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
|
/* $OpenBSD: uipc_socket.c,v 1.78 2009/08/10 16:49:38 thib Exp $ */
/* $NetBSD: uipc_socket.c,v 1.21 1996/02/04 02:17:52 christos Exp $ */
/*
* Copyright (c) 1982, 1986, 1988, 1990, 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. 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.
*
* @(#)uipc_socket.c 8.3 (Berkeley) 4/15/94
*/
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/proc.h>
#include <sys/file.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/domain.h>
#include <sys/kernel.h>
#include <sys/event.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/signalvar.h>
#include <sys/resourcevar.h>
#include <net/route.h>
#include <sys/pool.h>
void filt_sordetach(struct knote *kn);
int filt_soread(struct knote *kn, long hint);
void filt_sowdetach(struct knote *kn);
int filt_sowrite(struct knote *kn, long hint);
int filt_solisten(struct knote *kn, long hint);
struct filterops solisten_filtops =
{ 1, NULL, filt_sordetach, filt_solisten };
struct filterops soread_filtops =
{ 1, NULL, filt_sordetach, filt_soread };
struct filterops sowrite_filtops =
{ 1, NULL, filt_sowdetach, filt_sowrite };
#ifndef SOMINCONN
#define SOMINCONN 80
#endif /* SOMINCONN */
int somaxconn = SOMAXCONN;
int sominconn = SOMINCONN;
struct pool socket_pool;
void
soinit(void)
{
pool_init(&socket_pool, sizeof(struct socket), 0, 0, 0, "sockpl", NULL);
}
/*
* Socket operation routines.
* These routines are called by the routines in
* sys_socket.c or from a system process, and
* implement the semantics of socket operations by
* switching out to the protocol specific routines.
*/
/*ARGSUSED*/
int
socreate(int dom, struct socket **aso, int type, int proto)
{
struct proc *p = curproc; /* XXX */
struct protosw *prp;
struct socket *so;
int error, s;
if (proto)
prp = pffindproto(dom, proto, type);
else
prp = pffindtype(dom, type);
if (prp == NULL || prp->pr_usrreq == 0)
return (EPROTONOSUPPORT);
if (prp->pr_type != type)
return (EPROTOTYPE);
s = splsoftnet();
so = pool_get(&socket_pool, PR_WAITOK | PR_ZERO);
TAILQ_INIT(&so->so_q0);
TAILQ_INIT(&so->so_q);
so->so_type = type;
if (p->p_ucred->cr_uid == 0)
so->so_state = SS_PRIV;
so->so_ruid = p->p_cred->p_ruid;
so->so_euid = p->p_ucred->cr_uid;
so->so_rgid = p->p_cred->p_rgid;
so->so_egid = p->p_ucred->cr_gid;
so->so_cpid = p->p_pid;
so->so_proto = prp;
error = (*prp->pr_usrreq)(so, PRU_ATTACH, NULL,
(struct mbuf *)(long)proto, NULL, p);
if (error) {
so->so_state |= SS_NOFDREF;
sofree(so);
splx(s);
return (error);
}
#ifdef COMPAT_SUNOS
{
extern struct emul emul_sunos;
if (p->p_emul == &emul_sunos && type == SOCK_DGRAM)
so->so_options |= SO_BROADCAST;
}
#endif
splx(s);
*aso = so;
return (0);
}
int
sobind(struct socket *so, struct mbuf *nam, struct proc *p)
{
int s = splsoftnet();
int error;
error = (*so->so_proto->pr_usrreq)(so, PRU_BIND, NULL, nam, NULL, p);
splx(s);
return (error);
}
int
solisten(struct socket *so, int backlog)
{
int s = splsoftnet(), error;
error = (*so->so_proto->pr_usrreq)(so, PRU_LISTEN, NULL, NULL, NULL,
curproc);
if (error) {
splx(s);
return (error);
}
if (TAILQ_FIRST(&so->so_q) == NULL)
so->so_options |= SO_ACCEPTCONN;
if (backlog < 0 || backlog > somaxconn)
backlog = somaxconn;
if (backlog < sominconn)
backlog = sominconn;
so->so_qlimit = backlog;
splx(s);
return (0);
}
/*
* Must be called at splsoftnet()
*/
void
sofree(struct socket *so)
{
splsoftassert(IPL_SOFTNET);
if (so->so_pcb || (so->so_state & SS_NOFDREF) == 0)
return;
if (so->so_head) {
/*
* We must not decommission a socket that's on the accept(2)
* queue. If we do, then accept(2) may hang after select(2)
* indicated that the listening socket was ready.
*/
if (!soqremque(so, 0))
return;
}
sbrelease(&so->so_snd);
sorflush(so);
pool_put(&socket_pool, so);
}
/*
* Close a socket on last file table reference removal.
* Initiate disconnect if connected.
* Free socket when disconnect complete.
