Re: [PATCH v3 09/12] xfs: Add xfs_file_dio_write_atomic()

["Darrick J. Wong" <djwong@kernel.org>]

On Thu, Feb 27, 2025 at 06:08:10PM +0000, John Garry wrote:
> Add xfs_file_dio_write_atomic() for dedicated handling of atomic writes.
> 
> In case of -EAGAIN being returned from iomap_dio_rw(), reissue the write
> in CoW-based atomic write mode.
> 
> For CoW-based mode, ensure that we have no outstanding IOs which we
> may trample on.
> 
> Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
> Signed-off-by: John Garry <john.g.garry@oracle.com>
> ---
>  fs/xfs/xfs_file.c | 42 ++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 42 insertions(+)
> 
> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
> index 258c82cbce12..76ea59c638c3 100644
> --- a/fs/xfs/xfs_file.c
> +++ b/fs/xfs/xfs_file.c
> @@ -619,6 +619,46 @@ xfs_file_dio_write_aligned(
>  	return ret;
>  }
>  
> +static noinline ssize_t
> +xfs_file_dio_write_atomic(
> +	struct xfs_inode	*ip,
> +	struct kiocb		*iocb,
> +	struct iov_iter		*from)
> +{
> +	unsigned int		iolock = XFS_IOLOCK_SHARED;
> +	unsigned int		dio_flags = 0;
> +	ssize_t			ret;
> +
> +retry:
> +	ret = xfs_ilock_iocb_for_write(iocb, &iolock);
> +	if (ret)
> +		return ret;
> +
> +	ret = xfs_file_write_checks(iocb, from, &iolock);
> +	if (ret)
> +		goto out_unlock;
> +
> +	if (dio_flags & IOMAP_DIO_FORCE_WAIT)
> +		inode_dio_wait(VFS_I(ip));
> +
> +	trace_xfs_file_direct_write(iocb, from);
> +	ret = iomap_dio_rw(iocb, from, &xfs_atomic_write_iomap_ops,
> +			&xfs_dio_write_ops, dio_flags, NULL, 0);
> +
> +	if (ret == -EAGAIN && !(iocb->ki_flags & IOCB_NOWAIT) &&
> +	    !(dio_flags & IOMAP_DIO_ATOMIC_SW)) {
> +		xfs_iunlock(ip, iolock);
> +		dio_flags = IOMAP_DIO_ATOMIC_SW | IOMAP_DIO_FORCE_WAIT;

One last little nit here: if the filesystem doesn't have reflink, you
can't use copy on write as a fallback.

		/*
		 * The atomic write fallback uses out of place writes
		 * implemented with the COW code, so we must fail the
		 * atomic write if that is not supported.
		 */
		if (!xfs_has_reflink(ip->i_mount))
			return -EOPNOTSUPP;
		dio_flags = IOMAP_DIO_ATOMIC_SW | IOMAP_DIO_FORCE_WAIT;

You can retain my RVB if you add that.

--D

> +		iolock = XFS_IOLOCK_EXCL;
> +		goto retry;
> +	}
> +
> +out_unlock:
> +	if (iolock)
> +		xfs_iunlock(ip, iolock);
> +	return ret;
> +}
> +
>  /*
>   * Handle block unaligned direct I/O writes
>   *
> @@ -723,6 +763,8 @@ xfs_file_dio_write(
>  		return -EINVAL;
>  	if ((iocb->ki_pos | count) & ip->i_mount->m_blockmask)
>  		return xfs_file_dio_write_unaligned(ip, iocb, from);
> +	if (iocb->ki_flags & IOCB_ATOMIC)
> +		return xfs_file_dio_write_atomic(ip, iocb, from);
>  	return xfs_file_dio_write_aligned(ip, iocb, from);
>  }
>  
> -- 
> 2.31.1
>