Merge tag 'repair-inode-mode-6.9_2024-02-23' of...

Merge tag 'repair-inode-mode-6.9_2024-02-23' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux into xfs-6.9-mergeC

xfs: repair inode mode by scanning dirs

One missing piece of functionality in the inode record repair code is
figuring out what to do with a file whose mode is so corrupt that we
cannot tell us the type of the file.  Originally this was done by
guessing the mode from the ondisk inode contents, but Christoph didn't
like that because it read from data fork block 0, which could be user
controlled data.

Therefore, I've replaced all that with a directory scanner that looks
for any dirents that point to the file with the garbage mode.  If so,
the ftype in the dirent will tell us exactly what mode to set on the
file.  Since users cannot directly write to the ftype field of a dirent,
this should be safe.
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>

* tag 'repair-inode-mode-6.9_2024-02-23' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux:
  xfs: repair file modes by scanning for a dirent pointing to us
  xfs: create a macro for decoding ftypes in tracepoints
  xfs: create a predicate to determine if two xfs_names are the same
  xfs: create a static name for the dot entry too
  xfs: iscan batching should handle unallocated inodes too
  xfs: cache a bunch of inodes for repair scans
  xfs: stagger the starting AG of scrub iscans to reduce contention
  xfs: allow scrub to hook metadata updates in other writers
  xfs: implement live inode scan for scrub
  xfs: speed up xfs_iwalk_adjust_start a little bit

fs/xfs/Kconfig

@@ -124,11 +124,16 @@ config XFS_DRAIN_INTENTS
 	bool
 	select JUMP_LABEL if HAVE_ARCH_JUMP_LABEL
 
+config XFS_LIVE_HOOKS
+	bool
+	select JUMP_LABEL if HAVE_ARCH_JUMP_LABEL
+
 config XFS_ONLINE_SCRUB
 	bool "XFS online metadata check support"
 	default n
 	depends on XFS_FS
 	depends on TMPFS && SHMEM
+	select XFS_LIVE_HOOKS
 	select XFS_DRAIN_INTENTS
 	help
 	  If you say Y here you will be able to check metadata on a

fs/xfs/Makefile

@@ -136,6 +136,7 @@ xfs-$(CONFIG_FS_DAX)		+= xfs_notify_failure.o
 endif
 
 xfs-$(CONFIG_XFS_DRAIN_INTENTS)	+= xfs_drain.o
+xfs-$(CONFIG_XFS_LIVE_HOOKS)	+= xfs_hooks.o
 
 # online scrub/repair
 ifeq ($(CONFIG_XFS_ONLINE_SCRUB),y)
@@ -158,6 +159,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   health.o \
 				   ialloc.o \
 				   inode.o \
+				   iscan.o \
 				   parent.o \
 				   readdir.o \
 				   refcount.o \

fs/xfs/libxfs/xfs_da_format.h

@@ -159,6 +159,17 @@ struct xfs_da3_intnode {
 
 #define XFS_DIR3_FT_MAX			9
 
+#define XFS_DIR3_FTYPE_STR \
+	{ XFS_DIR3_FT_UNKNOWN,	"unknown" }, \
+	{ XFS_DIR3_FT_REG_FILE,	"file" }, \
+	{ XFS_DIR3_FT_DIR,	"directory" }, \
+	{ XFS_DIR3_FT_CHRDEV,	"char" }, \
+	{ XFS_DIR3_FT_BLKDEV,	"block" }, \
+	{ XFS_DIR3_FT_FIFO,	"fifo" }, \
+	{ XFS_DIR3_FT_SOCK,	"sock" }, \
+	{ XFS_DIR3_FT_SYMLINK,	"symlink" }, \
+	{ XFS_DIR3_FT_WHT,	"whiteout" }
+
 /*
  * Byte offset in data block and shortform entry.
  */

fs/xfs/libxfs/xfs_dir2.c

@@ -25,6 +25,12 @@ const struct xfs_name xfs_name_dotdot = {
 	.type	= XFS_DIR3_FT_DIR,
 };
 
