block_dev.c 37.5 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14
/*
 *  linux/fs/block_dev.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *  Copyright (C) 2001  Andrea Arcangeli <andrea@suse.de> SuSE
 */

#include <linux/init.h>
#include <linux/mm.h>
#include <linux/fcntl.h>
#include <linux/slab.h>
#include <linux/kmod.h>
#include <linux/major.h>
#include <linux/smp_lock.h>
15
#include <linux/device_cgroup.h>
L
Linus Torvalds 已提交
16 17 18 19 20
#include <linux/highmem.h>
#include <linux/blkdev.h>
#include <linux/module.h>
#include <linux/blkpg.h>
#include <linux/buffer_head.h>
N
Nick Piggin 已提交
21
#include <linux/pagevec.h>
22
#include <linux/writeback.h>
L
Linus Torvalds 已提交
23 24 25 26
#include <linux/mpage.h>
#include <linux/mount.h>
#include <linux/uio.h>
#include <linux/namei.h>
27
#include <linux/log2.h>
28
#include <linux/kmemleak.h>
L
Linus Torvalds 已提交
29
#include <asm/uaccess.h>
30
#include "internal.h"
L
Linus Torvalds 已提交
31 32 33 34 35 36

struct bdev_inode {
	struct block_device bdev;
	struct inode vfs_inode;
};

A
Adrian Bunk 已提交
37 38
static const struct address_space_operations def_blk_aops;

L
Linus Torvalds 已提交
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
static inline struct bdev_inode *BDEV_I(struct inode *inode)
{
	return container_of(inode, struct bdev_inode, vfs_inode);
}

inline struct block_device *I_BDEV(struct inode *inode)
{
	return &BDEV_I(inode)->bdev;
}

EXPORT_SYMBOL(I_BDEV);

static sector_t max_block(struct block_device *bdev)
{
	sector_t retval = ~((sector_t)0);
	loff_t sz = i_size_read(bdev->bd_inode);

	if (sz) {
		unsigned int size = block_size(bdev);
		unsigned int sizebits = blksize_bits(size);
		retval = (sz >> sizebits);
	}
	return retval;
}

P
Peter Zijlstra 已提交
64
/* Kill _all_ buffers and pagecache , dirty or not.. */
L
Linus Torvalds 已提交
65 66
static void kill_bdev(struct block_device *bdev)
{
P
Peter Zijlstra 已提交
67 68 69
	if (bdev->bd_inode->i_mapping->nrpages == 0)
		return;
	invalidate_bh_lrus();
L
Linus Torvalds 已提交
70 71 72 73 74 75
	truncate_inode_pages(bdev->bd_inode->i_mapping, 0);
}	

int set_blocksize(struct block_device *bdev, int size)
{
	/* Size must be a power of two, and between 512 and PAGE_SIZE */
76
	if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size))
L
Linus Torvalds 已提交
77 78 79
		return -EINVAL;

	/* Size cannot be smaller than the size supported by the device */
80
	if (size < bdev_logical_block_size(bdev))
L
Linus Torvalds 已提交
81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101
		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)
{
	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;
102
	sb->s_blocksize_bits = blksize_bits(size);
L
Linus Torvalds 已提交
103 104 105 106 107 108 109
	return sb->s_blocksize;
}

EXPORT_SYMBOL(sb_set_blocksize);

int sb_min_blocksize(struct super_block *sb, int size)
{
110
	int minsize = bdev_logical_block_size(sb->s_bdev);
L
Linus Torvalds 已提交
111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139
	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)
{
	if (iblock >= max_block(I_BDEV(inode))) {
		if (create)
			return -EIO;

		/*
		 * for reads, we're just trying to fill a partial page.
		 * return a hole, they will have to call get_block again
		 * before they can fill it, and they will get -EIO at that
		 * time
		 */
		return 0;
	}
	bh->b_bdev = I_BDEV(inode);
	bh->b_blocknr = iblock;
	set_buffer_mapped(bh);
	return 0;
}

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
static int
blkdev_get_blocks(struct inode *inode, sector_t iblock,
		struct buffer_head *bh, int create)
{
	sector_t end_block = max_block(I_BDEV(inode));
	unsigned long max_blocks = bh->b_size >> inode->i_blkbits;

	if ((iblock + max_blocks) > end_block) {
		max_blocks = end_block - iblock;
		if ((long)max_blocks <= 0) {
			if (create)
				return -EIO;	/* write fully beyond EOF */
			/*
			 * It is a read which is fully beyond EOF.  We return
			 * a !buffer_mapped buffer
			 */
			max_blocks = 0;
		}
	}

	bh->b_bdev = I_BDEV(inode);
	bh->b_blocknr = iblock;
	bh->b_size = max_blocks << inode->i_blkbits;
	if (max_blocks)
		set_buffer_mapped(bh);
	return 0;
}

static ssize_t
blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
			loff_t offset, unsigned long nr_segs)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file->f_mapping->host;

	return blockdev_direct_IO_no_locking(rw, iocb, inode, I_BDEV(inode),
				iov, offset, nr_segs, blkdev_get_blocks, NULL);
}

179 180 181 182 183 184 185 186 187
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);
}

N
Nick Piggin 已提交
188 189 190 191 192 193
/*
 * 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)
{
194
	return __sync_blockdev(bdev, 1);
N
Nick Piggin 已提交
195 196 197 198 199 200 201 202 203 204 205 206
}
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) {
207
		int res = sync_filesystem(sb);
N
Nick Piggin 已提交
208 209 210 211 212
		drop_super(sb);
		return res;
	}
	return sync_blockdev(bdev);
}
213
EXPORT_SYMBOL(fsync_bdev);
N
Nick Piggin 已提交
214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245

/**
 * freeze_bdev  --  lock a filesystem and force it into a consistent state
 * @bdev:	blockdevice to lock
 *
 * 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);
	if (bdev->bd_fsfreeze_count > 0) {
		bdev->bd_fsfreeze_count++;
		sb = get_super(bdev);
		mutex_unlock(&bdev->bd_fsfreeze_mutex);
		return sb;
	}
	bdev->bd_fsfreeze_count++;

	sb = get_super(bdev);
	if (sb && !(sb->s_flags & MS_RDONLY)) {
		sb->s_frozen = SB_FREEZE_WRITE;
		smp_wmb();

