summaryrefslogtreecommitdiffstats
path: root/sys/netinet/tcp_usrreq.c
blob: 5d8934cbffc0dd2627fe6da8639cf916c4fa734e (plain)
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
/*
 * Copyright (c) 1982, 1986, 1988, 1993
 *	The Regents of the University of California.  All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 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.
 *
 *	From: @(#)tcp_usrreq.c	8.2 (Berkeley) 1/3/94
 * $FreeBSD$
 */

#include "opt_ipsec.h"
#include "opt_inet6.h"
#include "opt_tcpdebug.h"

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/sysctl.h>
#include <sys/mbuf.h>
#ifdef INET6
#include <sys/domain.h>
#endif /* INET6 */
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/protosw.h>
#include <sys/proc.h>
#include <sys/jail.h>

#include <net/if.h>
#include <net/route.h>

#include <netinet/in.h>
#include <netinet/in_systm.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>
#include <netinet/tcpip.h>
#ifdef TCPDEBUG
#include <netinet/tcp_debug.h>
#endif

#ifdef IPSEC
#include <netinet6/ipsec.h>
#endif /*IPSEC*/

/*
 * TCP protocol interface to socket abstraction.
 */
extern	char *tcpstates[];	/* XXX ??? */

static int	tcp_attach(struct socket *, struct thread *td);
static int	tcp_connect(struct tcpcb *, struct sockaddr *,
		    struct thread *td);
#ifdef INET6
static int	tcp6_connect(struct tcpcb *, struct sockaddr *,
		    struct thread *td);
#endif /* INET6 */
static struct tcpcb *
		tcp_disconnect(struct tcpcb *);
static struct tcpcb *
		tcp_usrclosed(struct tcpcb *);

#ifdef TCPDEBUG
#define	TCPDEBUG0	int ostate = 0
#define	TCPDEBUG1()	ostate = tp ? tp->t_state : 0
#define	TCPDEBUG2(req)								\
	do {									\
		if (tp != 0) {							\
			SOCK_LOCK(so);						\
			if (so->so_options & SO_DEBUG) {			\
				SOCK_UNLOCK(so);				\
				tcp_trace(TA_USER, ostate, tp, 0, 0, req);	\
			} else							\
				SOCK_UNLOCK(so);				\
		}								\
	} while(0)
#else
#define	TCPDEBUG0
#define	TCPDEBUG1()
#define	TCPDEBUG2(req)
#endif

/*
 * TCP attaches to socket via pru_attach(), reserving space,
 * and an internet control block.
 */
static int
tcp_usr_attach(struct socket *so, int proto, struct thread *td)
{
	int s = splnet();
	int error;
	struct inpcb *inp = sotoinpcb(so);
	struct tcpcb *tp = 0;
	TCPDEBUG0;

	TCPDEBUG1();
	if (inp) {
		error = EISCONN;
		goto out;
	}

	error = tcp_attach(so, td);
	if (error)
		goto out;

	SOCK_LOCK(so);
	if ((so->so_options & SO_LINGER) && so->so_linger == 0)
		so->so_linger = TCP_LINGERTIME;
	SOCK_UNLOCK(so);
	tp = sototcpcb(so);
out:
	TCPDEBUG2(PRU_ATTACH);
	splx(s);
	return error;
}

/*
 * pru_detach() detaches the TCP protocol from the socket.
 * If the protocol state is non-embryonic, then can't
 * do this directly: have to initiate a pru_disconnect(),
 * which may finish later; embryonic TCB's can just
 * be discarded here.
 */
static int
tcp_usr_detach(struct socket *so)
{
	int s = splnet();
	int error = 0;
	struct inpcb *inp = sotoinpcb(so);
	struct tcpcb *tp;
	TCPDEBUG0;

	if (inp == 0) {
		splx(s);
		return EINVAL;	/* XXX */
	}
	tp = intotcpcb(inp);
	TCPDEBUG1();
	tp = tcp_disconnect(tp);

	TCPDEBUG2(PRU_DETACH);
	splx(s);
	return error;
}

#define	COMMON_START()	TCPDEBUG0; \
			do { \
				     if (inp == 0) { \
					     splx(s); \
					     return EINVAL; \
				     } \
				     tp = intotcpcb(inp); \
				     TCPDEBUG1(); \
		     } while(0)
			     
#define COMMON_END(req)	out: TCPDEBUG2(req); splx(s); return error; goto out


/*
 * Give the socket an address.
 */
static int
tcp_usr_bind(struct socket *so, struct sockaddr *nam, struct thread *td)
{
	int s = splnet();
	int error = 0;
	struct inpcb *inp = sotoinpcb(so);
	struct tcpcb *tp;
	struct sockaddr_in *sinp;

