-
Notifications
You must be signed in to change notification settings - Fork 2.9k
/
sys_generic.c
1914 lines (1751 loc) · 42.5 KB
/
sys_generic.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
/*-
* SPDX-License-Identifier: BSD-3-Clause
*
* Copyright (c) 1982, 1986, 1989, 1993
* The Regents of the University of California. All rights reserved.
* (c) UNIX System Laboratories, Inc.
* All or some portions of this file are derived from material licensed
* to the University of California by American Telephone and Telegraph
* Co. or Unix System Laboratories, Inc. and are reproduced herein with
* the permission of UNIX System Laboratories, 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.
* 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.
*
* @(#)sys_generic.c 8.5 (Berkeley) 1/21/94
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include "opt_capsicum.h"
#include "opt_ktrace.h"
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/sysproto.h>
#include <sys/capsicum.h>
#include <sys/filedesc.h>
#include <sys/filio.h>
#include <sys/fcntl.h>
#include <sys/file.h>
#include <sys/lock.h>
#include <sys/proc.h>
#include <sys/signalvar.h>
#include <sys/socketvar.h>
#include <sys/uio.h>
#include <sys/kernel.h>
#include <sys/ktr.h>
#include <sys/limits.h>
#include <sys/malloc.h>
#include <sys/poll.h>
#include <sys/resourcevar.h>
#include <sys/selinfo.h>
#include <sys/sleepqueue.h>
#include <sys/syscallsubr.h>
#include <sys/sysctl.h>
#include <sys/sysent.h>
#include <sys/vnode.h>
#include <sys/bio.h>
#include <sys/buf.h>
#include <sys/condvar.h>
#ifdef KTRACE
#include <sys/ktrace.h>
#endif
#include <security/audit/audit.h>
/*
* The following macro defines how many bytes will be allocated from
* the stack instead of memory allocated when passing the IOCTL data
* structures from userspace and to the kernel. Some IOCTLs having
* small data structures are used very frequently and this small
* buffer on the stack gives a significant speedup improvement for
* those requests. The value of this define should be greater or equal
* to 64 bytes and should also be power of two. The data structure is
* currently hard-aligned to a 8-byte boundary on the stack. This
* should currently be sufficient for all supported platforms.
*/
#define SYS_IOCTL_SMALL_SIZE 128 /* bytes */
#define SYS_IOCTL_SMALL_ALIGN 8 /* bytes */
#ifdef __LP64__
static int iosize_max_clamp = 0;
SYSCTL_INT(_debug, OID_AUTO, iosize_max_clamp, CTLFLAG_RW,
&iosize_max_clamp, 0, "Clamp max i/o size to INT_MAX");
static int devfs_iosize_max_clamp = 1;
SYSCTL_INT(_debug, OID_AUTO, devfs_iosize_max_clamp, CTLFLAG_RW,
&devfs_iosize_max_clamp, 0, "Clamp max i/o size to INT_MAX for devices");
#endif
/*
* Assert that the return value of read(2) and write(2) syscalls fits
* into a register. If not, an architecture will need to provide the
* usermode wrappers to reconstruct the result.
*/
CTASSERT(sizeof(register_t) >= sizeof(size_t));
static MALLOC_DEFINE(M_IOCTLOPS, "ioctlops", "ioctl data buffer");
static MALLOC_DEFINE(M_SELECT, "select", "select() buffer");
MALLOC_DEFINE(M_IOV, "iov", "large iov's");
static int pollout(struct thread *, struct pollfd *, struct pollfd *,
u_int);
static int pollscan(struct thread *, struct pollfd *, u_int);
static int pollrescan(struct thread *);
static int selscan(struct thread *, fd_mask **, fd_mask **, int);
static int selrescan(struct thread *, fd_mask **, fd_mask **);
static void selfdalloc(struct thread *, void *);
static void selfdfree(struct seltd *, struct selfd *);
static int dofileread(struct thread *, int, struct file *, struct uio *,
off_t, int);
static int dofilewrite(struct thread *, int, struct file *, struct uio *,
off_t, int);
static void doselwakeup(struct selinfo *, int);
static void seltdinit(struct thread *);
static int seltdwait(struct thread *, sbintime_t, sbintime_t);
static void seltdclear(struct thread *);
/*
* One seltd per-thread allocated on demand as needed.
