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
|
/* $OpenBSD: vfs_vnops.c,v 1.105 2019/08/12 08:17:05 anton Exp $ */
/* $NetBSD: vfs_vnops.c,v 1.20 1996/02/04 02:18:41 christos Exp $ */
/*
* 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.
*
* @(#)vfs_vnops.c 8.5 (Berkeley) 12/8/94
*/
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/malloc.h>
#include <sys/fcntl.h>
#include <sys/file.h>
#include <sys/stat.h>
#include <sys/proc.h>
#include <sys/resourcevar.h>
#include <sys/signalvar.h>
#include <sys/mount.h>
#include <sys/namei.h>
#include <sys/lock.h>
#include <sys/vnode.h>
#include <sys/ioctl.h>
#include <sys/tty.h>
#include <sys/cdio.h>
#include <sys/poll.h>
#include <sys/filedesc.h>
#include <sys/specdev.h>
#include <sys/unistd.h>
int vn_read(struct file *, struct uio *, int);
int vn_write(struct file *, struct uio *, int);
int vn_poll(struct file *, int, struct proc *);
int vn_kqfilter(struct file *, struct knote *);
int vn_closefile(struct file *, struct proc *);
int vn_seek(struct file *, off_t *, int, struct proc *);
struct fileops vnops = {
.fo_read = vn_read,
.fo_write = vn_write,
.fo_ioctl = vn_ioctl,
.fo_poll = vn_poll,
.fo_kqfilter = vn_kqfilter,
.fo_stat = vn_statfile,
.fo_close = vn_closefile,
.fo_seek = vn_seek,
};
/*
* Common code for vnode open operations.
* Check permissions, and call the VOP_OPEN or VOP_CREATE routine.
*/
int
vn_open(struct nameidata *ndp, int fmode, int cmode)
{
struct vnode *vp;
struct proc *p = ndp->ni_cnd.cn_proc;
struct ucred *cred = p->p_ucred;
struct vattr va;
struct cloneinfo *cip;
int error;
if ((fmode & (FREAD|FWRITE)) == 0)
return (EINVAL);
if ((fmode & (O_TRUNC | FWRITE)) == O_TRUNC)
return (EINVAL);
if (fmode & O_CREAT) {
ndp->ni_cnd.cn_nameiop = CREATE;
ndp->ni_cnd.cn_flags = LOCKPARENT | LOCKLEAF;
if ((fmode & O_EXCL) == 0 && (fmode & O_NOFOLLOW) == 0)
ndp->ni_cnd.cn_flags |= FOLLOW;
if ((error = namei(ndp)) != 0)
return (error);
if (ndp->ni_vp == NULL) {
VATTR_NULL(&va);
va.va_type = VREG;
va.va_mode = cmode;
if (fmode & O_EXCL)
va.va_vaflags |= VA_EXCLUSIVE;
error = VOP_CREATE(ndp->ni_dvp, &ndp->ni_vp,
&ndp->ni_cnd, &va);
vput(ndp->ni_dvp);
if (error)
return (error);
fmode &= ~O_TRUNC;
vp = ndp->ni_vp;
} else {
VOP_ABORTOP(ndp->ni_dvp, &ndp->ni_cnd);
if (ndp->ni_dvp == ndp->ni_vp)
vrele(ndp->ni_dvp);
else
vput(ndp->ni_dvp);
ndp->ni_dvp = NULL;
vp = ndp->ni_vp;
if (fmode & O_EXCL) {
error = EEXIST;
goto bad;
}
fmode &= ~O_CREAT;
}
} else {
ndp->ni_cnd.cn_nameiop = LOOKUP;
ndp->ni_cnd.cn_flags =
((fmode & O_NOFOLLOW) ? NOFOLLOW : FOLLOW) | LOCKLEAF;
if ((error = namei(ndp)) != 0)
return (error);
vp = ndp->ni_vp;
}
if (vp->v_type == VSOCK) {
error = EOPNOTSUPP;
goto bad;
}
if (vp->v_type == VLNK) {
error = ELOOP;
goto bad;
}
if ((fmode & O_DIRECTORY) && vp->v_type != VDIR) {
error = ENOTDIR;
goto bad;
}
if ((fmode & O_CREAT) == 0) {
if (fmode & FREAD) {
if ((error = VOP_ACCESS(vp, VREAD, cred, p)) != 0)
goto bad;
}
if (fmode & FWRITE) {
if (vp->v_type == VDIR) {
error = EISDIR;
goto bad;
}
if ((error = vn_writechk(vp)) != 0 ||
(error = VOP_ACCESS(vp, VWRITE, cred, p)) != 0)
goto bad;
}
}
if ((fmode & O_TRUNC) && vp->v_type == VREG) {
VATTR_NULL(&va);
va.va_size = 0;
if ((error = VOP_SETATTR(vp, &va, cred, p)) != 0)
goto bad;
}
if ((error = VOP_OPEN(vp, fmode, cred, p)) != 0)
goto bad;
if (vp->v_flag & VCLONED) {
cip = (struct cloneinfo *)vp->v_data;
vp->v_flag &= ~VCLONED;
ndp->ni_vp = cip->ci_vp; /* return cloned vnode */
vp->v_data = cip->ci_data; /* restore v_data */
VOP_UNLOCK(vp); /* keep a reference */
vp = ndp->ni_vp; /* for the increment below */
free(cip, M_TEMP, sizeof(*cip));
}
if (fmode & FWRITE)
vp->v_writecount++;
return (0);
bad:
vput(vp);
return (error);
}
/*
* Check for write permissions on the specified vnode.
