block_dev.c

/*
 *  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/device_cgroup.h>
#include <linux/highmem.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/module.h>
#include <linux/blkpg.h>
#include <linux/magic.h>
#include <linux/buffer_head.h>
#include <linux/swap.h>
#include <linux/pagevec.h>
#include <linux/writeback.h>
#include <linux/mpage.h>
#include <linux/mount.h>
#include <linux/uio.h>
#include <linux/namei.h>
#include <linux/log2.h>
#include <linux/cleancache.h>
#include <linux/dax.h>
#include <linux/badblocks.h>
#include <linux/falloc.h>
#include <asm/uaccess.h>
#include "internal.h"

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

static const struct address_space_operations def_blk_aops;

static inline struct bdev_inode *BDEV_I(struct inode *inode)
{
	return container_of(inode, struct bdev_inode, vfs_inode);
}

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

void __vfs_msg(struct super_block *sb, const char *prefix, const char *fmt, ...)
{
	struct va_format vaf;
	va_list args;

	va_start(args, fmt);
	vaf.fmt = fmt;
	vaf.va = &args;
	printk_ratelimited("%sVFS (%s): %pV\n", prefix, sb->s_id, &vaf);
	va_end(args);
}

static void bdev_write_inode(struct block_device *bdev)
{
	struct inode *inode = bdev->bd_inode;
	int ret;

	spin_lock(&inode->i_lock);
	while (inode->i_state & I_DIRTY) {
		spin_unlock(&inode->i_lock);
		ret = write_inode_now(inode, true);
		if (ret) {
			char name[BDEVNAME_SIZE];
			pr_warn_ratelimited("VFS: Dirty inode writeback failed "
					    "for block device %s (err=%d).\n",
					    bdevname(bdev, name), ret);
		}
		spin_lock(&inode->i_lock);
	}
	spin_unlock(&inode->i_lock);
}

/* Kill _all_ buffers and pagecache , dirty or not.. */
void kill_bdev(struct block_device *bdev)
{
	struct address_space *mapping = bdev->bd_inode->i_mapping;

	if (mapping->nrpages == 0 && mapping->nrexceptional == 0)
		return;

	invalidate_bh_lrus();
	truncate_inode_pages(mapping, 0);
}	
EXPORT_SYMBOL(kill_bdev);

/* Invalidate clean unused buffers and pagecache. */
void invalidate_bdev(struct block_device *bdev)
{
	struct address_space *mapping = bdev->bd_inode->i_mapping;

	if (mapping->nrpages) {
		invalidate_bh_lrus();
		lru_add_drain_all();	/* make sure all lru add caches are flushed */
		invalidate_mapping_pages(mapping, 0, -1);
	}
	/* 99% of the time, we don't need to flush the cleancache on the bdev.
	 * But, for the strange corners, lets be cautious
	 */
	cleancache_invalidate_inode(mapping);
}
EXPORT_SYMBOL(invalidate_bdev);

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 || !is_power_of_2(size))
		return -EINVAL;

	/* Size cannot be smaller than the size supported by the device */
	if (size < bdev_logical_block_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;
	sb->s_blocksize_bits = blksize_bits(size);
	return sb->s_blocksize;
}

EXPORT_SYMBOL(sb_set_blocksize);

int sb_min_blocksize(struct super_block *sb, int size)
{
	int minsize = bdev_logical_block_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)
{
	bh->b_bdev = I_BDEV(inode);
	bh->b_blocknr = iblock;
	set_buffer_mapped(bh);
	return 0;
}

static struct inode *bdev_file_inode(struct file *file)
{
	return file->f_mapping->host;
}

static ssize_t
blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = bdev_file_inode(file);

	return __blockdev_direct_IO(iocb, inode, I_BDEV(inode), iter,
				    blkdev_get_block, NULL, NULL,
				    DIO_SKIP_DIO_COUNT);
}

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);
}

/*
 * 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)
{
	return __sync_blockdev(bdev, 1);
}
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) {
		int res = sync_filesystem(sb);
		drop_super(sb);
		return res;
	}
	return sync_blockdev(bdev);
}
EXPORT_SYMBOL(fsync_bdev);