+const struct xfs_name xfs_name_dot = {
+	.name	= (const unsigned char *)".",
+	.len	= 1,
+	.type	= XFS_DIR3_FT_DIR,
+};
+
 /*
  * Convert inode mode to directory entry filetype
  */

fs/xfs/libxfs/xfs_dir2.h

@@ -22,6 +22,19 @@ struct xfs_dir3_icfree_hdr;
 struct xfs_dir3_icleaf_hdr;
 
 extern const struct xfs_name	xfs_name_dotdot;
+extern const struct xfs_name	xfs_name_dot;
+
+static inline bool
+xfs_dir2_samename(
+	const struct xfs_name	*n1,
+	const struct xfs_name	*n2)
+{
+	if (n1 == n2)
+		return true;
+	if (n1->len != n2->len)
+		return false;
+	return !memcmp(n1->name, n2->name, n1->len);
+}
 
 /*
  * Convert inode mode to directory entry filetype

fs/xfs/scrub/dir.c

@@ -93,11 +93,11 @@ xchk_dir_actor(
 		return -ECANCELED;
 	}
 
-	if (!strncmp(".", name->name, name->len)) {
+	if (xfs_dir2_samename(name, &xfs_name_dot)) {
 		/* If this is "." then check that the inum matches the dir. */
 		if (ino != dp->i_ino)
 			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
-	} else if (!strncmp("..", name->name, name->len)) {
+	} else if (xfs_dir2_samename(name, &xfs_name_dotdot)) {
 		/*
 		 * If this is ".." in the root inode, check that the inum
 		 * matches this dir.

fs/xfs/scrub/inode_repair.c

@@ -43,6 +43,8 @@
 #include "scrub/btree.h"
 #include "scrub/trace.h"
 #include "scrub/repair.h"
+#include "scrub/iscan.h"
+#include "scrub/readdir.h"
 
 /*
  * Inode Record Repair
@@ -126,6 +128,10 @@ struct xrep_inode {
 
 	/* Must we remove all access from this file? */
 	bool			zap_acls;
+
+	/* Inode scanner to see if we can find the ftype from dirents */
+	struct xchk_iscan	ftype_iscan;
+	uint8_t			alleged_ftype;
 };
 
 /*
@@ -227,26 +233,233 @@ xrep_dinode_header(
 	dip->di_gen = cpu_to_be32(sc->sm->sm_gen);
 }
 
