xfs: define the on-disk format for the metadir feature

Define the on-disk layout and feature flags for the metadata inode
directory feature.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>

4 files changed, 51 insertions, 2 deletions

diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index c6a3e71f99eb..bf96b006bd24 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -175,6 +175,14 @@ typedef struct xfs_sb {
 	xfs_lsn_t	sb_lsn;		/* last write sequence */
 	uuid_t		sb_meta_uuid;	/* metadata file system unique id */
 
+	/*
+	 * Metadata Directory Inode.  On disk this lives in the sb_rbmino slot,
+	 * but we continue to use the in-core superblock to cache the classic
+	 * inodes (rt bitmap; rt summary; user, group, and project quotas) so
+	 * we cache the metadir inode value here too.
+	 */
+	xfs_ino_t	sb_metadirino;
+
 	/* must be padded to 64 bit alignment */
 } xfs_sb_t;
 
@@ -193,7 +201,14 @@ typedef struct xfs_dsb {
 	uuid_t		sb_uuid;	/* user-visible file system unique id */
 	__be64		sb_logstart;	/* starting block of log if internal */
 	__be64		sb_rootino;	/* root inode number */
-	__be64		sb_rbmino;	/* bitmap inode for realtime extents */
+	/*
+	 * bitmap inode for realtime extents.
+	 *
+	 * The metadata directory feature uses the sb_rbmino field to point to
+	 * the root of the metadata directory tree.  All other sb inode
+	 * pointers are no longer used.
+	 */
+	__be64		sb_rbmino;
 	__be64		sb_rsumino;	/* summary inode for rt bitmap */
 	__be32		sb_rextsize;	/* realtime extent size, blocks */
 	__be32		sb_agblocks;	/* size of an allocation group */
@@ -468,6 +483,7 @@ xfs_sb_has_ro_compat_feature(
 #define XFS_SB_FEAT_INCOMPAT_SPINODES	(1 << 1)	/* sparse inode chunks */
 #define XFS_SB_FEAT_INCOMPAT_META_UUID	(1 << 2)	/* metadata UUID */
 #define XFS_SB_FEAT_INCOMPAT_BIGTIME	(1 << 3)	/* large timestamps */
+#define XFS_SB_FEAT_INCOMPAT_METADIR	(1 << 4)	/* metadata ino dir */
 #define XFS_SB_FEAT_INCOMPAT_ALL \
 		(XFS_SB_FEAT_INCOMPAT_FTYPE|	\
 		 XFS_SB_FEAT_INCOMPAT_SPINODES|	\
@@ -593,6 +609,12 @@ static inline bool xfs_sb_version_hasatomicswap(struct xfs_sb *sbp)
 		 XFS_SB_FEAT_INCOMPAT_LOG_ATOMIC_SWAP);
 }
 
+static inline bool xfs_sb_version_hasmetadir(struct xfs_sb *sbp)
+{
+	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 &&
+		(sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR);
+}
+
 /*
  * end of superblock version macros
  */
@@ -1174,15 +1196,25 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev)
 #define XFS_DIFLAG2_REFLINK_BIT	1	/* file's blocks may be shared */
 #define XFS_DIFLAG2_COWEXTSIZE_BIT   2  /* copy on write extent size hint */
 #define XFS_DIFLAG2_BIGTIME_BIT	3	/* big timestamps */
+#define XFS_DIFLAG2_METADATA_BIT 4	/* filesystem metadata */
 
 #define XFS_DIFLAG2_DAX		(1 << XFS_DIFLAG2_DAX_BIT)
 #define XFS_DIFLAG2_REFLINK     (1 << XFS_DIFLAG2_REFLINK_BIT)
 #define XFS_DIFLAG2_COWEXTSIZE  (1 << XFS_DIFLAG2_COWEXTSIZE_BIT)
 #define XFS_DIFLAG2_BIGTIME	(1 << XFS_DIFLAG2_BIGTIME_BIT)
 
+/*
+ * The inode contains filesystem metadata and can be found through the metadata
+ * directory tree.  The only valid modes are regular files and directories;
+ * the user, group, and project IDs must be zero; and none of the access mode
+ * bits can be set.  Metadata inodes must never be resolvable through the root
+ * directory and cannot be accessed by userspace.
+ */
+#define XFS_DIFLAG2_METADATA	(1 << XFS_DIFLAG2_METADATA_BIT)
+
 #define XFS_DIFLAG2_ANY \
 	(XFS_DIFLAG2_DAX | XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE | \
-	 XFS_DIFLAG2_BIGTIME)
+	 XFS_DIFLAG2_BIGTIME | XFS_DIFLAG2_METADATA)
 
 static inline bool xfs_dinode_has_bigtime(const struct xfs_dinode *dip)
 {
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 2fed392c158c..41bc5d947945 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1503,6 +1503,10 @@ xfs_inode_needs_inactivation(
 	if (mp->m_flags & XFS_MOUNT_RDONLY)
 		return false;
 
+	/* Metadata inodes require explicit resource cleanup. */
+	if (xfs_is_metadata_inode(ip))
+		return false;
+
 	/* Try to clean out the cow blocks if there are any. */
 	if (cow_ifp && cow_ifp->if_bytes > 0)
 		return true;
@@ -1597,6 +1601,10 @@ xfs_inactive(
 	if (mp->m_flags & XFS_MOUNT_RDONLY)
 		return;
 
+	/* Metadata inodes require explicit resource cleanup. */
+	if (xfs_is_metadata_inode(ip))
+		return;
+
 	xfs_inactive_health(ip);
 
 	/*
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index aa000a2a60fd..78311c2a74f8 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -177,6 +177,11 @@ static inline bool xfs_is_reflink_inode(struct xfs_inode *ip)
 	return ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK;
 }
 
+static inline bool xfs_is_metadata_inode(struct xfs_inode *ip)
+{
+	return ip->i_d.di_flags2 & XFS_DIFLAG2_METADATA;
+}
+
 bool xfs_is_always_cow_inode(struct xfs_inode *ip);
 
 /*
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index fbbf341bd215..19c3804aae20 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1684,6 +1684,10 @@ xfs_fc_fill_super(
 		}
 	}
 
+	if (xfs_sb_version_hasmetadir(&mp->m_sb))
+		xfs_warn(mp,
+"EXPERIMENTAL metadata directory feature in use. Use at your own risk!");
+
 	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
 		if (mp->m_sb.sb_rblocks) {
 			xfs_alert(mp,