-
-
Notifications
You must be signed in to change notification settings - Fork 602
/
tcp_usrreq.cc
2031 lines (1844 loc) · 49.4 KB
/
tcp_usrreq.cc
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*-
* Copyright (c) 1982, 1986, 1988, 1993
* The Regents of the University of California.
* Copyright (c) 2006-2007 Robert N. M. Watson
* Copyright (c) 2010-2011 Juniper Networks, Inc.
* All rights reserved.
*
* Portions of this software were developed by Robert N. M. Watson under
* contract to Juniper Networks, Inc.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 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
*/
#include <sys/cdefs.h>
#include <osv/initialize.hh>
#include <bsd/porting/netport.h>
#include <bsd/porting/sync_stub.h>
#include <bsd/sys/sys/libkern.h>
#include <bsd/sys/sys/param.h>
#include <bsd/sys/sys/limits.h>
#include <bsd/sys/sys/mbuf.h>
#ifdef INET6
#include <bsd/sys/sys/domain.h>
#endif /* INET6 */
#include <bsd/sys/sys/socket.h>
#include <bsd/sys/sys/socketvar.h>
#include <bsd/sys/sys/protosw.h>
#ifdef DDB
#include <ddb/ddb.h>
#endif
#include <bsd/sys/net/if.h>
#include <bsd/sys/net/route.h>
#include <bsd/sys/net/vnet.h>
#include <bsd/sys/netinet/cc.h>
#include <bsd/sys/netinet/in.h>
#include <bsd/sys/netinet/in_pcb.h>
#include <bsd/sys/netinet/in_systm.h>
#include <bsd/sys/netinet/in_var.h>
#include <bsd/sys/netinet/ip_var.h>
#ifdef INET6
#include <bsd/sys/netinet/ip6.h>
#include <bsd/sys/netinet6/in6_pcb.h>
#include <bsd/sys/netinet6/ip6_var.h>
#include <bsd/sys/netinet6/scope6_var.h>
#endif
#include <bsd/sys/netinet/tcp_fsm.h>
#include <bsd/sys/netinet/tcp_seq.h>
#include <bsd/sys/netinet/tcp_timer.h>
#include <bsd/sys/netinet/tcp_var.h>
#include <bsd/sys/netinet/tcpip.h>
#ifdef TCPDEBUG
#include <bsd/sys/netinet/tcp_debug.h>
#endif
#include <osv/poll.h>
/*
* TCP protocol interface to socket abstraction.
*/
static int tcp_attach(struct socket *);
#ifdef INET
static int tcp_connect(struct tcpcb *, struct bsd_sockaddr *,
struct thread *td);
#endif /* INET */
#ifdef INET6
static int tcp6_connect(struct tcpcb *, struct bsd_sockaddr *,
struct thread *td);
#endif /* INET6 */
static void tcp_disconnect(struct tcpcb *);
static void tcp_usrclosed(struct tcpcb *);
static void tcp_fill_info(struct tcpcb *, struct tcp_info *);
#ifdef TCPDEBUG
#define TCPDEBUG0 int ostate = 0
#define TCPDEBUG1() ostate = tp ? tp->get_state() : 0
#define TCPDEBUG2(req) if (tp && (so->so_options & SO_DEBUG)) \
tcp_trace(TA_USER, ostate, tp, 0, 0, req)
#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)
{
struct inpcb *inp;
struct tcpcb *tp = NULL;
int error;
TCPDEBUG0;
inp = sotoinpcb(so);
KASSERT(inp == NULL, ("tcp_usr_attach: inp != NULL"));
TCPDEBUG1();
error = tcp_attach(so);
if (error)
goto out;
if ((so->so_options & SO_LINGER) && so->so_linger == 0)
so->so_linger = TCP_LINGERTIME;
inp = sotoinpcb(so);
tp = intotcpcb(inp);
if (tp->nc) {
so->so_nc = tp->nc;
for (auto&& pl : so->fp->f_poll_list) {
so->so_nc->add_poller(*pl._req);
}
if (so->fp->f_epolls) {
for (auto&& ep : *so->fp->f_epolls) {
so->so_nc->add_epoll(ep);
}
}
}
out:
TCPDEBUG2(PRU_ATTACH);
return error;
}
/*
* tcp_detach is called when the socket layer loses its final reference
* to the socket, be it a file descriptor reference, a reference from TCP,
* etc. At this point, there is only one case in which we will keep around
* inpcb state: time wait.
