block_dev.c 30.3 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19
/*
 *  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>
#include <linux/highmem.h>
#include <linux/blkdev.h>
#include <linux/module.h>
#include <linux/blkpg.h>
#include <linux/buffer_head.h>
20
#include <linux/writeback.h>
L
Linus Torvalds 已提交
21 22 23 24
#include <linux/mpage.h>
#include <linux/mount.h>
#include <linux/uio.h>
#include <linux/namei.h>
25
#include <linux/log2.h>
L
Linus Torvalds 已提交
26
#include <asm/uaccess.h>
27
#include "internal.h"
L
Linus Torvalds 已提交
28 29 30 31 32 33

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

A
Adrian Bunk 已提交
34 35
static const struct address_space_operations def_blk_aops;

L
Linus Torvalds 已提交
36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60
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
61
/* Kill _all_ buffers and pagecache , dirty or not.. */
L
Linus Torvalds 已提交
62 63
static void kill_bdev(struct block_device *bdev)
{
P
Peter Zijlstra 已提交
64 65 66
	if (bdev->bd_inode->i_mapping->nrpages == 0)
		return;
	invalidate_bh_lrus();
L
Linus Torvalds 已提交
67 68 69 70 71 72
	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 */
73
	if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size))
L
Linus Torvalds 已提交
74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98
		return -EINVAL;

	/* Size cannot be smaller than the size supported by the device */
	if (size < bdev_hardsect_size(bdev))
		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;
99
	sb->s_blocksize_bits = blksize_bits(size);
L
Linus Torvalds 已提交
100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136
	return sb->s_blocksize;
}

EXPORT_SYMBOL(sb_set_blocksize);

int sb_min_blocksize(struct super_block *sb, int size)
{
	int minsize = bdev_hardsect_size(sb->s_bdev);
	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;
}

137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175
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);
}

L
Linus Torvalds 已提交
176 177 178 179 180 181 182 183 184 185
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
186 187 188
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
189
{
N
Nick Piggin 已提交
190 191 192
	*pagep = NULL;
	return block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
				blkdev_get_block);
L
Linus Torvalds 已提交
193 194
}

N
Nick Piggin 已提交
195 196 197
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
198
{
N
Nick Piggin 已提交
199 200 201 202 203 204 205
	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
206 207 208 209
}

/*
 * private llseek:
210
 * for a block special file file->f_path.dentry->d_inode->i_size is zero
L
Linus Torvalds 已提交
211 212 213 214 215 216 217 218
 * 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;

219
	mutex_lock(&bd_inode->i_mutex);
L
Linus Torvalds 已提交
220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235
	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;
	}
236
	mutex_unlock(&bd_inode->i_mutex);
L
Linus Torvalds 已提交
237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254
	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);
255
static struct kmem_cache * bdev_cachep __read_mostly;
L
Linus Torvalds 已提交
256 257 258

static struct inode *bdev_alloc_inode(struct super_block *sb)
{
259
	struct bdev_inode *ei = kmem_cache_alloc(bdev_cachep, GFP_KERNEL);
L
Linus Torvalds 已提交
260 261 262 263 264 265 266 267 268 269 270 271 272
	if (!ei)
		return NULL;
	return &ei->vfs_inode;
}

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

	bdi->bdev.bd_inode_backing_dev_info = NULL;
	kmem_cache_free(bdev_cachep, bdi);
}

273
static void init_once(struct kmem_cache * cachep, void *foo)
L
Linus Torvalds 已提交
274 275 276 277
{
	struct bdev_inode *ei = (struct bdev_inode *) foo;
	struct block_device *bdev = &ei->bdev;

