Blame view
fs/block_dev.c
49.7 KB
1da177e4c
|
1 2 3 4 5 6 |
/* * linux/fs/block_dev.c * * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE */ |
1da177e4c
|
7 8 9 10 11 12 |
#include <linux/init.h> #include <linux/mm.h> #include <linux/fcntl.h> #include <linux/slab.h> #include <linux/kmod.h> #include <linux/major.h> |
7db9cfd38
|
13 |
#include <linux/device_cgroup.h> |
1da177e4c
|
14 15 |
#include <linux/highmem.h> #include <linux/blkdev.h> |
66114cad6
|
16 |
#include <linux/backing-dev.h> |
1da177e4c
|
17 18 |
#include <linux/module.h> #include <linux/blkpg.h> |
b502bd115
|
19 |
#include <linux/magic.h> |
1da177e4c
|
20 |
#include <linux/buffer_head.h> |
ff01bb483
|
21 |
#include <linux/swap.h> |
585d3bc06
|
22 |
#include <linux/pagevec.h> |
811d736f9
|
23 |
#include <linux/writeback.h> |
1da177e4c
|
24 25 26 27 |
#include <linux/mpage.h> #include <linux/mount.h> #include <linux/uio.h> #include <linux/namei.h> |
1368c4f24
|
28 |
#include <linux/log2.h> |
ff01bb483
|
29 |
#include <linux/cleancache.h> |
c94c2acf8
|
30 |
#include <linux/dax.h> |
acc93d30d
|
31 |
#include <linux/badblocks.h> |
25f4c4141
|
32 |
#include <linux/falloc.h> |
1da177e4c
|
33 |
#include <asm/uaccess.h> |
07f3f05c1
|
34 |
#include "internal.h" |
1da177e4c
|
35 36 37 38 39 |
struct bdev_inode { struct block_device bdev; struct inode vfs_inode; }; |
4c54ac62d
|
40 |
static const struct address_space_operations def_blk_aops; |
1da177e4c
|
41 42 43 44 |
static inline struct bdev_inode *BDEV_I(struct inode *inode) { return container_of(inode, struct bdev_inode, vfs_inode); } |
ff5053f66
|
45 |
struct block_device *I_BDEV(struct inode *inode) |
1da177e4c
|
46 47 48 |
{ return &BDEV_I(inode)->bdev; } |
1da177e4c
|
49 |
EXPORT_SYMBOL(I_BDEV); |
2af3a8159
|
50 51 52 53 54 55 56 57 58 59 60 61 |
void __vfs_msg(struct super_block *sb, const char *prefix, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk_ratelimited("%sVFS (%s): %pV ", prefix, sb->s_id, &vaf); va_end(args); } |
dbd3ca507
|
62 |
static void bdev_write_inode(struct block_device *bdev) |
564f00f6c
|
63 |
{ |
dbd3ca507
|
64 65 |
struct inode *inode = bdev->bd_inode; int ret; |
564f00f6c
|
66 67 68 |
spin_lock(&inode->i_lock); while (inode->i_state & I_DIRTY) { spin_unlock(&inode->i_lock); |
dbd3ca507
|
69 70 71 72 73 74 75 76 |
ret = write_inode_now(inode, true); if (ret) { char name[BDEVNAME_SIZE]; pr_warn_ratelimited("VFS: Dirty inode writeback failed " "for block device %s (err=%d). ", bdevname(bdev, name), ret); } |
564f00f6c
|
77 78 79 80 |
spin_lock(&inode->i_lock); } spin_unlock(&inode->i_lock); } |
f9a14399a
|
81 |
/* Kill _all_ buffers and pagecache , dirty or not.. */ |
ff01bb483
|
82 |
void kill_bdev(struct block_device *bdev) |
1da177e4c
|
83 |
{ |
ff01bb483
|
84 |
struct address_space *mapping = bdev->bd_inode->i_mapping; |
f9fe48bec
|
85 |
if (mapping->nrpages == 0 && mapping->nrexceptional == 0) |
f9a14399a
|
86 |
return; |
ff01bb483
|
87 |
|
f9a14399a
|
88 |
invalidate_bh_lrus(); |
ff01bb483
|
89 |
truncate_inode_pages(mapping, 0); |
1da177e4c
|
90 |
} |
ff01bb483
|
91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 |
EXPORT_SYMBOL(kill_bdev); /* Invalidate clean unused buffers and pagecache. */ void invalidate_bdev(struct block_device *bdev) { struct address_space *mapping = bdev->bd_inode->i_mapping; if (mapping->nrpages == 0) return; invalidate_bh_lrus(); lru_add_drain_all(); /* make sure all lru add caches are flushed */ invalidate_mapping_pages(mapping, 0, -1); /* 99% of the time, we don't need to flush the cleancache on the bdev. * But, for the strange corners, lets be cautious */ |
3167760f8
|
107 |
cleancache_invalidate_inode(mapping); |
ff01bb483
|
108 109 |
} EXPORT_SYMBOL(invalidate_bdev); |
1da177e4c
|
110 111 112 113 |
int set_blocksize(struct block_device *bdev, int size) { /* Size must be a power of two, and between 512 and PAGE_SIZE */ |
1368c4f24
|
114 |
if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size)) |
1da177e4c
|
115 116 117 |
return -EINVAL; /* Size cannot be smaller than the size supported by the device */ |
e1defc4ff
|
118 |
if (size < bdev_logical_block_size(bdev)) |
1da177e4c
|
119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 |
return -EINVAL; /* Don't change the size if it is same as current */ if (bdev->bd_block_size != size) { sync_blockdev(bdev); bdev->bd_block_size = size; bdev->bd_inode->i_blkbits = blksize_bits(size); kill_bdev(bdev); } return 0; } EXPORT_SYMBOL(set_blocksize); int sb_set_blocksize(struct super_block *sb, int size) { |
1da177e4c
|
135 136 137 138 139 |
if (set_blocksize(sb->s_bdev, size)) return 0; /* If we get here, we know size is power of two * and it's value is between 512 and PAGE_SIZE */ sb->s_blocksize = size; |
38885bd4c
|
140 |
sb->s_blocksize_bits = blksize_bits(size); |
1da177e4c
|
141 142 143 144 145 146 147 |
return sb->s_blocksize; } EXPORT_SYMBOL(sb_set_blocksize); int sb_min_blocksize(struct super_block *sb, int size) { |
e1defc4ff
|
148 |
int minsize = bdev_logical_block_size(sb->s_bdev); |
1da177e4c
|
149 150 151 152 153 154 155 156 157 158 159 |
if (size < minsize) size = minsize; return sb_set_blocksize(sb, size); } EXPORT_SYMBOL(sb_min_blocksize); static int blkdev_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh, int create) { |
1da177e4c
|
160 161 162 163 164 |
bh->b_bdev = I_BDEV(inode); bh->b_blocknr = iblock; set_buffer_mapped(bh); return 0; } |
4ebb16ca9
|
165 166 167 168 |
static struct inode *bdev_file_inode(struct file *file) { return file->f_mapping->host; } |
b2e895dbd
|
169 |
static ssize_t |
c8b8e32d7
|
170 |
blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter) |
b2e895dbd
|
171 172 |
{ struct file *file = iocb->ki_filp; |
4ebb16ca9
|
173 |
struct inode *inode = bdev_file_inode(file); |
b2e895dbd
|
174 |
|
c8b8e32d7
|
175 |
return __blockdev_direct_IO(iocb, inode, I_BDEV(inode), iter, |
fe0f07d08
|
176 177 |
blkdev_get_block, NULL, NULL, DIO_SKIP_DIO_COUNT); |
b2e895dbd
|
178 |
} |
5cee5815d
|
179 180 181 182 183 184 185 186 |
int __sync_blockdev(struct block_device *bdev, int wait) { if (!bdev) return 0; if (!wait) return filemap_flush(bdev->bd_inode->i_mapping); return filemap_write_and_wait(bdev->bd_inode->i_mapping); } |
585d3bc06
|
187 188 189 190 191 192 |
/* * Write out and wait upon all the dirty data associated with a block * device via its mapping. Does not take the superblock lock. */ int sync_blockdev(struct block_device *bdev) { |
5cee5815d
|
193 |
return __sync_blockdev(bdev, 1); |
585d3bc06
|
194 195 196 197 198 199 200 201 202 203 204 205 |
} EXPORT_SYMBOL(sync_blockdev); /* * Write out and wait upon all dirty data associated with this * device. Filesystem data as well as the underlying block * device. Takes the superblock lock. */ int fsync_bdev(struct block_device *bdev) { struct super_block *sb = get_super(bdev); if (sb) { |
60b0680fa
|
206 |
int res = sync_filesystem(sb); |
585d3bc06
|
207 208 209 210 211 |
drop_super(sb); return res; } return sync_blockdev(bdev); } |
47e4491b4
|
212 |
EXPORT_SYMBOL(fsync_bdev); |
585d3bc06
|
213 214 215 216 217 |
/** * freeze_bdev -- lock a filesystem and force it into a consistent state * @bdev: blockdevice to lock * |
585d3bc06
|
218 219 220 221 222 223 224 225 226 227 228 229 230 231 |
* If a superblock is found on this device, we take the s_umount semaphore * on it to make sure nobody unmounts until the snapshot creation is done. * The reference counter (bd_fsfreeze_count) guarantees that only the last * unfreeze process can unfreeze the frozen filesystem actually when multiple * freeze requests arrive simultaneously. It counts up in freeze_bdev() and * count down in thaw_bdev(). When it becomes 0, thaw_bdev() will unfreeze * actually. */ struct super_block *freeze_bdev(struct block_device *bdev) { struct super_block *sb; int error = 0; mutex_lock(&bdev->bd_fsfreeze_mutex); |
4504230a7
|
232 233 234 235 236 237 |
if (++bdev->bd_fsfreeze_count > 1) { /* * We don't even need to grab a reference - the first call * to freeze_bdev grab an active reference and only the last * thaw_bdev drops it. */ |
585d3bc06
|
238 |
sb = get_super(bdev); |
5bb53c0fb
|
239 240 |
if (sb) drop_super(sb); |
4504230a7
|
241 242 243 244 245 246 247 |