* Prototype text segments cannot be written.
*/
int
vn_writechk(struct vnode *vp)
{
/*
* Disallow write attempts on read-only file systems;
* unless the file is a socket or a block or character
* device resident on the file system.
*/
if (vp->v_mount && (vp->v_mount->mnt_flag & MNT_RDONLY)) {
switch (vp->v_type) {
case VREG:
case VDIR:
case VLNK:
return (EROFS);
case VNON:
case VCHR:
case VSOCK:
case VFIFO:
case VBAD:
case VBLK:
break;
}
}
/*
* If there's shared text associated with
* the vnode, try to free it up once. If
* we fail, we can't allow writing.
*/
if ((vp->v_flag & VTEXT) && !uvm_vnp_uncache(vp))
return (ETXTBSY);
return (0);
}
/*
* Check whether a write operation would exceed the file size rlimit
* for the process, if one should be applied for this operation.
* If a partial write should take place, the uio is adjusted and the
* amount by which the request would have exceeded the limit is returned
* via the 'overrun' argument.
*/
int
vn_fsizechk(struct vnode *vp, struct uio *uio, int ioflag, ssize_t *overrun)
{
struct proc *p = uio->uio_procp;
*overrun = 0;
if (vp->v_type == VREG && p != NULL && !(ioflag & IO_NOLIMIT)) {
rlim_t limit = lim_cur_proc(p, RLIMIT_FSIZE);
/* if already at or over the limit, send the signal and fail */
if (uio->uio_offset >= limit) {
psignal(p, SIGXFSZ);
return (EFBIG);
}
/* otherwise, clamp the write to stay under the limit */
if (uio->uio_resid > limit - uio->uio_offset) {
*overrun = uio->uio_resid - (limit - uio->uio_offset);
uio->uio_resid = limit - uio->uio_offset;
}
}
return (0);
}
/*
* Mark a vnode as being the text image of a running process.
*/
void
vn_marktext(struct vnode *vp)
{
vp->v_flag |= VTEXT;
}
/*
* Vnode close call
*/
int
vn_close(struct vnode *vp, int flags, struct ucred *cred, struct proc *p)
{
int error;
if (flags & FWRITE)
vp->v_writecount--;
vn_lock(vp, LK_EXCLUSIVE | LK_RETRY);
error = VOP_CLOSE(vp, flags, cred, p);
vput(vp);
return (error);
}
/*
* Package up an I/O request on a vnode into a uio and do it.
*/
int
vn_rdwr(enum uio_rw rw, struct vnode *vp, caddr_t base, int len, off_t offset,
enum uio_seg segflg, int ioflg, struct ucred *cred, size_t *aresid,
struct proc *p)
{
struct uio auio;
struct iovec aiov;
int error;
auio.uio_iov = &aiov;
auio.uio_iovcnt = 1;
aiov.iov_base = base;
aiov.iov_len = len;
auio.uio_resid = len;
auio.uio_offset = offset;
auio.uio_segflg = segflg;
auio.uio_rw = rw;
auio.uio_procp = p;
if ((ioflg & IO_NODELOCKED) == 0)
vn_lock(vp, LK_EXCLUSIVE | LK_RETRY);
if (rw == UIO_READ) {
error = VOP_READ(vp, &auio, ioflg, cred);
} else {
error = VOP_WRITE(vp, &auio, ioflg, cred);
}
if ((ioflg & IO_NODELOCKED) == 0)
VOP_UNLOCK(vp);
if (aresid)
*aresid = auio.uio_resid;
else
if (auio.uio_resid && error == 0)
error = EIO;
return (error);
}
/*
* File table vnode read routine.
