Blame view
fs/iomap/direct-io.c
17 KB
db074436f iomap: move the d... |
1 2 3 4 5 6 7 8 |
// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2010 Red Hat, Inc. * Copyright (c) 2016-2018 Christoph Hellwig. */ #include <linux/module.h> #include <linux/compiler.h> #include <linux/fs.h> |
141f59b91 ANDROID: ext4, f2... |
9 |
#include <linux/fscrypt.h> |
db074436f iomap: move the d... |
10 11 12 13 |
#include <linux/iomap.h> #include <linux/backing-dev.h> #include <linux/uio.h> #include <linux/task_io_accounting_ops.h> |
60263d588 iomap: fall back ... |
14 |
#include "trace.h" |
db074436f iomap: move the d... |
15 16 17 18 19 20 21 22 23 24 25 26 27 28 |
#include "../internal.h" /* * Private flags for iomap_dio, must not overlap with the public ones in * iomap.h: */ #define IOMAP_DIO_WRITE_FUA (1 << 28) #define IOMAP_DIO_NEED_SYNC (1 << 29) #define IOMAP_DIO_WRITE (1 << 30) #define IOMAP_DIO_DIRTY (1 << 31) struct iomap_dio { struct kiocb *iocb; |
838c4f3d7 iomap: move the i... |
29 |
const struct iomap_dio_ops *dops; |
db074436f iomap: move the d... |
30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 |
loff_t i_size; loff_t size; atomic_t ref; unsigned flags; int error; bool wait_for_completion; union { /* used during submission and for synchronous completion: */ struct { struct iov_iter *iter; struct task_struct *waiter; struct request_queue *last_queue; blk_qc_t cookie; } submit; /* used for aio completion: */ struct { struct work_struct work; } aio; }; }; int iomap_dio_iopoll(struct kiocb *kiocb, bool spin) { struct request_queue *q = READ_ONCE(kiocb->private); if (!q) return 0; return blk_poll(q, READ_ONCE(kiocb->ki_cookie), spin); } EXPORT_SYMBOL_GPL(iomap_dio_iopoll); static void iomap_dio_submit_bio(struct iomap_dio *dio, struct iomap *iomap, |
8cecd0ba8 iomap: add a file... |
64 |
struct bio *bio, loff_t pos) |
db074436f iomap: move the d... |
65 66 67 68 69 70 71 |
{ atomic_inc(&dio->ref); if (dio->iocb->ki_flags & IOCB_HIPRI) bio_set_polled(bio, dio->iocb); dio->submit.last_queue = bdev_get_queue(iomap->bdev); |
8cecd0ba8 iomap: add a file... |
72 73 74 75 76 77 |
if (dio->dops && dio->dops->submit_io) dio->submit.cookie = dio->dops->submit_io( file_inode(dio->iocb->ki_filp), iomap, bio, pos); else dio->submit.cookie = submit_bio(bio); |
db074436f iomap: move the d... |
78 |
} |
c3d4ed1ab iomap: Allow file... |
79 |
ssize_t iomap_dio_complete(struct iomap_dio *dio) |
db074436f iomap: move the d... |
80 |
{ |
838c4f3d7 iomap: move the i... |
81 |
const struct iomap_dio_ops *dops = dio->dops; |
db074436f iomap: move the d... |
82 83 84 |
struct kiocb *iocb = dio->iocb; struct inode *inode = file_inode(iocb->ki_filp); loff_t offset = iocb->ki_pos; |
838c4f3d7 iomap: move the i... |
85 |
ssize_t ret = dio->error; |
db074436f iomap: move the d... |
86 |
|
838c4f3d7 iomap: move the i... |
87 88 |
if (dops && dops->end_io) ret = dops->end_io(iocb, dio->size, ret, dio->flags); |
db074436f iomap: move the d... |
89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 |
if (likely(!ret)) { ret = dio->size; /* check for short read */ if (offset + ret > dio->i_size && !(dio->flags & IOMAP_DIO_WRITE)) ret = dio->i_size - offset; iocb->ki_pos += ret; } /* * Try again to invalidate clean pages which might have been cached by * non-direct readahead, or faulted in by get_user_pages() if the source * of the write was an mmap'ed region of the file we're writing. Either * one is a pretty crazy thing to do, so we don't support it 100%. If * this invalidation fails, tough, the write still worked... * |
838c4f3d7 iomap: move the i... |
106 107 108 |
