xfs: move orphan files to the orphanage

When we're repairing a directory structure or fixing the dotdot entry of
a subdirectory, it's possible that we won't ever find a parent for the
subdirectory.  When this is the case, move it to the orphanage, aka
/lost+found.
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>

Documentation/filesystems/xfs/xfs-online-fsck-design.rst

@@ -4778,14 +4778,21 @@ Orphaned files are adopted by the orphanage as follows:
    The ``xrep_orphanage_iolock_two`` function follows the inode locking
    strategy discussed earlier.
 
-3. Call ``xrep_orphanage_compute_blkres`` and ``xrep_orphanage_compute_name``
-   to compute the new name in the orphanage and the block reservation required.
-
-4. Use ``xrep_orphanage_adoption_prep`` to reserve resources to the repair
+3. Use ``xrep_adoption_trans_alloc`` to reserve resources to the repair
    transaction.
 
-5. Call ``xrep_orphanage_adopt`` to reparent the orphaned file into the lost
-   and found, and update the kernel dentry cache.
+4. Call ``xrep_orphanage_compute_name`` to compute the new name in the
+   orphanage.
+
+5. If the adoption is going to happen, call ``xrep_adoption_reparent`` to
+   reparent the orphaned file into the lost and found and invalidate the dentry
+   cache.
+
+6. Call ``xrep_adoption_finish`` to commit any filesystem updates, release the
+   orphanage ILOCK, and clean the scrub transaction.
+
+7. If a runtime error happens, call ``xrep_adoption_cancel`` to release all
+   resources.
 
 The proposed patches are in the
 `orphanage adoption

fs/xfs/Makefile

@@ -205,6 +205,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   inode_repair.o \
 				   newbt.o \
 				   nlinks_repair.o \
+				   orphanage.o \
 				   parent_repair.o \
 				   rcbag_btree.o \
 				   rcbag.o \

fs/xfs/scrub/dir_repair.c

@@ -42,6 +42,7 @@
 #include "scrub/readdir.h"
 #include "scrub/reap.h"
 #include "scrub/findparent.h"
+#include "scrub/orphanage.h"
 
 /*
  * Directory Repair
@@ -115,12 +116,21 @@ struct xrep_dir {
 	 */
 	struct xrep_parent_scan_info pscan;
 
+	/*
+	 * Context information for attaching this directory to the lost+found
+	 * if this directory does not have a parent.
+	 */
+	struct xrep_adoption	adoption;
+
 	/* How many subdirectories did we find? */
 	uint64_t		subdirs;
 
 	/* How many dirents did we find? */
 	unsigned int		dirents;
 
+	/* Should we move this directory to the orphanage? */
+	bool			needs_adoption;
+
 	/* Directory entry name, plus the trailing null. */
 	struct xfs_name		xname;
 	unsigned char		namebuf[MAXNAMELEN];
@@ -148,6 +158,10 @@ xrep_setup_directory(
 
 	xchk_fsgates_enable(sc, XCHK_FSGATES_DIRENTS);
 
+	error = xrep_orphanage_try_create(sc);
+	if (error)
+		return error;
+
 	error = xrep_tempfile_create(sc, S_IFDIR);
 	if (error)
 		return error;
@@ -1137,10 +1151,8 @@ xrep_dir_set_nlink(
 	/*
 	 * The directory is not on the incore unlinked list, which means that
 	 * it needs to be reachable via the directory tree.  Update the nlink
-	 * with our observed link count.
-	 *
-	 * XXX: A subsequent patch will handle parentless directories by moving
-	 * them to the lost and found instead of aborting the repair.
+	 * with our observed link count.  If the directory has no parent, it
+	 * will be moved to the orphanage.
 	 */
 	if (!xfs_inode_on_unlinked_list(dp))
 		goto reset_nlink;
@@ -1151,6 +1163,7 @@ xrep_dir_set_nlink(
 	 * inactivate when the last reference drops.
 	 */
 	if (rd->dirents == 0) {
+		rd->needs_adoption = false;
 		new_nlink = 0;
 		goto reset_nlink;
 	}
@@ -1159,7 +1172,8 @@ xrep_dir_set_nlink(
 	 * The directory is on the unlinked list and we found dirents.  This
 	 * directory needs to be reachable via the directory tree.  Remove the
 	 * dir from the unlinked list and update nlink with the observed link
-	 * count.
+	 * count.  If the directory has no parent, it will be moved to the
+	 * orphanage.
 	 */
 	pag = xfs_perag_get(sc->mp, XFS_INO_TO_AGNO(sc->mp, dp->i_ino));
 	if (!pag) {
@@ -1195,12 +1209,16 @@ xrep_dir_swap(
 		return -EFSCORRUPTED;
 
