xfs: skip bmbt block ino validation during owner change

commit 99c794c639a65cc7b74f30a674048fd100fe9ac8 upstream.

Extent swap uses xfs_btree_visit_blocks() to fix up bmbt block
owners on v5 (!rmapbt) filesystems. The bmbt scan uses
xfs_btree_lookup_get_block() to read bmbt blocks which verifies the
current owner of the block against the parent inode of the bmbt.
This works during extent swap because the bmbt owners are updated to
the opposite inode number before the inode extent forks are swapped.

The modified bmbt blocks are marked as ordered buffers which allows
everything to commit in a single transaction. If the transaction
commits to the log and the system crashes such that recovery of the
extent swap is required, log recovery restarts the bmbt scan to fix
up any bmbt blocks that may have not been written back before the
crash. The log recovery bmbt scan occurs after the inode forks have
been swapped, however. This causes the bmbt block owner verification
to fail, leads to log recovery failure and requires xfs_repair to
zap the log to recover.

Define a new invalid inode owner flag to inform the btree block
lookup mechanism that the current inode may be invalid with respect
to the current owner of the bmbt block. Set this flag on the cursor
used for change owner scans to allow this operation to work at
runtime and during log recovery.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Fixes: bb3be7e7c ("xfs: check for bogus values in btree block headers")
Cc: stable@vger.kernel.org
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 5c3918678bb6e0fef546e7fcc8e0c4ce0e3071b7..9968a746c649c8e45c473b8c7ab97c4ac9213916 100644 (file)
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -888,6 +888,7 @@ xfs_bmbt_change_owner(
        cur = xfs_bmbt_init_cursor(ip->i_mount, tp, ip, whichfork);
        if (!cur)
                return -ENOMEM;
+       cur->bc_private.b.flags |= XFS_BTCUR_BPRV_INVALID_OWNER;
 
        error = xfs_btree_change_owner(cur, new_owner, buffer_list);
        xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);

diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 69c3f428b5821bef421b7a871c51fc51363b929f..1df747fadc3aa8400c849dd36b0e03134855e6bd 100644 (file)
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -1774,6 +1774,7 @@ xfs_btree_lookup_get_block(
 
        /* Check the inode owner since the verifiers don't. */
        if (xfs_sb_version_hascrc(&cur->bc_mp->m_sb) &&
+           !(cur->bc_private.b.flags & XFS_BTCUR_BPRV_INVALID_OWNER) &&
            (cur->bc_flags & XFS_BTREE_LONG_PTRS) &&
            be64_to_cpu((*blkp)->bb_u.l.bb_owner) !=
                        cur->bc_private.b.ip->i_ino)

diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 3b0fc1afada501409268979ae8bf4d5d9e768937..33c7be2357b9f6cdf8936ea39ff33588bab9ef5c 100644 (file)
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -268,7 +268,8 @@ typedef struct xfs_btree_cur
                        short           forksize;       /* fork's inode space */
                        char            whichfork;      /* data or attr fork */
                        char            flags;          /* flags */
-#define        XFS_BTCUR_BPRV_WASDEL   1                       /* was delayed */
+#define        XFS_BTCUR_BPRV_WASDEL           (1<<0)          /* was delayed */
+#define        XFS_BTCUR_BPRV_INVALID_OWNER    (1<<1)          /* for ext swap */
                } b;
        }               bc_private;     /* per-btree type data */
 } xfs_btree_cur_t;