1 files changed, 145 insertions, 81 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 8c3c6899ccf3..73d6a735b8f3 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -25,6 +25,7 @@
 #include <linux/uio.h>
 #include <linux/namei.h>
 #include <linux/log2.h>
+#include <linux/kmemleak.h>
 #include <asm/uaccess.h>
 #include "internal.h"
 
@@ -76,7 +77,7 @@ int set_blocksize(struct block_device *bdev, int 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 */
@@ -106,7 +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);
@@ -175,17 +176,22 @@ blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 				iov, offset, nr_segs, blkdev_get_blocks, NULL);
 }
 
+int __sync_blockdev(struct block_device *bdev, int wait)
+{
+	if (!bdev)
+		return 0;
+	if (!wait)
+		return filemap_flush(bdev->bd_inode->i_mapping);
+	return filemap_write_and_wait(bdev->bd_inode->i_mapping);
+}
+
 /*
  * Write out and wait upon all the dirty data associated with a block
  * device via its mapping.  Does not take the superblock lock.
  */
 int sync_blockdev(struct block_device *bdev)
 {
-	int ret = 0;
-
-	if (bdev)
-		ret = filemap_write_and_wait(bdev->bd_inode->i_mapping);
-	return ret;
+	return __sync_blockdev(bdev, 1);
 }
 EXPORT_SYMBOL(sync_blockdev);
 
@@ -198,19 +204,18 @@ int fsync_bdev(struct block_device *bdev)
 {
 	struct super_block *sb = get_super(bdev);
 	if (sb) {
-		int res = fsync_super(sb);
+		int res = sync_filesystem(sb);
 		drop_super(sb);
 		return res;
 	}
 	return sync_blockdev(bdev);
 }
+EXPORT_SYMBOL(fsync_bdev);
 
 /**
  * freeze_bdev  --  lock a filesystem and force it into a consistent state
  * @bdev:	blockdevice to lock
  *
- * This takes the block device bd_mount_sem to make sure no new mounts
- * happen on bdev until thaw_bdev() is called.
  * 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
@@ -225,46 +230,55 @@ struct super_block *freeze_bdev(struct block_device *bdev)
 	int error = 0;
 
 	mutex_lock(&bdev->bd_fsfreeze_mutex);
-	if (bdev->bd_fsfreeze_count > 0) {
-		bdev->bd_fsfreeze_count++;
+	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;
 	}
-	bdev->bd_fsfreeze_count++;
-
-	down(&bdev->bd_mount_sem);
-	sb = get_super(bdev);
-	if (sb && !(sb->s_flags & MS_RDONLY)) {
-		sb->s_frozen = SB_FREEZE_WRITE;
-		smp_wmb();
-
-		__fsync_super(sb);
-
-		sb->s_frozen = SB_FREEZE_TRANS;
-		smp_wmb();
-
-		sync_blockdev(sb->s_bdev);
-
-		if (sb->s_op->freeze_fs) {
-			error = sb->s_op->freeze_fs(sb);
-			if (error) {
-				printk(KERN_ERR
-					"VFS:Filesystem freeze failed\n");
-				sb->s_frozen = SB_UNFROZEN;
-				drop_super(sb);
-				up(&bdev->bd_mount_sem);
-				bdev->bd_fsfreeze_count--;
-				mutex_unlock(&bdev->bd_fsfreeze_mutex);
-				return ERR_PTR(error);
-			}
+
+	sb = get_active_super(bdev);
+	if (!sb)
+		goto out;
+	if (sb->s_flags & MS_RDONLY) {
+		deactivate_locked_super(sb);
+		mutex_unlock(&bdev->bd_fsfreeze_mutex);
+		return sb;
+	}
+
+	sb->s_frozen = SB_FREEZE_WRITE;
+	smp_wmb();
+
+	sync_filesystem(sb);
+
+	sb->s_frozen = SB_FREEZE_TRANS;
+	smp_wmb();
+
+	sync_blockdev(sb->s_bdev);
+
+	if (sb->s_op->freeze_fs) {
+		error = sb->s_op->freeze_fs(sb);
+		if (error) {
+			printk(KERN_ERR
+				"VFS:Filesystem freeze failed\n");
+			sb->s_frozen = SB_UNFROZEN;
+			deactivate_locked_super(sb);
+			bdev->bd_fsfreeze_count--;
+			mutex_unlock(&bdev->bd_fsfreeze_mutex);
+			return ERR_PTR(error);
 		}
 	}
+	up_write(&sb->s_umount);
 
+ out:
 	sync_blockdev(bdev);
 	mutex_unlock(&bdev->bd_fsfreeze_mutex);
-
-	return sb;	/* thaw_bdev releases s->s_umount and bd_mount_sem */
+	return sb;	/* thaw_bdev releases s->s_umount */
 }
 EXPORT_SYMBOL(freeze_bdev);
 