*/
int
vn_read(struct file *fp, struct uio *uio, int fflags)
{
struct vnode *vp = fp->f_data;
struct ucred *cred = fp->f_cred;
size_t count = uio->uio_resid;
off_t offset;
int error;
KERNEL_LOCK();
vn_lock(vp, LK_EXCLUSIVE | LK_RETRY);
if ((fflags & FO_POSITION) == 0)
offset = uio->uio_offset = fp->f_offset;
else
offset = uio->uio_offset;
/* no wrap around of offsets except on character devices */
if (vp->v_type != VCHR && count > LLONG_MAX - offset) {
error = EINVAL;
goto done;
}
if (vp->v_type == VDIR) {
error = EISDIR;
goto done;
}
error = VOP_READ(vp, uio, (fp->f_flag & FNONBLOCK) ? IO_NDELAY : 0,
cred);
if ((fflags & FO_POSITION) == 0) {
mtx_enter(&fp->f_mtx);
fp->f_offset += count - uio->uio_resid;
mtx_leave(&fp->f_mtx);
}
done:
VOP_UNLOCK(vp);
KERNEL_UNLOCK();
return (error);
}
/*
* File table vnode write routine.
*/
int
vn_write(struct file *fp, struct uio *uio, int fflags)
{
struct vnode *vp = fp->f_data;
struct ucred *cred = fp->f_cred;
int error, ioflag = IO_UNIT;
size_t count;
KERNEL_LOCK();
/* note: pwrite/pwritev are unaffected by O_APPEND */
if (vp->v_type == VREG && (fp->f_flag & O_APPEND) &&
(fflags & FO_POSITION) == 0)
ioflag |= IO_APPEND;
if (fp->f_flag & FNONBLOCK)
ioflag |= IO_NDELAY;
if ((fp->f_flag & FFSYNC) ||
(vp->v_mount && (vp->v_mount->mnt_flag & MNT_SYNCHRONOUS)))
ioflag |= IO_SYNC;
vn_lock(vp, LK_EXCLUSIVE | LK_RETRY);
if ((fflags & FO_POSITION) == 0)
uio->uio_offset = fp->f_offset;
count = uio->uio_resid;
error = VOP_WRITE(vp, uio, ioflag, cred);
if ((fflags & FO_POSITION) == 0) {
mtx_enter(&fp->f_mtx);
if (ioflag & IO_APPEND)
fp->f_offset = uio->uio_offset;
else
fp->f_offset += count - uio->uio_resid;
mtx_leave(&fp->f_mtx);
}
VOP_UNLOCK(vp);
KERNEL_UNLOCK();
return (error);
}
/*
* File table wrapper for vn_stat
*/
int
vn_statfile(struct file *fp, struct stat *sb, struct proc *p)
{
struct vnode *vp = fp->f_data;
return vn_stat(vp, sb, p);
}
/*
* vnode stat routine.
*/
int
vn_stat(struct vnode *vp, struct stat *sb, struct proc *p)
{
struct vattr va;
int error;
mode_t mode;
error = VOP_GETATTR(vp, &va, p->p_ucred, p);
if (error)
return (error);
/*
* Copy from vattr table
*/
memset(sb, 0, sizeof(*sb));
sb->st_dev = va.va_fsid;
sb->st_ino = va.va_fileid;
mode = va.va_mode;
switch (vp->v_type) {
case VREG:
mode |= S_IFREG;
break;
case VDIR:
mode |= S_IFDIR;
break;
case VBLK:
mode |= S_IFBLK;
break;
case VCHR:
mode |= S_IFCHR;
break;
case VLNK:
mode |= S_IFLNK;
break;
case VSOCK:
mode |= S_IFSOCK;
break;
case VFIFO:
mode |= S_IFIFO;
break;
default:
return (EBADF);
}
sb->st_mode = mode;
sb->st_nlink = va.va_nlink;
sb->st_uid = va.va_uid;
sb->st_gid = va.va_gid;
sb->st_rdev = va.va_rdev;
sb->st_size = va.va_size;
sb->st_atim.tv_sec = va.va_atime.tv_sec;
sb->st_atim.tv_nsec = va.va_atime.tv_nsec;
sb->st_mtim.tv_sec = va.va_mtime.tv_sec;
sb->st_mtim.tv_nsec = va.va_mtime.tv_nsec;
sb->st_ctim.tv_sec = va.va_ctime.tv_sec;
sb->st_ctim.tv_nsec = va.va_ctime.tv_nsec;
sb->st_blksize = va.va_blocksize;
sb->st_flags = va.va_flags;
sb->st_gen = va.va_gen;
sb->st_blocks = va.va_bytes / S_BLKSIZE;
return (0);
}
/*
* File table vnode ioctl routine.
