Merge tag 'scrub-rtsummary-6.6_2023-08-10' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux into xfs-6.6-mergeA

xfs: online scrubbing of realtime summary files

This patchset implements an online checker for the realtime summary
file.  The first few changes are some general cleanups -- scrub should
get its own references to all inodes, and we also wrap the inode lock
functions so that we can standardize unlocking and releasing inodes that
are the focus of a scrub.

With that out of the way, we move on to constructing a shadow copy of
the rtsummary information from the rtbitmap, and compare the new copy
against the ondisk copy.

This has been running on the djcloud for years with no problems.  Enjoy!

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

* tag 'scrub-rtsummary-6.6_2023-08-10' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux:
  xfs: implement online scrubbing of rtsummary info
  xfs: move the realtime summary file scrubber to a separate source file
  xfs: wrap ilock/iunlock operations on sc->ip
  xfs: get our own reference to inodes that we want to scrub

Author: Chandan Babu R

fs/xfs/Makefile

@@ -169,7 +169,12 @@ xfs-y				+= $(addprefix scrub/, \
 				   )
 
 xfs-$(CONFIG_XFS_ONLINE_SCRUB_STATS) += scrub/stats.o
-xfs-$(CONFIG_XFS_RT)		+= scrub/rtbitmap.o
+
+xfs-$(CONFIG_XFS_RT)		+= $(addprefix scrub/, \
+				   rtbitmap.o \
+				   rtsummary.o \
+				   )
+
 xfs-$(CONFIG_XFS_QUOTA)		+= scrub/quota.o
 
 # online repair

fs/xfs/scrub/bmap.c

@@ -38,8 +38,7 @@ xchk_setup_inode_bmap(
 	if (error)
 		goto out;
 
-	sc->ilock_flags = XFS_IOLOCK_EXCL;
-	xfs_ilock(sc->ip, XFS_IOLOCK_EXCL);
+	xchk_ilock(sc, XFS_IOLOCK_EXCL);
 
 	/*
 	 * We don't want any ephemeral data/cow fork updates sitting around
@@ -50,8 +49,7 @@ xchk_setup_inode_bmap(
 	    sc->sm->sm_type != XFS_SCRUB_TYPE_BMBTA) {
 		struct address_space	*mapping = VFS_I(sc->ip)->i_mapping;
 
-		sc->ilock_flags |= XFS_MMAPLOCK_EXCL;
-		xfs_ilock(sc->ip, XFS_MMAPLOCK_EXCL);
+		xchk_ilock(sc, XFS_MMAPLOCK_EXCL);
 
 		inode_dio_wait(VFS_I(sc->ip));
 
@@ -79,9 +77,8 @@ xchk_setup_inode_bmap(
 	error = xchk_trans_alloc(sc, 0);
 	if (error)
 		goto out;
-	sc->ilock_flags |= XFS_ILOCK_EXCL;
-	xfs_ilock(sc->ip, XFS_ILOCK_EXCL);
 
+	xchk_ilock(sc, XFS_ILOCK_EXCL);
 out:
 	/* scrub teardown will unlock and release the inode */
 	return error;

fs/xfs/scrub/common.c

@@ -831,6 +831,25 @@ xchk_install_handle_inode(
 	return 0;
 }
 
+/*
+ * Install an already-referenced inode for scrubbing.  Get our own reference to
+ * the inode to make disposal simpler.  The inode must not be in I_FREEING or
+ * I_WILL_FREE state!
+ */
+int
+xchk_install_live_inode(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
+{
+	if (!igrab(VFS_I(ip))) {
+		xchk_ino_set_corrupt(sc, ip->i_ino);
+		return -EFSCORRUPTED;
+	}
+
+	sc->ip = ip;
+	return 0;
+}
+
 /*
  * In preparation to scrub metadata structures that hang off of an inode,
  * grab either the inode referenced in the scrub control structure or the
@@ -854,10 +873,8 @@ xchk_iget_for_scrubbing(
 	ASSERT(sc->tp == NULL);
 
 	/* We want to scan the inode we already had opened. */
-	if (sc->sm->sm_ino == 0 || sc->sm->sm_ino == ip_in->i_ino) {
-		sc->ip = ip_in;
-		return 0;
-	}
+	if (sc->sm->sm_ino == 0 || sc->sm->sm_ino == ip_in->i_ino)
+		return xchk_install_live_inode(sc, ip_in);
 
 	/* Reject internal metadata files and obviously bad inode numbers. */
 	if (xfs_internal_inum(mp, sc->sm->sm_ino))
@@ -1005,20 +1022,48 @@ xchk_setup_inode_contents(
 		return error;
 
 	/* Lock the inode so the VFS cannot touch this file. */
-	sc->ilock_flags = XFS_IOLOCK_EXCL;
-	xfs_ilock(sc->ip, sc->ilock_flags);
+	xchk_ilock(sc, XFS_IOLOCK_EXCL);
 
 	error = xchk_trans_alloc(sc, resblks);
 	if (error)
 		goto out;
-	sc->ilock_flags |= XFS_ILOCK_EXCL;
-	xfs_ilock(sc->ip, XFS_ILOCK_EXCL);
-
+	xchk_ilock(sc, XFS_ILOCK_EXCL);
 out:
 	/* scrub teardown will unlock and release the inode for us */
 	return error;
 }
 
+void
+xchk_ilock(
+	struct xfs_scrub	*sc,
+	unsigned int		ilock_flags)
+{
+	xfs_ilock(sc->ip, ilock_flags);
+	sc->ilock_flags |= ilock_flags;
+}
+
+bool
+xchk_ilock_nowait(
+	struct xfs_scrub	*sc,
+	unsigned int		ilock_flags)
+{
+	if (xfs_ilock_nowait(sc->ip, ilock_flags)) {
+		sc->ilock_flags |= ilock_flags;
+		return true;
+	}
+
+	return false;
+}
+
+void
+xchk_iunlock(
+	struct xfs_scrub	*sc,
+	unsigned int		ilock_flags)
+{
+	sc->ilock_flags &= ~ilock_flags;
+	xfs_iunlock(sc->ip, ilock_flags);
+}
+
 /*
  * Predicate that decides if we need to evaluate the cross-reference check.
  * If there was an error accessing the cross-reference btree, just delete

fs/xfs/scrub/common.h

@@ -88,10 +88,16 @@ int xchk_setup_xattr(struct xfs_scrub *sc);
 int xchk_setup_symlink(struct xfs_scrub *sc);
 int xchk_setup_parent(struct xfs_scrub *sc);
 #ifdef CONFIG_XFS_RT
-int xchk_setup_rt(struct xfs_scrub *sc);
+int xchk_setup_rtbitmap(struct xfs_scrub *sc);
+int xchk_setup_rtsummary(struct xfs_scrub *sc);
 #else
 static inline int
-xchk_setup_rt(struct xfs_scrub *sc)
+xchk_setup_rtbitmap(struct xfs_scrub *sc)
+{
+	return -ENOENT;
+}
+static inline int
+xchk_setup_rtsummary(struct xfs_scrub *sc)
 {
 	return -ENOENT;
 }
@@ -137,6 +143,12 @@ int xchk_count_rmap_ownedby_ag(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
 int xchk_setup_ag_btree(struct xfs_scrub *sc, bool force_log);
 int xchk_iget_for_scrubbing(struct xfs_scrub *sc);
 int xchk_setup_inode_contents(struct xfs_scrub *sc, unsigned int resblks);
+int xchk_install_live_inode(struct xfs_scrub *sc, struct xfs_inode *ip);
+
+void xchk_ilock(struct xfs_scrub *sc, unsigned int ilock_flags);
+bool xchk_ilock_nowait(struct xfs_scrub *sc, unsigned int ilock_flags);
+void xchk_iunlock(struct xfs_scrub *sc, unsigned int ilock_flags);
+
 void xchk_buffer_recheck(struct xfs_scrub *sc, struct xfs_buf *bp);
 
 int xchk_iget(struct xfs_scrub *sc, xfs_ino_t inum, struct xfs_inode **ipp);
@@ -157,6 +169,14 @@ static inline bool xchk_skip_xref(struct xfs_scrub_metadata *sm)
 
 int xchk_metadata_inode_forks(struct xfs_scrub *sc);
 
+/*
+ * Helper macros to allocate and format xfile description strings.
+ * Callers must kfree the pointer returned.
+ */
+#define xchk_xfile_descr(sc, fmt, ...) \
+	kasprintf(XCHK_GFP_FLAGS, "XFS (%s): " fmt, \
+			(sc)->mp->m_super->s_id, ##__VA_ARGS__)
+
 /*
  * Setting up a hook to wait for intents to drain is costly -- we have to take
  * the CPU hotplug lock and force an i-cache flush on all CPUs once to set it

fs/xfs/scrub/inode.c

@@ -32,15 +32,13 @@ xchk_prepare_iscrub(
 {
 	int			error;
 
-	sc->ilock_flags = XFS_IOLOCK_EXCL;
-	xfs_ilock(sc->ip, sc->ilock_flags);
+	xchk_ilock(sc, XFS_IOLOCK_EXCL);
 
 	error = xchk_trans_alloc(sc, 0);
 	if (error)
 		return error;
 
-	sc->ilock_flags |= XFS_ILOCK_EXCL;
-	xfs_ilock(sc->ip, XFS_ILOCK_EXCL);
+	xchk_ilock(sc, XFS_ILOCK_EXCL);
 	return 0;
 }
 
@@ -83,7 +81,10 @@ xchk_setup_inode(
 
 	/* We want to scan the opened inode, so lock it and exit. */
 	if (sc->sm->sm_ino == 0 || sc->sm->sm_ino == ip_in->i_ino) {
-		sc->ip = ip_in;
+		error = xchk_install_live_inode(sc, ip_in);
+		if (error)
+			return error;
+
 		return xchk_prepare_iscrub(sc);
 	}
 

fs/xfs/scrub/parent.c

@@ -150,8 +150,8 @@ xchk_parent_validate(
 
 	lock_mode = xchk_parent_ilock_dir(dp);
 	if (!lock_mode) {
-		xfs_iunlock(sc->ip, XFS_ILOCK_EXCL);
-		xfs_ilock(sc->ip, XFS_ILOCK_EXCL);
+		xchk_iunlock(sc, XFS_ILOCK_EXCL);
+		xchk_ilock(sc, XFS_ILOCK_EXCL);
 		error = -EAGAIN;
 		goto out_rele;
 	}

fs/xfs/scrub/quota.c

@@ -59,9 +59,12 @@ xchk_setup_quota(
 	error = xchk_setup_fs(sc);
 	if (error)
 		return error;
-	sc->ip = xfs_quota_inode(sc->mp, dqtype);
-	xfs_ilock(sc->ip, XFS_ILOCK_EXCL);
-	sc->ilock_flags = XFS_ILOCK_EXCL;
+
+	error = xchk_install_live_inode(sc, xfs_quota_inode(sc->mp, dqtype));
+	if (error)
+		return error;
+
+	xchk_ilock(sc, XFS_ILOCK_EXCL);
 	return 0;
 }
 
@@ -235,13 +238,11 @@ xchk_quota(
 	 * data fork we have to drop ILOCK_EXCL to use the regular dquot
 	 * functions.
 	 */
-	xfs_iunlock(sc->ip, sc->ilock_flags);
-	sc->ilock_flags = 0;
+	xchk_iunlock(sc, sc->ilock_flags);
 	sqi.sc = sc;
 	sqi.last_id = 0;
 	error = xfs_qm_dqiterate(mp, dqtype, xchk_quota_item, &sqi);
-	sc->ilock_flags = XFS_ILOCK_EXCL;
-	xfs_ilock(sc->ip, sc->ilock_flags);
+	xchk_ilock(sc, XFS_ILOCK_EXCL);
 	if (error == -ECANCELED)
 		error = 0;
 	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK,

fs/xfs/scrub/rtbitmap.c

@@ -19,19 +19,20 @@
 
 /* Set us up with the realtime metadata locked. */
 int
-xchk_setup_rt(
+xchk_setup_rtbitmap(
 	struct xfs_scrub	*sc)
 {
 	int			error;
 
-	error = xchk_setup_fs(sc);
+	error = xchk_trans_alloc(sc, 0);
 	if (error)
 		return error;
 
-	sc->ilock_flags = XFS_ILOCK_EXCL | XFS_ILOCK_RTBITMAP;
-	sc->ip = sc->mp->m_rbmip;
-	xfs_ilock(sc->ip, sc->ilock_flags);
+	error = xchk_install_live_inode(sc, sc->mp->m_rbmip);
+	if (error)
+		return error;
 
+	xchk_ilock(sc, XFS_ILOCK_EXCL | XFS_ILOCK_RTBITMAP);
 	return 0;
 }
 
@@ -123,43 +124,6 @@ xchk_rtbitmap(
 	return error;
 }
 
-/* Scrub the realtime summary. */
-int
-xchk_rtsummary(
-	struct xfs_scrub	*sc)
-{
-	struct xfs_inode	*rsumip = sc->mp->m_rsumip;
-	struct xfs_inode	*old_ip = sc->ip;
-	uint			old_ilock_flags = sc->ilock_flags;
-	int			error = 0;
-
-	/*
-	 * We ILOCK'd the rt bitmap ip in the setup routine, now lock the
-	 * rt summary ip in compliance with the rt inode locking rules.
-	 *
-	 * Since we switch sc->ip to rsumip we have to save the old ilock
-	 * flags so that we don't mix up the inode state that @sc tracks.
-	 */
-	sc->ip = rsumip;
-	sc->ilock_flags = XFS_ILOCK_EXCL | XFS_ILOCK_RTSUM;
-	xfs_ilock(sc->ip, sc->ilock_flags);
-
-	/* Invoke the fork scrubber. */
-	error = xchk_metadata_inode_forks(sc);
-	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
-		goto out;
-
-	/* XXX: implement this some day */
-	xchk_set_incomplete(sc);
-out:
-	/* Switch back to the rtbitmap inode and lock flags. */
-	xfs_iunlock(sc->ip, sc->ilock_flags);
-	sc->ilock_flags = old_ilock_flags;
-	sc->ip = old_ip;
-	return error;
-}
-
-
 /* xref check that the extent is not free in the rtbitmap */
 void
 xchk_xref_is_used_rt_space(