Blame view
fs/read_write.c
47.2 KB
b24413180
|
1 |
// SPDX-License-Identifier: GPL-2.0 |
1da177e4c
|
2 3 4 5 6 |
/* * linux/fs/read_write.c * * Copyright (C) 1991, 1992 Linus Torvalds */ |
b12fb7f46
|
7 |
#include <linux/slab.h> |
1da177e4c
|
8 |
#include <linux/stat.h> |
b12fb7f46
|
9 |
#include <linux/sched/xacct.h> |
1da177e4c
|
10 11 12 |
#include <linux/fcntl.h> #include <linux/file.h> #include <linux/uio.h> |
0eeca2830
|
13 |
#include <linux/fsnotify.h> |
1da177e4c
|
14 |
#include <linux/security.h> |
630d9c472
|
15 |
#include <linux/export.h> |
1da177e4c
|
16 |
#include <linux/syscalls.h> |
e28cc7157
|
17 |
#include <linux/pagemap.h> |
d6b29d7ce
|
18 |
#include <linux/splice.h> |
561c67319
|
19 |
#include <linux/compat.h> |
29732938a
|
20 |
#include <linux/mount.h> |
2feb55f89
|
21 |
#include <linux/fs.h> |
06ae43f34
|
22 |
#include "internal.h" |
1da177e4c
|
23 |
|
7c0f6ba68
|
24 |
#include <linux/uaccess.h> |
1da177e4c
|
25 |
#include <asm/unistd.h> |
4b6f5d20b
|
26 |
const struct file_operations generic_ro_fops = { |
1da177e4c
|
27 |
.llseek = generic_file_llseek, |
aad4f8bb4
|
28 |
.read_iter = generic_file_read_iter, |
1da177e4c
|
29 |
.mmap = generic_file_readonly_mmap, |
534f2aaa6
|
30 |
.splice_read = generic_file_splice_read, |
1da177e4c
|
31 32 33 |
}; EXPORT_SYMBOL(generic_ro_fops); |
ddef7ed2b
|
34 |
static inline bool unsigned_offsets(struct file *file) |
4a3956c79
|
35 |
{ |
cccb5a1e6
|
36 |
return file->f_mode & FMODE_UNSIGNED_OFFSET; |
4a3956c79
|
37 |
} |
46a1c2c7a
|
38 39 40 41 42 43 44 45 46 47 48 49 50 |
/** * vfs_setpos - update the file offset for lseek * @file: file structure in question * @offset: file offset to seek to * @maxsize: maximum file size * * This is a low-level filesystem helper for updating the file offset to * the value specified by @offset if the given offset is valid and it is * not equal to the current file offset. * * Return the specified offset on success and -EINVAL on invalid offset. */ loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize) |
ef3d0fd27
|
51 52 53 54 55 56 57 58 59 60 61 62 |
{ if (offset < 0 && !unsigned_offsets(file)) return -EINVAL; if (offset > maxsize) return -EINVAL; if (offset != file->f_pos) { file->f_pos = offset; file->f_version = 0; } return offset; } |
46a1c2c7a
|
63 |
EXPORT_SYMBOL(vfs_setpos); |
ef3d0fd27
|
64 |
|
3a8cff4f0
|
65 |
/** |
5760495a8
|
66 |
* generic_file_llseek_size - generic llseek implementation for regular files |
3a8cff4f0
|
67 68 |
* @file: file structure to seek on * @offset: file offset to seek to |
965c8e59c
|
69 |
* @whence: type of seek |
e8b96eb50
|
70 71 |
* @size: max size of this file in file system * @eof: offset used for SEEK_END position |
3a8cff4f0
|
72 |
* |
5760495a8
|
73 |
* This is a variant of generic_file_llseek that allows passing in a custom |
e8b96eb50
|
74 |
* maximum file size and a custom EOF position, for e.g. hashed directories |
ef3d0fd27
|
75 76 |
* * Synchronization: |
5760495a8
|
77 |
* SEEK_SET and SEEK_END are unsynchronized (but atomic on 64bit platforms) |
ef3d0fd27
|
78 79 |
* SEEK_CUR is synchronized against other SEEK_CURs, but not read/writes. * read/writes behave like SEEK_SET against seeks. |
3a8cff4f0
|
80 |
*/ |
9465efc9e
|
81 |
loff_t |
965c8e59c
|
82 |
generic_file_llseek_size(struct file *file, loff_t offset, int whence, |
e8b96eb50
|
83 |
loff_t maxsize, loff_t eof) |
1da177e4c
|
84 |
{ |
965c8e59c
|
85 |
switch (whence) { |
3a8cff4f0
|
86 |
case SEEK_END: |
e8b96eb50
|
87 |
offset += eof; |
3a8cff4f0
|
88 89 |
break; case SEEK_CUR: |
5b6f1eb97
|
90 91 92 93 94 95 96 97 |
/* * Here we special-case the lseek(fd, 0, SEEK_CUR) * position-querying operation. Avoid rewriting the "same" * f_pos value back to the file because a concurrent read(), * write() or lseek() might have altered it */ if (offset == 0) return file->f_pos; |
ef3d0fd27
|
98 99 100 101 102 103 |
/* * f_lock protects against read/modify/write race with other * SEEK_CURs. Note that parallel writes and reads behave * like SEEK_SET. */ spin_lock(&file->f_lock); |
46a1c2c7a
|
104 |
offset = vfs_setpos(file, file->f_pos + offset, maxsize); |
ef3d0fd27
|
105 106 |
spin_unlock(&file->f_lock); return offset; |
982d81658
|
107 108 109 110 111 |
case SEEK_DATA: /* * In the generic case the entire file is data, so as long as * offset isn't at the end of the file then the offset is data. */ |
fc46820b2
|
112 |
if ((unsigned long long)offset >= eof) |
982d81658
|
113 114 115 116 117 118 119 |
return -ENXIO; break; case SEEK_HOLE: /* * There is a virtual hole at the end of the file, so as long as * offset isn't i_size or larger, return i_size. */ |
fc46820b2
|
120 |
if ((unsigned long long)offset >= eof) |
982d81658
|
121 |
return -ENXIO; |
e8b96eb50
|
122 |
offset = eof; |
982d81658
|
123 |
break; |
1da177e4c
|
124 |
} |
3a8cff4f0
|
125 |
|
46a1c2c7a
|
126 |
return vfs_setpos(file, offset, maxsize); |
5760495a8
|
127 128 129 130 131 132 133 |
} EXPORT_SYMBOL(generic_file_llseek_size); /** * generic_file_llseek - generic llseek implementation for regular files * @file: file structure to seek on * @offset: file offset to seek to |
965c8e59c
|
134 |
* @whence: type of seek |
5760495a8
|
135 136 137 |
* * This is a generic implemenation of ->llseek useable for all normal local * filesystems. It just updates the file offset to the value specified by |
546ae2d2f
|
138 |
* @offset and @whence. |
5760495a8
|
139 |
*/ |
965c8e59c
|
140 |
loff_t generic_file_llseek(struct file *file, loff_t offset, int whence) |
5760495a8
|
141 142 |
{ struct inode *inode = file->f_mapping->host; |
965c8e59c
|
143 |
return generic_file_llseek_size(file, offset, whence, |
e8b96eb50
|
144 145 |
inode->i_sb->s_maxbytes, i_size_read(inode)); |
1da177e4c
|
146 |
} |
9465efc9e
|
147 |
EXPORT_SYMBOL(generic_file_llseek); |
1da177e4c
|
148 |
|
ae6afc3f5
|
149 |
/** |
1bf9d14df
|
150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 |
* fixed_size_llseek - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @size: size of the file * */ loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size) { switch (whence) { case SEEK_SET: case SEEK_CUR: case SEEK_END: return generic_file_llseek_size(file, offset, whence, size, size); default: return -EINVAL; } } EXPORT_SYMBOL(fixed_size_llseek); /** |
b25472f9b
|
170 171 172 173 174 175 176 177 178 179 180 |
* no_seek_end_llseek - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * */ loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence) { switch (whence) { case SEEK_SET: case SEEK_CUR: return generic_file_llseek_size(file, offset, whence, |
2feb55f89
|
181 |
OFFSET_MAX, 0); |
b25472f9b
|
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 |
default: return -EINVAL; } } EXPORT_SYMBOL(no_seek_end_llseek); /** * no_seek_end_llseek_size - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @size: maximal offset allowed * */ loff_t no_seek_end_llseek_size(struct file *file, loff_t offset, int whence, loff_t size) { switch (whence) { case SEEK_SET: case SEEK_CUR: return generic_file_llseek_size(file, offset, whence, size, 0); default: return -EINVAL; } } EXPORT_SYMBOL(no_seek_end_llseek_size); /** |
ae6afc3f5
|
209 210 211 |
* noop_llseek - No Operation Performed llseek implementation * @file: file structure to seek on * @offset: file offset to seek to |
965c8e59c
|
212 |
* @whence: type of seek |
ae6afc3f5
|
213 214 215 216 217 218 |
