Blame view
block/bio.c
48.3 KB
1da177e4c
|
1 |
/* |
0fe234795
|
2 |
* Copyright (C) 2001 Jens Axboe <axboe@kernel.dk> |
1da177e4c
|
3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 |
* * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public Licens * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111- * */ #include <linux/mm.h> #include <linux/swap.h> #include <linux/bio.h> #include <linux/blkdev.h> |
a27bb332c
|
22 |
#include <linux/uio.h> |
852c788f8
|
23 |
#include <linux/iocontext.h> |
1da177e4c
|
24 25 26 |
#include <linux/slab.h> #include <linux/init.h> #include <linux/kernel.h> |
630d9c472
|
27 |
#include <linux/export.h> |
1da177e4c
|
28 29 |
#include <linux/mempool.h> #include <linux/workqueue.h> |
852c788f8
|
30 |
#include <linux/cgroup.h> |
1da177e4c
|
31 |
|
55782138e
|
32 |
#include <trace/events/block.h> |
0bfc24559
|
33 |
|
392ddc329
|
34 35 36 37 38 |
/* * Test patch to inline a certain number of bi_io_vec's inside the bio * itself, to shrink a bio data allocation from two mempool calls to one */ #define BIO_INLINE_VECS 4 |
1da177e4c
|
39 40 41 42 43 |
/* * if you change this list, also change bvec_alloc or things will * break badly! cannot be bigger than what you can fit into an * unsigned short */ |
1da177e4c
|
44 |
#define BV(x) { .nr_vecs = x, .name = "biovec-"__stringify(x) } |
df6771402
|
45 |
static struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] __read_mostly = { |
1da177e4c
|
46 47 48 49 50 |
BV(1), BV(4), BV(16), BV(64), BV(128), BV(BIO_MAX_PAGES), }; #undef BV /* |
1da177e4c
|
51 52 53 |
* fs_bio_set is the bio_set containing bio and iovec memory pools used by * IO code that does not need private memory pools. */ |
51d654e1d
|
54 |
struct bio_set *fs_bio_set; |
3f86a82ae
|
55 |
EXPORT_SYMBOL(fs_bio_set); |
1da177e4c
|
56 |
|
bb799ca02
|
57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 |
/* * Our slab pool management */ struct bio_slab { struct kmem_cache *slab; unsigned int slab_ref; unsigned int slab_size; char name[8]; }; static DEFINE_MUTEX(bio_slab_lock); static struct bio_slab *bio_slabs; static unsigned int bio_slab_nr, bio_slab_max; static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size) { unsigned int sz = sizeof(struct bio) + extra_size; struct kmem_cache *slab = NULL; |
389d7b26d
|
74 |
struct bio_slab *bslab, *new_bio_slabs; |
386bc35a2
|
75 |
unsigned int new_bio_slab_max; |
bb799ca02
|
76 77 78 79 80 81 |
unsigned int i, entry = -1; mutex_lock(&bio_slab_lock); i = 0; while (i < bio_slab_nr) { |
f06f135d8
|
82 |
bslab = &bio_slabs[i]; |
bb799ca02
|
83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 |
if (!bslab->slab && entry == -1) entry = i; else if (bslab->slab_size == sz) { slab = bslab->slab; bslab->slab_ref++; break; } i++; } if (slab) goto out_unlock; if (bio_slab_nr == bio_slab_max && entry == -1) { |
386bc35a2
|
98 |
new_bio_slab_max = bio_slab_max << 1; |
389d7b26d
|
99 |
new_bio_slabs = krealloc(bio_slabs, |
386bc35a2
|
100 |
new_bio_slab_max * sizeof(struct bio_slab), |
389d7b26d
|
101 102 |
GFP_KERNEL); if (!new_bio_slabs) |
bb799ca02
|
103 |
goto out_unlock; |
386bc35a2
|
104 |
bio_slab_max = new_bio_slab_max; |
389d7b26d
|
105 |
bio_slabs = new_bio_slabs; |
bb799ca02
|
106 107 108 109 110 111 112 |
} if (entry == -1) entry = bio_slab_nr++; bslab = &bio_slabs[entry]; snprintf(bslab->name, sizeof(bslab->name), "bio-%d", entry); |
6a2414836
|
113 114 |
slab = kmem_cache_create(bslab->name, sz, ARCH_KMALLOC_MINALIGN, SLAB_HWCACHE_ALIGN, NULL); |
bb799ca02
|
115 116 |
if (!slab) goto out_unlock; |
bb799ca02
|
117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 |
bslab->slab = slab; bslab->slab_ref = 1; bslab->slab_size = sz; out_unlock: mutex_unlock(&bio_slab_lock); return slab; } static void bio_put_slab(struct bio_set *bs) { struct bio_slab *bslab = NULL; unsigned int i; mutex_lock(&bio_slab_lock); for (i = 0; i < bio_slab_nr; i++) { if (bs->bio_slab == bio_slabs[i].slab) { bslab = &bio_slabs[i]; break; } } if (WARN(!bslab, KERN_ERR "bio: unable to find slab! ")) goto out; WARN_ON(!bslab->slab_ref); if (--bslab->slab_ref) goto out; kmem_cache_destroy(bslab->slab); bslab->slab = NULL; out: mutex_unlock(&bio_slab_lock); } |
7ba1ba12e
|
154 155 156 157 |
unsigned int bvec_nr_vecs(unsigned short idx) { return bvec_slabs[idx].nr_vecs; } |
9f060e223
|
158 |
void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned int idx) |
bb799ca02
|
159 160 161 162 |
{ BIO_BUG_ON(idx >= BIOVEC_NR_POOLS); if (idx == BIOVEC_MAX_IDX) |
9f060e223
|
163 |
mempool_free(bv, pool); |
bb799ca02
|
164 165 166 167 168 169 |
else { struct biovec_slab *bvs = bvec_slabs + idx; kmem_cache_free(bvs->slab, bv); } } |
9f060e223
|
170 171 |
struct bio_vec *bvec_alloc(gfp_t gfp_mask, int nr, unsigned long *idx, mempool_t *pool) |
1da177e4c
|
172 173 |
{ struct bio_vec *bvl; |
1da177e4c
|
174 175 |
/* |
7ff9345ff
|
176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 |
* see comment near bvec_array define! */ switch (nr) { case 1: *idx = 0; break; case 2 ... 4: *idx = 1; break; case 5 ... 16: *idx = 2; break; case 17 ... 64: *idx = 3; break; case 65 ... 128: *idx = 4; break; case 129 ... BIO_MAX_PAGES: *idx = 5; break; default: return NULL; } /* * idx now points to the pool we want to allocate from. only the * 1-vec entry pool is mempool backed. */ if (*idx == BIOVEC_MAX_IDX) { fallback: |
9f060e223
|
207 |
bvl = mempool_alloc(pool, gfp_mask); |
7ff9345ff
|
208 209 |
} else { struct biovec_slab *bvs = bvec_slabs + *idx; |
d0164adc8
|
210 |
gfp_t __gfp_mask = gfp_mask & ~(__GFP_DIRECT_RECLAIM | __GFP_IO); |
7ff9345ff
|
211 |
|
0a0d96b03
|
212 |
/* |
7ff9345ff
|
213 214 215 |
* Make this allocation restricted and don't dump info on * allocation failures, since we'll fallback to the mempool * in case of failure. |
0a0d96b03
|
216 |
*/ |
7ff9345ff
|
217 |
__gfp_mask |= __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN; |
1da177e4c
|
218 |
|
0a0d96b03
|
219 |
/* |
d0164adc8
|
220 |
* Try a slab allocation. If this fails and __GFP_DIRECT_RECLAIM |
7ff9345ff
|
221 |
* is set, retry with the 1-entry mempool |
0a0d96b03
|
222 |
*/ |
7ff9345ff
|
223 |
bvl = kmem_cache_alloc(bvs->slab, __gfp_mask); |
d0164adc8
|
224 |
if (unlikely(!bvl && (gfp_mask & __GFP_DIRECT_RECLAIM))) { |
7ff9345ff
|
225 226 227 228 |
*idx = BIOVEC_MAX_IDX; goto fallback; } } |
1da177e4c
|
229 230 |
return bvl; } |
4254bba17
|
231 |
static void __bio_free(struct bio *bio) |
1da177e4c
|
232 |
{ |
4254bba17
|
233 |
bio_disassociate_task(bio); |
1da177e4c
|
234 |
|
7ba1ba12e
|
235 |
if (bio_integrity(bio)) |
1e2a410ff
|
236 |
bio_integrity_free(bio); |
4254bba17
|
237 |
} |
7ba1ba12e
|
238 |
|
4254bba17
|
239 240 241 242 243 244 245 246 |
static void bio_free(struct bio *bio) { struct bio_set *bs = bio->bi_pool; void *p; __bio_free(bio); if (bs) { |
a38352e0a
|
247 |
if (bio_flagged(bio, BIO_OWNS_VEC)) |
9f060e223
|
248 |
bvec_free(bs->bvec_pool, bio->bi_io_vec, BIO_POOL_IDX(bio)); |
4254bba17
|
249 250 251 252 253 |
/* * If we have front padding, adjust the bio pointer before freeing */ p = bio; |
bb799ca02
|
254 |
p -= bs->front_pad; |
4254bba17
|
255 256 257 258 259 |
mempool_free(p, bs->bio_pool); } else { /* Bio was allocated by bio_kmalloc() */ kfree(bio); } |
3676347a5
|
260 |
} |
858119e15
|
261 |
void bio_init(struct bio *bio) |
1da177e4c
|
262 |
{ |
2b94de552
|
263 |
memset(bio, 0, sizeof(*bio)); |
c4cf5261f
|
264 |
atomic_set(&bio->__bi_remaining, 1); |
dac56212e
|
265 |
atomic_set(&bio->__bi_cnt, 1); |
1da177e4c
|
266 |
} |
a112a71d4
|
267 |
EXPORT_SYMBOL(bio_init); |
1da177e4c
|
268 269 |
/** |
f44b48c76
|
270 271 272 273 274 275 276 277 278 279 280 281 |
* bio_reset - reinitialize a bio * @bio: bio to reset * * Description: * After calling bio_reset(), @bio will be in the same state as a freshly * allocated bio returned bio bio_alloc_bioset() - the only fields that are * preserved are the ones that are initialized by bio_alloc_bioset(). See * comment in struct bio. */ void bio_reset(struct bio *bio) { unsigned long flags = bio->bi_flags & (~0UL << BIO_RESET_BITS); |
