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
|
/*
* 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. 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.
*
* @(#)vfs_vnops.c 8.2 (Berkeley) 1/21/94
* $Id: vfs_vnops.c,v 1.32 1997/03/08 15:14:30 guido Exp $
*/
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/fcntl.h>
#include <sys/file.h>
#include <sys/stat.h>
#include <sys/buf.h>
#include <sys/proc.h>
#include <sys/mount.h>
#include <sys/namei.h>
#include <sys/vnode.h>
#include <sys/ioctl.h>
#include <vm/vm.h>
#include <vm/vm_param.h>
#include <vm/vm_object.h>
#include <vm/vnode_pager.h>
static int vn_closefile __P((struct file *fp, struct proc *p));
static int vn_ioctl __P((struct file *fp, int com, caddr_t data,
struct proc *p));
static int vn_read __P((struct file *fp, struct uio *uio,
struct ucred *cred));
static int vn_select __P((struct file *fp, int which, struct proc *p));
static int vn_write __P((struct file *fp, struct uio *uio,
struct ucred *cred));
struct fileops vnops =
{ vn_read, vn_write, vn_ioctl, vn_select, vn_closefile };
/*
* Common code for vnode open operations.
* Check permissions, and call the VOP_OPEN or VOP_CREATE routine.
*/
int
vn_open(ndp, fmode, cmode)
register struct nameidata *ndp;
int fmode, cmode;
{
register struct vnode *vp;
register struct proc *p = ndp->ni_cnd.cn_proc;
register struct ucred *cred = p->p_ucred;
struct vattr vat;
struct vattr *vap = &vat;
int error;
if (fmode & O_CREAT) {
ndp->ni_cnd.cn_nameiop = CREATE;
ndp->ni_cnd.cn_flags = LOCKPARENT | LOCKLEAF;
if ((fmode & O_EXCL) == 0)
ndp->ni_cnd.cn_flags |= FOLLOW;
error = namei(ndp);
if (error)
return (error);
if (ndp->ni_vp == NULL) {
VATTR_NULL(vap);
vap->va_type = VREG;
vap->va_mode = cmode;
if (fmode & O_EXCL)
vap->va_vaflags |= VA_EXCLUSIVE;
VOP_LEASE(ndp->ni_dvp, p, cred, LEASE_WRITE);
if (error = VOP_CREATE(ndp->ni_dvp, &ndp->ni_vp,
&ndp->ni_cnd, vap))
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 = FOLLOW | LOCKLEAF;
error = namei(ndp);
if (error)
return (error);
vp = ndp->ni_vp;
}
if (vp->v_type == VSOCK) {
error = EOPNOTSUPP;
goto bad;
}
if ((fmode & O_CREAT) == 0) {
if (fmode & FREAD) {
error = VOP_ACCESS(vp, VREAD, cred, p);
if (error)
goto bad;
}
if (fmode & (FWRITE | O_TRUNC)) {
if (vp->v_type == VDIR) {
error = EISDIR;
goto bad;
}
error = vn_writechk(vp);
if (error)
goto bad;
error = VOP_ACCESS(vp, VWRITE, cred, p);
if (error)
goto bad;
}
}
if (fmode & O_TRUNC) {
VOP_UNLOCK(vp, 0, p); /* XXX */
VOP_LEASE(vp, p, cred, LEASE_WRITE);
vn_lock(vp, LK_EXCLUSIVE | LK_RETRY, p); /* XXX */
VATTR_NULL(vap);
vap->va_size = 0;
error = VOP_SETATTR(vp, vap, cred, p);
if (error)
goto bad;
}
error = VOP_OPEN(vp, fmode, cred, p);
if (error)
goto bad;
/*
* Make sure that a VM object is created for VMIO support.