* * This is an implementation of ->llseek useable for the rare special case when * userspace expects the seek to succeed but the (device) file is actually not * able to perform the seek. In this case you use noop_llseek() instead of * falling back to the default implementation of ->llseek. */ |
965c8e59c
|
219 |
loff_t noop_llseek(struct file *file, loff_t offset, int whence) |
ae6afc3f5
|
220 221 222 223 |
{ return file->f_pos; } EXPORT_SYMBOL(noop_llseek); |
965c8e59c
|
224 |
loff_t no_llseek(struct file *file, loff_t offset, int whence) |
1da177e4c
|
225 226 227 228 |
{ return -ESPIPE; } EXPORT_SYMBOL(no_llseek); |
965c8e59c
|
229 |
loff_t default_llseek(struct file *file, loff_t offset, int whence) |
1da177e4c
|
230 |
{ |
496ad9aa8
|
231 |
struct inode *inode = file_inode(file); |
16abef0e9
|
232 |
loff_t retval; |
1da177e4c
|
233 |
|
5955102c9
|
234 |
inode_lock(inode); |
965c8e59c
|
235 |
switch (whence) { |
7b8e89249
|
236 |
case SEEK_END: |
982d81658
|
237 |
offset += i_size_read(inode); |
1da177e4c
|
238 |
break; |
7b8e89249
|
239 |
case SEEK_CUR: |
5b6f1eb97
|
240 241 242 243 |
if (offset == 0) { retval = file->f_pos; goto out; } |
1da177e4c
|
244 |
offset += file->f_pos; |
982d81658
|
245 246 247 248 249 250 251 |
break; case SEEK_DATA: /* * In the generic case the entire file is data, so as * long as offset isn't at the end of the file then the * offset is data. */ |
bacb2d816
|
252 253 254 255 |
if (offset >= inode->i_size) { retval = -ENXIO; goto out; } |
982d81658
|
256 257 258 259 260 261 262 |
break; case SEEK_HOLE: /* * There is a virtual hole at the end of the file, so * as long as offset isn't i_size or larger, return * i_size. */ |
bacb2d816
|
263 264 265 266 |
if (offset >= inode->i_size) { retval = -ENXIO; goto out; } |
982d81658
|
267 268 |
offset = inode->i_size; break; |
1da177e4c
|
269 270 |
} retval = -EINVAL; |
cccb5a1e6
|
271 |
if (offset >= 0 || unsigned_offsets(file)) { |
1da177e4c
|
272 273 274 275 276 277 |
if (offset != file->f_pos) { file->f_pos = offset; file->f_version = 0; } retval = offset; } |
5b6f1eb97
|
278 |
out: |
5955102c9
|
279 |
inode_unlock(inode); |
1da177e4c
|
280 281 282 |
return retval; } EXPORT_SYMBOL(default_llseek); |
965c8e59c
|
283 |
loff_t vfs_llseek(struct file *file, loff_t offset, int whence) |
1da177e4c
|
284 285 286 287 288 |
{ loff_t (*fn)(struct file *, loff_t, int); fn = no_llseek; if (file->f_mode & FMODE_LSEEK) { |
72c2d5319
|
289 |
if (file->f_op->llseek) |
1da177e4c
|
290 291 |
fn = file->f_op->llseek; } |
965c8e59c
|
292 |
return fn(file, offset, whence); |
1da177e4c
|
293 294 |
} EXPORT_SYMBOL(vfs_llseek); |
965c8e59c
|
295 |
SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence) |
1da177e4c
|
296 297 |
{ off_t retval; |
9c225f265
|
298 |
struct fd f = fdget_pos(fd); |
2903ff019
|
299 300 |
if (!f.file) return -EBADF; |
1da177e4c
|
301 302 |
retval = -EINVAL; |
965c8e59c
|
303 304 |
if (whence <= SEEK_MAX) { loff_t res = vfs_llseek(f.file, offset, whence); |
1da177e4c
|
305 306 307 308 |
retval = res; if (res != (loff_t)retval) retval = -EOVERFLOW; /* LFS: should only happen on 32 bit platforms */ } |
9c225f265
|
309 |
fdput_pos(f); |
1da177e4c
|
310 311 |
return retval; } |
561c67319
|
312 313 314 315 316 317 |
#ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE3(lseek, unsigned int, fd, compat_off_t, offset, unsigned int, whence) { return sys_lseek(fd, offset, whence); } #endif |
1da177e4c
|
318 |
#ifdef __ARCH_WANT_SYS_LLSEEK |
003d7ab47
|
319 320 |
SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high, unsigned long, offset_low, loff_t __user *, result, |
965c8e59c
|
321 |
unsigned int, whence) |
1da177e4c
|
322 323 |
{ int retval; |
d7a15f8d0
|
324 |
struct fd f = fdget_pos(fd); |
1da177e4c
|
325 |
loff_t offset; |
1da177e4c
|
326 |
|
2903ff019
|
327 328 |
if (!f.file) return -EBADF; |
1da177e4c
|
329 330 |
retval = -EINVAL; |
965c8e59c
|
331 |
if (whence > SEEK_MAX) |
1da177e4c
|
332 |
goto out_putf; |
2903ff019
|
333 |
offset = vfs_llseek(f.file, ((loff_t) offset_high << 32) | offset_low, |
965c8e59c
|
334 |
whence); |
1da177e4c
|
335 336 337 338 339 340 341 342 |
retval = (int)offset; if (offset >= 0) { retval = -EFAULT; if (!copy_to_user(result, &offset, sizeof(offset))) retval = 0; } out_putf: |
d7a15f8d0
|
343 |
fdput_pos(f); |
1da177e4c
|
344 345 346 |
return retval; } #endif |
68d70d03f
|
347 |
int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count) |
1da177e4c
|
348 349 350 |
{ struct inode *inode; loff_t pos; |
c43e259cc
|
351 |
int retval = -EINVAL; |
1da177e4c
|
352 |
|
496ad9aa8
|
353 |
inode = file_inode(file); |
e28cc7157
|
354 |
if (unlikely((ssize_t) count < 0)) |
c43e259cc
|
355 |
return retval; |
1da177e4c
|
356 |
pos = *ppos; |
cccb5a1e6
|
357 358 359 360 361 362 363 |
if (unlikely(pos < 0)) { if (!unsigned_offsets(file)) return retval; if (count >= -pos) /* both values are in 0..LLONG_MAX */ return -EOVERFLOW; } else if (unlikely((loff_t) (pos + count) < 0)) { if (!unsigned_offsets(file)) |
4a3956c79
|
364 365 |
return retval; } |
1da177e4c
|
366 |
|
bd61e0a9c
|
367 |
if (unlikely(inode->i_flctx && mandatory_lock(inode))) { |
acc15575e
|
368 369 |
retval = locks_mandatory_area(inode, file, pos, pos + count - 1, read_write == READ ? F_RDLCK : F_WRLCK); |
e28cc7157
|
370 371 372 |
if (retval < 0) return retval; } |
bc61384dc
|
373 |
return security_file_permission(file, |
c43e259cc
|
374 |
read_write == READ ? MAY_READ : MAY_WRITE); |
1da177e4c
|
375 |
} |
5d5d56897
|
376 |
static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) |
293bc9822
|
377 378 379 380 381 382 383 384 |
{ struct iovec iov = { .iov_base = buf, .iov_len = len }; struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = *ppos; |
293bc9822
|
385 |
iov_iter_init(&iter, READ, &iov, 1, len); |
bb7462b6f
|
386 |
ret = call_read_iter(filp, &kiocb, &iter); |
599bd19bd
|
387 |
BUG_ON(ret == -EIOCBQUEUED); |
293bc9822
|
388 389 390 |
*ppos = kiocb.ki_pos; return ret; } |
6fb5032eb
|
391 392 393 |
ssize_t __vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { |
6fb5032eb
|
394 |
if (file->f_op->read) |
3d04c8a17
|
395 |
return file->f_op->read(file, buf, count, pos); |
6fb5032eb
|
396 |
else if (file->f_op->read_iter) |
3d04c8a17
|
397 |
return new_sync_read(file, buf, count, pos); |
6fb5032eb
|
398 |
else |
3d04c8a17
|
399 |
return -EINVAL; |
6fb5032eb
|
400 |
} |
bdd1d2d3d
|
401 |
ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) |
c41fbad01
|
402 403 |
{ mm_segment_t old_fs; |
bdd1d2d3d
|
404 |
ssize_t result; |
c41fbad01
|
405 406 407 408 |
old_fs = get_fs(); set_fs(get_ds()); /* The cast to a user pointer is valid due to the set_fs() */ |
bdd1d2d3d
|
409 |
result = vfs_read(file, (void __user *)buf, count, pos); |
c41fbad01
|
410 411 412 413 |
set_fs(old_fs); return result; } EXPORT_SYMBOL(kernel_read); |
6fb5032eb
|
414 |
|
1da177e4c
|
415 416 417 418 419 420 |
ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { ssize_t ret; if (!(file->f_mode & FMODE_READ)) return -EBADF; |
7f7f25e82
|
421 |
if (!(file->f_mode & FMODE_CAN_READ)) |
1da177e4c
|
422 423 424 425 426 |
return -EINVAL; if (unlikely(!access_ok(VERIFY_WRITE, buf, count))) return -EFAULT; ret = rw_verify_area(READ, file, pos, count); |
bc61384dc
|
427 428 429 |
if (!ret) { if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; |
6fb5032eb
|
430 |
ret = __vfs_read(file, buf, count, pos); |
c43e259cc
|
431 |
if (ret > 0) { |
2a12a9d78
|
432 |
fsnotify_access(file); |
c43e259cc
|
433 |
add_rchar(current, ret); |
1da177e4c
|
434 |
} |
c43e259cc
|
435 |
inc_syscr(current); |
1da177e4c
|
436 437 438 439 |
} return ret; } |
5d5d56897
|
440 |