/**
 * 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 > 1) {
		/*
		 * We don't even need to grab a reference - the first call
		 * to freeze_bdev grab an active reference and only the last
		 * thaw_bdev drops it.
		 */
		sb = get_super(bdev);
		if (sb)
			drop_super(sb);
		mutex_unlock(&bdev->bd_fsfreeze_mutex);
		return sb;
	}

	sb = get_active_super(bdev);
	if (!sb)
		goto out;
	if (sb->s_op->freeze_super)
		error = sb->s_op->freeze_super(sb);
	else
		error = freeze_super(sb);
	if (error) {
		deactivate_super(sb);
		bdev->bd_fsfreeze_count--;
		mutex_unlock(&bdev->bd_fsfreeze_mutex);
		return ERR_PTR(error);
	}
	deactivate_super(sb);
 out:
	sync_blockdev(bdev);
	mutex_unlock(&bdev->bd_fsfreeze_mutex);
	return sb;	/* thaw_bdev releases s->s_umount */
}
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 = -EINVAL;

	mutex_lock(&bdev->bd_fsfreeze_mutex);
	if (!bdev->bd_fsfreeze_count)
		goto out;

	error = 0;
	if (--bdev->bd_fsfreeze_count > 0)
		goto out;

	if (!sb)
		goto out;

	if (sb->s_op->thaw_super)
		error = sb->s_op->thaw_super(sb);
	else
		error = thaw_super(sb);
	if (error)
		bdev->bd_fsfreeze_count++;
out:
	mutex_unlock(&bdev->bd_fsfreeze_mutex);
	return error;
}
EXPORT_SYMBOL(thaw_bdev);

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_readpages(struct file *file, struct address_space *mapping,
			struct list_head *pages, unsigned nr_pages)
{
	return mpage_readpages(mapping, pages, nr_pages, blkdev_get_block);
}

static int blkdev_write_begin(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned flags,
			struct page **pagep, void **fsdata)
{
	return block_write_begin(mapping, pos, len, flags, pagep,
				 blkdev_get_block);
}

static int blkdev_write_end(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned copied,
			struct page *page, void *fsdata)
{
	int ret;
	ret = block_write_end(file, mapping, pos, len, copied, page, fsdata);

	unlock_page(page);
	put_page(page);

	return ret;
}

/*
 * private llseek:
 * for a block special file file_inode(file)->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 whence)
{
	struct inode *bd_inode = bdev_file_inode(file);
	loff_t retval;

	inode_lock(bd_inode);
	retval = fixed_size_llseek(file, offset, whence, i_size_read(bd_inode));
	inode_unlock(bd_inode);
	return retval;
}
	
int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
{
	struct inode *bd_inode = bdev_file_inode(filp);
	struct block_device *bdev = I_BDEV(bd_inode);
	int error;
	
	error = filemap_write_and_wait_range(filp->f_mapping, start, end);
	if (error)
		return error;

	/*
	 * There is no need to serialise calls to blkdev_issue_flush with
	 * i_mutex and doing so causes performance issues with concurrent
	 * O_SYNC writers to a block device.
	 */
	error = blkdev_issue_flush(bdev, GFP_KERNEL, NULL);
	if (error == -EOPNOTSUPP)
		error = 0;

	return error;
}
EXPORT_SYMBOL(blkdev_fsync);

