block cfq: make queue preempt work for queues from different workload

[linux-2.6/btrfs-unstable.git] / fs / 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/module.h>
#include <linux/blkpg.h>
#include <linux/buffer_head.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/kmemleak.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);
}

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

EXPORT_SYMBOL(I_BDEV);

/*
 * move the inode from it's current bdi to the a new bdi. if the inode is dirty
 * we need to move it onto the dirty list of @dst so that the inode is always
 * on the right list.
 */
static void bdev_inode_switch_bdi(struct inode *inode,
                        struct backing_dev_info *dst)
{
        spin_lock(&inode_lock);
        inode->i_data.backing_dev_info = dst;
        if (inode->i_state & I_DIRTY)
                list_move(&inode->i_wb_list, &dst->wb.b_dirty);
        spin_unlock(&inode_lock);
}

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 and pagecache , dirty or not.. */
static void kill_bdev(struct block_device *bdev)
{
        if (bdev->bd_inode->i_mapping->nrpages == 0)
                return;
        invalidate_bh_lrus();
        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 || !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)
{
        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,
                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(rw, iocb, inode, I_BDEV(inode), iov, offset,
                                    nr_segs, blkdev_get_blocks, NULL, NULL, 0);
}

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);
                drop_super(sb);
                mutex_unlock(&bdev->bd_fsfreeze_mutex);
                return sb;
        }

        sb = get_active_super(bdev);
        if (!sb)
                goto out;
        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;

        error = thaw_super(sb);
        if (error) {
                bdev->bd_fsfreeze_count++;
                mutex_unlock(&bdev->bd_fsfreeze_mutex);
                return error;
        }
out:
        mutex_unlock(&bdev->bd_fsfreeze_mutex);
        return 0;
}
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_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);
        page_cache_release(page);

        return ret;
}

/*
 * private llseek:
 * for a block special file file->f_path.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;

        mutex_lock(&bd_inode->i_mutex);
        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;
        }
        mutex_unlock(&bd_inode->i_mutex);
        return retval;
}
        
int blkdev_fsync(struct file *filp, int datasync)
{
        struct inode *bd_inode = filp->f_mapping->host;
        struct block_device *bdev = I_BDEV(bd_inode);
        int 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.
         */
        mutex_unlock(&bd_inode->i_mutex);

        error = blkdev_issue_flush(bdev, GFP_KERNEL, NULL);
        if (error == -EOPNOTSUPP)
                error = 0;

        mutex_lock(&bd_inode->i_mutex);

        return error;
}
EXPORT_SYMBOL(blkdev_fsync);

/*
 * 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);

        INIT_LIST_HEAD(&inode->i_dentry);
        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_inodes);
        INIT_LIST_HEAD(&bdev->bd_list);
        inode_init_once(&ei->vfs_inode);
        /* Initialize mutex for freeze. */
        mutex_init(&bdev->bd_fsfreeze_mutex);
}

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_evict_inode(struct inode *inode)
{
        struct block_device *bdev = &BDEV_I(inode)->bdev;
        struct list_head *p;
        truncate_inode_pages(&inode->i_data, 0);
        invalidate_inode_buffers(inode); /* is it needed here? */
        end_writeback(inode);
        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 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)
{
        return mount_pseudo(fs_type, "bdev:", &bdev_sops, NULL, 0x62646576);
}

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

struct super_block *blockdev_superblock __read_mostly;

void __init bdev_cache_init(void)
{
        int err;
        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_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");
        /*
         * This vfsmount structure is only used to obtain the
         * blockdev_superblock, so tell kmemleak not to report it.
         */
        kmemleak_not_leak(bd_mnt);
        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_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);