	COMMON_START();

	/*
	 * Must check for multicast addresses and disallow binding
	 * to them.
	 */
	sinp = (struct sockaddr_in *)nam;
	if (sinp->sin_family == AF_INET &&
	    IN_MULTICAST(ntohl(sinp->sin_addr.s_addr))) {
		error = EAFNOSUPPORT;
		goto out;
	}
	error = in_pcbbind(inp, nam, td);
	if (error)
		goto out;
	COMMON_END(PRU_BIND);

}

#ifdef INET6
static int
tcp6_usr_bind(struct socket *so, struct sockaddr *nam, struct thread *td)
{
	int s = splnet();
	int error = 0;
	struct inpcb *inp = sotoinpcb(so);
	struct tcpcb *tp;
	struct sockaddr_in6 *sin6p;

	COMMON_START();

	/*
	 * Must check for multicast addresses and disallow binding
	 * to them.
	 */
	sin6p = (struct sockaddr_in6 *)nam;
	if (sin6p->sin6_family == AF_INET6 &&
	    IN6_IS_ADDR_MULTICAST(&sin6p->sin6_addr)) {
		error = EAFNOSUPPORT;
		goto out;
	}
	inp->inp_vflag &= ~INP_IPV4;
	inp->inp_vflag |= INP_IPV6;
	if (ip6_mapped_addr_on && (inp->inp_flags & IN6P_IPV6_V6ONLY) == 0) {
		if (IN6_IS_ADDR_UNSPECIFIED(&sin6p->sin6_addr))
			inp->inp_vflag |= INP_IPV4;
		else if (IN6_IS_ADDR_V4MAPPED(&sin6p->sin6_addr)) {
			struct sockaddr_in sin;

			in6_sin6_2_sin(&sin, sin6p);
			inp->inp_vflag |= INP_IPV4;
			inp->inp_vflag &= ~INP_IPV6;
			error = in_pcbbind(inp, (struct sockaddr *)&sin, td);
			goto out;
		}
	}
	error = in6_pcbbind(inp, nam, td);
	if (error)
		goto out;
	COMMON_END(PRU_BIND);
}
#endif /* INET6 */

/*
 * Prepare to accept connections.
 */
static int
tcp_usr_listen(struct socket *so, struct thread *td)
{
	int s = splnet();
	int error = 0;
	struct inpcb *inp = sotoinpcb(so);
	struct tcpcb *tp;

	COMMON_START();
	if (inp->inp_lport == 0)
		error = in_pcbbind(inp, (struct sockaddr *)0, td);
	if (error == 0)
		tp->t_state = TCPS_LISTEN;
	COMMON_END(PRU_LISTEN);
}

#ifdef INET6
static int
tcp6_usr_listen(struct socket *so, struct thread *td)
{
	int s = splnet();
	int error = 0;
	struct inpcb *inp = sotoinpcb(so);
	struct tcpcb *tp;

	COMMON_START();
	if (inp->inp_lport == 0) {
		inp->inp_vflag &= ~INP_IPV4;
		if (ip6_mapped_addr_on &&
		    (inp->inp_flags & IN6P_IPV6_V6ONLY) == 0)
			inp->inp_vflag |= INP_IPV4;
		error = in6_pcbbind(inp, (struct sockaddr *)0, td);
	}
	if (error == 0)
		tp->t_state = TCPS_LISTEN;
	COMMON_END(PRU_LISTEN);
}
#endif /* INET6 */

/*
 * Initiate connection to peer.
 * Create a template for use in transmissions on this connection.
 * Enter SYN_SENT state, and mark socket as connecting.
 * Start keep-alive timer, and seed output sequence space.
 * Send initial segment on connection.
 */
static int
tcp_usr_connect(struct socket *so, struct sockaddr *nam, struct thread *td)
{
	int s = splnet();
	int error = 0;
	struct inpcb *inp = sotoinpcb(so);
	struct tcpcb *tp;
	struct sockaddr_in *sinp;

	COMMON_START();

	/*
	 * Must disallow TCP ``connections'' to multicast addresses.
	 */
	sinp = (struct sockaddr_in *)nam;
	if (sinp->sin_family == AF_INET
	    && IN_MULTICAST(ntohl(sinp->sin_addr.s_addr))) {
		error = EAFNOSUPPORT;
		goto out;
	}

	if (td && jailed(td->td_ucred))
		prison_remote_ip(td->td_ucred, 0, &sinp->sin_addr.s_addr);

	if ((error = tcp_connect(tp, nam, td)) != 0)
		goto out;
	error = tcp_output(tp);
	COMMON_END(PRU_CONNECT);
}