@@ -277,44 +291,44 @@ EXPORT_SYMBOL(freeze_bdev);
  */
 int thaw_bdev(struct block_device *bdev, struct super_block *sb)
 {
-	int error = 0;
+	int error = -EINVAL;
 
 	mutex_lock(&bdev->bd_fsfreeze_mutex);
-	if (!bdev->bd_fsfreeze_count) {
-		mutex_unlock(&bdev->bd_fsfreeze_mutex);
-		return -EINVAL;
-	}
-
-	bdev->bd_fsfreeze_count--;
-	if (bdev->bd_fsfreeze_count > 0) {
-		if (sb)
-			drop_super(sb);
-		mutex_unlock(&bdev->bd_fsfreeze_mutex);
-		return 0;
-	}
-
-	if (sb) {
-		BUG_ON(sb->s_bdev != bdev);
-		if (!(sb->s_flags & MS_RDONLY)) {
-			if (sb->s_op->unfreeze_fs) {
-				error = sb->s_op->unfreeze_fs(sb);
-				if (error) {
-					printk(KERN_ERR
-						"VFS:Filesystem thaw failed\n");
-					sb->s_frozen = SB_FREEZE_TRANS;
-					bdev->bd_fsfreeze_count++;
-					mutex_unlock(&bdev->bd_fsfreeze_mutex);
-					return error;
-				}
-			}
-			sb->s_frozen = SB_UNFROZEN;
-			smp_wmb();
-			wake_up(&sb->s_wait_unfrozen);
+	if (!bdev->bd_fsfreeze_count)
+		goto out_unlock;
+
+	error = 0;
+	if (--bdev->bd_fsfreeze_count > 0)
+		goto out_unlock;
+
+	if (!sb)
+		goto out_unlock;
+
+	BUG_ON(sb->s_bdev != bdev);
+	down_write(&sb->s_umount);
+	if (sb->s_flags & MS_RDONLY)
+		goto out_deactivate;
+
+	if (sb->s_op->unfreeze_fs) {
+		error = sb->s_op->unfreeze_fs(sb);
+		if (error) {
+			printk(KERN_ERR
+				"VFS:Filesystem thaw failed\n");
+			sb->s_frozen = SB_FREEZE_TRANS;
+			bdev->bd_fsfreeze_count++;
+			mutex_unlock(&bdev->bd_fsfreeze_mutex);
+			return error;
 		}
-		drop_super(sb);
 	}
 
-	up(&bdev->bd_mount_sem);
+	sb->s_frozen = SB_UNFROZEN;
+	smp_wmb();
+	wake_up(&sb->s_wait_unfrozen);
+
+out_deactivate:
+	if (sb)
+		deactivate_locked_super(sb);
+out_unlock:
 	mutex_unlock(&bdev->bd_fsfreeze_mutex);
 	return 0;
 }
@@ -391,7 +405,17 @@ static loff_t block_llseek(struct file *file, loff_t offset, int origin)
  
 static int block_fsync(struct file *filp, struct dentry *dentry, int datasync)
 {
-	return sync_blockdev(I_BDEV(filp->f_mapping->host));
+	struct block_device *bdev = I_BDEV(filp->f_mapping->host);
+	int error;
+
+	error = sync_blockdev(bdev);
+	if (error)
+		return error;
+	
+	error = blkdev_issue_flush(bdev, NULL);
+	if (error == -EOPNOTSUPP)
+		error = 0;
+	return error;
 }
 
 /*
@@ -413,7 +437,6 @@ 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);
 }
 
@@ -424,7 +447,6 @@ static void init_once(void *foo)
 
 	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
@@ -491,6 +513,11 @@ void __init bdev_cache_init(void)
 	bd_mnt = kern_mount(&bd_type);
 	if (IS_ERR(bd_mnt))
 		panic("Cannot create bdev pseudo-fs");
+	/*
+	 * This vfsmount structure is only used to obtain the
+	 * blockdev_superblock, so tell kmemleak not to report it.
+	 */
+	kmemleak_not_leak(bd_mnt);
 	blockdev_superblock = bd_mnt->mnt_sb;	/* For writeback */
 }
 
@@ -552,6 +579,16 @@ 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 block_device *bdev;
@@ -1093,7 +1130,7 @@ EXPORT_SYMBOL(revalidate_disk);
 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;
@@ -1110,7 +1147,7 @@ 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) {
@@ -1221,8 +1258,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
 		}
 	} else {
-		put_disk(disk);
 		module_put(disk->fops->owner);
+		put_disk(disk);
 		disk = NULL;
 		if (bdev->bd_contains == bdev) {
 			if (bdev->bd_disk->fops->open) {
@@ -1383,6 +1420,33 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 }
 
 /*
+ * Write data to the block device.  Only intended for the block device itself
+ * and the raw driver which basically is a fake block device.
+ *
+ * Does not take i_mutex for the write and thus is not for general purpose
+ * use.
+ */
+ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
+			 unsigned long nr_segs, loff_t pos)
+{
+	struct file *file = iocb->ki_filp;
+	ssize_t ret;
+
+	BUG_ON(iocb->ki_pos != pos);
+
+	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+	if (ret > 0 || ret == -EIOCBQUEUED) {
+		ssize_t err;
+
+		err = generic_write_sync(file, pos, ret);
+		if (err < 0 && ret > 0)
+			ret = err;
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(blkdev_aio_write);
+
+/*
  * Try to release a page associated with block device when the system
  * is under memory pressure.
  */
@@ -1414,7 +1478,7 @@ 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,
 	.unlocked_ioctl	= block_ioctl,