4254bba17
|
282 |
__bio_free(bio); |
f44b48c76
|
283 284 |
memset(bio, 0, BIO_RESET_BYTES); |
4246a0b63
|
285 |
bio->bi_flags = flags; |
c4cf5261f
|
286 |
atomic_set(&bio->__bi_remaining, 1); |
f44b48c76
|
287 288 |
} EXPORT_SYMBOL(bio_reset); |
38f8baae8
|
289 |
static struct bio *__bio_chain_endio(struct bio *bio) |
196d38bcc
|
290 |
{ |
4246a0b63
|
291 |
struct bio *parent = bio->bi_private; |
af3e3a525
|
292 293 |
if (!parent->bi_error) parent->bi_error = bio->bi_error; |
196d38bcc
|
294 |
bio_put(bio); |
38f8baae8
|
295 296 297 298 299 300 |
return parent; } static void bio_chain_endio(struct bio *bio) { bio_endio(__bio_chain_endio(bio)); |
196d38bcc
|
301 302 303 304 |
} /** * bio_chain - chain bio completions |
1051a902f
|
305 306 |
* @bio: the target bio * @parent: the @bio's parent bio |
196d38bcc
|
307 308 309 310 311 312 313 314 315 316 317 318 319 |
* * The caller won't have a bi_end_io called when @bio completes - instead, * @parent's bi_end_io won't be called until both @parent and @bio have * completed; the chained bio will also be freed when it completes. * * The caller must not set bi_private or bi_end_io in @bio. */ void bio_chain(struct bio *bio, struct bio *parent) { BUG_ON(bio->bi_private || bio->bi_end_io); bio->bi_private = parent; bio->bi_end_io = bio_chain_endio; |
c4cf5261f
|
320 |
bio_inc_remaining(parent); |
196d38bcc
|
321 322 |
} EXPORT_SYMBOL(bio_chain); |
df2cb6daa
|
323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 |
static void bio_alloc_rescue(struct work_struct *work) { struct bio_set *bs = container_of(work, struct bio_set, rescue_work); struct bio *bio; while (1) { spin_lock(&bs->rescue_lock); bio = bio_list_pop(&bs->rescue_list); spin_unlock(&bs->rescue_lock); if (!bio) break; generic_make_request(bio); } } static void punt_bios_to_rescuer(struct bio_set *bs) { struct bio_list punt, nopunt; struct bio *bio; /* * In order to guarantee forward progress we must punt only bios that * were allocated from this bio_set; otherwise, if there was a bio on * there for a stacking driver higher up in the stack, processing it * could require allocating bios from this bio_set, and doing that from * our own rescuer would be bad. * * Since bio lists are singly linked, pop them all instead of trying to * remove from the middle of the list: */ bio_list_init(&punt); bio_list_init(&nopunt); while ((bio = bio_list_pop(current->bio_list))) bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio); *current->bio_list = nopunt; spin_lock(&bs->rescue_lock); bio_list_merge(&bs->rescue_list, &punt); spin_unlock(&bs->rescue_lock); queue_work(bs->rescue_workqueue, &bs->rescue_work); } |
f44b48c76
|
370 |
/** |
1da177e4c
|
371 372 373 |
* bio_alloc_bioset - allocate a bio for I/O * @gfp_mask: the GFP_ mask given to the slab allocator * @nr_iovecs: number of iovecs to pre-allocate |
db18efac0
|
374 |
* @bs: the bio_set to allocate from. |
1da177e4c
|
375 376 |
* * Description: |
3f86a82ae
|
377 378 379 |
* If @bs is NULL, uses kmalloc() to allocate the bio; else the allocation is * backed by the @bs's mempool. * |
d0164adc8
|
380 381 382 383 384 385 |
* When @bs is not NULL, if %__GFP_DIRECT_RECLAIM is set then bio_alloc will * always be able to allocate a bio. This is due to the mempool guarantees. * To make this work, callers must never allocate more than 1 bio at a time * from this pool. Callers that need to allocate more than 1 bio must always * submit the previously allocated bio for IO before attempting to allocate * a new one. Failure to do so can cause deadlocks under memory pressure. |
3f86a82ae
|
386 |
* |
df2cb6daa
|
387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 |
* Note that when running under generic_make_request() (i.e. any block * driver), bios are not submitted until after you return - see the code in * generic_make_request() that converts recursion into iteration, to prevent * stack overflows. * * This would normally mean allocating multiple bios under * generic_make_request() would be susceptible to deadlocks, but we have * deadlock avoidance code that resubmits any blocked bios from a rescuer * thread. * * However, we do not guarantee forward progress for allocations from other * mempools. Doing multiple allocations from the same mempool under * generic_make_request() should be avoided - instead, use bio_set's front_pad * for per bio allocations. * |
3f86a82ae
|
402 403 404 |
* RETURNS: * Pointer to new bio on success, NULL on failure. */ |
dd0fc66fb
|
405 |
struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs) |
1da177e4c
|
406 |
{ |
df2cb6daa
|
407 |
gfp_t saved_gfp = gfp_mask; |
3f86a82ae
|
408 409 |
unsigned front_pad; unsigned inline_vecs; |
451a9ebf6
|
410 |
unsigned long idx = BIO_POOL_NONE; |
34053979f
|
411 |
struct bio_vec *bvl = NULL; |
451a9ebf6
|
412 413 |
struct bio *bio; void *p; |
3f86a82ae
|
414 415 416 417 418 419 420 421 422 423 |
if (!bs) { if (nr_iovecs > UIO_MAXIOV) return NULL; p = kmalloc(sizeof(struct bio) + nr_iovecs * sizeof(struct bio_vec), gfp_mask); front_pad = 0; inline_vecs = nr_iovecs; } else { |
d8f429e16
|
424 425 426 |
/* should not use nobvec bioset for nr_iovecs > 0 */ if (WARN_ON_ONCE(!bs->bvec_pool && nr_iovecs > 0)) return NULL; |
df2cb6daa
|
427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 |
/* * generic_make_request() converts recursion to iteration; this * means if we're running beneath it, any bios we allocate and * submit will not be submitted (and thus freed) until after we * return. * * This exposes us to a potential deadlock if we allocate * multiple bios from the same bio_set() while running * underneath generic_make_request(). If we were to allocate * multiple bios (say a stacking block driver that was splitting * bios), we would deadlock if we exhausted the mempool's * reserve. * * We solve this, and guarantee forward progress, with a rescuer * workqueue per bio_set. If we go to allocate and there are * bios on current->bio_list, we first try the allocation |
d0164adc8
|
443 444 445 |
* without __GFP_DIRECT_RECLAIM; if that fails, we punt those * bios we would be blocking to the rescuer workqueue before * we retry with the original gfp_flags. |
df2cb6daa
|
446 447 448 |
*/ if (current->bio_list && !bio_list_empty(current->bio_list)) |
d0164adc8
|
449 |
gfp_mask &= ~__GFP_DIRECT_RECLAIM; |
df2cb6daa
|
450 |
|
3f86a82ae
|
451 |
p = mempool_alloc(bs->bio_pool, gfp_mask); |
df2cb6daa
|
452 453 454 455 456 |
if (!p && gfp_mask != saved_gfp) { punt_bios_to_rescuer(bs); gfp_mask = saved_gfp; p = mempool_alloc(bs->bio_pool, gfp_mask); } |
3f86a82ae
|
457 458 459 |
front_pad = bs->front_pad; inline_vecs = BIO_INLINE_VECS; } |
451a9ebf6
|
460 461 |
if (unlikely(!p)) return NULL; |
1da177e4c
|
462 |
|
3f86a82ae
|
463 |
bio = p + front_pad; |
34053979f
|
464 |
bio_init(bio); |
3f86a82ae
|
465 |
if (nr_iovecs > inline_vecs) { |
9f060e223
|
466 |
bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, bs->bvec_pool); |
df2cb6daa
|
467 468 469 |
if (!bvl && gfp_mask != saved_gfp) { punt_bios_to_rescuer(bs); gfp_mask = saved_gfp; |
9f060e223
|
470 |
bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, bs->bvec_pool); |
df2cb6daa
|
471 |
} |
34053979f
|
472 473 |
if (unlikely(!bvl)) goto err_free; |
a38352e0a
|
474 |
|
b7c44ed9d
|
475 |
bio_set_flag(bio, BIO_OWNS_VEC); |
3f86a82ae
|
476 477 |
} else if (nr_iovecs) { bvl = bio->bi_inline_vecs; |
1da177e4c
|
478 |
} |
3f86a82ae
|
479 480 |
bio->bi_pool = bs; |
34053979f
|
481 482 |
bio->bi_flags |= idx << BIO_POOL_OFFSET; bio->bi_max_vecs = nr_iovecs; |
34053979f
|
483 |
bio->bi_io_vec = bvl; |
1da177e4c
|
484 |
return bio; |
34053979f
|
485 486 |
err_free: |
451a9ebf6
|
487 |
mempool_free(p, bs->bio_pool); |
34053979f
|
488 |
return NULL; |
1da177e4c
|
489 |
} |
a112a71d4
|
490 |
EXPORT_SYMBOL(bio_alloc_bioset); |
1da177e4c
|
491 |
|
1da177e4c
|
492 493 494 |
void zero_fill_bio(struct bio *bio) { unsigned long flags; |
