/
uipc_socket.c
2599 lines (2298 loc) · 59.7 KB
/
uipc_socket.c
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
/* $NetBSD: uipc_socket.c,v 1.302 2022/04/09 23:52:22 riastradh Exp $ */
/*
* Copyright (c) 2002, 2007, 2008, 2009 The NetBSD Foundation, Inc.
* All rights reserved.
*
* This code is derived from software contributed to The NetBSD Foundation
* by Jason R. Thorpe of Wasabi Systems, Inc, and by Andrew Doran.
*
* 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.
*
* THIS SOFTWARE IS PROVIDED BY THE NETBSD FOUNDATION, INC. 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 FOUNDATION 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.
*/
/*
* Copyright (c) 2004 The FreeBSD Foundation
* Copyright (c) 2004 Robert Watson
* 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 8.6 (Berkeley) 5/2/95
*/
/*
* 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.
*/
#include <sys/cdefs.h>
__KERNEL_RCSID(0, "$NetBSD: uipc_socket.c,v 1.302 2022/04/09 23:52:22 riastradh Exp $");
#ifdef _KERNEL_OPT
#include "opt_compat_netbsd.h"
#include "opt_sock_counters.h"
#include "opt_sosend_loan.h"
#include "opt_mbuftrace.h"
#include "opt_somaxkva.h"
#include "opt_multiprocessor.h" /* XXX */
#include "opt_sctp.h"
#endif
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/proc.h>
#include <sys/file.h>
#include <sys/filedesc.h>
#include <sys/kmem.h>
#include <sys/mbuf.h>
#include <sys/domain.h>
#include <sys/kernel.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/signalvar.h>
#include <sys/resourcevar.h>
#include <sys/uidinfo.h>
#include <sys/event.h>
#include <sys/poll.h>
#include <sys/kauth.h>
#include <sys/mutex.h>
#include <sys/condvar.h>
#include <sys/kthread.h>
#include <sys/compat_stub.h>
#include <compat/sys/time.h>
#include <compat/sys/socket.h>
#include <uvm/uvm_extern.h>
#include <uvm/uvm_loan.h>
#include <uvm/uvm_page.h>
#ifdef SCTP
#include <netinet/sctp_route.h>
#endif
MALLOC_DEFINE(M_SONAME, "soname", "socket name");
extern const struct fileops socketops;
static int sooptions;
extern int somaxconn; /* patchable (XXX sysctl) */
int somaxconn = SOMAXCONN;
kmutex_t *softnet_lock;
#ifdef SOSEND_COUNTERS
#include <sys/device.h>
static struct evcnt sosend_loan_big = EVCNT_INITIALIZER(EVCNT_TYPE_MISC,
NULL, "sosend", "loan big");
static struct evcnt sosend_copy_big = EVCNT_INITIALIZER(EVCNT_TYPE_MISC,
NULL, "sosend", "copy big");
static struct evcnt sosend_copy_small = EVCNT_INITIALIZER(EVCNT_TYPE_MISC,
NULL, "sosend", "copy small");
static struct evcnt sosend_kvalimit = EVCNT_INITIALIZER(EVCNT_TYPE_MISC,
NULL, "sosend", "kva limit");
#define SOSEND_COUNTER_INCR(ev) (ev)->ev_count++
EVCNT_ATTACH_STATIC(sosend_loan_big);
EVCNT_ATTACH_STATIC(sosend_copy_big);
EVCNT_ATTACH_STATIC(sosend_copy_small);
EVCNT_ATTACH_STATIC(sosend_kvalimit);
#else
#define SOSEND_COUNTER_INCR(ev) /* nothing */
#endif /* SOSEND_COUNTERS */
#if defined(SOSEND_NO_LOAN) || defined(MULTIPROCESSOR)
int sock_loan_thresh = -1;
#else
int sock_loan_thresh = 4096;
#endif
static kmutex_t so_pendfree_lock;
static struct mbuf *so_pendfree = NULL;
#ifndef SOMAXKVA
#define SOMAXKVA (16 * 1024 * 1024)
#endif
int somaxkva = SOMAXKVA;
static int socurkva;
static kcondvar_t socurkva_cv;
#ifndef SOFIXEDBUF
#define SOFIXEDBUF true
#endif
bool sofixedbuf = SOFIXEDBUF;
static kauth_listener_t socket_listener;
#define SOCK_LOAN_CHUNK 65536
static void sopendfree_thread(void *);
static kcondvar_t pendfree_thread_cv;
static lwp_t *sopendfree_lwp;
static void sysctl_kern_socket_setup(void);
static struct sysctllog *socket_sysctllog;
static vsize_t
sokvareserve(struct socket *so, vsize_t len)
{
int error;
mutex_enter(&so_pendfree_lock);
while (socurkva + len > somaxkva) {
SOSEND_COUNTER_INCR(&sosend_kvalimit);
error = cv_wait_sig(&socurkva_cv, &so_pendfree_lock);
if (error) {
len = 0;
break;
}
}
socurkva += len;
mutex_exit(&so_pendfree_lock);
return len;
}
static void
sokvaunreserve(vsize_t len)
{
mutex_enter(&so_pendfree_lock);
socurkva -= len;
cv_broadcast(&socurkva_cv);
mutex_exit(&so_pendfree_lock);
}
/*
* sokvaalloc: allocate kva for loan.