#ifdef INET6
static int
tcp6_usr_connect(struct socket *so, struct sockaddr *nam, struct thread *td)
{
	int s = splnet();
	int error = 0;
	struct inpcb *inp = sotoinpcb(so);
	struct tcpcb *tp;
	struct sockaddr_in6 *sin6p;

	COMMON_START();

	/*
	 * Must disallow TCP ``connections'' to multicast addresses.
	 */
	sin6p = (struct sockaddr_in6 *)nam;
	if (sin6p->sin6_family == AF_INET6
	    && IN6_IS_ADDR_MULTICAST(&sin6p->sin6_addr)) {
		error = EAFNOSUPPORT;
		goto out;
	}

	if (IN6_IS_ADDR_V4MAPPED(&sin6p->sin6_addr)) {
		struct sockaddr_in sin;

		if (!ip6_mapped_addr_on ||
		    (inp->inp_flags & IN6P_IPV6_V6ONLY))
			return(EINVAL);

		in6_sin6_2_sin(&sin, sin6p);
		inp->inp_vflag |= INP_IPV4;
		inp->inp_vflag &= ~INP_IPV6;
		if ((error = tcp_connect(tp, (struct sockaddr *)&sin, td)) != 0)
			goto out;
		error = tcp_output(tp);
		goto out;
	}
	inp->inp_vflag &= ~INP_IPV4;
	inp->inp_vflag |= INP_IPV6;
	inp->inp_inc.inc_isipv6 = 1;
	if ((error = tcp6_connect(tp, nam, td)) != 0)
		goto out;
	error = tcp_output(tp);
	COMMON_END(PRU_CONNECT);
}
#endif /* INET6 */

/*
 * Initiate disconnect from peer.
 * If connection never passed embryonic stage, just drop;
 * else if don't need to let data drain, then can just drop anyways,
 * else have to begin TCP shutdown process: mark socket disconnecting,
 * drain unread data, state switch to reflect user close, and
 * send segment (e.g. FIN) to peer.  Socket will be really disconnected
 * when peer sends FIN and acks ours.
 *
 * SHOULD IMPLEMENT LATER PRU_CONNECT VIA REALLOC TCPCB.
 */
static int
tcp_usr_disconnect(struct socket *so)
{
	int s = splnet();
	int error = 0;
	struct inpcb *inp = sotoinpcb(so);
	struct tcpcb *tp;

	COMMON_START();
	tp = tcp_disconnect(tp);
	COMMON_END(PRU_DISCONNECT);
}

/*
 * Accept a connection.  Essentially all the work is
 * done at higher levels; just return the address
 * of the peer, storing through addr.
 */
static int
tcp_usr_accept(struct socket *so, struct sockaddr **nam)
{
	int s = splnet();
	int error = 0;
	struct inpcb *inp = sotoinpcb(so);
	struct tcpcb *tp = NULL;
	TCPDEBUG0;

	SOCK_LOCK(so);
	if (so->so_state & SS_ISDISCONNECTED) {
		SOCK_UNLOCK(so);
		error = ECONNABORTED;
		goto out;
	}
	SOCK_UNLOCK(so);
	if (inp == 0) {
		splx(s);
		return (EINVAL);
	}
	tp = intotcpcb(inp);
	TCPDEBUG1();
	in_setpeeraddr(so, nam);
	COMMON_END(PRU_ACCEPT);
}

#ifdef INET6
static int
tcp6_usr_accept(struct socket *so, struct sockaddr **nam)
{
	int s = splnet();
	int error = 0;
	struct inpcb *inp = sotoinpcb(so);
	struct tcpcb *tp = NULL;
	TCPDEBUG0;

	SOCK_LOCK(so);
	if (so->so_state & SS_ISDISCONNECTED) {
		SOCK_UNLOCK(so);
		error = ECONNABORTED;
		goto out;
	}
	SOCK_UNLOCK(so);
	if (inp == 0) {
		splx(s);
		return (EINVAL);
	}
	tp = intotcpcb(inp);
	TCPDEBUG1();
	in6_mapped_peeraddr(so, nam);
	COMMON_END(PRU_ACCEPT);
}
#endif /* INET6 */
/*
 * Mark the connection as being incapable of further output.
 */
static int
tcp_usr_shutdown(struct socket *so)
{
	int s = splnet();
	int error = 0;
	struct inpcb *inp = sotoinpcb(so);
	struct tcpcb *tp;