-/* Turn di_mode into /something/ recognizable. */
-STATIC void
+/*
+ * If this directory entry points to the scrub target inode, then the directory
+ * we're scanning is the parent of the scrub target inode.
+ */
+STATIC int
+xrep_dinode_findmode_dirent(
+	struct xfs_scrub		*sc,
+	struct xfs_inode		*dp,
+	xfs_dir2_dataptr_t		dapos,
+	const struct xfs_name		*name,
+	xfs_ino_t			ino,
+	void				*priv)
+{
+	struct xrep_inode		*ri = priv;
+	int				error = 0;
+
+	if (xchk_should_terminate(ri->sc, &error))
+		return error;
+
+	if (ino != sc->sm->sm_ino)
+		return 0;
+
+	/* Ignore garbage directory entry names. */
+	if (name->len == 0 || !xfs_dir2_namecheck(name->name, name->len))
+		return -EFSCORRUPTED;
+
+	/* Don't pick up dot or dotdot entries; we only want child dirents. */
+	if (xfs_dir2_samename(name, &xfs_name_dotdot) ||
+	    xfs_dir2_samename(name, &xfs_name_dot))
+		return 0;
+
+	/*
+	 * Uhoh, more than one parent for this inode and they don't agree on
+	 * the file type?
+	 */
+	if (ri->alleged_ftype != XFS_DIR3_FT_UNKNOWN &&
+	    ri->alleged_ftype != name->type) {
+		trace_xrep_dinode_findmode_dirent_inval(ri->sc, dp, name->type,
+				ri->alleged_ftype);
+		return -EFSCORRUPTED;
+	}
+
+	/* We found a potential parent; remember the ftype. */
+	trace_xrep_dinode_findmode_dirent(ri->sc, dp, name->type);
+	ri->alleged_ftype = name->type;
+	return 0;
+}
+
+/*
+ * If this is a directory, walk the dirents looking for any that point to the
+ * scrub target inode.
+ */
+STATIC int
+xrep_dinode_findmode_walk_directory(
+	struct xrep_inode	*ri,
+	struct xfs_inode	*dp)
+{
+	struct xfs_scrub	*sc = ri->sc;
+	unsigned int		lock_mode;
+	int			error = 0;
+
+	/*
+	 * Scan the directory to see if there it contains an entry pointing to
+	 * the directory that we are repairing.
+	 */
+	lock_mode = xfs_ilock_data_map_shared(dp);
+
+	/*
+	 * If this directory is known to be sick, we cannot scan it reliably
+	 * and must abort.
+	 */
+	if (xfs_inode_has_sickness(dp, XFS_SICK_INO_CORE |
+				       XFS_SICK_INO_BMBTD |
+				       XFS_SICK_INO_DIR)) {
+		error = -EFSCORRUPTED;
+		goto out_unlock;
+	}
+
+	/*
+	 * We cannot complete our parent pointer scan if a directory looks as
+	 * though it has been zapped by the inode record repair code.
+	 */
+	if (xchk_dir_looks_zapped(dp)) {
+		error = -EBUSY;
+		goto out_unlock;
+	}
+
+	error = xchk_dir_walk(sc, dp, xrep_dinode_findmode_dirent, ri);
+	if (error)
+		goto out_unlock;
+
+out_unlock:
+	xfs_iunlock(dp, lock_mode);
+	return error;
+}
+
+/*
+ * Try to find the mode of the inode being repaired by looking for directories
+ * that point down to this file.
+ */
+STATIC int
+xrep_dinode_find_mode(
+	struct xrep_inode	*ri,
+	uint16_t		*mode)
+{
+	struct xfs_scrub	*sc = ri->sc;
+	struct xfs_inode	*dp;
+	int			error;
+
+	/* No ftype means we have no other metadata to consult. */
+	if (!xfs_has_ftype(sc->mp)) {
+		*mode = S_IFREG;
+		return 0;
+	}
+
+	/*
+	 * Scan all directories for parents that might point down to this
+	 * inode.  Skip the inode being repaired during the scan since it
+	 * cannot be its own parent.  Note that we still hold the AGI locked
+	 * so there's a real possibility that _iscan_iter can return EBUSY.
+	 */
+	xchk_iscan_start(sc, 5000, 100, &ri->ftype_iscan);
+	ri->ftype_iscan.skip_ino = sc->sm->sm_ino;
+	ri->alleged_ftype = XFS_DIR3_FT_UNKNOWN;
+	while ((error = xchk_iscan_iter(&ri->ftype_iscan, &dp)) == 1) {
+		if (S_ISDIR(VFS_I(dp)->i_mode))
+			error = xrep_dinode_findmode_walk_directory(ri, dp);
+		xchk_iscan_mark_visited(&ri->ftype_iscan, dp);
+		xchk_irele(sc, dp);
+		if (error < 0)
+			break;
+		if (xchk_should_terminate(sc, &error))
+			break;
+	}
+	xchk_iscan_iter_finish(&ri->ftype_iscan);
+	xchk_iscan_teardown(&ri->ftype_iscan);
+
+	if (error == -EBUSY) {
+		if (ri->alleged_ftype != XFS_DIR3_FT_UNKNOWN) {
+			/*
+			 * If we got an EBUSY after finding at least one
+			 * dirent, that means the scan found an inode on the
+			 * inactivation list and could not open it.  Accept the
+			 * alleged ftype and install a new mode below.
+			 */
+			error = 0;
+		} else if (!(sc->flags & XCHK_TRY_HARDER)) {
+			/*
+			 * Otherwise, retry the operation one time to see if
+			 * the reason for the delay is an inode from the same
+			 * cluster buffer waiting on the inactivation list.
+			 */
+			error = -EDEADLOCK;
+		}
+	}
+	if (error)
+		return error;
+
+	/*
+	 * Convert the discovered ftype into the file mode.  If all else fails,
+	 * return S_IFREG.
+	 */
+	switch (ri->alleged_ftype) {
+	case XFS_DIR3_FT_DIR:
+		*mode = S_IFDIR;
+		break;
+	case XFS_DIR3_FT_WHT:
+	case XFS_DIR3_FT_CHRDEV:
+		*mode = S_IFCHR;
+		break;
+	case XFS_DIR3_FT_BLKDEV:
+		*mode = S_IFBLK;
+		break;
+	case XFS_DIR3_FT_FIFO:
+		*mode = S_IFIFO;
+		break;
+	case XFS_DIR3_FT_SOCK:
+		*mode = S_IFSOCK;
+		break;
+	case XFS_DIR3_FT_SYMLINK:
+		*mode = S_IFLNK;
+		break;
+	default:
+		*mode = S_IFREG;
+		break;
+	}
+	return 0;
+}
+
+/* Turn di_mode into /something/ recognizable.  Returns true if we succeed. */
+STATIC int
 xrep_dinode_mode(
 	struct xrep_inode	*ri,
 	struct xfs_dinode	*dip)
 {
 	struct xfs_scrub	*sc = ri->sc;
 	uint16_t		mode = be16_to_cpu(dip->di_mode);
+	int			error;
 
