
}
SYSCTL_PROC(_net_inet_tcp, OID_AUTO, getcred, CTLTYPE_OPAQUE|CTLFLAG_RW,
0, 0, tcp_getcred, "S,ucred", "Get the ucred of a TCP connection");
#ifdef INET6
static int
tcp6_getcred(SYSCTL_HANDLER_ARGS)
{
struct sockaddr_in6 addrs[2];
struct inpcb *inp;
int error, s, mapped = 0;
error = suser(req->p);
if (error)
return (error);
error = SYSCTL_IN(req, addrs, sizeof(addrs));
if (error)
return (error);
if (IN6_IS_ADDR_V4MAPPED(&addrs[0].sin6_addr)) {
if (IN6_IS_ADDR_V4MAPPED(&addrs[1].sin6_addr))
mapped = 1;
else
return (EINVAL);
}
s = splnet();
if (mapped == 1)
inp = in_pcblookup_hash(&tcbinfo,
*(struct in_addr *)&addrs[1].sin6_addr.s6_addr[12],
addrs[1].sin6_port,
*(struct in_addr *)&addrs[0].sin6_addr.s6_addr[12],
addrs[0].sin6_port,
0, NULL);
else
inp = in6_pcblookup_hash(&tcbinfo, &addrs[1].sin6_addr,
addrs[1].sin6_port,
&addrs[0].sin6_addr, addrs[0].sin6_port,
0, NULL);
if (inp == NULL || inp->inp_socket == NULL) {
error = ENOENT;
goto out;
}
error = SYSCTL_OUT(req, inp->inp_socket->so_cred,
sizeof(struct ucred));
out:
splx(s);
return (error);
}
SYSCTL_PROC(_net_inet6_tcp6, OID_AUTO, getcred, CTLTYPE_OPAQUE|CTLFLAG_RW,
0, 0,
tcp6_getcred, "S,ucred", "Get the ucred of a TCP6 connection");
#endif
void
tcp_ctlinput(cmd, sa, vip)
int cmd;
struct sockaddr *sa;
void *vip;
{
register struct ip *ip = vip;
register struct tcphdr *th;
void (*notify) __P((struct inpcb *, int)) = tcp_notify;
tcp_seq tcp_sequence = 0;
int tcp_seq_check = 0;
if (cmd == PRC_QUENCH)
notify = tcp_quench;
else if ((icmp_admin_prohib_like_rst == 1) && (cmd == PRC_UNREACH_PORT) &&
(ip) && ((IP_VHL_HL(ip->ip_vhl) << 2) == sizeof(struct ip))) {
/*
* Only go here if the length of the IP header in the ICMP packet
* is 20 bytes, that is it doesn't have options, if it does have
* options, we will not have the first 8 bytes of the TCP header,
* and thus we cannot match against TCP source/destination port
* numbers and TCP sequence number.
*/
tcp_seq_check = 1;
notify = tcp_drop_syn_sent;
} else if (cmd == PRC_MSGSIZE)
notify = tcp_mtudisc;
else if (!PRC_IS_REDIRECT(cmd) &&
((unsigned)cmd > PRC_NCMDS || inetctlerrmap[cmd] == 0))
return;
if (ip) {
th = (struct tcphdr *)((caddr_t)ip
+ (IP_VHL_HL(ip->ip_vhl) << 2));
if (tcp_seq_check == 1)
tcp_sequence = ntohl(th->th_seq);
in_pcbnotify(&tcb, sa, th->th_dport, ip->ip_src, th->th_sport,
cmd, notify, tcp_sequence, tcp_seq_check);
} else
in_pcbnotify(&tcb, sa, 0, zeroin_addr, 0, cmd, notify, 0, 0);
}
#ifdef INET6
void
tcp6_ctlinput(cmd, sa, d)
int cmd;
struct sockaddr *sa;
void *d;
{
register struct tcphdr *thp;
struct tcphdr th;
void (*notify) __P((struct inpcb *, int)) = tcp_notify;
struct sockaddr_in6 sa6;
struct ip6_hdr *ip6;
struct mbuf *m;
int off;
if (sa->sa_family != AF_INET6 ||
sa->sa_len != sizeof(struct sockaddr_in6))
return;
if (cmd == PRC_QUENCH)
notify = tcp_quench;
else if (cmd == PRC_MSGSIZE)
notify = tcp_mtudisc;
else if (!PRC_IS_REDIRECT(cmd) &&
((unsigned)cmd > PRC_NCMDS || inet6ctlerrmap[cmd] == 0))
return;
/* if the parameter is from icmp6, decode it. */
if (d != NULL) {
struct ip6ctlparam *ip6cp = (struct ip6ctlparam *)d;
m = ip6cp->ip6c_m;
ip6 = ip6cp->ip6c_ip6;
off = ip6cp->ip6c_off;
} else {
m = NULL;
ip6 = NULL;
off = 0; /* fool gcc */
}
/*
* Translate addresses into internal form.
