Re: [PATCH 02/15] xfs: refactor clonerange preparation into a separate helper

[Dave Chinner <david@fromorbit.com>]

On Thu, Oct 04, 2018 at 05:44:47PM -0700, Darrick J. Wong wrote:
> From: Darrick J. Wong <darrick.wong@oracle.com>
> 
> Refactor all the reflink preparation steps into a separate helper that
> we'll use to land all the upcoming fixes for insufficient input checks.

If I've read the patch right, this also changes the location of the
page cache truncation, right?  i.e. it now happens in the
xfs_reflink_remap_prep() function instead of after the remap?  I
think the commit message needs to mention that because it's a fix to
incorrect behaviour....

I've added:

--
This rework also moves the invalidation of the destination range to
the prep function so that it is done before the range is remapped.
This ensures that nobody can access the data in range being remapped
until the remap is complete.
--

Sound OK?

Otherwise this looks fine.

Reviewed-by: Dave Chinner <dchinner@redhat.com>

-Dave.

> 
> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
> ---
>  fs/xfs/xfs_reflink.c |   96 +++++++++++++++++++++++++++++++++++++-------------
>  1 file changed, 71 insertions(+), 25 deletions(-)
> 
> 
> diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
> index 38f405415b88..80ca9b6793cd 100644
> --- a/fs/xfs/xfs_reflink.c
> +++ b/fs/xfs/xfs_reflink.c
> @@ -1195,11 +1195,33 @@ xfs_iolock_two_inodes_and_break_layout(
>  	return 0;
>  }
>  
> +/* Unlock both inodes after they've been prepped for a range clone. */
> +STATIC void
> +xfs_reflink_remap_unlock(
> +	struct file		*file_in,
> +	struct file		*file_out)
> +{
> +	struct inode		*inode_in = file_inode(file_in);
> +	struct xfs_inode	*src = XFS_I(inode_in);
> +	struct inode		*inode_out = file_inode(file_out);
> +	struct xfs_inode	*dest = XFS_I(inode_out);
> +	bool			same_inode = (inode_in == inode_out);
> +
> +	xfs_iunlock(dest, XFS_MMAPLOCK_EXCL);
> +	if (!same_inode)
> +		xfs_iunlock(src, XFS_MMAPLOCK_SHARED);
> +	inode_unlock(inode_out);
> +	if (!same_inode)
> +		inode_unlock_shared(inode_in);
> +}
> +
>  /*
> - * Link a range of blocks from one file to another.
> + * Prepare two files for range cloning.  Upon a successful return both inodes
> + * will have the iolock and mmaplock held, the page cache of the out file
> + * will be truncated, and any leases on the out file will have been broken.
>   */
> -int
> -xfs_reflink_remap_range(
> +STATIC int
> +xfs_reflink_remap_prep(
>  	struct file		*file_in,
>  	loff_t			pos_in,
>  	struct file		*file_out,
> @@ -1211,19 +1233,9 @@ xfs_reflink_remap_range(
>  	struct xfs_inode	*src = XFS_I(inode_in);
>  	struct inode		*inode_out = file_inode(file_out);
>  	struct xfs_inode	*dest = XFS_I(inode_out);
> -	struct xfs_mount	*mp = src->i_mount;
>  	bool			same_inode = (inode_in == inode_out);
> -	xfs_fileoff_t		sfsbno, dfsbno;
> -	xfs_filblks_t		fsblen;
> -	xfs_extlen_t		cowextsize;
>  	ssize_t			ret;
>  
> -	if (!xfs_sb_version_hasreflink(&mp->m_sb))
> -		return -EOPNOTSUPP;
> -
> -	if (XFS_FORCED_SHUTDOWN(mp))
> -		return -EIO;
> -
>  	/* Lock both files against IO */
>  	ret = xfs_iolock_two_inodes_and_break_layout(inode_in, inode_out);
>  	if (ret)
> @@ -1254,8 +1266,6 @@ xfs_reflink_remap_range(
>  	if (ret)
>  		goto out_unlock;
>  
> -	trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out);
> -
>  	/*
>  	 * Clear out post-eof preallocations because we don't have page cache
>  	 * backing the delayed allocations and they'll never get freed on
> @@ -1272,6 +1282,51 @@ xfs_reflink_remap_range(
>  	if (ret)
>  		goto out_unlock;
>  
> +	/* Zap any page cache for the destination file's range. */
> +	truncate_inode_pages_range(&inode_out->i_data, pos_out,
> +				   PAGE_ALIGN(pos_out + len) - 1);
> +	return 0;
> +out_unlock:
> +	xfs_reflink_remap_unlock(file_in, file_out);
> +	return ret;
> +}
> +
> +/*
> + * Link a range of blocks from one file to another.
> + */
> +int
> +xfs_reflink_remap_range(
> +	struct file		*file_in,
> +	loff_t			pos_in,
> +	struct file		*file_out,
> +	loff_t			pos_out,
> +	u64			len,
> +	bool			is_dedupe)
> +{
> +	struct inode		*inode_in = file_inode(file_in);
> +	struct xfs_inode	*src = XFS_I(inode_in);
> +	struct inode		*inode_out = file_inode(file_out);
> +	struct xfs_inode	*dest = XFS_I(inode_out);
> +	struct xfs_mount	*mp = src->i_mount;
> +	xfs_fileoff_t		sfsbno, dfsbno;
> +	xfs_filblks_t		fsblen;
> +	xfs_extlen_t		cowextsize;
> +	ssize_t			ret;
> +
> +	if (!xfs_sb_version_hasreflink(&mp->m_sb))
> +		return -EOPNOTSUPP;
> +
> +	if (XFS_FORCED_SHUTDOWN(mp))
> +		return -EIO;
> +
> +	/* Prepare and then clone file data. */
> +	ret = xfs_reflink_remap_prep(file_in, pos_in, file_out, pos_out,
> +			len, is_dedupe);
> +	if (ret)
> +		return ret;
> +
> +	trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out);
> +
>  	dfsbno = XFS_B_TO_FSBT(mp, pos_out);
>  	sfsbno = XFS_B_TO_FSBT(mp, pos_in);
>  	fsblen = XFS_B_TO_FSB(mp, len);
> @@ -1280,10 +1335,6 @@ xfs_reflink_remap_range(
>  	if (ret)
>  		goto out_unlock;
>  
> -	/* Zap any page cache for the destination file's range. */
> -	truncate_inode_pages_range(&inode_out->i_data, pos_out,
> -				   PAGE_ALIGN(pos_out + len) - 1);
> -
>  	/*
>  	 * Carry the cowextsize hint from src to dest if we're sharing the
>  	 * entire source file to the entire destination file, the source file
> @@ -1300,12 +1351,7 @@ xfs_reflink_remap_range(
>  			is_dedupe);
>  
>  out_unlock:
> -	xfs_iunlock(dest, XFS_MMAPLOCK_EXCL);
> -	if (!same_inode)
> -		xfs_iunlock(src, XFS_MMAPLOCK_SHARED);
> -	inode_unlock(inode_out);
> -	if (!same_inode)
> -		inode_unlock_shared(inode_in);
> +	xfs_reflink_remap_unlock(file_in, file_out);
>  	if (ret)
>  		trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_);
>  	return ret;
> 
> 

-- 
Dave Chinner
david@fromorbit.com