* And this page cache invalidation has to be after ->end_io(), as some * filesystems convert unwritten extents to real allocations in * ->end_io() when necessary, otherwise a racing buffer read would cache |
db074436f iomap: move the d... |
109 110 |
* zeros from unwritten extents. */ |
c114bbc6c iomap: Fix direct... |
111 |
if (!dio->error && dio->size && |
db074436f iomap: move the d... |
112 113 114 115 116 117 118 119 |
(dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) { int err; err = invalidate_inode_pages2_range(inode->i_mapping, offset >> PAGE_SHIFT, (offset + dio->size - 1) >> PAGE_SHIFT); if (err) dio_warn_stale_pagecache(iocb->ki_filp); } |
1a31182ed iomap: Call inode... |
120 |
inode_dio_end(file_inode(iocb->ki_filp)); |
db074436f iomap: move the d... |
121 122 123 124 125 126 |
/* * If this is a DSYNC write, make sure we push it to stable storage now * that we've written data. */ if (ret > 0 && (dio->flags & IOMAP_DIO_NEED_SYNC)) ret = generic_write_sync(iocb, ret); |
db074436f iomap: move the d... |
127 128 129 130 |
kfree(dio); return ret; } |
c3d4ed1ab iomap: Allow file... |
131 |
EXPORT_SYMBOL_GPL(iomap_dio_complete); |
db074436f iomap: move the d... |
132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 |
static void iomap_dio_complete_work(struct work_struct *work) { struct iomap_dio *dio = container_of(work, struct iomap_dio, aio.work); struct kiocb *iocb = dio->iocb; iocb->ki_complete(iocb, iomap_dio_complete(dio), 0); } /* * Set an error in the dio if none is set yet. We have to use cmpxchg * as the submission context and the completion context(s) can race to * update the error. */ static inline void iomap_dio_set_error(struct iomap_dio *dio, int ret) { cmpxchg(&dio->error, 0, ret); } static void iomap_dio_bio_end_io(struct bio *bio) { struct iomap_dio *dio = bio->bi_private; bool should_dirty = (dio->flags & IOMAP_DIO_DIRTY); if (bio->bi_status) iomap_dio_set_error(dio, blk_status_to_errno(bio->bi_status)); if (atomic_dec_and_test(&dio->ref)) { if (dio->wait_for_completion) { struct task_struct *waiter = dio->submit.waiter; WRITE_ONCE(dio->submit.waiter, NULL); blk_wake_io_task(waiter); } else if (dio->flags & IOMAP_DIO_WRITE) { struct inode *inode = file_inode(dio->iocb->ki_filp); INIT_WORK(&dio->aio.work, iomap_dio_complete_work); queue_work(inode->i_sb->s_dio_done_wq, &dio->aio.work); } else { iomap_dio_complete_work(&dio->aio.work); } } if (should_dirty) { bio_check_pages_dirty(bio); } else { bio_release_pages(bio, false); bio_put(bio); } } static void iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos, unsigned len) { |
141f59b91 ANDROID: ext4, f2... |
186 |
struct inode *inode = file_inode(dio->iocb->ki_filp); |
db074436f iomap: move the d... |
187 188 189 190 191 |
struct page *page = ZERO_PAGE(0); int flags = REQ_SYNC | REQ_IDLE; struct bio *bio; bio = bio_alloc(GFP_KERNEL, 1); |
141f59b91 ANDROID: ext4, f2... |
192 193 |
fscrypt_set_bio_crypt_ctx(bio, inode, pos >> inode->i_blkbits, GFP_KERNEL); |
db074436f iomap: move the d... |
194 195 196 197 198 199 200 201 |
bio_set_dev(bio, iomap->bdev); bio->bi_iter.bi_sector = iomap_sector(iomap, pos); bio->bi_private = dio; bio->bi_end_io = iomap_dio_bio_end_io; get_page(page); __bio_add_page(bio, page, len, 0); bio_set_op_attrs(bio, REQ_OP_WRITE, flags); |
8cecd0ba8 iomap: add a file... |
202 |
iomap_dio_submit_bio(dio, iomap, bio, pos); |
db074436f iomap: move the d... |
203 204 205 206 207 208 209 210 211 |
} static loff_t iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, struct iomap_dio *dio, struct iomap *iomap) { unsigned int blkbits = blksize_bits(bdev_logical_block_size(iomap->bdev)); unsigned int fs_block_size = i_blocksize(inode), pad; unsigned int align = iov_iter_alignment(dio->submit.iter); |
db074436f iomap: move the d... |
