Blame view
fs/file.c
23.5 KB
1da177e4c
|
1 2 3 4 5 6 7 |
/* * linux/fs/file.c * * Copyright (C) 1998-1999, Stephen Tweedie and Bill Hawes * * Manage the dynamic fd arrays in the process files_struct. */ |
fe17f22d7
|
8 |
#include <linux/syscalls.h> |
630d9c472
|
9 |
#include <linux/export.h> |
1da177e4c
|
10 11 |
#include <linux/fs.h> #include <linux/mm.h> |
6d4831c28
|
12 |
#include <linux/mmzone.h> |
1da177e4c
|
13 |
#include <linux/time.h> |
d43c36dc6
|
14 |
#include <linux/sched.h> |
1da177e4c
|
15 16 17 |
#include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/file.h> |
9f3acc314
|
18 |
#include <linux/fdtable.h> |
1da177e4c
|
19 |
#include <linux/bitops.h> |
ab2af1f50
|
20 21 22 23 |
#include <linux/interrupt.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> |
9cfe015aa
|
24 |
int sysctl_nr_open __read_mostly = 1024*1024; |
eceea0b3d
|
25 |
int sysctl_nr_open_min = BITS_PER_LONG; |
752343be6
|
26 27 28 |
/* our min() is unusable in constant expressions ;-/ */ #define __const_min(x, y) ((x) < (y) ? (x) : (y)) int sysctl_nr_open_max = __const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & |
7f4b36f9b
|
29 |
-BITS_PER_LONG; |
9cfe015aa
|
30 |
|
1fd36adcd
|
31 |
static void *alloc_fdmem(size_t size) |
1da177e4c
|
32 |
{ |
6d4831c28
|
33 34 35 36 37 |
/* * Very large allocations can stress page reclaim, so fall back to * vmalloc() if the allocation size will be considered "large" by the VM. */ if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { |
5d097056c
|
38 39 |
void *data = kmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_NOWARN | __GFP_NORETRY); |
6d4831c28
|
40 41 42 |
if (data != NULL) return data; } |
5d097056c
|
43 |
return __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_HIGHMEM, PAGE_KERNEL); |
1da177e4c
|
44 |
} |
a892e2d7d
|
45 |
static void __free_fdtable(struct fdtable *fdt) |
1da177e4c
|
46 |
{ |
f6c0a1920
|
47 48 |
kvfree(fdt->fd); kvfree(fdt->open_fds); |
a892e2d7d
|
49 |
kfree(fdt); |
ab2af1f50
|
50 |
} |
1da177e4c
|
51 |
|
7cf4dc3c8
|
52 |
static void free_fdtable_rcu(struct rcu_head *rcu) |
ab2af1f50
|
53 |
{ |
ac3e3c5b1
|
54 |
__free_fdtable(container_of(rcu, struct fdtable, rcu)); |
ab2af1f50
|
55 |
} |
f3f86e33d
|
56 57 |
#define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) #define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) |
ab2af1f50
|
58 |
/* |
ea5c58e70
|
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 |
* Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */ static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, unsigned int count) { unsigned int cpy, set; cpy = count / BITS_PER_BYTE; set = (nfdt->max_fds - count) / BITS_PER_BYTE; memcpy(nfdt->open_fds, ofdt->open_fds, cpy); memset((char *)nfdt->open_fds + cpy, 0, set); memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy); memset((char *)nfdt->close_on_exec + cpy, 0, set); cpy = BITBIT_SIZE(count); set = BITBIT_SIZE(nfdt->max_fds) - cpy; memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy); memset((char *)nfdt->full_fds_bits + cpy, 0, set); } /* * Copy all file descriptors from the old table to the new, expanded table and * clear the extra space. Called with the files spinlock held for write. |
ab2af1f50
|
84 |
*/ |
5466b456e
|
85 |
static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) |
ab2af1f50
|
86 |
{ |
5466b456e
|
87 |
unsigned int cpy, set; |
ab2af1f50
|
88 |
|
5466b456e
|
89 |
BUG_ON(nfdt->max_fds < ofdt->max_fds); |
5466b456e
|
90 91 92 93 |
cpy = ofdt->max_fds * sizeof(struct file *); set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *); memcpy(nfdt->fd, ofdt->fd, cpy); |
ea5c58e70
|
94 |
memset((char *)nfdt->fd + cpy, 0, set); |
5466b456e
|
95 |
|
ea5c58e70
|
96 |
copy_fd_bitmaps(nfdt, ofdt, ofdt->max_fds); |
1da177e4c
|
97 |
} |
5466b456e
|
98 |
static struct fdtable * alloc_fdtable(unsigned int nr) |