*/
vaddr_t
sokvaalloc(vaddr_t sva, vsize_t len, struct socket *so)
{
vaddr_t lva;
if (sokvareserve(so, len) == 0)
return 0;
lva = uvm_km_alloc(kernel_map, len, atop(sva) & uvmexp.colormask,
UVM_KMF_COLORMATCH | UVM_KMF_VAONLY | UVM_KMF_WAITVA);
if (lva == 0) {
sokvaunreserve(len);
return 0;
}
return lva;
}
/*
* sokvafree: free kva for loan.
*/
void
sokvafree(vaddr_t sva, vsize_t len)
{
uvm_km_free(kernel_map, sva, len, UVM_KMF_VAONLY);
sokvaunreserve(len);
}
static void
sodoloanfree(struct vm_page **pgs, void *buf, size_t size)
{
vaddr_t sva, eva;
vsize_t len;
int npgs;
KASSERT(pgs != NULL);
eva = round_page((vaddr_t) buf + size);
sva = trunc_page((vaddr_t) buf);
len = eva - sva;
npgs = len >> PAGE_SHIFT;
pmap_kremove(sva, len);
pmap_update(pmap_kernel());
uvm_unloan(pgs, npgs, UVM_LOAN_TOPAGE);
sokvafree(sva, len);
}
/*
* sopendfree_thread: free mbufs on "pendfree" list. Unlock and relock
* so_pendfree_lock when freeing mbufs.
*/
static void
sopendfree_thread(void *v)
{
struct mbuf *m, *next;
size_t rv;
mutex_enter(&so_pendfree_lock);
for (;;) {
rv = 0;
while (so_pendfree != NULL) {
m = so_pendfree;
so_pendfree = NULL;
mutex_exit(&so_pendfree_lock);
for (; m != NULL; m = next) {
next = m->m_next;
KASSERT((~m->m_flags & (M_EXT|M_EXT_PAGES)) ==
0);
KASSERT(m->m_ext.ext_refcnt == 0);
rv += m->m_ext.ext_size;
sodoloanfree(m->m_ext.ext_pgs, m->m_ext.ext_buf,
m->m_ext.ext_size);
pool_cache_put(mb_cache, m);
}
mutex_enter(&so_pendfree_lock);
}
if (rv)
cv_broadcast(&socurkva_cv);
cv_wait(&pendfree_thread_cv, &so_pendfree_lock);
}
panic("sopendfree_thread");
/* NOTREACHED */
}
void
soloanfree(struct mbuf *m, void *buf, size_t size, void *arg)
{
KASSERT(m != NULL);
/*
* postpone freeing mbuf.
*
* we can't do it in interrupt context
* because we need to put kva back to kernel_map.