7988613b0
|
495 496 |
struct bio_vec bv; struct bvec_iter iter; |
1da177e4c
|
497 |
|
7988613b0
|
498 499 500 501 |
bio_for_each_segment(bv, bio, iter) { char *data = bvec_kmap_irq(&bv, &flags); memset(data, 0, bv.bv_len); flush_dcache_page(bv.bv_page); |
1da177e4c
|
502 503 504 505 506 507 508 509 510 511 512 |
bvec_kunmap_irq(data, &flags); } } EXPORT_SYMBOL(zero_fill_bio); /** * bio_put - release a reference to a bio * @bio: bio to release reference to * * Description: * Put a reference to a &struct bio, either one you have gotten with |
ad0bf1107
|
513 |
* bio_alloc, bio_get or bio_clone. The last put of a bio will free it. |
1da177e4c
|
514 515 516 |
**/ void bio_put(struct bio *bio) { |
dac56212e
|
517 |
if (!bio_flagged(bio, BIO_REFFED)) |
4254bba17
|
518 |
bio_free(bio); |
dac56212e
|
519 520 521 522 523 524 525 526 527 |
else { BIO_BUG_ON(!atomic_read(&bio->__bi_cnt)); /* * last put frees it */ if (atomic_dec_and_test(&bio->__bi_cnt)) bio_free(bio); } |
1da177e4c
|
528 |
} |
a112a71d4
|
529 |
EXPORT_SYMBOL(bio_put); |
1da177e4c
|
530 |
|
165125e1e
|
531 |
inline int bio_phys_segments(struct request_queue *q, struct bio *bio) |
1da177e4c
|
532 533 534 535 536 537 |
{ if (unlikely(!bio_flagged(bio, BIO_SEG_VALID))) blk_recount_segments(q, bio); return bio->bi_phys_segments; } |
a112a71d4
|
538 |
EXPORT_SYMBOL(bio_phys_segments); |
1da177e4c
|
539 |
|
1da177e4c
|
540 |
/** |
59d276fe0
|
541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 |
* __bio_clone_fast - clone a bio that shares the original bio's biovec * @bio: destination bio * @bio_src: bio to clone * * Clone a &bio. Caller will own the returned bio, but not * the actual data it points to. Reference count of returned * bio will be one. * * Caller must ensure that @bio_src is not freed before @bio. */ void __bio_clone_fast(struct bio *bio, struct bio *bio_src) { BUG_ON(bio->bi_pool && BIO_POOL_IDX(bio) != BIO_POOL_NONE); /* * most users will be overriding ->bi_bdev with a new target, * so we don't set nor calculate new physical/hw segment counts here */ bio->bi_bdev = bio_src->bi_bdev; |
b7c44ed9d
|
560 |
bio_set_flag(bio, BIO_CLONED); |
59d276fe0
|
561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 |
bio->bi_rw = bio_src->bi_rw; bio->bi_iter = bio_src->bi_iter; bio->bi_io_vec = bio_src->bi_io_vec; } EXPORT_SYMBOL(__bio_clone_fast); /** * bio_clone_fast - clone a bio that shares the original bio's biovec * @bio: bio to clone * @gfp_mask: allocation priority * @bs: bio_set to allocate from * * Like __bio_clone_fast, only also allocates the returned bio */ struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs) { struct bio *b; b = bio_alloc_bioset(gfp_mask, 0, bs); if (!b) return NULL; __bio_clone_fast(b, bio); if (bio_integrity(bio)) { int ret; ret = bio_integrity_clone(b, bio, gfp_mask); if (ret < 0) { bio_put(b); return NULL; } } return b; } EXPORT_SYMBOL(bio_clone_fast); /** |
bdb532074
|
601 602 |
* bio_clone_bioset - clone a bio * @bio_src: bio to clone |
1da177e4c
|
603 |
* @gfp_mask: allocation priority |
bf800ef18
|
604 |
* @bs: bio_set to allocate from |
1da177e4c
|
605 |
* |
bdb532074
|
606 607 |
* Clone bio. Caller will own the returned bio, but not the actual data it * points to. Reference count of returned bio will be one. |
1da177e4c
|
608 |
*/ |
bdb532074
|
609 |
struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask, |
bf800ef18
|
610 |
struct bio_set *bs) |
1da177e4c
|
611 |
{ |
bdb532074
|
612 613 614 |
struct bvec_iter iter; struct bio_vec bv; struct bio *bio; |
1da177e4c
|
615 |
|
bdb532074
|
616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 |
/* * Pre immutable biovecs, __bio_clone() used to just do a memcpy from * bio_src->bi_io_vec to bio->bi_io_vec. * * We can't do that anymore, because: * * - The point of cloning the biovec is to produce a bio with a biovec * the caller can modify: bi_idx and bi_bvec_done should be 0. * * - The original bio could've had more than BIO_MAX_PAGES biovecs; if * we tried to clone the whole thing bio_alloc_bioset() would fail. * But the clone should succeed as long as the number of biovecs we * actually need to allocate is fewer than BIO_MAX_PAGES. * * - Lastly, bi_vcnt should not be looked at or relied upon by code * that does not own the bio - reason being drivers don't use it for * iterating over the biovec anymore, so expecting it to be kept up * to date (i.e. for clones that share the parent biovec) is just * asking for trouble and would force extra work on * __bio_clone_fast() anyways. */ |
8423ae3d7
|
637 |
bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs); |
bdb532074
|
638 |
if (!bio) |
7ba1ba12e
|
639 |
return NULL; |
bdb532074
|
640 641 642 643 |
bio->bi_bdev = bio_src->bi_bdev; bio->bi_rw = bio_src->bi_rw; bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; |
7ba1ba12e
|
644 |
|
8423ae3d7
|
645 646 647 648 649 650 651 |
if (bio->bi_rw & REQ_DISCARD) goto integrity_clone; if (bio->bi_rw & REQ_WRITE_SAME) { bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0]; goto integrity_clone; } |
bdb532074
|
652 653 |
bio_for_each_segment(bv, bio_src, iter) bio->bi_io_vec[bio->bi_vcnt++] = bv; |
7ba1ba12e
|
654 |
|
8423ae3d7
|
655 |
integrity_clone: |
bdb532074
|
656 657 |
if (bio_integrity(bio_src)) { int ret; |
7ba1ba12e
|
658 |
|
bdb532074
|
659 |
ret = bio_integrity_clone(bio, bio_src, gfp_mask); |
059ea3318
|
660 |
if (ret < 0) { |
bdb532074
|
661 |
bio_put(bio); |
7ba1ba12e
|
662 |
return NULL; |
059ea3318
|
663 |
} |
3676347a5
|
664 |
} |
1da177e4c
|
665 |
|
bdb532074
|
666 |
return bio; |
1da177e4c
|
667 |
} |
bf800ef18
|
668 |
EXPORT_SYMBOL(bio_clone_bioset); |
1da177e4c
|
669 670 |
/** |
c66a14d07
|
671 672 673 674 675 676 |
* bio_add_pc_page - attempt to add page to bio * @q: the target queue * @bio: destination bio * @page: page to add * @len: vec entry length * @offset: vec entry offset |
1da177e4c
|
677 |
* |
c66a14d07
|
678 679 680 681 682 683 |
* Attempt to add a page to the bio_vec maplist. This can fail for a * number of reasons, such as the bio being full or target block device * limitations. The target block device must allow bio's up to PAGE_SIZE, * so it is always possible to add a single page to an empty bio. * * This should only be used by REQ_PC bios. |
1da177e4c
|
684 |
*/ |
c66a14d07
|
685 686 |
int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset) |
1da177e4c
|
687 688 689 690 691 692 693 694 695 |
{ int retried_segments = 0; struct bio_vec *bvec; /* * cloned bio must not modify vec list */ if (unlikely(bio_flagged(bio, BIO_CLONED))) return 0; |
c66a14d07
|
696 |
if (((bio->bi_iter.bi_size + len) >> 9) > queue_max_hw_sectors(q)) |
1da177e4c
|
697 |
return 0; |
80cfd548e
|
698 699 700 701 702 703 704 705 706 707 708 |
/* * For filesystems with a blocksize smaller than the pagesize * we will often be called with the same page as last time and * a consecutive offset. Optimize this special case. */ if (bio->bi_vcnt > 0) { struct bio_vec *prev = &bio->bi_io_vec[bio->bi_vcnt - 1]; if (page == prev->bv_page && offset == prev->bv_offset + prev->bv_len) { prev->bv_len += len; |
fcbf6a087
|
709 |
bio->bi_iter.bi_size += len; |
80cfd548e
|
710 711 |
goto done; } |
66cb45aa4
|
712 713 714 715 716 |
/* * If the queue doesn't support SG gaps and adding this * offset would create a gap, disallow it. */ |
03100aada
|
717 |
if (bvec_gap_to_prev(q, prev, offset)) |
66cb45aa4
|
718 |
return 0; |
80cfd548e
|
719 720 721 |
} if (bio->bi_vcnt >= bio->bi_max_vecs) |
1da177e4c
|
722 723 724 |
return 0; /* |
fcbf6a087
|
725 726 727 728 729 730 731 732 733 734 735 736 737 738 |
* setup the new entry, we might clear it again later if we * cannot add the page */ bvec = &bio->bi_io_vec[bio->bi_vcnt]; bvec->bv_page = page; bvec->bv_len = len; bvec->bv_offset = offset; bio->bi_vcnt++; bio->bi_phys_segments++; bio->bi_iter.bi_size += len; /* * Perform a recount if the number of segments is greater * than queue_max_segments(q). |
1da177e4c
|
739 |
*/ |