1da177e4c
|
99 |
{ |
5466b456e
|
100 |
struct fdtable *fdt; |
1fd36adcd
|
101 |
void *data; |
1da177e4c
|
102 |
|
ab2af1f50
|
103 |
/* |
5466b456e
|
104 105 106 107 108 |
* Figure out how many fds we actually want to support in this fdtable. * Allocation steps are keyed to the size of the fdarray, since it * grows far faster than any of the other dynamic data. We try to fit * the fdarray into comfortable page-tuned chunks: starting at 1024B * and growing in powers of two from there on. |
ab2af1f50
|
109 |
*/ |
5466b456e
|
110 111 112 |
nr /= (1024 / sizeof(struct file *)); nr = roundup_pow_of_two(nr + 1); nr *= (1024 / sizeof(struct file *)); |
5c598b342
|
113 114 115 116 117 118 119 120 121 122 |
/* * Note that this can drive nr *below* what we had passed if sysctl_nr_open * had been set lower between the check in expand_files() and here. Deal * with that in caller, it's cheaper that way. * * We make sure that nr remains a multiple of BITS_PER_LONG - otherwise * bitmaps handling below becomes unpleasant, to put it mildly... */ if (unlikely(nr > sysctl_nr_open)) nr = ((sysctl_nr_open - 1) | (BITS_PER_LONG - 1)) + 1; |
bbea9f696
|
123 |
|
5d097056c
|
124 |
fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL_ACCOUNT); |
5466b456e
|
125 |
if (!fdt) |
bbea9f696
|
126 |
goto out; |
5466b456e
|
127 128 129 130 |
fdt->max_fds = nr; data = alloc_fdmem(nr * sizeof(struct file *)); if (!data) goto out_fdt; |
1fd36adcd
|
131 132 133 |
fdt->fd = data; data = alloc_fdmem(max_t(size_t, |
f3f86e33d
|
134 |
2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES)); |
5466b456e
|
135 136 |
if (!data) goto out_arr; |
1fd36adcd
|
137 |
fdt->open_fds = data; |
5466b456e
|
138 |
data += nr / BITS_PER_BYTE; |
1fd36adcd
|
139 |
fdt->close_on_exec = data; |
f3f86e33d
|
140 141 |
data += nr / BITS_PER_BYTE; fdt->full_fds_bits = data; |
5466b456e
|
142 |
|
ab2af1f50
|
143 |
return fdt; |
5466b456e
|
144 145 |
out_arr: |
f6c0a1920
|
146 |
kvfree(fdt->fd); |
5466b456e
|
147 |
out_fdt: |
ab2af1f50
|
148 |
kfree(fdt); |
5466b456e
|
149 |
out: |
ab2af1f50
|
150 151 |
return NULL; } |
1da177e4c
|
152 |
|
ab2af1f50
|
153 |
/* |
74d392aaa
|
154 155 156 157 158 |
* Expand the file descriptor table. * This function will allocate a new fdtable and both fd array and fdset, of * the given size. * Return <0 error code on error; 1 on successful completion. * The files->file_lock should be held on entry, and will be held on exit. |
ab2af1f50
|
159 160 161 162 163 |
*/ static int expand_fdtable(struct files_struct *files, int nr) __releases(files->file_lock) __acquires(files->file_lock) { |
74d392aaa
|
164 |
struct fdtable *new_fdt, *cur_fdt; |
ab2af1f50
|
165 166 |
spin_unlock(&files->file_lock); |
74d392aaa
|
167 |
new_fdt = alloc_fdtable(nr); |
8a81252b7
|
168 169 170 171 172 173 |
/* make sure all __fd_install() have seen resize_in_progress * or have finished their rcu_read_lock_sched() section. */ if (atomic_read(&files->count) > 1) synchronize_sched(); |
ab2af1f50
|
174 |
spin_lock(&files->file_lock); |
74d392aaa
|
175 176 |
if (!new_fdt) return -ENOMEM; |
ab2af1f50
|
177 |
/* |
5c598b342
|
178 179 180 181 |
* extremely unlikely race - sysctl_nr_open decreased between the check in * caller and alloc_fdtable(). Cheaper to catch it here... */ if (unlikely(new_fdt->max_fds <= nr)) { |
a892e2d7d
|
182 |
__free_fdtable(new_fdt); |
5c598b342
|
183 184 |
return -EMFILE; } |
74d392aaa
|
185 |
cur_fdt = files_fdtable(files); |
8a81252b7
|
186 187 188 189 190 191 192 |
BUG_ON(nr < cur_fdt->max_fds); copy_fdtable(new_fdt, cur_fdt); rcu_assign_pointer(files->fdt, new_fdt); if (cur_fdt != &files->fdtab) call_rcu(&cur_fdt->rcu, free_fdtable_rcu); /* coupled with smp_rmb() in __fd_install() */ smp_wmb(); |
74d392aaa
|
193 |
return 1; |
1da177e4c
|
194 195 196 197 |
} /* * Expand files. |
74d392aaa
|
