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
|
/*-
* Copyright (c) 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.
*
* @(#)ufs_readwrite.c 8.7 (Berkeley) 1/21/94
* $Id: ufs_readwrite.c,v 1.15 1995/11/05 21:01:10 dyson Exp $
*/
#ifdef LFS_READWRITE
#define BLKSIZE(a, b, c) blksize(a)
#define FS struct lfs
#define I_FS i_lfs
#define READ lfs_read
#define READ_S "lfs_read"
#define WRITE lfs_write
#define WRITE_S "lfs_write"
#define fs_bsize lfs_bsize
#define fs_maxfilesize lfs_maxfilesize
#else
#define BLKSIZE(a, b, c) blksize(a, b, c)
#define FS struct fs
#define I_FS i_fs
#define READ ffs_read
#define READ_S "ffs_read"
#define WRITE ffs_write
#define WRITE_S "ffs_write"
#include <vm/vm.h>
#include <vm/vm_pager.h>
#include <vm/vnode_pager.h>
#endif
/*
* Vnode op for reading.
*/
/* ARGSUSED */
int
READ(ap)
struct vop_read_args /* {
struct vnode *a_vp;
struct uio *a_uio;
int a_ioflag;
struct ucred *a_cred;
} */ *ap;
{
register struct vnode *vp;
register struct inode *ip;
register struct uio *uio;
register FS *fs;
struct buf *bp;
daddr_t lbn, nextlbn;
off_t bytesinfile;
long size, xfersize, blkoffset;
int error;
u_short mode;
vp = ap->a_vp;
ip = VTOI(vp);
mode = ip->i_mode;
uio = ap->a_uio;
#ifdef DIAGNOSTIC
if (uio->uio_rw != UIO_READ)
panic("%s: mode", READ_S);
if (vp->v_type == VLNK) {
if ((int)ip->i_size < vp->v_mount->mnt_maxsymlinklen)
panic("%s: short symlink", READ_S);
} else if (vp->v_type != VREG && vp->v_type != VDIR)
panic("%s: type %d", READ_S, vp->v_type);
#endif
fs = ip->I_FS;
if ((u_quad_t)uio->uio_offset > fs->fs_maxfilesize)
return (EFBIG);
for (error = 0, bp = NULL; uio->uio_resid > 0; bp = NULL) {
if ((bytesinfile = ip->i_size - uio->uio_offset) <= 0)
break;
lbn = lblkno(fs, uio->uio_offset);
nextlbn = lbn + 1;
size = BLKSIZE(fs, ip, lbn);
blkoffset = blkoff(fs, uio->uio_offset);
xfersize = fs->fs_bsize - blkoffset;
if (uio->uio_resid < xfersize)
xfersize = uio->uio_resid;
if (bytesinfile < xfersize)
xfersize = bytesinfile;
#ifdef LFS_READWRITE
(void)lfs_check(vp, lbn);
error = cluster_read(vp, ip->i_size, lbn, size, NOCRED, &bp);
#else
if (lblktosize(fs, nextlbn) > ip->i_size)
error = bread(vp, lbn, size, NOCRED, &bp);
else if (doclusterread)
error = cluster_read(vp,
ip->i_size, lbn, size, NOCRED, &bp);
else if (lbn - 1 == vp->v_lastr) {
int nextsize = BLKSIZE(fs, ip, nextlbn);
error = breadn(vp, lbn,
size, &nextlbn, &nextsize, 1, NOCRED, &bp);
} else
error = bread(vp, lbn, size, NOCRED, &bp);
#endif
if (error)
break;
vp->v_lastr = lbn;
/*
* We should only get non-zero b_resid when an I/O error
* has occurred, which should cause us to break above.
* However, if the short read did not cause an error,
* then we want to ensure that we do not uiomove bad
* or uninitialized data.
*/
size -= bp->b_resid;
if (size < xfersize) {
if (size == 0)
break;
xfersize = size;
}
if (uio->uio_segflg != UIO_NOCOPY)
ip->i_flag |= IN_RECURSE;
error =
uiomove((char *)bp->b_data + blkoffset, (int)xfersize, uio);
if (uio->uio_segflg != UIO_NOCOPY)
ip->i_flag &= ~IN_RECURSE;
if (error)
break;
brelse(bp);
}
if (bp != NULL)
brelse(bp);
ip->i_flag |= IN_ACCESS;
return (error);
}
/*
* Vnode op for writing.