/**
 * 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;
}

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) {
                ihold(bdev->bd_inode);
                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().
                         */
                        ihold(bdev->bd_inode);
                        inode->i_bdev = bdev;
                        inode->i_mapping = bdev->bd_inode->i_mapping;
                        list_add(&inode->i_devices, &bdev->bd_inodes);
                }
                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 (inode->i_bdev) {
                if (!sb_is_blkdev_sb(inode->i_sb))
                        bdev = inode->i_bdev;
                __bd_forget(inode);
        }
        spin_unlock(&bdev_lock);

        if (bdev)
                iput(bdev->bd_inode);
}

/**
 * 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 whther @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 (bdev->bd_contains == 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);

        whole = bdget_disk(disk, 0);
        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
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
 *
 * This functions creates the following sysfs symlinks.
 *
 * - from "slaves" directory of the holder @disk to the claimed @bdev
 * - from "holders" directory of the @bdev to the holder @disk
 *
 * For example, if /dev/dm-0 maps to /dev/sda and disk for dm-0 is
 * passed to bd_link_disk_holder(), then:
 *
 *   /sys/block/dm-0/slaves/sda --> /sys/block/sda
 *   /sys/block/sda/holders/dm-0 --> /sys/block/dm-0
 *
 * The caller must have claimed @bdev before calling this function and
 * ensure that both @bdev and @disk are valid during the creation and
 * lifetime of these symlinks.
 *
 * CONTEXT:
 * Might sleep.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
{
        int ret = 0;

        mutex_lock(&bdev->bd_mutex);

        WARN_ON_ONCE(!bdev->bd_holder || bdev->bd_holder_disk);

        /* FIXME: remove the following once add_disk() handles errors */
        if (WARN_ON(!disk->slave_dir || !bdev->bd_part->holder_dir))
                goto out_unlock;

        ret = add_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
        if (ret)
                goto out_unlock;

        ret = add_symlink(bdev->bd_part->holder_dir, &disk_to_dev(disk)->kobj);
        if (ret) {
                del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
                goto out_unlock;
        }

        bdev->bd_holder_disk = disk;
out_unlock:
        mutex_unlock(&bdev->bd_mutex);
        return ret;
}
EXPORT_SYMBOL_GPL(bd_link_disk_holder);

static void bd_unlink_disk_holder(struct block_device *bdev)
{
        struct gendisk *disk = bdev->bd_holder_disk;

        bdev->bd_holder_disk = NULL;
        if (!disk)
                return;

        del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
        del_symlink(bdev->bd_part->holder_dir, &disk_to_dev(disk)->kobj);
}
#else
static inline void bd_unlink_disk_holder(struct block_device *bdev)
{ }
#endif

/**
 * flush_disk - invalidates all buffer-cache entries on a disk
 *
 * @bdev:      struct block device to be flushed
 *
 * Invalidates all buffer-cache entries on a disk. It should be called
 * when a disk has been changed -- either by a media change or online
 * resize.
 */
static void flush_disk(struct block_device *bdev)
{
        if (__invalidate_device(bdev)) {
                char name[BDEVNAME_SIZE] = "";

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

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

/**
 * check_disk_size_change - checks for disk size change and adjusts bdev size.
 * @disk: struct gendisk to check
 * @bdev: struct bdev to adjust.
 *
 * This routine checks to see if the bdev size does not match the disk size
 * and adjusts it if it differs.
 */
void check_disk_size_change(struct gendisk *disk, struct block_device *bdev)
{
        loff_t disk_size, bdev_size;

        disk_size = (loff_t)get_capacity(disk) << 9;
        bdev_size = i_size_read(bdev->bd_inode);
        if (disk_size != bdev_size) {
                char name[BDEVNAME_SIZE];

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

/**
 * revalidate_disk - wrapper for lower-level driver's revalidate_disk call-back
 * @disk: struct gendisk to be revalidated
 *
 * This routine is a wrapper for lower-level driver's revalidate_disk
 * call-backs.  It is used to do common pre and post operations needed
 * for all revalidate_disk operations.
 */
int revalidate_disk(struct gendisk *disk)
{
        struct block_device *bdev;
        int ret = 0;