246
		sync_filesystem(sb);
N
Nick Piggin 已提交
247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269

		sb->s_frozen = SB_FREEZE_TRANS;
		smp_wmb();

		sync_blockdev(sb->s_bdev);

		if (sb->s_op->freeze_fs) {
			error = sb->s_op->freeze_fs(sb);
			if (error) {
				printk(KERN_ERR
					"VFS:Filesystem freeze failed\n");
				sb->s_frozen = SB_UNFROZEN;
				drop_super(sb);
				bdev->bd_fsfreeze_count--;
				mutex_unlock(&bdev->bd_fsfreeze_mutex);
				return ERR_PTR(error);
			}
		}
	}

	sync_blockdev(bdev);
	mutex_unlock(&bdev->bd_fsfreeze_mutex);

270
	return sb;	/* thaw_bdev releases s->s_umount */
N
Nick Piggin 已提交
271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324
}
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)
{
	int error = 0;

	mutex_lock(&bdev->bd_fsfreeze_mutex);
	if (!bdev->bd_fsfreeze_count) {
		mutex_unlock(&bdev->bd_fsfreeze_mutex);
		return -EINVAL;
	}

	bdev->bd_fsfreeze_count--;
	if (bdev->bd_fsfreeze_count > 0) {
		if (sb)
			drop_super(sb);
		mutex_unlock(&bdev->bd_fsfreeze_mutex);
		return 0;
	}

	if (sb) {
		BUG_ON(sb->s_bdev != bdev);
		if (!(sb->s_flags & MS_RDONLY)) {
			if (sb->s_op->unfreeze_fs) {
				error = sb->s_op->unfreeze_fs(sb);
				if (error) {
					printk(KERN_ERR
						"VFS:Filesystem thaw failed\n");
					sb->s_frozen = SB_FREEZE_TRANS;
					bdev->bd_fsfreeze_count++;
					mutex_unlock(&bdev->bd_fsfreeze_mutex);
					return error;
				}
			}
			sb->s_frozen = SB_UNFROZEN;
			smp_wmb();
			wake_up(&sb->s_wait_unfrozen);
		}
		drop_super(sb);
	}

	mutex_unlock(&bdev->bd_fsfreeze_mutex);
	return 0;
}
EXPORT_SYMBOL(thaw_bdev);

L
Linus Torvalds 已提交
325 326 327 328 329 330 331 332 333 334
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);
}

N
Nick Piggin 已提交
335 336 337
static int blkdev_write_begin(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned flags,
			struct page **pagep, void **fsdata)
L
Linus Torvalds 已提交
338
{
N
Nick Piggin 已提交
339 340 341
	*pagep = NULL;
	return block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
				blkdev_get_block);
L
Linus Torvalds 已提交
342 343
}

N
Nick Piggin 已提交
344 345 346
static int blkdev_write_end(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned copied,
			struct page *page, void *fsdata)
L
Linus Torvalds 已提交
347
{
N
Nick Piggin 已提交
348 349 350 351 352 353 354
	int ret;
	ret = block_write_end(file, mapping, pos, len, copied, page, fsdata);

	unlock_page(page);
	page_cache_release(page);

	return ret;
L
Linus Torvalds 已提交
355 356 357 358
}

/*
 * private llseek:
359
 * for a block special file file->f_path.dentry->d_inode->i_size is zero
L
Linus Torvalds 已提交
360 361 362 363 364 365 366 367
 * so we compute the size by hand (just as in block_read/write above)
 */
static loff_t block_llseek(struct file *file, loff_t offset, int origin)
{
	struct inode *bd_inode = file->f_mapping->host;
	loff_t size;
	loff_t retval;

368
	mutex_lock(&bd_inode->i_mutex);
L
Linus Torvalds 已提交
369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384
	size = i_size_read(bd_inode);

	switch (origin) {
		case 2:
			offset += size;
			break;
		case 1:
			offset += file->f_pos;
	}
	retval = -EINVAL;
	if (offset >= 0 && offset <= size) {
		if (offset != file->f_pos) {
			file->f_pos = offset;
		}
		retval = offset;
	}
385
	mutex_unlock(&bd_inode->i_mutex);
L
Linus Torvalds 已提交
386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403
	return retval;
}
	
/*
 *	Filp is never NULL; the only case when ->fsync() is called with
 *	NULL first argument is nfsd_sync_dir() and that's not a directory.
 */
 
static int block_fsync(struct file *filp, struct dentry *dentry, int datasync)
{
	return sync_blockdev(I_BDEV(filp->f_mapping->host));
}

/*
 * pseudo-fs
 */

static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(bdev_lock);
404
static struct kmem_cache * bdev_cachep __read_mostly;
L
Linus Torvalds 已提交
405 406 407

static struct inode *bdev_alloc_inode(struct super_block *sb)
{
408
	struct bdev_inode *ei = kmem_cache_alloc(bdev_cachep, GFP_KERNEL);
L
Linus Torvalds 已提交
409 410 411 412 413 414 415 416 417 418 419 420
	if (!ei)
		return NULL;
	return &ei->vfs_inode;
}

static void bdev_destroy_inode(struct inode *inode)
{
	struct bdev_inode *bdi = BDEV_I(inode);

	kmem_cache_free(bdev_cachep, bdi);
}

421
static void init_once(void *foo)
L
Linus Torvalds 已提交
422 423 424 425
{
	struct bdev_inode *ei = (struct bdev_inode *) foo;
	struct block_device *bdev = &ei->bdev;

C
Christoph Lameter 已提交
426 427 428 429
	memset(bdev, 0, sizeof(*bdev));
	mutex_init(&bdev->bd_mutex);
	INIT_LIST_HEAD(&bdev->bd_inodes);
	INIT_LIST_HEAD(&bdev->bd_list);
430
#ifdef CONFIG_SYSFS
C
Christoph Lameter 已提交
431
	INIT_LIST_HEAD(&bdev->bd_holder_list);
432
#endif
C
Christoph Lameter 已提交
433
	inode_init_once(&ei->vfs_inode);
434 435
	/* Initialize mutex for freeze. */
	mutex_init(&bdev->bd_fsfreeze_mutex);
L
Linus Torvalds 已提交
436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456
}

static inline void __bd_forget(struct inode *inode)
{
	list_del_init(&inode->i_devices);
	inode->i_bdev = NULL;
	inode->i_mapping = &inode->i_data;
}

static void bdev_clear_inode(struct inode *inode)
{
	struct block_device *bdev = &BDEV_I(inode)->bdev;
	struct list_head *p;
	spin_lock(&bdev_lock);
	while ( (p = bdev->bd_inodes.next) != &bdev->bd_inodes ) {
		__bd_forget(list_entry(p, struct inode, i_devices));
	}
	list_del_init(&bdev->bd_list);
	spin_unlock(&bdev_lock);
}