/**
 * bdev_read_page() - Start reading a page from a block device
 * @bdev: The device to read the page from
 * @sector: The offset on the device to read the page to (need not be aligned)
 * @page: The page to read
 *
 * On entry, the page should be locked.  It will be unlocked when the page
 * has been read.  If the block driver implements rw_page synchronously,
 * that will be true on exit from this function, but it need not be.
 *
 * Errors returned by this function are usually "soft", eg out of memory, or
 * queue full; callers should try a different route to read this page rather
 * than propagate an error back up the stack.
 *
 * Return: negative errno if an error occurs, 0 if submission was successful.
 */
int bdev_read_page(struct block_device *bdev, sector_t sector,
			struct page *page)
{
	const struct block_device_operations *ops = bdev->bd_disk->fops;
	int result = -EOPNOTSUPP;

	if (!ops->rw_page || bdev_get_integrity(bdev))
		return result;

	result = blk_queue_enter(bdev->bd_queue, false);
	if (result)
		return result;
	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, false);
	blk_queue_exit(bdev->bd_queue);
	return result;
}
EXPORT_SYMBOL_GPL(bdev_read_page);

/**
 * bdev_write_page() - Start writing a page to a block device
 * @bdev: The device to write the page to
 * @sector: The offset on the device to write the page to (need not be aligned)
 * @page: The page to write
 * @wbc: The writeback_control for the write
 *
 * On entry, the page should be locked and not currently under writeback.
 * On exit, if the write started successfully, the page will be unlocked and
 * under writeback.  If the write failed already (eg the driver failed to
 * queue the page to the device), the page will still be locked.  If the
 * caller is a ->writepage implementation, it will need to unlock the page.
 *
 * Errors returned by this function are usually "soft", eg out of memory, or
 * queue full; callers should try a different route to write this page rather
 * than propagate an error back up the stack.
 *
 * Return: negative errno if an error occurs, 0 if submission was successful.
 */
int bdev_write_page(struct block_device *bdev, sector_t sector,
			struct page *page, struct writeback_control *wbc)
{
	int result;
	const struct block_device_operations *ops = bdev->bd_disk->fops;

	if (!ops->rw_page || bdev_get_integrity(bdev))
		return -EOPNOTSUPP;
	result = blk_queue_enter(bdev->bd_queue, false);
	if (result)
		return result;

	set_page_writeback(page);
	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, true);
	if (result) {
		end_page_writeback(page);
	} else {
		clean_page_buffers(page);
		unlock_page(page);
	}
	blk_queue_exit(bdev->bd_queue);
	return result;
}
EXPORT_SYMBOL_GPL(bdev_write_page);

/**
 * bdev_direct_access() - Get the address for directly-accessibly memory
 * @bdev: The device containing the memory
 * @dax: control and output parameters for ->direct_access
 *
 * If a block device is made up of directly addressable memory, this function
 * will tell the caller the PFN and the address of the memory.  The address
 * may be directly dereferenced within the kernel without the need to call
 * ioremap(), kmap() or similar.  The PFN is suitable for inserting into
 * page tables.
 *
 * Return: negative errno if an error occurs, otherwise the number of bytes
 * accessible at this address.
 */
long bdev_direct_access(struct block_device *bdev, struct blk_dax_ctl *dax)
{
	sector_t sector = dax->sector;
	long avail, size = dax->size;
	const struct block_device_operations *ops = bdev->bd_disk->fops;

	/*
	 * The device driver is allowed to sleep, in order to make the
	 * memory directly accessible.
	 */
	might_sleep();

	if (size < 0)
		return size;
	if (!blk_queue_dax(bdev_get_queue(bdev)) || !ops->direct_access)
		return -EOPNOTSUPP;
	if ((sector + DIV_ROUND_UP(size, 512)) >
					part_nr_sects_read(bdev->bd_part))
		return -ERANGE;
	sector += get_start_sect(bdev);
	if (sector % (PAGE_SIZE / 512))
		return -EINVAL;
	avail = ops->direct_access(bdev, sector, &dax->addr, &dax->pfn, size);
	if (!avail)
		return -ERANGE;
	if (avail > 0 && avail & ~PAGE_MASK)
		return -ENXIO;
	return min(avail, size);
}
EXPORT_SYMBOL_GPL(bdev_direct_access);

