* 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/kmod.h>
#include <linux/major.h>
#include <linux/smp_lock.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/writeback.h>
#include <linux/mpage.h>
#include <linux/mount.h>
#include <linux/uio.h>
#include <linux/namei.h>
+#include <linux/log2.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);
return retval;
}
-/* Kill _all_ buffers, dirty or not.. */
+/* Kill _all_ buffers and pagecache , dirty or not.. */
static void kill_bdev(struct block_device *bdev)
{
- invalidate_bdev(bdev, 1);
+ 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 || (size & (size-1)))
+ if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size))
return -EINVAL;
/* Size cannot be smaller than the size supported by the device */
return block_read_full_page(page, blkdev_get_block);
}
-static int blkdev_prepare_write(struct file *file, struct page *page, unsigned from, unsigned to)
+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_prepare_write(page, from, to, blkdev_get_block);
+ *pagep = NULL;
+ return block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
+ blkdev_get_block);
}
-static int blkdev_commit_write(struct file *file, struct page *page, unsigned from, unsigned to)
+static int blkdev_write_end(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
{
- return block_commit_write(page, from, to);
+ 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_dentry->d_inode->i_size is zero
+ * 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)
*/
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(bdev_lock);
-static kmem_cache_t * bdev_cachep __read_mostly;
+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 bdev_inode *ei = (struct bdev_inode *) foo;
struct block_device *bdev = &ei->bdev;
- if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
- SLAB_CTOR_CONSTRUCTOR)
- {
- memset(bdev, 0, sizeof(*bdev));
- mutex_init(&bdev->bd_mutex);
- mutex_init(&bdev->bd_mount_mutex);
- INIT_LIST_HEAD(&bdev->bd_inodes);
- INIT_LIST_HEAD(&bdev->bd_list);
+ memset(bdev, 0, sizeof(*bdev));
+ mutex_init(&bdev->bd_mutex);
+ sema_init(&bdev->bd_mount_sem, 1);
+ INIT_LIST_HEAD(&bdev->bd_inodes);
+ INIT_LIST_HEAD(&bdev->bd_list);
#ifdef CONFIG_SYSFS
- INIT_LIST_HEAD(&bdev->bd_holder_list);
+ INIT_LIST_HEAD(&bdev->bd_holder_list);
#endif
- inode_init_once(&ei->vfs_inode);
- }
+ inode_init_once(&ei->vfs_inode);
+ /* Initialize mutex for freeze. */
+ mutex_init(&bdev->bd_fsfreeze_mutex);
}
static inline void __bd_forget(struct inode *inode)
spin_unlock(&bdev_lock);
}
-static struct super_operations bdev_sops = {
+static const struct super_operations bdev_sops = {
.statfs = simple_statfs,
.alloc_inode = bdev_alloc_inode,
.destroy_inode = bdev_destroy_inode,
.kill_sb = kill_anon_super,
};
-static struct vfsmount *bd_mnt __read_mostly;
-struct super_block *blockdev_superblock;
+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, NULL);
+ init_once);
err = register_filesystem(&bd_type);
if (err)
panic("Cannot register bdev pseudo-fs");
bd_mnt = kern_mount(&bd_type);
- err = PTR_ERR(bd_mnt);
if (IS_ERR(bd_mnt))
panic("Cannot create bdev pseudo-fs");
blockdev_superblock = bd_mnt->mnt_sb; /* For writeback */
struct block_device *bdev;
struct inode *inode;
- inode = iget5_locked(bd_mnt->mnt_sb, hash(dev),
+ inode = iget5_locked(blockdev_superblock, hash(dev),
bdev_test, bdev_set, &dev);
if (!inode)
long nr_blockdev_pages(void)
{
- struct list_head *p;
+ struct block_device *bdev;
long ret = 0;
spin_lock(&bdev_lock);
- list_for_each(p, &all_bdevs) {
- struct block_device *bdev;
- bdev = list_entry(p, struct block_device, bd_list);
+ list_for_each_entry(bdev, &all_bdevs, bd_list) {
ret += bdev->bd_inode->i_mapping->nrpages;
}
spin_unlock(&bdev_lock);
spin_lock(&bdev_lock);
if (inode->i_bdev) {
- if (inode->i_sb != blockdev_superblock)
+ if (!sb_is_blkdev_sb(inode->i_sb))
bdev = inode->i_bdev;
__bd_forget(inode);
}
* /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 void add_symlink(struct kobject *from, struct kobject *to)
+static int add_symlink(struct kobject *from, struct kobject *to)
{
if (!from || !to)
- return;
- sysfs_create_link(from, to, kobject_name(to));
+ return 0;
+ return sysfs_create_link(from, to, kobject_name(to));
}
static void del_symlink(struct kobject *from, struct kobject *to)
if (!bo->hdev)
goto fail_put_sdir;
- bo->sdev = bdev_get_kobj(bdev);
+ bo->sdev = kobject_get(&part_to_dev(bdev->bd_part)->kobj);
if (!bo->sdev)
goto fail_put_hdev;
- bo->hdir = bdev_get_holder(bdev);
+ bo->hdir = kobject_get(bdev->bd_part->holder_dir);
if (!bo->hdir)
goto fail_put_sdev;
}
/**
+ * 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()
*
- * If there is no matching entry with @bo in @bdev->bd_holder_list,
- * add @bo to the list, create symlinks.
