[v3,4/6] dax: give DAX clearing code correct bdev

Commit Message

Ross Zwisler Feb. 17, 2016, 3:34 a.m. UTC

dax_clear_blocks() needs a valid struct block_device and previously it was
using inode->i_sb->s_bdev in all cases.  This is correct for normal inodes
on mounted ext2, ext4 and XFS filesystems, but is incorrect for DAX raw
block devices and for XFS real-time devices.

Instead, rename dax_clear_blocks() to dax_clear_sectors(), and change its
arguments to take a bdev and a sector instead of an inode and a block.
This better reflects what the function does, and it allows the filesystem
and raw block device code to pass in an appropriate struct block_device.

Signed-off-by: Ross Zwisler <[e-mail]>
Suggested-by: Dan Williams <[e-mail]>
---
 fs/dax.c               | 9 ++++-----
 fs/ext2/inode.c        | 6 ++++--
 fs/xfs/xfs_aops.c      | 2 +-
 fs/xfs/xfs_aops.h      | 1 +
 fs/xfs/xfs_bmap_util.c | 3 ++-
 include/linux/dax.h    | 2 +-
 6 files changed, 13 insertions(+), 10 deletions(-)

Comments

Jan Kara Feb. 17, 2016, 9:37 p.m. UTC | #1

On Tue 16-02-16 20:34:17, Ross Zwisler wrote:
> dax_clear_blocks() needs a valid struct block_device and previously it was
> using inode->i_sb->s_bdev in all cases.  This is correct for normal inodes
> on mounted ext2, ext4 and XFS filesystems, but is incorrect for DAX raw
> block devices and for XFS real-time devices.
> 
> Instead, rename dax_clear_blocks() to dax_clear_sectors(), and change its
> arguments to take a bdev and a sector instead of an inode and a block.
> This better reflects what the function does, and it allows the filesystem
> and raw block device code to pass in an appropriate struct block_device.
> 
> Signed-off-by: Ross Zwisler <[e-mail]>
> Suggested-by: Dan Williams <[e-mail]>

The patch looks good to me. You can add:

Reviewed-by: Jan Kara <[e-mail]>

								Honza

> ---
>  fs/dax.c               | 9 ++++-----
>  fs/ext2/inode.c        | 6 ++++--
>  fs/xfs/xfs_aops.c      | 2 +-
>  fs/xfs/xfs_aops.h      | 1 +
>  fs/xfs/xfs_bmap_util.c | 3 ++-
>  include/linux/dax.h    | 2 +-
>  6 files changed, 13 insertions(+), 10 deletions(-)
> 
> diff --git a/fs/dax.c b/fs/dax.c
> index fc2e314..9a173dd 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
> @@ -79,15 +79,14 @@ struct page *read_dax_sector(struct block_device *bdev, sector_t n)
>  }
>  
>  /*
> - * dax_clear_blocks() is called from within transaction context from XFS,
> + * dax_clear_sectors() is called from within transaction context from XFS,
>   * and hence this means the stack from this point must follow GFP_NOFS
>   * semantics for all operations.
>   */
> -int dax_clear_blocks(struct inode *inode, sector_t block, long _size)
> +int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size)
>  {
> -	struct block_device *bdev = inode->i_sb->s_bdev;
>  	struct blk_dax_ctl dax = {
> -		.sector = block << (inode->i_blkbits - 9),
> +		.sector = _sector,
>  		.size = _size,
>  	};
>  
> @@ -109,7 +108,7 @@ int dax_clear_blocks(struct inode *inode, sector_t block, long _size)
>  	wmb_pmem();
>  	return 0;
>  }
> -EXPORT_SYMBOL_GPL(dax_clear_blocks);
> +EXPORT_SYMBOL_GPL(dax_clear_sectors);
>  
>  /* the clear_pmem() calls are ordered by a wmb_pmem() in the caller */
>  static void dax_new_buf(void __pmem *addr, unsigned size, unsigned first,
> diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
> index 27e2cdd..4467cbd 100644
> --- a/fs/ext2/inode.c
> +++ b/fs/ext2/inode.c
> @@ -737,8 +737,10 @@ static int ext2_get_blocks(struct inode *inode,
>  		 * so that it's not found by another thread before it's
>  		 * initialised
>  		 */
> -		err = dax_clear_blocks(inode, le32_to_cpu(chain[depth-1].key),
> -						1 << inode->i_blkbits);
> +		err = dax_clear_sectors(inode->i_sb->s_bdev,
> +				le32_to_cpu(chain[depth-1].key) <<
> +				(inode->i_blkbits - 9),
> +				1 << inode->i_blkbits);
>  		if (err) {
>  			mutex_unlock(&ei->truncate_mutex);
>  			goto cleanup;
> diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
> index 379c089..fc20518 100644
> --- a/fs/xfs/xfs_aops.c
> +++ b/fs/xfs/xfs_aops.c
> @@ -55,7 +55,7 @@ xfs_count_page_state(
>  	} while ((bh = bh->b_this_page) != head);
>  }
>  
> -STATIC struct block_device *
> +struct block_device *
>  xfs_find_bdev_for_inode(
>  	struct inode		*inode)
>  {
> diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
> index f6ffc9a..a4343c6 100644
> --- a/fs/xfs/xfs_aops.h
> +++ b/fs/xfs/xfs_aops.h
> @@ -62,5 +62,6 @@ int	xfs_get_blocks_dax_fault(struct inode *inode, sector_t offset,
>  			         struct buffer_head *map_bh, int create);
>  
>  extern void xfs_count_page_state(struct page *, int *, int *);
> +extern struct block_device *xfs_find_bdev_for_inode(struct inode *);
>  
>  #endif /* __XFS_AOPS_H__ */
> diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
> index 45ec9e4..6c87601 100644
> --- a/fs/xfs/xfs_bmap_util.c
> +++ b/fs/xfs/xfs_bmap_util.c
> @@ -75,7 +75,8 @@ xfs_zero_extent(
>  	ssize_t		size = XFS_FSB_TO_B(mp, count_fsb);
>  
>  	if (IS_DAX(VFS_I(ip)))
> -		return dax_clear_blocks(VFS_I(ip), block, size);
> +		return dax_clear_sectors(xfs_find_bdev_for_inode(VFS_I(ip)),
> +				sector, size);
>  
>  	/*
>  	 * let the block layer decide on the fastest method of
> diff --git a/include/linux/dax.h b/include/linux/dax.h
> index 818e450..7b6bced 100644
> --- a/include/linux/dax.h
> +++ b/include/linux/dax.h
> @@ -7,7 +7,7 @@
>  
>  ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t,
>  		  get_block_t, dio_iodone_t, int flags);
> -int dax_clear_blocks(struct inode *, sector_t block, long size);
> +int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size);
>  int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
>  int dax_truncate_page(struct inode *, loff_t from, get_block_t);
>  int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
> -- 
> 2.5.0
> 
>