*/
mutex_enter(&so_pendfree_lock);
m->m_next = so_pendfree;
so_pendfree = m;
cv_signal(&pendfree_thread_cv);
mutex_exit(&so_pendfree_lock);
}
static long
sosend_loan(struct socket *so, struct uio *uio, struct mbuf *m, long space)
{
struct iovec *iov = uio->uio_iov;
vaddr_t sva, eva;
vsize_t len;
vaddr_t lva;
int npgs, error;
vaddr_t va;
int i;
if (VMSPACE_IS_KERNEL_P(uio->uio_vmspace))
return 0;
if (iov->iov_len < (size_t) space)
space = iov->iov_len;
if (space > SOCK_LOAN_CHUNK)
space = SOCK_LOAN_CHUNK;
eva = round_page((vaddr_t) iov->iov_base + space);
sva = trunc_page((vaddr_t) iov->iov_base);
len = eva - sva;
npgs = len >> PAGE_SHIFT;
KASSERT(npgs <= M_EXT_MAXPAGES);
lva = sokvaalloc(sva, len, so);
if (lva == 0)
return 0;
error = uvm_loan(&uio->uio_vmspace->vm_map, sva, len,
m->m_ext.ext_pgs, UVM_LOAN_TOPAGE);
if (error) {
sokvafree(lva, len);
return 0;
}
for (i = 0, va = lva; i < npgs; i++, va += PAGE_SIZE)
pmap_kenter_pa(va, VM_PAGE_TO_PHYS(m->m_ext.ext_pgs[i]),
VM_PROT_READ, 0);
pmap_update(pmap_kernel());
lva += (vaddr_t) iov->iov_base & PAGE_MASK;
MEXTADD(m, (void *) lva, space, M_MBUF, soloanfree, so);
m->m_flags |= M_EXT_PAGES | M_EXT_ROMAP;
uio->uio_resid -= space;
/* uio_offset not updated, not set/used for write(2) */
uio->uio_iov->iov_base = (char *)uio->uio_iov->iov_base + space;
uio->uio_iov->iov_len -= space;
if (uio->uio_iov->iov_len == 0) {
uio->uio_iov++;
uio->uio_iovcnt--;
}
return space;
}
static int
socket_listener_cb(kauth_cred_t cred, kauth_action_t action, void *cookie,
void *arg0, void *arg1, void *arg2, void *arg3)
{
int result;
enum kauth_network_req req;
result = KAUTH_RESULT_DEFER;
req = (enum kauth_network_req)(uintptr_t)arg0;
if ((action != KAUTH_NETWORK_SOCKET) &&
(action != KAUTH_NETWORK_BIND))
return result;
switch (req) {
case KAUTH_REQ_NETWORK_BIND_PORT:
result = KAUTH_RESULT_ALLOW;
break;
case KAUTH_REQ_NETWORK_SOCKET_DROP: {
/* Normal users can only drop their own connections. */
struct socket *so = (struct socket *)arg1;
if (so->so_cred && proc_uidmatch(cred, so->so_cred) == 0)
result = KAUTH_RESULT_ALLOW;
break;
}
case KAUTH_REQ_NETWORK_SOCKET_OPEN:
/* We allow "raw" routing/bluetooth sockets to anyone. */
switch ((u_long)arg1) {
case PF_ROUTE:
case PF_OROUTE:
case PF_BLUETOOTH:
case PF_CAN:
result = KAUTH_RESULT_ALLOW;
break;
default:
/* Privileged, let secmodel handle this. */
if ((u_long)arg2 == SOCK_RAW)
break;
result = KAUTH_RESULT_ALLOW;
break;
}
break;
case KAUTH_REQ_NETWORK_SOCKET_CANSEE:
result = KAUTH_RESULT_ALLOW;
break;
default:
break;
}
return result;
}
void
soinit(void)
{
sysctl_kern_socket_setup();
#ifdef SCTP
/* Update the SCTP function hooks if necessary*/
vec_sctp_add_ip_address = sctp_add_ip_address;
vec_sctp_delete_ip_address = sctp_delete_ip_address;
#endif
mutex_init(&so_pendfree_lock, MUTEX_DEFAULT, IPL_VM);
softnet_lock = mutex_obj_alloc(MUTEX_DEFAULT, IPL_NONE);
cv_init(&socurkva_cv, "sokva");
cv_init(&pendfree_thread_cv, "sopendfr");
soinit2();
/* Set the initial adjusted socket buffer size. */
if (sb_max_set(sb_max))
panic("bad initial sb_max value: %lu", sb_max);
socket_listener = kauth_listen_scope(KAUTH_SCOPE_NETWORK,
socket_listener_cb, NULL);
}
void
soinit1(void)
{
int error = kthread_create(PRI_NONE, KTHREAD_MPSAFE, NULL,
sopendfree_thread, NULL, &sopendfree_lwp, "sopendfree");
if (error)
panic("soinit1 %d", error);
}
/*
* socreate: create a new socket of the specified type and the protocol.