457
static const struct super_operations bdev_sops = {
L
Linus Torvalds 已提交
458 459 460 461 462 463 464
	.statfs = simple_statfs,
	.alloc_inode = bdev_alloc_inode,
	.destroy_inode = bdev_destroy_inode,
	.drop_inode = generic_delete_inode,
	.clear_inode = bdev_clear_inode,
};

465 466
static int bd_get_sb(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
L
Linus Torvalds 已提交
467
{
468
	return get_sb_pseudo(fs_type, "bdev:", &bdev_sops, 0x62646576, mnt);
L
Linus Torvalds 已提交
469 470 471 472 473 474 475 476
}

static struct file_system_type bd_type = {
	.name		= "bdev",
	.get_sb		= bd_get_sb,
	.kill_sb	= kill_anon_super,
};

477
struct super_block *blockdev_superblock __read_mostly;
L
Linus Torvalds 已提交
478 479 480 481

void __init bdev_cache_init(void)
{
	int err;
482 483
	struct vfsmount *bd_mnt;

L
Linus Torvalds 已提交
484
	bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode),
485 486
			0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
				SLAB_MEM_SPREAD|SLAB_PANIC),
487
			init_once);
L
Linus Torvalds 已提交
488 489 490 491 492 493
	err = register_filesystem(&bd_type);
	if (err)
		panic("Cannot register bdev pseudo-fs");
	bd_mnt = kern_mount(&bd_type);
	if (IS_ERR(bd_mnt))
		panic("Cannot create bdev pseudo-fs");
494 495 496 497 498
	/*
	 * This vfsmount structure is only used to obtain the
	 * blockdev_superblock, so tell kmemleak not to report it.
	 */
	kmemleak_not_leak(bd_mnt);
L
Linus Torvalds 已提交
499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529
	blockdev_superblock = bd_mnt->mnt_sb;	/* For writeback */
}

/*
 * 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;

530
	inode = iget5_locked(blockdev_superblock, hash(dev),
L
Linus Torvalds 已提交
531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559
			bdev_test, bdev_set, &dev);

	if (!inode)
		return NULL;

	bdev = &BDEV_I(inode)->bdev;

	if (inode->i_state & I_NEW) {
		bdev->bd_contains = NULL;
		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);
		inode->i_data.backing_dev_info = &default_backing_dev_info;
		spin_lock(&bdev_lock);
		list_add(&bdev->bd_list, &all_bdevs);
		spin_unlock(&bdev_lock);
		unlock_new_inode(inode);
	}
	return bdev;
}

EXPORT_SYMBOL(bdget);

560 561 562 563 564 565 566 567 568 569
/**
 * 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)
{
	atomic_inc(&bdev->bd_inode->i_count);
	return bdev;
}

L
Linus Torvalds 已提交
570 571
long nr_blockdev_pages(void)
{
572
	struct block_device *bdev;
L
Linus Torvalds 已提交
573 574
	long ret = 0;
	spin_lock(&bdev_lock);
575
	list_for_each_entry(bdev, &all_bdevs, bd_list) {
L
Linus Torvalds 已提交
576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591
		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;
592

L
Linus Torvalds 已提交
593 594
	spin_lock(&bdev_lock);
	bdev = inode->i_bdev;
595 596
	if (bdev) {
		atomic_inc(&bdev->bd_inode->i_count);
L
Linus Torvalds 已提交
597 598 599 600
		spin_unlock(&bdev_lock);
		return bdev;
	}
	spin_unlock(&bdev_lock);
601

L
Linus Torvalds 已提交
602 603 604
	bdev = bdget(inode->i_rdev);
	if (bdev) {
		spin_lock(&bdev_lock);
605 606 607 608 609 610 611 612 613 614 615 616
		if (!inode->i_bdev) {
			/*
			 * We take an additional bd_inode->i_count for inode,
			 * and it's released in clear_inode() of inode.
			 * So, we can access it via ->i_mapping always
			 * without igrab().
			 */
			atomic_inc(&bdev->bd_inode->i_count);
			inode->i_bdev = bdev;
			inode->i_mapping = bdev->bd_inode->i_mapping;
			list_add(&inode->i_devices, &bdev->bd_inodes);
		}
L
Linus Torvalds 已提交
617 618 619 620 621 622 623 624 625
		spin_unlock(&bdev_lock);
	}
	return bdev;
}

/* Call when you free inode */

void bd_forget(struct inode *inode)
{
626 627
	struct block_device *bdev = NULL;

L
Linus Torvalds 已提交
628
	spin_lock(&bdev_lock);
629
	if (inode->i_bdev) {
630
		if (!sb_is_blkdev_sb(inode->i_sb))
631
			bdev = inode->i_bdev;
L
Linus Torvalds 已提交
632
		__bd_forget(inode);
633
	}
L
Linus Torvalds 已提交
634
	spin_unlock(&bdev_lock);
635 636 637

	if (bdev)
		iput(bdev->bd_inode);
L
Linus Torvalds 已提交
638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688
}

int bd_claim(struct block_device *bdev, void *holder)
{
	int res;
	spin_lock(&bdev_lock);

	/* first decide result */
	if (bdev->bd_holder == holder)
		res = 0;	 /* already a holder */
	else if (bdev->bd_holder != NULL)
		res = -EBUSY; 	 /* held by someone else */
	else if (bdev->bd_contains == bdev)
		res = 0;  	 /* is a whole device which isn't held */

	else if (bdev->bd_contains->bd_holder == bd_claim)
		res = 0; 	 /* is a partition of a device that is being partitioned */
	else if (bdev->bd_contains->bd_holder != NULL)
		res = -EBUSY;	 /* is a partition of a held device */
	else
		res = 0;	 /* is a partition of an un-held device */

	/* now impose change */
	if (res==0) {
		/* note that for a whole device bd_holders
		 * will be incremented twice, and bd_holder will
		 * be set to bd_claim before being set to holder
		 */
		bdev->bd_contains->bd_holders ++;
		bdev->bd_contains->bd_holder = bd_claim;
		bdev->bd_holders++;
		bdev->bd_holder = holder;
	}
	spin_unlock(&bdev_lock);
	return res;
}