fcbf6a087
|
740 |
while (bio->bi_phys_segments > queue_max_segments(q)) { |
1da177e4c
|
741 742 |
if (retried_segments) |
fcbf6a087
|
743 |
goto failed; |
1da177e4c
|
744 745 746 747 |
retried_segments = 1; blk_recount_segments(q, bio); } |
1da177e4c
|
748 |
/* If we may be able to merge these biovecs, force a recount */ |
fcbf6a087
|
749 |
if (bio->bi_vcnt > 1 && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec))) |
b7c44ed9d
|
750 |
bio_clear_flag(bio, BIO_SEG_VALID); |
1da177e4c
|
751 |
|
80cfd548e
|
752 |
done: |
1da177e4c
|
753 |
return len; |
fcbf6a087
|
754 755 756 757 758 759 760 761 762 |
failed: bvec->bv_page = NULL; bvec->bv_len = 0; bvec->bv_offset = 0; bio->bi_vcnt--; bio->bi_iter.bi_size -= len; blk_recount_segments(q, bio); return 0; |
1da177e4c
|
763 |
} |
a112a71d4
|
764 |
EXPORT_SYMBOL(bio_add_pc_page); |
6e68af666
|
765 766 |
/** |
1da177e4c
|
767 768 769 770 771 772 |
* bio_add_page - attempt to add page to bio * @bio: destination bio * @page: page to add * @len: vec entry length * @offset: vec entry offset * |
c66a14d07
|
773 774 |
* Attempt to add a page to the bio_vec maplist. This will only fail * if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio. |
1da177e4c
|
775 |
*/ |
c66a14d07
|
776 777 |
int bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset) |
1da177e4c
|
778 |
{ |
c66a14d07
|
779 780 781 782 783 784 785 |
struct bio_vec *bv; /* * cloned bio must not modify vec list */ if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) return 0; |
762380ad9
|
786 |
|
c66a14d07
|
787 788 789 790 791 792 793 |
/* * For filesystems with a blocksize smaller than the pagesize * we will often be called with the same page as last time and * a consecutive offset. Optimize this special case. */ if (bio->bi_vcnt > 0) { bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; |
58a4915ad
|
794 |
|
c66a14d07
|
795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 |
if (page == bv->bv_page && offset == bv->bv_offset + bv->bv_len) { bv->bv_len += len; goto done; } } if (bio->bi_vcnt >= bio->bi_max_vecs) return 0; bv = &bio->bi_io_vec[bio->bi_vcnt]; bv->bv_page = page; bv->bv_len = len; bv->bv_offset = offset; bio->bi_vcnt++; done: bio->bi_iter.bi_size += len; return len; |
1da177e4c
|
814 |
} |
a112a71d4
|
815 |
EXPORT_SYMBOL(bio_add_page); |
1da177e4c
|
816 |
|
9e882242c
|
817 818 819 820 |
struct submit_bio_ret { struct completion event; int error; }; |
4246a0b63
|
821 |
static void submit_bio_wait_endio(struct bio *bio) |
9e882242c
|
822 823 |
{ struct submit_bio_ret *ret = bio->bi_private; |
4246a0b63
|
824 |
ret->error = bio->bi_error; |
9e882242c
|
825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 |
complete(&ret->event); } /** * submit_bio_wait - submit a bio, and wait until it completes * @rw: whether to %READ or %WRITE, or maybe to %READA (read ahead) * @bio: The &struct bio which describes the I/O * * Simple wrapper around submit_bio(). Returns 0 on success, or the error from * bio_endio() on failure. */ int submit_bio_wait(int rw, struct bio *bio) { struct submit_bio_ret ret; rw |= REQ_SYNC; init_completion(&ret.event); bio->bi_private = &ret; bio->bi_end_io = submit_bio_wait_endio; submit_bio(rw, bio); |
d57d61150
|
845 |
wait_for_completion_io(&ret.event); |
9e882242c
|
846 847 848 849 |
return ret.error; } EXPORT_SYMBOL(submit_bio_wait); |
054bdf646
|
850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 |
/** * bio_advance - increment/complete a bio by some number of bytes * @bio: bio to advance * @bytes: number of bytes to complete * * This updates bi_sector, bi_size and bi_idx; if the number of bytes to * complete doesn't align with a bvec boundary, then bv_len and bv_offset will * be updated on the last bvec as well. * * @bio will then represent the remaining, uncompleted portion of the io. */ void bio_advance(struct bio *bio, unsigned bytes) { if (bio_integrity(bio)) bio_integrity_advance(bio, bytes); |
4550dd6c6
|
865 |
bio_advance_iter(bio, &bio->bi_iter, bytes); |
054bdf646
|
866 867 |
} EXPORT_SYMBOL(bio_advance); |
16ac3d63e
|
868 |
/** |
a07876064
|
869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 |
* bio_alloc_pages - allocates a single page for each bvec in a bio * @bio: bio to allocate pages for * @gfp_mask: flags for allocation * * Allocates pages up to @bio->bi_vcnt. * * Returns 0 on success, -ENOMEM on failure. On failure, any allocated pages are * freed. */ int bio_alloc_pages(struct bio *bio, gfp_t gfp_mask) { int i; struct bio_vec *bv; bio_for_each_segment_all(bv, bio, i) { bv->bv_page = alloc_page(gfp_mask); if (!bv->bv_page) { while (--bv >= bio->bi_io_vec) __free_page(bv->bv_page); return -ENOMEM; } } return 0; } EXPORT_SYMBOL(bio_alloc_pages); /** |
16ac3d63e
|
897 898 899 900 901 902 903 904 905 906 907 908 909 |
* bio_copy_data - copy contents of data buffers from one chain of bios to * another * @src: source bio list * @dst: destination bio list * * If @src and @dst are single bios, bi_next must be NULL - otherwise, treats * @src and @dst as linked lists of bios. * * Stops when it reaches the end of either @src or @dst - that is, copies * min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of bios). */ void bio_copy_data(struct bio *dst, struct bio *src) { |
1cb9dda4f
|
910 911 |
struct bvec_iter src_iter, dst_iter; struct bio_vec src_bv, dst_bv; |
16ac3d63e
|
912 |
void *src_p, *dst_p; |
1cb9dda4f
|
913 |
unsigned bytes; |
16ac3d63e
|
914 |
|
1cb9dda4f
|
915 916 |
src_iter = src->bi_iter; dst_iter = dst->bi_iter; |
16ac3d63e
|
917 918 |
while (1) { |
1cb9dda4f
|
919 920 921 922 |
if (!src_iter.bi_size) { src = src->bi_next; if (!src) break; |
16ac3d63e
|
923 |
|
1cb9dda4f
|
924 |
src_iter = src->bi_iter; |
16ac3d63e
|
925 |
} |
1cb9dda4f
|
926 927 928 929 |
if (!dst_iter.bi_size) { dst = dst->bi_next; if (!dst) break; |
16ac3d63e
|
930 |
|
1cb9dda4f
|
931 |
dst_iter = dst->bi_iter; |
16ac3d63e
|
932 |
} |
1cb9dda4f
|
933 934 935 936 |
src_bv = bio_iter_iovec(src, src_iter); dst_bv = bio_iter_iovec(dst, dst_iter); bytes = min(src_bv.bv_len, dst_bv.bv_len); |
16ac3d63e
|
937 |
|
1cb9dda4f
|
938 939 |
src_p = kmap_atomic(src_bv.bv_page); dst_p = kmap_atomic(dst_bv.bv_page); |
16ac3d63e
|
940 |
|
1cb9dda4f
|
941 942 |
memcpy(dst_p + dst_bv.bv_offset, src_p + src_bv.bv_offset, |
16ac3d63e
|
943 944 945 946 |
bytes); kunmap_atomic(dst_p); kunmap_atomic(src_p); |
1cb9dda4f
|
947 948 |
bio_advance_iter(src, &src_iter, bytes); bio_advance_iter(dst, &dst_iter, bytes); |
16ac3d63e
|
949 950 951 |
} } EXPORT_SYMBOL(bio_copy_data); |
1da177e4c
|
952 |
struct bio_map_data { |
152e283fd
|
953 |
int is_our_pages; |
26e49cfc7
|
954 955 |
struct iov_iter iter; struct iovec iov[]; |
1da177e4c
|
956 |
}; |
7410b3c6c
|
957 |
static struct bio_map_data *bio_alloc_map_data(unsigned int iov_count, |
76029ff37
|
958 |
gfp_t gfp_mask) |
1da177e4c
|
959 |
{ |
f3f63c1c2
|
960 961 |
if (iov_count > UIO_MAXIOV) return NULL; |
1da177e4c
|
962 |
|
c8db44482
|
963 |
return kmalloc(sizeof(struct bio_map_data) + |
26e49cfc7
|
964 |
sizeof(struct iovec) * iov_count, gfp_mask); |
1da177e4c
|
965 |
} |
9124d3fe2
|
966 967 968 969 970 971 972 973 974 |
/** * bio_copy_from_iter - copy all pages from iov_iter to bio * @bio: The &struct bio which describes the I/O as destination * @iter: iov_iter as source * * Copy all pages from iov_iter to bio. * Returns 0 on success, or error on failure. */ static int bio_copy_from_iter(struct bio *bio, struct iov_iter iter) |
c5dec1c30
|
975 |
{ |
9124d3fe2
|
976 |
int i; |
c5dec1c30
|
977 |
struct bio_vec *bvec; |
c5dec1c30
|
978 |
|
d74c6d514
|
979 |
bio_for_each_segment_all(bvec, bio, i) { |
9124d3fe2
|
980 |
ssize_t ret; |
c5dec1c30
|
981 |
|
9124d3fe2
|
982 983 984 985 986 987 988 989 990 991 |
ret = copy_page_from_iter(bvec->bv_page, bvec->bv_offset, bvec->bv_len, &iter); if (!iov_iter_count(&iter)) break; if (ret < bvec->bv_len) return -EFAULT; |
c5dec1c30
|
992 |
} |
9124d3fe2
|
993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 |