* Sa check if it is AF_INET6 is done at the top of this funciton.
*/
sa6 = *(struct sockaddr_in6 *)sa;
if (IN6_IS_ADDR_LINKLOCAL(&sa6.sin6_addr) != 0 && m != NULL &&
m->m_pkthdr.rcvif != NULL)
sa6.sin6_addr.s6_addr16[1] = htons(m->m_pkthdr.rcvif->if_index);
if (ip6) {
/*
* XXX: We assume that when IPV6 is non NULL,
* M and OFF are valid.
*/
struct in6_addr s;
/* translate addresses into internal form */
memcpy(&s, &ip6->ip6_src, sizeof(s));
if (IN6_IS_ADDR_LINKLOCAL(&s) != 0 && m != NULL &&
m->m_pkthdr.rcvif != NULL)
s.s6_addr16[1] = htons(m->m_pkthdr.rcvif->if_index);
/* check if we can safely examine src and dst ports */
if (m->m_pkthdr.len < off + sizeof(th))
return;
if (m->m_len < off + sizeof(th)) {
/*
* this should be rare case
* because now MINCLSIZE is "(MHLEN + 1)",
* so we compromise on this copy...
*/
m_copydata(m, off, sizeof(th), (caddr_t)&th);
thp = &th;
} else
thp = (struct tcphdr *)(mtod(m, caddr_t) + off);
in6_pcbnotify(&tcb, (struct sockaddr *)&sa6, thp->th_dport,
&s, thp->th_sport, cmd, notify);
} else
in6_pcbnotify(&tcb, (struct sockaddr *)&sa6, 0, &zeroin6_addr,
0, cmd, notify);
}
#endif /* INET6 */
/*
* Check if the supplied TCP sequence number is a sequence number
* for a sent but unacknowledged packet on the given TCP session.
*/
int
tcp_seq_vs_sess(inp, tcp_sequence)
struct inpcb *inp;
tcp_seq tcp_sequence;
{
struct tcpcb *tp = intotcpcb(inp);
/*
* If the sequence number is less than that of the last
* unacknowledged packet, or greater than that of the
* last sent, the given sequence number is not that
* of a sent but unacknowledged packet for this session.
*/
if (SEQ_LT(tcp_sequence, tp->snd_una) ||
SEQ_GT(tcp_sequence, tp->snd_max)) {
return(0);
} else {
return(1);
}
}
/*
* When a source quench is received, close congestion window
* to one segment. We will gradually open it again as we proceed.
*/
void
tcp_quench(inp, errno)
struct inpcb *inp;
int errno;
{
struct tcpcb *tp = intotcpcb(inp);
if (tp)
tp->snd_cwnd = tp->t_maxseg;
}
/*
* When a ICMP unreachable is recieved, drop the
* TCP connection, depending on the sysctl
* icmp_like_rst_syn_sent_only, it only drops
* the session if it's in SYN-SENT state
*/
void
tcp_drop_syn_sent(inp, errno)
struct inpcb *inp;
int errno;
{
struct tcpcb *tp = intotcpcb(inp);
if((tp) && ((icmp_like_rst_syn_sent_only == 0) ||
(tp->t_state == TCPS_SYN_SENT)))
tcp_drop(tp, errno);
}
/*
* When `need fragmentation' ICMP is received, update our idea of the MSS
* based on the new value in the route. Also nudge TCP to send something,
* since we know the packet we just sent was dropped.