C
Christoph Lameter 已提交
278 279 280 281 282
	memset(bdev, 0, sizeof(*bdev));
	mutex_init(&bdev->bd_mutex);
	sema_init(&bdev->bd_mount_sem, 1);
	INIT_LIST_HEAD(&bdev->bd_inodes);
	INIT_LIST_HEAD(&bdev->bd_list);
283
#ifdef CONFIG_SYSFS
C
Christoph Lameter 已提交
284
	INIT_LIST_HEAD(&bdev->bd_holder_list);
285
#endif
C
Christoph Lameter 已提交
286
	inode_init_once(&ei->vfs_inode);
L
Linus Torvalds 已提交
287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307
}

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);
}

308
static const struct super_operations bdev_sops = {
L
Linus Torvalds 已提交
309 310 311 312 313 314 315
	.statfs = simple_statfs,
	.alloc_inode = bdev_alloc_inode,
	.destroy_inode = bdev_destroy_inode,
	.drop_inode = generic_delete_inode,
	.clear_inode = bdev_clear_inode,
};

316 317
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
318
{
319
	return get_sb_pseudo(fs_type, "bdev:", &bdev_sops, 0x62646576, mnt);
L
Linus Torvalds 已提交
320 321 322 323 324 325 326 327
}

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

328
static struct vfsmount *bd_mnt __read_mostly;
L
Linus Torvalds 已提交
329 330 331 332 333 334
struct super_block *blockdev_superblock;

void __init bdev_cache_init(void)
{
	int err;
	bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode),
335 336
			0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
				SLAB_MEM_SPREAD|SLAB_PANIC),
337
			init_once);
L
Linus Torvalds 已提交
338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406
	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");
	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;

	inode = iget5_locked(bd_mnt->mnt_sb, hash(dev),
			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);

long nr_blockdev_pages(void)
{
407
	struct block_device *bdev;
L
Linus Torvalds 已提交
408 409
	long ret = 0;
	spin_lock(&bdev_lock);
410
	list_for_each_entry(bdev, &all_bdevs, bd_list) {
L
Linus Torvalds 已提交
411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426
		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;
427

L
Linus Torvalds 已提交
428 429
	spin_lock(&bdev_lock);
	bdev = inode->i_bdev;
430 431
	if (bdev) {
		atomic_inc(&bdev->bd_inode->i_count);
L
Linus Torvalds 已提交
432 433 434 435
		spin_unlock(&bdev_lock);
		return bdev;
	}
	spin_unlock(&bdev_lock);
436

L
Linus Torvalds 已提交
437 438 439
	bdev = bdget(inode->i_rdev);
	if (bdev) {
		spin_lock(&bdev_lock);
440 441 442 443 444 445 446 447 448 449 450 451
		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
452 453 454 455 456 457 458 459 460
		spin_unlock(&bdev_lock);
	}
	return bdev;
}

/* Call when you free inode */

void bd_forget(struct inode *inode)
{
461 462
	struct block_device *bdev = NULL;

L
Linus Torvalds 已提交
463
	spin_lock(&bdev_lock);
464 465 466
	if (inode->i_bdev) {
		if (inode->i_sb != blockdev_superblock)
			bdev = inode->i_bdev;
L
Linus Torvalds 已提交
467
		__bd_forget(inode);
468
	}
L
Linus Torvalds 已提交
469
	spin_unlock(&bdev_lock);
470 471 472

	if (bdev)
		iput(bdev->bd_inode);
L
Linus Torvalds 已提交
473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523
}

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);

524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544
#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
 */

static struct kobject *bdev_get_kobj(struct block_device *bdev)
{
	if (bdev->bd_contains != bdev)
545
		return kobject_get(&bdev->bd_part->dev.kobj);
546
	else
547
		return kobject_get(&bdev->bd_disk->dev.kobj);
548 549 550 551 552 553 554 555 556 557
}

static struct kobject *bdev_get_holder(struct block_device *bdev)
{
	if (bdev->bd_contains != bdev)
		return kobject_get(bdev->bd_part->holder_dir);
	else
		return kobject_get(bdev->bd_disk->holder_dir);
}