mutex_unlock(&bdev->bd_fsfreeze_mutex); return sb; } sb = get_active_super(bdev); if (!sb) goto out; |
48b6bca6b
|
248 249 250 251 |
if (sb->s_op->freeze_super) error = sb->s_op->freeze_super(sb); else error = freeze_super(sb); |
18e9e5104
|
252 253 254 |
if (error) { deactivate_super(sb); bdev->bd_fsfreeze_count--; |
585d3bc06
|
255 |
mutex_unlock(&bdev->bd_fsfreeze_mutex); |
18e9e5104
|
256 |
return ERR_PTR(error); |
585d3bc06
|
257 |
} |
18e9e5104
|
258 |
deactivate_super(sb); |
4504230a7
|
259 |
out: |
585d3bc06
|
260 261 |
sync_blockdev(bdev); mutex_unlock(&bdev->bd_fsfreeze_mutex); |
4fadd7bb2
|
262 |
return sb; /* thaw_bdev releases s->s_umount */ |
585d3bc06
|
263 264 265 266 267 268 269 270 271 272 273 274 |
} EXPORT_SYMBOL(freeze_bdev); /** * thaw_bdev -- unlock filesystem * @bdev: blockdevice to unlock * @sb: associated superblock * * Unlocks the filesystem and marks it writeable again after freeze_bdev(). */ int thaw_bdev(struct block_device *bdev, struct super_block *sb) { |
4504230a7
|
275 |
int error = -EINVAL; |
585d3bc06
|
276 277 |
mutex_lock(&bdev->bd_fsfreeze_mutex); |
4504230a7
|
278 |
if (!bdev->bd_fsfreeze_count) |
18e9e5104
|
279 |
goto out; |
4504230a7
|
280 281 282 |
error = 0; if (--bdev->bd_fsfreeze_count > 0) |
18e9e5104
|
283 |
goto out; |
4504230a7
|
284 285 |
if (!sb) |
18e9e5104
|
286 |
goto out; |
4504230a7
|
287 |
|
48b6bca6b
|
288 289 290 291 |
if (sb->s_op->thaw_super) error = sb->s_op->thaw_super(sb); else error = thaw_super(sb); |
997198ba1
|
292 |
if (error) |
18e9e5104
|
293 |
bdev->bd_fsfreeze_count++; |
18e9e5104
|
294 |
out: |
585d3bc06
|
295 |
mutex_unlock(&bdev->bd_fsfreeze_mutex); |
997198ba1
|
296 |
return error; |
585d3bc06
|
297 298 |
} EXPORT_SYMBOL(thaw_bdev); |
1da177e4c
|
299 300 301 302 303 304 305 306 307 |
static int blkdev_writepage(struct page *page, struct writeback_control *wbc) { return block_write_full_page(page, blkdev_get_block, wbc); } static int blkdev_readpage(struct file * file, struct page * page) { return block_read_full_page(page, blkdev_get_block); } |
447f05bb4
|
308 309 310 311 312 |
static int blkdev_readpages(struct file *file, struct address_space *mapping, struct list_head *pages, unsigned nr_pages) { return mpage_readpages(mapping, pages, nr_pages, blkdev_get_block); } |
6272b5a58
|
313 314 315 |
static int blkdev_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) |
1da177e4c
|
316 |
{ |
155130a4f
|
317 318 |
return block_write_begin(mapping, pos, len, flags, pagep, blkdev_get_block); |
1da177e4c
|
319 |
} |
6272b5a58
|
320 321 322 |
static int blkdev_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) |
1da177e4c
|
323 |
{ |
6272b5a58
|
324 325 326 327 |
int ret; ret = block_write_end(file, mapping, pos, len, copied, page, fsdata); unlock_page(page); |
09cbfeaf1
|
328 |
put_page(page); |
6272b5a58
|
329 330 |
return ret; |
1da177e4c
|
331 332 333 334 |
} /* * private llseek: |
496ad9aa8
|
335 |
* for a block special file file_inode(file)->i_size is zero |
1da177e4c
|
336 337 |
* so we compute the size by hand (just as in block_read/write above) */ |
965c8e59c
|
338 |
static loff_t block_llseek(struct file *file, loff_t offset, int whence) |
1da177e4c
|
339 |
{ |
4ebb16ca9
|
340 |
struct inode *bd_inode = bdev_file_inode(file); |
1da177e4c
|
341 |
loff_t retval; |
5955102c9
|
342 |
inode_lock(bd_inode); |
5d48f3a2d
|
343 |
retval = fixed_size_llseek(file, offset, whence, i_size_read(bd_inode)); |
5955102c9
|
344 |
inode_unlock(bd_inode); |
1da177e4c
|
345 346 347 |
return retval; } |
02c24a821
|
348 |
int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync) |
1da177e4c
|
349 |
{ |
4ebb16ca9
|
350 |
struct inode *bd_inode = bdev_file_inode(filp); |
b8af67e26
|
351 |
struct block_device *bdev = I_BDEV(bd_inode); |
ab0a9735e
|
352 |
int error; |
da5aa861b
|
353 354 355 356 |
error = filemap_write_and_wait_range(filp->f_mapping, start, end); if (error) return error; |
ab0a9735e
|
357 |
|
b8af67e26
|
358 359 360 361 362 |
/* * There is no need to serialise calls to blkdev_issue_flush with * i_mutex and doing so causes performance issues with concurrent * O_SYNC writers to a block device. */ |
dd3932edd
|
363 |
error = blkdev_issue_flush(bdev, GFP_KERNEL, NULL); |
ab0a9735e
|
364 365 |
if (error == -EOPNOTSUPP) error = 0; |
b8af67e26
|
366 |
|
ab0a9735e
|
367 |
return error; |
1da177e4c
|
368 |
} |
b1dd3b284
|
369 |
EXPORT_SYMBOL(blkdev_fsync); |
1da177e4c
|
370 |
|
47a191fd3
|
371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 |
/** * bdev_read_page() - Start reading a page from a block device * @bdev: The device to read the page from * @sector: The offset on the device to read the page to (need not be aligned) * @page: The page to read * * On entry, the page should be locked. It will be unlocked when the page * has been read. If the block driver implements rw_page synchronously, * that will be true on exit from this function, but it need not be. * * Errors returned by this function are usually "soft", eg out of memory, or * queue full; callers should try a different route to read this page rather * than propagate an error back up the stack. * * Return: negative errno if an error occurs, 0 if submission was successful. */ int bdev_read_page(struct block_device *bdev, sector_t sector, struct page *page) { const struct block_device_operations *ops = bdev->bd_disk->fops; |
2e6edc953
|
391 |
int result = -EOPNOTSUPP; |
f68eb1e71
|
392 |
if (!ops->rw_page || bdev_get_integrity(bdev)) |
2e6edc953
|
393 |
return result; |
6f3b0e8bc
|
394 |
result = blk_queue_enter(bdev->bd_queue, false); |
2e6edc953
|
395 396 |
if (result) return result; |
c11f0c0b5
|
397 |
result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, false); |
2e6edc953
|
398 399 |
blk_queue_exit(bdev->bd_queue); return result; |
47a191fd3
|
400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 |
} EXPORT_SYMBOL_GPL(bdev_read_page); /** * bdev_write_page() - Start writing a page to a block device * @bdev: The device to write the page to * @sector: The offset on the device to write the page to (need not be aligned) * @page: The page to write * @wbc: The writeback_control for the write * * On entry, the page should be locked and not currently under writeback. * On exit, if the write started successfully, the page will be unlocked and * under writeback. If the write failed already (eg the driver failed to * queue the page to the device), the page will still be locked. If the * caller is a ->writepage implementation, it will need to unlock the page. * * Errors returned by this function are usually "soft", eg out of memory, or * queue full; callers should try a different route to write this page rather * than propagate an error back up the stack. * * Return: negative errno if an error occurs, 0 if submission was successful. */ int bdev_write_page(struct block_device *bdev, sector_t sector, struct page *page, struct writeback_control *wbc) { int result; |
47a191fd3
|
426 |
const struct block_device_operations *ops = bdev->bd_disk->fops; |
2e6edc953
|
427 |
|
f68eb1e71
|
428 |
if (!ops->rw_page || bdev_get_integrity(bdev)) |
47a191fd3
|
429 |
return -EOPNOTSUPP; |
6f3b0e8bc
|
430 |
result = blk_queue_enter(bdev->bd_queue, false); |
2e6edc953
|
431 432 |
if (result) return result; |
47a191fd3
|
433 |
set_page_writeback(page); |
c11f0c0b5
|
434 |
result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, true); |
47a191fd3
|
435 436 437 438 |
if (result) end_page_writeback(page); else unlock_page(page); |
2e6edc953
|
439 |
blk_queue_exit(bdev->bd_queue); |
47a191fd3
|
440 441 442 |
return result; } EXPORT_SYMBOL_GPL(bdev_write_page); |
dd22f551a
|
443 444 445 |
/** * bdev_direct_access() - Get the address for directly-accessibly memory * @bdev: The device containing the memory |
b2e0d1625
|
446 |
* @dax: control and output parameters for ->direct_access |
dd22f551a
|
447 448 449 450 451 452 453 454 455 456 |
* * If a block device is made up of directly addressable memory, this function * will tell the caller the PFN and the address of the memory. The address * may be directly dereferenced within the kernel without the need to call * ioremap(), kmap() or similar. The PFN is suitable for inserting into * page tables. * * Return: negative errno if an error occurs, otherwise the number of bytes * accessible at this address. */ |