*
* t - protected by st_mtx
* k - Only accessed by curthread or read-only
*/
struct seltd {
STAILQ_HEAD(, selfd) st_selq; /* (k) List of selfds. */
struct selfd *st_free1; /* (k) free fd for read set. */
struct selfd *st_free2; /* (k) free fd for write set. */
struct mtx st_mtx; /* Protects struct seltd */
struct cv st_wait; /* (t) Wait channel. */
int st_flags; /* (t) SELTD_ flags. */
};
#define SELTD_PENDING 0x0001 /* We have pending events. */
#define SELTD_RESCAN 0x0002 /* Doing a rescan. */
/*
* One selfd allocated per-thread per-file-descriptor.
* f - protected by sf_mtx
*/
struct selfd {
STAILQ_ENTRY(selfd) sf_link; /* (k) fds owned by this td. */
TAILQ_ENTRY(selfd) sf_threads; /* (f) fds on this selinfo. */
struct selinfo *sf_si; /* (f) selinfo when linked. */
struct mtx *sf_mtx; /* Pointer to selinfo mtx. */
struct seltd *sf_td; /* (k) owning seltd. */
void *sf_cookie; /* (k) fd or pollfd. */
u_int sf_refs;
};
static uma_zone_t selfd_zone;
static struct mtx_pool *mtxpool_select;
#ifdef __LP64__
size_t
devfs_iosize_max(void)
{
return (devfs_iosize_max_clamp || SV_CURPROC_FLAG(SV_ILP32) ?
INT_MAX : SSIZE_MAX);
}
size_t
iosize_max(void)
{
return (iosize_max_clamp || SV_CURPROC_FLAG(SV_ILP32) ?
INT_MAX : SSIZE_MAX);
}
#endif
#ifndef _SYS_SYSPROTO_H_
struct read_args {
int fd;
void *buf;
size_t nbyte;
};
#endif
int
sys_read(struct thread *td, struct read_args *uap)
{
struct uio auio;
struct iovec aiov;
int error;
if (uap->nbyte > IOSIZE_MAX)
return (EINVAL);
aiov.iov_base = uap->buf;
aiov.iov_len = uap->nbyte;
auio.uio_iov = &aiov;
auio.uio_iovcnt = 1;
auio.uio_resid = uap->nbyte;
auio.uio_segflg = UIO_USERSPACE;
error = kern_readv(td, uap->fd, &auio);
return (error);
}
/*
* Positioned read system call
*/
#ifndef _SYS_SYSPROTO_H_
struct pread_args {
int fd;
void *buf;
size_t nbyte;
int pad;
off_t offset;
};
#endif
int
sys_pread(struct thread *td, struct pread_args *uap)
{
return (kern_pread(td, uap->fd, uap->buf, uap->nbyte, uap->offset));
}
int
kern_pread(struct thread *td, int fd, void *buf, size_t nbyte, off_t offset)
{
struct uio auio;
struct iovec aiov;
int error;
if (nbyte > IOSIZE_MAX)
return (EINVAL);
aiov.iov_base = buf;
aiov.iov_len = nbyte;
auio.uio_iov = &aiov;
auio.uio_iovcnt = 1;
auio.uio_resid = nbyte;
auio.uio_segflg = UIO_USERSPACE;
error = kern_preadv(td, fd, &auio, offset);
return (error);
}
#if defined(COMPAT_FREEBSD6)
int
freebsd6_pread(struct thread *td, struct freebsd6_pread_args *uap)
{
return (kern_pread(td, uap->fd, uap->buf, uap->nbyte, uap->offset));
}
#endif
/*
* Scatter read system call.