/**
 * bdev_dax_supported() - Check if the device supports dax for filesystem
 * @sb: The superblock of the device
 * @blocksize: The block size of the device
 *
 * This is a library function for filesystems to check if the block device
 * can be mounted with dax option.
 *
 * Return: negative errno if unsupported, 0 if supported.
 */
int bdev_dax_supported(struct super_block *sb, int blocksize)
{
	struct blk_dax_ctl dax = {
		.sector = 0,
		.size = PAGE_SIZE,
	};
	int err;

	if (blocksize != PAGE_SIZE) {
		vfs_msg(sb, KERN_ERR, "error: unsupported blocksize for dax");
		return -EINVAL;
	}

	err = bdev_direct_access(sb->s_bdev, &dax);
	if (err < 0) {
		switch (err) {
		case -EOPNOTSUPP:
			vfs_msg(sb, KERN_ERR,
				"error: device does not support dax");
			break;
		case -EINVAL:
			vfs_msg(sb, KERN_ERR,
				"error: unaligned partition for dax");
			break;
		default:
			vfs_msg(sb, KERN_ERR,
				"error: dax access failed (%d)", err);
		}
		return err;
	}

	return 0;
}
EXPORT_SYMBOL_GPL(bdev_dax_supported);

/**
 * bdev_dax_capable() - Return if the raw device is capable for dax
 * @bdev: The device for raw block device access
 */
bool bdev_dax_capable(struct block_device *bdev)
{
	struct blk_dax_ctl dax = {
		.size = PAGE_SIZE,
	};

	if (!IS_ENABLED(CONFIG_FS_DAX))
		return false;

	dax.sector = 0;
	if (bdev_direct_access(bdev, &dax) < 0)
		return false;

	dax.sector = bdev->bd_part->nr_sects - (PAGE_SIZE / 512);
	if (bdev_direct_access(bdev, &dax) < 0)
		return false;

	return true;
}

/*
 * pseudo-fs
 */

static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(bdev_lock);
static struct kmem_cache * bdev_cachep __read_mostly;

static struct inode *bdev_alloc_inode(struct super_block *sb)
{
	struct bdev_inode *ei = kmem_cache_alloc(bdev_cachep, GFP_KERNEL);
	if (!ei)
		return NULL;
	return &ei->vfs_inode;
}

static void bdev_i_callback(struct rcu_head *head)
{
	struct inode *inode = container_of(head, struct inode, i_rcu);
	struct bdev_inode *bdi = BDEV_I(inode);

	kmem_cache_free(bdev_cachep, bdi);
}

static void bdev_destroy_inode(struct inode *inode)
{
	call_rcu(&inode->i_rcu, bdev_i_callback);
}

static void init_once(void *foo)
{
	struct bdev_inode *ei = (struct bdev_inode *) foo;
	struct block_device *bdev = &ei->bdev;

	memset(bdev, 0, sizeof(*bdev));
	mutex_init(&bdev->bd_mutex);
	INIT_LIST_HEAD(&bdev->bd_list);
#ifdef CONFIG_SYSFS
	INIT_LIST_HEAD(&bdev->bd_holder_disks);
#endif
	inode_init_once(&ei->vfs_inode);
	/* Initialize mutex for freeze. */
	mutex_init(&bdev->bd_fsfreeze_mutex);
}

static void bdev_evict_inode(struct inode *inode)
{
	struct block_device *bdev = &BDEV_I(inode)->bdev;
	truncate_inode_pages_final(&inode->i_data);
	invalidate_inode_buffers(inode); /* is it needed here? */
	clear_inode(inode);
	spin_lock(&bdev_lock);
	list_del_init(&bdev->bd_list);
	spin_unlock(&bdev_lock);
}

static const struct super_operations bdev_sops = {
	.statfs = simple_statfs,
	.alloc_inode = bdev_alloc_inode,
	.destroy_inode = bdev_destroy_inode,
	.drop_inode = generic_delete_inode,
	.evict_inode = bdev_evict_inode,
};

static struct dentry *bd_mount(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data)
{
	struct dentry *dent;
	dent = mount_pseudo(fs_type, "bdev:", &bdev_sops, NULL, BDEVFS_MAGIC);
	if (!IS_ERR(dent))
		dent->d_sb->s_iflags |= SB_I_CGROUPWB;
	return dent;
}

static struct file_system_type bd_type = {
	.name		= "bdev",
	.mount		= bd_mount,
	.kill_sb	= kill_anon_super,
};

struct super_block *blockdev_superblock __read_mostly;
EXPORT_SYMBOL_GPL(blockdev_superblock);