*
* This function can probably be re-absorbed back into tcp_usr_detach() now
* that there is a single detach path.
*/
static void
tcp_detach(struct socket *so, struct inpcb *inp)
{
struct tcpcb *tp;
INP_INFO_WLOCK_ASSERT(&V_tcbinfo);
INP_LOCK_ASSERT(inp);
KASSERT(so->so_pcb == inp, ("tcp_detach: so_pcb != inp"));
KASSERT(inp->inp_socket == so, ("tcp_detach: inp_socket != so"));
tp = intotcpcb(inp);
if (inp->inp_flags & INP_TIMEWAIT) {
/*
* There are two cases to handle: one in which the time wait
* state is being discarded (INP_DROPPED), and one in which
* this connection will remain in timewait. In the former,
* it is time to discard all state (except tcptw, which has
* already been discarded by the timewait close code, which
* should be further up the call stack somewhere). In the
* latter case, we detach from the socket, but leave the pcb
* present until timewait ends.
*
* XXXRW: Would it be cleaner to free the tcptw here?
*/
if (inp->inp_flags & INP_DROPPED) {
KASSERT(tp == NULL, ("tcp_detach: INP_TIMEWAIT && "
"INP_DROPPED && tp != NULL"));
in_pcbdetach(inp);
in_pcbfree(inp);
} else {
in_pcbdetach(inp);
INP_UNLOCK(inp);
}
} else {
/*
* If the connection is not in timewait, we consider two
* two conditions: one in which no further processing is
* necessary (dropped || embryonic), and one in which TCP is
* not yet done, but no longer requires the socket, so the
* pcb will persist for the time being.
*
* XXXRW: Does the second case still occur?
*/
if (inp->inp_flags & INP_DROPPED ||
tp->get_state() < TCPS_SYN_SENT) {
tcp_discardcb(tp);
in_pcbdetach(inp);
in_pcbfree(inp);
} else {
in_pcbdetach(inp);
INP_UNLOCK(inp);
}
}
}
/*
* 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 void
tcp_usr_detach(struct socket *so)
{
struct inpcb *inp;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("tcp_usr_detach: inp == NULL"));
INP_INFO_WLOCK(&V_tcbinfo);
INP_LOCK(inp);
KASSERT(inp->inp_socket != NULL,
("tcp_usr_detach: inp_socket == NULL"));
tcp_detach(so, inp);
INP_INFO_WUNLOCK(&V_tcbinfo);
}
#ifdef INET
/*
* Give the socket an address.
*/
static int
tcp_usr_bind(struct socket *so, struct bsd_sockaddr *nam, struct thread *td)
{
int error = 0;
struct inpcb *inp;
struct tcpcb *tp = NULL;
struct bsd_sockaddr_in *sinp;
sinp = (struct bsd_sockaddr_in *)nam;
if (nam->sa_len != sizeof (*sinp))
return (EINVAL);
/*
* Must check for multicast addresses and disallow binding
* to them.
*/
if (sinp->sin_family == AF_INET &&
IN_MULTICAST(ntohl(sinp->sin_addr.s_addr)))
return (EAFNOSUPPORT);
TCPDEBUG0;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("tcp_usr_bind: inp == NULL"));
INP_LOCK(inp);
if (inp->inp_flags & (INP_TIMEWAIT | INP_DROPPED)) {
error = EINVAL;
goto out;
}
tp = intotcpcb(inp);
TCPDEBUG1();
INP_HASH_WLOCK(&V_tcbinfo);
error = in_pcbbind(inp, nam, 0);
INP_HASH_WUNLOCK(&V_tcbinfo);
out:
TCPDEBUG2(PRU_BIND);
INP_UNLOCK(inp);
return (error);
}
#endif /* INET */
#ifdef INET6
static int
tcp6_usr_bind(struct socket *so, struct bsd_sockaddr *nam, struct thread *td)
{
int error = 0;
struct inpcb *inp;
struct tcpcb *tp = NULL;
struct bsd_sockaddr_in6 *sin6p;
sin6p = (struct bsd_sockaddr_in6 *)nam;
if (nam->sa_len != sizeof (*sin6p))
return (EINVAL);
/*
* Must check for multicast addresses and disallow binding
* to them.