return 0; } /** * bio_copy_to_iter - copy all pages from bio to iov_iter * @bio: The &struct bio which describes the I/O as source * @iter: iov_iter as destination * * Copy all pages from bio to iov_iter. * Returns 0 on success, or error on failure. */ static int bio_copy_to_iter(struct bio *bio, struct iov_iter iter) { int i; struct bio_vec *bvec; bio_for_each_segment_all(bvec, bio, i) { ssize_t ret; ret = copy_page_to_iter(bvec->bv_page, bvec->bv_offset, bvec->bv_len, &iter); if (!iov_iter_count(&iter)) break; if (ret < bvec->bv_len) return -EFAULT; } return 0; |
c5dec1c30
|
1025 |
} |
1dfa0f68c
|
1026 1027 1028 1029 1030 1031 1032 1033 |
static void bio_free_pages(struct bio *bio) { struct bio_vec *bvec; int i; bio_for_each_segment_all(bvec, bio, i) __free_page(bvec->bv_page); } |
1da177e4c
|
1034 1035 1036 1037 |
/** * bio_uncopy_user - finish previously mapped bio * @bio: bio being terminated * |
ddad8dd0a
|
1038 |
* Free pages allocated from bio_copy_user_iov() and write back data |
1da177e4c
|
1039 1040 1041 1042 1043 |
* to user space in case of a read. */ int bio_uncopy_user(struct bio *bio) { struct bio_map_data *bmd = bio->bi_private; |
1dfa0f68c
|
1044 |
int ret = 0; |
1da177e4c
|
1045 |
|
35dc24838
|
1046 1047 1048 |
if (!bio_flagged(bio, BIO_NULL_MAPPED)) { /* * if we're in a workqueue, the request is orphaned, so |
2d99b55d3
|
1049 1050 |
* don't copy into a random user address space, just free * and return -EINTR so user space doesn't expect any data. |
35dc24838
|
1051 |
*/ |
2d99b55d3
|
1052 1053 1054 |
if (!current->mm) ret = -EINTR; else if (bio_data_dir(bio) == READ) |
9124d3fe2
|
1055 |
ret = bio_copy_to_iter(bio, bmd->iter); |
1dfa0f68c
|
1056 1057 |
if (bmd->is_our_pages) bio_free_pages(bio); |
35dc24838
|
1058 |
} |
c8db44482
|
1059 |
kfree(bmd); |
1da177e4c
|
1060 1061 1062 |
bio_put(bio); return ret; } |
a112a71d4
|
1063 |
EXPORT_SYMBOL(bio_uncopy_user); |
1da177e4c
|
1064 1065 |
/** |
c5dec1c30
|
1066 |
* bio_copy_user_iov - copy user data to bio |
26e49cfc7
|
1067 1068 1069 1070 |
* @q: destination block queue * @map_data: pointer to the rq_map_data holding pages (if necessary) * @iter: iovec iterator * @gfp_mask: memory allocation flags |
1da177e4c
|
1071 1072 1073 1074 1075 |
* * Prepares and returns a bio for indirect user io, bouncing data * to/from kernel pages as necessary. Must be paired with * call bio_uncopy_user() on io completion. */ |
152e283fd
|
1076 1077 |
struct bio *bio_copy_user_iov(struct request_queue *q, struct rq_map_data *map_data, |
26e49cfc7
|
1078 1079 |
const struct iov_iter *iter, gfp_t gfp_mask) |
1da177e4c
|
1080 |
{ |
1da177e4c
|
1081 |
struct bio_map_data *bmd; |
1da177e4c
|
1082 1083 1084 |
struct page *page; struct bio *bio; int i, ret; |
c5dec1c30
|
1085 |
int nr_pages = 0; |
26e49cfc7
|
1086 |
unsigned int len = iter->count; |
bd5cecea4
|
1087 |
unsigned int offset = map_data ? offset_in_page(map_data->offset) : 0; |
1da177e4c
|
1088 |
|
26e49cfc7
|
1089 |
for (i = 0; i < iter->nr_segs; i++) { |
c5dec1c30
|
1090 1091 1092 |
unsigned long uaddr; unsigned long end; unsigned long start; |
26e49cfc7
|
1093 1094 1095 |
uaddr = (unsigned long) iter->iov[i].iov_base; end = (uaddr + iter->iov[i].iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT; |
c5dec1c30
|
1096 |
start = uaddr >> PAGE_SHIFT; |
cb4644cac
|
1097 1098 1099 1100 1101 |
/* * Overflow, abort */ if (end < start) return ERR_PTR(-EINVAL); |
c5dec1c30
|
1102 |
nr_pages += end - start; |
c5dec1c30
|
1103 |
} |
69838727b
|
1104 1105 |
if (offset) nr_pages++; |
26e49cfc7
|
1106 |
bmd = bio_alloc_map_data(iter->nr_segs, gfp_mask); |
1da177e4c
|
1107 1108 |
if (!bmd) return ERR_PTR(-ENOMEM); |
26e49cfc7
|
1109 1110 1111 1112 1113 1114 1115 1116 1117 |
/* * We need to do a deep copy of the iov_iter including the iovecs. * The caller provided iov might point to an on-stack or otherwise * shortlived one. */ bmd->is_our_pages = map_data ? 0 : 1; memcpy(bmd->iov, iter->iov, sizeof(struct iovec) * iter->nr_segs); iov_iter_init(&bmd->iter, iter->type, bmd->iov, iter->nr_segs, iter->count); |
1da177e4c
|
1118 |
ret = -ENOMEM; |
a9e9dc24b
|
1119 |
bio = bio_kmalloc(gfp_mask, nr_pages); |
1da177e4c
|
1120 1121 |
if (!bio) goto out_bmd; |
26e49cfc7
|
1122 |
if (iter->type & WRITE) |
7b6d91dae
|
1123 |
bio->bi_rw |= REQ_WRITE; |
1da177e4c
|
1124 1125 |
ret = 0; |
56c451f4b
|
1126 1127 |
if (map_data) { |
e623ddb4e
|
1128 |
nr_pages = 1 << map_data->page_order; |
56c451f4b
|
1129 1130 |
i = map_data->offset / PAGE_SIZE; } |
1da177e4c
|
1131 |
while (len) { |
e623ddb4e
|
1132 |
unsigned int bytes = PAGE_SIZE; |
1da177e4c
|
1133 |
|
56c451f4b
|
1134 |
bytes -= offset; |
1da177e4c
|
1135 1136 |
if (bytes > len) bytes = len; |
152e283fd
|
1137 |
if (map_data) { |
e623ddb4e
|
1138 |
if (i == map_data->nr_entries * nr_pages) { |
152e283fd
|
1139 1140 1141 |
ret = -ENOMEM; break; } |
e623ddb4e
|
1142 1143 1144 1145 1146 1147 |
page = map_data->pages[i / nr_pages]; page += (i % nr_pages); i++; } else { |
152e283fd
|
1148 |
page = alloc_page(q->bounce_gfp | gfp_mask); |
e623ddb4e
|
1149 1150 1151 1152 |
if (!page) { ret = -ENOMEM; break; } |
1da177e4c
|
1153 |
} |
56c451f4b
|
1154 |
if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes) |
1da177e4c
|
1155 |
break; |
1da177e4c
|
1156 1157 |
len -= bytes; |
56c451f4b
|
1158 |
offset = 0; |
1da177e4c
|
1159 1160 1161 1162 1163 1164 1165 1166 |
} if (ret) goto cleanup; /* * success */ |
26e49cfc7
|
1167 |
if (((iter->type & WRITE) && (!map_data || !map_data->null_mapped)) || |
ecb554a84
|
1168 |
(map_data && map_data->from_user)) { |
9124d3fe2
|
1169 |
ret = bio_copy_from_iter(bio, *iter); |
c5dec1c30
|
1170 1171 |
if (ret) goto cleanup; |
1da177e4c
|
1172 |
} |
26e49cfc7
|
1173 |
bio->bi_private = bmd; |
1da177e4c
|
1174 1175 |
return bio; cleanup: |
152e283fd
|
1176 |
if (!map_data) |
1dfa0f68c
|
1177 |
bio_free_pages(bio); |
1da177e4c
|
1178 1179 |
bio_put(bio); out_bmd: |
c8db44482
|
1180 |
kfree(bmd); |
1da177e4c
|
1181 1182 |
return ERR_PTR(ret); } |
37f19e57a
|
1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 |
/** * bio_map_user_iov - map user iovec into bio * @q: the struct request_queue for the bio * @iter: iovec iterator * @gfp_mask: memory allocation flags * * Map the user space address into a bio suitable for io to a block * device. Returns an error pointer in case of error. */ struct bio *bio_map_user_iov(struct request_queue *q, const struct iov_iter *iter, gfp_t gfp_mask) |
1da177e4c
|
1195 |
{ |
26e49cfc7
|
1196 |
int j; |
f1970baf6
|
1197 |
int nr_pages = 0; |
1da177e4c
|
1198 1199 |
struct page **pages; struct bio *bio; |
f1970baf6
|
1200 1201 |
int cur_page = 0; int ret, offset; |
26e49cfc7
|
1202 1203 |
struct iov_iter i; struct iovec iov; |
1da177e4c
|
1204 |
|
26e49cfc7
|
1205 1206 1207 |
iov_for_each(iov, i, *iter) { unsigned long uaddr = (unsigned long) iov.iov_base; unsigned long len = iov.iov_len; |
f1970baf6
|
1208 1209 |
unsigned long end = (uaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT; unsigned long start = uaddr >> PAGE_SHIFT; |
cb4644cac
|
1210 1211 1212 1213 1214 |
/* * Overflow, abort */ if (end < start) return ERR_PTR(-EINVAL); |
f1970baf6
|
1215 1216 |
nr_pages += end - start; /* |
ad2d72257
|
1217 |
* buffer must be aligned to at least hardsector size for now |
f1970baf6
|
1218 |
*/ |
ad2d72257
|
1219 |
if (uaddr & queue_dma_alignment(q)) |
f1970baf6
|
1220 1221 1222 1223 |
return ERR_PTR(-EINVAL); } if (!nr_pages) |
1da177e4c
|
1224 |
return ERR_PTR(-EINVAL); |
a9e9dc24b
|
1225 |
bio = bio_kmalloc(gfp_mask, nr_pages); |
1da177e4c
|
1226 1227 1228 1229 |
if (!bio) return ERR_PTR(-ENOMEM); ret = -ENOMEM; |
a3bce90ed
|
1230 |
pages = kcalloc(nr_pages, sizeof(struct page *), gfp_mask); |
1da177e4c
|
1231 1232 |
if (!pages) goto out; |
26e49cfc7
|
1233 1234 1235 |
iov_for_each(iov, i, *iter) { unsigned long uaddr = (unsigned long) iov.iov_base; unsigned long len = iov.iov_len; |
f1970baf6
|
1236 1237 1238 1239 |