212 213 214 215 216 |
struct bio *bio; bool need_zeroout = false; bool use_fua = false; int nr_pages, ret = 0; size_t copied = 0; |
f550ee9b8 iomap: Do not cre... |
217 |
size_t orig_count; |
db074436f iomap: move the d... |
218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 |
if ((pos | length | align) & ((1 << blkbits) - 1)) return -EINVAL; if (iomap->type == IOMAP_UNWRITTEN) { dio->flags |= IOMAP_DIO_UNWRITTEN; need_zeroout = true; } if (iomap->flags & IOMAP_F_SHARED) dio->flags |= IOMAP_DIO_COW; if (iomap->flags & IOMAP_F_NEW) { need_zeroout = true; } else if (iomap->type == IOMAP_MAPPED) { /* * Use a FUA write if we need datasync semantics, this is a pure * data IO that doesn't require any metadata updates (including * after IO completion such as unwritten extent conversion) and * the underlying device supports FUA. This allows us to avoid * cache flushes on IO completion. */ if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) && (dio->flags & IOMAP_DIO_WRITE_FUA) && blk_queue_fua(bdev_get_queue(iomap->bdev))) use_fua = true; } /* |
f550ee9b8 iomap: Do not cre... |
247 248 249 |
* Save the original count and trim the iter to just the extent we * are operating on right now. The iter will be re-expanded once * we are done. |
db074436f iomap: move the d... |
250 |
*/ |
f550ee9b8 iomap: Do not cre... |
251 252 |
orig_count = iov_iter_count(dio->submit.iter); iov_iter_truncate(dio->submit.iter, length); |
db074436f iomap: move the d... |
253 |
|
f550ee9b8 iomap: Do not cre... |
254 255 256 257 258 |
nr_pages = iov_iter_npages(dio->submit.iter, BIO_MAX_PAGES); if (nr_pages <= 0) { ret = nr_pages; goto out; } |
8d6c90c9d ANDROID: fscrypt:... |
259 |
nr_pages = fscrypt_limit_dio_pages(inode, pos, nr_pages); |
db074436f iomap: move the d... |
260 261 262 263 264 265 266 267 268 269 270 271 |
if (need_zeroout) { /* zero out from the start of the block to the write offset */ pad = pos & (fs_block_size - 1); if (pad) iomap_dio_zero(dio, iomap, pos - pad, pad); } do { size_t n; if (dio->error) { iov_iter_revert(dio->submit.iter, copied); |
f550ee9b8 iomap: Do not cre... |
272 273 |
copied = ret = 0; goto out; |
db074436f iomap: move the d... |
274 275 276 |
} bio = bio_alloc(GFP_KERNEL, nr_pages); |
141f59b91 ANDROID: ext4, f2... |
277 278 |
fscrypt_set_bio_crypt_ctx(bio, inode, pos >> inode->i_blkbits, GFP_KERNEL); |
db074436f iomap: move the d... |
279 280 281 282 283 284 |
bio_set_dev(bio, iomap->bdev); bio->bi_iter.bi_sector = iomap_sector(iomap, pos); bio->bi_write_hint = dio->iocb->ki_hint; bio->bi_ioprio = dio->iocb->ki_ioprio; bio->bi_private = dio; bio->bi_end_io = iomap_dio_bio_end_io; |
f550ee9b8 iomap: Do not cre... |
285 |
ret = bio_iov_iter_get_pages(bio, dio->submit.iter); |
db074436f iomap: move the d... |
286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 |
if (unlikely(ret)) { /* * We have to stop part way through an IO. We must fall * through to the sub-block tail zeroing here, otherwise * this short IO may expose stale data in the tail of * the block we haven't written data to. */ bio_put(bio); goto zero_tail; } n = bio->bi_iter.bi_size; if (dio->flags & IOMAP_DIO_WRITE) { bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE; if (use_fua) bio->bi_opf |= REQ_FUA; else dio->flags &= ~IOMAP_DIO_WRITE_FUA; task_io_account_write(n); } else { bio->bi_opf = REQ_OP_READ; if (dio->flags & IOMAP_DIO_DIRTY) bio_set_pages_dirty(bio); } |
db074436f iomap: move the d... |
310 |
dio->size += n; |
db074436f iomap: move the d... |
311 |
copied += n; |
f550ee9b8 iomap: Do not cre... |
312 |
nr_pages = iov_iter_npages(dio->submit.iter, BIO_MAX_PAGES); |
8d6c90c9d ANDROID: fscrypt:... |
313 |
