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

13 files changed, 421 insertions, 82 deletions

diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index d59fcf3fd0d5..7762c01a85cf 100644
--- a/fs/xfs/Makefile
+++ b/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
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 5bf4326e9783..20ab5d4e92ff 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/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;
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 7a20256be969..82d2a85d6461 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -832,6 +832,25 @@ xchk_install_handle_inode(
 }
 
 /*
+ * 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
  * inode passed in.  If the inumber does not reference an allocated inode
@@ -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
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index 791235cd9b00..5fe6d661d42d 100644
--- a/fs/xfs/scrub/common.h
+++ b/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);
@@ -158,6 +170,14 @@ 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
  * up, and again to tear it down.  These costs add up quickly, so we only want
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index 3e1e02e340a6..59d7912fb75f 100644
--- a/fs/xfs/scrub/inode.c
+++ b/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);
 	}
 
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index 58d5dfb7ea21..e6155d86f791 100644
--- a/fs/xfs/scrub/parent.c
+++ b/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;
 	}
diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c
index e6caa358cbda..5671c8153433 100644
--- a/fs/xfs/scrub/quota.c
+++ b/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,
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index e7dace7b4be8..008ddb599e13 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/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 @@ out:
 	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(
diff --git a/fs/xfs/scrub/rtsummary.c b/fs/xfs/scrub/rtsummary.c
new file mode 100644
index 000000000000..437ed9acbb27
--- /dev/null
+++ b/fs/xfs/scrub/rtsummary.c
@@ -0,0 +1,264 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2017-2023 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <[email protected]>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_btree.h"
+#include "xfs_inode.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_rtalloc.h"
+#include "xfs_bit.h"
+#include "xfs_bmap.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/xfile.h"
+
+/*
+ * Realtime Summary
+ * ================
+ *
+ * We check the realtime summary by scanning the realtime bitmap file to create
+ * a new summary file incore, and then we compare the computed version against
+ * the ondisk version.  We use the 'xfile' functionality to store this
+ * (potentially large) amount of data in pageable memory.
+ */
+
+/* Set us up to check the rtsummary file. */
+int
+xchk_setup_rtsummary(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_mount	*mp = sc->mp;
+	char			*descr;
+	int			error;
+
+	/*
+	 * Create an xfile to construct a new rtsummary file.  The xfile allows
+	 * us to avoid pinning kernel memory for this purpose.
+	 */
+	descr = xchk_xfile_descr(sc, "realtime summary file");
+	error = xfile_create(descr, mp->m_rsumsize, &sc->xfile);
+	kfree(descr);
+	if (error)
+		return error;
+
+	error = xchk_trans_alloc(sc, 0);
+	if (error)
+		return error;
+
+	/* Allocate a memory buffer for the summary comparison. */
+	sc->buf = kvmalloc(mp->m_sb.sb_blocksize, XCHK_GFP_FLAGS);
+	if (!sc->buf)
+		return -ENOMEM;
+
+	error = xchk_install_live_inode(sc, mp->m_rsumip);
+	if (error)
+		return error;
+
+	/*
+	 * Locking order requires us to take the rtbitmap first.  We must be
+	 * careful to unlock it ourselves when we are done with the rtbitmap
+	 * file since the scrub infrastructure won't do that for us.  Only
+	 * then we can lock the rtsummary inode.
+	 */
+	xfs_ilock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
+	xchk_ilock(sc, XFS_ILOCK_EXCL | XFS_ILOCK_RTSUM);
+	return 0;
+}
+
+/* Helper functions to record suminfo words in an xfile. */
+
+typedef unsigned int xchk_rtsumoff_t;
+
+static inline int
+xfsum_load(
+	struct xfs_scrub	*sc,
+	xchk_rtsumoff_t		sumoff,
+	xfs_suminfo_t		*info)
+{
+	return xfile_obj_load(sc->xfile, info, sizeof(xfs_suminfo_t),
+			sumoff << XFS_WORDLOG);
+}
+
+static inline int
+xfsum_store(
+	struct xfs_scrub	*sc,
+	xchk_rtsumoff_t		sumoff,
+	const xfs_suminfo_t	info)
+{
+	return xfile_obj_store(sc->xfile, &info, sizeof(xfs_suminfo_t),
+			sumoff << XFS_WORDLOG);
+}
+
+static inline int
+xfsum_copyout(
+	struct xfs_scrub	*sc,
+	xchk_rtsumoff_t		sumoff,
+	xfs_suminfo_t		*info,
+	unsigned int		nr_words)
+{
+	return xfile_obj_load(sc->xfile, info, nr_words << XFS_WORDLOG,
+			sumoff << XFS_WORDLOG);
+}
+
+/* Update the summary file to reflect the free extent that we've accumulated. */
+STATIC int
+xchk_rtsum_record_free(
+	struct xfs_mount		*mp,
+	struct xfs_trans		*tp,
+	const struct xfs_rtalloc_rec	*rec,
+	void				*priv)
+{
+	struct xfs_scrub		*sc = priv;
+	xfs_fileoff_t			rbmoff;
+	xfs_rtblock_t			rtbno;
+	xfs_filblks_t			rtlen;
+	xchk_rtsumoff_t			offs;
+	unsigned int			lenlog;
+	xfs_suminfo_t			v = 0;
+	int				error = 0;
+
+	if (xchk_should_terminate(sc, &error))
+		return error;
+
+	/* Compute the relevant location in the rtsum file. */
+	rbmoff = XFS_BITTOBLOCK(mp, rec->ar_startext);
+	lenlog = XFS_RTBLOCKLOG(rec->ar_extcount);
+	offs = XFS_SUMOFFS(mp, lenlog, rbmoff);
+
+	rtbno = rec->ar_startext * mp->m_sb.sb_rextsize;
+	rtlen = rec->ar_extcount * mp->m_sb.sb_rextsize;
+
+	if (!xfs_verify_rtext(mp, rtbno, rtlen)) {
+		xchk_ino_xref_set_corrupt(sc, mp->m_rbmip->i_ino);
+		return -EFSCORRUPTED;
+	}
+
+	/* Bump the summary count. */
+	error = xfsum_load(sc, offs, &v);
+	if (error)
+		return error;
+
+	v++;
+	trace_xchk_rtsum_record_free(mp, rec->ar_startext, rec->ar_extcount,
+			lenlog, offs, v);
+
+	return xfsum_store(sc, offs, v);
+}
+
+/* Compute the realtime summary from the realtime bitmap. */
+STATIC int
+xchk_rtsum_compute(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_mount	*mp = sc->mp;
+	unsigned long long	rtbmp_bytes;
+
+	/* If the bitmap size doesn't match the computed size, bail. */
+	rtbmp_bytes = howmany_64(mp->m_sb.sb_rextents, NBBY);
+	if (roundup_64(rtbmp_bytes, mp->m_sb.sb_blocksize) !=
+			mp->m_rbmip->i_disk_size)
+		return -EFSCORRUPTED;
+
+	return xfs_rtalloc_query_all(sc->mp, sc->tp, xchk_rtsum_record_free,
+			sc);
+}
+
+/* Compare the rtsummary file against the one we computed. */
+STATIC int
+xchk_rtsum_compare(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_buf		*bp;
+	struct xfs_bmbt_irec	map;
+	xfs_fileoff_t		off;
+	xchk_rtsumoff_t		sumoff = 0;
+	int			nmap;
+
+	for (off = 0; off < XFS_B_TO_FSB(mp, mp->m_rsumsize); off++) {
+		int		error = 0;
+
+		if (xchk_should_terminate(sc, &error))
+			return error;
+		if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+			return 0;
+
+		/* Make sure we have a written extent. */
+		nmap = 1;
+		error = xfs_bmapi_read(mp->m_rsumip, off, 1, &map, &nmap,
+				XFS_DATA_FORK);
+		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, off, &error))
+			return error;
+
+		if (nmap != 1 || !xfs_bmap_is_written_extent(&map)) {
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, off);
+			return 0;
+		}
+
+		/* Read a block's worth of ondisk rtsummary file. */
+		error = xfs_rtbuf_get(mp, sc->tp, off, 1, &bp);
+		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, off, &error))
+			return error;
+
+		/* Read a block's worth of computed rtsummary file. */
+		error = xfsum_copyout(sc, sumoff, sc->buf, mp->m_blockwsize);
+		if (error) {
+			xfs_trans_brelse(sc->tp, bp);
+			return error;
+		}
+
+		if (memcmp(bp->b_addr, sc->buf,
+					mp->m_blockwsize << XFS_WORDLOG) != 0)
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, off);
+
+		xfs_trans_brelse(sc->tp, bp);
+		sumoff += mp->m_blockwsize;
+	}
+
+	return 0;
+}
+
+/* Scrub the realtime summary. */
+int
+xchk_rtsummary(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_mount	*mp = sc->mp;
+	int			error = 0;
+
+	/* Invoke the fork scrubber. */
+	error = xchk_metadata_inode_forks(sc);
+	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
+		goto out_rbm;
+
+	/* Construct the new summary file from the rtbitmap. */
+	error = xchk_rtsum_compute(sc);
+	if (error == -EFSCORRUPTED) {
+		/*
+		 * EFSCORRUPTED means the rtbitmap is corrupt, which is an xref
+		 * error since we're checking the summary file.
+		 */
+		xchk_ino_xref_set_corrupt(sc, mp->m_rbmip->i_ino);
+		error = 0;
+		goto out_rbm;
+	}
+	if (error)
+		goto out_rbm;
+
+	/* Does the computed summary file match the actual rtsummary file? */
+	error = xchk_rtsum_compare(sc);
+
+out_rbm:
+	/* Unlock the rtbitmap since we're done with it. */
+	xfs_iunlock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
+	return error;
+}
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index e6962cf651d9..939d1d12917b 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -23,6 +23,7 @@
 #include "scrub/repair.h"
 #include "scrub/health.h"
 #include "scrub/stats.h"
+#include "scrub/xfile.h"
 
 /*
  * Online Scrub and Repair
@@ -167,8 +168,6 @@ xchk_teardown(
 	struct xfs_scrub	*sc,
 	int			error)
 {
-	struct xfs_inode	*ip_in = XFS_I(file_inode(sc->file));
-
 	xchk_ag_free(sc, &sc->sa);
 	if (sc->tp) {
 		if (error == 0 && (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR))
@@ -179,14 +178,16 @@ xchk_teardown(
 	}
 	if (sc->ip) {
 		if (sc->ilock_flags)
-			xfs_iunlock(sc->ip, sc->ilock_flags);
-		if (sc->ip != ip_in &&
-		    !xfs_internal_inum(sc->mp, sc->ip->i_ino))
-			xchk_irele(sc, sc->ip);
+			xchk_iunlock(sc, sc->ilock_flags);
+		xchk_irele(sc, sc->ip);
 		sc->ip = NULL;
 	}
 	if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)
 		mnt_drop_write_file(sc->file);
+	if (sc->xfile) {
+		xfile_destroy(sc->xfile);
+		sc->xfile = NULL;
+	}
 	if (sc->buf) {
 		if (sc->buf_cleanup)
 			sc->buf_cleanup(sc->buf);
@@ -321,14 +322,14 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 	},
 	[XFS_SCRUB_TYPE_RTBITMAP] = {	/* realtime bitmap */
 		.type	= ST_FS,
-		.setup	= xchk_setup_rt,
+		.setup	= xchk_setup_rtbitmap,
 		.scrub	= xchk_rtbitmap,
 		.has	= xfs_has_realtime,
 		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_RTSUM] = {	/* realtime summary */
 		.type	= ST_FS,
-		.setup	= xchk_setup_rt,
+		.setup	= xchk_setup_rtsummary,
 		.scrub	= xchk_rtsummary,
 		.has	= xfs_has_realtime,
 		.repair	= xrep_notsupported,
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index e113f2f5c254..f198c6cecef0 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -88,6 +88,10 @@ struct xfs_scrub {
 	 */
 	void				(*buf_cleanup)(void *buf);
 
+	/* xfile used by the scrubbers; freed at teardown. */
+	struct xfile			*xfile;
+
+	/* Lock flags for @ip. */
 	uint				ilock_flags;
 
 	/* See the XCHK/XREP state flags below. */
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 5100745086c8..98f6773f3ec1 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -985,6 +985,40 @@ TRACE_EVENT(xfarray_sort_stats,
 		  __entry->error)
 );
 
+#ifdef CONFIG_XFS_RT
+TRACE_EVENT(xchk_rtsum_record_free,
+	TP_PROTO(struct xfs_mount *mp, xfs_rtblock_t start,
+		 uint64_t len, unsigned int log, loff_t pos, xfs_suminfo_t v),
+	TP_ARGS(mp, start, len, log, pos, v),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(dev_t, rtdev)
+		__field(xfs_rtblock_t, start)
+		__field(unsigned long long, len)
+		__field(unsigned int, log)
+		__field(loff_t, pos)
+		__field(xfs_suminfo_t, v)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->rtdev = mp->m_rtdev_targp->bt_dev;
+		__entry->start = start;
+		__entry->len = len;
+		__entry->log = log;
+		__entry->pos = pos;
+		__entry->v = v;
+	),
+	TP_printk("dev %d:%d rtdev %d:%d rtx 0x%llx rtxcount 0x%llx log %u rsumpos 0x%llx sumcount %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  MAJOR(__entry->rtdev), MINOR(__entry->rtdev),
+		  __entry->start,
+		  __entry->len,
+		  __entry->log,
+		  __entry->pos,
+		  __entry->v)
+);
+#endif /* CONFIG_XFS_RT */
+
 /* repair tracepoints */
 #if IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR)
 
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index f3cc204bb4bf..36bd42ed9ec8 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -22,6 +22,9 @@
  * daddr: physical block number in 512b blocks
  * bbcount: number of blocks in a physical extent, in 512b blocks
  *
+ * rtx: physical rt extent number for extent mappings
+ * rtxcount: number of rt extents in an extent mapping
+ *
  * owner: reverse-mapping owner, usually inodes
  *
  * fileoff: file offset, in fs blocks