*
* => Caller may specify another socket for lock sharing (must not be held).
* => Returns the new socket without lock held.
*/
int
socreate(int dom, struct socket **aso, int type, int proto, struct lwp *l,
struct socket *lockso)
{
const struct protosw *prp;
struct socket *so;
uid_t uid;
int error;
kmutex_t *lock;
error = kauth_authorize_network(l->l_cred, KAUTH_NETWORK_SOCKET,
KAUTH_REQ_NETWORK_SOCKET_OPEN, KAUTH_ARG(dom), KAUTH_ARG(type),
KAUTH_ARG(proto));
if (error != 0)
return error;
if (proto)
prp = pffindproto(dom, proto, type);
else
prp = pffindtype(dom, type);
if (prp == NULL) {
/* no support for domain */
if (pffinddomain(dom) == 0)
return EAFNOSUPPORT;
/* no support for socket type */
if (proto == 0 && type != 0)
return EPROTOTYPE;
return EPROTONOSUPPORT;
}
if (prp->pr_usrreqs == NULL)
return EPROTONOSUPPORT;
if (prp->pr_type != type)
return EPROTOTYPE;
so = soget(true);
so->so_type = type;
so->so_proto = prp;
so->so_send = sosend;
so->so_receive = soreceive;
so->so_options = sooptions;
#ifdef MBUFTRACE
so->so_rcv.sb_mowner = &prp->pr_domain->dom_mowner;
so->so_snd.sb_mowner = &prp->pr_domain->dom_mowner;
so->so_mowner = &prp->pr_domain->dom_mowner;
#endif
uid = kauth_cred_geteuid(l->l_cred);
so->so_uidinfo = uid_find(uid);
so->so_egid = kauth_cred_getegid(l->l_cred);
so->so_cpid = l->l_proc->p_pid;
/*
* Lock assigned and taken during PCB attach, unless we share
* the lock with another socket, e.g. socketpair(2) case.
*/
if (lockso) {
/*
* lockso->so_lock should be stable at this point, so
* no need for atomic_load_*.
*/
lock = lockso->so_lock;
so->so_lock = lock;
mutex_obj_hold(lock);
mutex_enter(lock);
}
/* Attach the PCB (returns with the socket lock held). */
error = (*prp->pr_usrreqs->pr_attach)(so, proto);
KASSERT(solocked(so));
if (error) {
KASSERT(so->so_pcb == NULL);
so->so_state |= SS_NOFDREF;
sofree(so);
return error;
}
so->so_cred = kauth_cred_dup(l->l_cred);
sounlock(so);
*aso = so;
return 0;
}
/*
* fsocreate: create a socket and a file descriptor associated with it.
*
* => On success, write file descriptor to fdout and return zero.
* => On failure, return non-zero; *fdout will be undefined.