*/
if (vp->v_type == VREG) {
if ((error = vfs_object_create(vp, p, cred, 1)) != 0)
goto bad;
}
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(vp)
register struct vnode *vp;
{
/*
* 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)
return (ETXTBSY);
return (0);
}
/*
* Vnode close call
*/
int
vn_close(vp, flags, cred, p)
register struct vnode *vp;
int flags;
struct ucred *cred;
struct proc *p;
{
int error;
if (flags & FWRITE)
vp->v_writecount--;
error = VOP_CLOSE(vp, flags, cred, p);
vrele(vp);
return (error);
}
/*
* Package up an I/O request on a vnode into a uio and do it.
*/
int
vn_rdwr(rw, vp, base, len, offset, segflg, ioflg, cred, aresid, p)
enum uio_rw rw;
struct vnode *vp;
caddr_t base;
int len;
off_t offset;
enum uio_seg segflg;
int ioflg;
struct ucred *cred;
int *aresid;
struct proc *p;
{
struct uio auio;
struct iovec aiov;
int error;
if ((ioflg & IO_NODELOCKED) == 0)
vn_lock(vp, LK_EXCLUSIVE | LK_RETRY, p);
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 (rw == UIO_READ) {
error = VOP_READ(vp, &auio, ioflg, cred);
} else {
error = VOP_WRITE(vp, &auio, ioflg, cred);
}
if (aresid)
*aresid = auio.uio_resid;
else
if (auio.uio_resid && error == 0)
error = EIO;
if ((ioflg & IO_NODELOCKED) == 0)
VOP_UNLOCK(vp, 0, p);
return (error);
}
/*
* File table vnode read routine.
*/
static int
vn_read(fp, uio, cred)
struct file *fp;
struct uio *uio;
struct ucred *cred;
{
struct vnode *vp = (struct vnode *)fp->f_data;
struct proc *p = uio->uio_procp;
int count, error;
int flag, seq;
VOP_LEASE(vp, p, cred, LEASE_READ);
vn_lock(vp, LK_EXCLUSIVE | LK_RETRY, p);
uio->uio_offset = fp->f_offset;
count = uio->uio_resid;
flag = 0;
if (fp->f_flag & FNONBLOCK)
flag |= IO_NDELAY;
/*
* Sequential read heuristic.
* If we have been doing sequential input,
* a rewind operation doesn't turn off
* sequential input mode.
*/
if (((fp->f_offset == 0) && (fp->f_seqcount > 0)) ||
(fp->f_offset == fp->f_nextread)) {
int tmpseq = fp->f_seqcount;
/*
* XXX we assume that the filesystem block size is
* the default. Not true, but still gives us a pretty
* good indicator of how sequential the read operations
* are.
*/
tmpseq += ((count + BKVASIZE - 1) / BKVASIZE);
if (tmpseq >= CHAR_MAX)
tmpseq = CHAR_MAX;
fp->f_seqcount = tmpseq;
flag |= (fp->f_seqcount << 16);
} else {
if (fp->f_seqcount > 1)
fp->f_seqcount = 1;
else
fp->f_seqcount = 0;
}
error = VOP_READ(vp, uio, flag, cred);
fp->f_offset += count - uio->uio_resid;
fp->f_nextread = fp->f_offset;
VOP_UNLOCK(vp, 0, p);
return (error);
}
/*
* File table vnode write routine.
*/
static int
vn_write(fp, uio, cred)
struct file *fp;
struct uio *uio;
struct ucred *cred;
{
struct vnode *vp = (struct vnode *)fp->f_data;
struct proc *p = uio->uio_procp;
int count, error, ioflag = IO_UNIT;
if (vp->v_type == VREG && (fp->f_flag & O_APPEND))
ioflag |= IO_APPEND;
if (fp->f_flag & FNONBLOCK)
ioflag |= IO_NDELAY;
if ((fp->f_flag & O_FSYNC) ||
(vp->v_mount && (vp->v_mount->mnt_flag & MNT_SYNCHRONOUS)))
ioflag |= IO_SYNC;
VOP_LEASE(vp, p, cred, LEASE_WRITE);
vn_lock(vp, LK_EXCLUSIVE | LK_RETRY, p);
uio->uio_offset = fp->f_offset;
count = uio->uio_resid;
error = VOP_WRITE(vp, uio, ioflag, cred);
if (ioflag & IO_APPEND)
fp->f_offset = uio->uio_offset;
else
fp->f_offset += count - uio->uio_resid;
VOP_UNLOCK(vp, 0, p);
return (error);
}
/*
* File table vnode stat routine.