b2e0d1625
|
457 |
long bdev_direct_access(struct block_device *bdev, struct blk_dax_ctl *dax) |
dd22f551a
|
458 |
{ |
b2e0d1625
|
459 460 |
sector_t sector = dax->sector; long avail, size = dax->size; |
dd22f551a
|
461 |
const struct block_device_operations *ops = bdev->bd_disk->fops; |
43c3dd08d
|
462 463 464 465 466 |
/* * The device driver is allowed to sleep, in order to make the * memory directly accessible. */ might_sleep(); |
dd22f551a
|
467 468 |
if (size < 0) return size; |
163d4baae
|
469 |
if (!blk_queue_dax(bdev_get_queue(bdev)) || !ops->direct_access) |
dd22f551a
|
470 471 472 473 474 475 476 |
return -EOPNOTSUPP; if ((sector + DIV_ROUND_UP(size, 512)) > part_nr_sects_read(bdev->bd_part)) return -ERANGE; sector += get_start_sect(bdev); if (sector % (PAGE_SIZE / 512)) return -EINVAL; |
0a70bd430
|
477 |
avail = ops->direct_access(bdev, sector, &dax->addr, &dax->pfn, size); |
dd22f551a
|
478 479 |
if (!avail) return -ERANGE; |
fe683adab
|
480 481 |
if (avail > 0 && avail & ~PAGE_MASK) return -ENXIO; |
dd22f551a
|
482 483 484 |
return min(avail, size); } EXPORT_SYMBOL_GPL(bdev_direct_access); |
2d96afc8f
|
485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 |
/** * bdev_dax_supported() - Check if the device supports dax for filesystem * @sb: The superblock of the device * @blocksize: The block size of the device * * This is a library function for filesystems to check if the block device * can be mounted with dax option. * * Return: negative errno if unsupported, 0 if supported. */ int bdev_dax_supported(struct super_block *sb, int blocksize) { struct blk_dax_ctl dax = { .sector = 0, .size = PAGE_SIZE, }; int err; if (blocksize != PAGE_SIZE) { vfs_msg(sb, KERN_ERR, "error: unsupported blocksize for dax"); return -EINVAL; } err = bdev_direct_access(sb->s_bdev, &dax); if (err < 0) { switch (err) { case -EOPNOTSUPP: vfs_msg(sb, KERN_ERR, "error: device does not support dax"); break; case -EINVAL: vfs_msg(sb, KERN_ERR, "error: unaligned partition for dax"); break; default: vfs_msg(sb, KERN_ERR, "error: dax access failed (%d)", err); } return err; } return 0; } EXPORT_SYMBOL_GPL(bdev_dax_supported); |
a8078b1fc
|
529 530 531 532 533 534 |
/** * bdev_dax_capable() - Return if the raw device is capable for dax * @bdev: The device for raw block device access */ bool bdev_dax_capable(struct block_device *bdev) { |
a8078b1fc
|
535 536 537 538 539 540 541 542 543 544 545 546 547 548 |
struct blk_dax_ctl dax = { .size = PAGE_SIZE, }; if (!IS_ENABLED(CONFIG_FS_DAX)) return false; dax.sector = 0; if (bdev_direct_access(bdev, &dax) < 0) return false; dax.sector = bdev->bd_part->nr_sects - (PAGE_SIZE / 512); if (bdev_direct_access(bdev, &dax) < 0) return false; |
a8078b1fc
|
549 550 |
return true; } |
1da177e4c
|
551 552 553 554 555 |
/* * pseudo-fs */ static __cacheline_aligned_in_smp DEFINE_SPINLOCK(bdev_lock); |
e18b890bb
|
556 |
static struct kmem_cache * bdev_cachep __read_mostly; |
1da177e4c
|
557 558 559 |
static struct inode *bdev_alloc_inode(struct super_block *sb) { |
e94b17660
|
560 |
struct bdev_inode *ei = kmem_cache_alloc(bdev_cachep, GFP_KERNEL); |
1da177e4c
|
561 562 563 564 |
if (!ei) return NULL; return &ei->vfs_inode; } |
fa0d7e3de
|
565 |
static void bdev_i_callback(struct rcu_head *head) |
1da177e4c
|
566 |
{ |
fa0d7e3de
|
567 |
struct inode *inode = container_of(head, struct inode, i_rcu); |
1da177e4c
|
568 |
struct bdev_inode *bdi = BDEV_I(inode); |
1da177e4c
|
569 570 |
kmem_cache_free(bdev_cachep, bdi); } |
fa0d7e3de
|
571 572 573 574 |
static void bdev_destroy_inode(struct inode *inode) { call_rcu(&inode->i_rcu, bdev_i_callback); } |
51cc50685
|
575 |
static void init_once(void *foo) |
1da177e4c
|
576 577 578 |
{ struct bdev_inode *ei = (struct bdev_inode *) foo; struct block_device *bdev = &ei->bdev; |
a35afb830
|
579 580 |
memset(bdev, 0, sizeof(*bdev)); mutex_init(&bdev->bd_mutex); |
a35afb830
|
581 |
INIT_LIST_HEAD(&bdev->bd_list); |
49731baa4
|
582 583 584 |
#ifdef CONFIG_SYSFS INIT_LIST_HEAD(&bdev->bd_holder_disks); #endif |
a35afb830
|
585 |
inode_init_once(&ei->vfs_inode); |
fcccf5025
|
586 587 |
/* Initialize mutex for freeze. */ mutex_init(&bdev->bd_fsfreeze_mutex); |
1da177e4c
|
588 |
} |
b57922d97
|
589 |
static void bdev_evict_inode(struct inode *inode) |
1da177e4c
|
590 591 |
{ struct block_device *bdev = &BDEV_I(inode)->bdev; |
91b0abe36
|
592 |
truncate_inode_pages_final(&inode->i_data); |
b57922d97
|
593 |
invalidate_inode_buffers(inode); /* is it needed here? */ |
dbd5768f8
|
594 |
clear_inode(inode); |
1da177e4c
|
595 |
spin_lock(&bdev_lock); |
1da177e4c
|
596 597 598 |
list_del_init(&bdev->bd_list); spin_unlock(&bdev_lock); } |
ee9b6d61a
|
599 |
static const struct super_operations bdev_sops = { |
1da177e4c
|
600 601 602 603 |
.statfs = simple_statfs, .alloc_inode = bdev_alloc_inode, .destroy_inode = bdev_destroy_inode, .drop_inode = generic_delete_inode, |
b57922d97
|
604 |
.evict_inode = bdev_evict_inode, |
1da177e4c
|
605 |
}; |
51139adac
|
606 607 |
static struct dentry *bd_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) |
1da177e4c
|
608 |
{ |
3684aa709
|
609 610 |
struct dentry *dent; dent = mount_pseudo(fs_type, "bdev:", &bdev_sops, NULL, BDEVFS_MAGIC); |
e9e5e3fae
|
611 |
if (!IS_ERR(dent)) |
3684aa709
|
612 613 |
dent->d_sb->s_iflags |= SB_I_CGROUPWB; return dent; |
1da177e4c
|
614 615 616 617 |
} static struct file_system_type bd_type = { .name = "bdev", |
51139adac
|
618 |
.mount = bd_mount, |
1da177e4c
|
619 620 |
.kill_sb = kill_anon_super, }; |
a212b105b
|
621 622 |
struct super_block *blockdev_superblock __read_mostly; EXPORT_SYMBOL_GPL(blockdev_superblock); |
1da177e4c
|
623 624 625 626 |
void __init bdev_cache_init(void) { int err; |
ace8577ae
|
627 |
static struct vfsmount *bd_mnt; |
c2acf7b90
|
628 |
|
1da177e4c
|
629 |
bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode), |
fffb60f93
|
630 |
0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| |
5d097056c
|
631 |
SLAB_MEM_SPREAD|SLAB_ACCOUNT|SLAB_PANIC), |
20c2df83d
|
632 |
init_once); |
1da177e4c
|
633 634 635 636 |
err = register_filesystem(&bd_type); if (err) panic("Cannot register bdev pseudo-fs"); bd_mnt = kern_mount(&bd_type); |
1da177e4c
|
637 638 |
if (IS_ERR(bd_mnt)) panic("Cannot create bdev pseudo-fs"); |
ace8577ae
|
639 |
blockdev_superblock = bd_mnt->mnt_sb; /* For writeback */ |
1da177e4c
|
640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 |
} /* * Most likely _very_ bad one - but then it's hardly critical for small * /dev and can be fixed when somebody will need really large one. * Keep in mind that it will be fed through icache hash function too. */ static inline unsigned long hash(dev_t dev) { return MAJOR(dev)+MINOR(dev); } static int bdev_test(struct inode *inode, void *data) { return BDEV_I(inode)->bdev.bd_dev == *(dev_t *)data; } static int bdev_set(struct inode *inode, void *data) { BDEV_I(inode)->bdev.bd_dev = *(dev_t *)data; return 0; } static LIST_HEAD(all_bdevs); struct block_device *bdget(dev_t dev) { struct block_device *bdev; struct inode *inode; |
c2acf7b90
|
669 |
inode = iget5_locked(blockdev_superblock, hash(dev), |
1da177e4c
|
670 671 672 673 674 675 676 677 678 |
bdev_test, bdev_set, &dev); if (!inode) return NULL; bdev = &BDEV_I(inode)->bdev; if (inode->i_state & I_NEW) { bdev->bd_contains = NULL; |
782b94cdf
|
679 |
bdev->bd_super = NULL; |
1da177e4c
|
680 681 682 683 684 685 686 687 688 |
bdev->bd_inode = inode; bdev->bd_block_size = (1 << inode->i_blkbits); bdev->bd_part_count = 0; bdev->bd_invalidated = 0; inode->i_mode = S_IFBLK; inode->i_rdev = dev; inode->i_bdev = bdev; inode->i_data.a_ops = &def_blk_aops; mapping_set_gfp_mask(&inode->i_data, GFP_USER); |
1da177e4c
|
689 690 691 692 693 694 695 696 697 |
spin_lock(&bdev_lock); list_add(&bdev->bd_list, &all_bdevs); spin_unlock(&bdev_lock); unlock_new_inode(inode); } return bdev; } EXPORT_SYMBOL(bdget); |
dddac6a7b
|
698 699 700 701 702 703 |
/** * bdgrab -- Grab a reference to an already referenced block device * @bdev: Block device to grab a reference to. */ struct block_device *bdgrab(struct block_device *bdev) { |
7de9c6ee3
|
704 |
ihold(bdev->bd_inode); |
dddac6a7b
|
705 706 |
return bdev; } |
c1681bf8a
|
707 |