*/
int
soclose(struct socket *so)
{
struct socket *so2;
int s = splsoftnet(); /* conservative */
int error = 0;
if (so->so_options & SO_ACCEPTCONN) {
while ((so2 = TAILQ_FIRST(&so->so_q0)) != NULL) {
(void) soqremque(so2, 0);
(void) soabort(so2);
}
while ((so2 = TAILQ_FIRST(&so->so_q)) != NULL) {
(void) soqremque(so2, 1);
(void) soabort(so2);
}
}
if (so->so_pcb == 0)
goto discard;
if (so->so_state & SS_ISCONNECTED) {
if ((so->so_state & SS_ISDISCONNECTING) == 0) {
error = sodisconnect(so);
if (error)
goto drop;
}
if (so->so_options & SO_LINGER) {
if ((so->so_state & SS_ISDISCONNECTING) &&
(so->so_state & SS_NBIO))
goto drop;
while (so->so_state & SS_ISCONNECTED) {
error = tsleep(&so->so_timeo,
PSOCK | PCATCH, "netcls",
so->so_linger * hz);
if (error)
break;
}
}
}
drop:
if (so->so_pcb) {
int error2 = (*so->so_proto->pr_usrreq)(so, PRU_DETACH, NULL,
NULL, NULL, curproc);
if (error == 0)
error = error2;
}
discard:
if (so->so_state & SS_NOFDREF)
panic("soclose: NOFDREF");
so->so_state |= SS_NOFDREF;
sofree(so);
splx(s);
return (error);
}
/*
* Must be called at splsoftnet.
*/
int
soabort(struct socket *so)
{
splsoftassert(IPL_SOFTNET);
return (*so->so_proto->pr_usrreq)(so, PRU_ABORT, NULL, NULL, NULL,
curproc);
}
int
soaccept(struct socket *so, struct mbuf *nam)
{
int s = splsoftnet();
int error = 0;
if ((so->so_state & SS_NOFDREF) == 0)
panic("soaccept: !NOFDREF");
so->so_state &= ~SS_NOFDREF;
if ((so->so_state & SS_ISDISCONNECTED) == 0 ||
(so->so_proto->pr_flags & PR_ABRTACPTDIS) == 0)
error = (*so->so_proto->pr_usrreq)(so, PRU_ACCEPT, NULL,
nam, NULL, curproc);
else
error = ECONNABORTED;
splx(s);
return (error);
}
int
soconnect(struct socket *so, struct mbuf *nam)
{
int s;
int error;
if (so->so_options & SO_ACCEPTCONN)
return (EOPNOTSUPP);
s = splsoftnet();
/*
* If protocol is connection-based, can only connect once.
* Otherwise, if connected, try to disconnect first.
* This allows user to disconnect by connecting to, e.g.,
* a null address.
*/
if (so->so_state & (SS_ISCONNECTED|SS_ISCONNECTING) &&
((so->so_proto->pr_flags & PR_CONNREQUIRED) ||
(error = sodisconnect(so))))
error = EISCONN;
else
error = (*so->so_proto->pr_usrreq)(so, PRU_CONNECT,
NULL, nam, NULL, curproc);
splx(s);
return (error);
}
int
soconnect2(struct socket *so1, struct socket *so2)
{
int s = splsoftnet();
int error;
error = (*so1->so_proto->pr_usrreq)(so1, PRU_CONNECT2, NULL,
(struct mbuf *)so2, NULL, curproc);
splx(s);
return (error);
}
int
sodisconnect(struct socket *so)
{
int s = splsoftnet();
int error;
if ((so->so_state & SS_ISCONNECTED) == 0) {
error = ENOTCONN;
goto bad;
}
if (so->so_state & SS_ISDISCONNECTING) {
error = EALREADY;
goto bad;
}
error = (*so->so_proto->pr_usrreq)(so, PRU_DISCONNECT, NULL, NULL,
NULL, curproc);
bad:
splx(s);
return (error);
}
#define SBLOCKWAIT(f) (((f) & MSG_DONTWAIT) ? M_NOWAIT : M_WAITOK)
/*
* Send on a socket.
* If send must go all at once and message is larger than
* send buffering, then hard error.
* Lock against other senders.
* If must go all at once and not enough room now, then
* inform user that this would block and do nothing.
* Otherwise, if nonblocking, send as much as possible.
* The data to be sent is described by "uio" if nonzero,
* otherwise by the mbuf chain "top" (which must be null
* if uio is not). Data provided in mbuf chain must be small
* enough to send all at once.
*
* Returns nonzero on error, timeout or signal; callers
* must check for short counts if EINTR/ERESTART are returned.
* Data and control buffers are freed on return.
*/
int
sosend(struct socket *so, struct mbuf *addr, struct uio *uio, struct mbuf *top,
struct mbuf *control, int flags)
{
struct mbuf **mp;
struct mbuf *m;
long space, len, mlen, clen = 0;
quad_t resid;
int error, s, dontroute;
int atomic = sosendallatonce(so) || top;
if (uio)
resid = uio->uio_resid;
else
resid = top->m_pkthdr.len;
/*
* In theory resid should be unsigned (since uio->uio_resid is).