nr_pages = fscrypt_limit_dio_pages(inode, pos, nr_pages); |
8cecd0ba8 iomap: add a file... |
314 315 |
iomap_dio_submit_bio(dio, iomap, bio, pos); pos += n; |
db074436f iomap: move the d... |
316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 |
} while (nr_pages); /* * We need to zeroout the tail of a sub-block write if the extent type * requires zeroing or the write extends beyond EOF. If we don't zero * the block tail in the latter case, we can expose stale data via mmap * reads of the EOF block. */ zero_tail: if (need_zeroout || ((dio->flags & IOMAP_DIO_WRITE) && pos >= i_size_read(inode))) { /* zero out from the end of the write to the end of the block */ pad = pos & (fs_block_size - 1); if (pad) iomap_dio_zero(dio, iomap, pos, fs_block_size - pad); } |
f550ee9b8 iomap: Do not cre... |
332 333 334 |
out: /* Undo iter limitation to current extent */ iov_iter_reexpand(dio->submit.iter, orig_count - copied); |
e9f930ac8 iomap: fix return... |
335 336 337 |
if (copied) return copied; return ret; |
db074436f iomap: move the d... |
338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 |
} static loff_t iomap_dio_hole_actor(loff_t length, struct iomap_dio *dio) { length = iov_iter_zero(length, dio->submit.iter); dio->size += length; return length; } static loff_t iomap_dio_inline_actor(struct inode *inode, loff_t pos, loff_t length, struct iomap_dio *dio, struct iomap *iomap) { struct iov_iter *iter = dio->submit.iter; size_t copied; BUG_ON(pos + length > PAGE_SIZE - offset_in_page(iomap->inline_data)); if (dio->flags & IOMAP_DIO_WRITE) { loff_t size = inode->i_size; if (pos > size) memset(iomap->inline_data + size, 0, pos - size); copied = copy_from_iter(iomap->inline_data + pos, length, iter); if (copied) { if (pos + copied > size) i_size_write(inode, pos + copied); mark_inode_dirty(inode); } } else { copied = copy_to_iter(iomap->inline_data + pos, length, iter); } dio->size += copied; return copied; } static loff_t iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length, |
c039b9979 iomap: use a srcm... |
377 |
void *data, struct iomap *iomap, struct iomap *srcmap) |
db074436f iomap: move the d... |
378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 |
{ struct iomap_dio *dio = data; switch (iomap->type) { case IOMAP_HOLE: if (WARN_ON_ONCE(dio->flags & IOMAP_DIO_WRITE)) return -EIO; return iomap_dio_hole_actor(length, dio); case IOMAP_UNWRITTEN: if (!(dio->flags & IOMAP_DIO_WRITE)) return iomap_dio_hole_actor(length, dio); return iomap_dio_bio_actor(inode, pos, length, dio, iomap); case IOMAP_MAPPED: return iomap_dio_bio_actor(inode, pos, length, dio, iomap); case IOMAP_INLINE: return iomap_dio_inline_actor(inode, pos, length, dio, iomap); |
a805c1116 iomap: fix WARN_O... |
394 395 396 397 398 399 400 401 402 403 404 |
case IOMAP_DELALLOC: /* * DIO is not serialised against mmap() access at all, and so * if the page_mkwrite occurs between the writeback and the * iomap_apply() call in the DIO path, then it will see the * DELALLOC block that the page-mkwrite allocated. */ pr_warn_ratelimited("Direct I/O collision with buffered writes! File: %pD4 Comm: %.20s ", dio->iocb->ki_filp, current->comm); return -EIO; |
db074436f iomap: move the d... |
405 406 407 408 409 410 411 412 413 414 415 416 417 418 |
default: WARN_ON_ONCE(1); return -EIO; } } /* * iomap_dio_rw() always completes O_[D]SYNC writes regardless of whether the IO * is being issued as AIO or not. This allows us to optimise pure data writes * to use REQ_FUA rather than requiring generic_write_sync() to issue a * REQ_FLUSH post write. This is slightly tricky because a single request here * can be mapped into multiple disjoint IOs and only a subset of the IOs issued * may be pure data writes. In that case, we still need to do a full data sync * completion. |
