block_dev.c 31.5 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 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91
/*
 *  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>
#include <linux/mpage.h>
#include <linux/mount.h>
#include <linux/uio.h>
#include <linux/namei.h>
#include <asm/uaccess.h>

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

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;
}

/* Kill _all_ buffers, dirty or not.. */
static void kill_bdev(struct block_device *bdev)
{
	invalidate_bdev(bdev, 1);
	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 */
	if (size > PAGE_SIZE || size < 512 || (size & (size-1)))
		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;
92
	sb->s_blocksize_bits = blksize_bits(size);
L
Linus Torvalds 已提交
93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131
	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;
}

static int
blkdev_get_blocks(struct inode *inode, sector_t iblock,
132
		struct buffer_head *bh, int create)
L
Linus Torvalds 已提交
133 134
{
	sector_t end_block = max_block(I_BDEV(inode));
135
	unsigned long max_blocks = bh->b_size >> inode->i_blkbits;
L
Linus Torvalds 已提交
136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199

	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);
}

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);
}

static int blkdev_prepare_write(struct file *file, struct page *page, unsigned from, unsigned to)
{
	return block_prepare_write(page, from, to, blkdev_get_block);
}

static int blkdev_commit_write(struct file *file, struct page *page, unsigned from, unsigned to)
{
	return block_commit_write(page, from, to);
}

/*
 * private llseek:
 * for a block special file file->f_dentry->d_inode->i_size is zero
 * 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;

200
	mutex_lock(&bd_inode->i_mutex);
L
Linus Torvalds 已提交
201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216
	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;
	}
217
	mutex_unlock(&bd_inode->i_mutex);
L
Linus Torvalds 已提交
218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235
	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);
236
static kmem_cache_t * bdev_cachep __read_mostly;
L
Linus Torvalds 已提交
237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262

static struct inode *bdev_alloc_inode(struct super_block *sb)
{
	struct bdev_inode *ei = kmem_cache_alloc(bdev_cachep, SLAB_KERNEL);
	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);
}

static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags)
{
	struct bdev_inode *ei = (struct bdev_inode *) foo;
	struct block_device *bdev = &ei->bdev;

	if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
	    SLAB_CTOR_CONSTRUCTOR)
	{
		memset(bdev, 0, sizeof(*bdev));
263 264
		mutex_init(&bdev->bd_mutex);
		mutex_init(&bdev->bd_mount_mutex);
L
Linus Torvalds 已提交
265 266
		INIT_LIST_HEAD(&bdev->bd_inodes);
		INIT_LIST_HEAD(&bdev->bd_list);
267 268 269
#ifdef CONFIG_SYSFS
		INIT_LIST_HEAD(&bdev->bd_holder_list);
#endif
L
Linus Torvalds 已提交
270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300
		inode_init_once(&ei->vfs_inode);
	}
}

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);
}

static struct super_operations bdev_sops = {
	.statfs = simple_statfs,
	.alloc_inode = bdev_alloc_inode,
	.destroy_inode = bdev_destroy_inode,
	.drop_inode = generic_delete_inode,
	.clear_inode = bdev_clear_inode,
};

301 302
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
303
{
304
	return get_sb_pseudo(fs_type, "bdev:", &bdev_sops, 0x62646576, mnt);
L
Linus Torvalds 已提交
305 306 307 308 309 310 311 312
}

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

313
static struct vfsmount *bd_mnt __read_mostly;
L
Linus Torvalds 已提交
314 315 316 317 318 319
struct super_block *blockdev_superblock;

void __init bdev_cache_init(void)
{
	int err;
	bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode),
320 321
			0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
				SLAB_MEM_SPREAD|SLAB_PANIC),
L
Linus Torvalds 已提交
322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414
			init_once, NULL);
	err = register_filesystem(&bd_type);
	if (err)
		panic("Cannot register bdev pseudo-fs");
	bd_mnt = kern_mount(&bd_type);
	err = PTR_ERR(bd_mnt);
	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)
{
	struct list_head *p;
	long ret = 0;
	spin_lock(&bdev_lock);
	list_for_each(p, &all_bdevs) {
		struct block_device *bdev;
		bdev = list_entry(p, struct block_device, bd_list);
		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;
415

L
Linus Torvalds 已提交
416 417
	spin_lock(&bdev_lock);
	bdev = inode->i_bdev;
418 419
	if (bdev) {
		atomic_inc(&bdev->bd_inode->i_count);
L
Linus Torvalds 已提交
420 421 422 423
		spin_unlock(&bdev_lock);
		return bdev;
	}
	spin_unlock(&bdev_lock);
424

L
Linus Torvalds 已提交
425 426 427
	bdev = bdget(inode->i_rdev);
	if (bdev) {
		spin_lock(&bdev_lock);
428 429 430 431 432 433 434 435 436 437 438 439
		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
440 441 442 443 444 445 446 447 448
		spin_unlock(&bdev_lock);
	}
	return bdev;
}

/* Call when you free inode */

void bd_forget(struct inode *inode)
{
449 450
	struct block_device *bdev = NULL;

L
Linus Torvalds 已提交
451
	spin_lock(&bdev_lock);
452 453 454
	if (inode->i_bdev) {
		if (inode->i_sb != blockdev_superblock)
			bdev = inode->i_bdev;
L
Linus Torvalds 已提交
455
		__bd_forget(inode);
456
	}
L
Linus Torvalds 已提交
457
	spin_unlock(&bdev_lock);
458 459 460

	if (bdev)
		iput(bdev->bd_inode);
L
Linus Torvalds 已提交
461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511
}

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);

512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545
#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)
		return kobject_get(&bdev->bd_part->kobj);
	else
		return kobject_get(&bdev->bd_disk->kobj);
}

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);
}

546
static int add_symlink(struct kobject *from, struct kobject *to)
547 548
{
	if (!from || !to)
549 550
		return 0;
	return sysfs_create_link(from, to, kobject_name(to));
551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650
}

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);
}

/**
 * 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()
 *
 * If there is no matching entry with @bo in @bdev->bd_holder_list,
 * add @bo to the list, create symlinks.
 *
651 652
 * Returns 0 if symlinks are created or already there.
 * Returns -ve if something fails and @bo can be freed.
653 654 655 656
 */
static int add_bd_holder(struct block_device *bdev, struct bd_holder *bo)
{
	struct bd_holder *tmp;
657
	int ret;
658 659

	if (!bo)
660
		return -EINVAL;
661 662 663 664

	list_for_each_entry(tmp, &bdev->bd_holder_list, list) {
		if (tmp->sdir == bo->sdir) {
			tmp->count++;
665 666
			/* We've already done what we need to do here. */
			free_bd_holder(bo);
667 668 669 670 671
			return 0;
		}
	}

	if (!bd_holder_grab_dirs(bdev, bo))
672
		return -EBUSY;
673

674 675 676 677 678 679 680 681 682
	ret = add_symlink(bo->sdir, bo->sdev);
	if (ret == 0) {
		ret = add_symlink(bo->hdir, bo->hdev);
		if (ret)
			del_symlink(bo->sdir, bo->sdev);
	}
	if (ret == 0)
		list_add_tail(&bo->list, &bdev->bd_holder_list);
	return ret;
683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749
}

/**
 * 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)
{
	int res;
	struct bd_holder *bo;

	if (!kobj)
		return -EINVAL;

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

750
	mutex_lock_nested(&bdev->bd_mutex, BD_MUTEX_PARTITION);
751
	res = bd_claim(bdev, holder);
752 753 754
	if (res == 0)
		res = add_bd_holder(bdev, bo);
	if (res)
755
		free_bd_holder(bo);
756
	mutex_unlock(&bdev->bd_mutex);
757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776

	return res;
}

/**
 * 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)
{
	struct bd_holder *bo;

	if (!kobj)
		return;

777
	mutex_lock_nested(&bdev->bd_mutex, BD_MUTEX_PARTITION);
778 779 780
	bd_release(bdev);
	if ((bo = del_bd_holder(bdev, kobj)))
		free_bd_holder(bo);
781
	mutex_unlock(&bdev->bd_mutex);
782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815
}

/**
 * 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
816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834
/*
 * 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);

835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850
static int
blkdev_get_partition(struct block_device *bdev, mode_t mode, unsigned flags);

struct block_device *open_partition_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_partition(bdev, mode, flags);
	return err ? ERR_PTR(err) : bdev;
}

EXPORT_SYMBOL(open_partition_by_devnum);


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
/*
 * 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;

870
	if (__invalidate_device(bdev))
L
Linus Torvalds 已提交
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
		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);

897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951
static int __blkdev_put(struct block_device *bdev, unsigned int subclass)
{
	int ret = 0;
	struct inode *bd_inode = bdev->bd_inode;
	struct gendisk *disk = bdev->bd_disk;

	mutex_lock_nested(&bdev->bd_mutex, subclass);
	lock_kernel();
	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);
	} else {
		mutex_lock_nested(&bdev->bd_contains->bd_mutex,
				  subclass + 1);
		bdev->bd_contains->bd_part_count--;
		mutex_unlock(&bdev->bd_contains->bd_mutex);
	}
	if (!bdev->bd_openers) {
		struct module *owner = disk->fops->owner;

		put_disk(disk);
		module_put(owner);

		if (bdev->bd_contains != bdev) {
			kobject_put(&bdev->bd_part->kobj);
			bdev->bd_part = NULL;
		}
		bdev->bd_disk = NULL;
		bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
		if (bdev != bdev->bd_contains)
			__blkdev_put(bdev->bd_contains, subclass + 1);
		bdev->bd_contains = NULL;
	}
	unlock_kernel();
	mutex_unlock(&bdev->bd_mutex);
	bdput(bdev);
	return ret;
}

int blkdev_put(struct block_device *bdev)
{
	return __blkdev_put(bdev, BD_MUTEX_NORMAL);
}
EXPORT_SYMBOL(blkdev_put);

int blkdev_put_partition(struct block_device *bdev)
{
	return __blkdev_put(bdev, BD_MUTEX_PARTITION);
}
EXPORT_SYMBOL(blkdev_put_partition);

952 953 954 955 956
static int
blkdev_get_whole(struct block_device *bdev, mode_t mode, unsigned flags);

static int
do_open(struct block_device *bdev, struct file *file, unsigned int subclass)
L
Linus Torvalds 已提交
957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972
{
	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;

973 974
	mutex_lock_nested(&bdev->bd_mutex, subclass);

L
Linus Torvalds 已提交
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 1000
	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;
1001
			ret = blkdev_get_whole(whole, file->f_mode, file->f_flags);
L
Linus Torvalds 已提交
1002 1003 1004
			if (ret)
				goto out_first;
			bdev->bd_contains = whole;
1005
			mutex_lock_nested(&whole->bd_mutex, BD_MUTEX_WHOLE);
L
Linus Torvalds 已提交
1006 1007 1008 1009 1010 1011
			whole->bd_part_count++;
			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) {
				whole->bd_part_count--;
1012
				mutex_unlock(&whole->bd_mutex);
L
Linus Torvalds 已提交
1013 1014 1015 1016 1017 1018
				ret = -ENXIO;
				goto out_first;
			}
			kobject_get(&p->kobj);
			bdev->bd_part = p;
			bd_set_size(bdev, (loff_t) p->nr_sects << 9);
1019
			mutex_unlock(&whole->bd_mutex);
L
Linus Torvalds 已提交
1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032
		}
	} 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);
		} else {
1033
			mutex_lock_nested(&bdev->bd_contains->bd_mutex,
1034
					  BD_MUTEX_WHOLE);
L
Linus Torvalds 已提交
1035
			bdev->bd_contains->bd_part_count++;
1036
			mutex_unlock(&bdev->bd_contains->bd_mutex);
L
Linus Torvalds 已提交
1037 1038 1039
		}
	}
	bdev->bd_openers++;
1040
	mutex_unlock(&bdev->bd_mutex);
L
Linus Torvalds 已提交
1041 1042 1043 1044 1045 1046 1047
	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)
1048
		__blkdev_put(bdev->bd_contains, BD_MUTEX_WHOLE);
L
Linus Torvalds 已提交
1049 1050 1051 1052
	bdev->bd_contains = NULL;
	put_disk(disk);
	module_put(owner);
out:
1053
	mutex_unlock(&bdev->bd_mutex);
L
Linus Torvalds 已提交
1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074
	unlock_kernel();
	if (ret)
		bdput(bdev);
	return ret;
}

int blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags)
{
	/*
	 * 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;
	fake_file.f_dentry = &fake_dentry;
	fake_dentry.d_inode = bdev->bd_inode;