static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos) |
293bc9822
|
441 442 443 444 445 446 447 448 |
{ struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len }; struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = *ppos; |
293bc9822
|
449 |
iov_iter_init(&iter, WRITE, &iov, 1, len); |
bb7462b6f
|
450 |
ret = call_write_iter(filp, &kiocb, &iter); |
599bd19bd
|
451 |
BUG_ON(ret == -EIOCBQUEUED); |
f765b134c
|
452 453 |
if (ret > 0) *ppos = kiocb.ki_pos; |
293bc9822
|
454 455 |
return ret; } |
493c84c07
|
456 457 458 459 460 |
ssize_t __vfs_write(struct file *file, const char __user *p, size_t count, loff_t *pos) { if (file->f_op->write) return file->f_op->write(file, p, count, pos); |
493c84c07
|
461 462 463 464 465 |
else if (file->f_op->write_iter) return new_sync_write(file, p, count, pos); else return -EINVAL; } |
493c84c07
|
466 |
|
73e18f7c0
|
467 |
ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) |
06ae43f34
|
468 469 470 471 |
{ mm_segment_t old_fs; const char __user *p; ssize_t ret; |
7f7f25e82
|
472 |
if (!(file->f_mode & FMODE_CAN_WRITE)) |
3e84f48ed
|
473 |
return -EINVAL; |
06ae43f34
|
474 475 476 477 478 |
old_fs = get_fs(); set_fs(get_ds()); p = (__force const char __user *)buf; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; |
493c84c07
|
479 |
ret = __vfs_write(file, p, count, pos); |
06ae43f34
|
480 481 482 483 484 485 486 487 |
set_fs(old_fs); if (ret > 0) { fsnotify_modify(file); add_wchar(current, ret); } inc_syscw(current); return ret; } |
2ec3a12a6
|
488 |
EXPORT_SYMBOL(__kernel_write); |
e13ec939e
|
489 490 |
ssize_t kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) |
ac452acae
|
491 492 493 494 495 496 497 |
{ mm_segment_t old_fs; ssize_t res; old_fs = get_fs(); set_fs(get_ds()); /* The cast to a user pointer is valid due to the set_fs() */ |
e13ec939e
|
498 |
res = vfs_write(file, (__force const char __user *)buf, count, pos); |
ac452acae
|
499 500 501 502 503 |
set_fs(old_fs); return res; } EXPORT_SYMBOL(kernel_write); |
1da177e4c
|
504 505 506 507 508 509 |
ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { ssize_t ret; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; |
7f7f25e82
|
510 |
if (!(file->f_mode & FMODE_CAN_WRITE)) |
1da177e4c
|
511 512 513 514 515 |
return -EINVAL; if (unlikely(!access_ok(VERIFY_READ, buf, count))) return -EFAULT; ret = rw_verify_area(WRITE, file, pos, count); |
bc61384dc
|
516 517 518 |
if (!ret) { if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; |
03d95eb2f
|
519 |
file_start_write(file); |
493c84c07
|
520 |
ret = __vfs_write(file, buf, count, pos); |
c43e259cc
|
521 |
if (ret > 0) { |
2a12a9d78
|
522 |
fsnotify_modify(file); |
c43e259cc
|
523 |
add_wchar(current, ret); |
1da177e4c
|
524 |
} |
c43e259cc
|
525 |
inc_syscw(current); |
03d95eb2f
|
526 |
file_end_write(file); |
1da177e4c
|
527 528 529 530 |
} return ret; } |
1da177e4c
|
531 532 533 534 535 536 537 538 539 |
static inline loff_t file_pos_read(struct file *file) { return file->f_pos; } static inline void file_pos_write(struct file *file, loff_t pos) { file->f_pos = pos; } |
3cdad4288
|
540 |
SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) |
1da177e4c
|
541 |
{ |
9c225f265
|
542 |
struct fd f = fdget_pos(fd); |
1da177e4c
|
543 |
ssize_t ret = -EBADF; |
1da177e4c
|
544 |
|
2903ff019
|
545 546 547 |
if (f.file) { loff_t pos = file_pos_read(f.file); ret = vfs_read(f.file, buf, count, &pos); |
5faf153eb
|
548 549 |
if (ret >= 0) file_pos_write(f.file, pos); |
9c225f265
|
550 |
fdput_pos(f); |
1da177e4c
|
551 |
} |
1da177e4c
|
552 553 |
return ret; } |
1da177e4c
|
554 |
|
3cdad4288
|
555 556 |
SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf, size_t, count) |
1da177e4c
|
557 |
{ |
9c225f265
|
558 |
struct fd f = fdget_pos(fd); |
1da177e4c
|
559 |
ssize_t ret = -EBADF; |
1da177e4c
|
560 |
|
2903ff019
|
561 562 563 |
if (f.file) { loff_t pos = file_pos_read(f.file); ret = vfs_write(f.file, buf, count, &pos); |
5faf153eb
|
564 565 |
if (ret >= 0) file_pos_write(f.file, pos); |
9c225f265
|
566 |
fdput_pos(f); |
1da177e4c
|
567 568 569 570 |
} return ret; } |
4a0fd5bf0
|
571 572 |
SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf, size_t, count, loff_t, pos) |
1da177e4c
|
573 |
{ |
2903ff019
|
574 |
struct fd f; |
1da177e4c
|
575 |
ssize_t ret = -EBADF; |
1da177e4c
|
576 577 578 |
if (pos < 0) return -EINVAL; |
2903ff019
|
579 580 |
f = fdget(fd); if (f.file) { |
1da177e4c
|
581 |
ret = -ESPIPE; |
2903ff019
|
582 583 584 |
if (f.file->f_mode & FMODE_PREAD) ret = vfs_read(f.file, buf, count, &pos); fdput(f); |
1da177e4c
|
585 586 587 588 |
} return ret; } |
4a0fd5bf0
|
589 590 |
SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf, size_t, count, loff_t, pos) |
1da177e4c
|
591 |
{ |
2903ff019
|
592 |
struct fd f; |
1da177e4c
|
593 |
ssize_t ret = -EBADF; |
1da177e4c
|
594 595 596 |
if (pos < 0) return -EINVAL; |
2903ff019
|
597 598 |
f = fdget(fd); if (f.file) { |
1da177e4c
|
599 |
ret = -ESPIPE; |
2903ff019
|
600 601 602 |
if (f.file->f_mode & FMODE_PWRITE) ret = vfs_write(f.file, buf, count, &pos); fdput(f); |
1da177e4c
|
603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 |
} return ret; } /* * Reduce an iovec's length in-place. Return the resulting number of segments */ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to) { unsigned long seg = 0; size_t len = 0; while (seg < nr_segs) { seg++; if (len + iov->iov_len >= to) { iov->iov_len = to - len; break; } len += iov->iov_len; iov++; } return seg; } |
19295529d
|
627 |
EXPORT_SYMBOL(iov_shorten); |
1da177e4c
|
628 |
|
ac15ac066
|
629 |
static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, |
ddef7ed2b
|
630 |
loff_t *ppos, int type, rwf_t flags) |
293bc9822
|
631 632 |
{ struct kiocb kiocb; |
293bc9822
|
633 634 635 |
ssize_t ret; init_sync_kiocb(&kiocb, filp); |
fdd2f5b7d
|
636 637 638 |
ret = kiocb_set_rw_flags(&kiocb, flags); if (ret) return ret; |
293bc9822
|
639 |
kiocb.ki_pos = *ppos; |
293bc9822
|
640 |
|
0f78d06ac
|
641 |
if (type == READ) |
bb7462b6f
|
642 |
ret = call_read_iter(filp, &kiocb, iter); |
0f78d06ac
|
643 |
else |
bb7462b6f
|
644 |
ret = call_write_iter(filp, &kiocb, iter); |
599bd19bd
|
645 |
BUG_ON(ret == -EIOCBQUEUED); |
293bc9822
|
646 647 648 |
*ppos = kiocb.ki_pos; return ret; } |
ee0b3e671
|
649 |
/* Do it by hand, with file-ops */ |
ac15ac066
|
650 |
static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, |
ddef7ed2b
|
651 |
loff_t *ppos, int type, rwf_t flags) |
ee0b3e671
|
652 |
{ |
ee0b3e671
|
653 |
ssize_t ret = 0; |
97be7ebe5
|
654 |
if (flags & ~RWF_HIPRI) |
793b80ef1
|
655 |
return -EOPNOTSUPP; |
ac15ac066
|
656 657 |
while (iov_iter_count(iter)) { struct iovec iovec = iov_iter_iovec(iter); |
ee0b3e671
|
658 |
ssize_t nr; |
0f78d06ac
|
659 660 661 662 663 664 665 |
if (type == READ) { nr = filp->f_op->read(filp, iovec.iov_base, iovec.iov_len, ppos); } else { nr = filp->f_op->write(filp, iovec.iov_base, iovec.iov_len, ppos); } |
ee0b3e671
|
666 667 668 669 670 671 672 |
if (nr < 0) { if (!ret) ret = nr; break; } ret += nr; |
ac15ac066
|
673 |
if (nr != iovec.iov_len) |
ee0b3e671
|
674 |
break; |
ac15ac066
|
675 |
iov_iter_advance(iter, nr); |
ee0b3e671
|
676 677 678 679 |
} return ret; } |
1da177e4c
|
680 681 |
/* A write operation does a read from user space and vice versa */ #define vrfy_dir(type) ((type) == READ ? VERIFY_WRITE : VERIFY_READ) |
ffecee4f2
|
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 |