* This duplicates some code in the tcp_mss() function in tcp_input.c.
*/
void
tcp_mtudisc(inp, errno)
struct inpcb *inp;
int errno;
{
struct tcpcb *tp = intotcpcb(inp);
struct rtentry *rt;
struct rmxp_tao *taop;
struct socket *so = inp->inp_socket;
int offered;
int mss;
#ifdef INET6
int isipv6 = (tp->t_inpcb->inp_vflag & INP_IPV6) != 0;
#endif /* INET6 */
if (tp) {
#ifdef INET6
if (isipv6)
rt = tcp_rtlookup6(inp);
else
#endif /* INET6 */
rt = tcp_rtlookup(inp);
if (!rt || !rt->rt_rmx.rmx_mtu) {
tp->t_maxopd = tp->t_maxseg =
#ifdef INET6
isipv6 ? tcp_v6mssdflt :
#endif /* INET6 */
tcp_mssdflt;
return;
}
taop = rmx_taop(rt->rt_rmx);
offered = taop->tao_mssopt;
mss = rt->rt_rmx.rmx_mtu -
#ifdef INET6
(isipv6 ?
sizeof(struct ip6_hdr) + sizeof(struct tcphdr) :
#endif /* INET6 */
sizeof(struct tcpiphdr)
#ifdef INET6
)
#endif /* INET6 */
;
if (offered)
mss = min(mss, offered);
/*
* XXX - The above conditional probably violates the TCP
* spec. The problem is that, since we don't know the
* other end's MSS, we are supposed to use a conservative
* default. But, if we do that, then MTU discovery will
* never actually take place, because the conservative
* default is much less than the MTUs typically seen
* on the Internet today. For the moment, we'll sweep
* this under the carpet.
*
* The conservative default might not actually be a problem
* if the only case this occurs is when sending an initial
* SYN with options and data to a host we've never talked
* to before. Then, they will reply with an MSS value which
* will get recorded and the new parameters should get
* recomputed. For Further Study.
*/
if (tp->t_maxopd <= mss)
return;
tp->t_maxopd = mss;
if ((tp->t_flags & (TF_REQ_TSTMP|TF_NOOPT)) == TF_REQ_TSTMP &&
(tp->t_flags & TF_RCVD_TSTMP) == TF_RCVD_TSTMP)
mss -= TCPOLEN_TSTAMP_APPA;
if ((tp->t_flags & (TF_REQ_CC|TF_NOOPT)) == TF_REQ_CC &&
(tp->t_flags & TF_RCVD_CC) == TF_RCVD_CC)
mss -= TCPOLEN_CC_APPA;
#if (MCLBYTES & (MCLBYTES - 1)) == 0
if (mss > MCLBYTES)
mss &= ~(MCLBYTES-1);
#else
if (mss > MCLBYTES)
mss = mss / MCLBYTES * MCLBYTES;
#endif
if (so->so_snd.sb_hiwat < mss)
mss = so->so_snd.sb_hiwat;
tp->t_maxseg = mss;
tcpstat.tcps_mturesent++;
tp->t_rtttime = 0;
tp->snd_nxt = tp->snd_una;
tcp_output(tp);
}
}
/*
* Look-up the routing entry to the peer of this inpcb. If no route
* is found and it cannot be allocated the return NULL. This routine
* is called by TCP routines that access the rmx structure and by tcp_mss
* to get the interface MTU.
