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
|
/*
* Copyright (c) 1982, 1986, 1989, 1991, 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: @(#)uipc_usrreq.c 8.3 (Berkeley) 1/4/94
* $Id: uipc_usrreq.c,v 1.19 1997/02/22 09:39:29 peter Exp $
*/
#include <sys/param.h>
#include <sys/queue.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/domain.h>
#include <sys/file.h>
#include <sys/filedesc.h>
#include <sys/mbuf.h>
#include <sys/namei.h>
#include <sys/proc.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/stat.h>
#include <sys/sysctl.h>
#include <sys/un.h>
#include <sys/unpcb.h>
#include <sys/vnode.h>
/*
* Unix communications domain.
*
* TODO:
* SEQPACKET, RDM
* rethink name space problems
* need a proper out-of-band
*/
static struct sockaddr sun_noname = { sizeof(sun_noname), AF_LOCAL };
static ino_t unp_ino; /* prototype for fake inode numbers */
static int unp_attach __P((struct socket *));
static void unp_detach __P((struct unpcb *));
static int unp_bind __P((struct unpcb *,struct mbuf *, struct proc *));
static int unp_connect __P((struct socket *,struct mbuf *, struct proc *));
static void unp_disconnect __P((struct unpcb *));
static void unp_shutdown __P((struct unpcb *));
static void unp_drop __P((struct unpcb *, int));
static void unp_gc __P((void));
static void unp_scan __P((struct mbuf *, void (*)(struct file *)));
static void unp_mark __P((struct file *));
static void unp_discard __P((struct file *));
static int unp_internalize __P((struct mbuf *, struct proc *));
/*ARGSUSED*/
int
uipc_usrreq(so, req, m, nam, control)
struct socket *so;
int req;
struct mbuf *m, *nam, *control;
{
struct unpcb *unp = sotounpcb(so);
register struct socket *so2;
register int error = 0;
struct proc *p = curproc; /* XXX */
if (req == PRU_CONTROL)
return (EOPNOTSUPP);
if (req != PRU_SEND && control && control->m_len) {
error = EOPNOTSUPP;
goto release;
}
if (unp == 0 && req != PRU_ATTACH) {
error = EINVAL;
goto release;
}
switch (req) {
case PRU_ATTACH:
if (unp) {
error = EISCONN;
break;
}
error = unp_attach(so);
break;
case PRU_DETACH:
unp_detach(unp);
break;
case PRU_BIND:
error = unp_bind(unp, nam, p);
break;
case PRU_LISTEN:
if (unp->unp_vnode == 0)
error = EINVAL;
break;
case PRU_CONNECT:
error = unp_connect(so, nam, p);
break;
case PRU_CONNECT2:
error = unp_connect2(so, (struct socket *)nam);
break;
case PRU_DISCONNECT:
unp_disconnect(unp);
break;
case PRU_ACCEPT:
/*
* Pass back name of connected socket,
* if it was bound and we are still connected
* (our peer may have closed already!).
*/
if (unp->unp_conn && unp->unp_conn->unp_addr) {
nam->m_len = unp->unp_conn->unp_addr->m_len;
bcopy(mtod(unp->unp_conn->unp_addr, caddr_t),
mtod(nam, caddr_t), (unsigned)nam->m_len);
} else {
nam->m_len = sizeof(sun_noname);
*(mtod(nam, struct sockaddr *)) = sun_noname;
}
break;
case PRU_SHUTDOWN:
socantsendmore(so);
unp_shutdown(unp);
break;
case PRU_RCVD:
switch (so->so_type) {
case SOCK_DGRAM:
panic("uipc 1");
/*NOTREACHED*/
case SOCK_STREAM:
#define rcv (&so->so_rcv)
#define snd (&so2->so_snd)
if (unp->unp_conn == 0)
break;
so2 = unp->unp_conn->unp_socket;
/*
* Adjust backpressure on sender
* and wakeup any waiting to write.