/** * rw_copy_check_uvector() - Copy an array of &struct iovec from userspace * into the kernel and check that it is valid. * * @type: One of %CHECK_IOVEC_ONLY, %READ, or %WRITE. * @uvector: Pointer to the userspace array. * @nr_segs: Number of elements in userspace array. * @fast_segs: Number of elements in @fast_pointer. * @fast_pointer: Pointer to (usually small on-stack) kernel array. * @ret_pointer: (output parameter) Pointer to a variable that will point to * either @fast_pointer, a newly allocated kernel array, or NULL, * depending on which array was used. * * This function copies an array of &struct iovec of @nr_segs from * userspace into the kernel and checks that each element is valid (e.g. * it does not point to a kernel address or cause overflow by being too * large, etc.). * * As an optimization, the caller may provide a pointer to a small * on-stack array in @fast_pointer, typically %UIO_FASTIOV elements long * (the size of this array, or 0 if unused, should be given in @fast_segs). * * @ret_pointer will always point to the array that was used, so the * caller must take care not to call kfree() on it e.g. in case the * @fast_pointer array was used and it was allocated on the stack. * * Return: The total number of bytes covered by the iovec array on success * or a negative error code on error. */ |
eed4e51fb
|
711 712 713 |
ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_pointer, |
ac34ebb3a
|
714 |
struct iovec **ret_pointer) |
435f49a51
|
715 |
{ |
eed4e51fb
|
716 |
unsigned long seg; |
435f49a51
|
717 |
ssize_t ret; |
eed4e51fb
|
718 |
struct iovec *iov = fast_pointer; |
435f49a51
|
719 720 721 722 723 |
/* * SuS says "The readv() function *may* fail if the iovcnt argument * was less than or equal to 0, or greater than {IOV_MAX}. Linux has * traditionally returned zero for zero segments, so... */ |
eed4e51fb
|
724 725 |
if (nr_segs == 0) { ret = 0; |
435f49a51
|
726 |
goto out; |
eed4e51fb
|
727 |
} |
435f49a51
|
728 729 730 731 |
/* * First get the "struct iovec" from user memory and * verify all the pointers */ |
eed4e51fb
|
732 733 |
if (nr_segs > UIO_MAXIOV) { ret = -EINVAL; |
435f49a51
|
734 |
goto out; |
eed4e51fb
|
735 736 |
} if (nr_segs > fast_segs) { |
435f49a51
|
737 |
iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL); |
eed4e51fb
|
738 739 |
if (iov == NULL) { ret = -ENOMEM; |
435f49a51
|
740 |
goto out; |
eed4e51fb
|
741 |
} |
435f49a51
|
742 |
} |
eed4e51fb
|
743 744 |
if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector))) { ret = -EFAULT; |
435f49a51
|
745 |
goto out; |
eed4e51fb
|
746 |
} |
435f49a51
|
747 |
/* |
eed4e51fb
|
748 749 750 751 |
* According to the Single Unix Specification we should return EINVAL * if an element length is < 0 when cast to ssize_t or if the * total length would overflow the ssize_t return value of the * system call. |
435f49a51
|
752 753 754 755 |
* * Linux caps all read/write calls to MAX_RW_COUNT, and avoids the * overflow case. */ |
eed4e51fb
|
756 |
ret = 0; |
435f49a51
|
757 758 759 |
for (seg = 0; seg < nr_segs; seg++) { void __user *buf = iov[seg].iov_base; ssize_t len = (ssize_t)iov[seg].iov_len; |
eed4e51fb
|
760 761 762 |
/* see if we we're about to use an invalid len or if * it's about to overflow ssize_t */ |
435f49a51
|
763 |
if (len < 0) { |
eed4e51fb
|
764 |
ret = -EINVAL; |
435f49a51
|
765 |
goto out; |
eed4e51fb
|
766 |
} |
ac34ebb3a
|
767 |
if (type >= 0 |
fcf634098
|
768 |
&& unlikely(!access_ok(vrfy_dir(type), buf, len))) { |
eed4e51fb
|
769 |
ret = -EFAULT; |
435f49a51
|
770 771 772 773 774 |
goto out; } if (len > MAX_RW_COUNT - ret) { len = MAX_RW_COUNT - ret; iov[seg].iov_len = len; |
eed4e51fb
|
775 |
} |
eed4e51fb
|
776 |
ret += len; |
435f49a51
|
777 |
} |
eed4e51fb
|
778 779 780 781 |
out: *ret_pointer = iov; return ret; } |
f50298556
|
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 |
#ifdef CONFIG_COMPAT ssize_t compat_rw_copy_check_uvector(int type, const struct compat_iovec __user *uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_pointer, struct iovec **ret_pointer) { compat_ssize_t tot_len; struct iovec *iov = *ret_pointer = fast_pointer; ssize_t ret = 0; int seg; /* * SuS says "The readv() function *may* fail if the iovcnt argument * was less than or equal to 0, or greater than {IOV_MAX}. Linux has * traditionally returned zero for zero segments, so... */ if (nr_segs == 0) goto out; ret = -EINVAL; if (nr_segs > UIO_MAXIOV) goto out; if (nr_segs > fast_segs) { ret = -ENOMEM; iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL); if (iov == NULL) goto out; } *ret_pointer = iov; ret = -EFAULT; if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector))) goto out; /* * Single unix specification: * We should -EINVAL if an element length is not >= 0 and fitting an * ssize_t. * * In Linux, the total length is limited to MAX_RW_COUNT, there is * no overflow possibility. */ tot_len = 0; ret = -EINVAL; for (seg = 0; seg < nr_segs; seg++) { compat_uptr_t buf; compat_ssize_t len; if (__get_user(len, &uvector->iov_len) || __get_user(buf, &uvector->iov_base)) { ret = -EFAULT; goto out; } if (len < 0) /* size_t not fitting in compat_ssize_t .. */ goto out; if (type >= 0 && !access_ok(vrfy_dir(type), compat_ptr(buf), len)) { ret = -EFAULT; goto out; } if (len > MAX_RW_COUNT - tot_len) len = MAX_RW_COUNT - tot_len; tot_len += len; iov->iov_base = compat_ptr(buf); iov->iov_len = (compat_size_t) len; uvector++; iov++; } ret = tot_len; out: return ret; } #endif |
19c735868
|
856 |
static ssize_t do_iter_read(struct file *file, struct iov_iter *iter, |
ddef7ed2b
|
857 |
loff_t *pos, rwf_t flags) |
1da177e4c
|
858 |
{ |
1da177e4c
|
859 |
size_t tot_len; |
7687a7a44
|
860 |
ssize_t ret = 0; |
1da177e4c
|
861 |
|
edab5fe38
|
862 863 864 865 |
if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; |
7687a7a44
|
866 |
tot_len = iov_iter_count(iter); |
0504c074b
|
867 868 |
if (!tot_len) goto out; |
19c735868
|
869 |
ret = rw_verify_area(READ, file, pos, tot_len); |
e28cc7157
|
870 |
if (ret < 0) |
19c735868
|
871 |
return ret; |
1da177e4c
|
872 |
|
19c735868
|
873 874 |
if (file->f_op->read_iter) ret = do_iter_readv_writev(file, iter, pos, READ, flags); |
ee0b3e671
|
875 |
else |
19c735868
|
876 |
ret = do_loop_readv_writev(file, iter, pos, READ, flags); |
1da177e4c
|
877 |
out: |
19c735868
|
878 879 |
if (ret >= 0) fsnotify_access(file); |
1da177e4c
|
880 |
return ret; |
1da177e4c
|
881 |
} |
18e9710ee
|
882 |
ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, |
ddef7ed2b
|
883 |
rwf_t flags) |
7687a7a44
|
884 |
{ |
18e9710ee
|
885 886 887 888 889 |
if (!file->f_op->read_iter) return -EINVAL; return do_iter_read(file, iter, ppos, flags); } EXPORT_SYMBOL(vfs_iter_read); |
7687a7a44
|
890 |
|
19c735868
|
891 |
static ssize_t do_iter_write(struct file *file, struct iov_iter *iter, |
ddef7ed2b
|
892 |
loff_t *pos, rwf_t flags) |
19c735868
|
893 894 895 |
{ size_t tot_len; ssize_t ret = 0; |
03d95eb2f
|
896 |
|
edab5fe38
|
897 898 899 900 |
if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; |
19c735868
|
901 902 903 904 |
tot_len = iov_iter_count(iter); if (!tot_len) return 0; ret = rw_verify_area(WRITE, file, pos, tot_len); |
7687a7a44
|
905 906 |
if (ret < 0) return ret; |
19c735868
|
907 908 909 910 |
if (file->f_op->write_iter) ret = do_iter_readv_writev(file, iter, pos, WRITE, flags); else ret = do_loop_readv_writev(file, iter, pos, WRITE, flags); |
19c735868
|
911 912 |
if (ret > 0) fsnotify_modify(file); |
7687a7a44
|
913 914 |
return ret; } |
abbb65899
|
915 |
ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, |