1075
	return do_open(bdev, &fake_file, BD_MUTEX_NORMAL);
L
Linus Torvalds 已提交
1076 1077 1078 1079
}

EXPORT_SYMBOL(blkdev_get);

1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117
static int
blkdev_get_whole(struct block_device *bdev, mode_t mode, unsigned flags)
{
	/*
	 * 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;
	fake_file.f_dentry = &fake_dentry;
	fake_dentry.d_inode = bdev->bd_inode;

	return do_open(bdev, &fake_file, BD_MUTEX_WHOLE);
}

static int
blkdev_get_partition(struct block_device *bdev, mode_t mode, unsigned flags)
{
	/*
	 * 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;
	fake_file.f_dentry = &fake_dentry;
	fake_dentry.d_inode = bdev->bd_inode;

	return do_open(bdev, &fake_file, BD_MUTEX_PARTITION);
}

L
Linus Torvalds 已提交
1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132
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);

1133
	res = do_open(bdev, filp, BD_MUTEX_NORMAL);
L
Linus Torvalds 已提交
1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170
	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;
}

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);
}

static ssize_t blkdev_file_write(struct file *file, const char __user *buf,
				   size_t count, loff_t *ppos)
{
	struct iovec local_iov = { .iov_base = (void __user *)buf, .iov_len = count };

	return generic_file_write_nolock(file, &local_iov, 1, ppos);
}

static ssize_t blkdev_file_aio_write(struct kiocb *iocb, const char __user *buf,
				   size_t count, loff_t pos)
{
	struct iovec local_iov = { .iov_base = (void __user *)buf, .iov_len = count };

	return generic_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos);
}

1171
static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
L
Linus Torvalds 已提交
1172 1173 1174 1175
{
	return blkdev_ioctl(file->f_mapping->host, file, cmd, arg);
}

1176
const struct address_space_operations def_blk_aops = {
L
Linus Torvalds 已提交
1177 1178 1179 1180 1181 1182 1183 1184 1185
	.readpage	= blkdev_readpage,
	.writepage	= blkdev_writepage,
	.sync_page	= block_sync_page,
	.prepare_write	= blkdev_prepare_write,
	.commit_write	= blkdev_commit_write,
	.writepages	= generic_writepages,
	.direct_IO	= blkdev_direct_IO,
};

1186
const struct file_operations def_blk_fops = {
L
Linus Torvalds 已提交
1187 1188 1189 1190 1191 1192 1193 1194 1195
	.open		= blkdev_open,
	.release	= blkdev_close,
	.llseek		= block_llseek,
	.read		= generic_file_read,
	.write		= blkdev_file_write,
  	.aio_read	= generic_file_aio_read,
  	.aio_write	= blkdev_file_aio_write, 
	.mmap		= generic_file_mmap,
	.fsync		= block_fsync,
1196
	.unlocked_ioctl	= block_ioctl,
L
Linus Torvalds 已提交
1197 1198 1199 1200 1201 1202
#ifdef CONFIG_COMPAT
	.compat_ioctl	= compat_blkdev_ioctl,
#endif
	.readv		= generic_file_readv,
	.writev		= generic_file_write_nolock,
	.sendfile	= generic_file_sendfile,
1203 1204
	.splice_read	= generic_file_splice_read,
	.splice_write	= generic_file_splice_write,
L
Linus Torvalds 已提交
1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 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 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315
};

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);

	inode = nd.dentry->d_inode;
	error = -ENOTBLK;
	if (!S_ISBLK(inode->i_mode))
		goto fail;
	error = -EACCES;
	if (nd.mnt->mnt_flags & MNT_NODEV)
		goto fail;
	error = -ENOMEM;
	bdev = bd_acquire(inode);
	if (!bdev)
		goto fail;
out:
	path_release(&nd);
	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);