*/
snd->sb_mbmax += unp->unp_mbcnt - rcv->sb_mbcnt;
unp->unp_mbcnt = rcv->sb_mbcnt;
snd->sb_hiwat += unp->unp_cc - rcv->sb_cc;
unp->unp_cc = rcv->sb_cc;
sowwakeup(so2);
#undef snd
#undef rcv
break;
default:
panic("uipc 2");
}
break;
case PRU_SEND:
case PRU_SEND_EOF:
if (control && (error = unp_internalize(control, p)))
break;
switch (so->so_type) {
case SOCK_DGRAM: {
struct sockaddr *from;
if (nam) {
if (unp->unp_conn) {
error = EISCONN;
break;
}
error = unp_connect(so, nam, p);
if (error)
break;
} else {
if (unp->unp_conn == 0) {
error = ENOTCONN;
break;
}
}
so2 = unp->unp_conn->unp_socket;
if (unp->unp_addr)
from = mtod(unp->unp_addr, struct sockaddr *);
else
from = &sun_noname;
if (sbappendaddr(&so2->so_rcv, from, m, control)) {
sorwakeup(so2);
m = 0;
control = 0;
} else
error = ENOBUFS;
if (nam)
unp_disconnect(unp);
break;
}
case SOCK_STREAM:
#define rcv (&so2->so_rcv)
#define snd (&so->so_snd)
/* Connect if not connected yet. */
/*
* Note: A better implementation would complain
* if not equal to the peer's address.
*/
if ((so->so_state & SS_ISCONNECTED) == 0) {
if (nam) {
error = unp_connect(so, nam, p);
if (error)
break; /* XXX */
} else {
error = ENOTCONN;
break;
}
}
if (so->so_state & SS_CANTSENDMORE) {
error = EPIPE;
break;
}
if (unp->unp_conn == 0)
panic("uipc 3");
so2 = unp->unp_conn->unp_socket;
/*
* Send to paired receive port, and then reduce
* send buffer hiwater marks to maintain backpressure.
* Wake up readers.
*/
if (control) {
if (sbappendcontrol(rcv, m, control))
control = 0;
} else
sbappend(rcv, m);
snd->sb_mbmax -=
rcv->sb_mbcnt - unp->unp_conn->unp_mbcnt;
unp->unp_conn->unp_mbcnt = rcv->sb_mbcnt;
snd->sb_hiwat -= rcv->sb_cc - unp->unp_conn->unp_cc;
unp->unp_conn->unp_cc = rcv->sb_cc;
sorwakeup(so2);
m = 0;
#undef snd
#undef rcv
break;
default:
panic("uipc 4");
}
/*
* SEND_EOF is equivalent to a SEND followed by
* a SHUTDOWN.
*/
if (req == PRU_SEND_EOF) {
socantsendmore(so);
unp_shutdown(unp);
}
break;
case PRU_ABORT:
unp_drop(unp, ECONNABORTED);
break;
case PRU_SENSE:
((struct stat *) m)->st_blksize = so->so_snd.sb_hiwat;
if (so->so_type == SOCK_STREAM && unp->unp_conn != 0) {
so2 = unp->unp_conn->unp_socket;
((struct stat *) m)->st_blksize += so2->so_rcv.sb_cc;
}
((struct stat *) m)->st_dev = NODEV;
if (unp->unp_ino == 0)
unp->unp_ino = unp_ino++;
((struct stat *) m)->st_ino = unp->unp_ino;
return (0);
case PRU_RCVOOB:
return (EOPNOTSUPP);
case PRU_SENDOOB:
error = EOPNOTSUPP;
break;
case PRU_SOCKADDR:
if (unp->unp_addr) {
nam->m_len = unp->unp_addr->m_len;
bcopy(mtod(unp->unp_addr, caddr_t),
mtod(nam, caddr_t), (unsigned)nam->m_len);
} else
nam->m_len = 0;
break;
case PRU_PEERADDR:
if (unp->unp_conn && unp->unp_conn->unp_addr) {
nam->m_len = unp->unp_conn->unp_addr->m_len;
bcopy(mtod(unp->unp_conn->unp_addr, caddr_t),
mtod(nam, caddr_t), (unsigned)nam->m_len);
} else
nam->m_len = 0;
break;
case PRU_SLOWTIMO:
break;
default:
panic("piusrreq");
}
release:
if (control)
m_freem(control);
if (m)
m_freem(m);
return (error);
}
/*
* Both send and receive buffers are allocated PIPSIZ bytes of buffering
* for stream sockets, although the total for sender and receiver is
* actually only PIPSIZ.
* Datagram sockets really use the sendspace as the maximum datagram size,
* and don't really want to reserve the sendspace. Their recvspace should
* be large enough for at least one max-size datagram plus address.