60263d588 iomap: fall back ... |
419 420 421 |
* * Returns -ENOTBLK In case of a page invalidation invalidation failure for * writes. The callers needs to fall back to buffered I/O in this case. |
db074436f iomap: move the d... |
422 |
*/ |
c3d4ed1ab iomap: Allow file... |
423 424 |
struct iomap_dio * __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, |
13ef95444 iomap: Allow forc... |
425 426 |
const struct iomap_ops *ops, const struct iomap_dio_ops *dops, bool wait_for_completion) |
db074436f iomap: move the d... |
427 428 429 430 |
{ struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = file_inode(iocb->ki_filp); size_t count = iov_iter_count(iter); |
88cfd30e1 iomap: remove unn... |
431 |
loff_t pos = iocb->ki_pos; |
db074436f iomap: move the d... |
432 433 |
loff_t end = iocb->ki_pos + count - 1, ret = 0; unsigned int flags = IOMAP_DIRECT; |
db074436f iomap: move the d... |
434 435 |
struct blk_plug plug; struct iomap_dio *dio; |
db074436f iomap: move the d... |
436 |
if (!count) |
c3d4ed1ab iomap: Allow file... |
437 |
return NULL; |
db074436f iomap: move the d... |
438 |
|
13ef95444 iomap: Allow forc... |
439 |
if (WARN_ON(is_sync_kiocb(iocb) && !wait_for_completion)) |
c3d4ed1ab iomap: Allow file... |
440 |
return ERR_PTR(-EIO); |
13ef95444 iomap: Allow forc... |
441 |
|
db074436f iomap: move the d... |
442 443 |
dio = kmalloc(sizeof(*dio), GFP_KERNEL); if (!dio) |
c3d4ed1ab iomap: Allow file... |
444 |
return ERR_PTR(-ENOMEM); |
db074436f iomap: move the d... |
445 446 447 448 449 |
dio->iocb = iocb; atomic_set(&dio->ref, 1); dio->size = 0; dio->i_size = i_size_read(inode); |
838c4f3d7 iomap: move the i... |
450 |
dio->dops = dops; |
db074436f iomap: move the d... |
451 452 453 454 455 456 457 458 459 460 461 |
dio->error = 0; dio->flags = 0; dio->submit.iter = iter; dio->submit.waiter = current; dio->submit.cookie = BLK_QC_T_NONE; dio->submit.last_queue = NULL; if (iov_iter_rw(iter) == READ) { if (pos >= dio->i_size) goto out_free_dio; |
a90100421 fs/iomap: remove ... |
462 |
if (iter_is_iovec(iter)) |
db074436f iomap: move the d... |
463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 |
dio->flags |= IOMAP_DIO_DIRTY; } else { flags |= IOMAP_WRITE; dio->flags |= IOMAP_DIO_WRITE; /* for data sync or sync, we need sync completion processing */ if (iocb->ki_flags & IOCB_DSYNC) dio->flags |= IOMAP_DIO_NEED_SYNC; /* * For datasync only writes, we optimistically try using FUA for * this IO. Any non-FUA write that occurs will clear this flag, * hence we know before completion whether a cache flush is * necessary. */ if ((iocb->ki_flags & (IOCB_DSYNC | IOCB_SYNC)) == IOCB_DSYNC) dio->flags |= IOMAP_DIO_WRITE_FUA; } if (iocb->ki_flags & IOCB_NOWAIT) { |
88cfd30e1 iomap: remove unn... |
483 |
if (filemap_range_has_page(mapping, pos, end)) { |
db074436f iomap: move the d... |
484 485 486 487 488 |
ret = -EAGAIN; goto out_free_dio; } flags |= IOMAP_NOWAIT; } |
88cfd30e1 iomap: remove unn... |
489 |
ret = filemap_write_and_wait_range(mapping, pos, end); |
db074436f iomap: move the d... |
490 491 |
if (ret) goto out_free_dio; |
54752de92 iomap: Only inval... |
492 493 494 |
if (iov_iter_rw(iter) == WRITE) { /* * Try to invalidate cache pages for the range we are writing. |
60263d588 iomap: fall back ... |
495 496 |
* If this invalidation fails, let the caller fall back to * buffered I/O. |
54752de92 iomap: Only inval... |
497 498 |
*/ if (invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, |
60263d588 iomap: fall back ... |
499 500 501 |
end >> PAGE_SHIFT)) { trace_iomap_dio_invalidate_fail(inode, pos, count); ret = -ENOTBLK; |
db074436f iomap: move the d... |