*/
#ifndef _SYS_SYSPROTO_H_
struct readv_args {
int fd;
struct iovec *iovp;
u_int iovcnt;
};
#endif
int
sys_readv(struct thread *td, struct readv_args *uap)
{
struct uio *auio;
int error;
error = copyinuio(uap->iovp, uap->iovcnt, &auio);
if (error)
return (error);
error = kern_readv(td, uap->fd, auio);
free(auio, M_IOV);
return (error);
}
int
kern_readv(struct thread *td, int fd, struct uio *auio)
{
struct file *fp;
int error;
error = fget_read(td, fd, &cap_read_rights, &fp);
if (error)
return (error);
error = dofileread(td, fd, fp, auio, (off_t)-1, 0);
fdrop(fp, td);
return (error);
}
/*
* Scatter positioned read system call.
*/
#ifndef _SYS_SYSPROTO_H_
struct preadv_args {
int fd;
struct iovec *iovp;
u_int iovcnt;
off_t offset;
};
#endif
int
sys_preadv(struct thread *td, struct preadv_args *uap)
{
struct uio *auio;
int error;
error = copyinuio(uap->iovp, uap->iovcnt, &auio);
if (error)
return (error);
error = kern_preadv(td, uap->fd, auio, uap->offset);
free(auio, M_IOV);
return (error);
}
int
kern_preadv(struct thread *td, int fd, struct uio *auio, off_t offset)
{
struct file *fp;
int error;
error = fget_read(td, fd, &cap_pread_rights, &fp);
if (error)
return (error);
if (!(fp->f_ops->fo_flags & DFLAG_SEEKABLE))
error = ESPIPE;
else if (offset < 0 &&
(fp->f_vnode == NULL || fp->f_vnode->v_type != VCHR))
error = EINVAL;
else
error = dofileread(td, fd, fp, auio, offset, FOF_OFFSET);
fdrop(fp, td);
return (error);
}
/*
* Common code for readv and preadv that reads data in
* from a file using the passed in uio, offset, and flags.
*/
static int
dofileread(struct thread *td, int fd, struct file *fp, struct uio *auio,
off_t offset, int flags)
{
ssize_t cnt;
int error;
#ifdef KTRACE
struct uio *ktruio = NULL;
#endif
AUDIT_ARG_FD(fd);
/* Finish zero length reads right here */
if (auio->uio_resid == 0) {
td->td_retval[0] = 0;
return (0);
}
auio->uio_rw = UIO_READ;
auio->uio_offset = offset;
auio->uio_td = td;
#ifdef KTRACE
if (KTRPOINT(td, KTR_GENIO))
ktruio = cloneuio(auio);
#endif
cnt = auio->uio_resid;
if ((error = fo_read(fp, auio, td->td_ucred, flags, td))) {
if (auio->uio_resid != cnt && (error == ERESTART ||
error == EINTR || error == EWOULDBLOCK))
error = 0;
}
cnt -= auio->uio_resid;
#ifdef KTRACE
if (ktruio != NULL) {
ktruio->uio_resid = cnt;
ktrgenio(fd, UIO_READ, ktruio, error);
}
#endif
td->td_retval[0] = cnt;
return (error);
}
#ifndef _SYS_SYSPROTO_H_
struct write_args {
int fd;
const void *buf;
size_t nbyte;
};
#endif
int
sys_write(struct thread *td, struct write_args *uap)
{
struct uio auio;
struct iovec aiov;
int error;
if (uap->nbyte > IOSIZE_MAX)
return (EINVAL);
aiov.iov_base = (void *)(uintptr_t)uap->buf;
aiov.iov_len = uap->nbyte;
auio.uio_iov = &aiov;
auio.uio_iovcnt = 1;
auio.uio_resid = uap->nbyte;
auio.uio_segflg = UIO_USERSPACE;
error = kern_writev(td, uap->fd, &auio);
return (error);
}
/*
* Positioned write system call.