*/
int
vn_ioctl(struct file *fp, u_long com, caddr_t data, struct proc *p)
{
struct vnode *vp = fp->f_data;
struct vattr vattr;
int error;
switch (vp->v_type) {
case VREG:
case VDIR:
if (com == FIONREAD) {
error = VOP_GETATTR(vp, &vattr, p->p_ucred, p);
if (error)
return (error);
*(int *)data = vattr.va_size - foffset(fp);
return (0);
}
if (com == FIONBIO || com == FIOASYNC) /* XXX */
return (0); /* XXX */
/* FALLTHROUGH */
default:
return (ENOTTY);
case VFIFO:
case VCHR:
case VBLK:
error = VOP_IOCTL(vp, com, data, fp->f_flag, p->p_ucred, p);
if (error == 0 && com == TIOCSCTTY) {
struct session *s = p->p_p->ps_session;
struct vnode *ovp = s->s_ttyvp;
s->s_ttyvp = vp;
vref(vp);
if (ovp)
vrele(ovp);
}
return (error);
}
}
/*
* File table vnode poll routine.
*/
int
vn_poll(struct file *fp, int events, struct proc *p)
{
return (VOP_POLL(fp->f_data, fp->f_flag, events, p));
}
/*
* Check that the vnode is still valid, and if so
* acquire requested lock.
*/
int
vn_lock(struct vnode *vp, int flags)
{
int error;
do {
if (vp->v_flag & VXLOCK) {
vp->v_flag |= VXWANT;
tsleep(vp, PINOD, "vn_lock", 0);
error = ENOENT;
} else {
error = VOP_LOCK(vp, flags);
if (error == 0)
return (error);
}
} while (flags & LK_RETRY);
return (error);
}
/*
* File table vnode close routine.
*/
int
vn_closefile(struct file *fp, struct proc *p)
{
struct vnode *vp = fp->f_data;
struct flock lf;
int error;
KERNEL_LOCK();
if ((fp->f_iflags & FIF_HASLOCK)) {
lf.l_whence = SEEK_SET;
lf.l_start = 0;
lf.l_len = 0;
lf.l_type = F_UNLCK;
(void) VOP_ADVLOCK(vp, (caddr_t)fp, F_UNLCK, &lf, F_FLOCK);
}
error = vn_close(vp, fp->f_flag, fp->f_cred, p);
KERNEL_UNLOCK();
return (error);
}
int
vn_kqfilter(struct file *fp, struct knote *kn)
{
return (VOP_KQFILTER(fp->f_data, kn));
}
int
vn_seek(struct file *fp, off_t *offset, int whence, struct proc *p)
{
struct ucred *cred = p->p_ucred;
struct vnode *vp = fp->f_data;
struct vattr vattr;
off_t newoff;
int error = 0;
int special;
if (vp->v_type == VFIFO)
return (ESPIPE);
vn_lock(vp, LK_EXCLUSIVE | LK_RETRY);
if (vp->v_type == VCHR)
special = 1;
else
special = 0;
switch (whence) {
case SEEK_CUR:
newoff = fp->f_offset + *offset;
break;
case SEEK_END:
KERNEL_LOCK();
error = VOP_GETATTR(vp, &vattr, cred, p);
KERNEL_UNLOCK();
if (error)
goto out;
newoff = *offset + (off_t)vattr.va_size;
break;
case SEEK_SET:
newoff = *offset;
break;
default:
error = EINVAL;
goto out;
}
if (!special && newoff < 0) {
error = EINVAL;
goto out;
}
mtx_enter(&fp->f_mtx);
fp->f_offset = newoff;
mtx_leave(&fp->f_mtx);
*offset = newoff;
out:
VOP_UNLOCK(vp);
return (error);
}
/*
* Common code for vnode access operations.
*/
/* Check if a directory can be found inside another in the hierarchy */
int
vn_isunder(struct vnode *lvp, struct vnode *rvp, struct proc *p)
{
int error;
error = vfs_getcwd_common(lvp, rvp, NULL, NULL, MAXPATHLEN/2, 0, p);
if (!error)
return (1);
return (0);
}
|