*/
#ifndef PIPSIZ
#define PIPSIZ 8192
#endif
static u_long unpst_sendspace = PIPSIZ;
static u_long unpst_recvspace = PIPSIZ;
static u_long unpdg_sendspace = 2*1024; /* really max datagram size */
static u_long unpdg_recvspace = 4*1024;
static int unp_rights; /* file descriptors in flight */
SYSCTL_INT(_net_local_stream, OID_AUTO, sendspace, CTLFLAG_RW,
&unpst_sendspace, 0, "");
SYSCTL_INT(_net_local_stream, OID_AUTO, recvspace, CTLFLAG_RW,
&unpst_recvspace, 0, "");
SYSCTL_INT(_net_local_dgram, OID_AUTO, maxdgram, CTLFLAG_RW,
&unpdg_sendspace, 0, "");
SYSCTL_INT(_net_local_dgram, OID_AUTO, recvspace, CTLFLAG_RW,
&unpdg_recvspace, 0, "");
SYSCTL_INT(_net_local, OID_AUTO, inflight, CTLFLAG_RD, &unp_rights, 0, "");
static int
unp_attach(so)
struct socket *so;
{
register struct mbuf *m;
register struct unpcb *unp;
int error;
if (so->so_snd.sb_hiwat == 0 || so->so_rcv.sb_hiwat == 0) {
switch (so->so_type) {
case SOCK_STREAM:
error = soreserve(so, unpst_sendspace, unpst_recvspace);
break;
case SOCK_DGRAM:
error = soreserve(so, unpdg_sendspace, unpdg_recvspace);
break;
default:
panic("unp_attach");
}
if (error)
return (error);
}
m = m_getclr(M_DONTWAIT, MT_PCB);
if (m == NULL)
return (ENOBUFS);
unp = mtod(m, struct unpcb *);
so->so_pcb = (caddr_t)unp;
unp->unp_socket = so;
return (0);
}
static void
unp_detach(unp)
register struct unpcb *unp;
{
if (unp->unp_vnode) {
unp->unp_vnode->v_socket = 0;
vrele(unp->unp_vnode);
unp->unp_vnode = 0;
}
if (unp->unp_conn)
unp_disconnect(unp);
while (unp->unp_refs)
unp_drop(unp->unp_refs, ECONNRESET);
soisdisconnected(unp->unp_socket);
unp->unp_socket->so_pcb = 0;
if (unp_rights) {
/*
* Normally the receive buffer is flushed later,
* in sofree, but if our receive buffer holds references
* to descriptors that are now garbage, we will dispose
* of those descriptor references after the garbage collector
* gets them (resulting in a "panic: closef: count < 0").
*/
sorflush(unp->unp_socket);
unp_gc();
}
m_freem(unp->unp_addr);
(void) m_free(dtom(unp));
}
static int
unp_bind(unp, nam, p)
struct unpcb *unp;
struct mbuf *nam;
struct proc *p;
{
struct sockaddr_un *soun = mtod(nam, struct sockaddr_un *);
register struct vnode *vp;
struct vattr vattr;
int error;
struct nameidata nd;
NDINIT(&nd, CREATE, FOLLOW | LOCKPARENT, UIO_SYSSPACE,
soun->sun_path, p);
if (unp->unp_vnode != NULL)
return (EINVAL);
if (nam->m_len == MLEN) {
if (*(mtod(nam, caddr_t) + nam->m_len - 1) != 0)
return (EINVAL);
} else
*(mtod(nam, caddr_t) + nam->m_len) = 0;
/* SHOULD BE ABLE TO ADOPT EXISTING AND wakeup() ALA FIFO's */
error = namei(&nd);
if (error)
return (error);
vp = nd.ni_vp;
if (vp != NULL) {
VOP_ABORTOP(nd.ni_dvp, &nd.ni_cnd);
if (nd.ni_dvp == vp)
vrele(nd.ni_dvp);
else
vput(nd.ni_dvp);
vrele(vp);
return (EADDRINUSE);
}
VATTR_NULL(&vattr);
vattr.va_type = VSOCK;
vattr.va_mode = ACCESSPERMS;
VOP_LEASE(nd.ni_dvp, p, p->p_ucred, LEASE_WRITE);
if (error = VOP_CREATE(nd.ni_dvp, &nd.ni_vp, &nd.ni_cnd, &vattr))
return (error);
vp = nd.ni_vp;
vp->v_socket = unp->unp_socket;
unp->unp_vnode = vp;
unp->unp_addr = m_copy(nam, 0, (int)M_COPYALL);
VOP_UNLOCK(vp, 0, p);
return (0);
}
static int
unp_connect(so, nam, p)
struct socket *so;
struct mbuf *nam;
struct proc *p;
{
register struct sockaddr_un *soun = mtod(nam, struct sockaddr_un *);
register struct vnode *vp;
register struct socket *so2, *so3;
struct unpcb *unp2, *unp3;