EXPORT_SYMBOL(bd_claim);

void bd_release(struct block_device *bdev)
{
	spin_lock(&bdev_lock);
	if (!--bdev->bd_contains->bd_holders)
		bdev->bd_contains->bd_holder = NULL;
	if (!--bdev->bd_holders)
		bdev->bd_holder = NULL;
	spin_unlock(&bdev_lock);
}

EXPORT_SYMBOL(bd_release);

689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706
#ifdef CONFIG_SYSFS
/*
 * Functions for bd_claim_by_kobject / bd_release_from_kobject
 *
 *     If a kobject is passed to bd_claim_by_kobject()
 *     and the kobject has a parent directory,
 *     following symlinks are created:
 *        o from the kobject to the claimed bdev
 *        o from "holders" directory of the bdev to the parent of the kobject
 *     bd_release_from_kobject() removes these symlinks.
 *
 *     Example:
 *        If /dev/dm-0 maps to /dev/sda, kobject corresponding to
 *        /sys/block/dm-0/slaves is passed to bd_claim_by_kobject(), then:
 *           /sys/block/dm-0/slaves/sda --> /sys/block/sda
 *           /sys/block/sda/holders/dm-0 --> /sys/block/dm-0
 */

707
static int add_symlink(struct kobject *from, struct kobject *to)
708 709
{
	if (!from || !to)
710 711
		return 0;
	return sysfs_create_link(from, to, kobject_name(to));
712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754
}

static void del_symlink(struct kobject *from, struct kobject *to)
{
	if (!from || !to)
		return;
	sysfs_remove_link(from, kobject_name(to));
}

/*
 * 'struct bd_holder' contains pointers to kobjects symlinked by
 * bd_claim_by_kobject.
 * It's connected to bd_holder_list which is protected by bdev->bd_sem.
 */
struct bd_holder {
	struct list_head list;	/* chain of holders of the bdev */
	int count;		/* references from the holder */
	struct kobject *sdir;	/* holder object, e.g. "/block/dm-0/slaves" */
	struct kobject *hdev;	/* e.g. "/block/dm-0" */
	struct kobject *hdir;	/* e.g. "/block/sda/holders" */
	struct kobject *sdev;	/* e.g. "/block/sda" */
};

/*
 * Get references of related kobjects at once.
 * Returns 1 on success. 0 on failure.
 *
 * Should call bd_holder_release_dirs() after successful use.
 */
static int bd_holder_grab_dirs(struct block_device *bdev,
			struct bd_holder *bo)
{
	if (!bdev || !bo)
		return 0;

	bo->sdir = kobject_get(bo->sdir);
	if (!bo->sdir)
		return 0;

	bo->hdev = kobject_get(bo->sdir->parent);
	if (!bo->hdev)
		goto fail_put_sdir;

T
Tejun Heo 已提交
755
	bo->sdev = kobject_get(&part_to_dev(bdev->bd_part)->kobj);
756 757 758
	if (!bo->sdev)
		goto fail_put_hdev;

759
	bo->hdir = kobject_get(bdev->bd_part->holder_dir);
760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802
	if (!bo->hdir)
		goto fail_put_sdev;

	return 1;

fail_put_sdev:
	kobject_put(bo->sdev);
fail_put_hdev:
	kobject_put(bo->hdev);
fail_put_sdir:
	kobject_put(bo->sdir);

	return 0;
}

/* Put references of related kobjects at once. */
static void bd_holder_release_dirs(struct bd_holder *bo)
{
	kobject_put(bo->hdir);
	kobject_put(bo->sdev);
	kobject_put(bo->hdev);
	kobject_put(bo->sdir);
}

static struct bd_holder *alloc_bd_holder(struct kobject *kobj)
{
	struct bd_holder *bo;

	bo = kzalloc(sizeof(*bo), GFP_KERNEL);
	if (!bo)
		return NULL;

	bo->count = 1;
	bo->sdir = kobj;

	return bo;
}

static void free_bd_holder(struct bd_holder *bo)
{
	kfree(bo);
}

J
Jun'ichi Nomura 已提交
803 804 805 806 807 808 809 810 811 812
/**
 * find_bd_holder - find matching struct bd_holder from the block device
 *
 * @bdev:	struct block device to be searched
 * @bo:		target struct bd_holder
 *
 * Returns matching entry with @bo in @bdev->bd_holder_list.
 * If found, increment the reference count and return the pointer.
 * If not found, returns NULL.
 */
A
Andrew Morton 已提交
813 814
static struct bd_holder *find_bd_holder(struct block_device *bdev,
					struct bd_holder *bo)
J
Jun'ichi Nomura 已提交
815 816 817 818 819 820 821 822 823 824 825 826
{
	struct bd_holder *tmp;

	list_for_each_entry(tmp, &bdev->bd_holder_list, list)
		if (tmp->sdir == bo->sdir) {
			tmp->count++;
			return tmp;
		}

	return NULL;
}

827 828 829 830 831 832
/**
 * add_bd_holder - create sysfs symlinks for bd_claim() relationship
 *
 * @bdev:	block device to be bd_claimed
 * @bo:		preallocated and initialized by alloc_bd_holder()
 *
J
Jun'ichi Nomura 已提交
833
 * Add @bo to @bdev->bd_holder_list, create symlinks.
834
 *
J
Jun'ichi Nomura 已提交
835 836
 * Returns 0 if symlinks are created.
 * Returns -ve if something fails.
837 838 839
 */
static int add_bd_holder(struct block_device *bdev, struct bd_holder *bo)
{
840
	int err;
841 842

	if (!bo)
843
		return -EINVAL;
844 845

	if (!bd_holder_grab_dirs(bdev, bo))
846
		return -EBUSY;
847

848 849 850 851 852 853 854 855
	err = add_symlink(bo->sdir, bo->sdev);
	if (err)
		return err;

	err = add_symlink(bo->hdir, bo->hdev);
	if (err) {
		del_symlink(bo->sdir, bo->sdev);
		return err;
856
	}
857 858 859

	list_add_tail(&bo->list, &bdev->bd_holder_list);
	return 0;
860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916
}

