int set_blocksize(struct block_device *bdev, int size)
{
- int oldsize;
-
/* Size must be a power of two, and between 512 and PAGE_SIZE */
if (size > PAGE_SIZE || size < 512 || (size & (size-1)))
return -EINVAL;
if (size < bdev_hardsect_size(bdev))
return -EINVAL;
- oldsize = bdev->bd_block_size;
- if (oldsize == size)
- return 0;
-
- /* Ok, we're actually changing the blocksize.. */
- sync_blockdev(bdev);
- bdev->bd_block_size = size;
- bdev->bd_inode->i_blkbits = blksize_bits(size);
- kill_bdev(bdev);
+ /* 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;
}
int sb_set_blocksize(struct super_block *sb, int size)
{
- int bits;
- if (set_blocksize(sb->s_bdev, size) < 0)
+ 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 (bits = 9, size >>= 9; 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)
{
- if ((iblock + max_blocks) > max_block(I_BDEV(inode)))
- return -EIO;
+ 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;
- set_buffer_mapped(bh);
+ if (max_blocks)
+ set_buffer_mapped(bh);
return 0;
}
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;
}
* pseudo-fs
*/
-static spinlock_t bdev_lock __cacheline_aligned_in_smp = SPIN_LOCK_UNLOCKED;
-static kmem_cache_t * bdev_cachep;
+static __cacheline_aligned_in_smp DEFINE_SPINLOCK(bdev_lock);
+static kmem_cache_t * bdev_cachep __read_mostly;
static struct inode *bdev_alloc_inode(struct super_block *sb)
{
static void bdev_destroy_inode(struct inode *inode)
{
- kmem_cache_free(bdev_cachep, BDEV_I(inode));
+ struct bdev_inode *bdi = BDEV_I(inode);
+
+ bdi->bdev.bd_inode_backing_dev_info = NULL;
+ kmem_cache_free(bdev_cachep, bdi);
}
static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags)
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);
}
}
.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,
- init_once,
- NULL);
- if (!bdev_cachep)
- panic("Cannot create bdev_cache SLAB cache");
+ 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);
err = register_filesystem(&bd_type);
if (err)
panic("Cannot register bdev pseudo-fs");
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 void add_symlink(struct kobject *from, struct kobject *to)
+{
+ if (!from || !to)
+ 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);
+}
+
+/**
+ * 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.
+ *
+ * Returns 1 if @bo was added to the list.
+ * Returns 0 if @bo wasn't used by any reason and should be freed.
+ */
+static int add_bd_holder(struct block_device *bdev, struct bd_holder *bo)
+{
+ struct bd_holder *tmp;
+
+ if (!bo)
+ return 0;
+
+ list_for_each_entry(tmp, &bdev->bd_holder_list, list) {
+ if (tmp->sdir == bo->sdir) {
+ tmp->count++;
+ return 0;
+ }
+ }
+
+ if (!bd_holder_grab_dirs(bdev, bo))
+ return 0;
+
+ add_symlink(bo->sdir, bo->sdev);
+ add_symlink(bo->hdir, bo->hdev);
+ list_add_tail(&bo->list, &bdev->bd_holder_list);
+ return 1;
+}
+
+/**
+ * del_bd_holder - delete sysfs symlinks for bd_claim() relationship
+ *
+ * @bdev: block device to be bd_claimed
+ * @kobj: holder's kobject
+ *
+ * If there is matching entry with @kobj in @bdev->bd_holder_list
+ * and no other bd_claim() from the same kobject,
+ * remove the struct bd_holder from the list, delete symlinks for it.
+ *
+ * Returns a pointer to the struct bd_holder when it's removed from the list
+ * and ready to be freed.
+ * Returns NULL if matching claim isn't found or there is other bd_claim()
+ * by the same kobject.
+ */
+static struct bd_holder *del_bd_holder(struct block_device *bdev,
+ struct kobject *kobj)
+{
+ struct bd_holder *bo;
+
+ list_for_each_entry(bo, &bdev->bd_holder_list, list) {
+ if (bo->sdir == kobj) {
+ bo->count--;
+ BUG_ON(bo->count < 0);
+ if (!bo->count) {
+ list_del(&bo->list);
+ del_symlink(bo->sdir, bo->sdev);
+ del_symlink(bo->hdir, bo->hdev);
+ bd_holder_release_dirs(bo);
+ return bo;
+ }
+ break;
+ }
+ }
+
+ return NULL;
+}
+
+/**
+ * bd_claim_by_kobject - bd_claim() with additional kobject signature
+ *
+ * @bdev: block device to be claimed
+ * @holder: holder's signature
+ * @kobj: holder's kobject
+ *
+ * Do bd_claim() and if it succeeds, create sysfs symlinks between
+ * the bdev and the holder's kobject.
+ * Use bd_release_from_kobject() when relesing the claimed bdev.
+ *
+ * Returns 0 on success. (same as bd_claim())
+ * Returns errno on failure.
+ */
+static int bd_claim_by_kobject(struct block_device *bdev, void *holder,
+ struct kobject *kobj)
+{
+ int res;
+ struct bd_holder *bo;
+
+ if (!kobj)
+ return -EINVAL;
+
+ bo = alloc_bd_holder(kobj);
+ if (!bo)
+ return -ENOMEM;
+
+ 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;
+}
+
+/**
+ * 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
if (!bdops->media_changed(bdev->bd_disk))
return 0;
- if (__invalidate_device(bdev, 0))
+ if (__invalidate_device(bdev))
printk("VFS: busy inodes on changed media.\n");
if (bdops->revalidate_disk)
}
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);
EXPORT_SYMBOL(blkdev_get);
-int blkdev_open(struct inode * inode, struct file * filp)
+static int blkdev_open(struct inode * inode, struct file * filp)
{
struct block_device *bdev;
int res;
return res;
}
-EXPORT_SYMBOL(blkdev_open);
-
int blkdev_put(struct block_device *bdev)
{
int ret = 0;
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 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);
}
.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,
.aio_write = blkdev_file_aio_write,
.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,
};
-EXPORT_SYMBOL(def_blk_fops);
-
int ioctl_by_bdev(struct block_device *bdev, unsigned cmd, unsigned long arg)
{
int res;
git://git.onelab.eu / linux-2.6.git / blobdiff