Merge tag 'fix-ro-mounts-6.6_2023-09-12' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux into xfs-6.6-fixesA

xfs: fix ro mounting with unknown rocompat features

Dave pointed out some failures in xfs/270 when he upgraded Debian
unstable and util-linux started using the new mount apis.  Upon further
inquiry I noticed that XFS is quite a hot mess when it encounters a
filesystem with unrecognized rocompat bits set in the superblock.

Whereas we used to allow readonly mounts under these conditions, a
change to the sb write verifier several years ago resulted in the
filesystem going down immediately because the post-mount log cleaning
writes the superblock, which trips the sb write verifier on the
unrecognized rocompat bit.  I made the observation that the ROCOMPAT
features RMAPBT and REFLINK both protect new log intent item types,
which means that we actually cannot support recovering the log if we
don't recognize all the rocompat bits.

Therefore -- fix inode inactivation to work when we're recovering the
log, disallow recovery when there's unrecognized rocompat bits, and
don't clean the log if doing so would trip the rocompat checks.

Signed-off-by: Darrick J. Wong <[email protected]>
Signed-off-by: Chandan Babu R <[email protected]>

* tag 'fix-ro-mounts-6.6_2023-09-12' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux:
  xfs: fix log recovery when unknown rocompat bits are set
  xfs: allow inode inactivation during a ro mount log recovery

Author: Chandan Babu R

fs/xfs/libxfs/xfs_sb.c

@@ -266,7 +266,8 @@ xfs_validate_sb_write(
 		return -EFSCORRUPTED;
 	}
 
-	if (xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
+	if (!xfs_is_readonly(mp) &&
+	    xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
 		xfs_alert(mp,
 "Corruption detected in superblock read-only compatible features (0x%x)!",
 			(sbp->sb_features_ro_compat &

fs/xfs/xfs_inode.c

@@ -1642,8 +1642,11 @@ xfs_inode_needs_inactive(
 	if (VFS_I(ip)->i_mode == 0)
 		return false;
 
-	/* If this is a read-only mount, don't do this (would generate I/O) */
-	if (xfs_is_readonly(mp))
+	/*
+	 * If this is a read-only mount, don't do this (would generate I/O)
+	 * unless we're in log recovery and cleaning the iunlinked list.
+	 */
+	if (xfs_is_readonly(mp) && !xlog_recovery_needed(mp->m_log))
 		return false;
 
 	/* If the log isn't running, push inodes straight to reclaim. */
@@ -1703,8 +1706,11 @@ xfs_inactive(
 	mp = ip->i_mount;
 	ASSERT(!xfs_iflags_test(ip, XFS_IRECOVERY));
 
-	/* If this is a read-only mount, don't do this (would generate I/O) */
-	if (xfs_is_readonly(mp))
+	/*
+	 * If this is a read-only mount, don't do this (would generate I/O)
+	 * unless we're in log recovery and cleaning the iunlinked list.
+	 */
+	if (xfs_is_readonly(mp) && !xlog_recovery_needed(mp->m_log))
 		goto out;
 
 	/* Metadata inodes require explicit resource cleanup. */

fs/xfs/xfs_log.c

@@ -715,15 +715,7 @@ xfs_log_mount(
 	 * just worked.
 	 */
 	if (!xfs_has_norecovery(mp)) {
-		/*
-		 * log recovery ignores readonly state and so we need to clear
-		 * mount-based read only state so it can write to disk.
-		 */
-		bool	readonly = test_and_clear_bit(XFS_OPSTATE_READONLY,
-						&mp->m_opstate);
 		error = xlog_recover(log);
-		if (readonly)
-			set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate);
 		if (error) {
 			xfs_warn(mp, "log mount/recovery failed: error %d",
 				error);
@@ -772,20 +764,13 @@ xfs_log_mount_finish(
 	struct xfs_mount	*mp)
 {
 	struct xlog		*log = mp->m_log;
-	bool			readonly;
 	int			error = 0;
 
 	if (xfs_has_norecovery(mp)) {
 		ASSERT(xfs_is_readonly(mp));
 		return 0;
 	}
 
-	/*
-	 * log recovery ignores readonly state and so we need to clear
-	 * mount-based read only state so it can write to disk.
-	 */
-	readonly = test_and_clear_bit(XFS_OPSTATE_READONLY, &mp->m_opstate);
-
 	/*
 	 * During the second phase of log recovery, we need iget and
 	 * iput to behave like they do for an active filesystem.
@@ -835,8 +820,6 @@ xfs_log_mount_finish(
 	xfs_buftarg_drain(mp->m_ddev_targp);
 
 	clear_bit(XLOG_RECOVERY_NEEDED, &log->l_opstate);
-	if (readonly)
-		set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate);
 
 	/* Make sure the log is dead if we're returning failure. */
 	ASSERT(!error || xlog_is_shutdown(log));