unsigned long end = (uaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT; unsigned long start = uaddr >> PAGE_SHIFT; const int local_nr_pages = end - start; const int page_limit = cur_page + local_nr_pages; |
cb4644cac
|
1240 |
|
f5dd33c49
|
1241 |
ret = get_user_pages_fast(uaddr, local_nr_pages, |
26e49cfc7
|
1242 1243 |
(iter->type & WRITE) != WRITE, &pages[cur_page]); |
991721572
|
1244 1245 |
if (ret < local_nr_pages) { ret = -EFAULT; |
f1970baf6
|
1246 |
goto out_unmap; |
991721572
|
1247 |
} |
f1970baf6
|
1248 |
|
bd5cecea4
|
1249 |
offset = offset_in_page(uaddr); |
f1970baf6
|
1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 |
for (j = cur_page; j < page_limit; j++) { unsigned int bytes = PAGE_SIZE - offset; if (len <= 0) break; if (bytes > len) bytes = len; /* * sorry... */ |
defd94b75
|
1262 1263 |
if (bio_add_pc_page(q, bio, pages[j], bytes, offset) < bytes) |
f1970baf6
|
1264 1265 1266 1267 1268 |
break; len -= bytes; offset = 0; } |
1da177e4c
|
1269 |
|
f1970baf6
|
1270 |
cur_page = j; |
1da177e4c
|
1271 |
/* |
f1970baf6
|
1272 |
* release the pages we didn't map into the bio, if any |
1da177e4c
|
1273 |
*/ |
f1970baf6
|
1274 |
while (j < page_limit) |
09cbfeaf1
|
1275 |
put_page(pages[j++]); |
1da177e4c
|
1276 |
} |
1da177e4c
|
1277 1278 1279 1280 1281 |
kfree(pages); /* * set data direction, and check if mapped pages need bouncing */ |
26e49cfc7
|
1282 |
if (iter->type & WRITE) |
7b6d91dae
|
1283 |
bio->bi_rw |= REQ_WRITE; |
1da177e4c
|
1284 |
|
b7c44ed9d
|
1285 |
bio_set_flag(bio, BIO_USER_MAPPED); |
37f19e57a
|
1286 1287 1288 1289 1290 1291 1292 1293 |
/* * subtle -- if __bio_map_user() ended up bouncing a bio, * it would normally disappear when its bi_end_io is run. * however, we need it for the unmap, so grab an extra * reference to it */ bio_get(bio); |
1da177e4c
|
1294 |
return bio; |
f1970baf6
|
1295 1296 |
out_unmap: |
26e49cfc7
|
1297 1298 |
for (j = 0; j < nr_pages; j++) { if (!pages[j]) |
f1970baf6
|
1299 |
break; |
09cbfeaf1
|
1300 |
put_page(pages[j]); |
f1970baf6
|
1301 1302 |
} out: |
1da177e4c
|
1303 1304 1305 1306 |
kfree(pages); bio_put(bio); return ERR_PTR(ret); } |
1da177e4c
|
1307 1308 1309 1310 1311 1312 1313 1314 |
static void __bio_unmap_user(struct bio *bio) { struct bio_vec *bvec; int i; /* * make sure we dirty pages we wrote to */ |
d74c6d514
|
1315 |
bio_for_each_segment_all(bvec, bio, i) { |
1da177e4c
|
1316 1317 |
if (bio_data_dir(bio) == READ) set_page_dirty_lock(bvec->bv_page); |
09cbfeaf1
|
1318 |
put_page(bvec->bv_page); |
1da177e4c
|
1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 |
} bio_put(bio); } /** * bio_unmap_user - unmap a bio * @bio: the bio being unmapped * * Unmap a bio previously mapped by bio_map_user(). Must be called with * a process context. * * bio_unmap_user() may sleep. */ void bio_unmap_user(struct bio *bio) { __bio_unmap_user(bio); bio_put(bio); } |
a112a71d4
|
1338 |
EXPORT_SYMBOL(bio_unmap_user); |
1da177e4c
|
1339 |
|
4246a0b63
|
1340 |
static void bio_map_kern_endio(struct bio *bio) |
b823825e8
|
1341 |
{ |
b823825e8
|
1342 |
bio_put(bio); |
b823825e8
|
1343 |
} |
75c72b836
|
1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 |
/** * bio_map_kern - map kernel address into bio * @q: the struct request_queue for the bio * @data: pointer to buffer to map * @len: length in bytes * @gfp_mask: allocation flags for bio allocation * * Map the kernel address into a bio suitable for io to a block * device. Returns an error pointer in case of error. */ struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len, gfp_t gfp_mask) |
df46b9a44
|
1356 1357 1358 1359 1360 1361 1362 |
{ unsigned long kaddr = (unsigned long)data; unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT; unsigned long start = kaddr >> PAGE_SHIFT; const int nr_pages = end - start; int offset, i; struct bio *bio; |
a9e9dc24b
|
1363 |
bio = bio_kmalloc(gfp_mask, nr_pages); |
df46b9a44
|
1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 |
if (!bio) return ERR_PTR(-ENOMEM); offset = offset_in_page(kaddr); for (i = 0; i < nr_pages; i++) { unsigned int bytes = PAGE_SIZE - offset; if (len <= 0) break; if (bytes > len) bytes = len; |
defd94b75
|
1376 |
if (bio_add_pc_page(q, bio, virt_to_page(data), bytes, |
75c72b836
|
1377 1378 1379 1380 1381 |
offset) < bytes) { /* we don't support partial mappings */ bio_put(bio); return ERR_PTR(-EINVAL); } |
df46b9a44
|
1382 1383 1384 1385 1386 |
data += bytes; len -= bytes; offset = 0; } |
b823825e8
|
1387 |
bio->bi_end_io = bio_map_kern_endio; |
df46b9a44
|
1388 1389 |
return bio; } |
a112a71d4
|
1390 |
EXPORT_SYMBOL(bio_map_kern); |
df46b9a44
|
1391 |
|
4246a0b63
|
1392 |
static void bio_copy_kern_endio(struct bio *bio) |
68154e90c
|
1393 |
{ |
1dfa0f68c
|
1394 1395 1396 |
bio_free_pages(bio); bio_put(bio); } |
4246a0b63
|
1397 |
static void bio_copy_kern_endio_read(struct bio *bio) |
1dfa0f68c
|
1398 |
{ |
42d2683a2
|
1399 |
char *p = bio->bi_private; |
1dfa0f68c
|
1400 |
struct bio_vec *bvec; |
68154e90c
|
1401 |
int i; |
d74c6d514
|
1402 |
bio_for_each_segment_all(bvec, bio, i) { |
1dfa0f68c
|
1403 |
memcpy(p, page_address(bvec->bv_page), bvec->bv_len); |
c8db44482
|
1404 |
p += bvec->bv_len; |
68154e90c
|
1405 |
} |
4246a0b63
|
1406 |
bio_copy_kern_endio(bio); |
68154e90c
|
1407 1408 1409 1410 1411 1412 1413 1414 |
} /** * bio_copy_kern - copy kernel address into bio * @q: the struct request_queue for the bio * @data: pointer to buffer to copy * @len: length in bytes * @gfp_mask: allocation flags for bio and page allocation |
ffee0259c
|
1415 |
* @reading: data direction is READ |
68154e90c
|
1416 1417 1418 1419 1420 1421 1422 |
* * copy the kernel address into a bio suitable for io to a block * device. Returns an error pointer in case of error. */ struct bio *bio_copy_kern(struct request_queue *q, void *data, unsigned int len, gfp_t gfp_mask, int reading) { |
42d2683a2
|
1423 1424 1425 |
unsigned long kaddr = (unsigned long)data; unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT; unsigned long start = kaddr >> PAGE_SHIFT; |
42d2683a2
|
1426 1427 |
struct bio *bio; void *p = data; |
1dfa0f68c
|
1428 |
int nr_pages = 0; |
68154e90c
|
1429 |
|
42d2683a2
|
1430 1431 1432 1433 1434 |
/* * Overflow, abort */ if (end < start) return ERR_PTR(-EINVAL); |
68154e90c
|
1435 |
|
42d2683a2
|
1436 1437 1438 1439 |
nr_pages = end - start; bio = bio_kmalloc(gfp_mask, nr_pages); if (!bio) return ERR_PTR(-ENOMEM); |
68154e90c
|
1440 |
|
42d2683a2
|
1441 1442 1443 |
while (len) { struct page *page; unsigned int bytes = PAGE_SIZE; |
68154e90c
|
1444 |
|
42d2683a2
|
1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 |
if (bytes > len) bytes = len; page = alloc_page(q->bounce_gfp | gfp_mask); if (!page) goto cleanup; if (!reading) memcpy(page_address(page), p, bytes); if (bio_add_pc_page(q, bio, page, bytes, 0) < bytes) break; len -= bytes; p += bytes; |
68154e90c
|
1460 |
} |
1dfa0f68c
|
1461 1462 1463 1464 1465 |
if (reading) { bio->bi_end_io = bio_copy_kern_endio_read; bio->bi_private = data; } else { bio->bi_end_io = bio_copy_kern_endio; |
42d2683a2
|
1466 |
bio->bi_rw |= REQ_WRITE; |
1dfa0f68c
|
1467 |
} |
76029ff37
|
1468 |
|
68154e90c
|
1469 |
return bio; |
42d2683a2
|
1470 1471 |
cleanup: |
1dfa0f68c
|
1472 |
bio_free_pages(bio); |
42d2683a2
|
1473 1474 |
bio_put(bio); return ERR_PTR(-ENOMEM); |
68154e90c
|
1475 |
} |
a112a71d4
|
1476 |
EXPORT_SYMBOL(bio_copy_kern); |
68154e90c
|
1477 |
|
1da177e4c
|
1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 |