int error;
struct nameidata nd;
NDINIT(&nd, LOOKUP, FOLLOW | LOCKLEAF, UIO_SYSSPACE, soun->sun_path, p);
if (nam->m_data + nam->m_len == &nam->m_dat[MLEN]) { /* XXX */
if (*(mtod(nam, caddr_t) + nam->m_len - 1) != 0)
return (EMSGSIZE);
} else
*(mtod(nam, caddr_t) + nam->m_len) = 0;
error = namei(&nd);
if (error)
return (error);
vp = nd.ni_vp;
if (vp->v_type != VSOCK) {
error = ENOTSOCK;
goto bad;
}
error = VOP_ACCESS(vp, VWRITE, p->p_ucred, p);
if (error)
goto bad;
so2 = vp->v_socket;
if (so2 == 0) {
error = ECONNREFUSED;
goto bad;
}
if (so->so_type != so2->so_type) {
error = EPROTOTYPE;
goto bad;
}
if (so->so_proto->pr_flags & PR_CONNREQUIRED) {
if ((so2->so_options & SO_ACCEPTCONN) == 0 ||
(so3 = sonewconn(so2, 0)) == 0) {
error = ECONNREFUSED;
goto bad;
}
unp2 = sotounpcb(so2);
unp3 = sotounpcb(so3);
if (unp2->unp_addr)
unp3->unp_addr =
m_copy(unp2->unp_addr, 0, (int)M_COPYALL);
so2 = so3;
}
error = unp_connect2(so, so2);
bad:
vput(vp);
return (error);
}
int
unp_connect2(so, so2)
register struct socket *so;
register struct socket *so2;
{
register struct unpcb *unp = sotounpcb(so);
register struct unpcb *unp2;
if (so2->so_type != so->so_type)
return (EPROTOTYPE);
unp2 = sotounpcb(so2);
unp->unp_conn = unp2;
switch (so->so_type) {
case SOCK_DGRAM:
unp->unp_nextref = unp2->unp_refs;
unp2->unp_refs = unp;
soisconnected(so);
break;
case SOCK_STREAM:
unp2->unp_conn = unp;
soisconnected(so);
soisconnected(so2);
break;
default:
panic("unp_connect2");
}
return (0);
}
static void
unp_disconnect(unp)
struct unpcb *unp;
{
register struct unpcb *unp2 = unp->unp_conn;
if (unp2 == 0)
return;
unp->unp_conn = 0;
switch (unp->unp_socket->so_type) {
case SOCK_DGRAM:
if (unp2->unp_refs == unp)
unp2->unp_refs = unp->unp_nextref;
else {
unp2 = unp2->unp_refs;
for (;;) {
if (unp2 == 0)
panic("unp_disconnect");
if (unp2->unp_nextref == unp)
break;
unp2 = unp2->unp_nextref;
}
unp2->unp_nextref = unp->unp_nextref;
}
unp->unp_nextref = 0;
unp->unp_socket->so_state &= ~SS_ISCONNECTED;
break;
case SOCK_STREAM:
soisdisconnected(unp->unp_socket);
unp2->unp_conn = 0;
soisdisconnected(unp2->unp_socket);
break;
}
}
#ifdef notdef
void
unp_abort(unp)
struct unpcb *unp;
{
unp_detach(unp);
}
#endif
static void
unp_shutdown(unp)
struct unpcb *unp;
{
struct socket *so;
if (unp->unp_socket->so_type == SOCK_STREAM && unp->unp_conn &&
(so = unp->unp_conn->unp_socket))
socantrcvmore(so);
}
static void
unp_drop(unp, errno)
struct unpcb *unp;
int errno;
{
struct socket *so = unp->unp_socket;
so->so_error = errno;
unp_disconnect(unp);
if (so->so_head) {
so->so_pcb = (caddr_t) 0;
m_freem(unp->unp_addr);
(void) m_free(dtom(unp));
sofree(so);
}
}
#ifdef notdef
void
unp_drain()
{
}
#endif
int
unp_externalize(rights)
struct mbuf *rights;
{
struct proc *p = curproc; /* XXX */
register int i;
register struct cmsghdr *cm = mtod(rights, struct cmsghdr *);
register struct file **rp = (struct file **)(cm + 1);
register struct file *fp;
int newfds = (cm->cmsg_len - sizeof(*cm)) / sizeof (int);
int f;
/*
* if the new FD's will not fit, then we free them all
*/
if (!fdavail(p, newfds)) {
for (i = 0; i < newfds; i++) {
fp = *rp;
unp_discard(fp);
*rp++ = 0;
}
return (EMSGSIZE);
}
/*
* now change each pointer to an fd in the global table to
* an integer that is the index to the local fd table entry
* that we set up to point to the global one we are transferring.