*/
#ifndef _SYS_SYSPROTO_H_
struct pwrite_args {
int fd;
const void *buf;
size_t nbyte;
int pad;
off_t offset;
};
#endif
int
sys_pwrite(struct thread *td, struct pwrite_args *uap)
{
return (kern_pwrite(td, uap->fd, uap->buf, uap->nbyte, uap->offset));
}
int
kern_pwrite(struct thread *td, int fd, const void *buf, size_t nbyte,
off_t offset)
{
struct uio auio;
struct iovec aiov;
int error;
if (nbyte > IOSIZE_MAX)
return (EINVAL);
aiov.iov_base = (void *)(uintptr_t)buf;
aiov.iov_len = nbyte;
auio.uio_iov = &aiov;
auio.uio_iovcnt = 1;
auio.uio_resid = nbyte;
auio.uio_segflg = UIO_USERSPACE;
error = kern_pwritev(td, fd, &auio, offset);
return (error);
}
#if defined(COMPAT_FREEBSD6)
int
freebsd6_pwrite(struct thread *td, struct freebsd6_pwrite_args *uap)
{
return (kern_pwrite(td, uap->fd, uap->buf, uap->nbyte, uap->offset));
}
#endif
/*
* Gather write system call.
*/
#ifndef _SYS_SYSPROTO_H_
struct writev_args {
int fd;
struct iovec *iovp;
u_int iovcnt;
};
#endif
int
sys_writev(struct thread *td, struct writev_args *uap)
{
struct uio *auio;
int error;
error = copyinuio(uap->iovp, uap->iovcnt, &auio);
if (error)
return (error);
error = kern_writev(td, uap->fd, auio);
free(auio, M_IOV);
return (error);
}
int
kern_writev(struct thread *td, int fd, struct uio *auio)
{
struct file *fp;
int error;
error = fget_write(td, fd, &cap_write_rights, &fp);
if (error)
return (error);
error = dofilewrite(td, fd, fp, auio, (off_t)-1, 0);
fdrop(fp, td);
return (error);
}
/*
* Gather positioned write system call.
*/
#ifndef _SYS_SYSPROTO_H_
struct pwritev_args {
int fd;
struct iovec *iovp;
u_int iovcnt;
off_t offset;
};
#endif
int
sys_pwritev(struct thread *td, struct pwritev_args *uap)
{
struct uio *auio;
int error;
error = copyinuio(uap->iovp, uap->iovcnt, &auio);
if (error)
return (error);
error = kern_pwritev(td, uap->fd, auio, uap->offset);
free(auio, M_IOV);
return (error);
}
int
kern_pwritev(struct thread *td, int fd, struct uio *auio, off_t offset)
{
struct file *fp;
int error;
error = fget_write(td, fd, &cap_pwrite_rights, &fp);
if (error)
return (error);
if (!(fp->f_ops->fo_flags & DFLAG_SEEKABLE))
error = ESPIPE;
else if (offset < 0 &&
(fp->f_vnode == NULL || fp->f_vnode->v_type != VCHR))
error = EINVAL;
else
error = dofilewrite(td, fd, fp, auio, offset, FOF_OFFSET);
fdrop(fp, td);
return (error);
}
/*
* Common code for writev and pwritev that writes data to
* a file using the passed in uio, offset, and flags.
*/
static int
dofilewrite(struct thread *td, int fd, struct file *fp, struct uio *auio,
off_t offset, int flags)
{
ssize_t cnt;
int error;
#ifdef KTRACE
struct uio *ktruio = NULL;
#endif
AUDIT_ARG_FD(fd);
auio->uio_rw = UIO_WRITE;
auio->uio_td = td;
auio->uio_offset = offset;
#ifdef KTRACE
if (KTRPOINT(td, KTR_GENIO))
ktruio = cloneuio(auio);
#endif
cnt = auio->uio_resid;
if ((error = fo_write(fp, auio, td->td_ucred, flags, td))) {
if (auio->uio_resid != cnt && (error == ERESTART ||
error == EINTR || error == EWOULDBLOCK))
error = 0;
/* Socket layer is responsible for issuing SIGPIPE. */
if (fp->f_type != DTYPE_SOCKET && error == EPIPE) {
PROC_LOCK(td->td_proc);
tdsignal(td, SIGPIPE);
PROC_UNLOCK(td->td_proc);
}
}
cnt -= auio->uio_resid;
#ifdef KTRACE
if (ktruio != NULL) {
ktruio->uio_resid = cnt;
ktrgenio(fd, UIO_WRITE, ktruio, error);
}
#endif
td->td_retval[0] = cnt;
return (error);
}
/*
* Truncate a file given a file descriptor.