EXPORT_SYMBOL(bdgrab); |
dddac6a7b
|
708 |
|
1da177e4c
|
709 710 |
long nr_blockdev_pages(void) { |
203a2935c
|
711 |
struct block_device *bdev; |
1da177e4c
|
712 713 |
long ret = 0; spin_lock(&bdev_lock); |
203a2935c
|
714 |
list_for_each_entry(bdev, &all_bdevs, bd_list) { |
1da177e4c
|
715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 |
ret += bdev->bd_inode->i_mapping->nrpages; } spin_unlock(&bdev_lock); return ret; } void bdput(struct block_device *bdev) { iput(bdev->bd_inode); } EXPORT_SYMBOL(bdput); static struct block_device *bd_acquire(struct inode *inode) { struct block_device *bdev; |
09d967c6f
|
731 |
|
1da177e4c
|
732 733 |
spin_lock(&bdev_lock); bdev = inode->i_bdev; |
09d967c6f
|
734 |
if (bdev) { |
ed8a9d2c8
|
735 |
bdgrab(bdev); |
1da177e4c
|
736 737 738 739 |
spin_unlock(&bdev_lock); return bdev; } spin_unlock(&bdev_lock); |
09d967c6f
|
740 |
|
1da177e4c
|
741 742 743 |
bdev = bdget(inode->i_rdev); if (bdev) { spin_lock(&bdev_lock); |
09d967c6f
|
744 745 |
if (!inode->i_bdev) { /* |
7de9c6ee3
|
746 |
* We take an additional reference to bd_inode, |
09d967c6f
|
747 748 749 750 |
* and it's released in clear_inode() of inode. * So, we can access it via ->i_mapping always * without igrab(). */ |
ed8a9d2c8
|
751 |
bdgrab(bdev); |
09d967c6f
|
752 753 |
inode->i_bdev = bdev; inode->i_mapping = bdev->bd_inode->i_mapping; |
09d967c6f
|
754 |
} |
1da177e4c
|
755 756 757 758 759 760 761 762 763 |
spin_unlock(&bdev_lock); } return bdev; } /* Call when you free inode */ void bd_forget(struct inode *inode) { |
09d967c6f
|
764 |
struct block_device *bdev = NULL; |
1da177e4c
|
765 |
spin_lock(&bdev_lock); |
b4ea2eaa1
|
766 767 |
if (!sb_is_blkdev_sb(inode->i_sb)) bdev = inode->i_bdev; |
a4a4f9439
|
768 769 |
inode->i_bdev = NULL; inode->i_mapping = &inode->i_data; |
1da177e4c
|
770 |
spin_unlock(&bdev_lock); |
09d967c6f
|
771 772 |
if (bdev) |
ed8a9d2c8
|
773 |
bdput(bdev); |
1da177e4c
|
774 |
} |
1a3cbbc5a
|
775 776 777 778 779 780 |
/** * bd_may_claim - test whether a block device can be claimed * @bdev: block device of interest * @whole: whole block device containing @bdev, may equal @bdev * @holder: holder trying to claim @bdev * |
25985edce
|
781 |
* Test whether @bdev can be claimed by @holder. |
1a3cbbc5a
|
782 783 784 785 786 787 788 789 790 |
* * CONTEXT: * spin_lock(&bdev_lock). * * RETURNS: * %true if @bdev can be claimed, %false otherwise. */ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole, void *holder) |
1da177e4c
|
791 |
{ |
1da177e4c
|
792 |
if (bdev->bd_holder == holder) |
1a3cbbc5a
|
793 |
return true; /* already a holder */ |
1da177e4c
|
794 |
else if (bdev->bd_holder != NULL) |
1a3cbbc5a
|
795 |
return false; /* held by someone else */ |
1da177e4c
|
796 |
else if (bdev->bd_contains == bdev) |
1a3cbbc5a
|
797 |
return true; /* is a whole device which isn't held */ |
1da177e4c
|
798 |
|
e525fd89d
|
799 |
else if (whole->bd_holder == bd_may_claim) |
1a3cbbc5a
|
800 801 802 |
return true; /* is a partition of a device that is being partitioned */ else if (whole->bd_holder != NULL) return false; /* is a partition of a held device */ |
1da177e4c
|
803 |
else |
1a3cbbc5a
|
804 805 806 807 |
return true; /* is a partition of an un-held device */ } /** |
6b4517a79
|
808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 |
* bd_prepare_to_claim - prepare to claim a block device * @bdev: block device of interest * @whole: the whole device containing @bdev, may equal @bdev * @holder: holder trying to claim @bdev * * Prepare to claim @bdev. This function fails if @bdev is already * claimed by another holder and waits if another claiming is in * progress. This function doesn't actually claim. On successful * return, the caller has ownership of bd_claiming and bd_holder[s]. * * CONTEXT: * spin_lock(&bdev_lock). Might release bdev_lock, sleep and regrab * it multiple times. * * RETURNS: * 0 if @bdev can be claimed, -EBUSY otherwise. */ static int bd_prepare_to_claim(struct block_device *bdev, struct block_device *whole, void *holder) { retry: /* if someone else claimed, fail */ if (!bd_may_claim(bdev, whole, holder)) return -EBUSY; |
e75aa8589
|
832 833 |
/* if claiming is already in progress, wait for it to finish */ if (whole->bd_claiming) { |
6b4517a79
|
834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 |
wait_queue_head_t *wq = bit_waitqueue(&whole->bd_claiming, 0); DEFINE_WAIT(wait); prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE); spin_unlock(&bdev_lock); schedule(); finish_wait(wq, &wait); spin_lock(&bdev_lock); goto retry; } /* yay, all mine */ return 0; } /** * bd_start_claiming - start claiming a block device * @bdev: block device of interest * @holder: holder trying to claim @bdev * * @bdev is about to be opened exclusively. Check @bdev can be opened * exclusively and mark that an exclusive open is in progress. Each * successful call to this function must be matched with a call to |
b0018361c
|
857 858 859 860 861 862 863 |
* either bd_finish_claiming() or bd_abort_claiming() (which do not * fail). * * This function is used to gain exclusive access to the block device * without actually causing other exclusive open attempts to fail. It * should be used when the open sequence itself requires exclusive * access but may subsequently fail. |
6b4517a79
|
864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 |
* * CONTEXT: * Might sleep. * * RETURNS: * Pointer to the block device containing @bdev on success, ERR_PTR() * value on failure. */ static struct block_device *bd_start_claiming(struct block_device *bdev, void *holder) { struct gendisk *disk; struct block_device *whole; int partno, err; might_sleep(); /* * @bdev might not have been initialized properly yet, look up * and grab the outer block device the hard way. */ disk = get_gendisk(bdev->bd_dev, &partno); if (!disk) return ERR_PTR(-ENXIO); |
d4c208b86
|
888 889 890 891 892 893 894 895 896 897 898 899 |
/* * Normally, @bdev should equal what's returned from bdget_disk() * if partno is 0; however, some drivers (floppy) use multiple * bdev's for the same physical device and @bdev may be one of the * aliases. Keep @bdev if partno is 0. This means claimer * tracking is broken for those devices but it has always been that * way. */ if (partno) whole = bdget_disk(disk, 0); else whole = bdgrab(bdev); |
cf3425707
|
900 |
module_put(disk->fops->owner); |
6b4517a79
|
901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 |
put_disk(disk); if (!whole) return ERR_PTR(-ENOMEM); /* prepare to claim, if successful, mark claiming in progress */ spin_lock(&bdev_lock); err = bd_prepare_to_claim(bdev, whole, holder); if (err == 0) { whole->bd_claiming = holder; spin_unlock(&bdev_lock); return whole; } else { spin_unlock(&bdev_lock); bdput(whole); return ERR_PTR(err); } } |
641dc636b
|
919 |
#ifdef CONFIG_SYSFS |
49731baa4
|
920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 |
struct bd_holder_disk { struct list_head list; struct gendisk *disk; int refcnt; }; static struct bd_holder_disk *bd_find_holder_disk(struct block_device *bdev, struct gendisk *disk) { struct bd_holder_disk *holder; list_for_each_entry(holder, &bdev->bd_holder_disks, list) if (holder->disk == disk) return holder; return NULL; } |
4d7dd8fd9
|
936 |
static int add_symlink(struct kobject *from, struct kobject *to) |
641dc636b
|
937 |
{ |
4d7dd8fd9
|
938 |
return sysfs_create_link(from, to, kobject_name(to)); |
641dc636b
|
939 940 941 942 |
} static void del_symlink(struct kobject *from, struct kobject *to) { |
641dc636b
|
943 944 |
sysfs_remove_link(from, kobject_name(to)); } |
641dc636b
|
945 |
/** |
e09b457bd
|
946 947 948 |
* bd_link_disk_holder - create symlinks between holding disk and slave bdev * @bdev: the claimed slave bdev * @disk: the holding disk |
df6c0cd9a
|
949 |
* |
49731baa4
|
950 951 |
* DON'T USE THIS UNLESS YOU'RE ALREADY USING IT. * |
e09b457bd
|
952 |
* This functions creates the following sysfs symlinks. |
641dc636b
|
953 |
* |
e09b457bd
|
954 955 |
* - from "slaves" directory of the holder @disk to the claimed @bdev * - from "holders" directory of the @bdev to the holder @disk |
641dc636b
|
956 |
* |
e09b457bd
|
957 958 |
* For example, if /dev/dm-0 maps to /dev/sda and disk for dm-0 is * passed to bd_link_disk_holder(), then: |