558
static int add_symlink(struct kobject *from, struct kobject *to)
559 560
{
	if (!from || !to)
561 562
		return 0;
	return sysfs_create_link(from, to, kobject_name(to));
563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653
}

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;

	bo->sdev = bdev_get_kobj(bdev);
	if (!bo->sdev)
		goto fail_put_hdev;

	bo->hdir = bdev_get_holder(bdev);
	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
654 655 656 657 658 659 660 661 662 663
/**
 * 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
664 665
static struct bd_holder *find_bd_holder(struct block_device *bdev,
					struct bd_holder *bo)
J
Jun'ichi Nomura 已提交
666 667 668 669 670 671 672 673 674 675 676 677
{
	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;
}

678 679 680 681 682 683
/**
 * 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
684
 * Add @bo to @bdev->bd_holder_list, create symlinks.
685
 *
J
Jun'ichi Nomura 已提交
686 687
 * Returns 0 if symlinks are created.
 * Returns -ve if something fails.
688 689 690
 */
static int add_bd_holder(struct block_device *bdev, struct bd_holder *bo)
{
691
	int err;
692 693

	if (!bo)
694
		return -EINVAL;
695 696

	if (!bd_holder_grab_dirs(bdev, bo))
697
		return -EBUSY;
698

699 700 701 702 703 704 705 706
	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;
707
	}
708 709 710

	list_add_tail(&bo->list, &bdev->bd_holder_list);
	return 0;
711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767
}

/**
 * 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)
{
768
	int err;
J
Jun'ichi Nomura 已提交
769
	struct bd_holder *bo, *found;
770 771 772 773 774 775 776 777

	if (!kobj)
		return -EINVAL;

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

778
	mutex_lock(&bdev->bd_mutex);
J
Jun'ichi Nomura 已提交
779

780 781
	err = bd_claim(bdev, holder);
	if (err)
A
Andrew Morton 已提交
782
		goto fail;
783 784 785

	found = find_bd_holder(bdev, bo);
	if (found)
A
Andrew Morton 已提交
786
		goto fail;
787 788 789 790

	err = add_bd_holder(bdev, bo);
	if (err)
		bd_release(bdev);
A
Andrew Morton 已提交
791 792 793
	else
		bo = NULL;
fail:
794
	mutex_unlock(&bdev->bd_mutex);
A
Andrew Morton 已提交
795
	free_bd_holder(bo);
796
	return err;
797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812
}

/**
 * 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;

813
	mutex_lock(&bdev->bd_mutex);
814
	bd_release(bdev);
A
Andrew Morton 已提交
815
	free_bd_holder(del_bd_holder(bdev, kobj));
816
	mutex_unlock(&bdev->bd_mutex);
817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850
}

/**
 * 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
851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888
/*
 * 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.
 */
struct block_device *open_by_devnum(dev_t dev, unsigned mode)
{
	struct block_device *bdev = bdget(dev);
	int err = -ENOMEM;
	int flags = mode & FMODE_WRITE ? O_RDWR : O_RDONLY;
	if (bdev)
		err = blkdev_get(bdev, mode, flags);
	return err ? ERR_PTR(err) : bdev;
}

EXPORT_SYMBOL(open_by_devnum);

/*
 * 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;
	struct block_device_operations * bdops = disk->fops;

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

889
	if (__invalidate_device(bdev))
L
Linus Torvalds 已提交
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
		printk("VFS: busy inodes on changed media.\n");

	if (bdops->revalidate_disk)
		bdops->revalidate_disk(bdev->bd_disk);
	if (bdev->bd_disk->minors > 1)
		bdev->bd_invalidated = 1;
	return 1;
}

EXPORT_SYMBOL(check_disk_change);

void bd_set_size(struct block_device *bdev, loff_t size)
{
	unsigned bsize = bdev_hardsect_size(bdev);

	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);

916 917
static int __blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags,
			int for_part);
918
static int __blkdev_put(struct block_device *bdev, int for_part);
919

