X-Git-Url: http://ftp.safe.ca/?p=safe%2Fjmp%2Flinux-2.6;a=blobdiff_plain;f=fs%2Fblock_dev.c;h=99d6af8117473b661a64a5f05e58a024570d4fe0;hp=f02b7bdd9864874c5f038c792c20763a1bfa7437;hb=3e6c05052c262ebe7fdd85e75e9d4f956cdd8d82;hpb=50953fe9e00ebbeffa032a565ab2f08312d51a87

diff --git a/fs/block_dev.c b/fs/block_dev.c
index f02b7bd..99d6af8 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -12,16 +12,20 @@
 #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/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"
 
@@ -30,6 +34,8 @@ struct bdev_inode {
 	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);
@@ -67,11 +73,11 @@ static void kill_bdev(struct block_device *bdev)
 int set_blocksize(struct block_device *bdev, int size)
 {
 	/* Size must be a power of two, and between 512 and PAGE_SIZE */
-	if (size > PAGE_SIZE || size < 512 || (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 */
-	if (size < bdev_hardsect_size(bdev))
+	if (size < bdev_logical_block_size(bdev))
 		return -EINVAL;
 
 	/* Don't change the size if it is same as current */
@@ -101,7 +107,7 @@ EXPORT_SYMBOL(sb_set_blocksize);
 
 int sb_min_blocksize(struct super_block *sb, int size)
 {
-	int minsize = bdev_hardsect_size(sb->s_bdev);
+	int minsize = bdev_logical_block_size(sb->s_bdev);
 	if (size < minsize)
 		size = minsize;
 	return sb_set_blocksize(sb, size);
@@ -166,206 +172,128 @@ blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 
-	return blockdev_direct_IO_no_locking(rw, iocb, inode, I_BDEV(inode),
-				iov, offset, nr_segs, blkdev_get_blocks, NULL);
+	return blockdev_direct_IO_no_locking_newtrunc(rw, iocb, inode,
+				I_BDEV(inode), iov, offset, nr_segs,
+				blkdev_get_blocks, NULL);
 }
 
-#if 0
-static int blk_end_aio(struct bio *bio, unsigned int bytes_done, int error)
+int __sync_blockdev(struct block_device *bdev, int wait)
 {
-	struct kiocb *iocb = bio->bi_private;
-	atomic_t *bio_count = &iocb->ki_bio_count;
-
-	if (bio_data_dir(bio) == READ)
-		bio_check_pages_dirty(bio);
-	else {
-		bio_release_pages(bio);
-		bio_put(bio);
-	}
-
-	/* iocb->ki_nbytes stores error code from LLDD */
-	if (error)
-		iocb->ki_nbytes = -EIO;
-
-	if (atomic_dec_and_test(bio_count)) {
-		if ((long)iocb->ki_nbytes < 0)
-			aio_complete(iocb, iocb->ki_nbytes, 0);
-		else
-			aio_complete(iocb, iocb->ki_left, 0);
-	}
-
-	return 0;
+	if (!bdev)
+		return 0;
+	if (!wait)
+		return filemap_flush(bdev->bd_inode->i_mapping);
+	return filemap_write_and_wait(bdev->bd_inode->i_mapping);
 }
 
-#define VEC_SIZE	16
-struct pvec {
-	unsigned short nr;
-	unsigned short idx;
-	struct page *page[VEC_SIZE];
-};
-
-#define PAGES_SPANNED(addr, len)	\
-	(DIV_ROUND_UP((addr) + (len), PAGE_SIZE) - (addr) / PAGE_SIZE);
-
 /*
- * get page pointer for user addr, we internally cache struct page array for
- * (addr, count) range in pvec to avoid frequent call to get_user_pages.  If
- * internal page list is exhausted, a batch count of up to VEC_SIZE is used
- * to get next set of page struct.
+ * Write out and wait upon all the dirty data associated with a block
+ * device via its mapping.  Does not take the superblock lock.
  */
-static struct page *blk_get_page(unsigned long addr, size_t count, int rw,
-				 struct pvec *pvec)
-{
-	int ret, nr_pages;
-	if (pvec->idx == pvec->nr) {
-		nr_pages = PAGES_SPANNED(addr, count);
-		nr_pages = min(nr_pages, VEC_SIZE);
-		down_read(&current->mm->mmap_sem);
-		ret = get_user_pages(current, current->mm, addr, nr_pages,
-				     rw == READ, 0, pvec->page, NULL);
-		up_read(&current->mm->mmap_sem);
-		if (ret < 0)
-			return ERR_PTR(ret);
-		pvec->nr = ret;
-		pvec->idx = 0;
-	}
-	return pvec->page[pvec->idx++];
+int sync_blockdev(struct block_device *bdev)
+{
+	return __sync_blockdev(bdev, 1);
 }
+EXPORT_SYMBOL(sync_blockdev);
 