 	trace_xrep_dinode_mode(sc, dip);
 
 	if (mode == 0 || xfs_mode_to_ftype(mode) != XFS_DIR3_FT_UNKNOWN)
-		return;
+		return 0;
+
+	/* Try to fix the mode.  If we cannot, then leave everything alone. */
+	error = xrep_dinode_find_mode(ri, &mode);
+	switch (error) {
+	case -EINTR:
+	case -EBUSY:
+	case -EDEADLOCK:
+		/* temporary failure or fatal signal */
+		return error;
+	case 0:
+		/* found mode */
+		break;
+	default:
+		/* some other error, assume S_IFREG */
+		mode = S_IFREG;
+		break;
+	}
 
 	/* bad mode, so we set it to a file that only root can read */
-	mode = S_IFREG;
 	dip->di_mode = cpu_to_be16(mode);
 	dip->di_uid = 0;
 	dip->di_gid = 0;
 	ri->zap_acls = true;
+	return 0;
 }
 
 /* Fix any conflicting flags that the verifiers complain about. */
@@ -1107,12 +1320,15 @@ xrep_dinode_core(
 	/* Fix everything the verifier will complain about. */
 	dip = xfs_buf_offset(bp, ri->imap.im_boffset);
 	xrep_dinode_header(sc, dip);
-	xrep_dinode_mode(ri, dip);
+	iget_error = xrep_dinode_mode(ri, dip);
+	if (iget_error)
+		goto write;
 	xrep_dinode_flags(sc, dip, ri->rt_extents > 0);
 	xrep_dinode_size(ri, dip);
 	xrep_dinode_extsize_hints(sc, dip);
 	xrep_dinode_zap_forks(ri, dip);
 
+write:
 	/* Write out the inode. */
 	trace_xrep_dinode_fixed(sc, dip);
 	xfs_dinode_calc_crc(sc->mp, dip);
@@ -1128,7 +1344,8 @@ xrep_dinode_core(
 	 * accessing the inode.  If iget fails, we still need to commit the
 	 * changes.
 	 */
-	iget_error = xchk_iget(sc, ino, &sc->ip);
+	if (!iget_error)
+		iget_error = xchk_iget(sc, ino, &sc->ip);
 	if (!iget_error)
 		xchk_ilock(sc, XFS_IOLOCK_EXCL);
 
@@ -1496,6 +1713,13 @@ xrep_inode(
 		ASSERT(ri != NULL);
 
 		error = xrep_dinode_problems(ri);
+		if (error == -EBUSY) {
+			/*
+			 * Directory scan to recover inode mode encountered a
+			 * busy inode, so we did not continue repairing things.
+			 */
+			return 0;
+		}
 		if (error)
 			return error;
 