920 921 922 923 924 925 926
/*
 * bd_mutex locking:
 *
 *  mutex_lock(part->bd_mutex)
 *    mutex_lock_nested(whole->bd_mutex, 1)
 */

927
static int do_open(struct block_device *bdev, struct file *file, int for_part)
L
Linus Torvalds 已提交
928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943
{
	struct module *owner = NULL;
	struct gendisk *disk;
	int ret = -ENXIO;
	int part;

	file->f_mapping = bdev->bd_inode->i_mapping;
	lock_kernel();
	disk = get_gendisk(bdev->bd_dev, &part);
	if (!disk) {
		unlock_kernel();
		bdput(bdev);
		return ret;
	}
	owner = disk->fops->owner;

944
	mutex_lock_nested(&bdev->bd_mutex, for_part);
L
Linus Torvalds 已提交
945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970
	if (!bdev->bd_openers) {
		bdev->bd_disk = disk;
		bdev->bd_contains = bdev;
		if (!part) {
			struct backing_dev_info *bdi;
			if (disk->fops->open) {
				ret = disk->fops->open(bdev->bd_inode, file);
				if (ret)
					goto out_first;
			}
			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 hd_struct *p;
			struct block_device *whole;
			whole = bdget_disk(disk, 0);
			ret = -ENOMEM;
			if (!whole)
				goto out_first;
971 972
			BUG_ON(for_part);
			ret = __blkdev_get(whole, file->f_mode, file->f_flags, 1);
L
Linus Torvalds 已提交
973 974 975 976 977 978 979 980 981 982
			if (ret)
				goto out_first;
			bdev->bd_contains = whole;
			p = disk->part[part - 1];
			bdev->bd_inode->i_data.backing_dev_info =
			   whole->bd_inode->i_data.backing_dev_info;
			if (!(disk->flags & GENHD_FL_UP) || !p || !p->nr_sects) {
				ret = -ENXIO;
				goto out_first;
			}
983
			kobject_get(&p->dev.kobj);
L
Linus Torvalds 已提交
984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000
			bdev->bd_part = p;
			bd_set_size(bdev, (loff_t) p->nr_sects << 9);
		}
	} else {
		put_disk(disk);
		module_put(owner);
		if (bdev->bd_contains == bdev) {
			if (bdev->bd_disk->fops->open) {
				ret = bdev->bd_disk->fops->open(bdev->bd_inode, file);
				if (ret)
					goto out;
			}
			if (bdev->bd_invalidated)
				rescan_partitions(bdev->bd_disk, bdev);
		}
	}
	bdev->bd_openers++;
1001 1002
	if (for_part)
		bdev->bd_part_count++;
1003
	mutex_unlock(&bdev->bd_mutex);
L
Linus Torvalds 已提交
1004 1005 1006 1007 1008 1009 1010
	unlock_kernel();
	return 0;

out_first:
	bdev->bd_disk = NULL;
	bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
	if (bdev != bdev->bd_contains)
1011
		__blkdev_put(bdev->bd_contains, 1);
L
Linus Torvalds 已提交
1012 1013 1014 1015
	bdev->bd_contains = NULL;
	put_disk(disk);
	module_put(owner);
out:
1016
	mutex_unlock(&bdev->bd_mutex);
L
Linus Torvalds 已提交
1017 1018 1019 1020 1021 1022
	unlock_kernel();
	if (ret)
		bdput(bdev);
	return ret;
}

1023 1024
static int __blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags,
			int for_part)
L
Linus Torvalds 已提交
1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035
{
	/*
	 * This crockload is due to bad choice of ->open() type.
	 * It will go away.
	 * For now, block device ->open() routine must _not_
	 * examine anything in 'inode' argument except ->i_rdev.
	 */
	struct file fake_file = {};
	struct dentry fake_dentry = {};
	fake_file.f_mode = mode;
	fake_file.f_flags = flags;
1036
	fake_file.f_path.dentry = &fake_dentry;
L
Linus Torvalds 已提交
1037 1038
	fake_dentry.d_inode = bdev->bd_inode;