+ * Add @bo to @bdev->bd_holder_list, create symlinks.
*
- * Returns 1 if @bo was added to the list.
- * Returns 0 if @bo wasn't used by any reason and should be freed.
+ * Returns 0 if symlinks are created.
+ * Returns -ve if something fails.
*/
static int add_bd_holder(struct block_device *bdev, struct bd_holder *bo)
{
- struct bd_holder *tmp;
+ int err;
if (!bo)
- return 0;
-
- list_for_each_entry(tmp, &bdev->bd_holder_list, list) {
- if (tmp->sdir == bo->sdir) {
- tmp->count++;
- return 0;
- }
- }
+ return -EINVAL;
if (!bd_holder_grab_dirs(bdev, bo))
- return 0;
+ return -EBUSY;
+
+ err = add_symlink(bo->sdir, bo->sdev);
+ if (err)
+ return err;
+
+ err = add_symlink(bo->hdir, bo->hdev);
+ if (err) {
+ del_symlink(bo->sdir, bo->sdev);
+ return err;
+ }
- add_symlink(bo->sdir, bo->sdev);
- add_symlink(bo->hdir, bo->hdev);
list_add_tail(&bo->list, &bdev->bd_holder_list);
- return 1;
+ return 0;
}
/**
static int bd_claim_by_kobject(struct block_device *bdev, void *holder,
struct kobject *kobj)
{
- int res;
- struct bd_holder *bo;
+ int err;
+ struct bd_holder *bo, *found;
if (!kobj)
return -EINVAL;
return -ENOMEM;
mutex_lock(&bdev->bd_mutex);
- res = bd_claim(bdev, holder);
- if (res || !add_bd_holder(bdev, bo))
- free_bd_holder(bo);
- mutex_unlock(&bdev->bd_mutex);
- return res;
+ err = bd_claim(bdev, holder);
+ if (err)
+ goto fail;
+
+ found = find_bd_holder(bdev, bo);
+ if (found)
+ goto fail;
+
+ err = add_bd_holder(bdev, bo);
+ if (err)
+ bd_release(bdev);
+ else
+ bo = NULL;
+fail:
+ mutex_unlock(&bdev->bd_mutex);
+ free_bd_holder(bo);
+ return err;
}
/**
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);
+ free_bd_holder(del_bd_holder(bdev, kobj));
mutex_unlock(&bdev->bd_mutex);
}
* to be used for internal purposes. If you ever need it - reconsider
* your API.