fs/xfs/scrub/iscan.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_ISCAN_H__
+#define __XFS_SCRUB_ISCAN_H__
+
+struct xchk_iscan {
+	struct xfs_scrub	*sc;
+
+	/* Lock to protect the scan cursor. */
+	struct mutex		lock;
+
+	/*
+	 * This is the first inode in the inumber address space that we
+	 * examined.  When the scan wraps around back to here, the scan is
+	 * finished.
+	 */
+	xfs_ino_t		scan_start_ino;
+
+	/* This is the inode that will be examined next. */
+	xfs_ino_t		cursor_ino;
+
+	/* If nonzero and non-NULL, skip this inode when scanning. */
+	xfs_ino_t		skip_ino;
+
+	/*
+	 * This is the last inode that we've successfully scanned, either
+	 * because the caller scanned it, or we moved the cursor past an empty
+	 * part of the inode address space.  Scan callers should only use the
+	 * xchk_iscan_visit function to modify this.
+	 */
+	xfs_ino_t		__visited_ino;
+
+	/* Operational state of the livescan. */
+	unsigned long		__opstate;
+
+	/* Give up on iterating @cursor_ino if we can't iget it by this time. */
+	unsigned long		__iget_deadline;
+
+	/* Amount of time (in ms) that we will try to iget an inode. */
+	unsigned int		iget_timeout;
+
+	/* Wait this many ms to retry an iget. */
+	unsigned int		iget_retry_delay;
+
+	/*
+	 * The scan grabs batches of inodes and stashes them here before
+	 * handing them out with _iter.  Unallocated inodes are set in the
+	 * mask so that all updates to that inode are selected for live
+	 * update propagation.
+	 */
+	xfs_ino_t		__batch_ino;
+	xfs_inofree_t		__skipped_inomask;
+	struct xfs_inode	*__inodes[XFS_INODES_PER_CHUNK];
+};
+
+/* Set if the scan has been aborted due to some event in the fs. */
+#define XCHK_ISCAN_OPSTATE_ABORTED	(1)
+
+static inline bool
+xchk_iscan_aborted(const struct xchk_iscan *iscan)
+{
+	return test_bit(XCHK_ISCAN_OPSTATE_ABORTED, &iscan->__opstate);
+}
+
+static inline void
+xchk_iscan_abort(struct xchk_iscan *iscan)
+{
+	set_bit(XCHK_ISCAN_OPSTATE_ABORTED, &iscan->__opstate);
+}
+
+void xchk_iscan_start(struct xfs_scrub *sc, unsigned int iget_timeout,
+		unsigned int iget_retry_delay, struct xchk_iscan *iscan);
+void xchk_iscan_teardown(struct xchk_iscan *iscan);
+
+int xchk_iscan_iter(struct xchk_iscan *iscan, struct xfs_inode **ipp);
+void xchk_iscan_iter_finish(struct xchk_iscan *iscan);
+
+void xchk_iscan_mark_visited(struct xchk_iscan *iscan, struct xfs_inode *ip);
+bool xchk_iscan_want_live_update(struct xchk_iscan *iscan, xfs_ino_t ino);
+
+#endif /* __XFS_SCRUB_ISCAN_H__ */

fs/xfs/scrub/trace.c

@@ -16,10 +16,12 @@
 #include "xfs_rtbitmap.h"
 #include "xfs_quota.h"
 #include "xfs_quota_defs.h"
+#include "xfs_da_format.h"
 #include "scrub/scrub.h"
 #include "scrub/xfile.h"
 #include "scrub/xfarray.h"
 #include "scrub/quota.h"
+#include "scrub/iscan.h"
 
 /* Figure out which block the btree cursor was pointing to. */
 static inline xfs_fsblock_t

fs/xfs/scrub/trace.h

@@ -16,10 +16,12 @@
 #include <linux/tracepoint.h>
 #include "xfs_bit.h"
 
+struct xfs_scrub;
 struct xfile;
 struct xfarray;
 struct xfarray_sortinfo;
 struct xchk_dqiter;
+struct xchk_iscan;
 
 /*
  * ftrace's __print_symbolic requires that all enum values be wrapped in the
@@ -1146,6 +1148,149 @@ TRACE_EVENT(xchk_rtsum_record_free,
 );
 #endif /* CONFIG_XFS_RT */
 