* XXX this assumes a pointer and int are the same size...!
*/
for (i = 0; i < newfds; i++) {
if (fdalloc(p, 0, &f))
panic("unp_externalize");
fp = *rp;
p->p_fd->fd_ofiles[f] = fp;
fp->f_msgcount--;
unp_rights--;
*(int *)rp++ = f;
}
return (0);
}
static int
unp_internalize(control, p)
struct mbuf *control;
struct proc *p;
{
struct filedesc *fdp = p->p_fd;
register struct cmsghdr *cm = mtod(control, struct cmsghdr *);
register struct file **rp;
register struct file *fp;
register int i, fd;
int oldfds;
if (cm->cmsg_type != SCM_RIGHTS || cm->cmsg_level != SOL_SOCKET ||
cm->cmsg_len != control->m_len)
return (EINVAL);
oldfds = (cm->cmsg_len - sizeof (*cm)) / sizeof (int);
/*
* check that all the FDs passed in refer to legal OPEN files
* If not, reject the entire operation.
*/
rp = (struct file **)(cm + 1);
for (i = 0; i < oldfds; i++) {
fd = *(int *)rp++;
if ((unsigned)fd >= fdp->fd_nfiles ||
fdp->fd_ofiles[fd] == NULL)
return (EBADF);
}
/*
* Now replace the integer FDs with pointers to
* the associated global file table entry..
* XXX this assumes a pointer and an int are the same size!
*/
rp = (struct file **)(cm + 1);
for (i = 0; i < oldfds; i++) {
fp = fdp->fd_ofiles[*(int *)rp];
*rp++ = fp;
fp->f_count++;
fp->f_msgcount++;
unp_rights++;
}
return (0);
}
static int unp_defer, unp_gcing;
static void
unp_gc()
{
register struct file *fp, *nextfp;
register struct socket *so;
struct file **extra_ref, **fpp;
int nunref, i;
if (unp_gcing)
return;
unp_gcing = 1;
unp_defer = 0;
/*
* before going through all this, set all FDs to
* be NOT defered and NOT externally accessible
*/
for (fp = filehead.lh_first; fp != 0; fp = fp->f_list.le_next)
fp->f_flag &= ~(FMARK|FDEFER);
do {
for (fp = filehead.lh_first; fp != 0; fp = fp->f_list.le_next) {
/*
* If the file is not open, skip it
*/
if (fp->f_count == 0)
continue;
/*
* If we already marked it as 'defer' in a
* previous pass, then try process it this time
* and un-mark it
*/
if (fp->f_flag & FDEFER) {
fp->f_flag &= ~FDEFER;
unp_defer--;
} else {
/*
* if it's not defered, then check if it's
* already marked.. if so skip it
*/
if (fp->f_flag & FMARK)
continue;
/*
* If all references are from messages
* in transit, then skip it. it's not
* externally accessible.
*/
if (fp->f_count == fp->f_msgcount)
continue;
/*
* If it got this far then it must be
* externally accessible.
*/
fp->f_flag |= FMARK;
}
/*
* either it was defered, or it is externally
* accessible and not already marked so.
* Now check if it is possibly one of OUR sockets.
*/
if (fp->f_type != DTYPE_SOCKET ||
(so = (struct socket *)fp->f_data) == 0)
continue;
if (so->so_proto->pr_domain != &localdomain ||
(so->so_proto->pr_flags&PR_RIGHTS) == 0)
continue;
#ifdef notdef
if (so->so_rcv.sb_flags & SB_LOCK) {
/*
* This is problematical; it's not clear
* we need to wait for the sockbuf to be
* unlocked (on a uniprocessor, at least),
* and it's also not clear what to do
* if sbwait returns an error due to receipt
* of a signal. If sbwait does return
* an error, we'll go into an infinite
* loop. Delete all of this for now.