641dc636b
|
959 |
* |
e09b457bd
|
960 961 |
* /sys/block/dm-0/slaves/sda --> /sys/block/sda * /sys/block/sda/holders/dm-0 --> /sys/block/dm-0 |
641dc636b
|
962 |
* |
e09b457bd
|
963 964 965 |
* The caller must have claimed @bdev before calling this function and * ensure that both @bdev and @disk are valid during the creation and * lifetime of these symlinks. |
641dc636b
|
966 |
* |
e09b457bd
|
967 968 |
* CONTEXT: * Might sleep. |
641dc636b
|
969 |
* |
e09b457bd
|
970 971 |
* RETURNS: * 0 on success, -errno on failure. |
641dc636b
|
972 |
*/ |
e09b457bd
|
973 |
int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) |
641dc636b
|
974 |
{ |
49731baa4
|
975 |
struct bd_holder_disk *holder; |
e09b457bd
|
976 |
int ret = 0; |
641dc636b
|
977 |
|
2e7b651df
|
978 |
mutex_lock(&bdev->bd_mutex); |
df6c0cd9a
|
979 |
|
49731baa4
|
980 |
WARN_ON_ONCE(!bdev->bd_holder); |
4e91672c7
|
981 |
|
e09b457bd
|
982 983 984 |
/* FIXME: remove the following once add_disk() handles errors */ if (WARN_ON(!disk->slave_dir || !bdev->bd_part->holder_dir)) goto out_unlock; |
4e91672c7
|
985 |
|
49731baa4
|
986 987 988 |
holder = bd_find_holder_disk(bdev, disk); if (holder) { holder->refcnt++; |
e09b457bd
|
989 |
goto out_unlock; |
49731baa4
|
990 |
} |
641dc636b
|
991 |
|
49731baa4
|
992 993 994 |
holder = kzalloc(sizeof(*holder), GFP_KERNEL); if (!holder) { ret = -ENOMEM; |
e09b457bd
|
995 996 |
goto out_unlock; } |
641dc636b
|
997 |
|
49731baa4
|
998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 |
INIT_LIST_HEAD(&holder->list); holder->disk = disk; holder->refcnt = 1; ret = add_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj); if (ret) goto out_free; ret = add_symlink(bdev->bd_part->holder_dir, &disk_to_dev(disk)->kobj); if (ret) goto out_del; |
e7407d161
|
1009 1010 1011 1012 1013 |
/* * bdev could be deleted beneath us which would implicitly destroy * the holder directory. Hold on to it. */ kobject_get(bdev->bd_part->holder_dir); |
49731baa4
|
1014 1015 1016 1017 1018 1019 1020 1021 |
list_add(&holder->list, &bdev->bd_holder_disks); goto out_unlock; out_del: del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj); out_free: kfree(holder); |
e09b457bd
|
1022 |
out_unlock: |
b4cf1b72e
|
1023 |
mutex_unlock(&bdev->bd_mutex); |
e09b457bd
|
1024 |
return ret; |
641dc636b
|
1025 |
} |
e09b457bd
|
1026 |
EXPORT_SYMBOL_GPL(bd_link_disk_holder); |
641dc636b
|
1027 |
|
49731baa4
|
1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 |
/** * bd_unlink_disk_holder - destroy symlinks created by bd_link_disk_holder() * @bdev: the calimed slave bdev * @disk: the holding disk * * DON'T USE THIS UNLESS YOU'RE ALREADY USING IT. * * CONTEXT: * Might sleep. */ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) |
641dc636b
|
1039 |
{ |
49731baa4
|
1040 |
struct bd_holder_disk *holder; |
641dc636b
|
1041 |
|
49731baa4
|
1042 |
mutex_lock(&bdev->bd_mutex); |
641dc636b
|
1043 |
|
49731baa4
|
1044 1045 1046 1047 1048 1049 |
holder = bd_find_holder_disk(bdev, disk); if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) { del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj); del_symlink(bdev->bd_part->holder_dir, &disk_to_dev(disk)->kobj); |
e7407d161
|
1050 |
kobject_put(bdev->bd_part->holder_dir); |
49731baa4
|
1051 1052 1053 1054 1055 |
list_del_init(&holder->list); kfree(holder); } mutex_unlock(&bdev->bd_mutex); |
1da177e4c
|
1056 |
} |
49731baa4
|
1057 |
EXPORT_SYMBOL_GPL(bd_unlink_disk_holder); |
641dc636b
|
1058 |
#endif |
1da177e4c
|
1059 |
|
0c002c2f7
|
1060 |
/** |
56ade44b4
|
1061 1062 1063 |
* flush_disk - invalidates all buffer-cache entries on a disk * * @bdev: struct block device to be flushed |
e6eb5ce1b
|
1064 |
* @kill_dirty: flag to guide handling of dirty inodes |
56ade44b4
|
1065 1066 1067 1068 1069 |
* * Invalidates all buffer-cache entries on a disk. It should be called * when a disk has been changed -- either by a media change or online * resize. */ |
93b270f76
|
1070 |
static void flush_disk(struct block_device *bdev, bool kill_dirty) |
56ade44b4
|
1071 |
{ |
93b270f76
|
1072 |
if (__invalidate_device(bdev, kill_dirty)) { |
56ade44b4
|
1073 |
printk(KERN_WARNING "VFS: busy inodes on changed media or " |
424081f3c
|
1074 1075 1076 |
"resized disk %s ", bdev->bd_disk ? bdev->bd_disk->disk_name : ""); |
56ade44b4
|
1077 1078 1079 1080 |
} if (!bdev->bd_disk) return; |
d27769ec3
|
1081 |
if (disk_part_scan_enabled(bdev->bd_disk)) |
56ade44b4
|
1082 1083 1084 1085 |
bdev->bd_invalidated = 1; } /** |
57d1b5366
|
1086 |
* check_disk_size_change - checks for disk size change and adjusts bdev size. |
c3279d145
|
1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 |
* @disk: struct gendisk to check * @bdev: struct bdev to adjust. * * This routine checks to see if the bdev size does not match the disk size * and adjusts it if it differs. */ void check_disk_size_change(struct gendisk *disk, struct block_device *bdev) { loff_t disk_size, bdev_size; disk_size = (loff_t)get_capacity(disk) << 9; bdev_size = i_size_read(bdev->bd_inode); if (disk_size != bdev_size) { |
c3279d145
|
1100 1101 1102 |
printk(KERN_INFO "%s: detected capacity change from %lld to %lld ", |
424081f3c
|
1103 |
disk->disk_name, bdev_size, disk_size); |
c3279d145
|
1104 |
i_size_write(bdev->bd_inode, disk_size); |
93b270f76
|
1105 |
flush_disk(bdev, false); |
c3279d145
|
1106 1107 1108 1109 1110 |
} } EXPORT_SYMBOL(check_disk_size_change); /** |
57d1b5366
|
1111 |
* revalidate_disk - wrapper for lower-level driver's revalidate_disk call-back |
0c002c2f7
|
1112 1113 1114 1115 1116 1117 1118 1119 |
* @disk: struct gendisk to be revalidated * * This routine is a wrapper for lower-level driver's revalidate_disk * call-backs. It is used to do common pre and post operations needed * for all revalidate_disk operations. */ int revalidate_disk(struct gendisk *disk) { |
c3279d145
|
1120 |
struct block_device *bdev; |
0c002c2f7
|
1121 1122 1123 1124 |
int ret = 0; if (disk->fops->revalidate_disk) ret = disk->fops->revalidate_disk(disk); |
25520d55c
|
1125 |
blk_integrity_revalidate(disk); |
c3279d145
|
1126 1127 1128 1129 1130 1131 |
bdev = bdget_disk(disk, 0); if (!bdev) return ret; mutex_lock(&bdev->bd_mutex); check_disk_size_change(disk, bdev); |
7630b661d
|
1132 |
bdev->bd_invalidated = 0; |
c3279d145
|
1133 1134 |
mutex_unlock(&bdev->bd_mutex); bdput(bdev); |
0c002c2f7
|
1135 1136 1137 |
return ret; } EXPORT_SYMBOL(revalidate_disk); |
1da177e4c
|
1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 |
/* * This routine checks whether a removable media has been changed, * and invalidates all buffer-cache-entries in that case. This * is a relatively slow routine, so we have to try to minimize using * it. Thus it is called only upon a 'mount' or 'open'. This * is the best way of combining speed and utility, I think. * People changing diskettes in the middle of an operation deserve * to lose :-) */ int check_disk_change(struct block_device *bdev) { struct gendisk *disk = bdev->bd_disk; |
83d5cde47
|
1150 |
const struct block_device_operations *bdops = disk->fops; |
77ea887e4
|
1151 |
unsigned int events; |
1da177e4c
|
1152 |
|
77ea887e4
|
1153 1154 1155 |
events = disk_clear_events(disk, DISK_EVENT_MEDIA_CHANGE | DISK_EVENT_EJECT_REQUEST); if (!(events & DISK_EVENT_MEDIA_CHANGE)) |
1da177e4c
|
1156 |
return 0; |
93b270f76
|
1157 |
flush_disk(bdev, true); |
1da177e4c
|
1158 1159 |
if (bdops->revalidate_disk) bdops->revalidate_disk(bdev->bd_disk); |
1da177e4c
|
1160 1161 1162 1163 1164 1165 1166 |
return 1; } EXPORT_SYMBOL(check_disk_change); void bd_set_size(struct block_device *bdev, loff_t size) { |
e1defc4ff
|
1167 |
unsigned bsize = bdev_logical_block_size(bdev); |
1da177e4c
|
1168 |
|
5955102c9
|
1169 |
inode_lock(bdev->bd_inode); |
d646a02a9
|
1170 |
i_size_write(bdev->bd_inode, size); |
5955102c9
|
1171 |
inode_unlock(bdev->bd_inode); |
09cbfeaf1
|
1172 |
while (bsize < PAGE_SIZE) { |
1da177e4c
|
1173 1174 1175 1176 1177 1178 1179 1180 |
if (size & bsize) break; bsize <<= 1; } bdev->bd_block_size = bsize; bdev->bd_inode->i_blkbits = blksize_bits(bsize); } EXPORT_SYMBOL(bd_set_size); |
4385bab12
|
1181 |
static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part); |
37be41241
|
1182 |
|
6d740cd5b
|