*/
if (sin6p->sin6_family == AF_INET6 &&
IN6_IS_ADDR_MULTICAST(&sin6p->sin6_addr))
return (EAFNOSUPPORT);
TCPDEBUG0;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("tcp6_usr_bind: inp == NULL"));
INP_LOCK(inp);
if (inp->inp_flags & (INP_TIMEWAIT | INP_DROPPED)) {
error = EINVAL;
goto out;
}
tp = intotcpcb(inp);
TCPDEBUG1();
INP_HASH_WLOCK(&V_tcbinfo);
inp->inp_vflag &= ~INP_IPV4;
inp->inp_vflag |= INP_IPV6;
#ifdef INET
if ((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 bsd_sockaddr_in sin;
in6_sin6_2_sin(&sin, sin6p);
inp->inp_vflag |= INP_IPV4;
inp->inp_vflag &= ~INP_IPV6;
error = in_pcbbind(inp, (struct bsd_sockaddr *)&sin,
td->td_ucred);
INP_HASH_WUNLOCK(&V_tcbinfo);
goto out;
}
}
#endif
error = in6_pcbbind(inp, nam, td->td_ucred);
INP_HASH_WUNLOCK(&V_tcbinfo);
out:
TCPDEBUG2(PRU_BIND);
INP_UNLOCK(inp);
return (error);
}
#endif /* INET6 */
#ifdef INET
/*
* Prepare to accept connections.
*/
static int
tcp_usr_listen(struct socket *so, int backlog, struct thread *td)
{
int error = 0;
struct inpcb *inp;
struct tcpcb *tp = NULL;
TCPDEBUG0;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("tcp_usr_listen: inp == NULL"));
INP_LOCK(inp);
if (inp->inp_flags & (INP_TIMEWAIT | INP_DROPPED)) {
error = EINVAL;
goto out;
}
tp = intotcpcb(inp);
TCPDEBUG1();
SOCK_LOCK(so);
error = solisten_proto_check(so);
INP_HASH_WLOCK(&V_tcbinfo);
if (error == 0 && inp->inp_lport == 0)
error = in_pcbbind(inp, (struct bsd_sockaddr *)0, 0);
INP_HASH_WUNLOCK(&V_tcbinfo);
if (error == 0) {
tp->set_state(TCPS_LISTEN);
solisten_proto(so, backlog);
}
SOCK_UNLOCK(so);
out:
TCPDEBUG2(PRU_LISTEN);
INP_UNLOCK(inp);
return (error);
}
#endif /* INET */
#ifdef INET6
static int
tcp6_usr_listen(struct socket *so, int backlog, struct thread *td)
{
int error = 0;
struct inpcb *inp;
struct tcpcb *tp = NULL;
TCPDEBUG0;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("tcp6_usr_listen: inp == NULL"));
INP_LOCK(inp);
if (inp->inp_flags & (INP_TIMEWAIT | INP_DROPPED)) {
error = EINVAL;
goto out;
}
tp = intotcpcb(inp);
TCPDEBUG1();
SOCK_LOCK(so);
error = solisten_proto_check(so);
INP_HASH_WLOCK(&V_tcbinfo);
if (error == 0 && inp->inp_lport == 0) {
inp->inp_vflag &= ~INP_IPV4;
if ((inp->inp_flags & IN6P_IPV6_V6ONLY) == 0)
inp->inp_vflag |= INP_IPV4;
error = in6_pcbbind(inp, (struct bsd_sockaddr *)0, td->td_ucred);
}
INP_HASH_WUNLOCK(&V_tcbinfo);
if (error == 0) {
tp->set_state(TCPS_LISTEN);
solisten_proto(so, backlog);
}
SOCK_UNLOCK(so);
out:
TCPDEBUG2(PRU_LISTEN);
INP_UNLOCK(inp);
return (error);
}
#endif /* INET6 */
#ifdef INET
/*
* 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 bsd_sockaddr *nam, struct thread *td)
{
int error = 0;
struct inpcb *inp;
struct tcpcb *tp = NULL;
struct bsd_sockaddr_in *sinp;
sinp = (struct bsd_sockaddr_in *)nam;
if (nam->sa_len != sizeof (*sinp))
return (EINVAL);
/*
* Must disallow TCP ``connections'' to multicast addresses.