*/
-struct block_device *open_by_devnum(dev_t dev, unsigned mode)
+struct block_device *open_by_devnum(dev_t dev, fmode_t mode)
{
struct block_device *bdev = bdget(dev);
int err = -ENOMEM;
- int flags = mode & FMODE_WRITE ? O_RDWR : O_RDONLY;
if (bdev)
- err = blkdev_get(bdev, mode, flags);
+ err = blkdev_get(bdev, mode);
return err ? ERR_PTR(err) : bdev;
}
EXPORT_SYMBOL(open_by_devnum);
+/**
+ * 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
if (!bdops->media_changed(bdev->bd_disk))
return 0;
- if (__invalidate_device(bdev))
- printk("VFS: busy inodes on changed media.\n");
-
+ flush_disk(bdev);
if (bdops->revalidate_disk)
bdops->revalidate_disk(bdev->bd_disk);
- if (bdev->bd_disk->minors > 1)
- bdev->bd_invalidated = 1;
return 1;
}
}
EXPORT_SYMBOL(bd_set_size);
-static int do_open(struct block_device *bdev, struct file *file)
+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 module *owner = NULL;
struct gendisk *disk;
- int ret = -ENXIO;
- int part;
-
- file->f_mapping = bdev->bd_inode->i_mapping;
- lock_kernel();
- disk = get_gendisk(bdev->bd_dev, &part);
- if (!disk) {
- unlock_kernel();
+ 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".
+ */
+ ret = devcgroup_inode_permission(bdev->bd_inode, perm);
+ if (ret != 0) {
bdput(bdev);
return ret;
}
- owner = disk->fops->owner;
- mutex_lock(&bdev->bd_mutex);
+ lock_kernel();
+ restart:
+
+ ret = -ENXIO;
+ disk = get_gendisk(bdev->bd_dev, &partno);
+ if (!disk)
+ goto out_unlock_kernel;
+
+ mutex_lock_nested(&bdev->bd_mutex, for_part);
if (!bdev->bd_openers) {
bdev->bd_disk = disk;
bdev->bd_contains = bdev;
- if (!part) {
+ 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->bd_inode, file);
+ 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_first;
+ goto out_clear;
}
if (!bdev->bd_openers) {
bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
if (bdev->bd_invalidated)
rescan_partitions(disk, bdev);
} else {
- struct hd_struct *p;
struct block_device *whole;
whole = bdget_disk(disk, 0);
ret = -ENOMEM;
if (!whole)
- goto out_first;
- ret = blkdev_get(whole, file->f_mode, file->f_flags);
+ goto out_clear;
+ BUG_ON(for_part);
+ ret = __blkdev_get(whole, mode, 1);
if (ret)
- goto out_first;
+ goto out_clear;
bdev->bd_contains = whole;
- 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--;
- mutex_unlock(&whole->bd_mutex);
+ 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_first;
+ goto out_clear;
}
- kobject_get(&p->kobj);
- bdev->bd_part = p;
- bd_set_size(bdev, (loff_t) p->nr_sects << 9);
- mutex_unlock(&whole->bd_mutex);
+ bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
}
} else {
put_disk(disk);
- module_put(owner);
+ module_put(disk->fops->owner);
+ disk = NULL;
if (bdev->bd_contains == bdev) {
if (bdev->bd_disk->fops->open) {
- ret = bdev->bd_disk->fops->open(bdev->bd_inode, file);
+ ret = bdev->bd_disk->fops->open(bdev, mode);
if (ret)
- goto out;
+ goto out_unlock_bdev;
}
if (bdev->bd_invalidated)
rescan_partitions(bdev->bd_disk, bdev);
- } else {
- mutex_lock(&bdev->bd_contains->bd_mutex);
- bdev->bd_contains->bd_part_count++;
- mutex_unlock(&bdev->bd_contains->bd_mutex);
}
}
bdev->bd_openers++;
+ if (for_part)
+ bdev->bd_part_count++;
mutex_unlock(&bdev->bd_mutex);
unlock_kernel();
return 0;
-out_first:
+ out_clear:
+ disk_put_part(bdev->bd_part);
bdev->bd_disk = NULL;
+ bdev->bd_part = NULL;
bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
if (bdev != bdev->bd_contains)
- blkdev_put(bdev->bd_contains);
+ __blkdev_put(bdev->bd_contains, mode, 1);
bdev->bd_contains = NULL;
- put_disk(disk);
- module_put(owner);
-out:
+ out_unlock_bdev:
mutex_unlock(&bdev->bd_mutex);
+ out_unlock_kernel:
unlock_kernel();
- if (ret)
- bdput(bdev);
+
+ if (disk)
+ module_put(disk->fops->owner);
+ put_disk(disk);
+ bdput(bdev);
+
return ret;
}
-int blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags)
+int blkdev_get(struct block_device *bdev, fmode_t mode)
{
- /*
- * This crockload is due to bad choice of ->open() type.