*/
(void) sbwait(&so->so_rcv);
goto restart;
}
#endif
/*
* So, Ok, it's one of our sockets and it IS externally
* accessible (or was defered). Now we look
* to see if we hold any file descriptors in it's
* message buffers. Follow those links and mark them
* as accessible too.
*/
unp_scan(so->so_rcv.sb_mb, unp_mark);
}
} while (unp_defer);
/*
* We grab an extra reference to each of the file table entries
* that are not otherwise accessible and then free the rights
* that are stored in messages on them.
*
* The bug in the orginal code is a little tricky, so I'll describe
* what's wrong with it here.
*
* It is incorrect to simply unp_discard each entry for f_msgcount
* times -- consider the case of sockets A and B that contain
* references to each other. On a last close of some other socket,
* we trigger a gc since the number of outstanding rights (unp_rights)
* is non-zero. If during the sweep phase the gc code un_discards,
* we end up doing a (full) closef on the descriptor. A closef on A
* results in the following chain. Closef calls soo_close, which
* calls soclose. Soclose calls first (through the switch
* uipc_usrreq) unp_detach, which re-invokes unp_gc. Unp_gc simply
* returns because the previous instance had set unp_gcing, and
* we return all the way back to soclose, which marks the socket
* with SS_NOFDREF, and then calls sofree. Sofree calls sorflush
* to free up the rights that are queued in messages on the socket A,
* i.e., the reference on B. The sorflush calls via the dom_dispose
* switch unp_dispose, which unp_scans with unp_discard. This second
* instance of unp_discard just calls closef on B.
*
* Well, a similar chain occurs on B, resulting in a sorflush on B,
* which results in another closef on A. Unfortunately, A is already
* being closed, and the descriptor has already been marked with
* SS_NOFDREF, and soclose panics at this point.
*
* Here, we first take an extra reference to each inaccessible
* descriptor. Then, we call sorflush ourself, since we know
* it is a Unix domain socket anyhow. After we destroy all the
* rights carried in messages, we do a last closef to get rid
* of our extra reference. This is the last close, and the
* unp_detach etc will shut down the socket.
*
* 91/09/19, bsy@cs.cmu.edu
*/
extra_ref = malloc(nfiles * sizeof(struct file *), M_FILE, M_WAITOK);
for (nunref = 0, fp = filehead.lh_first, fpp = extra_ref; fp != 0;
fp = nextfp) {
nextfp = fp->f_list.le_next;
/*
* If it's not open, skip it
*/
if (fp->f_count == 0)
continue;
/*
* If all refs are from msgs, and it's not marked accessible
* then it must be referenced from some unreachable cycle
* of (shut-down) FDs, so include it in our
* list of FDs to remove
*/
if (fp->f_count == fp->f_msgcount && !(fp->f_flag & FMARK)) {
*fpp++ = fp;
nunref++;
fp->f_count++;
}
}
/*
* for each FD on our hit list, do the following two things
*/
for (i = nunref, fpp = extra_ref; --i >= 0; ++fpp)
sorflush((struct socket *)(*fpp)->f_data);
for (i = nunref, fpp = extra_ref; --i >= 0; ++fpp)
closef(*fpp, (struct proc *) NULL);
free((caddr_t)extra_ref, M_FILE);
unp_gcing = 0;
}
void
unp_dispose(m)
struct mbuf *m;
{
if (m)
unp_scan(m, unp_discard);
}
static void
unp_scan(m0, op)
register struct mbuf *m0;
void (*op) __P((struct file *));
{
register struct mbuf *m;
register struct file **rp;
register struct cmsghdr *cm;
register int i;
int qfds;
while (m0) {
for (m = m0; m; m = m->m_next)
if (m->m_type == MT_CONTROL &&
m->m_len >= sizeof(*cm)) {
cm = mtod(m, struct cmsghdr *);
if (cm->cmsg_level != SOL_SOCKET ||
cm->cmsg_type != SCM_RIGHTS)
continue;
qfds = (cm->cmsg_len - sizeof *cm)
/ sizeof (struct file *);
rp = (struct file **)(cm + 1);
for (i = 0; i < qfds; i++)
(*op)(*rp++);
break; /* XXX, but saves time */
}
m0 = m0->m_act;
}
}
static void
unp_mark(fp)
struct file *fp;
{
if (fp->f_flag & FMARK)
return;
unp_defer++;
fp->f_flag |= (FMARK|FDEFER);
}
static void
unp_discard(fp)
struct file *fp;
{
fp->f_msgcount--;
unp_rights--;
(void) closef(fp, (struct proc *)NULL);
}
|