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

        bdev = bdget_disk(disk, 0);
        if (!bdev)
                return ret;

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

/*
 * 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;
        const struct block_device_operations *bdops = disk->fops;
        unsigned int events;

        events = disk_clear_events(disk, DISK_EVENT_MEDIA_CHANGE |
                                   DISK_EVENT_EJECT_REQUEST);
        if (!(events & DISK_EVENT_MEDIA_CHANGE))
                return 0;

        flush_disk(bdev);
        if (bdops->revalidate_disk)
                bdops->revalidate_disk(bdev->bd_disk);
        return 1;
}

EXPORT_SYMBOL(check_disk_change);

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

static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);

/*
 * bd_mutex locking:
 *
 *  mutex_lock(part->bd_mutex)
 *    mutex_lock_nested(whole->bd_mutex, 1)
 */

static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
{
        struct gendisk *disk;
        int ret;
        int partno;
        int perm = 0;

        if (mode & FMODE_READ)
                perm |= MAY_READ;
        if (mode & FMODE_WRITE)
                perm |= MAY_WRITE;
        /*
         * hooks: /n/, see "layering violations".
         */
        if (!for_part) {
                ret = devcgroup_inode_permission(bdev->bd_inode, perm);
                if (ret != 0) {
                        bdput(bdev);
                        return ret;
                }
        }

 restart:

        ret = -ENXIO;
        disk = get_gendisk(bdev->bd_dev, &partno);
        if (!disk)
                goto out;

        mutex_lock_nested(&bdev->bd_mutex, for_part);
        if (!bdev->bd_openers) {
                bdev->bd_disk = disk;
                bdev->bd_contains = bdev;
                if (!partno) {
                        struct backing_dev_info *bdi;

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

                        if (disk->fops->open) {
                                ret = disk->fops->open(bdev, mode);
                                if (ret == -ERESTARTSYS) {
                                        /* Lost a race with 'disk' being
                                         * deleted, try again.
                                         * See md.c
                                         */
                                        disk_put_part(bdev->bd_part);
                                        bdev->bd_part = NULL;
                                        module_put(disk->fops->owner);
                                        put_disk(disk);
                                        bdev->bd_disk = NULL;
                                        mutex_unlock(&bdev->bd_mutex);
                                        goto restart;
                                }
                                if (ret)
                                        goto out_clear;
                        }
                        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_inode_switch_bdi(bdev->bd_inode, bdi);
                        }
                        if (bdev->bd_invalidated)
                                rescan_partitions(disk, bdev);
                } else {
                        struct block_device *whole;
                        whole = bdget_disk(disk, 0);
                        ret = -ENOMEM;
                        if (!whole)
                                goto out_clear;
                        BUG_ON(for_part);
                        ret = __blkdev_get(whole, mode, 1);
                        if (ret)
                                goto out_clear;
                        bdev->bd_contains = whole;
                        bdev_inode_switch_bdi(bdev->bd_inode,
                                whole->bd_inode->i_data.backing_dev_info);
                        bdev->bd_part = disk_get_part(disk, partno);
                        if (!(disk->flags & GENHD_FL_UP) ||
                            !bdev->bd_part || !bdev->bd_part->nr_sects) {
                                ret = -ENXIO;
                                goto out_clear;
                        }
                        bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
                }
        } else {
                module_put(disk->fops->owner);
                put_disk(disk);
                disk = NULL;
                if (bdev->bd_contains == bdev) {
                        if (bdev->bd_disk->fops->open) {
                                ret = bdev->bd_disk->fops->open(bdev, mode);
                                if (ret)
                                        goto out_unlock_bdev;
                        }
                        if (bdev->bd_invalidated)
                                rescan_partitions(bdev->bd_disk, bdev);
                }
        }
        bdev->bd_openers++;
        if (for_part)
                bdev->bd_part_count++;
        mutex_unlock(&bdev->bd_mutex);
        return 0;