/**
 * del_bd_holder - delete sysfs symlinks for bd_claim() relationship
 *
 * @bdev:	block device to be bd_claimed
 * @kobj:	holder's kobject
 *
 * If there is matching entry with @kobj in @bdev->bd_holder_list
 * and no other bd_claim() from the same kobject,
 * remove the struct bd_holder from the list, delete symlinks for it.
 *
 * Returns a pointer to the struct bd_holder when it's removed from the list
 * and ready to be freed.
 * Returns NULL if matching claim isn't found or there is other bd_claim()
 * by the same kobject.
 */
static struct bd_holder *del_bd_holder(struct block_device *bdev,
					struct kobject *kobj)
{
	struct bd_holder *bo;

	list_for_each_entry(bo, &bdev->bd_holder_list, list) {
		if (bo->sdir == kobj) {
			bo->count--;
			BUG_ON(bo->count < 0);
			if (!bo->count) {
				list_del(&bo->list);
				del_symlink(bo->sdir, bo->sdev);
				del_symlink(bo->hdir, bo->hdev);
				bd_holder_release_dirs(bo);
				return bo;
			}
			break;
		}
	}

	return NULL;
}

/**
 * bd_claim_by_kobject - bd_claim() with additional kobject signature
 *
 * @bdev:	block device to be claimed
 * @holder:	holder's signature
 * @kobj:	holder's kobject
 *
 * Do bd_claim() and if it succeeds, create sysfs symlinks between
 * the bdev and the holder's kobject.
 * Use bd_release_from_kobject() when relesing the claimed bdev.
 *
 * Returns 0 on success. (same as bd_claim())
 * Returns errno on failure.
 */
static int bd_claim_by_kobject(struct block_device *bdev, void *holder,
				struct kobject *kobj)
{
917
	int err;
J
Jun'ichi Nomura 已提交
918
	struct bd_holder *bo, *found;
919 920 921 922 923 924 925 926

	if (!kobj)
		return -EINVAL;

	bo = alloc_bd_holder(kobj);
	if (!bo)
		return -ENOMEM;

927
	mutex_lock(&bdev->bd_mutex);
J
Jun'ichi Nomura 已提交
928

929 930
	err = bd_claim(bdev, holder);
	if (err)
A
Andrew Morton 已提交
931
		goto fail;
932 933 934

	found = find_bd_holder(bdev, bo);
	if (found)
A
Andrew Morton 已提交
935
		goto fail;
936 937 938 939

	err = add_bd_holder(bdev, bo);
	if (err)
		bd_release(bdev);
A
Andrew Morton 已提交
940 941 942
	else
		bo = NULL;
fail:
943
	mutex_unlock(&bdev->bd_mutex);
A
Andrew Morton 已提交
944
	free_bd_holder(bo);
945
	return err;
946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961
}

/**
 * bd_release_from_kobject - bd_release() with additional kobject signature
 *
 * @bdev:	block device to be released
 * @kobj:	holder's kobject
 *
 * Do bd_release() and remove sysfs symlinks created by bd_claim_by_kobject().
 */
static void bd_release_from_kobject(struct block_device *bdev,
					struct kobject *kobj)
{
	if (!kobj)
		return;

962
	mutex_lock(&bdev->bd_mutex);
963
	bd_release(bdev);
A
Andrew Morton 已提交
964
	free_bd_holder(del_bd_holder(bdev, kobj));
965
	mutex_unlock(&bdev->bd_mutex);
966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999
}

/**
 * bd_claim_by_disk - wrapper function for bd_claim_by_kobject()
 *
 * @bdev:	block device to be claimed
 * @holder:	holder's signature
 * @disk:	holder's gendisk
 *
 * Call bd_claim_by_kobject() with getting @disk->slave_dir.
 */
int bd_claim_by_disk(struct block_device *bdev, void *holder,
			struct gendisk *disk)
{
	return bd_claim_by_kobject(bdev, holder, kobject_get(disk->slave_dir));
}
EXPORT_SYMBOL_GPL(bd_claim_by_disk);

/**
 * bd_release_from_disk - wrapper function for bd_release_from_kobject()
 *
 * @bdev:	block device to be claimed
 * @disk:	holder's gendisk
 *
 * Call bd_release_from_kobject() and put @disk->slave_dir.
 */
void bd_release_from_disk(struct block_device *bdev, struct gendisk *disk)
{
	bd_release_from_kobject(bdev, disk->slave_dir);
	kobject_put(disk->slave_dir);
}
EXPORT_SYMBOL_GPL(bd_release_from_disk);
#endif

L
Linus Torvalds 已提交
1000 1001 1002 1003 1004 1005 1006
/*
 * Tries to open block device by device number.  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.
 */
1007
struct block_device *open_by_devnum(dev_t dev, fmode_t mode)
L
Linus Torvalds 已提交
1008 1009 1010 1011
{
	struct block_device *bdev = bdget(dev);
	int err = -ENOMEM;
	if (bdev)
1012
		err = blkdev_get(bdev, mode);
L
Linus Torvalds 已提交
1013 1014 1015 1016 1017
	return err ? ERR_PTR(err) : bdev;
}

EXPORT_SYMBOL(open_by_devnum);

1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043
/**
 * flush_disk - invalidates all buffer-cache entries on a disk
 *
 * @bdev:      struct block device to be flushed
 *
 * 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.
 */
static void flush_disk(struct block_device *bdev)
{
	if (__invalidate_device(bdev)) {
		char name[BDEVNAME_SIZE] = "";

		if (bdev->bd_disk)
			disk_name(bdev->bd_disk, 0, name);
		printk(KERN_WARNING "VFS: busy inodes on changed media or "
		       "resized disk %s\n", name);
	}

	if (!bdev->bd_disk)
		return;
	if (disk_partitionable(bdev->bd_disk))
		bdev->bd_invalidated = 1;
}

1044
/**
1045
 * check_disk_size_change - checks for disk size change and adjusts bdev size.
1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065
 * @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) {
		char name[BDEVNAME_SIZE];

		disk_name(disk, 0, name);
		printk(KERN_INFO
		       "%s: detected capacity change from %lld to %lld\n",
		       name, bdev_size, disk_size);
		i_size_write(bdev->bd_inode, disk_size);
1066
		flush_disk(bdev);
1067 1068 1069 1070
	}
}
EXPORT_SYMBOL(check_disk_size_change);