*/
if (sinp->sin_family == AF_INET
&& IN_MULTICAST(ntohl(sinp->sin_addr.s_addr)))
return (EAFNOSUPPORT);
TCPDEBUG0;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("tcp_usr_connect: inp == NULL"));
INP_LOCK(inp);
if (inp->inp_flags & (INP_TIMEWAIT | INP_DROPPED)) {
error = EINVAL;
goto out;
}
tp = intotcpcb(inp);
TCPDEBUG1();
if ((error = tcp_connect(tp, nam, td)) != 0)
goto out;
error = tcp_output(tp);
out:
TCPDEBUG2(PRU_CONNECT);
INP_UNLOCK(inp);
return (error);
}
#endif /* INET */
#ifdef INET6
static int
tcp6_usr_connect(struct socket *so, struct bsd_sockaddr *nam, struct thread *td)
{
int error = 0;
struct inpcb *inp;
struct tcpcb *tp = NULL;
struct bsd_sockaddr_in6 *sin6p;
TCPDEBUG0;
sin6p = (struct bsd_sockaddr_in6 *)nam;
if (nam->sa_len != sizeof (*sin6p))
return (EINVAL);
/*
* Must disallow TCP ``connections'' to multicast addresses.
*/
if (sin6p->sin6_family == AF_INET6
&& IN6_IS_ADDR_MULTICAST(&sin6p->sin6_addr))
return (EAFNOSUPPORT);
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("tcp6_usr_connect: inp == NULL"));
INP_LOCK(inp);
if (inp->inp_flags & (INP_TIMEWAIT | INP_DROPPED)) {
error = EINVAL;
goto out;
}
tp = intotcpcb(inp);
TCPDEBUG1();
#ifdef INET
/*
* XXXRW: Some confusion: V4/V6 flags relate to binding, and
* therefore probably require the hash lock, which isn't held here.
* Is this a significant problem?
*/
if (IN6_IS_ADDR_V4MAPPED(&sin6p->sin6_addr)) {
struct bsd_sockaddr_in sin;
if ((inp->inp_flags & IN6P_IPV6_V6ONLY) != 0) {
error = EINVAL;
goto out;
}
in6_sin6_2_sin(&sin, sin6p);
inp->inp_vflag |= INP_IPV4;
inp->inp_vflag &= ~INP_IPV6;
if ((error = prison_remote_ip4(td->td_ucred,
&sin.sin_addr)) != 0)
goto out;
if ((error = tcp_connect(tp, (struct bsd_sockaddr *)&sin, td)) != 0)
goto out;
error = tcp_output_connect(so, nam);
goto out;
}
#endif
inp->inp_vflag &= ~INP_IPV4;
inp->inp_vflag |= INP_IPV6;
inp->inp_inc.inc_flags |= INC_ISIPV6;
if ((error = prison_remote_ip6(td->td_ucred, &sin6p->sin6_addr)) != 0)
goto out;
if ((error = tcp6_connect(tp, nam, td)) != 0)
goto out;
error = tcp_output_connect(so, nam);
out:
TCPDEBUG2(PRU_CONNECT);
INP_UNLOCK(inp);
return (error);
}
#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)
{
struct inpcb *inp;
struct tcpcb *tp = NULL;
int error = 0;
TCPDEBUG0;
INP_INFO_WLOCK(&V_tcbinfo);
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("tcp_usr_disconnect: inp == NULL"));
INP_LOCK(inp);
if (inp->inp_flags & (INP_TIMEWAIT | INP_DROPPED)) {
error = ECONNRESET;
goto out;
}
tp = intotcpcb(inp);
TCPDEBUG1();
tcp_disconnect(tp);
out:
TCPDEBUG2(PRU_DISCONNECT);
INP_UNLOCK(inp);
INP_INFO_WUNLOCK(&V_tcbinfo);
return (error);
}
#ifdef INET
/*
* 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 bsd_sockaddr **nam)
{
int error = 0;
struct inpcb *inp = NULL;
struct tcpcb *tp = NULL;
struct in_addr addr;
in_port_t port = 0;
TCPDEBUG0;
if (so->so_state & SS_ISDISCONNECTED)
return (ECONNABORTED);
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("tcp_usr_accept: inp == NULL"));
INP_LOCK(inp);
if (inp->inp_flags & (INP_TIMEWAIT | INP_DROPPED)) {
error = ECONNABORTED;
goto out;
}
tp = intotcpcb(inp);
TCPDEBUG1();
/*
* We inline in_getpeeraddr and COMMON_END here, so that we can
* copy the data of interest and defer the malloc until after we
* release the lock.