ddef7ed2b
|
916 |
rwf_t flags) |
abbb65899
|
917 918 919 920 921 922 |
{ if (!file->f_op->write_iter) return -EINVAL; return do_iter_write(file, iter, ppos, flags); } EXPORT_SYMBOL(vfs_iter_write); |
1da177e4c
|
923 |
ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, |
ddef7ed2b
|
924 |
unsigned long vlen, loff_t *pos, rwf_t flags) |
1da177e4c
|
925 |
{ |
7687a7a44
|
926 927 928 929 |
struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; ssize_t ret; |
1da177e4c
|
930 |
|
251b42a1d
|
931 |
ret = import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); |
edab5fe38
|
932 933 934 935 |
if (ret >= 0) { ret = do_iter_read(file, &iter, pos, flags); kfree(iov); } |
1da177e4c
|
936 |
|
251b42a1d
|
937 938 |
return ret; } |
1da177e4c
|
939 |
|
9725d4cef
|
940 |
static ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, |
ddef7ed2b
|
941 |
unsigned long vlen, loff_t *pos, rwf_t flags) |
1da177e4c
|
942 |
{ |
251b42a1d
|
943 944 945 946 |
struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; ssize_t ret; |
1da177e4c
|
947 |
|
251b42a1d
|
948 |
ret = import_iovec(WRITE, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); |
edab5fe38
|
949 |
if (ret >= 0) { |
62473a2d6
|
950 |
file_start_write(file); |
edab5fe38
|
951 |
ret = do_iter_write(file, &iter, pos, flags); |
62473a2d6
|
952 |
file_end_write(file); |
edab5fe38
|
953 954 |
kfree(iov); } |
251b42a1d
|
955 |
return ret; |
1da177e4c
|
956 |
} |
1da177e4c
|
957 |
|
f17d8b354
|
958 |
static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec, |
ddef7ed2b
|
959 |
unsigned long vlen, rwf_t flags) |
1da177e4c
|
960 |
{ |
9c225f265
|
961 |
struct fd f = fdget_pos(fd); |
1da177e4c
|
962 |
ssize_t ret = -EBADF; |
1da177e4c
|
963 |
|
2903ff019
|
964 965 |
if (f.file) { loff_t pos = file_pos_read(f.file); |
f17d8b354
|
966 |
ret = vfs_readv(f.file, vec, vlen, &pos, flags); |
5faf153eb
|
967 968 |
if (ret >= 0) file_pos_write(f.file, pos); |
9c225f265
|
969 |
fdput_pos(f); |
1da177e4c
|
970 971 972 |
} if (ret > 0) |
4b98d11b4
|
973 974 |
add_rchar(current, ret); inc_syscr(current); |
1da177e4c
|
975 976 |
return ret; } |
f17d8b354
|
977 |
static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec, |
ddef7ed2b
|
978 |
unsigned long vlen, rwf_t flags) |
1da177e4c
|
979 |
{ |
9c225f265
|
980 |
struct fd f = fdget_pos(fd); |
1da177e4c
|
981 |
ssize_t ret = -EBADF; |
1da177e4c
|
982 |
|
2903ff019
|
983 984 |
if (f.file) { loff_t pos = file_pos_read(f.file); |
f17d8b354
|
985 |
ret = vfs_writev(f.file, vec, vlen, &pos, flags); |
5faf153eb
|
986 987 |
if (ret >= 0) file_pos_write(f.file, pos); |
9c225f265
|
988 |
fdput_pos(f); |
1da177e4c
|
989 990 991 |
} if (ret > 0) |
4b98d11b4
|
992 993 |
add_wchar(current, ret); inc_syscw(current); |
1da177e4c
|
994 995 |
return ret; } |
601cc11d0
|
996 997 998 999 1000 |
static inline loff_t pos_from_hilo(unsigned long high, unsigned long low) { #define HALF_LONG_BITS (BITS_PER_LONG / 2) return (((loff_t)high << HALF_LONG_BITS) << HALF_LONG_BITS) | low; } |
f17d8b354
|
1001 |
static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec, |
ddef7ed2b
|
1002 |
unsigned long vlen, loff_t pos, rwf_t flags) |
f3554f4bc
|
1003 |
{ |
2903ff019
|
1004 |
struct fd f; |
f3554f4bc
|
1005 |
ssize_t ret = -EBADF; |
f3554f4bc
|
1006 1007 1008 |
if (pos < 0) return -EINVAL; |
2903ff019
|
1009 1010 |
f = fdget(fd); if (f.file) { |
f3554f4bc
|
1011 |
ret = -ESPIPE; |
2903ff019
|
1012 |
if (f.file->f_mode & FMODE_PREAD) |
f17d8b354
|
1013 |
ret = vfs_readv(f.file, vec, vlen, &pos, flags); |
2903ff019
|
1014 |
fdput(f); |
f3554f4bc
|
1015 1016 1017 1018 1019 1020 1021 |
} if (ret > 0) add_rchar(current, ret); inc_syscr(current); return ret; } |
f17d8b354
|
1022 |
static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec, |
ddef7ed2b
|
1023 |
unsigned long vlen, loff_t pos, rwf_t flags) |
f3554f4bc
|
1024 |
{ |
2903ff019
|
1025 |
struct fd f; |
f3554f4bc
|
1026 |
ssize_t ret = -EBADF; |
f3554f4bc
|
1027 1028 1029 |
if (pos < 0) return -EINVAL; |
2903ff019
|
1030 1031 |
f = fdget(fd); if (f.file) { |
f3554f4bc
|
1032 |
ret = -ESPIPE; |
2903ff019
|
1033 |
if (f.file->f_mode & FMODE_PWRITE) |
f17d8b354
|
1034 |
ret = vfs_writev(f.file, vec, vlen, &pos, flags); |
2903ff019
|
1035 |
fdput(f); |
f3554f4bc
|
1036 1037 1038 1039 1040 1041 1042 |
} if (ret > 0) add_wchar(current, ret); inc_syscw(current); return ret; } |
f17d8b354
|
1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 |
SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen) { return do_readv(fd, vec, vlen, 0); } SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen) { return do_writev(fd, vec, vlen, 0); } SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) { loff_t pos = pos_from_hilo(pos_h, pos_l); return do_preadv(fd, vec, vlen, pos, 0); } SYSCALL_DEFINE6(preadv2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, |
ddef7ed2b
|
1065 |
rwf_t, flags) |
f17d8b354
|
1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 |
{ loff_t pos = pos_from_hilo(pos_h, pos_l); if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) { loff_t pos = pos_from_hilo(pos_h, pos_l); return do_pwritev(fd, vec, vlen, pos, 0); } SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, |
ddef7ed2b
|
1085 |
rwf_t, flags) |
f17d8b354
|
1086 1087 1088 1089 1090 1091 1092 1093 |
{ loff_t pos = pos_from_hilo(pos_h, pos_l); if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } |
72ec35163
|
1094 |
#ifdef CONFIG_COMPAT |
72ec35163
|
1095 1096 |
static size_t compat_readv(struct file *file, const struct compat_iovec __user *vec, |
ddef7ed2b
|
1097 |
unsigned long vlen, loff_t *pos, rwf_t flags) |
72ec35163
|
1098 |
{ |
72ec35163
|
1099 1100 |
struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; |
ac15ac066
|
1101 |
struct iov_iter iter; |
72ec35163
|
1102 |
ssize_t ret; |
72ec35163
|
1103 |
|
26c87fb7d
|
1104 |
ret = compat_import_iovec(READ, vec, vlen, UIO_FASTIOV, &iov, &iter); |
edab5fe38
|
1105 1106 1107 1108 |
if (ret >= 0) { ret = do_iter_read(file, &iter, pos, flags); kfree(iov); } |
72ec35163
|
1109 1110 1111 1112 1113 |
if (ret > 0) add_rchar(current, ret); inc_syscr(current); return ret; } |
f17d8b354
|
1114 1115 |
static size_t do_compat_readv(compat_ulong_t fd, const struct compat_iovec __user *vec, |
ddef7ed2b
|
1116 |
compat_ulong_t vlen, rwf_t flags) |
72ec35163
|
1117 |
{ |
9c225f265
|
1118 |
struct fd f = fdget_pos(fd); |
72ec35163
|
1119 1120 1121 1122 1123 1124 |
ssize_t ret; loff_t pos; if (!f.file) return -EBADF; pos = f.file->f_pos; |
f17d8b354
|
1125 |
ret = compat_readv(f.file, vec, vlen, &pos, flags); |
5faf153eb
|
1126 1127 |
if (ret >= 0) f.file->f_pos = pos; |
9c225f265
|
1128 |
fdput_pos(f); |
72ec35163
|
1129 |
return ret; |
f17d8b354
|
1130 |
|
72ec35163
|
1131 |
} |
f17d8b354
|
1132 1133 1134 1135 1136 1137 1138 1139 |
COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd, const struct compat_iovec __user *,vec, compat_ulong_t, vlen) { return do_compat_readv(fd, vec, vlen, 0); } static long do_compat_preadv64(unsigned long fd, |
378a10f3a
|
1140 |
const struct compat_iovec __user *vec, |
ddef7ed2b
|
1141 |
unsigned long vlen, loff_t pos, rwf_t flags) |
72ec35163
|
1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 |
{ struct fd f; ssize_t ret; if (pos < 0) return -EINVAL; f = fdget(fd); if (!f.file) return -EBADF; ret = -ESPIPE; if (f.file->f_mode & FMODE_PREAD) |
f17d8b354
|
1153 |
ret = compat_readv(f.file, vec, vlen, &pos, flags); |
72ec35163
|
1154 1155 1156 |
fdput(f); return ret; } |
378a10f3a
|