198 199 200 201 202 |
* This function will expand the file structures, if the requested size exceeds * the current capacity and there is room for expansion. * Return <0 error code on error; 0 when nothing done; 1 when files were * expanded and execution may have blocked. * The files->file_lock should be held on entry, and will be held on exit. |
1da177e4c
|
203 |
*/ |
ad47bd725
|
204 |
static int expand_files(struct files_struct *files, int nr) |
8a81252b7
|
205 206 |
__releases(files->file_lock) __acquires(files->file_lock) |
1da177e4c
|
207 |
{ |
badf16621
|
208 |
struct fdtable *fdt; |
8a81252b7
|
209 |
int expanded = 0; |
1da177e4c
|
210 |
|
8a81252b7
|
211 |
repeat: |
badf16621
|
212 |
fdt = files_fdtable(files); |
4e1e018ec
|
213 |
|
74d392aaa
|
214 |
/* Do we need to expand? */ |
bbea9f696
|
215 |
if (nr < fdt->max_fds) |
8a81252b7
|
216 |
return expanded; |
4e1e018ec
|
217 |
|
74d392aaa
|
218 |
/* Can we expand? */ |
9cfe015aa
|
219 |
if (nr >= sysctl_nr_open) |
74d392aaa
|
220 |
return -EMFILE; |
8a81252b7
|
221 222 223 224 225 226 227 |
if (unlikely(files->resize_in_progress)) { spin_unlock(&files->file_lock); expanded = 1; wait_event(files->resize_wait, !files->resize_in_progress); spin_lock(&files->file_lock); goto repeat; } |
74d392aaa
|
228 |
/* All good, so we try */ |
8a81252b7
|
229 230 231 232 233 234 |
files->resize_in_progress = true; expanded = expand_fdtable(files, nr); files->resize_in_progress = false; wake_up_all(&files->resize_wait); return expanded; |
1da177e4c
|
235 |
} |
ab2af1f50
|
236 |
|
b8318b01a
|
237 238 239 240 241 242 243 |
static inline void __set_close_on_exec(int fd, struct fdtable *fdt) { __set_bit(fd, fdt->close_on_exec); } static inline void __clear_close_on_exec(int fd, struct fdtable *fdt) { |
fc90888d0
|
244 245 |
if (test_bit(fd, fdt->close_on_exec)) __clear_bit(fd, fdt->close_on_exec); |
b8318b01a
|
246 |
} |
f3f86e33d
|
247 |
static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt) |
b8318b01a
|
248 249 |
{ __set_bit(fd, fdt->open_fds); |
f3f86e33d
|
250 251 252 |
fd /= BITS_PER_LONG; if (!~fdt->open_fds[fd]) __set_bit(fd, fdt->full_fds_bits); |
b8318b01a
|
253 |
} |
f3f86e33d
|
254 |
static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt) |
b8318b01a
|
255 256 |
{ __clear_bit(fd, fdt->open_fds); |
f3f86e33d
|
257 |
__clear_bit(fd / BITS_PER_LONG, fdt->full_fds_bits); |
b8318b01a
|
258 |
} |
02afc6267
|
259 260 261 262 263 264 |
static int count_open_files(struct fdtable *fdt) { int size = fdt->max_fds; int i; /* Find the last open fd */ |
1fd36adcd
|
265 266 |
for (i = size / BITS_PER_LONG; i > 0; ) { if (fdt->open_fds[--i]) |
02afc6267
|
267 268 |
break; } |
1fd36adcd
|
269 |
i = (i + 1) * BITS_PER_LONG; |
02afc6267
|
270 271 |
return i; } |
02afc6267
|
272 273 274 275 276 277 278 279 280 |
/* * Allocate a new files structure and copy contents from the * passed in files structure. * errorp will be valid only when the returned files_struct is NULL. */ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp) { struct files_struct *newf; struct file **old_fds, **new_fds; |
ea5c58e70
|
281 |
int open_files, i; |
02afc6267
|
282 283 284 |
struct fdtable *old_fdt, *new_fdt; *errorp = -ENOMEM; |
afbec7fff
|
285 |
newf = kmem_cache_alloc(files_cachep, GFP_KERNEL); |
02afc6267
|
286 287 |
if (!newf) goto out; |
afbec7fff
|
288 289 290 |
atomic_set(&newf->count, 1); spin_lock_init(&newf->file_lock); |
8a81252b7
|
291 292 |
newf->resize_in_progress = false; init_waitqueue_head(&newf->resize_wait); |
afbec7fff
|
293 294 295 |
newf->next_fd = 0; new_fdt = &newf->fdtab; new_fdt->max_fds = NR_OPEN_DEFAULT; |
1fd36adcd
|
296 297 |
new_fdt->close_on_exec = newf->close_on_exec_init; new_fdt->open_fds = newf->open_fds_init; |
f3f86e33d
|
298 |
new_fdt->full_fds_bits = newf->full_fds_bits_init; |
afbec7fff
|
299 |
new_fdt->fd = &newf->fd_array[0]; |