1071
/**
1072
 * revalidate_disk - wrapper for lower-level driver's revalidate_disk call-back
1073 1074 1075 1076 1077 1078 1079 1080
 * @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)
{
1081
	struct block_device *bdev;
1082 1083 1084 1085 1086
	int ret = 0;

	if (disk->fops->revalidate_disk)
		ret = disk->fops->revalidate_disk(disk);

1087 1088 1089 1090 1091 1092 1093 1094
	bdev = bdget_disk(disk, 0);
	if (!bdev)
		return ret;

	mutex_lock(&bdev->bd_mutex);
	check_disk_size_change(disk, bdev);
	mutex_unlock(&bdev->bd_mutex);
	bdput(bdev);
1095 1096 1097 1098
	return ret;
}
EXPORT_SYMBOL(revalidate_disk);

L
Linus Torvalds 已提交
1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110
/*
 * 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;
1111
	const struct block_device_operations *bdops = disk->fops;
L
Linus Torvalds 已提交
1112 1113 1114 1115 1116 1117

	if (!bdops->media_changed)
		return 0;
	if (!bdops->media_changed(bdev->bd_disk))
		return 0;

1118
	flush_disk(bdev);
L
Linus Torvalds 已提交
1119 1120 1121 1122 1123 1124 1125 1126 1127
	if (bdops->revalidate_disk)
		bdops->revalidate_disk(bdev->bd_disk);
	return 1;
}

EXPORT_SYMBOL(check_disk_change);

void bd_set_size(struct block_device *bdev, loff_t size)
{
1128
	unsigned bsize = bdev_logical_block_size(bdev);
L
Linus Torvalds 已提交
1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140

	bdev->bd_inode->i_size = size;
	while (bsize < PAGE_CACHE_SIZE) {
		if (size & bsize)
			break;
		bsize <<= 1;
	}
	bdev->bd_block_size = bsize;
	bdev->bd_inode->i_blkbits = blksize_bits(bsize);
}
EXPORT_SYMBOL(bd_set_size);

A
Al Viro 已提交
1141
static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
1142

1143 1144 1145 1146 1147 1148 1149
/*
 * bd_mutex locking:
 *
 *  mutex_lock(part->bd_mutex)
 *    mutex_lock_nested(whole->bd_mutex, 1)
 */

1150
static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
L
Linus Torvalds 已提交
1151 1152
{
	struct gendisk *disk;
1153
	int ret;
1154
	int partno;
1155 1156
	int perm = 0;

1157
	if (mode & FMODE_READ)
1158
		perm |= MAY_READ;
1159
	if (mode & FMODE_WRITE)
1160 1161 1162 1163 1164
		perm |= MAY_WRITE;
	/*
	 * hooks: /n/, see "layering violations".
	 */
	ret = devcgroup_inode_permission(bdev->bd_inode, perm);
1165 1166
	if (ret != 0) {
		bdput(bdev);
1167
		return ret;
1168
	}
1169

L
Linus Torvalds 已提交
1170
	lock_kernel();
1171
 restart:
T
Tejun Heo 已提交
1172

1173
	ret = -ENXIO;
1174
	disk = get_gendisk(bdev->bd_dev, &partno);
T
Tejun Heo 已提交
1175 1176
	if (!disk)
		goto out_unlock_kernel;
L
Linus Torvalds 已提交
1177

1178
	mutex_lock_nested(&bdev->bd_mutex, for_part);
L
Linus Torvalds 已提交
1179 1180 1181
	if (!bdev->bd_openers) {
		bdev->bd_disk = disk;
		bdev->bd_contains = bdev;
1182
		if (!partno) {
L
Linus Torvalds 已提交
1183
			struct backing_dev_info *bdi;
1184 1185 1186 1187 1188 1189

			ret = -ENXIO;
			bdev->bd_part = disk_get_part(disk, partno);
			if (!bdev->bd_part)
				goto out_clear;

L
Linus Torvalds 已提交
1190
			if (disk->fops->open) {
1191
				ret = disk->fops->open(bdev, mode);
1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204
				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;
					module_put(disk->fops->owner);
					put_disk(disk);
					bdev->bd_disk = NULL;
					mutex_unlock(&bdev->bd_mutex);
					goto restart;
				}
L
Linus Torvalds 已提交
1205
				if (ret)
T
Tejun Heo 已提交
1206
					goto out_clear;
L
Linus Torvalds 已提交
1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221
			}
			if (!bdev->bd_openers) {
				bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
				bdi = blk_get_backing_dev_info(bdev);
				if (bdi == NULL)
					bdi = &default_backing_dev_info;
				bdev->bd_inode->i_data.backing_dev_info = bdi;
			}
			if (bdev->bd_invalidated)
				rescan_partitions(disk, bdev);
		} else {
			struct block_device *whole;
			whole = bdget_disk(disk, 0);
			ret = -ENOMEM;
			if (!whole)
T
Tejun Heo 已提交
1222
				goto out_clear;
1223
			BUG_ON(for_part);
1224
			ret = __blkdev_get(whole, mode, 1);
L
Linus Torvalds 已提交
1225
			if (ret)
T
Tejun Heo 已提交
1226
				goto out_clear;
L
Linus Torvalds 已提交
1227 1228 1229
			bdev->bd_contains = whole;
			bdev->bd_inode->i_data.backing_dev_info =
			   whole->bd_inode->i_data.backing_dev_info;
1230
			bdev->bd_part = disk_get_part(disk, partno);
1231
			if (!(disk->flags & GENHD_FL_UP) ||
1232
			    !bdev->bd_part || !bdev->bd_part->nr_sects) {
L
Linus Torvalds 已提交
1233
				ret = -ENXIO;
T
Tejun Heo 已提交
1234
				goto out_clear;
L
Linus Torvalds 已提交
1235
			}
1236
			bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
L
Linus Torvalds 已提交
1237 1238 1239
		}
	} else {
		put_disk(disk);
T
Tejun Heo 已提交
1240 1241
		module_put(disk->fops->owner);
		disk = NULL;
L
Linus Torvalds 已提交
1242 1243
		if (bdev->bd_contains == bdev) {
			if (bdev->bd_disk->fops->open) {
1244
				ret = bdev->bd_disk->fops->open(bdev, mode);
L
Linus Torvalds 已提交
1245
				if (ret)
T
Tejun Heo 已提交
1246
					goto out_unlock_bdev;
L
Linus Torvalds 已提交
1247 1248 1249 1250 1251 1252
			}
			if (bdev->bd_invalidated)
				rescan_partitions(bdev->bd_disk, bdev);
		}
	}
	bdev->bd_openers++;
1253 1254
	if (for_part)
		bdev->bd_part_count++;
1255
	mutex_unlock(&bdev->bd_mutex);
L
Linus Torvalds 已提交
1256 1257 1258
	unlock_kernel();
	return 0;