1039
	return do_open(bdev, &fake_file, for_part);
L
Linus Torvalds 已提交
1040 1041
}

1042 1043 1044 1045
int blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags)
{
	return __blkdev_get(bdev, mode, flags, 0);
}
L
Linus Torvalds 已提交
1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061
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;

	bdev = bd_acquire(inode);
1062 1063
	if (bdev == NULL)
		return -ENOMEM;
L
Linus Torvalds 已提交
1064

1065
	res = do_open(bdev, filp, 0);
L
Linus Torvalds 已提交
1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078
	if (res)
		return res;

	if (!(filp->f_flags & O_EXCL) )
		return 0;

	if (!(res = bd_claim(bdev, filp)))
		return 0;

	blkdev_put(bdev);
	return res;
}

1079
static int __blkdev_put(struct block_device *bdev, int for_part)
1080 1081 1082 1083
{
	int ret = 0;
	struct inode *bd_inode = bdev->bd_inode;
	struct gendisk *disk = bdev->bd_disk;
1084
	struct block_device *victim = NULL;
1085

1086
	mutex_lock_nested(&bdev->bd_mutex, for_part);
1087
	lock_kernel();
1088 1089 1090
	if (for_part)
		bdev->bd_part_count--;

1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105
	if (!--bdev->bd_openers) {
		sync_blockdev(bdev);
		kill_bdev(bdev);
	}
	if (bdev->bd_contains == bdev) {
		if (disk->fops->release)
			ret = disk->fops->release(bd_inode, NULL);
	}
	if (!bdev->bd_openers) {
		struct module *owner = disk->fops->owner;

		put_disk(disk);
		module_put(owner);

		if (bdev->bd_contains != bdev) {
1106
			kobject_put(&bdev->bd_part->dev.kobj);
1107 1108 1109 1110
			bdev->bd_part = NULL;
		}
		bdev->bd_disk = NULL;
		bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
1111 1112
		if (bdev != bdev->bd_contains)
			victim = bdev->bd_contains;
1113 1114 1115 1116 1117
		bdev->bd_contains = NULL;
	}
	unlock_kernel();
	mutex_unlock(&bdev->bd_mutex);
	bdput(bdev);
1118 1119
	if (victim)
		__blkdev_put(victim, 1);
1120 1121 1122
	return ret;
}

1123 1124 1125 1126
int blkdev_put(struct block_device *bdev)
{
	return __blkdev_put(bdev, 0);
}
1127 1128
EXPORT_SYMBOL(blkdev_put);

L
Linus Torvalds 已提交
1129 1130 1131 1132 1133 1134 1135 1136
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);
	return blkdev_put(bdev);
}

1137
static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
L
Linus Torvalds 已提交
1138 1139 1140 1141
{
	return blkdev_ioctl(file->f_mapping->host, file, cmd, arg);
}

A
Adrian Bunk 已提交
1142
static const struct address_space_operations def_blk_aops = {
L
Linus Torvalds 已提交
1143 1144 1145
	.readpage	= blkdev_readpage,
	.writepage	= blkdev_writepage,
	.sync_page	= block_sync_page,
N
Nick Piggin 已提交
1146 1147
	.write_begin	= blkdev_write_begin,
	.write_end	= blkdev_write_end,
L
Linus Torvalds 已提交
1148 1149 1150 1151
	.writepages	= generic_writepages,
	.direct_IO	= blkdev_direct_IO,
};