*/
port = inp->inp_fport;
addr = inp->inp_faddr;
out:
TCPDEBUG2(PRU_ACCEPT);
INP_UNLOCK(inp);
if (error == 0)
*nam = in_sockaddr(port, &addr);
return error;
}
#endif /* INET */
#ifdef INET6
static int
tcp6_usr_accept(struct socket *so, struct bsd_sockaddr **nam)
{
struct inpcb *inp = NULL;
int error = 0;
struct tcpcb *tp = NULL;
struct in_addr addr;
struct in6_addr addr6;
in_port_t port = 0;
int v4 = 0;
TCPDEBUG0;
if (so->so_state & SS_ISDISCONNECTED)
return (ECONNABORTED);
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("tcp6_usr_accept: inp == NULL"));
INP_INFO_RLOCK(&V_tcbinfo);
INP_LOCK(inp);
if (inp->inp_flags & (INP_TIMEWAIT | INP_DROPPED)) {
error = ECONNABORTED;
goto out;
}
tp = intotcpcb(inp);
TCPDEBUG1();
/*
* We inline in6_mapped_peeraddr and COMMON_END here, so that we can
* copy the data of interest and defer the malloc until after we
* release the lock.
*/
if (inp->inp_vflag & INP_IPV4) {
v4 = 1;
port = inp->inp_fport;
addr = inp->inp_faddr;
} else {
port = inp->inp_fport;
addr6 = inp->in6p_faddr;
}
out:
TCPDEBUG2(PRU_ACCEPT);
INP_UNLOCK(inp);
INP_INFO_RUNLOCK(&V_tcbinfo);
if (error == 0) {
if (v4)
*nam = in6_v4mapsin6_sockaddr(port, &addr);
else
*nam = in6_sockaddr(port, &addr6);
}
return error;
}
#endif /* INET6 */
/*
* Mark the connection as being incapable of further output.
*/
static int
tcp_usr_shutdown(struct socket *so)
{
int error = 0;
struct inpcb *inp;
struct tcpcb *tp = NULL;
TCPDEBUG0;
INP_INFO_WLOCK(&V_tcbinfo);
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("inp == NULL"));
INP_LOCK(inp);
if (inp->inp_flags & (INP_TIMEWAIT | INP_DROPPED)) {
error = ECONNRESET;
goto out;
}
tp = intotcpcb(inp);
TCPDEBUG1();
socantsendmore_locked(so);
tcp_usrclosed(tp);
if (!(inp->inp_flags & INP_DROPPED))
error = tcp_output(tp);
out:
TCPDEBUG2(PRU_SHUTDOWN);
INP_UNLOCK(inp);
INP_INFO_WUNLOCK(&V_tcbinfo);
return (error);
}
/*
* After a receive, possibly send window update to peer.
*/
static int
tcp_usr_rcvd(struct socket *so, int flags)
{
struct inpcb *inp;
struct tcpcb *tp = NULL;
int error = 0;
TCPDEBUG0;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("tcp_usr_rcvd: inp == NULL"));
INP_LOCK(inp);
if (inp->inp_flags & (INP_TIMEWAIT | INP_DROPPED)) {
error = ECONNRESET;
goto out;
}
tp = intotcpcb(inp);
TCPDEBUG1();
tcp_output(tp);
out:
TCPDEBUG2(PRU_RCVD);
INP_UNLOCK(inp);
return (error);
}
/*
* 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 bsd_sockaddr *nam, struct mbuf *control, struct thread *td)
{
int error = 0;
struct inpcb *inp;
struct tcpcb *tp = NULL;
#ifdef INET6
int isipv6;
#endif
TCPDEBUG0;
/*
* We require the pcbinfo lock if we will close the socket as part of
* this call.
*/
if (flags & PRUS_EOF)
INP_INFO_WLOCK(&V_tcbinfo);
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("tcp_usr_send: inp == NULL"));
INP_LOCK(inp);
if (inp->inp_flags & (INP_TIMEWAIT | INP_DROPPED)) {
if (control)
m_freem(control);
if (m)
m_freem(m);
error = ECONNRESET;
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_hdr.mh_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)) {
sbappendstream(so, &so->so_snd, m);
if (nam && tp->get_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);
#endif /* INET6 */
#if defined(INET6) && defined(INET)
else
#endif
#ifdef INET
error = tcp_connect(tp, nam, td);
#endif
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.
*/
INP_INFO_WLOCK_ASSERT(&V_tcbinfo);
socantsendmore_locked(so);
tcp_usrclosed(tp);
}
if (!(inp->inp_flags & INP_DROPPED)) {
if (flags & PRUS_MORETOCOME)
tp->t_flags |= TF_MORETOCOME;
error = tcp_output(tp);
if (flags & PRUS_MORETOCOME)
tp->t_flags &= ~TF_MORETOCOME;
}
} else {
/*
* XXXRW: PRUS_EOF not implemented with PRUS_OOB?