*
* Can't use fget_write() here, since must return EINVAL and not EBADF if the
* descriptor isn't writable.
*/
int
kern_ftruncate(struct thread *td, int fd, off_t length)
{
struct file *fp;
int error;
AUDIT_ARG_FD(fd);
if (length < 0)
return (EINVAL);
error = fget(td, fd, &cap_ftruncate_rights, &fp);
if (error)
return (error);
AUDIT_ARG_FILE(td->td_proc, fp);
if (!(fp->f_flag & FWRITE)) {
fdrop(fp, td);
return (EINVAL);
}
error = fo_truncate(fp, length, td->td_ucred, td);
fdrop(fp, td);
return (error);
}
#ifndef _SYS_SYSPROTO_H_
struct ftruncate_args {
int fd;
int pad;
off_t length;
};
#endif
int
sys_ftruncate(struct thread *td, struct ftruncate_args *uap)
{
return (kern_ftruncate(td, uap->fd, uap->length));
}
#if defined(COMPAT_43)
#ifndef _SYS_SYSPROTO_H_
struct oftruncate_args {
int fd;
long length;
};
#endif
int
oftruncate(struct thread *td, struct oftruncate_args *uap)
{
return (kern_ftruncate(td, uap->fd, uap->length));
}
#endif /* COMPAT_43 */
#ifndef _SYS_SYSPROTO_H_
struct ioctl_args {
int fd;
u_long com;
caddr_t data;
};
#endif
/* ARGSUSED */
int
sys_ioctl(struct thread *td, struct ioctl_args *uap)
{
u_char smalldata[SYS_IOCTL_SMALL_SIZE] __aligned(SYS_IOCTL_SMALL_ALIGN);
u_long com;
int arg, error;
u_int size;
caddr_t data;
if (uap->com > 0xffffffff) {
printf(
"WARNING pid %d (%s): ioctl sign-extension ioctl %lx\n",
td->td_proc->p_pid, td->td_name, uap->com);
uap->com &= 0xffffffff;
}
com = uap->com;
/*
* Interpret high order word to find amount of data to be
* copied to/from the user's address space.
*/
size = IOCPARM_LEN(com);
if ((size > IOCPARM_MAX) ||
((com & (IOC_VOID | IOC_IN | IOC_OUT)) == 0) ||
#if defined(COMPAT_FREEBSD5) || defined(COMPAT_FREEBSD4) || defined(COMPAT_43)
((com & IOC_OUT) && size == 0) ||
#else
((com & (IOC_IN | IOC_OUT)) && size == 0) ||
#endif
((com & IOC_VOID) && size > 0 && size != sizeof(int)))
return (ENOTTY);
if (size > 0) {
if (com & IOC_VOID) {
/* Integer argument. */
arg = (intptr_t)uap->data;
data = (void *)&arg;
size = 0;
} else {
if (size > SYS_IOCTL_SMALL_SIZE)
data = malloc((u_long)size, M_IOCTLOPS, M_WAITOK);
else
data = smalldata;
}
} else
data = (void *)&uap->data;
if (com & IOC_IN) {
error = copyin(uap->data, data, (u_int)size);
if (error != 0)
goto out;
} else if (com & IOC_OUT) {
/*
* Zero the buffer so the user always
* gets back something deterministic.