*/
int
WRITE(ap)
struct vop_write_args /* {
struct vnode *a_vp;
struct uio *a_uio;
int a_ioflag;
struct ucred *a_cred;
} */ *ap;
{
register struct vnode *vp;
register struct uio *uio;
register struct inode *ip;
register FS *fs;
struct buf *bp;
struct proc *p;
daddr_t lbn;
off_t osize;
int blkoffset, error, flags, ioflag, resid, size, xfersize;
struct timeval tv;
ioflag = ap->a_ioflag;
uio = ap->a_uio;
vp = ap->a_vp;
ip = VTOI(vp);
#ifdef DIAGNOSTIC
if (uio->uio_rw != UIO_WRITE)
panic("%s: mode", WRITE_S);
#endif
switch (vp->v_type) {
case VREG:
if (ioflag & IO_APPEND)
uio->uio_offset = ip->i_size;
if ((ip->i_flags & APPEND) && uio->uio_offset != ip->i_size)
return (EPERM);
/* FALLTHROUGH */
case VLNK:
break;
case VDIR:
if ((ioflag & IO_SYNC) == 0)
panic("%s: nonsync dir write", WRITE_S);
break;
default:
panic("%s: type", WRITE_S);
}
fs = ip->I_FS;
if (uio->uio_offset < 0 ||
(u_quad_t)uio->uio_offset + uio->uio_resid > fs->fs_maxfilesize)
return (EFBIG);
/*
* Maybe this should be above the vnode op call, but so long as
* file servers have no limits, I don't think it matters.
*/
p = uio->uio_procp;
if (vp->v_type == VREG && p &&
uio->uio_offset + uio->uio_resid >
p->p_rlimit[RLIMIT_FSIZE].rlim_cur) {
psignal(p, SIGXFSZ);
return (EFBIG);
}
resid = uio->uio_resid;
osize = ip->i_size;
flags = ioflag & IO_SYNC ? B_SYNC : 0;
for (error = 0; uio->uio_resid > 0;) {
lbn = lblkno(fs, uio->uio_offset);
blkoffset = blkoff(fs, uio->uio_offset);
xfersize = fs->fs_bsize - blkoffset;
if (uio->uio_resid < xfersize)
xfersize = uio->uio_resid;
if (uio->uio_offset + xfersize > ip->i_size)
vnode_pager_setsize(vp, (u_long)uio->uio_offset + xfersize);
#ifdef LFS_READWRITE
(void)lfs_check(vp, lbn);
error = lfs_balloc(vp, xfersize, lbn, &bp);
#else
if (fs->fs_bsize > xfersize)
flags |= B_CLRBUF;
else
flags &= ~B_CLRBUF;
error = ffs_balloc(ip,
lbn, blkoffset + xfersize, ap->a_cred, &bp, flags);
#endif
if (error)
break;
if (uio->uio_offset + xfersize > ip->i_size) {
ip->i_size = uio->uio_offset + xfersize;
}
size = BLKSIZE(fs, ip, lbn) - bp->b_resid;
if (size < xfersize)
xfersize = size;
if (uio->uio_segflg != UIO_NOCOPY)
ip->i_flag |= IN_RECURSE;
error =
uiomove((char *)bp->b_data + blkoffset, (int)xfersize, uio);
if (uio->uio_segflg != UIO_NOCOPY)
ip->i_flag &= ~IN_RECURSE;
#ifdef LFS_READWRITE
(void)VOP_BWRITE(bp);
#else
if (ioflag & IO_VMIO)
bp->b_flags |= B_RELBUF;
if (ioflag & IO_SYNC) {
(void)bwrite(bp);
} else if (xfersize + blkoffset == fs->fs_bsize &&
(vp->v_mount->mnt_flag & MNT_ASYNC) == 0) {
if (doclusterwrite) {
bp->b_flags |= B_CLUSTEROK;
cluster_write(bp, ip->i_size);
} else {
bawrite(bp);
}
} else {
bp->b_flags |= B_CLUSTEROK;
bdwrite(bp);
}
#endif
if (error || xfersize == 0)
break;
ip->i_flag |= IN_CHANGE | IN_UPDATE;
}
/*
* If we successfully wrote any data, and we are not the superuser
* we clear the setuid and setgid bits as a precaution against
* tampering.