*/
if (sbspace(&so->so_snd) < -512) {
SOCK_UNLOCK(so);
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.
*/
sbappendstream_locked(so, &so->so_snd, m);
if (nam && tp->get_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);
#endif /* INET6 */
#if defined(INET6) && defined(INET)
else
#endif
#ifdef INET
error = tcp_connect(tp, nam, td);
#endif
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_flags |= TF_FORCEDATA;
error = tcp_output(tp);
tp->t_flags &= ~TF_FORCEDATA;
}
out:
TCPDEBUG2((flags & PRUS_OOB) ? PRU_SENDOOB :
((flags & PRUS_EOF) ? PRU_SEND_EOF : PRU_SEND));
INP_UNLOCK(inp);
if (flags & PRUS_EOF)
INP_INFO_WUNLOCK(&V_tcbinfo);
return (error);
}
/*
* Abort the TCP. Drop the connection abruptly.
*/
static void
tcp_usr_abort(struct socket *so)
{
struct inpcb *inp;
struct tcpcb *tp = NULL;
TCPDEBUG0;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("tcp_usr_abort: inp == NULL"));
INP_INFO_WLOCK(&V_tcbinfo);
INP_LOCK(inp);
KASSERT(inp->inp_socket != NULL,
("tcp_usr_abort: inp_socket == NULL"));
/*
* If we still have full TCP state, and we're not dropped, drop.
*/
if (!(inp->inp_flags & INP_TIMEWAIT) &&
!(inp->inp_flags & INP_DROPPED)) {
tp = intotcpcb(inp);
TCPDEBUG1();
tcp_drop(tp, ECONNABORTED);
TCPDEBUG2(PRU_ABORT);
}
if (!(inp->inp_flags & INP_DROPPED)) {
so->so_state |= SS_PROTOREF;
inp->inp_flags |= INP_SOCKREF;
}
INP_UNLOCK(inp);
INP_INFO_WUNLOCK(&V_tcbinfo);
}
/*
* TCP socket is closed. Start friendly disconnect.
*/
static void
tcp_usr_close(struct socket *so)
{
struct inpcb *inp;
struct tcpcb *tp = NULL;
TCPDEBUG0;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("tcp_usr_close: inp == NULL"));
INP_INFO_WLOCK(&V_tcbinfo);
INP_LOCK(inp);
KASSERT(inp->inp_socket != NULL,
("tcp_usr_close: inp_socket == NULL"));
/*
* If we still have full TCP state, and we're not dropped, initiate
* a disconnect.
*/
if (!(inp->inp_flags & INP_TIMEWAIT) &&
!(inp->inp_flags & INP_DROPPED)) {
tp = intotcpcb(inp);
tcp_teardown_net_channel(tp);
TCPDEBUG1();
tcp_disconnect(tp);
TCPDEBUG2(PRU_CLOSE);
}
if (!(inp->inp_flags & INP_DROPPED)) {
SOCK_LOCK(so);
so->so_state |= SS_PROTOREF;
SOCK_UNLOCK(so);
inp->inp_flags |= INP_SOCKREF;
}
INP_UNLOCK(inp);
INP_INFO_WUNLOCK(&V_tcbinfo);
}
/*
* Receive out-of-band data.
*/
static int
tcp_usr_rcvoob(struct socket *so, struct mbuf *m, int flags)
{
int error = 0;
struct inpcb *inp;
struct tcpcb *tp = NULL;
TCPDEBUG0;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("tcp_usr_rcvoob: inp == NULL"));
INP_LOCK(inp);
if (inp->inp_flags & (INP_TIMEWAIT | INP_DROPPED)) {
error = ECONNRESET;
goto out;
}
tp = intotcpcb(inp);
TCPDEBUG1();
if ((so->so_oobmark == 0 &&
(so->so_rcv.sb_state & SBS_RCVATMARK) == 0) ||
so->so_options & SO_OOBINLINE ||
tp->t_oobflags & TCPOOB_HADDATA) {
error = EINVAL;
goto out;
}
if ((tp->t_oobflags & TCPOOB_HAVEDATA) == 0) {
error = EWOULDBLOCK;
goto out;
}
m->m_hdr.mh_len = 1;
*mtod(m, caddr_t) = tp->t_iobc;
if ((flags & MSG_PEEK) == 0)