*/
bzero(data, size);
}
error = kern_ioctl(td, uap->fd, com, data);
if (error == 0 && (com & IOC_OUT))
error = copyout(data, uap->data, (u_int)size);
out:
if (size > SYS_IOCTL_SMALL_SIZE)
free(data, M_IOCTLOPS);
return (error);
}
int
kern_ioctl(struct thread *td, int fd, u_long com, caddr_t data)
{
struct file *fp;
struct filedesc *fdp;
int error, tmp, locked;
AUDIT_ARG_FD(fd);
AUDIT_ARG_CMD(com);
fdp = td->td_proc->p_fd;
switch (com) {
case FIONCLEX:
case FIOCLEX:
FILEDESC_XLOCK(fdp);
locked = LA_XLOCKED;
break;
default:
#ifdef CAPABILITIES
FILEDESC_SLOCK(fdp);
locked = LA_SLOCKED;
#else
locked = LA_UNLOCKED;
#endif
break;
}
#ifdef CAPABILITIES
if ((fp = fget_locked(fdp, fd)) == NULL) {
error = EBADF;
goto out;
}
if ((error = cap_ioctl_check(fdp, fd, com)) != 0) {
fp = NULL; /* fhold() was not called yet */
goto out;
}
if (!fhold(fp)) {
error = EBADF;
fp = NULL;
goto out;
}
if (locked == LA_SLOCKED) {
FILEDESC_SUNLOCK(fdp);
locked = LA_UNLOCKED;
}
#else
error = fget(td, fd, &cap_ioctl_rights, &fp);
if (error != 0) {
fp = NULL;
goto out;
}
#endif
if ((fp->f_flag & (FREAD | FWRITE)) == 0) {
error = EBADF;
goto out;
}
switch (com) {
case FIONCLEX:
fdp->fd_ofiles[fd].fde_flags &= ~UF_EXCLOSE;
goto out;
case FIOCLEX:
fdp->fd_ofiles[fd].fde_flags |= UF_EXCLOSE;
goto out;
case FIONBIO:
if ((tmp = *(int *)data))
atomic_set_int(&fp->f_flag, FNONBLOCK);
else
atomic_clear_int(&fp->f_flag, FNONBLOCK);
data = (void *)&tmp;
break;
case FIOASYNC:
if ((tmp = *(int *)data))
atomic_set_int(&fp->f_flag, FASYNC);
else
atomic_clear_int(&fp->f_flag, FASYNC);
data = (void *)&tmp;
break;
}
error = fo_ioctl(fp, com, data, td->td_ucred, td);
out:
switch (locked) {
case LA_XLOCKED:
FILEDESC_XUNLOCK(fdp);
break;
#ifdef CAPABILITIES
case LA_SLOCKED:
FILEDESC_SUNLOCK(fdp);
break;
#endif
default:
FILEDESC_UNLOCK_ASSERT(fdp);
break;
}
if (fp != NULL)
fdrop(fp, td);
return (error);
}
int
sys_posix_fallocate(struct thread *td, struct posix_fallocate_args *uap)
{
int error;
error = kern_posix_fallocate(td, uap->fd, uap->offset, uap->len);
return (kern_posix_error(td, error));
}
int
kern_posix_fallocate(struct thread *td, int fd, off_t offset, off_t len)
{
struct file *fp;
int error;
AUDIT_ARG_FD(fd);
if (offset < 0 || len <= 0)
return (EINVAL);
/* Check for wrap. */
if (offset > OFF_MAX - len)
return (EFBIG);
AUDIT_ARG_FD(fd);
error = fget(td, fd, &cap_pwrite_rights, &fp);
if (error != 0)
return (error);
AUDIT_ARG_FILE(td->td_proc, fp);
if ((fp->f_ops->fo_flags & DFLAG_SEEKABLE) == 0) {
error = ESPIPE;
goto out;
}
if ((fp->f_flag & FWRITE) == 0) {
error = EBADF;
goto out;
}
error = fo_fallocate(fp, offset, len, td);
out:
fdrop(fp, td);
return (error);
}
int
poll_no_poll(int events)
{
/*
* Return true for read/write. If the user asked for something
* special, return POLLNVAL, so that clients have a way of
* determining reliably whether or not the extended
* functionality is present without hard-coding knowledge
* of specific filesystem implementations.