*/
int
fsocreate(int domain, struct socket **sop, int type, int proto, int *fdout)
{
lwp_t *l = curlwp;
int error, fd, flags;
struct socket *so;
struct file *fp;
if ((error = fd_allocfile(&fp, &fd)) != 0) {
return error;
}
flags = type & SOCK_FLAGS_MASK;
fd_set_exclose(l, fd, (flags & SOCK_CLOEXEC) != 0);
fp->f_flag = FREAD|FWRITE|((flags & SOCK_NONBLOCK) ? FNONBLOCK : 0)|
((flags & SOCK_NOSIGPIPE) ? FNOSIGPIPE : 0);
fp->f_type = DTYPE_SOCKET;
fp->f_ops = &socketops;
type &= ~SOCK_FLAGS_MASK;
error = socreate(domain, &so, type, proto, l, NULL);
if (error) {
fd_abort(curproc, fp, fd);
return error;
}
if (flags & SOCK_NONBLOCK) {
so->so_state |= SS_NBIO;
}
fp->f_socket = so;
fd_affix(curproc, fp, fd);
if (sop != NULL) {
*sop = so;
}
*fdout = fd;
return error;
}
int
sofamily(const struct socket *so)
{
const struct protosw *pr;
const struct domain *dom;
if ((pr = so->so_proto) == NULL)
return AF_UNSPEC;
if ((dom = pr->pr_domain) == NULL)
return AF_UNSPEC;
return dom->dom_family;
}
int
sobind(struct socket *so, struct sockaddr *nam, struct lwp *l)
{
int error;
solock(so);
if (nam->sa_family != so->so_proto->pr_domain->dom_family) {
sounlock(so);
return EAFNOSUPPORT;
}
error = (*so->so_proto->pr_usrreqs->pr_bind)(so, nam, l);
sounlock(so);
return error;
}
int
solisten(struct socket *so, int backlog, struct lwp *l)
{
int error;
short oldopt, oldqlimit;
solock(so);
if ((so->so_state & (SS_ISCONNECTED | SS_ISCONNECTING |
SS_ISDISCONNECTING)) != 0) {
sounlock(so);
return EINVAL;
}
oldopt = so->so_options;
oldqlimit = so->so_qlimit;
if (TAILQ_EMPTY(&so->so_q))
so->so_options |= SO_ACCEPTCONN;
if (backlog < 0)
backlog = 0;
so->so_qlimit = uimin(backlog, somaxconn);
error = (*so->so_proto->pr_usrreqs->pr_listen)(so, l);
if (error != 0) {
so->so_options = oldopt;
so->so_qlimit = oldqlimit;
sounlock(so);
return error;
}
sounlock(so);
return 0;
}
void
sofree(struct socket *so)
{
u_int refs;
KASSERT(solocked(so));
if (so->so_pcb || (so->so_state & SS_NOFDREF) == 0) {
sounlock(so);
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)) {
sounlock(so);
return;
}
}
if (so->so_rcv.sb_hiwat)
(void)chgsbsize(so->so_uidinfo, &so->so_rcv.sb_hiwat, 0,
RLIM_INFINITY);
if (so->so_snd.sb_hiwat)
(void)chgsbsize(so->so_uidinfo, &so->so_snd.sb_hiwat, 0,
RLIM_INFINITY);
sbrelease(&so->so_snd, so);
KASSERT(!cv_has_waiters(&so->so_cv));
KASSERT(!cv_has_waiters(&so->so_rcv.sb_cv));
KASSERT(!cv_has_waiters(&so->so_snd.sb_cv));
sorflush(so);
refs = so->so_aborting; /* XXX */
/* Remove acccept filter if one is present. */
if (so->so_accf != NULL)
(void)accept_filt_clear(so);
sounlock(so);
if (refs == 0) /* XXX */
soput(so);
}
/*
* soclose: 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 error = 0;
solock(so);
if (so->so_options & SO_ACCEPTCONN) {
for (;;) {
if ((so2 = TAILQ_FIRST(&so->so_q0)) != 0) {
KASSERT(solocked2(so, so2));
(void) soqremque(so2, 0);
/* soabort drops the lock. */
(void) soabort(so2);
solock(so);
continue;
}
if ((so2 = TAILQ_FIRST(&so->so_q)) != 0) {
KASSERT(solocked2(so, so2));
(void) soqremque(so2, 1);
/* soabort drops the lock. */
(void) soabort(so2);
solock(so);
continue;
}
break;
}
}
if (so->so_pcb == NULL)
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|SS_NBIO)) ==
(SS_ISDISCONNECTING|SS_NBIO))
goto drop;
while (so->so_state & SS_ISCONNECTED) {
error = sowait(so, true, so->so_linger * hz);
if (error)
break;
}
}
}
drop:
if (so->so_pcb) {
KASSERT(solocked(so));
(*so->so_proto->pr_usrreqs->pr_detach)(so);
}
discard:
KASSERT((so->so_state & SS_NOFDREF) == 0);
kauth_cred_free(so->so_cred);
so->so_cred = NULL;
so->so_state |= SS_NOFDREF;
sofree(so);
return error;
}
/*
* Must be called with the socket locked.. Will return with it unlocked.