 out_clear:
        disk_put_part(bdev->bd_part);
        bdev->bd_disk = NULL;
        bdev->bd_part = NULL;
        bdev_inode_switch_bdi(bdev->bd_inode, &default_backing_dev_info);
        if (bdev != bdev->bd_contains)
                __blkdev_put(bdev->bd_contains, mode, 1);
        bdev->bd_contains = NULL;
 out_unlock_bdev:
        mutex_unlock(&bdev->bd_mutex);
 out:
        if (disk)
                module_put(disk->fops->owner);
        put_disk(disk);
        bdput(bdev);

        return ret;
}

/**
 * blkdev_get - open a block device
 * @bdev: block_device to open
 * @mode: FMODE_* mask
 * @holder: exclusive holder identifier
 *
 * Open @bdev with @mode.  If @mode includes %FMODE_EXCL, @bdev is
 * open with exclusive access.  Specifying %FMODE_EXCL with %NULL
 * @holder is invalid.  Exclusive opens may nest for the same @holder.
 *
 * On success, the reference count of @bdev is unchanged.  On failure,
 * @bdev is put.
 *
 * CONTEXT:
 * Might sleep.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
{
        struct block_device *whole = NULL;
        int res;

        WARN_ON_ONCE((mode & FMODE_EXCL) && !holder);

        if ((mode & FMODE_EXCL) && holder) {
                whole = bd_start_claiming(bdev, holder);
                if (IS_ERR(whole)) {
                        bdput(bdev);
                        return PTR_ERR(whole);
                }
        }

        res = __blkdev_get(bdev, mode, 0);

        /* __blkdev_get() may alter read only status, check it afterwards */
        if (!res && (mode & FMODE_WRITE) && bdev_read_only(bdev)) {
                __blkdev_put(bdev, mode, 0);
                res = -EACCES;
        }

        if (whole) {
                /* finish claiming */
                mutex_lock(&bdev->bd_mutex);
                spin_lock(&bdev_lock);

                if (!res) {
                        BUG_ON(!bd_may_claim(bdev, whole, holder));
                        /*
                         * Note that for a whole device bd_holders
                         * will be incremented twice, and bd_holder
                         * will be set to bd_may_claim before being
                         * set to holder
                         */
                        whole->bd_holders++;
                        whole->bd_holder = bd_may_claim;
                        bdev->bd_holders++;
                        bdev->bd_holder = holder;
                }

                /* tell others that we're done */
                BUG_ON(whole->bd_claiming != holder);
                whole->bd_claiming = NULL;
                wake_up_bit(&whole->bd_claiming, 0);

                spin_unlock(&bdev_lock);

                /*
                 * Block event polling for write claims.  Any write
                 * holder makes the write_holder state stick until all
                 * are released.  This is good enough and tracking
                 * individual writeable reference is too fragile given
                 * the way @mode is used in blkdev_get/put().
                 */
                if (!res && (mode & FMODE_WRITE) && !bdev->bd_write_holder) {
                        bdev->bd_write_holder = true;
                        disk_block_events(bdev->bd_disk);
                }

                mutex_unlock(&bdev->bd_mutex);
                bdput(whole);
        }

        return res;
}
EXPORT_SYMBOL(blkdev_get);

/**
 * blkdev_get_by_path - open a block device by name
 * @path: path to the block device to open
 * @mode: FMODE_* mask
 * @holder: exclusive holder identifier
 *
 * Open the blockdevice described by the device file at @path.  @mode
 * and @holder are identical to blkdev_get().
 *
 * On success, the returned block_device has reference count of one.
 *
 * CONTEXT:
 * Might sleep.
 *
 * RETURNS:
 * Pointer to block_device on success, ERR_PTR(-errno) on failure.
 */
struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
                                        void *holder)
{
        struct block_device *bdev;
        int err;