T
Tejun Heo 已提交
1259
 out_clear:
1260
	disk_put_part(bdev->bd_part);
L
Linus Torvalds 已提交
1261
	bdev->bd_disk = NULL;
T
Tejun Heo 已提交
1262
	bdev->bd_part = NULL;
L
Linus Torvalds 已提交
1263 1264
	bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
	if (bdev != bdev->bd_contains)
1265
		__blkdev_put(bdev->bd_contains, mode, 1);
L
Linus Torvalds 已提交
1266
	bdev->bd_contains = NULL;
T
Tejun Heo 已提交
1267
 out_unlock_bdev:
1268
	mutex_unlock(&bdev->bd_mutex);
T
Tejun Heo 已提交
1269
 out_unlock_kernel:
L
Linus Torvalds 已提交
1270
	unlock_kernel();
T
Tejun Heo 已提交
1271 1272 1273 1274 1275 1276

	if (disk)
		module_put(disk->fops->owner);
	put_disk(disk);
	bdput(bdev);

L
Linus Torvalds 已提交
1277 1278 1279
	return ret;
}

1280
int blkdev_get(struct block_device *bdev, fmode_t mode)
L
Linus Torvalds 已提交
1281
{
1282
	return __blkdev_get(bdev, mode, 0);
1283
}
L
Linus Torvalds 已提交
1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298
EXPORT_SYMBOL(blkdev_get);

static int blkdev_open(struct inode * inode, struct file * filp)
{
	struct block_device *bdev;
	int res;

	/*
	 * 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;

1299 1300 1301 1302 1303 1304 1305
	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;

L
Linus Torvalds 已提交
1306
	bdev = bd_acquire(inode);
1307 1308
	if (bdev == NULL)
		return -ENOMEM;
L
Linus Torvalds 已提交
1309

1310 1311 1312
	filp->f_mapping = bdev->bd_inode->i_mapping;

	res = blkdev_get(bdev, filp->f_mode);
L
Linus Torvalds 已提交
1313 1314 1315
	if (res)
		return res;

1316 1317 1318 1319 1320
	if (filp->f_mode & FMODE_EXCL) {
		res = bd_claim(bdev, filp);
		if (res)
			goto out_blkdev_put;
	}
L
Linus Torvalds 已提交
1321

1322
	return 0;
L
Linus Torvalds 已提交
1323

1324
 out_blkdev_put:
A
Al Viro 已提交
1325
	blkdev_put(bdev, filp->f_mode);
L
Linus Torvalds 已提交
1326 1327 1328
	return res;
}

A
Al Viro 已提交
1329
static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
1330 1331 1332
{
	int ret = 0;
	struct gendisk *disk = bdev->bd_disk;
1333
	struct block_device *victim = NULL;
1334

1335
	mutex_lock_nested(&bdev->bd_mutex, for_part);
1336
	lock_kernel();
1337 1338 1339
	if (for_part)
		bdev->bd_part_count--;

1340 1341 1342 1343 1344 1345
	if (!--bdev->bd_openers) {
		sync_blockdev(bdev);
		kill_bdev(bdev);
	}
	if (bdev->bd_contains == bdev) {
		if (disk->fops->release)
A
Al Viro 已提交
1346
			ret = disk->fops->release(disk, mode);
1347 1348 1349 1350 1351 1352
	}
	if (!bdev->bd_openers) {
		struct module *owner = disk->fops->owner;

		put_disk(disk);
		module_put(owner);
T
Tejun Heo 已提交
1353 1354
		disk_put_part(bdev->bd_part);
		bdev->bd_part = NULL;
1355 1356
		bdev->bd_disk = NULL;
		bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
1357 1358
		if (bdev != bdev->bd_contains)
			victim = bdev->bd_contains;
1359 1360 1361 1362 1363
		bdev->bd_contains = NULL;
	}
	unlock_kernel();
	mutex_unlock(&bdev->bd_mutex);
	bdput(bdev);
1364
	if (victim)
A
Al Viro 已提交
1365
		__blkdev_put(victim, mode, 1);
1366 1367 1368
	return ret;
}

A
Al Viro 已提交
1369
int blkdev_put(struct block_device *bdev, fmode_t mode)
1370
{
A
Al Viro 已提交
1371
	return __blkdev_put(bdev, mode, 0);
1372
}
1373 1374
EXPORT_SYMBOL(blkdev_put);

L
Linus Torvalds 已提交
1375 1376 1377 1378 1379
static int blkdev_close(struct inode * inode, struct file * filp)
{
	struct block_device *bdev = I_BDEV(filp->f_mapping->host);
	if (bdev->bd_holder == filp)
		bd_release(bdev);
A
Al Viro 已提交
1380
	return blkdev_put(bdev, filp->f_mode);
L
Linus Torvalds 已提交
1381 1382
}

1383
static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
L
Linus Torvalds 已提交
1384
{
1385 1386
	struct block_device *bdev = I_BDEV(file->f_mapping->host);
	fmode_t mode = file->f_mode;
1387 1388 1389 1390 1391

	/*
	 * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have
	 * to updated it before every ioctl.
	 */
1392
	if (file->f_flags & O_NDELAY)
1393 1394 1395 1396
		mode |= FMODE_NDELAY;
	else
		mode &= ~FMODE_NDELAY;

1397
	return blkdev_ioctl(bdev, mode, cmd, arg);
L
Linus Torvalds 已提交
1398 1399
}

1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426
/*
 * 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.
 */
ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
			 unsigned long nr_segs, loff_t pos)
{
	struct file *file = iocb->ki_filp;
	ssize_t ret;

	BUG_ON(iocb->ki_pos != pos);

	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
	if (ret > 0 || ret == -EIOCBQUEUED) {
		ssize_t err;

		err = generic_write_sync(file, pos, ret);
		if (err < 0 && ret > 0)
			ret = err;
	}
	return ret;
}
EXPORT_SYMBOL_GPL(blkdev_aio_write);

1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440
/*
 * 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);
}