1183 1184 1185 1186 1187 1188 |
/* * bd_mutex locking: * * mutex_lock(part->bd_mutex) * mutex_lock_nested(whole->bd_mutex, 1) */ |
572c48921
|
1189 |
static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) |
1da177e4c
|
1190 |
{ |
1da177e4c
|
1191 |
struct gendisk *disk; |
523e1d399
|
1192 |
struct module *owner; |
7db9cfd38
|
1193 |
int ret; |
cf771cb5a
|
1194 |
int partno; |
fe6e9c1f2
|
1195 |
int perm = 0; |
572c48921
|
1196 |
if (mode & FMODE_READ) |
fe6e9c1f2
|
1197 |
perm |= MAY_READ; |
572c48921
|
1198 |
if (mode & FMODE_WRITE) |
fe6e9c1f2
|
1199 1200 1201 1202 |
perm |= MAY_WRITE; /* * hooks: /n/, see "layering violations". */ |
b7300b78d
|
1203 1204 1205 1206 1207 1208 |
if (!for_part) { ret = devcgroup_inode_permission(bdev->bd_inode, perm); if (ret != 0) { bdput(bdev); return ret; } |
826660203
|
1209 |
} |
7db9cfd38
|
1210 |
|
d3374825c
|
1211 |
restart: |
0762b8bde
|
1212 |
|
89f97496e
|
1213 |
ret = -ENXIO; |
cf771cb5a
|
1214 |
disk = get_gendisk(bdev->bd_dev, &partno); |
0762b8bde
|
1215 |
if (!disk) |
6e9624b8c
|
1216 |
goto out; |
523e1d399
|
1217 |
owner = disk->fops->owner; |
1da177e4c
|
1218 |
|
69e02c59a
|
1219 |
disk_block_events(disk); |
6796bf54a
|
1220 |
mutex_lock_nested(&bdev->bd_mutex, for_part); |
1da177e4c
|
1221 1222 |
if (!bdev->bd_openers) { bdev->bd_disk = disk; |
87192a2a4
|
1223 |
bdev->bd_queue = disk->queue; |
1da177e4c
|
1224 |
bdev->bd_contains = bdev; |
03cdadb04
|
1225 |
|
cf771cb5a
|
1226 |
if (!partno) { |
89f97496e
|
1227 1228 1229 1230 |
ret = -ENXIO; bdev->bd_part = disk_get_part(disk, partno); if (!bdev->bd_part) goto out_clear; |
1196f8b81
|
1231 |
ret = 0; |
1da177e4c
|
1232 |
if (disk->fops->open) { |
572c48921
|
1233 |
ret = disk->fops->open(bdev, mode); |
d3374825c
|
1234 1235 1236 1237 1238 1239 1240 |
if (ret == -ERESTARTSYS) { /* Lost a race with 'disk' being * deleted, try again. * See md.c */ disk_put_part(bdev->bd_part); bdev->bd_part = NULL; |
d3374825c
|
1241 |
bdev->bd_disk = NULL; |
87192a2a4
|
1242 |
bdev->bd_queue = NULL; |
d3374825c
|
1243 |
mutex_unlock(&bdev->bd_mutex); |
69e02c59a
|
1244 |
disk_unblock_events(disk); |
69e02c59a
|
1245 |
put_disk(disk); |
523e1d399
|
1246 |
module_put(owner); |
d3374825c
|
1247 1248 |
goto restart; } |
1da177e4c
|
1249 |
} |
7e69723fe
|
1250 |
|
223757016
|
1251 |
if (!ret) |
7e69723fe
|
1252 |
bd_set_size(bdev,(loff_t)get_capacity(disk)<<9); |
7e69723fe
|
1253 |
|
1196f8b81
|
1254 1255 1256 1257 1258 1259 |
/* * If the device is invalidated, rescan partition * if open succeeded or failed with -ENOMEDIUM. * The latter is necessary to prevent ghost * partitions on a removed medium. */ |
fe316bf2d
|
1260 1261 1262 1263 1264 1265 |
if (bdev->bd_invalidated) { if (!ret) rescan_partitions(disk, bdev); else if (ret == -ENOMEDIUM) invalidate_partitions(disk, bdev); } |
5a023cdba
|
1266 |
|
1196f8b81
|
1267 1268 |
if (ret) goto out_clear; |
1da177e4c
|
1269 |
} else { |
1da177e4c
|
1270 1271 1272 1273 |
struct block_device *whole; whole = bdget_disk(disk, 0); ret = -ENOMEM; if (!whole) |
0762b8bde
|
1274 |
goto out_clear; |
37be41241
|
1275 |
BUG_ON(for_part); |
572c48921
|
1276 |
ret = __blkdev_get(whole, mode, 1); |
1da177e4c
|
1277 |
if (ret) |
0762b8bde
|
1278 |
goto out_clear; |
1da177e4c
|
1279 |
bdev->bd_contains = whole; |
89f97496e
|
1280 |
bdev->bd_part = disk_get_part(disk, partno); |
e71bf0d0e
|
1281 |
if (!(disk->flags & GENHD_FL_UP) || |
89f97496e
|
1282 |
!bdev->bd_part || !bdev->bd_part->nr_sects) { |
1da177e4c
|
1283 |
ret = -ENXIO; |
0762b8bde
|
1284 |
goto out_clear; |
1da177e4c
|
1285 |
} |
89f97496e
|
1286 |
bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9); |
1da177e4c
|
1287 1288 |
} } else { |
1da177e4c
|
1289 |
if (bdev->bd_contains == bdev) { |
1196f8b81
|
1290 1291 |
ret = 0; if (bdev->bd_disk->fops->open) |
572c48921
|
1292 |
ret = bdev->bd_disk->fops->open(bdev, mode); |
1196f8b81
|
1293 |
/* the same as first opener case, read comment there */ |
fe316bf2d
|
1294 1295 1296 1297 1298 1299 |
if (bdev->bd_invalidated) { if (!ret) rescan_partitions(bdev->bd_disk, bdev); else if (ret == -ENOMEDIUM) invalidate_partitions(bdev->bd_disk, bdev); } |
1196f8b81
|
1300 1301 |
if (ret) goto out_unlock_bdev; |
1da177e4c
|
1302 |
} |
69e02c59a
|
1303 |
/* only one opener holds refs to the module and disk */ |
69e02c59a
|
1304 |
put_disk(disk); |
523e1d399
|
1305 |
module_put(owner); |
1da177e4c
|
1306 1307 |
} bdev->bd_openers++; |
37be41241
|
1308 1309 |
if (for_part) bdev->bd_part_count++; |
c039e3134
|
1310 |
mutex_unlock(&bdev->bd_mutex); |
69e02c59a
|
1311 |
disk_unblock_events(disk); |
1da177e4c
|
1312 |
return 0; |
0762b8bde
|
1313 |
out_clear: |
89f97496e
|
1314 |
disk_put_part(bdev->bd_part); |
1da177e4c
|
1315 |
bdev->bd_disk = NULL; |
0762b8bde
|
1316 |
bdev->bd_part = NULL; |
87192a2a4
|
1317 |
bdev->bd_queue = NULL; |
1da177e4c
|
1318 |
if (bdev != bdev->bd_contains) |
572c48921
|
1319 |
__blkdev_put(bdev->bd_contains, mode, 1); |
1da177e4c
|
1320 |
bdev->bd_contains = NULL; |
0762b8bde
|
1321 |
out_unlock_bdev: |
c039e3134
|
1322 |
mutex_unlock(&bdev->bd_mutex); |
69e02c59a
|
1323 |
disk_unblock_events(disk); |
0762b8bde
|
1324 |
put_disk(disk); |
523e1d399
|
1325 |
module_put(owner); |
4345caba3
|
1326 |
out: |
0762b8bde
|
1327 |
bdput(bdev); |
1da177e4c
|
1328 1329 |
return ret; } |
d4d776299
|
1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 |
/** * blkdev_get - open a block device * @bdev: block_device to open * @mode: FMODE_* mask * @holder: exclusive holder identifier * * Open @bdev with @mode. If @mode includes %FMODE_EXCL, @bdev is * open with exclusive access. Specifying %FMODE_EXCL with %NULL * @holder is invalid. Exclusive opens may nest for the same @holder. * * On success, the reference count of @bdev is unchanged. On failure, * @bdev is put. * * CONTEXT: * Might sleep. * * RETURNS: * 0 on success, -errno on failure. */ |
e525fd89d
|
1349 |
int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder) |
1da177e4c
|
1350 |
{ |
e525fd89d
|
1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 |
struct block_device *whole = NULL; int res; WARN_ON_ONCE((mode & FMODE_EXCL) && !holder); if ((mode & FMODE_EXCL) && holder) { whole = bd_start_claiming(bdev, holder); if (IS_ERR(whole)) { bdput(bdev); return PTR_ERR(whole); } } res = __blkdev_get(bdev, mode, 0); if (whole) { |
d4dc210f6
|
1367 |
struct gendisk *disk = whole->bd_disk; |
6a027eff6
|
1368 |
/* finish claiming */ |
77ea887e4
|
1369 |
mutex_lock(&bdev->bd_mutex); |
6a027eff6
|
1370 |
spin_lock(&bdev_lock); |
77ea887e4
|
1371 |
if (!res) { |
6a027eff6
|
1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 |
BUG_ON(!bd_may_claim(bdev, whole, holder)); /* * Note that for a whole device bd_holders * will be incremented twice, and bd_holder * will be set to bd_may_claim before being * set to holder */ whole->bd_holders++; whole->bd_holder = bd_may_claim; bdev->bd_holders++; bdev->bd_holder = holder; } /* tell others that we're done */ BUG_ON(whole->bd_claiming != holder); whole->bd_claiming = NULL; wake_up_bit(&whole->bd_claiming, 0); spin_unlock(&bdev_lock); |
77ea887e4
|
1391 1392 |
/* |
d4dc210f6
|
1393 1394 1395 1396 1397 |
* Block event polling for write claims if requested. Any * write holder makes the write_holder state stick until * all are released. This is good enough and tracking * individual writeable reference is too fragile given the * way @mode is used in blkdev_get/put(). |
77ea887e4
|
1398 |
*/ |
4c49ff3fe
|
1399 1400 |
if (!res && (mode & FMODE_WRITE) && !bdev->bd_write_holder && (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) { |
77ea887e4
|
1401 |
bdev->bd_write_holder = true; |
d4dc210f6
|
1402 |
disk_block_events(disk); |
77ea887e4
|
1403 1404 1405 |
} mutex_unlock(&bdev->bd_mutex); |
6a027eff6
|
1406 |
bdput(whole); |
e525fd89d
|
1407 1408 1409 |
} return res; |
37be41241
|
1410 |
} |
1da177e4c
|
1411 |
EXPORT_SYMBOL(blkdev_get); |
d4d776299
|
1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 |