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

        err = blkdev_get(bdev, mode, holder);
        if (err)
                return ERR_PTR(err);

        return bdev;
}
EXPORT_SYMBOL(blkdev_get_by_path);

/**
 * blkdev_get_by_dev - open a block device by device number
 * @dev: device number of block device to open
 * @mode: FMODE_* mask
 * @holder: exclusive holder identifier
 *
 * Open the blockdevice described by device number @dev.  @mode and
 * @holder are identical to blkdev_get().
 *
 * Use it ONLY if you really do not have anything better - i.e. when
 * you are behind a truly sucky interface and all you are given is a
 * device number.  _Never_ to be used for internal purposes.  If you
 * ever need it - reconsider your API.
 *
 * On success, the returned block_device has reference count of one.
 *
 * CONTEXT:
 * Might sleep.
 *
 * RETURNS:
 * Pointer to block_device on success, ERR_PTR(-errno) on failure.
 */
struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
{
        struct block_device *bdev;
        int err;

        bdev = bdget(dev);
        if (!bdev)
                return ERR_PTR(-ENOMEM);

        err = blkdev_get(bdev, mode, holder);
        if (err)
                return ERR_PTR(err);

        return bdev;
}
EXPORT_SYMBOL(blkdev_get_by_dev);

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

        /*
         * 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;

        if (filp->f_flags & O_NDELAY)
                filp->f_mode |= FMODE_NDELAY;
        if (filp->f_flags & O_EXCL)
                filp->f_mode |= FMODE_EXCL;
        if ((filp->f_flags & O_ACCMODE) == 3)
                filp->f_mode |= FMODE_WRITE_IOCTL;

        bdev = bd_acquire(inode);
        if (bdev == NULL)
                return -ENOMEM;

        filp->f_mapping = bdev->bd_inode->i_mapping;

        return blkdev_get(bdev, filp->f_mode, filp);
}

static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
{
        int ret = 0;
        struct gendisk *disk = bdev->bd_disk;
        struct block_device *victim = NULL;

        mutex_lock_nested(&bdev->bd_mutex, for_part);
        if (for_part)
                bdev->bd_part_count--;

        if (!--bdev->bd_openers) {
                WARN_ON_ONCE(bdev->bd_holders);
                sync_blockdev(bdev);
                kill_bdev(bdev);
        }
        if (bdev->bd_contains == bdev) {
                if (disk->fops->release)
                        ret = disk->fops->release(disk, mode);
        }
        if (!bdev->bd_openers) {
                struct module *owner = disk->fops->owner;

                put_disk(disk);
                module_put(owner);
                disk_put_part(bdev->bd_part);
                bdev->bd_part = NULL;
                bdev->bd_disk = NULL;
                bdev_inode_switch_bdi(bdev->bd_inode,
                                        &default_backing_dev_info);
                if (bdev != bdev->bd_contains)
                        victim = bdev->bd_contains;
                bdev->bd_contains = NULL;
        }
        mutex_unlock(&bdev->bd_mutex);
        bdput(bdev);
        if (victim)
                __blkdev_put(victim, mode, 1);
        return ret;
}

int blkdev_put(struct block_device *bdev, fmode_t mode)
{
        if (mode & FMODE_EXCL) {
                bool bdev_free;

                /*
                 * Release a claim on the device.  The holder fields
                 * are protected with bdev_lock.  bd_mutex is to
                 * synchronize disk_holder unlinking.
                 */
                mutex_lock(&bdev->bd_mutex);
                spin_lock(&bdev_lock);

                WARN_ON_ONCE(--bdev->bd_holders < 0);
                WARN_ON_ONCE(--bdev->bd_contains->bd_holders < 0);

                /* bd_contains might point to self, check in a separate step */
                if ((bdev_free = !bdev->bd_holders))
                        bdev->bd_holder = NULL;
                if (!bdev->bd_contains->bd_holders)
                        bdev->bd_contains->bd_holder = NULL;

                spin_unlock(&bdev_lock);