* However, space must be signed, as it might be less than 0
* if we over-committed, and we must use a signed comparison
* of space and resid. On the other hand, a negative resid
* causes us to loop sending 0-length segments to the protocol.
* MSG_EOR on a SOCK_STREAM socket is also invalid.
*/
if (resid < 0 ||
(so->so_type == SOCK_STREAM && (flags & MSG_EOR))) {
error = EINVAL;
goto out;
}
dontroute =
(flags & MSG_DONTROUTE) && (so->so_options & SO_DONTROUTE) == 0 &&
(so->so_proto->pr_flags & PR_ATOMIC);
if (uio && uio->uio_procp)
uio->uio_procp->p_stats->p_ru.ru_msgsnd++;
if (control)
clen = control->m_len;
#define snderr(errno) { error = errno; splx(s); goto release; }
restart:
if ((error = sblock(&so->so_snd, SBLOCKWAIT(flags))) != 0)
goto out;
so->so_state |= SS_ISSENDING;
do {
s = splsoftnet();
if (so->so_state & SS_CANTSENDMORE)
snderr(EPIPE);
if (so->so_error) {
error = so->so_error;
so->so_error = 0;
splx(s);
goto release;
}
if ((so->so_state & SS_ISCONNECTED) == 0) {
if (so->so_proto->pr_flags & PR_CONNREQUIRED) {
if ((so->so_state & SS_ISCONFIRMING) == 0 &&
!(resid == 0 && clen != 0))
snderr(ENOTCONN);
} else if (addr == 0)
snderr(EDESTADDRREQ);
}
space = sbspace(&so->so_snd);
if (flags & MSG_OOB)
space += 1024;
if ((atomic && resid > so->so_snd.sb_hiwat) ||
clen > so->so_snd.sb_hiwat)
snderr(EMSGSIZE);
if (space < resid + clen &&
(atomic || space < so->so_snd.sb_lowat || space < clen)) {
if (so->so_state & SS_NBIO)
snderr(EWOULDBLOCK);
sbunlock(&so->so_snd);
error = sbwait(&so->so_snd);
so->so_state &= ~SS_ISSENDING;
splx(s);
if (error)
goto out;
goto restart;
}
splx(s);
mp = ⊤
space -= clen;
do {
if (uio == NULL) {
/*
* Data is prepackaged in "top".
*/
resid = 0;
if (flags & MSG_EOR)
top->m_flags |= M_EOR;
} else do {
if (top == 0) {
MGETHDR(m, M_WAIT, MT_DATA);
mlen = MHLEN;
m->m_pkthdr.len = 0;
m->m_pkthdr.rcvif = (struct ifnet *)0;
} else {
MGET(m, M_WAIT, MT_DATA);
mlen = MLEN;
}
if (resid >= MINCLSIZE && space >= MCLBYTES) {
MCLGET(m, M_NOWAIT);
if ((m->m_flags & M_EXT) == 0)
goto nopages;
mlen = MCLBYTES;
if (atomic && top == 0) {
len = lmin(MCLBYTES - max_hdr, resid);
m->m_data += max_hdr;
} else
len = lmin(MCLBYTES, resid);
space -= len;
} else {
nopages:
len = lmin(lmin(mlen, resid), space);
space -= len;
/*
* For datagram protocols, leave room
* for protocol headers in first mbuf.
*/
if (atomic && top == 0 && len < mlen)
MH_ALIGN(m, len);
}
error = uiomove(mtod(m, caddr_t), (int)len,
uio);
resid = uio->uio_resid;
m->m_len = len;
*mp = m;
top->m_pkthdr.len += len;
if (error)
goto release;
mp = &m->m_next;
if (resid <= 0) {
if (flags & MSG_EOR)
top->m_flags |= M_EOR;
break;
}
} while (space > 0 && atomic);
if (dontroute)
so->so_options |= SO_DONTROUTE;
s = splsoftnet(); /* XXX */
if (resid <= 0)
so->so_state &= ~SS_ISSENDING;
error = (*so->so_proto->pr_usrreq)(so,
(flags & MSG_OOB) ? PRU_SENDOOB : PRU_SEND,
top, addr, control, curproc);
splx(s);
if (dontroute)
so->so_options &= ~SO_DONTROUTE;
clen = 0;
control = 0;
top = 0;
mp = ⊤
if (error)
goto release;
} while (resid && space > 0);
} while (resid);
release:
so->so_state &= ~SS_ISSENDING;
sbunlock(&so->so_snd);
out:
if (top)
m_freem(top);
if (control)
m_freem(control);
return (error);
}
/*
* Implement receive operations on a socket.
* We depend on the way that records are added to the sockbuf
* by sbappend*. In particular, each record (mbufs linked through m_next)
* must begin with an address if the protocol so specifies,
* followed by an optional mbuf or mbufs containing ancillary data,
* and then zero or more mbufs of data.