/** * blkdev_get_by_path - open a block device by name * @path: path to the block device to open * @mode: FMODE_* mask * @holder: exclusive holder identifier * * Open the blockdevice described by the device file at @path. @mode * and @holder are identical to blkdev_get(). * * On success, the returned block_device has reference count of one. * * CONTEXT: * Might sleep. * * RETURNS: * Pointer to block_device on success, ERR_PTR(-errno) on failure. */ struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, void *holder) { struct block_device *bdev; int err; bdev = lookup_bdev(path); if (IS_ERR(bdev)) return bdev; err = blkdev_get(bdev, mode, holder); if (err) return ERR_PTR(err); |
e51900f7d
|
1442 1443 1444 1445 |
if ((mode & FMODE_WRITE) && bdev_read_only(bdev)) { blkdev_put(bdev, mode); return ERR_PTR(-EACCES); } |
d4d776299
|
1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 |
return bdev; } EXPORT_SYMBOL(blkdev_get_by_path); /** * blkdev_get_by_dev - open a block device by device number * @dev: device number of block device to open * @mode: FMODE_* mask * @holder: exclusive holder identifier * * Open the blockdevice described by device number @dev. @mode and * @holder are identical to blkdev_get(). * * Use it ONLY if you really do not have anything better - i.e. when * you are behind a truly sucky interface and all you are given is a * device number. _Never_ to be used for internal purposes. If you * ever need it - reconsider your API. * * On success, the returned block_device has reference count of one. * * CONTEXT: * Might sleep. * * RETURNS: * Pointer to block_device on success, ERR_PTR(-errno) on failure. */ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) { struct block_device *bdev; int err; bdev = bdget(dev); if (!bdev) return ERR_PTR(-ENOMEM); err = blkdev_get(bdev, mode, holder); if (err) return ERR_PTR(err); return bdev; } EXPORT_SYMBOL(blkdev_get_by_dev); |
1da177e4c
|
1488 1489 1490 |
static int blkdev_open(struct inode * inode, struct file * filp) { struct block_device *bdev; |
1da177e4c
|
1491 1492 1493 1494 1495 1496 1497 1498 |
/* * Preserve backwards compatibility and allow large file access * even if userspace doesn't ask for it explicitly. Some mkfs * binary needs it. We might want to drop this workaround * during an unstable branch. */ filp->f_flags |= O_LARGEFILE; |
572c48921
|
1499 1500 1501 1502 1503 1504 |
if (filp->f_flags & O_NDELAY) filp->f_mode |= FMODE_NDELAY; if (filp->f_flags & O_EXCL) filp->f_mode |= FMODE_EXCL; if ((filp->f_flags & O_ACCMODE) == 3) filp->f_mode |= FMODE_WRITE_IOCTL; |
1da177e4c
|
1505 |
bdev = bd_acquire(inode); |
6a2aae06c
|
1506 1507 |
if (bdev == NULL) return -ENOMEM; |
1da177e4c
|
1508 |
|
572c48921
|
1509 |
filp->f_mapping = bdev->bd_inode->i_mapping; |
e525fd89d
|
1510 |
return blkdev_get(bdev, filp->f_mode, filp); |
1da177e4c
|
1511 |
} |
4385bab12
|
1512 |
static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) |
2e7b651df
|
1513 |
{ |
2e7b651df
|
1514 |
struct gendisk *disk = bdev->bd_disk; |
37be41241
|
1515 |
struct block_device *victim = NULL; |
2e7b651df
|
1516 |
|
6796bf54a
|
1517 |
mutex_lock_nested(&bdev->bd_mutex, for_part); |
37be41241
|
1518 1519 |
if (for_part) bdev->bd_part_count--; |
2e7b651df
|
1520 |
if (!--bdev->bd_openers) { |
6a027eff6
|
1521 |
WARN_ON_ONCE(bdev->bd_holders); |
2e7b651df
|
1522 1523 |
sync_blockdev(bdev); kill_bdev(bdev); |
43d1c0eb7
|
1524 1525 |
bdev_write_inode(bdev); |
564f00f6c
|
1526 |
/* |
43d1c0eb7
|
1527 1528 1529 |
* Detaching bdev inode from its wb in __destroy_inode() * is too late: the queue which embeds its bdi (along with * root wb) can be gone as soon as we put_disk() below. |
94007751b
|
1530 |
*/ |
43d1c0eb7
|
1531 |
inode_detach_wb(bdev->bd_inode); |
2e7b651df
|
1532 1533 1534 |
} if (bdev->bd_contains == bdev) { if (disk->fops->release) |
db2a144be
|
1535 |
disk->fops->release(disk, mode); |
2e7b651df
|
1536 1537 1538 |
} if (!bdev->bd_openers) { struct module *owner = disk->fops->owner; |
0762b8bde
|
1539 1540 |
disk_put_part(bdev->bd_part); bdev->bd_part = NULL; |
2e7b651df
|
1541 |
bdev->bd_disk = NULL; |
37be41241
|
1542 1543 |
if (bdev != bdev->bd_contains) victim = bdev->bd_contains; |
2e7b651df
|
1544 |
bdev->bd_contains = NULL; |
523e1d399
|
1545 1546 1547 |
put_disk(disk); module_put(owner); |
2e7b651df
|
1548 |
} |
2e7b651df
|
1549 1550 |
mutex_unlock(&bdev->bd_mutex); bdput(bdev); |
37be41241
|
1551 |
if (victim) |
9a1c35427
|
1552 |
__blkdev_put(victim, mode, 1); |
2e7b651df
|
1553 |
} |
4385bab12
|
1554 |
void blkdev_put(struct block_device *bdev, fmode_t mode) |
37be41241
|
1555 |
{ |
85ef06d1d
|
1556 |
mutex_lock(&bdev->bd_mutex); |
e525fd89d
|
1557 |
if (mode & FMODE_EXCL) { |
6a027eff6
|
1558 1559 1560 1561 1562 1563 1564 |
bool bdev_free; /* * Release a claim on the device. The holder fields * are protected with bdev_lock. bd_mutex is to * synchronize disk_holder unlinking. */ |
6a027eff6
|
1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 |
spin_lock(&bdev_lock); WARN_ON_ONCE(--bdev->bd_holders < 0); WARN_ON_ONCE(--bdev->bd_contains->bd_holders < 0); /* bd_contains might point to self, check in a separate step */ if ((bdev_free = !bdev->bd_holders)) bdev->bd_holder = NULL; if (!bdev->bd_contains->bd_holders) bdev->bd_contains->bd_holder = NULL; spin_unlock(&bdev_lock); |
77ea887e4
|
1577 1578 1579 1580 |
/* * If this was the last claim, remove holder link and * unblock evpoll if it was a write holder. */ |
85ef06d1d
|
1581 1582 1583 |
if (bdev_free && bdev->bd_write_holder) { disk_unblock_events(bdev->bd_disk); bdev->bd_write_holder = false; |
77ea887e4
|
1584 |
} |
6936217cc
|
1585 |
} |
77ea887e4
|
1586 |
|
85ef06d1d
|
1587 1588 1589 1590 1591 1592 1593 1594 |
/* * Trigger event checking and tell drivers to flush MEDIA_CHANGE * event. This is to ensure detection of media removal commanded * from userland - e.g. eject(1). */ disk_flush_events(bdev->bd_disk, DISK_EVENT_MEDIA_CHANGE); mutex_unlock(&bdev->bd_mutex); |
4385bab12
|
1595 |
__blkdev_put(bdev, mode, 0); |
37be41241
|
1596 |
} |
2e7b651df
|
1597 |
EXPORT_SYMBOL(blkdev_put); |
1da177e4c
|
1598 1599 |
static int blkdev_close(struct inode * inode, struct file * filp) { |
4ebb16ca9
|
1600 |
struct block_device *bdev = I_BDEV(bdev_file_inode(filp)); |
4385bab12
|
1601 1602 |
blkdev_put(bdev, filp->f_mode); return 0; |
1da177e4c
|
1603 |
} |
bb93e3a52
|
1604 |
static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg) |
1da177e4c
|
1605 |
{ |
4ebb16ca9
|
1606 |
struct block_device *bdev = I_BDEV(bdev_file_inode(file)); |
56b26add0
|
1607 |
fmode_t mode = file->f_mode; |
fd4ce1acd
|
1608 1609 1610 1611 1612 |
/* * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have * to updated it before every ioctl. */ |
56b26add0
|
1613 |
if (file->f_flags & O_NDELAY) |
fd4ce1acd
|
1614 1615 1616 |
mode |= FMODE_NDELAY; else mode &= ~FMODE_NDELAY; |
56b26add0
|
1617 |
return blkdev_ioctl(bdev, mode, cmd, arg); |
1da177e4c
|
1618 |
} |
87d8fe1ee
|
1619 |
/* |
eef993806
|
1620 1621 1622 1623 1624 1625 |
* Write data to the block device. Only intended for the block device itself * and the raw driver which basically is a fake block device. * * Does not take i_mutex for the write and thus is not for general purpose * use. */ |
1456c0a87
|
1626 |
ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from) |
eef993806
|
1627 1628 |
{ struct file *file = iocb->ki_filp; |
4ebb16ca9
|
1629 |
struct inode *bd_inode = bdev_file_inode(file); |
7ec7b94a3
|
1630 |
loff_t size = i_size_read(bd_inode); |
53362a05a
|
1631 |
struct blk_plug plug; |
eef993806
|
1632 |
ssize_t ret; |
5f380c7fa
|
1633 |
|
7ec7b94a3
|
1634 1635 |
if (bdev_read_only(I_BDEV(bd_inode))) return -EPERM; |
5f380c7fa
|
1636 |
|
7ec7b94a3
|
1637 |
if (!iov_iter_count(from)) |
5f380c7fa
|
1638 |
return 0; |
7ec7b94a3
|
1639 1640 1641 1642 |
if (iocb->ki_pos >= size) return -ENOSPC; iov_iter_truncate(from, size - iocb->ki_pos); |
eef993806
|
1643 |
|
53362a05a
|
1644 |
blk_start_plug(&plug); |
1456c0a87
|
1645 |
ret = __generic_file_write_iter(iocb, from); |
e25922176
|
1646 1647 |
if (ret > 0) ret = generic_write_sync(iocb, ret); |
53362a05a
|
1648 |
blk_finish_plug(&plug); |
eef993806
|
1649 1650 |
return ret; } |
1456c0a87
|
1651 |
EXPORT_SYMBOL_GPL(blkdev_write_iter); |
eef993806
|
1652 |
|
b2de525f0
|
1653 |
ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) |
684c9aaeb
|
1654 1655 |
{ struct file *file = iocb->ki_filp; |
4ebb16ca9
|
1656 |
struct inode *bd_inode = bdev_file_inode(file); |
684c9aaeb
|