/* * bio_set_pages_dirty() and bio_check_pages_dirty() are support functions * for performing direct-IO in BIOs. * * The problem is that we cannot run set_page_dirty() from interrupt context * because the required locks are not interrupt-safe. So what we can do is to * mark the pages dirty _before_ performing IO. And in interrupt context, * check that the pages are still dirty. If so, fine. If not, redirty them * in process context. * * We special-case compound pages here: normally this means reads into hugetlb * pages. The logic in here doesn't really work right for compound pages * because the VM does not uniformly chase down the head page in all cases. * But dirtiness of compound pages is pretty meaningless anyway: the VM doesn't * handle them at all. So we skip compound pages here at an early stage. * * Note that this code is very hard to test under normal circumstances because * direct-io pins the pages with get_user_pages(). This makes * is_page_cache_freeable return false, and the VM will not clean the pages. |
0d5c3eba2
|
1497 |
* But other code (eg, flusher threads) could clean the pages if they are mapped |
1da177e4c
|
1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 |
* pagecache. * * Simply disabling the call to bio_set_pages_dirty() is a good way to test the * deferred bio dirtying paths. */ /* * bio_set_pages_dirty() will mark all the bio's pages as dirty. */ void bio_set_pages_dirty(struct bio *bio) { |
cb34e057a
|
1509 |
struct bio_vec *bvec; |
1da177e4c
|
1510 |
int i; |
cb34e057a
|
1511 1512 |
bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; |
1da177e4c
|
1513 1514 1515 1516 1517 |
if (page && !PageCompound(page)) set_page_dirty_lock(page); } } |
86b6c7a7f
|
1518 |
static void bio_release_pages(struct bio *bio) |
1da177e4c
|
1519 |
{ |
cb34e057a
|
1520 |
struct bio_vec *bvec; |
1da177e4c
|
1521 |
int i; |
cb34e057a
|
1522 1523 |
bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; |
1da177e4c
|
1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 |
if (page) put_page(page); } } /* * bio_check_pages_dirty() will check that all the BIO's pages are still dirty. * If they are, then fine. If, however, some pages are clean then they must * have been written out during the direct-IO read. So we take another ref on * the BIO and the offending pages and re-dirty the pages in process context. * * It is expected that bio_check_pages_dirty() will wholly own the BIO from |
ea1754a08
|
1537 1538 |
* here on. It will run one put_page() against each page and will run one * bio_put() against the BIO. |
1da177e4c
|
1539 |
*/ |
65f27f384
|
1540 |
static void bio_dirty_fn(struct work_struct *work); |
1da177e4c
|
1541 |
|
65f27f384
|
1542 |
static DECLARE_WORK(bio_dirty_work, bio_dirty_fn); |
1da177e4c
|
1543 1544 1545 1546 1547 1548 |
static DEFINE_SPINLOCK(bio_dirty_lock); static struct bio *bio_dirty_list; /* * This runs in process context */ |
65f27f384
|
1549 |
static void bio_dirty_fn(struct work_struct *work) |
1da177e4c
|
1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 |
{ unsigned long flags; struct bio *bio; spin_lock_irqsave(&bio_dirty_lock, flags); bio = bio_dirty_list; bio_dirty_list = NULL; spin_unlock_irqrestore(&bio_dirty_lock, flags); while (bio) { struct bio *next = bio->bi_private; bio_set_pages_dirty(bio); bio_release_pages(bio); bio_put(bio); bio = next; } } void bio_check_pages_dirty(struct bio *bio) { |
cb34e057a
|
1571 |
struct bio_vec *bvec; |
1da177e4c
|
1572 1573 |
int nr_clean_pages = 0; int i; |
cb34e057a
|
1574 1575 |
bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; |
1da177e4c
|
1576 1577 |
if (PageDirty(page) || PageCompound(page)) { |
09cbfeaf1
|
1578 |
put_page(page); |
cb34e057a
|
1579 |
bvec->bv_page = NULL; |
1da177e4c
|
1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 |
} else { nr_clean_pages++; } } if (nr_clean_pages) { unsigned long flags; spin_lock_irqsave(&bio_dirty_lock, flags); bio->bi_private = bio_dirty_list; bio_dirty_list = bio; spin_unlock_irqrestore(&bio_dirty_lock, flags); schedule_work(&bio_dirty_work); } else { bio_put(bio); } } |
394ffa503
|
1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 |
void generic_start_io_acct(int rw, unsigned long sectors, struct hd_struct *part) { int cpu = part_stat_lock(); part_round_stats(cpu, part); part_stat_inc(cpu, part, ios[rw]); part_stat_add(cpu, part, sectors[rw], sectors); part_inc_in_flight(part, rw); part_stat_unlock(); } EXPORT_SYMBOL(generic_start_io_acct); void generic_end_io_acct(int rw, struct hd_struct *part, unsigned long start_time) { unsigned long duration = jiffies - start_time; int cpu = part_stat_lock(); part_stat_add(cpu, part, ticks[rw], duration); part_round_stats(cpu, part); part_dec_in_flight(part, rw); part_stat_unlock(); } EXPORT_SYMBOL(generic_end_io_acct); |
2d4dc890b
|
1624 1625 1626 |
#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE void bio_flush_dcache_pages(struct bio *bi) { |
7988613b0
|
1627 1628 |
struct bio_vec bvec; struct bvec_iter iter; |
2d4dc890b
|
1629 |
|
7988613b0
|
1630 1631 |
bio_for_each_segment(bvec, bi, iter) flush_dcache_page(bvec.bv_page); |
2d4dc890b
|
1632 1633 1634 |
} EXPORT_SYMBOL(bio_flush_dcache_pages); #endif |
c4cf5261f
|
1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 |
static inline bool bio_remaining_done(struct bio *bio) { /* * If we're not chaining, then ->__bi_remaining is always 1 and * we always end io on the first invocation. */ if (!bio_flagged(bio, BIO_CHAIN)) return true; BUG_ON(atomic_read(&bio->__bi_remaining) <= 0); |
326e1dbb5
|
1645 |
if (atomic_dec_and_test(&bio->__bi_remaining)) { |
b7c44ed9d
|
1646 |
bio_clear_flag(bio, BIO_CHAIN); |
c4cf5261f
|
1647 |
return true; |
326e1dbb5
|
1648 |
} |
c4cf5261f
|
1649 1650 1651 |
return false; } |
1da177e4c
|
1652 1653 1654 |
/** * bio_endio - end I/O on a bio * @bio: bio |
1da177e4c
|
1655 1656 |
* * Description: |
4246a0b63
|
1657 1658 1659 |
* bio_endio() will end I/O on the whole bio. bio_endio() is the preferred * way to end I/O on a bio. No one should call bi_end_io() directly on a * bio unless they own it and thus know that it has an end_io function. |
1da177e4c
|
1660 |
**/ |
4246a0b63
|
1661 |
void bio_endio(struct bio *bio) |
1da177e4c
|
1662 |
{ |
ba8c6967b
|
1663 |
again: |
2b8855171
|
1664 |
if (!bio_remaining_done(bio)) |
ba8c6967b
|
1665 |
return; |
1da177e4c
|
1666 |
|
ba8c6967b
|
1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 |
/* * Need to have a real endio function for chained bios, otherwise * various corner cases will break (like stacking block devices that * save/restore bi_end_io) - however, we want to avoid unbounded * recursion and blowing the stack. Tail call optimization would * handle this, but compiling with frame pointers also disables * gcc's sibling call optimization. */ if (bio->bi_end_io == bio_chain_endio) { bio = __bio_chain_endio(bio); goto again; |
196d38bcc
|
1678 |
} |
ba8c6967b
|
1679 1680 1681 |
if (bio->bi_end_io) bio->bi_end_io(bio); |
1da177e4c
|
1682 |
} |
a112a71d4
|
1683 |
EXPORT_SYMBOL(bio_endio); |
1da177e4c
|
1684 |
|
196d38bcc
|
1685 |
/** |
20d0189b1
|
1686 1687 1688 1689 1690 1691 1692 1693 1694 |
* bio_split - split a bio * @bio: bio to split * @sectors: number of sectors to split from the front of @bio * @gfp: gfp mask * @bs: bio set to allocate from * * Allocates and returns a new bio which represents @sectors from the start of * @bio, and updates @bio to represent the remaining sectors. * |
f3f5da624
|
1695 1696 1697 |
* Unless this is a discard request the newly allocated bio will point * to @bio's bi_io_vec; it is the caller's responsibility to ensure that * @bio is not freed before the split. |
20d0189b1
|
1698 1699 1700 1701 1702 1703 1704 1705 |
*/ struct bio *bio_split(struct bio *bio, int sectors, gfp_t gfp, struct bio_set *bs) { struct bio *split = NULL; BUG_ON(sectors <= 0); BUG_ON(sectors >= bio_sectors(bio)); |
f3f5da624
|
1706 1707 1708 1709 1710 1711 1712 1713 |
/* * Discards need a mutable bio_vec to accommodate the payload * required by the DSM TRIM and UNMAP commands. */ if (bio->bi_rw & REQ_DISCARD) split = bio_clone_bioset(bio, gfp, bs); else split = bio_clone_fast(bio, gfp, bs); |
20d0189b1
|
1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 |
if (!split) return NULL; split->bi_iter.bi_size = sectors << 9; if (bio_integrity(split)) bio_integrity_trim(split, 0, sectors); bio_advance(bio, split->bi_iter.bi_size); return split; } EXPORT_SYMBOL(bio_split); |
ad3316bf4
|
1727 |
/** |