1152
const struct file_operations def_blk_fops = {
L
Linus Torvalds 已提交
1153 1154 1155
	.open		= blkdev_open,
	.release	= blkdev_close,
	.llseek		= block_llseek,
1156 1157
	.read		= do_sync_read,
	.write		= do_sync_write,
L
Linus Torvalds 已提交
1158
  	.aio_read	= generic_file_aio_read,
1159
  	.aio_write	= generic_file_aio_write_nolock,
L
Linus Torvalds 已提交
1160 1161
	.mmap		= generic_file_mmap,
	.fsync		= block_fsync,
1162
	.unlocked_ioctl	= block_ioctl,
L
Linus Torvalds 已提交
1163 1164 1165
#ifdef CONFIG_COMPAT
	.compat_ioctl	= compat_blkdev_ioctl,
#endif
1166 1167
	.splice_read	= generic_file_splice_read,
	.splice_write	= generic_file_splice_write,
L
Linus Torvalds 已提交
1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204
};

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);
	res = blkdev_ioctl(bdev->bd_inode, NULL, cmd, arg);
	set_fs(old_fs);
	return res;
}

EXPORT_SYMBOL(ioctl_by_bdev);

/**
 * lookup_bdev  - lookup a struct block_device by name
 *
 * @path:	special file representing the block device
 *
 * Get a reference to the blockdevice at @path in the current
 * namespace if possible and return it.  Return ERR_PTR(error)
 * otherwise.
 */
struct block_device *lookup_bdev(const char *path)
{
	struct block_device *bdev;
	struct inode *inode;
	struct nameidata nd;
	int error;

	if (!path || !*path)
		return ERR_PTR(-EINVAL);

	error = path_lookup(path, LOOKUP_FOLLOW, &nd);
	if (error)
		return ERR_PTR(error);

1205
	inode = nd.path.dentry->d_inode;
L
Linus Torvalds 已提交
1206 1207 1208 1209
	error = -ENOTBLK;
	if (!S_ISBLK(inode->i_mode))
		goto fail;
	error = -EACCES;
1210
	if (nd.path.mnt->mnt_flags & MNT_NODEV)
L
Linus Torvalds 已提交
1211 1212 1213 1214 1215 1216
		goto fail;
	error = -ENOMEM;
	bdev = bd_acquire(inode);
	if (!bdev)
		goto fail;
out:
J
Jan Blunck 已提交
1217
	path_put(&nd.path);
L
Linus Torvalds 已提交
1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278
	return bdev;
fail:
	bdev = ERR_PTR(error);
	goto out;
}

/**
 * open_bdev_excl  -  open a block device by name and set it up for use
 *
 * @path:	special file representing the block device
 * @flags:	%MS_RDONLY for opening read-only
 * @holder:	owner for exclusion
 *
 * Open the blockdevice described by the special file at @path, claim it
 * for the @holder.
 */
struct block_device *open_bdev_excl(const char *path, int flags, void *holder)
{
	struct block_device *bdev;
	mode_t mode = FMODE_READ;
	int error = 0;

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

	if (!(flags & MS_RDONLY))
		mode |= FMODE_WRITE;
	error = blkdev_get(bdev, mode, 0);
	if (error)
		return ERR_PTR(error);
	error = -EACCES;
	if (!(flags & MS_RDONLY) && bdev_read_only(bdev))
		goto blkdev_put;
	error = bd_claim(bdev, holder);
	if (error)
		goto blkdev_put;

	return bdev;
	
blkdev_put:
	blkdev_put(bdev);
	return ERR_PTR(error);
}

EXPORT_SYMBOL(open_bdev_excl);

/**
 * close_bdev_excl  -  release a blockdevice openen by open_bdev_excl()
 *
 * @bdev:	blockdevice to close
 *
 * This is the counterpart to open_bdev_excl().
 */
void close_bdev_excl(struct block_device *bdev)
{
	bd_release(bdev);
	blkdev_put(bdev);
}

EXPORT_SYMBOL(close_bdev_excl);
1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295

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);
	}
1296
	invalidate_bdev(bdev);
1297 1298 1299
	return res;
}
EXPORT_SYMBOL(__invalidate_device);