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

	bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode),
			0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
				SLAB_MEM_SPREAD|SLAB_ACCOUNT|SLAB_PANIC),
			init_once);
	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(blockdev_superblock, 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_super = NULL;
		bdev->bd_inode = inode;
		bdev->bd_block_size = i_blocksize(inode);
		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);
		spin_lock(&bdev_lock);
		list_add(&bdev->bd_list, &all_bdevs);
		spin_unlock(&bdev_lock);
		unlock_new_inode(inode);
	}
	return bdev;
}

EXPORT_SYMBOL(bdget);

/**
 * 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)
{
	ihold(bdev->bd_inode);
	return bdev;
}
EXPORT_SYMBOL(bdgrab);

long nr_blockdev_pages(void)
{
	struct block_device *bdev;
	long ret = 0;
	spin_lock(&bdev_lock);
	list_for_each_entry(bdev, &all_bdevs, 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;

	spin_lock(&bdev_lock);
	bdev = inode->i_bdev;
	if (bdev) {
		bdgrab(bdev);
		spin_unlock(&bdev_lock);
		return bdev;
	}
	spin_unlock(&bdev_lock);

	bdev = bdget(inode->i_rdev);
	if (bdev) {
		spin_lock(&bdev_lock);
		if (!inode->i_bdev) {
			/*
			 * We take an additional reference to bd_inode,
			 * and it's released in clear_inode() of inode.
			 * So, we can access it via ->i_mapping always
			 * without igrab().
			 */
			bdgrab(bdev);
			inode->i_bdev = bdev;
			inode->i_mapping = bdev->bd_inode->i_mapping;
		}
		spin_unlock(&bdev_lock);
	}
	return bdev;
}

/* Call when you free inode */

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

	spin_lock(&bdev_lock);
	if (!sb_is_blkdev_sb(inode->i_sb))
		bdev = inode->i_bdev;
	inode->i_bdev = NULL;
	inode->i_mapping = &inode->i_data;
	spin_unlock(&bdev_lock);

	if (bdev)
		bdput(bdev);
}

/**
 * bd_may_claim - test whether a block device can be claimed
 * @bdev: block device of interest
 * @whole: whole block device containing @bdev, may equal @bdev
 * @holder: holder trying to claim @bdev
 *
 * Test whether @bdev can be claimed by @holder.
 *
 * CONTEXT:
 * spin_lock(&bdev_lock).
 *
 * RETURNS:
 * %true if @bdev can be claimed, %false otherwise.
 */
static bool bd_may_claim(struct block_device *bdev, struct block_device *whole,
			 void *holder)
{
	if (bdev->bd_holder == holder)
		return true;	 /* already a holder */
	else if (bdev->bd_holder != NULL)
		return false; 	 /* held by someone else */
	else if (whole == bdev)
		return true;  	 /* is a whole device which isn't held */

	else if (whole->bd_holder == bd_may_claim)
		return true; 	 /* is a partition of a device that is being partitioned */
	else if (whole->bd_holder != NULL)
		return false;	 /* is a partition of a held device */
	else
		return true;	 /* is a partition of an un-held device */
}

/**
 * bd_prepare_to_claim - prepare to claim a block device
 * @bdev: block device of interest
 * @whole: the whole device containing @bdev, may equal @bdev
 * @holder: holder trying to claim @bdev
 *
 * Prepare to claim @bdev.  This function fails if @bdev is already
 * claimed by another holder and waits if another claiming is in
 * progress.  This function doesn't actually claim.  On successful
 * return, the caller has ownership of bd_claiming and bd_holder[s].
 *
 * CONTEXT:
 * spin_lock(&bdev_lock).  Might release bdev_lock, sleep and regrab
 * it multiple times.
 *
 * RETURNS:
 * 0 if @bdev can be claimed, -EBUSY otherwise.
 */
static int bd_prepare_to_claim(struct block_device *bdev,
			       struct block_device *whole, void *holder)
{
retry:
	/* if someone else claimed, fail */
	if (!bd_may_claim(bdev, whole, holder))
		return -EBUSY;