502 |
goto out_free_dio; |
60263d588 iomap: fall back ... |
503 |
} |
db074436f iomap: move the d... |
504 |
|
54752de92 iomap: Only inval... |
505 506 507 508 509 |
if (!wait_for_completion && !inode->i_sb->s_dio_done_wq) { ret = sb_init_dio_done_wq(inode->i_sb); if (ret < 0) goto out_free_dio; } |
db074436f iomap: move the d... |
510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 |
} inode_dio_begin(inode); blk_start_plug(&plug); do { ret = iomap_apply(inode, pos, count, flags, ops, dio, iomap_dio_actor); if (ret <= 0) { /* magic error code to fall back to buffered I/O */ if (ret == -ENOTBLK) { wait_for_completion = true; ret = 0; } break; } pos += ret; |
419e9c38a iomap: Fix pipe p... |
527 528 529 530 531 532 533 |
if (iov_iter_rw(iter) == READ && pos >= dio->i_size) { /* * We only report that we've read data up to i_size. * Revert iter to a state corresponding to that as * some callers (such as splice code) rely on it. */ iov_iter_revert(iter, pos - dio->i_size); |
db074436f iomap: move the d... |
534 |
break; |
419e9c38a iomap: Fix pipe p... |
535 |
} |
db074436f iomap: move the d... |
536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 |
} while ((count = iov_iter_count(iter)) > 0); blk_finish_plug(&plug); if (ret < 0) iomap_dio_set_error(dio, ret); /* * If all the writes we issued were FUA, we don't need to flush the * cache on IO completion. Clear the sync flag for this case. */ if (dio->flags & IOMAP_DIO_WRITE_FUA) dio->flags &= ~IOMAP_DIO_NEED_SYNC; WRITE_ONCE(iocb->ki_cookie, dio->submit.cookie); WRITE_ONCE(iocb->private, dio->submit.last_queue); /* * We are about to drop our additional submission reference, which |
d9973ce2f iomap: fix commen... |
554 555 |
* might be the last reference to the dio. There are three different * ways we can progress here: |
db074436f iomap: move the d... |
556 557 558 559 560 561 562 563 564 565 566 567 568 569 |
* * (a) If this is the last reference we will always complete and free * the dio ourselves. * (b) If this is not the last reference, and we serve an asynchronous * iocb, we must never touch the dio after the decrement, the * I/O completion handler will complete and free it. * (c) If this is not the last reference, but we serve a synchronous * iocb, the I/O completion handler will wake us up on the drop * of the final reference, and we will complete and free it here * after we got woken by the I/O completion handler. */ dio->wait_for_completion = wait_for_completion; if (!atomic_dec_and_test(&dio->ref)) { if (!wait_for_completion) |
c3d4ed1ab iomap: Allow file... |
570 |
return ERR_PTR(-EIOCBQUEUED); |
db074436f iomap: move the d... |
571 572 573 574 575 576 577 578 579 580 |
for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (!READ_ONCE(dio->submit.waiter)) break; if (!(iocb->ki_flags & IOCB_HIPRI) || !dio->submit.last_queue || !blk_poll(dio->submit.last_queue, dio->submit.cookie, true)) |
e6249cdd4 block: add blk_io... |
581 |
blk_io_schedule(); |
db074436f iomap: move the d... |
582 583 584 |
} __set_current_state(TASK_RUNNING); } |
c3d4ed1ab iomap: Allow file... |
585 |
return dio; |
db074436f iomap: move the d... |
586 587 588 |
out_free_dio: kfree(dio); |
c3d4ed1ab iomap: Allow file... |
589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 |
if (ret) return ERR_PTR(ret); return NULL; } EXPORT_SYMBOL_GPL(__iomap_dio_rw); ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, bool wait_for_completion) { struct iomap_dio *dio; dio = __iomap_dio_rw(iocb, iter, ops, dops, wait_for_completion); if (IS_ERR_OR_NULL(dio)) return PTR_ERR_OR_ZERO(dio); return iomap_dio_complete(dio); |
db074436f iomap: move the d... |
606 607 |
} EXPORT_SYMBOL_GPL(iomap_dio_rw); |