diff --git a/fs/block_dev.c b/fs/block_dev.c
index f5958f4..44aaba2 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -414,21 +414,31 @@
 static struct block_device *bd_acquire(struct inode *inode)
 {
 	struct block_device *bdev;
+
 	spin_lock(&bdev_lock);
 	bdev = inode->i_bdev;
-	if (bdev && igrab(bdev->bd_inode)) {
+	if (bdev) {
+		atomic_inc(&bdev->bd_inode->i_count);
 		spin_unlock(&bdev_lock);
 		return bdev;
 	}
 	spin_unlock(&bdev_lock);
+
 	bdev = bdget(inode->i_rdev);
 	if (bdev) {
 		spin_lock(&bdev_lock);
-		if (inode->i_bdev)
-			__bd_forget(inode);
-		inode->i_bdev = bdev;
-		inode->i_mapping = bdev->bd_inode->i_mapping;
-		list_add(&inode->i_devices, &bdev->bd_inodes);
+		if (!inode->i_bdev) {
+			/*
+			 * We take an additional bd_inode->i_count for inode,
+			 * and it's released in clear_inode() of inode.
+			 * So, we can access it via ->i_mapping always
+			 * without igrab().
+			 */
+			atomic_inc(&bdev->bd_inode->i_count);
+			inode->i_bdev = bdev;
+			inode->i_mapping = bdev->bd_inode->i_mapping;
+			list_add(&inode->i_devices, &bdev->bd_inodes);
+		}
 		spin_unlock(&bdev_lock);
 	}
 	return bdev;
@@ -438,10 +448,18 @@
 
 void bd_forget(struct inode *inode)
 {
+	struct block_device *bdev = NULL;
+
 	spin_lock(&bdev_lock);
-	if (inode->i_bdev)
+	if (inode->i_bdev) {
+		if (inode->i_sb != blockdev_superblock)
+			bdev = inode->i_bdev;
 		__bd_forget(inode);
+	}
 	spin_unlock(&bdev_lock);
+
+	if (bdev)
+		iput(bdev->bd_inode);
 }
 
 int bd_claim(struct block_device *bdev, void *holder)