* In order to avoid blocking network interrupts for the entire time here,
* we splx() while doing the actual copy to user space.
* Although the sockbuf is locked, new data may still be appended,
* and thus we must maintain consistency of the sockbuf during that time.
*
* The caller may receive the data as a single mbuf chain by supplying
* an mbuf **mp0 for use in returning the chain. The uio is then used
* only for the count in uio_resid.
*/
int
soreceive(struct socket *so, struct mbuf **paddr, struct uio *uio,
struct mbuf **mp0, struct mbuf **controlp, int *flagsp,
socklen_t controllen)
{
struct mbuf *m, **mp;
int flags, len, error, s, offset;
struct protosw *pr = so->so_proto;
struct mbuf *nextrecord;
int moff, type = 0;
size_t orig_resid = uio->uio_resid;
int uio_error = 0;
int resid;
mp = mp0;
if (paddr)
*paddr = 0;
if (controlp)
*controlp = 0;
if (flagsp)
flags = *flagsp &~ MSG_EOR;
else
flags = 0;
if (so->so_state & SS_NBIO)
flags |= MSG_DONTWAIT;
if (flags & MSG_OOB) {
m = m_get(M_WAIT, MT_DATA);
error = (*pr->pr_usrreq)(so, PRU_RCVOOB, m,
(struct mbuf *)(long)(flags & MSG_PEEK), NULL, curproc);
if (error)
goto bad;
do {
error = uiomove(mtod(m, caddr_t),
(int) min(uio->uio_resid, m->m_len), uio);
m = m_free(m);
} while (uio->uio_resid && error == 0 && m);
bad:
if (m)
m_freem(m);
return (error);
}
if (mp)
*mp = NULL;
if (so->so_state & SS_ISCONFIRMING && uio->uio_resid)
(*pr->pr_usrreq)(so, PRU_RCVD, NULL, NULL, NULL, curproc);
restart:
if ((error = sblock(&so->so_rcv, SBLOCKWAIT(flags))) != 0)
return (error);
s = splsoftnet();
m = so->so_rcv.sb_mb;
/*
* If we have less data than requested, block awaiting more
* (subject to any timeout) if:
* 1. the current count is less than the low water mark,
* 2. MSG_WAITALL is set, and it is possible to do the entire
* receive operation at once if we block (resid <= hiwat), or
* 3. MSG_DONTWAIT is not set.
* If MSG_WAITALL is set but resid is larger than the receive buffer,
* we have to do the receive in sections, and thus risk returning
* a short count if a timeout or signal occurs after we start.
*/
if (m == NULL || (((flags & MSG_DONTWAIT) == 0 &&
so->so_rcv.sb_cc < uio->uio_resid) &&
(so->so_rcv.sb_cc < so->so_rcv.sb_lowat ||
((flags & MSG_WAITALL) && uio->uio_resid <= so->so_rcv.sb_hiwat)) &&
m->m_nextpkt == NULL && (pr->pr_flags & PR_ATOMIC) == 0)) {
#ifdef DIAGNOSTIC
if (m == NULL && so->so_rcv.sb_cc)
panic("receive 1");
#endif
if (so->so_error) {
if (m)
goto dontblock;
error = so->so_error;
if ((flags & MSG_PEEK) == 0)
so->so_error = 0;
goto release;
}
if (so->so_state & SS_CANTRCVMORE) {
if (m)
goto dontblock;
else
goto release;
}
for (; m; m = m->m_next)
if (m->m_type == MT_OOBDATA || (m->m_flags & M_EOR)) {
m = so->so_rcv.sb_mb;
goto dontblock;
}
if ((so->so_state & (SS_ISCONNECTED|SS_ISCONNECTING)) == 0 &&
(so->so_proto->pr_flags & PR_CONNREQUIRED)) {
error = ENOTCONN;
goto release;
}
if (uio->uio_resid == 0 && controlp == NULL)
goto release;
if ((so->so_state & SS_NBIO) || (flags & MSG_DONTWAIT)) {
error = EWOULDBLOCK;
goto release;
}
SBLASTRECORDCHK(&so->so_rcv, "soreceive sbwait 1");
SBLASTMBUFCHK(&so->so_rcv, "soreceive sbwait 1");
sbunlock(&so->so_rcv);
error = sbwait(&so->so_rcv);
splx(s);
if (error)
return (error);
goto restart;
}
dontblock:
/*
* On entry here, m points to the first record of the socket buffer.
* While we process the initial mbufs containing address and control
* info, we save a copy of m->m_nextpkt into nextrecord.