 	/*
-	 * If we never found the parent for this directory, we can't fix this
-	 * directory.
+	 * If we never found the parent for this directory, temporarily assign
+	 * the root dir as the parent; we'll move this to the orphanage after
+	 * exchanging the dir contents.  We hold the ILOCK of the dir being
+	 * repaired, so we're not worried about racy updates of dotdot.
 	 */
 	ASSERT(sc->ilock_flags & XFS_ILOCK_EXCL);
-	if (rd->pscan.parent_ino == NULLFSINO)
-		return -EFSCORRUPTED;
+	if (rd->pscan.parent_ino == NULLFSINO) {
+		rd->needs_adoption = true;
+		rd->pscan.parent_ino = rd->sc->mp->m_sb.sb_rootino;
+	}
 
 	/*
 	 * Reset the temporary directory's '..' entry to point to the parent
@@ -1358,6 +1376,91 @@ xrep_dir_setup_scan(
 	return error;
 }
 
+/*
+ * Move the current file to the orphanage.
+ *
+ * Caller must hold IOLOCK_EXCL on @sc->ip, and no other inode locks.  Upon
+ * successful return, the scrub transaction will have enough extra reservation
+ * to make the move; it will hold IOLOCK_EXCL and ILOCK_EXCL of @sc->ip and the
+ * orphanage; and both inodes will be ijoined.
+ */
+STATIC int
+xrep_dir_move_to_orphanage(
+	struct xrep_dir		*rd)
+{
+	struct xfs_scrub	*sc = rd->sc;
+	xfs_ino_t		orig_parent, new_parent;
+	int			error;
+
+	/*
+	 * We are about to drop the ILOCK on sc->ip to lock the orphanage and
+	 * prepare for the adoption.  Therefore, look up the old dotdot entry
+	 * for sc->ip so that we can compare it after we re-lock sc->ip.
+	 */
+	error = xchk_dir_lookup(sc, sc->ip, &xfs_name_dotdot, &orig_parent);
+	if (error)
+		return error;
+
+	/*
+	 * Drop the ILOCK on the scrub target and commit the transaction.
+	 * Adoption computes its own resource requirements and gathers the
+	 * necessary components.
+	 */
+	error = xrep_trans_commit(sc);
+	if (error)
+		return error;
+	xchk_iunlock(sc, XFS_ILOCK_EXCL);
+
+	/* If we can take the orphanage's iolock then we're ready to move. */
+	if (!xrep_orphanage_ilock_nowait(sc, XFS_IOLOCK_EXCL)) {
+		xchk_iunlock(sc, sc->ilock_flags);
+		error = xrep_orphanage_iolock_two(sc);
+		if (error)
+			return error;
+	}
+
+	/* Grab transaction and ILOCK the two files. */
+	error = xrep_adoption_trans_alloc(sc, &rd->adoption);
+	if (error)
+		return error;
+
+	error = xrep_adoption_compute_name(&rd->adoption, &rd->xname);
+	if (error)
+		return error;
+
+	/*
+	 * Now that we've reacquired the ILOCK on sc->ip, look up the dotdot
+	 * entry again.  If the parent changed or the child was unlinked while
+	 * the child directory was unlocked, we don't need to move the child to
+	 * the orphanage after all.
+	 */
+	error = xchk_dir_lookup(sc, sc->ip, &xfs_name_dotdot, &new_parent);
+	if (error)
+		return error;
+
+	/*
+	 * Attach to the orphanage if we still have a linked directory and it
+	 * hasn't been moved.
+	 */
+	if (orig_parent == new_parent && VFS_I(sc->ip)->i_nlink > 0) {
+		error = xrep_adoption_move(&rd->adoption);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * Launder the scrub transaction so we can drop the orphanage ILOCK
+	 * and IOLOCK.  Return holding the scrub target's ILOCK and IOLOCK.
+	 */
+	error = xrep_adoption_trans_roll(&rd->adoption);
+	if (error)
+		return error;
+
+	xrep_orphanage_iunlock(sc, XFS_ILOCK_EXCL);
+	xrep_orphanage_iunlock(sc, XFS_IOLOCK_EXCL);
+	return 0;
+}
+
 /*
  * Repair the directory metadata.
  *
@@ -1396,6 +1499,15 @@ xrep_directory(
 	if (error)
 		goto out_teardown;
 
+	if (rd->needs_adoption) {
+		if (!xrep_orphanage_can_adopt(rd->sc))
+			error = -EFSCORRUPTED;
+		else
+			error = xrep_dir_move_to_orphanage(rd);
+		if (error)
+			goto out_teardown;
+	}
+
 out_teardown:
 	xrep_dir_teardown(sc);
 	return error;

fs/xfs/scrub/orphanage.h

+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2021-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_ORPHANAGE_H__
+#define __XFS_SCRUB_ORPHANAGE_H__
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+int xrep_orphanage_create(struct xfs_scrub *sc);
+
+/*
+ * If we're doing a repair, ensure that the orphanage exists and attach it to
+ * the scrub context.
+ */
+static inline int
+xrep_orphanage_try_create(
+	struct xfs_scrub	*sc)
+{
+	int			error;
+
+	ASSERT(sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR);
+
+	error = xrep_orphanage_create(sc);
+	switch (error) {
+	case 0:
+	case -ENOENT:
+	case -ENOTDIR:
+	case -ENOSPC:
+		/*
+		 * If the orphanage can't be found or isn't a directory, we'll
+		 * keep going, but we won't be able to attach the file to the
+		 * orphanage if we can't find the parent.
+		 */
+		return 0;
+	}
+
+	return error;
+}
+
+int xrep_orphanage_iolock_two(struct xfs_scrub *sc);
+
+void xrep_orphanage_ilock(struct xfs_scrub *sc, unsigned int ilock_flags);
+bool xrep_orphanage_ilock_nowait(struct xfs_scrub *sc,
+		unsigned int ilock_flags);
+void xrep_orphanage_iunlock(struct xfs_scrub *sc, unsigned int ilock_flags);
+
+void xrep_orphanage_rele(struct xfs_scrub *sc);
+
+/* Information about a request to add a file to the orphanage. */
+struct xrep_adoption {
+	struct xfs_scrub	*sc;
+
+	/* Name used for the adoption. */
+	struct xfs_name		*xname;
+
+	/* Block reservations for orphanage and child (if directory). */
+	unsigned int		orphanage_blkres;
+	unsigned int		child_blkres;
+};
+
+bool xrep_orphanage_can_adopt(struct xfs_scrub *sc);
+
+int xrep_adoption_trans_alloc(struct xfs_scrub *sc,
+		struct xrep_adoption *adopt);
+int xrep_adoption_compute_name(struct xrep_adoption *adopt,
+		struct xfs_name *xname);
+int xrep_adoption_move(struct xrep_adoption *adopt);
+int xrep_adoption_trans_roll(struct xrep_adoption *adopt);
+#else
+struct xrep_adoption { /* empty */ };
+# define xrep_orphanage_rele(sc)	((void)0)
+#endif /* CONFIG_XFS_ONLINE_REPAIR */
+
+#endif /* __XFS_SCRUB_ORPHANAGE_H__ */

fs/xfs/scrub/parent_repair.c

@@ -32,6 +32,8 @@
 #include "scrub/iscan.h"
 #include "scrub/findparent.h"
 #include "scrub/readdir.h"
+#include "scrub/tempfile.h"
+#include "scrub/orphanage.h"
 
 /*
  * Repairing The Directory Parent Pointer
@@ -57,6 +59,13 @@ struct xrep_parent {
 	 * dotdot entry for this directory.
 	 */
 	struct xrep_parent_scan_info pscan;
+
+	/* Orphanage reparenting request. */
+	struct xrep_adoption	adoption;
+
+	/* Directory entry name, plus the trailing null. */
+	struct xfs_name		xname;
+	unsigned char		namebuf[MAXNAMELEN];
 };
 
 /* Tear down all the incore stuff we created. */
@@ -80,9 +89,10 @@ xrep_setup_parent(
 	if (!rp)
 		return -ENOMEM;
 	rp->sc = sc;
+	rp->xname.name = rp->namebuf;
 	sc->buf = rp;
 
-	return 0;
+	return xrep_orphanage_try_create(sc);
 }
 
 /*
@@ -179,6 +189,91 @@ xrep_parent_reset_dotdot(
 	return xfs_trans_roll(&sc->tp);
 }
 
+/*
+ * Move the current file to the orphanage.
+ *
+ * Caller must hold IOLOCK_EXCL on @sc->ip, and no other inode locks.  Upon
+ * successful return, the scrub transaction will have enough extra reservation
+ * to make the move; it will hold IOLOCK_EXCL and ILOCK_EXCL of @sc->ip and the
+ * orphanage; and both inodes will be ijoined.
+ */
+STATIC int
+xrep_parent_move_to_orphanage(
+	struct xrep_parent	*rp)
+{
+	struct xfs_scrub	*sc = rp->sc;
+	xfs_ino_t		orig_parent, new_parent;
+	int			error;
+
+	/*
+	 * We are about to drop the ILOCK on sc->ip to lock the orphanage and
+	 * prepare for the adoption.  Therefore, look up the old dotdot entry
+	 * for sc->ip so that we can compare it after we re-lock sc->ip.
+	 */
+	error = xchk_dir_lookup(sc, sc->ip, &xfs_name_dotdot, &orig_parent);
+	if (error)
+		return error;
+
+	/*
+	 * Drop the ILOCK on the scrub target and commit the transaction.
+	 * Adoption computes its own resource requirements and gathers the
+	 * necessary components.
+	 */
+	error = xrep_trans_commit(sc);
+	if (error)
+		return error;
+	xchk_iunlock(sc, XFS_ILOCK_EXCL);
+
+	/* If we can take the orphanage's iolock then we're ready to move. */
+	if (!xrep_orphanage_ilock_nowait(sc, XFS_IOLOCK_EXCL)) {
+		xchk_iunlock(sc, sc->ilock_flags);
+		error = xrep_orphanage_iolock_two(sc);
+		if (error)
+			return error;
+	}
+
+	/* Grab transaction and ILOCK the two files. */
+	error = xrep_adoption_trans_alloc(sc, &rp->adoption);
+	if (error)
+		return error;
+
+	error = xrep_adoption_compute_name(&rp->adoption, &rp->xname);
+	if (error)
+		return error;
+
+	/*
+	 * Now that we've reacquired the ILOCK on sc->ip, look up the dotdot
+	 * entry again.  If the parent changed or the child was unlinked while
+	 * the child directory was unlocked, we don't need to move the child to
+	 * the orphanage after all.
+	 */
+	error = xchk_dir_lookup(sc, sc->ip, &xfs_name_dotdot, &new_parent);
+	if (error)
+		return error;
+
+	/*
+	 * Attach to the orphanage if we still have a linked directory and it
+	 * hasn't been moved.
+	 */
+	if (orig_parent == new_parent && VFS_I(sc->ip)->i_nlink > 0) {
+		error = xrep_adoption_move(&rp->adoption);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * Launder the scrub transaction so we can drop the orphanage ILOCK
+	 * and IOLOCK.  Return holding the scrub target's ILOCK and IOLOCK.
+	 */
+	error = xrep_adoption_trans_roll(&rp->adoption);
+	if (error)
+		return error;
+
+	xrep_orphanage_iunlock(sc, XFS_ILOCK_EXCL);
+	xrep_orphanage_iunlock(sc, XFS_IOLOCK_EXCL);
+	return 0;
+}
+
 /*
  * Commit the new parent pointer structure (currently only the dotdot entry) to
  * the file that we're repairing.
@@ -188,7 +283,8 @@ xrep_parent_rebuild_tree(
 	struct xrep_parent	*rp)
 {
 	if (rp->pscan.parent_ino == NULLFSINO) {
-		/* Cannot fix orphaned directories yet. */
+		if (xrep_orphanage_can_adopt(rp->sc))
+			return xrep_parent_move_to_orphanage(rp);
 		return -EFSCORRUPTED;
 	}
 

fs/xfs/scrub/scrub.c

@@ -27,6 +27,7 @@
 #include "scrub/stats.h"
 #include "scrub/xfile.h"
 #include "scrub/tempfile.h"
+#include "scrub/orphanage.h"
 
 /*
  * Online Scrub and Repair
@@ -217,6 +218,7 @@ xchk_teardown(
 	}
 
 	xrep_tempfile_rele(sc);
+	xrep_orphanage_rele(sc);
 	xchk_fsgates_disable(sc);
 	return error;
 }

fs/xfs/scrub/scrub.h

@@ -105,6 +105,10 @@ struct xfs_scrub {
 	/* Lock flags for @ip. */
 	uint				ilock_flags;
 
+	/* The orphanage, for stashing files that have lost their parent. */
+	uint				orphanage_ilock_flags;
+	struct xfs_inode		*orphanage;
+
 	/* A temporary file on this filesystem, for staging new metadata. */
 	struct xfs_inode		*tempip;
 	uint				temp_ilock_flags;

fs/xfs/scrub/trace.h

@@ -2588,6 +2588,34 @@ DEFINE_EVENT(xrep_dirent_class, name, \
 DEFINE_XREP_DIRENT_EVENT(xrep_dir_salvage_entry);
 DEFINE_XREP_DIRENT_EVENT(xrep_dir_stash_createname);
 DEFINE_XREP_DIRENT_EVENT(xrep_dir_replay_createname);
+DEFINE_XREP_DIRENT_EVENT(xrep_adoption_reparent);
+
+DECLARE_EVENT_CLASS(xrep_adoption_class,
+	TP_PROTO(struct xfs_inode *dp, struct xfs_inode *ip, bool moved),
+	TP_ARGS(dp, ip, moved),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, dir_ino)
+		__field(xfs_ino_t, child_ino)
+		__field(bool, moved)
+	),
+	TP_fast_assign(
+		__entry->dev = dp->i_mount->m_super->s_dev;
+		__entry->dir_ino = dp->i_ino;
+		__entry->child_ino = ip->i_ino;
+		__entry->moved = moved;
+	),
+	TP_printk("dev %d:%d dir 0x%llx child 0x%llx moved? %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->dir_ino,
+		  __entry->child_ino,
+		  __entry->moved)
+);
+#define DEFINE_XREP_ADOPTION_EVENT(name) \
+DEFINE_EVENT(xrep_adoption_class, name, \
+	TP_PROTO(struct xfs_inode *dp, struct xfs_inode *ip, bool moved), \
+	TP_ARGS(dp, ip, moved))
+DEFINE_XREP_ADOPTION_EVENT(xrep_adoption_trans_roll);
 
 DECLARE_EVENT_CLASS(xrep_parent_salvage_class,
 	TP_PROTO(struct xfs_inode *dp, xfs_ino_t ino),

fs/xfs/xfs_inode.c

@@ -914,10 +914,10 @@ xfs_droplink(
 /*
  * Increment the link count on an inode & log the change.
  */
-static void
+void
 xfs_bumplink(
-	xfs_trans_t *tp,
-	xfs_inode_t *ip)
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip)
 {
 	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
 

fs/xfs/xfs_inode.h

@@ -625,6 +625,7 @@ void xfs_end_io(struct work_struct *work);
 int xfs_ilock2_io_mmap(struct xfs_inode *ip1, struct xfs_inode *ip2);
 void xfs_iunlock2_io_mmap(struct xfs_inode *ip1, struct xfs_inode *ip2);
 void xfs_iunlock2_remapping(struct xfs_inode *ip1, struct xfs_inode *ip2);
+void xfs_bumplink(struct xfs_trans *tp, struct xfs_inode *ip);
 
 static inline bool
 xfs_inode_unlinked_incomplete(