*/
int
soabort(struct socket *so)
{
u_int refs;
int error;
KASSERT(solocked(so));
KASSERT(so->so_head == NULL);
so->so_aborting++; /* XXX */
error = (*so->so_proto->pr_usrreqs->pr_abort)(so);
refs = --so->so_aborting; /* XXX */
if (error || (refs == 0)) {
sofree(so);
} else {
sounlock(so);
}
return error;
}
int
soaccept(struct socket *so, struct sockaddr *nam)
{
int error;
KASSERT(solocked(so));
KASSERT((so->so_state & SS_NOFDREF) != 0);
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_usrreqs->pr_accept)(so, nam);
else
error = ECONNABORTED;
return error;
}
int
soconnect(struct socket *so, struct sockaddr *nam, struct lwp *l)
{
int error;
KASSERT(solocked(so));
if (so->so_options & SO_ACCEPTCONN)
return EOPNOTSUPP;
/*
* 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 {
if (nam->sa_family != so->so_proto->pr_domain->dom_family) {
return EAFNOSUPPORT;
}
error = (*so->so_proto->pr_usrreqs->pr_connect)(so, nam, l);
}
return error;
}
int
soconnect2(struct socket *so1, struct socket *so2)
{
KASSERT(solocked2(so1, so2));
return (*so1->so_proto->pr_usrreqs->pr_connect2)(so1, so2);
}
int
sodisconnect(struct socket *so)
{
int error;
KASSERT(solocked(so));
if ((so->so_state & SS_ISCONNECTED) == 0) {
error = ENOTCONN;
} else if (so->so_state & SS_ISDISCONNECTING) {
error = EALREADY;
} else {
error = (*so->so_proto->pr_usrreqs->pr_disconnect)(so);
}
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 sockaddr *addr, struct uio *uio,
struct mbuf *top, struct mbuf *control, int flags, struct lwp *l)
{
struct mbuf **mp, *m;
long space, len, resid, clen, mlen;
int error, s, dontroute, atomic;
short wakeup_state = 0;
clen = 0;
/*
* solock() provides atomicity of access. splsoftnet() prevents
* protocol processing soft interrupts from interrupting us and
* blocking (expensive).
*/
s = splsoftnet();
solock(so);
atomic = sosendallatonce(so) || top;
if (uio)
resid = uio->uio_resid;
else
resid = top->m_pkthdr.len;
/*
* In theory resid should be unsigned.
* 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.
*/
if (resid < 0) {
error = EINVAL;
goto out;
}
dontroute =
(flags & MSG_DONTROUTE) && (so->so_options & SO_DONTROUTE) == 0 &&
(so->so_proto->pr_flags & PR_ATOMIC);
l->l_ru.ru_msgsnd++;
if (control)
clen = control->m_len;
restart:
if ((error = sblock(&so->so_snd, SBLOCKWAIT(flags))) != 0)
goto out;
do {
if (so->so_state & SS_CANTSENDMORE) {
error = EPIPE;
goto release;
}
if (so->so_error) {
error = so->so_error;
if ((flags & MSG_PEEK) == 0)
so->so_error = 0;
goto release;
}
if ((so->so_state & SS_ISCONNECTED) == 0) {
if (so->so_proto->pr_flags & PR_CONNREQUIRED) {
if (resid || clen == 0) {
error = ENOTCONN;
goto release;
}
} else if (addr == NULL) {
error = EDESTADDRREQ;
goto release;
}
}
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) {
error = EMSGSIZE;
goto release;
}
if (space < resid + clen &&
(atomic || space < so->so_snd.sb_lowat || space < clen)) {
if ((so->so_state & SS_NBIO) || (flags & MSG_NBIO)) {
error = EWOULDBLOCK;
goto release;
}
sbunlock(&so->so_snd);
if (wakeup_state & SS_RESTARTSYS) {
error = ERESTART;
goto out;
}
error = sbwait(&so->so_snd);
if (error)
goto out;
wakeup_state = so->so_state;
goto restart;
}
wakeup_state = 0;
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 {
sounlock(so);
splx(s);
if (top == NULL) {
m = m_gethdr(M_WAIT, MT_DATA);
mlen = MHLEN;
m->m_pkthdr.len = 0;
m_reset_rcvif(m);
} else {