	COMMON_START();
	socantsendmore(so);
	tp = tcp_usrclosed(tp);
	if (tp)
		error = tcp_output(tp);
	COMMON_END(PRU_SHUTDOWN);
}

/*
 * After a receive, possibly send window update to peer.
 */
static int
tcp_usr_rcvd(struct socket *so, int flags)
{
	int s = splnet();
	int error = 0;
	struct inpcb *inp = sotoinpcb(so);
	struct tcpcb *tp;

	COMMON_START();
	tcp_output(tp);
	COMMON_END(PRU_RCVD);
}

/*
 * Do a send by putting data in output queue and updating urgent
 * marker if URG set.  Possibly send more data.  Unlike the other
 * pru_*() routines, the mbuf chains are our responsibility.  We
 * must either enqueue them or free them.  The other pru_* routines
 * generally are caller-frees.
 */
static int
tcp_usr_send(struct socket *so, int flags, struct mbuf *m, 
	     struct sockaddr *nam, struct mbuf *control, struct thread *td)
{
	int s = splnet();
	int error = 0;
	struct inpcb *inp = sotoinpcb(so);
	struct tcpcb *tp;
#ifdef INET6
	int isipv6;
#endif
	TCPDEBUG0;

	if (inp == NULL) {
		/*
		 * OOPS! we lost a race, the TCP session got reset after
		 * we checked SS_CANTSENDMORE, eg: while doing uiomove or a
		 * network interrupt in the non-splnet() section of sosend().
		 */
		if (m)
			m_freem(m);
		if (control)
			m_freem(control);
		error = ECONNRESET;	/* XXX EPIPE? */
		tp = NULL;
		TCPDEBUG1();
		goto out;
	}
#ifdef INET6
	isipv6 = nam && nam->sa_family == AF_INET6;
#endif /* INET6 */
	tp = intotcpcb(inp);
	TCPDEBUG1();
	if (control) {
		/* TCP doesn't do control messages (rights, creds, etc) */
		if (control->m_len) {
			m_freem(control);
			if (m)
				m_freem(m);
			error = EINVAL;
			goto out;
		}
		m_freem(control);	/* empty control, just free it */
	}
	if(!(flags & PRUS_OOB)) {
		sbappend(&so->so_snd, m);
		if (nam && tp->t_state < TCPS_SYN_SENT) {
			/*
			 * Do implied connect if not yet connected,
			 * initialize window to default value, and
			 * initialize maxseg/maxopd using peer's cached
			 * MSS.
			 */
#ifdef INET6
			if (isipv6)
				error = tcp6_connect(tp, nam, td);
			else
#endif /* INET6 */
			error = tcp_connect(tp, nam, td);
			if (error)
				goto out;
			tp->snd_wnd = TTCP_CLIENT_SND_WND;
			tcp_mss(tp, -1);
		}

		if (flags & PRUS_EOF) {
			/*
			 * Close the send side of the connection after
			 * the data is sent.
			 */
			socantsendmore(so);
			tp = tcp_usrclosed(tp);
		}
		if (tp != NULL) {
			if (flags & PRUS_MORETOCOME)
				tp->t_flags |= TF_MORETOCOME;
			error = tcp_output(tp);
			if (flags & PRUS_MORETOCOME)
				tp->t_flags &= ~TF_MORETOCOME;
		}
	} else {
		if (sbspace(&so->so_snd) < -512) {
			m_freem(m);
			error = ENOBUFS;
			goto out;
		}
		/*
		 * According to RFC961 (Assigned Protocols),
		 * the urgent pointer points to the last octet
		 * of urgent data.  We continue, however,
		 * to consider it to indicate the first octet
		 * of data past the urgent section.
		 * Otherwise, snd_up should be one lower.
		 */
		sbappend(&so->so_snd, m);
		if (nam && tp->t_state < TCPS_SYN_SENT) {
			/*
			 * Do implied connect if not yet connected,
			 * initialize window to default value, and
			 * initialize maxseg/maxopd using peer's cached
			 * MSS.
			 */
#ifdef INET6
			if (isipv6)
				error = tcp6_connect(tp, nam, td);
			else
#endif /* INET6 */
			error = tcp_connect(tp, nam, td);
			if (error)
				goto out;
			tp->snd_wnd = TTCP_CLIENT_SND_WND;
			tcp_mss(tp, -1);
		}
		tp->snd_up = tp->snd_una + so->so_snd.sb_cc;
		tp->t_force = 1;
		error = tcp_output(tp);
		tp->t_force = 0;
	}
	COMMON_END((flags & PRUS_OOB) ? PRU_SENDOOB : 
		   ((flags & PRUS_EOF) ? PRU_SEND_EOF : PRU_SEND));
}