*/
if (resid > uio->uio_resid && ap->a_cred && ap->a_cred->cr_uid != 0)
ip->i_mode &= ~(ISUID | ISGID);
if (error) {
if (ioflag & IO_UNIT) {
(void)VOP_TRUNCATE(vp, osize,
ioflag & IO_SYNC, ap->a_cred, uio->uio_procp);
uio->uio_offset -= resid - uio->uio_resid;
uio->uio_resid = resid;
}
} else if (resid > uio->uio_resid && (ioflag & IO_SYNC)) {
tv = time;
error = VOP_UPDATE(vp, &tv, &tv, 1);
}
return (error);
}
#ifndef LFS_READWRITE
/*
* get page routine
*/
int
ffs_getpages(ap)
struct vop_getpages_args *ap;
{
vm_offset_t foff, physoffset;
int i, size, bsize;
struct vnode *dp;
int bbackwards, bforwards;
int pbackwards, pforwards;
int firstpage;
int reqlblkno;
daddr_t reqblkno;
int poff;
int pcount;
int rtval;
int pagesperblock;
pcount = round_page(ap->a_count) / PAGE_SIZE;
/*
* if ANY DEV_BSIZE blocks are valid on a large filesystem block
* then, the entire page is valid --
*/
if (ap->a_m[ap->a_reqpage]->valid) {
ap->a_m[ap->a_reqpage]->valid = VM_PAGE_BITS_ALL;
for (i = 0; i < pcount; i++) {
if (i != ap->a_reqpage)
vnode_pager_freepage(ap->a_m[i]);
}
return VM_PAGER_OK;
}
bsize = ap->a_vp->v_mount->mnt_stat.f_iosize;
/*
* foff is the file offset of the required page
* reqlblkno is the logical block that contains the page
* poff is the index of the page into the logical block
*/
foff = ap->a_m[ap->a_reqpage]->offset + ap->a_offset;
reqlblkno = foff / bsize;
poff = (foff % bsize) / PAGE_SIZE;
if ( VOP_BMAP( ap->a_vp, reqlblkno, &dp, &reqblkno,
&bforwards, &bbackwards) || (reqblkno == -1)) {
for(i = 0; i < pcount; i++) {
if (i != ap->a_reqpage)
vnode_pager_freepage(ap->a_m[i]);
}
if (reqblkno == -1) {
if ((ap->a_m[ap->a_reqpage]->flags & PG_ZERO) == 0)
vm_page_zero_fill(ap->a_m[ap->a_reqpage]);
ap->a_m[ap->a_reqpage]->dirty = 0;
ap->a_m[ap->a_reqpage]->valid = VM_PAGE_BITS_ALL;
return VM_PAGER_OK;
} else {
return VM_PAGER_ERROR;
}
}
physoffset = reqblkno * DEV_BSIZE + poff * PAGE_SIZE;
pagesperblock = bsize / PAGE_SIZE;
/*
* find the first page that is contiguous...
* note that pbackwards is the number of pages that are contiguous
* backwards.
*/
firstpage = 0;
if (ap->a_count) {
pbackwards = poff + bbackwards * pagesperblock;
if (ap->a_reqpage > pbackwards) {
firstpage = ap->a_reqpage - pbackwards;
for(i=0;i<firstpage;i++)
vnode_pager_freepage(ap->a_m[i]);
}
/*
* pforwards is the number of pages that are contiguous
* after the current page.
*/
pforwards = (pagesperblock - (poff + 1)) +
bforwards * pagesperblock;
if (pforwards < (pcount - (ap->a_reqpage + 1))) {
for( i = ap->a_reqpage + pforwards + 1; i < pcount; i++)
vnode_pager_freepage(ap->a_m[i]);
pcount = ap->a_reqpage + pforwards + 1;
}
/*
* number of pages for I/O corrected for the non-contig pages at
* the beginning of the array.
*/
pcount -= firstpage;
}
/*
* calculate the size of the transfer
*/
size = pcount * PAGE_SIZE;
if ((ap->a_m[firstpage]->offset + size) >
((vm_object_t) ap->a_vp->v_object)->un_pager.vnp.vnp_size)
size = ((vm_object_t) ap->a_vp->v_object)->un_pager.vnp.vnp_size - ap->a_m[firstpage]->offset;
physoffset -= ap->a_m[ap->a_reqpage]->offset;
rtval = VOP_GETPAGES(dp, &ap->a_m[firstpage], size,
(ap->a_reqpage - firstpage), physoffset);
return (rtval);
}
#endif
|