* Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
*/
-#include <linux/config.h>
#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/devfs_fs_kernel.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/writeback.h>
#include <linux/mpage.h>
#include <linux/mount.h>
#include <linux/uio.h>
#include <linux/namei.h>
#include <asm/uaccess.h>
+#include "internal.h"
struct bdev_inode {
struct block_device bdev;
int sb_set_blocksize(struct super_block *sb, int size)
{
- int bits = 9; /* 2^9 = 512 */
-
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;
- for (size >>= 10; size; size >>= 1)
- ++bits;
- sb->s_blocksize_bits = bits;
+ sb->s_blocksize_bits = blksize_bits(size);
return sb->s_blocksize;
}
static int
blkdev_get_blocks(struct inode *inode, sector_t iblock,
- unsigned long max_blocks, struct buffer_head *bh, int create)
+ 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;
loff_t size;
loff_t retval;
- down(&bd_inode->i_sem);
+ mutex_lock(&bd_inode->i_mutex);
size = i_size_read(bd_inode);
switch (origin) {
}
retval = offset;
}
- up(&bd_inode->i_sem);
+ mutex_unlock(&bd_inode->i_mutex);
return retval;
}
*/
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(bdev_lock);
-static kmem_cache_t * bdev_cachep;
+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, SLAB_KERNEL);
+ struct bdev_inode *ei = kmem_cache_alloc(bdev_cachep, GFP_KERNEL);
if (!ei)
return NULL;
return &ei->vfs_inode;
kmem_cache_free(bdev_cachep, bdi);
}
-static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags)
+static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flags)
{
struct bdev_inode *ei = (struct bdev_inode *) foo;
struct block_device *bdev = &ei->bdev;
SLAB_CTOR_CONSTRUCTOR)
{
memset(bdev, 0, sizeof(*bdev));
- sema_init(&bdev->bd_sem, 1);
- sema_init(&bdev->bd_mount_sem, 1);
+ mutex_init(&bdev->bd_mutex);
+ mutex_init(&bdev->bd_mount_mutex);
INIT_LIST_HEAD(&bdev->bd_inodes);
INIT_LIST_HEAD(&bdev->bd_list);
+#ifdef CONFIG_SYSFS
+ INIT_LIST_HEAD(&bdev->bd_holder_list);
+#endif
inode_init_once(&ei->vfs_inode);
}
}
.clear_inode = bdev_clear_inode,
};
-static struct super_block *bd_get_sb(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data)
+static int bd_get_sb(struct file_system_type *fs_type,
+ int flags, const char *dev_name, void *data, struct vfsmount *mnt)
{
- return get_sb_pseudo(fs_type, "bdev:", &bdev_sops, 0x62646576);
+ return get_sb_pseudo(fs_type, "bdev:", &bdev_sops, 0x62646576, mnt);
}
static struct file_system_type bd_type = {
.kill_sb = kill_anon_super,
};
-static struct vfsmount *bd_mnt;
+static struct vfsmount *bd_mnt __read_mostly;
struct super_block *blockdev_superblock;
void __init bdev_cache_init(void)
{
int err;
bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode),
- 0, SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|SLAB_PANIC,
+ 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
+ SLAB_MEM_SPREAD|SLAB_PANIC),
init_once, NULL);
err = register_filesystem(&bd_type);
if (err)
static struct block_device *bd_acquire(struct inode *inode)
{
struct block_device *bdev;
+
spin_lock(&bdev_lock);
bdev = inode->i_bdev;
- if (bdev && igrab(bdev->bd_inode)) {
+ if (bdev) {
+ atomic_inc(&bdev->bd_inode->i_count);
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)
- __bd_forget(inode);
- inode->i_bdev = bdev;
- inode->i_mapping = bdev->bd_inode->i_mapping;
- list_add(&inode->i_devices, &bdev->bd_inodes);
+ 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);
+ }
spin_unlock(&bdev_lock);
}
return bdev;
void bd_forget(struct inode *inode)
{
+ struct block_device *bdev = NULL;
+
spin_lock(&bdev_lock);
- if (inode->i_bdev)
+ if (inode->i_bdev) {
+ if (inode->i_sb != blockdev_superblock)
+ bdev = inode->i_bdev;
__bd_forget(inode);
+ }
spin_unlock(&bdev_lock);
+
+ if (bdev)
+ iput(bdev->bd_inode);
}
int bd_claim(struct block_device *bdev, void *holder)
EXPORT_SYMBOL(bd_release);
+#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);
+}
+
+static int add_symlink(struct kobject *from, struct kobject *to)
+{
+ if (!from || !to)
+ return 0;
+ return sysfs_create_link(from, to, kobject_name(to));
+}
+
+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);
+}
+
+/**
+ * find_bd_holder - find matching struct bd_holder from the block device
+ *
+ * @bdev: struct block device to be searched
+ * @bo: target struct bd_holder
+ *
+ * Returns matching entry with @bo in @bdev->bd_holder_list.
+ * If found, increment the reference count and return the pointer.
+ * If not found, returns NULL.
+ */
+static struct bd_holder *find_bd_holder(struct block_device *bdev,
+ struct bd_holder *bo)
+{
+ struct bd_holder *tmp;
+
+ list_for_each_entry(tmp, &bdev->bd_holder_list, list)
+ if (tmp->sdir == bo->sdir) {
+ tmp->count++;
+ return tmp;
+ }
+
+ return NULL;
+}
+
+/**
+ * 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()
+ *
+ * Add @bo to @bdev->bd_holder_list, create symlinks.