-/* return a page back to pvec array */
-static void blk_unget_page(struct page *page, struct pvec *pvec)
+/*
+ * 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)
 {
-	pvec->page[--pvec->idx] = page;
+	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);
 
-static ssize_t
-blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
-		 loff_t pos, unsigned long nr_segs)
-{
-	struct inode *inode = iocb->ki_filp->f_mapping->host;
-	unsigned blkbits = blksize_bits(bdev_hardsect_size(I_BDEV(inode)));
-	unsigned blocksize_mask = (1 << blkbits) - 1;
-	unsigned long seg = 0;	/* iov segment iterator */
-	unsigned long nvec;	/* number of bio vec needed */
-	unsigned long cur_off;	/* offset into current page */
-	unsigned long cur_len;	/* I/O len of current page, up to PAGE_SIZE */
-
-	unsigned long addr;	/* user iovec address */
-	size_t count;		/* user iovec len */
-	size_t nbytes = iocb->ki_nbytes = iocb->ki_left; /* total xfer size */
-	loff_t size;		/* size of block device */
-	struct bio *bio;
-	atomic_t *bio_count = &iocb->ki_bio_count;
-	struct page *page;
-	struct pvec pvec;
-
-	pvec.nr = 0;
-	pvec.idx = 0;
-
-	if (pos & blocksize_mask)
-		return -EINVAL;
+/**
+ * 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;
 
-	size = i_size_read(inode);
-	if (pos + nbytes > size) {
-		nbytes = size - pos;
-		iocb->ki_left = nbytes;
+	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;
 	}
 
-	/*
-	 * check first non-zero iov alignment, the remaining
-	 * iov alignment is checked inside bio loop below.
-	 */
-	do {
-		addr = (unsigned long) iov[seg].iov_base;
-		count = min(iov[seg].iov_len, nbytes);
-		if (addr & blocksize_mask || count & blocksize_mask)
-			return -EINVAL;
-	} while (!count && ++seg < nr_segs);
-	atomic_set(bio_count, 1);
-
-	while (nbytes) {
-		/* roughly estimate number of bio vec needed */
-		nvec = (nbytes + PAGE_SIZE - 1) / PAGE_SIZE;
-		nvec = max(nvec, nr_segs - seg);
-		nvec = min(nvec, (unsigned long) BIO_MAX_PAGES);
-
-		/* bio_alloc should not fail with GFP_KERNEL flag */
-		bio = bio_alloc(GFP_KERNEL, nvec);
-		bio->bi_bdev = I_BDEV(inode);
-		bio->bi_end_io = blk_end_aio;
-		bio->bi_private = iocb;
-		bio->bi_sector = pos >> blkbits;
-same_bio:
-		cur_off = addr & ~PAGE_MASK;
-		cur_len = PAGE_SIZE - cur_off;
-		if (count < cur_len)
-			cur_len = count;
-
-		page = blk_get_page(addr, count, rw, &pvec);
-		if (unlikely(IS_ERR(page)))
-			goto backout;
-
-		if (bio_add_page(bio, page, cur_len, cur_off)) {
-			pos += cur_len;
-			addr += cur_len;
-			count -= cur_len;
-			nbytes -= cur_len;
-
-			if (count)
-				goto same_bio;
-			while (++seg < nr_segs) {
-				addr = (unsigned long) iov[seg].iov_base;
-				count = iov[seg].iov_len;
-				if (!count)
-					continue;
-				if (unlikely(addr & blocksize_mask ||
-					     count & blocksize_mask)) {
-					page = ERR_PTR(-EINVAL);
-					goto backout;
-				}
-				count = min(count, nbytes);
-				goto same_bio;
-			}
-		} else {
-			blk_unget_page(page, &pvec);
-		}
-
-		/* bio is ready, submit it */
-		if (rw == READ)
-			bio_set_pages_dirty(bio);
-		atomic_inc(bio_count);
-		submit_bio(rw, bio);
+	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);
 