- * It will go away.
- * For now, block device ->open() routine must _not_
- * examine anything in 'inode' argument except ->i_rdev.
- */
- struct file fake_file = {};
- struct dentry fake_dentry = {};
- fake_file.f_mode = mode;
- fake_file.f_flags = flags;
- fake_file.f_dentry = &fake_dentry;
- fake_dentry.d_inode = bdev->bd_inode;
-
- return do_open(bdev, &fake_file);
+ return __blkdev_get(bdev, mode, 0);
}
-
EXPORT_SYMBOL(blkdev_get);
static int blkdev_open(struct inode * inode, struct file * filp)
*/
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;
- res = do_open(bdev, filp);
+ res = blkdev_get(bdev, filp->f_mode);
if (res)
return res;
- if (!(filp->f_flags & O_EXCL) )
- return 0;
+ if (filp->f_mode & FMODE_EXCL) {
+ res = bd_claim(bdev, filp);
+ if (res)
+ goto out_blkdev_put;
+ }
- if (!(res = bd_claim(bdev, filp)))
- return 0;
+ return 0;
- blkdev_put(bdev);
+ out_blkdev_put:
+ blkdev_put(bdev, filp->f_mode);
return res;
}
-int blkdev_put(struct block_device *bdev)
+static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
{
int ret = 0;
- struct inode *bd_inode = bdev->bd_inode;
struct gendisk *disk = bdev->bd_disk;
+ struct block_device *victim = NULL;
- mutex_lock(&bdev->bd_mutex);
+ mutex_lock_nested(&bdev->bd_mutex, for_part);
lock_kernel();
+ if (for_part)
+ bdev->bd_part_count--;
+
if (!--bdev->bd_openers) {
sync_blockdev(bdev);
kill_bdev(bdev);
}
if (bdev->bd_contains == bdev) {
if (disk->fops->release)
- ret = disk->fops->release(bd_inode, NULL);
- } else {
- mutex_lock(&bdev->bd_contains->bd_mutex);
- bdev->bd_contains->bd_part_count--;
- mutex_unlock(&bdev->bd_contains->bd_mutex);
+ ret = disk->fops->release(disk, mode);
}
if (!bdev->bd_openers) {
struct module *owner = disk->fops->owner;
put_disk(disk);
module_put(owner);
-
- if (bdev->bd_contains != bdev) {
- kobject_put(&bdev->bd_part->kobj);
- bdev->bd_part = NULL;
- }
+ disk_put_part(bdev->bd_part);
+ bdev->bd_part = NULL;
bdev->bd_disk = NULL;
bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
- if (bdev != bdev->bd_contains) {
- blkdev_put(bdev->bd_contains);
- }
+ if (bdev != bdev->bd_contains)
+ victim = bdev->bd_contains;
bdev->bd_contains = NULL;
}
unlock_kernel();
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)
+{
+ 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);
if (bdev->bd_holder == filp)
bd_release(bdev);
- return blkdev_put(bdev);
+ return blkdev_put(bdev, filp->f_mode);
}
-static ssize_t blkdev_file_write(struct file *file, const char __user *buf,
- size_t count, loff_t *ppos)
+static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
{
- struct iovec local_iov = { .iov_base = (void __user *)buf, .iov_len = count };
+ 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 generic_file_write_nolock(file, &local_iov, 1, ppos);
+ return blkdev_ioctl(bdev, mode, cmd, arg);
}
-static ssize_t blkdev_file_aio_write(struct kiocb *iocb, const char __user *buf,
- size_t count, loff_t pos)
+/*
+ * 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 iovec local_iov = { .iov_base = (void __user *)buf, .iov_len = count };
+ struct super_block *super = BDEV_I(page->mapping->host)->bdev.bd_super;
- return generic_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos);
-}
+ if (super && super->s_op->bdev_try_to_free_page)
+ return super->s_op->bdev_try_to_free_page(super, page, wait);
-static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
-{
- return blkdev_ioctl(file->f_mapping->host, file, cmd, arg);
+ return try_to_free_buffers(page);
}
-struct address_space_operations def_blk_aops = {
+static const struct address_space_operations def_blk_aops = {
.readpage = blkdev_readpage,