+DECLARE_EVENT_CLASS(xchk_iscan_class,
+	TP_PROTO(struct xchk_iscan *iscan),
+	TP_ARGS(iscan),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, cursor)
+		__field(xfs_ino_t, visited)
+	),
+	TP_fast_assign(
+		__entry->dev = iscan->sc->mp->m_super->s_dev;
+		__entry->cursor = iscan->cursor_ino;
+		__entry->visited = iscan->__visited_ino;
+	),
+	TP_printk("dev %d:%d iscan cursor 0x%llx visited 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->cursor,
+		  __entry->visited)
+)
+#define DEFINE_ISCAN_EVENT(name) \
+DEFINE_EVENT(xchk_iscan_class, name, \
+	TP_PROTO(struct xchk_iscan *iscan), \
+	TP_ARGS(iscan))
+DEFINE_ISCAN_EVENT(xchk_iscan_move_cursor);
+DEFINE_ISCAN_EVENT(xchk_iscan_visit);
+DEFINE_ISCAN_EVENT(xchk_iscan_skip);
+DEFINE_ISCAN_EVENT(xchk_iscan_advance_ag);
+
+DECLARE_EVENT_CLASS(xchk_iscan_ino_class,
+	TP_PROTO(struct xchk_iscan *iscan, xfs_ino_t ino),
+	TP_ARGS(iscan, ino),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, startino)
+		__field(xfs_ino_t, cursor)
+		__field(xfs_ino_t, visited)
+		__field(xfs_ino_t, ino)
+	),
+	TP_fast_assign(
+		__entry->dev = iscan->sc->mp->m_super->s_dev;
+		__entry->startino = iscan->scan_start_ino;
+		__entry->cursor = iscan->cursor_ino;
+		__entry->visited = iscan->__visited_ino;
+		__entry->ino = ino;
+	),
+	TP_printk("dev %d:%d iscan start 0x%llx cursor 0x%llx visited 0x%llx ino 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->startino,
+		  __entry->cursor,
+		  __entry->visited,
+		  __entry->ino)
+)
+#define DEFINE_ISCAN_INO_EVENT(name) \
+DEFINE_EVENT(xchk_iscan_ino_class, name, \
+	TP_PROTO(struct xchk_iscan *iscan, xfs_ino_t ino), \
+	TP_ARGS(iscan, ino))
+DEFINE_ISCAN_INO_EVENT(xchk_iscan_want_live_update);
+DEFINE_ISCAN_INO_EVENT(xchk_iscan_start);
+
+TRACE_EVENT(xchk_iscan_iget,
+	TP_PROTO(struct xchk_iscan *iscan, int error),
+	TP_ARGS(iscan, error),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, cursor)
+		__field(xfs_ino_t, visited)
+		__field(int, error)
+	),
+	TP_fast_assign(
+		__entry->dev = iscan->sc->mp->m_super->s_dev;
+		__entry->cursor = iscan->cursor_ino;
+		__entry->visited = iscan->__visited_ino;
+		__entry->error = error;
+	),
+	TP_printk("dev %d:%d iscan cursor 0x%llx visited 0x%llx error %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->cursor,
+		  __entry->visited,
+		  __entry->error)
+);
+
+TRACE_EVENT(xchk_iscan_iget_batch,
+	TP_PROTO(struct xfs_mount *mp, struct xchk_iscan *iscan,
+		 unsigned int nr, unsigned int avail),
+	TP_ARGS(mp, iscan, nr, avail),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, cursor)
+		__field(xfs_ino_t, visited)
+		__field(unsigned int, nr)
+		__field(unsigned int, avail)
+		__field(unsigned int, unavail)
+		__field(xfs_ino_t, batch_ino)
+		__field(unsigned long long, skipmask)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->cursor = iscan->cursor_ino;
+		__entry->visited = iscan->__visited_ino;
+		__entry->nr = nr;
+		__entry->avail = avail;
+		__entry->unavail = hweight64(iscan->__skipped_inomask);
+		__entry->batch_ino = iscan->__batch_ino;
+		__entry->skipmask = iscan->__skipped_inomask;
+	),
+	TP_printk("dev %d:%d iscan cursor 0x%llx visited 0x%llx batchino 0x%llx skipmask 0x%llx nr %u avail %u unavail %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->cursor,
+		  __entry->visited,
+		  __entry->batch_ino,
+		  __entry->skipmask,
+		  __entry->nr,
+		  __entry->avail,
+		  __entry->unavail)
+);
+
+TRACE_EVENT(xchk_iscan_iget_retry_wait,
+	TP_PROTO(struct xchk_iscan *iscan),
+	TP_ARGS(iscan),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, cursor)
+		__field(xfs_ino_t, visited)
+		__field(unsigned int, retry_delay)
+		__field(unsigned long, remaining)
+		__field(unsigned int, iget_timeout)
+	),
+	TP_fast_assign(
+		__entry->dev = iscan->sc->mp->m_super->s_dev;
+		__entry->cursor = iscan->cursor_ino;
+		__entry->visited = iscan->__visited_ino;
+		__entry->retry_delay = iscan->iget_retry_delay;
+		__entry->remaining = jiffies_to_msecs(iscan->__iget_deadline - jiffies);
+		__entry->iget_timeout = iscan->iget_timeout;
+	),
+	TP_printk("dev %d:%d iscan cursor 0x%llx visited 0x%llx remaining %lu timeout %u delay %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->cursor,
+		  __entry->visited,
+		  __entry->remaining,
+		  __entry->iget_timeout,
+		  __entry->retry_delay)
+);
+
 /* repair tracepoints */
 #if IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR)
 
@@ -1672,6 +1817,55 @@ TRACE_EVENT(xrep_dinode_count_rmaps,
 		  __entry->attr_extents)
 );
 
+TRACE_EVENT(xrep_dinode_findmode_dirent,
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_inode *dp,
+		 unsigned int ftype),
+	TP_ARGS(sc, dp, ftype),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(xfs_ino_t, parent_ino)
+		__field(unsigned int, ftype)
+	),
+	TP_fast_assign(
+		__entry->dev = sc->mp->m_super->s_dev;
+		__entry->ino = sc->sm->sm_ino;
+		__entry->parent_ino = dp->i_ino;
+		__entry->ftype = ftype;
+	),
+	TP_printk("dev %d:%d ino 0x%llx parent_ino 0x%llx ftype '%s'",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->parent_ino,
+		  __print_symbolic(__entry->ftype, XFS_DIR3_FTYPE_STR))
+);
+
+TRACE_EVENT(xrep_dinode_findmode_dirent_inval,
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_inode *dp,
+		 unsigned int ftype, unsigned int found_ftype),
+	TP_ARGS(sc, dp, ftype, found_ftype),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(xfs_ino_t, parent_ino)
+		__field(unsigned int, ftype)
+		__field(unsigned int, found_ftype)
+	),
+	TP_fast_assign(
+		__entry->dev = sc->mp->m_super->s_dev;
+		__entry->ino = sc->sm->sm_ino;
+		__entry->parent_ino = dp->i_ino;
+		__entry->ftype = ftype;
+		__entry->found_ftype = found_ftype;
+	),
+	TP_printk("dev %d:%d ino 0x%llx parent_ino 0x%llx ftype '%s' found_ftype '%s'",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->parent_ino,
+		  __print_symbolic(__entry->ftype, XFS_DIR3_FTYPE_STR),
+		  __print_symbolic(__entry->found_ftype, XFS_DIR3_FTYPE_STR))
+);
+
 TRACE_EVENT(xrep_cow_mark_file_range,
 	TP_PROTO(struct xfs_inode *ip, xfs_fsblock_t startblock,
 		 xfs_fileoff_t startoff, xfs_filblks_t blockcount),

fs/xfs/xfs_hooks.c

+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2022-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#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_ag.h"
+#include "xfs_trace.h"
+
+/* Initialize a notifier chain. */
+void
+xfs_hooks_init(
+	struct xfs_hooks	*chain)
+{
+	BLOCKING_INIT_NOTIFIER_HEAD(&chain->head);
+}
+
+/* Make it so a function gets called whenever we hit a certain hook point. */
+int
+xfs_hooks_add(
+	struct xfs_hooks	*chain,
+	struct xfs_hook		*hook)
+{
+	ASSERT(hook->nb.notifier_call != NULL);
+	BUILD_BUG_ON(offsetof(struct xfs_hook, nb) != 0);
+
+	return blocking_notifier_chain_register(&chain->head, &hook->nb);
+}
+
+/* Remove a previously installed hook. */
+void
+xfs_hooks_del(
+	struct xfs_hooks	*chain,
+	struct xfs_hook		*hook)
+{
+	blocking_notifier_chain_unregister(&chain->head, &hook->nb);
+}
+
+/* Call a hook.  Returns the NOTIFY_* value returned by the last hook. */
+int
+xfs_hooks_call(
+	struct xfs_hooks	*chain,
+	unsigned long		val,
+	void			*priv)
+{
+	return blocking_notifier_call_chain(&chain->head, val, priv);
+}