A
Adrian Bunk 已提交
1441
static const struct address_space_operations def_blk_aops = {
L
Linus Torvalds 已提交
1442 1443 1444
	.readpage	= blkdev_readpage,
	.writepage	= blkdev_writepage,
	.sync_page	= block_sync_page,
N
Nick Piggin 已提交
1445 1446
	.write_begin	= blkdev_write_begin,
	.write_end	= blkdev_write_end,
L
Linus Torvalds 已提交
1447
	.writepages	= generic_writepages,
1448
	.releasepage	= blkdev_releasepage,
L
Linus Torvalds 已提交
1449 1450 1451
	.direct_IO	= blkdev_direct_IO,
};

1452
const struct file_operations def_blk_fops = {
L
Linus Torvalds 已提交
1453 1454 1455
	.open		= blkdev_open,
	.release	= blkdev_close,
	.llseek		= block_llseek,
1456 1457
	.read		= do_sync_read,
	.write		= do_sync_write,
L
Linus Torvalds 已提交
1458
  	.aio_read	= generic_file_aio_read,
1459
	.aio_write	= blkdev_aio_write,
L
Linus Torvalds 已提交
1460 1461
	.mmap		= generic_file_mmap,
	.fsync		= block_fsync,
1462
	.unlocked_ioctl	= block_ioctl,
L
Linus Torvalds 已提交
1463 1464 1465
#ifdef CONFIG_COMPAT
	.compat_ioctl	= compat_blkdev_ioctl,
#endif
1466 1467
	.splice_read	= generic_file_splice_read,
	.splice_write	= generic_file_splice_write,
L
Linus Torvalds 已提交
1468 1469 1470 1471 1472 1473 1474
};

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);
1475
	res = blkdev_ioctl(bdev, 0, cmd, arg);
L
Linus Torvalds 已提交
1476 1477 1478 1479 1480 1481 1482 1483
	set_fs(old_fs);
	return res;
}

EXPORT_SYMBOL(ioctl_by_bdev);

/**
 * lookup_bdev  - lookup a struct block_device by name
1484
 * @pathname:	special file representing the block device
L
Linus Torvalds 已提交
1485
 *
1486
 * Get a reference to the blockdevice at @pathname in the current
L
Linus Torvalds 已提交
1487 1488 1489
 * namespace if possible and return it.  Return ERR_PTR(error)
 * otherwise.
 */
1490
struct block_device *lookup_bdev(const char *pathname)
L
Linus Torvalds 已提交
1491 1492 1493
{
	struct block_device *bdev;
	struct inode *inode;
1494
	struct path path;
L
Linus Torvalds 已提交
1495 1496
	int error;

1497
	if (!pathname || !*pathname)
L
Linus Torvalds 已提交
1498 1499
		return ERR_PTR(-EINVAL);

1500
	error = kern_path(pathname, LOOKUP_FOLLOW, &path);
L
Linus Torvalds 已提交
1501 1502 1503
	if (error)
		return ERR_PTR(error);

1504
	inode = path.dentry->d_inode;
L
Linus Torvalds 已提交
1505 1506 1507 1508
	error = -ENOTBLK;
	if (!S_ISBLK(inode->i_mode))
		goto fail;
	error = -EACCES;
1509
	if (path.mnt->mnt_flags & MNT_NODEV)
L
Linus Torvalds 已提交
1510 1511 1512 1513 1514 1515
		goto fail;
	error = -ENOMEM;
	bdev = bd_acquire(inode);
	if (!bdev)
		goto fail;
out:
1516
	path_put(&path);
L
Linus Torvalds 已提交
1517 1518 1519 1520 1521
	return bdev;
fail:
	bdev = ERR_PTR(error);
	goto out;
}
1522
EXPORT_SYMBOL(lookup_bdev);
L
Linus Torvalds 已提交
1523 1524

/**
1525
 * open_bdev_exclusive  -  open a block device by name and set it up for use
L
Linus Torvalds 已提交
1526 1527
 *
 * @path:	special file representing the block device
1528
 * @mode:	FMODE_... combination to pass be used
L
Linus Torvalds 已提交
1529 1530 1531 1532 1533
 * @holder:	owner for exclusion
 *
 * Open the blockdevice described by the special file at @path, claim it
 * for the @holder.
 */
1534
struct block_device *open_bdev_exclusive(const char *path, fmode_t mode, void *holder)
L
Linus Torvalds 已提交
1535 1536 1537 1538 1539 1540 1541 1542
{
	struct block_device *bdev;
	int error = 0;

	bdev = lookup_bdev(path);
	if (IS_ERR(bdev))
		return bdev;

1543
	error = blkdev_get(bdev, mode);
L
Linus Torvalds 已提交
1544 1545 1546
	if (error)
		return ERR_PTR(error);
	error = -EACCES;
1547
	if ((mode & FMODE_WRITE) && bdev_read_only(bdev))
L
Linus Torvalds 已提交
1548 1549 1550 1551 1552 1553 1554 1555
		goto blkdev_put;
	error = bd_claim(bdev, holder);
	if (error)
		goto blkdev_put;

	return bdev;
	
blkdev_put:
A
Al Viro 已提交
1556
	blkdev_put(bdev, mode);
L
Linus Torvalds 已提交
1557 1558 1559
	return ERR_PTR(error);
}

1560
EXPORT_SYMBOL(open_bdev_exclusive);
L
Linus Torvalds 已提交
1561 1562

/**
1563
 * close_bdev_exclusive  -  close a blockdevice opened by open_bdev_exclusive()
L
Linus Torvalds 已提交
1564 1565
 *
 * @bdev:	blockdevice to close
1566
 * @mode:	mode, must match that used to open.
L
Linus Torvalds 已提交
1567
 *
1568
 * This is the counterpart to open_bdev_exclusive().
L
Linus Torvalds 已提交
1569
 */
1570
void close_bdev_exclusive(struct block_device *bdev, fmode_t mode)
L
Linus Torvalds 已提交
1571 1572
{
	bd_release(bdev);
1573
	blkdev_put(bdev, mode);
L
Linus Torvalds 已提交
1574 1575
}

1576
EXPORT_SYMBOL(close_bdev_exclusive);
1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593

int __invalidate_device(struct block_device *bdev)
{
	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);
		res = invalidate_inodes(sb);
		drop_super(sb);
	}
1594
	invalidate_bdev(bdev);
1595 1596 1597
	return res;
}
EXPORT_SYMBOL(__invalidate_device);