1157 1158 1159 1160 1161 |
#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd, const struct compat_iovec __user *,vec, unsigned long, vlen, loff_t, pos) { |
f17d8b354
|
1162 |
return do_compat_preadv64(fd, vec, vlen, pos, 0); |
378a10f3a
|
1163 1164 |
} #endif |
dfd948e32
|
1165 |
COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd, |
72ec35163
|
1166 |
const struct compat_iovec __user *,vec, |
dfd948e32
|
1167 |
compat_ulong_t, vlen, u32, pos_low, u32, pos_high) |
72ec35163
|
1168 1169 |
{ loff_t pos = ((loff_t)pos_high << 32) | pos_low; |
378a10f3a
|
1170 |
|
f17d8b354
|
1171 1172 |
return do_compat_preadv64(fd, vec, vlen, pos, 0); } |
3ebfd81f7
|
1173 1174 1175 |
#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd, const struct compat_iovec __user *,vec, |
ddef7ed2b
|
1176 |
unsigned long, vlen, loff_t, pos, rwf_t, flags) |
3ebfd81f7
|
1177 1178 1179 1180 |
{ return do_compat_preadv64(fd, vec, vlen, pos, flags); } #endif |
f17d8b354
|
1181 1182 1183 |
COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd, const struct compat_iovec __user *,vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high, |
ddef7ed2b
|
1184 |
rwf_t, flags) |
f17d8b354
|
1185 1186 1187 1188 1189 1190 1191 |
{ loff_t pos = ((loff_t)pos_high << 32) | pos_low; if (pos == -1) return do_compat_readv(fd, vec, vlen, flags); return do_compat_preadv64(fd, vec, vlen, pos, flags); |
72ec35163
|
1192 1193 1194 1195 |
} static size_t compat_writev(struct file *file, const struct compat_iovec __user *vec, |
ddef7ed2b
|
1196 |
unsigned long vlen, loff_t *pos, rwf_t flags) |
72ec35163
|
1197 |
{ |
26c87fb7d
|
1198 1199 1200 |
struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; |
edab5fe38
|
1201 |
ssize_t ret; |
72ec35163
|
1202 |
|
26c87fb7d
|
1203 |
ret = compat_import_iovec(WRITE, vec, vlen, UIO_FASTIOV, &iov, &iter); |
edab5fe38
|
1204 |
if (ret >= 0) { |
62473a2d6
|
1205 |
file_start_write(file); |
edab5fe38
|
1206 |
ret = do_iter_write(file, &iter, pos, flags); |
62473a2d6
|
1207 |
file_end_write(file); |
edab5fe38
|
1208 1209 |
kfree(iov); } |
72ec35163
|
1210 1211 1212 1213 1214 |
if (ret > 0) add_wchar(current, ret); inc_syscw(current); return ret; } |
f17d8b354
|
1215 1216 |
static size_t do_compat_writev(compat_ulong_t fd, const struct compat_iovec __user* vec, |
ddef7ed2b
|
1217 |
compat_ulong_t vlen, rwf_t flags) |
72ec35163
|
1218 |
{ |
9c225f265
|
1219 |
struct fd f = fdget_pos(fd); |
72ec35163
|
1220 1221 1222 1223 1224 1225 |
ssize_t ret; loff_t pos; if (!f.file) return -EBADF; pos = f.file->f_pos; |
f17d8b354
|
1226 |
ret = compat_writev(f.file, vec, vlen, &pos, flags); |
5faf153eb
|
1227 1228 |
if (ret >= 0) f.file->f_pos = pos; |
9c225f265
|
1229 |
fdput_pos(f); |
72ec35163
|
1230 1231 |
return ret; } |
f17d8b354
|
1232 1233 1234 1235 1236 1237 1238 1239 |
COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd, const struct compat_iovec __user *, vec, compat_ulong_t, vlen) { return do_compat_writev(fd, vec, vlen, 0); } static long do_compat_pwritev64(unsigned long fd, |
378a10f3a
|
1240 |
const struct compat_iovec __user *vec, |
ddef7ed2b
|
1241 |
unsigned long vlen, loff_t pos, rwf_t flags) |
72ec35163
|
1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 |
{ struct fd f; ssize_t ret; if (pos < 0) return -EINVAL; f = fdget(fd); if (!f.file) return -EBADF; ret = -ESPIPE; if (f.file->f_mode & FMODE_PWRITE) |
f17d8b354
|
1253 |
ret = compat_writev(f.file, vec, vlen, &pos, flags); |
72ec35163
|
1254 1255 1256 |
fdput(f); return ret; } |
378a10f3a
|
1257 1258 1259 1260 1261 |
#ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64 COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd, const struct compat_iovec __user *,vec, unsigned long, vlen, loff_t, pos) { |
f17d8b354
|
1262 |
return do_compat_pwritev64(fd, vec, vlen, pos, 0); |
378a10f3a
|
1263 1264 |
} #endif |
dfd948e32
|
1265 |
COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd, |
72ec35163
|
1266 |
const struct compat_iovec __user *,vec, |
dfd948e32
|
1267 |
compat_ulong_t, vlen, u32, pos_low, u32, pos_high) |
72ec35163
|
1268 1269 |
{ loff_t pos = ((loff_t)pos_high << 32) | pos_low; |
378a10f3a
|
1270 |
|
f17d8b354
|
1271 |
return do_compat_pwritev64(fd, vec, vlen, pos, 0); |
72ec35163
|
1272 |
} |
f17d8b354
|
1273 |
|
3ebfd81f7
|
1274 1275 1276 |
#ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd, const struct compat_iovec __user *,vec, |
ddef7ed2b
|
1277 |
unsigned long, vlen, loff_t, pos, rwf_t, flags) |
3ebfd81f7
|
1278 1279 1280 1281 |
{ return do_compat_pwritev64(fd, vec, vlen, pos, flags); } #endif |
f17d8b354
|
1282 1283 |
COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd, const struct compat_iovec __user *,vec, |
ddef7ed2b
|
1284 |
compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags) |
f17d8b354
|
1285 1286 1287 1288 1289 1290 1291 |
{ loff_t pos = ((loff_t)pos_high << 32) | pos_low; if (pos == -1) return do_compat_writev(fd, vec, vlen, flags); return do_compat_pwritev64(fd, vec, vlen, pos, flags); |
72ec35163
|
1292 |
} |
f17d8b354
|
1293 |
|
72ec35163
|
1294 |
#endif |
19f4fc3ae
|
1295 1296 |
static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, size_t count, loff_t max) |
1da177e4c
|
1297 |
{ |
2903ff019
|
1298 1299 |
struct fd in, out; struct inode *in_inode, *out_inode; |
1da177e4c
|
1300 |
loff_t pos; |
7995bd287
|
1301 |
loff_t out_pos; |
1da177e4c
|
1302 |
ssize_t retval; |
2903ff019
|
1303 |
int fl; |
1da177e4c
|
1304 1305 1306 1307 1308 |
/* * Get input file, and verify that it is ok.. */ retval = -EBADF; |
2903ff019
|
1309 1310 |
in = fdget(in_fd); if (!in.file) |
1da177e4c
|
1311 |
goto out; |
2903ff019
|
1312 |
if (!(in.file->f_mode & FMODE_READ)) |
1da177e4c
|
1313 |
goto fput_in; |
1da177e4c
|
1314 |
retval = -ESPIPE; |
7995bd287
|
1315 1316 1317 1318 |
if (!ppos) { pos = in.file->f_pos; } else { pos = *ppos; |
2903ff019
|
1319 |
if (!(in.file->f_mode & FMODE_PREAD)) |
1da177e4c
|
1320 |
goto fput_in; |
7995bd287
|
1321 1322 |
} retval = rw_verify_area(READ, in.file, &pos, count); |
e28cc7157
|
1323 |
if (retval < 0) |
1da177e4c
|
1324 |
goto fput_in; |
bc61384dc
|
1325 1326 |
if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; |
1da177e4c
|
1327 |
|
1da177e4c
|
1328 1329 1330 1331 |
/* * Get output file, and verify that it is ok.. */ retval = -EBADF; |
2903ff019
|
1332 1333 |
out = fdget(out_fd); if (!out.file) |
1da177e4c
|
1334 |
goto fput_in; |
2903ff019
|
1335 |
if (!(out.file->f_mode & FMODE_WRITE)) |
1da177e4c
|
1336 1337 |
goto fput_out; retval = -EINVAL; |
496ad9aa8
|
1338 1339 |
in_inode = file_inode(in.file); out_inode = file_inode(out.file); |
7995bd287
|
1340 1341 |
out_pos = out.file->f_pos; retval = rw_verify_area(WRITE, out.file, &out_pos, count); |
e28cc7157
|
1342 |
if (retval < 0) |
1da177e4c
|
1343 |
goto fput_out; |
1da177e4c
|
1344 1345 |
if (!max) max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes); |
1da177e4c
|
1346 1347 1348 1349 1350 1351 |
if (unlikely(pos + count > max)) { retval = -EOVERFLOW; if (pos >= max) goto fput_out; count = max - pos; } |
d96e6e716
|
1352 |
fl = 0; |
534f2aaa6
|
1353 |
#if 0 |
d96e6e716
|
1354 1355 1356 1357 1358 1359 |
/* * We need to debate whether we can enable this or not. The * man page documents EAGAIN return for the output at least, * and the application is arguably buggy if it doesn't expect * EAGAIN on a non-blocking file descriptor. */ |
2903ff019
|
1360 |
if (in.file->f_flags & O_NONBLOCK) |
d96e6e716
|
1361 |
fl = SPLICE_F_NONBLOCK; |
534f2aaa6
|
1362 |
#endif |
50cd2c577