afbec7fff
|
300 |
|
02afc6267
|
301 302 |
spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); |
02afc6267
|
303 304 305 306 |
open_files = count_open_files(old_fdt); /* * Check whether we need to allocate a larger fd array and fd set. |
02afc6267
|
307 |
*/ |
adbecb128
|
308 |
while (unlikely(open_files > new_fdt->max_fds)) { |
02afc6267
|
309 |
spin_unlock(&oldf->file_lock); |
9dec3c4d3
|
310 |
|
a892e2d7d
|
311 312 |
if (new_fdt != &newf->fdtab) __free_fdtable(new_fdt); |
adbecb128
|
313 |
|
9dec3c4d3
|
314 315 316 317 318 319 320 321 |
new_fdt = alloc_fdtable(open_files - 1); if (!new_fdt) { *errorp = -ENOMEM; goto out_release; } /* beyond sysctl_nr_open; nothing to do */ if (unlikely(new_fdt->max_fds < open_files)) { |
a892e2d7d
|
322 |
__free_fdtable(new_fdt); |
9dec3c4d3
|
323 |
*errorp = -EMFILE; |
02afc6267
|
324 |
goto out_release; |
9dec3c4d3
|
325 |
} |
9dec3c4d3
|
326 |
|
02afc6267
|
327 328 329 330 331 332 333 |
/* * Reacquire the oldf lock and a pointer to its fd table * who knows it may have a new bigger fd table. We need * the latest pointer. */ spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); |
adbecb128
|
334 |
open_files = count_open_files(old_fdt); |
02afc6267
|
335 |
} |
ea5c58e70
|
336 |
copy_fd_bitmaps(new_fdt, old_fdt, open_files); |
02afc6267
|
337 338 |
old_fds = old_fdt->fd; new_fds = new_fdt->fd; |
02afc6267
|
339 340 341 342 343 344 345 346 347 348 349 |
for (i = open_files; i != 0; i--) { struct file *f = *old_fds++; if (f) { get_file(f); } else { /* * The fd may be claimed in the fd bitmap but not yet * instantiated in the files array if a sibling thread * is partway through open(). So make sure that this * fd is available to the new process. */ |
1dce27c5a
|
350 |
__clear_open_fd(open_files - i, new_fdt); |
02afc6267
|
351 352 353 354 |
} rcu_assign_pointer(*new_fds++, f); } spin_unlock(&oldf->file_lock); |
ea5c58e70
|
355 356 |
/* clear the remainder */ memset(new_fds, 0, (new_fdt->max_fds - open_files) * sizeof(struct file *)); |
02afc6267
|
357 |
|
afbec7fff
|
358 |
rcu_assign_pointer(newf->fdt, new_fdt); |
02afc6267
|
359 360 361 362 363 364 365 |
return newf; out_release: kmem_cache_free(files_cachep, newf); out: return NULL; } |
ce08b62d1
|
366 |
static struct fdtable *close_files(struct files_struct * files) |
7cf4dc3c8
|
367 |
{ |
7cf4dc3c8
|
368 369 370 |
/* * It is safe to dereference the fd table without RCU or * ->file_lock because this is the last reference to the |
ce08b62d1
|
371 |
* files structure. |
7cf4dc3c8
|
372 |
*/ |
ce08b62d1
|
373 374 |
struct fdtable *fdt = rcu_dereference_raw(files->fdt); int i, j = 0; |
7cf4dc3c8
|
375 376 377 378 379 380 381 382 383 384 385 |
for (;;) { unsigned long set; i = j * BITS_PER_LONG; if (i >= fdt->max_fds) break; set = fdt->open_fds[j++]; while (set) { if (set & 1) { struct file * file = xchg(&fdt->fd[i], NULL); if (file) { filp_close(file, files); |
bde6c3aa9
|
386 |
cond_resched_rcu_qs(); |
7cf4dc3c8
|
387 388 389 390 391 392 |
} } i++; set >>= 1; } } |
ce08b62d1
|
393 394 |
return fdt; |
7cf4dc3c8
|
395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 |
} struct files_struct *get_files_struct(struct task_struct *task) { struct files_struct *files; task_lock(task); files = task->files; if (files) atomic_inc(&files->count); task_unlock(task); return files; } void put_files_struct(struct files_struct *files) { |
7cf4dc3c8
|
412 |
if (atomic_dec_and_test(&files->count)) { |
ce08b62d1
|
413 |
struct fdtable *fdt = close_files(files); |
b9e02af0a
|
414 415 416 417 |
/* free the arrays if they are not embedded */ if (fdt != &files->fdtab) __free_fdtable(fdt); kmem_cache_free(files_cachep, files); |
7cf4dc3c8
|
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 |