                /*
                 * If this was the last claim, remove holder link and
                 * unblock evpoll if it was a write holder.
                 */
                if (bdev_free) {
                        bd_unlink_disk_holder(bdev);
                        if (bdev->bd_write_holder) {
                                disk_unblock_events(bdev->bd_disk);
                                bdev->bd_write_holder = false;
                        } else
                                disk_check_events(bdev->bd_disk);
                }

                mutex_unlock(&bdev->bd_mutex);
        } else
                disk_check_events(bdev->bd_disk);

        return __blkdev_put(bdev, mode, 0);
}
EXPORT_SYMBOL(blkdev_put);

static int blkdev_close(struct inode * inode, struct file * filp)
{
        struct block_device *bdev = I_BDEV(filp->f_mapping->host);

        return blkdev_put(bdev, filp->f_mode);
}

static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
{
        struct block_device *bdev = I_BDEV(file->f_mapping->host);
        fmode_t mode = file->f_mode;

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

        return blkdev_ioctl(bdev, mode, cmd, arg);
}

/*
 * Write data to the block device.  Only intended for the block device itself
 * and the raw driver which basically is a fake block device.
 *
 * Does not take i_mutex for the write and thus is not for general purpose
 * use.
 */
ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
                         unsigned long nr_segs, loff_t pos)
{
        struct file *file = iocb->ki_filp;
        ssize_t ret;

        BUG_ON(iocb->ki_pos != pos);

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

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

/*
 * Try to release a page associated with block device when the system
 * is under memory pressure.
 */
static int blkdev_releasepage(struct page *page, gfp_t wait)
{
        struct super_block *super = BDEV_I(page->mapping->host)->bdev.bd_super;

        if (super && super->s_op->bdev_try_to_free_page)
                return super->s_op->bdev_try_to_free_page(super, page, wait);

        return try_to_free_buffers(page);
}

static const struct address_space_operations def_blk_aops = {
        .readpage       = blkdev_readpage,
        .writepage      = blkdev_writepage,
        .sync_page      = block_sync_page,
        .write_begin    = blkdev_write_begin,
        .write_end      = blkdev_write_end,
        .writepages     = generic_writepages,
        .releasepage    = blkdev_releasepage,
        .direct_IO      = blkdev_direct_IO,
};

const struct file_operations def_blk_fops = {
        .open           = blkdev_open,
        .release        = blkdev_close,
        .llseek         = block_llseek,
        .read           = do_sync_read,
        .write          = do_sync_write,
        .aio_read       = generic_file_aio_read,
        .aio_write      = blkdev_aio_write,
        .mmap           = generic_file_mmap,
        .fsync          = blkdev_fsync,
        .unlocked_ioctl = block_ioctl,
#ifdef CONFIG_COMPAT
        .compat_ioctl   = compat_blkdev_ioctl,
#endif
        .splice_read    = generic_file_splice_read,
        .splice_write   = generic_file_splice_write,
};

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, 0, cmd, arg);
        set_fs(old_fs);
        return res;
}

EXPORT_SYMBOL(ioctl_by_bdev);

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

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

        error = kern_path(pathname, LOOKUP_FOLLOW, &path);
        if (error)
                return ERR_PTR(error);

        inode = path.dentry->d_inode;
        error = -ENOTBLK;
        if (!S_ISBLK(inode->i_mode))
                goto fail;
        error = -EACCES;
        if (path.mnt->mnt_flags & MNT_NODEV)
                goto fail;
        error = -ENOMEM;
        bdev = bd_acquire(inode);
        if (!bdev)
                goto fail;
out:
        path_put(&path);
        return bdev;
fail:
        bdev = ERR_PTR(error);
        goto out;
}
EXPORT_SYMBOL(lookup_bdev);

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);
        }
        invalidate_bdev(bdev);
        return res;
}
EXPORT_SYMBOL(__invalidate_device);