*/
int
vn_stat(vp, sb, p)
struct vnode *vp;
register struct stat *sb;
struct proc *p;
{
struct vattr vattr;
register struct vattr *vap;
int error;
u_short mode;
vap = &vattr;
error = VOP_GETATTR(vp, vap, p->p_ucred, p);
if (error)
return (error);
/*
* Copy from vattr table
*/
sb->st_dev = vap->va_fsid;
sb->st_ino = vap->va_fileid;
mode = vap->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 = vap->va_nlink;
sb->st_uid = vap->va_uid;
sb->st_gid = vap->va_gid;
sb->st_rdev = vap->va_rdev;
sb->st_size = vap->va_size;
sb->st_atimespec = vap->va_atime;
sb->st_mtimespec = vap->va_mtime;
sb->st_ctimespec = vap->va_ctime;
sb->st_blksize = vap->va_blocksize;
sb->st_flags = vap->va_flags;
if (p->p_ucred->cr_uid != 0)
sb->st_gen = 0;
else
sb->st_gen = vap->va_gen;
#if (S_BLKSIZE == 512)
/* Optimize this case */
sb->st_blocks = vap->va_bytes >> 9;
#else
sb->st_blocks = vap->va_bytes / S_BLKSIZE;
#endif
return (0);
}
/*
* File table vnode ioctl routine.
*/
static int
vn_ioctl(fp, com, data, p)
struct file *fp;
int com;
caddr_t data;
struct proc *p;
{
register struct vnode *vp = ((struct vnode *)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 - fp->f_offset;
return (0);
}
if (com == FIONBIO || com == FIOASYNC) /* XXX */
return (0); /* XXX */
/* fall into ... */
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) {
/* Do nothing if reassigning same control tty */
if (p->p_session->s_ttyvp == vp)
return (0);
/* Get rid of reference to old control tty */
if (p->p_session->s_ttyvp)
vrele(p->p_session->s_ttyvp);
p->p_session->s_ttyvp = vp;
VREF(vp);
}
return (error);
}
}
/*
* File table vnode select routine.
*/
static int
vn_select(fp, which, p)
struct file *fp;
int which;
struct proc *p;
{
return (VOP_SELECT(((struct vnode *)fp->f_data), which, fp->f_flag,
fp->f_cred, p));
}
/*
* File table vnode close routine.
*/
static int
vn_closefile(fp, p)
struct file *fp;
struct proc *p;
{
return (vn_close(((struct vnode *)fp->f_data), fp->f_flag,
fp->f_cred, p));
}
/*
* Check that the vnode is still valid, and if so
* acquire requested lock.
*/
int
vn_lock(vp, flags, p)
struct vnode *vp;
int flags;
struct proc *p;
{
int error;
do {
if ((flags & LK_INTERLOCK) == 0) {
simple_lock(&vp->v_interlock);
}
if (vp->v_flag & VXLOCK) {
vp->v_flag |= VXWANT;
simple_unlock(&vp->v_interlock);
tsleep((caddr_t)vp, PINOD, "vn_lock", 0);
error = ENOENT;
} else {
error = VOP_LOCK(vp, flags | LK_INTERLOCK, p);
if (error == 0)
return (error);
}
flags &= ~LK_INTERLOCK;
} while (flags & LK_RETRY);
return (error);
}
|