-completion:
-	iocb->ki_left -= nbytes;
-	nbytes = iocb->ki_left;
-	iocb->ki_pos += nbytes;
+/**
+ * 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;
 
-	blk_run_address_space(inode->i_mapping);
-	if (atomic_dec_and_test(bio_count))
-		aio_complete(iocb, nbytes, 0);
+	mutex_lock(&bdev->bd_fsfreeze_mutex);
+	if (!bdev->bd_fsfreeze_count)
+		goto out;
 
-	return -EIOCBQUEUED;
+	error = 0;
+	if (--bdev->bd_fsfreeze_count > 0)
+		goto out;
 
-backout:
-	/*
-	 * back out nbytes count constructed so far for this bio,
-	 * we will throw away current bio.
-	 */
-	nbytes += bio->bi_size;
-	bio_release_pages(bio);
-	bio_put(bio);
+	if (!sb)
+		goto out;
 
-	/*
-	 * if no bio was submmitted, return the error code.
-	 * otherwise, proceed with pending I/O completion.
-	 */
-	if (atomic_read(bio_count) == 1)
-		return PTR_ERR(page);
-	goto completion;
+	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;
 }
-#endif
+EXPORT_SYMBOL(thaw_bdev);
 
 static int blkdev_writepage(struct page *page, struct writeback_control *wbc)
 {
@@ -377,14 +305,26 @@ static int blkdev_readpage(struct file * file, struct page * page)
 	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_newtrunc(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;
 }
 
 /*
@@ -419,15 +359,28 @@ static loff_t block_llseek(struct file *file, loff_t offset, int origin)
 	return retval;
 }
 	
-/*
- *	Filp is never NULL; the only case when ->fsync() is called with
- *	NULL first argument is nfsd_sync_dir() and that's not a directory.
- */
- 
-static int block_fsync(struct file *filp, struct dentry *dentry, int datasync)
+int blkdev_fsync(struct file *filp, int datasync)
 {
-	return sync_blockdev(I_BDEV(filp->f_mapping->host));
+	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, BLKDEV_IFL_WAIT);
+	if (error == -EOPNOTSUPP)
+		error = 0;
+
+	mutex_lock(&bd_inode->i_mutex);
+
+	return error;
 }
+EXPORT_SYMBOL(blkdev_fsync);
 
 /*
  * pseudo-fs
@@ -448,26 +401,24 @@ static void bdev_destroy_inode(struct inode *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, struct kmem_cache * 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_CONSTRUCTOR) {
-		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);
+	memset(bdev, 0, sizeof(*bdev));
+	mutex_init(&bdev->bd_mutex);
+	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)
@@ -509,23 +460,28 @@ static struct file_system_type bd_type = {
 	.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");
+	/*
+	 * 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 */
 }
 
@@ -557,7 +513,7 @@ struct block_device *bdget(dev_t dev)
 	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)
@@ -587,14 +543,22 @@ struct block_device *bdget(dev_t dev)
 
 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)
+{
+	atomic_inc(&bdev->bd_inode->i_count);
+	return bdev;
+}
+
 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);
@@ -649,7 +613,7 @@ void bd_forget(struct inode *inode)
 
 	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);
 	}
@@ -659,41 +623,233 @@ void bd_forget(struct inode *inode)
 		iput(bdev->bd_inode);
 }
 
-int bd_claim(struct block_device *bdev, void *holder)
+/**
+ * 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)
 {
-	int res;
-	spin_lock(&bdev_lock);
-
-	/* first decide result */
 	if (bdev->bd_holder == holder)
-		res = 0;	 /* already a holder */
+		return true;	 /* already a holder */
 	else if (bdev->bd_holder != NULL)
-		res = -EBUSY; 	 /* held by someone else */
+		return false; 	 /* held by someone else */
 	else if (bdev->bd_contains == bdev)
-		res = 0;  	 /* is a whole device which isn't held */
+		return true;  	 /* is a whole device which isn't held */
 
-	else if (bdev->bd_contains->bd_holder == bd_claim)
-		res = 0; 	 /* is a partition of a device that is being partitioned */
-	else if (bdev->bd_contains->bd_holder != NULL)
-		res = -EBUSY;	 /* is a partition of a held device */
+	else if (whole->bd_holder == bd_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
-		res = 0;	 /* is a partition of an un-held device */
+		return true;	 /* is a partition of an un-held device */
+}
 
