Re: [PATCH v3 4/9] xfs: distinguish between inobt and finobt magic values

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Mon, Feb 04, 2019 at 09:52:26AM -0500, Brian Foster wrote:
> The inode btree verifier code is shared between the inode btree and
> free inode btree because the underlying metadata formats are
> essentially equivalent. A side effect of this is that the verifier
> cannot determine whether a particular btree block should have an
> inobt or finobt magic value.
> 
> This logic allows an unfortunate xfs_repair bug to escape detection
> where certain level > 0 nodes of the finobt are stamped with inobt
> magic by xfs_repair finobt reconstruction. This is fortunately not a
> severe problem since the inode btree magic values do not contribute
> to any changes in kernel behavior, but we do need a means to detect
> and prevent this problem in the future.
> 
> Add a field to xfs_buf_ops to store the v4 and v5 superblock magic
> values expected by a particular verifier. Add a helper to check an
> on-disk magic value against the value expected by the verifier. Call
> the helper from the shared [f]inobt verifier code for magic value
> verification. This ensures that the inode btree blocks each have the
> appropriate magic value based on specific tree type and superblock
> version.
> 
> Signed-off-by: Brian Foster <bfoster@xxxxxxxxxx>
> ---
>  fs/xfs/libxfs/xfs_ialloc_btree.c | 16 +++++++---------
>  fs/xfs/xfs_buf.c                 | 19 +++++++++++++++++++
>  fs/xfs/xfs_buf.h                 |  2 ++
>  3 files changed, 28 insertions(+), 9 deletions(-)
> 
> diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
> index 798269eb4767..c2df1f89eec8 100644
> --- a/fs/xfs/libxfs/xfs_ialloc_btree.c
> +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
> @@ -260,6 +260,9 @@ xfs_inobt_verify(
>  	xfs_failaddr_t		fa;
>  	unsigned int		level;
>  
> +	if (!xfs_verify_magic(bp, block->bb_magic))
> +		return __this_address;
> +
>  	/*
>  	 * During growfs operations, we can't verify the exact owner as the
>  	 * perag is not fully initialised and hence not attached to the buffer.
> @@ -270,18 +273,10 @@ xfs_inobt_verify(
>  	 * but beware of the landmine (i.e. need to check pag->pagi_init) if we
>  	 * ever do.
>  	 */
> -	switch (block->bb_magic) {
> -	case cpu_to_be32(XFS_IBT_CRC_MAGIC):
> -	case cpu_to_be32(XFS_FIBT_CRC_MAGIC):
> +	if (xfs_sb_version_hascrc(&mp->m_sb)) {
>  		fa = xfs_btree_sblock_v5hdr_verify(bp);
>  		if (fa)
>  			return fa;
> -		/* fall through */
> -	case cpu_to_be32(XFS_IBT_MAGIC):
> -	case cpu_to_be32(XFS_FIBT_MAGIC):
> -		break;
> -	default:
> -		return __this_address;
>  	}
>  
>  	/* level verification */
> @@ -328,6 +323,7 @@ xfs_inobt_write_verify(
>  
>  const struct xfs_buf_ops xfs_inobt_buf_ops = {
>  	.name = "xfs_inobt",
> +	.magic = { cpu_to_be32(XFS_IBT_MAGIC), cpu_to_be32(XFS_IBT_CRC_MAGIC) },
>  	.verify_read = xfs_inobt_read_verify,
>  	.verify_write = xfs_inobt_write_verify,
>  	.verify_struct = xfs_inobt_verify,
> @@ -335,6 +331,8 @@ const struct xfs_buf_ops xfs_inobt_buf_ops = {
>  
>  const struct xfs_buf_ops xfs_finobt_buf_ops = {
>  	.name = "xfs_finobt",
> +	.magic = { cpu_to_be32(XFS_FIBT_MAGIC),
> +		   cpu_to_be32(XFS_FIBT_CRC_MAGIC) },
>  	.verify_read = xfs_inobt_read_verify,
>  	.verify_write = xfs_inobt_write_verify,
>  	.verify_struct = xfs_inobt_verify,
> diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
> index 222b5260ed35..0481c19fe5ae 100644
> --- a/fs/xfs/xfs_buf.c
> +++ b/fs/xfs/xfs_buf.c
> @@ -2204,3 +2204,22 @@ void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref)
>  
>  	atomic_set(&bp->b_lru_ref, lru_ref);
>  }
> +
> +/*
> + * Verify an on-disk magic value against the magic value specified in the
> + * verifier structure. The verifier magic is in disk byte order so the caller is
> + * expected to pass the value directly from disk.
> + */
> +bool
> +xfs_verify_magic(
> +	struct xfs_buf		*bp,
> +	uint32_t		dmagic)
> +{
> +	struct xfs_mount	*mp = bp->b_target->bt_mount;
> +	int			idx;
> +
> +	idx = xfs_sb_version_hascrc(&mp->m_sb);
> +	if (unlikely(WARN_ON(!bp->b_ops || !bp->b_ops->magic[idx])))

/me kinda wonders if we ought to have a #define for "no magic number" to
put in the .magic = {}, but OTOH we're never going to have a magic
number of zero.

Reviewed-by: Darrick J. Wong <darrick.wong@xxxxxxxxxx>

--D

> +		return false;
> +	return dmagic == bp->b_ops->magic[idx];
> +}
> diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
> index 1c436a85b71d..44f9423a1861 100644
> --- a/fs/xfs/xfs_buf.h
> +++ b/fs/xfs/xfs_buf.h
> @@ -125,6 +125,7 @@ struct xfs_buf_map {
>  
>  struct xfs_buf_ops {
>  	char *name;
> +	uint32_t magic[2];		/* v4 and v5 on disk magic values */
>  	void (*verify_read)(struct xfs_buf *);
>  	void (*verify_write)(struct xfs_buf *);
>  	xfs_failaddr_t (*verify_struct)(struct xfs_buf *bp);
> @@ -386,5 +387,6 @@ extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int);
>  #define xfs_readonly_buftarg(buftarg)	bdev_read_only((buftarg)->bt_bdev)
>  
>  int xfs_buf_reverify(struct xfs_buf *bp, const struct xfs_buf_ops *ops);
> +bool xfs_verify_magic(struct xfs_buf *bp, uint32_t dmagic);
>  
>  #endif	/* __XFS_BUF_H__ */
> -- 
> 2.17.2
> 



[Index of Archives]     [XFS Filesystem Development (older mail)]     [Linux Filesystem Development]     [Linux Audio Users]     [Yosemite Trails]     [Linux Kernel]     [Linux RAID]     [Linux SCSI]


  Powered by Linux