Patch

diff --git a/fs/dax.c b/fs/dax.c
index fc2e314..9a173dd 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -79,15 +79,14 @@  struct page *read_dax_sector(struct block_device *bdev, sector_t n)
 }
 
 /*
- * dax_clear_blocks() is called from within transaction context from XFS,
+ * dax_clear_sectors() is called from within transaction context from XFS,
  * and hence this means the stack from this point must follow GFP_NOFS
  * semantics for all operations.
  */
-int dax_clear_blocks(struct inode *inode, sector_t block, long _size)
+int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size)
 {
-	struct block_device *bdev = inode->i_sb->s_bdev;
 	struct blk_dax_ctl dax = {
-		.sector = block << (inode->i_blkbits - 9),
+		.sector = _sector,
 		.size = _size,
 	};
 
@@ -109,7 +108,7 @@  int dax_clear_blocks(struct inode *inode, sector_t block, long _size)
 	wmb_pmem();
 	return 0;
 }
-EXPORT_SYMBOL_GPL(dax_clear_blocks);
+EXPORT_SYMBOL_GPL(dax_clear_sectors);
 
 /* the clear_pmem() calls are ordered by a wmb_pmem() in the caller */
 static void dax_new_buf(void __pmem *addr, unsigned size, unsigned first,
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 27e2cdd..4467cbd 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -737,8 +737,10 @@  static int ext2_get_blocks(struct inode *inode,
 		 * so that it's not found by another thread before it's
 		 * initialised
 		 */
-		err = dax_clear_blocks(inode, le32_to_cpu(chain[depth-1].key),
-						1 << inode->i_blkbits);
+		err = dax_clear_sectors(inode->i_sb->s_bdev,
+				le32_to_cpu(chain[depth-1].key) <<
+				(inode->i_blkbits - 9),
+				1 << inode->i_blkbits);
 		if (err) {
 			mutex_unlock(&ei->truncate_mutex);
 			goto cleanup;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 379c089..fc20518 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -55,7 +55,7 @@  xfs_count_page_state(
 	} while ((bh = bh->b_this_page) != head);
 }
 
-STATIC struct block_device *
+struct block_device *
 xfs_find_bdev_for_inode(
 	struct inode		*inode)
 {
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index f6ffc9a..a4343c6 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -62,5 +62,6 @@  int	xfs_get_blocks_dax_fault(struct inode *inode, sector_t offset,
 			         struct buffer_head *map_bh, int create);
 
 extern void xfs_count_page_state(struct page *, int *, int *);
+extern struct block_device *xfs_find_bdev_for_inode(struct inode *);
 
 #endif /* __XFS_AOPS_H__ */
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 45ec9e4..6c87601 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -75,7 +75,8 @@  xfs_zero_extent(
 	ssize_t		size = XFS_FSB_TO_B(mp, count_fsb);
 
 	if (IS_DAX(VFS_I(ip)))
-		return dax_clear_blocks(VFS_I(ip), block, size);
+		return dax_clear_sectors(xfs_find_bdev_for_inode(VFS_I(ip)),
+				sector, size);
 
 	/*
 	 * let the block layer decide on the fastest method of
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 818e450..7b6bced 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -7,7 +7,7 @@ 
 
 ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t,
 		  get_block_t, dio_iodone_t, int flags);
-int dax_clear_blocks(struct inode *, sector_t block, long size);
+int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size);
 int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
 int dax_truncate_page(struct inode *, loff_t from, get_block_t);
 int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,