*/
if (uio->uio_procp)
uio->uio_procp->p_stats->p_ru.ru_msgrcv++;
KASSERT(m == so->so_rcv.sb_mb);
SBLASTRECORDCHK(&so->so_rcv, "soreceive 1");
SBLASTMBUFCHK(&so->so_rcv, "soreceive 1");
nextrecord = m->m_nextpkt;
if (pr->pr_flags & PR_ADDR) {
#ifdef DIAGNOSTIC
if (m->m_type != MT_SONAME)
panic("receive 1a");
#endif
orig_resid = 0;
if (flags & MSG_PEEK) {
if (paddr)
*paddr = m_copy(m, 0, m->m_len);
m = m->m_next;
} else {
sbfree(&so->so_rcv, m);
if (paddr) {
*paddr = m;
so->so_rcv.sb_mb = m->m_next;
m->m_next = 0;
m = so->so_rcv.sb_mb;
} else {
MFREE(m, so->so_rcv.sb_mb);
m = so->so_rcv.sb_mb;
}
}
}
while (m && m->m_type == MT_CONTROL && error == 0) {
if (flags & MSG_PEEK) {
if (controlp)
*controlp = m_copy(m, 0, m->m_len);
m = m->m_next;
} else {
sbfree(&so->so_rcv, m);
if (controlp) {
if (pr->pr_domain->dom_externalize &&
mtod(m, struct cmsghdr *)->cmsg_type ==
SCM_RIGHTS)
error = (*pr->pr_domain->dom_externalize)(m,
controllen);
*controlp = m;
so->so_rcv.sb_mb = m->m_next;
m->m_next = 0;
m = so->so_rcv.sb_mb;
} else {
/*
* Dispose of any SCM_RIGHTS message that went
* through the read path rather than recv.
*/
if (pr->pr_domain->dom_dispose &&
mtod(m, struct cmsghdr *)->cmsg_type == SCM_RIGHTS)
pr->pr_domain->dom_dispose(m);
MFREE(m, so->so_rcv.sb_mb);
m = so->so_rcv.sb_mb;
}
}
if (controlp) {
orig_resid = 0;
controlp = &(*controlp)->m_next;
}
}
/*
* If m is non-NULL, we have some data to read. From now on,
* make sure to keep sb_lastrecord consistent when working on
* the last packet on the chain (nextrecord == NULL) and we
* change m->m_nextpkt.
*/
if (m) {
if ((flags & MSG_PEEK) == 0) {
m->m_nextpkt = nextrecord;
/*
* If nextrecord == NULL (this is a single chain),
* then sb_lastrecord may not be valid here if m
* was changed earlier.
*/
if (nextrecord == NULL) {
KASSERT(so->so_rcv.sb_mb == m);
so->so_rcv.sb_lastrecord = m;
}
}
type = m->m_type;
if (type == MT_OOBDATA)
flags |= MSG_OOB;
if (m->m_flags & M_BCAST)
flags |= MSG_BCAST;
if (m->m_flags & M_MCAST)
flags |= MSG_MCAST;
} else {
if ((flags & MSG_PEEK) == 0) {
KASSERT(so->so_rcv.sb_mb == m);
so->so_rcv.sb_mb = nextrecord;
SB_EMPTY_FIXUP(&so->so_rcv);
}
}
SBLASTRECORDCHK(&so->so_rcv, "soreceive 2");
SBLASTMBUFCHK(&so->so_rcv, "soreceive 2");
moff = 0;
offset = 0;
while (m && uio->uio_resid > 0 && error == 0) {
if (m->m_type == MT_OOBDATA) {
if (type != MT_OOBDATA)
break;
} else if (type == MT_OOBDATA)
break;
#ifdef DIAGNOSTIC
else if (m->m_type != MT_DATA && m->m_type != MT_HEADER)
panic("receive 3");
#endif
so->so_state &= ~SS_RCVATMARK;
len = uio->uio_resid;
if (so->so_oobmark && len > so->so_oobmark - offset)
len = so->so_oobmark - offset;
if (len > m->m_len - moff)
len = m->m_len - moff;
/*
* If mp is set, just pass back the mbufs.
* Otherwise copy them out via the uio, then free.
* Sockbuf must be consistent here (points to current mbuf,
* it points to next record) when we drop priority;
* we must note any additions to the sockbuf when we
* block interrupts again.
*/
if (mp == NULL && uio_error == 0) {
SBLASTRECORDCHK(&so->so_rcv, "soreceive uiomove");
SBLASTMBUFCHK(&so->so_rcv, "soreceive uiomove");
resid = uio->uio_resid;
splx(s);
uio_error =
uiomove(mtod(m, caddr_t) + moff, (int)len,
uio);
s = splsoftnet();
if (uio_error)
uio->uio_resid = resid - len;
} else
uio->uio_resid -= len;
if (len == m->m_len - moff) {
if (m->m_flags & M_EOR)
flags |= MSG_EOR;
if (flags & MSG_PEEK) {
m = m->m_next;
moff = 0;
} else {
nextrecord = m->m_nextpkt;
sbfree(&so->so_rcv, m);
if (mp) {
*mp = m;
mp = &m->m_next;
so->so_rcv.sb_mb = m = m->m_next;
*mp = NULL;
} else {
MFREE(m, so->so_rcv.sb_mb);
m = so->so_rcv.sb_mb;
}
/*
* If m != NULL, we also know that
* so->so_rcv.sb_mb != NULL.