*/
if (events & ~POLLSTANDARD)
return (POLLNVAL);
return (events & (POLLIN | POLLOUT | POLLRDNORM | POLLWRNORM));
}
int
sys_pselect(struct thread *td, struct pselect_args *uap)
{
struct timespec ts;
struct timeval tv, *tvp;
sigset_t set, *uset;
int error;
if (uap->ts != NULL) {
error = copyin(uap->ts, &ts, sizeof(ts));
if (error != 0)
return (error);
TIMESPEC_TO_TIMEVAL(&tv, &ts);
tvp = &tv;
} else
tvp = NULL;
if (uap->sm != NULL) {
error = copyin(uap->sm, &set, sizeof(set));
if (error != 0)
return (error);
uset = &set;
} else
uset = NULL;
return (kern_pselect(td, uap->nd, uap->in, uap->ou, uap->ex, tvp,
uset, NFDBITS));
}
int
kern_pselect(struct thread *td, int nd, fd_set *in, fd_set *ou, fd_set *ex,
struct timeval *tvp, sigset_t *uset, int abi_nfdbits)
{
int error;
if (uset != NULL) {
error = kern_sigprocmask(td, SIG_SETMASK, uset,
&td->td_oldsigmask, 0);
if (error != 0)
return (error);
td->td_pflags |= TDP_OLDMASK;
/*
* Make sure that ast() is called on return to
* usermode and TDP_OLDMASK is cleared, restoring old
* sigmask.
*/
thread_lock(td);
td->td_flags |= TDF_ASTPENDING;
thread_unlock(td);
}
error = kern_select(td, nd, in, ou, ex, tvp, abi_nfdbits);
return (error);
}
#ifndef _SYS_SYSPROTO_H_
struct select_args {
int nd;
fd_set *in, *ou, *ex;
struct timeval *tv;
};
#endif
int
sys_select(struct thread *td, struct select_args *uap)
{
struct timeval tv, *tvp;
int error;
if (uap->tv != NULL) {
error = copyin(uap->tv, &tv, sizeof(tv));
if (error)
return (error);
tvp = &tv;
} else
tvp = NULL;
return (kern_select(td, uap->nd, uap->in, uap->ou, uap->ex, tvp,
NFDBITS));
}
/*
* In the unlikely case when user specified n greater then the last
* open file descriptor, check that no bits are set after the last
* valid fd. We must return EBADF if any is set.
*
* There are applications that rely on the behaviour.
*
* nd is fd_lastfile + 1.
*/
static int
select_check_badfd(fd_set *fd_in, int nd, int ndu, int abi_nfdbits)
{
char *addr, *oaddr;
int b, i, res;
uint8_t bits;
if (nd >= ndu || fd_in == NULL)
return (0);
oaddr = NULL;
bits = 0; /* silence gcc */
for (i = nd; i < ndu; i++) {
b = i / NBBY;
#if BYTE_ORDER == LITTLE_ENDIAN
addr = (char *)fd_in + b;
#else
addr = (char *)fd_in;
if (abi_nfdbits == NFDBITS) {
addr += rounddown(b, sizeof(fd_mask)) +
sizeof(fd_mask) - 1 - b % sizeof(fd_mask);
} else {
addr += rounddown(b, sizeof(uint32_t)) +
sizeof(uint32_t) - 1 - b % sizeof(uint32_t);
}
#endif
if (addr != oaddr) {
res = fubyte(addr);
if (res == -1)
return (EFAULT);
oaddr = addr;
bits = res;
}
if ((bits & (1 << (i % NBBY))) != 0)
return (EBADF);
}
return (0);