-	/* now impose change */
-	if (res==0) {
-		/* note that for a whole device bd_holders
-		 * will be incremented twice, and bd_holder will
-		 * be set to bd_claim before being set to holder
-		 */
-		bdev->bd_contains->bd_holders ++;
-		bdev->bd_contains->bd_holder = bd_claim;
-		bdev->bd_holders++;
-		bdev->bd_holder = holder;
+/**
+ * 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 someone else is claiming, wait for it to finish */
+	if (whole->bd_claiming && whole->bd_claiming != holder) {
+		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);
 	}
+}
+
+/* releases bdev_lock */
+static void __bd_abort_claiming(struct block_device *whole, void *holder)
+{
+	BUG_ON(whole->bd_claiming != holder);
+	whole->bd_claiming = NULL;
+	wake_up_bit(&whole->bd_claiming, 0);
+
 	spin_unlock(&bdev_lock);
-	return res;
+	bdput(whole);
 }
 
+/**
+ * bd_abort_claiming - abort claiming a block device
+ * @whole: whole block device returned by bd_start_claiming()
+ * @holder: holder trying to claim @bdev
+ *
+ * Abort a claiming block started by bd_start_claiming().  Note that
+ * @whole is not the block device to be claimed but the whole device
+ * returned by bd_start_claiming().
+ *
+ * CONTEXT:
+ * Grabs and releases bdev_lock.
+ */
+static void bd_abort_claiming(struct block_device *whole, void *holder)
+{
+	spin_lock(&bdev_lock);
+	__bd_abort_claiming(whole, holder);		/* releases bdev_lock */
+}
+
+/* increment holders when we have a legitimate claim. requires bdev_lock */
+static void __bd_claim(struct block_device *bdev, struct block_device *whole,
+					void *holder)
+{
+	/* note that for a whole device bd_holders
+	 * will be incremented twice, and bd_holder will
+	 * be set to bd_claim before being set to holder
+	 */
+	whole->bd_holders++;
+	whole->bd_holder = bd_claim;
+	bdev->bd_holders++;
+	bdev->bd_holder = holder;
+}
+
+/**
+ * bd_finish_claiming - finish claiming a block device
+ * @bdev: block device of interest (passed to bd_start_claiming())
+ * @whole: whole block device returned by bd_start_claiming()
+ * @holder: holder trying to claim @bdev
+ *
+ * Finish a claiming block started by bd_start_claiming().
+ *
+ * CONTEXT:
+ * Grabs and releases bdev_lock.
+ */
+static void bd_finish_claiming(struct block_device *bdev,
+				struct block_device *whole, void *holder)
+{
+	spin_lock(&bdev_lock);
+	BUG_ON(!bd_may_claim(bdev, whole, holder));
+	__bd_claim(bdev, whole, holder);
+	__bd_abort_claiming(whole, holder); /* not actually an abort */
+}
+
+/**
+ * bd_claim - claim a block device
+ * @bdev: block device to claim
+ * @holder: holder trying to claim @bdev
+ *
+ * Try to claim @bdev which must have been opened successfully.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * 0 if successful, -EBUSY if @bdev is already claimed.
+ */
+int bd_claim(struct block_device *bdev, void *holder)
+{
+	struct block_device *whole = bdev->bd_contains;
+	int res;
+
+	might_sleep();
+
+	spin_lock(&bdev_lock);
+	res = bd_prepare_to_claim(bdev, whole, holder);
+	if (res == 0)
+		__bd_claim(bdev, whole, holder);
+	spin_unlock(&bdev_lock);
+
+	return res;
+}
 EXPORT_SYMBOL(bd_claim);
 
 void bd_release(struct block_device *bdev)
@@ -726,22 +882,6 @@ EXPORT_SYMBOL(bd_release);
  *           /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)
@@ -790,11 +930,11 @@ static int bd_holder_grab_dirs(struct block_device *bdev,
 	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;
 
@@ -875,7 +1015,7 @@ static struct bd_holder *find_bd_holder(struct block_device *bdev,
  */
 static int add_bd_holder(struct block_device *bdev, struct bd_holder *bo)
 {
-	int ret;
+	int err;
 
 	if (!bo)
 		return -EINVAL;
@@ -883,15 +1023,18 @@ static int add_bd_holder(struct block_device *bdev, struct bd_holder *bo)
 	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);
+	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;
 	}
-	if (ret == 0)
-		list_add_tail(&bo->list, &bdev->bd_holder_list);
-	return ret;
+
+	list_add_tail(&bo->list, &bdev->bd_holder_list);
+	return 0;
 }
 