fs/xfs/xfs_hooks.h

+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2022-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef XFS_HOOKS_H_
+#define XFS_HOOKS_H_
+
+#ifdef CONFIG_XFS_LIVE_HOOKS
+struct xfs_hooks {
+	struct blocking_notifier_head	head;
+};
+
+/*
+ * If jump labels are enabled in Kconfig, the static key uses nop sleds and
+ * code patching to eliminate the overhead of taking the rwsem in
+ * blocking_notifier_call_chain when there are no hooks configured.  If not,
+ * the static key per-call overhead is an atomic read.  Most arches that can
+ * handle XFS also support jump labels.
+ *
+ * Note: Patching the kernel code requires taking the cpu hotplug lock.  Other
+ * parts of the kernel allocate memory with that lock held, which means that
+ * XFS callers cannot hold any locks that might be used by memory reclaim or
+ * writeback when calling the static_branch_{inc,dec} functions.
+ */
+# define DEFINE_STATIC_XFS_HOOK_SWITCH(name) \
+	static DEFINE_STATIC_KEY_FALSE(name)
+# define xfs_hooks_switch_on(name)	static_branch_inc(name)
+# define xfs_hooks_switch_off(name)	static_branch_dec(name)
+# define xfs_hooks_switched_on(name)	static_branch_unlikely(name)
+
+struct xfs_hook {
+	/* This must come at the start of the structure. */
+	struct notifier_block		nb;
+};
+
+typedef	int (*xfs_hook_fn_t)(struct xfs_hook *hook, unsigned long action,
+		void *data);
+
+void xfs_hooks_init(struct xfs_hooks *chain);
+int xfs_hooks_add(struct xfs_hooks *chain, struct xfs_hook *hook);
+void xfs_hooks_del(struct xfs_hooks *chain, struct xfs_hook *hook);
+int xfs_hooks_call(struct xfs_hooks *chain, unsigned long action,
+		void *priv);
+
+static inline void xfs_hook_setup(struct xfs_hook *hook, notifier_fn_t fn)
+{
+	hook->nb.notifier_call = fn;
+	hook->nb.priority = 0;
+}
+
+#else
+
+struct xfs_hooks { /* empty */ };
+
+# define DEFINE_STATIC_XFS_HOOK_SWITCH(name)
+# define xfs_hooks_switch_on(name)		((void)0)
+# define xfs_hooks_switch_off(name)		((void)0)
+# define xfs_hooks_switched_on(name)		(false)
+
+# define xfs_hooks_init(chain)			((void)0)
+# define xfs_hooks_call(chain, val, priv)	(NOTIFY_DONE)
+#endif
+
+#endif /* XFS_HOOKS_H_ */

fs/xfs/xfs_iwalk.c

@@ -22,6 +22,7 @@
 #include "xfs_trans.h"
 #include "xfs_pwork.h"
 #include "xfs_ag.h"
+#include "xfs_bit.h"
 
 /*
  * Walking Inodes in the Filesystem
@@ -131,21 +132,11 @@ xfs_iwalk_adjust_start(
 	struct xfs_inobt_rec_incore	*irec)	/* btree record */
 {
 	int				idx;	/* index into inode chunk */
-	int				i;
 
 	idx = agino - irec->ir_startino;
 
-	/*
-	 * We got a right chunk with some left inodes allocated at it.  Grab
-	 * the chunk record.  Mark all the uninteresting inodes free because
-	 * they're before our start point.
-	 */
-	for (i = 0; i < idx; i++) {
-		if (XFS_INOBT_MASK(i) & ~irec->ir_free)
-			irec->ir_freecount++;
-	}
-
 	irec->ir_free |= xfs_inobt_maskn(0, idx);
+	irec->ir_freecount = hweight64(irec->ir_free);
 }
 
 /* Allocate memory for a walk. */

fs/xfs/xfs_linux.h

@@ -81,6 +81,7 @@ typedef __u32			xfs_nlink_t;
 #include "xfs_buf.h"
 #include "xfs_message.h"
 #include "xfs_drain.h"
+#include "xfs_hooks.h"
 
 #ifdef __BIG_ENDIAN
 #define XFS_NATIVE_HOST 1