|
1363 |
file_start_write(out.file); |
7995bd287
|
1364 |
retval = do_splice_direct(in.file, &pos, out.file, &out_pos, count, fl); |
50cd2c577
|
1365 |
file_end_write(out.file); |
1da177e4c
|
1366 1367 |
if (retval > 0) { |
4b98d11b4
|
1368 1369 |
add_rchar(current, retval); add_wchar(current, retval); |
a68c2f12b
|
1370 1371 |
fsnotify_access(in.file); fsnotify_modify(out.file); |
7995bd287
|
1372 1373 1374 1375 1376 |
out.file->f_pos = out_pos; if (ppos) *ppos = pos; else in.file->f_pos = pos; |
1da177e4c
|
1377 |
} |
1da177e4c
|
1378 |
|
4b98d11b4
|
1379 1380 |
inc_syscr(current); inc_syscw(current); |
7995bd287
|
1381 |
if (pos > max) |
1da177e4c
|
1382 1383 1384 |
retval = -EOVERFLOW; fput_out: |
2903ff019
|
1385 |
fdput(out); |
1da177e4c
|
1386 |
fput_in: |
2903ff019
|
1387 |
fdput(in); |
1da177e4c
|
1388 1389 1390 |
out: return retval; } |
002c8976e
|
1391 |
SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, off_t __user *, offset, size_t, count) |
1da177e4c
|
1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 |
{ loff_t pos; off_t off; ssize_t ret; if (offset) { if (unlikely(get_user(off, offset))) return -EFAULT; pos = off; ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } |
002c8976e
|
1409 |
SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, loff_t __user *, offset, size_t, count) |
1da177e4c
|
1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 |
{ loff_t pos; ssize_t ret; if (offset) { if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t)))) return -EFAULT; ret = do_sendfile(out_fd, in_fd, &pos, count, 0); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } |
19f4fc3ae
|
1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 |
#ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, compat_off_t __user *, offset, compat_size_t, count) { loff_t pos; off_t off; ssize_t ret; if (offset) { if (unlikely(get_user(off, offset))) return -EFAULT; pos = off; ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, compat_loff_t __user *, offset, compat_size_t, count) { loff_t pos; ssize_t ret; if (offset) { if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t)))) return -EFAULT; ret = do_sendfile(out_fd, in_fd, &pos, count, 0); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } #endif |
29732938a
|
1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 |
/* * copy_file_range() differs from regular file read and write in that it * specifically allows return partial success. When it does so is up to * the copy_file_range method. */ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len, unsigned int flags) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); ssize_t ret; if (flags != 0) return -EINVAL; |
11cbfb107
|
1481 1482 1483 1484 |
if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) return -EISDIR; if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) return -EINVAL; |
29732938a
|
1485 |
ret = rw_verify_area(READ, file_in, &pos_in, len); |
bc61384dc
|
1486 1487 1488 1489 1490 |
if (unlikely(ret)) return ret; ret = rw_verify_area(WRITE, file_out, &pos_out, len); if (unlikely(ret)) |
29732938a
|
1491 1492 1493 1494 |
return ret; if (!(file_in->f_mode & FMODE_READ) || !(file_out->f_mode & FMODE_WRITE) || |
eac70053a
|
1495 |
(file_out->f_flags & O_APPEND)) |
29732938a
|
1496 1497 1498 1499 1500 1501 1502 1503 |
return -EBADF; /* this could be relaxed once a method supports cross-fs copies */ if (inode_in->i_sb != inode_out->i_sb) return -EXDEV; if (len == 0) return 0; |
bfe219d37
|
1504 |
file_start_write(file_out); |
29732938a
|
1505 |
|
a76b5b043
|
1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 |
/* * Try cloning first, this is supported by more file systems, and * more efficient if both clone and copy are supported (e.g. NFS). */ if (file_in->f_op->clone_file_range) { ret = file_in->f_op->clone_file_range(file_in, pos_in, file_out, pos_out, len); if (ret == 0) { ret = len; goto done; } } if (file_out->f_op->copy_file_range) { |
eac70053a
|
1520 1521 |
ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out, pos_out, len, flags); |
a76b5b043
|
1522 1523 1524 |
if (ret != -EOPNOTSUPP) goto done; } |
eac70053a
|
1525 |
|
a76b5b043
|
1526 1527 |
ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out, len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0); |
eac70053a
|
1528 |
|
a76b5b043
|
1529 |
done: |
29732938a
|
1530 1531 1532 1533 1534 1535 |
if (ret > 0) { fsnotify_access(file_in); add_rchar(current, ret); fsnotify_modify(file_out); add_wchar(current, ret); } |
a76b5b043
|
1536 |
|
29732938a
|
1537 1538 |
inc_syscr(current); inc_syscw(current); |
bfe219d37
|
1539 |
file_end_write(file_out); |
29732938a
|
1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 |
return ret; } EXPORT_SYMBOL(vfs_copy_file_range); SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags) { loff_t pos_in; loff_t pos_out; struct fd f_in; struct fd f_out; ssize_t ret = -EBADF; f_in = fdget(fd_in); if (!f_in.file) goto out2; f_out = fdget(fd_out); if (!f_out.file) goto out1; ret = -EFAULT; if (off_in) { if (copy_from_user(&pos_in, off_in, sizeof(loff_t))) goto out; } else { pos_in = f_in.file->f_pos; } if (off_out) { if (copy_from_user(&pos_out, off_out, sizeof(loff_t))) goto out; } else { pos_out = f_out.file->f_pos; } ret = vfs_copy_file_range(f_in.file, pos_in, f_out.file, pos_out, len, flags); if (ret > 0) { pos_in += ret; pos_out += ret; if (off_in) { if (copy_to_user(off_in, &pos_in, sizeof(loff_t))) ret = -EFAULT; } else { f_in.file->f_pos = pos_in; } if (off_out) { if (copy_to_user(off_out, &pos_out, sizeof(loff_t))) ret = -EFAULT; } else { f_out.file->f_pos = pos_out; } } out: fdput(f_out); out1: fdput(f_in); out2: return ret; } |
04b38d601
|
1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 |
static int clone_verify_area(struct file *file, loff_t pos, u64 len, bool write) { struct inode *inode = file_inode(file); if (unlikely(pos < 0)) return -EINVAL; if (unlikely((loff_t) (pos + len) < 0)) return -EINVAL; if (unlikely(inode->i_flctx && mandatory_lock(inode))) { loff_t end = len ? pos + len - 1 : OFFSET_MAX; int retval; retval = locks_mandatory_area(inode, file, pos, end, write ? F_WRLCK : F_RDLCK); if (retval < 0) return retval; } return security_file_permission(file, write ? MAY_WRITE : MAY_READ); } |
876bec6f9
|
1629 1630 1631 1632 |
/* * Check that the two inodes are eligible for cloning, the ranges make * sense, and then flush all dirty data. Caller must ensure that the * inodes have been locked against any other modifications. |
22725ce4e
|
1633 1634 1635 |
* * Returns: 0 for "nothing to clone", 1 for "something to clone", or * the usual negative error code. |
876bec6f9
|
1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 |
*/ int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, struct inode *inode_out, loff_t pos_out, u64 *len, bool is_dedupe) { loff_t bs = inode_out->i_sb->s_blocksize; loff_t blen; loff_t isize; bool same_inode = (inode_in == inode_out); int ret; /* Don't touch certain kinds of inodes */ if (IS_IMMUTABLE(inode_out)) return -EPERM; if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out)) return -ETXTBSY; /* Don't reflink dirs, pipes, sockets... */ if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) return -EISDIR; if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) return -EINVAL; /* Are we going all the way to the end? */ isize = i_size_read(inode_in); |
22725ce4e
|
1662 |
if (isize == 0) |
876bec6f9
|
1663 |
return 0; |
876bec6f9
|
1664 1665 1666 |