} } void reset_files_struct(struct files_struct *files) { struct task_struct *tsk = current; struct files_struct *old; old = tsk->files; task_lock(tsk); tsk->files = files; task_unlock(tsk); put_files_struct(old); } void exit_files(struct task_struct *tsk) { struct files_struct * files = tsk->files; if (files) { task_lock(tsk); tsk->files = NULL; task_unlock(tsk); put_files_struct(files); } } |
f52111b15
|
444 445 446 447 448 449 |
struct files_struct init_files = { .count = ATOMIC_INIT(1), .fdt = &init_files.fdtab, .fdtab = { .max_fds = NR_OPEN_DEFAULT, .fd = &init_files.fd_array[0], |
1fd36adcd
|
450 451 |
.close_on_exec = init_files.close_on_exec_init, .open_fds = init_files.open_fds_init, |
f3f86e33d
|
452 |
.full_fds_bits = init_files.full_fds_bits_init, |
f52111b15
|
453 |
}, |
eece09ec2
|
454 |
.file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock), |
f52111b15
|
455 |
}; |
1027abe88
|
456 |
|
f3f86e33d
|
457 458 459 460 461 462 463 464 465 466 467 468 469 |
static unsigned long find_next_fd(struct fdtable *fdt, unsigned long start) { unsigned long maxfd = fdt->max_fds; unsigned long maxbit = maxfd / BITS_PER_LONG; unsigned long bitbit = start / BITS_PER_LONG; bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG; if (bitbit > maxfd) return maxfd; if (bitbit > start) start = bitbit; return find_next_zero_bit(fdt->open_fds, maxfd, start); } |
1027abe88
|
470 471 472 |
/* * allocate a file descriptor, mark it busy. */ |
dcfadfa4e
|
473 474 |
int __alloc_fd(struct files_struct *files, unsigned start, unsigned end, unsigned flags) |
1027abe88
|
475 |
{ |
1027abe88
|
476 477 478 479 480 481 482 483 484 485 486 487 |
unsigned int fd; int error; struct fdtable *fdt; spin_lock(&files->file_lock); repeat: fdt = files_fdtable(files); fd = start; if (fd < files->next_fd) fd = files->next_fd; if (fd < fdt->max_fds) |
f3f86e33d
|
488 |
fd = find_next_fd(fdt, fd); |
1027abe88
|
489 |
|
f33ff9927
|
490 491 492 493 494 495 496 |
/* * N.B. For clone tasks sharing a files structure, this test * will limit the total number of files that can be opened. */ error = -EMFILE; if (fd >= end) goto out; |
1027abe88
|
497 498 499 500 501 502 503 504 505 506 507 508 509 |
error = expand_files(files, fd); if (error < 0) goto out; /* * If we needed to expand the fs array we * might have blocked - try again. */ if (error) goto repeat; if (start <= files->next_fd) files->next_fd = fd + 1; |
1dce27c5a
|
510 |
__set_open_fd(fd, fdt); |
1027abe88
|
511 |
if (flags & O_CLOEXEC) |
1dce27c5a
|
512 |
__set_close_on_exec(fd, fdt); |
1027abe88
|
513 |
else |
1dce27c5a
|
514 |
__clear_close_on_exec(fd, fdt); |
1027abe88
|
515 516 517 |
error = fd; #if 1 /* Sanity check */ |
add1f0995
|
518 |
if (rcu_access_pointer(fdt->fd[fd]) != NULL) { |
1027abe88
|
519 520 521 522 523 524 525 526 527 528 |
printk(KERN_WARNING "alloc_fd: slot %d not NULL! ", fd); rcu_assign_pointer(fdt->fd[fd], NULL); } #endif out: spin_unlock(&files->file_lock); return error; } |
ad47bd725
|
529 |
static int alloc_fd(unsigned start, unsigned flags) |
dcfadfa4e
|
530 531 532 |
{ return __alloc_fd(current->files, start, rlimit(RLIMIT_NOFILE), flags); } |
1a7bd2265
|
533 |
int get_unused_fd_flags(unsigned flags) |
1027abe88
|
534 |
{ |
dcfadfa4e
|
535 |
return __alloc_fd(current->files, 0, rlimit(RLIMIT_NOFILE), flags); |
1027abe88
|
536 |
} |
1a7bd2265
|
537 |
EXPORT_SYMBOL(get_unused_fd_flags); |
56007cae9
|
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 |
static void __put_unused_fd(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = files_fdtable(files); __clear_open_fd(fd, fdt); if (fd < files->next_fd) files->next_fd = fd; } void put_unused_fd(unsigned int fd) { struct files_struct *files = current->files; spin_lock(&files->file_lock); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); } EXPORT_SYMBOL(put_unused_fd); /* * Install a file pointer in the fd array. * * The VFS is full of places where we drop the files lock between * setting the open_fds bitmap and installing the file in the file * array. At any such point, we are vulnerable to a dup2() race * installing a file in the array before us. We need to detect this and * fput() the struct file we are about to overwrite in this case. * * It should never happen - if we allow dup2() do it, _really_ bad things * will follow. |