.writepage = blkdev_writepage,
.sync_page = block_sync_page,
- .prepare_write = blkdev_prepare_write,
- .commit_write = blkdev_commit_write,
+ .write_begin = blkdev_write_begin,
+ .write_end = blkdev_write_end,
.writepages = generic_writepages,
+ .releasepage = blkdev_releasepage,
.direct_IO = blkdev_direct_IO,
};
.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,
.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 res;
mm_segment_t old_fs = get_fs();
set_fs(KERNEL_DS);
- res = blkdev_ioctl(bdev->bd_inode, NULL, cmd, arg);
+ res = blkdev_ioctl(bdev, 0, cmd, arg);
set_fs(old_fs);
return res;
}
/**
* lookup_bdev - lookup a struct block_device by name
+ * @pathname: special file representing the block device
*
- * @path: special file representing the block device
- *
- * Get a reference to the blockdevice at @path in the current
+ * 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 *path)
+struct block_device *lookup_bdev(const char *pathname)
{
struct block_device *bdev;
struct inode *inode;
- struct nameidata nd;
+ struct path path;
int error;
- if (!path || !*path)
+ if (!pathname || !*pathname)
return ERR_PTR(-EINVAL);
- error = path_lookup(path, LOOKUP_FOLLOW, &nd);
+ error = kern_path(pathname, LOOKUP_FOLLOW, &path);
if (error)
return ERR_PTR(error);
- inode = nd.dentry->d_inode;
+ inode = path.dentry->d_inode;
error = -ENOTBLK;
if (!S_ISBLK(inode->i_mode))
goto fail;
error = -EACCES;
- if (nd.mnt->mnt_flags & MNT_NODEV)
+ if (path.mnt->mnt_flags & MNT_NODEV)
goto fail;
error = -ENOMEM;
bdev = bd_acquire(inode);
if (!bdev)
goto fail;
out:
- path_release(&nd);
+ path_put(&path);
return bdev;
fail:
bdev = ERR_PTR(error);
goto out;
}
+EXPORT_SYMBOL(lookup_bdev);
/**
- * open_bdev_excl - open a block device by name and set it up for use
+ * open_bdev_exclusive - open a block device by name and set it up for use
*
* @path: special file representing the block device
- * @flags: %MS_RDONLY for opening read-only
+ * @mode: FMODE_... combination to pass be used
* @holder: owner for exclusion
*
* Open the blockdevice described by the special file at @path, claim it
* for the @holder.
*/
-struct block_device *open_bdev_excl(const char *path, int flags, void *holder)
+struct block_device *open_bdev_exclusive(const char *path, fmode_t mode, void *holder)
{
struct block_device *bdev;
- mode_t mode = FMODE_READ;
int error = 0;
bdev = lookup_bdev(path);
if (IS_ERR(bdev))
return bdev;
- if (!(flags & MS_RDONLY))
- mode |= FMODE_WRITE;
- error = blkdev_get(bdev, mode, 0);
+ error = blkdev_get(bdev, mode);
if (error)
return ERR_PTR(error);
error = -EACCES;
- if (!(flags & MS_RDONLY) && bdev_read_only(bdev))
+ if ((mode & FMODE_WRITE) && bdev_read_only(bdev))
goto blkdev_put;
error = bd_claim(bdev, holder);
if (error)
return bdev;
blkdev_put:
- blkdev_put(bdev);
+ blkdev_put(bdev, mode);
return ERR_PTR(error);
}
-EXPORT_SYMBOL(open_bdev_excl);
+EXPORT_SYMBOL(open_bdev_exclusive);
/**
- * close_bdev_excl - release a blockdevice openen by open_bdev_excl()
+ * close_bdev_exclusive - close a blockdevice opened by open_bdev_exclusive()
*
* @bdev: blockdevice to close
+ * @mode: mode, must match that used to open.
*
- * This is the counterpart to open_bdev_excl().
+ * This is the counterpart to open_bdev_exclusive().
*/
-void close_bdev_excl(struct block_device *bdev)
+void close_bdev_exclusive(struct block_device *bdev, fmode_t mode)
{
bd_release(bdev);
- blkdev_put(bdev);
+ blkdev_put(bdev, mode);
}
-EXPORT_SYMBOL(close_bdev_excl);
+EXPORT_SYMBOL(close_bdev_exclusive);
+
+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);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff