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 <djwong@kernel.org>

6 files changed, 61 insertions, 2 deletions

diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index d70e9de22546..de83127f660d 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 */
@@ -372,6 +387,7 @@ xfs_sb_has_ro_compat_feature(
 #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_NEEDSREPAIR (1 << 4)	/* needs xfs_repair */
+#define XFS_SB_FEAT_INCOMPAT_METADIR	(1 << 5)	/* metadata dir tree */
 #define XFS_SB_FEAT_INCOMPAT_ALL \
 		(XFS_SB_FEAT_INCOMPAT_FTYPE|	\
 		 XFS_SB_FEAT_INCOMPAT_SPINODES|	\
@@ -975,15 +991,41 @@ 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.  Metadata inodes must satisfy the following constraints:
+ *
+ * - V5 filesystem (and ftype) are enabled;
+ * - The only valid modes are regular files and directories;
+ * - The access bits must be zero;
+ * - DMAPI event and state masks are zero;
+ * - The user, group, and project IDs must be zero;
+ * - The immutable, sync, noatime, nodump, nodefrag flags must be set.
+ * - The dax flag must not be set.
+ * - Directories must have nosymlinks set.
+ *
+ * These requirements are chosen defensively to minimize the ability of
+ * userspace to read or modify the contents, should a metadata file ever
+ * escape to userspace.
+ *
+ * There are further constraints on the directory tree itself:
+ *
+ * - Metadata inodes must never be resolvable through the root directory;
+ * - They must never be accessed by userspace;
+ * - Metadata directory entries must have correct ftype.
+ */
+#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/libxfs/xfs_inode_util.c b/fs/xfs/libxfs/xfs_inode_util.c
index fb68eeb58d0a..bd59b899629b 100644
--- a/fs/xfs/libxfs/xfs_inode_util.c
+++ b/fs/xfs/libxfs/xfs_inode_util.c
@@ -223,6 +223,8 @@ xfs_inode_inherit_flags2(
 	}
 	if (pip->i_diflags2 & XFS_DIFLAG2_DAX)
 		ip->i_diflags2 |= XFS_DIFLAG2_DAX;
+	if (pip->i_diflags2 & XFS_DIFLAG2_METADATA)
+		ip->i_diflags2 |= XFS_DIFLAG2_METADATA;
 
 	/* Don't let invalid cowextsize hints propagate. */
 	failaddr = xfs_inode_validate_cowextsize(ip->i_mount, ip->i_cowextsize,
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index e31ea65eaba5..488f1dfbbe12 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -124,6 +124,8 @@ xfs_sb_version_to_features(
 		features |= XFS_FEAT_BIGTIME;
 	if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR)
 		features |= XFS_FEAT_NEEDSREPAIR;
+	if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)
+		features |= XFS_FEAT_METADIR;
 
 	if (sbp->sb_features_log_incompat & XFS_SB_FEAT_INCOMPAT_LOG_ATOMIC_SWAP)
 		features |= XFS_FEAT_ATOMIC_SWAP;
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index e4c15a94284f..41954c0bfbef 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -192,6 +192,13 @@ static inline bool xfs_is_metadata_inode(struct xfs_inode *ip)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 
+	if (xfs_has_metadir(mp))
+		return ip->i_diflags2 & XFS_DIFLAG2_METADATA;
+
+	/*
+	 * Before metadata directories, the only metadata inodes were the
+	 * three quota files, the realtime bitmap, and the realtime summary.
+	 */
 	return ip == mp->m_rbmip || ip == mp->m_rsumip ||
 		xfs_is_quota_inode(&mp->m_sb, ip->i_ino);
 }
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 24c740721b28..96560e430a75 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -299,6 +299,7 @@ typedef struct xfs_mount {
 #define XFS_FEAT_BIGTIME	(1ULL << 24)	/* large timestamps */
 #define XFS_FEAT_NEEDSREPAIR	(1ULL << 25)	/* needs xfs_repair */
 #define XFS_FEAT_ATOMIC_SWAP	(1ULL << 26)	/* extent swap log items */
+#define XFS_FEAT_METADIR	(1ULL << 27)	/* metadata directory tree */
 
 /* Mount features */
 #define XFS_FEAT_NOATTR2	(1ULL << 48)	/* disable attr2 creation */
@@ -380,6 +381,7 @@ __XFS_HAS_FEAT(inobtcounts, INOBTCNT)
 __XFS_HAS_FEAT(bigtime, BIGTIME)
 __XFS_HAS_FEAT(needsrepair, NEEDSREPAIR)
 __XFS_LOG_FEAT(atomicswap, ATOMIC_SWAP)
+__XFS_HAS_FEAT(metadir, METADIR)
 
 /*
  * Decide if this filesystem can use log-assisted ("atomic") extent swapping.
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index ec1e5b86e971..b1b06b593b97 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1675,6 +1675,10 @@ xfs_fs_fill_super(
 		}
 	}
 
+	if (xfs_has_metadir(mp))
+		xfs_warn(mp,
+"EXPERIMENTAL metadata directory feature in use. Use at your own risk!");
+
 	if (xfs_has_reflink(mp)) {
 		if (mp->m_sb.sb_rblocks) {
 			xfs_alert(mp,