1657 |
loff_t size = i_size_read(bd_inode); |
a886038ba
|
1658 |
loff_t pos = iocb->ki_pos; |
684c9aaeb
|
1659 1660 1661 1662 1663 |
if (pos >= size) return 0; size -= pos; |
a886038ba
|
1664 1665 |
iov_iter_truncate(to, size); return generic_file_read_iter(iocb, to); |
684c9aaeb
|
1666 |
} |
b2de525f0
|
1667 |
EXPORT_SYMBOL_GPL(blkdev_read_iter); |
684c9aaeb
|
1668 |
|
eef993806
|
1669 |
/* |
87d8fe1ee
|
1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 |
* Try to release a page associated with block device when the system * is under memory pressure. */ static int blkdev_releasepage(struct page *page, gfp_t wait) { struct super_block *super = BDEV_I(page->mapping->host)->bdev.bd_super; if (super && super->s_op->bdev_try_to_free_page) return super->s_op->bdev_try_to_free_page(super, page, wait); return try_to_free_buffers(page); } |
7f6d5b529
|
1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 |
static int blkdev_writepages(struct address_space *mapping, struct writeback_control *wbc) { if (dax_mapping(mapping)) { struct block_device *bdev = I_BDEV(mapping->host); return dax_writeback_mapping_range(mapping, bdev, wbc); } return generic_writepages(mapping, wbc); } |
4c54ac62d
|
1692 |
static const struct address_space_operations def_blk_aops = { |
1da177e4c
|
1693 |
.readpage = blkdev_readpage, |
447f05bb4
|
1694 |
.readpages = blkdev_readpages, |
1da177e4c
|
1695 |
.writepage = blkdev_writepage, |
6272b5a58
|
1696 1697 |
.write_begin = blkdev_write_begin, .write_end = blkdev_write_end, |
7f6d5b529
|
1698 |
.writepages = blkdev_writepages, |
87d8fe1ee
|
1699 |
.releasepage = blkdev_releasepage, |
1da177e4c
|
1700 |
.direct_IO = blkdev_direct_IO, |
b45972265
|
1701 |
.is_dirty_writeback = buffer_check_dirty_writeback, |
1da177e4c
|
1702 |
}; |
25f4c4141
|
1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 |
#define BLKDEV_FALLOC_FL_SUPPORTED \ (FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | \ FALLOC_FL_ZERO_RANGE | FALLOC_FL_NO_HIDE_STALE) static long blkdev_fallocate(struct file *file, int mode, loff_t start, loff_t len) { struct block_device *bdev = I_BDEV(bdev_file_inode(file)); struct request_queue *q = bdev_get_queue(bdev); struct address_space *mapping; loff_t end = start + len - 1; loff_t isize; int error; /* Fail if we don't recognize the flags. */ if (mode & ~BLKDEV_FALLOC_FL_SUPPORTED) return -EOPNOTSUPP; /* Don't go off the end of the device. */ isize = i_size_read(bdev->bd_inode); if (start >= isize) return -EINVAL; if (end >= isize) { if (mode & FALLOC_FL_KEEP_SIZE) { len = isize - start; end = start + len - 1; } else return -EINVAL; } /* * Don't allow IO that isn't aligned to logical block size. */ if ((start | len) & (bdev_logical_block_size(bdev) - 1)) return -EINVAL; /* Invalidate the page cache, including dirty pages. */ mapping = bdev->bd_inode->i_mapping; truncate_inode_pages_range(mapping, start, end); switch (mode) { case FALLOC_FL_ZERO_RANGE: case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE: error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL, false); break; case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE: /* Only punch if the device can do zeroing discard. */ if (!blk_queue_discard(q) || !q->limits.discard_zeroes_data) return -EOPNOTSUPP; error = blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL, 0); break; case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE: if (!blk_queue_discard(q)) return -EOPNOTSUPP; error = blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL, 0); break; default: return -EOPNOTSUPP; } if (error) return error; /* * Invalidate again; if someone wandered in and dirtied a page, * the caller will be given -EBUSY. The third argument is * inclusive, so the rounding here is safe. */ return invalidate_inode_pages2_range(mapping, start >> PAGE_SHIFT, end >> PAGE_SHIFT); } |
4b6f5d20b
|
1777 |
const struct file_operations def_blk_fops = { |
1da177e4c
|
1778 1779 1780 |
.open = blkdev_open, .release = blkdev_close, .llseek = block_llseek, |
a886038ba
|
1781 |
.read_iter = blkdev_read_iter, |
1456c0a87
|
1782 |
.write_iter = blkdev_write_iter, |
acc93d30d
|
1783 |
.mmap = generic_file_mmap, |
b1dd3b284
|
1784 |
.fsync = blkdev_fsync, |
bb93e3a52
|
1785 |
.unlocked_ioctl = block_ioctl, |
1da177e4c
|
1786 1787 1788 |
#ifdef CONFIG_COMPAT .compat_ioctl = compat_blkdev_ioctl, #endif |
1e8b33328
|
1789 |
.splice_read = generic_file_splice_read, |
8d0207652
|
1790 |
.splice_write = iter_file_splice_write, |
25f4c4141
|
1791 |
.fallocate = blkdev_fallocate, |
1da177e4c
|
1792 1793 1794 1795 1796 1797 1798 |
}; int ioctl_by_bdev(struct block_device *bdev, unsigned cmd, unsigned long arg) { int res; mm_segment_t old_fs = get_fs(); set_fs(KERNEL_DS); |
56b26add0
|
1799 |
res = blkdev_ioctl(bdev, 0, cmd, arg); |
1da177e4c
|
1800 1801 1802 1803 1804 1805 1806 1807 |
set_fs(old_fs); return res; } EXPORT_SYMBOL(ioctl_by_bdev); /** * lookup_bdev - lookup a struct block_device by name |
94e2959e7
|
1808 |
* @pathname: special file representing the block device |
1da177e4c
|
1809 |
* |
57d1b5366
|
1810 |
* Get a reference to the blockdevice at @pathname in the current |
1da177e4c
|
1811 1812 1813 |
* namespace if possible and return it. Return ERR_PTR(error) * otherwise. */ |
421748ecd
|
1814 |
struct block_device *lookup_bdev(const char *pathname) |
1da177e4c
|
1815 1816 1817 |
{ struct block_device *bdev; struct inode *inode; |
421748ecd
|
1818 |
struct path path; |
1da177e4c
|
1819 |
int error; |
421748ecd
|
1820 |
if (!pathname || !*pathname) |
1da177e4c
|
1821 |
return ERR_PTR(-EINVAL); |
421748ecd
|
1822 |
error = kern_path(pathname, LOOKUP_FOLLOW, &path); |
1da177e4c
|
1823 1824 |
if (error) return ERR_PTR(error); |
bb668734c
|
1825 |
inode = d_backing_inode(path.dentry); |
1da177e4c
|
1826 1827 1828 1829 |
error = -ENOTBLK; if (!S_ISBLK(inode->i_mode)) goto fail; error = -EACCES; |
a2982cc92
|
1830 |
if (!may_open_dev(&path)) |
1da177e4c
|
1831 1832 1833 1834 1835 1836 |
goto fail; error = -ENOMEM; bdev = bd_acquire(inode); if (!bdev) goto fail; out: |
421748ecd
|
1837 |
path_put(&path); |
1da177e4c
|
1838 1839 1840 1841 1842 |
return bdev; fail: bdev = ERR_PTR(error); goto out; } |
d5686b444
|
1843 |
EXPORT_SYMBOL(lookup_bdev); |
1da177e4c
|
1844 |
|
93b270f76
|
1845 |
int __invalidate_device(struct block_device *bdev, bool kill_dirty) |
b71e8a4ce
|
1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 |
{ struct super_block *sb = get_super(bdev); int res = 0; if (sb) { /* * no need to lock the super, get_super holds the * read mutex so the filesystem cannot go away * under us (->put_super runs with the write lock * hold). */ shrink_dcache_sb(sb); |
93b270f76
|
1858 |
res = invalidate_inodes(sb, kill_dirty); |
b71e8a4ce
|
1859 1860 |
drop_super(sb); } |
f98393a64
|
1861 |
invalidate_bdev(bdev); |
b71e8a4ce
|
1862 1863 1864 |
return res; } EXPORT_SYMBOL(__invalidate_device); |
5c0d6b60a
|
1865 1866 1867 1868 |
void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg) { struct inode *inode, *old_inode = NULL; |
74278da9f
|
1869 |
spin_lock(&blockdev_superblock->s_inode_list_lock); |
5c0d6b60a
|
1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 |
list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) { struct address_space *mapping = inode->i_mapping; spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW) || mapping->nrpages == 0) { spin_unlock(&inode->i_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); |
74278da9f
|
1881 |
spin_unlock(&blockdev_superblock->s_inode_list_lock); |
5c0d6b60a
|
1882 1883 1884 |
/* * We hold a reference to 'inode' so it couldn't have been * removed from s_inodes list while we dropped the |
74278da9f
|
1885 |
* s_inode_list_lock We cannot iput the inode now as we can |
5c0d6b60a
|
1886 |
* be holding the last reference and we cannot iput it under |
74278da9f
|
1887 |
* s_inode_list_lock. So we keep the reference and iput it |
5c0d6b60a
|
1888 1889 1890 1891 1892 1893 |
* later. */ iput(old_inode); old_inode = inode; func(I_BDEV(inode), arg); |
74278da9f
|
1894 |
spin_lock(&blockdev_superblock->s_inode_list_lock); |
5c0d6b60a
|
1895 |
} |
74278da9f
|
1896 |
spin_unlock(&blockdev_superblock->s_inode_list_lock); |
5c0d6b60a
|
1897 1898 |
iput(old_inode); } |