f869e8a7f
|
568 569 570 571 572 573 574 |
* * NOTE: __fd_install() variant is really, really low-level; don't * use it unless you are forced to by truly lousy API shoved down * your throat. 'files' *MUST* be either current->files or obtained * by get_files_struct(current) done by whoever had given it to you, * or really bad things will happen. Normally you want to use * fd_install() instead. |
56007cae9
|
575 |
*/ |
f869e8a7f
|
576 577 |
void __fd_install(struct files_struct *files, unsigned int fd, struct file *file) |
56007cae9
|
578 |
{ |
56007cae9
|
579 |
struct fdtable *fdt; |
8a81252b7
|
580 581 582 583 584 585 586 587 588 589 590 591 |
might_sleep(); rcu_read_lock_sched(); while (unlikely(files->resize_in_progress)) { rcu_read_unlock_sched(); wait_event(files->resize_wait, !files->resize_in_progress); rcu_read_lock_sched(); } /* coupled with smp_wmb() in expand_fdtable() */ smp_rmb(); fdt = rcu_dereference_sched(files->fdt); |
56007cae9
|
592 593 |
BUG_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); |
8a81252b7
|
594 |
rcu_read_unlock_sched(); |
56007cae9
|
595 |
} |
f869e8a7f
|
596 597 598 599 |
void fd_install(unsigned int fd, struct file *file) { __fd_install(current->files, fd, file); } |
56007cae9
|
600 |
EXPORT_SYMBOL(fd_install); |
0ee8cdfe6
|
601 |
|
483ce1d4b
|
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 |
/* * The same warnings as for __alloc_fd()/__fd_install() apply here... */ int __close_fd(struct files_struct *files, unsigned fd) { struct file *file; struct fdtable *fdt; spin_lock(&files->file_lock); fdt = files_fdtable(files); if (fd >= fdt->max_fds) goto out_unlock; file = fdt->fd[fd]; if (!file) goto out_unlock; rcu_assign_pointer(fdt->fd[fd], NULL); __clear_close_on_exec(fd, fdt); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); return filp_close(file, files); out_unlock: spin_unlock(&files->file_lock); return -EBADF; } |
6a6d27de3
|
627 628 629 630 631 632 |
void do_close_on_exec(struct files_struct *files) { unsigned i; struct fdtable *fdt; /* exec unshares first */ |
6a6d27de3
|
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 |
spin_lock(&files->file_lock); for (i = 0; ; i++) { unsigned long set; unsigned fd = i * BITS_PER_LONG; fdt = files_fdtable(files); if (fd >= fdt->max_fds) break; set = fdt->close_on_exec[i]; if (!set) continue; fdt->close_on_exec[i] = 0; for ( ; set ; fd++, set >>= 1) { struct file *file; if (!(set & 1)) continue; file = fdt->fd[fd]; if (!file) continue; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); } } spin_unlock(&files->file_lock); } |
1deb46e25
|
662 |
static struct file *__fget(unsigned int fd, fmode_t mask) |
0ee8cdfe6
|
663 |
{ |
0ee8cdfe6
|
664 |
struct files_struct *files = current->files; |
1deb46e25
|
665 |
struct file *file; |
0ee8cdfe6
|
666 667 |
rcu_read_lock(); |
5ba97d283
|
668 |
loop: |
0ee8cdfe6
|
669 670 |
file = fcheck_files(files, fd); if (file) { |
5ba97d283
|
671 672 673 674 675 |
/* File object ref couldn't be taken. * dup2() atomicity guarantee is the reason * we loop to catch the new file (or NULL pointer) */ if (file->f_mode & mask) |
0ee8cdfe6
|
676 |
file = NULL; |
5ba97d283
|
677 678 |
else if (!get_file_rcu(file)) goto loop; |
0ee8cdfe6
|
679 680 681 682 683 |
} rcu_read_unlock(); return file; } |
1deb46e25
|
684 685 686 687 |
struct file *fget(unsigned int fd) { return __fget(fd, FMODE_PATH); } |
0ee8cdfe6
|
688 689 690 691 |
EXPORT_SYMBOL(fget); struct file *fget_raw(unsigned int fd) { |