6678d83f1
|
1728 1729 1730 1731 1732 1733 1734 1735 1736 |
* bio_trim - trim a bio * @bio: bio to trim * @offset: number of sectors to trim from the front of @bio * @size: size we want to trim @bio to, in sectors */ void bio_trim(struct bio *bio, int offset, int size) { /* 'bio' is a cloned bio which we need to trim to match * the given offset and size. |
6678d83f1
|
1737 |
*/ |
6678d83f1
|
1738 1739 |
size <<= 9; |
4f024f379
|
1740 |
if (offset == 0 && size == bio->bi_iter.bi_size) |
6678d83f1
|
1741 |
return; |
b7c44ed9d
|
1742 |
bio_clear_flag(bio, BIO_SEG_VALID); |
6678d83f1
|
1743 1744 |
bio_advance(bio, offset << 9); |
4f024f379
|
1745 |
bio->bi_iter.bi_size = size; |
6678d83f1
|
1746 1747 |
} EXPORT_SYMBOL_GPL(bio_trim); |
1da177e4c
|
1748 1749 1750 1751 |
/* * create memory pools for biovec's in a bio_set. * use the global biovec slabs created for general use. */ |
a6c39cb4f
|
1752 |
mempool_t *biovec_create_pool(int pool_entries) |
1da177e4c
|
1753 |
{ |
7ff9345ff
|
1754 |
struct biovec_slab *bp = bvec_slabs + BIOVEC_MAX_IDX; |
1da177e4c
|
1755 |
|
9f060e223
|
1756 |
return mempool_create_slab_pool(pool_entries, bp->slab); |
1da177e4c
|
1757 1758 1759 1760 |
} void bioset_free(struct bio_set *bs) { |
df2cb6daa
|
1761 1762 |
if (bs->rescue_workqueue) destroy_workqueue(bs->rescue_workqueue); |
1da177e4c
|
1763 1764 |
if (bs->bio_pool) mempool_destroy(bs->bio_pool); |
9f060e223
|
1765 1766 |
if (bs->bvec_pool) mempool_destroy(bs->bvec_pool); |
7878cba9f
|
1767 |
bioset_integrity_free(bs); |
bb799ca02
|
1768 |
bio_put_slab(bs); |
1da177e4c
|
1769 1770 1771 |
kfree(bs); } |
a112a71d4
|
1772 |
EXPORT_SYMBOL(bioset_free); |
1da177e4c
|
1773 |
|
d8f429e16
|
1774 1775 1776 |
static struct bio_set *__bioset_create(unsigned int pool_size, unsigned int front_pad, bool create_bvec_pool) |
1da177e4c
|
1777 |
{ |
392ddc329
|
1778 |
unsigned int back_pad = BIO_INLINE_VECS * sizeof(struct bio_vec); |
1b4344986
|
1779 |
struct bio_set *bs; |
1da177e4c
|
1780 |
|
1b4344986
|
1781 |
bs = kzalloc(sizeof(*bs), GFP_KERNEL); |
1da177e4c
|
1782 1783 |
if (!bs) return NULL; |
bb799ca02
|
1784 |
bs->front_pad = front_pad; |
1b4344986
|
1785 |
|
df2cb6daa
|
1786 1787 1788 |
spin_lock_init(&bs->rescue_lock); bio_list_init(&bs->rescue_list); INIT_WORK(&bs->rescue_work, bio_alloc_rescue); |
392ddc329
|
1789 |
bs->bio_slab = bio_find_or_create_slab(front_pad + back_pad); |
bb799ca02
|
1790 1791 1792 1793 1794 1795 |
if (!bs->bio_slab) { kfree(bs); return NULL; } bs->bio_pool = mempool_create_slab_pool(pool_size, bs->bio_slab); |
1da177e4c
|
1796 1797 |
if (!bs->bio_pool) goto bad; |
d8f429e16
|
1798 1799 1800 1801 1802 |
if (create_bvec_pool) { bs->bvec_pool = biovec_create_pool(pool_size); if (!bs->bvec_pool) goto bad; } |
df2cb6daa
|
1803 1804 1805 1806 |
bs->rescue_workqueue = alloc_workqueue("bioset", WQ_MEM_RECLAIM, 0); if (!bs->rescue_workqueue) goto bad; |
1da177e4c
|
1807 |
|
df2cb6daa
|
1808 |
return bs; |
1da177e4c
|
1809 1810 1811 1812 |
bad: bioset_free(bs); return NULL; } |
d8f429e16
|
1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 |
/** * bioset_create - Create a bio_set * @pool_size: Number of bio and bio_vecs to cache in the mempool * @front_pad: Number of bytes to allocate in front of the returned bio * * Description: * Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller * to ask for a number of bytes to be allocated in front of the bio. * Front pad allocation is useful for embedding the bio inside * another structure, to avoid allocating extra data to go with the bio. * Note that the bio must be embedded at the END of that structure always, * or things will break badly. */ struct bio_set *bioset_create(unsigned int pool_size, unsigned int front_pad) { return __bioset_create(pool_size, front_pad, true); } |
a112a71d4
|
1831 |
EXPORT_SYMBOL(bioset_create); |
1da177e4c
|
1832 |
|
d8f429e16
|
1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 |
/** * bioset_create_nobvec - Create a bio_set without bio_vec mempool * @pool_size: Number of bio to cache in the mempool * @front_pad: Number of bytes to allocate in front of the returned bio * * Description: * Same functionality as bioset_create() except that mempool is not * created for bio_vecs. Saving some memory for bio_clone_fast() users. */ struct bio_set *bioset_create_nobvec(unsigned int pool_size, unsigned int front_pad) { return __bioset_create(pool_size, front_pad, false); } EXPORT_SYMBOL(bioset_create_nobvec); |
852c788f8
|
1847 |
#ifdef CONFIG_BLK_CGROUP |
1d933cf09
|
1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 |
/** * bio_associate_blkcg - associate a bio with the specified blkcg * @bio: target bio * @blkcg_css: css of the blkcg to associate * * Associate @bio with the blkcg specified by @blkcg_css. Block layer will * treat @bio as if it were issued by a task which belongs to the blkcg. * * This function takes an extra reference of @blkcg_css which will be put * when @bio is released. The caller must own @bio and is responsible for * synchronizing calls to this function. */ int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css) { if (unlikely(bio->bi_css)) return -EBUSY; css_get(blkcg_css); bio->bi_css = blkcg_css; return 0; } |
5aa2a96b3
|
1869 |
EXPORT_SYMBOL_GPL(bio_associate_blkcg); |
1d933cf09
|
1870 |
|
852c788f8
|
1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 |
/** * bio_associate_current - associate a bio with %current * @bio: target bio * * Associate @bio with %current if it hasn't been associated yet. Block * layer will treat @bio as if it were issued by %current no matter which * task actually issues it. * * This function takes an extra reference of @task's io_context and blkcg * which will be put when @bio is released. The caller must own @bio, * ensure %current->io_context exists, and is responsible for synchronizing * calls to this function. */ int bio_associate_current(struct bio *bio) { struct io_context *ioc; |
852c788f8
|
1887 |
|
1d933cf09
|
1888 |
if (bio->bi_css) |
852c788f8
|
1889 1890 1891 1892 1893 |
return -EBUSY; ioc = current->io_context; if (!ioc) return -ENOENT; |
852c788f8
|
1894 1895 |
get_io_context_active(ioc); bio->bi_ioc = ioc; |
c165b3e3c
|
1896 |
bio->bi_css = task_get_css(current, io_cgrp_id); |
852c788f8
|
1897 1898 |
return 0; } |
5aa2a96b3
|
1899 |
EXPORT_SYMBOL_GPL(bio_associate_current); |
852c788f8
|
1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 |
/** * bio_disassociate_task - undo bio_associate_current() * @bio: target bio */ void bio_disassociate_task(struct bio *bio) { if (bio->bi_ioc) { put_io_context(bio->bi_ioc); bio->bi_ioc = NULL; } if (bio->bi_css) { css_put(bio->bi_css); bio->bi_css = NULL; } } #endif /* CONFIG_BLK_CGROUP */ |
1da177e4c
|
1918 1919 1920 1921 1922 1923 1924 |
static void __init biovec_init_slabs(void) { int i; for (i = 0; i < BIOVEC_NR_POOLS; i++) { int size; struct biovec_slab *bvs = bvec_slabs + i; |
a7fcd37cd
|
1925 1926 1927 1928 |
if (bvs->nr_vecs <= BIO_INLINE_VECS) { bvs->slab = NULL; continue; } |
a7fcd37cd
|
1929 |
|
1da177e4c
|
1930 1931 |
size = bvs->nr_vecs * sizeof(struct bio_vec); bvs->slab = kmem_cache_create(bvs->name, size, 0, |
20c2df83d
|
1932 |
SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); |
1da177e4c
|
1933 1934 1935 1936 1937 |
} } static int __init init_bio(void) { |
bb799ca02
|
1938 1939 1940 1941 1942 1943 |
bio_slab_max = 2; bio_slab_nr = 0; bio_slabs = kzalloc(bio_slab_max * sizeof(struct bio_slab), GFP_KERNEL); if (!bio_slabs) panic("bio: can't allocate bios "); |
1da177e4c
|
1944 |
|
7878cba9f
|
1945 |
bio_integrity_init(); |
1da177e4c
|
1946 |
biovec_init_slabs(); |
bb799ca02
|
1947 |
fs_bio_set = bioset_create(BIO_POOL_SIZE, 0); |
1da177e4c
|
1948 1949 1950 |
if (!fs_bio_set) panic("bio: can't allocate bios "); |
a91a2785b
|
1951 1952 1953 |
if (bioset_integrity_create(fs_bio_set, BIO_POOL_SIZE)) panic("bio: can't create integrity pool "); |
1da177e4c
|
1954 1955 |
return 0; } |
1da177e4c
|
1956 |
subsys_initcall(init_bio); |