/* Zero length dedupe exits immediately; reflink goes to EOF. */ if (*len == 0) { |
22725ce4e
|
1667 |
if (is_dedupe || pos_in == isize) |
876bec6f9
|
1668 |
return 0; |
22725ce4e
|
1669 1670 |
if (pos_in > isize) return -EINVAL; |
876bec6f9
|
1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 |
*len = isize - pos_in; } /* Ensure offsets don't wrap and the input is inside i_size */ if (pos_in + *len < pos_in || pos_out + *len < pos_out || pos_in + *len > isize) return -EINVAL; /* Don't allow dedupe past EOF in the dest file */ if (is_dedupe) { loff_t disize; disize = i_size_read(inode_out); if (pos_out >= disize || pos_out + *len > disize) return -EINVAL; } /* If we're linking to EOF, continue to the block boundary. */ if (pos_in + *len == isize) blen = ALIGN(isize, bs) - pos_in; else blen = *len; /* Only reflink if we're aligned to block boundaries */ if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) || !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs)) return -EINVAL; /* Don't allow overlapped reflink within the same file */ if (same_inode) { if (pos_out + blen > pos_in && pos_out < pos_in + blen) return -EINVAL; } /* Wait for the completion of any pending IOs on both files */ inode_dio_wait(inode_in); if (!same_inode) inode_dio_wait(inode_out); ret = filemap_write_and_wait_range(inode_in->i_mapping, pos_in, pos_in + *len - 1); if (ret) return ret; ret = filemap_write_and_wait_range(inode_out->i_mapping, pos_out, pos_out + *len - 1); if (ret) return ret; /* * Check that the extents are the same. */ if (is_dedupe) { bool is_same = false; ret = vfs_dedupe_file_range_compare(inode_in, pos_in, inode_out, pos_out, *len, &is_same); if (ret) return ret; if (!is_same) return -EBADE; } |
22725ce4e
|
1733 |
return 1; |
876bec6f9
|
1734 1735 |
} EXPORT_SYMBOL(vfs_clone_file_prep_inodes); |
04b38d601
|
1736 1737 1738 1739 1740 1741 |
int vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); int ret; |
b335e9d99
|
1742 1743 1744 1745 |
if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) return -EISDIR; if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) return -EINVAL; |
913b86e92
|
1746 1747 1748 1749 1750 1751 |
/* * FICLONE/FICLONERANGE ioctls enforce that src and dest files are on * the same mount. Practically, they only need to be on the same file * system. */ if (inode_in->i_sb != inode_out->i_sb) |
04b38d601
|
1752 |
return -EXDEV; |
04b38d601
|
1753 1754 |
if (!(file_in->f_mode & FMODE_READ) || !(file_out->f_mode & FMODE_WRITE) || |
0fcbf996d
|
1755 |
(file_out->f_flags & O_APPEND)) |
04b38d601
|
1756 |
return -EBADF; |
0fcbf996d
|
1757 1758 |
if (!file_in->f_op->clone_file_range) return -EOPNOTSUPP; |
04b38d601
|
1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 |
ret = clone_verify_area(file_in, pos_in, len, false); if (ret) return ret; ret = clone_verify_area(file_out, pos_out, len, true); if (ret) return ret; if (pos_in + len > i_size_read(inode_in)) return -EINVAL; |
04b38d601
|
1769 1770 1771 1772 1773 1774 |
ret = file_in->f_op->clone_file_range(file_in, pos_in, file_out, pos_out, len); if (!ret) { fsnotify_access(file_in); fsnotify_modify(file_out); } |
04b38d601
|
1775 1776 1777 |
return ret; } EXPORT_SYMBOL(vfs_clone_file_range); |
54dbc1517
|
1778 |
|
876bec6f9
|
1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 |
/* * Read a page's worth of file data into the page cache. Return the page * locked. */ static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset) { struct address_space *mapping; struct page *page; pgoff_t n; n = offset >> PAGE_SHIFT; mapping = inode->i_mapping; page = read_mapping_page(mapping, n, NULL); if (IS_ERR(page)) return page; if (!PageUptodate(page)) { put_page(page); return ERR_PTR(-EIO); } lock_page(page); return page; } /* * Compare extents of two files to see if they are the same. * Caller must have locked both inodes to prevent write races. */ int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, struct inode *dest, loff_t destoff, loff_t len, bool *is_same) { loff_t src_poff; loff_t dest_poff; void *src_addr; void *dest_addr; struct page *src_page; struct page *dest_page; loff_t cmp_len; bool same; int error; error = -EINVAL; same = true; while (len) { src_poff = srcoff & (PAGE_SIZE - 1); dest_poff = destoff & (PAGE_SIZE - 1); cmp_len = min(PAGE_SIZE - src_poff, PAGE_SIZE - dest_poff); cmp_len = min(cmp_len, len); if (cmp_len <= 0) goto out_error; src_page = vfs_dedupe_get_page(src, srcoff); if (IS_ERR(src_page)) { error = PTR_ERR(src_page); goto out_error; } dest_page = vfs_dedupe_get_page(dest, destoff); if (IS_ERR(dest_page)) { error = PTR_ERR(dest_page); unlock_page(src_page); put_page(src_page); goto out_error; } src_addr = kmap_atomic(src_page); dest_addr = kmap_atomic(dest_page); flush_dcache_page(src_page); flush_dcache_page(dest_page); if (memcmp(src_addr + src_poff, dest_addr + dest_poff, cmp_len)) same = false; kunmap_atomic(dest_addr); kunmap_atomic(src_addr); unlock_page(dest_page); unlock_page(src_page); put_page(dest_page); put_page(src_page); if (!same) break; srcoff += cmp_len; destoff += cmp_len; len -= cmp_len; } *is_same = same; return 0; out_error: return error; } EXPORT_SYMBOL(vfs_dedupe_file_range_compare); |
54dbc1517
|
1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 |
int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same) { struct file_dedupe_range_info *info; struct inode *src = file_inode(file); u64 off; u64 len; int i; int ret; bool is_admin = capable(CAP_SYS_ADMIN); u16 count = same->dest_count; struct file *dst_file; loff_t dst_off; ssize_t deduped; if (!(file->f_mode & FMODE_READ)) return -EINVAL; if (same->reserved1 || same->reserved2) return -EINVAL; off = same->src_offset; len = same->src_length; ret = -EISDIR; if (S_ISDIR(src->i_mode)) goto out; ret = -EINVAL; if (!S_ISREG(src->i_mode)) goto out; ret = clone_verify_area(file, off, len, false); if (ret < 0) goto out; ret = 0; |
22725ce4e
|
1909 1910 |
if (off + len > i_size_read(src)) return -EINVAL; |
54dbc1517
|
1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 |
/* pre-format output fields to sane values */ for (i = 0; i < count; i++) { same->info[i].bytes_deduped = 0ULL; same->info[i].status = FILE_DEDUPE_RANGE_SAME; } for (i = 0, info = same->info; i < count; i++, info++) { struct inode *dst; struct fd dst_fd = fdget(info->dest_fd); dst_file = dst_fd.file; if (!dst_file) { info->status = -EBADF; goto next_loop; } dst = file_inode(dst_file); ret = mnt_want_write_file(dst_file); if (ret) { info->status = ret; goto next_loop; } dst_off = info->dest_offset; ret = clone_verify_area(dst_file, dst_off, len, true); if (ret < 0) { info->status = ret; goto next_file; } ret = 0; if (info->reserved) { info->status = -EINVAL; } else if (!(is_admin || (dst_file->f_mode & FMODE_WRITE))) { info->status = -EINVAL; } else if (file->f_path.mnt != dst_file->f_path.mnt) { info->status = -EXDEV; } else if (S_ISDIR(dst->i_mode)) { info->status = -EISDIR; } else if (dst_file->f_op->dedupe_file_range == NULL) { info->status = -EINVAL; } else { deduped = dst_file->f_op->dedupe_file_range(file, off, len, dst_file, info->dest_offset); if (deduped == -EBADE) info->status = FILE_DEDUPE_RANGE_DIFFERS; else if (deduped < 0) info->status = deduped; else info->bytes_deduped += deduped; } next_file: mnt_drop_write_file(dst_file); next_loop: fdput(dst_fd); |
e62e560fc
|
1968 1969 1970 |
if (fatal_signal_pending(current)) goto out; |
54dbc1517
|
1971 1972 1973 1974 1975 1976 |
} out: return ret; } EXPORT_SYMBOL(vfs_dedupe_file_range); |