1deb46e25
|
692 |
return __fget(fd, 0); |
0ee8cdfe6
|
693 |
} |
0ee8cdfe6
|
694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 |
EXPORT_SYMBOL(fget_raw); /* * Lightweight file lookup - no refcnt increment if fd table isn't shared. * * You can use this instead of fget if you satisfy all of the following * conditions: * 1) You must call fput_light before exiting the syscall and returning control * to userspace (i.e. you cannot remember the returned struct file * after * returning to userspace). * 2) You must not call filp_close on the returned struct file * in between * calls to fget_light and fput_light. * 3) You must not clone the current task in between the calls to fget_light * and fput_light. * * The fput_needed flag returned by fget_light should be passed to the * corresponding fput_light. */ |
bd2a31d52
|
712 |
static unsigned long __fget_light(unsigned int fd, fmode_t mask) |
0ee8cdfe6
|
713 |
{ |
0ee8cdfe6
|
714 |
struct files_struct *files = current->files; |
ad4618344
|
715 |
struct file *file; |
0ee8cdfe6
|
716 |
|
0ee8cdfe6
|
717 |
if (atomic_read(&files->count) == 1) { |
a8d4b8345
|
718 |
file = __fcheck_files(files, fd); |
bd2a31d52
|
719 720 721 |
if (!file || unlikely(file->f_mode & mask)) return 0; return (unsigned long)file; |
0ee8cdfe6
|
722 |
} else { |
e6ff9a9fa
|
723 |
file = __fget(fd, mask); |
bd2a31d52
|
724 725 726 |
if (!file) return 0; return FDPUT_FPUT | (unsigned long)file; |
0ee8cdfe6
|
727 |
} |
0ee8cdfe6
|
728 |
} |
bd2a31d52
|
729 |
unsigned long __fdget(unsigned int fd) |
ad4618344
|
730 |
{ |
bd2a31d52
|
731 |
return __fget_light(fd, FMODE_PATH); |
ad4618344
|
732 |
} |
bd2a31d52
|
733 |
EXPORT_SYMBOL(__fdget); |
0ee8cdfe6
|
734 |
|
bd2a31d52
|
735 |
unsigned long __fdget_raw(unsigned int fd) |
0ee8cdfe6
|
736 |
{ |
bd2a31d52
|
737 |
return __fget_light(fd, 0); |
0ee8cdfe6
|
738 |
} |
fe17f22d7
|
739 |
|
bd2a31d52
|
740 741 |
unsigned long __fdget_pos(unsigned int fd) { |
99aea6813
|
742 743 |
unsigned long v = __fdget(fd); struct file *file = (struct file *)(v & ~3); |
bd2a31d52
|
744 |
|
99aea6813
|
745 |
if (file && (file->f_mode & FMODE_ATOMIC_POS)) { |
bd2a31d52
|
746 747 748 749 750 |
if (file_count(file) > 1) { v |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); } } |
99aea6813
|
751 |
return v; |
bd2a31d52
|
752 753 754 755 756 757 758 |
} /* * We only lock f_pos if we have threads or if the file might be * shared with another process. In both cases we'll have an elevated * file count (done either by fdget() or by fork()). */ |
fe17f22d7
|
759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 |
void set_close_on_exec(unsigned int fd, int flag) { struct files_struct *files = current->files; struct fdtable *fdt; spin_lock(&files->file_lock); fdt = files_fdtable(files); if (flag) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); spin_unlock(&files->file_lock); } bool get_close_on_exec(unsigned int fd) { struct files_struct *files = current->files; struct fdtable *fdt; bool res; rcu_read_lock(); fdt = files_fdtable(files); res = close_on_exec(fd, fdt); rcu_read_unlock(); return res; } |
8280d1617
|
783 784 |
static int do_dup2(struct files_struct *files, struct file *file, unsigned fd, unsigned flags) |
e983094d6
|
785 |
__releases(&files->file_lock) |
fe17f22d7
|
786 |
{ |
8280d1617
|
787 |
struct file *tofree; |
fe17f22d7
|
788 |
struct fdtable *fdt; |
fe17f22d7
|
789 790 791 792 793 794 795 796 797 798 799 800 801 802 |
/* * We need to detect attempts to do dup2() over allocated but still * not finished descriptor. NB: OpenBSD avoids that at the price of * extra work in their equivalent of fget() - they insert struct * file immediately after grabbing descriptor, mark it larval if * more work (e.g. actual opening) is needed and make sure that * fget() treats larval files as absent. Potentially interesting, * but while extra work in fget() is trivial, locking implications * and amount of surgery on open()-related paths in VFS are not. * FreeBSD fails with -EBADF in the same situation, NetBSD "solution" * deadlocks in rather amusing ways, AFAICS. All of that is out of * scope of POSIX or SUS, since neither considers shared descriptor * tables and this condition does not arise without those. */ |