/*
 * Abort the TCP.
 */
static int
tcp_usr_abort(struct socket *so)
{
	int s = splnet();
	int error = 0;
	struct inpcb *inp = sotoinpcb(so);
	struct tcpcb *tp;

	COMMON_START();
	tp = tcp_drop(tp, ECONNABORTED);
	COMMON_END(PRU_ABORT);
}

/*
 * Receive out-of-band data.
 */
static int
tcp_usr_rcvoob(struct socket *so, struct mbuf *m, int flags)
{
	int s = splnet();
	int error = 0;
	struct inpcb *inp = sotoinpcb(so);
	struct tcpcb *tp;

	COMMON_START();
	SOCK_LOCK(so);
	if ((so->so_oobmark == 0 &&
	     (so->so_state & SS_RCVATMARK) == 0) ||
	    so->so_options & SO_OOBINLINE) {
		SOCK_UNLOCK(so);
		error = EINVAL;
		goto out;
	}
	SOCK_UNLOCK(so);
	if (tp->t_oobflags & TCPOOB_HADDATA) {
		error = EINVAL;
		goto out;
	}
	if ((tp->t_oobflags & TCPOOB_HAVEDATA) == 0) {
		error = EWOULDBLOCK;
		goto out;
	}
	m->m_len = 1;
	*mtod(m, caddr_t) = tp->t_iobc;
	if ((flags & MSG_PEEK) == 0)
		tp->t_oobflags ^= (TCPOOB_HAVEDATA | TCPOOB_HADDATA);
	COMMON_END(PRU_RCVOOB);
}

/* xxx - should be const */
struct pr_usrreqs tcp_usrreqs = {
	tcp_usr_abort, tcp_usr_accept, tcp_usr_attach, tcp_usr_bind,
	tcp_usr_connect, pru_connect2_notsupp, in_control, tcp_usr_detach,
	tcp_usr_disconnect, tcp_usr_listen, in_setpeeraddr, tcp_usr_rcvd,
	tcp_usr_rcvoob, tcp_usr_send, pru_sense_null, tcp_usr_shutdown,
	in_setsockaddr, sosend, soreceive, sopoll
};

#ifdef INET6
struct pr_usrreqs tcp6_usrreqs = {
	tcp_usr_abort, tcp6_usr_accept, tcp_usr_attach, tcp6_usr_bind,
	tcp6_usr_connect, pru_connect2_notsupp, in6_control, tcp_usr_detach,
	tcp_usr_disconnect, tcp6_usr_listen, in6_mapped_peeraddr, tcp_usr_rcvd,
	tcp_usr_rcvoob, tcp_usr_send, pru_sense_null, tcp_usr_shutdown,
	in6_mapped_sockaddr, sosend, soreceive, sopoll
};
#endif /* INET6 */

/*
 * Common subroutine to open a TCP connection to remote host specified
 * by struct sockaddr_in in mbuf *nam.  Call in_pcbbind to assign a local
 * port number if needed.  Call in_pcbladdr to do the routing and to choose
 * a local host address (interface).  If there is an existing incarnation
 * of the same connection in TIME-WAIT state and if the remote host was
 * sending CC options and if the connection duration was < MSL, then
 * truncate the previous TIME-WAIT state and proceed.
 * Initialize connection parameters and enter SYN-SENT state.
 */
static int
tcp_connect(tp, nam, td)
	register struct tcpcb *tp;
	struct sockaddr *nam;
	struct thread *td;
{
	struct inpcb *inp = tp->t_inpcb, *oinp;
	struct socket *so = inp->inp_socket;
	struct tcpcb *otp;
	struct sockaddr_in *sin = (struct sockaddr_in *)nam;
	struct sockaddr_in *ifaddr;
	struct rmxp_tao *taop;
	struct rmxp_tao tao_noncached;
	int error;

	if (inp->inp_lport == 0) {
		error = in_pcbbind(inp, (struct sockaddr *)0, td);
		if (error)
			return error;
	}