	/* if claiming is already in progress, wait for it to finish */
	if (whole->bd_claiming) {
		wait_queue_head_t *wq = bit_waitqueue(&whole->bd_claiming, 0);
		DEFINE_WAIT(wait);

		prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE);
		spin_unlock(&bdev_lock);
		schedule();
		finish_wait(wq, &wait);
		spin_lock(&bdev_lock);
		goto retry;
	}

	/* yay, all mine */
	return 0;
}

/**
 * bd_start_claiming - start claiming a block device
 * @bdev: block device of interest
 * @holder: holder trying to claim @bdev
 *
 * @bdev is about to be opened exclusively.  Check @bdev can be opened
 * exclusively and mark that an exclusive open is in progress.  Each
 * successful call to this function must be matched with a call to
 * either bd_finish_claiming() or bd_abort_claiming() (which do not
 * fail).
 *
 * This function is used to gain exclusive access to the block device
 * without actually causing other exclusive open attempts to fail. It
 * should be used when the open sequence itself requires exclusive
 * access but may subsequently fail.
 *
 * CONTEXT:
 * Might sleep.
 *
 * RETURNS:
 * Pointer to the block device containing @bdev on success, ERR_PTR()
 * value on failure.
 */
static struct block_device *bd_start_claiming(struct block_device *bdev,
					      void *holder)
{
	struct gendisk *disk;
	struct block_device *whole;
	int partno, err;

	might_sleep();

	/*
	 * @bdev might not have been initialized properly yet, look up
	 * and grab the outer block device the hard way.
	 */
	disk = get_gendisk(bdev->bd_dev, &partno);
	if (!disk)
		return ERR_PTR(-ENXIO);

	/*
	 * Normally, @bdev should equal what's returned from bdget_disk()
	 * if partno is 0; however, some drivers (floppy) use multiple
	 * bdev's for the same physical device and @bdev may be one of the
	 * aliases.  Keep @bdev if partno is 0.  This means claimer
	 * tracking is broken for those devices but it has always been that
	 * way.
	 */
	if (partno)
		whole = bdget_disk(disk, 0);
	else
		whole = bdgrab(bdev);

	module_put(disk->fops->owner);
	put_disk(disk);
	if (!whole)
		return ERR_PTR(-ENOMEM);

	/* prepare to claim, if successful, mark claiming in progress */
	spin_lock(&bdev_lock);

	err = bd_prepare_to_claim(bdev, whole, holder);
	if (err == 0) {
		whole->bd_claiming = holder;
		spin_unlock(&bdev_lock);
		return whole;
	} else {
		spin_unlock(&bdev_lock);
		bdput(whole);
		return ERR_PTR(err);
	}
}

#ifdef CONFIG_SYSFS
struct bd_holder_disk {
	struct list_head	list;
	struct gendisk		*disk;
	int			refcnt;
};

static struct bd_holder_disk *bd_find_holder_disk(struct block_device *bdev,
						  struct gendisk *disk)
{
	struct bd_holder_disk *holder;

	list_for_each_entry(holder, &bdev->bd_holder_disks, list)
		if (holder->disk == disk)
			return holder;
	return NULL;
}

static int add_symlink(struct kobject *from, struct kobject *to)
{
	return sysfs_create_link(from, to, kobject_name(to));
}

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

/**
 * bd_link_disk_holder - create symlinks between holding disk and slave bdev
 * @bdev: the claimed slave bdev
 * @disk: the holding disk
 *
 * DON'T USE THIS UNLESS YOU'RE ALREADY USING IT.
 *
 * This functions creates the following sysfs symlinks.
 *
 * - from "slaves" directory of the holder @disk to the claimed @bdev