fe17f22d7
|
803 |
fdt = files_fdtable(files); |
8280d1617
|
804 805 806 |
tofree = fdt->fd[fd]; if (!tofree && fd_is_open(fd, fdt)) goto Ebusy; |
fe17f22d7
|
807 |
get_file(file); |
8280d1617
|
808 809 |
rcu_assign_pointer(fdt->fd[fd], file); __set_open_fd(fd, fdt); |
fe17f22d7
|
810 |
if (flags & O_CLOEXEC) |
8280d1617
|
811 |
__set_close_on_exec(fd, fdt); |
fe17f22d7
|
812 |
else |
8280d1617
|
813 |
__clear_close_on_exec(fd, fdt); |
fe17f22d7
|
814 815 816 817 |
spin_unlock(&files->file_lock); if (tofree) filp_close(tofree, files); |
8280d1617
|
818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 |
return fd; Ebusy: spin_unlock(&files->file_lock); return -EBUSY; } int replace_fd(unsigned fd, struct file *file, unsigned flags) { int err; struct files_struct *files = current->files; if (!file) return __close_fd(files, fd); if (fd >= rlimit(RLIMIT_NOFILE)) |
08f05c497
|
834 |
return -EBADF; |
8280d1617
|
835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 |
spin_lock(&files->file_lock); err = expand_files(files, fd); if (unlikely(err < 0)) goto out_unlock; return do_dup2(files, file, fd, flags); out_unlock: spin_unlock(&files->file_lock); return err; } SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags) { int err = -EBADF; struct file *file; struct files_struct *files = current->files; if ((flags & ~O_CLOEXEC) != 0) return -EINVAL; |
aed976475
|
855 856 |
if (unlikely(oldfd == newfd)) return -EINVAL; |
8280d1617
|
857 |
if (newfd >= rlimit(RLIMIT_NOFILE)) |
08f05c497
|
858 |
return -EBADF; |
8280d1617
|
859 860 861 862 863 864 865 866 867 868 869 870 |
spin_lock(&files->file_lock); err = expand_files(files, newfd); file = fcheck(oldfd); if (unlikely(!file)) goto Ebadf; if (unlikely(err < 0)) { if (err == -EMFILE) goto Ebadf; goto out_unlock; } return do_dup2(files, file, newfd, flags); |
fe17f22d7
|
871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 |
Ebadf: err = -EBADF; out_unlock: spin_unlock(&files->file_lock); return err; } SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) { if (unlikely(newfd == oldfd)) { /* corner case */ struct files_struct *files = current->files; int retval = oldfd; rcu_read_lock(); if (!fcheck_files(files, oldfd)) retval = -EBADF; rcu_read_unlock(); return retval; } return sys_dup3(oldfd, newfd, 0); } SYSCALL_DEFINE1(dup, unsigned int, fildes) { int ret = -EBADF; struct file *file = fget_raw(fildes); if (file) { |
8d10a0358
|
900 |
ret = get_unused_fd_flags(0); |
fe17f22d7
|
901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 |
if (ret >= 0) fd_install(ret, file); else fput(file); } return ret; } int f_dupfd(unsigned int from, struct file *file, unsigned flags) { int err; if (from >= rlimit(RLIMIT_NOFILE)) return -EINVAL; err = alloc_fd(from, flags); if (err >= 0) { get_file(file); fd_install(err, file); } return err; } |
c3c073f80
|
921 922 923 924 925 926 |
int iterate_fd(struct files_struct *files, unsigned n, int (*f)(const void *, struct file *, unsigned), const void *p) { struct fdtable *fdt; |
c3c073f80
|
927 928 929 930 |
int res = 0; if (!files) return 0; spin_lock(&files->file_lock); |
a77cfcb42
|
931 932 933 934 935 936 937 938 |
for (fdt = files_fdtable(files); n < fdt->max_fds; n++) { struct file *file; file = rcu_dereference_check_fdtable(files, fdt->fd[n]); if (!file) continue; res = f(p, file, n); if (res) break; |
c3c073f80
|
939 940 941 942 943 |
} spin_unlock(&files->file_lock); return res; } EXPORT_SYMBOL(iterate_fd); |