 /**
@@ -949,7 +1092,7 @@ static struct bd_holder *del_bd_holder(struct block_device *bdev,
 static int bd_claim_by_kobject(struct block_device *bdev, void *holder,
 				struct kobject *kobj)
 {
-	int res;
+	int err;
 	struct bd_holder *bo, *found;
 
 	if (!kobj)
@@ -960,21 +1103,24 @@ static int bd_claim_by_kobject(struct block_device *bdev, void *holder,
 		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);
+	err = bd_claim(bdev, holder);
+	if (err)
+		goto fail;
 
-	return res;
+	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;
 }
 
 /**
@@ -988,15 +1134,12 @@ static int bd_claim_by_kobject(struct block_device *bdev, void *holder,
 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);
 }
 
@@ -1039,18 +1182,98 @@ EXPORT_SYMBOL_GPL(bd_release_from_disk);
  * 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
@@ -1063,20 +1286,16 @@ EXPORT_SYMBOL(open_by_devnum);
 int check_disk_change(struct block_device *bdev)
 {
 	struct gendisk *disk = bdev->bd_disk;
-	struct block_device_operations * bdops = disk->fops;
+	const struct block_device_operations *bdops = disk->fops;
 
 	if (!bdops->media_changed)
 		return 0;
 	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;
 }
 
@@ -1084,7 +1303,7 @@ EXPORT_SYMBOL(check_disk_change);
 
 void bd_set_size(struct block_device *bdev, loff_t size)
 {
-	unsigned bsize = bdev_hardsect_size(bdev);
+	unsigned bsize = bdev_logical_block_size(bdev);
 
 	bdev->bd_inode->i_size = size;
 	while (bsize < PAGE_CACHE_SIZE) {
@@ -1097,9 +1316,7 @@ void bd_set_size(struct block_device *bdev, loff_t size)
 }
 EXPORT_SYMBOL(bd_set_size);
 
-static int __blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags,
-			int for_part);
-static int __blkdev_put(struct block_device *bdev, int for_part);
+static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 
 /*
  * bd_mutex locking:
@@ -1108,33 +1325,63 @@ static int __blkdev_put(struct block_device *bdev, int for_part);
  *    mutex_lock_nested(whole->bd_mutex, 1)
  */
 
-static int do_open(struct block_device *bdev, struct file *file, int for_part)
+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;
+	int ret;
+	int partno;
+	int perm = 0;
 
-	file->f_mapping = bdev->bd_inode->i_mapping;
-	lock_kernel();
-	disk = get_gendisk(bdev->bd_dev, &part);
-	if (!disk) {
-		unlock_kernel();
+	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;
+
+	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);
@@ -1146,36 +1393,35 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 			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;
+				goto out_clear;
 			BUG_ON(for_part);
-			ret = __blkdev_get(whole, file->f_mode, file->f_flags, 1);
+			ret = __blkdev_get(whole, mode, 1);
 			if (ret)
-				goto out_first;
+				goto out_clear;
 			bdev->bd_contains = whole;
-			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) {
+			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);
+			bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
 		}
 	} else {
+		module_put(disk->fops->owner);
 		put_disk(disk);
-		module_put(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);
@@ -1188,49 +1434,36 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 	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, 1);
+		__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);
-	return ret;
-}
 
-static int __blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags,
-			int for_part)
-{
-	/*
-	 * 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_path.dentry = &fake_dentry;
-	fake_dentry.d_inode = bdev->bd_inode;
+	if (disk)
+		module_put(disk->fops->owner);
+	put_disk(disk);
+	bdput(bdev);
 
-	return do_open(bdev, &fake_file, for_part);
+	return ret;
 }
 
-int blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags)
+int blkdev_get(struct block_device *bdev, fmode_t mode)
 {
-	return __blkdev_get(bdev, mode, flags, 0);
+	return __blkdev_get(bdev, mode, 0);
 }
 EXPORT_SYMBOL(blkdev_get);
 
 static int blkdev_open(struct inode * inode, struct file * filp)
 {
+	struct block_device *whole = NULL;
 	struct block_device *bdev;
 	int res;
 
@@ -1242,28 +1475,42 @@ 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;
 