	/*
	 * Cannot simply call in_pcbconnect, because there might be an
	 * earlier incarnation of this same connection still in
	 * TIME_WAIT state, creating an ADDRINUSE error.
	 */
	error = in_pcbladdr(inp, nam, &ifaddr);
	if (error)
		return error;
	oinp = in_pcblookup_hash(inp->inp_pcbinfo,
	    sin->sin_addr, sin->sin_port,
	    inp->inp_laddr.s_addr != INADDR_ANY ? inp->inp_laddr
						: ifaddr->sin_addr,
	    inp->inp_lport,  0, NULL);
	if (oinp) {
		if (oinp != inp && (otp = intotcpcb(oinp)) != NULL &&
		otp->t_state == TCPS_TIME_WAIT &&
		    (ticks - otp->t_starttime) < tcp_msl &&
		    (otp->t_flags & TF_RCVD_CC))
			otp = tcp_close(otp);
		else
			return EADDRINUSE;
	}
	if (inp->inp_laddr.s_addr == INADDR_ANY)
		inp->inp_laddr = ifaddr->sin_addr;
	inp->inp_faddr = sin->sin_addr;
	inp->inp_fport = sin->sin_port;
	in_pcbrehash(inp);

	/* Compute window scaling to request.  */
	while (tp->request_r_scale < TCP_MAX_WINSHIFT &&
	    (TCP_MAXWIN << tp->request_r_scale) < so->so_rcv.sb_hiwat)
		tp->request_r_scale++;

	SOCK_LOCK(so);
	soisconnecting(so);
	SOCK_UNLOCK(so);
	tcpstat.tcps_connattempt++;
	tp->t_state = TCPS_SYN_SENT;
	callout_reset(tp->tt_keep, tcp_keepinit, tcp_timer_keep, tp);
	tp->iss = tcp_new_isn(tp);
	tcp_sendseqinit(tp);

	/*
	 * Generate a CC value for this connection and
	 * check whether CC or CCnew should be used.
	 */
	if ((taop = tcp_gettaocache(&tp->t_inpcb->inp_inc)) == NULL) {
		taop = &tao_noncached;
		bzero(taop, sizeof(*taop));
	}

	tp->cc_send = CC_INC(tcp_ccgen);
	if (taop->tao_ccsent != 0 &&
	    CC_GEQ(tp->cc_send, taop->tao_ccsent)) {
		taop->tao_ccsent = tp->cc_send;
	} else {
		taop->tao_ccsent = 0;
		tp->t_flags |= TF_SENDCCNEW;
	}

	return 0;
}

#ifdef INET6
static int
tcp6_connect(tp, nam, td)
	register struct tcpcb *tp;
	struct sockaddr *nam;
	struct thread *td;
{
	struct inpcb *inp = tp->t_inpcb, *oinp;
	struct socket *so = inp->inp_socket;
	struct tcpcb *otp;
	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)nam;
	struct in6_addr *addr6;
	struct rmxp_tao *taop;
	struct rmxp_tao tao_noncached;
	int error;

	if (inp->inp_lport == 0) {
		error = in6_pcbbind(inp, (struct sockaddr *)0, td);
		if (error)
			return error;
	}

	/*
	 * Cannot simply call in_pcbconnect, because there might be an
	 * earlier incarnation of this same connection still in
	 * TIME_WAIT state, creating an ADDRINUSE error.
	 */
	error = in6_pcbladdr(inp, nam, &addr6);
	if (error)
		return error;
	oinp = in6_pcblookup_hash(inp->inp_pcbinfo,
				  &sin6->sin6_addr, sin6->sin6_port,
				  IN6_IS_ADDR_UNSPECIFIED(&inp->in6p_laddr)
				  ? addr6
				  : &inp->in6p_laddr,
				  inp->inp_lport,  0, NULL);
	if (oinp) {
		if (oinp != inp && (otp = intotcpcb(oinp)) != NULL &&
		    otp->t_state == TCPS_TIME_WAIT &&
		    (ticks - otp->t_starttime) < tcp_msl &&
		    (otp->t_flags & TF_RCVD_CC))
			otp = tcp_close(otp);
		else
			return EADDRINUSE;
	}
	if (IN6_IS_ADDR_UNSPECIFIED(&inp->in6p_laddr))
		inp->in6p_laddr = *addr6;
	inp->in6p_faddr = sin6->sin6_addr;
	inp->inp_fport = sin6->sin6_port;
	if ((sin6->sin6_flowinfo & IPV6_FLOWINFO_MASK) != NULL)
		inp->in6p_flowinfo = sin6->sin6_flowinfo;
	in_pcbrehash(inp);

	/* Compute window scaling to request.  */
	while (tp->request_r_scale < TCP_MAX_WINSHIFT &&
	    (TCP_MAXWIN << tp->request_r_scale) < so->so_rcv.sb_hiwat)
		tp->request_r_scale++;

	SOCK_LOCK(so);
	soisconnecting(so);
	SOCK_UNLOCK(so);
	tcpstat.tcps_connattempt++;
	tp->t_state = TCPS_SYN_SENT;
	callout_reset(tp->tt_keep, tcp_keepinit, tcp_timer_keep, tp);
	tp->iss = tcp_new_isn(tp);
	tcp_sendseqinit(tp);

	/*
	 * Generate a CC value for this connection and
	 * check whether CC or CCnew should be used.
	 */
	if ((taop = tcp_gettaocache(&tp->t_inpcb->inp_inc)) == NULL) {
		taop = &tao_noncached;
		bzero(taop, sizeof(*taop));
	}

	tp->cc_send = CC_INC(tcp_ccgen);
	if (taop->tao_ccsent != 0 &&
	    CC_GEQ(tp->cc_send, taop->tao_ccsent)) {
		taop->tao_ccsent = tp->cc_send;
	} else {
		taop->tao_ccsent = 0;
		tp->t_flags |= TF_SENDCCNEW;
	}

	return 0;
}
#endif /* INET6 */

/*
 * The new sockopt interface makes it possible for us to block in the
 * copyin/out step (if we take a page fault).  Taking a page fault at
 * splnet() is probably a Bad Thing.  (Since sockets and pcbs both now
 * use TSM, there probably isn't any need for this function to run at
 * splnet() any more.  This needs more examination.)
 */
int
tcp_ctloutput(so, sopt)
	struct socket *so;
	struct sockopt *sopt;
{
	int	error, opt, optval, s;
	struct	inpcb *inp;
	struct	tcpcb *tp;

	error = 0;
	s = splnet();		/* XXX */
	inp = sotoinpcb(so);
	if (inp == NULL) {
		splx(s);
		return (ECONNRESET);
	}
	if (sopt->sopt_level != IPPROTO_TCP) {
#ifdef INET6
		if (INP_CHECK_SOCKAF(so, AF_INET6))
			error = ip6_ctloutput(so, sopt);
		else
#endif /* INET6 */
		error = ip_ctloutput(so, sopt);
		splx(s);
		return (error);
	}
	tp = intotcpcb(inp);

	switch (sopt->sopt_dir) {
	case SOPT_SET:
		switch (sopt->sopt_name) {
		case TCP_NODELAY:
		case TCP_NOOPT:
			error = sooptcopyin(sopt, &optval, sizeof optval,
					    sizeof optval);
			if (error)
				break;

			switch (sopt->sopt_name) {
			case TCP_NODELAY:
				opt = TF_NODELAY;
				break;
			case TCP_NOOPT:
				opt = TF_NOOPT;
				break;
			default:
				opt = 0; /* dead code to fool gcc */
				break;
			}

			if (optval)
				tp->t_flags |= opt;
			else
				tp->t_flags &= ~opt;
			break;

		case TCP_NOPUSH:
			error = sooptcopyin(sopt, &optval, sizeof optval,
					    sizeof optval);
			if (error)
				break;

			if (optval)
				tp->t_flags |= TF_NOPUSH;
			else {
				tp->t_flags &= ~TF_NOPUSH;
				error = tcp_output(tp);
			}
			break;

		case TCP_MAXSEG:
			error = sooptcopyin(sopt, &optval, sizeof optval,
					    sizeof optval);
			if (error)
				break;

			if (optval > 0 && optval <= tp->t_maxseg)
				tp->t_maxseg = optval;
			else
				error = EINVAL;
			break;

		default:
			error = ENOPROTOOPT;
			break;
		}
		break;

	case SOPT_GET:
		switch (sopt->sopt_name) {
		case TCP_NODELAY:
			optval = tp->t_flags & TF_NODELAY;
			break;
		case TCP_MAXSEG:
			optval = tp->t_maxseg;
			break;
		case TCP_NOOPT:
			optval = tp->t_flags & TF_NOOPT;
			break;
		case TCP_NOPUSH:
			optval = tp->t_flags & TF_NOPUSH;
			break;
		default:
			error = ENOPROTOOPT;
			break;
		}
		if (error == 0)
			error = sooptcopyout(sopt, &optval, sizeof optval);
		break;
	}
	splx(s);
	return (error);
}

/*
 * tcp_sendspace and tcp_recvspace are the default send and receive window
 * sizes, respectively.  These are obsolescent (this information should
 * be set by the route).
 */
u_long	tcp_sendspace = 1024*32;
SYSCTL_INT(_net_inet_tcp, TCPCTL_SENDSPACE, sendspace, CTLFLAG_RW, 
    &tcp_sendspace , 0, "Maximum outgoing TCP datagram size");
u_long	tcp_recvspace = 1024*64;
SYSCTL_INT(_net_inet_tcp, TCPCTL_RECVSPACE, recvspace, CTLFLAG_RW, 
    &tcp_recvspace , 0, "Maximum incoming TCP datagram size");

/*
 * Attach TCP protocol to socket, allocating
 * internet protocol control block, tcp control block,
 * bufer space, and entering LISTEN state if to accept connections.
 */
static int
tcp_attach(so, td)
	struct socket *so;
	struct thread *td;
{
	register struct tcpcb *tp;
	struct inpcb *inp;
	int error;
#ifdef INET6
	int isipv6 = INP_CHECK_SOCKAF(so, AF_INET6) != NULL;
#endif

	if (so->so_snd.sb_hiwat == 0 || so->so_rcv.sb_hiwat == 0) {
		error = soreserve(so, tcp_sendspace, tcp_recvspace);
		if (error)
			return (error);
	}
	error = in_pcballoc(so, &tcbinfo, td);
	if (error)
		return (error);
	inp = sotoinpcb(so);
#ifdef INET6
	if (isipv6) {
		inp->inp_vflag |= INP_IPV6;
		inp->in6p_hops = -1;	/* use kernel default */
	}
	else
#endif
	inp->inp_vflag |= INP_IPV4;
	tp = tcp_newtcpcb(inp);
	if (tp == 0) {
		int nofd;

		SOCK_LOCK(so);
		nofd = so->so_state & SS_NOFDREF;	/* XXX */
		so->so_state &= ~SS_NOFDREF;	/* don't free the socket yet */
		SOCK_UNLOCK(so);
#ifdef INET6
		if (isipv6)
			in6_pcbdetach(inp);
		else
#endif
		in_pcbdetach(inp);
		SOCK_LOCK(so);
		so->so_state |= nofd;
		SOCK_UNLOCK(so);
		return (ENOBUFS);
	}
	tp->t_state = TCPS_CLOSED;
	return (0);
}

/*
 * Initiate (or continue) disconnect.
 * If embryonic state, just send reset (once).
 * If in ``let data drain'' option and linger null, just drop.
 * Otherwise (hard), mark socket disconnecting and drop
 * current input data; switch states based on user close, and
 * send segment to peer (with FIN).
 */
static struct tcpcb *
tcp_disconnect(tp)
	register struct tcpcb *tp;
{
	struct socket *so = tp->t_inpcb->inp_socket;

	if (tp->t_state < TCPS_ESTABLISHED)
		tp = tcp_close(tp);
	else {
		SOCK_LOCK(so);
		if ((so->so_options & SO_LINGER) && so->so_linger == 0) {
			SOCK_UNLOCK(so);
			tp = tcp_drop(tp, 0);
		} else {
			soisdisconnecting(so);
			SOCK_UNLOCK(so);
			sbflush(&so->so_rcv);
			tp = tcp_usrclosed(tp);
			if (tp)
				(void) tcp_output(tp);
		}
	}
	return (tp);
}

/*
 * User issued close, and wish to trail through shutdown states:
 * if never received SYN, just forget it.  If got a SYN from peer,
 * but haven't sent FIN, then go to FIN_WAIT_1 state to send peer a FIN.
 * If already got a FIN from peer, then almost done; go to LAST_ACK
 * state.  In all other cases, have already sent FIN to peer (e.g.
 * after PRU_SHUTDOWN), and just have to play tedious game waiting
 * for peer to send FIN or not respond to keep-alives, etc.
 * We can let the user exit from the close as soon as the FIN is acked.
 */
static struct tcpcb *
tcp_usrclosed(tp)
	register struct tcpcb *tp;
{

	switch (tp->t_state) {

	case TCPS_CLOSED:
	case TCPS_LISTEN:
		tp->t_state = TCPS_CLOSED;
		tp = tcp_close(tp);
		break;

	case TCPS_SYN_SENT:
	case TCPS_SYN_RECEIVED:
		tp->t_flags |= TF_NEEDFIN;
		break;

	case TCPS_ESTABLISHED:
		tp->t_state = TCPS_FIN_WAIT_1;
		break;

	case TCPS_CLOSE_WAIT:
		tp->t_state = TCPS_LAST_ACK;
		break;
	}
	if (tp && tp->t_state >= TCPS_FIN_WAIT_2) {
		SOCK_LOCK(tp->t_inpcb->inp_socket);
		soisdisconnected(tp->t_inpcb->inp_socket);
		SOCK_UNLOCK(tp->t_inpcb->inp_socket);
		/* To prevent the connection hanging in FIN_WAIT_2 forever. */
		if (tp->t_state == TCPS_FIN_WAIT_2)
			callout_reset(tp->tt_2msl, tcp_maxidle,
				      tcp_timer_2msl, tp);
	}
	return (tp);
}

OpenPOWER on IntegriCloud