*/
KASSERT(so->so_rcv.sb_mb == m);
if (m) {
m->m_nextpkt = nextrecord;
if (nextrecord == NULL)
so->so_rcv.sb_lastrecord = m;
} else {
so->so_rcv.sb_mb = nextrecord;
SB_EMPTY_FIXUP(&so->so_rcv);
}
SBLASTRECORDCHK(&so->so_rcv, "soreceive 3");
SBLASTMBUFCHK(&so->so_rcv, "soreceive 3");
}
} else {
if (flags & MSG_PEEK)
moff += len;
else {
if (mp)
*mp = m_copym(m, 0, len, M_WAIT);
m->m_data += len;
m->m_len -= len;
so->so_rcv.sb_cc -= len;
so->so_rcv.sb_datacc -= len;
}
}
if (so->so_oobmark) {
if ((flags & MSG_PEEK) == 0) {
so->so_oobmark -= len;
if (so->so_oobmark == 0) {
so->so_state |= SS_RCVATMARK;
break;
}
} else {
offset += len;
if (offset == so->so_oobmark)
break;
}
}
if (flags & MSG_EOR)
break;
/*
* If the MSG_WAITALL flag is set (for non-atomic socket),
* we must not quit until "uio->uio_resid == 0" or an error
* termination. If a signal/timeout occurs, return
* with a short count but without error.
* Keep sockbuf locked against other readers.
*/
while (flags & MSG_WAITALL && m == NULL && uio->uio_resid > 0 &&
!sosendallatonce(so) && !nextrecord) {
if (so->so_error || so->so_state & SS_CANTRCVMORE)
break;
SBLASTRECORDCHK(&so->so_rcv, "soreceive sbwait 2");
SBLASTMBUFCHK(&so->so_rcv, "soreceive sbwait 2");
error = sbwait(&so->so_rcv);
if (error) {
sbunlock(&so->so_rcv);
splx(s);
return (0);
}
if ((m = so->so_rcv.sb_mb) != NULL)
nextrecord = m->m_nextpkt;
}
}
if (m && pr->pr_flags & PR_ATOMIC) {
flags |= MSG_TRUNC;
if ((flags & MSG_PEEK) == 0)
(void) sbdroprecord(&so->so_rcv);
}
if ((flags & MSG_PEEK) == 0) {
if (m == NULL) {
/*
* First part is an inline SB_EMPTY_FIXUP(). Second
* part makes sure sb_lastrecord is up-to-date if
* there is still data in the socket buffer.
*/
so->so_rcv.sb_mb = nextrecord;
if (so->so_rcv.sb_mb == NULL) {
so->so_rcv.sb_mbtail = NULL;
so->so_rcv.sb_lastrecord = NULL;
} else if (nextrecord->m_nextpkt == NULL)
so->so_rcv.sb_lastrecord = nextrecord;
}
SBLASTRECORDCHK(&so->so_rcv, "soreceive 4");
SBLASTMBUFCHK(&so->so_rcv, "soreceive 4");
if (pr->pr_flags & PR_WANTRCVD && so->so_pcb)
(*pr->pr_usrreq)(so, PRU_RCVD, NULL,
(struct mbuf *)(long)flags, NULL, curproc);
}
if (orig_resid == uio->uio_resid && orig_resid &&
(flags & MSG_EOR) == 0 && (so->so_state & SS_CANTRCVMORE) == 0) {
sbunlock(&so->so_rcv);
splx(s);
goto restart;
}
if (uio_error)
error = uio_error;
if (flagsp)
*flagsp |= flags;
release:
sbunlock(&so->so_rcv);
splx(s);
return (error);
}
int
soshutdown(struct socket *so, int how)
{
struct protosw *pr = so->so_proto;
switch (how) {
case SHUT_RD:
case SHUT_RDWR:
sorflush(so);
if (how == SHUT_RD)
return (0);
/* FALLTHROUGH */
case SHUT_WR:
return (*pr->pr_usrreq)(so, PRU_SHUTDOWN, NULL, NULL, NULL,
curproc);
default:
return (EINVAL);
}
}
void
sorflush(struct socket *so)
{
struct sockbuf *sb = &so->so_rcv;
struct protosw *pr = so->so_proto;
int s;
struct sockbuf asb;
sb->sb_flags |= SB_NOINTR;
(void) sblock(sb, M_WAITOK);
s = splnet();
socantrcvmore(so);
sbunlock(sb);
asb = *sb;
bzero(sb, sizeof (*sb));
/* XXX - the bzero stumps all over so_rcv */
if (asb.sb_flags & SB_KNOTE) {
sb->sb_sel.si_note = asb.sb_sel.si_note;
sb->sb_flags = SB_KNOTE;
}
splx(s);
if (pr->pr_flags & PR_RIGHTS && pr->pr_domain->dom_dispose)
(*pr->pr_domain->dom_dispose)(asb.sb_mb);
sbrelease(&asb);
}
int
sosetopt(struct socket *so, int level, int optname, struct mbuf *m0)
{
int error = 0;
struct mbuf *m = m0;
if (level != SOL_SOCKET) {
if (so->so_proto && so->so_proto->pr_ctloutput)
return ((*so->so_proto->pr_ctloutput)