-	res = do_open(bdev, filp, 0);
-	if (res)
-		return res;
+	if (filp->f_mode & FMODE_EXCL) {
+		whole = bd_start_claiming(bdev, filp);
+		if (IS_ERR(whole)) {
+			bdput(bdev);
+			return PTR_ERR(whole);
+		}
+	}
 
-	if (!(filp->f_flags & O_EXCL) )
-		return 0;
+	filp->f_mapping = bdev->bd_inode->i_mapping;
 
-	if (!(res = bd_claim(bdev, filp)))
-		return 0;
+	res = blkdev_get(bdev, filp->f_mode);
+
+	if (whole) {
+		if (res == 0)
+			bd_finish_claiming(bdev, whole, filp);
+		else
+			bd_abort_claiming(whole, filp);
+	}
 
-	blkdev_put(bdev);
 	return res;
 }
 
-static int __blkdev_put(struct block_device *bdev, int for_part)
+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;
 
@@ -1278,18 +1525,15 @@ static int __blkdev_put(struct block_device *bdev, int for_part)
 	}
 	if (bdev->bd_contains == bdev) {
 		if (disk->fops->release)
-			ret = disk->fops->release(bd_inode, NULL);
+			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)
@@ -1300,13 +1544,13 @@ static int __blkdev_put(struct block_device *bdev, int for_part)
 	mutex_unlock(&bdev->bd_mutex);
 	bdput(bdev);
 	if (victim)
-		__blkdev_put(victim, 1);
+		__blkdev_put(victim, mode, 1);
 	return ret;
 }
 
-int blkdev_put(struct block_device *bdev)
+int blkdev_put(struct block_device *bdev, fmode_t mode)
 {
-	return __blkdev_put(bdev, 0);
+	return __blkdev_put(bdev, mode, 0);
 }
 EXPORT_SYMBOL(blkdev_put);
 
@@ -1315,21 +1559,75 @@ 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 long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 {
-	return blkdev_ioctl(file->f_mapping->host, file, cmd, 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);
 
-const struct address_space_operations def_blk_aops = {
+/*
+ * 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,
-	.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,
 };
 
@@ -1340,14 +1638,13 @@ const struct file_operations def_blk_fops = {
 	.read		= do_sync_read,
 	.write		= do_sync_write,
   	.aio_read	= generic_file_aio_read,
-  	.aio_write	= generic_file_aio_write_nolock,
+	.aio_write	= blkdev_aio_write,
 	.mmap		= generic_file_mmap,
-	.fsync		= block_fsync,
+	.fsync		= blkdev_fsync,
 	.unlocked_ioctl	= block_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= compat_blkdev_ioctl,
 #endif
-	.sendfile	= generic_file_sendfile,
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= generic_file_splice_write,
 };
@@ -1357,7 +1654,7 @@ 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->bd_inode, NULL, cmd, arg);
+	res = blkdev_ioctl(bdev, 0, cmd, arg);
 	set_fs(old_fs);
 	return res;
 }
@@ -1366,101 +1663,106 @@ EXPORT_SYMBOL(ioctl_by_bdev);
 
 /**
  * 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;
+	struct block_device *bdev, *whole;
+	int error;
 
 	bdev = lookup_bdev(path);
 	if (IS_ERR(bdev))
 		return bdev;
 
-	if (!(flags & MS_RDONLY))
-		mode |= FMODE_WRITE;
-	error = blkdev_get(bdev, mode, 0);
+	whole = bd_start_claiming(bdev, holder);
+	if (IS_ERR(whole)) {
+		bdput(bdev);
+		return whole;
+	}
+
+	error = blkdev_get(bdev, mode);
 	if (error)
-		return ERR_PTR(error);
+		goto out_abort_claiming;
+
 	error = -EACCES;
-	if (!(flags & MS_RDONLY) && bdev_read_only(bdev))
-		goto blkdev_put;
-	error = bd_claim(bdev, holder);
-	if (error)
-		goto blkdev_put;
+	if ((mode & FMODE_WRITE) && bdev_read_only(bdev))
+		goto out_blkdev_put;
 
+	bd_finish_claiming(bdev, whole, holder);
 	return bdev;
-	
-blkdev_put:
-	blkdev_put(bdev);
+
+out_blkdev_put:
+	blkdev_put(bdev, mode);
+out_abort_claiming:
+	bd_abort_claiming(whole, holder);
 	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)
 {