*/
struct rtentry *
tcp_rtlookup(inp)
struct inpcb *inp;
{
struct route *ro;
struct rtentry *rt;
ro = &inp->inp_route;
rt = ro->ro_rt;
if (rt == NULL || !(rt->rt_flags & RTF_UP)) {
/* No route yet, so try to acquire one */
if (inp->inp_faddr.s_addr != INADDR_ANY) {
ro->ro_dst.sa_family = AF_INET;
ro->ro_dst.sa_len = sizeof(ro->ro_dst);
((struct sockaddr_in *) &ro->ro_dst)->sin_addr =
inp->inp_faddr;
rtalloc(ro);
rt = ro->ro_rt;
}
}
return rt;
}
#ifdef INET6
struct rtentry *
tcp_rtlookup6(inp)
struct inpcb *inp;
{
struct route_in6 *ro6;
struct rtentry *rt;
ro6 = &inp->in6p_route;
rt = ro6->ro_rt;
if (rt == NULL || !(rt->rt_flags & RTF_UP)) {
/* No route yet, so try to acquire one */
if (!IN6_IS_ADDR_UNSPECIFIED(&inp->in6p_faddr)) {
ro6->ro_dst.sin6_family = AF_INET6;
ro6->ro_dst.sin6_len = sizeof(ro6->ro_dst);
ro6->ro_dst.sin6_addr = inp->in6p_faddr;
rtalloc((struct route *)ro6);
rt = ro6->ro_rt;
}
}
return rt;
}
#endif /* INET6 */
#ifdef IPSEC
/* compute ESP/AH header size for TCP, including outer IP header. */
size_t
ipsec_hdrsiz_tcp(tp)
struct tcpcb *tp;
{
struct inpcb *inp;
struct mbuf *m;
size_t hdrsiz;
struct ip *ip;
#ifdef INET6
struct ip6_hdr *ip6;
#endif /* INET6 */
struct tcphdr *th;
if (!tp || !tp->t_template || !(inp = tp->t_inpcb))
return 0;
MGETHDR(m, M_DONTWAIT, MT_DATA);
if (!m)
return 0;
#ifdef INET6
if ((inp->inp_vflag & INP_IPV6) != 0) {
ip6 = mtod(m, struct ip6_hdr *);
th = (struct tcphdr *)(ip6 + 1);
m->m_pkthdr.len = m->m_len =
sizeof(struct ip6_hdr) + sizeof(struct tcphdr);
bcopy((caddr_t)tp->t_template->tt_ipgen, (caddr_t)ip6,
sizeof(struct ip6_hdr));
bcopy((caddr_t)&tp->t_template->tt_t, (caddr_t)th,
sizeof(struct tcphdr));
hdrsiz = ipsec6_hdrsiz(m, IPSEC_DIR_OUTBOUND, inp);
} else
#endif /* INET6 */
{
ip = mtod(m, struct ip *);
th = (struct tcphdr *)(ip + 1);
m->m_pkthdr.len = m->m_len = sizeof(struct tcpiphdr);
bcopy((caddr_t)tp->t_template->tt_ipgen, (caddr_t)ip,
sizeof(struct ip));
bcopy((caddr_t)&tp->t_template->tt_t, (caddr_t)th,
sizeof(struct tcphdr));
hdrsiz = ipsec4_hdrsiz(m, IPSEC_DIR_OUTBOUND, inp);
}
m_free(m);
return hdrsiz;
}
#endif /*IPSEC*/
/*
* Return a pointer to the cached information about the remote host.
* The cached information is stored in the protocol specific part of
* the route metrics.
*/
struct rmxp_tao *
tcp_gettaocache(inp)
struct inpcb *inp;
{
struct rtentry *rt;
#ifdef INET6
if ((inp->inp_vflag & INP_IPV6) != 0)
rt = tcp_rtlookup6(inp);
else
#endif /* INET6 */
rt = tcp_rtlookup(inp);
/* Make sure this is a host route and is up. */
if (rt == NULL ||
(rt->rt_flags & (RTF_UP|RTF_HOST)) != (RTF_UP|RTF_HOST))
return NULL;
return rmx_taop(rt->rt_rmx);
}
/*
* Clear all the TAO cache entries, called from tcp_init.
*
* XXX
* This routine is just an empty one, because we assume that the routing
* routing tables are initialized at the same time when TCP, so there is
* nothing in the cache left over.
*/
static void
tcp_cleartaocache()
{
}
|