(PRCO_SETOPT, so, level, optname, &m0));
error = ENOPROTOOPT;
} else {
switch (optname) {
case SO_BINDANY:
case SO_RDOMAIN:
if ((error = suser(curproc, 0)) != 0) /* XXX */
goto bad;
break;
}
switch (optname) {
case SO_LINGER:
if (m == NULL || m->m_len != sizeof (struct linger) ||
mtod(m, struct linger *)->l_linger < 0 ||
mtod(m, struct linger *)->l_linger > SHRT_MAX) {
error = EINVAL;
goto bad;
}
so->so_linger = mtod(m, struct linger *)->l_linger;
/* FALLTHROUGH */
case SO_BINDANY:
case SO_DEBUG:
case SO_KEEPALIVE:
case SO_DONTROUTE:
case SO_USELOOPBACK:
case SO_BROADCAST:
case SO_REUSEADDR:
case SO_REUSEPORT:
case SO_OOBINLINE:
case SO_JUMBO:
case SO_TIMESTAMP:
if (m == NULL || m->m_len < sizeof (int)) {
error = EINVAL;
goto bad;
}
if (*mtod(m, int *))
so->so_options |= optname;
else
so->so_options &= ~optname;
break;
case SO_SNDBUF:
case SO_RCVBUF:
case SO_SNDLOWAT:
case SO_RCVLOWAT:
{
u_long cnt;
if (m == NULL || m->m_len < sizeof (int)) {
error = EINVAL;
goto bad;
}
cnt = *mtod(m, int *);
if ((long)cnt <= 0)
cnt = 1;
switch (optname) {
case SO_SNDBUF:
if (sbcheckreserve(cnt, so->so_snd.sb_hiwat) ||
sbreserve(&so->so_snd, cnt)) {
error = ENOBUFS;
goto bad;
}
break;
case SO_RCVBUF:
if (sbcheckreserve(cnt, so->so_rcv.sb_hiwat) ||
sbreserve(&so->so_rcv, cnt)) {
error = ENOBUFS;
goto bad;
}
break;
case SO_SNDLOWAT:
so->so_snd.sb_lowat = (cnt > so->so_snd.sb_hiwat) ?
so->so_snd.sb_hiwat : cnt;
break;
case SO_RCVLOWAT:
so->so_rcv.sb_lowat = (cnt > so->so_rcv.sb_hiwat) ?
so->so_rcv.sb_hiwat : cnt;
break;
}
break;
}
case SO_SNDTIMEO:
case SO_RCVTIMEO:
{
struct timeval *tv;
u_short val;
if (m == NULL || m->m_len < sizeof (*tv)) {
error = EINVAL;
goto bad;
}
tv = mtod(m, struct timeval *);
if (tv->tv_sec > (USHRT_MAX - tv->tv_usec / tick) / hz) {
error = EDOM;
goto bad;
}
val = tv->tv_sec * hz + tv->tv_usec / tick;
if (val == 0 && tv->tv_usec != 0)
val = 1;
switch (optname) {
case SO_SNDTIMEO:
so->so_snd.sb_timeo = val;
break;
case SO_RCVTIMEO:
so->so_rcv.sb_timeo = val;
break;
}
break;
}
default:
error = ENOPROTOOPT;
break;
}
if (error == 0 && so->so_proto && so->so_proto->pr_ctloutput) {
(void) ((*so->so_proto->pr_ctloutput)
(PRCO_SETOPT, so, level, optname, &m0));
m = NULL; /* freed by protocol */
}
}
bad:
if (m)
(void) m_free(m);
return (error);
}
int
sogetopt(struct socket *so, int level, int optname, struct mbuf **mp)
{
struct mbuf *m;
if (level != SOL_SOCKET) {
if (so->so_proto && so->so_proto->pr_ctloutput) {
return ((*so->so_proto->pr_ctloutput)
(PRCO_GETOPT, so, level, optname, mp));
} else
return (ENOPROTOOPT);
} else {
m = m_get(M_WAIT, MT_SOOPTS);
m->m_len = sizeof (int);
switch (optname) {
case SO_LINGER:
m->m_len = sizeof (struct linger);
mtod(m, struct linger *)->l_onoff =
so->so_options & SO_LINGER;
mtod(m, struct linger *)->l_linger = so->so_linger;
break;
case SO_BINDANY:
case SO_USELOOPBACK:
case SO_DONTROUTE:
case SO_DEBUG:
case SO_KEEPALIVE:
case SO_REUSEADDR:
case SO_REUSEPORT:
case SO_BROADCAST:
case SO_OOBINLINE:
case SO_JUMBO:
case SO_TIMESTAMP:
*mtod(m, int *) = so->so_options & optname;
break;
case SO_TYPE:
*mtod(m, int *) = so->so_type;
break;
case SO_ERROR:
*mtod(m, int *) = so->so_error;
so->so_error = 0;
break;
case SO_SNDBUF:
*mtod(m, int *) = so->so_snd.sb_hiwat;
break;
case SO_RCVBUF:
*mtod(m, int *) = so->so_rcv.sb_hiwat;
break;
case SO_SNDLOWAT:
*mtod(m, int *) = so->so_snd.sb_lowat;
break;
case SO_RCVLOWAT:
*mtod(m, int *) = so->so_rcv.sb_lowat;
break;
case SO_SNDTIMEO:
case SO_RCVTIMEO:
{
int val = (optname == SO_SNDTIMEO ?
so->so_snd.sb_timeo : so->so_rcv.sb_timeo);
m->m_len = sizeof(struct timeval);
mtod(m, struct timeval *)->tv_sec = val / hz;
mtod(m, struct timeval *)->tv_usec =
(val % hz) * tick;
break;
}
default:
(void)m_free(m);
return (ENOPROTOOPT);
}
*mp = m;
return (0);
}
}
void
sohasoutofband(struct socket *so)
{
csignal(so->so_pgid, SIGURG, so->so_siguid, so->so_sigeuid);
selwakeup(&so->so_rcv.sb_sel);
}
int
soo_kqfilter(struct file *fp, struct knote *kn)
{
struct socket *so = (struct socket *)kn->kn_fp->f_data;
struct sockbuf *sb;
int s;
switch (kn->kn_filter) {
case EVFILT_READ:
if (so->so_options & SO_ACCEPTCONN)
kn->kn_fop = &solisten_filtops;
else
kn->kn_fop = &soread_filtops;
sb = &so->so_rcv;
break;
case EVFILT_WRITE:
kn->kn_fop = &sowrite_filtops;
sb = &so->so_snd;
break;
default:
return (1);
}
s = splnet();
SLIST_INSERT_HEAD(&sb->sb_sel.si_note, kn, kn_selnext);
sb->sb_flags |= SB_KNOTE;
splx(s);
return (0);
}
void
filt_sordetach(struct knote *kn)
{
struct socket *so = (struct socket *)kn->kn_fp->f_data;
int s = splnet();
SLIST_REMOVE(&so->so_rcv.sb_sel.si_note, kn, knote, kn_selnext);
if (SLIST_EMPTY(&so->so_rcv.sb_sel.si_note))
so->so_rcv.sb_flags &= ~SB_KNOTE;
splx(s);
}
/*ARGSUSED*/
int
filt_soread(struct knote *kn, long hint)
{
struct socket *so = (struct socket *)kn->kn_fp->f_data;
kn->kn_data = so->so_rcv.sb_cc;
if (so->so_state & SS_CANTRCVMORE) {
kn->kn_flags |= EV_EOF;
kn->kn_fflags = so->so_error;
return (1);
}
if (so->so_error) /* temporary udp error */
return (1);
if (kn->kn_sfflags & NOTE_LOWAT)
return (kn->kn_data >= kn->kn_sdata);
return (kn->kn_data >= so->so_rcv.sb_lowat);
}
void
filt_sowdetach(struct knote *kn)
{
struct socket *so = (struct socket *)kn->kn_fp->f_data;
int s = splnet();
SLIST_REMOVE(&so->so_snd.sb_sel.si_note, kn, knote, kn_selnext);
if (SLIST_EMPTY(&so->so_snd.sb_sel.si_note))
so->so_snd.sb_flags &= ~SB_KNOTE;
splx(s);
}
/*ARGSUSED*/
int
filt_sowrite(struct knote *kn, long hint)
{
struct socket *so = (struct socket *)kn->kn_fp->f_data;
kn->kn_data = sbspace(&so->so_snd);
if (so->so_state & SS_CANTSENDMORE) {
kn->kn_flags |= EV_EOF;
kn->kn_fflags = so->so_error;
return (1);
}
if (so->so_error) /* temporary udp error */
return (1);
if (((so->so_state & SS_ISCONNECTED) == 0) &&
(so->so_proto->pr_flags & PR_CONNREQUIRED))
return (0);
if (kn->kn_sfflags & NOTE_LOWAT)
return (kn->kn_data >= kn->kn_sdata);
return (kn->kn_data >= so->so_snd.sb_lowat);
}
/*ARGSUSED*/
int
filt_solisten(struct knote *kn, long hint)
{
struct socket *so = (struct socket *)kn->kn_fp->f_data;
kn->kn_data = so->so_qlen;
return (so->so_qlen != 0);
}
|