+ *
+ * Returns 0 if symlinks are created.
+ * Returns -ve if something fails.
+ */
+static int add_bd_holder(struct block_device *bdev, struct bd_holder *bo)
+{
+ int ret;
+
+ if (!bo)
+ return -EINVAL;
+
+ if (!bd_holder_grab_dirs(bdev, bo))
+ return -EBUSY;
+
+ 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;
+}
+
+/**
+ * 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, *found;
+
+ if (!kobj)
+ return -EINVAL;
+
+ bo = alloc_bd_holder(kobj);
+ if (!bo)
+ return -ENOMEM;
+
+ mutex_lock(&bdev->bd_mutex);
+ res = bd_claim(bdev, holder);
+ if (res == 0) {
+ found = find_bd_holder(bdev, bo);
+ if (found == NULL) {
+ res = add_bd_holder(bdev, bo);
+ if (res)
+ bd_release(bdev);
+ }
+ }
+
+ if (res || found)
+ free_bd_holder(bo);
+ mutex_unlock(&bdev->bd_mutex);
+
+ 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;
+
+ mutex_lock(&bdev->bd_mutex);
+ bd_release(bdev);
+ if ((bo = del_bd_holder(bdev, kobj)))
+ free_bd_holder(bo);
+ mutex_unlock(&bdev->bd_mutex);
+}
+
+/**
+ * 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
+
/*
* 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
}
owner = disk->fops->owner;
- down(&bdev->bd_sem);
+ mutex_lock(&bdev->bd_mutex);
if (!bdev->bd_openers) {
bdev->bd_disk = disk;
bdev->bd_contains = bdev;
if (ret)
goto out_first;
bdev->bd_contains = whole;
- down(&whole->bd_sem);
+ mutex_lock(&whole->bd_mutex);
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--;
- up(&whole->bd_sem);
+ mutex_unlock(&whole->bd_mutex);
ret = -ENXIO;
goto out_first;
}
kobject_get(&p->kobj);
bdev->bd_part = p;
bd_set_size(bdev, (loff_t) p->nr_sects << 9);
- up(&whole->bd_sem);
+ mutex_unlock(&whole->bd_mutex);
}
} else {
put_disk(disk);
if (bdev->bd_invalidated)
rescan_partitions(bdev->bd_disk, bdev);
} else {
- down(&bdev->bd_contains->bd_sem);
+ mutex_lock(&bdev->bd_contains->bd_mutex);
bdev->bd_contains->bd_part_count++;
- up(&bdev->bd_contains->bd_sem);
+ mutex_unlock(&bdev->bd_contains->bd_mutex);
}
}
bdev->bd_openers++;
- up(&bdev->bd_sem);
+ mutex_unlock(&bdev->bd_mutex);
unlock_kernel();
return 0;
put_disk(disk);
module_put(owner);
out:
- up(&bdev->bd_sem);
+ mutex_unlock(&bdev->bd_mutex);
unlock_kernel();
if (ret)
bdput(bdev);
filp->f_flags |= O_LARGEFILE;
bdev = bd_acquire(inode);
+ if (bdev == NULL)
+ return -ENOMEM;
res = do_open(bdev, filp);
if (res)
struct inode *bd_inode = bdev->bd_inode;
struct gendisk *disk = bdev->bd_disk;
- down(&bdev->bd_sem);
+ mutex_lock(&bdev->bd_mutex);
lock_kernel();
if (!--bdev->bd_openers) {
sync_blockdev(bdev);
if (disk->fops->release)
ret = disk->fops->release(bd_inode, NULL);
} else {
- down(&bdev->bd_contains->bd_sem);
+ mutex_lock(&bdev->bd_contains->bd_mutex);
bdev->bd_contains->bd_part_count--;
- up(&bdev->bd_contains->bd_sem);
+ mutex_unlock(&bdev->bd_contains->bd_mutex);
}
if (!bdev->bd_openers) {
struct module *owner = disk->fops->owner;
bdev->bd_contains = NULL;
}
unlock_kernel();
- up(&bdev->bd_sem);
+ mutex_unlock(&bdev->bd_mutex);
bdput(bdev);
return ret;
}
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);
-}
-
-static int block_ioctl(struct inode *inode, struct file *file, unsigned cmd,
- unsigned long arg)
+static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
{
return blkdev_ioctl(file->f_mapping->host, file, cmd, arg);
}
-struct address_space_operations def_blk_aops = {
+const struct address_space_operations def_blk_aops = {
.readpage = blkdev_readpage,
.writepage = blkdev_writepage,
.sync_page = block_sync_page,
.direct_IO = blkdev_direct_IO,
};
-struct file_operations def_blk_fops = {
+const struct file_operations def_blk_fops = {
.open = blkdev_open,
.release = blkdev_close,
.llseek = block_llseek,
- .read = generic_file_read,
- .write = blkdev_file_write,
+ .read = do_sync_read,
+ .write = do_sync_write,
.aio_read = generic_file_aio_read,
- .aio_write = blkdev_file_aio_write,
+ .aio_write = generic_file_aio_write_nolock,
.mmap = generic_file_mmap,
.fsync = block_fsync,
- .ioctl = block_ioctl,
+ .unlocked_ioctl = block_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = compat_blkdev_ioctl,
#endif
- .readv = generic_file_readv,
- .writev = generic_file_write_nolock,
.sendfile = generic_file_sendfile,
+ .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)
}
EXPORT_SYMBOL(close_bdev_excl);
+
+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, 0);
+ return res;
+}
+EXPORT_SYMBOL(__invalidate_device);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff