[PATCH 1/3] fuzzy: mask off a few more inode fields from the fuzz tests

[PATCH 1/3] fuzzy: mask off a few more inode fields from the fuzz tests

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

XFS doesn't do any validation for filestreams, so don't waste time
fuzzing that.  Exclude the bigtime flag, since we already have inode
timestamps on the no-fuzz list.  Exclude the warning counters, since
they're defunct now.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 common/fuzzy |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)


diff --git a/common/fuzzy b/common/fuzzy
index f5d45cb28f..35cf581cd3 100644
--- a/common/fuzzy
+++ b/common/fuzzy
@@ -120,7 +120,11 @@ __filter_unvalidated_xfs_db_fields() {
 	    -e '/^entries.*secure/d' \
 	    -e '/^a.sfattr.list.*value/d' \
 	    -e '/^a.sfattr.list.*root/d' \
-	    -e '/^a.sfattr.list.*secure/d'
+	    -e '/^a.sfattr.list.*secure/d' \
+	    -e '/^core.filestream/d' \
+	    -e '/^v3.bigtime/d' \
+	    -e '/\.rtbwarns/d' \
+	    -e '/\.[ib]warns/d'
 }
 
 # Filter the xfs_db print command's field debug information

[PATCH 2/3] fuzzy: allow FUZZ_REWRITE_DURATION to control fsstress runtime when fuzzing

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

For each iteration of the fuzz test loop, we try to correct the problem,
and then we run fsstress on the (allegedly corrected) filesystem to
check that subsequent use of the filesystem won't crash the kernel or
panic.

Now that fsstress has a --duration switch, let's add a new config
variable that people can set to constrain the amount of time that a fuzz
test run takes.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 check        |   12 ++++++++++++
 common/fuzzy |    7 +++++--
 2 files changed, 17 insertions(+), 2 deletions(-)


diff --git a/check b/check
index 71b9fbd075..e567c5e4bb 100755
--- a/check
+++ b/check
@@ -382,6 +382,18 @@ if [ -n "$SOAK_DURATION" ]; then
 	fi
 fi
 
+# If the test config specified a fuzz rewrite test duration, see if there are
+# any unit suffixes that need converting to an integer seconds count.
+if [ -n "$FUZZ_REWRITE_DURATION" ]; then
+	FUZZ_REWRITE_DURATION="$(echo "$FUZZ_REWRITE_DURATION" | \
+		sed -e 's/^\([.0-9]*\)\([a-z]\)*/\1 \2/g' | \
+		$AWK_PROG -f $here/src/soak_duration.awk)"
+	if [ $? -ne 0 ]; then
+		status=1
+		exit 1
+	fi
+fi
+
 if [ -n "$subdir_xfile" ]; then
 	for d in $SRC_GROUPS $FSTYP; do
 		[ -f $SRC_DIR/$d/$subdir_xfile ] || continue
diff --git a/common/fuzzy b/common/fuzzy
index 35cf581cd3..bbf7f83d9e 100644
--- a/common/fuzzy
+++ b/common/fuzzy
@@ -6,15 +6,18 @@
 
 # Modify various files after a fuzzing operation
 _scratch_fuzz_modify() {
+	local fsstress_args=(-n $((TIME_FACTOR * 10000)) -p $((LOAD_FACTOR * 4)) )
+	test -n "${FUZZ_REWRITE_DURATION}" && fsstress_args+=("--duration=${FUZZ_REWRITE_DURATION}")
+
 	echo "+++ stressing filesystem"
 	mkdir -p $SCRATCH_MNT/data
 	_xfs_force_bdev data $SCRATCH_MNT/data
-	$FSSTRESS_PROG -n $((TIME_FACTOR * 10000)) -p $((LOAD_FACTOR * 4)) -d $SCRATCH_MNT/data
+	$FSSTRESS_PROG "${fsstress_args[@]}" -d $SCRATCH_MNT/data
 
 	if _xfs_has_feature "$SCRATCH_MNT" realtime; then
 		mkdir -p $SCRATCH_MNT/rt
 		_xfs_force_bdev realtime $SCRATCH_MNT/rt
-		$FSSTRESS_PROG -n $((TIME_FACTOR * 10000)) -p $((LOAD_FACTOR * 4)) -d $SCRATCH_MNT/rt
+		$FSSTRESS_PROG "${fsstress_args[@]}" -d $SCRATCH_MNT/rt
 	else
 		echo "+++ xfs realtime not configured"
 	fi

[PATCH 3/3] fuzzy: test other dquot ids

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 common/fuzzy    |   14 ++++++++++++++
 common/populate |   14 ++++++++++++++
 tests/xfs/425   |   10 +++++++---
 tests/xfs/426   |   10 +++++++---
 tests/xfs/427   |   10 +++++++---
 tests/xfs/428   |   10 +++++++---
 tests/xfs/429   |   10 +++++++---
 tests/xfs/430   |   10 +++++++---
 tests/xfs/487   |   10 +++++++---
 tests/xfs/488   |   10 +++++++---
 tests/xfs/489   |   10 +++++++---
 tests/xfs/779   |   10 +++++++---
 tests/xfs/780   |   10 +++++++---
 tests/xfs/781   |   10 +++++++---
 14 files changed, 112 insertions(+), 36 deletions(-)


diff --git a/common/fuzzy b/common/fuzzy
index bbf7f83d9e..b72b4a9fe7 100644
--- a/common/fuzzy
+++ b/common/fuzzy
@@ -678,6 +678,20 @@ _scratch_xfs_set_xattr_fuzz_types() {
 	SCRATCH_XFS_XATTR_FUZZ_TYPES=(EXTENTS_REMOTE3K EXTENTS_REMOTE4K LEAF NODE)
 }
 
+# Sets the array SCRATCH_XFS_QUOTA_FUZZ_IDS to the list of dquot ids available
+# for fuzzing.  By default, this list contains 0 (root), 4242 (non-root), and
+# 8484 (zero counts).  Users can override this by setting
+# SCRATCH_XFS_LIST_FUZZ_QUOTAIDS in the environment.
+_scratch_xfs_set_quota_fuzz_ids() {
+	if [ -n "${SCRATCH_XFS_LIST_FUZZ_QUOTAIDS}" ]; then
+		mapfile -t SCRATCH_XFS_QUOTA_FUZZ_IDS < \
+				<(echo "${SCRATCH_XFS_LIST_FUZZ_QUOTAIDS}" | tr '[ ,]' '[\n\n]')
+		return
+	fi
+
+	SCRATCH_XFS_QUOTA_FUZZ_IDS=(0 4242 8484)
+}
+
 # Grab the list of available fuzzing verbs
 _scratch_xfs_list_fuzz_verbs() {
 	if [ -n "${SCRATCH_XFS_LIST_FUZZ_VERBS}" ]; then
diff --git a/common/populate b/common/populate
index 3d233073c9..8097151919 100644
--- a/common/populate
+++ b/common/populate
@@ -360,6 +360,20 @@ _scratch_xfs_populate() {
 	mknod "${SCRATCH_MNT}/S_IFBLK" b 1 1
 	mknod "${SCRATCH_MNT}/S_IFIFO" p
 
+	# non-root dquot
+	local nonroot_id=4242
+	echo "${nonroot_id}" > "${SCRATCH_MNT}/non_root_dquot"
+	chown "${nonroot_id}:${nonroot_id}" "${SCRATCH_MNT}/non_root_dquot"
+	$XFS_IO_PROG -c "chproj ${nonroot_id}" "${SCRATCH_MNT}/non_root_dquot"
+
+	# empty dquot
+	local empty_id=8484
+	echo "${empty_id}" > "${SCRATCH_MNT}/empty_dquot"
+	chown "${empty_id}:${empty_id}" "${SCRATCH_MNT}/empty_dquot"
+	$XFS_IO_PROG -c "chproj ${empty_id}" "${SCRATCH_MNT}/empty_dquot"
+	chown "0:0" "${SCRATCH_MNT}/empty_dquot"
+	$XFS_IO_PROG -c "chproj 0" "${SCRATCH_MNT}/empty_dquot"
+
 	# special file with an xattr
 	setfacl -P -m u:nobody:r ${SCRATCH_MNT}/S_IFCHR
 
diff --git a/tests/xfs/425 b/tests/xfs/425
index c2e16ee87e..5275e594b2 100755
--- a/tests/xfs/425
+++ b/tests/xfs/425
@@ -27,9 +27,13 @@ echo "Format and populate"
 _scratch_populate_cached nofill > $seqres.full 2>&1
 echo "${MOUNT_OPTIONS}" | grep -q 'usrquota' || _notrun "user quota disabled"
 
-echo "Fuzz user 0 dquot"
-_scratch_xfs_fuzz_metadata '' 'offline'  "dquot -u 0" >> $seqres.full
-echo "Done fuzzing dquot"
+_scratch_xfs_set_quota_fuzz_ids
+
+for id in "${SCRATCH_XFS_QUOTA_FUZZ_IDS[@]}"; do
+	echo "Fuzz user $id dquot"
+	_scratch_xfs_fuzz_metadata '' 'offline'  "dquot -u $id" >> $seqres.full
+	echo "Done fuzzing dquot"
+done
 
 # success, all done
 status=0
diff --git a/tests/xfs/426 b/tests/xfs/426
index e52b15f28d..06f0f44b62 100755
--- a/tests/xfs/426
+++ b/tests/xfs/426
@@ -27,9 +27,13 @@ echo "Format and populate"
 _scratch_populate_cached nofill > $seqres.full 2>&1
 echo "${MOUNT_OPTIONS}" | grep -q 'usrquota' || _notrun "user quota disabled"
 
-echo "Fuzz user 0 dquot"
-_scratch_xfs_fuzz_metadata '' 'online'  "dquot -u 0" >> $seqres.full
-echo "Done fuzzing dquot"
+_scratch_xfs_set_quota_fuzz_ids
+
+for id in "${SCRATCH_XFS_QUOTA_FUZZ_IDS[@]}"; do
+	echo "Fuzz user $id dquot"
+	_scratch_xfs_fuzz_metadata '' 'online'  "dquot -u $id" >> $seqres.full
+	echo "Done fuzzing dquot"
+done
 
 # success, all done
 status=0
diff --git a/tests/xfs/427 b/tests/xfs/427
index 19f45fbd81..327cddd879 100755
--- a/tests/xfs/427
+++ b/tests/xfs/427
@@ -27,9 +27,13 @@ echo "Format and populate"
 _scratch_populate_cached nofill > $seqres.full 2>&1
 echo "${MOUNT_OPTIONS}" | grep -q 'grpquota' || _notrun "group quota disabled"
 
-echo "Fuzz group 0 dquot"
-_scratch_xfs_fuzz_metadata '' 'offline'  "dquot -g 0" >> $seqres.full
-echo "Done fuzzing dquot"
+_scratch_xfs_set_quota_fuzz_ids
+
+for id in "${SCRATCH_XFS_QUOTA_FUZZ_IDS[@]}"; do
+	echo "Fuzz group $id dquot"
+	_scratch_xfs_fuzz_metadata '' 'offline'  "dquot -g $id" >> $seqres.full
+	echo "Done fuzzing dquot"
+done
 
 # success, all done
 status=0
diff --git a/tests/xfs/428 b/tests/xfs/428
index 338e659df2..80b05b8450 100755
--- a/tests/xfs/428
+++ b/tests/xfs/428
@@ -27,9 +27,13 @@ echo "Format and populate"
 _scratch_populate_cached nofill > $seqres.full 2>&1
 echo "${MOUNT_OPTIONS}" | grep -q 'grpquota' || _notrun "group quota disabled"
 
-echo "Fuzz group 0 dquot"
-_scratch_xfs_fuzz_metadata '' 'online'  "dquot -g 0" >> $seqres.full
-echo "Done fuzzing dquot"
+_scratch_xfs_set_quota_fuzz_ids
+
+for id in "${SCRATCH_XFS_QUOTA_FUZZ_IDS[@]}"; do
+	echo "Fuzz group $id dquot"
+	_scratch_xfs_fuzz_metadata '' 'online'  "dquot -g $id" >> $seqres.full
+	echo "Done fuzzing dquot"
+done
 
 # success, all done
 status=0
diff --git a/tests/xfs/429 b/tests/xfs/429
index a4aeb6e440..5fa3b2ce29 100755
--- a/tests/xfs/429
+++ b/tests/xfs/429
@@ -27,9 +27,13 @@ echo "Format and populate"
 _scratch_populate_cached nofill > $seqres.full 2>&1
 echo "${MOUNT_OPTIONS}" | grep -q 'prjquota' || _notrun "project quota disabled"
 
-echo "Fuzz project 0 dquot"
-_scratch_xfs_fuzz_metadata '' 'offline'  "dquot -p 0" >> $seqres.full
-echo "Done fuzzing dquot"
+_scratch_xfs_set_quota_fuzz_ids
+
+for id in "${SCRATCH_XFS_QUOTA_FUZZ_IDS[@]}"; do
+	echo "Fuzz project $id dquot"
+	_scratch_xfs_fuzz_metadata '' 'offline'  "dquot -p $id" >> $seqres.full
+	echo "Done fuzzing dquot"
+done
 
 # success, all done
 status=0
diff --git a/tests/xfs/430 b/tests/xfs/430
index d94f65bd14..6f5c772dfb 100755
--- a/tests/xfs/430
+++ b/tests/xfs/430
@@ -27,9 +27,13 @@ echo "Format and populate"
 _scratch_populate_cached nofill > $seqres.full 2>&1
 echo "${MOUNT_OPTIONS}" | grep -q 'prjquota' || _notrun "project quota disabled"
 
-echo "Fuzz project 0 dquot"
-_scratch_xfs_fuzz_metadata '' 'online'  "dquot -p 0" >> $seqres.full
-echo "Done fuzzing dquot"
+_scratch_xfs_set_quota_fuzz_ids
+
+for id in "${SCRATCH_XFS_QUOTA_FUZZ_IDS[@]}"; do
+	echo "Fuzz project $id dquot"
+	_scratch_xfs_fuzz_metadata '' 'online'  "dquot -p $id" >> $seqres.full
+	echo "Done fuzzing dquot"
+done
 
 # success, all done
 status=0
diff --git a/tests/xfs/487 b/tests/xfs/487
index 337541bbcd..a688593950 100755
--- a/tests/xfs/487
+++ b/tests/xfs/487
@@ -28,9 +28,13 @@ echo "Format and populate"
 _scratch_populate_cached nofill > $seqres.full 2>&1
 echo "${MOUNT_OPTIONS}" | grep -q 'usrquota' || _notrun "user quota disabled"
 
-echo "Fuzz user 0 dquot"
-_scratch_xfs_fuzz_metadata '' 'none'  "dquot -u 0" >> $seqres.full
-echo "Done fuzzing dquot"
+_scratch_xfs_set_quota_fuzz_ids
+
+for id in "${SCRATCH_XFS_QUOTA_FUZZ_IDS[@]}"; do
+	echo "Fuzz user $id dquot"
+	_scratch_xfs_fuzz_metadata '' 'none'  "dquot -u $id" >> $seqres.full
+	echo "Done fuzzing dquot"
+done
 
 # success, all done
 status=0
diff --git a/tests/xfs/488 b/tests/xfs/488
index 4347768964..0d54ab8c7d 100755
--- a/tests/xfs/488
+++ b/tests/xfs/488
@@ -28,9 +28,13 @@ echo "Format and populate"
 _scratch_populate_cached nofill > $seqres.full 2>&1
 echo "${MOUNT_OPTIONS}" | grep -q 'grpquota' || _notrun "group quota disabled"
 
-echo "Fuzz group 0 dquot"
-_scratch_xfs_fuzz_metadata '' 'none'  "dquot -g 0" >> $seqres.full
-echo "Done fuzzing dquot"
+_scratch_xfs_set_quota_fuzz_ids
+
+for id in "${SCRATCH_XFS_QUOTA_FUZZ_IDS[@]}"; do
+	echo "Fuzz group $id dquot"
+	_scratch_xfs_fuzz_metadata '' 'none'  "dquot -g $id" >> $seqres.full
+	echo "Done fuzzing dquot"
+done
 
 # success, all done
 status=0
diff --git a/tests/xfs/489 b/tests/xfs/489
index c70e674ccc..012416f989 100755
--- a/tests/xfs/489
+++ b/tests/xfs/489
@@ -28,9 +28,13 @@ echo "Format and populate"
 _scratch_populate_cached nofill > $seqres.full 2>&1
 echo "${MOUNT_OPTIONS}" | grep -q 'prjquota' || _notrun "project quota disabled"
 
-echo "Fuzz project 0 dquot"
-_scratch_xfs_fuzz_metadata '' 'none'  "dquot -p 0" >> $seqres.full
-echo "Done fuzzing dquot"
+_scratch_xfs_set_quota_fuzz_ids
+
+for id in "${SCRATCH_XFS_QUOTA_FUZZ_IDS[@]}"; do
+	echo "Fuzz project $id dquot"
+	_scratch_xfs_fuzz_metadata '' 'none'  "dquot -p $id" >> $seqres.full
+	echo "Done fuzzing dquot"
+done
 
 # success, all done
 status=0
diff --git a/tests/xfs/779 b/tests/xfs/779
index fe0de3087a..05f2718632 100755
--- a/tests/xfs/779
+++ b/tests/xfs/779
@@ -29,9 +29,13 @@ echo "Format and populate"
 _scratch_populate_cached nofill > $seqres.full 2>&1
 echo "${MOUNT_OPTIONS}" | grep -q 'usrquota' || _notrun "user quota disabled"
 
-echo "Fuzz user 0 dquot"
-_scratch_xfs_fuzz_metadata '' 'both'  "dquot -u 0" >> $seqres.full
-echo "Done fuzzing dquot"
+_scratch_xfs_set_quota_fuzz_ids
+
+for id in "${SCRATCH_XFS_QUOTA_FUZZ_IDS[@]}"; do
+	echo "Fuzz user $id dquot"
+	_scratch_xfs_fuzz_metadata '' 'both'  "dquot -u $id" >> $seqres.full
+	echo "Done fuzzing dquot"
+done
 
 # success, all done
 status=0
diff --git a/tests/xfs/780 b/tests/xfs/780
index 0a23473538..9dd8f4527e 100755
--- a/tests/xfs/780
+++ b/tests/xfs/780
@@ -29,9 +29,13 @@ echo "Format and populate"
 _scratch_populate_cached nofill > $seqres.full 2>&1
 echo "${MOUNT_OPTIONS}" | grep -q 'grpquota' || _notrun "group quota disabled"
 
-echo "Fuzz group 0 dquot"
-_scratch_xfs_fuzz_metadata '' 'both'  "dquot -g 0" >> $seqres.full
-echo "Done fuzzing dquot"
+_scratch_xfs_set_quota_fuzz_ids
+
+for id in "${SCRATCH_XFS_QUOTA_FUZZ_IDS[@]}"; do
+	echo "Fuzz group $id dquot"
+	_scratch_xfs_fuzz_metadata '' 'both'  "dquot -g $id" >> $seqres.full
+	echo "Done fuzzing dquot"
+done
 
 # success, all done
 status=0
diff --git a/tests/xfs/781 b/tests/xfs/781
index ada0f8a1ca..604c9bdd87 100755
--- a/tests/xfs/781
+++ b/tests/xfs/781
@@ -29,9 +29,13 @@ echo "Format and populate"
 _scratch_populate_cached nofill > $seqres.full 2>&1
 echo "${MOUNT_OPTIONS}" | grep -q 'prjquota' || _notrun "project quota disabled"
 
-echo "Fuzz project 0 dquot"
-_scratch_xfs_fuzz_metadata '' 'both'  "dquot -p 0" >> $seqres.full
-echo "Done fuzzing dquot"
+_scratch_xfs_set_quota_fuzz_ids
+
+for id in "${SCRATCH_XFS_QUOTA_FUZZ_IDS[@]}"; do
+	echo "Fuzz project $id dquot"
+	_scratch_xfs_fuzz_metadata '' 'both'  "dquot -p $id" >> $seqres.full
+	echo "Done fuzzing dquot"
+done
 
 # success, all done
 status=0

[PATCH 1/1] xfs: test scaling of the mkfs concurrency options

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Make sure that the AG count and log size scale up with the new
concurrency options to mkfs.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 tests/xfs/1842     |   51 +++++++++++++++
 tests/xfs/1842.out |  177 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 228 insertions(+)
 create mode 100755 tests/xfs/1842
 create mode 100644 tests/xfs/1842.out


diff --git a/tests/xfs/1842 b/tests/xfs/1842
new file mode 100755
index 0000000000..41254a1581
--- /dev/null
+++ b/tests/xfs/1842
@@ -0,0 +1,51 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2022-2024 Oracle.  All Rights Reserved.
+#
+# FS QA Test No. 1842
+#
+# mkfs concurrency test - ensure the log and agsize scaling works for various
+# concurrency= parameters
+#
+. ./common/preamble
+_begin_fstest log metadata auto quick
+
+# Import common functions.
+. ./common/filter
+. ./common/reflink
+
+_cleanup()
+{
+	cd /
+	rm -r -f $tmp.* $loop_file
+}
+
+# real QA test starts here
+_supported_fs xfs
+
+_require_test
+_require_loop
+$MKFS_XFS_PROG 2>&1 | grep -q concurrency || \
+	_notrun "mkfs does not support concurrency options"
+
+loop_file=$TEST_DIR/$seq.loop
+
+rm -f "$loop_file"
+for sz in 16M 512M 1G 2G 16G 64G 256G 512G 1T 2T 4T 16T 64T 256T 512T 1P; do
+	for cpus in 2 4 8 16 32 40 64 96 160 512; do
+		truncate -s "$sz" "$loop_file"
+		echo "sz $sz cpus $cpus" >> $seqres.full
+		echo "-----------------" >> $seqres.full
+
+		$MKFS_XFS_PROG -f -N "$loop_file" -d concurrency=$cpus -l concurrency=$cpus &> $tmp.mkfsout
+		cat $tmp.mkfsout >> $seqres.full
+
+		_filter_mkfs > /dev/null 2> $tmp.mkfs < $tmp.mkfsout
+		. $tmp.mkfs
+		echo "sz $sz cpus $cpus agcount $agcount logblocks $lblocks"
+	done
+	echo "-----------------"
+done
+
+status=0
+exit
diff --git a/tests/xfs/1842.out b/tests/xfs/1842.out
new file mode 100644
index 0000000000..9d1e22120b
--- /dev/null
+++ b/tests/xfs/1842.out
@@ -0,0 +1,177 @@
+QA output created by 1842
+sz 16M cpus 2 agcount 1 logblocks 3075
+sz 16M cpus 4 agcount 1 logblocks 3075
+sz 16M cpus 8 agcount 1 logblocks 3075
+sz 16M cpus 16 agcount 1 logblocks 3075
+sz 16M cpus 32 agcount 1 logblocks 3075
+sz 16M cpus 40 agcount 1 logblocks 3075
+sz 16M cpus 64 agcount 1 logblocks 3075
+sz 16M cpus 96 agcount 1 logblocks 3075
+sz 16M cpus 160 agcount 1 logblocks 3075
+sz 16M cpus 512 agcount 1 logblocks 3075
+-----------------
+sz 512M cpus 2 agcount 4 logblocks 16384
+sz 512M cpus 4 agcount 4 logblocks 16384
+sz 512M cpus 8 agcount 4 logblocks 16384
+sz 512M cpus 16 agcount 4 logblocks 16384
+sz 512M cpus 32 agcount 4 logblocks 16384
+sz 512M cpus 40 agcount 4 logblocks 16384
+sz 512M cpus 64 agcount 4 logblocks 16384
+sz 512M cpus 96 agcount 4 logblocks 16384
+sz 512M cpus 160 agcount 4 logblocks 16384
+sz 512M cpus 512 agcount 4 logblocks 16384
+-----------------
+sz 1G cpus 2 agcount 4 logblocks 16384
+sz 1G cpus 4 agcount 4 logblocks 16384
+sz 1G cpus 8 agcount 4 logblocks 16384
+sz 1G cpus 16 agcount 4 logblocks 22482
+sz 1G cpus 32 agcount 4 logblocks 44964
+sz 1G cpus 40 agcount 4 logblocks 56205
+sz 1G cpus 64 agcount 4 logblocks 65524
+sz 1G cpus 96 agcount 4 logblocks 65524
+sz 1G cpus 160 agcount 4 logblocks 65524
+sz 1G cpus 512 agcount 4 logblocks 65524
+-----------------
+sz 2G cpus 2 agcount 4 logblocks 16384
+sz 2G cpus 4 agcount 4 logblocks 16384
+sz 2G cpus 8 agcount 4 logblocks 16384
+sz 2G cpus 16 agcount 4 logblocks 25650
+sz 2G cpus 32 agcount 4 logblocks 51300
+sz 2G cpus 40 agcount 4 logblocks 64125
+sz 2G cpus 64 agcount 4 logblocks 102600
+sz 2G cpus 96 agcount 4 logblocks 131060
+sz 2G cpus 160 agcount 4 logblocks 131060
+sz 2G cpus 512 agcount 4 logblocks 131060
+-----------------
+sz 16G cpus 2 agcount 4 logblocks 16384
+sz 16G cpus 4 agcount 4 logblocks 16384
+sz 16G cpus 8 agcount 4 logblocks 16384
+sz 16G cpus 16 agcount 4 logblocks 25650
+sz 16G cpus 32 agcount 4 logblocks 51300
+sz 16G cpus 40 agcount 4 logblocks 64125
+sz 16G cpus 64 agcount 4 logblocks 102600
+sz 16G cpus 96 agcount 4 logblocks 153900
+sz 16G cpus 160 agcount 4 logblocks 256500
+sz 16G cpus 512 agcount 4 logblocks 296512
+-----------------
+sz 64G cpus 2 agcount 4 logblocks 16384
+sz 64G cpus 4 agcount 4 logblocks 16384
+sz 64G cpus 8 agcount 8 logblocks 16384
+sz 64G cpus 16 agcount 16 logblocks 25650
+sz 64G cpus 32 agcount 16 logblocks 51300
+sz 64G cpus 40 agcount 16 logblocks 64125
+sz 64G cpus 64 agcount 16 logblocks 102600
+sz 64G cpus 96 agcount 16 logblocks 153900
+sz 64G cpus 160 agcount 16 logblocks 256500
+sz 64G cpus 512 agcount 16 logblocks 296512
+-----------------
+sz 256G cpus 2 agcount 4 logblocks 32768
+sz 256G cpus 4 agcount 4 logblocks 32768
+sz 256G cpus 8 agcount 8 logblocks 32768
+sz 256G cpus 16 agcount 16 logblocks 32768
+sz 256G cpus 32 agcount 32 logblocks 51300
+sz 256G cpus 40 agcount 40 logblocks 64125
+sz 256G cpus 64 agcount 64 logblocks 102600
+sz 256G cpus 96 agcount 64 logblocks 153900
+sz 256G cpus 160 agcount 64 logblocks 256500
+sz 256G cpus 512 agcount 64 logblocks 296512
+-----------------
+sz 512G cpus 2 agcount 4 logblocks 65536
+sz 512G cpus 4 agcount 4 logblocks 65536
+sz 512G cpus 8 agcount 8 logblocks 65536
+sz 512G cpus 16 agcount 16 logblocks 65536
+sz 512G cpus 32 agcount 32 logblocks 65536
+sz 512G cpus 40 agcount 40 logblocks 65535
+sz 512G cpus 64 agcount 64 logblocks 102600
+sz 512G cpus 96 agcount 96 logblocks 153900
+sz 512G cpus 160 agcount 128 logblocks 256500
+sz 512G cpus 512 agcount 128 logblocks 296512
+-----------------
+sz 1T cpus 2 agcount 4 logblocks 131072
+sz 1T cpus 4 agcount 4 logblocks 131072
+sz 1T cpus 8 agcount 8 logblocks 131072
+sz 1T cpus 16 agcount 16 logblocks 131072
+sz 1T cpus 32 agcount 32 logblocks 131072
+sz 1T cpus 40 agcount 40 logblocks 131071
+sz 1T cpus 64 agcount 64 logblocks 131072
+sz 1T cpus 96 agcount 96 logblocks 153900
+sz 1T cpus 160 agcount 160 logblocks 256500
+sz 1T cpus 512 agcount 256 logblocks 296512
+-----------------
+sz 2T cpus 2 agcount 4 logblocks 262144
+sz 2T cpus 4 agcount 4 logblocks 262144
+sz 2T cpus 8 agcount 8 logblocks 262144
+sz 2T cpus 16 agcount 16 logblocks 262144
+sz 2T cpus 32 agcount 32 logblocks 262144
+sz 2T cpus 40 agcount 40 logblocks 262143
+sz 2T cpus 64 agcount 64 logblocks 262144
+sz 2T cpus 96 agcount 96 logblocks 262143
+sz 2T cpus 160 agcount 160 logblocks 262143
+sz 2T cpus 512 agcount 512 logblocks 296512
+-----------------
+sz 4T cpus 2 agcount 4 logblocks 521728
+sz 4T cpus 4 agcount 4 logblocks 521728
+sz 4T cpus 8 agcount 8 logblocks 521728
+sz 4T cpus 16 agcount 16 logblocks 521728
+sz 4T cpus 32 agcount 32 logblocks 521728
+sz 4T cpus 40 agcount 40 logblocks 521728
+sz 4T cpus 64 agcount 64 logblocks 521728
+sz 4T cpus 96 agcount 96 logblocks 521728
+sz 4T cpus 160 agcount 160 logblocks 521728
+sz 4T cpus 512 agcount 512 logblocks 521728
+-----------------
+sz 16T cpus 2 agcount 16 logblocks 521728
+sz 16T cpus 4 agcount 16 logblocks 521728
+sz 16T cpus 8 agcount 16 logblocks 521728
+sz 16T cpus 16 agcount 16 logblocks 521728
+sz 16T cpus 32 agcount 32 logblocks 521728
+sz 16T cpus 40 agcount 40 logblocks 521728
+sz 16T cpus 64 agcount 64 logblocks 521728
+sz 16T cpus 96 agcount 96 logblocks 521728
+sz 16T cpus 160 agcount 160 logblocks 521728
+sz 16T cpus 512 agcount 512 logblocks 521728
+-----------------
+sz 64T cpus 2 agcount 64 logblocks 521728
+sz 64T cpus 4 agcount 64 logblocks 521728
+sz 64T cpus 8 agcount 64 logblocks 521728
+sz 64T cpus 16 agcount 64 logblocks 521728
+sz 64T cpus 32 agcount 64 logblocks 521728
+sz 64T cpus 40 agcount 64 logblocks 521728
+sz 64T cpus 64 agcount 64 logblocks 521728
+sz 64T cpus 96 agcount 96 logblocks 521728
+sz 64T cpus 160 agcount 160 logblocks 521728
+sz 64T cpus 512 agcount 512 logblocks 521728
+-----------------
+sz 256T cpus 2 agcount 256 logblocks 521728
+sz 256T cpus 4 agcount 256 logblocks 521728
+sz 256T cpus 8 agcount 256 logblocks 521728
+sz 256T cpus 16 agcount 256 logblocks 521728
+sz 256T cpus 32 agcount 256 logblocks 521728
+sz 256T cpus 40 agcount 256 logblocks 521728
+sz 256T cpus 64 agcount 256 logblocks 521728
+sz 256T cpus 96 agcount 256 logblocks 521728
+sz 256T cpus 160 agcount 256 logblocks 521728
+sz 256T cpus 512 agcount 512 logblocks 521728
+-----------------
+sz 512T cpus 2 agcount 512 logblocks 521728
+sz 512T cpus 4 agcount 512 logblocks 521728
+sz 512T cpus 8 agcount 512 logblocks 521728
+sz 512T cpus 16 agcount 512 logblocks 521728
+sz 512T cpus 32 agcount 512 logblocks 521728
+sz 512T cpus 40 agcount 512 logblocks 521728
+sz 512T cpus 64 agcount 512 logblocks 521728
+sz 512T cpus 96 agcount 512 logblocks 521728
+sz 512T cpus 160 agcount 512 logblocks 521728
+sz 512T cpus 512 agcount 512 logblocks 521728
+-----------------
+sz 1P cpus 2 agcount 1024 logblocks 521728
+sz 1P cpus 4 agcount 1024 logblocks 521728
+sz 1P cpus 8 agcount 1024 logblocks 521728
+sz 1P cpus 16 agcount 1024 logblocks 521728
+sz 1P cpus 32 agcount 1024 logblocks 521728
+sz 1P cpus 40 agcount 1024 logblocks 521728
+sz 1P cpus 64 agcount 1024 logblocks 521728
+sz 1P cpus 96 agcount 1024 logblocks 521728
+sz 1P cpus 160 agcount 1024 logblocks 521728
+sz 1P cpus 512 agcount 1024 logblocks 521728
+-----------------

[PATCH 1/4] xfs: online fuzz test known output

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Record all the currently known failures of the xfs_scrub check and
repair code when parent pointers and rtgroups are enabled.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 tests/xfs/351.out |   75 ++++++++++++++++++++++++++++++
 tests/xfs/353.out |   96 +++++++++++++++++++++++++++++++++++++++
 tests/xfs/355.out |   47 +++++++++++++++++++
 tests/xfs/357.out |  109 ++++++++++++++++++++++++++++++++++++++++++++
 tests/xfs/361.out |   14 ++++++
 tests/xfs/369.out |   57 +++++++++++++++++++++++
 tests/xfs/371.out |  108 +++++++++++++++++++++++++++++++++++++++++++
 tests/xfs/375.out |   94 ++++++++++++++++++++++++++++++++++++++
 tests/xfs/377.out |   62 +++++++++++++++++++++++++
 tests/xfs/379.out |   74 ++++++++++++++++++++++++++++++
 tests/xfs/381.out |    1 
 tests/xfs/383.out |    4 ++
 tests/xfs/385.out |   68 +++++++++++++++++++++++++++
 tests/xfs/399.out |   63 +++++++++++++++++++++++++
 tests/xfs/401.out |   72 +++++++++++++++++++++++++++++
 tests/xfs/405.out |    5 ++
 tests/xfs/413.out |   48 +++++++++++++++++++
 tests/xfs/415.out |   56 ++++++++++++++++++++++
 tests/xfs/417.out |   56 ++++++++++++++++++++++
 tests/xfs/426.out |  132 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 tests/xfs/428.out |  132 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 tests/xfs/430.out |  132 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 tests/xfs/730.out |   10 ++++
 23 files changed, 1515 insertions(+)


diff --git a/tests/xfs/351.out b/tests/xfs/351.out
index 36d7b96a11..7f8dbdfebd 100644
--- a/tests/xfs/351.out
+++ b/tests/xfs/351.out
@@ -1,4 +1,79 @@
 QA output created by 351
 Format and populate
 Fuzz superblock
+uuid = zeroes: online scrub didn't fail.
+uuid = ones: online scrub didn't fail.
+uuid = firstbit: online scrub didn't fail.
+uuid = middlebit: online scrub didn't fail.
+uuid = lastbit: online scrub didn't fail.
+rootino = zeroes: online scrub didn't fail.
+rootino = ones: online scrub didn't fail.
+rootino = firstbit: online scrub didn't fail.
+rootino = middlebit: online scrub didn't fail.
+rootino = lastbit: online scrub didn't fail.
+rootino = add: online scrub didn't fail.
+rootino = sub: online scrub didn't fail.
+metadirino = zeroes: online scrub didn't fail.
+metadirino = firstbit: online scrub didn't fail.
+metadirino = middlebit: online scrub didn't fail.
+metadirino = lastbit: online scrub didn't fail.
+metadirino = add: online scrub didn't fail.
+metadirino = sub: online scrub didn't fail.
+rgblocks = middlebit: online scrub didn't fail.
+rgblocks = lastbit: online scrub didn't fail.
+rgblocks = add: online scrub didn't fail.
+rgblocks = sub: online scrub didn't fail.
+fname = ones: online scrub didn't fail.
+fname = firstbit: online scrub didn't fail.
+fname = middlebit: online scrub didn't fail.
+fname = lastbit: online scrub didn't fail.
+inprogress = zeroes: online scrub didn't fail.
+inprogress = ones: online scrub didn't fail.
+inprogress = firstbit: online scrub didn't fail.
+inprogress = middlebit: online scrub didn't fail.
+inprogress = lastbit: online scrub didn't fail.
+inprogress = add: online scrub didn't fail.
+inprogress = sub: online scrub didn't fail.
+imax_pct = zeroes: online scrub didn't fail.
+imax_pct = middlebit: online scrub didn't fail.
+imax_pct = lastbit: online scrub didn't fail.
+icount = ones: online scrub didn't fail.
+icount = firstbit: online scrub didn't fail.
+icount = middlebit: online scrub didn't fail.
+icount = lastbit: online scrub didn't fail.
+icount = add: online scrub didn't fail.
+icount = sub: online scrub didn't fail.
+ifree = ones: online scrub didn't fail.
+ifree = firstbit: online scrub didn't fail.
+ifree = middlebit: online scrub didn't fail.
+ifree = lastbit: online scrub didn't fail.
+ifree = add: online scrub didn't fail.
+ifree = sub: online scrub didn't fail.
+fdblocks = zeroes: online scrub didn't fail.
+fdblocks = ones: online scrub didn't fail.
+fdblocks = firstbit: online scrub didn't fail.
+fdblocks = middlebit: online scrub didn't fail.
+fdblocks = lastbit: online scrub didn't fail.
+fdblocks = add: online scrub didn't fail.
+fdblocks = sub: online scrub didn't fail.
+qflags = firstbit: online scrub didn't fail.
+qflags = middlebit: online scrub didn't fail.
+qflags = lastbit: online scrub didn't fail.
+bad_features2 = zeroes: online scrub didn't fail.
+bad_features2 = ones: online scrub didn't fail.
+bad_features2 = firstbit: online scrub didn't fail.
+bad_features2 = middlebit: online scrub didn't fail.
+bad_features2 = lastbit: online scrub didn't fail.
+bad_features2 = add: online scrub didn't fail.
+bad_features2 = sub: online scrub didn't fail.
+features_log_incompat = ones: online scrub didn't fail.
+features_log_incompat = firstbit: online scrub didn't fail.
+features_log_incompat = middlebit: online scrub didn't fail.
+features_log_incompat = lastbit: online scrub didn't fail.
+features_log_incompat = add: online scrub didn't fail.
+features_log_incompat = sub: online scrub didn't fail.
+meta_uuid = ones: online scrub didn't fail.
+meta_uuid = firstbit: online scrub didn't fail.
+meta_uuid = middlebit: online scrub didn't fail.
+meta_uuid = lastbit: online scrub didn't fail.
 Done fuzzing superblock
diff --git a/tests/xfs/353.out b/tests/xfs/353.out
index 6f0ec45d6e..7c8af7b8e5 100644
--- a/tests/xfs/353.out
+++ b/tests/xfs/353.out
@@ -1,4 +1,100 @@
 QA output created by 353
 Format and populate
 Fuzz AGF
+magicnum = zeroes: mount failed (32).
+magicnum = ones: mount failed (32).
+magicnum = firstbit: mount failed (32).
+magicnum = middlebit: mount failed (32).
+magicnum = lastbit: mount failed (32).
+magicnum = add: mount failed (32).
+magicnum = sub: mount failed (32).
+versionnum = zeroes: mount failed (32).
+versionnum = ones: mount failed (32).
+versionnum = firstbit: mount failed (32).
+versionnum = middlebit: mount failed (32).
+versionnum = lastbit: mount failed (32).
+versionnum = add: mount failed (32).
+versionnum = sub: mount failed (32).
+seqno = ones: mount failed (32).
+seqno = firstbit: mount failed (32).
+seqno = middlebit: mount failed (32).
+seqno = lastbit: mount failed (32).
+seqno = add: mount failed (32).
+seqno = sub: mount failed (32).
+length = zeroes: mount failed (32).
+length = ones: mount failed (32).
+length = firstbit: mount failed (32).
+length = middlebit: mount failed (32).
+length = lastbit: mount failed (32).
+length = add: mount failed (32).
+length = sub: mount failed (32).
+bnolevel = zeroes: mount failed (32).
+bnolevel = ones: mount failed (32).
+bnolevel = firstbit: mount failed (32).
+bnolevel = middlebit: mount failed (32).
+bnolevel = add: mount failed (32).
+bnolevel = sub: mount failed (32).
+cntlevel = zeroes: mount failed (32).
+cntlevel = ones: mount failed (32).
+cntlevel = firstbit: mount failed (32).
+cntlevel = middlebit: mount failed (32).
+cntlevel = add: mount failed (32).
+cntlevel = sub: mount failed (32).
+rmaplevel = zeroes: mount failed (32).
+rmaplevel = ones: mount failed (32).
+rmaplevel = firstbit: mount failed (32).
+rmaplevel = middlebit: mount failed (32).
+rmaplevel = add: mount failed (32).
+rmaplevel = sub: mount failed (32).
+refcntlevel = zeroes: mount failed (32).
+refcntlevel = ones: mount failed (32).
+refcntlevel = firstbit: mount failed (32).
+refcntlevel = middlebit: mount failed (32).
+refcntlevel = add: mount failed (32).
+refcntlevel = sub: mount failed (32).
+rmapblocks = ones: mount failed (32).
+rmapblocks = firstbit: mount failed (32).
+rmapblocks = sub: mount failed (32).
+refcntblocks = ones: mount failed (32).
+refcntblocks = firstbit: mount failed (32).
+refcntblocks = sub: mount failed (32).
+flfirst = ones: mount failed (32).
+flfirst = firstbit: mount failed (32).
+flfirst = middlebit: mount failed (32).
+flfirst = add: mount failed (32).
+flfirst = sub: mount failed (32).
+fllast = ones: mount failed (32).
+fllast = firstbit: mount failed (32).
+fllast = middlebit: mount failed (32).
+fllast = add: mount failed (32).
+fllast = sub: mount failed (32).
+flcount = ones: mount failed (32).
+flcount = firstbit: mount failed (32).
+flcount = middlebit: mount failed (32).
+flcount = add: mount failed (32).
+flcount = sub: mount failed (32).
+freeblks = zeroes: mount failed (32).
+freeblks = ones: mount failed (32).
+freeblks = firstbit: mount failed (32).
+freeblks = middlebit: mount failed (32).
+freeblks = add: mount failed (32).
+freeblks = sub: mount failed (32).
+longest = ones: mount failed (32).
+longest = firstbit: mount failed (32).
+longest = add: mount failed (32).
+btreeblks = ones: mount failed (32).
+btreeblks = firstbit: mount failed (32).
+btreeblks = sub: mount failed (32).
+uuid = zeroes: mount failed (32).
+uuid = ones: mount failed (32).
+uuid = firstbit: mount failed (32).
+uuid = middlebit: mount failed (32).
+uuid = lastbit: mount failed (32).
+crc = zeroes: mount failed (32).
+crc = ones: mount failed (32).
+crc = firstbit: mount failed (32).
+crc = middlebit: mount failed (32).
+crc = lastbit: mount failed (32).
+crc = add: mount failed (32).
+crc = sub: mount failed (32).
 Done fuzzing AGF
diff --git a/tests/xfs/355.out b/tests/xfs/355.out
index d537761abf..1df816c083 100644
--- a/tests/xfs/355.out
+++ b/tests/xfs/355.out
@@ -1,6 +1,53 @@
 QA output created by 355
 Format and populate
 Fuzz AGFL
+bno[0] = zeroes: online scrub didn't fail.
+bno[0] = add: online scrub didn't fail.
+bno[1] = zeroes: online scrub didn't fail.
+bno[1] = ones: online scrub didn't fail.
+bno[1] = middlebit: online scrub didn't fail.
+bno[1] = lastbit: online scrub didn't fail.
+bno[1] = add: online scrub didn't fail.
+bno[2] = zeroes: online scrub didn't fail.
+bno[2] = ones: online scrub didn't fail.
+bno[2] = middlebit: online scrub didn't fail.
+bno[2] = lastbit: online scrub didn't fail.
+bno[2] = add: online scrub didn't fail.
+bno[3] = zeroes: online scrub didn't fail.
+bno[3] = ones: online scrub didn't fail.
+bno[3] = middlebit: online scrub didn't fail.
+bno[3] = lastbit: online scrub didn't fail.
+bno[3] = add: online scrub didn't fail.
+bno[4] = zeroes: online scrub didn't fail.
+bno[4] = ones: online scrub didn't fail.
+bno[4] = middlebit: online scrub didn't fail.
+bno[4] = lastbit: online scrub didn't fail.
+bno[4] = add: online scrub didn't fail.
+bno[5] = zeroes: online scrub didn't fail.
+bno[5] = ones: online scrub didn't fail.
+bno[5] = middlebit: online scrub didn't fail.
+bno[5] = lastbit: online scrub didn't fail.
+bno[5] = add: online scrub didn't fail.
+bno[6] = zeroes: online scrub didn't fail.
+bno[6] = ones: online scrub didn't fail.
+bno[6] = middlebit: online scrub didn't fail.
+bno[6] = lastbit: online scrub didn't fail.
+bno[6] = add: online scrub didn't fail.
+bno[7] = zeroes: online scrub didn't fail.
+bno[7] = ones: online scrub didn't fail.
+bno[7] = middlebit: online scrub didn't fail.
+bno[7] = lastbit: online scrub didn't fail.
+bno[7] = add: online scrub didn't fail.
+bno[8] = zeroes: online scrub didn't fail.
+bno[8] = ones: online scrub didn't fail.
+bno[8] = middlebit: online scrub didn't fail.
+bno[8] = lastbit: online scrub didn't fail.
+bno[8] = add: online scrub didn't fail.
+bno[9] = zeroes: online scrub didn't fail.
+bno[9] = ones: online scrub didn't fail.
+bno[9] = middlebit: online scrub didn't fail.
+bno[9] = lastbit: online scrub didn't fail.
+bno[9] = add: online scrub didn't fail.
 Done fuzzing AGFL
 Fuzz AGFL flfirst
 Done fuzzing AGFL flfirst
diff --git a/tests/xfs/357.out b/tests/xfs/357.out
index c9cf6d2681..400530ff0e 100644
--- a/tests/xfs/357.out
+++ b/tests/xfs/357.out
@@ -1,4 +1,113 @@
 QA output created by 357
 Format and populate
 Fuzz AGI
+magicnum = zeroes: mount failed (32).
+magicnum = ones: mount failed (32).
+magicnum = firstbit: mount failed (32).
+magicnum = middlebit: mount failed (32).
+magicnum = lastbit: mount failed (32).
+magicnum = add: mount failed (32).
+magicnum = sub: mount failed (32).
+versionnum = zeroes: mount failed (32).
+versionnum = ones: mount failed (32).
+versionnum = firstbit: mount failed (32).
+versionnum = middlebit: mount failed (32).
+versionnum = lastbit: mount failed (32).
+versionnum = add: mount failed (32).
+versionnum = sub: mount failed (32).
+seqno = zeroes: mount failed (32).
+seqno = ones: mount failed (32).
+seqno = firstbit: mount failed (32).
+seqno = middlebit: mount failed (32).
+seqno = lastbit: mount failed (32).
+seqno = add: mount failed (32).
+seqno = sub: mount failed (32).
+length = zeroes: mount failed (32).
+length = ones: mount failed (32).
+length = firstbit: mount failed (32).
+length = middlebit: mount failed (32).
+length = lastbit: mount failed (32).
+length = add: mount failed (32).
+length = sub: mount failed (32).
+level = zeroes: mount failed (32).
+level = ones: mount failed (32).
+level = firstbit: mount failed (32).
+level = middlebit: mount failed (32).
+level = lastbit: mount failed (32).
+level = add: mount failed (32).
+level = sub: mount failed (32).
+newino = ones: online scrub didn't fail.
+newino = middlebit: online scrub didn't fail.
+newino = lastbit: online scrub didn't fail.
+newino = add: online scrub didn't fail.
+dirino = add: online scrub didn't fail.
+unlinked[0] = zeroes: mount failed (32).
+unlinked[0] = firstbit: mount failed (32).
+unlinked[0] = middlebit: mount failed (32).
+unlinked[0] = lastbit: mount failed (32).
+unlinked[0] = sub: mount failed (32).
+unlinked[1] = zeroes: mount failed (32).
+unlinked[1] = firstbit: mount failed (32).
+unlinked[1] = middlebit: mount failed (32).
+unlinked[1] = lastbit: mount failed (32).
+unlinked[1] = sub: mount failed (32).
+unlinked[2] = zeroes: mount failed (32).
+unlinked[2] = firstbit: mount failed (32).
+unlinked[2] = middlebit: mount failed (32).
+unlinked[2] = lastbit: mount failed (32).
+unlinked[2] = sub: mount failed (32).
+unlinked[3] = zeroes: mount failed (32).
+unlinked[3] = firstbit: mount failed (32).
+unlinked[3] = middlebit: mount failed (32).
+unlinked[3] = lastbit: mount failed (32).
+unlinked[3] = sub: mount failed (32).
+unlinked[4] = zeroes: mount failed (32).
+unlinked[4] = firstbit: mount failed (32).
+unlinked[4] = middlebit: mount failed (32).
+unlinked[4] = lastbit: mount failed (32).
+unlinked[4] = sub: mount failed (32).
+unlinked[5] = zeroes: mount failed (32).
+unlinked[5] = firstbit: mount failed (32).
+unlinked[5] = middlebit: mount failed (32).
+unlinked[5] = lastbit: mount failed (32).
+unlinked[5] = sub: mount failed (32).
+unlinked[6] = zeroes: mount failed (32).
+unlinked[6] = firstbit: mount failed (32).
+unlinked[6] = middlebit: mount failed (32).
+unlinked[6] = lastbit: mount failed (32).
+unlinked[6] = sub: mount failed (32).
+unlinked[7] = zeroes: mount failed (32).
+unlinked[7] = firstbit: mount failed (32).
+unlinked[7] = middlebit: mount failed (32).
+unlinked[7] = lastbit: mount failed (32).
+unlinked[7] = sub: mount failed (32).
+unlinked[8] = zeroes: mount failed (32).
+unlinked[8] = firstbit: mount failed (32).
+unlinked[8] = middlebit: mount failed (32).
+unlinked[8] = lastbit: mount failed (32).
+unlinked[8] = sub: mount failed (32).
+unlinked[9] = zeroes: mount failed (32).
+unlinked[9] = firstbit: mount failed (32).
+unlinked[9] = middlebit: mount failed (32).
+unlinked[9] = lastbit: mount failed (32).
+unlinked[9] = sub: mount failed (32).
+uuid = zeroes: mount failed (32).
+uuid = ones: mount failed (32).
+uuid = firstbit: mount failed (32).
+uuid = middlebit: mount failed (32).
+uuid = lastbit: mount failed (32).
+crc = zeroes: mount failed (32).
+crc = ones: mount failed (32).
+crc = firstbit: mount failed (32).
+crc = middlebit: mount failed (32).
+crc = lastbit: mount failed (32).
+crc = add: mount failed (32).
+crc = sub: mount failed (32).
+free_level = zeroes: mount failed (32).
+free_level = ones: mount failed (32).
+free_level = firstbit: mount failed (32).
+free_level = middlebit: mount failed (32).
+free_level = lastbit: mount failed (32).
+free_level = add: mount failed (32).
+free_level = sub: mount failed (32).
 Done fuzzing AGI
diff --git a/tests/xfs/361.out b/tests/xfs/361.out
index d8e021bddb..95ae5f5e71 100644
--- a/tests/xfs/361.out
+++ b/tests/xfs/361.out
@@ -1,4 +1,18 @@
 QA output created by 361
 Format and populate
 Fuzz bnobt keyptr
+keys[1].blockcount = zeroes: online scrub didn't fail.
+keys[1].blockcount = ones: online scrub didn't fail.
+keys[1].blockcount = firstbit: online scrub didn't fail.
+keys[1].blockcount = middlebit: online scrub didn't fail.
+keys[1].blockcount = lastbit: online scrub didn't fail.
+keys[1].blockcount = add: online scrub didn't fail.
+keys[1].blockcount = sub: online scrub didn't fail.
+keys[2].blockcount = zeroes: online scrub didn't fail.
+keys[2].blockcount = ones: online scrub didn't fail.
+keys[2].blockcount = firstbit: online scrub didn't fail.
+keys[2].blockcount = middlebit: online scrub didn't fail.
+keys[2].blockcount = lastbit: online scrub didn't fail.
+keys[2].blockcount = add: online scrub didn't fail.
+keys[2].blockcount = sub: online scrub didn't fail.
 Done fuzzing bnobt keyptr
diff --git a/tests/xfs/369.out b/tests/xfs/369.out
index 1f97134ab4..4b399d7b47 100644
--- a/tests/xfs/369.out
+++ b/tests/xfs/369.out
@@ -1,4 +1,61 @@
 QA output created by 369
 Format and populate
 Fuzz rmapbt recs
+recs[2].owner = add: offline re-scrub failed (1).
+recs[2].owner = add: offline post-mod scrub failed (1).
+recs[3].owner = add: offline re-scrub failed (1).
+recs[3].owner = add: offline post-mod scrub failed (1).
+recs[5].owner = lastbit: online repair failed (1).
+recs[5].owner = lastbit: online re-scrub failed (5).
+recs[5].owner = lastbit: offline re-scrub failed (1).
+recs[5].owner = lastbit: online post-mod scrub failed (1).
+recs[5].owner = lastbit: offline post-mod scrub failed (1).
+recs[7].owner = lastbit: offline re-scrub failed (1).
+recs[7].owner = lastbit: offline post-mod scrub failed (1).
+recs[7].owner = add: offline re-scrub failed (1).
+recs[7].owner = add: offline post-mod scrub failed (1).
+recs[7].attrfork = ones: offline re-scrub failed (1).
+recs[7].attrfork = ones: offline post-mod scrub failed (1).
+recs[7].attrfork = firstbit: offline re-scrub failed (1).
+recs[7].attrfork = firstbit: offline post-mod scrub failed (1).
+recs[7].attrfork = middlebit: offline re-scrub failed (1).
+recs[7].attrfork = middlebit: offline post-mod scrub failed (1).
+recs[7].attrfork = lastbit: offline re-scrub failed (1).
+recs[7].attrfork = lastbit: offline post-mod scrub failed (1).
+recs[7].attrfork = add: offline re-scrub failed (1).
+recs[7].attrfork = add: offline post-mod scrub failed (1).
+recs[7].attrfork = sub: offline re-scrub failed (1).
+recs[7].attrfork = sub: offline post-mod scrub failed (1).
+recs[8].owner = lastbit: offline re-scrub failed (1).
+recs[8].owner = lastbit: offline post-mod scrub failed (1).
+recs[8].owner = add: offline re-scrub failed (1).
+recs[8].owner = add: offline post-mod scrub failed (1).
+recs[8].attrfork = ones: offline re-scrub failed (1).
+recs[8].attrfork = ones: offline post-mod scrub failed (1).
+recs[8].attrfork = firstbit: offline re-scrub failed (1).
+recs[8].attrfork = firstbit: offline post-mod scrub failed (1).
+recs[8].attrfork = middlebit: offline re-scrub failed (1).
+recs[8].attrfork = middlebit: offline post-mod scrub failed (1).
+recs[8].attrfork = lastbit: offline re-scrub failed (1).
+recs[8].attrfork = lastbit: offline post-mod scrub failed (1).
+recs[8].attrfork = add: offline re-scrub failed (1).
+recs[8].attrfork = add: offline post-mod scrub failed (1).
+recs[8].attrfork = sub: offline re-scrub failed (1).
+recs[8].attrfork = sub: offline post-mod scrub failed (1).
+recs[9].owner = lastbit: offline re-scrub failed (1).
+recs[9].owner = lastbit: offline post-mod scrub failed (1).
+recs[9].owner = add: offline re-scrub failed (1).
+recs[9].owner = add: offline post-mod scrub failed (1).
+recs[9].attrfork = ones: offline re-scrub failed (1).
+recs[9].attrfork = ones: offline post-mod scrub failed (1).
+recs[9].attrfork = firstbit: offline re-scrub failed (1).
+recs[9].attrfork = firstbit: offline post-mod scrub failed (1).
+recs[9].attrfork = middlebit: offline re-scrub failed (1).
+recs[9].attrfork = middlebit: offline post-mod scrub failed (1).
+recs[9].attrfork = lastbit: offline re-scrub failed (1).
+recs[9].attrfork = lastbit: offline post-mod scrub failed (1).
+recs[9].attrfork = add: offline re-scrub failed (1).
+recs[9].attrfork = add: offline post-mod scrub failed (1).
+recs[9].attrfork = sub: offline re-scrub failed (1).
+recs[9].attrfork = sub: offline post-mod scrub failed (1).
 Done fuzzing rmapbt recs
diff --git a/tests/xfs/371.out b/tests/xfs/371.out
index c7c943f332..477cd32e51 100644
--- a/tests/xfs/371.out
+++ b/tests/xfs/371.out
@@ -1,4 +1,112 @@
 QA output created by 371
 Format and populate
 Fuzz rmapbt keyptr
+keys[1].extentflag = ones: online scrub didn't fail.
+keys[1].extentflag = firstbit: online scrub didn't fail.
+keys[1].extentflag = middlebit: online scrub didn't fail.
+keys[1].extentflag = lastbit: online scrub didn't fail.
+keys[1].extentflag = add: online scrub didn't fail.
+keys[1].extentflag = sub: online scrub didn't fail.
+keys[1].extentflag_hi = ones: online scrub didn't fail.
+keys[1].extentflag_hi = firstbit: online scrub didn't fail.
+keys[1].extentflag_hi = middlebit: online scrub didn't fail.
+keys[1].extentflag_hi = lastbit: online scrub didn't fail.
+keys[1].extentflag_hi = add: online scrub didn't fail.
+keys[1].extentflag_hi = sub: online scrub didn't fail.
+keys[2].extentflag = ones: online scrub didn't fail.
+keys[2].extentflag = firstbit: online scrub didn't fail.
+keys[2].extentflag = middlebit: online scrub didn't fail.
+keys[2].extentflag = lastbit: online scrub didn't fail.
+keys[2].extentflag = add: online scrub didn't fail.
+keys[2].extentflag = sub: online scrub didn't fail.
+keys[2].extentflag_hi = ones: online scrub didn't fail.
+keys[2].extentflag_hi = firstbit: online scrub didn't fail.
+keys[2].extentflag_hi = middlebit: online scrub didn't fail.
+keys[2].extentflag_hi = lastbit: online scrub didn't fail.
+keys[2].extentflag_hi = add: online scrub didn't fail.
+keys[2].extentflag_hi = sub: online scrub didn't fail.
+keys[3].extentflag = ones: online scrub didn't fail.
+keys[3].extentflag = firstbit: online scrub didn't fail.
+keys[3].extentflag = middlebit: online scrub didn't fail.
+keys[3].extentflag = lastbit: online scrub didn't fail.
+keys[3].extentflag = add: online scrub didn't fail.
+keys[3].extentflag = sub: online scrub didn't fail.
+keys[3].extentflag_hi = ones: online scrub didn't fail.
+keys[3].extentflag_hi = firstbit: online scrub didn't fail.
+keys[3].extentflag_hi = middlebit: online scrub didn't fail.
+keys[3].extentflag_hi = lastbit: online scrub didn't fail.
+keys[3].extentflag_hi = add: online scrub didn't fail.
+keys[3].extentflag_hi = sub: online scrub didn't fail.
+keys[4].extentflag = ones: online scrub didn't fail.
+keys[4].extentflag = firstbit: online scrub didn't fail.
+keys[4].extentflag = middlebit: online scrub didn't fail.
+keys[4].extentflag = lastbit: online scrub didn't fail.
+keys[4].extentflag = add: online scrub didn't fail.
+keys[4].extentflag = sub: online scrub didn't fail.
+keys[4].extentflag_hi = ones: online scrub didn't fail.
+keys[4].extentflag_hi = firstbit: online scrub didn't fail.
+keys[4].extentflag_hi = middlebit: online scrub didn't fail.
+keys[4].extentflag_hi = lastbit: online scrub didn't fail.
+keys[4].extentflag_hi = add: online scrub didn't fail.
+keys[4].extentflag_hi = sub: online scrub didn't fail.
+keys[5].extentflag = ones: online scrub didn't fail.
+keys[5].extentflag = firstbit: online scrub didn't fail.
+keys[5].extentflag = middlebit: online scrub didn't fail.
+keys[5].extentflag = lastbit: online scrub didn't fail.
+keys[5].extentflag = add: online scrub didn't fail.
+keys[5].extentflag = sub: online scrub didn't fail.
+keys[5].extentflag_hi = ones: online scrub didn't fail.
+keys[5].extentflag_hi = firstbit: online scrub didn't fail.
+keys[5].extentflag_hi = middlebit: online scrub didn't fail.
+keys[5].extentflag_hi = lastbit: online scrub didn't fail.
+keys[5].extentflag_hi = add: online scrub didn't fail.
+keys[5].extentflag_hi = sub: online scrub didn't fail.
+keys[6].extentflag = ones: online scrub didn't fail.
+keys[6].extentflag = firstbit: online scrub didn't fail.
+keys[6].extentflag = middlebit: online scrub didn't fail.
+keys[6].extentflag = lastbit: online scrub didn't fail.
+keys[6].extentflag = add: online scrub didn't fail.
+keys[6].extentflag = sub: online scrub didn't fail.
+keys[6].extentflag_hi = ones: online scrub didn't fail.
+keys[6].extentflag_hi = firstbit: online scrub didn't fail.
+keys[6].extentflag_hi = middlebit: online scrub didn't fail.
+keys[6].extentflag_hi = lastbit: online scrub didn't fail.
+keys[6].extentflag_hi = add: online scrub didn't fail.
+keys[6].extentflag_hi = sub: online scrub didn't fail.
+keys[7].extentflag = ones: online scrub didn't fail.
+keys[7].extentflag = firstbit: online scrub didn't fail.
+keys[7].extentflag = middlebit: online scrub didn't fail.
+keys[7].extentflag = lastbit: online scrub didn't fail.
+keys[7].extentflag = add: online scrub didn't fail.
+keys[7].extentflag = sub: online scrub didn't fail.
+keys[7].extentflag_hi = ones: online scrub didn't fail.
+keys[7].extentflag_hi = firstbit: online scrub didn't fail.
+keys[7].extentflag_hi = middlebit: online scrub didn't fail.
+keys[7].extentflag_hi = lastbit: online scrub didn't fail.
+keys[7].extentflag_hi = add: online scrub didn't fail.
+keys[7].extentflag_hi = sub: online scrub didn't fail.
+keys[8].extentflag = ones: online scrub didn't fail.
+keys[8].extentflag = firstbit: online scrub didn't fail.
+keys[8].extentflag = middlebit: online scrub didn't fail.
+keys[8].extentflag = lastbit: online scrub didn't fail.
+keys[8].extentflag = add: online scrub didn't fail.
+keys[8].extentflag = sub: online scrub didn't fail.
+keys[8].extentflag_hi = ones: online scrub didn't fail.
+keys[8].extentflag_hi = firstbit: online scrub didn't fail.
+keys[8].extentflag_hi = middlebit: online scrub didn't fail.
+keys[8].extentflag_hi = lastbit: online scrub didn't fail.
+keys[8].extentflag_hi = add: online scrub didn't fail.
+keys[8].extentflag_hi = sub: online scrub didn't fail.
+keys[9].extentflag = ones: online scrub didn't fail.
+keys[9].extentflag = firstbit: online scrub didn't fail.
+keys[9].extentflag = middlebit: online scrub didn't fail.
+keys[9].extentflag = lastbit: online scrub didn't fail.
+keys[9].extentflag = add: online scrub didn't fail.
+keys[9].extentflag = sub: online scrub didn't fail.
+keys[9].extentflag_hi = ones: online scrub didn't fail.
+keys[9].extentflag_hi = firstbit: online scrub didn't fail.
+keys[9].extentflag_hi = middlebit: online scrub didn't fail.
+keys[9].extentflag_hi = lastbit: online scrub didn't fail.
+keys[9].extentflag_hi = add: online scrub didn't fail.
+keys[9].extentflag_hi = sub: online scrub didn't fail.
 Done fuzzing rmapbt keyptr
diff --git a/tests/xfs/375.out b/tests/xfs/375.out
index ea92d7087f..746fa31ea0 100644
--- a/tests/xfs/375.out
+++ b/tests/xfs/375.out
@@ -2,4 +2,98 @@ QA output created by 375
 Format and populate
 Find btree-format dir inode
 Fuzz inode
+core.mode = zeroes: offline re-scrub failed (1).
+core.mode = zeroes: offline post-mod scrub failed (1).
+core.mode = firstbit: online repair failed (1).
+core.mode = firstbit: online re-scrub failed (5).
+core.mode = firstbit: offline re-scrub failed (1).
+core.mode = firstbit: online post-mod scrub failed (1).
+core.mode = firstbit: offline post-mod scrub failed (1).
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.uid = ones: online re-scrub failed (1).
+core.gid = ones: online re-scrub failed (1).
+core.nlinkv2 = zeroes: online repair failed (4).
+core.nlinkv2 = zeroes: online re-scrub failed (4).
+core.nlinkv2 = zeroes: offline re-scrub failed (1).
+core.nlinkv2 = zeroes: online post-mod scrub failed (1).
+core.nlinkv2 = zeroes: offline post-mod scrub failed (1).
+core.size = zeroes: online repair failed (1).
+core.size = zeroes: online re-scrub failed (5).
+core.size = zeroes: offline re-scrub failed (1).
+core.size = zeroes: online post-mod scrub failed (1).
+core.size = zeroes: offline post-mod scrub failed (1).
+core.size = middlebit: online health check failed (0).
+core.size = middlebit: online repair failed (4).
+core.size = middlebit: online re-scrub failed (4).
+core.size = middlebit: online post-mod scrub failed (4).
+core.size = lastbit: online scrub didn't fail.
+core.size = add: online scrub didn't fail.
+core.size = sub: online scrub didn't fail.
+core.naextents = lastbit: online repair failed (1).
+core.naextents = lastbit: online re-scrub failed (5).
+core.naextents = lastbit: offline re-scrub failed (1).
+core.naextents = lastbit: online post-mod scrub failed (1).
+core.naextents = lastbit: offline post-mod scrub failed (1).
+core.forkoff = ones: online repair failed (1).
+core.forkoff = ones: online re-scrub failed (5).
+core.forkoff = ones: offline re-scrub failed (1).
+core.forkoff = ones: online post-mod scrub failed (1).
+core.forkoff = ones: offline post-mod scrub failed (1).
+core.forkoff = firstbit: online repair failed (1).
+core.forkoff = firstbit: online re-scrub failed (5).
+core.forkoff = firstbit: offline re-scrub failed (1).
+core.forkoff = firstbit: online post-mod scrub failed (1).
+core.forkoff = firstbit: offline post-mod scrub failed (1).
+core.forkoff = add: online repair failed (1).
+core.forkoff = add: online re-scrub failed (5).
+core.forkoff = add: offline re-scrub failed (1).
+core.forkoff = add: online post-mod scrub failed (1).
+core.forkoff = add: offline post-mod scrub failed (1).
+core.forkoff = sub: online repair failed (1).
+core.forkoff = sub: online re-scrub failed (5).
+core.forkoff = sub: offline re-scrub failed (1).
+core.forkoff = sub: online post-mod scrub failed (1).
+core.forkoff = sub: offline post-mod scrub failed (1).
+core.rtinherit = ones: online scrub didn't fail.
+core.rtinherit = firstbit: online scrub didn't fail.
+core.rtinherit = middlebit: online scrub didn't fail.
+core.rtinherit = lastbit: online scrub didn't fail.
+core.rtinherit = add: online scrub didn't fail.
+core.rtinherit = sub: online scrub didn't fail.
+core.projinherit = ones: online scrub didn't fail.
+core.projinherit = firstbit: online scrub didn't fail.
+core.projinherit = middlebit: online scrub didn't fail.
+core.projinherit = lastbit: online scrub didn't fail.
+core.projinherit = add: online scrub didn't fail.
+core.projinherit = sub: online scrub didn't fail.
+core.nosymlinks = ones: online scrub didn't fail.
+core.nosymlinks = firstbit: online scrub didn't fail.
+core.nosymlinks = middlebit: online scrub didn't fail.
+core.nosymlinks = lastbit: online scrub didn't fail.
+core.nosymlinks = add: online scrub didn't fail.
+core.nosymlinks = sub: online scrub didn't fail.
+next_unlinked = add: online scrub didn't fail.
+next_unlinked = add: offline re-scrub failed (1).
+next_unlinked = add: offline post-mod scrub failed (1).
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = ones: offline re-scrub failed (1).
+v3.flags2 = ones: offline post-mod scrub failed (1).
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.flags2 = middlebit: offline re-scrub failed (1).
+v3.flags2 = middlebit: offline post-mod scrub failed (1).
+v3.flags2 = lastbit: online scrub didn't fail.
+v3.flags2 = add: online scrub didn't fail.
+v3.flags2 = add: offline re-scrub failed (1).
+v3.flags2 = add: offline post-mod scrub failed (1).
+v3.flags2 = sub: offline re-scrub failed (1).
+v3.flags2 = sub: offline post-mod scrub failed (1).
+u3.bmbt.ptrs[1] = firstbit: online scrub didn't fail.
 Done fuzzing inode
diff --git a/tests/xfs/377.out b/tests/xfs/377.out
index e70a34fd17..acc01a4669 100644
--- a/tests/xfs/377.out
+++ b/tests/xfs/377.out
@@ -2,4 +2,66 @@ QA output created by 377
 Format and populate
 Find extents-format file inode
 Fuzz inode
+core.mode = zeroes: offline re-scrub failed (1).
+core.mode = zeroes: offline post-mod scrub failed (1).
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.uid = ones: online re-scrub failed (1).
+core.gid = ones: online re-scrub failed (1).
+core.nlinkv2 = zeroes: online repair failed (4).
+core.nlinkv2 = zeroes: online re-scrub failed (4).
+core.nlinkv2 = zeroes: offline re-scrub failed (1).
+core.nlinkv2 = zeroes: online post-mod scrub failed (4).
+core.nlinkv2 = zeroes: offline post-mod scrub failed (1).
+core.nlinkv2 = lastbit: online repair failed (4).
+core.nlinkv2 = lastbit: online re-scrub failed (4).
+core.nlinkv2 = lastbit: offline re-scrub failed (1).
+core.nlinkv2 = lastbit: online post-mod scrub failed (4).
+core.nlinkv2 = lastbit: offline post-mod scrub failed (1).
+core.size = zeroes: online scrub didn't fail.
+core.size = middlebit: online scrub didn't fail.
+core.size = lastbit: online scrub didn't fail.
+core.size = add: online scrub didn't fail.
+core.size = sub: online scrub didn't fail.
+core.forkoff = firstbit: online repair failed (1).
+core.forkoff = firstbit: online re-scrub failed (5).
+core.forkoff = firstbit: offline re-scrub failed (1).
+core.forkoff = firstbit: online post-mod scrub failed (1).
+core.forkoff = firstbit: offline post-mod scrub failed (1).
+next_unlinked = add: online scrub didn't fail.
+next_unlinked = add: offline re-scrub failed (1).
+next_unlinked = add: offline post-mod scrub failed (1).
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = ones: offline re-scrub failed (1).
+v3.flags2 = ones: offline post-mod scrub failed (1).
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.flags2 = middlebit: offline re-scrub failed (1).
+v3.flags2 = middlebit: offline post-mod scrub failed (1).
+v3.flags2 = lastbit: online scrub didn't fail.
+v3.flags2 = add: online scrub didn't fail.
+v3.flags2 = add: offline re-scrub failed (1).
+v3.flags2 = add: offline post-mod scrub failed (1).
+v3.flags2 = sub: offline re-scrub failed (1).
+v3.flags2 = sub: offline post-mod scrub failed (1).
+v3.reflink = ones: online scrub didn't fail.
+v3.reflink = firstbit: online scrub didn't fail.
+v3.reflink = middlebit: online scrub didn't fail.
+v3.reflink = lastbit: online scrub didn't fail.
+v3.reflink = add: online scrub didn't fail.
+v3.reflink = sub: online scrub didn't fail.
+u3.bmx[0].blockcount = middlebit: online repair failed (4).
+u3.bmx[0].blockcount = middlebit: online re-scrub failed (4).
+u3.bmx[0].blockcount = middlebit: offline re-scrub failed (1).
+u3.bmx[0].blockcount = middlebit: pre-mod mount failed (32).
+u3.bmx[0].blockcount = add: online repair failed (4).
+u3.bmx[0].blockcount = add: online re-scrub failed (4).
+u3.bmx[0].blockcount = add: offline re-scrub failed (1).
+u3.bmx[0].blockcount = add: pre-mod mount failed (32).
 Done fuzzing inode
diff --git a/tests/xfs/379.out b/tests/xfs/379.out
index 308b193490..2b856af2f4 100644
--- a/tests/xfs/379.out
+++ b/tests/xfs/379.out
@@ -2,4 +2,78 @@ QA output created by 379
 Format and populate
 Find btree-format file inode
 Fuzz inode
+core.mode = zeroes: offline re-scrub failed (1).
+core.mode = zeroes: offline post-mod scrub failed (1).
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.uid = ones: online re-scrub failed (1).
+core.gid = ones: online re-scrub failed (1).
+core.nlinkv2 = zeroes: online repair failed (4).
+core.nlinkv2 = zeroes: online re-scrub failed (4).
+core.nlinkv2 = zeroes: offline re-scrub failed (1).
+core.nlinkv2 = zeroes: online post-mod scrub failed (4).
+core.nlinkv2 = zeroes: offline post-mod scrub failed (1).
+core.nlinkv2 = lastbit: online repair failed (4).
+core.nlinkv2 = lastbit: online re-scrub failed (4).
+core.nlinkv2 = lastbit: offline re-scrub failed (1).
+core.nlinkv2 = lastbit: online post-mod scrub failed (4).
+core.nlinkv2 = lastbit: offline post-mod scrub failed (1).
+core.size = zeroes: online scrub didn't fail.
+core.size = middlebit: online scrub didn't fail.
+core.size = lastbit: online scrub didn't fail.
+core.size = add: online scrub didn't fail.
+core.size = sub: online scrub didn't fail.
+core.naextents = lastbit: online repair failed (1).
+core.naextents = lastbit: online re-scrub failed (5).
+core.naextents = lastbit: offline re-scrub failed (1).
+core.naextents = lastbit: online post-mod scrub failed (1).
+core.naextents = lastbit: offline post-mod scrub failed (1).
+core.forkoff = ones: online repair failed (1).
+core.forkoff = ones: online re-scrub failed (5).
+core.forkoff = ones: offline re-scrub failed (1).
+core.forkoff = ones: online post-mod scrub failed (1).
+core.forkoff = ones: offline post-mod scrub failed (1).
+core.forkoff = firstbit: online repair failed (1).
+core.forkoff = firstbit: online re-scrub failed (5).
+core.forkoff = firstbit: offline re-scrub failed (1).
+core.forkoff = firstbit: online post-mod scrub failed (1).
+core.forkoff = firstbit: offline post-mod scrub failed (1).
+core.forkoff = add: online repair failed (1).
+core.forkoff = add: online re-scrub failed (5).
+core.forkoff = add: offline re-scrub failed (1).
+core.forkoff = add: online post-mod scrub failed (1).
+core.forkoff = add: offline post-mod scrub failed (1).
+core.forkoff = sub: online repair failed (1).
+core.forkoff = sub: online re-scrub failed (5).
+core.forkoff = sub: offline re-scrub failed (1).
+core.forkoff = sub: online post-mod scrub failed (1).
+core.forkoff = sub: offline post-mod scrub failed (1).
+next_unlinked = add: online scrub didn't fail.
+next_unlinked = add: offline re-scrub failed (1).
+next_unlinked = add: offline post-mod scrub failed (1).
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = ones: offline re-scrub failed (1).
+v3.flags2 = ones: offline post-mod scrub failed (1).
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.flags2 = middlebit: offline re-scrub failed (1).
+v3.flags2 = middlebit: offline post-mod scrub failed (1).
+v3.flags2 = lastbit: online scrub didn't fail.
+v3.flags2 = add: online scrub didn't fail.
+v3.flags2 = add: offline re-scrub failed (1).
+v3.flags2 = add: offline post-mod scrub failed (1).
+v3.flags2 = sub: offline re-scrub failed (1).
+v3.flags2 = sub: offline post-mod scrub failed (1).
+v3.reflink = ones: online scrub didn't fail.
+v3.reflink = firstbit: online scrub didn't fail.
+v3.reflink = middlebit: online scrub didn't fail.
+v3.reflink = lastbit: online scrub didn't fail.
+v3.reflink = add: online scrub didn't fail.
+v3.reflink = sub: online scrub didn't fail.
 Done fuzzing inode
diff --git a/tests/xfs/381.out b/tests/xfs/381.out
index 217b15e325..4141e66342 100644
--- a/tests/xfs/381.out
+++ b/tests/xfs/381.out
@@ -2,4 +2,5 @@ QA output created by 381
 Format and populate
 Find bmbt block
 Fuzz bmbt
+rightsib = lastbit: online re-scrub failed (5).
 Done fuzzing bmbt
diff --git a/tests/xfs/383.out b/tests/xfs/383.out
index 69e2bca491..b124a4e2a9 100644
--- a/tests/xfs/383.out
+++ b/tests/xfs/383.out
@@ -2,4 +2,8 @@ QA output created by 383
 Format and populate
 Find symlink remote block
 Fuzz symlink remote block
+data = ones: online scrub didn't fail.
+data = firstbit: online scrub didn't fail.
+data = middlebit: online scrub didn't fail.
+data = lastbit: online scrub didn't fail.
 Done fuzzing symlink remote block
diff --git a/tests/xfs/385.out b/tests/xfs/385.out
index e2b6bffd90..02dd1d5085 100644
--- a/tests/xfs/385.out
+++ b/tests/xfs/385.out
@@ -2,4 +2,72 @@ QA output created by 385
 Format and populate
 Find inline-format dir inode
 Fuzz inline-format dir inode
+core.mode = firstbit: online repair failed (1).
+core.mode = firstbit: online re-scrub failed (5).
+core.mode = firstbit: offline re-scrub failed (1).
+core.mode = firstbit: online post-mod scrub failed (1).
+core.mode = firstbit: offline post-mod scrub failed (1).
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.uid = ones: online re-scrub failed (1).
+core.gid = ones: online re-scrub failed (1).
+core.nlinkv2 = zeroes: online repair failed (4).
+core.nlinkv2 = zeroes: online re-scrub failed (4).
+core.nlinkv2 = zeroes: offline re-scrub failed (1).
+core.nlinkv2 = zeroes: online post-mod scrub failed (4).
+core.nlinkv2 = zeroes: offline post-mod scrub failed (1).
+core.forkoff = firstbit: online repair failed (1).
+core.forkoff = firstbit: online re-scrub failed (5).
+core.forkoff = firstbit: offline re-scrub failed (1).
+core.forkoff = firstbit: online post-mod scrub failed (1).
+core.forkoff = firstbit: offline post-mod scrub failed (1).
+core.rtinherit = ones: online scrub didn't fail.
+core.rtinherit = firstbit: online scrub didn't fail.
+core.rtinherit = middlebit: online scrub didn't fail.
+core.rtinherit = lastbit: online scrub didn't fail.
+core.rtinherit = add: online scrub didn't fail.
+core.rtinherit = sub: online scrub didn't fail.
+core.projinherit = ones: online scrub didn't fail.
+core.projinherit = firstbit: online scrub didn't fail.
+core.projinherit = middlebit: online scrub didn't fail.
+core.projinherit = lastbit: online scrub didn't fail.
+core.projinherit = add: online scrub didn't fail.
+core.projinherit = sub: online scrub didn't fail.
+core.nosymlinks = ones: online scrub didn't fail.
+core.nosymlinks = firstbit: online scrub didn't fail.
+core.nosymlinks = middlebit: online scrub didn't fail.
+core.nosymlinks = lastbit: online scrub didn't fail.
+core.nosymlinks = add: online scrub didn't fail.
+core.nosymlinks = sub: online scrub didn't fail.
+next_unlinked = add: online scrub didn't fail.
+next_unlinked = add: offline re-scrub failed (1).
+next_unlinked = add: offline post-mod scrub failed (1).
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = ones: offline re-scrub failed (1).
+v3.flags2 = ones: offline post-mod scrub failed (1).
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.flags2 = middlebit: offline re-scrub failed (1).
+v3.flags2 = middlebit: offline post-mod scrub failed (1).
+v3.flags2 = lastbit: online scrub didn't fail.
+v3.flags2 = add: online scrub didn't fail.
+v3.flags2 = add: offline re-scrub failed (1).
+v3.flags2 = add: offline post-mod scrub failed (1).
+v3.flags2 = sub: offline re-scrub failed (1).
+v3.flags2 = sub: offline post-mod scrub failed (1).
+v3.nrext64 = zeroes: online scrub didn't fail.
+v3.nrext64 = firstbit: online scrub didn't fail.
+v3.nrext64 = middlebit: online scrub didn't fail.
+v3.nrext64 = lastbit: online scrub didn't fail.
+v3.nrext64 = add: online scrub didn't fail.
+v3.nrext64 = sub: online scrub didn't fail.
+u3.sfdir3.list[1].offset = middlebit: online scrub didn't fail.
+u3.sfdir3.list[1].offset = lastbit: online scrub didn't fail.
+u3.sfdir3.list[1].offset = add: online scrub didn't fail.
 Done fuzzing inline-format dir inode
diff --git a/tests/xfs/399.out b/tests/xfs/399.out
index 229bcc0353..8379781def 100644
--- a/tests/xfs/399.out
+++ b/tests/xfs/399.out
@@ -2,4 +2,67 @@ QA output created by 399
 Format and populate
 Find inline-format attr inode
 Fuzz inline-format attr inode
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.uid = ones: online re-scrub failed (1).
+core.gid = ones: online re-scrub failed (1).
+core.nlinkv2 = zeroes: online repair failed (4).
+core.nlinkv2 = zeroes: online re-scrub failed (4).
+core.nlinkv2 = zeroes: offline re-scrub failed (1).
+core.nlinkv2 = zeroes: online post-mod scrub failed (4).
+core.nlinkv2 = zeroes: offline post-mod scrub failed (1).
+core.nlinkv2 = lastbit: online repair failed (4).
+core.nlinkv2 = lastbit: online re-scrub failed (4).
+core.nlinkv2 = lastbit: offline re-scrub failed (1).
+core.nlinkv2 = lastbit: online post-mod scrub failed (4).
+core.nlinkv2 = lastbit: offline post-mod scrub failed (1).
+core.size = middlebit: online scrub didn't fail.
+core.size = lastbit: online scrub didn't fail.
+core.size = add: online scrub didn't fail.
+next_unlinked = add: online scrub didn't fail.
+next_unlinked = add: offline re-scrub failed (1).
+next_unlinked = add: offline post-mod scrub failed (1).
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = ones: offline re-scrub failed (1).
+v3.flags2 = ones: offline post-mod scrub failed (1).
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.flags2 = middlebit: offline re-scrub failed (1).
+v3.flags2 = middlebit: offline post-mod scrub failed (1).
+v3.flags2 = lastbit: online scrub didn't fail.
+v3.flags2 = add: online scrub didn't fail.
+v3.flags2 = add: offline re-scrub failed (1).
+v3.flags2 = add: offline post-mod scrub failed (1).
+v3.flags2 = sub: offline re-scrub failed (1).
+v3.flags2 = sub: offline post-mod scrub failed (1).
+v3.reflink = ones: online scrub didn't fail.
+v3.reflink = firstbit: online scrub didn't fail.
+v3.reflink = middlebit: online scrub didn't fail.
+v3.reflink = lastbit: online scrub didn't fail.
+v3.reflink = add: online scrub didn't fail.
+v3.reflink = sub: online scrub didn't fail.
+v3.nrext64 = zeroes: online scrub didn't fail.
+v3.nrext64 = firstbit: online scrub didn't fail.
+v3.nrext64 = middlebit: online scrub didn't fail.
+v3.nrext64 = lastbit: online scrub didn't fail.
+v3.nrext64 = add: online scrub didn't fail.
+v3.nrext64 = sub: online scrub didn't fail.
+a.sfattr.list[1].name = ones: online scrub didn't fail.
+a.sfattr.list[1].name = firstbit: online scrub didn't fail.
+a.sfattr.list[1].name = middlebit: online scrub didn't fail.
+a.sfattr.list[1].name = lastbit: online scrub didn't fail.
+a.sfattr.list[1].name = add: online scrub didn't fail.
+a.sfattr.list[1].name = sub: online scrub didn't fail.
+a.sfattr.list[2].name = ones: online scrub didn't fail.
+a.sfattr.list[2].name = firstbit: online scrub didn't fail.
+a.sfattr.list[2].name = middlebit: online scrub didn't fail.
+a.sfattr.list[2].name = lastbit: online scrub didn't fail.
+a.sfattr.list[2].name = add: online scrub didn't fail.
+a.sfattr.list[2].name = sub: online scrub didn't fail.
 Done fuzzing inline-format attr inode
diff --git a/tests/xfs/401.out b/tests/xfs/401.out
index 2729f3eafb..3102736cff 100644
--- a/tests/xfs/401.out
+++ b/tests/xfs/401.out
@@ -2,4 +2,76 @@ QA output created by 401
 Format and populate
 Find leaf-format attr block
 Fuzz leaf-format attr block
+hdr.firstused = middlebit: online scrub didn't fail.
+hdr.firstused = middlebit: offline re-scrub failed (1).
+hdr.firstused = middlebit: offline post-mod scrub failed (1).
+hdr.holes = ones: online scrub didn't fail.
+hdr.holes = firstbit: online scrub didn't fail.
+hdr.holes = middlebit: online scrub didn't fail.
+hdr.holes = lastbit: online scrub didn't fail.
+hdr.holes = add: online scrub didn't fail.
+hdr.holes = sub: online scrub didn't fail.
+hdr.freemap[0].size = zeroes: online scrub didn't fail.
+hdr.freemap[1].base = middlebit: online scrub didn't fail.
+hdr.freemap[2].base = middlebit: online scrub didn't fail.
+entries[0].incomplete = ones: online scrub didn't fail.
+entries[0].incomplete = firstbit: online scrub didn't fail.
+entries[0].incomplete = middlebit: online scrub didn't fail.
+entries[0].incomplete = lastbit: online scrub didn't fail.
+entries[0].incomplete = add: online scrub didn't fail.
+entries[0].incomplete = sub: online scrub didn't fail.
+entries[1].incomplete = ones: online scrub didn't fail.
+entries[1].incomplete = firstbit: online scrub didn't fail.
+entries[1].incomplete = middlebit: online scrub didn't fail.
+entries[1].incomplete = lastbit: online scrub didn't fail.
+entries[1].incomplete = add: online scrub didn't fail.
+entries[1].incomplete = sub: online scrub didn't fail.
+entries[2].incomplete = ones: online scrub didn't fail.
+entries[2].incomplete = firstbit: online scrub didn't fail.
+entries[2].incomplete = middlebit: online scrub didn't fail.
+entries[2].incomplete = lastbit: online scrub didn't fail.
+entries[2].incomplete = add: online scrub didn't fail.
+entries[2].incomplete = sub: online scrub didn't fail.
+entries[3].incomplete = ones: online scrub didn't fail.
+entries[3].incomplete = firstbit: online scrub didn't fail.
+entries[3].incomplete = middlebit: online scrub didn't fail.
+entries[3].incomplete = lastbit: online scrub didn't fail.
+entries[3].incomplete = add: online scrub didn't fail.
+entries[3].incomplete = sub: online scrub didn't fail.
+entries[4].incomplete = ones: online scrub didn't fail.
+entries[4].incomplete = firstbit: online scrub didn't fail.
+entries[4].incomplete = middlebit: online scrub didn't fail.
+entries[4].incomplete = lastbit: online scrub didn't fail.
+entries[4].incomplete = add: online scrub didn't fail.
+entries[4].incomplete = sub: online scrub didn't fail.
+entries[5].incomplete = ones: online scrub didn't fail.
+entries[5].incomplete = firstbit: online scrub didn't fail.
+entries[5].incomplete = middlebit: online scrub didn't fail.
+entries[5].incomplete = lastbit: online scrub didn't fail.
+entries[5].incomplete = add: online scrub didn't fail.
+entries[5].incomplete = sub: online scrub didn't fail.
+entries[6].incomplete = ones: online scrub didn't fail.
+entries[6].incomplete = firstbit: online scrub didn't fail.
+entries[6].incomplete = middlebit: online scrub didn't fail.
+entries[6].incomplete = lastbit: online scrub didn't fail.
+entries[6].incomplete = add: online scrub didn't fail.
+entries[6].incomplete = sub: online scrub didn't fail.
+entries[7].incomplete = ones: online scrub didn't fail.
+entries[7].incomplete = firstbit: online scrub didn't fail.
+entries[7].incomplete = middlebit: online scrub didn't fail.
+entries[7].incomplete = lastbit: online scrub didn't fail.
+entries[7].incomplete = add: online scrub didn't fail.
+entries[7].incomplete = sub: online scrub didn't fail.
+entries[8].incomplete = ones: online scrub didn't fail.
+entries[8].incomplete = firstbit: online scrub didn't fail.
+entries[8].incomplete = middlebit: online scrub didn't fail.
+entries[8].incomplete = lastbit: online scrub didn't fail.
+entries[8].incomplete = add: online scrub didn't fail.
+entries[8].incomplete = sub: online scrub didn't fail.
+entries[9].incomplete = ones: online scrub didn't fail.
+entries[9].incomplete = firstbit: online scrub didn't fail.
+entries[9].incomplete = middlebit: online scrub didn't fail.
+entries[9].incomplete = lastbit: online scrub didn't fail.
+entries[9].incomplete = add: online scrub didn't fail.
+entries[9].incomplete = sub: online scrub didn't fail.
 Done fuzzing leaf-format attr block
diff --git a/tests/xfs/405.out b/tests/xfs/405.out
index b7c114cf69..0f9ad76bd5 100644
--- a/tests/xfs/405.out
+++ b/tests/xfs/405.out
@@ -2,4 +2,9 @@ QA output created by 405
 Format and populate
 Find external attr block
 Fuzz external attr block
+data = zeroes: online scrub didn't fail.
+data = ones: online scrub didn't fail.
+data = firstbit: online scrub didn't fail.
+data = middlebit: online scrub didn't fail.
+data = lastbit: online scrub didn't fail.
 Done fuzzing external attr block
diff --git a/tests/xfs/413.out b/tests/xfs/413.out
index cebe104e6e..8ad1b3d239 100644
--- a/tests/xfs/413.out
+++ b/tests/xfs/413.out
@@ -2,4 +2,52 @@ QA output created by 413
 Format and populate
 Find btree-format attr inode
 Fuzz inode
+core.mode = zeroes: offline re-scrub failed (1).
+core.mode = zeroes: offline post-mod scrub failed (1).
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.uid = ones: online re-scrub failed (1).
+core.gid = ones: online re-scrub failed (1).
+core.nlinkv2 = zeroes: online repair failed (4).
+core.nlinkv2 = zeroes: online re-scrub failed (4).
+core.nlinkv2 = zeroes: offline re-scrub failed (1).
+core.nlinkv2 = zeroes: online post-mod scrub failed (4).
+core.nlinkv2 = zeroes: offline post-mod scrub failed (1).
+core.nlinkv2 = lastbit: online repair failed (4).
+core.nlinkv2 = lastbit: online re-scrub failed (4).
+core.nlinkv2 = lastbit: offline re-scrub failed (1).
+core.nlinkv2 = lastbit: online post-mod scrub failed (4).
+core.nlinkv2 = lastbit: offline post-mod scrub failed (1).
+core.size = middlebit: online scrub didn't fail.
+core.size = lastbit: online scrub didn't fail.
+core.size = add: online scrub didn't fail.
+next_unlinked = add: online scrub didn't fail.
+next_unlinked = add: offline re-scrub failed (1).
+next_unlinked = add: offline post-mod scrub failed (1).
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = ones: offline re-scrub failed (1).
+v3.flags2 = ones: offline post-mod scrub failed (1).
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.flags2 = middlebit: offline re-scrub failed (1).
+v3.flags2 = middlebit: offline post-mod scrub failed (1).
+v3.flags2 = lastbit: online scrub didn't fail.
+v3.flags2 = add: online scrub didn't fail.
+v3.flags2 = add: offline re-scrub failed (1).
+v3.flags2 = add: offline post-mod scrub failed (1).
+v3.flags2 = sub: offline re-scrub failed (1).
+v3.flags2 = sub: offline post-mod scrub failed (1).
+v3.reflink = ones: online scrub didn't fail.
+v3.reflink = firstbit: online scrub didn't fail.
+v3.reflink = middlebit: online scrub didn't fail.
+v3.reflink = lastbit: online scrub didn't fail.
+v3.reflink = add: online scrub didn't fail.
+v3.reflink = sub: online scrub didn't fail.
+a.bmbt.ptrs[1] = firstbit: online scrub didn't fail.
 Done fuzzing inode
diff --git a/tests/xfs/415.out b/tests/xfs/415.out
index 0784c0d5d8..6ff2573796 100644
--- a/tests/xfs/415.out
+++ b/tests/xfs/415.out
@@ -2,4 +2,60 @@ QA output created by 415
 Format and populate
 Find blockdev inode
 Fuzz inode
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.uid = ones: online re-scrub failed (1).
+core.gid = ones: online re-scrub failed (1).
+core.nlinkv2 = zeroes: online repair failed (4).
+core.nlinkv2 = zeroes: online re-scrub failed (4).
+core.nlinkv2 = zeroes: offline re-scrub failed (1).
+core.nlinkv2 = zeroes: online post-mod scrub failed (4).
+core.nlinkv2 = zeroes: offline post-mod scrub failed (1).
+core.nlinkv2 = lastbit: online repair failed (4).
+core.nlinkv2 = lastbit: online re-scrub failed (4).
+core.nlinkv2 = lastbit: offline re-scrub failed (1).
+core.nlinkv2 = lastbit: online post-mod scrub failed (4).
+core.nlinkv2 = lastbit: offline post-mod scrub failed (1).
+core.size = middlebit: online scrub didn't fail.
+core.size = middlebit: offline re-scrub failed (1).
+core.size = middlebit: offline post-mod scrub failed (1).
+core.size = lastbit: online scrub didn't fail.
+core.size = lastbit: offline re-scrub failed (1).
+core.size = lastbit: offline post-mod scrub failed (1).
+core.size = add: online scrub didn't fail.
+core.size = add: offline re-scrub failed (1).
+core.size = add: offline post-mod scrub failed (1).
+next_unlinked = add: online scrub didn't fail.
+next_unlinked = add: offline re-scrub failed (1).
+next_unlinked = add: offline post-mod scrub failed (1).
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = ones: offline re-scrub failed (1).
+v3.flags2 = ones: offline post-mod scrub failed (1).
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.flags2 = middlebit: offline re-scrub failed (1).
+v3.flags2 = middlebit: offline post-mod scrub failed (1).
+v3.flags2 = add: offline re-scrub failed (1).
+v3.flags2 = add: offline post-mod scrub failed (1).
+v3.flags2 = sub: offline re-scrub failed (1).
+v3.flags2 = sub: offline post-mod scrub failed (1).
+v3.nrext64 = zeroes: online scrub didn't fail.
+v3.nrext64 = firstbit: online scrub didn't fail.
+v3.nrext64 = middlebit: online scrub didn't fail.
+v3.nrext64 = lastbit: online scrub didn't fail.
+v3.nrext64 = add: online scrub didn't fail.
+v3.nrext64 = sub: online scrub didn't fail.
+u3.dev = zeroes: online scrub didn't fail.
+u3.dev = ones: online scrub didn't fail.
+u3.dev = firstbit: online scrub didn't fail.
+u3.dev = middlebit: online scrub didn't fail.
+u3.dev = lastbit: online scrub didn't fail.
+u3.dev = add: online scrub didn't fail.
+u3.dev = sub: online scrub didn't fail.
 Done fuzzing inode
diff --git a/tests/xfs/417.out b/tests/xfs/417.out
index 744cc2c715..cbd2b8f6e3 100644
--- a/tests/xfs/417.out
+++ b/tests/xfs/417.out
@@ -2,4 +2,60 @@ QA output created by 417
 Format and populate
 Find local-format symlink inode
 Fuzz inode
+core.mode = firstbit: online repair failed (1).
+core.mode = firstbit: online re-scrub failed (5).
+core.mode = firstbit: offline re-scrub failed (1).
+core.mode = firstbit: online post-mod scrub failed (1).
+core.mode = firstbit: offline post-mod scrub failed (1).
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.uid = ones: online re-scrub failed (1).
+core.gid = ones: online re-scrub failed (1).
+core.nlinkv2 = zeroes: online repair failed (4).
+core.nlinkv2 = zeroes: online re-scrub failed (4).
+core.nlinkv2 = zeroes: offline re-scrub failed (1).
+core.nlinkv2 = zeroes: online post-mod scrub failed (4).
+core.nlinkv2 = zeroes: offline post-mod scrub failed (1).
+core.nlinkv2 = lastbit: online repair failed (4).
+core.nlinkv2 = lastbit: online re-scrub failed (4).
+core.nlinkv2 = lastbit: offline re-scrub failed (1).
+core.nlinkv2 = lastbit: online post-mod scrub failed (4).
+core.nlinkv2 = lastbit: offline post-mod scrub failed (1).
+core.forkoff = firstbit: online repair failed (1).
+core.forkoff = firstbit: online re-scrub failed (5).
+core.forkoff = firstbit: offline re-scrub failed (1).
+core.forkoff = firstbit: online post-mod scrub failed (1).
+core.forkoff = firstbit: offline post-mod scrub failed (1).
+next_unlinked = add: online scrub didn't fail.
+next_unlinked = add: offline re-scrub failed (1).
+next_unlinked = add: offline post-mod scrub failed (1).
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = ones: offline re-scrub failed (1).
+v3.flags2 = ones: offline post-mod scrub failed (1).
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.flags2 = middlebit: offline re-scrub failed (1).
+v3.flags2 = middlebit: offline post-mod scrub failed (1).
+v3.flags2 = add: offline re-scrub failed (1).
+v3.flags2 = add: offline post-mod scrub failed (1).
+v3.flags2 = sub: offline re-scrub failed (1).
+v3.flags2 = sub: offline post-mod scrub failed (1).
+v3.nrext64 = zeroes: online scrub didn't fail.
+v3.nrext64 = firstbit: online scrub didn't fail.
+v3.nrext64 = middlebit: online scrub didn't fail.
+v3.nrext64 = lastbit: online scrub didn't fail.
+v3.nrext64 = add: online scrub didn't fail.
+v3.nrext64 = sub: online scrub didn't fail.
+u3.symlink = ones: online scrub didn't fail.
+u3.symlink = firstbit: online scrub didn't fail.
+u3.symlink = middlebit: online scrub didn't fail.
+u3.symlink = lastbit: online scrub didn't fail.
+u3.symlink = add: online scrub didn't fail.
+u3.symlink = sub: online scrub didn't fail.
 Done fuzzing inode
diff --git a/tests/xfs/426.out b/tests/xfs/426.out
index daddd1f3c8..d431c3dfb9 100644
--- a/tests/xfs/426.out
+++ b/tests/xfs/426.out
@@ -1,4 +1,136 @@
 QA output created by 426
 Format and populate
 Fuzz user 0 dquot
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.blk_softlimit = ones: online repair failed (1).
+diskdq.blk_softlimit = ones: online re-scrub failed (5).
+diskdq.blk_softlimit = ones: online post-mod scrub failed (1).
+diskdq.blk_softlimit = firstbit: online repair failed (1).
+diskdq.blk_softlimit = firstbit: online re-scrub failed (5).
+diskdq.blk_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = middlebit: online repair failed (1).
+diskdq.blk_softlimit = middlebit: online re-scrub failed (5).
+diskdq.blk_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = lastbit: online repair failed (1).
+diskdq.blk_softlimit = lastbit: online re-scrub failed (5).
+diskdq.blk_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = add: online repair failed (1).
+diskdq.blk_softlimit = add: online re-scrub failed (5).
+diskdq.blk_softlimit = add: online post-mod scrub failed (1).
+diskdq.blk_softlimit = sub: online repair failed (1).
+diskdq.blk_softlimit = sub: online re-scrub failed (5).
+diskdq.blk_softlimit = sub: online post-mod scrub failed (1).
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_softlimit = ones: online repair failed (1).
+diskdq.ino_softlimit = ones: online re-scrub failed (5).
+diskdq.ino_softlimit = ones: online post-mod scrub failed (1).
+diskdq.ino_softlimit = firstbit: online repair failed (1).
+diskdq.ino_softlimit = firstbit: online re-scrub failed (5).
+diskdq.ino_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = middlebit: online repair failed (1).
+diskdq.ino_softlimit = middlebit: online re-scrub failed (5).
+diskdq.ino_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = lastbit: online repair failed (1).
+diskdq.ino_softlimit = lastbit: online re-scrub failed (5).
+diskdq.ino_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = add: online repair failed (1).
+diskdq.ino_softlimit = add: online re-scrub failed (5).
+diskdq.ino_softlimit = add: online post-mod scrub failed (1).
+diskdq.ino_softlimit = sub: online repair failed (1).
+diskdq.ino_softlimit = sub: online re-scrub failed (5).
+diskdq.ino_softlimit = sub: online post-mod scrub failed (1).
+diskdq.itimer = ones: online scrub didn't fail.
+diskdq.itimer = firstbit: online scrub didn't fail.
+diskdq.itimer = middlebit: online scrub didn't fail.
+diskdq.itimer = lastbit: online scrub didn't fail.
+diskdq.itimer = add: online scrub didn't fail.
+diskdq.itimer = sub: online scrub didn't fail.
+diskdq.btimer = ones: online scrub didn't fail.
+diskdq.btimer = firstbit: online scrub didn't fail.
+diskdq.btimer = middlebit: online scrub didn't fail.
+diskdq.btimer = lastbit: online scrub didn't fail.
+diskdq.btimer = add: online scrub didn't fail.
+diskdq.btimer = sub: online scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_softlimit = ones: online repair failed (1).
+diskdq.rtb_softlimit = ones: online re-scrub failed (5).
+diskdq.rtb_softlimit = ones: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = firstbit: online repair failed (1).
+diskdq.rtb_softlimit = firstbit: online re-scrub failed (5).
+diskdq.rtb_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = middlebit: online repair failed (1).
+diskdq.rtb_softlimit = middlebit: online re-scrub failed (5).
+diskdq.rtb_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = lastbit: online repair failed (1).
+diskdq.rtb_softlimit = lastbit: online re-scrub failed (5).
+diskdq.rtb_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = add: online repair failed (1).
+diskdq.rtb_softlimit = add: online re-scrub failed (5).
+diskdq.rtb_softlimit = add: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = sub: online repair failed (1).
+diskdq.rtb_softlimit = sub: online re-scrub failed (5).
+diskdq.rtb_softlimit = sub: online post-mod scrub failed (1).
+diskdq.rtbtimer = ones: online scrub didn't fail.
+diskdq.rtbtimer = firstbit: online scrub didn't fail.
+diskdq.rtbtimer = middlebit: online scrub didn't fail.
+diskdq.rtbtimer = lastbit: online scrub didn't fail.
+diskdq.rtbtimer = add: online scrub didn't fail.
+diskdq.rtbtimer = sub: online scrub didn't fail.
+Done fuzzing dquot
+Fuzz user 4242 dquot
+diskdq.type = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+Done fuzzing dquot
+Fuzz user 8484 dquot
+diskdq.type = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
 Done fuzzing dquot
diff --git a/tests/xfs/428.out b/tests/xfs/428.out
index f694aa03a6..b0ea71f271 100644
--- a/tests/xfs/428.out
+++ b/tests/xfs/428.out
@@ -1,4 +1,136 @@
 QA output created by 428
 Format and populate
 Fuzz group 0 dquot
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.blk_softlimit = ones: online repair failed (1).
+diskdq.blk_softlimit = ones: online re-scrub failed (5).
+diskdq.blk_softlimit = ones: online post-mod scrub failed (1).
+diskdq.blk_softlimit = firstbit: online repair failed (1).
+diskdq.blk_softlimit = firstbit: online re-scrub failed (5).
+diskdq.blk_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = middlebit: online repair failed (1).
+diskdq.blk_softlimit = middlebit: online re-scrub failed (5).
+diskdq.blk_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = lastbit: online repair failed (1).
+diskdq.blk_softlimit = lastbit: online re-scrub failed (5).
+diskdq.blk_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = add: online repair failed (1).
+diskdq.blk_softlimit = add: online re-scrub failed (5).
+diskdq.blk_softlimit = add: online post-mod scrub failed (1).
+diskdq.blk_softlimit = sub: online repair failed (1).
+diskdq.blk_softlimit = sub: online re-scrub failed (5).
+diskdq.blk_softlimit = sub: online post-mod scrub failed (1).
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_softlimit = ones: online repair failed (1).
+diskdq.ino_softlimit = ones: online re-scrub failed (5).
+diskdq.ino_softlimit = ones: online post-mod scrub failed (1).
+diskdq.ino_softlimit = firstbit: online repair failed (1).
+diskdq.ino_softlimit = firstbit: online re-scrub failed (5).
+diskdq.ino_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = middlebit: online repair failed (1).
+diskdq.ino_softlimit = middlebit: online re-scrub failed (5).
+diskdq.ino_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = lastbit: online repair failed (1).
+diskdq.ino_softlimit = lastbit: online re-scrub failed (5).
+diskdq.ino_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = add: online repair failed (1).
+diskdq.ino_softlimit = add: online re-scrub failed (5).
+diskdq.ino_softlimit = add: online post-mod scrub failed (1).
+diskdq.ino_softlimit = sub: online repair failed (1).
+diskdq.ino_softlimit = sub: online re-scrub failed (5).
+diskdq.ino_softlimit = sub: online post-mod scrub failed (1).
+diskdq.itimer = ones: online scrub didn't fail.
+diskdq.itimer = firstbit: online scrub didn't fail.
+diskdq.itimer = middlebit: online scrub didn't fail.
+diskdq.itimer = lastbit: online scrub didn't fail.
+diskdq.itimer = add: online scrub didn't fail.
+diskdq.itimer = sub: online scrub didn't fail.
+diskdq.btimer = ones: online scrub didn't fail.
+diskdq.btimer = firstbit: online scrub didn't fail.
+diskdq.btimer = middlebit: online scrub didn't fail.
+diskdq.btimer = lastbit: online scrub didn't fail.
+diskdq.btimer = add: online scrub didn't fail.
+diskdq.btimer = sub: online scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_softlimit = ones: online repair failed (1).
+diskdq.rtb_softlimit = ones: online re-scrub failed (5).
+diskdq.rtb_softlimit = ones: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = firstbit: online repair failed (1).
+diskdq.rtb_softlimit = firstbit: online re-scrub failed (5).
+diskdq.rtb_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = middlebit: online repair failed (1).
+diskdq.rtb_softlimit = middlebit: online re-scrub failed (5).
+diskdq.rtb_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = lastbit: online repair failed (1).
+diskdq.rtb_softlimit = lastbit: online re-scrub failed (5).
+diskdq.rtb_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = add: online repair failed (1).
+diskdq.rtb_softlimit = add: online re-scrub failed (5).
+diskdq.rtb_softlimit = add: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = sub: online repair failed (1).
+diskdq.rtb_softlimit = sub: online re-scrub failed (5).
+diskdq.rtb_softlimit = sub: online post-mod scrub failed (1).
+diskdq.rtbtimer = ones: online scrub didn't fail.
+diskdq.rtbtimer = firstbit: online scrub didn't fail.
+diskdq.rtbtimer = middlebit: online scrub didn't fail.
+diskdq.rtbtimer = lastbit: online scrub didn't fail.
+diskdq.rtbtimer = add: online scrub didn't fail.
+diskdq.rtbtimer = sub: online scrub didn't fail.
+Done fuzzing dquot
+Fuzz group 4242 dquot
+diskdq.type = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+Done fuzzing dquot
+Fuzz group 8484 dquot
+diskdq.type = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
 Done fuzzing dquot
diff --git a/tests/xfs/430.out b/tests/xfs/430.out
index 0e7fa85c30..5193cae57e 100644
--- a/tests/xfs/430.out
+++ b/tests/xfs/430.out
@@ -1,4 +1,136 @@
 QA output created by 430
 Format and populate
 Fuzz project 0 dquot
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.blk_softlimit = ones: online repair failed (1).
+diskdq.blk_softlimit = ones: online re-scrub failed (5).
+diskdq.blk_softlimit = ones: online post-mod scrub failed (1).
+diskdq.blk_softlimit = firstbit: online repair failed (1).
+diskdq.blk_softlimit = firstbit: online re-scrub failed (5).
+diskdq.blk_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = middlebit: online repair failed (1).
+diskdq.blk_softlimit = middlebit: online re-scrub failed (5).
+diskdq.blk_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = lastbit: online repair failed (1).
+diskdq.blk_softlimit = lastbit: online re-scrub failed (5).
+diskdq.blk_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = add: online repair failed (1).
+diskdq.blk_softlimit = add: online re-scrub failed (5).
+diskdq.blk_softlimit = add: online post-mod scrub failed (1).
+diskdq.blk_softlimit = sub: online repair failed (1).
+diskdq.blk_softlimit = sub: online re-scrub failed (5).
+diskdq.blk_softlimit = sub: online post-mod scrub failed (1).
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_softlimit = ones: online repair failed (1).
+diskdq.ino_softlimit = ones: online re-scrub failed (5).
+diskdq.ino_softlimit = ones: online post-mod scrub failed (1).
+diskdq.ino_softlimit = firstbit: online repair failed (1).
+diskdq.ino_softlimit = firstbit: online re-scrub failed (5).
+diskdq.ino_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = middlebit: online repair failed (1).
+diskdq.ino_softlimit = middlebit: online re-scrub failed (5).
+diskdq.ino_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = lastbit: online repair failed (1).
+diskdq.ino_softlimit = lastbit: online re-scrub failed (5).
+diskdq.ino_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = add: online repair failed (1).
+diskdq.ino_softlimit = add: online re-scrub failed (5).
+diskdq.ino_softlimit = add: online post-mod scrub failed (1).
+diskdq.ino_softlimit = sub: online repair failed (1).
+diskdq.ino_softlimit = sub: online re-scrub failed (5).
+diskdq.ino_softlimit = sub: online post-mod scrub failed (1).
+diskdq.itimer = ones: online scrub didn't fail.
+diskdq.itimer = firstbit: online scrub didn't fail.
+diskdq.itimer = middlebit: online scrub didn't fail.
+diskdq.itimer = lastbit: online scrub didn't fail.
+diskdq.itimer = add: online scrub didn't fail.
+diskdq.itimer = sub: online scrub didn't fail.
+diskdq.btimer = ones: online scrub didn't fail.
+diskdq.btimer = firstbit: online scrub didn't fail.
+diskdq.btimer = middlebit: online scrub didn't fail.
+diskdq.btimer = lastbit: online scrub didn't fail.
+diskdq.btimer = add: online scrub didn't fail.
+diskdq.btimer = sub: online scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_softlimit = ones: online repair failed (1).
+diskdq.rtb_softlimit = ones: online re-scrub failed (5).
+diskdq.rtb_softlimit = ones: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = firstbit: online repair failed (1).
+diskdq.rtb_softlimit = firstbit: online re-scrub failed (5).
+diskdq.rtb_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = middlebit: online repair failed (1).
+diskdq.rtb_softlimit = middlebit: online re-scrub failed (5).
+diskdq.rtb_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = lastbit: online repair failed (1).
+diskdq.rtb_softlimit = lastbit: online re-scrub failed (5).
+diskdq.rtb_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = add: online repair failed (1).
+diskdq.rtb_softlimit = add: online re-scrub failed (5).
+diskdq.rtb_softlimit = add: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = sub: online repair failed (1).
+diskdq.rtb_softlimit = sub: online re-scrub failed (5).
+diskdq.rtb_softlimit = sub: online post-mod scrub failed (1).
+diskdq.rtbtimer = ones: online scrub didn't fail.
+diskdq.rtbtimer = firstbit: online scrub didn't fail.
+diskdq.rtbtimer = middlebit: online scrub didn't fail.
+diskdq.rtbtimer = lastbit: online scrub didn't fail.
+diskdq.rtbtimer = add: online scrub didn't fail.
+diskdq.rtbtimer = sub: online scrub didn't fail.
+Done fuzzing dquot
+Fuzz project 4242 dquot
+diskdq.type = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+Done fuzzing dquot
+Fuzz project 8484 dquot
+diskdq.type = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
 Done fuzzing dquot
diff --git a/tests/xfs/730.out b/tests/xfs/730.out
index 28d4becad3..c35b704a11 100644
--- a/tests/xfs/730.out
+++ b/tests/xfs/730.out
@@ -1,4 +1,14 @@
 QA output created by 730
 Format and populate
 Fuzz fscounters
+icount = zeroes: online scrub didn't fail.
+icount = ones: online scrub didn't fail.
+icount = firstbit: online scrub didn't fail.
+icount = middlebit: online scrub didn't fail.
+ifree = ones: online scrub didn't fail.
+ifree = firstbit: online scrub didn't fail.
+ifree = middlebit: online scrub didn't fail.
+fdblocks = ones: online scrub didn't fail.
+fdblocks = firstbit: online scrub didn't fail.
+fdblocks = middlebit: online scrub didn't fail.
 Done fuzzing fscounters

[PATCH 2/4] xfs: offline fuzz test known output

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Record all the currently known failures of the xfs_repair check and
repair code.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 tests/xfs/350.out |   91 +++++++++
 tests/xfs/354.out |   87 +++++++++
 tests/xfs/356.out |   13 +
 tests/xfs/358.out |    5 
 tests/xfs/360.out |   30 +++
 tests/xfs/362.out |    5 
 tests/xfs/364.out |    6 +
 tests/xfs/366.out |    6 +
 tests/xfs/368.out |    8 +
 tests/xfs/370.out |  417 +++++++++++++++++++++++++++++++++++++++++
 tests/xfs/372.out |    5 
 tests/xfs/374.out |   35 +++
 tests/xfs/376.out |   22 ++
 tests/xfs/378.out |   22 ++
 tests/xfs/382.out |    4 
 tests/xfs/384.out |   38 ++++
 tests/xfs/386.out |   28 +++
 tests/xfs/388.out |  535 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 tests/xfs/392.out |    7 +
 tests/xfs/394.out |   12 +
 tests/xfs/398.out |   38 ++++
 tests/xfs/400.out |   26 +++
 tests/xfs/402.out |    7 +
 tests/xfs/404.out |   33 +++
 tests/xfs/410.out |    6 +
 tests/xfs/412.out |   21 ++
 tests/xfs/414.out |   23 ++
 tests/xfs/416.out |   22 ++
 tests/xfs/418.out |   90 +++++++++
 tests/xfs/425.out |  258 ++++++++++++++++++++++++++
 tests/xfs/427.out |  258 ++++++++++++++++++++++++++
 tests/xfs/429.out |  258 ++++++++++++++++++++++++++
 tests/xfs/496.out |   24 ++
 tests/xfs/734.out |    9 +
 tests/xfs/737.out |   14 +
 tests/xfs/754.out |   23 ++
 tests/xfs/785.out |   23 ++
 37 files changed, 2509 insertions(+)


diff --git a/tests/xfs/350.out b/tests/xfs/350.out
index 3bb9762b30..a0b70cf907 100644
--- a/tests/xfs/350.out
+++ b/tests/xfs/350.out
@@ -1,4 +1,95 @@
 QA output created by 350
 Format and populate
 Fuzz superblock
+rgblocks = middlebit: offline scrub didn't fail.
+rgblocks = lastbit: offline scrub didn't fail.
+rgblocks = add: offline scrub didn't fail.
+rgblocks = sub: offline scrub didn't fail.
+fname = ones: offline scrub didn't fail.
+fname = firstbit: offline scrub didn't fail.
+fname = middlebit: offline scrub didn't fail.
+fname = lastbit: offline scrub didn't fail.
+imax_pct = zeroes: offline scrub didn't fail.
+imax_pct = middlebit: offline scrub didn't fail.
+imax_pct = lastbit: offline scrub didn't fail.
+qflags = zeroes: offline scrub didn't fail.
+qflags = ones: offline scrub didn't fail.
+qflags = firstbit: offline scrub didn't fail.
+qflags = middlebit: offline scrub didn't fail.
+qflags = lastbit: offline scrub didn't fail.
+qflags = add: offline scrub didn't fail.
+qflags = sub: offline scrub didn't fail.
+dirblklog = lastbit: online post-mod scrub failed (1).
+logsunit = zeroes: offline scrub didn't fail.
+logsunit = zeroes: online post-mod scrub failed (1).
+logsunit = lastbit: offline scrub didn't fail.
+logsunit = lastbit: online post-mod scrub failed (1).
+bad_features2 = zeroes: offline scrub didn't fail.
+features_compat = ones: offline repair failed (1).
+features_compat = ones: offline re-scrub failed (1).
+features_compat = ones: pre-mod mount failed (32).
+features_compat = firstbit: offline repair failed (1).
+features_compat = firstbit: offline re-scrub failed (1).
+features_compat = firstbit: pre-mod mount failed (32).
+features_compat = middlebit: offline repair failed (1).
+features_compat = middlebit: offline re-scrub failed (1).
+features_compat = middlebit: pre-mod mount failed (32).
+features_compat = lastbit: offline repair failed (1).
+features_compat = lastbit: offline re-scrub failed (1).
+features_compat = lastbit: pre-mod mount failed (32).
+features_compat = add: offline repair failed (1).
+features_compat = add: offline re-scrub failed (1).
+features_compat = add: pre-mod mount failed (32).
+features_compat = sub: offline repair failed (1).
+features_compat = sub: offline re-scrub failed (1).
+features_compat = sub: pre-mod mount failed (32).
+features_ro_compat = zeroes: offline re-scrub failed (1).
+features_ro_compat = zeroes: offline post-mod scrub failed (1).
+features_ro_compat = ones: offline repair failed (1).
+features_ro_compat = ones: offline re-scrub failed (1).
+features_ro_compat = ones: pre-mod mount failed (32).
+features_ro_compat = firstbit: offline repair failed (1).
+features_ro_compat = firstbit: offline re-scrub failed (1).
+features_ro_compat = firstbit: pre-mod mount failed (32).
+features_ro_compat = middlebit: offline repair failed (1).
+features_ro_compat = middlebit: offline re-scrub failed (1).
+features_ro_compat = middlebit: pre-mod mount failed (32).
+features_ro_compat = lastbit: offline re-scrub failed (1).
+features_ro_compat = lastbit: offline post-mod scrub failed (1).
+features_ro_compat = add: offline repair failed (1).
+features_ro_compat = add: offline re-scrub failed (1).
+features_ro_compat = add: pre-mod mount failed (32).
+features_ro_compat = sub: offline repair failed (1).
+features_ro_compat = sub: offline re-scrub failed (1).
+features_ro_compat = sub: pre-mod mount failed (32).
+features_incompat = ones: offline repair failed (1).
+features_incompat = ones: offline re-scrub failed (1).
+features_incompat = ones: pre-mod mount failed (32).
+features_incompat = middlebit: offline repair failed (1).
+features_incompat = middlebit: offline re-scrub failed (1).
+features_incompat = middlebit: pre-mod mount failed (32).
+features_incompat = lastbit: offline repair failed (1).
+features_incompat = lastbit: offline re-scrub failed (1).
+features_incompat = lastbit: pre-mod mount failed (32).
+features_incompat = sub: offline repair failed (1).
+features_incompat = sub: offline re-scrub failed (1).
+features_incompat = sub: pre-mod mount failed (32).
+features_log_incompat = ones: offline scrub didn't fail.
+features_log_incompat = ones: offline repair failed (1).
+features_log_incompat = ones: offline re-scrub failed (1).
+features_log_incompat = ones: pre-mod mount failed (32).
+features_log_incompat = firstbit: offline scrub didn't fail.
+features_log_incompat = middlebit: offline scrub didn't fail.
+features_log_incompat = middlebit: offline repair failed (1).
+features_log_incompat = middlebit: offline re-scrub failed (1).
+features_log_incompat = middlebit: pre-mod mount failed (32).
+features_log_incompat = lastbit: offline scrub didn't fail.
+features_log_incompat = add: offline scrub didn't fail.
+features_log_incompat = add: offline repair failed (1).
+features_log_incompat = add: offline re-scrub failed (1).
+features_log_incompat = add: pre-mod mount failed (32).
+features_log_incompat = sub: offline scrub didn't fail.
+features_log_incompat = sub: offline repair failed (1).
+features_log_incompat = sub: offline re-scrub failed (1).
+features_log_incompat = sub: pre-mod mount failed (32).
 Done fuzzing superblock
diff --git a/tests/xfs/354.out b/tests/xfs/354.out
index d8b33f64ea..0e53e4909f 100644
--- a/tests/xfs/354.out
+++ b/tests/xfs/354.out
@@ -1,6 +1,93 @@
 QA output created by 354
 Format and populate
 Fuzz AGFL
+magicnum = zeroes: offline scrub didn't fail.
+magicnum = ones: offline scrub didn't fail.
+magicnum = firstbit: offline scrub didn't fail.
+magicnum = middlebit: offline scrub didn't fail.
+magicnum = lastbit: offline scrub didn't fail.
+magicnum = add: offline scrub didn't fail.
+magicnum = sub: offline scrub didn't fail.
+seqno = ones: offline scrub didn't fail.
+seqno = firstbit: offline scrub didn't fail.
+seqno = middlebit: offline scrub didn't fail.
+seqno = lastbit: offline scrub didn't fail.
+seqno = add: offline scrub didn't fail.
+seqno = sub: offline scrub didn't fail.
+uuid = zeroes: offline scrub didn't fail.
+uuid = ones: offline scrub didn't fail.
+uuid = firstbit: offline scrub didn't fail.
+uuid = middlebit: offline scrub didn't fail.
+uuid = lastbit: offline scrub didn't fail.
+bno[0] = zeroes: offline scrub didn't fail.
+bno[0] = firstbit: offline scrub didn't fail.
+bno[0] = middlebit: offline scrub didn't fail.
+bno[0] = lastbit: offline scrub didn't fail.
+bno[0] = add: offline scrub didn't fail.
+bno[0] = sub: offline scrub didn't fail.
+bno[1] = zeroes: offline scrub didn't fail.
+bno[1] = ones: offline scrub didn't fail.
+bno[1] = firstbit: offline scrub didn't fail.
+bno[1] = middlebit: offline scrub didn't fail.
+bno[1] = lastbit: offline scrub didn't fail.
+bno[1] = add: offline scrub didn't fail.
+bno[1] = sub: offline scrub didn't fail.
+bno[2] = zeroes: offline scrub didn't fail.
+bno[2] = ones: offline scrub didn't fail.
+bno[2] = firstbit: offline scrub didn't fail.
+bno[2] = middlebit: offline scrub didn't fail.
+bno[2] = lastbit: offline scrub didn't fail.
+bno[2] = add: offline scrub didn't fail.
+bno[2] = sub: offline scrub didn't fail.
+bno[3] = zeroes: offline scrub didn't fail.
+bno[3] = ones: offline scrub didn't fail.
+bno[3] = firstbit: offline scrub didn't fail.
+bno[3] = middlebit: offline scrub didn't fail.
+bno[3] = lastbit: offline scrub didn't fail.
+bno[3] = add: offline scrub didn't fail.
+bno[3] = sub: offline scrub didn't fail.
+bno[4] = zeroes: offline scrub didn't fail.
+bno[4] = ones: offline scrub didn't fail.
+bno[4] = firstbit: offline scrub didn't fail.
+bno[4] = middlebit: offline scrub didn't fail.
+bno[4] = lastbit: offline scrub didn't fail.
+bno[4] = add: offline scrub didn't fail.
+bno[4] = sub: offline scrub didn't fail.
+bno[5] = zeroes: offline scrub didn't fail.
+bno[5] = ones: offline scrub didn't fail.
+bno[5] = firstbit: offline scrub didn't fail.
+bno[5] = middlebit: offline scrub didn't fail.
+bno[5] = lastbit: offline scrub didn't fail.
+bno[5] = add: offline scrub didn't fail.
+bno[5] = sub: offline scrub didn't fail.
+bno[6] = zeroes: offline scrub didn't fail.
+bno[6] = ones: offline scrub didn't fail.
+bno[6] = firstbit: offline scrub didn't fail.
+bno[6] = middlebit: offline scrub didn't fail.
+bno[6] = lastbit: offline scrub didn't fail.
+bno[6] = add: offline scrub didn't fail.
+bno[6] = sub: offline scrub didn't fail.
+bno[7] = zeroes: offline scrub didn't fail.
+bno[7] = ones: offline scrub didn't fail.
+bno[7] = firstbit: offline scrub didn't fail.
+bno[7] = middlebit: offline scrub didn't fail.
+bno[7] = lastbit: offline scrub didn't fail.
+bno[7] = add: offline scrub didn't fail.
+bno[7] = sub: offline scrub didn't fail.
+bno[8] = zeroes: offline scrub didn't fail.
+bno[8] = ones: offline scrub didn't fail.
+bno[8] = firstbit: offline scrub didn't fail.
+bno[8] = middlebit: offline scrub didn't fail.
+bno[8] = lastbit: offline scrub didn't fail.
+bno[8] = add: offline scrub didn't fail.
+bno[8] = sub: offline scrub didn't fail.
+bno[9] = zeroes: offline scrub didn't fail.
+bno[9] = ones: offline scrub didn't fail.
+bno[9] = firstbit: offline scrub didn't fail.
+bno[9] = middlebit: offline scrub didn't fail.
+bno[9] = lastbit: offline scrub didn't fail.
+bno[9] = add: offline scrub didn't fail.
+bno[9] = sub: offline scrub didn't fail.
 Done fuzzing AGFL
 Fuzz AGFL flfirst
 Done fuzzing AGFL flfirst
diff --git a/tests/xfs/356.out b/tests/xfs/356.out
index ca7834467a..aa40e3e1a3 100644
--- a/tests/xfs/356.out
+++ b/tests/xfs/356.out
@@ -1,4 +1,17 @@
 QA output created by 356
 Format and populate
 Fuzz AGI
+newino = zeroes: offline scrub didn't fail.
+newino = ones: offline scrub didn't fail.
+newino = firstbit: offline scrub didn't fail.
+newino = middlebit: offline scrub didn't fail.
+newino = lastbit: offline scrub didn't fail.
+newino = add: offline scrub didn't fail.
+newino = sub: offline scrub didn't fail.
+dirino = zeroes: offline scrub didn't fail.
+dirino = firstbit: offline scrub didn't fail.
+dirino = middlebit: offline scrub didn't fail.
+dirino = lastbit: offline scrub didn't fail.
+dirino = add: offline scrub didn't fail.
+dirino = sub: offline scrub didn't fail.
 Done fuzzing AGI
diff --git a/tests/xfs/358.out b/tests/xfs/358.out
index e1ec8623ad..0e04f3a81c 100644
--- a/tests/xfs/358.out
+++ b/tests/xfs/358.out
@@ -1,4 +1,9 @@
 QA output created by 358
 Format and populate
 Fuzz bnobt recs
+leftsib = add: offline scrub didn't fail.
+rightsib = ones: offline scrub didn't fail.
+rightsib = middlebit: offline scrub didn't fail.
+rightsib = lastbit: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
 Done fuzzing bnobt recs
diff --git a/tests/xfs/360.out b/tests/xfs/360.out
index fd7ce6cdb3..30011ce698 100644
--- a/tests/xfs/360.out
+++ b/tests/xfs/360.out
@@ -1,4 +1,34 @@
 QA output created by 360
 Format and populate
 Fuzz bnobt keyptr
+leftsib = add: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
+keys[1].startblock = zeroes: offline scrub didn't fail.
+keys[1].startblock = ones: offline scrub didn't fail.
+keys[1].startblock = firstbit: offline scrub didn't fail.
+keys[1].startblock = middlebit: offline scrub didn't fail.
+keys[1].startblock = lastbit: offline scrub didn't fail.
+keys[1].startblock = add: offline scrub didn't fail.
+keys[1].startblock = sub: offline scrub didn't fail.
+keys[1].blockcount = zeroes: offline scrub didn't fail.
+keys[1].blockcount = ones: offline scrub didn't fail.
+keys[1].blockcount = firstbit: offline scrub didn't fail.
+keys[1].blockcount = middlebit: offline scrub didn't fail.
+keys[1].blockcount = lastbit: offline scrub didn't fail.
+keys[1].blockcount = add: offline scrub didn't fail.
+keys[1].blockcount = sub: offline scrub didn't fail.
+keys[2].startblock = zeroes: offline scrub didn't fail.
+keys[2].startblock = ones: offline scrub didn't fail.
+keys[2].startblock = firstbit: offline scrub didn't fail.
+keys[2].startblock = middlebit: offline scrub didn't fail.
+keys[2].startblock = lastbit: offline scrub didn't fail.
+keys[2].startblock = add: offline scrub didn't fail.
+keys[2].startblock = sub: offline scrub didn't fail.
+keys[2].blockcount = zeroes: offline scrub didn't fail.
+keys[2].blockcount = ones: offline scrub didn't fail.
+keys[2].blockcount = firstbit: offline scrub didn't fail.
+keys[2].blockcount = middlebit: offline scrub didn't fail.
+keys[2].blockcount = lastbit: offline scrub didn't fail.
+keys[2].blockcount = add: offline scrub didn't fail.
+keys[2].blockcount = sub: offline scrub didn't fail.
 Done fuzzing bnobt keyptr
diff --git a/tests/xfs/362.out b/tests/xfs/362.out
index d39175e590..9c5fb8064d 100644
--- a/tests/xfs/362.out
+++ b/tests/xfs/362.out
@@ -1,4 +1,9 @@
 QA output created by 362
 Format and populate
 Fuzz cntbt
+leftsib = add: offline scrub didn't fail.
+rightsib = ones: offline scrub didn't fail.
+rightsib = middlebit: offline scrub didn't fail.
+rightsib = lastbit: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
 Done fuzzing cntbt
diff --git a/tests/xfs/364.out b/tests/xfs/364.out
index 2d6fad24e4..2df69904ed 100644
--- a/tests/xfs/364.out
+++ b/tests/xfs/364.out
@@ -1,4 +1,10 @@
 QA output created by 364
 Format and populate
 Fuzz inobt
+leftsib = add: offline scrub didn't fail.
+rightsib = ones: offline scrub didn't fail.
+rightsib = middlebit: offline scrub didn't fail.
+rightsib = lastbit: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
+rightsib = sub: offline scrub didn't fail.
 Done fuzzing inobt
diff --git a/tests/xfs/366.out b/tests/xfs/366.out
index 14906508ea..0970587bc9 100644
--- a/tests/xfs/366.out
+++ b/tests/xfs/366.out
@@ -1,4 +1,10 @@
 QA output created by 366
 Format and populate
 Fuzz finobt
+leftsib = add: offline scrub didn't fail.
+rightsib = ones: offline scrub didn't fail.
+rightsib = middlebit: offline scrub didn't fail.
+rightsib = lastbit: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
+rightsib = sub: offline scrub didn't fail.
 Done fuzzing finobt
diff --git a/tests/xfs/368.out b/tests/xfs/368.out
index 370ea0ef9a..213e1dab3d 100644
--- a/tests/xfs/368.out
+++ b/tests/xfs/368.out
@@ -1,4 +1,12 @@
 QA output created by 368
 Format and populate
 Fuzz rmapbt recs
+leftsib = add: offline scrub didn't fail.
+rightsib = ones: offline scrub didn't fail.
+rightsib = middlebit: offline scrub didn't fail.
+rightsib = lastbit: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
+recs[3].startblock = lastbit: offline scrub didn't fail.
+recs[3].blockcount = lastbit: offline scrub didn't fail.
+recs[6].owner = lastbit: offline scrub didn't fail.
 Done fuzzing rmapbt recs
diff --git a/tests/xfs/370.out b/tests/xfs/370.out
index 6858e135ad..84b9ded9b5 100644
--- a/tests/xfs/370.out
+++ b/tests/xfs/370.out
@@ -1,4 +1,421 @@
 QA output created by 370
 Format and populate
 Fuzz rmapbt keyptr
+leftsib = add: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
+keys[1].startblock = lastbit: offline scrub didn't fail.
+keys[1].owner = zeroes: offline scrub didn't fail.
+keys[1].owner = ones: offline scrub didn't fail.
+keys[1].owner = firstbit: offline scrub didn't fail.
+keys[1].owner = middlebit: offline scrub didn't fail.
+keys[1].owner = lastbit: offline scrub didn't fail.
+keys[1].owner = add: offline scrub didn't fail.
+keys[1].owner = sub: offline scrub didn't fail.
+keys[1].offset = ones: offline scrub didn't fail.
+keys[1].offset = firstbit: offline scrub didn't fail.
+keys[1].offset = middlebit: offline scrub didn't fail.
+keys[1].offset = lastbit: offline scrub didn't fail.
+keys[1].offset = add: offline scrub didn't fail.
+keys[1].offset = sub: offline scrub didn't fail.
+keys[1].extentflag = ones: offline scrub didn't fail.
+keys[1].extentflag = firstbit: offline scrub didn't fail.
+keys[1].extentflag = middlebit: offline scrub didn't fail.
+keys[1].extentflag = lastbit: offline scrub didn't fail.
+keys[1].extentflag = add: offline scrub didn't fail.
+keys[1].extentflag = sub: offline scrub didn't fail.
+keys[1].attrfork = ones: offline scrub didn't fail.
+keys[1].attrfork = firstbit: offline scrub didn't fail.
+keys[1].attrfork = middlebit: offline scrub didn't fail.
+keys[1].attrfork = lastbit: offline scrub didn't fail.
+keys[1].attrfork = add: offline scrub didn't fail.
+keys[1].attrfork = sub: offline scrub didn't fail.
+keys[1].bmbtblock = ones: offline scrub didn't fail.
+keys[1].bmbtblock = firstbit: offline scrub didn't fail.
+keys[1].bmbtblock = middlebit: offline scrub didn't fail.
+keys[1].bmbtblock = lastbit: offline scrub didn't fail.
+keys[1].bmbtblock = add: offline scrub didn't fail.
+keys[1].bmbtblock = sub: offline scrub didn't fail.
+keys[1].startblock_hi = ones: offline scrub didn't fail.
+keys[1].startblock_hi = firstbit: offline scrub didn't fail.
+keys[1].startblock_hi = middlebit: offline scrub didn't fail.
+keys[1].startblock_hi = lastbit: offline scrub didn't fail.
+keys[1].startblock_hi = add: offline scrub didn't fail.
+keys[1].startblock_hi = sub: offline scrub didn't fail.
+keys[1].owner_hi = ones: offline scrub didn't fail.
+keys[1].owner_hi = firstbit: offline scrub didn't fail.
+keys[1].owner_hi = middlebit: offline scrub didn't fail.
+keys[1].owner_hi = lastbit: offline scrub didn't fail.
+keys[1].owner_hi = add: offline scrub didn't fail.
+keys[1].owner_hi = sub: offline scrub didn't fail.
+keys[1].offset_hi = ones: offline scrub didn't fail.
+keys[1].offset_hi = firstbit: offline scrub didn't fail.
+keys[1].offset_hi = middlebit: offline scrub didn't fail.
+keys[1].offset_hi = add: offline scrub didn't fail.
+keys[1].offset_hi = sub: offline scrub didn't fail.
+keys[1].extentflag_hi = ones: offline scrub didn't fail.
+keys[1].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[1].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[1].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[1].extentflag_hi = add: offline scrub didn't fail.
+keys[1].extentflag_hi = sub: offline scrub didn't fail.
+keys[1].attrfork_hi = ones: offline scrub didn't fail.
+keys[1].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[1].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[1].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[1].attrfork_hi = add: offline scrub didn't fail.
+keys[1].attrfork_hi = sub: offline scrub didn't fail.
+keys[1].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[1].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[1].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[1].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[1].bmbtblock_hi = add: offline scrub didn't fail.
+keys[1].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[2].owner = zeroes: offline scrub didn't fail.
+keys[2].offset = zeroes: offline scrub didn't fail.
+keys[2].offset = lastbit: offline scrub didn't fail.
+keys[2].extentflag = ones: offline scrub didn't fail.
+keys[2].extentflag = firstbit: offline scrub didn't fail.
+keys[2].extentflag = middlebit: offline scrub didn't fail.
+keys[2].extentflag = lastbit: offline scrub didn't fail.
+keys[2].extentflag = add: offline scrub didn't fail.
+keys[2].extentflag = sub: offline scrub didn't fail.
+keys[2].startblock_hi = ones: offline scrub didn't fail.
+keys[2].startblock_hi = firstbit: offline scrub didn't fail.
+keys[2].startblock_hi = middlebit: offline scrub didn't fail.
+keys[2].startblock_hi = lastbit: offline scrub didn't fail.
+keys[2].startblock_hi = add: offline scrub didn't fail.
+keys[2].startblock_hi = sub: offline scrub didn't fail.
+keys[2].owner_hi = ones: offline scrub didn't fail.
+keys[2].owner_hi = firstbit: offline scrub didn't fail.
+keys[2].owner_hi = middlebit: offline scrub didn't fail.
+keys[2].owner_hi = lastbit: offline scrub didn't fail.
+keys[2].owner_hi = add: offline scrub didn't fail.
+keys[2].owner_hi = sub: offline scrub didn't fail.
+keys[2].offset_hi = ones: offline scrub didn't fail.
+keys[2].offset_hi = firstbit: offline scrub didn't fail.
+keys[2].offset_hi = middlebit: offline scrub didn't fail.
+keys[2].offset_hi = add: offline scrub didn't fail.
+keys[2].offset_hi = sub: offline scrub didn't fail.
+keys[2].extentflag_hi = ones: offline scrub didn't fail.
+keys[2].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[2].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[2].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[2].extentflag_hi = add: offline scrub didn't fail.
+keys[2].extentflag_hi = sub: offline scrub didn't fail.
+keys[2].attrfork_hi = ones: offline scrub didn't fail.
+keys[2].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[2].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[2].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[2].attrfork_hi = add: offline scrub didn't fail.
+keys[2].attrfork_hi = sub: offline scrub didn't fail.
+keys[2].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[2].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[2].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[2].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[2].bmbtblock_hi = add: offline scrub didn't fail.
+keys[2].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[3].owner = zeroes: offline scrub didn't fail.
+keys[3].offset = zeroes: offline scrub didn't fail.
+keys[3].offset = lastbit: offline scrub didn't fail.
+keys[3].extentflag = ones: offline scrub didn't fail.
+keys[3].extentflag = firstbit: offline scrub didn't fail.
+keys[3].extentflag = middlebit: offline scrub didn't fail.
+keys[3].extentflag = lastbit: offline scrub didn't fail.
+keys[3].extentflag = add: offline scrub didn't fail.
+keys[3].extentflag = sub: offline scrub didn't fail.
+keys[3].startblock_hi = ones: offline scrub didn't fail.
+keys[3].startblock_hi = firstbit: offline scrub didn't fail.
+keys[3].startblock_hi = middlebit: offline scrub didn't fail.
+keys[3].startblock_hi = lastbit: offline scrub didn't fail.
+keys[3].startblock_hi = add: offline scrub didn't fail.
+keys[3].startblock_hi = sub: offline scrub didn't fail.
+keys[3].owner_hi = ones: offline scrub didn't fail.
+keys[3].owner_hi = firstbit: offline scrub didn't fail.
+keys[3].owner_hi = middlebit: offline scrub didn't fail.
+keys[3].owner_hi = lastbit: offline scrub didn't fail.
+keys[3].owner_hi = add: offline scrub didn't fail.
+keys[3].offset_hi = ones: offline scrub didn't fail.
+keys[3].offset_hi = firstbit: offline scrub didn't fail.
+keys[3].offset_hi = middlebit: offline scrub didn't fail.
+keys[3].offset_hi = add: offline scrub didn't fail.
+keys[3].offset_hi = sub: offline scrub didn't fail.
+keys[3].extentflag_hi = ones: offline scrub didn't fail.
+keys[3].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[3].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[3].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[3].extentflag_hi = add: offline scrub didn't fail.
+keys[3].extentflag_hi = sub: offline scrub didn't fail.
+keys[3].attrfork_hi = ones: offline scrub didn't fail.
+keys[3].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[3].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[3].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[3].attrfork_hi = add: offline scrub didn't fail.
+keys[3].attrfork_hi = sub: offline scrub didn't fail.
+keys[3].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[3].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[3].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[3].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[3].bmbtblock_hi = add: offline scrub didn't fail.
+keys[3].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[4].owner = zeroes: offline scrub didn't fail.
+keys[4].owner = sub: offline scrub didn't fail.
+keys[4].offset = zeroes: offline scrub didn't fail.
+keys[4].offset = lastbit: offline scrub didn't fail.
+keys[4].extentflag = ones: offline scrub didn't fail.
+keys[4].extentflag = firstbit: offline scrub didn't fail.
+keys[4].extentflag = middlebit: offline scrub didn't fail.
+keys[4].extentflag = lastbit: offline scrub didn't fail.
+keys[4].extentflag = add: offline scrub didn't fail.
+keys[4].extentflag = sub: offline scrub didn't fail.
+keys[4].startblock_hi = ones: offline scrub didn't fail.
+keys[4].startblock_hi = firstbit: offline scrub didn't fail.
+keys[4].startblock_hi = middlebit: offline scrub didn't fail.
+keys[4].startblock_hi = lastbit: offline scrub didn't fail.
+keys[4].startblock_hi = add: offline scrub didn't fail.
+keys[4].startblock_hi = sub: offline scrub didn't fail.
+keys[4].owner_hi = ones: offline scrub didn't fail.
+keys[4].owner_hi = firstbit: offline scrub didn't fail.
+keys[4].owner_hi = middlebit: offline scrub didn't fail.
+keys[4].owner_hi = lastbit: offline scrub didn't fail.
+keys[4].owner_hi = add: offline scrub didn't fail.
+keys[4].offset_hi = ones: offline scrub didn't fail.
+keys[4].offset_hi = firstbit: offline scrub didn't fail.
+keys[4].offset_hi = middlebit: offline scrub didn't fail.
+keys[4].offset_hi = add: offline scrub didn't fail.
+keys[4].offset_hi = sub: offline scrub didn't fail.
+keys[4].extentflag_hi = ones: offline scrub didn't fail.
+keys[4].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[4].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[4].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[4].extentflag_hi = add: offline scrub didn't fail.
+keys[4].extentflag_hi = sub: offline scrub didn't fail.
+keys[4].attrfork_hi = ones: offline scrub didn't fail.
+keys[4].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[4].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[4].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[4].attrfork_hi = add: offline scrub didn't fail.
+keys[4].attrfork_hi = sub: offline scrub didn't fail.
+keys[4].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[4].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[4].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[4].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[4].bmbtblock_hi = add: offline scrub didn't fail.
+keys[4].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[5].owner = zeroes: offline scrub didn't fail.
+keys[5].owner = sub: offline scrub didn't fail.
+keys[5].offset = zeroes: offline scrub didn't fail.
+keys[5].offset = lastbit: offline scrub didn't fail.
+keys[5].extentflag = ones: offline scrub didn't fail.
+keys[5].extentflag = firstbit: offline scrub didn't fail.
+keys[5].extentflag = middlebit: offline scrub didn't fail.
+keys[5].extentflag = lastbit: offline scrub didn't fail.
+keys[5].extentflag = add: offline scrub didn't fail.
+keys[5].extentflag = sub: offline scrub didn't fail.
+keys[5].startblock_hi = ones: offline scrub didn't fail.
+keys[5].startblock_hi = firstbit: offline scrub didn't fail.
+keys[5].startblock_hi = middlebit: offline scrub didn't fail.
+keys[5].startblock_hi = lastbit: offline scrub didn't fail.
+keys[5].startblock_hi = add: offline scrub didn't fail.
+keys[5].startblock_hi = sub: offline scrub didn't fail.
+keys[5].owner_hi = ones: offline scrub didn't fail.
+keys[5].owner_hi = firstbit: offline scrub didn't fail.
+keys[5].owner_hi = middlebit: offline scrub didn't fail.
+keys[5].owner_hi = lastbit: offline scrub didn't fail.
+keys[5].owner_hi = add: offline scrub didn't fail.
+keys[5].offset_hi = ones: offline scrub didn't fail.
+keys[5].offset_hi = firstbit: offline scrub didn't fail.
+keys[5].offset_hi = middlebit: offline scrub didn't fail.
+keys[5].offset_hi = add: offline scrub didn't fail.
+keys[5].offset_hi = sub: offline scrub didn't fail.
+keys[5].extentflag_hi = ones: offline scrub didn't fail.
+keys[5].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[5].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[5].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[5].extentflag_hi = add: offline scrub didn't fail.
+keys[5].extentflag_hi = sub: offline scrub didn't fail.
+keys[5].attrfork_hi = ones: offline scrub didn't fail.
+keys[5].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[5].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[5].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[5].attrfork_hi = add: offline scrub didn't fail.
+keys[5].attrfork_hi = sub: offline scrub didn't fail.
+keys[5].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[5].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[5].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[5].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[5].bmbtblock_hi = add: offline scrub didn't fail.
+keys[5].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[6].owner = zeroes: offline scrub didn't fail.
+keys[6].owner = sub: offline scrub didn't fail.
+keys[6].offset = zeroes: offline scrub didn't fail.
+keys[6].offset = lastbit: offline scrub didn't fail.
+keys[6].extentflag = ones: offline scrub didn't fail.
+keys[6].extentflag = firstbit: offline scrub didn't fail.
+keys[6].extentflag = middlebit: offline scrub didn't fail.
+keys[6].extentflag = lastbit: offline scrub didn't fail.
+keys[6].extentflag = add: offline scrub didn't fail.
+keys[6].extentflag = sub: offline scrub didn't fail.
+keys[6].startblock_hi = ones: offline scrub didn't fail.
+keys[6].startblock_hi = firstbit: offline scrub didn't fail.
+keys[6].startblock_hi = middlebit: offline scrub didn't fail.
+keys[6].startblock_hi = lastbit: offline scrub didn't fail.
+keys[6].startblock_hi = add: offline scrub didn't fail.
+keys[6].owner_hi = ones: offline scrub didn't fail.
+keys[6].owner_hi = firstbit: offline scrub didn't fail.
+keys[6].owner_hi = middlebit: offline scrub didn't fail.
+keys[6].owner_hi = lastbit: offline scrub didn't fail.
+keys[6].owner_hi = add: offline scrub didn't fail.
+keys[6].offset_hi = ones: offline scrub didn't fail.
+keys[6].offset_hi = firstbit: offline scrub didn't fail.
+keys[6].offset_hi = middlebit: offline scrub didn't fail.
+keys[6].offset_hi = add: offline scrub didn't fail.
+keys[6].offset_hi = sub: offline scrub didn't fail.
+keys[6].extentflag_hi = ones: offline scrub didn't fail.
+keys[6].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[6].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[6].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[6].extentflag_hi = add: offline scrub didn't fail.
+keys[6].extentflag_hi = sub: offline scrub didn't fail.
+keys[6].attrfork_hi = ones: offline scrub didn't fail.
+keys[6].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[6].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[6].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[6].attrfork_hi = add: offline scrub didn't fail.
+keys[6].attrfork_hi = sub: offline scrub didn't fail.
+keys[6].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[6].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[6].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[6].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[6].bmbtblock_hi = add: offline scrub didn't fail.
+keys[6].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[7].owner = zeroes: offline scrub didn't fail.
+keys[7].owner = lastbit: offline scrub didn't fail.
+keys[7].owner = sub: offline scrub didn't fail.
+keys[7].offset = zeroes: offline scrub didn't fail.
+keys[7].offset = lastbit: offline scrub didn't fail.
+keys[7].extentflag = ones: offline scrub didn't fail.
+keys[7].extentflag = firstbit: offline scrub didn't fail.
+keys[7].extentflag = middlebit: offline scrub didn't fail.
+keys[7].extentflag = lastbit: offline scrub didn't fail.
+keys[7].extentflag = add: offline scrub didn't fail.
+keys[7].extentflag = sub: offline scrub didn't fail.
+keys[7].startblock_hi = ones: offline scrub didn't fail.
+keys[7].startblock_hi = firstbit: offline scrub didn't fail.
+keys[7].startblock_hi = middlebit: offline scrub didn't fail.
+keys[7].startblock_hi = lastbit: offline scrub didn't fail.
+keys[7].startblock_hi = add: offline scrub didn't fail.
+keys[7].owner_hi = ones: offline scrub didn't fail.
+keys[7].owner_hi = firstbit: offline scrub didn't fail.
+keys[7].owner_hi = middlebit: offline scrub didn't fail.
+keys[7].owner_hi = add: offline scrub didn't fail.
+keys[7].offset_hi = ones: offline scrub didn't fail.
+keys[7].offset_hi = firstbit: offline scrub didn't fail.
+keys[7].offset_hi = middlebit: offline scrub didn't fail.
+keys[7].offset_hi = add: offline scrub didn't fail.
+keys[7].offset_hi = sub: offline scrub didn't fail.
+keys[7].extentflag_hi = ones: offline scrub didn't fail.
+keys[7].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[7].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[7].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[7].extentflag_hi = add: offline scrub didn't fail.
+keys[7].extentflag_hi = sub: offline scrub didn't fail.
+keys[7].attrfork_hi = ones: offline scrub didn't fail.
+keys[7].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[7].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[7].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[7].attrfork_hi = add: offline scrub didn't fail.
+keys[7].attrfork_hi = sub: offline scrub didn't fail.
+keys[7].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[7].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[7].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[7].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[7].bmbtblock_hi = add: offline scrub didn't fail.
+keys[7].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[8].owner = zeroes: offline scrub didn't fail.
+keys[8].owner = lastbit: offline scrub didn't fail.
+keys[8].owner = sub: offline scrub didn't fail.
+keys[8].offset = zeroes: offline scrub didn't fail.
+keys[8].offset = lastbit: offline scrub didn't fail.
+keys[8].extentflag = ones: offline scrub didn't fail.
+keys[8].extentflag = firstbit: offline scrub didn't fail.
+keys[8].extentflag = middlebit: offline scrub didn't fail.
+keys[8].extentflag = lastbit: offline scrub didn't fail.
+keys[8].extentflag = add: offline scrub didn't fail.
+keys[8].extentflag = sub: offline scrub didn't fail.
+keys[8].startblock_hi = ones: offline scrub didn't fail.
+keys[8].startblock_hi = firstbit: offline scrub didn't fail.
+keys[8].startblock_hi = middlebit: offline scrub didn't fail.
+keys[8].startblock_hi = lastbit: offline scrub didn't fail.
+keys[8].startblock_hi = add: offline scrub didn't fail.
+keys[8].owner_hi = ones: offline scrub didn't fail.
+keys[8].owner_hi = firstbit: offline scrub didn't fail.
+keys[8].owner_hi = middlebit: offline scrub didn't fail.
+keys[8].owner_hi = lastbit: offline scrub didn't fail.
+keys[8].owner_hi = add: offline scrub didn't fail.
+keys[8].offset_hi = ones: offline scrub didn't fail.
+keys[8].offset_hi = firstbit: offline scrub didn't fail.
+keys[8].offset_hi = middlebit: offline scrub didn't fail.
+keys[8].offset_hi = add: offline scrub didn't fail.
+keys[8].offset_hi = sub: offline scrub didn't fail.
+keys[8].extentflag_hi = ones: offline scrub didn't fail.
+keys[8].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[8].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[8].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[8].extentflag_hi = add: offline scrub didn't fail.
+keys[8].extentflag_hi = sub: offline scrub didn't fail.
+keys[8].attrfork_hi = ones: offline scrub didn't fail.
+keys[8].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[8].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[8].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[8].attrfork_hi = add: offline scrub didn't fail.
+keys[8].attrfork_hi = sub: offline scrub didn't fail.
+keys[8].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[8].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[8].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[8].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[8].bmbtblock_hi = add: offline scrub didn't fail.
+keys[8].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[9].owner = zeroes: offline scrub didn't fail.
+keys[9].owner = sub: offline scrub didn't fail.
+keys[9].offset = zeroes: offline scrub didn't fail.
+keys[9].offset = lastbit: offline scrub didn't fail.
+keys[9].extentflag = ones: offline scrub didn't fail.
+keys[9].extentflag = firstbit: offline scrub didn't fail.
+keys[9].extentflag = middlebit: offline scrub didn't fail.
+keys[9].extentflag = lastbit: offline scrub didn't fail.
+keys[9].extentflag = add: offline scrub didn't fail.
+keys[9].extentflag = sub: offline scrub didn't fail.
+keys[9].startblock_hi = ones: offline scrub didn't fail.
+keys[9].startblock_hi = firstbit: offline scrub didn't fail.
+keys[9].startblock_hi = middlebit: offline scrub didn't fail.
+keys[9].startblock_hi = lastbit: offline scrub didn't fail.
+keys[9].startblock_hi = add: offline scrub didn't fail.
+keys[9].owner_hi = ones: offline scrub didn't fail.
+keys[9].owner_hi = firstbit: offline scrub didn't fail.
+keys[9].owner_hi = middlebit: offline scrub didn't fail.
+keys[9].owner_hi = lastbit: offline scrub didn't fail.
+keys[9].owner_hi = add: offline scrub didn't fail.
+keys[9].offset_hi = ones: offline scrub didn't fail.
+keys[9].offset_hi = firstbit: offline scrub didn't fail.
+keys[9].offset_hi = middlebit: offline scrub didn't fail.
+keys[9].offset_hi = add: offline scrub didn't fail.
+keys[9].offset_hi = sub: offline scrub didn't fail.
+keys[9].extentflag_hi = ones: offline scrub didn't fail.
+keys[9].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[9].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[9].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[9].extentflag_hi = add: offline scrub didn't fail.
+keys[9].extentflag_hi = sub: offline scrub didn't fail.
+keys[9].attrfork_hi = ones: offline scrub didn't fail.
+keys[9].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[9].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[9].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[9].attrfork_hi = add: offline scrub didn't fail.
+keys[9].attrfork_hi = sub: offline scrub didn't fail.
+keys[9].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[9].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[9].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[9].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[9].bmbtblock_hi = add: offline scrub didn't fail.
+keys[9].bmbtblock_hi = sub: offline scrub didn't fail.
 Done fuzzing rmapbt keyptr
diff --git a/tests/xfs/372.out b/tests/xfs/372.out
index da95f3d5eb..45fcdfc61f 100644
--- a/tests/xfs/372.out
+++ b/tests/xfs/372.out
@@ -1,4 +1,9 @@
 QA output created by 372
 Format and populate
 Fuzz refcountbt
+leftsib = add: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
+keys[1].startblock = zeroes: offline scrub didn't fail.
+keys[1].startblock = lastbit: offline scrub didn't fail.
+keys[1].startblock = sub: offline scrub didn't fail.
 Done fuzzing refcountbt
diff --git a/tests/xfs/374.out b/tests/xfs/374.out
index 853d07a90b..116a4c17ec 100644
--- a/tests/xfs/374.out
+++ b/tests/xfs/374.out
@@ -2,4 +2,39 @@ QA output created by 374
 Format and populate
 Find btree-format dir inode
 Fuzz inode
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+core.size = middlebit: offline scrub didn't fail.
+core.size = middlebit: online post-mod scrub failed (4).
+core.size = lastbit: offline scrub didn't fail.
+core.size = add: offline scrub didn't fail.
+core.size = sub: offline scrub didn't fail.
+core.rtinherit = ones: offline scrub didn't fail.
+core.rtinherit = firstbit: offline scrub didn't fail.
+core.rtinherit = middlebit: offline scrub didn't fail.
+core.rtinherit = lastbit: offline scrub didn't fail.
+core.rtinherit = add: offline scrub didn't fail.
+core.rtinherit = sub: offline scrub didn't fail.
+core.projinherit = ones: offline scrub didn't fail.
+core.projinherit = firstbit: offline scrub didn't fail.
+core.projinherit = middlebit: offline scrub didn't fail.
+core.projinherit = lastbit: offline scrub didn't fail.
+core.projinherit = add: offline scrub didn't fail.
+core.projinherit = sub: offline scrub didn't fail.
+core.nosymlinks = ones: offline scrub didn't fail.
+core.nosymlinks = firstbit: offline scrub didn't fail.
+core.nosymlinks = middlebit: offline scrub didn't fail.
+core.nosymlinks = lastbit: offline scrub didn't fail.
+core.nosymlinks = add: offline scrub didn't fail.
+core.nosymlinks = sub: offline scrub didn't fail.
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.flags2 = lastbit: offline scrub didn't fail.
+u3.bmbt.ptrs[1] = firstbit: offline scrub didn't fail.
 Done fuzzing inode
diff --git a/tests/xfs/376.out b/tests/xfs/376.out
index 40f360e97f..de52138584 100644
--- a/tests/xfs/376.out
+++ b/tests/xfs/376.out
@@ -2,4 +2,26 @@ QA output created by 376
 Format and populate
 Find extents-format file inode
 Fuzz inode
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+core.size = zeroes: offline scrub didn't fail.
+core.size = middlebit: offline scrub didn't fail.
+core.size = lastbit: offline scrub didn't fail.
+core.size = add: offline scrub didn't fail.
+core.size = sub: offline scrub didn't fail.
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.flags2 = lastbit: offline scrub didn't fail.
+v3.reflink = ones: offline scrub didn't fail.
+v3.reflink = firstbit: offline scrub didn't fail.
+v3.reflink = middlebit: offline scrub didn't fail.
+v3.reflink = lastbit: offline scrub didn't fail.
+v3.reflink = add: offline scrub didn't fail.
+v3.reflink = sub: offline scrub didn't fail.
 Done fuzzing inode
diff --git a/tests/xfs/378.out b/tests/xfs/378.out
index f0b1c640d8..04a10ba1c4 100644
--- a/tests/xfs/378.out
+++ b/tests/xfs/378.out
@@ -2,4 +2,26 @@ QA output created by 378
 Format and populate
 Find btree-format file inode
 Fuzz inode
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+core.size = zeroes: offline scrub didn't fail.
+core.size = middlebit: offline scrub didn't fail.
+core.size = lastbit: offline scrub didn't fail.
+core.size = add: offline scrub didn't fail.
+core.size = sub: offline scrub didn't fail.
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.flags2 = lastbit: offline scrub didn't fail.
+v3.reflink = ones: offline scrub didn't fail.
+v3.reflink = firstbit: offline scrub didn't fail.
+v3.reflink = middlebit: offline scrub didn't fail.
+v3.reflink = lastbit: offline scrub didn't fail.
+v3.reflink = add: offline scrub didn't fail.
+v3.reflink = sub: offline scrub didn't fail.
 Done fuzzing inode
diff --git a/tests/xfs/382.out b/tests/xfs/382.out
index 255bd382db..a20d560f74 100644
--- a/tests/xfs/382.out
+++ b/tests/xfs/382.out
@@ -2,4 +2,8 @@ QA output created by 382
 Format and populate
 Find symlink remote block
 Fuzz symlink remote block
+data = ones: offline scrub didn't fail.
+data = firstbit: offline scrub didn't fail.
+data = middlebit: offline scrub didn't fail.
+data = lastbit: offline scrub didn't fail.
 Done fuzzing symlink remote block
diff --git a/tests/xfs/384.out b/tests/xfs/384.out
index 6d0a6ae14a..3b11cb3f7d 100644
--- a/tests/xfs/384.out
+++ b/tests/xfs/384.out
@@ -2,4 +2,42 @@ QA output created by 384
 Format and populate
 Find inline-format dir inode
 Fuzz inline-format dir inode
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+core.rtinherit = ones: offline scrub didn't fail.
+core.rtinherit = firstbit: offline scrub didn't fail.
+core.rtinherit = middlebit: offline scrub didn't fail.
+core.rtinherit = lastbit: offline scrub didn't fail.
+core.rtinherit = add: offline scrub didn't fail.
+core.rtinherit = sub: offline scrub didn't fail.
+core.projinherit = ones: offline scrub didn't fail.
+core.projinherit = firstbit: offline scrub didn't fail.
+core.projinherit = middlebit: offline scrub didn't fail.
+core.projinherit = lastbit: offline scrub didn't fail.
+core.projinherit = add: offline scrub didn't fail.
+core.projinherit = sub: offline scrub didn't fail.
+core.nosymlinks = ones: offline scrub didn't fail.
+core.nosymlinks = firstbit: offline scrub didn't fail.
+core.nosymlinks = middlebit: offline scrub didn't fail.
+core.nosymlinks = lastbit: offline scrub didn't fail.
+core.nosymlinks = add: offline scrub didn't fail.
+core.nosymlinks = sub: offline scrub didn't fail.
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.flags2 = lastbit: offline scrub didn't fail.
+v3.nrext64 = zeroes: offline scrub didn't fail.
+v3.nrext64 = firstbit: offline scrub didn't fail.
+v3.nrext64 = middlebit: offline scrub didn't fail.
+v3.nrext64 = lastbit: offline scrub didn't fail.
+v3.nrext64 = add: offline scrub didn't fail.
+v3.nrext64 = sub: offline scrub didn't fail.
+u3.sfdir3.list[1].offset = middlebit: offline scrub didn't fail.
+u3.sfdir3.list[1].offset = lastbit: offline scrub didn't fail.
+u3.sfdir3.list[1].offset = add: offline scrub didn't fail.
 Done fuzzing inline-format dir inode
diff --git a/tests/xfs/386.out b/tests/xfs/386.out
index a1f1afc8a6..9d9f9c6818 100644
--- a/tests/xfs/386.out
+++ b/tests/xfs/386.out
@@ -2,4 +2,32 @@ QA output created by 386
 Format and populate
 Find data-format dir block
 Fuzz data-format dir block
+bhdr.hdr.crc = zeroes: offline scrub didn't fail.
+bhdr.hdr.crc = ones: offline scrub didn't fail.
+bhdr.hdr.crc = firstbit: offline scrub didn't fail.
+bhdr.hdr.crc = middlebit: offline scrub didn't fail.
+bhdr.hdr.crc = lastbit: offline scrub didn't fail.
+bhdr.hdr.crc = add: offline scrub didn't fail.
+bhdr.hdr.crc = sub: offline scrub didn't fail.
+bhdr.hdr.owner = zeroes: offline re-scrub failed (1).
+bhdr.hdr.owner = zeroes: online post-mod scrub failed (1).
+bhdr.hdr.owner = zeroes: offline post-mod scrub failed (1).
+bhdr.hdr.owner = ones: offline re-scrub failed (1).
+bhdr.hdr.owner = ones: online post-mod scrub failed (1).
+bhdr.hdr.owner = ones: offline post-mod scrub failed (1).
+bhdr.hdr.owner = firstbit: offline re-scrub failed (1).
+bhdr.hdr.owner = firstbit: online post-mod scrub failed (1).
+bhdr.hdr.owner = firstbit: offline post-mod scrub failed (1).
+bhdr.hdr.owner = middlebit: offline re-scrub failed (1).
+bhdr.hdr.owner = middlebit: online post-mod scrub failed (1).
+bhdr.hdr.owner = middlebit: offline post-mod scrub failed (1).
+bhdr.hdr.owner = lastbit: offline re-scrub failed (1).
+bhdr.hdr.owner = lastbit: online post-mod scrub failed (1).
+bhdr.hdr.owner = lastbit: offline post-mod scrub failed (1).
+bhdr.hdr.owner = add: offline re-scrub failed (1).
+bhdr.hdr.owner = add: online post-mod scrub failed (1).
+bhdr.hdr.owner = add: offline post-mod scrub failed (1).
+bhdr.hdr.owner = sub: offline re-scrub failed (1).
+bhdr.hdr.owner = sub: online post-mod scrub failed (1).
+bhdr.hdr.owner = sub: offline post-mod scrub failed (1).
 Done fuzzing data-format dir block
diff --git a/tests/xfs/388.out b/tests/xfs/388.out
index 175d3b46f2..4848c6c9de 100644
--- a/tests/xfs/388.out
+++ b/tests/xfs/388.out
@@ -2,4 +2,539 @@ QA output created by 388
 Format and populate
 Find data-format dir block
 Fuzz data-format dir block
+dhdr.hdr.crc = zeroes: offline scrub didn't fail.
+dhdr.hdr.crc = ones: offline scrub didn't fail.
+dhdr.hdr.crc = firstbit: offline scrub didn't fail.
+dhdr.hdr.crc = middlebit: offline scrub didn't fail.
+dhdr.hdr.crc = lastbit: offline scrub didn't fail.
+dhdr.hdr.crc = add: offline scrub didn't fail.
+dhdr.hdr.crc = sub: offline scrub didn't fail.
+dhdr.hdr.bno = zeroes: offline re-scrub failed (1).
+dhdr.hdr.bno = zeroes: online post-mod scrub failed (1).
+dhdr.hdr.bno = zeroes: offline post-mod scrub failed (1).
+dhdr.hdr.bno = ones: offline re-scrub failed (1).
+dhdr.hdr.bno = ones: online post-mod scrub failed (1).
+dhdr.hdr.bno = ones: offline post-mod scrub failed (1).
+dhdr.hdr.bno = firstbit: offline re-scrub failed (1).
+dhdr.hdr.bno = firstbit: online post-mod scrub failed (1).
+dhdr.hdr.bno = firstbit: offline post-mod scrub failed (1).
+dhdr.hdr.bno = middlebit: offline re-scrub failed (1).
+dhdr.hdr.bno = middlebit: online post-mod scrub failed (1).
+dhdr.hdr.bno = middlebit: offline post-mod scrub failed (1).
+dhdr.hdr.bno = lastbit: offline re-scrub failed (1).
+dhdr.hdr.bno = lastbit: online post-mod scrub failed (1).
+dhdr.hdr.bno = lastbit: offline post-mod scrub failed (1).
+dhdr.hdr.bno = add: offline re-scrub failed (1).
+dhdr.hdr.bno = add: online post-mod scrub failed (1).
+dhdr.hdr.bno = add: offline post-mod scrub failed (1).
+dhdr.hdr.bno = sub: offline re-scrub failed (1).
+dhdr.hdr.bno = sub: online post-mod scrub failed (1).
+dhdr.hdr.bno = sub: offline post-mod scrub failed (1).
+dhdr.hdr.uuid = zeroes: offline re-scrub failed (1).
+dhdr.hdr.uuid = zeroes: online post-mod scrub failed (1).
+dhdr.hdr.uuid = zeroes: offline post-mod scrub failed (1).
+dhdr.hdr.uuid = ones: offline re-scrub failed (1).
+dhdr.hdr.uuid = ones: online post-mod scrub failed (1).
+dhdr.hdr.uuid = ones: offline post-mod scrub failed (1).
+dhdr.hdr.uuid = firstbit: offline re-scrub failed (1).
+dhdr.hdr.uuid = firstbit: online post-mod scrub failed (1).
+dhdr.hdr.uuid = firstbit: offline post-mod scrub failed (1).
+dhdr.hdr.uuid = middlebit: offline re-scrub failed (1).
+dhdr.hdr.uuid = middlebit: online post-mod scrub failed (1).
+dhdr.hdr.uuid = middlebit: offline post-mod scrub failed (1).
+dhdr.hdr.uuid = lastbit: offline re-scrub failed (1).
+dhdr.hdr.uuid = lastbit: online post-mod scrub failed (1).
+dhdr.hdr.uuid = lastbit: offline post-mod scrub failed (1).
+dhdr.hdr.owner = zeroes: offline re-scrub failed (1).
+dhdr.hdr.owner = zeroes: online post-mod scrub failed (1).
+dhdr.hdr.owner = zeroes: offline post-mod scrub failed (1).
+dhdr.hdr.owner = ones: offline re-scrub failed (1).
+dhdr.hdr.owner = ones: online post-mod scrub failed (1).
+dhdr.hdr.owner = ones: offline post-mod scrub failed (1).
+dhdr.hdr.owner = firstbit: offline re-scrub failed (1).
+dhdr.hdr.owner = firstbit: online post-mod scrub failed (1).
+dhdr.hdr.owner = firstbit: offline post-mod scrub failed (1).
+dhdr.hdr.owner = middlebit: offline re-scrub failed (1).
+dhdr.hdr.owner = middlebit: online post-mod scrub failed (1).
+dhdr.hdr.owner = middlebit: offline post-mod scrub failed (1).
+dhdr.hdr.owner = lastbit: offline re-scrub failed (1).
+dhdr.hdr.owner = lastbit: online post-mod scrub failed (1).
+dhdr.hdr.owner = lastbit: offline post-mod scrub failed (1).
+dhdr.hdr.owner = add: offline re-scrub failed (1).
+dhdr.hdr.owner = add: online post-mod scrub failed (1).
+dhdr.hdr.owner = add: offline post-mod scrub failed (1).
+dhdr.hdr.owner = sub: offline re-scrub failed (1).
+dhdr.hdr.owner = sub: online post-mod scrub failed (1).
+dhdr.hdr.owner = sub: offline post-mod scrub failed (1).
+du[0].inumber = ones: offline re-scrub failed (1).
+du[0].inumber = ones: online post-mod scrub failed (1).
+du[0].inumber = ones: offline post-mod scrub failed (1).
+du[0].inumber = sub: offline re-scrub failed (1).
+du[0].inumber = sub: online post-mod scrub failed (1).
+du[0].inumber = sub: offline post-mod scrub failed (1).
+du[0].namelen = zeroes: offline re-scrub failed (1).
+du[0].namelen = zeroes: online post-mod scrub failed (1).
+du[0].namelen = zeroes: offline post-mod scrub failed (1).
+du[0].namelen = ones: offline re-scrub failed (1).
+du[0].namelen = ones: online post-mod scrub failed (1).
+du[0].namelen = ones: offline post-mod scrub failed (1).
+du[0].namelen = firstbit: offline re-scrub failed (1).
+du[0].namelen = firstbit: online post-mod scrub failed (1).
+du[0].namelen = firstbit: offline post-mod scrub failed (1).
+du[0].namelen = middlebit: offline re-scrub failed (1).
+du[0].namelen = middlebit: online post-mod scrub failed (1).
+du[0].namelen = middlebit: offline post-mod scrub failed (1).
+du[0].namelen = lastbit: offline re-scrub failed (1).
+du[0].namelen = lastbit: online post-mod scrub failed (1).
+du[0].namelen = lastbit: offline post-mod scrub failed (1).
+du[0].namelen = add: offline re-scrub failed (1).
+du[0].namelen = add: online post-mod scrub failed (1).
+du[0].namelen = add: offline post-mod scrub failed (1).
+du[0].namelen = sub: offline re-scrub failed (1).
+du[0].namelen = sub: online post-mod scrub failed (1).
+du[0].namelen = sub: offline post-mod scrub failed (1).
+du[0].name = zeroes: offline re-scrub failed (1).
+du[0].name = zeroes: online post-mod scrub failed (1).
+du[0].name = zeroes: offline post-mod scrub failed (1).
+du[0].name = ones: offline re-scrub failed (1).
+du[0].name = ones: online post-mod scrub failed (1).
+du[0].name = ones: offline post-mod scrub failed (1).
+du[0].name = firstbit: offline re-scrub failed (1).
+du[0].name = firstbit: online post-mod scrub failed (1).
+du[0].name = firstbit: offline post-mod scrub failed (1).
+du[0].name = middlebit: offline re-scrub failed (1).
+du[0].name = middlebit: online post-mod scrub failed (1).
+du[0].name = middlebit: offline post-mod scrub failed (1).
+du[0].name = lastbit: offline re-scrub failed (1).
+du[0].name = lastbit: online post-mod scrub failed (1).
+du[0].name = lastbit: offline post-mod scrub failed (1).
+du[0].name = add: offline re-scrub failed (1).
+du[0].name = add: online post-mod scrub failed (1).
+du[0].name = add: offline post-mod scrub failed (1).
+du[0].name = sub: offline re-scrub failed (1).
+du[0].name = sub: online post-mod scrub failed (1).
+du[0].name = sub: offline post-mod scrub failed (1).
+du[0].tag = zeroes: offline re-scrub failed (1).
+du[0].tag = zeroes: online post-mod scrub failed (1).
+du[0].tag = zeroes: offline post-mod scrub failed (1).
+du[0].tag = ones: offline re-scrub failed (1).
+du[0].tag = ones: online post-mod scrub failed (1).
+du[0].tag = ones: offline post-mod scrub failed (1).
+du[0].tag = firstbit: offline re-scrub failed (1).
+du[0].tag = firstbit: online post-mod scrub failed (1).
+du[0].tag = firstbit: offline post-mod scrub failed (1).
+du[0].tag = middlebit: offline re-scrub failed (1).
+du[0].tag = middlebit: online post-mod scrub failed (1).
+du[0].tag = middlebit: offline post-mod scrub failed (1).
+du[0].tag = lastbit: offline re-scrub failed (1).
+du[0].tag = lastbit: online post-mod scrub failed (1).
+du[0].tag = lastbit: offline post-mod scrub failed (1).
+du[0].tag = add: offline re-scrub failed (1).
+du[0].tag = add: online post-mod scrub failed (1).
+du[0].tag = add: offline post-mod scrub failed (1).
+du[0].tag = sub: offline re-scrub failed (1).
+du[0].tag = sub: online post-mod scrub failed (1).
+du[0].tag = sub: offline post-mod scrub failed (1).
+du[1].inumber = ones: offline re-scrub failed (1).
+du[1].inumber = ones: online post-mod scrub failed (1).
+du[1].inumber = ones: offline post-mod scrub failed (1).
+du[1].inumber = sub: offline re-scrub failed (1).
+du[1].inumber = sub: online post-mod scrub failed (1).
+du[1].inumber = sub: offline post-mod scrub failed (1).
+du[1].namelen = ones: offline re-scrub failed (1).
+du[1].namelen = ones: online post-mod scrub failed (1).
+du[1].namelen = ones: offline post-mod scrub failed (1).
+du[1].namelen = firstbit: offline re-scrub failed (1).
+du[1].namelen = firstbit: online post-mod scrub failed (1).
+du[1].namelen = firstbit: offline post-mod scrub failed (1).
+du[1].namelen = middlebit: offline re-scrub failed (1).
+du[1].namelen = middlebit: online post-mod scrub failed (1).
+du[1].namelen = middlebit: offline post-mod scrub failed (1).
+du[1].namelen = add: offline re-scrub failed (1).
+du[1].namelen = add: online post-mod scrub failed (1).
+du[1].namelen = add: offline post-mod scrub failed (1).
+du[1].namelen = sub: offline re-scrub failed (1).
+du[1].namelen = sub: online post-mod scrub failed (1).
+du[1].namelen = sub: offline post-mod scrub failed (1).
+du[1].tag = zeroes: offline re-scrub failed (1).
+du[1].tag = zeroes: online post-mod scrub failed (1).
+du[1].tag = zeroes: offline post-mod scrub failed (1).
+du[1].tag = ones: offline re-scrub failed (1).
+du[1].tag = ones: online post-mod scrub failed (1).
+du[1].tag = ones: offline post-mod scrub failed (1).
+du[1].tag = firstbit: offline re-scrub failed (1).
+du[1].tag = firstbit: online post-mod scrub failed (1).
+du[1].tag = firstbit: offline post-mod scrub failed (1).
+du[1].tag = middlebit: offline re-scrub failed (1).
+du[1].tag = middlebit: online post-mod scrub failed (1).
+du[1].tag = middlebit: offline post-mod scrub failed (1).
+du[1].tag = lastbit: offline re-scrub failed (1).
+du[1].tag = lastbit: online post-mod scrub failed (1).
+du[1].tag = lastbit: offline post-mod scrub failed (1).
+du[1].tag = add: offline re-scrub failed (1).
+du[1].tag = add: online post-mod scrub failed (1).
+du[1].tag = add: offline post-mod scrub failed (1).
+du[1].tag = sub: offline re-scrub failed (1).
+du[1].tag = sub: online post-mod scrub failed (1).
+du[1].tag = sub: offline post-mod scrub failed (1).
+du[2].inumber = ones: offline re-scrub failed (1).
+du[2].inumber = ones: online post-mod scrub failed (1).
+du[2].inumber = ones: offline post-mod scrub failed (1).
+du[2].inumber = sub: offline re-scrub failed (1).
+du[2].inumber = sub: online post-mod scrub failed (1).
+du[2].inumber = sub: offline post-mod scrub failed (1).
+du[2].namelen = zeroes: offline re-scrub failed (1).
+du[2].namelen = zeroes: online post-mod scrub failed (1).
+du[2].namelen = zeroes: offline post-mod scrub failed (1).
+du[2].namelen = ones: offline re-scrub failed (1).
+du[2].namelen = ones: online post-mod scrub failed (1).
+du[2].namelen = ones: offline post-mod scrub failed (1).
+du[2].namelen = firstbit: offline re-scrub failed (1).
+du[2].namelen = firstbit: online post-mod scrub failed (1).
+du[2].namelen = firstbit: offline post-mod scrub failed (1).
+du[2].namelen = middlebit: offline re-scrub failed (1).
+du[2].namelen = middlebit: online post-mod scrub failed (1).
+du[2].namelen = middlebit: offline post-mod scrub failed (1).
+du[2].namelen = add: offline re-scrub failed (1).
+du[2].namelen = add: online post-mod scrub failed (1).
+du[2].namelen = add: offline post-mod scrub failed (1).
+du[2].namelen = sub: offline re-scrub failed (1).
+du[2].namelen = sub: online post-mod scrub failed (1).
+du[2].namelen = sub: offline post-mod scrub failed (1).
+du[2].tag = zeroes: offline re-scrub failed (1).
+du[2].tag = zeroes: online post-mod scrub failed (1).
+du[2].tag = zeroes: offline post-mod scrub failed (1).
+du[2].tag = ones: offline re-scrub failed (1).
+du[2].tag = ones: online post-mod scrub failed (1).
+du[2].tag = ones: offline post-mod scrub failed (1).
+du[2].tag = firstbit: offline re-scrub failed (1).
+du[2].tag = firstbit: online post-mod scrub failed (1).
+du[2].tag = firstbit: offline post-mod scrub failed (1).
+du[2].tag = middlebit: offline re-scrub failed (1).
+du[2].tag = middlebit: online post-mod scrub failed (1).
+du[2].tag = middlebit: offline post-mod scrub failed (1).
+du[2].tag = lastbit: offline re-scrub failed (1).
+du[2].tag = lastbit: online post-mod scrub failed (1).
+du[2].tag = lastbit: offline post-mod scrub failed (1).
+du[2].tag = add: offline re-scrub failed (1).
+du[2].tag = add: online post-mod scrub failed (1).
+du[2].tag = add: offline post-mod scrub failed (1).
+du[2].tag = sub: offline re-scrub failed (1).
+du[2].tag = sub: online post-mod scrub failed (1).
+du[2].tag = sub: offline post-mod scrub failed (1).
+du[3].inumber = ones: offline re-scrub failed (1).
+du[3].inumber = ones: online post-mod scrub failed (1).
+du[3].inumber = ones: offline post-mod scrub failed (1).
+du[3].inumber = sub: offline re-scrub failed (1).
+du[3].inumber = sub: online post-mod scrub failed (1).
+du[3].inumber = sub: offline post-mod scrub failed (1).
+du[3].namelen = zeroes: offline re-scrub failed (1).
+du[3].namelen = zeroes: online post-mod scrub failed (1).
+du[3].namelen = zeroes: offline post-mod scrub failed (1).
+du[3].namelen = ones: offline re-scrub failed (1).
+du[3].namelen = ones: online post-mod scrub failed (1).
+du[3].namelen = ones: offline post-mod scrub failed (1).
+du[3].namelen = firstbit: offline re-scrub failed (1).
+du[3].namelen = firstbit: online post-mod scrub failed (1).
+du[3].namelen = firstbit: offline post-mod scrub failed (1).
+du[3].namelen = middlebit: offline re-scrub failed (1).
+du[3].namelen = middlebit: online post-mod scrub failed (1).
+du[3].namelen = middlebit: offline post-mod scrub failed (1).
+du[3].namelen = add: offline re-scrub failed (1).
+du[3].namelen = add: online post-mod scrub failed (1).
+du[3].namelen = add: offline post-mod scrub failed (1).
+du[3].namelen = sub: offline re-scrub failed (1).
+du[3].namelen = sub: online post-mod scrub failed (1).
+du[3].namelen = sub: offline post-mod scrub failed (1).
+du[3].tag = zeroes: offline re-scrub failed (1).
+du[3].tag = zeroes: online post-mod scrub failed (1).
+du[3].tag = zeroes: offline post-mod scrub failed (1).
+du[3].tag = ones: offline re-scrub failed (1).
+du[3].tag = ones: online post-mod scrub failed (1).
+du[3].tag = ones: offline post-mod scrub failed (1).
+du[3].tag = firstbit: offline re-scrub failed (1).
+du[3].tag = firstbit: online post-mod scrub failed (1).
+du[3].tag = firstbit: offline post-mod scrub failed (1).
+du[3].tag = middlebit: offline re-scrub failed (1).
+du[3].tag = middlebit: online post-mod scrub failed (1).
+du[3].tag = middlebit: offline post-mod scrub failed (1).
+du[3].tag = lastbit: offline re-scrub failed (1).
+du[3].tag = lastbit: online post-mod scrub failed (1).
+du[3].tag = lastbit: offline post-mod scrub failed (1).
+du[3].tag = add: offline re-scrub failed (1).
+du[3].tag = add: online post-mod scrub failed (1).
+du[3].tag = add: offline post-mod scrub failed (1).
+du[3].tag = sub: offline re-scrub failed (1).
+du[3].tag = sub: online post-mod scrub failed (1).
+du[3].tag = sub: offline post-mod scrub failed (1).
+du[4].inumber = ones: offline re-scrub failed (1).
+du[4].inumber = ones: online post-mod scrub failed (1).
+du[4].inumber = ones: offline post-mod scrub failed (1).
+du[4].inumber = sub: offline re-scrub failed (1).
+du[4].inumber = sub: online post-mod scrub failed (1).
+du[4].inumber = sub: offline post-mod scrub failed (1).
+du[4].namelen = zeroes: offline re-scrub failed (1).
+du[4].namelen = zeroes: online post-mod scrub failed (1).
+du[4].namelen = zeroes: offline post-mod scrub failed (1).
+du[4].namelen = ones: offline re-scrub failed (1).
+du[4].namelen = ones: online post-mod scrub failed (1).
+du[4].namelen = ones: offline post-mod scrub failed (1).
+du[4].namelen = firstbit: offline re-scrub failed (1).
+du[4].namelen = firstbit: online post-mod scrub failed (1).
+du[4].namelen = firstbit: offline post-mod scrub failed (1).
+du[4].namelen = middlebit: offline re-scrub failed (1).
+du[4].namelen = middlebit: online post-mod scrub failed (1).
+du[4].namelen = middlebit: offline post-mod scrub failed (1).
+du[4].namelen = add: offline re-scrub failed (1).
+du[4].namelen = add: online post-mod scrub failed (1).
+du[4].namelen = add: offline post-mod scrub failed (1).
+du[4].namelen = sub: offline re-scrub failed (1).
+du[4].namelen = sub: online post-mod scrub failed (1).
+du[4].namelen = sub: offline post-mod scrub failed (1).
+du[4].tag = zeroes: offline re-scrub failed (1).
+du[4].tag = zeroes: online post-mod scrub failed (1).
+du[4].tag = zeroes: offline post-mod scrub failed (1).
+du[4].tag = ones: offline re-scrub failed (1).
+du[4].tag = ones: online post-mod scrub failed (1).
+du[4].tag = ones: offline post-mod scrub failed (1).
+du[4].tag = firstbit: offline re-scrub failed (1).
+du[4].tag = firstbit: online post-mod scrub failed (1).
+du[4].tag = firstbit: offline post-mod scrub failed (1).
+du[4].tag = middlebit: offline re-scrub failed (1).
+du[4].tag = middlebit: online post-mod scrub failed (1).
+du[4].tag = middlebit: offline post-mod scrub failed (1).
+du[4].tag = lastbit: offline re-scrub failed (1).
+du[4].tag = lastbit: online post-mod scrub failed (1).
+du[4].tag = lastbit: offline post-mod scrub failed (1).
+du[4].tag = add: offline re-scrub failed (1).
+du[4].tag = add: online post-mod scrub failed (1).
+du[4].tag = add: offline post-mod scrub failed (1).
+du[4].tag = sub: offline re-scrub failed (1).
+du[4].tag = sub: online post-mod scrub failed (1).
+du[4].tag = sub: offline post-mod scrub failed (1).
+du[5].inumber = ones: offline re-scrub failed (1).
+du[5].inumber = ones: online post-mod scrub failed (1).
+du[5].inumber = ones: offline post-mod scrub failed (1).
+du[5].inumber = sub: offline re-scrub failed (1).
+du[5].inumber = sub: online post-mod scrub failed (1).
+du[5].inumber = sub: offline post-mod scrub failed (1).
+du[5].namelen = zeroes: offline re-scrub failed (1).
+du[5].namelen = zeroes: online post-mod scrub failed (1).
+du[5].namelen = zeroes: offline post-mod scrub failed (1).
+du[5].namelen = ones: offline re-scrub failed (1).
+du[5].namelen = ones: online post-mod scrub failed (1).
+du[5].namelen = ones: offline post-mod scrub failed (1).
+du[5].namelen = firstbit: offline re-scrub failed (1).
+du[5].namelen = firstbit: online post-mod scrub failed (1).
+du[5].namelen = firstbit: offline post-mod scrub failed (1).
+du[5].namelen = middlebit: offline re-scrub failed (1).
+du[5].namelen = middlebit: online post-mod scrub failed (1).
+du[5].namelen = middlebit: offline post-mod scrub failed (1).
+du[5].namelen = add: offline re-scrub failed (1).
+du[5].namelen = add: online post-mod scrub failed (1).
+du[5].namelen = add: offline post-mod scrub failed (1).
+du[5].namelen = sub: offline re-scrub failed (1).
+du[5].namelen = sub: online post-mod scrub failed (1).
+du[5].namelen = sub: offline post-mod scrub failed (1).
+du[5].tag = zeroes: offline re-scrub failed (1).
+du[5].tag = zeroes: online post-mod scrub failed (1).
+du[5].tag = zeroes: offline post-mod scrub failed (1).
+du[5].tag = ones: offline re-scrub failed (1).
+du[5].tag = ones: online post-mod scrub failed (1).
+du[5].tag = ones: offline post-mod scrub failed (1).
+du[5].tag = firstbit: offline re-scrub failed (1).
+du[5].tag = firstbit: online post-mod scrub failed (1).
+du[5].tag = firstbit: offline post-mod scrub failed (1).
+du[5].tag = middlebit: offline re-scrub failed (1).
+du[5].tag = middlebit: online post-mod scrub failed (1).
+du[5].tag = middlebit: offline post-mod scrub failed (1).
+du[5].tag = lastbit: offline re-scrub failed (1).
+du[5].tag = lastbit: online post-mod scrub failed (1).
+du[5].tag = lastbit: offline post-mod scrub failed (1).
+du[5].tag = add: offline re-scrub failed (1).
+du[5].tag = add: online post-mod scrub failed (1).
+du[5].tag = add: offline post-mod scrub failed (1).
+du[5].tag = sub: offline re-scrub failed (1).
+du[5].tag = sub: online post-mod scrub failed (1).
+du[5].tag = sub: offline post-mod scrub failed (1).
+du[6].inumber = ones: offline re-scrub failed (1).
+du[6].inumber = ones: online post-mod scrub failed (1).
+du[6].inumber = ones: offline post-mod scrub failed (1).
+du[6].inumber = sub: offline re-scrub failed (1).
+du[6].inumber = sub: online post-mod scrub failed (1).
+du[6].inumber = sub: offline post-mod scrub failed (1).
+du[6].namelen = zeroes: offline re-scrub failed (1).
+du[6].namelen = zeroes: online post-mod scrub failed (1).
+du[6].namelen = zeroes: offline post-mod scrub failed (1).
+du[6].namelen = ones: offline re-scrub failed (1).
+du[6].namelen = ones: online post-mod scrub failed (1).
+du[6].namelen = ones: offline post-mod scrub failed (1).
+du[6].namelen = firstbit: offline re-scrub failed (1).
+du[6].namelen = firstbit: online post-mod scrub failed (1).
+du[6].namelen = firstbit: offline post-mod scrub failed (1).
+du[6].namelen = middlebit: offline re-scrub failed (1).
+du[6].namelen = middlebit: online post-mod scrub failed (1).
+du[6].namelen = middlebit: offline post-mod scrub failed (1).
+du[6].namelen = add: offline re-scrub failed (1).
+du[6].namelen = add: online post-mod scrub failed (1).
+du[6].namelen = add: offline post-mod scrub failed (1).
+du[6].namelen = sub: offline re-scrub failed (1).
+du[6].namelen = sub: online post-mod scrub failed (1).
+du[6].namelen = sub: offline post-mod scrub failed (1).
+du[6].tag = zeroes: offline re-scrub failed (1).
+du[6].tag = zeroes: online post-mod scrub failed (1).
+du[6].tag = zeroes: offline post-mod scrub failed (1).
+du[6].tag = ones: offline re-scrub failed (1).
+du[6].tag = ones: online post-mod scrub failed (1).
+du[6].tag = ones: offline post-mod scrub failed (1).
+du[6].tag = firstbit: offline re-scrub failed (1).
+du[6].tag = firstbit: online post-mod scrub failed (1).
+du[6].tag = firstbit: offline post-mod scrub failed (1).
+du[6].tag = middlebit: offline re-scrub failed (1).
+du[6].tag = middlebit: online post-mod scrub failed (1).
+du[6].tag = middlebit: offline post-mod scrub failed (1).
+du[6].tag = lastbit: offline re-scrub failed (1).
+du[6].tag = lastbit: online post-mod scrub failed (1).
+du[6].tag = lastbit: offline post-mod scrub failed (1).
+du[6].tag = add: offline re-scrub failed (1).
+du[6].tag = add: online post-mod scrub failed (1).
+du[6].tag = add: offline post-mod scrub failed (1).
+du[6].tag = sub: offline re-scrub failed (1).
+du[6].tag = sub: online post-mod scrub failed (1).
+du[6].tag = sub: offline post-mod scrub failed (1).
+du[7].inumber = ones: offline re-scrub failed (1).
+du[7].inumber = ones: online post-mod scrub failed (1).
+du[7].inumber = ones: offline post-mod scrub failed (1).
+du[7].inumber = sub: offline re-scrub failed (1).
+du[7].inumber = sub: online post-mod scrub failed (1).
+du[7].inumber = sub: offline post-mod scrub failed (1).
+du[7].namelen = zeroes: offline re-scrub failed (1).
+du[7].namelen = zeroes: online post-mod scrub failed (1).
+du[7].namelen = zeroes: offline post-mod scrub failed (1).
+du[7].namelen = ones: offline re-scrub failed (1).
+du[7].namelen = ones: online post-mod scrub failed (1).
+du[7].namelen = ones: offline post-mod scrub failed (1).
+du[7].namelen = firstbit: offline re-scrub failed (1).
+du[7].namelen = firstbit: online post-mod scrub failed (1).
+du[7].namelen = firstbit: offline post-mod scrub failed (1).
+du[7].namelen = middlebit: offline re-scrub failed (1).
+du[7].namelen = middlebit: online post-mod scrub failed (1).
+du[7].namelen = middlebit: offline post-mod scrub failed (1).
+du[7].namelen = add: offline re-scrub failed (1).
+du[7].namelen = add: online post-mod scrub failed (1).
+du[7].namelen = add: offline post-mod scrub failed (1).
+du[7].namelen = sub: offline re-scrub failed (1).
+du[7].namelen = sub: online post-mod scrub failed (1).
+du[7].namelen = sub: offline post-mod scrub failed (1).
+du[7].tag = zeroes: offline re-scrub failed (1).
+du[7].tag = zeroes: online post-mod scrub failed (1).
+du[7].tag = zeroes: offline post-mod scrub failed (1).
+du[7].tag = ones: offline re-scrub failed (1).
+du[7].tag = ones: online post-mod scrub failed (1).
+du[7].tag = ones: offline post-mod scrub failed (1).
+du[7].tag = firstbit: offline re-scrub failed (1).
+du[7].tag = firstbit: online post-mod scrub failed (1).
+du[7].tag = firstbit: offline post-mod scrub failed (1).
+du[7].tag = middlebit: offline re-scrub failed (1).
+du[7].tag = middlebit: online post-mod scrub failed (1).
+du[7].tag = middlebit: offline post-mod scrub failed (1).
+du[7].tag = lastbit: offline re-scrub failed (1).
+du[7].tag = lastbit: online post-mod scrub failed (1).
+du[7].tag = lastbit: offline post-mod scrub failed (1).
+du[7].tag = add: offline re-scrub failed (1).
+du[7].tag = add: online post-mod scrub failed (1).
+du[7].tag = add: offline post-mod scrub failed (1).
+du[7].tag = sub: offline re-scrub failed (1).
+du[7].tag = sub: online post-mod scrub failed (1).
+du[7].tag = sub: offline post-mod scrub failed (1).
+du[8].inumber = ones: offline re-scrub failed (1).
+du[8].inumber = ones: online post-mod scrub failed (1).
+du[8].inumber = ones: offline post-mod scrub failed (1).
+du[8].inumber = sub: offline re-scrub failed (1).
+du[8].inumber = sub: online post-mod scrub failed (1).
+du[8].inumber = sub: offline post-mod scrub failed (1).
+du[8].namelen = zeroes: offline re-scrub failed (1).
+du[8].namelen = zeroes: online post-mod scrub failed (1).
+du[8].namelen = zeroes: offline post-mod scrub failed (1).
+du[8].namelen = ones: offline re-scrub failed (1).
+du[8].namelen = ones: online post-mod scrub failed (1).
+du[8].namelen = ones: offline post-mod scrub failed (1).
+du[8].namelen = firstbit: offline re-scrub failed (1).
+du[8].namelen = firstbit: online post-mod scrub failed (1).
+du[8].namelen = firstbit: offline post-mod scrub failed (1).
+du[8].namelen = middlebit: offline re-scrub failed (1).
+du[8].namelen = middlebit: online post-mod scrub failed (1).
+du[8].namelen = middlebit: offline post-mod scrub failed (1).
+du[8].namelen = add: offline re-scrub failed (1).
+du[8].namelen = add: online post-mod scrub failed (1).
+du[8].namelen = add: offline post-mod scrub failed (1).
+du[8].namelen = sub: offline re-scrub failed (1).
+du[8].namelen = sub: online post-mod scrub failed (1).
+du[8].namelen = sub: offline post-mod scrub failed (1).
+du[8].tag = zeroes: offline re-scrub failed (1).
+du[8].tag = zeroes: online post-mod scrub failed (1).
+du[8].tag = zeroes: offline post-mod scrub failed (1).
+du[8].tag = ones: offline re-scrub failed (1).
+du[8].tag = ones: online post-mod scrub failed (1).
+du[8].tag = ones: offline post-mod scrub failed (1).
+du[8].tag = firstbit: offline re-scrub failed (1).
+du[8].tag = firstbit: online post-mod scrub failed (1).
+du[8].tag = firstbit: offline post-mod scrub failed (1).
+du[8].tag = middlebit: offline re-scrub failed (1).
+du[8].tag = middlebit: online post-mod scrub failed (1).
+du[8].tag = middlebit: offline post-mod scrub failed (1).
+du[8].tag = lastbit: offline re-scrub failed (1).
+du[8].tag = lastbit: online post-mod scrub failed (1).
+du[8].tag = lastbit: offline post-mod scrub failed (1).
+du[8].tag = add: offline re-scrub failed (1).
+du[8].tag = add: online post-mod scrub failed (1).
+du[8].tag = add: offline post-mod scrub failed (1).
+du[8].tag = sub: offline re-scrub failed (1).
+du[8].tag = sub: online post-mod scrub failed (1).
+du[8].tag = sub: offline post-mod scrub failed (1).
+du[9].inumber = ones: offline re-scrub failed (1).
+du[9].inumber = ones: online post-mod scrub failed (1).
+du[9].inumber = ones: offline post-mod scrub failed (1).
+du[9].inumber = sub: offline re-scrub failed (1).
+du[9].inumber = sub: online post-mod scrub failed (1).
+du[9].inumber = sub: offline post-mod scrub failed (1).
+du[9].namelen = zeroes: offline re-scrub failed (1).
+du[9].namelen = zeroes: online post-mod scrub failed (1).
+du[9].namelen = zeroes: offline post-mod scrub failed (1).
+du[9].namelen = ones: offline re-scrub failed (1).
+du[9].namelen = ones: online post-mod scrub failed (1).
+du[9].namelen = ones: offline post-mod scrub failed (1).
+du[9].namelen = firstbit: offline re-scrub failed (1).
+du[9].namelen = firstbit: online post-mod scrub failed (1).
+du[9].namelen = firstbit: offline post-mod scrub failed (1).
+du[9].namelen = middlebit: offline re-scrub failed (1).
+du[9].namelen = middlebit: online post-mod scrub failed (1).
+du[9].namelen = middlebit: offline post-mod scrub failed (1).
+du[9].namelen = add: offline re-scrub failed (1).
+du[9].namelen = add: online post-mod scrub failed (1).
+du[9].namelen = add: offline post-mod scrub failed (1).
+du[9].namelen = sub: offline re-scrub failed (1).
+du[9].namelen = sub: online post-mod scrub failed (1).
+du[9].namelen = sub: offline post-mod scrub failed (1).
+du[9].tag = zeroes: offline re-scrub failed (1).
+du[9].tag = zeroes: online post-mod scrub failed (1).
+du[9].tag = zeroes: offline post-mod scrub failed (1).
+du[9].tag = ones: offline re-scrub failed (1).
+du[9].tag = ones: online post-mod scrub failed (1).
+du[9].tag = ones: offline post-mod scrub failed (1).
+du[9].tag = firstbit: offline re-scrub failed (1).
+du[9].tag = firstbit: online post-mod scrub failed (1).
+du[9].tag = firstbit: offline post-mod scrub failed (1).
+du[9].tag = middlebit: offline re-scrub failed (1).
+du[9].tag = middlebit: online post-mod scrub failed (1).
+du[9].tag = middlebit: offline post-mod scrub failed (1).
+du[9].tag = lastbit: offline re-scrub failed (1).
+du[9].tag = lastbit: online post-mod scrub failed (1).
+du[9].tag = lastbit: offline post-mod scrub failed (1).
+du[9].tag = add: offline re-scrub failed (1).
+du[9].tag = add: online post-mod scrub failed (1).
+du[9].tag = add: offline post-mod scrub failed (1).
+du[9].tag = sub: offline re-scrub failed (1).
+du[9].tag = sub: online post-mod scrub failed (1).
+du[9].tag = sub: offline post-mod scrub failed (1).
 Done fuzzing data-format dir block
diff --git a/tests/xfs/392.out b/tests/xfs/392.out
index 9ff34805a8..8bc5d14cd2 100644
--- a/tests/xfs/392.out
+++ b/tests/xfs/392.out
@@ -2,4 +2,11 @@ QA output created by 392
 Format and populate
 Find leafn-format dir block
 Fuzz leafn-format dir block
+lhdr.info.crc = zeroes: offline scrub didn't fail.
+lhdr.info.crc = ones: offline scrub didn't fail.
+lhdr.info.crc = firstbit: offline scrub didn't fail.
+lhdr.info.crc = middlebit: offline scrub didn't fail.
+lhdr.info.crc = lastbit: offline scrub didn't fail.
+lhdr.info.crc = add: offline scrub didn't fail.
+lhdr.info.crc = sub: offline scrub didn't fail.
 Done fuzzing leafn-format dir block
diff --git a/tests/xfs/394.out b/tests/xfs/394.out
index bc50b85217..5c26f64289 100644
--- a/tests/xfs/394.out
+++ b/tests/xfs/394.out
@@ -2,4 +2,16 @@ QA output created by 394
 Format and populate
 Find node-format dir block
 Fuzz node-format dir block
+nhdr.info.hdr.back = ones: offline scrub didn't fail.
+nhdr.info.hdr.back = ones: online post-mod scrub failed (1).
+nhdr.info.hdr.back = firstbit: offline scrub didn't fail.
+nhdr.info.hdr.back = firstbit: online post-mod scrub failed (1).
+nhdr.info.hdr.back = middlebit: offline scrub didn't fail.
+nhdr.info.hdr.back = middlebit: online post-mod scrub failed (1).
+nhdr.info.hdr.back = lastbit: offline scrub didn't fail.
+nhdr.info.hdr.back = lastbit: online post-mod scrub failed (1).
+nhdr.info.hdr.back = add: offline scrub didn't fail.
+nhdr.info.hdr.back = add: online post-mod scrub failed (1).
+nhdr.info.hdr.back = sub: offline scrub didn't fail.
+nhdr.info.hdr.back = sub: online post-mod scrub failed (1).
 Done fuzzing node-format dir block
diff --git a/tests/xfs/398.out b/tests/xfs/398.out
index 63c899d2e5..11bac3af85 100644
--- a/tests/xfs/398.out
+++ b/tests/xfs/398.out
@@ -2,4 +2,42 @@ QA output created by 398
 Format and populate
 Find inline-format attr inode
 Fuzz inline-format attr inode
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+core.size = middlebit: offline scrub didn't fail.
+core.size = lastbit: offline scrub didn't fail.
+core.size = add: offline scrub didn't fail.
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.flags2 = lastbit: offline scrub didn't fail.
+v3.reflink = ones: offline scrub didn't fail.
+v3.reflink = firstbit: offline scrub didn't fail.
+v3.reflink = middlebit: offline scrub didn't fail.
+v3.reflink = lastbit: offline scrub didn't fail.
+v3.reflink = add: offline scrub didn't fail.
+v3.reflink = sub: offline scrub didn't fail.
+v3.nrext64 = zeroes: offline scrub didn't fail.
+v3.nrext64 = firstbit: offline scrub didn't fail.
+v3.nrext64 = middlebit: offline scrub didn't fail.
+v3.nrext64 = lastbit: offline scrub didn't fail.
+v3.nrext64 = add: offline scrub didn't fail.
+v3.nrext64 = sub: offline scrub didn't fail.
+a.sfattr.list[1].name = ones: offline scrub didn't fail.
+a.sfattr.list[1].name = firstbit: offline scrub didn't fail.
+a.sfattr.list[1].name = middlebit: offline scrub didn't fail.
+a.sfattr.list[1].name = lastbit: offline scrub didn't fail.
+a.sfattr.list[1].name = add: offline scrub didn't fail.
+a.sfattr.list[1].name = sub: offline scrub didn't fail.
+a.sfattr.list[2].name = ones: offline scrub didn't fail.
+a.sfattr.list[2].name = firstbit: offline scrub didn't fail.
+a.sfattr.list[2].name = middlebit: offline scrub didn't fail.
+a.sfattr.list[2].name = lastbit: offline scrub didn't fail.
+a.sfattr.list[2].name = add: offline scrub didn't fail.
+a.sfattr.list[2].name = sub: offline scrub didn't fail.
 Done fuzzing inline-format attr inode
diff --git a/tests/xfs/400.out b/tests/xfs/400.out
index 6ac33ef2c5..9a0555448e 100644
--- a/tests/xfs/400.out
+++ b/tests/xfs/400.out
@@ -2,4 +2,30 @@ QA output created by 400
 Format and populate
 Find leaf-format attr block
 Fuzz leaf-format attr block
+hdr.info.crc = zeroes: offline scrub didn't fail.
+hdr.info.crc = ones: offline scrub didn't fail.
+hdr.info.crc = firstbit: offline scrub didn't fail.
+hdr.info.crc = middlebit: offline scrub didn't fail.
+hdr.info.crc = lastbit: offline scrub didn't fail.
+hdr.info.crc = add: offline scrub didn't fail.
+hdr.info.crc = sub: offline scrub didn't fail.
+hdr.holes = ones: offline scrub didn't fail.
+hdr.holes = firstbit: offline scrub didn't fail.
+hdr.holes = middlebit: offline scrub didn't fail.
+hdr.holes = lastbit: offline scrub didn't fail.
+hdr.holes = add: offline scrub didn't fail.
+hdr.holes = sub: offline scrub didn't fail.
+hdr.freemap[0].base = zeroes: offline scrub didn't fail.
+hdr.freemap[0].base = zeroes: online post-mod scrub failed (1).
+hdr.freemap[0].base = middlebit: offline scrub didn't fail.
+hdr.freemap[0].base = middlebit: online post-mod scrub failed (1).
+hdr.freemap[0].size = zeroes: offline scrub didn't fail.
+hdr.freemap[0].size = middlebit: offline scrub didn't fail.
+hdr.freemap[0].size = middlebit: online post-mod scrub failed (1).
+hdr.freemap[1].base = middlebit: offline scrub didn't fail.
+hdr.freemap[1].size = middlebit: offline scrub didn't fail.
+hdr.freemap[1].size = middlebit: online post-mod scrub failed (1).
+hdr.freemap[2].base = middlebit: offline scrub didn't fail.
+hdr.freemap[2].size = middlebit: offline scrub didn't fail.
+hdr.freemap[2].size = middlebit: online post-mod scrub failed (1).
 Done fuzzing leaf-format attr block
diff --git a/tests/xfs/402.out b/tests/xfs/402.out
index 94e89f4c87..b7e36901d1 100644
--- a/tests/xfs/402.out
+++ b/tests/xfs/402.out
@@ -2,4 +2,11 @@ QA output created by 402
 Format and populate
 Find node-format attr block
 Fuzz node-format attr block
+hdr.info.crc = zeroes: offline scrub didn't fail.
+hdr.info.crc = ones: offline scrub didn't fail.
+hdr.info.crc = firstbit: offline scrub didn't fail.
+hdr.info.crc = middlebit: offline scrub didn't fail.
+hdr.info.crc = lastbit: offline scrub didn't fail.
+hdr.info.crc = add: offline scrub didn't fail.
+hdr.info.crc = sub: offline scrub didn't fail.
 Done fuzzing node-format attr block
diff --git a/tests/xfs/404.out b/tests/xfs/404.out
index 30ddbd87c8..45d47248e9 100644
--- a/tests/xfs/404.out
+++ b/tests/xfs/404.out
@@ -2,4 +2,37 @@ QA output created by 404
 Format and populate
 Find external attr block
 Fuzz external attr block
+hdr.offset = ones: offline scrub didn't fail.
+hdr.offset = ones: online post-mod scrub failed (1).
+hdr.offset = middlebit: offline scrub didn't fail.
+hdr.offset = middlebit: online post-mod scrub failed (1).
+hdr.offset = lastbit: offline scrub didn't fail.
+hdr.offset = lastbit: online post-mod scrub failed (1).
+hdr.offset = add: offline scrub didn't fail.
+hdr.offset = add: online post-mod scrub failed (1).
+hdr.offset = sub: offline scrub didn't fail.
+hdr.offset = sub: online post-mod scrub failed (1).
+hdr.bytes = zeroes: offline scrub didn't fail.
+hdr.bytes = zeroes: online post-mod scrub failed (1).
+hdr.bytes = lastbit: offline scrub didn't fail.
+hdr.bytes = lastbit: online post-mod scrub failed (1).
+hdr.bytes = sub: offline scrub didn't fail.
+hdr.bytes = sub: online post-mod scrub failed (1).
+hdr.owner = ones: offline scrub didn't fail.
+hdr.owner = ones: online post-mod scrub failed (1).
+hdr.owner = firstbit: offline scrub didn't fail.
+hdr.owner = firstbit: online post-mod scrub failed (1).
+hdr.owner = middlebit: offline scrub didn't fail.
+hdr.owner = middlebit: online post-mod scrub failed (1).
+hdr.owner = lastbit: offline scrub didn't fail.
+hdr.owner = lastbit: online post-mod scrub failed (1).
+hdr.owner = add: offline scrub didn't fail.
+hdr.owner = add: online post-mod scrub failed (1).
+hdr.owner = sub: offline scrub didn't fail.
+hdr.owner = sub: online post-mod scrub failed (1).
+data = zeroes: offline scrub didn't fail.
+data = ones: offline scrub didn't fail.
+data = firstbit: offline scrub didn't fail.
+data = middlebit: offline scrub didn't fail.
+data = lastbit: offline scrub didn't fail.
 Done fuzzing external attr block
diff --git a/tests/xfs/410.out b/tests/xfs/410.out
index c43ae75efd..47a9eab8f9 100644
--- a/tests/xfs/410.out
+++ b/tests/xfs/410.out
@@ -1,4 +1,10 @@
 QA output created by 410
 Format and populate
 Fuzz refcountbt
+numrecs = lastbit: offline scrub didn't fail.
+leftsib = add: offline scrub didn't fail.
+rightsib = ones: offline scrub didn't fail.
+rightsib = middlebit: offline scrub didn't fail.
+rightsib = lastbit: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
 Done fuzzing refcountbt
diff --git a/tests/xfs/412.out b/tests/xfs/412.out
index b93eec2262..550ca4e85c 100644
--- a/tests/xfs/412.out
+++ b/tests/xfs/412.out
@@ -2,4 +2,25 @@ QA output created by 412
 Format and populate
 Find btree-format attr inode
 Fuzz inode
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+core.size = middlebit: offline scrub didn't fail.
+core.size = lastbit: offline scrub didn't fail.
+core.size = add: offline scrub didn't fail.
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.flags2 = lastbit: offline scrub didn't fail.
+v3.reflink = ones: offline scrub didn't fail.
+v3.reflink = firstbit: offline scrub didn't fail.
+v3.reflink = middlebit: offline scrub didn't fail.
+v3.reflink = lastbit: offline scrub didn't fail.
+v3.reflink = add: offline scrub didn't fail.
+v3.reflink = sub: offline scrub didn't fail.
+a.bmbt.ptrs[1] = firstbit: offline scrub didn't fail.
 Done fuzzing inode
diff --git a/tests/xfs/414.out b/tests/xfs/414.out
index 3d6e4d2f5e..107c625114 100644
--- a/tests/xfs/414.out
+++ b/tests/xfs/414.out
@@ -2,4 +2,27 @@ QA output created by 414
 Format and populate
 Find blockdev inode
 Fuzz inode
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.nrext64 = zeroes: offline scrub didn't fail.
+v3.nrext64 = firstbit: offline scrub didn't fail.
+v3.nrext64 = middlebit: offline scrub didn't fail.
+v3.nrext64 = lastbit: offline scrub didn't fail.
+v3.nrext64 = add: offline scrub didn't fail.
+v3.nrext64 = sub: offline scrub didn't fail.
+u3.dev = zeroes: offline scrub didn't fail.
+u3.dev = ones: offline scrub didn't fail.
+u3.dev = firstbit: offline scrub didn't fail.
+u3.dev = middlebit: offline scrub didn't fail.
+u3.dev = lastbit: offline scrub didn't fail.
+u3.dev = add: offline scrub didn't fail.
+u3.dev = sub: offline scrub didn't fail.
 Done fuzzing inode
diff --git a/tests/xfs/416.out b/tests/xfs/416.out
index d17d2f73a1..9abc7867da 100644
--- a/tests/xfs/416.out
+++ b/tests/xfs/416.out
@@ -2,4 +2,26 @@ QA output created by 416
 Format and populate
 Find local-format symlink inode
 Fuzz inode
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.nrext64 = zeroes: offline scrub didn't fail.
+v3.nrext64 = firstbit: offline scrub didn't fail.
+v3.nrext64 = middlebit: offline scrub didn't fail.
+v3.nrext64 = lastbit: offline scrub didn't fail.
+v3.nrext64 = add: offline scrub didn't fail.
+v3.nrext64 = sub: offline scrub didn't fail.
+u3.symlink = ones: offline scrub didn't fail.
+u3.symlink = firstbit: offline scrub didn't fail.
+u3.symlink = middlebit: offline scrub didn't fail.
+u3.symlink = lastbit: offline scrub didn't fail.
+u3.symlink = add: offline scrub didn't fail.
+u3.symlink = sub: offline scrub didn't fail.
 Done fuzzing inode
diff --git a/tests/xfs/418.out b/tests/xfs/418.out
index 9051605b9c..ae181693a1 100644
--- a/tests/xfs/418.out
+++ b/tests/xfs/418.out
@@ -1,4 +1,94 @@
 QA output created by 418
 Format and populate
 Fuzz superblock
+uuid = zeroes: offline scrub didn't fail.
+uuid = ones: offline scrub didn't fail.
+uuid = firstbit: offline scrub didn't fail.
+uuid = middlebit: offline scrub didn't fail.
+uuid = lastbit: offline scrub didn't fail.
+rootino = zeroes: offline scrub didn't fail.
+rootino = ones: offline scrub didn't fail.
+rootino = firstbit: offline scrub didn't fail.
+rootino = middlebit: offline scrub didn't fail.
+rootino = lastbit: offline scrub didn't fail.
+rootino = add: offline scrub didn't fail.
+rootino = sub: offline scrub didn't fail.
+metadirino = zeroes: offline scrub didn't fail.
+metadirino = firstbit: offline scrub didn't fail.
+metadirino = middlebit: offline scrub didn't fail.
+metadirino = lastbit: offline scrub didn't fail.
+metadirino = add: offline scrub didn't fail.
+metadirino = sub: offline scrub didn't fail.
+rgblocks = middlebit: offline scrub didn't fail.
+rgblocks = lastbit: offline scrub didn't fail.
+rgblocks = add: offline scrub didn't fail.
+rgblocks = sub: offline scrub didn't fail.
+fname = ones: offline scrub didn't fail.
+fname = firstbit: offline scrub didn't fail.
+fname = middlebit: offline scrub didn't fail.
+fname = lastbit: offline scrub didn't fail.
+inprogress = zeroes: offline scrub didn't fail.
+inprogress = ones: offline scrub didn't fail.
+inprogress = firstbit: offline scrub didn't fail.
+inprogress = middlebit: offline scrub didn't fail.
+inprogress = lastbit: offline scrub didn't fail.
+inprogress = add: offline scrub didn't fail.
+inprogress = sub: offline scrub didn't fail.
+imax_pct = zeroes: offline scrub didn't fail.
+imax_pct = middlebit: offline scrub didn't fail.
+imax_pct = lastbit: offline scrub didn't fail.
+icount = ones: offline scrub didn't fail.
+icount = firstbit: offline scrub didn't fail.
+icount = middlebit: offline scrub didn't fail.
+icount = lastbit: offline scrub didn't fail.
+icount = add: offline scrub didn't fail.
+icount = sub: offline scrub didn't fail.
+ifree = ones: offline scrub didn't fail.
+ifree = firstbit: offline scrub didn't fail.
+ifree = middlebit: offline scrub didn't fail.
+ifree = lastbit: offline scrub didn't fail.
+ifree = add: offline scrub didn't fail.
+ifree = sub: offline scrub didn't fail.
+fdblocks = zeroes: offline scrub didn't fail.
+fdblocks = ones: offline scrub didn't fail.
+fdblocks = firstbit: offline scrub didn't fail.
+fdblocks = middlebit: offline scrub didn't fail.
+fdblocks = lastbit: offline scrub didn't fail.
+fdblocks = add: offline scrub didn't fail.
+fdblocks = sub: offline scrub didn't fail.
+shared_vn = ones: offline scrub didn't fail.
+shared_vn = ones: online post-mod scrub failed (1).
+shared_vn = firstbit: offline scrub didn't fail.
+shared_vn = firstbit: online post-mod scrub failed (1).
+shared_vn = middlebit: offline scrub didn't fail.
+shared_vn = middlebit: online post-mod scrub failed (1).
+shared_vn = lastbit: offline scrub didn't fail.
+shared_vn = lastbit: online post-mod scrub failed (1).
+shared_vn = add: offline scrub didn't fail.
+shared_vn = add: online post-mod scrub failed (1).
+shared_vn = sub: offline scrub didn't fail.
+shared_vn = sub: online post-mod scrub failed (1).
+dirblklog = lastbit: offline scrub didn't fail.
+dirblklog = lastbit: online post-mod scrub failed (1).
+logsunit = zeroes: offline scrub didn't fail.
+logsunit = zeroes: online post-mod scrub failed (1).
+logsunit = lastbit: offline scrub didn't fail.
+logsunit = lastbit: online post-mod scrub failed (1).
+bad_features2 = zeroes: offline scrub didn't fail.
+bad_features2 = ones: offline scrub didn't fail.
+bad_features2 = firstbit: offline scrub didn't fail.
+bad_features2 = middlebit: offline scrub didn't fail.
+bad_features2 = lastbit: offline scrub didn't fail.
+bad_features2 = add: offline scrub didn't fail.
+bad_features2 = sub: offline scrub didn't fail.
+features_incompat = sub: offline repair failed (1).
+features_incompat = sub: offline re-scrub failed (1).
+features_incompat = sub: online post-mod scrub failed (1).
+features_incompat = sub: offline post-mod scrub failed (1).
+features_log_incompat = ones: offline scrub didn't fail.
+features_log_incompat = firstbit: offline scrub didn't fail.
+features_log_incompat = middlebit: offline scrub didn't fail.
+features_log_incompat = lastbit: offline scrub didn't fail.
+features_log_incompat = add: offline scrub didn't fail.
+features_log_incompat = sub: offline scrub didn't fail.
 Done fuzzing superblock
diff --git a/tests/xfs/425.out b/tests/xfs/425.out
index 14445b44c0..ddeb2ba6bb 100644
--- a/tests/xfs/425.out
+++ b/tests/xfs/425.out
@@ -1,4 +1,262 @@
 QA output created by 425
 Format and populate
 Fuzz user 0 dquot
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = ones: online post-mod scrub failed (1).
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = add: online post-mod scrub failed (1).
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: online post-mod scrub failed (1).
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = ones: online post-mod scrub failed (1).
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = add: online post-mod scrub failed (1).
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: online post-mod scrub failed (1).
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = ones: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: online post-mod scrub failed (1).
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = sub: offline scrub didn't fail.
+Done fuzzing dquot
+Fuzz user 4242 dquot
+diskdq.type = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = ones: online post-mod scrub failed (1).
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = add: online post-mod scrub failed (1).
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: online post-mod scrub failed (1).
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = ones: online post-mod scrub failed (1).
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = add: online post-mod scrub failed (1).
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: online post-mod scrub failed (1).
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = ones: online post-mod scrub failed (1).
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = firstbit: online post-mod scrub failed (1).
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = middlebit: online post-mod scrub failed (1).
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = lastbit: online post-mod scrub failed (1).
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = add: online post-mod scrub failed (1).
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.itimer = sub: online post-mod scrub failed (1).
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = ones: online post-mod scrub failed (1).
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = firstbit: online post-mod scrub failed (1).
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = middlebit: online post-mod scrub failed (1).
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = lastbit: online post-mod scrub failed (1).
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = add: online post-mod scrub failed (1).
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.btimer = sub: online post-mod scrub failed (1).
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = ones: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: online post-mod scrub failed (1).
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = ones: online post-mod scrub failed (1).
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: online post-mod scrub failed (1).
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: online post-mod scrub failed (1).
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: online post-mod scrub failed (1).
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = add: online post-mod scrub failed (1).
+diskdq.rtbtimer = sub: offline scrub didn't fail.
+diskdq.rtbtimer = sub: online post-mod scrub failed (1).
+Done fuzzing dquot
+Fuzz user 8484 dquot
+diskdq.type = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = ones: online post-mod scrub failed (1).
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = add: online post-mod scrub failed (1).
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: online post-mod scrub failed (1).
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = ones: online post-mod scrub failed (1).
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = add: online post-mod scrub failed (1).
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: online post-mod scrub failed (1).
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = ones: online post-mod scrub failed (1).
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = firstbit: online post-mod scrub failed (1).
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = middlebit: online post-mod scrub failed (1).
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = lastbit: online post-mod scrub failed (1).
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = add: online post-mod scrub failed (1).
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.itimer = sub: online post-mod scrub failed (1).
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = ones: online post-mod scrub failed (1).
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = firstbit: online post-mod scrub failed (1).
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = middlebit: online post-mod scrub failed (1).
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = lastbit: online post-mod scrub failed (1).
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = add: online post-mod scrub failed (1).
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.btimer = sub: online post-mod scrub failed (1).
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = ones: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: online post-mod scrub failed (1).
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = ones: online post-mod scrub failed (1).
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: online post-mod scrub failed (1).
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: online post-mod scrub failed (1).
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: online post-mod scrub failed (1).
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = add: online post-mod scrub failed (1).
+diskdq.rtbtimer = sub: offline scrub didn't fail.
+diskdq.rtbtimer = sub: online post-mod scrub failed (1).
 Done fuzzing dquot
diff --git a/tests/xfs/427.out b/tests/xfs/427.out
index 9074c64527..2a79e3e621 100644
--- a/tests/xfs/427.out
+++ b/tests/xfs/427.out
@@ -1,4 +1,262 @@
 QA output created by 427
 Format and populate
 Fuzz group 0 dquot
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = ones: online post-mod scrub failed (1).
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = add: online post-mod scrub failed (1).
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: online post-mod scrub failed (1).
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = ones: online post-mod scrub failed (1).
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = add: online post-mod scrub failed (1).
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: online post-mod scrub failed (1).
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = ones: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: online post-mod scrub failed (1).
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = sub: offline scrub didn't fail.
+Done fuzzing dquot
+Fuzz group 4242 dquot
+diskdq.type = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = ones: online post-mod scrub failed (1).
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = add: online post-mod scrub failed (1).
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: online post-mod scrub failed (1).
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = ones: online post-mod scrub failed (1).
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = add: online post-mod scrub failed (1).
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: online post-mod scrub failed (1).
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = ones: online post-mod scrub failed (1).
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = firstbit: online post-mod scrub failed (1).
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = middlebit: online post-mod scrub failed (1).
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = lastbit: online post-mod scrub failed (1).
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = add: online post-mod scrub failed (1).
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.itimer = sub: online post-mod scrub failed (1).
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = ones: online post-mod scrub failed (1).
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = firstbit: online post-mod scrub failed (1).
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = middlebit: online post-mod scrub failed (1).
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = lastbit: online post-mod scrub failed (1).
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = add: online post-mod scrub failed (1).
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.btimer = sub: online post-mod scrub failed (1).
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = ones: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: online post-mod scrub failed (1).
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = ones: online post-mod scrub failed (1).
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: online post-mod scrub failed (1).
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: online post-mod scrub failed (1).
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: online post-mod scrub failed (1).
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = add: online post-mod scrub failed (1).
+diskdq.rtbtimer = sub: offline scrub didn't fail.
+diskdq.rtbtimer = sub: online post-mod scrub failed (1).
+Done fuzzing dquot
+Fuzz group 8484 dquot
+diskdq.type = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = ones: online post-mod scrub failed (1).
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = add: online post-mod scrub failed (1).
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: online post-mod scrub failed (1).
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = ones: online post-mod scrub failed (1).
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = add: online post-mod scrub failed (1).
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: online post-mod scrub failed (1).
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = ones: online post-mod scrub failed (1).
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = firstbit: online post-mod scrub failed (1).
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = middlebit: online post-mod scrub failed (1).
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = lastbit: online post-mod scrub failed (1).
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = add: online post-mod scrub failed (1).
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.itimer = sub: online post-mod scrub failed (1).
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = ones: online post-mod scrub failed (1).
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = firstbit: online post-mod scrub failed (1).
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = middlebit: online post-mod scrub failed (1).
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = lastbit: online post-mod scrub failed (1).
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = add: online post-mod scrub failed (1).
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.btimer = sub: online post-mod scrub failed (1).
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = ones: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: online post-mod scrub failed (1).
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = ones: online post-mod scrub failed (1).
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: online post-mod scrub failed (1).
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: online post-mod scrub failed (1).
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: online post-mod scrub failed (1).
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = add: online post-mod scrub failed (1).
+diskdq.rtbtimer = sub: offline scrub didn't fail.
+diskdq.rtbtimer = sub: online post-mod scrub failed (1).
 Done fuzzing dquot
diff --git a/tests/xfs/429.out b/tests/xfs/429.out
index b5ea503b01..c212bb7fe3 100644
--- a/tests/xfs/429.out
+++ b/tests/xfs/429.out
@@ -1,4 +1,262 @@
 QA output created by 429
 Format and populate
 Fuzz project 0 dquot
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = ones: online post-mod scrub failed (1).
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = add: online post-mod scrub failed (1).
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: online post-mod scrub failed (1).
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = ones: online post-mod scrub failed (1).
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = add: online post-mod scrub failed (1).
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: online post-mod scrub failed (1).
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = ones: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: online post-mod scrub failed (1).
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = sub: offline scrub didn't fail.
+Done fuzzing dquot
+Fuzz project 4242 dquot
+diskdq.type = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = ones: online post-mod scrub failed (1).
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = add: online post-mod scrub failed (1).
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: online post-mod scrub failed (1).
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = ones: online post-mod scrub failed (1).
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = add: online post-mod scrub failed (1).
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: online post-mod scrub failed (1).
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = ones: online post-mod scrub failed (1).
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = firstbit: online post-mod scrub failed (1).
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = middlebit: online post-mod scrub failed (1).
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = lastbit: online post-mod scrub failed (1).
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = add: online post-mod scrub failed (1).
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.itimer = sub: online post-mod scrub failed (1).
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = ones: online post-mod scrub failed (1).
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = firstbit: online post-mod scrub failed (1).
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = middlebit: online post-mod scrub failed (1).
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = lastbit: online post-mod scrub failed (1).
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = add: online post-mod scrub failed (1).
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.btimer = sub: online post-mod scrub failed (1).
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = ones: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: online post-mod scrub failed (1).
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = ones: online post-mod scrub failed (1).
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: online post-mod scrub failed (1).
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: online post-mod scrub failed (1).
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: online post-mod scrub failed (1).
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = add: online post-mod scrub failed (1).
+diskdq.rtbtimer = sub: offline scrub didn't fail.
+diskdq.rtbtimer = sub: online post-mod scrub failed (1).
+Done fuzzing dquot
+Fuzz project 8484 dquot
+diskdq.type = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = ones: online post-mod scrub failed (1).
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = add: online post-mod scrub failed (1).
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: online post-mod scrub failed (1).
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = ones: online post-mod scrub failed (1).
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = add: online post-mod scrub failed (1).
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: online post-mod scrub failed (1).
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = ones: online post-mod scrub failed (1).
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = firstbit: online post-mod scrub failed (1).
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = middlebit: online post-mod scrub failed (1).
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = lastbit: online post-mod scrub failed (1).
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = add: online post-mod scrub failed (1).
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.itimer = sub: online post-mod scrub failed (1).
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = ones: online post-mod scrub failed (1).
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = firstbit: online post-mod scrub failed (1).
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = middlebit: online post-mod scrub failed (1).
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = lastbit: online post-mod scrub failed (1).
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = add: online post-mod scrub failed (1).
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.btimer = sub: online post-mod scrub failed (1).
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = ones: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: online post-mod scrub failed (1).
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = ones: online post-mod scrub failed (1).
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: online post-mod scrub failed (1).
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: online post-mod scrub failed (1).
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: online post-mod scrub failed (1).
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = add: online post-mod scrub failed (1).
+diskdq.rtbtimer = sub: offline scrub didn't fail.
+diskdq.rtbtimer = sub: online post-mod scrub failed (1).
 Done fuzzing dquot
diff --git a/tests/xfs/496.out b/tests/xfs/496.out
index 08597a2d88..c0ed81584b 100644
--- a/tests/xfs/496.out
+++ b/tests/xfs/496.out
@@ -2,4 +2,28 @@ QA output created by 496
 Format and populate
 Find single-leafn-format dir block
 Fuzz single-leafn-format dir block
+lhdr.info.hdr.forw = ones: offline scrub didn't fail.
+lhdr.info.hdr.forw = ones: online post-mod scrub failed (1).
+lhdr.info.hdr.forw = firstbit: offline scrub didn't fail.
+lhdr.info.hdr.forw = firstbit: online post-mod scrub failed (1).
+lhdr.info.hdr.forw = middlebit: offline scrub didn't fail.
+lhdr.info.hdr.forw = middlebit: online post-mod scrub failed (1).
+lhdr.info.hdr.forw = lastbit: offline scrub didn't fail.
+lhdr.info.hdr.forw = lastbit: online post-mod scrub failed (1).
+lhdr.info.hdr.forw = add: offline scrub didn't fail.
+lhdr.info.hdr.forw = add: online post-mod scrub failed (1).
+lhdr.info.hdr.forw = sub: offline scrub didn't fail.
+lhdr.info.hdr.forw = sub: online post-mod scrub failed (1).
+lhdr.info.hdr.back = ones: offline scrub didn't fail.
+lhdr.info.hdr.back = ones: online post-mod scrub failed (1).
+lhdr.info.hdr.back = firstbit: offline scrub didn't fail.
+lhdr.info.hdr.back = firstbit: online post-mod scrub failed (1).
+lhdr.info.hdr.back = middlebit: offline scrub didn't fail.
+lhdr.info.hdr.back = middlebit: online post-mod scrub failed (1).
+lhdr.info.hdr.back = lastbit: offline scrub didn't fail.
+lhdr.info.hdr.back = lastbit: online post-mod scrub failed (1).
+lhdr.info.hdr.back = add: offline scrub didn't fail.
+lhdr.info.hdr.back = add: online post-mod scrub failed (1).
+lhdr.info.hdr.back = sub: offline scrub didn't fail.
+lhdr.info.hdr.back = sub: online post-mod scrub failed (1).
 Done fuzzing single-leafn-format dir block
diff --git a/tests/xfs/734.out b/tests/xfs/734.out
index 80b91b6a9b..68b6b7dd8a 100644
--- a/tests/xfs/734.out
+++ b/tests/xfs/734.out
@@ -3,8 +3,17 @@ Format and populate
 Fuzz block map for BLOCK
 Done fuzzing dir map BLOCK
 Fuzz block map for LEAF
+u3.bmx[0].startblock = add: offline repair failed (1).
+u3.bmx[0].startblock = add: offline re-scrub failed (1).
+u3.bmx[0].startblock = add: pre-mod mount failed (32).
+u3.bmx[1].startblock = add: offline repair failed (1).
+u3.bmx[1].startblock = add: offline re-scrub failed (1).
+u3.bmx[1].startblock = add: pre-mod mount failed (32).
 Done fuzzing dir map LEAF
 Fuzz block map for LEAFN
+u3.bmx[0].startblock = add: offline re-scrub failed (1).
+u3.bmx[0].startblock = add: online post-mod scrub failed (1).
+u3.bmx[0].startblock = add: offline post-mod scrub failed (1).
 Done fuzzing dir map LEAFN
 Fuzz block map for NODE
 Done fuzzing dir map NODE
diff --git a/tests/xfs/737.out b/tests/xfs/737.out
index 7ee0f0c625..ba2105d891 100644
--- a/tests/xfs/737.out
+++ b/tests/xfs/737.out
@@ -1,10 +1,24 @@
 QA output created by 737
 Format and populate
 Fuzz block map for EXTENTS_REMOTE3K
+a.bmx[0].blockcount = middlebit: online post-mod scrub failed (1).
+a.bmx[0].blockcount = lastbit: online post-mod scrub failed (1).
 Done fuzzing attr map EXTENTS_REMOTE3K
 Fuzz block map for EXTENTS_REMOTE4K
+a.bmx[0].blockcount = middlebit: offline repair failed (1).
+a.bmx[0].blockcount = middlebit: offline re-scrub failed (1).
+a.bmx[0].blockcount = middlebit: online post-mod scrub failed (1).
+a.bmx[0].blockcount = middlebit: offline post-mod scrub failed (1).
 Done fuzzing attr map EXTENTS_REMOTE4K
 Fuzz block map for LEAF
+a.bmx[0].blockcount = middlebit: offline repair failed (1).
+a.bmx[0].blockcount = middlebit: offline re-scrub failed (1).
+a.bmx[0].blockcount = middlebit: online post-mod scrub failed (1).
+a.bmx[0].blockcount = middlebit: offline post-mod scrub failed (1).
 Done fuzzing attr map LEAF
 Fuzz block map for NODE
+a.bmx[0].blockcount = middlebit: offline repair failed (1).
+a.bmx[0].blockcount = middlebit: offline re-scrub failed (1).
+a.bmx[0].blockcount = middlebit: online post-mod scrub failed (1).
+a.bmx[0].blockcount = middlebit: offline post-mod scrub failed (1).
 Done fuzzing attr map NODE
diff --git a/tests/xfs/754.out b/tests/xfs/754.out
index 0b8eef9ced..174c4300d8 100644
--- a/tests/xfs/754.out
+++ b/tests/xfs/754.out
@@ -1,4 +1,27 @@
 QA output created by 754
 Format and populate
 Fuzz inobt
+leftsib = add: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
+keys[1].startino = zeroes: offline scrub didn't fail.
+keys[1].startino = ones: offline scrub didn't fail.
+keys[1].startino = firstbit: offline scrub didn't fail.
+keys[1].startino = middlebit: offline scrub didn't fail.
+keys[1].startino = lastbit: offline scrub didn't fail.
+keys[1].startino = add: offline scrub didn't fail.
+keys[1].startino = sub: offline scrub didn't fail.
+keys[2].startino = zeroes: offline scrub didn't fail.
+keys[2].startino = ones: offline scrub didn't fail.
+keys[2].startino = firstbit: offline scrub didn't fail.
+keys[2].startino = middlebit: offline scrub didn't fail.
+keys[2].startino = lastbit: offline scrub didn't fail.
+keys[2].startino = add: offline scrub didn't fail.
+keys[2].startino = sub: offline scrub didn't fail.
+keys[3].startino = zeroes: offline scrub didn't fail.
+keys[3].startino = ones: offline scrub didn't fail.
+keys[3].startino = firstbit: offline scrub didn't fail.
+keys[3].startino = middlebit: offline scrub didn't fail.
+keys[3].startino = lastbit: offline scrub didn't fail.
+keys[3].startino = add: offline scrub didn't fail.
+keys[3].startino = sub: offline scrub didn't fail.
 Done fuzzing inobt
diff --git a/tests/xfs/785.out b/tests/xfs/785.out
index f5cdc6b73d..062b80f967 100644
--- a/tests/xfs/785.out
+++ b/tests/xfs/785.out
@@ -1,4 +1,27 @@
 QA output created by 785
 Format and populate
 Fuzz inobt
+leftsib = add: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
+keys[1].startino = zeroes: offline scrub didn't fail.
+keys[1].startino = ones: offline scrub didn't fail.
+keys[1].startino = firstbit: offline scrub didn't fail.
+keys[1].startino = middlebit: offline scrub didn't fail.
+keys[1].startino = lastbit: offline scrub didn't fail.
+keys[1].startino = add: offline scrub didn't fail.
+keys[1].startino = sub: offline scrub didn't fail.
+keys[2].startino = zeroes: offline scrub didn't fail.
+keys[2].startino = ones: offline scrub didn't fail.
+keys[2].startino = firstbit: offline scrub didn't fail.
+keys[2].startino = middlebit: offline scrub didn't fail.
+keys[2].startino = lastbit: offline scrub didn't fail.
+keys[2].startino = add: offline scrub didn't fail.
+keys[2].startino = sub: offline scrub didn't fail.
+keys[3].startino = zeroes: offline scrub didn't fail.
+keys[3].startino = ones: offline scrub didn't fail.
+keys[3].startino = firstbit: offline scrub didn't fail.
+keys[3].startino = middlebit: offline scrub didn't fail.
+keys[3].startino = lastbit: offline scrub didn't fail.
+keys[3].startino = add: offline scrub didn't fail.
+keys[3].startino = sub: offline scrub didn't fail.
 Done fuzzing inobt

[PATCH 3/4] xfs: norepair fuzz test known output

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Record all the currently known failures of the kernel verifier code.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 tests/xfs/453.out |  152 +++++++++++++++
 tests/xfs/454.out |   96 ++++++++++
 tests/xfs/455.out |  134 ++++++++++++++
 tests/xfs/456.out |  129 +++++++++++++
 tests/xfs/457.out |    5 +
 tests/xfs/458.out |   44 ++++
 tests/xfs/459.out |    5 +
 tests/xfs/460.out |    6 +
 tests/xfs/461.out |    6 +
 tests/xfs/462.out |    8 +
 tests/xfs/463.out |  525 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 tests/xfs/464.out |    5 +
 tests/xfs/465.out |   71 +++++++
 tests/xfs/466.out |   51 +++++
 tests/xfs/467.out |   47 +++++
 tests/xfs/469.out |    8 +
 tests/xfs/470.out |   79 ++++++++
 tests/xfs/471.out |    7 +
 tests/xfs/472.out |    7 +
 tests/xfs/474.out |    7 +
 tests/xfs/475.out |    6 +
 tests/xfs/477.out |   79 ++++++++
 tests/xfs/478.out |   91 +++++++++
 tests/xfs/479.out |    7 +
 tests/xfs/480.out |   24 ++
 tests/xfs/483.out |    6 +
 tests/xfs/484.out |   45 +++++
 tests/xfs/485.out |   51 +++++
 tests/xfs/486.out |   46 +++++
 tests/xfs/487.out |  242 ++++++++++++++++++++++++
 tests/xfs/488.out |  242 ++++++++++++++++++++++++
 tests/xfs/489.out |  242 ++++++++++++++++++++++++
 tests/xfs/498.out |   12 +
 tests/xfs/788.out |   23 ++
 34 files changed, 2508 insertions(+)


diff --git a/tests/xfs/453.out b/tests/xfs/453.out
index 4b89bb01d8..15626b9caa 100644
--- a/tests/xfs/453.out
+++ b/tests/xfs/453.out
@@ -1,4 +1,156 @@
 QA output created by 453
 Format and populate
 Fuzz superblock
+uuid = zeroes: offline scrub didn't fail.
+uuid = zeroes: online scrub didn't fail.
+uuid = ones: offline scrub didn't fail.
+uuid = ones: online scrub didn't fail.
+uuid = firstbit: offline scrub didn't fail.
+uuid = firstbit: online scrub didn't fail.
+uuid = middlebit: offline scrub didn't fail.
+uuid = middlebit: online scrub didn't fail.
+uuid = lastbit: offline scrub didn't fail.
+uuid = lastbit: online scrub didn't fail.
+rootino = zeroes: offline scrub didn't fail.
+rootino = zeroes: online scrub didn't fail.
+rootino = ones: offline scrub didn't fail.
+rootino = ones: online scrub didn't fail.
+rootino = firstbit: offline scrub didn't fail.
+rootino = firstbit: online scrub didn't fail.
+rootino = middlebit: offline scrub didn't fail.
+rootino = middlebit: online scrub didn't fail.
+rootino = lastbit: offline scrub didn't fail.
+rootino = lastbit: online scrub didn't fail.
+rootino = add: offline scrub didn't fail.
+rootino = add: online scrub didn't fail.
+rootino = sub: offline scrub didn't fail.
+rootino = sub: online scrub didn't fail.
+metadirino = zeroes: offline scrub didn't fail.
+metadirino = zeroes: online scrub didn't fail.
+metadirino = firstbit: offline scrub didn't fail.
+metadirino = firstbit: online scrub didn't fail.
+metadirino = middlebit: offline scrub didn't fail.
+metadirino = middlebit: online scrub didn't fail.
+metadirino = lastbit: offline scrub didn't fail.
+metadirino = lastbit: online scrub didn't fail.
+metadirino = add: offline scrub didn't fail.
+metadirino = add: online scrub didn't fail.
+metadirino = sub: offline scrub didn't fail.
+metadirino = sub: online scrub didn't fail.
+rgblocks = middlebit: offline scrub didn't fail.
+rgblocks = middlebit: online scrub didn't fail.
+rgblocks = lastbit: offline scrub didn't fail.
+rgblocks = lastbit: online scrub didn't fail.
+rgblocks = add: offline scrub didn't fail.
+rgblocks = add: online scrub didn't fail.
+rgblocks = sub: offline scrub didn't fail.
+rgblocks = sub: online scrub didn't fail.
+fname = ones: offline scrub didn't fail.
+fname = ones: online scrub didn't fail.
+fname = firstbit: offline scrub didn't fail.
+fname = firstbit: online scrub didn't fail.
+fname = middlebit: offline scrub didn't fail.
+fname = middlebit: online scrub didn't fail.
+fname = lastbit: offline scrub didn't fail.
+fname = lastbit: online scrub didn't fail.
+inprogress = zeroes: offline scrub didn't fail.
+inprogress = zeroes: online scrub didn't fail.
+inprogress = ones: offline scrub didn't fail.
+inprogress = ones: online scrub didn't fail.
+inprogress = firstbit: offline scrub didn't fail.
+inprogress = firstbit: online scrub didn't fail.
+inprogress = middlebit: offline scrub didn't fail.
+inprogress = middlebit: online scrub didn't fail.
+inprogress = lastbit: offline scrub didn't fail.
+inprogress = lastbit: online scrub didn't fail.
+inprogress = add: offline scrub didn't fail.
+inprogress = add: online scrub didn't fail.
+inprogress = sub: offline scrub didn't fail.
+inprogress = sub: online scrub didn't fail.
+imax_pct = zeroes: offline scrub didn't fail.
+imax_pct = zeroes: online scrub didn't fail.
+imax_pct = middlebit: offline scrub didn't fail.
+imax_pct = middlebit: online scrub didn't fail.
+imax_pct = lastbit: offline scrub didn't fail.
+imax_pct = lastbit: online scrub didn't fail.
+icount = ones: offline scrub didn't fail.
+icount = ones: online scrub didn't fail.
+icount = firstbit: offline scrub didn't fail.
+icount = firstbit: online scrub didn't fail.
+icount = middlebit: offline scrub didn't fail.
+icount = middlebit: online scrub didn't fail.
+icount = lastbit: offline scrub didn't fail.
+icount = lastbit: online scrub didn't fail.
+icount = add: offline scrub didn't fail.
+icount = add: online scrub didn't fail.
+icount = sub: offline scrub didn't fail.
+icount = sub: online scrub didn't fail.
+ifree = ones: offline scrub didn't fail.
+ifree = ones: online scrub didn't fail.
+ifree = firstbit: offline scrub didn't fail.
+ifree = firstbit: online scrub didn't fail.
+ifree = middlebit: offline scrub didn't fail.
+ifree = middlebit: online scrub didn't fail.
+ifree = lastbit: offline scrub didn't fail.
+ifree = lastbit: online scrub didn't fail.
+ifree = add: offline scrub didn't fail.
+ifree = add: online scrub didn't fail.
+ifree = sub: offline scrub didn't fail.
+ifree = sub: online scrub didn't fail.
+fdblocks = zeroes: offline scrub didn't fail.
+fdblocks = zeroes: online scrub didn't fail.
+fdblocks = ones: offline scrub didn't fail.
+fdblocks = ones: online scrub didn't fail.
+fdblocks = firstbit: offline scrub didn't fail.
+fdblocks = firstbit: online scrub didn't fail.
+fdblocks = middlebit: offline scrub didn't fail.
+fdblocks = middlebit: online scrub didn't fail.
+fdblocks = lastbit: offline scrub didn't fail.
+fdblocks = lastbit: online scrub didn't fail.
+fdblocks = add: offline scrub didn't fail.
+fdblocks = add: online scrub didn't fail.
+fdblocks = sub: offline scrub didn't fail.
+fdblocks = sub: online scrub didn't fail.
+qflags = firstbit: online scrub didn't fail.
+qflags = middlebit: online scrub didn't fail.
+qflags = lastbit: online scrub didn't fail.
+shared_vn = ones: offline scrub didn't fail.
+shared_vn = firstbit: offline scrub didn't fail.
+shared_vn = middlebit: offline scrub didn't fail.
+shared_vn = lastbit: offline scrub didn't fail.
+shared_vn = add: offline scrub didn't fail.
+shared_vn = sub: offline scrub didn't fail.
+dirblklog = lastbit: offline scrub didn't fail.
+logsunit = zeroes: offline scrub didn't fail.
+logsunit = lastbit: offline scrub didn't fail.
+bad_features2 = zeroes: offline scrub didn't fail.
+bad_features2 = zeroes: online scrub didn't fail.
+bad_features2 = ones: offline scrub didn't fail.
+bad_features2 = ones: online scrub didn't fail.
+bad_features2 = firstbit: offline scrub didn't fail.
+bad_features2 = firstbit: online scrub didn't fail.
+bad_features2 = middlebit: offline scrub didn't fail.
+bad_features2 = middlebit: online scrub didn't fail.
+bad_features2 = lastbit: offline scrub didn't fail.
+bad_features2 = lastbit: online scrub didn't fail.
+bad_features2 = add: offline scrub didn't fail.
+bad_features2 = add: online scrub didn't fail.
+bad_features2 = sub: offline scrub didn't fail.
+bad_features2 = sub: online scrub didn't fail.
+features_log_incompat = ones: offline scrub didn't fail.
+features_log_incompat = ones: online scrub didn't fail.
+features_log_incompat = firstbit: offline scrub didn't fail.
+features_log_incompat = firstbit: online scrub didn't fail.
+features_log_incompat = middlebit: offline scrub didn't fail.
+features_log_incompat = middlebit: online scrub didn't fail.
+features_log_incompat = lastbit: offline scrub didn't fail.
+features_log_incompat = lastbit: online scrub didn't fail.
+features_log_incompat = add: offline scrub didn't fail.
+features_log_incompat = add: online scrub didn't fail.
+features_log_incompat = sub: offline scrub didn't fail.
+features_log_incompat = sub: online scrub didn't fail.
+meta_uuid = ones: online scrub didn't fail.
+meta_uuid = firstbit: online scrub didn't fail.
+meta_uuid = middlebit: online scrub didn't fail.
+meta_uuid = lastbit: online scrub didn't fail.
 Done fuzzing superblock
diff --git a/tests/xfs/454.out b/tests/xfs/454.out
index ba7a8c24ba..dc89b2a488 100644
--- a/tests/xfs/454.out
+++ b/tests/xfs/454.out
@@ -1,4 +1,100 @@
 QA output created by 454
 Format and populate
 Fuzz AGF
+magicnum = zeroes: mount failed (32).
+magicnum = ones: mount failed (32).
+magicnum = firstbit: mount failed (32).
+magicnum = middlebit: mount failed (32).
+magicnum = lastbit: mount failed (32).
+magicnum = add: mount failed (32).
+magicnum = sub: mount failed (32).
+versionnum = zeroes: mount failed (32).
+versionnum = ones: mount failed (32).
+versionnum = firstbit: mount failed (32).
+versionnum = middlebit: mount failed (32).
+versionnum = lastbit: mount failed (32).
+versionnum = add: mount failed (32).
+versionnum = sub: mount failed (32).
+seqno = ones: mount failed (32).
+seqno = firstbit: mount failed (32).
+seqno = middlebit: mount failed (32).
+seqno = lastbit: mount failed (32).
+seqno = add: mount failed (32).
+seqno = sub: mount failed (32).
+length = zeroes: mount failed (32).
+length = ones: mount failed (32).
+length = firstbit: mount failed (32).
+length = middlebit: mount failed (32).
+length = lastbit: mount failed (32).
+length = add: mount failed (32).
+length = sub: mount failed (32).
+bnolevel = zeroes: mount failed (32).
+bnolevel = ones: mount failed (32).
+bnolevel = firstbit: mount failed (32).
+bnolevel = middlebit: mount failed (32).
+bnolevel = add: mount failed (32).
+bnolevel = sub: mount failed (32).
+cntlevel = zeroes: mount failed (32).
+cntlevel = ones: mount failed (32).
+cntlevel = firstbit: mount failed (32).
+cntlevel = middlebit: mount failed (32).
+cntlevel = add: mount failed (32).
+cntlevel = sub: mount failed (32).
+rmaplevel = zeroes: mount failed (32).
+rmaplevel = ones: mount failed (32).
+rmaplevel = firstbit: mount failed (32).
+rmaplevel = middlebit: mount failed (32).
+rmaplevel = add: mount failed (32).
+rmaplevel = sub: mount failed (32).
+refcntlevel = zeroes: mount failed (32).
+refcntlevel = ones: mount failed (32).
+refcntlevel = firstbit: mount failed (32).
+refcntlevel = middlebit: mount failed (32).
+refcntlevel = add: mount failed (32).
+refcntlevel = sub: mount failed (32).
+rmapblocks = ones: mount failed (32).
+rmapblocks = firstbit: mount failed (32).
+rmapblocks = sub: mount failed (32).
+refcntblocks = ones: mount failed (32).
+refcntblocks = firstbit: mount failed (32).
+refcntblocks = sub: mount failed (32).
+flfirst = ones: mount failed (32).
+flfirst = firstbit: mount failed (32).
+flfirst = middlebit: mount failed (32).
+flfirst = add: mount failed (32).
+flfirst = sub: mount failed (32).
+fllast = ones: mount failed (32).
+fllast = firstbit: mount failed (32).
+fllast = middlebit: mount failed (32).
+fllast = add: mount failed (32).
+fllast = sub: mount failed (32).
+flcount = ones: mount failed (32).
+flcount = firstbit: mount failed (32).
+flcount = middlebit: mount failed (32).
+flcount = add: mount failed (32).
+flcount = sub: mount failed (32).
+freeblks = zeroes: mount failed (32).
+freeblks = ones: mount failed (32).
+freeblks = firstbit: mount failed (32).
+freeblks = middlebit: mount failed (32).
+freeblks = add: mount failed (32).
+freeblks = sub: mount failed (32).
+longest = ones: mount failed (32).
+longest = firstbit: mount failed (32).
+longest = add: mount failed (32).
+btreeblks = ones: mount failed (32).
+btreeblks = firstbit: mount failed (32).
+btreeblks = sub: mount failed (32).
+uuid = zeroes: mount failed (32).
+uuid = ones: mount failed (32).
+uuid = firstbit: mount failed (32).
+uuid = middlebit: mount failed (32).
+uuid = lastbit: mount failed (32).
+crc = zeroes: mount failed (32).
+crc = ones: mount failed (32).
+crc = firstbit: mount failed (32).
+crc = middlebit: mount failed (32).
+crc = lastbit: mount failed (32).
+crc = add: mount failed (32).
+crc = sub: mount failed (32).
 Done fuzzing AGF
diff --git a/tests/xfs/455.out b/tests/xfs/455.out
index ff68505f92..ffe9c557a1 100644
--- a/tests/xfs/455.out
+++ b/tests/xfs/455.out
@@ -1,6 +1,140 @@
 QA output created by 455
 Format and populate
 Fuzz AGFL
+magicnum = zeroes: offline scrub didn't fail.
+magicnum = ones: offline scrub didn't fail.
+magicnum = firstbit: offline scrub didn't fail.
+magicnum = middlebit: offline scrub didn't fail.
+magicnum = lastbit: offline scrub didn't fail.
+magicnum = add: offline scrub didn't fail.
+magicnum = sub: offline scrub didn't fail.
+seqno = ones: offline scrub didn't fail.
+seqno = firstbit: offline scrub didn't fail.
+seqno = middlebit: offline scrub didn't fail.
+seqno = lastbit: offline scrub didn't fail.
+seqno = add: offline scrub didn't fail.
+seqno = sub: offline scrub didn't fail.
+uuid = zeroes: offline scrub didn't fail.
+uuid = ones: offline scrub didn't fail.
+uuid = firstbit: offline scrub didn't fail.
+uuid = middlebit: offline scrub didn't fail.
+uuid = lastbit: offline scrub didn't fail.
+bno[0] = zeroes: offline scrub didn't fail.
+bno[0] = zeroes: online scrub didn't fail.
+bno[0] = firstbit: offline scrub didn't fail.
+bno[0] = middlebit: offline scrub didn't fail.
+bno[0] = lastbit: offline scrub didn't fail.
+bno[0] = add: offline scrub didn't fail.
+bno[0] = add: online scrub didn't fail.
+bno[0] = sub: offline scrub didn't fail.
+bno[1] = zeroes: offline scrub didn't fail.
+bno[1] = zeroes: online scrub didn't fail.
+bno[1] = ones: offline scrub didn't fail.
+bno[1] = ones: online scrub didn't fail.
+bno[1] = firstbit: offline scrub didn't fail.
+bno[1] = middlebit: offline scrub didn't fail.
+bno[1] = middlebit: online scrub didn't fail.
+bno[1] = lastbit: offline scrub didn't fail.
+bno[1] = lastbit: online scrub didn't fail.
+bno[1] = add: offline scrub didn't fail.
+bno[1] = add: online scrub didn't fail.
+bno[1] = sub: offline scrub didn't fail.
+bno[2] = zeroes: offline scrub didn't fail.
+bno[2] = zeroes: online scrub didn't fail.
+bno[2] = ones: offline scrub didn't fail.
+bno[2] = ones: online scrub didn't fail.
+bno[2] = firstbit: offline scrub didn't fail.
+bno[2] = middlebit: offline scrub didn't fail.
+bno[2] = middlebit: online scrub didn't fail.
+bno[2] = lastbit: offline scrub didn't fail.
+bno[2] = lastbit: online scrub didn't fail.
+bno[2] = add: offline scrub didn't fail.
+bno[2] = add: online scrub didn't fail.
+bno[2] = sub: offline scrub didn't fail.
+bno[3] = zeroes: offline scrub didn't fail.
+bno[3] = zeroes: online scrub didn't fail.
+bno[3] = ones: offline scrub didn't fail.
+bno[3] = ones: online scrub didn't fail.
+bno[3] = firstbit: offline scrub didn't fail.
+bno[3] = middlebit: offline scrub didn't fail.
+bno[3] = middlebit: online scrub didn't fail.
+bno[3] = lastbit: offline scrub didn't fail.
+bno[3] = lastbit: online scrub didn't fail.
+bno[3] = add: offline scrub didn't fail.
+bno[3] = add: online scrub didn't fail.
+bno[3] = sub: offline scrub didn't fail.
+bno[4] = zeroes: offline scrub didn't fail.
+bno[4] = zeroes: online scrub didn't fail.
+bno[4] = ones: offline scrub didn't fail.
+bno[4] = ones: online scrub didn't fail.
+bno[4] = firstbit: offline scrub didn't fail.
+bno[4] = middlebit: offline scrub didn't fail.
+bno[4] = middlebit: online scrub didn't fail.
+bno[4] = lastbit: offline scrub didn't fail.
+bno[4] = lastbit: online scrub didn't fail.
+bno[4] = add: offline scrub didn't fail.
+bno[4] = add: online scrub didn't fail.
+bno[4] = sub: offline scrub didn't fail.
+bno[5] = zeroes: offline scrub didn't fail.
+bno[5] = zeroes: online scrub didn't fail.
+bno[5] = ones: offline scrub didn't fail.
+bno[5] = ones: online scrub didn't fail.
+bno[5] = firstbit: offline scrub didn't fail.
+bno[5] = middlebit: offline scrub didn't fail.
+bno[5] = middlebit: online scrub didn't fail.
+bno[5] = lastbit: offline scrub didn't fail.
+bno[5] = lastbit: online scrub didn't fail.
+bno[5] = add: offline scrub didn't fail.
+bno[5] = add: online scrub didn't fail.
+bno[5] = sub: offline scrub didn't fail.
+bno[6] = zeroes: offline scrub didn't fail.
+bno[6] = zeroes: online scrub didn't fail.
+bno[6] = ones: offline scrub didn't fail.
+bno[6] = ones: online scrub didn't fail.
+bno[6] = firstbit: offline scrub didn't fail.
+bno[6] = middlebit: offline scrub didn't fail.
+bno[6] = middlebit: online scrub didn't fail.
+bno[6] = lastbit: offline scrub didn't fail.
+bno[6] = lastbit: online scrub didn't fail.
+bno[6] = add: offline scrub didn't fail.
+bno[6] = add: online scrub didn't fail.
+bno[6] = sub: offline scrub didn't fail.
+bno[7] = zeroes: offline scrub didn't fail.
+bno[7] = zeroes: online scrub didn't fail.
+bno[7] = ones: offline scrub didn't fail.
+bno[7] = ones: online scrub didn't fail.
+bno[7] = firstbit: offline scrub didn't fail.
+bno[7] = middlebit: offline scrub didn't fail.
+bno[7] = middlebit: online scrub didn't fail.
+bno[7] = lastbit: offline scrub didn't fail.
+bno[7] = lastbit: online scrub didn't fail.
+bno[7] = add: offline scrub didn't fail.
+bno[7] = add: online scrub didn't fail.
+bno[7] = sub: offline scrub didn't fail.
+bno[8] = zeroes: offline scrub didn't fail.
+bno[8] = zeroes: online scrub didn't fail.
+bno[8] = ones: offline scrub didn't fail.
+bno[8] = ones: online scrub didn't fail.
+bno[8] = firstbit: offline scrub didn't fail.
+bno[8] = middlebit: offline scrub didn't fail.
+bno[8] = middlebit: online scrub didn't fail.
+bno[8] = lastbit: offline scrub didn't fail.
+bno[8] = lastbit: online scrub didn't fail.
+bno[8] = add: offline scrub didn't fail.
+bno[8] = add: online scrub didn't fail.
+bno[8] = sub: offline scrub didn't fail.
+bno[9] = zeroes: offline scrub didn't fail.
+bno[9] = zeroes: online scrub didn't fail.
+bno[9] = ones: offline scrub didn't fail.
+bno[9] = ones: online scrub didn't fail.
+bno[9] = firstbit: offline scrub didn't fail.
+bno[9] = middlebit: offline scrub didn't fail.
+bno[9] = middlebit: online scrub didn't fail.
+bno[9] = lastbit: offline scrub didn't fail.
+bno[9] = lastbit: online scrub didn't fail.
+bno[9] = add: offline scrub didn't fail.
+bno[9] = add: online scrub didn't fail.
+bno[9] = sub: offline scrub didn't fail.
 Done fuzzing AGFL
 Fuzz AGFL flfirst
 Done fuzzing AGFL flfirst
diff --git a/tests/xfs/456.out b/tests/xfs/456.out
index 75c6ef160c..a896b754ed 100644
--- a/tests/xfs/456.out
+++ b/tests/xfs/456.out
@@ -1,4 +1,133 @@
 QA output created by 456
 Format and populate
 Fuzz AGI
+magicnum = zeroes: mount failed (32).
+magicnum = ones: mount failed (32).
+magicnum = firstbit: mount failed (32).
+magicnum = middlebit: mount failed (32).
+magicnum = lastbit: mount failed (32).
+magicnum = add: mount failed (32).
+magicnum = sub: mount failed (32).
+versionnum = zeroes: mount failed (32).
+versionnum = ones: mount failed (32).
+versionnum = firstbit: mount failed (32).
+versionnum = middlebit: mount failed (32).
+versionnum = lastbit: mount failed (32).
+versionnum = add: mount failed (32).
+versionnum = sub: mount failed (32).
+seqno = ones: mount failed (32).
+seqno = firstbit: mount failed (32).
+seqno = middlebit: mount failed (32).
+seqno = lastbit: mount failed (32).
+seqno = add: mount failed (32).
+seqno = sub: mount failed (32).
+length = zeroes: mount failed (32).
+length = ones: mount failed (32).
+length = firstbit: mount failed (32).
+length = middlebit: mount failed (32).
+length = lastbit: mount failed (32).
+length = add: mount failed (32).
+length = sub: mount failed (32).
+root = zeroes: mount failed (32).
+root = ones: mount failed (32).
+root = firstbit: mount failed (32).
+root = middlebit: mount failed (32).
+root = lastbit: mount failed (32).
+root = add: mount failed (32).
+root = sub: mount failed (32).
+level = zeroes: mount failed (32).
+level = ones: mount failed (32).
+level = firstbit: mount failed (32).
+level = middlebit: mount failed (32).
+level = lastbit: mount failed (32).
+level = add: mount failed (32).
+level = sub: mount failed (32).
+newino = zeroes: offline scrub didn't fail.
+newino = ones: offline scrub didn't fail.
+newino = ones: online scrub didn't fail.
+newino = firstbit: offline scrub didn't fail.
+newino = middlebit: offline scrub didn't fail.
+newino = middlebit: online scrub didn't fail.
+newino = lastbit: offline scrub didn't fail.
+newino = lastbit: online scrub didn't fail.
+newino = add: offline scrub didn't fail.
+newino = add: online scrub didn't fail.
+newino = sub: offline scrub didn't fail.
+newino = sub: online scrub didn't fail.
+dirino = zeroes: offline scrub didn't fail.
+dirino = firstbit: offline scrub didn't fail.
+dirino = middlebit: offline scrub didn't fail.
+dirino = lastbit: offline scrub didn't fail.
+dirino = add: offline scrub didn't fail.
+dirino = add: online scrub didn't fail.
+dirino = sub: offline scrub didn't fail.
+unlinked[0] = zeroes: mount failed (32).
+unlinked[0] = firstbit: mount failed (32).
+unlinked[0] = middlebit: mount failed (32).
+unlinked[0] = lastbit: mount failed (32).
+unlinked[0] = sub: mount failed (32).
+unlinked[1] = zeroes: mount failed (32).
+unlinked[1] = firstbit: mount failed (32).
+unlinked[1] = middlebit: mount failed (32).
+unlinked[1] = lastbit: mount failed (32).
+unlinked[1] = sub: mount failed (32).
+unlinked[2] = zeroes: mount failed (32).
+unlinked[2] = firstbit: mount failed (32).
+unlinked[2] = middlebit: mount failed (32).
+unlinked[2] = lastbit: mount failed (32).
+unlinked[2] = sub: mount failed (32).
+unlinked[3] = zeroes: mount failed (32).
+unlinked[3] = firstbit: mount failed (32).
+unlinked[3] = middlebit: mount failed (32).
+unlinked[3] = lastbit: mount failed (32).
+unlinked[3] = sub: mount failed (32).
+unlinked[4] = zeroes: mount failed (32).
+unlinked[4] = firstbit: mount failed (32).
+unlinked[4] = middlebit: mount failed (32).
+unlinked[4] = lastbit: mount failed (32).
+unlinked[4] = sub: mount failed (32).
+unlinked[5] = zeroes: mount failed (32).
+unlinked[5] = firstbit: mount failed (32).
+unlinked[5] = middlebit: mount failed (32).
+unlinked[5] = lastbit: mount failed (32).
+unlinked[5] = sub: mount failed (32).
+unlinked[6] = zeroes: mount failed (32).
+unlinked[6] = firstbit: mount failed (32).
+unlinked[6] = middlebit: mount failed (32).
+unlinked[6] = lastbit: mount failed (32).
+unlinked[6] = sub: mount failed (32).
+unlinked[7] = zeroes: mount failed (32).
+unlinked[7] = firstbit: mount failed (32).
+unlinked[7] = middlebit: mount failed (32).
+unlinked[7] = lastbit: mount failed (32).
+unlinked[7] = sub: mount failed (32).
+unlinked[8] = zeroes: mount failed (32).
+unlinked[8] = firstbit: mount failed (32).
+unlinked[8] = middlebit: mount failed (32).
+unlinked[8] = lastbit: mount failed (32).
+unlinked[8] = sub: mount failed (32).
+unlinked[9] = zeroes: mount failed (32).
+unlinked[9] = firstbit: mount failed (32).
+unlinked[9] = middlebit: mount failed (32).
+unlinked[9] = lastbit: mount failed (32).
+unlinked[9] = sub: mount failed (32).
+uuid = zeroes: mount failed (32).
+uuid = ones: mount failed (32).
+uuid = firstbit: mount failed (32).
+uuid = middlebit: mount failed (32).
+uuid = lastbit: mount failed (32).
+crc = zeroes: mount failed (32).
+crc = ones: mount failed (32).
+crc = firstbit: mount failed (32).
+crc = middlebit: mount failed (32).
+crc = lastbit: mount failed (32).
+crc = add: mount failed (32).
+crc = sub: mount failed (32).
+free_level = zeroes: mount failed (32).
+free_level = ones: mount failed (32).
+free_level = firstbit: mount failed (32).
+free_level = middlebit: mount failed (32).
+free_level = lastbit: mount failed (32).
+free_level = add: mount failed (32).
+free_level = sub: mount failed (32).
 Done fuzzing AGI
diff --git a/tests/xfs/457.out b/tests/xfs/457.out
index 9d5c40150c..414fd7096e 100644
--- a/tests/xfs/457.out
+++ b/tests/xfs/457.out
@@ -1,4 +1,9 @@
 QA output created by 457
 Format and populate
 Fuzz bnobt recs
+leftsib = add: offline scrub didn't fail.
+rightsib = ones: offline scrub didn't fail.
+rightsib = middlebit: offline scrub didn't fail.
+rightsib = lastbit: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
 Done fuzzing bnobt recs
diff --git a/tests/xfs/458.out b/tests/xfs/458.out
index a6ab9879c2..ba9de90280 100644
--- a/tests/xfs/458.out
+++ b/tests/xfs/458.out
@@ -1,4 +1,48 @@
 QA output created by 458
 Format and populate
 Fuzz bnobt keyptr
+leftsib = add: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
+keys[1].startblock = zeroes: offline scrub didn't fail.
+keys[1].startblock = ones: offline scrub didn't fail.
+keys[1].startblock = firstbit: offline scrub didn't fail.
+keys[1].startblock = middlebit: offline scrub didn't fail.
+keys[1].startblock = lastbit: offline scrub didn't fail.
+keys[1].startblock = add: offline scrub didn't fail.
+keys[1].startblock = sub: offline scrub didn't fail.
+keys[1].blockcount = zeroes: offline scrub didn't fail.
+keys[1].blockcount = zeroes: online scrub didn't fail.
+keys[1].blockcount = ones: offline scrub didn't fail.
+keys[1].blockcount = ones: online scrub didn't fail.
+keys[1].blockcount = firstbit: offline scrub didn't fail.
+keys[1].blockcount = firstbit: online scrub didn't fail.
+keys[1].blockcount = middlebit: offline scrub didn't fail.
+keys[1].blockcount = middlebit: online scrub didn't fail.
+keys[1].blockcount = lastbit: offline scrub didn't fail.
+keys[1].blockcount = lastbit: online scrub didn't fail.
+keys[1].blockcount = add: offline scrub didn't fail.
+keys[1].blockcount = add: online scrub didn't fail.
+keys[1].blockcount = sub: offline scrub didn't fail.
+keys[1].blockcount = sub: online scrub didn't fail.
+keys[2].startblock = zeroes: offline scrub didn't fail.
+keys[2].startblock = ones: offline scrub didn't fail.
+keys[2].startblock = firstbit: offline scrub didn't fail.
+keys[2].startblock = middlebit: offline scrub didn't fail.
+keys[2].startblock = lastbit: offline scrub didn't fail.
+keys[2].startblock = add: offline scrub didn't fail.
+keys[2].startblock = sub: offline scrub didn't fail.
+keys[2].blockcount = zeroes: offline scrub didn't fail.
+keys[2].blockcount = zeroes: online scrub didn't fail.
+keys[2].blockcount = ones: offline scrub didn't fail.
+keys[2].blockcount = ones: online scrub didn't fail.
+keys[2].blockcount = firstbit: offline scrub didn't fail.
+keys[2].blockcount = firstbit: online scrub didn't fail.
+keys[2].blockcount = middlebit: offline scrub didn't fail.
+keys[2].blockcount = middlebit: online scrub didn't fail.
+keys[2].blockcount = lastbit: offline scrub didn't fail.
+keys[2].blockcount = lastbit: online scrub didn't fail.
+keys[2].blockcount = add: offline scrub didn't fail.
+keys[2].blockcount = add: online scrub didn't fail.
+keys[2].blockcount = sub: offline scrub didn't fail.
+keys[2].blockcount = sub: online scrub didn't fail.
 Done fuzzing bnobt keyptr
diff --git a/tests/xfs/459.out b/tests/xfs/459.out
index 3100f78360..9b39b14e97 100644
--- a/tests/xfs/459.out
+++ b/tests/xfs/459.out
@@ -1,4 +1,9 @@
 QA output created by 459
 Format and populate
 Fuzz cntbt
+leftsib = add: offline scrub didn't fail.
+rightsib = ones: offline scrub didn't fail.
+rightsib = middlebit: offline scrub didn't fail.
+rightsib = lastbit: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
 Done fuzzing cntbt
diff --git a/tests/xfs/460.out b/tests/xfs/460.out
index 3ca46b4c4c..e8bb9625ab 100644
--- a/tests/xfs/460.out
+++ b/tests/xfs/460.out
@@ -1,4 +1,10 @@
 QA output created by 460
 Format and populate
 Fuzz inobt
+leftsib = add: offline scrub didn't fail.
+rightsib = ones: offline scrub didn't fail.
+rightsib = middlebit: offline scrub didn't fail.
+rightsib = lastbit: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
+rightsib = sub: offline scrub didn't fail.
 Done fuzzing inobt
diff --git a/tests/xfs/461.out b/tests/xfs/461.out
index 8d616bf2fd..429b1711d1 100644
--- a/tests/xfs/461.out
+++ b/tests/xfs/461.out
@@ -1,4 +1,10 @@
 QA output created by 461
 Format and populate
 Fuzz finobt
+leftsib = add: offline scrub didn't fail.
+rightsib = ones: offline scrub didn't fail.
+rightsib = middlebit: offline scrub didn't fail.
+rightsib = lastbit: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
+rightsib = sub: offline scrub didn't fail.
 Done fuzzing finobt
diff --git a/tests/xfs/462.out b/tests/xfs/462.out
index 4ff2d33b7c..842095dc9b 100644
--- a/tests/xfs/462.out
+++ b/tests/xfs/462.out
@@ -1,4 +1,12 @@
 QA output created by 462
 Format and populate
 Fuzz rmapbt recs
+leftsib = add: offline scrub didn't fail.
+rightsib = ones: offline scrub didn't fail.
+rightsib = middlebit: offline scrub didn't fail.
+rightsib = lastbit: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
+recs[3].startblock = lastbit: offline scrub didn't fail.
+recs[3].blockcount = lastbit: offline scrub didn't fail.
+recs[6].owner = lastbit: offline scrub didn't fail.
 Done fuzzing rmapbt recs
diff --git a/tests/xfs/463.out b/tests/xfs/463.out
index 87d2eef540..a7482abdb9 100644
--- a/tests/xfs/463.out
+++ b/tests/xfs/463.out
@@ -1,4 +1,529 @@
 QA output created by 463
 Format and populate
 Fuzz rmapbt keyptr
+leftsib = add: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
+keys[1].startblock = lastbit: offline scrub didn't fail.
+keys[1].owner = zeroes: offline scrub didn't fail.
+keys[1].owner = ones: offline scrub didn't fail.
+keys[1].owner = firstbit: offline scrub didn't fail.
+keys[1].owner = middlebit: offline scrub didn't fail.
+keys[1].owner = lastbit: offline scrub didn't fail.
+keys[1].owner = add: offline scrub didn't fail.
+keys[1].owner = sub: offline scrub didn't fail.
+keys[1].offset = ones: offline scrub didn't fail.
+keys[1].offset = firstbit: offline scrub didn't fail.
+keys[1].offset = middlebit: offline scrub didn't fail.
+keys[1].offset = lastbit: offline scrub didn't fail.
+keys[1].offset = add: offline scrub didn't fail.
+keys[1].offset = sub: offline scrub didn't fail.
+keys[1].extentflag = ones: offline scrub didn't fail.
+keys[1].extentflag = ones: online scrub didn't fail.
+keys[1].extentflag = firstbit: offline scrub didn't fail.
+keys[1].extentflag = firstbit: online scrub didn't fail.
+keys[1].extentflag = middlebit: offline scrub didn't fail.
+keys[1].extentflag = middlebit: online scrub didn't fail.
+keys[1].extentflag = lastbit: offline scrub didn't fail.
+keys[1].extentflag = lastbit: online scrub didn't fail.
+keys[1].extentflag = add: offline scrub didn't fail.
+keys[1].extentflag = add: online scrub didn't fail.
+keys[1].extentflag = sub: offline scrub didn't fail.
+keys[1].extentflag = sub: online scrub didn't fail.
+keys[1].attrfork = ones: offline scrub didn't fail.
+keys[1].attrfork = firstbit: offline scrub didn't fail.
+keys[1].attrfork = middlebit: offline scrub didn't fail.
+keys[1].attrfork = lastbit: offline scrub didn't fail.
+keys[1].attrfork = add: offline scrub didn't fail.
+keys[1].attrfork = sub: offline scrub didn't fail.
+keys[1].bmbtblock = ones: offline scrub didn't fail.
+keys[1].bmbtblock = firstbit: offline scrub didn't fail.
+keys[1].bmbtblock = middlebit: offline scrub didn't fail.
+keys[1].bmbtblock = lastbit: offline scrub didn't fail.
+keys[1].bmbtblock = add: offline scrub didn't fail.
+keys[1].bmbtblock = sub: offline scrub didn't fail.
+keys[1].startblock_hi = ones: offline scrub didn't fail.
+keys[1].startblock_hi = firstbit: offline scrub didn't fail.
+keys[1].startblock_hi = middlebit: offline scrub didn't fail.
+keys[1].startblock_hi = lastbit: offline scrub didn't fail.
+keys[1].startblock_hi = add: offline scrub didn't fail.
+keys[1].startblock_hi = sub: offline scrub didn't fail.
+keys[1].owner_hi = ones: offline scrub didn't fail.
+keys[1].owner_hi = firstbit: offline scrub didn't fail.
+keys[1].owner_hi = middlebit: offline scrub didn't fail.
+keys[1].owner_hi = lastbit: offline scrub didn't fail.
+keys[1].owner_hi = add: offline scrub didn't fail.
+keys[1].owner_hi = sub: offline scrub didn't fail.
+keys[1].offset_hi = ones: offline scrub didn't fail.
+keys[1].offset_hi = firstbit: offline scrub didn't fail.
+keys[1].offset_hi = middlebit: offline scrub didn't fail.
+keys[1].offset_hi = add: offline scrub didn't fail.
+keys[1].offset_hi = sub: offline scrub didn't fail.
+keys[1].extentflag_hi = ones: offline scrub didn't fail.
+keys[1].extentflag_hi = ones: online scrub didn't fail.
+keys[1].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[1].extentflag_hi = firstbit: online scrub didn't fail.
+keys[1].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[1].extentflag_hi = middlebit: online scrub didn't fail.
+keys[1].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[1].extentflag_hi = lastbit: online scrub didn't fail.
+keys[1].extentflag_hi = add: offline scrub didn't fail.
+keys[1].extentflag_hi = add: online scrub didn't fail.
+keys[1].extentflag_hi = sub: offline scrub didn't fail.
+keys[1].extentflag_hi = sub: online scrub didn't fail.
+keys[1].attrfork_hi = ones: offline scrub didn't fail.
+keys[1].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[1].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[1].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[1].attrfork_hi = add: offline scrub didn't fail.
+keys[1].attrfork_hi = sub: offline scrub didn't fail.
+keys[1].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[1].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[1].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[1].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[1].bmbtblock_hi = add: offline scrub didn't fail.
+keys[1].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[2].owner = zeroes: offline scrub didn't fail.
+keys[2].offset = zeroes: offline scrub didn't fail.
+keys[2].offset = lastbit: offline scrub didn't fail.
+keys[2].extentflag = ones: offline scrub didn't fail.
+keys[2].extentflag = ones: online scrub didn't fail.
+keys[2].extentflag = firstbit: offline scrub didn't fail.
+keys[2].extentflag = firstbit: online scrub didn't fail.
+keys[2].extentflag = middlebit: offline scrub didn't fail.
+keys[2].extentflag = middlebit: online scrub didn't fail.
+keys[2].extentflag = lastbit: offline scrub didn't fail.
+keys[2].extentflag = lastbit: online scrub didn't fail.
+keys[2].extentflag = add: offline scrub didn't fail.
+keys[2].extentflag = add: online scrub didn't fail.
+keys[2].extentflag = sub: offline scrub didn't fail.
+keys[2].extentflag = sub: online scrub didn't fail.
+keys[2].startblock_hi = ones: offline scrub didn't fail.
+keys[2].startblock_hi = firstbit: offline scrub didn't fail.
+keys[2].startblock_hi = middlebit: offline scrub didn't fail.
+keys[2].startblock_hi = lastbit: offline scrub didn't fail.
+keys[2].startblock_hi = add: offline scrub didn't fail.
+keys[2].startblock_hi = sub: offline scrub didn't fail.
+keys[2].owner_hi = ones: offline scrub didn't fail.
+keys[2].owner_hi = firstbit: offline scrub didn't fail.
+keys[2].owner_hi = middlebit: offline scrub didn't fail.
+keys[2].owner_hi = lastbit: offline scrub didn't fail.
+keys[2].owner_hi = add: offline scrub didn't fail.
+keys[2].owner_hi = sub: offline scrub didn't fail.
+keys[2].offset_hi = ones: offline scrub didn't fail.
+keys[2].offset_hi = firstbit: offline scrub didn't fail.
+keys[2].offset_hi = middlebit: offline scrub didn't fail.
+keys[2].offset_hi = add: offline scrub didn't fail.
+keys[2].offset_hi = sub: offline scrub didn't fail.
+keys[2].extentflag_hi = ones: offline scrub didn't fail.
+keys[2].extentflag_hi = ones: online scrub didn't fail.
+keys[2].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[2].extentflag_hi = firstbit: online scrub didn't fail.
+keys[2].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[2].extentflag_hi = middlebit: online scrub didn't fail.
+keys[2].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[2].extentflag_hi = lastbit: online scrub didn't fail.
+keys[2].extentflag_hi = add: offline scrub didn't fail.
+keys[2].extentflag_hi = add: online scrub didn't fail.
+keys[2].extentflag_hi = sub: offline scrub didn't fail.
+keys[2].extentflag_hi = sub: online scrub didn't fail.
+keys[2].attrfork_hi = ones: offline scrub didn't fail.
+keys[2].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[2].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[2].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[2].attrfork_hi = add: offline scrub didn't fail.
+keys[2].attrfork_hi = sub: offline scrub didn't fail.
+keys[2].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[2].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[2].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[2].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[2].bmbtblock_hi = add: offline scrub didn't fail.
+keys[2].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[3].owner = zeroes: offline scrub didn't fail.
+keys[3].offset = zeroes: offline scrub didn't fail.
+keys[3].offset = lastbit: offline scrub didn't fail.
+keys[3].extentflag = ones: offline scrub didn't fail.
+keys[3].extentflag = ones: online scrub didn't fail.
+keys[3].extentflag = firstbit: offline scrub didn't fail.
+keys[3].extentflag = firstbit: online scrub didn't fail.
+keys[3].extentflag = middlebit: offline scrub didn't fail.
+keys[3].extentflag = middlebit: online scrub didn't fail.
+keys[3].extentflag = lastbit: offline scrub didn't fail.
+keys[3].extentflag = lastbit: online scrub didn't fail.
+keys[3].extentflag = add: offline scrub didn't fail.
+keys[3].extentflag = add: online scrub didn't fail.
+keys[3].extentflag = sub: offline scrub didn't fail.
+keys[3].extentflag = sub: online scrub didn't fail.
+keys[3].startblock_hi = ones: offline scrub didn't fail.
+keys[3].startblock_hi = firstbit: offline scrub didn't fail.
+keys[3].startblock_hi = middlebit: offline scrub didn't fail.
+keys[3].startblock_hi = lastbit: offline scrub didn't fail.
+keys[3].startblock_hi = add: offline scrub didn't fail.
+keys[3].startblock_hi = sub: offline scrub didn't fail.
+keys[3].owner_hi = ones: offline scrub didn't fail.
+keys[3].owner_hi = firstbit: offline scrub didn't fail.
+keys[3].owner_hi = middlebit: offline scrub didn't fail.
+keys[3].owner_hi = lastbit: offline scrub didn't fail.
+keys[3].owner_hi = add: offline scrub didn't fail.
+keys[3].offset_hi = ones: offline scrub didn't fail.
+keys[3].offset_hi = firstbit: offline scrub didn't fail.
+keys[3].offset_hi = middlebit: offline scrub didn't fail.
+keys[3].offset_hi = add: offline scrub didn't fail.
+keys[3].offset_hi = sub: offline scrub didn't fail.
+keys[3].extentflag_hi = ones: offline scrub didn't fail.
+keys[3].extentflag_hi = ones: online scrub didn't fail.
+keys[3].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[3].extentflag_hi = firstbit: online scrub didn't fail.
+keys[3].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[3].extentflag_hi = middlebit: online scrub didn't fail.
+keys[3].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[3].extentflag_hi = lastbit: online scrub didn't fail.
+keys[3].extentflag_hi = add: offline scrub didn't fail.
+keys[3].extentflag_hi = add: online scrub didn't fail.
+keys[3].extentflag_hi = sub: offline scrub didn't fail.
+keys[3].extentflag_hi = sub: online scrub didn't fail.
+keys[3].attrfork_hi = ones: offline scrub didn't fail.
+keys[3].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[3].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[3].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[3].attrfork_hi = add: offline scrub didn't fail.
+keys[3].attrfork_hi = sub: offline scrub didn't fail.
+keys[3].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[3].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[3].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[3].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[3].bmbtblock_hi = add: offline scrub didn't fail.
+keys[3].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[4].owner = zeroes: offline scrub didn't fail.
+keys[4].owner = sub: offline scrub didn't fail.
+keys[4].offset = zeroes: offline scrub didn't fail.
+keys[4].offset = lastbit: offline scrub didn't fail.
+keys[4].extentflag = ones: offline scrub didn't fail.
+keys[4].extentflag = ones: online scrub didn't fail.
+keys[4].extentflag = firstbit: offline scrub didn't fail.
+keys[4].extentflag = firstbit: online scrub didn't fail.
+keys[4].extentflag = middlebit: offline scrub didn't fail.
+keys[4].extentflag = middlebit: online scrub didn't fail.
+keys[4].extentflag = lastbit: offline scrub didn't fail.
+keys[4].extentflag = lastbit: online scrub didn't fail.
+keys[4].extentflag = add: offline scrub didn't fail.
+keys[4].extentflag = add: online scrub didn't fail.
+keys[4].extentflag = sub: offline scrub didn't fail.
+keys[4].extentflag = sub: online scrub didn't fail.
+keys[4].startblock_hi = ones: offline scrub didn't fail.
+keys[4].startblock_hi = firstbit: offline scrub didn't fail.
+keys[4].startblock_hi = middlebit: offline scrub didn't fail.
+keys[4].startblock_hi = lastbit: offline scrub didn't fail.
+keys[4].startblock_hi = add: offline scrub didn't fail.
+keys[4].startblock_hi = sub: offline scrub didn't fail.
+keys[4].owner_hi = ones: offline scrub didn't fail.
+keys[4].owner_hi = firstbit: offline scrub didn't fail.
+keys[4].owner_hi = middlebit: offline scrub didn't fail.
+keys[4].owner_hi = lastbit: offline scrub didn't fail.
+keys[4].owner_hi = add: offline scrub didn't fail.
+keys[4].offset_hi = ones: offline scrub didn't fail.
+keys[4].offset_hi = firstbit: offline scrub didn't fail.
+keys[4].offset_hi = middlebit: offline scrub didn't fail.
+keys[4].offset_hi = add: offline scrub didn't fail.
+keys[4].offset_hi = sub: offline scrub didn't fail.
+keys[4].extentflag_hi = ones: offline scrub didn't fail.
+keys[4].extentflag_hi = ones: online scrub didn't fail.
+keys[4].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[4].extentflag_hi = firstbit: online scrub didn't fail.
+keys[4].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[4].extentflag_hi = middlebit: online scrub didn't fail.
+keys[4].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[4].extentflag_hi = lastbit: online scrub didn't fail.
+keys[4].extentflag_hi = add: offline scrub didn't fail.
+keys[4].extentflag_hi = add: online scrub didn't fail.
+keys[4].extentflag_hi = sub: offline scrub didn't fail.
+keys[4].extentflag_hi = sub: online scrub didn't fail.
+keys[4].attrfork_hi = ones: offline scrub didn't fail.
+keys[4].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[4].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[4].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[4].attrfork_hi = add: offline scrub didn't fail.
+keys[4].attrfork_hi = sub: offline scrub didn't fail.
+keys[4].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[4].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[4].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[4].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[4].bmbtblock_hi = add: offline scrub didn't fail.
+keys[4].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[5].owner = zeroes: offline scrub didn't fail.
+keys[5].owner = sub: offline scrub didn't fail.
+keys[5].offset = zeroes: offline scrub didn't fail.
+keys[5].offset = lastbit: offline scrub didn't fail.
+keys[5].extentflag = ones: offline scrub didn't fail.
+keys[5].extentflag = ones: online scrub didn't fail.
+keys[5].extentflag = firstbit: offline scrub didn't fail.
+keys[5].extentflag = firstbit: online scrub didn't fail.
+keys[5].extentflag = middlebit: offline scrub didn't fail.
+keys[5].extentflag = middlebit: online scrub didn't fail.
+keys[5].extentflag = lastbit: offline scrub didn't fail.
+keys[5].extentflag = lastbit: online scrub didn't fail.
+keys[5].extentflag = add: offline scrub didn't fail.
+keys[5].extentflag = add: online scrub didn't fail.
+keys[5].extentflag = sub: offline scrub didn't fail.
+keys[5].extentflag = sub: online scrub didn't fail.
+keys[5].startblock_hi = ones: offline scrub didn't fail.
+keys[5].startblock_hi = firstbit: offline scrub didn't fail.
+keys[5].startblock_hi = middlebit: offline scrub didn't fail.
+keys[5].startblock_hi = lastbit: offline scrub didn't fail.
+keys[5].startblock_hi = add: offline scrub didn't fail.
+keys[5].startblock_hi = sub: offline scrub didn't fail.
+keys[5].owner_hi = ones: offline scrub didn't fail.
+keys[5].owner_hi = firstbit: offline scrub didn't fail.
+keys[5].owner_hi = middlebit: offline scrub didn't fail.
+keys[5].owner_hi = lastbit: offline scrub didn't fail.
+keys[5].owner_hi = add: offline scrub didn't fail.
+keys[5].offset_hi = ones: offline scrub didn't fail.
+keys[5].offset_hi = firstbit: offline scrub didn't fail.
+keys[5].offset_hi = middlebit: offline scrub didn't fail.
+keys[5].offset_hi = add: offline scrub didn't fail.
+keys[5].offset_hi = sub: offline scrub didn't fail.
+keys[5].extentflag_hi = ones: offline scrub didn't fail.
+keys[5].extentflag_hi = ones: online scrub didn't fail.
+keys[5].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[5].extentflag_hi = firstbit: online scrub didn't fail.
+keys[5].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[5].extentflag_hi = middlebit: online scrub didn't fail.
+keys[5].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[5].extentflag_hi = lastbit: online scrub didn't fail.
+keys[5].extentflag_hi = add: offline scrub didn't fail.
+keys[5].extentflag_hi = add: online scrub didn't fail.
+keys[5].extentflag_hi = sub: offline scrub didn't fail.
+keys[5].extentflag_hi = sub: online scrub didn't fail.
+keys[5].attrfork_hi = ones: offline scrub didn't fail.
+keys[5].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[5].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[5].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[5].attrfork_hi = add: offline scrub didn't fail.
+keys[5].attrfork_hi = sub: offline scrub didn't fail.
+keys[5].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[5].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[5].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[5].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[5].bmbtblock_hi = add: offline scrub didn't fail.
+keys[5].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[6].owner = zeroes: offline scrub didn't fail.
+keys[6].owner = sub: offline scrub didn't fail.
+keys[6].offset = zeroes: offline scrub didn't fail.
+keys[6].offset = lastbit: offline scrub didn't fail.
+keys[6].extentflag = ones: offline scrub didn't fail.
+keys[6].extentflag = ones: online scrub didn't fail.
+keys[6].extentflag = firstbit: offline scrub didn't fail.
+keys[6].extentflag = firstbit: online scrub didn't fail.
+keys[6].extentflag = middlebit: offline scrub didn't fail.
+keys[6].extentflag = middlebit: online scrub didn't fail.
+keys[6].extentflag = lastbit: offline scrub didn't fail.
+keys[6].extentflag = lastbit: online scrub didn't fail.
+keys[6].extentflag = add: offline scrub didn't fail.
+keys[6].extentflag = add: online scrub didn't fail.
+keys[6].extentflag = sub: offline scrub didn't fail.
+keys[6].extentflag = sub: online scrub didn't fail.
+keys[6].startblock_hi = ones: offline scrub didn't fail.
+keys[6].startblock_hi = firstbit: offline scrub didn't fail.
+keys[6].startblock_hi = middlebit: offline scrub didn't fail.
+keys[6].startblock_hi = lastbit: offline scrub didn't fail.
+keys[6].startblock_hi = add: offline scrub didn't fail.
+keys[6].owner_hi = ones: offline scrub didn't fail.
+keys[6].owner_hi = firstbit: offline scrub didn't fail.
+keys[6].owner_hi = middlebit: offline scrub didn't fail.
+keys[6].owner_hi = lastbit: offline scrub didn't fail.
+keys[6].owner_hi = add: offline scrub didn't fail.
+keys[6].offset_hi = ones: offline scrub didn't fail.
+keys[6].offset_hi = firstbit: offline scrub didn't fail.
+keys[6].offset_hi = middlebit: offline scrub didn't fail.
+keys[6].offset_hi = add: offline scrub didn't fail.
+keys[6].offset_hi = sub: offline scrub didn't fail.
+keys[6].extentflag_hi = ones: offline scrub didn't fail.
+keys[6].extentflag_hi = ones: online scrub didn't fail.
+keys[6].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[6].extentflag_hi = firstbit: online scrub didn't fail.
+keys[6].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[6].extentflag_hi = middlebit: online scrub didn't fail.
+keys[6].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[6].extentflag_hi = lastbit: online scrub didn't fail.
+keys[6].extentflag_hi = add: offline scrub didn't fail.
+keys[6].extentflag_hi = add: online scrub didn't fail.
+keys[6].extentflag_hi = sub: offline scrub didn't fail.
+keys[6].extentflag_hi = sub: online scrub didn't fail.
+keys[6].attrfork_hi = ones: offline scrub didn't fail.
+keys[6].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[6].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[6].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[6].attrfork_hi = add: offline scrub didn't fail.
+keys[6].attrfork_hi = sub: offline scrub didn't fail.
+keys[6].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[6].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[6].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[6].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[6].bmbtblock_hi = add: offline scrub didn't fail.
+keys[6].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[7].owner = zeroes: offline scrub didn't fail.
+keys[7].owner = lastbit: offline scrub didn't fail.
+keys[7].owner = sub: offline scrub didn't fail.
+keys[7].offset = zeroes: offline scrub didn't fail.
+keys[7].offset = lastbit: offline scrub didn't fail.
+keys[7].extentflag = ones: offline scrub didn't fail.
+keys[7].extentflag = ones: online scrub didn't fail.
+keys[7].extentflag = firstbit: offline scrub didn't fail.
+keys[7].extentflag = firstbit: online scrub didn't fail.
+keys[7].extentflag = middlebit: offline scrub didn't fail.
+keys[7].extentflag = middlebit: online scrub didn't fail.
+keys[7].extentflag = lastbit: offline scrub didn't fail.
+keys[7].extentflag = lastbit: online scrub didn't fail.
+keys[7].extentflag = add: offline scrub didn't fail.
+keys[7].extentflag = add: online scrub didn't fail.
+keys[7].extentflag = sub: offline scrub didn't fail.
+keys[7].extentflag = sub: online scrub didn't fail.
+keys[7].startblock_hi = ones: offline scrub didn't fail.
+keys[7].startblock_hi = firstbit: offline scrub didn't fail.
+keys[7].startblock_hi = middlebit: offline scrub didn't fail.
+keys[7].startblock_hi = lastbit: offline scrub didn't fail.
+keys[7].startblock_hi = add: offline scrub didn't fail.
+keys[7].owner_hi = ones: offline scrub didn't fail.
+keys[7].owner_hi = firstbit: offline scrub didn't fail.
+keys[7].owner_hi = middlebit: offline scrub didn't fail.
+keys[7].owner_hi = add: offline scrub didn't fail.
+keys[7].offset_hi = ones: offline scrub didn't fail.
+keys[7].offset_hi = firstbit: offline scrub didn't fail.
+keys[7].offset_hi = middlebit: offline scrub didn't fail.
+keys[7].offset_hi = add: offline scrub didn't fail.
+keys[7].offset_hi = sub: offline scrub didn't fail.
+keys[7].extentflag_hi = ones: offline scrub didn't fail.
+keys[7].extentflag_hi = ones: online scrub didn't fail.
+keys[7].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[7].extentflag_hi = firstbit: online scrub didn't fail.
+keys[7].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[7].extentflag_hi = middlebit: online scrub didn't fail.
+keys[7].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[7].extentflag_hi = lastbit: online scrub didn't fail.
+keys[7].extentflag_hi = add: offline scrub didn't fail.
+keys[7].extentflag_hi = add: online scrub didn't fail.
+keys[7].extentflag_hi = sub: offline scrub didn't fail.
+keys[7].extentflag_hi = sub: online scrub didn't fail.
+keys[7].attrfork_hi = ones: offline scrub didn't fail.
+keys[7].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[7].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[7].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[7].attrfork_hi = add: offline scrub didn't fail.
+keys[7].attrfork_hi = sub: offline scrub didn't fail.
+keys[7].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[7].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[7].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[7].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[7].bmbtblock_hi = add: offline scrub didn't fail.
+keys[7].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[8].owner = zeroes: offline scrub didn't fail.
+keys[8].owner = lastbit: offline scrub didn't fail.
+keys[8].owner = sub: offline scrub didn't fail.
+keys[8].offset = zeroes: offline scrub didn't fail.
+keys[8].offset = lastbit: offline scrub didn't fail.
+keys[8].extentflag = ones: offline scrub didn't fail.
+keys[8].extentflag = ones: online scrub didn't fail.
+keys[8].extentflag = firstbit: offline scrub didn't fail.
+keys[8].extentflag = firstbit: online scrub didn't fail.
+keys[8].extentflag = middlebit: offline scrub didn't fail.
+keys[8].extentflag = middlebit: online scrub didn't fail.
+keys[8].extentflag = lastbit: offline scrub didn't fail.
+keys[8].extentflag = lastbit: online scrub didn't fail.
+keys[8].extentflag = add: offline scrub didn't fail.
+keys[8].extentflag = add: online scrub didn't fail.
+keys[8].extentflag = sub: offline scrub didn't fail.
+keys[8].extentflag = sub: online scrub didn't fail.
+keys[8].startblock_hi = ones: offline scrub didn't fail.
+keys[8].startblock_hi = firstbit: offline scrub didn't fail.
+keys[8].startblock_hi = middlebit: offline scrub didn't fail.
+keys[8].startblock_hi = lastbit: offline scrub didn't fail.
+keys[8].startblock_hi = add: offline scrub didn't fail.
+keys[8].owner_hi = ones: offline scrub didn't fail.
+keys[8].owner_hi = firstbit: offline scrub didn't fail.
+keys[8].owner_hi = middlebit: offline scrub didn't fail.
+keys[8].owner_hi = lastbit: offline scrub didn't fail.
+keys[8].owner_hi = add: offline scrub didn't fail.
+keys[8].offset_hi = ones: offline scrub didn't fail.
+keys[8].offset_hi = firstbit: offline scrub didn't fail.
+keys[8].offset_hi = middlebit: offline scrub didn't fail.
+keys[8].offset_hi = add: offline scrub didn't fail.
+keys[8].offset_hi = sub: offline scrub didn't fail.
+keys[8].extentflag_hi = ones: offline scrub didn't fail.
+keys[8].extentflag_hi = ones: online scrub didn't fail.
+keys[8].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[8].extentflag_hi = firstbit: online scrub didn't fail.
+keys[8].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[8].extentflag_hi = middlebit: online scrub didn't fail.
+keys[8].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[8].extentflag_hi = lastbit: online scrub didn't fail.
+keys[8].extentflag_hi = add: offline scrub didn't fail.
+keys[8].extentflag_hi = add: online scrub didn't fail.
+keys[8].extentflag_hi = sub: offline scrub didn't fail.
+keys[8].extentflag_hi = sub: online scrub didn't fail.
+keys[8].attrfork_hi = ones: offline scrub didn't fail.
+keys[8].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[8].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[8].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[8].attrfork_hi = add: offline scrub didn't fail.
+keys[8].attrfork_hi = sub: offline scrub didn't fail.
+keys[8].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[8].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[8].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[8].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[8].bmbtblock_hi = add: offline scrub didn't fail.
+keys[8].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[9].owner = zeroes: offline scrub didn't fail.
+keys[9].owner = sub: offline scrub didn't fail.
+keys[9].offset = zeroes: offline scrub didn't fail.
+keys[9].offset = lastbit: offline scrub didn't fail.
+keys[9].extentflag = ones: offline scrub didn't fail.
+keys[9].extentflag = ones: online scrub didn't fail.
+keys[9].extentflag = firstbit: offline scrub didn't fail.
+keys[9].extentflag = firstbit: online scrub didn't fail.
+keys[9].extentflag = middlebit: offline scrub didn't fail.
+keys[9].extentflag = middlebit: online scrub didn't fail.
+keys[9].extentflag = lastbit: offline scrub didn't fail.
+keys[9].extentflag = lastbit: online scrub didn't fail.
+keys[9].extentflag = add: offline scrub didn't fail.
+keys[9].extentflag = add: online scrub didn't fail.
+keys[9].extentflag = sub: offline scrub didn't fail.
+keys[9].extentflag = sub: online scrub didn't fail.
+keys[9].startblock_hi = ones: offline scrub didn't fail.
+keys[9].startblock_hi = firstbit: offline scrub didn't fail.
+keys[9].startblock_hi = middlebit: offline scrub didn't fail.
+keys[9].startblock_hi = lastbit: offline scrub didn't fail.
+keys[9].startblock_hi = add: offline scrub didn't fail.
+keys[9].owner_hi = ones: offline scrub didn't fail.
+keys[9].owner_hi = firstbit: offline scrub didn't fail.
+keys[9].owner_hi = middlebit: offline scrub didn't fail.
+keys[9].owner_hi = lastbit: offline scrub didn't fail.
+keys[9].owner_hi = add: offline scrub didn't fail.
+keys[9].offset_hi = ones: offline scrub didn't fail.
+keys[9].offset_hi = firstbit: offline scrub didn't fail.
+keys[9].offset_hi = middlebit: offline scrub didn't fail.
+keys[9].offset_hi = add: offline scrub didn't fail.
+keys[9].offset_hi = sub: offline scrub didn't fail.
+keys[9].extentflag_hi = ones: offline scrub didn't fail.
+keys[9].extentflag_hi = ones: online scrub didn't fail.
+keys[9].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[9].extentflag_hi = firstbit: online scrub didn't fail.
+keys[9].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[9].extentflag_hi = middlebit: online scrub didn't fail.
+keys[9].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[9].extentflag_hi = lastbit: online scrub didn't fail.
+keys[9].extentflag_hi = add: offline scrub didn't fail.
+keys[9].extentflag_hi = add: online scrub didn't fail.
+keys[9].extentflag_hi = sub: offline scrub didn't fail.
+keys[9].extentflag_hi = sub: online scrub didn't fail.
+keys[9].attrfork_hi = ones: offline scrub didn't fail.
+keys[9].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[9].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[9].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[9].attrfork_hi = add: offline scrub didn't fail.
+keys[9].attrfork_hi = sub: offline scrub didn't fail.
+keys[9].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[9].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[9].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[9].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[9].bmbtblock_hi = add: offline scrub didn't fail.
+keys[9].bmbtblock_hi = sub: offline scrub didn't fail.
 Done fuzzing rmapbt keyptr
diff --git a/tests/xfs/464.out b/tests/xfs/464.out
index fd949298f5..a949fa0875 100644
--- a/tests/xfs/464.out
+++ b/tests/xfs/464.out
@@ -1,4 +1,9 @@
 QA output created by 464
 Format and populate
 Fuzz refcountbt
+leftsib = add: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
+keys[1].startblock = zeroes: offline scrub didn't fail.
+keys[1].startblock = lastbit: offline scrub didn't fail.
+keys[1].startblock = sub: offline scrub didn't fail.
 Done fuzzing refcountbt
diff --git a/tests/xfs/465.out b/tests/xfs/465.out
index bb560881ae..5d8e6818fb 100644
--- a/tests/xfs/465.out
+++ b/tests/xfs/465.out
@@ -2,4 +2,75 @@ QA output created by 465
 Format and populate
 Find btree-format dir inode
 Fuzz inode
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.size = middlebit: offline scrub didn't fail.
+core.size = middlebit: online health check failed (0).
+core.size = lastbit: offline scrub didn't fail.
+core.size = lastbit: online scrub didn't fail.
+core.size = add: offline scrub didn't fail.
+core.size = add: online scrub didn't fail.
+core.size = sub: offline scrub didn't fail.
+core.size = sub: online scrub didn't fail.
+core.rtinherit = ones: offline scrub didn't fail.
+core.rtinherit = ones: online scrub didn't fail.
+core.rtinherit = firstbit: offline scrub didn't fail.
+core.rtinherit = firstbit: online scrub didn't fail.
+core.rtinherit = middlebit: offline scrub didn't fail.
+core.rtinherit = middlebit: online scrub didn't fail.
+core.rtinherit = lastbit: offline scrub didn't fail.
+core.rtinherit = lastbit: online scrub didn't fail.
+core.rtinherit = add: offline scrub didn't fail.
+core.rtinherit = add: online scrub didn't fail.
+core.rtinherit = sub: offline scrub didn't fail.
+core.rtinherit = sub: online scrub didn't fail.
+core.projinherit = ones: offline scrub didn't fail.
+core.projinherit = ones: online scrub didn't fail.
+core.projinherit = firstbit: offline scrub didn't fail.
+core.projinherit = firstbit: online scrub didn't fail.
+core.projinherit = middlebit: offline scrub didn't fail.
+core.projinherit = middlebit: online scrub didn't fail.
+core.projinherit = lastbit: offline scrub didn't fail.
+core.projinherit = lastbit: online scrub didn't fail.
+core.projinherit = add: offline scrub didn't fail.
+core.projinherit = add: online scrub didn't fail.
+core.projinherit = sub: offline scrub didn't fail.
+core.projinherit = sub: online scrub didn't fail.
+core.nosymlinks = ones: offline scrub didn't fail.
+core.nosymlinks = ones: online scrub didn't fail.
+core.nosymlinks = firstbit: offline scrub didn't fail.
+core.nosymlinks = firstbit: online scrub didn't fail.
+core.nosymlinks = middlebit: offline scrub didn't fail.
+core.nosymlinks = middlebit: online scrub didn't fail.
+core.nosymlinks = lastbit: offline scrub didn't fail.
+core.nosymlinks = lastbit: online scrub didn't fail.
+core.nosymlinks = add: offline scrub didn't fail.
+core.nosymlinks = add: online scrub didn't fail.
+core.nosymlinks = sub: offline scrub didn't fail.
+core.nosymlinks = sub: online scrub didn't fail.
+next_unlinked = add: online scrub didn't fail.
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.flags2 = lastbit: offline scrub didn't fail.
+v3.flags2 = lastbit: online scrub didn't fail.
+v3.flags2 = add: online scrub didn't fail.
+u3.bmbt.ptrs[1] = firstbit: offline scrub didn't fail.
+u3.bmbt.ptrs[1] = firstbit: online scrub didn't fail.
 Done fuzzing inode
diff --git a/tests/xfs/466.out b/tests/xfs/466.out
index b1762f2478..b2d84cd0fa 100644
--- a/tests/xfs/466.out
+++ b/tests/xfs/466.out
@@ -2,4 +2,55 @@ QA output created by 466
 Format and populate
 Find extents-format file inode
 Fuzz inode
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.size = zeroes: offline scrub didn't fail.
+core.size = zeroes: online scrub didn't fail.
+core.size = middlebit: offline scrub didn't fail.
+core.size = middlebit: online scrub didn't fail.
+core.size = lastbit: offline scrub didn't fail.
+core.size = lastbit: online scrub didn't fail.
+core.size = add: offline scrub didn't fail.
+core.size = add: online scrub didn't fail.
+core.size = sub: offline scrub didn't fail.
+core.size = sub: online scrub didn't fail.
+next_unlinked = add: online scrub didn't fail.
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.flags2 = lastbit: offline scrub didn't fail.
+v3.flags2 = lastbit: online scrub didn't fail.
+v3.flags2 = add: online scrub didn't fail.
+v3.reflink = ones: offline scrub didn't fail.
+v3.reflink = ones: online scrub didn't fail.
+v3.reflink = firstbit: offline scrub didn't fail.
+v3.reflink = firstbit: online scrub didn't fail.
+v3.reflink = middlebit: offline scrub didn't fail.
+v3.reflink = middlebit: online scrub didn't fail.
+v3.reflink = lastbit: offline scrub didn't fail.
+v3.reflink = lastbit: online scrub didn't fail.
+v3.reflink = add: offline scrub didn't fail.
+v3.reflink = add: online scrub didn't fail.
+v3.reflink = sub: offline scrub didn't fail.
+v3.reflink = sub: online scrub didn't fail.
+u3.bmx[0].startoff = lastbit: pre-mod mount failed (32).
+u3.bmx[0].blockcount = middlebit: pre-mod mount failed (32).
+u3.bmx[0].blockcount = add: pre-mod mount failed (32).
+a.sfattr.list[0].parent_ino = lastbit: online scrub didn't fail.
 Done fuzzing inode
diff --git a/tests/xfs/467.out b/tests/xfs/467.out
index 1ca0e21d40..f68fab8444 100644
--- a/tests/xfs/467.out
+++ b/tests/xfs/467.out
@@ -2,4 +2,51 @@ QA output created by 467
 Format and populate
 Find btree-format file inode
 Fuzz inode
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.size = zeroes: offline scrub didn't fail.
+core.size = zeroes: online scrub didn't fail.
+core.size = middlebit: offline scrub didn't fail.
+core.size = middlebit: online scrub didn't fail.
+core.size = lastbit: offline scrub didn't fail.
+core.size = lastbit: online scrub didn't fail.
+core.size = add: offline scrub didn't fail.
+core.size = add: online scrub didn't fail.
+core.size = sub: offline scrub didn't fail.
+core.size = sub: online scrub didn't fail.
+next_unlinked = add: online scrub didn't fail.
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.flags2 = lastbit: offline scrub didn't fail.
+v3.flags2 = lastbit: online scrub didn't fail.
+v3.flags2 = add: online scrub didn't fail.
+v3.reflink = ones: offline scrub didn't fail.
+v3.reflink = ones: online scrub didn't fail.
+v3.reflink = firstbit: offline scrub didn't fail.
+v3.reflink = firstbit: online scrub didn't fail.
+v3.reflink = middlebit: offline scrub didn't fail.
+v3.reflink = middlebit: online scrub didn't fail.
+v3.reflink = lastbit: offline scrub didn't fail.
+v3.reflink = lastbit: online scrub didn't fail.
+v3.reflink = add: offline scrub didn't fail.
+v3.reflink = add: online scrub didn't fail.
+v3.reflink = sub: offline scrub didn't fail.
+v3.reflink = sub: online scrub didn't fail.
 Done fuzzing inode
diff --git a/tests/xfs/469.out b/tests/xfs/469.out
index 1f514019b8..641a63fee7 100644
--- a/tests/xfs/469.out
+++ b/tests/xfs/469.out
@@ -2,4 +2,12 @@ QA output created by 469
 Format and populate
 Find symlink remote block
 Fuzz symlink remote block
+data = ones: offline scrub didn't fail.
+data = ones: online scrub didn't fail.
+data = firstbit: offline scrub didn't fail.
+data = firstbit: online scrub didn't fail.
+data = middlebit: offline scrub didn't fail.
+data = middlebit: online scrub didn't fail.
+data = lastbit: offline scrub didn't fail.
+data = lastbit: online scrub didn't fail.
 Done fuzzing symlink remote block
diff --git a/tests/xfs/470.out b/tests/xfs/470.out
index 88abc0bc6a..41b0739d9d 100644
--- a/tests/xfs/470.out
+++ b/tests/xfs/470.out
@@ -2,4 +2,83 @@ QA output created by 470
 Format and populate
 Find inline-format dir inode
 Fuzz inline-format dir inode
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.rtinherit = ones: offline scrub didn't fail.
+core.rtinherit = ones: online scrub didn't fail.
+core.rtinherit = firstbit: offline scrub didn't fail.
+core.rtinherit = firstbit: online scrub didn't fail.
+core.rtinherit = middlebit: offline scrub didn't fail.
+core.rtinherit = middlebit: online scrub didn't fail.
+core.rtinherit = lastbit: offline scrub didn't fail.
+core.rtinherit = lastbit: online scrub didn't fail.
+core.rtinherit = add: offline scrub didn't fail.
+core.rtinherit = add: online scrub didn't fail.
+core.rtinherit = sub: offline scrub didn't fail.
+core.rtinherit = sub: online scrub didn't fail.
+core.projinherit = ones: offline scrub didn't fail.
+core.projinherit = ones: online scrub didn't fail.
+core.projinherit = firstbit: offline scrub didn't fail.
+core.projinherit = firstbit: online scrub didn't fail.
+core.projinherit = middlebit: offline scrub didn't fail.
+core.projinherit = middlebit: online scrub didn't fail.
+core.projinherit = lastbit: offline scrub didn't fail.
+core.projinherit = lastbit: online scrub didn't fail.
+core.projinherit = add: offline scrub didn't fail.
+core.projinherit = add: online scrub didn't fail.
+core.projinherit = sub: offline scrub didn't fail.
+core.projinherit = sub: online scrub didn't fail.
+core.nosymlinks = ones: offline scrub didn't fail.
+core.nosymlinks = ones: online scrub didn't fail.
+core.nosymlinks = firstbit: offline scrub didn't fail.
+core.nosymlinks = firstbit: online scrub didn't fail.
+core.nosymlinks = middlebit: offline scrub didn't fail.
+core.nosymlinks = middlebit: online scrub didn't fail.
+core.nosymlinks = lastbit: offline scrub didn't fail.
+core.nosymlinks = lastbit: online scrub didn't fail.
+core.nosymlinks = add: offline scrub didn't fail.
+core.nosymlinks = add: online scrub didn't fail.
+core.nosymlinks = sub: offline scrub didn't fail.
+core.nosymlinks = sub: online scrub didn't fail.
+next_unlinked = add: online scrub didn't fail.
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.flags2 = lastbit: offline scrub didn't fail.
+v3.flags2 = lastbit: online scrub didn't fail.
+v3.flags2 = add: online scrub didn't fail.
+v3.nrext64 = zeroes: offline scrub didn't fail.
+v3.nrext64 = zeroes: online scrub didn't fail.
+v3.nrext64 = firstbit: offline scrub didn't fail.
+v3.nrext64 = firstbit: online scrub didn't fail.
+v3.nrext64 = middlebit: offline scrub didn't fail.
+v3.nrext64 = middlebit: online scrub didn't fail.
+v3.nrext64 = lastbit: offline scrub didn't fail.
+v3.nrext64 = lastbit: online scrub didn't fail.
+v3.nrext64 = add: offline scrub didn't fail.
+v3.nrext64 = add: online scrub didn't fail.
+v3.nrext64 = sub: offline scrub didn't fail.
+v3.nrext64 = sub: online scrub didn't fail.
+u3.sfdir3.list[1].offset = middlebit: offline scrub didn't fail.
+u3.sfdir3.list[1].offset = middlebit: online scrub didn't fail.
+u3.sfdir3.list[1].offset = lastbit: offline scrub didn't fail.
+u3.sfdir3.list[1].offset = lastbit: online scrub didn't fail.
+u3.sfdir3.list[1].offset = add: offline scrub didn't fail.
+u3.sfdir3.list[1].offset = add: online scrub didn't fail.
 Done fuzzing inline-format dir inode
diff --git a/tests/xfs/471.out b/tests/xfs/471.out
index 25e55ff03b..cbc61d9491 100644
--- a/tests/xfs/471.out
+++ b/tests/xfs/471.out
@@ -2,4 +2,11 @@ QA output created by 471
 Format and populate
 Find data-format dir block
 Fuzz data-format dir block
+bhdr.hdr.crc = zeroes: offline scrub didn't fail.
+bhdr.hdr.crc = ones: offline scrub didn't fail.
+bhdr.hdr.crc = firstbit: offline scrub didn't fail.
+bhdr.hdr.crc = middlebit: offline scrub didn't fail.
+bhdr.hdr.crc = lastbit: offline scrub didn't fail.
+bhdr.hdr.crc = add: offline scrub didn't fail.
+bhdr.hdr.crc = sub: offline scrub didn't fail.
 Done fuzzing data-format dir block
diff --git a/tests/xfs/472.out b/tests/xfs/472.out
index 3f4d23acce..a2eead205e 100644
--- a/tests/xfs/472.out
+++ b/tests/xfs/472.out
@@ -2,4 +2,11 @@ QA output created by 472
 Format and populate
 Find data-format dir block
 Fuzz data-format dir block
+dhdr.hdr.crc = zeroes: offline scrub didn't fail.
+dhdr.hdr.crc = ones: offline scrub didn't fail.
+dhdr.hdr.crc = firstbit: offline scrub didn't fail.
+dhdr.hdr.crc = middlebit: offline scrub didn't fail.
+dhdr.hdr.crc = lastbit: offline scrub didn't fail.
+dhdr.hdr.crc = add: offline scrub didn't fail.
+dhdr.hdr.crc = sub: offline scrub didn't fail.
 Done fuzzing data-format dir block
diff --git a/tests/xfs/474.out b/tests/xfs/474.out
index bba106d249..93e1147d3f 100644
--- a/tests/xfs/474.out
+++ b/tests/xfs/474.out
@@ -2,4 +2,11 @@ QA output created by 474
 Format and populate
 Find leafn-format dir block
 Fuzz leafn-format dir block
+lhdr.info.crc = zeroes: offline scrub didn't fail.
+lhdr.info.crc = ones: offline scrub didn't fail.
+lhdr.info.crc = firstbit: offline scrub didn't fail.
+lhdr.info.crc = middlebit: offline scrub didn't fail.
+lhdr.info.crc = lastbit: offline scrub didn't fail.
+lhdr.info.crc = add: offline scrub didn't fail.
+lhdr.info.crc = sub: offline scrub didn't fail.
 Done fuzzing leafn-format dir block
diff --git a/tests/xfs/475.out b/tests/xfs/475.out
index 5e64381922..d4d8b9ec9d 100644
--- a/tests/xfs/475.out
+++ b/tests/xfs/475.out
@@ -2,4 +2,10 @@ QA output created by 475
 Format and populate
 Find node-format dir block
 Fuzz node-format dir block
+nhdr.info.hdr.back = ones: offline scrub didn't fail.
+nhdr.info.hdr.back = firstbit: offline scrub didn't fail.
+nhdr.info.hdr.back = middlebit: offline scrub didn't fail.
+nhdr.info.hdr.back = lastbit: offline scrub didn't fail.
+nhdr.info.hdr.back = add: offline scrub didn't fail.
+nhdr.info.hdr.back = sub: offline scrub didn't fail.
 Done fuzzing node-format dir block
diff --git a/tests/xfs/477.out b/tests/xfs/477.out
index f3dd00ea51..c6f06d5efc 100644
--- a/tests/xfs/477.out
+++ b/tests/xfs/477.out
@@ -2,4 +2,83 @@ QA output created by 477
 Format and populate
 Find inline-format attr inode
 Fuzz inline-format attr inode
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.size = middlebit: offline scrub didn't fail.
+core.size = middlebit: online scrub didn't fail.
+core.size = lastbit: offline scrub didn't fail.
+core.size = lastbit: online scrub didn't fail.
+core.size = add: offline scrub didn't fail.
+core.size = add: online scrub didn't fail.
+next_unlinked = add: online scrub didn't fail.
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.flags2 = lastbit: offline scrub didn't fail.
+v3.flags2 = lastbit: online scrub didn't fail.
+v3.flags2 = add: online scrub didn't fail.
+v3.reflink = ones: offline scrub didn't fail.
+v3.reflink = ones: online scrub didn't fail.
+v3.reflink = firstbit: offline scrub didn't fail.
+v3.reflink = firstbit: online scrub didn't fail.
+v3.reflink = middlebit: offline scrub didn't fail.
+v3.reflink = middlebit: online scrub didn't fail.
+v3.reflink = lastbit: offline scrub didn't fail.
+v3.reflink = lastbit: online scrub didn't fail.
+v3.reflink = add: offline scrub didn't fail.
+v3.reflink = add: online scrub didn't fail.
+v3.reflink = sub: offline scrub didn't fail.
+v3.reflink = sub: online scrub didn't fail.
+v3.nrext64 = zeroes: offline scrub didn't fail.
+v3.nrext64 = zeroes: online scrub didn't fail.
+v3.nrext64 = firstbit: offline scrub didn't fail.
+v3.nrext64 = firstbit: online scrub didn't fail.
+v3.nrext64 = middlebit: offline scrub didn't fail.
+v3.nrext64 = middlebit: online scrub didn't fail.
+v3.nrext64 = lastbit: offline scrub didn't fail.
+v3.nrext64 = lastbit: online scrub didn't fail.
+v3.nrext64 = add: offline scrub didn't fail.
+v3.nrext64 = add: online scrub didn't fail.
+v3.nrext64 = sub: offline scrub didn't fail.
+v3.nrext64 = sub: online scrub didn't fail.
+a.sfattr.list[1].name = ones: offline scrub didn't fail.
+a.sfattr.list[1].name = ones: online scrub didn't fail.
+a.sfattr.list[1].name = firstbit: offline scrub didn't fail.
+a.sfattr.list[1].name = firstbit: online scrub didn't fail.
+a.sfattr.list[1].name = middlebit: offline scrub didn't fail.
+a.sfattr.list[1].name = middlebit: online scrub didn't fail.
+a.sfattr.list[1].name = lastbit: offline scrub didn't fail.
+a.sfattr.list[1].name = lastbit: online scrub didn't fail.
+a.sfattr.list[1].name = add: offline scrub didn't fail.
+a.sfattr.list[1].name = add: online scrub didn't fail.
+a.sfattr.list[1].name = sub: offline scrub didn't fail.
+a.sfattr.list[1].name = sub: online scrub didn't fail.
+a.sfattr.list[2].name = ones: offline scrub didn't fail.
+a.sfattr.list[2].name = ones: online scrub didn't fail.
+a.sfattr.list[2].name = firstbit: offline scrub didn't fail.
+a.sfattr.list[2].name = firstbit: online scrub didn't fail.
+a.sfattr.list[2].name = middlebit: offline scrub didn't fail.
+a.sfattr.list[2].name = middlebit: online scrub didn't fail.
+a.sfattr.list[2].name = lastbit: offline scrub didn't fail.
+a.sfattr.list[2].name = lastbit: online scrub didn't fail.
+a.sfattr.list[2].name = add: offline scrub didn't fail.
+a.sfattr.list[2].name = add: online scrub didn't fail.
+a.sfattr.list[2].name = sub: offline scrub didn't fail.
+a.sfattr.list[2].name = sub: online scrub didn't fail.
 Done fuzzing inline-format attr inode
diff --git a/tests/xfs/478.out b/tests/xfs/478.out
index ff2067f09f..961be25626 100644
--- a/tests/xfs/478.out
+++ b/tests/xfs/478.out
@@ -2,4 +2,95 @@ QA output created by 478
 Format and populate
 Find leaf-format attr block
 Fuzz leaf-format attr block
+hdr.info.crc = zeroes: offline scrub didn't fail.
+hdr.info.crc = ones: offline scrub didn't fail.
+hdr.info.crc = firstbit: offline scrub didn't fail.
+hdr.info.crc = middlebit: offline scrub didn't fail.
+hdr.info.crc = lastbit: offline scrub didn't fail.
+hdr.info.crc = add: offline scrub didn't fail.
+hdr.info.crc = sub: offline scrub didn't fail.
+hdr.firstused = middlebit: online scrub didn't fail.
+hdr.holes = ones: offline scrub didn't fail.
+hdr.holes = ones: online scrub didn't fail.
+hdr.holes = firstbit: offline scrub didn't fail.
+hdr.holes = firstbit: online scrub didn't fail.
+hdr.holes = middlebit: offline scrub didn't fail.
+hdr.holes = middlebit: online scrub didn't fail.
+hdr.holes = lastbit: offline scrub didn't fail.
+hdr.holes = lastbit: online scrub didn't fail.
+hdr.holes = add: offline scrub didn't fail.
+hdr.holes = add: online scrub didn't fail.
+hdr.holes = sub: offline scrub didn't fail.
+hdr.holes = sub: online scrub didn't fail.
+hdr.freemap[0].base = zeroes: offline scrub didn't fail.
+hdr.freemap[0].base = middlebit: offline scrub didn't fail.
+hdr.freemap[0].size = zeroes: offline scrub didn't fail.
+hdr.freemap[0].size = zeroes: online scrub didn't fail.
+hdr.freemap[0].size = middlebit: offline scrub didn't fail.
+hdr.freemap[1].base = middlebit: offline scrub didn't fail.
+hdr.freemap[1].base = middlebit: online scrub didn't fail.
+hdr.freemap[1].size = middlebit: offline scrub didn't fail.
+hdr.freemap[2].base = middlebit: offline scrub didn't fail.
+hdr.freemap[2].base = middlebit: online scrub didn't fail.
+hdr.freemap[2].size = middlebit: offline scrub didn't fail.
+entries[0].incomplete = ones: online scrub didn't fail.
+entries[0].incomplete = firstbit: online scrub didn't fail.
+entries[0].incomplete = middlebit: online scrub didn't fail.
+entries[0].incomplete = lastbit: online scrub didn't fail.
+entries[0].incomplete = add: online scrub didn't fail.
+entries[0].incomplete = sub: online scrub didn't fail.
+entries[1].incomplete = ones: online scrub didn't fail.
+entries[1].incomplete = firstbit: online scrub didn't fail.
+entries[1].incomplete = middlebit: online scrub didn't fail.
+entries[1].incomplete = lastbit: online scrub didn't fail.
+entries[1].incomplete = add: online scrub didn't fail.
+entries[1].incomplete = sub: online scrub didn't fail.
+entries[2].incomplete = ones: online scrub didn't fail.
+entries[2].incomplete = firstbit: online scrub didn't fail.
+entries[2].incomplete = middlebit: online scrub didn't fail.
+entries[2].incomplete = lastbit: online scrub didn't fail.
+entries[2].incomplete = add: online scrub didn't fail.
+entries[2].incomplete = sub: online scrub didn't fail.
+entries[3].incomplete = ones: online scrub didn't fail.
+entries[3].incomplete = firstbit: online scrub didn't fail.
+entries[3].incomplete = middlebit: online scrub didn't fail.
+entries[3].incomplete = lastbit: online scrub didn't fail.
+entries[3].incomplete = add: online scrub didn't fail.
+entries[3].incomplete = sub: online scrub didn't fail.
+entries[4].incomplete = ones: online scrub didn't fail.
+entries[4].incomplete = firstbit: online scrub didn't fail.
+entries[4].incomplete = middlebit: online scrub didn't fail.
+entries[4].incomplete = lastbit: online scrub didn't fail.
+entries[4].incomplete = add: online scrub didn't fail.
+entries[4].incomplete = sub: online scrub didn't fail.
+entries[5].incomplete = ones: online scrub didn't fail.
+entries[5].incomplete = firstbit: online scrub didn't fail.
+entries[5].incomplete = middlebit: online scrub didn't fail.
+entries[5].incomplete = lastbit: online scrub didn't fail.
+entries[5].incomplete = add: online scrub didn't fail.
+entries[5].incomplete = sub: online scrub didn't fail.
+entries[6].incomplete = ones: online scrub didn't fail.
+entries[6].incomplete = firstbit: online scrub didn't fail.
+entries[6].incomplete = middlebit: online scrub didn't fail.
+entries[6].incomplete = lastbit: online scrub didn't fail.
+entries[6].incomplete = add: online scrub didn't fail.
+entries[6].incomplete = sub: online scrub didn't fail.
+entries[7].incomplete = ones: online scrub didn't fail.
+entries[7].incomplete = firstbit: online scrub didn't fail.
+entries[7].incomplete = middlebit: online scrub didn't fail.
+entries[7].incomplete = lastbit: online scrub didn't fail.
+entries[7].incomplete = add: online scrub didn't fail.
+entries[7].incomplete = sub: online scrub didn't fail.
+entries[8].incomplete = ones: online scrub didn't fail.
+entries[8].incomplete = firstbit: online scrub didn't fail.
+entries[8].incomplete = middlebit: online scrub didn't fail.
+entries[8].incomplete = lastbit: online scrub didn't fail.
+entries[8].incomplete = add: online scrub didn't fail.
+entries[8].incomplete = sub: online scrub didn't fail.
+entries[9].incomplete = ones: online scrub didn't fail.
+entries[9].incomplete = firstbit: online scrub didn't fail.
+entries[9].incomplete = middlebit: online scrub didn't fail.
+entries[9].incomplete = lastbit: online scrub didn't fail.
+entries[9].incomplete = add: online scrub didn't fail.
+entries[9].incomplete = sub: online scrub didn't fail.
 Done fuzzing leaf-format attr block
diff --git a/tests/xfs/479.out b/tests/xfs/479.out
index 320a82ac39..ca8ff9f71f 100644
--- a/tests/xfs/479.out
+++ b/tests/xfs/479.out
@@ -2,4 +2,11 @@ QA output created by 479
 Format and populate
 Find node-format attr block
 Fuzz node-format attr block
+hdr.info.crc = zeroes: offline scrub didn't fail.
+hdr.info.crc = ones: offline scrub didn't fail.
+hdr.info.crc = firstbit: offline scrub didn't fail.
+hdr.info.crc = middlebit: offline scrub didn't fail.
+hdr.info.crc = lastbit: offline scrub didn't fail.
+hdr.info.crc = add: offline scrub didn't fail.
+hdr.info.crc = sub: offline scrub didn't fail.
 Done fuzzing node-format attr block
diff --git a/tests/xfs/480.out b/tests/xfs/480.out
index 6225f4daad..d4628171ba 100644
--- a/tests/xfs/480.out
+++ b/tests/xfs/480.out
@@ -2,4 +2,28 @@ QA output created by 480
 Format and populate
 Find external attr block
 Fuzz external attr block
+hdr.offset = ones: offline scrub didn't fail.
+hdr.offset = middlebit: offline scrub didn't fail.
+hdr.offset = lastbit: offline scrub didn't fail.
+hdr.offset = add: offline scrub didn't fail.
+hdr.offset = sub: offline scrub didn't fail.
+hdr.bytes = zeroes: offline scrub didn't fail.
+hdr.bytes = lastbit: offline scrub didn't fail.
+hdr.bytes = sub: offline scrub didn't fail.
+hdr.owner = ones: offline scrub didn't fail.
+hdr.owner = firstbit: offline scrub didn't fail.
+hdr.owner = middlebit: offline scrub didn't fail.
+hdr.owner = lastbit: offline scrub didn't fail.
+hdr.owner = add: offline scrub didn't fail.
+hdr.owner = sub: offline scrub didn't fail.
+data = zeroes: offline scrub didn't fail.
+data = zeroes: online scrub didn't fail.
+data = ones: offline scrub didn't fail.
+data = ones: online scrub didn't fail.
+data = firstbit: offline scrub didn't fail.
+data = firstbit: online scrub didn't fail.
+data = middlebit: offline scrub didn't fail.
+data = middlebit: online scrub didn't fail.
+data = lastbit: offline scrub didn't fail.
+data = lastbit: online scrub didn't fail.
 Done fuzzing external attr block
diff --git a/tests/xfs/483.out b/tests/xfs/483.out
index 07b75b3655..01c95a3bac 100644
--- a/tests/xfs/483.out
+++ b/tests/xfs/483.out
@@ -1,4 +1,10 @@
 QA output created by 483
 Format and populate
 Fuzz refcountbt
+numrecs = lastbit: offline scrub didn't fail.
+leftsib = add: offline scrub didn't fail.
+rightsib = ones: offline scrub didn't fail.
+rightsib = middlebit: offline scrub didn't fail.
+rightsib = lastbit: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
 Done fuzzing refcountbt
diff --git a/tests/xfs/484.out b/tests/xfs/484.out
index 1295aaad34..89ee83772d 100644
--- a/tests/xfs/484.out
+++ b/tests/xfs/484.out
@@ -2,4 +2,49 @@ QA output created by 484
 Format and populate
 Find btree-format attr inode
 Fuzz inode
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.size = middlebit: offline scrub didn't fail.
+core.size = middlebit: online scrub didn't fail.
+core.size = lastbit: offline scrub didn't fail.
+core.size = lastbit: online scrub didn't fail.
+core.size = add: offline scrub didn't fail.
+core.size = add: online scrub didn't fail.
+next_unlinked = add: online scrub didn't fail.
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.flags2 = lastbit: offline scrub didn't fail.
+v3.flags2 = lastbit: online scrub didn't fail.
+v3.flags2 = add: online scrub didn't fail.
+v3.reflink = ones: offline scrub didn't fail.
+v3.reflink = ones: online scrub didn't fail.
+v3.reflink = firstbit: offline scrub didn't fail.
+v3.reflink = firstbit: online scrub didn't fail.
+v3.reflink = middlebit: offline scrub didn't fail.
+v3.reflink = middlebit: online scrub didn't fail.
+v3.reflink = lastbit: offline scrub didn't fail.
+v3.reflink = lastbit: online scrub didn't fail.
+v3.reflink = add: offline scrub didn't fail.
+v3.reflink = add: online scrub didn't fail.
+v3.reflink = sub: offline scrub didn't fail.
+v3.reflink = sub: online scrub didn't fail.
+a.bmbt.ptrs[1] = firstbit: offline scrub didn't fail.
+a.bmbt.ptrs[1] = firstbit: online scrub didn't fail.
 Done fuzzing inode
diff --git a/tests/xfs/485.out b/tests/xfs/485.out
index c89c0e5a37..dfd131d4f3 100644
--- a/tests/xfs/485.out
+++ b/tests/xfs/485.out
@@ -2,4 +2,55 @@ QA output created by 485
 Format and populate
 Find blockdev inode
 Fuzz inode
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.size = middlebit: online scrub didn't fail.
+core.size = lastbit: online scrub didn't fail.
+core.size = add: online scrub didn't fail.
+next_unlinked = add: online scrub didn't fail.
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.nrext64 = zeroes: offline scrub didn't fail.
+v3.nrext64 = zeroes: online scrub didn't fail.
+v3.nrext64 = firstbit: offline scrub didn't fail.
+v3.nrext64 = firstbit: online scrub didn't fail.
+v3.nrext64 = middlebit: offline scrub didn't fail.
+v3.nrext64 = middlebit: online scrub didn't fail.
+v3.nrext64 = lastbit: offline scrub didn't fail.
+v3.nrext64 = lastbit: online scrub didn't fail.
+v3.nrext64 = add: offline scrub didn't fail.
+v3.nrext64 = add: online scrub didn't fail.
+v3.nrext64 = sub: offline scrub didn't fail.
+v3.nrext64 = sub: online scrub didn't fail.
+u3.dev = zeroes: offline scrub didn't fail.
+u3.dev = zeroes: online scrub didn't fail.
+u3.dev = ones: offline scrub didn't fail.
+u3.dev = ones: online scrub didn't fail.
+u3.dev = firstbit: offline scrub didn't fail.
+u3.dev = firstbit: online scrub didn't fail.
+u3.dev = middlebit: offline scrub didn't fail.
+u3.dev = middlebit: online scrub didn't fail.
+u3.dev = lastbit: offline scrub didn't fail.
+u3.dev = lastbit: online scrub didn't fail.
+u3.dev = add: offline scrub didn't fail.
+u3.dev = add: online scrub didn't fail.
+u3.dev = sub: offline scrub didn't fail.
+u3.dev = sub: online scrub didn't fail.
 Done fuzzing inode
diff --git a/tests/xfs/486.out b/tests/xfs/486.out
index 26f1a362d9..1e4f7102a3 100644
--- a/tests/xfs/486.out
+++ b/tests/xfs/486.out
@@ -2,4 +2,50 @@ QA output created by 486
 Format and populate
 Find local-format symlink inode
 Fuzz inode
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+next_unlinked = add: online scrub didn't fail.
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.nrext64 = zeroes: offline scrub didn't fail.
+v3.nrext64 = zeroes: online scrub didn't fail.
+v3.nrext64 = firstbit: offline scrub didn't fail.
+v3.nrext64 = firstbit: online scrub didn't fail.
+v3.nrext64 = middlebit: offline scrub didn't fail.
+v3.nrext64 = middlebit: online scrub didn't fail.
+v3.nrext64 = lastbit: offline scrub didn't fail.
+v3.nrext64 = lastbit: online scrub didn't fail.
+v3.nrext64 = add: offline scrub didn't fail.
+v3.nrext64 = add: online scrub didn't fail.
+v3.nrext64 = sub: offline scrub didn't fail.
+v3.nrext64 = sub: online scrub didn't fail.
+u3.symlink = ones: offline scrub didn't fail.
+u3.symlink = ones: online scrub didn't fail.
+u3.symlink = firstbit: offline scrub didn't fail.
+u3.symlink = firstbit: online scrub didn't fail.
+u3.symlink = middlebit: offline scrub didn't fail.
+u3.symlink = middlebit: online scrub didn't fail.
+u3.symlink = lastbit: offline scrub didn't fail.
+u3.symlink = lastbit: online scrub didn't fail.
+u3.symlink = add: offline scrub didn't fail.
+u3.symlink = add: online scrub didn't fail.
+u3.symlink = sub: offline scrub didn't fail.
+u3.symlink = sub: online scrub didn't fail.
 Done fuzzing inode
diff --git a/tests/xfs/487.out b/tests/xfs/487.out
index a7d2926ce5..4e036a7d6b 100644
--- a/tests/xfs/487.out
+++ b/tests/xfs/487.out
@@ -1,4 +1,246 @@
 QA output created by 487
 Format and populate
 Fuzz user 0 dquot
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = ones: online scrub didn't fail.
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = firstbit: online scrub didn't fail.
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = middlebit: online scrub didn't fail.
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = lastbit: online scrub didn't fail.
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = add: online scrub didn't fail.
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.itimer = sub: online scrub didn't fail.
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = ones: online scrub didn't fail.
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = firstbit: online scrub didn't fail.
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = middlebit: online scrub didn't fail.
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = lastbit: online scrub didn't fail.
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = add: online scrub didn't fail.
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.btimer = sub: online scrub didn't fail.
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = ones: online scrub didn't fail.
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: online scrub didn't fail.
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: online scrub didn't fail.
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: online scrub didn't fail.
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = add: online scrub didn't fail.
+diskdq.rtbtimer = sub: offline scrub didn't fail.
+diskdq.rtbtimer = sub: online scrub didn't fail.
+Done fuzzing dquot
+Fuzz user 4242 dquot
+diskdq.type = firstbit: offline scrub didn't fail.
+diskdq.type = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = sub: offline scrub didn't fail.
+Done fuzzing dquot
+Fuzz user 8484 dquot
+diskdq.type = firstbit: offline scrub didn't fail.
+diskdq.type = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = sub: offline scrub didn't fail.
 Done fuzzing dquot
diff --git a/tests/xfs/488.out b/tests/xfs/488.out
index 2fc75d163e..738a7297a3 100644
--- a/tests/xfs/488.out
+++ b/tests/xfs/488.out
@@ -1,4 +1,246 @@
 QA output created by 488
 Format and populate
 Fuzz group 0 dquot
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = ones: online scrub didn't fail.
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = firstbit: online scrub didn't fail.
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = middlebit: online scrub didn't fail.
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = lastbit: online scrub didn't fail.
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = add: online scrub didn't fail.
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.itimer = sub: online scrub didn't fail.
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = ones: online scrub didn't fail.
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = firstbit: online scrub didn't fail.
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = middlebit: online scrub didn't fail.
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = lastbit: online scrub didn't fail.
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = add: online scrub didn't fail.
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.btimer = sub: online scrub didn't fail.
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = ones: online scrub didn't fail.
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: online scrub didn't fail.
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: online scrub didn't fail.
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: online scrub didn't fail.
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = add: online scrub didn't fail.
+diskdq.rtbtimer = sub: offline scrub didn't fail.
+diskdq.rtbtimer = sub: online scrub didn't fail.
+Done fuzzing dquot
+Fuzz group 4242 dquot
+diskdq.type = firstbit: offline scrub didn't fail.
+diskdq.type = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = sub: offline scrub didn't fail.
+Done fuzzing dquot
+Fuzz group 8484 dquot
+diskdq.type = firstbit: offline scrub didn't fail.
+diskdq.type = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = sub: offline scrub didn't fail.
 Done fuzzing dquot
diff --git a/tests/xfs/489.out b/tests/xfs/489.out
index 7483e6420c..15aa6efefc 100644
--- a/tests/xfs/489.out
+++ b/tests/xfs/489.out
@@ -1,4 +1,246 @@
 QA output created by 489
 Format and populate
 Fuzz project 0 dquot
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = ones: online scrub didn't fail.
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = firstbit: online scrub didn't fail.
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = middlebit: online scrub didn't fail.
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = lastbit: online scrub didn't fail.
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = add: online scrub didn't fail.
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.itimer = sub: online scrub didn't fail.
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = ones: online scrub didn't fail.
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = firstbit: online scrub didn't fail.
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = middlebit: online scrub didn't fail.
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = lastbit: online scrub didn't fail.
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = add: online scrub didn't fail.
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.btimer = sub: online scrub didn't fail.
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = ones: online scrub didn't fail.
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: online scrub didn't fail.
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: online scrub didn't fail.
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: online scrub didn't fail.
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = add: online scrub didn't fail.
+diskdq.rtbtimer = sub: offline scrub didn't fail.
+diskdq.rtbtimer = sub: online scrub didn't fail.
+Done fuzzing dquot
+Fuzz project 4242 dquot
+diskdq.type = firstbit: offline scrub didn't fail.
+diskdq.type = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = sub: offline scrub didn't fail.
+Done fuzzing dquot
+Fuzz project 8484 dquot
+diskdq.type = firstbit: offline scrub didn't fail.
+diskdq.type = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = sub: offline scrub didn't fail.
 Done fuzzing dquot
diff --git a/tests/xfs/498.out b/tests/xfs/498.out
index 5c5ef5917c..5295aeb3e5 100644
--- a/tests/xfs/498.out
+++ b/tests/xfs/498.out
@@ -2,4 +2,16 @@ QA output created by 498
 Format and populate
 Find single-leafn-format dir block
 Fuzz single-leafn-format dir block
+lhdr.info.hdr.forw = ones: offline scrub didn't fail.
+lhdr.info.hdr.forw = firstbit: offline scrub didn't fail.
+lhdr.info.hdr.forw = middlebit: offline scrub didn't fail.
+lhdr.info.hdr.forw = lastbit: offline scrub didn't fail.
+lhdr.info.hdr.forw = add: offline scrub didn't fail.
+lhdr.info.hdr.forw = sub: offline scrub didn't fail.
+lhdr.info.hdr.back = ones: offline scrub didn't fail.
+lhdr.info.hdr.back = firstbit: offline scrub didn't fail.
+lhdr.info.hdr.back = middlebit: offline scrub didn't fail.
+lhdr.info.hdr.back = lastbit: offline scrub didn't fail.
+lhdr.info.hdr.back = add: offline scrub didn't fail.
+lhdr.info.hdr.back = sub: offline scrub didn't fail.
 Done fuzzing single-leafn-format dir block
diff --git a/tests/xfs/788.out b/tests/xfs/788.out
index 5f6414d0f1..525d385160 100644
--- a/tests/xfs/788.out
+++ b/tests/xfs/788.out
@@ -1,4 +1,27 @@
 QA output created by 788
 Format and populate
 Fuzz inobt
+leftsib = add: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
+keys[1].startino = zeroes: offline scrub didn't fail.
+keys[1].startino = ones: offline scrub didn't fail.
+keys[1].startino = firstbit: offline scrub didn't fail.
+keys[1].startino = middlebit: offline scrub didn't fail.
+keys[1].startino = lastbit: offline scrub didn't fail.
+keys[1].startino = add: offline scrub didn't fail.
+keys[1].startino = sub: offline scrub didn't fail.
+keys[2].startino = zeroes: offline scrub didn't fail.
+keys[2].startino = ones: offline scrub didn't fail.
+keys[2].startino = firstbit: offline scrub didn't fail.
+keys[2].startino = middlebit: offline scrub didn't fail.
+keys[2].startino = lastbit: offline scrub didn't fail.
+keys[2].startino = add: offline scrub didn't fail.
+keys[2].startino = sub: offline scrub didn't fail.
+keys[3].startino = zeroes: offline scrub didn't fail.
+keys[3].startino = ones: offline scrub didn't fail.
+keys[3].startino = firstbit: offline scrub didn't fail.
+keys[3].startino = middlebit: offline scrub didn't fail.
+keys[3].startino = lastbit: offline scrub didn't fail.
+keys[3].startino = add: offline scrub didn't fail.
+keys[3].startino = sub: offline scrub didn't fail.
 Done fuzzing inobt

[PATCH 4/4] xfs: bothrepair fuzz test known output

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Record all the currently known failures of the online-then-offline
repair code.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 tests/xfs/747.out |  152 +++++++++++++++
 tests/xfs/748.out |   96 ++++++++++
 tests/xfs/749.out |  134 ++++++++++++++
 tests/xfs/750.out |  129 +++++++++++++
 tests/xfs/751.out |    5 +
 tests/xfs/752.out |   44 ++++
 tests/xfs/753.out |    5 +
 tests/xfs/754.out |   25 ---
 tests/xfs/755.out |    6 +
 tests/xfs/756.out |   61 ++++++
 tests/xfs/757.out |  525 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 tests/xfs/758.out |    5 +
 tests/xfs/759.out |   94 +++++++++
 tests/xfs/760.out |   64 ++++++
 tests/xfs/761.out |   66 +++++++
 tests/xfs/762.out |    1 
 tests/xfs/763.out |    8 +
 tests/xfs/764.out |   92 +++++++++
 tests/xfs/765.out |    7 +
 tests/xfs/766.out |   11 +
 tests/xfs/768.out |    7 +
 tests/xfs/769.out |    6 +
 tests/xfs/771.out |   91 +++++++++
 tests/xfs/772.out |   93 +++++++++
 tests/xfs/773.out |    7 +
 tests/xfs/774.out |   24 ++
 tests/xfs/775.out |    6 +
 tests/xfs/776.out |   59 ++++++
 tests/xfs/777.out |   69 +++++++
 tests/xfs/778.out |   60 ++++++
 tests/xfs/779.out |  296 ++++++++++++++++++++++++++++++
 tests/xfs/780.out |  296 ++++++++++++++++++++++++++++++
 tests/xfs/781.out |  296 ++++++++++++++++++++++++++++++
 tests/xfs/782.out |   12 +
 tests/xfs/783.out |  210 +++++++++++++++++++++
 tests/xfs/784.out |   10 +
 tests/xfs/787.out |   23 ++
 37 files changed, 3074 insertions(+), 21 deletions(-)


diff --git a/tests/xfs/747.out b/tests/xfs/747.out
index 1cf4e747fb..80ef3c1fd7 100644
--- a/tests/xfs/747.out
+++ b/tests/xfs/747.out
@@ -1,4 +1,156 @@
 QA output created by 747
 Format and populate
 Fuzz superblock
+uuid = zeroes: offline scrub didn't fail.
+uuid = zeroes: online scrub didn't fail.
+uuid = ones: offline scrub didn't fail.
+uuid = ones: online scrub didn't fail.
+uuid = firstbit: offline scrub didn't fail.
+uuid = firstbit: online scrub didn't fail.
+uuid = middlebit: offline scrub didn't fail.
+uuid = middlebit: online scrub didn't fail.
+uuid = lastbit: offline scrub didn't fail.
+uuid = lastbit: online scrub didn't fail.
+rootino = zeroes: offline scrub didn't fail.
+rootino = zeroes: online scrub didn't fail.
+rootino = ones: offline scrub didn't fail.
+rootino = ones: online scrub didn't fail.
+rootino = firstbit: offline scrub didn't fail.
+rootino = firstbit: online scrub didn't fail.
+rootino = middlebit: offline scrub didn't fail.
+rootino = middlebit: online scrub didn't fail.
+rootino = lastbit: offline scrub didn't fail.
+rootino = lastbit: online scrub didn't fail.
+rootino = add: offline scrub didn't fail.
+rootino = add: online scrub didn't fail.
+rootino = sub: offline scrub didn't fail.
+rootino = sub: online scrub didn't fail.
+metadirino = zeroes: offline scrub didn't fail.
+metadirino = zeroes: online scrub didn't fail.
+metadirino = firstbit: offline scrub didn't fail.
+metadirino = firstbit: online scrub didn't fail.
+metadirino = middlebit: offline scrub didn't fail.
+metadirino = middlebit: online scrub didn't fail.
+metadirino = lastbit: offline scrub didn't fail.
+metadirino = lastbit: online scrub didn't fail.
+metadirino = add: offline scrub didn't fail.
+metadirino = add: online scrub didn't fail.
+metadirino = sub: offline scrub didn't fail.
+metadirino = sub: online scrub didn't fail.
+rgblocks = middlebit: offline scrub didn't fail.
+rgblocks = middlebit: online scrub didn't fail.
+rgblocks = lastbit: offline scrub didn't fail.
+rgblocks = lastbit: online scrub didn't fail.
+rgblocks = add: offline scrub didn't fail.
+rgblocks = add: online scrub didn't fail.
+rgblocks = sub: offline scrub didn't fail.
+rgblocks = sub: online scrub didn't fail.
+fname = ones: offline scrub didn't fail.
+fname = ones: online scrub didn't fail.
+fname = firstbit: offline scrub didn't fail.
+fname = firstbit: online scrub didn't fail.
+fname = middlebit: offline scrub didn't fail.
+fname = middlebit: online scrub didn't fail.
+fname = lastbit: offline scrub didn't fail.
+fname = lastbit: online scrub didn't fail.
+inprogress = zeroes: offline scrub didn't fail.
+inprogress = zeroes: online scrub didn't fail.
+inprogress = ones: offline scrub didn't fail.
+inprogress = ones: online scrub didn't fail.
+inprogress = firstbit: offline scrub didn't fail.
+inprogress = firstbit: online scrub didn't fail.
+inprogress = middlebit: offline scrub didn't fail.
+inprogress = middlebit: online scrub didn't fail.
+inprogress = lastbit: offline scrub didn't fail.
+inprogress = lastbit: online scrub didn't fail.
+inprogress = add: offline scrub didn't fail.
+inprogress = add: online scrub didn't fail.
+inprogress = sub: offline scrub didn't fail.
+inprogress = sub: online scrub didn't fail.
+imax_pct = zeroes: offline scrub didn't fail.
+imax_pct = zeroes: online scrub didn't fail.
+imax_pct = middlebit: offline scrub didn't fail.
+imax_pct = middlebit: online scrub didn't fail.
+imax_pct = lastbit: offline scrub didn't fail.
+imax_pct = lastbit: online scrub didn't fail.
+icount = ones: offline scrub didn't fail.
+icount = ones: online scrub didn't fail.
+icount = firstbit: offline scrub didn't fail.
+icount = firstbit: online scrub didn't fail.
+icount = middlebit: offline scrub didn't fail.
+icount = middlebit: online scrub didn't fail.
+icount = lastbit: offline scrub didn't fail.
+icount = lastbit: online scrub didn't fail.
+icount = add: offline scrub didn't fail.
+icount = add: online scrub didn't fail.
+icount = sub: offline scrub didn't fail.
+icount = sub: online scrub didn't fail.
+ifree = ones: offline scrub didn't fail.
+ifree = ones: online scrub didn't fail.
+ifree = firstbit: offline scrub didn't fail.
+ifree = firstbit: online scrub didn't fail.
+ifree = middlebit: offline scrub didn't fail.
+ifree = middlebit: online scrub didn't fail.
+ifree = lastbit: offline scrub didn't fail.
+ifree = lastbit: online scrub didn't fail.
+ifree = add: offline scrub didn't fail.
+ifree = add: online scrub didn't fail.
+ifree = sub: offline scrub didn't fail.
+ifree = sub: online scrub didn't fail.
+fdblocks = zeroes: offline scrub didn't fail.
+fdblocks = zeroes: online scrub didn't fail.
+fdblocks = ones: offline scrub didn't fail.
+fdblocks = ones: online scrub didn't fail.
+fdblocks = firstbit: offline scrub didn't fail.
+fdblocks = firstbit: online scrub didn't fail.
+fdblocks = middlebit: offline scrub didn't fail.
+fdblocks = middlebit: online scrub didn't fail.
+fdblocks = lastbit: offline scrub didn't fail.
+fdblocks = lastbit: online scrub didn't fail.
+fdblocks = add: offline scrub didn't fail.
+fdblocks = add: online scrub didn't fail.
+fdblocks = sub: offline scrub didn't fail.
+fdblocks = sub: online scrub didn't fail.
+qflags = firstbit: online scrub didn't fail.
+qflags = middlebit: online scrub didn't fail.
+qflags = lastbit: online scrub didn't fail.
+shared_vn = ones: offline scrub didn't fail.
+shared_vn = firstbit: offline scrub didn't fail.
+shared_vn = middlebit: offline scrub didn't fail.
+shared_vn = lastbit: offline scrub didn't fail.
+shared_vn = add: offline scrub didn't fail.
+shared_vn = sub: offline scrub didn't fail.
+dirblklog = lastbit: offline scrub didn't fail.
+logsunit = zeroes: offline scrub didn't fail.
+logsunit = lastbit: offline scrub didn't fail.
+bad_features2 = zeroes: offline scrub didn't fail.
+bad_features2 = zeroes: online scrub didn't fail.
+bad_features2 = ones: offline scrub didn't fail.
+bad_features2 = ones: online scrub didn't fail.
+bad_features2 = firstbit: offline scrub didn't fail.
+bad_features2 = firstbit: online scrub didn't fail.
+bad_features2 = middlebit: offline scrub didn't fail.
+bad_features2 = middlebit: online scrub didn't fail.
+bad_features2 = lastbit: offline scrub didn't fail.
+bad_features2 = lastbit: online scrub didn't fail.
+bad_features2 = add: offline scrub didn't fail.
+bad_features2 = add: online scrub didn't fail.
+bad_features2 = sub: offline scrub didn't fail.
+bad_features2 = sub: online scrub didn't fail.
+features_log_incompat = ones: offline scrub didn't fail.
+features_log_incompat = ones: online scrub didn't fail.
+features_log_incompat = firstbit: offline scrub didn't fail.
+features_log_incompat = firstbit: online scrub didn't fail.
+features_log_incompat = middlebit: offline scrub didn't fail.
+features_log_incompat = middlebit: online scrub didn't fail.
+features_log_incompat = lastbit: offline scrub didn't fail.
+features_log_incompat = lastbit: online scrub didn't fail.
+features_log_incompat = add: offline scrub didn't fail.
+features_log_incompat = add: online scrub didn't fail.
+features_log_incompat = sub: offline scrub didn't fail.
+features_log_incompat = sub: online scrub didn't fail.
+meta_uuid = ones: online scrub didn't fail.
+meta_uuid = firstbit: online scrub didn't fail.
+meta_uuid = middlebit: online scrub didn't fail.
+meta_uuid = lastbit: online scrub didn't fail.
 Done fuzzing superblock
diff --git a/tests/xfs/748.out b/tests/xfs/748.out
index a281c130ea..4caad4f092 100644
--- a/tests/xfs/748.out
+++ b/tests/xfs/748.out
@@ -1,4 +1,100 @@
 QA output created by 748
 Format and populate
 Fuzz AGF
+magicnum = zeroes: mount failed (32).
+magicnum = ones: mount failed (32).
+magicnum = firstbit: mount failed (32).
+magicnum = middlebit: mount failed (32).
+magicnum = lastbit: mount failed (32).
+magicnum = add: mount failed (32).
+magicnum = sub: mount failed (32).
+versionnum = zeroes: mount failed (32).
+versionnum = ones: mount failed (32).
+versionnum = firstbit: mount failed (32).
+versionnum = middlebit: mount failed (32).
+versionnum = lastbit: mount failed (32).
+versionnum = add: mount failed (32).
+versionnum = sub: mount failed (32).
+seqno = ones: mount failed (32).
+seqno = firstbit: mount failed (32).
+seqno = middlebit: mount failed (32).
+seqno = lastbit: mount failed (32).
+seqno = add: mount failed (32).
+seqno = sub: mount failed (32).
+length = zeroes: mount failed (32).
+length = ones: mount failed (32).
+length = firstbit: mount failed (32).
+length = middlebit: mount failed (32).
+length = lastbit: mount failed (32).
+length = add: mount failed (32).
+length = sub: mount failed (32).
+bnolevel = zeroes: mount failed (32).
+bnolevel = ones: mount failed (32).
+bnolevel = firstbit: mount failed (32).
+bnolevel = middlebit: mount failed (32).
+bnolevel = add: mount failed (32).
+bnolevel = sub: mount failed (32).
+cntlevel = zeroes: mount failed (32).
+cntlevel = ones: mount failed (32).
+cntlevel = firstbit: mount failed (32).
+cntlevel = middlebit: mount failed (32).
+cntlevel = add: mount failed (32).
+cntlevel = sub: mount failed (32).
+rmaplevel = zeroes: mount failed (32).
+rmaplevel = ones: mount failed (32).
+rmaplevel = firstbit: mount failed (32).
+rmaplevel = middlebit: mount failed (32).
+rmaplevel = add: mount failed (32).
+rmaplevel = sub: mount failed (32).
+refcntlevel = zeroes: mount failed (32).
+refcntlevel = ones: mount failed (32).
+refcntlevel = firstbit: mount failed (32).
+refcntlevel = middlebit: mount failed (32).
+refcntlevel = add: mount failed (32).
+refcntlevel = sub: mount failed (32).
+rmapblocks = ones: mount failed (32).
+rmapblocks = firstbit: mount failed (32).
+rmapblocks = sub: mount failed (32).
+refcntblocks = ones: mount failed (32).
+refcntblocks = firstbit: mount failed (32).
+refcntblocks = sub: mount failed (32).
+flfirst = ones: mount failed (32).
+flfirst = firstbit: mount failed (32).
+flfirst = middlebit: mount failed (32).
+flfirst = add: mount failed (32).
+flfirst = sub: mount failed (32).
+fllast = ones: mount failed (32).
+fllast = firstbit: mount failed (32).
+fllast = middlebit: mount failed (32).
+fllast = add: mount failed (32).
+fllast = sub: mount failed (32).
+flcount = ones: mount failed (32).
+flcount = firstbit: mount failed (32).
+flcount = middlebit: mount failed (32).
+flcount = add: mount failed (32).
+flcount = sub: mount failed (32).
+freeblks = zeroes: mount failed (32).
+freeblks = ones: mount failed (32).
+freeblks = firstbit: mount failed (32).
+freeblks = middlebit: mount failed (32).
+freeblks = add: mount failed (32).
+freeblks = sub: mount failed (32).
+longest = ones: mount failed (32).
+longest = firstbit: mount failed (32).
+longest = add: mount failed (32).
+btreeblks = ones: mount failed (32).
+btreeblks = firstbit: mount failed (32).
+btreeblks = sub: mount failed (32).
+uuid = zeroes: mount failed (32).
+uuid = ones: mount failed (32).
+uuid = firstbit: mount failed (32).
+uuid = middlebit: mount failed (32).
+uuid = lastbit: mount failed (32).
+crc = zeroes: mount failed (32).
+crc = ones: mount failed (32).
+crc = firstbit: mount failed (32).
+crc = middlebit: mount failed (32).
+crc = lastbit: mount failed (32).
+crc = add: mount failed (32).
+crc = sub: mount failed (32).
 Done fuzzing AGF
diff --git a/tests/xfs/749.out b/tests/xfs/749.out
index 478ce52818..57b505aa85 100644
--- a/tests/xfs/749.out
+++ b/tests/xfs/749.out
@@ -1,6 +1,140 @@
 QA output created by 749
 Format and populate
 Fuzz AGFL
+magicnum = zeroes: offline scrub didn't fail.
+magicnum = ones: offline scrub didn't fail.
+magicnum = firstbit: offline scrub didn't fail.
+magicnum = middlebit: offline scrub didn't fail.
+magicnum = lastbit: offline scrub didn't fail.
+magicnum = add: offline scrub didn't fail.
+magicnum = sub: offline scrub didn't fail.
+seqno = ones: offline scrub didn't fail.
+seqno = firstbit: offline scrub didn't fail.
+seqno = middlebit: offline scrub didn't fail.
+seqno = lastbit: offline scrub didn't fail.
+seqno = add: offline scrub didn't fail.
+seqno = sub: offline scrub didn't fail.
+uuid = zeroes: offline scrub didn't fail.
+uuid = ones: offline scrub didn't fail.
+uuid = firstbit: offline scrub didn't fail.
+uuid = middlebit: offline scrub didn't fail.
+uuid = lastbit: offline scrub didn't fail.
+bno[0] = zeroes: offline scrub didn't fail.
+bno[0] = zeroes: online scrub didn't fail.
+bno[0] = firstbit: offline scrub didn't fail.
+bno[0] = middlebit: offline scrub didn't fail.
+bno[0] = lastbit: offline scrub didn't fail.
+bno[0] = add: offline scrub didn't fail.
+bno[0] = add: online scrub didn't fail.
+bno[0] = sub: offline scrub didn't fail.
+bno[1] = zeroes: offline scrub didn't fail.
+bno[1] = zeroes: online scrub didn't fail.
+bno[1] = ones: offline scrub didn't fail.
+bno[1] = ones: online scrub didn't fail.
+bno[1] = firstbit: offline scrub didn't fail.
+bno[1] = middlebit: offline scrub didn't fail.
+bno[1] = middlebit: online scrub didn't fail.
+bno[1] = lastbit: offline scrub didn't fail.
+bno[1] = lastbit: online scrub didn't fail.
+bno[1] = add: offline scrub didn't fail.
+bno[1] = add: online scrub didn't fail.
+bno[1] = sub: offline scrub didn't fail.
+bno[2] = zeroes: offline scrub didn't fail.
+bno[2] = zeroes: online scrub didn't fail.
+bno[2] = ones: offline scrub didn't fail.
+bno[2] = ones: online scrub didn't fail.
+bno[2] = firstbit: offline scrub didn't fail.
+bno[2] = middlebit: offline scrub didn't fail.
+bno[2] = middlebit: online scrub didn't fail.
+bno[2] = lastbit: offline scrub didn't fail.
+bno[2] = lastbit: online scrub didn't fail.
+bno[2] = add: offline scrub didn't fail.
+bno[2] = add: online scrub didn't fail.
+bno[2] = sub: offline scrub didn't fail.
+bno[3] = zeroes: offline scrub didn't fail.
+bno[3] = zeroes: online scrub didn't fail.
+bno[3] = ones: offline scrub didn't fail.
+bno[3] = ones: online scrub didn't fail.
+bno[3] = firstbit: offline scrub didn't fail.
+bno[3] = middlebit: offline scrub didn't fail.
+bno[3] = middlebit: online scrub didn't fail.
+bno[3] = lastbit: offline scrub didn't fail.
+bno[3] = lastbit: online scrub didn't fail.
+bno[3] = add: offline scrub didn't fail.
+bno[3] = add: online scrub didn't fail.
+bno[3] = sub: offline scrub didn't fail.
+bno[4] = zeroes: offline scrub didn't fail.
+bno[4] = zeroes: online scrub didn't fail.
+bno[4] = ones: offline scrub didn't fail.
+bno[4] = ones: online scrub didn't fail.
+bno[4] = firstbit: offline scrub didn't fail.
+bno[4] = middlebit: offline scrub didn't fail.
+bno[4] = middlebit: online scrub didn't fail.
+bno[4] = lastbit: offline scrub didn't fail.
+bno[4] = lastbit: online scrub didn't fail.
+bno[4] = add: offline scrub didn't fail.
+bno[4] = add: online scrub didn't fail.
+bno[4] = sub: offline scrub didn't fail.
+bno[5] = zeroes: offline scrub didn't fail.
+bno[5] = zeroes: online scrub didn't fail.
+bno[5] = ones: offline scrub didn't fail.
+bno[5] = ones: online scrub didn't fail.
+bno[5] = firstbit: offline scrub didn't fail.
+bno[5] = middlebit: offline scrub didn't fail.
+bno[5] = middlebit: online scrub didn't fail.
+bno[5] = lastbit: offline scrub didn't fail.
+bno[5] = lastbit: online scrub didn't fail.
+bno[5] = add: offline scrub didn't fail.
+bno[5] = add: online scrub didn't fail.
+bno[5] = sub: offline scrub didn't fail.
+bno[6] = zeroes: offline scrub didn't fail.
+bno[6] = zeroes: online scrub didn't fail.
+bno[6] = ones: offline scrub didn't fail.
+bno[6] = ones: online scrub didn't fail.
+bno[6] = firstbit: offline scrub didn't fail.
+bno[6] = middlebit: offline scrub didn't fail.
+bno[6] = middlebit: online scrub didn't fail.
+bno[6] = lastbit: offline scrub didn't fail.
+bno[6] = lastbit: online scrub didn't fail.
+bno[6] = add: offline scrub didn't fail.
+bno[6] = add: online scrub didn't fail.
+bno[6] = sub: offline scrub didn't fail.
+bno[7] = zeroes: offline scrub didn't fail.
+bno[7] = zeroes: online scrub didn't fail.
+bno[7] = ones: offline scrub didn't fail.
+bno[7] = ones: online scrub didn't fail.
+bno[7] = firstbit: offline scrub didn't fail.
+bno[7] = middlebit: offline scrub didn't fail.
+bno[7] = middlebit: online scrub didn't fail.
+bno[7] = lastbit: offline scrub didn't fail.
+bno[7] = lastbit: online scrub didn't fail.
+bno[7] = add: offline scrub didn't fail.
+bno[7] = add: online scrub didn't fail.
+bno[7] = sub: offline scrub didn't fail.
+bno[8] = zeroes: offline scrub didn't fail.
+bno[8] = zeroes: online scrub didn't fail.
+bno[8] = ones: offline scrub didn't fail.
+bno[8] = ones: online scrub didn't fail.
+bno[8] = firstbit: offline scrub didn't fail.
+bno[8] = middlebit: offline scrub didn't fail.
+bno[8] = middlebit: online scrub didn't fail.
+bno[8] = lastbit: offline scrub didn't fail.
+bno[8] = lastbit: online scrub didn't fail.
+bno[8] = add: offline scrub didn't fail.
+bno[8] = add: online scrub didn't fail.
+bno[8] = sub: offline scrub didn't fail.
+bno[9] = zeroes: offline scrub didn't fail.
+bno[9] = zeroes: online scrub didn't fail.
+bno[9] = ones: offline scrub didn't fail.
+bno[9] = ones: online scrub didn't fail.
+bno[9] = firstbit: offline scrub didn't fail.
+bno[9] = middlebit: offline scrub didn't fail.
+bno[9] = middlebit: online scrub didn't fail.
+bno[9] = lastbit: offline scrub didn't fail.
+bno[9] = lastbit: online scrub didn't fail.
+bno[9] = add: offline scrub didn't fail.
+bno[9] = add: online scrub didn't fail.
+bno[9] = sub: offline scrub didn't fail.
 Done fuzzing AGFL
 Fuzz AGFL flfirst
 Done fuzzing AGFL flfirst
diff --git a/tests/xfs/750.out b/tests/xfs/750.out
index 7521416f9b..047728583d 100644
--- a/tests/xfs/750.out
+++ b/tests/xfs/750.out
@@ -1,4 +1,133 @@
 QA output created by 750
 Format and populate
 Fuzz AGI
+magicnum = zeroes: mount failed (32).
+magicnum = ones: mount failed (32).
+magicnum = firstbit: mount failed (32).
+magicnum = middlebit: mount failed (32).
+magicnum = lastbit: mount failed (32).
+magicnum = add: mount failed (32).
+magicnum = sub: mount failed (32).
+versionnum = zeroes: mount failed (32).
+versionnum = ones: mount failed (32).
+versionnum = firstbit: mount failed (32).
+versionnum = middlebit: mount failed (32).
+versionnum = lastbit: mount failed (32).
+versionnum = add: mount failed (32).
+versionnum = sub: mount failed (32).
+seqno = ones: mount failed (32).
+seqno = firstbit: mount failed (32).
+seqno = middlebit: mount failed (32).
+seqno = lastbit: mount failed (32).
+seqno = add: mount failed (32).
+seqno = sub: mount failed (32).
+length = zeroes: mount failed (32).
+length = ones: mount failed (32).
+length = firstbit: mount failed (32).
+length = middlebit: mount failed (32).
+length = lastbit: mount failed (32).
+length = add: mount failed (32).
+length = sub: mount failed (32).
+root = zeroes: mount failed (32).
+root = ones: mount failed (32).
+root = firstbit: mount failed (32).
+root = middlebit: mount failed (32).
+root = lastbit: mount failed (32).
+root = add: mount failed (32).
+root = sub: mount failed (32).
+level = zeroes: mount failed (32).
+level = ones: mount failed (32).
+level = firstbit: mount failed (32).
+level = middlebit: mount failed (32).
+level = lastbit: mount failed (32).
+level = add: mount failed (32).
+level = sub: mount failed (32).
+newino = zeroes: offline scrub didn't fail.
+newino = ones: offline scrub didn't fail.
+newino = ones: online scrub didn't fail.
+newino = firstbit: offline scrub didn't fail.
+newino = middlebit: offline scrub didn't fail.
+newino = middlebit: online scrub didn't fail.
+newino = lastbit: offline scrub didn't fail.
+newino = lastbit: online scrub didn't fail.
+newino = add: offline scrub didn't fail.
+newino = add: online scrub didn't fail.
+newino = sub: offline scrub didn't fail.
+newino = sub: online scrub didn't fail.
+dirino = zeroes: offline scrub didn't fail.
+dirino = firstbit: offline scrub didn't fail.
+dirino = middlebit: offline scrub didn't fail.
+dirino = lastbit: offline scrub didn't fail.
+dirino = add: offline scrub didn't fail.
+dirino = add: online scrub didn't fail.
+dirino = sub: offline scrub didn't fail.
+unlinked[0] = zeroes: mount failed (32).
+unlinked[0] = firstbit: mount failed (32).
+unlinked[0] = middlebit: mount failed (32).
+unlinked[0] = lastbit: mount failed (32).
+unlinked[0] = sub: mount failed (32).
+unlinked[1] = zeroes: mount failed (32).
+unlinked[1] = firstbit: mount failed (32).
+unlinked[1] = middlebit: mount failed (32).
+unlinked[1] = lastbit: mount failed (32).
+unlinked[1] = sub: mount failed (32).
+unlinked[2] = zeroes: mount failed (32).
+unlinked[2] = firstbit: mount failed (32).
+unlinked[2] = middlebit: mount failed (32).
+unlinked[2] = lastbit: mount failed (32).
+unlinked[2] = sub: mount failed (32).
+unlinked[3] = zeroes: mount failed (32).
+unlinked[3] = firstbit: mount failed (32).
+unlinked[3] = middlebit: mount failed (32).
+unlinked[3] = lastbit: mount failed (32).
+unlinked[3] = sub: mount failed (32).
+unlinked[4] = zeroes: mount failed (32).
+unlinked[4] = firstbit: mount failed (32).
+unlinked[4] = middlebit: mount failed (32).
+unlinked[4] = lastbit: mount failed (32).
+unlinked[4] = sub: mount failed (32).
+unlinked[5] = zeroes: mount failed (32).
+unlinked[5] = firstbit: mount failed (32).
+unlinked[5] = middlebit: mount failed (32).
+unlinked[5] = lastbit: mount failed (32).
+unlinked[5] = sub: mount failed (32).
+unlinked[6] = zeroes: mount failed (32).
+unlinked[6] = firstbit: mount failed (32).
+unlinked[6] = middlebit: mount failed (32).
+unlinked[6] = lastbit: mount failed (32).
+unlinked[6] = sub: mount failed (32).
+unlinked[7] = zeroes: mount failed (32).
+unlinked[7] = firstbit: mount failed (32).
+unlinked[7] = middlebit: mount failed (32).
+unlinked[7] = lastbit: mount failed (32).
+unlinked[7] = sub: mount failed (32).
+unlinked[8] = zeroes: mount failed (32).
+unlinked[8] = firstbit: mount failed (32).
+unlinked[8] = middlebit: mount failed (32).
+unlinked[8] = lastbit: mount failed (32).
+unlinked[8] = sub: mount failed (32).
+unlinked[9] = zeroes: mount failed (32).
+unlinked[9] = firstbit: mount failed (32).
+unlinked[9] = middlebit: mount failed (32).
+unlinked[9] = lastbit: mount failed (32).
+unlinked[9] = sub: mount failed (32).
+uuid = zeroes: mount failed (32).
+uuid = ones: mount failed (32).
+uuid = firstbit: mount failed (32).
+uuid = middlebit: mount failed (32).
+uuid = lastbit: mount failed (32).
+crc = zeroes: mount failed (32).
+crc = ones: mount failed (32).
+crc = firstbit: mount failed (32).
+crc = middlebit: mount failed (32).
+crc = lastbit: mount failed (32).
+crc = add: mount failed (32).
+crc = sub: mount failed (32).
+free_level = zeroes: mount failed (32).
+free_level = ones: mount failed (32).
+free_level = firstbit: mount failed (32).
+free_level = middlebit: mount failed (32).
+free_level = lastbit: mount failed (32).
+free_level = add: mount failed (32).
+free_level = sub: mount failed (32).
 Done fuzzing AGI
diff --git a/tests/xfs/751.out b/tests/xfs/751.out
index 77a74f3b4c..655a943dd1 100644
--- a/tests/xfs/751.out
+++ b/tests/xfs/751.out
@@ -1,4 +1,9 @@
 QA output created by 751
 Format and populate
 Fuzz bnobt recs
+leftsib = add: offline scrub didn't fail.
+rightsib = ones: offline scrub didn't fail.
+rightsib = middlebit: offline scrub didn't fail.
+rightsib = lastbit: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
 Done fuzzing bnobt recs
diff --git a/tests/xfs/752.out b/tests/xfs/752.out
index 2e8348d5d2..b4eaed97c8 100644
--- a/tests/xfs/752.out
+++ b/tests/xfs/752.out
@@ -1,4 +1,48 @@
 QA output created by 752
 Format and populate
 Fuzz bnobt keyptr
+leftsib = add: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
+keys[1].startblock = zeroes: offline scrub didn't fail.
+keys[1].startblock = ones: offline scrub didn't fail.
+keys[1].startblock = firstbit: offline scrub didn't fail.
+keys[1].startblock = middlebit: offline scrub didn't fail.
+keys[1].startblock = lastbit: offline scrub didn't fail.
+keys[1].startblock = add: offline scrub didn't fail.
+keys[1].startblock = sub: offline scrub didn't fail.
+keys[1].blockcount = zeroes: offline scrub didn't fail.
+keys[1].blockcount = zeroes: online scrub didn't fail.
+keys[1].blockcount = ones: offline scrub didn't fail.
+keys[1].blockcount = ones: online scrub didn't fail.
+keys[1].blockcount = firstbit: offline scrub didn't fail.
+keys[1].blockcount = firstbit: online scrub didn't fail.
+keys[1].blockcount = middlebit: offline scrub didn't fail.
+keys[1].blockcount = middlebit: online scrub didn't fail.
+keys[1].blockcount = lastbit: offline scrub didn't fail.
+keys[1].blockcount = lastbit: online scrub didn't fail.
+keys[1].blockcount = add: offline scrub didn't fail.
+keys[1].blockcount = add: online scrub didn't fail.
+keys[1].blockcount = sub: offline scrub didn't fail.
+keys[1].blockcount = sub: online scrub didn't fail.
+keys[2].startblock = zeroes: offline scrub didn't fail.
+keys[2].startblock = ones: offline scrub didn't fail.
+keys[2].startblock = firstbit: offline scrub didn't fail.
+keys[2].startblock = middlebit: offline scrub didn't fail.
+keys[2].startblock = lastbit: offline scrub didn't fail.
+keys[2].startblock = add: offline scrub didn't fail.
+keys[2].startblock = sub: offline scrub didn't fail.
+keys[2].blockcount = zeroes: offline scrub didn't fail.
+keys[2].blockcount = zeroes: online scrub didn't fail.
+keys[2].blockcount = ones: offline scrub didn't fail.
+keys[2].blockcount = ones: online scrub didn't fail.
+keys[2].blockcount = firstbit: offline scrub didn't fail.
+keys[2].blockcount = firstbit: online scrub didn't fail.
+keys[2].blockcount = middlebit: offline scrub didn't fail.
+keys[2].blockcount = middlebit: online scrub didn't fail.
+keys[2].blockcount = lastbit: offline scrub didn't fail.
+keys[2].blockcount = lastbit: online scrub didn't fail.
+keys[2].blockcount = add: offline scrub didn't fail.
+keys[2].blockcount = add: online scrub didn't fail.
+keys[2].blockcount = sub: offline scrub didn't fail.
+keys[2].blockcount = sub: online scrub didn't fail.
 Done fuzzing bnobt keyptr
diff --git a/tests/xfs/753.out b/tests/xfs/753.out
index 0c981968b0..f2fb9daa01 100644
--- a/tests/xfs/753.out
+++ b/tests/xfs/753.out
@@ -1,4 +1,9 @@
 QA output created by 753
 Format and populate
 Fuzz cntbt
+leftsib = add: offline scrub didn't fail.
+rightsib = ones: offline scrub didn't fail.
+rightsib = middlebit: offline scrub didn't fail.
+rightsib = lastbit: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
 Done fuzzing cntbt
diff --git a/tests/xfs/754.out b/tests/xfs/754.out
index 174c4300d8..7f8da151ed 100644
--- a/tests/xfs/754.out
+++ b/tests/xfs/754.out
@@ -2,26 +2,9 @@ QA output created by 754
 Format and populate
 Fuzz inobt
 leftsib = add: offline scrub didn't fail.
+rightsib = ones: offline scrub didn't fail.
+rightsib = middlebit: offline scrub didn't fail.
+rightsib = lastbit: offline scrub didn't fail.
 rightsib = add: offline scrub didn't fail.
-keys[1].startino = zeroes: offline scrub didn't fail.
-keys[1].startino = ones: offline scrub didn't fail.
-keys[1].startino = firstbit: offline scrub didn't fail.
-keys[1].startino = middlebit: offline scrub didn't fail.
-keys[1].startino = lastbit: offline scrub didn't fail.
-keys[1].startino = add: offline scrub didn't fail.
-keys[1].startino = sub: offline scrub didn't fail.
-keys[2].startino = zeroes: offline scrub didn't fail.
-keys[2].startino = ones: offline scrub didn't fail.
-keys[2].startino = firstbit: offline scrub didn't fail.
-keys[2].startino = middlebit: offline scrub didn't fail.
-keys[2].startino = lastbit: offline scrub didn't fail.
-keys[2].startino = add: offline scrub didn't fail.
-keys[2].startino = sub: offline scrub didn't fail.
-keys[3].startino = zeroes: offline scrub didn't fail.
-keys[3].startino = ones: offline scrub didn't fail.
-keys[3].startino = firstbit: offline scrub didn't fail.
-keys[3].startino = middlebit: offline scrub didn't fail.
-keys[3].startino = lastbit: offline scrub didn't fail.
-keys[3].startino = add: offline scrub didn't fail.
-keys[3].startino = sub: offline scrub didn't fail.
+rightsib = sub: offline scrub didn't fail.
 Done fuzzing inobt
diff --git a/tests/xfs/755.out b/tests/xfs/755.out
index 55e5ff4fcb..a5ff9a1f9f 100644
--- a/tests/xfs/755.out
+++ b/tests/xfs/755.out
@@ -1,4 +1,10 @@
 QA output created by 755
 Format and populate
 Fuzz finobt
+leftsib = add: offline scrub didn't fail.
+rightsib = ones: offline scrub didn't fail.
+rightsib = middlebit: offline scrub didn't fail.
+rightsib = lastbit: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
+rightsib = sub: offline scrub didn't fail.
 Done fuzzing finobt
diff --git a/tests/xfs/756.out b/tests/xfs/756.out
index 76df05ad60..05094c2fce 100644
--- a/tests/xfs/756.out
+++ b/tests/xfs/756.out
@@ -1,4 +1,65 @@
 QA output created by 756
 Format and populate
 Fuzz rmapbt recs
+leftsib = add: offline scrub didn't fail.
+rightsib = ones: offline scrub didn't fail.
+rightsib = middlebit: offline scrub didn't fail.
+rightsib = lastbit: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
+recs[2].owner = add: offline re-scrub failed (1).
+recs[2].owner = add: offline post-mod scrub failed (1).
+recs[3].startblock = lastbit: offline scrub didn't fail.
+recs[3].blockcount = lastbit: offline scrub didn't fail.
+recs[3].owner = add: offline re-scrub failed (1).
+recs[3].owner = add: offline post-mod scrub failed (1).
+recs[5].owner = lastbit: online repair failed (1).
+recs[6].owner = lastbit: offline scrub didn't fail.
+recs[7].owner = lastbit: offline re-scrub failed (1).
+recs[7].owner = lastbit: offline post-mod scrub failed (1).
+recs[7].owner = add: offline re-scrub failed (1).
+recs[7].owner = add: offline post-mod scrub failed (1).
+recs[7].attrfork = ones: offline re-scrub failed (1).
+recs[7].attrfork = ones: offline post-mod scrub failed (1).
+recs[7].attrfork = firstbit: offline re-scrub failed (1).
+recs[7].attrfork = firstbit: offline post-mod scrub failed (1).
+recs[7].attrfork = middlebit: offline re-scrub failed (1).
+recs[7].attrfork = middlebit: offline post-mod scrub failed (1).
+recs[7].attrfork = lastbit: offline re-scrub failed (1).
+recs[7].attrfork = lastbit: offline post-mod scrub failed (1).
+recs[7].attrfork = add: offline re-scrub failed (1).
+recs[7].attrfork = add: offline post-mod scrub failed (1).
+recs[7].attrfork = sub: offline re-scrub failed (1).
+recs[7].attrfork = sub: offline post-mod scrub failed (1).
+recs[8].owner = lastbit: offline re-scrub failed (1).
+recs[8].owner = lastbit: offline post-mod scrub failed (1).
+recs[8].owner = add: offline re-scrub failed (1).
+recs[8].owner = add: offline post-mod scrub failed (1).
+recs[8].attrfork = ones: offline re-scrub failed (1).
+recs[8].attrfork = ones: offline post-mod scrub failed (1).
+recs[8].attrfork = firstbit: offline re-scrub failed (1).
+recs[8].attrfork = firstbit: offline post-mod scrub failed (1).
+recs[8].attrfork = middlebit: offline re-scrub failed (1).
+recs[8].attrfork = middlebit: offline post-mod scrub failed (1).
+recs[8].attrfork = lastbit: offline re-scrub failed (1).
+recs[8].attrfork = lastbit: offline post-mod scrub failed (1).
+recs[8].attrfork = add: offline re-scrub failed (1).
+recs[8].attrfork = add: offline post-mod scrub failed (1).
+recs[8].attrfork = sub: offline re-scrub failed (1).
+recs[8].attrfork = sub: offline post-mod scrub failed (1).
+recs[9].owner = lastbit: offline re-scrub failed (1).
+recs[9].owner = lastbit: offline post-mod scrub failed (1).
+recs[9].owner = add: offline re-scrub failed (1).
+recs[9].owner = add: offline post-mod scrub failed (1).
+recs[9].attrfork = ones: offline re-scrub failed (1).
+recs[9].attrfork = ones: offline post-mod scrub failed (1).
+recs[9].attrfork = firstbit: offline re-scrub failed (1).
+recs[9].attrfork = firstbit: offline post-mod scrub failed (1).
+recs[9].attrfork = middlebit: offline re-scrub failed (1).
+recs[9].attrfork = middlebit: offline post-mod scrub failed (1).
+recs[9].attrfork = lastbit: offline re-scrub failed (1).
+recs[9].attrfork = lastbit: offline post-mod scrub failed (1).
+recs[9].attrfork = add: offline re-scrub failed (1).
+recs[9].attrfork = add: offline post-mod scrub failed (1).
+recs[9].attrfork = sub: offline re-scrub failed (1).
+recs[9].attrfork = sub: offline post-mod scrub failed (1).
 Done fuzzing rmapbt recs
diff --git a/tests/xfs/757.out b/tests/xfs/757.out
index 293a86329d..b0622d5cf1 100644
--- a/tests/xfs/757.out
+++ b/tests/xfs/757.out
@@ -1,4 +1,529 @@
 QA output created by 757
 Format and populate
 Fuzz rmapbt keyptr
+leftsib = add: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
+keys[1].startblock = lastbit: offline scrub didn't fail.
+keys[1].owner = zeroes: offline scrub didn't fail.
+keys[1].owner = ones: offline scrub didn't fail.
+keys[1].owner = firstbit: offline scrub didn't fail.
+keys[1].owner = middlebit: offline scrub didn't fail.
+keys[1].owner = lastbit: offline scrub didn't fail.
+keys[1].owner = add: offline scrub didn't fail.
+keys[1].owner = sub: offline scrub didn't fail.
+keys[1].offset = ones: offline scrub didn't fail.
+keys[1].offset = firstbit: offline scrub didn't fail.
+keys[1].offset = middlebit: offline scrub didn't fail.
+keys[1].offset = lastbit: offline scrub didn't fail.
+keys[1].offset = add: offline scrub didn't fail.
+keys[1].offset = sub: offline scrub didn't fail.
+keys[1].extentflag = ones: offline scrub didn't fail.
+keys[1].extentflag = ones: online scrub didn't fail.
+keys[1].extentflag = firstbit: offline scrub didn't fail.
+keys[1].extentflag = firstbit: online scrub didn't fail.
+keys[1].extentflag = middlebit: offline scrub didn't fail.
+keys[1].extentflag = middlebit: online scrub didn't fail.
+keys[1].extentflag = lastbit: offline scrub didn't fail.
+keys[1].extentflag = lastbit: online scrub didn't fail.
+keys[1].extentflag = add: offline scrub didn't fail.
+keys[1].extentflag = add: online scrub didn't fail.
+keys[1].extentflag = sub: offline scrub didn't fail.
+keys[1].extentflag = sub: online scrub didn't fail.
+keys[1].attrfork = ones: offline scrub didn't fail.
+keys[1].attrfork = firstbit: offline scrub didn't fail.
+keys[1].attrfork = middlebit: offline scrub didn't fail.
+keys[1].attrfork = lastbit: offline scrub didn't fail.
+keys[1].attrfork = add: offline scrub didn't fail.
+keys[1].attrfork = sub: offline scrub didn't fail.
+keys[1].bmbtblock = ones: offline scrub didn't fail.
+keys[1].bmbtblock = firstbit: offline scrub didn't fail.
+keys[1].bmbtblock = middlebit: offline scrub didn't fail.
+keys[1].bmbtblock = lastbit: offline scrub didn't fail.
+keys[1].bmbtblock = add: offline scrub didn't fail.
+keys[1].bmbtblock = sub: offline scrub didn't fail.
+keys[1].startblock_hi = ones: offline scrub didn't fail.
+keys[1].startblock_hi = firstbit: offline scrub didn't fail.
+keys[1].startblock_hi = middlebit: offline scrub didn't fail.
+keys[1].startblock_hi = lastbit: offline scrub didn't fail.
+keys[1].startblock_hi = add: offline scrub didn't fail.
+keys[1].startblock_hi = sub: offline scrub didn't fail.
+keys[1].owner_hi = ones: offline scrub didn't fail.
+keys[1].owner_hi = firstbit: offline scrub didn't fail.
+keys[1].owner_hi = middlebit: offline scrub didn't fail.
+keys[1].owner_hi = lastbit: offline scrub didn't fail.
+keys[1].owner_hi = add: offline scrub didn't fail.
+keys[1].owner_hi = sub: offline scrub didn't fail.
+keys[1].offset_hi = ones: offline scrub didn't fail.
+keys[1].offset_hi = firstbit: offline scrub didn't fail.
+keys[1].offset_hi = middlebit: offline scrub didn't fail.
+keys[1].offset_hi = add: offline scrub didn't fail.
+keys[1].offset_hi = sub: offline scrub didn't fail.
+keys[1].extentflag_hi = ones: offline scrub didn't fail.
+keys[1].extentflag_hi = ones: online scrub didn't fail.
+keys[1].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[1].extentflag_hi = firstbit: online scrub didn't fail.
+keys[1].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[1].extentflag_hi = middlebit: online scrub didn't fail.
+keys[1].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[1].extentflag_hi = lastbit: online scrub didn't fail.
+keys[1].extentflag_hi = add: offline scrub didn't fail.
+keys[1].extentflag_hi = add: online scrub didn't fail.
+keys[1].extentflag_hi = sub: offline scrub didn't fail.
+keys[1].extentflag_hi = sub: online scrub didn't fail.
+keys[1].attrfork_hi = ones: offline scrub didn't fail.
+keys[1].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[1].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[1].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[1].attrfork_hi = add: offline scrub didn't fail.
+keys[1].attrfork_hi = sub: offline scrub didn't fail.
+keys[1].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[1].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[1].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[1].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[1].bmbtblock_hi = add: offline scrub didn't fail.
+keys[1].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[2].owner = zeroes: offline scrub didn't fail.
+keys[2].offset = zeroes: offline scrub didn't fail.
+keys[2].offset = lastbit: offline scrub didn't fail.
+keys[2].extentflag = ones: offline scrub didn't fail.
+keys[2].extentflag = ones: online scrub didn't fail.
+keys[2].extentflag = firstbit: offline scrub didn't fail.
+keys[2].extentflag = firstbit: online scrub didn't fail.
+keys[2].extentflag = middlebit: offline scrub didn't fail.
+keys[2].extentflag = middlebit: online scrub didn't fail.
+keys[2].extentflag = lastbit: offline scrub didn't fail.
+keys[2].extentflag = lastbit: online scrub didn't fail.
+keys[2].extentflag = add: offline scrub didn't fail.
+keys[2].extentflag = add: online scrub didn't fail.
+keys[2].extentflag = sub: offline scrub didn't fail.
+keys[2].extentflag = sub: online scrub didn't fail.
+keys[2].startblock_hi = ones: offline scrub didn't fail.
+keys[2].startblock_hi = firstbit: offline scrub didn't fail.
+keys[2].startblock_hi = middlebit: offline scrub didn't fail.
+keys[2].startblock_hi = lastbit: offline scrub didn't fail.
+keys[2].startblock_hi = add: offline scrub didn't fail.
+keys[2].startblock_hi = sub: offline scrub didn't fail.
+keys[2].owner_hi = ones: offline scrub didn't fail.
+keys[2].owner_hi = firstbit: offline scrub didn't fail.
+keys[2].owner_hi = middlebit: offline scrub didn't fail.
+keys[2].owner_hi = lastbit: offline scrub didn't fail.
+keys[2].owner_hi = add: offline scrub didn't fail.
+keys[2].owner_hi = sub: offline scrub didn't fail.
+keys[2].offset_hi = ones: offline scrub didn't fail.
+keys[2].offset_hi = firstbit: offline scrub didn't fail.
+keys[2].offset_hi = middlebit: offline scrub didn't fail.
+keys[2].offset_hi = add: offline scrub didn't fail.
+keys[2].offset_hi = sub: offline scrub didn't fail.
+keys[2].extentflag_hi = ones: offline scrub didn't fail.
+keys[2].extentflag_hi = ones: online scrub didn't fail.
+keys[2].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[2].extentflag_hi = firstbit: online scrub didn't fail.
+keys[2].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[2].extentflag_hi = middlebit: online scrub didn't fail.
+keys[2].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[2].extentflag_hi = lastbit: online scrub didn't fail.
+keys[2].extentflag_hi = add: offline scrub didn't fail.
+keys[2].extentflag_hi = add: online scrub didn't fail.
+keys[2].extentflag_hi = sub: offline scrub didn't fail.
+keys[2].extentflag_hi = sub: online scrub didn't fail.
+keys[2].attrfork_hi = ones: offline scrub didn't fail.
+keys[2].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[2].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[2].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[2].attrfork_hi = add: offline scrub didn't fail.
+keys[2].attrfork_hi = sub: offline scrub didn't fail.
+keys[2].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[2].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[2].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[2].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[2].bmbtblock_hi = add: offline scrub didn't fail.
+keys[2].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[3].owner = zeroes: offline scrub didn't fail.
+keys[3].offset = zeroes: offline scrub didn't fail.
+keys[3].offset = lastbit: offline scrub didn't fail.
+keys[3].extentflag = ones: offline scrub didn't fail.
+keys[3].extentflag = ones: online scrub didn't fail.
+keys[3].extentflag = firstbit: offline scrub didn't fail.
+keys[3].extentflag = firstbit: online scrub didn't fail.
+keys[3].extentflag = middlebit: offline scrub didn't fail.
+keys[3].extentflag = middlebit: online scrub didn't fail.
+keys[3].extentflag = lastbit: offline scrub didn't fail.
+keys[3].extentflag = lastbit: online scrub didn't fail.
+keys[3].extentflag = add: offline scrub didn't fail.
+keys[3].extentflag = add: online scrub didn't fail.
+keys[3].extentflag = sub: offline scrub didn't fail.
+keys[3].extentflag = sub: online scrub didn't fail.
+keys[3].startblock_hi = ones: offline scrub didn't fail.
+keys[3].startblock_hi = firstbit: offline scrub didn't fail.
+keys[3].startblock_hi = middlebit: offline scrub didn't fail.
+keys[3].startblock_hi = lastbit: offline scrub didn't fail.
+keys[3].startblock_hi = add: offline scrub didn't fail.
+keys[3].startblock_hi = sub: offline scrub didn't fail.
+keys[3].owner_hi = ones: offline scrub didn't fail.
+keys[3].owner_hi = firstbit: offline scrub didn't fail.
+keys[3].owner_hi = middlebit: offline scrub didn't fail.
+keys[3].owner_hi = lastbit: offline scrub didn't fail.
+keys[3].owner_hi = add: offline scrub didn't fail.
+keys[3].offset_hi = ones: offline scrub didn't fail.
+keys[3].offset_hi = firstbit: offline scrub didn't fail.
+keys[3].offset_hi = middlebit: offline scrub didn't fail.
+keys[3].offset_hi = add: offline scrub didn't fail.
+keys[3].offset_hi = sub: offline scrub didn't fail.
+keys[3].extentflag_hi = ones: offline scrub didn't fail.
+keys[3].extentflag_hi = ones: online scrub didn't fail.
+keys[3].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[3].extentflag_hi = firstbit: online scrub didn't fail.
+keys[3].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[3].extentflag_hi = middlebit: online scrub didn't fail.
+keys[3].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[3].extentflag_hi = lastbit: online scrub didn't fail.
+keys[3].extentflag_hi = add: offline scrub didn't fail.
+keys[3].extentflag_hi = add: online scrub didn't fail.
+keys[3].extentflag_hi = sub: offline scrub didn't fail.
+keys[3].extentflag_hi = sub: online scrub didn't fail.
+keys[3].attrfork_hi = ones: offline scrub didn't fail.
+keys[3].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[3].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[3].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[3].attrfork_hi = add: offline scrub didn't fail.
+keys[3].attrfork_hi = sub: offline scrub didn't fail.
+keys[3].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[3].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[3].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[3].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[3].bmbtblock_hi = add: offline scrub didn't fail.
+keys[3].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[4].owner = zeroes: offline scrub didn't fail.
+keys[4].owner = sub: offline scrub didn't fail.
+keys[4].offset = zeroes: offline scrub didn't fail.
+keys[4].offset = lastbit: offline scrub didn't fail.
+keys[4].extentflag = ones: offline scrub didn't fail.
+keys[4].extentflag = ones: online scrub didn't fail.
+keys[4].extentflag = firstbit: offline scrub didn't fail.
+keys[4].extentflag = firstbit: online scrub didn't fail.
+keys[4].extentflag = middlebit: offline scrub didn't fail.
+keys[4].extentflag = middlebit: online scrub didn't fail.
+keys[4].extentflag = lastbit: offline scrub didn't fail.
+keys[4].extentflag = lastbit: online scrub didn't fail.
+keys[4].extentflag = add: offline scrub didn't fail.
+keys[4].extentflag = add: online scrub didn't fail.
+keys[4].extentflag = sub: offline scrub didn't fail.
+keys[4].extentflag = sub: online scrub didn't fail.
+keys[4].startblock_hi = ones: offline scrub didn't fail.
+keys[4].startblock_hi = firstbit: offline scrub didn't fail.
+keys[4].startblock_hi = middlebit: offline scrub didn't fail.
+keys[4].startblock_hi = lastbit: offline scrub didn't fail.
+keys[4].startblock_hi = add: offline scrub didn't fail.
+keys[4].startblock_hi = sub: offline scrub didn't fail.
+keys[4].owner_hi = ones: offline scrub didn't fail.
+keys[4].owner_hi = firstbit: offline scrub didn't fail.
+keys[4].owner_hi = middlebit: offline scrub didn't fail.
+keys[4].owner_hi = lastbit: offline scrub didn't fail.
+keys[4].owner_hi = add: offline scrub didn't fail.
+keys[4].offset_hi = ones: offline scrub didn't fail.
+keys[4].offset_hi = firstbit: offline scrub didn't fail.
+keys[4].offset_hi = middlebit: offline scrub didn't fail.
+keys[4].offset_hi = add: offline scrub didn't fail.
+keys[4].offset_hi = sub: offline scrub didn't fail.
+keys[4].extentflag_hi = ones: offline scrub didn't fail.
+keys[4].extentflag_hi = ones: online scrub didn't fail.
+keys[4].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[4].extentflag_hi = firstbit: online scrub didn't fail.
+keys[4].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[4].extentflag_hi = middlebit: online scrub didn't fail.
+keys[4].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[4].extentflag_hi = lastbit: online scrub didn't fail.
+keys[4].extentflag_hi = add: offline scrub didn't fail.
+keys[4].extentflag_hi = add: online scrub didn't fail.
+keys[4].extentflag_hi = sub: offline scrub didn't fail.
+keys[4].extentflag_hi = sub: online scrub didn't fail.
+keys[4].attrfork_hi = ones: offline scrub didn't fail.
+keys[4].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[4].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[4].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[4].attrfork_hi = add: offline scrub didn't fail.
+keys[4].attrfork_hi = sub: offline scrub didn't fail.
+keys[4].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[4].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[4].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[4].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[4].bmbtblock_hi = add: offline scrub didn't fail.
+keys[4].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[5].owner = zeroes: offline scrub didn't fail.
+keys[5].owner = sub: offline scrub didn't fail.
+keys[5].offset = zeroes: offline scrub didn't fail.
+keys[5].offset = lastbit: offline scrub didn't fail.
+keys[5].extentflag = ones: offline scrub didn't fail.
+keys[5].extentflag = ones: online scrub didn't fail.
+keys[5].extentflag = firstbit: offline scrub didn't fail.
+keys[5].extentflag = firstbit: online scrub didn't fail.
+keys[5].extentflag = middlebit: offline scrub didn't fail.
+keys[5].extentflag = middlebit: online scrub didn't fail.
+keys[5].extentflag = lastbit: offline scrub didn't fail.
+keys[5].extentflag = lastbit: online scrub didn't fail.
+keys[5].extentflag = add: offline scrub didn't fail.
+keys[5].extentflag = add: online scrub didn't fail.
+keys[5].extentflag = sub: offline scrub didn't fail.
+keys[5].extentflag = sub: online scrub didn't fail.
+keys[5].startblock_hi = ones: offline scrub didn't fail.
+keys[5].startblock_hi = firstbit: offline scrub didn't fail.
+keys[5].startblock_hi = middlebit: offline scrub didn't fail.
+keys[5].startblock_hi = lastbit: offline scrub didn't fail.
+keys[5].startblock_hi = add: offline scrub didn't fail.
+keys[5].startblock_hi = sub: offline scrub didn't fail.
+keys[5].owner_hi = ones: offline scrub didn't fail.
+keys[5].owner_hi = firstbit: offline scrub didn't fail.
+keys[5].owner_hi = middlebit: offline scrub didn't fail.
+keys[5].owner_hi = lastbit: offline scrub didn't fail.
+keys[5].owner_hi = add: offline scrub didn't fail.
+keys[5].offset_hi = ones: offline scrub didn't fail.
+keys[5].offset_hi = firstbit: offline scrub didn't fail.
+keys[5].offset_hi = middlebit: offline scrub didn't fail.
+keys[5].offset_hi = add: offline scrub didn't fail.
+keys[5].offset_hi = sub: offline scrub didn't fail.
+keys[5].extentflag_hi = ones: offline scrub didn't fail.
+keys[5].extentflag_hi = ones: online scrub didn't fail.
+keys[5].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[5].extentflag_hi = firstbit: online scrub didn't fail.
+keys[5].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[5].extentflag_hi = middlebit: online scrub didn't fail.
+keys[5].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[5].extentflag_hi = lastbit: online scrub didn't fail.
+keys[5].extentflag_hi = add: offline scrub didn't fail.
+keys[5].extentflag_hi = add: online scrub didn't fail.
+keys[5].extentflag_hi = sub: offline scrub didn't fail.
+keys[5].extentflag_hi = sub: online scrub didn't fail.
+keys[5].attrfork_hi = ones: offline scrub didn't fail.
+keys[5].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[5].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[5].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[5].attrfork_hi = add: offline scrub didn't fail.
+keys[5].attrfork_hi = sub: offline scrub didn't fail.
+keys[5].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[5].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[5].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[5].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[5].bmbtblock_hi = add: offline scrub didn't fail.
+keys[5].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[6].owner = zeroes: offline scrub didn't fail.
+keys[6].owner = sub: offline scrub didn't fail.
+keys[6].offset = zeroes: offline scrub didn't fail.
+keys[6].offset = lastbit: offline scrub didn't fail.
+keys[6].extentflag = ones: offline scrub didn't fail.
+keys[6].extentflag = ones: online scrub didn't fail.
+keys[6].extentflag = firstbit: offline scrub didn't fail.
+keys[6].extentflag = firstbit: online scrub didn't fail.
+keys[6].extentflag = middlebit: offline scrub didn't fail.
+keys[6].extentflag = middlebit: online scrub didn't fail.
+keys[6].extentflag = lastbit: offline scrub didn't fail.
+keys[6].extentflag = lastbit: online scrub didn't fail.
+keys[6].extentflag = add: offline scrub didn't fail.
+keys[6].extentflag = add: online scrub didn't fail.
+keys[6].extentflag = sub: offline scrub didn't fail.
+keys[6].extentflag = sub: online scrub didn't fail.
+keys[6].startblock_hi = ones: offline scrub didn't fail.
+keys[6].startblock_hi = firstbit: offline scrub didn't fail.
+keys[6].startblock_hi = middlebit: offline scrub didn't fail.
+keys[6].startblock_hi = lastbit: offline scrub didn't fail.
+keys[6].startblock_hi = add: offline scrub didn't fail.
+keys[6].owner_hi = ones: offline scrub didn't fail.
+keys[6].owner_hi = firstbit: offline scrub didn't fail.
+keys[6].owner_hi = middlebit: offline scrub didn't fail.
+keys[6].owner_hi = lastbit: offline scrub didn't fail.
+keys[6].owner_hi = add: offline scrub didn't fail.
+keys[6].offset_hi = ones: offline scrub didn't fail.
+keys[6].offset_hi = firstbit: offline scrub didn't fail.
+keys[6].offset_hi = middlebit: offline scrub didn't fail.
+keys[6].offset_hi = add: offline scrub didn't fail.
+keys[6].offset_hi = sub: offline scrub didn't fail.
+keys[6].extentflag_hi = ones: offline scrub didn't fail.
+keys[6].extentflag_hi = ones: online scrub didn't fail.
+keys[6].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[6].extentflag_hi = firstbit: online scrub didn't fail.
+keys[6].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[6].extentflag_hi = middlebit: online scrub didn't fail.
+keys[6].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[6].extentflag_hi = lastbit: online scrub didn't fail.
+keys[6].extentflag_hi = add: offline scrub didn't fail.
+keys[6].extentflag_hi = add: online scrub didn't fail.
+keys[6].extentflag_hi = sub: offline scrub didn't fail.
+keys[6].extentflag_hi = sub: online scrub didn't fail.
+keys[6].attrfork_hi = ones: offline scrub didn't fail.
+keys[6].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[6].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[6].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[6].attrfork_hi = add: offline scrub didn't fail.
+keys[6].attrfork_hi = sub: offline scrub didn't fail.
+keys[6].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[6].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[6].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[6].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[6].bmbtblock_hi = add: offline scrub didn't fail.
+keys[6].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[7].owner = zeroes: offline scrub didn't fail.
+keys[7].owner = lastbit: offline scrub didn't fail.
+keys[7].owner = sub: offline scrub didn't fail.
+keys[7].offset = zeroes: offline scrub didn't fail.
+keys[7].offset = lastbit: offline scrub didn't fail.
+keys[7].extentflag = ones: offline scrub didn't fail.
+keys[7].extentflag = ones: online scrub didn't fail.
+keys[7].extentflag = firstbit: offline scrub didn't fail.
+keys[7].extentflag = firstbit: online scrub didn't fail.
+keys[7].extentflag = middlebit: offline scrub didn't fail.
+keys[7].extentflag = middlebit: online scrub didn't fail.
+keys[7].extentflag = lastbit: offline scrub didn't fail.
+keys[7].extentflag = lastbit: online scrub didn't fail.
+keys[7].extentflag = add: offline scrub didn't fail.
+keys[7].extentflag = add: online scrub didn't fail.
+keys[7].extentflag = sub: offline scrub didn't fail.
+keys[7].extentflag = sub: online scrub didn't fail.
+keys[7].startblock_hi = ones: offline scrub didn't fail.
+keys[7].startblock_hi = firstbit: offline scrub didn't fail.
+keys[7].startblock_hi = middlebit: offline scrub didn't fail.
+keys[7].startblock_hi = lastbit: offline scrub didn't fail.
+keys[7].startblock_hi = add: offline scrub didn't fail.
+keys[7].owner_hi = ones: offline scrub didn't fail.
+keys[7].owner_hi = firstbit: offline scrub didn't fail.
+keys[7].owner_hi = middlebit: offline scrub didn't fail.
+keys[7].owner_hi = add: offline scrub didn't fail.
+keys[7].offset_hi = ones: offline scrub didn't fail.
+keys[7].offset_hi = firstbit: offline scrub didn't fail.
+keys[7].offset_hi = middlebit: offline scrub didn't fail.
+keys[7].offset_hi = add: offline scrub didn't fail.
+keys[7].offset_hi = sub: offline scrub didn't fail.
+keys[7].extentflag_hi = ones: offline scrub didn't fail.
+keys[7].extentflag_hi = ones: online scrub didn't fail.
+keys[7].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[7].extentflag_hi = firstbit: online scrub didn't fail.
+keys[7].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[7].extentflag_hi = middlebit: online scrub didn't fail.
+keys[7].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[7].extentflag_hi = lastbit: online scrub didn't fail.
+keys[7].extentflag_hi = add: offline scrub didn't fail.
+keys[7].extentflag_hi = add: online scrub didn't fail.
+keys[7].extentflag_hi = sub: offline scrub didn't fail.
+keys[7].extentflag_hi = sub: online scrub didn't fail.
+keys[7].attrfork_hi = ones: offline scrub didn't fail.
+keys[7].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[7].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[7].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[7].attrfork_hi = add: offline scrub didn't fail.
+keys[7].attrfork_hi = sub: offline scrub didn't fail.
+keys[7].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[7].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[7].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[7].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[7].bmbtblock_hi = add: offline scrub didn't fail.
+keys[7].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[8].owner = zeroes: offline scrub didn't fail.
+keys[8].owner = lastbit: offline scrub didn't fail.
+keys[8].owner = sub: offline scrub didn't fail.
+keys[8].offset = zeroes: offline scrub didn't fail.
+keys[8].offset = lastbit: offline scrub didn't fail.
+keys[8].extentflag = ones: offline scrub didn't fail.
+keys[8].extentflag = ones: online scrub didn't fail.
+keys[8].extentflag = firstbit: offline scrub didn't fail.
+keys[8].extentflag = firstbit: online scrub didn't fail.
+keys[8].extentflag = middlebit: offline scrub didn't fail.
+keys[8].extentflag = middlebit: online scrub didn't fail.
+keys[8].extentflag = lastbit: offline scrub didn't fail.
+keys[8].extentflag = lastbit: online scrub didn't fail.
+keys[8].extentflag = add: offline scrub didn't fail.
+keys[8].extentflag = add: online scrub didn't fail.
+keys[8].extentflag = sub: offline scrub didn't fail.
+keys[8].extentflag = sub: online scrub didn't fail.
+keys[8].startblock_hi = ones: offline scrub didn't fail.
+keys[8].startblock_hi = firstbit: offline scrub didn't fail.
+keys[8].startblock_hi = middlebit: offline scrub didn't fail.
+keys[8].startblock_hi = lastbit: offline scrub didn't fail.
+keys[8].startblock_hi = add: offline scrub didn't fail.
+keys[8].owner_hi = ones: offline scrub didn't fail.
+keys[8].owner_hi = firstbit: offline scrub didn't fail.
+keys[8].owner_hi = middlebit: offline scrub didn't fail.
+keys[8].owner_hi = lastbit: offline scrub didn't fail.
+keys[8].owner_hi = add: offline scrub didn't fail.
+keys[8].offset_hi = ones: offline scrub didn't fail.
+keys[8].offset_hi = firstbit: offline scrub didn't fail.
+keys[8].offset_hi = middlebit: offline scrub didn't fail.
+keys[8].offset_hi = add: offline scrub didn't fail.
+keys[8].offset_hi = sub: offline scrub didn't fail.
+keys[8].extentflag_hi = ones: offline scrub didn't fail.
+keys[8].extentflag_hi = ones: online scrub didn't fail.
+keys[8].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[8].extentflag_hi = firstbit: online scrub didn't fail.
+keys[8].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[8].extentflag_hi = middlebit: online scrub didn't fail.
+keys[8].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[8].extentflag_hi = lastbit: online scrub didn't fail.
+keys[8].extentflag_hi = add: offline scrub didn't fail.
+keys[8].extentflag_hi = add: online scrub didn't fail.
+keys[8].extentflag_hi = sub: offline scrub didn't fail.
+keys[8].extentflag_hi = sub: online scrub didn't fail.
+keys[8].attrfork_hi = ones: offline scrub didn't fail.
+keys[8].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[8].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[8].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[8].attrfork_hi = add: offline scrub didn't fail.
+keys[8].attrfork_hi = sub: offline scrub didn't fail.
+keys[8].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[8].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[8].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[8].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[8].bmbtblock_hi = add: offline scrub didn't fail.
+keys[8].bmbtblock_hi = sub: offline scrub didn't fail.
+keys[9].owner = zeroes: offline scrub didn't fail.
+keys[9].owner = sub: offline scrub didn't fail.
+keys[9].offset = zeroes: offline scrub didn't fail.
+keys[9].offset = lastbit: offline scrub didn't fail.
+keys[9].extentflag = ones: offline scrub didn't fail.
+keys[9].extentflag = ones: online scrub didn't fail.
+keys[9].extentflag = firstbit: offline scrub didn't fail.
+keys[9].extentflag = firstbit: online scrub didn't fail.
+keys[9].extentflag = middlebit: offline scrub didn't fail.
+keys[9].extentflag = middlebit: online scrub didn't fail.
+keys[9].extentflag = lastbit: offline scrub didn't fail.
+keys[9].extentflag = lastbit: online scrub didn't fail.
+keys[9].extentflag = add: offline scrub didn't fail.
+keys[9].extentflag = add: online scrub didn't fail.
+keys[9].extentflag = sub: offline scrub didn't fail.
+keys[9].extentflag = sub: online scrub didn't fail.
+keys[9].startblock_hi = ones: offline scrub didn't fail.
+keys[9].startblock_hi = firstbit: offline scrub didn't fail.
+keys[9].startblock_hi = middlebit: offline scrub didn't fail.
+keys[9].startblock_hi = lastbit: offline scrub didn't fail.
+keys[9].startblock_hi = add: offline scrub didn't fail.
+keys[9].owner_hi = ones: offline scrub didn't fail.
+keys[9].owner_hi = firstbit: offline scrub didn't fail.
+keys[9].owner_hi = middlebit: offline scrub didn't fail.
+keys[9].owner_hi = lastbit: offline scrub didn't fail.
+keys[9].owner_hi = add: offline scrub didn't fail.
+keys[9].offset_hi = ones: offline scrub didn't fail.
+keys[9].offset_hi = firstbit: offline scrub didn't fail.
+keys[9].offset_hi = middlebit: offline scrub didn't fail.
+keys[9].offset_hi = add: offline scrub didn't fail.
+keys[9].offset_hi = sub: offline scrub didn't fail.
+keys[9].extentflag_hi = ones: offline scrub didn't fail.
+keys[9].extentflag_hi = ones: online scrub didn't fail.
+keys[9].extentflag_hi = firstbit: offline scrub didn't fail.
+keys[9].extentflag_hi = firstbit: online scrub didn't fail.
+keys[9].extentflag_hi = middlebit: offline scrub didn't fail.
+keys[9].extentflag_hi = middlebit: online scrub didn't fail.
+keys[9].extentflag_hi = lastbit: offline scrub didn't fail.
+keys[9].extentflag_hi = lastbit: online scrub didn't fail.
+keys[9].extentflag_hi = add: offline scrub didn't fail.
+keys[9].extentflag_hi = add: online scrub didn't fail.
+keys[9].extentflag_hi = sub: offline scrub didn't fail.
+keys[9].extentflag_hi = sub: online scrub didn't fail.
+keys[9].attrfork_hi = ones: offline scrub didn't fail.
+keys[9].attrfork_hi = firstbit: offline scrub didn't fail.
+keys[9].attrfork_hi = middlebit: offline scrub didn't fail.
+keys[9].attrfork_hi = lastbit: offline scrub didn't fail.
+keys[9].attrfork_hi = add: offline scrub didn't fail.
+keys[9].attrfork_hi = sub: offline scrub didn't fail.
+keys[9].bmbtblock_hi = ones: offline scrub didn't fail.
+keys[9].bmbtblock_hi = firstbit: offline scrub didn't fail.
+keys[9].bmbtblock_hi = middlebit: offline scrub didn't fail.
+keys[9].bmbtblock_hi = lastbit: offline scrub didn't fail.
+keys[9].bmbtblock_hi = add: offline scrub didn't fail.
+keys[9].bmbtblock_hi = sub: offline scrub didn't fail.
 Done fuzzing rmapbt keyptr
diff --git a/tests/xfs/758.out b/tests/xfs/758.out
index e969d7ba02..8a911c9735 100644
--- a/tests/xfs/758.out
+++ b/tests/xfs/758.out
@@ -1,4 +1,9 @@
 QA output created by 758
 Format and populate
 Fuzz refcountbt
+leftsib = add: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
+keys[1].startblock = zeroes: offline scrub didn't fail.
+keys[1].startblock = lastbit: offline scrub didn't fail.
+keys[1].startblock = sub: offline scrub didn't fail.
 Done fuzzing refcountbt
diff --git a/tests/xfs/759.out b/tests/xfs/759.out
index 3eaa678c0a..220883bd84 100644
--- a/tests/xfs/759.out
+++ b/tests/xfs/759.out
@@ -2,4 +2,98 @@ QA output created by 759
 Format and populate
 Find btree-format dir inode
 Fuzz inode
+core.mode = zeroes: offline re-scrub failed (1).
+core.mode = zeroes: offline post-mod scrub failed (1).
+core.mode = firstbit: online repair failed (1).
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.nlinkv2 = zeroes: online repair failed (4).
+core.size = zeroes: online repair failed (1).
+core.size = middlebit: offline scrub didn't fail.
+core.size = middlebit: online health check failed (0).
+core.size = middlebit: online repair failed (4).
+core.size = middlebit: online re-scrub failed (4).
+core.size = middlebit: online post-mod scrub failed (4).
+core.size = lastbit: offline scrub didn't fail.
+core.size = lastbit: online scrub didn't fail.
+core.size = add: offline scrub didn't fail.
+core.size = add: online scrub didn't fail.
+core.size = sub: offline scrub didn't fail.
+core.size = sub: online scrub didn't fail.
+core.naextents = lastbit: online repair failed (1).
+core.forkoff = ones: online repair failed (1).
+core.forkoff = firstbit: online repair failed (1).
+core.forkoff = add: online repair failed (1).
+core.forkoff = sub: online repair failed (1).
+core.rtinherit = ones: offline scrub didn't fail.
+core.rtinherit = ones: online scrub didn't fail.
+core.rtinherit = firstbit: offline scrub didn't fail.
+core.rtinherit = firstbit: online scrub didn't fail.
+core.rtinherit = middlebit: offline scrub didn't fail.
+core.rtinherit = middlebit: online scrub didn't fail.
+core.rtinherit = lastbit: offline scrub didn't fail.
+core.rtinherit = lastbit: online scrub didn't fail.
+core.rtinherit = add: offline scrub didn't fail.
+core.rtinherit = add: online scrub didn't fail.
+core.rtinherit = sub: offline scrub didn't fail.
+core.rtinherit = sub: online scrub didn't fail.
+core.projinherit = ones: offline scrub didn't fail.
+core.projinherit = ones: online scrub didn't fail.
+core.projinherit = firstbit: offline scrub didn't fail.
+core.projinherit = firstbit: online scrub didn't fail.
+core.projinherit = middlebit: offline scrub didn't fail.
+core.projinherit = middlebit: online scrub didn't fail.
+core.projinherit = lastbit: offline scrub didn't fail.
+core.projinherit = lastbit: online scrub didn't fail.
+core.projinherit = add: offline scrub didn't fail.
+core.projinherit = add: online scrub didn't fail.
+core.projinherit = sub: offline scrub didn't fail.
+core.projinherit = sub: online scrub didn't fail.
+core.nosymlinks = ones: offline scrub didn't fail.
+core.nosymlinks = ones: online scrub didn't fail.
+core.nosymlinks = firstbit: offline scrub didn't fail.
+core.nosymlinks = firstbit: online scrub didn't fail.
+core.nosymlinks = middlebit: offline scrub didn't fail.
+core.nosymlinks = middlebit: online scrub didn't fail.
+core.nosymlinks = lastbit: offline scrub didn't fail.
+core.nosymlinks = lastbit: online scrub didn't fail.
+core.nosymlinks = add: offline scrub didn't fail.
+core.nosymlinks = add: online scrub didn't fail.
+core.nosymlinks = sub: offline scrub didn't fail.
+core.nosymlinks = sub: online scrub didn't fail.
+next_unlinked = add: online scrub didn't fail.
+next_unlinked = add: offline re-scrub failed (1).
+next_unlinked = add: offline post-mod scrub failed (1).
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = ones: offline re-scrub failed (1).
+v3.flags2 = ones: offline post-mod scrub failed (1).
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.flags2 = middlebit: offline re-scrub failed (1).
+v3.flags2 = middlebit: offline post-mod scrub failed (1).
+v3.flags2 = lastbit: offline scrub didn't fail.
+v3.flags2 = lastbit: online scrub didn't fail.
+v3.flags2 = add: online scrub didn't fail.
+v3.flags2 = add: offline re-scrub failed (1).
+v3.flags2 = add: offline post-mod scrub failed (1).
+v3.flags2 = sub: offline re-scrub failed (1).
+v3.flags2 = sub: offline post-mod scrub failed (1).
+u3.bmbt.ptrs[1] = firstbit: offline scrub didn't fail.
+u3.bmbt.ptrs[1] = firstbit: online scrub didn't fail.
 Done fuzzing inode
diff --git a/tests/xfs/760.out b/tests/xfs/760.out
index 9b66d13f2c..c08d5c5672 100644
--- a/tests/xfs/760.out
+++ b/tests/xfs/760.out
@@ -2,4 +2,68 @@ QA output created by 760
 Format and populate
 Find extents-format file inode
 Fuzz inode
+core.mode = zeroes: offline re-scrub failed (1).
+core.mode = zeroes: offline post-mod scrub failed (1).
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.nlinkv2 = zeroes: online repair failed (4).
+core.nlinkv2 = lastbit: online repair failed (4).
+core.size = zeroes: offline scrub didn't fail.
+core.size = zeroes: online scrub didn't fail.
+core.size = middlebit: offline scrub didn't fail.
+core.size = middlebit: online scrub didn't fail.
+core.size = lastbit: offline scrub didn't fail.
+core.size = lastbit: online scrub didn't fail.
+core.size = add: offline scrub didn't fail.
+core.size = add: online scrub didn't fail.
+core.size = sub: offline scrub didn't fail.
+core.size = sub: online scrub didn't fail.
+core.forkoff = firstbit: online repair failed (1).
+next_unlinked = add: online scrub didn't fail.
+next_unlinked = add: offline re-scrub failed (1).
+next_unlinked = add: offline post-mod scrub failed (1).
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = ones: offline re-scrub failed (1).
+v3.flags2 = ones: offline post-mod scrub failed (1).
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.flags2 = middlebit: offline re-scrub failed (1).
+v3.flags2 = middlebit: offline post-mod scrub failed (1).
+v3.flags2 = lastbit: offline scrub didn't fail.
+v3.flags2 = lastbit: online scrub didn't fail.
+v3.flags2 = add: online scrub didn't fail.
+v3.flags2 = add: offline re-scrub failed (1).
+v3.flags2 = add: offline post-mod scrub failed (1).
+v3.flags2 = sub: offline re-scrub failed (1).
+v3.flags2 = sub: offline post-mod scrub failed (1).
+v3.reflink = ones: offline scrub didn't fail.
+v3.reflink = ones: online scrub didn't fail.
+v3.reflink = firstbit: offline scrub didn't fail.
+v3.reflink = firstbit: online scrub didn't fail.
+v3.reflink = middlebit: offline scrub didn't fail.
+v3.reflink = middlebit: online scrub didn't fail.
+v3.reflink = lastbit: offline scrub didn't fail.
+v3.reflink = lastbit: online scrub didn't fail.
+v3.reflink = add: offline scrub didn't fail.
+v3.reflink = add: online scrub didn't fail.
+v3.reflink = sub: offline scrub didn't fail.
+v3.reflink = sub: online scrub didn't fail.
+u3.bmx[0].blockcount = middlebit: online repair failed (4).
+u3.bmx[0].blockcount = add: online repair failed (4).
 Done fuzzing inode
diff --git a/tests/xfs/761.out b/tests/xfs/761.out
index 43cbe4d000..28db068aa4 100644
--- a/tests/xfs/761.out
+++ b/tests/xfs/761.out
@@ -2,4 +2,70 @@ QA output created by 761
 Format and populate
 Find btree-format file inode
 Fuzz inode
+core.mode = zeroes: offline re-scrub failed (1).
+core.mode = zeroes: offline post-mod scrub failed (1).
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.nlinkv2 = zeroes: online repair failed (4).
+core.nlinkv2 = lastbit: online repair failed (4).
+core.size = zeroes: offline scrub didn't fail.
+core.size = zeroes: online scrub didn't fail.
+core.size = middlebit: offline scrub didn't fail.
+core.size = middlebit: online scrub didn't fail.
+core.size = lastbit: offline scrub didn't fail.
+core.size = lastbit: online scrub didn't fail.
+core.size = add: offline scrub didn't fail.
+core.size = add: online scrub didn't fail.
+core.size = sub: offline scrub didn't fail.
+core.size = sub: online scrub didn't fail.
+core.naextents = lastbit: online repair failed (1).
+core.forkoff = ones: online repair failed (1).
+core.forkoff = firstbit: online repair failed (1).
+core.forkoff = add: online repair failed (1).
+core.forkoff = sub: online repair failed (1).
+next_unlinked = add: online scrub didn't fail.
+next_unlinked = add: offline re-scrub failed (1).
+next_unlinked = add: offline post-mod scrub failed (1).
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = ones: offline re-scrub failed (1).
+v3.flags2 = ones: offline post-mod scrub failed (1).
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.flags2 = middlebit: offline re-scrub failed (1).
+v3.flags2 = middlebit: offline post-mod scrub failed (1).
+v3.flags2 = lastbit: offline scrub didn't fail.
+v3.flags2 = lastbit: online scrub didn't fail.
+v3.flags2 = add: online scrub didn't fail.
+v3.flags2 = add: offline re-scrub failed (1).
+v3.flags2 = add: offline post-mod scrub failed (1).
+v3.flags2 = sub: offline re-scrub failed (1).
+v3.flags2 = sub: offline post-mod scrub failed (1).
+v3.reflink = ones: offline scrub didn't fail.
+v3.reflink = ones: online scrub didn't fail.
+v3.reflink = firstbit: offline scrub didn't fail.
+v3.reflink = firstbit: online scrub didn't fail.
+v3.reflink = middlebit: offline scrub didn't fail.
+v3.reflink = middlebit: online scrub didn't fail.
+v3.reflink = lastbit: offline scrub didn't fail.
+v3.reflink = lastbit: online scrub didn't fail.
+v3.reflink = add: offline scrub didn't fail.
+v3.reflink = add: online scrub didn't fail.
+v3.reflink = sub: offline scrub didn't fail.
+v3.reflink = sub: online scrub didn't fail.
 Done fuzzing inode
diff --git a/tests/xfs/762.out b/tests/xfs/762.out
index 1ff528e296..0dcc55f7ba 100644
--- a/tests/xfs/762.out
+++ b/tests/xfs/762.out
@@ -2,4 +2,5 @@ QA output created by 762
 Format and populate
 Find bmbt block
 Fuzz bmbt
+rightsib = lastbit: online re-scrub failed (5).
 Done fuzzing bmbt
diff --git a/tests/xfs/763.out b/tests/xfs/763.out
index 00fe93dbd5..017ebae31e 100644
--- a/tests/xfs/763.out
+++ b/tests/xfs/763.out
@@ -2,4 +2,12 @@ QA output created by 763
 Format and populate
 Find symlink remote block
 Fuzz symlink remote block
+data = ones: offline scrub didn't fail.
+data = ones: online scrub didn't fail.
+data = firstbit: offline scrub didn't fail.
+data = firstbit: online scrub didn't fail.
+data = middlebit: offline scrub didn't fail.
+data = middlebit: online scrub didn't fail.
+data = lastbit: offline scrub didn't fail.
+data = lastbit: online scrub didn't fail.
 Done fuzzing symlink remote block
diff --git a/tests/xfs/764.out b/tests/xfs/764.out
index 727f797f77..9515240556 100644
--- a/tests/xfs/764.out
+++ b/tests/xfs/764.out
@@ -2,4 +2,96 @@ QA output created by 764
 Format and populate
 Find inline-format dir inode
 Fuzz inline-format dir inode
+core.mode = firstbit: online repair failed (1).
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.nlinkv2 = zeroes: online repair failed (4).
+core.forkoff = firstbit: online repair failed (1).
+core.rtinherit = ones: offline scrub didn't fail.
+core.rtinherit = ones: online scrub didn't fail.
+core.rtinherit = firstbit: offline scrub didn't fail.
+core.rtinherit = firstbit: online scrub didn't fail.
+core.rtinherit = middlebit: offline scrub didn't fail.
+core.rtinherit = middlebit: online scrub didn't fail.
+core.rtinherit = lastbit: offline scrub didn't fail.
+core.rtinherit = lastbit: online scrub didn't fail.
+core.rtinherit = add: offline scrub didn't fail.
+core.rtinherit = add: online scrub didn't fail.
+core.rtinherit = sub: offline scrub didn't fail.
+core.rtinherit = sub: online scrub didn't fail.
+core.projinherit = ones: offline scrub didn't fail.
+core.projinherit = ones: online scrub didn't fail.
+core.projinherit = firstbit: offline scrub didn't fail.
+core.projinherit = firstbit: online scrub didn't fail.
+core.projinherit = middlebit: offline scrub didn't fail.
+core.projinherit = middlebit: online scrub didn't fail.
+core.projinherit = lastbit: offline scrub didn't fail.
+core.projinherit = lastbit: online scrub didn't fail.
+core.projinherit = add: offline scrub didn't fail.
+core.projinherit = add: online scrub didn't fail.
+core.projinherit = sub: offline scrub didn't fail.
+core.projinherit = sub: online scrub didn't fail.
+core.nosymlinks = ones: offline scrub didn't fail.
+core.nosymlinks = ones: online scrub didn't fail.
+core.nosymlinks = firstbit: offline scrub didn't fail.
+core.nosymlinks = firstbit: online scrub didn't fail.
+core.nosymlinks = middlebit: offline scrub didn't fail.
+core.nosymlinks = middlebit: online scrub didn't fail.
+core.nosymlinks = lastbit: offline scrub didn't fail.
+core.nosymlinks = lastbit: online scrub didn't fail.
+core.nosymlinks = add: offline scrub didn't fail.
+core.nosymlinks = add: online scrub didn't fail.
+core.nosymlinks = sub: offline scrub didn't fail.
+core.nosymlinks = sub: online scrub didn't fail.
+next_unlinked = add: online scrub didn't fail.
+next_unlinked = add: offline re-scrub failed (1).
+next_unlinked = add: offline post-mod scrub failed (1).
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = ones: offline re-scrub failed (1).
+v3.flags2 = ones: offline post-mod scrub failed (1).
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.flags2 = middlebit: offline re-scrub failed (1).
+v3.flags2 = middlebit: offline post-mod scrub failed (1).
+v3.flags2 = lastbit: offline scrub didn't fail.
+v3.flags2 = lastbit: online scrub didn't fail.
+v3.flags2 = add: online scrub didn't fail.
+v3.flags2 = add: offline re-scrub failed (1).
+v3.flags2 = add: offline post-mod scrub failed (1).
+v3.flags2 = sub: offline re-scrub failed (1).
+v3.flags2 = sub: offline post-mod scrub failed (1).
+v3.nrext64 = zeroes: offline scrub didn't fail.
+v3.nrext64 = zeroes: online scrub didn't fail.
+v3.nrext64 = firstbit: offline scrub didn't fail.
+v3.nrext64 = firstbit: online scrub didn't fail.
+v3.nrext64 = middlebit: offline scrub didn't fail.
+v3.nrext64 = middlebit: online scrub didn't fail.
+v3.nrext64 = lastbit: offline scrub didn't fail.
+v3.nrext64 = lastbit: online scrub didn't fail.
+v3.nrext64 = add: offline scrub didn't fail.
+v3.nrext64 = add: online scrub didn't fail.
+v3.nrext64 = sub: offline scrub didn't fail.
+v3.nrext64 = sub: online scrub didn't fail.
+u3.sfdir3.list[1].offset = middlebit: offline scrub didn't fail.
+u3.sfdir3.list[1].offset = middlebit: online scrub didn't fail.
+u3.sfdir3.list[1].offset = lastbit: offline scrub didn't fail.
+u3.sfdir3.list[1].offset = lastbit: online scrub didn't fail.
+u3.sfdir3.list[1].offset = add: offline scrub didn't fail.
+u3.sfdir3.list[1].offset = add: online scrub didn't fail.
 Done fuzzing inline-format dir inode
diff --git a/tests/xfs/765.out b/tests/xfs/765.out
index 008c22e4c6..e147cdd7e9 100644
--- a/tests/xfs/765.out
+++ b/tests/xfs/765.out
@@ -2,4 +2,11 @@ QA output created by 765
 Format and populate
 Find data-format dir block
 Fuzz data-format dir block
+bhdr.hdr.crc = zeroes: offline scrub didn't fail.
+bhdr.hdr.crc = ones: offline scrub didn't fail.
+bhdr.hdr.crc = firstbit: offline scrub didn't fail.
+bhdr.hdr.crc = middlebit: offline scrub didn't fail.
+bhdr.hdr.crc = lastbit: offline scrub didn't fail.
+bhdr.hdr.crc = add: offline scrub didn't fail.
+bhdr.hdr.crc = sub: offline scrub didn't fail.
 Done fuzzing data-format dir block
diff --git a/tests/xfs/766.out b/tests/xfs/766.out
index 29b8e227a3..15bce8f504 100644
--- a/tests/xfs/766.out
+++ b/tests/xfs/766.out
@@ -2,4 +2,15 @@ QA output created by 766
 Format and populate
 Find data-format dir block
 Fuzz data-format dir block
+dhdr.hdr.crc = zeroes: offline scrub didn't fail.
+dhdr.hdr.crc = ones: offline scrub didn't fail.
+dhdr.hdr.crc = firstbit: offline scrub didn't fail.
+dhdr.hdr.crc = middlebit: offline scrub didn't fail.
+dhdr.hdr.crc = lastbit: offline scrub didn't fail.
+dhdr.hdr.crc = add: offline scrub didn't fail.
+dhdr.hdr.crc = sub: offline scrub didn't fail.
+du[4].name = lastbit: offline re-scrub failed (1).
+du[4].name = lastbit: online re-scrub failed (5).
+du[4].name = lastbit: online post-mod scrub failed (1).
+du[4].name = lastbit: offline post-mod scrub failed (1).
 Done fuzzing data-format dir block
diff --git a/tests/xfs/768.out b/tests/xfs/768.out
index b45ce63b40..e7e87f724a 100644
--- a/tests/xfs/768.out
+++ b/tests/xfs/768.out
@@ -2,4 +2,11 @@ QA output created by 768
 Format and populate
 Find leafn-format dir block
 Fuzz leafn-format dir block
+lhdr.info.crc = zeroes: offline scrub didn't fail.
+lhdr.info.crc = ones: offline scrub didn't fail.
+lhdr.info.crc = firstbit: offline scrub didn't fail.
+lhdr.info.crc = middlebit: offline scrub didn't fail.
+lhdr.info.crc = lastbit: offline scrub didn't fail.
+lhdr.info.crc = add: offline scrub didn't fail.
+lhdr.info.crc = sub: offline scrub didn't fail.
 Done fuzzing leafn-format dir block
diff --git a/tests/xfs/769.out b/tests/xfs/769.out
index dc42f6f1db..fb338c0e59 100644
--- a/tests/xfs/769.out
+++ b/tests/xfs/769.out
@@ -2,4 +2,10 @@ QA output created by 769
 Format and populate
 Find node-format dir block
 Fuzz node-format dir block
+nhdr.info.hdr.back = ones: offline scrub didn't fail.
+nhdr.info.hdr.back = firstbit: offline scrub didn't fail.
+nhdr.info.hdr.back = middlebit: offline scrub didn't fail.
+nhdr.info.hdr.back = lastbit: offline scrub didn't fail.
+nhdr.info.hdr.back = add: offline scrub didn't fail.
+nhdr.info.hdr.back = sub: offline scrub didn't fail.
 Done fuzzing node-format dir block
diff --git a/tests/xfs/771.out b/tests/xfs/771.out
index 526bb00ed6..c92ae0a42c 100644
--- a/tests/xfs/771.out
+++ b/tests/xfs/771.out
@@ -2,4 +2,95 @@ QA output created by 771
 Format and populate
 Find inline-format attr inode
 Fuzz inline-format attr inode
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.nlinkv2 = zeroes: online repair failed (4).
+core.nlinkv2 = lastbit: online repair failed (4).
+core.size = middlebit: offline scrub didn't fail.
+core.size = middlebit: online scrub didn't fail.
+core.size = lastbit: offline scrub didn't fail.
+core.size = lastbit: online scrub didn't fail.
+core.size = add: offline scrub didn't fail.
+core.size = add: online scrub didn't fail.
+next_unlinked = add: online scrub didn't fail.
+next_unlinked = add: offline re-scrub failed (1).
+next_unlinked = add: offline post-mod scrub failed (1).
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = ones: offline re-scrub failed (1).
+v3.flags2 = ones: offline post-mod scrub failed (1).
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.flags2 = middlebit: offline re-scrub failed (1).
+v3.flags2 = middlebit: offline post-mod scrub failed (1).
+v3.flags2 = lastbit: offline scrub didn't fail.
+v3.flags2 = lastbit: online scrub didn't fail.
+v3.flags2 = add: online scrub didn't fail.
+v3.flags2 = add: offline re-scrub failed (1).
+v3.flags2 = add: offline post-mod scrub failed (1).
+v3.flags2 = sub: offline re-scrub failed (1).
+v3.flags2 = sub: offline post-mod scrub failed (1).
+v3.reflink = ones: offline scrub didn't fail.
+v3.reflink = ones: online scrub didn't fail.
+v3.reflink = firstbit: offline scrub didn't fail.
+v3.reflink = firstbit: online scrub didn't fail.
+v3.reflink = middlebit: offline scrub didn't fail.
+v3.reflink = middlebit: online scrub didn't fail.
+v3.reflink = lastbit: offline scrub didn't fail.
+v3.reflink = lastbit: online scrub didn't fail.
+v3.reflink = add: offline scrub didn't fail.
+v3.reflink = add: online scrub didn't fail.
+v3.reflink = sub: offline scrub didn't fail.
+v3.reflink = sub: online scrub didn't fail.
+v3.nrext64 = zeroes: offline scrub didn't fail.
+v3.nrext64 = zeroes: online scrub didn't fail.
+v3.nrext64 = firstbit: offline scrub didn't fail.
+v3.nrext64 = firstbit: online scrub didn't fail.
+v3.nrext64 = middlebit: offline scrub didn't fail.
+v3.nrext64 = middlebit: online scrub didn't fail.
+v3.nrext64 = lastbit: offline scrub didn't fail.
+v3.nrext64 = lastbit: online scrub didn't fail.
+v3.nrext64 = add: offline scrub didn't fail.
+v3.nrext64 = add: online scrub didn't fail.
+v3.nrext64 = sub: offline scrub didn't fail.
+v3.nrext64 = sub: online scrub didn't fail.
+a.sfattr.list[1].name = ones: offline scrub didn't fail.
+a.sfattr.list[1].name = ones: online scrub didn't fail.
+a.sfattr.list[1].name = firstbit: offline scrub didn't fail.
+a.sfattr.list[1].name = firstbit: online scrub didn't fail.
+a.sfattr.list[1].name = middlebit: offline scrub didn't fail.
+a.sfattr.list[1].name = middlebit: online scrub didn't fail.
+a.sfattr.list[1].name = lastbit: offline scrub didn't fail.
+a.sfattr.list[1].name = lastbit: online scrub didn't fail.
+a.sfattr.list[1].name = add: offline scrub didn't fail.
+a.sfattr.list[1].name = add: online scrub didn't fail.
+a.sfattr.list[1].name = sub: offline scrub didn't fail.
+a.sfattr.list[1].name = sub: online scrub didn't fail.
+a.sfattr.list[2].name = ones: offline scrub didn't fail.
+a.sfattr.list[2].name = ones: online scrub didn't fail.
+a.sfattr.list[2].name = firstbit: offline scrub didn't fail.
+a.sfattr.list[2].name = firstbit: online scrub didn't fail.
+a.sfattr.list[2].name = middlebit: offline scrub didn't fail.
+a.sfattr.list[2].name = middlebit: online scrub didn't fail.
+a.sfattr.list[2].name = lastbit: offline scrub didn't fail.
+a.sfattr.list[2].name = lastbit: online scrub didn't fail.
+a.sfattr.list[2].name = add: offline scrub didn't fail.
+a.sfattr.list[2].name = add: online scrub didn't fail.
+a.sfattr.list[2].name = sub: offline scrub didn't fail.
+a.sfattr.list[2].name = sub: online scrub didn't fail.
 Done fuzzing inline-format attr inode
diff --git a/tests/xfs/772.out b/tests/xfs/772.out
index c774116ea3..ffa4023ae6 100644
--- a/tests/xfs/772.out
+++ b/tests/xfs/772.out
@@ -2,4 +2,97 @@ QA output created by 772
 Format and populate
 Find leaf-format attr block
 Fuzz leaf-format attr block
+hdr.info.crc = zeroes: offline scrub didn't fail.
+hdr.info.crc = ones: offline scrub didn't fail.
+hdr.info.crc = firstbit: offline scrub didn't fail.
+hdr.info.crc = middlebit: offline scrub didn't fail.
+hdr.info.crc = lastbit: offline scrub didn't fail.
+hdr.info.crc = add: offline scrub didn't fail.
+hdr.info.crc = sub: offline scrub didn't fail.
+hdr.firstused = middlebit: online scrub didn't fail.
+hdr.firstused = middlebit: offline re-scrub failed (1).
+hdr.firstused = middlebit: offline post-mod scrub failed (1).
+hdr.holes = ones: offline scrub didn't fail.
+hdr.holes = ones: online scrub didn't fail.
+hdr.holes = firstbit: offline scrub didn't fail.
+hdr.holes = firstbit: online scrub didn't fail.
+hdr.holes = middlebit: offline scrub didn't fail.
+hdr.holes = middlebit: online scrub didn't fail.
+hdr.holes = lastbit: offline scrub didn't fail.
+hdr.holes = lastbit: online scrub didn't fail.
+hdr.holes = add: offline scrub didn't fail.
+hdr.holes = add: online scrub didn't fail.
+hdr.holes = sub: offline scrub didn't fail.
+hdr.holes = sub: online scrub didn't fail.
+hdr.freemap[0].base = zeroes: offline scrub didn't fail.
+hdr.freemap[0].base = middlebit: offline scrub didn't fail.
+hdr.freemap[0].size = zeroes: offline scrub didn't fail.
+hdr.freemap[0].size = zeroes: online scrub didn't fail.
+hdr.freemap[0].size = middlebit: offline scrub didn't fail.
+hdr.freemap[1].base = middlebit: offline scrub didn't fail.
+hdr.freemap[1].base = middlebit: online scrub didn't fail.
+hdr.freemap[1].size = middlebit: offline scrub didn't fail.
+hdr.freemap[2].base = middlebit: offline scrub didn't fail.
+hdr.freemap[2].base = middlebit: online scrub didn't fail.
+hdr.freemap[2].size = middlebit: offline scrub didn't fail.
+entries[0].incomplete = ones: online scrub didn't fail.
+entries[0].incomplete = firstbit: online scrub didn't fail.
+entries[0].incomplete = middlebit: online scrub didn't fail.
+entries[0].incomplete = lastbit: online scrub didn't fail.
+entries[0].incomplete = add: online scrub didn't fail.
+entries[0].incomplete = sub: online scrub didn't fail.
+entries[1].incomplete = ones: online scrub didn't fail.
+entries[1].incomplete = firstbit: online scrub didn't fail.
+entries[1].incomplete = middlebit: online scrub didn't fail.
+entries[1].incomplete = lastbit: online scrub didn't fail.
+entries[1].incomplete = add: online scrub didn't fail.
+entries[1].incomplete = sub: online scrub didn't fail.
+entries[2].incomplete = ones: online scrub didn't fail.
+entries[2].incomplete = firstbit: online scrub didn't fail.
+entries[2].incomplete = middlebit: online scrub didn't fail.
+entries[2].incomplete = lastbit: online scrub didn't fail.
+entries[2].incomplete = add: online scrub didn't fail.
+entries[2].incomplete = sub: online scrub didn't fail.
+entries[3].incomplete = ones: online scrub didn't fail.
+entries[3].incomplete = firstbit: online scrub didn't fail.
+entries[3].incomplete = middlebit: online scrub didn't fail.
+entries[3].incomplete = lastbit: online scrub didn't fail.
+entries[3].incomplete = add: online scrub didn't fail.
+entries[3].incomplete = sub: online scrub didn't fail.
+entries[4].incomplete = ones: online scrub didn't fail.
+entries[4].incomplete = firstbit: online scrub didn't fail.
+entries[4].incomplete = middlebit: online scrub didn't fail.
+entries[4].incomplete = lastbit: online scrub didn't fail.
+entries[4].incomplete = add: online scrub didn't fail.
+entries[4].incomplete = sub: online scrub didn't fail.
+entries[5].incomplete = ones: online scrub didn't fail.
+entries[5].incomplete = firstbit: online scrub didn't fail.
+entries[5].incomplete = middlebit: online scrub didn't fail.
+entries[5].incomplete = lastbit: online scrub didn't fail.
+entries[5].incomplete = add: online scrub didn't fail.
+entries[5].incomplete = sub: online scrub didn't fail.
+entries[6].incomplete = ones: online scrub didn't fail.
+entries[6].incomplete = firstbit: online scrub didn't fail.
+entries[6].incomplete = middlebit: online scrub didn't fail.
+entries[6].incomplete = lastbit: online scrub didn't fail.
+entries[6].incomplete = add: online scrub didn't fail.
+entries[6].incomplete = sub: online scrub didn't fail.
+entries[7].incomplete = ones: online scrub didn't fail.
+entries[7].incomplete = firstbit: online scrub didn't fail.
+entries[7].incomplete = middlebit: online scrub didn't fail.
+entries[7].incomplete = lastbit: online scrub didn't fail.
+entries[7].incomplete = add: online scrub didn't fail.
+entries[7].incomplete = sub: online scrub didn't fail.
+entries[8].incomplete = ones: online scrub didn't fail.
+entries[8].incomplete = firstbit: online scrub didn't fail.
+entries[8].incomplete = middlebit: online scrub didn't fail.
+entries[8].incomplete = lastbit: online scrub didn't fail.
+entries[8].incomplete = add: online scrub didn't fail.
+entries[8].incomplete = sub: online scrub didn't fail.
+entries[9].incomplete = ones: online scrub didn't fail.
+entries[9].incomplete = firstbit: online scrub didn't fail.
+entries[9].incomplete = middlebit: online scrub didn't fail.
+entries[9].incomplete = lastbit: online scrub didn't fail.
+entries[9].incomplete = add: online scrub didn't fail.
+entries[9].incomplete = sub: online scrub didn't fail.
 Done fuzzing leaf-format attr block
diff --git a/tests/xfs/773.out b/tests/xfs/773.out
index d301cda524..2439706f7d 100644
--- a/tests/xfs/773.out
+++ b/tests/xfs/773.out
@@ -2,4 +2,11 @@ QA output created by 773
 Format and populate
 Find node-format attr block
 Fuzz node-format attr block
+hdr.info.crc = zeroes: offline scrub didn't fail.
+hdr.info.crc = ones: offline scrub didn't fail.
+hdr.info.crc = firstbit: offline scrub didn't fail.
+hdr.info.crc = middlebit: offline scrub didn't fail.
+hdr.info.crc = lastbit: offline scrub didn't fail.
+hdr.info.crc = add: offline scrub didn't fail.
+hdr.info.crc = sub: offline scrub didn't fail.
 Done fuzzing node-format attr block
diff --git a/tests/xfs/774.out b/tests/xfs/774.out
index 58b3ea004c..8d99820951 100644
--- a/tests/xfs/774.out
+++ b/tests/xfs/774.out
@@ -2,4 +2,28 @@ QA output created by 774
 Format and populate
 Find external attr block
 Fuzz external attr block
+hdr.offset = ones: offline scrub didn't fail.
+hdr.offset = middlebit: offline scrub didn't fail.
+hdr.offset = lastbit: offline scrub didn't fail.
+hdr.offset = add: offline scrub didn't fail.
+hdr.offset = sub: offline scrub didn't fail.
+hdr.bytes = zeroes: offline scrub didn't fail.
+hdr.bytes = lastbit: offline scrub didn't fail.
+hdr.bytes = sub: offline scrub didn't fail.
+hdr.owner = ones: offline scrub didn't fail.
+hdr.owner = firstbit: offline scrub didn't fail.
+hdr.owner = middlebit: offline scrub didn't fail.
+hdr.owner = lastbit: offline scrub didn't fail.
+hdr.owner = add: offline scrub didn't fail.
+hdr.owner = sub: offline scrub didn't fail.
+data = zeroes: offline scrub didn't fail.
+data = zeroes: online scrub didn't fail.
+data = ones: offline scrub didn't fail.
+data = ones: online scrub didn't fail.
+data = firstbit: offline scrub didn't fail.
+data = firstbit: online scrub didn't fail.
+data = middlebit: offline scrub didn't fail.
+data = middlebit: online scrub didn't fail.
+data = lastbit: offline scrub didn't fail.
+data = lastbit: online scrub didn't fail.
 Done fuzzing external attr block
diff --git a/tests/xfs/775.out b/tests/xfs/775.out
index 71eaf9c0ed..b842b6853d 100644
--- a/tests/xfs/775.out
+++ b/tests/xfs/775.out
@@ -1,4 +1,10 @@
 QA output created by 775
 Format and populate
 Fuzz refcountbt
+numrecs = lastbit: offline scrub didn't fail.
+leftsib = add: offline scrub didn't fail.
+rightsib = ones: offline scrub didn't fail.
+rightsib = middlebit: offline scrub didn't fail.
+rightsib = lastbit: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
 Done fuzzing refcountbt
diff --git a/tests/xfs/776.out b/tests/xfs/776.out
index 226fc02005..5d83a310a4 100644
--- a/tests/xfs/776.out
+++ b/tests/xfs/776.out
@@ -2,4 +2,63 @@ QA output created by 776
 Format and populate
 Find btree-format attr inode
 Fuzz inode
+core.mode = zeroes: offline re-scrub failed (1).
+core.mode = zeroes: offline post-mod scrub failed (1).
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.nlinkv2 = zeroes: online repair failed (4).
+core.nlinkv2 = lastbit: online repair failed (4).
+core.size = middlebit: offline scrub didn't fail.
+core.size = middlebit: online scrub didn't fail.
+core.size = lastbit: offline scrub didn't fail.
+core.size = lastbit: online scrub didn't fail.
+core.size = add: offline scrub didn't fail.
+core.size = add: online scrub didn't fail.
+next_unlinked = add: online scrub didn't fail.
+next_unlinked = add: offline re-scrub failed (1).
+next_unlinked = add: offline post-mod scrub failed (1).
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = ones: offline re-scrub failed (1).
+v3.flags2 = ones: offline post-mod scrub failed (1).
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.flags2 = middlebit: offline re-scrub failed (1).
+v3.flags2 = middlebit: offline post-mod scrub failed (1).
+v3.flags2 = lastbit: offline scrub didn't fail.
+v3.flags2 = lastbit: online scrub didn't fail.
+v3.flags2 = add: online scrub didn't fail.
+v3.flags2 = add: offline re-scrub failed (1).
+v3.flags2 = add: offline post-mod scrub failed (1).
+v3.flags2 = sub: offline re-scrub failed (1).
+v3.flags2 = sub: offline post-mod scrub failed (1).
+v3.reflink = ones: offline scrub didn't fail.
+v3.reflink = ones: online scrub didn't fail.
+v3.reflink = firstbit: offline scrub didn't fail.
+v3.reflink = firstbit: online scrub didn't fail.
+v3.reflink = middlebit: offline scrub didn't fail.
+v3.reflink = middlebit: online scrub didn't fail.
+v3.reflink = lastbit: offline scrub didn't fail.
+v3.reflink = lastbit: online scrub didn't fail.
+v3.reflink = add: offline scrub didn't fail.
+v3.reflink = add: online scrub didn't fail.
+v3.reflink = sub: offline scrub didn't fail.
+v3.reflink = sub: online scrub didn't fail.
+a.bmbt.ptrs[1] = firstbit: offline scrub didn't fail.
+a.bmbt.ptrs[1] = firstbit: online scrub didn't fail.
 Done fuzzing inode
diff --git a/tests/xfs/777.out b/tests/xfs/777.out
index daca70d863..f16d70ee45 100644
--- a/tests/xfs/777.out
+++ b/tests/xfs/777.out
@@ -2,4 +2,73 @@ QA output created by 777
 Format and populate
 Find blockdev inode
 Fuzz inode
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.nlinkv2 = zeroes: online repair failed (4).
+core.nlinkv2 = lastbit: online repair failed (4).
+core.size = middlebit: online scrub didn't fail.
+core.size = middlebit: offline re-scrub failed (1).
+core.size = middlebit: offline post-mod scrub failed (1).
+core.size = lastbit: online scrub didn't fail.
+core.size = lastbit: offline re-scrub failed (1).
+core.size = lastbit: offline post-mod scrub failed (1).
+core.size = add: online scrub didn't fail.
+core.size = add: offline re-scrub failed (1).
+core.size = add: offline post-mod scrub failed (1).
+next_unlinked = add: online scrub didn't fail.
+next_unlinked = add: offline re-scrub failed (1).
+next_unlinked = add: offline post-mod scrub failed (1).
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = ones: offline re-scrub failed (1).
+v3.flags2 = ones: offline post-mod scrub failed (1).
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.flags2 = middlebit: offline re-scrub failed (1).
+v3.flags2 = middlebit: offline post-mod scrub failed (1).
+v3.flags2 = add: offline re-scrub failed (1).
+v3.flags2 = add: offline post-mod scrub failed (1).
+v3.flags2 = sub: offline re-scrub failed (1).
+v3.flags2 = sub: offline post-mod scrub failed (1).
+v3.nrext64 = zeroes: offline scrub didn't fail.
+v3.nrext64 = zeroes: online scrub didn't fail.
+v3.nrext64 = firstbit: offline scrub didn't fail.
+v3.nrext64 = firstbit: online scrub didn't fail.
+v3.nrext64 = middlebit: offline scrub didn't fail.
+v3.nrext64 = middlebit: online scrub didn't fail.
+v3.nrext64 = lastbit: offline scrub didn't fail.
+v3.nrext64 = lastbit: online scrub didn't fail.
+v3.nrext64 = add: offline scrub didn't fail.
+v3.nrext64 = add: online scrub didn't fail.
+v3.nrext64 = sub: offline scrub didn't fail.
+v3.nrext64 = sub: online scrub didn't fail.
+u3.dev = zeroes: offline scrub didn't fail.
+u3.dev = zeroes: online scrub didn't fail.
+u3.dev = ones: offline scrub didn't fail.
+u3.dev = ones: online scrub didn't fail.
+u3.dev = firstbit: offline scrub didn't fail.
+u3.dev = firstbit: online scrub didn't fail.
+u3.dev = middlebit: offline scrub didn't fail.
+u3.dev = middlebit: online scrub didn't fail.
+u3.dev = lastbit: offline scrub didn't fail.
+u3.dev = lastbit: online scrub didn't fail.
+u3.dev = add: offline scrub didn't fail.
+u3.dev = add: online scrub didn't fail.
+u3.dev = sub: offline scrub didn't fail.
+u3.dev = sub: online scrub didn't fail.
 Done fuzzing inode
diff --git a/tests/xfs/778.out b/tests/xfs/778.out
index a729f111d1..2f490d642d 100644
--- a/tests/xfs/778.out
+++ b/tests/xfs/778.out
@@ -2,4 +2,64 @@ QA output created by 778
 Format and populate
 Find local-format symlink inode
 Fuzz inode
+core.mode = firstbit: online repair failed (1).
+core.mode = middlebit: offline scrub didn't fail.
+core.mode = middlebit: online scrub didn't fail.
+core.mode = lastbit: offline scrub didn't fail.
+core.mode = lastbit: online scrub didn't fail.
+core.mode = add: offline scrub didn't fail.
+core.mode = add: online scrub didn't fail.
+core.nlinkv2 = zeroes: online repair failed (4).
+core.nlinkv2 = lastbit: online repair failed (4).
+core.forkoff = firstbit: online repair failed (1).
+next_unlinked = add: online scrub didn't fail.
+next_unlinked = add: offline re-scrub failed (1).
+next_unlinked = add: offline post-mod scrub failed (1).
+v3.change_count = zeroes: offline scrub didn't fail.
+v3.change_count = zeroes: online scrub didn't fail.
+v3.change_count = ones: offline scrub didn't fail.
+v3.change_count = ones: online scrub didn't fail.
+v3.change_count = firstbit: offline scrub didn't fail.
+v3.change_count = firstbit: online scrub didn't fail.
+v3.change_count = middlebit: offline scrub didn't fail.
+v3.change_count = middlebit: online scrub didn't fail.
+v3.change_count = lastbit: offline scrub didn't fail.
+v3.change_count = lastbit: online scrub didn't fail.
+v3.change_count = add: offline scrub didn't fail.
+v3.change_count = add: online scrub didn't fail.
+v3.change_count = sub: offline scrub didn't fail.
+v3.change_count = sub: online scrub didn't fail.
+v3.flags2 = ones: offline re-scrub failed (1).
+v3.flags2 = ones: offline post-mod scrub failed (1).
+v3.flags2 = middlebit: online scrub didn't fail.
+v3.flags2 = middlebit: offline re-scrub failed (1).
+v3.flags2 = middlebit: offline post-mod scrub failed (1).
+v3.flags2 = add: offline re-scrub failed (1).
+v3.flags2 = add: offline post-mod scrub failed (1).
+v3.flags2 = sub: offline re-scrub failed (1).
+v3.flags2 = sub: offline post-mod scrub failed (1).
+v3.nrext64 = zeroes: offline scrub didn't fail.
+v3.nrext64 = zeroes: online scrub didn't fail.
+v3.nrext64 = firstbit: offline scrub didn't fail.
+v3.nrext64 = firstbit: online scrub didn't fail.
+v3.nrext64 = middlebit: offline scrub didn't fail.
+v3.nrext64 = middlebit: online scrub didn't fail.
+v3.nrext64 = lastbit: offline scrub didn't fail.
+v3.nrext64 = lastbit: online scrub didn't fail.
+v3.nrext64 = add: offline scrub didn't fail.
+v3.nrext64 = add: online scrub didn't fail.
+v3.nrext64 = sub: offline scrub didn't fail.
+v3.nrext64 = sub: online scrub didn't fail.
+u3.symlink = ones: offline scrub didn't fail.
+u3.symlink = ones: online scrub didn't fail.
+u3.symlink = firstbit: offline scrub didn't fail.
+u3.symlink = firstbit: online scrub didn't fail.
+u3.symlink = middlebit: offline scrub didn't fail.
+u3.symlink = middlebit: online scrub didn't fail.
+u3.symlink = lastbit: offline scrub didn't fail.
+u3.symlink = lastbit: online scrub didn't fail.
+u3.symlink = add: offline scrub didn't fail.
+u3.symlink = add: online scrub didn't fail.
+u3.symlink = sub: offline scrub didn't fail.
+u3.symlink = sub: online scrub didn't fail.
 Done fuzzing inode
diff --git a/tests/xfs/779.out b/tests/xfs/779.out
index a8c19a9a05..7d98ff2cc9 100644
--- a/tests/xfs/779.out
+++ b/tests/xfs/779.out
@@ -1,4 +1,300 @@
 QA output created by 779
 Format and populate
 Fuzz user 0 dquot
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = ones: online repair failed (1).
+diskdq.blk_softlimit = ones: online re-scrub failed (5).
+diskdq.blk_softlimit = ones: online post-mod scrub failed (1).
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: online repair failed (1).
+diskdq.blk_softlimit = firstbit: online re-scrub failed (5).
+diskdq.blk_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: online repair failed (1).
+diskdq.blk_softlimit = middlebit: online re-scrub failed (5).
+diskdq.blk_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: online repair failed (1).
+diskdq.blk_softlimit = lastbit: online re-scrub failed (5).
+diskdq.blk_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = add: online repair failed (1).
+diskdq.blk_softlimit = add: online re-scrub failed (5).
+diskdq.blk_softlimit = add: online post-mod scrub failed (1).
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: online repair failed (1).
+diskdq.blk_softlimit = sub: online re-scrub failed (5).
+diskdq.blk_softlimit = sub: online post-mod scrub failed (1).
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = ones: online repair failed (1).
+diskdq.ino_softlimit = ones: online re-scrub failed (5).
+diskdq.ino_softlimit = ones: online post-mod scrub failed (1).
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: online repair failed (1).
+diskdq.ino_softlimit = firstbit: online re-scrub failed (5).
+diskdq.ino_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: online repair failed (1).
+diskdq.ino_softlimit = middlebit: online re-scrub failed (5).
+diskdq.ino_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: online repair failed (1).
+diskdq.ino_softlimit = lastbit: online re-scrub failed (5).
+diskdq.ino_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = add: online repair failed (1).
+diskdq.ino_softlimit = add: online re-scrub failed (5).
+diskdq.ino_softlimit = add: online post-mod scrub failed (1).
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: online repair failed (1).
+diskdq.ino_softlimit = sub: online re-scrub failed (5).
+diskdq.ino_softlimit = sub: online post-mod scrub failed (1).
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = ones: online scrub didn't fail.
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = firstbit: online scrub didn't fail.
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = middlebit: online scrub didn't fail.
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = lastbit: online scrub didn't fail.
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = add: online scrub didn't fail.
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.itimer = sub: online scrub didn't fail.
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = ones: online scrub didn't fail.
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = firstbit: online scrub didn't fail.
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = middlebit: online scrub didn't fail.
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = lastbit: online scrub didn't fail.
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = add: online scrub didn't fail.
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.btimer = sub: online scrub didn't fail.
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = ones: online repair failed (1).
+diskdq.rtb_softlimit = ones: online re-scrub failed (5).
+diskdq.rtb_softlimit = ones: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: online repair failed (1).
+diskdq.rtb_softlimit = firstbit: online re-scrub failed (5).
+diskdq.rtb_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: online repair failed (1).
+diskdq.rtb_softlimit = middlebit: online re-scrub failed (5).
+diskdq.rtb_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: online repair failed (1).
+diskdq.rtb_softlimit = lastbit: online re-scrub failed (5).
+diskdq.rtb_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: online repair failed (1).
+diskdq.rtb_softlimit = add: online re-scrub failed (5).
+diskdq.rtb_softlimit = add: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: online repair failed (1).
+diskdq.rtb_softlimit = sub: online re-scrub failed (5).
+diskdq.rtb_softlimit = sub: online post-mod scrub failed (1).
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = ones: online scrub didn't fail.
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: online scrub didn't fail.
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: online scrub didn't fail.
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: online scrub didn't fail.
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = add: online scrub didn't fail.
+diskdq.rtbtimer = sub: offline scrub didn't fail.
+diskdq.rtbtimer = sub: online scrub didn't fail.
+Done fuzzing dquot
+Fuzz user 4242 dquot
+diskdq.type = firstbit: offline scrub didn't fail.
+diskdq.type = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = sub: offline scrub didn't fail.
+Done fuzzing dquot
+Fuzz user 8484 dquot
+diskdq.type = firstbit: offline scrub didn't fail.
+diskdq.type = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = sub: offline scrub didn't fail.
 Done fuzzing dquot
diff --git a/tests/xfs/780.out b/tests/xfs/780.out
index df5784d5a8..f3823cc932 100644
--- a/tests/xfs/780.out
+++ b/tests/xfs/780.out
@@ -1,4 +1,300 @@
 QA output created by 780
 Format and populate
 Fuzz group 0 dquot
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = ones: online repair failed (1).
+diskdq.blk_softlimit = ones: online re-scrub failed (5).
+diskdq.blk_softlimit = ones: online post-mod scrub failed (1).
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: online repair failed (1).
+diskdq.blk_softlimit = firstbit: online re-scrub failed (5).
+diskdq.blk_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: online repair failed (1).
+diskdq.blk_softlimit = middlebit: online re-scrub failed (5).
+diskdq.blk_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: online repair failed (1).
+diskdq.blk_softlimit = lastbit: online re-scrub failed (5).
+diskdq.blk_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = add: online repair failed (1).
+diskdq.blk_softlimit = add: online re-scrub failed (5).
+diskdq.blk_softlimit = add: online post-mod scrub failed (1).
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: online repair failed (1).
+diskdq.blk_softlimit = sub: online re-scrub failed (5).
+diskdq.blk_softlimit = sub: online post-mod scrub failed (1).
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = ones: online repair failed (1).
+diskdq.ino_softlimit = ones: online re-scrub failed (5).
+diskdq.ino_softlimit = ones: online post-mod scrub failed (1).
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: online repair failed (1).
+diskdq.ino_softlimit = firstbit: online re-scrub failed (5).
+diskdq.ino_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: online repair failed (1).
+diskdq.ino_softlimit = middlebit: online re-scrub failed (5).
+diskdq.ino_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: online repair failed (1).
+diskdq.ino_softlimit = lastbit: online re-scrub failed (5).
+diskdq.ino_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = add: online repair failed (1).
+diskdq.ino_softlimit = add: online re-scrub failed (5).
+diskdq.ino_softlimit = add: online post-mod scrub failed (1).
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: online repair failed (1).
+diskdq.ino_softlimit = sub: online re-scrub failed (5).
+diskdq.ino_softlimit = sub: online post-mod scrub failed (1).
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = ones: online scrub didn't fail.
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = firstbit: online scrub didn't fail.
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = middlebit: online scrub didn't fail.
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = lastbit: online scrub didn't fail.
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = add: online scrub didn't fail.
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.itimer = sub: online scrub didn't fail.
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = ones: online scrub didn't fail.
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = firstbit: online scrub didn't fail.
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = middlebit: online scrub didn't fail.
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = lastbit: online scrub didn't fail.
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = add: online scrub didn't fail.
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.btimer = sub: online scrub didn't fail.
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = ones: online repair failed (1).
+diskdq.rtb_softlimit = ones: online re-scrub failed (5).
+diskdq.rtb_softlimit = ones: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: online repair failed (1).
+diskdq.rtb_softlimit = firstbit: online re-scrub failed (5).
+diskdq.rtb_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: online repair failed (1).
+diskdq.rtb_softlimit = middlebit: online re-scrub failed (5).
+diskdq.rtb_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: online repair failed (1).
+diskdq.rtb_softlimit = lastbit: online re-scrub failed (5).
+diskdq.rtb_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: online repair failed (1).
+diskdq.rtb_softlimit = add: online re-scrub failed (5).
+diskdq.rtb_softlimit = add: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: online repair failed (1).
+diskdq.rtb_softlimit = sub: online re-scrub failed (5).
+diskdq.rtb_softlimit = sub: online post-mod scrub failed (1).
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = ones: online scrub didn't fail.
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: online scrub didn't fail.
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: online scrub didn't fail.
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: online scrub didn't fail.
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = add: online scrub didn't fail.
+diskdq.rtbtimer = sub: offline scrub didn't fail.
+diskdq.rtbtimer = sub: online scrub didn't fail.
+Done fuzzing dquot
+Fuzz group 4242 dquot
+diskdq.type = firstbit: offline scrub didn't fail.
+diskdq.type = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = sub: offline scrub didn't fail.
+Done fuzzing dquot
+Fuzz group 8484 dquot
+diskdq.type = firstbit: offline scrub didn't fail.
+diskdq.type = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = sub: offline scrub didn't fail.
 Done fuzzing dquot
diff --git a/tests/xfs/781.out b/tests/xfs/781.out
index 68c42e6fce..a7b6651b77 100644
--- a/tests/xfs/781.out
+++ b/tests/xfs/781.out
@@ -1,4 +1,300 @@
 QA output created by 781
 Format and populate
 Fuzz project 0 dquot
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = ones: online repair failed (1).
+diskdq.blk_softlimit = ones: online re-scrub failed (5).
+diskdq.blk_softlimit = ones: online post-mod scrub failed (1).
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: online repair failed (1).
+diskdq.blk_softlimit = firstbit: online re-scrub failed (5).
+diskdq.blk_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: online repair failed (1).
+diskdq.blk_softlimit = middlebit: online re-scrub failed (5).
+diskdq.blk_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: online repair failed (1).
+diskdq.blk_softlimit = lastbit: online re-scrub failed (5).
+diskdq.blk_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = add: online repair failed (1).
+diskdq.blk_softlimit = add: online re-scrub failed (5).
+diskdq.blk_softlimit = add: online post-mod scrub failed (1).
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: online repair failed (1).
+diskdq.blk_softlimit = sub: online re-scrub failed (5).
+diskdq.blk_softlimit = sub: online post-mod scrub failed (1).
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = ones: online repair failed (1).
+diskdq.ino_softlimit = ones: online re-scrub failed (5).
+diskdq.ino_softlimit = ones: online post-mod scrub failed (1).
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: online repair failed (1).
+diskdq.ino_softlimit = firstbit: online re-scrub failed (5).
+diskdq.ino_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: online repair failed (1).
+diskdq.ino_softlimit = middlebit: online re-scrub failed (5).
+diskdq.ino_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: online repair failed (1).
+diskdq.ino_softlimit = lastbit: online re-scrub failed (5).
+diskdq.ino_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = add: online repair failed (1).
+diskdq.ino_softlimit = add: online re-scrub failed (5).
+diskdq.ino_softlimit = add: online post-mod scrub failed (1).
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: online repair failed (1).
+diskdq.ino_softlimit = sub: online re-scrub failed (5).
+diskdq.ino_softlimit = sub: online post-mod scrub failed (1).
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = ones: online scrub didn't fail.
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = firstbit: online scrub didn't fail.
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = middlebit: online scrub didn't fail.
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = lastbit: online scrub didn't fail.
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = add: online scrub didn't fail.
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.itimer = sub: online scrub didn't fail.
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = ones: online scrub didn't fail.
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = firstbit: online scrub didn't fail.
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = middlebit: online scrub didn't fail.
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = lastbit: online scrub didn't fail.
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = add: online scrub didn't fail.
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.btimer = sub: online scrub didn't fail.
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = ones: online repair failed (1).
+diskdq.rtb_softlimit = ones: online re-scrub failed (5).
+diskdq.rtb_softlimit = ones: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: online repair failed (1).
+diskdq.rtb_softlimit = firstbit: online re-scrub failed (5).
+diskdq.rtb_softlimit = firstbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: online repair failed (1).
+diskdq.rtb_softlimit = middlebit: online re-scrub failed (5).
+diskdq.rtb_softlimit = middlebit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: online repair failed (1).
+diskdq.rtb_softlimit = lastbit: online re-scrub failed (5).
+diskdq.rtb_softlimit = lastbit: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: online repair failed (1).
+diskdq.rtb_softlimit = add: online re-scrub failed (5).
+diskdq.rtb_softlimit = add: online post-mod scrub failed (1).
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: online repair failed (1).
+diskdq.rtb_softlimit = sub: online re-scrub failed (5).
+diskdq.rtb_softlimit = sub: online post-mod scrub failed (1).
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = ones: online scrub didn't fail.
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: online scrub didn't fail.
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: online scrub didn't fail.
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: online scrub didn't fail.
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = add: online scrub didn't fail.
+diskdq.rtbtimer = sub: offline scrub didn't fail.
+diskdq.rtbtimer = sub: online scrub didn't fail.
+Done fuzzing dquot
+Fuzz project 4242 dquot
+diskdq.type = firstbit: offline scrub didn't fail.
+diskdq.type = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = sub: offline scrub didn't fail.
+Done fuzzing dquot
+Fuzz project 8484 dquot
+diskdq.type = firstbit: offline scrub didn't fail.
+diskdq.type = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = ones: offline scrub didn't fail.
+diskdq.blk_hardlimit = ones: online scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = firstbit: online scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_hardlimit = middlebit: online scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_hardlimit = lastbit: online scrub didn't fail.
+diskdq.blk_hardlimit = add: offline scrub didn't fail.
+diskdq.blk_hardlimit = add: online scrub didn't fail.
+diskdq.blk_hardlimit = sub: offline scrub didn't fail.
+diskdq.blk_hardlimit = sub: online scrub didn't fail.
+diskdq.blk_softlimit = ones: offline scrub didn't fail.
+diskdq.blk_softlimit = firstbit: offline scrub didn't fail.
+diskdq.blk_softlimit = middlebit: offline scrub didn't fail.
+diskdq.blk_softlimit = lastbit: offline scrub didn't fail.
+diskdq.blk_softlimit = add: offline scrub didn't fail.
+diskdq.blk_softlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: offline scrub didn't fail.
+diskdq.ino_hardlimit = ones: online scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = firstbit: online scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_hardlimit = middlebit: online scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_hardlimit = lastbit: online scrub didn't fail.
+diskdq.ino_hardlimit = add: offline scrub didn't fail.
+diskdq.ino_hardlimit = add: online scrub didn't fail.
+diskdq.ino_hardlimit = sub: offline scrub didn't fail.
+diskdq.ino_hardlimit = sub: online scrub didn't fail.
+diskdq.ino_softlimit = ones: offline scrub didn't fail.
+diskdq.ino_softlimit = firstbit: offline scrub didn't fail.
+diskdq.ino_softlimit = middlebit: offline scrub didn't fail.
+diskdq.ino_softlimit = lastbit: offline scrub didn't fail.
+diskdq.ino_softlimit = add: offline scrub didn't fail.
+diskdq.ino_softlimit = sub: offline scrub didn't fail.
+diskdq.itimer = ones: offline scrub didn't fail.
+diskdq.itimer = firstbit: offline scrub didn't fail.
+diskdq.itimer = middlebit: offline scrub didn't fail.
+diskdq.itimer = lastbit: offline scrub didn't fail.
+diskdq.itimer = add: offline scrub didn't fail.
+diskdq.itimer = sub: offline scrub didn't fail.
+diskdq.btimer = ones: offline scrub didn't fail.
+diskdq.btimer = firstbit: offline scrub didn't fail.
+diskdq.btimer = middlebit: offline scrub didn't fail.
+diskdq.btimer = lastbit: offline scrub didn't fail.
+diskdq.btimer = add: offline scrub didn't fail.
+diskdq.btimer = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: offline scrub didn't fail.
+diskdq.rtb_hardlimit = ones: online scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = firstbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = middlebit: online scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_hardlimit = lastbit: online scrub didn't fail.
+diskdq.rtb_hardlimit = add: offline scrub didn't fail.
+diskdq.rtb_hardlimit = add: online scrub didn't fail.
+diskdq.rtb_hardlimit = sub: offline scrub didn't fail.
+diskdq.rtb_hardlimit = sub: online scrub didn't fail.
+diskdq.rtb_softlimit = ones: offline scrub didn't fail.
+diskdq.rtb_softlimit = firstbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = middlebit: offline scrub didn't fail.
+diskdq.rtb_softlimit = lastbit: offline scrub didn't fail.
+diskdq.rtb_softlimit = add: offline scrub didn't fail.
+diskdq.rtb_softlimit = sub: offline scrub didn't fail.
+diskdq.rtbtimer = ones: offline scrub didn't fail.
+diskdq.rtbtimer = firstbit: offline scrub didn't fail.
+diskdq.rtbtimer = middlebit: offline scrub didn't fail.
+diskdq.rtbtimer = lastbit: offline scrub didn't fail.
+diskdq.rtbtimer = add: offline scrub didn't fail.
+diskdq.rtbtimer = sub: offline scrub didn't fail.
 Done fuzzing dquot
diff --git a/tests/xfs/782.out b/tests/xfs/782.out
index ec750a670b..9c98cf1cf6 100644
--- a/tests/xfs/782.out
+++ b/tests/xfs/782.out
@@ -2,4 +2,16 @@ QA output created by 782
 Format and populate
 Find single-leafn-format dir block
 Fuzz single-leafn-format dir block
+lhdr.info.hdr.forw = ones: offline scrub didn't fail.
+lhdr.info.hdr.forw = firstbit: offline scrub didn't fail.
+lhdr.info.hdr.forw = middlebit: offline scrub didn't fail.
+lhdr.info.hdr.forw = lastbit: offline scrub didn't fail.
+lhdr.info.hdr.forw = add: offline scrub didn't fail.
+lhdr.info.hdr.forw = sub: offline scrub didn't fail.
+lhdr.info.hdr.back = ones: offline scrub didn't fail.
+lhdr.info.hdr.back = firstbit: offline scrub didn't fail.
+lhdr.info.hdr.back = middlebit: offline scrub didn't fail.
+lhdr.info.hdr.back = lastbit: offline scrub didn't fail.
+lhdr.info.hdr.back = add: offline scrub didn't fail.
+lhdr.info.hdr.back = sub: offline scrub didn't fail.
 Done fuzzing single-leafn-format dir block
diff --git a/tests/xfs/783.out b/tests/xfs/783.out
index 11e6d93b88..41892794b4 100644
--- a/tests/xfs/783.out
+++ b/tests/xfs/783.out
@@ -1,10 +1,220 @@
 QA output created by 783
 Format and populate
 Fuzz block map for BLOCK
+u3.bmx[0].blockcount = middlebit: online repair failed (1).
+u3.bmx[0].blockcount = middlebit: offline re-scrub failed (1).
+u3.bmx[0].blockcount = middlebit: offline post-mod scrub failed (1).
+u3.bmx[0].blockcount = add: online repair failed (1).
+u3.bmx[0].blockcount = add: offline re-scrub failed (1).
+u3.bmx[0].blockcount = add: offline post-mod scrub failed (1).
 Done fuzzing dir map BLOCK
 Fuzz block map for LEAF
+u3.bmx[0].startblock = zeroes: offline re-scrub failed (1).
+u3.bmx[0].startblock = zeroes: offline post-mod scrub failed (1).
+u3.bmx[0].startblock = ones: offline re-scrub failed (1).
+u3.bmx[0].startblock = ones: offline post-mod scrub failed (1).
+u3.bmx[0].startblock = firstbit: offline re-scrub failed (1).
+u3.bmx[0].startblock = firstbit: offline post-mod scrub failed (1).
+u3.bmx[0].startblock = middlebit: offline re-scrub failed (1).
+u3.bmx[0].startblock = middlebit: offline post-mod scrub failed (1).
+u3.bmx[0].startblock = sub: offline re-scrub failed (1).
+u3.bmx[0].startblock = sub: offline post-mod scrub failed (1).
+u3.bmx[0].blockcount = zeroes: offline re-scrub failed (1).
+u3.bmx[0].blockcount = zeroes: offline post-mod scrub failed (1).
+u3.bmx[0].blockcount = ones: offline re-scrub failed (1).
+u3.bmx[0].blockcount = ones: offline post-mod scrub failed (1).
+u3.bmx[0].blockcount = firstbit: offline re-scrub failed (1).
+u3.bmx[0].blockcount = firstbit: offline post-mod scrub failed (1).
+u3.bmx[0].blockcount = lastbit: offline re-scrub failed (1).
+u3.bmx[0].blockcount = lastbit: offline post-mod scrub failed (1).
+u3.bmx[0].blockcount = sub: offline re-scrub failed (1).
+u3.bmx[0].blockcount = sub: offline post-mod scrub failed (1).
+u3.bmx[1].startoff = zeroes: offline re-scrub failed (1).
+u3.bmx[1].startoff = zeroes: offline post-mod scrub failed (1).
+u3.bmx[1].startoff = ones: offline re-scrub failed (1).
+u3.bmx[1].startoff = ones: offline post-mod scrub failed (1).
+u3.bmx[1].startoff = firstbit: offline re-scrub failed (1).
+u3.bmx[1].startoff = firstbit: offline post-mod scrub failed (1).
+u3.bmx[1].startoff = middlebit: offline re-scrub failed (1).
+u3.bmx[1].startoff = middlebit: offline post-mod scrub failed (1).
+u3.bmx[1].startoff = lastbit: offline re-scrub failed (1).
+u3.bmx[1].startoff = lastbit: offline post-mod scrub failed (1).
+u3.bmx[1].startoff = add: offline re-scrub failed (1).
+u3.bmx[1].startoff = add: offline post-mod scrub failed (1).
+u3.bmx[1].startoff = sub: offline re-scrub failed (1).
+u3.bmx[1].startoff = sub: offline post-mod scrub failed (1).
+u3.bmx[1].startblock = zeroes: offline re-scrub failed (1).
+u3.bmx[1].startblock = zeroes: offline post-mod scrub failed (1).
+u3.bmx[1].startblock = ones: offline re-scrub failed (1).
+u3.bmx[1].startblock = ones: offline post-mod scrub failed (1).
+u3.bmx[1].startblock = firstbit: offline re-scrub failed (1).
+u3.bmx[1].startblock = firstbit: offline post-mod scrub failed (1).
+u3.bmx[1].startblock = middlebit: offline re-scrub failed (1).
+u3.bmx[1].startblock = middlebit: offline post-mod scrub failed (1).
+u3.bmx[1].startblock = sub: offline re-scrub failed (1).
+u3.bmx[1].startblock = sub: offline post-mod scrub failed (1).
+u3.bmx[1].blockcount = zeroes: offline re-scrub failed (1).
+u3.bmx[1].blockcount = zeroes: offline post-mod scrub failed (1).
+u3.bmx[1].blockcount = ones: offline re-scrub failed (1).
+u3.bmx[1].blockcount = ones: offline post-mod scrub failed (1).
+u3.bmx[1].blockcount = firstbit: offline re-scrub failed (1).
+u3.bmx[1].blockcount = firstbit: offline post-mod scrub failed (1).
+u3.bmx[1].blockcount = lastbit: offline re-scrub failed (1).
+u3.bmx[1].blockcount = lastbit: offline post-mod scrub failed (1).
+u3.bmx[1].blockcount = sub: offline re-scrub failed (1).
+u3.bmx[1].blockcount = sub: offline post-mod scrub failed (1).
+u3.bmx[2].startoff = zeroes: offline re-scrub failed (1).
+u3.bmx[2].startoff = zeroes: offline post-mod scrub failed (1).
+u3.bmx[2].startoff = ones: offline re-scrub failed (1).
+u3.bmx[2].startoff = ones: offline post-mod scrub failed (1).
+u3.bmx[2].startoff = firstbit: offline re-scrub failed (1).
+u3.bmx[2].startoff = firstbit: offline post-mod scrub failed (1).
+u3.bmx[2].startoff = middlebit: offline re-scrub failed (1).
+u3.bmx[2].startoff = middlebit: offline post-mod scrub failed (1).
+u3.bmx[2].startoff = sub: offline re-scrub failed (1).
+u3.bmx[2].startoff = sub: offline post-mod scrub failed (1).
+u3.bmx[2].startblock = zeroes: offline re-scrub failed (1).
+u3.bmx[2].startblock = zeroes: offline post-mod scrub failed (1).
+u3.bmx[2].startblock = ones: offline re-scrub failed (1).
+u3.bmx[2].startblock = ones: offline post-mod scrub failed (1).
+u3.bmx[2].startblock = firstbit: offline re-scrub failed (1).
+u3.bmx[2].startblock = firstbit: offline post-mod scrub failed (1).
+u3.bmx[2].startblock = middlebit: offline re-scrub failed (1).
+u3.bmx[2].startblock = middlebit: offline post-mod scrub failed (1).
+u3.bmx[2].startblock = sub: offline re-scrub failed (1).
+u3.bmx[2].startblock = sub: offline post-mod scrub failed (1).
+u3.bmx[2].blockcount = zeroes: offline re-scrub failed (1).
+u3.bmx[2].blockcount = zeroes: offline post-mod scrub failed (1).
+u3.bmx[2].blockcount = ones: offline re-scrub failed (1).
+u3.bmx[2].blockcount = ones: offline post-mod scrub failed (1).
+u3.bmx[2].blockcount = firstbit: offline re-scrub failed (1).
+u3.bmx[2].blockcount = firstbit: offline post-mod scrub failed (1).
+u3.bmx[2].blockcount = middlebit: online repair failed (1).
+u3.bmx[2].blockcount = middlebit: online re-scrub failed (5).
+u3.bmx[2].blockcount = middlebit: online post-mod scrub failed (1).
+u3.bmx[2].blockcount = lastbit: offline re-scrub failed (1).
+u3.bmx[2].blockcount = lastbit: offline post-mod scrub failed (1).
+u3.bmx[2].blockcount = add: online repair failed (1).
+u3.bmx[2].blockcount = add: online re-scrub failed (5).
+u3.bmx[2].blockcount = add: online post-mod scrub failed (1).
+u3.bmx[2].blockcount = sub: offline re-scrub failed (1).
+u3.bmx[2].blockcount = sub: offline post-mod scrub failed (1).
+u3.bmx[3].startblock = zeroes: offline re-scrub failed (1).
+u3.bmx[3].startblock = zeroes: offline post-mod scrub failed (1).
+u3.bmx[3].startblock = ones: offline re-scrub failed (1).
+u3.bmx[3].startblock = ones: offline post-mod scrub failed (1).
+u3.bmx[3].startblock = firstbit: offline re-scrub failed (1).
+u3.bmx[3].startblock = firstbit: offline post-mod scrub failed (1).
+u3.bmx[3].startblock = middlebit: offline re-scrub failed (1).
+u3.bmx[3].startblock = middlebit: offline post-mod scrub failed (1).
+u3.bmx[3].startblock = sub: offline re-scrub failed (1).
+u3.bmx[3].startblock = sub: offline post-mod scrub failed (1).
+u3.bmx[3].blockcount = zeroes: offline re-scrub failed (1).
+u3.bmx[3].blockcount = zeroes: offline post-mod scrub failed (1).
+u3.bmx[3].blockcount = ones: offline re-scrub failed (1).
+u3.bmx[3].blockcount = ones: offline post-mod scrub failed (1).
+u3.bmx[3].blockcount = firstbit: offline re-scrub failed (1).
+u3.bmx[3].blockcount = firstbit: offline post-mod scrub failed (1).
+u3.bmx[3].blockcount = lastbit: offline re-scrub failed (1).
+u3.bmx[3].blockcount = lastbit: offline post-mod scrub failed (1).
+u3.bmx[3].blockcount = sub: offline re-scrub failed (1).
+u3.bmx[3].blockcount = sub: offline post-mod scrub failed (1).
 Done fuzzing dir map LEAF
 Fuzz block map for LEAFN
+u3.bmx[1].startoff = lastbit: offline re-scrub failed (1).
+u3.bmx[1].startoff = lastbit: offline post-mod scrub failed (1).
 Done fuzzing dir map LEAFN
 Fuzz block map for NODE
+u3.bmx[1].startoff = zeroes: offline re-scrub failed (1).
+u3.bmx[1].startoff = zeroes: offline post-mod scrub failed (1).
+u3.bmx[1].startoff = ones: offline re-scrub failed (1).
+u3.bmx[1].startoff = ones: offline post-mod scrub failed (1).
+u3.bmx[1].startoff = firstbit: offline re-scrub failed (1).
+u3.bmx[1].startoff = firstbit: offline post-mod scrub failed (1).
+u3.bmx[1].startoff = middlebit: offline re-scrub failed (1).
+u3.bmx[1].startoff = middlebit: offline post-mod scrub failed (1).
+u3.bmx[1].startoff = lastbit: offline re-scrub failed (1).
+u3.bmx[1].startoff = lastbit: offline post-mod scrub failed (1).
+u3.bmx[1].startoff = add: offline re-scrub failed (1).
+u3.bmx[1].startoff = add: offline post-mod scrub failed (1).
+u3.bmx[1].startoff = sub: offline re-scrub failed (1).
+u3.bmx[1].startoff = sub: offline post-mod scrub failed (1).
+u3.bmx[1].blockcount = ones: offline re-scrub failed (1).
+u3.bmx[1].blockcount = ones: offline post-mod scrub failed (1).
+u3.bmx[2].startoff = zeroes: offline re-scrub failed (1).
+u3.bmx[2].startoff = zeroes: offline post-mod scrub failed (1).
+u3.bmx[2].startoff = ones: offline re-scrub failed (1).
+u3.bmx[2].startoff = ones: offline post-mod scrub failed (1).
+u3.bmx[2].startoff = firstbit: offline re-scrub failed (1).
+u3.bmx[2].startoff = firstbit: offline post-mod scrub failed (1).
+u3.bmx[2].startoff = middlebit: offline re-scrub failed (1).
+u3.bmx[2].startoff = middlebit: offline post-mod scrub failed (1).
+u3.bmx[2].startoff = lastbit: offline re-scrub failed (1).
+u3.bmx[2].startoff = lastbit: offline post-mod scrub failed (1).
+u3.bmx[2].startoff = add: offline re-scrub failed (1).
+u3.bmx[2].startoff = add: offline post-mod scrub failed (1).
+u3.bmx[2].startoff = sub: offline re-scrub failed (1).
+u3.bmx[2].startoff = sub: offline post-mod scrub failed (1).
+u3.bmx[3].startoff = zeroes: offline re-scrub failed (1).
+u3.bmx[3].startoff = zeroes: offline post-mod scrub failed (1).
+u3.bmx[3].startoff = ones: offline re-scrub failed (1).
+u3.bmx[3].startoff = ones: offline post-mod scrub failed (1).
+u3.bmx[3].startoff = firstbit: offline re-scrub failed (1).
+u3.bmx[3].startoff = firstbit: offline post-mod scrub failed (1).
+u3.bmx[3].startoff = middlebit: offline re-scrub failed (1).
+u3.bmx[3].startoff = middlebit: offline post-mod scrub failed (1).
+u3.bmx[3].startoff = lastbit: offline re-scrub failed (1).
+u3.bmx[3].startoff = lastbit: offline post-mod scrub failed (1).
+u3.bmx[3].startoff = add: offline re-scrub failed (1).
+u3.bmx[3].startoff = add: offline post-mod scrub failed (1).
+u3.bmx[3].startoff = sub: offline re-scrub failed (1).
+u3.bmx[3].startoff = sub: offline post-mod scrub failed (1).
+u3.bmx[4].startoff = zeroes: offline re-scrub failed (1).
+u3.bmx[4].startoff = zeroes: offline post-mod scrub failed (1).
+u3.bmx[4].startoff = ones: offline re-scrub failed (1).
+u3.bmx[4].startoff = ones: offline post-mod scrub failed (1).
+u3.bmx[4].startoff = firstbit: offline re-scrub failed (1).
+u3.bmx[4].startoff = firstbit: offline post-mod scrub failed (1).
+u3.bmx[4].startoff = middlebit: offline re-scrub failed (1).
+u3.bmx[4].startoff = middlebit: offline post-mod scrub failed (1).
+u3.bmx[4].startoff = lastbit: offline re-scrub failed (1).
+u3.bmx[4].startoff = lastbit: offline post-mod scrub failed (1).
+u3.bmx[4].startoff = add: offline re-scrub failed (1).
+u3.bmx[4].startoff = add: offline post-mod scrub failed (1).
+u3.bmx[4].startoff = sub: offline re-scrub failed (1).
+u3.bmx[4].startoff = sub: offline post-mod scrub failed (1).
+u3.bmx[5].startoff = zeroes: offline re-scrub failed (1).
+u3.bmx[5].startoff = zeroes: offline post-mod scrub failed (1).
+u3.bmx[5].startoff = ones: offline re-scrub failed (1).
+u3.bmx[5].startoff = ones: offline post-mod scrub failed (1).
+u3.bmx[5].startoff = firstbit: offline re-scrub failed (1).
+u3.bmx[5].startoff = firstbit: offline post-mod scrub failed (1).
+u3.bmx[5].startoff = middlebit: offline re-scrub failed (1).
+u3.bmx[5].startoff = middlebit: offline post-mod scrub failed (1).
+u3.bmx[5].startoff = lastbit: offline re-scrub failed (1).
+u3.bmx[5].startoff = lastbit: offline post-mod scrub failed (1).
+u3.bmx[5].startoff = add: offline re-scrub failed (1).
+u3.bmx[5].startoff = add: offline post-mod scrub failed (1).
+u3.bmx[5].startoff = sub: offline re-scrub failed (1).
+u3.bmx[5].startoff = sub: offline post-mod scrub failed (1).
+u3.bmx[5].blockcount = lastbit: offline re-scrub failed (1).
+u3.bmx[5].blockcount = lastbit: offline post-mod scrub failed (1).
+u3.bmx[6].startoff = zeroes: offline re-scrub failed (1).
+u3.bmx[6].startoff = zeroes: offline post-mod scrub failed (1).
+u3.bmx[6].startoff = ones: offline re-scrub failed (1).
+u3.bmx[6].startoff = ones: offline post-mod scrub failed (1).
+u3.bmx[6].startoff = firstbit: offline re-scrub failed (1).
+u3.bmx[6].startoff = firstbit: offline post-mod scrub failed (1).
+u3.bmx[6].startoff = middlebit: offline re-scrub failed (1).
+u3.bmx[6].startoff = middlebit: offline post-mod scrub failed (1).
+u3.bmx[6].startoff = sub: offline re-scrub failed (1).
+u3.bmx[6].startoff = sub: offline post-mod scrub failed (1).
+u3.bmx[6].startblock = middlebit: offline re-scrub failed (1).
+u3.bmx[6].startblock = middlebit: offline post-mod scrub failed (1).
+u3.bmx[7].blockcount = lastbit: offline re-scrub failed (1).
+u3.bmx[7].blockcount = lastbit: offline post-mod scrub failed (1).
+u3.bmx[8].blockcount = zeroes: offline re-scrub failed (1).
+u3.bmx[8].blockcount = zeroes: offline post-mod scrub failed (1).
+u3.bmx[9].blockcount = zeroes: offline re-scrub failed (1).
+u3.bmx[9].blockcount = zeroes: offline post-mod scrub failed (1).
 Done fuzzing dir map NODE
diff --git a/tests/xfs/784.out b/tests/xfs/784.out
index b5c3fddabd..0b345dbc72 100644
--- a/tests/xfs/784.out
+++ b/tests/xfs/784.out
@@ -1,10 +1,20 @@
 QA output created by 784
 Format and populate
 Fuzz block map for EXTENTS_REMOTE3K
+a.bmx[0].startblock = firstbit: offline scrub didn't fail.
+a.bmx[0].startblock = firstbit: online scrub didn't fail.
+a.bmx[1].startblock = firstbit: offline scrub didn't fail.
+a.bmx[1].startblock = firstbit: online scrub didn't fail.
 Done fuzzing attr map EXTENTS_REMOTE3K
 Fuzz block map for EXTENTS_REMOTE4K
+a.bmx[0].startblock = firstbit: offline scrub didn't fail.
+a.bmx[0].startblock = firstbit: online scrub didn't fail.
+a.bmx[1].startblock = firstbit: offline scrub didn't fail.
+a.bmx[1].startblock = firstbit: online scrub didn't fail.
 Done fuzzing attr map EXTENTS_REMOTE4K
 Fuzz block map for LEAF
+a.bmx[0].startblock = firstbit: offline scrub didn't fail.
+a.bmx[0].startblock = firstbit: online scrub didn't fail.
 Done fuzzing attr map LEAF
 Fuzz block map for NODE
 Done fuzzing attr map NODE
diff --git a/tests/xfs/787.out b/tests/xfs/787.out
index 39bd7c2469..80a334f4ca 100755
--- a/tests/xfs/787.out
+++ b/tests/xfs/787.out
@@ -1,4 +1,27 @@
 QA output created by 787
 Format and populate
 Fuzz inobt
+leftsib = add: offline scrub didn't fail.
+rightsib = add: offline scrub didn't fail.
+keys[1].startino = zeroes: offline scrub didn't fail.
+keys[1].startino = ones: offline scrub didn't fail.
+keys[1].startino = firstbit: offline scrub didn't fail.
+keys[1].startino = middlebit: offline scrub didn't fail.
+keys[1].startino = lastbit: offline scrub didn't fail.
+keys[1].startino = add: offline scrub didn't fail.
+keys[1].startino = sub: offline scrub didn't fail.
+keys[2].startino = zeroes: offline scrub didn't fail.
+keys[2].startino = ones: offline scrub didn't fail.
+keys[2].startino = firstbit: offline scrub didn't fail.
+keys[2].startino = middlebit: offline scrub didn't fail.
+keys[2].startino = lastbit: offline scrub didn't fail.
+keys[2].startino = add: offline scrub didn't fail.
+keys[2].startino = sub: offline scrub didn't fail.
+keys[3].startino = zeroes: offline scrub didn't fail.
+keys[3].startino = ones: offline scrub didn't fail.
+keys[3].startino = firstbit: offline scrub didn't fail.
+keys[3].startino = middlebit: offline scrub didn't fail.
+keys[3].startino = lastbit: offline scrub didn't fail.
+keys[3].startino = add: offline scrub didn't fail.
+keys[3].startino = sub: offline scrub didn't fail.
 Done fuzzing inobt

[PATCH 1/1] swapext: make sure that we don't swap unwritten extents unless they're part of a rt extent(??)

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 tests/xfs/1213     |   73 ++++++++++++++++
 tests/xfs/1213.out |    2 
 tests/xfs/1214     |  232 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 tests/xfs/1214.out |    2 
 4 files changed, 309 insertions(+)
 create mode 100755 tests/xfs/1213
 create mode 100644 tests/xfs/1213.out
 create mode 100755 tests/xfs/1214
 create mode 100644 tests/xfs/1214.out


diff --git a/tests/xfs/1213 b/tests/xfs/1213
new file mode 100755
index 0000000000..40bf3838af
--- /dev/null
+++ b/tests/xfs/1213
@@ -0,0 +1,73 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2023-2024 Oracle.  All Rights Reserved.
+#
+# FS QA Test No. 1213
+#
+# Make sure that the XFS_EXCH_RANGE_FILE1_WRITTEN actually skips holes and
+# unwritten extents on the data device and the rt device when the rextsize
+# is 1 fsblock.
+#
+. ./common/preamble
+_begin_fstest auto fiexchange swapext
+
+. ./common/filter
+
+# real QA test starts here
+
+# Modify as appropriate.
+_supported_fs generic
+_require_xfs_io_command "falloc"
+_require_xfs_io_command swapext '-v exchrange -a'
+_require_scratch
+
+_scratch_mkfs >> $seqres.full
+_scratch_mount
+
+# This test doesn't deal with the unwritten extents that must be created when
+# the realtime file allocation unit is larger than the fs blocksize.
+file_blksz=$(_get_file_block_size $SCRATCH_MNT)
+fs_blksz=$(_get_block_size $SCRATCH_MNT)
+test "$file_blksz" -eq "$fs_blksz" || \
+	_notrun "test requires file alloc unit ($file_blksz) == fs block size ($fs_blksz)"
+
+swap_and_check_contents() {
+	local a="$1"
+	local b="$2"
+	local tag="$3"
+
+	local a_md5_before=$(md5sum $a | awk '{print $1}')
+	local b_md5_before=$(md5sum $b | awk '{print $1}')
+
+	# Test swapext.  -h means skip holes in /b, and -e means operate to EOF
+	echo "swap $tag" >> $seqres.full
+	$XFS_IO_PROG -c fsync -c 'bmap -elpvvvv' $a $b >> $seqres.full
+	$XFS_IO_PROG -c "swapext -v exchrange -f -u -h -e -a $b" $a >> $seqres.full
+	$XFS_IO_PROG -c 'bmap -elpvvvv' $a $b >> $seqres.full
+	_scratch_cycle_mount
+
+	local a_md5_after=$(md5sum $a | awk '{print $1}')
+	local b_md5_after=$(md5sum $b | awk '{print $1}')
+
+	test "$a_md5_before" != "$a_md5_after" && \
+		echo "$a: md5 $a_md5_before -> $a_md5_after in $tag"
+
+	test "$b_md5_before" != "$b_md5_after" && \
+		echo "$b: md5 $b_md5_before -> $b_md5_after in $tag"
+}
+
+# plain preallocations on the data device
+$XFS_IO_PROG -c 'extsize 0' $SCRATCH_MNT
+_pwrite_byte 0x58 0 1m $SCRATCH_MNT/dar >> $seqres.full
+$XFS_IO_PROG -f -c 'truncate 1m' -c "falloc 640k 64k" $SCRATCH_MNT/dbr
+swap_and_check_contents $SCRATCH_MNT/dar $SCRATCH_MNT/dbr "plain prealloc"
+
+# extent size hints on the data device
+$XFS_IO_PROG -c 'extsize 1m' $SCRATCH_MNT
+_pwrite_byte 0x58 0 1m $SCRATCH_MNT/dae >> $seqres.full
+$XFS_IO_PROG -f -c 'truncate 1m' -c "falloc 640k 64k" $SCRATCH_MNT/dbe
+swap_and_check_contents $SCRATCH_MNT/dae $SCRATCH_MNT/dbe "data dev extsize prealloc"
+
+echo Silence is golden
+status=0
+exit
diff --git a/tests/xfs/1213.out b/tests/xfs/1213.out
new file mode 100644
index 0000000000..5a28b8b45f
--- /dev/null
+++ b/tests/xfs/1213.out
@@ -0,0 +1,2 @@
+QA output created by 1213
+Silence is golden
diff --git a/tests/xfs/1214 b/tests/xfs/1214
new file mode 100755
index 0000000000..5b78b5e348
--- /dev/null
+++ b/tests/xfs/1214
@@ -0,0 +1,232 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2023-2024 Oracle.  All Rights Reserved.
+#
+# FS QA Test No. 1214
+#
+# Make sure that the XFS_EXCH_RANGE_FILE1_WRITTEN actually skips holes and
+# unwritten extents on the realtime device when the rextsize is larger than 1
+# fs block.
+#
+. ./common/preamble
+_begin_fstest auto fiexchange swapext
+
+. ./common/filter
+
+# real QA test starts here
+
+# Modify as appropriate.
+_supported_fs generic
+_require_xfs_io_command "falloc"
+_require_xfs_io_command swapext '-v exchrange -a'
+_require_realtime
+_require_scratch
+
+_scratch_mkfs >> $seqres.full
+_scratch_mount
+
+# This test only deals with the unwritten extents that must be created when
+# the realtime file allocation unit is larger than the fs blocksize.
+file_blksz=$(_get_file_block_size $SCRATCH_MNT)
+fs_blksz=$(_get_block_size $SCRATCH_MNT)
+test "$file_blksz" -ge "$((3 * fs_blksz))" || \
+	_notrun "test requires file alloc unit ($file_blksz) >= 3 * fs block size ($fs_blksz)"
+
+swap_and_check_contents() {
+	local a="$1"
+	local b="$2"
+	local tag="$3"
+
+	sync
+
+	# Test swapext.  -h means skip holes in /b, and -e means operate to EOF
+	echo "swap $tag" >> $seqres.full
+	$XFS_IO_PROG -c 'bmap -elpvvvv' $a $b >> $seqres.full
+	$XFS_IO_PROG -c "swapext -v exchrange -f -u -h -e -a $b" $a >> $seqres.full
+	$XFS_IO_PROG -c 'bmap -elpvvvv' $a $b >> $seqres.full
+
+	local a_md5_before=$(md5sum $a | awk '{print $1}')
+	local b_md5_before=$(md5sum $b | awk '{print $1}')
+
+	_scratch_cycle_mount
+
+	local a_md5_check=$(md5sum $a.chk | awk '{print $1}')
+	local b_md5_check=$(md5sum $b.chk | awk '{print $1}')
+
+	local a_md5_after=$(md5sum $a | awk '{print $1}')
+	local b_md5_after=$(md5sum $b | awk '{print $1}')
+
+	test "$a_md5_before" != "$a_md5_after" && \
+		echo "$a: md5 $a_md5_before -> $a_md5_after in $tag"
+
+	test "$b_md5_before" != "$b_md5_after" && \
+		echo "$b: md5 $b_md5_before -> $b_md5_after in $tag"
+
+	if [ "$a_md5_check" != "$a_md5_after" ]; then
+		echo "$a: md5 $a_md5_after, expected $a_md5_check in $tag" | tee -a $seqres.full
+		echo "$a contents" >> $seqres.full
+		od -tx1 -Ad -c $a >> $seqres.full
+		echo "$a.chk contents" >> $seqres.full
+		od -tx1 -Ad -c $a.chk >> $seqres.full
+	fi
+
+	if [ "$b_md5_check" != "$b_md5_after" ]; then
+		echo "$b: md5 $b_md5_after, expected $b_md5_check in $tag" | tee -a $seqres.full
+		echo "$b contents" >> $seqres.full
+		od -tx1 -Ad -c $b >> $seqres.full
+		echo "$b.chk contents" >> $seqres.full
+		od -tx1 -Ad -c $b.chk >> $seqres.full
+	fi
+}
+
+filesz=$((5 * file_blksz))
+
+# first rtblock of the second rtextent is unwritten
+rm -f $SCRATCH_MNT/da $SCRATCH_MNT/db $SCRATCH_MNT/*.chk
+_pwrite_byte 0x58 0 $filesz $SCRATCH_MNT/da >> $seqres.full
+$XFS_IO_PROG -f -c "truncate $filesz" \
+	-c "pwrite -S 0x59 $((file_blksz + fs_blksz)) $((file_blksz - fs_blksz))" \
+	$SCRATCH_MNT/db >> $seqres.full
+$XFS_IO_PROG -f -c "truncate $filesz" \
+	-c "pwrite -S 0x58 0 $file_blksz" \
+	-c "pwrite -S 0x00 $file_blksz $fs_blksz" \
+	-c "pwrite -S 0x59 $((file_blksz + fs_blksz)) $((file_blksz - fs_blksz))" \
+	-c "pwrite -S 0x58 $((file_blksz * 2)) $((filesz - (file_blksz * 2) ))" \
+	$SCRATCH_MNT/da.chk >> /dev/null
+$XFS_IO_PROG -f -c "truncate $filesz" \
+	-c "pwrite -S 0x58 $file_blksz $file_blksz" \
+	$SCRATCH_MNT/db.chk >> /dev/null
+swap_and_check_contents $SCRATCH_MNT/da $SCRATCH_MNT/db \
+	"first rtb of second rtx"
+
+# second rtblock of the second rtextent is unwritten
+rm -f $SCRATCH_MNT/da $SCRATCH_MNT/db $SCRATCH_MNT/*.chk
+_pwrite_byte 0x58 0 $filesz $SCRATCH_MNT/da >> $seqres.full
+$XFS_IO_PROG -f -c "truncate $filesz" \
+	-c "pwrite -S 0x59 $file_blksz $fs_blksz" \
+	-c "pwrite -S 0x59 $((file_blksz + (2 * fs_blksz) )) $((file_blksz - (2 * fs_blksz) ))" \
+	$SCRATCH_MNT/db >> $seqres.full
+$XFS_IO_PROG -f -c "truncate $filesz" \
+	-c "pwrite -S 0x58 0 $file_blksz" \
+	-c "pwrite -S 0x59 $file_blksz $fs_blksz" \
+	-c "pwrite -S 0x00 $((file_blksz + fs_blksz)) $fs_blksz" \
+	-c "pwrite -S 0x59 $((file_blksz + (2 * fs_blksz) )) $((file_blksz - (2 * fs_blksz) ))" \
+	-c "pwrite -S 0x58 $((file_blksz * 2)) $((filesz - (file_blksz * 2) ))" \
+	$SCRATCH_MNT/da.chk >> /dev/null
+$XFS_IO_PROG -f -c "truncate $filesz" \
+	-c "pwrite -S 0x58 $file_blksz $file_blksz" \
+	$SCRATCH_MNT/db.chk >> /dev/null
+swap_and_check_contents $SCRATCH_MNT/da $SCRATCH_MNT/db \
+	"second rtb of second rtx"
+
+# last rtblock of the second rtextent is unwritten
+rm -f $SCRATCH_MNT/da $SCRATCH_MNT/db $SCRATCH_MNT/*.chk
+_pwrite_byte 0x58 0 $filesz $SCRATCH_MNT/da >> $seqres.full
+$XFS_IO_PROG -f -c "truncate $filesz" \
+	-c "pwrite -S 0x59 $file_blksz $((file_blksz - fs_blksz))" \
+	$SCRATCH_MNT/db >> $seqres.full
+$XFS_IO_PROG -f -c "truncate $filesz" \
+	-c "pwrite -S 0x58 0 $file_blksz" \
+	-c "pwrite -S 0x59 $file_blksz $((file_blksz - fs_blksz))" \
+	-c "pwrite -S 0x00 $(( (2 * file_blksz) - fs_blksz)) $fs_blksz" \
+	-c "pwrite -S 0x58 $((file_blksz * 2)) $((filesz - (file_blksz * 2) ))" \
+	$SCRATCH_MNT/da.chk >> /dev/null
+$XFS_IO_PROG -f -c "truncate $filesz" \
+	-c "pwrite -S 0x58 $file_blksz $file_blksz" \
+	$SCRATCH_MNT/db.chk >> /dev/null
+swap_and_check_contents $SCRATCH_MNT/da $SCRATCH_MNT/db \
+	"last rtb of second rtx"
+
+# last rtb of the 2nd rtx and first rtb of the 3rd rtx is unwritten
+rm -f $SCRATCH_MNT/da $SCRATCH_MNT/db $SCRATCH_MNT/*.chk
+_pwrite_byte 0x58 0 $filesz $SCRATCH_MNT/da >> $seqres.full
+$XFS_IO_PROG -f -c "truncate $filesz" \
+	-c "falloc $file_blksz $((2 * file_blksz))" \
+	-c "pwrite -S 0x59 $file_blksz $((file_blksz - fs_blksz))" \
+	-c "pwrite -S 0x59 $(( (2 * file_blksz) + fs_blksz)) $((file_blksz - fs_blksz))" \
+	$SCRATCH_MNT/db >> $seqres.full
+$XFS_IO_PROG -f -c "truncate $filesz" \
+	-c "pwrite -S 0x58 0 $file_blksz" \
+	-c "pwrite -S 0x59 $file_blksz $((file_blksz - fs_blksz))" \
+	-c "pwrite -S 0x00 $(( (2 * file_blksz) - fs_blksz)) $((2 * fs_blksz))" \
+	-c "pwrite -S 0x59 $(( (2 * file_blksz) + fs_blksz)) $((file_blksz - fs_blksz))" \
+	-c "pwrite -S 0x58 $((file_blksz * 3)) $((filesz - (file_blksz * 3) ))" \
+	$SCRATCH_MNT/da.chk >> /dev/null
+$XFS_IO_PROG -f -c "truncate $filesz" \
+	-c "pwrite -S 0x58 $file_blksz $((2 * file_blksz))" \
+	$SCRATCH_MNT/db.chk >> /dev/null
+swap_and_check_contents $SCRATCH_MNT/da $SCRATCH_MNT/db \
+	"last rtb of 2nd rtx and first rtb of 3rd rtx"
+
+# last rtb of the 2nd rtx and first rtb of the 4th rtx is unwritten; 3rd rtx
+# is a hole
+rm -f $SCRATCH_MNT/da $SCRATCH_MNT/db $SCRATCH_MNT/*.chk
+_pwrite_byte 0x58 0 $filesz $SCRATCH_MNT/da >> $seqres.full
+$XFS_IO_PROG -f -c "truncate $filesz" \
+	-c "pwrite -S 0x59 $file_blksz $((file_blksz - fs_blksz))" \
+	-c "pwrite -S 0x59 $(( (3 * file_blksz) + fs_blksz)) $((file_blksz - fs_blksz))" \
+	-c "fpunch $((2 * file_blksz)) $file_blksz" \
+	$SCRATCH_MNT/db >> $seqres.full
+$XFS_IO_PROG -f -c "truncate $filesz" \
+	-c "pwrite -S 0x58 0 $file_blksz" \
+	-c "pwrite -S 0x59 $file_blksz $((file_blksz - fs_blksz))" \
+	-c "pwrite -S 0x00 $(( (2 * file_blksz) - fs_blksz)) $fs_blksz" \
+	-c "pwrite -S 0x58 $((file_blksz * 2)) $file_blksz" \
+	-c "pwrite -S 0x00 $((3 * file_blksz)) $fs_blksz" \
+	-c "pwrite -S 0x59 $(( (3 * file_blksz) + fs_blksz)) $((file_blksz - fs_blksz))" \
+	-c "pwrite -S 0x58 $((file_blksz * 4)) $((filesz - (file_blksz * 4) ))" \
+	$SCRATCH_MNT/da.chk >> /dev/null
+$XFS_IO_PROG -f -c "truncate $filesz" \
+	-c "pwrite -S 0x58 $file_blksz $file_blksz" \
+	-c "pwrite -S 0x58 $((file_blksz * 3)) $file_blksz" \
+	$SCRATCH_MNT/db.chk >> /dev/null
+swap_and_check_contents $SCRATCH_MNT/da $SCRATCH_MNT/db \
+	"last rtb of 2nd rtx and first rtb of 4th rtx; 3rd rtx is hole"
+
+# last rtb of the 2nd rtx and first rtb of the 4th rtx is unwritten; 3rd rtx
+# is preallocated
+rm -f $SCRATCH_MNT/da $SCRATCH_MNT/db $SCRATCH_MNT/*.chk
+_pwrite_byte 0x58 0 $filesz $SCRATCH_MNT/da >> $seqres.full
+$XFS_IO_PROG -f -c "truncate $filesz" \
+	-c "falloc $file_blksz $((file_blksz * 3))" \
+	-c "pwrite -S 0x59 $file_blksz $((file_blksz - fs_blksz))" \
+	-c "pwrite -S 0x59 $(( (3 * file_blksz) + fs_blksz)) $((file_blksz - fs_blksz))" \
+	$SCRATCH_MNT/db >> $seqres.full
+$XFS_IO_PROG -f -c "truncate $filesz" \
+	-c "pwrite -S 0x58 0 $file_blksz" \
+	-c "pwrite -S 0x59 $file_blksz $((file_blksz - fs_blksz))" \
+	-c "pwrite -S 0x00 $(( (2 * file_blksz) - fs_blksz)) $fs_blksz" \
+	-c "pwrite -S 0x58 $((file_blksz * 2)) $file_blksz" \
+	-c "pwrite -S 0x00 $((3 * file_blksz)) $fs_blksz" \
+	-c "pwrite -S 0x59 $(( (3 * file_blksz) + fs_blksz)) $((file_blksz - fs_blksz))" \
+	-c "pwrite -S 0x58 $((file_blksz * 4)) $((filesz - (file_blksz * 4) ))" \
+	$SCRATCH_MNT/da.chk >> /dev/null
+$XFS_IO_PROG -f -c "truncate $filesz" \
+	-c "pwrite -S 0x58 $file_blksz $file_blksz" \
+	-c "pwrite -S 0x58 $((file_blksz * 3)) $file_blksz" \
+	$SCRATCH_MNT/db.chk >> /dev/null
+swap_and_check_contents $SCRATCH_MNT/da $SCRATCH_MNT/db \
+	"last rtb of 2nd rtx and first rtb of 4th rtx; 3rd rtx is prealloc"
+
+# 2nd rtx is preallocated and first rtb of 3rd rtx is unwritten
+rm -f $SCRATCH_MNT/da $SCRATCH_MNT/db $SCRATCH_MNT/*.chk
+_pwrite_byte 0x58 0 $filesz $SCRATCH_MNT/da >> $seqres.full
+$XFS_IO_PROG -f -c "truncate $filesz" \
+	-c "falloc $file_blksz $((file_blksz * 2))" \
+	-c "pwrite -S 0x59 $(( (2 * file_blksz) + fs_blksz)) $((file_blksz - fs_blksz))" \
+	$SCRATCH_MNT/db >> $seqres.full
+$XFS_IO_PROG -f -c "truncate $filesz" \
+	-c "pwrite -S 0x58 0 $((2 * file_blksz))" \
+	-c "pwrite -S 0x00 $((2 * file_blksz)) $fs_blksz" \
+	-c "pwrite -S 0x59 $(( (2 * file_blksz) + fs_blksz)) $((file_blksz - fs_blksz))" \
+	-c "pwrite -S 0x58 $((file_blksz * 3)) $((filesz - (file_blksz * 3) ))" \
+	$SCRATCH_MNT/da.chk >> /dev/null
+$XFS_IO_PROG -f -c "truncate $filesz" \
+	-c "pwrite -S 0x58 $((2 * file_blksz)) $file_blksz" \
+	$SCRATCH_MNT/db.chk >> /dev/null
+swap_and_check_contents $SCRATCH_MNT/da $SCRATCH_MNT/db \
+	"2nd rtx is prealloc and first rtb of 3rd rtx is unwritten"
+
+echo Silence is golden
+status=0
+exit
diff --git a/tests/xfs/1214.out b/tests/xfs/1214.out
new file mode 100644
index 0000000000..a529e42333
--- /dev/null
+++ b/tests/xfs/1214.out
@@ -0,0 +1,2 @@
+QA output created by 1214
+Silence is golden

[PATCH 1/2] generic/453: test confusable name detection with 32-bit unicode codepoints

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Test the confusable name detection when there are 32-bit unicode
sequences in use.  In other words, emoji.  Change the xfs_scrub test to
dump the output to a file instead of passing huge echo commands around.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 tests/generic/453 |   32 +++++++++++++++++++++-----------
 1 file changed, 21 insertions(+), 11 deletions(-)


diff --git a/tests/generic/453 b/tests/generic/453
index a0fb802e9b..930e6408ff 100755
--- a/tests/generic/453
+++ b/tests/generic/453
@@ -148,6 +148,10 @@ setf "combmark_\xe1\x80\x9c\xe1\x80\xaf\xe1\x80\xad.txt" "combining marks"
 setd ".\xe2\x80\x8d" "zero width joiners in dot entry"
 setd "..\xe2\x80\x8d" "zero width joiners in dotdot entry"
 
+# utf8 sequence mapping to a u32 unicode codepoint that can be confused
+setf "toilet_bowl.\xf0\x9f\x9a\xbd" "toilet emoji"
+setf "toilet_bow\xe2\x80\x8dl.\xf0\x9f\x9a\xbd" "toilet emoji with zero width joiner"
+
 ls -la $testdir >> $seqres.full
 
 echo "Test files"
@@ -198,6 +202,9 @@ testf "combmark_\xe1\x80\x9c\xe1\x80\xaf\xe1\x80\xad.txt" "combining marks"
 testd ".\xe2\x80\x8d" "zero width joiners in dot entry"
 testd "..\xe2\x80\x8d" "zero width joiners in dotdot entry"
 
+testf "toilet_bowl.\xf0\x9f\x9a\xbd" "toilet emoji"
+testf "toilet_bow\xe2\x80\x8dl.\xf0\x9f\x9a\xbd" "toilet emoji with zero width joiner"
+
 echo "Uniqueness of inodes?"
 stat -c '%i' "${testdir}/"* | sort | uniq -c | while read nr inum; do
 	if [ "${nr}" -gt 1 ]; then
@@ -208,18 +215,21 @@ done
 echo "Test XFS online scrub, if applicable"
 
 if _check_xfs_scrub_does_unicode "$SCRATCH_MNT" "$SCRATCH_DEV"; then
-	output="$(LC_ALL="C.UTF-8" ${XFS_SCRUB_PROG} -v -n "${SCRATCH_MNT}" 2>&1 | filter_scrub)"
-	echo "${output}" | grep -q "french_" || echo "No complaints about french e accent?"
-	echo "${output}" | grep -q "greek_" || echo "No complaints about greek letter mess?"
-	echo "${output}" | grep -q "arabic_" || echo "No complaints about arabic expanded string?"
-	echo "${output}" | grep -q "mixed_" || echo "No complaints about mixed script confusables?"
-	echo "${output}" | grep -q "hyphens_" || echo "No complaints about hyphenation confusables?"
-	echo "${output}" | grep -q "dz_digraph_" || echo "No complaints about single script confusables?"
-	echo "${output}" | grep -q "inadequate_" || echo "No complaints about inadequate rendering confusables?"
-	echo "${output}" | grep -q "prohibition_" || echo "No complaints about prohibited sequence confusables?"
-	echo "${output}" | grep -q "zerojoin_" || echo "No complaints about zero-width join confusables?"
+	LC_ALL="C.UTF-8" ${XFS_SCRUB_PROG} -v -n "${SCRATCH_MNT}" 2>&1 | filter_scrub > $tmp.scrub
+
+	grep -q "french_" $tmp.scrub || echo "No complaints about french e accent?"
+	grep -q "greek_" $tmp.scrub || echo "No complaints about greek letter mess?"
+	grep -q "arabic_" $tmp.scrub || echo "No complaints about arabic expanded string?"
+	grep -q "mixed_" $tmp.scrub || echo "No complaints about mixed script confusables?"
+	grep -q "hyphens_" $tmp.scrub || echo "No complaints about hyphenation confusables?"
+	grep -q "dz_digraph_" $tmp.scrub || echo "No complaints about single script confusables?"
+	grep -q "inadequate_" $tmp.scrub || echo "No complaints about inadequate rendering confusables?"
+	grep -q "prohibition_" $tmp.scrub || echo "No complaints about prohibited sequence confusables?"
+	grep -q "zerojoin_" $tmp.scrub || echo "No complaints about zero-width join confusables?"
+	grep -q "toilet_" $tmp.scrub || echo "No complaints about zero-width join confusables with emoji?"
+
 	echo "Actual xfs_scrub output:" >> $seqres.full
-	echo "${output}" >> $seqres.full
+	cat $tmp.scrub >> $seqres.full
 fi
 
 # success, all done

[PATCH 2/2] generic/453: check xfs_scrub detection of confusing job offers

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Earlier this year, ESET revealed that Linux users had been tricked into
opening executables containing malware payloads.  The trickery came in
the form of a malicious zip file containing a filename with the string
"job offer․pdf".  Note that the filename does *not* denote a real pdf
file, since the last four codepoints in the file name are "ONE DOT
LEADER", p, d, and f.  Not period (ok, FULL STOP), p, d, f like you'd
normally expect.

Now that xfs_scrub can look for codepoints that could be confused with a
period followed by alphanumerics, let's make sure it actually works.

Link: https://www.welivesecurity.com/2023/04/20/linux-malware-strengthens-links-lazarus-3cx-supply-chain-attack/
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 tests/generic/453 |   79 ++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 78 insertions(+), 1 deletion(-)


diff --git a/tests/generic/453 b/tests/generic/453
index 930e6408ff..855243a860 100755
--- a/tests/generic/453
+++ b/tests/generic/453
@@ -36,6 +36,15 @@ setf() {
 	echo "Storing ${key} ($(hexbytes "${key}")) -> ${value}" >> $seqres.full
 }
 
+setchild() {
+	subdir="$1"
+	key="$(echo -e "$2")"
+
+	mkdir -p "${testdir}/${subdir}"
+	echo "$subdir" > "${testdir}/${subdir}/${key}"
+	echo "Storing ${subdir}/${key} ($(hexbytes "${key}")) -> ${subdir}" >> $seqres.full
+}
+
 setd() {
 	key="$(echo -e "$1")"
 	value="$2"
@@ -63,6 +72,24 @@ testf() {
 	fi
 }
 
+testchild() {
+	subdir="$1"
+	key="$(echo -e "$2")"
+	fname="${testdir}/${subdir}/${key}"
+
+	echo "Testing ${subdir}/${key} ($(hexbytes "${key}")) -> ${subdir}" >> $seqres.full
+
+	if [ ! -e "${fname}" ]; then
+		echo "Key ${key} does not exist for ${subdir} test??"
+		return
+	fi
+
+	actual_value="$(cat "${fname}")"
+	if [ "${actual_value}" != "${subdir}" ]; then
+		echo "Key ${key} has value ${subdir}, expected ${actual_value}."
+	fi
+}
+
 testd() {
 	key="$(echo -e "$1")"
 	value="$2"
@@ -152,7 +179,27 @@ setd "..\xe2\x80\x8d" "zero width joiners in dotdot entry"
 setf "toilet_bowl.\xf0\x9f\x9a\xbd" "toilet emoji"
 setf "toilet_bow\xe2\x80\x8dl.\xf0\x9f\x9a\xbd" "toilet emoji with zero width joiner"
 
-ls -la $testdir >> $seqres.full
+# decoy file extensions used in 3cx malware attack, and similar ones
+setchild "one_dot_leader" "job offer\xe2\x80\xa4pdf"
+setchild "small_full_stop" "job offer\xef\xb9\x92pdf"
+setchild "fullwidth_full_stop" "job offer\xef\xbc\x8epdf"
+setchild "syriac_supralinear" "job offer\xdc\x81pdf"
+setchild "syriac_sublinear" "job offer\xdc\x82pdf"
+setchild "lisu_letter_tone" "job offer\xea\x93\xb8pdf"
+setchild "actual_period" "job offer.pdf"
+setchild "one_dot_leader_zero_width_space" "job offer\xe2\x80\xa4\xe2\x80\x8dpdf"
+
+# again, but this time all in the same directory to trip the confusable
+# detector
+setf "job offer\xe2\x80\xa4pdf" "one dot leader"
+setf "job offer\xef\xb9\x92pdf" "small full stop"
+setf "job offer\xef\xbc\x8epdf" "fullwidth full stop"
+setf "job offer\xdc\x81pdf" "syriac supralinear full stop"
+setf "job offer\xdc\x82pdf" "syriac sublinear full stop"
+setf "job offer\xea\x93\xb8pdf" "lisu letter tone mya ti"
+setf "job offer.pdf" "actual period"
+
+ls -laR $testdir >> $seqres.full
 
 echo "Test files"
 testf "french_caf\xc3\xa9.txt" "NFC"
@@ -205,6 +252,23 @@ testd "..\xe2\x80\x8d" "zero width joiners in dotdot entry"
 testf "toilet_bowl.\xf0\x9f\x9a\xbd" "toilet emoji"
 testf "toilet_bow\xe2\x80\x8dl.\xf0\x9f\x9a\xbd" "toilet emoji with zero width joiner"
 
+testchild "one_dot_leader" "job offer\xe2\x80\xa4pdf"
+testchild "small_full_stop" "job offer\xef\xb9\x92pdf"
+testchild "fullwidth_full_stop" "job offer\xef\xbc\x8epdf"
+testchild "syriac_supralinear" "job offer\xdc\x81pdf"
+testchild "syriac_sublinear" "job offer\xdc\x82pdf"
+testchild "lisu_letter_tone" "job offer\xea\x93\xb8pdf"
+testchild "actual_period" "job offer.pdf"
+testchild "one_dot_leader_zero_width_space" "job offer\xe2\x80\xa4\xe2\x80\x8dpdf"
+
+testf "job offer\xe2\x80\xa4pdf" "one dot leader"
+testf "job offer\xef\xb9\x92pdf" "small full stop"
+testf "job offer\xef\xbc\x8epdf" "fullwidth full stop"
+testf "job offer\xdc\x81pdf" "syriac supralinear full stop"
+testf "job offer\xdc\x82pdf" "syriac sublinear full stop"
+testf "job offer\xea\x93\xb8pdf" "lisu letter tone mya ti"
+testf "job offer.pdf" "actual period"
+
 echo "Uniqueness of inodes?"
 stat -c '%i' "${testdir}/"* | sort | uniq -c | while read nr inum; do
 	if [ "${nr}" -gt 1 ]; then
@@ -228,6 +292,19 @@ if _check_xfs_scrub_does_unicode "$SCRATCH_MNT" "$SCRATCH_DEV"; then
 	grep -q "zerojoin_" $tmp.scrub || echo "No complaints about zero-width join confusables?"
 	grep -q "toilet_" $tmp.scrub || echo "No complaints about zero-width join confusables with emoji?"
 
+	# Does xfs_scrub complain at all about the job offer files?  Pre-2023
+	# versions did not know to screen for that.
+	if grep -q "job offer" $tmp.scrub; then
+		grep -q 'job offer.xe2.x80.xa4pdf' $tmp.scrub || echo "No complaints about one dot leader?"
+		grep -q "job offer.xef.xb9.x92pdf" $tmp.scrub || echo "No complaints about small full stop?"
+		grep -q "job offer.xef.xbc.x8epdf" $tmp.scrub || echo "No complaints about fullwidth full stop?"
+		grep -q "job offer.xdc.x81pdf" $tmp.scrub || echo "No complaints about syriac supralinear full stop?"
+		grep -q "job offer.xdc.x82pdf" $tmp.scrub || echo "No complaints about syriac sublinear full stop?"
+		grep -q "job offer.xea.x93.xb8pdf" $tmp.scrub || echo "No complaints about lisu letter tone mya ti?"
+		grep -q "job offer.*could be confused with" $tmp.scrub || echo "No complaints about confusing job offers?"
+		grep -q "job offer.xe2.x80.xa4.xe2.x80.x8dpdf" $tmp.scrub || echo "No complaints about one dot leader with invisible space?"
+	fi
+
 	echo "Actual xfs_scrub output:" >> $seqres.full
 	cat $tmp.scrub >> $seqres.full
 fi

[PATCH 1/1] xfs: test xfs_scrub services

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a pair of new tests that check that xfs_scrub and xfs_scrub_all
will find and test mounted filesystems.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 common/rc          |   22 ++++++++
 tests/xfs/1863     |  136 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 tests/xfs/1863.out |    6 ++
 3 files changed, 164 insertions(+)
 create mode 100755 tests/xfs/1863
 create mode 100644 tests/xfs/1863.out


diff --git a/common/rc b/common/rc
index a9e0ba7e22..969ff93de7 100644
--- a/common/rc
+++ b/common/rc
@@ -5333,6 +5333,7 @@ _soak_loop_running() {
 	return 0
 }
 
+
 _require_unshare() {
 	unshare -f -r -m -p -U $@ true &>/dev/null || \
 		_notrun "unshare $*: command not found, should be in util-linux"
@@ -5345,6 +5346,27 @@ _random_file() {
 	echo "$basedir/$(ls -U $basedir | shuf -n 1)"
 }
 
+_require_program() {
+	local cmd="$1"
+	local tag="$2"
+
+	test -z "$tag" && tag="$(basename "$cmd")"
+	command -v "$1" &>/dev/null || _notrun "$tag required"
+}
+
+_require_systemd_service() {
+	_require_program systemctl systemd
+
+	systemctl cat "$1" >/dev/null || \
+		_notrun "systemd service \"$1\" not found"
+}
+
+_require_systemd_running() {
+	_require_systemd_service "$1"
+	test "$(systemctl is-active "$1")" = "active" || \
+		_notrun "systemd service \"$1\" not running"
+}
+
 init_rc
 
 ################################################################################
diff --git a/tests/xfs/1863 b/tests/xfs/1863
new file mode 100755
index 0000000000..36f10a0826
--- /dev/null
+++ b/tests/xfs/1863
@@ -0,0 +1,136 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2023-2024 Oracle.  All Rights Reserved.
+#
+# FS QA Test No. 1863
+#
+# Check that the online fsck systemd services find and check the test and
+# scratch filesystems, and that we can read the health reports after the fact.
+# IOWs, basic testing for the systemd background services.
+#
+. ./common/preamble
+_begin_fstest auto scrub
+
+_cleanup()
+{
+	cd /
+	if [ -n "$new_svcfile" ]; then
+		rm -f "$new_svcfile"
+		systemctl daemon-reload
+	fi
+	rm -r -f $tmp.*
+}
+
+# Import common functions.
+. ./common/filter
+. ./common/populate
+. ./common/fuzzy
+
+# real QA test starts here
+
+_supported_fs xfs
+_require_systemd_service xfs_scrub@.service
+_require_systemd_service xfs_scrub_all.service
+_require_scratch
+_require_scrub
+_require_xfs_io_command "scrub"
+_require_xfs_spaceman_command "health"
+_require_populate_commands
+
+_xfs_skip_online_rebuild
+_xfs_skip_offline_rebuild
+
+# Back when xfs_scrub was really experimental, the systemd service definitions
+# contained various bugs that resulted in weird problems such as logging
+# messages sometimes dropping slashes from paths, and the xfs_scrub@ service
+# being logged as completing long after the process actually stopped.  These
+# problems were all fixed by the time the --auto-media-scan-stamp option was
+# added to xfs_scrub_all, so turn off this test for such old codebases.
+scruball_exe="$(systemctl cat xfs_scrub_all | grep '^ExecStart=' | sed -e 's/ExecStart=//g' -e 's/ .*$//g')"
+grep -q -- '--auto-media-scan-stamp' "$scruball_exe" || \
+	_notrun "xfs_scrub service too old, skipping test"
+
+orig_svcfile="/lib/systemd/system/xfs_scrub_all.service"
+test -f "$orig_svcfile" || \
+	_notrun "cannot find xfs_scrub_all service file"
+
+new_svcdir="/run/systemd/system/"
+test -d "$new_svcdir" || \
+	_notrun "cannot find runtime systemd service dir"
+
+# We need to make some local mods to the xfs_scrub_all service definition
+# so we fork it and create a new service just for this test.
+new_scruball_svc="xfs_scrub_all_fstest.service"
+systemctl status "$new_scruball_svc" 2>&1 | grep -E -q '(could not be found|Loaded: not-found)' || \
+	_notrun "systemd service \"$new_scruball_svc\" found, will not mess with this"
+
+find_scrub_trace() {
+	local path="$1"
+
+	$XFS_SPACEMAN_PROG -c "health" "$path" | grep -q ": ok$" || \
+		echo "cannot find evidence that $path was scrubbed"
+}
+
+echo "Format and populate"
+_scratch_populate_cached nofill > $seqres.full 2>&1
+_scratch_mount
+
+run_service() {
+	systemctl start --wait "$1"
+
+	# Sometimes systemctl start --wait returns early due to some external
+	# event, such as somebody else reloading the daemon, which closes the
+	# socket.  The CLI has no way to resume waiting for the service once
+	# the connection breaks, so we'll pgrep for up to 30 seconds until
+	# there are no xfs_scrub processes running on the system.
+	for ((i = 0; i < 30; i++)); do
+		pgrep -f 'xfs_scrub*' > /dev/null 2>&1 || break
+		sleep 1
+	done
+}
+
+echo "Scrub Test FS"
+test_path=$(systemd-escape --path "$TEST_DIR")
+run_service xfs_scrub@$test_path
+find_scrub_trace "$TEST_DIR"
+
+echo "Scrub Scratch FS"
+scratch_path=$(systemd-escape --path "$SCRATCH_MNT")
+run_service xfs_scrub@$scratch_path
+find_scrub_trace "$SCRATCH_MNT"
+
+# Remove the xfs_scrub_all media scan stamp directory (if specified) because we
+# want to leave the regular system's stamp file alone.
+mkdir -p $tmp/stamp
+
+new_svcfile="$new_svcdir/$new_scruball_svc"
+cp "$orig_svcfile" "$new_svcfile"
+
+execstart="$(grep '^ExecStart=' $new_svcfile | sed -e 's/--auto-media-scan-interval[[:space:]]*[0-9]*[a-z]*//g')"
+sed -e '/ExecStart=/d' -e '/BindPaths=/d' -i $new_svcfile
+cat >> "$new_svcfile" << ENDL
+[Service]
+$execstart
+ENDL
+systemctl daemon-reload
+
+# Emit the results of our editing to the full log.
+systemctl cat "$new_scruball_svc" >> $seqres.full
+
+# Cycle both mounts to clear all the incore CHECKED bits.
+_test_cycle_mount
+_scratch_cycle_mount
+
+echo "Scrub Everything"
+run_service "$new_scruball_svc"
+
+sleep 2 # give systemd a chance to tear down the service container mount tree
+
+find_scrub_trace "$TEST_DIR"
+find_scrub_trace "$SCRATCH_MNT"
+
+echo "Scrub Done" | tee -a $seqres.full
+
+# success, all done
+status=0
+exit
diff --git a/tests/xfs/1863.out b/tests/xfs/1863.out
new file mode 100644
index 0000000000..a1dd7d4bf4
--- /dev/null
+++ b/tests/xfs/1863.out
@@ -0,0 +1,6 @@
+QA output created by 1863
+Format and populate
+Scrub Test FS
+Scrub Scratch FS
+Scrub Everything
+Scrub Done

[PATCH 1/1] xfs/004: fix column extraction code

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Now that the xfs_db freesp command prints a CDF of the free space
histograms, fix the pct column extraction code to handle the two
new columns by <cough> using awk.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 tests/xfs/004 |   19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)


diff --git a/tests/xfs/004 b/tests/xfs/004
index f18316b333..2d55d18801 100755
--- a/tests/xfs/004
+++ b/tests/xfs/004
@@ -84,14 +84,17 @@ then
 fi
 
 # check the 'pct' field from freesp command is good
-perl -ne '
-	    BEGIN	{ $percent = 0; }
-	    /free/	&& next;	# skip over free extent size number
-	    if (/\s+(\d+\.\d+)$/) {
-		$percent += $1;
-	    }
-	    END	{ $percent += 0.5; print int($percent), "\n" }	# round up
-' <$tmp.xfs_db >$tmp.ans
+awk '
+{
+	if ($0 ~ /free/) {
+		next;
+	}
+
+	percent += $5;
+}
+END {
+	printf("%d\n", int(percent + 0.5));
+}' < $tmp.xfs_db > $tmp.ans
 ans="`cat $tmp.ans`"
 echo "Checking percent column yields 100: $ans"
 if [ "$ans" != 100 ]

[PATCH 1/1] xfs: test upgrading old features

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Test the ability to add older v5 features.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 tests/xfs/1856     |  247 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 tests/xfs/1856.out |    2 
 2 files changed, 249 insertions(+)
 create mode 100755 tests/xfs/1856
 create mode 100644 tests/xfs/1856.out


diff --git a/tests/xfs/1856 b/tests/xfs/1856
new file mode 100755
index 0000000000..84e72d7c81
--- /dev/null
+++ b/tests/xfs/1856
@@ -0,0 +1,247 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0-or-later
+# Copyright (c) 2022-2024 Oracle.  All Rights Reserved.
+#
+# FS QA Test No. 1856
+#
+# Test upgrading filesystems with new features.
+#
+. ./common/preamble
+_begin_fstest auto mkfs repair
+
+# Import common functions.
+. ./common/filter
+. ./common/populate
+
+# real QA test starts here
+_supported_fs xfs
+
+_require_check_dmesg
+_require_scratch_nocheck
+_require_scratch_xfs_crc
+
+# Does repair know how to add a particular feature to a filesystem?
+check_repair_upgrade()
+{
+	$XFS_REPAIR_PROG -c "$1=narf" 2>&1 | \
+		grep -q 'unknown option' && return 1
+	return 0
+}
+
+# Are we configured for realtime?
+rt_configured()
+{
+	test "$USE_EXTERNAL" = "yes" && test -n "$SCRATCH_RTDEV"
+}
+
+# Compute the MKFS_OPTIONS string for a particular feature upgrade test
+compute_mkfs_options()
+{
+	local m_opts=""
+	local caller_options="$MKFS_OPTIONS"
+
+	for feat in "${FEATURES[@]}"; do
+		local feat_state="${FEATURE_STATE["${feat}"]}"
+
+		if echo "$caller_options" | grep -E -w -q "${feat}=[0-9]*"; then
+			# Change the caller's options
+			caller_options="$(echo "$caller_options" | \
+				sed -e "s/\([^[:alnum:]]\)${feat}=[0-9]*/\1${feat}=${feat_state}/g")"
+		else
+			# Add it to our list of new mkfs flags
+			m_opts="${feat}=${feat_state},${m_opts}"
+		fi
+	done
+
+	test -n "$m_opts" && m_opts=" -m $m_opts"
+
+	echo "$caller_options$m_opts"
+}
+
+# Log the start of an upgrade.
+upgrade_start_message()
+{
+	local feat="$1"
+
+	echo "Add $feat to filesystem"
+}
+
+# Find dmesg log messages since we started a particular upgrade test
+dmesg_since_feature_upgrade_start()
+{
+	local feat_logmsg="$(upgrade_start_message "$1")"
+
+	# search the dmesg log of last run of $seqnum for possible failures
+	# use sed \cregexpc address type, since $seqnum contains "/"
+	dmesg | \
+		tac | \
+		sed -ne "0,\#run fstests $seqnum at $date_time#p" | \
+		sed -ne "0,\#${feat_logmsg}#p" | \
+		tac
+}
+
+# Did the mount fail because this feature is not supported?
+feature_unsupported()
+{
+	local feat="$1"
+
+	dmesg_since_feature_upgrade_start "$feat" | \
+		grep -q 'has unknown.*features'
+}
+
+# Exercise the scratch fs
+scratch_fsstress()
+{
+	echo moo > $SCRATCH_MNT/sample.txt
+	$FSSTRESS_PROG -n $((TIME_FACTOR * 1000)) -p $((LOAD_FACTOR * 4)) \
+		-d $SCRATCH_MNT/data >> $seqres.full
+}
+
+# Exercise the filesystem a little bit and emit a manifest.
+pre_exercise()
+{
+	local feat="$1"
+
+	_try_scratch_mount &> $tmp.mount
+	res=$?
+	# If the kernel doesn't support the filesystem even after a
+	# fresh format, skip the rest of the upgrade test quietly.
+	if [ $res -eq 32 ] && feature_unsupported "$feat"; then
+		echo "mount failed due to unsupported feature $feat" >> $seqres.full
+		return 1
+	fi
+	if [ $res -ne 0 ]; then
+		cat $tmp.mount
+		echo "mount failed with $res before upgrading to $feat" | \
+			tee -a $seqres.full
+		return 1
+	fi
+
+	scratch_fsstress
+	find $SCRATCH_MNT -type f -print0 | xargs -r -0 md5sum > $tmp.manifest
+	_scratch_unmount
+	return 0
+}
+
+# Check the manifest and exercise the filesystem more
+post_exercise()
+{
+	local feat="$1"
+
+	_try_scratch_mount &> $tmp.mount
+	res=$?
+	# If the kernel doesn't support the filesystem even after a
+	# fresh format, skip the rest of the upgrade test quietly.
+	if [ $res -eq 32 ] && feature_unsupported "$feat"; then
+		echo "mount failed due to unsupported feature $feat" >> $seqres.full
+		return 1
+	fi
+	if [ $res -ne 0 ]; then
+		cat $tmp.mount
+		echo "mount failed with $res after upgrading to $feat" | \
+			tee -a $seqres.full
+		return 1
+	fi
+
+	md5sum --quiet -c $tmp.manifest || \
+		echo "fs contents ^^^ changed after adding $feat"
+
+	iam="check" _check_scratch_fs || \
+		echo "scratch fs check failed after adding $feat"
+
+	# Try to mount the fs in case the check unmounted it
+	_try_scratch_mount &>> $seqres.full
+
+	scratch_fsstress
+
+	iam="check" _check_scratch_fs || \
+		echo "scratch fs check failed after exercising $feat"
+
+	# Try to unmount the fs in case the check didn't
+	_scratch_unmount &>> $seqres.full
+	return 0
+}
+
+# Create a list of fs features in the order that support for them was added
+# to the kernel driver.  For each feature upgrade test, we enable all the
+# features that came before it and none of the ones after, which means we're
+# testing incremental migrations.  We start each run with a clean fs so that
+# errors and unsatisfied requirements (log size, root ino position, etc) in one
+# upgrade don't spread failure to the rest of the tests.
+FEATURES=()
+if rt_configured; then
+	check_repair_upgrade finobt && FEATURES+=("finobt")
+	check_repair_upgrade inobtcount && FEATURES+=("inobtcount")
+	check_repair_upgrade bigtime && FEATURES+=("bigtime")
+else
+	check_repair_upgrade finobt && FEATURES+=("finobt")
+	check_repair_upgrade rmapbt && FEATURES+=("rmapbt")
+	check_repair_upgrade reflink && FEATURES+=("reflink")
+	check_repair_upgrade inobtcount && FEATURES+=("inobtcount")
+	check_repair_upgrade bigtime && FEATURES+=("bigtime")
+fi
+
+test "${#FEATURES[@]}" -eq 0 && \
+	_notrun "xfs_repair does not know how to add V5 features"
+
+declare -A FEATURE_STATE
+for f in "${FEATURES[@]}"; do
+	FEATURE_STATE["$f"]=0
+done
+
+for feat in "${FEATURES[@]}"; do
+	echo "-----------------------" >> $seqres.full
+
+	upgrade_start_message "$feat" | _tee_kernlog $seqres.full > /dev/null
+
+	opts="$(compute_mkfs_options)"
+	echo "mkfs.xfs $opts" >> $seqres.full
+
+	# Format filesystem
+	MKFS_OPTIONS="$opts" _scratch_mkfs &>> $seqres.full
+	res=$?
+	outcome="mkfs returns $res for $feat upgrade test"
+	echo "$outcome" >> $seqres.full
+	if [ $res -ne 0 ]; then
+		echo "$outcome"
+		continue
+	fi
+
+	# Create some files to make things interesting.
+	pre_exercise "$feat" || break
+
+	# Upgrade the fs
+	_scratch_xfs_repair -c "${feat}=1" &> $tmp.upgrade
+	res=$?
+	cat $tmp.upgrade >> $seqres.full
+	grep -q "^Adding" $tmp.upgrade || \
+		echo "xfs_repair ignored command to add $feat"
+
+	outcome="xfs_repair returns $res while adding $feat"
+	echo "$outcome" >> $seqres.full
+	if [ $res -ne 0 ]; then
+		# Couldn't upgrade filesystem, move on to the next feature.
+		FEATURE_STATE["$feat"]=1
+		continue
+	fi
+
+	# Make sure repair runs cleanly afterwards
+	_scratch_xfs_repair -n &>> $seqres.full
+	res=$?
+	outcome="xfs_repair -n returns $res after adding $feat"
+	echo "$outcome" >> $seqres.full
+	if [ $res -ne 0 ]; then
+		echo "$outcome"
+	fi
+
+	# Make sure we can still exercise the filesystem.
+	post_exercise "$feat" || break
+
+	# Update feature state for next run
+	FEATURE_STATE["$feat"]=1
+done
+
+# success, all done
+echo Silence is golden.
+status=0
+exit
diff --git a/tests/xfs/1856.out b/tests/xfs/1856.out
new file mode 100644
index 0000000000..3c569451b3
--- /dev/null
+++ b/tests/xfs/1856.out
@@ -0,0 +1,2 @@
+QA output created by 1856
+Silence is golden.

[PATCH 1/1] design: document atomic extent swap log intent structures

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Document the log formats for the atomic extent swapping feature.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 .../allocation_groups.asciidoc                     |    7 +
 .../journaling_log.asciidoc                        |  111 ++++++++++++++++++++
 design/XFS_Filesystem_Structure/magic.asciidoc     |    2 
 3 files changed, 120 insertions(+)


diff --git a/design/XFS_Filesystem_Structure/allocation_groups.asciidoc b/design/XFS_Filesystem_Structure/allocation_groups.asciidoc
index c0ba16a8..7b128838 100644
--- a/design/XFS_Filesystem_Structure/allocation_groups.asciidoc
+++ b/design/XFS_Filesystem_Structure/allocation_groups.asciidoc
@@ -470,6 +470,13 @@ the FS log if it doesn't understand the flag.
 | Flag					| Description
 | +XFS_SB_FEAT_INCOMPAT_LOG_XATTRS+	|
 Extended attribute updates have been committed to the ondisk log.
+| +XFS_SB_FEAT_INCOMPAT_LOG_ATOMIC_SWAP+ |
+Atomic file content swapping.  The filesystem is capable of swapping the
+extents mapped to two arbitrary ranges of a file's fork by using intent log
+items to track the progress of the high level operation.  In other words, a
+range swap operation can be restarted if the system goes down, which is
+necessary for userspace to commit of new file contents atomically.  See the
+section about xref:SXI_Log_Item[extent swap log intents] for more information.
 
 |=====
 
diff --git a/design/XFS_Filesystem_Structure/journaling_log.asciidoc b/design/XFS_Filesystem_Structure/journaling_log.asciidoc
index 8ff437fe..daf9b225 100644
--- a/design/XFS_Filesystem_Structure/journaling_log.asciidoc
+++ b/design/XFS_Filesystem_Structure/journaling_log.asciidoc
@@ -217,6 +217,8 @@ magic number to distinguish themselves.  Buffer data items only appear after
 | +XFS_LI_BUD+			| 0x1245        | xref:BUD_Log_Item[File Block Mapping Update Done]
 | +XFS_LI_ATTRI+		| 0x1246        | xref:ATTRI_Log_Item[Extended Attribute Update Intent]
 | +XFS_LI_ATTRD+		| 0x1247        | xref:ATTRD_Log_Item[Extended Attribute Update Done]
+| +XFS_LI_SXI+			| 0x1248        | xref:SXI_Log_Item[File Extent Swap Intent]
+| +XFS_LI_SXD+			| 0x1249        | xref:SXD_Log_Item[File Extent Swap Done]
 |=====
 
 Note that all log items (except for transaction headers) MUST start with
@@ -649,6 +651,8 @@ file block mapping operation we want.  The upper three bytes are flag bits.
 | Value				| Description
 | +XFS_BMAP_EXTENT_ATTR_FORK+	| Extent is for the attribute fork.
 | +XFS_BMAP_EXTENT_UNWRITTEN+	| Extent is unwritten.
+| +XFS_BMAP_EXTENT_REALTIME+	| Mapping applies to the data fork of a
+realtime file.  This flag cannot be combined with +XFS_BMAP_EXTENT_ATTR_FORK+.
 |=====
 
 The ``file block mapping update intent'' operation comes first; it tells the
@@ -821,6 +825,113 @@ These regions contain the name and value components of the extended attribute
 being updated, as needed.  There are no magic numbers; each region contains the
 data and nothing else.
 
+[[SXI_Log_Item]]
+=== File Extent Swap Intent
+
+These two log items work together to track the exchange of mapped extents
+between the forks of two files.  Each operation requires a separate SXI/SXD
+pair.  The log intent item has the following format:
+
+[source, c]
+----
+struct xfs_sxi_log_format {
+     uint16_t                  sxi_type;
+     uint16_t                  sxi_size;
+     uint32_t                  __pad;
+     uint64_t                  sxi_id;
+     uint64_t                  sxi_inode1;
+     uint64_t                  sxi_inode2;
+     uint64_t                  sxi_startoff1;
+     uint64_t                  sxi_startoff2;
+     uint64_t                  sxi_blockcount;
+     uint64_t                  sxi_flags;
+     int64_t                   sxi_isize1;
+     int64_t                   sxi_isize2;
+};
+----
+
+*sxi_type*::
+The signature of an SXI operation, 0x1246.  This value is in host-endian order,
+not big-endian like the rest of XFS.
+
+*sxi_size*::
+Size of this log item.  Should be 1.
+
+*__pad*::
+Must be zero.
+
+*sxi_id*::
+A 64-bit number that binds the corresponding SXD log item to this SXI log item.
+
+*sxi_inode1*::
+Inode number of the first file involved in the operation.
+
+*sxi_inode2*::
+Inode number of the second file involved in the operation.
+
+*sxi_startoff1*::
+Starting point within the first file, in units of filesystem blocks.
+
+*sxi_startoff2*::
+Starting point within the second file, in units of filesystem blocks.
+
+*sxi_blockcount*::
+The length to be exchanged, in units of filesystem blocks.
+
+*sxi_flags*::
+Behavioral changes to the operation, as follows:
+
+.File Extent Swap Intent Item Flags
+[options="header"]
+|=====
+| Value				   | Description
+| +XFS_SWAP_EXTENT_ATTR_FORK+	   | Exchange extents between attribute forks.
+| +XFS_SWAP_EXTENT_SET_SIZES+	   | Exchange the file sizes of the two files
+after the operation completes.
+| +XFS_SWAP_EXTENT_INO2_SHORTFORM+ | Convert the second file fork back to
+inline format after the exchange completes.
+|=====
+
+*sxi_isize1*::
+The original size of the first file, in bytes.  This is zero if the
++XFS_SWAP_EXTENT_SET_SIZES+ flag is not set.
+
+*sxi_isize2*::
+The original size of the second file, in bytes.  This is zero if the
++XFS_SWAP_EXTENT_SET_SIZES+ flag is not set.
+
+[[SXD_Log_Item]]
+=== Completion of File Extent Swap
+
+The ``file extent swap done'' operation complements the ``file extent swap
+intent'' operation.  This second operation indicates that the update actually
+happened, so that log recovery needn't replay the update.  The SXD and the
+actual updates are typically found in a new transaction following the
+transaction in which the SXI was logged.  The completion has this format:
+
+[source, c]
+----
+struct xfs_sxd_log_format {
+     uint16_t                  sxd_type;
+     uint16_t                  sxd_size;
+     uint32_t                  __pad;
+     uint64_t                  sxd_sxi_id;
+};
+----
+
+*sxd_type*::
+The signature of an SXD operation, 0x1247.  This value is in host-endian order,
+not big-endian like the rest of XFS.
+
+*sxd_size*::
+Size of this log item.  Should be 1.
+
+*__pad*::
+Must be zero.
+
+*sxd_id*::
+A 64-bit number that binds the corresponding SXI log item to this SXD log item.
+
 [[Inode_Log_Item]]
 === Inode Updates
 
diff --git a/design/XFS_Filesystem_Structure/magic.asciidoc b/design/XFS_Filesystem_Structure/magic.asciidoc
index a343271a..613e50c0 100644
--- a/design/XFS_Filesystem_Structure/magic.asciidoc
+++ b/design/XFS_Filesystem_Structure/magic.asciidoc
@@ -73,6 +73,8 @@ are not aligned to blocks.
 | +XFS_LI_BUD+			| 0x1245        |       | xref:BUD_Log_Item[File Block Mapping Update Done]
 | +XFS_LI_ATTRI+		| 0x1246        |       | xref:ATTRI_Log_Item[Extended Attribute Update Intent]
 | +XFS_LI_ATTRD+		| 0x1247        |       | xref:ATTRD_Log_Item[Extended Attribute Update Done]
+| +XFS_LI_SXI+			| 0x1248        |       | xref:SXI_Log_Item[File Extent Swap Intent]
+| +XFS_LI_SXD+			| 0x1249        |       | xref:SXD_Log_Item[File Extent Swap Done]
 |=====
 
 = Theoretical Limits

[NYE PATCHRIVER 1/4] xfs: the rest of online repair part 1

[Darrick J. Wong]

Hi everyone,

In last year's NYE deluges, I mentioned that I wanted to get online
repair merged for the 2023 LTS kernel.  That goal was not attained, so
now I want to get this merged in time for the 2024 LTS kernel.

(Big thanks to Dave earlier for helping to get all 120 scrub fixes
merged; and Christoph more recently for doing the same for the first 30
patches of repair and a bunch of rt refactorings from the modernization
series.)

But seriously, folks, this is dragging on unnecessarily.  Either you all
need to step up and actually review the 55 patchsets and 458 patches
needed to get online repair done, or decide to let me merge it and deal
with the consequences, which I will.  The only part of this deluge that
changes the ondisk format are the swapext patches that add a new log
intent item type.  Everything else is guarded by Kconfig options and
won't destabilize the rest of the filesystem.  I haven't changed the
swapext log intent item format since 2021.  2+ years to get feedback is
dysfunctional.

In the meantime, lack of upstream merging means that I cannot start
wider testing of this code with the people who run (b)leading edge XFS
code; I cannot solicit user and customer feedback because they don't
have the code; and there's no way I can meaningfully prioritize
improvements to the code because **I cannot get feedback**.

Fuzz and stress testing of online repairs have been running well for two
years now.  As of this writing, online repair can fix more things than
offline repair, and the fsstress+repair long soak test has passed 300
million repairs with zero problems observed.

(For comparison, the long soak fsx test recently passed 110 billion file
operations, so online fsck has a ways to go...)

--D

[PATCHSET v29.0 01/28] xfs: live inode scans for online fsck

[Darrick J. Wong]

Hi all,

The design document discusses the need for a specialized inode scan
cursor to manage walking every file on a live filesystem to build
replacement metadata objects while receiving updates about the files
already scanned.  This series adds three pieces of infrastructure -- the
scan cursor, live hooks to deliver information about updates going
on in other parts of the filesystem, and then adds a batching mechanism
to amortize AGI lookups over a batch of inodes to improve performance.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=scrub-iscan
---
 fs/xfs/Kconfig       |   36 ++
 fs/xfs/Makefile      |    2 
 fs/xfs/scrub/iscan.c |  738 ++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/iscan.h |   81 +++++
 fs/xfs/scrub/trace.c |    1 
 fs/xfs/scrub/trace.h |  145 ++++++++++
 fs/xfs/xfs_hooks.c   |   94 ++++++
 fs/xfs/xfs_hooks.h   |   72 +++++
 fs/xfs/xfs_iwalk.c   |   13 -
 fs/xfs/xfs_linux.h   |    1 
 10 files changed, 1172 insertions(+), 11 deletions(-)
 create mode 100644 fs/xfs/scrub/iscan.c
 create mode 100644 fs/xfs/scrub/iscan.h
 create mode 100644 fs/xfs/xfs_hooks.c
 create mode 100644 fs/xfs/xfs_hooks.h

[PATCHSET v29.0 02/28] xfs: repair inode mode by scanning dirs

[Darrick J. Wong]

Hi all,

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.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=repair-inode-mode

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=repair-inode-mode
---
 fs/xfs/libxfs/xfs_da_format.h |   11 ++
 fs/xfs/libxfs/xfs_dir2.c      |    6 +
 fs/xfs/libxfs/xfs_dir2.h      |   10 ++
 fs/xfs/scrub/dir.c            |    4 -
 fs/xfs/scrub/inode_repair.c   |  236 ++++++++++++++++++++++++++++++++++++++++-
 fs/xfs/scrub/iscan.c          |   29 +++++
 fs/xfs/scrub/iscan.h          |    3 +
 fs/xfs/scrub/trace.c          |    1 
 fs/xfs/scrub/trace.h          |   49 +++++++++
 9 files changed, 341 insertions(+), 8 deletions(-)

[PATCHSET v29.0 03/28] xfs: online repair of quota counters

[Darrick J. Wong]

Hi all,

This series uses the inode scanner and live update hook functionality
introduced in the last patchset to implement quotacheck on a live
filesystem.  The quotacheck scrubber builds an incore copy of the
dquot resource usage counters and compares it to the live dquots to
report discrepancies.

If the user chooses to repair the quota counters, the repair function
visits each incore dquot to update the counts from the live information.
The live update hooks are key to keeping the incore copy up to date.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=repair-quotacheck

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=repair-quotacheck

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=repair-quotacheck
---
 fs/xfs/Makefile                  |    2 
 fs/xfs/libxfs/xfs_fs.h           |    4 
 fs/xfs/libxfs/xfs_health.h       |    4 
 fs/xfs/scrub/common.c            |   47 ++
 fs/xfs/scrub/common.h            |   11 
 fs/xfs/scrub/fscounters.c        |    2 
 fs/xfs/scrub/health.c            |    1 
 fs/xfs/scrub/quotacheck.c        |  862 ++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/quotacheck.h        |   76 +++
 fs/xfs/scrub/quotacheck_repair.c |  261 ++++++++++++
 fs/xfs/scrub/repair.c            |   46 ++
 fs/xfs/scrub/repair.h            |    5 
 fs/xfs/scrub/scrub.c             |    9 
 fs/xfs/scrub/scrub.h             |   10 
 fs/xfs/scrub/stats.c             |    1 
 fs/xfs/scrub/trace.h             |   30 +
 fs/xfs/scrub/xfarray.h           |   19 +
 fs/xfs/xfs_health.c              |    1 
 fs/xfs/xfs_inode.c               |   21 +
 fs/xfs/xfs_inode.h               |    2 
 fs/xfs/xfs_qm.c                  |   23 +
 fs/xfs/xfs_qm.h                  |   16 +
 fs/xfs/xfs_qm_bhv.c              |    1 
 fs/xfs/xfs_quota.h               |   45 ++
 fs/xfs/xfs_trans_dquot.c         |  158 +++++++
 25 files changed, 1632 insertions(+), 25 deletions(-)
 create mode 100644 fs/xfs/scrub/quotacheck.c
 create mode 100644 fs/xfs/scrub/quotacheck.h
 create mode 100644 fs/xfs/scrub/quotacheck_repair.c

[PATCHSET v29.0 04/28] xfs: online repair of file link counts

[Darrick J. Wong]

Hi all,

Now that we've created the infrastructure to perform live scans of every
file in the filesystem and the necessary hook infrastructure to observe
live updates, use it to scan directories to compute the correct link
counts for files in the filesystem, and reset those link counts.

This patchset creates a tailored readdir implementation for scrub
because the regular version has to cycle ILOCKs to copy information to
userspace.  We can't cycle the ILOCK during the nlink scan and we don't
need all the other VFS support code (maintaining a readdir cursor and
translating XFS structures to VFS structures and back) so it was easier
to duplicate the code.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=scrub-nlinks

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=scrub-nlinks

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=scrub-nlinks
---
 fs/xfs/Makefile              |    2 
 fs/xfs/libxfs/xfs_fs.h       |    4 
 fs/xfs/libxfs/xfs_health.h   |    4 
 fs/xfs/scrub/common.c        |    3 
 fs/xfs/scrub/common.h        |    1 
 fs/xfs/scrub/health.c        |    1 
 fs/xfs/scrub/nlinks.c        |  930 ++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/nlinks.h        |  102 +++++
 fs/xfs/scrub/nlinks_repair.c |  223 ++++++++++
 fs/xfs/scrub/repair.h        |    2 
 fs/xfs/scrub/scrub.c         |    9 
 fs/xfs/scrub/scrub.h         |    5 
 fs/xfs/scrub/stats.c         |    1 
 fs/xfs/scrub/trace.c         |    2 
 fs/xfs/scrub/trace.h         |  183 ++++++++
 fs/xfs/xfs_health.c          |    1 
 fs/xfs/xfs_inode.c           |  108 +++++
 fs/xfs/xfs_inode.h           |   31 +
 fs/xfs/xfs_mount.h           |    3 
 fs/xfs/xfs_super.c           |    2 
 fs/xfs/xfs_symlink.c         |    1 
 21 files changed, 1614 insertions(+), 4 deletions(-)
 create mode 100644 fs/xfs/scrub/nlinks.c
 create mode 100644 fs/xfs/scrub/nlinks.h
 create mode 100644 fs/xfs/scrub/nlinks_repair.c

[PATCHSET v29.0 05/28] xfs: report corruption to the health trackers

[Darrick J. Wong]

Hi all,

Any time that the runtime code thinks it has found corrupt metadata, it
should tell the health tracking subsystem that the corresponding part of
the filesystem is sick.  These reports come primarily from two places --
code that is reading a buffer that fails validation, and higher level
pieces that observe a conflict involving multiple buffers.  This
patchset uses automated scanning to update all such callsites with a
mark_sick call.

Doing this enables the health system to record problem observed at
runtime, which (for now) can prompt the sysadmin to run xfs_scrub, and
(later) may enable more targetted fixing of the filesystem.

Note: Earlier reviewers of this patchset suggested that the verifier
functions themselves should be responsible for calling _mark_sick.  In a
higher level language this would be easily accomplished with lambda
functions and closures.  For the kernel, however, we'd have to create
the necessary closures by hand, pass them to the buf_read calls, and
then implement necessary state tracking to detach the xfs_buf from the
closure at the necessary time.  This is far too much work and complexity
and will not be pursued further.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=corruption-health-reports

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=corruption-health-reports

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=corruption-health-reports
---
 fs/xfs/libxfs/xfs_ag.c          |    5 +
 fs/xfs/libxfs/xfs_alloc.c       |  105 ++++++++++++++++++++----
 fs/xfs/libxfs/xfs_attr_leaf.c   |    4 +
 fs/xfs/libxfs/xfs_attr_remote.c |   35 +++++---
 fs/xfs/libxfs/xfs_bmap.c        |  135 +++++++++++++++++++++++++++----
 fs/xfs/libxfs/xfs_btree.c       |   39 ++++++++-
 fs/xfs/libxfs/xfs_da_btree.c    |   37 +++++++-
 fs/xfs/libxfs/xfs_dir2.c        |    5 +
 fs/xfs/libxfs/xfs_dir2_block.c  |    2 
 fs/xfs/libxfs/xfs_dir2_data.c   |    3 +
 fs/xfs/libxfs/xfs_dir2_leaf.c   |    3 +
 fs/xfs/libxfs/xfs_dir2_node.c   |    7 ++
 fs/xfs/libxfs/xfs_health.h      |   35 +++++++-
 fs/xfs/libxfs/xfs_ialloc.c      |   57 +++++++++++--
 fs/xfs/libxfs/xfs_inode_buf.c   |   12 ++-
 fs/xfs/libxfs/xfs_inode_fork.c  |    8 ++
 fs/xfs/libxfs/xfs_refcount.c    |   43 +++++++++-
 fs/xfs/libxfs/xfs_rmap.c        |   83 ++++++++++++++++++-
 fs/xfs/libxfs/xfs_rtbitmap.c    |    9 ++
 fs/xfs/libxfs/xfs_sb.c          |    2 
 fs/xfs/scrub/health.c           |   20 +++--
 fs/xfs/scrub/refcount_repair.c  |    9 ++
 fs/xfs/xfs_attr_inactive.c      |    4 +
 fs/xfs/xfs_attr_list.c          |   18 +++-
 fs/xfs/xfs_dir2_readdir.c       |    6 +
 fs/xfs/xfs_discard.c            |    2 
 fs/xfs/xfs_dquot.c              |   30 +++++++
 fs/xfs/xfs_health.c             |  172 +++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_icache.c             |    9 ++
 fs/xfs/xfs_inode.c              |   16 +++-
 fs/xfs/xfs_iomap.c              |   15 +++
 fs/xfs/xfs_iwalk.c              |    5 +
 fs/xfs/xfs_mount.c              |    5 +
 fs/xfs/xfs_qm.c                 |    8 +-
 fs/xfs/xfs_reflink.c            |    6 +
 fs/xfs/xfs_rtalloc.c            |    6 +
 fs/xfs/xfs_symlink.c            |   17 +++-
 37 files changed, 867 insertions(+), 110 deletions(-)

[PATCHSET v29.0 06/28] xfs: indirect health reporting

[Darrick J. Wong]

Hi all,

This series enables the XFS health reporting infrastructure to remember
indirect health concerns when resources are scarce.  For example, if a
scrub notices that there's something wrong with an inode's metadata but
memory reclaim needs to free the incore inode, we want to record in the
perag data the fact that there was some inode somewhere with an error.
The perag structures never go away.

The first two patches in this series set that up, and the third one
provides a means for xfs_scrub to tell the kernel that it can forget the
indirect problem report.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=indirect-health-reporting

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=indirect-health-reporting
---
 fs/xfs/libxfs/xfs_fs.h        |    4 ++
 fs/xfs/libxfs/xfs_health.h    |   47 +++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_inode_buf.c |    2 +
 fs/xfs/scrub/health.c         |   76 ++++++++++++++++++++++++++++++++++++++++-
 fs/xfs/scrub/health.h         |    1 +
 fs/xfs/scrub/repair.c         |    1 +
 fs/xfs/scrub/scrub.c          |    6 +++
 fs/xfs/scrub/trace.h          |    4 ++
 fs/xfs/xfs_health.c           |   27 ++++++++++-----
 fs/xfs/xfs_inode.c            |   35 +++++++++++++++++++
 fs/xfs/xfs_trace.h            |    1 +
 11 files changed, 191 insertions(+), 13 deletions(-)

[PATCHSET v29.0 07/28] xfs: online repair for fs summary counters

[Darrick J. Wong]

Hi all,

A longstanding deficiency in the online fs summary counter scrubbing
code is that it hasn't any means to quiesce the incore percpu counters
while it's running.  There is no way to coordinate with other threads
are reserving or freeing free space simultaneously, which leads to false
error reports.  Right now, if the discrepancy is large, we just sort of
shrug and bail out with an incomplete flag, but this is lame.

For repair activity, we actually /do/ need to stabilize the counters to
get an accurate reading and install it in the percpu counter.  To
improve the former and enable the latter, allow the fscounters online
fsck code to perform an exclusive mini-freeze on the filesystem.  The
exclusivity prevents userspace from thawing while we're running, and the
mini-freeze means that we don't wait for the log to quiesce, which will
make both speedier.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=repair-fscounters

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=repair-fscounters
---
 fs/xfs/Makefile                  |    1 +
 fs/xfs/scrub/fscounters.c        |   27 +++++++-------
 fs/xfs/scrub/fscounters.h        |   20 +++++++++++
 fs/xfs/scrub/fscounters_repair.c |   72 ++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/repair.h            |    2 +
 fs/xfs/scrub/scrub.c             |    2 +
 fs/xfs/scrub/trace.c             |    1 +
 fs/xfs/scrub/trace.h             |   21 +++++++++--
 8 files changed, 128 insertions(+), 18 deletions(-)
 create mode 100644 fs/xfs/scrub/fscounters.h
 create mode 100644 fs/xfs/scrub/fscounters_repair.c

[PATCHSET v29.0 08/28] xfs: support in-memory btrees

[Darrick J. Wong]

Hi all,

Online repair of the reverse-mapping btrees presens some unique
challenges.  To construct a new reverse mapping btree, we must scan the
entire filesystem, but we cannot afford to quiesce the entire filesystem
for the potentially lengthy scan.

For rmap btrees, therefore, we relax our requirements of totally atomic
repairs.  Instead, repairs will scan all inodes, construct a new reverse
mapping dataset, format a new btree, and commit it before anyone trips
over the corruption.  This is exactly the same strategy as was used in
the quotacheck and nlink scanners.

Unfortunately, the xfarray cannot perform key-based lookups and is
therefore unsuitable for supporting live updates.  Luckily, we already a
data structure that maintains an indexed rmap recordset -- the existing
rmap btree code!  Hence we port the existing btree and buffer target
code to be able to create a btree using the xfile we developed earlier.
Live hooks keep the in-memory btree up to date for any resources that
have already been scanned.

This approach is not maximally memory efficient, but we can use the same
rmap code that we do everywhere else, which provides improved stability
without growing the code base even more.  Note that in-memory btree
blocks are always page sized.

This patchset modifies the kernel xfs buffer cache to be capable of
using a xfile (aka a shmem file) as a backing device.  It then augments
the btree code to support creating btree cursors with buffers that come
from a buftarg other than the data device (namely an xfile-backed
buftarg).  For the userspace xfs buffer cache, we instead use a memfd or
an O_TMPFILE file as a backing device.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=in-memory-btrees

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=in-memory-btrees
---
 fs/xfs/Kconfig                     |    8 
 fs/xfs/Makefile                    |    2 
 fs/xfs/libxfs/xfs_ag.c             |    6 
 fs/xfs/libxfs/xfs_ag.h             |    4 
 fs/xfs/libxfs/xfs_btree.c          |  173 ++++++-
 fs/xfs/libxfs/xfs_btree.h          |   17 +
 fs/xfs/libxfs/xfs_btree_mem.h      |  128 ++++++
 fs/xfs/libxfs/xfs_refcount_btree.c |    4 
 fs/xfs/libxfs/xfs_rmap_btree.c     |    4 
 fs/xfs/scrub/bitmap.c              |   28 +
 fs/xfs/scrub/bitmap.h              |    3 
 fs/xfs/scrub/scrub.c               |    5 
 fs/xfs/scrub/scrub.h               |    3 
 fs/xfs/scrub/trace.c               |   11 
 fs/xfs/scrub/trace.h               |  109 +++++
 fs/xfs/scrub/xfbtree.c             |  837 ++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/xfbtree.h             |   63 +++
 fs/xfs/scrub/xfile.c               |  181 ++++++++
 fs/xfs/scrub/xfile.h               |   66 +++
 fs/xfs/xfs_aops.c                  |    5 
 fs/xfs/xfs_bmap_util.c             |    8 
 fs/xfs/xfs_buf.c                   |  203 ++++++---
 fs/xfs/xfs_buf.h                   |   79 +++
 fs/xfs/xfs_buf_xfile.c             |   97 ++++
 fs/xfs/xfs_buf_xfile.h             |   20 +
 fs/xfs/xfs_discard.c               |    9 
 fs/xfs/xfs_file.c                  |    6 
 fs/xfs/xfs_health.c                |    3 
 fs/xfs/xfs_ioctl.c                 |    3 
 fs/xfs/xfs_iomap.c                 |    4 
 fs/xfs/xfs_log.c                   |    4 
 fs/xfs/xfs_log_recover.c           |    3 
 fs/xfs/xfs_mount.h                 |    3 
 fs/xfs/xfs_trace.c                 |    3 
 fs/xfs/xfs_trace.h                 |   85 +++-
 fs/xfs/xfs_trans.h                 |    1 
 fs/xfs/xfs_trans_buf.c             |   42 ++
 37 files changed, 2105 insertions(+), 125 deletions(-)
 create mode 100644 fs/xfs/libxfs/xfs_btree_mem.h
 create mode 100644 fs/xfs/scrub/xfbtree.c
 create mode 100644 fs/xfs/scrub/xfbtree.h
 create mode 100644 fs/xfs/xfs_buf_xfile.c
 create mode 100644 fs/xfs/xfs_buf_xfile.h

[PATCHSET v29.0 09/28] xfs: online repair of rmap btrees

[Darrick J. Wong]

Hi all,

We have now constructed the four tools that we need to scan the
filesystem looking for reverse mappings: an inode scanner, hooks to
receive live updates from other writer threads, the ability to construct
btrees in memory, and a btree bulk loader.

This series glues those three together, enabling us to scan the
filesystem for mappings and keep it up to date while other writers run,
and then commit the new btree to disk atomically.

To reduce the size of each patch, the functionality is left disabled
until the end of the series and broken up into three patches: one to
create the mechanics of scanning the filesystem, a second to transition
to in-memory btrees, and a third to set up the live hooks.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=repair-rmap-btree

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=repair-rmap-btree

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=repair-rmap-btree
---
 fs/xfs/Makefile                |    1 
 fs/xfs/libxfs/xfs_ag.c         |    1 
 fs/xfs/libxfs/xfs_ag.h         |    3 
 fs/xfs/libxfs/xfs_bmap.c       |   49 +
 fs/xfs/libxfs/xfs_bmap.h       |    8 
 fs/xfs/libxfs/xfs_inode_fork.c |    9 
 fs/xfs/libxfs/xfs_inode_fork.h |    1 
 fs/xfs/libxfs/xfs_rmap.c       |  190 +++-
 fs/xfs/libxfs/xfs_rmap.h       |   30 +
 fs/xfs/libxfs/xfs_rmap_btree.c |  136 +++
 fs/xfs/libxfs/xfs_rmap_btree.h |    9 
 fs/xfs/scrub/agb_bitmap.h      |    5 
 fs/xfs/scrub/bitmap.c          |   14 
 fs/xfs/scrub/bitmap.h          |    2 
 fs/xfs/scrub/bmap.c            |    2 
 fs/xfs/scrub/common.c          |    7 
 fs/xfs/scrub/common.h          |    1 
 fs/xfs/scrub/newbt.c           |   12 
 fs/xfs/scrub/newbt.h           |    7 
 fs/xfs/scrub/reap.c            |    2 
 fs/xfs/scrub/repair.c          |   59 +
 fs/xfs/scrub/repair.h          |   12 
 fs/xfs/scrub/rmap.c            |   11 
 fs/xfs/scrub/rmap_repair.c     | 1726 ++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/scrub.c           |    6 
 fs/xfs/scrub/scrub.h           |    4 
 fs/xfs/scrub/trace.c           |    1 
 fs/xfs/scrub/trace.h           |   80 ++
 28 files changed, 2319 insertions(+), 69 deletions(-)
 create mode 100644 fs/xfs/scrub/rmap_repair.c

[PATCHSET v29.0 10/28] xfs: move btree geometry to ops struct

[Darrick J. Wong]

Hi all,

This patchset prepares the generic btree code to allow for the creation
of new btree types outside of libxfs.  The end goal here is for online
fsck to be able to create its own in-memory btrees that will be used to
improve the performance (and reduce the memory requirements of) the
refcount btree.

To enable this, I decided that the btree ops structure is the ideal
place to encode all of the geometry information about a btree. The btree
ops struture already contains the buffer ops (and hence the btree block
magic numbers) as well as the key and record sizes, so it doesn't seem
all that farfetched to encode the XFS_BTREE_ flags that determine the
geometry (ROOT_IN_INODE, LONG_PTRS, etc).

The rest of the patchset cleans up the btree functions that initialize
btree blocks and btree buffers.  The bulk of this work is to replace
btree geometry related function call arguments with a single pointer to
the ops structure, and then clean up everything else around that.  As a
side effect, we rename the functions.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=btree-geometry-in-ops

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=btree-geometry-in-ops
---
 fs/xfs/libxfs/xfs_ag.c             |   33 +++++++----------
 fs/xfs/libxfs/xfs_ag.h             |    2 +
 fs/xfs/libxfs/xfs_alloc_btree.c    |   21 ++++-------
 fs/xfs/libxfs/xfs_bmap.c           |    9 +----
 fs/xfs/libxfs/xfs_bmap_btree.c     |   14 ++-----
 fs/xfs/libxfs/xfs_btree.c          |   70 +++++++++++++++++++-----------------
 fs/xfs/libxfs/xfs_btree.h          |   36 ++++++++-----------
 fs/xfs/libxfs/xfs_btree_mem.h      |    9 -----
 fs/xfs/libxfs/xfs_btree_staging.c  |    6 +--
 fs/xfs/libxfs/xfs_ialloc_btree.c   |   17 ++++-----
 fs/xfs/libxfs/xfs_refcount_btree.c |    8 ++--
 fs/xfs/libxfs/xfs_rmap_btree.c     |   16 ++++----
 fs/xfs/libxfs/xfs_shared.h         |    9 +++++
 fs/xfs/scrub/trace.h               |   10 ++---
 fs/xfs/scrub/xfbtree.c             |   16 +++-----
 15 files changed, 118 insertions(+), 158 deletions(-)

[PATCHSET v29.0 11/28] xfs: reduce refcount repair memory usage

[Darrick J. Wong]

Hi all,

The refcountbt repair code has serious memory usage problems when the
block sharing factor of the filesystem is very high.  This can happen if
a deduplication tool has been run against the filesystem, or if the fs
stores reflinked VM images that have been aging for a long time.

Recall that the original reference counting algorithm walks the reverse
mapping records of the filesystem to generate reference counts.  For any
given block in the AG, the rmap bag structure contains the all rmap
records that cover that block; the refcount is the size of that bag.

For online repair, the bag doesn't need the owner, offset, or state flag
information, so it discards those.  This halves the record size, but the
bag structure still stores one excerpted record for each reverse
mapping.  If the sharing count is high, this will use a LOT of memory
storing redundant records.  In the extreme case, 100k mappings to the
same piece of space will consume 100k*16 bytes = 1.6M of memory.

For offline repair, the bag stores the owner values so that we know
which inodes need to be marked as being reflink inodes.  If a
deduplication tool has been run and there are many blocks within a file
pointing to the same physical space, this will stll use a lot of memory
to store redundant records.

The solution to this problem is to deduplicate the bag records when
possible by adding a reference count to the bag record, and changing the
bag add function to detect an existing record to bump the refcount.  In
the above example, the 100k mappings will now use 24 bytes of memory.
These lookups can be done efficiently with a btree, so we create a new
refcount bag btree type (inside of online repair).  This is why we
refactored the btree code in the previous patchset.

The btree conversion also dramatically reduces the runtime of the
refcount generation algorithm, because the code to delete all bag
records that end at a given agblock now only has to delete one record
instead of (using the example above) 100k records.  As an added benefit,
record deletion now gives back the unused xfile space, which it did not
do previously.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=repair-refcount-scalability

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=repair-refcount-scalability
---
 fs/xfs/Makefile                    |    2 
 fs/xfs/libxfs/xfs_alloc_btree.c    |    2 
 fs/xfs/libxfs/xfs_bmap_btree.c     |    1 
 fs/xfs/libxfs/xfs_btree.c          |   24 --
 fs/xfs/libxfs/xfs_btree.h          |    4 
 fs/xfs/libxfs/xfs_ialloc_btree.c   |    2 
 fs/xfs/libxfs/xfs_refcount_btree.c |    1 
 fs/xfs/libxfs/xfs_rmap_btree.c     |    2 
 fs/xfs/libxfs/xfs_types.h          |    6 -
 fs/xfs/scrub/rcbag.c               |  331 ++++++++++++++++++++++++++++++++
 fs/xfs/scrub/rcbag.h               |   28 +++
 fs/xfs/scrub/rcbag_btree.c         |  372 ++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/rcbag_btree.h         |   83 ++++++++
 fs/xfs/scrub/refcount.c            |   12 +
 fs/xfs/scrub/refcount_repair.c     |  164 ++++++----------
 fs/xfs/scrub/repair.h              |    2 
 fs/xfs/scrub/trace.h               |    1 
 fs/xfs/xfs_super.c                 |   10 +
 fs/xfs/xfs_trace.h                 |    1 
 19 files changed, 917 insertions(+), 131 deletions(-)
 create mode 100644 fs/xfs/scrub/rcbag.c
 create mode 100644 fs/xfs/scrub/rcbag.h
 create mode 100644 fs/xfs/scrub/rcbag_btree.c
 create mode 100644 fs/xfs/scrub/rcbag_btree.h

[PATCHSET v29.0 12/28] xfs: bmap log intent cleanups

[Darrick J. Wong]

Hi all,

The next major target of online repair are metadata that are persisted
in blocks mapped by a file fork.  In other words, we want to repair
directories, extended attributes, symbolic links, and the realtime free
space information.  For file-based metadata, we assume that the space
metadata is correct, which enables repair to construct new versions of
the metadata in a temporary file.  We then need to swap the file fork
mappings of the two files atomically.  With this patchset, we begin
constructing such a facility based on the existing bmap log items and a
new extent swap log item.

This series cleans up a few parts of the file block mapping log intent
code before we start adding support for realtime bmap intents.  Most of
it involves cleaning up tracepoints so that more of the data extraction
logic ends up in the tracepoint code and not the tracepoint call site,
which should reduce overhead further when tracepoints are disabled.
There is also a change to pass bmap intents all the way back to the bmap
code instead of unboxing the intent values and re-boxing them after the
_finish_one function completes.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=bmap-intent-cleanups

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=bmap-intent-cleanups
---
 fs/xfs/libxfs/xfs_bmap.c |   21 +---
 fs/xfs/libxfs/xfs_bmap.h |    7 +
 fs/xfs/xfs_attr_item.c   |   11 +-
 fs/xfs/xfs_bmap_item.c   |   95 ++++++++--------
 fs/xfs/xfs_bmap_item.h   |    4 +
 fs/xfs/xfs_trace.c       |    1 
 fs/xfs/xfs_trace.h       |  267 +++++++++++++++++++++++++++++-----------------
 7 files changed, 237 insertions(+), 169 deletions(-)

[PATCHSET v29.0 13/28] xfs: widen BUI formats to support realtime

[Darrick J. Wong]

Hi all,

Atomic extent swapping (and later, reverse mapping and reflink) on the
realtime device needs to be able to defer file mapping and extent
freeing work in much the same manner as is required on the data volume.
Make the BUI log items operate on rt extents in preparation for atomic
swapping and realtime rmap.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=realtime-bmap-intents

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=realtime-bmap-intents
---
 fs/xfs/libxfs/xfs_bmap.c       |    4 ++--
 fs/xfs/libxfs/xfs_log_format.h |    4 +++-
 fs/xfs/xfs_bmap_item.c         |   17 +++++++++++++++++
 fs/xfs/xfs_trace.h             |   23 ++++++++++++++++++-----
 4 files changed, 40 insertions(+), 8 deletions(-)

[PATCHSET v29.0 14/28] xfs: support attrfork and unwritten BUIs

[Darrick J. Wong]

Hi all,

In preparation for atomic extent swapping and the online repair
functionality that wants atomic extent swaps, enhance the BUI code so
that we can support deferred work on the extended attribute fork and on
unwritten extents.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=expand-bmap-intent-usage

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=expand-bmap-intent-usage
---
 fs/xfs/libxfs/xfs_bmap.c |   49 ++++++++++++++++++++--------------------------
 fs/xfs/libxfs/xfs_bmap.h |    4 ++--
 fs/xfs/xfs_bmap_util.c   |    8 ++++----
 fs/xfs/xfs_reflink.c     |    8 ++++----
 4 files changed, 31 insertions(+), 38 deletions(-)

[PATCHSET v29.0 15/28] xfs: clean up symbolic link code

[Darrick J. Wong]

Hi all,

This series cleans up a few bits of the symbolic link code as needed for
future projects.  Online repair requires the ability to commit fixed
fork-based filesystem metadata such as directories, xattrs, and symbolic
links atomically, so we need to rearrange the symlink code before we
land the atomic extent swapping.

Accomplish this by moving the remote symlink target block code and
declarations to xfs_symlink_remote.[ch].

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=symlink-cleanups

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=symlink-cleanups
---
 fs/xfs/libxfs/xfs_bmap.c           |    1 
 fs/xfs/libxfs/xfs_inode_fork.c     |    1 
 fs/xfs/libxfs/xfs_shared.h         |   13 ---
 fs/xfs/libxfs/xfs_symlink_remote.c |  155 ++++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_symlink_remote.h |   26 ++++++
 fs/xfs/scrub/inode_repair.c        |    1 
 fs/xfs/scrub/symlink.c             |    3 -
 fs/xfs/xfs_symlink.c               |  145 ++--------------------------------
 fs/xfs/xfs_symlink.h               |    1 
 9 files changed, 192 insertions(+), 154 deletions(-)
 create mode 100644 fs/xfs/libxfs/xfs_symlink_remote.h

[PATCHSET v29.0 16/28] xfs: atomic file updates

[Darrick J. Wong]

Hi all,

This series creates a new FIEXCHANGE_RANGE system call to exchange
ranges of bytes between two files atomically.  This new functionality
enables data storage programs to stage and commit file updates such that
reader programs will see either the old contents or the new contents in
their entirety, with no chance of torn writes.  A successful call
completion guarantees that the new contents will be seen even if the
system fails.

The ability to swap extent mappings between files in this manner is
critical to supporting online filesystem repair, which is built upon the
strategy of constructing a clean copy of a damaged structure and
committing the new structure into the metadata file atomically.

User programs will be able to update files atomically by opening an
O_TMPFILE, reflinking the source file to it, making whatever updates
they want to make, and exchange the relevant ranges of the temp file
with the original file.  If the updates are aligned with the file block
size, a new (since v2) flag provides for exchanging only the written
areas.  Callers can arrange for the update to be rejected if the
original file has been changed.

The intent behind this new userspace functionality is to enable atomic
rewrites of arbitrary parts of individual files.  For years, application
programmers wanting to ensure the atomicity of a file update had to
write the changes to a new file in the same directory, fsync the new
file, rename the new file on top of the old filename, and then fsync the
directory.  People get it wrong all the time, and $fs hacks abound.
Here is the proposed manual page:

IOCTL-XFS-EXCHANGE-RANGE(2System Calls ManuIOCTL-XFS-EXCHANGE-RANGE(2)

NAME
       ioctl_xfs_exchange_range  -  exchange  the contents of parts of
       two files

SYNOPSIS
       #include <sys/ioctl.h>
       #include <xfs/xfs_fs_staging.h>

       int   ioctl(int   file2_fd,   XFS_IOC_EXCHANGE_RANGE,    struct
       xfs_exch_range *arg);

DESCRIPTION
       Given  a  range  of bytes in a first file file1_fd and a second
       range of bytes in a second file  file2_fd,  this  ioctl(2)  ex‐
       changes the contents of the two ranges.

       Exchanges  are  atomic  with  regards to concurrent file opera‐
       tions, so no userspace-level locks need to be taken  to  obtain
       consistent  results.  Implementations must guarantee that read‐
       ers see either the old contents or the new  contents  in  their
       entirety, even if the system fails.

       The exchange parameters are conveyed in a structure of the fol‐
       lowing form:

           struct xfs_exch_range {
               __s64    file1_fd;
               __s64    file1_offset;
               __s64    file2_offset;
               __s64    length;

               __u64    flags;

               __s64    file2_ino;
               __s64    file2_mtime;
               __s64    file2_ctime;
               __s32    file2_mtime_nsec;
               __s32    file2_ctime_nsec;

               __u64    pad[6];
           };

       The field pad must be zero.

       The fields file1_fd, file1_offset, and length define the  first
       range of bytes to be exchanged.

       The fields file2_fd, file2_offset, and length define the second
       range of bytes to be exchanged.

       Both files must be from the same filesystem mount.  If the  two
       file  descriptors represent the same file, the byte ranges must
       not overlap.  Most  disk-based  filesystems  require  that  the
       starts  of  both ranges must be aligned to the file block size.
       If this is the case, the ends of the ranges  must  also  be  so
       aligned unless the XFS_EXCH_RANGE_TO_EOF flag is set.

       The field flags control the behavior of the exchange operation.

           XFS_EXCH_RANGE_FILE2_FRESH
                  Check  the  freshness  of file2_fd after locking the
                  file but before exchanging the contents.   The  sup‐
                  plied  file2_ino field must match file2's inode num‐
                  ber, and the supplied file2_mtime, file2_mtime_nsec,
                  file2_ctime,  and file2_ctime_nsec fields must match
                  the modification time and change time of file2.   If
                  they do not match, EBUSY will be returned.

           XFS_EXCH_RANGE_TO_EOF
                  Ignore  the length parameter.  All bytes in file1_fd
                  from file1_offset to EOF are moved to file2_fd,  and
                  file2's  size is set to (file2_offset+(file1_length-
                  file1_offset)).  Meanwhile, all bytes in file2  from
                  file2_offset  to  EOF are moved to file1 and file1's
                  size   is   set   to    (file1_offset+(file2_length-
                  file2_offset)).   This option is not compatible with
                  XFS_EXCH_RANGE_FULL_FILES.

           XFS_EXCH_RANGE_FSYNC
                  Ensure that all modified in-core data in  both  file
                  ranges  and  all  metadata updates pertaining to the
                  exchange operation are flushed to persistent storage
                  before  the  call  returns.  Opening either file de‐
                  scriptor with O_SYNC or O_DSYNC will have  the  same
                  effect.

           XFS_EXCH_RANGE_FILE1_WRITTEN
                  Only  exchange sub-ranges of file1_fd that are known
                  to contain data  written  by  application  software.
                  Each  sub-range  may  be  expanded (both upwards and
                  downwards) to align with the file  allocation  unit.
                  For files on the data device, this is one filesystem
                  block.  For files on the realtime  device,  this  is
                  the realtime extent size.  This facility can be used
                  to implement fast atomic  scatter-gather  writes  of
                  any  complexity for software-defined storage targets
                  if all writes are aligned  to  the  file  allocation
                  unit.

           XFS_EXCH_RANGE_DRY_RUN
                  Check  the parameters and the feasibility of the op‐
                  eration, but do not change anything.

           XFS_EXCH_RANGE_COMMIT
                  This     flag     is      a      combination      of
                  XFS_EXCH_RANGE_FILE2_FRESH   |  XFS_EXCH_RANGE_FSYNC
                  and can be used to commit  changes  to  file2_fd  to
                  persistent  storage  if  and  only  if file2 has not
                  changed.

           XFS_EXCH_RANGE_FULL_FILES
                  Require that file1_offset and file2_offset are zero,
                  and  that  the  length  field matches the lengths of
                  both files.  If not, EDOM will  be  returned.   This
                  option is not compatible with XFS_EXCH_RANGE_TO_EOF.

           XFS_EXCH_RANGE_NONATOMIC
                  This  flag  relaxes the requirement that readers see
                  only the old contents or the new contents  in  their
                  entirety.   If  the system fails before all modified
                  in-core data and metadata updates are  persisted  to
                  disk,  the contents of both file ranges after recov‐
                  ery are not defined and may be a mix of both.

                  Do not use this flag unless  the  contents  of  both
                  ranges  are  known  to be identical and there are no
                  other writers.

RETURN VALUE
       On error, -1 is returned, and errno is set to indicate the  er‐
       ror.

ERRORS
       Error  codes can be one of, but are not limited to, the follow‐
       ing:

       EBADF  file1_fd is not open for reading and writing or is  open
              for  append-only  writes;  or  file2_fd  is not open for
              reading and writing or is open for append-only writes.

       EBUSY  The inode number and timestamps supplied  do  not  match
              file2_fd   and  XFS_EXCH_RANGE_FILE2_FRESH  was  set  in
              flags.

       EDOM   The ranges do not cover the entirety of both files,  and
              XFS_EXCH_RANGE_FULL_FILES was set in flags.

       EINVAL The  parameters  are  not correct for these files.  This
              error can also appear if either file  descriptor  repre‐
              sents  a device, FIFO, or socket.  Disk filesystems gen‐
              erally require the offset and  length  arguments  to  be
              aligned to the fundamental block sizes of both files.

       EIO    An I/O error occurred.

       EISDIR One of the files is a directory.

       ENOMEM The  kernel  was unable to allocate sufficient memory to
              perform the operation.

       ENOSPC There is not enough free space  in  the  filesystem  ex‐
              change the contents safely.

       EOPNOTSUPP
              The filesystem does not support exchanging bytes between
              the two files.

       EPERM  file1_fd or file2_fd are immutable.

       ETXTBSY
              One of the files is a swap file.

       EUCLEAN
              The filesystem is corrupt.

       EXDEV  file1_fd and  file2_fd  are  not  on  the  same  mounted
              filesystem.

CONFORMING TO
       This API is XFS-specific.

USE CASES
       Three use cases are imagined for this system call.

       The  first  is a filesystem defragmenter, which copies the con‐
       tents of a file into another file and wishes  to  exchange  the
       space  mappings  of  the  two files, provided that the original
       file has not changed.  The flags NONATOMIC and FILE2_FRESH  are
       recommended for this application.

       The  second is a data storage program that wants to commit non-
       contiguous updates to a file atomically.  This can be  done  by
       creating a temporary file, calling FICLONE(2) to share the con‐
       tents, and staging the updates into the temporary file.  Either
       of  the  FULL_FILES or TO_EOF flags are recommended, along with
       FSYNC.  Depending on  the  application's  locking  design,  the
       flags FILE2_FRESH or COMMIT may be applicable here.  The tempo‐
       rary file can be deleted or punched out afterwards.

       The third is a software-defined storage host (e.g. a disk juke‐
       box)  which  implements an atomic scatter-gather write command.
       Provided the exported disk's logical  block  size  matches  the
       file's  allocation  unit  size,  this can be done by creating a
       temporary file and writing the data at the appropriate offsets.
       It  is  recommended that the temporary file be truncated to the
       size of the regular file before any writes are  staged  to  the
       temporary  file  to avoid issues with zeroing during EOF exten‐
       sion.  Use this call with the FILE1_WRITTEN  flag  to  exchange
       only  the  file  allocation  units involved in the emulated de‐
       vice's write command.  The use of the FSYNC flag is recommended
       here.  The temporary file should be deleted or punched out com‐
       pletely before being reused to stage another write.

NOTES
       Some filesystems may limit the amount of data or the number  of
       extents that can be exchanged in a single call.

SEE ALSO
       ioctl(2)

The reference implementation in XFS creates a new log incompat feature
and log intent items to track high level progress of swapping ranges of
two files and finish interrupted work if the system goes down.  Sample
code can be found in the corresponding changes to xfs_io to exercise the
use case mentioned above.

Note that this function is /not/ the O_DIRECT atomic file writes concept
that has also been floating around for years.  It is also not the
RWF_ATOMIC patchset that has been shared.  This RFC is constructed
entirely in software, which means that there are no limitations other
than the general filesystem limits.

As a side note, the original motivation behind the kernel functionality
is online repair of file-based metadata.  The atomic file swap is
implemented as an atomic inode fork swap, which means that we can
implement online reconstruction of extended attributes and directories
by building a new one in another inode and atomically swap the contents.

Subsequent patchsets adapt the online filesystem repair code to use
atomic extent swapping.  This enables repair functions to construct a
clean copy of a directory, xattr information, symbolic links, realtime
bitmaps, and realtime summary information in a temporary inode.  If this
completes successfully, the new contents can be swapped atomically into
the inode being repaired.  This is essential to avoid making corruption
problems worse if the system goes down in the middle of running repair.

This patchset also ports the old XFS extent swap ioctl interface to use
the new extent swap code.

For userspace, this series also includes the userspace pieces needed to
test the new functionality, and a sample implementation of atomic file
updates.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=atomic-file-updates

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=atomic-file-updates

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=atomic-file-updates

xfsdocs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-documentation.git/log/?h=atomic-file-updates
---
 fs/read_write.c                    |    2 
 fs/remap_range.c                   |    4 
 fs/xfs/Makefile                    |    3 
 fs/xfs/libxfs/xfs_bmap.h           |    2 
 fs/xfs/libxfs/xfs_defer.c          |    6 
 fs/xfs/libxfs/xfs_defer.h          |    2 
 fs/xfs/libxfs/xfs_errortag.h       |    4 
 fs/xfs/libxfs/xfs_format.h         |   20 -
 fs/xfs/libxfs/xfs_fs.h             |    4 
 fs/xfs/libxfs/xfs_fs_staging.h     |  107 +++
 fs/xfs/libxfs/xfs_log_format.h     |   83 ++
 fs/xfs/libxfs/xfs_log_recover.h    |    2 
 fs/xfs/libxfs/xfs_sb.c             |    3 
 fs/xfs/libxfs/xfs_swapext.c        | 1318 ++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_swapext.h        |  223 ++++++
 fs/xfs/libxfs/xfs_symlink_remote.c |   47 +
 fs/xfs/libxfs/xfs_symlink_remote.h |    1 
 fs/xfs/libxfs/xfs_trans_space.h    |    4 
 fs/xfs/xfs_bmap_util.c             |  732 ++++---------------
 fs/xfs/xfs_bmap_util.h             |   10 
 fs/xfs/xfs_error.c                 |    3 
 fs/xfs/xfs_file.c                  |   88 --
 fs/xfs/xfs_file.h                  |   15 
 fs/xfs/xfs_inode.c                 |   75 ++
 fs/xfs/xfs_inode.h                 |   12 
 fs/xfs/xfs_ioctl.c                 |  133 ++-
 fs/xfs/xfs_ioctl.h                 |    4 
 fs/xfs/xfs_ioctl32.c               |   11 
 fs/xfs/xfs_iops.c                  |    1 
 fs/xfs/xfs_iops.h                  |    7 
 fs/xfs/xfs_linux.h                 |    6 
 fs/xfs/xfs_log.c                   |   47 +
 fs/xfs/xfs_log.h                   |   10 
 fs/xfs/xfs_log_priv.h              |    3 
 fs/xfs/xfs_log_recover.c           |    5 
 fs/xfs/xfs_mount.c                 |   11 
 fs/xfs/xfs_mount.h                 |    7 
 fs/xfs/xfs_super.c                 |   19 
 fs/xfs/xfs_swapext_item.c          |  616 ++++++++++++++++
 fs/xfs/xfs_swapext_item.h          |   60 ++
 fs/xfs/xfs_symlink.c               |   49 -
 fs/xfs/xfs_trace.c                 |    2 
 fs/xfs/xfs_trace.h                 |  359 +++++++++
 fs/xfs/xfs_xattr.c                 |    6 
 fs/xfs/xfs_xchgrange.c             | 1393 ++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_xchgrange.h             |   56 +
 include/linux/fs.h                 |    1 
 47 files changed, 4727 insertions(+), 849 deletions(-)
 create mode 100644 fs/xfs/libxfs/xfs_fs_staging.h
 create mode 100644 fs/xfs/libxfs/xfs_swapext.c
 create mode 100644 fs/xfs/libxfs/xfs_swapext.h
 create mode 100644 fs/xfs/xfs_file.h
 create mode 100644 fs/xfs/xfs_swapext_item.c
 create mode 100644 fs/xfs/xfs_swapext_item.h
 create mode 100644 fs/xfs/xfs_xchgrange.c
 create mode 100644 fs/xfs/xfs_xchgrange.h

[PATCHSET v29.0 17/28] xfs: create temporary files for online repair

[Darrick J. Wong]

Hi all,

As mentioned earlier, the repair strategy for file-based metadata is to
build a new copy in a temporary file and swap the file fork mappings
with the metadata inode.  We've built the atomic extent swap facility,
so now we need to build a facility for handling private temporary files.

The first step is to teach the filesystem to ignore the temporary files.
We'll mark them as PRIVATE in the VFS so that the kernel security
modules will leave it alone.  The second step is to add the online
repair code the ability to create a temporary file and reap extents from
the temporary file after the extent swap.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=repair-tempfiles
---
 fs/xfs/Makefile         |    1 
 fs/xfs/scrub/parent.c   |    2 
 fs/xfs/scrub/reap.c     |  445 +++++++++++++++++++++++++++++++++++++++++++++--
 fs/xfs/scrub/reap.h     |   21 ++
 fs/xfs/scrub/scrub.c    |    3 
 fs/xfs/scrub/scrub.h    |    4 
 fs/xfs/scrub/tempfile.c |  251 +++++++++++++++++++++++++++
 fs/xfs/scrub/tempfile.h |   28 +++
 fs/xfs/scrub/trace.h    |   96 ++++++++++
 fs/xfs/xfs_export.c     |    2 
 fs/xfs/xfs_inode.c      |    3 
 fs/xfs/xfs_inode.h      |    2 
 fs/xfs/xfs_itable.c     |    8 +
 13 files changed, 840 insertions(+), 26 deletions(-)
 create mode 100644 fs/xfs/scrub/tempfile.c
 create mode 100644 fs/xfs/scrub/tempfile.h

[PATCHSET v29.0 18/28] xfs: online repair of realtime summaries

[Darrick J. Wong]

Hi all,

We now have all the infrastructure we need to repair file metadata.
We'll begin with the realtime summary file, because it is the least
complex data structure.  To support this we need to add three more
pieces to the temporary file code from the previous patchset --
preallocating space in the temp file, formatting metadata into that
space and writing the blocks to disk, and swapping the fork mappings
atomically.

After that, the actual reconstruction of the realtime summary
information is pretty simple, since we can simply write the incore
copy computed by the rtsummary scrubber to the temporary file, swap the
contents, and reap the old blocks.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=repair-rtsummary

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=repair-rtsummary

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=repair-rtsummary
---
 fs/xfs/Makefile                 |    1 
 fs/xfs/scrub/common.c           |    1 
 fs/xfs/scrub/repair.h           |    3 
 fs/xfs/scrub/rtsummary.c        |   33 ++-
 fs/xfs/scrub/rtsummary.h        |   37 ++++
 fs/xfs/scrub/rtsummary_repair.c |  177 +++++++++++++++++
 fs/xfs/scrub/scrub.c            |   14 +
 fs/xfs/scrub/scrub.h            |    7 +
 fs/xfs/scrub/tempfile.c         |  401 +++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/tempfile.h         |   15 +
 fs/xfs/scrub/tempswap.h         |   21 ++
 fs/xfs/scrub/trace.h            |   40 ++++
 12 files changed, 731 insertions(+), 19 deletions(-)
 create mode 100644 fs/xfs/scrub/rtsummary.h
 create mode 100644 fs/xfs/scrub/rtsummary_repair.c
 create mode 100644 fs/xfs/scrub/tempswap.h

[PATCHSET v29.0 19/28] xfs: set and validate dir/attr block owners

[Darrick J. Wong]

Hi all,

There are a couple of significant changes that need to be made to the
directory and xattr code before we can support online repairs of those
data structures.

The first change is because online repair is designed to use libxfs to
create a replacement dir/xattr structure in a temporary file, and use
atomic extent swapping to commit the corrected structure.  To avoid the
performance hit of walking every block of the new structure to rewrite
the owner number before the swap, we instead change libxfs to allow
callers of the dir and xattr code the ability to set an explicit owner
number to be written into the header fields of any new blocks that are
created.  For regular operation this will be the directory inode number.

The second change is to update the dir/xattr code to actually *check*
the owner number in each block that is read off the disk, since we don't
currently do that.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=dirattr-validate-owners

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=dirattr-validate-owners
---
 fs/xfs/libxfs/xfs_attr.c        |   10 +-
 fs/xfs/libxfs/xfs_attr_leaf.c   |   59 +++++++++++---
 fs/xfs/libxfs/xfs_attr_leaf.h   |    4 +
 fs/xfs/libxfs/xfs_attr_remote.c |   13 +--
 fs/xfs/libxfs/xfs_bmap.c        |    1 
 fs/xfs/libxfs/xfs_da_btree.c    |  168 +++++++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_da_btree.h    |    3 +
 fs/xfs/libxfs/xfs_dir2.c        |    5 +
 fs/xfs/libxfs/xfs_dir2.h        |    4 +
 fs/xfs/libxfs/xfs_dir2_block.c  |   44 ++++++----
 fs/xfs/libxfs/xfs_dir2_data.c   |   17 ++--
 fs/xfs/libxfs/xfs_dir2_leaf.c   |   99 ++++++++++++++++++-----
 fs/xfs/libxfs/xfs_dir2_node.c   |   44 ++++++----
 fs/xfs/libxfs/xfs_dir2_priv.h   |   11 +--
 fs/xfs/libxfs/xfs_swapext.c     |    7 +-
 fs/xfs/scrub/attr.c             |    1 
 fs/xfs/scrub/dabtree.c          |    8 ++
 fs/xfs/scrub/dir.c              |   23 +++--
 fs/xfs/scrub/readdir.c          |    6 +
 fs/xfs/xfs_acl.c                |    2 
 fs/xfs/xfs_attr_item.c          |    1 
 fs/xfs/xfs_attr_list.c          |   35 +++++++-
 fs/xfs/xfs_dir2_readdir.c       |    6 +
 fs/xfs/xfs_ioctl.c              |    2 
 fs/xfs/xfs_iops.c               |    1 
 fs/xfs/xfs_trace.h              |    7 +-
 fs/xfs/xfs_xattr.c              |    2 
 27 files changed, 464 insertions(+), 119 deletions(-)

[PATCHSET v29.0 20/28] xfs: online repair of extended attributes

[Darrick J. Wong]

Hi all,

This series employs atomic extent swapping to enable safe reconstruction
of extended attribute data attached to a file.  Because xattrs do not
have any redundant information to draw off of, we can at best salvage
as much data as we can and build a new structure.

Rebuilding an extended attribute structure consists of these three
steps:

First, we walk the existing attributes to salvage as many of them as we
can, by adding them as new attributes attached to the repair tempfile.
We need to add a new xfile-based data structure to hold blobs of
arbitrary length to stage the xattr names and values.

Second, we write the salvaged attributes to a temporary file, and use
atomic extent swaps to exchange the entire attribute fork between the
two files.

Finally, we reap the old xattr blocks (which are now in the temporary
file) as carefully as we can.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=repair-xattrs

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=repair-xattrs

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=repair-xattrs
---
 fs/xfs/Makefile               |    3 
 fs/xfs/libxfs/xfs_attr.c      |    2 
 fs/xfs/libxfs/xfs_attr.h      |    2 
 fs/xfs/libxfs/xfs_da_format.h |    5 
 fs/xfs/libxfs/xfs_swapext.c   |    2 
 fs/xfs/libxfs/xfs_swapext.h   |    1 
 fs/xfs/scrub/attr.c           |  158 +++--
 fs/xfs/scrub/attr.h           |    7 
 fs/xfs/scrub/attr_repair.c    | 1203 +++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/attr_repair.h    |   11 
 fs/xfs/scrub/dab_bitmap.h     |   37 +
 fs/xfs/scrub/dabtree.c        |   16 +
 fs/xfs/scrub/dabtree.h        |    3 
 fs/xfs/scrub/listxattr.c      |  310 +++++++++++
 fs/xfs/scrub/listxattr.h      |   17 +
 fs/xfs/scrub/repair.c         |   46 ++
 fs/xfs/scrub/repair.h         |    6 
 fs/xfs/scrub/scrub.c          |    2 
 fs/xfs/scrub/tempfile.c       |  203 +++++++
 fs/xfs/scrub/tempfile.h       |    3 
 fs/xfs/scrub/tempswap.h       |    2 
 fs/xfs/scrub/trace.h          |   84 +++
 fs/xfs/scrub/xfarray.c        |   17 +
 fs/xfs/scrub/xfarray.h        |    2 
 fs/xfs/scrub/xfblob.c         |  168 ++++++
 fs/xfs/scrub/xfblob.h         |   26 +
 fs/xfs/scrub/xfile.h          |   12 
 fs/xfs/xfs_buf.c              |    3 
 fs/xfs/xfs_trace.h            |    2 
 29 files changed, 2270 insertions(+), 83 deletions(-)
 create mode 100644 fs/xfs/scrub/attr_repair.c
 create mode 100644 fs/xfs/scrub/attr_repair.h
 create mode 100644 fs/xfs/scrub/dab_bitmap.h
 create mode 100644 fs/xfs/scrub/listxattr.c
 create mode 100644 fs/xfs/scrub/listxattr.h
 create mode 100644 fs/xfs/scrub/xfblob.c
 create mode 100644 fs/xfs/scrub/xfblob.h

[PATCHSET v29.0 21/28] xfs: online repair of inode unlinked state

[Darrick J. Wong]

Hi all,

This series adds some logic to the inode scrubbers so that they can
detect and deal with consistency errors between the link count and the
per-inode unlinked list state.  The helpers needed to do this are
presented here because they are a prequisite for rebuildng directories,
since we need to get a rebuilt non-empty directory off the unlinked
list.

Note that this patchset does not provide comprehensive reconstruction of
the AGI unlinked list; that is coming in a subsequent patchset.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=repair-unlinked-inode-state
---
 fs/xfs/scrub/inode.c         |   19 ++++++++++++++++++
 fs/xfs/scrub/inode_repair.c  |   45 ++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/nlinks_repair.c |   42 +++++++++++++++++++++++++++++++--------
 fs/xfs/xfs_inode.c           |    5 +----
 fs/xfs/xfs_inode.h           |    2 ++
 5 files changed, 100 insertions(+), 13 deletions(-)

[PATCHSET v29.0 22/28] xfs: online repair of directories

[Darrick J. Wong]

Hi all,

This series employs atomic extent swapping to enable safe reconstruction
of directory data.  For now, XFS does not support reverse directory
links (aka parent pointers), so we can only salvage the dirents of a
directory and construct a new structure.

Directory repair therefore consists of five main parts:

First, we walk the existing directory to salvage as many entries as we
can, by adding them as new directory entries to the repair temp dir.

Second, we validate the parent pointer found in the directory.  If one
was not found, we scan the entire filesystem looking for a potential
parent.

Third, we use atomic extent swaps to exchange the entire data fork
between the two directories.

Fourth, we reap the old directory blocks as carefully as we can.

To wrap up the directory repair code, we need to add to the regular
filesystem the ability to free all the data fork blocks in a directory.
This does not change anything with normal directories, since they must
still unlink and shrink one entry at a time.  However, this will
facilitate freeing of partially-inactivated temporary directories during
log recovery.

The second half of this patchset implements repairs for the dotdot
entries of directories.  For now there is only rudimentary support for
this, because there are no directory parent pointers, so the best we can
do is scanning the filesystem and the VFS dcache for answers.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=repair-dirs

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=repair-dirs

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=repair-dirs
---
 fs/xfs/Makefile              |    3 
 fs/xfs/scrub/dir.c           |    9 
 fs/xfs/scrub/dir_repair.c    | 1399 ++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/findparent.c    |  451 ++++++++++++++
 fs/xfs/scrub/findparent.h    |   50 ++
 fs/xfs/scrub/inode_repair.c  |    5 
 fs/xfs/scrub/iscan.c         |   18 +
 fs/xfs/scrub/iscan.h         |    1 
 fs/xfs/scrub/nlinks.c        |   23 +
 fs/xfs/scrub/nlinks_repair.c |    9 
 fs/xfs/scrub/parent.c        |   14 
 fs/xfs/scrub/parent_repair.c |  234 +++++++
 fs/xfs/scrub/readdir.c       |    7 
 fs/xfs/scrub/repair.c        |    1 
 fs/xfs/scrub/repair.h        |    8 
 fs/xfs/scrub/scrub.c         |    4 
 fs/xfs/scrub/tempfile.c      |   13 
 fs/xfs/scrub/tempfile.h      |    2 
 fs/xfs/scrub/trace.h         |  115 +++
 fs/xfs/xfs_inode.c           |   51 ++
 20 files changed, 2413 insertions(+), 4 deletions(-)
 create mode 100644 fs/xfs/scrub/dir_repair.c
 create mode 100644 fs/xfs/scrub/findparent.c
 create mode 100644 fs/xfs/scrub/findparent.h
 create mode 100644 fs/xfs/scrub/parent_repair.c

[PATCHSET v29.0 23/28] xfs: move orphan files to lost and found

[Darrick J. Wong]

Hi all,

Orphaned files are defined to be files with nonzero ondisk link count
but no observable parent directory.  This series enables online repair
to reparent orphaned files into the filesystem directory tree, and wires
up this reparenting ability into the directory, file link count, and
parent pointer repair functions.  This is how we fix files with positive
link count that are not reachable through the directory tree.

This patch will also create the orphanage directory (lost+found) if it
is not present.  In contrast to xfs_repair, we follow e2fsck in creating
the lost+found without group or other-owner access to avoid accidental
disclosure of files that were previously hidden by an 0700 directory.
That's silly security, but people have been known to do it.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=repair-orphanage
---
 .../filesystems/xfs-online-fsck-design.rst         |   20 -
 fs/xfs/Makefile                                    |    1 
 fs/xfs/scrub/dir_repair.c                          |  130 ++++
 fs/xfs/scrub/nlinks.c                              |   11 
 fs/xfs/scrub/nlinks.h                              |    6 
 fs/xfs/scrub/nlinks_repair.c                       |  124 ++++
 fs/xfs/scrub/orphanage.c                           |  587 ++++++++++++++++++++
 fs/xfs/scrub/orphanage.h                           |   75 +++
 fs/xfs/scrub/parent_repair.c                       |   98 +++
 fs/xfs/scrub/repair.h                              |    2 
 fs/xfs/scrub/scrub.c                               |    2 
 fs/xfs/scrub/scrub.h                               |    4 
 fs/xfs/scrub/trace.c                               |    1 
 fs/xfs/scrub/trace.h                               |   96 +++
 fs/xfs/xfs_inode.c                                 |    6 
 fs/xfs/xfs_inode.h                                 |    1 
 16 files changed, 1130 insertions(+), 34 deletions(-)
 create mode 100644 fs/xfs/scrub/orphanage.c
 create mode 100644 fs/xfs/scrub/orphanage.h

[PATCHSET v29.0 24/28] xfs: online repair of symbolic links

[Darrick J. Wong]

Hi all,

The sole patch in this set adds the ability to repair the target buffer
of a symbolic link, using the same salvage, rebuild, and swap strategy
used everywhere else.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=repair-symlink

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=repair-symlink
---
 fs/xfs/Makefile                    |    1 
 fs/xfs/libxfs/xfs_bmap.c           |   11 -
 fs/xfs/libxfs/xfs_bmap.h           |    6 
 fs/xfs/libxfs/xfs_symlink_remote.c |    9 -
 fs/xfs/libxfs/xfs_symlink_remote.h |   22 +-
 fs/xfs/scrub/repair.h              |    8 +
 fs/xfs/scrub/scrub.c               |    2 
 fs/xfs/scrub/symlink.c             |   13 +
 fs/xfs/scrub/symlink_repair.c      |  488 ++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/tempfile.c            |    5 
 fs/xfs/scrub/trace.h               |   46 +++
 11 files changed, 596 insertions(+), 15 deletions(-)
 create mode 100644 fs/xfs/scrub/symlink_repair.c

[PATCHSET v29.0 25/28] xfs: online fsck of iunlink buckets

[Darrick J. Wong]

Hi all,

This series enhances the AGI scrub code to check the unlinked inode
bucket lists for errors, and fixes them if necessary.  Now that iunlink
pointer updates are virtual log items, we can batch updates pretty
efficiently in the logging code.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=repair-iunlink

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=repair-iunlink
---
 fs/xfs/scrub/agheader.c        |   40 ++
 fs/xfs/scrub/agheader_repair.c |  879 ++++++++++++++++++++++++++++++++++++++--
 fs/xfs/scrub/agino_bitmap.h    |   49 ++
 fs/xfs/scrub/trace.h           |  255 ++++++++++++
 fs/xfs/xfs_inode.c             |    2 
 fs/xfs/xfs_inode.h             |    1 
 6 files changed, 1179 insertions(+), 47 deletions(-)
 create mode 100644 fs/xfs/scrub/agino_bitmap.h

[PATCHSET v29.0 26/28] xfs: cache xfile pages for better performance

[Darrick J. Wong]

Hi all,

This patchset improves the performance of xfile-backed btrees by
teaching the buffer cache to directly map pages from the xfile.  It also
speeds up xfarray operations substantially by implementing a small page
cache to avoid repeated kmap/kunmap calls.  Collectively, these can
reduce the runtime of online repair functions by twenty percent or so.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=xfile-page-caching

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=xfile-page-caching
---
 fs/xfs/libxfs/xfs_btree_mem.h  |    6 +
 fs/xfs/libxfs/xfs_rmap_btree.c |    1 
 fs/xfs/scrub/rcbag_btree.c     |    1 
 fs/xfs/scrub/trace.h           |   44 ++++++
 fs/xfs/scrub/xfbtree.c         |   23 +++
 fs/xfs/scrub/xfile.c           |  307 ++++++++++++++++++++++++++--------------
 fs/xfs/scrub/xfile.h           |   23 +++
 fs/xfs/xfs_buf.c               |  116 ++++++++++++---
 fs/xfs/xfs_buf.h               |   16 ++
 fs/xfs/xfs_buf_xfile.c         |  173 +++++++++++++++++++++++
 fs/xfs/xfs_buf_xfile.h         |   11 +
 11 files changed, 584 insertions(+), 137 deletions(-)

[PATCHSET v29.0 27/28] xfs: inode-related repair fixes

[Darrick J. Wong]

Hi all,

While doing QA of the online fsck code, I made a few observations:
First, nobody was checking that the di_onlink field is actually zero;
Second, that allocating a temporary file for repairs can fail (and
thus bring down the entire fs) if the inode cluster is corrupt; and
Third, that file link counts do not pin at ~0U to prevent integer
overflows.  Fourth, the x{chk,rep}_metadata_inode_fork functions
should be subclassing the main scrub context, not modifying the
parent's setup willy-nilly.

This scattered patchset fixes those three problems.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=inode-repair-improvements

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=inode-repair-improvements
---
 fs/xfs/libxfs/xfs_format.h    |    6 ++++
 fs/xfs/libxfs/xfs_ialloc.c    |   40 ++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_inode_buf.c |    8 +++++
 fs/xfs/scrub/common.c         |   23 ++------------
 fs/xfs/scrub/dir_repair.c     |   11 ++-----
 fs/xfs/scrub/inode_repair.c   |   12 +++++++
 fs/xfs/scrub/nlinks.c         |    4 ++
 fs/xfs/scrub/nlinks_repair.c  |    8 +----
 fs/xfs/scrub/repair.c         |   67 ++++++++---------------------------------
 fs/xfs/scrub/scrub.c          |   63 +++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/scrub.h          |   11 +++++++
 fs/xfs/xfs_inode.c            |   33 +++++++++++++-------
 12 files changed, 187 insertions(+), 99 deletions(-)

[PATCHSET v29.0 28/28] xfs: less heavy locks during fstrim

[Darrick J. Wong]

Hi all,

Congratulations!  You have made it to the final patchset of the main
online fsck feature!  This patchset fixes some stalling behavior that I
observed when running FITRIM against large flash-based filesystems with
very heavily fragmented free space data.  In summary -- the current
fstrim implementation optimizes for trimming the largest free extents
first, and holds the AGF lock for the duration of the operation.  This
is great if fstrim is being run as a foreground process by a sysadmin.

For xfs_scrub, however, this isn't so good -- we don't really want to
block on one huge kernel call while reporting no progress information.
We don't want to hold the AGF so long that background processes stall.
These problems are easily fixable by issuing smaller FITRIM calls, but
there's still the problem of walking the entire cntbt.  To solve that
second problem, we introduce a new sub-AG FITRIM implementation.  To
solve the first problem, make it relax the AGF periodically.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=discard-relax-locks
---
 fs/xfs/xfs_discard.c |  164 +++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 162 insertions(+), 2 deletions(-)

[PATCHSET v29.0 01/40] xfs_scrub: fix licensing and copyright notices

[Darrick J. Wong]

Hi all,

Fix various attribution problems in the xfs_scrub source code, such as
the author's contact information, out of date SPDX tags, and a rough
estimate of when the feature was under heavy development.  The most
egregious parts are the files that are missing license information
completely.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=scrub-fix-legalese

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=scrub-fix-legalese
---
 scrub/Makefile                   |    2 +-
 scrub/common.c                   |    6 +++---
 scrub/common.h                   |    6 +++---
 scrub/counter.c                  |    6 +++---
 scrub/counter.h                  |    6 +++---
 scrub/descr.c                    |    4 ++--
 scrub/descr.h                    |    4 ++--
 scrub/disk.c                     |    6 +++---
 scrub/disk.h                     |    6 +++---
 scrub/filemap.c                  |    6 +++---
 scrub/filemap.h                  |    6 +++---
 scrub/fscounters.c               |    6 +++---
 scrub/fscounters.h               |    6 +++---
 scrub/inodes.c                   |    6 +++---
 scrub/inodes.h                   |    6 +++---
 scrub/phase1.c                   |    6 +++---
 scrub/phase2.c                   |    6 +++---
 scrub/phase3.c                   |    6 +++---
 scrub/phase4.c                   |    6 +++---
 scrub/phase5.c                   |    6 +++---
 scrub/phase6.c                   |    6 +++---
 scrub/phase7.c                   |    6 +++---
 scrub/progress.c                 |    6 +++---
 scrub/progress.h                 |    6 +++---
 scrub/read_verify.c              |    6 +++---
 scrub/read_verify.h              |    6 +++---
 scrub/repair.c                   |    6 +++---
 scrub/repair.h                   |    6 +++---
 scrub/scrub.c                    |    6 +++---
 scrub/scrub.h                    |    6 +++---
 scrub/spacemap.c                 |    6 +++---
 scrub/spacemap.h                 |    6 +++---
 scrub/unicrash.c                 |    6 +++---
 scrub/unicrash.h                 |    6 +++---
 scrub/vfs.c                      |    6 +++---
 scrub/vfs.h                      |    6 +++---
 scrub/xfs_scrub.c                |    6 +++---
 scrub/xfs_scrub.h                |    6 +++---
 scrub/xfs_scrub@.service.in      |    5 +++++
 scrub/xfs_scrub_all.cron.in      |    5 +++++
 scrub/xfs_scrub_all.in           |    6 +++---
 scrub/xfs_scrub_all.service.in   |    5 +++++
 scrub/xfs_scrub_all.timer        |    5 +++++
 scrub/xfs_scrub_fail             |    5 +++++
 scrub/xfs_scrub_fail@.service.in |    5 +++++
 45 files changed, 143 insertions(+), 113 deletions(-)

[PATCHSET 02/40] mkfs: scale shards on ssds

[Darrick J. Wong]

Hi all,

For a long time, the maintainers have had a gut feeling that we could
optimize performance of XFS filesystems on non-mechanical storage by
scaling the number of allocation groups to be a multiple of the CPU
count.

With modern ~2022 hardware, it is common for systems to have more than
four CPU cores and non-striped SSDs ranging in size from 256GB to 4TB.
The default mkfs geometry still defaults to 4 AGs regardless of core
count, which was settled on in the age of spinning rust.

This patchset adds a different computation for AG count and log size
that is based entirely on a desired level of concurrency.  If we detect
storage that is non-rotational (or the sysadmin provides a CLI option),
then we will try to match the AG count to the CPU count to minimize AGF
contention and make the log large enough to minimize grant head
contention.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=mkfs-scale-geo-on-ssds

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=mkfs-scale-geo-on-ssds
---
 man/man8/mkfs.xfs.8.in |   46 +++++++++
 mkfs/xfs_mkfs.c        |  254 +++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 293 insertions(+), 7 deletions(-)

[PATCHSET v29.0 03/40] xfs_scrub: scan metadata files in parallel

[Darrick J. Wong]

Hi all,

At this point, we need to clean up the libfrog and xfs_scrub code a
little bit.  First, correct some of the weird naming and organizing
choices I made in libfrog for scrub types and fs summary counter scans.
Second, break out metadata file scans as a separate group, and teach
xfs_scrub that it can ask the kernel to scan them in parallel.  On
filesystems with quota or realtime volumes, this can speed up that part
significantly.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=scrub-metafile-parallel
---
 io/scrub.c      |   13 +++--
 libfrog/scrub.c |   51 ++++++++++-----------
 libfrog/scrub.h |   24 ++++------
 scrub/phase2.c  |  135 ++++++++++++++++++++++++++++++++++++++++++-------------
 scrub/phase4.c  |    2 -
 scrub/phase7.c  |    4 +-
 scrub/scrub.c   |   75 ++++++++++++++++++-------------
 scrub/scrub.h   |    6 ++
 8 files changed, 194 insertions(+), 116 deletions(-)

[PATCHSET v29.0 04/40] xfs: repair inode mode by scanning dirs

[Darrick J. Wong]

Hi all,

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.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=repair-inode-mode

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=repair-inode-mode
---
 libxfs/xfs_da_format.h |   11 +++++++++++
 libxfs/xfs_dir2.c      |    6 ++++++
 libxfs/xfs_dir2.h      |   10 ++++++++++
 repair/phase6.c        |    4 ----
 4 files changed, 27 insertions(+), 4 deletions(-)

[PATCHSET v29.0 05/40] xfsprogs: online repair of quota counters

[Darrick J. Wong]

Hi all,

This series uses the inode scanner and live update hook functionality
introduced in the last patchset to implement quotacheck on a live
filesystem.  The quotacheck scrubber builds an incore copy of the
dquot resource usage counters and compares it to the live dquots to
report discrepancies.

If the user chooses to repair the quota counters, the repair function
visits each incore dquot to update the counts from the live information.
The live update hooks are key to keeping the incore copy up to date.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=repair-quotacheck

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=repair-quotacheck

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=repair-quotacheck
---
 io/scrub.c                      |    1 +
 libfrog/scrub.c                 |    5 +++++
 libfrog/scrub.h                 |    1 +
 libxfs/xfs_fs.h                 |    4 +++-
 libxfs/xfs_health.h             |    4 +++-
 man/man2/ioctl_xfs_fsgeometry.2 |    3 +++
 scrub/phase4.c                  |   17 ++++++++++++++++
 scrub/phase5.c                  |   22 +++++++++++++++++++-
 scrub/repair.c                  |    3 +++
 scrub/scrub.c                   |   42 +++++++++++++++++++++++++++++++++++++++
 scrub/scrub.h                   |    2 ++
 scrub/xfs_scrub.h               |    1 +
 spaceman/health.c               |    4 ++++
 13 files changed, 105 insertions(+), 4 deletions(-)

[PATCHSET v29.0 06/40] xfs_repair: rebuild inode fork mappings

[Darrick J. Wong]

Hi all,

Add the ability to regenerate inode fork mappings if the rmapbt
otherwise looks ok.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=repair-rebuild-forks
---
 include/xfs_trans.h      |    2 
 libxfs/libxfs_api_defs.h |   16 +
 libxfs/trans.c           |   48 +++
 repair/Makefile          |    2 
 repair/agbtree.c         |   24 +
 repair/bmap_repair.c     |  749 ++++++++++++++++++++++++++++++++++++++++++++++
 repair/bmap_repair.h     |   13 +
 repair/bulkload.c        |  260 +++++++++++++++-
 repair/bulkload.h        |   34 ++
 repair/dino_chunks.c     |    5 
 repair/dinode.c          |  142 ++++++---
 repair/dinode.h          |    7 
 repair/phase5.c          |    2 
 repair/rmap.c            |    2 
 repair/rmap.h            |    1 
 15 files changed, 1227 insertions(+), 80 deletions(-)
 create mode 100644 repair/bmap_repair.c
 create mode 100644 repair/bmap_repair.h

[PATCHSET 07/40] xfs_repair: support more than 4 billion records

[Darrick J. Wong]

Hi all,

I started looking through all the places where XFS has to deal with the
rc_refcount attribute of refcount records, and noticed that offline
repair doesn't handle the situation where there are more than 2^32
reverse mappings in an AG, or that there are more than 2^32 owners of a
particular piece of AG space.  I've estimated that it would take several
months to produce a filesystem with this many records, but we really
ought to do better at handling them than crashing or (worse) not
crashing and writing out corrupt btrees due to integer truncation.

Once I started using the bmap_inflate debugger command to create extreme
reflink scenarios, I noticed that the memory usage of xfs_repair was
astronomical.  This I observed to be due to the fact that it allocates a
single huge block mapping array for all files on the system, even though
it only uses that array for data and attr forks that map metadata blocks
(e.g. directories, xattrs, symlinks) and does not use it for regular
data files.

So I got rid of the 2^31-1 limits on the block map array and turned off
the block mapping for regular data files.  This doesn't answer the
question of what to do if there are a lot of extents, but it kicks the
can down the road until someone creates a maximally sized xattr tree,
which so far nobody's ever stuck to long enough to complain about.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=repair-support-4bn-records
---
 db/Makefile       |    4 
 db/bmap_inflate.c |  564 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 db/command.c      |    1 
 db/command.h      |    1 
 man/man8/xfs_db.8 |   23 ++
 repair/bmap.c     |   26 +-
 repair/bmap.h     |    9 -
 repair/dinode.c   |   12 +
 repair/dir2.c     |    2 
 repair/incore.c   |    9 +
 repair/rmap.c     |   26 +-
 repair/rmap.h     |    4 
 repair/slab.c     |   36 ++-
 repair/slab.h     |   36 ++-
 14 files changed, 680 insertions(+), 73 deletions(-)
 create mode 100644 db/bmap_inflate.c

[PATCHSET v29.0 08/40] xfsprogs: online repair of file link counts

[Darrick J. Wong]

Hi all,

Now that we've created the infrastructure to perform live scans of every
file in the filesystem and the necessary hook infrastructure to observe
live updates, use it to scan directories to compute the correct link
counts for files in the filesystem, and reset those link counts.

This patchset creates a tailored readdir implementation for scrub
because the regular version has to cycle ILOCKs to copy information to
userspace.  We can't cycle the ILOCK during the nlink scan and we don't
need all the other VFS support code (maintaining a readdir cursor and
translating XFS structures to VFS structures and back) so it was easier
to duplicate the code.


If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=scrub-nlinks

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=scrub-nlinks

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=scrub-nlinks
---
 libfrog/scrub.c                     |    5 +
 libxfs/xfs_fs.h                     |    4 +
 libxfs/xfs_health.h                 |    4 +
 man/man2/ioctl_xfs_scrub_metadata.2 |    4 +
 scrub/phase5.c                      |  150 ++++++++++++++++++++++++++++++++---
 scrub/scrub.c                       |   18 ++--
 scrub/scrub.h                       |    1 
 spaceman/health.c                   |    4 +
 8 files changed, 164 insertions(+), 26 deletions(-)

[PATCHSET v29.0 09/40] xfsprogs: report corruption to the health trackers

[Darrick J. Wong]

Hi all,

Any time that the runtime code thinks it has found corrupt metadata, it
should tell the health tracking subsystem that the corresponding part of
the filesystem is sick.  These reports come primarily from two places --
code that is reading a buffer that fails validation, and higher level
pieces that observe a conflict involving multiple buffers.  This
patchset uses automated scanning to update all such callsites with a
mark_sick call.

Doing this enables the health system to record problem observed at
runtime, which (for now) can prompt the sysadmin to run xfs_scrub, and
(later) may enable more targetted fixing of the filesystem.

Note: Earlier reviewers of this patchset suggested that the verifier
functions themselves should be responsible for calling _mark_sick.  In a
higher level language this would be easily accomplished with lambda
functions and closures.  For the kernel, however, we'd have to create
the necessary closures by hand, pass them to the buf_read calls, and
then implement necessary state tracking to detach the xfs_buf from the
closure at the necessary time.  This is far too much work and complexity
and will not be pursued further.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=corruption-health-reports

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=corruption-health-reports

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=corruption-health-reports
---
 libxfs/util.c            |   10 +++
 libxfs/xfs_ag.c          |    5 +-
 libxfs/xfs_alloc.c       |  105 ++++++++++++++++++++++++++++++------
 libxfs/xfs_attr_leaf.c   |    4 +
 libxfs/xfs_attr_remote.c |   35 +++++++-----
 libxfs/xfs_bmap.c        |  135 +++++++++++++++++++++++++++++++++++++++++-----
 libxfs/xfs_btree.c       |   39 ++++++++++++-
 libxfs/xfs_da_btree.c    |   37 +++++++++++--
 libxfs/xfs_dir2.c        |    5 +-
 libxfs/xfs_dir2_block.c  |    2 +
 libxfs/xfs_dir2_data.c   |    3 +
 libxfs/xfs_dir2_leaf.c   |    3 +
 libxfs/xfs_dir2_node.c   |    7 ++
 libxfs/xfs_health.h      |   35 +++++++++++-
 libxfs/xfs_ialloc.c      |   57 ++++++++++++++++---
 libxfs/xfs_inode_buf.c   |   12 +++-
 libxfs/xfs_inode_fork.c  |    8 +++
 libxfs/xfs_refcount.c    |   43 ++++++++++++++-
 libxfs/xfs_rmap.c        |   83 +++++++++++++++++++++++++++-
 libxfs/xfs_rtbitmap.c    |    9 +++
 libxfs/xfs_sb.c          |    2 +
 21 files changed, 559 insertions(+), 80 deletions(-)

[PATCHSET v29.0 10/40] xfsprogs: indirect health reporting

[Darrick J. Wong]

Hi all,

This series enables the XFS health reporting infrastructure to remember
indirect health concerns when resources are scarce.  For example, if a
scrub notices that there's something wrong with an inode's metadata but
memory reclaim needs to free the incore inode, we want to record in the
perag data the fact that there was some inode somewhere with an error.
The perag structures never go away.

The first two patches in this series set that up, and the third one
provides a means for xfs_scrub to tell the kernel that it can forget the
indirect problem report.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=indirect-health-reporting

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=indirect-health-reporting
---
 libfrog/scrub.c                     |    5 ++++
 libxfs/xfs_fs.h                     |    4 ++-
 libxfs/xfs_health.h                 |   47 +++++++++++++++++++++++++++++++++++
 libxfs/xfs_inode_buf.c              |    2 +
 man/man2/ioctl_xfs_scrub_metadata.2 |    6 ++++
 scrub/phase1.c                      |   38 ++++++++++++++++++++++++++++
 scrub/repair.c                      |   15 +++++++++++
 scrub/repair.h                      |    1 +
 scrub/scrub.c                       |   16 +++++++-----
 scrub/scrub.h                       |    1 +
 spaceman/health.c                   |    4 +++
 11 files changed, 131 insertions(+), 8 deletions(-)

[PATCHSET v29.0 11/40] xfsprogs: support in-memory btrees

[Darrick J. Wong]

Hi all,

Online repair of the reverse-mapping btrees presens some unique
challenges.  To construct a new reverse mapping btree, we must scan the
entire filesystem, but we cannot afford to quiesce the entire filesystem
for the potentially lengthy scan.

For rmap btrees, therefore, we relax our requirements of totally atomic
repairs.  Instead, repairs will scan all inodes, construct a new reverse
mapping dataset, format a new btree, and commit it before anyone trips
over the corruption.  This is exactly the same strategy as was used in
the quotacheck and nlink scanners.

Unfortunately, the xfarray cannot perform key-based lookups and is
therefore unsuitable for supporting live updates.  Luckily, we already a
data structure that maintains an indexed rmap recordset -- the existing
rmap btree code!  Hence we port the existing btree and buffer target
code to be able to create a btree using the xfile we developed earlier.
Live hooks keep the in-memory btree up to date for any resources that
have already been scanned.

This approach is not maximally memory efficient, but we can use the same
rmap code that we do everywhere else, which provides improved stability
without growing the code base even more.  Note that in-memory btree
blocks are always page sized.

This patchset modifies the kernel xfs buffer cache to be capable of
using a xfile (aka a shmem file) as a backing device.  It then augments
the btree code to support creating btree cursors with buffers that come
from a buftarg other than the data device (namely an xfile-backed
buftarg).  For the userspace xfs buffer cache, we instead use a memfd or
an O_TMPFILE file as a backing device.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=in-memory-btrees

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=in-memory-btrees
---
 configure.ac                |    4 
 include/builddefs.in        |    4 
 include/libxfs.h            |    2 
 include/xfs_mount.h         |   10 +
 include/xfs_trace.h         |   15 +
 include/xfs_trans.h         |    1 
 libfrog/bitmap.c            |   64 +++
 libfrog/bitmap.h            |    3 
 libxfs/Makefile             |   18 +
 libxfs/init.c               |  121 +++++--
 libxfs/libxfs_io.h          |   23 +
 libxfs/libxfs_priv.h        |    5 
 libxfs/rdwr.c               |  109 +++++-
 libxfs/trans.c              |   40 ++
 libxfs/xfbtree.c            |  797 +++++++++++++++++++++++++++++++++++++++++++
 libxfs/xfbtree.h            |   57 +++
 libxfs/xfile.c              |  299 ++++++++++++++++
 libxfs/xfile.h              |  108 ++++++
 libxfs/xfs_ag.c             |    6 
 libxfs/xfs_ag.h             |    4 
 libxfs/xfs_btree.c          |  173 ++++++++-
 libxfs/xfs_btree.h          |   17 +
 libxfs/xfs_btree_mem.h      |  128 +++++++
 libxfs/xfs_refcount_btree.c |    4 
 libxfs/xfs_rmap_btree.c     |    4 
 m4/package_libcdev.m4       |   66 ++++
 mkfs/xfs_mkfs.c             |    2 
 repair/prefetch.c           |   12 -
 repair/prefetch.h           |    1 
 repair/progress.c           |   14 -
 repair/progress.h           |    2 
 repair/scan.c               |    2 
 repair/xfs_repair.c         |   47 ++-
 33 files changed, 2022 insertions(+), 140 deletions(-)
 create mode 100644 libxfs/xfbtree.c
 create mode 100644 libxfs/xfbtree.h
 create mode 100644 libxfs/xfile.c
 create mode 100644 libxfs/xfile.h
 create mode 100644 libxfs/xfs_btree_mem.h

[PATCHSET v29.0 12/40] xfsprogs: online repair of rmap btrees

[Darrick J. Wong]

Hi all,

We have now constructed the four tools that we need to scan the
filesystem looking for reverse mappings: an inode scanner, hooks to
receive live updates from other writer threads, the ability to construct
btrees in memory, and a btree bulk loader.

This series glues those three together, enabling us to scan the
filesystem for mappings and keep it up to date while other writers run,
and then commit the new btree to disk atomically.

To reduce the size of each patch, the functionality is left disabled
until the end of the series and broken up into three patches: one to
create the mechanics of scanning the filesystem, a second to transition
to in-memory btrees, and a third to set up the live hooks.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=repair-rmap-btree

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=repair-rmap-btree

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=repair-rmap-btree
---
 include/xfs_mount.h     |    6 +
 libxfs/xfs_ag.c         |    1 
 libxfs/xfs_ag.h         |    3 +
 libxfs/xfs_bmap.c       |   49 +++++++++++-
 libxfs/xfs_bmap.h       |    8 ++
 libxfs/xfs_inode_fork.c |    9 ++
 libxfs/xfs_inode_fork.h |    1 
 libxfs/xfs_rmap.c       |  190 +++++++++++++++++++++++++++++++++++------------
 libxfs/xfs_rmap.h       |   30 +++++++
 libxfs/xfs_rmap_btree.c |  136 +++++++++++++++++++++++++++++++++-
 libxfs/xfs_rmap_btree.h |    9 ++
 11 files changed, 387 insertions(+), 55 deletions(-)

[PATCHSET v29.0 13/40] xfs_repair: use in-memory rmap btrees

[Darrick J. Wong]

Hi all,

Now that we've ported support for in-memory btrees to userspace, port
xfs_repair to use them instead of the clunky slab interface that we
currently use.  This has the effect of moving memory consumption for
tracking reverse mappings into a memfd file, which means that we could
(theoretically) reduce the memory requirements by pointing it at an
on-disk file or something.  It also enables us to remove the sorting
step and to avoid having to coalesce adjacent contiguous bmap records
into a single rmap record.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=repair-use-in-memory-btrees
---
 include/xfs_mount.h      |    2 
 libfrog/linux.c          |   33 ++
 libfrog/platform.h       |    3 
 libxfs/init.c            |    3 
 libxfs/libxfs_api_defs.h |   13 +
 libxfs/xfbtree.c         |    8 
 libxfs/xfbtree.h         |    1 
 libxfs/xfile.c           |  200 +++++++++++-
 libxfs/xfile.h           |    9 -
 repair/agbtree.c         |   18 +
 repair/agbtree.h         |    1 
 repair/dinode.c          |    9 -
 repair/phase4.c          |   25 -
 repair/phase5.c          |    2 
 repair/rmap.c            |  768 ++++++++++++++++++++++++++++++----------------
 repair/rmap.h            |   32 +-
 repair/scan.c            |    7 
 repair/slab.c            |   49 ++-
 repair/slab.h            |    2 
 repair/xfs_repair.c      |    6 
 20 files changed, 839 insertions(+), 352 deletions(-)

[PATCHSET v29.0 14/40] xfsprogs: move btree geometry to ops struct

[Darrick J. Wong]

Hi all,

This patchset prepares the generic btree code to allow for the creation
of new btree types outside of libxfs.  The end goal here is for online
fsck to be able to create its own in-memory btrees that will be used to
improve the performance (and reduce the memory requirements of) the
refcount btree.

To enable this, I decided that the btree ops structure is the ideal
place to encode all of the geometry information about a btree. The btree
ops struture already contains the buffer ops (and hence the btree block
magic numbers) as well as the key and record sizes, so it doesn't seem
all that farfetched to encode the XFS_BTREE_ flags that determine the
geometry (ROOT_IN_INODE, LONG_PTRS, etc).

The rest of the patchset cleans up the btree functions that initialize
btree blocks and btree buffers.  The bulk of this work is to replace
btree geometry related function call arguments with a single pointer to
the ops structure, and then clean up everything else around that.  As a
side effect, we rename the functions.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=btree-geometry-in-ops

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=btree-geometry-in-ops
---
 libxfs/xfbtree.c            |   15 ++-------
 libxfs/xfs_ag.c             |   33 ++++++++------------
 libxfs/xfs_ag.h             |    2 +
 libxfs/xfs_alloc_btree.c    |   21 +++++--------
 libxfs/xfs_bmap.c           |    9 +-----
 libxfs/xfs_bmap_btree.c     |   14 ++-------
 libxfs/xfs_btree.c          |   70 ++++++++++++++++++++++---------------------
 libxfs/xfs_btree.h          |   36 ++++++++++------------
 libxfs/xfs_btree_mem.h      |    9 ------
 libxfs/xfs_btree_staging.c  |    6 +---
 libxfs/xfs_ialloc_btree.c   |   17 +++++-----
 libxfs/xfs_refcount_btree.c |    8 ++---
 libxfs/xfs_rmap_btree.c     |   16 ++++------
 libxfs/xfs_shared.h         |    9 ++++++
 14 files changed, 113 insertions(+), 152 deletions(-)

[PATCHSET v29.0 15/40] xfs_repair: reduce refcount repair memory usage

[Darrick J. Wong]

Hi all,

The refcountbt repair code has serious memory usage problems when the
block sharing factor of the filesystem is very high.  This can happen if
a deduplication tool has been run against the filesystem, or if the fs
stores reflinked VM images that have been aging for a long time.

Recall that the original reference counting algorithm walks the reverse
mapping records of the filesystem to generate reference counts.  For any
given block in the AG, the rmap bag structure contains the all rmap
records that cover that block; the refcount is the size of that bag.

For online repair, the bag doesn't need the owner, offset, or state flag
information, so it discards those.  This halves the record size, but the
bag structure still stores one excerpted record for each reverse
mapping.  If the sharing count is high, this will use a LOT of memory
storing redundant records.  In the extreme case, 100k mappings to the
same piece of space will consume 100k*16 bytes = 1.6M of memory.

For offline repair, the bag stores the owner values so that we know
which inodes need to be marked as being reflink inodes.  If a
deduplication tool has been run and there are many blocks within a file
pointing to the same physical space, this will stll use a lot of memory
to store redundant records.

The solution to this problem is to deduplicate the bag records when
possible by adding a reference count to the bag record, and changing the
bag add function to detect an existing record to bump the refcount.  In
the above example, the 100k mappings will now use 24 bytes of memory.
These lookups can be done efficiently with a btree, so we create a new
refcount bag btree type (inside of online repair).  This is why we
refactored the btree code in the previous patchset.

The btree conversion also dramatically reduces the runtime of the
refcount generation algorithm, because the code to delete all bag
records that end at a given agblock now only has to delete one record
instead of (using the example above) 100k records.  As an added benefit,
record deletion now gives back the unused xfile space, which it did not
do previously.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=repair-refcount-scalability

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=repair-refcount-scalability
---
 libxfs/libxfs_api_defs.h    |    8 +
 libxfs/xfs_alloc_btree.c    |    2 
 libxfs/xfs_bmap_btree.c     |    1 
 libxfs/xfs_btree.c          |   24 ---
 libxfs/xfs_btree.h          |    4 
 libxfs/xfs_ialloc_btree.c   |    2 
 libxfs/xfs_refcount_btree.c |    1 
 libxfs/xfs_rmap_btree.c     |    2 
 libxfs/xfs_types.h          |    6 -
 repair/Makefile             |    4 
 repair/rcbag.c              |  396 +++++++++++++++++++++++++++++++++++++++++++
 repair/rcbag.h              |   33 ++++
 repair/rcbag_btree.c        |  394 +++++++++++++++++++++++++++++++++++++++++++
 repair/rcbag_btree.h        |   78 ++++++++
 repair/rmap.c               |  159 +++++------------
 repair/slab.c               |  130 --------------
 repair/slab.h               |   19 --
 repair/xfs_repair.c         |    6 +
 18 files changed, 983 insertions(+), 286 deletions(-)
 create mode 100644 repair/rcbag.c
 create mode 100644 repair/rcbag.h
 create mode 100644 repair/rcbag_btree.c
 create mode 100644 repair/rcbag_btree.h

[PATCHSET v29.0 16/40] xfsprogs: bmap log intent cleanups

[Darrick J. Wong]

Hi all,

The next major target of online repair are metadata that are persisted
in blocks mapped by a file fork.  In other words, we want to repair
directories, extended attributes, symbolic links, and the realtime free
space information.  For file-based metadata, we assume that the space
metadata is correct, which enables repair to construct new versions of
the metadata in a temporary file.  We then need to swap the file fork
mappings of the two files atomically.  With this patchset, we begin
constructing such a facility based on the existing bmap log items and a
new extent swap log item.

This series cleans up a few parts of the file block mapping log intent
code before we start adding support for realtime bmap intents.  Most of
it involves cleaning up tracepoints so that more of the data extraction
logic ends up in the tracepoint code and not the tracepoint call site,
which should reduce overhead further when tracepoints are disabled.
There is also a change to pass bmap intents all the way back to the bmap
code instead of unboxing the intent values and re-boxing them after the
_finish_one function completes.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=bmap-intent-cleanups

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=bmap-intent-cleanups
---
 libxfs/Makefile     |    1 +
 libxfs/defer_item.c |   71 ++++++++++++++++++++++++++++++++-------------------
 libxfs/defer_item.h |   13 +++++++++
 libxfs/xfs_bmap.c   |   21 ++-------------
 libxfs/xfs_bmap.h   |    7 +++--
 5 files changed, 65 insertions(+), 48 deletions(-)
 create mode 100644 libxfs/defer_item.h

[PATCHSET v29.0 17/40] xfsprogs: widen BUI formats to support realtime

[Darrick J. Wong]

Hi all,

Atomic extent swapping (and later, reverse mapping and reflink) on the
realtime device needs to be able to defer file mapping and extent
freeing work in much the same manner as is required on the data volume.
Make the BUI log items operate on rt extents in preparation for atomic
swapping and realtime rmap.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=realtime-bmap-intents

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=realtime-bmap-intents
---
 libxfs/defer_item.c     |    6 ++++++
 libxfs/xfs_bmap.c       |    4 ++--
 libxfs/xfs_log_format.h |    4 +++-
 3 files changed, 11 insertions(+), 3 deletions(-)

[PATCHSET v29.0 18/40] xfsprogs: support attrfork and unwritten BUIs

[Darrick J. Wong]

Hi all,

In preparation for atomic extent swapping and the online repair
functionality that wants atomic extent swaps, enhance the BUI code so
that we can support deferred work on the extended attribute fork and on
unwritten extents.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=expand-bmap-intent-usage

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=expand-bmap-intent-usage
---
 libxfs/xfs_bmap.c |   49 +++++++++++++++++++++----------------------------
 libxfs/xfs_bmap.h |    4 ++--
 2 files changed, 23 insertions(+), 30 deletions(-)

[PATCHSET v29.0 19/40] xfsprogs: clean up symbolic link code

[Darrick J. Wong]

Hi all,

This series cleans up a few bits of the symbolic link code as needed for
future projects.  Online repair requires the ability to commit fixed
fork-based filesystem metadata such as directories, xattrs, and symbolic
links atomically, so we need to rearrange the symlink code before we
land the atomic extent swapping.

Accomplish this by moving the remote symlink target block code and
declarations to xfs_symlink_remote.[ch].

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=symlink-cleanups

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=symlink-cleanups
---
 include/libxfs.h            |    1 
 libxfs/libxfs_api_defs.h    |    1 
 libxfs/xfs_bmap.c           |    1 
 libxfs/xfs_inode_fork.c     |    1 
 libxfs/xfs_shared.h         |   13 ----
 libxfs/xfs_symlink_remote.c |  155 +++++++++++++++++++++++++++++++++++++++++++
 libxfs/xfs_symlink_remote.h |   26 +++++++
 mkfs/proto.c                |   72 +++++++++++---------
 8 files changed, 222 insertions(+), 48 deletions(-)
 create mode 100644 libxfs/xfs_symlink_remote.h

[PATCHSET v29.0 20/40] xfsprogs: atomic file updates

[Darrick J. Wong]

Hi all,

This series creates a new FIEXCHANGE_RANGE system call to exchange
ranges of bytes between two files atomically.  This new functionality
enables data storage programs to stage and commit file updates such that
reader programs will see either the old contents or the new contents in
their entirety, with no chance of torn writes.  A successful call
completion guarantees that the new contents will be seen even if the
system fails.

The ability to swap extent mappings between files in this manner is
critical to supporting online filesystem repair, which is built upon the
strategy of constructing a clean copy of a damaged structure and
committing the new structure into the metadata file atomically.

User programs will be able to update files atomically by opening an
O_TMPFILE, reflinking the source file to it, making whatever updates
they want to make, and exchange the relevant ranges of the temp file
with the original file.  If the updates are aligned with the file block
size, a new (since v2) flag provides for exchanging only the written
areas.  Callers can arrange for the update to be rejected if the
original file has been changed.

The intent behind this new userspace functionality is to enable atomic
rewrites of arbitrary parts of individual files.  For years, application
programmers wanting to ensure the atomicity of a file update had to
write the changes to a new file in the same directory, fsync the new
file, rename the new file on top of the old filename, and then fsync the
directory.  People get it wrong all the time, and $fs hacks abound.

The reference implementation in XFS creates a new log incompat feature
and log intent items to track high level progress of swapping ranges of
two files and finish interrupted work if the system goes down.  Sample
code can be found in the corresponding changes to xfs_io to exercise the
use case mentioned above.

Note that this function is /not/ the O_DIRECT atomic file writes concept
that has also been floating around for years.  It is also not the
RWF_ATOMIC patchset that has been shared.  This RFC is constructed
entirely in software, which means that there are no limitations other
than the general filesystem limits.

As a side note, the original motivation behind the kernel functionality
is online repair of file-based metadata.  The atomic file swap is
implemented as an atomic inode fork swap, which means that we can
implement online reconstruction of extended attributes and directories
by building a new one in another inode and atomically swap the contents.

Subsequent patchsets adapt the online filesystem repair code to use
atomic extent swapping.  This enables repair functions to construct a
clean copy of a directory, xattr information, symbolic links, realtime
bitmaps, and realtime summary information in a temporary inode.  If this
completes successfully, the new contents can be swapped atomically into
the inode being repaired.  This is essential to avoid making corruption
problems worse if the system goes down in the middle of running repair.

This patchset also ports the old XFS extent swap ioctl interface to use
the new extent swap code.

For userspace, this series also includes the userspace pieces needed to
test the new functionality, and a sample implementation of atomic file
updates.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=atomic-file-updates

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=atomic-file-updates

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=atomic-file-updates

xfsdocs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-documentation.git/log/?h=atomic-file-updates
---
 fsr/xfs_fsr.c                       |  213 +++---
 include/jdm.h                       |   24 +
 include/libxfs.h                    |    1 
 include/xfs.h                       |    1 
 include/xfs_inode.h                 |    5 
 include/xfs_trace.h                 |   14 
 io/Makefile                         |    2 
 io/atomicupdate.c                   |  386 ++++++++++
 io/init.c                           |    1 
 io/inject.c                         |    1 
 io/io.h                             |    5 
 io/open.c                           |   27 +
 io/swapext.c                        |  194 ++++-
 libfrog/Makefile                    |    2 
 libfrog/file_exchange.c             |  186 +++++
 libfrog/file_exchange.h             |   16 
 libfrog/fsgeom.c                    |   45 +
 libfrog/fsgeom.h                    |    7 
 libhandle/jdm.c                     |  117 +++
 libxfs/Makefile                     |    3 
 libxfs/defer_item.c                 |   91 ++
 libxfs/defer_item.h                 |    4 
 libxfs/libxfs_priv.h                |   31 +
 libxfs/xfs_bmap.h                   |    2 
 libxfs/xfs_defer.c                  |    6 
 libxfs/xfs_defer.h                  |    2 
 libxfs/xfs_errortag.h               |    4 
 libxfs/xfs_format.h                 |   20 -
 libxfs/xfs_fs.h                     |    4 
 libxfs/xfs_fs_staging.h             |  107 +++
 libxfs/xfs_log_format.h             |   83 ++
 libxfs/xfs_sb.c                     |    3 
 libxfs/xfs_swapext.c                | 1316 +++++++++++++++++++++++++++++++++++
 libxfs/xfs_swapext.h                |  223 ++++++
 libxfs/xfs_symlink_remote.c         |   47 +
 libxfs/xfs_symlink_remote.h         |    1 
 libxfs/xfs_trans_space.h            |    4 
 logprint/log_misc.c                 |   11 
 logprint/log_print_all.c            |   12 
 logprint/log_redo.c                 |  128 +++
 logprint/logprint.h                 |    6 
 man/man2/ioctl_xfs_exchange_range.2 |  296 ++++++++
 man/man2/ioctl_xfs_fsgeometry.2     |    3 
 man/man8/xfs_io.8                   |   86 ++
 44 files changed, 3590 insertions(+), 150 deletions(-)
 create mode 100644 io/atomicupdate.c
 create mode 100644 libfrog/file_exchange.c
 create mode 100644 libfrog/file_exchange.h
 create mode 100644 libxfs/xfs_fs_staging.h
 create mode 100644 libxfs/xfs_swapext.c
 create mode 100644 libxfs/xfs_swapext.h
 create mode 100644 man/man2/ioctl_xfs_exchange_range.2

[PATCHSET v29.0 21/40] xfsprogs: set and validate dir/attr block owners

[Darrick J. Wong]

Hi all,

There are a couple of significatn changes that need to be made to the
directory and xattr code before we can support online repairs of those
data structures.

The first change is because online repair is designed to use libxfs to
create a replacement dir/xattr structure in a temporary file, and use
atomic extent swapping to commit the corrected structure.  To avoid the
performance hit of walking every block of the new structure to rewrite
the owner number, we instead change libxfs to allow callers of the dir
and xattr code the ability to set an explicit owner number to be written
into the header fields of any new blocks that are created.

The second change is to update the dir/xattr code to actually *check*
the owner number in each block that is read off the disk, since we don't
currently do that.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=dirattr-validate-owners

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=dirattr-validate-owners
---
 db/attrset.c             |    2 +
 db/namei.c               |    6 +-
 libxfs/libxfs_api_defs.h |    3 +
 libxfs/xfs_attr.c        |   10 +--
 libxfs/xfs_attr_leaf.c   |   59 +++++++++++++---
 libxfs/xfs_attr_leaf.h   |    4 +
 libxfs/xfs_attr_remote.c |   13 ++--
 libxfs/xfs_bmap.c        |    1 
 libxfs/xfs_da_btree.c    |  168 ++++++++++++++++++++++++++++++++++++++++++++++
 libxfs/xfs_da_btree.h    |    3 +
 libxfs/xfs_dir2.c        |    5 +
 libxfs/xfs_dir2.h        |    4 +
 libxfs/xfs_dir2_block.c  |   44 +++++++-----
 libxfs/xfs_dir2_data.c   |   17 +++--
 libxfs/xfs_dir2_leaf.c   |   99 +++++++++++++++++++++------
 libxfs/xfs_dir2_node.c   |   44 +++++++-----
 libxfs/xfs_dir2_priv.h   |   11 ++-
 libxfs/xfs_swapext.c     |    7 +-
 repair/phase6.c          |    3 +
 19 files changed, 402 insertions(+), 101 deletions(-)

[PATCHSET v29.0 22/40] xfsprogs: online repair of extended attributes

[Darrick J. Wong]

Hi all,

This series employs atomic extent swapping to enable safe reconstruction
of extended attribute data attached to a file.  Because xattrs do not
have any redundant information to draw off of, we can at best salvage
as much data as we can and build a new structure.

Rebuilding an extended attribute structure consists of these three
steps:

First, we walk the existing attributes to salvage as many of them as we
can, by adding them as new attributes attached to the repair tempfile.
We need to add a new xfile-based data structure to hold blobs of
arbitrary length to stage the xattr names and values.

Second, we write the salvaged attributes to a temporary file, and use
atomic extent swaps to exchange the entire attribute fork between the
two files.

Finally, we reap the old xattr blocks (which are now in the temporary
file) as carefully as we can.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=repair-xattrs

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=repair-xattrs

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=repair-xattrs
---
 libxfs/xfs_attr.c      |    2 +-
 libxfs/xfs_attr.h      |    2 ++
 libxfs/xfs_da_format.h |    5 +++++
 libxfs/xfs_swapext.c   |    2 +-
 libxfs/xfs_swapext.h   |    1 +
 5 files changed, 10 insertions(+), 2 deletions(-)

[PATCHSET v29.0 23/40] xfsprogs: online repair of symbolic links

[Darrick J. Wong]

Hi all,

Congratulations!  You have made it to the final patchset of the main
online fsck feature!  The sole patch in this set adds the ability to
repair the target buffer of a symbolic link, using the same salvage,
rebuild, and swap strategy used everywhere else.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=repair-symlink

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=repair-symlink
---
 libxfs/xfs_bmap.c           |   11 ++++++-----
 libxfs/xfs_bmap.h           |    6 ++++++
 libxfs/xfs_symlink_remote.c |    9 +++++----
 libxfs/xfs_symlink_remote.h |   22 ++++++++++++++++++----
 4 files changed, 35 insertions(+), 13 deletions(-)

[PATCHSET v29.0 24/40] libxfs: cache xfile pages for better performance

[Darrick J. Wong]

Hi all,

Congratulations!  You have made it to the final patchset of the main
online fsck feature!  This last series improves the performance of
xfile-backed btrees by teaching the buffer cache to directly map pages
from the xfile.  It also speeds up xfarray operations substantially by
implementing a small page cache to avoid repeated kmap/kunmap calls.
Collectively, these can reduce the runtime of online repair functions by
twenty percent or so.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=xfile-page-caching

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=xfile-page-caching
---
 libxfs/xfs_btree_mem.h  |    6 ++++++
 libxfs/xfs_rmap_btree.c |    1 +
 2 files changed, 7 insertions(+)

[PATCHSET v29.0 25/40] xfsprogs: inode-related repair fixes

[Darrick J. Wong]

Hi all,

While doing QA of the online fsck code, I made a few observations:
First, nobody was checking that the di_onlink field is actually zero;
Second, that allocating a temporary file for repairs can fail (and
thus bring down the entire fs) if the inode cluster is corrupt; and
Third, that file link counts do not pin at ~0U to prevent integer
overflows.

This scattered patchset fixes those three problems.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=inode-repair-improvements

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=inode-repair-improvements
---
 include/xfs_inode.h    |    2 ++
 libxfs/util.c          |   24 ++++++++++++++++++++++++
 libxfs/xfs_format.h    |    6 ++++++
 libxfs/xfs_ialloc.c    |   40 ++++++++++++++++++++++++++++++++++++++++
 libxfs/xfs_inode_buf.c |    8 ++++++++
 mkfs/proto.c           |    4 ++--
 repair/incore_ino.c    |    3 ++-
 repair/phase6.c        |   10 +++++-----
 8 files changed, 89 insertions(+), 8 deletions(-)

[PATCHSET v29.0 26/40] xfs_scrub: fixes to the repair code

[Darrick J. Wong]

Hi all,

Now that we've landed the new kernel code, it's time to reorganize the
xfs_scrub code that handles repairs.  Clean up various naming warts and
misleading error messages.  Move the repair code to scrub/repair.c as
the first step.  Then, fix various issues in the repair code before we
start reorganizing things.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=scrub-repair-fixes
---
 scrub/phase1.c        |    2 
 scrub/phase2.c        |    3 -
 scrub/phase3.c        |    2 
 scrub/phase4.c        |   22 ++++-
 scrub/phase5.c        |    2 
 scrub/phase6.c        |   13 +++
 scrub/phase7.c        |    2 
 scrub/repair.c        |  177 ++++++++++++++++++++++++++++++++++++++++++-
 scrub/repair.h        |   16 +++-
 scrub/scrub.c         |  204 +------------------------------------------------
 scrub/scrub.h         |   16 ----
 scrub/scrub_private.h |   55 +++++++++++++
 scrub/xfs_scrub.c     |    2 
 13 files changed, 283 insertions(+), 233 deletions(-)
 create mode 100644 scrub/scrub_private.h

[PATCHSET v29.0 27/40] xfs_scrub: improve warnings about difficult repairs

[Darrick J. Wong]

Hi all,

While I was poking through the QA results for xfs_scrub, I noticed that
it doesn't warn the user when the primary and secondary realtime
metadata are so out of whack that the chances of a successful repair are
not so high.  I decided that it was worth refactoring the scrub code a
bit so that we could warn the user about these types of things, and
ended up refactoring unnecessary helpers out of existence and fixing
other reporting gaps.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=scrub-better-repair-warnings
---
 man/man8/xfs_scrub.8 |   19 ++++++++++++++++++
 scrub/common.c       |    2 ++
 scrub/phase1.c       |    2 +-
 scrub/phase2.c       |   53 +++++++++++++++++++++++++++++++-------------------
 scrub/phase3.c       |   21 ++++++++++++++++----
 scrub/phase4.c       |    9 +++++---
 scrub/phase5.c       |   15 +++++++-------
 scrub/repair.c       |   47 ++++++++++++++++++++++++++++++++++----------
 scrub/repair.h       |   10 +++++++--
 scrub/scrub.c        |   52 +------------------------------------------------
 scrub/scrub.h        |    7 ++-----
 scrub/xfs_scrub.c    |   45 ++++++++++++++++++++++++++++++++++++++++++
 scrub/xfs_scrub.h    |    1 +
 13 files changed, 175 insertions(+), 108 deletions(-)

[PATCHSET v29.0 28/40] xfs_scrub: track data dependencies for repairs

[Darrick J. Wong]

Hi all,

Certain kinds of XFS metadata depend on the correctness of lower level
metadata.  For example, directory indexes depends on the directory data
fork, which in turn depend on the directory inode to be correct.  The
current scrub code does not strictly preserve these dependencies if it
has to defer a repair until phase 4, because phase 4 prioritizes repairs
by type (corruption, then cross referencing, and then preening) and
loses the ordering of in the previous phases.  This leads to absurd
things like trying to repair a directory before repairing its corrupted
fork, which is absurd.

To solve this problem, introduce a repair ticket structure to track all
the repairs pending for a principal object (inode, AG, etc).  This
reduces memory requirements if an object requires more than one type of
repair and makes it very easy to track the data dependencies between
sub-objects of a principal object.  Repair dependencies between object
types (e.g.  bnobt before inodes) must still be encoded statically into
phase 4.

A secondary benefit of this new ticket structure is that we can decide
to attempt a repair of an object A that was flagged for a cross
referencing error during the scan if a different object B depends on A
but only B showed definitive signs of corruption.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=scrub-repair-data-deps
---
 libfrog/scrub.c       |    1 
 scrub/phase1.c        |    9 -
 scrub/phase2.c        |   46 ++--
 scrub/phase3.c        |   77 ++++---
 scrub/phase4.c        |   17 +-
 scrub/phase5.c        |    9 -
 scrub/phase7.c        |    9 -
 scrub/repair.c        |  530 +++++++++++++++++++++++++++++++++----------------
 scrub/repair.h        |   47 +++-
 scrub/scrub.c         |  136 ++++++-------
 scrub/scrub.h         |  108 ++++++++--
 scrub/scrub_private.h |   37 +++
 12 files changed, 664 insertions(+), 362 deletions(-)

[PATCHSET v29.0 29/40] xfs_scrub: use scrub_item to track check progress

[Darrick J. Wong]

Hi all,

Now that we've introduced tickets to track the status of repairs to a
specific principal XFS object (fs, ag, file), use them to track the
scrub state of those same objects.  Ultimately, we want to make it easy
to introduce vectorized repair, where we send a batch of repair requests
to the kernel instead of making millions of ioctl calls.  For now,
however, we'll settle for easier bookkeepping.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=scrub-object-tracking
---
 scrub/phase1.c        |    3 
 scrub/phase2.c        |   12 +-
 scrub/phase3.c        |   41 ++----
 scrub/phase4.c        |   16 +-
 scrub/phase5.c        |    5 -
 scrub/phase7.c        |    5 +
 scrub/repair.c        |   71 +++++------
 scrub/scrub.c         |  321 ++++++++++++++++++++++---------------------------
 scrub/scrub.h         |   40 ++++--
 scrub/scrub_private.h |   14 ++
 10 files changed, 257 insertions(+), 271 deletions(-)

[PATCHSET v29.0 30/40] xfs_scrub: improve scheduling of repair items

[Darrick J. Wong]

Hi all,

Currently, phase 4 of xfs_scrub uses per-AG repair item lists to
schedule repair work across a thread pool.  This scheme is suboptimal
when most of the repairs involve a single AG because all the work gets
dumped on a single pool thread.

Instead, we should create a thread pool with the same number of workers
as CPUs, and dispatch individual repair tickets as separate work items
to maximize parallelization.

However, we also need to ensure that repairs to space metadata and file
metadata are kept in separate queues because file repairs generally
depend on correctness of space metadata.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=scrub-repair-scheduling
---
 libfrog/ptvar.c       |    9 ++
 libfrog/ptvar.h       |    4 +
 scrub/counter.c       |    2 
 scrub/descr.c         |    2 
 scrub/phase1.c        |   15 ++-
 scrub/phase2.c        |   23 ++++-
 scrub/phase3.c        |  106 ++++++++++++++-------
 scrub/phase4.c        |  244 ++++++++++++++++++++++++++++++++++++-------------
 scrub/phase7.c        |    2 
 scrub/read_verify.c   |    2 
 scrub/repair.c        |  172 ++++++++++++++++++++++-------------
 scrub/repair.h        |   37 ++++++-
 scrub/scrub.c         |    5 +
 scrub/scrub.h         |   10 ++
 scrub/scrub_private.h |    2 
 scrub/xfs_scrub.h     |    3 -
 16 files changed, 455 insertions(+), 183 deletions(-)

[PATCHSET v29.0 31/40] xfs_scrub: detect deceptive filename extensions

[Darrick J. Wong]

Hi all,

In early 2023, malware researchers disclosed a phishing attack that was
targeted at people running Linux workstations.  The attack vector
involved the use of filenames containing what looked like a file
extension but instead contained a lookalike for the full stop (".")
and a common extension ("pdf").  Enhance xfs_scrub phase 5 to detect
these types of attacks and warn the system administrator.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=scrub-detect-deceptive-extensions

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=scrub-detect-deceptive-extensions
---
 scrub/unicrash.c |  530 +++++++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 424 insertions(+), 106 deletions(-)

[PATCHSET v29.0 32/40] xfs_scrub: move fstrim to a separate phase

[Darrick J. Wong]

Hi all,

Back when I originally designed xfs_scrub, all filesystem metadata
checks were complete by the end of phase 3, and phase 4 was where all
the metadata repairs occurred.  On the grounds that the filesystem
should be fully consistent by then, I made a call to FITRIM at the end
of phase 4 to discard empty space in the filesystem.

Unfortunately, that's no longer the case -- summary counters, link
counts, and quota counters are not checked until phase 7.  It's not safe
to instruct the storage to unmap "empty" areas if we don't know where
those empty areas are, so we need to create a phase 8 to trim the fs.
While we're at it, make it more obvious that fstrim only gets to run if
there are no unfixed corruptions and no other runtime errors have
occurred.

Finally, reduce the latency impacts on the rest of the system by
breaking up the fstrim work into a loop that targets only 16GB per call.
This enables better progress reporting for interactive runs and cgroup
based resource constraints for background runs.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=scrub-fstrim-phase
---
 scrub/Makefile    |    1 
 scrub/phase4.c    |   30 +----------
 scrub/phase8.c    |  151 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 scrub/vfs.c       |   22 +++++---
 scrub/vfs.h       |    2 -
 scrub/xfs_scrub.c |   11 ++++
 scrub/xfs_scrub.h |    3 +
 7 files changed, 183 insertions(+), 37 deletions(-)
 create mode 100644 scrub/phase8.c

[PATCHSET v29.0 33/40] xfs_scrub: use free space histograms to reduce fstrim runtime

[Darrick J. Wong]

Hi all,

This patchset dramatically reduces the runtime of the FITRIM calls made
during phase 8 of xfs_scrub.  It turns out that phase 8 can really get
bogged down if the free space contains a large number of very small
extents.  In these cases, the runtime can increase by an order of
magnitude to free less than 1% of the free space.  This is not worth the
time, since we're spending a lot of time to do very little work.  The
FITRIM ioctl allows us to specify a minimum extent length, so we can use
statistical methods to compute a minlen parameter.

It turns out xfs_db/spaceman already have the code needed to create
histograms of free space extent lengths.  We add the ability to compute
a CDF of the extent lengths, which make it easy to pick a minimum length
corresponding to 99% of the free space.  In most cases, this results in
dramatic reductions in phase 8 runtime.  Hence, move the histogram code
to libfrog, and wire up xfs_scrub, since phase 7 already walks the
fsmap.

We also add a new -o suboption to xfs_scrub so that people who /do/ want
to examine every free extent can do so.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=scrub-fstrim-minlen-freesp-histogram

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=scrub-fstrim-minlen-freesp-histogram
---
 db/freesp.c          |   83 +++-------------
 libfrog/Makefile     |    2 
 libfrog/histogram.c  |  252 ++++++++++++++++++++++++++++++++++++++++++++++++++
 libfrog/histogram.h  |   54 +++++++++++
 man/man8/xfs_scrub.8 |   16 +++
 scrub/phase7.c       |   47 +++++++++
 scrub/phase8.c       |   75 ++++++++++++++-
 scrub/spacemap.c     |   11 +-
 scrub/vfs.c          |    4 +
 scrub/vfs.h          |    2 
 scrub/xfs_scrub.c    |   45 +++++++++
 scrub/xfs_scrub.h    |   16 +++
 spaceman/freesp.c    |   93 +++++-------------
 13 files changed, 544 insertions(+), 156 deletions(-)
 create mode 100644 libfrog/histogram.c
 create mode 100644 libfrog/histogram.h

[PATCHSET v29.0 34/40] xfs_scrub: fixes for systemd services

[Darrick J. Wong]

Hi all,

This series fixes deficiencies in the systemd services that were created
to manage background scans.  First, improve the debian packaging so that
services get installed at package install time.  Next, fix copyright and
spdx header omissions.

Finally, fix bugs in the mailer scripts so that scrub failures are
reported effectively.  Finally, fix xfs_scrub_all to deal with systemd
restarts causing it to think that a scrub has finished before the
service actually finishes.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=scrub-service-fixes
---
 debian/rules                     |    1 +
 include/builddefs.in             |    2 +-
 scrub/Makefile                   |   26 ++++++++++++++------
 scrub/xfs_scrub@.service.in      |    6 ++---
 scrub/xfs_scrub_all.in           |   49 ++++++++++++++++----------------------
 scrub/xfs_scrub_fail.in          |   12 ++++++++-
 scrub/xfs_scrub_fail@.service.in |    4 ++-
 7 files changed, 55 insertions(+), 45 deletions(-)
 rename scrub/{xfs_scrub_fail => xfs_scrub_fail.in} (62%)

[PATCHSET v29.0 35/40] xfs_scrub_all: fixes for systemd services

[Darrick J. Wong]

Hi all,

This patchset ties up some problems in the xfs_scrub_all program and
service, which are essential for finding mounted filesystems to scrub
and creating the background service instances that do the scrub.

First, we need to fix various errors in pathname escaping, because
systemd does /not/ like slashes in service names.  Then, teach
xfs_scrub_all to deal with systemd restarts causing it to think that a
scrub has finished before the service actually finishes.  Finally,
implement a signal handler so that SIGINT (console ^C) and SIGTERM
(systemd stopping the service) shut down the xfs_scrub@ services
correctly.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=scruball-service-fixes
---
 scrub/xfs_scrub_all.in |  157 ++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 125 insertions(+), 32 deletions(-)

[PATCHSET v29.0 36/40] xfs_scrub: tighten security of systemd services

[Darrick J. Wong]

Hi all,

To reduce the risk of the online fsck service suffering some sort of
catastrophic breach that results in attackers reconfiguring the running
system, I embarked on a security audit of the systemd service files.
The result should be that all elements of the background service
(individual scrub jobs, the scrub_all initiator, and the failure
reporting) run with as few privileges and within as strong of a sandbox
as possible.

Granted, this does nothing about the potential for the /kernel/ screwing
up, but at least we could prevent obvious container escapes.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=scrub-service-security
---
 man/man8/xfs_scrub.8             |    9 +++-
 scrub/Makefile                   |    7 ++-
 scrub/phase1.c                   |    4 +-
 scrub/system-xfs_scrub.slice     |   30 ++++++++++++
 scrub/vfs.c                      |    2 -
 scrub/xfs_scrub.c                |   11 +++-
 scrub/xfs_scrub.h                |    5 ++
 scrub/xfs_scrub@.service.in      |   97 ++++++++++++++++++++++++++++++++++----
 scrub/xfs_scrub_all.service.in   |   66 ++++++++++++++++++++++++++
 scrub/xfs_scrub_fail@.service.in |   59 +++++++++++++++++++++++
 10 files changed, 270 insertions(+), 20 deletions(-)
 create mode 100644 scrub/system-xfs_scrub.slice

[PATCHSET v29.0 37/40] xfs_scrub_all: automatic media scan service

[Darrick J. Wong]

Hi all,

Now that we've completed the online fsck functionality, there are a few
things that could be improved in the automatic service.  Specifically,
we would like to perform a more intensive metadata + media scan once per
month, to give the user confidence that the filesystem isn't losing data
silently.  To accomplish this, enhance xfs_scrub_all to be able to
trigger media scans.  Next, add a duplicate set of system services that
start the media scans automatically.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=scrub-media-scan-service
---
 debian/rules                           |    3 +
 include/builddefs.in                   |    3 +
 man/man8/Makefile                      |    7 ++
 man/man8/xfs_scrub_all.8.in            |   20 +++++
 scrub/Makefile                         |   21 +++++-
 scrub/xfs_scrub@.service.in            |    2 -
 scrub/xfs_scrub_all.cron.in            |    2 -
 scrub/xfs_scrub_all.in                 |  122 ++++++++++++++++++++++++++------
 scrub/xfs_scrub_all.service.in         |    9 ++
 scrub/xfs_scrub_all_fail.service.in    |   71 +++++++++++++++++++
 scrub/xfs_scrub_fail.in                |   46 +++++++++---
 scrub/xfs_scrub_fail@.service.in       |    2 -
 scrub/xfs_scrub_media@.service.in      |  100 ++++++++++++++++++++++++++
 scrub/xfs_scrub_media_fail@.service.in |   76 ++++++++++++++++++++
 14 files changed, 439 insertions(+), 45 deletions(-)
 rename man/man8/{xfs_scrub_all.8 => xfs_scrub_all.8.in} (59%)
 create mode 100644 scrub/xfs_scrub_all_fail.service.in
 create mode 100644 scrub/xfs_scrub_media@.service.in
 create mode 100644 scrub/xfs_scrub_media_fail@.service.in

[PATCHSET v29.0 38/40] xfs_scrub_all: improve systemd handling

[Darrick J. Wong]

Hi all,



If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=scrub-all-improve-systemd-handling
---
 debian/control         |    2 
 scrub/xfs_scrub_all.in |  279 ++++++++++++++++++++++++++++++++++++------------
 2 files changed, 209 insertions(+), 72 deletions(-)

[PATCHSET v29.0 39/40] xfs_scrub: automatic optimization by default

[Darrick J. Wong]

Hi all,

This final patchset in the online fsck series enables the background
service to optimize filesystems by default.  This is the first step
towards enabling repairs by default.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=scrub-optimize-by-default

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=scrub-optimize-by-default
---
 debian/rules         |    2 +-
 man/man8/xfs_scrub.8 |    6 +++++-
 scrub/Makefile       |    2 +-
 scrub/phase1.c       |   13 +++++++++++++
 scrub/phase4.c       |    6 ++++++
 scrub/repair.c       |   37 ++++++++++++++++++++++++++++++++++++-
 scrub/repair.h       |    2 ++
 scrub/scrub.c        |    4 ++--
 scrub/xfs_scrub.c    |   21 +++++++++++++++++++--
 scrub/xfs_scrub.h    |    1 +
 10 files changed, 86 insertions(+), 8 deletions(-)

[PATCHSET 40/40] xfs_repair: add other v5 features to filesystems

[Darrick J. Wong]

Hi all,

This series enables xfs_repair to add select features to existing V5
filesystems.  Specifically, one can add free inode btrees, reflink
support, and reverse mapping.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=upgrade-older-features

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=upgrade-older-features
---
 include/libxfs.h     |    1 
 man/man8/xfs_admin.8 |   21 +++++
 repair/globals.c     |    3 +
 repair/globals.h     |    3 +
 repair/phase2.c      |  229 ++++++++++++++++++++++++++++++++++++++++++++++++++
 repair/rmap.c        |    8 +-
 repair/xfs_repair.c  |   33 +++++++
 7 files changed, 294 insertions(+), 4 deletions(-)

[PATCHSET 1/8] fstests: fuzz non-root dquots on xfs

[Darrick J. Wong]

Hi all,

During testing of online fsck part 2, I noticed that the dquot iteration
code in online fsck had some math bugs that resulted in it only ever
checking the root dquot.  Loooking into why I never noticed that, I
discovered that fstests also never checked them.  Strengthen our testing
by adding that.

While we're at it, hide a few more inode fields from the fuzzer, since
their contents are completely user-controlled and have no other
validation.  Hence they just generate noise in the test system and
increase runtimes unnecessarily.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=fuzz-dquots
---
 check           |   12 ++++++++++++
 common/fuzzy    |   27 ++++++++++++++++++++++++---
 common/populate |   14 ++++++++++++++
 tests/xfs/425   |   10 +++++++---
 tests/xfs/426   |   10 +++++++---
 tests/xfs/427   |   10 +++++++---
 tests/xfs/428   |   10 +++++++---
 tests/xfs/429   |   10 +++++++---
 tests/xfs/430   |   10 +++++++---
 tests/xfs/487   |   10 +++++++---
 tests/xfs/488   |   10 +++++++---
 tests/xfs/489   |   10 +++++++---
 tests/xfs/779   |   10 +++++++---
 tests/xfs/780   |   10 +++++++---
 tests/xfs/781   |   10 +++++++---
 15 files changed, 134 insertions(+), 39 deletions(-)

[PATCHSET 2/8] xfsprogs: scale shards on ssds

[Darrick J. Wong]

Hi all,

For a long time, the maintainers have had a gut feeling that we could
optimize performance of XFS filesystems on non-mechanical storage by
scaling the number of allocation groups to be a multiple of the CPU
count.

With modern ~2022 hardware, it is common for systems to have more than
four CPU cores and non-striped SSDs ranging in size from 256GB to 4TB.
The default mkfs geometry still defaults to 4 AGs regardless of core
count, which was settled on in the age of spinning rust.

This patchset adds a different computation for AG count and log size
that is based entirely on a desired level of concurrency.  If we detect
storage that is non-rotational (or the sysadmin provides a CLI option),
then we will try to match the AG count to the CPU count to minimize AGF
contention and make the log large enough to minimize grant head
contention.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=mkfs-scale-geo-on-ssds

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=mkfs-scale-geo-on-ssds
---
 tests/xfs/1842     |   51 +++++++++++++++
 tests/xfs/1842.out |  177 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 228 insertions(+)
 create mode 100755 tests/xfs/1842
 create mode 100644 tests/xfs/1842.out

[PATCHSET v29.0 3/8] fstests: establish baseline for fuzz tests

[Darrick J. Wong]

Hi all,

Establish a baseline golden output for all current fuzz tests.  This
shouldn't be merged upstream because the output is very dependent on the
geometry of the filesystem that is created.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=fuzz-baseline
---
 tests/xfs/350.out |   91 +++++++++
 tests/xfs/351.out |   75 +++++++
 tests/xfs/353.out |   96 ++++++++++
 tests/xfs/354.out |   87 +++++++++
 tests/xfs/355.out |   47 +++++
 tests/xfs/356.out |   13 +
 tests/xfs/357.out |  109 +++++++++++
 tests/xfs/358.out |    5 
 tests/xfs/360.out |   30 +++
 tests/xfs/361.out |   14 +
 tests/xfs/362.out |    5 
 tests/xfs/364.out |    6 +
 tests/xfs/366.out |    6 +
 tests/xfs/368.out |    8 +
 tests/xfs/369.out |   57 ++++++
 tests/xfs/370.out |  417 +++++++++++++++++++++++++++++++++++++++++
 tests/xfs/371.out |  108 +++++++++++
 tests/xfs/372.out |    5 
 tests/xfs/374.out |   35 +++
 tests/xfs/375.out |   94 +++++++++
 tests/xfs/376.out |   22 ++
 tests/xfs/377.out |   62 ++++++
 tests/xfs/378.out |   22 ++
 tests/xfs/379.out |   74 +++++++
 tests/xfs/381.out |    1 
 tests/xfs/382.out |    4 
 tests/xfs/383.out |    4 
 tests/xfs/384.out |   38 ++++
 tests/xfs/385.out |   68 +++++++
 tests/xfs/386.out |   28 +++
 tests/xfs/388.out |  535 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 tests/xfs/392.out |    7 +
 tests/xfs/394.out |   12 +
 tests/xfs/398.out |   38 ++++
 tests/xfs/399.out |   63 ++++++
 tests/xfs/400.out |   26 +++
 tests/xfs/401.out |   72 +++++++
 tests/xfs/402.out |    7 +
 tests/xfs/404.out |   33 +++
 tests/xfs/405.out |    5 
 tests/xfs/410.out |    6 +
 tests/xfs/412.out |   21 ++
 tests/xfs/413.out |   48 +++++
 tests/xfs/414.out |   23 ++
 tests/xfs/415.out |   56 ++++++
 tests/xfs/416.out |   22 ++
 tests/xfs/417.out |   56 ++++++
 tests/xfs/418.out |   90 +++++++++
 tests/xfs/425.out |  258 ++++++++++++++++++++++++++
 tests/xfs/426.out |  132 +++++++++++++
 tests/xfs/427.out |  258 ++++++++++++++++++++++++++
 tests/xfs/428.out |  132 +++++++++++++
 tests/xfs/429.out |  258 ++++++++++++++++++++++++++
 tests/xfs/430.out |  132 +++++++++++++
 tests/xfs/453.out |  152 +++++++++++++++
 tests/xfs/454.out |   96 ++++++++++
 tests/xfs/455.out |  134 +++++++++++++
 tests/xfs/456.out |  129 +++++++++++++
 tests/xfs/457.out |    5 
 tests/xfs/458.out |   44 ++++
 tests/xfs/459.out |    5 
 tests/xfs/460.out |    6 +
 tests/xfs/461.out |    6 +
 tests/xfs/462.out |    8 +
 tests/xfs/463.out |  525 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 tests/xfs/464.out |    5 
 tests/xfs/465.out |   71 +++++++
 tests/xfs/466.out |   51 +++++
 tests/xfs/467.out |   47 +++++
 tests/xfs/469.out |    8 +
 tests/xfs/470.out |   79 ++++++++
 tests/xfs/471.out |    7 +
 tests/xfs/472.out |    7 +
 tests/xfs/474.out |    7 +
 tests/xfs/475.out |    6 +
 tests/xfs/477.out |   79 ++++++++
 tests/xfs/478.out |   91 +++++++++
 tests/xfs/479.out |    7 +
 tests/xfs/480.out |   24 ++
 tests/xfs/483.out |    6 +
 tests/xfs/484.out |   45 ++++
 tests/xfs/485.out |   51 +++++
 tests/xfs/486.out |   46 +++++
 tests/xfs/487.out |  242 ++++++++++++++++++++++++
 tests/xfs/488.out |  242 ++++++++++++++++++++++++
 tests/xfs/489.out |  242 ++++++++++++++++++++++++
 tests/xfs/496.out |   24 ++
 tests/xfs/498.out |   12 +
 tests/xfs/730.out |   10 +
 tests/xfs/734.out |    9 +
 tests/xfs/737.out |   14 +
 tests/xfs/747.out |  152 +++++++++++++++
 tests/xfs/748.out |   96 ++++++++++
 tests/xfs/749.out |  134 +++++++++++++
 tests/xfs/750.out |  129 +++++++++++++
 tests/xfs/751.out |    5 
 tests/xfs/752.out |   44 ++++
 tests/xfs/753.out |    5 
 tests/xfs/754.out |    6 +
 tests/xfs/755.out |    6 +
 tests/xfs/756.out |   61 ++++++
 tests/xfs/757.out |  525 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 tests/xfs/758.out |    5 
 tests/xfs/759.out |   94 +++++++++
 tests/xfs/760.out |   64 ++++++
 tests/xfs/761.out |   66 +++++++
 tests/xfs/762.out |    1 
 tests/xfs/763.out |    8 +
 tests/xfs/764.out |   92 +++++++++
 tests/xfs/765.out |    7 +
 tests/xfs/766.out |   11 +
 tests/xfs/768.out |    7 +
 tests/xfs/769.out |    6 +
 tests/xfs/771.out |   91 +++++++++
 tests/xfs/772.out |   93 +++++++++
 tests/xfs/773.out |    7 +
 tests/xfs/774.out |   24 ++
 tests/xfs/775.out |    6 +
 tests/xfs/776.out |   59 ++++++
 tests/xfs/777.out |   69 +++++++
 tests/xfs/778.out |   60 ++++++
 tests/xfs/779.out |  296 +++++++++++++++++++++++++++++
 tests/xfs/780.out |  296 +++++++++++++++++++++++++++++
 tests/xfs/781.out |  296 +++++++++++++++++++++++++++++
 tests/xfs/782.out |   12 +
 tests/xfs/783.out |  210 +++++++++++++++++++++
 tests/xfs/784.out |   10 +
 tests/xfs/785.out |   23 ++
 tests/xfs/787.out |   23 ++
 tests/xfs/788.out |   23 ++
 130 files changed, 9585 insertions(+)

[PATCHSET v29.0 4/8] fstests: atomic file updates

[Darrick J. Wong]

Hi all,

This series creates a new FIEXCHANGE_RANGE system call to exchange
ranges of bytes between two files atomically.  This new functionality
enables data storage programs to stage and commit file updates such that
reader programs will see either the old contents or the new contents in
their entirety, with no chance of torn writes.  A successful call
completion guarantees that the new contents will be seen even if the
system fails.

The ability to swap extent mappings between files in this manner is
critical to supporting online filesystem repair, which is built upon the
strategy of constructing a clean copy of a damaged structure and
committing the new structure into the metadata file atomically.

User programs will be able to update files atomically by opening an
O_TMPFILE, reflinking the source file to it, making whatever updates
they want to make, and exchange the relevant ranges of the temp file
with the original file.  If the updates are aligned with the file block
size, a new (since v2) flag provides for exchanging only the written
areas.  Callers can arrange for the update to be rejected if the
original file has been changed.

The intent behind this new userspace functionality is to enable atomic
rewrites of arbitrary parts of individual files.  For years, application
programmers wanting to ensure the atomicity of a file update had to
write the changes to a new file in the same directory, fsync the new
file, rename the new file on top of the old filename, and then fsync the
directory.  People get it wrong all the time, and $fs hacks abound.

The reference implementation in XFS creates a new log incompat feature
and log intent items to track high level progress of swapping ranges of
two files and finish interrupted work if the system goes down.  Sample
code can be found in the corresponding changes to xfs_io to exercise the
use case mentioned above.

Note that this function is /not/ the O_DIRECT atomic file writes concept
that has also been floating around for years.  It is also not the
RWF_ATOMIC patchset that has been shared.  This RFC is constructed
entirely in software, which means that there are no limitations other
than the general filesystem limits.

As a side note, the original motivation behind the kernel functionality
is online repair of file-based metadata.  The atomic file swap is
implemented as an atomic inode fork swap, which means that we can
implement online reconstruction of extended attributes and directories
by building a new one in another inode and atomically swap the contents.

Subsequent patchsets adapt the online filesystem repair code to use
atomic extent swapping.  This enables repair functions to construct a
clean copy of a directory, xattr information, symbolic links, realtime
bitmaps, and realtime summary information in a temporary inode.  If this
completes successfully, the new contents can be swapped atomically into
the inode being repaired.  This is essential to avoid making corruption
problems worse if the system goes down in the middle of running repair.

This patchset also ports the old XFS extent swap ioctl interface to use
the new extent swap code.

For userspace, this series also includes the userspace pieces needed to
test the new functionality, and a sample implementation of atomic file
updates.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=atomic-file-updates

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=atomic-file-updates

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=atomic-file-updates

xfsdocs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-documentation.git/log/?h=atomic-file-updates
---
 tests/xfs/1213     |   73 ++++++++++++++++
 tests/xfs/1213.out |    2 
 tests/xfs/1214     |  232 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 tests/xfs/1214.out |    2 
 4 files changed, 309 insertions(+)
 create mode 100755 tests/xfs/1213
 create mode 100644 tests/xfs/1213.out
 create mode 100755 tests/xfs/1214
 create mode 100644 tests/xfs/1214.out

[PATCHSET v29.0 5/8] fstests: detect deceptive filename extensions

[Darrick J. Wong]

Hi all,

In early 2023, malware researchers disclosed a phishing attack that was
targeted at people running Linux workstations.  The attack vector
involved the use of filenames containing what looked like a file
extension but instead contained a lookalike for the full stop (".")
and a common extension ("pdf").  Enhance xfs_scrub phase 5 to detect
these types of attacks and warn the system administrator.  Add
functional testing for this code.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=scrub-detect-deceptive-extensions

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=scrub-detect-deceptive-extensions
---
 tests/generic/453 |  111 +++++++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 99 insertions(+), 12 deletions(-)

[PATCHSET v29.0 6/8] fstests: test systemd background services

[Darrick J. Wong]

Hi all,

Add a couple of new tests to check that the systemd services for
xfs_scrub are at least minimally functional.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=scrub-improvements
---
 common/rc          |   22 ++++++++
 tests/xfs/1863     |  136 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 tests/xfs/1863.out |    6 ++
 3 files changed, 164 insertions(+)
 create mode 100755 tests/xfs/1863
 create mode 100644 tests/xfs/1863.out

[PATCHSET v29.0 7/8] fstests: use free space histograms to reduce fstrim runtime

[Darrick J. Wong]

Hi all,

This patchset dramatically reduces the runtime of the FITRIM calls made
during phase 8 of xfs_scrub.  It turns out that phase 8 can really get
bogged down if the free space contains a large number of very small
extents.  In these cases, the runtime can increase by an order of
magnitude to free less than 1% of the free space.  This is not worth the
time, since we're spending a lot of time to do very little work.  The
FITRIM ioctl allows us to specify a minimum extent length, so we can use
statistical methods to compute a minlen parameter.

It turns out xfs_db/spaceman already have the code needed to create
histograms of free space extent lengths.  We add the ability to compute
a CDF of the extent lengths, which make it easy to pick a minimum length
corresponding to 99% of the free space.  In most cases, this results in
dramatic reductions in phase 8 runtime.  Hence, move the histogram code
to libfrog, and wire up xfs_scrub, since phase 7 already walks the
fsmap.

We also add a new -o suboption to xfs_scrub so that people who /do/ want
to examine every free extent can do so.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=scrub-fstrim-minlen-freesp-histogram

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=scrub-fstrim-minlen-freesp-histogram
---
 tests/xfs/004 |   19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

[PATCHSET 8/8] fstests: test upgrading older features

[Darrick J. Wong]

Hi all,

Here is a general regression test to make sure that we can invoke the
xfs_repair feature to add new features to V5 filesystems without errors.
There are already targeted functionality tests for inobtcount and
bigtime; this new one exists as a general upgrade exerciser.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

This has been running on the djcloud for months with no problems.  Enjoy!
Comments and questions are, as always, welcome.

--D

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=upgrade-older-features

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=upgrade-older-features
---
 tests/xfs/1856     |  247 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 tests/xfs/1856.out |    2 
 2 files changed, 249 insertions(+)
 create mode 100755 tests/xfs/1856
 create mode 100644 tests/xfs/1856.out

[PATCHSET v29.0] xfs-documentation: atomic file updates

[Darrick J. Wong]

Hi all,

This patch documents the new log incompat feature and log intent items to
track high level progress of swapping ranges of two files and finish
interrupted work if the system goes down.

If you're going to start using this code, I strongly recommend pulling
from my git trees, which are linked below.

Comments and questions are, as always, welcome.

kernel git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=atomic-file-updates

xfsprogs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=atomic-file-updates

fstests git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h=atomic-file-updates

xfsdocs git tree:
https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-documentation.git/log/?h=atomic-file-updates
---
 .../allocation_groups.asciidoc                     |    7 +
 .../journaling_log.asciidoc                        |  111 ++++++++++++++++++++
 design/XFS_Filesystem_Structure/magic.asciidoc     |    2 
 3 files changed, 120 insertions(+)

[PATCH 1/7] xfs: speed up xfs_iwalk_adjust_start a little bit

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Replace the open-coded loop that recomputes freecount with a single call
to a bit weight function.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_iwalk.c |   13 ++-----------
 1 file changed, 2 insertions(+), 11 deletions(-)


diff --git a/fs/xfs/xfs_iwalk.c b/fs/xfs/xfs_iwalk.c
index b3275e8d47b60..4ce85423ef3e0 100644
--- a/fs/xfs/xfs_iwalk.c
+++ b/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. */

[PATCH 2/7] xfs: implement live inode scan for scrub

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

This patch implements a live file scanner for online fsck functions that
require the ability to walk a filesystem to gather metadata records and
stay informed about metadata changes to files that have already been
visited.

The iscan structure consists of two inode number cursors: one to track
which inode we want to visit next, and a second one to track which
inodes have already been visited.  This second cursor is key to
capturing live updates to files previously scanned while the main thread
continues scanning -- any inode greater than this value hasn't been
scanned and can go on its way; any other update must be incorporated
into the collected data.  It is critical for the scanning thraad to hold
exclusive access on the inode until after marking the inode visited.

This new code is a separate patch from the patchsets adding callers for
the sake of enabling the author to move patches around his tree with
ease.  The intended usage model for this code is roughly:

	xchk_iscan_start(iscan, 0, 0);
	while ((error = xchk_iscan_iter(sc, iscan, &ip)) == 1) {
		xfs_ilock(ip, ...);
		/* capture inode metadata */
		xchk_iscan_mark_visited(iscan, ip);
		xfs_iunlock(ip, ...);

		xfs_irele(ip);
	}
	xchk_iscan_stop(iscan);
	if (error)
		return error;

Hook functions for live updates can then do:

	if (xchk_iscan_want_live_update(...))
		/* update the captured inode metadata */

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Makefile      |    1 
 fs/xfs/scrub/iscan.c |  485 ++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/iscan.h |   63 ++++++
 fs/xfs/scrub/trace.c |    1 
 fs/xfs/scrub/trace.h |  106 +++++++++++
 5 files changed, 656 insertions(+)
 create mode 100644 fs/xfs/scrub/iscan.c
 create mode 100644 fs/xfs/scrub/iscan.h


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index fbe3cdc79036b..e5990a392ad62 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -159,6 +159,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   health.o \
 				   ialloc.o \
 				   inode.o \
+				   iscan.o \
 				   parent.o \
 				   readdir.o \
 				   refcount.o \
diff --git a/fs/xfs/scrub/iscan.c b/fs/xfs/scrub/iscan.c
new file mode 100644
index 0000000000000..d4c1fe0538df9
--- /dev/null
+++ b/fs/xfs/scrub/iscan.c
@@ -0,0 +1,485 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2021-2024 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_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_inode.h"
+#include "xfs_btree.h"
+#include "xfs_ialloc.h"
+#include "xfs_ialloc_btree.h"
+#include "xfs_ag.h"
+#include "xfs_error.h"
+#include "xfs_bit.h"
+#include "xfs_icache.h"
+#include "scrub/scrub.h"
+#include "scrub/iscan.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+
+/*
+ * Live File Scan
+ * ==============
+ *
+ * Live file scans walk every inode in a live filesystem.  This is more or
+ * less like a regular iwalk, except that when we're advancing the scan cursor,
+ * we must ensure that inodes cannot be added or deleted anywhere between the
+ * old cursor value and the new cursor value.  If we're advancing the cursor
+ * by one inode, the caller must hold that inode; if we're finding the next
+ * inode to scan, we must grab the AGI and hold it until we've updated the
+ * scan cursor.
+ *
+ * Callers are expected to use this code to scan all files in the filesystem to
+ * construct a new metadata index of some kind.  The scan races against other
+ * live updates, which means there must be a provision to update the new index
+ * when updates are made to inodes that already been scanned.  The iscan lock
+ * can be used in live update hook code to stop the scan and protect this data
+ * structure.
+ *
+ * To keep the new index up to date with other metadata updates being made to
+ * the live filesystem, it is assumed that the caller will add hooks as needed
+ * to be notified when a metadata update occurs.  The inode scanner must tell
+ * the hook code when an inode has been visited with xchk_iscan_mark_visit.
+ * Hook functions can use xchk_iscan_want_live_update to decide if the
+ * scanner's observations must be updated.
+ */
+
+/*
+ * Set *cursor to the next allocated inode after whatever it's set to now.
+ * If there are no more inodes in this AG, cursor is set to NULLAGINO.
+ */
+STATIC int
+xchk_iscan_find_next(
+	struct xchk_iscan	*iscan,
+	struct xfs_buf		*agi_bp,
+	struct xfs_perag	*pag,
+	xfs_agino_t		*cursor)
+{
+	struct xfs_scrub	*sc = iscan->sc;
+	struct xfs_inobt_rec_incore	rec;
+	struct xfs_btree_cur	*cur;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_trans	*tp = sc->tp;
+	xfs_agnumber_t		agno = pag->pag_agno;
+	xfs_agino_t		lastino = NULLAGINO;
+	xfs_agino_t		first, last;
+	xfs_agino_t		agino = *cursor;
+	int			has_rec;
+	int			error;
+
+	/* If the cursor is beyond the end of this AG, move to the next one. */
+	xfs_agino_range(mp, agno, &first, &last);
+	if (agino > last) {
+		*cursor = NULLAGINO;
+		return 0;
+	}
+
+	/*
+	 * Look up the inode chunk for the current cursor position.  If there
+	 * is no chunk here, we want the next one.
+	 */
+	cur = xfs_inobt_init_cursor(pag, tp, agi_bp, XFS_BTNUM_INO);
+	error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &has_rec);
+	if (!error && !has_rec)
+		error = xfs_btree_increment(cur, 0, &has_rec);
+	for (; !error; error = xfs_btree_increment(cur, 0, &has_rec)) {
+		xfs_inofree_t	allocmask;
+
+		/*
+		 * If we've run out of inobt records in this AG, move the
+		 * cursor on to the next AG and exit.  The caller can try
+		 * again with the next AG.
+		 */
+		if (!has_rec) {
+			*cursor = NULLAGINO;
+			break;
+		}
+
+		error = xfs_inobt_get_rec(cur, &rec, &has_rec);
+		if (error)
+			break;
+		if (!has_rec) {
+			error = -EFSCORRUPTED;
+			break;
+		}
+
+		/* Make sure that we always move forward. */
+		if (lastino != NULLAGINO &&
+		    XFS_IS_CORRUPT(mp, lastino >= rec.ir_startino)) {
+			error = -EFSCORRUPTED;
+			break;
+		}
+		lastino = rec.ir_startino + XFS_INODES_PER_CHUNK - 1;
+
+		/*
+		 * If this record only covers inodes that come before the
+		 * cursor, advance to the next record.
+		 */
+		if (rec.ir_startino + XFS_INODES_PER_CHUNK <= agino)
+			continue;
+
+		/*
+		 * If the incoming lookup put us in the middle of an inobt
+		 * record, mark it and the previous inodes "free" so that the
+		 * search for allocated inodes will start at the cursor.
+		 * We don't care about ir_freecount here.
+		 */
+		if (agino >= rec.ir_startino)
+			rec.ir_free |= xfs_inobt_maskn(0,
+						agino + 1 - rec.ir_startino);
+
+		/*
+		 * If there are allocated inodes in this chunk, find them
+		 * and update the scan cursor.
+		 */
+		allocmask = ~rec.ir_free;
+		if (hweight64(allocmask) > 0) {
+			int	next = xfs_lowbit64(allocmask);
+
+			ASSERT(next >= 0);
+			*cursor = rec.ir_startino + next;
+			break;
+		}
+	}
+
+	xfs_btree_del_cursor(cur, error);
+	return error;
+}
+
+/*
+ * Advance both the scan and the visited cursors.
+ *
+ * The inumber address space for a given filesystem is sparse, which means that
+ * the scan cursor can jump a long ways in a single iter() call.  There are no
+ * inodes in these sparse areas, so we must move the visited cursor forward at
+ * the same time so that the scan user can receive live updates for inodes that
+ * may get created once we release the AGI buffer.
+ */
+static inline void
+xchk_iscan_move_cursor(
+	struct xchk_iscan	*iscan,
+	xfs_agnumber_t		agno,
+	xfs_agino_t		agino)
+{
+	struct xfs_scrub	*sc = iscan->sc;
+	struct xfs_mount	*mp = sc->mp;
+
+	mutex_lock(&iscan->lock);
+	iscan->cursor_ino = XFS_AGINO_TO_INO(mp, agno, agino);
+	iscan->__visited_ino = iscan->cursor_ino - 1;
+	trace_xchk_iscan_move_cursor(iscan);
+	mutex_unlock(&iscan->lock);
+}
+
+/*
+ * Prepare to return agno/agino to the iscan caller by moving the lastino
+ * cursor to the previous inode.  Do this while we still hold the AGI so that
+ * no other threads can create or delete inodes in this AG.
+ */
+static inline void
+xchk_iscan_finish(
+	struct xchk_iscan	*iscan)
+{
+	mutex_lock(&iscan->lock);
+	iscan->cursor_ino = NULLFSINO;
+
+	/* All live updates will be applied from now on */
+	iscan->__visited_ino = NULLFSINO;
+
+	mutex_unlock(&iscan->lock);
+}
+
+/*
+ * Advance ino to the next inode that the inobt thinks is allocated, being
+ * careful to jump to the next AG if we've reached the right end of this AG's
+ * inode btree.  Advancing ino effectively means that we've pushed the inode
+ * scan forward, so set the iscan cursor to (ino - 1) so that our live update
+ * predicates will track inode allocations in that part of the inode number
+ * key space once we release the AGI buffer.
+ *
+ * Returns 1 if there's a new inode to examine, 0 if we've run out of inodes,
+ * -ECANCELED if the live scan aborted, or the usual negative errno.
+ */
+STATIC int
+xchk_iscan_advance(
+	struct xchk_iscan	*iscan,
+	struct xfs_perag	**pagp,
+	struct xfs_buf		**agi_bpp)
+{
+	struct xfs_scrub	*sc = iscan->sc;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_buf		*agi_bp;
+	struct xfs_perag	*pag;
+	xfs_agnumber_t		agno;
+	xfs_agino_t		agino;
+	int			ret;
+
+	ASSERT(iscan->cursor_ino >= iscan->__visited_ino);
+
+	do {
+		if (xchk_iscan_aborted(iscan))
+			return -ECANCELED;
+
+		agno = XFS_INO_TO_AGNO(mp, iscan->cursor_ino);
+		pag = xfs_perag_get(mp, agno);
+		if (!pag)
+			return -ECANCELED;
+
+		ret = xfs_ialloc_read_agi(pag, sc->tp, &agi_bp);
+		if (ret)
+			goto out_pag;
+
+		agino = XFS_INO_TO_AGINO(mp, iscan->cursor_ino);
+		ret = xchk_iscan_find_next(iscan, agi_bp, pag, &agino);
+		if (ret)
+			goto out_buf;
+
+		if (agino != NULLAGINO) {
+			/*
+			 * Found the next inode in this AG, so return it along
+			 * with the AGI buffer and the perag structure to
+			 * ensure it cannot go away.
+			 */
+			xchk_iscan_move_cursor(iscan, agno, agino);
+			*agi_bpp = agi_bp;
+			*pagp = pag;
+			return 1;
+		}
+
+		/*
+		 * Did not find any more inodes in this AG, move on to the next
+		 * AG.
+		 */
+		xchk_iscan_move_cursor(iscan, ++agno, 0);
+		xfs_trans_brelse(sc->tp, agi_bp);
+		xfs_perag_put(pag);
+
+		trace_xchk_iscan_advance_ag(iscan);
+	} while (agno < mp->m_sb.sb_agcount);
+
+	xchk_iscan_finish(iscan);
+	return 0;
+
+out_buf:
+	xfs_trans_brelse(sc->tp, agi_bp);
+out_pag:
+	xfs_perag_put(pag);
+	return ret;
+}
+
+/*
+ * Grabbing the inode failed, so we need to back up the scan and ask the caller
+ * to try to _advance the scan again.  Returns -EBUSY if we've run out of retry
+ * opportunities, -ECANCELED if the process has a fatal signal pending, or
+ * -EAGAIN if we should try again.
+ */
+STATIC int
+xchk_iscan_iget_retry(
+	struct xchk_iscan	*iscan,
+	bool			wait)
+{
+	ASSERT(iscan->cursor_ino == iscan->__visited_ino + 1);
+
+	if (!iscan->iget_timeout ||
+	    time_is_before_jiffies(iscan->__iget_deadline))
+		return -EBUSY;
+
+	if (wait) {
+		unsigned long	relax;
+
+		/*
+		 * Sleep for a period of time to let the rest of the system
+		 * catch up.  If we return early, someone sent a kill signal to
+		 * the calling process.
+		 */
+		relax = msecs_to_jiffies(iscan->iget_retry_delay);
+		trace_xchk_iscan_iget_retry_wait(iscan);
+
+		if (schedule_timeout_killable(relax) ||
+		    xchk_iscan_aborted(iscan))
+			return -ECANCELED;
+	}
+
+	iscan->cursor_ino--;
+	return -EAGAIN;
+}
+
+/*
+ * Grab an inode as part of an inode scan.  While scanning this inode, the
+ * caller must ensure that no other threads can modify the inode until a call
+ * to xchk_iscan_visit succeeds.
+ *
+ * Returns 0 and an incore inode; -EAGAIN if the caller should call again
+ * xchk_iscan_advance; -EBUSY if we couldn't grab an inode; -ECANCELED if
+ * there's a fatal signal pending; or some other negative errno.
+ */
+STATIC int
+xchk_iscan_iget(
+	struct xchk_iscan	*iscan,
+	struct xfs_perag	*pag,
+	struct xfs_buf		*agi_bp,
+	struct xfs_inode	**ipp)
+{
+	struct xfs_scrub	*sc = iscan->sc;
+	struct xfs_mount	*mp = sc->mp;
+	int			error;
+
+	error = xfs_iget(sc->mp, sc->tp, iscan->cursor_ino, XFS_IGET_NORETRY,
+			0, ipp);
+	xfs_trans_brelse(sc->tp, agi_bp);
+	xfs_perag_put(pag);
+
+	trace_xchk_iscan_iget(iscan, error);
+
+	if (error == -ENOENT || error == -EAGAIN) {
+		/*¬
+		 * It's possible that this inode has lost all of its links but
+		 * hasn't yet been inactivated.  If we don't have a transaction
+		 * or it's not writable, flush the inodegc workers and wait.
+		 */
+		xfs_inodegc_flush(mp);
+		return xchk_iscan_iget_retry(iscan, true);
+	}
+
+	if (error == -EINVAL) {
+		/*
+		 * We thought the inode was allocated, but the inode btree
+		 * lookup failed, which means that it was freed since the last
+		 * time we advanced the cursor.  Back up and try again.  This
+		 * should never happen since still hold the AGI buffer from the
+		 * inobt check, but we need to be careful about infinite loops.
+		 */
+		return xchk_iscan_iget_retry(iscan, false);
+	}
+
+	return error;
+}
+
+/*
+ * Advance the inode scan cursor to the next allocated inode and return the
+ * incore inode structure associated with it.
+ *
+ * Returns 1 if there's a new inode to examine, 0 if we've run out of inodes,
+ * -ECANCELED if the live scan aborted, -EBUSY if the incore inode could not be
+ * grabbed, or the usual negative errno.
+ *
+ * If the function returns -EBUSY and the caller can handle skipping an inode,
+ * it may call this function again to continue the scan with the next allocated
+ * inode.
+ */
+int
+xchk_iscan_iter(
+	struct xchk_iscan	*iscan,
+	struct xfs_inode	**ipp)
+{
+	struct xfs_scrub	*sc = iscan->sc;
+	int			ret;
+
+	if (iscan->iget_timeout)
+		iscan->__iget_deadline = jiffies +
+					 msecs_to_jiffies(iscan->iget_timeout);
+
+	do {
+		struct xfs_buf	*agi_bp = NULL;
+		struct xfs_perag *pag = NULL;
+
+		ret = xchk_iscan_advance(iscan, &pag, &agi_bp);
+		if (ret != 1)
+			return ret;
+
+		if (xchk_iscan_aborted(iscan)) {
+			xfs_trans_brelse(sc->tp, agi_bp);
+			xfs_perag_put(pag);
+			ret = -ECANCELED;
+			break;
+		}
+
+		ret = xchk_iscan_iget(iscan, pag, agi_bp, ipp);
+	} while (ret == -EAGAIN);
+
+	if (!ret)
+		return 1;
+
+	return ret;
+}
+
+
+/* Mark this inode scan finished and release resources. */
+void
+xchk_iscan_teardown(
+	struct xchk_iscan	*iscan)
+{
+	xchk_iscan_finish(iscan);
+	mutex_destroy(&iscan->lock);
+}
+
+/*
+ * Set ourselves up to start an inode scan.  If the @iget_timeout and
+ * @iget_retry_delay parameters are set, the scan will try to iget each inode
+ * for @iget_timeout milliseconds.  If an iget call indicates that the inode is
+ * waiting to be inactivated, the CPU will relax for @iget_retry_delay
+ * milliseconds after pushing the inactivation workers.
+ */
+void
+xchk_iscan_start(
+	struct xfs_scrub	*sc,
+	unsigned int		iget_timeout,
+	unsigned int		iget_retry_delay,
+	struct xchk_iscan	*iscan)
+{
+	iscan->sc = sc;
+	clear_bit(XCHK_ISCAN_OPSTATE_ABORTED, &iscan->__opstate);
+	iscan->iget_timeout = iget_timeout;
+	iscan->iget_retry_delay = iget_retry_delay;
+	iscan->__visited_ino = 0;
+	iscan->cursor_ino = 0;
+	mutex_init(&iscan->lock);
+
+	trace_xchk_iscan_start(iscan);
+}
+
+/*
+ * Mark this inode as having been visited.  Callers must hold a sufficiently
+ * exclusive lock on the inode to prevent concurrent modifications.
+ */
+void
+xchk_iscan_mark_visited(
+	struct xchk_iscan	*iscan,
+	struct xfs_inode	*ip)
+{
+	mutex_lock(&iscan->lock);
+	iscan->__visited_ino = ip->i_ino;
+	trace_xchk_iscan_visit(iscan);
+	mutex_unlock(&iscan->lock);
+}
+
+/*
+ * Do we need a live update for this inode?  This is true if the scanner thread
+ * has visited this inode and the scan hasn't been aborted due to errors.
+ * Callers must hold a sufficiently exclusive lock on the inode to prevent
+ * scanners from reading any inode metadata.
+ */
+bool
+xchk_iscan_want_live_update(
+	struct xchk_iscan	*iscan,
+	xfs_ino_t		ino)
+{
+	bool			ret;
+
+	if (xchk_iscan_aborted(iscan))
+		return false;
+
+	mutex_lock(&iscan->lock);
+	trace_xchk_iscan_want_live_update(iscan, ino);
+	ret = iscan->__visited_ino >= ino;
+	mutex_unlock(&iscan->lock);
+
+	return ret;
+}
diff --git a/fs/xfs/scrub/iscan.h b/fs/xfs/scrub/iscan.h
new file mode 100644
index 0000000000000..c25f121859ce2
--- /dev/null
+++ b/fs/xfs/scrub/iscan.h
@@ -0,0 +1,63 @@
+/* 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 inode that will be examined next. */
+	xfs_ino_t		cursor_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;
+};
+
+/* 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_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__ */
diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c
index d0e24ffaf7547..4542eeebab6f1 100644
--- a/fs/xfs/scrub/trace.c
+++ b/fs/xfs/scrub/trace.c
@@ -20,6 +20,7 @@
 #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
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 6bbb4e8639dca..138637198ad86 100644
--- a/fs/xfs/scrub/trace.h
+++ b/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
@@ -1119,6 +1121,110 @@ 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_advance_ag);
+DEFINE_ISCAN_EVENT(xchk_iscan_start);
+
+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, cursor)
+		__field(xfs_ino_t, visited)
+		__field(xfs_ino_t, ino)
+	),
+	TP_fast_assign(
+		__entry->dev = iscan->sc->mp->m_super->s_dev;
+		__entry->cursor = iscan->cursor_ino;
+		__entry->visited = iscan->__visited_ino;
+		__entry->ino = ino;
+	),
+	TP_printk("dev %d:%d iscan cursor 0x%llx visited 0x%llx ino 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __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);
+
+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_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)
 

[PATCH 3/7] xfs: allow scrub to hook metadata updates in other writers

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Certain types of filesystem metadata can only be checked by scanning
every file in the entire filesystem.  Specific examples of this include
quota counts, file link counts, and reverse mappings of file extents.
Directory and parent pointer reconstruction may also fall into this
category.  File scanning is much trickier than scanning AG metadata
because we have to take inode locks in the same order as the rest of
[VX]FS, we can't be holding buffer locks when we do that, and scanning
the whole filesystem takes time.

Earlier versions of the online repair patchset relied heavily on
fsfreeze as a means to quiesce the filesystem so that we could take
locks in the proper order without worrying about concurrent updates from
other writers.  Reviewers of those patches opined that freezing the
entire fs to check and repair something was not sufficiently better than
unmounting to run fsck offline.  I don't agree with that 100%, but the
message was clear: find a way to repair things that minimizes the
quiet period where nobody can write to the filesystem.

Generally, building btree indexes online can be split into two phases: a
collection phase where we compute the records that will be put into the
new btree; and a construction phase, where we construct the physical
btree blocks and persist them.  While it's simple to hold resource locks
for the entirety of the two phases to ensure that the new index is
consistent with the rest of the system, we don't need to hold resource
locks during the collection phase if we have a means to receive live
updates of other work going on elsewhere in the system.

The goal of this patch, then, is to enable online fsck to learn about
metadata updates going on in other threads while it constructs a shadow
copy of the metadata records to verify or correct the real metadata.  To
minimize the overhead when online fsck isn't running, we use srcu
notifiers because they prioritize fast access to the notifier call chain
(particularly when the chain is empty) at a cost to configuring
notifiers.  Online fsck should be relatively infrequent, so this is
acceptable.

The intended usage model is fairly simple.  Code that modifies a
metadata structure of interest should declare a xfs_hook_chain structure
in some well defined place, and call xfs_hook_call whenever an update
happens.  Online fsck code should define a struct notifier_block and use
xfs_hook_add to attach the block to the chain, along with a function to
be called.  This function should synchronize with the fsck scanner to
update whatever in-memory data the scanner is collecting.  When
finished, xfs_hook_del removes the notifier from the list and waits for
them all to complete.

On the author's computer, calling an empty srcu notifier chain was
observed to have an overhead averaging ~40ns with a maximum of 60ns.
Adding a no-op notifier function increased the average to ~58ns and
66ns.  When the quotacheck live update notifier is attached, the average
increases to ~322ns with a max of 372ns to update scrub's in-memory
observation data, assuming no lock contention.

With jump labels enabled, calls to empty srcu notifier chains are elided
from the call sites when there are no hooks registered, which means that
the overhead is 0.36ns when fsck is not running.  For compilers that do
not support jump labels (all major architectures do), the overhead of a
no-op notifier call is less bad (on a many-cpu system) than the atomic
counter ops, so we make the hook switch itself a nop.

Note: This new code is also split out as a separate patch from its
initial user so that the author can move patches around his tree with
ease.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Kconfig     |    5 ++++
 fs/xfs/Makefile    |    1 +
 fs/xfs/xfs_hooks.c |   53 +++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_hooks.h |   68 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_linux.h |    1 +
 5 files changed, 128 insertions(+)
 create mode 100644 fs/xfs/xfs_hooks.c
 create mode 100644 fs/xfs/xfs_hooks.h


diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index 567fb37274d35..fa7eb3e2a2484 100644
--- a/fs/xfs/Kconfig
+++ b/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
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index e5990a392ad62..7a5c637e449e5 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -137,6 +137,7 @@ 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)
diff --git a/fs/xfs/xfs_hooks.c b/fs/xfs/xfs_hooks.c
new file mode 100644
index 0000000000000..757aadc90eb03
--- /dev/null
+++ b/fs/xfs/xfs_hooks.c
@@ -0,0 +1,53 @@
+// 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)
+{
+	srcu_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 srcu_notifier_chain_register(&chain->head, &hook->nb);
+}
+
+/* Remove a previously installed hook. */
+void
+xfs_hooks_del(
+	struct xfs_hooks	*chain,
+	struct xfs_hook		*hook)
+{
+	srcu_notifier_chain_unregister(&chain->head, &hook->nb);
+	rcu_barrier();
+}
+
+/* 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 srcu_notifier_call_chain(&chain->head, val, priv);
+}
diff --git a/fs/xfs/xfs_hooks.h b/fs/xfs/xfs_hooks.h
new file mode 100644
index 0000000000000..f3d0631147f28
--- /dev/null
+++ b/fs/xfs/xfs_hooks.h
@@ -0,0 +1,68 @@
+// 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 srcu_notifier_head	head;
+};
+#else
+struct xfs_hooks { /* empty */ };
+#endif
+
+/*
+ * If hooks and jump labels are enabled, we use jump labels (aka patching of
+ * the code segment) to avoid the minute overhead of calling an empty notifier
+ * chain when we know there are no callers.  If hooks are enabled without jump
+ * labels, hardwire the predicate to true because calling an empty srcu
+ * notifier chain isn't so expensive.
+ */
+#if defined(CONFIG_JUMP_LABEL) && defined(CONFIG_XFS_LIVE_HOOKS)
+# 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)
+#elif defined(CONFIG_XFS_LIVE_HOOKS)
+# 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)	(true)
+#else
+# 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)
+#endif /* JUMP_LABEL && XFS_LIVE_HOOKS */
+
+#ifdef CONFIG_XFS_LIVE_HOOKS
+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
+# define xfs_hooks_init(chain)			((void)0)
+# define xfs_hooks_call(chain, val, priv)	(NOTIFY_DONE)
+#endif
+
+#endif /* XFS_HOOKS_H_ */
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index d7873e0360f0b..73854ad981eb5 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -82,6 +82,7 @@ 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

[PATCH 4/7] xfs: allow blocking notifier chains with filesystem hooks

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Make it so that we can switch between notifier chain implementations for
testing purposes.  On the author's test system, calling an empty srcu
notifier chain cost about 19ns per call, vs. 4ns for a blocking notifier
chain.  Hm.  Might we actually want regular blocking notifiers?

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Kconfig     |   31 +++++++++++++++++++++++++++++++
 fs/xfs/xfs_hooks.c |   41 +++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_hooks.h |    6 +++++-
 3 files changed, 77 insertions(+), 1 deletion(-)


diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index fa7eb3e2a2484..dbcf55377e9fe 100644
--- a/fs/xfs/Kconfig
+++ b/fs/xfs/Kconfig
@@ -165,6 +165,37 @@ config XFS_ONLINE_SCRUB_STATS
 
 	  If unsure, say N.
 
+choice
+	prompt "XFS hook implementation"
+	depends on XFS_FS && XFS_LIVE_HOOKS && XFS_ONLINE_SCRUB
+	default XFS_LIVE_HOOKS_BLOCKING if HAVE_ARCH_JUMP_LABEL
+	default XFS_LIVE_HOOKS_SRCU if !HAVE_ARCH_JUMP_LABEL
+	help
+	  Pick one
+
+config XFS_LIVE_HOOKS_SRCU
+	bool "SRCU notifier chains"
+	help
+	  Use SRCU notifier chains for filesystem hooks.  These have very low
+	  overhead for event initiators (the main filesystem) and higher
+	  overhead for chain modifiers (scrub waits for RCU grace).  This is
+	  the best option when jump labels are not supported or there are many
+	  CPUs in the system.
+
+	  This may cause problems with CPU hotplug invoking reclaim invoking
+	  XFS.
+
+config XFS_LIVE_HOOKS_BLOCKING
+	bool "Blocking notifier chains"
+	help
+	  Use blocking notifier chains for filesystem hooks.  These have medium
+	  overhead for event initiators (the main fs) and chain modifiers
+	  (scrub) due to their use of rwsems.  This is the best option when
+	  jump labels can be used to eliminate overhead for the filesystem when
+	  scrub is not running.
+
+endchoice
+
 config XFS_ONLINE_REPAIR
 	bool "XFS online metadata repair support"
 	default n
diff --git a/fs/xfs/xfs_hooks.c b/fs/xfs/xfs_hooks.c
index 757aadc90eb03..8f7e449442972 100644
--- a/fs/xfs/xfs_hooks.c
+++ b/fs/xfs/xfs_hooks.c
@@ -12,6 +12,7 @@
 #include "xfs_ag.h"
 #include "xfs_trace.h"
 
+#if defined(CONFIG_XFS_LIVE_HOOKS_SRCU)
 /* Initialize a notifier chain. */
 void
 xfs_hooks_init(
@@ -51,3 +52,43 @@ xfs_hooks_call(
 {
 	return srcu_notifier_call_chain(&chain->head, val, priv);
 }
+#elif defined(CONFIG_XFS_LIVE_HOOKS_BLOCKING)
+/* 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);
+}
+#endif /* CONFIG_XFS_LIVE_HOOKS_BLOCKING */
diff --git a/fs/xfs/xfs_hooks.h b/fs/xfs/xfs_hooks.h
index f3d0631147f28..751f348a8cc0f 100644
--- a/fs/xfs/xfs_hooks.h
+++ b/fs/xfs/xfs_hooks.h
@@ -6,10 +6,14 @@
 #ifndef XFS_HOOKS_H_
 #define XFS_HOOKS_H_
 
-#ifdef CONFIG_XFS_LIVE_HOOKS
+#if defined(CONFIG_XFS_LIVE_HOOKS_SRCU)
 struct xfs_hooks {
 	struct srcu_notifier_head	head;
 };
+#elif defined(CONFIG_XFS_LIVE_HOOKS_BLOCKING)
+struct xfs_hooks {
+	struct blocking_notifier_head	head;
+};
 #else
 struct xfs_hooks { /* empty */ };
 #endif

[PATCH 5/7] xfs: stagger the starting AG of scrub iscans to reduce contention

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Online directory and parent repairs on parent-pointer equipped
filesystems have shown that starting a large number of parallel iscans
causes a lot of AGI buffer contention.  Try to reduce this by making it
so that iscans scan wrap around the end of the filesystem, and using a
rotor to stagger where each scanner begins.  Surprisingly, this boosts
CPU utilization (on the author's test machines) from effectively
single-threaded to 160%.  Not great, but see the next patch.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/iscan.c |   87 ++++++++++++++++++++++++++++++++++++++++++++------
 fs/xfs/scrub/iscan.h |    7 ++++
 fs/xfs/scrub/trace.h |    7 +++-
 3 files changed, 89 insertions(+), 12 deletions(-)


diff --git a/fs/xfs/scrub/iscan.c b/fs/xfs/scrub/iscan.c
index d4c1fe0538df9..ef78620dcc846 100644
--- a/fs/xfs/scrub/iscan.c
+++ b/fs/xfs/scrub/iscan.c
@@ -170,10 +170,24 @@ xchk_iscan_move_cursor(
 {
 	struct xfs_scrub	*sc = iscan->sc;
 	struct xfs_mount	*mp = sc->mp;
+	xfs_ino_t		cursor, visited;
+
+	BUILD_BUG_ON(XFS_MAXINUMBER == NULLFSINO);
+
+	/*
+	 * Special-case ino == 0 here so that we never set visited_ino to
+	 * NULLFSINO when wrapping around EOFS, for that will let through all
+	 * live updates.
+	 */
+	cursor = XFS_AGINO_TO_INO(mp, agno, agino);
+	if (cursor == 0)
+		visited = XFS_MAXINUMBER;
+	else
+		visited = cursor - 1;
 
 	mutex_lock(&iscan->lock);
-	iscan->cursor_ino = XFS_AGINO_TO_INO(mp, agno, agino);
-	iscan->__visited_ino = iscan->cursor_ino - 1;
+	iscan->cursor_ino = cursor;
+	iscan->__visited_ino = visited;
 	trace_xchk_iscan_move_cursor(iscan);
 	mutex_unlock(&iscan->lock);
 }
@@ -257,12 +271,13 @@ xchk_iscan_advance(
 		 * Did not find any more inodes in this AG, move on to the next
 		 * AG.
 		 */
-		xchk_iscan_move_cursor(iscan, ++agno, 0);
+		agno = (agno + 1) % mp->m_sb.sb_agcount;
+		xchk_iscan_move_cursor(iscan, agno, 0);
 		xfs_trans_brelse(sc->tp, agi_bp);
 		xfs_perag_put(pag);
 
 		trace_xchk_iscan_advance_ag(iscan);
-	} while (agno < mp->m_sb.sb_agcount);
+	} while (iscan->cursor_ino != iscan->scan_start_ino);
 
 	xchk_iscan_finish(iscan);
 	return 0;
@@ -420,6 +435,23 @@ xchk_iscan_teardown(
 	mutex_destroy(&iscan->lock);
 }
 
+/* Pick an AG from which to start a scan. */
+static inline xfs_ino_t
+xchk_iscan_rotor(
+	struct xfs_mount	*mp)
+{
+	static atomic_t		agi_rotor;
+	unsigned int		r = atomic_inc_return(&agi_rotor) - 1;
+
+	/*
+	 * Rotoring *backwards* through the AGs, so we add one here before
+	 * subtracting from the agcount to arrive at an AG number.
+	 */
+	r = (r % mp->m_sb.sb_agcount) + 1;
+
+	return XFS_AGINO_TO_INO(mp, mp->m_sb.sb_agcount - r, 0);
+}
+
 /*
  * Set ourselves up to start an inode scan.  If the @iget_timeout and
  * @iget_retry_delay parameters are set, the scan will try to iget each inode
@@ -434,15 +466,20 @@ xchk_iscan_start(
 	unsigned int		iget_retry_delay,
 	struct xchk_iscan	*iscan)
 {
+	xfs_ino_t		start_ino;
+
+	start_ino = xchk_iscan_rotor(sc->mp);
+
 	iscan->sc = sc;
 	clear_bit(XCHK_ISCAN_OPSTATE_ABORTED, &iscan->__opstate);
 	iscan->iget_timeout = iget_timeout;
 	iscan->iget_retry_delay = iget_retry_delay;
-	iscan->__visited_ino = 0;
-	iscan->cursor_ino = 0;
+	iscan->__visited_ino = start_ino;
+	iscan->cursor_ino = start_ino;
+	iscan->scan_start_ino = start_ino;
 	mutex_init(&iscan->lock);
 
-	trace_xchk_iscan_start(iscan);
+	trace_xchk_iscan_start(iscan, start_ino);
 }
 
 /*
@@ -471,15 +508,45 @@ xchk_iscan_want_live_update(
 	struct xchk_iscan	*iscan,
 	xfs_ino_t		ino)
 {
-	bool			ret;
+	bool			ret = false;
 
 	if (xchk_iscan_aborted(iscan))
 		return false;
 
 	mutex_lock(&iscan->lock);
+
 	trace_xchk_iscan_want_live_update(iscan, ino);
-	ret = iscan->__visited_ino >= ino;
+
+	/* Scan is finished, caller should receive all updates. */
+	if (iscan->__visited_ino == NULLFSINO) {
+		ret = true;
+		goto unlock;
+	}
+
+	/*
+	 * The visited cursor hasn't yet wrapped around the end of the FS.  If
+	 * @ino is inside the starred range, the caller should receive updates:
+	 *
+	 * 0 ------------ S ************ V ------------ EOFS
+	 */
+	if (iscan->scan_start_ino <= iscan->__visited_ino) {
+		if (ino >= iscan->scan_start_ino &&
+		    ino <= iscan->__visited_ino)
+			ret = true;
+
+		goto unlock;
+	}
+
+	/*
+	 * The visited cursor wrapped around the end of the FS.  If @ino is
+	 * inside the starred range, the caller should receive updates:
+	 *
+	 * 0 ************ V ------------ S ************ EOFS
+	 */
+	if (ino >= iscan->scan_start_ino || ino <= iscan->__visited_ino)
+		ret = true;
+
+unlock:
 	mutex_unlock(&iscan->lock);
-
 	return ret;
 }
diff --git a/fs/xfs/scrub/iscan.h b/fs/xfs/scrub/iscan.h
index c25f121859ce2..0db97d98ee8da 100644
--- a/fs/xfs/scrub/iscan.h
+++ b/fs/xfs/scrub/iscan.h
@@ -12,6 +12,13 @@ struct xchk_iscan {
 	/* 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;
 
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 138637198ad86..92d1f3b6203db 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -1146,25 +1146,27 @@ DEFINE_EVENT(xchk_iscan_class, name, \
 DEFINE_ISCAN_EVENT(xchk_iscan_move_cursor);
 DEFINE_ISCAN_EVENT(xchk_iscan_visit);
 DEFINE_ISCAN_EVENT(xchk_iscan_advance_ag);
-DEFINE_ISCAN_EVENT(xchk_iscan_start);
 
 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 cursor 0x%llx visited 0x%llx ino 0x%llx",
+	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)
@@ -1174,6 +1176,7 @@ 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),

[PATCH 6/7] xfs: cache a bunch of inodes for repair scans

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

After observing xfs_scrub taking forever to rebuild parent pointers on a
pptrs enabled filesystem, I decided to profile what the system was
doing.  It turns out that when there are a lot of threads trying to scan
the filesystem, most of our time is spent contending on AGI buffer
locks.  Given that we're walking the inobt records anyway, we can often
tell ahead of time when there's a bunch of (up to 64) consecutive inodes
that we could grab all at once.

Do this to amortize the cost of taking the AGI lock across as many
inodes as we possibly can.  On the author's system this seems to improve
parallel throughput from barely one and a half cores to slightly
sublinear scaling.  The obvious antipattern here of course is where the
freemask has every other bit set (e.g. all 0xA's)

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/iscan.c |  159 +++++++++++++++++++++++++++++++++++++++++---------
 fs/xfs/scrub/iscan.h |    7 ++
 fs/xfs/scrub/trace.h |   23 +++++++
 3 files changed, 159 insertions(+), 30 deletions(-)


diff --git a/fs/xfs/scrub/iscan.c b/fs/xfs/scrub/iscan.c
index ef78620dcc846..ba93258c47030 100644
--- a/fs/xfs/scrub/iscan.c
+++ b/fs/xfs/scrub/iscan.c
@@ -60,6 +60,7 @@ xchk_iscan_find_next(
 	struct xchk_iscan	*iscan,
 	struct xfs_buf		*agi_bp,
 	struct xfs_perag	*pag,
+	xfs_inofree_t		*allocmaskp,
 	xfs_agino_t		*cursor)
 {
 	struct xfs_scrub	*sc = iscan->sc;
@@ -145,6 +146,7 @@ xchk_iscan_find_next(
 
 			ASSERT(next >= 0);
 			*cursor = rec.ir_startino + next;
+			*allocmaskp = allocmask >> next;
 			break;
 		}
 	}
@@ -225,7 +227,8 @@ STATIC int
 xchk_iscan_advance(
 	struct xchk_iscan	*iscan,
 	struct xfs_perag	**pagp,
-	struct xfs_buf		**agi_bpp)
+	struct xfs_buf		**agi_bpp,
+	xfs_inofree_t		*allocmaskp)
 {
 	struct xfs_scrub	*sc = iscan->sc;
 	struct xfs_mount	*mp = sc->mp;
@@ -251,7 +254,8 @@ xchk_iscan_advance(
 			goto out_pag;
 
 		agino = XFS_INO_TO_AGINO(mp, iscan->cursor_ino);
-		ret = xchk_iscan_find_next(iscan, agi_bp, pag, &agino);
+		ret = xchk_iscan_find_next(iscan, agi_bp, pag, allocmaskp,
+				&agino);
 		if (ret)
 			goto out_buf;
 
@@ -331,29 +335,35 @@ xchk_iscan_iget_retry(
  * caller must ensure that no other threads can modify the inode until a call
  * to xchk_iscan_visit succeeds.
  *
- * Returns 0 and an incore inode; -EAGAIN if the caller should call again
- * xchk_iscan_advance; -EBUSY if we couldn't grab an inode; -ECANCELED if
- * there's a fatal signal pending; or some other negative errno.
+ * Returns the number of incore inodes grabbed; -EAGAIN if the caller should
+ * call again xchk_iscan_advance; -EBUSY if we couldn't grab an inode;
+ * -ECANCELED if there's a fatal signal pending; or some other negative errno.
  */
 STATIC int
 xchk_iscan_iget(
 	struct xchk_iscan	*iscan,
 	struct xfs_perag	*pag,
 	struct xfs_buf		*agi_bp,
-	struct xfs_inode	**ipp)
+	xfs_inofree_t		allocmask)
 {
 	struct xfs_scrub	*sc = iscan->sc;
 	struct xfs_mount	*mp = sc->mp;
+	xfs_ino_t		ino = iscan->cursor_ino;
+	unsigned int		idx = 0;
 	int			error;
 
-	error = xfs_iget(sc->mp, sc->tp, iscan->cursor_ino, XFS_IGET_NORETRY,
-			0, ipp);
-	xfs_trans_brelse(sc->tp, agi_bp);
-	xfs_perag_put(pag);
+	ASSERT(iscan->__inodes[0] == NULL);
+
+	/* Fill the first slot in the inode array. */
+	error = xfs_iget(sc->mp, sc->tp, ino, XFS_IGET_NORETRY, 0,
+			&iscan->__inodes[idx]);
 
 	trace_xchk_iscan_iget(iscan, error);
 
 	if (error == -ENOENT || error == -EAGAIN) {
+		xfs_trans_brelse(sc->tp, agi_bp);
+		xfs_perag_put(pag);
+
 		/*¬
 		 * It's possible that this inode has lost all of its links but
 		 * hasn't yet been inactivated.  If we don't have a transaction
@@ -364,6 +374,9 @@ xchk_iscan_iget(
 	}
 
 	if (error == -EINVAL) {
+		xfs_trans_brelse(sc->tp, agi_bp);
+		xfs_perag_put(pag);
+
 		/*
 		 * We thought the inode was allocated, but the inode btree
 		 * lookup failed, which means that it was freed since the last
@@ -374,25 +387,47 @@ xchk_iscan_iget(
 		return xchk_iscan_iget_retry(iscan, false);
 	}
 
-	return error;
+	if (error) {
+		xfs_trans_brelse(sc->tp, agi_bp);
+		xfs_perag_put(pag);
+		return error;
+	}
+	idx++;
+	ino++;
+	allocmask >>= 1;
+
+	/*
+	 * Now that we've filled the first slot in __inodes, try to fill the
+	 * rest of the batch with consecutively ordered inodes.  to reduce the
+	 * number of _iter calls.  If we can't get an inode, we stop and return
+	 * what we have.
+	 */
+	for (; allocmask & 1; allocmask >>= 1, ino++, idx++) {
+		ASSERT(iscan->__inodes[idx] == NULL);
+
+		error = xfs_iget(sc->mp, sc->tp, ino, XFS_IGET_NORETRY, 0,
+				&iscan->__inodes[idx]);
+		if (error)
+			break;
+
+		mutex_lock(&iscan->lock);
+		iscan->cursor_ino = ino;
+		mutex_unlock(&iscan->lock);
+	}
+
+	trace_xchk_iscan_iget_batch(sc->mp, iscan, idx);
+	xfs_trans_brelse(sc->tp, agi_bp);
+	xfs_perag_put(pag);
+	return idx;
 }
 
 /*
- * Advance the inode scan cursor to the next allocated inode and return the
- * incore inode structure associated with it.
- *
- * Returns 1 if there's a new inode to examine, 0 if we've run out of inodes,
- * -ECANCELED if the live scan aborted, -EBUSY if the incore inode could not be
- * grabbed, or the usual negative errno.
- *
- * If the function returns -EBUSY and the caller can handle skipping an inode,
- * it may call this function again to continue the scan with the next allocated
- * inode.
+ * Advance the inode scan cursor to the next allocated inode and return up to
+ * 64 consecutive allocated inodes starting with the cursor position.
  */
-int
-xchk_iscan_iter(
-	struct xchk_iscan	*iscan,
-	struct xfs_inode	**ipp)
+STATIC int
+xchk_iscan_iter_batch(
+	struct xchk_iscan	*iscan)
 {
 	struct xfs_scrub	*sc = iscan->sc;
 	int			ret;
@@ -404,8 +439,9 @@ xchk_iscan_iter(
 	do {
 		struct xfs_buf	*agi_bp = NULL;
 		struct xfs_perag *pag = NULL;
+		xfs_inofree_t	allocmask = 0;
 
-		ret = xchk_iscan_advance(iscan, &pag, &agi_bp);
+		ret = xchk_iscan_advance(iscan, &pag, &agi_bp, &allocmask);
 		if (ret != 1)
 			return ret;
 
@@ -416,21 +452,74 @@ xchk_iscan_iter(
 			break;
 		}
 
-		ret = xchk_iscan_iget(iscan, pag, agi_bp, ipp);
+		ret = xchk_iscan_iget(iscan, pag, agi_bp, allocmask);
 	} while (ret == -EAGAIN);
 
-	if (!ret)
-		return 1;
-
 	return ret;
 }
 
+/*
+ * Advance the inode scan cursor to the next allocated inode and return the
+ * incore inode structure associated with it.
+ *
+ * Returns 1 if there's a new inode to examine, 0 if we've run out of inodes,
+ * -ECANCELED if the live scan aborted, -EBUSY if the incore inode could not be
+ * grabbed, or the usual negative errno.
+ *
+ * If the function returns -EBUSY and the caller can handle skipping an inode,
+ * it may call this function again to continue the scan with the next allocated
+ * inode.
+ */
+int
+xchk_iscan_iter(
+	struct xchk_iscan	*iscan,
+	struct xfs_inode	**ipp)
+{
+	unsigned int		i;
+	int			error;
+
+	/* Find a cached inode, or go get another batch. */
+	for (i = 0; i < XFS_INODES_PER_CHUNK; i++) {
+		if (iscan->__inodes[i])
+			goto foundit;
+	}
+
+	error = xchk_iscan_iter_batch(iscan);
+	if (error <= 0)
+		return error;
+
+	ASSERT(iscan->__inodes[0] != NULL);
+	i = 0;
+
+foundit:
+	/* Give the caller our reference. */
+	*ipp = iscan->__inodes[i];
+	iscan->__inodes[i] = NULL;
+	return 1;
+}
+
+/* Clean up an xfs_iscan_iter call by dropping any inodes that we still hold. */
+void
+xchk_iscan_iter_finish(
+	struct xchk_iscan	*iscan)
+{
+	struct xfs_scrub	*sc = iscan->sc;
+	unsigned int		i;
+
+	for (i = 0; i < XFS_INODES_PER_CHUNK; i++) {
+		if (iscan->__inodes[i]) {
+			xchk_irele(sc, iscan->__inodes[i]);
+			iscan->__inodes[i] = NULL;
+		}
+	}
+}
 
 /* Mark this inode scan finished and release resources. */
 void
 xchk_iscan_teardown(
 	struct xchk_iscan	*iscan)
 {
+	xchk_iscan_iter_finish(iscan);
 	xchk_iscan_finish(iscan);
 	mutex_destroy(&iscan->lock);
 }
@@ -478,6 +567,7 @@ xchk_iscan_start(
 	iscan->cursor_ino = start_ino;
 	iscan->scan_start_ino = start_ino;
 	mutex_init(&iscan->lock);
+	memset(iscan->__inodes, 0, sizeof(iscan->__inodes));
 
 	trace_xchk_iscan_start(iscan, start_ino);
 }
@@ -523,6 +613,15 @@ xchk_iscan_want_live_update(
 		goto unlock;
 	}
 
+	/*
+	 * No inodes have been visited yet, so the visited cursor points at the
+	 * start of the scan range.  The caller should not receive any updates.
+	 */
+	if (iscan->scan_start_ino == iscan->__visited_ino) {
+		ret = false;
+		goto unlock;
+	}
+
 	/*
 	 * The visited cursor hasn't yet wrapped around the end of the FS.  If
 	 * @ino is inside the starred range, the caller should receive updates:
diff --git a/fs/xfs/scrub/iscan.h b/fs/xfs/scrub/iscan.h
index 0db97d98ee8da..f7317af807ddc 100644
--- a/fs/xfs/scrub/iscan.h
+++ b/fs/xfs/scrub/iscan.h
@@ -41,6 +41,12 @@ struct xchk_iscan {
 
 	/* 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.
+	 */
+	struct xfs_inode	*__inodes[XFS_INODES_PER_CHUNK];
 };
 
 /* Set if the scan has been aborted due to some event in the fs. */
@@ -63,6 +69,7 @@ void xchk_iscan_start(struct xfs_scrub *sc, unsigned int iget_timeout,
 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);
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 92d1f3b6203db..896910be3173b 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -1200,6 +1200,29 @@ TRACE_EVENT(xchk_iscan_iget,
 		  __entry->error)
 );
 
+TRACE_EVENT(xchk_iscan_iget_batch,
+	TP_PROTO(struct xfs_mount *mp, struct xchk_iscan *iscan,
+		 unsigned int nr),
+	TP_ARGS(mp, iscan, nr),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, cursor)
+		__field(xfs_ino_t, visited)
+		__field(unsigned int, nr)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->cursor = iscan->cursor_ino;
+		__entry->visited = iscan->__visited_ino;
+		__entry->nr = nr;
+	),
+	TP_printk("dev %d:%d iscan cursor 0x%llx visited 0x%llx nr %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->cursor,
+		  __entry->visited,
+		  __entry->nr)
+);
+
 TRACE_EVENT(xchk_iscan_iget_retry_wait,
 	TP_PROTO(struct xchk_iscan *iscan),
 	TP_ARGS(iscan),

[PATCH 7/7] xfs: iscan batching should handle unallocated inodes too

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

The inode scanner tries to reduce contention on the AGI header buffer
lock by grabbing references to consecutive allocated inodes.  Batching
stops as soon as we encounter an unallocated inode.  This is unfortunate
because in the worst case performance collapses to the old "one at a
time" behavior if every other inode is free.

This is correct behavior, but we could do better.  Unallocated inodes by
definition have nothing to scan, which means the iscan can ignore them
as long as someone ensures that the scan data will reflect another
thread allocating the inode and adding interesting metadata to that
inode.  That mechanism is, of course, the live update hooks.

Therefore, extend the batching mechanism to track unallocated inodes
adjacent to the scan cursor.  The _want_live_update predicate can tell
the caller's live update hook to incorporate all live updates to what
the scanner thinks is an unallocated inode if (after dropping the AGI)
some other thread allocates one of those inodes and begins using it.

Note that we cannot just copy the ir_free bitmap into the scan cursor
because the batching stops if iget says the inode is in an intermediate
state (e.g. on the inactivation list) and cannot be igrabbed.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/iscan.c |  107 +++++++++++++++++++++++++++++++++++++++++++++-----
 fs/xfs/scrub/iscan.h |    6 ++-
 fs/xfs/scrub/trace.h |   21 ++++++++--
 3 files changed, 119 insertions(+), 15 deletions(-)


diff --git a/fs/xfs/scrub/iscan.c b/fs/xfs/scrub/iscan.c
index ba93258c47030..4e570b5d98b1b 100644
--- a/fs/xfs/scrub/iscan.c
+++ b/fs/xfs/scrub/iscan.c
@@ -61,7 +61,8 @@ xchk_iscan_find_next(
 	struct xfs_buf		*agi_bp,
 	struct xfs_perag	*pag,
 	xfs_inofree_t		*allocmaskp,
-	xfs_agino_t		*cursor)
+	xfs_agino_t		*cursor,
+	uint8_t			*nr_inodesp)
 {
 	struct xfs_scrub	*sc = iscan->sc;
 	struct xfs_inobt_rec_incore	rec;
@@ -147,6 +148,7 @@ xchk_iscan_find_next(
 			ASSERT(next >= 0);
 			*cursor = rec.ir_startino + next;
 			*allocmaskp = allocmask >> next;
+			*nr_inodesp = XFS_INODES_PER_CHUNK - next;
 			break;
 		}
 	}
@@ -228,7 +230,8 @@ xchk_iscan_advance(
 	struct xchk_iscan	*iscan,
 	struct xfs_perag	**pagp,
 	struct xfs_buf		**agi_bpp,
-	xfs_inofree_t		*allocmaskp)
+	xfs_inofree_t		*allocmaskp,
+	uint8_t			*nr_inodesp)
 {
 	struct xfs_scrub	*sc = iscan->sc;
 	struct xfs_mount	*mp = sc->mp;
@@ -255,7 +258,7 @@ xchk_iscan_advance(
 
 		agino = XFS_INO_TO_AGINO(mp, iscan->cursor_ino);
 		ret = xchk_iscan_find_next(iscan, agi_bp, pag, allocmaskp,
-				&agino);
+				&agino, nr_inodesp);
 		if (ret)
 			goto out_buf;
 
@@ -344,12 +347,14 @@ xchk_iscan_iget(
 	struct xchk_iscan	*iscan,
 	struct xfs_perag	*pag,
 	struct xfs_buf		*agi_bp,
-	xfs_inofree_t		allocmask)
+	xfs_inofree_t		allocmask,
+	uint8_t			nr_inodes)
 {
 	struct xfs_scrub	*sc = iscan->sc;
 	struct xfs_mount	*mp = sc->mp;
 	xfs_ino_t		ino = iscan->cursor_ino;
 	unsigned int		idx = 0;
+	unsigned int		i;
 	int			error;
 
 	ASSERT(iscan->__inodes[0] == NULL);
@@ -399,10 +404,28 @@ xchk_iscan_iget(
 	/*
 	 * Now that we've filled the first slot in __inodes, try to fill the
 	 * rest of the batch with consecutively ordered inodes.  to reduce the
-	 * number of _iter calls.  If we can't get an inode, we stop and return
-	 * what we have.
+	 * number of _iter calls.  Make a bitmap of unallocated inodes from the
+	 * zeroes in the inuse bitmap; these inodes will not be scanned, but
+	 * the _want_live_update predicate will pass through all live updates.
+	 *
+	 * If we can't iget an allocated inode, stop and return what we have.
 	 */
-	for (; allocmask & 1; allocmask >>= 1, ino++, idx++) {
+	mutex_lock(&iscan->lock);
+	iscan->__batch_ino = ino - 1;
+	iscan->__skipped_inomask = 0;
+	mutex_unlock(&iscan->lock);
+
+	for (i = 1; i < nr_inodes; i++, ino++, allocmask >>= 1) {
+		if (!(allocmask & 1)) {
+			ASSERT(!(iscan->__skipped_inomask & (1ULL << i)));
+
+			mutex_lock(&iscan->lock);
+			iscan->cursor_ino = ino;
+			iscan->__skipped_inomask |= (1ULL << i);
+			mutex_unlock(&iscan->lock);
+			continue;
+		}
+
 		ASSERT(iscan->__inodes[idx] == NULL);
 
 		error = xfs_iget(sc->mp, sc->tp, ino, XFS_IGET_NORETRY, 0,
@@ -413,14 +436,42 @@ xchk_iscan_iget(
 		mutex_lock(&iscan->lock);
 		iscan->cursor_ino = ino;
 		mutex_unlock(&iscan->lock);
+		idx++;
 	}
 
-	trace_xchk_iscan_iget_batch(sc->mp, iscan, idx);
+	trace_xchk_iscan_iget_batch(sc->mp, iscan, nr_inodes, idx);
 	xfs_trans_brelse(sc->tp, agi_bp);
 	xfs_perag_put(pag);
 	return idx;
 }
 
+/*
+ * Advance the visit cursor to reflect skipped inodes beyond whatever we
+ * scanned.
+ */
+STATIC void
+xchk_iscan_finish_batch(
+	struct xchk_iscan	*iscan)
+{
+	xfs_ino_t		highest_skipped;
+
+	mutex_lock(&iscan->lock);
+
+	if (iscan->__batch_ino != NULLFSINO) {
+		highest_skipped = iscan->__batch_ino +
+					xfs_highbit64(iscan->__skipped_inomask);
+		iscan->__visited_ino = max(iscan->__visited_ino,
+					   highest_skipped);
+
+		trace_xchk_iscan_skip(iscan);
+	}
+
+	iscan->__batch_ino = NULLFSINO;
+	iscan->__skipped_inomask = 0;
+
+	mutex_unlock(&iscan->lock);
+}
+
 /*
  * Advance the inode scan cursor to the next allocated inode and return up to
  * 64 consecutive allocated inodes starting with the cursor position.
@@ -432,6 +483,8 @@ xchk_iscan_iter_batch(
 	struct xfs_scrub	*sc = iscan->sc;
 	int			ret;
 
+	xchk_iscan_finish_batch(iscan);
+
 	if (iscan->iget_timeout)
 		iscan->__iget_deadline = jiffies +
 					 msecs_to_jiffies(iscan->iget_timeout);
@@ -440,8 +493,10 @@ xchk_iscan_iter_batch(
 		struct xfs_buf	*agi_bp = NULL;
 		struct xfs_perag *pag = NULL;
 		xfs_inofree_t	allocmask = 0;
+		uint8_t		nr_inodes = 0;
 
-		ret = xchk_iscan_advance(iscan, &pag, &agi_bp, &allocmask);
+		ret = xchk_iscan_advance(iscan, &pag, &agi_bp, &allocmask,
+				&nr_inodes);
 		if (ret != 1)
 			return ret;
 
@@ -452,7 +507,7 @@ xchk_iscan_iter_batch(
 			break;
 		}
 
-		ret = xchk_iscan_iget(iscan, pag, agi_bp, allocmask);
+		ret = xchk_iscan_iget(iscan, pag, agi_bp, allocmask, nr_inodes);
 	} while (ret == -EAGAIN);
 
 	return ret;
@@ -559,6 +614,9 @@ xchk_iscan_start(
 
 	start_ino = xchk_iscan_rotor(sc->mp);
 
+	iscan->__batch_ino = NULLFSINO;
+	iscan->__skipped_inomask = 0;
+
 	iscan->sc = sc;
 	clear_bit(XCHK_ISCAN_OPSTATE_ABORTED, &iscan->__opstate);
 	iscan->iget_timeout = iget_timeout;
@@ -587,6 +645,26 @@ xchk_iscan_mark_visited(
 	mutex_unlock(&iscan->lock);
 }
 
+/*
+ * Did we skip this inode because it wasn't allocated when we loaded the batch?
+ * If so, it is newly allocated and will not be scanned.  All live updates to
+ * this inode must be passed to the caller to maintain scan correctness.
+ */
+static inline bool
+xchk_iscan_skipped(
+	const struct xchk_iscan	*iscan,
+	xfs_ino_t		ino)
+{
+	if (iscan->__batch_ino == NULLFSINO)
+		return false;
+	if (ino < iscan->__batch_ino)
+		return false;
+	if (ino >= iscan->__batch_ino + XFS_INODES_PER_CHUNK)
+		return false;
+
+	return iscan->__skipped_inomask & (1ULL << (ino - iscan->__batch_ino));
+}
+
 /*
  * Do we need a live update for this inode?  This is true if the scanner thread
  * has visited this inode and the scan hasn't been aborted due to errors.
@@ -622,6 +700,15 @@ xchk_iscan_want_live_update(
 		goto unlock;
 	}
 
+	/*
+	 * This inode was not allocated at the time of the iscan batch.
+	 * The caller should receive all updates.
+	 */
+	if (xchk_iscan_skipped(iscan, ino)) {
+		ret = true;
+		goto unlock;
+	}
+
 	/*
 	 * The visited cursor hasn't yet wrapped around the end of the FS.  If
 	 * @ino is inside the starred range, the caller should receive updates:
diff --git a/fs/xfs/scrub/iscan.h b/fs/xfs/scrub/iscan.h
index f7317af807ddc..365d54e35cd94 100644
--- a/fs/xfs/scrub/iscan.h
+++ b/fs/xfs/scrub/iscan.h
@@ -44,8 +44,12 @@ struct xchk_iscan {
 
 	/*
 	 * The scan grabs batches of inodes and stashes them here before
-	 * handing them out with _iter.
+	 * 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];
 };
 
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 896910be3173b..e1dcd5f6ce5dd 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -1145,6 +1145,7 @@ DEFINE_EVENT(xchk_iscan_class, name, \
 	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,
@@ -1202,25 +1203,37 @@ TRACE_EVENT(xchk_iscan_iget,
 
 TRACE_EVENT(xchk_iscan_iget_batch,
 	TP_PROTO(struct xfs_mount *mp, struct xchk_iscan *iscan,
-		 unsigned int nr),
-	TP_ARGS(mp, iscan, nr),
+		 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 nr %d",
+	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->nr)
+		  __entry->batch_ino,
+		  __entry->skipmask,
+		  __entry->nr,
+		  __entry->avail,
+		  __entry->unavail)
 );
 
 TRACE_EVENT(xchk_iscan_iget_retry_wait,

[PATCH 1/4] xfs: create a static name for the dot entry too

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create an xfs_name_dot object so that upcoming scrub code can compare
against that.  Offline repair already has such an object, so we're
really just hoisting it to the kernel.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_dir2.c |    6 ++++++
 fs/xfs/libxfs/xfs_dir2.h |    1 +
 2 files changed, 7 insertions(+)


diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index f5462fd582d50..422e8fc488325 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/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
  */
diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h
index 19af22a16c415..7d7cd8d808e4d 100644
--- a/fs/xfs/libxfs/xfs_dir2.h
+++ b/fs/xfs/libxfs/xfs_dir2.h
@@ -22,6 +22,7 @@ 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;
 
 /*
  * Convert inode mode to directory entry filetype

[PATCH 2/4] xfs: create a predicate to determine if two xfs_names are the same

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a simple predicate to determine if two xfs_names are the same
objects or have the exact same name.  The comparison is always case
sensitive.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_dir2.h |    9 +++++++++
 fs/xfs/scrub/dir.c       |    4 ++--
 2 files changed, 11 insertions(+), 2 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h
index 7d7cd8d808e4d..ac3c264402dda 100644
--- a/fs/xfs/libxfs/xfs_dir2.h
+++ b/fs/xfs/libxfs/xfs_dir2.h
@@ -24,6 +24,15 @@ 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)
+{
+	return n1 == n2 || (n1->len == n2->len &&
+			    !memcmp(n1->name, n2->name, n1->len));
+}
+
 /*
  * Convert inode mode to directory entry filetype
  */
diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index d86ab51af9282..076a310b8eb00 100644
--- a/fs/xfs/scrub/dir.c
+++ b/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.

[PATCH 3/4] xfs: create a macro for decoding ftypes in tracepoints

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create the XFS_DIR3_FTYPE_STR macro so that we can report ftype as
strings instead of numbers in tracepoints.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_da_format.h |   11 +++++++++++
 1 file changed, 11 insertions(+)


diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h
index f9015f88eca70..44748f1640e53 100644
--- a/fs/xfs/libxfs/xfs_da_format.h
+++ b/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.
  */

[PATCH 4/4] xfs: repair file modes by scanning for a dirent pointing to us

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

An earlier version of this patch ("xfs: repair obviously broken inode
modes") tried to reset the di_mode of a file by guessing it from the
data fork format and/or data block 0 contents.  Christoph didn't like
this approach because it opens the possibility that users could craft a
file to look like a directory and trick online repair into turning the
mode into S_IFDIR.

However, he allowed that gathering evidence from the rest of the fs
metadata would be fine as long as none of that metadata can be
controlled by unprivileged users.  The ftype flag of V5 filesystem
directory entries fits that description!

Now that we have the ability to scan all the files in the filesystem,
let's try scanning all the directory entries in the filesystem to see if
there's a dirent referencing the inode that we're trying to repair.  For
the first dirent found we save the ftype; and compare for subsequent
ones.

If all the dirents have the same ftype, then we can translate that back
into an S_IFMT flag and fix the file.  If not, reset the mode to S_IFREG.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/inode_repair.c |  236 ++++++++++++++++++++++++++++++++++++++++++-
 fs/xfs/scrub/iscan.c        |   29 +++++
 fs/xfs/scrub/iscan.h        |    3 +
 fs/xfs/scrub/trace.c        |    1 
 fs/xfs/scrub/trace.h        |   49 +++++++++
 5 files changed, 312 insertions(+), 6 deletions(-)


diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c
index 66949cc3d7cc9..20cecf3c69342 100644
--- a/fs/xfs/scrub/inode_repair.c
+++ b/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;
 
diff --git a/fs/xfs/scrub/iscan.c b/fs/xfs/scrub/iscan.c
index 4e570b5d98b1b..bce8b34a460a1 100644
--- a/fs/xfs/scrub/iscan.c
+++ b/fs/xfs/scrub/iscan.c
@@ -51,6 +51,32 @@
  * scanner's observations must be updated.
  */
 
+/*
+ * If the inobt record @rec covers @iscan->skip_ino, mark the inode free so
+ * that the scan ignores that inode.
+ */
+STATIC void
+xchk_iscan_mask_skipino(
+	struct xchk_iscan	*iscan,
+	struct xfs_perag	*pag,
+	struct xfs_inobt_rec_incore	*rec,
+	xfs_agino_t		lastrecino)
+{
+	struct xfs_scrub	*sc = iscan->sc;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agnumber_t		skip_agno = XFS_INO_TO_AGNO(mp, iscan->skip_ino);
+	xfs_agnumber_t		skip_agino = XFS_INO_TO_AGINO(mp, iscan->skip_ino);
+
+	if (pag->pag_agno != skip_agno)
+		return;
+	if (skip_agino < rec->ir_startino)
+		return;
+	if (skip_agino > lastrecino)
+		return;
+
+	rec->ir_free |= xfs_inobt_maskn(skip_agino - rec->ir_startino, 1);
+}
+
 /*
  * Set *cursor to the next allocated inode after whatever it's set to now.
  * If there are no more inodes in this AG, cursor is set to NULLAGINO.
@@ -127,6 +153,9 @@ xchk_iscan_find_next(
 		if (rec.ir_startino + XFS_INODES_PER_CHUNK <= agino)
 			continue;
 
+		if (iscan->skip_ino)
+			xchk_iscan_mask_skipino(iscan, pag, &rec, lastino);
+
 		/*
 		 * If the incoming lookup put us in the middle of an inobt
 		 * record, mark it and the previous inodes "free" so that the
diff --git a/fs/xfs/scrub/iscan.h b/fs/xfs/scrub/iscan.h
index 365d54e35cd94..71f657552dfac 100644
--- a/fs/xfs/scrub/iscan.h
+++ b/fs/xfs/scrub/iscan.h
@@ -22,6 +22,9 @@ struct xchk_iscan {
 	/* 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
diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c
index 4542eeebab6f1..5ed75cc33b928 100644
--- a/fs/xfs/scrub/trace.c
+++ b/fs/xfs/scrub/trace.c
@@ -16,6 +16,7 @@
 #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"
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index e1dcd5f6ce5dd..790982b769f72 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -1790,6 +1790,55 @@ 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),

[PATCH 1/5] xfs: report the health of quota counts

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Report the health of quota counts.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_fs.h     |    1 +
 fs/xfs/libxfs/xfs_health.h |    4 +++-
 fs/xfs/xfs_health.c        |    1 +
 fs/xfs/xfs_qm.c            |    7 ++++++-
 fs/xfs/xfs_trans_dquot.c   |    2 ++
 5 files changed, 13 insertions(+), 2 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 6360073865dbc..711e0fc7efab6 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -195,6 +195,7 @@ struct xfs_fsop_geom {
 #define XFS_FSOP_GEOM_SICK_PQUOTA	(1 << 3)  /* project quota */
 #define XFS_FSOP_GEOM_SICK_RT_BITMAP	(1 << 4)  /* realtime bitmap */
 #define XFS_FSOP_GEOM_SICK_RT_SUMMARY	(1 << 5)  /* realtime summary */
+#define XFS_FSOP_GEOM_SICK_QUOTACHECK	(1 << 6)  /* quota counts */
 
 /* Output for XFS_FS_COUNTS */
 typedef struct xfs_fsop_counts {
diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index 6296993ff8f3d..5626e53b3f0fe 100644
--- a/fs/xfs/libxfs/xfs_health.h
+++ b/fs/xfs/libxfs/xfs_health.h
@@ -41,6 +41,7 @@ struct xfs_fsop_geom;
 #define XFS_SICK_FS_UQUOTA	(1 << 1)  /* user quota */
 #define XFS_SICK_FS_GQUOTA	(1 << 2)  /* group quota */
 #define XFS_SICK_FS_PQUOTA	(1 << 3)  /* project quota */
+#define XFS_SICK_FS_QUOTACHECK	(1 << 4)  /* quota counts */
 
 /* Observable health issues for realtime volume metadata. */
 #define XFS_SICK_RT_BITMAP	(1 << 0)  /* realtime bitmap */
@@ -77,7 +78,8 @@ struct xfs_fsop_geom;
 #define XFS_SICK_FS_PRIMARY	(XFS_SICK_FS_COUNTERS | \
 				 XFS_SICK_FS_UQUOTA | \
 				 XFS_SICK_FS_GQUOTA | \
-				 XFS_SICK_FS_PQUOTA)
+				 XFS_SICK_FS_PQUOTA | \
+				 XFS_SICK_FS_QUOTACHECK)
 
 #define XFS_SICK_RT_PRIMARY	(XFS_SICK_RT_BITMAP | \
 				 XFS_SICK_RT_SUMMARY)
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index 9a57afee93383..ef07af9f753d3 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -280,6 +280,7 @@ static const struct ioctl_sick_map fs_map[] = {
 	{ XFS_SICK_FS_UQUOTA,	XFS_FSOP_GEOM_SICK_UQUOTA },
 	{ XFS_SICK_FS_GQUOTA,	XFS_FSOP_GEOM_SICK_GQUOTA },
 	{ XFS_SICK_FS_PQUOTA,	XFS_FSOP_GEOM_SICK_PQUOTA },
+	{ XFS_SICK_FS_QUOTACHECK, XFS_FSOP_GEOM_SICK_QUOTACHECK },
 	{ 0, 0 },
 };
 
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 94a7932ac5700..826aa5790cdeb 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -26,6 +26,7 @@
 #include "xfs_ag.h"
 #include "xfs_ialloc.h"
 #include "xfs_log_priv.h"
+#include "xfs_health.h"
 
 /*
  * The global quota manager. There is only one of these for the entire
@@ -1406,8 +1407,12 @@ xfs_qm_quotacheck(
 			xfs_warn(mp,
 				"Quotacheck: Failed to reset quota flags.");
 		}
-	} else
+		xfs_fs_mark_sick(mp, XFS_SICK_FS_QUOTACHECK);
+	} else {
 		xfs_notice(mp, "Quotacheck: Done.");
+		xfs_fs_mark_healthy(mp, XFS_SICK_FS_QUOTACHECK);
+	}
+
 	return error;
 
 error_purge:
diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c
index aa00cf67ad72a..968dc7af4fc7d 100644
--- a/fs/xfs/xfs_trans_dquot.c
+++ b/fs/xfs/xfs_trans_dquot.c
@@ -17,6 +17,7 @@
 #include "xfs_qm.h"
 #include "xfs_trace.h"
 #include "xfs_error.h"
+#include "xfs_health.h"
 
 STATIC void	xfs_trans_alloc_dqinfo(xfs_trans_t *);
 
@@ -706,6 +707,7 @@ xfs_trans_dqresv(
 error_corrupt:
 	xfs_dqunlock(dqp);
 	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+	xfs_fs_mark_sick(mp, XFS_SICK_FS_QUOTACHECK);
 	return -EFSCORRUPTED;
 }
 

[PATCH 2/5] xfs: implement live quotacheck inode scan

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a new trio of scrub functions to check quota counters.  While the
dquots themselves are filesystem metadata and should be checked early,
the dquot counter values are computed from other metadata and are
therefore summary counters.  We don't plug these into the scrub dispatch
just yet, because we still need to be able to watch quota updates while
doing our scan.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Makefile           |    1 
 fs/xfs/libxfs/xfs_fs.h    |    3 
 fs/xfs/scrub/common.c     |   43 ++++
 fs/xfs/scrub/common.h     |   11 +
 fs/xfs/scrub/fscounters.c |    2 
 fs/xfs/scrub/health.c     |    1 
 fs/xfs/scrub/quotacheck.c |  512 +++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/quotacheck.h |   67 ++++++
 fs/xfs/scrub/scrub.c      |    6 +
 fs/xfs/scrub/scrub.h      |    6 +
 fs/xfs/scrub/stats.c      |    1 
 fs/xfs/scrub/trace.h      |   28 ++
 fs/xfs/scrub/xfarray.h    |   19 ++
 fs/xfs/xfs_inode.c        |   21 ++
 fs/xfs/xfs_inode.h        |    2 
 15 files changed, 718 insertions(+), 5 deletions(-)
 create mode 100644 fs/xfs/scrub/quotacheck.c
 create mode 100644 fs/xfs/scrub/quotacheck.h


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 7a5c637e449e5..12266812fa107 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -181,6 +181,7 @@ xfs-$(CONFIG_XFS_RT)		+= $(addprefix scrub/, \
 xfs-$(CONFIG_XFS_QUOTA)		+= $(addprefix scrub/, \
 				   dqiterate.o \
 				   quota.o \
+				   quotacheck.o \
 				   )
 
 # online repair
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 711e0fc7efab6..07acbed9235c5 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -710,9 +710,10 @@ struct xfs_scrub_metadata {
 #define XFS_SCRUB_TYPE_GQUOTA	22	/* group quotas */
 #define XFS_SCRUB_TYPE_PQUOTA	23	/* project quotas */
 #define XFS_SCRUB_TYPE_FSCOUNTERS 24	/* fs summary counters */
+#define XFS_SCRUB_TYPE_QUOTACHECK 25	/* quota counters */
 
 /* Number of scrub subcommands. */
-#define XFS_SCRUB_TYPE_NR	25
+#define XFS_SCRUB_TYPE_NR	26
 
 /* i: Repair this metadata. */
 #define XFS_SCRUB_IFLAG_REPAIR		(1u << 0)
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 81f2b96bb5a74..fc23bd9d38195 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -29,6 +29,7 @@
 #include "xfs_attr.h"
 #include "xfs_reflink.h"
 #include "xfs_ag.h"
+#include "xfs_error.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
@@ -82,6 +83,15 @@ __xchk_process_error(
 				sc->ip ? sc->ip : XFS_I(file_inode(sc->file)),
 				sc->sm, *error);
 		break;
+	case -ECANCELED:
+		/*
+		 * ECANCELED here means that the caller set one of the scrub
+		 * outcome flags (corrupt, xfail, xcorrupt) and wants to exit
+		 * quickly.  Set error to zero and do not continue.
+		 */
+		trace_xchk_op_error(sc, agno, bno, *error, ret_ip);
+		*error = 0;
+		break;
 	case -EFSBADCRC:
 	case -EFSCORRUPTED:
 		/* Note the badness but don't abort. */
@@ -89,8 +99,7 @@ __xchk_process_error(
 		*error = 0;
 		fallthrough;
 	default:
-		trace_xchk_op_error(sc, agno, bno, *error,
-				ret_ip);
+		trace_xchk_op_error(sc, agno, bno, *error, ret_ip);
 		break;
 	}
 	return false;
@@ -136,6 +145,16 @@ __xchk_fblock_process_error(
 		/* Used to restart an op with deadlock avoidance. */
 		trace_xchk_deadlock_retry(sc->ip, sc->sm, *error);
 		break;
+	case -ECANCELED:
+		/*
+		 * ECANCELED here means that the caller set one of the scrub
+		 * outcome flags (corrupt, xfail, xcorrupt) and wants to exit
+		 * quickly.  Set error to zero and do not continue.
+		 */
+		trace_xchk_file_op_error(sc, whichfork, offset, *error,
+				ret_ip);
+		*error = 0;
+		break;
 	case -EFSBADCRC:
 	case -EFSCORRUPTED:
 		/* Note the badness but don't abort. */
@@ -227,6 +246,19 @@ xchk_block_set_corrupt(
 	trace_xchk_block_error(sc, xfs_buf_daddr(bp), __return_address);
 }
 
+#ifdef CONFIG_XFS_QUOTA
+/* Record a corrupt quota counter. */
+void
+xchk_qcheck_set_corrupt(
+	struct xfs_scrub	*sc,
+	unsigned int		dqtype,
+	xfs_dqid_t		id)
+{
+	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
+	trace_xchk_qcheck_error(sc, dqtype, id, __return_address);
+}
+#endif /* CONFIG_XFS_QUOTA */
+
 /* Record a corruption while cross-referencing. */
 void
 xchk_block_xref_set_corrupt(
@@ -653,6 +685,13 @@ xchk_trans_cancel(
 	sc->tp = NULL;
 }
 
+int
+xchk_trans_alloc_empty(
+	struct xfs_scrub	*sc)
+{
+	return xfs_trans_alloc_empty(sc->mp, &sc->tp);
+}
+
 /*
  * Grab an empty transaction so that we can re-grab locked buffers if
  * one of our btrees turns out to be cyclic.
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index da09580b454a0..79516d1f4983a 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -32,6 +32,7 @@ xchk_should_terminate(
 }
 
 int xchk_trans_alloc(struct xfs_scrub *sc, uint resblks);
+int xchk_trans_alloc_empty(struct xfs_scrub *sc);
 void xchk_trans_cancel(struct xfs_scrub *sc);
 
 bool xchk_process_error(struct xfs_scrub *sc, xfs_agnumber_t agno,
@@ -54,6 +55,10 @@ void xchk_block_set_corrupt(struct xfs_scrub *sc,
 void xchk_ino_set_corrupt(struct xfs_scrub *sc, xfs_ino_t ino);
 void xchk_fblock_set_corrupt(struct xfs_scrub *sc, int whichfork,
 		xfs_fileoff_t offset);
+#ifdef CONFIG_XFS_QUOTA
+void xchk_qcheck_set_corrupt(struct xfs_scrub *sc, unsigned int dqtype,
+		xfs_dqid_t id);
+#endif /* CONFIG_XFS_QUOTA */
 
 void xchk_block_xref_set_corrupt(struct xfs_scrub *sc,
 		struct xfs_buf *bp);
@@ -105,6 +110,7 @@ xchk_setup_rtsummary(struct xfs_scrub *sc)
 #ifdef CONFIG_XFS_QUOTA
 int xchk_ino_dqattach(struct xfs_scrub *sc);
 int xchk_setup_quota(struct xfs_scrub *sc);
+int xchk_setup_quotacheck(struct xfs_scrub *sc);
 #else
 static inline int
 xchk_ino_dqattach(struct xfs_scrub *sc)
@@ -116,6 +122,11 @@ xchk_setup_quota(struct xfs_scrub *sc)
 {
 	return -ENOENT;
 }
+static inline int
+xchk_setup_quotacheck(struct xfs_scrub *sc)
+{
+	return -ENOENT;
+}
 #endif
 int xchk_setup_fscounters(struct xfs_scrub *sc);
 
diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c
index 5799e9a94f1f6..893c5a6e3ddb0 100644
--- a/fs/xfs/scrub/fscounters.c
+++ b/fs/xfs/scrub/fscounters.c
@@ -242,7 +242,7 @@ xchk_setup_fscounters(
 			return error;
 	}
 
-	return xfs_trans_alloc_empty(sc->mp, &sc->tp);
+	return xchk_trans_alloc_empty(sc);
 }
 
 /*
diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c
index df716da11226b..55313a26ae9a7 100644
--- a/fs/xfs/scrub/health.c
+++ b/fs/xfs/scrub/health.c
@@ -107,6 +107,7 @@ static const struct xchk_health_map type_to_health_flag[XFS_SCRUB_TYPE_NR] = {
 	[XFS_SCRUB_TYPE_GQUOTA]		= { XHG_FS,  XFS_SICK_FS_GQUOTA },
 	[XFS_SCRUB_TYPE_PQUOTA]		= { XHG_FS,  XFS_SICK_FS_PQUOTA },
 	[XFS_SCRUB_TYPE_FSCOUNTERS]	= { XHG_FS,  XFS_SICK_FS_COUNTERS },
+	[XFS_SCRUB_TYPE_QUOTACHECK]	= { XHG_FS,  XFS_SICK_FS_QUOTACHECK },
 };
 
 /* Return the health status mask for this scrub type. */
diff --git a/fs/xfs/scrub/quotacheck.c b/fs/xfs/scrub/quotacheck.c
new file mode 100644
index 0000000000000..79a6ac25419d7
--- /dev/null
+++ b/fs/xfs/scrub/quotacheck.c
@@ -0,0 +1,512 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2020-2024 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_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_inode.h"
+#include "xfs_quota.h"
+#include "xfs_qm.h"
+#include "xfs_icache.h"
+#include "xfs_bmap_util.h"
+#include "xfs_ialloc.h"
+#include "xfs_ag.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/repair.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/iscan.h"
+#include "scrub/quota.h"
+#include "scrub/quotacheck.h"
+#include "scrub/trace.h"
+
+/*
+ * Live Quotacheck
+ * ===============
+ *
+ * Quota counters are "summary" metadata, in the sense that they are computed
+ * as the summation of the block usage counts for every file on the filesystem.
+ * Therefore, we compute the correct icount, bcount, and rtbcount values by
+ * creating a shadow quota counter structure and walking every inode.
+ */
+
+/* Set us up to scrub quota counters. */
+int
+xchk_setup_quotacheck(
+	struct xfs_scrub	*sc)
+{
+	/* Not ready for general consumption yet. */
+	return -EOPNOTSUPP;
+
+	if (!XFS_IS_QUOTA_ON(sc->mp))
+		return -ENOENT;
+
+	sc->buf = kzalloc(sizeof(struct xqcheck), XCHK_GFP_FLAGS);
+	if (!sc->buf)
+		return -ENOMEM;
+
+	return xchk_setup_fs(sc);
+}
+
+/*
+ * Part 1: Collecting dquot resource usage counts.  For each xfs_dquot attached
+ * to each inode, we create a shadow dquot, and compute the inode count and add
+ * the data/rt block usage from what we see.
+ *
+ * To avoid false corruption reports in part 2, any failure in this part must
+ * set the INCOMPLETE flag even when a negative errno is returned.  This care
+ * must be taken with certain errno values (i.e. EFSBADCRC, EFSCORRUPTED,
+ * ECANCELED) that are absorbed into a scrub state flag update by
+ * xchk_*_process_error.
+ */
+
+/* Update an incore dquot counter information from a live update. */
+static int
+xqcheck_update_incore_counts(
+	struct xqcheck		*xqc,
+	struct xfarray		*counts,
+	xfs_dqid_t		id,
+	int64_t			inodes,
+	int64_t			nblks,
+	int64_t			rtblks)
+{
+	struct xqcheck_dquot	xcdq;
+	int			error;
+
+	error = xfarray_load_sparse(counts, id, &xcdq);
+	if (error)
+		return error;
+
+	xcdq.flags |= XQCHECK_DQUOT_WRITTEN;
+	xcdq.icount += inodes;
+	xcdq.bcount += nblks;
+	xcdq.rtbcount += rtblks;
+
+	error = xfarray_store(counts, id, &xcdq);
+	if (error == -EFBIG) {
+		/*
+		 * EFBIG means we tried to store data at too high a byte offset
+		 * in the sparse array.  IOWs, we cannot complete the check and
+		 * must notify userspace that the check was incomplete.
+		 */
+		error = -ECANCELED;
+	}
+	return error;
+}
+
+/* Record this inode's quota usage in our shadow quota counter data. */
+STATIC int
+xqcheck_collect_inode(
+	struct xqcheck		*xqc,
+	struct xfs_inode	*ip)
+{
+	struct xfs_trans	*tp = xqc->sc->tp;
+	xfs_filblks_t		nblks, rtblks;
+	uint			ilock_flags = 0;
+	xfs_dqid_t		id;
+	bool			isreg = S_ISREG(VFS_I(ip)->i_mode);
+	int			error = 0;
+
+	if (xfs_is_quota_inode(&tp->t_mountp->m_sb, ip->i_ino)) {
+		/*
+		 * Quota files are never counted towards quota, so we do not
+		 * need to take the lock.
+		 */
+		xchk_iscan_mark_visited(&xqc->iscan, ip);
+		return 0;
+	}
+
+	/* Figure out the data / rt device block counts. */
+	xfs_ilock(ip, XFS_IOLOCK_SHARED);
+	if (isreg)
+		xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
+	if (XFS_IS_REALTIME_INODE(ip)) {
+		ilock_flags = xfs_ilock_data_map_shared(ip);
+		error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
+		if (error)
+			goto out_incomplete;
+	} else {
+		ilock_flags = XFS_ILOCK_SHARED;
+		xfs_ilock(ip, XFS_ILOCK_SHARED);
+	}
+	xfs_inode_count_blocks(tp, ip, &nblks, &rtblks);
+
+	/* Update the shadow dquot counters. */
+	mutex_lock(&xqc->lock);
+	if (xqc->ucounts) {
+		id = xfs_qm_id_for_quotatype(ip, XFS_DQTYPE_USER);
+		error = xqcheck_update_incore_counts(xqc, xqc->ucounts, id, 1,
+				nblks, rtblks);
+		if (error)
+			goto out_mutex;
+	}
+
+	if (xqc->gcounts) {
+		id = xfs_qm_id_for_quotatype(ip, XFS_DQTYPE_GROUP);
+		error = xqcheck_update_incore_counts(xqc, xqc->gcounts, id, 1,
+				nblks, rtblks);
+		if (error)
+			goto out_mutex;
+	}
+
+	if (xqc->pcounts) {
+		id = xfs_qm_id_for_quotatype(ip, XFS_DQTYPE_PROJ);
+		error = xqcheck_update_incore_counts(xqc, xqc->pcounts, id, 1,
+				nblks, rtblks);
+		if (error)
+			goto out_mutex;
+	}
+	mutex_unlock(&xqc->lock);
+
+	xchk_iscan_mark_visited(&xqc->iscan, ip);
+	goto out_ilock;
+
+out_mutex:
+	mutex_unlock(&xqc->lock);
+out_incomplete:
+	xchk_set_incomplete(xqc->sc);
+out_ilock:
+	xfs_iunlock(ip, ilock_flags);
+	if (isreg)
+		xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
+	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
+	return error;
+}
+
+/* Walk all the allocated inodes and run a quota scan on them. */
+STATIC int
+xqcheck_collect_counts(
+	struct xqcheck		*xqc)
+{
+	struct xfs_scrub	*sc = xqc->sc;
+	struct xfs_inode	*ip;
+	int			error;
+
+	/*
+	 * Set up for a potentially lengthy filesystem scan by reducing our
+	 * transaction resource usage for the duration.  Specifically:
+	 *
+	 * Cancel the transaction to release the log grant space while we scan
+	 * the filesystem.
+	 *
+	 * Create a new empty transaction to eliminate the possibility of the
+	 * inode scan deadlocking on cyclical metadata.
+	 *
+	 * We pass the empty transaction to the file scanning function to avoid
+	 * repeatedly cycling empty transactions.  This can be done without
+	 * risk of deadlock between sb_internal and the IOLOCK (we take the
+	 * IOLOCK to quiesce the file before scanning) because empty
+	 * transactions do not take sb_internal.
+	 */
+	xchk_trans_cancel(sc);
+	error = xchk_trans_alloc_empty(sc);
+	if (error)
+		return error;
+
+	while ((error = xchk_iscan_iter(&xqc->iscan, &ip)) == 1) {
+		error = xqcheck_collect_inode(xqc, ip);
+		xchk_irele(sc, ip);
+		if (error)
+			break;
+
+		if (xchk_should_terminate(sc, &error))
+			break;
+	}
+	xchk_iscan_iter_finish(&xqc->iscan);
+	if (error) {
+		xchk_set_incomplete(sc);
+		/*
+		 * If we couldn't grab an inode that was busy with a state
+		 * change, change the error code so that we exit to userspace
+		 * as quickly as possible.
+		 */
+		if (error == -EBUSY)
+			return -ECANCELED;
+		return error;
+	}
+
+	/*
+	 * Switch out for a real transaction in preparation for building a new
+	 * tree.
+	 */
+	xchk_trans_cancel(sc);
+	return xchk_setup_fs(sc);
+}
+
+/*
+ * Part 2: Comparing dquot resource counters.  Walk each xfs_dquot, comparing
+ * the resource usage counters against our shadow dquots; and then walk each
+ * shadow dquot (that wasn't covered in the first part), comparing it against
+ * the xfs_dquot.
+ */
+
+/*
+ * Check the dquot data against what we observed.  Caller must hold the dquot
+ * lock.
+ */
+STATIC int
+xqcheck_compare_dquot(
+	struct xqcheck		*xqc,
+	xfs_dqtype_t		dqtype,
+	struct xfs_dquot	*dq)
+{
+	struct xqcheck_dquot	xcdq;
+	struct xfarray		*counts = xqcheck_counters_for(xqc, dqtype);
+	int			error;
+
+	mutex_lock(&xqc->lock);
+	error = xfarray_load_sparse(counts, dq->q_id, &xcdq);
+	if (error)
+		goto out_unlock;
+
+	if (xcdq.icount != dq->q_ino.count)
+		xchk_qcheck_set_corrupt(xqc->sc, dqtype, dq->q_id);
+
+	if (xcdq.bcount != dq->q_blk.count)
+		xchk_qcheck_set_corrupt(xqc->sc, dqtype, dq->q_id);
+
+	if (xcdq.rtbcount != dq->q_rtb.count)
+		xchk_qcheck_set_corrupt(xqc->sc, dqtype, dq->q_id);
+
+	xcdq.flags |= (XQCHECK_DQUOT_COMPARE_SCANNED | XQCHECK_DQUOT_WRITTEN);
+	error = xfarray_store(counts, dq->q_id, &xcdq);
+	if (error == -EFBIG) {
+		/*
+		 * EFBIG means we tried to store data at too high a byte offset
+		 * in the sparse array.  IOWs, we cannot complete the check and
+		 * must notify userspace that the check was incomplete.  This
+		 * should never happen, since we just read the record.
+		 */
+		xchk_set_incomplete(xqc->sc);
+		error = -ECANCELED;
+	}
+	mutex_unlock(&xqc->lock);
+	if (error)
+		return error;
+
+	if (xqc->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		return -ECANCELED;
+
+	return 0;
+
+out_unlock:
+	mutex_unlock(&xqc->lock);
+	return error;
+}
+
+/*
+ * Walk all the observed dquots, and make sure there's a matching incore
+ * dquot and that its counts match ours.
+ */
+STATIC int
+xqcheck_walk_observations(
+	struct xqcheck		*xqc,
+	xfs_dqtype_t		dqtype)
+{
+	struct xqcheck_dquot	xcdq;
+	struct xfs_dquot	*dq;
+	struct xfarray		*counts = xqcheck_counters_for(xqc, dqtype);
+	xfarray_idx_t		cur = XFARRAY_CURSOR_INIT;
+	int			error;
+
+	mutex_lock(&xqc->lock);
+	while ((error = xfarray_iter(counts, &cur, &xcdq)) == 1) {
+		xfs_dqid_t	id = cur - 1;
+
+		if (xcdq.flags & XQCHECK_DQUOT_COMPARE_SCANNED)
+			continue;
+
+		mutex_unlock(&xqc->lock);
+
+		error = xfs_qm_dqget(xqc->sc->mp, id, dqtype, false, &dq);
+		if (error == -ENOENT) {
+			xchk_qcheck_set_corrupt(xqc->sc, dqtype, id);
+			return 0;
+		}
+		if (error)
+			return error;
+
+		error = xqcheck_compare_dquot(xqc, dqtype, dq);
+		xfs_qm_dqput(dq);
+		if (error)
+			return error;
+
+		if (xchk_should_terminate(xqc->sc, &error))
+			return error;
+
+		mutex_lock(&xqc->lock);
+	}
+	mutex_unlock(&xqc->lock);
+
+	return error;
+}
+
+/* Compare the quota counters we observed against the live dquots. */
+STATIC int
+xqcheck_compare_dqtype(
+	struct xqcheck		*xqc,
+	xfs_dqtype_t		dqtype)
+{
+	struct xchk_dqiter	cursor = { };
+	struct xfs_scrub	*sc = xqc->sc;
+	struct xfs_dquot	*dq;
+	int			error;
+
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		return 0;
+
+	/* If the quota CHKD flag is cleared, we need to repair this quota. */
+	if (!(xfs_quota_chkd_flag(dqtype) & sc->mp->m_qflags)) {
+		xchk_qcheck_set_corrupt(xqc->sc, dqtype, 0);
+		return 0;
+	}
+
+	/* Compare what we observed against the actual dquots. */
+	xchk_dqiter_init(&cursor, sc, dqtype);
+	while ((error = xchk_dquot_iter(&cursor, &dq)) == 1) {
+		error = xqcheck_compare_dquot(xqc, dqtype, dq);
+		xfs_qm_dqput(dq);
+		if (error)
+			break;
+	}
+	if (error)
+		return error;
+
+	/* Walk all the observed dquots and compare to the incore ones. */
+	return xqcheck_walk_observations(xqc, dqtype);
+}
+
+/* Tear down everything associated with a quotacheck. */
+static void
+xqcheck_teardown_scan(
+	void			*priv)
+{
+	struct xqcheck		*xqc = priv;
+
+	if (xqc->pcounts) {
+		xfarray_destroy(xqc->pcounts);
+		xqc->pcounts = NULL;
+	}
+
+	if (xqc->gcounts) {
+		xfarray_destroy(xqc->gcounts);
+		xqc->gcounts = NULL;
+	}
+
+	if (xqc->ucounts) {
+		xfarray_destroy(xqc->ucounts);
+		xqc->ucounts = NULL;
+	}
+
+	xchk_iscan_teardown(&xqc->iscan);
+	mutex_destroy(&xqc->lock);
+	xqc->sc = NULL;
+}
+
+/*
+ * Scan all inodes in the entire filesystem to generate quota counter data.
+ * If the scan is successful, the quota data will be left alive for a repair.
+ * If any error occurs, we'll tear everything down.
+ */
+STATIC int
+xqcheck_setup_scan(
+	struct xfs_scrub	*sc,
+	struct xqcheck		*xqc)
+{
+	char			*descr;
+	unsigned long long	max_dquots = XFS_DQ_ID_MAX + 1ULL;
+	int			error;
+
+	ASSERT(xqc->sc == NULL);
+	xqc->sc = sc;
+
+	mutex_init(&xqc->lock);
+
+	/* Retry iget every tenth of a second for up to 30 seconds. */
+	xchk_iscan_start(sc, 30000, 100, &xqc->iscan);
+
+	error = -ENOMEM;
+	if (xfs_this_quota_on(sc->mp, XFS_DQTYPE_USER)) {
+		descr = xchk_xfile_descr(sc, "user dquot records");
+		error = xfarray_create(descr, max_dquots,
+				sizeof(struct xqcheck_dquot), &xqc->ucounts);
+		kfree(descr);
+		if (error)
+			goto out_teardown;
+	}
+
+	if (xfs_this_quota_on(sc->mp, XFS_DQTYPE_GROUP)) {
+		descr = xchk_xfile_descr(sc, "group dquot records");
+		error = xfarray_create(descr, max_dquots,
+				sizeof(struct xqcheck_dquot), &xqc->gcounts);
+		kfree(descr);
+		if (error)
+			goto out_teardown;
+	}
+
+	if (xfs_this_quota_on(sc->mp, XFS_DQTYPE_PROJ)) {
+		descr = xchk_xfile_descr(sc, "project dquot records");
+		error = xfarray_create(descr, max_dquots,
+				sizeof(struct xqcheck_dquot), &xqc->pcounts);
+		kfree(descr);
+		if (error)
+			goto out_teardown;
+	}
+
+	/* Use deferred cleanup to pass the quota count data to repair. */
+	sc->buf_cleanup = xqcheck_teardown_scan;
+	return 0;
+
+out_teardown:
+	xqcheck_teardown_scan(xqc);
+	return error;
+}
+
+/* Scrub all counters for a given quota type. */
+int
+xchk_quotacheck(
+	struct xfs_scrub	*sc)
+{
+	struct xqcheck		*xqc = sc->buf;
+	int			error = 0;
+
+	/* Check quota counters on the live filesystem. */
+	error = xqcheck_setup_scan(sc, xqc);
+	if (error)
+		return error;
+
+	/* Walk all inodes, picking up quota information. */
+	error = xqcheck_collect_counts(xqc);
+	if (!xchk_xref_process_error(sc, 0, 0, &error))
+		return error;
+
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_INCOMPLETE)
+		return 0;
+
+	/* Compare quota counters. */
+	if (xqc->ucounts) {
+		error = xqcheck_compare_dqtype(xqc, XFS_DQTYPE_USER);
+		if (!xchk_xref_process_error(sc, 0, 0, &error))
+			return error;
+	}
+	if (xqc->gcounts) {
+		error = xqcheck_compare_dqtype(xqc, XFS_DQTYPE_GROUP);
+		if (!xchk_xref_process_error(sc, 0, 0, &error))
+			return error;
+	}
+	if (xqc->pcounts) {
+		error = xqcheck_compare_dqtype(xqc, XFS_DQTYPE_PROJ);
+		if (!xchk_xref_process_error(sc, 0, 0, &error))
+			return error;
+	}
+
+	return 0;
+}
diff --git a/fs/xfs/scrub/quotacheck.h b/fs/xfs/scrub/quotacheck.h
new file mode 100644
index 0000000000000..99eae596dd410
--- /dev/null
+++ b/fs/xfs/scrub/quotacheck.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2020-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_QUOTACHECK_H__
+#define __XFS_SCRUB_QUOTACHECK_H__
+
+/* Quota counters for live quotacheck. */
+struct xqcheck_dquot {
+	/* block usage count */
+	int64_t			bcount;
+
+	/* inode usage count */
+	int64_t			icount;
+
+	/* realtime block usage count */
+	int64_t			rtbcount;
+
+	/* Record state */
+	unsigned int		flags;
+};
+
+/*
+ * This incore dquot record has been written at least once.  We never want to
+ * store an xqcheck_dquot that looks uninitialized.
+ */
+#define XQCHECK_DQUOT_WRITTEN		(1U << 0)
+
+/* Already checked this dquot. */
+#define XQCHECK_DQUOT_COMPARE_SCANNED	(1U << 1)
+
+/* Live quotacheck control structure. */
+struct xqcheck {
+	struct xfs_scrub	*sc;
+
+	/* Shadow dquot counter data. */
+	struct xfarray		*ucounts;
+	struct xfarray		*gcounts;
+	struct xfarray		*pcounts;
+
+	/* Lock protecting quotacheck count observations */
+	struct mutex		lock;
+
+	struct xchk_iscan	iscan;
+};
+
+/* Return the incore counter array for a given quota type. */
+static inline struct xfarray *
+xqcheck_counters_for(
+	struct xqcheck		*xqc,
+	xfs_dqtype_t		dqtype)
+{
+	switch (dqtype) {
+	case XFS_DQTYPE_USER:
+		return xqc->ucounts;
+	case XFS_DQTYPE_GROUP:
+		return xqc->gcounts;
+	case XFS_DQTYPE_PROJ:
+		return xqc->pcounts;
+	}
+
+	ASSERT(0);
+	return NULL;
+}
+
+#endif /* __XFS_SCRUB_QUOTACHECK_H__ */
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index caf324c2b9910..d9fcf992d5899 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -360,6 +360,12 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.scrub	= xchk_fscounters,
 		.repair	= xrep_notsupported,
 	},
+	[XFS_SCRUB_TYPE_QUOTACHECK] = {	/* quota counters */
+		.type	= ST_FS,
+		.setup	= xchk_setup_quotacheck,
+		.scrub	= xchk_quotacheck,
+		.repair	= xrep_notsupported,
+	},
 };
 
 static int
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index 7fc50654c4fe7..779f37b1cb1a6 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -167,12 +167,18 @@ xchk_rtsummary(struct xfs_scrub *sc)
 #endif
 #ifdef CONFIG_XFS_QUOTA
 int xchk_quota(struct xfs_scrub *sc);
+int xchk_quotacheck(struct xfs_scrub *sc);
 #else
 static inline int
 xchk_quota(struct xfs_scrub *sc)
 {
 	return -ENOENT;
 }
+static inline int
+xchk_quotacheck(struct xfs_scrub *sc)
+{
+	return -ENOENT;
+}
 #endif
 int xchk_fscounters(struct xfs_scrub *sc);
 
diff --git a/fs/xfs/scrub/stats.c b/fs/xfs/scrub/stats.c
index cd91db4a55489..d716a432227b0 100644
--- a/fs/xfs/scrub/stats.c
+++ b/fs/xfs/scrub/stats.c
@@ -77,6 +77,7 @@ static const char *name_map[XFS_SCRUB_TYPE_NR] = {
 	[XFS_SCRUB_TYPE_GQUOTA]		= "grpquota",
 	[XFS_SCRUB_TYPE_PQUOTA]		= "prjquota",
 	[XFS_SCRUB_TYPE_FSCOUNTERS]	= "fscounters",
+	[XFS_SCRUB_TYPE_QUOTACHECK]	= "quotacheck",
 };
 
 /* Format the scrub stats into a text buffer, similar to pcp style. */
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 790982b769f72..499ba68d1fb2a 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -15,6 +15,7 @@
 
 #include <linux/tracepoint.h>
 #include "xfs_bit.h"
+#include "xfs_quota_defs.h"
 
 struct xfs_scrub;
 struct xfile;
@@ -65,6 +66,7 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_UQUOTA);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_GQUOTA);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_PQUOTA);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_FSCOUNTERS);
+TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_QUOTACHECK);
 
 #define XFS_SCRUB_TYPE_STRINGS \
 	{ XFS_SCRUB_TYPE_PROBE,		"probe" }, \
@@ -91,7 +93,8 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_FSCOUNTERS);
 	{ XFS_SCRUB_TYPE_UQUOTA,	"usrquota" }, \
 	{ XFS_SCRUB_TYPE_GQUOTA,	"grpquota" }, \
 	{ XFS_SCRUB_TYPE_PQUOTA,	"prjquota" }, \
-	{ XFS_SCRUB_TYPE_FSCOUNTERS,	"fscounters" }
+	{ XFS_SCRUB_TYPE_FSCOUNTERS,	"fscounters" }, \
+	{ XFS_SCRUB_TYPE_QUOTACHECK,	"quotacheck" }
 
 #define XFS_SCRUB_FLAG_STRINGS \
 	{ XFS_SCRUB_IFLAG_REPAIR,		"repair" }, \
@@ -397,6 +400,29 @@ DEFINE_SCRUB_DQITER_EVENT(xchk_dquot_iter_revalidate_bmap);
 DEFINE_SCRUB_DQITER_EVENT(xchk_dquot_iter_advance_bmap);
 DEFINE_SCRUB_DQITER_EVENT(xchk_dquot_iter_advance_incore);
 DEFINE_SCRUB_DQITER_EVENT(xchk_dquot_iter);
+
+TRACE_EVENT(xchk_qcheck_error,
+	TP_PROTO(struct xfs_scrub *sc, xfs_dqtype_t dqtype, xfs_dqid_t id,
+		 void *ret_ip),
+	TP_ARGS(sc, dqtype, id, ret_ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_dqtype_t, dqtype)
+		__field(xfs_dqid_t, id)
+		__field(void *, ret_ip)
+	),
+	TP_fast_assign(
+		__entry->dev = sc->mp->m_super->s_dev;
+		__entry->dqtype = dqtype;
+		__entry->id = id;
+		__entry->ret_ip = ret_ip;
+	),
+	TP_printk("dev %d:%d dquot type %s id 0x%x ret_ip %pS",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __print_symbolic(__entry->dqtype, XFS_DQTYPE_STRINGS),
+		  __entry->id,
+		  __entry->ret_ip)
+);
 #endif /* CONFIG_XFS_QUOTA */
 
 TRACE_EVENT(xchk_incomplete,
diff --git a/fs/xfs/scrub/xfarray.h b/fs/xfs/scrub/xfarray.h
index 62b9c506fdd1b..0f1dac3aa1916 100644
--- a/fs/xfs/scrub/xfarray.h
+++ b/fs/xfs/scrub/xfarray.h
@@ -45,6 +45,25 @@ int xfarray_store(struct xfarray *array, xfarray_idx_t idx, const void *ptr);
 int xfarray_store_anywhere(struct xfarray *array, const void *ptr);
 bool xfarray_element_is_null(struct xfarray *array, const void *ptr);
 
+/*
+ * Load an array element, but zero the buffer if there's no data because we
+ * haven't stored to that array element yet.
+ */
+static inline int
+xfarray_load_sparse(
+	struct xfarray	*array,
+	uint64_t	idx,
+	void		*rec)
+{
+	int		error = xfarray_load(array, idx, rec);
+
+	if (error == -ENODATA) {
+		memset(rec, 0, array->obj_size);
+		return 0;
+	}
+	return error;
+}
+
 /* Append an element to the array. */
 static inline int xfarray_append(struct xfarray *array, const void *ptr)
 {
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 1ffc8dfa2a52c..078073168fdfd 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -3777,3 +3777,24 @@ xfs_ifork_zapped(
 		return false;
 	}
 }
+
+/* Compute the number of data and realtime blocks used by a file. */
+void
+xfs_inode_count_blocks(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	xfs_filblks_t		*dblocks,
+	xfs_filblks_t		*rblocks)
+{
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
+
+	if (!XFS_IS_REALTIME_INODE(ip)) {
+		*dblocks = ip->i_nblocks;
+		*rblocks = 0;
+		return;
+	}
+
+	*rblocks = 0;
+	xfs_bmap_count_leaves(ifp, rblocks);
+	*dblocks = ip->i_nblocks - *rblocks;
+}
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 97f63bacd4c2b..15a16e1404eea 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -623,5 +623,7 @@ int xfs_inode_reload_unlinked_bucket(struct xfs_trans *tp, struct xfs_inode *ip)
 int xfs_inode_reload_unlinked(struct xfs_inode *ip);
 
 bool xfs_ifork_zapped(const struct xfs_inode *ip, int whichfork);
+void xfs_inode_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip,
+		xfs_filblks_t *dblocks, xfs_filblks_t *rblocks);
 
 #endif	/* __XFS_INODE_H__ */

[PATCH 3/5] xfs: track quota updates during live quotacheck

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a shadow dqtrx system in the quotacheck code that hooks the
regular dquot counter update code.  This will be the means to keep our
copy of the dquot counters up to date while the scan runs in real time.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/common.c     |    4 +
 fs/xfs/scrub/quotacheck.c |  358 ++++++++++++++++++++++++++++++++++++++++++++-
 fs/xfs/scrub/quotacheck.h |    6 +
 fs/xfs/scrub/scrub.c      |    3 
 fs/xfs/scrub/scrub.h      |    4 -
 fs/xfs/scrub/trace.h      |    1 
 fs/xfs/xfs_qm.c           |   16 +-
 fs/xfs/xfs_qm.h           |   16 ++
 fs/xfs/xfs_qm_bhv.c       |    1 
 fs/xfs/xfs_quota.h        |   45 ++++++
 fs/xfs/xfs_trans_dquot.c  |  156 +++++++++++++++++++-
 11 files changed, 594 insertions(+), 16 deletions(-)


diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index fc23bd9d38195..6e193aee12666 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -30,6 +30,7 @@
 #include "xfs_reflink.h"
 #include "xfs_ag.h"
 #include "xfs_error.h"
+#include "xfs_quota.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
@@ -1298,6 +1299,9 @@ xchk_fsgates_enable(
 	if (scrub_fsgates & XCHK_FSGATES_DRAIN)
 		xfs_drain_wait_enable();
 
+	if (scrub_fsgates & XCHK_FSGATES_QUOTA)
+		xfs_dqtrx_hook_enable();
+
 	sc->flags |= scrub_fsgates;
 }
 
diff --git a/fs/xfs/scrub/quotacheck.c b/fs/xfs/scrub/quotacheck.c
index 79a6ac25419d7..d1597838cdac4 100644
--- a/fs/xfs/scrub/quotacheck.c
+++ b/fs/xfs/scrub/quotacheck.c
@@ -38,17 +38,54 @@
  * creating a shadow quota counter structure and walking every inode.
  */
 
+/* Track the quota deltas for a dquot in a transaction. */
+struct xqcheck_dqtrx {
+	xfs_dqtype_t		q_type;
+	xfs_dqid_t		q_id;
+
+	int64_t			icount_delta;
+
+	int64_t			bcount_delta;
+	int64_t			delbcnt_delta;
+
+	int64_t			rtbcount_delta;
+	int64_t			delrtb_delta;
+};
+
+#define XQCHECK_MAX_NR_DQTRXS	(XFS_QM_TRANS_DQTYPES * XFS_QM_TRANS_MAXDQS)
+
+/*
+ * Track the quota deltas for all dquots attached to a transaction if the
+ * quota deltas are being applied to an inode that we already scanned.
+ */
+struct xqcheck_dqacct {
+	struct rhash_head	hash;
+	uintptr_t		tx_id;
+	struct xqcheck_dqtrx	dqtrx[XQCHECK_MAX_NR_DQTRXS];
+	unsigned int		refcount;
+};
+
+/* Free a shadow dquot accounting structure. */
+static void
+xqcheck_dqacct_free(
+	void			*ptr,
+	void			*arg)
+{
+	struct xqcheck_dqacct	*dqa = ptr;
+
+	kfree(dqa);
+}
+
 /* Set us up to scrub quota counters. */
 int
 xchk_setup_quotacheck(
 	struct xfs_scrub	*sc)
 {
-	/* Not ready for general consumption yet. */
-	return -EOPNOTSUPP;
-
 	if (!XFS_IS_QUOTA_ON(sc->mp))
 		return -ENOENT;
 
+	xchk_fsgates_enable(sc, XCHK_FSGATES_QUOTA);
+
 	sc->buf = kzalloc(sizeof(struct xqcheck), XCHK_GFP_FLAGS);
 	if (!sc->buf)
 		return -ENOMEM;
@@ -66,6 +103,22 @@ xchk_setup_quotacheck(
  * must be taken with certain errno values (i.e. EFSBADCRC, EFSCORRUPTED,
  * ECANCELED) that are absorbed into a scrub state flag update by
  * xchk_*_process_error.
+ *
+ * Because we are scanning a live filesystem, it's possible that another thread
+ * will try to update the quota counters for an inode that we've already
+ * scanned.  This will cause our counts to be incorrect.  Therefore, we hook
+ * the live transaction code in two places: (1) when the callers update the
+ * per-transaction dqtrx structure to log quota counter updates; and (2) when
+ * transaction commit actually logs those updates to the incore dquot.  By
+ * shadowing transaction updates in this manner, live quotacheck can ensure
+ * by locking the dquot and the shadow structure that its own copies are not
+ * out of date.  Because the hook code runs in a different process context from
+ * the scrub code and the scrub state flags are not accessed atomically,
+ * failures in the hook code must abort the iscan and the scrubber must notice
+ * the aborted scan and set the incomplete flag.
+ *
+ * Note that we use srcu notifier hooks to minimize the overhead when live
+ * quotacheck is /not/ running.
  */
 
 /* Update an incore dquot counter information from a live update. */
@@ -102,6 +155,234 @@ xqcheck_update_incore_counts(
 	return error;
 }
 
+/* Decide if this is the shadow dquot accounting structure for a transaction. */
+static int
+xqcheck_dqacct_obj_cmpfn(
+	struct rhashtable_compare_arg	*arg,
+	const void			*obj)
+{
+	const uintptr_t			*tx_idp = arg->key;
+	const struct xqcheck_dqacct	*dqa = obj;
+
+	if (dqa->tx_id != *tx_idp)
+		return 1;
+	return 0;
+}
+
+static const struct rhashtable_params xqcheck_dqacct_hash_params = {
+	.min_size		= 32,
+	.key_len		= sizeof(uintptr_t),
+	.key_offset		= offsetof(struct xqcheck_dqacct, tx_id),
+	.head_offset		= offsetof(struct xqcheck_dqacct, hash),
+	.automatic_shrinking	= true,
+	.obj_cmpfn		= xqcheck_dqacct_obj_cmpfn,
+};
+
+/* Find a shadow dqtrx slot for the given dquot. */
+STATIC struct xqcheck_dqtrx *
+xqcheck_get_dqtrx(
+	struct xqcheck_dqacct	*dqa,
+	xfs_dqtype_t		q_type,
+	xfs_dqid_t		q_id)
+{
+	int			i;
+
+	for (i = 0; i < XQCHECK_MAX_NR_DQTRXS; i++) {
+		if (dqa->dqtrx[i].q_type == 0 ||
+		    (dqa->dqtrx[i].q_type == q_type &&
+		     dqa->dqtrx[i].q_id == q_id))
+			return &dqa->dqtrx[i];
+	}
+
+	return NULL;
+}
+
+/*
+ * Create and fill out a quota delta tracking structure to shadow the updates
+ * going on in the regular quota code.
+ */
+static int
+xqcheck_mod_live_ino_dqtrx(
+	struct notifier_block		*nb,
+	unsigned long			action,
+	void				*data)
+{
+	struct xfs_mod_ino_dqtrx_params *p = data;
+	struct xqcheck			*xqc;
+	struct xqcheck_dqacct		*dqa;
+	struct xqcheck_dqtrx		*dqtrx;
+	int				error;
+
+	xqc = container_of(nb, struct xqcheck, hooks.mod_hook.nb);
+
+	/* Skip quota reservation fields. */
+	switch (action) {
+	case XFS_TRANS_DQ_BCOUNT:
+	case XFS_TRANS_DQ_DELBCOUNT:
+	case XFS_TRANS_DQ_ICOUNT:
+	case XFS_TRANS_DQ_RTBCOUNT:
+	case XFS_TRANS_DQ_DELRTBCOUNT:
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	/* Ignore dqtrx updates for quota types we don't care about. */
+	switch (p->q_type) {
+	case XFS_DQTYPE_USER:
+		if (!xqc->ucounts)
+			return NOTIFY_DONE;
+		break;
+	case XFS_DQTYPE_GROUP:
+		if (!xqc->gcounts)
+			return NOTIFY_DONE;
+		break;
+	case XFS_DQTYPE_PROJ:
+		if (!xqc->pcounts)
+			return NOTIFY_DONE;
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	/* Skip inodes that haven't been scanned yet. */
+	if (!xchk_iscan_want_live_update(&xqc->iscan, p->ino))
+		return NOTIFY_DONE;
+
+	/* Make a shadow quota accounting tracker for this transaction. */
+	mutex_lock(&xqc->lock);
+	dqa = rhashtable_lookup_fast(&xqc->shadow_dquot_acct, &p->tx_id,
+			xqcheck_dqacct_hash_params);
+	if (!dqa) {
+		dqa = kzalloc(sizeof(struct xqcheck_dqacct), XCHK_GFP_FLAGS);
+		if (!dqa)
+			goto out_abort;
+
+		dqa->tx_id = p->tx_id;
+		error = rhashtable_insert_fast(&xqc->shadow_dquot_acct,
+				&dqa->hash, xqcheck_dqacct_hash_params);
+		if (error)
+			goto out_abort;
+	}
+
+	/* Find the shadow dqtrx (or an empty slot) here. */
+	dqtrx = xqcheck_get_dqtrx(dqa, p->q_type, p->q_id);
+	if (!dqtrx)
+		goto out_abort;
+	if (dqtrx->q_type == 0) {
+		dqtrx->q_type = p->q_type;
+		dqtrx->q_id = p->q_id;
+		dqa->refcount++;
+	}
+
+	/* Update counter */
+	switch (action) {
+	case XFS_TRANS_DQ_BCOUNT:
+		dqtrx->bcount_delta += p->delta;
+		break;
+	case XFS_TRANS_DQ_DELBCOUNT:
+		dqtrx->delbcnt_delta += p->delta;
+		break;
+	case XFS_TRANS_DQ_ICOUNT:
+		dqtrx->icount_delta += p->delta;
+		break;
+	case XFS_TRANS_DQ_RTBCOUNT:
+		dqtrx->rtbcount_delta += p->delta;
+		break;
+	case XFS_TRANS_DQ_DELRTBCOUNT:
+		dqtrx->delrtb_delta += p->delta;
+		break;
+	}
+
+	mutex_unlock(&xqc->lock);
+	return NOTIFY_DONE;
+
+out_abort:
+	xchk_iscan_abort(&xqc->iscan);
+	mutex_unlock(&xqc->lock);
+	return NOTIFY_DONE;
+}
+
+/*
+ * Apply the transaction quota deltas to our shadow quota accounting info when
+ * the regular quota code are doing the same.
+ */
+static int
+xqcheck_apply_live_dqtrx(
+	struct notifier_block		*nb,
+	unsigned long			action,
+	void				*data)
+{
+	struct xfs_apply_dqtrx_params	*p = data;
+	struct xqcheck			*xqc;
+	struct xqcheck_dqacct		*dqa;
+	struct xqcheck_dqtrx		*dqtrx;
+	struct xfarray			*counts;
+	int				error;
+
+	xqc = container_of(nb, struct xqcheck, hooks.apply_hook.nb);
+
+	/* Map the dquot type to an incore counter object. */
+	switch (p->q_type) {
+	case XFS_DQTYPE_USER:
+		counts = xqc->ucounts;
+		break;
+	case XFS_DQTYPE_GROUP:
+		counts = xqc->gcounts;
+		break;
+	case XFS_DQTYPE_PROJ:
+		counts = xqc->pcounts;
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	if (xchk_iscan_aborted(&xqc->iscan) || counts == NULL)
+		return NOTIFY_DONE;
+
+	/*
+	 * Find the shadow dqtrx for this transaction and dquot, if any deltas
+	 * need to be applied here.  If not, we're finished early.
+	 */
+	mutex_lock(&xqc->lock);
+	dqa = rhashtable_lookup_fast(&xqc->shadow_dquot_acct, &p->tx_id,
+			xqcheck_dqacct_hash_params);
+	if (!dqa)
+		goto out_unlock;
+	dqtrx = xqcheck_get_dqtrx(dqa, p->q_type, p->q_id);
+	if (!dqtrx || dqtrx->q_type == 0)
+		goto out_unlock;
+
+	/* Update our shadow dquot if we're committing. */
+	if (action == XFS_APPLY_DQTRX_COMMIT) {
+		error = xqcheck_update_incore_counts(xqc, counts, p->q_id,
+				dqtrx->icount_delta,
+				dqtrx->bcount_delta + dqtrx->delbcnt_delta,
+				dqtrx->rtbcount_delta + dqtrx->delrtb_delta);
+		if (error)
+			goto out_abort;
+	}
+
+	/* Free the shadow accounting structure if that was the last user. */
+	dqa->refcount--;
+	if (dqa->refcount == 0) {
+		error = rhashtable_remove_fast(&xqc->shadow_dquot_acct,
+				&dqa->hash, xqcheck_dqacct_hash_params);
+		if (error)
+			goto out_abort;
+		xqcheck_dqacct_free(dqa, NULL);
+	}
+
+	mutex_unlock(&xqc->lock);
+	return NOTIFY_DONE;
+
+out_abort:
+	xchk_iscan_abort(&xqc->iscan);
+out_unlock:
+	mutex_unlock(&xqc->lock);
+	return NOTIFY_DONE;
+}
+
 /* Record this inode's quota usage in our shadow quota counter data. */
 STATIC int
 xqcheck_collect_inode(
@@ -132,13 +413,18 @@ xqcheck_collect_inode(
 		ilock_flags = xfs_ilock_data_map_shared(ip);
 		error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
 		if (error)
-			goto out_incomplete;
+			goto out_abort;
 	} else {
 		ilock_flags = XFS_ILOCK_SHARED;
 		xfs_ilock(ip, XFS_ILOCK_SHARED);
 	}
 	xfs_inode_count_blocks(tp, ip, &nblks, &rtblks);
 
+	if (xchk_iscan_aborted(&xqc->iscan)) {
+		error = -ECANCELED;
+		goto out_incomplete;
+	}
+
 	/* Update the shadow dquot counters. */
 	mutex_lock(&xqc->lock);
 	if (xqc->ucounts) {
@@ -171,6 +457,8 @@ xqcheck_collect_inode(
 
 out_mutex:
 	mutex_unlock(&xqc->lock);
+out_abort:
+	xchk_iscan_abort(&xqc->iscan);
 out_incomplete:
 	xchk_set_incomplete(xqc->sc);
 out_ilock:
@@ -262,6 +550,11 @@ xqcheck_compare_dquot(
 	struct xfarray		*counts = xqcheck_counters_for(xqc, dqtype);
 	int			error;
 
+	if (xchk_iscan_aborted(&xqc->iscan)) {
+		xchk_set_incomplete(xqc->sc);
+		return -ECANCELED;
+	}
+
 	mutex_lock(&xqc->lock);
 	error = xfarray_load_sparse(counts, dq->q_id, &xcdq);
 	if (error)
@@ -283,7 +576,7 @@ xqcheck_compare_dquot(
 		 * EFBIG means we tried to store data at too high a byte offset
 		 * in the sparse array.  IOWs, we cannot complete the check and
 		 * must notify userspace that the check was incomplete.  This
-		 * should never happen, since we just read the record.
+		 * should never happen outside of the collection phase.
 		 */
 		xchk_set_incomplete(xqc->sc);
 		error = -ECANCELED;
@@ -390,6 +683,26 @@ xqcheck_teardown_scan(
 	void			*priv)
 {
 	struct xqcheck		*xqc = priv;
+	struct xfs_quotainfo	*qi = xqc->sc->mp->m_quotainfo;
+
+	/* Discourage any hook functions that might be running. */
+	xchk_iscan_abort(&xqc->iscan);
+
+	/*
+	 * As noted above, the apply hook is responsible for cleaning up the
+	 * shadow dquot accounting data when a transaction completes.  The mod
+	 * hook must be removed before the apply hook so that we don't
+	 * mistakenly leave an active shadow account for the mod hook to get
+	 * its hands on.  No hooks should be running after these functions
+	 * return.
+	 */
+	xfs_dqtrx_hook_del(qi, &xqc->hooks);
+
+	if (xqc->shadow_dquot_acct.key_len) {
+		rhashtable_free_and_destroy(&xqc->shadow_dquot_acct,
+				xqcheck_dqacct_free, NULL);
+		xqc->shadow_dquot_acct.key_len = 0;
+	}
 
 	if (xqc->pcounts) {
 		xfarray_destroy(xqc->pcounts);
@@ -422,6 +735,7 @@ xqcheck_setup_scan(
 	struct xqcheck		*xqc)
 {
 	char			*descr;
+	struct xfs_quotainfo	*qi = sc->mp->m_quotainfo;
 	unsigned long long	max_dquots = XFS_DQ_ID_MAX + 1ULL;
 	int			error;
 
@@ -461,6 +775,33 @@ xqcheck_setup_scan(
 			goto out_teardown;
 	}
 
+	/*
+	 * Set up hash table to map transactions to our internal shadow dqtrx
+	 * structures.
+	 */
+	error = rhashtable_init(&xqc->shadow_dquot_acct,
+			&xqcheck_dqacct_hash_params);
+	if (error)
+		goto out_teardown;
+
+	/*
+	 * Hook into the quota code.  The hook only triggers for inodes that
+	 * were already scanned, and the scanner thread takes each inode's
+	 * ILOCK, which means that any in-progress inode updates will finish
+	 * before we can scan the inode.
+	 *
+	 * The apply hook (which removes the shadow dquot accounting struct)
+	 * must be installed before the mod hook so that we never fail to catch
+	 * the end of a quota update sequence and leave stale shadow data.
+	 */
+	ASSERT(sc->flags & XCHK_FSGATES_QUOTA);
+	xfs_hook_setup(&xqc->hooks.mod_hook, xqcheck_mod_live_ino_dqtrx);
+	xfs_hook_setup(&xqc->hooks.apply_hook, xqcheck_apply_live_dqtrx);
+
+	error = xfs_dqtrx_hook_add(qi, &xqc->hooks);
+	if (error)
+		goto out_teardown;
+
 	/* Use deferred cleanup to pass the quota count data to repair. */
 	sc->buf_cleanup = xqcheck_teardown_scan;
 	return 0;
@@ -488,6 +829,9 @@ xchk_quotacheck(
 	if (!xchk_xref_process_error(sc, 0, 0, &error))
 		return error;
 
+	/* Fail fast if we're not playing with a full dataset. */
+	if (xchk_iscan_aborted(&xqc->iscan))
+		xchk_set_incomplete(sc);
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_INCOMPLETE)
 		return 0;
 
@@ -508,5 +852,9 @@ xchk_quotacheck(
 			return error;
 	}
 
+	/* Check one last time for an incomplete dataset. */
+	if (xchk_iscan_aborted(&xqc->iscan))
+		xchk_set_incomplete(sc);
+
 	return 0;
 }
diff --git a/fs/xfs/scrub/quotacheck.h b/fs/xfs/scrub/quotacheck.h
index 99eae596dd410..3615fec3e409e 100644
--- a/fs/xfs/scrub/quotacheck.h
+++ b/fs/xfs/scrub/quotacheck.h
@@ -43,6 +43,12 @@ struct xqcheck {
 	struct mutex		lock;
 
 	struct xchk_iscan	iscan;
+
+	/* Hooks into the quota code. */
+	struct xfs_dqtrx_hook	hooks;
+
+	/* Shadow quota delta tracking structure. */
+	struct rhashtable	shadow_dquot_acct;
 };
 
 /* Return the incore counter array for a given quota type. */
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index d9fcf992d5899..71a9eb48e1de7 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -157,6 +157,9 @@ xchk_fsgates_disable(
 	if (sc->flags & XCHK_FSGATES_DRAIN)
 		xfs_drain_wait_disable();
 
+	if (sc->flags & XCHK_FSGATES_QUOTA)
+		xfs_dqtrx_hook_disable();
+
 	sc->flags &= ~XCHK_FSGATES_ALL;
 }
 
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index 779f37b1cb1a6..5cd4550155f23 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -121,6 +121,7 @@ struct xfs_scrub {
 #define XCHK_HAVE_FREEZE_PROT	(1U << 1)  /* do we have freeze protection? */
 #define XCHK_FSGATES_DRAIN	(1U << 2)  /* defer ops draining enabled */
 #define XCHK_NEED_DRAIN		(1U << 3)  /* scrub needs to drain defer ops */
+#define XCHK_FSGATES_QUOTA	(1U << 4)  /* quota live update enabled */
 #define XREP_RESET_PERAG_RESV	(1U << 30) /* must reset AG space reservation */
 #define XREP_ALREADY_FIXED	(1U << 31) /* checking our repair work */
 
@@ -130,7 +131,8 @@ struct xfs_scrub {
  * features are gated off via dynamic code patching, which is why the state
  * must be enabled during scrub setup and can only be torn down afterwards.
  */
-#define XCHK_FSGATES_ALL	(XCHK_FSGATES_DRAIN)
+#define XCHK_FSGATES_ALL	(XCHK_FSGATES_DRAIN | \
+				 XCHK_FSGATES_QUOTA)
 
 /* Metadata scrubbers */
 int xchk_tester(struct xfs_scrub *sc);
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 499ba68d1fb2a..afe2c92233f1b 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -112,6 +112,7 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_QUOTACHECK);
 	{ XCHK_HAVE_FREEZE_PROT,		"nofreeze" }, \
 	{ XCHK_FSGATES_DRAIN,			"fsgates_drain" }, \
 	{ XCHK_NEED_DRAIN,			"need_drain" }, \
+	{ XCHK_FSGATES_QUOTA,			"fsgates_quota" }, \
 	{ XREP_RESET_PERAG_RESV,		"reset_perag_resv" }, \
 	{ XREP_ALREADY_FIXED,			"already_fixed" }
 
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 826aa5790cdeb..3cc1be30a9f74 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -692,6 +692,9 @@ xfs_qm_init_quotainfo(
 
 	shrinker_register(qinf->qi_shrinker);
 
+	xfs_hooks_init(&qinf->qi_mod_ino_dqtrx_hooks);
+	xfs_hooks_init(&qinf->qi_apply_dqtrx_hooks);
+
 	return 0;
 
 out_free_inos:
@@ -1822,12 +1825,12 @@ xfs_qm_vop_chown(
 	ASSERT(prevdq);
 	ASSERT(prevdq != newdq);
 
-	xfs_trans_mod_dquot(tp, prevdq, bfield, -(ip->i_nblocks));
-	xfs_trans_mod_dquot(tp, prevdq, XFS_TRANS_DQ_ICOUNT, -1);
+	xfs_trans_mod_ino_dquot(tp, ip, prevdq, bfield, -(ip->i_nblocks));
+	xfs_trans_mod_ino_dquot(tp, ip, prevdq, XFS_TRANS_DQ_ICOUNT, -1);
 
 	/* the sparkling new dquot */
-	xfs_trans_mod_dquot(tp, newdq, bfield, ip->i_nblocks);
-	xfs_trans_mod_dquot(tp, newdq, XFS_TRANS_DQ_ICOUNT, 1);
+	xfs_trans_mod_ino_dquot(tp, ip, newdq, bfield, ip->i_nblocks);
+	xfs_trans_mod_ino_dquot(tp, ip, newdq, XFS_TRANS_DQ_ICOUNT, 1);
 
 	/*
 	 * Back when we made quota reservations for the chown, we reserved the
@@ -1909,22 +1912,21 @@ xfs_qm_vop_create_dqattach(
 		ASSERT(i_uid_read(VFS_I(ip)) == udqp->q_id);
 
 		ip->i_udquot = xfs_qm_dqhold(udqp);
-		xfs_trans_mod_dquot(tp, udqp, XFS_TRANS_DQ_ICOUNT, 1);
 	}
 	if (gdqp && XFS_IS_GQUOTA_ON(mp)) {
 		ASSERT(ip->i_gdquot == NULL);
 		ASSERT(i_gid_read(VFS_I(ip)) == gdqp->q_id);
 
 		ip->i_gdquot = xfs_qm_dqhold(gdqp);
-		xfs_trans_mod_dquot(tp, gdqp, XFS_TRANS_DQ_ICOUNT, 1);
 	}
 	if (pdqp && XFS_IS_PQUOTA_ON(mp)) {
 		ASSERT(ip->i_pdquot == NULL);
 		ASSERT(ip->i_projid == pdqp->q_id);
 
 		ip->i_pdquot = xfs_qm_dqhold(pdqp);
-		xfs_trans_mod_dquot(tp, pdqp, XFS_TRANS_DQ_ICOUNT, 1);
 	}
+
+	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_ICOUNT, 1);
 }
 
 /* Decide if this inode's dquot is near an enforcement boundary. */
diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h
index d5c9fc4ba591e..f5993012bf98f 100644
--- a/fs/xfs/xfs_qm.h
+++ b/fs/xfs/xfs_qm.h
@@ -68,6 +68,10 @@ struct xfs_quotainfo {
 	/* Minimum and maximum quota expiration timestamp values. */
 	time64_t		qi_expiry_min;
 	time64_t		qi_expiry_max;
+
+	/* Hook to feed quota counter updates to an active online repair. */
+	struct xfs_hooks	qi_mod_ino_dqtrx_hooks;
+	struct xfs_hooks	qi_apply_dqtrx_hooks;
 };
 
 static inline struct radix_tree_root *
@@ -104,6 +108,18 @@ xfs_quota_inode(struct xfs_mount *mp, xfs_dqtype_t type)
 	return NULL;
 }
 
+/*
+ * Parameters for tracking dqtrx changes on behalf of an inode.  The hook
+ * function arg parameter is the field being updated.
+ */
+struct xfs_mod_ino_dqtrx_params {
+	uintptr_t		tx_id;
+	xfs_ino_t		ino;
+	xfs_dqtype_t		q_type;
+	xfs_dqid_t		q_id;
+	int64_t			delta;
+};
+
 extern void	xfs_trans_mod_dquot(struct xfs_trans *tp, struct xfs_dquot *dqp,
 				    uint field, int64_t delta);
 extern void	xfs_trans_dqjoin(struct xfs_trans *, struct xfs_dquot *);
diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c
index b77673dd05581..271c1021c7335 100644
--- a/fs/xfs/xfs_qm_bhv.c
+++ b/fs/xfs/xfs_qm_bhv.c
@@ -9,6 +9,7 @@
 #include "xfs_format.h"
 #include "xfs_log_format.h"
 #include "xfs_trans_resv.h"
+#include "xfs_mount.h"
 #include "xfs_quota.h"
 #include "xfs_mount.h"
 #include "xfs_inode.h"
diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h
index dcc785fdd3453..fe63489d91b2f 100644
--- a/fs/xfs/xfs_quota.h
+++ b/fs/xfs/xfs_quota.h
@@ -74,6 +74,22 @@ struct xfs_dqtrx {
 	int64_t		qt_icount_delta;  /* dquot inode count changes */
 };
 
+enum xfs_apply_dqtrx_type {
+	XFS_APPLY_DQTRX_COMMIT = 0,
+	XFS_APPLY_DQTRX_UNRESERVE,
+};
+
+/*
+ * Parameters for applying dqtrx changes to a dquot.  The hook function arg
+ * parameter is enum xfs_apply_dqtrx_type.
+ */
+struct xfs_apply_dqtrx_params {
+	uintptr_t		tx_id;
+	xfs_ino_t		ino;
+	xfs_dqtype_t		q_type;
+	xfs_dqid_t		q_id;
+};
+
 #ifdef CONFIG_XFS_QUOTA
 extern void xfs_trans_dup_dqinfo(struct xfs_trans *, struct xfs_trans *);
 extern void xfs_trans_free_dqinfo(struct xfs_trans *);
@@ -114,6 +130,29 @@ xfs_quota_reserve_blkres(struct xfs_inode *ip, int64_t blocks)
 	return xfs_trans_reserve_quota_nblks(NULL, ip, blocks, 0, false);
 }
 bool xfs_inode_near_dquot_enforcement(struct xfs_inode *ip, xfs_dqtype_t type);
+
+# ifdef CONFIG_XFS_LIVE_HOOKS
+void xfs_trans_mod_ino_dquot(struct xfs_trans *tp, struct xfs_inode *ip,
+		struct xfs_dquot *dqp, unsigned int field, int64_t delta);
+
+struct xfs_quotainfo;
+
+struct xfs_dqtrx_hook {
+	struct xfs_hook		mod_hook;
+	struct xfs_hook		apply_hook;
+};
+
+void xfs_dqtrx_hook_disable(void);
+void xfs_dqtrx_hook_enable(void);
+
+int xfs_dqtrx_hook_add(struct xfs_quotainfo *qi, struct xfs_dqtrx_hook *hook);
+void xfs_dqtrx_hook_del(struct xfs_quotainfo *qi, struct xfs_dqtrx_hook *hook);
+
+# else
+#  define xfs_trans_mod_ino_dquot(tp, ip, dqp, field, delta) \
+		xfs_trans_mod_dquot((tp), (dqp), (field), (delta))
+# endif /* CONFIG_XFS_LIVE_HOOKS */
+
 #else
 static inline int
 xfs_qm_vop_dqalloc(struct xfs_inode *ip, kuid_t kuid, kgid_t kgid,
@@ -170,6 +209,12 @@ xfs_trans_reserve_quota_icreate(struct xfs_trans *tp, struct xfs_dquot *udqp,
 #define xfs_qm_unmount(mp)
 #define xfs_qm_unmount_quotas(mp)
 #define xfs_inode_near_dquot_enforcement(ip, type)			(false)
+
+# ifdef CONFIG_XFS_LIVE_HOOKS
+#  define xfs_dqtrx_hook_enable()		((void)0)
+#  define xfs_dqtrx_hook_disable()		((void)0)
+# endif /* CONFIG_XFS_LIVE_HOOKS */
+
 #endif /* CONFIG_XFS_QUOTA */
 
 static inline int
diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c
index 968dc7af4fc7d..f5e9d76fb9a2f 100644
--- a/fs/xfs/xfs_trans_dquot.c
+++ b/fs/xfs/xfs_trans_dquot.c
@@ -121,6 +121,105 @@ xfs_trans_dup_dqinfo(
 	}
 }
 
+#ifdef CONFIG_XFS_LIVE_HOOKS
+/*
+ * Use a static key here to reduce the overhead of quota live updates.  If the
+ * compiler supports jump labels, the static branch will be replaced by a nop
+ * sled when there are no hook users.  Online fsck is currently the only
+ * caller, so this is a reasonable tradeoff.
+ *
+ * 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_STATIC_XFS_HOOK_SWITCH(xfs_dqtrx_hooks_switch);
+
+void
+xfs_dqtrx_hook_disable(void)
+{
+	xfs_hooks_switch_off(&xfs_dqtrx_hooks_switch);
+}
+
+void
+xfs_dqtrx_hook_enable(void)
+{
+	xfs_hooks_switch_on(&xfs_dqtrx_hooks_switch);
+}
+
+/* Schedule a transactional dquot update on behalf of an inode. */
+void
+xfs_trans_mod_ino_dquot(
+	struct xfs_trans		*tp,
+	struct xfs_inode		*ip,
+	struct xfs_dquot		*dqp,
+	unsigned int			field,
+	int64_t				delta)
+{
+	xfs_trans_mod_dquot(tp, dqp, field, delta);
+
+	if (xfs_hooks_switched_on(&xfs_dqtrx_hooks_switch)) {
+		struct xfs_mod_ino_dqtrx_params	p = {
+			.tx_id		= (uintptr_t)tp,
+			.ino		= ip->i_ino,
+			.q_type		= xfs_dquot_type(dqp),
+			.q_id		= dqp->q_id,
+			.delta		= delta
+		};
+		struct xfs_quotainfo	*qi = tp->t_mountp->m_quotainfo;
+
+		xfs_hooks_call(&qi->qi_mod_ino_dqtrx_hooks, field, &p);
+	}
+}
+
+/* Call the specified functions during a dquot counter update. */
+int
+xfs_dqtrx_hook_add(
+	struct xfs_quotainfo	*qi,
+	struct xfs_dqtrx_hook	*hook)
+{
+	int			error;
+
+	/*
+	 * Transactional dquot updates first call the mod hook when changes
+	 * are attached to the transaction and then call the apply hook when
+	 * those changes are committed (or canceled).
+	 *
+	 * The apply hook must be installed before the mod hook so that we
+	 * never fail to catch the end of a quota update sequence.
+	 */
+	error = xfs_hooks_add(&qi->qi_apply_dqtrx_hooks, &hook->apply_hook);
+	if (error)
+		goto out;
+
+	error = xfs_hooks_add(&qi->qi_mod_ino_dqtrx_hooks, &hook->mod_hook);
+	if (error)
+		goto out_apply;
+
+	return 0;
+
+out_apply:
+	xfs_hooks_del(&qi->qi_apply_dqtrx_hooks, &hook->apply_hook);
+out:
+	return error;
+}
+
+/* Stop calling the specified function during a dquot counter update. */
+void
+xfs_dqtrx_hook_del(
+	struct xfs_quotainfo	*qi,
+	struct xfs_dqtrx_hook	*hook)
+{
+	/*
+	 * The mod hook must be removed before apply hook to avoid giving the
+	 * hook consumer with an incomplete update.  No hooks should be running
+	 * after these functions return.
+	 */
+	xfs_hooks_del(&qi->qi_mod_ino_dqtrx_hooks, &hook->mod_hook);
+	xfs_hooks_del(&qi->qi_apply_dqtrx_hooks, &hook->apply_hook);
+}
+#endif /* CONFIG_XFS_LIVE_HOOKS */
+
 /*
  * Wrap around mod_dquot to account for both user and group quotas.
  */
@@ -138,11 +237,11 @@ xfs_trans_mod_dquot_byino(
 		return;
 
 	if (XFS_IS_UQUOTA_ON(mp) && ip->i_udquot)
-		(void) xfs_trans_mod_dquot(tp, ip->i_udquot, field, delta);
+		xfs_trans_mod_ino_dquot(tp, ip, ip->i_udquot, field, delta);
 	if (XFS_IS_GQUOTA_ON(mp) && ip->i_gdquot)
-		(void) xfs_trans_mod_dquot(tp, ip->i_gdquot, field, delta);
+		xfs_trans_mod_ino_dquot(tp, ip, ip->i_gdquot, field, delta);
 	if (XFS_IS_PQUOTA_ON(mp) && ip->i_pdquot)
-		(void) xfs_trans_mod_dquot(tp, ip->i_pdquot, field, delta);
+		xfs_trans_mod_ino_dquot(tp, ip, ip->i_pdquot, field, delta);
 }
 
 STATIC struct xfs_dqtrx *
@@ -322,6 +421,29 @@ xfs_apply_quota_reservation_deltas(
 	}
 }
 
+#ifdef CONFIG_XFS_LIVE_HOOKS
+/* Call downstream hooks now that it's time to apply dquot deltas. */
+static inline void
+xfs_trans_apply_dquot_deltas_hook(
+	struct xfs_trans		*tp,
+	struct xfs_dquot		*dqp)
+{
+	if (xfs_hooks_switched_on(&xfs_dqtrx_hooks_switch)) {
+		struct xfs_apply_dqtrx_params	p = {
+			.tx_id		= (uintptr_t)tp,
+			.q_type		= xfs_dquot_type(dqp),
+			.q_id		= dqp->q_id,
+		};
+		struct xfs_quotainfo	*qi = tp->t_mountp->m_quotainfo;
+
+		xfs_hooks_call(&qi->qi_apply_dqtrx_hooks,
+				XFS_APPLY_DQTRX_COMMIT, &p);
+	}
+}
+#else
+# define xfs_trans_apply_dquot_deltas_hook(tp, dqp)	((void)0)
+#endif /* CONFIG_XFS_LIVE_HOOKS */
+
 /*
  * Called by xfs_trans_commit() and similar in spirit to
  * xfs_trans_apply_sb_deltas().
@@ -367,6 +489,8 @@ xfs_trans_apply_dquot_deltas(
 
 			ASSERT(XFS_DQ_IS_LOCKED(dqp));
 
+			xfs_trans_apply_dquot_deltas_hook(tp, dqp);
+
 			/*
 			 * adjust the actual number of blocks used
 			 */
@@ -466,6 +590,29 @@ xfs_trans_apply_dquot_deltas(
 	}
 }
 
+#ifdef CONFIG_XFS_LIVE_HOOKS
+/* Call downstream hooks now that it's time to cancel dquot deltas. */
+static inline void
+xfs_trans_unreserve_and_mod_dquots_hook(
+	struct xfs_trans		*tp,
+	struct xfs_dquot		*dqp)
+{
+	if (xfs_hooks_switched_on(&xfs_dqtrx_hooks_switch)) {
+		struct xfs_apply_dqtrx_params	p = {
+			.tx_id		= (uintptr_t)tp,
+			.q_type		= xfs_dquot_type(dqp),
+			.q_id		= dqp->q_id,
+		};
+		struct xfs_quotainfo	*qi = tp->t_mountp->m_quotainfo;
+
+		xfs_hooks_call(&qi->qi_apply_dqtrx_hooks,
+				XFS_APPLY_DQTRX_UNRESERVE, &p);
+	}
+}
+#else
+# define xfs_trans_unreserve_and_mod_dquots_hook(tp, dqp)	((void)0)
+#endif /* CONFIG_XFS_LIVE_HOOKS */
+
 /*
  * Release the reservations, and adjust the dquots accordingly.
  * This is called only when the transaction is being aborted. If by
@@ -496,6 +643,9 @@ xfs_trans_unreserve_and_mod_dquots(
 			 */
 			if ((dqp = qtrx->qt_dquot) == NULL)
 				break;
+
+			xfs_trans_unreserve_and_mod_dquots_hook(tp, dqp);
+
 			/*
 			 * Unreserve the original reservation. We don't care
 			 * about the number of blocks used field, or deltas.

[PATCH 4/5] xfs: repair cannot update the summary counters when logging quota flags

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

While running xfs/804 (quota repairs racing with fsstress), I observed a
filesystem shutdown in the primary sb write verifier:

run fstests xfs/804 at 2022-05-23 18:43:48
XFS (sda4): Mounting V5 Filesystem
XFS (sda4): Ending clean mount
XFS (sda4): Quotacheck needed: Please wait.
XFS (sda4): Quotacheck: Done.
XFS (sda4): EXPERIMENTAL online scrub feature in use. Use at your own risk!
XFS (sda4): SB ifree sanity check failed 0xb5 > 0x80
XFS (sda4): Metadata corruption detected at xfs_sb_write_verify+0x5e/0x100 [xfs], xfs_sb block 0x0
XFS (sda4): Unmount and run xfs_repair

The "SB ifree sanity check failed" message was a debugging printk that I
added to the kernel; observe that 0xb5 - 0x80 = 53, which is less than
one inode chunk.

I traced this to the xfs_log_sb calls from the online quota repair code,
which tries to clear the CHKD flags from the superblock to force a
mount-time quotacheck if the repair fails.  On a V5 filesystem,
xfs_log_sb updates the ondisk sb summary counters with the current
contents of the percpu counters.  This is done without quiescing other
writer threads, which means it could be racing with a thread that has
updated icount and is about to update ifree.

If the other write thread had incremented ifree before updating icount,
the repair thread will write icount > ifree into the logged update.  If
the AIL writes the logged superblock back to disk before anyone else
fixes this siutation, this will lead to a write verifier failure, which
causes a filesystem shutdown.

Resolve this problem by updating the quota flags and calling
xfs_sb_to_disk directly, which does not touch the percpu counters.
While we're at it, we can elide the entire update if the selected qflags
aren't set.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/repair.c |   41 ++++++++++++++++++++++++++++++++++-------
 1 file changed, 34 insertions(+), 7 deletions(-)


diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 745d5b8f405a9..3d2c4dbb6909e 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -687,6 +687,39 @@ xrep_find_ag_btree_roots(
 }
 
 #ifdef CONFIG_XFS_QUOTA
+/* Update some quota flags in the superblock. */
+static void
+xrep_update_qflags(
+	struct xfs_scrub	*sc,
+	unsigned int		clear_flags)
+{
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_buf		*bp;
+
+	mutex_lock(&mp->m_quotainfo->qi_quotaofflock);
+	if ((mp->m_qflags & clear_flags) == 0)
+		goto no_update;
+
+	mp->m_qflags &= ~clear_flags;
+	spin_lock(&mp->m_sb_lock);
+	mp->m_sb.sb_qflags &= ~clear_flags;
+	spin_unlock(&mp->m_sb_lock);
+
+	/*
+	 * Update the quota flags in the ondisk superblock without touching
+	 * the summary counters.  We have not quiesced inode chunk allocation,
+	 * so we cannot coordinate with updates to the icount and ifree percpu
+	 * counters.
+	 */
+	bp = xfs_trans_getsb(sc->tp);
+	xfs_sb_to_disk(bp->b_addr, &mp->m_sb);
+	xfs_trans_buf_set_type(sc->tp, bp, XFS_BLFT_SB_BUF);
+	xfs_trans_log_buf(sc->tp, bp, 0, sizeof(struct xfs_dsb) - 1);
+
+no_update:
+	mutex_unlock(&sc->mp->m_quotainfo->qi_quotaofflock);
+}
+
 /* Force a quotacheck the next time we mount. */
 void
 xrep_force_quotacheck(
@@ -699,13 +732,7 @@ xrep_force_quotacheck(
 	if (!(flag & sc->mp->m_qflags))
 		return;
 
-	mutex_lock(&sc->mp->m_quotainfo->qi_quotaofflock);
-	sc->mp->m_qflags &= ~flag;
-	spin_lock(&sc->mp->m_sb_lock);
-	sc->mp->m_sb.sb_qflags &= ~flag;
-	spin_unlock(&sc->mp->m_sb_lock);
-	xfs_log_sb(sc->tp);
-	mutex_unlock(&sc->mp->m_quotainfo->qi_quotaofflock);
+	xrep_update_qflags(sc, flag);
 }
 
 /*

[PATCH 5/5] xfs: repair dquots based on live quotacheck results

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Use the shadow quota counters that live quotacheck creates to reset the
incore dquot counters.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Makefile                  |    1 
 fs/xfs/scrub/quotacheck.c        |    4 -
 fs/xfs/scrub/quotacheck.h        |    3 
 fs/xfs/scrub/quotacheck_repair.c |  261 ++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/repair.c            |   13 +-
 fs/xfs/scrub/repair.h            |    5 +
 fs/xfs/scrub/scrub.c             |    2 
 fs/xfs/scrub/trace.h             |    1 
 8 files changed, 284 insertions(+), 6 deletions(-)
 create mode 100644 fs/xfs/scrub/quotacheck_repair.c


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 12266812fa107..563178216393f 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -205,6 +205,7 @@ xfs-$(CONFIG_XFS_RT)		+= $(addprefix scrub/, \
 
 xfs-$(CONFIG_XFS_QUOTA)		+= $(addprefix scrub/, \
 				   quota_repair.o \
+				   quotacheck_repair.o \
 				   )
 endif
 endif
diff --git a/fs/xfs/scrub/quotacheck.c b/fs/xfs/scrub/quotacheck.c
index d1597838cdac4..a2f728d76fab2 100644
--- a/fs/xfs/scrub/quotacheck.c
+++ b/fs/xfs/scrub/quotacheck.c
@@ -102,7 +102,9 @@ xchk_setup_quotacheck(
  * set the INCOMPLETE flag even when a negative errno is returned.  This care
  * must be taken with certain errno values (i.e. EFSBADCRC, EFSCORRUPTED,
  * ECANCELED) that are absorbed into a scrub state flag update by
- * xchk_*_process_error.
+ * xchk_*_process_error.  Scrub and repair share the same incore data
+ * structures, so the INCOMPLETE flag is critical to prevent a repair based on
+ * insufficient information.
  *
  * Because we are scanning a live filesystem, it's possible that another thread
  * will try to update the quota counters for an inode that we've already
diff --git a/fs/xfs/scrub/quotacheck.h b/fs/xfs/scrub/quotacheck.h
index 3615fec3e409e..4726fc63c8fe4 100644
--- a/fs/xfs/scrub/quotacheck.h
+++ b/fs/xfs/scrub/quotacheck.h
@@ -30,6 +30,9 @@ struct xqcheck_dquot {
 /* Already checked this dquot. */
 #define XQCHECK_DQUOT_COMPARE_SCANNED	(1U << 1)
 
+/* Already repaired this dquot. */
+#define XQCHECK_DQUOT_REPAIR_SCANNED	(1U << 2)
+
 /* Live quotacheck control structure. */
 struct xqcheck {
 	struct xfs_scrub	*sc;
diff --git a/fs/xfs/scrub/quotacheck_repair.c b/fs/xfs/scrub/quotacheck_repair.c
new file mode 100644
index 0000000000000..dd8554c755b5b
--- /dev/null
+++ b/fs/xfs/scrub/quotacheck_repair.c
@@ -0,0 +1,261 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2020-2024 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_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_inode.h"
+#include "xfs_quota.h"
+#include "xfs_qm.h"
+#include "xfs_icache.h"
+#include "xfs_bmap_util.h"
+#include "xfs_iwalk.h"
+#include "xfs_ialloc.h"
+#include "xfs_sb.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/repair.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/iscan.h"
+#include "scrub/quota.h"
+#include "scrub/quotacheck.h"
+#include "scrub/trace.h"
+
+/*
+ * Live Quotacheck Repair
+ * ======================
+ *
+ * Use the live quota counter information that we collected to replace the
+ * counter values in the incore dquots.  A scrub->repair cycle should have left
+ * the live data and hooks active, so this is safe so long as we make sure the
+ * dquot is locked.
+ */
+
+/* Commit new counters to a dquot. */
+static int
+xqcheck_commit_dquot(
+	struct xqcheck		*xqc,
+	xfs_dqtype_t		dqtype,
+	struct xfs_dquot	*dq)
+{
+	struct xqcheck_dquot	xcdq;
+	struct xfarray		*counts = xqcheck_counters_for(xqc, dqtype);
+	int64_t			delta;
+	bool			dirty = false;
+	int			error = 0;
+
+	/* Unlock the dquot just long enough to allocate a transaction. */
+	xfs_dqunlock(dq);
+	error = xchk_trans_alloc(xqc->sc, 0);
+	xfs_dqlock(dq);
+	if (error)
+		return error;
+
+	xfs_trans_dqjoin(xqc->sc->tp, dq);
+
+	if (xchk_iscan_aborted(&xqc->iscan)) {
+		error = -ECANCELED;
+		goto out_cancel;
+	}
+
+	mutex_lock(&xqc->lock);
+	error = xfarray_load_sparse(counts, dq->q_id, &xcdq);
+	if (error)
+		goto out_unlock;
+
+	/* Adjust counters as needed. */
+	delta = (int64_t)xcdq.icount - dq->q_ino.count;
+	if (delta) {
+		dq->q_ino.reserved += delta;
+		dq->q_ino.count += delta;
+		dirty = true;
+	}
+
+	delta = (int64_t)xcdq.bcount - dq->q_blk.count;
+	if (delta) {
+		dq->q_blk.reserved += delta;
+		dq->q_blk.count += delta;
+		dirty = true;
+	}
+
+	delta = (int64_t)xcdq.rtbcount - dq->q_rtb.count;
+	if (delta) {
+		dq->q_rtb.reserved += delta;
+		dq->q_rtb.count += delta;
+		dirty = true;
+	}
+
+	xcdq.flags |= (XQCHECK_DQUOT_REPAIR_SCANNED | XQCHECK_DQUOT_WRITTEN);
+	error = xfarray_store(counts, dq->q_id, &xcdq);
+	if (error == -EFBIG) {
+		/*
+		 * EFBIG means we tried to store data at too high a byte offset
+		 * in the sparse array.  IOWs, we cannot complete the repair
+		 * and must cancel the whole operation.  This should never
+		 * happen, but we need to catch it anyway.
+		 */
+		error = -ECANCELED;
+	}
+	mutex_unlock(&xqc->lock);
+	if (error || !dirty)
+		goto out_cancel;
+
+	trace_xrep_quotacheck_dquot(xqc->sc->mp, dq->q_type, dq->q_id);
+
+	/* Commit the dirty dquot to disk. */
+	dq->q_flags |= XFS_DQFLAG_DIRTY;
+	if (dq->q_id)
+		xfs_qm_adjust_dqtimers(dq);
+	xfs_trans_log_dquot(xqc->sc->tp, dq);
+
+	/*
+	 * Transaction commit unlocks the dquot, so we must re-lock it so that
+	 * the caller can put the reference (which apparently requires a locked
+	 * dquot).
+	 */
+	error = xrep_trans_commit(xqc->sc);
+	xfs_dqlock(dq);
+	return error;
+
+out_unlock:
+	mutex_unlock(&xqc->lock);
+out_cancel:
+	xchk_trans_cancel(xqc->sc);
+
+	/* Re-lock the dquot so the caller can put the reference. */
+	xfs_dqlock(dq);
+	return error;
+}
+
+/* Commit new quota counters for a particular quota type. */
+STATIC int
+xqcheck_commit_dqtype(
+	struct xqcheck		*xqc,
+	unsigned int		dqtype)
+{
+	struct xchk_dqiter	cursor = { };
+	struct xqcheck_dquot	xcdq;
+	struct xfs_scrub	*sc = xqc->sc;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfarray		*counts = xqcheck_counters_for(xqc, dqtype);
+	struct xfs_dquot	*dq;
+	xfarray_idx_t		cur = XFARRAY_CURSOR_INIT;
+	int			error;
+
+	/*
+	 * Update the counters of every dquot that the quota file knows about.
+	 */
+	xchk_dqiter_init(&cursor, sc, dqtype);
+	while ((error = xchk_dquot_iter(&cursor, &dq)) == 1) {
+		error = xqcheck_commit_dquot(xqc, dqtype, dq);
+		xfs_qm_dqput(dq);
+		if (error)
+			break;
+	}
+	if (error)
+		return error;
+
+	/*
+	 * Make a second pass to deal with the dquots that we know about but
+	 * the quota file previously did not know about.
+	 */
+	mutex_lock(&xqc->lock);
+	while ((error = xfarray_iter(counts, &cur, &xcdq)) == 1) {
+		xfs_dqid_t	id = cur - 1;
+
+		if (xcdq.flags & XQCHECK_DQUOT_REPAIR_SCANNED)
+			continue;
+
+		mutex_unlock(&xqc->lock);
+
+		/*
+		 * Grab the dquot, allowing for dquot block allocation in a
+		 * separate transaction.  We committed the scrub transaction
+		 * in a previous step, so we will not be creating nested
+		 * transactions here.
+		 */
+		error = xfs_qm_dqget(mp, id, dqtype, true, &dq);
+		if (error)
+			return error;
+
+		error = xqcheck_commit_dquot(xqc, dqtype, dq);
+		xfs_qm_dqput(dq);
+		if (error)
+			return error;
+
+		mutex_lock(&xqc->lock);
+	}
+	mutex_unlock(&xqc->lock);
+
+	return error;
+}
+
+/* Figure out quota CHKD flags for the running quota types. */
+static inline unsigned int
+xqcheck_chkd_flags(
+	struct xfs_mount	*mp)
+{
+	unsigned int		ret = 0;
+
+	if (XFS_IS_UQUOTA_ON(mp))
+		ret |= XFS_UQUOTA_CHKD;
+	if (XFS_IS_GQUOTA_ON(mp))
+		ret |= XFS_GQUOTA_CHKD;
+	if (XFS_IS_PQUOTA_ON(mp))
+		ret |= XFS_PQUOTA_CHKD;
+	return ret;
+}
+
+/* Commit the new dquot counters. */
+int
+xrep_quotacheck(
+	struct xfs_scrub	*sc)
+{
+	struct xqcheck		*xqc = sc->buf;
+	unsigned int		qflags = xqcheck_chkd_flags(sc->mp);
+	int			error;
+
+	/*
+	 * Clear the CHKD flag for the running quota types and commit the scrub
+	 * transaction so that we can allocate new quota block mappings if we
+	 * have to.  If we crash after this point, the sb still has the CHKD
+	 * flags cleared, so mount quotacheck will fix all of this up.
+	 */
+	xrep_update_qflags(sc, qflags, 0);
+	error = xrep_trans_commit(sc);
+	if (error)
+		return error;
+
+	/* Commit the new counters to the dquots. */
+	if (xqc->ucounts) {
+		error = xqcheck_commit_dqtype(xqc, XFS_DQTYPE_USER);
+		if (error)
+			return error;
+	}
+	if (xqc->gcounts) {
+		error = xqcheck_commit_dqtype(xqc, XFS_DQTYPE_GROUP);
+		if (error)
+			return error;
+	}
+	if (xqc->pcounts) {
+		error = xqcheck_commit_dqtype(xqc, XFS_DQTYPE_PROJ);
+		if (error)
+			return error;
+	}
+
+	/* Set the CHKD flags now that we've fixed quota counts. */
+	error = xchk_trans_alloc(sc, 0);
+	if (error)
+		return error;
+
+	xrep_update_qflags(sc, 0, qflags);
+	return xrep_trans_commit(sc);
+}
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 3d2c4dbb6909e..7141b17789028 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -688,21 +688,26 @@ xrep_find_ag_btree_roots(
 
 #ifdef CONFIG_XFS_QUOTA
 /* Update some quota flags in the superblock. */
-static void
+void
 xrep_update_qflags(
 	struct xfs_scrub	*sc,
-	unsigned int		clear_flags)
+	unsigned int		clear_flags,
+	unsigned int		set_flags)
 {
 	struct xfs_mount	*mp = sc->mp;
 	struct xfs_buf		*bp;
 
 	mutex_lock(&mp->m_quotainfo->qi_quotaofflock);
-	if ((mp->m_qflags & clear_flags) == 0)
+	if ((mp->m_qflags & clear_flags) == 0 &&
+	    (mp->m_qflags & set_flags) == set_flags)
 		goto no_update;
 
 	mp->m_qflags &= ~clear_flags;
+	mp->m_qflags |= set_flags;
+
 	spin_lock(&mp->m_sb_lock);
 	mp->m_sb.sb_qflags &= ~clear_flags;
+	mp->m_sb.sb_qflags |= set_flags;
 	spin_unlock(&mp->m_sb_lock);
 
 	/*
@@ -732,7 +737,7 @@ xrep_force_quotacheck(
 	if (!(flag & sc->mp->m_qflags))
 		return;
 
-	xrep_update_qflags(sc, flag);
+	xrep_update_qflags(sc, flag, 0);
 }
 
 /*
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 17114327e6fa7..fdfa066999218 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -72,6 +72,8 @@ int xrep_find_ag_btree_roots(struct xfs_scrub *sc, struct xfs_buf *agf_bp,
 		struct xrep_find_ag_btree *btree_info, struct xfs_buf *agfl_bp);
 
 #ifdef CONFIG_XFS_QUOTA
+void xrep_update_qflags(struct xfs_scrub *sc, unsigned int clear_flags,
+		unsigned int set_flags);
 void xrep_force_quotacheck(struct xfs_scrub *sc, xfs_dqtype_t type);
 int xrep_ino_dqattach(struct xfs_scrub *sc);
 #else
@@ -123,8 +125,10 @@ int xrep_rtbitmap(struct xfs_scrub *sc);
 
 #ifdef CONFIG_XFS_QUOTA
 int xrep_quota(struct xfs_scrub *sc);
+int xrep_quotacheck(struct xfs_scrub *sc);
 #else
 # define xrep_quota			xrep_notsupported
+# define xrep_quotacheck		xrep_notsupported
 #endif /* CONFIG_XFS_QUOTA */
 
 int xrep_reinit_pagf(struct xfs_scrub *sc);
@@ -191,6 +195,7 @@ xrep_setup_nothing(
 #define xrep_bmap_cow			xrep_notsupported
 #define xrep_rtbitmap			xrep_notsupported
 #define xrep_quota			xrep_notsupported
+#define xrep_quotacheck			xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 71a9eb48e1de7..9112c0985c62b 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -367,7 +367,7 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.type	= ST_FS,
 		.setup	= xchk_setup_quotacheck,
 		.scrub	= xchk_quotacheck,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_quotacheck,
 	},
 };
 
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index afe2c92233f1b..955af3de92813 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -1977,6 +1977,7 @@ DEFINE_EVENT(xrep_dquot_class, name, \
 DEFINE_XREP_DQUOT_EVENT(xrep_dquot_item);
 DEFINE_XREP_DQUOT_EVENT(xrep_disk_dquot);
 DEFINE_XREP_DQUOT_EVENT(xrep_dquot_item_fill_bmap_hole);
+DEFINE_XREP_DQUOT_EVENT(xrep_quotacheck_dquot);
 #endif /* CONFIG_XFS_QUOTA */
 
 #endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */

[PATCH 1/4] xfs: report health of inode link counts

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Report on the health of the inode link counts.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_fs.h     |    1 +
 fs/xfs/libxfs/xfs_health.h |    4 +++-
 fs/xfs/xfs_health.c        |    1 +
 3 files changed, 5 insertions(+), 1 deletion(-)


diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 07acbed9235c5..f10d0aa0e337f 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -196,6 +196,7 @@ struct xfs_fsop_geom {
 #define XFS_FSOP_GEOM_SICK_RT_BITMAP	(1 << 4)  /* realtime bitmap */
 #define XFS_FSOP_GEOM_SICK_RT_SUMMARY	(1 << 5)  /* realtime summary */
 #define XFS_FSOP_GEOM_SICK_QUOTACHECK	(1 << 6)  /* quota counts */
+#define XFS_FSOP_GEOM_SICK_NLINKS	(1 << 7)  /* inode link counts */
 
 /* Output for XFS_FS_COUNTS */
 typedef struct xfs_fsop_counts {
diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index 5626e53b3f0fe..2bfe2dc404a19 100644
--- a/fs/xfs/libxfs/xfs_health.h
+++ b/fs/xfs/libxfs/xfs_health.h
@@ -42,6 +42,7 @@ struct xfs_fsop_geom;
 #define XFS_SICK_FS_GQUOTA	(1 << 2)  /* group quota */
 #define XFS_SICK_FS_PQUOTA	(1 << 3)  /* project quota */
 #define XFS_SICK_FS_QUOTACHECK	(1 << 4)  /* quota counts */
+#define XFS_SICK_FS_NLINKS	(1 << 5)  /* inode link counts */
 
 /* Observable health issues for realtime volume metadata. */
 #define XFS_SICK_RT_BITMAP	(1 << 0)  /* realtime bitmap */
@@ -79,7 +80,8 @@ struct xfs_fsop_geom;
 				 XFS_SICK_FS_UQUOTA | \
 				 XFS_SICK_FS_GQUOTA | \
 				 XFS_SICK_FS_PQUOTA | \
-				 XFS_SICK_FS_QUOTACHECK)
+				 XFS_SICK_FS_QUOTACHECK | \
+				 XFS_SICK_FS_NLINKS)
 
 #define XFS_SICK_RT_PRIMARY	(XFS_SICK_RT_BITMAP | \
 				 XFS_SICK_RT_SUMMARY)
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index ef07af9f753d3..111c27a6b1079 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -281,6 +281,7 @@ static const struct ioctl_sick_map fs_map[] = {
 	{ XFS_SICK_FS_GQUOTA,	XFS_FSOP_GEOM_SICK_GQUOTA },
 	{ XFS_SICK_FS_PQUOTA,	XFS_FSOP_GEOM_SICK_PQUOTA },
 	{ XFS_SICK_FS_QUOTACHECK, XFS_FSOP_GEOM_SICK_QUOTACHECK },
+	{ XFS_SICK_FS_NLINKS,	XFS_FSOP_GEOM_SICK_NLINKS },
 	{ 0, 0 },
 };
 

[PATCH 2/4] xfs: teach scrub to check file nlinks

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create the necessary scrub code to walk the filesystem's directory tree
so that we can compute file link counts.  Similar to quotacheck, we
create an incore shadow array of link count information and then we walk
the filesystem a second time to compare the link counts.  We need live
updates to keep the information up to date during the lengthy scan, so
this scrubber remains disabled until the next patch.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Makefile        |    1 
 fs/xfs/libxfs/xfs_fs.h |    3 
 fs/xfs/scrub/common.h  |    1 
 fs/xfs/scrub/health.c  |    1 
 fs/xfs/scrub/nlinks.c  |  839 ++++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/nlinks.h  |   93 +++++
 fs/xfs/scrub/scrub.c   |    6 
 fs/xfs/scrub/scrub.h   |    1 
 fs/xfs/scrub/stats.c   |    1 
 fs/xfs/scrub/trace.c   |    2 
 fs/xfs/scrub/trace.h   |  147 ++++++++
 11 files changed, 1093 insertions(+), 2 deletions(-)
 create mode 100644 fs/xfs/scrub/nlinks.c
 create mode 100644 fs/xfs/scrub/nlinks.h


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 563178216393f..cabf1dd341adc 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -161,6 +161,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   ialloc.o \
 				   inode.o \
 				   iscan.o \
+				   nlinks.o \
 				   parent.o \
 				   readdir.o \
 				   refcount.o \
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index f10d0aa0e337f..515cd27d3b3a8 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -712,9 +712,10 @@ struct xfs_scrub_metadata {
 #define XFS_SCRUB_TYPE_PQUOTA	23	/* project quotas */
 #define XFS_SCRUB_TYPE_FSCOUNTERS 24	/* fs summary counters */
 #define XFS_SCRUB_TYPE_QUOTACHECK 25	/* quota counters */
+#define XFS_SCRUB_TYPE_NLINKS	26	/* inode link counts */
 
 /* Number of scrub subcommands. */
-#define XFS_SCRUB_TYPE_NR	26
+#define XFS_SCRUB_TYPE_NR	27
 
 /* i: Repair this metadata. */
 #define XFS_SCRUB_IFLAG_REPAIR		(1u << 0)
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index 79516d1f4983a..6d7364fe13b00 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -129,6 +129,7 @@ xchk_setup_quotacheck(struct xfs_scrub *sc)
 }
 #endif
 int xchk_setup_fscounters(struct xfs_scrub *sc);
+int xchk_setup_nlinks(struct xfs_scrub *sc);
 
 void xchk_ag_free(struct xfs_scrub *sc, struct xchk_ag *sa);
 int xchk_ag_init(struct xfs_scrub *sc, xfs_agnumber_t agno,
diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c
index 55313a26ae9a7..42be435227794 100644
--- a/fs/xfs/scrub/health.c
+++ b/fs/xfs/scrub/health.c
@@ -108,6 +108,7 @@ static const struct xchk_health_map type_to_health_flag[XFS_SCRUB_TYPE_NR] = {
 	[XFS_SCRUB_TYPE_PQUOTA]		= { XHG_FS,  XFS_SICK_FS_PQUOTA },
 	[XFS_SCRUB_TYPE_FSCOUNTERS]	= { XHG_FS,  XFS_SICK_FS_COUNTERS },
 	[XFS_SCRUB_TYPE_QUOTACHECK]	= { XHG_FS,  XFS_SICK_FS_QUOTACHECK },
+	[XFS_SCRUB_TYPE_NLINKS]		= { XHG_FS,  XFS_SICK_FS_NLINKS },
 };
 
 /* Return the health status mask for this scrub type. */
diff --git a/fs/xfs/scrub/nlinks.c b/fs/xfs/scrub/nlinks.c
new file mode 100644
index 0000000000000..c899a50a83daf
--- /dev/null
+++ b/fs/xfs/scrub/nlinks.c
@@ -0,0 +1,839 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2021-2024 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_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_iwalk.h"
+#include "xfs_ialloc.h"
+#include "xfs_dir2.h"
+#include "xfs_dir2_priv.h"
+#include "xfs_ag.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/repair.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/iscan.h"
+#include "scrub/nlinks.h"
+#include "scrub/trace.h"
+#include "scrub/readdir.h"
+
+/*
+ * Live Inode Link Count Checking
+ * ==============================
+ *
+ * Inode link counts are "summary" metadata, in the sense that they are
+ * computed as the number of directory entries referencing each file on the
+ * filesystem.  Therefore, we compute the correct link counts by creating a
+ * shadow link count structure and walking every inode.
+ */
+
+/* Set us up to scrub inode link counts. */
+int
+xchk_setup_nlinks(
+	struct xfs_scrub	*sc)
+{
+	/* Not ready for general consumption yet. */
+	return -EOPNOTSUPP;
+
+	sc->buf = kzalloc(sizeof(struct xchk_nlink_ctrs), XCHK_GFP_FLAGS);
+	if (!sc->buf)
+		return -ENOMEM;
+
+	return xchk_setup_fs(sc);
+}
+
+/*
+ * Part 1: Collecting file link counts.  For each file, we create a shadow link
+ * counting structure, then walk the entire directory tree, incrementing parent
+ * and child link counts for each directory entry seen.
+ *
+ * To avoid false corruption reports in part 2, any failure in this part must
+ * set the INCOMPLETE flag even when a negative errno is returned.  This care
+ * must be taken with certain errno values (i.e. EFSBADCRC, EFSCORRUPTED,
+ * ECANCELED) that are absorbed into a scrub state flag update by
+ * xchk_*_process_error.
+ */
+
+/*
+ * Add a delta to an nlink counter, clamping the value to U32_MAX.  Because
+ * XFS_MAXLINK < U32_MAX, the checking code will produce the correct results
+ * even if we lose some precision.
+ */
+static inline void
+careful_add(
+	xfs_nlink_t	*nlinkp,
+	int		delta)
+{
+	uint64_t	new_value = (uint64_t)(*nlinkp) + delta;
+
+	BUILD_BUG_ON(XFS_MAXLINK > U32_MAX);
+	*nlinkp = min_t(uint64_t, new_value, U32_MAX);
+}
+
+/* Update incore link count information.  Caller must hold the nlinks lock. */
+STATIC int
+xchk_nlinks_update_incore(
+	struct xchk_nlink_ctrs	*xnc,
+	xfs_ino_t		ino,
+	int			parents_delta,
+	int			backrefs_delta,
+	int			children_delta)
+{
+	struct xchk_nlink	nl;
+	int			error;
+
+	if (!xnc->nlinks)
+		return 0;
+
+	error = xfarray_load_sparse(xnc->nlinks, ino, &nl);
+	if (error)
+		return error;
+
+	trace_xchk_nlinks_update_incore(xnc->sc->mp, ino, &nl, parents_delta,
+			backrefs_delta, children_delta);
+
+	careful_add(&nl.parents, parents_delta);
+	careful_add(&nl.backrefs, backrefs_delta);
+	careful_add(&nl.children, children_delta);
+
+	nl.flags |= XCHK_NLINK_WRITTEN;
+	error = xfarray_store(xnc->nlinks, ino, &nl);
+	if (error == -EFBIG) {
+		/*
+		 * EFBIG means we tried to store data at too high a byte offset
+		 * in the sparse array.  IOWs, we cannot complete the check and
+		 * must notify userspace that the check was incomplete.
+		 */
+		error = -ECANCELED;
+	}
+	return error;
+}
+
+/* Bump the observed link count for the inode referenced by this entry. */
+STATIC int
+xchk_nlinks_collect_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 xchk_nlink_ctrs	*xnc = priv;
+	bool			dot = false, dotdot = false;
+	int			error;
+
+	/* Does this name make sense? */
+	if (name->len == 0 || !xfs_dir2_namecheck(name->name, name->len)) {
+		error = -ECANCELED;
+		goto out_abort;
+	}
+
+	if (name->len == 1 && name->name[0] == '.')
+		dot = true;
+	else if (name->len == 2 && name->name[0] == '.' &&
+				   name->name[1] == '.')
+		dotdot = true;
+
+	/* Don't accept a '.' entry that points somewhere else. */
+	if (dot && ino != dp->i_ino) {
+		error = -ECANCELED;
+		goto out_abort;
+	}
+
+	/* Don't accept an invalid inode number. */
+	if (!xfs_verify_dir_ino(sc->mp, ino)) {
+		error = -ECANCELED;
+		goto out_abort;
+	}
+
+	/* Update the shadow link counts if we haven't already failed. */
+
+	if (xchk_iscan_aborted(&xnc->collect_iscan)) {
+		error = -ECANCELED;
+		goto out_incomplete;
+	}
+
+	trace_xchk_nlinks_collect_dirent(sc->mp, dp, ino, name);
+
+	mutex_lock(&xnc->lock);
+
+	/*
+	 * If this is a dotdot entry, it is a back link from dp to ino.  How
+	 * we handle this depends on whether or not dp is the root directory.
+	 *
+	 * The root directory is its own parent, so we pretend the dotdot entry
+	 * establishes the "parent" of the root directory.  Increment the
+	 * number of parents of the root directory.
+	 *
+	 * Otherwise, increment the number of backrefs pointing back to ino.
+	 */
+	if (dotdot) {
+		if (dp == sc->mp->m_rootip)
+			error = xchk_nlinks_update_incore(xnc, ino, 1, 0, 0);
+		else
+			error = xchk_nlinks_update_incore(xnc, ino, 0, 1, 0);
+		if (error)
+			goto out_unlock;
+	}
+
+	/*
+	 * If this dirent is a forward link from dp to ino, increment the
+	 * number of parents linking into ino.
+	 */
+	if (!dot && !dotdot) {
+		error = xchk_nlinks_update_incore(xnc, ino, 1, 0, 0);
+		if (error)
+			goto out_unlock;
+	}
+
+	/*
+	 * If this dirent is a forward link to a subdirectory, increment the
+	 * number of child links of dp.
+	 */
+	if (!dot && !dotdot && name->type == XFS_DIR3_FT_DIR) {
+		error = xchk_nlinks_update_incore(xnc, dp->i_ino, 0, 0, 1);
+		if (error)
+			goto out_unlock;
+	}
+
+	mutex_unlock(&xnc->lock);
+	return 0;
+
+out_unlock:
+	mutex_unlock(&xnc->lock);
+out_abort:
+	xchk_iscan_abort(&xnc->collect_iscan);
+out_incomplete:
+	xchk_set_incomplete(sc);
+	return error;
+}
+
+/* Walk a directory to bump the observed link counts of the children. */
+STATIC int
+xchk_nlinks_collect_dir(
+	struct xchk_nlink_ctrs	*xnc,
+	struct xfs_inode	*dp)
+{
+	struct xfs_scrub	*sc = xnc->sc;
+	unsigned int		lock_mode;
+	int			error = 0;
+
+	/* Prevent anyone from changing this directory while we walk it. */
+	xfs_ilock(dp, XFS_IOLOCK_SHARED);
+	lock_mode = xfs_ilock_data_map_shared(dp);
+
+	/*
+	 * The dotdot entry of an unlinked directory still points to the last
+	 * parent, but the parent no longer links to this directory.  Skip the
+	 * directory to avoid overcounting.
+	 */
+	if (VFS_I(dp)->i_nlink == 0)
+		goto out_unlock;
+
+	/*
+	 * We cannot count file links if the directory looks as though it has
+	 * been zapped by the inode record repair code.
+	 */
+	if (xchk_dir_looks_zapped(dp)) {
+		error = -EBUSY;
+		goto out_abort;
+	}
+
+	error = xchk_dir_walk(sc, dp, xchk_nlinks_collect_dirent, xnc);
+	if (error == -ECANCELED) {
+		error = 0;
+		goto out_unlock;
+	}
+	if (error)
+		goto out_abort;
+
+	xchk_iscan_mark_visited(&xnc->collect_iscan, dp);
+	goto out_unlock;
+
+out_abort:
+	xchk_set_incomplete(sc);
+	xchk_iscan_abort(&xnc->collect_iscan);
+out_unlock:
+	xfs_iunlock(dp, lock_mode);
+	xfs_iunlock(dp, XFS_IOLOCK_SHARED);
+	return error;
+}
+
+/* If this looks like a valid pointer, count it. */
+static inline int
+xchk_nlinks_collect_metafile(
+	struct xchk_nlink_ctrs	*xnc,
+	xfs_ino_t		ino)
+{
+	if (!xfs_verify_ino(xnc->sc->mp, ino))
+		return 0;
+
+	trace_xchk_nlinks_collect_metafile(xnc->sc->mp, ino);
+	return xchk_nlinks_update_incore(xnc, ino, 1, 0, 0);
+}
+
+/* Bump the link counts of metadata files rooted in the superblock. */
+STATIC int
+xchk_nlinks_collect_metafiles(
+	struct xchk_nlink_ctrs	*xnc)
+{
+	struct xfs_mount	*mp = xnc->sc->mp;
+	int			error = -ECANCELED;
+
+
+	if (xchk_iscan_aborted(&xnc->collect_iscan))
+		goto out_incomplete;
+
+	mutex_lock(&xnc->lock);
+	error = xchk_nlinks_collect_metafile(xnc, mp->m_sb.sb_rbmino);
+	if (error)
+		goto out_abort;
+
+	error = xchk_nlinks_collect_metafile(xnc, mp->m_sb.sb_rsumino);
+	if (error)
+		goto out_abort;
+
+	error = xchk_nlinks_collect_metafile(xnc, mp->m_sb.sb_uquotino);
+	if (error)
+		goto out_abort;
+
+	error = xchk_nlinks_collect_metafile(xnc, mp->m_sb.sb_gquotino);
+	if (error)
+		goto out_abort;
+
+	error = xchk_nlinks_collect_metafile(xnc, mp->m_sb.sb_pquotino);
+	if (error)
+		goto out_abort;
+	mutex_unlock(&xnc->lock);
+
+	return 0;
+
+out_abort:
+	mutex_unlock(&xnc->lock);
+	xchk_iscan_abort(&xnc->collect_iscan);
+out_incomplete:
+	xchk_set_incomplete(xnc->sc);
+	return error;
+}
+
+/* Advance the collection scan cursor for this non-directory file. */
+static inline int
+xchk_nlinks_collect_file(
+	struct xchk_nlink_ctrs	*xnc,
+	struct xfs_inode	*ip)
+{
+	xfs_ilock(ip, XFS_IOLOCK_SHARED);
+	xchk_iscan_mark_visited(&xnc->collect_iscan, ip);
+	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
+	return 0;
+}
+
+/* Walk all directories and count inode links. */
+STATIC int
+xchk_nlinks_collect(
+	struct xchk_nlink_ctrs	*xnc)
+{
+	struct xfs_scrub	*sc = xnc->sc;
+	struct xfs_inode	*ip;
+	int			error;
+
+	/* Count the rt and quota files that are rooted in the superblock. */
+	error = xchk_nlinks_collect_metafiles(xnc);
+	if (error)
+		return error;
+
+	/*
+	 * Set up for a potentially lengthy filesystem scan by reducing our
+	 * transaction resource usage for the duration.  Specifically:
+	 *
+	 * Cancel the transaction to release the log grant space while we scan
+	 * the filesystem.
+	 *
+	 * Create a new empty transaction to eliminate the possibility of the
+	 * inode scan deadlocking on cyclical metadata.
+	 *
+	 * We pass the empty transaction to the file scanning function to avoid
+	 * repeatedly cycling empty transactions.  This can be done even though
+	 * we take the IOLOCK to quiesce the file because empty transactions
+	 * do not take sb_internal.
+	 */
+	xchk_trans_cancel(sc);
+	error = xchk_trans_alloc_empty(sc);
+	if (error)
+		return error;
+
+	while ((error = xchk_iscan_iter(&xnc->collect_iscan, &ip)) == 1) {
+		if (S_ISDIR(VFS_I(ip)->i_mode))
+			error = xchk_nlinks_collect_dir(xnc, ip);
+		else
+			error = xchk_nlinks_collect_file(xnc, ip);
+		xchk_irele(sc, ip);
+		if (error)
+			break;
+
+		if (xchk_should_terminate(sc, &error))
+			break;
+	}
+	xchk_iscan_iter_finish(&xnc->collect_iscan);
+	if (error) {
+		xchk_set_incomplete(sc);
+		/*
+		 * If we couldn't grab an inode that was busy with a state
+		 * change, change the error code so that we exit to userspace
+		 * as quickly as possible.
+		 */
+		if (error == -EBUSY)
+			return -ECANCELED;
+		return error;
+	}
+
+	/*
+	 * Switch out for a real transaction in preparation for building a new
+	 * tree.
+	 */
+	xchk_trans_cancel(sc);
+	return xchk_setup_fs(sc);
+}
+
+/*
+ * Part 2: Comparing file link counters.  Walk each inode and compare the link
+ * counts against our shadow information; and then walk each shadow link count
+ * structure (that wasn't covered in the first part), comparing it against the
+ * file.
+ */
+
+/* Read the observed link count for comparison with the actual inode. */
+STATIC int
+xchk_nlinks_comparison_read(
+	struct xchk_nlink_ctrs	*xnc,
+	xfs_ino_t		ino,
+	struct xchk_nlink	*obs)
+{
+	struct xchk_nlink	nl;
+	int			error;
+
+	error = xfarray_load_sparse(xnc->nlinks, ino, &nl);
+	if (error)
+		return error;
+
+	nl.flags |= (XCHK_NLINK_COMPARE_SCANNED | XCHK_NLINK_WRITTEN);
+
+	error = xfarray_store(xnc->nlinks, ino, &nl);
+	if (error == -EFBIG) {
+		/*
+		 * EFBIG means we tried to store data at too high a byte offset
+		 * in the sparse array.  IOWs, we cannot complete the check and
+		 * must notify userspace that the check was incomplete.  This
+		 * shouldn't really happen outside of the collection phase.
+		 */
+		xchk_set_incomplete(xnc->sc);
+		return -ECANCELED;
+	}
+	if (error)
+		return error;
+
+	/* Copy the counters, but do not expose the internal state. */
+	obs->parents = nl.parents;
+	obs->backrefs = nl.backrefs;
+	obs->children = nl.children;
+	obs->flags = 0;
+	return 0;
+}
+
+/* Check our link count against an inode. */
+STATIC int
+xchk_nlinks_compare_inode(
+	struct xchk_nlink_ctrs	*xnc,
+	struct xfs_inode	*ip)
+{
+	struct xchk_nlink	obs;
+	struct xfs_scrub	*sc = xnc->sc;
+	uint64_t		total_links;
+	unsigned int		actual_nlink;
+	int			error;
+
+	xfs_ilock(ip, XFS_ILOCK_SHARED);
+	mutex_lock(&xnc->lock);
+
+	if (xchk_iscan_aborted(&xnc->collect_iscan)) {
+		xchk_set_incomplete(xnc->sc);
+		error = -ECANCELED;
+		goto out_scanlock;
+	}
+
+	error = xchk_nlinks_comparison_read(xnc, ip->i_ino, &obs);
+	if (error)
+		goto out_scanlock;
+
+	/*
+	 * If we don't have ftype to get an accurate count of the subdirectory
+	 * entries in this directory, take advantage of the fact that on a
+	 * consistent ftype=0 filesystem, the number of subdirectory
+	 * backreferences (dotdot entries) pointing towards this directory
+	 * should be equal to the number of subdirectory entries in the
+	 * directory.
+	 */
+	if (!xfs_has_ftype(sc->mp) && S_ISDIR(VFS_I(ip)->i_mode))
+		obs.children = obs.backrefs;
+
+	total_links = xchk_nlink_total(ip, &obs);
+	actual_nlink = VFS_I(ip)->i_nlink;
+
+	trace_xchk_nlinks_compare_inode(sc->mp, ip, &obs);
+
+	/*
+	 * If we found so many parents that we'd overflow i_nlink, we must flag
+	 * this as a corruption.  The VFS won't let users increase the link
+	 * count, but it will let them decrease it.
+	 */
+	if (total_links > XFS_MAXLINK) {
+		xchk_ino_set_corrupt(sc, ip->i_ino);
+		goto out_corrupt;
+	}
+
+	/* Link counts should match. */
+	if (total_links != actual_nlink) {
+		xchk_ino_set_corrupt(sc, ip->i_ino);
+		goto out_corrupt;
+	}
+
+	if (S_ISDIR(VFS_I(ip)->i_mode) && actual_nlink > 0) {
+		/*
+		 * The collection phase ignores directories with zero link
+		 * count, so we ignore them here too.
+		 *
+		 * The number of subdirectory backreferences (dotdot entries)
+		 * pointing towards this directory should be equal to the
+		 * number of subdirectory entries in the directory.
+		 */
+		if (obs.children != obs.backrefs)
+			xchk_ino_xref_set_corrupt(sc, ip->i_ino);
+	} else {
+		/*
+		 * Non-directories and unlinked directories should not have
+		 * back references.
+		 */
+		if (obs.backrefs != 0) {
+			xchk_ino_set_corrupt(sc, ip->i_ino);
+			goto out_corrupt;
+		}
+
+		/*
+		 * Non-directories and unlinked directories should not have
+		 * children.
+		 */
+		if (obs.children != 0) {
+			xchk_ino_set_corrupt(sc, ip->i_ino);
+			goto out_corrupt;
+		}
+	}
+
+	if (ip == sc->mp->m_rootip) {
+		/*
+		 * For the root of a directory tree, both the '.' and '..'
+		 * entries should point to the root directory.  The dotdot
+		 * entry is counted as a parent of the root /and/ a backref of
+		 * the root directory.
+		 */
+		if (obs.parents != 1) {
+			xchk_ino_set_corrupt(sc, ip->i_ino);
+			goto out_corrupt;
+		}
+	} else if (actual_nlink > 0) {
+		/*
+		 * Linked files that are not the root directory should have at
+		 * least one parent.
+		 */
+		if (obs.parents == 0) {
+			xchk_ino_set_corrupt(sc, ip->i_ino);
+			goto out_corrupt;
+		}
+	}
+
+out_corrupt:
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		error = -ECANCELED;
+out_scanlock:
+	mutex_unlock(&xnc->lock);
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+	return error;
+}
+
+/*
+ * Check our link count against an inode that wasn't checked previously.  This
+ * is intended to catch directories with dangling links, though we could be
+ * racing with inode allocation in other threads.
+ */
+STATIC int
+xchk_nlinks_compare_inum(
+	struct xchk_nlink_ctrs	*xnc,
+	xfs_ino_t		ino)
+{
+	struct xchk_nlink	obs;
+	struct xfs_mount	*mp = xnc->sc->mp;
+	struct xfs_trans	*tp = xnc->sc->tp;
+	struct xfs_buf		*agi_bp;
+	struct xfs_inode	*ip;
+	int			error;
+
+	/*
+	 * The first iget failed, so try again with the variant that returns
+	 * either an incore inode or the AGI buffer.  If the function returns
+	 * EINVAL/ENOENT, it should have passed us the AGI buffer so that we
+	 * can guarantee that the inode won't be allocated while we check for
+	 * a zero link count in the observed link count data.
+	 */
+	error = xchk_iget_agi(xnc->sc, ino, &agi_bp, &ip);
+	if (!error) {
+		/* Actually got an inode, so use the inode compare. */
+		error = xchk_nlinks_compare_inode(xnc, ip);
+		xchk_irele(xnc->sc, ip);
+		return error;
+	}
+	if (error == -ENOENT || error == -EINVAL) {
+		/* No inode was found.  Check for zero link count below. */
+		error = 0;
+	}
+	if (error)
+		goto out_agi;
+
+	/* Ensure that we have protected against inode allocation/freeing. */
+	if (agi_bp == NULL) {
+		ASSERT(agi_bp != NULL);
+		xchk_set_incomplete(xnc->sc);
+		return -ECANCELED;
+	}
+
+	if (xchk_iscan_aborted(&xnc->collect_iscan)) {
+		xchk_set_incomplete(xnc->sc);
+		error = -ECANCELED;
+		goto out_agi;
+	}
+
+	mutex_lock(&xnc->lock);
+	error = xchk_nlinks_comparison_read(xnc, ino, &obs);
+	if (error)
+		goto out_scanlock;
+
+	trace_xchk_nlinks_check_zero(mp, ino, &obs);
+
+	/*
+	 * If we can't grab the inode, the link count had better be zero.  We
+	 * still hold the AGI to prevent inode allocation/freeing.
+	 */
+	if (xchk_nlink_total(NULL, &obs) != 0) {
+		xchk_ino_set_corrupt(xnc->sc, ino);
+		error = -ECANCELED;
+	}
+
+out_scanlock:
+	mutex_unlock(&xnc->lock);
+out_agi:
+	if (agi_bp)
+		xfs_trans_brelse(tp, agi_bp);
+	return error;
+}
+
+/*
+ * Try to visit every inode in the filesystem to compare the link count.  Move
+ * on if we can't grab an inode, since we'll revisit unchecked nlink records in
+ * the second part.
+ */
+static int
+xchk_nlinks_compare_iter(
+	struct xchk_nlink_ctrs	*xnc,
+	struct xfs_inode	**ipp)
+{
+	int			error;
+
+	do {
+		error = xchk_iscan_iter(&xnc->compare_iscan, ipp);
+	} while (error == -EBUSY);
+
+	return error;
+}
+
+/* Compare the link counts we observed against the live information. */
+STATIC int
+xchk_nlinks_compare(
+	struct xchk_nlink_ctrs	*xnc)
+{
+	struct xchk_nlink	nl;
+	struct xfs_scrub	*sc = xnc->sc;
+	struct xfs_inode	*ip;
+	xfarray_idx_t		cur = XFARRAY_CURSOR_INIT;
+	int			error;
+
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		return 0;
+
+	/*
+	 * Create a new empty transaction so that we can advance the iscan
+	 * cursor without deadlocking if the inobt has a cycle and push on the
+	 * inactivation workqueue.
+	 */
+	xchk_trans_cancel(sc);
+	error = xchk_trans_alloc_empty(sc);
+	if (error)
+		return error;
+
+	/*
+	 * Use the inobt to walk all allocated inodes to compare the link
+	 * counts.  Inodes skipped by _compare_iter will be tried again in the
+	 * next phase of the scan.
+	 */
+	xchk_iscan_start(sc, 0, 0, &xnc->compare_iscan);
+	while ((error = xchk_nlinks_compare_iter(xnc, &ip)) == 1) {
+		error = xchk_nlinks_compare_inode(xnc, ip);
+		xchk_iscan_mark_visited(&xnc->compare_iscan, ip);
+		xchk_irele(sc, ip);
+		if (error)
+			break;
+
+		if (xchk_should_terminate(sc, &error))
+			break;
+	}
+	xchk_iscan_iter_finish(&xnc->compare_iscan);
+	xchk_iscan_teardown(&xnc->compare_iscan);
+	if (error)
+		return error;
+
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+		return 0;
+
+	/*
+	 * Walk all the non-null nlink observations that weren't checked in the
+	 * previous step.
+	 */
+	mutex_lock(&xnc->lock);
+	while ((error = xfarray_iter(xnc->nlinks, &cur, &nl)) == 1) {
+		xfs_ino_t	ino = cur - 1;
+
+		if (nl.flags & XCHK_NLINK_COMPARE_SCANNED)
+			continue;
+
+		mutex_unlock(&xnc->lock);
+
+		error = xchk_nlinks_compare_inum(xnc, ino);
+		if (error)
+			return error;
+
+		if (xchk_should_terminate(xnc->sc, &error))
+			return error;
+
+		mutex_lock(&xnc->lock);
+	}
+	mutex_unlock(&xnc->lock);
+
+	return error;
+}
+
+/* Tear down everything associated with a nlinks check. */
+static void
+xchk_nlinks_teardown_scan(
+	void			*priv)
+{
+	struct xchk_nlink_ctrs	*xnc = priv;
+
+	xfarray_destroy(xnc->nlinks);
+	xnc->nlinks = NULL;
+
+	xchk_iscan_teardown(&xnc->collect_iscan);
+	mutex_destroy(&xnc->lock);
+	xnc->sc = NULL;
+}
+
+/*
+ * Scan all inodes in the entire filesystem to generate link count data.  If
+ * the scan is successful, the counts will be left alive for a repair.  If any
+ * error occurs, we'll tear everything down.
+ */
+STATIC int
+xchk_nlinks_setup_scan(
+	struct xfs_scrub	*sc,
+	struct xchk_nlink_ctrs	*xnc)
+{
+	struct xfs_mount	*mp = sc->mp;
+	char			*descr;
+	unsigned long long	max_inos;
+	xfs_agnumber_t		last_agno = mp->m_sb.sb_agcount - 1;
+	xfs_agino_t		first_agino, last_agino;
+	int			error;
+
+	ASSERT(xnc->sc == NULL);
+	xnc->sc = sc;
+
+	mutex_init(&xnc->lock);
+
+	/* Retry iget every tenth of a second for up to 30 seconds. */
+	xchk_iscan_start(sc, 30000, 100, &xnc->collect_iscan);
+
+	/*
+	 * Set up enough space to store an nlink record for the highest
+	 * possible inode number in this system.
+	 */
+	xfs_agino_range(mp, last_agno, &first_agino, &last_agino);
+	max_inos = XFS_AGINO_TO_INO(mp, last_agno, last_agino) + 1;
+	descr = xchk_xfile_descr(sc, "file link counts");
+	error = xfarray_create(descr, min(XFS_MAXINUMBER + 1, max_inos),
+			sizeof(struct xchk_nlink), &xnc->nlinks);
+	kfree(descr);
+	if (error)
+		goto out_teardown;
+
+	/* Use deferred cleanup to pass the inode link count data to repair. */
+	sc->buf_cleanup = xchk_nlinks_teardown_scan;
+	return 0;
+
+out_teardown:
+	xchk_nlinks_teardown_scan(xnc);
+	return error;
+}
+
+/* Scrub the link count of all inodes on the filesystem. */
+int
+xchk_nlinks(
+	struct xfs_scrub	*sc)
+{
+	struct xchk_nlink_ctrs	*xnc = sc->buf;
+	int			error = 0;
+
+	/* Set ourselves up to check link counts on the live filesystem. */
+	error = xchk_nlinks_setup_scan(sc, xnc);
+	if (error)
+		return error;
+
+	/* Walk all inodes, picking up link count information. */
+	error = xchk_nlinks_collect(xnc);
+	if (!xchk_xref_process_error(sc, 0, 0, &error))
+		return error;
+
+	/* Fail fast if we're not playing with a full dataset. */
+	if (xchk_iscan_aborted(&xnc->collect_iscan))
+		xchk_set_incomplete(sc);
+	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_INCOMPLETE)
+		return 0;
+
+	/* Compare link counts. */
+	error = xchk_nlinks_compare(xnc);
+	if (!xchk_xref_process_error(sc, 0, 0, &error))
+		return error;
+
+	/* Check one last time for an incomplete dataset. */
+	if (xchk_iscan_aborted(&xnc->collect_iscan))
+		xchk_set_incomplete(sc);
+
+	return 0;
+}
diff --git a/fs/xfs/scrub/nlinks.h b/fs/xfs/scrub/nlinks.h
new file mode 100644
index 0000000000000..69a3460c5e52f
--- /dev/null
+++ b/fs/xfs/scrub/nlinks.h
@@ -0,0 +1,93 @@
+/* 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_NLINKS_H__
+#define __XFS_SCRUB_NLINKS_H__
+
+/* Live link count control structure. */
+struct xchk_nlink_ctrs {
+	struct xfs_scrub	*sc;
+
+	/* Shadow link count data and its mutex. */
+	struct xfarray		*nlinks;
+	struct mutex		lock;
+
+	/*
+	 * The collection step uses a separate iscan context from the compare
+	 * step because the collection iscan coordinates live updates to the
+	 * observation data while this scanner is running.  The compare iscan
+	 * is secondary and can be reinitialized as needed.
+	 */
+	struct xchk_iscan	collect_iscan;
+	struct xchk_iscan	compare_iscan;
+};
+
+/*
+ * In-core link counts for a given inode in the filesystem.
+ *
+ * For an empty rootdir, the directory entries and the field to which they are
+ * accounted are as follows:
+ *
+ * Root directory:
+ *
+ * . points to self		(root.child)
+ * .. points to self		(root.parent)
+ * f1 points to a child file	(f1.parent)
+ * d1 points to a child dir	(d1.parent, root.child)
+ *
+ * Subdirectory d1:
+ *
+ * . points to self		(d1.child)
+ * .. points to root dir	(root.backref)
+ * f2 points to child file	(f2.parent)
+ * f3 points to root.f1		(f1.parent)
+ *
+ * root.nlink == 3 (root.dot, root.dotdot, root.d1)
+ * d1.nlink == 2 (root.d1, d1.dot)
+ * f1.nlink == 2 (root.f1, d1.f3)
+ * f2.nlink == 1 (d1.f2)
+ */
+struct xchk_nlink {
+	/* Count of forward links from parent directories to this file. */
+	xfs_nlink_t		parents;
+
+	/*
+	 * Count of back links to this parent directory from child
+	 * subdirectories.
+	 */
+	xfs_nlink_t		backrefs;
+
+	/*
+	 * Count of forward links from this directory to all child files and
+	 * the number of dot entries.  Should be zero for non-directories.
+	 */
+	xfs_nlink_t		children;
+
+	/* Record state flags */
+	unsigned int		flags;
+};
+
+/*
+ * This incore link count has been written at least once.  We never want to
+ * store an xchk_nlink that looks uninitialized.
+ */
+#define XCHK_NLINK_WRITTEN		(1U << 0)
+
+/* This data item was seen by the check-time compare function. */
+#define XCHK_NLINK_COMPARE_SCANNED	(1U << 1)
+
+/* Compute total link count, using large enough variables to detect overflow. */
+static inline uint64_t
+xchk_nlink_total(struct xfs_inode *ip, const struct xchk_nlink *live)
+{
+	uint64_t	ret = live->parents;
+
+	/* Add one link count for the dot entry of any linked directory. */
+	if (ip && S_ISDIR(VFS_I(ip)->i_mode) && VFS_I(ip)->i_nlink)
+		ret++;
+	return ret + live->children;
+}
+
+#endif /* __XFS_SCRUB_NLINKS_H__ */
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 9112c0985c62b..8c60774d5f345 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -369,6 +369,12 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.scrub	= xchk_quotacheck,
 		.repair	= xrep_quotacheck,
 	},
+	[XFS_SCRUB_TYPE_NLINKS] = {	/* inode link counts */
+		.type	= ST_FS,
+		.setup	= xchk_setup_nlinks,
+		.scrub	= xchk_nlinks,
+		.repair	= xrep_notsupported,
+	},
 };
 
 static int
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index 5cd4550155f23..de6b45f99dd5f 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -183,6 +183,7 @@ xchk_quotacheck(struct xfs_scrub *sc)
 }
 #endif
 int xchk_fscounters(struct xfs_scrub *sc);
+int xchk_nlinks(struct xfs_scrub *sc);
 
 /* cross-referencing helpers */
 void xchk_xref_is_used_space(struct xfs_scrub *sc, xfs_agblock_t agbno,
diff --git a/fs/xfs/scrub/stats.c b/fs/xfs/scrub/stats.c
index d716a432227b0..b4ef1ebe28ab8 100644
--- a/fs/xfs/scrub/stats.c
+++ b/fs/xfs/scrub/stats.c
@@ -78,6 +78,7 @@ static const char *name_map[XFS_SCRUB_TYPE_NR] = {
 	[XFS_SCRUB_TYPE_PQUOTA]		= "prjquota",
 	[XFS_SCRUB_TYPE_FSCOUNTERS]	= "fscounters",
 	[XFS_SCRUB_TYPE_QUOTACHECK]	= "quotacheck",
+	[XFS_SCRUB_TYPE_NLINKS]		= "nlinks",
 };
 
 /* Format the scrub stats into a text buffer, similar to pcp style. */
diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c
index 5ed75cc33b928..2d5a330afe10c 100644
--- a/fs/xfs/scrub/trace.c
+++ b/fs/xfs/scrub/trace.c
@@ -17,11 +17,13 @@
 #include "xfs_quota.h"
 #include "xfs_quota_defs.h"
 #include "xfs_da_format.h"
+#include "xfs_dir2.h"
 #include "scrub/scrub.h"
 #include "scrub/xfile.h"
 #include "scrub/xfarray.h"
 #include "scrub/quota.h"
 #include "scrub/iscan.h"
+#include "scrub/nlinks.h"
 
 /* Figure out which block the btree cursor was pointing to. */
 static inline xfs_fsblock_t
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 955af3de92813..2d6439f4aee4b 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -23,6 +23,7 @@ struct xfarray;
 struct xfarray_sortinfo;
 struct xchk_dqiter;
 struct xchk_iscan;
+struct xchk_nlink;
 
 /*
  * ftrace's __print_symbolic requires that all enum values be wrapped in the
@@ -67,6 +68,7 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_GQUOTA);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_PQUOTA);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_FSCOUNTERS);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_QUOTACHECK);
+TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_NLINKS);
 
 #define XFS_SCRUB_TYPE_STRINGS \
 	{ XFS_SCRUB_TYPE_PROBE,		"probe" }, \
@@ -94,7 +96,8 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_QUOTACHECK);
 	{ XFS_SCRUB_TYPE_GQUOTA,	"grpquota" }, \
 	{ XFS_SCRUB_TYPE_PQUOTA,	"prjquota" }, \
 	{ XFS_SCRUB_TYPE_FSCOUNTERS,	"fscounters" }, \
-	{ XFS_SCRUB_TYPE_QUOTACHECK,	"quotacheck" }
+	{ XFS_SCRUB_TYPE_QUOTACHECK,	"quotacheck" }, \
+	{ XFS_SCRUB_TYPE_NLINKS,	"nlinks" }
 
 #define XFS_SCRUB_FLAG_STRINGS \
 	{ XFS_SCRUB_IFLAG_REPAIR,		"repair" }, \
@@ -1291,6 +1294,148 @@ TRACE_EVENT(xchk_iscan_iget_retry_wait,
 		  __entry->retry_delay)
 );
 
+TRACE_EVENT(xchk_nlinks_collect_dirent,
+	TP_PROTO(struct xfs_mount *mp, struct xfs_inode *dp,
+		 xfs_ino_t ino, const struct xfs_name *name),
+	TP_ARGS(mp, dp, ino, name),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, dir)
+		__field(xfs_ino_t, ino)
+		__field(unsigned int, namelen)
+		__dynamic_array(char, name, name->len)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->dir = dp->i_ino;
+		__entry->ino = ino;
+		__entry->namelen = name->len;
+		memcpy(__get_str(name), name->name, name->len);
+	),
+	TP_printk("dev %d:%d dir 0x%llx -> ino 0x%llx name '%.*s'",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->dir,
+		  __entry->ino,
+		  __entry->namelen,
+		  __get_str(name))
+);
+
+TRACE_EVENT(xchk_nlinks_collect_metafile,
+	TP_PROTO(struct xfs_mount *mp, xfs_ino_t ino),
+	TP_ARGS(mp, ino),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->ino = ino;
+	),
+	TP_printk("dev %d:%d ino 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino)
+);
+
+TRACE_EVENT(xchk_nlinks_check_zero,
+	TP_PROTO(struct xfs_mount *mp, xfs_ino_t ino,
+		 const struct xchk_nlink *live),
+	TP_ARGS(mp, ino, live),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(xfs_nlink_t, parents)
+		__field(xfs_nlink_t, backrefs)
+		__field(xfs_nlink_t, children)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->ino = ino;
+		__entry->parents = live->parents;
+		__entry->backrefs = live->backrefs;
+		__entry->children = live->children;
+	),
+	TP_printk("dev %d:%d ino 0x%llx parents %u backrefs %u children %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->parents,
+		  __entry->backrefs,
+		  __entry->children)
+);
+
+TRACE_EVENT(xchk_nlinks_update_incore,
+	TP_PROTO(struct xfs_mount *mp, xfs_ino_t ino,
+		 const struct xchk_nlink *live, int parents_delta,
+		 int backrefs_delta, int children_delta),
+	TP_ARGS(mp, ino, live, parents_delta, backrefs_delta, children_delta),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(xfs_nlink_t, parents)
+		__field(xfs_nlink_t, backrefs)
+		__field(xfs_nlink_t, children)
+		__field(int, parents_delta)
+		__field(int, backrefs_delta)
+		__field(int, children_delta)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->ino = ino;
+		__entry->parents = live->parents;
+		__entry->backrefs = live->backrefs;
+		__entry->children = live->children;
+		__entry->parents_delta = parents_delta;
+		__entry->backrefs_delta = backrefs_delta;
+		__entry->children_delta = children_delta;
+	),
+	TP_printk("dev %d:%d ino 0x%llx parents %d:%u backrefs %d:%u children %d:%u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->parents_delta,
+		  __entry->parents,
+		  __entry->backrefs_delta,
+		  __entry->backrefs,
+		  __entry->children_delta,
+		  __entry->children)
+);
+
+DECLARE_EVENT_CLASS(xchk_nlinks_diff_class,
+	TP_PROTO(struct xfs_mount *mp, struct xfs_inode *ip,
+		 const struct xchk_nlink *live),
+	TP_ARGS(mp, ip, live),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(uint8_t, ftype)
+		__field(xfs_nlink_t, nlink)
+		__field(xfs_nlink_t, parents)
+		__field(xfs_nlink_t, backrefs)
+		__field(xfs_nlink_t, children)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->ino = ip->i_ino;
+		__entry->ftype = xfs_mode_to_ftype(VFS_I(ip)->i_mode);
+		__entry->nlink = VFS_I(ip)->i_nlink;
+		__entry->parents = live->parents;
+		__entry->backrefs = live->backrefs;
+		__entry->children = live->children;
+	),
+	TP_printk("dev %d:%d ino 0x%llx ftype %s nlink %u parents %u backrefs %u children %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __print_symbolic(__entry->ftype, XFS_DIR3_FTYPE_STR),
+		  __entry->nlink,
+		  __entry->parents,
+		  __entry->backrefs,
+		  __entry->children)
+);
+#define DEFINE_SCRUB_NLINKS_DIFF_EVENT(name) \
+DEFINE_EVENT(xchk_nlinks_diff_class, name, \
+	TP_PROTO(struct xfs_mount *mp, struct xfs_inode *ip, \
+		 const struct xchk_nlink *live), \
+	TP_ARGS(mp, ip, live))
+DEFINE_SCRUB_NLINKS_DIFF_EVENT(xchk_nlinks_compare_inode);
+
 /* repair tracepoints */
 #if IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR)
 

[PATCH 3/4] xfs: track directory entry updates during live nlinks fsck

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create the necessary hooks in the directory operations
(create/link/unlink/rename) code so that our live nlink scrub code can
stay up to date with link count updates in the rest of the filesystem.
This will be the means to keep our shadow link count information up to
date while the scan runs in real time.

In online fsck part 2, we'll use these same hooks to handle repairs
to directories and parent pointer information.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/common.c |    3 +
 fs/xfs/scrub/nlinks.c |   93 +++++++++++++++++++++++++++++++++++++++++-
 fs/xfs/scrub/nlinks.h |    6 +++
 fs/xfs/scrub/scrub.c  |    3 +
 fs/xfs/scrub/scrub.h  |    4 +-
 fs/xfs/scrub/trace.h  |   33 +++++++++++++++
 fs/xfs/xfs_inode.c    |  108 +++++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_inode.h    |   31 ++++++++++++++
 fs/xfs/xfs_mount.h    |    3 +
 fs/xfs/xfs_super.c    |    2 +
 fs/xfs/xfs_symlink.c  |    1 
 11 files changed, 284 insertions(+), 3 deletions(-)


diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 6e193aee12666..86fea1d816d60 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -1302,6 +1302,9 @@ xchk_fsgates_enable(
 	if (scrub_fsgates & XCHK_FSGATES_QUOTA)
 		xfs_dqtrx_hook_enable();
 
+	if (scrub_fsgates & XCHK_FSGATES_DIRENTS)
+		xfs_dir_hook_enable();
+
 	sc->flags |= scrub_fsgates;
 }
 
diff --git a/fs/xfs/scrub/nlinks.c b/fs/xfs/scrub/nlinks.c
index c899a50a83daf..421615136972b 100644
--- a/fs/xfs/scrub/nlinks.c
+++ b/fs/xfs/scrub/nlinks.c
@@ -43,8 +43,7 @@ int
 xchk_setup_nlinks(
 	struct xfs_scrub	*sc)
 {
-	/* Not ready for general consumption yet. */
-	return -EOPNOTSUPP;
+	xchk_fsgates_enable(sc, XCHK_FSGATES_DIRENTS);
 
 	sc->buf = kzalloc(sizeof(struct xchk_nlink_ctrs), XCHK_GFP_FLAGS);
 	if (!sc->buf)
@@ -63,6 +62,21 @@ xchk_setup_nlinks(
  * must be taken with certain errno values (i.e. EFSBADCRC, EFSCORRUPTED,
  * ECANCELED) that are absorbed into a scrub state flag update by
  * xchk_*_process_error.
+ *
+ * Because we are scanning a live filesystem, it's possible that another thread
+ * will try to update the link counts for an inode that we've already scanned.
+ * This will cause our counts to be incorrect.  Therefore, we hook all
+ * directory entry updates because that is when link count updates occur.  By
+ * shadowing transaction updates in this manner, live nlink check can ensure by
+ * locking the inode and the shadow structure that its own copies are not out
+ * of date.  Because the hook code runs in a different process context from the
+ * scrub code and the scrub state flags are not accessed atomically, failures
+ * in the hook code must abort the iscan and the scrubber must notice the
+ * aborted scan and set the incomplete flag.
+ *
+ * Note that we use jump labels and srcu notifier hooks to minimize the
+ * overhead when live nlinks is /not/ running.  Locking order for nlink
+ * observations is inode ILOCK -> iscan_lock/xchk_nlink_ctrs lock.
  */
 
 /*
@@ -120,6 +134,63 @@ xchk_nlinks_update_incore(
 	return error;
 }
 
+/*
+ * Apply a link count change from the regular filesystem into our shadow link
+ * count structure based on a directory update in progress.
+ */
+STATIC int
+xchk_nlinks_live_update(
+	struct notifier_block		*nb,
+	unsigned long			action,
+	void				*data)
+{
+	struct xfs_dir_update_params	*p = data;
+	struct xchk_nlink_ctrs		*xnc;
+	int				error;
+
+	xnc = container_of(nb, struct xchk_nlink_ctrs, hooks.dirent_hook.nb);
+
+	trace_xchk_nlinks_live_update(xnc->sc->mp, p->dp, action, p->ip->i_ino,
+			p->delta, p->name->name, p->name->len);
+
+	/*
+	 * If we've already scanned @dp, update the number of parents that link
+	 * to @ip.  If @ip is a subdirectory, update the number of child links
+	 * going out of @dp.
+	 */
+	if (xchk_iscan_want_live_update(&xnc->collect_iscan, p->dp->i_ino)) {
+		mutex_lock(&xnc->lock);
+		error = xchk_nlinks_update_incore(xnc, p->ip->i_ino, p->delta,
+				0, 0);
+		if (!error && S_ISDIR(VFS_IC(p->ip)->i_mode))
+			error = xchk_nlinks_update_incore(xnc, p->dp->i_ino, 0,
+					0, p->delta);
+		mutex_unlock(&xnc->lock);
+		if (error)
+			goto out_abort;
+	}
+
+	/*
+	 * If @ip is a subdirectory and we've already scanned it, update the
+	 * number of backrefs pointing to @dp.
+	 */
+	if (S_ISDIR(VFS_IC(p->ip)->i_mode) &&
+	    xchk_iscan_want_live_update(&xnc->collect_iscan, p->ip->i_ino)) {
+		mutex_lock(&xnc->lock);
+		error = xchk_nlinks_update_incore(xnc, p->dp->i_ino, 0,
+				p->delta, 0);
+		mutex_unlock(&xnc->lock);
+		if (error)
+			goto out_abort;
+	}
+
+	return NOTIFY_DONE;
+
+out_abort:
+	xchk_iscan_abort(&xnc->collect_iscan);
+	return NOTIFY_DONE;
+}
+
 /* Bump the observed link count for the inode referenced by this entry. */
 STATIC int
 xchk_nlinks_collect_dirent(
@@ -747,6 +818,11 @@ xchk_nlinks_teardown_scan(
 {
 	struct xchk_nlink_ctrs	*xnc = priv;
 
+	/* Discourage any hook functions that might be running. */
+	xchk_iscan_abort(&xnc->collect_iscan);
+
+	xfs_dir_hook_del(xnc->sc->mp, &xnc->hooks);
+
 	xfarray_destroy(xnc->nlinks);
 	xnc->nlinks = NULL;
 
@@ -793,6 +869,19 @@ xchk_nlinks_setup_scan(
 	if (error)
 		goto out_teardown;
 
+	/*
+	 * Hook into the directory entry code so that we can capture updates to
+	 * file link counts.  The hook only triggers for inodes that were
+	 * already scanned, and the scanner thread takes each inode's ILOCK,
+	 * which means that any in-progress inode updates will finish before we
+	 * can scan the inode.
+	 */
+	ASSERT(sc->flags & XCHK_FSGATES_DIRENTS);
+	xfs_hook_setup(&xnc->hooks.dirent_hook, xchk_nlinks_live_update);
+	error = xfs_dir_hook_add(mp, &xnc->hooks);
+	if (error)
+		goto out_teardown;
+
 	/* Use deferred cleanup to pass the inode link count data to repair. */
 	sc->buf_cleanup = xchk_nlinks_teardown_scan;
 	return 0;
diff --git a/fs/xfs/scrub/nlinks.h b/fs/xfs/scrub/nlinks.h
index 69a3460c5e52f..58d247c051292 100644
--- a/fs/xfs/scrub/nlinks.h
+++ b/fs/xfs/scrub/nlinks.h
@@ -22,6 +22,12 @@ struct xchk_nlink_ctrs {
 	 */
 	struct xchk_iscan	collect_iscan;
 	struct xchk_iscan	compare_iscan;
+
+	/*
+	 * Hook into directory updates so that we can receive live updates
+	 * from other writer threads.
+	 */
+	struct xfs_dir_hook	hooks;
 };
 
 /*
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 8c60774d5f345..883c47b6c6860 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -160,6 +160,9 @@ xchk_fsgates_disable(
 	if (sc->flags & XCHK_FSGATES_QUOTA)
 		xfs_dqtrx_hook_disable();
 
+	if (sc->flags & XCHK_FSGATES_DIRENTS)
+		xfs_dir_hook_disable();
+
 	sc->flags &= ~XCHK_FSGATES_ALL;
 }
 
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index de6b45f99dd5f..f99a3c21d02ea 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -122,6 +122,7 @@ struct xfs_scrub {
 #define XCHK_FSGATES_DRAIN	(1U << 2)  /* defer ops draining enabled */
 #define XCHK_NEED_DRAIN		(1U << 3)  /* scrub needs to drain defer ops */
 #define XCHK_FSGATES_QUOTA	(1U << 4)  /* quota live update enabled */
+#define XCHK_FSGATES_DIRENTS	(1U << 5)  /* directory live update enabled */
 #define XREP_RESET_PERAG_RESV	(1U << 30) /* must reset AG space reservation */
 #define XREP_ALREADY_FIXED	(1U << 31) /* checking our repair work */
 
@@ -132,7 +133,8 @@ struct xfs_scrub {
  * must be enabled during scrub setup and can only be torn down afterwards.
  */
 #define XCHK_FSGATES_ALL	(XCHK_FSGATES_DRAIN | \
-				 XCHK_FSGATES_QUOTA)
+				 XCHK_FSGATES_QUOTA | \
+				 XCHK_FSGATES_DIRENTS)
 
 /* Metadata scrubbers */
 int xchk_tester(struct xfs_scrub *sc);
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 2d6439f4aee4b..52d70d73c26ba 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -116,6 +116,7 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_NLINKS);
 	{ XCHK_FSGATES_DRAIN,			"fsgates_drain" }, \
 	{ XCHK_NEED_DRAIN,			"need_drain" }, \
 	{ XCHK_FSGATES_QUOTA,			"fsgates_quota" }, \
+	{ XCHK_FSGATES_DIRENTS,			"fsgates_dirents" }, \
 	{ XREP_RESET_PERAG_RESV,		"reset_perag_resv" }, \
 	{ XREP_ALREADY_FIXED,			"already_fixed" }
 
@@ -1336,6 +1337,38 @@ TRACE_EVENT(xchk_nlinks_collect_metafile,
 		  __entry->ino)
 );
 
+TRACE_EVENT(xchk_nlinks_live_update,
+	TP_PROTO(struct xfs_mount *mp, const struct xfs_inode *dp,
+		 int action, xfs_ino_t ino, int delta,
+		 const char *name, unsigned int namelen),
+	TP_ARGS(mp, dp, action, ino, delta, name, namelen),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, dir)
+		__field(int, action)
+		__field(xfs_ino_t, ino)
+		__field(int, delta)
+		__field(unsigned int, namelen)
+		__dynamic_array(char, name, namelen)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->dir = dp ? dp->i_ino : NULLFSINO;
+		__entry->action = action;
+		__entry->ino = ino;
+		__entry->delta = delta;
+		__entry->namelen = namelen;
+		memcpy(__get_str(name), name, namelen);
+	),
+	TP_printk("dev %d:%d dir 0x%llx ino 0x%llx nlink_delta %d name '%.*s'",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->dir,
+		  __entry->ino,
+		  __entry->delta,
+		  __entry->namelen,
+		  __get_str(name))
+);
+
 TRACE_EVENT(xchk_nlinks_check_zero,
 	TP_PROTO(struct xfs_mount *mp, xfs_ino_t ino,
 		 const struct xchk_nlink *live),
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 078073168fdfd..ed620597d289b 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -947,6 +947,72 @@ xfs_bumplink(
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 }
 
+#ifdef CONFIG_XFS_LIVE_HOOKS
+/*
+ * Use a static key here to reduce the overhead of directory live update hooks.
+ * If the compiler supports jump labels, the static branch will be replaced by
+ * a nop sled when there are no hook users.  Online fsck is currently the only
+ * caller, so this is a reasonable tradeoff.
+ *
+ * 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_STATIC_XFS_HOOK_SWITCH(xfs_dir_hooks_switch);
+
+void
+xfs_dir_hook_disable(void)
+{
+	xfs_hooks_switch_off(&xfs_dir_hooks_switch);
+}
+
+void
+xfs_dir_hook_enable(void)
+{
+	xfs_hooks_switch_on(&xfs_dir_hooks_switch);
+}
+
+/* Call hooks for a directory update relating to a child dirent update. */
+inline void
+xfs_dir_update_hook(
+	struct xfs_inode		*dp,
+	struct xfs_inode		*ip,
+	int				delta,
+	const struct xfs_name		*name)
+{
+	if (xfs_hooks_switched_on(&xfs_dir_hooks_switch)) {
+		struct xfs_dir_update_params	p = {
+			.dp		= dp,
+			.ip		= ip,
+			.delta		= delta,
+			.name		= name,
+		};
+		struct xfs_mount	*mp = ip->i_mount;
+
+		xfs_hooks_call(&mp->m_dir_update_hooks, 0, &p);
+	}
+}
+
+/* Call the specified function during a directory update. */
+int
+xfs_dir_hook_add(
+	struct xfs_mount	*mp,
+	struct xfs_dir_hook	*hook)
+{
+	return xfs_hooks_add(&mp->m_dir_update_hooks, &hook->dirent_hook);
+}
+
+/* Stop calling the specified function during a directory update. */
+void
+xfs_dir_hook_del(
+	struct xfs_mount	*mp,
+	struct xfs_dir_hook	*hook)
+{
+	xfs_hooks_del(&mp->m_dir_update_hooks, &hook->dirent_hook);
+}
+#endif /* CONFIG_XFS_LIVE_HOOKS */
+
 int
 xfs_create(
 	struct mnt_idmap	*idmap,
@@ -1057,6 +1123,12 @@ xfs_create(
 		xfs_bumplink(tp, dp);
 	}
 
+	/*
+	 * Create ip with a reference from dp, and add '.' and '..' references
+	 * if it's a directory.
+	 */
+	xfs_dir_update_hook(dp, ip, 1, name);
+
 	/*
 	 * If this is a synchronous mount, make sure that the
 	 * create transaction goes to disk before returning to
@@ -1271,6 +1343,7 @@ xfs_link(
 	xfs_trans_log_inode(tp, tdp, XFS_ILOG_CORE);
 
 	xfs_bumplink(tp, sip);
+	xfs_dir_update_hook(tdp, sip, 1, target_name);
 
 	/*
 	 * If this is a synchronous mount, make sure that the
@@ -2584,6 +2657,12 @@ xfs_remove(
 		goto out_trans_cancel;
 	}
 
+	/*
+	 * Drop the link from dp to ip, and if ip was a directory, remove the
+	 * '.' and '..' references since we freed the directory.
+	 */
+	xfs_dir_update_hook(dp, ip, -1, name);
+
 	/*
 	 * If this is a synchronous mount, make sure that the
 	 * remove transaction goes to disk before returning to
@@ -2774,6 +2853,20 @@ xfs_cross_rename(
 	}
 	xfs_trans_ichgtime(tp, dp1, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 	xfs_trans_log_inode(tp, dp1, XFS_ILOG_CORE);
+
+	/*
+	 * Inform our hook clients that we've finished an exchange operation as
+	 * follows: removed the source and target files from their directories;
+	 * added the target to the source directory; and added the source to
+	 * the target directory.  All inodes are locked, so it's ok to model a
+	 * rename this way so long as we say we deleted entries before we add
+	 * new ones.
+	 */
+	xfs_dir_update_hook(dp1, ip1, -1, name1);
+	xfs_dir_update_hook(dp2, ip2, -1, name2);
+	xfs_dir_update_hook(dp1, ip2, 1, name1);
+	xfs_dir_update_hook(dp2, ip1, 1, name2);
+
 	return xfs_finish_rename(tp);
 
 out_trans_abort:
@@ -3157,6 +3250,21 @@ xfs_rename(
 	if (new_parent)
 		xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE);
 
+	/*
+	 * Inform our hook clients that we've finished a rename operation as
+	 * follows: removed the source and target files from their directories;
+	 * that we've added the source to the target directory; and finally
+	 * that we've added the whiteout, if there was one.  All inodes are
+	 * locked, so it's ok to model a rename this way so long as we say we
+	 * deleted entries before we add new ones.
+	 */
+	if (target_ip)
+		xfs_dir_update_hook(target_dp, target_ip, -1, target_name);
+	xfs_dir_update_hook(src_dp, src_ip, -1, src_name);
+	xfs_dir_update_hook(target_dp, src_ip, 1, target_name);
+	if (wip)
+		xfs_dir_update_hook(src_dp, wip, 1, src_name);
+
 	error = xfs_finish_rename(tp);
 	if (wip)
 		xfs_irele(wip);
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 15a16e1404eea..764d88198366d 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -171,6 +171,12 @@ static inline struct inode *VFS_I(struct xfs_inode *ip)
 	return &ip->i_vnode;
 }
 
+/* convert from const xfs inode to const vfs inode */
+static inline const struct inode *VFS_IC(const struct xfs_inode *ip)
+{
+	return &ip->i_vnode;
+}
+
 /*
  * For regular files we only update the on-disk filesize when actually
  * writing data back to disk.  Until then only the copy in the VFS inode
@@ -626,4 +632,29 @@ bool xfs_ifork_zapped(const struct xfs_inode *ip, int whichfork);
 void xfs_inode_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_filblks_t *dblocks, xfs_filblks_t *rblocks);
 
+struct xfs_dir_update_params {
+	const struct xfs_inode	*dp;
+	const struct xfs_inode	*ip;
+	const struct xfs_name	*name;
+	int			delta;
+};
+
+#ifdef CONFIG_XFS_LIVE_HOOKS
+void xfs_dir_update_hook(struct xfs_inode *dp, struct xfs_inode *ip,
+		int delta, const struct xfs_name *name);
+
+struct xfs_dir_hook {
+	struct xfs_hook		dirent_hook;
+};
+
+void xfs_dir_hook_disable(void);
+void xfs_dir_hook_enable(void);
+
+int xfs_dir_hook_add(struct xfs_mount *mp, struct xfs_dir_hook *hook);
+void xfs_dir_hook_del(struct xfs_mount *mp, struct xfs_dir_hook *hook);
+
+#else
+# define xfs_dir_update_hook(dp, ip, delta, name)	((void)0)
+#endif /* CONFIG_XFS_LIVE_HOOKS */
+
 #endif	/* __XFS_INODE_H__ */
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 503fe3c7edbf8..e86dfe67894fb 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -252,6 +252,9 @@ typedef struct xfs_mount {
 
 	/* cpus that have inodes queued for inactivation */
 	struct cpumask		m_inodegc_cpumask;
+
+	/* Hook to feed dirent updates to an active online repair. */
+	struct xfs_hooks	m_dir_update_hooks;
 } xfs_mount_t;
 
 #define M_IGEO(mp)		(&(mp)->m_ino_geo)
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 764304595e8b0..8619f517b1bf3 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -2010,6 +2010,8 @@ static int xfs_init_fs_context(
 	mp->m_logbsize = -1;
 	mp->m_allocsize_log = 16; /* 64k */
 
+	xfs_hooks_init(&mp->m_dir_update_hooks);
+
 	/*
 	 * Copy binary VFS mount flags we are interested in.
 	 */
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 7c713727f7fd3..2a8b3071411f0 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -322,6 +322,7 @@ xfs_symlink(
 		goto out_trans_cancel;
 	xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 	xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
+	xfs_dir_update_hook(dp, ip, 1, link_name);
 
 	/*
 	 * If this is a synchronous mount, make sure that the

[PATCH 4/4] xfs: teach repair to fix file nlinks

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Fix the nlinks now too.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Makefile              |    1 
 fs/xfs/scrub/nlinks.c        |    4 +
 fs/xfs/scrub/nlinks.h        |    5 +
 fs/xfs/scrub/nlinks_repair.c |  223 ++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/repair.h        |    2 
 fs/xfs/scrub/scrub.c         |    2 
 fs/xfs/scrub/trace.h         |    3 +
 7 files changed, 237 insertions(+), 3 deletions(-)
 create mode 100644 fs/xfs/scrub/nlinks_repair.c


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index cabf1dd341adc..1efc3b7727dc0 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -195,6 +195,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   ialloc_repair.o \
 				   inode_repair.o \
 				   newbt.o \
+				   nlinks_repair.o \
 				   reap.o \
 				   refcount_repair.o \
 				   repair.o \
diff --git a/fs/xfs/scrub/nlinks.c b/fs/xfs/scrub/nlinks.c
index 421615136972b..8eb0f96932866 100644
--- a/fs/xfs/scrub/nlinks.c
+++ b/fs/xfs/scrub/nlinks.c
@@ -61,7 +61,9 @@ xchk_setup_nlinks(
  * set the INCOMPLETE flag even when a negative errno is returned.  This care
  * must be taken with certain errno values (i.e. EFSBADCRC, EFSCORRUPTED,
  * ECANCELED) that are absorbed into a scrub state flag update by
- * xchk_*_process_error.
+ * xchk_*_process_error.  Scrub and repair share the same incore data
+ * structures, so the INCOMPLETE flag is critical to prevent a repair based on
+ * insufficient information.
  *
  * Because we are scanning a live filesystem, it's possible that another thread
  * will try to update the link counts for an inode that we've already scanned.
diff --git a/fs/xfs/scrub/nlinks.h b/fs/xfs/scrub/nlinks.h
index 58d247c051292..6b651ac0822e2 100644
--- a/fs/xfs/scrub/nlinks.h
+++ b/fs/xfs/scrub/nlinks.h
@@ -81,9 +81,12 @@ struct xchk_nlink {
  */
 #define XCHK_NLINK_WRITTEN		(1U << 0)
 
-/* This data item was seen by the check-time compare function. */
+/* Already checked this link count record. */
 #define XCHK_NLINK_COMPARE_SCANNED	(1U << 1)
 
+/* Already made a repair with this link count record. */
+#define XREP_NLINK_DIRTY		(1U << 2)
+
 /* Compute total link count, using large enough variables to detect overflow. */
 static inline uint64_t
 xchk_nlink_total(struct xfs_inode *ip, const struct xchk_nlink *live)
diff --git a/fs/xfs/scrub/nlinks_repair.c b/fs/xfs/scrub/nlinks_repair.c
new file mode 100644
index 0000000000000..b87618322f55b
--- /dev/null
+++ b/fs/xfs/scrub/nlinks_repair.c
@@ -0,0 +1,223 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2021-2024 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_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_bmap_util.h"
+#include "xfs_iwalk.h"
+#include "xfs_ialloc.h"
+#include "xfs_sb.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/repair.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/iscan.h"
+#include "scrub/nlinks.h"
+#include "scrub/trace.h"
+
+/*
+ * Live Inode Link Count Repair
+ * ============================
+ *
+ * Use the live inode link count information that we collected to replace the
+ * nlink values of the incore inodes.  A scrub->repair cycle should have left
+ * the live data and hooks active, so this is safe so long as we make sure the
+ * inode is locked.
+ */
+
+/*
+ * Correct the link count of the given inode.  Because we have to grab locks
+ * and resources in a certain order, it's possible that this will be a no-op.
+ */
+STATIC int
+xrep_nlinks_repair_inode(
+	struct xchk_nlink_ctrs	*xnc)
+{
+	struct xchk_nlink	obs;
+	struct xfs_scrub	*sc = xnc->sc;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_inode	*ip = sc->ip;
+	uint64_t		total_links;
+	uint64_t		actual_nlink;
+	bool			dirty = false;
+	int			error;
+
+	xchk_ilock(sc, XFS_IOLOCK_EXCL);
+
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_link, 0, 0, 0, &sc->tp);
+	if (error)
+		return error;
+
+	xchk_ilock(sc, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(sc->tp, ip, 0);
+
+	mutex_lock(&xnc->lock);
+
+	if (xchk_iscan_aborted(&xnc->collect_iscan)) {
+		error = -ECANCELED;
+		goto out_scanlock;
+	}
+
+	error = xfarray_load_sparse(xnc->nlinks, ip->i_ino, &obs);
+	if (error)
+		goto out_scanlock;
+
+	/*
+	 * We're done accessing the shared scan data, so we can drop the lock.
+	 * We still hold @ip's ILOCK, so its link count cannot change.
+	 */
+	mutex_unlock(&xnc->lock);
+
+	total_links = xchk_nlink_total(ip, &obs);
+	actual_nlink = VFS_I(ip)->i_nlink;
+
+	/*
+	 * Non-directories cannot have directories pointing up to them.
+	 *
+	 * We previously set error to zero, but set it again because one static
+	 * checker author fears that programmers will fail to maintain this
+	 * invariant and built their tool to flag this as a security risk.  A
+	 * different tool author made their bot complain about the redundant
+	 * store.  This is a never-ending and stupid battle; both tools missed
+	 * *actual bugs* elsewhere; and I no longer care.
+	 */
+	if (!S_ISDIR(VFS_I(ip)->i_mode) && obs.children != 0) {
+		trace_xrep_nlinks_unfixable_inode(mp, ip, &obs);
+		error = 0;
+		goto out_trans;
+	}
+
+	/*
+	 * We did not find any links to this inode.  If the inode agrees, we
+	 * have nothing further to do.  If not, the inode has a nonzero link
+	 * count and we don't have anywhere to graft the child onto.  Dropping
+	 * a live inode's link count to zero can cause unexpected shutdowns in
+	 * inactivation, so leave it alone.
+	 */
+	if (total_links == 0) {
+		if (actual_nlink != 0)
+			trace_xrep_nlinks_unfixable_inode(mp, ip, &obs);
+		goto out_trans;
+	}
+
+	/* Commit the new link count if it changed. */
+	if (total_links != actual_nlink) {
+		if (total_links > XFS_MAXLINK) {
+			trace_xrep_nlinks_unfixable_inode(mp, ip, &obs);
+			goto out_trans;
+		}
+
+		trace_xrep_nlinks_update_inode(mp, ip, &obs);
+
+		set_nlink(VFS_I(ip), total_links);
+		dirty = true;
+	}
+
+	if (!dirty) {
+		error = 0;
+		goto out_trans;
+	}
+
+	xfs_trans_log_inode(sc->tp, ip, XFS_ILOG_CORE);
+
+	error = xrep_trans_commit(sc);
+	xchk_iunlock(sc, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+	return error;
+
+out_scanlock:
+	mutex_unlock(&xnc->lock);
+out_trans:
+	xchk_trans_cancel(sc);
+	xchk_iunlock(sc, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+	return error;
+}
+
+/*
+ * Try to visit every inode in the filesystem for repairs.  Move on if we can't
+ * grab an inode, since we're still making forward progress.
+ */
+static int
+xrep_nlinks_iter(
+	struct xchk_nlink_ctrs	*xnc,
+	struct xfs_inode	**ipp)
+{
+	int			error;
+
+	do {
+		error = xchk_iscan_iter(&xnc->compare_iscan, ipp);
+	} while (error == -EBUSY);
+
+	return error;
+}
+
+/* Commit the new inode link counters. */
+int
+xrep_nlinks(
+	struct xfs_scrub	*sc)
+{
+	struct xchk_nlink_ctrs	*xnc = sc->buf;
+	int			error;
+
+	/*
+	 * We need ftype for an accurate count of the number of child
+	 * subdirectory links.  Child subdirectories with a back link (dotdot
+	 * entry) but no forward link are unfixable, so we cannot repair the
+	 * link count of the parent directory based on the back link count
+	 * alone.  Filesystems without ftype support are rare (old V4) so we
+	 * just skip out here.
+	 */
+	if (!xfs_has_ftype(sc->mp))
+		return -EOPNOTSUPP;
+
+	/*
+	 * Use the inobt to walk all allocated inodes to compare and fix the
+	 * link counts.  Retry iget every tenth of a second for up to 30
+	 * seconds -- even if repair misses a few inodes, we still try to fix
+	 * as many of them as we can.
+	 */
+	xchk_iscan_start(sc, 30000, 100, &xnc->compare_iscan);
+	ASSERT(sc->ip == NULL);
+
+	while ((error = xrep_nlinks_iter(xnc, &sc->ip)) == 1) {
+		/*
+		 * Commit the scrub transaction so that we can create repair
+		 * transactions with the correct reservations.
+		 */
+		xchk_trans_cancel(sc);
+
+		error = xrep_nlinks_repair_inode(xnc);
+		xchk_iscan_mark_visited(&xnc->compare_iscan, sc->ip);
+		xchk_irele(sc, sc->ip);
+		sc->ip = NULL;
+		if (error)
+			break;
+
+		if (xchk_should_terminate(sc, &error))
+			break;
+
+		/*
+		 * Create a new empty transaction so that we can advance the
+		 * iscan cursor without deadlocking if the inobt has a cycle.
+		 * We can only push the inactivation workqueues with an empty
+		 * transaction.
+		 */
+		error = xchk_trans_alloc_empty(sc);
+		if (error)
+			break;
+	}
+	xchk_iscan_iter_finish(&xnc->compare_iscan);
+	xchk_iscan_teardown(&xnc->compare_iscan);
+
+	return error;
+}
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index fdfa066999218..8edac0150e960 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -116,6 +116,7 @@ int xrep_inode(struct xfs_scrub *sc);
 int xrep_bmap_data(struct xfs_scrub *sc);
 int xrep_bmap_attr(struct xfs_scrub *sc);
 int xrep_bmap_cow(struct xfs_scrub *sc);
+int xrep_nlinks(struct xfs_scrub *sc);
 
 #ifdef CONFIG_XFS_RT
 int xrep_rtbitmap(struct xfs_scrub *sc);
@@ -196,6 +197,7 @@ xrep_setup_nothing(
 #define xrep_rtbitmap			xrep_notsupported
 #define xrep_quota			xrep_notsupported
 #define xrep_quotacheck			xrep_notsupported
+#define xrep_nlinks			xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 883c47b6c6860..c0b99184bb3ef 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -376,7 +376,7 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.type	= ST_FS,
 		.setup	= xchk_setup_nlinks,
 		.scrub	= xchk_nlinks,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_nlinks,
 	},
 };
 
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 52d70d73c26ba..fbadec84f45a2 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -2158,6 +2158,9 @@ DEFINE_XREP_DQUOT_EVENT(xrep_dquot_item_fill_bmap_hole);
 DEFINE_XREP_DQUOT_EVENT(xrep_quotacheck_dquot);
 #endif /* CONFIG_XFS_QUOTA */
 
+DEFINE_SCRUB_NLINKS_DIFF_EVENT(xrep_nlinks_update_inode);
+DEFINE_SCRUB_NLINKS_DIFF_EVENT(xrep_nlinks_unfixable_inode);
+
 #endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
 
 #endif /* _TRACE_XFS_SCRUB_TRACE_H */

[PATCH 01/11] xfs: separate the marking of sick and checked metadata

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Split the setting of the sick and checked masks into separate functions
as part of preparing to add the ability for regular runtime fs code
(i.e. not scrub) to mark metadata structures sick when corruptions are
found.  Improve the documentation of libxfs' requirements for helper
behavior.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_health.h |   16 +++++++++++++-
 fs/xfs/scrub/health.c      |   20 ++++++++++-------
 fs/xfs/xfs_health.c        |   51 +++++++++++++++++++++++++++++++++++++++++++-
 fs/xfs/xfs_mount.c         |    5 +++-
 4 files changed, 81 insertions(+), 11 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index 2bfe2dc404a19..2b40fe8165702 100644
--- a/fs/xfs/libxfs/xfs_health.h
+++ b/fs/xfs/libxfs/xfs_health.h
@@ -111,24 +111,38 @@ struct xfs_fsop_geom;
 				 XFS_SICK_INO_DIR_ZAPPED | \
 				 XFS_SICK_INO_SYMLINK_ZAPPED)
 
-/* These functions must be provided by the xfs implementation. */
+/*
+ * These functions must be provided by the xfs implementation.  Function
+ * behavior with respect to the first argument should be as follows:
+ *
+ * xfs_*_mark_sick:    set the sick flags and do not set checked flags.
+ * xfs_*_mark_checked: set the checked flags.
+ * xfs_*_mark_healthy: clear the sick flags and set the checked flags.
+ *
+ * xfs_*_measure_sickness: return the sick and check status in the provided
+ * out parameters.
+ */
 
 void xfs_fs_mark_sick(struct xfs_mount *mp, unsigned int mask);
+void xfs_fs_mark_checked(struct xfs_mount *mp, unsigned int mask);
 void xfs_fs_mark_healthy(struct xfs_mount *mp, unsigned int mask);
 void xfs_fs_measure_sickness(struct xfs_mount *mp, unsigned int *sick,
 		unsigned int *checked);
 
 void xfs_rt_mark_sick(struct xfs_mount *mp, unsigned int mask);
+void xfs_rt_mark_checked(struct xfs_mount *mp, unsigned int mask);
 void xfs_rt_mark_healthy(struct xfs_mount *mp, unsigned int mask);
 void xfs_rt_measure_sickness(struct xfs_mount *mp, unsigned int *sick,
 		unsigned int *checked);
 
 void xfs_ag_mark_sick(struct xfs_perag *pag, unsigned int mask);
+void xfs_ag_mark_checked(struct xfs_perag *pag, unsigned int mask);
 void xfs_ag_mark_healthy(struct xfs_perag *pag, unsigned int mask);
 void xfs_ag_measure_sickness(struct xfs_perag *pag, unsigned int *sick,
 		unsigned int *checked);
 
 void xfs_inode_mark_sick(struct xfs_inode *ip, unsigned int mask);
+void xfs_inode_mark_checked(struct xfs_inode *ip, unsigned int mask);
 void xfs_inode_mark_healthy(struct xfs_inode *ip, unsigned int mask);
 void xfs_inode_measure_sickness(struct xfs_inode *ip, unsigned int *sick,
 		unsigned int *checked);
diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c
index 42be435227794..0f235501ed8a5 100644
--- a/fs/xfs/scrub/health.c
+++ b/fs/xfs/scrub/health.c
@@ -176,30 +176,34 @@ xchk_update_health(
 	switch (type_to_health_flag[sc->sm->sm_type].group) {
 	case XHG_AG:
 		pag = xfs_perag_get(sc->mp, sc->sm->sm_agno);
-		if (bad)
+		if (bad) {
 			xfs_ag_mark_sick(pag, sc->sick_mask);
-		else
+			xfs_ag_mark_checked(pag, sc->sick_mask);
+		} else
 			xfs_ag_mark_healthy(pag, sc->sick_mask);
 		xfs_perag_put(pag);
 		break;
 	case XHG_INO:
 		if (!sc->ip)
 			return;
-		if (bad)
+		if (bad) {
 			xfs_inode_mark_sick(sc->ip, sc->sick_mask);
-		else
+			xfs_inode_mark_checked(sc->ip, sc->sick_mask);
+		} else
 			xfs_inode_mark_healthy(sc->ip, sc->sick_mask);
 		break;
 	case XHG_FS:
-		if (bad)
+		if (bad) {
 			xfs_fs_mark_sick(sc->mp, sc->sick_mask);
-		else
+			xfs_fs_mark_checked(sc->mp, sc->sick_mask);
+		} else
 			xfs_fs_mark_healthy(sc->mp, sc->sick_mask);
 		break;
 	case XHG_RT:
-		if (bad)
+		if (bad) {
 			xfs_rt_mark_sick(sc->mp, sc->sick_mask);
-		else
+			xfs_rt_mark_checked(sc->mp, sc->sick_mask);
+		} else
 			xfs_rt_mark_healthy(sc->mp, sc->sick_mask);
 		break;
 	default:
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index 111c27a6b1079..f79c332aaa076 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -98,6 +98,18 @@ xfs_fs_mark_sick(
 
 	spin_lock(&mp->m_sb_lock);
 	mp->m_fs_sick |= mask;
+	spin_unlock(&mp->m_sb_lock);
+}
+
+/* Mark per-fs metadata as having been checked. */
+void
+xfs_fs_mark_checked(
+	struct xfs_mount	*mp,
+	unsigned int		mask)
+{
+	ASSERT(!(mask & ~XFS_SICK_FS_PRIMARY));
+
+	spin_lock(&mp->m_sb_lock);
 	mp->m_fs_checked |= mask;
 	spin_unlock(&mp->m_sb_lock);
 }
@@ -141,6 +153,19 @@ xfs_rt_mark_sick(
 
 	spin_lock(&mp->m_sb_lock);
 	mp->m_rt_sick |= mask;
+	spin_unlock(&mp->m_sb_lock);
+}
+
+/* Mark realtime metadata as having been checked. */
+void
+xfs_rt_mark_checked(
+	struct xfs_mount	*mp,
+	unsigned int		mask)
+{
+	ASSERT(!(mask & ~XFS_SICK_RT_PRIMARY));
+	trace_xfs_rt_mark_sick(mp, mask);
+
+	spin_lock(&mp->m_sb_lock);
 	mp->m_rt_checked |= mask;
 	spin_unlock(&mp->m_sb_lock);
 }
@@ -184,6 +209,18 @@ xfs_ag_mark_sick(
 
 	spin_lock(&pag->pag_state_lock);
 	pag->pag_sick |= mask;
+	spin_unlock(&pag->pag_state_lock);
+}
+
+/* Mark per-ag metadata as having been checked. */
+void
+xfs_ag_mark_checked(
+	struct xfs_perag	*pag,
+	unsigned int		mask)
+{
+	ASSERT(!(mask & ~XFS_SICK_AG_PRIMARY));
+
+	spin_lock(&pag->pag_state_lock);
 	pag->pag_checked |= mask;
 	spin_unlock(&pag->pag_state_lock);
 }
@@ -227,7 +264,6 @@ xfs_inode_mark_sick(
 
 	spin_lock(&ip->i_flags_lock);
 	ip->i_sick |= mask;
-	ip->i_checked |= mask;
 	spin_unlock(&ip->i_flags_lock);
 
 	/*
@@ -240,6 +276,19 @@ xfs_inode_mark_sick(
 	spin_unlock(&VFS_I(ip)->i_lock);
 }
 
+/* Mark inode metadata as having been checked. */
+void
+xfs_inode_mark_checked(
+	struct xfs_inode	*ip,
+	unsigned int		mask)
+{
+	ASSERT(!(mask & ~(XFS_SICK_INO_PRIMARY | XFS_SICK_INO_ZAPPED)));
+
+	spin_lock(&ip->i_flags_lock);
+	ip->i_checked |= mask;
+	spin_unlock(&ip->i_flags_lock);
+}
+
 /* Mark parts of an inode healed. */
 void
 xfs_inode_mark_healthy(
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index aed5be5508fe5..469eeab347518 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -497,8 +497,10 @@ xfs_check_summary_counts(
 	if (xfs_is_clean(mp) &&
 	    (mp->m_sb.sb_fdblocks > mp->m_sb.sb_dblocks ||
 	     !xfs_verify_icount(mp, mp->m_sb.sb_icount) ||
-	     mp->m_sb.sb_ifree > mp->m_sb.sb_icount))
+	     mp->m_sb.sb_ifree > mp->m_sb.sb_icount)) {
 		xfs_fs_mark_sick(mp, XFS_SICK_FS_COUNTERS);
+		xfs_fs_mark_checked(mp, XFS_SICK_FS_COUNTERS);
+	}
 
 	/*
 	 * We can safely re-initialise incore superblock counters from the
@@ -1276,6 +1278,7 @@ xfs_force_summary_recalc(
 		return;
 
 	xfs_fs_mark_sick(mp, XFS_SICK_FS_COUNTERS);
+	xfs_fs_mark_checked(mp, XFS_SICK_FS_COUNTERS);
 }
 
 /*

[PATCH 02/11] xfs: report fs corruption errors to the health tracking system

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Whenever we encounter corrupt fs metadata, we should report that to the
health monitoring system for later reporting.  A convenient program for
identifying places to insert xfs_*_mark_sick calls is as follows:

#!/bin/bash

# Detect missing calls to xfs_*_mark_sick

filter=cat
tty -s && filter=less

git grep -B3 EFSCORRUPTED fs/xfs/*.[ch] fs/xfs/libxfs/*.[ch] fs/xfs/scrub/*.[ch] | awk '
BEGIN {
	ignore = 0;
	lineno = 0;
	delete lines;
}
{
	if ($0 == "--") {
		if (!ignore) {
			for (i = 0; i < lineno; i++) {
				print(lines[i]);
			}
			printf("--\n");
		}
		delete lines;
		lineno = 0;
		ignore = 0;
	} else if ($0 ~ /mark_sick/) {
		ignore = 1;
	} else if ($0 ~ /if .fa/) {
		ignore = 1;
	} else if ($0 ~ /failaddr/) {
		ignore = 1;
	} else if ($0 ~ /_verifier_error/) {
		ignore = 1;
	} else if ($0 ~ /^ \* .*EFSCORRUPTED/) {
		ignore = 1;
	} else if ($0 ~ /== -EFSCORRUPTED/) {
		ignore = 1;
	} else if ($0 ~ /!= -EFSCORRUPTED/) {
		ignore = 1;
	} else {
		lines[lineno++] = $0;
	}
}
' | $filter

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_ag.c |    1 +
 1 file changed, 1 insertion(+)


diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index f62ff125a50ac..b857fc54562a7 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -217,6 +217,7 @@ xfs_initialize_perag_data(
 	 */
 	if (fdblocks > sbp->sb_dblocks || ifree > ialloc) {
 		xfs_alert(mp, "AGF corruption. Please run xfs_repair.");
+		xfs_fs_mark_sick(mp, XFS_SICK_FS_COUNTERS);
 		error = -EFSCORRUPTED;
 		goto out;
 	}

[PATCH 03/11] xfs: report ag header corruption errors to the health tracking system

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Whenever we encounter a corrupt AG header, we should report that to the
health monitoring system for later reporting.  Buffer readers that don't
respond to corruption events with a _mark_sick call can be detected with
the following script:

#!/bin/bash

# Detect missing calls to xfs_*_mark_sick

filter=cat
tty -s && filter=less

git grep -A10  -E '( = xfs_trans_read_buf| = xfs_buf_read\()' fs/xfs/*.[ch] fs/xfs/libxfs/*.[ch] | awk '
BEGIN {
	ignore = 0;
	lineno = 0;
	delete lines;
}
{
	if ($0 == "--") {
		if (!ignore) {
			for (i = 0; i < lineno; i++) {
				print(lines[i]);
			}
			printf("--\n");
		}
		delete lines;
		lineno = 0;
		ignore = 0;
	} else if ($0 ~ /mark_sick/) {
		ignore = 1;
	} else {
		lines[lineno++] = $0;
	}
}
' | $filter

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_alloc.c  |    6 ++++++
 fs/xfs/libxfs/xfs_health.h |   13 ++++++++++---
 fs/xfs/libxfs/xfs_ialloc.c |    3 +++
 fs/xfs/libxfs/xfs_sb.c     |    2 ++
 fs/xfs/xfs_health.c        |   17 +++++++++++++++++
 fs/xfs/xfs_inode.c         |   14 ++++++++++++--
 6 files changed, 50 insertions(+), 5 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 3bd0a33fee0a6..1cb2569c43cfc 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -26,6 +26,7 @@
 #include "xfs_ag.h"
 #include "xfs_ag_resv.h"
 #include "xfs_bmap.h"
+#include "xfs_health.h"
 
 struct kmem_cache	*xfs_extfree_item_cache;
 
@@ -755,6 +756,8 @@ xfs_alloc_read_agfl(
 			mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGFL_DADDR(mp)),
 			XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_agfl_buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL);
 	if (error)
 		return error;
 	xfs_buf_set_ref(bp, XFS_AGFL_REF);
@@ -776,6 +779,7 @@ xfs_alloc_update_counters(
 	if (unlikely(be32_to_cpu(agf->agf_freeblks) >
 		     be32_to_cpu(agf->agf_length))) {
 		xfs_buf_mark_corrupt(agbp);
+		xfs_ag_mark_sick(agbp->b_pag, XFS_SICK_AG_AGF);
 		return -EFSCORRUPTED;
 	}
 
@@ -3268,6 +3272,8 @@ xfs_read_agf(
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGF_DADDR(mp)),
 			XFS_FSS_TO_BB(mp, 1), flags, agfbpp, &xfs_agf_buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGF);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index 2b40fe8165702..cd7a1370a1ed8 100644
--- a/fs/xfs/libxfs/xfs_health.h
+++ b/fs/xfs/libxfs/xfs_health.h
@@ -26,9 +26,11 @@
  * and the "sick" field tells us if that piece was found to need repairs.
  * Therefore we can conclude that for a given sick flag value:
  *
- *  - checked && sick  => metadata needs repair
- *  - checked && !sick => metadata is ok
- *  - !checked         => has not been examined since mount
+ *  - checked && sick   => metadata needs repair
+ *  - checked && !sick  => metadata is ok
+ *  - !checked && sick  => errors have been observed during normal operation,
+ *                         but the metadata has not been checked thoroughly
+ *  - !checked && !sick => has not been examined since mount
  */
 
 struct xfs_mount;
@@ -135,6 +137,8 @@ void xfs_rt_mark_healthy(struct xfs_mount *mp, unsigned int mask);
 void xfs_rt_measure_sickness(struct xfs_mount *mp, unsigned int *sick,
 		unsigned int *checked);
 
+void xfs_agno_mark_sick(struct xfs_mount *mp, xfs_agnumber_t agno,
+		unsigned int mask);
 void xfs_ag_mark_sick(struct xfs_perag *pag, unsigned int mask);
 void xfs_ag_mark_checked(struct xfs_perag *pag, unsigned int mask);
 void xfs_ag_mark_healthy(struct xfs_perag *pag, unsigned int mask);
@@ -215,4 +219,7 @@ void xfs_fsop_geom_health(struct xfs_mount *mp, struct xfs_fsop_geom *geo);
 void xfs_ag_geom_health(struct xfs_perag *pag, struct xfs_ag_geometry *ageo);
 void xfs_bulkstat_health(struct xfs_inode *ip, struct xfs_bulkstat *bs);
 
+#define xfs_metadata_is_sick(error) \
+	(unlikely((error) == -EFSCORRUPTED || (error) == -EFSBADCRC))
+
 #endif	/* __XFS_HEALTH_H__ */
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 2361a22035b0c..2531b4c08915d 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -27,6 +27,7 @@
 #include "xfs_log.h"
 #include "xfs_rmap.h"
 #include "xfs_ag.h"
+#include "xfs_health.h"
 
 /*
  * Lookup a record by ino in the btree given by cur.
@@ -2604,6 +2605,8 @@ xfs_read_agi(
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGI_DADDR(mp)),
 			XFS_FSS_TO_BB(mp, 1), 0, agibpp, &xfs_agi_buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
 	if (error)
 		return error;
 	if (tp)
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 4a9e8588f4c98..7f2a5aee0ab83 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -1290,6 +1290,8 @@ xfs_sb_read_secondary(
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
 			XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_sb_buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_agno_mark_sick(mp, agno, XFS_SICK_AG_SB);
 	if (error)
 		return error;
 	xfs_buf_set_ref(bp, XFS_SSB_REF);
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index f79c332aaa076..229a51cef47ee 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -198,6 +198,23 @@ xfs_rt_measure_sickness(
 	spin_unlock(&mp->m_sb_lock);
 }
 
+/* Mark unhealthy per-ag metadata given a raw AG number. */
+void
+xfs_agno_mark_sick(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno,
+	unsigned int		mask)
+{
+	struct xfs_perag	*pag = xfs_perag_get(mp, agno);
+
+	/* per-ag structure not set up yet? */
+	if (!pag)
+		return;
+
+	xfs_ag_mark_sick(pag, mask);
+	xfs_perag_put(pag);
+}
+
 /* Mark unhealthy per-ag metadata. */
 void
 xfs_ag_mark_sick(
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index ed620597d289b..0ba41fa29e9e7 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -802,6 +802,8 @@ xfs_init_new_inode(
 	 */
 	if ((pip && ino == pip->i_ino) || !xfs_verify_dir_ino(mp, ino)) {
 		xfs_alert(mp, "Allocated a known in-use inode 0x%llx!", ino);
+		xfs_agno_mark_sick(mp, XFS_INO_TO_AGNO(mp, ino),
+				XFS_SICK_AG_INOBT);
 		return -EFSCORRUPTED;
 	}
 
@@ -1983,6 +1985,7 @@ xfs_iunlink_update_bucket(
 	 */
 	if (old_value == new_agino) {
 		xfs_buf_mark_corrupt(agibp);
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
 		return -EFSCORRUPTED;
 	}
 
@@ -2032,11 +2035,14 @@ xfs_iunlink_reload_next(
 	 */
 	ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, next_agino);
 	error = xfs_iget(mp, tp, ino, XFS_IGET_UNTRUSTED, 0, &next_ip);
-	if (error)
+	if (error) {
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
 		return error;
+	}
 
 	/* If this is not an unlinked inode, something is very wrong. */
 	if (VFS_I(next_ip)->i_nlink != 0) {
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
 		error = -EFSCORRUPTED;
 		goto rele;
 	}
@@ -2074,6 +2080,7 @@ xfs_iunlink_insert_inode(
 	if (next_agino == agino ||
 	    !xfs_verify_agino_or_null(pag, next_agino)) {
 		xfs_buf_mark_corrupt(agibp);
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
 		return -EFSCORRUPTED;
 	}
 
@@ -2161,6 +2168,7 @@ xfs_iunlink_remove_inode(
 	if (!xfs_verify_agino(pag, head_agino)) {
 		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
 				agi, sizeof(*agi));
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
 		return -EFSCORRUPTED;
 	}
 
@@ -2189,8 +2197,10 @@ xfs_iunlink_remove_inode(
 		struct xfs_inode	*prev_ip;
 
 		prev_ip = xfs_iunlink_lookup(pag, ip->i_prev_unlinked);
-		if (!prev_ip)
+		if (!prev_ip) {
+			xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
 			return -EFSCORRUPTED;
+		}
 
 		error = xfs_iunlink_log_inode(tp, prev_ip, pag,
 				ip->i_next_unlinked);

[PATCH 04/11] xfs: report block map corruption errors to the health tracking system

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Whenever we encounter a corrupt block mapping, we should report that to
the health monitoring system for later reporting.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_bmap.c   |   35 +++++++++++++++++++++++++++++------
 fs/xfs/libxfs/xfs_health.h |    1 +
 fs/xfs/xfs_health.c        |   26 ++++++++++++++++++++++++++
 fs/xfs/xfs_iomap.c         |   15 ++++++++++++---
 fs/xfs/xfs_reflink.c       |    6 +++++-
 5 files changed, 73 insertions(+), 10 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 523926fe50eb0..752e424600807 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -36,6 +36,7 @@
 #include "xfs_refcount.h"
 #include "xfs_icache.h"
 #include "xfs_iomap.h"
+#include "xfs_health.h"
 
 struct kmem_cache		*xfs_bmap_intent_cache;
 
@@ -960,6 +961,7 @@ xfs_bmap_add_attrfork_local(
 
 	/* should only be called for types that support local format data */
 	ASSERT(0);
+	xfs_bmap_mark_sick(ip, XFS_ATTR_FORK);
 	return -EFSCORRUPTED;
 }
 
@@ -1143,6 +1145,7 @@ xfs_iread_bmbt_block(
 				(unsigned long long)ip->i_ino);
 		xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, block,
 				sizeof(*block), __this_address);
+		xfs_bmap_mark_sick(ip, whichfork);
 		return -EFSCORRUPTED;
 	}
 
@@ -1158,6 +1161,7 @@ xfs_iread_bmbt_block(
 			xfs_inode_verifier_error(ip, -EFSCORRUPTED,
 					"xfs_iread_extents(2)", frp,
 					sizeof(*frp), fa);
+			xfs_bmap_mark_sick(ip, whichfork);
 			return xfs_bmap_complain_bad_rec(ip, whichfork, fa,
 					&new);
 		}
@@ -1213,6 +1217,8 @@ xfs_iread_extents(
 	smp_store_release(&ifp->if_needextents, 0);
 	return 0;
 out:
+	if (xfs_metadata_is_sick(error))
+		xfs_bmap_mark_sick(ip, whichfork);
 	xfs_iext_destroy(ifp);
 	return error;
 }
@@ -1292,6 +1298,7 @@ xfs_bmap_last_before(
 		break;
 	default:
 		ASSERT(0);
+		xfs_bmap_mark_sick(ip, whichfork);
 		return -EFSCORRUPTED;
 	}
 
@@ -3885,12 +3892,16 @@ xfs_bmapi_read(
 	ASSERT(!(flags & ~(XFS_BMAPI_ATTRFORK | XFS_BMAPI_ENTIRE)));
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED|XFS_ILOCK_EXCL));
 
-	if (WARN_ON_ONCE(!ifp))
+	if (WARN_ON_ONCE(!ifp)) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		return -EFSCORRUPTED;
+	}
 
 	if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) ||
-	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT))
+	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		return -EFSCORRUPTED;
+	}
 
 	if (xfs_is_shutdown(mp))
 		return -EIO;
@@ -4371,6 +4382,7 @@ xfs_bmapi_write(
 
 	if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) ||
 	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		return -EFSCORRUPTED;
 	}
 
@@ -4598,9 +4610,11 @@ xfs_bmapi_convert_delalloc(
 	error = -ENOSPC;
 	if (WARN_ON_ONCE(bma.blkno == NULLFSBLOCK))
 		goto out_finish;
-	error = -EFSCORRUPTED;
-	if (WARN_ON_ONCE(!xfs_valid_startblock(ip, bma.got.br_startblock)))
+	if (WARN_ON_ONCE(!xfs_valid_startblock(ip, bma.got.br_startblock))) {
+		xfs_bmap_mark_sick(ip, whichfork);
+		error = -EFSCORRUPTED;
 		goto out_finish;
+	}
 
 	XFS_STATS_ADD(mp, xs_xstrat_bytes, XFS_FSB_TO_B(mp, bma.length));
 	XFS_STATS_INC(mp, xs_xstrat_quick);
@@ -4659,6 +4673,7 @@ xfs_bmapi_remap(
 
 	if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) ||
 	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		return -EFSCORRUPTED;
 	}
 
@@ -5271,8 +5286,10 @@ __xfs_bunmapi(
 	whichfork = xfs_bmapi_whichfork(flags);
 	ASSERT(whichfork != XFS_COW_FORK);
 	ifp = xfs_ifork_ptr(ip, whichfork);
-	if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)))
+	if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp))) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		return -EFSCORRUPTED;
+	}
 	if (xfs_is_shutdown(mp))
 		return -EIO;
 
@@ -5743,6 +5760,7 @@ xfs_bmap_collapse_extents(
 
 	if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) ||
 	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		return -EFSCORRUPTED;
 	}
 
@@ -5858,6 +5876,7 @@ xfs_bmap_insert_extents(
 
 	if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) ||
 	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		return -EFSCORRUPTED;
 	}
 
@@ -5961,6 +5980,7 @@ xfs_bmap_split_extent(
 
 	if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) ||
 	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		return -EFSCORRUPTED;
 	}
 
@@ -6143,8 +6163,10 @@ xfs_bmap_finish_one(
 			bmap->br_startoff, bmap->br_blockcount,
 			bmap->br_state);
 
-	if (WARN_ON_ONCE(bi->bi_whichfork != XFS_DATA_FORK))
+	if (WARN_ON_ONCE(bi->bi_whichfork != XFS_DATA_FORK)) {
+		xfs_bmap_mark_sick(bi->bi_owner, bi->bi_whichfork);
 		return -EFSCORRUPTED;
+	}
 
 	if (XFS_TEST_ERROR(false, tp->t_mountp,
 			XFS_ERRTAG_BMAP_FINISH_ONE))
@@ -6162,6 +6184,7 @@ xfs_bmap_finish_one(
 		break;
 	default:
 		ASSERT(0);
+		xfs_bmap_mark_sick(bi->bi_owner, bi->bi_whichfork);
 		error = -EFSCORRUPTED;
 	}
 
diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index cd7a1370a1ed8..50515920c9578 100644
--- a/fs/xfs/libxfs/xfs_health.h
+++ b/fs/xfs/libxfs/xfs_health.h
@@ -152,6 +152,7 @@ void xfs_inode_measure_sickness(struct xfs_inode *ip, unsigned int *sick,
 		unsigned int *checked);
 
 void xfs_health_unmount(struct xfs_mount *mp);
+void xfs_bmap_mark_sick(struct xfs_inode *ip, int whichfork);
 
 /* Now some helpers. */
 
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index 229a51cef47ee..9a86c1491e28e 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -465,3 +465,29 @@ xfs_bulkstat_health(
 			bs->bs_sick |= m->ioctl_mask;
 	}
 }
+
+/* Mark a block mapping sick. */
+void
+xfs_bmap_mark_sick(
+	struct xfs_inode	*ip,
+	int			whichfork)
+{
+	unsigned int		mask;
+
+	switch (whichfork) {
+	case XFS_DATA_FORK:
+		mask = XFS_SICK_INO_BMBTD;
+		break;
+	case XFS_ATTR_FORK:
+		mask = XFS_SICK_INO_BMBTA;
+		break;
+	case XFS_COW_FORK:
+		mask = XFS_SICK_INO_BMBTC;
+		break;
+	default:
+		ASSERT(0);
+		return;
+	}
+
+	xfs_inode_mark_sick(ip, mask);
+}
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 18c8f168b1532..0ff46e3997e0e 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -27,6 +27,7 @@
 #include "xfs_dquot_item.h"
 #include "xfs_dquot.h"
 #include "xfs_reflink.h"
+#include "xfs_health.h"
 
 #define XFS_ALLOC_ALIGN(mp, off) \
 	(((off) >> mp->m_allocsize_log) << mp->m_allocsize_log)
@@ -45,6 +46,7 @@ xfs_alert_fsblock_zero(
 		(unsigned long long)imap->br_startoff,
 		(unsigned long long)imap->br_blockcount,
 		imap->br_state);
+	xfs_bmap_mark_sick(ip, XFS_DATA_FORK);
 	return -EFSCORRUPTED;
 }
 
@@ -99,8 +101,10 @@ xfs_bmbt_to_iomap(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_buftarg	*target = xfs_inode_buftarg(ip);
 
-	if (unlikely(!xfs_valid_startblock(ip, imap->br_startblock)))
+	if (unlikely(!xfs_valid_startblock(ip, imap->br_startblock))) {
+		xfs_bmap_mark_sick(ip, XFS_DATA_FORK);
 		return xfs_alert_fsblock_zero(ip, imap);
+	}
 
 	if (imap->br_startblock == HOLESTARTBLOCK) {
 		iomap->addr = IOMAP_NULL_ADDR;
@@ -325,8 +329,10 @@ xfs_iomap_write_direct(
 		goto out_unlock;
 	}
 
-	if (unlikely(!xfs_valid_startblock(ip, imap->br_startblock)))
+	if (unlikely(!xfs_valid_startblock(ip, imap->br_startblock))) {
+		xfs_bmap_mark_sick(ip, XFS_DATA_FORK);
 		error = xfs_alert_fsblock_zero(ip, imap);
+	}
 
 out_unlock:
 	*seq = xfs_iomap_inode_sequence(ip, 0);
@@ -639,8 +645,10 @@ xfs_iomap_write_unwritten(
 		if (error)
 			return error;
 
-		if (unlikely(!xfs_valid_startblock(ip, imap.br_startblock)))
+		if (unlikely(!xfs_valid_startblock(ip, imap.br_startblock))) {
+			xfs_bmap_mark_sick(ip, XFS_DATA_FORK);
 			return xfs_alert_fsblock_zero(ip, &imap);
+		}
 
 		if ((numblks_fsb = imap.br_blockcount) == 0) {
 			/*
@@ -986,6 +994,7 @@ xfs_buffered_write_iomap_begin(
 
 	if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(&ip->i_df)) ||
 	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
+		xfs_bmap_mark_sick(ip, XFS_DATA_FORK);
 		error = -EFSCORRUPTED;
 		goto out_unlock;
 	}
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index d5ca8bcae65b6..ad1f235a3c492 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -29,6 +29,7 @@
 #include "xfs_iomap.h"
 #include "xfs_ag.h"
 #include "xfs_ag_resv.h"
+#include "xfs_health.h"
 
 /*
  * Copy on Write of Shared Blocks
@@ -1227,8 +1228,10 @@ xfs_reflink_remap_extent(
 	 * extent if they're both holes or both the same physical extent.
 	 */
 	if (dmap->br_startblock == smap.br_startblock) {
-		if (dmap->br_state != smap.br_state)
+		if (dmap->br_state != smap.br_state) {
+			xfs_bmap_mark_sick(ip, XFS_DATA_FORK);
 			error = -EFSCORRUPTED;
+		}
 		goto out_cancel;
 	}
 
@@ -1391,6 +1394,7 @@ xfs_reflink_remap_blocks(
 		ASSERT(nimaps == 1 && imap.br_startoff == srcoff);
 		if (imap.br_startblock == DELAYSTARTBLOCK) {
 			ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
+			xfs_bmap_mark_sick(src, XFS_DATA_FORK);
 			error = -EFSCORRUPTED;
 			break;
 		}

[PATCH 05/11] xfs: report btree block corruption errors to the health system

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Whenever we encounter corrupt btree blocks, we should report that to the
health monitoring system for later reporting.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_alloc.c    |    2 ++
 fs/xfs/libxfs/xfs_bmap.c     |    6 ++++++
 fs/xfs/libxfs/xfs_btree.c    |   25 ++++++++++++++++++++++---
 fs/xfs/libxfs/xfs_health.h   |    2 ++
 fs/xfs/libxfs/xfs_ialloc.c   |    1 +
 fs/xfs/libxfs/xfs_refcount.c |    6 +++++-
 fs/xfs/libxfs/xfs_rmap.c     |    6 +++++-
 fs/xfs/xfs_health.c          |   38 ++++++++++++++++++++++++++++++++++++++
 8 files changed, 81 insertions(+), 5 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 1cb2569c43cfc..2464b64b1cb4e 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -275,6 +275,7 @@ xfs_alloc_complain_bad_rec(
 	xfs_warn(mp,
 		"start block 0x%x block count 0x%x", irec->ar_startblock,
 		irec->ar_blockcount);
+	xfs_btree_mark_sick(cur);
 	return -EFSCORRUPTED;
 }
 
@@ -2702,6 +2703,7 @@ xfs_exact_minlen_extent_available(
 		goto out;
 
 	if (*stat == 0) {
+		xfs_btree_mark_sick(cnt_cur);
 		error = -EFSCORRUPTED;
 		goto out;
 	}
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 752e424600807..61918ca34658b 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -368,6 +368,8 @@ xfs_bmap_check_leaf_extents(
 			error = xfs_btree_read_bufl(mp, NULL, bno, &bp,
 						XFS_BMAP_BTREE_REF,
 						&xfs_bmbt_buf_ops);
+			if (xfs_metadata_is_sick(error))
+				xfs_btree_mark_sick(cur);
 			if (error)
 				goto error_norelse;
 		}
@@ -454,6 +456,8 @@ xfs_bmap_check_leaf_extents(
 			error = xfs_btree_read_bufl(mp, NULL, bno, &bp,
 						XFS_BMAP_BTREE_REF,
 						&xfs_bmbt_buf_ops);
+			if (xfs_metadata_is_sick(error))
+				xfs_btree_mark_sick(cur);
 			if (error)
 				goto error_norelse;
 		}
@@ -568,6 +572,8 @@ xfs_bmap_btree_to_extents(
 #endif
 	error = xfs_btree_read_bufl(mp, tp, cbno, &cbp, XFS_BMAP_BTREE_REF,
 				&xfs_bmbt_buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_btree_mark_sick(cur);
 	if (error)
 		return error;
 	cblock = XFS_BUF_TO_BLOCK(cbp);
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index ea8d3659df208..51d0a569e8216 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -27,6 +27,7 @@
 #include "xfs_bmap_btree.h"
 #include "xfs_rmap_btree.h"
 #include "xfs_refcount_btree.h"
+#include "xfs_health.h"
 
 /*
  * Btree magic numbers.
@@ -177,6 +178,7 @@ xfs_btree_check_lblock(
 	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BTREE_CHECK_LBLOCK)) {
 		if (bp)
 			trace_xfs_btree_corrupt(bp, _RET_IP_);
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
 	}
 	return 0;
@@ -243,6 +245,7 @@ xfs_btree_check_sblock(
 	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BTREE_CHECK_SBLOCK)) {
 		if (bp)
 			trace_xfs_btree_corrupt(bp, _RET_IP_);
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
 	}
 	return 0;
@@ -318,6 +321,7 @@ xfs_btree_check_ptr(
 				level, index);
 	}
 
+	xfs_btree_mark_sick(cur);
 	return -EFSCORRUPTED;
 }
 
@@ -498,6 +502,8 @@ xfs_btree_dup_cursor(
 						   xfs_buf_daddr(bp), mp->m_bsize,
 						   0, &bp,
 						   cur->bc_ops->buf_ops);
+			if (xfs_metadata_is_sick(error))
+				xfs_btree_mark_sick(new);
 			if (error) {
 				xfs_btree_del_cursor(new, error);
 				*ncur = NULL;
@@ -1351,6 +1357,8 @@ xfs_btree_read_buf_block(
 	error = xfs_trans_read_buf(mp, cur->bc_tp, mp->m_ddev_targp, d,
 				   mp->m_bsize, flags, bpp,
 				   cur->bc_ops->buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_btree_mark_sick(cur);
 	if (error)
 		return error;
 
@@ -1661,6 +1669,7 @@ xfs_btree_increment(
 		if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
 			goto out0;
 		ASSERT(0);
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -1754,6 +1763,7 @@ xfs_btree_decrement(
 		if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
 			goto out0;
 		ASSERT(0);
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -1846,6 +1856,7 @@ xfs_btree_lookup_get_block(
 	*blkp = NULL;
 	xfs_buf_mark_corrupt(bp);
 	xfs_trans_brelse(cur->bc_tp, bp);
+	xfs_btree_mark_sick(cur);
 	return -EFSCORRUPTED;
 }
 
@@ -1892,8 +1903,10 @@ xfs_btree_lookup(
 	XFS_BTREE_STATS_INC(cur, lookup);
 
 	/* No such thing as a zero-level tree. */
-	if (XFS_IS_CORRUPT(cur->bc_mp, cur->bc_nlevels == 0))
+	if (XFS_IS_CORRUPT(cur->bc_mp, cur->bc_nlevels == 0)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	block = NULL;
 	keyno = 0;
@@ -1936,6 +1949,7 @@ xfs_btree_lookup(
 							XFS_ERRLEVEL_LOW,
 							cur->bc_mp, block,
 							sizeof(*block));
+					xfs_btree_mark_sick(cur);
 					return -EFSCORRUPTED;
 				}
 
@@ -4369,12 +4383,16 @@ xfs_btree_visit_block(
 	 */
 	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
 		if (be64_to_cpu(rptr.l) == XFS_DADDR_TO_FSB(cur->bc_mp,
-							xfs_buf_daddr(bp)))
+							xfs_buf_daddr(bp))) {
+			xfs_btree_mark_sick(cur);
 			return -EFSCORRUPTED;
+		}
 	} else {
 		if (be32_to_cpu(rptr.s) == xfs_daddr_to_agbno(cur->bc_mp,
-							xfs_buf_daddr(bp)))
+							xfs_buf_daddr(bp))) {
+			xfs_btree_mark_sick(cur);
 			return -EFSCORRUPTED;
+		}
 	}
 	return xfs_btree_lookup_get_block(cur, level, &rptr, &block);
 }
@@ -5233,6 +5251,7 @@ xfs_btree_goto_left_edge(
 		return error;
 	if (stat != 0) {
 		ASSERT(0);
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
 	}
 
diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index 50515920c9578..0876c767d9ddc 100644
--- a/fs/xfs/libxfs/xfs_health.h
+++ b/fs/xfs/libxfs/xfs_health.h
@@ -37,6 +37,7 @@ struct xfs_mount;
 struct xfs_perag;
 struct xfs_inode;
 struct xfs_fsop_geom;
+struct xfs_btree_cur;
 
 /* Observable health issues for metadata spanning the entire filesystem. */
 #define XFS_SICK_FS_COUNTERS	(1 << 0)  /* summary counters */
@@ -153,6 +154,7 @@ void xfs_inode_measure_sickness(struct xfs_inode *ip, unsigned int *sick,
 
 void xfs_health_unmount(struct xfs_mount *mp);
 void xfs_bmap_mark_sick(struct xfs_inode *ip, int whichfork);
+void xfs_btree_mark_sick(struct xfs_btree_cur *cur);
 
 /* Now some helpers. */
 
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 2531b4c08915d..91584e96f05f6 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -148,6 +148,7 @@ xfs_inobt_complain_bad_rec(
 "start inode 0x%x, count 0x%x, free 0x%x freemask 0x%llx, holemask 0x%x",
 		irec->ir_startino, irec->ir_count, irec->ir_freecount,
 		irec->ir_free, irec->ir_holemask);
+	xfs_btree_mark_sick(cur);
 	return -EFSCORRUPTED;
 }
 
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 6709a7f8bad5a..91f1066f408b9 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -23,6 +23,7 @@
 #include "xfs_refcount.h"
 #include "xfs_rmap.h"
 #include "xfs_ag.h"
+#include "xfs_health.h"
 
 struct kmem_cache	*xfs_refcount_intent_cache;
 
@@ -156,6 +157,7 @@ xfs_refcount_complain_bad_rec(
 	xfs_warn(mp,
 		"Start block 0x%x, block count 0x%x, references 0x%x",
 		irec->rc_startblock, irec->rc_blockcount, irec->rc_refcount);
+	xfs_btree_mark_sick(cur);
 	return -EFSCORRUPTED;
 }
 
@@ -1889,8 +1891,10 @@ xfs_refcount_recover_extent(
 	struct xfs_refcount_recovery	*rr;
 
 	if (XFS_IS_CORRUPT(cur->bc_mp,
-			   be32_to_cpu(rec->refc.rc_refcount) != 1))
+			   be32_to_cpu(rec->refc.rc_refcount) != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	rr = kmalloc(sizeof(struct xfs_refcount_recovery),
 			GFP_KERNEL | __GFP_NOFAIL);
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 76bf7f48cb5ac..76a2e47b8a8ee 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -23,6 +23,7 @@
 #include "xfs_error.h"
 #include "xfs_inode.h"
 #include "xfs_ag.h"
+#include "xfs_health.h"
 
 struct kmem_cache	*xfs_rmap_intent_cache;
 
@@ -56,8 +57,10 @@ xfs_rmap_lookup_le(
 	error = xfs_rmap_get_rec(cur, irec, &get_stat);
 	if (error)
 		return error;
-	if (!get_stat)
+	if (!get_stat) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	return 0;
 }
@@ -277,6 +280,7 @@ xfs_rmap_complain_bad_rec(
 		"Owner 0x%llx, flags 0x%x, start block 0x%x block count 0x%x",
 		irec->rm_owner, irec->rm_flags, irec->rm_startblock,
 		irec->rm_blockcount);
+	xfs_btree_mark_sick(cur);
 	return -EFSCORRUPTED;
 }
 
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index 9a86c1491e28e..27a27e27a2316 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -14,6 +14,7 @@
 #include "xfs_trace.h"
 #include "xfs_health.h"
 #include "xfs_ag.h"
+#include "xfs_btree.h"
 
 /*
  * Warn about metadata corruption that we detected but haven't fixed, and
@@ -491,3 +492,40 @@ xfs_bmap_mark_sick(
 
 	xfs_inode_mark_sick(ip, mask);
 }
+
+/* Record observations of btree corruption with the health tracking system. */
+void
+xfs_btree_mark_sick(
+	struct xfs_btree_cur		*cur)
+{
+	unsigned int			mask;
+
+	switch (cur->bc_btnum) {
+	case XFS_BTNUM_BMAP:
+		xfs_bmap_mark_sick(cur->bc_ino.ip, cur->bc_ino.whichfork);
+		return;
+	case XFS_BTNUM_BNO:
+		mask = XFS_SICK_AG_BNOBT;
+		break;
+	case XFS_BTNUM_CNT:
+		mask = XFS_SICK_AG_CNTBT;
+		break;
+	case XFS_BTNUM_INO:
+		mask = XFS_SICK_AG_INOBT;
+		break;
+	case XFS_BTNUM_FINO:
+		mask = XFS_SICK_AG_FINOBT;
+		break;
+	case XFS_BTNUM_RMAP:
+		mask = XFS_SICK_AG_RMAPBT;
+		break;
+	case XFS_BTNUM_REFC:
+		mask = XFS_SICK_AG_REFCNTBT;
+		break;
+	default:
+		ASSERT(0);
+		return;
+	}
+
+	xfs_ag_mark_sick(cur->bc_ag.pag, mask);
+}

[PATCH 06/11] xfs: report dir/attr block corruption errors to the health system

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Whenever we encounter corrupt directory or extended attribute blocks, we
should report that to the health monitoring system for later reporting.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_attr_leaf.c   |    4 ++++
 fs/xfs/libxfs/xfs_attr_remote.c |   27 ++++++++++++++++-----------
 fs/xfs/libxfs/xfs_da_btree.c    |   37 ++++++++++++++++++++++++++++++++-----
 fs/xfs/libxfs/xfs_dir2.c        |    5 ++++-
 fs/xfs/libxfs/xfs_dir2_block.c  |    2 ++
 fs/xfs/libxfs/xfs_dir2_data.c   |    3 +++
 fs/xfs/libxfs/xfs_dir2_leaf.c   |    3 +++
 fs/xfs/libxfs/xfs_dir2_node.c   |    7 +++++++
 fs/xfs/libxfs/xfs_health.h      |    3 +++
 fs/xfs/xfs_attr_inactive.c      |    4 ++++
 fs/xfs/xfs_attr_list.c          |    9 ++++++++-
 fs/xfs/xfs_health.c             |   39 +++++++++++++++++++++++++++++++++++++++
 12 files changed, 125 insertions(+), 18 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 5d1ab4978f329..94893f19ee187 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -29,6 +29,7 @@
 #include "xfs_log.h"
 #include "xfs_ag.h"
 #include "xfs_errortag.h"
+#include "xfs_health.h"
 
 
 /*
@@ -2414,6 +2415,7 @@ xfs_attr3_leaf_lookup_int(
 	entries = xfs_attr3_leaf_entryp(leaf);
 	if (ichdr.count >= args->geo->blksize / 8) {
 		xfs_buf_mark_corrupt(bp);
+		xfs_da_mark_sick(args);
 		return -EFSCORRUPTED;
 	}
 
@@ -2433,10 +2435,12 @@ xfs_attr3_leaf_lookup_int(
 	}
 	if (!(probe >= 0 && (!ichdr.count || probe < ichdr.count))) {
 		xfs_buf_mark_corrupt(bp);
+		xfs_da_mark_sick(args);
 		return -EFSCORRUPTED;
 	}
 	if (!(span <= 4 || be32_to_cpu(entry->hashval) == hashval)) {
 		xfs_buf_mark_corrupt(bp);
+		xfs_da_mark_sick(args);
 		return -EFSCORRUPTED;
 	}
 
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index d440393b40eb8..b18a3cf44192e 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -22,6 +22,7 @@
 #include "xfs_attr_remote.h"
 #include "xfs_trace.h"
 #include "xfs_error.h"
+#include "xfs_health.h"
 
 #define ATTR_RMTVALUE_MAPSIZE	1	/* # of map entries at once */
 
@@ -276,17 +277,18 @@ xfs_attr3_rmt_hdr_set(
  */
 STATIC int
 xfs_attr_rmtval_copyout(
-	struct xfs_mount *mp,
-	struct xfs_buf	*bp,
-	xfs_ino_t	ino,
-	int		*offset,
-	int		*valuelen,
-	uint8_t		**dst)
+	struct xfs_mount	*mp,
+	struct xfs_buf		*bp,
+	struct xfs_inode	*dp,
+	int			*offset,
+	int			*valuelen,
+	uint8_t			**dst)
 {
-	char		*src = bp->b_addr;
-	xfs_daddr_t	bno = xfs_buf_daddr(bp);
-	int		len = BBTOB(bp->b_length);
-	int		blksize = mp->m_attr_geo->blksize;
+	char			*src = bp->b_addr;
+	xfs_ino_t		ino = dp->i_ino;
+	xfs_daddr_t		bno = xfs_buf_daddr(bp);
+	int			len = BBTOB(bp->b_length);
+	int			blksize = mp->m_attr_geo->blksize;
 
 	ASSERT(len >= blksize);
 
@@ -302,6 +304,7 @@ xfs_attr_rmtval_copyout(
 				xfs_alert(mp,
 "remote attribute header mismatch bno/off/len/owner (0x%llx/0x%x/Ox%x/0x%llx)",
 					bno, *offset, byte_cnt, ino);
+				xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
 				return -EFSCORRUPTED;
 			}
 			hdr_size = sizeof(struct xfs_attr3_rmt_hdr);
@@ -418,10 +421,12 @@ xfs_attr_rmtval_get(
 			dblkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount);
 			error = xfs_buf_read(mp->m_ddev_targp, dblkno, dblkcnt,
 					0, &bp, &xfs_attr3_rmt_buf_ops);
+			if (xfs_metadata_is_sick(error))
+				xfs_dirattr_mark_sick(args->dp, XFS_ATTR_FORK);
 			if (error)
 				return error;
 
-			error = xfs_attr_rmtval_copyout(mp, bp, args->dp->i_ino,
+			error = xfs_attr_rmtval_copyout(mp, bp, args->dp,
 							&offset, &valuelen,
 							&dst);
 			xfs_buf_relse(bp);
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 5457188bb4deb..21fb8aff40df7 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -23,6 +23,7 @@
 #include "xfs_buf_item.h"
 #include "xfs_log.h"
 #include "xfs_errortag.h"
+#include "xfs_health.h"
 
 /*
  * xfs_da_btree.c
@@ -352,6 +353,8 @@ const struct xfs_buf_ops xfs_da3_node_buf_ops = {
 static int
 xfs_da3_node_set_type(
 	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
+	int			whichfork,
 	struct xfs_buf		*bp)
 {
 	struct xfs_da_blkinfo	*info = bp->b_addr;
@@ -373,6 +376,7 @@ xfs_da3_node_set_type(
 		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, tp->t_mountp,
 				info, sizeof(*info));
 		xfs_trans_brelse(tp, bp);
+		xfs_dirattr_mark_sick(dp, whichfork);
 		return -EFSCORRUPTED;
 	}
 }
@@ -391,7 +395,7 @@ xfs_da3_node_read(
 			&xfs_da3_node_buf_ops);
 	if (error || !*bpp || !tp)
 		return error;
-	return xfs_da3_node_set_type(tp, *bpp);
+	return xfs_da3_node_set_type(tp, dp, whichfork, *bpp);
 }
 
 int
@@ -408,6 +412,8 @@ xfs_da3_node_read_mapped(
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, mappedbno,
 			XFS_FSB_TO_BB(mp, xfs_dabuf_nfsb(mp, whichfork)), 0,
 			bpp, &xfs_da3_node_buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_dirattr_mark_sick(dp, whichfork);
 	if (error || !*bpp)
 		return error;
 
@@ -418,7 +424,7 @@ xfs_da3_node_read_mapped(
 
 	if (!tp)
 		return 0;
-	return xfs_da3_node_set_type(tp, *bpp);
+	return xfs_da3_node_set_type(tp, dp, whichfork, *bpp);
 }
 
 /*
@@ -631,6 +637,7 @@ xfs_da3_split(
 	if (node->hdr.info.forw) {
 		if (be32_to_cpu(node->hdr.info.forw) != addblk->blkno) {
 			xfs_buf_mark_corrupt(oldblk->bp);
+			xfs_da_mark_sick(state->args);
 			error = -EFSCORRUPTED;
 			goto out;
 		}
@@ -644,6 +651,7 @@ xfs_da3_split(
 	if (node->hdr.info.back) {
 		if (be32_to_cpu(node->hdr.info.back) != addblk->blkno) {
 			xfs_buf_mark_corrupt(oldblk->bp);
+			xfs_da_mark_sick(state->args);
 			error = -EFSCORRUPTED;
 			goto out;
 		}
@@ -1635,6 +1643,7 @@ xfs_da3_node_lookup_int(
 
 		if (magic != XFS_DA_NODE_MAGIC && magic != XFS_DA3_NODE_MAGIC) {
 			xfs_buf_mark_corrupt(blk->bp);
+			xfs_da_mark_sick(args);
 			return -EFSCORRUPTED;
 		}
 
@@ -1650,6 +1659,7 @@ xfs_da3_node_lookup_int(
 		/* Tree taller than we can handle; bail out! */
 		if (nodehdr.level >= XFS_DA_NODE_MAXDEPTH) {
 			xfs_buf_mark_corrupt(blk->bp);
+			xfs_da_mark_sick(args);
 			return -EFSCORRUPTED;
 		}
 
@@ -1658,6 +1668,7 @@ xfs_da3_node_lookup_int(
 			expected_level = nodehdr.level - 1;
 		else if (expected_level != nodehdr.level) {
 			xfs_buf_mark_corrupt(blk->bp);
+			xfs_da_mark_sick(args);
 			return -EFSCORRUPTED;
 		} else
 			expected_level--;
@@ -1709,12 +1720,16 @@ xfs_da3_node_lookup_int(
 		}
 
 		/* We can't point back to the root. */
-		if (XFS_IS_CORRUPT(dp->i_mount, blkno == args->geo->leafblk))
+		if (XFS_IS_CORRUPT(dp->i_mount, blkno == args->geo->leafblk)) {
+			xfs_da_mark_sick(args);
 			return -EFSCORRUPTED;
+		}
 	}
 
-	if (XFS_IS_CORRUPT(dp->i_mount, expected_level != 0))
+	if (XFS_IS_CORRUPT(dp->i_mount, expected_level != 0)) {
+		xfs_da_mark_sick(args);
 		return -EFSCORRUPTED;
+	}
 
 	/*
 	 * A leaf block that ends in the hashval that we are interested in
@@ -1732,6 +1747,7 @@ xfs_da3_node_lookup_int(
 			args->blkno = blk->blkno;
 		} else {
 			ASSERT(0);
+			xfs_da_mark_sick(args);
 			return -EFSCORRUPTED;
 		}
 		if (((retval == -ENOENT) || (retval == -ENOATTR)) &&
@@ -2297,8 +2313,10 @@ xfs_da3_swap_lastblock(
 	error = xfs_bmap_last_before(tp, dp, &lastoff, w);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(mp, lastoff == 0))
+	if (XFS_IS_CORRUPT(mp, lastoff == 0)) {
+		xfs_da_mark_sick(args);
 		return -EFSCORRUPTED;
+	}
 	/*
 	 * Read the last block in the btree space.
 	 */
@@ -2348,6 +2366,7 @@ xfs_da3_swap_lastblock(
 		if (XFS_IS_CORRUPT(mp,
 				   be32_to_cpu(sib_info->forw) != last_blkno ||
 				   sib_info->magic != dead_info->magic)) {
+			xfs_da_mark_sick(args);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -2368,6 +2387,7 @@ xfs_da3_swap_lastblock(
 		if (XFS_IS_CORRUPT(mp,
 				   be32_to_cpu(sib_info->back) != last_blkno ||
 				   sib_info->magic != dead_info->magic)) {
+			xfs_da_mark_sick(args);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -2390,6 +2410,7 @@ xfs_da3_swap_lastblock(
 		xfs_da3_node_hdr_from_disk(dp->i_mount, &par_hdr, par_node);
 		if (XFS_IS_CORRUPT(mp,
 				   level >= 0 && level != par_hdr.level + 1)) {
+			xfs_da_mark_sick(args);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -2401,6 +2422,7 @@ xfs_da3_swap_lastblock(
 		     entno++)
 			continue;
 		if (XFS_IS_CORRUPT(mp, entno == par_hdr.count)) {
+			xfs_da_mark_sick(args);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -2426,6 +2448,7 @@ xfs_da3_swap_lastblock(
 		xfs_trans_brelse(tp, par_buf);
 		par_buf = NULL;
 		if (XFS_IS_CORRUPT(mp, par_blkno == 0)) {
+			xfs_da_mark_sick(args);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -2435,6 +2458,7 @@ xfs_da3_swap_lastblock(
 		par_node = par_buf->b_addr;
 		xfs_da3_node_hdr_from_disk(dp->i_mount, &par_hdr, par_node);
 		if (XFS_IS_CORRUPT(mp, par_hdr.level != level)) {
+			xfs_da_mark_sick(args);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -2563,6 +2587,7 @@ xfs_dabuf_map(
 invalid_mapping:
 	/* Caller ok with no mapping. */
 	if (XFS_IS_CORRUPT(mp, !(flags & XFS_DABUF_MAP_HOLE_OK))) {
+		xfs_dirattr_mark_sick(dp, whichfork);
 		error = -EFSCORRUPTED;
 		if (xfs_error_level >= XFS_ERRLEVEL_LOW) {
 			xfs_alert(mp, "%s: bno %u inode %llu",
@@ -2644,6 +2669,8 @@ xfs_da_read_buf(
 
 	error = xfs_trans_read_buf_map(mp, tp, mp->m_ddev_targp, mapp, nmap, 0,
 			&bp, ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_dirattr_mark_sick(dp, whichfork);
 	if (error)
 		goto out_free;
 
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index 422e8fc488325..748fe2c514922 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -18,6 +18,7 @@
 #include "xfs_errortag.h"
 #include "xfs_error.h"
 #include "xfs_trace.h"
+#include "xfs_health.h"
 
 const struct xfs_name xfs_name_dotdot = {
 	.name	= (const unsigned char *)"..",
@@ -632,8 +633,10 @@ xfs_dir2_isblock(
 		return 0;
 
 	*isblock = true;
-	if (XFS_IS_CORRUPT(mp, args->dp->i_disk_size != args->geo->blksize))
+	if (XFS_IS_CORRUPT(mp, args->dp->i_disk_size != args->geo->blksize)) {
+		xfs_da_mark_sick(args);
 		return -EFSCORRUPTED;
+	}
 	return 0;
 }
 
diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c
index 00f960a703b2e..6b3ca2b384cf1 100644
--- a/fs/xfs/libxfs/xfs_dir2_block.c
+++ b/fs/xfs/libxfs/xfs_dir2_block.c
@@ -20,6 +20,7 @@
 #include "xfs_error.h"
 #include "xfs_trace.h"
 #include "xfs_log.h"
+#include "xfs_health.h"
 
 /*
  * Local function prototypes.
@@ -152,6 +153,7 @@ xfs_dir3_block_read(
 		__xfs_buf_mark_corrupt(*bpp, fa);
 		xfs_trans_brelse(tp, *bpp);
 		*bpp = NULL;
+		xfs_dirattr_mark_sick(dp, XFS_DATA_FORK);
 		return -EFSCORRUPTED;
 	}
 
diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c
index dbcf58979a598..7a6d965bea71b 100644
--- a/fs/xfs/libxfs/xfs_dir2_data.c
+++ b/fs/xfs/libxfs/xfs_dir2_data.c
@@ -18,6 +18,7 @@
 #include "xfs_trans.h"
 #include "xfs_buf_item.h"
 #include "xfs_log.h"
+#include "xfs_health.h"
 
 static xfs_failaddr_t xfs_dir2_data_freefind_verify(
 		struct xfs_dir2_data_hdr *hdr, struct xfs_dir2_data_free *bf,
@@ -433,6 +434,7 @@ xfs_dir3_data_read(
 		__xfs_buf_mark_corrupt(*bpp, fa);
 		xfs_trans_brelse(tp, *bpp);
 		*bpp = NULL;
+		xfs_dirattr_mark_sick(dp, XFS_DATA_FORK);
 		return -EFSCORRUPTED;
 	}
 
@@ -1198,6 +1200,7 @@ xfs_dir2_data_use_free(
 corrupt:
 	xfs_corruption_error(__func__, XFS_ERRLEVEL_LOW, args->dp->i_mount,
 			hdr, sizeof(*hdr), __FILE__, __LINE__, fa);
+	xfs_da_mark_sick(args);
 	return -EFSCORRUPTED;
 }
 
diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c
index cb9e950a911d8..08dda5ce9d91c 100644
--- a/fs/xfs/libxfs/xfs_dir2_leaf.c
+++ b/fs/xfs/libxfs/xfs_dir2_leaf.c
@@ -19,6 +19,7 @@
 #include "xfs_trace.h"
 #include "xfs_trans.h"
 #include "xfs_buf_item.h"
+#include "xfs_health.h"
 
 /*
  * Local function declarations.
@@ -1393,8 +1394,10 @@ xfs_dir2_leaf_removename(
 	bestsp = xfs_dir2_leaf_bests_p(ltp);
 	if (be16_to_cpu(bestsp[db]) != oldbest) {
 		xfs_buf_mark_corrupt(lbp);
+		xfs_da_mark_sick(args);
 		return -EFSCORRUPTED;
 	}
+
 	/*
 	 * Mark the former data entry unused.
 	 */
diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c
index 7a03aeb9f4c91..be0b8834028c0 100644
--- a/fs/xfs/libxfs/xfs_dir2_node.c
+++ b/fs/xfs/libxfs/xfs_dir2_node.c
@@ -20,6 +20,7 @@
 #include "xfs_trans.h"
 #include "xfs_buf_item.h"
 #include "xfs_log.h"
+#include "xfs_health.h"
 
 /*
  * Function declarations.
@@ -231,6 +232,7 @@ __xfs_dir3_free_read(
 		__xfs_buf_mark_corrupt(*bpp, fa);
 		xfs_trans_brelse(tp, *bpp);
 		*bpp = NULL;
+		xfs_dirattr_mark_sick(dp, XFS_DATA_FORK);
 		return -EFSCORRUPTED;
 	}
 
@@ -443,6 +445,7 @@ xfs_dir2_leaf_to_node(
 	if (be32_to_cpu(ltp->bestcount) >
 				(uint)dp->i_disk_size / args->geo->blksize) {
 		xfs_buf_mark_corrupt(lbp);
+		xfs_da_mark_sick(args);
 		return -EFSCORRUPTED;
 	}
 
@@ -517,6 +520,7 @@ xfs_dir2_leafn_add(
 	 */
 	if (index < 0) {
 		xfs_buf_mark_corrupt(bp);
+		xfs_da_mark_sick(args);
 		return -EFSCORRUPTED;
 	}
 
@@ -736,6 +740,7 @@ xfs_dir2_leafn_lookup_for_addname(
 					   cpu_to_be16(NULLDATAOFF))) {
 				if (curfdb != newfdb)
 					xfs_trans_brelse(tp, curbp);
+				xfs_da_mark_sick(args);
 				return -EFSCORRUPTED;
 			}
 			curfdb = newfdb;
@@ -804,6 +809,7 @@ xfs_dir2_leafn_lookup_for_entry(
 	xfs_dir3_leaf_check(dp, bp);
 	if (leafhdr.count <= 0) {
 		xfs_buf_mark_corrupt(bp);
+		xfs_da_mark_sick(args);
 		return -EFSCORRUPTED;
 	}
 
@@ -1739,6 +1745,7 @@ xfs_dir2_node_add_datablk(
 			} else {
 				xfs_alert(mp, " ... fblk is NULL");
 			}
+			xfs_da_mark_sick(args);
 			return -EFSCORRUPTED;
 		}
 
diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index 0876c767d9ddc..a5b346b377cbb 100644
--- a/fs/xfs/libxfs/xfs_health.h
+++ b/fs/xfs/libxfs/xfs_health.h
@@ -38,6 +38,7 @@ struct xfs_perag;
 struct xfs_inode;
 struct xfs_fsop_geom;
 struct xfs_btree_cur;
+struct xfs_da_args;
 
 /* Observable health issues for metadata spanning the entire filesystem. */
 #define XFS_SICK_FS_COUNTERS	(1 << 0)  /* summary counters */
@@ -155,6 +156,8 @@ void xfs_inode_measure_sickness(struct xfs_inode *ip, unsigned int *sick,
 void xfs_health_unmount(struct xfs_mount *mp);
 void xfs_bmap_mark_sick(struct xfs_inode *ip, int whichfork);
 void xfs_btree_mark_sick(struct xfs_btree_cur *cur);
+void xfs_dirattr_mark_sick(struct xfs_inode *ip, int whichfork);
+void xfs_da_mark_sick(struct xfs_da_args *args);
 
 /* Now some helpers. */
 
diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c
index 89c7a9f4f9305..24fb12986a568 100644
--- a/fs/xfs/xfs_attr_inactive.c
+++ b/fs/xfs/xfs_attr_inactive.c
@@ -23,6 +23,7 @@
 #include "xfs_quota.h"
 #include "xfs_dir2.h"
 #include "xfs_error.h"
+#include "xfs_health.h"
 
 /*
  * Invalidate any incore buffers associated with this remote attribute value
@@ -147,6 +148,7 @@ xfs_attr3_node_inactive(
 	if (level > XFS_DA_NODE_MAXDEPTH) {
 		xfs_buf_mark_corrupt(bp);
 		xfs_trans_brelse(*trans, bp);	/* no locks for later trans */
+		xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
 		return -EFSCORRUPTED;
 	}
 
@@ -197,6 +199,7 @@ xfs_attr3_node_inactive(
 		default:
 			xfs_buf_mark_corrupt(child_bp);
 			xfs_trans_brelse(*trans, child_bp);
+			xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
 			error = -EFSCORRUPTED;
 			break;
 		}
@@ -286,6 +289,7 @@ xfs_attr3_root_inactive(
 		error = xfs_attr3_leaf_inactive(trans, dp, bp);
 		break;
 	default:
+		xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
 		error = -EFSCORRUPTED;
 		xfs_buf_mark_corrupt(bp);
 		xfs_trans_brelse(*trans, bp);
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index 99bbbe1a0e447..305559bfe2a14 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -22,6 +22,7 @@
 #include "xfs_error.h"
 #include "xfs_trace.h"
 #include "xfs_dir2.h"
+#include "xfs_health.h"
 
 STATIC int
 xfs_attr_shortform_compare(const void *a, const void *b)
@@ -126,6 +127,7 @@ xfs_attr_shortform_list(
 					     context->dp->i_mount, sfe,
 					     sizeof(*sfe));
 			kmem_free(sbuf);
+			xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
 			return -EFSCORRUPTED;
 		}
 
@@ -263,8 +265,10 @@ xfs_attr_node_list_lookup(
 			return 0;
 
 		/* We can't point back to the root. */
-		if (XFS_IS_CORRUPT(mp, cursor->blkno == 0))
+		if (XFS_IS_CORRUPT(mp, cursor->blkno == 0)) {
+			xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
 			return -EFSCORRUPTED;
+		}
 	}
 
 	if (expected_level != 0)
@@ -276,6 +280,7 @@ xfs_attr_node_list_lookup(
 out_corruptbuf:
 	xfs_buf_mark_corrupt(bp);
 	xfs_trans_brelse(tp, bp);
+	xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
 	return -EFSCORRUPTED;
 }
 
@@ -305,6 +310,8 @@ xfs_attr_node_list(
 	if (cursor->blkno > 0) {
 		error = xfs_da3_node_read(context->tp, dp, cursor->blkno, &bp,
 				XFS_ATTR_FORK);
+		if (xfs_metadata_is_sick(error))
+			xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
 		if ((error != 0) && (error != -EFSCORRUPTED))
 			return error;
 		if (bp) {
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index 27a27e27a2316..7c5e132609011 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -15,6 +15,8 @@
 #include "xfs_health.h"
 #include "xfs_ag.h"
 #include "xfs_btree.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
 
 /*
  * Warn about metadata corruption that we detected but haven't fixed, and
@@ -529,3 +531,40 @@ xfs_btree_mark_sick(
 
 	xfs_ag_mark_sick(cur->bc_ag.pag, mask);
 }
+
+/*
+ * Record observations of dir/attr btree corruption with the health tracking
+ * system.
+ */
+void
+xfs_dirattr_mark_sick(
+	struct xfs_inode	*ip,
+	int			whichfork)
+{
+	unsigned int		mask;
+
+	switch (whichfork) {
+	case XFS_DATA_FORK:
+		mask = XFS_SICK_INO_DIR;
+		break;
+	case XFS_ATTR_FORK:
+		mask = XFS_SICK_INO_XATTR;
+		break;
+	default:
+		ASSERT(0);
+		return;
+	}
+
+	xfs_inode_mark_sick(ip, mask);
+}
+
+/*
+ * Record observations of dir/attr btree corruption with the health tracking
+ * system.
+ */
+void
+xfs_da_mark_sick(
+	struct xfs_da_args	*args)
+{
+	xfs_dirattr_mark_sick(args->dp, args->whichfork);
+}

[PATCH 07/11] xfs: report symlink block corruption errors to the health system

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Whenever we encounter corrupt symbolic link blocks, we should report
that to the health monitoring system for later reporting.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_symlink.c |   17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)


diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 2a8b3071411f0..b7f251fc2951c 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -58,6 +58,8 @@ xfs_readlink_bmap_ilocked(
 
 		error = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt), 0,
 				&bp, &xfs_symlink_buf_ops);
+		if (xfs_metadata_is_sick(error))
+			xfs_inode_mark_sick(ip, XFS_SICK_INO_SYMLINK);
 		if (error)
 			return error;
 		byte_cnt = XFS_SYMLINK_BUF_SPACE(mp, byte_cnt);
@@ -68,6 +70,7 @@ xfs_readlink_bmap_ilocked(
 		if (xfs_has_crc(mp)) {
 			if (!xfs_symlink_hdr_ok(ip->i_ino, offset,
 							byte_cnt, bp)) {
+				xfs_inode_mark_sick(ip, XFS_SICK_INO_SYMLINK);
 				error = -EFSCORRUPTED;
 				xfs_alert(mp,
 "symlink header does not match required off/len/owner (0x%x/Ox%x,0x%llx)",
@@ -103,7 +106,7 @@ xfs_readlink(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fsize_t		pathlen;
-	int			error = -EFSCORRUPTED;
+	int			error;
 
 	trace_xfs_readlink(ip);
 
@@ -116,14 +119,14 @@ xfs_readlink(
 
 	pathlen = ip->i_disk_size;
 	if (!pathlen)
-		goto out;
+		goto out_corrupt;
 
 	if (pathlen < 0 || pathlen > XFS_SYMLINK_MAXLEN) {
 		xfs_alert(mp, "%s: inode (%llu) bad symlink length (%lld)",
 			 __func__, (unsigned long long) ip->i_ino,
 			 (long long) pathlen);
 		ASSERT(0);
-		goto out;
+		goto out_corrupt;
 	}
 
 	if (ip->i_df.if_format == XFS_DINODE_FMT_LOCAL) {
@@ -132,7 +135,7 @@ xfs_readlink(
 		 * if if_data is junk.
 		 */
 		if (XFS_IS_CORRUPT(ip->i_mount, !ip->i_df.if_u1.if_data))
-			goto out;
+			goto out_corrupt;
 
 		memcpy(link, ip->i_df.if_u1.if_data, pathlen + 1);
 		error = 0;
@@ -140,9 +143,12 @@ xfs_readlink(
 		error = xfs_readlink_bmap_ilocked(ip, link);
 	}
 
- out:
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
 	return error;
+ out_corrupt:
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+	xfs_inode_mark_sick(ip, XFS_SICK_INO_SYMLINK);
+	return -EFSCORRUPTED;
 }
 
 int
@@ -497,6 +503,7 @@ xfs_inactive_symlink(
 			 __func__, (unsigned long long)ip->i_ino, pathlen);
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 		ASSERT(0);
+		xfs_inode_mark_sick(ip, XFS_SICK_INO_SYMLINK);
 		return -EFSCORRUPTED;
 	}
 

[PATCH 08/11] xfs: report inode corruption errors to the health system

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Whenever we encounter corrupt inode records, we should report that to
the health monitoring system for later reporting.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_ialloc.c     |    1 +
 fs/xfs/libxfs/xfs_inode_buf.c  |   12 +++++++++---
 fs/xfs/libxfs/xfs_inode_fork.c |    8 ++++++++
 fs/xfs/xfs_icache.c            |    9 +++++++++
 fs/xfs/xfs_inode.c             |    2 ++
 5 files changed, 29 insertions(+), 3 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 91584e96f05f6..56f82b8af07e8 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -2999,6 +2999,7 @@ xfs_ialloc_check_shrink(
 		goto out;
 
 	if (!has) {
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_INOBT);
 		error = -EFSCORRUPTED;
 		goto out;
 	}
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 137a65bda95dc..1280d6acd1c1b 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -18,6 +18,7 @@
 #include "xfs_trans.h"
 #include "xfs_ialloc.h"
 #include "xfs_dir2.h"
+#include "xfs_health.h"
 
 #include <linux/iversion.h>
 
@@ -132,9 +133,14 @@ xfs_imap_to_bp(
 	struct xfs_imap		*imap,
 	struct xfs_buf		**bpp)
 {
-	return xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
-				   imap->im_len, XBF_UNMAPPED, bpp,
-				   &xfs_inode_buf_ops);
+	int			error;
+
+	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
+			imap->im_len, XBF_UNMAPPED, bpp, &xfs_inode_buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_agno_mark_sick(mp, xfs_daddr_to_agno(mp, imap->im_blkno),
+				XFS_SICK_AG_INOBT);
+	return error;
 }
 
 static inline struct timespec64 xfs_inode_decode_bigtime(uint64_t ts)
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index b86d57589f67e..88aff6b0bda02 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -25,6 +25,7 @@
 #include "xfs_attr_leaf.h"
 #include "xfs_types.h"
 #include "xfs_errortag.h"
+#include "xfs_health.h"
 
 struct kmem_cache *xfs_ifork_cache;
 
@@ -84,6 +85,7 @@ xfs_iformat_local(
 		xfs_inode_verifier_error(ip, -EFSCORRUPTED,
 				"xfs_iformat_local", dip, sizeof(*dip),
 				__this_address);
+		xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
 		return -EFSCORRUPTED;
 	}
 
@@ -121,6 +123,7 @@ xfs_iformat_extents(
 		xfs_inode_verifier_error(ip, -EFSCORRUPTED,
 				"xfs_iformat_extents(1)", dip, sizeof(*dip),
 				__this_address);
+		xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
 		return -EFSCORRUPTED;
 	}
 
@@ -140,6 +143,7 @@ xfs_iformat_extents(
 				xfs_inode_verifier_error(ip, -EFSCORRUPTED,
 						"xfs_iformat_extents(2)",
 						dp, sizeof(*dp), fa);
+				xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
 				return xfs_bmap_complain_bad_rec(ip, whichfork,
 						fa, &new);
 			}
@@ -198,6 +202,7 @@ xfs_iformat_btree(
 		xfs_inode_verifier_error(ip, -EFSCORRUPTED,
 				"xfs_iformat_btree", dfp, size,
 				__this_address);
+		xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
 		return -EFSCORRUPTED;
 	}
 
@@ -262,12 +267,14 @@ xfs_iformat_data_fork(
 		default:
 			xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__,
 					dip, sizeof(*dip), __this_address);
+			xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
 			return -EFSCORRUPTED;
 		}
 		break;
 	default:
 		xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip,
 				sizeof(*dip), __this_address);
+		xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
 		return -EFSCORRUPTED;
 	}
 }
@@ -340,6 +347,7 @@ xfs_iformat_attr_fork(
 	default:
 		xfs_inode_verifier_error(ip, error, __func__, dip,
 				sizeof(*dip), __this_address);
+		xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
 		error = -EFSCORRUPTED;
 		break;
 	}
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index dba514a2c84d9..f6a9c4f40cfd0 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -24,6 +24,7 @@
 #include "xfs_ialloc.h"
 #include "xfs_ag.h"
 #include "xfs_log_priv.h"
+#include "xfs_health.h"
 
 #include <linux/iversion.h>
 
@@ -415,6 +416,9 @@ xfs_iget_check_free_state(
 			xfs_warn(ip->i_mount,
 "Corruption detected! Free inode 0x%llx not marked free! (mode 0x%x)",
 				ip->i_ino, VFS_I(ip)->i_mode);
+			xfs_agno_mark_sick(ip->i_mount,
+					XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
+					XFS_SICK_AG_INOBT);
 			return -EFSCORRUPTED;
 		}
 
@@ -422,6 +426,9 @@ xfs_iget_check_free_state(
 			xfs_warn(ip->i_mount,
 "Corruption detected! Free inode 0x%llx has blocks allocated!",
 				ip->i_ino);
+			xfs_agno_mark_sick(ip->i_mount,
+					XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
+					XFS_SICK_AG_INOBT);
 			return -EFSCORRUPTED;
 		}
 		return 0;
@@ -640,6 +647,8 @@ xfs_iget_cache_miss(
 				xfs_buf_offset(bp, ip->i_imap.im_boffset));
 		if (!error)
 			xfs_buf_set_ref(bp, XFS_INO_REF);
+		else
+			xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
 		xfs_trans_brelse(tp, bp);
 
 		if (error)
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 0ba41fa29e9e7..6db00c5097ec0 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -3435,6 +3435,8 @@ xfs_iflush(
 
 	/* generate the checksum. */
 	xfs_dinode_calc_crc(mp, dip);
+	if (error)
+		xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
 	return error;
 }
 

[PATCH 09/11] xfs: report quota block corruption errors to the health system

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Whenever we encounter corrupt quota blocks, we should report that to the
health monitoring system for later reporting.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_dquot.c  |   30 ++++++++++++++++++++++++++++++
 fs/xfs/xfs_health.c |    1 +
 fs/xfs/xfs_qm.c     |    8 ++++++--
 3 files changed, 37 insertions(+), 2 deletions(-)


diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index a93ad76f23c56..8703495c2fdc6 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -24,6 +24,7 @@
 #include "xfs_log.h"
 #include "xfs_bmap_btree.h"
 #include "xfs_error.h"
+#include "xfs_health.h"
 
 /*
  * Lock order:
@@ -44,6 +45,29 @@ static struct kmem_cache	*xfs_dquot_cache;
 static struct lock_class_key xfs_dquot_group_class;
 static struct lock_class_key xfs_dquot_project_class;
 
+/* Record observations of quota corruption with the health tracking system. */
+static void
+xfs_dquot_mark_sick(
+	struct xfs_dquot	*dqp)
+{
+	struct xfs_mount	*mp = dqp->q_mount;
+
+	switch (dqp->q_type) {
+	case XFS_DQTYPE_USER:
+		xfs_fs_mark_sick(mp, XFS_SICK_FS_UQUOTA);
+		break;
+	case XFS_DQTYPE_GROUP:
+		xfs_fs_mark_sick(mp, XFS_SICK_FS_GQUOTA);
+		break;
+	case XFS_DQTYPE_PROJ:
+		xfs_fs_mark_sick(mp, XFS_SICK_FS_PQUOTA);
+		break;
+	default:
+		ASSERT(0);
+		break;
+	}
+}
+
 /*
  * This is called to free all the memory associated with a dquot
  */
@@ -451,6 +475,8 @@ xfs_dquot_disk_read(
 	error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno,
 			mp->m_quotainfo->qi_dqchunklen, 0, &bp,
 			&xfs_dquot_buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_dquot_mark_sick(dqp);
 	if (error) {
 		ASSERT(bp == NULL);
 		return error;
@@ -574,6 +600,7 @@ xfs_dquot_from_disk(
 			  "Metadata corruption detected at %pS, quota %u",
 			  __this_address, dqp->q_id);
 		xfs_alert(bp->b_mount, "Unmount and run xfs_repair");
+		xfs_dquot_mark_sick(dqp);
 		return -EFSCORRUPTED;
 	}
 
@@ -1238,6 +1265,8 @@ xfs_qm_dqflush(
 				   &bp, &xfs_dquot_buf_ops);
 	if (error == -EAGAIN)
 		goto out_unlock;
+	if (xfs_metadata_is_sick(error))
+		xfs_dquot_mark_sick(dqp);
 	if (error)
 		goto out_abort;
 
@@ -1246,6 +1275,7 @@ xfs_qm_dqflush(
 		xfs_alert(mp, "corrupt dquot ID 0x%x in memory at %pS",
 				dqp->q_id, fa);
 		xfs_buf_relse(bp);
+		xfs_dquot_mark_sick(dqp);
 		error = -EFSCORRUPTED;
 		goto out_abort;
 	}
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index 7c5e132609011..64dffc69a219d 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -17,6 +17,7 @@
 #include "xfs_btree.h"
 #include "xfs_da_format.h"
 #include "xfs_da_btree.h"
+#include "xfs_quota_defs.h"
 
 /*
  * Warn about metadata corruption that we detected but haven't fixed, and
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 3cc1be30a9f74..4f357cb6de748 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -762,14 +762,18 @@ xfs_qm_qino_alloc(
 			     (mp->m_sb.sb_gquotino != NULLFSINO)) {
 			ino = mp->m_sb.sb_gquotino;
 			if (XFS_IS_CORRUPT(mp,
-					   mp->m_sb.sb_pquotino != NULLFSINO))
+					   mp->m_sb.sb_pquotino != NULLFSINO)) {
+				xfs_fs_mark_sick(mp, XFS_SICK_FS_PQUOTA);
 				return -EFSCORRUPTED;
+			}
 		} else if ((flags & XFS_QMOPT_GQUOTA) &&
 			     (mp->m_sb.sb_pquotino != NULLFSINO)) {
 			ino = mp->m_sb.sb_pquotino;
 			if (XFS_IS_CORRUPT(mp,
-					   mp->m_sb.sb_gquotino != NULLFSINO))
+					   mp->m_sb.sb_gquotino != NULLFSINO)) {
+				xfs_fs_mark_sick(mp, XFS_SICK_FS_GQUOTA);
 				return -EFSCORRUPTED;
+			}
 		}
 		if (ino != NULLFSINO) {
 			error = xfs_iget(mp, NULL, ino, 0, 0, ipp);

[PATCH 10/11] xfs: report realtime metadata corruption errors to the health system

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Whenever we encounter corrupt realtime metadat blocks, we should report
that to the health monitoring system for later reporting.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_rtbitmap.c |    9 ++++++++-
 fs/xfs/xfs_rtalloc.c         |    6 ++++++
 2 files changed, 14 insertions(+), 1 deletion(-)


diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 30a2844f62e30..f43f31dca69d7 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -17,6 +17,7 @@
 #include "xfs_rtalloc.h"
 #include "xfs_error.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_health.h"
 
 /*
  * Realtime allocator bitmap functions shared with userspace.
@@ -115,13 +116,19 @@ xfs_rtbuf_get(
 	if (error)
 		return error;
 
-	if (XFS_IS_CORRUPT(mp, nmap == 0 || !xfs_bmap_is_written_extent(&map)))
+	if (XFS_IS_CORRUPT(mp, nmap == 0 || !xfs_bmap_is_written_extent(&map))) {
+		xfs_rt_mark_sick(mp, issum ? XFS_SICK_RT_SUMMARY :
+					     XFS_SICK_RT_BITMAP);
 		return -EFSCORRUPTED;
+	}
 
 	ASSERT(map.br_startblock != NULLFSBLOCK);
 	error = xfs_trans_read_buf(mp, args->tp, mp->m_ddev_targp,
 				   XFS_FSB_TO_DADDR(mp, map.br_startblock),
 				   mp->m_bsize, 0, &bp, &xfs_rtbuf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_rt_mark_sick(mp, issum ? XFS_SICK_RT_SUMMARY :
+					     XFS_SICK_RT_BITMAP);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 0c9893b9f2a99..379462ea9a14f 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -20,6 +20,8 @@
 #include "xfs_rtalloc.h"
 #include "xfs_sb.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_log_priv.h"
+#include "xfs_health.h"
 
 /*
  * Read and return the summary information for a given extent size,
@@ -1374,6 +1376,8 @@ xfs_rtmount_inodes(
 
 	sbp = &mp->m_sb;
 	error = xfs_iget(mp, NULL, sbp->sb_rbmino, 0, 0, &mp->m_rbmip);
+	if (xfs_metadata_is_sick(error))
+		xfs_rt_mark_sick(mp, XFS_SICK_RT_BITMAP);
 	if (error)
 		return error;
 	ASSERT(mp->m_rbmip != NULL);
@@ -1383,6 +1387,8 @@ xfs_rtmount_inodes(
 		goto out_rele_bitmap;
 
 	error = xfs_iget(mp, NULL, sbp->sb_rsumino, 0, 0, &mp->m_rsumip);
+	if (xfs_metadata_is_sick(error))
+		xfs_rt_mark_sick(mp, XFS_SICK_RT_SUMMARY);
 	if (error)
 		goto out_rele_bitmap;
 	ASSERT(mp->m_rsumip != NULL);

[PATCH 11/11] xfs: report XFS_IS_CORRUPT errors to the health system

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Whenever we encounter XFS_IS_CORRUPT failures, we should report that to
the health monitoring system for later reporting.

I started with this semantic patch and massaged everything until it
built:

@@
expression mp, test;
@@

- if (XFS_IS_CORRUPT(mp, test)) return -EFSCORRUPTED;
+ if (XFS_IS_CORRUPT(mp, test)) { xfs_btree_mark_sick(cur); return -EFSCORRUPTED; }

@@
expression mp, test;
identifier label, error;
@@

- if (XFS_IS_CORRUPT(mp, test)) { error = -EFSCORRUPTED; goto label; }
+ if (XFS_IS_CORRUPT(mp, test)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto label; }

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_ag.c          |    4 +-
 fs/xfs/libxfs/xfs_alloc.c       |   97 +++++++++++++++++++++++++++++++++------
 fs/xfs/libxfs/xfs_attr_remote.c |    8 ++-
 fs/xfs/libxfs/xfs_bmap.c        |   94 ++++++++++++++++++++++++++++++++++----
 fs/xfs/libxfs/xfs_btree.c       |   14 +++++-
 fs/xfs/libxfs/xfs_ialloc.c      |   52 +++++++++++++++++----
 fs/xfs/libxfs/xfs_refcount.c    |   37 ++++++++++++++-
 fs/xfs/libxfs/xfs_rmap.c        |   77 +++++++++++++++++++++++++++++--
 fs/xfs/scrub/refcount_repair.c  |    9 +++-
 fs/xfs/xfs_attr_list.c          |    9 +++-
 fs/xfs/xfs_dir2_readdir.c       |    6 ++
 fs/xfs/xfs_discard.c            |    2 +
 fs/xfs/xfs_iwalk.c              |    5 ++
 13 files changed, 364 insertions(+), 50 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index b857fc54562a7..ccad54d1dadaf 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -931,8 +931,10 @@ xfs_ag_shrink_space(
 	agf = agfbp->b_addr;
 	aglen = be32_to_cpu(agi->agi_length);
 	/* some extra paranoid checks before we shrink the ag */
-	if (XFS_IS_CORRUPT(mp, agf->agf_length != agi->agi_length))
+	if (XFS_IS_CORRUPT(mp, agf->agf_length != agi->agi_length)) {
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGF);
 		return -EFSCORRUPTED;
+	}
 	if (delta >= aglen)
 		return -EINVAL;
 
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 2464b64b1cb4e..ac31b62e70177 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -499,14 +499,18 @@ xfs_alloc_fixup_trees(
 		if (XFS_IS_CORRUPT(mp,
 				   i != 1 ||
 				   nfbno1 != fbno ||
-				   nflen1 != flen))
+				   nflen1 != flen)) {
+			xfs_btree_mark_sick(cnt_cur);
 			return -EFSCORRUPTED;
+		}
 #endif
 	} else {
 		if ((error = xfs_alloc_lookup_eq(cnt_cur, fbno, flen, &i)))
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 1))
+		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			return -EFSCORRUPTED;
+		}
 	}
 	/*
 	 * Look up the record in the by-block tree if necessary.
@@ -518,14 +522,18 @@ xfs_alloc_fixup_trees(
 		if (XFS_IS_CORRUPT(mp,
 				   i != 1 ||
 				   nfbno1 != fbno ||
-				   nflen1 != flen))
+				   nflen1 != flen)) {
+			xfs_btree_mark_sick(bno_cur);
 			return -EFSCORRUPTED;
+		}
 #endif
 	} else {
 		if ((error = xfs_alloc_lookup_eq(bno_cur, fbno, flen, &i)))
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 1))
+		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(bno_cur);
 			return -EFSCORRUPTED;
+		}
 	}
 
 #ifdef DEBUG
@@ -538,8 +546,10 @@ xfs_alloc_fixup_trees(
 
 		if (XFS_IS_CORRUPT(mp,
 				   bnoblock->bb_numrecs !=
-				   cntblock->bb_numrecs))
+				   cntblock->bb_numrecs)) {
+			xfs_btree_mark_sick(bno_cur);
 			return -EFSCORRUPTED;
+		}
 	}
 #endif
 
@@ -569,30 +579,40 @@ xfs_alloc_fixup_trees(
 	 */
 	if ((error = xfs_btree_delete(cnt_cur, &i)))
 		return error;
-	if (XFS_IS_CORRUPT(mp, i != 1))
+	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cnt_cur);
 		return -EFSCORRUPTED;
+	}
 	/*
 	 * Add new by-size btree entry(s).
 	 */
 	if (nfbno1 != NULLAGBLOCK) {
 		if ((error = xfs_alloc_lookup_eq(cnt_cur, nfbno1, nflen1, &i)))
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 0))
+		if (XFS_IS_CORRUPT(mp, i != 0)) {
+			xfs_btree_mark_sick(cnt_cur);
 			return -EFSCORRUPTED;
+		}
 		if ((error = xfs_btree_insert(cnt_cur, &i)))
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 1))
+		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			return -EFSCORRUPTED;
+		}
 	}
 	if (nfbno2 != NULLAGBLOCK) {
 		if ((error = xfs_alloc_lookup_eq(cnt_cur, nfbno2, nflen2, &i)))
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 0))
+		if (XFS_IS_CORRUPT(mp, i != 0)) {
+			xfs_btree_mark_sick(cnt_cur);
 			return -EFSCORRUPTED;
+		}
 		if ((error = xfs_btree_insert(cnt_cur, &i)))
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 1))
+		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			return -EFSCORRUPTED;
+		}
 	}
 	/*
 	 * Fix up the by-block btree entry(s).
@@ -603,8 +623,10 @@ xfs_alloc_fixup_trees(
 		 */
 		if ((error = xfs_btree_delete(bno_cur, &i)))
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 1))
+		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(bno_cur);
 			return -EFSCORRUPTED;
+		}
 	} else {
 		/*
 		 * Update the by-block entry to start later|be shorter.
@@ -618,12 +640,16 @@ xfs_alloc_fixup_trees(
 		 */
 		if ((error = xfs_alloc_lookup_eq(bno_cur, nfbno2, nflen2, &i)))
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 0))
+		if (XFS_IS_CORRUPT(mp, i != 0)) {
+			xfs_btree_mark_sick(bno_cur);
 			return -EFSCORRUPTED;
+		}
 		if ((error = xfs_btree_insert(bno_cur, &i)))
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 1))
+		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(bno_cur);
 			return -EFSCORRUPTED;
+		}
 	}
 	return 0;
 }
@@ -896,8 +922,10 @@ xfs_alloc_cur_check(
 	error = xfs_alloc_get_rec(cur, &bno, &len, &i);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(args->mp, i != 1))
+	if (XFS_IS_CORRUPT(args->mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	/*
 	 * Check minlen and deactivate a cntbt cursor if out of acceptable size
@@ -1103,6 +1131,7 @@ xfs_alloc_ag_vextent_small(
 		if (error)
 			goto error;
 		if (XFS_IS_CORRUPT(args->mp, i != 1)) {
+			xfs_btree_mark_sick(ccur);
 			error = -EFSCORRUPTED;
 			goto error;
 		}
@@ -1137,6 +1166,7 @@ xfs_alloc_ag_vextent_small(
 	*fbnop = args->agbno = fbno;
 	*flenp = args->len = 1;
 	if (XFS_IS_CORRUPT(args->mp, fbno >= be32_to_cpu(agf->agf_length))) {
+		xfs_btree_mark_sick(ccur);
 		error = -EFSCORRUPTED;
 		goto error;
 	}
@@ -1223,6 +1253,7 @@ xfs_alloc_ag_vextent_exact(
 	if (error)
 		goto error0;
 	if (XFS_IS_CORRUPT(args->mp, i != 1)) {
+		xfs_btree_mark_sick(bno_cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -1502,8 +1533,10 @@ xfs_alloc_ag_vextent_lastblock(
 			error = xfs_alloc_get_rec(acur->cnt, bno, len, &i);
 			if (error)
 				return error;
-			if (XFS_IS_CORRUPT(args->mp, i != 1))
+			if (XFS_IS_CORRUPT(args->mp, i != 1)) {
+				xfs_btree_mark_sick(acur->cnt);
 				return -EFSCORRUPTED;
+			}
 			if (*len >= args->minlen)
 				break;
 			error = xfs_btree_increment(acur->cnt, 0, &i);
@@ -1715,6 +1748,7 @@ xfs_alloc_ag_vextent_size(
 			if (error)
 				goto error0;
 			if (XFS_IS_CORRUPT(args->mp, i != 1)) {
+				xfs_btree_mark_sick(cnt_cur);
 				error = -EFSCORRUPTED;
 				goto error0;
 			}
@@ -1761,6 +1795,7 @@ xfs_alloc_ag_vextent_size(
 			   rlen != 0 &&
 			   (rlen > flen ||
 			    rbno + rlen > fbno + flen))) {
+		xfs_btree_mark_sick(cnt_cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -1783,6 +1818,7 @@ xfs_alloc_ag_vextent_size(
 					&i)))
 				goto error0;
 			if (XFS_IS_CORRUPT(args->mp, i != 1)) {
+				xfs_btree_mark_sick(cnt_cur);
 				error = -EFSCORRUPTED;
 				goto error0;
 			}
@@ -1795,6 +1831,7 @@ xfs_alloc_ag_vextent_size(
 					   rlen != 0 &&
 					   (rlen > flen ||
 					    rbno + rlen > fbno + flen))) {
+				xfs_btree_mark_sick(cnt_cur);
 				error = -EFSCORRUPTED;
 				goto error0;
 			}
@@ -1811,6 +1848,7 @@ xfs_alloc_ag_vextent_size(
 				&i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(args->mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -1849,6 +1887,7 @@ xfs_alloc_ag_vextent_size(
 
 	rlen = args->len;
 	if (XFS_IS_CORRUPT(args->mp, rlen > flen)) {
+		xfs_btree_mark_sick(cnt_cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -1868,6 +1907,7 @@ xfs_alloc_ag_vextent_size(
 	if (XFS_IS_CORRUPT(args->mp,
 			   args->agbno + args->len >
 			   be32_to_cpu(agf->agf_length))) {
+		xfs_ag_mark_sick(args->pag, XFS_SICK_AG_BNOBT);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -1943,6 +1983,7 @@ xfs_free_ag_extent(
 		if ((error = xfs_alloc_get_rec(bno_cur, &ltbno, &ltlen, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(bno_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -1958,6 +1999,7 @@ xfs_free_ag_extent(
 			 * Very bad.
 			 */
 			if (XFS_IS_CORRUPT(mp, ltbno + ltlen > bno)) {
+				xfs_btree_mark_sick(bno_cur);
 				error = -EFSCORRUPTED;
 				goto error0;
 			}
@@ -1976,6 +2018,7 @@ xfs_free_ag_extent(
 		if ((error = xfs_alloc_get_rec(bno_cur, &gtbno, &gtlen, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(bno_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -1991,6 +2034,7 @@ xfs_free_ag_extent(
 			 * Very bad.
 			 */
 			if (XFS_IS_CORRUPT(mp, bno + len > gtbno)) {
+				xfs_btree_mark_sick(bno_cur);
 				error = -EFSCORRUPTED;
 				goto error0;
 			}
@@ -2011,12 +2055,14 @@ xfs_free_ag_extent(
 		if ((error = xfs_alloc_lookup_eq(cnt_cur, ltbno, ltlen, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
 		if ((error = xfs_btree_delete(cnt_cur, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -2026,12 +2072,14 @@ xfs_free_ag_extent(
 		if ((error = xfs_alloc_lookup_eq(cnt_cur, gtbno, gtlen, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
 		if ((error = xfs_btree_delete(cnt_cur, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -2041,6 +2089,7 @@ xfs_free_ag_extent(
 		if ((error = xfs_btree_delete(bno_cur, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(bno_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -2050,6 +2099,7 @@ xfs_free_ag_extent(
 		if ((error = xfs_btree_decrement(bno_cur, 0, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(bno_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -2069,6 +2119,7 @@ xfs_free_ag_extent(
 					   i != 1 ||
 					   xxbno != ltbno ||
 					   xxlen != ltlen)) {
+				xfs_btree_mark_sick(bno_cur);
 				error = -EFSCORRUPTED;
 				goto error0;
 			}
@@ -2093,12 +2144,14 @@ xfs_free_ag_extent(
 		if ((error = xfs_alloc_lookup_eq(cnt_cur, ltbno, ltlen, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
 		if ((error = xfs_btree_delete(cnt_cur, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -2109,6 +2162,7 @@ xfs_free_ag_extent(
 		if ((error = xfs_btree_decrement(bno_cur, 0, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(bno_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -2128,12 +2182,14 @@ xfs_free_ag_extent(
 		if ((error = xfs_alloc_lookup_eq(cnt_cur, gtbno, gtlen, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
 		if ((error = xfs_btree_delete(cnt_cur, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -2156,6 +2212,7 @@ xfs_free_ag_extent(
 		if ((error = xfs_btree_insert(bno_cur, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(bno_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -2168,12 +2225,14 @@ xfs_free_ag_extent(
 	if ((error = xfs_alloc_lookup_eq(cnt_cur, nbno, nlen, &i)))
 		goto error0;
 	if (XFS_IS_CORRUPT(mp, i != 0)) {
+		xfs_btree_mark_sick(cnt_cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
 	if ((error = xfs_btree_insert(cnt_cur, &i)))
 		goto error0;
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cnt_cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -3903,17 +3962,23 @@ __xfs_free_extent(
 		return -EIO;
 
 	error = xfs_free_extent_fix_freelist(tp, pag, &agbp);
-	if (error)
+	if (error) {
+		if (xfs_metadata_is_sick(error))
+			xfs_ag_mark_sick(pag, XFS_SICK_AG_BNOBT);
 		return error;
+	}
+
 	agf = agbp->b_addr;
 
 	if (XFS_IS_CORRUPT(mp, agbno >= mp->m_sb.sb_agblocks)) {
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_BNOBT);
 		error = -EFSCORRUPTED;
 		goto err_release;
 	}
 
 	/* validate the extent size is legal now we have the agf locked */
 	if (XFS_IS_CORRUPT(mp, agbno + len > be32_to_cpu(agf->agf_length))) {
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_BNOBT);
 		error = -EFSCORRUPTED;
 		goto err_release;
 	}
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index b18a3cf44192e..bb4cf1fa0dc2c 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -553,8 +553,10 @@ xfs_attr_rmtval_stale(
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 
 	if (XFS_IS_CORRUPT(mp, map->br_startblock == DELAYSTARTBLOCK) ||
-	    XFS_IS_CORRUPT(mp, map->br_startblock == HOLESTARTBLOCK))
+	    XFS_IS_CORRUPT(mp, map->br_startblock == HOLESTARTBLOCK)) {
+		xfs_bmap_mark_sick(ip, XFS_ATTR_FORK);
 		return -EFSCORRUPTED;
+	}
 
 	error = xfs_buf_incore(mp->m_ddev_targp,
 			XFS_FSB_TO_DADDR(mp, map->br_startblock),
@@ -664,8 +666,10 @@ xfs_attr_rmtval_invalidate(
 				       blkcnt, &map, &nmap, XFS_BMAPI_ATTRFORK);
 		if (error)
 			return error;
-		if (XFS_IS_CORRUPT(args->dp->i_mount, nmap != 1))
+		if (XFS_IS_CORRUPT(args->dp->i_mount, nmap != 1)) {
+			xfs_bmap_mark_sick(args->dp, XFS_ATTR_FORK);
 			return -EFSCORRUPTED;
+		}
 		error = xfs_attr_rmtval_stale(args->dp, &map, XBF_TRYLOCK);
 		if (error)
 			return error;
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 61918ca34658b..f815e8b2809bc 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -386,6 +386,7 @@ xfs_bmap_check_leaf_extents(
 		pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
 		bno = be64_to_cpu(*pp);
 		if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbno(mp, bno))) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -567,8 +568,10 @@ xfs_bmap_btree_to_extents(
 	pp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, ifp->if_broot_bytes);
 	cbno = be64_to_cpu(*pp);
 #ifdef DEBUG
-	if (XFS_IS_CORRUPT(cur->bc_mp, !xfs_btree_check_lptr(cur, cbno, 1)))
+	if (XFS_IS_CORRUPT(cur->bc_mp, !xfs_btree_check_lptr(cur, cbno, 1))) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 #endif
 	error = xfs_btree_read_bufl(mp, tp, cbno, &cbp, XFS_BMAP_BTREE_REF,
 				&xfs_bmbt_buf_ops);
@@ -885,6 +888,7 @@ xfs_bmap_add_attrfork_btree(
 			goto error0;
 		/* must be at least one entry */
 		if (XFS_IS_CORRUPT(mp, stat != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -1211,6 +1215,7 @@ xfs_iread_extents(
 		goto out;
 
 	if (XFS_IS_CORRUPT(mp, ir.loaded != ifp->if_nextents)) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		error = -EFSCORRUPTED;
 		goto out;
 	}
@@ -1401,8 +1406,10 @@ xfs_bmap_last_offset(
 	if (ifp->if_format == XFS_DINODE_FMT_LOCAL)
 		return 0;
 
-	if (XFS_IS_CORRUPT(ip->i_mount, !xfs_ifork_has_extents(ifp)))
+	if (XFS_IS_CORRUPT(ip->i_mount, !xfs_ifork_has_extents(ifp))) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		return -EFSCORRUPTED;
+	}
 
 	error = xfs_bmap_last_extent(NULL, ip, whichfork, &rec, &is_empty);
 	if (error || is_empty)
@@ -1541,6 +1548,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1548,6 +1556,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1555,6 +1564,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1584,6 +1594,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1617,6 +1628,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1645,6 +1657,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 0)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1652,6 +1665,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1686,6 +1700,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1711,6 +1726,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 0)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1718,6 +1734,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1762,6 +1779,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1798,6 +1816,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 0)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1805,6 +1824,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1884,6 +1904,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 0)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1891,6 +1912,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2087,30 +2109,35 @@ xfs_bmap_add_extent_unwritten_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
 			if ((error = xfs_btree_delete(cur, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
 			if ((error = xfs_btree_decrement(cur, 0, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
 			if ((error = xfs_btree_delete(cur, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
 			if ((error = xfs_btree_decrement(cur, 0, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2139,18 +2166,21 @@ xfs_bmap_add_extent_unwritten_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
 			if ((error = xfs_btree_delete(cur, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
 			if ((error = xfs_btree_decrement(cur, 0, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2182,18 +2212,21 @@ xfs_bmap_add_extent_unwritten_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
 			if ((error = xfs_btree_delete(cur, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
 			if ((error = xfs_btree_decrement(cur, 0, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2220,6 +2253,7 @@ xfs_bmap_add_extent_unwritten_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2253,6 +2287,7 @@ xfs_bmap_add_extent_unwritten_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2290,6 +2325,7 @@ xfs_bmap_add_extent_unwritten_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2300,6 +2336,7 @@ xfs_bmap_add_extent_unwritten_real(
 			if ((error = xfs_btree_insert(cur, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2330,6 +2367,7 @@ xfs_bmap_add_extent_unwritten_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2366,6 +2404,7 @@ xfs_bmap_add_extent_unwritten_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2376,12 +2415,14 @@ xfs_bmap_add_extent_unwritten_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 0)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
 			if ((error = xfs_btree_insert(cur, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2418,6 +2459,7 @@ xfs_bmap_add_extent_unwritten_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2430,6 +2472,7 @@ xfs_bmap_add_extent_unwritten_real(
 			if ((error = xfs_btree_insert(cur, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2442,6 +2485,7 @@ xfs_bmap_add_extent_unwritten_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 0)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2449,6 +2493,7 @@ xfs_bmap_add_extent_unwritten_real(
 			if ((error = xfs_btree_insert(cur, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2734,6 +2779,7 @@ xfs_bmap_add_extent_hole_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2741,6 +2787,7 @@ xfs_bmap_add_extent_hole_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2748,6 +2795,7 @@ xfs_bmap_add_extent_hole_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2777,6 +2825,7 @@ xfs_bmap_add_extent_hole_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2807,6 +2856,7 @@ xfs_bmap_add_extent_hole_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2833,6 +2883,7 @@ xfs_bmap_add_extent_hole_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 0)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2840,6 +2891,7 @@ xfs_bmap_add_extent_hole_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -5094,8 +5146,10 @@ xfs_bmap_del_extent_real(
 		error = xfs_bmbt_lookup_eq(cur, &got, &i);
 		if (error)
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 1))
+		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			return -EFSCORRUPTED;
+		}
 	}
 
 	if (got.br_startoff == del->br_startoff)
@@ -5119,8 +5173,10 @@ xfs_bmap_del_extent_real(
 		}
 		if ((error = xfs_btree_delete(cur, &i)))
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 1))
+		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			return -EFSCORRUPTED;
+		}
 		break;
 	case BMAP_LEFT_FILLING:
 		/*
@@ -5192,8 +5248,10 @@ xfs_bmap_del_extent_real(
 				error = xfs_bmbt_lookup_eq(cur, &got, &i);
 				if (error)
 					return error;
-				if (XFS_IS_CORRUPT(mp, i != 1))
+				if (XFS_IS_CORRUPT(mp, i != 1)) {
+					xfs_btree_mark_sick(cur);
 					return -EFSCORRUPTED;
+				}
 				/*
 				 * Update the btree record back
 				 * to the original value.
@@ -5209,8 +5267,10 @@ xfs_bmap_del_extent_real(
 				*logflagsp = 0;
 				return -ENOSPC;
 			}
-			if (XFS_IS_CORRUPT(mp, i != 1))
+			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				return -EFSCORRUPTED;
+			}
 		} else
 			*logflagsp |= xfs_ilog_fext(whichfork);
 
@@ -5665,21 +5725,27 @@ xfs_bmse_merge(
 	error = xfs_bmbt_lookup_eq(cur, got, &i);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(mp, i != 1))
+	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	error = xfs_btree_delete(cur, &i);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(mp, i != 1))
+	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	/* lookup and update size of the previous extent */
 	error = xfs_bmbt_lookup_eq(cur, left, &i);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(mp, i != 1))
+	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	error = xfs_bmbt_update(cur, &new);
 	if (error)
@@ -5727,8 +5793,10 @@ xfs_bmap_shift_update_extent(
 		error = xfs_bmbt_lookup_eq(cur, &prev, &i);
 		if (error)
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 1))
+		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			return -EFSCORRUPTED;
+		}
 
 		error = xfs_bmbt_update(cur, got);
 		if (error)
@@ -5789,6 +5857,7 @@ xfs_bmap_collapse_extents(
 		goto del_cursor;
 	}
 	if (XFS_IS_CORRUPT(mp, isnullstartblock(got.br_startblock))) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		error = -EFSCORRUPTED;
 		goto del_cursor;
 	}
@@ -5914,11 +5983,13 @@ xfs_bmap_insert_extents(
 		}
 	}
 	if (XFS_IS_CORRUPT(mp, isnullstartblock(got.br_startblock))) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		error = -EFSCORRUPTED;
 		goto del_cursor;
 	}
 
 	if (XFS_IS_CORRUPT(mp, stop_fsb > got.br_startoff)) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		error = -EFSCORRUPTED;
 		goto del_cursor;
 	}
@@ -6018,6 +6089,7 @@ xfs_bmap_split_extent(
 		if (error)
 			goto del_cursor;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto del_cursor;
 		}
@@ -6045,6 +6117,7 @@ xfs_bmap_split_extent(
 		if (error)
 			goto del_cursor;
 		if (XFS_IS_CORRUPT(mp, i != 0)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto del_cursor;
 		}
@@ -6052,6 +6125,7 @@ xfs_bmap_split_extent(
 		if (error)
 			goto del_cursor;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto del_cursor;
 		}
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 51d0a569e8216..28ba528086888 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -2026,8 +2026,10 @@ xfs_btree_lookup(
 			error = xfs_btree_increment(cur, 0, &i);
 			if (error)
 				goto error0;
-			if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+			if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				return -EFSCORRUPTED;
+			}
 			*stat = 1;
 			return 0;
 		}
@@ -2480,6 +2482,7 @@ xfs_btree_lshift(
 			goto error0;
 		i = xfs_btree_firstrec(tcur, level);
 		if (XFS_IS_CORRUPT(tcur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -2650,6 +2653,7 @@ xfs_btree_rshift(
 		goto error0;
 	i = xfs_btree_lastrec(tcur, level);
 	if (XFS_IS_CORRUPT(tcur->bc_mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -3538,6 +3542,7 @@ xfs_btree_insert(
 		}
 
 		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -3945,6 +3950,7 @@ xfs_btree_delrec(
 		 */
 		i = xfs_btree_lastrec(tcur, level);
 		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -3953,12 +3959,14 @@ xfs_btree_delrec(
 		if (error)
 			goto error0;
 		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
 
 		i = xfs_btree_lastrec(tcur, level);
 		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -4006,6 +4014,7 @@ xfs_btree_delrec(
 		if (!xfs_btree_ptr_is_null(cur, &lptr)) {
 			i = xfs_btree_firstrec(tcur, level);
 			if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto error0;
 			}
@@ -4014,6 +4023,7 @@ xfs_btree_delrec(
 			if (error)
 				goto error0;
 			if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto error0;
 			}
@@ -4031,6 +4041,7 @@ xfs_btree_delrec(
 		 */
 		i = xfs_btree_firstrec(tcur, level);
 		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -4040,6 +4051,7 @@ xfs_btree_delrec(
 			goto error0;
 		i = xfs_btree_firstrec(tcur, level);
 		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 56f82b8af07e8..1ff867075026d 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -573,6 +573,7 @@ xfs_inobt_insert_sprec(
 		if (error)
 			goto error;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error;
 		}
@@ -589,10 +590,12 @@ xfs_inobt_insert_sprec(
 		if (error)
 			goto error;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error;
 		}
 		if (XFS_IS_CORRUPT(mp, rec.ir_startino != nrec->ir_startino)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error;
 		}
@@ -602,6 +605,7 @@ xfs_inobt_insert_sprec(
 		 * cannot merge, something is seriously wrong.
 		 */
 		if (XFS_IS_CORRUPT(mp, !__xfs_inobt_can_merge(nrec, &rec))) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error;
 		}
@@ -951,8 +955,10 @@ xfs_ialloc_next_rec(
 		error = xfs_inobt_get_rec(cur, rec, &i);
 		if (error)
 			return error;
-		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			return -EFSCORRUPTED;
+		}
 	}
 
 	return 0;
@@ -976,8 +982,10 @@ xfs_ialloc_get_rec(
 		error = xfs_inobt_get_rec(cur, rec, &i);
 		if (error)
 			return error;
-		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			return -EFSCORRUPTED;
+		}
 	}
 
 	return 0;
@@ -1055,6 +1063,7 @@ xfs_dialloc_ag_inobt(
 		if (error)
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -1063,6 +1072,7 @@ xfs_dialloc_ag_inobt(
 		if (error)
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, j != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -1221,6 +1231,7 @@ xfs_dialloc_ag_inobt(
 	if (error)
 		goto error0;
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -1230,6 +1241,7 @@ xfs_dialloc_ag_inobt(
 		if (error)
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -1239,6 +1251,7 @@ xfs_dialloc_ag_inobt(
 		if (error)
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -1299,8 +1312,10 @@ xfs_dialloc_ag_finobt_near(
 		error = xfs_inobt_get_rec(lcur, rec, &i);
 		if (error)
 			return error;
-		if (XFS_IS_CORRUPT(lcur->bc_mp, i != 1))
+		if (XFS_IS_CORRUPT(lcur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(lcur);
 			return -EFSCORRUPTED;
+		}
 
 		/*
 		 * See if we've landed in the parent inode record. The finobt
@@ -1324,12 +1339,14 @@ xfs_dialloc_ag_finobt_near(
 		if (error)
 			goto error_rcur;
 		if (XFS_IS_CORRUPT(lcur->bc_mp, j != 1)) {
+			xfs_btree_mark_sick(lcur);
 			error = -EFSCORRUPTED;
 			goto error_rcur;
 		}
 	}
 
 	if (XFS_IS_CORRUPT(lcur->bc_mp, i != 1 && j != 1)) {
+		xfs_btree_mark_sick(lcur);
 		error = -EFSCORRUPTED;
 		goto error_rcur;
 	}
@@ -1385,8 +1402,10 @@ xfs_dialloc_ag_finobt_newino(
 			error = xfs_inobt_get_rec(cur, rec, &i);
 			if (error)
 				return error;
-			if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+			if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				return -EFSCORRUPTED;
+			}
 			return 0;
 		}
 	}
@@ -1397,14 +1416,18 @@ xfs_dialloc_ag_finobt_newino(
 	error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &i);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	error = xfs_inobt_get_rec(cur, rec, &i);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	return 0;
 }
@@ -1426,14 +1449,18 @@ xfs_dialloc_ag_update_inobt(
 	error = xfs_inobt_lookup(cur, frec->ir_startino, XFS_LOOKUP_EQ, &i);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	error = xfs_inobt_get_rec(cur, &rec, &i);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 	ASSERT((XFS_AGINO_TO_OFFSET(cur->bc_mp, rec.ir_startino) %
 				   XFS_INODES_PER_CHUNK) == 0);
 
@@ -1442,8 +1469,10 @@ xfs_dialloc_ag_update_inobt(
 
 	if (XFS_IS_CORRUPT(cur->bc_mp,
 			   rec.ir_free != frec->ir_free ||
-			   rec.ir_freecount != frec->ir_freecount))
+			   rec.ir_freecount != frec->ir_freecount)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	return xfs_inobt_update(cur, &rec);
 }
@@ -1960,6 +1989,7 @@ xfs_difree_inobt(
 		goto error0;
 	}
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -1970,6 +2000,7 @@ xfs_difree_inobt(
 		goto error0;
 	}
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -2082,6 +2113,7 @@ xfs_difree_finobt(
 		 * something is out of sync.
 		 */
 		if (XFS_IS_CORRUPT(mp, ibtrec->ir_freecount != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error;
 		}
@@ -2108,6 +2140,7 @@ xfs_difree_finobt(
 	if (error)
 		goto error;
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error;
 	}
@@ -2118,6 +2151,7 @@ xfs_difree_finobt(
 	if (XFS_IS_CORRUPT(mp,
 			   rec.ir_free != ibtrec->ir_free ||
 			   rec.ir_freecount != ibtrec->ir_freecount)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error;
 	}
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 91f1066f408b9..90a4526fef929 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -240,6 +240,7 @@ xfs_refcount_insert(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, *i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -270,12 +271,14 @@ xfs_refcount_delete(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
 	trace_xfs_refcount_delete(cur->bc_mp, cur->bc_ag.pag->pag_agno, &irec);
 	error = xfs_btree_delete(cur, i);
 	if (XFS_IS_CORRUPT(cur->bc_mp, *i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -400,6 +403,7 @@ xfs_refcount_split_extent(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -427,6 +431,7 @@ xfs_refcount_split_extent(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -472,6 +477,7 @@ xfs_refcount_merge_center_extents(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -480,6 +486,7 @@ xfs_refcount_merge_center_extents(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -489,6 +496,7 @@ xfs_refcount_merge_center_extents(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -500,6 +508,7 @@ xfs_refcount_merge_center_extents(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -544,6 +553,7 @@ xfs_refcount_merge_left_extent(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -552,6 +562,7 @@ xfs_refcount_merge_left_extent(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -563,6 +574,7 @@ xfs_refcount_merge_left_extent(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -610,6 +622,7 @@ xfs_refcount_merge_right_extent(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -618,6 +631,7 @@ xfs_refcount_merge_right_extent(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -629,6 +643,7 @@ xfs_refcount_merge_right_extent(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -676,6 +691,7 @@ xfs_refcount_find_left_extents(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -695,6 +711,7 @@ xfs_refcount_find_left_extents(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -769,6 +786,7 @@ xfs_refcount_find_right_extents(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -788,6 +806,7 @@ xfs_refcount_find_right_extents(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -1144,6 +1163,7 @@ xfs_refcount_adjust_extents(
 					goto out_error;
 				if (XFS_IS_CORRUPT(cur->bc_mp,
 						   found_tmp != 1)) {
+					xfs_btree_mark_sick(cur);
 					error = -EFSCORRUPTED;
 					goto out_error;
 				}
@@ -1182,6 +1202,7 @@ xfs_refcount_adjust_extents(
 		 */
 		if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount == 0) ||
 		    XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount > *aglen)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -1205,6 +1226,7 @@ xfs_refcount_adjust_extents(
 			if (error)
 				goto out_error;
 			if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto out_error;
 			}
@@ -1329,8 +1351,10 @@ xfs_refcount_continue_op(
 	struct xfs_perag		*pag = cur->bc_ag.pag;
 
 	if (XFS_IS_CORRUPT(mp, !xfs_verify_agbext(pag, new_agbno,
-					ri->ri_blockcount)))
+					ri->ri_blockcount))) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	ri->ri_startblock = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno);
 
@@ -1537,6 +1561,7 @@ xfs_refcount_find_shared(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -1554,6 +1579,7 @@ xfs_refcount_find_shared(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -1587,6 +1613,7 @@ xfs_refcount_find_shared(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -1684,6 +1711,7 @@ xfs_refcount_adjust_cow_extents(
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec &&
 				ext.rc_domain != XFS_REFC_DOMAIN_COW)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -1699,6 +1727,7 @@ xfs_refcount_adjust_cow_extents(
 		/* Adding a CoW reservation, there should be nothing here. */
 		if (XFS_IS_CORRUPT(cur->bc_mp,
 				   agbno + aglen > ext.rc_startblock)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -1716,6 +1745,7 @@ xfs_refcount_adjust_cow_extents(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, found_tmp != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -1723,14 +1753,17 @@ xfs_refcount_adjust_cow_extents(
 	case XFS_REFCOUNT_ADJUST_COW_FREE:
 		/* Removing a CoW reservation, there should be one extent. */
 		if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_startblock != agbno)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
 		if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount != aglen)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
 		if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_refcount != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -1742,6 +1775,7 @@ xfs_refcount_adjust_cow_extents(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -1904,6 +1938,7 @@ xfs_refcount_recover_extent(
 	if (xfs_refcount_check_irec(cur->bc_ag.pag, &rr->rr_rrec) != NULL ||
 	    XFS_IS_CORRUPT(cur->bc_mp,
 			   rr->rr_rrec.rc_domain != XFS_REFC_DOMAIN_COW)) {
+		xfs_btree_mark_sick(cur);
 		kfree(rr);
 		return -EFSCORRUPTED;
 	}
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 76a2e47b8a8ee..cad9b456db81f 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -135,6 +135,7 @@ xfs_rmap_insert(
 	if (error)
 		goto done;
 	if (XFS_IS_CORRUPT(rcur->bc_mp, i != 0)) {
+		xfs_btree_mark_sick(rcur);
 		error = -EFSCORRUPTED;
 		goto done;
 	}
@@ -148,6 +149,7 @@ xfs_rmap_insert(
 	if (error)
 		goto done;
 	if (XFS_IS_CORRUPT(rcur->bc_mp, i != 1)) {
+		xfs_btree_mark_sick(rcur);
 		error = -EFSCORRUPTED;
 		goto done;
 	}
@@ -177,6 +179,7 @@ xfs_rmap_delete(
 	if (error)
 		goto done;
 	if (XFS_IS_CORRUPT(rcur->bc_mp, i != 1)) {
+		xfs_btree_mark_sick(rcur);
 		error = -EFSCORRUPTED;
 		goto done;
 	}
@@ -185,6 +188,7 @@ xfs_rmap_delete(
 	if (error)
 		goto done;
 	if (XFS_IS_CORRUPT(rcur->bc_mp, i != 1)) {
+		xfs_btree_mark_sick(rcur);
 		error = -EFSCORRUPTED;
 		goto done;
 	}
@@ -516,7 +520,7 @@ xfs_rmap_lookup_le_range(
  */
 static int
 xfs_rmap_free_check_owner(
-	struct xfs_mount	*mp,
+	struct xfs_btree_cur	*cur,
 	uint64_t		ltoff,
 	struct xfs_rmap_irec	*rec,
 	xfs_filblks_t		len,
@@ -524,6 +528,7 @@ xfs_rmap_free_check_owner(
 	uint64_t		offset,
 	unsigned int		flags)
 {
+	struct xfs_mount	*mp = cur->bc_mp;
 	int			error = 0;
 
 	if (owner == XFS_RMAP_OWN_UNKNOWN)
@@ -533,12 +538,14 @@ xfs_rmap_free_check_owner(
 	if (XFS_IS_CORRUPT(mp,
 			   (flags & XFS_RMAP_UNWRITTEN) !=
 			   (rec->rm_flags & XFS_RMAP_UNWRITTEN))) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out;
 	}
 
 	/* Make sure the owner matches what we expect to find in the tree. */
 	if (XFS_IS_CORRUPT(mp, owner != rec->rm_owner)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out;
 	}
@@ -550,16 +557,19 @@ xfs_rmap_free_check_owner(
 	if (flags & XFS_RMAP_BMBT_BLOCK) {
 		if (XFS_IS_CORRUPT(mp,
 				   !(rec->rm_flags & XFS_RMAP_BMBT_BLOCK))) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out;
 		}
 	} else {
 		if (XFS_IS_CORRUPT(mp, rec->rm_offset > offset)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out;
 		}
 		if (XFS_IS_CORRUPT(mp,
 				   offset + len > ltoff + rec->rm_blockcount)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out;
 		}
@@ -622,6 +632,7 @@ xfs_rmap_unmap(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -643,6 +654,7 @@ xfs_rmap_unmap(
 		if (XFS_IS_CORRUPT(mp,
 				   bno <
 				   ltrec.rm_startblock + ltrec.rm_blockcount)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -669,6 +681,7 @@ xfs_rmap_unmap(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -681,12 +694,13 @@ xfs_rmap_unmap(
 			   ltrec.rm_startblock > bno ||
 			   ltrec.rm_startblock + ltrec.rm_blockcount <
 			   bno + len)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
 
 	/* Check owner information. */
-	error = xfs_rmap_free_check_owner(mp, ltoff, &ltrec, len, owner,
+	error = xfs_rmap_free_check_owner(cur, ltoff, &ltrec, len, owner,
 			offset, flags);
 	if (error)
 		goto out_error;
@@ -701,6 +715,7 @@ xfs_rmap_unmap(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -904,6 +919,7 @@ xfs_rmap_map(
 	if (XFS_IS_CORRUPT(mp,
 			   have_lt != 0 &&
 			   ltrec.rm_startblock + ltrec.rm_blockcount > bno)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -921,10 +937,12 @@ xfs_rmap_map(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(mp, have_gt != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
 		if (XFS_IS_CORRUPT(mp, bno + len > gtrec.rm_startblock)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -978,6 +996,7 @@ xfs_rmap_map(
 			if (error)
 				goto out_error;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto out_error;
 			}
@@ -1025,6 +1044,7 @@ xfs_rmap_map(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -1120,6 +1140,7 @@ xfs_rmap_convert(
 	if (error)
 		goto done;
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto done;
 	}
@@ -1157,12 +1178,14 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
 		if (XFS_IS_CORRUPT(mp,
 				   LEFT.rm_startblock + LEFT.rm_blockcount >
 				   bno)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1185,6 +1208,7 @@ xfs_rmap_convert(
 	if (error)
 		goto done;
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto done;
 	}
@@ -1197,10 +1221,12 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
 		if (XFS_IS_CORRUPT(mp, bno + len > RIGHT.rm_startblock)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1231,6 +1257,7 @@ xfs_rmap_convert(
 	if (error)
 		goto done;
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto done;
 	}
@@ -1250,6 +1277,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1261,6 +1289,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1268,6 +1297,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1279,6 +1309,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1286,6 +1317,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1309,6 +1341,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1316,6 +1349,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1335,6 +1369,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1346,6 +1381,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1353,6 +1389,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1423,6 +1460,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1465,6 +1503,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 0)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1480,6 +1519,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1513,6 +1553,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1526,6 +1567,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 0)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1538,6 +1580,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1610,6 +1653,7 @@ xfs_rmap_convert_shared(
 	if (error)
 		goto done;
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto done;
 	}
@@ -1638,6 +1682,7 @@ xfs_rmap_convert_shared(
 		if (XFS_IS_CORRUPT(mp,
 				   LEFT.rm_startblock + LEFT.rm_blockcount >
 				   bno)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1656,10 +1701,12 @@ xfs_rmap_convert_shared(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
 		if (XFS_IS_CORRUPT(mp, bno + len > RIGHT.rm_startblock)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1710,6 +1757,7 @@ xfs_rmap_convert_shared(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1736,6 +1784,7 @@ xfs_rmap_convert_shared(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1762,6 +1811,7 @@ xfs_rmap_convert_shared(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1785,6 +1835,7 @@ xfs_rmap_convert_shared(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1820,6 +1871,7 @@ xfs_rmap_convert_shared(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1865,6 +1917,7 @@ xfs_rmap_convert_shared(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1900,6 +1953,7 @@ xfs_rmap_convert_shared(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1938,6 +1992,7 @@ xfs_rmap_convert_shared(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -2027,6 +2082,7 @@ xfs_rmap_unmap_shared(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -2037,12 +2093,14 @@ xfs_rmap_unmap_shared(
 			   ltrec.rm_startblock > bno ||
 			   ltrec.rm_startblock + ltrec.rm_blockcount <
 			   bno + len)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
 
 	/* Make sure the owner matches what we expect to find in the tree. */
 	if (XFS_IS_CORRUPT(mp, owner != ltrec.rm_owner)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -2051,16 +2109,19 @@ xfs_rmap_unmap_shared(
 	if (XFS_IS_CORRUPT(mp,
 			   (flags & XFS_RMAP_UNWRITTEN) !=
 			   (ltrec.rm_flags & XFS_RMAP_UNWRITTEN))) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
 
 	/* Check the offset. */
 	if (XFS_IS_CORRUPT(mp, ltrec.rm_offset > offset)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
 	if (XFS_IS_CORRUPT(mp, offset > ltoff + ltrec.rm_blockcount)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -2117,6 +2178,7 @@ xfs_rmap_unmap_shared(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -2146,6 +2208,7 @@ xfs_rmap_unmap_shared(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -2225,6 +2288,7 @@ xfs_rmap_map_shared(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(mp, have_gt != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -2277,6 +2341,7 @@ xfs_rmap_map_shared(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -2480,10 +2545,14 @@ xfs_rmap_finish_one(
 		 * allocate blocks.
 		 */
 		error = xfs_free_extent_fix_freelist(tp, ri->ri_pag, &agbp);
-		if (error)
+		if (error) {
+			xfs_ag_mark_sick(ri->ri_pag, XFS_SICK_AG_AGFL);
 			return error;
-		if (XFS_IS_CORRUPT(tp->t_mountp, !agbp))
+		}
+		if (XFS_IS_CORRUPT(tp->t_mountp, !agbp)) {
+			xfs_ag_mark_sick(ri->ri_pag, XFS_SICK_AG_AGFL);
 			return -EFSCORRUPTED;
+		}
 
 		rcur = xfs_rmapbt_init_cursor(mp, tp, agbp, ri->ri_pag);
 	}
diff --git a/fs/xfs/scrub/refcount_repair.c b/fs/xfs/scrub/refcount_repair.c
index f38fccc42a209..9c39af03ee1d8 100644
--- a/fs/xfs/scrub/refcount_repair.c
+++ b/fs/xfs/scrub/refcount_repair.c
@@ -25,6 +25,7 @@
 #include "xfs_refcount_btree.h"
 #include "xfs_error.h"
 #include "xfs_ag.h"
+#include "xfs_health.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
@@ -253,8 +254,10 @@ xrep_refc_walk_rmaps(
 		error = xfs_rmap_get_rec(cur, &rmap, &have_gt);
 		if (error)
 			return error;
-		if (XFS_IS_CORRUPT(mp, !have_gt))
+		if (XFS_IS_CORRUPT(mp, !have_gt)) {
+			xfs_btree_mark_sick(cur);
 			return -EFSCORRUPTED;
+		}
 
 		if (rmap.rm_owner == XFS_RMAP_OWN_COW) {
 			error = xrep_refc_stash_cow(rr, rmap.rm_startblock,
@@ -425,8 +428,10 @@ xrep_refc_push_rmaps_at(
 	error = xfs_btree_decrement(sc->sa.rmap_cur, 0, &have_gt);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(sc->mp, !have_gt))
+	if (XFS_IS_CORRUPT(sc->mp, !have_gt)) {
+		xfs_btree_mark_sick(sc->sa.rmap_cur);
 		return -EFSCORRUPTED;
+	}
 
 	return 0;
 }
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index 305559bfe2a14..dcfa8e8e146a3 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -84,8 +84,10 @@ xfs_attr_shortform_list(
 		for (i = 0, sfe = &sf->list[0]; i < sf->hdr.count; i++) {
 			if (XFS_IS_CORRUPT(context->dp->i_mount,
 					   !xfs_attr_namecheck(sfe->nameval,
-							       sfe->namelen)))
+							       sfe->namelen))) {
+				xfs_dirattr_mark_sick(context->dp, XFS_ATTR_FORK);
 				return -EFSCORRUPTED;
+			}
 			context->put_listent(context,
 					     sfe->flags,
 					     sfe->nameval,
@@ -178,6 +180,7 @@ xfs_attr_shortform_list(
 		if (XFS_IS_CORRUPT(context->dp->i_mount,
 				   !xfs_attr_namecheck(sbp->name,
 						       sbp->namelen))) {
+			xfs_dirattr_mark_sick(context->dp, XFS_ATTR_FORK);
 			error = -EFSCORRUPTED;
 			goto out;
 		}
@@ -472,8 +475,10 @@ xfs_attr3_leaf_list_int(
 		}
 
 		if (XFS_IS_CORRUPT(context->dp->i_mount,
-				   !xfs_attr_namecheck(name, namelen)))
+				   !xfs_attr_namecheck(name, namelen))) {
+			xfs_dirattr_mark_sick(context->dp, XFS_ATTR_FORK);
 			return -EFSCORRUPTED;
+		}
 		context->put_listent(context, entry->flags,
 					      name, namelen, valuelen);
 		if (context->seen_enough)
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index 57f42c2af0a31..a457be34b3fff 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -120,8 +120,10 @@ xfs_dir2_sf_getdents(
 		ctx->pos = off & 0x7fffffff;
 		if (XFS_IS_CORRUPT(dp->i_mount,
 				   !xfs_dir2_namecheck(sfep->name,
-						       sfep->namelen)))
+						       sfep->namelen))) {
+			xfs_dirattr_mark_sick(dp, XFS_DATA_FORK);
 			return -EFSCORRUPTED;
+		}
 		if (!dir_emit(ctx, (char *)sfep->name, sfep->namelen, ino,
 			    xfs_dir3_get_dtype(mp, filetype)))
 			return 0;
@@ -213,6 +215,7 @@ xfs_dir2_block_getdents(
 		if (XFS_IS_CORRUPT(dp->i_mount,
 				   !xfs_dir2_namecheck(dep->name,
 						       dep->namelen))) {
+			xfs_dirattr_mark_sick(dp, XFS_DATA_FORK);
 			error = -EFSCORRUPTED;
 			goto out_rele;
 		}
@@ -467,6 +470,7 @@ xfs_dir2_leaf_getdents(
 		if (XFS_IS_CORRUPT(dp->i_mount,
 				   !xfs_dir2_namecheck(dep->name,
 						       dep->namelen))) {
+			xfs_dirattr_mark_sick(dp, XFS_DATA_FORK);
 			error = -EFSCORRUPTED;
 			break;
 		}
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index d5787991bb5b4..e38c4c46d1275 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -18,6 +18,7 @@
 #include "xfs_trace.h"
 #include "xfs_log.h"
 #include "xfs_ag.h"
+#include "xfs_health.h"
 
 /*
  * Notes on an efficient, low latency fstrim algorithm
@@ -204,6 +205,7 @@ xfs_trim_gather_extents(
 		if (error)
 			break;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			break;
 		}
diff --git a/fs/xfs/xfs_iwalk.c b/fs/xfs/xfs_iwalk.c
index 4ce85423ef3e0..6f26a791f17f0 100644
--- a/fs/xfs/xfs_iwalk.c
+++ b/fs/xfs/xfs_iwalk.c
@@ -297,8 +297,10 @@ xfs_iwalk_ag_start(
 	error = xfs_inobt_get_rec(*curpp, irec, has_more);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(mp, *has_more != 1))
+	if (XFS_IS_CORRUPT(mp, *has_more != 1)) {
+		xfs_btree_mark_sick(*curpp);
 		return -EFSCORRUPTED;
+	}
 
 	iwag->lastino = XFS_AGINO_TO_INO(mp, pag->pag_agno,
 				irec->ir_startino + XFS_INODES_PER_CHUNK - 1);
@@ -425,6 +427,7 @@ xfs_iwalk_ag(
 		rec_fsino = XFS_AGINO_TO_INO(mp, pag->pag_agno, irec->ir_startino);
 		if (iwag->lastino != NULLFSINO &&
 		    XFS_IS_CORRUPT(mp, iwag->lastino >= rec_fsino)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out;
 		}

[PATCH 1/3] xfs: add secondary and indirect classes to the health tracking system

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Establish two more classes of health tracking bits:

 * Indirect problems, which suggest problems in other health domains
   that we weren't able to preserve.

 * Secondary problems, which track state that's related to primary
   evidence of health problems; and

The first class we'll use in an upcoming patch to record in the AG
health status the fact that we ran out of memory and had to inactivate
an inode with defective metadata.  The second class we use to indicate
that repair knows that an inode is bad and we need to fix it later.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_health.h |   43 +++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_health.c        |   26 +++++++++++++++++---------
 2 files changed, 60 insertions(+), 9 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index a5b346b377cbb..26a2661571b1d 100644
--- a/fs/xfs/libxfs/xfs_health.h
+++ b/fs/xfs/libxfs/xfs_health.h
@@ -31,6 +31,19 @@
  *  - !checked && sick  => errors have been observed during normal operation,
  *                         but the metadata has not been checked thoroughly
  *  - !checked && !sick => has not been examined since mount
+ *
+ * Evidence of health problems can be sorted into three basic categories:
+ *
+ * a) Primary evidence, which signals that something is defective within the
+ *    general grouping of metadata.
+ *
+ * b) Secondary evidence, which are side effects of primary problem but are
+ *    not themselves problems.  These can be forgotten when the primary
+ *    health problems are addressed.
+ *
+ * c) Indirect evidence, which points to something being wrong in another
+ *    group, but we had to release resources and this is all that's left of
+ *    that state.
  */
 
 struct xfs_mount;
@@ -115,6 +128,36 @@ struct xfs_da_args;
 				 XFS_SICK_INO_DIR_ZAPPED | \
 				 XFS_SICK_INO_SYMLINK_ZAPPED)
 
+/* Secondary state related to (but not primary evidence of) health problems. */
+#define XFS_SICK_FS_SECONDARY	(0)
+#define XFS_SICK_RT_SECONDARY	(0)
+#define XFS_SICK_AG_SECONDARY	(0)
+#define XFS_SICK_INO_SECONDARY	(0)
+
+/* Evidence of health problems elsewhere. */
+#define XFS_SICK_FS_INDIRECT	(0)
+#define XFS_SICK_RT_INDIRECT	(0)
+#define XFS_SICK_AG_INDIRECT	(0)
+#define XFS_SICK_INO_INDIRECT	(0)
+
+/* All health masks. */
+#define XFS_SICK_FS_ALL	(XFS_SICK_FS_PRIMARY | \
+				 XFS_SICK_FS_SECONDARY | \
+				 XFS_SICK_FS_INDIRECT)
+
+#define XFS_SICK_RT_ALL	(XFS_SICK_RT_PRIMARY | \
+				 XFS_SICK_RT_SECONDARY | \
+				 XFS_SICK_RT_INDIRECT)
+
+#define XFS_SICK_AG_ALL	(XFS_SICK_AG_PRIMARY | \
+				 XFS_SICK_AG_SECONDARY | \
+				 XFS_SICK_AG_INDIRECT)
+
+#define XFS_SICK_INO_ALL	(XFS_SICK_INO_PRIMARY | \
+				 XFS_SICK_INO_SECONDARY | \
+				 XFS_SICK_INO_INDIRECT | \
+				 XFS_SICK_INO_ZAPPED)
+
 /*
  * These functions must be provided by the xfs implementation.  Function
  * behavior with respect to the first argument should be as follows:
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index 64dffc69a219d..6ea85cd6b66f8 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -97,7 +97,7 @@ xfs_fs_mark_sick(
 	struct xfs_mount	*mp,
 	unsigned int		mask)
 {
-	ASSERT(!(mask & ~XFS_SICK_FS_PRIMARY));
+	ASSERT(!(mask & ~XFS_SICK_FS_ALL));
 	trace_xfs_fs_mark_sick(mp, mask);
 
 	spin_lock(&mp->m_sb_lock);
@@ -124,11 +124,13 @@ xfs_fs_mark_healthy(
 	struct xfs_mount	*mp,
 	unsigned int		mask)
 {
-	ASSERT(!(mask & ~XFS_SICK_FS_PRIMARY));
+	ASSERT(!(mask & ~XFS_SICK_FS_ALL));
 	trace_xfs_fs_mark_healthy(mp, mask);
 
 	spin_lock(&mp->m_sb_lock);
 	mp->m_fs_sick &= ~mask;
+	if (!(mp->m_fs_sick & XFS_SICK_FS_PRIMARY))
+		mp->m_fs_sick &= ~XFS_SICK_FS_SECONDARY;
 	mp->m_fs_checked |= mask;
 	spin_unlock(&mp->m_sb_lock);
 }
@@ -152,7 +154,7 @@ xfs_rt_mark_sick(
 	struct xfs_mount	*mp,
 	unsigned int		mask)
 {
-	ASSERT(!(mask & ~XFS_SICK_RT_PRIMARY));
+	ASSERT(!(mask & ~XFS_SICK_RT_ALL));
 	trace_xfs_rt_mark_sick(mp, mask);
 
 	spin_lock(&mp->m_sb_lock);
@@ -180,11 +182,13 @@ xfs_rt_mark_healthy(
 	struct xfs_mount	*mp,
 	unsigned int		mask)
 {
-	ASSERT(!(mask & ~XFS_SICK_RT_PRIMARY));
+	ASSERT(!(mask & ~XFS_SICK_RT_ALL));
 	trace_xfs_rt_mark_healthy(mp, mask);
 
 	spin_lock(&mp->m_sb_lock);
 	mp->m_rt_sick &= ~mask;
+	if (!(mp->m_rt_sick & XFS_SICK_RT_PRIMARY))
+		mp->m_rt_sick &= ~XFS_SICK_RT_SECONDARY;
 	mp->m_rt_checked |= mask;
 	spin_unlock(&mp->m_sb_lock);
 }
@@ -225,7 +229,7 @@ xfs_ag_mark_sick(
 	struct xfs_perag	*pag,
 	unsigned int		mask)
 {
-	ASSERT(!(mask & ~XFS_SICK_AG_PRIMARY));
+	ASSERT(!(mask & ~XFS_SICK_AG_ALL));
 	trace_xfs_ag_mark_sick(pag->pag_mount, pag->pag_agno, mask);
 
 	spin_lock(&pag->pag_state_lock);
@@ -252,11 +256,13 @@ xfs_ag_mark_healthy(
 	struct xfs_perag	*pag,
 	unsigned int		mask)
 {
-	ASSERT(!(mask & ~XFS_SICK_AG_PRIMARY));
+	ASSERT(!(mask & ~XFS_SICK_AG_ALL));
 	trace_xfs_ag_mark_healthy(pag->pag_mount, pag->pag_agno, mask);
 
 	spin_lock(&pag->pag_state_lock);
 	pag->pag_sick &= ~mask;
+	if (!(pag->pag_sick & XFS_SICK_AG_PRIMARY))
+		pag->pag_sick &= ~XFS_SICK_AG_SECONDARY;
 	pag->pag_checked |= mask;
 	spin_unlock(&pag->pag_state_lock);
 }
@@ -280,7 +286,7 @@ xfs_inode_mark_sick(
 	struct xfs_inode	*ip,
 	unsigned int		mask)
 {
-	ASSERT(!(mask & ~(XFS_SICK_INO_PRIMARY | XFS_SICK_INO_ZAPPED)));
+	ASSERT(!(mask & ~XFS_SICK_INO_ALL));
 	trace_xfs_inode_mark_sick(ip, mask);
 
 	spin_lock(&ip->i_flags_lock);
@@ -303,7 +309,7 @@ xfs_inode_mark_checked(
 	struct xfs_inode	*ip,
 	unsigned int		mask)
 {
-	ASSERT(!(mask & ~(XFS_SICK_INO_PRIMARY | XFS_SICK_INO_ZAPPED)));
+	ASSERT(!(mask & ~XFS_SICK_INO_ALL));
 
 	spin_lock(&ip->i_flags_lock);
 	ip->i_checked |= mask;
@@ -316,11 +322,13 @@ xfs_inode_mark_healthy(
 	struct xfs_inode	*ip,
 	unsigned int		mask)
 {
-	ASSERT(!(mask & ~(XFS_SICK_INO_PRIMARY | XFS_SICK_INO_ZAPPED)));
+	ASSERT(!(mask & ~XFS_SICK_INO_ALL));
 	trace_xfs_inode_mark_healthy(ip, mask);
 
 	spin_lock(&ip->i_flags_lock);
 	ip->i_sick &= ~mask;
+	if (!(ip->i_sick & XFS_SICK_INO_PRIMARY))
+		ip->i_sick &= ~XFS_SICK_INO_SECONDARY;
 	ip->i_checked |= mask;
 	spin_unlock(&ip->i_flags_lock);
 }

[PATCH 2/3] xfs: remember sick inodes that get inactivated

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If an unhealthy inode gets inactivated, remember this fact in the
per-fs health summary.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_fs.h        |    1 +
 fs/xfs/libxfs/xfs_health.h    |    8 ++++++--
 fs/xfs/libxfs/xfs_inode_buf.c |    2 +-
 fs/xfs/scrub/health.c         |   12 +++++++++++-
 fs/xfs/xfs_health.c           |    1 +
 fs/xfs/xfs_inode.c            |   35 +++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_trace.h            |    1 +
 7 files changed, 56 insertions(+), 4 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 515cd27d3b3a8..b5c8da7e6aa99 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -294,6 +294,7 @@ struct xfs_ag_geometry {
 #define XFS_AG_GEOM_SICK_FINOBT	(1 << 7)  /* free inode index */
 #define XFS_AG_GEOM_SICK_RMAPBT	(1 << 8)  /* reverse mappings */
 #define XFS_AG_GEOM_SICK_REFCNTBT (1 << 9)  /* reference counts */
+#define XFS_AG_GEOM_SICK_INODES	(1 << 10) /* bad inodes were seen */
 
 /*
  * Structures for XFS_IOC_FSGROWFSDATA, XFS_IOC_FSGROWFSLOG & XFS_IOC_FSGROWFSRT
diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index 26a2661571b1d..df07c5877ba44 100644
--- a/fs/xfs/libxfs/xfs_health.h
+++ b/fs/xfs/libxfs/xfs_health.h
@@ -76,6 +76,7 @@ struct xfs_da_args;
 #define XFS_SICK_AG_FINOBT	(1 << 7)  /* free inode index */
 #define XFS_SICK_AG_RMAPBT	(1 << 8)  /* reverse mappings */
 #define XFS_SICK_AG_REFCNTBT	(1 << 9)  /* reference counts */
+#define XFS_SICK_AG_INODES	(1 << 10) /* inactivated bad inodes */
 
 /* Observable health issues for inode metadata. */
 #define XFS_SICK_INO_CORE	(1 << 0)  /* inode core */
@@ -92,6 +93,9 @@ struct xfs_da_args;
 #define XFS_SICK_INO_DIR_ZAPPED		(1 << 10) /* directory erased */
 #define XFS_SICK_INO_SYMLINK_ZAPPED	(1 << 11) /* symlink erased */
 
+/* Don't propagate sick status to ag health summary during inactivation */
+#define XFS_SICK_INO_FORGET	(1 << 12)
+
 /* Primary evidence of health problems in a given group. */
 #define XFS_SICK_FS_PRIMARY	(XFS_SICK_FS_COUNTERS | \
 				 XFS_SICK_FS_UQUOTA | \
@@ -132,12 +136,12 @@ struct xfs_da_args;
 #define XFS_SICK_FS_SECONDARY	(0)
 #define XFS_SICK_RT_SECONDARY	(0)
 #define XFS_SICK_AG_SECONDARY	(0)
-#define XFS_SICK_INO_SECONDARY	(0)
+#define XFS_SICK_INO_SECONDARY	(XFS_SICK_INO_FORGET)
 
 /* Evidence of health problems elsewhere. */
 #define XFS_SICK_FS_INDIRECT	(0)
 #define XFS_SICK_RT_INDIRECT	(0)
-#define XFS_SICK_AG_INDIRECT	(0)
+#define XFS_SICK_AG_INDIRECT	(XFS_SICK_AG_INODES)
 #define XFS_SICK_INO_INDIRECT	(0)
 
 /* All health masks. */
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 1280d6acd1c1b..d0dcce462bf42 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -139,7 +139,7 @@ xfs_imap_to_bp(
 			imap->im_len, XBF_UNMAPPED, bpp, &xfs_inode_buf_ops);
 	if (xfs_metadata_is_sick(error))
 		xfs_agno_mark_sick(mp, xfs_daddr_to_agno(mp, imap->im_blkno),
-				XFS_SICK_AG_INOBT);
+				XFS_SICK_AG_INODES);
 	return error;
 }
 
diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c
index 0f235501ed8a5..e26d71716c922 100644
--- a/fs/xfs/scrub/health.c
+++ b/fs/xfs/scrub/health.c
@@ -187,7 +187,17 @@ xchk_update_health(
 		if (!sc->ip)
 			return;
 		if (bad) {
-			xfs_inode_mark_sick(sc->ip, sc->sick_mask);
+			unsigned int	mask = sc->sick_mask;
+
+			/*
+			 * If we're coming in for repairs then we don't want
+			 * sickness flags to propagate to the incore health
+			 * status if the inode gets inactivated before we can
+			 * fix it.
+			 */
+			if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)
+				mask |= XFS_SICK_INO_FORGET;
+			xfs_inode_mark_sick(sc->ip, mask);
 			xfs_inode_mark_checked(sc->ip, sc->sick_mask);
 		} else
 			xfs_inode_mark_healthy(sc->ip, sc->sick_mask);
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index 6ea85cd6b66f8..2be1ac83f4c41 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -415,6 +415,7 @@ static const struct ioctl_sick_map ag_map[] = {
 	{ XFS_SICK_AG_FINOBT,	XFS_AG_GEOM_SICK_FINOBT },
 	{ XFS_SICK_AG_RMAPBT,	XFS_AG_GEOM_SICK_RMAPBT },
 	{ XFS_SICK_AG_REFCNTBT,	XFS_AG_GEOM_SICK_REFCNTBT },
+	{ XFS_SICK_AG_INODES,	XFS_AG_GEOM_SICK_INODES },
 	{ 0, 0 },
 };
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 6db00c5097ec0..04fa933061c7d 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1751,6 +1751,39 @@ xfs_inode_needs_inactive(
 	return xfs_can_free_eofblocks(ip, true);
 }
 
+/*
+ * Save health status somewhere, if we're dumping an inode with uncorrected
+ * errors and online repair isn't running.
+ */
+static inline void
+xfs_inactive_health(
+	struct xfs_inode	*ip)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_perag	*pag;
+	unsigned int		sick;
+	unsigned int		checked;
+
+	xfs_inode_measure_sickness(ip, &sick, &checked);
+	if (!sick)
+		return;
+
+	trace_xfs_inode_unfixed_corruption(ip, sick);
+
+	if (sick & XFS_SICK_INO_FORGET)
+		return;
+
+	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
+	if (!pag) {
+		/* There had better still be a perag structure! */
+		ASSERT(0);
+		return;
+	}
+
+	xfs_ag_mark_sick(pag, XFS_SICK_AG_INODES);
+	xfs_perag_put(pag);
+}
+
 /*
  * xfs_inactive
  *
@@ -1779,6 +1812,8 @@ xfs_inactive(
 	mp = ip->i_mount;
 	ASSERT(!xfs_iflags_test(ip, XFS_IRECOVERY));
 
+	xfs_inactive_health(ip);
+
 	/*
 	 * If this is a read-only mount, don't do this (would generate I/O)
 	 * unless we're in log recovery and cleaning the iunlinked list.
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 0efcdb79d10e5..7d075e426c5d0 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -3978,6 +3978,7 @@ DEFINE_EVENT(xfs_inode_corrupt_class, name,	\
 	TP_ARGS(ip, flags))
 DEFINE_INODE_CORRUPT_EVENT(xfs_inode_mark_sick);
 DEFINE_INODE_CORRUPT_EVENT(xfs_inode_mark_healthy);
+DEFINE_INODE_CORRUPT_EVENT(xfs_inode_unfixed_corruption);
 
 TRACE_EVENT(xfs_iwalk_ag,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,

[PATCH 3/3] xfs: update health status if we get a clean bill of health

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If scrub finds that everything is ok with the filesystem, we need a way
to tell the health tracking that it can let go of indirect health flags,
since indirect flags only mean that at some point in the past we lost
some context.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_fs.h |    3 ++
 fs/xfs/scrub/health.c  |   64 ++++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/health.h  |    1 +
 fs/xfs/scrub/repair.c  |    1 +
 fs/xfs/scrub/scrub.c   |    6 +++++
 fs/xfs/scrub/trace.h   |    4 ++-
 6 files changed, 77 insertions(+), 2 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index b5c8da7e6aa99..ca1b17d014377 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -714,9 +714,10 @@ struct xfs_scrub_metadata {
 #define XFS_SCRUB_TYPE_FSCOUNTERS 24	/* fs summary counters */
 #define XFS_SCRUB_TYPE_QUOTACHECK 25	/* quota counters */
 #define XFS_SCRUB_TYPE_NLINKS	26	/* inode link counts */
+#define XFS_SCRUB_TYPE_HEALTHY	27	/* everything checked out ok */
 
 /* Number of scrub subcommands. */
-#define XFS_SCRUB_TYPE_NR	27
+#define XFS_SCRUB_TYPE_NR	28
 
 /* i: Repair this metadata. */
 #define XFS_SCRUB_IFLAG_REPAIR		(1u << 0)
diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c
index e26d71716c922..664d57247ddf5 100644
--- a/fs/xfs/scrub/health.c
+++ b/fs/xfs/scrub/health.c
@@ -16,6 +16,7 @@
 #include "xfs_health.h"
 #include "scrub/scrub.h"
 #include "scrub/health.h"
+#include "scrub/common.h"
 
 /*
  * Scrub and In-Core Filesystem Health Assessments
@@ -151,6 +152,24 @@ xchk_file_looks_zapped(
 	return xfs_inode_has_sickness(sc->ip, mask);
 }
 
+/*
+ * Scrub gave the filesystem a clean bill of health, so clear all the indirect
+ * markers of past problems (at least for the fs and ags) so that we can be
+ * healthy again.
+ */
+STATIC void
+xchk_mark_all_healthy(
+	struct xfs_mount	*mp)
+{
+	struct xfs_perag	*pag;
+	xfs_agnumber_t		agno;
+
+	xfs_fs_mark_healthy(mp, XFS_SICK_FS_INDIRECT);
+	xfs_rt_mark_healthy(mp, XFS_SICK_RT_INDIRECT);
+	for_each_perag(mp, agno, pag)
+		xfs_ag_mark_healthy(pag, XFS_SICK_AG_INDIRECT);
+}
+
 /*
  * Update filesystem health assessments based on what we found and did.
  *
@@ -168,6 +187,18 @@ xchk_update_health(
 	struct xfs_perag	*pag;
 	bool			bad;
 
+	/*
+	 * The HEALTHY scrub type is a request from userspace to clear all the
+	 * indirect flags after a clean scan of the entire filesystem.  As such
+	 * there's no sick flag defined for it, so we branch here ahead of the
+	 * mask check.
+	 */
+	if (sc->sm->sm_type == XFS_SCRUB_TYPE_HEALTHY &&
+	    !(sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) {
+		xchk_mark_all_healthy(sc->mp);
+		return;
+	}
+
 	if (!sc->sick_mask)
 		return;
 
@@ -291,3 +322,36 @@ xchk_ag_btree_healthy_enough(
 
 	return true;
 }
+
+/*
+ * Quick scan to double-check that there isn't any evidence of lingering
+ * primary health problems.  If we're still clear, then the health update will
+ * take care of clearing the indirect evidence.
+ */
+int
+xchk_health_record(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_perag	*pag;
+	xfs_agnumber_t		agno;
+
+	unsigned int		sick;
+	unsigned int		checked;
+
+	xfs_fs_measure_sickness(mp, &sick, &checked);
+	if (sick & XFS_SICK_FS_PRIMARY)
+		xchk_set_corrupt(sc);
+
+	xfs_rt_measure_sickness(mp, &sick, &checked);
+	if (sick & XFS_SICK_RT_PRIMARY)
+		xchk_set_corrupt(sc);
+
+	for_each_perag(mp, agno, pag) {
+		xfs_ag_measure_sickness(pag, &sick, &checked);
+		if (sick & XFS_SICK_AG_PRIMARY)
+			xchk_set_corrupt(sc);
+	}
+
+	return 0;
+}
diff --git a/fs/xfs/scrub/health.h b/fs/xfs/scrub/health.h
index a731b2467399f..06d17941776cc 100644
--- a/fs/xfs/scrub/health.h
+++ b/fs/xfs/scrub/health.h
@@ -12,5 +12,6 @@ bool xchk_ag_btree_healthy_enough(struct xfs_scrub *sc, struct xfs_perag *pag,
 		xfs_btnum_t btnum);
 void xchk_mark_healthy_if_clean(struct xfs_scrub *sc, unsigned int mask);
 bool xchk_file_looks_zapped(struct xfs_scrub *sc, unsigned int mask);
+int xchk_health_record(struct xfs_scrub *sc);
 
 #endif /* __XFS_SCRUB_HEALTH_H__ */
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 7141b17789028..ab510cea96d86 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -30,6 +30,7 @@
 #include "xfs_errortag.h"
 #include "xfs_error.h"
 #include "xfs_reflink.h"
+#include "xfs_health.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index c0b99184bb3ef..0f23b7f36d4a5 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -378,6 +378,12 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.scrub	= xchk_nlinks,
 		.repair	= xrep_nlinks,
 	},
+	[XFS_SCRUB_TYPE_HEALTHY] = {	/* fs healthy; clean all reminders */
+		.type	= ST_FS,
+		.setup	= xchk_setup_fs,
+		.scrub	= xchk_health_record,
+		.repair = xrep_notsupported,
+	},
 };
 
 static int
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index fbadec84f45a2..86af0efa15d7c 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -69,6 +69,7 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_PQUOTA);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_FSCOUNTERS);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_QUOTACHECK);
 TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_NLINKS);
+TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_HEALTHY);
 
 #define XFS_SCRUB_TYPE_STRINGS \
 	{ XFS_SCRUB_TYPE_PROBE,		"probe" }, \
@@ -97,7 +98,8 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_NLINKS);
 	{ XFS_SCRUB_TYPE_PQUOTA,	"prjquota" }, \
 	{ XFS_SCRUB_TYPE_FSCOUNTERS,	"fscounters" }, \
 	{ XFS_SCRUB_TYPE_QUOTACHECK,	"quotacheck" }, \
-	{ XFS_SCRUB_TYPE_NLINKS,	"nlinks" }
+	{ XFS_SCRUB_TYPE_NLINKS,	"nlinks" }, \
+	{ XFS_SCRUB_TYPE_HEALTHY,	"healthy" }
 
 #define XFS_SCRUB_FLAG_STRINGS \
 	{ XFS_SCRUB_IFLAG_REPAIR,		"repair" }, \

[PATCH 1/1] xfs: repair summary counters

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Use the same summary counter calculation infrastructure to generate new
values for the in-core summary counters.   The difference between the
scrubber and the repairer is that the repairer will freeze the fs during
setup, which means that the values should match exactly.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Makefile                  |    1 +
 fs/xfs/scrub/fscounters.c        |   27 +++++++-------
 fs/xfs/scrub/fscounters.h        |   20 +++++++++++
 fs/xfs/scrub/fscounters_repair.c |   72 ++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/repair.h            |    2 +
 fs/xfs/scrub/scrub.c             |    2 +
 fs/xfs/scrub/trace.c             |    1 +
 fs/xfs/scrub/trace.h             |   21 +++++++++--
 8 files changed, 128 insertions(+), 18 deletions(-)
 create mode 100644 fs/xfs/scrub/fscounters.h
 create mode 100644 fs/xfs/scrub/fscounters_repair.c


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 1efc3b7727dc0..a6a455ac5a38b 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -192,6 +192,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   alloc_repair.o \
 				   bmap_repair.o \
 				   cow_repair.o \
+				   fscounters_repair.o \
 				   ialloc_repair.o \
 				   inode_repair.o \
 				   newbt.o \
diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c
index 893c5a6e3ddb0..d310737c88236 100644
--- a/fs/xfs/scrub/fscounters.c
+++ b/fs/xfs/scrub/fscounters.c
@@ -22,6 +22,7 @@
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
+#include "scrub/fscounters.h"
 
 /*
  * FS Summary Counters
@@ -48,17 +49,6 @@
  * our tolerance for mismatch between expected and actual counter values.
  */
 
-struct xchk_fscounters {
-	struct xfs_scrub	*sc;
-	uint64_t		icount;
-	uint64_t		ifree;
-	uint64_t		fdblocks;
-	uint64_t		frextents;
-	unsigned long long	icount_min;
-	unsigned long long	icount_max;
-	bool			frozen;
-};
-
 /*
  * Since the expected value computation is lockless but only browses incore
  * values, the percpu counters should be fairly close to each other.  However,
@@ -235,8 +225,13 @@ xchk_setup_fscounters(
 	 * Pause all writer activity in the filesystem while we're scrubbing to
 	 * reduce the likelihood of background perturbations to the counters
 	 * throwing off our calculations.
+	 *
+	 * If we're repairing, we need to prevent any other thread from
+	 * changing the global fs summary counters while we're repairing them.
+	 * This requires the fs to be frozen, which will disable background
+	 * reclaim and purge all inactive inodes.
 	 */
-	if (sc->flags & XCHK_TRY_HARDER) {
+	if ((sc->flags & XCHK_TRY_HARDER) || xchk_could_repair(sc)) {
 		error = xchk_fscounters_freeze(sc);
 		if (error)
 			return error;
@@ -254,7 +249,9 @@ xchk_setup_fscounters(
  * set the INCOMPLETE flag even when a negative errno is returned.  This care
  * must be taken with certain errno values (i.e. EFSBADCRC, EFSCORRUPTED,
  * ECANCELED) that are absorbed into a scrub state flag update by
- * xchk_*_process_error.
+ * xchk_*_process_error.  Scrub and repair share the same incore data
+ * structures, so the INCOMPLETE flag is critical to prevent a repair based on
+ * insufficient information.
  */
 
 /* Count free space btree blocks manually for pre-lazysbcount filesystems. */
@@ -482,6 +479,10 @@ xchk_fscount_within_range(
 	if (curr_value == expected)
 		return true;
 
+	/* We require exact matches when repair is running. */
+	if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)
+		return false;
+
 	min_value = min(old_value, curr_value);
 	max_value = max(old_value, curr_value);
 
diff --git a/fs/xfs/scrub/fscounters.h b/fs/xfs/scrub/fscounters.h
new file mode 100644
index 0000000000000..461a13d25f4b3
--- /dev/null
+++ b/fs/xfs/scrub/fscounters.h
@@ -0,0 +1,20 @@
+/* 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_FSCOUNTERS_H__
+#define __XFS_SCRUB_FSCOUNTERS_H__
+
+struct xchk_fscounters {
+	struct xfs_scrub	*sc;
+	uint64_t		icount;
+	uint64_t		ifree;
+	uint64_t		fdblocks;
+	uint64_t		frextents;
+	unsigned long long	icount_min;
+	unsigned long long	icount_max;
+	bool			frozen;
+};
+
+#endif /* __XFS_SCRUB_FSCOUNTERS_H__ */
diff --git a/fs/xfs/scrub/fscounters_repair.c b/fs/xfs/scrub/fscounters_repair.c
new file mode 100644
index 0000000000000..94cdb852bee46
--- /dev/null
+++ b/fs/xfs/scrub/fscounters_repair.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2018-2024 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_defer.h"
+#include "xfs_btree.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_alloc.h"
+#include "xfs_ialloc.h"
+#include "xfs_rmap.h"
+#include "xfs_health.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/fscounters.h"
+
+/*
+ * FS Summary Counters
+ * ===================
+ *
+ * We correct errors in the filesystem summary counters by setting them to the
+ * values computed during the obligatory scrub phase.  However, we must be
+ * careful not to allow any other thread to change the counters while we're
+ * computing and setting new values.  To achieve this, we freeze the
+ * filesystem for the whole operation if the REPAIR flag is set.  The checking
+ * function is stricter when we've frozen the fs.
+ */
+
+/*
+ * Reset the superblock counters.  Caller is responsible for freezing the
+ * filesystem during the calculation and reset phases.
+ */
+int
+xrep_fscounters(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_mount	*mp = sc->mp;
+	struct xchk_fscounters	*fsc = sc->buf;
+
+	/*
+	 * Reinitialize the in-core counters from what we computed.  We froze
+	 * the filesystem, so there shouldn't be anyone else trying to modify
+	 * these counters.
+	 */
+	if (!fsc->frozen) {
+		ASSERT(fsc->frozen);
+		return -EFSCORRUPTED;
+	}
+
+	trace_xrep_reset_counters(mp, fsc);
+
+	percpu_counter_set(&mp->m_icount, fsc->icount);
+	percpu_counter_set(&mp->m_ifree, fsc->ifree);
+	percpu_counter_set(&mp->m_fdblocks, fsc->fdblocks);
+	percpu_counter_set(&mp->m_frextents, fsc->frextents);
+	mp->m_sb.sb_frextents = fsc->frextents;
+
+	return 0;
+}
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 8edac0150e960..2ff2bb79c540c 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -117,6 +117,7 @@ int xrep_bmap_data(struct xfs_scrub *sc);
 int xrep_bmap_attr(struct xfs_scrub *sc);
 int xrep_bmap_cow(struct xfs_scrub *sc);
 int xrep_nlinks(struct xfs_scrub *sc);
+int xrep_fscounters(struct xfs_scrub *sc);
 
 #ifdef CONFIG_XFS_RT
 int xrep_rtbitmap(struct xfs_scrub *sc);
@@ -198,6 +199,7 @@ xrep_setup_nothing(
 #define xrep_quota			xrep_notsupported
 #define xrep_quotacheck			xrep_notsupported
 #define xrep_nlinks			xrep_notsupported
+#define xrep_fscounters			xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 0f23b7f36d4a5..aeac9cae4ad4c 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -364,7 +364,7 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.type	= ST_FS,
 		.setup	= xchk_setup_fscounters,
 		.scrub	= xchk_fscounters,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_fscounters,
 	},
 	[XFS_SCRUB_TYPE_QUOTACHECK] = {	/* quota counters */
 		.type	= ST_FS,
diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c
index 2d5a330afe10c..b8f3795f7d9b4 100644
--- a/fs/xfs/scrub/trace.c
+++ b/fs/xfs/scrub/trace.c
@@ -24,6 +24,7 @@
 #include "scrub/quota.h"
 #include "scrub/iscan.h"
 #include "scrub/nlinks.h"
+#include "scrub/fscounters.h"
 
 /* Figure out which block the btree cursor was pointing to. */
 static inline xfs_fsblock_t
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 86af0efa15d7c..88e921f4efd26 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -24,6 +24,7 @@ struct xfarray_sortinfo;
 struct xchk_dqiter;
 struct xchk_iscan;
 struct xchk_nlink;
+struct xchk_fscounters;
 
 /*
  * ftrace's __print_symbolic requires that all enum values be wrapped in the
@@ -1777,16 +1778,28 @@ TRACE_EVENT(xrep_calc_ag_resblks_btsize,
 		  __entry->refcbt_sz)
 )
 TRACE_EVENT(xrep_reset_counters,
-	TP_PROTO(struct xfs_mount *mp),
-	TP_ARGS(mp),
+	TP_PROTO(struct xfs_mount *mp, struct xchk_fscounters *fsc),
+	TP_ARGS(mp, fsc),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
+		__field(uint64_t, icount)
+		__field(uint64_t, ifree)
+		__field(uint64_t, fdblocks)
+		__field(uint64_t, frextents)
 	),
 	TP_fast_assign(
 		__entry->dev = mp->m_super->s_dev;
+		__entry->icount = fsc->icount;
+		__entry->ifree = fsc->ifree;
+		__entry->fdblocks = fsc->fdblocks;
+		__entry->frextents = fsc->frextents;
 	),
-	TP_printk("dev %d:%d",
-		  MAJOR(__entry->dev), MINOR(__entry->dev))
+	TP_printk("dev %d:%d icount %llu ifree %llu fdblocks %llu frextents %llu",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->icount,
+		  __entry->ifree,
+		  __entry->fdblocks,
+		  __entry->frextents)
 )
 
 DECLARE_EVENT_CLASS(xrep_newbt_extent_class,

[PATCH 1/9] xfs: dump xfiles for debugging purposes

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add a debug function to dump an xfile's contents for debug purposes.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/xfile.c |   98 ++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/xfile.h |    2 +
 2 files changed, 100 insertions(+)


diff --git a/fs/xfs/scrub/xfile.c b/fs/xfs/scrub/xfile.c
index 090c3ead43fdf..a76677cba6a3b 100644
--- a/fs/xfs/scrub/xfile.c
+++ b/fs/xfs/scrub/xfile.c
@@ -417,3 +417,101 @@ xfile_put_page(
 		return -EIO;
 	return 0;
 }
+
+/* Dump an xfile to dmesg. */
+int
+xfile_dump(
+	struct xfile		*xf)
+{
+	struct xfile_stat	sb;
+	struct inode		*inode = file_inode(xf->file);
+	struct address_space	*mapping = inode->i_mapping;
+	loff_t			holepos = 0;
+	loff_t			datapos;
+	loff_t			ret;
+	unsigned int		pflags;
+	bool			all_zeroes = true;
+	int			error = 0;
+
+	error = xfile_stat(xf, &sb);
+	if (error)
+		return error;
+
+	printk(KERN_ALERT "xfile ino 0x%lx isize 0x%llx dump:", inode->i_ino,
+			sb.size);
+	pflags = memalloc_nofs_save();
+
+	while ((ret = vfs_llseek(xf->file, holepos, SEEK_DATA)) >= 0) {
+		datapos = rounddown_64(ret, PAGE_SIZE);
+		ret = vfs_llseek(xf->file, datapos, SEEK_HOLE);
+		if (ret < 0)
+			break;
+		holepos = min_t(loff_t, sb.size, roundup_64(ret, PAGE_SIZE));
+
+		while (datapos < holepos) {
+			struct page	*page = NULL;
+			void		*p, *kaddr;
+			u64		datalen = holepos - datapos;
+			unsigned int	pagepos;
+			unsigned int	pagelen;
+
+			cond_resched();
+
+			if (fatal_signal_pending(current)) {
+				error = -EINTR;
+				goto out_pflags;
+			}
+
+			pagelen = min_t(u64, datalen, PAGE_SIZE);
+
+			page = shmem_read_mapping_page_gfp(mapping,
+					datapos >> PAGE_SHIFT, __GFP_NOWARN);
+			if (IS_ERR(page)) {
+				error = PTR_ERR(page);
+				if (error == -EIO)
+					printk(KERN_ALERT "%.8llx: poisoned",
+							datapos);
+				else if (error != -ENOMEM)
+					goto out_pflags;
+
+				goto next_pgoff;
+			}
+
+			if (!PageUptodate(page))
+				goto next_page;
+
+			kaddr = kmap_local_page(page);
+			p = kaddr;
+
+			for (pagepos = 0; pagepos < pagelen; pagepos += 16) {
+				char prefix[16];
+				unsigned int linelen;
+
+				linelen = min_t(unsigned int, pagelen, 16);
+
+				if (!memchr_inv(p + pagepos, 0, linelen))
+					continue;
+
+				snprintf(prefix, 16, "%.8llx: ",
+						datapos + pagepos);
+
+				all_zeroes = false;
+				print_hex_dump(KERN_ALERT, prefix,
+						DUMP_PREFIX_NONE, 16, 1,
+						p + pagepos, linelen, true);
+			}
+			kunmap_local(kaddr);
+next_page:
+			put_page(page);
+next_pgoff:
+			datapos += PAGE_SIZE;
+		}
+	}
+	if (all_zeroes)
+		printk(KERN_ALERT "<all zeroes>");
+	if (ret != -ENXIO)
+		error = ret;
+out_pflags:
+	memalloc_nofs_restore(pflags);
+	return error;
+}
diff --git a/fs/xfs/scrub/xfile.h b/fs/xfs/scrub/xfile.h
index d56643b0f429e..9022fe8924b94 100644
--- a/fs/xfs/scrub/xfile.h
+++ b/fs/xfs/scrub/xfile.h
@@ -74,4 +74,6 @@ int xfile_get_page(struct xfile *xf, loff_t offset, unsigned int len,
 		struct xfile_page *xbuf);
 int xfile_put_page(struct xfile *xf, struct xfile_page *xbuf);
 
+int xfile_dump(struct xfile *xf);
+
 #endif /* __XFS_SCRUB_XFILE_H__ */

[PATCH 2/9] xfs: teach buftargs to maintain their own buffer hashtable

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Currently, cached buffers are indexed by per-AG hashtables.  This works
great for the data device, but won't work for in-memory btrees.  Make it
so that buftargs can index buffers too.

We accomplish this by hoisting the rhashtable and its lock into a
separate xfs_buf_cache structure and reworking various functions to use
it.  Next, we introduce to the buftarg a new XFS_BUFTARG_SELF_CACHED
flag to indicate that the buftarg's cache is active (vs. the per-ag
cache for the regular filesystem).

Finally, make it so that each xfs_buf points to its cache if there is
one.  This is how we distinguish uncached buffers from now on.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_ag.c |    6 +-
 fs/xfs/libxfs/xfs_ag.h |    4 -
 fs/xfs/xfs_buf.c       |  143 +++++++++++++++++++++++++++++++++---------------
 fs/xfs/xfs_buf.h       |   10 +++
 fs/xfs/xfs_mount.h     |    3 -
 5 files changed, 111 insertions(+), 55 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index ccad54d1dadaf..6a7bfc6797d23 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -264,7 +264,7 @@ xfs_free_perag(
 		xfs_defer_drain_free(&pag->pag_intents_drain);
 
 		cancel_delayed_work_sync(&pag->pag_blockgc_work);
-		xfs_buf_hash_destroy(pag);
+		xfs_buf_cache_destroy(&pag->pag_bcache);
 
 		/* drop the mount's active reference */
 		xfs_perag_rele(pag);
@@ -394,7 +394,7 @@ xfs_initialize_perag(
 		pag->pagb_tree = RB_ROOT;
 #endif /* __KERNEL__ */
 
-		error = xfs_buf_hash_init(pag);
+		error = xfs_buf_cache_init(&pag->pag_bcache);
 		if (error)
 			goto out_remove_pag;
 
@@ -434,7 +434,7 @@ xfs_initialize_perag(
 		pag = radix_tree_delete(&mp->m_perag_tree, index);
 		if (!pag)
 			break;
-		xfs_buf_hash_destroy(pag);
+		xfs_buf_cache_destroy(&pag->pag_bcache);
 		xfs_defer_drain_free(&pag->pag_intents_drain);
 		kmem_free(pag);
 	}
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 67c3260ee789f..fe5852873b82d 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -104,9 +104,7 @@ struct xfs_perag {
 	int		pag_ici_reclaimable;	/* reclaimable inodes */
 	unsigned long	pag_ici_reclaim_cursor;	/* reclaim restart point */
 
-	/* buffer cache index */
-	spinlock_t	pag_buf_lock;	/* lock for pag_buf_hash */
-	struct rhashtable pag_buf_hash;
+	struct xfs_buf_cache	pag_bcache;
 
 	/* background prealloc block trimming */
 	struct delayed_work	pag_blockgc_work;
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index ec4bd7a24d88c..0ae9a37cd1ddb 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -499,18 +499,18 @@ static const struct rhashtable_params xfs_buf_hash_params = {
 };
 
 int
-xfs_buf_hash_init(
-	struct xfs_perag	*pag)
+xfs_buf_cache_init(
+	struct xfs_buf_cache	*bch)
 {
-	spin_lock_init(&pag->pag_buf_lock);
-	return rhashtable_init(&pag->pag_buf_hash, &xfs_buf_hash_params);
+	spin_lock_init(&bch->bc_lock);
+	return rhashtable_init(&bch->bc_hash, &xfs_buf_hash_params);
 }
 
 void
-xfs_buf_hash_destroy(
-	struct xfs_perag	*pag)
+xfs_buf_cache_destroy(
+	struct xfs_buf_cache	*bch)
 {
-	rhashtable_destroy(&pag->pag_buf_hash);
+	rhashtable_destroy(&bch->bc_hash);
 }
 
 static int
@@ -573,7 +573,7 @@ xfs_buf_find_lock(
 
 static inline int
 xfs_buf_lookup(
-	struct xfs_perag	*pag,
+	struct xfs_buf_cache	*bch,
 	struct xfs_buf_map	*map,
 	xfs_buf_flags_t		flags,
 	struct xfs_buf		**bpp)
@@ -582,7 +582,7 @@ xfs_buf_lookup(
 	int			error;
 
 	rcu_read_lock();
-	bp = rhashtable_lookup(&pag->pag_buf_hash, map, xfs_buf_hash_params);
+	bp = rhashtable_lookup(&bch->bc_hash, map, xfs_buf_hash_params);
 	if (!bp || !atomic_inc_not_zero(&bp->b_hold)) {
 		rcu_read_unlock();
 		return -ENOENT;
@@ -607,6 +607,7 @@ xfs_buf_lookup(
 static int
 xfs_buf_find_insert(
 	struct xfs_buftarg	*btp,
+	struct xfs_buf_cache	*bch,
 	struct xfs_perag	*pag,
 	struct xfs_buf_map	*cmap,
 	struct xfs_buf_map	*map,
@@ -635,18 +636,18 @@ xfs_buf_find_insert(
 			goto out_free_buf;
 	}
 
-	spin_lock(&pag->pag_buf_lock);
-	bp = rhashtable_lookup_get_insert_fast(&pag->pag_buf_hash,
+	spin_lock(&bch->bc_lock);
+	bp = rhashtable_lookup_get_insert_fast(&bch->bc_hash,
 			&new_bp->b_rhash_head, xfs_buf_hash_params);
 	if (IS_ERR(bp)) {
 		error = PTR_ERR(bp);
-		spin_unlock(&pag->pag_buf_lock);
+		spin_unlock(&bch->bc_lock);
 		goto out_free_buf;
 	}
 	if (bp) {
 		/* found an existing buffer */
 		atomic_inc(&bp->b_hold);
-		spin_unlock(&pag->pag_buf_lock);
+		spin_unlock(&bch->bc_lock);
 		error = xfs_buf_find_lock(bp, flags);
 		if (error)
 			xfs_buf_rele(bp);
@@ -657,17 +658,38 @@ xfs_buf_find_insert(
 
 	/* The new buffer keeps the perag reference until it is freed. */
 	new_bp->b_pag = pag;
-	spin_unlock(&pag->pag_buf_lock);
+	new_bp->b_cache = bch;
+	spin_unlock(&bch->bc_lock);
 	*bpp = new_bp;
 	return 0;
 
 out_free_buf:
 	xfs_buf_free(new_bp);
 out_drop_pag:
-	xfs_perag_put(pag);
+	if (pag)
+		xfs_perag_put(pag);
 	return error;
 }
 
+/* Find the buffer cache for a particular buftarg and map. */
+static inline struct xfs_buf_cache *
+xfs_buftarg_get_cache(
+	struct xfs_buftarg		*btp,
+	const struct xfs_buf_map	*map,
+	struct xfs_perag		**pagp)
+{
+	struct xfs_mount		*mp = btp->bt_mount;
+
+	if (btp->bt_cache) {
+		*pagp = NULL;
+		return btp->bt_cache;
+	}
+
+	*pagp = xfs_perag_get(mp, xfs_daddr_to_agno(mp, map->bm_bn));
+	ASSERT(*pagp != NULL);
+	return &(*pagp)->pag_bcache;
+}
+
 /*
  * Assembles a buffer covering the specified range. The code is optimised for
  * cache hits, as metadata intensive workloads will see 3 orders of magnitude
@@ -681,6 +703,7 @@ xfs_buf_get_map(
 	xfs_buf_flags_t		flags,
 	struct xfs_buf		**bpp)
 {
+	struct xfs_buf_cache	*bch;
 	struct xfs_perag	*pag;
 	struct xfs_buf		*bp = NULL;
 	struct xfs_buf_map	cmap = { .bm_bn = map[0].bm_bn };
@@ -696,10 +719,9 @@ xfs_buf_get_map(
 	if (error)
 		return error;
 
-	pag = xfs_perag_get(btp->bt_mount,
-			    xfs_daddr_to_agno(btp->bt_mount, cmap.bm_bn));
+	bch = xfs_buftarg_get_cache(btp, &cmap, &pag);
 
-	error = xfs_buf_lookup(pag, &cmap, flags, &bp);
+	error = xfs_buf_lookup(bch, &cmap, flags, &bp);
 	if (error && error != -ENOENT)
 		goto out_put_perag;
 
@@ -711,13 +733,14 @@ xfs_buf_get_map(
 			goto out_put_perag;
 
 		/* xfs_buf_find_insert() consumes the perag reference. */
-		error = xfs_buf_find_insert(btp, pag, &cmap, map, nmaps,
+		error = xfs_buf_find_insert(btp, bch, pag, &cmap, map, nmaps,
 				flags, &bp);
 		if (error)
 			return error;
 	} else {
 		XFS_STATS_INC(btp->bt_mount, xb_get_locked);
-		xfs_perag_put(pag);
+		if (pag)
+			xfs_perag_put(pag);
 	}
 
 	/* We do not hold a perag reference anymore. */
@@ -745,7 +768,8 @@ xfs_buf_get_map(
 	return 0;
 
 out_put_perag:
-	xfs_perag_put(pag);
+	if (pag)
+		xfs_perag_put(pag);
 	return error;
 }
 
@@ -999,12 +1023,13 @@ xfs_buf_rele(
 	struct xfs_buf		*bp)
 {
 	struct xfs_perag	*pag = bp->b_pag;
+	struct xfs_buf_cache	*bch = bp->b_cache;
 	bool			release;
 	bool			freebuf = false;
 
 	trace_xfs_buf_rele(bp, _RET_IP_);
 
-	if (!pag) {
+	if (!bch) {
 		ASSERT(list_empty(&bp->b_lru));
 		if (atomic_dec_and_test(&bp->b_hold)) {
 			xfs_buf_ioacct_dec(bp);
@@ -1026,7 +1051,7 @@ xfs_buf_rele(
 	 * leading to a use-after-free scenario.
 	 */
 	spin_lock(&bp->b_lock);
-	release = atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock);
+	release = atomic_dec_and_lock(&bp->b_hold, &bch->bc_lock);
 	if (!release) {
 		/*
 		 * Drop the in-flight state if the buffer is already on the LRU
@@ -1051,7 +1076,7 @@ xfs_buf_rele(
 			bp->b_state &= ~XFS_BSTATE_DISPOSE;
 			atomic_inc(&bp->b_hold);
 		}
-		spin_unlock(&pag->pag_buf_lock);
+		spin_unlock(&bch->bc_lock);
 	} else {
 		/*
 		 * most of the time buffers will already be removed from the
@@ -1066,10 +1091,13 @@ xfs_buf_rele(
 		}
 
 		ASSERT(!(bp->b_flags & _XBF_DELWRI_Q));
-		rhashtable_remove_fast(&pag->pag_buf_hash, &bp->b_rhash_head,
-				       xfs_buf_hash_params);
-		spin_unlock(&pag->pag_buf_lock);
-		xfs_perag_put(pag);
+		rhashtable_remove_fast(&bch->bc_hash, &bp->b_rhash_head,
+				xfs_buf_hash_params);
+		spin_unlock(&bch->bc_lock);
+		if (pag)
+			xfs_perag_put(pag);
+		bp->b_cache = NULL;
+		bp->b_pag = NULL;
 		freebuf = true;
 	}
 
@@ -1991,25 +2019,18 @@ xfs_setsize_buftarg_early(
 	return xfs_setsize_buftarg(btp, bdev_logical_block_size(btp->bt_bdev));
 }
 
-struct xfs_buftarg *
-xfs_alloc_buftarg(
+static struct xfs_buftarg *
+xfs_alloc_buftarg_common(
 	struct xfs_mount	*mp,
-	struct bdev_handle	*bdev_handle)
+	const char		*descr)
 {
-	xfs_buftarg_t		*btp;
-	const struct dax_holder_operations *ops = NULL;
+	struct xfs_buftarg	*btp;
 
-#if defined(CONFIG_FS_DAX) && defined(CONFIG_MEMORY_FAILURE)
-	ops = &xfs_dax_holder_operations;
-#endif
 	btp = kmem_zalloc(sizeof(*btp), KM_NOFS);
+	if (!btp)
+		return NULL;
 
 	btp->bt_mount = mp;
-	btp->bt_bdev_handle = bdev_handle;
-	btp->bt_dev = bdev_handle->bdev->bd_dev;
-	btp->bt_bdev = bdev_handle->bdev;
-	btp->bt_daxdev = fs_dax_get_by_bdev(btp->bt_bdev, &btp->bt_dax_part_off,
-					    mp, ops);
 
 	/*
 	 * Buffer IO error rate limiting. Limit it to no more than 10 messages
@@ -2018,17 +2039,14 @@ xfs_alloc_buftarg(
 	ratelimit_state_init(&btp->bt_ioerror_rl, 30 * HZ,
 			     DEFAULT_RATELIMIT_BURST);
 
-	if (xfs_setsize_buftarg_early(btp))
-		goto error_free;
-
 	if (list_lru_init(&btp->bt_lru))
 		goto error_free;
 
 	if (percpu_counter_init(&btp->bt_io_count, 0, GFP_KERNEL))
 		goto error_lru;
 
-	btp->bt_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE, "xfs-buf:%s",
-					  mp->m_super->s_id);
+	btp->bt_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE, "xfs-%s:%s",
+			descr, mp->m_super->s_id);
 	if (!btp->bt_shrinker)
 		goto error_pcpu;
 
@@ -2057,6 +2075,39 @@ xfs_buf_list_del(
 	wake_up_var(&bp->b_list);
 }
 
+/* Allocate a buffer cache target for a persistent block device. */
+struct xfs_buftarg *
+xfs_alloc_buftarg(
+	struct xfs_mount	*mp,
+	struct bdev_handle	*bdev_handle)
+{
+	struct xfs_buftarg	*btp;
+	const struct dax_holder_operations *ops = NULL;
+
+#if defined(CONFIG_FS_DAX) && defined(CONFIG_MEMORY_FAILURE)
+	ops = &xfs_dax_holder_operations;
+#endif
+
+	btp = xfs_alloc_buftarg_common(mp, "buf");
+	if (!btp)
+		return NULL;
+
+	btp->bt_bdev_handle = bdev_handle;
+	btp->bt_dev = bdev_handle->bdev->bd_dev;
+	btp->bt_bdev = bdev_handle->bdev;
+	btp->bt_daxdev = fs_dax_get_by_bdev(btp->bt_bdev, &btp->bt_dax_part_off,
+					    mp, ops);
+
+	if (xfs_setsize_buftarg_early(btp))
+		goto error_free;
+
+	return btp;
+
+error_free:
+	xfs_free_buftarg(btp);
+	return NULL;
+}
+
 /*
  * Cancel a delayed write list.
  *
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index b470de08a46ca..d4b6b58b16009 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -83,6 +83,14 @@ typedef unsigned int xfs_buf_flags_t;
 #define XFS_BSTATE_DISPOSE	 (1 << 0)	/* buffer being discarded */
 #define XFS_BSTATE_IN_FLIGHT	 (1 << 1)	/* I/O in flight */
 
+struct xfs_buf_cache {
+	spinlock_t		bc_lock;
+	struct rhashtable	bc_hash;
+};
+
+int xfs_buf_cache_init(struct xfs_buf_cache *bch);
+void xfs_buf_cache_destroy(struct xfs_buf_cache *bch);
+
 /*
  * The xfs_buftarg contains 2 notions of "sector size" -
  *
@@ -103,6 +111,7 @@ typedef struct xfs_buftarg {
 	struct dax_device	*bt_daxdev;
 	u64			bt_dax_part_off;
 	struct xfs_mount	*bt_mount;
+	struct xfs_buf_cache	*bt_cache;
 	unsigned int		bt_meta_sectorsize;
 	size_t			bt_meta_sectormask;
 	size_t			bt_logical_sectorsize;
@@ -212,6 +221,7 @@ struct xfs_buf {
 	int			b_last_error;
 
 	const struct xfs_buf_ops	*b_ops;
+	struct xfs_buf_cache	*b_cache;
 	struct rcu_head		b_rcu;
 };
 
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index e86dfe67894fb..772c913bcd2bd 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -505,9 +505,6 @@ xfs_daddr_to_agbno(struct xfs_mount *mp, xfs_daddr_t d)
 	return (xfs_agblock_t) do_div(ld, mp->m_sb.sb_agblocks);
 }
 
-int xfs_buf_hash_init(struct xfs_perag *pag);
-void xfs_buf_hash_destroy(struct xfs_perag *pag);
-
 extern void	xfs_uuid_table_free(void);
 extern uint64_t xfs_default_resblks(xfs_mount_t *mp);
 extern int	xfs_mountfs(xfs_mount_t *mp);

[PATCH 3/9] xfs: create buftarg helpers to abstract block_device operations

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

In the next few patches, we're going into introduce buffer targets that
are not block devices.  Introduce block_device helpers so that the
compiler can check that we're not feeding an xfile object to something
expecting a block device.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_aops.c        |    5 ++++-
 fs/xfs/xfs_bmap_util.c   |    8 ++++----
 fs/xfs/xfs_buf.h         |   37 +++++++++++++++++++++++++++++++++++--
 fs/xfs/xfs_discard.c     |    9 +++++----
 fs/xfs/xfs_file.c        |    6 +++---
 fs/xfs/xfs_ioctl.c       |    3 ++-
 fs/xfs/xfs_iomap.c       |    4 ++--
 fs/xfs/xfs_log.c         |    4 ++--
 fs/xfs/xfs_log_recover.c |    3 ++-
 9 files changed, 59 insertions(+), 20 deletions(-)


diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 465d7630bb218..3001ddf48d6c6 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -569,7 +569,10 @@ xfs_iomap_swapfile_activate(
 	struct file			*swap_file,
 	sector_t			*span)
 {
-	sis->bdev = xfs_inode_buftarg(XFS_I(file_inode(swap_file)))->bt_bdev;
+	struct xfs_inode		*ip = XFS_I(file_inode(swap_file));
+	struct xfs_buftarg		*btp = xfs_inode_buftarg(ip);
+
+	sis->bdev = xfs_buftarg_bdev(btp);
 	return iomap_swapfile_activate(sis, swap_file, span,
 			&xfs_read_iomap_ops);
 }
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 731260a5af6db..6b5a9ad18fcb3 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -63,10 +63,10 @@ xfs_zero_extent(
 	xfs_daddr_t		sector = xfs_fsb_to_db(ip, start_fsb);
 	sector_t		block = XFS_BB_TO_FSBT(mp, sector);
 
-	return blkdev_issue_zeroout(target->bt_bdev,
-		block << (mp->m_super->s_blocksize_bits - 9),
-		count_fsb << (mp->m_super->s_blocksize_bits - 9),
-		GFP_NOFS, 0);
+	return xfs_buftarg_zeroout(target,
+			block << (mp->m_super->s_blocksize_bits - 9),
+			count_fsb << (mp->m_super->s_blocksize_bits - 9),
+			GFP_NOFS, 0);
 }
 
 #ifdef CONFIG_XFS_RT
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index d4b6b58b16009..4e964470587ce 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -382,8 +382,41 @@ extern void xfs_buftarg_wait(struct xfs_buftarg *);
 extern void xfs_buftarg_drain(struct xfs_buftarg *);
 extern int xfs_setsize_buftarg(struct xfs_buftarg *, unsigned int);
 
-#define xfs_getsize_buftarg(buftarg)	block_size((buftarg)->bt_bdev)
-#define xfs_readonly_buftarg(buftarg)	bdev_read_only((buftarg)->bt_bdev)
+static inline struct block_device *
+xfs_buftarg_bdev(struct xfs_buftarg *btp)
+{
+	return btp->bt_bdev;
+}
+
+static inline unsigned int
+xfs_getsize_buftarg(struct xfs_buftarg *btp)
+{
+	return block_size(btp->bt_bdev);
+}
+
+static inline bool
+xfs_readonly_buftarg(struct xfs_buftarg *btp)
+{
+	return bdev_read_only(btp->bt_bdev);
+}
+
+static inline int
+xfs_buftarg_flush(struct xfs_buftarg *btp)
+{
+	return blkdev_issue_flush(btp->bt_bdev);
+}
+
+static inline int
+xfs_buftarg_zeroout(
+	struct xfs_buftarg	*btp,
+	sector_t		sector,
+	sector_t		nr_sects,
+	gfp_t			gfp_mask,
+	unsigned int		flags)
+{
+	return blkdev_issue_zeroout(btp->bt_bdev, sector, nr_sects, gfp_mask,
+			flags);
+}
 
 int xfs_buf_reverify(struct xfs_buf *bp, const struct xfs_buf_ops *ops);
 bool xfs_verify_magic(struct xfs_buf *bp, __be32 dmagic);
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index e38c4c46d1275..2ec6b99188a28 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -108,6 +108,7 @@ xfs_discard_extents(
 	struct xfs_mount	*mp,
 	struct xfs_busy_extents	*extents)
 {
+	struct block_device	*bdev = xfs_buftarg_bdev(mp->m_ddev_targp);
 	struct xfs_extent_busy	*busyp;
 	struct bio		*bio = NULL;
 	struct blk_plug		plug;
@@ -118,7 +119,7 @@ xfs_discard_extents(
 		trace_xfs_discard_extent(mp, busyp->agno, busyp->bno,
 					 busyp->length);
 
-		error = __blkdev_issue_discard(mp->m_ddev_targp->bt_bdev,
+		error = __blkdev_issue_discard(bdev,
 				XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno),
 				XFS_FSB_TO_BB(mp, busyp->length),
 				GFP_NOFS, &bio);
@@ -368,8 +369,8 @@ xfs_ioc_trim(
 	struct fstrim_range __user	*urange)
 {
 	struct xfs_perag	*pag;
-	unsigned int		granularity =
-		bdev_discard_granularity(mp->m_ddev_targp->bt_bdev);
+	struct block_device	*bdev = xfs_buftarg_bdev(mp->m_ddev_targp);
+	unsigned int		granularity = bdev_discard_granularity(bdev);
 	struct fstrim_range	range;
 	xfs_daddr_t		start, end, minlen;
 	xfs_agnumber_t		agno;
@@ -378,7 +379,7 @@ xfs_ioc_trim(
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
-	if (!bdev_max_discard_sectors(mp->m_ddev_targp->bt_bdev))
+	if (!bdev_max_discard_sectors(bdev))
 		return -EOPNOTSUPP;
 
 	/*
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index e33e5e13b95f4..0a38dde178738 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -164,9 +164,9 @@ xfs_file_fsync(
 	 * inode size in case of an extending write.
 	 */
 	if (XFS_IS_REALTIME_INODE(ip))
-		error = blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev);
+		error = xfs_buftarg_flush(mp->m_rtdev_targp);
 	else if (mp->m_logdev_targp != mp->m_ddev_targp)
-		error = blkdev_issue_flush(mp->m_ddev_targp->bt_bdev);
+		error = xfs_buftarg_flush(mp->m_ddev_targp);
 
 	/*
 	 * Any inode that has dirty modifications in the log is pinned.  The
@@ -189,7 +189,7 @@ xfs_file_fsync(
 	 */
 	if (!log_flushed && !XFS_IS_REALTIME_INODE(ip) &&
 	    mp->m_logdev_targp == mp->m_ddev_targp) {
-		err2 = blkdev_issue_flush(mp->m_ddev_targp->bt_bdev);
+		err2 = xfs_buftarg_flush(mp->m_ddev_targp);
 		if (err2 && !error)
 			error = err2;
 	}
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 6c3919687ea6b..8dcd6ca2a903b 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1773,6 +1773,7 @@ xfs_ioc_setlabel(
 	char			__user *newlabel)
 {
 	struct xfs_sb		*sbp = &mp->m_sb;
+	struct block_device	*bdev = xfs_buftarg_bdev(mp->m_ddev_targp);
 	char			label[XFSLABEL_MAX + 1];
 	size_t			len;
 	int			error;
@@ -1819,7 +1820,7 @@ xfs_ioc_setlabel(
 	error = xfs_update_secondary_sbs(mp);
 	mutex_unlock(&mp->m_growlock);
 
-	invalidate_bdev(mp->m_ddev_targp->bt_bdev);
+	invalidate_bdev(bdev);
 
 out:
 	mnt_drop_write_file(filp);
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 0ff46e3997e0e..559e8e7855952 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -129,7 +129,7 @@ xfs_bmbt_to_iomap(
 	if (mapping_flags & IOMAP_DAX)
 		iomap->dax_dev = target->bt_daxdev;
 	else
-		iomap->bdev = target->bt_bdev;
+		iomap->bdev = xfs_buftarg_bdev(target);
 	iomap->flags = iomap_flags;
 
 	if (xfs_ipincount(ip) &&
@@ -154,7 +154,7 @@ xfs_hole_to_iomap(
 	iomap->type = IOMAP_HOLE;
 	iomap->offset = XFS_FSB_TO_B(ip->i_mount, offset_fsb);
 	iomap->length = XFS_FSB_TO_B(ip->i_mount, end_fsb - offset_fsb);
-	iomap->bdev = target->bt_bdev;
+	iomap->bdev = xfs_buftarg_bdev(target);
 	iomap->dax_dev = target->bt_daxdev;
 }
 
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index a1650fc81382f..a9a8311e112c2 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1903,7 +1903,7 @@ xlog_write_iclog(
 	 * writeback throttle from throttling log writes behind background
 	 * metadata writeback and causing priority inversions.
 	 */
-	bio_init(&iclog->ic_bio, log->l_targ->bt_bdev, iclog->ic_bvec,
+	bio_init(&iclog->ic_bio, xfs_buftarg_bdev(log->l_targ), iclog->ic_bvec,
 		 howmany(count, PAGE_SIZE),
 		 REQ_OP_WRITE | REQ_META | REQ_SYNC | REQ_IDLE);
 	iclog->ic_bio.bi_iter.bi_sector = log->l_logBBstart + bno;
@@ -1924,7 +1924,7 @@ xlog_write_iclog(
 		 * avoid shutdown re-entering this path and erroring out again.
 		 */
 		if (log->l_targ != log->l_mp->m_ddev_targp &&
-		    blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev))
+		    xfs_buftarg_flush(log->l_mp->m_ddev_targp))
 			goto shutdown;
 	}
 	if (iclog->ic_flags & XLOG_ICL_NEED_FUA)
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 1251c81e55f98..53ffbb9dfd974 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -137,7 +137,8 @@ xlog_do_io(
 	nbblks = round_up(nbblks, log->l_sectBBsize);
 	ASSERT(nbblks > 0);
 
-	error = xfs_rw_bdev(log->l_targ->bt_bdev, log->l_logBBstart + blk_no,
+	error = xfs_rw_bdev(xfs_buftarg_bdev(log->l_targ),
+			log->l_logBBstart + blk_no,
 			BBTOB(nbblks), data, op);
 	if (error && !xlog_is_shutdown(log)) {
 		xfs_alert(log->l_mp,

[PATCH 4/9] xfs: make GFP_ usage consistent when allocating buftargs

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Convert kmem_zalloc to kzalloc, and make it so that both memory
allocation functions in this function use GFP_NOFS.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_buf.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)


diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 0ae9a37cd1ddb..05b651672085d 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1981,7 +1981,7 @@ xfs_free_buftarg(
 	if (btp->bt_bdev != btp->bt_mount->m_super->s_bdev)
 		bdev_release(btp->bt_bdev_handle);
 
-	kmem_free(btp);
+	kvfree(btp);
 }
 
 int
@@ -2026,7 +2026,7 @@ xfs_alloc_buftarg_common(
 {
 	struct xfs_buftarg	*btp;
 
-	btp = kmem_zalloc(sizeof(*btp), KM_NOFS);
+	btp = kzalloc(sizeof(*btp), GFP_NOFS);
 	if (!btp)
 		return NULL;
 
@@ -2042,7 +2042,7 @@ xfs_alloc_buftarg_common(
 	if (list_lru_init(&btp->bt_lru))
 		goto error_free;
 
-	if (percpu_counter_init(&btp->bt_io_count, 0, GFP_KERNEL))
+	if (percpu_counter_init(&btp->bt_io_count, 0, GFP_NOFS))
 		goto error_lru;
 
 	btp->bt_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE, "xfs-%s:%s",
@@ -2063,7 +2063,7 @@ xfs_alloc_buftarg_common(
 error_lru:
 	list_lru_destroy(&btp->bt_lru);
 error_free:
-	kmem_free(btp);
+	kvfree(btp);
 	return NULL;
 }
 

[PATCH 5/9] xfs: support in-memory buffer cache targets

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Allow the buffer cache to target in-memory files by connecting it to
xfiles.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Kconfig         |    4 ++
 fs/xfs/Makefile        |    1 +
 fs/xfs/scrub/xfile.h   |   16 +++++++++
 fs/xfs/xfs_buf.c       |   46 ++++++++++++++++++++++---
 fs/xfs/xfs_buf.h       |   22 ++++++++++++
 fs/xfs/xfs_buf_xfile.c |   89 ++++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_buf_xfile.h |   18 ++++++++++
 7 files changed, 191 insertions(+), 5 deletions(-)
 create mode 100644 fs/xfs/xfs_buf_xfile.c
 create mode 100644 fs/xfs/xfs_buf_xfile.h


diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index dbcf55377e9fe..7c016a8788456 100644
--- a/fs/xfs/Kconfig
+++ b/fs/xfs/Kconfig
@@ -128,6 +128,9 @@ config XFS_LIVE_HOOKS
 	bool
 	select JUMP_LABEL if HAVE_ARCH_JUMP_LABEL
 
+config XFS_IN_MEMORY_FILE
+	bool
+
 config XFS_ONLINE_SCRUB
 	bool "XFS online metadata check support"
 	default n
@@ -135,6 +138,7 @@ config XFS_ONLINE_SCRUB
 	depends on TMPFS && SHMEM
 	select XFS_LIVE_HOOKS
 	select XFS_DRAIN_INTENTS
+	select XFS_IN_MEMORY_FILE
 	help
 	  If you say Y here you will be able to check metadata on a
 	  mounted XFS filesystem.  This feature is intended to reduce
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index a6a455ac5a38b..7eb7c521c4a84 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -138,6 +138,7 @@ endif
 
 xfs-$(CONFIG_XFS_DRAIN_INTENTS)	+= xfs_drain.o
 xfs-$(CONFIG_XFS_LIVE_HOOKS)	+= xfs_hooks.o
+xfs-$(CONFIG_XFS_IN_MEMORY_FILE)	+= xfs_buf_xfile.o
 
 # online scrub/repair
 ifeq ($(CONFIG_XFS_ONLINE_SCRUB),y)
diff --git a/fs/xfs/scrub/xfile.h b/fs/xfs/scrub/xfile.h
index 9022fe8924b94..d7661ee909495 100644
--- a/fs/xfs/scrub/xfile.h
+++ b/fs/xfs/scrub/xfile.h
@@ -6,6 +6,8 @@
 #ifndef __XFS_SCRUB_XFILE_H__
 #define __XFS_SCRUB_XFILE_H__
 
+#ifdef CONFIG_XFS_IN_MEMORY_FILE
+
 struct xfile_page {
 	struct page		*page;
 	void			*fsdata;
@@ -24,6 +26,7 @@ static inline pgoff_t xfile_page_index(const struct xfile_page *xfpage)
 
 struct xfile {
 	struct file		*file;
+	struct xfs_buf_cache	bcache;
 };
 
 int xfile_create(const char *description, loff_t isize, struct xfile **xfilep);
@@ -75,5 +78,18 @@ int xfile_get_page(struct xfile *xf, loff_t offset, unsigned int len,
 int xfile_put_page(struct xfile *xf, struct xfile_page *xbuf);
 
 int xfile_dump(struct xfile *xf);
+#else
+static inline int
+xfile_obj_load(struct xfile *xf, void *buf, size_t count, loff_t offset)
+{
+	return -EIO;
+}
+
+static inline int
+xfile_obj_store(struct xfile *xf, const void *buf, size_t count, loff_t offset)
+{
+	return -EIO;
+}
+#endif /* CONFIG_XFS_IN_MEMORY_FILE */
 
 #endif /* __XFS_SCRUB_XFILE_H__ */
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 05b651672085d..9ce08a4823851 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -21,6 +21,7 @@
 #include "xfs_errortag.h"
 #include "xfs_error.h"
 #include "xfs_ag.h"
+#include "xfs_buf_xfile.h"
 
 struct kmem_cache *xfs_buf_cache;
 
@@ -1556,6 +1557,30 @@ xfs_buf_ioapply_map(
 
 }
 
+/* Start a synchronous process-context buffer IO. */
+static inline void
+xfs_buf_start_sync_io(
+	struct xfs_buf	*bp)
+{
+	atomic_inc(&bp->b_io_remaining);
+}
+
+/* Finish a synchronous bprocess-context uffer IO. */
+static void
+xfs_buf_end_sync_io(
+	struct xfs_buf	*bp,
+	int		error)
+{
+	if (error)
+		cmpxchg(&bp->b_io_error, 0, error);
+
+	if (!bp->b_error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ))
+		invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp));
+
+	if (atomic_dec_and_test(&bp->b_io_remaining) == 1)
+		xfs_buf_ioend(bp);
+}
+
 STATIC void
 _xfs_buf_ioapply(
 	struct xfs_buf	*bp)
@@ -1613,6 +1638,15 @@ _xfs_buf_ioapply(
 	/* we only use the buffer cache for meta-data */
 	op |= REQ_META;
 
+	if (bp->b_target->bt_flags & XFS_BUFTARG_XFILE) {
+		int	error;
+
+		xfs_buf_start_sync_io(bp);
+		error = xfile_buf_ioapply(bp);
+		xfs_buf_end_sync_io(bp, error);
+		return;
+	}
+
 	/*
 	 * Walk all the vectors issuing IO on them. Set up the initial offset
 	 * into the buffer and the desired IO size before we start -
@@ -1976,10 +2010,12 @@ xfs_free_buftarg(
 	percpu_counter_destroy(&btp->bt_io_count);
 	list_lru_destroy(&btp->bt_lru);
 
-	fs_put_dax(btp->bt_daxdev, btp->bt_mount);
-	/* the main block device is closed by kill_block_super */
-	if (btp->bt_bdev != btp->bt_mount->m_super->s_bdev)
-		bdev_release(btp->bt_bdev_handle);
+	if (!(btp->bt_flags & XFS_BUFTARG_XFILE)) {
+		fs_put_dax(btp->bt_daxdev, btp->bt_mount);
+		/* the main block device is closed by kill_block_super */
+		if (btp->bt_bdev != btp->bt_mount->m_super->s_bdev)
+			bdev_release(btp->bt_bdev_handle);
+	}
 
 	kvfree(btp);
 }
@@ -2019,7 +2055,7 @@ xfs_setsize_buftarg_early(
 	return xfs_setsize_buftarg(btp, bdev_logical_block_size(btp->bt_bdev));
 }
 
-static struct xfs_buftarg *
+struct xfs_buftarg *
 xfs_alloc_buftarg_common(
 	struct xfs_mount	*mp,
 	const char		*descr)
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 4e964470587ce..a86c0b8e5a85e 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -21,6 +21,7 @@ extern struct kmem_cache *xfs_buf_cache;
  *	Base types
  */
 struct xfs_buf;
+struct xfile;
 
 #define XFS_BUF_DADDR_NULL	((xfs_daddr_t) (-1LL))
 
@@ -109,9 +110,11 @@ typedef struct xfs_buftarg {
 	struct bdev_handle	*bt_bdev_handle;
 	struct block_device	*bt_bdev;
 	struct dax_device	*bt_daxdev;
+	struct xfile		*bt_xfile;
 	u64			bt_dax_part_off;
 	struct xfs_mount	*bt_mount;
 	struct xfs_buf_cache	*bt_cache;
+	unsigned int		bt_flags;
 	unsigned int		bt_meta_sectorsize;
 	size_t			bt_meta_sectormask;
 	size_t			bt_logical_sectorsize;
@@ -125,6 +128,13 @@ typedef struct xfs_buftarg {
 	struct ratelimit_state	bt_ioerror_rl;
 } xfs_buftarg_t;
 
+#ifdef CONFIG_XFS_IN_MEMORY_FILE
+/* in-memory buftarg via bt_xfile */
+# define XFS_BUFTARG_XFILE	(1U << 0)
+#else
+# define XFS_BUFTARG_XFILE	(0)
+#endif
+
 #define XB_PAGES	2
 
 struct xfs_buf_map {
@@ -375,6 +385,8 @@ xfs_buf_update_cksum(struct xfs_buf *bp, unsigned long cksum_offset)
 /*
  *	Handling of buftargs.
  */
+struct xfs_buftarg *xfs_alloc_buftarg_common(struct xfs_mount *mp,
+		const char *descr);
 struct xfs_buftarg *xfs_alloc_buftarg(struct xfs_mount *mp,
 		struct bdev_handle *bdev_handle);
 extern void xfs_free_buftarg(struct xfs_buftarg *);
@@ -385,24 +397,32 @@ extern int xfs_setsize_buftarg(struct xfs_buftarg *, unsigned int);
 static inline struct block_device *
 xfs_buftarg_bdev(struct xfs_buftarg *btp)
 {
+	if (btp->bt_flags & XFS_BUFTARG_XFILE)
+		return NULL;
 	return btp->bt_bdev;
 }
 
 static inline unsigned int
 xfs_getsize_buftarg(struct xfs_buftarg *btp)
 {
+	if (btp->bt_flags & XFS_BUFTARG_XFILE)
+		return SECTOR_SIZE;
 	return block_size(btp->bt_bdev);
 }
 
 static inline bool
 xfs_readonly_buftarg(struct xfs_buftarg *btp)
 {
+	if (btp->bt_flags & XFS_BUFTARG_XFILE)
+		return false;
 	return bdev_read_only(btp->bt_bdev);
 }
 
 static inline int
 xfs_buftarg_flush(struct xfs_buftarg *btp)
 {
+	if (btp->bt_flags & XFS_BUFTARG_XFILE)
+		return 0;
 	return blkdev_issue_flush(btp->bt_bdev);
 }
 
@@ -414,6 +434,8 @@ xfs_buftarg_zeroout(
 	gfp_t			gfp_mask,
 	unsigned int		flags)
 {
+	if (btp->bt_flags & XFS_BUFTARG_XFILE)
+		return -EOPNOTSUPP;
 	return blkdev_issue_zeroout(btp->bt_bdev, sector, nr_sects, gfp_mask,
 			flags);
 }
diff --git a/fs/xfs/xfs_buf_xfile.c b/fs/xfs/xfs_buf_xfile.c
new file mode 100644
index 0000000000000..15cbe3df7aa01
--- /dev/null
+++ b/fs/xfs/xfs_buf_xfile.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2023-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_buf.h"
+#include "xfs_buf_xfile.h"
+#include "scrub/xfile.h"
+
+/* Perform a buffer IO to an xfile.  Caller must be in process context. */
+int
+xfile_buf_ioapply(
+	struct xfs_buf		*bp)
+{
+	struct xfile		*xfile = bp->b_target->bt_xfile;
+	loff_t			pos = BBTOB(xfs_buf_daddr(bp));
+	size_t			size = BBTOB(bp->b_length);
+
+	if (bp->b_map_count > 1) {
+		/* We don't need or support multi-map buffers. */
+		ASSERT(0);
+		return -EIO;
+	}
+
+	if (bp->b_flags & XBF_WRITE)
+		return xfile_obj_store(xfile, bp->b_addr, size, pos);
+	return xfile_obj_load(xfile, bp->b_addr, size, pos);
+}
+
+/* Allocate a buffer cache target for a memory-backed file. */
+int
+xfile_alloc_buftarg(
+	struct xfs_mount	*mp,
+	const char		*descr,
+	struct xfs_buftarg	**btpp)
+{
+	struct xfs_buftarg	*btp;
+	struct xfile		*xfile;
+	int			error;
+
+	error = xfile_create(descr, 0, &xfile);
+	if (error)
+		return error;
+
+	error = xfs_buf_cache_init(&xfile->bcache);
+	if (error)
+		goto out_xfile;
+
+	btp = xfs_alloc_buftarg_common(mp, descr);
+	if (!btp) {
+		error = -ENOMEM;
+		goto out_bcache;
+	}
+
+	btp->bt_xfile = xfile;
+	btp->bt_dev = (dev_t)-1U;
+	btp->bt_flags |= XFS_BUFTARG_XFILE;
+	btp->bt_cache = &xfile->bcache;
+
+	btp->bt_meta_sectorsize = SECTOR_SIZE;
+	btp->bt_meta_sectormask = SECTOR_SIZE - 1;
+	btp->bt_logical_sectorsize = SECTOR_SIZE;
+	btp->bt_logical_sectormask = SECTOR_SIZE - 1;
+
+	*btpp = btp;
+	return 0;
+
+out_bcache:
+	xfs_buf_cache_destroy(&xfile->bcache);
+out_xfile:
+	xfile_destroy(xfile);
+	return error;
+}
+
+/* Free a buffer cache target for a memory-backed file. */
+void
+xfile_free_buftarg(
+	struct xfs_buftarg	*btp)
+{
+	struct xfile		*xfile = btp->bt_xfile;
+
+	ASSERT(btp->bt_flags & XFS_BUFTARG_XFILE);
+
+	xfs_free_buftarg(btp);
+	xfs_buf_cache_destroy(&xfile->bcache);
+	xfile_destroy(xfile);
+}
diff --git a/fs/xfs/xfs_buf_xfile.h b/fs/xfs/xfs_buf_xfile.h
new file mode 100644
index 0000000000000..69d7846215468
--- /dev/null
+++ b/fs/xfs/xfs_buf_xfile.h
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2023-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_BUF_XFILE_H__
+#define __XFS_BUF_XFILE_H__
+
+#ifdef CONFIG_XFS_IN_MEMORY_FILE
+int xfile_buf_ioapply(struct xfs_buf *bp);
+int xfile_alloc_buftarg(struct xfs_mount *mp, const char *descr,
+		struct xfs_buftarg **btpp);
+void xfile_free_buftarg(struct xfs_buftarg *btp);
+#else
+# define xfile_buf_ioapply(bp)			(-EOPNOTSUPP)
+#endif /* CONFIG_XFS_IN_MEMORY_FILE */
+
+#endif /* __XFS_BUF_XFILE_H__ */

[PATCH 6/9] xfs: consolidate btree block freeing tracepoints

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Don't waste tracepoint segment memory on per-btree block freeing
tracepoints when we can do it from the generic btree code.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_btree.c          |    2 ++
 fs/xfs/libxfs/xfs_refcount_btree.c |    2 --
 fs/xfs/libxfs/xfs_rmap_btree.c     |    2 --
 fs/xfs/xfs_trace.h                 |   32 ++++++++++++++++++++++++++++++--
 4 files changed, 32 insertions(+), 6 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 28ba528086888..3e966182b90a9 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -414,6 +414,8 @@ xfs_btree_free_block(
 {
 	int			error;
 
+	trace_xfs_btree_free_block(cur, bp);
+
 	error = cur->bc_ops->free_block(cur, bp);
 	if (!error) {
 		xfs_trans_binval(cur->bc_tp, bp);
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 0d80bd99147cc..a346e49981ac3 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -107,8 +107,6 @@ xfs_refcountbt_free_block(
 	struct xfs_agf		*agf = agbp->b_addr;
 	xfs_fsblock_t		fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp));
 
-	trace_xfs_refcountbt_free_block(cur->bc_mp, cur->bc_ag.pag->pag_agno,
-			XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1);
 	be32_add_cpu(&agf->agf_refcount_blocks, -1);
 	xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_REFCOUNT_BLOCKS);
 	return xfs_free_extent_later(cur->bc_tp, fsbno, 1,
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index 6c81b20e97d21..0dc086bc528f7 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -125,8 +125,6 @@ xfs_rmapbt_free_block(
 	int			error;
 
 	bno = xfs_daddr_to_agbno(cur->bc_mp, xfs_buf_daddr(bp));
-	trace_xfs_rmapbt_free_block(cur->bc_mp, pag->pag_agno,
-			bno, 1);
 	be32_add_cpu(&agf->agf_rmap_blocks, -1);
 	xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_RMAP_BLOCKS);
 	error = xfs_alloc_put_freelist(pag, cur->bc_tp, agbp, NULL, bno, 1);
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 7d075e426c5d0..5076770d9b000 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -2493,6 +2493,36 @@ DEFINE_EVENT(xfs_btree_cur_class, name, \
 DEFINE_BTREE_CUR_EVENT(xfs_btree_updkeys);
 DEFINE_BTREE_CUR_EVENT(xfs_btree_overlapped_query_range);
 
+TRACE_EVENT(xfs_btree_free_block,
+	TP_PROTO(struct xfs_btree_cur *cur, struct xfs_buf *bp),
+	TP_ARGS(cur, bp),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_ino_t, ino)
+		__field(xfs_btnum_t, btnum)
+		__field(xfs_agblock_t, agbno)
+	),
+	TP_fast_assign(
+		__entry->dev = cur->bc_mp->m_super->s_dev;
+		__entry->agno = xfs_daddr_to_agno(cur->bc_mp,
+							xfs_buf_daddr(bp));
+		if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
+			__entry->ino = cur->bc_ino.ip->i_ino;
+		else
+			__entry->ino = 0;
+		__entry->btnum = cur->bc_btnum;
+		__entry->agbno = xfs_daddr_to_agbno(cur->bc_mp,
+							xfs_buf_daddr(bp));
+	),
+	TP_printk("dev %d:%d btree %s agno 0x%x ino 0x%llx agbno 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __print_symbolic(__entry->btnum, XFS_BTNUM_STRINGS),
+		  __entry->agno,
+		  __entry->ino,
+		  __entry->agbno)
+);
+
 /* deferred ops */
 struct xfs_defer_pending;
 
@@ -2856,7 +2886,6 @@ DEFINE_RMAP_DEFERRED_EVENT(xfs_rmap_defer);
 DEFINE_RMAP_DEFERRED_EVENT(xfs_rmap_deferred);
 
 DEFINE_BUSY_EVENT(xfs_rmapbt_alloc_block);
-DEFINE_BUSY_EVENT(xfs_rmapbt_free_block);
 DEFINE_RMAPBT_EVENT(xfs_rmap_update);
 DEFINE_RMAPBT_EVENT(xfs_rmap_insert);
 DEFINE_RMAPBT_EVENT(xfs_rmap_delete);
@@ -3215,7 +3244,6 @@ DEFINE_EVENT(xfs_refcount_triple_extent_class, name, \
 
 /* refcount btree tracepoints */
 DEFINE_BUSY_EVENT(xfs_refcountbt_alloc_block);
-DEFINE_BUSY_EVENT(xfs_refcountbt_free_block);
 DEFINE_AG_BTREE_LOOKUP_EVENT(xfs_refcount_lookup);
 DEFINE_REFCOUNT_EXTENT_EVENT(xfs_refcount_get);
 DEFINE_REFCOUNT_EXTENT_EVENT(xfs_refcount_update);

[PATCH 7/9] xfs: consolidate btree block allocation tracepoints

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Don't waste tracepoint segment memory on per-btree block allocation
tracepoints when we can do it from the generic btree code.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_btree.c          |   20 ++++++++++++---
 fs/xfs/libxfs/xfs_refcount_btree.c |    2 -
 fs/xfs/libxfs/xfs_rmap_btree.c     |    2 -
 fs/xfs/xfs_trace.h                 |   49 +++++++++++++++++++++++++++++++++++-
 4 files changed, 64 insertions(+), 9 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 3e966182b90a9..fbed51b4462e8 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -2693,6 +2693,20 @@ xfs_btree_rshift(
 	return error;
 }
 
+static inline int
+xfs_btree_alloc_block(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_ptr	*hint_block,
+	union xfs_btree_ptr		*new_block,
+	int				*stat)
+{
+	int				error;
+
+	error = cur->bc_ops->alloc_block(cur, hint_block, new_block, stat);
+	trace_xfs_btree_alloc_block(cur, new_block, *stat, error);
+	return error;
+}
+
 /*
  * Split cur/level block in half.
  * Return new block number and the key to its first
@@ -2736,7 +2750,7 @@ __xfs_btree_split(
 	xfs_btree_buf_to_ptr(cur, lbp, &lptr);
 
 	/* Allocate the new block. If we can't do it, we're toast. Give up. */
-	error = cur->bc_ops->alloc_block(cur, &lptr, &rptr, stat);
+	error = xfs_btree_alloc_block(cur, &lptr, &rptr, stat);
 	if (error)
 		goto error0;
 	if (*stat == 0)
@@ -3016,7 +3030,7 @@ xfs_btree_new_iroot(
 	pp = xfs_btree_ptr_addr(cur, 1, block);
 
 	/* Allocate the new block. If we can't do it, we're toast. Give up. */
-	error = cur->bc_ops->alloc_block(cur, pp, &nptr, stat);
+	error = xfs_btree_alloc_block(cur, pp, &nptr, stat);
 	if (error)
 		goto error0;
 	if (*stat == 0)
@@ -3116,7 +3130,7 @@ xfs_btree_new_root(
 	cur->bc_ops->init_ptr_from_cur(cur, &rptr);
 
 	/* Allocate the new block. If we can't do it, we're toast. Give up. */
-	error = cur->bc_ops->alloc_block(cur, &rptr, &lptr, stat);
+	error = xfs_btree_alloc_block(cur, &rptr, &lptr, stat);
 	if (error)
 		goto error0;
 	if (*stat == 0)
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index a346e49981ac3..f904a92d1b590 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -77,8 +77,6 @@ xfs_refcountbt_alloc_block(
 					xfs_refc_block(args.mp)));
 	if (error)
 		goto out_error;
-	trace_xfs_refcountbt_alloc_block(cur->bc_mp, cur->bc_ag.pag->pag_agno,
-			args.agbno, 1);
 	if (args.fsbno == NULLFSBLOCK) {
 		*stat = 0;
 		return 0;
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index 0dc086bc528f7..43ff2236f6237 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -94,8 +94,6 @@ xfs_rmapbt_alloc_block(
 				       &bno, 1);
 	if (error)
 		return error;
-
-	trace_xfs_rmapbt_alloc_block(cur->bc_mp, pag->pag_agno, bno, 1);
 	if (bno == NULLAGBLOCK) {
 		*stat = 0;
 		return 0;
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 5076770d9b000..3c6c8a8dfae8e 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -2493,6 +2493,53 @@ DEFINE_EVENT(xfs_btree_cur_class, name, \
 DEFINE_BTREE_CUR_EVENT(xfs_btree_updkeys);
 DEFINE_BTREE_CUR_EVENT(xfs_btree_overlapped_query_range);
 
+TRACE_EVENT(xfs_btree_alloc_block,
+	TP_PROTO(struct xfs_btree_cur *cur, union xfs_btree_ptr *ptr, int stat,
+		 int error),
+	TP_ARGS(cur, ptr, stat, error),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_ino_t, ino)
+		__field(xfs_btnum_t, btnum)
+		__field(int, error)
+		__field(xfs_agblock_t, agbno)
+	),
+	TP_fast_assign(
+		__entry->dev = cur->bc_mp->m_super->s_dev;
+		if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) {
+			__entry->agno = 0;
+			__entry->ino = cur->bc_ino.ip->i_ino;
+		} else {
+			__entry->agno = cur->bc_ag.pag->pag_agno;
+			__entry->ino = 0;
+		}
+		__entry->btnum = cur->bc_btnum;
+		__entry->error = error;
+		if (!error && stat) {
+			if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+				xfs_fsblock_t	fsb = be64_to_cpu(ptr->l);
+
+				__entry->agno = XFS_FSB_TO_AGNO(cur->bc_mp,
+								fsb);
+				__entry->agbno = XFS_FSB_TO_AGBNO(cur->bc_mp,
+								fsb);
+			} else {
+				__entry->agbno = be32_to_cpu(ptr->s);
+			}
+		} else {
+			__entry->agbno = NULLAGBLOCK;
+		}
+	),
+	TP_printk("dev %d:%d btree %s agno 0x%x ino 0x%llx agbno 0x%x error %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __print_symbolic(__entry->btnum, XFS_BTNUM_STRINGS),
+		  __entry->agno,
+		  __entry->ino,
+		  __entry->agbno,
+		  __entry->error)
+);
+
 TRACE_EVENT(xfs_btree_free_block,
 	TP_PROTO(struct xfs_btree_cur *cur, struct xfs_buf *bp),
 	TP_ARGS(cur, bp),
@@ -2885,7 +2932,6 @@ DEFINE_EVENT(xfs_rmapbt_class, name, \
 DEFINE_RMAP_DEFERRED_EVENT(xfs_rmap_defer);
 DEFINE_RMAP_DEFERRED_EVENT(xfs_rmap_deferred);
 
-DEFINE_BUSY_EVENT(xfs_rmapbt_alloc_block);
 DEFINE_RMAPBT_EVENT(xfs_rmap_update);
 DEFINE_RMAPBT_EVENT(xfs_rmap_insert);
 DEFINE_RMAPBT_EVENT(xfs_rmap_delete);
@@ -3243,7 +3289,6 @@ DEFINE_EVENT(xfs_refcount_triple_extent_class, name, \
 	TP_ARGS(mp, agno, i1, i2, i3))
 
 /* refcount btree tracepoints */
-DEFINE_BUSY_EVENT(xfs_refcountbt_alloc_block);
 DEFINE_AG_BTREE_LOOKUP_EVENT(xfs_refcount_lookup);
 DEFINE_REFCOUNT_EXTENT_EVENT(xfs_refcount_get);
 DEFINE_REFCOUNT_EXTENT_EVENT(xfs_refcount_update);

[PATCH 8/9] xfs: support in-memory btrees

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Adapt the generic btree cursor code to be able to create a btree whose
buffers come from a (presumably in-memory) buftarg with a header block
that's specific to in-memory btrees.  We'll connect this to other parts
of online scrub in the next patches.

Note that in-memory btrees always have a block size matching the system
memory page size for efficiency reasons.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Kconfig                |    4 
 fs/xfs/Makefile               |    1 
 fs/xfs/libxfs/xfs_btree.c     |  151 ++++++++++++++----
 fs/xfs/libxfs/xfs_btree.h     |   17 ++
 fs/xfs/libxfs/xfs_btree_mem.h |   87 ++++++++++
 fs/xfs/scrub/xfbtree.c        |  352 +++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/xfbtree.h        |   34 ++++
 fs/xfs/scrub/xfile.h          |   46 +++++
 fs/xfs/xfs_buf.c              |   10 +
 fs/xfs/xfs_buf.h              |   10 +
 fs/xfs/xfs_buf_xfile.c        |    8 +
 fs/xfs/xfs_buf_xfile.h        |    2 
 fs/xfs/xfs_health.c           |    3 
 fs/xfs/xfs_trace.c            |    3 
 fs/xfs/xfs_trace.h            |    5 -
 15 files changed, 704 insertions(+), 29 deletions(-)
 create mode 100644 fs/xfs/libxfs/xfs_btree_mem.h
 create mode 100644 fs/xfs/scrub/xfbtree.c
 create mode 100644 fs/xfs/scrub/xfbtree.h


diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index 7c016a8788456..0ed89b2381936 100644
--- a/fs/xfs/Kconfig
+++ b/fs/xfs/Kconfig
@@ -131,6 +131,9 @@ config XFS_LIVE_HOOKS
 config XFS_IN_MEMORY_FILE
 	bool
 
+config XFS_BTREE_IN_XFILE
+	bool
+
 config XFS_ONLINE_SCRUB
 	bool "XFS online metadata check support"
 	default n
@@ -204,6 +207,7 @@ config XFS_ONLINE_REPAIR
 	bool "XFS online metadata repair support"
 	default n
 	depends on XFS_FS && XFS_ONLINE_SCRUB
+	select XFS_BTREE_IN_XFILE
 	help
 	  If you say Y here you will be able to repair metadata on a
 	  mounted XFS filesystem.  This feature is intended to reduce
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 7eb7c521c4a84..6dea286d7f194 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -201,6 +201,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   reap.o \
 				   refcount_repair.o \
 				   repair.o \
+				   xfbtree.o \
 				   )
 
 xfs-$(CONFIG_XFS_RT)		+= $(addprefix scrub/, \
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index fbed51b4462e8..dbd048bc1e8e0 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -28,6 +28,9 @@
 #include "xfs_rmap_btree.h"
 #include "xfs_refcount_btree.h"
 #include "xfs_health.h"
+#include "scrub/xfile.h"
+#include "scrub/xfbtree.h"
+#include "xfs_btree_mem.h"
 
 /*
  * Btree magic numbers.
@@ -82,6 +85,9 @@ xfs_btree_check_lblock_siblings(
 	if (level >= 0) {
 		if (!xfs_btree_check_lptr(cur, sibling, level + 1))
 			return __this_address;
+	} else if (cur && (cur->bc_flags & XFS_BTREE_IN_XFILE)) {
+		if (!xfbtree_verify_xfileoff(cur, sibling))
+			return __this_address;
 	} else {
 		if (!xfs_verify_fsbno(mp, sibling))
 			return __this_address;
@@ -109,6 +115,9 @@ xfs_btree_check_sblock_siblings(
 	if (level >= 0) {
 		if (!xfs_btree_check_sptr(cur, sibling, level + 1))
 			return __this_address;
+	} else if (cur && (cur->bc_flags & XFS_BTREE_IN_XFILE)) {
+		if (!xfbtree_verify_xfileoff(cur, sibling))
+			return __this_address;
 	} else {
 		if (!xfs_verify_agbno(pag, sibling))
 			return __this_address;
@@ -151,7 +160,9 @@ __xfs_btree_check_lblock(
 	    cur->bc_ops->get_maxrecs(cur, level))
 		return __this_address;
 
-	if (bp)
+	if ((cur->bc_flags & XFS_BTREE_IN_XFILE) && bp)
+		fsb = xfbtree_buf_to_xfoff(cur, bp);
+	else if (bp)
 		fsb = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp));
 
 	fa = xfs_btree_check_lblock_siblings(mp, cur, level, fsb,
@@ -218,8 +229,12 @@ __xfs_btree_check_sblock(
 	    cur->bc_ops->get_maxrecs(cur, level))
 		return __this_address;
 
-	if (bp)
+	if ((cur->bc_flags & XFS_BTREE_IN_XFILE) && bp) {
+		pag = NULL;
+		agbno = xfbtree_buf_to_xfoff(cur, bp);
+	} else if (bp) {
 		agbno = xfs_daddr_to_agbno(mp, xfs_buf_daddr(bp));
+	}
 
 	fa = xfs_btree_check_sblock_siblings(pag, cur, level, agbno,
 			block->bb_u.s.bb_leftsib);
@@ -276,6 +291,8 @@ xfs_btree_check_lptr(
 {
 	if (level <= 0)
 		return false;
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		return xfbtree_verify_xfileoff(cur, fsbno);
 	return xfs_verify_fsbno(cur->bc_mp, fsbno);
 }
 
@@ -288,6 +305,8 @@ xfs_btree_check_sptr(
 {
 	if (level <= 0)
 		return false;
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		return xfbtree_verify_xfileoff(cur, agbno);
 	return xfs_verify_agbno(cur->bc_ag.pag, agbno);
 }
 
@@ -302,6 +321,9 @@ xfs_btree_check_ptr(
 	int				index,
 	int				level)
 {
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		return xfbtree_check_ptr(cur, ptr, index, level);
+
 	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
 		if (xfs_btree_check_lptr(cur, be64_to_cpu((&ptr->l)[index]),
 				level))
@@ -458,11 +480,36 @@ xfs_btree_del_cursor(
 	       xfs_is_shutdown(cur->bc_mp) || error != 0);
 	if (unlikely(cur->bc_flags & XFS_BTREE_STAGING))
 		kmem_free(cur->bc_ops);
-	if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS) && cur->bc_ag.pag)
+	if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS) &&
+	    !(cur->bc_flags & XFS_BTREE_IN_XFILE) && cur->bc_ag.pag)
 		xfs_perag_put(cur->bc_ag.pag);
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE) {
+		if (cur->bc_mem.pag)
+			xfs_perag_put(cur->bc_mem.pag);
+	}
 	kmem_cache_free(cur->bc_cache, cur);
 }
 
+/* Return the buffer target for this btree's buffer. */
+static inline struct xfs_buftarg *
+xfs_btree_buftarg(
+	struct xfs_btree_cur	*cur)
+{
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		return xfbtree_target(cur->bc_mem.xfbtree);
+	return cur->bc_mp->m_ddev_targp;
+}
+
+/* Return the block size (in units of 512b sectors) for this btree. */
+static inline unsigned int
+xfs_btree_bbsize(
+	struct xfs_btree_cur	*cur)
+{
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		return xfbtree_bbsize();
+	return cur->bc_mp->m_bsize;
+}
+
 /*
  * Duplicate the btree cursor.
  * Allocate a new one, copy the record, re-get the buffers.
@@ -500,10 +547,11 @@ xfs_btree_dup_cursor(
 		new->bc_levels[i].ra = cur->bc_levels[i].ra;
 		bp = cur->bc_levels[i].bp;
 		if (bp) {
-			error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
-						   xfs_buf_daddr(bp), mp->m_bsize,
-						   0, &bp,
-						   cur->bc_ops->buf_ops);
+			error = xfs_trans_read_buf(mp, tp,
+					xfs_btree_buftarg(cur),
+					xfs_buf_daddr(bp),
+					xfs_btree_bbsize(cur), 0, &bp,
+					cur->bc_ops->buf_ops);
 			if (xfs_metadata_is_sick(error))
 				xfs_btree_mark_sick(new);
 			if (error) {
@@ -944,6 +992,9 @@ xfs_btree_readahead_lblock(
 	xfs_fsblock_t		left = be64_to_cpu(block->bb_u.l.bb_leftsib);
 	xfs_fsblock_t		right = be64_to_cpu(block->bb_u.l.bb_rightsib);
 
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		return 0;
+
 	if ((lr & XFS_BTCUR_LEFTRA) && left != NULLFSBLOCK) {
 		xfs_btree_reada_bufl(cur->bc_mp, left, 1,
 				     cur->bc_ops->buf_ops);
@@ -969,6 +1020,8 @@ xfs_btree_readahead_sblock(
 	xfs_agblock_t		left = be32_to_cpu(block->bb_u.s.bb_leftsib);
 	xfs_agblock_t		right = be32_to_cpu(block->bb_u.s.bb_rightsib);
 
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		return 0;
 
 	if ((lr & XFS_BTCUR_LEFTRA) && left != NULLAGBLOCK) {
 		xfs_btree_reada_bufs(cur->bc_mp, cur->bc_ag.pag->pag_agno,
@@ -1030,6 +1083,11 @@ xfs_btree_ptr_to_daddr(
 	if (error)
 		return error;
 
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE) {
+		*daddr = xfbtree_ptr_to_daddr(cur, ptr);
+		return 0;
+	}
+
 	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
 		fsbno = be64_to_cpu(ptr->l);
 		*daddr = XFS_FSB_TO_DADDR(cur->bc_mp, fsbno);
@@ -1058,8 +1116,9 @@ xfs_btree_readahead_ptr(
 
 	if (xfs_btree_ptr_to_daddr(cur, ptr, &daddr))
 		return;
-	xfs_buf_readahead(cur->bc_mp->m_ddev_targp, daddr,
-			  cur->bc_mp->m_bsize * count, cur->bc_ops->buf_ops);
+	xfs_buf_readahead(xfs_btree_buftarg(cur), daddr,
+			xfs_btree_bbsize(cur) * count,
+			cur->bc_ops->buf_ops);
 }
 
 /*
@@ -1233,7 +1292,9 @@ xfs_btree_init_block_cur(
 	 * change in future, but is safe for current users of the generic btree
 	 * code.
 	 */
-	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		owner = xfbtree_owner(cur);
+	else if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
 		owner = cur->bc_ino.ip->i_ino;
 	else
 		owner = cur->bc_ag.pag->pag_agno;
@@ -1273,6 +1334,11 @@ xfs_btree_buf_to_ptr(
 	struct xfs_buf		*bp,
 	union xfs_btree_ptr	*ptr)
 {
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE) {
+		xfbtree_buf_to_ptr(cur, bp, ptr);
+		return;
+	}
+
 	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
 		ptr->l = cpu_to_be64(XFS_DADDR_TO_FSB(cur->bc_mp,
 					xfs_buf_daddr(bp)));
@@ -1317,15 +1383,14 @@ xfs_btree_get_buf_block(
 	struct xfs_btree_block		**block,
 	struct xfs_buf			**bpp)
 {
-	struct xfs_mount	*mp = cur->bc_mp;
-	xfs_daddr_t		d;
-	int			error;
+	xfs_daddr_t			d;
+	int				error;
 
 	error = xfs_btree_ptr_to_daddr(cur, ptr, &d);
 	if (error)
 		return error;
-	error = xfs_trans_get_buf(cur->bc_tp, mp->m_ddev_targp, d, mp->m_bsize,
-			0, bpp);
+	error = xfs_trans_get_buf(cur->bc_tp, xfs_btree_buftarg(cur), d,
+			xfs_btree_bbsize(cur), 0, bpp);
 	if (error)
 		return error;
 
@@ -1356,9 +1421,9 @@ xfs_btree_read_buf_block(
 	error = xfs_btree_ptr_to_daddr(cur, ptr, &d);
 	if (error)
 		return error;
-	error = xfs_trans_read_buf(mp, cur->bc_tp, mp->m_ddev_targp, d,
-				   mp->m_bsize, flags, bpp,
-				   cur->bc_ops->buf_ops);
+	error = xfs_trans_read_buf(mp, cur->bc_tp, xfs_btree_buftarg(cur), d,
+			xfs_btree_bbsize(cur), flags, bpp,
+			cur->bc_ops->buf_ops);
 	if (xfs_metadata_is_sick(error))
 		xfs_btree_mark_sick(cur);
 	if (error)
@@ -1798,6 +1863,37 @@ xfs_btree_decrement(
 	return error;
 }
 
+/*
+ * Check the btree block owner now that we have the context to know who the
+ * real owner is.
+ */
+static inline xfs_failaddr_t
+xfs_btree_check_block_owner(
+	struct xfs_btree_cur	*cur,
+	struct xfs_btree_block	*block)
+{
+	if (!xfs_has_crc(cur->bc_mp))
+		return NULL;
+
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		return xfbtree_check_block_owner(cur, block);
+
+	if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS)) {
+		if (be32_to_cpu(block->bb_u.s.bb_owner) !=
+						cur->bc_ag.pag->pag_agno)
+			return __this_address;
+		return NULL;
+	}
+
+	if (cur->bc_ino.flags & XFS_BTCUR_BMBT_INVALID_OWNER)
+		return NULL;
+
+	if (be64_to_cpu(block->bb_u.l.bb_owner) != cur->bc_ino.ip->i_ino)
+		return __this_address;
+
+	return NULL;
+}
+
 int
 xfs_btree_lookup_get_block(
 	struct xfs_btree_cur		*cur,	/* btree cursor */
@@ -1836,11 +1932,7 @@ xfs_btree_lookup_get_block(
 		return error;
 
 	/* Check the inode owner since the verifiers don't. */
-	if (xfs_has_crc(cur->bc_mp) &&
-	    !(cur->bc_ino.flags & XFS_BTCUR_BMBT_INVALID_OWNER) &&
-	    (cur->bc_flags & XFS_BTREE_LONG_PTRS) &&
-	    be64_to_cpu((*blkp)->bb_u.l.bb_owner) !=
-			cur->bc_ino.ip->i_ino)
+	if (xfs_btree_check_block_owner(cur, *blkp) != NULL)
 		goto out_bad;
 
 	/* Did we get the level we were looking for? */
@@ -4386,7 +4478,7 @@ xfs_btree_visit_block(
 {
 	struct xfs_btree_block		*block;
 	struct xfs_buf			*bp;
-	union xfs_btree_ptr		rptr;
+	union xfs_btree_ptr		rptr, bufptr;
 	int				error;
 
 	/* do right sibling readahead */
@@ -4409,15 +4501,14 @@ xfs_btree_visit_block(
 	 * return the same block without checking if the right sibling points
 	 * back to us and creates a cyclic reference in the btree.
 	 */
+	xfs_btree_buf_to_ptr(cur, bp, &bufptr);
 	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
-		if (be64_to_cpu(rptr.l) == XFS_DADDR_TO_FSB(cur->bc_mp,
-							xfs_buf_daddr(bp))) {
+		if (rptr.l == bufptr.l) {
 			xfs_btree_mark_sick(cur);
 			return -EFSCORRUPTED;
 		}
 	} else {
-		if (be32_to_cpu(rptr.s) == xfs_daddr_to_agbno(cur->bc_mp,
-							xfs_buf_daddr(bp))) {
+		if (rptr.s == bufptr.s) {
 			xfs_btree_mark_sick(cur);
 			return -EFSCORRUPTED;
 		}
@@ -4599,6 +4690,8 @@ xfs_btree_lblock_verify(
 	xfs_fsblock_t		fsb;
 	xfs_failaddr_t		fa;
 
+	ASSERT(!(bp->b_target->bt_flags & XFS_BUFTARG_XFILE));
+
 	/* numrecs verification */
 	if (be16_to_cpu(block->bb_numrecs) > max_recs)
 		return __this_address;
@@ -4654,6 +4747,8 @@ xfs_btree_sblock_verify(
 	xfs_agblock_t		agbno;
 	xfs_failaddr_t		fa;
 
+	ASSERT(!(bp->b_target->bt_flags & XFS_BUFTARG_XFILE));
+
 	/* numrecs verification */
 	if (be16_to_cpu(block->bb_numrecs) > max_recs)
 		return __this_address;
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index d906324e25c86..3e6bdbc507039 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -248,6 +248,15 @@ struct xfs_btree_cur_ino {
 #define	XFS_BTCUR_BMBT_INVALID_OWNER	(1 << 1)
 };
 
+/* In-memory btree information */
+struct xfbtree;
+
+struct xfs_btree_cur_mem {
+	struct xfbtree			*xfbtree;
+	struct xfs_buf			*head_bp;
+	struct xfs_perag		*pag;
+};
+
 struct xfs_btree_level {
 	/* buffer pointer */
 	struct xfs_buf		*bp;
@@ -287,6 +296,7 @@ struct xfs_btree_cur
 	union {
 		struct xfs_btree_cur_ag	bc_ag;
 		struct xfs_btree_cur_ino bc_ino;
+		struct xfs_btree_cur_mem bc_mem;
 	};
 
 	/* Must be at the end of the struct! */
@@ -317,6 +327,13 @@ xfs_btree_cur_sizeof(unsigned int nlevels)
  */
 #define XFS_BTREE_STAGING		(1<<5)
 
+/* btree stored in memory; not compatible with ROOT_IN_INODE */
+#ifdef CONFIG_XFS_BTREE_IN_XFILE
+# define XFS_BTREE_IN_XFILE		(1<<7)
+#else
+# define XFS_BTREE_IN_XFILE		(0)
+#endif
+
 #define	XFS_BTREE_NOERROR	0
 #define	XFS_BTREE_ERROR		1
 
diff --git a/fs/xfs/libxfs/xfs_btree_mem.h b/fs/xfs/libxfs/xfs_btree_mem.h
new file mode 100644
index 0000000000000..2c42ca85c58fb
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_btree_mem.h
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2021-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_BTREE_MEM_H__
+#define __XFS_BTREE_MEM_H__
+
+struct xfbtree;
+
+#ifdef CONFIG_XFS_BTREE_IN_XFILE
+unsigned int xfs_btree_mem_head_nlevels(struct xfs_buf *head_bp);
+
+struct xfs_buftarg *xfbtree_target(struct xfbtree *xfbtree);
+int xfbtree_check_ptr(struct xfs_btree_cur *cur,
+		const union xfs_btree_ptr *ptr, int index, int level);
+xfs_daddr_t xfbtree_ptr_to_daddr(struct xfs_btree_cur *cur,
+		const union xfs_btree_ptr *ptr);
+void xfbtree_buf_to_ptr(struct xfs_btree_cur *cur, struct xfs_buf *bp,
+		union xfs_btree_ptr *ptr);
+
+unsigned int xfbtree_bbsize(void);
+
+void xfbtree_set_root(struct xfs_btree_cur *cur,
+		const union xfs_btree_ptr *ptr, int inc);
+void xfbtree_init_ptr_from_cur(struct xfs_btree_cur *cur,
+		union xfs_btree_ptr *ptr);
+struct xfs_btree_cur *xfbtree_dup_cursor(struct xfs_btree_cur *cur);
+bool xfbtree_verify_xfileoff(struct xfs_btree_cur *cur,
+		unsigned long long xfoff);
+xfs_failaddr_t xfbtree_check_block_owner(struct xfs_btree_cur *cur,
+		struct xfs_btree_block *block);
+unsigned long long xfbtree_owner(struct xfs_btree_cur *cur);
+xfs_failaddr_t xfbtree_lblock_verify(struct xfs_buf *bp, unsigned int max_recs);
+xfs_failaddr_t xfbtree_sblock_verify(struct xfs_buf *bp, unsigned int max_recs);
+unsigned long long xfbtree_buf_to_xfoff(struct xfs_btree_cur *cur,
+		struct xfs_buf *bp);
+#else
+static inline unsigned int xfs_btree_mem_head_nlevels(struct xfs_buf *head_bp)
+{
+	return 0;
+}
+
+static inline struct xfs_buftarg *
+xfbtree_target(struct xfbtree *xfbtree)
+{
+	return NULL;
+}
+
+static inline int
+xfbtree_check_ptr(struct xfs_btree_cur *cur, const union xfs_btree_ptr *ptr,
+		  int index, int level)
+{
+	return 0;
+}
+
+static inline xfs_daddr_t
+xfbtree_ptr_to_daddr(struct xfs_btree_cur *cur, const union xfs_btree_ptr *ptr)
+{
+	return 0;
+}
+
+static inline void
+xfbtree_buf_to_ptr(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp,
+	union xfs_btree_ptr	*ptr)
+{
+	memset(ptr, 0xFF, sizeof(*ptr));
+}
+
+static inline unsigned int xfbtree_bbsize(void)
+{
+	return 0;
+}
+
+#define xfbtree_set_root			NULL
+#define xfbtree_init_ptr_from_cur		NULL
+#define xfbtree_dup_cursor			NULL
+#define xfbtree_verify_xfileoff(cur, xfoff)	(false)
+#define xfbtree_check_block_owner(cur, block)	NULL
+#define xfbtree_owner(cur)			(0ULL)
+#define xfbtree_buf_to_xfoff(cur, bp)		(-1)
+
+#endif /* CONFIG_XFS_BTREE_IN_XFILE */
+
+#endif /* __XFS_BTREE_MEM_H__ */
diff --git a/fs/xfs/scrub/xfbtree.c b/fs/xfs/scrub/xfbtree.c
new file mode 100644
index 0000000000000..b7b5aa52b40b4
--- /dev/null
+++ b/fs/xfs/scrub/xfbtree.c
@@ -0,0 +1,352 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2021-2024 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_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_trans.h"
+#include "xfs_btree.h"
+#include "xfs_error.h"
+#include "xfs_btree_mem.h"
+#include "xfs_ag.h"
+#include "scrub/xfile.h"
+#include "scrub/xfbtree.h"
+
+/* btree ops functions for in-memory btrees. */
+
+static xfs_failaddr_t
+xfs_btree_mem_head_verify(
+	struct xfs_buf			*bp)
+{
+	struct xfs_btree_mem_head	*mhead = bp->b_addr;
+	struct xfs_mount		*mp = bp->b_mount;
+
+	if (!xfs_verify_magic(bp, mhead->mh_magic))
+		return __this_address;
+	if (be32_to_cpu(mhead->mh_nlevels) == 0)
+		return __this_address;
+	if (!uuid_equal(&mhead->mh_uuid, &mp->m_sb.sb_meta_uuid))
+		return __this_address;
+
+	return NULL;
+}
+
+static void
+xfs_btree_mem_head_read_verify(
+	struct xfs_buf		*bp)
+{
+	xfs_failaddr_t		fa = xfs_btree_mem_head_verify(bp);
+
+	if (fa)
+		xfs_verifier_error(bp, -EFSCORRUPTED, fa);
+}
+
+static void
+xfs_btree_mem_head_write_verify(
+	struct xfs_buf		*bp)
+{
+	xfs_failaddr_t		fa = xfs_btree_mem_head_verify(bp);
+
+	if (fa)
+		xfs_verifier_error(bp, -EFSCORRUPTED, fa);
+}
+
+static const struct xfs_buf_ops xfs_btree_mem_head_buf_ops = {
+	.name			= "xfs_btree_mem_head",
+	.magic			= { cpu_to_be32(XFS_BTREE_MEM_HEAD_MAGIC),
+				    cpu_to_be32(XFS_BTREE_MEM_HEAD_MAGIC) },
+	.verify_read		= xfs_btree_mem_head_read_verify,
+	.verify_write		= xfs_btree_mem_head_write_verify,
+	.verify_struct		= xfs_btree_mem_head_verify,
+};
+
+/* Initialize the header block for an in-memory btree. */
+static inline void
+xfs_btree_mem_head_init(
+	struct xfs_buf			*head_bp,
+	unsigned long long		owner,
+	xfileoff_t			leaf_xfoff)
+{
+	struct xfs_btree_mem_head	*mhead = head_bp->b_addr;
+	struct xfs_mount		*mp = head_bp->b_mount;
+
+	mhead->mh_magic = cpu_to_be32(XFS_BTREE_MEM_HEAD_MAGIC);
+	mhead->mh_nlevels = cpu_to_be32(1);
+	mhead->mh_owner = cpu_to_be64(owner);
+	mhead->mh_root = cpu_to_be64(leaf_xfoff);
+	uuid_copy(&mhead->mh_uuid, &mp->m_sb.sb_meta_uuid);
+
+	head_bp->b_ops = &xfs_btree_mem_head_buf_ops;
+}
+
+/* Return tree height from the in-memory btree head. */
+unsigned int
+xfs_btree_mem_head_nlevels(
+	struct xfs_buf			*head_bp)
+{
+	struct xfs_btree_mem_head	*mhead = head_bp->b_addr;
+
+	return be32_to_cpu(mhead->mh_nlevels);
+}
+
+/* Extract the buftarg target for this xfile btree. */
+struct xfs_buftarg *
+xfbtree_target(struct xfbtree *xfbtree)
+{
+	return xfbtree->target;
+}
+
+/* Is this daddr (sector offset) contained within the buffer target? */
+static inline bool
+xfbtree_verify_buftarg_xfileoff(
+	struct xfs_buftarg	*btp,
+	xfileoff_t		xfoff)
+{
+	xfs_daddr_t		xfoff_daddr = xfo_to_daddr(xfoff);
+
+	return xfs_buftarg_verify_daddr(btp, xfoff_daddr);
+}
+
+/* Is this btree xfile offset contained within the xfile? */
+bool
+xfbtree_verify_xfileoff(
+	struct xfs_btree_cur	*cur,
+	unsigned long long	xfoff)
+{
+	struct xfs_buftarg	*btp = xfbtree_target(cur->bc_mem.xfbtree);
+
+	return xfbtree_verify_buftarg_xfileoff(btp, xfoff);
+}
+
+/* Check if a btree pointer is reasonable. */
+int
+xfbtree_check_ptr(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_ptr	*ptr,
+	int				index,
+	int				level)
+{
+	xfileoff_t			bt_xfoff;
+	xfs_failaddr_t			fa = NULL;
+
+	ASSERT(cur->bc_flags & XFS_BTREE_IN_XFILE);
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+		bt_xfoff = be64_to_cpu(ptr->l);
+	else
+		bt_xfoff = be32_to_cpu(ptr->s);
+
+	if (!xfbtree_verify_xfileoff(cur, bt_xfoff))
+		fa = __this_address;
+
+	if (fa) {
+		xfs_err(cur->bc_mp,
+"In-memory: Corrupt btree %d flags 0x%x pointer at level %d index %d fa %pS.",
+				cur->bc_btnum, cur->bc_flags, level, index,
+				fa);
+		return -EFSCORRUPTED;
+	}
+	return 0;
+}
+
+/* Convert a btree pointer to a daddr */
+xfs_daddr_t
+xfbtree_ptr_to_daddr(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_ptr	*ptr)
+{
+	xfileoff_t			bt_xfoff;
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+		bt_xfoff = be64_to_cpu(ptr->l);
+	else
+		bt_xfoff = be32_to_cpu(ptr->s);
+	return xfo_to_daddr(bt_xfoff);
+}
+
+/* Set the pointer to point to this buffer. */
+void
+xfbtree_buf_to_ptr(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp,
+	union xfs_btree_ptr	*ptr)
+{
+	xfileoff_t		xfoff = xfs_daddr_to_xfo(xfs_buf_daddr(bp));
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+		ptr->l = cpu_to_be64(xfoff);
+	else
+		ptr->s = cpu_to_be32(xfoff);
+}
+
+/* Return the in-memory btree block size, in units of 512 bytes. */
+unsigned int xfbtree_bbsize(void)
+{
+	return xfo_to_daddr(1);
+}
+
+/* Set the root of an in-memory btree. */
+void
+xfbtree_set_root(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_ptr	*ptr,
+	int				inc)
+{
+	struct xfs_buf			*head_bp = cur->bc_mem.head_bp;
+	struct xfs_btree_mem_head	*mhead = head_bp->b_addr;
+
+	ASSERT(cur->bc_flags & XFS_BTREE_IN_XFILE);
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+		mhead->mh_root = ptr->l;
+	} else {
+		uint32_t		root = be32_to_cpu(ptr->s);
+
+		mhead->mh_root = cpu_to_be64(root);
+	}
+	be32_add_cpu(&mhead->mh_nlevels, inc);
+	xfs_trans_log_buf(cur->bc_tp, head_bp, 0, sizeof(*mhead) - 1);
+}
+
+/* Initialize a pointer from the in-memory btree header. */
+void
+xfbtree_init_ptr_from_cur(
+	struct xfs_btree_cur		*cur,
+	union xfs_btree_ptr		*ptr)
+{
+	struct xfs_buf			*head_bp = cur->bc_mem.head_bp;
+	struct xfs_btree_mem_head	*mhead = head_bp->b_addr;
+
+	ASSERT(cur->bc_flags & XFS_BTREE_IN_XFILE);
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+		ptr->l = mhead->mh_root;
+	} else {
+		uint64_t		root = be64_to_cpu(mhead->mh_root);
+
+		ptr->s = cpu_to_be32(root);
+	}
+}
+
+/* Duplicate an in-memory btree cursor. */
+struct xfs_btree_cur *
+xfbtree_dup_cursor(
+	struct xfs_btree_cur		*cur)
+{
+	struct xfs_btree_cur		*ncur;
+
+	ASSERT(cur->bc_flags & XFS_BTREE_IN_XFILE);
+
+	ncur = xfs_btree_alloc_cursor(cur->bc_mp, cur->bc_tp, cur->bc_btnum,
+			cur->bc_maxlevels, cur->bc_cache);
+	ncur->bc_flags = cur->bc_flags;
+	ncur->bc_nlevels = cur->bc_nlevels;
+	ncur->bc_statoff = cur->bc_statoff;
+	ncur->bc_ops = cur->bc_ops;
+	memcpy(&ncur->bc_mem, &cur->bc_mem, sizeof(cur->bc_mem));
+
+	if (cur->bc_mem.pag)
+		ncur->bc_mem.pag = xfs_perag_hold(cur->bc_mem.pag);
+
+	return ncur;
+}
+
+/* Check the owner of an in-memory btree block. */
+xfs_failaddr_t
+xfbtree_check_block_owner(
+	struct xfs_btree_cur	*cur,
+	struct xfs_btree_block	*block)
+{
+	struct xfbtree		*xfbt = cur->bc_mem.xfbtree;
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+		if (be64_to_cpu(block->bb_u.l.bb_owner) != xfbt->owner)
+			return __this_address;
+
+		return NULL;
+	}
+
+	if (be32_to_cpu(block->bb_u.s.bb_owner) != xfbt->owner)
+		return __this_address;
+
+	return NULL;
+}
+
+/* Return the owner of this in-memory btree. */
+unsigned long long
+xfbtree_owner(
+	struct xfs_btree_cur	*cur)
+{
+	return cur->bc_mem.xfbtree->owner;
+}
+
+/* Return the xfile offset (in blocks) of a btree buffer. */
+unsigned long long
+xfbtree_buf_to_xfoff(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp)
+{
+	ASSERT(cur->bc_flags & XFS_BTREE_IN_XFILE);
+
+	return xfs_daddr_to_xfo(xfs_buf_daddr(bp));
+}
+
+/* Verify a long-format btree block. */
+xfs_failaddr_t
+xfbtree_lblock_verify(
+	struct xfs_buf		*bp,
+	unsigned int		max_recs)
+{
+	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
+	struct xfs_buftarg	*btp = bp->b_target;
+
+	/* numrecs verification */
+	if (be16_to_cpu(block->bb_numrecs) > max_recs)
+		return __this_address;
+
+	/* sibling pointer verification */
+	if (block->bb_u.l.bb_leftsib != cpu_to_be64(NULLFSBLOCK) &&
+	    !xfbtree_verify_buftarg_xfileoff(btp,
+				be64_to_cpu(block->bb_u.l.bb_leftsib)))
+		return __this_address;
+
+	if (block->bb_u.l.bb_rightsib != cpu_to_be64(NULLFSBLOCK) &&
+	    !xfbtree_verify_buftarg_xfileoff(btp,
+				be64_to_cpu(block->bb_u.l.bb_rightsib)))
+		return __this_address;
+
+	return NULL;
+}
+
+/* Verify a short-format btree block. */
+xfs_failaddr_t
+xfbtree_sblock_verify(
+	struct xfs_buf		*bp,
+	unsigned int		max_recs)
+{
+	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
+	struct xfs_buftarg	*btp = bp->b_target;
+
+	/* numrecs verification */
+	if (be16_to_cpu(block->bb_numrecs) > max_recs)
+		return __this_address;
+
+	/* sibling pointer verification */
+	if (block->bb_u.s.bb_leftsib != cpu_to_be32(NULLAGBLOCK) &&
+	    !xfbtree_verify_buftarg_xfileoff(btp,
+				be32_to_cpu(block->bb_u.s.bb_leftsib)))
+		return __this_address;
+
+	if (block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK) &&
+	    !xfbtree_verify_buftarg_xfileoff(btp,
+				be32_to_cpu(block->bb_u.s.bb_rightsib)))
+		return __this_address;
+
+	return NULL;
+}
diff --git a/fs/xfs/scrub/xfbtree.h b/fs/xfs/scrub/xfbtree.h
new file mode 100644
index 0000000000000..b8d2f628e6b7c
--- /dev/null
+++ b/fs/xfs/scrub/xfbtree.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2021-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef XFS_SCRUB_XFBTREE_H__
+#define XFS_SCRUB_XFBTREE_H__
+
+#ifdef CONFIG_XFS_BTREE_IN_XFILE
+
+/* Root block for an in-memory btree. */
+struct xfs_btree_mem_head {
+	__be32				mh_magic;
+	__be32				mh_nlevels;
+	__be64				mh_owner;
+	__be64				mh_root;
+	uuid_t				mh_uuid;
+};
+
+#define XFS_BTREE_MEM_HEAD_MAGIC	0x4341544D	/* "CATM" */
+
+/* xfile-backed in-memory btrees */
+
+struct xfbtree {
+	/* buffer cache target for this in-memory btree */
+	struct xfs_buftarg		*target;
+
+	/* Owner of this btree. */
+	unsigned long long		owner;
+};
+
+#endif /* CONFIG_XFS_BTREE_IN_XFILE */
+
+#endif /* XFS_SCRUB_XFBTREE_H__ */
diff --git a/fs/xfs/scrub/xfile.h b/fs/xfs/scrub/xfile.h
index d7661ee909495..8bdea8788a8a7 100644
--- a/fs/xfs/scrub/xfile.h
+++ b/fs/xfs/scrub/xfile.h
@@ -78,6 +78,47 @@ int xfile_get_page(struct xfile *xf, loff_t offset, unsigned int len,
 int xfile_put_page(struct xfile *xf, struct xfile_page *xbuf);
 
 int xfile_dump(struct xfile *xf);
+
+static inline loff_t xfile_size(struct xfile *xf)
+{
+	return i_size_read(file_inode(xf->file));
+}
+
+/* file block (aka system page size) to basic block conversions. */
+typedef unsigned long long	xfileoff_t;
+#define XFB_BLOCKSIZE		(PAGE_SIZE)
+#define XFB_BSHIFT		(PAGE_SHIFT)
+#define XFB_SHIFT		(XFB_BSHIFT - BBSHIFT)
+
+static inline loff_t xfo_to_b(xfileoff_t xfoff)
+{
+	return xfoff << XFB_BSHIFT;
+}
+
+static inline xfileoff_t b_to_xfo(loff_t pos)
+{
+	return (pos + (XFB_BLOCKSIZE - 1)) >> XFB_BSHIFT;
+}
+
+static inline xfileoff_t b_to_xfot(loff_t pos)
+{
+	return pos >> XFB_BSHIFT;
+}
+
+static inline xfs_daddr_t xfo_to_daddr(xfileoff_t xfoff)
+{
+	return xfoff << XFB_SHIFT;
+}
+
+static inline xfileoff_t xfs_daddr_to_xfo(xfs_daddr_t bb)
+{
+	return (bb + (xfo_to_daddr(1) - 1)) >> XFB_SHIFT;
+}
+
+static inline xfileoff_t xfs_daddr_to_xfot(xfs_daddr_t bb)
+{
+	return bb >> XFB_SHIFT;
+}
 #else
 static inline int
 xfile_obj_load(struct xfile *xf, void *buf, size_t count, loff_t offset)
@@ -90,6 +131,11 @@ xfile_obj_store(struct xfile *xf, const void *buf, size_t count, loff_t offset)
 {
 	return -EIO;
 }
+
+static inline loff_t xfile_size(struct xfile *xf)
+{
+	return 0;
+}
 #endif /* CONFIG_XFS_IN_MEMORY_FILE */
 
 #endif /* __XFS_SCRUB_XFILE_H__ */
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 9ce08a4823851..a61ad61cb9136 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -2497,3 +2497,13 @@ xfs_verify_magic16(
 		return false;
 	return dmagic == bp->b_ops->magic16[idx];
 }
+
+/* Return the number of sectors for a buffer target. */
+xfs_daddr_t
+xfs_buftarg_nr_sectors(
+	struct xfs_buftarg	*btp)
+{
+	if (btp->bt_flags & XFS_BUFTARG_XFILE)
+		return xfile_buftarg_nr_sectors(btp);
+	return bdev_nr_sectors(btp->bt_bdev);
+}
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index a86c0b8e5a85e..5a6cf3d5a9f53 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -440,6 +440,16 @@ xfs_buftarg_zeroout(
 			flags);
 }
 
+xfs_daddr_t xfs_buftarg_nr_sectors(struct xfs_buftarg *btp);
+
+static inline bool
+xfs_buftarg_verify_daddr(
+	struct xfs_buftarg	*btp,
+	xfs_daddr_t		daddr)
+{
+	return daddr < xfs_buftarg_nr_sectors(btp);
+}
+
 int xfs_buf_reverify(struct xfs_buf *bp, const struct xfs_buf_ops *ops);
 bool xfs_verify_magic(struct xfs_buf *bp, __be32 dmagic);
 bool xfs_verify_magic16(struct xfs_buf *bp, __be16 dmagic);
diff --git a/fs/xfs/xfs_buf_xfile.c b/fs/xfs/xfs_buf_xfile.c
index 15cbe3df7aa01..51c5c692156b1 100644
--- a/fs/xfs/xfs_buf_xfile.c
+++ b/fs/xfs/xfs_buf_xfile.c
@@ -87,3 +87,11 @@ xfile_free_buftarg(
 	xfs_buf_cache_destroy(&xfile->bcache);
 	xfile_destroy(xfile);
 }
+
+/* Sector count for this xfile buftarg. */
+xfs_daddr_t
+xfile_buftarg_nr_sectors(
+	struct xfs_buftarg	*btp)
+{
+	return xfile_size(btp->bt_xfile) >> SECTOR_SHIFT;
+}
diff --git a/fs/xfs/xfs_buf_xfile.h b/fs/xfs/xfs_buf_xfile.h
index 69d7846215468..c8d78d01ea5df 100644
--- a/fs/xfs/xfs_buf_xfile.h
+++ b/fs/xfs/xfs_buf_xfile.h
@@ -11,8 +11,10 @@ int xfile_buf_ioapply(struct xfs_buf *bp);
 int xfile_alloc_buftarg(struct xfs_mount *mp, const char *descr,
 		struct xfs_buftarg **btpp);
 void xfile_free_buftarg(struct xfs_buftarg *btp);
+xfs_daddr_t xfile_buftarg_nr_sectors(struct xfs_buftarg *btp);
 #else
 # define xfile_buf_ioapply(bp)			(-EOPNOTSUPP)
+# define xfile_buftarg_nr_sectors(btp)		(0)
 #endif /* CONFIG_XFS_IN_MEMORY_FILE */
 
 #endif /* __XFS_BUF_XFILE_H__ */
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index 2be1ac83f4c41..bd884c154cf37 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -512,6 +512,9 @@ xfs_btree_mark_sick(
 {
 	unsigned int			mask;
 
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		return;
+
 	switch (cur->bc_btnum) {
 	case XFS_BTNUM_BMAP:
 		xfs_bmap_mark_sick(cur->bc_ino.ip, cur->bc_ino.whichfork);
diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c
index 8a5dc1538aa82..2d49310fb9128 100644
--- a/fs/xfs/xfs_trace.c
+++ b/fs/xfs/xfs_trace.c
@@ -36,6 +36,9 @@
 #include "xfs_error.h"
 #include <linux/iomap.h>
 #include "xfs_iomap.h"
+#include "scrub/xfile.h"
+#include "scrub/xfbtree.h"
+#include "xfs_btree_mem.h"
 
 /*
  * We include this last to have the helpers above available for the trace
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 3c6c8a8dfae8e..4a2615db742aa 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -2507,7 +2507,10 @@ TRACE_EVENT(xfs_btree_alloc_block,
 	),
 	TP_fast_assign(
 		__entry->dev = cur->bc_mp->m_super->s_dev;
-		if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) {
+		if (cur->bc_flags & XFS_BTREE_IN_XFILE) {
+			__entry->agno = 0;
+			__entry->ino = 0;
+		} else if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) {
 			__entry->agno = 0;
 			__entry->ino = cur->bc_ino.ip->i_ino;
 		} else {

[PATCH 9/9] xfs: connect in-memory btrees to xfiles

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add to our stubbed-out in-memory btrees the ability to connect them with
an actual in-memory backing file (aka xfiles) and the necessary pieces
to track free space in the xfile and flush dirty xfbtree buffers on
demand, which we'll need for online repair.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_btree_mem.h |   41 +++
 fs/xfs/scrub/bitmap.c         |   28 ++
 fs/xfs/scrub/bitmap.h         |    3 
 fs/xfs/scrub/scrub.c          |    5 
 fs/xfs/scrub/scrub.h          |    3 
 fs/xfs/scrub/trace.c          |   11 +
 fs/xfs/scrub/trace.h          |  109 +++++++++
 fs/xfs/scrub/xfbtree.c        |  487 +++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/xfbtree.h        |   31 +++
 fs/xfs/scrub/xfile.c          |   83 +++++++
 fs/xfs/scrub/xfile.h          |    2 
 fs/xfs/xfs_trace.h            |    1 
 fs/xfs/xfs_trans.h            |    1 
 fs/xfs/xfs_trans_buf.c        |   42 ++++
 14 files changed, 845 insertions(+), 2 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_btree_mem.h b/fs/xfs/libxfs/xfs_btree_mem.h
index 2c42ca85c58fb..29f97c5030465 100644
--- a/fs/xfs/libxfs/xfs_btree_mem.h
+++ b/fs/xfs/libxfs/xfs_btree_mem.h
@@ -8,6 +8,26 @@
 
 struct xfbtree;
 
+struct xfbtree_config {
+	/* Buffer ops for the btree root block */
+	const struct xfs_btree_ops	*btree_ops;
+
+	/* Buffer target for the xfile backing this btree. */
+	struct xfs_buftarg		*target;
+
+	/* Owner of this btree. */
+	unsigned long long		owner;
+
+	/* Btree type number */
+	xfs_btnum_t			btnum;
+
+	/* XFBTREE_CREATE_* flags */
+	unsigned int			flags;
+};
+
+/* btree has long pointers */
+#define XFBTREE_CREATE_LONG_PTRS	(1U << 0)
+
 #ifdef CONFIG_XFS_BTREE_IN_XFILE
 unsigned int xfs_btree_mem_head_nlevels(struct xfs_buf *head_bp);
 
@@ -35,6 +55,16 @@ xfs_failaddr_t xfbtree_lblock_verify(struct xfs_buf *bp, unsigned int max_recs);
 xfs_failaddr_t xfbtree_sblock_verify(struct xfs_buf *bp, unsigned int max_recs);
 unsigned long long xfbtree_buf_to_xfoff(struct xfs_btree_cur *cur,
 		struct xfs_buf *bp);
+
+int xfbtree_get_minrecs(struct xfs_btree_cur *cur, int level);
+int xfbtree_get_maxrecs(struct xfs_btree_cur *cur, int level);
+
+int xfbtree_create(struct xfs_mount *mp, const struct xfbtree_config *cfg,
+		struct xfbtree **xfbtreep);
+int xfbtree_alloc_block(struct xfs_btree_cur *cur,
+		const union xfs_btree_ptr *start, union xfs_btree_ptr *ptr,
+		int *stat);
+int xfbtree_free_block(struct xfs_btree_cur *cur, struct xfs_buf *bp);
 #else
 static inline unsigned int xfs_btree_mem_head_nlevels(struct xfs_buf *head_bp)
 {
@@ -77,11 +107,22 @@ static inline unsigned int xfbtree_bbsize(void)
 #define xfbtree_set_root			NULL
 #define xfbtree_init_ptr_from_cur		NULL
 #define xfbtree_dup_cursor			NULL
+#define xfbtree_get_minrecs			NULL
+#define xfbtree_get_maxrecs			NULL
+#define xfbtree_alloc_block			NULL
+#define xfbtree_free_block			NULL
 #define xfbtree_verify_xfileoff(cur, xfoff)	(false)
 #define xfbtree_check_block_owner(cur, block)	NULL
 #define xfbtree_owner(cur)			(0ULL)
 #define xfbtree_buf_to_xfoff(cur, bp)		(-1)
 
+static inline int
+xfbtree_create(struct xfs_mount *mp, const struct xfbtree_config *cfg,
+		struct xfbtree **xfbtreep)
+{
+	return -EOPNOTSUPP;
+}
+
 #endif /* CONFIG_XFS_BTREE_IN_XFILE */
 
 #endif /* __XFS_BTREE_MEM_H__ */
diff --git a/fs/xfs/scrub/bitmap.c b/fs/xfs/scrub/bitmap.c
index 1449bb5262d95..a82e2e3f93706 100644
--- a/fs/xfs/scrub/bitmap.c
+++ b/fs/xfs/scrub/bitmap.c
@@ -293,6 +293,34 @@ xbitmap64_test(
 	return false;
 }
 
+/*
+ * Find the first set bit in this bitmap, clear it, and return the index of
+ * that bit in @valp.  Returns -ENODATA if no bits were set, or the usual
+ * negative errno.
+ */
+int
+xbitmap64_take_first_set(
+	struct xbitmap64	*bitmap,
+	uint64_t		start,
+	uint64_t		last,
+	uint64_t		*valp)
+{
+	struct xbitmap64_node	*bn;
+	uint64_t		val;
+	int			error;
+
+	bn = xbitmap64_tree_iter_first(&bitmap->xb_root, start, last);
+	if (!bn)
+		return -ENODATA;
+
+	val = bn->bn_start;
+	error = xbitmap64_clear(bitmap, bn->bn_start, 1);
+	if (error)
+		return error;
+	*valp = val;
+	return 0;
+}
+
 /* u32 bitmap */
 
 struct xbitmap32_node {
diff --git a/fs/xfs/scrub/bitmap.h b/fs/xfs/scrub/bitmap.h
index 2df8911606d6d..c88b7bda1b5d8 100644
--- a/fs/xfs/scrub/bitmap.h
+++ b/fs/xfs/scrub/bitmap.h
@@ -34,6 +34,9 @@ int xbitmap64_walk(struct xbitmap64 *bitmap, xbitmap64_walk_fn fn,
 bool xbitmap64_empty(struct xbitmap64 *bitmap);
 bool xbitmap64_test(struct xbitmap64 *bitmap, uint64_t start, uint64_t *len);
 
+int xbitmap64_take_first_set(struct xbitmap64 *bitmap, uint64_t start,
+		uint64_t last, uint64_t *valp);
+
 /* u32 bitmap */
 
 struct xbitmap32 {
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index aeac9cae4ad4c..4a6853accdf12 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -15,6 +15,7 @@
 #include "xfs_quota.h"
 #include "xfs_qm.h"
 #include "xfs_scrub.h"
+#include "xfs_buf_xfile.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
@@ -190,6 +191,10 @@ xchk_teardown(
 		sc->flags &= ~XCHK_HAVE_FREEZE_PROT;
 		mnt_drop_write_file(sc->file);
 	}
+	if (sc->xfile_buftarg) {
+		xfile_free_buftarg(sc->xfile_buftarg);
+		sc->xfile_buftarg = NULL;
+	}
 	if (sc->xfile) {
 		xfile_destroy(sc->xfile);
 		sc->xfile = NULL;
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index f99a3c21d02ea..1f0d655941e32 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -99,6 +99,9 @@ struct xfs_scrub {
 	/* xfile used by the scrubbers; freed at teardown. */
 	struct xfile			*xfile;
 
+	/* buffer target for the xfile; also freed at teardown. */
+	struct xfs_buftarg		*xfile_buftarg;
+
 	/* Lock flags for @ip. */
 	uint				ilock_flags;
 
diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c
index b8f3795f7d9b4..bffe138abc057 100644
--- a/fs/xfs/scrub/trace.c
+++ b/fs/xfs/scrub/trace.c
@@ -12,6 +12,7 @@
 #include "xfs_mount.h"
 #include "xfs_inode.h"
 #include "xfs_btree.h"
+#include "xfs_btree_mem.h"
 #include "xfs_ag.h"
 #include "xfs_rtbitmap.h"
 #include "xfs_quota.h"
@@ -25,6 +26,7 @@
 #include "scrub/iscan.h"
 #include "scrub/nlinks.h"
 #include "scrub/fscounters.h"
+#include "scrub/xfbtree.h"
 
 /* Figure out which block the btree cursor was pointing to. */
 static inline xfs_fsblock_t
@@ -43,6 +45,15 @@ xchk_btree_cur_fsbno(
 	return NULLFSBLOCK;
 }
 
+#ifdef CONFIG_XFS_BTREE_IN_XFILE
+static inline unsigned long
+xfbtree_ino(
+	struct xfbtree		*xfbt)
+{
+	return file_inode(xfbt->target->bt_xfile->file)->i_ino;
+}
+#endif /* CONFIG_XFS_BTREE_IN_XFILE */
+
 /*
  * We include this last to have the helpers above available for the trace
  * event implementations.
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 88e921f4efd26..acea536e09c38 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -25,6 +25,8 @@ struct xchk_dqiter;
 struct xchk_iscan;
 struct xchk_nlink;
 struct xchk_fscounters;
+struct xfbtree;
+struct xfbtree_config;
 
 /*
  * ftrace's __print_symbolic requires that all enum values be wrapped in the
@@ -958,6 +960,8 @@ DEFINE_XFILE_EVENT(xfile_pwrite);
 DEFINE_XFILE_EVENT(xfile_seek_data);
 DEFINE_XFILE_EVENT(xfile_get_page);
 DEFINE_XFILE_EVENT(xfile_put_page);
+DEFINE_XFILE_EVENT(xfile_discard);
+DEFINE_XFILE_EVENT(xfile_prealloc);
 
 TRACE_EVENT(xfarray_create,
 	TP_PROTO(struct xfarray *xfa, unsigned long long required_capacity),
@@ -2176,8 +2180,113 @@ DEFINE_XREP_DQUOT_EVENT(xrep_quotacheck_dquot);
 DEFINE_SCRUB_NLINKS_DIFF_EVENT(xrep_nlinks_update_inode);
 DEFINE_SCRUB_NLINKS_DIFF_EVENT(xrep_nlinks_unfixable_inode);
 
+TRACE_EVENT(xfbtree_create,
+	TP_PROTO(struct xfs_mount *mp, const struct xfbtree_config *cfg,
+		 struct xfbtree *xfbt),
+	TP_ARGS(mp, cfg, xfbt),
+	TP_STRUCT__entry(
+		__field(xfs_btnum_t, btnum)
+		__field(unsigned int, xfbtree_flags)
+		__field(unsigned long, xfino)
+		__field(unsigned int, leaf_mxr)
+		__field(unsigned int, leaf_mnr)
+		__field(unsigned int, node_mxr)
+		__field(unsigned int, node_mnr)
+		__field(unsigned long long, owner)
+	),
+	TP_fast_assign(
+		__entry->btnum = cfg->btnum;
+		__entry->xfbtree_flags = cfg->flags;
+		__entry->xfino = xfbtree_ino(xfbt);
+		__entry->leaf_mxr = xfbt->maxrecs[0];
+		__entry->node_mxr = xfbt->maxrecs[1];
+		__entry->leaf_mnr = xfbt->minrecs[0];
+		__entry->node_mnr = xfbt->minrecs[1];
+		__entry->owner = cfg->owner;
+	),
+	TP_printk("xfino 0x%lx btnum %s owner 0x%llx leaf_mxr %u leaf_mnr %u node_mxr %u node_mnr %u",
+		  __entry->xfino,
+		  __print_symbolic(__entry->btnum, XFS_BTNUM_STRINGS),
+		  __entry->owner,
+		  __entry->leaf_mxr,
+		  __entry->leaf_mnr,
+		  __entry->node_mxr,
+		  __entry->node_mnr)
+);
+
+DECLARE_EVENT_CLASS(xfbtree_buf_class,
+	TP_PROTO(struct xfbtree *xfbt, struct xfs_buf *bp),
+	TP_ARGS(xfbt, bp),
+	TP_STRUCT__entry(
+		__field(unsigned long, xfino)
+		__field(xfs_daddr_t, bno)
+		__field(int, nblks)
+		__field(int, hold)
+		__field(int, pincount)
+		__field(unsigned int, lockval)
+		__field(unsigned int, flags)
+	),
+	TP_fast_assign(
+		__entry->xfino = xfbtree_ino(xfbt);
+		__entry->bno = xfs_buf_daddr(bp);
+		__entry->nblks = bp->b_length;
+		__entry->hold = atomic_read(&bp->b_hold);
+		__entry->pincount = atomic_read(&bp->b_pin_count);
+		__entry->lockval = bp->b_sema.count;
+		__entry->flags = bp->b_flags;
+	),
+	TP_printk("xfino 0x%lx daddr 0x%llx bbcount 0x%x hold %d pincount %d lock %d flags %s",
+		  __entry->xfino,
+		  (unsigned long long)__entry->bno,
+		  __entry->nblks,
+		  __entry->hold,
+		  __entry->pincount,
+		  __entry->lockval,
+		  __print_flags(__entry->flags, "|", XFS_BUF_FLAGS))
+)
+
+#define DEFINE_XFBTREE_BUF_EVENT(name) \
+DEFINE_EVENT(xfbtree_buf_class, name, \
+	TP_PROTO(struct xfbtree *xfbt, struct xfs_buf *bp), \
+	TP_ARGS(xfbt, bp))
+DEFINE_XFBTREE_BUF_EVENT(xfbtree_create_root_buf);
+DEFINE_XFBTREE_BUF_EVENT(xfbtree_trans_commit_buf);
+DEFINE_XFBTREE_BUF_EVENT(xfbtree_trans_cancel_buf);
+
+DECLARE_EVENT_CLASS(xfbtree_freesp_class,
+	TP_PROTO(struct xfbtree *xfbt, struct xfs_btree_cur *cur,
+		 xfs_fileoff_t fileoff),
+	TP_ARGS(xfbt, cur, fileoff),
+	TP_STRUCT__entry(
+		__field(unsigned long, xfino)
+		__field(xfs_btnum_t, btnum)
+		__field(int, nlevels)
+		__field(xfs_fileoff_t, fileoff)
+	),
+	TP_fast_assign(
+		__entry->xfino = xfbtree_ino(xfbt);
+		__entry->btnum = cur->bc_btnum;
+		__entry->nlevels = cur->bc_nlevels;
+		__entry->fileoff = fileoff;
+	),
+	TP_printk("xfino 0x%lx btree %s nlevels %d fileoff 0x%llx",
+		  __entry->xfino,
+		  __print_symbolic(__entry->btnum, XFS_BTNUM_STRINGS),
+		  __entry->nlevels,
+		  (unsigned long long)__entry->fileoff)
+)
+
+#define DEFINE_XFBTREE_FREESP_EVENT(name) \
+DEFINE_EVENT(xfbtree_freesp_class, name, \
+	TP_PROTO(struct xfbtree *xfbt, struct xfs_btree_cur *cur, \
+		 xfs_fileoff_t fileoff), \
+	TP_ARGS(xfbt, cur, fileoff))
+DEFINE_XFBTREE_FREESP_EVENT(xfbtree_alloc_block);
+DEFINE_XFBTREE_FREESP_EVENT(xfbtree_free_block);
+
 #endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
 
+
 #endif /* _TRACE_XFS_SCRUB_TRACE_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/fs/xfs/scrub/xfbtree.c b/fs/xfs/scrub/xfbtree.c
index b7b5aa52b40b4..8879b54068a75 100644
--- a/fs/xfs/scrub/xfbtree.c
+++ b/fs/xfs/scrub/xfbtree.c
@@ -9,14 +9,50 @@
 #include "xfs_format.h"
 #include "xfs_log_format.h"
 #include "xfs_trans_resv.h"
+#include "xfs_bit.h"
 #include "xfs_mount.h"
 #include "xfs_trans.h"
+#include "xfs_buf_item.h"
 #include "xfs_btree.h"
 #include "xfs_error.h"
 #include "xfs_btree_mem.h"
 #include "xfs_ag.h"
+#include "scrub/scrub.h"
 #include "scrub/xfile.h"
 #include "scrub/xfbtree.h"
+#include "scrub/bitmap.h"
+#include "scrub/trace.h"
+
+/* Bitmaps, but for type-checked for xfileoff_t */
+
+static inline void xfboff_bitmap_init(struct xfboff_bitmap *bitmap)
+{
+	xbitmap64_init(&bitmap->xfoffbitmap);
+}
+
+static inline void xfboff_bitmap_destroy(struct xfboff_bitmap *bitmap)
+{
+	xbitmap64_destroy(&bitmap->xfoffbitmap);
+}
+
+static inline int xfboff_bitmap_set(struct xfboff_bitmap *bitmap,
+		xfs_fileoff_t start, xfs_filblks_t len)
+{
+	return xbitmap64_set(&bitmap->xfoffbitmap, start, len);
+}
+
+static inline int xfboff_bitmap_take_first_set(struct xfboff_bitmap *bitmap,
+		xfileoff_t *valp)
+{
+	uint64_t	val;
+	int		error;
+
+	error = xbitmap64_take_first_set(&bitmap->xfoffbitmap, 0, -1ULL, &val);
+	if (error)
+		return error;
+	*valp = val;
+	return 0;
+}
 
 /* btree ops functions for in-memory btrees. */
 
@@ -142,9 +178,18 @@ xfbtree_check_ptr(
 	else
 		bt_xfoff = be32_to_cpu(ptr->s);
 
-	if (!xfbtree_verify_xfileoff(cur, bt_xfoff))
+	if (!xfbtree_verify_xfileoff(cur, bt_xfoff)) {
 		fa = __this_address;
+		goto done;
+	}
 
+	/* Can't point to the head or anything before it */
+	if (bt_xfoff < XFBTREE_INIT_LEAF_BLOCK) {
+		fa = __this_address;
+		goto done;
+	}
+
+done:
 	if (fa) {
 		xfs_err(cur->bc_mp,
 "In-memory: Corrupt btree %d flags 0x%x pointer at level %d index %d fa %pS.",
@@ -350,3 +395,443 @@ xfbtree_sblock_verify(
 
 	return NULL;
 }
+
+/* Close the btree xfile and release all resources. */
+void
+xfbtree_destroy(
+	struct xfbtree		*xfbt)
+{
+	xfboff_bitmap_destroy(&xfbt->freespace);
+	xfs_buftarg_drain(xfbt->target);
+	kfree(xfbt);
+}
+
+/* Compute the number of bytes available for records. */
+static inline unsigned int
+xfbtree_rec_bytes(
+	struct xfs_mount		*mp,
+	const struct xfbtree_config	*cfg)
+{
+	unsigned int			blocklen = xfo_to_b(1);
+
+	if (cfg->flags & XFBTREE_CREATE_LONG_PTRS) {
+		if (xfs_has_crc(mp))
+			return blocklen - XFS_BTREE_LBLOCK_CRC_LEN;
+
+		return blocklen - XFS_BTREE_LBLOCK_LEN;
+	}
+
+	if (xfs_has_crc(mp))
+		return blocklen - XFS_BTREE_SBLOCK_CRC_LEN;
+
+	return blocklen - XFS_BTREE_SBLOCK_LEN;
+}
+
+/* Initialize an empty leaf block as the btree root. */
+STATIC int
+xfbtree_init_leaf_block(
+	struct xfs_mount		*mp,
+	struct xfbtree			*xfbt,
+	const struct xfbtree_config	*cfg)
+{
+	struct xfs_buf			*bp;
+	xfs_daddr_t			daddr;
+	int				error;
+	unsigned int			bc_flags = 0;
+
+	if (cfg->flags & XFBTREE_CREATE_LONG_PTRS)
+		bc_flags |= XFS_BTREE_LONG_PTRS;
+
+	daddr = xfo_to_daddr(XFBTREE_INIT_LEAF_BLOCK);
+	error = xfs_buf_get(xfbt->target, daddr, xfbtree_bbsize(), &bp);
+	if (error)
+		return error;
+
+	trace_xfbtree_create_root_buf(xfbt, bp);
+
+	bp->b_ops = cfg->btree_ops->buf_ops;
+	xfs_btree_init_block_int(mp, bp->b_addr, daddr, cfg->btnum, 0, 0,
+			cfg->owner, bc_flags);
+	error = xfs_bwrite(bp);
+	xfs_buf_relse(bp);
+	if (error)
+		return error;
+
+	xfbt->highest_offset++;
+	return 0;
+}
+
+/* Initialize the in-memory btree header block. */
+STATIC int
+xfbtree_init_head(
+	struct xfbtree		*xfbt)
+{
+	struct xfs_buf		*bp;
+	xfs_daddr_t		daddr;
+	int			error;
+
+	daddr = xfo_to_daddr(XFBTREE_HEAD_BLOCK);
+	error = xfs_buf_get(xfbt->target, daddr, xfbtree_bbsize(), &bp);
+	if (error)
+		return error;
+
+	xfs_btree_mem_head_init(bp, xfbt->owner, XFBTREE_INIT_LEAF_BLOCK);
+	error = xfs_bwrite(bp);
+	xfs_buf_relse(bp);
+	if (error)
+		return error;
+
+	xfbt->highest_offset++;
+	return 0;
+}
+
+/* Create an xfile btree backing thing that can be used for in-memory btrees. */
+int
+xfbtree_create(
+	struct xfs_mount		*mp,
+	const struct xfbtree_config	*cfg,
+	struct xfbtree			**xfbtreep)
+{
+	struct xfbtree			*xfbt;
+	unsigned int			blocklen = xfbtree_rec_bytes(mp, cfg);
+	unsigned int			keyptr_len = cfg->btree_ops->key_len;
+	int				error;
+
+	/* Requires an xfile-backed buftarg. */
+	if (!(cfg->target->bt_flags & XFS_BUFTARG_XFILE)) {
+		ASSERT(cfg->target->bt_flags & XFS_BUFTARG_XFILE);
+		return -EINVAL;
+	}
+
+	xfbt = kzalloc(sizeof(struct xfbtree), XCHK_GFP_FLAGS);
+	if (!xfbt)
+		return -ENOMEM;
+	xfbt->target = cfg->target;
+	xfboff_bitmap_init(&xfbt->freespace);
+
+	/* Set up min/maxrecs for this btree. */
+	if (cfg->flags & XFBTREE_CREATE_LONG_PTRS)
+		keyptr_len += sizeof(__be64);
+	else
+		keyptr_len += sizeof(__be32);
+	xfbt->maxrecs[0] = blocklen / cfg->btree_ops->rec_len;
+	xfbt->maxrecs[1] = blocklen / keyptr_len;
+	xfbt->minrecs[0] = xfbt->maxrecs[0] / 2;
+	xfbt->minrecs[1] = xfbt->maxrecs[1] / 2;
+	xfbt->owner = cfg->owner;
+
+	/* Initialize the empty btree. */
+	error = xfbtree_init_leaf_block(mp, xfbt, cfg);
+	if (error)
+		goto err_freesp;
+
+	error = xfbtree_init_head(xfbt);
+	if (error)
+		goto err_freesp;
+
+	trace_xfbtree_create(mp, cfg, xfbt);
+
+	*xfbtreep = xfbt;
+	return 0;
+
+err_freesp:
+	xfboff_bitmap_destroy(&xfbt->freespace);
+	xfs_buftarg_drain(xfbt->target);
+	kfree(xfbt);
+	return error;
+}
+
+/* Read the in-memory btree head. */
+int
+xfbtree_head_read_buf(
+	struct xfbtree		*xfbt,
+	struct xfs_trans	*tp,
+	struct xfs_buf		**bpp)
+{
+	struct xfs_buftarg	*btp = xfbt->target;
+	struct xfs_mount	*mp = btp->bt_mount;
+	struct xfs_btree_mem_head *mhead;
+	struct xfs_buf		*bp;
+	xfs_daddr_t		daddr;
+	int			error;
+
+	daddr = xfo_to_daddr(XFBTREE_HEAD_BLOCK);
+	error = xfs_trans_read_buf(mp, tp, btp, daddr, xfbtree_bbsize(), 0,
+			&bp, &xfs_btree_mem_head_buf_ops);
+	if (error)
+		return error;
+
+	mhead = bp->b_addr;
+	if (be64_to_cpu(mhead->mh_owner) != xfbt->owner) {
+		xfs_verifier_error(bp, -EFSCORRUPTED, __this_address);
+		xfs_trans_brelse(tp, bp);
+		return -EFSCORRUPTED;
+	}
+
+	*bpp = bp;
+	return 0;
+}
+
+static inline struct xfile *xfbtree_xfile(struct xfbtree *xfbt)
+{
+	return xfbt->target->bt_xfile;
+}
+
+/* Allocate a block to our in-memory btree. */
+int
+xfbtree_alloc_block(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_ptr	*start,
+	union xfs_btree_ptr		*new,
+	int				*stat)
+{
+	struct xfbtree			*xfbt = cur->bc_mem.xfbtree;
+	xfileoff_t			bt_xfoff;
+	loff_t				pos;
+	int				error;
+
+	ASSERT(cur->bc_flags & XFS_BTREE_IN_XFILE);
+
+	/*
+	 * Find the first free block in the free space bitmap and take it.  If
+	 * none are found, seek to end of the file.
+	 */
+	error = xfboff_bitmap_take_first_set(&xfbt->freespace, &bt_xfoff);
+	if (error == -ENODATA) {
+		bt_xfoff = xfbt->highest_offset++;
+		error = 0;
+	}
+	if (error)
+		return error;
+
+	trace_xfbtree_alloc_block(xfbt, cur, bt_xfoff);
+
+	/* Fail if the block address exceeds the maximum for short pointers. */
+	if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS) && bt_xfoff >= INT_MAX) {
+		*stat = 0;
+		return 0;
+	}
+
+	/* Make sure we actually can write to the block before we return it. */
+	pos = xfo_to_b(bt_xfoff);
+	error = xfile_prealloc(xfbtree_xfile(xfbt), pos, xfo_to_b(1));
+	if (error)
+		return error;
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+		new->l = cpu_to_be64(bt_xfoff);
+	else
+		new->s = cpu_to_be32(bt_xfoff);
+
+	*stat = 1;
+	return 0;
+}
+
+/* Free a block from our in-memory btree. */
+int
+xfbtree_free_block(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp)
+{
+	struct xfbtree		*xfbt = cur->bc_mem.xfbtree;
+	xfileoff_t		bt_xfoff, bt_xflen;
+
+	ASSERT(cur->bc_flags & XFS_BTREE_IN_XFILE);
+
+	bt_xfoff = xfs_daddr_to_xfot(xfs_buf_daddr(bp));
+	bt_xflen = xfs_daddr_to_xfot(bp->b_length);
+
+	trace_xfbtree_free_block(xfbt, cur, bt_xfoff);
+
+	return xfboff_bitmap_set(&xfbt->freespace, bt_xfoff, bt_xflen);
+}
+
+/* Return the minimum number of records for a btree block. */
+int
+xfbtree_get_minrecs(
+	struct xfs_btree_cur	*cur,
+	int			level)
+{
+	struct xfbtree		*xfbt = cur->bc_mem.xfbtree;
+
+	return xfbt->minrecs[level != 0];
+}
+
+/* Return the maximum number of records for a btree block. */
+int
+xfbtree_get_maxrecs(
+	struct xfs_btree_cur	*cur,
+	int			level)
+{
+	struct xfbtree		*xfbt = cur->bc_mem.xfbtree;
+
+	return xfbt->maxrecs[level != 0];
+}
+
+/* If this log item is a buffer item that came from the xfbtree, return it. */
+static inline struct xfs_buf *
+xfbtree_buf_match(
+	struct xfbtree			*xfbt,
+	const struct xfs_log_item	*lip)
+{
+	const struct xfs_buf_log_item	*bli;
+	struct xfs_buf			*bp;
+
+	if (lip->li_type != XFS_LI_BUF)
+		return NULL;
+
+	bli = container_of(lip, struct xfs_buf_log_item, bli_item);
+	bp = bli->bli_buf;
+	if (bp->b_target != xfbt->target)
+		return NULL;
+
+	return bp;
+}
+
+/*
+ * Detach this (probably dirty) xfbtree buffer from the transaction by any
+ * means necessary.  Returns true if the buffer needs to be written.
+ */
+STATIC bool
+xfbtree_trans_bdetach(
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp)
+{
+	struct xfs_buf_log_item	*bli = bp->b_log_item;
+	bool			dirty;
+
+	ASSERT(bli != NULL);
+
+	dirty = bli->bli_flags & (XFS_BLI_DIRTY | XFS_BLI_ORDERED);
+
+	bli->bli_flags &= ~(XFS_BLI_DIRTY | XFS_BLI_ORDERED |
+			    XFS_BLI_LOGGED | XFS_BLI_STALE);
+	clear_bit(XFS_LI_DIRTY, &bli->bli_item.li_flags);
+
+	while (bp->b_log_item != NULL)
+		xfs_trans_bdetach(tp, bp);
+
+	return dirty;
+}
+
+/*
+ * Commit changes to the incore btree immediately by writing all dirty xfbtree
+ * buffers to the backing xfile.  This detaches all xfbtree buffers from the
+ * transaction, even on failure.  The buffer locks are dropped between the
+ * delwri queue and submit, so the caller must synchronize btree access.
+ *
+ * Normally we'd let the buffers commit with the transaction and get written to
+ * the xfile via the log, but online repair stages ephemeral btrees in memory
+ * and uses the btree_staging functions to write new btrees to disk atomically.
+ * The in-memory btree (and its backing store) are discarded at the end of the
+ * repair phase, which means that xfbtree buffers cannot commit with the rest
+ * of a transaction.
+ *
+ * In other words, online repair only needs the transaction to collect buffer
+ * pointers and to avoid buffer deadlocks, not to guarantee consistency of
+ * updates.
+ */
+int
+xfbtree_trans_commit(
+	struct xfbtree		*xfbt,
+	struct xfs_trans	*tp)
+{
+	LIST_HEAD(buffer_list);
+	struct xfs_log_item	*lip, *n;
+	bool			corrupt = false;
+	bool			tp_dirty = false;
+
+	/*
+	 * For each xfbtree buffer attached to the transaction, write the dirty
+	 * buffers to the xfile and release them.
+	 */
+	list_for_each_entry_safe(lip, n, &tp->t_items, li_trans) {
+		struct xfs_buf	*bp = xfbtree_buf_match(xfbt, lip);
+		bool		dirty;
+
+		if (!bp) {
+			if (test_bit(XFS_LI_DIRTY, &lip->li_flags))
+				tp_dirty |= true;
+			continue;
+		}
+
+		trace_xfbtree_trans_commit_buf(xfbt, bp);
+
+		dirty = xfbtree_trans_bdetach(tp, bp);
+		if (dirty && !corrupt) {
+			xfs_failaddr_t	fa = bp->b_ops->verify_struct(bp);
+
+			/*
+			 * Because this btree is ephemeral, validate the buffer
+			 * structure before delwri_submit so that we can return
+			 * corruption errors to the caller without shutting
+			 * down the filesystem.
+			 *
+			 * If the buffer fails verification, log the failure
+			 * but continue walking the transaction items so that
+			 * we remove all ephemeral btree buffers.
+			 */
+			if (fa) {
+				corrupt = true;
+				xfs_verifier_error(bp, -EFSCORRUPTED, fa);
+			} else {
+				xfs_buf_delwri_queue_here(bp, &buffer_list);
+			}
+		}
+
+		xfs_buf_relse(bp);
+	}
+
+	/*
+	 * Reset the transaction's dirty flag to reflect the dirty state of the
+	 * log items that are still attached.
+	 */
+	tp->t_flags = (tp->t_flags & ~XFS_TRANS_DIRTY) |
+			(tp_dirty ? XFS_TRANS_DIRTY : 0);
+
+	if (corrupt) {
+		xfs_buf_delwri_cancel(&buffer_list);
+		return -EFSCORRUPTED;
+	}
+
+	if (list_empty(&buffer_list))
+		return 0;
+
+	return xfs_buf_delwri_submit(&buffer_list);
+}
+
+/*
+ * Cancel changes to the incore btree by detaching all the xfbtree buffers.
+ * Changes are not written to the backing store.  This is needed for online
+ * repair btrees, which are by nature ephemeral.
+ */
+void
+xfbtree_trans_cancel(
+	struct xfbtree		*xfbt,
+	struct xfs_trans	*tp)
+{
+	struct xfs_log_item	*lip, *n;
+	bool			tp_dirty = false;
+
+	list_for_each_entry_safe(lip, n, &tp->t_items, li_trans) {
+		struct xfs_buf	*bp = xfbtree_buf_match(xfbt, lip);
+
+		if (!bp) {
+			if (test_bit(XFS_LI_DIRTY, &lip->li_flags))
+				tp_dirty |= true;
+			continue;
+		}
+
+		trace_xfbtree_trans_cancel_buf(xfbt, bp);
+
+		xfbtree_trans_bdetach(tp, bp);
+		xfs_buf_relse(bp);
+	}
+
+	/*
+	 * Reset the transaction's dirty flag to reflect the dirty state of the
+	 * log items that are still attached.
+	 */
+	tp->t_flags = (tp->t_flags & ~XFS_TRANS_DIRTY) |
+			(tp_dirty ? XFS_TRANS_DIRTY : 0);
+}
diff --git a/fs/xfs/scrub/xfbtree.h b/fs/xfs/scrub/xfbtree.h
index b8d2f628e6b7c..ed48981e6c347 100644
--- a/fs/xfs/scrub/xfbtree.h
+++ b/fs/xfs/scrub/xfbtree.h
@@ -8,6 +8,8 @@
 
 #ifdef CONFIG_XFS_BTREE_IN_XFILE
 
+#include "scrub/bitmap.h"
+
 /* Root block for an in-memory btree. */
 struct xfs_btree_mem_head {
 	__be32				mh_magic;
@@ -21,14 +23,41 @@ struct xfs_btree_mem_head {
 
 /* xfile-backed in-memory btrees */
 
+struct xfboff_bitmap {
+	struct xbitmap64		xfoffbitmap;
+};
+
 struct xfbtree {
-	/* buffer cache target for this in-memory btree */
+	/* buffer cache target for the xfile backing this in-memory btree */
 	struct xfs_buftarg		*target;
 
+	/* Bitmap of free space from pos to used */
+	struct xfboff_bitmap		freespace;
+
+	/* Highest xfile offset that has been written to. */
+	xfileoff_t			highest_offset;
+
 	/* Owner of this btree. */
 	unsigned long long		owner;
+
+	/* Minimum and maximum records per block. */
+	unsigned int			maxrecs[2];
+	unsigned int			minrecs[2];
 };
 
+/* The head of the in-memory btree is always at block 0 */
+#define XFBTREE_HEAD_BLOCK		0
+
+/* in-memory btrees are always created with an empty leaf block at block 1 */
+#define XFBTREE_INIT_LEAF_BLOCK		1
+
+int xfbtree_head_read_buf(struct xfbtree *xfbt, struct xfs_trans *tp,
+		struct xfs_buf **bpp);
+
+void xfbtree_destroy(struct xfbtree *xfbt);
+int xfbtree_trans_commit(struct xfbtree *xfbt, struct xfs_trans *tp);
+void xfbtree_trans_cancel(struct xfbtree *xfbt, struct xfs_trans *tp);
+
 #endif /* CONFIG_XFS_BTREE_IN_XFILE */
 
 #endif /* XFS_SCRUB_XFBTREE_H__ */
diff --git a/fs/xfs/scrub/xfile.c b/fs/xfs/scrub/xfile.c
index a76677cba6a3b..9ab5d87963be2 100644
--- a/fs/xfs/scrub/xfile.c
+++ b/fs/xfs/scrub/xfile.c
@@ -278,6 +278,89 @@ xfile_pwrite(
 	return error;
 }
 
+/* Discard pages backing a range of the xfile. */
+void
+xfile_discard(
+	struct xfile		*xf,
+	loff_t			pos,
+	u64			count)
+{
+	trace_xfile_discard(xf, pos, count);
+	shmem_truncate_range(file_inode(xf->file), pos, pos + count - 1);
+}
+
+/* Ensure that there is storage backing the given range. */
+int
+xfile_prealloc(
+	struct xfile		*xf,
+	loff_t			pos,
+	u64			count)
+{
+	struct inode		*inode = file_inode(xf->file);
+	struct address_space	*mapping = inode->i_mapping;
+	const struct address_space_operations *aops = mapping->a_ops;
+	struct page		*page = NULL;
+	unsigned int		pflags;
+	int			error = 0;
+
+	if (count > MAX_RW_COUNT)
+		return -E2BIG;
+	if (inode->i_sb->s_maxbytes - pos < count)
+		return -EFBIG;
+
+	trace_xfile_prealloc(xf, pos, count);
+
+	pflags = memalloc_nofs_save();
+	while (count > 0) {
+		void		*fsdata = NULL;
+		unsigned int	len;
+		int		ret;
+
+		len = min_t(ssize_t, count, PAGE_SIZE - offset_in_page(pos));
+
+		/*
+		 * We call write_begin directly here to avoid all the freezer
+		 * protection lock-taking that happens in the normal path.
+		 * shmem doesn't support fs freeze, but lockdep doesn't know
+		 * that and will trip over that.
+		 */
+		error = aops->write_begin(NULL, mapping, pos, len, &page,
+				&fsdata);
+		if (error)
+			break;
+
+		/*
+		 * xfile pages must never be mapped into userspace, so we skip
+		 * the dcache flush.  If the page is not uptodate, zero it to
+		 * ensure we never go lacking for space here.
+		 */
+		if (!PageUptodate(page)) {
+			void	*kaddr = kmap_local_page(page);
+
+			memset(kaddr, 0, PAGE_SIZE);
+			SetPageUptodate(page);
+			kunmap_local(kaddr);
+		}
+
+		ret = aops->write_end(NULL, mapping, pos, len, len, page,
+				fsdata);
+		if (ret < 0) {
+			error = ret;
+			break;
+		}
+		if (ret != len) {
+			error = -EIO;
+			break;
+		}
+
+		count -= len;
+		pos += len;
+	}
+	memalloc_nofs_restore(pflags);
+
+	return error;
+}
+
 /* Find the next written area in the xfile data for a given offset. */
 loff_t
 xfile_seek_data(
diff --git a/fs/xfs/scrub/xfile.h b/fs/xfs/scrub/xfile.h
index 8bdea8788a8a7..36061af2c1352 100644
--- a/fs/xfs/scrub/xfile.h
+++ b/fs/xfs/scrub/xfile.h
@@ -64,6 +64,8 @@ xfile_obj_store(struct xfile *xf, const void *buf, size_t count, loff_t pos)
 	return 0;
 }
 
+void xfile_discard(struct xfile *xf, loff_t pos, u64 count);
+int xfile_prealloc(struct xfile *xf, loff_t pos, u64 count);
 loff_t xfile_seek_data(struct xfile *xf, loff_t pos);
 
 struct xfile_stat {
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 4a2615db742aa..ba3eed23533f0 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -637,6 +637,7 @@ DEFINE_BUF_ITEM_EVENT(xfs_trans_read_buf);
 DEFINE_BUF_ITEM_EVENT(xfs_trans_read_buf_recur);
 DEFINE_BUF_ITEM_EVENT(xfs_trans_log_buf);
 DEFINE_BUF_ITEM_EVENT(xfs_trans_brelse);
+DEFINE_BUF_ITEM_EVENT(xfs_trans_bdetach);
 DEFINE_BUF_ITEM_EVENT(xfs_trans_bjoin);
 DEFINE_BUF_ITEM_EVENT(xfs_trans_bhold);
 DEFINE_BUF_ITEM_EVENT(xfs_trans_bhold_release);
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 08ce757c74545..3f7e3a09a49ff 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -215,6 +215,7 @@ struct xfs_buf	*xfs_trans_getsb(struct xfs_trans *);
 
 void		xfs_trans_brelse(xfs_trans_t *, struct xfs_buf *);
 void		xfs_trans_bjoin(xfs_trans_t *, struct xfs_buf *);
+void		xfs_trans_bdetach(struct xfs_trans *tp, struct xfs_buf *bp);
 void		xfs_trans_bhold(xfs_trans_t *, struct xfs_buf *);
 void		xfs_trans_bhold_release(xfs_trans_t *, struct xfs_buf *);
 void		xfs_trans_binval(xfs_trans_t *, struct xfs_buf *);
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index 6549e50d852c0..e28ab74af4f0e 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -392,6 +392,48 @@ xfs_trans_brelse(
 	xfs_buf_relse(bp);
 }
 
+/*
+ * Forcibly detach a buffer previously joined to the transaction.  The caller
+ * will retain its locked reference to the buffer after this function returns.
+ * The buffer must be completely clean and must not be held to the transaction.
+ */
+void
+xfs_trans_bdetach(
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp)
+{
+	struct xfs_buf_log_item	*bip = bp->b_log_item;
+
+	ASSERT(tp != NULL);
+	ASSERT(bp->b_transp == tp);
+	ASSERT(bip->bli_item.li_type == XFS_LI_BUF);
+	ASSERT(atomic_read(&bip->bli_refcount) > 0);
+
+	trace_xfs_trans_bdetach(bip);
+
+	/*
+	 * Erase all recursion count, since we're removing this buffer from the
+	 * transaction.
+	 */
+	bip->bli_recur = 0;
+
+	/*
+	 * The buffer must be completely clean.  Specifically, it had better
+	 * not be dirty, stale, logged, ordered, or held to the transaction.
+	 */
+	ASSERT(!test_bit(XFS_LI_DIRTY, &bip->bli_item.li_flags));
+	ASSERT(!(bip->bli_flags & XFS_BLI_DIRTY));
+	ASSERT(!(bip->bli_flags & XFS_BLI_HOLD));
+	ASSERT(!(bip->bli_flags & XFS_BLI_LOGGED));
+	ASSERT(!(bip->bli_flags & XFS_BLI_ORDERED));
+	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
+
+	/* Unlink the log item from the transaction and drop the log item. */
+	xfs_trans_del_item(&bip->bli_item);
+	xfs_buf_item_put(bip);
+	bp->b_transp = NULL;
+}
+
 /*
  * Mark the buffer as not needing to be unlocked when the buf item's
  * iop_committing() routine is called.  The buffer must already be locked

[PATCH 1/4] xfs: create a helper to decide if a file mapping targets the rt volume

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a helper so that we can stop open-coding this decision
everywhere.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_bmap.c       |    6 +++---
 fs/xfs/libxfs/xfs_inode_fork.c |    9 +++++++++
 fs/xfs/libxfs/xfs_inode_fork.h |    1 +
 fs/xfs/scrub/bmap.c            |    2 +-
 4 files changed, 14 insertions(+), 4 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index f815e8b2809bc..e03754826db56 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -4889,7 +4889,7 @@ xfs_bmap_del_extent_delay(
 
 	XFS_STATS_INC(mp, xs_del_exlist);
 
-	isrt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(ip);
+	isrt = xfs_ifork_is_realtime(ip, whichfork);
 	del_endoff = del->br_startoff + del->br_blockcount;
 	got_endoff = got->br_startoff + got->br_blockcount;
 	da_old = startblockval(got->br_startblock);
@@ -5125,7 +5125,7 @@ xfs_bmap_del_extent_real(
 		return -ENOSPC;
 
 	*logflagsp = XFS_ILOG_CORE;
-	if (whichfork == XFS_DATA_FORK && XFS_IS_REALTIME_INODE(ip)) {
+	if (xfs_ifork_is_realtime(ip, whichfork)) {
 		if (!(bflags & XFS_BMAPI_REMAP)) {
 			error = xfs_rtfree_blocks(tp, del->br_startblock,
 					del->br_blockcount);
@@ -5372,7 +5372,7 @@ __xfs_bunmapi(
 		return 0;
 	}
 	XFS_STATS_INC(mp, xs_blk_unmap);
-	isrt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(ip);
+	isrt = xfs_ifork_is_realtime(ip, whichfork);
 	end = start + len;
 
 	if (!xfs_iext_lookup_extent_before(ip, ifp, &end, &icur, &got)) {
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index 88aff6b0bda02..bce36df4402a3 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -820,3 +820,12 @@ xfs_iext_count_upgrade(
 
 	return 0;
 }
+
+/* Decide if a file mapping is on the realtime device or not. */
+bool
+xfs_ifork_is_realtime(
+	struct xfs_inode	*ip,
+	int			whichfork)
+{
+	return XFS_IS_REALTIME_INODE(ip) && whichfork != XFS_ATTR_FORK;
+}
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index 535be5c036899..ebeb925be09d9 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -262,6 +262,7 @@ int xfs_iext_count_may_overflow(struct xfs_inode *ip, int whichfork,
 		int nr_to_add);
 int xfs_iext_count_upgrade(struct xfs_trans *tp, struct xfs_inode *ip,
 		uint nr_to_add);
+bool xfs_ifork_is_realtime(struct xfs_inode *ip, int whichfork);
 
 /* returns true if the fork has extents but they are not read in yet. */
 static inline bool xfs_need_iread_extents(const struct xfs_ifork *ifp)
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index b169cddde6da4..24a15bf784f11 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -924,7 +924,7 @@ xchk_bmap(
 	if (!ifp)
 		return -ENOENT;
 
-	info.is_rt = whichfork == XFS_DATA_FORK && XFS_IS_REALTIME_INODE(ip);
+	info.is_rt = xfs_ifork_is_realtime(ip, whichfork);
 	info.whichfork = whichfork;
 	info.is_shared = whichfork == XFS_DATA_FORK && xfs_is_reflink_inode(ip);
 	info.sc = sc;

[PATCH 2/4] xfs: repair the rmapbt

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Rebuild the reverse mapping btree from all primary metadata.  This first
patch establishes the bare mechanics of finding records and putting
together a new ondisk tree; more complex pieces are needed to make it
work properly.

Link: https://docs.kernel.org/filesystems/xfs-online-fsck-design.html#case-study-rebuilding-reverse-mapping-records
Link: https://docs.kernel.org/filesystems/xfs-online-fsck-design.html#case-study-reaping-after-repairing-reverse-mapping-btrees
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Makefile                |    1 
 fs/xfs/libxfs/xfs_bmap.c       |   43 +
 fs/xfs/libxfs/xfs_bmap.h       |    8 
 fs/xfs/libxfs/xfs_rmap.c       |   12 
 fs/xfs/libxfs/xfs_rmap.h       |    2 
 fs/xfs/libxfs/xfs_rmap_btree.c |   13 
 fs/xfs/scrub/agb_bitmap.h      |    5 
 fs/xfs/scrub/bitmap.c          |   14 
 fs/xfs/scrub/bitmap.h          |    2 
 fs/xfs/scrub/common.c          |    4 
 fs/xfs/scrub/common.h          |    1 
 fs/xfs/scrub/newbt.c           |   12 
 fs/xfs/scrub/newbt.h           |    7 
 fs/xfs/scrub/reap.c            |    2 
 fs/xfs/scrub/repair.c          |    5 
 fs/xfs/scrub/repair.h          |    6 
 fs/xfs/scrub/rmap.c            |   11 
 fs/xfs/scrub/rmap_repair.c     | 1465 ++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/scrub.c           |    2 
 fs/xfs/scrub/trace.h           |   33 +
 20 files changed, 1628 insertions(+), 20 deletions(-)
 create mode 100644 fs/xfs/scrub/rmap_repair.c


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 6dea286d7f194..dfa142eb16f46 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -201,6 +201,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   reap.o \
 				   refcount_repair.o \
 				   repair.o \
+				   rmap_repair.o \
 				   xfbtree.o \
 				   )
 
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index e03754826db56..46ab108825754 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -6362,3 +6362,46 @@ xfs_bunmapi_range(
 out:
 	return error;
 }
+
+struct xfs_bmap_query_range {
+	xfs_bmap_query_range_fn	fn;
+	void			*priv;
+};
+
+/* Format btree record and pass to our callback. */
+STATIC int
+xfs_bmap_query_range_helper(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_rec	*rec,
+	void				*priv)
+{
+	struct xfs_bmap_query_range	*query = priv;
+	struct xfs_bmbt_irec		irec;
+	xfs_failaddr_t			fa;
+
+	xfs_bmbt_disk_get_all(&rec->bmbt, &irec);
+	fa = xfs_bmap_validate_extent(cur->bc_ino.ip, cur->bc_ino.whichfork,
+			&irec);
+	if (fa) {
+		xfs_btree_mark_sick(cur);
+		return xfs_bmap_complain_bad_rec(cur->bc_ino.ip,
+				cur->bc_ino.whichfork, fa, &irec);
+	}
+
+	return query->fn(cur, &irec, query->priv);
+}
+
+/* Find all bmaps. */
+int
+xfs_bmap_query_all(
+	struct xfs_btree_cur		*cur,
+	xfs_bmap_query_range_fn		fn,
+	void				*priv)
+{
+	struct xfs_bmap_query_range	query = {
+		.priv			= priv,
+		.fn			= fn,
+	};
+
+	return xfs_btree_query_all(cur, xfs_bmap_query_range_helper, &query);
+}
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 4b83f6148e007..9dd631bc2dc72 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -278,4 +278,12 @@ extern struct kmem_cache	*xfs_bmap_intent_cache;
 int __init xfs_bmap_intent_init_cache(void);
 void xfs_bmap_intent_destroy_cache(void);
 
+typedef int (*xfs_bmap_query_range_fn)(
+	struct xfs_btree_cur	*cur,
+	struct xfs_bmbt_irec	*rec,
+	void			*priv);
+
+int xfs_bmap_query_all(struct xfs_btree_cur *cur, xfs_bmap_query_range_fn fn,
+		void *priv);
+
 #endif	/* __XFS_BMAP_H__ */
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index cad9b456db81f..4e105207fc7ed 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -215,10 +215,10 @@ xfs_rmap_btrec_to_irec(
 /* Simple checks for rmap records. */
 xfs_failaddr_t
 xfs_rmap_check_irec(
-	struct xfs_btree_cur		*cur,
+	struct xfs_perag		*pag,
 	const struct xfs_rmap_irec	*irec)
 {
-	struct xfs_mount		*mp = cur->bc_mp;
+	struct xfs_mount		*mp = pag->pag_mount;
 	bool				is_inode;
 	bool				is_unwritten;
 	bool				is_bmbt;
@@ -233,8 +233,8 @@ xfs_rmap_check_irec(
 			return __this_address;
 	} else {
 		/* check for valid extent range, including overflow */
-		if (!xfs_verify_agbext(cur->bc_ag.pag, irec->rm_startblock,
-						       irec->rm_blockcount))
+		if (!xfs_verify_agbext(pag, irec->rm_startblock,
+					    irec->rm_blockcount))
 			return __this_address;
 	}
 
@@ -307,7 +307,7 @@ xfs_rmap_get_rec(
 
 	fa = xfs_rmap_btrec_to_irec(rec, irec);
 	if (!fa)
-		fa = xfs_rmap_check_irec(cur, irec);
+		fa = xfs_rmap_check_irec(cur->bc_ag.pag, irec);
 	if (fa)
 		return xfs_rmap_complain_bad_rec(cur, fa, irec);
 
@@ -2442,7 +2442,7 @@ xfs_rmap_query_range_helper(
 
 	fa = xfs_rmap_btrec_to_irec(rec, &irec);
 	if (!fa)
-		fa = xfs_rmap_check_irec(cur, &irec);
+		fa = xfs_rmap_check_irec(cur->bc_ag.pag, &irec);
 	if (fa)
 		return xfs_rmap_complain_bad_rec(cur, fa, &irec);
 
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index 3c98d9d50afb8..58c67896d12cb 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -195,7 +195,7 @@ int xfs_rmap_compare(const struct xfs_rmap_irec *a,
 union xfs_btree_rec;
 xfs_failaddr_t xfs_rmap_btrec_to_irec(const union xfs_btree_rec *rec,
 		struct xfs_rmap_irec *irec);
-xfs_failaddr_t xfs_rmap_check_irec(struct xfs_btree_cur *cur,
+xfs_failaddr_t xfs_rmap_check_irec(struct xfs_perag *pag,
 		const struct xfs_rmap_irec *irec);
 
 int xfs_rmap_has_records(struct xfs_btree_cur *cur, xfs_agblock_t bno,
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index 43ff2236f6237..6d9c6d078bf15 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -342,7 +342,18 @@ xfs_rmapbt_verify(
 
 	level = be16_to_cpu(block->bb_level);
 	if (pag && xfs_perag_initialised_agf(pag)) {
-		if (level >= pag->pagf_levels[XFS_BTNUM_RMAPi])
+		unsigned int	maxlevel = pag->pagf_levels[XFS_BTNUM_RMAPi];
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+		/*
+		 * Online repair could be rewriting the free space btrees, so
+		 * we'll validate against the larger of either tree while this
+		 * is going on.
+		 */
+		maxlevel = max_t(unsigned int, maxlevel,
+				pag->pagf_repair_levels[XFS_BTNUM_RMAPi]);
+#endif
+		if (level >= maxlevel)
 			return __this_address;
 	} else if (level >= mp->m_rmap_maxlevels)
 		return __this_address;
diff --git a/fs/xfs/scrub/agb_bitmap.h b/fs/xfs/scrub/agb_bitmap.h
index ed08f76ff4f3a..e488e1f4f63d3 100644
--- a/fs/xfs/scrub/agb_bitmap.h
+++ b/fs/xfs/scrub/agb_bitmap.h
@@ -65,4 +65,9 @@ int xagb_bitmap_set_btblocks(struct xagb_bitmap *bitmap,
 int xagb_bitmap_set_btcur_path(struct xagb_bitmap *bitmap,
 		struct xfs_btree_cur *cur);
 
+static inline uint32_t xagb_bitmap_count_set_regions(struct xagb_bitmap *b)
+{
+	return xbitmap32_count_set_regions(&b->agbitmap);
+}
+
 #endif	/* __XFS_SCRUB_AGB_BITMAP_H__ */
diff --git a/fs/xfs/scrub/bitmap.c b/fs/xfs/scrub/bitmap.c
index a82e2e3f93706..a9113f32c12ad 100644
--- a/fs/xfs/scrub/bitmap.c
+++ b/fs/xfs/scrub/bitmap.c
@@ -594,3 +594,17 @@ xbitmap32_test(
 	*len = bn->bn_start - start;
 	return false;
 }
+
+/* Count the number of set regions in this bitmap. */
+uint32_t
+xbitmap32_count_set_regions(
+	struct xbitmap32	*bitmap)
+{
+	struct xbitmap32_node	*bn;
+	uint32_t		nr = 0;
+
+	for_each_xbitmap32_extent(bn, bitmap)
+		nr++;
+
+	return nr;
+}
diff --git a/fs/xfs/scrub/bitmap.h b/fs/xfs/scrub/bitmap.h
index c88b7bda1b5d8..7c885d07d4d45 100644
--- a/fs/xfs/scrub/bitmap.h
+++ b/fs/xfs/scrub/bitmap.h
@@ -65,4 +65,6 @@ int xbitmap32_walk(struct xbitmap32 *bitmap, xbitmap32_walk_fn fn,
 bool xbitmap32_empty(struct xbitmap32 *bitmap);
 bool xbitmap32_test(struct xbitmap32 *bitmap, uint32_t start, uint32_t *len);
 
+uint32_t xbitmap32_count_set_regions(struct xbitmap32 *bitmap);
+
 #endif	/* __XFS_SCRUB_BITMAP_H__ */
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 86fea1d816d60..68ec3d5834aee 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -460,7 +460,7 @@ xchk_perag_read_headers(
  * Grab the AG headers for the attached perag structure and wait for pending
  * intents to drain.
  */
-static int
+int
 xchk_perag_drain_and_lock(
 	struct xfs_scrub	*sc)
 {
@@ -712,7 +712,7 @@ xchk_trans_alloc(
 		return xfs_trans_alloc(sc->mp, &M_RES(sc->mp)->tr_itruncate,
 				resblks, 0, 0, &sc->tp);
 
-	return xfs_trans_alloc_empty(sc->mp, &sc->tp);
+	return xchk_trans_alloc_empty(sc);
 }
 
 /* Set us up with a transaction and an empty context. */
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index 6d7364fe13b00..2e6af46519b58 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -134,6 +134,7 @@ int xchk_setup_nlinks(struct xfs_scrub *sc);
 void xchk_ag_free(struct xfs_scrub *sc, struct xchk_ag *sa);
 int xchk_ag_init(struct xfs_scrub *sc, xfs_agnumber_t agno,
 		struct xchk_ag *sa);
+int xchk_perag_drain_and_lock(struct xfs_scrub *sc);
 
 /*
  * Grab all AG resources, treating the inability to grab the perag structure as
diff --git a/fs/xfs/scrub/newbt.c b/fs/xfs/scrub/newbt.c
index bb6d980b4fcdc..ad2da235d21bb 100644
--- a/fs/xfs/scrub/newbt.c
+++ b/fs/xfs/scrub/newbt.c
@@ -239,7 +239,11 @@ xrep_newbt_alloc_ag_blocks(
 
 		xrep_newbt_validate_ag_alloc_hint(xnr);
 
-		error = xfs_alloc_vextent_near_bno(&args, xnr->alloc_hint);
+		if (xnr->alloc_vextent)
+			error = xnr->alloc_vextent(sc, &args, xnr->alloc_hint);
+		else
+			error = xfs_alloc_vextent_near_bno(&args,
+					xnr->alloc_hint);
 		if (error)
 			return error;
 		if (args.fsbno == NULLFSBLOCK)
@@ -309,7 +313,11 @@ xrep_newbt_alloc_file_blocks(
 
 		xrep_newbt_validate_file_alloc_hint(xnr);
 
-		error = xfs_alloc_vextent_start_ag(&args, xnr->alloc_hint);
+		if (xnr->alloc_vextent)
+			error = xnr->alloc_vextent(sc, &args, xnr->alloc_hint);
+		else
+			error = xfs_alloc_vextent_start_ag(&args,
+					xnr->alloc_hint);
 		if (error)
 			return error;
 		if (args.fsbno == NULLFSBLOCK)
diff --git a/fs/xfs/scrub/newbt.h b/fs/xfs/scrub/newbt.h
index 89f8e3970b1f6..3d804d31af24a 100644
--- a/fs/xfs/scrub/newbt.h
+++ b/fs/xfs/scrub/newbt.h
@@ -6,6 +6,8 @@
 #ifndef __XFS_SCRUB_NEWBT_H__
 #define __XFS_SCRUB_NEWBT_H__
 
+struct xfs_alloc_arg;
+
 struct xrep_newbt_resv {
 	/* Link to list of extents that we've reserved. */
 	struct list_head	list;
@@ -28,6 +30,11 @@ struct xrep_newbt_resv {
 struct xrep_newbt {
 	struct xfs_scrub	*sc;
 
+	/* Custom allocation function, or NULL for xfs_alloc_vextent */
+	int			(*alloc_vextent)(struct xfs_scrub *sc,
+						 struct xfs_alloc_arg *args,
+						 xfs_fsblock_t alloc_hint);
+
 	/* List of extents that we've reserved. */
 	struct list_head	resv_list;
 
diff --git a/fs/xfs/scrub/reap.c b/fs/xfs/scrub/reap.c
index f99eca799809b..0252a3b5b65ac 100644
--- a/fs/xfs/scrub/reap.c
+++ b/fs/xfs/scrub/reap.c
@@ -114,7 +114,7 @@ xreap_put_freelist(
 	int			error;
 
 	/* Make sure there's space on the freelist. */
-	error = xrep_fix_freelist(sc, true);
+	error = xrep_fix_freelist(sc, 0);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index ab510cea96d86..5a3ae65ccbc41 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -401,7 +401,7 @@ xrep_calc_ag_resblks(
 int
 xrep_fix_freelist(
 	struct xfs_scrub	*sc,
-	bool			can_shrink)
+	int			alloc_flags)
 {
 	struct xfs_alloc_arg	args = {0};
 
@@ -411,8 +411,7 @@ xrep_fix_freelist(
 	args.alignment = 1;
 	args.pag = sc->sa.pag;
 
-	return xfs_alloc_fix_freelist(&args,
-			can_shrink ? 0 : XFS_ALLOC_FLAG_NOSHRINK);
+	return xfs_alloc_fix_freelist(&args, alloc_flags);
 }
 
 /*
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 2ff2bb79c540c..c01e56799bd1d 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -51,7 +51,7 @@ struct xbitmap;
 struct xagb_bitmap;
 struct xfsb_bitmap;
 
-int xrep_fix_freelist(struct xfs_scrub *sc, bool can_shrink);
+int xrep_fix_freelist(struct xfs_scrub *sc, int alloc_flags);
 
 struct xrep_find_ag_btree {
 	/* in: rmap owner of the btree we're looking for */
@@ -86,6 +86,7 @@ int xrep_ino_ensure_extent_count(struct xfs_scrub *sc, int whichfork,
 int xrep_reset_perag_resv(struct xfs_scrub *sc);
 int xrep_bmap(struct xfs_scrub *sc, int whichfork, bool allow_unwritten);
 int xrep_metadata_inode_forks(struct xfs_scrub *sc);
+int xrep_setup_ag_rmapbt(struct xfs_scrub *sc);
 
 /* Repair setup functions */
 int xrep_setup_ag_allocbt(struct xfs_scrub *sc);
@@ -111,6 +112,7 @@ int xrep_agfl(struct xfs_scrub *sc);
 int xrep_agi(struct xfs_scrub *sc);
 int xrep_allocbt(struct xfs_scrub *sc);
 int xrep_iallocbt(struct xfs_scrub *sc);
+int xrep_rmapbt(struct xfs_scrub *sc);
 int xrep_refcountbt(struct xfs_scrub *sc);
 int xrep_inode(struct xfs_scrub *sc);
 int xrep_bmap_data(struct xfs_scrub *sc);
@@ -177,6 +179,7 @@ xrep_setup_nothing(
 	return 0;
 }
 #define xrep_setup_ag_allocbt		xrep_setup_nothing
+#define xrep_setup_ag_rmapbt		xrep_setup_nothing
 
 #define xrep_setup_inode(sc, imap)	((void)0)
 
@@ -190,6 +193,7 @@ xrep_setup_nothing(
 #define xrep_agi			xrep_notsupported
 #define xrep_allocbt			xrep_notsupported
 #define xrep_iallocbt			xrep_notsupported
+#define xrep_rmapbt			xrep_notsupported
 #define xrep_refcountbt			xrep_notsupported
 #define xrep_inode			xrep_notsupported
 #define xrep_bmap_data			xrep_notsupported
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index c99d1714f283b..ec3a019521980 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -25,6 +25,7 @@
 #include "scrub/btree.h"
 #include "scrub/bitmap.h"
 #include "scrub/agb_bitmap.h"
+#include "scrub/repair.h"
 
 /*
  * Set us up to scrub reverse mapping btrees.
@@ -36,6 +37,14 @@ xchk_setup_ag_rmapbt(
 	if (xchk_need_intent_drain(sc))
 		xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN);
 
+	if (xchk_could_repair(sc)) {
+		int		error;
+
+		error = xrep_setup_ag_rmapbt(sc);
+		if (error)
+			return error;
+	}
+
 	return xchk_setup_ag_btree(sc, false);
 }
 
@@ -349,7 +358,7 @@ xchk_rmapbt_rec(
 	struct xfs_rmap_irec	irec;
 
 	if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL ||
-	    xfs_rmap_check_irec(bs->cur, &irec) != NULL) {
+	    xfs_rmap_check_irec(bs->cur->bc_ag.pag, &irec) != NULL) {
 		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 		return 0;
 	}
diff --git a/fs/xfs/scrub/rmap_repair.c b/fs/xfs/scrub/rmap_repair.c
new file mode 100644
index 0000000000000..e835ce296af7f
--- /dev/null
+++ b/fs/xfs/scrub/rmap_repair.c
@@ -0,0 +1,1465 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2018-2024 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_defer.h"
+#include "xfs_btree.h"
+#include "xfs_btree_staging.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_alloc.h"
+#include "xfs_alloc_btree.h"
+#include "xfs_ialloc.h"
+#include "xfs_ialloc_btree.h"
+#include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_refcount.h"
+#include "xfs_refcount_btree.h"
+#include "xfs_ag.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/btree.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/bitmap.h"
+#include "scrub/agb_bitmap.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/iscan.h"
+#include "scrub/newbt.h"
+#include "scrub/reap.h"
+
+/*
+ * Reverse Mapping Btree Repair
+ * ============================
+ *
+ * This is the most involved of all the AG space btree rebuilds.  Everywhere
+ * else in XFS we lock inodes and then AG data structures, but generating the
+ * list of rmap records requires that we be able to scan both block mapping
+ * btrees of every inode in the filesystem to see if it owns any extents in
+ * this AG.  We can't tolerate any inode updates while we do this, so we
+ * freeze the filesystem to lock everyone else out, and grant ourselves
+ * special privileges to run transactions with regular background reclamation
+ * turned off.
+ *
+ * We also have to be very careful not to allow inode reclaim to start a
+ * transaction because all transactions (other than our own) will block.
+ * Deferred inode inactivation helps us out there.
+ *
+ * I) Reverse mappings for all non-space metadata and file data are collected
+ * according to the following algorithm:
+ *
+ * 1. For each fork of each inode:
+ * 1.1. Create a bitmap BMBIT to track bmbt blocks if necessary.
+ * 1.2. If the incore extent map isn't loaded, walk the bmbt to accumulate
+ *      bmaps into rmap records (see 1.1.4).  Set bits in BMBIT for each btree
+ *      block.
+ * 1.3. If the incore extent map is loaded but the fork is in btree format,
+ *      just visit the bmbt blocks to set the corresponding BMBIT areas.
+ * 1.4. From the incore extent map, accumulate each bmap that falls into our
+ *      target AG.  Remember, multiple bmap records can map to a single rmap
+ *      record, so we cannot simply emit rmap records 1:1.
+ * 1.5. Emit rmap records for each extent in BMBIT and free it.
+ * 2. Create bitmaps INOBIT and ICHUNKBIT.
+ * 3. For each record in the inobt, set the corresponding areas in ICHUNKBIT,
+ *    and set bits in INOBIT for each btree block.  If the inobt has no records
+ *    at all, we must be careful to record its root in INOBIT.
+ * 4. For each block in the finobt, set the corresponding INOBIT area.
+ * 5. Emit rmap records for each extent in INOBIT and ICHUNKBIT and free them.
+ * 6. Create bitmaps REFCBIT and COWBIT.
+ * 7. For each CoW staging extent in the refcountbt, set the corresponding
+ *    areas in COWBIT.
+ * 8. For each block in the refcountbt, set the corresponding REFCBIT area.
+ * 9. Emit rmap records for each extent in REFCBIT and COWBIT and free them.
+ * A. Emit rmap for the AG headers.
+ * B. Emit rmap for the log, if there is one.
+ *
+ * II) The rmapbt shape and space metadata rmaps are computed as follows:
+ *
+ * 1. Count the rmaps collected in the previous step. (= NR)
+ * 2. Estimate the number of rmapbt blocks needed to store NR records. (= RMB)
+ * 3. Reserve RMB blocks through the newbt using the allocator in normap mode.
+ * 4. Create bitmap AGBIT.
+ * 5. For each reservation in the newbt, set the corresponding areas in AGBIT.
+ * 6. For each block in the AGFL, bnobt, and cntbt, set the bits in AGBIT.
+ * 7. Count the extents in AGBIT. (= AGNR)
+ * 8. Estimate the number of rmapbt blocks needed for NR + AGNR rmaps. (= RMB')
+ * 9. If RMB' >= RMB, reserve RMB' - RMB more newbt blocks, set RMB = RMB',
+ *    and clear AGBIT.  Go to step 5.
+ * A. Emit rmaps for each extent in AGBIT.
+ *
+ * III) The rmapbt is constructed and set in place as follows:
+ *
+ * 1. Sort the rmap records.
+ * 2. Bulk load the rmaps.
+ *
+ * IV) Reap the old btree blocks.
+ *
+ * 1. Create a bitmap OLDRMBIT.
+ * 2. For each gap in the new rmapbt, set the corresponding areas of OLDRMBIT.
+ * 3. For each extent in the bnobt, clear the corresponding parts of OLDRMBIT.
+ * 4. Reap the extents corresponding to the set areas in OLDRMBIT.  These are
+ *    the parts of the AG that the rmap didn't find during its scan of the
+ *    primary metadata and aren't known to be in the free space, which implies
+ *    that they were the old rmapbt blocks.
+ * 5. Commit.
+ *
+ * We use the 'xrep_rmap' prefix for all the rmap functions.
+ */
+
+/*
+ * Packed rmap record.  The ATTR/BMBT/UNWRITTEN flags are hidden in the upper
+ * bits of offset, just like the on-disk record.
+ */
+struct xrep_rmap_extent {
+	xfs_agblock_t	startblock;
+	xfs_extlen_t	blockcount;
+	uint64_t	owner;
+	uint64_t	offset;
+} __packed;
+
+/* Context for collecting rmaps */
+struct xrep_rmap {
+	/* new rmapbt information */
+	struct xrep_newbt	new_btree;
+
+	/* rmap records generated from primary metadata */
+	struct xfarray		*rmap_records;
+
+	struct xfs_scrub	*sc;
+
+	/* get_records()'s position in the rmap record array. */
+	xfarray_idx_t		array_cur;
+
+	/* inode scan cursor */
+	struct xchk_iscan	iscan;
+
+	/* bnobt/cntbt contribution to btreeblks */
+	xfs_agblock_t		freesp_btblocks;
+
+	/* old agf_rmap_blocks counter */
+	unsigned int		old_rmapbt_fsbcount;
+};
+
+/* Set us up to repair reverse mapping btrees. */
+int
+xrep_setup_ag_rmapbt(
+	struct xfs_scrub	*sc)
+{
+	struct xrep_rmap	*rr;
+
+	rr = kzalloc(sizeof(struct xrep_rmap), XCHK_GFP_FLAGS);
+	if (!rr)
+		return -ENOMEM;
+
+	rr->sc = sc;
+	sc->buf = rr;
+	return 0;
+}
+
+/* Make sure there's nothing funny about this mapping. */
+STATIC int
+xrep_rmap_check_mapping(
+	struct xfs_scrub	*sc,
+	const struct xfs_rmap_irec *rec)
+{
+	enum xbtree_recpacking	outcome;
+	int			error;
+
+	if (xfs_rmap_check_irec(sc->sa.pag, rec) != NULL)
+		return -EFSCORRUPTED;
+
+	/* Make sure this isn't free space. */
+	error = xfs_alloc_has_records(sc->sa.bno_cur, rec->rm_startblock,
+			rec->rm_blockcount, &outcome);
+	if (error)
+		return error;
+	if (outcome != XBTREE_RECPACKING_EMPTY)
+		return -EFSCORRUPTED;
+
+	return 0;
+}
+
+/* Store a reverse-mapping record. */
+static inline int
+xrep_rmap_stash(
+	struct xrep_rmap	*rr,
+	xfs_agblock_t		startblock,
+	xfs_extlen_t		blockcount,
+	uint64_t		owner,
+	uint64_t		offset,
+	unsigned int		flags)
+{
+	struct xrep_rmap_extent	rre = {
+		.startblock	= startblock,
+		.blockcount	= blockcount,
+		.owner		= owner,
+	};
+	struct xfs_rmap_irec	rmap = {
+		.rm_startblock	= startblock,
+		.rm_blockcount	= blockcount,
+		.rm_owner	= owner,
+		.rm_offset	= offset,
+		.rm_flags	= flags,
+	};
+	struct xfs_scrub	*sc = rr->sc;
+	int			error = 0;
+
+	if (xchk_should_terminate(sc, &error))
+		return error;
+
+	trace_xrep_rmap_found(sc->mp, sc->sa.pag->pag_agno, &rmap);
+
+	rre.offset = xfs_rmap_irec_offset_pack(&rmap);
+	return xfarray_append(rr->rmap_records, &rre);
+}
+
+struct xrep_rmap_stash_run {
+	struct xrep_rmap	*rr;
+	uint64_t		owner;
+	unsigned int		rmap_flags;
+};
+
+static int
+xrep_rmap_stash_run(
+	uint32_t			start,
+	uint32_t			len,
+	void				*priv)
+{
+	struct xrep_rmap_stash_run	*rsr = priv;
+	struct xrep_rmap		*rr = rsr->rr;
+
+	return xrep_rmap_stash(rr, start, len, rsr->owner, 0, rsr->rmap_flags);
+}
+
+/*
+ * Emit rmaps for every extent of bits set in the bitmap.  Caller must ensure
+ * that the ranges are in units of FS blocks.
+ */
+STATIC int
+xrep_rmap_stash_bitmap(
+	struct xrep_rmap		*rr,
+	struct xagb_bitmap		*bitmap,
+	const struct xfs_owner_info	*oinfo)
+{
+	struct xrep_rmap_stash_run	rsr = {
+		.rr			= rr,
+		.owner			= oinfo->oi_owner,
+		.rmap_flags		= 0,
+	};
+
+	if (oinfo->oi_flags & XFS_OWNER_INFO_ATTR_FORK)
+		rsr.rmap_flags |= XFS_RMAP_ATTR_FORK;
+	if (oinfo->oi_flags & XFS_OWNER_INFO_BMBT_BLOCK)
+		rsr.rmap_flags |= XFS_RMAP_BMBT_BLOCK;
+
+	return xagb_bitmap_walk(bitmap, xrep_rmap_stash_run, &rsr);
+}
+
+/* Section (I): Finding all file and bmbt extents. */
+
+/* Context for accumulating rmaps for an inode fork. */
+struct xrep_rmap_ifork {
+	/*
+	 * Accumulate rmap data here to turn multiple adjacent bmaps into a
+	 * single rmap.
+	 */
+	struct xfs_rmap_irec	accum;
+
+	/* Bitmap of bmbt blocks in this AG. */
+	struct xagb_bitmap	bmbt_blocks;
+
+	struct xrep_rmap	*rr;
+
+	/* Which inode fork? */
+	int			whichfork;
+};
+
+/* Stash an rmap that we accumulated while walking an inode fork. */
+STATIC int
+xrep_rmap_stash_accumulated(
+	struct xrep_rmap_ifork	*rf)
+{
+	if (rf->accum.rm_blockcount == 0)
+		return 0;
+
+	return xrep_rmap_stash(rf->rr, rf->accum.rm_startblock,
+			rf->accum.rm_blockcount, rf->accum.rm_owner,
+			rf->accum.rm_offset, rf->accum.rm_flags);
+}
+
+/* Accumulate a bmbt record. */
+STATIC int
+xrep_rmap_visit_bmbt(
+	struct xfs_btree_cur	*cur,
+	struct xfs_bmbt_irec	*rec,
+	void			*priv)
+{
+	struct xrep_rmap_ifork	*rf = priv;
+	struct xfs_mount	*mp = rf->rr->sc->mp;
+	struct xfs_rmap_irec	*accum = &rf->accum;
+	xfs_agblock_t		agbno;
+	unsigned int		rmap_flags = 0;
+	int			error;
+
+	if (XFS_FSB_TO_AGNO(mp, rec->br_startblock) !=
+			rf->rr->sc->sa.pag->pag_agno)
+		return 0;
+
+	agbno = XFS_FSB_TO_AGBNO(mp, rec->br_startblock);
+	if (rf->whichfork == XFS_ATTR_FORK)
+		rmap_flags |= XFS_RMAP_ATTR_FORK;
+	if (rec->br_state == XFS_EXT_UNWRITTEN)
+		rmap_flags |= XFS_RMAP_UNWRITTEN;
+
+	/* If this bmap is adjacent to the previous one, just add it. */
+	if (accum->rm_blockcount > 0 &&
+	    rec->br_startoff == accum->rm_offset + accum->rm_blockcount &&
+	    agbno == accum->rm_startblock + accum->rm_blockcount &&
+	    rmap_flags == accum->rm_flags) {
+		accum->rm_blockcount += rec->br_blockcount;
+		return 0;
+	}
+
+	/* Otherwise stash the old rmap and start accumulating a new one. */
+	error = xrep_rmap_stash_accumulated(rf);
+	if (error)
+		return error;
+
+	accum->rm_startblock = agbno;
+	accum->rm_blockcount = rec->br_blockcount;
+	accum->rm_offset = rec->br_startoff;
+	accum->rm_flags = rmap_flags;
+	return 0;
+}
+
+/* Add a btree block to the bitmap. */
+STATIC int
+xrep_rmap_visit_iroot_btree_block(
+	struct xfs_btree_cur	*cur,
+	int			level,
+	void			*priv)
+{
+	struct xrep_rmap_ifork	*rf = priv;
+	struct xfs_buf		*bp;
+	xfs_fsblock_t		fsbno;
+	xfs_agblock_t		agbno;
+
+	xfs_btree_get_block(cur, level, &bp);
+	if (!bp)
+		return 0;
+
+	fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp));
+	if (XFS_FSB_TO_AGNO(cur->bc_mp, fsbno) != rf->rr->sc->sa.pag->pag_agno)
+		return 0;
+
+	agbno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno);
+	return xagb_bitmap_set(&rf->bmbt_blocks, agbno, 1);
+}
+
+/*
+ * Iterate a metadata btree rooted in an inode to collect rmap records for
+ * anything in this fork that matches the AG.
+ */
+STATIC int
+xrep_rmap_scan_iroot_btree(
+	struct xrep_rmap_ifork	*rf,
+	struct xfs_btree_cur	*cur)
+{
+	struct xfs_owner_info	oinfo;
+	struct xrep_rmap	*rr = rf->rr;
+	int			error;
+
+	xagb_bitmap_init(&rf->bmbt_blocks);
+
+	/* Record all the blocks in the btree itself. */
+	error = xfs_btree_visit_blocks(cur, xrep_rmap_visit_iroot_btree_block,
+			XFS_BTREE_VISIT_ALL, rf);
+	if (error)
+		goto out;
+
+	/* Emit rmaps for the btree blocks. */
+	xfs_rmap_ino_bmbt_owner(&oinfo, rf->accum.rm_owner, rf->whichfork);
+	error = xrep_rmap_stash_bitmap(rr, &rf->bmbt_blocks, &oinfo);
+	if (error)
+		goto out;
+
+	/* Stash any remaining accumulated rmaps. */
+	error = xrep_rmap_stash_accumulated(rf);
+out:
+	xagb_bitmap_destroy(&rf->bmbt_blocks);
+	return error;
+}
+
+static inline bool
+is_rt_data_fork(
+	struct xfs_inode	*ip,
+	int			whichfork)
+{
+	return XFS_IS_REALTIME_INODE(ip) && whichfork == XFS_DATA_FORK;
+}
+
+/*
+ * Iterate the block mapping btree to collect rmap records for anything in this
+ * fork that matches the AG.  Sets @mappings_done to true if we've scanned the
+ * block mappings in this fork.
+ */
+STATIC int
+xrep_rmap_scan_bmbt(
+	struct xrep_rmap_ifork	*rf,
+	struct xfs_inode	*ip,
+	bool			*mappings_done)
+{
+	struct xrep_rmap	*rr = rf->rr;
+	struct xfs_btree_cur	*cur;
+	struct xfs_ifork	*ifp;
+	int			error;
+
+	*mappings_done = false;
+	ifp = xfs_ifork_ptr(ip, rf->whichfork);
+	cur = xfs_bmbt_init_cursor(rr->sc->mp, rr->sc->tp, ip, rf->whichfork);
+
+	if (!xfs_ifork_is_realtime(ip, rf->whichfork) &&
+	    xfs_need_iread_extents(ifp)) {
+		/*
+		 * If the incore extent cache isn't loaded, scan the bmbt for
+		 * mapping records.  This avoids loading the incore extent
+		 * tree, which will increase memory pressure at a time when
+		 * we're trying to run as quickly as we possibly can.  Ignore
+		 * realtime extents.
+		 */
+		error = xfs_bmap_query_all(cur, xrep_rmap_visit_bmbt, rf);
+		if (error)
+			goto out_cur;
+
+		*mappings_done = true;
+	}
+
+	/* Scan for the bmbt blocks, which always live on the data device. */
+	error = xrep_rmap_scan_iroot_btree(rf, cur);
+out_cur:
+	xfs_btree_del_cursor(cur, error);
+	return error;
+}
+
+/*
+ * Iterate the in-core extent cache to collect rmap records for anything in
+ * this fork that matches the AG.
+ */
+STATIC int
+xrep_rmap_scan_iext(
+	struct xrep_rmap_ifork	*rf,
+	struct xfs_ifork	*ifp)
+{
+	struct xfs_bmbt_irec	rec;
+	struct xfs_iext_cursor	icur;
+	int			error;
+
+	for_each_xfs_iext(ifp, &icur, &rec) {
+		if (isnullstartblock(rec.br_startblock))
+			continue;
+		error = xrep_rmap_visit_bmbt(NULL, &rec, rf);
+		if (error)
+			return error;
+	}
+
+	return xrep_rmap_stash_accumulated(rf);
+}
+
+/* Find all the extents from a given AG in an inode fork. */
+STATIC int
+xrep_rmap_scan_ifork(
+	struct xrep_rmap	*rr,
+	struct xfs_inode	*ip,
+	int			whichfork)
+{
+	struct xrep_rmap_ifork	rf = {
+		.accum		= { .rm_owner = ip->i_ino, },
+		.rr		= rr,
+		.whichfork	= whichfork,
+	};
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);
+	int			error = 0;
+
+	if (!ifp)
+		return 0;
+
+	if (ifp->if_format == XFS_DINODE_FMT_BTREE) {
+		bool		mappings_done;
+
+		/*
+		 * Scan the bmap btree for data device mappings.  This includes
+		 * the btree blocks themselves, even if this is a realtime
+		 * file.
+		 */
+		error = xrep_rmap_scan_bmbt(&rf, ip, &mappings_done);
+		if (error || mappings_done)
+			return error;
+	} else if (ifp->if_format != XFS_DINODE_FMT_EXTENTS) {
+		return 0;
+	}
+
+	/* Scan incore extent cache if this isn't a realtime file. */
+	if (xfs_ifork_is_realtime(ip, whichfork))
+		return 0;
+
+	return xrep_rmap_scan_iext(&rf, ifp);
+}
+
+/*
+ * Take ILOCK on a file that we want to scan.
+ *
+ * Select ILOCK_EXCL if the file has an unloaded data bmbt or has an unloaded
+ * attr bmbt.  Otherwise, take ILOCK_SHARED.
+ */
+static inline unsigned int
+xrep_rmap_scan_ilock(
+	struct xfs_inode	*ip)
+{
+	uint			lock_mode = XFS_ILOCK_SHARED;
+
+	if (xfs_need_iread_extents(&ip->i_df)) {
+		lock_mode = XFS_ILOCK_EXCL;
+		goto lock;
+	}
+
+	if (xfs_inode_has_attr_fork(ip) && xfs_need_iread_extents(&ip->i_af))
+		lock_mode = XFS_ILOCK_EXCL;
+
+lock:
+	xfs_ilock(ip, lock_mode);
+	return lock_mode;
+}
+
+/* Record reverse mappings for a file. */
+STATIC int
+xrep_rmap_scan_inode(
+	struct xrep_rmap	*rr,
+	struct xfs_inode	*ip)
+{
+	unsigned int		lock_mode = 0;
+	int			error;
+
+	/*
+	 * Directory updates (create/link/unlink/rename) drop the directory's
+	 * ILOCK before finishing any rmapbt updates associated with directory
+	 * shape changes.  For this scan to coordinate correctly with the live
+	 * update hook, we must take the only lock (i_rwsem) that is held all
+	 * the way to dir op completion.  This will get fixed by the parent
+	 * pointer patchset.
+	 */
+	if (S_ISDIR(VFS_I(ip)->i_mode)) {
+		lock_mode = XFS_IOLOCK_SHARED;
+		xfs_ilock(ip, lock_mode);
+	}
+	lock_mode |= xrep_rmap_scan_ilock(ip);
+
+	/* Check the data fork. */
+	error = xrep_rmap_scan_ifork(rr, ip, XFS_DATA_FORK);
+	if (error)
+		goto out_unlock;
+
+	/* Check the attr fork. */
+	error = xrep_rmap_scan_ifork(rr, ip, XFS_ATTR_FORK);
+	if (error)
+		goto out_unlock;
+
+	/* COW fork extents are "owned" by the refcount btree. */
+
+	xchk_iscan_mark_visited(&rr->iscan, ip);
+out_unlock:
+	xfs_iunlock(ip, lock_mode);
+	return error;
+}
+
+/* Section (I): Find all AG metadata extents except for free space metadata. */
+
+struct xrep_rmap_inodes {
+	struct xrep_rmap	*rr;
+	struct xagb_bitmap	inobt_blocks;	/* INOBIT */
+	struct xagb_bitmap	ichunk_blocks;	/* ICHUNKBIT */
+};
+
+/* Record inode btree rmaps. */
+STATIC int
+xrep_rmap_walk_inobt(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_rec	*rec,
+	void				*priv)
+{
+	struct xfs_inobt_rec_incore	irec;
+	struct xrep_rmap_inodes		*ri = priv;
+	struct xfs_mount		*mp = cur->bc_mp;
+	xfs_agblock_t			agbno;
+	xfs_agino_t			agino;
+	xfs_agino_t			iperhole;
+	unsigned int			i;
+	int				error;
+
+	/* Record the inobt blocks. */
+	error = xagb_bitmap_set_btcur_path(&ri->inobt_blocks, cur);
+	if (error)
+		return error;
+
+	xfs_inobt_btrec_to_irec(mp, rec, &irec);
+	if (xfs_inobt_check_irec(cur->bc_ag.pag, &irec) != NULL)
+		return -EFSCORRUPTED;
+
+	agino = irec.ir_startino;
+
+	/* Record a non-sparse inode chunk. */
+	if (!xfs_inobt_issparse(irec.ir_holemask)) {
+		agbno = XFS_AGINO_TO_AGBNO(mp, agino);
+
+		return xagb_bitmap_set(&ri->ichunk_blocks, agbno,
+				XFS_INODES_PER_CHUNK / mp->m_sb.sb_inopblock);
+	}
+
+	/* Iterate each chunk. */
+	iperhole = max_t(xfs_agino_t, mp->m_sb.sb_inopblock,
+			XFS_INODES_PER_HOLEMASK_BIT);
+	for (i = 0, agino = irec.ir_startino;
+	     i < XFS_INOBT_HOLEMASK_BITS;
+	     i += iperhole / XFS_INODES_PER_HOLEMASK_BIT, agino += iperhole) {
+		/* Skip holes. */
+		if (irec.ir_holemask & (1 << i))
+			continue;
+
+		/* Record the inode chunk otherwise. */
+		agbno = XFS_AGINO_TO_AGBNO(mp, agino);
+		error = xagb_bitmap_set(&ri->ichunk_blocks, agbno,
+				iperhole / mp->m_sb.sb_inopblock);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+/* Collect rmaps for the blocks containing inode btrees and the inode chunks. */
+STATIC int
+xrep_rmap_find_inode_rmaps(
+	struct xrep_rmap	*rr)
+{
+	struct xrep_rmap_inodes	ri = {
+		.rr		= rr,
+	};
+	struct xfs_scrub	*sc = rr->sc;
+	int			error;
+
+	xagb_bitmap_init(&ri.inobt_blocks);
+	xagb_bitmap_init(&ri.ichunk_blocks);
+
+	/*
+	 * Iterate every record in the inobt so we can capture all the inode
+	 * chunks and the blocks in the inobt itself.
+	 */
+	error = xfs_btree_query_all(sc->sa.ino_cur, xrep_rmap_walk_inobt, &ri);
+	if (error)
+		goto out_bitmap;
+
+	/*
+	 * Note that if there are zero records in the inobt then query_all does
+	 * nothing and we have to account the empty inobt root manually.
+	 */
+	if (xagb_bitmap_empty(&ri.ichunk_blocks)) {
+		struct xfs_agi	*agi = sc->sa.agi_bp->b_addr;
+
+		error = xagb_bitmap_set(&ri.inobt_blocks,
+				be32_to_cpu(agi->agi_root), 1);
+		if (error)
+			goto out_bitmap;
+	}
+
+	/* Scan the finobt too. */
+	if (xfs_has_finobt(sc->mp)) {
+		error = xagb_bitmap_set_btblocks(&ri.inobt_blocks,
+				sc->sa.fino_cur);
+		if (error)
+			goto out_bitmap;
+	}
+
+	/* Generate rmaps for everything. */
+	error = xrep_rmap_stash_bitmap(rr, &ri.inobt_blocks,
+			&XFS_RMAP_OINFO_INOBT);
+	if (error)
+		goto out_bitmap;
+	error = xrep_rmap_stash_bitmap(rr, &ri.ichunk_blocks,
+			&XFS_RMAP_OINFO_INODES);
+
+out_bitmap:
+	xagb_bitmap_destroy(&ri.inobt_blocks);
+	xagb_bitmap_destroy(&ri.ichunk_blocks);
+	return error;
+}
+
+/* Record a CoW staging extent. */
+STATIC int
+xrep_rmap_walk_cowblocks(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_refcount_irec	*irec,
+	void				*priv)
+{
+	struct xagb_bitmap		*bitmap = priv;
+
+	if (!xfs_refcount_check_domain(irec) ||
+	    irec->rc_domain != XFS_REFC_DOMAIN_COW)
+		return -EFSCORRUPTED;
+
+	return xagb_bitmap_set(bitmap, irec->rc_startblock, irec->rc_blockcount);
+}
+
+/*
+ * Collect rmaps for the blocks containing the refcount btree, and all CoW
+ * staging extents.
+ */
+STATIC int
+xrep_rmap_find_refcount_rmaps(
+	struct xrep_rmap	*rr)
+{
+	struct xagb_bitmap	refcountbt_blocks;	/* REFCBIT */
+	struct xagb_bitmap	cow_blocks;		/* COWBIT */
+	struct xfs_refcount_irec low = {
+		.rc_startblock	= 0,
+		.rc_domain	= XFS_REFC_DOMAIN_COW,
+	};
+	struct xfs_refcount_irec high = {
+		.rc_startblock	= -1U,
+		.rc_domain	= XFS_REFC_DOMAIN_COW,
+	};
+	struct xfs_scrub	*sc = rr->sc;
+	int			error;
+
+	if (!xfs_has_reflink(sc->mp))
+		return 0;
+
+	xagb_bitmap_init(&refcountbt_blocks);
+	xagb_bitmap_init(&cow_blocks);
+
+	/* refcountbt */
+	error = xagb_bitmap_set_btblocks(&refcountbt_blocks, sc->sa.refc_cur);
+	if (error)
+		goto out_bitmap;
+
+	/* Collect rmaps for CoW staging extents. */
+	error = xfs_refcount_query_range(sc->sa.refc_cur, &low, &high,
+			xrep_rmap_walk_cowblocks, &cow_blocks);
+	if (error)
+		goto out_bitmap;
+
+	/* Generate rmaps for everything. */
+	error = xrep_rmap_stash_bitmap(rr, &cow_blocks, &XFS_RMAP_OINFO_COW);
+	if (error)
+		goto out_bitmap;
+	error = xrep_rmap_stash_bitmap(rr, &refcountbt_blocks,
+			&XFS_RMAP_OINFO_REFC);
+
+out_bitmap:
+	xagb_bitmap_destroy(&cow_blocks);
+	xagb_bitmap_destroy(&refcountbt_blocks);
+	return error;
+}
+
+/* Generate rmaps for the AG headers (AGI/AGF/AGFL) */
+STATIC int
+xrep_rmap_find_agheader_rmaps(
+	struct xrep_rmap	*rr)
+{
+	struct xfs_scrub	*sc = rr->sc;
+
+	/* Create a record for the AG sb->agfl. */
+	return xrep_rmap_stash(rr, XFS_SB_BLOCK(sc->mp),
+			XFS_AGFL_BLOCK(sc->mp) - XFS_SB_BLOCK(sc->mp) + 1,
+			XFS_RMAP_OWN_FS, 0, 0);
+}
+
+/* Generate rmaps for the log, if it's in this AG. */
+STATIC int
+xrep_rmap_find_log_rmaps(
+	struct xrep_rmap	*rr)
+{
+	struct xfs_scrub	*sc = rr->sc;
+
+	if (!xfs_ag_contains_log(sc->mp, sc->sa.pag->pag_agno))
+		return 0;
+
+	return xrep_rmap_stash(rr,
+			XFS_FSB_TO_AGBNO(sc->mp, sc->mp->m_sb.sb_logstart),
+			sc->mp->m_sb.sb_logblocks, XFS_RMAP_OWN_LOG, 0, 0);
+}
+
+/*
+ * Generate all the reverse-mappings for this AG, a list of the old rmapbt
+ * blocks, and the new btreeblks count.  Figure out if we have enough free
+ * space to reconstruct the inode btrees.  The caller must clean up the lists
+ * if anything goes wrong.  This implements section (I) above.
+ */
+STATIC int
+xrep_rmap_find_rmaps(
+	struct xrep_rmap	*rr)
+{
+	struct xfs_scrub	*sc = rr->sc;
+	struct xchk_ag		*sa = &sc->sa;
+	struct xfs_inode	*ip;
+	int			error;
+
+	/* Find all the per-AG metadata. */
+	xrep_ag_btcur_init(sc, &sc->sa);
+
+	error = xrep_rmap_find_inode_rmaps(rr);
+	if (error)
+		goto end_agscan;
+
+	error = xrep_rmap_find_refcount_rmaps(rr);
+	if (error)
+		goto end_agscan;
+
+	error = xrep_rmap_find_agheader_rmaps(rr);
+	if (error)
+		goto end_agscan;
+
+	error = xrep_rmap_find_log_rmaps(rr);
+end_agscan:
+	xchk_ag_btcur_free(&sc->sa);
+	if (error)
+		return error;
+
+	/*
+	 * Set up for a potentially lengthy filesystem scan by reducing our
+	 * transaction resource usage for the duration.  Specifically:
+	 *
+	 * Unlock the AG header buffers and cancel the transaction to release
+	 * the log grant space while we scan the filesystem.
+	 *
+	 * Create a new empty transaction to eliminate the possibility of the
+	 * inode scan deadlocking on cyclical metadata.
+	 *
+	 * We pass the empty transaction to the file scanning function to avoid
+	 * repeatedly cycling empty transactions.  This can be done even though
+	 * we take the IOLOCK to quiesce the file because empty transactions
+	 * do not take sb_internal.
+	 */
+	sa->agf_bp = NULL;
+	sa->agi_bp = NULL;
+	xchk_trans_cancel(sc);
+	error = xchk_trans_alloc_empty(sc);
+	if (error)
+		return error;
+
+	/* Iterate all AGs for inodes rmaps. */
+	while ((error = xchk_iscan_iter(&rr->iscan, &ip)) == 1) {
+		error = xrep_rmap_scan_inode(rr, ip);
+		xchk_irele(sc, ip);
+		if (error)
+			break;
+
+		if (xchk_should_terminate(sc, &error))
+			break;
+	}
+	xchk_iscan_iter_finish(&rr->iscan);
+	if (error)
+		return error;
+
+	/*
+	 * Switch out for a real transaction and lock the AG headers in
+	 * preparation for building a new tree.
+	 */
+	xchk_trans_cancel(sc);
+	error = xchk_setup_fs(sc);
+	if (error)
+		return error;
+	return xchk_perag_drain_and_lock(sc);
+}
+
+/* Section (II): Reserving space for new rmapbt and setting free space bitmap */
+
+struct xrep_rmap_agfl {
+	struct xagb_bitmap	*bitmap;
+	xfs_agnumber_t		agno;
+};
+
+/* Add an AGFL block to the rmap list. */
+STATIC int
+xrep_rmap_walk_agfl(
+	struct xfs_mount	*mp,
+	xfs_agblock_t		agbno,
+	void			*priv)
+{
+	struct xrep_rmap_agfl	*ra = priv;
+
+	return xagb_bitmap_set(ra->bitmap, agbno, 1);
+}
+
+/*
+ * Run one round of reserving space for the new rmapbt and recomputing the
+ * number of blocks needed to store the previously observed rmapbt records and
+ * the ones we'll create for the free space metadata.  When we don't need more
+ * blocks, return a bitmap of OWN_AG extents in @freesp_blocks and set @done to
+ * true.
+ */
+STATIC int
+xrep_rmap_try_reserve(
+	struct xrep_rmap	*rr,
+	struct xfs_btree_cur	*rmap_cur,
+	uint64_t		nr_records,
+	struct xagb_bitmap	*freesp_blocks,
+	uint64_t		*blocks_reserved,
+	bool			*done)
+{
+	struct xrep_rmap_agfl	ra = {
+		.bitmap		= freesp_blocks,
+		.agno		= rr->sc->sa.pag->pag_agno,
+	};
+	struct xfs_scrub	*sc = rr->sc;
+	struct xrep_newbt_resv	*resv, *n;
+	struct xfs_agf		*agf = sc->sa.agf_bp->b_addr;
+	struct xfs_buf		*agfl_bp;
+	uint64_t		nr_blocks;	/* RMB */
+	uint64_t		freesp_records;
+	int			error;
+
+	/*
+	 * We're going to recompute new_btree.bload.nr_blocks at the end of
+	 * this function to reflect however many btree blocks we need to store
+	 * all the rmap records (including the ones that reflect the changes we
+	 * made to support the new rmapbt blocks), so we save the old value
+	 * here so we can decide if we've reserved enough blocks.
+	 */
+	nr_blocks = rr->new_btree.bload.nr_blocks;
+
+	/*
+	 * Make sure we've reserved enough space for the new btree.  This can
+	 * change the shape of the free space btrees, which can cause secondary
+	 * interactions with the rmap records because all three space btrees
+	 * have the same rmap owner.  We'll account for all that below.
+	 */
+	error = xrep_newbt_alloc_blocks(&rr->new_btree,
+			nr_blocks - *blocks_reserved);
+	if (error)
+		return error;
+
+	*blocks_reserved = rr->new_btree.bload.nr_blocks;
+
+	/* Clear everything in the bitmap. */
+	xagb_bitmap_destroy(freesp_blocks);
+
+	/* Set all the bnobt blocks in the bitmap. */
+	sc->sa.bno_cur = xfs_allocbt_init_cursor(sc->mp, sc->tp, sc->sa.agf_bp,
+			sc->sa.pag, XFS_BTNUM_BNO);
+	error = xagb_bitmap_set_btblocks(freesp_blocks, sc->sa.bno_cur);
+	xfs_btree_del_cursor(sc->sa.bno_cur, error);
+	sc->sa.bno_cur = NULL;
+	if (error)
+		return error;
+
+	/* Set all the cntbt blocks in the bitmap. */
+	sc->sa.cnt_cur = xfs_allocbt_init_cursor(sc->mp, sc->tp, sc->sa.agf_bp,
+			sc->sa.pag, XFS_BTNUM_CNT);
+	error = xagb_bitmap_set_btblocks(freesp_blocks, sc->sa.cnt_cur);
+	xfs_btree_del_cursor(sc->sa.cnt_cur, error);
+	sc->sa.cnt_cur = NULL;
+	if (error)
+		return error;
+
+	/* Record our new btreeblks value. */
+	rr->freesp_btblocks = xagb_bitmap_hweight(freesp_blocks) - 2;
+
+	/* Set all the new rmapbt blocks in the bitmap. */
+	list_for_each_entry_safe(resv, n, &rr->new_btree.resv_list, list) {
+		error = xagb_bitmap_set(freesp_blocks, resv->agbno, resv->len);
+		if (error)
+			return error;
+	}
+
+	/* Set all the AGFL blocks in the bitmap. */
+	error = xfs_alloc_read_agfl(sc->sa.pag, sc->tp, &agfl_bp);
+	if (error)
+		return error;
+
+	error = xfs_agfl_walk(sc->mp, agf, agfl_bp, xrep_rmap_walk_agfl, &ra);
+	if (error)
+		return error;
+
+	/* Count the extents in the bitmap. */
+	freesp_records = xagb_bitmap_count_set_regions(freesp_blocks);
+
+	/* Compute how many blocks we'll need for all the rmaps. */
+	error = xfs_btree_bload_compute_geometry(rmap_cur,
+			&rr->new_btree.bload, nr_records + freesp_records);
+	if (error)
+		return error;
+
+	/* We're done when we don't need more blocks. */
+	*done = nr_blocks >= rr->new_btree.bload.nr_blocks;
+	return 0;
+}
+
+/*
+ * Iteratively reserve space for rmap btree while recording OWN_AG rmaps for
+ * the free space metadata.  This implements section (II) above.
+ */
+STATIC int
+xrep_rmap_reserve_space(
+	struct xrep_rmap	*rr,
+	struct xfs_btree_cur	*rmap_cur)
+{
+	struct xagb_bitmap	freesp_blocks;	/* AGBIT */
+	uint64_t		nr_records;	/* NR */
+	uint64_t		blocks_reserved = 0;
+	bool			done = false;
+	int			error;
+
+	nr_records = xfarray_length(rr->rmap_records);
+
+	/* Compute how many blocks we'll need for the rmaps collected so far. */
+	error = xfs_btree_bload_compute_geometry(rmap_cur,
+			&rr->new_btree.bload, nr_records);
+	if (error)
+		return error;
+
+	/* Last chance to abort before we start committing fixes. */
+	if (xchk_should_terminate(rr->sc, &error))
+		return error;
+
+	xagb_bitmap_init(&freesp_blocks);
+
+	/*
+	 * Iteratively reserve space for the new rmapbt and recompute the
+	 * number of blocks needed to store the previously observed rmapbt
+	 * records and the ones we'll create for the free space metadata.
+	 * Finish when we don't need more blocks.
+	 */
+	do {
+		error = xrep_rmap_try_reserve(rr, rmap_cur, nr_records,
+				&freesp_blocks, &blocks_reserved, &done);
+		if (error)
+			goto out_bitmap;
+	} while (!done);
+
+	/* Emit rmaps for everything in the free space bitmap. */
+	xrep_ag_btcur_init(rr->sc, &rr->sc->sa);
+	error = xrep_rmap_stash_bitmap(rr, &freesp_blocks, &XFS_RMAP_OINFO_AG);
+	xchk_ag_btcur_free(&rr->sc->sa);
+
+out_bitmap:
+	xagb_bitmap_destroy(&freesp_blocks);
+	return error;
+}
+
+/* Section (III): Building the new rmap btree. */
+
+/* Update the AGF counters. */
+STATIC int
+xrep_rmap_reset_counters(
+	struct xrep_rmap	*rr)
+{
+	struct xfs_scrub	*sc = rr->sc;
+	struct xfs_perag	*pag = sc->sa.pag;
+	struct xfs_agf		*agf = sc->sa.agf_bp->b_addr;
+	xfs_agblock_t		rmap_btblocks;
+
+	/*
+	 * The AGF header contains extra information related to the reverse
+	 * mapping btree, so we must update those fields here.
+	 */
+	rmap_btblocks = rr->new_btree.afake.af_blocks - 1;
+	agf->agf_btreeblks = cpu_to_be32(rr->freesp_btblocks + rmap_btblocks);
+	xfs_alloc_log_agf(sc->tp, sc->sa.agf_bp, XFS_AGF_BTREEBLKS);
+
+	/*
+	 * After we commit the new btree to disk, it is possible that the
+	 * process to reap the old btree blocks will race with the AIL trying
+	 * to checkpoint the old btree blocks into the filesystem.  If the new
+	 * tree is shorter than the old one, the rmapbt write verifier will
+	 * fail and the AIL will shut down the filesystem.
+	 *
+	 * To avoid this, save the old incore btree height values as the alt
+	 * height values before re-initializing the perag info from the updated
+	 * AGF to capture all the new values.
+	 */
+	pag->pagf_repair_levels[XFS_BTNUM_RMAPi] =
+					pag->pagf_levels[XFS_BTNUM_RMAPi];
+
+	/* Reinitialize with the values we just logged. */
+	return xrep_reinit_pagf(sc);
+}
+
+/* Retrieve rmapbt data for bulk load. */
+STATIC int
+xrep_rmap_get_records(
+	struct xfs_btree_cur	*cur,
+	unsigned int		idx,
+	struct xfs_btree_block	*block,
+	unsigned int		nr_wanted,
+	void			*priv)
+{
+	struct xrep_rmap_extent	rec;
+	struct xfs_rmap_irec	*irec = &cur->bc_rec.r;
+	struct xrep_rmap	*rr = priv;
+	union xfs_btree_rec	*block_rec;
+	unsigned int		loaded;
+	int			error;
+
+	for (loaded = 0; loaded < nr_wanted; loaded++, idx++) {
+		error = xfarray_load_next(rr->rmap_records, &rr->array_cur,
+				&rec);
+		if (error)
+			return error;
+
+		irec->rm_startblock = rec.startblock;
+		irec->rm_blockcount = rec.blockcount;
+		irec->rm_owner = rec.owner;
+		if (xfs_rmap_irec_offset_unpack(rec.offset, irec) != NULL)
+			return -EFSCORRUPTED;
+
+		error = xrep_rmap_check_mapping(rr->sc, irec);
+		if (error)
+			return error;
+
+		block_rec = xfs_btree_rec_addr(cur, idx, block);
+		cur->bc_ops->init_rec_from_cur(cur, block_rec);
+	}
+
+	return loaded;
+}
+
+/* Feed one of the new btree blocks to the bulk loader. */
+STATIC int
+xrep_rmap_claim_block(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*ptr,
+	void			*priv)
+{
+	struct xrep_rmap        *rr = priv;
+
+	return xrep_newbt_claim_block(cur, &rr->new_btree, ptr);
+}
+
+/* Custom allocation function for new rmap btrees. */
+STATIC int
+xrep_rmap_alloc_vextent(
+	struct xfs_scrub	*sc,
+	struct xfs_alloc_arg	*args,
+	xfs_fsblock_t		alloc_hint)
+{
+	int			error;
+
+	/*
+	 * We don't want an rmap update on the allocation, since we iteratively
+	 * compute the OWN_AG records /after/ allocating blocks for the records
+	 * that we already know we need to store.  Therefore, fix the freelist
+	 * with the NORMAP flag set so that we don't also try to create an rmap
+	 * for new AGFL blocks.
+	 */
+	error = xrep_fix_freelist(sc, XFS_ALLOC_FLAG_NORMAP);
+	if (error)
+		return error;
+
+	/*
+	 * If xrep_fix_freelist fixed the freelist by moving blocks from the
+	 * free space btrees or by removing blocks from the AGFL and queueing
+	 * an EFI to free the block, the transaction will be dirty.  This
+	 * second case is of interest to us.
+	 *
+	 * Later on, we will need to compare gaps in the new recordset against
+	 * the block usage of all OWN_AG owners in order to free the old
+	 * btree's blocks, which means that we can't have EFIs for former AGFL
+	 * blocks attached to the repair transaction when we commit the new
+	 * btree.
+	 *
+	 * xrep_newbt_alloc_blocks guarantees this for us by calling
+	 * xrep_defer_finish to commit anything that fix_freelist may have
+	 * added to the transaction.
+	 */
+	return xfs_alloc_vextent_near_bno(args, alloc_hint);
+}
+
+/*
+ * Use the collected rmap information to stage a new rmap btree.  If this is
+ * successful we'll return with the new btree root information logged to the
+ * repair transaction but not yet committed.  This implements section (III)
+ * above.
+ */
+STATIC int
+xrep_rmap_build_new_tree(
+	struct xrep_rmap	*rr)
+{
+	struct xfs_scrub	*sc = rr->sc;
+	struct xfs_perag	*pag = sc->sa.pag;
+	struct xfs_agf		*agf = sc->sa.agf_bp->b_addr;
+	struct xfs_btree_cur	*rmap_cur;
+	xfs_fsblock_t		fsbno;
+	int			error;
+
+	/*
+	 * Preserve the old rmapbt block count so that we can adjust the
+	 * per-AG rmapbt reservation after we commit the new btree root and
+	 * want to dispose of the old btree blocks.
+	 */
+	rr->old_rmapbt_fsbcount = be32_to_cpu(agf->agf_rmap_blocks);
+
+	/*
+	 * Prepare to construct the new btree by reserving disk space for the
+	 * new btree and setting up all the accounting information we'll need
+	 * to root the new btree while it's under construction and before we
+	 * attach it to the AG header.  The new blocks are accounted to the
+	 * rmapbt per-AG reservation, which we will adjust further after
+	 * committing the new btree.
+	 */
+	fsbno = XFS_AGB_TO_FSB(sc->mp, pag->pag_agno, XFS_RMAP_BLOCK(sc->mp));
+	xrep_newbt_init_ag(&rr->new_btree, sc, &XFS_RMAP_OINFO_SKIP_UPDATE,
+			fsbno, XFS_AG_RESV_RMAPBT);
+	rr->new_btree.bload.get_records = xrep_rmap_get_records;
+	rr->new_btree.bload.claim_block = xrep_rmap_claim_block;
+	rr->new_btree.alloc_vextent = xrep_rmap_alloc_vextent;
+	rmap_cur = xfs_rmapbt_stage_cursor(sc->mp, &rr->new_btree.afake, pag);
+
+	/*
+	 * Initialize @rr->new_btree, reserve space for the new rmapbt,
+	 * and compute OWN_AG rmaps.
+	 */
+	error = xrep_rmap_reserve_space(rr, rmap_cur);
+	if (error)
+		goto err_cur;
+
+	/*
+	 * Due to btree slack factors, it's possible for a new btree to be one
+	 * level taller than the old btree.  Update the incore btree height so
+	 * that we don't trip the verifiers when writing the new btree blocks
+	 * to disk.
+	 */
+	pag->pagf_repair_levels[XFS_BTNUM_RMAPi] =
+					rr->new_btree.bload.btree_height;
+
+	/* Add all observed rmap records. */
+	rr->array_cur = XFARRAY_CURSOR_INIT;
+	sc->sa.bno_cur = xfs_allocbt_init_cursor(sc->mp, sc->tp, sc->sa.agf_bp,
+			sc->sa.pag, XFS_BTNUM_BNO);
+	error = xfs_btree_bload(rmap_cur, &rr->new_btree.bload, rr);
+	xfs_btree_del_cursor(sc->sa.bno_cur, error);
+	sc->sa.bno_cur = NULL;
+	if (error)
+		goto err_level;
+
+	/*
+	 * Install the new btree in the AG header.  After this point the old
+	 * btree is no longer accessible and the new tree is live.
+	 */
+	xfs_rmapbt_commit_staged_btree(rmap_cur, sc->tp, sc->sa.agf_bp);
+	xfs_btree_del_cursor(rmap_cur, 0);
+
+	/*
+	 * The newly committed rmap recordset includes mappings for the blocks
+	 * that we reserved to build the new btree.  If there is excess space
+	 * reservation to be freed, the corresponding rmap records must also be
+	 * removed.
+	 */
+	rr->new_btree.oinfo = XFS_RMAP_OINFO_AG;
+
+	/* Reset the AGF counters now that we've changed the btree shape. */
+	error = xrep_rmap_reset_counters(rr);
+	if (error)
+		goto err_newbt;
+
+	/* Dispose of any unused blocks and the accounting information. */
+	error = xrep_newbt_commit(&rr->new_btree);
+	if (error)
+		return error;
+
+	return xrep_roll_ag_trans(sc);
+
+err_level:
+	pag->pagf_repair_levels[XFS_BTNUM_RMAPi] = 0;
+err_cur:
+	xfs_btree_del_cursor(rmap_cur, error);
+err_newbt:
+	xrep_newbt_cancel(&rr->new_btree);
+	return error;
+}
+
+/* Section (IV): Reaping the old btree. */
+
+struct xrep_rmap_find_gaps {
+	struct xagb_bitmap	rmap_gaps;
+	xfs_agblock_t		next_agbno;
+};
+
+/* Subtract each free extent in the bnobt from the rmap gaps. */
+STATIC int
+xrep_rmap_find_freesp(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_alloc_rec_incore *rec,
+	void				*priv)
+{
+	struct xrep_rmap_find_gaps	*rfg = priv;
+
+	return xagb_bitmap_clear(&rfg->rmap_gaps, rec->ar_startblock,
+			rec->ar_blockcount);
+}
+
+/*
+ * Reap the old rmapbt blocks.  Now that the rmapbt is fully rebuilt, we make
+ * a list of gaps in the rmap records and a list of the extents mentioned in
+ * the bnobt.  Any block that's in the new rmapbt gap list but not mentioned
+ * in the bnobt is a block from the old rmapbt and can be removed.
+ */
+STATIC int
+xrep_rmap_remove_old_tree(
+	struct xrep_rmap	*rr)
+{
+	struct xrep_rmap_find_gaps rfg = {
+		.next_agbno	= 0,
+	};
+	struct xfs_scrub	*sc = rr->sc;
+	struct xfs_agf		*agf = sc->sa.agf_bp->b_addr;
+	struct xfs_perag	*pag = sc->sa.pag;
+	xfs_agblock_t		agend;
+	xfarray_idx_t		array_cur;
+	int			error;
+
+	xagb_bitmap_init(&rfg.rmap_gaps);
+
+	/* Compute free space from the new rmapbt. */
+	foreach_xfarray_idx(rr->rmap_records, array_cur) {
+		struct xrep_rmap_extent	rec;
+
+		error = xfarray_load(rr->rmap_records, array_cur, &rec);
+		if (error)
+			goto out_bitmap;
+
+		/* Record the free space we find. */
+		if (rec.startblock > rfg.next_agbno) {
+			error = xagb_bitmap_set(&rfg.rmap_gaps, rfg.next_agbno,
+					rec.startblock - rfg.next_agbno);
+			if (error)
+				goto out_bitmap;
+		}
+		rfg.next_agbno = max_t(xfs_agblock_t, rfg.next_agbno,
+					rec.startblock + rec.blockcount);
+	}
+
+	/* Insert a record for space between the last rmap and EOAG. */
+	agend = be32_to_cpu(agf->agf_length);
+	if (rfg.next_agbno < agend) {
+		error = xagb_bitmap_set(&rfg.rmap_gaps, rfg.next_agbno,
+				agend - rfg.next_agbno);
+		if (error)
+			goto out_bitmap;
+	}
+
+	/* Compute free space from the existing bnobt. */
+	sc->sa.bno_cur = xfs_allocbt_init_cursor(sc->mp, sc->tp, sc->sa.agf_bp,
+			sc->sa.pag, XFS_BTNUM_BNO);
+	error = xfs_alloc_query_all(sc->sa.bno_cur, xrep_rmap_find_freesp,
+			&rfg);
+	xfs_btree_del_cursor(sc->sa.bno_cur, error);
+	sc->sa.bno_cur = NULL;
+	if (error)
+		goto out_bitmap;
+
+	/*
+	 * Free the "free" blocks that the new rmapbt knows about but the bnobt
+	 * doesn't--these are the old rmapbt blocks.  Credit the old rmapbt
+	 * block usage count back to the per-AG rmapbt reservation (and not
+	 * fdblocks, since the rmap btree lives in free space) to keep the
+	 * reservation and free space accounting correct.
+	 */
+	error = xrep_reap_agblocks(sc, &rfg.rmap_gaps,
+			&XFS_RMAP_OINFO_ANY_OWNER, XFS_AG_RESV_RMAPBT);
+	if (error)
+		goto out_bitmap;
+
+	/*
+	 * Now that we've zapped all the old rmapbt blocks we can turn off
+	 * the alternate height mechanism and reset the per-AG space
+	 * reservation.
+	 */
+	pag->pagf_repair_levels[XFS_BTNUM_RMAPi] = 0;
+	sc->flags |= XREP_RESET_PERAG_RESV;
+out_bitmap:
+	xagb_bitmap_destroy(&rfg.rmap_gaps);
+	return error;
+}
+
+/* Set up the filesystem scan components. */
+STATIC int
+xrep_rmap_setup_scan(
+	struct xrep_rmap	*rr)
+{
+	struct xfs_scrub	*sc = rr->sc;
+	char			*descr;
+	int			error;
+
+	/* Set up some storage */
+	descr = xchk_xfile_ag_descr(sc, "reverse mapping records");
+	error = xfarray_create(descr, 0, sizeof(struct xrep_rmap_extent),
+			&rr->rmap_records);
+	kfree(descr);
+	if (error)
+		return error;
+
+	/* Retry iget every tenth of a second for up to 30 seconds. */
+	xchk_iscan_start(sc, 30000, 100, &rr->iscan);
+	return 0;
+}
+
+/* Tear down scan components. */
+STATIC void
+xrep_rmap_teardown(
+	struct xrep_rmap	*rr)
+{
+	xchk_iscan_teardown(&rr->iscan);
+	xfarray_destroy(rr->rmap_records);
+}
+
+/* Repair the rmap btree for some AG. */
+int
+xrep_rmapbt(
+	struct xfs_scrub	*sc)
+{
+	struct xrep_rmap	*rr = sc->buf;
+	int			error;
+
+	/* Functionality is not yet complete. */
+	return xrep_notsupported(sc);
+
+	error = xrep_rmap_setup_scan(rr);
+	if (error)
+		return error;
+
+	/*
+	 * Collect rmaps for everything in this AG that isn't space metadata.
+	 * These rmaps won't change even as we try to allocate blocks.
+	 */
+	error = xrep_rmap_find_rmaps(rr);
+	if (error)
+		goto out_records;
+
+	/* Rebuild the rmap information. */
+	error = xrep_rmap_build_new_tree(rr);
+	if (error)
+		goto out_records;
+
+	/* Kill the old tree. */
+	error = xrep_rmap_remove_old_tree(rr);
+	if (error)
+		goto out_records;
+
+out_records:
+	xrep_rmap_teardown(rr);
+	return error;
+}
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 4a6853accdf12..a37476a2a956b 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -278,7 +278,7 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.setup	= xchk_setup_ag_rmapbt,
 		.scrub	= xchk_rmapbt,
 		.has	= xfs_has_rmapbt,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_rmapbt,
 	},
 	[XFS_SCRUB_TYPE_REFCNTBT] = {	/* refcountbt */
 		.type	= ST_PERAG,
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index acea536e09c38..82ab945c5479b 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -1580,7 +1580,6 @@ DEFINE_EVENT(xrep_rmap_class, name, \
 		 uint64_t owner, uint64_t offset, unsigned int flags), \
 	TP_ARGS(mp, agno, agbno, len, owner, offset, flags))
 DEFINE_REPAIR_RMAP_EVENT(xrep_ibt_walk_rmap);
-DEFINE_REPAIR_RMAP_EVENT(xrep_rmap_extent_fn);
 DEFINE_REPAIR_RMAP_EVENT(xrep_bmap_walk_rmap);
 
 TRACE_EVENT(xrep_abt_found,
@@ -1698,6 +1697,38 @@ TRACE_EVENT(xrep_bmap_found,
 		  __entry->state)
 );
 
+TRACE_EVENT(xrep_rmap_found,
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+		 const struct xfs_rmap_irec *rec),
+	TP_ARGS(mp, agno, rec),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agblock_t, agbno)
+		__field(xfs_extlen_t, len)
+		__field(uint64_t, owner)
+		__field(uint64_t, offset)
+		__field(unsigned int, flags)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->agno = agno;
+		__entry->agbno = rec->rm_startblock;
+		__entry->len = rec->rm_blockcount;
+		__entry->owner = rec->rm_owner;
+		__entry->offset = rec->rm_offset;
+		__entry->flags = rec->rm_flags;
+	),
+	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->agbno,
+		  __entry->len,
+		  __entry->owner,
+		  __entry->offset,
+		  __entry->flags)
+);
+
 TRACE_EVENT(xrep_findroot_block,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,
 		 uint32_t magic, uint16_t level),

[PATCH 3/4] xfs: create a shadow rmap btree during rmap repair

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create an in-memory btree of rmap records instead of an array.  This
enables us to do live record collection instead of freezing the fs.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_rmap.c       |   37 ++++--
 fs/xfs/libxfs/xfs_rmap_btree.c |  123 +++++++++++++++++++
 fs/xfs/libxfs/xfs_rmap_btree.h |    9 +
 fs/xfs/scrub/repair.c          |   18 +++
 fs/xfs/scrub/repair.h          |    2 
 fs/xfs/scrub/rmap_repair.c     |  258 +++++++++++++++++++++++++++++-----------
 6 files changed, 365 insertions(+), 82 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 4e105207fc7ed..23bc79c96db76 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -269,6 +269,16 @@ xfs_rmap_check_irec(
 	return NULL;
 }
 
+static inline xfs_failaddr_t
+xfs_rmap_check_btrec(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*irec)
+{
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		return xfs_rmap_check_irec(cur->bc_mem.pag, irec);
+	return xfs_rmap_check_irec(cur->bc_ag.pag, irec);
+}
+
 static inline int
 xfs_rmap_complain_bad_rec(
 	struct xfs_btree_cur		*cur,
@@ -277,9 +287,13 @@ xfs_rmap_complain_bad_rec(
 {
 	struct xfs_mount		*mp = cur->bc_mp;
 
-	xfs_warn(mp,
-		"Reverse Mapping BTree record corruption in AG %d detected at %pS!",
-		cur->bc_ag.pag->pag_agno, fa);
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		xfs_warn(mp,
+ "In-Memory Reverse Mapping BTree record corruption detected at %pS!", fa);
+	else
+		xfs_warn(mp,
+ "Reverse Mapping BTree record corruption in AG %d detected at %pS!",
+			cur->bc_ag.pag->pag_agno, fa);
 	xfs_warn(mp,
 		"Owner 0x%llx, flags 0x%x, start block 0x%x block count 0x%x",
 		irec->rm_owner, irec->rm_flags, irec->rm_startblock,
@@ -307,7 +321,7 @@ xfs_rmap_get_rec(
 
 	fa = xfs_rmap_btrec_to_irec(rec, irec);
 	if (!fa)
-		fa = xfs_rmap_check_irec(cur->bc_ag.pag, irec);
+		fa = xfs_rmap_check_btrec(cur, irec);
 	if (fa)
 		return xfs_rmap_complain_bad_rec(cur, fa, irec);
 
@@ -2404,15 +2418,12 @@ xfs_rmap_map_raw(
 {
 	struct xfs_owner_info	oinfo;
 
-	oinfo.oi_owner = rmap->rm_owner;
-	oinfo.oi_offset = rmap->rm_offset;
-	oinfo.oi_flags = 0;
-	if (rmap->rm_flags & XFS_RMAP_ATTR_FORK)
-		oinfo.oi_flags |= XFS_OWNER_INFO_ATTR_FORK;
-	if (rmap->rm_flags & XFS_RMAP_BMBT_BLOCK)
-		oinfo.oi_flags |= XFS_OWNER_INFO_BMBT_BLOCK;
+	xfs_owner_info_pack(&oinfo, rmap->rm_owner, rmap->rm_offset,
+			rmap->rm_flags);
 
-	if (rmap->rm_flags || XFS_RMAP_NON_INODE_OWNER(rmap->rm_owner))
+	if ((rmap->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK |
+			       XFS_RMAP_UNWRITTEN)) ||
+	    XFS_RMAP_NON_INODE_OWNER(rmap->rm_owner))
 		return xfs_rmap_map(cur, rmap->rm_startblock,
 				rmap->rm_blockcount,
 				rmap->rm_flags & XFS_RMAP_UNWRITTEN,
@@ -2442,7 +2453,7 @@ xfs_rmap_query_range_helper(
 
 	fa = xfs_rmap_btrec_to_irec(rec, &irec);
 	if (!fa)
-		fa = xfs_rmap_check_irec(cur->bc_ag.pag, &irec);
+		fa = xfs_rmap_check_btrec(cur, &irec);
 	if (fa)
 		return xfs_rmap_complain_bad_rec(cur, fa, &irec);
 
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index 6d9c6d078bf15..e29ae6d0f79d4 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -21,6 +21,9 @@
 #include "xfs_extent_busy.h"
 #include "xfs_ag.h"
 #include "xfs_ag_resv.h"
+#include "scrub/xfile.h"
+#include "scrub/xfbtree.h"
+#include "xfs_btree_mem.h"
 
 static struct kmem_cache	*xfs_rmapbt_cur_cache;
 
@@ -555,6 +558,126 @@ xfs_rmapbt_stage_cursor(
 	return cur;
 }
 
+#ifdef CONFIG_XFS_BTREE_IN_XFILE
+/*
+ * Validate an in-memory rmap btree block.  Callers are allowed to generate an
+ * in-memory btree even if the ondisk feature is not enabled.
+ */
+static xfs_failaddr_t
+xfs_rmapbt_mem_verify(
+	struct xfs_buf		*bp)
+{
+	struct xfs_mount	*mp = bp->b_mount;
+	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
+	xfs_failaddr_t		fa;
+	unsigned int		level;
+
+	if (!xfs_verify_magic(bp, block->bb_magic))
+		return __this_address;
+
+	fa = xfs_btree_sblock_v5hdr_verify(bp);
+	if (fa)
+		return fa;
+
+	level = be16_to_cpu(block->bb_level);
+	if (xfs_has_rmapbt(mp)) {
+		if (level >= mp->m_rmap_maxlevels)
+			return __this_address;
+	} else {
+		if (level >= xfs_rmapbt_maxlevels_ondisk())
+			return __this_address;
+	}
+
+	return xfbtree_sblock_verify(bp,
+			xfs_rmapbt_maxrecs(xfo_to_b(1), level == 0));
+}
+
+static void
+xfs_rmapbt_mem_rw_verify(
+	struct xfs_buf	*bp)
+{
+	xfs_failaddr_t	fa = xfs_rmapbt_mem_verify(bp);
+
+	if (fa)
+		xfs_verifier_error(bp, -EFSCORRUPTED, fa);
+}
+
+/* skip crc checks on in-memory btrees to save time */
+static const struct xfs_buf_ops xfs_rmapbt_mem_buf_ops = {
+	.name			= "xfs_rmapbt_mem",
+	.magic			= { 0, cpu_to_be32(XFS_RMAP_CRC_MAGIC) },
+	.verify_read		= xfs_rmapbt_mem_rw_verify,
+	.verify_write		= xfs_rmapbt_mem_rw_verify,
+	.verify_struct		= xfs_rmapbt_mem_verify,
+};
+
+static const struct xfs_btree_ops xfs_rmapbt_mem_ops = {
+	.rec_len		= sizeof(struct xfs_rmap_rec),
+	.key_len		= 2 * sizeof(struct xfs_rmap_key),
+
+	.dup_cursor		= xfbtree_dup_cursor,
+	.set_root		= xfbtree_set_root,
+	.alloc_block		= xfbtree_alloc_block,
+	.free_block		= xfbtree_free_block,
+	.get_minrecs		= xfbtree_get_minrecs,
+	.get_maxrecs		= xfbtree_get_maxrecs,
+	.init_key_from_rec	= xfs_rmapbt_init_key_from_rec,
+	.init_high_key_from_rec	= xfs_rmapbt_init_high_key_from_rec,
+	.init_rec_from_cur	= xfs_rmapbt_init_rec_from_cur,
+	.init_ptr_from_cur	= xfbtree_init_ptr_from_cur,
+	.key_diff		= xfs_rmapbt_key_diff,
+	.buf_ops		= &xfs_rmapbt_mem_buf_ops,
+	.diff_two_keys		= xfs_rmapbt_diff_two_keys,
+	.keys_inorder		= xfs_rmapbt_keys_inorder,
+	.recs_inorder		= xfs_rmapbt_recs_inorder,
+	.keys_contiguous	= xfs_rmapbt_keys_contiguous,
+};
+
+/* Create a cursor for an in-memory btree. */
+struct xfs_btree_cur *
+xfs_rmapbt_mem_cursor(
+	struct xfs_perag	*pag,
+	struct xfs_trans	*tp,
+	struct xfs_buf		*head_bp,
+	struct xfbtree		*xfbtree)
+{
+	struct xfs_btree_cur	*cur;
+	struct xfs_mount	*mp = pag->pag_mount;
+
+	/* Overlapping btree; 2 keys per pointer. */
+	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_RMAP,
+			mp->m_rmap_maxlevels, xfs_rmapbt_cur_cache);
+	cur->bc_flags = XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING |
+			XFS_BTREE_IN_XFILE;
+	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_rmap_2);
+	cur->bc_ops = &xfs_rmapbt_mem_ops;
+	cur->bc_mem.xfbtree = xfbtree;
+	cur->bc_mem.head_bp = head_bp;
+	cur->bc_nlevels = xfs_btree_mem_head_nlevels(head_bp);
+
+	cur->bc_mem.pag = xfs_perag_hold(pag);
+	return cur;
+}
+
+/* Create an in-memory rmap btree. */
+int
+xfs_rmapbt_mem_create(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno,
+	struct xfs_buftarg	*target,
+	struct xfbtree		**xfbtreep)
+{
+	struct xfbtree_config	cfg = {
+		.btree_ops	= &xfs_rmapbt_mem_ops,
+		.target		= target,
+		.btnum		= XFS_BTNUM_RMAP,
+		.owner		= agno,
+	};
+
+	return xfbtree_create(mp, &cfg, xfbtreep);
+}
+#endif /* CONFIG_XFS_BTREE_IN_XFILE */
+
 /*
  * Install a new reverse mapping btree root.  Caller is responsible for
  * invalidating and freeing the old btree blocks.
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.h b/fs/xfs/libxfs/xfs_rmap_btree.h
index 3244715dd111b..5d0454fd05299 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.h
+++ b/fs/xfs/libxfs/xfs_rmap_btree.h
@@ -64,4 +64,13 @@ unsigned int xfs_rmapbt_maxlevels_ondisk(void);
 int __init xfs_rmapbt_init_cur_cache(void);
 void xfs_rmapbt_destroy_cur_cache(void);
 
+#ifdef CONFIG_XFS_BTREE_IN_XFILE
+struct xfbtree;
+struct xfs_btree_cur *xfs_rmapbt_mem_cursor(struct xfs_perag *pag,
+		struct xfs_trans *tp, struct xfs_buf *head_bp,
+		struct xfbtree *xfbtree);
+int xfs_rmapbt_mem_create(struct xfs_mount *mp, xfs_agnumber_t agno,
+		struct xfs_buftarg *target, struct xfbtree **xfbtreep);
+#endif /* CONFIG_XFS_BTREE_IN_XFILE */
+
 #endif /* __XFS_RMAP_BTREE_H__ */
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 5a3ae65ccbc41..4786d56fb7f76 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -31,12 +31,14 @@
 #include "xfs_error.h"
 #include "xfs_reflink.h"
 #include "xfs_health.h"
+#include "xfs_buf_xfile.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
 #include "scrub/repair.h"
 #include "scrub/bitmap.h"
 #include "scrub/stats.h"
+#include "scrub/xfile.h"
 
 /*
  * Attempt to repair some metadata, if the metadata is corrupt and userspace
@@ -1147,3 +1149,19 @@ xrep_metadata_inode_forks(
 
 	return 0;
 }
+
+/*
+ * Set up an xfile and a buffer cache so that we can use the xfbtree.  Buffer
+ * target initialization registers a shrinker, so we cannot be in transaction
+ * context.  Park our resources in the scrub context and let the teardown
+ * function take care of them at the right time.
+ */
+int
+xrep_setup_buftarg(
+	struct xfs_scrub	*sc,
+	const char		*descr)
+{
+	ASSERT(sc->tp == NULL);
+
+	return xfile_alloc_buftarg(sc->mp, descr, &sc->xfile_buftarg);
+}
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index c01e56799bd1d..2139a85cdb83b 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -81,6 +81,8 @@ int xrep_ino_dqattach(struct xfs_scrub *sc);
 # define xrep_ino_dqattach(sc)			(0)
 #endif /* CONFIG_XFS_QUOTA */
 
+int xrep_setup_buftarg(struct xfs_scrub *sc, const char *descr);
+
 int xrep_ino_ensure_extent_count(struct xfs_scrub *sc, int whichfork,
 		xfs_extnum_t nextents);
 int xrep_reset_perag_resv(struct xfs_scrub *sc);
diff --git a/fs/xfs/scrub/rmap_repair.c b/fs/xfs/scrub/rmap_repair.c
index e835ce296af7f..832f221bc4757 100644
--- a/fs/xfs/scrub/rmap_repair.c
+++ b/fs/xfs/scrub/rmap_repair.c
@@ -12,6 +12,7 @@
 #include "xfs_defer.h"
 #include "xfs_btree.h"
 #include "xfs_btree_staging.h"
+#include "xfs_btree_mem.h"
 #include "xfs_bit.h"
 #include "xfs_log_format.h"
 #include "xfs_trans.h"
@@ -42,6 +43,7 @@
 #include "scrub/iscan.h"
 #include "scrub/newbt.h"
 #include "scrub/reap.h"
+#include "scrub/xfbtree.h"
 
 /*
  * Reverse Mapping Btree Repair
@@ -121,33 +123,25 @@
  * We use the 'xrep_rmap' prefix for all the rmap functions.
  */
 
-/*
- * Packed rmap record.  The ATTR/BMBT/UNWRITTEN flags are hidden in the upper
- * bits of offset, just like the on-disk record.
- */
-struct xrep_rmap_extent {
-	xfs_agblock_t	startblock;
-	xfs_extlen_t	blockcount;
-	uint64_t	owner;
-	uint64_t	offset;
-} __packed;
-
 /* Context for collecting rmaps */
 struct xrep_rmap {
 	/* new rmapbt information */
 	struct xrep_newbt	new_btree;
 
 	/* rmap records generated from primary metadata */
-	struct xfarray		*rmap_records;
+	struct xfbtree		*rmap_btree;
 
 	struct xfs_scrub	*sc;
 
-	/* get_records()'s position in the rmap record array. */
-	xfarray_idx_t		array_cur;
+	/* in-memory btree cursor for the xfs_btree_bload iteration */
+	struct xfs_btree_cur	*mcur;
 
 	/* inode scan cursor */
 	struct xchk_iscan	iscan;
 
+	/* Number of non-freespace records found. */
+	unsigned long long	nr_records;
+
 	/* bnobt/cntbt contribution to btreeblks */
 	xfs_agblock_t		freesp_btblocks;
 
@@ -161,6 +155,14 @@ xrep_setup_ag_rmapbt(
 	struct xfs_scrub	*sc)
 {
 	struct xrep_rmap	*rr;
+	char			*descr;
+	int			error;
+
+	descr = xchk_xfile_ag_descr(sc, "reverse mapping records");
+	error = xrep_setup_buftarg(sc, descr);
+	kfree(descr);
+	if (error)
+		return error;
 
 	rr = kzalloc(sizeof(struct xrep_rmap), XCHK_GFP_FLAGS);
 	if (!rr)
@@ -204,11 +206,6 @@ xrep_rmap_stash(
 	uint64_t		offset,
 	unsigned int		flags)
 {
-	struct xrep_rmap_extent	rre = {
-		.startblock	= startblock,
-		.blockcount	= blockcount,
-		.owner		= owner,
-	};
 	struct xfs_rmap_irec	rmap = {
 		.rm_startblock	= startblock,
 		.rm_blockcount	= blockcount,
@@ -217,6 +214,8 @@ xrep_rmap_stash(
 		.rm_flags	= flags,
 	};
 	struct xfs_scrub	*sc = rr->sc;
+	struct xfs_btree_cur	*mcur;
+	struct xfs_buf		*mhead_bp;
 	int			error = 0;
 
 	if (xchk_should_terminate(sc, &error))
@@ -224,8 +223,22 @@ xrep_rmap_stash(
 
 	trace_xrep_rmap_found(sc->mp, sc->sa.pag->pag_agno, &rmap);
 
-	rre.offset = xfs_rmap_irec_offset_pack(&rmap);
-	return xfarray_append(rr->rmap_records, &rre);
+	error = xfbtree_head_read_buf(rr->rmap_btree, sc->tp, &mhead_bp);
+	if (error)
+		return error;
+
+	mcur = xfs_rmapbt_mem_cursor(sc->sa.pag, sc->tp, mhead_bp,
+			rr->rmap_btree);
+	error = xfs_rmap_map_raw(mcur, &rmap);
+	xfs_btree_del_cursor(mcur, error);
+	if (error)
+		goto out_cancel;
+
+	return xfbtree_trans_commit(rr->rmap_btree, sc->tp);
+
+out_cancel:
+	xfbtree_trans_cancel(rr->rmap_btree, sc->tp);
+	return error;
 }
 
 struct xrep_rmap_stash_run {
@@ -802,6 +815,24 @@ xrep_rmap_find_log_rmaps(
 			sc->mp->m_sb.sb_logblocks, XFS_RMAP_OWN_LOG, 0, 0);
 }
 
+/* Check and count all the records that we gathered. */
+STATIC int
+xrep_rmap_check_record(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*rec,
+	void				*priv)
+{
+	struct xrep_rmap		*rr = priv;
+	int				error;
+
+	error = xrep_rmap_check_mapping(rr->sc, rec);
+	if (error)
+		return error;
+
+	rr->nr_records++;
+	return 0;
+}
+
 /*
  * Generate all the reverse-mappings for this AG, a list of the old rmapbt
  * blocks, and the new btreeblks count.  Figure out if we have enough free
@@ -815,6 +846,8 @@ xrep_rmap_find_rmaps(
 	struct xfs_scrub	*sc = rr->sc;
 	struct xchk_ag		*sa = &sc->sa;
 	struct xfs_inode	*ip;
+	struct xfs_buf		*mhead_bp;
+	struct xfs_btree_cur	*mcur;
 	int			error;
 
 	/* Find all the per-AG metadata. */
@@ -882,7 +915,35 @@ xrep_rmap_find_rmaps(
 	error = xchk_setup_fs(sc);
 	if (error)
 		return error;
-	return xchk_perag_drain_and_lock(sc);
+	error = xchk_perag_drain_and_lock(sc);
+	if (error)
+		return error;
+
+	/*
+	 * Now that we have everything locked again, we need to count the
+	 * number of rmap records stashed in the btree.  This should reflect
+	 * all actively-owned space in the filesystem.  At the same time, check
+	 * all our records before we start building a new btree, which requires
+	 * a bnobt cursor.
+	 */
+	error = xfbtree_head_read_buf(rr->rmap_btree, NULL, &mhead_bp);
+	if (error)
+		return error;
+
+	mcur = xfs_rmapbt_mem_cursor(rr->sc->sa.pag, NULL, mhead_bp,
+			rr->rmap_btree);
+	sc->sa.bno_cur = xfs_allocbt_init_cursor(sc->mp, sc->tp, sc->sa.agf_bp,
+			sc->sa.pag, XFS_BTNUM_BNO);
+
+	rr->nr_records = 0;
+	error = xfs_rmap_query_all(mcur, xrep_rmap_check_record, rr);
+
+	xfs_btree_del_cursor(sc->sa.bno_cur, error);
+	sc->sa.bno_cur = NULL;
+	xfs_btree_del_cursor(mcur, error);
+	xfs_buf_relse(mhead_bp);
+
+	return error;
 }
 
 /* Section (II): Reserving space for new rmapbt and setting free space bitmap */
@@ -915,7 +976,6 @@ STATIC int
 xrep_rmap_try_reserve(
 	struct xrep_rmap	*rr,
 	struct xfs_btree_cur	*rmap_cur,
-	uint64_t		nr_records,
 	struct xagb_bitmap	*freesp_blocks,
 	uint64_t		*blocks_reserved,
 	bool			*done)
@@ -999,7 +1059,7 @@ xrep_rmap_try_reserve(
 
 	/* Compute how many blocks we'll need for all the rmaps. */
 	error = xfs_btree_bload_compute_geometry(rmap_cur,
-			&rr->new_btree.bload, nr_records + freesp_records);
+			&rr->new_btree.bload, rr->nr_records + freesp_records);
 	if (error)
 		return error;
 
@@ -1018,16 +1078,13 @@ xrep_rmap_reserve_space(
 	struct xfs_btree_cur	*rmap_cur)
 {
 	struct xagb_bitmap	freesp_blocks;	/* AGBIT */
-	uint64_t		nr_records;	/* NR */
 	uint64_t		blocks_reserved = 0;
 	bool			done = false;
 	int			error;
 
-	nr_records = xfarray_length(rr->rmap_records);
-
 	/* Compute how many blocks we'll need for the rmaps collected so far. */
 	error = xfs_btree_bload_compute_geometry(rmap_cur,
-			&rr->new_btree.bload, nr_records);
+			&rr->new_btree.bload, rr->nr_records);
 	if (error)
 		return error;
 
@@ -1044,8 +1101,8 @@ xrep_rmap_reserve_space(
 	 * Finish when we don't need more blocks.
 	 */
 	do {
-		error = xrep_rmap_try_reserve(rr, rmap_cur, nr_records,
-				&freesp_blocks, &blocks_reserved, &done);
+		error = xrep_rmap_try_reserve(rr, rmap_cur, &freesp_blocks,
+				&blocks_reserved, &done);
 		if (error)
 			goto out_bitmap;
 	} while (!done);
@@ -1107,28 +1164,25 @@ xrep_rmap_get_records(
 	unsigned int		nr_wanted,
 	void			*priv)
 {
-	struct xrep_rmap_extent	rec;
-	struct xfs_rmap_irec	*irec = &cur->bc_rec.r;
 	struct xrep_rmap	*rr = priv;
 	union xfs_btree_rec	*block_rec;
 	unsigned int		loaded;
 	int			error;
 
 	for (loaded = 0; loaded < nr_wanted; loaded++, idx++) {
-		error = xfarray_load_next(rr->rmap_records, &rr->array_cur,
-				&rec);
+		int		stat = 0;
+
+		error = xfs_btree_increment(rr->mcur, 0, &stat);
 		if (error)
 			return error;
-
-		irec->rm_startblock = rec.startblock;
-		irec->rm_blockcount = rec.blockcount;
-		irec->rm_owner = rec.owner;
-		if (xfs_rmap_irec_offset_unpack(rec.offset, irec) != NULL)
+		if (!stat)
 			return -EFSCORRUPTED;
 
-		error = xrep_rmap_check_mapping(rr->sc, irec);
+		error = xfs_rmap_get_rec(rr->mcur, &cur->bc_rec.r, &stat);
 		if (error)
 			return error;
+		if (!stat)
+			return -EFSCORRUPTED;
 
 		block_rec = xfs_btree_rec_addr(cur, idx, block);
 		cur->bc_ops->init_rec_from_cur(cur, block_rec);
@@ -1188,6 +1242,29 @@ xrep_rmap_alloc_vextent(
 	return xfs_alloc_vextent_near_bno(args, alloc_hint);
 }
 
+
+/* Count the records in this btree. */
+STATIC int
+xrep_rmap_count_records(
+	struct xfs_btree_cur	*cur,
+	unsigned long long	*nr)
+{
+	int			running = 1;
+	int			error;
+
+	*nr = 0;
+
+	error = xfs_btree_goto_left_edge(cur);
+	if (error)
+		return error;
+
+	while (running && !(error = xfs_btree_increment(cur, 0, &running))) {
+		if (running)
+			(*nr)++;
+	}
+
+	return error;
+}
 /*
  * Use the collected rmap information to stage a new rmap btree.  If this is
  * successful we'll return with the new btree root information logged to the
@@ -1202,6 +1279,7 @@ xrep_rmap_build_new_tree(
 	struct xfs_perag	*pag = sc->sa.pag;
 	struct xfs_agf		*agf = sc->sa.agf_bp->b_addr;
 	struct xfs_btree_cur	*rmap_cur;
+	struct xfs_buf		*mhead_bp;
 	xfs_fsblock_t		fsbno;
 	int			error;
 
@@ -1236,6 +1314,21 @@ xrep_rmap_build_new_tree(
 	if (error)
 		goto err_cur;
 
+	/*
+	 * Count the rmapbt records again, because the space reservation
+	 * for the rmapbt itself probably added more records to the btree.
+	 */
+	error = xfbtree_head_read_buf(rr->rmap_btree, NULL, &mhead_bp);
+	if (error)
+		goto err_cur;
+
+	rr->mcur = xfs_rmapbt_mem_cursor(rr->sc->sa.pag, NULL, mhead_bp,
+			rr->rmap_btree);
+
+	error = xrep_rmap_count_records(rr->mcur, &rr->nr_records);
+	if (error)
+		goto err_mcur;
+
 	/*
 	 * Due to btree slack factors, it's possible for a new btree to be one
 	 * level taller than the old btree.  Update the incore btree height so
@@ -1245,13 +1338,16 @@ xrep_rmap_build_new_tree(
 	pag->pagf_repair_levels[XFS_BTNUM_RMAPi] =
 					rr->new_btree.bload.btree_height;
 
+	/*
+	 * Move the cursor to the left edge of the tree so that the first
+	 * increment in ->get_records positions us at the first record.
+	 */
+	error = xfs_btree_goto_left_edge(rr->mcur);
+	if (error)
+		goto err_level;
+
 	/* Add all observed rmap records. */
-	rr->array_cur = XFARRAY_CURSOR_INIT;
-	sc->sa.bno_cur = xfs_allocbt_init_cursor(sc->mp, sc->tp, sc->sa.agf_bp,
-			sc->sa.pag, XFS_BTNUM_BNO);
 	error = xfs_btree_bload(rmap_cur, &rr->new_btree.bload, rr);
-	xfs_btree_del_cursor(sc->sa.bno_cur, error);
-	sc->sa.bno_cur = NULL;
 	if (error)
 		goto err_level;
 
@@ -1261,6 +1357,15 @@ xrep_rmap_build_new_tree(
 	 */
 	xfs_rmapbt_commit_staged_btree(rmap_cur, sc->tp, sc->sa.agf_bp);
 	xfs_btree_del_cursor(rmap_cur, 0);
+	xfs_btree_del_cursor(rr->mcur, 0);
+	rr->mcur = NULL;
+	xfs_buf_relse(mhead_bp);
+
+	/*
+	 * Now that we've written the new btree to disk, we don't need to keep
+	 * updating the in-memory btree.  Abort the scan to stop live updates.
+	 */
+	xchk_iscan_abort(&rr->iscan);
 
 	/*
 	 * The newly committed rmap recordset includes mappings for the blocks
@@ -1284,6 +1389,9 @@ xrep_rmap_build_new_tree(
 
 err_level:
 	pag->pagf_repair_levels[XFS_BTNUM_RMAPi] = 0;
+err_mcur:
+	xfs_btree_del_cursor(rr->mcur, error);
+	xfs_buf_relse(mhead_bp);
 err_cur:
 	xfs_btree_del_cursor(rmap_cur, error);
 err_newbt:
@@ -1311,6 +1419,28 @@ xrep_rmap_find_freesp(
 			rec->ar_blockcount);
 }
 
+/* Record the free space we find, as part of cleaning out the btree. */
+STATIC int
+xrep_rmap_find_gaps(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*rec,
+	void				*priv)
+{
+	struct xrep_rmap_find_gaps	*rfg = priv;
+	int				error;
+
+	if (rec->rm_startblock > rfg->next_agbno) {
+		error = xagb_bitmap_set(&rfg->rmap_gaps, rfg->next_agbno,
+				rec->rm_startblock - rfg->next_agbno);
+		if (error)
+			return error;
+	}
+
+	rfg->next_agbno = max_t(xfs_agblock_t, rfg->next_agbno,
+				rec->rm_startblock + rec->rm_blockcount);
+	return 0;
+}
+
 /*
  * Reap the old rmapbt blocks.  Now that the rmapbt is fully rebuilt, we make
  * a list of gaps in the rmap records and a list of the extents mentioned in
@@ -1327,30 +1457,23 @@ xrep_rmap_remove_old_tree(
 	struct xfs_scrub	*sc = rr->sc;
 	struct xfs_agf		*agf = sc->sa.agf_bp->b_addr;
 	struct xfs_perag	*pag = sc->sa.pag;
+	struct xfs_btree_cur	*mcur;
+	struct xfs_buf		*mhead_bp;
 	xfs_agblock_t		agend;
-	xfarray_idx_t		array_cur;
 	int			error;
 
 	xagb_bitmap_init(&rfg.rmap_gaps);
 
 	/* Compute free space from the new rmapbt. */
-	foreach_xfarray_idx(rr->rmap_records, array_cur) {
-		struct xrep_rmap_extent	rec;
+	error = xfbtree_head_read_buf(rr->rmap_btree, NULL, &mhead_bp);
+	mcur = xfs_rmapbt_mem_cursor(rr->sc->sa.pag, NULL, mhead_bp,
+			rr->rmap_btree);
 
-		error = xfarray_load(rr->rmap_records, array_cur, &rec);
-		if (error)
-			goto out_bitmap;
-
-		/* Record the free space we find. */
-		if (rec.startblock > rfg.next_agbno) {
-			error = xagb_bitmap_set(&rfg.rmap_gaps, rfg.next_agbno,
-					rec.startblock - rfg.next_agbno);
-			if (error)
-				goto out_bitmap;
-		}
-		rfg.next_agbno = max_t(xfs_agblock_t, rfg.next_agbno,
-					rec.startblock + rec.blockcount);
-	}
+	error = xfs_rmap_query_all(mcur, xrep_rmap_find_gaps, &rfg);
+	xfs_btree_del_cursor(mcur, error);
+	xfs_buf_relse(mhead_bp);
+	if (error)
+		goto out_bitmap;
 
 	/* Insert a record for space between the last rmap and EOAG. */
 	agend = be32_to_cpu(agf->agf_length);
@@ -1401,14 +1524,11 @@ xrep_rmap_setup_scan(
 	struct xrep_rmap	*rr)
 {
 	struct xfs_scrub	*sc = rr->sc;
-	char			*descr;
 	int			error;
 
-	/* Set up some storage */
-	descr = xchk_xfile_ag_descr(sc, "reverse mapping records");
-	error = xfarray_create(descr, 0, sizeof(struct xrep_rmap_extent),
-			&rr->rmap_records);
-	kfree(descr);
+	/* Set up in-memory rmap btree */
+	error = xfs_rmapbt_mem_create(sc->mp, sc->sa.pag->pag_agno,
+			sc->xfile_buftarg, &rr->rmap_btree);
 	if (error)
 		return error;
 
@@ -1423,7 +1543,7 @@ xrep_rmap_teardown(
 	struct xrep_rmap	*rr)
 {
 	xchk_iscan_teardown(&rr->iscan);
-	xfarray_destroy(rr->rmap_records);
+	xfbtree_destroy(rr->rmap_btree);
 }
 
 /* Repair the rmap btree for some AG. */

[PATCH 4/4] xfs: hook live rmap operations during a repair operation

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Hook the regular rmap code when an rmapbt repair operation is running so
that we can unlock the AGF buffer to scan the filesystem and keep the
in-memory btree up to date during the scan.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_ag.c     |    1 
 fs/xfs/libxfs/xfs_ag.h     |    3 +
 fs/xfs/libxfs/xfs_rmap.c   |  145 ++++++++++++++++++++++++++++++++----------
 fs/xfs/libxfs/xfs_rmap.h   |   28 ++++++++
 fs/xfs/scrub/common.c      |    3 +
 fs/xfs/scrub/repair.c      |   36 ++++++++++
 fs/xfs/scrub/repair.h      |    4 +
 fs/xfs/scrub/rmap_repair.c |  153 ++++++++++++++++++++++++++++++++++++++++++--
 fs/xfs/scrub/scrub.c       |    4 +
 fs/xfs/scrub/scrub.h       |    4 +
 fs/xfs/scrub/trace.c       |    1 
 fs/xfs/scrub/trace.h       |   47 ++++++++++++++
 12 files changed, 389 insertions(+), 40 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 6a7bfc6797d23..6274c8222f76a 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -392,6 +392,7 @@ xfs_initialize_perag(
 		init_waitqueue_head(&pag->pag_active_wq);
 		pag->pagb_count = 0;
 		pag->pagb_tree = RB_ROOT;
+		xfs_hooks_init(&pag->pag_rmap_update_hooks);
 #endif /* __KERNEL__ */
 
 		error = xfs_buf_cache_init(&pag->pag_bcache);
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index fe5852873b82d..06506e09a82d5 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -117,6 +117,9 @@ struct xfs_perag {
 	 * inconsistencies.
 	 */
 	struct xfs_defer_drain	pag_intents_drain;
+
+	/* Hook to feed rmapbt updates to an active online repair. */
+	struct xfs_hooks	pag_rmap_update_hooks;
 #endif /* __KERNEL__ */
 };
 
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 23bc79c96db76..539200e4b2516 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -821,6 +821,77 @@ xfs_rmap_unmap(
 	return error;
 }
 
+#ifdef CONFIG_XFS_LIVE_HOOKS
+/*
+ * Use a static key here to reduce the overhead of rmapbt live updates.  If
+ * the compiler supports jump labels, the static branch will be replaced by a
+ * nop sled when there are no hook users.  Online fsck is currently the only
+ * caller, so this is a reasonable tradeoff.
+ *
+ * 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_STATIC_XFS_HOOK_SWITCH(xfs_rmap_hooks_switch);
+
+void
+xfs_rmap_hook_disable(void)
+{
+	xfs_hooks_switch_off(&xfs_rmap_hooks_switch);
+}
+
+void
+xfs_rmap_hook_enable(void)
+{
+	xfs_hooks_switch_on(&xfs_rmap_hooks_switch);
+}
+
+/* Call downstream hooks for a reverse mapping update. */
+static inline void
+xfs_rmap_update_hook(
+	struct xfs_trans		*tp,
+	struct xfs_perag		*pag,
+	enum xfs_rmap_intent_type	op,
+	xfs_agblock_t			startblock,
+	xfs_extlen_t			blockcount,
+	bool				unwritten,
+	const struct xfs_owner_info	*oinfo)
+{
+	if (xfs_hooks_switched_on(&xfs_rmap_hooks_switch)) {
+		struct xfs_rmap_update_params	p = {
+			.startblock	= startblock,
+			.blockcount	= blockcount,
+			.unwritten	= unwritten,
+			.oinfo		= *oinfo, /* struct copy */
+		};
+
+		if (pag)
+			xfs_hooks_call(&pag->pag_rmap_update_hooks, op, &p);
+	}
+}
+
+/* Call the specified function during a reverse mapping update. */
+int
+xfs_rmap_hook_add(
+	struct xfs_perag	*pag,
+	struct xfs_rmap_hook	*hook)
+{
+	return xfs_hooks_add(&pag->pag_rmap_update_hooks, &hook->update_hook);
+}
+
+/* Stop calling the specified function during a reverse mapping update. */
+void
+xfs_rmap_hook_del(
+	struct xfs_perag	*pag,
+	struct xfs_rmap_hook	*hook)
+{
+	xfs_hooks_del(&pag->pag_rmap_update_hooks, &hook->update_hook);
+}
+#else
+# define xfs_rmap_update_hook(t, p, o, s, b, u, oi)	do { } while (0)
+#endif /* CONFIG_XFS_LIVE_HOOKS */
+
 /*
  * Remove a reference to an extent in the rmap btree.
  */
@@ -841,7 +912,7 @@ xfs_rmap_free(
 		return 0;
 
 	cur = xfs_rmapbt_init_cursor(mp, tp, agbp, pag);
-
+	xfs_rmap_update_hook(tp, pag, XFS_RMAP_UNMAP, bno, len, false, oinfo);
 	error = xfs_rmap_unmap(cur, bno, len, false, oinfo);
 
 	xfs_btree_del_cursor(cur, error);
@@ -1093,6 +1164,7 @@ xfs_rmap_alloc(
 		return 0;
 
 	cur = xfs_rmapbt_init_cursor(mp, tp, agbp, pag);
+	xfs_rmap_update_hook(tp, pag, XFS_RMAP_MAP, bno, len, false, oinfo);
 	error = xfs_rmap_map(cur, bno, len, false, oinfo);
 
 	xfs_btree_del_cursor(cur, error);
@@ -2508,6 +2580,38 @@ xfs_rmap_finish_one_cleanup(
 		xfs_trans_brelse(tp, agbp);
 }
 
+/* Commit an rmap operation into the ondisk tree. */
+int
+__xfs_rmap_finish_intent(
+	struct xfs_btree_cur		*rcur,
+	enum xfs_rmap_intent_type	op,
+	xfs_agblock_t			bno,
+	xfs_extlen_t			len,
+	const struct xfs_owner_info	*oinfo,
+	bool				unwritten)
+{
+	switch (op) {
+	case XFS_RMAP_ALLOC:
+	case XFS_RMAP_MAP:
+		return xfs_rmap_map(rcur, bno, len, unwritten, oinfo);
+	case XFS_RMAP_MAP_SHARED:
+		return xfs_rmap_map_shared(rcur, bno, len, unwritten, oinfo);
+	case XFS_RMAP_FREE:
+	case XFS_RMAP_UNMAP:
+		return xfs_rmap_unmap(rcur, bno, len, unwritten, oinfo);
+	case XFS_RMAP_UNMAP_SHARED:
+		return xfs_rmap_unmap_shared(rcur, bno, len, unwritten, oinfo);
+	case XFS_RMAP_CONVERT:
+		return xfs_rmap_convert(rcur, bno, len, !unwritten, oinfo);
+	case XFS_RMAP_CONVERT_SHARED:
+		return xfs_rmap_convert_shared(rcur, bno, len, !unwritten,
+				oinfo);
+	default:
+		ASSERT(0);
+		return -EFSCORRUPTED;
+	}
+}
+
 /*
  * Process one of the deferred rmap operations.  We pass back the
  * btree cursor to maintain our lock on the rmapbt between calls.
@@ -2574,39 +2678,14 @@ xfs_rmap_finish_one(
 	unwritten = ri->ri_bmap.br_state == XFS_EXT_UNWRITTEN;
 	bno = XFS_FSB_TO_AGBNO(rcur->bc_mp, ri->ri_bmap.br_startblock);
 
-	switch (ri->ri_type) {
-	case XFS_RMAP_ALLOC:
-	case XFS_RMAP_MAP:
-		error = xfs_rmap_map(rcur, bno, ri->ri_bmap.br_blockcount,
-				unwritten, &oinfo);
-		break;
-	case XFS_RMAP_MAP_SHARED:
-		error = xfs_rmap_map_shared(rcur, bno,
-				ri->ri_bmap.br_blockcount, unwritten, &oinfo);
-		break;
-	case XFS_RMAP_FREE:
-	case XFS_RMAP_UNMAP:
-		error = xfs_rmap_unmap(rcur, bno, ri->ri_bmap.br_blockcount,
-				unwritten, &oinfo);
-		break;
-	case XFS_RMAP_UNMAP_SHARED:
-		error = xfs_rmap_unmap_shared(rcur, bno,
-				ri->ri_bmap.br_blockcount, unwritten, &oinfo);
-		break;
-	case XFS_RMAP_CONVERT:
-		error = xfs_rmap_convert(rcur, bno, ri->ri_bmap.br_blockcount,
-				!unwritten, &oinfo);
-		break;
-	case XFS_RMAP_CONVERT_SHARED:
-		error = xfs_rmap_convert_shared(rcur, bno,
-				ri->ri_bmap.br_blockcount, !unwritten, &oinfo);
-		break;
-	default:
-		ASSERT(0);
-		error = -EFSCORRUPTED;
-	}
+	error = __xfs_rmap_finish_intent(rcur, ri->ri_type, bno,
+			ri->ri_bmap.br_blockcount, &oinfo, unwritten);
+	if (error)
+		return error;
 
-	return error;
+	xfs_rmap_update_hook(tp, ri->ri_pag, ri->ri_type, bno,
+			ri->ri_bmap.br_blockcount, unwritten, &oinfo);
+	return 0;
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index 58c67896d12cb..3a153b4801b46 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -186,6 +186,10 @@ void xfs_rmap_finish_one_cleanup(struct xfs_trans *tp,
 		struct xfs_btree_cur *rcur, int error);
 int xfs_rmap_finish_one(struct xfs_trans *tp, struct xfs_rmap_intent *ri,
 		struct xfs_btree_cur **pcur);
+int __xfs_rmap_finish_intent(struct xfs_btree_cur *rcur,
+		enum xfs_rmap_intent_type op, xfs_agblock_t bno,
+		xfs_extlen_t len, const struct xfs_owner_info *oinfo,
+		bool unwritten);
 
 int xfs_rmap_lookup_le_range(struct xfs_btree_cur *cur, xfs_agblock_t bno,
 		uint64_t owner, uint64_t offset, unsigned int flags,
@@ -235,4 +239,28 @@ extern struct kmem_cache	*xfs_rmap_intent_cache;
 int __init xfs_rmap_intent_init_cache(void);
 void xfs_rmap_intent_destroy_cache(void);
 
+/*
+ * Parameters for tracking reverse mapping changes.  The hook function arg
+ * parameter is enum xfs_rmap_intent_type, and the rest is below.
+ */
+struct xfs_rmap_update_params {
+	xfs_agblock_t			startblock;
+	xfs_extlen_t			blockcount;
+	struct xfs_owner_info		oinfo;
+	bool				unwritten;
+};
+
+#ifdef CONFIG_XFS_LIVE_HOOKS
+
+struct xfs_rmap_hook {
+	struct xfs_hook			update_hook;
+};
+
+void xfs_rmap_hook_disable(void);
+void xfs_rmap_hook_enable(void);
+
+int xfs_rmap_hook_add(struct xfs_perag *pag, struct xfs_rmap_hook *hook);
+void xfs_rmap_hook_del(struct xfs_perag *pag, struct xfs_rmap_hook *hook);
+#endif
+
 #endif	/* __XFS_RMAP_H__ */
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 68ec3d5834aee..78ffd6137d498 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -1305,6 +1305,9 @@ xchk_fsgates_enable(
 	if (scrub_fsgates & XCHK_FSGATES_DIRENTS)
 		xfs_dir_hook_enable();
 
+	if (scrub_fsgates & XCHK_FSGATES_RMAP)
+		xfs_rmap_hook_enable();
+
 	sc->flags |= scrub_fsgates;
 }
 
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 4786d56fb7f76..6490f064e091f 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -1165,3 +1165,39 @@ xrep_setup_buftarg(
 
 	return xfile_alloc_buftarg(sc->mp, descr, &sc->xfile_buftarg);
 }
+
+/*
+ * Create a dummy transaction for use in a live update hook function.  This
+ * function MUST NOT be called from regular repair code because the current
+ * process' transaction is saved via the cookie.
+ */
+int
+xrep_trans_alloc_hook_dummy(
+	struct xfs_mount	*mp,
+	void			**cookiep,
+	struct xfs_trans	**tpp)
+{
+	int			error;
+
+	*cookiep = current->journal_info;
+	current->journal_info = NULL;
+
+	error = xfs_trans_alloc_empty(mp, tpp);
+	if (!error)
+		return 0;
+
+	current->journal_info = *cookiep;
+	*cookiep = NULL;
+	return error;
+}
+
+/* Cancel a dummy transaction used by a live update hook function. */
+void
+xrep_trans_cancel_hook_dummy(
+	void			**cookiep,
+	struct xfs_trans	*tp)
+{
+	xfs_trans_cancel(tp);
+	current->journal_info = *cookiep;
+	*cookiep = NULL;
+}
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 2139a85cdb83b..0243481f770fe 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -140,6 +140,10 @@ int xrep_quotacheck(struct xfs_scrub *sc);
 int xrep_reinit_pagf(struct xfs_scrub *sc);
 int xrep_reinit_pagi(struct xfs_scrub *sc);
 
+int xrep_trans_alloc_hook_dummy(struct xfs_mount *mp, void **cookiep,
+		struct xfs_trans **tpp);
+void xrep_trans_cancel_hook_dummy(void **cookiep, struct xfs_trans *tp);
+
 #else
 
 #define xrep_ino_dqattach(sc)	(0)
diff --git a/fs/xfs/scrub/rmap_repair.c b/fs/xfs/scrub/rmap_repair.c
index 832f221bc4757..9ece83704518d 100644
--- a/fs/xfs/scrub/rmap_repair.c
+++ b/fs/xfs/scrub/rmap_repair.c
@@ -128,6 +128,9 @@ struct xrep_rmap {
 	/* new rmapbt information */
 	struct xrep_newbt	new_btree;
 
+	/* lock for the xfbtree and xfile */
+	struct mutex		lock;
+
 	/* rmap records generated from primary metadata */
 	struct xfbtree		*rmap_btree;
 
@@ -136,6 +139,9 @@ struct xrep_rmap {
 	/* in-memory btree cursor for the xfs_btree_bload iteration */
 	struct xfs_btree_cur	*mcur;
 
+	/* Hooks into rmap update code. */
+	struct xfs_rmap_hook	hooks;
+
 	/* inode scan cursor */
 	struct xchk_iscan	iscan;
 
@@ -158,6 +164,8 @@ xrep_setup_ag_rmapbt(
 	char			*descr;
 	int			error;
 
+	xchk_fsgates_enable(sc, XCHK_FSGATES_RMAP);
+
 	descr = xchk_xfile_ag_descr(sc, "reverse mapping records");
 	error = xrep_setup_buftarg(sc, descr);
 	kfree(descr);
@@ -221,11 +229,15 @@ xrep_rmap_stash(
 	if (xchk_should_terminate(sc, &error))
 		return error;
 
+	if (xchk_iscan_aborted(&rr->iscan))
+		return -EFSCORRUPTED;
+
 	trace_xrep_rmap_found(sc->mp, sc->sa.pag->pag_agno, &rmap);
 
+	mutex_lock(&rr->lock);
 	error = xfbtree_head_read_buf(rr->rmap_btree, sc->tp, &mhead_bp);
 	if (error)
-		return error;
+		goto out_abort;
 
 	mcur = xfs_rmapbt_mem_cursor(sc->sa.pag, sc->tp, mhead_bp,
 			rr->rmap_btree);
@@ -234,10 +246,18 @@ xrep_rmap_stash(
 	if (error)
 		goto out_cancel;
 
-	return xfbtree_trans_commit(rr->rmap_btree, sc->tp);
+	error = xfbtree_trans_commit(rr->rmap_btree, sc->tp);
+	if (error)
+		goto out_abort;
+
+	mutex_unlock(&rr->lock);
+	return 0;
 
 out_cancel:
 	xfbtree_trans_cancel(rr->rmap_btree, sc->tp);
+out_abort:
+	xchk_iscan_abort(&rr->iscan);
+	mutex_unlock(&rr->lock);
 	return error;
 }
 
@@ -919,6 +939,13 @@ xrep_rmap_find_rmaps(
 	if (error)
 		return error;
 
+	/*
+	 * If a hook failed to update the in-memory btree, we lack the data to
+	 * continue the repair.
+	 */
+	if (xchk_iscan_aborted(&rr->iscan))
+		return -EFSCORRUPTED;
+
 	/*
 	 * Now that we have everything locked again, we need to count the
 	 * number of rmap records stashed in the btree.  This should reflect
@@ -1518,6 +1545,97 @@ xrep_rmap_remove_old_tree(
 	return error;
 }
 
+static inline bool
+xrep_rmapbt_want_live_update(
+	struct xchk_iscan		*iscan,
+	const struct xfs_owner_info	*oi)
+{
+	if (xchk_iscan_aborted(iscan))
+		return false;
+
+	/*
+	 * Before unlocking the AG header to perform the inode scan, we
+	 * recorded reverse mappings for all AG metadata except for the OWN_AG
+	 * metadata.  IOWs, the in-memory btree knows about the AG headers, the
+	 * two inode btrees, the CoW staging extents, and the refcount btrees.
+	 * For these types of metadata, we need to record the live updates in
+	 * the in-memory rmap btree.
+	 *
+	 * However, we do not scan the free space btrees or the AGFL until we
+	 * have re-locked the AGF and are ready to reserve space for the new
+	 * rmap btree, so we do not want live updates for OWN_AG metadata.
+	 */
+	if (XFS_RMAP_NON_INODE_OWNER(oi->oi_owner))
+		return oi->oi_owner != XFS_RMAP_OWN_AG;
+
+	/* Ignore updates to files that the scanner hasn't visited yet. */
+	return xchk_iscan_want_live_update(iscan, oi->oi_owner);
+}
+
+/*
+ * Apply a rmapbt update from the regular filesystem into our shadow btree.
+ * We're running from the thread that owns the AGF buffer and is generating
+ * the update, so we must be careful about which parts of the struct xrep_rmap
+ * that we change.
+ */
+static int
+xrep_rmapbt_live_update(
+	struct notifier_block		*nb,
+	unsigned long			action,
+	void				*data)
+{
+	struct xfs_rmap_update_params	*p = data;
+	struct xrep_rmap		*rr;
+	struct xfs_mount		*mp;
+	struct xfs_btree_cur		*mcur;
+	struct xfs_buf			*mhead_bp;
+	struct xfs_trans		*tp;
+	void				*txcookie;
+	int				error;
+
+	rr = container_of(nb, struct xrep_rmap, hooks.update_hook.nb);
+	mp = rr->sc->mp;
+
+	if (!xrep_rmapbt_want_live_update(&rr->iscan, &p->oinfo))
+		goto out_unlock;
+
+	trace_xrep_rmap_live_update(mp, rr->sc->sa.pag->pag_agno, action, p);
+
+	error = xrep_trans_alloc_hook_dummy(mp, &txcookie, &tp);
+	if (error)
+		goto out_abort;
+
+	mutex_lock(&rr->lock);
+	error = xfbtree_head_read_buf(rr->rmap_btree, tp, &mhead_bp);
+	if (error)
+		goto out_cancel;
+
+	mcur = xfs_rmapbt_mem_cursor(rr->sc->sa.pag, tp, mhead_bp,
+			rr->rmap_btree);
+	error = __xfs_rmap_finish_intent(mcur, action, p->startblock,
+			p->blockcount, &p->oinfo, p->unwritten);
+	xfs_btree_del_cursor(mcur, error);
+	if (error)
+		goto out_cancel;
+
+	error = xfbtree_trans_commit(rr->rmap_btree, tp);
+	if (error)
+		goto out_cancel;
+
+	xrep_trans_cancel_hook_dummy(&txcookie, tp);
+	mutex_unlock(&rr->lock);
+	return NOTIFY_DONE;
+
+out_cancel:
+	xfbtree_trans_cancel(rr->rmap_btree, tp);
+	xrep_trans_cancel_hook_dummy(&txcookie, tp);
+out_abort:
+	mutex_unlock(&rr->lock);
+	xchk_iscan_abort(&rr->iscan);
+out_unlock:
+	return NOTIFY_DONE;
+}
+
 /* Set up the filesystem scan components. */
 STATIC int
 xrep_rmap_setup_scan(
@@ -1526,15 +1644,36 @@ xrep_rmap_setup_scan(
 	struct xfs_scrub	*sc = rr->sc;
 	int			error;
 
+	mutex_init(&rr->lock);
+
 	/* Set up in-memory rmap btree */
 	error = xfs_rmapbt_mem_create(sc->mp, sc->sa.pag->pag_agno,
 			sc->xfile_buftarg, &rr->rmap_btree);
 	if (error)
-		return error;
+		goto out_mutex;
 
 	/* Retry iget every tenth of a second for up to 30 seconds. */
 	xchk_iscan_start(sc, 30000, 100, &rr->iscan);
+
+	/*
+	 * Hook into live rmap operations so that we can update our in-memory
+	 * btree to reflect live changes on the filesystem.  Since we drop the
+	 * AGF buffer to scan all the inodes, we need this piece to avoid
+	 * installing a stale btree.
+	 */
+	ASSERT(sc->flags & XCHK_FSGATES_RMAP);
+	xfs_hook_setup(&rr->hooks.update_hook, xrep_rmapbt_live_update);
+	error = xfs_rmap_hook_add(sc->sa.pag, &rr->hooks);
+	if (error)
+		goto out_iscan;
 	return 0;
+
+out_iscan:
+	xchk_iscan_teardown(&rr->iscan);
+	xfbtree_destroy(rr->rmap_btree);
+out_mutex:
+	mutex_destroy(&rr->lock);
+	return error;
 }
 
 /* Tear down scan components. */
@@ -1542,8 +1681,13 @@ STATIC void
 xrep_rmap_teardown(
 	struct xrep_rmap	*rr)
 {
+	struct xfs_scrub	*sc = rr->sc;
+
+	xchk_iscan_abort(&rr->iscan);
+	xfs_rmap_hook_del(sc->sa.pag, &rr->hooks);
 	xchk_iscan_teardown(&rr->iscan);
 	xfbtree_destroy(rr->rmap_btree);
+	mutex_destroy(&rr->lock);
 }
 
 /* Repair the rmap btree for some AG. */
@@ -1554,9 +1698,6 @@ xrep_rmapbt(
 	struct xrep_rmap	*rr = sc->buf;
 	int			error;
 
-	/* Functionality is not yet complete. */
-	return xrep_notsupported(sc);
-
 	error = xrep_rmap_setup_scan(rr);
 	if (error)
 		return error;
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index a37476a2a956b..2075bfd83e3dc 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -16,6 +16,7 @@
 #include "xfs_qm.h"
 #include "xfs_scrub.h"
 #include "xfs_buf_xfile.h"
+#include "xfs_rmap.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
@@ -164,6 +165,9 @@ xchk_fsgates_disable(
 	if (sc->flags & XCHK_FSGATES_DIRENTS)
 		xfs_dir_hook_disable();
 
+	if (sc->flags & XCHK_FSGATES_RMAP)
+		xfs_rmap_hook_disable();
+
 	sc->flags &= ~XCHK_FSGATES_ALL;
 }
 
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index 1f0d655941e32..165cef0b1d25a 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -126,6 +126,7 @@ struct xfs_scrub {
 #define XCHK_NEED_DRAIN		(1U << 3)  /* scrub needs to drain defer ops */
 #define XCHK_FSGATES_QUOTA	(1U << 4)  /* quota live update enabled */
 #define XCHK_FSGATES_DIRENTS	(1U << 5)  /* directory live update enabled */
+#define XCHK_FSGATES_RMAP	(1U << 6)  /* rmapbt live update enabled */
 #define XREP_RESET_PERAG_RESV	(1U << 30) /* must reset AG space reservation */
 #define XREP_ALREADY_FIXED	(1U << 31) /* checking our repair work */
 
@@ -137,7 +138,8 @@ struct xfs_scrub {
  */
 #define XCHK_FSGATES_ALL	(XCHK_FSGATES_DRAIN | \
 				 XCHK_FSGATES_QUOTA | \
-				 XCHK_FSGATES_DIRENTS)
+				 XCHK_FSGATES_DIRENTS | \
+				 XCHK_FSGATES_RMAP)
 
 /* Metadata scrubbers */
 int xchk_tester(struct xfs_scrub *sc);
diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c
index bffe138abc057..ea41b5d9b3c6a 100644
--- a/fs/xfs/scrub/trace.c
+++ b/fs/xfs/scrub/trace.c
@@ -19,6 +19,7 @@
 #include "xfs_quota_defs.h"
 #include "xfs_da_format.h"
 #include "xfs_dir2.h"
+#include "xfs_rmap.h"
 #include "scrub/scrub.h"
 #include "scrub/xfile.h"
 #include "scrub/xfarray.h"
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 82ab945c5479b..06d593dcd697a 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -27,6 +27,7 @@ struct xchk_nlink;
 struct xchk_fscounters;
 struct xfbtree;
 struct xfbtree_config;
+struct xfs_rmap_update_params;
 
 /*
  * ftrace's __print_symbolic requires that all enum values be wrapped in the
@@ -122,6 +123,7 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_HEALTHY);
 	{ XCHK_NEED_DRAIN,			"need_drain" }, \
 	{ XCHK_FSGATES_QUOTA,			"fsgates_quota" }, \
 	{ XCHK_FSGATES_DIRENTS,			"fsgates_dirents" }, \
+	{ XCHK_FSGATES_RMAP,			"fsgates_rmap" }, \
 	{ XREP_RESET_PERAG_RESV,		"reset_perag_resv" }, \
 	{ XREP_ALREADY_FIXED,			"already_fixed" }
 
@@ -2315,6 +2317,51 @@ DEFINE_EVENT(xfbtree_freesp_class, name, \
 DEFINE_XFBTREE_FREESP_EVENT(xfbtree_alloc_block);
 DEFINE_XFBTREE_FREESP_EVENT(xfbtree_free_block);
 
+TRACE_DEFINE_ENUM(XFS_RMAP_MAP);
+TRACE_DEFINE_ENUM(XFS_RMAP_MAP_SHARED);
+TRACE_DEFINE_ENUM(XFS_RMAP_UNMAP);
+TRACE_DEFINE_ENUM(XFS_RMAP_UNMAP_SHARED);
+TRACE_DEFINE_ENUM(XFS_RMAP_CONVERT);
+TRACE_DEFINE_ENUM(XFS_RMAP_CONVERT_SHARED);
+TRACE_DEFINE_ENUM(XFS_RMAP_ALLOC);
+TRACE_DEFINE_ENUM(XFS_RMAP_FREE);
+
+TRACE_EVENT(xrep_rmap_live_update,
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, unsigned int op,
+		 const struct xfs_rmap_update_params *p),
+	TP_ARGS(mp, agno, op, p),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(unsigned int, op)
+		__field(xfs_agblock_t, agbno)
+		__field(xfs_extlen_t, len)
+		__field(uint64_t, owner)
+		__field(uint64_t, offset)
+		__field(unsigned int, flags)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->agno = agno;
+		__entry->op = op;
+		__entry->agbno = p->startblock;
+		__entry->len = p->blockcount;
+		xfs_owner_info_unpack(&p->oinfo, &__entry->owner,
+				&__entry->offset, &__entry->flags);
+		if (p->unwritten)
+			__entry->flags |= XFS_RMAP_UNWRITTEN;
+	),
+	TP_printk("dev %d:%d agno 0x%x op %d agbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->op,
+		  __entry->agbno,
+		  __entry->len,
+		  __entry->owner,
+		  __entry->offset,
+		  __entry->flags)
+);
+
 #endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
 
 

[PATCH 1/9] xfs: set the btree cursor bc_ops in xfs_btree_alloc_cursor

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

This is a precursor to putting more static data in the btree ops structure.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_alloc_btree.c    |   11 +++++------
 fs/xfs/libxfs/xfs_bmap_btree.c     |    3 +--
 fs/xfs/libxfs/xfs_btree.h          |    2 ++
 fs/xfs/libxfs/xfs_ialloc_btree.c   |   10 ++++++----
 fs/xfs/libxfs/xfs_refcount_btree.c |    4 ++--
 fs/xfs/libxfs/xfs_rmap_btree.c     |    7 +++----
 fs/xfs/scrub/xfbtree.c             |    4 ++--
 7 files changed, 21 insertions(+), 20 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index a7032bf0cd37a..cdcb2358351c6 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -512,18 +512,17 @@ xfs_allocbt_init_common(
 
 	ASSERT(btnum == XFS_BTNUM_BNO || btnum == XFS_BTNUM_CNT);
 
-	cur = xfs_btree_alloc_cursor(mp, tp, btnum, mp->m_alloc_maxlevels,
-			xfs_allocbt_cur_cache);
-	cur->bc_ag.abt.active = false;
-
 	if (btnum == XFS_BTNUM_CNT) {
-		cur->bc_ops = &xfs_cntbt_ops;
+		cur = xfs_btree_alloc_cursor(mp, tp, btnum, &xfs_cntbt_ops,
+				mp->m_alloc_maxlevels, xfs_allocbt_cur_cache);
 		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtc_2);
 		cur->bc_flags = XFS_BTREE_LASTREC_UPDATE;
 	} else {
-		cur->bc_ops = &xfs_bnobt_ops;
+		cur = xfs_btree_alloc_cursor(mp, tp, btnum, &xfs_bnobt_ops,
+				mp->m_alloc_maxlevels, xfs_allocbt_cur_cache);
 		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtb_2);
 	}
+	cur->bc_ag.abt.active = false;
 
 	cur->bc_ag.pag = xfs_perag_hold(pag);
 
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 71f2d50f78238..19414c7118867 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -549,11 +549,10 @@ xfs_bmbt_init_common(
 
 	ASSERT(whichfork != XFS_COW_FORK);
 
-	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_BMAP,
+	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_BMAP, &xfs_bmbt_ops,
 			mp->m_bm_maxlevels[whichfork], xfs_bmbt_cur_cache);
 	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_bmbt_2);
 
-	cur->bc_ops = &xfs_bmbt_ops;
 	cur->bc_flags = XFS_BTREE_LONG_PTRS | XFS_BTREE_ROOT_IN_INODE;
 	if (xfs_has_crc(mp))
 		cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 3e6bdbc507039..ed1388890315b 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -737,12 +737,14 @@ xfs_btree_alloc_cursor(
 	struct xfs_mount	*mp,
 	struct xfs_trans	*tp,
 	xfs_btnum_t		btnum,
+	const struct xfs_btree_ops *ops,
 	uint8_t			maxlevels,
 	struct kmem_cache	*cache)
 {
 	struct xfs_btree_cur	*cur;
 
 	cur = kmem_cache_zalloc(cache, GFP_NOFS | __GFP_NOFAIL);
+	cur->bc_ops = ops;
 	cur->bc_tp = tp;
 	cur->bc_mp = mp;
 	cur->bc_btnum = btnum;
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 42a5e1f227a05..8b705cc62d3d3 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -454,14 +454,16 @@ xfs_inobt_init_common(
 	struct xfs_mount	*mp = pag->pag_mount;
 	struct xfs_btree_cur	*cur;
 
-	cur = xfs_btree_alloc_cursor(mp, tp, btnum,
-			M_IGEO(mp)->inobt_maxlevels, xfs_inobt_cur_cache);
 	if (btnum == XFS_BTNUM_INO) {
+		cur = xfs_btree_alloc_cursor(mp, tp, btnum, &xfs_inobt_ops,
+				M_IGEO(mp)->inobt_maxlevels,
+				xfs_inobt_cur_cache);
 		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_ibt_2);
-		cur->bc_ops = &xfs_inobt_ops;
 	} else {
+		cur = xfs_btree_alloc_cursor(mp, tp, btnum, &xfs_finobt_ops,
+				M_IGEO(mp)->inobt_maxlevels,
+				xfs_inobt_cur_cache);
 		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_fibt_2);
-		cur->bc_ops = &xfs_finobt_ops;
 	}
 
 	if (xfs_has_crc(mp))
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index f904a92d1b590..1eb164816825f 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -353,7 +353,8 @@ xfs_refcountbt_init_common(
 	ASSERT(pag->pag_agno < mp->m_sb.sb_agcount);
 
 	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_REFC,
-			mp->m_refc_maxlevels, xfs_refcountbt_cur_cache);
+			&xfs_refcountbt_ops, mp->m_refc_maxlevels,
+			xfs_refcountbt_cur_cache);
 	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_refcbt_2);
 
 	cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
@@ -361,7 +362,6 @@ xfs_refcountbt_init_common(
 	cur->bc_ag.pag = xfs_perag_hold(pag);
 	cur->bc_ag.refc.nr_ops = 0;
 	cur->bc_ag.refc.shape_changes = 0;
-	cur->bc_ops = &xfs_refcountbt_ops;
 	return cur;
 }
 
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index e29ae6d0f79d4..e0c60ee5b59db 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -517,11 +517,10 @@ xfs_rmapbt_init_common(
 	struct xfs_btree_cur	*cur;
 
 	/* Overlapping btree; 2 keys per pointer. */
-	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_RMAP,
+	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_RMAP, &xfs_rmapbt_ops,
 			mp->m_rmap_maxlevels, xfs_rmapbt_cur_cache);
 	cur->bc_flags = XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING;
 	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_rmap_2);
-	cur->bc_ops = &xfs_rmapbt_ops;
 
 	cur->bc_ag.pag = xfs_perag_hold(pag);
 	return cur;
@@ -646,11 +645,11 @@ xfs_rmapbt_mem_cursor(
 
 	/* Overlapping btree; 2 keys per pointer. */
 	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_RMAP,
-			mp->m_rmap_maxlevels, xfs_rmapbt_cur_cache);
+			&xfs_rmapbt_mem_ops, mp->m_rmap_maxlevels,
+			xfs_rmapbt_cur_cache);
 	cur->bc_flags = XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING |
 			XFS_BTREE_IN_XFILE;
 	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_rmap_2);
-	cur->bc_ops = &xfs_rmapbt_mem_ops;
 	cur->bc_mem.xfbtree = xfbtree;
 	cur->bc_mem.head_bp = head_bp;
 	cur->bc_nlevels = xfs_btree_mem_head_nlevels(head_bp);
diff --git a/fs/xfs/scrub/xfbtree.c b/fs/xfs/scrub/xfbtree.c
index 8879b54068a75..c5ef0ea8cad22 100644
--- a/fs/xfs/scrub/xfbtree.c
+++ b/fs/xfs/scrub/xfbtree.c
@@ -289,11 +289,11 @@ xfbtree_dup_cursor(
 	ASSERT(cur->bc_flags & XFS_BTREE_IN_XFILE);
 
 	ncur = xfs_btree_alloc_cursor(cur->bc_mp, cur->bc_tp, cur->bc_btnum,
-			cur->bc_maxlevels, cur->bc_cache);
+			cur->bc_ops, cur->bc_maxlevels, cur->bc_cache);
 	ncur->bc_flags = cur->bc_flags;
 	ncur->bc_nlevels = cur->bc_nlevels;
 	ncur->bc_statoff = cur->bc_statoff;
-	ncur->bc_ops = cur->bc_ops;
+
 	memcpy(&ncur->bc_mem, &cur->bc_mem, sizeof(cur->bc_mem));
 
 	if (cur->bc_mem.pag)

[PATCH 2/9] xfs: encode the default bc_flags in the btree ops structure

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Certain btree flags never change for the life of a btree cursor because
they describe the geometry of the btree itself.  Encode these in the
btree ops structure and reduce the amount of code required in each btree
type's init_cursor functions.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_alloc_btree.c    |    8 ++------
 fs/xfs/libxfs/xfs_bmap_btree.c     |    5 +----
 fs/xfs/libxfs/xfs_btree.h          |    6 ++++++
 fs/xfs/libxfs/xfs_ialloc_btree.c   |    3 ---
 fs/xfs/libxfs/xfs_refcount_btree.c |    2 --
 fs/xfs/libxfs/xfs_rmap_btree.c     |    6 +++---
 6 files changed, 12 insertions(+), 18 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index cdcb2358351c6..76dbfc591cd57 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -480,6 +480,7 @@ static const struct xfs_btree_ops xfs_bnobt_ops = {
 static const struct xfs_btree_ops xfs_cntbt_ops = {
 	.rec_len		= sizeof(xfs_alloc_rec_t),
 	.key_len		= sizeof(xfs_alloc_key_t),
+	.geom_flags		= XFS_BTREE_LASTREC_UPDATE,
 
 	.dup_cursor		= xfs_allocbt_dup_cursor,
 	.set_root		= xfs_allocbt_set_root,
@@ -516,19 +517,14 @@ xfs_allocbt_init_common(
 		cur = xfs_btree_alloc_cursor(mp, tp, btnum, &xfs_cntbt_ops,
 				mp->m_alloc_maxlevels, xfs_allocbt_cur_cache);
 		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtc_2);
-		cur->bc_flags = XFS_BTREE_LASTREC_UPDATE;
 	} else {
 		cur = xfs_btree_alloc_cursor(mp, tp, btnum, &xfs_bnobt_ops,
 				mp->m_alloc_maxlevels, xfs_allocbt_cur_cache);
 		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtb_2);
 	}
-	cur->bc_ag.abt.active = false;
 
 	cur->bc_ag.pag = xfs_perag_hold(pag);
-
-	if (xfs_has_crc(mp))
-		cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
-
+	cur->bc_ag.abt.active = false;
 	return cur;
 }
 
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 19414c7118867..ca7ea824b818b 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -518,6 +518,7 @@ xfs_bmbt_keys_contiguous(
 static const struct xfs_btree_ops xfs_bmbt_ops = {
 	.rec_len		= sizeof(xfs_bmbt_rec_t),
 	.key_len		= sizeof(xfs_bmbt_key_t),
+	.geom_flags		= XFS_BTREE_LONG_PTRS | XFS_BTREE_ROOT_IN_INODE,
 
 	.dup_cursor		= xfs_bmbt_dup_cursor,
 	.update_cursor		= xfs_bmbt_update_cursor,
@@ -553,10 +554,6 @@ xfs_bmbt_init_common(
 			mp->m_bm_maxlevels[whichfork], xfs_bmbt_cur_cache);
 	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_bmbt_2);
 
-	cur->bc_flags = XFS_BTREE_LONG_PTRS | XFS_BTREE_ROOT_IN_INODE;
-	if (xfs_has_crc(mp))
-		cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
-
 	cur->bc_ino.ip = ip;
 	cur->bc_ino.allocated = 0;
 	cur->bc_ino.flags = 0;
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index ed1388890315b..2c2d5db94b1dc 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -116,6 +116,9 @@ struct xfs_btree_ops {
 	size_t	key_len;
 	size_t	rec_len;
 
+	/* XFS_BTREE_* flags that determine the geometry of the btree */
+	unsigned int	geom_flags;
+
 	/* cursor operations */
 	struct xfs_btree_cur *(*dup_cursor)(struct xfs_btree_cur *);
 	void	(*update_cursor)(struct xfs_btree_cur *src,
@@ -750,6 +753,9 @@ xfs_btree_alloc_cursor(
 	cur->bc_btnum = btnum;
 	cur->bc_maxlevels = maxlevels;
 	cur->bc_cache = cache;
+	cur->bc_flags = ops->geom_flags;
+	if (xfs_has_crc(mp))
+		cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
 
 	return cur;
 }
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 8b705cc62d3d3..3e65f028f3eea 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -466,9 +466,6 @@ xfs_inobt_init_common(
 		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_fibt_2);
 	}
 
-	if (xfs_has_crc(mp))
-		cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
-
 	cur->bc_ag.pag = xfs_perag_hold(pag);
 	return cur;
 }
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 1eb164816825f..6a3a827dd3663 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -357,8 +357,6 @@ xfs_refcountbt_init_common(
 			xfs_refcountbt_cur_cache);
 	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_refcbt_2);
 
-	cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
-
 	cur->bc_ag.pag = xfs_perag_hold(pag);
 	cur->bc_ag.refc.nr_ops = 0;
 	cur->bc_ag.refc.shape_changes = 0;
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index e0c60ee5b59db..bc01c71982fb6 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -489,6 +489,7 @@ xfs_rmapbt_keys_contiguous(
 static const struct xfs_btree_ops xfs_rmapbt_ops = {
 	.rec_len		= sizeof(struct xfs_rmap_rec),
 	.key_len		= 2 * sizeof(struct xfs_rmap_key),
+	.geom_flags		= XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING,
 
 	.dup_cursor		= xfs_rmapbt_dup_cursor,
 	.set_root		= xfs_rmapbt_set_root,
@@ -519,7 +520,6 @@ xfs_rmapbt_init_common(
 	/* Overlapping btree; 2 keys per pointer. */
 	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_RMAP, &xfs_rmapbt_ops,
 			mp->m_rmap_maxlevels, xfs_rmapbt_cur_cache);
-	cur->bc_flags = XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING;
 	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_rmap_2);
 
 	cur->bc_ag.pag = xfs_perag_hold(pag);
@@ -613,6 +613,8 @@ static const struct xfs_buf_ops xfs_rmapbt_mem_buf_ops = {
 static const struct xfs_btree_ops xfs_rmapbt_mem_ops = {
 	.rec_len		= sizeof(struct xfs_rmap_rec),
 	.key_len		= 2 * sizeof(struct xfs_rmap_key),
+	.geom_flags		= XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING |
+				  XFS_BTREE_IN_XFILE,
 
 	.dup_cursor		= xfbtree_dup_cursor,
 	.set_root		= xfbtree_set_root,
@@ -647,8 +649,6 @@ xfs_rmapbt_mem_cursor(
 	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_RMAP,
 			&xfs_rmapbt_mem_ops, mp->m_rmap_maxlevels,
 			xfs_rmapbt_cur_cache);
-	cur->bc_flags = XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING |
-			XFS_BTREE_IN_XFILE;
 	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_rmap_2);
 	cur->bc_mem.xfbtree = xfbtree;
 	cur->bc_mem.head_bp = head_bp;

[PATCH 3/9] xfs: export some of the btree ops structures

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Export these btree ops structures so that we can reference them in the
AG initialization code in the next patch.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_alloc_btree.c    |    4 ++--
 fs/xfs/libxfs/xfs_bmap_btree.c     |    2 +-
 fs/xfs/libxfs/xfs_ialloc_btree.c   |    4 ++--
 fs/xfs/libxfs/xfs_refcount_btree.c |    2 +-
 fs/xfs/libxfs/xfs_rmap_btree.c     |    2 +-
 fs/xfs/libxfs/xfs_shared.h         |    9 +++++++++
 6 files changed, 16 insertions(+), 7 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index 76dbfc591cd57..08aa92f574334 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -454,7 +454,7 @@ xfs_allocbt_keys_contiguous(
 				 be32_to_cpu(key2->alloc.ar_startblock));
 }
 
-static const struct xfs_btree_ops xfs_bnobt_ops = {
+const struct xfs_btree_ops xfs_bnobt_ops = {
 	.rec_len		= sizeof(xfs_alloc_rec_t),
 	.key_len		= sizeof(xfs_alloc_key_t),
 
@@ -477,7 +477,7 @@ static const struct xfs_btree_ops xfs_bnobt_ops = {
 	.keys_contiguous	= xfs_allocbt_keys_contiguous,
 };
 
-static const struct xfs_btree_ops xfs_cntbt_ops = {
+const struct xfs_btree_ops xfs_cntbt_ops = {
 	.rec_len		= sizeof(xfs_alloc_rec_t),
 	.key_len		= sizeof(xfs_alloc_key_t),
 	.geom_flags		= XFS_BTREE_LASTREC_UPDATE,
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index ca7ea824b818b..5777c51a0c01d 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -515,7 +515,7 @@ xfs_bmbt_keys_contiguous(
 				 be64_to_cpu(key2->bmbt.br_startoff));
 }
 
-static const struct xfs_btree_ops xfs_bmbt_ops = {
+const struct xfs_btree_ops xfs_bmbt_ops = {
 	.rec_len		= sizeof(xfs_bmbt_rec_t),
 	.key_len		= sizeof(xfs_bmbt_key_t),
 	.geom_flags		= XFS_BTREE_LONG_PTRS | XFS_BTREE_ROOT_IN_INODE,
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 3e65f028f3eea..69086fdc3be6f 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -398,7 +398,7 @@ xfs_inobt_keys_contiguous(
 				 be32_to_cpu(key2->inobt.ir_startino));
 }
 
-static const struct xfs_btree_ops xfs_inobt_ops = {
+const struct xfs_btree_ops xfs_inobt_ops = {
 	.rec_len		= sizeof(xfs_inobt_rec_t),
 	.key_len		= sizeof(xfs_inobt_key_t),
 
@@ -420,7 +420,7 @@ static const struct xfs_btree_ops xfs_inobt_ops = {
 	.keys_contiguous	= xfs_inobt_keys_contiguous,
 };
 
-static const struct xfs_btree_ops xfs_finobt_ops = {
+const struct xfs_btree_ops xfs_finobt_ops = {
 	.rec_len		= sizeof(xfs_inobt_rec_t),
 	.key_len		= sizeof(xfs_inobt_key_t),
 
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 6a3a827dd3663..36e7b26d5e3b2 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -317,7 +317,7 @@ xfs_refcountbt_keys_contiguous(
 				 be32_to_cpu(key2->refc.rc_startblock));
 }
 
-static const struct xfs_btree_ops xfs_refcountbt_ops = {
+const struct xfs_btree_ops xfs_refcountbt_ops = {
 	.rec_len		= sizeof(struct xfs_refcount_rec),
 	.key_len		= sizeof(struct xfs_refcount_key),
 
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index bc01c71982fb6..f5889da0bff76 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -486,7 +486,7 @@ xfs_rmapbt_keys_contiguous(
 				 be32_to_cpu(key2->rmap.rm_startblock));
 }
 
-static const struct xfs_btree_ops xfs_rmapbt_ops = {
+const struct xfs_btree_ops xfs_rmapbt_ops = {
 	.rec_len		= sizeof(struct xfs_rmap_rec),
 	.key_len		= 2 * sizeof(struct xfs_rmap_key),
 	.geom_flags		= XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING,
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index 4220d3584c1b0..518ea9456ebae 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -43,6 +43,15 @@ extern const struct xfs_buf_ops xfs_sb_buf_ops;
 extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops;
 extern const struct xfs_buf_ops xfs_symlink_buf_ops;
 
+/* btree ops */
+extern const struct xfs_btree_ops xfs_bnobt_ops;
+extern const struct xfs_btree_ops xfs_cntbt_ops;
+extern const struct xfs_btree_ops xfs_inobt_ops;
+extern const struct xfs_btree_ops xfs_finobt_ops;
+extern const struct xfs_btree_ops xfs_bmbt_ops;
+extern const struct xfs_btree_ops xfs_refcountbt_ops;
+extern const struct xfs_btree_ops xfs_rmapbt_ops;
+
 /* log size calculation functions */
 int	xfs_log_calc_unit_res(struct xfs_mount *mp, int unit_bytes);
 int	xfs_log_calc_minimum_size(struct xfs_mount *);

[PATCH 4/9] xfs: initialize btree blocks using btree_ops structure

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Notice now that the btree ops structure encodes btree geometry flags and
the magic number through the buffer ops.  Refactor the btree block
initialization functions to use the btree ops so that we no longer have
to open code all that.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_ag.c            |   33 +++++++++--------------
 fs/xfs/libxfs/xfs_ag.h            |    2 +
 fs/xfs/libxfs/xfs_bmap.c          |   10 +++----
 fs/xfs/libxfs/xfs_bmap_btree.c    |    5 +--
 fs/xfs/libxfs/xfs_btree.c         |   53 +++++++++++++++----------------------
 fs/xfs/libxfs/xfs_btree.h         |   28 ++++++--------------
 fs/xfs/libxfs/xfs_btree_staging.c |    5 +--
 fs/xfs/scrub/xfbtree.c            |    8 +-----
 8 files changed, 53 insertions(+), 91 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 6274c8222f76a..16bdebf5bedb1 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -473,7 +473,7 @@ xfs_btroot_init(
 	struct xfs_buf		*bp,
 	struct aghdr_init_data	*id)
 {
-	xfs_btree_init_block(mp, bp, id->type, 0, 0, id->agno);
+	xfs_btree_init_block(mp, bp, id->bc_ops, 0, 0, id->agno);
 }
 
 /* Finish initializing a free space btree. */
@@ -531,7 +531,7 @@ xfs_freesp_init_recs(
 }
 
 /*
- * Alloc btree root block init functions
+ * bnobt/cntbt btree root block init functions
  */
 static void
 xfs_bnoroot_init(
@@ -539,17 +539,7 @@ xfs_bnoroot_init(
 	struct xfs_buf		*bp,
 	struct aghdr_init_data	*id)
 {
-	xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 0, id->agno);
-	xfs_freesp_init_recs(mp, bp, id);
-}
-
-static void
-xfs_cntroot_init(
-	struct xfs_mount	*mp,
-	struct xfs_buf		*bp,
-	struct aghdr_init_data	*id)
-{
-	xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 0, id->agno);
+	xfs_btree_init_block(mp, bp, id->bc_ops, 0, 0, id->agno);
 	xfs_freesp_init_recs(mp, bp, id);
 }
 
@@ -565,7 +555,7 @@ xfs_rmaproot_init(
 	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
 	struct xfs_rmap_rec	*rrec;
 
-	xfs_btree_init_block(mp, bp, XFS_BTNUM_RMAP, 0, 4, id->agno);
+	xfs_btree_init_block(mp, bp, id->bc_ops, 0, 4, id->agno);
 
 	/*
 	 * mark the AG header regions as static metadata The BNO
@@ -778,7 +768,7 @@ struct xfs_aghdr_grow_data {
 	size_t			numblks;
 	const struct xfs_buf_ops *ops;
 	aghdr_init_work_f	work;
-	xfs_btnum_t		type;
+	const struct xfs_btree_ops *bc_ops;
 	bool			need_init;
 };
 
@@ -832,13 +822,15 @@ xfs_ag_init_headers(
 		.numblks = BTOBB(mp->m_sb.sb_blocksize),
 		.ops = &xfs_bnobt_buf_ops,
 		.work = &xfs_bnoroot_init,
+		.bc_ops = &xfs_bnobt_ops,
 		.need_init = true
 	},
 	{ /* CNT root block */
 		.daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_CNT_BLOCK(mp)),
 		.numblks = BTOBB(mp->m_sb.sb_blocksize),
 		.ops = &xfs_cntbt_buf_ops,
-		.work = &xfs_cntroot_init,
+		.work = &xfs_bnoroot_init,
+		.bc_ops = &xfs_cntbt_ops,
 		.need_init = true
 	},
 	{ /* INO root block */
@@ -846,7 +838,7 @@ xfs_ag_init_headers(
 		.numblks = BTOBB(mp->m_sb.sb_blocksize),
 		.ops = &xfs_inobt_buf_ops,
 		.work = &xfs_btroot_init,
-		.type = XFS_BTNUM_INO,
+		.bc_ops = &xfs_inobt_ops,
 		.need_init = true
 	},
 	{ /* FINO root block */
@@ -854,7 +846,7 @@ xfs_ag_init_headers(
 		.numblks = BTOBB(mp->m_sb.sb_blocksize),
 		.ops = &xfs_finobt_buf_ops,
 		.work = &xfs_btroot_init,
-		.type = XFS_BTNUM_FINO,
+		.bc_ops = &xfs_finobt_ops,
 		.need_init =  xfs_has_finobt(mp)
 	},
 	{ /* RMAP root block */
@@ -862,6 +854,7 @@ xfs_ag_init_headers(
 		.numblks = BTOBB(mp->m_sb.sb_blocksize),
 		.ops = &xfs_rmapbt_buf_ops,
 		.work = &xfs_rmaproot_init,
+		.bc_ops = &xfs_rmapbt_ops,
 		.need_init = xfs_has_rmapbt(mp)
 	},
 	{ /* REFC root block */
@@ -869,7 +862,7 @@ xfs_ag_init_headers(
 		.numblks = BTOBB(mp->m_sb.sb_blocksize),
 		.ops = &xfs_refcountbt_buf_ops,
 		.work = &xfs_btroot_init,
-		.type = XFS_BTNUM_REFC,
+		.bc_ops = &xfs_refcountbt_ops,
 		.need_init = xfs_has_reflink(mp)
 	},
 	{ /* NULL terminating block */
@@ -887,7 +880,7 @@ xfs_ag_init_headers(
 
 		id->daddr = dp->daddr;
 		id->numblks = dp->numblks;
-		id->type = dp->type;
+		id->bc_ops = dp->bc_ops;
 		error = xfs_ag_init_hdr(mp, id, dp->work, dp->ops);
 		if (error)
 			break;
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 06506e09a82d5..79017fcd3df58 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -330,7 +330,7 @@ struct aghdr_init_data {
 	/* per header data */
 	xfs_daddr_t		daddr;		/* header location */
 	size_t			numblks;	/* size of header */
-	xfs_btnum_t		type;		/* type of btree root block */
+	const struct xfs_btree_ops *bc_ops;	/* btree ops */
 };
 
 int xfs_ag_init_headers(struct xfs_mount *mp, struct aghdr_init_data *id);
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 46ab108825754..d77ee22bcaed8 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -644,9 +644,8 @@ xfs_bmap_extents_to_btree(
 	 * Fill in the root.
 	 */
 	block = ifp->if_broot;
-	xfs_btree_init_block_int(mp, block, XFS_BUF_DADDR_NULL,
-				 XFS_BTNUM_BMAP, 1, 1, ip->i_ino,
-				 XFS_BTREE_LONG_PTRS);
+	xfs_btree_init_block_int(mp, block, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL,
+			1, 1, ip->i_ino);
 	/*
 	 * Need a cursor.  Can't allocate until bb_level is filled in.
 	 */
@@ -691,9 +690,8 @@ xfs_bmap_extents_to_btree(
 	 */
 	abp->b_ops = &xfs_bmbt_buf_ops;
 	ablock = XFS_BUF_TO_BLOCK(abp);
-	xfs_btree_init_block_int(mp, ablock, xfs_buf_daddr(abp),
-				XFS_BTNUM_BMAP, 0, 0, ip->i_ino,
-				XFS_BTREE_LONG_PTRS);
+	xfs_btree_init_block_int(mp, ablock, &xfs_bmbt_ops, xfs_buf_daddr(abp),
+			0, 0, ip->i_ino);
 
 	for_each_xfs_iext(ifp, &icur, &rec) {
 		if (isnullstartblock(rec.br_startblock))
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 5777c51a0c01d..e241b88db4b01 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -44,9 +44,8 @@ xfs_bmdr_to_bmbt(
 	xfs_bmbt_key_t		*tkp;
 	__be64			*tpp;
 
-	xfs_btree_init_block_int(mp, rblock, XFS_BUF_DADDR_NULL,
-				 XFS_BTNUM_BMAP, 0, 0, ip->i_ino,
-				 XFS_BTREE_LONG_PTRS);
+	xfs_btree_init_block_int(mp, rblock, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL,
+			0, 0, ip->i_ino);
 	rblock->bb_level = dblock->bb_level;
 	ASSERT(be16_to_cpu(rblock->bb_level) > 0);
 	rblock->bb_numrecs = dblock->bb_numrecs;
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index dbd048bc1e8e0..bb2a7473fe052 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -35,24 +35,17 @@
 /*
  * Btree magic numbers.
  */
-static const uint32_t xfs_magics[2][XFS_BTNUM_MAX] = {
-	{ XFS_ABTB_MAGIC, XFS_ABTC_MAGIC, 0, XFS_BMAP_MAGIC, XFS_IBT_MAGIC,
-	  XFS_FIBT_MAGIC, 0 },
-	{ XFS_ABTB_CRC_MAGIC, XFS_ABTC_CRC_MAGIC, XFS_RMAP_CRC_MAGIC,
-	  XFS_BMAP_CRC_MAGIC, XFS_IBT_CRC_MAGIC, XFS_FIBT_CRC_MAGIC,
-	  XFS_REFC_CRC_MAGIC }
-};
-
 uint32_t
 xfs_btree_magic(
-	int			crc,
-	xfs_btnum_t		btnum)
+	struct xfs_mount		*mp,
+	const struct xfs_btree_ops	*ops)
 {
-	uint32_t		magic = xfs_magics[crc][btnum];
+	int				idx = xfs_has_crc(mp) ? 1 : 0;
+	__be32				magic = ops->buf_ops->magic[idx];
 
 	/* Ensure we asked for crc for crc-only magics. */
 	ASSERT(magic != 0);
-	return magic;
+	return be32_to_cpu(magic);
 }
 
 /*
@@ -137,7 +130,6 @@ __xfs_btree_check_lblock(
 	struct xfs_buf		*bp)
 {
 	struct xfs_mount	*mp = cur->bc_mp;
-	xfs_btnum_t		btnum = cur->bc_btnum;
 	int			crc = xfs_has_crc(mp);
 	xfs_failaddr_t		fa;
 	xfs_fsblock_t		fsb = NULLFSBLOCK;
@@ -152,7 +144,7 @@ __xfs_btree_check_lblock(
 			return __this_address;
 	}
 
-	if (be32_to_cpu(block->bb_magic) != xfs_btree_magic(crc, btnum))
+	if (be32_to_cpu(block->bb_magic) != xfs_btree_magic(mp, cur->bc_ops))
 		return __this_address;
 	if (be16_to_cpu(block->bb_level) != level)
 		return __this_address;
@@ -208,7 +200,6 @@ __xfs_btree_check_sblock(
 {
 	struct xfs_mount	*mp = cur->bc_mp;
 	struct xfs_perag	*pag = cur->bc_ag.pag;
-	xfs_btnum_t		btnum = cur->bc_btnum;
 	int			crc = xfs_has_crc(mp);
 	xfs_failaddr_t		fa;
 	xfs_agblock_t		agbno = NULLAGBLOCK;
@@ -221,7 +212,7 @@ __xfs_btree_check_sblock(
 			return __this_address;
 	}
 
-	if (be32_to_cpu(block->bb_magic) != xfs_btree_magic(crc, btnum))
+	if (be32_to_cpu(block->bb_magic) != xfs_btree_magic(mp, cur->bc_ops))
 		return __this_address;
 	if (be16_to_cpu(block->bb_level) != level)
 		return __this_address;
@@ -1225,21 +1216,20 @@ void
 xfs_btree_init_block_int(
 	struct xfs_mount	*mp,
 	struct xfs_btree_block	*buf,
+	const struct xfs_btree_ops *ops,
 	xfs_daddr_t		blkno,
-	xfs_btnum_t		btnum,
 	__u16			level,
 	__u16			numrecs,
-	__u64			owner,
-	unsigned int		flags)
+	__u64			owner)
 {
 	int			crc = xfs_has_crc(mp);
-	__u32			magic = xfs_btree_magic(crc, btnum);
+	__u32			magic = xfs_btree_magic(mp, ops);
 
 	buf->bb_magic = cpu_to_be32(magic);
 	buf->bb_level = cpu_to_be16(level);
 	buf->bb_numrecs = cpu_to_be16(numrecs);
 
-	if (flags & XFS_BTREE_LONG_PTRS) {
+	if (ops->geom_flags & XFS_BTREE_LONG_PTRS) {
 		buf->bb_u.l.bb_leftsib = cpu_to_be64(NULLFSBLOCK);
 		buf->bb_u.l.bb_rightsib = cpu_to_be64(NULLFSBLOCK);
 		if (crc) {
@@ -1266,15 +1256,15 @@ xfs_btree_init_block_int(
 
 void
 xfs_btree_init_block(
-	struct xfs_mount *mp,
-	struct xfs_buf	*bp,
-	xfs_btnum_t	btnum,
-	__u16		level,
-	__u16		numrecs,
-	__u64		owner)
+	struct xfs_mount		*mp,
+	struct xfs_buf			*bp,
+	const struct xfs_btree_ops	*ops,
+	__u16				level,
+	__u16				numrecs,
+	__u64				owner)
 {
-	xfs_btree_init_block_int(mp, XFS_BUF_TO_BLOCK(bp), xfs_buf_daddr(bp),
-				 btnum, level, numrecs, owner, 0);
+	xfs_btree_init_block_int(mp, XFS_BUF_TO_BLOCK(bp), ops,
+			xfs_buf_daddr(bp), level, numrecs, owner);
 }
 
 void
@@ -1299,9 +1289,8 @@ xfs_btree_init_block_cur(
 	else
 		owner = cur->bc_ag.pag->pag_agno;
 
-	xfs_btree_init_block_int(cur->bc_mp, XFS_BUF_TO_BLOCK(bp),
-				xfs_buf_daddr(bp), cur->bc_btnum, level,
-				numrecs, owner, cur->bc_flags);
+	xfs_btree_init_block_int(cur->bc_mp, XFS_BUF_TO_BLOCK(bp), cur->bc_ops,
+			xfs_buf_daddr(bp), level, numrecs, owner);
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 2c2d5db94b1dc..4ee3f13625e47 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -63,7 +63,8 @@ union xfs_btree_rec {
 #define	XFS_BTNUM_RMAP	((xfs_btnum_t)XFS_BTNUM_RMAPi)
 #define	XFS_BTNUM_REFC	((xfs_btnum_t)XFS_BTNUM_REFCi)
 
-uint32_t xfs_btree_magic(int crc, xfs_btnum_t btnum);
+struct xfs_btree_ops;
+uint32_t xfs_btree_magic(struct xfs_mount *mp, const struct xfs_btree_ops *ops);
 
 /*
  * For logging record fields.
@@ -450,25 +451,12 @@ xfs_btree_reada_bufs(
 /*
  * Initialise a new btree block header
  */
-void
-xfs_btree_init_block(
-	struct xfs_mount *mp,
-	struct xfs_buf	*bp,
-	xfs_btnum_t	btnum,
-	__u16		level,
-	__u16		numrecs,
-	__u64		owner);
-
-void
-xfs_btree_init_block_int(
-	struct xfs_mount	*mp,
-	struct xfs_btree_block	*buf,
-	xfs_daddr_t		blkno,
-	xfs_btnum_t		btnum,
-	__u16			level,
-	__u16			numrecs,
-	__u64			owner,
-	unsigned int		flags);
+void xfs_btree_init_block(struct xfs_mount *mp, struct xfs_buf *bp,
+		const struct xfs_btree_ops *ops, __u16 level, __u16 numrecs,
+		__u64 owner);
+void xfs_btree_init_block_int(struct xfs_mount *mp,
+		struct xfs_btree_block *buf, const struct xfs_btree_ops *ops,
+		xfs_daddr_t blkno, __u16 level, __u16 numrecs, __u64 owner);
 
 /*
  * Common btree core entry points.
diff --git a/fs/xfs/libxfs/xfs_btree_staging.c b/fs/xfs/libxfs/xfs_btree_staging.c
index e276eba87cb19..8c43e8da93a55 100644
--- a/fs/xfs/libxfs/xfs_btree_staging.c
+++ b/fs/xfs/libxfs/xfs_btree_staging.c
@@ -411,9 +411,8 @@ xfs_btree_bload_prep_block(
 
 		/* Initialize it and send it out. */
 		xfs_btree_init_block_int(cur->bc_mp, ifp->if_broot,
-				XFS_BUF_DADDR_NULL, cur->bc_btnum, level,
-				nr_this_block, cur->bc_ino.ip->i_ino,
-				cur->bc_flags);
+				cur->bc_ops, XFS_BUF_DADDR_NULL, level,
+				nr_this_block, cur->bc_ino.ip->i_ino);
 
 		*bpp = NULL;
 		*blockp = ifp->if_broot;
diff --git a/fs/xfs/scrub/xfbtree.c b/fs/xfs/scrub/xfbtree.c
index c5ef0ea8cad22..2b41511c2a88c 100644
--- a/fs/xfs/scrub/xfbtree.c
+++ b/fs/xfs/scrub/xfbtree.c
@@ -437,10 +437,6 @@ xfbtree_init_leaf_block(
 	struct xfs_buf			*bp;
 	xfs_daddr_t			daddr;
 	int				error;
-	unsigned int			bc_flags = 0;
-
-	if (cfg->flags & XFBTREE_CREATE_LONG_PTRS)
-		bc_flags |= XFS_BTREE_LONG_PTRS;
 
 	daddr = xfo_to_daddr(XFBTREE_INIT_LEAF_BLOCK);
 	error = xfs_buf_get(xfbt->target, daddr, xfbtree_bbsize(), &bp);
@@ -450,8 +446,8 @@ xfbtree_init_leaf_block(
 	trace_xfbtree_create_root_buf(xfbt, bp);
 
 	bp->b_ops = cfg->btree_ops->buf_ops;
-	xfs_btree_init_block_int(mp, bp->b_addr, daddr, cfg->btnum, 0, 0,
-			cfg->owner, bc_flags);
+	xfs_btree_init_block_int(mp, bp->b_addr, cfg->btree_ops, daddr, 0, 0,
+			cfg->owner);
 	error = xfs_bwrite(bp);
 	xfs_buf_relse(bp);
 	if (error)

[PATCH 5/9] xfs: rename btree block/buffer init functions

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Rename xfs_btree_init_block_int to xfs_btree_init_block, and
xfs_btree_init_block to xfs_btree_init_buf so that the name suggests the
type that caller are supposed to pass in.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_ag.c            |    6 +++---
 fs/xfs/libxfs/xfs_bmap.c          |    6 +++---
 fs/xfs/libxfs/xfs_bmap_btree.c    |    2 +-
 fs/xfs/libxfs/xfs_btree.c         |    8 ++++----
 fs/xfs/libxfs/xfs_btree.h         |    4 ++--
 fs/xfs/libxfs/xfs_btree_staging.c |    2 +-
 fs/xfs/scrub/xfbtree.c            |    2 +-
 7 files changed, 15 insertions(+), 15 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 16bdebf5bedb1..77309a1ce12fb 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -473,7 +473,7 @@ xfs_btroot_init(
 	struct xfs_buf		*bp,
 	struct aghdr_init_data	*id)
 {
-	xfs_btree_init_block(mp, bp, id->bc_ops, 0, 0, id->agno);
+	xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 0, id->agno);
 }
 
 /* Finish initializing a free space btree. */
@@ -539,7 +539,7 @@ xfs_bnoroot_init(
 	struct xfs_buf		*bp,
 	struct aghdr_init_data	*id)
 {
-	xfs_btree_init_block(mp, bp, id->bc_ops, 0, 0, id->agno);
+	xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 0, id->agno);
 	xfs_freesp_init_recs(mp, bp, id);
 }
 
@@ -555,7 +555,7 @@ xfs_rmaproot_init(
 	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
 	struct xfs_rmap_rec	*rrec;
 
-	xfs_btree_init_block(mp, bp, id->bc_ops, 0, 4, id->agno);
+	xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 4, id->agno);
 
 	/*
 	 * mark the AG header regions as static metadata The BNO
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index d77ee22bcaed8..59cad8b79fb6d 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -644,8 +644,8 @@ xfs_bmap_extents_to_btree(
 	 * Fill in the root.
 	 */
 	block = ifp->if_broot;
-	xfs_btree_init_block_int(mp, block, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL,
-			1, 1, ip->i_ino);
+	xfs_btree_init_block(mp, block, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL, 1,
+			1, ip->i_ino);
 	/*
 	 * Need a cursor.  Can't allocate until bb_level is filled in.
 	 */
@@ -690,7 +690,7 @@ xfs_bmap_extents_to_btree(
 	 */
 	abp->b_ops = &xfs_bmbt_buf_ops;
 	ablock = XFS_BUF_TO_BLOCK(abp);
-	xfs_btree_init_block_int(mp, ablock, &xfs_bmbt_ops, xfs_buf_daddr(abp),
+	xfs_btree_init_block(mp, ablock, &xfs_bmbt_ops, xfs_buf_daddr(abp),
 			0, 0, ip->i_ino);
 
 	for_each_xfs_iext(ifp, &icur, &rec) {
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index e241b88db4b01..22ce7bf32b06a 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -44,7 +44,7 @@ xfs_bmdr_to_bmbt(
 	xfs_bmbt_key_t		*tkp;
 	__be64			*tpp;
 
-	xfs_btree_init_block_int(mp, rblock, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL,
+	xfs_btree_init_block(mp, rblock, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL,
 			0, 0, ip->i_ino);
 	rblock->bb_level = dblock->bb_level;
 	ASSERT(be16_to_cpu(rblock->bb_level) > 0);
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index bb2a7473fe052..742e24b24ba26 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -1213,7 +1213,7 @@ xfs_btree_set_sibling(
 }
 
 void
-xfs_btree_init_block_int(
+xfs_btree_init_block(
 	struct xfs_mount	*mp,
 	struct xfs_btree_block	*buf,
 	const struct xfs_btree_ops *ops,
@@ -1255,7 +1255,7 @@ xfs_btree_init_block_int(
 }
 
 void
-xfs_btree_init_block(
+xfs_btree_init_buf(
 	struct xfs_mount		*mp,
 	struct xfs_buf			*bp,
 	const struct xfs_btree_ops	*ops,
@@ -1263,7 +1263,7 @@ xfs_btree_init_block(
 	__u16				numrecs,
 	__u64				owner)
 {
-	xfs_btree_init_block_int(mp, XFS_BUF_TO_BLOCK(bp), ops,
+	xfs_btree_init_block(mp, XFS_BUF_TO_BLOCK(bp), ops,
 			xfs_buf_daddr(bp), level, numrecs, owner);
 }
 
@@ -1289,7 +1289,7 @@ xfs_btree_init_block_cur(
 	else
 		owner = cur->bc_ag.pag->pag_agno;
 
-	xfs_btree_init_block_int(cur->bc_mp, XFS_BUF_TO_BLOCK(bp), cur->bc_ops,
+	xfs_btree_init_block(cur->bc_mp, XFS_BUF_TO_BLOCK(bp), cur->bc_ops,
 			xfs_buf_daddr(bp), level, numrecs, owner);
 }
 
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 4ee3f13625e47..6a27c34e68c30 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -451,10 +451,10 @@ xfs_btree_reada_bufs(
 /*
  * Initialise a new btree block header
  */
-void xfs_btree_init_block(struct xfs_mount *mp, struct xfs_buf *bp,
+void xfs_btree_init_buf(struct xfs_mount *mp, struct xfs_buf *bp,
 		const struct xfs_btree_ops *ops, __u16 level, __u16 numrecs,
 		__u64 owner);
-void xfs_btree_init_block_int(struct xfs_mount *mp,
+void xfs_btree_init_block(struct xfs_mount *mp,
 		struct xfs_btree_block *buf, const struct xfs_btree_ops *ops,
 		xfs_daddr_t blkno, __u16 level, __u16 numrecs, __u64 owner);
 
diff --git a/fs/xfs/libxfs/xfs_btree_staging.c b/fs/xfs/libxfs/xfs_btree_staging.c
index 8c43e8da93a55..c4b628a606da7 100644
--- a/fs/xfs/libxfs/xfs_btree_staging.c
+++ b/fs/xfs/libxfs/xfs_btree_staging.c
@@ -410,7 +410,7 @@ xfs_btree_bload_prep_block(
 		ifp->if_broot_bytes = (int)new_size;
 
 		/* Initialize it and send it out. */
-		xfs_btree_init_block_int(cur->bc_mp, ifp->if_broot,
+		xfs_btree_init_block(cur->bc_mp, ifp->if_broot,
 				cur->bc_ops, XFS_BUF_DADDR_NULL, level,
 				nr_this_block, cur->bc_ino.ip->i_ino);
 
diff --git a/fs/xfs/scrub/xfbtree.c b/fs/xfs/scrub/xfbtree.c
index 2b41511c2a88c..e9445da09845f 100644
--- a/fs/xfs/scrub/xfbtree.c
+++ b/fs/xfs/scrub/xfbtree.c
@@ -446,7 +446,7 @@ xfbtree_init_leaf_block(
 	trace_xfbtree_create_root_buf(xfbt, bp);
 
 	bp->b_ops = cfg->btree_ops->buf_ops;
-	xfs_btree_init_block_int(mp, bp->b_addr, cfg->btree_ops, daddr, 0, 0,
+	xfs_btree_init_block(mp, bp->b_addr, cfg->btree_ops, daddr, 0, 0,
 			cfg->owner);
 	error = xfs_bwrite(bp);
 	xfs_buf_relse(bp);

[PATCH 6/9] xfs: btree convert xfs_btree_init_block to xfs_btree_init_buf calls

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Convert any place we call xfs_btree_init_block with a buffer to use the
_init_buf function.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_bmap.c  |    3 +--
 fs/xfs/libxfs/xfs_btree.c |    3 +--
 fs/xfs/scrub/xfbtree.c    |    3 +--
 3 files changed, 3 insertions(+), 6 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 59cad8b79fb6d..75ab7d203c6de 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -690,8 +690,7 @@ xfs_bmap_extents_to_btree(
 	 */
 	abp->b_ops = &xfs_bmbt_buf_ops;
 	ablock = XFS_BUF_TO_BLOCK(abp);
-	xfs_btree_init_block(mp, ablock, &xfs_bmbt_ops, xfs_buf_daddr(abp),
-			0, 0, ip->i_ino);
+	xfs_btree_init_buf(mp, abp, &xfs_bmbt_ops, 0, 0, ip->i_ino);
 
 	for_each_xfs_iext(ifp, &icur, &rec) {
 		if (isnullstartblock(rec.br_startblock))
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 742e24b24ba26..0fdaacefe45e2 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -1289,8 +1289,7 @@ xfs_btree_init_block_cur(
 	else
 		owner = cur->bc_ag.pag->pag_agno;
 
-	xfs_btree_init_block(cur->bc_mp, XFS_BUF_TO_BLOCK(bp), cur->bc_ops,
-			xfs_buf_daddr(bp), level, numrecs, owner);
+	xfs_btree_init_buf(cur->bc_mp, bp, cur->bc_ops, level, numrecs, owner);
 }
 
 /*
diff --git a/fs/xfs/scrub/xfbtree.c b/fs/xfs/scrub/xfbtree.c
index e9445da09845f..f37f35c206354 100644
--- a/fs/xfs/scrub/xfbtree.c
+++ b/fs/xfs/scrub/xfbtree.c
@@ -446,8 +446,7 @@ xfbtree_init_leaf_block(
 	trace_xfbtree_create_root_buf(xfbt, bp);
 
 	bp->b_ops = cfg->btree_ops->buf_ops;
-	xfs_btree_init_block(mp, bp->b_addr, cfg->btree_ops, daddr, 0, 0,
-			cfg->owner);
+	xfs_btree_init_buf(mp, bp, cfg->btree_ops, 0, 0, cfg->owner);
 	error = xfs_bwrite(bp);
 	xfs_buf_relse(bp);
 	if (error)

[PATCH 7/9] xfs: remove the unnecessary daddr paramter to _init_block

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Now that all of the callers pass XFS_BUF_DADDR_NULL as the daddr
parameter, we can elide that too.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_bmap.c          |    3 +--
 fs/xfs/libxfs/xfs_bmap_btree.c    |    3 +--
 fs/xfs/libxfs/xfs_btree.c         |   19 ++++++++++++++++---
 fs/xfs/libxfs/xfs_btree.h         |    2 +-
 fs/xfs/libxfs/xfs_btree_staging.c |    5 ++---
 5 files changed, 21 insertions(+), 11 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 75ab7d203c6de..17a2194ac0486 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -644,8 +644,7 @@ xfs_bmap_extents_to_btree(
 	 * Fill in the root.
 	 */
 	block = ifp->if_broot;
-	xfs_btree_init_block(mp, block, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL, 1,
-			1, ip->i_ino);
+	xfs_btree_init_block(mp, block, &xfs_bmbt_ops, 1, 1, ip->i_ino);
 	/*
 	 * Need a cursor.  Can't allocate until bb_level is filled in.
 	 */
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 22ce7bf32b06a..54e0a47169487 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -44,8 +44,7 @@ xfs_bmdr_to_bmbt(
 	xfs_bmbt_key_t		*tkp;
 	__be64			*tpp;
 
-	xfs_btree_init_block(mp, rblock, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL,
-			0, 0, ip->i_ino);
+	xfs_btree_init_block(mp, rblock, &xfs_bmbt_ops, 0, 0, ip->i_ino);
 	rblock->bb_level = dblock->bb_level;
 	ASSERT(be16_to_cpu(rblock->bb_level) > 0);
 	rblock->bb_numrecs = dblock->bb_numrecs;
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 0fdaacefe45e2..285dc609daa8d 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -1212,8 +1212,8 @@ xfs_btree_set_sibling(
 	}
 }
 
-void
-xfs_btree_init_block(
+static void
+__xfs_btree_init_block(
 	struct xfs_mount	*mp,
 	struct xfs_btree_block	*buf,
 	const struct xfs_btree_ops *ops,
@@ -1254,6 +1254,19 @@ xfs_btree_init_block(
 	}
 }
 
+void
+xfs_btree_init_block(
+	struct xfs_mount	*mp,
+	struct xfs_btree_block	*block,
+	const struct xfs_btree_ops *ops,
+	__u16			level,
+	__u16			numrecs,
+	__u64			owner)
+{
+	__xfs_btree_init_block(mp, block, ops, XFS_BUF_DADDR_NULL, level,
+			numrecs, owner);
+}
+
 void
 xfs_btree_init_buf(
 	struct xfs_mount		*mp,
@@ -1263,7 +1276,7 @@ xfs_btree_init_buf(
 	__u16				numrecs,
 	__u64				owner)
 {
-	xfs_btree_init_block(mp, XFS_BUF_TO_BLOCK(bp), ops,
+	__xfs_btree_init_block(mp, XFS_BUF_TO_BLOCK(bp), ops,
 			xfs_buf_daddr(bp), level, numrecs, owner);
 }
 
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 6a27c34e68c30..41000bd6cccf7 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -456,7 +456,7 @@ void xfs_btree_init_buf(struct xfs_mount *mp, struct xfs_buf *bp,
 		__u64 owner);
 void xfs_btree_init_block(struct xfs_mount *mp,
 		struct xfs_btree_block *buf, const struct xfs_btree_ops *ops,
-		xfs_daddr_t blkno, __u16 level, __u16 numrecs, __u64 owner);
+		__u16 level, __u16 numrecs, __u64 owner);
 
 /*
  * Common btree core entry points.
diff --git a/fs/xfs/libxfs/xfs_btree_staging.c b/fs/xfs/libxfs/xfs_btree_staging.c
index c4b628a606da7..8f186ada630ba 100644
--- a/fs/xfs/libxfs/xfs_btree_staging.c
+++ b/fs/xfs/libxfs/xfs_btree_staging.c
@@ -410,9 +410,8 @@ xfs_btree_bload_prep_block(
 		ifp->if_broot_bytes = (int)new_size;
 
 		/* Initialize it and send it out. */
-		xfs_btree_init_block(cur->bc_mp, ifp->if_broot,
-				cur->bc_ops, XFS_BUF_DADDR_NULL, level,
-				nr_this_block, cur->bc_ino.ip->i_ino);
+		xfs_btree_init_block(cur->bc_mp, ifp->if_broot, cur->bc_ops,
+				level, nr_this_block, cur->bc_ino.ip->i_ino);
 
 		*bpp = NULL;
 		*blockp = ifp->if_broot;

[PATCH 8/9] xfs: set btree block buffer ops in _init_buf

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Set the btree block buffer ops in xfs_btree_init_buf since we already
have access to that information through the btree ops.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_bmap.c  |    1 -
 fs/xfs/libxfs/xfs_btree.c |    1 +
 fs/xfs/scrub/xfbtree.c    |    1 -
 3 files changed, 1 insertion(+), 2 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 17a2194ac0486..ae98f7e41ca7f 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -687,7 +687,6 @@ xfs_bmap_extents_to_btree(
 	/*
 	 * Fill in the child block.
 	 */
-	abp->b_ops = &xfs_bmbt_buf_ops;
 	ablock = XFS_BUF_TO_BLOCK(abp);
 	xfs_btree_init_buf(mp, abp, &xfs_bmbt_ops, 0, 0, ip->i_ino);
 
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 285dc609daa8d..5af19610d8919 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -1278,6 +1278,7 @@ xfs_btree_init_buf(
 {
 	__xfs_btree_init_block(mp, XFS_BUF_TO_BLOCK(bp), ops,
 			xfs_buf_daddr(bp), level, numrecs, owner);
+	bp->b_ops = ops->buf_ops;
 }
 
 void
diff --git a/fs/xfs/scrub/xfbtree.c b/fs/xfs/scrub/xfbtree.c
index f37f35c206354..9d2e01614d1ff 100644
--- a/fs/xfs/scrub/xfbtree.c
+++ b/fs/xfs/scrub/xfbtree.c
@@ -445,7 +445,6 @@ xfbtree_init_leaf_block(
 
 	trace_xfbtree_create_root_buf(xfbt, bp);
 
-	bp->b_ops = cfg->btree_ops->buf_ops;
 	xfs_btree_init_buf(mp, bp, cfg->btree_ops, 0, 0, cfg->owner);
 	error = xfs_bwrite(bp);
 	xfs_buf_relse(bp);

[PATCH 9/9] xfs: remove unnecessary fields in xfbtree_config

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Remove these fields now that we get all the info we need from the btree
ops.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_btree_mem.h  |    9 ---------
 fs/xfs/libxfs/xfs_rmap_btree.c |    1 -
 fs/xfs/scrub/trace.h           |   10 ++++------
 fs/xfs/scrub/xfbtree.c         |    4 ++--
 4 files changed, 6 insertions(+), 18 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_btree_mem.h b/fs/xfs/libxfs/xfs_btree_mem.h
index 29f97c5030465..1f961f3f55444 100644
--- a/fs/xfs/libxfs/xfs_btree_mem.h
+++ b/fs/xfs/libxfs/xfs_btree_mem.h
@@ -17,17 +17,8 @@ struct xfbtree_config {
 
 	/* Owner of this btree. */
 	unsigned long long		owner;
-
-	/* Btree type number */
-	xfs_btnum_t			btnum;
-
-	/* XFBTREE_CREATE_* flags */
-	unsigned int			flags;
 };
 
-/* btree has long pointers */
-#define XFBTREE_CREATE_LONG_PTRS	(1U << 0)
-
 #ifdef CONFIG_XFS_BTREE_IN_XFILE
 unsigned int xfs_btree_mem_head_nlevels(struct xfs_buf *head_bp);
 
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index f5889da0bff76..b4a8b4b62456b 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -669,7 +669,6 @@ xfs_rmapbt_mem_create(
 	struct xfbtree_config	cfg = {
 		.btree_ops	= &xfs_rmapbt_mem_ops,
 		.target		= target,
-		.btnum		= XFS_BTNUM_RMAP,
 		.owner		= agno,
 	};
 
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 06d593dcd697a..14bbefdd7ab81 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -2218,8 +2218,7 @@ TRACE_EVENT(xfbtree_create,
 		 struct xfbtree *xfbt),
 	TP_ARGS(mp, cfg, xfbt),
 	TP_STRUCT__entry(
-		__field(xfs_btnum_t, btnum)
-		__field(unsigned int, xfbtree_flags)
+		__field(const void *, btree_ops)
 		__field(unsigned long, xfino)
 		__field(unsigned int, leaf_mxr)
 		__field(unsigned int, leaf_mnr)
@@ -2228,8 +2227,7 @@ TRACE_EVENT(xfbtree_create,
 		__field(unsigned long long, owner)
 	),
 	TP_fast_assign(
-		__entry->btnum = cfg->btnum;
-		__entry->xfbtree_flags = cfg->flags;
+		__entry->btree_ops = cfg->btree_ops;
 		__entry->xfino = xfbtree_ino(xfbt);
 		__entry->leaf_mxr = xfbt->maxrecs[0];
 		__entry->node_mxr = xfbt->maxrecs[1];
@@ -2237,9 +2235,9 @@ TRACE_EVENT(xfbtree_create,
 		__entry->node_mnr = xfbt->minrecs[1];
 		__entry->owner = cfg->owner;
 	),
-	TP_printk("xfino 0x%lx btnum %s owner 0x%llx leaf_mxr %u leaf_mnr %u node_mxr %u node_mnr %u",
+	TP_printk("xfino 0x%lx btree_ops %pS owner 0x%llx leaf_mxr %u leaf_mnr %u node_mxr %u node_mnr %u",
 		  __entry->xfino,
-		  __print_symbolic(__entry->btnum, XFS_BTNUM_STRINGS),
+		  __entry->btree_ops,
 		  __entry->owner,
 		  __entry->leaf_mxr,
 		  __entry->leaf_mnr,
diff --git a/fs/xfs/scrub/xfbtree.c b/fs/xfs/scrub/xfbtree.c
index 9d2e01614d1ff..016026947019a 100644
--- a/fs/xfs/scrub/xfbtree.c
+++ b/fs/xfs/scrub/xfbtree.c
@@ -414,7 +414,7 @@ xfbtree_rec_bytes(
 {
 	unsigned int			blocklen = xfo_to_b(1);
 
-	if (cfg->flags & XFBTREE_CREATE_LONG_PTRS) {
+	if (cfg->btree_ops->geom_flags & XFS_BTREE_LONG_PTRS) {
 		if (xfs_has_crc(mp))
 			return blocklen - XFS_BTREE_LBLOCK_CRC_LEN;
 
@@ -504,7 +504,7 @@ xfbtree_create(
 	xfboff_bitmap_init(&xfbt->freespace);
 
 	/* Set up min/maxrecs for this btree. */
-	if (cfg->flags & XFBTREE_CREATE_LONG_PTRS)
+	if (cfg->btree_ops->geom_flags & XFS_BTREE_LONG_PTRS)
 		keyptr_len += sizeof(__be64);
 	else
 		keyptr_len += sizeof(__be32);

[PATCH 1/4] xfs: move lru refs to the btree ops structure

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Move the btree buffer LRU refcount to the btree ops structure so that we
can eliminate the last bc_btnum switch in the generic btree code.  We're
about to create repair-specific btree types, and we don't want that
stuff cluttering up libxfs.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_alloc_btree.c    |    2 ++
 fs/xfs/libxfs/xfs_bmap_btree.c     |    1 +
 fs/xfs/libxfs/xfs_btree.c          |   24 ++----------------------
 fs/xfs/libxfs/xfs_btree.h          |    3 +++
 fs/xfs/libxfs/xfs_ialloc_btree.c   |    2 ++
 fs/xfs/libxfs/xfs_refcount_btree.c |    1 +
 fs/xfs/libxfs/xfs_rmap_btree.c     |    2 ++
 7 files changed, 13 insertions(+), 22 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index 08aa92f574334..fd769e62cc35b 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -457,6 +457,7 @@ xfs_allocbt_keys_contiguous(
 const struct xfs_btree_ops xfs_bnobt_ops = {
 	.rec_len		= sizeof(xfs_alloc_rec_t),
 	.key_len		= sizeof(xfs_alloc_key_t),
+	.lru_refs		= XFS_ALLOC_BTREE_REF,
 
 	.dup_cursor		= xfs_allocbt_dup_cursor,
 	.set_root		= xfs_allocbt_set_root,
@@ -480,6 +481,7 @@ const struct xfs_btree_ops xfs_bnobt_ops = {
 const struct xfs_btree_ops xfs_cntbt_ops = {
 	.rec_len		= sizeof(xfs_alloc_rec_t),
 	.key_len		= sizeof(xfs_alloc_key_t),
+	.lru_refs		= XFS_ALLOC_BTREE_REF,
 	.geom_flags		= XFS_BTREE_LASTREC_UPDATE,
 
 	.dup_cursor		= xfs_allocbt_dup_cursor,
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 54e0a47169487..fd5fb8abf4448 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -516,6 +516,7 @@ xfs_bmbt_keys_contiguous(
 const struct xfs_btree_ops xfs_bmbt_ops = {
 	.rec_len		= sizeof(xfs_bmbt_rec_t),
 	.key_len		= sizeof(xfs_bmbt_key_t),
+	.lru_refs		= XFS_BMAP_BTREE_REF,
 	.geom_flags		= XFS_BTREE_LONG_PTRS | XFS_BTREE_ROOT_IN_INODE,
 
 	.dup_cursor		= xfs_bmbt_dup_cursor,
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 5af19610d8919..4c8e9dd25b739 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -1350,32 +1350,12 @@ xfs_btree_buf_to_ptr(
 	}
 }
 
-STATIC void
+static inline void
 xfs_btree_set_refs(
 	struct xfs_btree_cur	*cur,
 	struct xfs_buf		*bp)
 {
-	switch (cur->bc_btnum) {
-	case XFS_BTNUM_BNO:
-	case XFS_BTNUM_CNT:
-		xfs_buf_set_ref(bp, XFS_ALLOC_BTREE_REF);
-		break;
-	case XFS_BTNUM_INO:
-	case XFS_BTNUM_FINO:
-		xfs_buf_set_ref(bp, XFS_INO_BTREE_REF);
-		break;
-	case XFS_BTNUM_BMAP:
-		xfs_buf_set_ref(bp, XFS_BMAP_BTREE_REF);
-		break;
-	case XFS_BTNUM_RMAP:
-		xfs_buf_set_ref(bp, XFS_RMAP_BTREE_REF);
-		break;
-	case XFS_BTNUM_REFC:
-		xfs_buf_set_ref(bp, XFS_REFC_BTREE_REF);
-		break;
-	default:
-		ASSERT(0);
-	}
+	xfs_buf_set_ref(bp, cur->bc_ops->lru_refs);
 }
 
 int
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 41000bd6cccf7..edbcd4f0e9888 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -120,6 +120,9 @@ struct xfs_btree_ops {
 	/* XFS_BTREE_* flags that determine the geometry of the btree */
 	unsigned int	geom_flags;
 
+	/* LRU refcount to set on each btree buffer created */
+	int	lru_refs;
+
 	/* cursor operations */
 	struct xfs_btree_cur *(*dup_cursor)(struct xfs_btree_cur *);
 	void	(*update_cursor)(struct xfs_btree_cur *src,
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 69086fdc3be6f..cdb1f99970724 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -401,6 +401,7 @@ xfs_inobt_keys_contiguous(
 const struct xfs_btree_ops xfs_inobt_ops = {
 	.rec_len		= sizeof(xfs_inobt_rec_t),
 	.key_len		= sizeof(xfs_inobt_key_t),
+	.lru_refs		= XFS_INO_BTREE_REF,
 
 	.dup_cursor		= xfs_inobt_dup_cursor,
 	.set_root		= xfs_inobt_set_root,
@@ -423,6 +424,7 @@ const struct xfs_btree_ops xfs_inobt_ops = {
 const struct xfs_btree_ops xfs_finobt_ops = {
 	.rec_len		= sizeof(xfs_inobt_rec_t),
 	.key_len		= sizeof(xfs_inobt_key_t),
+	.lru_refs		= XFS_INO_BTREE_REF,
 
 	.dup_cursor		= xfs_inobt_dup_cursor,
 	.set_root		= xfs_finobt_set_root,
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 36e7b26d5e3b2..06a2f062b58cb 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -320,6 +320,7 @@ xfs_refcountbt_keys_contiguous(
 const struct xfs_btree_ops xfs_refcountbt_ops = {
 	.rec_len		= sizeof(struct xfs_refcount_rec),
 	.key_len		= sizeof(struct xfs_refcount_key),
+	.lru_refs		= XFS_REFC_BTREE_REF,
 
 	.dup_cursor		= xfs_refcountbt_dup_cursor,
 	.set_root		= xfs_refcountbt_set_root,
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index b4a8b4b62456b..23841ee6e2ff6 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -489,6 +489,7 @@ xfs_rmapbt_keys_contiguous(
 const struct xfs_btree_ops xfs_rmapbt_ops = {
 	.rec_len		= sizeof(struct xfs_rmap_rec),
 	.key_len		= 2 * sizeof(struct xfs_rmap_key),
+	.lru_refs		= XFS_RMAP_BTREE_REF,
 	.geom_flags		= XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING,
 
 	.dup_cursor		= xfs_rmapbt_dup_cursor,
@@ -613,6 +614,7 @@ static const struct xfs_buf_ops xfs_rmapbt_mem_buf_ops = {
 static const struct xfs_btree_ops xfs_rmapbt_mem_ops = {
 	.rec_len		= sizeof(struct xfs_rmap_rec),
 	.key_len		= 2 * sizeof(struct xfs_rmap_key),
+	.lru_refs		= XFS_RMAP_BTREE_REF,
 	.geom_flags		= XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING |
 				  XFS_BTREE_IN_XFILE,
 

[PATCH 2/4] xfs: define an in-memory btree for storing refcount bag info during repairs

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a new in-memory btree type so that we can store refcount bag info
in a much more memory-efficient format.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Makefile            |    1 
 fs/xfs/libxfs/xfs_btree.h  |    1 
 fs/xfs/libxfs/xfs_types.h  |    6 +
 fs/xfs/scrub/rcbag_btree.c |  314 ++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/rcbag_btree.h |   76 +++++++++++
 fs/xfs/scrub/trace.h       |    1 
 fs/xfs/xfs_trace.h         |    1 
 7 files changed, 398 insertions(+), 2 deletions(-)
 create mode 100644 fs/xfs/scrub/rcbag_btree.c
 create mode 100644 fs/xfs/scrub/rcbag_btree.h


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index dfa142eb16f46..f927a43cc16a5 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -198,6 +198,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   inode_repair.o \
 				   newbt.o \
 				   nlinks_repair.o \
+				   rcbag_btree.o \
 				   reap.o \
 				   refcount_repair.o \
 				   repair.o \
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index edbcd4f0e9888..339b5561e5b04 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -62,6 +62,7 @@ union xfs_btree_rec {
 #define	XFS_BTNUM_FINO	((xfs_btnum_t)XFS_BTNUM_FINOi)
 #define	XFS_BTNUM_RMAP	((xfs_btnum_t)XFS_BTNUM_RMAPi)
 #define	XFS_BTNUM_REFC	((xfs_btnum_t)XFS_BTNUM_REFCi)
+#define	XFS_BTNUM_RCBAG	((xfs_btnum_t)XFS_BTNUM_RCBAGi)
 
 struct xfs_btree_ops;
 uint32_t xfs_btree_magic(struct xfs_mount *mp, const struct xfs_btree_ops *ops);
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index 035bf703d719a..5556615a2ff9c 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -121,7 +121,8 @@ typedef enum {
  */
 typedef enum {
 	XFS_BTNUM_BNOi, XFS_BTNUM_CNTi, XFS_BTNUM_RMAPi, XFS_BTNUM_BMAPi,
-	XFS_BTNUM_INOi, XFS_BTNUM_FINOi, XFS_BTNUM_REFCi, XFS_BTNUM_MAX
+	XFS_BTNUM_INOi, XFS_BTNUM_FINOi, XFS_BTNUM_REFCi, XFS_BTNUM_RCBAGi,
+	XFS_BTNUM_MAX
 } xfs_btnum_t;
 
 #define XFS_BTNUM_STRINGS \
@@ -131,7 +132,8 @@ typedef enum {
 	{ XFS_BTNUM_BMAPi,	"bmbt" }, \
 	{ XFS_BTNUM_INOi,	"inobt" }, \
 	{ XFS_BTNUM_FINOi,	"finobt" }, \
-	{ XFS_BTNUM_REFCi,	"refcbt" }
+	{ XFS_BTNUM_REFCi,	"refcbt" }, \
+	{ XFS_BTNUM_RCBAGi,	"rcbagbt" }
 
 struct xfs_name {
 	const unsigned char	*name;
diff --git a/fs/xfs/scrub/rcbag_btree.c b/fs/xfs/scrub/rcbag_btree.c
new file mode 100644
index 0000000000000..4b0c849321b25
--- /dev/null
+++ b/fs/xfs/scrub/rcbag_btree.c
@@ -0,0 +1,314 @@
+// 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_defer.h"
+#include "xfs_btree.h"
+#include "xfs_btree_mem.h"
+#include "xfs_error.h"
+#include "scrub/xfile.h"
+#include "scrub/xfbtree.h"
+#include "scrub/rcbag_btree.h"
+#include "scrub/trace.h"
+
+static struct kmem_cache	*rcbagbt_cur_cache;
+
+STATIC void
+rcbagbt_init_key_from_rec(
+	union xfs_btree_key		*key,
+	const union xfs_btree_rec	*rec)
+{
+	struct rcbag_key	*bag_key = (struct rcbag_key *)key;
+	const struct rcbag_rec	*bag_rec = (const struct rcbag_rec *)rec;
+
+	BUILD_BUG_ON(sizeof(struct rcbag_key) > sizeof(union xfs_btree_key));
+	BUILD_BUG_ON(sizeof(struct rcbag_rec) > sizeof(union xfs_btree_rec));
+
+	bag_key->rbg_startblock = bag_rec->rbg_startblock;
+	bag_key->rbg_blockcount = bag_rec->rbg_blockcount;
+}
+
+STATIC void
+rcbagbt_init_rec_from_cur(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_rec	*rec)
+{
+	struct rcbag_rec	*bag_rec = (struct rcbag_rec *)rec;
+	struct rcbag_rec	*bag_irec = (struct rcbag_rec *)&cur->bc_rec;
+
+	bag_rec->rbg_startblock = bag_irec->rbg_startblock;
+	bag_rec->rbg_blockcount = bag_irec->rbg_blockcount;
+	bag_rec->rbg_refcount = bag_irec->rbg_refcount;
+}
+
+STATIC int64_t
+rcbagbt_key_diff(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_key	*key)
+{
+	struct rcbag_rec		*rec = (struct rcbag_rec *)&cur->bc_rec;
+	const struct rcbag_key		*kp = (const struct rcbag_key *)key;
+
+	if (kp->rbg_startblock > rec->rbg_startblock)
+		return 1;
+	if (kp->rbg_startblock < rec->rbg_startblock)
+		return -1;
+
+	if (kp->rbg_blockcount > rec->rbg_blockcount)
+		return 1;
+	if (kp->rbg_blockcount < rec->rbg_blockcount)
+		return -1;
+
+	return 0;
+}
+
+STATIC int64_t
+rcbagbt_diff_two_keys(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_key	*k1,
+	const union xfs_btree_key	*k2,
+	const union xfs_btree_key	*mask)
+{
+	const struct rcbag_key		*kp1 = (const struct rcbag_key *)k1;
+	const struct rcbag_key		*kp2 = (const struct rcbag_key *)k2;
+
+	ASSERT(mask == NULL);
+
+	if (kp1->rbg_startblock > kp2->rbg_startblock)
+		return 1;
+	if (kp1->rbg_startblock < kp2->rbg_startblock)
+		return -1;
+
+	if (kp1->rbg_blockcount > kp2->rbg_blockcount)
+		return 1;
+	if (kp1->rbg_blockcount < kp2->rbg_blockcount)
+		return -1;
+
+	return 0;
+}
+
+STATIC int
+rcbagbt_keys_inorder(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_key	*k1,
+	const union xfs_btree_key	*k2)
+{
+	const struct rcbag_key		*kp1 = (const struct rcbag_key *)k1;
+	const struct rcbag_key		*kp2 = (const struct rcbag_key *)k2;
+
+	if (kp1->rbg_startblock > kp2->rbg_startblock)
+		return 0;
+	if (kp1->rbg_startblock < kp2->rbg_startblock)
+		return 1;
+
+	if (kp1->rbg_blockcount > kp2->rbg_blockcount)
+		return 0;
+	if (kp1->rbg_blockcount < kp2->rbg_blockcount)
+		return 1;
+
+	return 0;
+}
+
+STATIC int
+rcbagbt_recs_inorder(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_rec	*r1,
+	const union xfs_btree_rec	*r2)
+{
+	const struct rcbag_rec		*rp1 = (const struct rcbag_rec *)r1;
+	const struct rcbag_rec		*rp2 = (const struct rcbag_rec *)r2;
+
+	if (rp1->rbg_startblock > rp2->rbg_startblock)
+		return 0;
+	if (rp1->rbg_startblock < rp2->rbg_startblock)
+		return 1;
+
+	if (rp1->rbg_blockcount > rp2->rbg_blockcount)
+		return 0;
+	if (rp1->rbg_blockcount < rp2->rbg_blockcount)
+		return 1;
+
+	return 0;
+}
+
+static xfs_failaddr_t
+rcbagbt_verify(
+	struct xfs_buf		*bp)
+{
+	struct xfs_mount	*mp = bp->b_mount;
+	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
+	xfs_failaddr_t		fa;
+	unsigned int		level;
+
+	if (!xfs_verify_magic(bp, block->bb_magic))
+		return __this_address;
+
+	fa = xfs_btree_lblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN);
+	if (fa)
+		return fa;
+
+	level = be16_to_cpu(block->bb_level);
+	if (level >= rcbagbt_maxlevels_possible())
+		return __this_address;
+
+	return xfbtree_lblock_verify(bp,
+			rcbagbt_maxrecs(mp, xfo_to_b(1), level == 0));
+}
+
+static void
+rcbagbt_rw_verify(
+	struct xfs_buf	*bp)
+{
+	xfs_failaddr_t	fa = rcbagbt_verify(bp);
+
+	if (fa)
+		xfs_verifier_error(bp, -EFSCORRUPTED, fa);
+}
+
+/* skip crc checks on in-memory btrees to save time */
+static const struct xfs_buf_ops rcbagbt_mem_buf_ops = {
+	.name			= "rcbagbt_mem",
+	.magic			= { 0, cpu_to_be32(RCBAG_MAGIC) },
+	.verify_read		= rcbagbt_rw_verify,
+	.verify_write		= rcbagbt_rw_verify,
+	.verify_struct		= rcbagbt_verify,
+};
+
+static const struct xfs_btree_ops rcbagbt_mem_ops = {
+	.rec_len		= sizeof(struct rcbag_rec),
+	.key_len		= sizeof(struct rcbag_key),
+	.lru_refs		= 1,
+	.geom_flags		= XFS_BTREE_CRC_BLOCKS | XFS_BTREE_LONG_PTRS |
+				  XFS_BTREE_IN_XFILE,
+
+	.dup_cursor		= xfbtree_dup_cursor,
+	.set_root		= xfbtree_set_root,
+	.alloc_block		= xfbtree_alloc_block,
+	.free_block		= xfbtree_free_block,
+	.get_minrecs		= xfbtree_get_minrecs,
+	.get_maxrecs		= xfbtree_get_maxrecs,
+	.init_key_from_rec	= rcbagbt_init_key_from_rec,
+	.init_rec_from_cur	= rcbagbt_init_rec_from_cur,
+	.init_ptr_from_cur	= xfbtree_init_ptr_from_cur,
+	.key_diff		= rcbagbt_key_diff,
+	.buf_ops		= &rcbagbt_mem_buf_ops,
+	.diff_two_keys		= rcbagbt_diff_two_keys,
+	.keys_inorder		= rcbagbt_keys_inorder,
+	.recs_inorder		= rcbagbt_recs_inorder,
+};
+
+/* Create a cursor for an in-memory btree. */
+struct xfs_btree_cur *
+rcbagbt_mem_cursor(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	struct xfs_buf		*head_bp,
+	struct xfbtree		*xfbtree)
+{
+	struct xfs_btree_cur	*cur;
+
+	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_RCBAG, &rcbagbt_mem_ops,
+			rcbagbt_maxlevels_possible(), rcbagbt_cur_cache);
+
+	cur->bc_mem.xfbtree = xfbtree;
+	cur->bc_mem.head_bp = head_bp;
+	cur->bc_nlevels = xfs_btree_mem_head_nlevels(head_bp);
+	return cur;
+}
+
+/* Create an in-memory refcount bag btree. */
+int
+rcbagbt_mem_create(
+	struct xfs_mount	*mp,
+	struct xfs_buftarg	*target,
+	struct xfbtree		**xfbtreep)
+{
+	struct xfbtree_config	cfg = {
+		.btree_ops	= &rcbagbt_mem_ops,
+		.target		= target,
+	};
+
+	return xfbtree_create(mp, &cfg, xfbtreep);
+}
+
+/* Calculate number of records in a refcount bag btree block. */
+static inline unsigned int
+rcbagbt_block_maxrecs(
+	unsigned int		blocklen,
+	bool			leaf)
+{
+	if (leaf)
+		return blocklen / sizeof(struct rcbag_rec);
+	return blocklen /
+		(sizeof(struct rcbag_key) + sizeof(rcbag_ptr_t));
+}
+
+/*
+ * Calculate number of records in an refcount bag btree block.
+ */
+unsigned int
+rcbagbt_maxrecs(
+	struct xfs_mount	*mp,
+	unsigned int		blocklen,
+	bool			leaf)
+{
+	blocklen -= RCBAG_BLOCK_LEN;
+	return rcbagbt_block_maxrecs(blocklen, leaf);
+}
+
+#define RCBAGBT_INIT_MINRECS(minrecs) \
+	do { \
+		unsigned int		blocklen; \
+\
+		blocklen = PAGE_SIZE - XFS_BTREE_LBLOCK_CRC_LEN; \
+\
+		minrecs[0] = rcbagbt_block_maxrecs(blocklen, true) / 2; \
+		minrecs[1] = rcbagbt_block_maxrecs(blocklen, false) / 2; \
+	} while (0)
+
+/* Compute the max possible height for refcount bag btrees. */
+unsigned int
+rcbagbt_maxlevels_possible(void)
+{
+	unsigned int		minrecs[2];
+
+	RCBAGBT_INIT_MINRECS(minrecs);
+	return xfs_btree_space_to_height(minrecs, ULLONG_MAX);
+}
+
+/* Calculate the refcount bag btree size for some records. */
+unsigned long long
+rcbagbt_calc_size(
+	unsigned long long	nr_records)
+{
+	unsigned int		minrecs[2];
+
+	RCBAGBT_INIT_MINRECS(minrecs);
+	return xfs_btree_calc_size(minrecs, nr_records);
+}
+
+int __init
+rcbagbt_init_cur_cache(void)
+{
+	rcbagbt_cur_cache = kmem_cache_create("xfs_rcbagbt_cur",
+			xfs_btree_cur_sizeof(rcbagbt_maxlevels_possible()),
+			0, 0, NULL);
+
+	if (!rcbagbt_cur_cache)
+		return -ENOMEM;
+	return 0;
+}
+
+void
+rcbagbt_destroy_cur_cache(void)
+{
+	kmem_cache_destroy(rcbagbt_cur_cache);
+	rcbagbt_cur_cache = NULL;
+}
diff --git a/fs/xfs/scrub/rcbag_btree.h b/fs/xfs/scrub/rcbag_btree.h
new file mode 100644
index 0000000000000..dfe276cfd96c1
--- /dev/null
+++ b/fs/xfs/scrub/rcbag_btree.h
@@ -0,0 +1,76 @@
+// 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_SCRUB_RCBAG_BTREE_H__
+#define __XFS_SCRUB_RCBAG_BTREE_H__
+
+#ifdef CONFIG_XFS_BTREE_IN_XFILE
+
+struct xfs_buf;
+struct xfs_btree_cur;
+struct xfs_mount;
+
+#define RCBAG_MAGIC	0x74826671	/* 'JRBG' */
+
+struct rcbag_key {
+	uint32_t	rbg_startblock;
+	uint32_t	rbg_blockcount;
+};
+
+struct rcbag_rec {
+	uint32_t	rbg_startblock;
+	uint32_t	rbg_blockcount;
+	uint64_t	rbg_refcount;
+};
+
+typedef __be64 rcbag_ptr_t;
+
+/* reflinks only exist on crc enabled filesystems */
+#define RCBAG_BLOCK_LEN	XFS_BTREE_LBLOCK_CRC_LEN
+
+/*
+ * Record, key, and pointer address macros for btree blocks.
+ *
+ * (note that some of these may appear unused, but they are used in userspace)
+ */
+#define RCBAG_REC_ADDR(block, index) \
+	((struct rcbag_rec *) \
+		((char *)(block) + RCBAG_BLOCK_LEN + \
+		 (((index) - 1) * sizeof(struct rcbag_rec))))
+
+#define RCBAG_KEY_ADDR(block, index) \
+	((struct rcbag_key *) \
+		((char *)(block) + RCBAG_BLOCK_LEN + \
+		 ((index) - 1) * sizeof(struct rcbag_key)))
+
+#define RCBAG_PTR_ADDR(block, index, maxrecs) \
+	((rcbag_ptr_t *) \
+		((char *)(block) + RCBAG_BLOCK_LEN + \
+		 (maxrecs) * sizeof(struct rcbag_key) + \
+		 ((index) - 1) * sizeof(rcbag_ptr_t)))
+
+unsigned int rcbagbt_maxrecs(struct xfs_mount *mp, unsigned int blocklen,
+		bool leaf);
+
+unsigned long long rcbagbt_calc_size(unsigned long long nr_records);
+
+unsigned int rcbagbt_maxlevels_possible(void);
+
+int __init rcbagbt_init_cur_cache(void);
+void rcbagbt_destroy_cur_cache(void);
+
+struct xfbtree;
+struct xfs_btree_cur *rcbagbt_mem_cursor(struct xfs_mount *mp,
+		struct xfs_trans *tp, struct xfs_buf *head_bp,
+		struct xfbtree *xfbtree);
+int rcbagbt_mem_create(struct xfs_mount *mp, struct xfs_buftarg *target,
+		struct xfbtree **xfbtreep);
+
+#else
+# define rcbagbt_init_cur_cache()		0
+# define rcbagbt_destroy_cur_cache()		((void)0)
+#endif /* CONFIG_XFS_BTREE_IN_XFILE */
+
+#endif /* __XFS_SCRUB_RCBAG_BTREE_H__ */
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 14bbefdd7ab81..e8f71179e1eab 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -42,6 +42,7 @@ TRACE_DEFINE_ENUM(XFS_BTNUM_INOi);
 TRACE_DEFINE_ENUM(XFS_BTNUM_FINOi);
 TRACE_DEFINE_ENUM(XFS_BTNUM_RMAPi);
 TRACE_DEFINE_ENUM(XFS_BTNUM_REFCi);
+TRACE_DEFINE_ENUM(XFS_BTNUM_RCBAGi);
 
 TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_SHARED);
 TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_COW);
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index ba3eed23533f0..1690f518ae74b 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -2458,6 +2458,7 @@ TRACE_DEFINE_ENUM(XFS_BTNUM_INOi);
 TRACE_DEFINE_ENUM(XFS_BTNUM_FINOi);
 TRACE_DEFINE_ENUM(XFS_BTNUM_RMAPi);
 TRACE_DEFINE_ENUM(XFS_BTNUM_REFCi);
+TRACE_DEFINE_ENUM(XFS_BTNUM_RCBAGi);
 
 DECLARE_EVENT_CLASS(xfs_btree_cur_class,
 	TP_PROTO(struct xfs_btree_cur *cur, int level, struct xfs_buf *bp),

[PATCH 3/4] xfs: create refcount bag structure for btree repairs

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a bag structure for refcount information that uses the refcount
bag btree defined in the previous patch.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Makefile            |    1 
 fs/xfs/scrub/rcbag.c       |  331 ++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/rcbag.h       |   28 ++++
 fs/xfs/scrub/rcbag_btree.c |   58 ++++++++
 fs/xfs/scrub/rcbag_btree.h |    7 +
 5 files changed, 425 insertions(+)
 create mode 100644 fs/xfs/scrub/rcbag.c
 create mode 100644 fs/xfs/scrub/rcbag.h


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index f927a43cc16a5..a76e98e94b64a 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -199,6 +199,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   newbt.o \
 				   nlinks_repair.o \
 				   rcbag_btree.o \
+				   rcbag.o \
 				   reap.o \
 				   refcount_repair.o \
 				   repair.o \
diff --git a/fs/xfs/scrub/rcbag.c b/fs/xfs/scrub/rcbag.c
new file mode 100644
index 0000000000000..63f1b6e6488e1
--- /dev/null
+++ b/fs/xfs/scrub/rcbag.c
@@ -0,0 +1,331 @@
+// 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_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_btree_mem.h"
+#include "xfs_error.h"
+#include "scrub/scrub.h"
+#include "scrub/xfile.h"
+#include "scrub/xfbtree.h"
+#include "scrub/rcbag_btree.h"
+#include "scrub/rcbag.h"
+#include "scrub/trace.h"
+
+struct rcbag {
+	struct xfs_mount	*mp;
+	struct xfbtree		*xfbtree;
+	uint64_t		nr_items;
+};
+
+int
+rcbag_init(
+	struct xfs_mount	*mp,
+	struct xfs_buftarg	*target,
+	struct rcbag		**bagp)
+{
+	struct rcbag		*bag;
+	int			error;
+
+	bag = kmalloc(sizeof(struct rcbag), XCHK_GFP_FLAGS);
+	if (!bag)
+		return -ENOMEM;
+
+	bag->nr_items = 0;
+	bag->mp = mp;
+
+	error = rcbagbt_mem_create(mp, target, &bag->xfbtree);
+	if (error)
+		goto out_bag;
+
+	*bagp = bag;
+	return 0;
+
+out_bag:
+	kfree(bag);
+	return error;
+}
+
+void
+rcbag_free(
+	struct rcbag		**bagp)
+{
+	struct rcbag		*bag = *bagp;
+
+	xfbtree_destroy(bag->xfbtree);
+	kfree(bag);
+	*bagp = NULL;
+}
+
+/* Track an rmap in the refcount bag. */
+int
+rcbag_add(
+	struct rcbag			*bag,
+	struct xfs_trans		*tp,
+	const struct xfs_rmap_irec	*rmap)
+{
+	struct rcbag_rec		bagrec;
+	struct xfs_mount		*mp = bag->mp;
+	struct xfs_buf			*head_bp;
+	struct xfs_btree_cur		*cur;
+	int				has;
+	int				error;
+
+	error = xfbtree_head_read_buf(bag->xfbtree, tp, &head_bp);
+	if (error)
+		return error;
+
+	cur = rcbagbt_mem_cursor(mp, tp, head_bp, bag->xfbtree);
+	error = rcbagbt_lookup_eq(cur, rmap, &has);
+	if (error)
+		goto out_cur;
+
+	if (has) {
+		error = rcbagbt_get_rec(cur, &bagrec, &has);
+		if (error)
+			goto out_cur;
+		if (!has) {
+			error = -EFSCORRUPTED;
+			goto out_cur;
+		}
+
+		bagrec.rbg_refcount++;
+		error = rcbagbt_update(cur, &bagrec);
+		if (error)
+			goto out_cur;
+	} else {
+		bagrec.rbg_startblock = rmap->rm_startblock;
+		bagrec.rbg_blockcount = rmap->rm_blockcount;
+		bagrec.rbg_refcount = 1;
+
+		error = rcbagbt_insert(cur, &bagrec, &has);
+		if (error)
+			goto out_cur;
+		if (!has) {
+			error = -EFSCORRUPTED;
+			goto out_cur;
+		}
+	}
+
+	xfs_btree_del_cursor(cur, 0);
+	xfs_trans_brelse(tp, head_bp);
+
+	error = xfbtree_trans_commit(bag->xfbtree, tp);
+	if (error)
+		return error;
+
+	bag->nr_items++;
+	return 0;
+
+out_cur:
+	xfs_btree_del_cursor(cur, error);
+	xfs_trans_brelse(tp, head_bp);
+	xfbtree_trans_cancel(bag->xfbtree, tp);
+	return error;
+}
+
+uint64_t
+rcbag_count(
+	const struct rcbag	*rcbag)
+{
+	return rcbag->nr_items;
+}
+
+#define BAGREC_NEXT(r)	((r)->rbg_startblock + (r)->rbg_blockcount)
+
+/*
+ * Find the next block where the refcount changes, given the next rmap we
+ * looked at and the ones we're already tracking.
+ */
+int
+rcbag_next_edge(
+	struct rcbag			*bag,
+	struct xfs_trans		*tp,
+	const struct xfs_rmap_irec	*next_rmap,
+	bool				next_valid,
+	uint32_t			*next_bnop)
+{
+	struct rcbag_rec		bagrec;
+	struct xfs_mount		*mp = bag->mp;
+	struct xfs_buf			*head_bp;
+	struct xfs_btree_cur		*cur;
+	uint32_t			next_bno = NULLAGBLOCK;
+	int				has;
+	int				error;
+
+	if (next_valid)
+		next_bno = next_rmap->rm_startblock;
+
+	error = xfbtree_head_read_buf(bag->xfbtree, tp, &head_bp);
+	if (error)
+		return error;
+
+	cur = rcbagbt_mem_cursor(mp, tp, head_bp, bag->xfbtree);
+	error = xfs_btree_goto_left_edge(cur);
+	if (error)
+		goto out_cur;
+
+	while (true) {
+		error = xfs_btree_increment(cur, 0, &has);
+		if (error)
+			goto out_cur;
+		if (!has)
+			break;
+
+		error = rcbagbt_get_rec(cur, &bagrec, &has);
+		if (error)
+			goto out_cur;
+		if (!has) {
+			error = -EFSCORRUPTED;
+			goto out_cur;
+		}
+
+		next_bno = min(next_bno, BAGREC_NEXT(&bagrec));
+	}
+
+	/*
+	 * We should have found /something/ because either next_rrm is the next
+	 * interesting rmap to look at after emitting this refcount extent, or
+	 * there are other rmaps in rmap_bag contributing to the current
+	 * sharing count.  But if something is seriously wrong, bail out.
+	 */
+	if (next_bno == NULLAGBLOCK) {
+		error = -EFSCORRUPTED;
+		goto out_cur;
+	}
+
+	xfs_btree_del_cursor(cur, 0);
+	xfs_trans_brelse(tp, head_bp);
+
+	*next_bnop = next_bno;
+	return 0;
+
+out_cur:
+	xfs_btree_del_cursor(cur, error);
+	xfs_trans_brelse(tp, head_bp);
+	return error;
+}
+
+/* Pop all refcount bag records that end at next_bno */
+int
+rcbag_remove_ending_at(
+	struct rcbag		*bag,
+	struct xfs_trans	*tp,
+	uint32_t		next_bno)
+{
+	struct rcbag_rec	bagrec;
+	struct xfs_mount	*mp = bag->mp;
+	struct xfs_buf		*head_bp;
+	struct xfs_btree_cur	*cur;
+	int			has;
+	int			error;
+
+	error = xfbtree_head_read_buf(bag->xfbtree, tp, &head_bp);
+	if (error)
+		return error;
+
+	/* go to the right edge of the tree */
+	cur = rcbagbt_mem_cursor(mp, tp, head_bp, bag->xfbtree);
+	memset(&cur->bc_rec, 0xFF, sizeof(cur->bc_rec));
+	error = xfs_btree_lookup(cur, XFS_LOOKUP_GE, &has);
+	if (error)
+		goto out_cur;
+
+	while (true) {
+		error = xfs_btree_decrement(cur, 0, &has);
+		if (error)
+			goto out_cur;
+		if (!has)
+			break;
+
+		error = rcbagbt_get_rec(cur, &bagrec, &has);
+		if (error)
+			goto out_cur;
+		if (!has) {
+			error = -EFSCORRUPTED;
+			goto out_cur;
+		}
+
+		if (BAGREC_NEXT(&bagrec) != next_bno)
+			continue;
+
+		error = xfs_btree_delete(cur, &has);
+		if (error)
+			goto out_cur;
+		if (!has) {
+			error = -EFSCORRUPTED;
+			goto out_cur;
+		}
+
+		bag->nr_items -= bagrec.rbg_refcount;
+	}
+
+	xfs_btree_del_cursor(cur, 0);
+	xfs_trans_brelse(tp, head_bp);
+	return xfbtree_trans_commit(bag->xfbtree, tp);
+out_cur:
+	xfs_btree_del_cursor(cur, error);
+	xfs_trans_brelse(tp, head_bp);
+	xfbtree_trans_cancel(bag->xfbtree, tp);
+	return error;
+}
+
+/* Dump the rcbag. */
+void
+rcbag_dump(
+	struct rcbag			*bag,
+	struct xfs_trans		*tp)
+{
+	struct rcbag_rec		bagrec;
+	struct xfs_mount		*mp = bag->mp;
+	struct xfs_buf			*head_bp;
+	struct xfs_btree_cur		*cur;
+	unsigned long long		nr = 0;
+	int				has;
+	int				error;
+
+	error = xfbtree_head_read_buf(bag->xfbtree, tp, &head_bp);
+	if (error)
+		return;
+
+	cur = rcbagbt_mem_cursor(mp, tp, head_bp, bag->xfbtree);
+	error = xfs_btree_goto_left_edge(cur);
+	if (error)
+		goto out_cur;
+
+	while (true) {
+		error = xfs_btree_increment(cur, 0, &has);
+		if (error)
+			goto out_cur;
+		if (!has)
+			break;
+
+		error = rcbagbt_get_rec(cur, &bagrec, &has);
+		if (error)
+			goto out_cur;
+		if (!has) {
+			error = -EFSCORRUPTED;
+			goto out_cur;
+		}
+
+		xfs_err(bag->mp, "[%llu]: bno 0x%x fsbcount 0x%x refcount 0x%llx\n",
+				nr++,
+				(unsigned int)bagrec.rbg_startblock,
+				(unsigned int)bagrec.rbg_blockcount,
+				(unsigned long long)bagrec.rbg_refcount);
+	}
+
+out_cur:
+	xfs_btree_del_cursor(cur, error);
+	xfs_trans_brelse(tp, head_bp);
+}
diff --git a/fs/xfs/scrub/rcbag.h b/fs/xfs/scrub/rcbag.h
new file mode 100644
index 0000000000000..08b6b85c09d6b
--- /dev/null
+++ b/fs/xfs/scrub/rcbag.h
@@ -0,0 +1,28 @@
+// 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_SCRUB_RCBAG_H__
+#define __XFS_SCRUB_RCBAG_H__
+
+struct xfs_mount;
+struct rcbag;
+struct xfs_buftarg;
+
+int rcbag_init(struct xfs_mount *mp, struct xfs_buftarg *target,
+		struct rcbag **bagp);
+void rcbag_free(struct rcbag **bagp);
+int rcbag_add(struct rcbag *bag, struct xfs_trans *tp,
+		const struct xfs_rmap_irec *rmap);
+uint64_t rcbag_count(const struct rcbag *bag);
+
+int rcbag_next_edge(struct rcbag *bag, struct xfs_trans *tp,
+		const struct xfs_rmap_irec *next_rmap, bool next_valid,
+		uint32_t *next_bnop);
+int rcbag_remove_ending_at(struct rcbag *bag, struct xfs_trans *tp,
+		uint32_t next_bno);
+
+void rcbag_dump(struct rcbag *bag, struct xfs_trans *tp);
+
+#endif /* __XFS_SCRUB_RCBAG_H__ */
diff --git a/fs/xfs/scrub/rcbag_btree.c b/fs/xfs/scrub/rcbag_btree.c
index 4b0c849321b25..3d66e80b7bc25 100644
--- a/fs/xfs/scrub/rcbag_btree.c
+++ b/fs/xfs/scrub/rcbag_btree.c
@@ -312,3 +312,61 @@ rcbagbt_destroy_cur_cache(void)
 	kmem_cache_destroy(rcbagbt_cur_cache);
 	rcbagbt_cur_cache = NULL;
 }
+
+/* Look up the refcount bag record corresponding to this reverse mapping. */
+int
+rcbagbt_lookup_eq(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*rmap,
+	int				*success)
+{
+	struct rcbag_rec		*rec = (struct rcbag_rec *)&cur->bc_rec;
+
+	rec->rbg_startblock = rmap->rm_startblock;
+	rec->rbg_blockcount = rmap->rm_blockcount;
+
+	return xfs_btree_lookup(cur, XFS_LOOKUP_EQ, success);
+}
+
+/* Get the data from the pointed-to record. */
+int
+rcbagbt_get_rec(
+	struct xfs_btree_cur	*cur,
+	struct rcbag_rec	*rec,
+	int			*has)
+{
+	union xfs_btree_rec	*btrec;
+	int			error;
+
+	error = xfs_btree_get_rec(cur, &btrec, has);
+	if (error || !(*has))
+		return error;
+
+	memcpy(rec, btrec, sizeof(struct rcbag_rec));
+	return 0;
+}
+
+/* Update the record referred to by cur to the value given. */
+int
+rcbagbt_update(
+	struct xfs_btree_cur	*cur,
+	const struct rcbag_rec	*rec)
+{
+	union xfs_btree_rec	btrec;
+
+	memcpy(&btrec, rec, sizeof(struct rcbag_rec));
+	return xfs_btree_update(cur, &btrec);
+}
+
+/* Update the record referred to by cur to the value given. */
+int
+rcbagbt_insert(
+	struct xfs_btree_cur	*cur,
+	const struct rcbag_rec	*rec,
+	int			*success)
+{
+	struct rcbag_rec	*btrec = (struct rcbag_rec *)&cur->bc_rec;
+
+	memcpy(btrec, rec, sizeof(struct rcbag_rec));
+	return xfs_btree_insert(cur, success);
+}
diff --git a/fs/xfs/scrub/rcbag_btree.h b/fs/xfs/scrub/rcbag_btree.h
index dfe276cfd96c1..6486b6ae53409 100644
--- a/fs/xfs/scrub/rcbag_btree.h
+++ b/fs/xfs/scrub/rcbag_btree.h
@@ -68,6 +68,13 @@ struct xfs_btree_cur *rcbagbt_mem_cursor(struct xfs_mount *mp,
 int rcbagbt_mem_create(struct xfs_mount *mp, struct xfs_buftarg *target,
 		struct xfbtree **xfbtreep);
 
+int rcbagbt_lookup_eq(struct xfs_btree_cur *cur,
+		const struct xfs_rmap_irec *rmap, int *success);
+int rcbagbt_get_rec(struct xfs_btree_cur *cur, struct rcbag_rec *rec, int *has);
+int rcbagbt_update(struct xfs_btree_cur *cur, const struct rcbag_rec *rec);
+int rcbagbt_insert(struct xfs_btree_cur *cur, const struct rcbag_rec *rec,
+		int *success);
+
 #else
 # define rcbagbt_init_cur_cache()		0
 # define rcbagbt_destroy_cur_cache()		((void)0)

[PATCH 4/4] xfs: port refcount repair to the new refcount bag structure

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Port the refcount record generating code to use the new refcount bag
data structure.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/refcount.c        |   12 +++
 fs/xfs/scrub/refcount_repair.c |  164 ++++++++++++++--------------------------
 fs/xfs/scrub/repair.h          |    2 
 fs/xfs/xfs_super.c             |   10 ++
 4 files changed, 81 insertions(+), 107 deletions(-)


diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index bf22f245bbfa8..d0c7d4a29c0fe 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -7,8 +7,10 @@
 #include "xfs_fs.h"
 #include "xfs_shared.h"
 #include "xfs_format.h"
+#include "xfs_log_format.h"
 #include "xfs_trans_resv.h"
 #include "xfs_mount.h"
+#include "xfs_trans.h"
 #include "xfs_ag.h"
 #include "xfs_btree.h"
 #include "xfs_rmap.h"
@@ -17,6 +19,7 @@
 #include "scrub/common.h"
 #include "scrub/btree.h"
 #include "scrub/trace.h"
+#include "scrub/repair.h"
 
 /*
  * Set us up to scrub reference count btrees.
@@ -27,6 +30,15 @@ xchk_setup_ag_refcountbt(
 {
 	if (xchk_need_intent_drain(sc))
 		xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN);
+
+	if (xchk_could_repair(sc)) {
+		int		error;
+
+		error = xrep_setup_ag_refcountbt(sc);
+		if (error)
+			return error;
+	}
+
 	return xchk_setup_ag_btree(sc, false);
 }
 
diff --git a/fs/xfs/scrub/refcount_repair.c b/fs/xfs/scrub/refcount_repair.c
index 9c39af03ee1d8..b485c5cc9f290 100644
--- a/fs/xfs/scrub/refcount_repair.c
+++ b/fs/xfs/scrub/refcount_repair.c
@@ -38,6 +38,7 @@
 #include "scrub/xfarray.h"
 #include "scrub/newbt.h"
 #include "scrub/reap.h"
+#include "scrub/rcbag.h"
 
 /*
  * Rebuilding the Reference Count Btree
@@ -98,12 +99,6 @@
  * insert all the records.
  */
 
-/* The only parts of the rmap that we care about for computing refcounts. */
-struct xrep_refc_rmap {
-	xfs_agblock_t		startblock;
-	xfs_extlen_t		blockcount;
-} __packed;
-
 struct xrep_refc {
 	/* refcount extents */
 	struct xfarray		*refcount_records;
@@ -123,6 +118,20 @@ struct xrep_refc {
 	xfs_extlen_t		btblocks;
 };
 
+/* Set us up to repair refcount btrees. */
+int
+xrep_setup_ag_refcountbt(
+	struct xfs_scrub	*sc)
+{
+	char			*descr;
+	int			error;
+
+	descr = xchk_xfile_ag_descr(sc, "rmap record bag");
+	error = xrep_setup_buftarg(sc, descr);
+	kfree(descr);
+	return error;
+}
+
 /* Check for any obvious conflicts with this shared/CoW staging extent. */
 STATIC int
 xrep_refc_check_ext(
@@ -224,10 +233,9 @@ xrep_refc_rmap_shareable(
 STATIC int
 xrep_refc_walk_rmaps(
 	struct xrep_refc	*rr,
-	struct xrep_refc_rmap	*rrm,
+	struct xfs_rmap_irec	*rmap,
 	bool			*have_rec)
 {
-	struct xfs_rmap_irec	rmap;
 	struct xfs_btree_cur	*cur = rr->sc->sa.rmap_cur;
 	struct xfs_mount	*mp = cur->bc_mp;
 	int			have_gt;
@@ -251,7 +259,7 @@ xrep_refc_walk_rmaps(
 		if (!have_gt)
 			return 0;
 
-		error = xfs_rmap_get_rec(cur, &rmap, &have_gt);
+		error = xfs_rmap_get_rec(cur, rmap, &have_gt);
 		if (error)
 			return error;
 		if (XFS_IS_CORRUPT(mp, !have_gt)) {
@@ -259,23 +267,22 @@ xrep_refc_walk_rmaps(
 			return -EFSCORRUPTED;
 		}
 
-		if (rmap.rm_owner == XFS_RMAP_OWN_COW) {
-			error = xrep_refc_stash_cow(rr, rmap.rm_startblock,
-					rmap.rm_blockcount);
+		if (rmap->rm_owner == XFS_RMAP_OWN_COW) {
+			error = xrep_refc_stash_cow(rr, rmap->rm_startblock,
+					rmap->rm_blockcount);
 			if (error)
 				return error;
-		} else if (rmap.rm_owner == XFS_RMAP_OWN_REFC) {
+		} else if (rmap->rm_owner == XFS_RMAP_OWN_REFC) {
 			/* refcountbt block, dump it when we're done. */
-			rr->btblocks += rmap.rm_blockcount;
+			rr->btblocks += rmap->rm_blockcount;
 			error = xagb_bitmap_set(&rr->old_refcountbt_blocks,
-					rmap.rm_startblock, rmap.rm_blockcount);
+					rmap->rm_startblock,
+					rmap->rm_blockcount);
 			if (error)
 				return error;
 		}
-	} while (!xrep_refc_rmap_shareable(mp, &rmap));
+	} while (!xrep_refc_rmap_shareable(mp, rmap));
 
-	rrm->startblock = rmap.rm_startblock;
-	rrm->blockcount = rmap.rm_blockcount;
 	*have_rec = true;
 	return 0;
 }
@@ -357,45 +364,6 @@ xrep_refc_sort_records(
 	return error;
 }
 
-#define RRM_NEXT(r)	((r).startblock + (r).blockcount)
-/*
- * Find the next block where the refcount changes, given the next rmap we
- * looked at and the ones we're already tracking.
- */
-static inline int
-xrep_refc_next_edge(
-	struct xfarray		*rmap_bag,
-	struct xrep_refc_rmap	*next_rrm,
-	bool			next_valid,
-	xfs_agblock_t		*nbnop)
-{
-	struct xrep_refc_rmap	rrm;
-	xfarray_idx_t		array_cur = XFARRAY_CURSOR_INIT;
-	xfs_agblock_t		nbno = NULLAGBLOCK;
-	int			error;
-
-	if (next_valid)
-		nbno = next_rrm->startblock;
-
-	while ((error = xfarray_iter(rmap_bag, &array_cur, &rrm)) == 1)
-		nbno = min_t(xfs_agblock_t, nbno, RRM_NEXT(rrm));
-
-	if (error)
-		return error;
-
-	/*
-	 * We should have found /something/ because either next_rrm is the next
-	 * interesting rmap to look at after emitting this refcount extent, or
-	 * there are other rmaps in rmap_bag contributing to the current
-	 * sharing count.  But if something is seriously wrong, bail out.
-	 */
-	if (nbno == NULLAGBLOCK)
-		return -EFSCORRUPTED;
-
-	*nbnop = nbno;
-	return 0;
-}
-
 /*
  * Walk forward through the rmap btree to collect all rmaps starting at
  * @bno in @rmap_bag.  These represent the file(s) that share ownership of
@@ -405,22 +373,21 @@ xrep_refc_next_edge(
 static int
 xrep_refc_push_rmaps_at(
 	struct xrep_refc	*rr,
-	struct xfarray		*rmap_bag,
+	struct rcbag		*rcstack,
 	xfs_agblock_t		bno,
-	struct xrep_refc_rmap	*rrm,
-	bool			*have,
-	uint64_t		*stack_sz)
+	struct xfs_rmap_irec	*rmap,
+	bool			*have)
 {
 	struct xfs_scrub	*sc = rr->sc;
 	int			have_gt;
 	int			error;
 
-	while (*have && rrm->startblock == bno) {
-		error = xfarray_store_anywhere(rmap_bag, rrm);
+	while (*have && rmap->rm_startblock == bno) {
+		error = rcbag_add(rcstack, rr->sc->tp, rmap);
 		if (error)
 			return error;
-		(*stack_sz)++;
-		error = xrep_refc_walk_rmaps(rr, rrm, have);
+
+		error = xrep_refc_walk_rmaps(rr, rmap, have);
 		if (error)
 			return error;
 	}
@@ -441,12 +408,9 @@ STATIC int
 xrep_refc_find_refcounts(
 	struct xrep_refc	*rr)
 {
-	struct xrep_refc_rmap	rrm;
 	struct xfs_scrub	*sc = rr->sc;
-	struct xfarray		*rmap_bag;
-	char			*descr;
-	uint64_t		old_stack_sz;
-	uint64_t		stack_sz = 0;
+	struct rcbag		*rcstack;
+	uint64_t		old_stack_height;
 	xfs_agblock_t		sbno;
 	xfs_agblock_t		cbno;
 	xfs_agblock_t		nbno;
@@ -456,14 +420,11 @@ xrep_refc_find_refcounts(
 	xrep_ag_btcur_init(sc, &sc->sa);
 
 	/*
-	 * Set up a sparse array to store all the rmap records that we're
-	 * tracking to generate a reference count record.  If this exceeds
+	 * Set up a bag to store all the rmap records that we're tracking to
+	 * generate a reference count record.  If the size of the bag exceeds
 	 * MAXREFCOUNT, we clamp rc_refcount.
 	 */
-	descr = xchk_xfile_ag_descr(sc, "rmap record bag");
-	error = xfarray_create(descr, 0, sizeof(struct xrep_refc_rmap),
-			&rmap_bag);
-	kfree(descr);
+	error = rcbag_init(sc->mp, sc->xfile_buftarg, &rcstack);
 	if (error)
 		goto out_cur;
 
@@ -474,62 +435,54 @@ xrep_refc_find_refcounts(
 
 	/* Process reverse mappings into refcount data. */
 	while (xfs_btree_has_more_records(sc->sa.rmap_cur)) {
+		struct xfs_rmap_irec	rmap;
+
 		/* Push all rmaps with pblk == sbno onto the stack */
-		error = xrep_refc_walk_rmaps(rr, &rrm, &have);
+		error = xrep_refc_walk_rmaps(rr, &rmap, &have);
 		if (error)
 			goto out_bag;
 		if (!have)
 			break;
-		sbno = cbno = rrm.startblock;
-		error = xrep_refc_push_rmaps_at(rr, rmap_bag, sbno,
-					&rrm, &have, &stack_sz);
+		sbno = cbno = rmap.rm_startblock;
+		error = xrep_refc_push_rmaps_at(rr, rcstack, sbno, &rmap,
+				&have);
 		if (error)
 			goto out_bag;
 
 		/* Set nbno to the bno of the next refcount change */
-		error = xrep_refc_next_edge(rmap_bag, &rrm, have, &nbno);
+		error = rcbag_next_edge(rcstack, sc->tp, &rmap, have, &nbno);
 		if (error)
 			goto out_bag;
 
 		ASSERT(nbno > sbno);
-		old_stack_sz = stack_sz;
+		old_stack_height = rcbag_count(rcstack);
 
 		/* While stack isn't empty... */
-		while (stack_sz) {
-			xfarray_idx_t	array_cur = XFARRAY_CURSOR_INIT;
-
+		while (rcbag_count(rcstack) > 0) {
 			/* Pop all rmaps that end at nbno */
-			while ((error = xfarray_iter(rmap_bag, &array_cur,
-								&rrm)) == 1) {
-				if (RRM_NEXT(rrm) != nbno)
-					continue;
-				error = xfarray_unset(rmap_bag, array_cur - 1);
-				if (error)
-					goto out_bag;
-				stack_sz--;
-			}
+			error = rcbag_remove_ending_at(rcstack, sc->tp, nbno);
 			if (error)
 				goto out_bag;
 
 			/* Push array items that start at nbno */
-			error = xrep_refc_walk_rmaps(rr, &rrm, &have);
+			error = xrep_refc_walk_rmaps(rr, &rmap, &have);
 			if (error)
 				goto out_bag;
 			if (have) {
-				error = xrep_refc_push_rmaps_at(rr, rmap_bag,
-						nbno, &rrm, &have, &stack_sz);
+				error = xrep_refc_push_rmaps_at(rr, rcstack,
+						nbno, &rmap, &have);
 				if (error)
 					goto out_bag;
 			}
 
 			/* Emit refcount if necessary */
 			ASSERT(nbno > cbno);
-			if (stack_sz != old_stack_sz) {
-				if (old_stack_sz > 1) {
+			if (rcbag_count(rcstack) != old_stack_height) {
+				if (old_stack_height > 1) {
 					error = xrep_refc_stash(rr,
 							XFS_REFC_DOMAIN_SHARED,
 							cbno, nbno - cbno,
-							old_stack_sz);
+							old_stack_height);
 					if (error)
 						goto out_bag;
 				}
@@ -537,13 +490,13 @@ xrep_refc_find_refcounts(
 			}
 
 			/* Stack empty, go find the next rmap */
-			if (stack_sz == 0)
+			if (rcbag_count(rcstack) == 0)
 				break;
-			old_stack_sz = stack_sz;
+			old_stack_height = rcbag_count(rcstack);
 			sbno = nbno;
 
 			/* Set nbno to the bno of the next refcount change */
-			error = xrep_refc_next_edge(rmap_bag, &rrm, have,
+			error = rcbag_next_edge(rcstack, sc->tp, &rmap, have,
 					&nbno);
 			if (error)
 				goto out_bag;
@@ -552,14 +505,13 @@ xrep_refc_find_refcounts(
 		}
 	}
 
-	ASSERT(stack_sz == 0);
+	ASSERT(rcbag_count(rcstack) == 0);
 out_bag:
-	xfarray_destroy(rmap_bag);
+	rcbag_free(&rcstack);
 out_cur:
 	xchk_ag_btcur_free(&sc->sa);
 	return error;
 }
-#undef RRM_NEXT
 
 /* Retrieve refcountbt data for bulk load. */
 STATIC int
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 0243481f770fe..38aa5c9649d71 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -89,6 +89,7 @@ int xrep_reset_perag_resv(struct xfs_scrub *sc);
 int xrep_bmap(struct xfs_scrub *sc, int whichfork, bool allow_unwritten);
 int xrep_metadata_inode_forks(struct xfs_scrub *sc);
 int xrep_setup_ag_rmapbt(struct xfs_scrub *sc);
+int xrep_setup_ag_refcountbt(struct xfs_scrub *sc);
 
 /* Repair setup functions */
 int xrep_setup_ag_allocbt(struct xfs_scrub *sc);
@@ -186,6 +187,7 @@ xrep_setup_nothing(
 }
 #define xrep_setup_ag_allocbt		xrep_setup_nothing
 #define xrep_setup_ag_rmapbt		xrep_setup_nothing
+#define xrep_setup_ag_refcountbt	xrep_setup_nothing
 
 #define xrep_setup_inode(sc, imap)	((void)0)
 
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 8619f517b1bf3..d535445129752 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -44,6 +44,7 @@
 #include "xfs_dahash_test.h"
 #include "xfs_rtbitmap.h"
 #include "scrub/stats.h"
+#include "scrub/rcbag_btree.h"
 
 #include <linux/magic.h>
 #include <linux/fs_context.h>
@@ -2069,10 +2070,14 @@ xfs_init_caches(void)
 	if (error)
 		goto out_destroy_log_ticket_cache;
 
-	error = xfs_defer_init_item_caches();
+	error = rcbagbt_init_cur_cache();
 	if (error)
 		goto out_destroy_btree_cur_cache;
 
+	error = xfs_defer_init_item_caches();
+	if (error)
+		goto out_destroy_rcbagbt_cur_cache;
+
 	xfs_da_state_cache = kmem_cache_create("xfs_da_state",
 					      sizeof(struct xfs_da_state),
 					      0, 0, NULL);
@@ -2229,6 +2234,8 @@ xfs_init_caches(void)
 	kmem_cache_destroy(xfs_da_state_cache);
  out_destroy_defer_item_cache:
 	xfs_defer_destroy_item_caches();
+ out_destroy_rcbagbt_cur_cache:
+	rcbagbt_destroy_cur_cache();
  out_destroy_btree_cur_cache:
 	xfs_btree_destroy_cur_caches();
  out_destroy_log_ticket_cache:
@@ -2266,6 +2273,7 @@ xfs_destroy_caches(void)
 	kmem_cache_destroy(xfs_ifork_cache);
 	kmem_cache_destroy(xfs_da_state_cache);
 	xfs_defer_destroy_item_caches();
+	rcbagbt_destroy_cur_cache();
 	xfs_btree_destroy_cur_caches();
 	kmem_cache_destroy(xfs_log_ticket_cache);
 	kmem_cache_destroy(xfs_buf_cache);

[PATCH 1/7] xfs: split tracepoint classes for deferred items

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

We're about to start adding support for deferred log intent items for
realtime extents, so split these four types into separate classes so
that we can customize them as the transition happens.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_trace.h |  273 ++++++++++++++++++++++++++++++++++------------------
 1 file changed, 177 insertions(+), 96 deletions(-)


diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 1690f518ae74b..fa829d1a8ecae 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -2658,94 +2658,6 @@ DEFINE_EVENT(xfs_defer_pending_class, name, \
 	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_pending *dfp), \
 	TP_ARGS(mp, dfp))
 
-DECLARE_EVENT_CLASS(xfs_phys_extent_deferred_class,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
-		 int type, xfs_agblock_t agbno, xfs_extlen_t len),
-	TP_ARGS(mp, agno, type, agbno, len),
-	TP_STRUCT__entry(
-		__field(dev_t, dev)
-		__field(xfs_agnumber_t, agno)
-		__field(int, type)
-		__field(xfs_agblock_t, agbno)
-		__field(xfs_extlen_t, len)
-	),
-	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
-		__entry->type = type;
-		__entry->agbno = agbno;
-		__entry->len = len;
-	),
-	TP_printk("dev %d:%d op %d agno 0x%x agbno 0x%x fsbcount 0x%x",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->type,
-		  __entry->agno,
-		  __entry->agbno,
-		  __entry->len)
-);
-#define DEFINE_PHYS_EXTENT_DEFERRED_EVENT(name) \
-DEFINE_EVENT(xfs_phys_extent_deferred_class, name, \
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
-		 int type, \
-		 xfs_agblock_t bno, \
-		 xfs_extlen_t len), \
-	TP_ARGS(mp, agno, type, bno, len))
-
-DECLARE_EVENT_CLASS(xfs_map_extent_deferred_class,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
-		 int op,
-		 xfs_agblock_t agbno,
-		 xfs_ino_t ino,
-		 int whichfork,
-		 xfs_fileoff_t offset,
-		 xfs_filblks_t len,
-		 xfs_exntst_t state),
-	TP_ARGS(mp, agno, op, agbno, ino, whichfork, offset, len, state),
-	TP_STRUCT__entry(
-		__field(dev_t, dev)
-		__field(xfs_agnumber_t, agno)
-		__field(xfs_ino_t, ino)
-		__field(xfs_agblock_t, agbno)
-		__field(int, whichfork)
-		__field(xfs_fileoff_t, l_loff)
-		__field(xfs_filblks_t, l_len)
-		__field(xfs_exntst_t, l_state)
-		__field(int, op)
-	),
-	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
-		__entry->ino = ino;
-		__entry->agbno = agbno;
-		__entry->whichfork = whichfork;
-		__entry->l_loff = offset;
-		__entry->l_len = len;
-		__entry->l_state = state;
-		__entry->op = op;
-	),
-	TP_printk("dev %d:%d op %d agno 0x%x agbno 0x%x owner 0x%llx %s fileoff 0x%llx fsbcount 0x%llx state %d",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->op,
-		  __entry->agno,
-		  __entry->agbno,
-		  __entry->ino,
-		  __print_symbolic(__entry->whichfork, XFS_WHICHFORK_STRINGS),
-		  __entry->l_loff,
-		  __entry->l_len,
-		  __entry->l_state)
-);
-#define DEFINE_MAP_EXTENT_DEFERRED_EVENT(name) \
-DEFINE_EVENT(xfs_map_extent_deferred_class, name, \
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
-		 int op, \
-		 xfs_agblock_t agbno, \
-		 xfs_ino_t ino, \
-		 int whichfork, \
-		 xfs_fileoff_t offset, \
-		 xfs_filblks_t len, \
-		 xfs_exntst_t state), \
-	TP_ARGS(mp, agno, op, agbno, ino, whichfork, offset, len, state))
-
 DEFINE_DEFER_EVENT(xfs_defer_cancel);
 DEFINE_DEFER_EVENT(xfs_defer_trans_roll);
 DEFINE_DEFER_EVENT(xfs_defer_trans_abort);
@@ -2764,11 +2676,42 @@ DEFINE_DEFER_PENDING_EVENT(xfs_defer_isolate_paused);
 DEFINE_DEFER_PENDING_EVENT(xfs_defer_item_pause);
 DEFINE_DEFER_PENDING_EVENT(xfs_defer_item_unpause);
 
-#define DEFINE_BMAP_FREE_DEFERRED_EVENT DEFINE_PHYS_EXTENT_DEFERRED_EVENT
-DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_bmap_free_defer);
-DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_bmap_free_deferred);
-DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_agfl_free_defer);
-DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_agfl_free_deferred);
+DECLARE_EVENT_CLASS(xfs_free_extent_deferred_class,
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+		 int type, xfs_agblock_t agbno, xfs_extlen_t len),
+	TP_ARGS(mp, agno, type, agbno, len),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(int, type)
+		__field(xfs_agblock_t, agbno)
+		__field(xfs_extlen_t, len)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->agno = agno;
+		__entry->type = type;
+		__entry->agbno = agbno;
+		__entry->len = len;
+	),
+	TP_printk("dev %d:%d op %d agno 0x%x agbno 0x%x fsbcount 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->type,
+		  __entry->agno,
+		  __entry->agbno,
+		  __entry->len)
+);
+#define DEFINE_FREE_EXTENT_DEFERRED_EVENT(name) \
+DEFINE_EVENT(xfs_free_extent_deferred_class, name, \
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
+		 int type, \
+		 xfs_agblock_t bno, \
+		 xfs_extlen_t len), \
+	TP_ARGS(mp, agno, type, bno, len))
+DEFINE_FREE_EXTENT_DEFERRED_EVENT(xfs_bmap_free_defer);
+DEFINE_FREE_EXTENT_DEFERRED_EVENT(xfs_bmap_free_deferred);
+DEFINE_FREE_EXTENT_DEFERRED_EVENT(xfs_agfl_free_defer);
+DEFINE_FREE_EXTENT_DEFERRED_EVENT(xfs_agfl_free_deferred);
 
 DECLARE_EVENT_CLASS(xfs_defer_pending_item_class,
 	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_pending *dfp,
@@ -2933,7 +2876,60 @@ DEFINE_EVENT(xfs_rmapbt_class, name, \
 		 uint64_t owner, uint64_t offset, unsigned int flags), \
 	TP_ARGS(mp, agno, agbno, len, owner, offset, flags))
 
-#define DEFINE_RMAP_DEFERRED_EVENT DEFINE_MAP_EXTENT_DEFERRED_EVENT
+DECLARE_EVENT_CLASS(xfs_rmap_deferred_class,
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+		 int op,
+		 xfs_agblock_t agbno,
+		 xfs_ino_t ino,
+		 int whichfork,
+		 xfs_fileoff_t offset,
+		 xfs_filblks_t len,
+		 xfs_exntst_t state),
+	TP_ARGS(mp, agno, op, agbno, ino, whichfork, offset, len, state),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_ino_t, ino)
+		__field(xfs_agblock_t, agbno)
+		__field(int, whichfork)
+		__field(xfs_fileoff_t, l_loff)
+		__field(xfs_filblks_t, l_len)
+		__field(xfs_exntst_t, l_state)
+		__field(int, op)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->agno = agno;
+		__entry->ino = ino;
+		__entry->agbno = agbno;
+		__entry->whichfork = whichfork;
+		__entry->l_loff = offset;
+		__entry->l_len = len;
+		__entry->l_state = state;
+		__entry->op = op;
+	),
+	TP_printk("dev %d:%d op %d agno 0x%x agbno 0x%x owner 0x%llx %s fileoff 0x%llx fsbcount 0x%llx state %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->op,
+		  __entry->agno,
+		  __entry->agbno,
+		  __entry->ino,
+		  __print_symbolic(__entry->whichfork, XFS_WHICHFORK_STRINGS),
+		  __entry->l_loff,
+		  __entry->l_len,
+		  __entry->l_state)
+);
+#define DEFINE_RMAP_DEFERRED_EVENT(name) \
+DEFINE_EVENT(xfs_rmap_deferred_class, name, \
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
+		 int op, \
+		 xfs_agblock_t agbno, \
+		 xfs_ino_t ino, \
+		 int whichfork, \
+		 xfs_fileoff_t offset, \
+		 xfs_filblks_t len, \
+		 xfs_exntst_t state), \
+	TP_ARGS(mp, agno, op, agbno, ino, whichfork, offset, len, state))
 DEFINE_RMAP_DEFERRED_EVENT(xfs_rmap_defer);
 DEFINE_RMAP_DEFERRED_EVENT(xfs_rmap_deferred);
 
@@ -2953,7 +2949,60 @@ DEFINE_RMAPBT_EVENT(xfs_rmap_find_right_neighbor_result);
 DEFINE_RMAPBT_EVENT(xfs_rmap_find_left_neighbor_result);
 
 /* deferred bmbt updates */
-#define DEFINE_BMAP_DEFERRED_EVENT	DEFINE_RMAP_DEFERRED_EVENT
+DECLARE_EVENT_CLASS(xfs_bmap_deferred_class,
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+		 int op,
+		 xfs_agblock_t agbno,
+		 xfs_ino_t ino,
+		 int whichfork,
+		 xfs_fileoff_t offset,
+		 xfs_filblks_t len,
+		 xfs_exntst_t state),
+	TP_ARGS(mp, agno, op, agbno, ino, whichfork, offset, len, state),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_ino_t, ino)
+		__field(xfs_agblock_t, agbno)
+		__field(int, whichfork)
+		__field(xfs_fileoff_t, l_loff)
+		__field(xfs_filblks_t, l_len)
+		__field(xfs_exntst_t, l_state)
+		__field(int, op)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->agno = agno;
+		__entry->ino = ino;
+		__entry->agbno = agbno;
+		__entry->whichfork = whichfork;
+		__entry->l_loff = offset;
+		__entry->l_len = len;
+		__entry->l_state = state;
+		__entry->op = op;
+	),
+	TP_printk("dev %d:%d op %d agno 0x%x agbno 0x%x owner 0x%llx %s fileoff 0x%llx fsbcount 0x%llx state %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->op,
+		  __entry->agno,
+		  __entry->agbno,
+		  __entry->ino,
+		  __print_symbolic(__entry->whichfork, XFS_WHICHFORK_STRINGS),
+		  __entry->l_loff,
+		  __entry->l_len,
+		  __entry->l_state)
+);
+#define DEFINE_BMAP_DEFERRED_EVENT(name) \
+DEFINE_EVENT(xfs_bmap_deferred_class, name, \
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
+		 int op, \
+		 xfs_agblock_t agbno, \
+		 xfs_ino_t ino, \
+		 int whichfork, \
+		 xfs_fileoff_t offset, \
+		 xfs_filblks_t len, \
+		 xfs_exntst_t state), \
+	TP_ARGS(mp, agno, op, agbno, ino, whichfork, offset, len, state))
 DEFINE_BMAP_DEFERRED_EVENT(xfs_bmap_defer);
 DEFINE_BMAP_DEFERRED_EVENT(xfs_bmap_deferred);
 
@@ -3330,7 +3379,39 @@ DEFINE_AG_ERROR_EVENT(xfs_refcount_find_right_extent_error);
 DEFINE_AG_EXTENT_EVENT(xfs_refcount_find_shared);
 DEFINE_AG_EXTENT_EVENT(xfs_refcount_find_shared_result);
 DEFINE_AG_ERROR_EVENT(xfs_refcount_find_shared_error);
-#define DEFINE_REFCOUNT_DEFERRED_EVENT DEFINE_PHYS_EXTENT_DEFERRED_EVENT
+
+DECLARE_EVENT_CLASS(xfs_refcount_deferred_class,
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+		 int type, xfs_agblock_t agbno, xfs_extlen_t len),
+	TP_ARGS(mp, agno, type, agbno, len),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(int, type)
+		__field(xfs_agblock_t, agbno)
+		__field(xfs_extlen_t, len)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->agno = agno;
+		__entry->type = type;
+		__entry->agbno = agbno;
+		__entry->len = len;
+	),
+	TP_printk("dev %d:%d op %d agno 0x%x agbno 0x%x fsbcount 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->type,
+		  __entry->agno,
+		  __entry->agbno,
+		  __entry->len)
+);
+#define DEFINE_REFCOUNT_DEFERRED_EVENT(name) \
+DEFINE_EVENT(xfs_refcount_deferred_class, name, \
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
+		 int type, \
+		 xfs_agblock_t bno, \
+		 xfs_extlen_t len), \
+	TP_ARGS(mp, agno, type, bno, len))
 DEFINE_REFCOUNT_DEFERRED_EVENT(xfs_refcount_defer);
 DEFINE_REFCOUNT_DEFERRED_EVENT(xfs_refcount_deferred);
 

[PATCH 2/7] xfs: clean up bmap log intent item tracepoint callsites

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Pass the incore bmap structure to the tracepoints instead of open-coding
the argument passing.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_bmap.c |   19 +++-------------
 fs/xfs/libxfs/xfs_bmap.h |    4 +++
 fs/xfs/xfs_trace.c       |    1 +
 fs/xfs/xfs_trace.h       |   54 ++++++++++++++++++++--------------------------
 4 files changed, 32 insertions(+), 46 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index ae98f7e41ca7f..0e506e83b4a62 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -6169,15 +6169,6 @@ __xfs_bmap_add(
 {
 	struct xfs_bmap_intent		*bi;
 
-	trace_xfs_bmap_defer(tp->t_mountp,
-			XFS_FSB_TO_AGNO(tp->t_mountp, bmap->br_startblock),
-			type,
-			XFS_FSB_TO_AGBNO(tp->t_mountp, bmap->br_startblock),
-			ip->i_ino, whichfork,
-			bmap->br_startoff,
-			bmap->br_blockcount,
-			bmap->br_state);
-
 	bi = kmem_cache_alloc(xfs_bmap_intent_cache, GFP_NOFS | __GFP_NOFAIL);
 	INIT_LIST_HEAD(&bi->bi_list);
 	bi->bi_type = type;
@@ -6185,6 +6176,8 @@ __xfs_bmap_add(
 	bi->bi_whichfork = whichfork;
 	bi->bi_bmap = *bmap;
 
+	trace_xfs_bmap_defer(bi);
+
 	xfs_bmap_update_get_group(tp->t_mountp, bi);
 	xfs_defer_add(tp, &bi->bi_list, &xfs_bmap_update_defer_type);
 	return 0;
@@ -6230,13 +6223,7 @@ xfs_bmap_finish_one(
 
 	ASSERT(tp->t_highest_agno == NULLAGNUMBER);
 
-	trace_xfs_bmap_deferred(tp->t_mountp,
-			XFS_FSB_TO_AGNO(tp->t_mountp, bmap->br_startblock),
-			bi->bi_type,
-			XFS_FSB_TO_AGBNO(tp->t_mountp, bmap->br_startblock),
-			bi->bi_owner->i_ino, bi->bi_whichfork,
-			bmap->br_startoff, bmap->br_blockcount,
-			bmap->br_state);
+	trace_xfs_bmap_deferred(bi);
 
 	if (WARN_ON_ONCE(bi->bi_whichfork != XFS_DATA_FORK)) {
 		xfs_bmap_mark_sick(bi->bi_owner, bi->bi_whichfork);
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 9dd631bc2dc72..b477f92c8508e 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -230,6 +230,10 @@ enum xfs_bmap_intent_type {
 	XFS_BMAP_UNMAP,
 };
 
+#define XFS_BMAP_INTENT_STRINGS \
+	{ XFS_BMAP_MAP,		"map" }, \
+	{ XFS_BMAP_UNMAP,	"unmap" }
+
 struct xfs_bmap_intent {
 	struct list_head			bi_list;
 	enum xfs_bmap_intent_type		bi_type;
diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c
index 2d49310fb9128..c9a5d8087b63c 100644
--- a/fs/xfs/xfs_trace.c
+++ b/fs/xfs/xfs_trace.c
@@ -39,6 +39,7 @@
 #include "scrub/xfile.h"
 #include "scrub/xfbtree.h"
 #include "xfs_btree_mem.h"
+#include "xfs_bmap.h"
 
 /*
  * We include this last to have the helpers above available for the trace
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index fa829d1a8ecae..52e54ec267cb8 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -78,6 +78,7 @@ union xfs_btree_ptr;
 struct xfs_dqtrx;
 struct xfs_icwalk;
 struct xfs_perag;
+struct xfs_bmap_intent;
 
 #define XFS_ATTR_FILTER_FLAGS \
 	{ XFS_ATTR_ROOT,	"ROOT" }, \
@@ -2949,16 +2950,12 @@ DEFINE_RMAPBT_EVENT(xfs_rmap_find_right_neighbor_result);
 DEFINE_RMAPBT_EVENT(xfs_rmap_find_left_neighbor_result);
 
 /* deferred bmbt updates */
+TRACE_DEFINE_ENUM(XFS_BMAP_MAP);
+TRACE_DEFINE_ENUM(XFS_BMAP_UNMAP);
+
 DECLARE_EVENT_CLASS(xfs_bmap_deferred_class,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
-		 int op,
-		 xfs_agblock_t agbno,
-		 xfs_ino_t ino,
-		 int whichfork,
-		 xfs_fileoff_t offset,
-		 xfs_filblks_t len,
-		 xfs_exntst_t state),
-	TP_ARGS(mp, agno, op, agbno, ino, whichfork, offset, len, state),
+	TP_PROTO(struct xfs_bmap_intent *bi),
+	TP_ARGS(bi),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
@@ -2971,22 +2968,26 @@ DECLARE_EVENT_CLASS(xfs_bmap_deferred_class,
 		__field(int, op)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
-		__entry->ino = ino;
-		__entry->agbno = agbno;
-		__entry->whichfork = whichfork;
-		__entry->l_loff = offset;
-		__entry->l_len = len;
-		__entry->l_state = state;
-		__entry->op = op;
+		struct xfs_inode	*ip = bi->bi_owner;
+
+		__entry->dev = ip->i_mount->m_super->s_dev;
+		__entry->agno = XFS_FSB_TO_AGNO(ip->i_mount,
+					bi->bi_bmap.br_startblock);
+		__entry->ino = ip->i_ino;
+		__entry->agbno = XFS_FSB_TO_AGBNO(ip->i_mount,
+					bi->bi_bmap.br_startblock);
+		__entry->whichfork = bi->bi_whichfork;
+		__entry->l_loff = bi->bi_bmap.br_startoff;
+		__entry->l_len = bi->bi_bmap.br_blockcount;
+		__entry->l_state = bi->bi_bmap.br_state;
+		__entry->op = bi->bi_type;
 	),
-	TP_printk("dev %d:%d op %d agno 0x%x agbno 0x%x owner 0x%llx %s fileoff 0x%llx fsbcount 0x%llx state %d",
+	TP_printk("dev %d:%d op %s ino 0x%llx agno 0x%x agbno 0x%x %s fileoff 0x%llx fsbcount 0x%llx state %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->op,
+		  __print_symbolic(__entry->op, XFS_BMAP_INTENT_STRINGS),
+		  __entry->ino,
 		  __entry->agno,
 		  __entry->agbno,
-		  __entry->ino,
 		  __print_symbolic(__entry->whichfork, XFS_WHICHFORK_STRINGS),
 		  __entry->l_loff,
 		  __entry->l_len,
@@ -2994,15 +2995,8 @@ DECLARE_EVENT_CLASS(xfs_bmap_deferred_class,
 );
 #define DEFINE_BMAP_DEFERRED_EVENT(name) \
 DEFINE_EVENT(xfs_bmap_deferred_class, name, \
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
-		 int op, \
-		 xfs_agblock_t agbno, \
-		 xfs_ino_t ino, \
-		 int whichfork, \
-		 xfs_fileoff_t offset, \
-		 xfs_filblks_t len, \
-		 xfs_exntst_t state), \
-	TP_ARGS(mp, agno, op, agbno, ino, whichfork, offset, len, state))
+	TP_PROTO(struct xfs_bmap_intent *bi), \
+	TP_ARGS(bi))
 DEFINE_BMAP_DEFERRED_EVENT(xfs_bmap_defer);
 DEFINE_BMAP_DEFERRED_EVENT(xfs_bmap_deferred);
 

[PATCH 3/7] xfs: remove xfs_trans_set_bmap_flags

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Remove this single-use helper.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_bmap_item.c |   38 +++++++++++++-------------------------
 1 file changed, 13 insertions(+), 25 deletions(-)


diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 52fb8a148b7dc..6faa9b9da95a3 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -236,29 +236,6 @@ xfs_bmap_update_diff_items(
 	return ba->bi_owner->i_ino - bb->bi_owner->i_ino;
 }
 
-/* Set the map extent flags for this mapping. */
-static void
-xfs_trans_set_bmap_flags(
-	struct xfs_map_extent		*map,
-	enum xfs_bmap_intent_type	type,
-	int				whichfork,
-	xfs_exntst_t			state)
-{
-	map->me_flags = 0;
-	switch (type) {
-	case XFS_BMAP_MAP:
-	case XFS_BMAP_UNMAP:
-		map->me_flags = type;
-		break;
-	default:
-		ASSERT(0);
-	}
-	if (state == XFS_EXT_UNWRITTEN)
-		map->me_flags |= XFS_BMAP_EXTENT_UNWRITTEN;
-	if (whichfork == XFS_ATTR_FORK)
-		map->me_flags |= XFS_BMAP_EXTENT_ATTR_FORK;
-}
-
 /* Log bmap updates in the intent item. */
 STATIC void
 xfs_bmap_update_log_item(
@@ -281,8 +258,19 @@ xfs_bmap_update_log_item(
 	map->me_startblock = bi->bi_bmap.br_startblock;
 	map->me_startoff = bi->bi_bmap.br_startoff;
 	map->me_len = bi->bi_bmap.br_blockcount;
-	xfs_trans_set_bmap_flags(map, bi->bi_type, bi->bi_whichfork,
-			bi->bi_bmap.br_state);
+
+	switch (bi->bi_type) {
+	case XFS_BMAP_MAP:
+	case XFS_BMAP_UNMAP:
+		map->me_flags = bi->bi_type;
+		break;
+	default:
+		ASSERT(0);
+	}
+	if (bi->bi_bmap.br_state == XFS_EXT_UNWRITTEN)
+		map->me_flags |= XFS_BMAP_EXTENT_UNWRITTEN;
+	if (bi->bi_whichfork == XFS_ATTR_FORK)
+		map->me_flags |= XFS_BMAP_EXTENT_ATTR_FORK;
 }
 
 static struct xfs_log_item *

[PATCH 4/7] xfs: add a bi_entry helper

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add a helper to translate from the item list head to the bmap_intent
structure and use it so shorten assignments and avoid the need for extra
local variables.

Inspired-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_bmap_item.c |   19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)


diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 6faa9b9da95a3..2a6afda6cb8ed 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -221,6 +221,11 @@ static const struct xfs_item_ops xfs_bud_item_ops = {
 	.iop_intent	= xfs_bud_item_intent,
 };
 
+static inline struct xfs_bmap_intent *bi_entry(const struct list_head *e)
+{
+	return list_entry(e, struct xfs_bmap_intent, bi_list);
+}
+
 /* Sort bmap intents by inode. */
 static int
 xfs_bmap_update_diff_items(
@@ -228,11 +233,9 @@ xfs_bmap_update_diff_items(
 	const struct list_head		*a,
 	const struct list_head		*b)
 {
-	struct xfs_bmap_intent		*ba;
-	struct xfs_bmap_intent		*bb;
+	struct xfs_bmap_intent		*ba = bi_entry(a);
+	struct xfs_bmap_intent		*bb = bi_entry(b);
 
-	ba = container_of(a, struct xfs_bmap_intent, bi_list);
-	bb = container_of(b, struct xfs_bmap_intent, bi_list);
 	return ba->bi_owner->i_ino - bb->bi_owner->i_ino;
 }
 
@@ -348,11 +351,9 @@ xfs_bmap_update_finish_item(
 	struct list_head		*item,
 	struct xfs_btree_cur		**state)
 {
-	struct xfs_bmap_intent		*bi;
+	struct xfs_bmap_intent		*bi = bi_entry(item);
 	int				error;
 
-	bi = container_of(item, struct xfs_bmap_intent, bi_list);
-
 	error = xfs_bmap_finish_one(tp, bi);
 	if (!error && bi->bi_bmap.br_blockcount > 0) {
 		ASSERT(bi->bi_type == XFS_BMAP_UNMAP);
@@ -377,9 +378,7 @@ STATIC void
 xfs_bmap_update_cancel_item(
 	struct list_head		*item)
 {
-	struct xfs_bmap_intent		*bi;
-
-	bi = container_of(item, struct xfs_bmap_intent, bi_list);
+	struct xfs_bmap_intent		*bi = bi_entry(item);
 
 	xfs_bmap_update_put_group(bi);
 	kmem_cache_free(xfs_bmap_intent_cache, bi);

[PATCH 5/7] xfs: reuse xfs_bmap_update_cancel_item

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Reuse xfs_bmap_update_cancel_item to put the AG/RTG and free the item in
a few places that currently open code the logic.

Inspired-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_bmap_item.c |   25 ++++++++++++-------------
 1 file changed, 12 insertions(+), 13 deletions(-)


diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 2a6afda6cb8ed..86c543282de73 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -343,6 +343,17 @@ xfs_bmap_update_put_group(
 	xfs_perag_intent_put(bi->bi_pag);
 }
 
+/* Cancel a deferred bmap update. */
+STATIC void
+xfs_bmap_update_cancel_item(
+	struct list_head		*item)
+{
+	struct xfs_bmap_intent		*bi = bi_entry(item);
+
+	xfs_bmap_update_put_group(bi);
+	kmem_cache_free(xfs_bmap_intent_cache, bi);
+}
+
 /* Process a deferred bmap update. */
 STATIC int
 xfs_bmap_update_finish_item(
@@ -360,8 +371,7 @@ xfs_bmap_update_finish_item(
 		return -EAGAIN;
 	}
 
-	xfs_bmap_update_put_group(bi);
-	kmem_cache_free(xfs_bmap_intent_cache, bi);
+	xfs_bmap_update_cancel_item(item);
 	return error;
 }
 
@@ -373,17 +383,6 @@ xfs_bmap_update_abort_intent(
 	xfs_bui_release(BUI_ITEM(intent));
 }
 
-/* Cancel a deferred bmap update. */
-STATIC void
-xfs_bmap_update_cancel_item(
-	struct list_head		*item)
-{
-	struct xfs_bmap_intent		*bi = bi_entry(item);
-
-	xfs_bmap_update_put_group(bi);
-	kmem_cache_free(xfs_bmap_intent_cache, bi);
-}
-
 /* Is this recovered BUI ok? */
 static inline bool
 xfs_bui_validate(

[PATCH 6/7] xfs: move xfs_bmap_defer_add to xfs_bmap_item.c

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Move the code that adds the incore xfs_bmap_item deferred work data to a
transaction live with the BUI log item code.  This means that the file
mapping code no longer has to know about the inner workings of the BUI
log items.

As a consequence, we can hide the _get_group helper.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_bmap.c |    6 ++----
 fs/xfs/libxfs/xfs_bmap.h |    3 ---
 fs/xfs/xfs_bmap_item.c   |   15 ++++++++++++++-
 fs/xfs/xfs_bmap_item.h   |    4 ++++
 4 files changed, 20 insertions(+), 8 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 0e506e83b4a62..3df6856cf4872 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -37,6 +37,7 @@
 #include "xfs_icache.h"
 #include "xfs_iomap.h"
 #include "xfs_health.h"
+#include "xfs_bmap_item.h"
 
 struct kmem_cache		*xfs_bmap_intent_cache;
 
@@ -6176,10 +6177,7 @@ __xfs_bmap_add(
 	bi->bi_whichfork = whichfork;
 	bi->bi_bmap = *bmap;
 
-	trace_xfs_bmap_defer(bi);
-
-	xfs_bmap_update_get_group(tp->t_mountp, bi);
-	xfs_defer_add(tp, &bi->bi_list, &xfs_bmap_update_defer_type);
+	xfs_bmap_defer_add(tp, bi);
 	return 0;
 }
 
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index b477f92c8508e..a5e37ef7b75d7 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -243,9 +243,6 @@ struct xfs_bmap_intent {
 	struct xfs_bmbt_irec			bi_bmap;
 };
 
-void xfs_bmap_update_get_group(struct xfs_mount *mp,
-		struct xfs_bmap_intent *bi);
-
 int	xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_bmap_intent *bi);
 void	xfs_bmap_map_extent(struct xfs_trans *tp, struct xfs_inode *ip,
 		struct xfs_bmbt_irec *imap);
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 86c543282de73..3315a38f35973 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -25,6 +25,7 @@
 #include "xfs_log_priv.h"
 #include "xfs_log_recover.h"
 #include "xfs_ag.h"
+#include "xfs_trace.h"
 
 struct kmem_cache	*xfs_bui_cache;
 struct kmem_cache	*xfs_bud_cache;
@@ -316,7 +317,7 @@ xfs_bmap_update_create_done(
 }
 
 /* Take a passive ref to the AG containing the space we're mapping. */
-void
+static inline void
 xfs_bmap_update_get_group(
 	struct xfs_mount	*mp,
 	struct xfs_bmap_intent	*bi)
@@ -335,6 +336,18 @@ xfs_bmap_update_get_group(
 	bi->bi_pag = xfs_perag_intent_get(mp, agno);
 }
 
+/* Add this deferred BUI to the transaction. */
+void
+xfs_bmap_defer_add(
+	struct xfs_trans	*tp,
+	struct xfs_bmap_intent	*bi)
+{
+	trace_xfs_bmap_defer(bi);
+
+	xfs_bmap_update_get_group(tp->t_mountp, bi);
+	xfs_defer_add(tp, &bi->bi_list, &xfs_bmap_update_defer_type);
+}
+
 /* Release a passive AG ref after finishing mapping work. */
 static inline void
 xfs_bmap_update_put_group(
diff --git a/fs/xfs/xfs_bmap_item.h b/fs/xfs/xfs_bmap_item.h
index 3fafd3881a0bb..6fee6a5083436 100644
--- a/fs/xfs/xfs_bmap_item.h
+++ b/fs/xfs/xfs_bmap_item.h
@@ -68,4 +68,8 @@ struct xfs_bud_log_item {
 extern struct kmem_cache	*xfs_bui_cache;
 extern struct kmem_cache	*xfs_bud_cache;
 
+struct xfs_bmap_intent;
+
+void xfs_bmap_defer_add(struct xfs_trans *tp, struct xfs_bmap_intent *bi);
+
 #endif	/* __XFS_BMAP_ITEM_H__ */

[PATCH 7/7] xfs: add a xattr_entry helper

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add a helper to translate from the item list head to the attr_intent
item structure and use it so shorten assignments and avoid the need for
extra local variables.

Inspired-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_attr_item.c |   11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)


diff --git a/fs/xfs/xfs_attr_item.c b/fs/xfs/xfs_attr_item.c
index 9e02111bd8901..f8c6c34e348f3 100644
--- a/fs/xfs/xfs_attr_item.c
+++ b/fs/xfs/xfs_attr_item.c
@@ -391,6 +391,11 @@ xfs_attr_free_item(
 		kmem_cache_free(xfs_attr_intent_cache, attr);
 }
 
+static inline struct xfs_attr_intent *attri_entry(const struct list_head *e)
+{
+	return list_entry(e, struct xfs_attr_intent, xattri_list);
+}
+
 /* Process an attr. */
 STATIC int
 xfs_attr_finish_item(
@@ -399,11 +404,10 @@ xfs_attr_finish_item(
 	struct list_head		*item,
 	struct xfs_btree_cur		**state)
 {
-	struct xfs_attr_intent		*attr;
+	struct xfs_attr_intent		*attr = attri_entry(item);
 	struct xfs_da_args		*args;
 	int				error;
 
-	attr = container_of(item, struct xfs_attr_intent, xattri_list);
 	args = attr->xattri_da_args;
 
 	/* Reset trans after EAGAIN cycle since the transaction is new */
@@ -443,9 +447,8 @@ STATIC void
 xfs_attr_cancel_item(
 	struct list_head		*item)
 {
-	struct xfs_attr_intent		*attr;
+	struct xfs_attr_intent		*attr = attri_entry(item);
 
-	attr = container_of(item, struct xfs_attr_intent, xattri_list);
 	xfs_attr_free_item(attr);
 }
 

[PATCH 1/3] xfs: fix xfs_bunmapi to allow unmapping of partial rt extents

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

When XFS_BMAPI_REMAP is passed to bunmapi, that means that we want to
remove part of a block mapping without touching the allocator.  For
realtime files with rtextsize > 1, that also means that we should skip
all the code that changes a partial remove request into an unwritten
extent conversion.  IOWs, bunmapi in this mode should handle removing
the mapping from the rt file and nothing else.

Note that XFS_BMAPI_REMAP callers are required to decrement the
reference count and/or free the space manually.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_bmap.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 3df6856cf4872..bf20267cf6378 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -5431,7 +5431,7 @@ __xfs_bunmapi(
 		if (del.br_startoff + del.br_blockcount > end + 1)
 			del.br_blockcount = end + 1 - del.br_startoff;
 
-		if (!isrt)
+		if (!isrt || (flags & XFS_BMAPI_REMAP))
 			goto delete;
 
 		mod = xfs_rtb_to_rtxoff(mp,
@@ -5449,7 +5449,7 @@ __xfs_bunmapi(
 				 * This piece is unwritten, or we're not
 				 * using unwritten extents.  Skip over it.
 				 */
-				ASSERT(end >= mod);
+				ASSERT((flags & XFS_BMAPI_REMAP) || end >= mod);
 				end -= mod > del.br_blockcount ?
 					del.br_blockcount : mod;
 				if (end < got.br_startoff &&

[PATCH 2/3] xfs: add a realtime flag to the bmap update log redo items

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Extend the bmap update (BUI) log items with a new realtime flag that
indicates that the updates apply against a realtime file's data fork.
We'll wire up the actual code later.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_log_format.h |    4 +++-
 fs/xfs/xfs_bmap_item.c         |    8 ++++++++
 fs/xfs/xfs_trace.h             |   23 ++++++++++++++++++-----
 3 files changed, 29 insertions(+), 6 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index 269573c828085..16872972e1e97 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -838,10 +838,12 @@ struct xfs_cud_log_format {
 
 #define XFS_BMAP_EXTENT_ATTR_FORK	(1U << 31)
 #define XFS_BMAP_EXTENT_UNWRITTEN	(1U << 30)
+#define XFS_BMAP_EXTENT_REALTIME	(1U << 29)
 
 #define XFS_BMAP_EXTENT_FLAGS		(XFS_BMAP_EXTENT_TYPE_MASK | \
 					 XFS_BMAP_EXTENT_ATTR_FORK | \
-					 XFS_BMAP_EXTENT_UNWRITTEN)
+					 XFS_BMAP_EXTENT_UNWRITTEN | \
+					 XFS_BMAP_EXTENT_REALTIME)
 
 /*
  * This is the structure used to lay out an bui log item in the
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 3315a38f35973..d19f82c367f2b 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -275,6 +275,8 @@ xfs_bmap_update_log_item(
 		map->me_flags |= XFS_BMAP_EXTENT_UNWRITTEN;
 	if (bi->bi_whichfork == XFS_ATTR_FORK)
 		map->me_flags |= XFS_BMAP_EXTENT_ATTR_FORK;
+	if (xfs_ifork_is_realtime(bi->bi_owner, bi->bi_whichfork))
+		map->me_flags |= XFS_BMAP_EXTENT_REALTIME;
 }
 
 static struct xfs_log_item *
@@ -324,6 +326,9 @@ xfs_bmap_update_get_group(
 {
 	xfs_agnumber_t		agno;
 
+	if (xfs_ifork_is_realtime(bi->bi_owner, bi->bi_whichfork))
+		return;
+
 	agno = XFS_FSB_TO_AGNO(mp, bi->bi_bmap.br_startblock);
 
 	/*
@@ -353,6 +358,9 @@ static inline void
 xfs_bmap_update_put_group(
 	struct xfs_bmap_intent	*bi)
 {
+	if (xfs_ifork_is_realtime(bi->bi_owner, bi->bi_whichfork))
+		return;
+
 	xfs_perag_intent_put(bi->bi_pag);
 }
 
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 52e54ec267cb8..a36b48432d093 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -2958,9 +2958,11 @@ DECLARE_EVENT_CLASS(xfs_bmap_deferred_class,
 	TP_ARGS(bi),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
+		__field(dev_t, opdev)
 		__field(xfs_agnumber_t, agno)
 		__field(xfs_ino_t, ino)
 		__field(xfs_agblock_t, agbno)
+		__field(xfs_fsblock_t, rtbno)
 		__field(int, whichfork)
 		__field(xfs_fileoff_t, l_loff)
 		__field(xfs_filblks_t, l_len)
@@ -2971,23 +2973,34 @@ DECLARE_EVENT_CLASS(xfs_bmap_deferred_class,
 		struct xfs_inode	*ip = bi->bi_owner;
 
 		__entry->dev = ip->i_mount->m_super->s_dev;
-		__entry->agno = XFS_FSB_TO_AGNO(ip->i_mount,
-					bi->bi_bmap.br_startblock);
+		if (xfs_ifork_is_realtime(ip, bi->bi_whichfork)) {
+			__entry->agno = 0;
+			__entry->agbno = 0;
+			__entry->rtbno = bi->bi_bmap.br_startblock;
+			__entry->opdev = ip->i_mount->m_rtdev_targp->bt_dev;
+		} else {
+			__entry->agno = XFS_FSB_TO_AGNO(ip->i_mount,
+						bi->bi_bmap.br_startblock);
+			__entry->agbno = XFS_FSB_TO_AGBNO(ip->i_mount,
+						bi->bi_bmap.br_startblock);
+			__entry->rtbno = 0;
+			__entry->opdev = __entry->dev;
+		}
 		__entry->ino = ip->i_ino;
-		__entry->agbno = XFS_FSB_TO_AGBNO(ip->i_mount,
-					bi->bi_bmap.br_startblock);
 		__entry->whichfork = bi->bi_whichfork;
 		__entry->l_loff = bi->bi_bmap.br_startoff;
 		__entry->l_len = bi->bi_bmap.br_blockcount;
 		__entry->l_state = bi->bi_bmap.br_state;
 		__entry->op = bi->bi_type;
 	),
-	TP_printk("dev %d:%d op %s ino 0x%llx agno 0x%x agbno 0x%x %s fileoff 0x%llx fsbcount 0x%llx state %d",
+	TP_printk("dev %d:%d op %s opdev %d:%d ino 0x%llx agno 0x%x agbno 0x%x rtbno 0x%llx %s fileoff 0x%llx fsbcount 0x%llx state %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __print_symbolic(__entry->op, XFS_BMAP_INTENT_STRINGS),
+		  MAJOR(__entry->opdev), MINOR(__entry->opdev),
 		  __entry->ino,
 		  __entry->agno,
 		  __entry->agbno,
+		  __entry->rtbno,
 		  __print_symbolic(__entry->whichfork, XFS_WHICHFORK_STRINGS),
 		  __entry->l_loff,
 		  __entry->l_len,

[PATCH 3/3] xfs: support recovering bmap intent items targetting realtime extents

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Now that we have reflink on the realtime device, bmap intent items have
to support remapping extents on the realtime volume.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_bmap_item.c |    9 +++++++++
 1 file changed, 9 insertions(+)


diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index d19f82c367f2b..02b872a133104 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -435,6 +435,9 @@ xfs_bui_validate(
 	if (!xfs_verify_fileext(mp, map->me_startoff, map->me_len))
 		return false;
 
+	if (map->me_flags & XFS_BMAP_EXTENT_REALTIME)
+		return xfs_verify_rtbext(mp, map->me_startblock, map->me_len);
+
 	return xfs_verify_fsbext(mp, map->me_startblock, map->me_len);
 }
 
@@ -509,6 +512,12 @@ xfs_bmap_recover_work(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
 
+	if (!!(map->me_flags & XFS_BMAP_EXTENT_REALTIME) !=
+	    xfs_ifork_is_realtime(ip, work->bi_whichfork)) {
+		error = -EFSCORRUPTED;
+		goto err_cancel;
+	}
+
 	if (work->bi_type == XFS_BMAP_MAP)
 		iext_delta = XFS_IEXT_ADD_NOSPLIT_CNT;
 	else

[PATCH 1/2] xfs: support deferred bmap updates on the attr fork

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

The deferred bmap update log item has always supported the attr fork, so
plumb this in so that higher layers can access this.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_bmap.c |   47 +++++++++++++++++++---------------------------
 fs/xfs/libxfs/xfs_bmap.h |    4 ++--
 fs/xfs/xfs_bmap_util.c   |    8 ++++----
 fs/xfs/xfs_reflink.c     |    8 ++++----
 4 files changed, 29 insertions(+), 38 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index bf20267cf6378..e7da6a72eb928 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -6150,17 +6150,8 @@ xfs_bmap_split_extent(
 	return error;
 }
 
-/* Deferred mapping is only for real extents in the data fork. */
-static bool
-xfs_bmap_is_update_needed(
-	struct xfs_bmbt_irec	*bmap)
-{
-	return  bmap->br_startblock != HOLESTARTBLOCK &&
-		bmap->br_startblock != DELAYSTARTBLOCK;
-}
-
 /* Record a bmap intent. */
-static int
+static inline void
 __xfs_bmap_add(
 	struct xfs_trans		*tp,
 	enum xfs_bmap_intent_type	type,
@@ -6170,6 +6161,11 @@ __xfs_bmap_add(
 {
 	struct xfs_bmap_intent		*bi;
 
+	if ((whichfork != XFS_DATA_FORK && whichfork != XFS_ATTR_FORK) ||
+	    bmap->br_startblock == HOLESTARTBLOCK ||
+	    bmap->br_startblock == DELAYSTARTBLOCK)
+		return;
+
 	bi = kmem_cache_alloc(xfs_bmap_intent_cache, GFP_NOFS | __GFP_NOFAIL);
 	INIT_LIST_HEAD(&bi->bi_list);
 	bi->bi_type = type;
@@ -6178,7 +6174,6 @@ __xfs_bmap_add(
 	bi->bi_bmap = *bmap;
 
 	xfs_bmap_defer_add(tp, bi);
-	return 0;
 }
 
 /* Map an extent into a file. */
@@ -6186,12 +6181,10 @@ void
 xfs_bmap_map_extent(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
+	int			whichfork,
 	struct xfs_bmbt_irec	*PREV)
 {
-	if (!xfs_bmap_is_update_needed(PREV))
-		return;
-
-	__xfs_bmap_add(tp, XFS_BMAP_MAP, ip, XFS_DATA_FORK, PREV);
+	__xfs_bmap_add(tp, XFS_BMAP_MAP, ip, whichfork, PREV);
 }
 
 /* Unmap an extent out of a file. */
@@ -6199,12 +6192,10 @@ void
 xfs_bmap_unmap_extent(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
+	int			whichfork,
 	struct xfs_bmbt_irec	*PREV)
 {
-	if (!xfs_bmap_is_update_needed(PREV))
-		return;
-
-	__xfs_bmap_add(tp, XFS_BMAP_UNMAP, ip, XFS_DATA_FORK, PREV);
+	__xfs_bmap_add(tp, XFS_BMAP_UNMAP, ip, whichfork, PREV);
 }
 
 /*
@@ -6218,29 +6209,29 @@ xfs_bmap_finish_one(
 {
 	struct xfs_bmbt_irec		*bmap = &bi->bi_bmap;
 	int				error = 0;
+	int				flags = 0;
+
+	if (bi->bi_whichfork == XFS_ATTR_FORK)
+		flags |= XFS_BMAPI_ATTRFORK;
 
 	ASSERT(tp->t_highest_agno == NULLAGNUMBER);
 
 	trace_xfs_bmap_deferred(bi);
 
-	if (WARN_ON_ONCE(bi->bi_whichfork != XFS_DATA_FORK)) {
-		xfs_bmap_mark_sick(bi->bi_owner, bi->bi_whichfork);
-		return -EFSCORRUPTED;
-	}
-
-	if (XFS_TEST_ERROR(false, tp->t_mountp,
-			XFS_ERRTAG_BMAP_FINISH_ONE))
+	if (XFS_TEST_ERROR(false, tp->t_mountp, XFS_ERRTAG_BMAP_FINISH_ONE))
 		return -EIO;
 
 	switch (bi->bi_type) {
 	case XFS_BMAP_MAP:
 		error = xfs_bmapi_remap(tp, bi->bi_owner, bmap->br_startoff,
-				bmap->br_blockcount, bmap->br_startblock, 0);
+				bmap->br_blockcount, bmap->br_startblock,
+				flags);
 		bmap->br_blockcount = 0;
 		break;
 	case XFS_BMAP_UNMAP:
 		error = __xfs_bunmapi(tp, bi->bi_owner, bmap->br_startoff,
-				&bmap->br_blockcount, XFS_BMAPI_REMAP, 1);
+				&bmap->br_blockcount, flags | XFS_BMAPI_REMAP,
+				1);
 		break;
 	default:
 		ASSERT(0);
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index a5e37ef7b75d7..1eee606f3924d 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -245,9 +245,9 @@ struct xfs_bmap_intent {
 
 int	xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_bmap_intent *bi);
 void	xfs_bmap_map_extent(struct xfs_trans *tp, struct xfs_inode *ip,
-		struct xfs_bmbt_irec *imap);
+		int whichfork, struct xfs_bmbt_irec *imap);
 void	xfs_bmap_unmap_extent(struct xfs_trans *tp, struct xfs_inode *ip,
-		struct xfs_bmbt_irec *imap);
+		int whichfork, struct xfs_bmbt_irec *imap);
 
 static inline uint32_t xfs_bmap_fork_to_state(int whichfork)
 {
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 6b5a9ad18fcb3..892622530431a 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1448,16 +1448,16 @@ xfs_swap_extent_rmap(
 			}
 
 			/* Remove the mapping from the donor file. */
-			xfs_bmap_unmap_extent(tp, tip, &uirec);
+			xfs_bmap_unmap_extent(tp, tip, XFS_DATA_FORK, &uirec);
 
 			/* Remove the mapping from the source file. */
-			xfs_bmap_unmap_extent(tp, ip, &irec);
+			xfs_bmap_unmap_extent(tp, ip, XFS_DATA_FORK, &irec);
 
 			/* Map the donor file's blocks into the source file. */
-			xfs_bmap_map_extent(tp, ip, &uirec);
+			xfs_bmap_map_extent(tp, ip, XFS_DATA_FORK, &uirec);
 
 			/* Map the source file's blocks into the donor file. */
-			xfs_bmap_map_extent(tp, tip, &irec);
+			xfs_bmap_map_extent(tp, tip, XFS_DATA_FORK, &irec);
 
 			error = xfs_defer_finish(tpp);
 			tp = *tpp;
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index ad1f235a3c492..69dfd7e430fe7 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -806,7 +806,7 @@ xfs_reflink_end_cow_extent(
 		 * If the extent we're remapping is backed by storage (written
 		 * or not), unmap the extent and drop its refcount.
 		 */
-		xfs_bmap_unmap_extent(tp, ip, &data);
+		xfs_bmap_unmap_extent(tp, ip, XFS_DATA_FORK, &data);
 		xfs_refcount_decrease_extent(tp, &data);
 		xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT,
 				-data.br_blockcount);
@@ -830,7 +830,7 @@ xfs_reflink_end_cow_extent(
 	xfs_refcount_free_cow_extent(tp, del.br_startblock, del.br_blockcount);
 
 	/* Map the new blocks into the data fork. */
-	xfs_bmap_map_extent(tp, ip, &del);
+	xfs_bmap_map_extent(tp, ip, XFS_DATA_FORK, &del);
 
 	/* Charge this new data fork mapping to the on-disk quota. */
 	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_DELBCOUNT,
@@ -1294,7 +1294,7 @@ xfs_reflink_remap_extent(
 		 * If the extent we're unmapping is backed by storage (written
 		 * or not), unmap the extent and drop its refcount.
 		 */
-		xfs_bmap_unmap_extent(tp, ip, &smap);
+		xfs_bmap_unmap_extent(tp, ip, XFS_DATA_FORK, &smap);
 		xfs_refcount_decrease_extent(tp, &smap);
 		qdelta -= smap.br_blockcount;
 	} else if (smap.br_startblock == DELAYSTARTBLOCK) {
@@ -1319,7 +1319,7 @@ xfs_reflink_remap_extent(
 	 */
 	if (dmap_written) {
 		xfs_refcount_increase_extent(tp, dmap);
-		xfs_bmap_map_extent(tp, ip, dmap);
+		xfs_bmap_map_extent(tp, ip, XFS_DATA_FORK, dmap);
 		qdelta += dmap->br_blockcount;
 	}
 

[PATCH 2/2] xfs: xfs_bmap_finish_one should map unwritten extents properly

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

The deferred bmap work state and the log item can transmit unwritten
state, so the XFS_BMAP_MAP handler must map in extents with that
unwritten state.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_bmap.c |    2 ++
 1 file changed, 2 insertions(+)


diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index e7da6a72eb928..03a67a4acd668 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -6223,6 +6223,8 @@ xfs_bmap_finish_one(
 
 	switch (bi->bi_type) {
 	case XFS_BMAP_MAP:
+		if (bi->bi_bmap.br_state == XFS_EXT_UNWRITTEN)
+			flags |= XFS_BMAPI_PREALLOC;
 		error = xfs_bmapi_remap(tp, bi->bi_owner, bmap->br_startoff,
 				bmap->br_blockcount, bmap->br_startblock,
 				flags);

[PATCH 1/3] xfs: move xfs_symlink_remote.c declarations to xfs_symlink_remote.h

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Move declarations for libxfs symlink functions into a separate header
file like we do for most everything else.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_bmap.c           |    1 +
 fs/xfs/libxfs/xfs_inode_fork.c     |    1 +
 fs/xfs/libxfs/xfs_shared.h         |   13 -------------
 fs/xfs/libxfs/xfs_symlink_remote.c |    2 +-
 fs/xfs/libxfs/xfs_symlink_remote.h |   22 ++++++++++++++++++++++
 fs/xfs/scrub/inode_repair.c        |    1 +
 fs/xfs/scrub/symlink.c             |    1 +
 fs/xfs/xfs_symlink.c               |    1 +
 8 files changed, 28 insertions(+), 14 deletions(-)
 create mode 100644 fs/xfs/libxfs/xfs_symlink_remote.h


diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 03a67a4acd668..17f607b3b8cdf 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -38,6 +38,7 @@
 #include "xfs_iomap.h"
 #include "xfs_health.h"
 #include "xfs_bmap_item.h"
+#include "xfs_symlink_remote.h"
 
 struct kmem_cache		*xfs_bmap_intent_cache;
 
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index bce36df4402a3..7e571fcfe9d1a 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -26,6 +26,7 @@
 #include "xfs_types.h"
 #include "xfs_errortag.h"
 #include "xfs_health.h"
+#include "xfs_symlink_remote.h"
 
 struct kmem_cache *xfs_ifork_cache;
 
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index 518ea9456ebae..7509c1406a355 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -137,19 +137,6 @@ void	xfs_log_get_max_trans_res(struct xfs_mount *mp,
 #define	XFS_ICHGTIME_CHG	0x2	/* inode field change timestamp */
 #define	XFS_ICHGTIME_CREATE	0x4	/* inode create timestamp */
 
-
-/*
- * Symlink decoding/encoding functions
- */
-int xfs_symlink_blocks(struct xfs_mount *mp, int pathlen);
-int xfs_symlink_hdr_set(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
-			uint32_t size, struct xfs_buf *bp);
-bool xfs_symlink_hdr_ok(xfs_ino_t ino, uint32_t offset,
-			uint32_t size, struct xfs_buf *bp);
-void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
-				 struct xfs_inode *ip, struct xfs_ifork *ifp);
-xfs_failaddr_t xfs_symlink_shortform_verify(void *sfp, int64_t size);
-
 /* Computed inode geometry for the filesystem. */
 struct xfs_ino_geometry {
 	/* Maximum inode count in this filesystem. */
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c
index 3c96d1d617fb0..a809a784d1741 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.c
+++ b/fs/xfs/libxfs/xfs_symlink_remote.c
@@ -16,7 +16,7 @@
 #include "xfs_trans.h"
 #include "xfs_buf_item.h"
 #include "xfs_log.h"
-
+#include "xfs_symlink_remote.h"
 
 /*
  * Each contiguous block has a header, so it is not just a simple pathlen
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.h b/fs/xfs/libxfs/xfs_symlink_remote.h
new file mode 100644
index 0000000000000..c6f621a0ec053
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_symlink_remote.h
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2000-2005 Silicon Graphics, Inc.
+ * Copyright (c) 2013 Red Hat, Inc.
+ * All Rights Reserved.
+ */
+#ifndef __XFS_SYMLINK_REMOTE_H
+#define __XFS_SYMLINK_REMOTE_H
+
+/*
+ * Symlink decoding/encoding functions
+ */
+int xfs_symlink_blocks(struct xfs_mount *mp, int pathlen);
+int xfs_symlink_hdr_set(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
+			uint32_t size, struct xfs_buf *bp);
+bool xfs_symlink_hdr_ok(xfs_ino_t ino, uint32_t offset,
+			uint32_t size, struct xfs_buf *bp);
+void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
+				 struct xfs_inode *ip, struct xfs_ifork *ifp);
+xfs_failaddr_t xfs_symlink_shortform_verify(void *sfp, int64_t size);
+
+#endif /* __XFS_SYMLINK_REMOTE_H */
diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c
index 20cecf3c69342..549b66ef826a9 100644
--- a/fs/xfs/scrub/inode_repair.c
+++ b/fs/xfs/scrub/inode_repair.c
@@ -37,6 +37,7 @@
 #include "xfs_attr_leaf.h"
 #include "xfs_log_priv.h"
 #include "xfs_health.h"
+#include "xfs_symlink_remote.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
diff --git a/fs/xfs/scrub/symlink.c b/fs/xfs/scrub/symlink.c
index 60643d791d4a2..06f8fe117cb4c 100644
--- a/fs/xfs/scrub/symlink.c
+++ b/fs/xfs/scrub/symlink.c
@@ -13,6 +13,7 @@
 #include "xfs_inode.h"
 #include "xfs_symlink.h"
 #include "xfs_health.h"
+#include "xfs_symlink_remote.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/health.h"
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index b7f251fc2951c..ca1daf8245fa6 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -24,6 +24,7 @@
 #include "xfs_ialloc.h"
 #include "xfs_error.h"
 #include "xfs_health.h"
+#include "xfs_symlink_remote.h"
 
 /* ----- Kernel only functions below ----- */
 int

[PATCH 2/3] xfs: move remote symlink target read function to libxfs

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Move xfs_readlink_bmap_ilocked to xfs_symlink_remote.c so that the
swapext code can use it to convert a remote format symlink back to
shortform format after a metadata repair.  While we're at it, fix a
broken printf prefix.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_symlink_remote.c |   77 ++++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_symlink_remote.h |    1 
 fs/xfs/scrub/symlink.c             |    2 -
 fs/xfs/xfs_symlink.c               |   75 -----------------------------------
 fs/xfs/xfs_symlink.h               |    1 
 5 files changed, 80 insertions(+), 76 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c
index a809a784d1741..b1ab6bdc3834e 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.c
+++ b/fs/xfs/libxfs/xfs_symlink_remote.c
@@ -17,6 +17,9 @@
 #include "xfs_buf_item.h"
 #include "xfs_log.h"
 #include "xfs_symlink_remote.h"
+#include "xfs_bit.h"
+#include "xfs_bmap.h"
+#include "xfs_health.h"
 
 /*
  * Each contiguous block has a header, so it is not just a simple pathlen
@@ -227,3 +230,77 @@ xfs_symlink_shortform_verify(
 		return __this_address;
 	return NULL;
 }
+
+/* Read a remote symlink target into the buffer. */
+int
+xfs_symlink_remote_read(
+	struct xfs_inode	*ip,
+	char			*link)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_bmbt_irec	mval[XFS_SYMLINK_MAPS];
+	struct xfs_buf		*bp;
+	xfs_daddr_t		d;
+	char			*cur_chunk;
+	int			pathlen = ip->i_disk_size;
+	int			nmaps = XFS_SYMLINK_MAPS;
+	int			byte_cnt;
+	int			n;
+	int			error = 0;
+	int			fsblocks = 0;
+	int			offset;
+
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
+
+	fsblocks = xfs_symlink_blocks(mp, pathlen);
+	error = xfs_bmapi_read(ip, 0, fsblocks, mval, &nmaps, 0);
+	if (error)
+		goto out;
+
+	offset = 0;
+	for (n = 0; n < nmaps; n++) {
+		d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
+		byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
+
+		error = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt), 0,
+				&bp, &xfs_symlink_buf_ops);
+		if (xfs_metadata_is_sick(error))
+			xfs_inode_mark_sick(ip, XFS_SICK_INO_SYMLINK);
+		if (error)
+			return error;
+		byte_cnt = XFS_SYMLINK_BUF_SPACE(mp, byte_cnt);
+		if (pathlen < byte_cnt)
+			byte_cnt = pathlen;
+
+		cur_chunk = bp->b_addr;
+		if (xfs_has_crc(mp)) {
+			if (!xfs_symlink_hdr_ok(ip->i_ino, offset,
+							byte_cnt, bp)) {
+				xfs_inode_mark_sick(ip, XFS_SICK_INO_SYMLINK);
+				error = -EFSCORRUPTED;
+				xfs_alert(mp,
+"symlink header does not match required off/len/owner (0x%x/0x%x,0x%llx)",
+					offset, byte_cnt, ip->i_ino);
+				xfs_buf_relse(bp);
+				goto out;
+
+			}
+
+			cur_chunk += sizeof(struct xfs_dsymlink_hdr);
+		}
+
+		memcpy(link + offset, cur_chunk, byte_cnt);
+
+		pathlen -= byte_cnt;
+		offset += byte_cnt;
+
+		xfs_buf_relse(bp);
+	}
+	ASSERT(pathlen == 0);
+
+	link[ip->i_disk_size] = '\0';
+	error = 0;
+
+ out:
+	return error;
+}
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.h b/fs/xfs/libxfs/xfs_symlink_remote.h
index c6f621a0ec053..bb83a8b8dfa66 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.h
+++ b/fs/xfs/libxfs/xfs_symlink_remote.h
@@ -18,5 +18,6 @@ bool xfs_symlink_hdr_ok(xfs_ino_t ino, uint32_t offset,
 void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
 				 struct xfs_inode *ip, struct xfs_ifork *ifp);
 xfs_failaddr_t xfs_symlink_shortform_verify(void *sfp, int64_t size);
+int xfs_symlink_remote_read(struct xfs_inode *ip, char *link);
 
 #endif /* __XFS_SYMLINK_REMOTE_H */
diff --git a/fs/xfs/scrub/symlink.c b/fs/xfs/scrub/symlink.c
index 06f8fe117cb4c..7239590c9dd29 100644
--- a/fs/xfs/scrub/symlink.c
+++ b/fs/xfs/scrub/symlink.c
@@ -68,7 +68,7 @@ xchk_symlink(
 	}
 
 	/* Remote symlink; must read the contents. */
-	error = xfs_readlink_bmap_ilocked(sc->ip, sc->buf);
+	error = xfs_symlink_remote_read(sc->ip, sc->buf);
 	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
 		return error;
 	if (strnlen(sc->buf, XFS_SYMLINK_MAXLEN) < len)
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index ca1daf8245fa6..0a9a1ad733336 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -27,79 +27,6 @@
 #include "xfs_symlink_remote.h"
 
 /* ----- Kernel only functions below ----- */
-int
-xfs_readlink_bmap_ilocked(
-	struct xfs_inode	*ip,
-	char			*link)
-{
-	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_bmbt_irec	mval[XFS_SYMLINK_MAPS];
-	struct xfs_buf		*bp;
-	xfs_daddr_t		d;
-	char			*cur_chunk;
-	int			pathlen = ip->i_disk_size;
-	int			nmaps = XFS_SYMLINK_MAPS;
-	int			byte_cnt;
-	int			n;
-	int			error = 0;
-	int			fsblocks = 0;
-	int			offset;
-
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
-
-	fsblocks = xfs_symlink_blocks(mp, pathlen);
-	error = xfs_bmapi_read(ip, 0, fsblocks, mval, &nmaps, 0);
-	if (error)
-		goto out;
-
-	offset = 0;
-	for (n = 0; n < nmaps; n++) {
-		d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
-		byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
-
-		error = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt), 0,
-				&bp, &xfs_symlink_buf_ops);
-		if (xfs_metadata_is_sick(error))
-			xfs_inode_mark_sick(ip, XFS_SICK_INO_SYMLINK);
-		if (error)
-			return error;
-		byte_cnt = XFS_SYMLINK_BUF_SPACE(mp, byte_cnt);
-		if (pathlen < byte_cnt)
-			byte_cnt = pathlen;
-
-		cur_chunk = bp->b_addr;
-		if (xfs_has_crc(mp)) {
-			if (!xfs_symlink_hdr_ok(ip->i_ino, offset,
-							byte_cnt, bp)) {
-				xfs_inode_mark_sick(ip, XFS_SICK_INO_SYMLINK);
-				error = -EFSCORRUPTED;
-				xfs_alert(mp,
-"symlink header does not match required off/len/owner (0x%x/Ox%x,0x%llx)",
-					offset, byte_cnt, ip->i_ino);
-				xfs_buf_relse(bp);
-				goto out;
-
-			}
-
-			cur_chunk += sizeof(struct xfs_dsymlink_hdr);
-		}
-
-		memcpy(link + offset, cur_chunk, byte_cnt);
-
-		pathlen -= byte_cnt;
-		offset += byte_cnt;
-
-		xfs_buf_relse(bp);
-	}
-	ASSERT(pathlen == 0);
-
-	link[ip->i_disk_size] = '\0';
-	error = 0;
-
- out:
-	return error;
-}
-
 int
 xfs_readlink(
 	struct xfs_inode	*ip,
@@ -141,7 +68,7 @@ xfs_readlink(
 		memcpy(link, ip->i_df.if_u1.if_data, pathlen + 1);
 		error = 0;
 	} else {
-		error = xfs_readlink_bmap_ilocked(ip, link);
+		error = xfs_symlink_remote_read(ip, link);
 	}
 
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
diff --git a/fs/xfs/xfs_symlink.h b/fs/xfs/xfs_symlink.h
index d1ca1ce62a93b..0d29a50e66fdc 100644
--- a/fs/xfs/xfs_symlink.h
+++ b/fs/xfs/xfs_symlink.h
@@ -10,7 +10,6 @@
 int xfs_symlink(struct mnt_idmap *idmap, struct xfs_inode *dp,
 		struct xfs_name *link_name, const char *target_path,
 		umode_t mode, struct xfs_inode **ipp);
-int xfs_readlink_bmap_ilocked(struct xfs_inode *ip, char *link);
 int xfs_readlink(struct xfs_inode *ip, char *link);
 int xfs_inactive_symlink(struct xfs_inode *ip);
 

[PATCH 3/3] xfs: move symlink target write function to libxfs

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Move xfs_symlink_write_target to xfs_symlink_remote.c so that kernel and
mkfs can share the same function.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_symlink_remote.c |   76 ++++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_symlink_remote.h |    3 +
 fs/xfs/xfs_symlink.c               |   69 ++-------------------------------
 3 files changed, 84 insertions(+), 64 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c
index b1ab6bdc3834e..1b8815159702e 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.c
+++ b/fs/xfs/libxfs/xfs_symlink_remote.c
@@ -304,3 +304,79 @@ xfs_symlink_remote_read(
  out:
 	return error;
 }
+
+/* Write the symlink target into the inode. */
+int
+xfs_symlink_write_target(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	const char		*target_path,
+	int			pathlen,
+	xfs_fsblock_t		fs_blocks,
+	uint			resblks)
+{
+	struct xfs_bmbt_irec	mval[XFS_SYMLINK_MAPS];
+	struct xfs_mount	*mp = tp->t_mountp;
+	const char		*cur_chunk;
+	struct xfs_buf		*bp;
+	xfs_daddr_t		d;
+	int			byte_cnt;
+	int			nmaps;
+	int			offset = 0;
+	int			n;
+	int			error;
+
+	/*
+	 * If the symlink will fit into the inode, write it inline.
+	 */
+	if (pathlen <= xfs_inode_data_fork_size(ip)) {
+		xfs_init_local_fork(ip, XFS_DATA_FORK, target_path, pathlen);
+
+		ip->i_disk_size = pathlen;
+		ip->i_df.if_format = XFS_DINODE_FMT_LOCAL;
+		xfs_trans_log_inode(tp, ip, XFS_ILOG_DDATA | XFS_ILOG_CORE);
+		return 0;
+	}
+
+	nmaps = XFS_SYMLINK_MAPS;
+	error = xfs_bmapi_write(tp, ip, 0, fs_blocks, XFS_BMAPI_METADATA,
+			resblks, mval, &nmaps);
+	if (error)
+		return error;
+
+	ip->i_disk_size = pathlen;
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+	cur_chunk = target_path;
+	offset = 0;
+	for (n = 0; n < nmaps; n++) {
+		char	*buf;
+
+		d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
+		byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
+		error = xfs_trans_get_buf(tp, mp->m_ddev_targp, d,
+				BTOBB(byte_cnt), 0, &bp);
+		if (error)
+			return error;
+		bp->b_ops = &xfs_symlink_buf_ops;
+
+		byte_cnt = XFS_SYMLINK_BUF_SPACE(mp, byte_cnt);
+		byte_cnt = min(byte_cnt, pathlen);
+
+		buf = bp->b_addr;
+		buf += xfs_symlink_hdr_set(mp, ip->i_ino, offset, byte_cnt,
+				bp);
+
+		memcpy(buf, cur_chunk, byte_cnt);
+
+		cur_chunk += byte_cnt;
+		pathlen -= byte_cnt;
+		offset += byte_cnt;
+
+		xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SYMLINK_BUF);
+		xfs_trans_log_buf(tp, bp, 0, (buf + byte_cnt - 1) -
+						(char *)bp->b_addr);
+	}
+	ASSERT(pathlen == 0);
+	return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.h b/fs/xfs/libxfs/xfs_symlink_remote.h
index bb83a8b8dfa66..a63bd38ae4faf 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.h
+++ b/fs/xfs/libxfs/xfs_symlink_remote.h
@@ -19,5 +19,8 @@ void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
 				 struct xfs_inode *ip, struct xfs_ifork *ifp);
 xfs_failaddr_t xfs_symlink_shortform_verify(void *sfp, int64_t size);
 int xfs_symlink_remote_read(struct xfs_inode *ip, char *link);
+int xfs_symlink_write_target(struct xfs_trans *tp, struct xfs_inode *ip,
+		const char *target_path, int pathlen, xfs_fsblock_t fs_blocks,
+		uint resblks);
 
 #endif /* __XFS_SYMLINK_REMOTE_H */
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 0a9a1ad733336..2a082749be5cf 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -94,15 +94,7 @@ xfs_symlink(
 	int			error = 0;
 	int			pathlen;
 	bool                    unlock_dp_on_error = false;
-	xfs_fileoff_t		first_fsb;
 	xfs_filblks_t		fs_blocks;
-	int			nmaps;
-	struct xfs_bmbt_irec	mval[XFS_SYMLINK_MAPS];
-	xfs_daddr_t		d;
-	const char		*cur_chunk;
-	int			byte_cnt;
-	int			n;
-	struct xfs_buf		*bp;
 	prid_t			prid;
 	struct xfs_dquot	*udqp = NULL;
 	struct xfs_dquot	*gdqp = NULL;
@@ -190,62 +182,11 @@ xfs_symlink(
 	xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp);
 
 	resblks -= XFS_IALLOC_SPACE_RES(mp);
-	/*
-	 * If the symlink will fit into the inode, write it inline.
-	 */
-	if (pathlen <= xfs_inode_data_fork_size(ip)) {
-		xfs_init_local_fork(ip, XFS_DATA_FORK, target_path, pathlen);
-
-		ip->i_disk_size = pathlen;
-		ip->i_df.if_format = XFS_DINODE_FMT_LOCAL;
-		xfs_trans_log_inode(tp, ip, XFS_ILOG_DDATA | XFS_ILOG_CORE);
-	} else {
-		int	offset;
-
-		first_fsb = 0;
-		nmaps = XFS_SYMLINK_MAPS;
-
-		error = xfs_bmapi_write(tp, ip, first_fsb, fs_blocks,
-				  XFS_BMAPI_METADATA, resblks, mval, &nmaps);
-		if (error)
-			goto out_trans_cancel;
-
-		resblks -= fs_blocks;
-		ip->i_disk_size = pathlen;
-		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-
-		cur_chunk = target_path;
-		offset = 0;
-		for (n = 0; n < nmaps; n++) {
-			char	*buf;
-
-			d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
-			byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
-			error = xfs_trans_get_buf(tp, mp->m_ddev_targp, d,
-					       BTOBB(byte_cnt), 0, &bp);
-			if (error)
-				goto out_trans_cancel;
-			bp->b_ops = &xfs_symlink_buf_ops;
-
-			byte_cnt = XFS_SYMLINK_BUF_SPACE(mp, byte_cnt);
-			byte_cnt = min(byte_cnt, pathlen);
-
-			buf = bp->b_addr;
-			buf += xfs_symlink_hdr_set(mp, ip->i_ino, offset,
-						   byte_cnt, bp);
-
-			memcpy(buf, cur_chunk, byte_cnt);
-
-			cur_chunk += byte_cnt;
-			pathlen -= byte_cnt;
-			offset += byte_cnt;
-
-			xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SYMLINK_BUF);
-			xfs_trans_log_buf(tp, bp, 0, (buf + byte_cnt - 1) -
-							(char *)bp->b_addr);
-		}
-		ASSERT(pathlen == 0);
-	}
+	error = xfs_symlink_write_target(tp, ip, target_path, pathlen,
+			fs_blocks, resblks);
+	if (error)
+		goto out_trans_cancel;
+	resblks -= fs_blocks;
 	i_size_write(VFS_I(ip), ip->i_disk_size);
 
 	/*

[PATCH 01/25] xfs: add a libxfs header file for staging new ioctls

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a new xfs_fs_staging.h header where we can land experimental
ioctls without committing them to any stable interfaces anywhere.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_fs_staging.h |   18 ++++++++++++++++++
 fs/xfs/xfs_linux.h             |    1 +
 2 files changed, 19 insertions(+)
 create mode 100644 fs/xfs/libxfs/xfs_fs_staging.h


diff --git a/fs/xfs/libxfs/xfs_fs_staging.h b/fs/xfs/libxfs/xfs_fs_staging.h
new file mode 100644
index 0000000000000..d220790d5b593
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_fs_staging.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+/*
+ * Copyright (c) 2020-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_FS_STAGING_H__
+#define __XFS_FS_STAGING_H__
+
+/*
+ * Experimental system calls, ioctls and data structures supporting them.
+ * Nothing in here should be considered part of a stable interface of any kind.
+ *
+ * If you add an ioctl here, please leave a comment in xfs_fs.h marking it
+ * reserved.  If you promote anything out of this file, please leave a comment
+ * explaining where it went.
+ */
+
+#endif /* __XFS_FS_STAGING_H__ */
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index 73854ad981eb5..c24e0d52bc04e 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -73,6 +73,7 @@ typedef __u32			xfs_nlink_t;
 #include <asm/unaligned.h>
 
 #include "xfs_fs.h"
+#include "xfs_fs_staging.h"
 #include "xfs_stats.h"
 #include "xfs_sysctl.h"
 #include "xfs_iops.h"

[PATCH 02/25] xfs: introduce new file range exchange ioctl

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Introduce a new ioctl to handle swapping ranges of bytes between files.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/read_write.c                |    2 
 fs/remap_range.c               |    4 
 fs/xfs/Makefile                |    1 
 fs/xfs/libxfs/xfs_fs.h         |    1 
 fs/xfs/libxfs/xfs_fs_staging.h |   89 ++++++++++
 fs/xfs/xfs_ioctl.c             |   30 +++
 fs/xfs/xfs_xchgrange.c         |  346 ++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_xchgrange.h         |   18 ++
 include/linux/fs.h             |    1 
 9 files changed, 490 insertions(+), 2 deletions(-)
 create mode 100644 fs/xfs/xfs_xchgrange.c
 create mode 100644 fs/xfs/xfs_xchgrange.h


diff --git a/fs/read_write.c b/fs/read_write.c
index 4771701c896ba..2a304724844f7 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1650,6 +1650,7 @@ int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count)
 
 	return 0;
 }
+EXPORT_SYMBOL(generic_write_check_limits);
 
 /* Like generic_write_checks(), but takes size of write instead of iter. */
 int generic_write_checks_count(struct kiocb *iocb, loff_t *count)
@@ -1718,3 +1719,4 @@ int generic_file_rw_checks(struct file *file_in, struct file *file_out)
 
 	return 0;
 }
+EXPORT_SYMBOL(generic_file_rw_checks);
diff --git a/fs/remap_range.c b/fs/remap_range.c
index 87ae4f0dc3aa0..f75ff15c94976 100644
--- a/fs/remap_range.c
+++ b/fs/remap_range.c
@@ -99,8 +99,7 @@ static int generic_remap_checks(struct file *file_in, loff_t pos_in,
 	return 0;
 }
 
-static int remap_verify_area(struct file *file, loff_t pos, loff_t len,
-			     bool write)
+int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write)
 {
 	loff_t tmp;
 
@@ -112,6 +111,7 @@ static int remap_verify_area(struct file *file, loff_t pos, loff_t len,
 
 	return security_file_permission(file, write ? MAY_WRITE : MAY_READ);
 }
+EXPORT_SYMBOL(remap_verify_area);
 
 /*
  * Ensure that we don't remap a partial EOF block in the middle of something
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index a76e98e94b64a..d0b538c11faaf 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -93,6 +93,7 @@ xfs-y				+= xfs_aops.o \
 				   xfs_sysfs.o \
 				   xfs_trans.o \
 				   xfs_xattr.o \
+				   xfs_xchgrange.o \
 				   kmem.o
 
 # low-level transaction/log code
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index ca1b17d014377..ec92e6ded6b8b 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -843,6 +843,7 @@ struct xfs_scrub_metadata {
 #define XFS_IOC_FSGEOMETRY	     _IOR ('X', 126, struct xfs_fsop_geom)
 #define XFS_IOC_BULKSTAT	     _IOR ('X', 127, struct xfs_bulkstat_req)
 #define XFS_IOC_INUMBERS	     _IOR ('X', 128, struct xfs_inumbers_req)
+/*	XFS_IOC_EXCHANGE_RANGE -------- staging 129	 */
 /*	XFS_IOC_GETFSUUID ---------- deprecated 140	 */
 
 
diff --git a/fs/xfs/libxfs/xfs_fs_staging.h b/fs/xfs/libxfs/xfs_fs_staging.h
index d220790d5b593..e3d9f3b32b078 100644
--- a/fs/xfs/libxfs/xfs_fs_staging.h
+++ b/fs/xfs/libxfs/xfs_fs_staging.h
@@ -15,4 +15,93 @@
  * explaining where it went.
  */
 
+/*
+ * Exchange part of file1 with part of the file that this ioctl that is being
+ * called against (which we'll call file2).  Filesystems must be able to
+ * restart and complete the operation even after the system goes down.
+ */
+struct xfs_exch_range {
+	__s64		file1_fd;
+	__s64		file1_offset;	/* file1 offset, bytes */
+	__s64		file2_offset;	/* file2 offset, bytes */
+	__u64		length;		/* bytes to exchange */
+
+	__u64		flags;		/* see XFS_EXCH_RANGE_* below */
+
+	/* file2 metadata for optional freshness checks */
+	__s64		file2_ino;	/* inode number */
+	__s64		file2_mtime;	/* modification time */
+	__s64		file2_ctime;	/* change time */
+	__s32		file2_mtime_nsec; /* mod time, nsec */
+	__s32		file2_ctime_nsec; /* change time, nsec */
+
+	__u64		pad[6];		/* must be zeroes */
+};
+
+/*
+ * Atomic exchange operations are not required.  This relaxes the requirement
+ * that the filesystem must be able to complete the operation after a crash.
+ */
+#define XFS_EXCH_RANGE_NONATOMIC	(1 << 0)
+
+/*
+ * Check that file2's inode number, mtime, and ctime against the values
+ * provided, and return -EBUSY if there isn't an exact match.
+ */
+#define XFS_EXCH_RANGE_FILE2_FRESH	(1 << 1)
+
+/*
+ * Check that the file1's length is equal to file1_offset + length, and that
+ * file2's length is equal to file2_offset + length.  Returns -EDOM if there
+ * isn't an exact match.
+ */
+#define XFS_EXCH_RANGE_FULL_FILES	(1 << 2)
+
+/*
+ * Exchange file data all the way to the ends of both files, and then exchange
+ * the file sizes.  This flag can be used to replace a file's contents with a
+ * different amount of data.  length will be ignored.
+ */
+#define XFS_EXCH_RANGE_TO_EOF		(1 << 3)
+
+/* Flush all changes in file data and file metadata to disk before returning. */
+#define XFS_EXCH_RANGE_FSYNC		(1 << 4)
+
+/* Dry run; do all the parameter verification but do not change anything. */
+#define XFS_EXCH_RANGE_DRY_RUN		(1 << 5)
+
+/*
+ * Exchange only the parts of the two files where the file allocation units
+ * mapped to file1's range have been written to.  This can accelerate
+ * scatter-gather atomic writes with a temp file if all writes are aligned to
+ * the file allocation unit.
+ */
+#define XFS_EXCH_RANGE_FILE1_WRITTEN	(1 << 6)
+
+/*
+ * Commit the contents of file1 into file2 if file2 has the same inode number,
+ * mtime, and ctime as the arguments provided to the call.  The old contents of
+ * file2 will be moved to file1.
+ *
+ * With this flag, all committed information can be retrieved even if the
+ * system crashes or is rebooted.  This includes writing through or flushing a
+ * disk cache if present.  The call blocks until the device reports that the
+ * commit is complete.
+ *
+ * This flag should not be combined with NONATOMIC.  It can be combined with
+ * FILE1_WRITTEN.
+ */
+#define XFS_EXCH_RANGE_COMMIT		(XFS_EXCH_RANGE_FILE2_FRESH | \
+					 XFS_EXCH_RANGE_FSYNC)
+
+#define XFS_EXCH_RANGE_ALL_FLAGS	(XFS_EXCH_RANGE_NONATOMIC | \
+					 XFS_EXCH_RANGE_FILE2_FRESH | \
+					 XFS_EXCH_RANGE_FULL_FILES | \
+					 XFS_EXCH_RANGE_TO_EOF | \
+					 XFS_EXCH_RANGE_FSYNC | \
+					 XFS_EXCH_RANGE_DRY_RUN | \
+					 XFS_EXCH_RANGE_FILE1_WRITTEN)
+
+#define XFS_IOC_EXCHANGE_RANGE	_IOWR('X', 129, struct xfs_exch_range)
+
 #endif /* __XFS_FS_STAGING_H__ */
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 8dcd6ca2a903b..d320f42dab32c 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -39,6 +39,7 @@
 #include "xfs_ioctl.h"
 #include "xfs_xattr.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_xchgrange.h"
 
 #include <linux/mount.h>
 #include <linux/namei.h>
@@ -1873,6 +1874,32 @@ xfs_fs_eofblocks_from_user(
 	return 0;
 }
 
+static long
+xfs_ioc_exchange_range(
+	struct file			*file2,
+	struct xfs_exch_range __user	*argp)
+{
+	struct xfs_exch_range		args;
+	struct fd			file1;
+	int				error;
+
+	if (copy_from_user(&args, argp, sizeof(args)))
+		return -EFAULT;
+
+	file1 = fdget(args.file1_fd);
+	if (!file1.file)
+		return -EBADF;
+
+	error = -EXDEV;
+	if (file1.file->f_path.mnt != file2->f_path.mnt)
+		goto fdput;
+
+	error = xfs_exch_range(file1.file, file2, &args);
+fdput:
+	fdput(file1);
+	return error;
+}
+
 /*
  * These long-unused ioctls were removed from the official ioctl API in 5.17,
  * but retain these definitions so that we can log warnings about them.
@@ -2161,6 +2188,9 @@ xfs_file_ioctl(
 		return error;
 	}
 
+	case XFS_IOC_EXCHANGE_RANGE:
+		return xfs_ioc_exchange_range(filp, arg);
+
 	default:
 		return -ENOTTY;
 	}
diff --git a/fs/xfs/xfs_xchgrange.c b/fs/xfs/xfs_xchgrange.c
new file mode 100644
index 0000000000000..764d64e04726b
--- /dev/null
+++ b/fs/xfs/xfs_xchgrange.c
@@ -0,0 +1,346 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2020-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_inode.h"
+#include "xfs_trans.h"
+#include "xfs_xchgrange.h"
+#include <linux/fsnotify.h>
+
+/*
+ * Generic code for exchanging ranges of two files via XFS_IOC_EXCHANGE_RANGE.
+ * This part does not deal with XFS-specific data structures, and may some day
+ * be ported to the VFS.
+ *
+ * The goal is to exchange fxr.length bytes starting at fxr.file1_offset in
+ * file1 with the same number of bytes starting at fxr.file2_offset in file2.
+ * Implementations must call xfs_exch_range_prep to prepare the two files
+ * prior to taking locks; they must call xfs_exch_range_check_fresh once
+ * the inode is locked to abort the call if file2 has changed; and they must
+ * update the inode change and mod times of both files as part of the metadata
+ * update.  The timestamp updates must be done atomically as part of the data
+ * exchange operation to ensure correctness of the freshness check.
+ */
+
+/*
+ * Check that both files' metadata agree with the snapshot that we took for
+ * the range exchange request.
+ *
+ * This should be called after the filesystem has locked /all/ inode metadata
+ * against modification.
+ */
+STATIC int
+xfs_exch_range_check_fresh(
+	struct inode			*inode2,
+	const struct xfs_exch_range	*fxr)
+{
+	struct timespec64		ctime = inode_get_ctime(inode2);
+	struct timespec64		mtime = inode_get_mtime(inode2);
+
+	/* Check that file2 hasn't otherwise been modified. */
+	if ((fxr->flags & XFS_EXCH_RANGE_FILE2_FRESH) &&
+	    (fxr->file2_ino        != inode2->i_ino ||
+	     fxr->file2_ctime      != ctime.tv_sec  ||
+	     fxr->file2_ctime_nsec != ctime.tv_nsec ||
+	     fxr->file2_mtime      != mtime.tv_sec  ||
+	     fxr->file2_mtime_nsec != mtime.tv_nsec))
+		return -EBUSY;
+
+	return 0;
+}
+
+/* Performs necessary checks before doing a range exchange. */
+STATIC int
+xfs_exch_range_checks(
+	struct file		*file1,
+	struct file		*file2,
+	struct xfs_exch_range	*fxr,
+	unsigned int		blocksize)
+{
+	struct inode		*inode1 = file1->f_mapping->host;
+	struct inode		*inode2 = file2->f_mapping->host;
+	uint64_t		blkmask = blocksize - 1;
+	int64_t			test_len;
+	uint64_t		blen;
+	loff_t			size1, size2;
+	int			error;
+
+	/* Don't touch certain kinds of inodes */
+	if (IS_IMMUTABLE(inode1) || IS_IMMUTABLE(inode2))
+		return -EPERM;
+	if (IS_SWAPFILE(inode1) || IS_SWAPFILE(inode2))
+		return -ETXTBSY;
+
+	size1 = i_size_read(inode1);
+	size2 = i_size_read(inode2);
+
+	/* Ranges cannot start after EOF. */
+	if (fxr->file1_offset > size1 || fxr->file2_offset > size2)
+		return -EINVAL;
+
+	/*
+	 * If the caller asked for full files, check that the offset/length
+	 * values cover all of both files.
+	 */
+	if ((fxr->flags & XFS_EXCH_RANGE_FULL_FILES) &&
+	    (fxr->file1_offset != 0 || fxr->file2_offset != 0 ||
+	     fxr->length != size1 || fxr->length != size2))
+		return -EDOM;
+
+	/*
+	 * If the caller said to exchange to EOF, we set the length of the
+	 * request large enough to cover everything to the end of both files.
+	 */
+	if (fxr->flags & XFS_EXCH_RANGE_TO_EOF)
+		fxr->length = max_t(int64_t, size1 - fxr->file1_offset,
+					     size2 - fxr->file2_offset);
+
+	/* The start of both ranges must be aligned to an fs block. */
+	if (!IS_ALIGNED(fxr->file1_offset, blocksize) ||
+	    !IS_ALIGNED(fxr->file2_offset, blocksize))
+		return -EINVAL;
+
+	/* Ensure offsets don't wrap. */
+	if (fxr->file1_offset + fxr->length < fxr->file1_offset ||
+	    fxr->file2_offset + fxr->length < fxr->file2_offset)
+		return -EINVAL;
+
+	/*
+	 * We require both ranges to be within EOF, unless we're exchanging
+	 * to EOF.  xfs_xchg_range_prep already checked that both
+	 * fxr->file1_offset and fxr->file2_offset are within EOF.
+	 */
+	if (!(fxr->flags & XFS_EXCH_RANGE_TO_EOF) &&
+	    (fxr->file1_offset + fxr->length > size1 ||
+	     fxr->file2_offset + fxr->length > size2))
+		return -EINVAL;
+
+	/*
+	 * Make sure we don't hit any file size limits.  If we hit any size
+	 * limits such that test_length was adjusted, we abort the whole
+	 * operation.
+	 */
+	test_len = fxr->length;
+	error = generic_write_check_limits(file2, fxr->file2_offset, &test_len);
+	if (error)
+		return error;
+	error = generic_write_check_limits(file1, fxr->file1_offset, &test_len);
+	if (error)
+		return error;
+	if (test_len != fxr->length)
+		return -EINVAL;
+
+	/*
+	 * If the user wanted us to exchange up to the infile's EOF, round up
+	 * to the next block boundary for this check.  Do the same for the
+	 * outfile.
+	 *
+	 * Otherwise, reject the range length if it's not block aligned.  We
+	 * already confirmed the starting offsets' block alignment.
+	 */
+	if (fxr->file1_offset + fxr->length == size1)
+		blen = ALIGN(size1, blocksize) - fxr->file1_offset;
+	else if (fxr->file2_offset + fxr->length == size2)
+		blen = ALIGN(size2, blocksize) - fxr->file2_offset;
+	else if (!IS_ALIGNED(fxr->length, blocksize))
+		return -EINVAL;
+	else
+		blen = fxr->length;
+
+	/* Don't allow overlapped exchanges within the same file. */
+	if (inode1 == inode2 &&
+	    fxr->file2_offset + blen > fxr->file1_offset &&
+	    fxr->file1_offset + blen > fxr->file2_offset)
+		return -EINVAL;
+
+	/* If we already failed the freshness check, we're done. */
+	error = xfs_exch_range_check_fresh(inode2, fxr);
+	if (error)
+		return error;
+
+	/*
+	 * Ensure that we don't exchange a partial EOF block into the middle of
+	 * another file.
+	 */
+	if ((fxr->length & blkmask) == 0)
+		return 0;
+
+	blen = fxr->length;
+	if (fxr->file2_offset + blen < size2)
+		blen &= ~blkmask;
+
+	if (fxr->file1_offset + blen < size1)
+		blen &= ~blkmask;
+
+	return blen == fxr->length ? 0 : -EINVAL;
+}
+
+/*
+ * Check that the two inodes are eligible for range exchanges, the ranges make
+ * sense, and then flush all dirty data.  Caller must ensure that the inodes
+ * have been locked against any other modifications.
+ */
+int
+xfs_exch_range_prep(
+	struct file		*file1,
+	struct file		*file2,
+	struct xfs_exch_range	*fxr,
+	unsigned int		blocksize)
+{
+	struct inode		*inode1 = file_inode(file1);
+	struct inode		*inode2 = file_inode(file2);
+	bool			same_inode = (inode1 == inode2);
+	int			error;
+
+	/* Check that we don't violate system file offset limits. */
+	error = xfs_exch_range_checks(file1, file2, fxr, blocksize);
+	if (error || fxr->length == 0)
+		return error;
+
+	/* Wait for the completion of any pending IOs on both files */
+	inode_dio_wait(inode1);
+	if (!same_inode)
+		inode_dio_wait(inode2);
+
+	error = filemap_write_and_wait_range(inode1->i_mapping,
+			fxr->file1_offset,
+			fxr->file1_offset + fxr->length - 1);
+	if (error)
+		return error;
+
+	error = filemap_write_and_wait_range(inode2->i_mapping,
+			fxr->file2_offset,
+			fxr->file2_offset + fxr->length - 1);
+	if (error)
+		return error;
+
+	/*
+	 * If the files or inodes involved require synchronous writes, amend
+	 * the request to force the filesystem to flush all data and metadata
+	 * to disk after the operation completes.
+	 */
+	if (((file1->f_flags | file2->f_flags) & (__O_SYNC | O_DSYNC)) ||
+	    IS_SYNC(inode1) || IS_SYNC(inode2))
+		fxr->flags |= XFS_EXCH_RANGE_FSYNC;
+
+	return 0;
+}
+
+/*
+ * Finish a range exchange operation, if it was successful.  Caller must ensure
+ * that the inodes are still locked against any other modifications.
+ */
+int
+xfs_exch_range_finish(
+	struct file		*file1,
+	struct file		*file2)
+{
+	int			error;
+
+	error = file_remove_privs(file1);
+	if (error)
+		return error;
+	if (file_inode(file1) == file_inode(file2))
+		return 0;
+
+	return file_remove_privs(file2);
+}
+
+/* Decide if it's ok to remap the selected range of a given file. */
+STATIC int
+xfs_exch_range_verify_area(
+	struct file		*file,
+	loff_t			pos,
+	struct xfs_exch_range	*fxr)
+{
+	int64_t			len = fxr->length;
+
+	if (pos < 0)
+		return -EINVAL;
+
+	if (fxr->flags & XFS_EXCH_RANGE_TO_EOF)
+		len = min_t(int64_t, len, i_size_read(file_inode(file)) - pos);
+	return remap_verify_area(file, pos, len, true);
+}
+
+/* Prepare for and exchange parts of two files. */
+static inline int
+__xfs_exch_range(
+	struct file		*file1,
+	struct file		*file2,
+	struct xfs_exch_range	*fxr)
+{
+	struct inode		*inode1 = file_inode(file1);
+	struct inode		*inode2 = file_inode(file2);
+	int			ret;
+
+	if ((fxr->flags & ~XFS_EXCH_RANGE_ALL_FLAGS) ||
+	    memchr_inv(&fxr->pad, 0, sizeof(fxr->pad)))
+		return -EINVAL;
+
+	if ((fxr->flags & XFS_EXCH_RANGE_FULL_FILES) &&
+	    (fxr->flags & XFS_EXCH_RANGE_TO_EOF))
+		return -EINVAL;
+
+	/*
+	 * The ioctl enforces that src and dest files are on the same mount.
+	 * However, they only need to be on the same file system.
+	 */
+	if (inode1->i_sb != inode2->i_sb)
+		return -EXDEV;
+
+	/* This only works for regular files. */
+	if (S_ISDIR(inode1->i_mode) || S_ISDIR(inode2->i_mode))
+		return -EISDIR;
+	if (!S_ISREG(inode1->i_mode) || !S_ISREG(inode2->i_mode))
+		return -EINVAL;
+
+	ret = generic_file_rw_checks(file1, file2);
+	if (ret < 0)
+		return ret;
+
+	ret = generic_file_rw_checks(file2, file1);
+	if (ret < 0)
+		return ret;
+
+	ret = xfs_exch_range_verify_area(file1, fxr->file1_offset, fxr);
+	if (ret)
+		return ret;
+
+	ret = xfs_exch_range_verify_area(file2, fxr->file2_offset, fxr);
+	if (ret)
+		return ret;
+
+	ret = -EOPNOTSUPP; /* XXX call out to xfs code */
+	if (ret)
+		return ret;
+
+	fsnotify_modify(file1);
+	if (file2 != file1)
+		fsnotify_modify(file2);
+	return 0;
+}
+
+/* Exchange parts of two files. */
+int
+xfs_exch_range(
+	struct file		*file1,
+	struct file		*file2,
+	struct xfs_exch_range	*fxr)
+{
+	int			error;
+
+	file_start_write(file2);
+	error = __xfs_exch_range(file1, file2, fxr);
+	file_end_write(file2);
+
+	return error;
+}
diff --git a/fs/xfs/xfs_xchgrange.h b/fs/xfs/xfs_xchgrange.h
new file mode 100644
index 0000000000000..9a73b08998b9b
--- /dev/null
+++ b/fs/xfs/xfs_xchgrange.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2020-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_XCHGRANGE_H__
+#define __XFS_XCHGRANGE_H__
+
+/* Prepare generic VFS data structures for file exchanges */
+
+int xfs_exch_range_prep(struct file *file1, struct file *file2,
+		struct xfs_exch_range *fxr, unsigned int blocksize);
+int xfs_exch_range_finish(struct file *file1, struct file *file2);
+
+int xfs_exch_range(struct file *file1, struct file *file2,
+		struct xfs_exch_range *fxr);
+
+#endif /* __XFS_XCHGRANGE_H__ */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 98b7a7a8c42e3..d9badb63bfc29 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2032,6 +2032,7 @@ extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
 extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in,
 				       struct file *file_out, loff_t pos_out,
 				       size_t len, unsigned int flags);
+int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write);
 int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 				    struct file *file_out, loff_t pos_out,
 				    loff_t *len, unsigned int remap_flags,

[PATCH 03/25] xfs: move inode lease breaking functions to xfs_inode.c

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

The lease breaking functions operate at the scope of the entire VFS
inode, not subranges of a file.  Move them to xfs_inode.c since they're
already declared in xfs_inode.h.  This cleanup moves us closer to
having xfs_FOO.h declare only the symbols in xfs_FOO.c.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_file.c  |   61 ---------------------------------------------------
 fs/xfs/xfs_inode.c |   62 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_inode.h |    1 -
 3 files changed, 62 insertions(+), 62 deletions(-)


diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 0a38dde178738..351e00065bf24 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -861,67 +861,6 @@ xfs_file_write_iter(
 	return xfs_file_buffered_write(iocb, from);
 }
 
-static void
-xfs_wait_dax_page(
-	struct inode		*inode)
-{
-	struct xfs_inode        *ip = XFS_I(inode);
-
-	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
-	schedule();
-	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
-}
-
-int
-xfs_break_dax_layouts(
-	struct inode		*inode,
-	bool			*retry)
-{
-	struct page		*page;
-
-	ASSERT(xfs_isilocked(XFS_I(inode), XFS_MMAPLOCK_EXCL));
-
-	page = dax_layout_busy_page(inode->i_mapping);
-	if (!page)
-		return 0;
-
-	*retry = true;
-	return ___wait_var_event(&page->_refcount,
-			atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
-			0, 0, xfs_wait_dax_page(inode));
-}
-
-int
-xfs_break_layouts(
-	struct inode		*inode,
-	uint			*iolock,
-	enum layout_break_reason reason)
-{
-	bool			retry;
-	int			error;
-
-	ASSERT(xfs_isilocked(XFS_I(inode), XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL));
-
-	do {
-		retry = false;
-		switch (reason) {
-		case BREAK_UNMAP:
-			error = xfs_break_dax_layouts(inode, &retry);
-			if (error || retry)
-				break;
-			fallthrough;
-		case BREAK_WRITE:
-			error = xfs_break_leased_layouts(inode, iolock, &retry);
-			break;
-		default:
-			WARN_ON_ONCE(1);
-			error = -EINVAL;
-		}
-	} while (error == 0 && retry);
-
-	return error;
-}
-
 /* Does this file, inode, or mount want synchronous writes? */
 static inline bool xfs_file_sync_writes(struct file *filp)
 {
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 04fa933061c7d..faa3d0abf4551 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -38,6 +38,7 @@
 #include "xfs_ag.h"
 #include "xfs_log_priv.h"
 #include "xfs_health.h"
+#include "xfs_pnfs.h"
 
 struct kmem_cache *xfs_inode_cache;
 
@@ -3953,3 +3954,64 @@ xfs_inode_count_blocks(
 	xfs_bmap_count_leaves(ifp, rblocks);
 	*dblocks = ip->i_nblocks - *rblocks;
 }
+
+static void
+xfs_wait_dax_page(
+	struct inode		*inode)
+{
+	struct xfs_inode        *ip = XFS_I(inode);
+
+	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
+	schedule();
+	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
+}
+
+int
+xfs_break_dax_layouts(
+	struct inode		*inode,
+	bool			*retry)
+{
+	struct page		*page;
+
+	ASSERT(xfs_isilocked(XFS_I(inode), XFS_MMAPLOCK_EXCL));
+
+	page = dax_layout_busy_page(inode->i_mapping);
+	if (!page)
+		return 0;
+
+	*retry = true;
+	return ___wait_var_event(&page->_refcount,
+			atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
+			0, 0, xfs_wait_dax_page(inode));
+}
+
+int
+xfs_break_layouts(
+	struct inode		*inode,
+	uint			*iolock,
+	enum layout_break_reason reason)
+{
+	bool			retry;
+	int			error;
+
+	ASSERT(xfs_isilocked(XFS_I(inode), XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL));
+
+	do {
+		retry = false;
+		switch (reason) {
+		case BREAK_UNMAP:
+			error = xfs_break_dax_layouts(inode, &retry);
+			if (error || retry)
+				break;
+			fallthrough;
+		case BREAK_WRITE:
+			error = xfs_break_leased_layouts(inode, iolock, &retry);
+			break;
+		default:
+			WARN_ON_ONCE(1);
+			error = -EINVAL;
+		}
+	} while (error == 0 && retry);
+
+	return error;
+}
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 764d88198366d..3611597343658 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -565,7 +565,6 @@ xfs_itruncate_extents(
 	return xfs_itruncate_extents_flags(tpp, ip, whichfork, new_size, 0);
 }
 
-/* from xfs_file.c */
 int	xfs_break_dax_layouts(struct inode *inode, bool *retry);
 int	xfs_break_layouts(struct inode *inode, uint *iolock,
 		enum layout_break_reason reason);

[PATCH 04/25] xfs: move xfs_iops.c declarations out of xfs_inode.h

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Similarly, move declarations of public symbols of xfs_iops.c from
xfs_inode.h to xfs_iops.h.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_inode.h |    5 -----
 fs/xfs/xfs_iops.h  |    4 ++++
 2 files changed, 4 insertions(+), 5 deletions(-)


diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 3611597343658..5e2f163fd7445 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -569,11 +569,6 @@ int	xfs_break_dax_layouts(struct inode *inode, bool *retry);
 int	xfs_break_layouts(struct inode *inode, uint *iolock,
 		enum layout_break_reason reason);
 
-/* from xfs_iops.c */
-extern void xfs_setup_inode(struct xfs_inode *ip);
-extern void xfs_setup_iops(struct xfs_inode *ip);
-extern void xfs_diflags_to_iflags(struct xfs_inode *ip, bool init);
-
 static inline void xfs_update_stable_writes(struct xfs_inode *ip)
 {
 	if (bdev_stable_writes(xfs_inode_buftarg(ip)->bt_bdev))
diff --git a/fs/xfs/xfs_iops.h b/fs/xfs/xfs_iops.h
index 7f84a0843b243..8a38c3e2ed0e8 100644
--- a/fs/xfs/xfs_iops.h
+++ b/fs/xfs/xfs_iops.h
@@ -19,4 +19,8 @@ int xfs_vn_setattr_size(struct mnt_idmap *idmap,
 int xfs_inode_init_security(struct inode *inode, struct inode *dir,
 		const struct qstr *qstr);
 
+extern void xfs_setup_inode(struct xfs_inode *ip);
+extern void xfs_setup_iops(struct xfs_inode *ip);
+extern void xfs_diflags_to_iflags(struct xfs_inode *ip, bool init);
+
 #endif /* __XFS_IOPS_H__ */

[PATCH 05/25] xfs: declare xfs_file.c symbols in xfs_file.h

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Move the two public symbols in xfs_file.c to xfs_file.h.  We're about to
add more public symbols in that source file, so let's finally create the
header file.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_file.c  |    1 +
 fs/xfs/xfs_file.h  |   12 ++++++++++++
 fs/xfs/xfs_ioctl.c |    1 +
 fs/xfs/xfs_iops.c  |    1 +
 fs/xfs/xfs_iops.h  |    3 ---
 5 files changed, 15 insertions(+), 3 deletions(-)
 create mode 100644 fs/xfs/xfs_file.h


diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 351e00065bf24..9becf6a075361 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -24,6 +24,7 @@
 #include "xfs_pnfs.h"
 #include "xfs_iomap.h"
 #include "xfs_reflink.h"
+#include "xfs_file.h"
 
 #include <linux/dax.h>
 #include <linux/falloc.h>
diff --git a/fs/xfs/xfs_file.h b/fs/xfs/xfs_file.h
new file mode 100644
index 0000000000000..7d39e3eca56dc
--- /dev/null
+++ b/fs/xfs/xfs_file.h
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2000-2005 Silicon Graphics, Inc.
+ * All Rights Reserved.
+ */
+#ifndef __XFS_FILE_H__
+#define __XFS_FILE_H__
+
+extern const struct file_operations xfs_file_operations;
+extern const struct file_operations xfs_dir_file_operations;
+
+#endif /* __XFS_FILE_H__ */
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index d320f42dab32c..372530698a154 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -40,6 +40,7 @@
 #include "xfs_xattr.h"
 #include "xfs_rtbitmap.h"
 #include "xfs_xchgrange.h"
+#include "xfs_file.h"
 
 #include <linux/mount.h>
 #include <linux/namei.h>
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index a0d77f5f512e2..11382c499c92c 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -25,6 +25,7 @@
 #include "xfs_error.h"
 #include "xfs_ioctl.h"
 #include "xfs_xattr.h"
+#include "xfs_file.h"
 
 #include <linux/posix_acl.h>
 #include <linux/security.h>
diff --git a/fs/xfs/xfs_iops.h b/fs/xfs/xfs_iops.h
index 8a38c3e2ed0e8..3c1a2605ffd2b 100644
--- a/fs/xfs/xfs_iops.h
+++ b/fs/xfs/xfs_iops.h
@@ -8,9 +8,6 @@
 
 struct xfs_inode;
 
-extern const struct file_operations xfs_file_operations;
-extern const struct file_operations xfs_dir_file_operations;
-
 extern ssize_t xfs_vn_listxattr(struct dentry *, char *data, size_t size);
 
 int xfs_vn_setattr_size(struct mnt_idmap *idmap,

Re: [PATCHSET v29.0 34/40] xfs_scrub: fixes for systemd services

[Neal Gompa]

On Sun, Dec 31, 2023 at 2:48 PM Darrick J. Wong <djwong@kernel.org> wrote:
>
> Hi all,
>
> This series fixes deficiencies in the systemd services that were created
> to manage background scans.  First, improve the debian packaging so that
> services get installed at package install time.  Next, fix copyright and
> spdx header omissions.
>
> Finally, fix bugs in the mailer scripts so that scrub failures are
> reported effectively.  Finally, fix xfs_scrub_all to deal with systemd
> restarts causing it to think that a scrub has finished before the
> service actually finishes.
>
> If you're going to start using this code, I strongly recommend pulling
> from my git trees, which are linked below.
>
> This has been running on the djcloud for months with no problems.  Enjoy!
> Comments and questions are, as always, welcome.
>
> --D
>
> xfsprogs git tree:
> https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=scrub-service-fixes
> ---
>  debian/rules                     |    1 +
>  include/builddefs.in             |    2 +-
>  scrub/Makefile                   |   26 ++++++++++++++------
>  scrub/xfs_scrub@.service.in      |    6 ++---
>  scrub/xfs_scrub_all.in           |   49 ++++++++++++++++----------------------
>  scrub/xfs_scrub_fail.in          |   12 ++++++++-
>  scrub/xfs_scrub_fail@.service.in |    4 ++-
>  7 files changed, 55 insertions(+), 45 deletions(-)
>  rename scrub/{xfs_scrub_fail => xfs_scrub_fail.in} (62%)
>

In your Makefile changes, you should be able to drop
PKG_LIB_SCRIPT_DIR entirely from your Makefiles since it should be
unused now, can you fold that into
https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfsprogs-dev.git/commit/?h=scrub-service-fixes&id=1e0dce5c54270f1813f5661c266989917f08baf8
?


-- 
真実はいつも一つ！/ Always, there's only one truth!

[PATCH 06/25] xfs: create a new helper to return a file's allocation unit

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a new helper function to calculate the fundamental allocation
unit (i.e. the smallest unit of space we can allocate) of a file.
Things are going to get hairy with range-exchange on the realtime
device, so prepare for this now.

While we're at it, export xfs_is_falloc_aligned since the next patch
will need it.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_file.c  |   28 ++++++++++------------------
 fs/xfs/xfs_file.h  |    3 +++
 fs/xfs/xfs_inode.c |   13 +++++++++++++
 fs/xfs/xfs_inode.h |    1 +
 4 files changed, 27 insertions(+), 18 deletions(-)


diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 9becf6a075361..8ac3bc98e4369 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -39,33 +39,25 @@ static const struct vm_operations_struct xfs_file_vm_ops;
  * Decide if the given file range is aligned to the size of the fundamental
  * allocation unit for the file.
  */
-static bool
+bool
 xfs_is_falloc_aligned(
 	struct xfs_inode	*ip,
 	loff_t			pos,
 	long long int		len)
 {
-	struct xfs_mount	*mp = ip->i_mount;
-	uint64_t		mask;
+	unsigned int		alloc_unit = xfs_inode_alloc_unitsize(ip);
 
-	if (XFS_IS_REALTIME_INODE(ip)) {
-		if (!is_power_of_2(mp->m_sb.sb_rextsize)) {
-			u64	rextbytes;
-			u32	mod;
+	if (!is_power_of_2(alloc_unit)) {
+		u32	mod;
 
-			rextbytes = XFS_FSB_TO_B(mp, mp->m_sb.sb_rextsize);
-			div_u64_rem(pos, rextbytes, &mod);
-			if (mod)
-				return false;
-			div_u64_rem(len, rextbytes, &mod);
-			return mod == 0;
-		}
-		mask = XFS_FSB_TO_B(mp, mp->m_sb.sb_rextsize) - 1;
-	} else {
-		mask = mp->m_sb.sb_blocksize - 1;
+		div_u64_rem(pos, alloc_unit, &mod);
+		if (mod)
+			return false;
+		div_u64_rem(len, alloc_unit, &mod);
+		return mod == 0;
 	}
 
-	return !((pos | len) & mask);
+	return !((pos | len) & (alloc_unit - 1));
 }
 
 /*
diff --git a/fs/xfs/xfs_file.h b/fs/xfs/xfs_file.h
index 7d39e3eca56dc..2ad91f755caf3 100644
--- a/fs/xfs/xfs_file.h
+++ b/fs/xfs/xfs_file.h
@@ -9,4 +9,7 @@
 extern const struct file_operations xfs_file_operations;
 extern const struct file_operations xfs_dir_file_operations;
 
+bool xfs_is_falloc_aligned(struct xfs_inode *ip, loff_t pos,
+		long long int len);
+
 #endif /* __XFS_FILE_H__ */
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index faa3d0abf4551..15668dbc5ca9e 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -4015,3 +4015,16 @@ xfs_break_layouts(
 
 	return error;
 }
+
+/* Returns the size of fundamental allocation unit for a file, in bytes. */
+unsigned int
+xfs_inode_alloc_unitsize(
+	struct xfs_inode	*ip)
+{
+	unsigned int		blocks = 1;
+
+	if (XFS_IS_REALTIME_INODE(ip))
+		blocks = ip->i_mount->m_sb.sb_rextsize;
+
+	return XFS_FSB_TO_B(ip->i_mount, blocks);
+}
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 5e2f163fd7445..e1d60ba75bbdd 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -625,6 +625,7 @@ int xfs_inode_reload_unlinked(struct xfs_inode *ip);
 bool xfs_ifork_zapped(const struct xfs_inode *ip, int whichfork);
 void xfs_inode_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_filblks_t *dblocks, xfs_filblks_t *rblocks);
+unsigned int xfs_inode_alloc_unitsize(struct xfs_inode *ip);
 
 struct xfs_dir_update_params {
 	const struct xfs_inode	*dp;

[PATCH 07/25] xfs: refactor non-power-of-two alignment checks

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a helper function that can compute if a 64-bit number is an
integer multiple of a 32-bit number, where the 32-bit number is not
required to be an even power of two.  This is needed for some new code
for the realtime device, where we can set 37k allocation units and then
have to remap them.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_file.c  |   12 +++---------
 fs/xfs/xfs_linux.h |    5 +++++
 2 files changed, 8 insertions(+), 9 deletions(-)


diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 8ac3bc98e4369..fdbeb6c3fbc44 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -47,15 +47,9 @@ xfs_is_falloc_aligned(
 {
 	unsigned int		alloc_unit = xfs_inode_alloc_unitsize(ip);
 
-	if (!is_power_of_2(alloc_unit)) {
-		u32	mod;
-
-		div_u64_rem(pos, alloc_unit, &mod);
-		if (mod)
-			return false;
-		div_u64_rem(len, alloc_unit, &mod);
-		return mod == 0;
-	}
+	if (!is_power_of_2(alloc_unit))
+		return isaligned_64(pos, alloc_unit) &&
+		       isaligned_64(len, alloc_unit);
 
 	return !((pos | len) & (alloc_unit - 1));
 }
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index c24e0d52bc04e..13511ff810d18 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -200,6 +200,11 @@ static inline uint64_t howmany_64(uint64_t x, uint32_t y)
 	return x;
 }
 
+static inline bool isaligned_64(uint64_t x, uint32_t y)
+{
+	return do_div(x, y) == 0;
+}
+
 /* If @b is a power of 2, return log2(b).  Else return -1. */
 static inline int8_t log2_if_power2(unsigned long b)
 {

[PATCH 08/25] xfs: parameterize all the incompat log feature helpers

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

We're about to define a new XFS_SB_FEAT_INCOMPAT_LOG_ bit, which means
that callers will soon require the ability to toggle on and off
different log incompat feature bits.  Parameterize the
xlog_{use,drop}_incompat_feat and xfs_sb_remove_incompat_log_features
functions so that callers can specify which feature they're trying to
use and so that we can clear individual log incompat bits as needed.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_format.h |    5 +++--
 fs/xfs/xfs_log.c           |   34 +++++++++++++++++++++++++---------
 fs/xfs/xfs_log.h           |    9 ++++++---
 fs/xfs/xfs_log_priv.h      |    2 +-
 fs/xfs/xfs_log_recover.c   |    3 ++-
 fs/xfs/xfs_mount.c         |   11 +++++------
 fs/xfs/xfs_mount.h         |    2 +-
 fs/xfs/xfs_xattr.c         |    6 +++---
 8 files changed, 46 insertions(+), 26 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index e6ca188e22712..4baafff619789 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -404,9 +404,10 @@ xfs_sb_has_incompat_log_feature(
 
 static inline void
 xfs_sb_remove_incompat_log_features(
-	struct xfs_sb	*sbp)
+	struct xfs_sb	*sbp,
+	uint32_t	feature)
 {
-	sbp->sb_features_log_incompat &= ~XFS_SB_FEAT_INCOMPAT_LOG_ALL;
+	sbp->sb_features_log_incompat &= ~feature;
 }
 
 static inline void
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index a9a8311e112c2..f62a6e233689c 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1048,7 +1048,7 @@ xfs_log_quiesce(
 	 * failures, though it's not fatal to have a higher log feature
 	 * protection level than the log contents actually require.
 	 */
-	if (xfs_clear_incompat_log_features(mp)) {
+	if (xfs_clear_incompat_log_features(mp, XFS_SB_FEAT_INCOMPAT_LOG_ALL)) {
 		int error;
 
 		error = xfs_sync_sb(mp, false);
@@ -1455,6 +1455,7 @@ xlog_clear_incompat(
 	struct xlog		*log)
 {
 	struct xfs_mount	*mp = log->l_mp;
+	uint32_t		incompat_mask = 0;
 
 	if (!xfs_sb_has_incompat_log_feature(&mp->m_sb,
 				XFS_SB_FEAT_INCOMPAT_LOG_ALL))
@@ -1463,11 +1464,16 @@ xlog_clear_incompat(
 	if (log->l_covered_state != XLOG_STATE_COVER_DONE2)
 		return;
 
-	if (!down_write_trylock(&log->l_incompat_users))
+	if (down_write_trylock(&log->l_incompat_xattrs))
+		incompat_mask |= XFS_SB_FEAT_INCOMPAT_LOG_XATTRS;
+
+	if (!incompat_mask)
 		return;
 
-	xfs_clear_incompat_log_features(mp);
-	up_write(&log->l_incompat_users);
+	xfs_clear_incompat_log_features(mp, incompat_mask);
+
+	if (incompat_mask & XFS_SB_FEAT_INCOMPAT_LOG_XATTRS)
+		up_write(&log->l_incompat_xattrs);
 }
 
 /*
@@ -1585,7 +1591,7 @@ xlog_alloc_log(
 	}
 	log->l_sectBBsize = 1 << log2_size;
 
-	init_rwsem(&log->l_incompat_users);
+	init_rwsem(&log->l_incompat_xattrs);
 
 	xlog_get_iclog_buffer_size(mp, log);
 
@@ -3877,15 +3883,25 @@ xfs_log_check_lsn(
  */
 void
 xlog_use_incompat_feat(
-	struct xlog		*log)
+	struct xlog		*log,
+	enum xlog_incompat_feat	what)
 {
-	down_read(&log->l_incompat_users);
+	switch (what) {
+	case XLOG_INCOMPAT_FEAT_XATTRS:
+		down_read(&log->l_incompat_xattrs);
+		break;
+	}
 }
 
 /* Notify the log that we've finished using log incompat features. */
 void
 xlog_drop_incompat_feat(
-	struct xlog		*log)
+	struct xlog		*log,
+	enum xlog_incompat_feat	what)
 {
-	up_read(&log->l_incompat_users);
+	switch (what) {
+	case XLOG_INCOMPAT_FEAT_XATTRS:
+		up_read(&log->l_incompat_xattrs);
+		break;
+	}
 }
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index 2728886c29639..d187f64459093 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -159,8 +159,11 @@ bool	xfs_log_check_lsn(struct xfs_mount *, xfs_lsn_t);
 xfs_lsn_t xlog_grant_push_threshold(struct xlog *log, int need_bytes);
 bool	  xlog_force_shutdown(struct xlog *log, uint32_t shutdown_flags);
 
-void xlog_use_incompat_feat(struct xlog *log);
-void xlog_drop_incompat_feat(struct xlog *log);
-int xfs_attr_use_log_assist(struct xfs_mount *mp);
+enum xlog_incompat_feat {
+	XLOG_INCOMPAT_FEAT_XATTRS = XFS_SB_FEAT_INCOMPAT_LOG_XATTRS,
+};
+
+void xlog_use_incompat_feat(struct xlog *log, enum xlog_incompat_feat what);
+void xlog_drop_incompat_feat(struct xlog *log, enum xlog_incompat_feat what);
 
 #endif	/* __XFS_LOG_H__ */
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index e30c06ec20e33..304aed840f962 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -452,7 +452,7 @@ struct xlog {
 	uint32_t		l_iclog_roundoff;/* padding roundoff */
 
 	/* Users of log incompat features should take a read lock. */
-	struct rw_semaphore	l_incompat_users;
+	struct rw_semaphore	l_incompat_xattrs;
 };
 
 /*
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 53ffbb9dfd974..6048f1b08acc0 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -3479,7 +3479,8 @@ xlog_recover_finish(
 	 * longer anything to protect.  We rely on the AIL push to write out the
 	 * updated superblock after everything else.
 	 */
-	if (xfs_clear_incompat_log_features(log->l_mp)) {
+	if (xfs_clear_incompat_log_features(log->l_mp,
+				XFS_SB_FEAT_INCOMPAT_LOG_ALL)) {
 		error = xfs_sync_sb(log->l_mp, false);
 		if (error < 0) {
 			xfs_alert(log->l_mp,
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 469eeab347518..85c7ca0b211b1 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1362,13 +1362,13 @@ xfs_add_incompat_log_feature(
  */
 bool
 xfs_clear_incompat_log_features(
-	struct xfs_mount	*mp)
+	struct xfs_mount	*mp,
+	uint32_t		features)
 {
 	bool			ret = false;
 
 	if (!xfs_has_crc(mp) ||
-	    !xfs_sb_has_incompat_log_feature(&mp->m_sb,
-				XFS_SB_FEAT_INCOMPAT_LOG_ALL) ||
+	    !xfs_sb_has_incompat_log_feature(&mp->m_sb, features) ||
 	    xfs_is_shutdown(mp))
 		return false;
 
@@ -1380,9 +1380,8 @@ xfs_clear_incompat_log_features(
 	xfs_buf_lock(mp->m_sb_bp);
 	xfs_buf_hold(mp->m_sb_bp);
 
-	if (xfs_sb_has_incompat_log_feature(&mp->m_sb,
-				XFS_SB_FEAT_INCOMPAT_LOG_ALL)) {
-		xfs_sb_remove_incompat_log_features(&mp->m_sb);
+	if (xfs_sb_has_incompat_log_feature(&mp->m_sb, features)) {
+		xfs_sb_remove_incompat_log_features(&mp->m_sb, features);
 		ret = true;
 	}
 
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 772c913bcd2bd..257bef8019307 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -565,7 +565,7 @@ struct xfs_error_cfg * xfs_error_get_cfg(struct xfs_mount *mp,
 		int error_class, int error);
 void xfs_force_summary_recalc(struct xfs_mount *mp);
 int xfs_add_incompat_log_feature(struct xfs_mount *mp, uint32_t feature);
-bool xfs_clear_incompat_log_features(struct xfs_mount *mp);
+bool xfs_clear_incompat_log_features(struct xfs_mount *mp, uint32_t feature);
 void xfs_mod_delalloc(struct xfs_mount *mp, int64_t delta);
 
 #endif	/* __XFS_MOUNT_H__ */
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index 364104e1b38ae..0e0e25e386f17 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -37,7 +37,7 @@ xfs_attr_grab_log_assist(
 	 * Protect ourselves from an idle log clearing the logged xattrs log
 	 * incompat feature bit.
 	 */
-	xlog_use_incompat_feat(mp->m_log);
+	xlog_use_incompat_feat(mp->m_log, XLOG_INCOMPAT_FEAT_XATTRS);
 
 	/*
 	 * If log-assisted xattrs are already enabled, the caller can use the
@@ -68,7 +68,7 @@ xfs_attr_grab_log_assist(
 
 	return 0;
 drop_incompat:
-	xlog_drop_incompat_feat(mp->m_log);
+	xlog_drop_incompat_feat(mp->m_log, XLOG_INCOMPAT_FEAT_XATTRS);
 	return error;
 }
 
@@ -76,7 +76,7 @@ static inline void
 xfs_attr_rele_log_assist(
 	struct xfs_mount	*mp)
 {
-	xlog_drop_incompat_feat(mp->m_log);
+	xlog_drop_incompat_feat(mp->m_log, XLOG_INCOMPAT_FEAT_XATTRS);
 }
 
 static inline bool

[PATCH 09/25] xfs: create a log incompat flag for atomic extent swapping

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a log incompat flag so that we only attempt to process swap
extent log items if the filesystem supports it, and a geometry flag to
advertise support if it's present.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_format.h  |    6 +++
 fs/xfs/libxfs/xfs_fs.h      |    3 ++
 fs/xfs/libxfs/xfs_sb.c      |    3 ++
 fs/xfs/libxfs/xfs_swapext.h |   75 +++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 87 insertions(+)
 create mode 100644 fs/xfs/libxfs/xfs_swapext.h


diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 4baafff619789..c0209bd21dba1 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -391,6 +391,12 @@ xfs_sb_has_incompat_feature(
 }
 
 #define XFS_SB_FEAT_INCOMPAT_LOG_XATTRS   (1 << 0)	/* Delayed Attributes */
+
+/*
+ * Log contains SXI log intent items which are not otherwise protected by
+ * an INCOMPAT/RO_COMPAT feature flag.
+ */
+#define XFS_SB_FEAT_INCOMPAT_LOG_SWAPEXT  (1U << 31)
 #define XFS_SB_FEAT_INCOMPAT_LOG_ALL \
 	(XFS_SB_FEAT_INCOMPAT_LOG_XATTRS)
 #define XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN	~XFS_SB_FEAT_INCOMPAT_LOG_ALL
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index ec92e6ded6b8b..63a145e50350b 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -240,6 +240,9 @@ typedef struct xfs_fsop_resblks {
 #define XFS_FSOP_GEOM_FLAGS_INOBTCNT	(1 << 22) /* inobt btree counter */
 #define XFS_FSOP_GEOM_FLAGS_NREXT64	(1 << 23) /* large extent counters */
 
+/* atomic file extent swap available to userspace */
+#define XFS_FSOP_GEOM_FLAGS_ATOMIC_SWAP	(1U << 31)
+
 /*
  * Minimum and maximum sizes need for growth checks.
  *
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 7f2a5aee0ab83..5de377c2b0fea 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -26,6 +26,7 @@
 #include "xfs_health.h"
 #include "xfs_ag.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_swapext.h"
 
 /*
  * Physical superblock buffer manipulations. Shared with libxfs in userspace.
@@ -1258,6 +1259,8 @@ xfs_fs_geometry(
 	}
 	if (xfs_has_large_extent_counts(mp))
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_NREXT64;
+	if (xfs_atomic_swap_supported(mp))
+		geo->flags |= XFS_FSOP_GEOM_FLAGS_ATOMIC_SWAP;
 	geo->rtsectsize = sbp->sb_blocksize;
 	geo->dirblocksize = xfs_dir2_dirblock_bytes(sbp);
 
diff --git a/fs/xfs/libxfs/xfs_swapext.h b/fs/xfs/libxfs/xfs_swapext.h
new file mode 100644
index 0000000000000..01bb3271f6474
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_swapext.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2020-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SWAPEXT_H_
+#define __XFS_SWAPEXT_H_ 1
+
+/*
+ * Decide if this filesystem supports the minimum feature set required to use
+ * the swapext iteration code in non-atomic swap mode.  This mode uses the
+ * BUI log items introduced for the rmapbt and reflink features, but does not
+ * use swapext log items to track progress over a file range.
+ */
+static inline bool
+xfs_swapext_supports_nonatomic(
+	struct xfs_mount	*mp)
+{
+	return xfs_has_reflink(mp) || xfs_has_rmapbt(mp);
+}
+
+/*
+ * Decide if this filesystem has a new enough permanent feature set to protect
+ * swapext log items from being replayed on a kernel that does not have
+ * XFS_SB_FEAT_INCOMPAT_LOG_SWAPEXT set.
+ */
+static inline bool
+xfs_swapext_can_use_without_log_assistance(
+	struct xfs_mount	*mp)
+{
+	if (!xfs_sb_is_v5(&mp->m_sb))
+		return false;
+
+	if (xfs_sb_has_incompat_feature(&mp->m_sb,
+				~(XFS_SB_FEAT_INCOMPAT_FTYPE |
+				  XFS_SB_FEAT_INCOMPAT_SPINODES |
+				  XFS_SB_FEAT_INCOMPAT_META_UUID |
+				  XFS_SB_FEAT_INCOMPAT_BIGTIME |
+				  XFS_SB_FEAT_INCOMPAT_NREXT64)))
+		return true;
+
+	return false;
+}
+
+/*
+ * Decide if atomic extent swapping could be used on this filesystem.  This
+ * does not say anything about the filesystem's readiness to do that.
+ */
+static inline bool
+xfs_atomic_swap_supported(
+	struct xfs_mount	*mp)
+{
+	/*
+	 * In theory, we could support atomic extent swapping by setting
+	 * XFS_SB_FEAT_INCOMPAT_LOG_SWAPEXT on any filesystem and that would be
+	 * sufficient to protect the swapext log items that would be created.
+	 * However, we don't want to enable new features on a really old
+	 * filesystem, so we'll only advertise atomic swap support on the ones
+	 * that support BUI log items.
+	 */
+	if (xfs_swapext_supports_nonatomic(mp))
+		return true;
+
+	/*
+	 * If the filesystem has an RO_COMPAT or INCOMPAT bit that we don't
+	 * recognize, then it's new enough not to need INCOMPAT_LOG_SWAPEXT
+	 * to protect swapext log items.
+	 */
+	if (xfs_swapext_can_use_without_log_assistance(mp))
+		return true;
+
+	return false;
+}
+
+#endif /* __XFS_SWAPEXT_H_ */

[PATCH 10/25] xfs: introduce a swap-extent log intent item

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Introduce a new intent log item to handle swapping extents.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Makefile                 |    1 
 fs/xfs/libxfs/xfs_log_format.h  |   51 ++++++++
 fs/xfs/libxfs/xfs_log_recover.h |    2 
 fs/xfs/xfs_log_recover.c        |    2 
 fs/xfs/xfs_super.c              |   19 +++
 fs/xfs/xfs_swapext_item.c       |  236 +++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_swapext_item.h       |   56 +++++++++
 7 files changed, 364 insertions(+), 3 deletions(-)
 create mode 100644 fs/xfs/xfs_swapext_item.c
 create mode 100644 fs/xfs/xfs_swapext_item.h


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index d0b538c11faaf..95f9b32d947c4 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -111,6 +111,7 @@ xfs-y				+= xfs_log.o \
 				   xfs_iunlink_item.o \
 				   xfs_refcount_item.o \
 				   xfs_rmap_item.o \
+				   xfs_swapext_item.o \
 				   xfs_log_recover.o \
 				   xfs_trans_ail.o \
 				   xfs_trans_buf.o
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index 16872972e1e97..24c3d5dc36182 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -117,8 +117,9 @@ struct xfs_unmount_log_format {
 #define XLOG_REG_TYPE_ATTRD_FORMAT	28
 #define XLOG_REG_TYPE_ATTR_NAME	29
 #define XLOG_REG_TYPE_ATTR_VALUE	30
-#define XLOG_REG_TYPE_MAX		30
-
+#define XLOG_REG_TYPE_SXI_FORMAT	31
+#define XLOG_REG_TYPE_SXD_FORMAT	32
+#define XLOG_REG_TYPE_MAX		32
 
 /*
  * Flags to log operation header
@@ -243,6 +244,8 @@ typedef struct xfs_trans_header {
 #define	XFS_LI_BUD		0x1245
 #define	XFS_LI_ATTRI		0x1246  /* attr set/remove intent*/
 #define	XFS_LI_ATTRD		0x1247  /* attr set/remove done */
+#define	XFS_LI_SXI		0x1248  /* extent swap intent */
+#define	XFS_LI_SXD		0x1249  /* extent swap done */
 
 #define XFS_LI_TYPE_DESC \
 	{ XFS_LI_EFI,		"XFS_LI_EFI" }, \
@@ -260,7 +263,9 @@ typedef struct xfs_trans_header {
 	{ XFS_LI_BUI,		"XFS_LI_BUI" }, \
 	{ XFS_LI_BUD,		"XFS_LI_BUD" }, \
 	{ XFS_LI_ATTRI,		"XFS_LI_ATTRI" }, \
-	{ XFS_LI_ATTRD,		"XFS_LI_ATTRD" }
+	{ XFS_LI_ATTRD,		"XFS_LI_ATTRD" }, \
+	{ XFS_LI_SXI,		"XFS_LI_SXI" }, \
+	{ XFS_LI_SXD,		"XFS_LI_SXD" }
 
 /*
  * Inode Log Item Format definitions.
@@ -878,6 +883,46 @@ struct xfs_bud_log_format {
 	uint64_t		bud_bui_id;	/* id of corresponding bui */
 };
 
+/*
+ * SXI/SXD (extent swapping) log format definitions
+ */
+
+struct xfs_swap_extent {
+	uint64_t		sx_inode1;
+	uint64_t		sx_inode2;
+	uint64_t		sx_startoff1;
+	uint64_t		sx_startoff2;
+	uint64_t		sx_blockcount;
+	uint64_t		sx_flags;
+	int64_t			sx_isize1;
+	int64_t			sx_isize2;
+};
+
+#define XFS_SWAP_EXT_FLAGS		(0)
+
+#define XFS_SWAP_EXT_STRINGS
+
+/* This is the structure used to lay out an sxi log item in the log. */
+struct xfs_sxi_log_format {
+	uint16_t		sxi_type;	/* sxi log item type */
+	uint16_t		sxi_size;	/* size of this item */
+	uint32_t		__pad;		/* must be zero */
+	uint64_t		sxi_id;		/* sxi identifier */
+	struct xfs_swap_extent	sxi_extent;	/* extent to swap */
+};
+
+/*
+ * This is the structure used to lay out an sxd log item in the
+ * log.  The sxd_extents array is a variable size array whose
+ * size is given by sxd_nextents;
+ */
+struct xfs_sxd_log_format {
+	uint16_t		sxd_type;	/* sxd log item type */
+	uint16_t		sxd_size;	/* size of this item */
+	uint32_t		__pad;
+	uint64_t		sxd_sxi_id;	/* id of corresponding bui */
+};
+
 /*
  * Dquot Log format definitions.
  *
diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h
index 9fe7a9564bca9..891221b0b83aa 100644
--- a/fs/xfs/libxfs/xfs_log_recover.h
+++ b/fs/xfs/libxfs/xfs_log_recover.h
@@ -75,6 +75,8 @@ extern const struct xlog_recover_item_ops xlog_cui_item_ops;
 extern const struct xlog_recover_item_ops xlog_cud_item_ops;
 extern const struct xlog_recover_item_ops xlog_attri_item_ops;
 extern const struct xlog_recover_item_ops xlog_attrd_item_ops;
+extern const struct xlog_recover_item_ops xlog_sxi_item_ops;
+extern const struct xlog_recover_item_ops xlog_sxd_item_ops;
 
 /*
  * Macros, structures, prototypes for internal log manager use.
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 6048f1b08acc0..628d7915120b0 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1790,6 +1790,8 @@ static const struct xlog_recover_item_ops *xlog_recover_item_ops[] = {
 	&xlog_bud_item_ops,
 	&xlog_attri_item_ops,
 	&xlog_attrd_item_ops,
+	&xlog_sxi_item_ops,
+	&xlog_sxd_item_ops,
 };
 
 static const struct xlog_recover_item_ops *
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index d535445129752..e6e8e8fb17a19 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -43,6 +43,7 @@
 #include "xfs_iunlink_item.h"
 #include "xfs_dahash_test.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_swapext_item.h"
 #include "scrub/stats.h"
 #include "scrub/rcbag_btree.h"
 
@@ -2196,8 +2197,24 @@ xfs_init_caches(void)
 	if (!xfs_iunlink_cache)
 		goto out_destroy_attri_cache;
 
+	xfs_sxd_cache = kmem_cache_create("xfs_sxd_item",
+					 sizeof(struct xfs_sxd_log_item),
+					 0, 0, NULL);
+	if (!xfs_sxd_cache)
+		goto out_destroy_iul_cache;
+
+	xfs_sxi_cache = kmem_cache_create("xfs_sxi_item",
+					 sizeof(struct xfs_sxi_log_item),
+					 0, 0, NULL);
+	if (!xfs_sxi_cache)
+		goto out_destroy_sxd_cache;
+
 	return 0;
 
+ out_destroy_sxd_cache:
+	kmem_cache_destroy(xfs_sxd_cache);
+ out_destroy_iul_cache:
+	kmem_cache_destroy(xfs_iunlink_cache);
  out_destroy_attri_cache:
 	kmem_cache_destroy(xfs_attri_cache);
  out_destroy_attrd_cache:
@@ -2254,6 +2271,8 @@ xfs_destroy_caches(void)
 	 * destroy caches.
 	 */
 	rcu_barrier();
+	kmem_cache_destroy(xfs_sxd_cache);
+	kmem_cache_destroy(xfs_sxi_cache);
 	kmem_cache_destroy(xfs_iunlink_cache);
 	kmem_cache_destroy(xfs_attri_cache);
 	kmem_cache_destroy(xfs_attrd_cache);
diff --git a/fs/xfs/xfs_swapext_item.c b/fs/xfs/xfs_swapext_item.c
new file mode 100644
index 0000000000000..0117735913cf1
--- /dev/null
+++ b/fs/xfs/xfs_swapext_item.c
@@ -0,0 +1,236 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2020-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_bit.h"
+#include "xfs_shared.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_inode.h"
+#include "xfs_trans.h"
+#include "xfs_trans_priv.h"
+#include "xfs_swapext_item.h"
+#include "xfs_log.h"
+#include "xfs_bmap.h"
+#include "xfs_icache.h"
+#include "xfs_trans_space.h"
+#include "xfs_error.h"
+#include "xfs_log_priv.h"
+#include "xfs_log_recover.h"
+
+struct kmem_cache	*xfs_sxi_cache;
+struct kmem_cache	*xfs_sxd_cache;
+
+static const struct xfs_item_ops xfs_sxi_item_ops;
+
+static inline struct xfs_sxi_log_item *SXI_ITEM(struct xfs_log_item *lip)
+{
+	return container_of(lip, struct xfs_sxi_log_item, sxi_item);
+}
+
+STATIC void
+xfs_sxi_item_free(
+	struct xfs_sxi_log_item	*sxi_lip)
+{
+	kmem_free(sxi_lip->sxi_item.li_lv_shadow);
+	kmem_cache_free(xfs_sxi_cache, sxi_lip);
+}
+
+/*
+ * Freeing the SXI requires that we remove it from the AIL if it has already
+ * been placed there. However, the SXI may not yet have been placed in the AIL
+ * when called by xfs_sxi_release() from SXD processing due to the ordering of
+ * committed vs unpin operations in bulk insert operations. Hence the reference
+ * count to ensure only the last caller frees the SXI.
+ */
+STATIC void
+xfs_sxi_release(
+	struct xfs_sxi_log_item	*sxi_lip)
+{
+	ASSERT(atomic_read(&sxi_lip->sxi_refcount) > 0);
+	if (atomic_dec_and_test(&sxi_lip->sxi_refcount)) {
+		xfs_trans_ail_delete(&sxi_lip->sxi_item, 0);
+		xfs_sxi_item_free(sxi_lip);
+	}
+}
+
+
+STATIC void
+xfs_sxi_item_size(
+	struct xfs_log_item	*lip,
+	int			*nvecs,
+	int			*nbytes)
+{
+	*nvecs += 1;
+	*nbytes += sizeof(struct xfs_sxi_log_format);
+}
+
+/*
+ * This is called to fill in the vector of log iovecs for the given sxi log
+ * item. We use only 1 iovec, and we point that at the sxi_log_format structure
+ * embedded in the sxi item.
+ */
+STATIC void
+xfs_sxi_item_format(
+	struct xfs_log_item	*lip,
+	struct xfs_log_vec	*lv)
+{
+	struct xfs_sxi_log_item	*sxi_lip = SXI_ITEM(lip);
+	struct xfs_log_iovec	*vecp = NULL;
+
+	sxi_lip->sxi_format.sxi_type = XFS_LI_SXI;
+	sxi_lip->sxi_format.sxi_size = 1;
+
+	xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_SXI_FORMAT,
+			&sxi_lip->sxi_format,
+			sizeof(struct xfs_sxi_log_format));
+}
+
+/*
+ * The unpin operation is the last place an SXI is manipulated in the log. It
+ * is either inserted in the AIL or aborted in the event of a log I/O error. In
+ * either case, the SXI transaction has been successfully committed to make it
+ * this far. Therefore, we expect whoever committed the SXI to either construct
+ * and commit the SXD or drop the SXD's reference in the event of error. Simply
+ * drop the log's SXI reference now that the log is done with it.
+ */
+STATIC void
+xfs_sxi_item_unpin(
+	struct xfs_log_item	*lip,
+	int			remove)
+{
+	struct xfs_sxi_log_item	*sxi_lip = SXI_ITEM(lip);
+
+	xfs_sxi_release(sxi_lip);
+}
+
+/*
+ * The SXI has been either committed or aborted if the transaction has been
+ * cancelled. If the transaction was cancelled, an SXD isn't going to be
+ * constructed and thus we free the SXI here directly.
+ */
+STATIC void
+xfs_sxi_item_release(
+	struct xfs_log_item	*lip)
+{
+	xfs_sxi_release(SXI_ITEM(lip));
+}
+
+/* Allocate and initialize an sxi item with the given number of extents. */
+STATIC struct xfs_sxi_log_item *
+xfs_sxi_init(
+	struct xfs_mount	*mp)
+
+{
+	struct xfs_sxi_log_item	*sxi_lip;
+
+	sxi_lip = kmem_cache_zalloc(xfs_sxi_cache, GFP_KERNEL | __GFP_NOFAIL);
+
+	xfs_log_item_init(mp, &sxi_lip->sxi_item, XFS_LI_SXI, &xfs_sxi_item_ops);
+	sxi_lip->sxi_format.sxi_id = (uintptr_t)(void *)sxi_lip;
+	atomic_set(&sxi_lip->sxi_refcount, 2);
+
+	return sxi_lip;
+}
+
+static inline struct xfs_sxd_log_item *SXD_ITEM(struct xfs_log_item *lip)
+{
+	return container_of(lip, struct xfs_sxd_log_item, sxd_item);
+}
+
+STATIC bool
+xfs_sxi_item_match(
+	struct xfs_log_item	*lip,
+	uint64_t		intent_id)
+{
+	return SXI_ITEM(lip)->sxi_format.sxi_id == intent_id;
+}
+
+static const struct xfs_item_ops xfs_sxi_item_ops = {
+	.flags		= XFS_ITEM_INTENT,
+	.iop_size	= xfs_sxi_item_size,
+	.iop_format	= xfs_sxi_item_format,
+	.iop_unpin	= xfs_sxi_item_unpin,
+	.iop_release	= xfs_sxi_item_release,
+	.iop_match	= xfs_sxi_item_match,
+};
+
+/*
+ * This routine is called to create an in-core extent swapext update item from
+ * the sxi format structure which was logged on disk.  It allocates an in-core
+ * sxi, copies the extents from the format structure into it, and adds the sxi
+ * to the AIL with the given LSN.
+ */
+STATIC int
+xlog_recover_sxi_commit_pass2(
+	struct xlog			*log,
+	struct list_head		*buffer_list,
+	struct xlog_recover_item	*item,
+	xfs_lsn_t			lsn)
+{
+	struct xfs_mount		*mp = log->l_mp;
+	struct xfs_sxi_log_item		*sxi_lip;
+	struct xfs_sxi_log_format	*sxi_formatp;
+	size_t				len;
+
+	sxi_formatp = item->ri_buf[0].i_addr;
+
+	if (sxi_formatp->__pad != 0) {
+		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
+		return -EFSCORRUPTED;
+	}
+
+	len = sizeof(struct xfs_sxi_log_format);
+	if (item->ri_buf[0].i_len != len) {
+		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
+		return -EFSCORRUPTED;
+	}
+
+	sxi_lip = xfs_sxi_init(mp);
+	memcpy(&sxi_lip->sxi_format, sxi_formatp, len);
+
+	/* not implemented yet */
+	return -EIO;
+}
+
+const struct xlog_recover_item_ops xlog_sxi_item_ops = {
+	.item_type		= XFS_LI_SXI,
+	.commit_pass2		= xlog_recover_sxi_commit_pass2,
+};
+
+/*
+ * This routine is called when an SXD format structure is found in a committed
+ * transaction in the log. Its purpose is to cancel the corresponding SXI if it
+ * was still in the log. To do this it searches the AIL for the SXI with an id
+ * equal to that in the SXD format structure. If we find it we drop the SXD
+ * reference, which removes the SXI from the AIL and frees it.
+ */
+STATIC int
+xlog_recover_sxd_commit_pass2(
+	struct xlog			*log,
+	struct list_head		*buffer_list,
+	struct xlog_recover_item	*item,
+	xfs_lsn_t			lsn)
+{
+	struct xfs_sxd_log_format	*sxd_formatp;
+
+	sxd_formatp = item->ri_buf[0].i_addr;
+	if (item->ri_buf[0].i_len != sizeof(struct xfs_sxd_log_format)) {
+		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
+		return -EFSCORRUPTED;
+	}
+
+	xlog_recover_release_intent(log, XFS_LI_SXI, sxd_formatp->sxd_sxi_id);
+	return 0;
+}
+
+const struct xlog_recover_item_ops xlog_sxd_item_ops = {
+	.item_type		= XFS_LI_SXD,
+	.commit_pass2		= xlog_recover_sxd_commit_pass2,
+};
diff --git a/fs/xfs/xfs_swapext_item.h b/fs/xfs/xfs_swapext_item.h
new file mode 100644
index 0000000000000..d816ab842a603
--- /dev/null
+++ b/fs/xfs/xfs_swapext_item.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2020-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef	__XFS_SWAPEXT_ITEM_H__
+#define	__XFS_SWAPEXT_ITEM_H__
+
+/*
+ * The extent swapping intent item help us perform atomic extent swaps between
+ * two inode forks.  It does this by tracking the range of logical offsets that
+ * still need to be swapped, and relogs as progress happens.
+ *
+ * *I items should be recorded in the *first* of a series of rolled
+ * transactions, and the *D items should be recorded in the same transaction
+ * that records the associated bmbt updates.
+ *
+ * Should the system crash after the commit of the first transaction but
+ * before the commit of the final transaction in a series, log recovery will
+ * use the redo information recorded by the intent items to replay the
+ * rest of the extent swaps.
+ */
+
+/* kernel only SXI/SXD definitions */
+
+struct xfs_mount;
+struct kmem_cache;
+
+/*
+ * This is the "swapext update intent" log item.  It is used to log the fact
+ * that we are swapping extents between two files.  It is used in conjunction
+ * with the "swapext update done" log item described below.
+ *
+ * These log items follow the same rules as struct xfs_efi_log_item; see the
+ * comments about that structure (in xfs_extfree_item.h) for more details.
+ */
+struct xfs_sxi_log_item {
+	struct xfs_log_item		sxi_item;
+	atomic_t			sxi_refcount;
+	struct xfs_sxi_log_format	sxi_format;
+};
+
+/*
+ * This is the "swapext update done" log item.  It is used to log the fact that
+ * some extent swapping mentioned in an earlier sxi item have been performed.
+ */
+struct xfs_sxd_log_item {
+	struct xfs_log_item		sxd_item;
+	struct xfs_sxi_log_item		*sxd_intent_log_item;
+	struct xfs_sxd_log_format	sxd_format;
+};
+
+extern struct kmem_cache	*xfs_sxi_cache;
+extern struct kmem_cache	*xfs_sxd_cache;
+
+#endif	/* __XFS_SWAPEXT_ITEM_H__ */

[PATCH 11/25] xfs: create deferred log items for extent swapping

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Now that we've created the skeleton of a log intent item to track and
restart extent swap operations, add the upper level logic to commit
intent items and turn them into concrete work recorded in the log.  We
use the deferred item "multihop" feature that was introduced a few
patches ago to constrain the number of active swap operations to one per
thread.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Makefile                 |    1 
 fs/xfs/libxfs/xfs_bmap.h        |    2 
 fs/xfs/libxfs/xfs_defer.c       |    6 
 fs/xfs/libxfs/xfs_defer.h       |    2 
 fs/xfs/libxfs/xfs_format.h      |    6 
 fs/xfs/libxfs/xfs_log_format.h  |   31 +
 fs/xfs/libxfs/xfs_swapext.c     | 1031 +++++++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_swapext.h     |  143 +++++
 fs/xfs/libxfs/xfs_trans_space.h |    4 
 fs/xfs/xfs_swapext_item.c       |  394 +++++++++++++++
 fs/xfs/xfs_swapext_item.h       |    4 
 fs/xfs/xfs_trace.c              |    1 
 fs/xfs/xfs_trace.h              |  216 ++++++++
 fs/xfs/xfs_xchgrange.c          |   50 ++
 fs/xfs/xfs_xchgrange.h          |   10 
 15 files changed, 1888 insertions(+), 13 deletions(-)
 create mode 100644 fs/xfs/libxfs/xfs_swapext.c


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 95f9b32d947c4..7e4e7b5e8a81d 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -46,6 +46,7 @@ xfs-y				+= $(addprefix libxfs/, \
 				   xfs_refcount.o \
 				   xfs_refcount_btree.o \
 				   xfs_sb.o \
+				   xfs_swapext.o \
 				   xfs_symlink_remote.o \
 				   xfs_trans_inode.o \
 				   xfs_trans_resv.o \
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 1eee606f3924d..ccd1ddcd78500 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -156,7 +156,7 @@ static inline bool xfs_bmap_is_real_extent(const struct xfs_bmbt_irec *irec)
  * Return true if the extent is a real, allocated extent, or false if it is  a
  * delayed allocation, and unwritten extent or a hole.
  */
-static inline bool xfs_bmap_is_written_extent(struct xfs_bmbt_irec *irec)
+static inline bool xfs_bmap_is_written_extent(const struct xfs_bmbt_irec *irec)
 {
 	return xfs_bmap_is_real_extent(irec) &&
 	       irec->br_state != XFS_EXT_UNWRITTEN;
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index ca7f0ac048960..f77b2eaaa1b0d 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -27,6 +27,7 @@
 #include "xfs_da_btree.h"
 #include "xfs_attr.h"
 #include "xfs_trans_priv.h"
+#include "xfs_swapext.h"
 
 static struct kmem_cache	*xfs_defer_pending_cache;
 
@@ -1180,6 +1181,10 @@ xfs_defer_init_item_caches(void)
 	error = xfs_attr_intent_init_cache();
 	if (error)
 		goto err;
+	error = xfs_swapext_intent_init_cache();
+	if (error)
+		goto err;
+
 	return 0;
 err:
 	xfs_defer_destroy_item_caches();
@@ -1190,6 +1195,7 @@ xfs_defer_init_item_caches(void)
 void
 xfs_defer_destroy_item_caches(void)
 {
+	xfs_swapext_intent_destroy_cache();
 	xfs_attr_intent_destroy_cache();
 	xfs_extfree_intent_destroy_cache();
 	xfs_bmap_intent_destroy_cache();
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index 18a9fb92dde8e..e3cf81bafca3e 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -72,7 +72,7 @@ extern const struct xfs_defer_op_type xfs_rmap_update_defer_type;
 extern const struct xfs_defer_op_type xfs_extent_free_defer_type;
 extern const struct xfs_defer_op_type xfs_agfl_free_defer_type;
 extern const struct xfs_defer_op_type xfs_attr_defer_type;
-
+extern const struct xfs_defer_op_type xfs_swapext_defer_type;
 
 /*
  * Deferred operation item relogging limits.
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index c0209bd21dba1..8b34754a5794e 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -430,6 +430,12 @@ static inline bool xfs_sb_version_haslogxattrs(struct xfs_sb *sbp)
 		 XFS_SB_FEAT_INCOMPAT_LOG_XATTRS);
 }
 
+static inline bool xfs_sb_version_haslogswapext(struct xfs_sb *sbp)
+{
+	return xfs_sb_is_v5(sbp) && (sbp->sb_features_log_incompat &
+		 XFS_SB_FEAT_INCOMPAT_LOG_SWAPEXT);
+}
+
 static inline bool
 xfs_is_quota_inode(struct xfs_sb *sbp, xfs_ino_t ino)
 {
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index 24c3d5dc36182..3341792cf43a5 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -898,9 +898,36 @@ struct xfs_swap_extent {
 	int64_t			sx_isize2;
 };
 
-#define XFS_SWAP_EXT_FLAGS		(0)
+/* Swap extents between extended attribute forks. */
+#define XFS_SWAP_EXT_ATTR_FORK		(1ULL << 0)
 
-#define XFS_SWAP_EXT_STRINGS
+/* Set the file sizes when finished. */
+#define XFS_SWAP_EXT_SET_SIZES		(1ULL << 1)
+
+/*
+ * Swap only the extents of the two files where the file allocation units
+ * mapped to file1's range have been written to.
+ */
+#define XFS_SWAP_EXT_INO1_WRITTEN	(1ULL << 2)
+
+/* Clear the reflink flag from inode1 after the operation. */
+#define XFS_SWAP_EXT_CLEAR_INO1_REFLINK	(1ULL << 3)
+
+/* Clear the reflink flag from inode2 after the operation. */
+#define XFS_SWAP_EXT_CLEAR_INO2_REFLINK	(1ULL << 4)
+
+#define XFS_SWAP_EXT_FLAGS		(XFS_SWAP_EXT_ATTR_FORK | \
+					 XFS_SWAP_EXT_SET_SIZES | \
+					 XFS_SWAP_EXT_INO1_WRITTEN | \
+					 XFS_SWAP_EXT_CLEAR_INO1_REFLINK | \
+					 XFS_SWAP_EXT_CLEAR_INO2_REFLINK)
+
+#define XFS_SWAP_EXT_STRINGS \
+	{ XFS_SWAP_EXT_ATTR_FORK,		"ATTRFORK" }, \
+	{ XFS_SWAP_EXT_SET_SIZES,		"SETSIZES" }, \
+	{ XFS_SWAP_EXT_INO1_WRITTEN,		"INO1_WRITTEN" }, \
+	{ XFS_SWAP_EXT_CLEAR_INO1_REFLINK,	"CLEAR_INO1_REFLINK" }, \
+	{ XFS_SWAP_EXT_CLEAR_INO2_REFLINK,	"CLEAR_INO2_REFLINK" }
 
 /* This is the structure used to lay out an sxi log item in the log. */
 struct xfs_sxi_log_format {
diff --git a/fs/xfs/libxfs/xfs_swapext.c b/fs/xfs/libxfs/xfs_swapext.c
new file mode 100644
index 0000000000000..f5dacd6f1ecb2
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_swapext.c
@@ -0,0 +1,1031 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2020-2024 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_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_inode.h"
+#include "xfs_trans.h"
+#include "xfs_bmap.h"
+#include "xfs_icache.h"
+#include "xfs_quota.h"
+#include "xfs_swapext.h"
+#include "xfs_trace.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_trans_space.h"
+#include "xfs_error.h"
+#include "xfs_errortag.h"
+#include "xfs_health.h"
+#include "xfs_swapext_item.h"
+
+struct kmem_cache	*xfs_swapext_intent_cache;
+
+/* bmbt mappings adjacent to a pair of records. */
+struct xfs_swapext_adjacent {
+	struct xfs_bmbt_irec		left1;
+	struct xfs_bmbt_irec		right1;
+	struct xfs_bmbt_irec		left2;
+	struct xfs_bmbt_irec		right2;
+};
+
+#define ADJACENT_INIT { \
+	.left1  = { .br_startblock = HOLESTARTBLOCK }, \
+	.right1 = { .br_startblock = HOLESTARTBLOCK }, \
+	.left2  = { .br_startblock = HOLESTARTBLOCK }, \
+	.right2 = { .br_startblock = HOLESTARTBLOCK }, \
+}
+
+/* Information to help us reset reflink flag / CoW fork state after a swap. */
+
+/* Previous state of the two inodes' reflink flags. */
+#define XFS_REFLINK_STATE_IP1		(1U << 0)
+#define XFS_REFLINK_STATE_IP2		(1U << 1)
+
+/*
+ * If the reflink flag is set on either inode, make sure it has an incore CoW
+ * fork, since all reflink inodes must have them.  If there's a CoW fork and it
+ * has extents in it, make sure the inodes are tagged appropriately so that
+ * speculative preallocations can be GC'd if we run low of space.
+ */
+static inline void
+xfs_swapext_ensure_cowfork(
+	struct xfs_inode	*ip)
+{
+	struct xfs_ifork	*cfork;
+
+	if (xfs_is_reflink_inode(ip))
+		xfs_ifork_init_cow(ip);
+
+	cfork = xfs_ifork_ptr(ip, XFS_COW_FORK);
+	if (!cfork)
+		return;
+	if (cfork->if_bytes > 0)
+		xfs_inode_set_cowblocks_tag(ip);
+	else
+		xfs_inode_clear_cowblocks_tag(ip);
+}
+
+/*
+ * Adjust the on-disk inode size upwards if needed so that we never map extents
+ * into the file past EOF.  This is crucial so that log recovery won't get
+ * confused by the sudden appearance of post-eof extents.
+ */
+STATIC void
+xfs_swapext_update_size(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	struct xfs_bmbt_irec	*imap,
+	xfs_fsize_t		new_isize)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+	xfs_fsize_t		len;
+
+	if (new_isize < 0)
+		return;
+
+	len = min(XFS_FSB_TO_B(mp, imap->br_startoff + imap->br_blockcount),
+		  new_isize);
+
+	if (len <= ip->i_disk_size)
+		return;
+
+	trace_xfs_swapext_update_inode_size(ip, len);
+
+	ip->i_disk_size = len;
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+}
+
+static inline bool
+sxi_has_more_swap_work(const struct xfs_swapext_intent *sxi)
+{
+	return sxi->sxi_blockcount > 0;
+}
+
+static inline bool
+sxi_has_postop_work(const struct xfs_swapext_intent *sxi)
+{
+	return sxi->sxi_flags & (XFS_SWAP_EXT_CLEAR_INO1_REFLINK |
+				 XFS_SWAP_EXT_CLEAR_INO2_REFLINK);
+}
+
+static inline void
+sxi_advance(
+	struct xfs_swapext_intent	*sxi,
+	const struct xfs_bmbt_irec	*irec)
+{
+	sxi->sxi_startoff1 += irec->br_blockcount;
+	sxi->sxi_startoff2 += irec->br_blockcount;
+	sxi->sxi_blockcount -= irec->br_blockcount;
+}
+
+/* Check all extents to make sure we can actually swap them. */
+int
+xfs_swapext_check_extents(
+	struct xfs_mount		*mp,
+	const struct xfs_swapext_req	*req)
+{
+	struct xfs_ifork		*ifp1, *ifp2;
+
+	/* No fork? */
+	ifp1 = xfs_ifork_ptr(req->ip1, req->whichfork);
+	ifp2 = xfs_ifork_ptr(req->ip2, req->whichfork);
+	if (!ifp1 || !ifp2)
+		return -EINVAL;
+
+	/* We don't know how to swap local format forks. */
+	if (ifp1->if_format == XFS_DINODE_FMT_LOCAL ||
+	    ifp2->if_format == XFS_DINODE_FMT_LOCAL)
+		return -EINVAL;
+
+	/* We don't support realtime data forks yet. */
+	if (!XFS_IS_REALTIME_INODE(req->ip1))
+		return 0;
+	if (req->whichfork == XFS_ATTR_FORK)
+		return 0;
+	return -EINVAL;
+}
+
+#ifdef CONFIG_XFS_QUOTA
+/* Log the actual updates to the quota accounting. */
+static inline void
+xfs_swapext_update_quota(
+	struct xfs_trans		*tp,
+	struct xfs_swapext_intent	*sxi,
+	struct xfs_bmbt_irec		*irec1,
+	struct xfs_bmbt_irec		*irec2)
+{
+	int64_t				ip1_delta = 0, ip2_delta = 0;
+	unsigned int			qflag;
+
+	qflag = XFS_IS_REALTIME_INODE(sxi->sxi_ip1) ? XFS_TRANS_DQ_RTBCOUNT :
+						      XFS_TRANS_DQ_BCOUNT;
+
+	if (xfs_bmap_is_real_extent(irec1)) {
+		ip1_delta -= irec1->br_blockcount;
+		ip2_delta += irec1->br_blockcount;
+	}
+
+	if (xfs_bmap_is_real_extent(irec2)) {
+		ip1_delta += irec2->br_blockcount;
+		ip2_delta -= irec2->br_blockcount;
+	}
+
+	xfs_trans_mod_dquot_byino(tp, sxi->sxi_ip1, qflag, ip1_delta);
+	xfs_trans_mod_dquot_byino(tp, sxi->sxi_ip2, qflag, ip2_delta);
+}
+#else
+# define xfs_swapext_update_quota(tp, sxi, irec1, irec2)	((void)0)
+#endif
+
+/* Decide if we want to skip this mapping from file1. */
+static inline bool
+xfs_swapext_can_skip_mapping(
+	struct xfs_swapext_intent	*sxi,
+	struct xfs_bmbt_irec		*irec)
+{
+	/* Do not skip this mapping if the caller did not tell us to. */
+	if (!(sxi->sxi_flags & XFS_SWAP_EXT_INO1_WRITTEN))
+		return false;
+
+	/* Do not skip mapped, written extents. */
+	if (xfs_bmap_is_written_extent(irec))
+		return false;
+
+	/*
+	 * The mapping is unwritten or a hole.  It cannot be a delalloc
+	 * reservation because we already excluded those.  It cannot be an
+	 * unwritten extent with dirty page cache because we flushed the page
+	 * cache.  We don't support realtime files yet, so we needn't (yet)
+	 * deal with them.
+	 */
+	return true;
+}
+
+/*
+ * Walk forward through the file ranges in @sxi until we find two different
+ * mappings to exchange.  If there is work to do, return the mappings;
+ * otherwise we've reached the end of the range and sxi_blockcount will be
+ * zero.
+ *
+ * If the walk skips over a pair of mappings to the same storage, save them as
+ * the left records in @adj (if provided) so that the simulation phase can
+ * avoid an extra lookup.
+  */
+static int
+xfs_swapext_find_mappings(
+	struct xfs_swapext_intent	*sxi,
+	struct xfs_bmbt_irec		*irec1,
+	struct xfs_bmbt_irec		*irec2,
+	struct xfs_swapext_adjacent	*adj)
+{
+	int				nimaps;
+	int				bmap_flags;
+	int				error;
+
+	bmap_flags = xfs_bmapi_aflag(xfs_swapext_whichfork(sxi));
+
+	for (; sxi_has_more_swap_work(sxi); sxi_advance(sxi, irec1)) {
+		/* Read extent from the first file */
+		nimaps = 1;
+		error = xfs_bmapi_read(sxi->sxi_ip1, sxi->sxi_startoff1,
+				sxi->sxi_blockcount, irec1, &nimaps,
+				bmap_flags);
+		if (error)
+			return error;
+		if (nimaps != 1 ||
+		    irec1->br_startblock == DELAYSTARTBLOCK ||
+		    irec1->br_startoff != sxi->sxi_startoff1) {
+			/*
+			 * We should never get no mapping or a delalloc extent
+			 * or something that doesn't match what we asked for,
+			 * since the caller flushed both inodes and we hold the
+			 * ILOCKs for both inodes.
+			 */
+			ASSERT(0);
+			return -EINVAL;
+		}
+
+		if (xfs_swapext_can_skip_mapping(sxi, irec1)) {
+			trace_xfs_swapext_extent1_skip(sxi->sxi_ip1, irec1);
+			continue;
+		}
+
+		/* Read extent from the second file */
+		nimaps = 1;
+		error = xfs_bmapi_read(sxi->sxi_ip2, sxi->sxi_startoff2,
+				irec1->br_blockcount, irec2, &nimaps,
+				bmap_flags);
+		if (error)
+			return error;
+		if (nimaps != 1 ||
+		    irec2->br_startblock == DELAYSTARTBLOCK ||
+		    irec2->br_startoff != sxi->sxi_startoff2) {
+			/*
+			 * We should never get no mapping or a delalloc extent
+			 * or something that doesn't match what we asked for,
+			 * since the caller flushed both inodes and we hold the
+			 * ILOCKs for both inodes.
+			 */
+			ASSERT(0);
+			return -EINVAL;
+		}
+
+		/*
+		 * We can only swap as many blocks as the smaller of the two
+		 * extent maps.
+		 */
+		irec1->br_blockcount = min(irec1->br_blockcount,
+					   irec2->br_blockcount);
+
+		trace_xfs_swapext_extent1(sxi->sxi_ip1, irec1);
+		trace_xfs_swapext_extent2(sxi->sxi_ip2, irec2);
+
+		/* We found something to swap, so return it. */
+		if (irec1->br_startblock != irec2->br_startblock)
+			return 0;
+
+		/*
+		 * Two extents mapped to the same physical block must not have
+		 * different states; that's filesystem corruption.  Move on to
+		 * the next extent if they're both holes or both the same
+		 * physical extent.
+		 */
+		if (irec1->br_state != irec2->br_state) {
+			xfs_bmap_mark_sick(sxi->sxi_ip1,
+					xfs_swapext_whichfork(sxi));
+			xfs_bmap_mark_sick(sxi->sxi_ip2,
+					xfs_swapext_whichfork(sxi));
+			return -EFSCORRUPTED;
+		}
+
+		/*
+		 * Save the mappings if we're estimating work and skipping
+		 * these identical mappings.
+		 */
+		if (adj) {
+			memcpy(&adj->left1, irec1, sizeof(*irec1));
+			memcpy(&adj->left2, irec2, sizeof(*irec2));
+		}
+	}
+
+	return 0;
+}
+
+/* Exchange these two mappings. */
+static void
+xfs_swapext_exchange_mappings(
+	struct xfs_trans		*tp,
+	struct xfs_swapext_intent	*sxi,
+	struct xfs_bmbt_irec		*irec1,
+	struct xfs_bmbt_irec		*irec2)
+{
+	int				whichfork = xfs_swapext_whichfork(sxi);
+
+	xfs_swapext_update_quota(tp, sxi, irec1, irec2);
+
+	/* Remove both mappings. */
+	xfs_bmap_unmap_extent(tp, sxi->sxi_ip1, whichfork, irec1);
+	xfs_bmap_unmap_extent(tp, sxi->sxi_ip2, whichfork, irec2);
+
+	/*
+	 * Re-add both mappings.  We swap the file offsets between the two maps
+	 * and add the opposite map, which has the effect of filling the
+	 * logical offsets we just unmapped, but with with the physical mapping
+	 * information swapped.
+	 */
+	swap(irec1->br_startoff, irec2->br_startoff);
+	xfs_bmap_map_extent(tp, sxi->sxi_ip1, whichfork, irec2);
+	xfs_bmap_map_extent(tp, sxi->sxi_ip2, whichfork, irec1);
+
+	/* Make sure we're not mapping extents past EOF. */
+	if (whichfork == XFS_DATA_FORK) {
+		xfs_swapext_update_size(tp, sxi->sxi_ip1, irec2,
+				sxi->sxi_isize1);
+		xfs_swapext_update_size(tp, sxi->sxi_ip2, irec1,
+				sxi->sxi_isize2);
+	}
+
+	/*
+	 * Advance our cursor and exit.   The caller (either defer ops or log
+	 * recovery) will log the SXD item, and if *blockcount is nonzero, it
+	 * will log a new SXI item for the remainder and call us back.
+	 */
+	sxi_advance(sxi, irec1);
+}
+
+static inline void
+xfs_swapext_clear_reflink(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip)
+{
+	trace_xfs_reflink_unset_inode_flag(ip);
+
+	ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+}
+
+/* Finish whatever work might come after a swap operation. */
+static int
+xfs_swapext_do_postop_work(
+	struct xfs_trans		*tp,
+	struct xfs_swapext_intent	*sxi)
+{
+	if (sxi->sxi_flags & XFS_SWAP_EXT_CLEAR_INO1_REFLINK) {
+		xfs_swapext_clear_reflink(tp, sxi->sxi_ip1);
+		sxi->sxi_flags &= ~XFS_SWAP_EXT_CLEAR_INO1_REFLINK;
+	}
+
+	if (sxi->sxi_flags & XFS_SWAP_EXT_CLEAR_INO2_REFLINK) {
+		xfs_swapext_clear_reflink(tp, sxi->sxi_ip2);
+		sxi->sxi_flags &= ~XFS_SWAP_EXT_CLEAR_INO2_REFLINK;
+	}
+
+	return 0;
+}
+
+/* Finish one extent swap, possibly log more. */
+int
+xfs_swapext_finish_one(
+	struct xfs_trans		*tp,
+	struct xfs_swapext_intent	*sxi)
+{
+	struct xfs_bmbt_irec		irec1, irec2;
+	int				error;
+
+	if (sxi_has_more_swap_work(sxi)) {
+		/*
+		 * If the operation state says that some range of the files
+		 * have not yet been swapped, look for extents in that range to
+		 * swap.  If we find some extents, swap them.
+		 */
+		error = xfs_swapext_find_mappings(sxi, &irec1, &irec2, NULL);
+		if (error)
+			return error;
+
+		if (sxi_has_more_swap_work(sxi))
+			xfs_swapext_exchange_mappings(tp, sxi, &irec1, &irec2);
+
+		/*
+		 * If the caller asked us to exchange the file sizes after the
+		 * swap and either we just swapped the last extents in the
+		 * range or we didn't find anything to swap, update the ondisk
+		 * file sizes.
+		 */
+		if ((sxi->sxi_flags & XFS_SWAP_EXT_SET_SIZES) &&
+		    !sxi_has_more_swap_work(sxi)) {
+			sxi->sxi_ip1->i_disk_size = sxi->sxi_isize1;
+			sxi->sxi_ip2->i_disk_size = sxi->sxi_isize2;
+
+			xfs_trans_log_inode(tp, sxi->sxi_ip1, XFS_ILOG_CORE);
+			xfs_trans_log_inode(tp, sxi->sxi_ip2, XFS_ILOG_CORE);
+		}
+	} else if (sxi_has_postop_work(sxi)) {
+		/*
+		 * Now that we're finished with the swap operation, complete
+		 * the post-op cleanup work.
+		 */
+		error = xfs_swapext_do_postop_work(tp, sxi);
+		if (error)
+			return error;
+	}
+
+	/* If we still have work to do, ask for a new transaction. */
+	if (sxi_has_more_swap_work(sxi) || sxi_has_postop_work(sxi)) {
+		trace_xfs_swapext_defer(tp->t_mountp, sxi);
+		return -EAGAIN;
+	}
+
+	/*
+	 * If we reach here, we've finished all the swapping work and the post
+	 * operation work.  The last thing we need to do before returning to
+	 * the caller is to make sure that COW forks are set up correctly.
+	 */
+	if (!(sxi->sxi_flags & XFS_SWAP_EXT_ATTR_FORK)) {
+		xfs_swapext_ensure_cowfork(sxi->sxi_ip1);
+		xfs_swapext_ensure_cowfork(sxi->sxi_ip2);
+	}
+
+	return 0;
+}
+
+/*
+ * Compute the amount of bmbt blocks we should reserve for each file.  In the
+ * worst case, each exchange will fill a hole with a new mapping, which could
+ * result in a btree split every time we add a new leaf block.
+ */
+static inline uint64_t
+xfs_swapext_bmbt_blocks(
+	struct xfs_mount		*mp,
+	const struct xfs_swapext_req	*req)
+{
+	return howmany_64(req->nr_exchanges,
+					XFS_MAX_CONTIG_BMAPS_PER_BLOCK(mp)) *
+			XFS_EXTENTADD_SPACE_RES(mp, req->whichfork);
+}
+
+static inline uint64_t
+xfs_swapext_rmapbt_blocks(
+	struct xfs_mount		*mp,
+	const struct xfs_swapext_req	*req)
+{
+	if (!xfs_has_rmapbt(mp))
+		return 0;
+	if (XFS_IS_REALTIME_INODE(req->ip1))
+		return 0;
+
+	return howmany_64(req->nr_exchanges,
+					XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)) *
+			XFS_RMAPADD_SPACE_RES(mp);
+}
+
+/* Estimate the bmbt and rmapbt overhead required to exchange extents. */
+static int
+xfs_swapext_estimate_overhead(
+	struct xfs_swapext_req	*req)
+{
+	struct xfs_mount	*mp = req->ip1->i_mount;
+	xfs_filblks_t		bmbt_blocks;
+	xfs_filblks_t		rmapbt_blocks;
+	xfs_filblks_t		resblks = req->resblks;
+
+	/*
+	 * Compute the number of bmbt and rmapbt blocks we might need to handle
+	 * the estimated number of exchanges.
+	 */
+	bmbt_blocks = xfs_swapext_bmbt_blocks(mp, req);
+	rmapbt_blocks = xfs_swapext_rmapbt_blocks(mp, req);
+
+	trace_xfs_swapext_overhead(mp, bmbt_blocks, rmapbt_blocks);
+
+	/* Make sure the change in file block count doesn't overflow. */
+	if (check_add_overflow(req->ip1_bcount, bmbt_blocks, &req->ip1_bcount))
+		return -EFBIG;
+	if (check_add_overflow(req->ip2_bcount, bmbt_blocks, &req->ip2_bcount))
+		return -EFBIG;
+
+	/*
+	 * Add together the number of blocks we need to handle btree growth,
+	 * then add it to the number of blocks we need to reserve to this
+	 * transaction.
+	 */
+	if (check_add_overflow(resblks, bmbt_blocks, &resblks))
+		return -ENOSPC;
+	if (check_add_overflow(resblks, bmbt_blocks, &resblks))
+		return -ENOSPC;
+	if (check_add_overflow(resblks, rmapbt_blocks, &resblks))
+		return -ENOSPC;
+	if (check_add_overflow(resblks, rmapbt_blocks, &resblks))
+		return -ENOSPC;
+
+	/* Can't actually reserve more than UINT_MAX blocks. */
+	if (req->resblks > UINT_MAX)
+		return -ENOSPC;
+
+	req->resblks = resblks;
+	trace_xfs_swapext_final_estimate(req);
+	return 0;
+}
+
+/* Decide if we can merge two real extents. */
+static inline bool
+can_merge(
+	const struct xfs_bmbt_irec	*b1,
+	const struct xfs_bmbt_irec	*b2)
+{
+	/* Don't merge holes. */
+	if (b1->br_startblock == HOLESTARTBLOCK ||
+	    b2->br_startblock == HOLESTARTBLOCK)
+		return false;
+
+	/* We don't merge holes. */
+	if (!xfs_bmap_is_real_extent(b1) || !xfs_bmap_is_real_extent(b2))
+		return false;
+
+	if (b1->br_startoff   + b1->br_blockcount == b2->br_startoff &&
+	    b1->br_startblock + b1->br_blockcount == b2->br_startblock &&
+	    b1->br_state			  == b2->br_state &&
+	    b1->br_blockcount + b2->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
+		return true;
+
+	return false;
+}
+
+#define CLEFT_CONTIG	0x01
+#define CRIGHT_CONTIG	0x02
+#define CHOLE		0x04
+#define CBOTH_CONTIG	(CLEFT_CONTIG | CRIGHT_CONTIG)
+
+#define NLEFT_CONTIG	0x10
+#define NRIGHT_CONTIG	0x20
+#define NHOLE		0x40
+#define NBOTH_CONTIG	(NLEFT_CONTIG | NRIGHT_CONTIG)
+
+/* Estimate the effect of a single swap on extent count. */
+static inline int
+delta_nextents_step(
+	struct xfs_mount		*mp,
+	const struct xfs_bmbt_irec	*left,
+	const struct xfs_bmbt_irec	*curr,
+	const struct xfs_bmbt_irec	*new,
+	const struct xfs_bmbt_irec	*right)
+{
+	bool				lhole, rhole, chole, nhole;
+	unsigned int			state = 0;
+	int				ret = 0;
+
+	lhole = left->br_startblock == HOLESTARTBLOCK;
+	rhole = right->br_startblock == HOLESTARTBLOCK;
+	chole = curr->br_startblock == HOLESTARTBLOCK;
+	nhole = new->br_startblock == HOLESTARTBLOCK;
+
+	if (chole)
+		state |= CHOLE;
+	if (!lhole && !chole && can_merge(left, curr))
+		state |= CLEFT_CONTIG;
+	if (!rhole && !chole && can_merge(curr, right))
+		state |= CRIGHT_CONTIG;
+	if ((state & CBOTH_CONTIG) == CBOTH_CONTIG &&
+	    left->br_startblock + curr->br_startblock +
+					right->br_startblock > XFS_MAX_BMBT_EXTLEN)
+		state &= ~CRIGHT_CONTIG;
+
+	if (nhole)
+		state |= NHOLE;
+	if (!lhole && !nhole && can_merge(left, new))
+		state |= NLEFT_CONTIG;
+	if (!rhole && !nhole && can_merge(new, right))
+		state |= NRIGHT_CONTIG;
+	if ((state & NBOTH_CONTIG) == NBOTH_CONTIG &&
+	    left->br_startblock + new->br_startblock +
+					right->br_startblock > XFS_MAX_BMBT_EXTLEN)
+		state &= ~NRIGHT_CONTIG;
+
+	switch (state & (CLEFT_CONTIG | CRIGHT_CONTIG | CHOLE)) {
+	case CLEFT_CONTIG | CRIGHT_CONTIG:
+		/*
+		 * left/curr/right are the same extent, so deleting curr causes
+		 * 2 new extents to be created.
+		 */
+		ret += 2;
+		break;
+	case 0:
+		/*
+		 * curr is not contiguous with any extent, so we remove curr
+		 * completely
+		 */
+		ret--;
+		break;
+	case CHOLE:
+		/* hole, do nothing */
+		break;
+	case CLEFT_CONTIG:
+	case CRIGHT_CONTIG:
+		/* trim either left or right, no change */
+		break;
+	}
+
+	switch (state & (NLEFT_CONTIG | NRIGHT_CONTIG | NHOLE)) {
+	case NLEFT_CONTIG | NRIGHT_CONTIG:
+		/*
+		 * left/curr/right will become the same extent, so adding
+		 * curr causes the deletion of right.
+		 */
+		ret--;
+		break;
+	case 0:
+		/* new is not contiguous with any extent */
+		ret++;
+		break;
+	case NHOLE:
+		/* hole, do nothing. */
+		break;
+	case NLEFT_CONTIG:
+	case NRIGHT_CONTIG:
+		/* new is absorbed into left or right, no change */
+		break;
+	}
+
+	trace_xfs_swapext_delta_nextents_step(mp, left, curr, new, right, ret,
+			state);
+	return ret;
+}
+
+/* Make sure we don't overflow the extent counters. */
+static inline int
+ensure_delta_nextents(
+	struct xfs_swapext_req	*req,
+	struct xfs_inode	*ip,
+	int64_t			delta)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, req->whichfork);
+	xfs_extnum_t		max_extents;
+	bool			large_extcount;
+
+	if (delta < 0)
+		return 0;
+
+	if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_REDUCE_MAX_IEXTENTS)) {
+		if (ifp->if_nextents + delta > 10)
+			return -EFBIG;
+	}
+
+	if (req->req_flags & XFS_SWAP_REQ_NREXT64)
+		large_extcount = true;
+	else
+		large_extcount = xfs_inode_has_large_extent_counts(ip);
+
+	max_extents = xfs_iext_max_nextents(large_extcount, req->whichfork);
+	if (ifp->if_nextents + delta <= max_extents)
+		return 0;
+	if (large_extcount)
+		return -EFBIG;
+	if (!xfs_has_large_extent_counts(mp))
+		return -EFBIG;
+
+	max_extents = xfs_iext_max_nextents(true, req->whichfork);
+	if (ifp->if_nextents + delta > max_extents)
+		return -EFBIG;
+
+	req->req_flags |= XFS_SWAP_REQ_NREXT64;
+	return 0;
+}
+
+/* Find the next extent after irec. */
+static inline int
+get_next_ext(
+	struct xfs_inode		*ip,
+	int				bmap_flags,
+	const struct xfs_bmbt_irec	*irec,
+	struct xfs_bmbt_irec		*nrec)
+{
+	xfs_fileoff_t			off;
+	xfs_filblks_t			blockcount;
+	int				nimaps = 1;
+	int				error;
+
+	off = irec->br_startoff + irec->br_blockcount;
+	blockcount = XFS_MAX_FILEOFF - off;
+	error = xfs_bmapi_read(ip, off, blockcount, nrec, &nimaps, bmap_flags);
+	if (error)
+		return error;
+	if (nrec->br_startblock == DELAYSTARTBLOCK ||
+	    nrec->br_startoff != off) {
+		/*
+		 * If we don't get the extent we want, return a zero-length
+		 * mapping, which our estimator function will pretend is a hole.
+		 * We shouldn't get delalloc reservations.
+		 */
+		nrec->br_startblock = HOLESTARTBLOCK;
+	}
+
+	return 0;
+}
+
+int __init
+xfs_swapext_intent_init_cache(void)
+{
+	xfs_swapext_intent_cache = kmem_cache_create("xfs_swapext_intent",
+			sizeof(struct xfs_swapext_intent),
+			0, 0, NULL);
+
+	return xfs_swapext_intent_cache != NULL ? 0 : -ENOMEM;
+}
+
+void
+xfs_swapext_intent_destroy_cache(void)
+{
+	kmem_cache_destroy(xfs_swapext_intent_cache);
+	xfs_swapext_intent_cache = NULL;
+}
+
+/*
+ * Decide if we will swap the reflink flags between the two files after the
+ * swap.  The only time we want to do this is if we're exchanging all extents
+ * under EOF and the inode reflink flags have different states.
+ */
+static inline bool
+sxi_can_exchange_reflink_flags(
+	const struct xfs_swapext_req	*req,
+	unsigned int			reflink_state)
+{
+	struct xfs_mount		*mp = req->ip1->i_mount;
+
+	if (hweight32(reflink_state) != 1)
+		return false;
+	if (req->startoff1 != 0 || req->startoff2 != 0)
+		return false;
+	if (req->blockcount != XFS_B_TO_FSB(mp, req->ip1->i_disk_size))
+		return false;
+	if (req->blockcount != XFS_B_TO_FSB(mp, req->ip2->i_disk_size))
+		return false;
+	return true;
+}
+
+
+/* Allocate and initialize a new incore intent item from a request. */
+struct xfs_swapext_intent *
+xfs_swapext_init_intent(
+	const struct xfs_swapext_req	*req,
+	unsigned int			*reflink_state)
+{
+	struct xfs_swapext_intent	*sxi;
+	unsigned int			rs = 0;
+
+	sxi = kmem_cache_zalloc(xfs_swapext_intent_cache,
+			GFP_NOFS | __GFP_NOFAIL);
+	INIT_LIST_HEAD(&sxi->sxi_list);
+	sxi->sxi_ip1 = req->ip1;
+	sxi->sxi_ip2 = req->ip2;
+	sxi->sxi_startoff1 = req->startoff1;
+	sxi->sxi_startoff2 = req->startoff2;
+	sxi->sxi_blockcount = req->blockcount;
+	sxi->sxi_isize1 = sxi->sxi_isize2 = -1;
+
+	if (req->whichfork == XFS_ATTR_FORK)
+		sxi->sxi_flags |= XFS_SWAP_EXT_ATTR_FORK;
+
+	if (req->whichfork == XFS_DATA_FORK &&
+	    (req->req_flags & XFS_SWAP_REQ_SET_SIZES)) {
+		sxi->sxi_flags |= XFS_SWAP_EXT_SET_SIZES;
+		sxi->sxi_isize1 = req->ip2->i_disk_size;
+		sxi->sxi_isize2 = req->ip1->i_disk_size;
+	}
+
+	if (req->req_flags & XFS_SWAP_REQ_INO1_WRITTEN)
+		sxi->sxi_flags |= XFS_SWAP_EXT_INO1_WRITTEN;
+
+	if (req->req_flags & XFS_SWAP_REQ_LOGGED)
+		sxi->sxi_op_flags |= XFS_SWAP_EXT_OP_LOGGED;
+	if (req->req_flags & XFS_SWAP_REQ_NREXT64)
+		sxi->sxi_op_flags |= XFS_SWAP_EXT_OP_NREXT64;
+
+	if (req->whichfork == XFS_DATA_FORK) {
+		/*
+		 * Record the state of each inode's reflink flag before the
+		 * operation.
+		 */
+		if (xfs_is_reflink_inode(req->ip1))
+			rs |= XFS_REFLINK_STATE_IP1;
+		if (xfs_is_reflink_inode(req->ip2))
+			rs |= XFS_REFLINK_STATE_IP2;
+
+		/*
+		 * Figure out if we're clearing the reflink flags (which
+		 * effectively swaps them) after the operation.
+		 */
+		if (sxi_can_exchange_reflink_flags(req, rs)) {
+			if (rs & XFS_REFLINK_STATE_IP1)
+				sxi->sxi_flags |=
+						XFS_SWAP_EXT_CLEAR_INO1_REFLINK;
+			if (rs & XFS_REFLINK_STATE_IP2)
+				sxi->sxi_flags |=
+						XFS_SWAP_EXT_CLEAR_INO2_REFLINK;
+		}
+	}
+
+	if (reflink_state)
+		*reflink_state = rs;
+	return sxi;
+}
+
+/*
+ * Estimate the number of exchange operations and the number of file blocks
+ * in each file that will be affected by the exchange operation.
+ */
+int
+xfs_swapext_estimate(
+	struct xfs_swapext_req		*req)
+{
+	struct xfs_swapext_intent	*sxi;
+	struct xfs_bmbt_irec		irec1, irec2;
+	struct xfs_swapext_adjacent	adj = ADJACENT_INIT;
+	xfs_filblks_t			ip1_blocks = 0, ip2_blocks = 0;
+	int64_t				d_nexts1, d_nexts2;
+	int				bmap_flags;
+	int				error;
+
+	ASSERT(!(req->req_flags & ~XFS_SWAP_REQ_FLAGS));
+
+	bmap_flags = xfs_bmapi_aflag(req->whichfork);
+	sxi = xfs_swapext_init_intent(req, NULL);
+
+	/*
+	 * To guard against the possibility of overflowing the extent counters,
+	 * we have to estimate an upper bound on the potential increase in that
+	 * counter.  We can split the extent at each end of the range, and for
+	 * each step of the swap we can split the extent that we're working on
+	 * if the extents do not align.
+	 */
+	d_nexts1 = d_nexts2 = 3;
+
+	while (sxi_has_more_swap_work(sxi)) {
+		/*
+		 * Walk through the file ranges until we find something to
+		 * swap.  Because we're simulating the swap, pass in adj to
+		 * capture skipped mappings for correct estimation of bmbt
+		 * record merges.
+		 */
+		error = xfs_swapext_find_mappings(sxi, &irec1, &irec2, &adj);
+		if (error)
+			goto out_free;
+		if (!sxi_has_more_swap_work(sxi))
+			break;
+
+		/* Update accounting. */
+		if (xfs_bmap_is_real_extent(&irec1))
+			ip1_blocks += irec1.br_blockcount;
+		if (xfs_bmap_is_real_extent(&irec2))
+			ip2_blocks += irec2.br_blockcount;
+		req->nr_exchanges++;
+
+		/* Read the next extents from both files. */
+		error = get_next_ext(req->ip1, bmap_flags, &irec1, &adj.right1);
+		if (error)
+			goto out_free;
+
+		error = get_next_ext(req->ip2, bmap_flags, &irec2, &adj.right2);
+		if (error)
+			goto out_free;
+
+		/* Update extent count deltas. */
+		d_nexts1 += delta_nextents_step(req->ip1->i_mount,
+				&adj.left1, &irec1, &irec2, &adj.right1);
+
+		d_nexts2 += delta_nextents_step(req->ip1->i_mount,
+				&adj.left2, &irec2, &irec1, &adj.right2);
+
+		/* Now pretend we swapped the extents. */
+		if (can_merge(&adj.left2, &irec1))
+			adj.left2.br_blockcount += irec1.br_blockcount;
+		else
+			memcpy(&adj.left2, &irec1, sizeof(irec1));
+
+		if (can_merge(&adj.left1, &irec2))
+			adj.left1.br_blockcount += irec2.br_blockcount;
+		else
+			memcpy(&adj.left1, &irec2, sizeof(irec2));
+
+		sxi_advance(sxi, &irec1);
+	}
+
+	/* Account for the blocks that are being exchanged. */
+	if (XFS_IS_REALTIME_INODE(req->ip1) &&
+	    req->whichfork == XFS_DATA_FORK) {
+		req->ip1_rtbcount = ip1_blocks;
+		req->ip2_rtbcount = ip2_blocks;
+	} else {
+		req->ip1_bcount = ip1_blocks;
+		req->ip2_bcount = ip2_blocks;
+	}
+
+	/*
+	 * Make sure that both forks have enough slack left in their extent
+	 * counters that the swap operation will not overflow.
+	 */
+	trace_xfs_swapext_delta_nextents(req, d_nexts1, d_nexts2);
+	if (req->ip1 == req->ip2) {
+		error = ensure_delta_nextents(req, req->ip1,
+				d_nexts1 + d_nexts2);
+	} else {
+		error = ensure_delta_nextents(req, req->ip1, d_nexts1);
+		if (error)
+			goto out_free;
+		error = ensure_delta_nextents(req, req->ip2, d_nexts2);
+	}
+	if (error)
+		goto out_free;
+
+	trace_xfs_swapext_initial_estimate(req);
+	error = xfs_swapext_estimate_overhead(req);
+out_free:
+	kmem_cache_free(xfs_swapext_intent_cache, sxi);
+	return error;
+}
+
+static inline void
+xfs_swapext_set_reflink(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip)
+{
+	trace_xfs_reflink_set_inode_flag(ip);
+
+	ip->i_diflags2 |= XFS_DIFLAG2_REFLINK;
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+}
+
+/*
+ * If either file has shared blocks and we're swapping data forks, we must flag
+ * the other file as having shared blocks so that we get the shared-block rmap
+ * functions if we need to fix up the rmaps.
+ */
+void
+xfs_swapext_ensure_reflink(
+	struct xfs_trans		*tp,
+	const struct xfs_swapext_intent	*sxi,
+	unsigned int			reflink_state)
+{
+	if ((reflink_state & XFS_REFLINK_STATE_IP1) &&
+	    !xfs_is_reflink_inode(sxi->sxi_ip2))
+		xfs_swapext_set_reflink(tp, sxi->sxi_ip2);
+
+	if ((reflink_state & XFS_REFLINK_STATE_IP2) &&
+	    !xfs_is_reflink_inode(sxi->sxi_ip1))
+		xfs_swapext_set_reflink(tp, sxi->sxi_ip1);
+}
+
+/* Widen the extent counts of both inodes if necessary. */
+static inline void
+xfs_swapext_upgrade_extent_counts(
+	struct xfs_trans		*tp,
+	const struct xfs_swapext_intent	*sxi)
+{
+	if (!(sxi->sxi_op_flags & XFS_SWAP_EXT_OP_NREXT64))
+		return;
+
+	sxi->sxi_ip1->i_diflags2 |= XFS_DIFLAG2_NREXT64;
+	xfs_trans_log_inode(tp, sxi->sxi_ip1, XFS_ILOG_CORE);
+
+	sxi->sxi_ip2->i_diflags2 |= XFS_DIFLAG2_NREXT64;
+	xfs_trans_log_inode(tp, sxi->sxi_ip2, XFS_ILOG_CORE);
+}
+
+/*
+ * Schedule a swap a range of extents from one inode to another.  If the atomic
+ * swap feature is enabled, then the operation progress can be resumed even if
+ * the system goes down.  The caller must commit the transaction to start the
+ * work.
+ *
+ * The caller must ensure the inodes must be joined to the transaction and
+ * ILOCKd; they will still be joined to the transaction at exit.
+ */
+void
+xfs_swapext(
+	struct xfs_trans		*tp,
+	const struct xfs_swapext_req	*req)
+{
+	struct xfs_swapext_intent	*sxi;
+	unsigned int			reflink_state;
+
+	ASSERT(xfs_isilocked(req->ip1, XFS_ILOCK_EXCL));
+	ASSERT(xfs_isilocked(req->ip2, XFS_ILOCK_EXCL));
+	ASSERT(req->whichfork != XFS_COW_FORK);
+	ASSERT(!(req->req_flags & ~XFS_SWAP_REQ_FLAGS));
+	if (req->req_flags & XFS_SWAP_REQ_SET_SIZES)
+		ASSERT(req->whichfork == XFS_DATA_FORK);
+
+	if (req->blockcount == 0)
+		return;
+
+	sxi = xfs_swapext_init_intent(req, &reflink_state);
+	xfs_swapext_defer_add(tp, sxi);
+	xfs_swapext_ensure_reflink(tp, sxi, reflink_state);
+	xfs_swapext_upgrade_extent_counts(tp, sxi);
+}
diff --git a/fs/xfs/libxfs/xfs_swapext.h b/fs/xfs/libxfs/xfs_swapext.h
index 01bb3271f6474..fa786bc93520a 100644
--- a/fs/xfs/libxfs/xfs_swapext.h
+++ b/fs/xfs/libxfs/xfs_swapext.h
@@ -72,4 +72,147 @@ xfs_atomic_swap_supported(
 	return false;
 }
 
+/*
+ * In-core information about an extent swap request between ranges of two
+ * inodes.
+ */
+struct xfs_swapext_intent {
+	/* List of other incore deferred work. */
+	struct list_head	sxi_list;
+
+	/* Inodes participating in the operation. */
+	struct xfs_inode	*sxi_ip1;
+	struct xfs_inode	*sxi_ip2;
+
+	/* File offset range information. */
+	xfs_fileoff_t		sxi_startoff1;
+	xfs_fileoff_t		sxi_startoff2;
+	xfs_filblks_t		sxi_blockcount;
+
+	/* Set these file sizes after the operation, unless negative. */
+	xfs_fsize_t		sxi_isize1;
+	xfs_fsize_t		sxi_isize2;
+
+	/* XFS_SWAP_EXT_* log operation flags */
+	unsigned int		sxi_flags;
+
+	/* XFS_SWAP_EXT_OP_* flags */
+	unsigned int		sxi_op_flags;
+};
+
+/* Use log intent items to track and restart the entire operation. */
+#define XFS_SWAP_EXT_OP_LOGGED	(1U << 0)
+
+/* Upgrade files to have large extent counts before proceeding. */
+#define XFS_SWAP_EXT_OP_NREXT64	(1U << 1)
+
+#define XFS_SWAP_EXT_OP_STRINGS \
+	{ XFS_SWAP_EXT_OP_LOGGED,		"LOGGED" }, \
+	{ XFS_SWAP_EXT_OP_NREXT64,		"NREXT64" }
+
+static inline int
+xfs_swapext_whichfork(const struct xfs_swapext_intent *sxi)
+{
+	if (sxi->sxi_flags & XFS_SWAP_EXT_ATTR_FORK)
+		return XFS_ATTR_FORK;
+	return XFS_DATA_FORK;
+}
+
+/* Parameters for a swapext request. */
+struct xfs_swapext_req {
+	/* Inodes participating in the operation. */
+	struct xfs_inode	*ip1;
+	struct xfs_inode	*ip2;
+
+	/* File offset range information. */
+	xfs_fileoff_t		startoff1;
+	xfs_fileoff_t		startoff2;
+	xfs_filblks_t		blockcount;
+
+	/* Data or attr fork? */
+	int			whichfork;
+
+	/* XFS_SWAP_REQ_* operation flags */
+	unsigned int		req_flags;
+
+	/*
+	 * Fields below this line are filled out by xfs_swapext_estimate;
+	 * callers should initialize this part of the struct to zero.
+	 */
+
+	/*
+	 * Data device blocks to be moved out of ip1, and free space needed to
+	 * handle the bmbt changes.
+	 */
+	xfs_filblks_t		ip1_bcount;
+
+	/*
+	 * Data device blocks to be moved out of ip2, and free space needed to
+	 * handle the bmbt changes.
+	 */
+	xfs_filblks_t		ip2_bcount;
+
+	/* rt blocks to be moved out of ip1. */
+	xfs_filblks_t		ip1_rtbcount;
+
+	/* rt blocks to be moved out of ip2. */
+	xfs_filblks_t		ip2_rtbcount;
+
+	/* Free space needed to handle the bmbt changes */
+	unsigned long long	resblks;
+
+	/* Number of extent swaps needed to complete the operation */
+	unsigned long long	nr_exchanges;
+};
+
+/* Caller has permission to use log intent items for the swapext operation. */
+#define XFS_SWAP_REQ_LOGGED		(1U << 0)
+
+/* Set the file sizes when finished. */
+#define XFS_SWAP_REQ_SET_SIZES		(1U << 1)
+
+/*
+ * Swap only the parts of the two files where the file allocation units
+ * mapped to file1's range have been written to.
+ */
+#define XFS_SWAP_REQ_INO1_WRITTEN	(1U << 2)
+
+/* Files need to be upgraded to have large extent counts. */
+#define XFS_SWAP_REQ_NREXT64		(1U << 3)
+
+#define XFS_SWAP_REQ_FLAGS		(XFS_SWAP_REQ_LOGGED | \
+					 XFS_SWAP_REQ_SET_SIZES | \
+					 XFS_SWAP_REQ_INO1_WRITTEN | \
+					 XFS_SWAP_REQ_NREXT64)
+
+#define XFS_SWAP_REQ_STRINGS \
+	{ XFS_SWAP_REQ_LOGGED,		"LOGGED" }, \
+	{ XFS_SWAP_REQ_SET_SIZES,	"SETSIZES" }, \
+	{ XFS_SWAP_REQ_INO1_WRITTEN,	"INO1_WRITTEN" }, \
+	{ XFS_SWAP_REQ_NREXT64,		"NREXT64" }
+
+unsigned int xfs_swapext_reflink_prep(const struct xfs_swapext_req *req);
+void xfs_swapext_reflink_finish(struct xfs_trans *tp,
+		const struct xfs_swapext_req *req, unsigned int reflink_state);
+
+int xfs_swapext_estimate(struct xfs_swapext_req *req);
+
+extern struct kmem_cache	*xfs_swapext_intent_cache;
+
+int __init xfs_swapext_intent_init_cache(void);
+void xfs_swapext_intent_destroy_cache(void);
+
+struct xfs_swapext_intent *xfs_swapext_init_intent(
+		const struct xfs_swapext_req *req, unsigned int *reflink_state);
+void xfs_swapext_ensure_reflink(struct xfs_trans *tp,
+		const struct xfs_swapext_intent *sxi, unsigned int reflink_state);
+
+int xfs_swapext_finish_one(struct xfs_trans *tp,
+		struct xfs_swapext_intent *sxi);
+
+int xfs_swapext_check_extents(struct xfs_mount *mp,
+		const struct xfs_swapext_req *req);
+
+void xfs_swapext(struct xfs_trans *tp, const struct xfs_swapext_req *req);
+
 #endif /* __XFS_SWAPEXT_H_ */
diff --git a/fs/xfs/libxfs/xfs_trans_space.h b/fs/xfs/libxfs/xfs_trans_space.h
index 87b31c69a7732..9640fc232c147 100644
--- a/fs/xfs/libxfs/xfs_trans_space.h
+++ b/fs/xfs/libxfs/xfs_trans_space.h
@@ -10,6 +10,10 @@
  * Components of space reservations.
  */
 
+/* Worst case number of bmaps that can be held in a block. */
+#define XFS_MAX_CONTIG_BMAPS_PER_BLOCK(mp)    \
+		(((mp)->m_bmap_dmxr[0]) - ((mp)->m_bmap_dmnr[0]))
+
 /* Worst case number of rmaps that can be held in a block. */
 #define XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)    \
 		(((mp)->m_rmap_mxr[0]) - ((mp)->m_rmap_mnr[0]))
diff --git a/fs/xfs/xfs_swapext_item.c b/fs/xfs/xfs_swapext_item.c
index 0117735913cf1..182417fee1e2f 100644
--- a/fs/xfs/xfs_swapext_item.c
+++ b/fs/xfs/xfs_swapext_item.c
@@ -16,13 +16,17 @@
 #include "xfs_trans.h"
 #include "xfs_trans_priv.h"
 #include "xfs_swapext_item.h"
+#include "xfs_swapext.h"
 #include "xfs_log.h"
 #include "xfs_bmap.h"
 #include "xfs_icache.h"
+#include "xfs_bmap_btree.h"
 #include "xfs_trans_space.h"
 #include "xfs_error.h"
 #include "xfs_log_priv.h"
 #include "xfs_log_recover.h"
+#include "xfs_xchgrange.h"
+#include "xfs_trace.h"
 
 struct kmem_cache	*xfs_sxi_cache;
 struct kmem_cache	*xfs_sxd_cache;
@@ -144,6 +148,381 @@ static inline struct xfs_sxd_log_item *SXD_ITEM(struct xfs_log_item *lip)
 	return container_of(lip, struct xfs_sxd_log_item, sxd_item);
 }
 
+STATIC void
+xfs_sxd_item_size(
+	struct xfs_log_item	*lip,
+	int			*nvecs,
+	int			*nbytes)
+{
+	*nvecs += 1;
+	*nbytes += sizeof(struct xfs_sxd_log_format);
+}
+
+/*
+ * This is called to fill in the vector of log iovecs for the given sxd log
+ * item. We use only 1 iovec, and we point that at the sxd_log_format structure
+ * embedded in the sxd item.
+ */
+STATIC void
+xfs_sxd_item_format(
+	struct xfs_log_item	*lip,
+	struct xfs_log_vec	*lv)
+{
+	struct xfs_sxd_log_item	*sxd_lip = SXD_ITEM(lip);
+	struct xfs_log_iovec	*vecp = NULL;
+
+	sxd_lip->sxd_format.sxd_type = XFS_LI_SXD;
+	sxd_lip->sxd_format.sxd_size = 1;
+
+	xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_SXD_FORMAT, &sxd_lip->sxd_format,
+			sizeof(struct xfs_sxd_log_format));
+}
+
+/*
+ * The SXD is either committed or aborted if the transaction is cancelled. If
+ * the transaction is cancelled, drop our reference to the SXI and free the
+ * SXD.
+ */
+STATIC void
+xfs_sxd_item_release(
+	struct xfs_log_item	*lip)
+{
+	struct xfs_sxd_log_item	*sxd_lip = SXD_ITEM(lip);
+
+	xfs_sxi_release(sxd_lip->sxd_intent_log_item);
+	kmem_free(sxd_lip->sxd_item.li_lv_shadow);
+	kmem_cache_free(xfs_sxd_cache, sxd_lip);
+}
+
+static struct xfs_log_item *
+xfs_sxd_item_intent(
+	struct xfs_log_item	*lip)
+{
+	return &SXD_ITEM(lip)->sxd_intent_log_item->sxi_item;
+}
+
+static const struct xfs_item_ops xfs_sxd_item_ops = {
+	.flags		= XFS_ITEM_RELEASE_WHEN_COMMITTED |
+			  XFS_ITEM_INTENT_DONE,
+	.iop_size	= xfs_sxd_item_size,
+	.iop_format	= xfs_sxd_item_format,
+	.iop_release	= xfs_sxd_item_release,
+	.iop_intent	= xfs_sxd_item_intent,
+};
+
+/* Log swapext updates in the intent item. */
+STATIC struct xfs_log_item *
+xfs_swapext_create_intent(
+	struct xfs_trans		*tp,
+	struct list_head		*items,
+	unsigned int			count,
+	bool				sort)
+{
+	struct xfs_sxi_log_item		*sxi_lip;
+	struct xfs_swapext_intent	*sxi;
+	struct xfs_swap_extent		*sx;
+
+	ASSERT(count == 1);
+
+	sxi = list_first_entry_or_null(items, struct xfs_swapext_intent,
+			sxi_list);
+
+	/*
+	 * We use the same defer ops control machinery to perform extent swaps
+	 * even if we aren't using the machinery to track the operation status
+	 * through log items.
+	 */
+	if (!(sxi->sxi_op_flags & XFS_SWAP_EXT_OP_LOGGED))
+		return NULL;
+
+	sxi_lip = xfs_sxi_init(tp->t_mountp);
+
+	sx = &sxi_lip->sxi_format.sxi_extent;
+	sx->sx_inode1 = sxi->sxi_ip1->i_ino;
+	sx->sx_inode2 = sxi->sxi_ip2->i_ino;
+	sx->sx_startoff1 = sxi->sxi_startoff1;
+	sx->sx_startoff2 = sxi->sxi_startoff2;
+	sx->sx_blockcount = sxi->sxi_blockcount;
+	sx->sx_isize1 = sxi->sxi_isize1;
+	sx->sx_isize2 = sxi->sxi_isize2;
+	sx->sx_flags = sxi->sxi_flags;
+
+	return &sxi_lip->sxi_item;
+}
+
+STATIC struct xfs_log_item *
+xfs_swapext_create_done(
+	struct xfs_trans		*tp,
+	struct xfs_log_item		*intent,
+	unsigned int			count)
+{
+	struct xfs_sxi_log_item		*sxi_lip = SXI_ITEM(intent);
+	struct xfs_sxd_log_item		*sxd_lip;
+
+	sxd_lip = kmem_cache_zalloc(xfs_sxd_cache, GFP_KERNEL | __GFP_NOFAIL);
+	xfs_log_item_init(tp->t_mountp, &sxd_lip->sxd_item, XFS_LI_SXD,
+			  &xfs_sxd_item_ops);
+	sxd_lip->sxd_intent_log_item = sxi_lip;
+	sxd_lip->sxd_format.sxd_sxi_id = sxi_lip->sxi_format.sxi_id;
+
+	return &sxd_lip->sxd_item;
+}
+
+/* Add this deferred SXI to the transaction. */
+void
+xfs_swapext_defer_add(
+	struct xfs_trans		*tp,
+	struct xfs_swapext_intent	*sxi)
+{
+	trace_xfs_swapext_defer(tp->t_mountp, sxi);
+
+	xfs_defer_add(tp, &sxi->sxi_list, &xfs_swapext_defer_type);
+}
+
+static inline struct xfs_swapext_intent *sxi_entry(const struct list_head *e)
+{
+	return list_entry(e, struct xfs_swapext_intent, sxi_list);
+}
+
+/* Cancel a deferred swapext update. */
+STATIC void
+xfs_swapext_cancel_item(
+	struct list_head		*item)
+{
+	struct xfs_swapext_intent	*sxi = sxi_entry(item);
+
+	kmem_cache_free(xfs_swapext_intent_cache, sxi);
+}
+
+/* Process a deferred swapext update. */
+STATIC int
+xfs_swapext_finish_item(
+	struct xfs_trans		*tp,
+	struct xfs_log_item		*done,
+	struct list_head		*item,
+	struct xfs_btree_cur		**state)
+{
+	struct xfs_swapext_intent	*sxi = sxi_entry(item);
+	int				error;
+
+	/*
+	 * Swap one more extent between the two files.  If there's still more
+	 * work to do, we want to requeue ourselves after all other pending
+	 * deferred operations have finished.  This includes all of the dfops
+	 * that we queued directly as well as any new ones created in the
+	 * process of finishing the others.  Doing so prevents us from queuing
+	 * a large number of SXI log items in kernel memory, which in turn
+	 * prevents us from pinning the tail of the log (while logging those
+	 * new SXI items) until the first SXI items can be processed.
+	 */
+	error = xfs_swapext_finish_one(tp, sxi);
+	if (error != -EAGAIN)
+		xfs_swapext_cancel_item(item);
+	return error;
+}
+
+/* Abort all pending SXIs. */
+STATIC void
+xfs_swapext_abort_intent(
+	struct xfs_log_item		*intent)
+{
+	xfs_sxi_release(SXI_ITEM(intent));
+}
+
+/* Is this recovered SXI ok? */
+static inline bool
+xfs_sxi_validate(
+	struct xfs_mount		*mp,
+	struct xfs_sxi_log_item		*sxi_lip)
+{
+	struct xfs_swap_extent		*sx = &sxi_lip->sxi_format.sxi_extent;
+
+	if (!xfs_sb_version_haslogswapext(&mp->m_sb) &&
+	    !xfs_swapext_can_use_without_log_assistance(mp))
+		return false;
+
+	if (sxi_lip->sxi_format.__pad != 0)
+		return false;
+
+	if (sx->sx_flags & ~XFS_SWAP_EXT_FLAGS)
+		return false;
+
+	if (!xfs_verify_ino(mp, sx->sx_inode1) ||
+	    !xfs_verify_ino(mp, sx->sx_inode2))
+		return false;
+
+	if ((sx->sx_flags & XFS_SWAP_EXT_SET_SIZES) &&
+	     (sx->sx_isize1 < 0 || sx->sx_isize2 < 0))
+		return false;
+
+	if (!xfs_verify_fileext(mp, sx->sx_startoff1, sx->sx_blockcount))
+		return false;
+
+	return xfs_verify_fileext(mp, sx->sx_startoff2, sx->sx_blockcount);
+}
+
+/*
+ * Use the recovered log state to create a new request, estimate resource
+ * requirements, and create a new incore intent state.
+ */
+STATIC struct xfs_swapext_intent *
+xfs_sxi_item_recover_intent(
+	struct xfs_mount		*mp,
+	struct xfs_defer_pending	*dfp,
+	const struct xfs_swap_extent	*sx,
+	struct xfs_swapext_req		*req,
+	struct xfs_inode		**ipp1,
+	struct xfs_inode		**ipp2,
+	unsigned int			*reflink_state)
+{
+	struct xfs_inode		*ip1, *ip2;
+	struct xfs_swapext_intent	*sxi;
+	int				error;
+
+	/*
+	 * Grab both inodes and set IRECOVERY to prevent trimming of post-eof
+	 * extents and freeing of unlinked inodes until we're totally done
+	 * processing files.
+	 */
+	error = xlog_recover_iget(mp, sx->sx_inode1, &ip1);
+	if (error)
+		return ERR_PTR(error);
+	error = xlog_recover_iget(mp, sx->sx_inode2, &ip2);
+	if (error)
+		goto err_rele1;
+
+	req->ip1 = ip1;
+	req->ip2 = ip2;
+	req->startoff1 = sx->sx_startoff1;
+	req->startoff2 = sx->sx_startoff2;
+	req->blockcount = sx->sx_blockcount;
+
+	if (sx->sx_flags & XFS_SWAP_EXT_ATTR_FORK)
+		req->whichfork = XFS_ATTR_FORK;
+	else
+		req->whichfork = XFS_DATA_FORK;
+
+	if (sx->sx_flags & XFS_SWAP_EXT_SET_SIZES)
+		req->req_flags |= XFS_SWAP_REQ_SET_SIZES;
+	if (sx->sx_flags & XFS_SWAP_EXT_INO1_WRITTEN)
+		req->req_flags |= XFS_SWAP_REQ_INO1_WRITTEN;
+	req->req_flags |= XFS_SWAP_REQ_LOGGED;
+
+	xfs_xchg_range_ilock(NULL, ip1, ip2);
+	error = xfs_swapext_estimate(req);
+	xfs_xchg_range_iunlock(ip1, ip2);
+	if (error)
+		goto err_rele2;
+
+	*ipp1 = ip1;
+	*ipp2 = ip2;
+	sxi = xfs_swapext_init_intent(req, reflink_state);
+	xfs_defer_add_item(dfp, &sxi->sxi_list);
+	return sxi;
+
+err_rele2:
+	xfs_irele(ip2);
+err_rele1:
+	xfs_irele(ip1);
+	req->ip2 = req->ip1 = NULL;
+	return ERR_PTR(error);
+}
+
+/* Process a swapext update intent item that was recovered from the log. */
+STATIC int
+xfs_swapext_recover_work(
+	struct xfs_defer_pending	*dfp,
+	struct list_head		*capture_list)
+{
+	struct xfs_swapext_req		req = { .req_flags = 0 };
+	struct xfs_trans_res		resv;
+	struct xfs_swapext_intent	*sxi;
+	struct xfs_log_item		*lip = dfp->dfp_intent;
+	struct xfs_sxi_log_item		*sxi_lip = SXI_ITEM(lip);
+	struct xfs_mount		*mp = lip->li_log->l_mp;
+	struct xfs_swap_extent		*sx = &sxi_lip->sxi_format.sxi_extent;
+	struct xfs_trans		*tp;
+	struct xfs_inode		*ip1, *ip2;
+	unsigned int			reflink_state;
+	int				error = 0;
+
+	if (!xfs_sxi_validate(mp, sxi_lip)) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				&sxi_lip->sxi_format,
+				sizeof(sxi_lip->sxi_format));
+		return -EFSCORRUPTED;
+	}
+
+	sxi = xfs_sxi_item_recover_intent(mp, dfp, sx, &req, &ip1, &ip2,
+			&reflink_state);
+	if (IS_ERR(sxi))
+		return PTR_ERR(sxi);
+
+	trace_xfs_swapext_recover(mp, sxi);
+
+	resv = xlog_recover_resv(&M_RES(mp)->tr_write);
+	error = xfs_trans_alloc(mp, &resv, req.resblks, 0, 0, &tp);
+	if (error)
+		goto err_rele;
+
+	xfs_xchg_range_ilock(tp, ip1, ip2);
+
+	xfs_swapext_ensure_reflink(tp, sxi, reflink_state);
+	error = xlog_recover_finish_intent(tp, dfp);
+	if (error == -EFSCORRUPTED)
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				&sxi_lip->sxi_format,
+				sizeof(sxi_lip->sxi_format));
+	if (error)
+		goto err_cancel;
+
+	/*
+	 * Commit transaction, which frees the transaction and saves the inodes
+	 * for later replay activities.
+	 */
+	error = xfs_defer_ops_capture_and_commit(tp, capture_list);
+	goto err_unlock;
+
+err_cancel:
+	xfs_trans_cancel(tp);
+err_unlock:
+	xfs_xchg_range_iunlock(ip1, ip2);
+err_rele:
+	xfs_irele(ip2);
+	xfs_irele(ip1);
+	return error;
+}
+
+/* Relog an intent item to push the log tail forward. */
+static struct xfs_log_item *
+xfs_swapext_relog_intent(
+	struct xfs_trans		*tp,
+	struct xfs_log_item		*intent,
+	struct xfs_log_item		*done_item)
+{
+	struct xfs_sxi_log_item		*sxi_lip;
+	struct xfs_swap_extent		*sx;
+
+	sx = &SXI_ITEM(intent)->sxi_format.sxi_extent;
+
+	sxi_lip = xfs_sxi_init(tp->t_mountp);
+	memcpy(&sxi_lip->sxi_format.sxi_extent, sx, sizeof(*sx));
+
+	return &sxi_lip->sxi_item;
+}
+
+const struct xfs_defer_op_type xfs_swapext_defer_type = {
+	.name		= "swapext",
+	.max_items	= 1,
+	.create_intent	= xfs_swapext_create_intent,
+	.abort_intent	= xfs_swapext_abort_intent,
+	.create_done	= xfs_swapext_create_done,
+	.finish_item	= xfs_swapext_finish_item,
+	.cancel_item	= xfs_swapext_cancel_item,
+	.recover_work	= xfs_swapext_recover_work,
+	.relog_intent	= xfs_swapext_relog_intent,
+};
+
 STATIC bool
 xfs_sxi_item_match(
 	struct xfs_log_item	*lip,
@@ -181,22 +560,23 @@ xlog_recover_sxi_commit_pass2(
 
 	sxi_formatp = item->ri_buf[0].i_addr;
 
-	if (sxi_formatp->__pad != 0) {
-		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
-		return -EFSCORRUPTED;
-	}
-
 	len = sizeof(struct xfs_sxi_log_format);
 	if (item->ri_buf[0].i_len != len) {
 		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
 		return -EFSCORRUPTED;
 	}
 
+	if (sxi_formatp->__pad != 0) {
+		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
+		return -EFSCORRUPTED;
+	}
+
 	sxi_lip = xfs_sxi_init(mp);
 	memcpy(&sxi_lip->sxi_format, sxi_formatp, len);
 
-	/* not implemented yet */
-	return -EIO;
+	xlog_recover_intent_item(log, &sxi_lip->sxi_item, lsn,
+			&xfs_swapext_defer_type);
+	return 0;
 }
 
 const struct xlog_recover_item_ops xlog_sxi_item_ops = {
diff --git a/fs/xfs/xfs_swapext_item.h b/fs/xfs/xfs_swapext_item.h
index d816ab842a603..814dfaaa2c4c5 100644
--- a/fs/xfs/xfs_swapext_item.h
+++ b/fs/xfs/xfs_swapext_item.h
@@ -53,4 +53,8 @@ struct xfs_sxd_log_item {
 extern struct kmem_cache	*xfs_sxi_cache;
 extern struct kmem_cache	*xfs_sxd_cache;
 
+struct xfs_swapext_intent;
+
+void xfs_swapext_defer_add(struct xfs_trans *tp, struct xfs_swapext_intent *sxi);
+
 #endif	/* __XFS_SWAPEXT_ITEM_H__ */
diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c
index c9a5d8087b63c..b43b973f0e102 100644
--- a/fs/xfs/xfs_trace.c
+++ b/fs/xfs/xfs_trace.c
@@ -40,6 +40,7 @@
 #include "scrub/xfbtree.h"
 #include "xfs_btree_mem.h"
 #include "xfs_bmap.h"
+#include "xfs_swapext.h"
 
 /*
  * We include this last to have the helpers above available for the trace
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index a36b48432d093..893f69a2308ca 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -79,6 +79,8 @@ struct xfs_dqtrx;
 struct xfs_icwalk;
 struct xfs_perag;
 struct xfs_bmap_intent;
+struct xfs_swapext_intent;
+struct xfs_swapext_req;
 
 #define XFS_ATTR_FILTER_FLAGS \
 	{ XFS_ATTR_ROOT,	"ROOT" }, \
@@ -2151,7 +2153,7 @@ TRACE_EVENT(xfs_dir2_leafn_moveents,
 		  __entry->count)
 );
 
-#define XFS_SWAPEXT_INODES \
+#define XFS_SWAP_EXT_INODES \
 	{ 0,	"target" }, \
 	{ 1,	"temp" }
 
@@ -2186,7 +2188,7 @@ DECLARE_EVENT_CLASS(xfs_swap_extent_class,
 		  "broot size %d, forkoff 0x%x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->ino,
-		  __print_symbolic(__entry->which, XFS_SWAPEXT_INODES),
+		  __print_symbolic(__entry->which, XFS_SWAP_EXT_INODES),
 		  __print_symbolic(__entry->format, XFS_INODE_FORMAT_STR),
 		  __entry->nex,
 		  __entry->broot_size,
@@ -3748,6 +3750,10 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_cancel_cow);
 DEFINE_INODE_IREC_EVENT(xfs_swap_extent_rmap_remap);
 DEFINE_INODE_IREC_EVENT(xfs_swap_extent_rmap_remap_piece);
 DEFINE_INODE_ERROR_EVENT(xfs_swap_extent_rmap_error);
+DEFINE_INODE_IREC_EVENT(xfs_swapext_extent1_skip);
+DEFINE_INODE_IREC_EVENT(xfs_swapext_extent1);
+DEFINE_INODE_IREC_EVENT(xfs_swapext_extent2);
+DEFINE_ITRUNC_EVENT(xfs_swapext_update_inode_size);
 
 /* fsmap traces */
 DECLARE_EVENT_CLASS(xfs_fsmap_class,
@@ -4636,6 +4642,212 @@ DEFINE_PERAG_INTENTS_EVENT(xfs_perag_wait_intents);
 
 #endif /* CONFIG_XFS_DRAIN_INTENTS */
 
+TRACE_EVENT(xfs_swapext_overhead,
+	TP_PROTO(struct xfs_mount *mp, unsigned long long bmbt_blocks,
+		 unsigned long long rmapbt_blocks),
+	TP_ARGS(mp, bmbt_blocks, rmapbt_blocks),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(unsigned long long, bmbt_blocks)
+		__field(unsigned long long, rmapbt_blocks)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->bmbt_blocks = bmbt_blocks;
+		__entry->rmapbt_blocks = rmapbt_blocks;
+	),
+	TP_printk("dev %d:%d bmbt_blocks 0x%llx rmapbt_blocks 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->bmbt_blocks,
+		  __entry->rmapbt_blocks)
+);
+
+DECLARE_EVENT_CLASS(xfs_swapext_estimate_class,
+	TP_PROTO(const struct xfs_swapext_req *req),
+	TP_ARGS(req),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino1)
+		__field(xfs_ino_t, ino2)
+		__field(xfs_fileoff_t, startoff1)
+		__field(xfs_fileoff_t, startoff2)
+		__field(xfs_filblks_t, blockcount)
+		__field(int, whichfork)
+		__field(unsigned int, req_flags)
+		__field(xfs_filblks_t, ip1_bcount)
+		__field(xfs_filblks_t, ip2_bcount)
+		__field(xfs_filblks_t, ip1_rtbcount)
+		__field(xfs_filblks_t, ip2_rtbcount)
+		__field(unsigned long long, resblks)
+		__field(unsigned long long, nr_exchanges)
+	),
+	TP_fast_assign(
+		__entry->dev = req->ip1->i_mount->m_super->s_dev;
+		__entry->ino1 = req->ip1->i_ino;
+		__entry->ino2 = req->ip2->i_ino;
+		__entry->startoff1 = req->startoff1;
+		__entry->startoff2 = req->startoff2;
+		__entry->blockcount = req->blockcount;
+		__entry->whichfork = req->whichfork;
+		__entry->req_flags = req->req_flags;
+		__entry->ip1_bcount = req->ip1_bcount;
+		__entry->ip2_bcount = req->ip2_bcount;
+		__entry->ip1_rtbcount = req->ip1_rtbcount;
+		__entry->ip2_rtbcount = req->ip2_rtbcount;
+		__entry->resblks = req->resblks;
+		__entry->nr_exchanges = req->nr_exchanges;
+	),
+	TP_printk("dev %d:%d ino1 0x%llx fileoff1 0x%llx ino2 0x%llx fileoff2 0x%llx fsbcount 0x%llx flags (%s) fork %s bcount1 0x%llx rtbcount1 0x%llx bcount2 0x%llx rtbcount2 0x%llx resblks 0x%llx nr_exchanges %llu",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino1, __entry->startoff1,
+		  __entry->ino2, __entry->startoff2,
+		  __entry->blockcount,
+		  __print_flags(__entry->req_flags, "|", XFS_SWAP_REQ_STRINGS),
+		  __print_symbolic(__entry->whichfork, XFS_WHICHFORK_STRINGS),
+		  __entry->ip1_bcount,
+		  __entry->ip1_rtbcount,
+		  __entry->ip2_bcount,
+		  __entry->ip2_rtbcount,
+		  __entry->resblks,
+		  __entry->nr_exchanges)
+);
+
+#define DEFINE_SWAPEXT_ESTIMATE_EVENT(name)	\
+DEFINE_EVENT(xfs_swapext_estimate_class, name,	\
+	TP_PROTO(const struct xfs_swapext_req *req), \
+	TP_ARGS(req))
+DEFINE_SWAPEXT_ESTIMATE_EVENT(xfs_swapext_initial_estimate);
+DEFINE_SWAPEXT_ESTIMATE_EVENT(xfs_swapext_final_estimate);
+
+DECLARE_EVENT_CLASS(xfs_swapext_intent_class,
+	TP_PROTO(struct xfs_mount *mp, const struct xfs_swapext_intent *sxi),
+	TP_ARGS(mp, sxi),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino1)
+		__field(xfs_ino_t, ino2)
+		__field(unsigned int, flags)
+		__field(unsigned int, opflags)
+		__field(xfs_fileoff_t, startoff1)
+		__field(xfs_fileoff_t, startoff2)
+		__field(xfs_filblks_t, blockcount)
+		__field(xfs_fsize_t, isize1)
+		__field(xfs_fsize_t, isize2)
+		__field(xfs_fsize_t, new_isize1)
+		__field(xfs_fsize_t, new_isize2)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->ino1 = sxi->sxi_ip1->i_ino;
+		__entry->ino2 = sxi->sxi_ip2->i_ino;
+		__entry->flags = sxi->sxi_flags;
+		__entry->opflags = sxi->sxi_op_flags;
+		__entry->startoff1 = sxi->sxi_startoff1;
+		__entry->startoff2 = sxi->sxi_startoff2;
+		__entry->blockcount = sxi->sxi_blockcount;
+		__entry->isize1 = sxi->sxi_ip1->i_disk_size;
+		__entry->isize2 = sxi->sxi_ip2->i_disk_size;
+		__entry->new_isize1 = sxi->sxi_isize1;
+		__entry->new_isize2 = sxi->sxi_isize2;
+	),
+	TP_printk("dev %d:%d ino1 0x%llx fileoff1 0x%llx ino2 0x%llx fileoff2 0x%llx fsbcount 0x%llx flags (%s) opflags (%s) isize1 0x%llx newisize1 0x%llx isize2 0x%llx newisize2 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino1, __entry->startoff1,
+		  __entry->ino2, __entry->startoff2,
+		  __entry->blockcount,
+		  __print_flags(__entry->flags, "|", XFS_SWAP_EXT_STRINGS),
+		  __print_flags(__entry->opflags, "|", XFS_SWAP_EXT_OP_STRINGS),
+		  __entry->isize1, __entry->new_isize1,
+		  __entry->isize2, __entry->new_isize2)
+);
+
+#define DEFINE_SWAPEXT_INTENT_EVENT(name)	\
+DEFINE_EVENT(xfs_swapext_intent_class, name,	\
+	TP_PROTO(struct xfs_mount *mp, const struct xfs_swapext_intent *sxi), \
+	TP_ARGS(mp, sxi))
+DEFINE_SWAPEXT_INTENT_EVENT(xfs_swapext_defer);
+DEFINE_SWAPEXT_INTENT_EVENT(xfs_swapext_recover);
+
+TRACE_EVENT(xfs_swapext_delta_nextents_step,
+	TP_PROTO(struct xfs_mount *mp,
+		 const struct xfs_bmbt_irec *left,
+		 const struct xfs_bmbt_irec *curr,
+		 const struct xfs_bmbt_irec *new,
+		 const struct xfs_bmbt_irec *right,
+		 int delta, unsigned int state),
+	TP_ARGS(mp, left, curr, new, right, delta, state),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_fileoff_t, loff)
+		__field(xfs_fsblock_t, lstart)
+		__field(xfs_filblks_t, lcount)
+		__field(xfs_fileoff_t, coff)
+		__field(xfs_fsblock_t, cstart)
+		__field(xfs_filblks_t, ccount)
+		__field(xfs_fileoff_t, noff)
+		__field(xfs_fsblock_t, nstart)
+		__field(xfs_filblks_t, ncount)
+		__field(xfs_fileoff_t, roff)
+		__field(xfs_fsblock_t, rstart)
+		__field(xfs_filblks_t, rcount)
+		__field(int, delta)
+		__field(unsigned int, state)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->loff = left->br_startoff;
+		__entry->lstart = left->br_startblock;
+		__entry->lcount = left->br_blockcount;
+		__entry->coff = curr->br_startoff;
+		__entry->cstart = curr->br_startblock;
+		__entry->ccount = curr->br_blockcount;
+		__entry->noff = new->br_startoff;
+		__entry->nstart = new->br_startblock;
+		__entry->ncount = new->br_blockcount;
+		__entry->roff = right->br_startoff;
+		__entry->rstart = right->br_startblock;
+		__entry->rcount = right->br_blockcount;
+		__entry->delta = delta;
+		__entry->state = state;
+	),
+	TP_printk("dev %d:%d left 0x%llx:0x%llx:0x%llx; curr 0x%llx:0x%llx:0x%llx <- new 0x%llx:0x%llx:0x%llx; right 0x%llx:0x%llx:0x%llx delta %d state 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		__entry->loff, __entry->lstart, __entry->lcount,
+		__entry->coff, __entry->cstart, __entry->ccount,
+		__entry->noff, __entry->nstart, __entry->ncount,
+		__entry->roff, __entry->rstart, __entry->rcount,
+		__entry->delta, __entry->state)
+);
+
+TRACE_EVENT(xfs_swapext_delta_nextents,
+	TP_PROTO(const struct xfs_swapext_req *req, int64_t d_nexts1,
+		 int64_t d_nexts2),
+	TP_ARGS(req, d_nexts1, d_nexts2),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino1)
+		__field(xfs_ino_t, ino2)
+		__field(xfs_extnum_t, nexts1)
+		__field(xfs_extnum_t, nexts2)
+		__field(int64_t, d_nexts1)
+		__field(int64_t, d_nexts2)
+	),
+	TP_fast_assign(
+		__entry->dev = req->ip1->i_mount->m_super->s_dev;
+		__entry->ino1 = req->ip1->i_ino;
+		__entry->ino2 = req->ip2->i_ino;
+		__entry->nexts1 = xfs_ifork_ptr(req->ip1, req->whichfork)->if_nextents;
+		__entry->nexts2 = xfs_ifork_ptr(req->ip2, req->whichfork)->if_nextents;
+		__entry->d_nexts1 = d_nexts1;
+		__entry->d_nexts2 = d_nexts2;
+	),
+	TP_printk("dev %d:%d ino1 0x%llx nexts %llu ino2 0x%llx nexts %llu delta1 %lld delta2 %lld",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino1, __entry->nexts1,
+		  __entry->ino2, __entry->nexts2,
+		  __entry->d_nexts1, __entry->d_nexts2)
+);
+
 #endif /* _TRACE_XFS_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/fs/xfs/xfs_xchgrange.c b/fs/xfs/xfs_xchgrange.c
index 764d64e04726b..ebbd7b1fe3983 100644
--- a/fs/xfs/xfs_xchgrange.c
+++ b/fs/xfs/xfs_xchgrange.c
@@ -12,6 +12,7 @@
 #include "xfs_defer.h"
 #include "xfs_inode.h"
 #include "xfs_trans.h"
+#include "xfs_swapext.h"
 #include "xfs_xchgrange.h"
 #include <linux/fsnotify.h>
 
@@ -341,6 +342,55 @@ xfs_exch_range(
 	file_start_write(file2);
 	error = __xfs_exch_range(file1, file2, fxr);
 	file_end_write(file2);
+	return error;
+}
+
+/* XFS-specific parts of XFS_IOC_EXCHANGE_RANGE */
+
+/* Lock (and optionally join) two inodes for a file range exchange. */
+void
+xfs_xchg_range_ilock(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip1,
+	struct xfs_inode	*ip2)
+{
+	if (ip1 != ip2)
+		xfs_lock_two_inodes(ip1, XFS_ILOCK_EXCL,
+				    ip2, XFS_ILOCK_EXCL);
+	else
+		xfs_ilock(ip1, XFS_ILOCK_EXCL);
+	if (tp) {
+		xfs_trans_ijoin(tp, ip1, 0);
+		if (ip2 != ip1)
+			xfs_trans_ijoin(tp, ip2, 0);
+	}
+
+}
+
+/* Unlock two inodes after a file range exchange operation. */
+void
+xfs_xchg_range_iunlock(
+	struct xfs_inode	*ip1,
+	struct xfs_inode	*ip2)
+{
+	if (ip2 != ip1)
+		xfs_iunlock(ip2, XFS_ILOCK_EXCL);
+	xfs_iunlock(ip1, XFS_ILOCK_EXCL);
+}
+
+/*
+ * Estimate the resource requirements to exchange file contents between the two
+ * files.  The caller is required to hold the IOLOCK and the MMAPLOCK and to
+ * have flushed both inodes' pagecache and active direct-ios.
+ */
+int
+xfs_xchg_range_estimate(
+	struct xfs_swapext_req	*req)
+{
+	int			error;
 
+	xfs_xchg_range_ilock(NULL, req->ip1, req->ip2);
+	error = xfs_swapext_estimate(req);
+	xfs_xchg_range_iunlock(req->ip1, req->ip2);
 	return error;
 }
diff --git a/fs/xfs/xfs_xchgrange.h b/fs/xfs/xfs_xchgrange.h
index 9a73b08998b9b..3544ed84e4106 100644
--- a/fs/xfs/xfs_xchgrange.h
+++ b/fs/xfs/xfs_xchgrange.h
@@ -15,4 +15,14 @@ int xfs_exch_range_finish(struct file *file1, struct file *file2);
 int xfs_exch_range(struct file *file1, struct file *file2,
 		struct xfs_exch_range *fxr);
 
+/* XFS-specific parts of file exchanges */
+
+struct xfs_swapext_req;
+
+void xfs_xchg_range_ilock(struct xfs_trans *tp, struct xfs_inode *ip1,
+		struct xfs_inode *ip2);
+void xfs_xchg_range_iunlock(struct xfs_inode *ip1, struct xfs_inode *ip2);
+
+int xfs_xchg_range_estimate(struct xfs_swapext_req *req);
+
 #endif /* __XFS_XCHGRANGE_H__ */

[PATCH 12/25] xfs: enable xlog users to toggle atomic extent swapping

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Plumb the necessary bits into the xlog code so that higher level callers
can enable the atomic extent swapping feature and have it clear
automatically when possible.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_log.c      |   13 +++++++++++++
 fs/xfs/xfs_log.h      |    1 +
 fs/xfs/xfs_log_priv.h |    1 +
 3 files changed, 15 insertions(+)


diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index f62a6e233689c..8874360e596c5 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1467,11 +1467,17 @@ xlog_clear_incompat(
 	if (down_write_trylock(&log->l_incompat_xattrs))
 		incompat_mask |= XFS_SB_FEAT_INCOMPAT_LOG_XATTRS;
 
+	if (down_write_trylock(&log->l_incompat_swapext))
+		incompat_mask |= XFS_SB_FEAT_INCOMPAT_LOG_SWAPEXT;
+
 	if (!incompat_mask)
 		return;
 
 	xfs_clear_incompat_log_features(mp, incompat_mask);
 
+	if (incompat_mask & XFS_SB_FEAT_INCOMPAT_LOG_SWAPEXT)
+		up_write(&log->l_incompat_swapext);
+
 	if (incompat_mask & XFS_SB_FEAT_INCOMPAT_LOG_XATTRS)
 		up_write(&log->l_incompat_xattrs);
 }
@@ -1592,6 +1598,7 @@ xlog_alloc_log(
 	log->l_sectBBsize = 1 << log2_size;
 
 	init_rwsem(&log->l_incompat_xattrs);
+	init_rwsem(&log->l_incompat_swapext);
 
 	xlog_get_iclog_buffer_size(mp, log);
 
@@ -3890,6 +3897,9 @@ xlog_use_incompat_feat(
 	case XLOG_INCOMPAT_FEAT_XATTRS:
 		down_read(&log->l_incompat_xattrs);
 		break;
+	case XLOG_INCOMPAT_FEAT_SWAPEXT:
+		down_read(&log->l_incompat_swapext);
+		break;
 	}
 }
 
@@ -3903,5 +3913,8 @@ xlog_drop_incompat_feat(
 	case XLOG_INCOMPAT_FEAT_XATTRS:
 		up_read(&log->l_incompat_xattrs);
 		break;
+	case XLOG_INCOMPAT_FEAT_SWAPEXT:
+		up_read(&log->l_incompat_swapext);
+		break;
 	}
 }
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index d187f64459093..30bdbf8ee25c3 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -161,6 +161,7 @@ bool	  xlog_force_shutdown(struct xlog *log, uint32_t shutdown_flags);
 
 enum xlog_incompat_feat {
 	XLOG_INCOMPAT_FEAT_XATTRS = XFS_SB_FEAT_INCOMPAT_LOG_XATTRS,
+	XLOG_INCOMPAT_FEAT_SWAPEXT = XFS_SB_FEAT_INCOMPAT_LOG_SWAPEXT
 };
 
 void xlog_use_incompat_feat(struct xlog *log, enum xlog_incompat_feat what);
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index 304aed840f962..32acdecdc1fa3 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -453,6 +453,7 @@ struct xlog {
 
 	/* Users of log incompat features should take a read lock. */
 	struct rw_semaphore	l_incompat_xattrs;
+	struct rw_semaphore	l_incompat_swapext;
 };
 
 /*

[PATCH 13/25] xfs: bind the xfs-specific extent swap code to the vfs-generic file exchange code

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

So far we've constructed the top half of file range exchange which
deals with VFS-level objects; and the bottom half of extent swapping,
which deals with file mappings in XFS data structures.  We still need to
glue the two pieces together so do that now.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_bmap_util.c |    1 
 fs/xfs/xfs_mount.h     |    5 -
 fs/xfs/xfs_trace.c     |    1 
 fs/xfs/xfs_trace.h     |  127 +++++++++++++
 fs/xfs/xfs_xchgrange.c |  462 ++++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_xchgrange.h |   28 +++
 6 files changed, 622 insertions(+), 2 deletions(-)


diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 892622530431a..87ac9777c1eaf 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -29,6 +29,7 @@
 #include "xfs_iomap.h"
 #include "xfs_reflink.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_swapext.h"
 
 /* Kernel only BMAP related definitions and functions */
 
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 257bef8019307..f80f04335acc5 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -412,6 +412,8 @@ __XFS_HAS_FEAT(nouuid, NOUUID)
 #define XFS_OPSTATE_WARNED_LARP		9
 /* Mount time quotacheck is running */
 #define XFS_OPSTATE_QUOTACHECK_RUNNING	10
+/* Kernel has logged a warning about extent swapping being used on this fs. */
+#define XFS_OPSTATE_WARNED_SWAPEXT	11
 
 #define __XFS_IS_OPSTATE(name, NAME) \
 static inline bool xfs_is_ ## name (struct xfs_mount *mp) \
@@ -457,7 +459,8 @@ xfs_should_warn(struct xfs_mount *mp, long nr)
 	{ (1UL << XFS_OPSTATE_WARNED_SCRUB),		"wscrub" }, \
 	{ (1UL << XFS_OPSTATE_WARNED_SHRINK),		"wshrink" }, \
 	{ (1UL << XFS_OPSTATE_WARNED_LARP),		"wlarp" }, \
-	{ (1UL << XFS_OPSTATE_QUOTACHECK_RUNNING),	"quotacheck" }
+	{ (1UL << XFS_OPSTATE_QUOTACHECK_RUNNING),	"quotacheck" }, \
+	{ (1UL << XFS_OPSTATE_WARNED_SWAPEXT),		"wswapext" }
 
 /*
  * Max and min values for mount-option defined I/O
diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c
index b43b973f0e102..e38814f4380c8 100644
--- a/fs/xfs/xfs_trace.c
+++ b/fs/xfs/xfs_trace.c
@@ -41,6 +41,7 @@
 #include "xfs_btree_mem.h"
 #include "xfs_bmap.h"
 #include "xfs_swapext.h"
+#include "xfs_xchgrange.h"
 
 /*
  * We include this last to have the helpers above available for the trace
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 893f69a2308ca..53a6122d307ff 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -3750,11 +3750,138 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_cancel_cow);
 DEFINE_INODE_IREC_EVENT(xfs_swap_extent_rmap_remap);
 DEFINE_INODE_IREC_EVENT(xfs_swap_extent_rmap_remap_piece);
 DEFINE_INODE_ERROR_EVENT(xfs_swap_extent_rmap_error);
+
+/* swapext tracepoints */
+DEFINE_INODE_ERROR_EVENT(xfs_file_xchg_range_error);
 DEFINE_INODE_IREC_EVENT(xfs_swapext_extent1_skip);
 DEFINE_INODE_IREC_EVENT(xfs_swapext_extent1);
 DEFINE_INODE_IREC_EVENT(xfs_swapext_extent2);
 DEFINE_ITRUNC_EVENT(xfs_swapext_update_inode_size);
 
+#define XFS_EXCH_RANGE_FLAGS_STRS \
+	{ XFS_EXCH_RANGE_NONATOMIC,	"NONATOMIC" }, \
+	{ XFS_EXCH_RANGE_FILE2_FRESH,	"F2_FRESH" }, \
+	{ XFS_EXCH_RANGE_FULL_FILES,	"FULL" }, \
+	{ XFS_EXCH_RANGE_TO_EOF,	"TO_EOF" }, \
+	{ XFS_EXCH_RANGE_FSYNC	,	"FSYNC" }, \
+	{ XFS_EXCH_RANGE_DRY_RUN,	"DRY_RUN" }, \
+	{ XFS_EXCH_RANGE_FILE1_WRITTEN,	"F1_WRITTEN" }
+
+/* file exchange-range tracepoint class */
+DECLARE_EVENT_CLASS(xfs_xchg_range_class,
+	TP_PROTO(struct xfs_inode *ip1, const struct xfs_exch_range *fxr,
+		 struct xfs_inode *ip2, unsigned int xchg_flags),
+	TP_ARGS(ip1, fxr, ip2, xchg_flags),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ip1_ino)
+		__field(loff_t, ip1_isize)
+		__field(loff_t, ip1_disize)
+		__field(xfs_ino_t, ip2_ino)
+		__field(loff_t, ip2_isize)
+		__field(loff_t, ip2_disize)
+
+		__field(loff_t, file1_offset)
+		__field(loff_t, file2_offset)
+		__field(unsigned long long, length)
+		__field(unsigned long long, vflags)
+		__field(unsigned int, xflags)
+	),
+	TP_fast_assign(
+		__entry->dev = VFS_I(ip1)->i_sb->s_dev;
+		__entry->ip1_ino = ip1->i_ino;
+		__entry->ip1_isize = VFS_I(ip1)->i_size;
+		__entry->ip1_disize = ip1->i_disk_size;
+		__entry->ip2_ino = ip2->i_ino;
+		__entry->ip2_isize = VFS_I(ip2)->i_size;
+		__entry->ip2_disize = ip2->i_disk_size;
+
+		__entry->file1_offset = fxr->file1_offset;
+		__entry->file2_offset = fxr->file2_offset;
+		__entry->length = fxr->length;
+		__entry->vflags = fxr->flags;
+		__entry->xflags = xchg_flags;
+	),
+	TP_printk("dev %d:%d vfs_flags %s xchg_flags %s bytecount 0x%llx "
+		  "ino1 0x%llx isize 0x%llx disize 0x%llx pos 0x%llx -> "
+		  "ino2 0x%llx isize 0x%llx disize 0x%llx pos 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		   __print_flags(__entry->vflags, "|", XFS_EXCH_RANGE_FLAGS_STRS),
+		   __print_flags(__entry->xflags, "|", XCHG_RANGE_FLAGS_STRS),
+		  __entry->length,
+		  __entry->ip1_ino,
+		  __entry->ip1_isize,
+		  __entry->ip1_disize,
+		  __entry->file1_offset,
+		  __entry->ip2_ino,
+		  __entry->ip2_isize,
+		  __entry->ip2_disize,
+		  __entry->file2_offset)
+)
+
+#define DEFINE_XCHG_RANGE_EVENT(name)	\
+DEFINE_EVENT(xfs_xchg_range_class, name,	\
+	TP_PROTO(struct xfs_inode *ip1, const struct xfs_exch_range *fxr, \
+		 struct xfs_inode *ip2, unsigned int xchg_flags), \
+	TP_ARGS(ip1, fxr, ip2, xchg_flags))
+DEFINE_XCHG_RANGE_EVENT(xfs_xchg_range_prep);
+DEFINE_XCHG_RANGE_EVENT(xfs_xchg_range_flush);
+DEFINE_XCHG_RANGE_EVENT(xfs_xchg_range);
+
+TRACE_EVENT(xfs_xchg_range_freshness,
+	TP_PROTO(struct xfs_inode *ip2, const struct xfs_exch_range *fxr),
+	TP_ARGS(ip2, fxr),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ip2_ino)
+		__field(long long, ip2_mtime)
+		__field(long long, ip2_ctime)
+		__field(int, ip2_mtime_nsec)
+		__field(int, ip2_ctime_nsec)
+
+		__field(xfs_ino_t, file2_ino)
+		__field(long long, file2_mtime)
+		__field(long long, file2_ctime)
+		__field(int, file2_mtime_nsec)
+		__field(int, file2_ctime_nsec)
+	),
+	TP_fast_assign(
+		struct timespec64	ts64;
+		struct inode		*inode2 = VFS_I(ip2);
+
+		__entry->dev = inode2->i_sb->s_dev;
+		__entry->ip2_ino = ip2->i_ino;
+
+		ts64 = inode_get_ctime(inode2);
+		__entry->ip2_ctime = ts64.tv_sec;
+		__entry->ip2_ctime_nsec = ts64.tv_nsec;
+
+		ts64 = inode_get_mtime(inode2);
+		__entry->ip2_mtime = ts64.tv_sec;
+		__entry->ip2_mtime_nsec = ts64.tv_nsec;
+
+		__entry->file2_ino = fxr->file2_ino;
+		__entry->file2_mtime = fxr->file2_mtime;
+		__entry->file2_ctime = fxr->file2_ctime;
+		__entry->file2_mtime_nsec = fxr->file2_mtime_nsec;
+		__entry->file2_ctime_nsec = fxr->file2_ctime_nsec;
+	),
+	TP_printk("dev %d:%d "
+		  "ino 0x%llx mtime %lld:%d ctime %lld:%d -> "
+		  "file 0x%llx mtime %lld:%d ctime %lld:%d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ip2_ino,
+		  __entry->ip2_mtime,
+		  __entry->ip2_mtime_nsec,
+		  __entry->ip2_ctime,
+		  __entry->ip2_ctime_nsec,
+		  __entry->file2_ino,
+		  __entry->file2_mtime,
+		  __entry->file2_mtime_nsec,
+		  __entry->file2_ctime,
+		  __entry->file2_ctime_nsec)
+);
+
 /* fsmap traces */
 DECLARE_EVENT_CLASS(xfs_fsmap_class,
 	TP_PROTO(struct xfs_mount *mp, u32 keydev, xfs_agnumber_t agno,
diff --git a/fs/xfs/xfs_xchgrange.c b/fs/xfs/xfs_xchgrange.c
index ebbd7b1fe3983..835e83c90f7f5 100644
--- a/fs/xfs/xfs_xchgrange.c
+++ b/fs/xfs/xfs_xchgrange.c
@@ -12,8 +12,15 @@
 #include "xfs_defer.h"
 #include "xfs_inode.h"
 #include "xfs_trans.h"
+#include "xfs_quota.h"
+#include "xfs_bmap_util.h"
+#include "xfs_reflink.h"
+#include "xfs_trace.h"
 #include "xfs_swapext.h"
 #include "xfs_xchgrange.h"
+#include "xfs_sb.h"
+#include "xfs_icache.h"
+#include "xfs_log.h"
 #include <linux/fsnotify.h>
 
 /*
@@ -320,7 +327,7 @@ __xfs_exch_range(
 	if (ret)
 		return ret;
 
-	ret = -EOPNOTSUPP; /* XXX call out to xfs code */
+	ret = xfs_file_xchg_range(file1, file2, fxr);
 	if (ret)
 		return ret;
 
@@ -347,6 +354,78 @@ xfs_exch_range(
 
 /* XFS-specific parts of XFS_IOC_EXCHANGE_RANGE */
 
+/*
+ * Exchanging ranges as a file operation.  This is the binding between the
+ * VFS-level concepts and the XFS-specific implementation.
+ */
+int
+xfs_file_xchg_range(
+	struct file		*file1,
+	struct file		*file2,
+	struct xfs_exch_range	*fxr)
+{
+	struct inode		*inode1 = file_inode(file1);
+	struct inode		*inode2 = file_inode(file2);
+	struct xfs_inode	*ip1 = XFS_I(inode1);
+	struct xfs_inode	*ip2 = XFS_I(inode2);
+	struct xfs_mount	*mp = ip1->i_mount;
+	unsigned int		priv_flags = 0;
+	bool			use_logging = false;
+	int			error;
+
+	if (xfs_is_shutdown(mp))
+		return -EIO;
+
+	/* Update cmtime if the fd/inode don't forbid it. */
+	if (likely(!(file1->f_mode & FMODE_NOCMTIME) && !IS_NOCMTIME(inode1)))
+		priv_flags |= XFS_XCHG_RANGE_UPD_CMTIME1;
+	if (likely(!(file2->f_mode & FMODE_NOCMTIME) && !IS_NOCMTIME(inode2)))
+		priv_flags |= XFS_XCHG_RANGE_UPD_CMTIME2;
+
+	/* Lock both files against IO */
+	error = xfs_ilock2_io_mmap(ip1, ip2);
+	if (error)
+		goto out_err;
+
+	/* Get permission to use log-assisted file content swaps. */
+	error = xfs_xchg_range_grab_log_assist(mp,
+			!(fxr->flags & XFS_EXCH_RANGE_NONATOMIC),
+			&use_logging);
+	if (error)
+		goto out_unlock;
+	if (use_logging)
+		priv_flags |= XFS_XCHG_RANGE_LOGGED;
+
+	/* Prepare and then exchange file contents. */
+	error = xfs_xchg_range_prep(file1, file2, fxr);
+	if (error)
+		goto out_drop_feat;
+
+	error = xfs_xchg_range(ip1, ip2, fxr, priv_flags);
+	if (error)
+		goto out_drop_feat;
+
+	/*
+	 * Finish the exchange by removing special file privileges like any
+	 * other file write would do.  This may involve turning on support for
+	 * logged xattrs if either file has security capabilities, which means
+	 * xfs_xchg_range_grab_log_assist before xfs_attr_grab_log_assist.
+	 */
+	error = xfs_exch_range_finish(file1, file2);
+	if (error)
+		goto out_drop_feat;
+
+out_drop_feat:
+	if (use_logging)
+		xfs_xchg_range_rele_log_assist(mp);
+out_unlock:
+	xfs_iunlock2_io_mmap(ip1, ip2);
+out_err:
+	if (error)
+		trace_xfs_file_xchg_range_error(ip2, error, _RET_IP_);
+	return error;
+}
+
 /* Lock (and optionally join) two inodes for a file range exchange. */
 void
 xfs_xchg_range_ilock(
@@ -394,3 +473,384 @@ xfs_xchg_range_estimate(
 	xfs_xchg_range_iunlock(req->ip1, req->ip2);
 	return error;
 }
+
+/* Prepare two files to have their data exchanged. */
+int
+xfs_xchg_range_prep(
+	struct file		*file1,
+	struct file		*file2,
+	struct xfs_exch_range	*fxr)
+{
+	struct xfs_inode	*ip1 = XFS_I(file_inode(file1));
+	struct xfs_inode	*ip2 = XFS_I(file_inode(file2));
+	int			error;
+
+	trace_xfs_xchg_range_prep(ip1, fxr, ip2, 0);
+
+	/* Verify both files are either real-time or non-realtime */
+	if (XFS_IS_REALTIME_INODE(ip1) != XFS_IS_REALTIME_INODE(ip2))
+		return -EINVAL;
+
+	/*
+	 * The alignment checks in the VFS helpers cannot deal with allocation
+	 * units that are not powers of 2.  This can happen with the realtime
+	 * volume if the extent size is set.  Note that alignment checks are
+	 * skipped if FULL_FILES is set.
+	 */
+	if (!(fxr->flags & XFS_EXCH_RANGE_FULL_FILES) &&
+	    !is_power_of_2(xfs_inode_alloc_unitsize(ip2)))
+		return -EOPNOTSUPP;
+
+	error = xfs_exch_range_prep(file1, file2, fxr,
+			xfs_inode_alloc_unitsize(ip2));
+	if (error || fxr->length == 0)
+		return error;
+
+	/* Attach dquots to both inodes before changing block maps. */
+	error = xfs_qm_dqattach(ip2);
+	if (error)
+		return error;
+	error = xfs_qm_dqattach(ip1);
+	if (error)
+		return error;
+
+	trace_xfs_xchg_range_flush(ip1, fxr, ip2, 0);
+
+	/* Flush the relevant ranges of both files. */
+	error = xfs_flush_unmap_range(ip2, fxr->file2_offset, fxr->length);
+	if (error)
+		return error;
+	error = xfs_flush_unmap_range(ip1, fxr->file1_offset, fxr->length);
+	if (error)
+		return error;
+
+	/*
+	 * Cancel CoW fork preallocations for the ranges of both files.  The
+	 * prep function should have flushed all the dirty data, so the only
+	 * extents remaining should be speculative.
+	 */
+	if (xfs_inode_has_cow_data(ip1)) {
+		error = xfs_reflink_cancel_cow_range(ip1, fxr->file1_offset,
+				fxr->length, true);
+		if (error)
+			return error;
+	}
+
+	if (xfs_inode_has_cow_data(ip2)) {
+		error = xfs_reflink_cancel_cow_range(ip2, fxr->file2_offset,
+				fxr->length, true);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+#define QRETRY_IP1	(0x1)
+#define QRETRY_IP2	(0x2)
+
+/*
+ * Obtain a quota reservation to make sure we don't hit EDQUOT.  We can skip
+ * this if quota enforcement is disabled or if both inodes' dquots are the
+ * same.  The qretry structure must be initialized to zeroes before the first
+ * call to this function.
+ */
+STATIC int
+xfs_xchg_range_reserve_quota(
+	struct xfs_trans		*tp,
+	const struct xfs_swapext_req	*req,
+	unsigned int			*qretry)
+{
+	int64_t				ddelta, rdelta;
+	int				ip1_error = 0;
+	int				error;
+
+	/*
+	 * Don't bother with a quota reservation if we're not enforcing them
+	 * or the two inodes have the same dquots.
+	 */
+	if (!XFS_IS_QUOTA_ON(tp->t_mountp) || req->ip1 == req->ip2 ||
+	    (req->ip1->i_udquot == req->ip2->i_udquot &&
+	     req->ip1->i_gdquot == req->ip2->i_gdquot &&
+	     req->ip1->i_pdquot == req->ip2->i_pdquot))
+		return 0;
+
+	*qretry = 0;
+
+	/*
+	 * For each file, compute the net gain in the number of regular blocks
+	 * that will be mapped into that file and reserve that much quota.  The
+	 * quota counts must be able to absorb at least that much space.
+	 */
+	ddelta = req->ip2_bcount - req->ip1_bcount;
+	rdelta = req->ip2_rtbcount - req->ip1_rtbcount;
+	if (ddelta > 0 || rdelta > 0) {
+		error = xfs_trans_reserve_quota_nblks(tp, req->ip1,
+				ddelta > 0 ? ddelta : 0,
+				rdelta > 0 ? rdelta : 0,
+				false);
+		if (error == -EDQUOT || error == -ENOSPC) {
+			/*
+			 * Save this error and see what happens if we try to
+			 * reserve quota for ip2.  Then report both.
+			 */
+			*qretry |= QRETRY_IP1;
+			ip1_error = error;
+			error = 0;
+		}
+		if (error)
+			return error;
+	}
+	if (ddelta < 0 || rdelta < 0) {
+		error = xfs_trans_reserve_quota_nblks(tp, req->ip2,
+				ddelta < 0 ? -ddelta : 0,
+				rdelta < 0 ? -rdelta : 0,
+				false);
+		if (error == -EDQUOT || error == -ENOSPC)
+			*qretry |= QRETRY_IP2;
+		if (error)
+			return error;
+	}
+	if (ip1_error)
+		return ip1_error;
+
+	/*
+	 * For each file, forcibly reserve the gross gain in mapped blocks so
+	 * that we don't trip over any quota block reservation assertions.
+	 * We must reserve the gross gain because the quota code subtracts from
+	 * bcount the number of blocks that we unmap; it does not add that
+	 * quantity back to the quota block reservation.
+	 */
+	error = xfs_trans_reserve_quota_nblks(tp, req->ip1, req->ip1_bcount,
+			req->ip1_rtbcount, true);
+	if (error)
+		return error;
+
+	return xfs_trans_reserve_quota_nblks(tp, req->ip2, req->ip2_bcount,
+			req->ip2_rtbcount, true);
+}
+
+/*
+ * Get permission to use log-assisted atomic exchange of file extents.
+ *
+ * Callers must hold the IOLOCK and MMAPLOCK of both files.  They must not be
+ * running any transactions or hold any ILOCKS.  If @use_logging is set after a
+ * successful return, callers must call xfs_xchg_range_rele_log_assist after
+ * the exchange is completed.
+ */
+int
+xfs_xchg_range_grab_log_assist(
+	struct xfs_mount	*mp,
+	bool			force,
+	bool			*use_logging)
+{
+	int			error = 0;
+
+	/*
+	 * As a performance optimization, skip the log force and super write
+	 * if the filesystem featureset already protects the swapext log items.
+	 */
+	if (xfs_swapext_can_use_without_log_assistance(mp)) {
+		*use_logging = true;
+		return 0;
+	}
+
+	/*
+	 * Protect ourselves from an idle log clearing the atomic swapext
+	 * log incompat feature bit.
+	 */
+	xlog_use_incompat_feat(mp->m_log, XLOG_INCOMPAT_FEAT_SWAPEXT);
+	*use_logging = true;
+
+	/*
+	 * If log-assisted swapping is already enabled, the caller can use the
+	 * log assisted swap functions with the log-incompat reference we got.
+	 */
+	if (xfs_sb_version_haslogswapext(&mp->m_sb))
+		return 0;
+
+	/*
+	 * If the caller doesn't /require/ log-assisted swapping, drop the
+	 * incore log-incompat feature protection and exit.  The caller will
+	 * not be able to use log assisted swapping.
+	 */
+	if (!force)
+		goto drop_incompat;
+
+	/*
+	 * Check if the filesystem featureset is new enough to set this log
+	 * incompat feature bit.  Strictly speaking, the minimum requirement is
+	 * a V5 filesystem for the superblock field, but we'll require bigtime
+	 * to avoid having to deal with really old kernels.
+	 */
+	if (!xfs_has_bigtime(mp)) {
+		error = -EOPNOTSUPP;
+		goto drop_incompat;
+	}
+
+	error = xfs_add_incompat_log_feature(mp,
+			XFS_SB_FEAT_INCOMPAT_LOG_SWAPEXT);
+	if (error)
+		goto drop_incompat;
+
+	xfs_warn_mount(mp, XFS_OPSTATE_WARNED_SWAPEXT,
+ "EXPERIMENTAL atomic file range swap feature in use. Use at your own risk!");
+
+	return 0;
+drop_incompat:
+	xlog_drop_incompat_feat(mp->m_log, XLOG_INCOMPAT_FEAT_SWAPEXT);
+	*use_logging = false;
+	return error;
+}
+
+/* Release permission to use log-assisted extent swapping. */
+void
+xfs_xchg_range_rele_log_assist(
+	struct xfs_mount	*mp)
+{
+	if (!xfs_swapext_can_use_without_log_assistance(mp))
+		xlog_drop_incompat_feat(mp->m_log, XLOG_INCOMPAT_FEAT_SWAPEXT);
+}
+
+/* Exchange the contents of two files. */
+int
+xfs_xchg_range(
+	struct xfs_inode		*ip1,
+	struct xfs_inode		*ip2,
+	const struct xfs_exch_range	*fxr,
+	unsigned int			xchg_flags)
+{
+	struct xfs_mount		*mp = ip1->i_mount;
+	struct xfs_swapext_req		req = {
+		.ip1			= ip1,
+		.ip2			= ip2,
+		.whichfork		= XFS_DATA_FORK,
+		.startoff1		= XFS_B_TO_FSBT(mp, fxr->file1_offset),
+		.startoff2		= XFS_B_TO_FSBT(mp, fxr->file2_offset),
+		.blockcount		= XFS_B_TO_FSB(mp, fxr->length),
+	};
+	struct xfs_trans		*tp;
+	unsigned int			qretry;
+	bool				retried = false;
+	int				error;
+
+	trace_xfs_xchg_range(ip1, fxr, ip2, xchg_flags);
+
+	/*
+	 * This function only supports using log intent items (SXI items if
+	 * atomic exchange is required, or BUI items if not) to exchange file
+	 * data.  The legacy whole-fork swap will be ported in a later patch.
+	 */
+	if (!(xchg_flags & XFS_XCHG_RANGE_LOGGED) &&
+	    !xfs_swapext_supports_nonatomic(mp))
+		return -EOPNOTSUPP;
+
+	if (fxr->flags & XFS_EXCH_RANGE_TO_EOF)
+		req.req_flags |= XFS_SWAP_REQ_SET_SIZES;
+	if (fxr->flags & XFS_EXCH_RANGE_FILE1_WRITTEN)
+		req.req_flags |= XFS_SWAP_REQ_INO1_WRITTEN;
+	if (xchg_flags & XFS_XCHG_RANGE_LOGGED)
+		req.req_flags |= XFS_SWAP_REQ_LOGGED;
+
+	error = xfs_xchg_range_estimate(&req);
+	if (error)
+		return error;
+
+retry:
+	/* Allocate the transaction, lock the inodes, and join them. */
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, req.resblks, 0,
+			XFS_TRANS_RES_FDBLKS, &tp);
+	if (error)
+		return error;
+
+	xfs_xchg_range_ilock(tp, ip1, ip2);
+
+	trace_xfs_swap_extent_before(ip2, 0);
+	trace_xfs_swap_extent_before(ip1, 1);
+
+	if (fxr->flags & XFS_EXCH_RANGE_FILE2_FRESH)
+		trace_xfs_xchg_range_freshness(ip2, fxr);
+
+	/*
+	 * Now that we've excluded all other inode metadata changes by taking
+	 * the ILOCK, repeat the freshness check.
+	 */
+	error = xfs_exch_range_check_fresh(VFS_I(ip2), fxr);
+	if (error)
+		goto out_trans_cancel;
+
+	error = xfs_swapext_check_extents(mp, &req);
+	if (error)
+		goto out_trans_cancel;
+
+	/*
+	 * Reserve ourselves some quota if any of them are in enforcing mode.
+	 * In theory we only need enough to satisfy the change in the number
+	 * of blocks between the two ranges being remapped.
+	 */
+	error = xfs_xchg_range_reserve_quota(tp, &req, &qretry);
+	if ((error == -EDQUOT || error == -ENOSPC) && !retried) {
+		xfs_trans_cancel(tp);
+		xfs_xchg_range_iunlock(ip1, ip2);
+		if (qretry & QRETRY_IP1)
+			xfs_blockgc_free_quota(ip1, 0);
+		if (qretry & QRETRY_IP2)
+			xfs_blockgc_free_quota(ip2, 0);
+		retried = true;
+		goto retry;
+	}
+	if (error)
+		goto out_trans_cancel;
+
+	/* If we got this far on a dry run, all parameters are ok. */
+	if (fxr->flags & XFS_EXCH_RANGE_DRY_RUN)
+		goto out_trans_cancel;
+
+	/* Update the mtime and ctime of both files. */
+	if (xchg_flags & XFS_XCHG_RANGE_UPD_CMTIME1)
+		xfs_trans_ichgtime(tp, ip1,
+				XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+	if (xchg_flags & XFS_XCHG_RANGE_UPD_CMTIME2)
+		xfs_trans_ichgtime(tp, ip2,
+				XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+
+	xfs_swapext(tp, &req);
+
+	/*
+	 * Force the log to persist metadata updates if the caller or the
+	 * administrator requires this.  The VFS prep function already flushed
+	 * the relevant parts of the page cache.
+	 */
+	if (xfs_has_wsync(mp) || (fxr->flags & XFS_EXCH_RANGE_FSYNC))
+		xfs_trans_set_sync(tp);
+
+	error = xfs_trans_commit(tp);
+
+	trace_xfs_swap_extent_after(ip2, 0);
+	trace_xfs_swap_extent_after(ip1, 1);
+
+	if (error)
+		goto out_unlock;
+
+	/*
+	 * If the caller wanted us to exchange the contents of two complete
+	 * files of unequal length, exchange the incore sizes now.  This should
+	 * be safe because we flushed both files' page caches, moved all the
+	 * extents, and updated the ondisk sizes.
+	 */
+	if (fxr->flags & XFS_EXCH_RANGE_TO_EOF) {
+		loff_t	temp;
+
+		temp = i_size_read(VFS_I(ip2));
+		i_size_write(VFS_I(ip2), i_size_read(VFS_I(ip1)));
+		i_size_write(VFS_I(ip1), temp);
+	}
+
+out_unlock:
+	xfs_xchg_range_iunlock(ip1, ip2);
+	return error;
+
+out_trans_cancel:
+	xfs_trans_cancel(tp);
+	goto out_unlock;
+}
diff --git a/fs/xfs/xfs_xchgrange.h b/fs/xfs/xfs_xchgrange.h
index 3544ed84e4106..3471182d1402f 100644
--- a/fs/xfs/xfs_xchgrange.h
+++ b/fs/xfs/xfs_xchgrange.h
@@ -15,6 +15,11 @@ int xfs_exch_range_finish(struct file *file1, struct file *file2);
 int xfs_exch_range(struct file *file1, struct file *file2,
 		struct xfs_exch_range *fxr);
 
+/* Binding between the generic VFS and the XFS-specific file exchange */
+
+int xfs_file_xchg_range(struct file *file1, struct file *file2,
+		struct xfs_exch_range *fxr);
+
 /* XFS-specific parts of file exchanges */
 
 struct xfs_swapext_req;
@@ -25,4 +30,27 @@ void xfs_xchg_range_iunlock(struct xfs_inode *ip1, struct xfs_inode *ip2);
 
 int xfs_xchg_range_estimate(struct xfs_swapext_req *req);
 
+int xfs_xchg_range_grab_log_assist(struct xfs_mount *mp, bool force,
+		bool *use_logging);
+void xfs_xchg_range_rele_log_assist(struct xfs_mount *mp);
+
+/* Caller has permission to use log intent items for the exchange operation. */
+#define XFS_XCHG_RANGE_LOGGED		(1U << 0)
+
+/* Update ip1's change and mod time. */
+#define XFS_XCHG_RANGE_UPD_CMTIME1	(1U << 1)
+
+/* Update ip2's change and mod time. */
+#define XFS_XCHG_RANGE_UPD_CMTIME2	(1U << 2)
+
+#define XCHG_RANGE_FLAGS_STRS \
+	{ XFS_XCHG_RANGE_LOGGED,		"LOGGED" }, \
+	{ XFS_XCHG_RANGE_UPD_CMTIME1,		"UPD_CMTIME1" }, \
+	{ XFS_XCHG_RANGE_UPD_CMTIME2,		"UPD_CMTIME2" }
+
+int xfs_xchg_range(struct xfs_inode *ip1, struct xfs_inode *ip2,
+		const struct xfs_exch_range *fxr, unsigned int xchg_flags);
+int xfs_xchg_range_prep(struct file *file1, struct file *file2,
+		struct xfs_exch_range *fxr);
+
 #endif /* __XFS_XCHGRANGE_H__ */

[PATCH 14/25] xfs: add error injection to test swapext recovery

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add an errortag so that we can test recovery of swapext log items.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_errortag.h |    4 +++-
 fs/xfs/libxfs/xfs_swapext.c  |    3 +++
 fs/xfs/xfs_error.c           |    3 +++
 3 files changed, 9 insertions(+), 1 deletion(-)


diff --git a/fs/xfs/libxfs/xfs_errortag.h b/fs/xfs/libxfs/xfs_errortag.h
index 01a9e86b30379..263d62a8d70f8 100644
--- a/fs/xfs/libxfs/xfs_errortag.h
+++ b/fs/xfs/libxfs/xfs_errortag.h
@@ -63,7 +63,8 @@
 #define XFS_ERRTAG_ATTR_LEAF_TO_NODE			41
 #define XFS_ERRTAG_WB_DELAY_MS				42
 #define XFS_ERRTAG_WRITE_DELAY_MS			43
-#define XFS_ERRTAG_MAX					44
+#define XFS_ERRTAG_SWAPEXT_FINISH_ONE			44
+#define XFS_ERRTAG_MAX					45
 
 /*
  * Random factors for above tags, 1 means always, 2 means 1/2 time, etc.
@@ -111,5 +112,6 @@
 #define XFS_RANDOM_ATTR_LEAF_TO_NODE			1
 #define XFS_RANDOM_WB_DELAY_MS				3000
 #define XFS_RANDOM_WRITE_DELAY_MS			3000
+#define XFS_RANDOM_SWAPEXT_FINISH_ONE			1
 
 #endif /* __XFS_ERRORTAG_H_ */
diff --git a/fs/xfs/libxfs/xfs_swapext.c b/fs/xfs/libxfs/xfs_swapext.c
index f5dacd6f1ecb2..7e72b43f7b782 100644
--- a/fs/xfs/libxfs/xfs_swapext.c
+++ b/fs/xfs/libxfs/xfs_swapext.c
@@ -436,6 +436,9 @@ xfs_swapext_finish_one(
 			return error;
 	}
 
+	if (XFS_TEST_ERROR(false, tp->t_mountp, XFS_ERRTAG_SWAPEXT_FINISH_ONE))
+		return -EIO;
+
 	/* If we still have work to do, ask for a new transaction. */
 	if (sxi_has_more_swap_work(sxi) || sxi_has_postop_work(sxi)) {
 		trace_xfs_swapext_defer(tp->t_mountp, sxi);
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index b2cbbba3e15a5..c3792ab41c271 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -62,6 +62,7 @@ static unsigned int xfs_errortag_random_default[] = {
 	XFS_RANDOM_ATTR_LEAF_TO_NODE,
 	XFS_RANDOM_WB_DELAY_MS,
 	XFS_RANDOM_WRITE_DELAY_MS,
+	XFS_RANDOM_SWAPEXT_FINISH_ONE,
 };
 
 struct xfs_errortag_attr {
@@ -179,6 +180,7 @@ XFS_ERRORTAG_ATTR_RW(da_leaf_split,	XFS_ERRTAG_DA_LEAF_SPLIT);
 XFS_ERRORTAG_ATTR_RW(attr_leaf_to_node,	XFS_ERRTAG_ATTR_LEAF_TO_NODE);
 XFS_ERRORTAG_ATTR_RW(wb_delay_ms,	XFS_ERRTAG_WB_DELAY_MS);
 XFS_ERRORTAG_ATTR_RW(write_delay_ms,	XFS_ERRTAG_WRITE_DELAY_MS);
+XFS_ERRORTAG_ATTR_RW(swapext_finish_one, XFS_ERRTAG_SWAPEXT_FINISH_ONE);
 
 static struct attribute *xfs_errortag_attrs[] = {
 	XFS_ERRORTAG_ATTR_LIST(noerror),
@@ -224,6 +226,7 @@ static struct attribute *xfs_errortag_attrs[] = {
 	XFS_ERRORTAG_ATTR_LIST(attr_leaf_to_node),
 	XFS_ERRORTAG_ATTR_LIST(wb_delay_ms),
 	XFS_ERRORTAG_ATTR_LIST(write_delay_ms),
+	XFS_ERRORTAG_ATTR_LIST(swapext_finish_one),
 	NULL,
 };
 ATTRIBUTE_GROUPS(xfs_errortag);

[PATCH 15/25] xfs: port xfs_swap_extents_rmap to our new code

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

The inner loop of xfs_swap_extents_rmap does the same work as
xfs_swapext_finish_one, so adapt it to use that.  Doing so has the side
benefit that the older code path no longer wastes its time remapping
shared extents.

This forms the basis of the non-atomic swaprange implementation.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_bmap_util.c |  151 +++++-------------------------------------------
 fs/xfs/xfs_trace.h     |    5 --
 2 files changed, 16 insertions(+), 140 deletions(-)


diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 87ac9777c1eaf..8ca681d78bbcb 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1354,138 +1354,6 @@ xfs_swap_extent_flush(
 	return 0;
 }
 
-/*
- * Move extents from one file to another, when rmap is enabled.
- */
-STATIC int
-xfs_swap_extent_rmap(
-	struct xfs_trans		**tpp,
-	struct xfs_inode		*ip,
-	struct xfs_inode		*tip)
-{
-	struct xfs_trans		*tp = *tpp;
-	struct xfs_bmbt_irec		irec;
-	struct xfs_bmbt_irec		uirec;
-	struct xfs_bmbt_irec		tirec;
-	xfs_fileoff_t			offset_fsb;
-	xfs_fileoff_t			end_fsb;
-	xfs_filblks_t			count_fsb;
-	int				error;
-	xfs_filblks_t			ilen;
-	xfs_filblks_t			rlen;
-	int				nimaps;
-	uint64_t			tip_flags2;
-
-	/*
-	 * If the source file has shared blocks, we must flag the donor
-	 * file as having shared blocks so that we get the shared-block
-	 * rmap functions when we go to fix up the rmaps.  The flags
-	 * will be switch for reals later.
-	 */
-	tip_flags2 = tip->i_diflags2;
-	if (ip->i_diflags2 & XFS_DIFLAG2_REFLINK)
-		tip->i_diflags2 |= XFS_DIFLAG2_REFLINK;
-
-	offset_fsb = 0;
-	end_fsb = XFS_B_TO_FSB(ip->i_mount, i_size_read(VFS_I(ip)));
-	count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb);
-
-	while (count_fsb) {
-		/* Read extent from the donor file */
-		nimaps = 1;
-		error = xfs_bmapi_read(tip, offset_fsb, count_fsb, &tirec,
-				&nimaps, 0);
-		if (error)
-			goto out;
-		ASSERT(nimaps == 1);
-		ASSERT(tirec.br_startblock != DELAYSTARTBLOCK);
-
-		trace_xfs_swap_extent_rmap_remap(tip, &tirec);
-		ilen = tirec.br_blockcount;
-
-		/* Unmap the old blocks in the source file. */
-		while (tirec.br_blockcount) {
-			ASSERT(tp->t_highest_agno == NULLAGNUMBER);
-			trace_xfs_swap_extent_rmap_remap_piece(tip, &tirec);
-
-			/* Read extent from the source file */
-			nimaps = 1;
-			error = xfs_bmapi_read(ip, tirec.br_startoff,
-					tirec.br_blockcount, &irec,
-					&nimaps, 0);
-			if (error)
-				goto out;
-			ASSERT(nimaps == 1);
-			ASSERT(tirec.br_startoff == irec.br_startoff);
-			trace_xfs_swap_extent_rmap_remap_piece(ip, &irec);
-
-			/* Trim the extent. */
-			uirec = tirec;
-			uirec.br_blockcount = rlen = min_t(xfs_filblks_t,
-					tirec.br_blockcount,
-					irec.br_blockcount);
-			trace_xfs_swap_extent_rmap_remap_piece(tip, &uirec);
-
-			if (xfs_bmap_is_real_extent(&uirec)) {
-				error = xfs_iext_count_may_overflow(ip,
-						XFS_DATA_FORK,
-						XFS_IEXT_SWAP_RMAP_CNT);
-				if (error == -EFBIG)
-					error = xfs_iext_count_upgrade(tp, ip,
-							XFS_IEXT_SWAP_RMAP_CNT);
-				if (error)
-					goto out;
-			}
-
-			if (xfs_bmap_is_real_extent(&irec)) {
-				error = xfs_iext_count_may_overflow(tip,
-						XFS_DATA_FORK,
-						XFS_IEXT_SWAP_RMAP_CNT);
-				if (error == -EFBIG)
-					error = xfs_iext_count_upgrade(tp, ip,
-							XFS_IEXT_SWAP_RMAP_CNT);
-				if (error)
-					goto out;
-			}
-
-			/* Remove the mapping from the donor file. */
-			xfs_bmap_unmap_extent(tp, tip, XFS_DATA_FORK, &uirec);
-
-			/* Remove the mapping from the source file. */
-			xfs_bmap_unmap_extent(tp, ip, XFS_DATA_FORK, &irec);
-
-			/* Map the donor file's blocks into the source file. */
-			xfs_bmap_map_extent(tp, ip, XFS_DATA_FORK, &uirec);
-
-			/* Map the source file's blocks into the donor file. */
-			xfs_bmap_map_extent(tp, tip, XFS_DATA_FORK, &irec);
-
-			error = xfs_defer_finish(tpp);
-			tp = *tpp;
-			if (error)
-				goto out;
-
-			tirec.br_startoff += rlen;
-			if (tirec.br_startblock != HOLESTARTBLOCK &&
-			    tirec.br_startblock != DELAYSTARTBLOCK)
-				tirec.br_startblock += rlen;
-			tirec.br_blockcount -= rlen;
-		}
-
-		/* Roll on... */
-		count_fsb -= ilen;
-		offset_fsb += ilen;
-	}
-
-	tip->i_diflags2 = tip_flags2;
-	return 0;
-
-out:
-	trace_xfs_swap_extent_rmap_error(ip, error, _RET_IP_);
-	tip->i_diflags2 = tip_flags2;
-	return error;
-}
-
 /* Swap the extents of two files by swapping data forks. */
 STATIC int
 xfs_swap_extent_forks(
@@ -1772,13 +1640,24 @@ xfs_swap_extents(
 	src_log_flags = XFS_ILOG_CORE;
 	target_log_flags = XFS_ILOG_CORE;
 
-	if (xfs_has_rmapbt(mp))
-		error = xfs_swap_extent_rmap(&tp, ip, tip);
-	else
+	if (xfs_has_rmapbt(mp)) {
+		struct xfs_swapext_req	req = {
+			.ip1		= tip,
+			.ip2		= ip,
+			.whichfork	= XFS_DATA_FORK,
+			.blockcount	= XFS_B_TO_FSB(ip->i_mount,
+						       i_size_read(VFS_I(ip))),
+		};
+
+		xfs_swapext(tp, &req);
+		error = xfs_defer_finish(&tp);
+	} else
 		error = xfs_swap_extent_forks(tp, ip, tip, &src_log_flags,
 				&target_log_flags);
-	if (error)
+	if (error) {
+		trace_xfs_swap_extent_error(ip, error, _THIS_IP_);
 		goto out_trans_cancel;
+	}
 
 	/* Do we have to swap reflink flags? */
 	if ((ip->i_diflags2 & XFS_DIFLAG2_REFLINK) ^
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 53a6122d307ff..47c30d8093289 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -3746,13 +3746,10 @@ DEFINE_INODE_ERROR_EVENT(xfs_reflink_end_cow_error);
 
 DEFINE_INODE_IREC_EVENT(xfs_reflink_cancel_cow);
 
-/* rmap swapext tracepoints */
-DEFINE_INODE_IREC_EVENT(xfs_swap_extent_rmap_remap);
-DEFINE_INODE_IREC_EVENT(xfs_swap_extent_rmap_remap_piece);
-DEFINE_INODE_ERROR_EVENT(xfs_swap_extent_rmap_error);
 
 /* swapext tracepoints */
 DEFINE_INODE_ERROR_EVENT(xfs_file_xchg_range_error);
+DEFINE_INODE_ERROR_EVENT(xfs_swap_extent_error);
 DEFINE_INODE_IREC_EVENT(xfs_swapext_extent1_skip);
 DEFINE_INODE_IREC_EVENT(xfs_swapext_extent1);
 DEFINE_INODE_IREC_EVENT(xfs_swapext_extent2);

[PATCH 16/25] xfs: consolidate all of the xfs_swap_extent_forks code

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Now that we've moved the old swapext code to use the new log-assisted
extent swap code for rmap filesystems, let's start porting the old
implementation to the new ioctl interface so that later we can port the
old interface to the new interface.

Consolidate the reflink flag swap code and the the bmbt owner change
scan code in xfs_swap_extent_forks, since both interfaces are going to
need that.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_bmap_util.c |  220 ++++++++++++++++++++++++------------------------
 1 file changed, 108 insertions(+), 112 deletions(-)


diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 8ca681d78bbcb..0056bee7ca1d6 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1354,19 +1354,61 @@ xfs_swap_extent_flush(
 	return 0;
 }
 
+/*
+ * Fix up the owners of the bmbt blocks to refer to the current inode. The
+ * change owner scan attempts to order all modified buffers in the current
+ * transaction. In the event of ordered buffer failure, the offending buffer is
+ * physically logged as a fallback and the scan returns -EAGAIN. We must roll
+ * the transaction in this case to replenish the fallback log reservation and
+ * restart the scan. This process repeats until the scan completes.
+ */
+static int
+xfs_swap_change_owner(
+	struct xfs_trans	**tpp,
+	struct xfs_inode	*ip,
+	struct xfs_inode	*tmpip)
+{
+	int			error;
+	struct xfs_trans	*tp = *tpp;
+
+	do {
+		error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK, ip->i_ino,
+					      NULL);
+		/* success or fatal error */
+		if (error != -EAGAIN)
+			break;
+
+		error = xfs_trans_roll(tpp);
+		if (error)
+			break;
+		tp = *tpp;
+
+		/*
+		 * Redirty both inodes so they can relog and keep the log tail
+		 * moving forward.
+		 */
+		xfs_trans_ijoin(tp, ip, 0);
+		xfs_trans_ijoin(tp, tmpip, 0);
+		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+		xfs_trans_log_inode(tp, tmpip, XFS_ILOG_CORE);
+	} while (true);
+
+	return error;
+}
+
 /* Swap the extents of two files by swapping data forks. */
 STATIC int
 xfs_swap_extent_forks(
-	struct xfs_trans	*tp,
+	struct xfs_trans	**tpp,
 	struct xfs_inode	*ip,
-	struct xfs_inode	*tip,
-	int			*src_log_flags,
-	int			*target_log_flags)
+	struct xfs_inode	*tip)
 {
 	xfs_filblks_t		aforkblks = 0;
 	xfs_filblks_t		taforkblks = 0;
 	xfs_extnum_t		junk;
 	uint64_t		tmp;
+	int			src_log_flags = XFS_ILOG_CORE;
+	int			target_log_flags = XFS_ILOG_CORE;
 	int			error;
 
 	/*
@@ -1374,14 +1416,14 @@ xfs_swap_extent_forks(
 	 */
 	if (xfs_inode_has_attr_fork(ip) && ip->i_af.if_nextents > 0 &&
 	    ip->i_af.if_format != XFS_DINODE_FMT_LOCAL) {
-		error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK, &junk,
+		error = xfs_bmap_count_blocks(*tpp, ip, XFS_ATTR_FORK, &junk,
 				&aforkblks);
 		if (error)
 			return error;
 	}
 	if (xfs_inode_has_attr_fork(tip) && tip->i_af.if_nextents > 0 &&
 	    tip->i_af.if_format != XFS_DINODE_FMT_LOCAL) {
-		error = xfs_bmap_count_blocks(tp, tip, XFS_ATTR_FORK, &junk,
+		error = xfs_bmap_count_blocks(*tpp, tip, XFS_ATTR_FORK, &junk,
 				&taforkblks);
 		if (error)
 			return error;
@@ -1396,9 +1438,9 @@ xfs_swap_extent_forks(
 	 */
 	if (xfs_has_v3inodes(ip->i_mount)) {
 		if (ip->i_df.if_format == XFS_DINODE_FMT_BTREE)
-			(*target_log_flags) |= XFS_ILOG_DOWNER;
+			target_log_flags |= XFS_ILOG_DOWNER;
 		if (tip->i_df.if_format == XFS_DINODE_FMT_BTREE)
-			(*src_log_flags) |= XFS_ILOG_DOWNER;
+			src_log_flags |= XFS_ILOG_DOWNER;
 	}
 
 	/*
@@ -1428,71 +1470,80 @@ xfs_swap_extent_forks(
 
 	switch (ip->i_df.if_format) {
 	case XFS_DINODE_FMT_EXTENTS:
-		(*src_log_flags) |= XFS_ILOG_DEXT;
+		src_log_flags |= XFS_ILOG_DEXT;
 		break;
 	case XFS_DINODE_FMT_BTREE:
 		ASSERT(!xfs_has_v3inodes(ip->i_mount) ||
-		       (*src_log_flags & XFS_ILOG_DOWNER));
-		(*src_log_flags) |= XFS_ILOG_DBROOT;
+		       (src_log_flags & XFS_ILOG_DOWNER));
+		src_log_flags |= XFS_ILOG_DBROOT;
 		break;
 	}
 
 	switch (tip->i_df.if_format) {
 	case XFS_DINODE_FMT_EXTENTS:
-		(*target_log_flags) |= XFS_ILOG_DEXT;
+		target_log_flags |= XFS_ILOG_DEXT;
 		break;
 	case XFS_DINODE_FMT_BTREE:
-		(*target_log_flags) |= XFS_ILOG_DBROOT;
+		target_log_flags |= XFS_ILOG_DBROOT;
 		ASSERT(!xfs_has_v3inodes(ip->i_mount) ||
-		       (*target_log_flags & XFS_ILOG_DOWNER));
+		       (target_log_flags & XFS_ILOG_DOWNER));
 		break;
 	}
 
+	/* Do we have to swap reflink flags? */
+	if ((ip->i_diflags2 & XFS_DIFLAG2_REFLINK) ^
+	    (tip->i_diflags2 & XFS_DIFLAG2_REFLINK)) {
+		uint64_t	f;
+
+		f = ip->i_diflags2 & XFS_DIFLAG2_REFLINK;
+		ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+		ip->i_diflags2 |= tip->i_diflags2 & XFS_DIFLAG2_REFLINK;
+		tip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+		tip->i_diflags2 |= f & XFS_DIFLAG2_REFLINK;
+	}
+
+	/* Swap the cow forks. */
+	if (xfs_has_reflink(ip->i_mount)) {
+		ASSERT(!ip->i_cowfp ||
+		       ip->i_cowfp->if_format == XFS_DINODE_FMT_EXTENTS);
+		ASSERT(!tip->i_cowfp ||
+		       tip->i_cowfp->if_format == XFS_DINODE_FMT_EXTENTS);
+
+		swap(ip->i_cowfp, tip->i_cowfp);
+
+		if (ip->i_cowfp && ip->i_cowfp->if_bytes)
+			xfs_inode_set_cowblocks_tag(ip);
+		else
+			xfs_inode_clear_cowblocks_tag(ip);
+		if (tip->i_cowfp && tip->i_cowfp->if_bytes)
+			xfs_inode_set_cowblocks_tag(tip);
+		else
+			xfs_inode_clear_cowblocks_tag(tip);
+	}
+
+	xfs_trans_log_inode(*tpp, ip,  src_log_flags);
+	xfs_trans_log_inode(*tpp, tip, target_log_flags);
+
+	/*
+	 * The extent forks have been swapped, but crc=1,rmapbt=0 filesystems
+	 * have inode number owner values in the bmbt blocks that still refer to
+	 * the old inode. Scan each bmbt to fix up the owner values with the
+	 * inode number of the current inode.
+	 */
+	if (src_log_flags & XFS_ILOG_DOWNER) {
+		error = xfs_swap_change_owner(tpp, ip, tip);
+		if (error)
+			return error;
+	}
+	if (target_log_flags & XFS_ILOG_DOWNER) {
+		error = xfs_swap_change_owner(tpp, tip, ip);
+		if (error)
+			return error;
+	}
+
 	return 0;
 }
 
-/*
- * Fix up the owners of the bmbt blocks to refer to the current inode. The
- * change owner scan attempts to order all modified buffers in the current
- * transaction. In the event of ordered buffer failure, the offending buffer is
- * physically logged as a fallback and the scan returns -EAGAIN. We must roll
- * the transaction in this case to replenish the fallback log reservation and
- * restart the scan. This process repeats until the scan completes.
- */
-static int
-xfs_swap_change_owner(
-	struct xfs_trans	**tpp,
-	struct xfs_inode	*ip,
-	struct xfs_inode	*tmpip)
-{
-	int			error;
-	struct xfs_trans	*tp = *tpp;
-
-	do {
-		error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK, ip->i_ino,
-					      NULL);
-		/* success or fatal error */
-		if (error != -EAGAIN)
-			break;
-
-		error = xfs_trans_roll(tpp);
-		if (error)
-			break;
-		tp = *tpp;
-
-		/*
-		 * Redirty both inodes so they can relog and keep the log tail
-		 * moving forward.
-		 */
-		xfs_trans_ijoin(tp, ip, 0);
-		xfs_trans_ijoin(tp, tmpip, 0);
-		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-		xfs_trans_log_inode(tp, tmpip, XFS_ILOG_CORE);
-	} while (true);
-
-	return error;
-}
-
 int
 xfs_swap_extents(
 	struct xfs_inode	*ip,	/* target inode */
@@ -1502,9 +1553,7 @@ xfs_swap_extents(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
 	struct xfs_bstat	*sbp = &sxp->sx_stat;
-	int			src_log_flags, target_log_flags;
 	int			error = 0;
-	uint64_t		f;
 	int			resblks = 0;
 	unsigned int		flags = 0;
 	struct timespec64	ctime, mtime;
@@ -1637,9 +1686,6 @@ xfs_swap_extents(
 	 * recovery is going to see the fork as owned by the swapped inode,
 	 * not the pre-swapped inodes.
 	 */
-	src_log_flags = XFS_ILOG_CORE;
-	target_log_flags = XFS_ILOG_CORE;
-
 	if (xfs_has_rmapbt(mp)) {
 		struct xfs_swapext_req	req = {
 			.ip1		= tip,
@@ -1652,62 +1698,12 @@ xfs_swap_extents(
 		xfs_swapext(tp, &req);
 		error = xfs_defer_finish(&tp);
 	} else
-		error = xfs_swap_extent_forks(tp, ip, tip, &src_log_flags,
-				&target_log_flags);
+		error = xfs_swap_extent_forks(&tp, ip, tip);
 	if (error) {
 		trace_xfs_swap_extent_error(ip, error, _THIS_IP_);
 		goto out_trans_cancel;
 	}
 
-	/* Do we have to swap reflink flags? */
-	if ((ip->i_diflags2 & XFS_DIFLAG2_REFLINK) ^
-	    (tip->i_diflags2 & XFS_DIFLAG2_REFLINK)) {
-		f = ip->i_diflags2 & XFS_DIFLAG2_REFLINK;
-		ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
-		ip->i_diflags2 |= tip->i_diflags2 & XFS_DIFLAG2_REFLINK;
-		tip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
-		tip->i_diflags2 |= f & XFS_DIFLAG2_REFLINK;
-	}
-
-	/* Swap the cow forks. */
-	if (xfs_has_reflink(mp)) {
-		ASSERT(!ip->i_cowfp ||
-		       ip->i_cowfp->if_format == XFS_DINODE_FMT_EXTENTS);
-		ASSERT(!tip->i_cowfp ||
-		       tip->i_cowfp->if_format == XFS_DINODE_FMT_EXTENTS);
-
-		swap(ip->i_cowfp, tip->i_cowfp);
-
-		if (ip->i_cowfp && ip->i_cowfp->if_bytes)
-			xfs_inode_set_cowblocks_tag(ip);
-		else
-			xfs_inode_clear_cowblocks_tag(ip);
-		if (tip->i_cowfp && tip->i_cowfp->if_bytes)
-			xfs_inode_set_cowblocks_tag(tip);
-		else
-			xfs_inode_clear_cowblocks_tag(tip);
-	}
-
-	xfs_trans_log_inode(tp, ip,  src_log_flags);
-	xfs_trans_log_inode(tp, tip, target_log_flags);
-
-	/*
-	 * The extent forks have been swapped, but crc=1,rmapbt=0 filesystems
-	 * have inode number owner values in the bmbt blocks that still refer to
-	 * the old inode. Scan each bmbt to fix up the owner values with the
-	 * inode number of the current inode.
-	 */
-	if (src_log_flags & XFS_ILOG_DOWNER) {
-		error = xfs_swap_change_owner(&tp, ip, tip);
-		if (error)
-			goto out_trans_cancel;
-	}
-	if (target_log_flags & XFS_ILOG_DOWNER) {
-		error = xfs_swap_change_owner(&tp, tip, ip);
-		if (error)
-			goto out_trans_cancel;
-	}
-
 	/*
 	 * If this is a synchronous mount, make sure that the
 	 * transaction goes to disk before returning to the user.

[PATCH 17/25] xfs: port xfs_swap_extent_forks to use xfs_swapext_req

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Port the old extent fork swapping function to take a xfs_swapext_req as
input, which aligns it with the new fiexchange interface.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_bmap_util.c |   21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)


diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 0056bee7ca1d6..c6d8d061c998b 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1400,9 +1400,10 @@ xfs_swap_change_owner(
 STATIC int
 xfs_swap_extent_forks(
 	struct xfs_trans	**tpp,
-	struct xfs_inode	*ip,
-	struct xfs_inode	*tip)
+	struct xfs_swapext_req	*req)
 {
+	struct xfs_inode	*ip = req->ip2;
+	struct xfs_inode	*tip = req->ip1;
 	xfs_filblks_t		aforkblks = 0;
 	xfs_filblks_t		taforkblks = 0;
 	xfs_extnum_t		junk;
@@ -1550,6 +1551,11 @@ xfs_swap_extents(
 	struct xfs_inode	*tip,	/* tmp inode */
 	struct xfs_swapext	*sxp)
 {
+	struct xfs_swapext_req	req = {
+		.ip1		= tip,
+		.ip2		= ip,
+		.whichfork	= XFS_DATA_FORK,
+	};
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
 	struct xfs_bstat	*sbp = &sxp->sx_stat;
@@ -1686,19 +1692,12 @@ xfs_swap_extents(
 	 * recovery is going to see the fork as owned by the swapped inode,
 	 * not the pre-swapped inodes.
 	 */
+	req.blockcount = XFS_B_TO_FSB(ip->i_mount, i_size_read(VFS_I(ip)));
 	if (xfs_has_rmapbt(mp)) {
-		struct xfs_swapext_req	req = {
-			.ip1		= tip,
-			.ip2		= ip,
-			.whichfork	= XFS_DATA_FORK,
-			.blockcount	= XFS_B_TO_FSB(ip->i_mount,
-						       i_size_read(VFS_I(ip))),
-		};
-
 		xfs_swapext(tp, &req);
 		error = xfs_defer_finish(&tp);
 	} else
-		error = xfs_swap_extent_forks(&tp, ip, tip);
+		error = xfs_swap_extent_forks(&tp, &req);
 	if (error) {
 		trace_xfs_swap_extent_error(ip, error, _THIS_IP_);
 		goto out_trans_cancel;

[PATCH 18/25] xfs: allow xfs_swap_range to use older extent swap algorithms

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If userspace permits non-atomic swap operations, use the older code
paths to implement the same functionality.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_bmap_util.c |    4 +-
 fs/xfs/xfs_bmap_util.h |    4 ++
 fs/xfs/xfs_xchgrange.c |  123 ++++++++++++++++++++++++++++++++++++++++++++----
 3 files changed, 118 insertions(+), 13 deletions(-)


diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index c6d8d061c998b..405d02e71ab65 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1255,7 +1255,7 @@ xfs_insert_file_space(
  * reject and log the attempt. basically we are putting the responsibility on
  * userspace to get this right.
  */
-static int
+int
 xfs_swap_extents_check_format(
 	struct xfs_inode	*ip,	/* target inode */
 	struct xfs_inode	*tip)	/* tmp inode */
@@ -1397,7 +1397,7 @@ xfs_swap_change_owner(
 }
 
 /* Swap the extents of two files by swapping data forks. */
-STATIC int
+int
 xfs_swap_extent_forks(
 	struct xfs_trans	**tpp,
 	struct xfs_swapext_req	*req)
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 6888078f5c31e..39c71da08403c 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -69,6 +69,10 @@ int	xfs_free_eofblocks(struct xfs_inode *ip);
 int	xfs_swap_extents(struct xfs_inode *ip, struct xfs_inode *tip,
 			 struct xfs_swapext *sx);
 
+struct xfs_swapext_req;
+int xfs_swap_extent_forks(struct xfs_trans **tpp, struct xfs_swapext_req *req);
+int xfs_swap_extents_check_format(struct xfs_inode *ip, struct xfs_inode *tip);
+
 xfs_daddr_t xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb);
 
 xfs_extnum_t xfs_bmap_count_leaves(struct xfs_ifork *ifp, xfs_filblks_t *count);
diff --git a/fs/xfs/xfs_xchgrange.c b/fs/xfs/xfs_xchgrange.c
index 835e83c90f7f5..328217551c1e8 100644
--- a/fs/xfs/xfs_xchgrange.c
+++ b/fs/xfs/xfs_xchgrange.c
@@ -712,6 +712,65 @@ xfs_xchg_range_rele_log_assist(
 		xlog_drop_incompat_feat(mp->m_log, XLOG_INCOMPAT_FEAT_SWAPEXT);
 }
 
+/*
+ * Can we use xfs_swapext() to perform the exchange?
+ *
+ * The swapext state tracking mechanism uses deferred bmap log intent (BUI)
+ * items to swap extents between file forks, and it /can/ track the overall
+ * operation status over a file range using swapext log intent (SXI) items.
+ */
+static inline bool
+xfs_xchg_use_swapext(
+	struct xfs_mount	*mp,
+	unsigned int		xchg_flags)
+{
+	/*
+	 * If the caller got permission from the log to use SXI items, we will
+	 * use xfs_swapext with both log items.
+	 */
+	if (xchg_flags & XFS_XCHG_RANGE_LOGGED)
+		return true;
+
+	/*
+	 * If the caller didn't get permission to use SXI items, then userspace
+	 * must have allowed non-atomic swap mode.  Use the state tracking in
+	 * xfs_swapext to log BUI log items if the fs supports rmap or reflink.
+	 */
+	return xfs_swapext_supports_nonatomic(mp);
+}
+
+/*
+ * Can we use the old data fork swapping to perform the exchange?
+ *
+ * Userspace must be asking for a full swap of two files with the same file
+ * size and cannot require atomic mode.
+ */
+static inline bool
+xfs_xchg_use_forkswap(
+	const struct xfs_exch_range	*fxr,
+	struct xfs_inode		*ip1,
+	struct xfs_inode		*ip2)
+{
+	if (!(fxr->flags & XFS_EXCH_RANGE_NONATOMIC))
+		return false;
+	if (!(fxr->flags & XFS_EXCH_RANGE_FULL_FILES))
+		return false;
+	if (fxr->flags & XFS_EXCH_RANGE_TO_EOF)
+		return false;
+	if (fxr->file1_offset != 0 || fxr->file2_offset != 0)
+		return false;
+	if (fxr->length != ip1->i_disk_size)
+		return false;
+	if (fxr->length != ip2->i_disk_size)
+		return false;
+	return true;
+}
+
+enum xchg_strategy {
+	SWAPEXT		= 1,	/* xfs_swapext() */
+	FORKSWAP	= 2,	/* exchange forks */
+};
+
 /* Exchange the contents of two files. */
 int
 xfs_xchg_range(
@@ -731,20 +790,13 @@ xfs_xchg_range(
 	};
 	struct xfs_trans		*tp;
 	unsigned int			qretry;
+	unsigned int			flags = 0;
 	bool				retried = false;
+	enum xchg_strategy		strategy;
 	int				error;
 
 	trace_xfs_xchg_range(ip1, fxr, ip2, xchg_flags);
 
-	/*
-	 * This function only supports using log intent items (SXI items if
-	 * atomic exchange is required, or BUI items if not) to exchange file
-	 * data.  The legacy whole-fork swap will be ported in a later patch.
-	 */
-	if (!(xchg_flags & XFS_XCHG_RANGE_LOGGED) &&
-	    !xfs_swapext_supports_nonatomic(mp))
-		return -EOPNOTSUPP;
-
 	if (fxr->flags & XFS_EXCH_RANGE_TO_EOF)
 		req.req_flags |= XFS_SWAP_REQ_SET_SIZES;
 	if (fxr->flags & XFS_EXCH_RANGE_FILE1_WRITTEN)
@@ -756,10 +808,25 @@ xfs_xchg_range(
 	if (error)
 		return error;
 
+	/*
+	 * We haven't decided which exchange strategy we want to use yet, but
+	 * here we must choose if we want freed blocks during the swap to be
+	 * added to the transaction block reservation (RES_FDBLKS) or freed
+	 * into the global fdblocks.  The legacy fork swap mechanism doesn't
+	 * free any blocks, so it doesn't require it.  It is also the only
+	 * option that works for older filesystems.
+	 *
+	 * The bmap log intent items that were added with rmap and reflink can
+	 * change the bmbt shape, so the intent-based swap strategies require
+	 * us to set RES_FDBLKS.
+	 */
+	if (xfs_has_lazysbcount(mp))
+		flags |= XFS_TRANS_RES_FDBLKS;
+
 retry:
 	/* Allocate the transaction, lock the inodes, and join them. */
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, req.resblks, 0,
-			XFS_TRANS_RES_FDBLKS, &tp);
+			flags, &tp);
 	if (error)
 		return error;
 
@@ -802,6 +869,30 @@ xfs_xchg_range(
 	if (error)
 		goto out_trans_cancel;
 
+	if (xfs_xchg_use_swapext(mp, xchg_flags)) {
+		/* Exchange the file contents with our fancy state tracking. */
+		strategy = SWAPEXT;
+	} else if (xfs_xchg_use_forkswap(fxr, ip1, ip2)) {
+		/*
+		 * Exchange the file contents by using the old bmap fork
+		 * exchange code, if we're a defrag tool doing a full file
+		 * swap.
+		 */
+		strategy = FORKSWAP;
+
+		error = xfs_swap_extents_check_format(ip2, ip1);
+		if (error) {
+			xfs_notice(mp,
+		"%s: inode 0x%llx format is incompatible for exchanging.",
+					__func__, ip2->i_ino);
+			goto out_trans_cancel;
+		}
+	} else {
+		/* We cannot exchange the file contents. */
+		error = -EOPNOTSUPP;
+		goto out_trans_cancel;
+	}
+
 	/* If we got this far on a dry run, all parameters are ok. */
 	if (fxr->flags & XFS_EXCH_RANGE_DRY_RUN)
 		goto out_trans_cancel;
@@ -814,7 +905,17 @@ xfs_xchg_range(
 		xfs_trans_ichgtime(tp, ip2,
 				XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 
-	xfs_swapext(tp, &req);
+	switch (strategy) {
+	case SWAPEXT:
+		xfs_swapext(tp, &req);
+		error = 0;
+		break;
+	case FORKSWAP:
+		error = xfs_swap_extent_forks(&tp, &req);
+		break;
+	}
+	if (error)
+		goto out_trans_cancel;
 
 	/*
 	 * Force the log to persist metadata updates if the caller or the

[PATCH 19/25] xfs: remove old swap extents implementation

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Migrate the old XFS_IOC_SWAPEXT implementation to use our shiny new one.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_bmap_util.c |  494 ------------------------------------------------
 fs/xfs/xfs_bmap_util.h |    7 -
 fs/xfs/xfs_ioctl.c     |  102 +++-------
 fs/xfs/xfs_ioctl.h     |    4 
 fs/xfs/xfs_ioctl32.c   |   11 -
 fs/xfs/xfs_xchgrange.c |  299 +++++++++++++++++++++++++++++
 6 files changed, 334 insertions(+), 583 deletions(-)


diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 405d02e71ab65..8eab56a62ce24 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1234,497 +1234,3 @@ xfs_insert_file_space(
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 }
-
-/*
- * We need to check that the format of the data fork in the temporary inode is
- * valid for the target inode before doing the swap. This is not a problem with
- * attr1 because of the fixed fork offset, but attr2 has a dynamically sized
- * data fork depending on the space the attribute fork is taking so we can get
- * invalid formats on the target inode.
- *
- * E.g. target has space for 7 extents in extent format, temp inode only has
- * space for 6.  If we defragment down to 7 extents, then the tmp format is a
- * btree, but when swapped it needs to be in extent format. Hence we can't just
- * blindly swap data forks on attr2 filesystems.
- *
- * Note that we check the swap in both directions so that we don't end up with
- * a corrupt temporary inode, either.
- *
- * Note that fixing the way xfs_fsr sets up the attribute fork in the source
- * inode will prevent this situation from occurring, so all we do here is
- * reject and log the attempt. basically we are putting the responsibility on
- * userspace to get this right.
- */
-int
-xfs_swap_extents_check_format(
-	struct xfs_inode	*ip,	/* target inode */
-	struct xfs_inode	*tip)	/* tmp inode */
-{
-	struct xfs_ifork	*ifp = &ip->i_df;
-	struct xfs_ifork	*tifp = &tip->i_df;
-
-	/* User/group/project quota ids must match if quotas are enforced. */
-	if (XFS_IS_QUOTA_ON(ip->i_mount) &&
-	    (!uid_eq(VFS_I(ip)->i_uid, VFS_I(tip)->i_uid) ||
-	     !gid_eq(VFS_I(ip)->i_gid, VFS_I(tip)->i_gid) ||
-	     ip->i_projid != tip->i_projid))
-		return -EINVAL;
-
-	/* Should never get a local format */
-	if (ifp->if_format == XFS_DINODE_FMT_LOCAL ||
-	    tifp->if_format == XFS_DINODE_FMT_LOCAL)
-		return -EINVAL;
-
-	/*
-	 * if the target inode has less extents that then temporary inode then
-	 * why did userspace call us?
-	 */
-	if (ifp->if_nextents < tifp->if_nextents)
-		return -EINVAL;
-
-	/*
-	 * If we have to use the (expensive) rmap swap method, we can
-	 * handle any number of extents and any format.
-	 */
-	if (xfs_has_rmapbt(ip->i_mount))
-		return 0;
-
-	/*
-	 * if the target inode is in extent form and the temp inode is in btree
-	 * form then we will end up with the target inode in the wrong format
-	 * as we already know there are less extents in the temp inode.
-	 */
-	if (ifp->if_format == XFS_DINODE_FMT_EXTENTS &&
-	    tifp->if_format == XFS_DINODE_FMT_BTREE)
-		return -EINVAL;
-
-	/* Check temp in extent form to max in target */
-	if (tifp->if_format == XFS_DINODE_FMT_EXTENTS &&
-	    tifp->if_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))
-		return -EINVAL;
-
-	/* Check target in extent form to max in temp */
-	if (ifp->if_format == XFS_DINODE_FMT_EXTENTS &&
-	    ifp->if_nextents > XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK))
-		return -EINVAL;
-
-	/*
-	 * If we are in a btree format, check that the temp root block will fit
-	 * in the target and that it has enough extents to be in btree format
-	 * in the target.
-	 *
-	 * Note that we have to be careful to allow btree->extent conversions
-	 * (a common defrag case) which will occur when the temp inode is in
-	 * extent format...
-	 */
-	if (tifp->if_format == XFS_DINODE_FMT_BTREE) {
-		if (xfs_inode_has_attr_fork(ip) &&
-		    XFS_BMAP_BMDR_SPACE(tifp->if_broot) > xfs_inode_fork_boff(ip))
-			return -EINVAL;
-		if (tifp->if_nextents <= XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))
-			return -EINVAL;
-	}
-
-	/* Reciprocal target->temp btree format checks */
-	if (ifp->if_format == XFS_DINODE_FMT_BTREE) {
-		if (xfs_inode_has_attr_fork(tip) &&
-		    XFS_BMAP_BMDR_SPACE(ip->i_df.if_broot) > xfs_inode_fork_boff(tip))
-			return -EINVAL;
-		if (ifp->if_nextents <= XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK))
-			return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int
-xfs_swap_extent_flush(
-	struct xfs_inode	*ip)
-{
-	int	error;
-
-	error = filemap_write_and_wait(VFS_I(ip)->i_mapping);
-	if (error)
-		return error;
-	truncate_pagecache_range(VFS_I(ip), 0, -1);
-
-	/* Verify O_DIRECT for ftmp */
-	if (VFS_I(ip)->i_mapping->nrpages)
-		return -EINVAL;
-	return 0;
-}
-
-/*
- * Fix up the owners of the bmbt blocks to refer to the current inode. The
- * change owner scan attempts to order all modified buffers in the current
- * transaction. In the event of ordered buffer failure, the offending buffer is
- * physically logged as a fallback and the scan returns -EAGAIN. We must roll
- * the transaction in this case to replenish the fallback log reservation and
- * restart the scan. This process repeats until the scan completes.
- */
-static int
-xfs_swap_change_owner(
-	struct xfs_trans	**tpp,
-	struct xfs_inode	*ip,
-	struct xfs_inode	*tmpip)
-{
-	int			error;
-	struct xfs_trans	*tp = *tpp;
-
-	do {
-		error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK, ip->i_ino,
-					      NULL);
-		/* success or fatal error */
-		if (error != -EAGAIN)
-			break;
-
-		error = xfs_trans_roll(tpp);
-		if (error)
-			break;
-		tp = *tpp;
-
-		/*
-		 * Redirty both inodes so they can relog and keep the log tail
-		 * moving forward.
-		 */
-		xfs_trans_ijoin(tp, ip, 0);
-		xfs_trans_ijoin(tp, tmpip, 0);
-		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-		xfs_trans_log_inode(tp, tmpip, XFS_ILOG_CORE);
-	} while (true);
-
-	return error;
-}
-
-/* Swap the extents of two files by swapping data forks. */
-int
-xfs_swap_extent_forks(
-	struct xfs_trans	**tpp,
-	struct xfs_swapext_req	*req)
-{
-	struct xfs_inode	*ip = req->ip2;
-	struct xfs_inode	*tip = req->ip1;
-	xfs_filblks_t		aforkblks = 0;
-	xfs_filblks_t		taforkblks = 0;
-	xfs_extnum_t		junk;
-	uint64_t		tmp;
-	int			src_log_flags = XFS_ILOG_CORE;
-	int			target_log_flags = XFS_ILOG_CORE;
-	int			error;
-
-	/*
-	 * Count the number of extended attribute blocks
-	 */
-	if (xfs_inode_has_attr_fork(ip) && ip->i_af.if_nextents > 0 &&
-	    ip->i_af.if_format != XFS_DINODE_FMT_LOCAL) {
-		error = xfs_bmap_count_blocks(*tpp, ip, XFS_ATTR_FORK, &junk,
-				&aforkblks);
-		if (error)
-			return error;
-	}
-	if (xfs_inode_has_attr_fork(tip) && tip->i_af.if_nextents > 0 &&
-	    tip->i_af.if_format != XFS_DINODE_FMT_LOCAL) {
-		error = xfs_bmap_count_blocks(*tpp, tip, XFS_ATTR_FORK, &junk,
-				&taforkblks);
-		if (error)
-			return error;
-	}
-
-	/*
-	 * Btree format (v3) inodes have the inode number stamped in the bmbt
-	 * block headers. We can't start changing the bmbt blocks until the
-	 * inode owner change is logged so recovery does the right thing in the
-	 * event of a crash. Set the owner change log flags now and leave the
-	 * bmbt scan as the last step.
-	 */
-	if (xfs_has_v3inodes(ip->i_mount)) {
-		if (ip->i_df.if_format == XFS_DINODE_FMT_BTREE)
-			target_log_flags |= XFS_ILOG_DOWNER;
-		if (tip->i_df.if_format == XFS_DINODE_FMT_BTREE)
-			src_log_flags |= XFS_ILOG_DOWNER;
-	}
-
-	/*
-	 * Swap the data forks of the inodes
-	 */
-	swap(ip->i_df, tip->i_df);
-
-	/*
-	 * Fix the on-disk inode values
-	 */
-	tmp = (uint64_t)ip->i_nblocks;
-	ip->i_nblocks = tip->i_nblocks - taforkblks + aforkblks;
-	tip->i_nblocks = tmp + taforkblks - aforkblks;
-
-	/*
-	 * The extents in the source inode could still contain speculative
-	 * preallocation beyond EOF (e.g. the file is open but not modified
-	 * while defrag is in progress). In that case, we need to copy over the
-	 * number of delalloc blocks the data fork in the source inode is
-	 * tracking beyond EOF so that when the fork is truncated away when the
-	 * temporary inode is unlinked we don't underrun the i_delayed_blks
-	 * counter on that inode.
-	 */
-	ASSERT(tip->i_delayed_blks == 0);
-	tip->i_delayed_blks = ip->i_delayed_blks;
-	ip->i_delayed_blks = 0;
-
-	switch (ip->i_df.if_format) {
-	case XFS_DINODE_FMT_EXTENTS:
-		src_log_flags |= XFS_ILOG_DEXT;
-		break;
-	case XFS_DINODE_FMT_BTREE:
-		ASSERT(!xfs_has_v3inodes(ip->i_mount) ||
-		       (src_log_flags & XFS_ILOG_DOWNER));
-		src_log_flags |= XFS_ILOG_DBROOT;
-		break;
-	}
-
-	switch (tip->i_df.if_format) {
-	case XFS_DINODE_FMT_EXTENTS:
-		target_log_flags |= XFS_ILOG_DEXT;
-		break;
-	case XFS_DINODE_FMT_BTREE:
-		target_log_flags |= XFS_ILOG_DBROOT;
-		ASSERT(!xfs_has_v3inodes(ip->i_mount) ||
-		       (target_log_flags & XFS_ILOG_DOWNER));
-		break;
-	}
-
-	/* Do we have to swap reflink flags? */
-	if ((ip->i_diflags2 & XFS_DIFLAG2_REFLINK) ^
-	    (tip->i_diflags2 & XFS_DIFLAG2_REFLINK)) {
-		uint64_t	f;
-
-		f = ip->i_diflags2 & XFS_DIFLAG2_REFLINK;
-		ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
-		ip->i_diflags2 |= tip->i_diflags2 & XFS_DIFLAG2_REFLINK;
-		tip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
-		tip->i_diflags2 |= f & XFS_DIFLAG2_REFLINK;
-	}
-
-	/* Swap the cow forks. */
-	if (xfs_has_reflink(ip->i_mount)) {
-		ASSERT(!ip->i_cowfp ||
-		       ip->i_cowfp->if_format == XFS_DINODE_FMT_EXTENTS);
-		ASSERT(!tip->i_cowfp ||
-		       tip->i_cowfp->if_format == XFS_DINODE_FMT_EXTENTS);
-
-		swap(ip->i_cowfp, tip->i_cowfp);
-
-		if (ip->i_cowfp && ip->i_cowfp->if_bytes)
-			xfs_inode_set_cowblocks_tag(ip);
-		else
-			xfs_inode_clear_cowblocks_tag(ip);
-		if (tip->i_cowfp && tip->i_cowfp->if_bytes)
-			xfs_inode_set_cowblocks_tag(tip);
-		else
-			xfs_inode_clear_cowblocks_tag(tip);
-	}
-
-	xfs_trans_log_inode(*tpp, ip,  src_log_flags);
-	xfs_trans_log_inode(*tpp, tip, target_log_flags);
-
-	/*
-	 * The extent forks have been swapped, but crc=1,rmapbt=0 filesystems
-	 * have inode number owner values in the bmbt blocks that still refer to
-	 * the old inode. Scan each bmbt to fix up the owner values with the
-	 * inode number of the current inode.
-	 */
-	if (src_log_flags & XFS_ILOG_DOWNER) {
-		error = xfs_swap_change_owner(tpp, ip, tip);
-		if (error)
-			return error;
-	}
-	if (target_log_flags & XFS_ILOG_DOWNER) {
-		error = xfs_swap_change_owner(tpp, tip, ip);
-		if (error)
-			return error;
-	}
-
-	return 0;
-}
-
-int
-xfs_swap_extents(
-	struct xfs_inode	*ip,	/* target inode */
-	struct xfs_inode	*tip,	/* tmp inode */
-	struct xfs_swapext	*sxp)
-{
-	struct xfs_swapext_req	req = {
-		.ip1		= tip,
-		.ip2		= ip,
-		.whichfork	= XFS_DATA_FORK,
-	};
-	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_trans	*tp;
-	struct xfs_bstat	*sbp = &sxp->sx_stat;
-	int			error = 0;
-	int			resblks = 0;
-	unsigned int		flags = 0;
-	struct timespec64	ctime, mtime;
-
-	/*
-	 * Lock the inodes against other IO, page faults and truncate to
-	 * begin with.  Then we can ensure the inodes are flushed and have no
-	 * page cache safely. Once we have done this we can take the ilocks and
-	 * do the rest of the checks.
-	 */
-	lock_two_nondirectories(VFS_I(ip), VFS_I(tip));
-	filemap_invalidate_lock_two(VFS_I(ip)->i_mapping,
-				    VFS_I(tip)->i_mapping);
-
-	/* Verify that both files have the same format */
-	if ((VFS_I(ip)->i_mode & S_IFMT) != (VFS_I(tip)->i_mode & S_IFMT)) {
-		error = -EINVAL;
-		goto out_unlock;
-	}
-
-	/* Verify both files are either real-time or non-realtime */
-	if (XFS_IS_REALTIME_INODE(ip) != XFS_IS_REALTIME_INODE(tip)) {
-		error = -EINVAL;
-		goto out_unlock;
-	}
-
-	error = xfs_qm_dqattach(ip);
-	if (error)
-		goto out_unlock;
-
-	error = xfs_qm_dqattach(tip);
-	if (error)
-		goto out_unlock;
-
-	error = xfs_swap_extent_flush(ip);
-	if (error)
-		goto out_unlock;
-	error = xfs_swap_extent_flush(tip);
-	if (error)
-		goto out_unlock;
-
-	if (xfs_inode_has_cow_data(tip)) {
-		error = xfs_reflink_cancel_cow_range(tip, 0, NULLFILEOFF, true);
-		if (error)
-			goto out_unlock;
-	}
-
-	/*
-	 * Extent "swapping" with rmap requires a permanent reservation and
-	 * a block reservation because it's really just a remap operation
-	 * performed with log redo items!
-	 */
-	if (xfs_has_rmapbt(mp)) {
-		int		w = XFS_DATA_FORK;
-		uint32_t	ipnext = ip->i_df.if_nextents;
-		uint32_t	tipnext	= tip->i_df.if_nextents;
-
-		/*
-		 * Conceptually this shouldn't affect the shape of either bmbt,
-		 * but since we atomically move extents one by one, we reserve
-		 * enough space to rebuild both trees.
-		 */
-		resblks = XFS_SWAP_RMAP_SPACE_RES(mp, ipnext, w);
-		resblks +=  XFS_SWAP_RMAP_SPACE_RES(mp, tipnext, w);
-
-		/*
-		 * If either inode straddles a bmapbt block allocation boundary,
-		 * the rmapbt algorithm triggers repeated allocs and frees as
-		 * extents are remapped. This can exhaust the block reservation
-		 * prematurely and cause shutdown. Return freed blocks to the
-		 * transaction reservation to counter this behavior.
-		 */
-		flags |= XFS_TRANS_RES_FDBLKS;
-	}
-	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, flags,
-				&tp);
-	if (error)
-		goto out_unlock;
-
-	/*
-	 * Lock and join the inodes to the tansaction so that transaction commit
-	 * or cancel will unlock the inodes from this point onwards.
-	 */
-	xfs_lock_two_inodes(ip, XFS_ILOCK_EXCL, tip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, ip, 0);
-	xfs_trans_ijoin(tp, tip, 0);
-
-
-	/* Verify all data are being swapped */
-	if (sxp->sx_offset != 0 ||
-	    sxp->sx_length != ip->i_disk_size ||
-	    sxp->sx_length != tip->i_disk_size) {
-		error = -EFAULT;
-		goto out_trans_cancel;
-	}
-
-	trace_xfs_swap_extent_before(ip, 0);
-	trace_xfs_swap_extent_before(tip, 1);
-
-	/* check inode formats now that data is flushed */
-	error = xfs_swap_extents_check_format(ip, tip);
-	if (error) {
-		xfs_notice(mp,
-		    "%s: inode 0x%llx format is incompatible for exchanging.",
-				__func__, ip->i_ino);
-		goto out_trans_cancel;
-	}
-
-	/*
-	 * Compare the current change & modify times with that
-	 * passed in.  If they differ, we abort this swap.
-	 * This is the mechanism used to ensure the calling
-	 * process that the file was not changed out from
-	 * under it.
-	 */
-	ctime = inode_get_ctime(VFS_I(ip));
-	mtime = inode_get_mtime(VFS_I(ip));
-	if ((sbp->bs_ctime.tv_sec != ctime.tv_sec) ||
-	    (sbp->bs_ctime.tv_nsec != ctime.tv_nsec) ||
-	    (sbp->bs_mtime.tv_sec != mtime.tv_sec) ||
-	    (sbp->bs_mtime.tv_nsec != mtime.tv_nsec)) {
-		error = -EBUSY;
-		goto out_trans_cancel;
-	}
-
-	/*
-	 * Note the trickiness in setting the log flags - we set the owner log
-	 * flag on the opposite inode (i.e. the inode we are setting the new
-	 * owner to be) because once we swap the forks and log that, log
-	 * recovery is going to see the fork as owned by the swapped inode,
-	 * not the pre-swapped inodes.
-	 */
-	req.blockcount = XFS_B_TO_FSB(ip->i_mount, i_size_read(VFS_I(ip)));
-	if (xfs_has_rmapbt(mp)) {
-		xfs_swapext(tp, &req);
-		error = xfs_defer_finish(&tp);
-	} else
-		error = xfs_swap_extent_forks(&tp, &req);
-	if (error) {
-		trace_xfs_swap_extent_error(ip, error, _THIS_IP_);
-		goto out_trans_cancel;
-	}
-
-	/*
-	 * If this is a synchronous mount, make sure that the
-	 * transaction goes to disk before returning to the user.
-	 */
-	if (xfs_has_wsync(mp))
-		xfs_trans_set_sync(tp);
-
-	error = xfs_trans_commit(tp);
-
-	trace_xfs_swap_extent_after(ip, 0);
-	trace_xfs_swap_extent_after(tip, 1);
-
-out_unlock_ilock:
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	xfs_iunlock(tip, XFS_ILOCK_EXCL);
-out_unlock:
-	filemap_invalidate_unlock_two(VFS_I(ip)->i_mapping,
-				      VFS_I(tip)->i_mapping);
-	unlock_two_nondirectories(VFS_I(ip), VFS_I(tip));
-	return error;
-
-out_trans_cancel:
-	xfs_trans_cancel(tp);
-	goto out_unlock_ilock;
-}
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 39c71da08403c..8eb7166aa9d41 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -66,13 +66,6 @@ int	xfs_insert_file_space(struct xfs_inode *, xfs_off_t offset,
 bool	xfs_can_free_eofblocks(struct xfs_inode *ip, bool force);
 int	xfs_free_eofblocks(struct xfs_inode *ip);
 
-int	xfs_swap_extents(struct xfs_inode *ip, struct xfs_inode *tip,
-			 struct xfs_swapext *sx);
-
-struct xfs_swapext_req;
-int xfs_swap_extent_forks(struct xfs_trans **tpp, struct xfs_swapext_req *req);
-int xfs_swap_extents_check_format(struct xfs_inode *ip, struct xfs_inode *tip);
-
 xfs_daddr_t xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb);
 
 xfs_extnum_t xfs_bmap_count_leaves(struct xfs_ifork *ifp, xfs_filblks_t *count);
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 372530698a154..071b135ec9653 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1668,81 +1668,43 @@ xfs_ioc_scrub_metadata(
 
 int
 xfs_ioc_swapext(
-	xfs_swapext_t	*sxp)
+	struct xfs_swapext	*sxp)
 {
-	xfs_inode_t     *ip, *tip;
-	struct fd	f, tmp;
-	int		error = 0;
+	struct xfs_exch_range	fxr = { 0 };
+	struct fd		fd2, fd1;
+	int			error = 0;
 
-	/* Pull information for the target fd */
-	f = fdget((int)sxp->sx_fdtarget);
-	if (!f.file) {
-		error = -EINVAL;
-		goto out;
-	}
-
-	if (!(f.file->f_mode & FMODE_WRITE) ||
-	    !(f.file->f_mode & FMODE_READ) ||
-	    (f.file->f_flags & O_APPEND)) {
-		error = -EBADF;
-		goto out_put_file;
-	}
+	fd2 = fdget((int)sxp->sx_fdtarget);
+	if (!fd2.file)
+		return -EINVAL;
 
-	tmp = fdget((int)sxp->sx_fdtmp);
-	if (!tmp.file) {
+	fd1 = fdget((int)sxp->sx_fdtmp);
+	if (!fd1.file) {
 		error = -EINVAL;
-		goto out_put_file;
+		goto dest_fdput;
 	}
 
-	if (!(tmp.file->f_mode & FMODE_WRITE) ||
-	    !(tmp.file->f_mode & FMODE_READ) ||
-	    (tmp.file->f_flags & O_APPEND)) {
-		error = -EBADF;
-		goto out_put_tmp_file;
-	}
+	fxr.file1_fd = sxp->sx_fdtmp;
+	fxr.length = sxp->sx_length;
+	fxr.flags = XFS_EXCH_RANGE_NONATOMIC | XFS_EXCH_RANGE_FILE2_FRESH |
+		    XFS_EXCH_RANGE_FULL_FILES;
+	fxr.file2_ino = sxp->sx_stat.bs_ino;
+	fxr.file2_mtime = sxp->sx_stat.bs_mtime.tv_sec;
+	fxr.file2_ctime = sxp->sx_stat.bs_ctime.tv_sec;
+	fxr.file2_mtime_nsec = sxp->sx_stat.bs_mtime.tv_nsec;
+	fxr.file2_ctime_nsec = sxp->sx_stat.bs_ctime.tv_nsec;
 
-	if (IS_SWAPFILE(file_inode(f.file)) ||
-	    IS_SWAPFILE(file_inode(tmp.file))) {
-		error = -EINVAL;
-		goto out_put_tmp_file;
-	}
+	error = xfs_exch_range(fd1.file, fd2.file, &fxr);
 
 	/*
-	 * We need to ensure that the fds passed in point to XFS inodes
-	 * before we cast and access them as XFS structures as we have no
-	 * control over what the user passes us here.
+	 * The old implementation returned EFAULT if the swap range was not
+	 * the entirety of both files.
 	 */
-	if (f.file->f_op != &xfs_file_operations ||
-	    tmp.file->f_op != &xfs_file_operations) {
-		error = -EINVAL;
-		goto out_put_tmp_file;
-	}
-
-	ip = XFS_I(file_inode(f.file));
-	tip = XFS_I(file_inode(tmp.file));
-
-	if (ip->i_mount != tip->i_mount) {
-		error = -EINVAL;
-		goto out_put_tmp_file;
-	}
-
-	if (ip->i_ino == tip->i_ino) {
-		error = -EINVAL;
-		goto out_put_tmp_file;
-	}
-
-	if (xfs_is_shutdown(ip->i_mount)) {
-		error = -EIO;
-		goto out_put_tmp_file;
-	}
-
-	error = xfs_swap_extents(ip, tip, sxp);
-
- out_put_tmp_file:
-	fdput(tmp);
- out_put_file:
-	fdput(f);
- out:
+	if (error == -EDOM)
+		error = -EFAULT;
+	fdput(fd1);
+dest_fdput:
+	fdput(fd2);
 	return error;
 }
 
@@ -2027,14 +1989,10 @@ xfs_file_ioctl(
 	case XFS_IOC_SWAPEXT: {
 		struct xfs_swapext	sxp;
 
-		if (copy_from_user(&sxp, arg, sizeof(xfs_swapext_t)))
+		if (copy_from_user(&sxp, arg, sizeof(struct xfs_swapext)))
 			return -EFAULT;
-		error = mnt_want_write_file(filp);
-		if (error)
-			return error;
-		error = xfs_ioc_swapext(&sxp);
-		mnt_drop_write_file(filp);
-		return error;
+
+		return xfs_ioc_swapext(&sxp);
 	}
 
 	case XFS_IOC_FSCOUNTS: {
diff --git a/fs/xfs/xfs_ioctl.h b/fs/xfs/xfs_ioctl.h
index 38be600b5e1e8..4e00846990f2d 100644
--- a/fs/xfs/xfs_ioctl.h
+++ b/fs/xfs/xfs_ioctl.h
@@ -10,9 +10,7 @@ struct xfs_bstat;
 struct xfs_ibulk;
 struct xfs_inogrp;
 
-int
-xfs_ioc_swapext(
-	xfs_swapext_t	*sxp);
+int xfs_ioc_swapext(struct xfs_swapext *sxp);
 
 extern int
 xfs_find_handle(
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index ee35eea1ecce6..a118d20854909 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -425,7 +425,6 @@ xfs_file_compat_ioctl(
 	struct inode		*inode = file_inode(filp);
 	struct xfs_inode	*ip = XFS_I(inode);
 	void			__user *arg = compat_ptr(p);
-	int			error;
 
 	trace_xfs_file_compat_ioctl(ip);
 
@@ -435,6 +434,7 @@ xfs_file_compat_ioctl(
 		return xfs_compat_ioc_fsgeometry_v1(ip->i_mount, arg);
 	case XFS_IOC_FSGROWFSDATA_32: {
 		struct xfs_growfs_data	in;
+		int			error;
 
 		if (xfs_compat_growfs_data_copyin(&in, arg))
 			return -EFAULT;
@@ -447,6 +447,7 @@ xfs_file_compat_ioctl(
 	}
 	case XFS_IOC_FSGROWFSRT_32: {
 		struct xfs_growfs_rt	in;
+		int			error;
 
 		if (xfs_compat_growfs_rt_copyin(&in, arg))
 			return -EFAULT;
@@ -471,12 +472,8 @@ xfs_file_compat_ioctl(
 				   offsetof(struct xfs_swapext, sx_stat)) ||
 		    xfs_ioctl32_bstat_copyin(&sxp.sx_stat, &sxu->sx_stat))
 			return -EFAULT;
-		error = mnt_want_write_file(filp);
-		if (error)
-			return error;
-		error = xfs_ioc_swapext(&sxp);
-		mnt_drop_write_file(filp);
-		return error;
+
+		return xfs_ioc_swapext(&sxp);
 	}
 	case XFS_IOC_FSBULKSTAT_32:
 	case XFS_IOC_FSBULKSTAT_SINGLE_32:
diff --git a/fs/xfs/xfs_xchgrange.c b/fs/xfs/xfs_xchgrange.c
index 328217551c1e8..c3476e68d6410 100644
--- a/fs/xfs/xfs_xchgrange.c
+++ b/fs/xfs/xfs_xchgrange.c
@@ -2,6 +2,11 @@
 /*
  * Copyright (c) 2020-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
+ *
+ * The xfs_swap_extent_* functions are:
+ * Copyright (c) 2000-2006 Silicon Graphics, Inc.
+ * Copyright (c) 2012 Red Hat, Inc.
+ * All Rights Reserved.
  */
 #include "xfs.h"
 #include "xfs_shared.h"
@@ -14,6 +19,7 @@
 #include "xfs_trans.h"
 #include "xfs_quota.h"
 #include "xfs_bmap_util.h"
+#include "xfs_bmap_btree.h"
 #include "xfs_reflink.h"
 #include "xfs_trace.h"
 #include "xfs_swapext.h"
@@ -474,6 +480,299 @@ xfs_xchg_range_estimate(
 	return error;
 }
 
+/*
+ * We need to check that the format of the data fork in the temporary inode is
+ * valid for the target inode before doing the swap. This is not a problem with
+ * attr1 because of the fixed fork offset, but attr2 has a dynamically sized
+ * data fork depending on the space the attribute fork is taking so we can get
+ * invalid formats on the target inode.
+ *
+ * E.g. target has space for 7 extents in extent format, temp inode only has
+ * space for 6.  If we defragment down to 7 extents, then the tmp format is a
+ * btree, but when swapped it needs to be in extent format. Hence we can't just
+ * blindly swap data forks on attr2 filesystems.
+ *
+ * Note that we check the swap in both directions so that we don't end up with
+ * a corrupt temporary inode, either.
+ *
+ * Note that fixing the way xfs_fsr sets up the attribute fork in the source
+ * inode will prevent this situation from occurring, so all we do here is
+ * reject and log the attempt. basically we are putting the responsibility on
+ * userspace to get this right.
+ */
+STATIC int
+xfs_swap_extents_check_format(
+	struct xfs_inode	*ip,	/* target inode */
+	struct xfs_inode	*tip)	/* tmp inode */
+{
+	struct xfs_ifork	*ifp = &ip->i_df;
+	struct xfs_ifork	*tifp = &tip->i_df;
+
+	/* User/group/project quota ids must match if quotas are enforced. */
+	if (XFS_IS_QUOTA_ON(ip->i_mount) &&
+	    (!uid_eq(VFS_I(ip)->i_uid, VFS_I(tip)->i_uid) ||
+	     !gid_eq(VFS_I(ip)->i_gid, VFS_I(tip)->i_gid) ||
+	     ip->i_projid != tip->i_projid))
+		return -EINVAL;
+
+	/* Should never get a local format */
+	if (ifp->if_format == XFS_DINODE_FMT_LOCAL ||
+	    tifp->if_format == XFS_DINODE_FMT_LOCAL)
+		return -EINVAL;
+
+	/*
+	 * if the target inode has less extents that then temporary inode then
+	 * why did userspace call us?
+	 */
+	if (ifp->if_nextents < tifp->if_nextents)
+		return -EINVAL;
+
+	/*
+	 * If we have to use the (expensive) rmap swap method, we can
+	 * handle any number of extents and any format.
+	 */
+	if (xfs_has_rmapbt(ip->i_mount))
+		return 0;
+
+	/*
+	 * if the target inode is in extent form and the temp inode is in btree
+	 * form then we will end up with the target inode in the wrong format
+	 * as we already know there are less extents in the temp inode.
+	 */
+	if (ifp->if_format == XFS_DINODE_FMT_EXTENTS &&
+	    tifp->if_format == XFS_DINODE_FMT_BTREE)
+		return -EINVAL;
+
+	/* Check temp in extent form to max in target */
+	if (tifp->if_format == XFS_DINODE_FMT_EXTENTS &&
+	    tifp->if_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))
+		return -EINVAL;
+
+	/* Check target in extent form to max in temp */
+	if (ifp->if_format == XFS_DINODE_FMT_EXTENTS &&
+	    ifp->if_nextents > XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK))
+		return -EINVAL;
+
+	/*
+	 * If we are in a btree format, check that the temp root block will fit
+	 * in the target and that it has enough extents to be in btree format
+	 * in the target.
+	 *
+	 * Note that we have to be careful to allow btree->extent conversions
+	 * (a common defrag case) which will occur when the temp inode is in
+	 * extent format...
+	 */
+	if (tifp->if_format == XFS_DINODE_FMT_BTREE) {
+		if (xfs_inode_has_attr_fork(ip) &&
+		    XFS_BMAP_BMDR_SPACE(tifp->if_broot) > xfs_inode_fork_boff(ip))
+			return -EINVAL;
+		if (tifp->if_nextents <= XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))
+			return -EINVAL;
+	}
+
+	/* Reciprocal target->temp btree format checks */
+	if (ifp->if_format == XFS_DINODE_FMT_BTREE) {
+		if (xfs_inode_has_attr_fork(tip) &&
+		    XFS_BMAP_BMDR_SPACE(ip->i_df.if_broot) > xfs_inode_fork_boff(tip))
+			return -EINVAL;
+		if (ifp->if_nextents <= XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ * Fix up the owners of the bmbt blocks to refer to the current inode. The
+ * change owner scan attempts to order all modified buffers in the current
+ * transaction. In the event of ordered buffer failure, the offending buffer is
+ * physically logged as a fallback and the scan returns -EAGAIN. We must roll
+ * the transaction in this case to replenish the fallback log reservation and
+ * restart the scan. This process repeats until the scan completes.
+ */
+static int
+xfs_swap_change_owner(
+	struct xfs_trans	**tpp,
+	struct xfs_inode	*ip,
+	struct xfs_inode	*tmpip)
+{
+	int			error;
+	struct xfs_trans	*tp = *tpp;
+
+	do {
+		error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK, ip->i_ino,
+					      NULL);
+		/* success or fatal error */
+		if (error != -EAGAIN)
+			break;
+
+		error = xfs_trans_roll(tpp);
+		if (error)
+			break;
+		tp = *tpp;
+
+		/*
+		 * Redirty both inodes so they can relog and keep the log tail
+		 * moving forward.
+		 */
+		xfs_trans_ijoin(tp, ip, 0);
+		xfs_trans_ijoin(tp, tmpip, 0);
+		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+		xfs_trans_log_inode(tp, tmpip, XFS_ILOG_CORE);
+	} while (true);
+
+	return error;
+}
+
+/* Swap the extents of two files by swapping data forks. */
+STATIC int
+xfs_swap_extent_forks(
+	struct xfs_trans	**tpp,
+	struct xfs_swapext_req	*req)
+{
+	struct xfs_inode	*ip = req->ip2;
+	struct xfs_inode	*tip = req->ip1;
+	xfs_filblks_t		aforkblks = 0;
+	xfs_filblks_t		taforkblks = 0;
+	xfs_extnum_t		junk;
+	uint64_t		tmp;
+	int			src_log_flags = XFS_ILOG_CORE;
+	int			target_log_flags = XFS_ILOG_CORE;
+	int			error;
+
+	/*
+	 * Count the number of extended attribute blocks
+	 */
+	if (xfs_inode_has_attr_fork(ip) && ip->i_af.if_nextents > 0 &&
+	    ip->i_af.if_format != XFS_DINODE_FMT_LOCAL) {
+		error = xfs_bmap_count_blocks(*tpp, ip, XFS_ATTR_FORK, &junk,
+				&aforkblks);
+		if (error)
+			return error;
+	}
+	if (xfs_inode_has_attr_fork(tip) && tip->i_af.if_nextents > 0 &&
+	    tip->i_af.if_format != XFS_DINODE_FMT_LOCAL) {
+		error = xfs_bmap_count_blocks(*tpp, tip, XFS_ATTR_FORK, &junk,
+				&taforkblks);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * Btree format (v3) inodes have the inode number stamped in the bmbt
+	 * block headers. We can't start changing the bmbt blocks until the
+	 * inode owner change is logged so recovery does the right thing in the
+	 * event of a crash. Set the owner change log flags now and leave the
+	 * bmbt scan as the last step.
+	 */
+	if (xfs_has_v3inodes(ip->i_mount)) {
+		if (ip->i_df.if_format == XFS_DINODE_FMT_BTREE)
+			target_log_flags |= XFS_ILOG_DOWNER;
+		if (tip->i_df.if_format == XFS_DINODE_FMT_BTREE)
+			src_log_flags |= XFS_ILOG_DOWNER;
+	}
+
+	/*
+	 * Swap the data forks of the inodes
+	 */
+	swap(ip->i_df, tip->i_df);
+
+	/*
+	 * Fix the on-disk inode values
+	 */
+	tmp = (uint64_t)ip->i_nblocks;
+	ip->i_nblocks = tip->i_nblocks - taforkblks + aforkblks;
+	tip->i_nblocks = tmp + taforkblks - aforkblks;
+
+	/*
+	 * The extents in the source inode could still contain speculative
+	 * preallocation beyond EOF (e.g. the file is open but not modified
+	 * while defrag is in progress). In that case, we need to copy over the
+	 * number of delalloc blocks the data fork in the source inode is
+	 * tracking beyond EOF so that when the fork is truncated away when the
+	 * temporary inode is unlinked we don't underrun the i_delayed_blks
+	 * counter on that inode.
+	 */
+	ASSERT(tip->i_delayed_blks == 0);
+	tip->i_delayed_blks = ip->i_delayed_blks;
+	ip->i_delayed_blks = 0;
+
+	switch (ip->i_df.if_format) {
+	case XFS_DINODE_FMT_EXTENTS:
+		src_log_flags |= XFS_ILOG_DEXT;
+		break;
+	case XFS_DINODE_FMT_BTREE:
+		ASSERT(!xfs_has_v3inodes(ip->i_mount) ||
+		       (src_log_flags & XFS_ILOG_DOWNER));
+		src_log_flags |= XFS_ILOG_DBROOT;
+		break;
+	}
+
+	switch (tip->i_df.if_format) {
+	case XFS_DINODE_FMT_EXTENTS:
+		target_log_flags |= XFS_ILOG_DEXT;
+		break;
+	case XFS_DINODE_FMT_BTREE:
+		target_log_flags |= XFS_ILOG_DBROOT;
+		ASSERT(!xfs_has_v3inodes(ip->i_mount) ||
+		       (target_log_flags & XFS_ILOG_DOWNER));
+		break;
+	}
+
+	/* Do we have to swap reflink flags? */
+	if ((ip->i_diflags2 & XFS_DIFLAG2_REFLINK) ^
+	    (tip->i_diflags2 & XFS_DIFLAG2_REFLINK)) {
+		uint64_t	f;
+
+		f = ip->i_diflags2 & XFS_DIFLAG2_REFLINK;
+		ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+		ip->i_diflags2 |= tip->i_diflags2 & XFS_DIFLAG2_REFLINK;
+		tip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+		tip->i_diflags2 |= f & XFS_DIFLAG2_REFLINK;
+	}
+
+	/* Swap the cow forks. */
+	if (xfs_has_reflink(ip->i_mount)) {
+		ASSERT(!ip->i_cowfp ||
+		       ip->i_cowfp->if_format == XFS_DINODE_FMT_EXTENTS);
+		ASSERT(!tip->i_cowfp ||
+		       tip->i_cowfp->if_format == XFS_DINODE_FMT_EXTENTS);
+
+		swap(ip->i_cowfp, tip->i_cowfp);
+
+		if (ip->i_cowfp && ip->i_cowfp->if_bytes)
+			xfs_inode_set_cowblocks_tag(ip);
+		else
+			xfs_inode_clear_cowblocks_tag(ip);
+		if (tip->i_cowfp && tip->i_cowfp->if_bytes)
+			xfs_inode_set_cowblocks_tag(tip);
+		else
+			xfs_inode_clear_cowblocks_tag(tip);
+	}
+
+	xfs_trans_log_inode(*tpp, ip,  src_log_flags);
+	xfs_trans_log_inode(*tpp, tip, target_log_flags);
+
+	/*
+	 * The extent forks have been swapped, but crc=1,rmapbt=0 filesystems
+	 * have inode number owner values in the bmbt blocks that still refer to
+	 * the old inode. Scan each bmbt to fix up the owner values with the
+	 * inode number of the current inode.
+	 */
+	if (src_log_flags & XFS_ILOG_DOWNER) {
+		error = xfs_swap_change_owner(tpp, ip, tip);
+		if (error)
+			return error;
+	}
+	if (target_log_flags & XFS_ILOG_DOWNER) {
+		error = xfs_swap_change_owner(tpp, tip, ip);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
 /* Prepare two files to have their data exchanged. */
 int
 xfs_xchg_range_prep(

[PATCH 20/25] xfs: condense extended attributes after an atomic swap

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add a new swapext flag that enables us to perform post-swap processing
on file2 once we're done swapping the extent maps.  If we were swapping
the extended attributes, we want to be able to convert file2's attr fork
from block to inline format.

This isn't used anywhere right now, but we need to have the basic ondisk
flags in place so that a future online xattr repair feature can create
salvaged attrs in a temporary file and swap the attr forks when ready.
If one file is in extents format and the other is inline, we will have to
promote both to extents format to perform the swap.  After the swap, we
can try to condense the fixed file's attr fork back down to inline
format if possible.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_log_format.h |    9 +++++--
 fs/xfs/libxfs/xfs_swapext.c    |   51 +++++++++++++++++++++++++++++++++++++++-
 fs/xfs/libxfs/xfs_swapext.h    |    9 +++++--
 3 files changed, 64 insertions(+), 5 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index 3341792cf43a5..d4531060b6b49 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -916,18 +916,23 @@ struct xfs_swap_extent {
 /* Clear the reflink flag from inode2 after the operation. */
 #define XFS_SWAP_EXT_CLEAR_INO2_REFLINK	(1ULL << 4)
 
+/* Try to convert inode2 from block to short format at the end, if possible. */
+#define XFS_SWAP_EXT_CVT_INO2_SF	(1ULL << 5)
+
 #define XFS_SWAP_EXT_FLAGS		(XFS_SWAP_EXT_ATTR_FORK | \
 					 XFS_SWAP_EXT_SET_SIZES | \
 					 XFS_SWAP_EXT_INO1_WRITTEN | \
 					 XFS_SWAP_EXT_CLEAR_INO1_REFLINK | \
-					 XFS_SWAP_EXT_CLEAR_INO2_REFLINK)
+					 XFS_SWAP_EXT_CLEAR_INO2_REFLINK | \
+					 XFS_SWAP_EXT_CVT_INO2_SF)
 
 #define XFS_SWAP_EXT_STRINGS \
 	{ XFS_SWAP_EXT_ATTR_FORK,		"ATTRFORK" }, \
 	{ XFS_SWAP_EXT_SET_SIZES,		"SETSIZES" }, \
 	{ XFS_SWAP_EXT_INO1_WRITTEN,		"INO1_WRITTEN" }, \
 	{ XFS_SWAP_EXT_CLEAR_INO1_REFLINK,	"CLEAR_INO1_REFLINK" }, \
-	{ XFS_SWAP_EXT_CLEAR_INO2_REFLINK,	"CLEAR_INO2_REFLINK" }
+	{ XFS_SWAP_EXT_CLEAR_INO2_REFLINK,	"CLEAR_INO2_REFLINK" }, \
+	{ XFS_SWAP_EXT_CVT_INO2_SF,		"CVT_INO2_SF" }
 
 /* This is the structure used to lay out an sxi log item in the log. */
 struct xfs_sxi_log_format {
diff --git a/fs/xfs/libxfs/xfs_swapext.c b/fs/xfs/libxfs/xfs_swapext.c
index 7e72b43f7b782..8e729fffb99df 100644
--- a/fs/xfs/libxfs/xfs_swapext.c
+++ b/fs/xfs/libxfs/xfs_swapext.c
@@ -24,6 +24,10 @@
 #include "xfs_errortag.h"
 #include "xfs_health.h"
 #include "xfs_swapext_item.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_attr_leaf.h"
+#include "xfs_attr.h"
 
 struct kmem_cache	*xfs_swapext_intent_cache;
 
@@ -112,7 +116,8 @@ static inline bool
 sxi_has_postop_work(const struct xfs_swapext_intent *sxi)
 {
 	return sxi->sxi_flags & (XFS_SWAP_EXT_CLEAR_INO1_REFLINK |
-				 XFS_SWAP_EXT_CLEAR_INO2_REFLINK);
+				 XFS_SWAP_EXT_CLEAR_INO2_REFLINK |
+				 XFS_SWAP_EXT_CVT_INO2_SF);
 }
 
 static inline void
@@ -360,6 +365,36 @@ xfs_swapext_exchange_mappings(
 	sxi_advance(sxi, irec1);
 }
 
+/* Convert inode2's leaf attr fork back to shortform, if possible.. */
+STATIC int
+xfs_swapext_attr_to_sf(
+	struct xfs_trans		*tp,
+	struct xfs_swapext_intent	*sxi)
+{
+	struct xfs_da_args	args = {
+		.dp		= sxi->sxi_ip2,
+		.geo		= tp->t_mountp->m_attr_geo,
+		.whichfork	= XFS_ATTR_FORK,
+		.trans		= tp,
+	};
+	struct xfs_buf		*bp;
+	int			forkoff;
+	int			error;
+
+	if (!xfs_attr_is_leaf(sxi->sxi_ip2))
+		return 0;
+
+	error = xfs_attr3_leaf_read(tp, sxi->sxi_ip2, 0, &bp);
+	if (error)
+		return error;
+
+	forkoff = xfs_attr_shortform_allfit(bp, sxi->sxi_ip2);
+	if (forkoff == 0)
+		return 0;
+
+	return xfs_attr3_leaf_to_shortform(bp, &args, forkoff);
+}
+
 static inline void
 xfs_swapext_clear_reflink(
 	struct xfs_trans	*tp,
@@ -377,6 +412,16 @@ xfs_swapext_do_postop_work(
 	struct xfs_trans		*tp,
 	struct xfs_swapext_intent	*sxi)
 {
+	if (sxi->sxi_flags & XFS_SWAP_EXT_CVT_INO2_SF) {
+		int			error = 0;
+
+		if (sxi->sxi_flags & XFS_SWAP_EXT_ATTR_FORK)
+			error = xfs_swapext_attr_to_sf(tp, sxi);
+		sxi->sxi_flags &= ~XFS_SWAP_EXT_CVT_INO2_SF;
+		if (error)
+			return error;
+	}
+
 	if (sxi->sxi_flags & XFS_SWAP_EXT_CLEAR_INO1_REFLINK) {
 		xfs_swapext_clear_reflink(tp, sxi->sxi_ip1);
 		sxi->sxi_flags &= ~XFS_SWAP_EXT_CLEAR_INO1_REFLINK;
@@ -804,6 +849,8 @@ xfs_swapext_init_intent(
 
 	if (req->req_flags & XFS_SWAP_REQ_INO1_WRITTEN)
 		sxi->sxi_flags |= XFS_SWAP_EXT_INO1_WRITTEN;
+	if (req->req_flags & XFS_SWAP_REQ_CVT_INO2_SF)
+		sxi->sxi_flags |= XFS_SWAP_EXT_CVT_INO2_SF;
 
 	if (req->req_flags & XFS_SWAP_REQ_LOGGED)
 		sxi->sxi_op_flags |= XFS_SWAP_EXT_OP_LOGGED;
@@ -1023,6 +1070,8 @@ xfs_swapext(
 	ASSERT(!(req->req_flags & ~XFS_SWAP_REQ_FLAGS));
 	if (req->req_flags & XFS_SWAP_REQ_SET_SIZES)
 		ASSERT(req->whichfork == XFS_DATA_FORK);
+	if (req->req_flags & XFS_SWAP_REQ_CVT_INO2_SF)
+		ASSERT(req->whichfork == XFS_ATTR_FORK);
 
 	if (req->blockcount == 0)
 		return;
diff --git a/fs/xfs/libxfs/xfs_swapext.h b/fs/xfs/libxfs/xfs_swapext.h
index fa786bc93520a..37842a4ee9a6d 100644
--- a/fs/xfs/libxfs/xfs_swapext.h
+++ b/fs/xfs/libxfs/xfs_swapext.h
@@ -180,16 +180,21 @@ struct xfs_swapext_req {
 /* Files need to be upgraded to have large extent counts. */
 #define XFS_SWAP_REQ_NREXT64		(1U << 3)
 
+/* Try to convert inode2's fork to local format, if possible. */
+#define XFS_SWAP_REQ_CVT_INO2_SF	(1U << 4)
+
 #define XFS_SWAP_REQ_FLAGS		(XFS_SWAP_REQ_LOGGED | \
 					 XFS_SWAP_REQ_SET_SIZES | \
 					 XFS_SWAP_REQ_INO1_WRITTEN | \
-					 XFS_SWAP_REQ_NREXT64)
+					 XFS_SWAP_REQ_NREXT64 | \
+					 XFS_SWAP_REQ_CVT_INO2_SF)
 
 #define XFS_SWAP_REQ_STRINGS \
 	{ XFS_SWAP_REQ_LOGGED,		"LOGGED" }, \
 	{ XFS_SWAP_REQ_SET_SIZES,	"SETSIZES" }, \
 	{ XFS_SWAP_REQ_INO1_WRITTEN,	"INO1_WRITTEN" }, \
-	{ XFS_SWAP_REQ_NREXT64,		"NREXT64" }
+	{ XFS_SWAP_REQ_NREXT64,		"NREXT64" }, \
+	{ XFS_SWAP_REQ_CVT_INO2_SF,	"CVT_INO2_SF" }
 
 unsigned int xfs_swapext_reflink_prep(const struct xfs_swapext_req *req);
 void xfs_swapext_reflink_finish(struct xfs_trans *tp,

[PATCH 21/25] xfs: condense directories after an atomic swap

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

The previous commit added a new swapext flag that enables us to perform
post-swap processing on file2 once we're done swapping the extent maps.
Now add this ability for directories.

This isn't used anywhere right now, but we need to have the basic ondisk
flags in place so that a future online directory repair feature can
create salvaged dirents in a temporary directory and swap the data forks
when ready.  If one file is in extents format and the other is inline,
we will have to promote both to extents format to perform the swap.
After the swap, we can try to condense the fixed directory down to
inline format if possible.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_swapext.c |   44 ++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 43 insertions(+), 1 deletion(-)


diff --git a/fs/xfs/libxfs/xfs_swapext.c b/fs/xfs/libxfs/xfs_swapext.c
index 8e729fffb99df..06c5fffec6423 100644
--- a/fs/xfs/libxfs/xfs_swapext.c
+++ b/fs/xfs/libxfs/xfs_swapext.c
@@ -28,6 +28,8 @@
 #include "xfs_da_btree.h"
 #include "xfs_attr_leaf.h"
 #include "xfs_attr.h"
+#include "xfs_dir2_priv.h"
+#include "xfs_dir2.h"
 
 struct kmem_cache	*xfs_swapext_intent_cache;
 
@@ -395,6 +397,42 @@ xfs_swapext_attr_to_sf(
 	return xfs_attr3_leaf_to_shortform(bp, &args, forkoff);
 }
 
+/* Convert inode2's block dir fork back to shortform, if possible.. */
+STATIC int
+xfs_swapext_dir_to_sf(
+	struct xfs_trans		*tp,
+	struct xfs_swapext_intent	*sxi)
+{
+	struct xfs_da_args	args = {
+		.dp		= sxi->sxi_ip2,
+		.geo		= tp->t_mountp->m_dir_geo,
+		.whichfork	= XFS_DATA_FORK,
+		.trans		= tp,
+	};
+	struct xfs_dir2_sf_hdr	sfh;
+	struct xfs_buf		*bp;
+	bool			isblock;
+	int			size;
+	int			error;
+
+	error = xfs_dir2_isblock(&args, &isblock);
+	if (error)
+		return error;
+
+	if (!isblock)
+		return 0;
+
+	error = xfs_dir3_block_read(tp, sxi->sxi_ip2, &bp);
+	if (error)
+		return error;
+
+	size = xfs_dir2_block_sfsize(sxi->sxi_ip2, bp->b_addr, &sfh);
+	if (size > xfs_inode_data_fork_size(sxi->sxi_ip2))
+		return 0;
+
+	return xfs_dir2_block_to_sf(&args, bp, size, &sfh);
+}
+
 static inline void
 xfs_swapext_clear_reflink(
 	struct xfs_trans	*tp,
@@ -417,6 +455,8 @@ xfs_swapext_do_postop_work(
 
 		if (sxi->sxi_flags & XFS_SWAP_EXT_ATTR_FORK)
 			error = xfs_swapext_attr_to_sf(tp, sxi);
+		else if (S_ISDIR(VFS_I(sxi->sxi_ip2)->i_mode))
+			error = xfs_swapext_dir_to_sf(tp, sxi);
 		sxi->sxi_flags &= ~XFS_SWAP_EXT_CVT_INO2_SF;
 		if (error)
 			return error;
@@ -1071,7 +1111,9 @@ xfs_swapext(
 	if (req->req_flags & XFS_SWAP_REQ_SET_SIZES)
 		ASSERT(req->whichfork == XFS_DATA_FORK);
 	if (req->req_flags & XFS_SWAP_REQ_CVT_INO2_SF)
-		ASSERT(req->whichfork == XFS_ATTR_FORK);
+		ASSERT(req->whichfork == XFS_ATTR_FORK ||
+		       (req->whichfork == XFS_DATA_FORK &&
+			S_ISDIR(VFS_I(req->ip2)->i_mode)));
 
 	if (req->blockcount == 0)
 		return;

[PATCH 22/25] xfs: condense symbolic links after an atomic swap

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

The previous commit added a new swapext flag that enables us to perform
post-swap processing on file2 once we're done swapping the extent maps.
Now add this ability for symlinks.

This isn't used anywhere right now, but we need to have the basic ondisk
flags in place so that a future online symlink repair feature can
salvage the remote target in a temporary link and swap the data forks
when ready.  If one file is in extents format and the other is inline,
we will have to promote both to extents format to perform the swap.
After the swap, we can try to condense the fixed symlink down to inline
format if possible.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_swapext.c        |   48 +++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_symlink_remote.c |   47 +++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_symlink_remote.h |    1 +
 fs/xfs/xfs_symlink.c               |   49 ++++--------------------------------
 4 files changed, 101 insertions(+), 44 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_swapext.c b/fs/xfs/libxfs/xfs_swapext.c
index 06c5fffec6423..e84b9ffe9df6b 100644
--- a/fs/xfs/libxfs/xfs_swapext.c
+++ b/fs/xfs/libxfs/xfs_swapext.c
@@ -30,6 +30,7 @@
 #include "xfs_attr.h"
 #include "xfs_dir2_priv.h"
 #include "xfs_dir2.h"
+#include "xfs_symlink_remote.h"
 
 struct kmem_cache	*xfs_swapext_intent_cache;
 
@@ -433,6 +434,48 @@ xfs_swapext_dir_to_sf(
 	return xfs_dir2_block_to_sf(&args, bp, size, &sfh);
 }
 
+/* Convert inode2's remote symlink target back to shortform, if possible. */
+STATIC int
+xfs_swapext_link_to_sf(
+	struct xfs_trans		*tp,
+	struct xfs_swapext_intent	*sxi)
+{
+	struct xfs_inode		*ip = sxi->sxi_ip2;
+	struct xfs_ifork		*ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
+	char				*buf;
+	int				error;
+
+	if (ifp->if_format == XFS_DINODE_FMT_LOCAL ||
+	    ip->i_disk_size > xfs_inode_data_fork_size(ip))
+		return 0;
+
+	/* Read the current symlink target into a buffer. */
+	buf = kmem_alloc(ip->i_disk_size + 1, KM_NOFS);
+	if (!buf) {
+		ASSERT(0);
+		return -ENOMEM;
+	}
+
+	error = xfs_symlink_remote_read(ip, buf);
+	if (error)
+		goto free;
+
+	/* Remove the blocks. */
+	error = xfs_symlink_remote_truncate(tp, ip);
+	if (error)
+		goto free;
+
+	/* Convert fork to local format and log our changes. */
+	xfs_idestroy_fork(ifp);
+	ifp->if_bytes = 0;
+	ifp->if_format = XFS_DINODE_FMT_LOCAL;
+	xfs_init_local_fork(ip, XFS_DATA_FORK, buf, ip->i_disk_size);
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_DDATA | XFS_ILOG_CORE);
+free:
+	kmem_free(buf);
+	return error;
+}
+
 static inline void
 xfs_swapext_clear_reflink(
 	struct xfs_trans	*tp,
@@ -457,6 +500,8 @@ xfs_swapext_do_postop_work(
 			error = xfs_swapext_attr_to_sf(tp, sxi);
 		else if (S_ISDIR(VFS_I(sxi->sxi_ip2)->i_mode))
 			error = xfs_swapext_dir_to_sf(tp, sxi);
+		else if (S_ISLNK(VFS_I(sxi->sxi_ip2)->i_mode))
+			error = xfs_swapext_link_to_sf(tp, sxi);
 		sxi->sxi_flags &= ~XFS_SWAP_EXT_CVT_INO2_SF;
 		if (error)
 			return error;
@@ -1113,7 +1158,8 @@ xfs_swapext(
 	if (req->req_flags & XFS_SWAP_REQ_CVT_INO2_SF)
 		ASSERT(req->whichfork == XFS_ATTR_FORK ||
 		       (req->whichfork == XFS_DATA_FORK &&
-			S_ISDIR(VFS_I(req->ip2)->i_mode)));
+			(S_ISDIR(VFS_I(req->ip2)->i_mode) ||
+			 S_ISLNK(VFS_I(req->ip2)->i_mode))));
 
 	if (req->blockcount == 0)
 		return;
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c
index 1b8815159702e..c9c50b50d2114 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.c
+++ b/fs/xfs/libxfs/xfs_symlink_remote.c
@@ -380,3 +380,50 @@ xfs_symlink_write_target(
 	ASSERT(pathlen == 0);
 	return 0;
 }
+
+/* Remove all the blocks from a symlink and invalidate buffers. */
+int
+xfs_symlink_remote_truncate(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip)
+{
+	struct xfs_bmbt_irec	mval[XFS_SYMLINK_MAPS];
+	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_buf		*bp;
+	int			nmaps = XFS_SYMLINK_MAPS;
+	int			done = 0;
+	int			i;
+	int			error;
+
+	/* Read mappings and invalidate buffers. */
+	error = xfs_bmapi_read(ip, 0, XFS_MAX_FILEOFF, mval, &nmaps, 0);
+	if (error)
+		return error;
+
+	for (i = 0; i < nmaps; i++) {
+		if (!xfs_bmap_is_real_extent(&mval[i]))
+			break;
+
+		error = xfs_trans_get_buf(tp, mp->m_ddev_targp,
+				XFS_FSB_TO_DADDR(mp, mval[i].br_startblock),
+				XFS_FSB_TO_BB(mp, mval[i].br_blockcount), 0,
+				&bp);
+		if (error)
+			return error;
+
+		xfs_trans_binval(tp, bp);
+	}
+
+	/* Unmap the remote blocks. */
+	error = xfs_bunmapi(tp, ip, 0, XFS_MAX_FILEOFF, 0, nmaps, &done);
+	if (error)
+		return error;
+	if (!done) {
+		ASSERT(done);
+		xfs_inode_mark_sick(ip, XFS_SICK_INO_SYMLINK);
+		return -EFSCORRUPTED;
+	}
+
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+	return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.h b/fs/xfs/libxfs/xfs_symlink_remote.h
index a63bd38ae4faf..ac3dac8f617ed 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.h
+++ b/fs/xfs/libxfs/xfs_symlink_remote.h
@@ -22,5 +22,6 @@ int xfs_symlink_remote_read(struct xfs_inode *ip, char *link);
 int xfs_symlink_write_target(struct xfs_trans *tp, struct xfs_inode *ip,
 		const char *target_path, int pathlen, xfs_fsblock_t fs_blocks,
 		uint resblks);
+int xfs_symlink_remote_truncate(struct xfs_trans *tp, struct xfs_inode *ip);
 
 #endif /* __XFS_SYMLINK_REMOTE_H */
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 2a082749be5cf..06df5522db7a5 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -251,19 +251,12 @@ xfs_symlink(
  */
 STATIC int
 xfs_inactive_symlink_rmt(
-	struct xfs_inode *ip)
+	struct xfs_inode	*ip)
 {
-	struct xfs_buf	*bp;
-	int		done;
-	int		error;
-	int		i;
-	xfs_mount_t	*mp;
-	xfs_bmbt_irec_t	mval[XFS_SYMLINK_MAPS];
-	int		nmaps;
-	int		size;
-	xfs_trans_t	*tp;
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_trans	*tp;
+	int			error;
 
-	mp = ip->i_mount;
 	ASSERT(!xfs_need_iread_extents(&ip->i_df));
 	/*
 	 * We're freeing a symlink that has some
@@ -287,44 +280,14 @@ xfs_inactive_symlink_rmt(
 	 * locked for the second transaction.  In the error paths we need it
 	 * held so the cancel won't rele it, see below.
 	 */
-	size = (int)ip->i_disk_size;
 	ip->i_disk_size = 0;
 	VFS_I(ip)->i_mode = (VFS_I(ip)->i_mode & ~S_IFMT) | S_IFREG;
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-	/*
-	 * Find the block(s) so we can inval and unmap them.
-	 */
-	done = 0;
-	nmaps = ARRAY_SIZE(mval);
-	error = xfs_bmapi_read(ip, 0, xfs_symlink_blocks(mp, size),
-				mval, &nmaps, 0);
-	if (error)
-		goto error_trans_cancel;
-	/*
-	 * Invalidate the block(s). No validation is done.
-	 */
-	for (i = 0; i < nmaps; i++) {
-		error = xfs_trans_get_buf(tp, mp->m_ddev_targp,
-				XFS_FSB_TO_DADDR(mp, mval[i].br_startblock),
-				XFS_FSB_TO_BB(mp, mval[i].br_blockcount), 0,
-				&bp);
-		if (error)
-			goto error_trans_cancel;
-		xfs_trans_binval(tp, bp);
-	}
-	/*
-	 * Unmap the dead block(s) to the dfops.
-	 */
-	error = xfs_bunmapi(tp, ip, 0, size, 0, nmaps, &done);
+
+	error = xfs_symlink_remote_truncate(tp, ip);
 	if (error)
 		goto error_trans_cancel;
-	ASSERT(done);
 
-	/*
-	 * Commit the transaction. This first logs the EFI and the inode, then
-	 * rolls and commits the transaction that frees the extents.
-	 */
-	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 	error = xfs_trans_commit(tp);
 	if (error) {
 		ASSERT(xfs_is_shutdown(mp));

[PATCH 23/25] xfs: make atomic extent swapping support realtime files

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Now that bmap items support the realtime device, we can add the
necessary pieces to the atomic extent swapping code to support such
things.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_swapext.c |  165 ++++++++++++++++++++++++++++++++++++--
 fs/xfs/xfs_bmap_util.c      |  185 +++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_bmap_util.h      |    7 ++
 fs/xfs/xfs_inode.h          |    5 +
 fs/xfs/xfs_trace.h          |   11 ++-
 fs/xfs/xfs_xchgrange.c      |   61 ++++++++++++++
 fs/xfs/xfs_xchgrange.h      |    2 
 7 files changed, 418 insertions(+), 18 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_swapext.c b/fs/xfs/libxfs/xfs_swapext.c
index e84b9ffe9df6b..7e36e136cee0d 100644
--- a/fs/xfs/libxfs/xfs_swapext.c
+++ b/fs/xfs/libxfs/xfs_swapext.c
@@ -31,6 +31,7 @@
 #include "xfs_dir2_priv.h"
 #include "xfs_dir2.h"
 #include "xfs_symlink_remote.h"
+#include "xfs_rtbitmap.h"
 
 struct kmem_cache	*xfs_swapext_intent_cache;
 
@@ -133,6 +134,102 @@ sxi_advance(
 	sxi->sxi_blockcount -= irec->br_blockcount;
 }
 
+#ifdef DEBUG
+/*
+ * If we're going to do a BUI-only extent swap, ensure that all mappings are
+ * aligned to the realtime extent size.
+ */
+static inline int
+xfs_swapext_check_rt_extents(
+	struct xfs_mount		*mp,
+	const struct xfs_swapext_req	*req)
+{
+	struct xfs_bmbt_irec		irec1, irec2;
+	xfs_fileoff_t			startoff1 = req->startoff1;
+	xfs_fileoff_t			startoff2 = req->startoff2;
+	xfs_filblks_t			blockcount = req->blockcount;
+	uint32_t			mod;
+	int				nimaps;
+	int				error;
+
+	/* xattrs don't live on the rt device */
+	if (req->whichfork == XFS_ATTR_FORK)
+		return 0;
+
+	/*
+	 * Caller got permission to use SXI log items, so log recovery will
+	 * finish the swap and not leave us with partially swapped rt extents
+	 * exposed to userspace.
+	 */
+	if (req->req_flags & XFS_SWAP_REQ_LOGGED)
+		return 0;
+
+	/*
+	 * Allocation units must be fully mapped to a file range.  For files
+	 * with a single-fsblock allocation unit, this is trivial.
+	 */
+	if (!xfs_inode_has_bigallocunit(req->ip2))
+		return 0;
+
+	/*
+	 * For multi-fsblock allocation units, we must check the alignment of
+	 * every single mapping.
+	 */
+	while (blockcount > 0) {
+		/* Read extent from the first file */
+		nimaps = 1;
+		error = xfs_bmapi_read(req->ip1, startoff1, blockcount,
+				&irec1, &nimaps, 0);
+		if (error)
+			return error;
+		ASSERT(nimaps == 1);
+
+		/* Read extent from the second file */
+		nimaps = 1;
+		error = xfs_bmapi_read(req->ip2, startoff2,
+				irec1.br_blockcount, &irec2, &nimaps,
+				0);
+		if (error)
+			return error;
+		ASSERT(nimaps == 1);
+
+		/*
+		 * We can only swap as many blocks as the smaller of the two
+		 * extent maps.
+		 */
+		irec1.br_blockcount = min(irec1.br_blockcount,
+					  irec2.br_blockcount);
+
+		/* Both mappings must be aligned to the realtime extent size. */
+		mod = xfs_rtb_to_rtxoff(mp, irec1.br_startoff);
+		if (mod) {
+			ASSERT(mod == 0);
+			return -EINVAL;
+		}
+
+		mod = xfs_rtb_to_rtxoff(mp, irec1.br_startoff);
+		if (mod) {
+			ASSERT(mod == 0);
+			return -EINVAL;
+		}
+
+		mod = xfs_rtb_to_rtxoff(mp, irec1.br_blockcount);
+		if (mod) {
+			ASSERT(mod == 0);
+			return -EINVAL;
+		}
+
+		startoff1 += irec1.br_blockcount;
+		startoff2 += irec1.br_blockcount;
+		blockcount -= irec1.br_blockcount;
+	}
+
+	return 0;
+}
+#else
+# define xfs_swapext_check_rt_extents(mp, req)		(0)
+#endif
+
 /* Check all extents to make sure we can actually swap them. */
 int
 xfs_swapext_check_extents(
@@ -152,12 +249,7 @@ xfs_swapext_check_extents(
 	    ifp2->if_format == XFS_DINODE_FMT_LOCAL)
 		return -EINVAL;
 
-	/* We don't support realtime data forks yet. */
-	if (!XFS_IS_REALTIME_INODE(req->ip1))
-		return 0;
-	if (req->whichfork == XFS_ATTR_FORK)
-		return 0;
-	return -EINVAL;
+	return xfs_swapext_check_rt_extents(mp, req);
 }
 
 #ifdef CONFIG_XFS_QUOTA
@@ -198,6 +290,8 @@ xfs_swapext_can_skip_mapping(
 	struct xfs_swapext_intent	*sxi,
 	struct xfs_bmbt_irec		*irec)
 {
+	struct xfs_mount		*mp = sxi->sxi_ip1->i_mount;
+
 	/* Do not skip this mapping if the caller did not tell us to. */
 	if (!(sxi->sxi_flags & XFS_SWAP_EXT_INO1_WRITTEN))
 		return false;
@@ -210,10 +304,63 @@ xfs_swapext_can_skip_mapping(
 	 * The mapping is unwritten or a hole.  It cannot be a delalloc
 	 * reservation because we already excluded those.  It cannot be an
 	 * unwritten extent with dirty page cache because we flushed the page
-	 * cache.  We don't support realtime files yet, so we needn't (yet)
-	 * deal with them.
+	 * cache.  For files where the allocation unit is 1FSB (files on the
+	 * data dev, rt files if the extent size is 1FSB), we can safely
+	 * skip this mapping.
 	 */
-	return true;
+	if (!xfs_inode_has_bigallocunit(sxi->sxi_ip1))
+		return true;
+
+	/*
+	 * For a realtime file with a multi-fsb allocation unit, the decision
+	 * is trickier because we can only swap full allocation units.
+	 * Unwritten mappings can appear in the middle of an rtx if the rtx is
+	 * partially written, but they can also appear for preallocations.
+	 *
+	 * If the mapping is a hole, skip it entirely.  Holes should align with
+	 * rtx boundaries.
+	 */
+	if (!xfs_bmap_is_real_extent(irec))
+		return true;
+
+	/*
+	 * All mappings below this point are unwritten.
+	 *
+	 * - If the beginning is not aligned to an rtx, trim the end of the
+	 *   mapping so that it does not cross an rtx boundary, and swap it.
+	 *
+	 * - If both ends are aligned to an rtx, skip the entire mapping.
+	 */
+	if (!isaligned_64(irec->br_startoff, mp->m_sb.sb_rextsize)) {
+		xfs_fileoff_t	new_end;
+
+		new_end = roundup_64(irec->br_startoff, mp->m_sb.sb_rextsize);
+		irec->br_blockcount = min(irec->br_blockcount,
+					  new_end - irec->br_startoff);
+		return false;
+	}
+	if (isaligned_64(irec->br_blockcount, mp->m_sb.sb_rextsize))
+		return true;
+
+	/*
+	 * All mappings below this point are unwritten, start on an rtx
+	 * boundary, and do not end on an rtx boundary.
+	 *
+	 * - If the mapping is longer than one rtx, trim the end of the mapping
+	 *   down to an rtx boundary and skip it.
+	 *
+	 * - The mapping is shorter than one rtx.  Swap it.
+	 */
+	if (irec->br_blockcount > mp->m_sb.sb_rextsize) {
+		xfs_fileoff_t	new_end;
+
+		new_end = rounddown_64(irec->br_startoff + irec->br_blockcount,
+				mp->m_sb.sb_rextsize);
+		irec->br_blockcount = new_end - irec->br_startoff;
+		return true;
+	}
+
+	return false;
 }
 
 /*
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 8eab56a62ce24..d1a57164de032 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -684,7 +684,7 @@ xfs_can_free_eofblocks(
 	 * forever.
 	 */
 	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_ISIZE(ip));
-	if (XFS_IS_REALTIME_INODE(ip) && mp->m_sb.sb_rextsize > 1)
+	if (xfs_inode_has_bigallocunit(ip))
 		end_fsb = xfs_rtb_roundup_rtx(mp, end_fsb);
 	last_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
 	if (last_fsb <= end_fsb)
@@ -985,7 +985,7 @@ xfs_free_file_space(
 	endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len);
 
 	/* We can only free complete realtime extents. */
-	if (XFS_IS_REALTIME_INODE(ip) && mp->m_sb.sb_rextsize > 1) {
+	if (xfs_inode_has_bigallocunit(ip)) {
 		startoffset_fsb = xfs_rtb_roundup_rtx(mp, startoffset_fsb);
 		endoffset_fsb = xfs_rtb_rounddown_rtx(mp, endoffset_fsb);
 	}
@@ -1234,3 +1234,184 @@ xfs_insert_file_space(
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 }
+
+#ifdef CONFIG_XFS_RT
+/*
+ * Decide if this is an unwritten extent that isn't aligned to an allocation
+ * unit boundary.
+ *
+ * If it is, shorten the mapping to the end of the allocation unit so that
+ * we're ready to convert all the mappings for this allocation unit to a zeroed
+ * written extent.  If not, return false.
+ */
+static inline bool
+xfs_want_convert_bigalloc_mapping(
+	struct xfs_mount	*mp,
+	struct xfs_bmbt_irec	*irec)
+{
+	xfs_fileoff_t		rext_next;
+	xfs_extlen_t		modoff, modcnt;
+
+	if (irec->br_state != XFS_EXT_UNWRITTEN)
+		return false;
+
+	modoff = xfs_rtb_to_rtxoff(mp, irec->br_startoff);
+	if (modoff == 0) {
+		xfs_rtbxlen_t	rexts;
+
+		rexts = xfs_rtb_to_rtxrem(mp, irec->br_blockcount, &modcnt);
+		if (rexts > 0) {
+			/*
+			 * Unwritten mapping starts at an rt extent boundary
+			 * and is longer than one rt extent.  Round the length
+			 * down to the nearest extent but don't select it for
+			 * conversion.
+			 */
+			irec->br_blockcount -= modcnt;
+			modcnt = 0;
+		}
+
+		/* Unwritten mapping is perfectly aligned, do not convert. */
+		if (modcnt == 0)
+			return false;
+	}
+
+	/*
+	 * Unaligned and unwritten; trim to the current rt extent and select it
+	 * for conversion.
+	 */
+	rext_next = (irec->br_startoff - modoff) + mp->m_sb.sb_rextsize;
+	xfs_trim_extent(irec, irec->br_startoff, rext_next - irec->br_startoff);
+	return true;
+}
+
+/*
+ * Find an unwritten extent in the given file range, zero it, and convert the
+ * mapping to written.  Adjust the scan cursor on the way out.
+ */
+STATIC int
+xfs_convert_bigalloc_mapping(
+	struct xfs_inode	*ip,
+	xfs_fileoff_t		*offp,
+	xfs_fileoff_t		endoff)
+{
+	struct xfs_bmbt_irec	irec;
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_trans	*tp;
+	unsigned int		resblks;
+	int			nmap;
+	int			error;
+
+	resblks = XFS_DIOSTRAT_SPACE_RES(mp, 1);
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
+	if (error)
+		return error;
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, 0);
+
+	/*
+	 * Read the mapping.  If we find an unwritten extent that isn't aligned
+	 * to an allocation unit...
+	 */
+retry:
+	nmap = 1;
+	error = xfs_bmapi_read(ip, *offp, endoff - *offp, &irec, &nmap, 0);
+	if (error)
+		goto out_cancel;
+	ASSERT(nmap == 1);
+	ASSERT(irec.br_startoff == *offp);
+	if (!xfs_want_convert_bigalloc_mapping(mp, &irec)) {
+		*offp = irec.br_startoff + irec.br_blockcount;
+		if (*offp >= endoff)
+			goto out_cancel;
+		goto retry;
+	}
+
+	/*
+	 * ...then write zeroes to the space and change the mapping state to
+	 * written.  This consolidates the mappings for this allocation unit.
+	 */
+	nmap = 1;
+	error = xfs_bmapi_write(tp, ip, irec.br_startoff, irec.br_blockcount,
+			XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO, 0, &irec, &nmap);
+	if (error)
+		goto out_cancel;
+	error = xfs_trans_commit(tp);
+	if (error)
+		goto out_unlock;
+
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+	/*
+	 * If an unwritten mapping was returned, something is very wrong.
+	 * If no mapping was returned, then bmapi_write thought it performed
+	 * a short allocation, which should be impossible since we previously
+	 * queried the mapping and haven't cycled locks since then.  Either
+	 * way, fail the operation.
+	 */
+	if (nmap == 0 || irec.br_state != XFS_EXT_NORM) {
+		ASSERT(nmap != 0);
+		ASSERT(irec.br_state == XFS_EXT_NORM);
+		return -EIO;
+	}
+
+	/* Advance the cursor to the end of the mapping returned. */
+	*offp = irec.br_startoff + irec.br_blockcount;
+	return 0;
+
+out_cancel:
+	xfs_trans_cancel(tp);
+out_unlock:
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	return error;
+}
+
+/*
+ * Prepare a file with multi-fsblock allocation units for a remapping.
+ *
+ * File allocation units (AU) must be fully mapped to the data fork.  If the
+ * space in an AU have not been fully written, there can be multiple extent
+ * mappings (e.g. mixed written and unwritten blocks) to the AU.  If the log
+ * does not have a means to ensure that all remappings for a given AU will be
+ * completed even if the fs goes down, we must maintain the above constraint in
+ * another way.
+ *
+ * Convert the unwritten parts of an AU to written by writing zeroes to the
+ * storage and flipping the mapping.  Once this completes, there will be a
+ * single mapping for the entire AU, and we can proceed with the remapping
+ * operation.
+ *
+ * Callers must ensure that there are no dirty pages in the given range.
+ */
+int
+xfs_convert_bigalloc_file_space(
+	struct xfs_inode	*ip,
+	loff_t			pos,
+	uint64_t		len)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	xfs_fileoff_t		off;
+	xfs_fileoff_t		endoff;
+	int			error;
+
+	if (!xfs_inode_has_bigallocunit(ip))
+		return 0;
+
+	off = xfs_rtb_rounddown_rtx(mp, XFS_B_TO_FSBT(mp, pos));
+	endoff = xfs_rtb_roundup_rtx(mp, XFS_B_TO_FSB(mp, pos + len));
+
+	trace_xfs_convert_bigalloc_file_space(ip, pos, len);
+
+	while (off < endoff) {
+		if (fatal_signal_pending(current))
+			return -EINTR;
+
+		error = xfs_convert_bigalloc_mapping(ip, &off, endoff);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+#endif /* CONFIG_XFS_RT */
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 8eb7166aa9d41..231c4f1629c66 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -76,4 +76,11 @@ int xfs_bmap_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip,
 int	xfs_flush_unmap_range(struct xfs_inode *ip, xfs_off_t offset,
 			      xfs_off_t len);
 
+#ifdef CONFIG_XFS_RT
+int xfs_convert_bigalloc_file_space(struct xfs_inode *ip, loff_t pos,
+		uint64_t len);
+#else
+# define xfs_convert_bigalloc_file_space(ip, pos, len)	(-EOPNOTSUPP)
+#endif
+
 #endif	/* __XFS_BMAP_UTIL_H__ */
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index e1d60ba75bbdd..77acc3177ecea 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -311,6 +311,11 @@ static inline bool xfs_inode_has_large_extent_counts(struct xfs_inode *ip)
 	return ip->i_diflags2 & XFS_DIFLAG2_NREXT64;
 }
 
+static inline bool xfs_inode_has_bigallocunit(struct xfs_inode *ip)
+{
+	return XFS_IS_REALTIME_INODE(ip) && ip->i_mount->m_sb.sb_rextsize > 1;
+}
+
 /*
  * Return the buftarg used for data allocations on a given inode.
  */
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 47c30d8093289..91ec676fcf8ed 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -1494,7 +1494,7 @@ DEFINE_IMAP_EVENT(xfs_iomap_alloc);
 DEFINE_IMAP_EVENT(xfs_iomap_found);
 
 DECLARE_EVENT_CLASS(xfs_simple_io_class,
-	TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count),
+	TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, u64 count),
 	TP_ARGS(ip, offset, count),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -1502,7 +1502,7 @@ DECLARE_EVENT_CLASS(xfs_simple_io_class,
 		__field(loff_t, isize)
 		__field(loff_t, disize)
 		__field(loff_t, offset)
-		__field(size_t, count)
+		__field(u64, count)
 	),
 	TP_fast_assign(
 		__entry->dev = VFS_I(ip)->i_sb->s_dev;
@@ -1513,7 +1513,7 @@ DECLARE_EVENT_CLASS(xfs_simple_io_class,
 		__entry->count = count;
 	),
 	TP_printk("dev %d:%d ino 0x%llx isize 0x%llx disize 0x%llx "
-		  "pos 0x%llx bytecount 0x%zx",
+		  "pos 0x%llx bytecount 0x%llx",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->ino,
 		  __entry->isize,
@@ -1524,7 +1524,7 @@ DECLARE_EVENT_CLASS(xfs_simple_io_class,
 
 #define DEFINE_SIMPLE_IO_EVENT(name)	\
 DEFINE_EVENT(xfs_simple_io_class, name,	\
-	TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count),	\
+	TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, u64 count),	\
 	TP_ARGS(ip, offset, count))
 DEFINE_SIMPLE_IO_EVENT(xfs_delalloc_enospc);
 DEFINE_SIMPLE_IO_EVENT(xfs_unwritten_convert);
@@ -3728,6 +3728,9 @@ TRACE_EVENT(xfs_ioctl_clone,
 /* unshare tracepoints */
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_unshare);
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_unshare_error);
+#ifdef CONFIG_XFS_RT
+DEFINE_SIMPLE_IO_EVENT(xfs_convert_bigalloc_file_space);
+#endif /* CONFIG_XFS_RT */
 
 /* copy on write */
 DEFINE_INODE_IREC_EVENT(xfs_reflink_trim_around_shared);
diff --git a/fs/xfs/xfs_xchgrange.c b/fs/xfs/xfs_xchgrange.c
index c3476e68d6410..fd09a2dfca9b9 100644
--- a/fs/xfs/xfs_xchgrange.c
+++ b/fs/xfs/xfs_xchgrange.c
@@ -27,6 +27,8 @@
 #include "xfs_sb.h"
 #include "xfs_icache.h"
 #include "xfs_log.h"
+#include "xfs_bmap_util.h"
+#include "xfs_rtbitmap.h"
 #include <linux/fsnotify.h>
 
 /*
@@ -403,7 +405,7 @@ xfs_file_xchg_range(
 		priv_flags |= XFS_XCHG_RANGE_LOGGED;
 
 	/* Prepare and then exchange file contents. */
-	error = xfs_xchg_range_prep(file1, file2, fxr);
+	error = xfs_xchg_range_prep(file1, file2, fxr, priv_flags);
 	if (error)
 		goto out_drop_feat;
 
@@ -773,12 +775,46 @@ xfs_swap_extent_forks(
 	return 0;
 }
 
+/*
+ * Do we need to convert partially written extents before a swap?
+ *
+ * There may be partially written rt extents lurking in the ranges to be
+ * swapped.  According to the rules for realtime files with big rt extents, we
+ * must guarantee that a userspace observer (an IO thread, realistically) never
+ * sees multiple physical rt extents mapped to the same logical file rt extent.
+ */
+static bool
+xfs_xchg_range_need_convert_bigalloc(
+	struct xfs_inode		*ip,
+	unsigned int			xchg_flags)
+{
+	/*
+	 * Extent swap log intent (SXI) items take care of this by ensuring
+	 * that we always complete the entire swap operation.  If the caller
+	 * obtained permission to use these log items, no conversion work is
+	 * needed.
+	 */
+	if (xchg_flags & XFS_XCHG_RANGE_LOGGED)
+		return false;
+
+	/*
+	 * If the caller did not get SXI permission but the filesystem is new
+	 * enough to use BUI log items and big rt extents are in play, the only
+	 * way to prevent userspace from seeing partially mapped big rt extents
+	 * in case of a crash midway through remapping a big rt extent is to
+	 * convert all the partially written rt extents before the swap.
+	 */
+	return xfs_swapext_supports_nonatomic(ip->i_mount) &&
+	       xfs_inode_has_bigallocunit(ip);
+}
+
 /* Prepare two files to have their data exchanged. */
 int
 xfs_xchg_range_prep(
 	struct file		*file1,
 	struct file		*file2,
-	struct xfs_exch_range	*fxr)
+	struct xfs_exch_range	*fxr,
+	unsigned int		xchg_flags)
 {
 	struct xfs_inode	*ip1 = XFS_I(file_inode(file1));
 	struct xfs_inode	*ip2 = XFS_I(file_inode(file2));
@@ -842,6 +878,19 @@ xfs_xchg_range_prep(
 			return error;
 	}
 
+	/* Convert unwritten sub-extent mappings if required. */
+	if (xfs_xchg_range_need_convert_bigalloc(ip2, xchg_flags)) {
+		error = xfs_convert_bigalloc_file_space(ip2, fxr->file2_offset,
+				fxr->length);
+		if (error)
+			return error;
+
+		error = xfs_convert_bigalloc_file_space(ip1, fxr->file1_offset,
+				fxr->length);
+		if (error)
+			return error;
+	}
+
 	return 0;
 }
 
@@ -1103,6 +1152,14 @@ xfs_xchg_range(
 	if (xchg_flags & XFS_XCHG_RANGE_LOGGED)
 		req.req_flags |= XFS_SWAP_REQ_LOGGED;
 
+	/*
+	 * Round the request length up to the nearest file allocation unit.
+	 * The prep function already checked that the request offsets and
+	 * length in @fxr are safe to round up.
+	 */
+	if (xfs_inode_has_bigallocunit(ip2))
+		req.blockcount = xfs_rtb_roundup_rtx(mp, req.blockcount);
+
 	error = xfs_xchg_range_estimate(&req);
 	if (error)
 		return error;
diff --git a/fs/xfs/xfs_xchgrange.h b/fs/xfs/xfs_xchgrange.h
index 3471182d1402f..5ca902b11c2e9 100644
--- a/fs/xfs/xfs_xchgrange.h
+++ b/fs/xfs/xfs_xchgrange.h
@@ -51,6 +51,6 @@ void xfs_xchg_range_rele_log_assist(struct xfs_mount *mp);
 int xfs_xchg_range(struct xfs_inode *ip1, struct xfs_inode *ip2,
 		const struct xfs_exch_range *fxr, unsigned int xchg_flags);
 int xfs_xchg_range_prep(struct file *file1, struct file *file2,
-		struct xfs_exch_range *fxr);
+		struct xfs_exch_range *fxr, unsigned int xchg_flags);
 
 #endif /* __XFS_XCHGRANGE_H__ */

[PATCH 24/25] xfs: support non-power-of-two rtextsize with exchange-range

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

The VFS exchange-range alignment checks use (fast) bitmasks to perform
block alignment checks on the exchange parameters.  Unfortunately,
bitmasks require that the alignment size be a power of two.  This isn't
true for realtime devices, so we have to copy-pasta the VFS checks using
long division for this to work properly.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_xchgrange.c |  102 +++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 91 insertions(+), 11 deletions(-)


diff --git a/fs/xfs/xfs_xchgrange.c b/fs/xfs/xfs_xchgrange.c
index fd09a2dfca9b9..d805678e946c1 100644
--- a/fs/xfs/xfs_xchgrange.c
+++ b/fs/xfs/xfs_xchgrange.c
@@ -808,6 +808,86 @@ xfs_xchg_range_need_convert_bigalloc(
 	       xfs_inode_has_bigallocunit(ip);
 }
 
+/*
+ * Check the alignment of an exchange request when the allocation unit size
+ * isn't a power of two.  The VFS helpers use (fast) bitmask-based alignment
+ * checks, but here we have to use slow long division.
+ */
+static int
+xfs_xchg_range_check_rtalign(
+	struct xfs_inode		*ip1,
+	struct xfs_inode		*ip2,
+	const struct xfs_exch_range	*fxr)
+{
+	struct xfs_mount		*mp = ip1->i_mount;
+	uint32_t			rextbytes;
+	uint64_t			length = fxr->length;
+	uint64_t			blen;
+	loff_t				size1, size2;
+
+	rextbytes = XFS_FSB_TO_B(mp, mp->m_sb.sb_rextsize);
+	size1 = i_size_read(VFS_I(ip1));
+	size2 = i_size_read(VFS_I(ip2));
+
+	/* The start of both ranges must be aligned to a rt extent. */
+	if (!isaligned_64(fxr->file1_offset, rextbytes) ||
+	    !isaligned_64(fxr->file2_offset, rextbytes))
+		return -EINVAL;
+
+	/*
+	 * If the caller asked for full files, check that the offset/length
+	 * values cover all of both files.
+	 */
+	if ((fxr->flags & XFS_EXCH_RANGE_FULL_FILES) &&
+	    (fxr->file1_offset != 0 || fxr->file2_offset != 0 ||
+	     fxr->length != size1 || fxr->length != size2))
+		return -EDOM;
+
+	if (fxr->flags & XFS_EXCH_RANGE_TO_EOF)
+		length = max_t(int64_t, size1 - fxr->file1_offset,
+					size2 - fxr->file2_offset);
+
+	/*
+	 * If the user wanted us to exchange up to the infile's EOF, round up
+	 * to the next rt extent boundary for this check.  Do the same for the
+	 * outfile.
+	 *
+	 * Otherwise, reject the range length if it's not rt extent aligned.
+	 * We already confirmed the starting offsets' rt extent block
+	 * alignment.
+	 */
+	if (fxr->file1_offset + length == size1)
+		blen = roundup_64(size1, rextbytes) - fxr->file1_offset;
+	else if (fxr->file2_offset + length == size2)
+		blen = roundup_64(size2, rextbytes) - fxr->file2_offset;
+	else if (!isaligned_64(length, rextbytes))
+		return -EINVAL;
+	else
+		blen = length;
+
+	/* Don't allow overlapped exchanges within the same file. */
+	if (ip1 == ip2 &&
+	    fxr->file2_offset + blen > fxr->file1_offset &&
+	    fxr->file1_offset + blen > fxr->file2_offset)
+		return -EINVAL;
+
+	/*
+	 * Ensure that we don't exchange a partial EOF rt extent into the
+	 * middle of another file.
+	 */
+	if (isaligned_64(length, rextbytes))
+		return 0;
+
+	blen = length;
+	if (fxr->file2_offset + length < size2)
+		blen = rounddown_64(blen, rextbytes);
+
+	if (fxr->file1_offset + blen < size1)
+		blen = rounddown_64(blen, rextbytes);
+
+	return blen == length ? 0 : -EINVAL;
+}
+
 /* Prepare two files to have their data exchanged. */
 int
 xfs_xchg_range_prep(
@@ -818,6 +898,7 @@ xfs_xchg_range_prep(
 {
 	struct xfs_inode	*ip1 = XFS_I(file_inode(file1));
 	struct xfs_inode	*ip2 = XFS_I(file_inode(file2));
+	unsigned int		alloc_unit = xfs_inode_alloc_unitsize(ip2);
 	int			error;
 
 	trace_xfs_xchg_range_prep(ip1, fxr, ip2, 0);
@@ -826,18 +907,17 @@ xfs_xchg_range_prep(
 	if (XFS_IS_REALTIME_INODE(ip1) != XFS_IS_REALTIME_INODE(ip2))
 		return -EINVAL;
 
-	/*
-	 * The alignment checks in the VFS helpers cannot deal with allocation
-	 * units that are not powers of 2.  This can happen with the realtime
-	 * volume if the extent size is set.  Note that alignment checks are
-	 * skipped if FULL_FILES is set.
-	 */
-	if (!(fxr->flags & XFS_EXCH_RANGE_FULL_FILES) &&
-	    !is_power_of_2(xfs_inode_alloc_unitsize(ip2)))
-		return -EOPNOTSUPP;
+	/* Check non-power of two alignment issues, if necessary. */
+	if (XFS_IS_REALTIME_INODE(ip2) && !is_power_of_2(alloc_unit)) {
+		error = xfs_xchg_range_check_rtalign(ip1, ip2, fxr);
+		if (error)
+			return error;
 
-	error = xfs_exch_range_prep(file1, file2, fxr,
-			xfs_inode_alloc_unitsize(ip2));
+		/* Do the VFS checks with the regular block alignment. */
+		alloc_unit = ip1->i_mount->m_sb.sb_blocksize;
+	}
+
+	error = xfs_exch_range_prep(file1, file2, fxr, alloc_unit);
 	if (error || fxr->length == 0)
 		return error;
 

[PATCH 25/25] xfs: enable atomic swapext feature

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add the atomic swapext feature to the set of features that we will
permit.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_format.h |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)


diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 8b34754a5794e..7861539ab8b68 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -398,7 +398,8 @@ xfs_sb_has_incompat_feature(
  */
 #define XFS_SB_FEAT_INCOMPAT_LOG_SWAPEXT  (1U << 31)
 #define XFS_SB_FEAT_INCOMPAT_LOG_ALL \
-	(XFS_SB_FEAT_INCOMPAT_LOG_XATTRS)
+		(XFS_SB_FEAT_INCOMPAT_LOG_XATTRS | \
+		 XFS_SB_FEAT_INCOMPAT_LOG_SWAPEXT)
 #define XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN	~XFS_SB_FEAT_INCOMPAT_LOG_ALL
 static inline bool
 xfs_sb_has_incompat_log_feature(

[PATCH 1/4] xfs: hide private inodes from bulkstat and handle functions

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

We're about to start adding functionality that uses internal inodes that
are private to XFS.  What this means is that userspace should never be
able to access any information about these files, and should not be able
to open these files by handle.  Callers are not allowed to link these
files into the directory tree, which should suffice to make these
private inodes actually private.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_export.c |    2 +-
 fs/xfs/xfs_itable.c |    8 ++++++++
 2 files changed, 9 insertions(+), 1 deletion(-)


diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c
index 7cd09c3a82cb5..4b03221351c0f 100644
--- a/fs/xfs/xfs_export.c
+++ b/fs/xfs/xfs_export.c
@@ -160,7 +160,7 @@ xfs_nfs_get_inode(
 		}
 	}
 
-	if (VFS_I(ip)->i_generation != generation) {
+	if (VFS_I(ip)->i_generation != generation || IS_PRIVATE(VFS_I(ip))) {
 		xfs_irele(ip);
 		return ERR_PTR(-ESTALE);
 	}
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 14462614fcc8d..4610660f267e6 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -97,6 +97,14 @@ xfs_bulkstat_one_int(
 	vfsuid = i_uid_into_vfsuid(idmap, inode);
 	vfsgid = i_gid_into_vfsgid(idmap, inode);
 
+	/* If this is a private inode, don't leak its details to userspace. */
+	if (IS_PRIVATE(inode)) {
+		xfs_iunlock(ip, XFS_ILOCK_SHARED);
+		xfs_irele(ip);
+		error = -EINVAL;
+		goto out_advance;
+	}
+
 	/* xfs_iget returns the following without needing
 	 * further change.
 	 */

[PATCH 2/4] xfs: create temporary files and directories for online repair

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Teach the online repair code how to create temporary files or
directories.  These temporary files can be used to stage reconstructed
information until we're ready to perform an atomic extent swap to commit
the new metadata.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Makefile         |    1 
 fs/xfs/scrub/parent.c   |    2 
 fs/xfs/scrub/scrub.c    |    3 +
 fs/xfs/scrub/scrub.h    |    4 +
 fs/xfs/scrub/tempfile.c |  251 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/tempfile.h |   28 +++++
 fs/xfs/scrub/trace.h    |   33 ++++++
 fs/xfs/xfs_inode.c      |    3 -
 fs/xfs/xfs_inode.h      |    2 
 9 files changed, 324 insertions(+), 3 deletions(-)
 create mode 100644 fs/xfs/scrub/tempfile.c
 create mode 100644 fs/xfs/scrub/tempfile.h


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 7e4e7b5e8a81d..9ce43c3037d2c 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -207,6 +207,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   refcount_repair.o \
 				   repair.o \
 				   rmap_repair.o \
+				   tempfile.o \
 				   xfbtree.o \
 				   )
 
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index 7db8736721461..5da10ed1fe8ce 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -143,7 +143,7 @@ xchk_parent_validate(
 	}
 	if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
 		return error;
-	if (dp == sc->ip || !S_ISDIR(VFS_I(dp)->i_mode)) {
+	if (dp == sc->ip || dp == sc->tempip || !S_ISDIR(VFS_I(dp)->i_mode)) {
 		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out_rele;
 	}
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 2075bfd83e3dc..51bcb21325cd3 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -17,6 +17,7 @@
 #include "xfs_scrub.h"
 #include "xfs_buf_xfile.h"
 #include "xfs_rmap.h"
+#include "xfs_xchgrange.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
@@ -24,6 +25,7 @@
 #include "scrub/health.h"
 #include "scrub/stats.h"
 #include "scrub/xfile.h"
+#include "scrub/tempfile.h"
 
 /*
  * Online Scrub and Repair
@@ -211,6 +213,7 @@ xchk_teardown(
 		sc->buf = NULL;
 	}
 
+	xrep_tempfile_rele(sc);
 	xchk_fsgates_disable(sc);
 	return error;
 }
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index 165cef0b1d25a..5f0e8e350295e 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -105,6 +105,10 @@ struct xfs_scrub {
 	/* Lock flags for @ip. */
 	uint				ilock_flags;
 
+	/* A temporary file on this filesystem, for staging new metadata. */
+	struct xfs_inode		*tempip;
+	uint				temp_ilock_flags;
+
 	/* See the XCHK/XREP state flags below. */
 	unsigned int			flags;
 
diff --git a/fs/xfs/scrub/tempfile.c b/fs/xfs/scrub/tempfile.c
new file mode 100644
index 0000000000000..5f4a931b1967c
--- /dev/null
+++ b/fs/xfs/scrub/tempfile.c
@@ -0,0 +1,251 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2021-2024 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_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_inode.h"
+#include "xfs_ialloc.h"
+#include "xfs_quota.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_trans_space.h"
+#include "xfs_dir2.h"
+#include "xfs_xchgrange.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/tempfile.h"
+
+/*
+ * Create a temporary file for reconstructing metadata, with the intention of
+ * atomically swapping the temporary file's contents with the file that's
+ * being repaired.
+ */
+int
+xrep_tempfile_create(
+	struct xfs_scrub	*sc,
+	uint16_t		mode)
+{
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_trans	*tp = NULL;
+	struct xfs_dquot	*udqp = NULL;
+	struct xfs_dquot	*gdqp = NULL;
+	struct xfs_dquot	*pdqp = NULL;
+	struct xfs_trans_res	*tres;
+	struct xfs_inode	*dp = mp->m_rootip;
+	xfs_ino_t		ino;
+	unsigned int		resblks;
+	bool			is_dir = S_ISDIR(mode);
+	int			error;
+
+	if (xfs_is_shutdown(mp))
+		return -EIO;
+	if (xfs_is_readonly(mp))
+		return -EROFS;
+
+	ASSERT(sc->tp == NULL);
+	ASSERT(sc->tempip == NULL);
+
+	/*
+	 * Make sure that we have allocated dquot(s) on disk.  The temporary
+	 * inode should be completely root owned so that we don't fail due to
+	 * quota limits.
+	 */
+	error = xfs_qm_vop_dqalloc(dp, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, 0,
+			XFS_QMOPT_QUOTALL, &udqp, &gdqp, &pdqp);
+	if (error)
+		return error;
+
+	if (is_dir) {
+		resblks = XFS_MKDIR_SPACE_RES(mp, 0);
+		tres = &M_RES(mp)->tr_mkdir;
+	} else {
+		resblks = XFS_IALLOC_SPACE_RES(mp);
+		tres = &M_RES(mp)->tr_create_tmpfile;
+	}
+
+	error = xfs_trans_alloc_icreate(mp, tres, udqp, gdqp, pdqp, resblks,
+			&tp);
+	if (error)
+		goto out_release_dquots;
+
+	/* Allocate inode, set up directory. */
+	error = xfs_dialloc(&tp, dp->i_ino, mode, &ino);
+	if (error)
+		goto out_trans_cancel;
+	error = xfs_init_new_inode(&nop_mnt_idmap, tp, dp, ino, mode, 0, 0,
+			0, false, &sc->tempip);
+	if (error)
+		goto out_trans_cancel;
+
+	/* Change the ownership of the inode to root. */
+	VFS_I(sc->tempip)->i_uid = GLOBAL_ROOT_UID;
+	VFS_I(sc->tempip)->i_gid = GLOBAL_ROOT_GID;
+	sc->tempip->i_diflags &= ~(XFS_DIFLAG_REALTIME | XFS_DIFLAG_RTINHERIT);
+	xfs_trans_log_inode(tp, sc->tempip, XFS_ILOG_CORE);
+
+	/*
+	 * Mark our temporary file as private so that LSMs and the ACL code
+	 * don't try to add their own metadata or reason about these files.
+	 * The file should never be exposed to userspace.
+	 */
+	VFS_I(sc->tempip)->i_flags |= S_PRIVATE;
+	VFS_I(sc->tempip)->i_opflags &= ~IOP_XATTR;
+
+	if (is_dir) {
+		error = xfs_dir_init(tp, sc->tempip, dp);
+		if (error)
+			goto out_trans_cancel;
+	}
+
+	/*
+	 * Attach the dquot(s) to the inodes and modify them incore.
+	 * These ids of the inode couldn't have changed since the new
+	 * inode has been locked ever since it was created.
+	 */
+	xfs_qm_vop_create_dqattach(tp, sc->tempip, udqp, gdqp, pdqp);
+
+	/*
+	 * Put our temp file on the unlinked list so it's purged automatically.
+	 * Anything being reconstructed using this file must be atomically
+	 * swapped with the original file because the contents here will be
+	 * purged when the inode is dropped or log recovery cleans out the
+	 * unlinked list.
+	 */
+	error = xfs_iunlink(tp, sc->tempip);
+	if (error)
+		goto out_trans_cancel;
+
+	error = xfs_trans_commit(tp);
+	if (error)
+		goto out_release_inode;
+
+	trace_xrep_tempfile_create(sc);
+
+	xfs_qm_dqrele(udqp);
+	xfs_qm_dqrele(gdqp);
+	xfs_qm_dqrele(pdqp);
+
+	/* Finish setting up the incore / vfs context. */
+	xfs_setup_iops(sc->tempip);
+	xfs_finish_inode_setup(sc->tempip);
+
+	sc->temp_ilock_flags = 0;
+	return error;
+
+out_trans_cancel:
+	xfs_trans_cancel(tp);
+out_release_inode:
+	/*
+	 * Wait until after the current transaction is aborted to finish the
+	 * setup of the inode and release the inode.  This prevents recursive
+	 * transactions and deadlocks from xfs_inactive.
+	 */
+	if (sc->tempip) {
+		xfs_finish_inode_setup(sc->tempip);
+		xchk_irele(sc, sc->tempip);
+	}
+out_release_dquots:
+	xfs_qm_dqrele(udqp);
+	xfs_qm_dqrele(gdqp);
+	xfs_qm_dqrele(pdqp);
+
+	return error;
+}
+
+/* Take IOLOCK_EXCL on the temporary file, maybe. */
+bool
+xrep_tempfile_iolock_nowait(
+	struct xfs_scrub	*sc)
+{
+	if (xfs_ilock_nowait(sc->tempip, XFS_IOLOCK_EXCL)) {
+		sc->temp_ilock_flags |= XFS_IOLOCK_EXCL;
+		return true;
+	}
+
+	return false;
+}
+
+/*
+ * Take the temporary file's IOLOCK while holding a different inode's IOLOCK.
+ * In theory nobody else should hold the tempfile's IOLOCK, but we use trylock
+ * to avoid deadlocks and lockdep complaints.
+ */
+int
+xrep_tempfile_iolock_polled(
+	struct xfs_scrub	*sc)
+{
+	int			error = 0;
+
+	while (!xrep_tempfile_iolock_nowait(sc)) {
+		if (xchk_should_terminate(sc, &error))
+			return error;
+		delay(1);
+	}
+
+	return 0;
+}
+
+/* Release IOLOCK_EXCL on the temporary file. */
+void
+xrep_tempfile_iounlock(
+	struct xfs_scrub	*sc)
+{
+	xfs_iunlock(sc->tempip, XFS_IOLOCK_EXCL);
+	sc->temp_ilock_flags &= ~XFS_IOLOCK_EXCL;
+}
+
+/* Prepare the temporary file for metadata updates by grabbing ILOCK_EXCL. */
+void
+xrep_tempfile_ilock(
+	struct xfs_scrub	*sc)
+{
+	sc->temp_ilock_flags |= XFS_ILOCK_EXCL;
+	xfs_ilock(sc->tempip, XFS_ILOCK_EXCL);
+}
+
+/* Try to grab ILOCK_EXCL on the temporary file. */
+bool
+xrep_tempfile_ilock_nowait(
+	struct xfs_scrub	*sc)
+{
+	if (xfs_ilock_nowait(sc->tempip, XFS_ILOCK_EXCL)) {
+		sc->temp_ilock_flags |= XFS_ILOCK_EXCL;
+		return true;
+	}
+
+	return false;
+}
+
+/* Unlock ILOCK_EXCL on the temporary file after an update. */
+void
+xrep_tempfile_iunlock(
+	struct xfs_scrub	*sc)
+{
+	xfs_iunlock(sc->tempip, XFS_ILOCK_EXCL);
+	sc->temp_ilock_flags &= ~XFS_ILOCK_EXCL;
+}
+
+/* Release the temporary file. */
+void
+xrep_tempfile_rele(
+	struct xfs_scrub	*sc)
+{
+	if (!sc->tempip)
+		return;
+
+	if (sc->temp_ilock_flags) {
+		xfs_iunlock(sc->tempip, sc->temp_ilock_flags);
+		sc->temp_ilock_flags = 0;
+	}
+
+	xchk_irele(sc, sc->tempip);
+	sc->tempip = NULL;
+}
diff --git a/fs/xfs/scrub/tempfile.h b/fs/xfs/scrub/tempfile.h
new file mode 100644
index 0000000000000..e165e0a3faf63
--- /dev/null
+++ b/fs/xfs/scrub/tempfile.h
@@ -0,0 +1,28 @@
+// 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_TEMPFILE_H__
+#define __XFS_SCRUB_TEMPFILE_H__
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+int xrep_tempfile_create(struct xfs_scrub *sc, uint16_t mode);
+void xrep_tempfile_rele(struct xfs_scrub *sc);
+
+bool xrep_tempfile_iolock_nowait(struct xfs_scrub *sc);
+int xrep_tempfile_iolock_polled(struct xfs_scrub *sc);
+void xrep_tempfile_iounlock(struct xfs_scrub *sc);
+
+void xrep_tempfile_ilock(struct xfs_scrub *sc);
+bool xrep_tempfile_ilock_nowait(struct xfs_scrub *sc);
+void xrep_tempfile_iunlock(struct xfs_scrub *sc);
+#else
+static inline void xrep_tempfile_iolock_both(struct xfs_scrub *sc)
+{
+	xchk_ilock(sc, XFS_IOLOCK_EXCL);
+}
+# define xrep_tempfile_rele(sc)
+#endif /* CONFIG_XFS_ONLINE_REPAIR */
+
+#endif /* __XFS_SCRUB_TEMPFILE_H__ */
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index e8f71179e1eab..00f906e50c341 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -2361,6 +2361,39 @@ TRACE_EVENT(xrep_rmap_live_update,
 		  __entry->flags)
 );
 
+TRACE_EVENT(xrep_tempfile_create,
+	TP_PROTO(struct xfs_scrub *sc),
+	TP_ARGS(sc),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(unsigned int, type)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_ino_t, inum)
+		__field(unsigned int, gen)
+		__field(unsigned int, flags)
+		__field(xfs_ino_t, temp_inum)
+	),
+	TP_fast_assign(
+		__entry->dev = sc->mp->m_super->s_dev;
+		__entry->ino = sc->file ? XFS_I(file_inode(sc->file))->i_ino : 0;
+		__entry->type = sc->sm->sm_type;
+		__entry->agno = sc->sm->sm_agno;
+		__entry->inum = sc->sm->sm_ino;
+		__entry->gen = sc->sm->sm_gen;
+		__entry->flags = sc->sm->sm_flags;
+		__entry->temp_inum = sc->tempip->i_ino;
+	),
+	TP_printk("dev %d:%d ino 0x%llx type %s inum 0x%llx gen 0x%x flags 0x%x temp_inum 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __print_symbolic(__entry->type, XFS_SCRUB_TYPE_STRINGS),
+		  __entry->inum,
+		  __entry->gen,
+		  __entry->flags,
+		  __entry->temp_inum)
+);
+
 #endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
 
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 15668dbc5ca9e..70705e2e30f79 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -42,7 +42,6 @@
 
 struct kmem_cache *xfs_inode_cache;
 
-STATIC int xfs_iunlink(struct xfs_trans *, struct xfs_inode *);
 STATIC int xfs_iunlink_remove(struct xfs_trans *tp, struct xfs_perag *pag,
 	struct xfs_inode *);
 
@@ -2153,7 +2152,7 @@ xfs_iunlink_insert_inode(
  * We place the on-disk inode on a list in the AGI.  It will be pulled from this
  * list when the inode is freed.
  */
-STATIC int
+int
 xfs_iunlink(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*ip)
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 77acc3177ecea..b6f10ea725857 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -612,6 +612,8 @@ extern struct kmem_cache	*xfs_inode_cache;
 
 bool xfs_inode_needs_inactive(struct xfs_inode *ip);
 
+int xfs_iunlink(struct xfs_trans *tp, struct xfs_inode *ip);
+
 void xfs_end_io(struct work_struct *work);
 
 int xfs_ilock2_io_mmap(struct xfs_inode *ip1, struct xfs_inode *ip2);

[PATCH 3/4] xfs: refactor live buffer invalidation for repairs

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

In an upcoming patch, we will need to be able to look for xfs_buf
objects caching file-based metadata blocks without needing to walk the
(possibly corrupt) structures to find all the buffers.  Repair already
has most of the code needed to scan the buffer cache, so hoist these
utility functions.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/reap.c |   73 ++++++++++++++++++++++++++++++++++++---------------
 fs/xfs/scrub/reap.h |   20 ++++++++++++++
 2 files changed, 71 insertions(+), 22 deletions(-)


diff --git a/fs/xfs/scrub/reap.c b/fs/xfs/scrub/reap.c
index 0252a3b5b65ac..7ae6253395e72 100644
--- a/fs/xfs/scrub/reap.c
+++ b/fs/xfs/scrub/reap.c
@@ -211,6 +211,48 @@ static inline void xreap_defer_finish_reset(struct xreap_state *rs)
 	rs->force_roll = false;
 }
 
+/*
+ * Compute the maximum length of a buffer cache scan (in units of sectors),
+ * given a quantity of fs blocks.
+ */
+xfs_daddr_t
+xrep_bufscan_max_sectors(
+	struct xfs_mount	*mp,
+	xfs_extlen_t		fsblocks)
+{
+	int			max_fsbs;
+
+	/* Remote xattr values are the largest buffers that we support. */
+	max_fsbs = xfs_attr3_rmt_blocks(mp, XFS_XATTR_SIZE_MAX);
+
+	return XFS_FSB_TO_BB(mp, min_t(xfs_extlen_t, fsblocks, max_fsbs));
+}
+
+/*
+ * Return an incore buffer from a sector scan, or NULL if there are no buffers
+ * left to return.
+ */
+struct xfs_buf *
+xrep_bufscan_advance(
+	struct xfs_mount	*mp,
+	struct xrep_bufscan	*scan)
+{
+	scan->__sector_count += scan->daddr_step;
+	while (scan->__sector_count <= scan->max_sectors) {
+		struct xfs_buf	*bp = NULL;
+		int		error;
+
+		error = xfs_buf_incore(mp->m_ddev_targp, scan->daddr,
+				scan->__sector_count, XBF_LIVESCAN, &bp);
+		if (!error)
+			return bp;
+
+		scan->__sector_count += scan->daddr_step;
+	}
+
+	return NULL;
+}
+
 /* Try to invalidate the incore buffers for an extent that we're freeing. */
 STATIC void
 xreap_agextent_binval(
@@ -241,28 +283,15 @@ xreap_agextent_binval(
 	 * of any plausible size.
 	 */
 	while (bno < agbno_next) {
-		xfs_agblock_t	fsbcount;
-		xfs_agblock_t	max_fsbs;
-
-		/*
-		 * Max buffer size is the max remote xattr buffer size, which
-		 * is one fs block larger than 64k.
-		 */
-		max_fsbs = min_t(xfs_agblock_t, agbno_next - bno,
-				xfs_attr3_rmt_blocks(mp, XFS_XATTR_SIZE_MAX));
-
-		for (fsbcount = 1; fsbcount <= max_fsbs; fsbcount++) {
-			struct xfs_buf	*bp = NULL;
-			xfs_daddr_t	daddr;
-			int		error;
-
-			daddr = XFS_AGB_TO_DADDR(mp, agno, bno);
-			error = xfs_buf_incore(mp->m_ddev_targp, daddr,
-					XFS_FSB_TO_BB(mp, fsbcount),
-					XBF_LIVESCAN, &bp);
-			if (error)
-				continue;
-
+		struct xrep_bufscan	scan = {
+			.daddr		= XFS_AGB_TO_DADDR(mp, agno, bno),
+			.max_sectors	= xrep_bufscan_max_sectors(mp,
+							agbno_next - bno),
+			.daddr_step	= XFS_FSB_TO_BB(mp, 1),
+		};
+		struct xfs_buf	*bp;
+
+		while ((bp = xrep_bufscan_advance(mp, &scan)) != NULL) {
 			xfs_trans_bjoin(sc->tp, bp);
 			xfs_trans_binval(sc->tp, bp);
 			rs->invalidated++;
diff --git a/fs/xfs/scrub/reap.h b/fs/xfs/scrub/reap.h
index 0b69f16dd98f9..bb09e21fcb172 100644
--- a/fs/xfs/scrub/reap.h
+++ b/fs/xfs/scrub/reap.h
@@ -14,4 +14,24 @@ int xrep_reap_agblocks(struct xfs_scrub *sc, struct xagb_bitmap *bitmap,
 int xrep_reap_fsblocks(struct xfs_scrub *sc, struct xfsb_bitmap *bitmap,
 		const struct xfs_owner_info *oinfo);
 
+/* Buffer cache scan context. */
+struct xrep_bufscan {
+	/* Disk address for the buffers we want to scan. */
+	xfs_daddr_t		daddr;
+
+	/* Maximum number of sectors to scan. */
+	xfs_daddr_t		max_sectors;
+
+	/* Each round, increment the search length by this number of sectors. */
+	xfs_daddr_t		daddr_step;
+
+	/* Internal scan state; initialize to zero. */
+	xfs_daddr_t		__sector_count;
+};
+
+xfs_daddr_t xrep_bufscan_max_sectors(struct xfs_mount *mp,
+		xfs_extlen_t fsblocks);
+struct xfs_buf *xrep_bufscan_advance(struct xfs_mount *mp,
+		struct xrep_bufscan *scan);
+
 #endif /* __XFS_SCRUB_REAP_H__ */

[PATCH 4/4] xfs: add the ability to reap entire inode forks

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

In preparation for supporting repair of indexed file-based metadata
(such as realtime bitmaps, directories, and extended attribute data),
add a function to reap the old blocks after a metadata repair finishes.
IOWs, this is an elaborate bunmapi call that deals with crosslinked
blocks by unmapping them without freeing them, and also scans for incore
buffers to invalidate.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/reap.c  |  372 ++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/reap.h  |    1 
 fs/xfs/scrub/trace.h |   63 ++++++++
 3 files changed, 436 insertions(+)


diff --git a/fs/xfs/scrub/reap.c b/fs/xfs/scrub/reap.c
index 7ae6253395e72..01ceaa4efa16b 100644
--- a/fs/xfs/scrub/reap.c
+++ b/fs/xfs/scrub/reap.c
@@ -675,3 +675,375 @@ xrep_reap_fsblocks(
 
 	return 0;
 }
+
+/*
+ * Metadata files are not supposed to share blocks with anything else.
+ * If blocks are shared, we remove the reverse mapping (thus reducing the
+ * crosslink factor); if blocks are not shared, we also need to free them.
+ *
+ * This first step determines the longest subset of the passed-in imap
+ * (starting at its beginning) that is either crosslinked or not crosslinked.
+ * The blockcount will be adjust down as needed.
+ */
+STATIC int
+xreap_bmapi_select(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip,
+	int			whichfork,
+	struct xfs_bmbt_irec	*imap,
+	bool			*crosslinked)
+{
+	struct xfs_owner_info	oinfo;
+	struct xfs_btree_cur	*cur;
+	xfs_filblks_t		len = 1;
+	xfs_agblock_t		bno;
+	xfs_agblock_t		agbno;
+	xfs_agblock_t		agbno_next;
+	int			error;
+
+	agbno = XFS_FSB_TO_AGBNO(sc->mp, imap->br_startblock);
+	agbno_next = agbno + imap->br_blockcount;
+
+	cur = xfs_rmapbt_init_cursor(sc->mp, sc->tp, sc->sa.agf_bp,
+			sc->sa.pag);
+
+	xfs_rmap_ino_owner(&oinfo, ip->i_ino, whichfork, imap->br_startoff);
+	error = xfs_rmap_has_other_keys(cur, agbno, 1, &oinfo, crosslinked);
+	if (error)
+		goto out_cur;
+
+	bno = agbno + 1;
+	while (bno < agbno_next) {
+		bool		also_crosslinked;
+
+		oinfo.oi_offset++;
+		error = xfs_rmap_has_other_keys(cur, bno, 1, &oinfo,
+				&also_crosslinked);
+		if (error)
+			goto out_cur;
+
+		if (also_crosslinked != *crosslinked)
+			break;
+
+		len++;
+		bno++;
+	}
+
+	imap->br_blockcount = len;
+	trace_xreap_bmapi_select(sc->sa.pag, agbno, len, *crosslinked);
+out_cur:
+	xfs_btree_del_cursor(cur, error);
+	return error;
+}
+
+/*
+ * Decide if this buffer can be joined to a transaction.  This is true for most
+ * buffers, but there are two cases that we want to catch: large remote xattr
+ * value buffers are not logged and can overflow the buffer log item dirty
+ * bitmap size; and oversized cached buffers if things have really gone
+ * haywire.
+ */
+static inline bool
+xreap_buf_loggable(
+	const struct xfs_buf	*bp)
+{
+	int			i;
+
+	for (i = 0; i < bp->b_map_count; i++) {
+		int		chunks;
+		int		map_size;
+
+		chunks = DIV_ROUND_UP(BBTOB(bp->b_maps[i].bm_len),
+				XFS_BLF_CHUNK);
+		map_size = DIV_ROUND_UP(chunks, NBWORD);
+		if (map_size > XFS_BLF_DATAMAP_SIZE)
+			return false;
+	}
+
+	return true;
+}
+
+/*
+ * Invalidate any buffers for this file mapping.  The @imap blockcount may be
+ * adjusted downward if we need to roll the transaction.
+ */
+STATIC int
+xreap_bmapi_binval(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip,
+	int			whichfork,
+	struct xfs_bmbt_irec	*imap)
+{
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_perag	*pag = sc->sa.pag;
+	int			bmap_flags = xfs_bmapi_aflag(whichfork);
+	xfs_fileoff_t		off;
+	xfs_fileoff_t		max_off;
+	xfs_extlen_t		scan_blocks;
+	xfs_agnumber_t		agno = sc->sa.pag->pag_agno;
+	xfs_agblock_t		bno;
+	xfs_agblock_t		agbno;
+	xfs_agblock_t		agbno_next;
+	unsigned int		invalidated = 0;
+	int			error;
+
+	/*
+	 * Avoid invalidating AG headers and post-EOFS blocks because we never
+	 * own those.
+	 */
+	agbno = bno = XFS_FSB_TO_AGBNO(sc->mp, imap->br_startblock);
+	agbno_next = agbno + imap->br_blockcount;
+	if (!xfs_verify_agbno(pag, agbno) ||
+	    !xfs_verify_agbno(pag, agbno_next - 1))
+		return 0;
+
+	/*
+	 * Buffers for file blocks can span multiple contiguous mappings.  This
+	 * means that for each block in the mapping, there could exist an
+	 * xfs_buf indexed by that block with any length up to the maximum
+	 * buffer size (remote xattr values) or to the next hole in the fork.
+	 * To set up our binval scan, first we need to figure out the location
+	 * of the next hole.
+	 */
+	off = imap->br_startoff + imap->br_blockcount;
+	max_off = off + xfs_attr3_rmt_blocks(mp, XFS_XATTR_SIZE_MAX);
+	while (off < max_off) {
+		struct xfs_bmbt_irec	hmap;
+		int			nhmaps = 1;
+
+		error = xfs_bmapi_read(ip, off, max_off - off, &hmap,
+				&nhmaps, bmap_flags);
+		if (error)
+			return error;
+		if (nhmaps != 1 || hmap.br_startblock == DELAYSTARTBLOCK) {
+			ASSERT(0);
+			return -EFSCORRUPTED;
+		}
+
+		if (!xfs_bmap_is_real_extent(&hmap))
+			break;
+
+		off = hmap.br_startoff + hmap.br_blockcount;
+	}
+	scan_blocks = off - imap->br_startoff;
+
+	trace_xreap_bmapi_binval_scan(sc, imap, scan_blocks);
+
+	/*
+	 * If there are incore buffers for these blocks, invalidate them.  If
+	 * we can't (try)lock the buffer we assume it's owned by someone else
+	 * and leave it alone.  The buffer cache cannot detect aliasing, so
+	 * employ nested loops to detect incore buffers of any plausible size.
+	 */
+	while (bno < agbno_next) {
+		struct xrep_bufscan	scan = {
+			.daddr		= XFS_AGB_TO_DADDR(mp, agno, bno),
+			.max_sectors	= xrep_bufscan_max_sectors(mp,
+								scan_blocks),
+			.daddr_step	= XFS_FSB_TO_BB(mp, 1),
+		};
+		struct xfs_buf		*bp;
+
+		while ((bp = xrep_bufscan_advance(mp, &scan)) != NULL) {
+			if (xreap_buf_loggable(bp)) {
+				xfs_trans_bjoin(sc->tp, bp);
+				xfs_trans_binval(sc->tp, bp);
+			} else {
+				xfs_buf_stale(bp);
+				xfs_buf_relse(bp);
+			}
+			invalidated++;
+
+			/*
+			 * Stop invalidating if we've hit the limit; we should
+			 * still have enough reservation left to free however
+			 * much of the mapping we've seen so far.
+			 */
+			if (invalidated > XREAP_MAX_BINVAL) {
+				imap->br_blockcount = agbno_next - bno;
+				goto out;
+			}
+		}
+
+		bno++;
+		scan_blocks--;
+	}
+
+out:
+	trace_xreap_bmapi_binval(sc->sa.pag, agbno, imap->br_blockcount);
+	return 0;
+}
+
+/*
+ * Dispose of as much of the beginning of this file fork mapping as possible.
+ * The number of blocks disposed of is returned in @imap->br_blockcount.
+ */
+STATIC int
+xrep_reap_bmapi_iter(
+	struct xfs_scrub		*sc,
+	struct xfs_inode		*ip,
+	int				whichfork,
+	struct xfs_bmbt_irec		*imap,
+	bool				crosslinked)
+{
+	int				error;
+
+	if (crosslinked) {
+		/*
+		 * If there are other rmappings, this block is cross linked and
+		 * must not be freed.  Remove the reverse mapping, leave the
+		 * buffer cache in its possibly confused state, and move on.
+		 * We don't want to risk discarding valid data buffers from
+		 * anybody else who thinks they own the block, even though that
+		 * runs the risk of stale buffer warnings in the future.
+		 */
+		trace_xreap_dispose_unmap_extent(sc->sa.pag,
+				XFS_FSB_TO_AGBNO(sc->mp, imap->br_startblock),
+				imap->br_blockcount);
+
+		/*
+		 * Schedule removal of the mapping from the fork.  We use
+		 * deferred log intents in this function to control the exact
+		 * sequence of metadata updates.
+		 */
+		xfs_bmap_unmap_extent(sc->tp, ip, whichfork, imap);
+		xfs_trans_mod_dquot_byino(sc->tp, ip, XFS_TRANS_DQ_BCOUNT,
+				-(int64_t)imap->br_blockcount);
+		xfs_rmap_unmap_extent(sc->tp, ip, whichfork, imap);
+		return 0;
+	}
+
+	/*
+	 * If the block is not crosslinked, we can invalidate all the incore
+	 * buffers for the extent, and then free the extent.  This is a bit of
+	 * a mess since we don't detect discontiguous buffers that are indexed
+	 * by a block starting before the first block of the extent but overlap
+	 * anyway.
+	 */
+	trace_xreap_dispose_free_extent(sc->sa.pag,
+			XFS_FSB_TO_AGBNO(sc->mp, imap->br_startblock),
+			imap->br_blockcount);
+
+	/*
+	 * Invalidate as many buffers as we can, starting at the beginning of
+	 * this mapping.  If this function sets blockcount to zero, the
+	 * transaction is full of logged buffer invalidations, so we need to
+	 * return early so that we can roll and retry.
+	 */
+	error = xreap_bmapi_binval(sc, ip, whichfork, imap);
+	if (error || imap->br_blockcount == 0)
+		return error;
+
+	/*
+	 * Schedule removal of the mapping from the fork.  We use deferred log
+	 * intents in this function to control the exact sequence of metadata
+	 * updates.
+	 */
+	xfs_bmap_unmap_extent(sc->tp, ip, whichfork, imap);
+	xfs_trans_mod_dquot_byino(sc->tp, ip, XFS_TRANS_DQ_BCOUNT,
+			-(int64_t)imap->br_blockcount);
+	return xfs_free_extent_later(sc->tp, imap->br_startblock,
+			imap->br_blockcount, NULL, XFS_AG_RESV_NONE, true);
+}
+
+/*
+ * Dispose of as much of this file extent as we can.  Upon successful return,
+ * the imap will reflect the mapping that was removed from the fork.
+ */
+STATIC int
+xreap_ifork_extent(
+	struct xfs_scrub		*sc,
+	struct xfs_inode		*ip,
+	int				whichfork,
+	struct xfs_bmbt_irec		*imap)
+{
+	xfs_agnumber_t			agno;
+	bool				crosslinked;
+	int				error;
+
+	ASSERT(sc->sa.pag == NULL);
+
+	trace_xreap_ifork_extent(sc, ip, whichfork, imap);
+
+	agno = XFS_FSB_TO_AGNO(sc->mp, imap->br_startblock);
+	sc->sa.pag = xfs_perag_get(sc->mp, agno);
+	if (!sc->sa.pag)
+		return -EFSCORRUPTED;
+
+	error = xfs_alloc_read_agf(sc->sa.pag, sc->tp, 0, &sc->sa.agf_bp);
+	if (error)
+		goto out_pag;
+
+	/*
+	 * Decide the fate of the blocks at the beginning of the mapping, then
+	 * update the mapping to use it with the unmap calls.
+	 */
+	error = xreap_bmapi_select(sc, ip, whichfork, imap, &crosslinked);
+	if (error)
+		goto out_agf;
+
+	error = xrep_reap_bmapi_iter(sc, ip, whichfork, imap, crosslinked);
+	if (error)
+		goto out_agf;
+
+out_agf:
+	xfs_trans_brelse(sc->tp, sc->sa.agf_bp);
+	sc->sa.agf_bp = NULL;
+out_pag:
+	xfs_perag_put(sc->sa.pag);
+	sc->sa.pag = NULL;
+	return error;
+}
+
+/*
+ * Dispose of each block mapped to the given fork of the given file.  Callers
+ * must hold ILOCK_EXCL, and ip can only be sc->ip or sc->tempip.  The fork
+ * must not have any delalloc reservations.
+ */
+int
+xrep_reap_ifork(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip,
+	int			whichfork)
+{
+	xfs_fileoff_t		off = 0;
+	int			bmap_flags = xfs_bmapi_aflag(whichfork);
+	int			error;
+
+	ASSERT(xfs_has_rmapbt(sc->mp));
+	ASSERT(ip == sc->ip || ip == sc->tempip);
+	ASSERT(whichfork == XFS_ATTR_FORK || !XFS_IS_REALTIME_INODE(ip));
+
+	while (off < XFS_MAX_FILEOFF) {
+		struct xfs_bmbt_irec	imap;
+		int			nimaps = 1;
+
+		/* Read the next extent, skip past holes and delalloc. */
+		error = xfs_bmapi_read(ip, off, XFS_MAX_FILEOFF - off, &imap,
+				&nimaps, bmap_flags);
+		if (error)
+			return error;
+		if (nimaps != 1 || imap.br_startblock == DELAYSTARTBLOCK) {
+			ASSERT(0);
+			return -EFSCORRUPTED;
+		}
+
+		/*
+		 * If this is a real space mapping, reap as much of it as we
+		 * can in a single transaction.
+		 */
+		if (xfs_bmap_is_real_extent(&imap)) {
+			error = xreap_ifork_extent(sc, ip, whichfork, &imap);
+			if (error)
+				return error;
+
+			error = xfs_defer_finish(&sc->tp);
+			if (error)
+				return error;
+		}
+
+		off = imap.br_startoff + imap.br_blockcount;
+	}
+
+	return 0;
+}
diff --git a/fs/xfs/scrub/reap.h b/fs/xfs/scrub/reap.h
index bb09e21fcb172..3f2f1775e29db 100644
--- a/fs/xfs/scrub/reap.h
+++ b/fs/xfs/scrub/reap.h
@@ -13,6 +13,7 @@ int xrep_reap_agblocks(struct xfs_scrub *sc, struct xagb_bitmap *bitmap,
 		const struct xfs_owner_info *oinfo, enum xfs_ag_resv_type type);
 int xrep_reap_fsblocks(struct xfs_scrub *sc, struct xfsb_bitmap *bitmap,
 		const struct xfs_owner_info *oinfo);
+int xrep_reap_ifork(struct xfs_scrub *sc, struct xfs_inode *ip, int whichfork);
 
 /* Buffer cache scan context. */
 struct xrep_bufscan {
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 00f906e50c341..691c91c9a5853 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -1510,6 +1510,7 @@ DEFINE_EVENT(xrep_extent_class, name, \
 DEFINE_REPAIR_EXTENT_EVENT(xreap_dispose_unmap_extent);
 DEFINE_REPAIR_EXTENT_EVENT(xreap_dispose_free_extent);
 DEFINE_REPAIR_EXTENT_EVENT(xreap_agextent_binval);
+DEFINE_REPAIR_EXTENT_EVENT(xreap_bmapi_binval);
 DEFINE_REPAIR_EXTENT_EVENT(xrep_agfl_insert);
 
 DECLARE_EVENT_CLASS(xrep_reap_find_class,
@@ -1543,6 +1544,7 @@ DEFINE_EVENT(xrep_reap_find_class, name, \
 		 bool crosslinked), \
 	TP_ARGS(pag, agbno, len, crosslinked))
 DEFINE_REPAIR_REAP_FIND_EVENT(xreap_agextent_select);
+DEFINE_REPAIR_REAP_FIND_EVENT(xreap_bmapi_select);
 
 DECLARE_EVENT_CLASS(xrep_rmap_class,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
@@ -2394,6 +2396,67 @@ TRACE_EVENT(xrep_tempfile_create,
 		  __entry->temp_inum)
 );
 
+TRACE_EVENT(xreap_ifork_extent,
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_inode *ip, int whichfork,
+		 const struct xfs_bmbt_irec *irec),
+	TP_ARGS(sc, ip, whichfork, irec),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(int, whichfork)
+		__field(xfs_fileoff_t, fileoff)
+		__field(xfs_filblks_t, len)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agblock_t, agbno)
+		__field(int, state)
+	),
+	TP_fast_assign(
+		__entry->dev = sc->mp->m_super->s_dev;
+		__entry->ino = ip->i_ino;
+		__entry->whichfork = whichfork;
+		__entry->fileoff = irec->br_startoff;
+		__entry->len = irec->br_blockcount;
+		__entry->agno = XFS_FSB_TO_AGNO(sc->mp, irec->br_startblock);
+		__entry->agbno = XFS_FSB_TO_AGBNO(sc->mp, irec->br_startblock);
+		__entry->state = irec->br_state;
+	),
+	TP_printk("dev %d:%d ip 0x%llx whichfork %s agno 0x%x agbno 0x%x fileoff 0x%llx fsbcount 0x%llx state 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __print_symbolic(__entry->whichfork, XFS_WHICHFORK_STRINGS),
+		  __entry->agno,
+		  __entry->agbno,
+		  __entry->fileoff,
+		  __entry->len,
+		  __entry->state)
+);
+
+TRACE_EVENT(xreap_bmapi_binval_scan,
+	TP_PROTO(struct xfs_scrub *sc, const struct xfs_bmbt_irec *irec,
+		 xfs_extlen_t scan_blocks),
+	TP_ARGS(sc, irec, scan_blocks),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_filblks_t, len)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agblock_t, agbno)
+		__field(xfs_extlen_t, scan_blocks)
+	),
+	TP_fast_assign(
+		__entry->dev = sc->mp->m_super->s_dev;
+		__entry->len = irec->br_blockcount;
+		__entry->agno = XFS_FSB_TO_AGNO(sc->mp, irec->br_startblock);
+		__entry->agbno = XFS_FSB_TO_AGBNO(sc->mp, irec->br_startblock);
+		__entry->scan_blocks = scan_blocks;
+	),
+	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%llx scan_blocks 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->agbno,
+		  __entry->len,
+		  __entry->scan_blocks)
+);
+
 #endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
 
 

[PATCH 1/3] xfs: support preallocating and copying content into temporary files

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create the routines we need to preallocate space in a temporary ondisk
file and then copy the contents of an xfile into the tempfile.  The
upcoming rtsummary repair feature will construct the contents of a
realtime summary file in memory, after which it will want to copy all
that into the ondisk temporary file before atomically committing the new
rtsummary contents.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/tempfile.c |  197 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/tempfile.h |   15 ++++
 fs/xfs/scrub/trace.h    |   39 +++++++++
 3 files changed, 251 insertions(+)


diff --git a/fs/xfs/scrub/tempfile.c b/fs/xfs/scrub/tempfile.c
index 5f4a931b1967c..936107d083545 100644
--- a/fs/xfs/scrub/tempfile.c
+++ b/fs/xfs/scrub/tempfile.c
@@ -14,14 +14,18 @@
 #include "xfs_inode.h"
 #include "xfs_ialloc.h"
 #include "xfs_quota.h"
+#include "xfs_bmap.h"
 #include "xfs_bmap_btree.h"
 #include "xfs_trans_space.h"
 #include "xfs_dir2.h"
 #include "xfs_xchgrange.h"
+#include "xfs_defer.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
+#include "scrub/repair.h"
 #include "scrub/trace.h"
 #include "scrub/tempfile.h"
+#include "scrub/xfile.h"
 
 /*
  * Create a temporary file for reconstructing metadata, with the intention of
@@ -249,3 +253,196 @@ xrep_tempfile_rele(
 	xchk_irele(sc, sc->tempip);
 	sc->tempip = NULL;
 }
+
+/*
+ * Make sure that the given range of the data fork of the temporary file is
+ * mapped to written blocks.  The caller must ensure that both inodes are
+ * joined to the transaction.
+ */
+int
+xrep_tempfile_prealloc(
+	struct xfs_scrub	*sc,
+	xfs_fileoff_t		off,
+	xfs_filblks_t		len)
+{
+	struct xfs_bmbt_irec	map;
+	xfs_fileoff_t		end = off + len;
+	int			error;
+
+	ASSERT(sc->tempip != NULL);
+	ASSERT(!XFS_NOT_DQATTACHED(sc->mp, sc->tempip));
+
+	for (; off < end; off = map.br_startoff + map.br_blockcount) {
+		int		nmaps = 1;
+
+		/*
+		 * If we have a real extent mapping this block then we're
+		 * in ok shape.
+		 */
+		error = xfs_bmapi_read(sc->tempip, off, end - off, &map, &nmaps,
+				XFS_DATA_FORK);
+		if (error)
+			return error;
+		if (nmaps == 0) {
+			ASSERT(nmaps != 0);
+			return -EFSCORRUPTED;
+		}
+
+		if (xfs_bmap_is_written_extent(&map))
+			continue;
+
+		/*
+		 * If we find a delalloc reservation then something is very
+		 * very wrong.  Bail out.
+		 */
+		if (map.br_startblock == DELAYSTARTBLOCK)
+			return -EFSCORRUPTED;
+
+		/*
+		 * Make sure this block has a real zeroed extent allocated to
+		 * it.
+		 */
+		nmaps = 1;
+		error = xfs_bmapi_write(sc->tp, sc->tempip, off, end - off,
+				XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO, 0, &map,
+				&nmaps);
+		if (error)
+			return error;
+		if (nmaps != 1)
+			return -EFSCORRUPTED;
+
+		trace_xrep_tempfile_prealloc(sc, XFS_DATA_FORK, &map);
+
+		/* Commit new extent and all deferred work. */
+		error = xfs_defer_finish(&sc->tp);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+/*
+ * Write data to each block of a file.  The given range of the tempfile's data
+ * fork must already be populated with written extents.
+ */
+int
+xrep_tempfile_copyin(
+	struct xfs_scrub	*sc,
+	xfs_fileoff_t		off,
+	xfs_filblks_t		len,
+	xrep_tempfile_copyin_fn	prep_fn,
+	void			*data)
+{
+	LIST_HEAD(buffers_list);
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_buf		*bp;
+	xfs_fileoff_t		flush_mask;
+	xfs_fileoff_t		end = off + len;
+	loff_t			pos = XFS_FSB_TO_B(mp, off);
+	int			error = 0;
+
+	ASSERT(S_ISREG(VFS_I(sc->tempip)->i_mode));
+
+	/* Flush buffers to disk every 512K */
+	flush_mask = XFS_B_TO_FSBT(mp, (1U << 19)) - 1;
+
+	for (; off < end; off++, pos += mp->m_sb.sb_blocksize) {
+		struct xfs_bmbt_irec	map;
+		int			nmaps = 1;
+
+		/* Read block mapping for this file block. */
+		error = xfs_bmapi_read(sc->tempip, off, 1, &map, &nmaps, 0);
+		if (error)
+			goto out_err;
+		if (nmaps == 0 || !xfs_bmap_is_written_extent(&map)) {
+			error = -EFSCORRUPTED;
+			goto out_err;
+		}
+
+		/* Get the metadata buffer for this offset in the file. */
+		error = xfs_trans_get_buf(sc->tp, mp->m_ddev_targp,
+				XFS_FSB_TO_DADDR(mp, map.br_startblock),
+				mp->m_bsize, 0, &bp);
+		if (error)
+			goto out_err;
+
+		trace_xrep_tempfile_copyin(sc, XFS_DATA_FORK, &map);
+
+		/* Read in a block's worth of data from the xfile. */
+		error = prep_fn(sc, bp, data);
+		if (error) {
+			xfs_trans_brelse(sc->tp, bp);
+			goto out_err;
+		}
+
+		/* Queue buffer, and flush if we have too much dirty data. */
+		xfs_buf_delwri_queue_here(bp, &buffers_list);
+		xfs_trans_brelse(sc->tp, bp);
+
+		if (!(off & flush_mask)) {
+			error = xfs_buf_delwri_submit(&buffers_list);
+			if (error)
+				goto out_err;
+		}
+	}
+
+	/*
+	 * Write the new blocks to disk.  If the ordered list isn't empty after
+	 * that, then something went wrong and we have to fail.  This should
+	 * never happen, but we'll check anyway.
+	 */
+	error = xfs_buf_delwri_submit(&buffers_list);
+	if (error)
+		goto out_err;
+
+	if (!list_empty(&buffers_list)) {
+		ASSERT(list_empty(&buffers_list));
+		error = -EIO;
+		goto out_err;
+	}
+
+	return 0;
+
+out_err:
+	xfs_buf_delwri_cancel(&buffers_list);
+	return error;
+}
+
+/*
+ * Set the temporary file's size.  Caller must join the tempfile to the scrub
+ * transaction and is responsible for adjusting block mappings as needed.
+ */
+int
+xrep_tempfile_set_isize(
+	struct xfs_scrub	*sc,
+	unsigned long long	isize)
+{
+	if (sc->tempip->i_disk_size == isize)
+		return 0;
+
+	sc->tempip->i_disk_size = isize;
+	i_size_write(VFS_I(sc->tempip), isize);
+	return xrep_tempfile_roll_trans(sc);
+}
+
+/*
+ * Roll a repair transaction involving the temporary file.  Caller must join
+ * both the temporary file and the file being scrubbed to the transaction.
+ * This function return with both inodes joined to a new scrub transaction,
+ * or the usual negative errno.
+ */
+int
+xrep_tempfile_roll_trans(
+	struct xfs_scrub	*sc)
+{
+	int			error;
+
+	xfs_trans_log_inode(sc->tp, sc->tempip, XFS_ILOG_CORE);
+	error = xrep_roll_trans(sc);
+	if (error)
+		return error;
+
+	xfs_trans_ijoin(sc->tp, sc->tempip, 0);
+	return 0;
+}
diff --git a/fs/xfs/scrub/tempfile.h b/fs/xfs/scrub/tempfile.h
index e165e0a3faf63..7980f9c4de552 100644
--- a/fs/xfs/scrub/tempfile.h
+++ b/fs/xfs/scrub/tempfile.h
@@ -17,6 +17,21 @@ void xrep_tempfile_iounlock(struct xfs_scrub *sc);
 void xrep_tempfile_ilock(struct xfs_scrub *sc);
 bool xrep_tempfile_ilock_nowait(struct xfs_scrub *sc);
 void xrep_tempfile_iunlock(struct xfs_scrub *sc);
+
+int xrep_tempfile_prealloc(struct xfs_scrub *sc, xfs_fileoff_t off,
+		xfs_filblks_t len);
+
+enum xfs_blft;
+
+typedef int (*xrep_tempfile_copyin_fn)(struct xfs_scrub *sc,
+		struct xfs_buf *bp, void *data);
+
+int xrep_tempfile_copyin(struct xfs_scrub *sc, xfs_fileoff_t off,
+		xfs_filblks_t len, xrep_tempfile_copyin_fn fn, void *data);
+
+int xrep_tempfile_set_isize(struct xfs_scrub *sc, unsigned long long isize);
+
+int xrep_tempfile_roll_trans(struct xfs_scrub *sc);
 #else
 static inline void xrep_tempfile_iolock_both(struct xfs_scrub *sc)
 {
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 691c91c9a5853..73ddaaadd2414 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -2396,6 +2396,45 @@ TRACE_EVENT(xrep_tempfile_create,
 		  __entry->temp_inum)
 );
 
+DECLARE_EVENT_CLASS(xrep_tempfile_class,
+	TP_PROTO(struct xfs_scrub *sc, int whichfork,
+		 struct xfs_bmbt_irec *irec),
+	TP_ARGS(sc, whichfork, irec),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(int, whichfork)
+		__field(xfs_fileoff_t, lblk)
+		__field(xfs_filblks_t, len)
+		__field(xfs_fsblock_t, pblk)
+		__field(int, state)
+	),
+	TP_fast_assign(
+		__entry->dev = sc->mp->m_super->s_dev;
+		__entry->ino = sc->tempip->i_ino;
+		__entry->whichfork = whichfork;
+		__entry->lblk = irec->br_startoff;
+		__entry->len = irec->br_blockcount;
+		__entry->pblk = irec->br_startblock;
+		__entry->state = irec->br_state;
+	),
+	TP_printk("dev %d:%d ino 0x%llx whichfork %s fileoff 0x%llx fsbcount 0x%llx startblock 0x%llx state %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __print_symbolic(__entry->whichfork, XFS_WHICHFORK_STRINGS),
+		  __entry->lblk,
+		  __entry->len,
+		  __entry->pblk,
+		  __entry->state)
+);
+#define DEFINE_XREP_TEMPFILE_EVENT(name) \
+DEFINE_EVENT(xrep_tempfile_class, name, \
+	TP_PROTO(struct xfs_scrub *sc, int whichfork, \
+		 struct xfs_bmbt_irec *irec), \
+	TP_ARGS(sc, whichfork, irec))
+DEFINE_XREP_TEMPFILE_EVENT(xrep_tempfile_prealloc);
+DEFINE_XREP_TEMPFILE_EVENT(xrep_tempfile_copyin);
+
 TRACE_EVENT(xreap_ifork_extent,
 	TP_PROTO(struct xfs_scrub *sc, struct xfs_inode *ip, int whichfork,
 		 const struct xfs_bmbt_irec *irec),

[PATCH 2/3] xfs: teach the tempfile to support atomic extent swapping

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create some new routines to exchange the contents of a temporary file
created to stage a repair with another ondisk file.  This will be used
by the realtime summary repair function to commit atomically the new
rtsummary data, which will be staged in the tempfile.

The rest of XFS coordinates access to the realtime metadata inodes
solely through the ILOCK.  For repair to hold its exclusive access to
the realtime summary file, it has to allocate a single large transaction
and roll it repeatedly throughout the repair while holding the ILOCK.
In turn, this means that for now there's only a partial swapext
implementation for the temporary file, because we can only work within
an existing transaction.  Hence the only tempswap functions needed here
are to estimate the resource requirements of swapext between, reserve
more space/quota to an existing transaction, and kick off the actual
swap.  The rest will be added in a later patch in preparation for
repairing xattrs and directories.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/scrub.c    |   11 ++-
 fs/xfs/scrub/scrub.h    |    7 ++
 fs/xfs/scrub/tempfile.c |  204 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/tempswap.h |   21 +++++
 fs/xfs/scrub/trace.h    |    1 
 5 files changed, 241 insertions(+), 3 deletions(-)
 create mode 100644 fs/xfs/scrub/tempswap.h


diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 51bcb21325cd3..afc82f1e40ffb 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -149,14 +149,15 @@ xchk_probe(
 
 /* Scrub setup and teardown */
 
+#define FSGATES_MASK	(XCHK_FSGATES_ALL | XREP_FSGATES_ALL)
 static inline void
 xchk_fsgates_disable(
 	struct xfs_scrub	*sc)
 {
-	if (!(sc->flags & XCHK_FSGATES_ALL))
+	if (!(sc->flags & FSGATES_MASK))
 		return;
 
-	trace_xchk_fsgates_disable(sc, sc->flags & XCHK_FSGATES_ALL);
+	trace_xchk_fsgates_disable(sc, sc->flags & FSGATES_MASK);
 
 	if (sc->flags & XCHK_FSGATES_DRAIN)
 		xfs_drain_wait_disable();
@@ -170,8 +171,12 @@ xchk_fsgates_disable(
 	if (sc->flags & XCHK_FSGATES_RMAP)
 		xfs_rmap_hook_disable();
 
-	sc->flags &= ~XCHK_FSGATES_ALL;
+	if (sc->flags & XREP_FSGATES_ATOMIC_XCHG)
+		xfs_xchg_range_rele_log_assist(sc->mp);
+
+	sc->flags &= ~FSGATES_MASK;
 }
+#undef FSGATES_MASK
 
 /* Free all the resources and finish the transactions. */
 STATIC int
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index 5f0e8e350295e..48b2fb8271499 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -131,6 +131,7 @@ struct xfs_scrub {
 #define XCHK_FSGATES_QUOTA	(1U << 4)  /* quota live update enabled */
 #define XCHK_FSGATES_DIRENTS	(1U << 5)  /* directory live update enabled */
 #define XCHK_FSGATES_RMAP	(1U << 6)  /* rmapbt live update enabled */
+#define XREP_FSGATES_ATOMIC_XCHG (1U << 29) /* uses atomic file content exchange */
 #define XREP_RESET_PERAG_RESV	(1U << 30) /* must reset AG space reservation */
 #define XREP_ALREADY_FIXED	(1U << 31) /* checking our repair work */
 
@@ -145,6 +146,12 @@ struct xfs_scrub {
 				 XCHK_FSGATES_DIRENTS | \
 				 XCHK_FSGATES_RMAP)
 
+/*
+ * The sole XREP_FSGATES* flag reflects a log intent item that is protected
+ * by a log-incompat feature flag.  No code patching in use here.
+ */
+#define XREP_FSGATES_ALL	(XREP_FSGATES_ATOMIC_XCHG)
+
 /* Metadata scrubbers */
 int xchk_tester(struct xfs_scrub *sc);
 int xchk_superblock(struct xfs_scrub *sc);
diff --git a/fs/xfs/scrub/tempfile.c b/fs/xfs/scrub/tempfile.c
index 936107d083545..a1736a3556a7d 100644
--- a/fs/xfs/scrub/tempfile.c
+++ b/fs/xfs/scrub/tempfile.c
@@ -19,12 +19,14 @@
 #include "xfs_trans_space.h"
 #include "xfs_dir2.h"
 #include "xfs_xchgrange.h"
+#include "xfs_swapext.h"
 #include "xfs_defer.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/repair.h"
 #include "scrub/trace.h"
 #include "scrub/tempfile.h"
+#include "scrub/tempswap.h"
 #include "scrub/xfile.h"
 
 /*
@@ -446,3 +448,205 @@ xrep_tempfile_roll_trans(
 	xfs_trans_ijoin(sc->tp, sc->tempip, 0);
 	return 0;
 }
+
+/* Enable atomic extent swapping. */
+int
+xrep_tempswap_grab_log_assist(
+	struct xfs_scrub	*sc)
+{
+	bool			need_rele = false;
+	int			error;
+
+	if (sc->flags & XREP_FSGATES_ATOMIC_XCHG)
+		return 0;
+
+	error = xfs_xchg_range_grab_log_assist(sc->mp, true, &need_rele);
+	if (error)
+		return error;
+	if (!need_rele) {
+		ASSERT(need_rele);
+		return -EOPNOTSUPP;
+	}
+
+	trace_xchk_fsgates_enable(sc, XREP_FSGATES_ATOMIC_XCHG);
+
+	sc->flags |= XREP_FSGATES_ATOMIC_XCHG;
+	return 0;
+}
+
+/*
+ * Fill out the swapext request in preparation for swapping the contents of a
+ * metadata file that we've rebuilt in the temp file.
+ */
+STATIC int
+xrep_tempswap_prep_request(
+	struct xfs_scrub	*sc,
+	int			whichfork,
+	struct xrep_tempswap	*tx)
+{
+	struct xfs_swapext_req	*req = &tx->req;
+
+	memset(tx, 0, sizeof(struct xrep_tempswap));
+
+	/* COW forks don't exist on disk. */
+	if (whichfork == XFS_COW_FORK) {
+		ASSERT(0);
+		return -EINVAL;
+	}
+
+	/* Both files should have the relevant forks. */
+	if (!xfs_ifork_ptr(sc->ip, whichfork) ||
+	    !xfs_ifork_ptr(sc->tempip, whichfork)) {
+		ASSERT(xfs_ifork_ptr(sc->ip, whichfork) != NULL);
+		ASSERT(xfs_ifork_ptr(sc->tempip, whichfork) != NULL);
+		return -EINVAL;
+	}
+
+	/* Swap all mappings in both forks. */
+	req->ip1 = sc->tempip;
+	req->ip2 = sc->ip;
+	req->startoff1 = 0;
+	req->startoff2 = 0;
+	req->whichfork = whichfork;
+	req->blockcount = XFS_MAX_FILEOFF;
+	req->req_flags = XFS_SWAP_REQ_LOGGED;
+
+	/* Always swap sizes when we're swapping data fork mappings. */
+	if (whichfork == XFS_DATA_FORK)
+		req->req_flags |= XFS_SWAP_REQ_SET_SIZES;
+
+	/*
+	 * If we're repairing symlinks, xattrs, or directories, always try to
+	 * convert ip2 to short format after swapping.
+	 */
+	if (whichfork == XFS_ATTR_FORK || S_ISDIR(VFS_I(sc->ip)->i_mode) ||
+	    S_ISLNK(VFS_I(sc->ip)->i_mode))
+		req->req_flags |= XFS_SWAP_REQ_CVT_INO2_SF;
+
+	return 0;
+}
+
+/*
+ * Obtain a quota reservation to make sure we don't hit EDQUOT.  We can skip
+ * this if quota enforcement is disabled or if both inodes' dquots are the
+ * same.  The qretry structure must be initialized to zeroes before the first
+ * call to this function.
+ */
+STATIC int
+xrep_tempswap_reserve_quota(
+	struct xfs_scrub		*sc,
+	const struct xrep_tempswap	*tx)
+{
+	struct xfs_trans		*tp = sc->tp;
+	const struct xfs_swapext_req	*req = &tx->req;
+	int64_t				ddelta, rdelta;
+	int				error;
+
+	/*
+	 * Don't bother with a quota reservation if we're not enforcing them
+	 * or the two inodes have the same dquots.
+	 */
+	if (!XFS_IS_QUOTA_ON(tp->t_mountp) || req->ip1 == req->ip2 ||
+	    (req->ip1->i_udquot == req->ip2->i_udquot &&
+	     req->ip1->i_gdquot == req->ip2->i_gdquot &&
+	     req->ip1->i_pdquot == req->ip2->i_pdquot))
+		return 0;
+
+	/*
+	 * Quota reservation for each file comes from two sources.  First, we
+	 * need to account for any net gain in mapped blocks during the swap.
+	 * Second, we need reservation for the gross gain in mapped blocks so
+	 * that we don't trip over any quota block reservation assertions.  We
+	 * must reserve the gross gain because the quota code subtracts from
+	 * bcount the number of blocks that we unmap; it does not add that
+	 * quantity back to the quota block reservation.
+	 */
+	ddelta = max_t(int64_t, 0, req->ip2_bcount - req->ip1_bcount);
+	rdelta = max_t(int64_t, 0, req->ip2_rtbcount - req->ip1_rtbcount);
+	error = xfs_trans_reserve_quota_nblks(tp, req->ip1,
+			ddelta + req->ip1_bcount, rdelta + req->ip1_rtbcount,
+			true);
+	if (error)
+		return error;
+
+	ddelta = max_t(int64_t, 0, req->ip1_bcount - req->ip2_bcount);
+	rdelta = max_t(int64_t, 0, req->ip1_rtbcount - req->ip2_rtbcount);
+	return xfs_trans_reserve_quota_nblks(tp, req->ip2,
+			ddelta + req->ip2_bcount, rdelta + req->ip2_rtbcount,
+			true);
+}
+
+/*
+ * Prepare an existing transaction for a swap.
+ *
+ * This function fills out the swapext request and resource estimation
+ * structures in preparation for swapping the contents of a metadata file that
+ * has been rebuilt in the temp file.  Next, it reserves space and quota for
+ * the transaction.
+ *
+ * The caller must hold ILOCK_EXCL of the scrub target file and the temporary
+ * file.  The caller must join both inodes to the transaction with no unlock
+ * flags, and is responsible for dropping both ILOCKs when appropriate.  Only
+ * use this when those ILOCKs cannot be dropped.
+ */
+int
+xrep_tempswap_trans_reserve(
+	struct xfs_scrub	*sc,
+	int			whichfork,
+	struct xrep_tempswap	*tx)
+{
+	int			error;
+
+	ASSERT(sc->tp != NULL);
+	ASSERT(xfs_isilocked(sc->ip, XFS_ILOCK_EXCL));
+	ASSERT(xfs_isilocked(sc->tempip, XFS_ILOCK_EXCL));
+
+	error = xrep_tempswap_prep_request(sc, whichfork, tx);
+	if (error)
+		return error;
+
+	error = xfs_swapext_estimate(&tx->req);
+	if (error)
+		return error;
+
+	error = xfs_trans_reserve_more(sc->tp, tx->req.resblks, 0);
+	if (error)
+		return error;
+
+	return xrep_tempswap_reserve_quota(sc, tx);
+}
+
+/*
+ * Swap forks between the file being repaired and the temporary file.  Returns
+ * with both inodes locked and joined to a clean scrub transaction.
+ */
+int
+xrep_tempswap_contents(
+	struct xfs_scrub	*sc,
+	struct xrep_tempswap	*tx)
+{
+	int			error;
+
+	ASSERT(sc->flags & XREP_FSGATES_ATOMIC_XCHG);
+
+	xfs_swapext(sc->tp, &tx->req);
+	error = xfs_defer_finish(&sc->tp);
+	if (error)
+		return error;
+
+	/*
+	 * If we swapped the ondisk sizes of two metadata files, we must swap
+	 * the incore sizes as well.  Since online fsck doesn't use swapext on
+	 * the data forks of user-accessible files, the two sizes are always
+	 * the same, so we don't need to log the inodes.
+	 */
+	if (tx->req.req_flags & XFS_SWAP_REQ_SET_SIZES) {
+		loff_t	temp;
+
+		temp = i_size_read(VFS_I(sc->ip));
+		i_size_write(VFS_I(sc->ip), i_size_read(VFS_I(sc->tempip)));
+		i_size_write(VFS_I(sc->tempip), temp);
+	}
+
+	return 0;
+}
diff --git a/fs/xfs/scrub/tempswap.h b/fs/xfs/scrub/tempswap.h
new file mode 100644
index 0000000000000..e8f8a6e3c8861
--- /dev/null
+++ b/fs/xfs/scrub/tempswap.h
@@ -0,0 +1,21 @@
+// 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_SCRUB_TEMPSWAP_H__
+#define __XFS_SCRUB_TEMPSWAP_H__
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+struct xrep_tempswap {
+	struct xfs_swapext_req	req;
+};
+
+int xrep_tempswap_grab_log_assist(struct xfs_scrub *sc);
+int xrep_tempswap_trans_reserve(struct xfs_scrub *sc, int whichfork,
+		struct xrep_tempswap *ti);
+
+int xrep_tempswap_contents(struct xfs_scrub *sc, struct xrep_tempswap *ti);
+#endif /* CONFIG_XFS_ONLINE_REPAIR */
+
+#endif /* __XFS_SCRUB_TEMPFILE_H__ */
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 73ddaaadd2414..1f06c1ace5902 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -125,6 +125,7 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_HEALTHY);
 	{ XCHK_FSGATES_QUOTA,			"fsgates_quota" }, \
 	{ XCHK_FSGATES_DIRENTS,			"fsgates_dirents" }, \
 	{ XCHK_FSGATES_RMAP,			"fsgates_rmap" }, \
+	{ XREP_FSGATES_ATOMIC_XCHG,		"fsgates_atomic_swapext" }, \
 	{ XREP_RESET_PERAG_RESV,		"reset_perag_resv" }, \
 	{ XREP_ALREADY_FIXED,			"already_fixed" }
 

[PATCH 3/3] xfs: online repair of realtime summaries

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Repair the realtime summary data by constructing a new rtsummary file in
the scrub temporary file, then atomically swapping the contents.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Makefile                 |    1 
 fs/xfs/scrub/common.c           |    1 
 fs/xfs/scrub/repair.h           |    3 +
 fs/xfs/scrub/rtsummary.c        |   33 ++++---
 fs/xfs/scrub/rtsummary.h        |   37 ++++++++
 fs/xfs/scrub/rtsummary_repair.c |  177 +++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/scrub.c            |    3 -
 7 files changed, 239 insertions(+), 16 deletions(-)
 create mode 100644 fs/xfs/scrub/rtsummary.h
 create mode 100644 fs/xfs/scrub/rtsummary_repair.c


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 9ce43c3037d2c..62e38f70c304b 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -213,6 +213,7 @@ xfs-y				+= $(addprefix scrub/, \
 
 xfs-$(CONFIG_XFS_RT)		+= $(addprefix scrub/, \
 				   rtbitmap_repair.o \
+				   rtsummary_repair.o \
 				   )
 
 xfs-$(CONFIG_XFS_QUOTA)		+= $(addprefix scrub/, \
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 78ffd6137d498..c16cd9774f525 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -31,6 +31,7 @@
 #include "xfs_ag.h"
 #include "xfs_error.h"
 #include "xfs_quota.h"
+#include "xfs_swapext.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 38aa5c9649d71..06125d0a2c602 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -126,8 +126,10 @@ int xrep_fscounters(struct xfs_scrub *sc);
 
 #ifdef CONFIG_XFS_RT
 int xrep_rtbitmap(struct xfs_scrub *sc);
+int xrep_rtsummary(struct xfs_scrub *sc);
 #else
 # define xrep_rtbitmap			xrep_notsupported
+# define xrep_rtsummary			xrep_notsupported
 #endif /* CONFIG_XFS_RT */
 
 #ifdef CONFIG_XFS_QUOTA
@@ -212,6 +214,7 @@ xrep_setup_nothing(
 #define xrep_quotacheck			xrep_notsupported
 #define xrep_nlinks			xrep_notsupported
 #define xrep_fscounters			xrep_notsupported
+#define xrep_rtsummary			xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
diff --git a/fs/xfs/scrub/rtsummary.c b/fs/xfs/scrub/rtsummary.c
index b0d90426a5cb8..5d1622203c8a9 100644
--- a/fs/xfs/scrub/rtsummary.c
+++ b/fs/xfs/scrub/rtsummary.c
@@ -16,10 +16,14 @@
 #include "xfs_rtbitmap.h"
 #include "xfs_bit.h"
 #include "xfs_bmap.h"
+#include "xfs_swapext.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
 #include "scrub/xfile.h"
+#include "scrub/repair.h"
+#include "scrub/tempswap.h"
+#include "scrub/rtsummary.h"
 
 /*
  * Realtime Summary
@@ -31,18 +35,6 @@
  * (potentially large) amount of data in pageable memory.
  */
 
-struct xchk_rtsummary {
-	struct xfs_rtalloc_args	args;
-
-	uint64_t		rextents;
-	uint64_t		rbmblocks;
-	uint64_t		rsumsize;
-	unsigned int		rsumlevels;
-
-	/* Memory buffer for the summary comparison. */
-	union xfs_suminfo_raw	words[];
-};
-
 /* Set us up to check the rtsummary file. */
 int
 xchk_setup_rtsummary(
@@ -59,6 +51,12 @@ xchk_setup_rtsummary(
 		return -ENOMEM;
 	sc->buf = rts;
 
+	if (xchk_could_repair(sc)) {
+		error = xrep_setup_rtsummary(sc, rts);
+		if (error)
+			return error;
+	}
+
 	/*
 	 * Create an xfile to construct a new rtsummary file.  The xfile allows
 	 * us to avoid pinning kernel memory for this purpose.
@@ -69,7 +67,7 @@ xchk_setup_rtsummary(
 	if (error)
 		return error;
 
-	error = xchk_trans_alloc(sc, 0);
+	error = xchk_trans_alloc(sc, rts->resblks);
 	if (error)
 		return error;
 
@@ -134,7 +132,7 @@ xfsum_store(
 			sumoff << XFS_WORDLOG);
 }
 
-static inline int
+inline int
 xfsum_copyout(
 	struct xfs_scrub	*sc,
 	xfs_rtsumoff_t		sumoff,
@@ -361,7 +359,12 @@ xchk_rtsummary(
 	error = xchk_rtsum_compare(sc);
 
 out_rbm:
-	/* Unlock the rtbitmap since we're done with it. */
+	/*
+	 * Unlock the rtbitmap since we're done with it.  All other writers of
+	 * the rt free space metadata grab the bitmap and summary ILOCKs in
+	 * that order, so we're still protected against allocation activities
+	 * even if we continue on to the repair function.
+	 */
 	xfs_iunlock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
 	return error;
 }
diff --git a/fs/xfs/scrub/rtsummary.h b/fs/xfs/scrub/rtsummary.h
new file mode 100644
index 0000000000000..8bcffd53fc2e2
--- /dev/null
+++ b/fs/xfs/scrub/rtsummary.h
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2020-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_RTSUMMARY_H__
+#define __XFS_SCRUB_RTSUMMARY_H__
+
+struct xchk_rtsummary {
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+	struct xrep_tempswap	tempswap;
+#endif
+	struct xfs_rtalloc_args	args;
+
+	uint64_t		rextents;
+	uint64_t		rbmblocks;
+	uint64_t		rsumsize;
+	unsigned int		rsumlevels;
+	unsigned int		resblks;
+
+	/* suminfo position of xfile as we write buffers to disk. */
+	xfs_rtsumoff_t		prep_wordoff;
+
+	/* Memory buffer for the summary comparison. */
+	union xfs_suminfo_raw	words[];
+};
+
+int xfsum_copyout(struct xfs_scrub *sc, xfs_rtsumoff_t sumoff,
+		union xfs_suminfo_raw *rawinfo, unsigned int nr_words);
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+int xrep_setup_rtsummary(struct xfs_scrub *sc, struct xchk_rtsummary *rts);
+#else
+# define xrep_setup_rtsummary(sc, rts)	(0)
+#endif /* CONFIG_XFS_ONLINE_REPAIR */
+
+#endif /* __XFS_SCRUB_RTSUMMARY_H__ */
diff --git a/fs/xfs/scrub/rtsummary_repair.c b/fs/xfs/scrub/rtsummary_repair.c
new file mode 100644
index 0000000000000..058c5ebabf9a2
--- /dev/null
+++ b/fs/xfs/scrub/rtsummary_repair.c
@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2020-2024 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_btree.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_rtalloc.h"
+#include "xfs_inode.h"
+#include "xfs_bit.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_swapext.h"
+#include "xfs_rtbitmap.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/tempfile.h"
+#include "scrub/tempswap.h"
+#include "scrub/reap.h"
+#include "scrub/xfile.h"
+#include "scrub/rtsummary.h"
+
+/* Set us up to repair the rtsummary file. */
+int
+xrep_setup_rtsummary(
+	struct xfs_scrub	*sc,
+	struct xchk_rtsummary	*rts)
+{
+	struct xfs_mount	*mp = sc->mp;
+	unsigned long long	blocks;
+	int			error;
+
+	error = xrep_tempfile_create(sc, S_IFREG);
+	if (error)
+		return error;
+
+	/*
+	 * If we're doing a repair, we reserve enough blocks to write out a
+	 * completely new summary file, plus twice as many blocks as we would
+	 * need if we can only allocate one block per data fork mapping.  This
+	 * should cover the preallocation of the temporary file and swapping
+	 * the extent mappings.
+	 *
+	 * We cannot use xfs_swapext_estimate because we have not yet
+	 * constructed the replacement rtsummary and therefore do not know how
+	 * many extents it will use.  By the time we do, we will have a dirty
+	 * transaction (which we cannot drop because we cannot drop the
+	 * rtsummary ILOCK) and cannot ask for more reservation.
+	 */
+	blocks = XFS_B_TO_FSB(mp, mp->m_rsumsize);
+	blocks += xfs_bmbt_calc_size(mp, blocks) * 2;
+	if (blocks > UINT_MAX)
+		return -EOPNOTSUPP;
+
+	rts->resblks += blocks;
+
+	/*
+	 * Grab support for atomic extent swapping before we allocate any
+	 * transactions or grab ILOCKs.
+	 */
+	return xrep_tempswap_grab_log_assist(sc);
+}
+
+static int
+xrep_rtsummary_prep_buf(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*bp,
+	void			*data)
+{
+	struct xchk_rtsummary	*rts = data;
+	struct xfs_mount	*mp = sc->mp;
+	union xfs_suminfo_raw	*ondisk;
+	int			error;
+
+	rts->args.mp = sc->mp;
+	rts->args.tp = sc->tp;
+	rts->args.sumbp = bp;
+	ondisk = xfs_rsumblock_infoptr(&rts->args, 0);
+	rts->args.sumbp = NULL;
+
+	bp->b_ops = &xfs_rtbuf_ops;
+
+	error = xfsum_copyout(sc, rts->prep_wordoff, ondisk, mp->m_blockwsize);
+	if (error)
+		return error;
+
+	rts->prep_wordoff += mp->m_blockwsize;
+	xfs_trans_buf_set_type(sc->tp, bp, XFS_BLFT_RTSUMMARY_BUF);
+	return 0;
+}
+
+/* Repair the realtime summary. */
+int
+xrep_rtsummary(
+	struct xfs_scrub	*sc)
+{
+	struct xchk_rtsummary	*rts = sc->buf;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_filblks_t		rsumblocks;
+	int			error;
+
+	/* We require the rmapbt to rebuild anything. */
+	if (!xfs_has_rmapbt(mp))
+		return -EOPNOTSUPP;
+
+	/* Walk away if we disagree on the size of the rt bitmap. */
+	if (rts->rbmblocks != mp->m_sb.sb_rbmblocks)
+		return 0;
+
+	/* Make sure any problems with the fork are fixed. */
+	error = xrep_metadata_inode_forks(sc);
+	if (error)
+		return error;
+
+	/*
+	 * Try to take ILOCK_EXCL of the temporary file.  We had better be the
+	 * only ones holding onto this inode, but we can't block while holding
+	 * the rtsummary file's ILOCK_EXCL.
+	 */
+	while (!xrep_tempfile_ilock_nowait(sc)) {
+		if (xchk_should_terminate(sc, &error))
+			return error;
+		delay(1);
+	}
+
+	/* Make sure we have space allocated for the entire summary file. */
+	rsumblocks = XFS_B_TO_FSB(mp, rts->rsumsize);
+	xfs_trans_ijoin(sc->tp, sc->ip, 0);
+	xfs_trans_ijoin(sc->tp, sc->tempip, 0);
+	error = xrep_tempfile_prealloc(sc, 0, rsumblocks);
+	if (error)
+		return error;
+
+	/* Last chance to abort before we start committing fixes. */
+	if (xchk_should_terminate(sc, &error))
+		return error;
+
+	/* Copy the rtsummary file that we generated. */
+	error = xrep_tempfile_copyin(sc, 0, rsumblocks,
+			xrep_rtsummary_prep_buf, rts);
+	if (error)
+		return error;
+	error = xrep_tempfile_set_isize(sc, rts->rsumsize);
+	if (error)
+		return error;
+
+	/*
+	 * Now swap the extents.  Nothing in repair uses the temporary buffer,
+	 * so we can reuse it for the tempfile swapext information.
+	 */
+	error = xrep_tempswap_trans_reserve(sc, XFS_DATA_FORK, &rts->tempswap);
+	if (error)
+		return error;
+
+	error = xrep_tempswap_contents(sc, &rts->tempswap);
+	if (error)
+		return error;
+
+	/* Reset incore state and blow out the summary cache. */
+	if (mp->m_rsum_cache)
+		memset(mp->m_rsum_cache, 0xFF, mp->m_sb.sb_rbmblocks);
+
+	mp->m_rsumlevels = rts->rsumlevels;
+	mp->m_rsumsize = rts->rsumsize;
+
+	/* Free the old rtsummary blocks if they're not in use. */
+	return xrep_reap_ifork(sc, sc->tempip, XFS_DATA_FORK);
+}
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index afc82f1e40ffb..9af91874e58b9 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -18,6 +18,7 @@
 #include "xfs_buf_xfile.h"
 #include "xfs_rmap.h"
 #include "xfs_xchgrange.h"
+#include "xfs_swapext.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
@@ -357,7 +358,7 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.type	= ST_FS,
 		.setup	= xchk_setup_rtsummary,
 		.scrub	= xchk_rtsummary,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_rtsummary,
 	},
 	[XFS_SCRUB_TYPE_UQUOTA] = {	/* user quota */
 		.type	= ST_FS,

[PATCH 1/9] xfs: add an explicit owner field to xfs_da_args

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add an explicit owner field to xfs_da_args, which will make it easier
for online fsck to set the owner field of the temporary directory and
xattr structures that it builds to repair damaged metadata.

Note: I hopefully found all the xfs_da_args definitions by looking for
automatic stack variable declarations and xfs_da_args.dp assignments:

git grep -E '(args.*dp =|struct xfs_da_args[[:space:]]*[a-z0-9][a-z0-9]*)'

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_attr_leaf.c |    2 ++
 fs/xfs/libxfs/xfs_bmap.c      |    1 +
 fs/xfs/libxfs/xfs_da_btree.h  |    1 +
 fs/xfs/libxfs/xfs_dir2.c      |    5 +++++
 fs/xfs/libxfs/xfs_swapext.c   |    2 ++
 fs/xfs/scrub/attr.c           |    1 +
 fs/xfs/scrub/dabtree.c        |    1 +
 fs/xfs/scrub/dir.c            |    3 ++-
 fs/xfs/scrub/readdir.c        |    2 ++
 fs/xfs/xfs_acl.c              |    2 ++
 fs/xfs/xfs_attr_item.c        |    1 +
 fs/xfs/xfs_dir2_readdir.c     |    1 +
 fs/xfs/xfs_ioctl.c            |    2 ++
 fs/xfs/xfs_iops.c             |    1 +
 fs/xfs/xfs_trace.h            |    7 +++++--
 fs/xfs/xfs_xattr.c            |    2 ++
 16 files changed, 31 insertions(+), 3 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 94893f19ee187..157117a049837 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -975,6 +975,7 @@ xfs_attr_shortform_to_leaf(
 	nargs.whichfork = XFS_ATTR_FORK;
 	nargs.trans = args->trans;
 	nargs.op_flags = XFS_DA_OP_OKNOENT;
+	nargs.owner = args->owner;
 
 	sfe = &sf->list[0];
 	for (i = 0; i < sf->hdr.count; i++) {
@@ -1178,6 +1179,7 @@ xfs_attr3_leaf_to_shortform(
 	nargs.whichfork = XFS_ATTR_FORK;
 	nargs.trans = args->trans;
 	nargs.op_flags = XFS_DA_OP_OKNOENT;
+	nargs.owner = args->owner;
 
 	for (i = 0; i < ichdr.count; entry++, i++) {
 		if (entry->flags & XFS_ATTR_INCOMPLETE)
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 17f607b3b8cdf..5a0e6cffb90d9 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -958,6 +958,7 @@ xfs_bmap_add_attrfork_local(
 		dargs.total = dargs.geo->fsbcount;
 		dargs.whichfork = XFS_DATA_FORK;
 		dargs.trans = tp;
+		dargs.owner = ip->i_ino;
 		return xfs_dir2_sf_to_block(&dargs);
 	}
 
diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h
index 706baf36e1751..7fb13f26edaa7 100644
--- a/fs/xfs/libxfs/xfs_da_btree.h
+++ b/fs/xfs/libxfs/xfs_da_btree.h
@@ -79,6 +79,7 @@ typedef struct xfs_da_args {
 	int		rmtvaluelen2;	/* remote attr value length in bytes */
 	uint32_t	op_flags;	/* operation flags */
 	enum xfs_dacmp	cmpresult;	/* name compare result for lookups */
+	xfs_ino_t	owner;		/* inode that owns the dir/attr data */
 } xfs_da_args_t;
 
 /*
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index 748fe2c514922..51eed639f2dfe 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -250,6 +250,7 @@ xfs_dir_init(
 	args->geo = dp->i_mount->m_dir_geo;
 	args->dp = dp;
 	args->trans = tp;
+	args->owner = dp->i_ino;
 	error = xfs_dir2_sf_create(args, pdp->i_ino);
 	kmem_free(args);
 	return error;
@@ -295,6 +296,7 @@ xfs_dir_createname(
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
 	args->op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
+	args->owner = dp->i_ino;
 	if (!inum)
 		args->op_flags |= XFS_DA_OP_JUSTCHECK;
 
@@ -389,6 +391,7 @@ xfs_dir_lookup(
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
 	args->op_flags = XFS_DA_OP_OKNOENT;
+	args->owner = dp->i_ino;
 	if (ci_name)
 		args->op_flags |= XFS_DA_OP_CILOOKUP;
 
@@ -462,6 +465,7 @@ xfs_dir_removename(
 	args->total = total;
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
+	args->owner = dp->i_ino;
 
 	if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL) {
 		rval = xfs_dir2_sf_removename(args);
@@ -523,6 +527,7 @@ xfs_dir_replace(
 	args->total = total;
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
+	args->owner = dp->i_ino;
 
 	if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL) {
 		rval = xfs_dir2_sf_replace(args);
diff --git a/fs/xfs/libxfs/xfs_swapext.c b/fs/xfs/libxfs/xfs_swapext.c
index 7e36e136cee0d..ced2365fa7b59 100644
--- a/fs/xfs/libxfs/xfs_swapext.c
+++ b/fs/xfs/libxfs/xfs_swapext.c
@@ -526,6 +526,7 @@ xfs_swapext_attr_to_sf(
 		.geo		= tp->t_mountp->m_attr_geo,
 		.whichfork	= XFS_ATTR_FORK,
 		.trans		= tp,
+		.owner		= sxi->sxi_ip2->i_ino,
 	};
 	struct xfs_buf		*bp;
 	int			forkoff;
@@ -556,6 +557,7 @@ xfs_swapext_dir_to_sf(
 		.geo		= tp->t_mountp->m_dir_geo,
 		.whichfork	= XFS_DATA_FORK,
 		.trans		= tp,
+		.owner		= sxi->sxi_ip2->i_ino,
 	};
 	struct xfs_dir2_sf_hdr	sfh;
 	struct xfs_buf		*bp;
diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c
index 6c16d9530ccac..40a59b24c209f 100644
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -169,6 +169,7 @@ xchk_xattr_listent(
 		.hashval		= xfs_da_hashname(name, namelen),
 		.trans			= context->tp,
 		.valuelen		= valuelen,
+		.owner			= context->dp->i_ino,
 	};
 	struct xchk_xattr_buf		*ab;
 	struct xchk_xattr		*sx;
diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c
index 82b150d3b8b70..fa6385a99ac4e 100644
--- a/fs/xfs/scrub/dabtree.c
+++ b/fs/xfs/scrub/dabtree.c
@@ -494,6 +494,7 @@ xchk_da_btree(
 	ds->dargs.whichfork = whichfork;
 	ds->dargs.trans = sc->tp;
 	ds->dargs.op_flags = XFS_DA_OP_OKNOENT;
+	ds->dargs.owner = sc->ip->i_ino;
 	ds->state = xfs_da_state_alloc(&ds->dargs);
 	ds->sc = sc;
 	ds->private = private;
diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index 076a310b8eb00..042e28547e044 100644
--- a/fs/xfs/scrub/dir.c
+++ b/fs/xfs/scrub/dir.c
@@ -621,10 +621,11 @@ xchk_directory_blocks(
 {
 	struct xfs_bmbt_irec	got;
 	struct xfs_da_args	args = {
-		.dp		= sc ->ip,
+		.dp		= sc->ip,
 		.whichfork	= XFS_DATA_FORK,
 		.geo		= sc->mp->m_dir_geo,
 		.trans		= sc->tp,
+		.owner		= sc->ip->i_ino,
 	};
 	struct xfs_ifork	*ifp = xfs_ifork_ptr(sc->ip, XFS_DATA_FORK);
 	struct xfs_mount	*mp = sc->mp;
diff --git a/fs/xfs/scrub/readdir.c b/fs/xfs/scrub/readdir.c
index e51c1544be632..20375c0972db9 100644
--- a/fs/xfs/scrub/readdir.c
+++ b/fs/xfs/scrub/readdir.c
@@ -275,6 +275,7 @@ xchk_dir_walk(
 		.dp		= dp,
 		.geo		= dp->i_mount->m_dir_geo,
 		.trans		= sc->tp,
+		.owner		= dp->i_ino,
 	};
 	bool			isblock;
 	int			error;
@@ -326,6 +327,7 @@ xchk_dir_lookup(
 		.hashval	= xfs_dir2_hashname(dp->i_mount, name),
 		.whichfork	= XFS_DATA_FORK,
 		.op_flags	= XFS_DA_OP_OKNOENT,
+		.owner		= dp->i_ino,
 	};
 	bool			isblock, isleaf;
 	int			error;
diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index 6b840301817a9..505c3069cbaaa 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -135,6 +135,7 @@ xfs_get_acl(struct inode *inode, int type, bool rcu)
 		.dp		= ip,
 		.attr_filter	= XFS_ATTR_ROOT,
 		.valuelen	= XFS_ACL_MAX_SIZE(mp),
+		.owner		= ip->i_ino,
 	};
 	int			error;
 
@@ -178,6 +179,7 @@ __xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	struct xfs_da_args	args = {
 		.dp		= ip,
 		.attr_filter	= XFS_ATTR_ROOT,
+		.owner		= ip->i_ino,
 	};
 	int			error;
 
diff --git a/fs/xfs/xfs_attr_item.c b/fs/xfs/xfs_attr_item.c
index f8c6c34e348f3..d7ebb54a03870 100644
--- a/fs/xfs/xfs_attr_item.c
+++ b/fs/xfs/xfs_attr_item.c
@@ -540,6 +540,7 @@ xfs_attri_recover_work(
 	args->attr_filter = attrp->alfi_attr_filter & XFS_ATTRI_FILTER_MASK;
 	args->op_flags = XFS_DA_OP_RECOVERY | XFS_DA_OP_OKNOENT |
 			 XFS_DA_OP_LOGGED;
+	args->owner = args->dp->i_ino;
 
 	ASSERT(xfs_sb_version_haslogxattrs(&mp->m_sb));
 
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index a457be34b3fff..263a897bee49e 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -534,6 +534,7 @@ xfs_readdir(
 	args.dp = dp;
 	args.geo = dp->i_mount->m_dir_geo;
 	args.trans = tp;
+	args.owner = dp->i_ino;
 
 	if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL)
 		return xfs_dir2_sf_getdents(&args, ctx);
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 071b135ec9653..de16dbc9e7ded 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -480,6 +480,7 @@ xfs_attrmulti_attr_get(
 		.name		= name,
 		.namelen	= strlen(name),
 		.valuelen	= *len,
+		.owner		= XFS_I(inode)->i_ino,
 	};
 	int			error;
 
@@ -513,6 +514,7 @@ xfs_attrmulti_attr_set(
 		.attr_flags	= xfs_attr_flags(flags),
 		.name		= name,
 		.namelen	= strlen(name),
+		.owner		= XFS_I(inode)->i_ino,
 	};
 	int			error;
 
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 11382c499c92c..037606e5eee40 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -62,6 +62,7 @@ xfs_initxattrs(
 			.namelen	= strlen(xattr->name),
 			.value		= xattr->value,
 			.valuelen	= xattr->value_len,
+			.owner		= ip->i_ino,
 		};
 		error = xfs_attr_change(&args);
 		if (error < 0)
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 91ec676fcf8ed..ee6f569c2f3d9 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -1927,6 +1927,7 @@ DECLARE_EVENT_CLASS(xfs_da_class,
 		__field(xfs_dahash_t, hashval)
 		__field(xfs_ino_t, inumber)
 		__field(uint32_t, op_flags)
+		__field(xfs_ino_t, owner)
 	),
 	TP_fast_assign(
 		__entry->dev = VFS_I(args->dp)->i_sb->s_dev;
@@ -1937,9 +1938,10 @@ DECLARE_EVENT_CLASS(xfs_da_class,
 		__entry->hashval = args->hashval;
 		__entry->inumber = args->inumber;
 		__entry->op_flags = args->op_flags;
+		__entry->owner = args->owner;
 	),
 	TP_printk("dev %d:%d ino 0x%llx name %.*s namelen %d hashval 0x%x "
-		  "inumber 0x%llx op_flags %s",
+		  "inumber 0x%llx op_flags %s owner 0x%llx",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->ino,
 		  __entry->namelen,
@@ -1947,7 +1949,8 @@ DECLARE_EVENT_CLASS(xfs_da_class,
 		  __entry->namelen,
 		  __entry->hashval,
 		  __entry->inumber,
-		  __print_flags(__entry->op_flags, "|", XFS_DA_OP_FLAGS))
+		  __print_flags(__entry->op_flags, "|", XFS_DA_OP_FLAGS),
+		  __entry->owner)
 )
 
 #define DEFINE_DIR2_EVENT(name) \
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index 0e0e25e386f17..1920ca49b08d6 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -133,6 +133,7 @@ xfs_xattr_get(const struct xattr_handler *handler, struct dentry *unused,
 		.namelen	= strlen(name),
 		.value		= value,
 		.valuelen	= size,
+		.owner		= XFS_I(inode)->i_ino,
 	};
 	int			error;
 
@@ -159,6 +160,7 @@ xfs_xattr_set(const struct xattr_handler *handler,
 		.namelen	= strlen(name),
 		.value		= (void *)value,
 		.valuelen	= size,
+		.owner		= XFS_I(inode)->i_ino,
 	};
 	int			error;
 

[PATCH 2/9] xfs: use the xfs_da_args owner field to set new dir/attr block owner

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

When we're creating leaf, data, freespace, or dabtree blocks for
directories and xattrs, use the explicit owner field (instead of the
xfs_inode) to set the owner field.  This will enable online repair to
construct replacement data structures in a temporary file without having
to change the owner fields prior to swapping the new and old structures.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_attr_leaf.c   |    2 +-
 fs/xfs/libxfs/xfs_attr_remote.c |    4 ++--
 fs/xfs/libxfs/xfs_da_btree.c    |    2 +-
 fs/xfs/libxfs/xfs_dir2_block.c  |   19 ++++++++++---------
 fs/xfs/libxfs/xfs_dir2_data.c   |    2 +-
 fs/xfs/libxfs/xfs_dir2_leaf.c   |   11 +++++------
 fs/xfs/libxfs/xfs_dir2_node.c   |    2 +-
 7 files changed, 21 insertions(+), 21 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 157117a049837..01f93122f4286 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -1311,7 +1311,7 @@ xfs_attr3_leaf_create(
 		ichdr.magic = XFS_ATTR3_LEAF_MAGIC;
 
 		hdr3->blkno = cpu_to_be64(xfs_buf_daddr(bp));
-		hdr3->owner = cpu_to_be64(dp->i_ino);
+		hdr3->owner = cpu_to_be64(args->owner);
 		uuid_copy(&hdr3->uuid, &mp->m_sb.sb_meta_uuid);
 
 		ichdr.freemap[0].base = sizeof(struct xfs_attr3_leaf_hdr);
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index bb4cf1fa0dc2c..b8cdd15c4e1af 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -522,8 +522,8 @@ xfs_attr_rmtval_set_value(
 			return error;
 		bp->b_ops = &xfs_attr3_rmt_buf_ops;
 
-		xfs_attr_rmtval_copyin(mp, bp, args->dp->i_ino, &offset,
-				       &valuelen, &src);
+		xfs_attr_rmtval_copyin(mp, bp, args->owner, &offset, &valuelen,
+				&src);
 
 		error = xfs_bwrite(bp);	/* GROT: NOTE: synchronous write */
 		xfs_buf_relse(bp);
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 21fb8aff40df7..a69d04ed74935 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -485,7 +485,7 @@ xfs_da3_node_create(
 		memset(hdr3, 0, sizeof(struct xfs_da3_node_hdr));
 		ichdr.magic = XFS_DA3_NODE_MAGIC;
 		hdr3->info.blkno = cpu_to_be64(xfs_buf_daddr(bp));
-		hdr3->info.owner = cpu_to_be64(args->dp->i_ino);
+		hdr3->info.owner = cpu_to_be64(args->owner);
 		uuid_copy(&hdr3->info.uuid, &mp->m_sb.sb_meta_uuid);
 	} else {
 		ichdr.magic = XFS_DA_NODE_MAGIC;
diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c
index 6b3ca2b384cf1..6bda6a4906718 100644
--- a/fs/xfs/libxfs/xfs_dir2_block.c
+++ b/fs/xfs/libxfs/xfs_dir2_block.c
@@ -163,12 +163,13 @@ xfs_dir3_block_read(
 
 static void
 xfs_dir3_block_init(
-	struct xfs_mount	*mp,
-	struct xfs_trans	*tp,
-	struct xfs_buf		*bp,
-	struct xfs_inode	*dp)
+	struct xfs_da_args	*args,
+	struct xfs_buf		*bp)
 {
-	struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;
+	struct xfs_trans	*tp = args->trans;
+	struct xfs_inode	*dp = args->dp;
+	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_dir3_blk_hdr	*hdr3 = bp->b_addr;
 
 	bp->b_ops = &xfs_dir3_block_buf_ops;
 	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DIR_BLOCK_BUF);
@@ -177,7 +178,7 @@ xfs_dir3_block_init(
 		memset(hdr3, 0, sizeof(*hdr3));
 		hdr3->magic = cpu_to_be32(XFS_DIR3_BLOCK_MAGIC);
 		hdr3->blkno = cpu_to_be64(xfs_buf_daddr(bp));
-		hdr3->owner = cpu_to_be64(dp->i_ino);
+		hdr3->owner = cpu_to_be64(args->owner);
 		uuid_copy(&hdr3->uuid, &mp->m_sb.sb_meta_uuid);
 		return;
 
@@ -1009,7 +1010,7 @@ xfs_dir2_leaf_to_block(
 	/*
 	 * Start converting it to block form.
 	 */
-	xfs_dir3_block_init(mp, tp, dbp, dp);
+	xfs_dir3_block_init(args, dbp);
 
 	needlog = 1;
 	needscan = 0;
@@ -1131,7 +1132,7 @@ xfs_dir2_sf_to_block(
 	error = xfs_dir3_data_init(args, blkno, &bp);
 	if (error)
 		goto out_free;
-	xfs_dir3_block_init(mp, tp, bp, dp);
+	xfs_dir3_block_init(args, bp);
 	hdr = bp->b_addr;
 
 	/*
@@ -1171,7 +1172,7 @@ xfs_dir2_sf_to_block(
 	 * Create entry for .
 	 */
 	dep = bp->b_addr + offset;
-	dep->inumber = cpu_to_be64(dp->i_ino);
+	dep->inumber = cpu_to_be64(args->owner);
 	dep->namelen = 1;
 	dep->name[0] = '.';
 	xfs_dir2_data_put_ftype(mp, dep, XFS_DIR3_FT_DIR);
diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c
index 7a6d965bea71b..c3ef720b5ff6e 100644
--- a/fs/xfs/libxfs/xfs_dir2_data.c
+++ b/fs/xfs/libxfs/xfs_dir2_data.c
@@ -725,7 +725,7 @@ xfs_dir3_data_init(
 		memset(hdr3, 0, sizeof(*hdr3));
 		hdr3->magic = cpu_to_be32(XFS_DIR3_DATA_MAGIC);
 		hdr3->blkno = cpu_to_be64(xfs_buf_daddr(bp));
-		hdr3->owner = cpu_to_be64(dp->i_ino);
+		hdr3->owner = cpu_to_be64(args->owner);
 		uuid_copy(&hdr3->uuid, &mp->m_sb.sb_meta_uuid);
 
 	} else
diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c
index 08dda5ce9d91c..20ce057d12e82 100644
--- a/fs/xfs/libxfs/xfs_dir2_leaf.c
+++ b/fs/xfs/libxfs/xfs_dir2_leaf.c
@@ -304,12 +304,12 @@ xfs_dir3_leafn_read(
  */
 static void
 xfs_dir3_leaf_init(
-	struct xfs_mount	*mp,
-	struct xfs_trans	*tp,
+	struct xfs_da_args	*args,
 	struct xfs_buf		*bp,
-	xfs_ino_t		owner,
 	uint16_t		type)
 {
+	struct xfs_mount	*mp = args->dp->i_mount;
+	struct xfs_trans	*tp = args->trans;
 	struct xfs_dir2_leaf	*leaf = bp->b_addr;
 
 	ASSERT(type == XFS_DIR2_LEAF1_MAGIC || type == XFS_DIR2_LEAFN_MAGIC);
@@ -323,7 +323,7 @@ xfs_dir3_leaf_init(
 					 ? cpu_to_be16(XFS_DIR3_LEAF1_MAGIC)
 					 : cpu_to_be16(XFS_DIR3_LEAFN_MAGIC);
 		leaf3->info.blkno = cpu_to_be64(xfs_buf_daddr(bp));
-		leaf3->info.owner = cpu_to_be64(owner);
+		leaf3->info.owner = cpu_to_be64(args->owner);
 		uuid_copy(&leaf3->info.uuid, &mp->m_sb.sb_meta_uuid);
 	} else {
 		memset(leaf, 0, sizeof(*leaf));
@@ -356,7 +356,6 @@ xfs_dir3_leaf_get_buf(
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_trans	*tp = args->trans;
-	struct xfs_mount	*mp = dp->i_mount;
 	struct xfs_buf		*bp;
 	int			error;
 
@@ -369,7 +368,7 @@ xfs_dir3_leaf_get_buf(
 	if (error)
 		return error;
 
-	xfs_dir3_leaf_init(mp, tp, bp, dp->i_ino, magic);
+	xfs_dir3_leaf_init(args, bp, magic);
 	xfs_dir3_leaf_log_header(args, bp);
 	if (magic == XFS_DIR2_LEAF1_MAGIC)
 		xfs_dir3_leaf_log_tail(args, bp);
diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c
index be0b8834028c0..1ad7405f9c389 100644
--- a/fs/xfs/libxfs/xfs_dir2_node.c
+++ b/fs/xfs/libxfs/xfs_dir2_node.c
@@ -349,7 +349,7 @@ xfs_dir3_free_get_buf(
 		hdr.magic = XFS_DIR3_FREE_MAGIC;
 
 		hdr3->hdr.blkno = cpu_to_be64(xfs_buf_daddr(bp));
-		hdr3->hdr.owner = cpu_to_be64(dp->i_ino);
+		hdr3->hdr.owner = cpu_to_be64(args->owner);
 		uuid_copy(&hdr3->hdr.uuid, &mp->m_sb.sb_meta_uuid);
 	} else
 		hdr.magic = XFS_DIR2_FREE_MAGIC;

[PATCH 3/9] xfs: validate attr leaf buffer owners

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a leaf block header checking function to validate the owner field
of xattr leaf blocks.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_attr.c      |   10 ++++---
 fs/xfs/libxfs/xfs_attr_leaf.c |   55 ++++++++++++++++++++++++++++++++++-------
 fs/xfs/libxfs/xfs_attr_leaf.h |    4 ++-
 fs/xfs/libxfs/xfs_da_btree.c  |   42 +++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_da_btree.h  |    1 +
 fs/xfs/libxfs/xfs_swapext.c   |    3 +-
 fs/xfs/scrub/dabtree.c        |    7 +++++
 fs/xfs/xfs_attr_list.c        |   25 ++++++++++++++++---
 8 files changed, 128 insertions(+), 19 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index fa49c795f4074..1e94e933d7682 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -647,8 +647,8 @@ xfs_attr_leaf_remove_attr(
 	int				forkoff;
 	int				error;
 
-	error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno,
-				   &bp);
+	error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner,
+			args->blkno, &bp);
 	if (error)
 		return error;
 
@@ -679,7 +679,7 @@ xfs_attr_leaf_shrink(
 	if (!xfs_attr_is_leaf(dp))
 		return 0;
 
-	error = xfs_attr3_leaf_read(args->trans, args->dp, 0, &bp);
+	error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, 0, &bp);
 	if (error)
 		return error;
 
@@ -1160,7 +1160,7 @@ xfs_attr_leaf_try_add(
 	struct xfs_buf		*bp;
 	int			error;
 
-	error = xfs_attr3_leaf_read(args->trans, args->dp, 0, &bp);
+	error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, 0, &bp);
 	if (error)
 		return error;
 
@@ -1208,7 +1208,7 @@ xfs_attr_leaf_hasname(
 {
 	int                     error = 0;
 
-	error = xfs_attr3_leaf_read(args->trans, args->dp, 0, bp);
+	error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, 0, bp);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 01f93122f4286..3face870b4dac 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -388,6 +388,26 @@ xfs_attr3_leaf_verify(
 	return NULL;
 }
 
+xfs_failaddr_t
+xfs_attr3_leaf_header_check(
+	struct xfs_buf		*bp,
+	xfs_ino_t		owner)
+{
+	struct xfs_mount	*mp = bp->b_mount;
+
+	if (xfs_has_crc(mp)) {
+		struct xfs_attr3_leafblock *hdr3 = bp->b_addr;
+
+		ASSERT(hdr3->hdr.info.hdr.magic ==
+				cpu_to_be16(XFS_ATTR3_LEAF_MAGIC));
+
+		if (be64_to_cpu(hdr3->hdr.info.owner) != owner)
+			return __this_address;
+	}
+
+	return NULL;
+}
+
 static void
 xfs_attr3_leaf_write_verify(
 	struct xfs_buf	*bp)
@@ -448,16 +468,30 @@ int
 xfs_attr3_leaf_read(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*dp,
+	xfs_ino_t		owner,
 	xfs_dablk_t		bno,
 	struct xfs_buf		**bpp)
 {
+	xfs_failaddr_t		fa;
 	int			err;
 
 	err = xfs_da_read_buf(tp, dp, bno, 0, bpp, XFS_ATTR_FORK,
 			&xfs_attr3_leaf_buf_ops);
-	if (!err && tp && *bpp)
+	if (err || !(*bpp))
+		return err;
+
+	fa = xfs_attr3_leaf_header_check(*bpp, owner);
+	if (fa) {
+		__xfs_buf_mark_corrupt(*bpp, fa);
+		xfs_trans_brelse(tp, *bpp);
+		*bpp = NULL;
+		xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
+		return -EFSCORRUPTED;
+	}
+
+	if (tp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_ATTR_LEAF_BUF);
-	return err;
+	return 0;
 }
 
 /*========================================================================
@@ -1232,7 +1266,7 @@ xfs_attr3_leaf_to_node(
 	error = xfs_da_grow_inode(args, &blkno);
 	if (error)
 		goto out;
-	error = xfs_attr3_leaf_read(args->trans, dp, 0, &bp1);
+	error = xfs_attr3_leaf_read(args->trans, dp, args->owner, 0, &bp1);
 	if (error)
 		goto out;
 
@@ -2067,7 +2101,7 @@ xfs_attr3_leaf_toosmall(
 		if (blkno == 0)
 			continue;
 		error = xfs_attr3_leaf_read(state->args->trans, state->args->dp,
-					blkno, &bp);
+					state->args->owner, blkno, &bp);
 		if (error)
 			return error;
 
@@ -2788,7 +2822,8 @@ xfs_attr3_leaf_clearflag(
 	/*
 	 * Set up the operation.
 	 */
-	error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, &bp);
+	error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner,
+			args->blkno, &bp);
 	if (error)
 		return error;
 
@@ -2852,7 +2887,8 @@ xfs_attr3_leaf_setflag(
 	/*
 	 * Set up the operation.
 	 */
-	error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, &bp);
+	error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner,
+			args->blkno, &bp);
 	if (error)
 		return error;
 
@@ -2911,7 +2947,8 @@ xfs_attr3_leaf_flipflags(
 	/*
 	 * Read the block containing the "old" attr
 	 */
-	error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, &bp1);
+	error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner,
+			args->blkno, &bp1);
 	if (error)
 		return error;
 
@@ -2919,8 +2956,8 @@ xfs_attr3_leaf_flipflags(
 	 * Read the block containing the "new" attr, if it is different
 	 */
 	if (args->blkno2 != args->blkno) {
-		error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno2,
-					   &bp2);
+		error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner,
+				args->blkno2, &bp2);
 		if (error)
 			return error;
 	} else {
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h
index ce6743463c868..70edddedd1ad3 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.h
+++ b/fs/xfs/libxfs/xfs_attr_leaf.h
@@ -101,12 +101,14 @@ int	xfs_attr_leaf_order(struct xfs_buf *leaf1_bp,
 				   struct xfs_buf *leaf2_bp);
 int	xfs_attr_leaf_newentsize(struct xfs_da_args *args, int *local);
 int	xfs_attr3_leaf_read(struct xfs_trans *tp, struct xfs_inode *dp,
-			xfs_dablk_t bno, struct xfs_buf **bpp);
+			xfs_ino_t owner, xfs_dablk_t bno, struct xfs_buf **bpp);
 void	xfs_attr3_leaf_hdr_from_disk(struct xfs_da_geometry *geo,
 				     struct xfs_attr3_icleaf_hdr *to,
 				     struct xfs_attr_leafblock *from);
 void	xfs_attr3_leaf_hdr_to_disk(struct xfs_da_geometry *geo,
 				   struct xfs_attr_leafblock *to,
 				   struct xfs_attr3_icleaf_hdr *from);
+xfs_failaddr_t xfs_attr3_leaf_header_check(struct xfs_buf *bp,
+		xfs_ino_t owner);
 
 #endif	/* __XFS_ATTR_LEAF_H__ */
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index a69d04ed74935..a7782055db6cd 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -251,6 +251,25 @@ xfs_da3_node_verify(
 	return NULL;
 }
 
+xfs_failaddr_t
+xfs_da3_header_check(
+	struct xfs_buf		*bp,
+	xfs_ino_t		owner)
+{
+	struct xfs_mount	*mp = bp->b_mount;
+	struct xfs_da_blkinfo	*hdr = bp->b_addr;
+
+	if (!xfs_has_crc(mp))
+		return NULL;
+
+	switch (hdr->magic) {
+	case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC):
+		return xfs_attr3_leaf_header_check(bp, owner);
+	}
+
+	return NULL;
+}
+
 static void
 xfs_da3_node_write_verify(
 	struct xfs_buf	*bp)
@@ -1590,6 +1609,7 @@ xfs_da3_node_lookup_int(
 	struct xfs_da_node_entry *btree;
 	struct xfs_da3_icnode_hdr nodehdr;
 	struct xfs_da_args	*args;
+	xfs_failaddr_t		fa;
 	xfs_dablk_t		blkno;
 	xfs_dahash_t		hashval;
 	xfs_dahash_t		btreehashval;
@@ -1628,6 +1648,12 @@ xfs_da3_node_lookup_int(
 
 		if (magic == XFS_ATTR_LEAF_MAGIC ||
 		    magic == XFS_ATTR3_LEAF_MAGIC) {
+			fa = xfs_attr3_leaf_header_check(blk->bp, args->owner);
+			if (fa) {
+				__xfs_buf_mark_corrupt(blk->bp, fa);
+				xfs_da_mark_sick(args);
+				return -EFSCORRUPTED;
+			}
 			blk->magic = XFS_ATTR_LEAF_MAGIC;
 			blk->hashval = xfs_attr_leaf_lasthash(blk->bp, NULL);
 			break;
@@ -1995,6 +2021,7 @@ xfs_da3_path_shift(
 	struct xfs_da_node_entry *btree;
 	struct xfs_da3_icnode_hdr nodehdr;
 	struct xfs_buf		*bp;
+	xfs_failaddr_t		fa;
 	xfs_dablk_t		blkno = 0;
 	int			level;
 	int			error;
@@ -2086,6 +2113,12 @@ xfs_da3_path_shift(
 			break;
 		case XFS_ATTR_LEAF_MAGIC:
 		case XFS_ATTR3_LEAF_MAGIC:
+			fa = xfs_attr3_leaf_header_check(blk->bp, args->owner);
+			if (fa) {
+				__xfs_buf_mark_corrupt(blk->bp, fa);
+				xfs_da_mark_sick(args);
+				return -EFSCORRUPTED;
+			}
 			blk->magic = XFS_ATTR_LEAF_MAGIC;
 			ASSERT(level == path->active-1);
 			blk->index = 0;
@@ -2288,6 +2321,7 @@ xfs_da3_swap_lastblock(
 	struct xfs_buf		*last_buf;
 	struct xfs_buf		*sib_buf;
 	struct xfs_buf		*par_buf;
+	xfs_failaddr_t		fa;
 	xfs_dahash_t		dead_hash;
 	xfs_fileoff_t		lastoff;
 	xfs_dablk_t		dead_blkno;
@@ -2324,6 +2358,14 @@ xfs_da3_swap_lastblock(
 	error = xfs_da3_node_read(tp, dp, last_blkno, &last_buf, w);
 	if (error)
 		return error;
+	fa = xfs_da3_header_check(last_buf, args->owner);
+	if (fa) {
+		__xfs_buf_mark_corrupt(last_buf, fa);
+		xfs_trans_brelse(tp, last_buf);
+		xfs_da_mark_sick(args);
+		return -EFSCORRUPTED;
+	}
+
 	/*
 	 * Copy the last block into the dead buffer and log it.
 	 */
diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h
index 7fb13f26edaa7..99618e0c8a72b 100644
--- a/fs/xfs/libxfs/xfs_da_btree.h
+++ b/fs/xfs/libxfs/xfs_da_btree.h
@@ -236,6 +236,7 @@ void	xfs_da3_node_hdr_from_disk(struct xfs_mount *mp,
 		struct xfs_da3_icnode_hdr *to, struct xfs_da_intnode *from);
 void	xfs_da3_node_hdr_to_disk(struct xfs_mount *mp,
 		struct xfs_da_intnode *to, struct xfs_da3_icnode_hdr *from);
+xfs_failaddr_t xfs_da3_header_check(struct xfs_buf *bp, xfs_ino_t owner);
 
 extern struct kmem_cache	*xfs_da_state_cache;
 
diff --git a/fs/xfs/libxfs/xfs_swapext.c b/fs/xfs/libxfs/xfs_swapext.c
index ced2365fa7b59..0446376365ec7 100644
--- a/fs/xfs/libxfs/xfs_swapext.c
+++ b/fs/xfs/libxfs/xfs_swapext.c
@@ -535,7 +535,8 @@ xfs_swapext_attr_to_sf(
 	if (!xfs_attr_is_leaf(sxi->sxi_ip2))
 		return 0;
 
-	error = xfs_attr3_leaf_read(tp, sxi->sxi_ip2, 0, &bp);
+	error = xfs_attr3_leaf_read(tp, sxi->sxi_ip2, sxi->sxi_ip2->i_ino, 0,
+			&bp);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c
index fa6385a99ac4e..c71254088dffe 100644
--- a/fs/xfs/scrub/dabtree.c
+++ b/fs/xfs/scrub/dabtree.c
@@ -320,6 +320,7 @@ xchk_da_btree_block(
 	struct xfs_da3_blkinfo		*hdr3;
 	struct xfs_da_args		*dargs = &ds->dargs;
 	struct xfs_inode		*ip = ds->dargs.dp;
+	xfs_failaddr_t			fa;
 	xfs_ino_t			owner;
 	int				*pmaxrecs;
 	struct xfs_da3_icnode_hdr	nodehdr;
@@ -442,6 +443,12 @@ xchk_da_btree_block(
 		goto out_freebp;
 	}
 
+	fa = xfs_da3_header_check(blk->bp, dargs->owner);
+	if (fa) {
+		xchk_da_set_corrupt(ds, level);
+		goto out_freebp;
+	}
+
 	/*
 	 * If we've been handed a block that is below the dabtree root, does
 	 * its hashval match what the parent block expected to see?
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index dcfa8e8e146a3..2954ed7cfaf43 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -215,6 +215,7 @@ xfs_attr_node_list_lookup(
 	struct xfs_mount		*mp = dp->i_mount;
 	struct xfs_trans		*tp = context->tp;
 	struct xfs_buf			*bp;
+	xfs_failaddr_t			fa;
 	int				i;
 	int				error = 0;
 	unsigned int			expected_level = 0;
@@ -274,6 +275,12 @@ xfs_attr_node_list_lookup(
 		}
 	}
 
+	fa = xfs_attr3_leaf_header_check(bp, dp->i_ino);
+	if (fa) {
+		__xfs_buf_mark_corrupt(bp, fa);
+		goto out_releasebuf;
+	}
+
 	if (expected_level != 0)
 		goto out_corruptbuf;
 
@@ -282,6 +289,7 @@ xfs_attr_node_list_lookup(
 
 out_corruptbuf:
 	xfs_buf_mark_corrupt(bp);
+out_releasebuf:
 	xfs_trans_brelse(tp, bp);
 	xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
 	return -EFSCORRUPTED;
@@ -298,6 +306,7 @@ xfs_attr_node_list(
 	struct xfs_buf			*bp;
 	struct xfs_inode		*dp = context->dp;
 	struct xfs_mount		*mp = dp->i_mount;
+	xfs_failaddr_t			fa;
 	int				error = 0;
 
 	trace_xfs_attr_node_list(context);
@@ -331,6 +340,15 @@ xfs_attr_node_list(
 			case XFS_ATTR_LEAF_MAGIC:
 			case XFS_ATTR3_LEAF_MAGIC:
 				leaf = bp->b_addr;
+				fa = xfs_attr3_leaf_header_check(bp,
+						dp->i_ino);
+				if (fa) {
+					__xfs_buf_mark_corrupt(bp, fa);
+					xfs_trans_brelse(context->tp, bp);
+					xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
+					bp = NULL;
+					break;
+				}
 				xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo,
 							     &leafhdr, leaf);
 				entries = xfs_attr3_leaf_entryp(leaf);
@@ -381,8 +399,8 @@ xfs_attr_node_list(
 			break;
 		cursor->blkno = leafhdr.forw;
 		xfs_trans_brelse(context->tp, bp);
-		error = xfs_attr3_leaf_read(context->tp, dp, cursor->blkno,
-					    &bp);
+		error = xfs_attr3_leaf_read(context->tp, dp, dp->i_ino,
+				cursor->blkno, &bp);
 		if (error)
 			return error;
 	}
@@ -502,7 +520,8 @@ xfs_attr_leaf_list(
 	trace_xfs_attr_leaf_list(context);
 
 	context->cursor.blkno = 0;
-	error = xfs_attr3_leaf_read(context->tp, context->dp, 0, &bp);
+	error = xfs_attr3_leaf_read(context->tp, context->dp,
+			context->dp->i_ino, 0, &bp);
 	if (error)
 		return error;
 

[PATCH 4/9] xfs: validate attr remote value buffer owners

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Check the owner field of xattr remote value blocks.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_attr_remote.c |    9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index b8cdd15c4e1af..3dd0b6b0956c0 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -280,12 +280,12 @@ xfs_attr_rmtval_copyout(
 	struct xfs_mount	*mp,
 	struct xfs_buf		*bp,
 	struct xfs_inode	*dp,
+	xfs_ino_t		owner,
 	int			*offset,
 	int			*valuelen,
 	uint8_t			**dst)
 {
 	char			*src = bp->b_addr;
-	xfs_ino_t		ino = dp->i_ino;
 	xfs_daddr_t		bno = xfs_buf_daddr(bp);
 	int			len = BBTOB(bp->b_length);
 	int			blksize = mp->m_attr_geo->blksize;
@@ -299,11 +299,11 @@ xfs_attr_rmtval_copyout(
 		byte_cnt = min(*valuelen, byte_cnt);
 
 		if (xfs_has_crc(mp)) {
-			if (xfs_attr3_rmt_hdr_ok(src, ino, *offset,
+			if (xfs_attr3_rmt_hdr_ok(src, owner, *offset,
 						  byte_cnt, bno)) {
 				xfs_alert(mp,
 "remote attribute header mismatch bno/off/len/owner (0x%llx/0x%x/Ox%x/0x%llx)",
-					bno, *offset, byte_cnt, ino);
+					bno, *offset, byte_cnt, owner);
 				xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
 				return -EFSCORRUPTED;
 			}
@@ -427,8 +427,7 @@ xfs_attr_rmtval_get(
 				return error;
 
 			error = xfs_attr_rmtval_copyout(mp, bp, args->dp,
-							&offset, &valuelen,
-							&dst);
+					args->owner, &offset, &valuelen, &dst);
 			xfs_buf_relse(bp);
 			if (error)
 				return error;

[PATCH 5/9] xfs: validate dabtree node buffer owners

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Check the owner field of dabtree node blocks.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_da_btree.c |  108 ++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_da_btree.h |    1 
 fs/xfs/xfs_attr_list.c       |   10 ++++
 3 files changed, 119 insertions(+)


diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index a7782055db6cd..61719f6093ec8 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -251,6 +251,25 @@ xfs_da3_node_verify(
 	return NULL;
 }
 
+xfs_failaddr_t
+xfs_da3_node_header_check(
+	struct xfs_buf		*bp,
+	xfs_ino_t		owner)
+{
+	struct xfs_mount	*mp = bp->b_mount;
+
+	if (xfs_has_crc(mp)) {
+		struct xfs_da3_blkinfo *hdr3 = bp->b_addr;
+
+		ASSERT(hdr3->hdr.magic == cpu_to_be16(XFS_DA3_NODE_MAGIC));
+
+		if (be64_to_cpu(hdr3->owner) != owner)
+			return __this_address;
+	}
+
+	return NULL;
+}
+
 xfs_failaddr_t
 xfs_da3_header_check(
 	struct xfs_buf		*bp,
@@ -265,6 +284,8 @@ xfs_da3_header_check(
 	switch (hdr->magic) {
 	case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC):
 		return xfs_attr3_leaf_header_check(bp, owner);
+	case cpu_to_be16(XFS_DA3_NODE_MAGIC):
+		return xfs_da3_node_header_check(bp, owner);
 	}
 
 	return NULL;
@@ -1217,6 +1238,7 @@ xfs_da3_root_join(
 	struct xfs_da3_icnode_hdr oldroothdr;
 	int			error;
 	struct xfs_inode	*dp = state->args->dp;
+	xfs_failaddr_t		fa;
 
 	trace_xfs_da_root_join(state->args);
 
@@ -1243,6 +1265,13 @@ xfs_da3_root_join(
 	error = xfs_da3_node_read(args->trans, dp, child, &bp, args->whichfork);
 	if (error)
 		return error;
+	fa = xfs_da3_header_check(bp, args->owner);
+	if (fa) {
+		__xfs_buf_mark_corrupt(bp, fa);
+		xfs_trans_brelse(args->trans, bp);
+		xfs_da_mark_sick(args);
+		return -EFSCORRUPTED;
+	}
 	xfs_da_blkinfo_onlychild_validate(bp->b_addr, oldroothdr.level);
 
 	/*
@@ -1277,6 +1306,7 @@ xfs_da3_node_toosmall(
 	struct xfs_da_blkinfo	*info;
 	xfs_dablk_t		blkno;
 	struct xfs_buf		*bp;
+	xfs_failaddr_t		fa;
 	struct xfs_da3_icnode_hdr nodehdr;
 	int			count;
 	int			forward;
@@ -1351,6 +1381,13 @@ xfs_da3_node_toosmall(
 				state->args->whichfork);
 		if (error)
 			return error;
+		fa = xfs_da3_node_header_check(bp, state->args->owner);
+		if (fa) {
+			__xfs_buf_mark_corrupt(bp, fa);
+			xfs_trans_brelse(state->args->trans, bp);
+			xfs_da_mark_sick(state->args);
+			return -EFSCORRUPTED;
+		}
 
 		node = bp->b_addr;
 		xfs_da3_node_hdr_from_disk(dp->i_mount, &thdr, node);
@@ -1673,6 +1710,13 @@ xfs_da3_node_lookup_int(
 			return -EFSCORRUPTED;
 		}
 
+		fa = xfs_da3_node_header_check(blk->bp, args->owner);
+		if (fa) {
+			__xfs_buf_mark_corrupt(blk->bp, fa);
+			xfs_da_mark_sick(args);
+			return -EFSCORRUPTED;
+		}
+
 		blk->magic = XFS_DA_NODE_MAGIC;
 
 		/*
@@ -1845,6 +1889,7 @@ xfs_da3_blk_link(
 	struct xfs_da_blkinfo	*tmp_info;
 	struct xfs_da_args	*args;
 	struct xfs_buf		*bp;
+	xfs_failaddr_t		fa;
 	int			before = 0;
 	int			error;
 	struct xfs_inode	*dp = state->args->dp;
@@ -1888,6 +1933,13 @@ xfs_da3_blk_link(
 						&bp, args->whichfork);
 			if (error)
 				return error;
+			fa = xfs_da3_header_check(bp, args->owner);
+			if (fa) {
+				__xfs_buf_mark_corrupt(bp, fa);
+				xfs_trans_brelse(args->trans, bp);
+				xfs_da_mark_sick(args);
+				return -EFSCORRUPTED;
+			}
 			ASSERT(bp != NULL);
 			tmp_info = bp->b_addr;
 			ASSERT(tmp_info->magic == old_info->magic);
@@ -1909,6 +1961,13 @@ xfs_da3_blk_link(
 						&bp, args->whichfork);
 			if (error)
 				return error;
+			fa = xfs_da3_header_check(bp, args->owner);
+			if (fa) {
+				__xfs_buf_mark_corrupt(bp, fa);
+				xfs_trans_brelse(args->trans, bp);
+				xfs_da_mark_sick(args);
+				return -EFSCORRUPTED;
+			}
 			ASSERT(bp != NULL);
 			tmp_info = bp->b_addr;
 			ASSERT(tmp_info->magic == old_info->magic);
@@ -1938,6 +1997,7 @@ xfs_da3_blk_unlink(
 	struct xfs_da_blkinfo	*tmp_info;
 	struct xfs_da_args	*args;
 	struct xfs_buf		*bp;
+	xfs_failaddr_t		fa;
 	int			error;
 
 	/*
@@ -1968,6 +2028,13 @@ xfs_da3_blk_unlink(
 						&bp, args->whichfork);
 			if (error)
 				return error;
+			fa = xfs_da3_header_check(bp, args->owner);
+			if (fa) {
+				__xfs_buf_mark_corrupt(bp, fa);
+				xfs_trans_brelse(args->trans, bp);
+				xfs_da_mark_sick(args);
+				return -EFSCORRUPTED;
+			}
 			ASSERT(bp != NULL);
 			tmp_info = bp->b_addr;
 			ASSERT(tmp_info->magic == save_info->magic);
@@ -1985,6 +2052,13 @@ xfs_da3_blk_unlink(
 						&bp, args->whichfork);
 			if (error)
 				return error;
+			fa = xfs_da3_header_check(bp, args->owner);
+			if (fa) {
+				__xfs_buf_mark_corrupt(bp, fa);
+				xfs_trans_brelse(args->trans, bp);
+				xfs_da_mark_sick(args);
+				return -EFSCORRUPTED;
+			}
 			ASSERT(bp != NULL);
 			tmp_info = bp->b_addr;
 			ASSERT(tmp_info->magic == save_info->magic);
@@ -2100,6 +2174,12 @@ xfs_da3_path_shift(
 		switch (be16_to_cpu(info->magic)) {
 		case XFS_DA_NODE_MAGIC:
 		case XFS_DA3_NODE_MAGIC:
+			fa = xfs_da3_node_header_check(blk->bp, args->owner);
+			if (fa) {
+				__xfs_buf_mark_corrupt(blk->bp, fa);
+				xfs_da_mark_sick(args);
+				return -EFSCORRUPTED;
+			}
 			blk->magic = XFS_DA_NODE_MAGIC;
 			xfs_da3_node_hdr_from_disk(dp->i_mount, &nodehdr,
 						   bp->b_addr);
@@ -2404,6 +2484,13 @@ xfs_da3_swap_lastblock(
 		error = xfs_da3_node_read(tp, dp, sib_blkno, &sib_buf, w);
 		if (error)
 			goto done;
+		fa = xfs_da3_header_check(sib_buf, args->owner);
+		if (fa) {
+			__xfs_buf_mark_corrupt(sib_buf, fa);
+			xfs_da_mark_sick(args);
+			error = -EFSCORRUPTED;
+			goto done;
+		}
 		sib_info = sib_buf->b_addr;
 		if (XFS_IS_CORRUPT(mp,
 				   be32_to_cpu(sib_info->forw) != last_blkno ||
@@ -2425,6 +2512,13 @@ xfs_da3_swap_lastblock(
 		error = xfs_da3_node_read(tp, dp, sib_blkno, &sib_buf, w);
 		if (error)
 			goto done;
+		fa = xfs_da3_header_check(sib_buf, args->owner);
+		if (fa) {
+			__xfs_buf_mark_corrupt(sib_buf, fa);
+			xfs_da_mark_sick(args);
+			error = -EFSCORRUPTED;
+			goto done;
+		}
 		sib_info = sib_buf->b_addr;
 		if (XFS_IS_CORRUPT(mp,
 				   be32_to_cpu(sib_info->back) != last_blkno ||
@@ -2448,6 +2542,13 @@ xfs_da3_swap_lastblock(
 		error = xfs_da3_node_read(tp, dp, par_blkno, &par_buf, w);
 		if (error)
 			goto done;
+		fa = xfs_da3_node_header_check(par_buf, args->owner);
+		if (fa) {
+			__xfs_buf_mark_corrupt(par_buf, fa);
+			xfs_da_mark_sick(args);
+			error = -EFSCORRUPTED;
+			goto done;
+		}
 		par_node = par_buf->b_addr;
 		xfs_da3_node_hdr_from_disk(dp->i_mount, &par_hdr, par_node);
 		if (XFS_IS_CORRUPT(mp,
@@ -2497,6 +2598,13 @@ xfs_da3_swap_lastblock(
 		error = xfs_da3_node_read(tp, dp, par_blkno, &par_buf, w);
 		if (error)
 			goto done;
+		fa = xfs_da3_node_header_check(par_buf, args->owner);
+		if (fa) {
+			__xfs_buf_mark_corrupt(par_buf, fa);
+			xfs_da_mark_sick(args);
+			error = -EFSCORRUPTED;
+			goto done;
+		}
 		par_node = par_buf->b_addr;
 		xfs_da3_node_hdr_from_disk(dp->i_mount, &par_hdr, par_node);
 		if (XFS_IS_CORRUPT(mp, par_hdr.level != level)) {
diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h
index 99618e0c8a72b..7a004786ee0a2 100644
--- a/fs/xfs/libxfs/xfs_da_btree.h
+++ b/fs/xfs/libxfs/xfs_da_btree.h
@@ -237,6 +237,7 @@ void	xfs_da3_node_hdr_from_disk(struct xfs_mount *mp,
 void	xfs_da3_node_hdr_to_disk(struct xfs_mount *mp,
 		struct xfs_da_intnode *to, struct xfs_da3_icnode_hdr *from);
 xfs_failaddr_t xfs_da3_header_check(struct xfs_buf *bp, xfs_ino_t owner);
+xfs_failaddr_t xfs_da3_node_header_check(struct xfs_buf *bp, xfs_ino_t owner);
 
 extern struct kmem_cache	*xfs_da_state_cache;
 
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index 2954ed7cfaf43..24516f3ff2df7 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -240,6 +240,10 @@ xfs_attr_node_list_lookup(
 			goto out_corruptbuf;
 		}
 
+		fa = xfs_da3_node_header_check(bp, dp->i_ino);
+		if (fa)
+			goto out_corruptbuf;
+
 		xfs_da3_node_hdr_from_disk(mp, &nodehdr, node);
 
 		/* Tree taller than we can handle; bail out! */
@@ -334,6 +338,12 @@ xfs_attr_node_list(
 			case XFS_DA_NODE_MAGIC:
 			case XFS_DA3_NODE_MAGIC:
 				trace_xfs_attr_list_wrong_blk(context);
+				fa = xfs_da3_node_header_check(bp,
+						dp->i_ino);
+				if (fa) {
+					__xfs_buf_mark_corrupt(bp, fa);
+					xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
+				}
 				xfs_trans_brelse(context->tp, bp);
 				bp = NULL;
 				break;

[PATCH 6/9] xfs: validate directory leaf buffer owners

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Check the owner field of directory leaf blocks.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_da_btree.c  |   16 ++++++++++
 fs/xfs/libxfs/xfs_dir2.h      |    2 +
 fs/xfs/libxfs/xfs_dir2_leaf.c |   64 +++++++++++++++++++++++++++++++++++++----
 fs/xfs/libxfs/xfs_dir2_node.c |    3 +-
 fs/xfs/libxfs/xfs_dir2_priv.h |    4 +--
 fs/xfs/scrub/dir.c            |    2 +
 6 files changed, 81 insertions(+), 10 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 61719f6093ec8..29646e3fbb56b 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -286,8 +286,12 @@ xfs_da3_header_check(
 		return xfs_attr3_leaf_header_check(bp, owner);
 	case cpu_to_be16(XFS_DA3_NODE_MAGIC):
 		return xfs_da3_node_header_check(bp, owner);
+	case cpu_to_be16(XFS_DIR3_LEAF1_MAGIC):
+	case cpu_to_be16(XFS_DIR3_LEAFN_MAGIC):
+		return xfs_dir3_leaf_header_check(bp, owner);
 	}
 
+	ASSERT(0);
 	return NULL;
 }
 
@@ -1698,6 +1702,12 @@ xfs_da3_node_lookup_int(
 
 		if (magic == XFS_DIR2_LEAFN_MAGIC ||
 		    magic == XFS_DIR3_LEAFN_MAGIC) {
+			fa = xfs_dir3_leaf_header_check(blk->bp, args->owner);
+			if (fa) {
+				__xfs_buf_mark_corrupt(blk->bp, fa);
+				xfs_da_mark_sick(args);
+				return -EFSCORRUPTED;
+			}
 			blk->magic = XFS_DIR2_LEAFN_MAGIC;
 			blk->hashval = xfs_dir2_leaf_lasthash(args->dp,
 							      blk->bp, NULL);
@@ -2206,6 +2216,12 @@ xfs_da3_path_shift(
 			break;
 		case XFS_DIR2_LEAFN_MAGIC:
 		case XFS_DIR3_LEAFN_MAGIC:
+			fa = xfs_dir3_leaf_header_check(blk->bp, args->owner);
+			if (fa) {
+				__xfs_buf_mark_corrupt(blk->bp, fa);
+				xfs_da_mark_sick(args);
+				return -EFSCORRUPTED;
+			}
 			blk->magic = XFS_DIR2_LEAFN_MAGIC;
 			ASSERT(level == path->active-1);
 			blk->index = 0;
diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h
index ac3c264402dda..0b01dd6ccf1eb 100644
--- a/fs/xfs/libxfs/xfs_dir2.h
+++ b/fs/xfs/libxfs/xfs_dir2.h
@@ -98,6 +98,8 @@ extern struct xfs_dir2_data_free *xfs_dir2_data_freefind(
 
 extern int xfs_dir_ino_validate(struct xfs_mount *mp, xfs_ino_t ino);
 
+xfs_failaddr_t xfs_dir3_leaf_header_check(struct xfs_buf *bp, xfs_ino_t owner);
+
 extern const struct xfs_buf_ops xfs_dir3_block_buf_ops;
 extern const struct xfs_buf_ops xfs_dir3_leafn_buf_ops;
 extern const struct xfs_buf_ops xfs_dir3_leaf1_buf_ops;
diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c
index 20ce057d12e82..16a581e225a37 100644
--- a/fs/xfs/libxfs/xfs_dir2_leaf.c
+++ b/fs/xfs/libxfs/xfs_dir2_leaf.c
@@ -208,6 +208,28 @@ xfs_dir3_leaf_verify(
 	return xfs_dir3_leaf_check_int(mp, &leafhdr, bp->b_addr, true);
 }
 
+xfs_failaddr_t
+xfs_dir3_leaf_header_check(
+	struct xfs_buf		*bp,
+	xfs_ino_t		owner)
+{
+	struct xfs_mount	*mp = bp->b_mount;
+
+	if (xfs_has_crc(mp)) {
+		struct xfs_dir3_leaf *hdr3 = bp->b_addr;
+
+		ASSERT(hdr3->hdr.info.hdr.magic ==
+					cpu_to_be16(XFS_DIR3_LEAF1_MAGIC) ||
+		       hdr3->hdr.info.hdr.magic ==
+					cpu_to_be16(XFS_DIR3_LEAFN_MAGIC));
+
+		if (be64_to_cpu(hdr3->hdr.info.owner) != owner)
+			return __this_address;
+	}
+
+	return NULL;
+}
+
 static void
 xfs_dir3_leaf_read_verify(
 	struct xfs_buf  *bp)
@@ -271,32 +293,60 @@ int
 xfs_dir3_leaf_read(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*dp,
+	xfs_ino_t		owner,
 	xfs_dablk_t		fbno,
 	struct xfs_buf		**bpp)
 {
+	xfs_failaddr_t		fa;
 	int			err;
 
 	err = xfs_da_read_buf(tp, dp, fbno, 0, bpp, XFS_DATA_FORK,
 			&xfs_dir3_leaf1_buf_ops);
-	if (!err && tp && *bpp)
+	if (err || !(*bpp))
+		return err;
+
+	fa = xfs_dir3_leaf_header_check(*bpp, owner);
+	if (fa) {
+		__xfs_buf_mark_corrupt(*bpp, fa);
+		xfs_trans_brelse(tp, *bpp);
+		*bpp = NULL;
+		xfs_dirattr_mark_sick(dp, XFS_DATA_FORK);
+		return -EFSCORRUPTED;
+	}
+
+	if (tp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAF1_BUF);
-	return err;
+	return 0;
 }
 
 int
 xfs_dir3_leafn_read(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*dp,
+	xfs_ino_t		owner,
 	xfs_dablk_t		fbno,
 	struct xfs_buf		**bpp)
 {
+	xfs_failaddr_t		fa;
 	int			err;
 
 	err = xfs_da_read_buf(tp, dp, fbno, 0, bpp, XFS_DATA_FORK,
 			&xfs_dir3_leafn_buf_ops);
-	if (!err && tp && *bpp)
+	if (err || !(*bpp))
+		return err;
+
+	fa = xfs_dir3_leaf_header_check(*bpp, owner);
+	if (fa) {
+		__xfs_buf_mark_corrupt(*bpp, fa);
+		xfs_trans_brelse(tp, *bpp);
+		*bpp = NULL;
+		xfs_dirattr_mark_sick(dp, XFS_DATA_FORK);
+		return -EFSCORRUPTED;
+	}
+
+	if (tp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAFN_BUF);
-	return err;
+	return 0;
 }
 
 /*
@@ -646,7 +696,8 @@ xfs_dir2_leaf_addname(
 
 	trace_xfs_dir2_leaf_addname(args);
 
-	error = xfs_dir3_leaf_read(tp, dp, args->geo->leafblk, &lbp);
+	error = xfs_dir3_leaf_read(tp, dp, args->owner, args->geo->leafblk,
+			&lbp);
 	if (error)
 		return error;
 
@@ -1237,7 +1288,8 @@ xfs_dir2_leaf_lookup_int(
 	tp = args->trans;
 	mp = dp->i_mount;
 
-	error = xfs_dir3_leaf_read(tp, dp, args->geo->leafblk, &lbp);
+	error = xfs_dir3_leaf_read(tp, dp, args->owner, args->geo->leafblk,
+			&lbp);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c
index 1ad7405f9c389..e21965788188b 100644
--- a/fs/xfs/libxfs/xfs_dir2_node.c
+++ b/fs/xfs/libxfs/xfs_dir2_node.c
@@ -1562,7 +1562,8 @@ xfs_dir2_leafn_toosmall(
 		/*
 		 * Read the sibling leaf block.
 		 */
-		error = xfs_dir3_leafn_read(state->args->trans, dp, blkno, &bp);
+		error = xfs_dir3_leafn_read(state->args->trans, dp,
+				state->args->owner, blkno, &bp);
 		if (error)
 			return error;
 
diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h
index 1db2e60ba827f..2f0e3ad47b371 100644
--- a/fs/xfs/libxfs/xfs_dir2_priv.h
+++ b/fs/xfs/libxfs/xfs_dir2_priv.h
@@ -95,9 +95,9 @@ void xfs_dir2_leaf_hdr_from_disk(struct xfs_mount *mp,
 void xfs_dir2_leaf_hdr_to_disk(struct xfs_mount *mp, struct xfs_dir2_leaf *to,
 		struct xfs_dir3_icleaf_hdr *from);
 int xfs_dir3_leaf_read(struct xfs_trans *tp, struct xfs_inode *dp,
-		xfs_dablk_t fbno, struct xfs_buf **bpp);
+		xfs_ino_t owner, xfs_dablk_t fbno, struct xfs_buf **bpp);
 int xfs_dir3_leafn_read(struct xfs_trans *tp, struct xfs_inode *dp,
-		xfs_dablk_t fbno, struct xfs_buf **bpp);
+		xfs_ino_t owner, xfs_dablk_t fbno, struct xfs_buf **bpp);
 extern int xfs_dir2_block_to_leaf(struct xfs_da_args *args,
 		struct xfs_buf *dbp);
 extern int xfs_dir2_leaf_addname(struct xfs_da_args *args);
diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index 042e28547e044..d94e265a8e1f2 100644
--- a/fs/xfs/scrub/dir.c
+++ b/fs/xfs/scrub/dir.c
@@ -470,7 +470,7 @@ xchk_directory_leaf1_bestfree(
 	int				error;
 
 	/* Read the free space block. */
-	error = xfs_dir3_leaf_read(sc->tp, sc->ip, lblk, &bp);
+	error = xfs_dir3_leaf_read(sc->tp, sc->ip, sc->ip->i_ino, lblk, &bp);
 	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
 		return error;
 	xchk_buffer_recheck(sc, bp);

[PATCH 7/9] xfs: validate explicit directory data buffer owners

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Port the existing directory data header checking function to accept an
owner number instead of an xfs_inode, then update the callsites to use
xfs_da_args.owner when possible.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_dir2.h       |    1 +
 fs/xfs/libxfs/xfs_dir2_block.c |    3 ++-
 fs/xfs/libxfs/xfs_dir2_data.c  |   15 +++++++++------
 fs/xfs/libxfs/xfs_dir2_leaf.c  |   21 +++++++++++----------
 fs/xfs/libxfs/xfs_dir2_node.c  |    7 +++----
 fs/xfs/libxfs/xfs_dir2_priv.h  |    3 ++-
 fs/xfs/scrub/dir.c             |   14 +++++++-------
 fs/xfs/scrub/readdir.c         |    2 +-
 fs/xfs/xfs_dir2_readdir.c      |    3 ++-
 9 files changed, 38 insertions(+), 31 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h
index 0b01dd6ccf1eb..537596b9de4a4 100644
--- a/fs/xfs/libxfs/xfs_dir2.h
+++ b/fs/xfs/libxfs/xfs_dir2.h
@@ -99,6 +99,7 @@ extern struct xfs_dir2_data_free *xfs_dir2_data_freefind(
 extern int xfs_dir_ino_validate(struct xfs_mount *mp, xfs_ino_t ino);
 
 xfs_failaddr_t xfs_dir3_leaf_header_check(struct xfs_buf *bp, xfs_ino_t owner);
+xfs_failaddr_t xfs_dir3_data_header_check(struct xfs_buf *bp, xfs_ino_t owner);
 
 extern const struct xfs_buf_ops xfs_dir3_block_buf_ops;
 extern const struct xfs_buf_ops xfs_dir3_leafn_buf_ops;
diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c
index 6bda6a4906718..184341bb1f6af 100644
--- a/fs/xfs/libxfs/xfs_dir2_block.c
+++ b/fs/xfs/libxfs/xfs_dir2_block.c
@@ -982,7 +982,8 @@ xfs_dir2_leaf_to_block(
 	 * Read the data block if we don't already have it, give up if it fails.
 	 */
 	if (!dbp) {
-		error = xfs_dir3_data_read(tp, dp, args->geo->datablk, 0, &dbp);
+		error = xfs_dir3_data_read(tp, dp, args->owner,
+				args->geo->datablk, 0, &dbp);
 		if (error)
 			return error;
 	}
diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c
index c3ef720b5ff6e..00c2061aed346 100644
--- a/fs/xfs/libxfs/xfs_dir2_data.c
+++ b/fs/xfs/libxfs/xfs_dir2_data.c
@@ -395,17 +395,19 @@ static const struct xfs_buf_ops xfs_dir3_data_reada_buf_ops = {
 	.verify_write = xfs_dir3_data_write_verify,
 };
 
-static xfs_failaddr_t
+xfs_failaddr_t
 xfs_dir3_data_header_check(
-	struct xfs_inode	*dp,
-	struct xfs_buf		*bp)
+	struct xfs_buf		*bp,
+	xfs_ino_t		owner)
 {
-	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_mount	*mp = bp->b_mount;
 
 	if (xfs_has_crc(mp)) {
 		struct xfs_dir3_data_hdr *hdr3 = bp->b_addr;
 
-		if (be64_to_cpu(hdr3->hdr.owner) != dp->i_ino)
+		ASSERT(hdr3->hdr.magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC));
+
+		if (be64_to_cpu(hdr3->hdr.owner) != owner)
 			return __this_address;
 	}
 
@@ -416,6 +418,7 @@ int
 xfs_dir3_data_read(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*dp,
+	xfs_ino_t		owner,
 	xfs_dablk_t		bno,
 	unsigned int		flags,
 	struct xfs_buf		**bpp)
@@ -429,7 +432,7 @@ xfs_dir3_data_read(
 		return err;
 
 	/* Check things that we can't do in the verifier. */
-	fa = xfs_dir3_data_header_check(dp, *bpp);
+	fa = xfs_dir3_data_header_check(*bpp, owner);
 	if (fa) {
 		__xfs_buf_mark_corrupt(*bpp, fa);
 		xfs_trans_brelse(tp, *bpp);
diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c
index 16a581e225a37..a6eee26044875 100644
--- a/fs/xfs/libxfs/xfs_dir2_leaf.c
+++ b/fs/xfs/libxfs/xfs_dir2_leaf.c
@@ -884,9 +884,9 @@ xfs_dir2_leaf_addname(
 		 * Already had space in some data block.
 		 * Just read that one in.
 		 */
-		error = xfs_dir3_data_read(tp, dp,
-				   xfs_dir2_db_to_da(args->geo, use_block),
-				   0, &dbp);
+		error = xfs_dir3_data_read(tp, dp, args->owner,
+				xfs_dir2_db_to_da(args->geo, use_block), 0,
+				&dbp);
 		if (error) {
 			xfs_trans_brelse(tp, lbp);
 			return error;
@@ -1327,9 +1327,9 @@ xfs_dir2_leaf_lookup_int(
 		if (newdb != curdb) {
 			if (dbp)
 				xfs_trans_brelse(tp, dbp);
-			error = xfs_dir3_data_read(tp, dp,
-					   xfs_dir2_db_to_da(args->geo, newdb),
-					   0, &dbp);
+			error = xfs_dir3_data_read(tp, dp, args->owner,
+					xfs_dir2_db_to_da(args->geo, newdb), 0,
+					&dbp);
 			if (error) {
 				xfs_trans_brelse(tp, lbp);
 				return error;
@@ -1369,9 +1369,9 @@ xfs_dir2_leaf_lookup_int(
 		ASSERT(cidb != -1);
 		if (cidb != curdb) {
 			xfs_trans_brelse(tp, dbp);
-			error = xfs_dir3_data_read(tp, dp,
-					   xfs_dir2_db_to_da(args->geo, cidb),
-					   0, &dbp);
+			error = xfs_dir3_data_read(tp, dp, args->owner,
+					xfs_dir2_db_to_da(args->geo, cidb), 0,
+					&dbp);
 			if (error) {
 				xfs_trans_brelse(tp, lbp);
 				return error;
@@ -1665,7 +1665,8 @@ xfs_dir2_leaf_trim_data(
 	/*
 	 * Read the offending data block.  We need its buffer.
 	 */
-	error = xfs_dir3_data_read(tp, dp, xfs_dir2_db_to_da(geo, db), 0, &dbp);
+	error = xfs_dir3_data_read(tp, dp, args->owner,
+			xfs_dir2_db_to_da(geo, db), 0, &dbp);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c
index e21965788188b..dc85197b8448e 100644
--- a/fs/xfs/libxfs/xfs_dir2_node.c
+++ b/fs/xfs/libxfs/xfs_dir2_node.c
@@ -863,7 +863,7 @@ xfs_dir2_leafn_lookup_for_entry(
 				ASSERT(state->extravalid);
 				curbp = state->extrablk.bp;
 			} else {
-				error = xfs_dir3_data_read(tp, dp,
+				error = xfs_dir3_data_read(tp, dp, args->owner,
 						xfs_dir2_db_to_da(args->geo,
 								  newdb),
 						0, &curbp);
@@ -1949,9 +1949,8 @@ xfs_dir2_node_addname_int(
 						  &freehdr, &findex);
 	} else {
 		/* Read the data block in. */
-		error = xfs_dir3_data_read(tp, dp,
-					   xfs_dir2_db_to_da(args->geo, dbno),
-					   0, &dbp);
+		error = xfs_dir3_data_read(tp, dp, args->owner,
+				xfs_dir2_db_to_da(args->geo, dbno), 0, &dbp);
 	}
 	if (error)
 		return error;
diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h
index 2f0e3ad47b371..879aa2e9fd730 100644
--- a/fs/xfs/libxfs/xfs_dir2_priv.h
+++ b/fs/xfs/libxfs/xfs_dir2_priv.h
@@ -78,7 +78,8 @@ extern void xfs_dir3_data_check(struct xfs_inode *dp, struct xfs_buf *bp);
 extern xfs_failaddr_t __xfs_dir3_data_check(struct xfs_inode *dp,
 		struct xfs_buf *bp);
 int xfs_dir3_data_read(struct xfs_trans *tp, struct xfs_inode *dp,
-		xfs_dablk_t bno, unsigned int flags, struct xfs_buf **bpp);
+		xfs_ino_t owner, xfs_dablk_t bno, unsigned int flags,
+		struct xfs_buf **bpp);
 int xfs_dir3_data_readahead(struct xfs_inode *dp, xfs_dablk_t bno,
 		unsigned int flags);
 
diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index d94e265a8e1f2..6b572196bb43d 100644
--- a/fs/xfs/scrub/dir.c
+++ b/fs/xfs/scrub/dir.c
@@ -196,8 +196,8 @@ xchk_dir_rec(
 		xchk_da_set_corrupt(ds, level);
 		goto out;
 	}
-	error = xfs_dir3_data_read(ds->dargs.trans, dp, rec_bno,
-			XFS_DABUF_MAP_HOLE_OK, &bp);
+	error = xfs_dir3_data_read(ds->dargs.trans, dp, ds->dargs.owner,
+			rec_bno, XFS_DABUF_MAP_HOLE_OK, &bp);
 	if (!xchk_fblock_process_error(ds->sc, XFS_DATA_FORK, rec_bno,
 			&error))
 		goto out;
@@ -318,7 +318,8 @@ xchk_directory_data_bestfree(
 		error = xfs_dir3_block_read(sc->tp, sc->ip, &bp);
 	} else {
 		/* dir data format */
-		error = xfs_dir3_data_read(sc->tp, sc->ip, lblk, 0, &bp);
+		error = xfs_dir3_data_read(sc->tp, sc->ip, sc->ip->i_ino, lblk,
+				0, &bp);
 	}
 	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
 		goto out;
@@ -531,10 +532,9 @@ xchk_directory_leaf1_bestfree(
 	/* Check all the bestfree entries. */
 	for (i = 0; i < bestcount; i++, bestp++) {
 		best = be16_to_cpu(*bestp);
-		error = xfs_dir3_data_read(sc->tp, sc->ip,
+		error = xfs_dir3_data_read(sc->tp, sc->ip, args->owner,
 				xfs_dir2_db_to_da(args->geo, i),
-				XFS_DABUF_MAP_HOLE_OK,
-				&dbp);
+				XFS_DABUF_MAP_HOLE_OK, &dbp);
 		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk,
 				&error))
 			break;
@@ -597,7 +597,7 @@ xchk_directory_free_bestfree(
 			stale++;
 			continue;
 		}
-		error = xfs_dir3_data_read(sc->tp, sc->ip,
+		error = xfs_dir3_data_read(sc->tp, sc->ip, args->owner,
 				(freehdr.firstdb + i) * args->geo->fsbcount,
 				0, &dbp);
 		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk,
diff --git a/fs/xfs/scrub/readdir.c b/fs/xfs/scrub/readdir.c
index 20375c0972db9..33035b98d25cf 100644
--- a/fs/xfs/scrub/readdir.c
+++ b/fs/xfs/scrub/readdir.c
@@ -177,7 +177,7 @@ xchk_read_leaf_dir_buf(
 	if (new_off > *curoff)
 		*curoff = new_off;
 
-	return xfs_dir3_data_read(tp, dp, map.br_startoff, 0, bpp);
+	return xfs_dir3_data_read(tp, dp, dp->i_ino, map.br_startoff, 0, bpp);
 }
 
 /* Call a function for every entry in a leaf directory. */
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index 263a897bee49e..260943447be9b 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -284,7 +284,8 @@ xfs_dir2_leaf_readbuf(
 	new_off = xfs_dir2_da_to_byte(geo, map.br_startoff);
 	if (new_off > *cur_off)
 		*cur_off = new_off;
-	error = xfs_dir3_data_read(args->trans, dp, map.br_startoff, 0, &bp);
+	error = xfs_dir3_data_read(args->trans, dp, args->owner,
+			map.br_startoff, 0, &bp);
 	if (error)
 		goto out;
 

[PATCH 8/9] xfs: validate explicit directory block buffer owners

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Port the existing directory block header checking function to accept an
owner number instead of an xfs_inode, then update the callsites to use
xfs_da_args.owner when possible.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_dir2.h       |    1 +
 fs/xfs/libxfs/xfs_dir2_block.c |   22 ++++++++++++++--------
 fs/xfs/libxfs/xfs_dir2_priv.h  |    2 +-
 fs/xfs/libxfs/xfs_swapext.c    |    2 +-
 fs/xfs/scrub/dir.c             |    2 +-
 fs/xfs/scrub/readdir.c         |    2 +-
 fs/xfs/xfs_dir2_readdir.c      |    2 +-
 7 files changed, 20 insertions(+), 13 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h
index 537596b9de4a4..f99788a1f3e63 100644
--- a/fs/xfs/libxfs/xfs_dir2.h
+++ b/fs/xfs/libxfs/xfs_dir2.h
@@ -100,6 +100,7 @@ extern int xfs_dir_ino_validate(struct xfs_mount *mp, xfs_ino_t ino);
 
 xfs_failaddr_t xfs_dir3_leaf_header_check(struct xfs_buf *bp, xfs_ino_t owner);
 xfs_failaddr_t xfs_dir3_data_header_check(struct xfs_buf *bp, xfs_ino_t owner);
+xfs_failaddr_t xfs_dir3_block_header_check(struct xfs_buf *bp, xfs_ino_t owner);
 
 extern const struct xfs_buf_ops xfs_dir3_block_buf_ops;
 extern const struct xfs_buf_ops xfs_dir3_leafn_buf_ops;
diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c
index 184341bb1f6af..30eef4d9d8667 100644
--- a/fs/xfs/libxfs/xfs_dir2_block.c
+++ b/fs/xfs/libxfs/xfs_dir2_block.c
@@ -115,18 +115,23 @@ const struct xfs_buf_ops xfs_dir3_block_buf_ops = {
 	.verify_struct = xfs_dir3_block_verify,
 };
 
-static xfs_failaddr_t
+xfs_failaddr_t
 xfs_dir3_block_header_check(
-	struct xfs_inode	*dp,
-	struct xfs_buf		*bp)
+	struct xfs_buf		*bp,
+	xfs_ino_t		owner)
 {
-	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_mount	*mp = bp->b_mount;
 
 	if (xfs_has_crc(mp)) {
 		struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;
 
-		if (be64_to_cpu(hdr3->owner) != dp->i_ino)
+		ASSERT(hdr3->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
+
+		if (be64_to_cpu(hdr3->owner) != owner) {
+			xfs_err(NULL, "dir block owner 0x%llx doesnt match block 0x%llx", owner, be64_to_cpu(hdr3->owner));
+			dump_stack();
 			return __this_address;
+		}
 	}
 
 	return NULL;
@@ -136,6 +141,7 @@ int
 xfs_dir3_block_read(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*dp,
+	xfs_ino_t		owner,
 	struct xfs_buf		**bpp)
 {
 	struct xfs_mount	*mp = dp->i_mount;
@@ -148,7 +154,7 @@ xfs_dir3_block_read(
 		return err;
 
 	/* Check things that we can't do in the verifier. */
-	fa = xfs_dir3_block_header_check(dp, *bpp);
+	fa = xfs_dir3_block_header_check(*bpp, owner);
 	if (fa) {
 		__xfs_buf_mark_corrupt(*bpp, fa);
 		xfs_trans_brelse(tp, *bpp);
@@ -383,7 +389,7 @@ xfs_dir2_block_addname(
 	tp = args->trans;
 
 	/* Read the (one and only) directory block into bp. */
-	error = xfs_dir3_block_read(tp, dp, &bp);
+	error = xfs_dir3_block_read(tp, dp, args->owner, &bp);
 	if (error)
 		return error;
 
@@ -698,7 +704,7 @@ xfs_dir2_block_lookup_int(
 	dp = args->dp;
 	tp = args->trans;
 
-	error = xfs_dir3_block_read(tp, dp, &bp);
+	error = xfs_dir3_block_read(tp, dp, args->owner, &bp);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h
index 879aa2e9fd730..969e36a03fe5e 100644
--- a/fs/xfs/libxfs/xfs_dir2_priv.h
+++ b/fs/xfs/libxfs/xfs_dir2_priv.h
@@ -51,7 +51,7 @@ extern int xfs_dir_cilookup_result(struct xfs_da_args *args,
 
 /* xfs_dir2_block.c */
 extern int xfs_dir3_block_read(struct xfs_trans *tp, struct xfs_inode *dp,
-			       struct xfs_buf **bpp);
+			       xfs_ino_t owner, struct xfs_buf **bpp);
 extern int xfs_dir2_block_addname(struct xfs_da_args *args);
 extern int xfs_dir2_block_lookup(struct xfs_da_args *args);
 extern int xfs_dir2_block_removename(struct xfs_da_args *args);
diff --git a/fs/xfs/libxfs/xfs_swapext.c b/fs/xfs/libxfs/xfs_swapext.c
index 0446376365ec7..554da23a575eb 100644
--- a/fs/xfs/libxfs/xfs_swapext.c
+++ b/fs/xfs/libxfs/xfs_swapext.c
@@ -573,7 +573,7 @@ xfs_swapext_dir_to_sf(
 	if (!isblock)
 		return 0;
 
-	error = xfs_dir3_block_read(tp, sxi->sxi_ip2, &bp);
+	error = xfs_dir3_block_read(tp, sxi->sxi_ip2, sxi->sxi_ip2->i_ino, &bp);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index 6b572196bb43d..43f5bc8ce0d46 100644
--- a/fs/xfs/scrub/dir.c
+++ b/fs/xfs/scrub/dir.c
@@ -315,7 +315,7 @@ xchk_directory_data_bestfree(
 		/* dir block format */
 		if (lblk != XFS_B_TO_FSBT(mp, XFS_DIR2_DATA_OFFSET))
 			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
-		error = xfs_dir3_block_read(sc->tp, sc->ip, &bp);
+		error = xfs_dir3_block_read(sc->tp, sc->ip, sc->ip->i_ino, &bp);
 	} else {
 		/* dir data format */
 		error = xfs_dir3_data_read(sc->tp, sc->ip, sc->ip->i_ino, lblk,
diff --git a/fs/xfs/scrub/readdir.c b/fs/xfs/scrub/readdir.c
index 33035b98d25cf..d58a15c63a2dc 100644
--- a/fs/xfs/scrub/readdir.c
+++ b/fs/xfs/scrub/readdir.c
@@ -101,7 +101,7 @@ xchk_dir_walk_block(
 	unsigned int		off, next_off, end;
 	int			error;
 
-	error = xfs_dir3_block_read(sc->tp, dp, &bp);
+	error = xfs_dir3_block_read(sc->tp, dp, dp->i_ino, &bp);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index 260943447be9b..09a095648c1c7 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -159,7 +159,7 @@ xfs_dir2_block_getdents(
 	if (xfs_dir2_dataptr_to_db(geo, ctx->pos) > geo->datablk)
 		return 0;
 
-	error = xfs_dir3_block_read(args->trans, dp, &bp);
+	error = xfs_dir3_block_read(args->trans, dp, args->owner, &bp);
 	if (error)
 		return error;
 

[PATCH 9/9] xfs: validate explicit directory free block owners

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Port the existing directory freespace block header checking function to
accept an owner number instead of an xfs_inode, then update the
callsites to use xfs_da_args.owner when possible.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_dir2_leaf.c |    3 ++-
 fs/xfs/libxfs/xfs_dir2_node.c |   32 ++++++++++++++++++--------------
 fs/xfs/libxfs/xfs_dir2_priv.h |    2 +-
 fs/xfs/scrub/dir.c            |    2 +-
 4 files changed, 22 insertions(+), 17 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c
index a6eee26044875..fb78ae79fdc6a 100644
--- a/fs/xfs/libxfs/xfs_dir2_leaf.c
+++ b/fs/xfs/libxfs/xfs_dir2_leaf.c
@@ -1805,7 +1805,8 @@ xfs_dir2_node_to_leaf(
 	/*
 	 * Read the freespace block.
 	 */
-	error = xfs_dir2_free_read(tp, dp,  args->geo->freeblk, &fbp);
+	error = xfs_dir2_free_read(tp, dp, args->owner, args->geo->freeblk,
+			&fbp);
 	if (error)
 		return error;
 	xfs_dir2_free_hdr_from_disk(mp, &freehdr, fbp->b_addr);
diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c
index dc85197b8448e..fe8d4fa131289 100644
--- a/fs/xfs/libxfs/xfs_dir2_node.c
+++ b/fs/xfs/libxfs/xfs_dir2_node.c
@@ -175,11 +175,11 @@ const struct xfs_buf_ops xfs_dir3_free_buf_ops = {
 /* Everything ok in the free block header? */
 static xfs_failaddr_t
 xfs_dir3_free_header_check(
-	struct xfs_inode	*dp,
-	xfs_dablk_t		fbno,
-	struct xfs_buf		*bp)
+	struct xfs_buf		*bp,
+	xfs_ino_t		owner,
+	xfs_dablk_t		fbno)
 {
-	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_mount	*mp = bp->b_mount;
 	int			maxbests = mp->m_dir_geo->free_max_bests;
 	unsigned int		firstdb;
 
@@ -195,7 +195,7 @@ xfs_dir3_free_header_check(
 			return __this_address;
 		if (be32_to_cpu(hdr3->nvalid) < be32_to_cpu(hdr3->nused))
 			return __this_address;
-		if (be64_to_cpu(hdr3->hdr.owner) != dp->i_ino)
+		if (be64_to_cpu(hdr3->hdr.owner) != owner)
 			return __this_address;
 	} else {
 		struct xfs_dir2_free_hdr *hdr = bp->b_addr;
@@ -214,6 +214,7 @@ static int
 __xfs_dir3_free_read(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*dp,
+	xfs_ino_t		owner,
 	xfs_dablk_t		fbno,
 	unsigned int		flags,
 	struct xfs_buf		**bpp)
@@ -227,7 +228,7 @@ __xfs_dir3_free_read(
 		return err;
 
 	/* Check things that we can't do in the verifier. */
-	fa = xfs_dir3_free_header_check(dp, fbno, *bpp);
+	fa = xfs_dir3_free_header_check(*bpp, owner, fbno);
 	if (fa) {
 		__xfs_buf_mark_corrupt(*bpp, fa);
 		xfs_trans_brelse(tp, *bpp);
@@ -299,20 +300,23 @@ int
 xfs_dir2_free_read(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*dp,
+	xfs_ino_t		owner,
 	xfs_dablk_t		fbno,
 	struct xfs_buf		**bpp)
 {
-	return __xfs_dir3_free_read(tp, dp, fbno, 0, bpp);
+	return __xfs_dir3_free_read(tp, dp, owner, fbno, 0, bpp);
 }
 
 static int
 xfs_dir2_free_try_read(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*dp,
+	xfs_ino_t		owner,
 	xfs_dablk_t		fbno,
 	struct xfs_buf		**bpp)
 {
-	return __xfs_dir3_free_read(tp, dp, fbno, XFS_DABUF_MAP_HOLE_OK, bpp);
+	return __xfs_dir3_free_read(tp, dp, owner, fbno, XFS_DABUF_MAP_HOLE_OK,
+			bpp);
 }
 
 static int
@@ -717,7 +721,7 @@ xfs_dir2_leafn_lookup_for_addname(
 				if (curbp)
 					xfs_trans_brelse(tp, curbp);
 
-				error = xfs_dir2_free_read(tp, dp,
+				error = xfs_dir2_free_read(tp, dp, args->owner,
 						xfs_dir2_db_to_da(args->geo,
 								  newfdb),
 						&curbp);
@@ -1356,8 +1360,8 @@ xfs_dir2_leafn_remove(
 		 * read in the free block.
 		 */
 		fdb = xfs_dir2_db_to_fdb(geo, db);
-		error = xfs_dir2_free_read(tp, dp, xfs_dir2_db_to_da(geo, fdb),
-					   &fbp);
+		error = xfs_dir2_free_read(tp, dp, args->owner,
+				xfs_dir2_db_to_da(geo, fdb), &fbp);
 		if (error)
 			return error;
 		free = fbp->b_addr;
@@ -1716,7 +1720,7 @@ xfs_dir2_node_add_datablk(
 	 * that was just allocated.
 	 */
 	fbno = xfs_dir2_db_to_fdb(args->geo, *dbno);
-	error = xfs_dir2_free_try_read(tp, dp,
+	error = xfs_dir2_free_try_read(tp, dp, args->owner,
 			       xfs_dir2_db_to_da(args->geo, fbno), &fbp);
 	if (error)
 		return error;
@@ -1863,7 +1867,7 @@ xfs_dir2_node_find_freeblk(
 		 * so this might not succeed.  This should be really rare, so
 		 * there's no reason to avoid it.
 		 */
-		error = xfs_dir2_free_try_read(tp, dp,
+		error = xfs_dir2_free_try_read(tp, dp, args->owner,
 				xfs_dir2_db_to_da(args->geo, fbno),
 				&fbp);
 		if (error)
@@ -2302,7 +2306,7 @@ xfs_dir2_node_trim_free(
 	/*
 	 * Read the freespace block.
 	 */
-	error = xfs_dir2_free_try_read(tp, dp, fo, &bp);
+	error = xfs_dir2_free_try_read(tp, dp, args->owner, fo, &bp);
 	if (error)
 		return error;
 	/*
diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h
index 969e36a03fe5e..f9bc280e8c26f 100644
--- a/fs/xfs/libxfs/xfs_dir2_priv.h
+++ b/fs/xfs/libxfs/xfs_dir2_priv.h
@@ -156,7 +156,7 @@ extern int xfs_dir2_node_replace(struct xfs_da_args *args);
 extern int xfs_dir2_node_trim_free(struct xfs_da_args *args, xfs_fileoff_t fo,
 		int *rvalp);
 extern int xfs_dir2_free_read(struct xfs_trans *tp, struct xfs_inode *dp,
-		xfs_dablk_t fbno, struct xfs_buf **bpp);
+		xfs_ino_t owner, xfs_dablk_t fbno, struct xfs_buf **bpp);
 
 /* xfs_dir2_sf.c */
 xfs_ino_t xfs_dir2_sf_get_ino(struct xfs_mount *mp, struct xfs_dir2_sf_hdr *hdr,
diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index 43f5bc8ce0d46..7bac74621af77 100644
--- a/fs/xfs/scrub/dir.c
+++ b/fs/xfs/scrub/dir.c
@@ -577,7 +577,7 @@ xchk_directory_free_bestfree(
 	int				error;
 
 	/* Read the free space block */
-	error = xfs_dir2_free_read(sc->tp, sc->ip, lblk, &bp);
+	error = xfs_dir2_free_read(sc->tp, sc->ip, sc->ip->i_ino, lblk, &bp);
 	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
 		return error;
 	xchk_buffer_recheck(sc, bp);

[PATCH 1/6] xfs: create a blob array data structure

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a simple 'blob array' data structure for storage of arbitrarily
sized metadata objects that will be used to reconstruct metadata.  For
the intended usage (temporarily storing extended attribute names and
values) we only have to support storing objects and retrieving them.
Use the xfile abstraction to store the attribute information in memory
that can be swapped out.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Makefile       |    1 
 fs/xfs/scrub/xfblob.c |  151 +++++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/xfblob.h |   24 ++++++++
 3 files changed, 176 insertions(+)
 create mode 100644 fs/xfs/scrub/xfblob.c
 create mode 100644 fs/xfs/scrub/xfblob.h


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 62e38f70c304b..72df9890edcf6 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -208,6 +208,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   repair.o \
 				   rmap_repair.o \
 				   tempfile.o \
+				   xfblob.o \
 				   xfbtree.o \
 				   )
 
diff --git a/fs/xfs/scrub/xfblob.c b/fs/xfs/scrub/xfblob.c
new file mode 100644
index 0000000000000..216f9cb2965a7
--- /dev/null
+++ b/fs/xfs/scrub/xfblob.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2021-2024 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 "scrub/scrub.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/xfblob.h"
+
+/*
+ * XFS Blob Storage
+ * ================
+ * Stores and retrieves blobs using an xfile.  Objects are appended to the file
+ * and the offset is returned as a magic cookie for retrieval.
+ */
+
+#define XB_KEY_MAGIC	0xABAADDAD
+struct xb_key {
+	uint32_t		xb_magic;  /* XB_KEY_MAGIC */
+	uint32_t		xb_size;   /* size of the blob, in bytes */
+	loff_t			xb_offset; /* byte offset of this key */
+	/* blob comes after here */
+} __packed;
+
+/* Initialize a blob storage object. */
+int
+xfblob_create(
+	const char		*description,
+	struct xfblob		**blobp)
+{
+	struct xfblob		*blob;
+	struct xfile		*xfile;
+	int			error;
+
+	error = xfile_create(description, 0, &xfile);
+	if (error)
+		return error;
+
+	blob = kmalloc(sizeof(struct xfblob), XCHK_GFP_FLAGS);
+	if (!blob) {
+		error = -ENOMEM;
+		goto out_xfile;
+	}
+
+	blob->xfile = xfile;
+	blob->last_offset = PAGE_SIZE;
+
+	*blobp = blob;
+	return 0;
+
+out_xfile:
+	xfile_destroy(xfile);
+	return error;
+}
+
+/* Destroy a blob storage object. */
+void
+xfblob_destroy(
+	struct xfblob	*blob)
+{
+	xfile_destroy(blob->xfile);
+	kfree(blob);
+}
+
+/* Retrieve a blob. */
+int
+xfblob_load(
+	struct xfblob	*blob,
+	xfblob_cookie	cookie,
+	void		*ptr,
+	uint32_t	size)
+{
+	struct xb_key	key;
+	int		error;
+
+	error = xfile_obj_load(blob->xfile, &key, sizeof(key), cookie);
+	if (error)
+		return error;
+
+	if (key.xb_magic != XB_KEY_MAGIC || key.xb_offset != cookie) {
+		ASSERT(0);
+		return -ENODATA;
+	}
+	if (size < key.xb_size) {
+		ASSERT(0);
+		return -EFBIG;
+	}
+
+	return xfile_obj_load(blob->xfile, ptr, key.xb_size,
+			cookie + sizeof(key));
+}
+
+/* Store a blob. */
+int
+xfblob_store(
+	struct xfblob	*blob,
+	xfblob_cookie	*cookie,
+	const void	*ptr,
+	uint32_t	size)
+{
+	struct xb_key	key = {
+		.xb_offset = blob->last_offset,
+		.xb_magic = XB_KEY_MAGIC,
+		.xb_size = size,
+	};
+	loff_t		pos = blob->last_offset;
+	int		error;
+
+	error = xfile_obj_store(blob->xfile, &key, sizeof(key), pos);
+	if (error)
+		return error;
+
+	pos += sizeof(key);
+	error = xfile_obj_store(blob->xfile, ptr, size, pos);
+	if (error)
+		goto out_err;
+
+	*cookie = blob->last_offset;
+	blob->last_offset += sizeof(key) + size;
+	return 0;
+out_err:
+	xfile_discard(blob->xfile, blob->last_offset, sizeof(key));
+	return error;
+}
+
+/* Free a blob. */
+int
+xfblob_free(
+	struct xfblob	*blob,
+	xfblob_cookie	cookie)
+{
+	struct xb_key	key;
+	int		error;
+
+	error = xfile_obj_load(blob->xfile, &key, sizeof(key), cookie);
+	if (error)
+		return error;
+
+	if (key.xb_magic != XB_KEY_MAGIC || key.xb_offset != cookie) {
+		ASSERT(0);
+		return -ENODATA;
+	}
+
+	xfile_discard(blob->xfile, cookie, sizeof(key) + key.xb_size);
+	return 0;
+}
diff --git a/fs/xfs/scrub/xfblob.h b/fs/xfs/scrub/xfblob.h
new file mode 100644
index 0000000000000..bd98647407f1d
--- /dev/null
+++ b/fs/xfs/scrub/xfblob.h
@@ -0,0 +1,24 @@
+/* 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_XFBLOB_H__
+#define __XFS_SCRUB_XFBLOB_H__
+
+struct xfblob {
+	struct xfile	*xfile;
+	loff_t		last_offset;
+};
+
+typedef loff_t		xfblob_cookie;
+
+int xfblob_create(const char *descr, struct xfblob **blobp);
+void xfblob_destroy(struct xfblob *blob);
+int xfblob_load(struct xfblob *blob, xfblob_cookie cookie, void *ptr,
+		uint32_t size);
+int xfblob_store(struct xfblob *blob, xfblob_cookie *cookie, const void *ptr,
+		uint32_t size);
+int xfblob_free(struct xfblob *blob, xfblob_cookie cookie);
+
+#endif /* __XFS_SCRUB_XFBLOB_H__ */

[PATCH 2/6] xfs: use atomic extent swapping to fix user file fork data

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Build on the code that was recently added to the temporary repair file
code so that we can atomically switch the contents of any file fork,
even if the fork is in local format.  The upcoming functions to repair
xattrs, directories, and symlinks will need that capability.

Repair can lock out access to these user files by holding IOLOCK_EXCL on
these user files.  Therefore, it is safe to drop the ILOCK of both the
file being repaired and the tempfile being used for staging, and cancel
the scrub transaction.  We do this so that we can reuse the resource
estimation and transaction allocation functions used by a regular file
exchange operation.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_swapext.c |    2 
 fs/xfs/libxfs/xfs_swapext.h |    1 
 fs/xfs/scrub/tempfile.c     |  203 +++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/tempfile.h     |    3 +
 fs/xfs/scrub/tempswap.h     |    2 
 5 files changed, 210 insertions(+), 1 deletion(-)


diff --git a/fs/xfs/libxfs/xfs_swapext.c b/fs/xfs/libxfs/xfs_swapext.c
index 554da23a575eb..244ef3d8431fd 100644
--- a/fs/xfs/libxfs/xfs_swapext.c
+++ b/fs/xfs/libxfs/xfs_swapext.c
@@ -769,7 +769,7 @@ xfs_swapext_rmapbt_blocks(
 }
 
 /* Estimate the bmbt and rmapbt overhead required to exchange extents. */
-static int
+int
 xfs_swapext_estimate_overhead(
 	struct xfs_swapext_req	*req)
 {
diff --git a/fs/xfs/libxfs/xfs_swapext.h b/fs/xfs/libxfs/xfs_swapext.h
index 37842a4ee9a6d..a4768eddc9c8c 100644
--- a/fs/xfs/libxfs/xfs_swapext.h
+++ b/fs/xfs/libxfs/xfs_swapext.h
@@ -200,6 +200,7 @@ unsigned int xfs_swapext_reflink_prep(const struct xfs_swapext_req *req);
 void xfs_swapext_reflink_finish(struct xfs_trans *tp,
 		const struct xfs_swapext_req *req, unsigned int reflink_state);
 
+int xfs_swapext_estimate_overhead(struct xfs_swapext_req *req);
 int xfs_swapext_estimate(struct xfs_swapext_req *req);
 
 extern struct kmem_cache	*xfs_swapext_intent_cache;
diff --git a/fs/xfs/scrub/tempfile.c b/fs/xfs/scrub/tempfile.c
index a1736a3556a7d..f1726822e18f7 100644
--- a/fs/xfs/scrub/tempfile.c
+++ b/fs/xfs/scrub/tempfile.c
@@ -239,6 +239,28 @@ xrep_tempfile_iunlock(
 	sc->temp_ilock_flags &= ~XFS_ILOCK_EXCL;
 }
 
+/*
+ * Begin the process of making changes to both the file being scrubbed and
+ * the temporary file by taking ILOCK_EXCL on both.
+ */
+void
+xrep_tempfile_ilock_both(
+	struct xfs_scrub	*sc)
+{
+	xfs_lock_two_inodes(sc->ip, XFS_ILOCK_EXCL, sc->tempip, XFS_ILOCK_EXCL);
+	sc->ilock_flags |= XFS_ILOCK_EXCL;
+	sc->temp_ilock_flags |= XFS_ILOCK_EXCL;
+}
+
+/* Unlock ILOCK_EXCL on both files. */
+void
+xrep_tempfile_iunlock_both(
+	struct xfs_scrub	*sc)
+{
+	xrep_tempfile_iunlock(sc);
+	xchk_iunlock(sc, XFS_ILOCK_EXCL);
+}
+
 /* Release the temporary file. */
 void
 xrep_tempfile_rele(
@@ -526,6 +548,88 @@ xrep_tempswap_prep_request(
 	return 0;
 }
 
+/*
+ * Fill out the swapext resource estimation structures in preparation for
+ * swapping the contents of a metadata file that we've rebuilt in the temp
+ * file.  Caller must hold IOLOCK_EXCL but not ILOCK_EXCL on both files.
+ */
+STATIC int
+xrep_tempswap_estimate(
+	struct xfs_scrub	*sc,
+	struct xrep_tempswap	*tx)
+{
+	struct xfs_swapext_req	*req = &tx->req;
+	struct xfs_ifork	*ifp;
+	struct xfs_ifork	*tifp;
+	int			state = 0;
+
+	/*
+	 * Deal with either fork being in local format.  The swapext code only
+	 * knows how to exchange block mappings for regular files, so we only
+	 * have to know about local format for xattrs and directories.
+	 */
+	ifp = xfs_ifork_ptr(sc->ip, req->whichfork);
+	if (ifp->if_format == XFS_DINODE_FMT_LOCAL)
+		state |= 1;
+
+	tifp = xfs_ifork_ptr(sc->tempip, req->whichfork);
+	if (tifp->if_format == XFS_DINODE_FMT_LOCAL)
+		state |= 2;
+
+	switch (state) {
+	case 0:
+		/* Both files have mapped extents; use the regular estimate. */
+		return xfs_xchg_range_estimate(req);
+	case 1:
+		/*
+		 * The file being repaired is in local format, but the temp
+		 * file has mapped extents.  To perform the swap, the file
+		 * being repaired must have its shorform data converted to a
+		 * fsblock, and the fork changed to extents format.  We need
+		 * one resblk for the conversion; the number of exchanges is
+		 * (worst case) the temporary file's extent count plus the
+		 * block we converted.
+		 */
+		req->ip1_bcount = sc->tempip->i_nblocks;
+		req->ip2_bcount = 1;
+		req->nr_exchanges = 1 + tifp->if_nextents;
+		req->resblks = 1;
+		break;
+	case 2:
+		/*
+		 * The temporary file is in local format, but the file being
+		 * repaired has mapped extents.  To perform the swap, the temp
+		 * file must have its shortform data converted to an fsblock,
+		 * and the fork changed to extents format.  We need one resblk
+		 * for the conversion; the number of exchanges is (worst case)
+		 * the extent count of the file being repaired plus the block
+		 * we converted.
+		 */
+		req->ip1_bcount = 1;
+		req->ip2_bcount = sc->ip->i_nblocks;
+		req->nr_exchanges = 1 + ifp->if_nextents;
+		req->resblks = 1;
+		break;
+	case 3:
+		/*
+		 * Both forks are in local format.  To perform the swap, both
+		 * files must have their shortform data converted to fsblocks,
+		 * and both forks must be converted to extents format.  We
+		 * need two resblks for the two conversions, and the number of
+		 * exchanges is 1 since there's only one block at fileoff 0.
+		 * Presumably, the caller could not exchange the two inode fork
+		 * areas directly.
+		 */
+		req->ip1_bcount = 1;
+		req->ip2_bcount = 1;
+		req->nr_exchanges = 1;
+		req->resblks = 2;
+		break;
+	}
+
+	return xfs_swapext_estimate_overhead(req);
+}
+
 /*
  * Obtain a quota reservation to make sure we don't hit EDQUOT.  We can skip
  * this if quota enforcement is disabled or if both inodes' dquots are the
@@ -616,6 +720,55 @@ xrep_tempswap_trans_reserve(
 	return xrep_tempswap_reserve_quota(sc, tx);
 }
 
+/*
+ * Create a new transaction for a swap.
+ *
+ * This function fills out the swapext request and resource estimation
+ * structures in preparation for swapping the contents of a metadata file that
+ * has been rebuilt in the temp file.  Next, it reserves space, takes
+ * ILOCK_EXCL of both inodes, joins them to the transaction and reserves quota
+ * for the transaction.
+ *
+ * The caller is responsible for dropping both ILOCKs when appropriate.
+ */
+int
+xrep_tempswap_trans_alloc(
+	struct xfs_scrub	*sc,
+	int			whichfork,
+	struct xrep_tempswap	*tx)
+{
+	unsigned int		flags = 0;
+	int			error;
+
+	ASSERT(sc->tp == NULL);
+
+	error = xrep_tempswap_prep_request(sc, whichfork, tx);
+	if (error)
+		return error;
+
+	error = xrep_tempswap_estimate(sc, tx);
+	if (error)
+		return error;
+
+	if (xfs_has_lazysbcount(sc->mp))
+		flags |= XFS_TRANS_RES_FDBLKS;
+
+	error = xrep_tempswap_grab_log_assist(sc);
+	if (error)
+		return error;
+
+	error = xfs_trans_alloc(sc->mp, &M_RES(sc->mp)->tr_itruncate,
+			tx->req.resblks, 0, flags, &sc->tp);
+	if (error)
+		return error;
+
+	sc->temp_ilock_flags |= XFS_ILOCK_EXCL;
+	sc->ilock_flags |= XFS_ILOCK_EXCL;
+	xfs_xchg_range_ilock(sc->tp, sc->ip, sc->tempip);
+
+	return xrep_tempswap_reserve_quota(sc, tx);
+}
+
 /*
  * Swap forks between the file being repaired and the temporary file.  Returns
  * with both inodes locked and joined to a clean scrub transaction.
@@ -650,3 +803,53 @@ xrep_tempswap_contents(
 
 	return 0;
 }
+
+/*
+ * Write local format data from one of the temporary file's forks into the same
+ * fork of file being repaired, and swap the file sizes, if appropriate.
+ * Caller must ensure that the file being repaired has enough fork space to
+ * hold all the bytes.
+ */
+void
+xrep_tempfile_copyout_local(
+	struct xfs_scrub	*sc,
+	int			whichfork)
+{
+	struct xfs_ifork	*temp_ifp;
+	struct xfs_ifork	*ifp;
+	unsigned int		ilog_flags = XFS_ILOG_CORE;
+
+	temp_ifp = xfs_ifork_ptr(sc->tempip, whichfork);
+	ifp = xfs_ifork_ptr(sc->ip, whichfork);
+
+	ASSERT(temp_ifp != NULL);
+	ASSERT(ifp != NULL);
+	ASSERT(temp_ifp->if_format == XFS_DINODE_FMT_LOCAL);
+	ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
+
+	switch (whichfork) {
+	case XFS_DATA_FORK:
+		ASSERT(sc->tempip->i_disk_size <=
+					xfs_inode_data_fork_size(sc->ip));
+		break;
+	case XFS_ATTR_FORK:
+		ASSERT(sc->tempip->i_forkoff >= sc->ip->i_forkoff);
+		break;
+	default:
+		ASSERT(0);
+		return;
+	}
+
+	/* Recreate @sc->ip's incore fork (ifp) with data from temp_ifp. */
+	xfs_idestroy_fork(ifp);
+	xfs_init_local_fork(sc->ip, whichfork, temp_ifp->if_u1.if_data,
+			temp_ifp->if_bytes);
+
+	if (whichfork == XFS_DATA_FORK) {
+		i_size_write(VFS_I(sc->ip), i_size_read(VFS_I(sc->tempip)));
+		sc->ip->i_disk_size = sc->tempip->i_disk_size;
+	}
+
+	ilog_flags |= xfs_ilog_fdata(whichfork);
+	xfs_trans_log_inode(sc->tp, sc->ip, ilog_flags);
+}
diff --git a/fs/xfs/scrub/tempfile.h b/fs/xfs/scrub/tempfile.h
index 7980f9c4de552..d57e4f145a7c8 100644
--- a/fs/xfs/scrub/tempfile.h
+++ b/fs/xfs/scrub/tempfile.h
@@ -17,6 +17,8 @@ void xrep_tempfile_iounlock(struct xfs_scrub *sc);
 void xrep_tempfile_ilock(struct xfs_scrub *sc);
 bool xrep_tempfile_ilock_nowait(struct xfs_scrub *sc);
 void xrep_tempfile_iunlock(struct xfs_scrub *sc);
+void xrep_tempfile_iunlock_both(struct xfs_scrub *sc);
+void xrep_tempfile_ilock_both(struct xfs_scrub *sc);
 
 int xrep_tempfile_prealloc(struct xfs_scrub *sc, xfs_fileoff_t off,
 		xfs_filblks_t len);
@@ -32,6 +34,7 @@ int xrep_tempfile_copyin(struct xfs_scrub *sc, xfs_fileoff_t off,
 int xrep_tempfile_set_isize(struct xfs_scrub *sc, unsigned long long isize);
 
 int xrep_tempfile_roll_trans(struct xfs_scrub *sc);
+void xrep_tempfile_copyout_local(struct xfs_scrub *sc, int whichfork);
 #else
 static inline void xrep_tempfile_iolock_both(struct xfs_scrub *sc)
 {
diff --git a/fs/xfs/scrub/tempswap.h b/fs/xfs/scrub/tempswap.h
index e8f8a6e3c8861..83900eef8cfc5 100644
--- a/fs/xfs/scrub/tempswap.h
+++ b/fs/xfs/scrub/tempswap.h
@@ -14,6 +14,8 @@ struct xrep_tempswap {
 int xrep_tempswap_grab_log_assist(struct xfs_scrub *sc);
 int xrep_tempswap_trans_reserve(struct xfs_scrub *sc, int whichfork,
 		struct xrep_tempswap *ti);
+int xrep_tempswap_trans_alloc(struct xfs_scrub *sc, int whichfork,
+		struct xrep_tempswap *ti);
 
 int xrep_tempswap_contents(struct xfs_scrub *sc, struct xrep_tempswap *ti);
 #endif /* CONFIG_XFS_ONLINE_REPAIR */

[PATCH 3/6] xfs: repair extended attributes

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If the extended attributes look bad, try to sift through the rubble to
find whatever keys/values we can, stage a new attribute structure in a
temporary file and use the atomic extent swapping mechanism to commit
the results in bulk.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Makefile               |    1 
 fs/xfs/libxfs/xfs_attr.c      |    2 
 fs/xfs/libxfs/xfs_attr.h      |    2 
 fs/xfs/libxfs/xfs_da_format.h |    5 
 fs/xfs/scrub/attr.c           |   20 +
 fs/xfs/scrub/attr.h           |    7 
 fs/xfs/scrub/attr_repair.c    | 1203 +++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/attr_repair.h    |   11 
 fs/xfs/scrub/repair.c         |   46 ++
 fs/xfs/scrub/repair.h         |    6 
 fs/xfs/scrub/scrub.c          |    2 
 fs/xfs/scrub/trace.h          |   83 +++
 fs/xfs/scrub/xfarray.c        |   17 +
 fs/xfs/scrub/xfarray.h        |    2 
 fs/xfs/scrub/xfblob.c         |   17 +
 fs/xfs/scrub/xfblob.h         |    2 
 fs/xfs/scrub/xfile.h          |   12 
 fs/xfs/xfs_buf.c              |    3 
 fs/xfs/xfs_trace.h            |    2 
 19 files changed, 1439 insertions(+), 4 deletions(-)
 create mode 100644 fs/xfs/scrub/attr_repair.c
 create mode 100644 fs/xfs/scrub/attr_repair.h


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 72df9890edcf6..9b227be3e28b6 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -194,6 +194,7 @@ ifeq ($(CONFIG_XFS_ONLINE_REPAIR),y)
 xfs-y				+= $(addprefix scrub/, \
 				   agheader_repair.o \
 				   alloc_repair.o \
+				   attr_repair.o \
 				   bmap_repair.o \
 				   cow_repair.o \
 				   fscounters_repair.o \
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 1e94e933d7682..b002ddd5f05a2 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -1047,7 +1047,7 @@ xfs_attr_set(
  * External routines when attribute list is inside the inode
  *========================================================================*/
 
-static inline int xfs_attr_sf_totsize(struct xfs_inode *dp)
+int xfs_attr_sf_totsize(struct xfs_inode *dp)
 {
 	struct xfs_attr_shortform *sf;
 
diff --git a/fs/xfs/libxfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h
index 81be9b3e40047..e4f55008552b4 100644
--- a/fs/xfs/libxfs/xfs_attr.h
+++ b/fs/xfs/libxfs/xfs_attr.h
@@ -618,4 +618,6 @@ extern struct kmem_cache *xfs_attr_intent_cache;
 int __init xfs_attr_intent_init_cache(void);
 void xfs_attr_intent_destroy_cache(void);
 
+int xfs_attr_sf_totsize(struct xfs_inode *dp);
+
 #endif	/* __XFS_ATTR_H__ */
diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h
index 44748f1640e53..0e1ada44f21ba 100644
--- a/fs/xfs/libxfs/xfs_da_format.h
+++ b/fs/xfs/libxfs/xfs_da_format.h
@@ -716,6 +716,11 @@ struct xfs_attr3_leafblock {
 #define XFS_ATTR_INCOMPLETE	(1u << XFS_ATTR_INCOMPLETE_BIT)
 #define XFS_ATTR_NSP_ONDISK_MASK	(XFS_ATTR_ROOT | XFS_ATTR_SECURE)
 
+#define XFS_ATTR_NAMESPACE_STR \
+	{ XFS_ATTR_LOCAL,	"local" }, \
+	{ XFS_ATTR_ROOT,	"root" }, \
+	{ XFS_ATTR_SECURE,	"secure" }
+
 /*
  * Alignment for namelist and valuelist entries (since they are mixed
  * there can be only one alignment value)
diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c
index 40a59b24c209f..692e1b2837bbb 100644
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -10,6 +10,7 @@
 #include "xfs_trans_resv.h"
 #include "xfs_mount.h"
 #include "xfs_log_format.h"
+#include "xfs_trans.h"
 #include "xfs_inode.h"
 #include "xfs_da_format.h"
 #include "xfs_da_btree.h"
@@ -20,6 +21,7 @@
 #include "scrub/common.h"
 #include "scrub/dabtree.h"
 #include "scrub/attr.h"
+#include "scrub/repair.h"
 
 /* Free the buffers linked from the xattr buffer. */
 static void
@@ -35,6 +37,8 @@ xchk_xattr_buf_cleanup(
 	kvfree(ab->value);
 	ab->value = NULL;
 	ab->value_sz = 0;
+	kvfree(ab->name);
+	ab->name = NULL;
 }
 
 /*
@@ -65,7 +69,7 @@ xchk_xattr_want_freemap(
  * reallocating the buffer if necessary.  Buffer contents are not preserved
  * across a reallocation.
  */
-static int
+int
 xchk_setup_xattr_buf(
 	struct xfs_scrub	*sc,
 	size_t			value_size)
@@ -95,6 +99,12 @@ xchk_setup_xattr_buf(
 			return -ENOMEM;
 	}
 
+	if (xchk_could_repair(sc)) {
+		ab->name = kvmalloc(XATTR_NAME_MAX + 1, XCHK_GFP_FLAGS);
+		if (!ab->name)
+			return -ENOMEM;
+	}
+
 resize_value:
 	if (ab->value_sz >= value_size)
 		return 0;
@@ -121,6 +131,12 @@ xchk_setup_xattr(
 {
 	int			error;
 
+	if (xchk_could_repair(sc)) {
+		error = xrep_setup_xattr(sc);
+		if (error)
+			return error;
+	}
+
 	/*
 	 * We failed to get memory while checking attrs, so this time try to
 	 * get all the memory we're ever going to need.  Allocate the buffer
@@ -247,7 +263,7 @@ xchk_xattr_listent(
  * Within a char, the lowest bit of the char represents the byte with
  * the smallest address
  */
-STATIC bool
+bool
 xchk_xattr_set_map(
 	struct xfs_scrub	*sc,
 	unsigned long		*map,
diff --git a/fs/xfs/scrub/attr.h b/fs/xfs/scrub/attr.h
index 48fd9402c4328..7db58af56646b 100644
--- a/fs/xfs/scrub/attr.h
+++ b/fs/xfs/scrub/attr.h
@@ -16,9 +16,16 @@ struct xchk_xattr_buf {
 	/* Bitmap of free space in xattr leaf blocks. */
 	unsigned long		*freemap;
 
+	/* Memory buffer used to hold salvaged xattr names. */
+	unsigned char		*name;
+
 	/* Memory buffer used to extract xattr values. */
 	void			*value;
 	size_t			value_sz;
 };
 
+bool xchk_xattr_set_map(struct xfs_scrub *sc, unsigned long *map,
+		unsigned int start, unsigned int len);
+int xchk_setup_xattr_buf(struct xfs_scrub *sc, size_t value_size);
+
 #endif	/* __XFS_SCRUB_ATTR_H__ */
diff --git a/fs/xfs/scrub/attr_repair.c b/fs/xfs/scrub/attr_repair.c
new file mode 100644
index 0000000000000..9a88d46392626
--- /dev/null
+++ b/fs/xfs/scrub/attr_repair.c
@@ -0,0 +1,1203 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2018-2024 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_defer.h"
+#include "xfs_btree.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_dir2.h"
+#include "xfs_attr.h"
+#include "xfs_attr_leaf.h"
+#include "xfs_attr_sf.h"
+#include "xfs_attr_remote.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
+#include "xfs_swapext.h"
+#include "xfs_xchgrange.h"
+#include "xfs_acl.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/tempfile.h"
+#include "scrub/tempswap.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/xfblob.h"
+#include "scrub/attr.h"
+#include "scrub/reap.h"
+#include "scrub/attr_repair.h"
+
+/*
+ * Extended Attribute Repair
+ * =========================
+ *
+ * We repair extended attributes by reading the attr leaf blocks looking for
+ * attributes entries that look salvageable (name passes verifiers, value can
+ * be retrieved, etc).  Each extended attribute worth salvaging is stashed in
+ * memory, and the stashed entries are periodically replayed into a temporary
+ * file to constrain memory use.  Batching the construction of the temporary
+ * extended attribute structure in this fashion reduces lock cycling of the
+ * file being repaired and the temporary file.
+ *
+ * When salvaging completes, the remaining stashed attributes are replayed to
+ * the temporary file.  An atomic extent swap is used to commit the new xattr
+ * blocks to the file being repaired.  This will disrupt attrmulti cursors.
+ */
+
+struct xrep_xattr_key {
+	/* Cookie for retrieval of the xattr name. */
+	xfblob_cookie		name_cookie;
+
+	/* Cookie for retrieval of the xattr value. */
+	xfblob_cookie		value_cookie;
+
+	/* XFS_ATTR_* flags */
+	int			flags;
+
+	/* Length of the value and name. */
+	uint32_t		valuelen;
+	uint16_t		namelen;
+};
+
+/*
+ * Stash up to 8 pages of attrs in xattr_records/xattr_blobs before we write
+ * them to the temp file.
+ */
+#define XREP_XATTR_MAX_STASH_BYTES	(PAGE_SIZE * 8)
+
+struct xrep_xattr {
+	struct xfs_scrub	*sc;
+
+	/* Information for swapping attr forks at the end. */
+	struct xrep_tempswap	tx;
+
+	/* xattr keys */
+	struct xfarray		*xattr_records;
+
+	/* xattr values */
+	struct xfblob		*xattr_blobs;
+
+	/* Number of attributes that we are salvaging. */
+	unsigned long long	attrs_found;
+};
+
+/* Set up to recreate the extended attributes. */
+int
+xrep_setup_xattr(
+	struct xfs_scrub	*sc)
+{
+	return xrep_tempfile_create(sc, S_IFREG);
+}
+
+/*
+ * Decide if we want to salvage this attribute.  We don't bother with
+ * incomplete or oversized keys or values.  The @value parameter can be null
+ * for remote attrs.
+ */
+STATIC int
+xrep_xattr_want_salvage(
+	struct xrep_xattr	*rx,
+	unsigned int		attr_flags,
+	const void		*name,
+	int			namelen,
+	const void		*value,
+	int			valuelen)
+{
+	if (attr_flags & XFS_ATTR_INCOMPLETE)
+		return false;
+	if (namelen > XATTR_NAME_MAX || namelen <= 0)
+		return false;
+	if (valuelen > XATTR_SIZE_MAX || valuelen < 0)
+		return false;
+	return true;
+}
+
+/* Allocate an in-core record to hold xattrs while we rebuild the xattr data. */
+STATIC int
+xrep_xattr_salvage_key(
+	struct xrep_xattr	*rx,
+	int			flags,
+	unsigned char		*name,
+	int			namelen,
+	unsigned char		*value,
+	int			valuelen)
+{
+	struct xrep_xattr_key	key = {
+		.valuelen	= valuelen,
+		.flags		= flags & XFS_ATTR_NSP_ONDISK_MASK,
+	};
+	unsigned int		i = 0;
+	int			error = 0;
+
+	if (xchk_should_terminate(rx->sc, &error))
+		return error;
+
+	/*
+	 * Truncate the name to the first character that would trip namecheck.
+	 * If we no longer have a name after that, ignore this attribute.
+	 */
+	while (i < namelen && name[i] != 0)
+		i++;
+	if (i == 0)
+		return 0;
+	key.namelen = i;
+
+	trace_xrep_xattr_salvage_rec(rx->sc->ip, flags, name, key.namelen,
+			valuelen);
+
+	error = xfblob_store(rx->xattr_blobs, &key.name_cookie, name,
+			key.namelen);
+	if (error)
+		return error;
+
+	error = xfblob_store(rx->xattr_blobs, &key.value_cookie, value,
+			key.valuelen);
+	if (error)
+		return error;
+
+	error = xfarray_append(rx->xattr_records, &key);
+	if (error)
+		return error;
+
+	rx->attrs_found++;
+	return 0;
+}
+
+/*
+ * Record a shortform extended attribute key & value for later reinsertion
+ * into the inode.
+ */
+STATIC int
+xrep_xattr_salvage_sf_attr(
+	struct xrep_xattr		*rx,
+	struct xfs_attr_shortform	*sf,
+	struct xfs_attr_sf_entry	*sfe)
+{
+	struct xfs_scrub		*sc = rx->sc;
+	struct xchk_xattr_buf		*ab = sc->buf;
+	unsigned char			*name = sfe->nameval;
+	unsigned char			*value = &sfe->nameval[sfe->namelen];
+
+	if (!xchk_xattr_set_map(sc, ab->usedmap, (char *)name - (char *)sf,
+			sfe->namelen))
+		return 0;
+
+	if (!xchk_xattr_set_map(sc, ab->usedmap, (char *)value - (char *)sf,
+			sfe->valuelen))
+		return 0;
+
+	if (!xrep_xattr_want_salvage(rx, sfe->flags, sfe->nameval,
+			sfe->namelen, value, sfe->valuelen))
+		return 0;
+
+	return xrep_xattr_salvage_key(rx, sfe->flags, sfe->nameval,
+			sfe->namelen, value, sfe->valuelen);
+}
+
+/*
+ * Record a local format extended attribute key & value for later reinsertion
+ * into the inode.
+ */
+STATIC int
+xrep_xattr_salvage_local_attr(
+	struct xrep_xattr		*rx,
+	struct xfs_attr_leaf_entry	*ent,
+	unsigned int			nameidx,
+	const char			*buf_end,
+	struct xfs_attr_leaf_name_local	*lentry)
+{
+	struct xchk_xattr_buf		*ab = rx->sc->buf;
+	unsigned char			*value;
+	unsigned int			valuelen;
+	unsigned int			namesize;
+
+	/*
+	 * Decode the leaf local entry format.  If something seems wrong, we
+	 * junk the attribute.
+	 */
+	value = &lentry->nameval[lentry->namelen];
+	valuelen = be16_to_cpu(lentry->valuelen);
+	namesize = xfs_attr_leaf_entsize_local(lentry->namelen, valuelen);
+	if ((char *)lentry + namesize > buf_end)
+		return 0;
+	if (!xrep_xattr_want_salvage(rx, ent->flags, lentry->nameval,
+			lentry->namelen, value, valuelen))
+		return 0;
+	if (!xchk_xattr_set_map(rx->sc, ab->usedmap, nameidx, namesize))
+		return 0;
+
+	/* Try to save this attribute. */
+	return xrep_xattr_salvage_key(rx, ent->flags, lentry->nameval,
+			lentry->namelen, value, valuelen);
+}
+
+/*
+ * Record a remote format extended attribute key & value for later reinsertion
+ * into the inode.
+ */
+STATIC int
+xrep_xattr_salvage_remote_attr(
+	struct xrep_xattr		*rx,
+	struct xfs_attr_leaf_entry	*ent,
+	unsigned int			nameidx,
+	const char			*buf_end,
+	struct xfs_attr_leaf_name_remote *rentry,
+	unsigned int			ent_idx,
+	struct xfs_buf			*leaf_bp)
+{
+	struct xfs_da_args		args = {
+		.trans			= rx->sc->tp,
+		.dp			= rx->sc->ip,
+		.index			= ent_idx,
+		.geo			= rx->sc->mp->m_attr_geo,
+		.owner			= rx->sc->ip->i_ino,
+	};
+	struct xchk_xattr_buf		*ab = rx->sc->buf;
+	unsigned int			valuelen;
+	unsigned int			namesize;
+	int				error;
+
+	/*
+	 * Decode the leaf remote entry format.  If something seems wrong, we
+	 * junk the attribute.  Note that we should never find a zero-length
+	 * remote attribute value.
+	 */
+	valuelen = be32_to_cpu(rentry->valuelen);
+	namesize = xfs_attr_leaf_entsize_remote(rentry->namelen);
+	if ((char *)rentry + namesize > buf_end)
+		return 0;
+	if (valuelen == 0 ||
+	    !xrep_xattr_want_salvage(rx, ent->flags, rentry->name,
+			rentry->namelen, NULL, valuelen))
+		return 0;
+	if (!xchk_xattr_set_map(rx->sc, ab->usedmap, nameidx, namesize))
+		return 0;
+
+	/*
+	 * Enlarge the buffer (if needed) to hold the value that we're trying
+	 * to salvage from the old extended attribute data.
+	 */
+	error = xchk_setup_xattr_buf(rx->sc, valuelen);
+	if (error == -ENOMEM)
+		error = -EDEADLOCK;
+	if (error)
+		return error;
+
+	/* Look up the remote value and stash it for reconstruction. */
+	args.valuelen = valuelen;
+	args.namelen = rentry->namelen;
+	args.name = rentry->name;
+	args.value = ab->value;
+	error = xfs_attr3_leaf_getvalue(leaf_bp, &args);
+	if (error || args.rmtblkno == 0)
+		goto err_free;
+
+	error = xfs_attr_rmtval_get(&args);
+	if (error)
+		goto err_free;
+
+	/* Try to save this attribute. */
+	error = xrep_xattr_salvage_key(rx, ent->flags, rentry->name,
+			rentry->namelen, ab->value, valuelen);
+err_free:
+	/* remote value was garbage, junk it */
+	if (error == -EFSBADCRC || error == -EFSCORRUPTED)
+		error = 0;
+	return error;
+}
+
+/* Extract every xattr key that we can from this attr fork block. */
+STATIC int
+xrep_xattr_recover_leaf(
+	struct xrep_xattr		*rx,
+	struct xfs_buf			*bp)
+{
+	struct xfs_attr3_icleaf_hdr	leafhdr;
+	struct xfs_scrub		*sc = rx->sc;
+	struct xfs_mount		*mp = sc->mp;
+	struct xfs_attr_leafblock	*leaf;
+	struct xfs_attr_leaf_name_local	*lentry;
+	struct xfs_attr_leaf_name_remote *rentry;
+	struct xfs_attr_leaf_entry	*ent;
+	struct xfs_attr_leaf_entry	*entries;
+	struct xchk_xattr_buf		*ab = rx->sc->buf;
+	char				*buf_end;
+	size_t				off;
+	unsigned int			nameidx;
+	unsigned int			hdrsize;
+	int				i;
+	int				error = 0;
+
+	bitmap_zero(ab->usedmap, mp->m_attr_geo->blksize);
+
+	/* Check the leaf header */
+	leaf = bp->b_addr;
+	xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &leafhdr, leaf);
+	hdrsize = xfs_attr3_leaf_hdr_size(leaf);
+	xchk_xattr_set_map(sc, ab->usedmap, 0, hdrsize);
+	entries = xfs_attr3_leaf_entryp(leaf);
+
+	buf_end = (char *)bp->b_addr + mp->m_attr_geo->blksize;
+	for (i = 0, ent = entries; i < leafhdr.count; ent++, i++) {
+		if (xchk_should_terminate(sc, &error))
+			return error;
+
+		/* Skip key if it conflicts with something else? */
+		off = (char *)ent - (char *)leaf;
+		if (!xchk_xattr_set_map(sc, ab->usedmap, off,
+				sizeof(xfs_attr_leaf_entry_t)))
+			continue;
+
+		/* Check the name information. */
+		nameidx = be16_to_cpu(ent->nameidx);
+		if (nameidx < leafhdr.firstused ||
+		    nameidx >= mp->m_attr_geo->blksize)
+			continue;
+
+		if (ent->flags & XFS_ATTR_LOCAL) {
+			lentry = xfs_attr3_leaf_name_local(leaf, i);
+			error = xrep_xattr_salvage_local_attr(rx, ent, nameidx,
+					buf_end, lentry);
+		} else {
+			rentry = xfs_attr3_leaf_name_remote(leaf, i);
+			error = xrep_xattr_salvage_remote_attr(rx, ent, nameidx,
+					buf_end, rentry, i, bp);
+		}
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+/* Try to recover shortform attrs. */
+STATIC int
+xrep_xattr_recover_sf(
+	struct xrep_xattr		*rx)
+{
+	struct xfs_scrub		*sc = rx->sc;
+	struct xchk_xattr_buf		*ab = sc->buf;
+	struct xfs_attr_shortform	*sf;
+	struct xfs_attr_sf_entry	*sfe;
+	struct xfs_attr_sf_entry	*next;
+	struct xfs_ifork		*ifp;
+	unsigned char			*end;
+	int				i;
+	int				error = 0;
+
+	ifp = xfs_ifork_ptr(rx->sc->ip, XFS_ATTR_FORK);
+
+	bitmap_zero(ab->usedmap, ifp->if_bytes);
+	sf = (struct xfs_attr_shortform *)rx->sc->ip->i_af.if_u1.if_data;
+	end = (unsigned char *)ifp->if_u1.if_data + ifp->if_bytes;
+	xchk_xattr_set_map(sc, ab->usedmap, 0, sizeof(sf->hdr));
+
+	sfe = &sf->list[0];
+	if ((unsigned char *)sfe > end)
+		return 0;
+
+	for (i = 0; i < sf->hdr.count; i++) {
+		if (xchk_should_terminate(sc, &error))
+			return error;
+
+		next = xfs_attr_sf_nextentry(sfe);
+		if ((unsigned char *)next > end)
+			break;
+
+		if (xchk_xattr_set_map(sc, ab->usedmap,
+				(char *)sfe - (char *)sf,
+				sizeof(struct xfs_attr_sf_entry))) {
+			/*
+			 * No conflicts with the sf entry; let's save this
+			 * attribute.
+			 */
+			error = xrep_xattr_salvage_sf_attr(rx, sf, sfe);
+			if (error)
+				return error;
+		}
+
+		sfe = next;
+	}
+
+	return 0;
+}
+
+/*
+ * Try to return a buffer of xattr data for a given physical extent.
+ *
+ * Because the buffer cache get function complains if it finds a buffer
+ * matching the block number but not matching the length, we must be careful to
+ * look for incore buffers (up to the maximum length of a remote value) that
+ * could be hiding anywhere in the physical range.  If we find an incore
+ * buffer, we can pass that to the caller.  Optionally, read a single block and
+ * pass that back.
+ *
+ * Note the subtlety that remote attr value blocks for which there is no incore
+ * buffer will be passed to the callback one block at a time.  These buffers
+ * will not have any ops attached and must be staled to prevent aliasing with
+ * multiblock buffers once we drop the ILOCK.
+ */
+STATIC int
+xrep_xattr_find_buf(
+	struct xfs_mount	*mp,
+	xfs_fsblock_t		fsbno,
+	xfs_extlen_t		max_len,
+	bool			can_read,
+	struct xfs_buf		**bpp)
+{
+	struct xrep_bufscan	scan = {
+		.daddr		= XFS_FSB_TO_DADDR(mp, fsbno),
+		.max_sectors	= xrep_bufscan_max_sectors(mp, max_len),
+		.daddr_step	= XFS_FSB_TO_BB(mp, 1),
+	};
+	struct xfs_buf		*bp;
+
+	while ((bp = xrep_bufscan_advance(mp, &scan)) != NULL) {
+		*bpp = bp;
+		return 0;
+	}
+
+	if (!can_read) {
+		*bpp = NULL;
+		return 0;
+	}
+
+	return xfs_buf_read(mp->m_ddev_targp, scan.daddr, XFS_FSB_TO_BB(mp, 1),
+			XBF_TRYLOCK, bpp, NULL);
+}
+
+/*
+ * Deal with a buffer that we found during our walk of the attr fork.
+ *
+ * Attribute leaf and node blocks are simple -- they're a single block, so we
+ * can walk them one at a time and we never have to worry about discontiguous
+ * multiblock buffers like we do for directories.
+ *
+ * Unfortunately, remote attr blocks add a lot of complexity here.  Each disk
+ * block is totally self contained, in the sense that the v5 header provides no
+ * indication that there could be more data in the next block.  The incore
+ * buffers can span multiple blocks, though they never cross extent records.
+ * However, they don't necessarily start or end on an extent record boundary.
+ * Therefore, we need a special buffer find function to walk the buffer cache
+ * for us.
+ *
+ * The caller must hold the ILOCK on the file being repaired.  We use
+ * XBF_TRYLOCK here to skip any locked buffer on the assumption that we don't
+ * own the block and don't want to hang the system on a potentially garbage
+ * buffer.
+ */
+STATIC int
+xrep_xattr_recover_block(
+	struct xrep_xattr	*rx,
+	xfs_dablk_t		dabno,
+	xfs_fsblock_t		fsbno,
+	xfs_extlen_t		max_len,
+	xfs_extlen_t		*actual_len)
+{
+	struct xfs_da_blkinfo	*info;
+	struct xfs_buf		*bp;
+	int			error;
+
+	error = xrep_xattr_find_buf(rx->sc->mp, fsbno, max_len, true, &bp);
+	if (error)
+		return error;
+	info = bp->b_addr;
+	*actual_len = XFS_BB_TO_FSB(rx->sc->mp, bp->b_length);
+
+	trace_xrep_xattr_recover_leafblock(rx->sc->ip, dabno,
+			be16_to_cpu(info->magic));
+
+	/*
+	 * If the buffer has the right magic number for an attr leaf block and
+	 * passes a structure check (we don't care about checksums), salvage
+	 * as much as we can from the block. */
+	if (info->magic == cpu_to_be16(XFS_ATTR3_LEAF_MAGIC) &&
+	    xrep_buf_verify_struct(bp, &xfs_attr3_leaf_buf_ops) &&
+	    xfs_attr3_leaf_header_check(bp, rx->sc->ip->i_ino) == NULL)
+		error = xrep_xattr_recover_leaf(rx, bp);
+
+	/*
+	 * If the buffer didn't already have buffer ops set, it was read in by
+	 * the _find_buf function and could very well be /part/ of a multiblock
+	 * remote block.  Mark it stale so that it doesn't hang around in
+	 * memory to cause problems.
+	 */
+	if (bp->b_ops == NULL)
+		xfs_buf_stale(bp);
+
+	xfs_buf_relse(bp);
+	return error;
+}
+
+/* Insert one xattr key/value. */
+STATIC int
+xrep_xattr_insert_rec(
+	struct xrep_xattr		*rx,
+	const struct xrep_xattr_key	*key)
+{
+	struct xfs_da_args		args = {
+		.dp			= rx->sc->tempip,
+		.attr_filter		= key->flags,
+		.attr_flags		= XATTR_CREATE,
+		.namelen		= key->namelen,
+		.valuelen		= key->valuelen,
+		.op_flags		= XFS_DA_OP_NOTIME,
+		.owner			= rx->sc->ip->i_ino,
+	};
+	struct xchk_xattr_buf		*ab = rx->sc->buf;
+	int				error;
+
+	/*
+	 * Grab pointers to the scrub buffer so that we can use them to insert
+	 * attrs into the temp file.
+	 */
+	args.name = ab->name;
+	args.value = ab->value;
+
+	/*
+	 * The attribute name is stored near the end of the in-core buffer,
+	 * though we reserve one more byte to ensure null termination.
+	 */
+	ab->name[XATTR_NAME_MAX] = 0;
+
+	error = xfblob_load(rx->xattr_blobs, key->name_cookie, ab->name,
+			key->namelen);
+	if (error)
+		return error;
+
+	error = xfblob_free(rx->xattr_blobs, key->name_cookie);
+	if (error)
+		return error;
+
+	error = xfblob_load(rx->xattr_blobs, key->value_cookie, args.value,
+			key->valuelen);
+	if (error)
+		return error;
+
+	error = xfblob_free(rx->xattr_blobs, key->value_cookie);
+	if (error)
+		return error;
+
+	ab->name[key->namelen] = 0;
+
+	trace_xrep_xattr_insert_rec(rx->sc->tempip, key->flags, ab->name,
+			key->namelen, key->valuelen);
+
+	/*
+	 * xfs_attr_set creates and commits its own transaction.  If the attr
+	 * already exists, we'll just drop it during the rebuild.
+	 */
+	error = xfs_attr_set(&args);
+	if (error == -EEXIST)
+		error = 0;
+
+	return error;
+}
+
+/*
+ * Periodically flush salvaged attributes to the temporary file.  This is done
+ * to reduce the memory requirements of the xattr rebuild because files can
+ * contain millions of attributes.
+ */
+STATIC int
+xrep_xattr_flush_stashed(
+	struct xrep_xattr	*rx)
+{
+	xfarray_idx_t		array_cur;
+	int			error;
+
+	/*
+	 * Entering this function, the scrub context has a reference to the
+	 * inode being repaired, the temporary file, and a scrub transaction
+	 * that we use during xattr salvaging to avoid livelocking if there
+	 * are cycles in the xattr structures.  We hold ILOCK_EXCL on both
+	 * the inode being repaired, though it is not ijoined to the scrub
+	 * transaction.
+	 *
+	 * To constrain kernel memory use, we occasionally flush salvaged
+	 * xattrs from the xfarray and xfblob structures into the temporary
+	 * file in preparation for swapping the xattr structures at the end.
+	 * Updating the temporary file requires a transaction, so we commit the
+	 * scrub transaction and drop the two ILOCKs so that xfs_attr_set can
+	 * allocate whatever transaction it wants.
+	 *
+	 * We still hold IOLOCK_EXCL on the inode being repaired, which
+	 * prevents anyone from modifying the damaged xattr data while we
+	 * repair it.
+	 */
+	error = xrep_trans_commit(rx->sc);
+	if (error)
+		return error;
+	xchk_iunlock(rx->sc, XFS_ILOCK_EXCL);
+
+	/*
+	 * Take the IOLOCK of the temporary file while we modify xattrs.  This
+	 * isn't strictly required because the temporary file is never revealed
+	 * to userspace, but we follow the same locking rules.  We still hold
+	 * sc->ip's IOLOCK.
+	 */
+	error = xrep_tempfile_iolock_polled(rx->sc);
+	if (error)
+		return error;
+
+	/* Add all the salvaged attrs to the temporary file. */
+	foreach_xfarray_idx(rx->xattr_records, array_cur) {
+		struct xrep_xattr_key	key;
+
+		error = xfarray_load(rx->xattr_records, array_cur, &key);
+		if (error)
+			return error;
+
+		error = xrep_xattr_insert_rec(rx, &key);
+		if (error)
+			return error;
+	}
+
+	/* Empty out both arrays now that we've added the entries. */
+	xfarray_truncate(rx->xattr_records);
+	xfblob_truncate(rx->xattr_blobs);
+
+	xrep_tempfile_iounlock(rx->sc);
+
+	/* Recreate the salvage transaction and relock the inode. */
+	error = xchk_trans_alloc(rx->sc, 0);
+	if (error)
+		return error;
+	xchk_ilock(rx->sc, XFS_ILOCK_EXCL);
+	return 0;
+}
+
+/* Decide if we've stashed too much xattr data in memory. */
+static inline bool
+xrep_xattr_want_flush_stashed(
+	struct xrep_xattr	*rx)
+{
+	unsigned long long	bytes;
+
+	bytes = xfarray_bytes(rx->xattr_records) +
+		xfblob_bytes(rx->xattr_blobs);
+	return bytes > XREP_XATTR_MAX_STASH_BYTES;
+}
+
+/* Extract as many attribute keys and values as we can. */
+STATIC int
+xrep_xattr_recover(
+	struct xrep_xattr	*rx)
+{
+	struct xfs_bmbt_irec	got;
+	struct xfs_scrub	*sc = rx->sc;
+	struct xfs_da_geometry	*geo = sc->mp->m_attr_geo;
+	xfs_fileoff_t		offset;
+	xfs_extlen_t		len;
+	xfs_dablk_t		dabno;
+	int			nmap;
+	int			error;
+
+	/*
+	 * Iterate each xattr leaf block in the attr fork to scan them for any
+	 * attributes that we might salvage.
+	 */
+	for (offset = 0;
+	     offset < XFS_MAX_FILEOFF;
+	     offset = got.br_startoff + got.br_blockcount) {
+		nmap = 1;
+		error = xfs_bmapi_read(sc->ip, offset, XFS_MAX_FILEOFF - offset,
+				&got, &nmap, XFS_BMAPI_ATTRFORK);
+		if (error)
+			return error;
+		if (nmap != 1)
+			return -EFSCORRUPTED;
+		if (!xfs_bmap_is_written_extent(&got))
+			continue;
+
+		for (dabno = round_up(got.br_startoff, geo->fsbcount);
+		     dabno < got.br_startoff + got.br_blockcount;
+		     dabno += len) {
+			xfs_fileoff_t	curr_offset = dabno - got.br_startoff;
+			xfs_extlen_t	maxlen;
+
+			if (xchk_should_terminate(rx->sc, &error))
+				return error;
+
+			maxlen = min_t(xfs_filblks_t, INT_MAX,
+					got.br_blockcount - curr_offset);
+			error = xrep_xattr_recover_block(rx, dabno,
+					curr_offset + got.br_startblock,
+					maxlen, &len);
+			if (error)
+				return error;
+
+			if (xrep_xattr_want_flush_stashed(rx)) {
+				error = xrep_xattr_flush_stashed(rx);
+				if (error)
+					return error;
+			}
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Reset the extended attribute fork to a state where we can start re-adding
+ * the salvaged attributes.
+ */
+STATIC int
+xrep_xattr_fork_remove(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
+{
+	struct xfs_attr_sf_hdr	*hdr;
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, XFS_ATTR_FORK);
+
+	/*
+	 * If the data fork is in btree format, we can't change di_forkoff
+	 * because we could run afoul of the rule that the data fork isn't
+	 * supposed to be in btree format if there's enough space in the fork
+	 * that it could have used extents format.  Instead, reinitialize the
+	 * attr fork to have a shortform structure with zero attributes.
+	 */
+	if (ip->i_df.if_format == XFS_DINODE_FMT_BTREE) {
+		ifp->if_format = XFS_DINODE_FMT_LOCAL;
+		xfs_idata_realloc(ip, (int)sizeof(*hdr) - ifp->if_bytes,
+				XFS_ATTR_FORK);
+		hdr = (struct xfs_attr_sf_hdr *)ifp->if_u1.if_data;
+		hdr->count = 0;
+		hdr->totsize = cpu_to_be16(sizeof(*hdr));
+		xfs_trans_log_inode(sc->tp, ip,
+				XFS_ILOG_CORE | XFS_ILOG_ADATA);
+		return 0;
+	}
+
+	/* If we still have attr fork extents, something's wrong. */
+	if (ifp->if_nextents != 0) {
+		struct xfs_iext_cursor	icur;
+		struct xfs_bmbt_irec	irec;
+		unsigned int		i = 0;
+
+		xfs_emerg(sc->mp,
+	"inode 0x%llx attr fork still has %llu attr extents, format %d?!",
+				ip->i_ino, ifp->if_nextents, ifp->if_format);
+		for_each_xfs_iext(ifp, &icur, &irec) {
+			xfs_err(sc->mp,
+	"[%u]: startoff %llu startblock %llu blockcount %llu state %u",
+					i++, irec.br_startoff,
+					irec.br_startblock, irec.br_blockcount,
+					irec.br_state);
+		}
+		ASSERT(0);
+		return -EFSCORRUPTED;
+	}
+
+	xfs_attr_fork_remove(ip, sc->tp);
+	return 0;
+}
+
+/*
+ * Free all the attribute fork blocks of the file being repaired and delete the
+ * fork.  The caller must ILOCK the scrub file and join it to the transaction.
+ * This function returns with the inode joined to a clean transaction.
+ */
+int
+xrep_xattr_reset_fork(
+	struct xfs_scrub	*sc)
+{
+	int			error;
+
+	trace_xrep_xattr_reset_fork(sc->ip, sc->ip);
+
+	/* Unmap all the attr blocks. */
+	if (xfs_ifork_has_extents(&sc->ip->i_af)) {
+		error = xrep_reap_ifork(sc, sc->ip, XFS_ATTR_FORK);
+		if (error)
+			return error;
+	}
+
+	error = xrep_xattr_fork_remove(sc, sc->ip);
+	if (error)
+		return error;
+
+	return xfs_trans_roll_inode(&sc->tp, sc->ip);
+}
+
+/*
+ * Free all the attribute fork blocks of the temporary file and delete the attr
+ * fork.  The caller must ILOCK the tempfile and join it to the transaction.
+ * This function returns with the inode joined to a clean scrub transaction.
+ */
+STATIC int
+xrep_xattr_reset_tempfile_fork(
+	struct xfs_scrub	*sc)
+{
+	int			error;
+
+	trace_xrep_xattr_reset_fork(sc->ip, sc->tempip);
+
+	/*
+	 * Wipe out the attr fork of the temp file so that regular inode
+	 * inactivation won't trip over the corrupt attr fork.
+	 */
+	if (xfs_ifork_has_extents(&sc->tempip->i_af)) {
+		error = xrep_reap_ifork(sc, sc->tempip, XFS_ATTR_FORK);
+		if (error)
+			return error;
+	}
+
+	return xrep_xattr_fork_remove(sc, sc->tempip);
+}
+
+/*
+ * Find all the extended attributes for this inode by scraping them out of the
+ * attribute key blocks by hand, and flushing them into the temp file.
+ * When we're done, free the staging memory before swapping the xattr
+ * structures to reduce memory usage.
+ */
+STATIC int
+xrep_xattr_salvage_attributes(
+	struct xrep_xattr	*rx)
+{
+	struct xfs_inode	*ip = rx->sc->ip;
+	int			error;
+
+	/* Short format xattrs are easy! */
+	if (rx->sc->ip->i_af.if_format == XFS_DINODE_FMT_LOCAL) {
+		error = xrep_xattr_recover_sf(rx);
+		if (error)
+			return error;
+
+		return xrep_xattr_flush_stashed(rx);
+	}
+
+	/*
+	 * For non-inline xattr structures, the salvage function scans the
+	 * buffer cache looking for potential attr leaf blocks.  The scan
+	 * requires the ability to lock any buffer found and runs independently
+	 * of any transaction <-> buffer item <-> buffer linkage.  Therefore,
+	 * roll the transaction to ensure there are no buffers joined.  We hold
+	 * the ILOCK independently of the transaction.
+	 */
+	error = xfs_trans_roll(&rx->sc->tp);
+	if (error)
+		return error;
+
+	error = xfs_iread_extents(rx->sc->tp, ip, XFS_ATTR_FORK);
+	if (error)
+		return error;
+
+	error = xrep_xattr_recover(rx);
+	if (error)
+		return error;
+
+	return xrep_xattr_flush_stashed(rx);
+}
+
+/*
+ * Prepare both inodes' attribute forks for extent swapping.  Promote the
+ * tempfile from short format to leaf format, and if the file being repaired
+ * has a short format attr fork, turn it into an empty extent list.
+ */
+STATIC int
+xrep_xattr_swap_prep(
+	struct xfs_scrub	*sc,
+	bool			temp_local,
+	bool			ip_local)
+{
+	int			error;
+
+	/*
+	 * If the tempfile's attributes are in shortform format, convert that
+	 * to a single leaf extent so that we can use the atomic extent swap.
+	 */
+	if (temp_local) {
+		struct xfs_da_args	args = {
+			.dp		= sc->tempip,
+			.geo		= sc->mp->m_attr_geo,
+			.whichfork	= XFS_ATTR_FORK,
+			.trans		= sc->tp,
+			.total		= 1,
+			.owner		= sc->ip->i_ino,
+		};
+
+		error = xfs_attr_shortform_to_leaf(&args);
+		if (error)
+			return error;
+
+		/*
+		 * Roll the deferred log items to get us back to a clean
+		 * transaction.
+		 */
+		error = xfs_defer_finish(&sc->tp);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * If the file being repaired had a shortform attribute fork, convert
+	 * that to an empty extent list in preparation for the atomic extent
+	 * swap.
+	 */
+	if (ip_local) {
+		struct xfs_ifork	*ifp;
+
+		ifp = xfs_ifork_ptr(sc->ip, XFS_ATTR_FORK);
+
+		xfs_idestroy_fork(ifp);
+		ifp->if_format = XFS_DINODE_FMT_EXTENTS;
+		ifp->if_nextents = 0;
+		ifp->if_bytes = 0;
+		ifp->if_u1.if_root = NULL;
+		ifp->if_height = 0;
+
+		xfs_trans_log_inode(sc->tp, sc->ip,
+				XFS_ILOG_CORE | XFS_ILOG_ADATA);
+	}
+
+	return 0;
+}
+
+/* Swap the temporary file's attribute fork with the one being repaired. */
+STATIC int
+xrep_xattr_swap(
+	struct xfs_scrub	*sc,
+	struct xrep_tempswap	*tx)
+{
+	bool			ip_local, temp_local;
+	int			error = 0;
+
+	ip_local = sc->ip->i_af.if_format == XFS_DINODE_FMT_LOCAL;
+	temp_local = sc->tempip->i_af.if_format == XFS_DINODE_FMT_LOCAL;
+
+	/*
+	 * If the both files have a local format attr fork and the rebuilt
+	 * xattr data would fit in the repaired file's attr fork, just copy
+	 * the contents from the tempfile and declare ourselves done.
+	 */
+	if (ip_local && temp_local) {
+		int	forkoff;
+		int	newsize;
+
+		newsize = xfs_attr_sf_totsize(sc->tempip);
+		forkoff = xfs_attr_shortform_bytesfit(sc->ip, newsize);
+		if (forkoff > 0) {
+			sc->ip->i_forkoff = forkoff;
+			xrep_tempfile_copyout_local(sc, XFS_ATTR_FORK);
+			return 0;
+		}
+	}
+
+	/* Otherwise, make sure both attr forks are in block-mapping mode. */
+	error = xrep_xattr_swap_prep(sc, temp_local, ip_local);
+	if (error)
+		return error;
+
+	return xrep_tempswap_contents(sc, tx);
+}
+
+/*
+ * Swap the new extended attribute data (which we created in the tempfile) into
+ * the file being repaired.
+ */
+STATIC int
+xrep_xattr_rebuild_tree(
+	struct xrep_xattr	*rx)
+{
+	struct xfs_scrub	*sc = rx->sc;
+	int			error;
+
+	/*
+	 * If we didn't find any attributes to salvage, repair the file by
+	 * zapping its attr fork.
+	 */
+	if (rx->attrs_found == 0) {
+		xfs_trans_ijoin(sc->tp, sc->ip, 0);
+		error = xrep_xattr_reset_fork(sc);
+		if (error)
+			return error;
+
+		goto forget_acls;
+	}
+
+	trace_xrep_xattr_rebuild_tree(sc->ip, sc->tempip);
+
+	/*
+	 * Commit the repair transaction and drop the ILOCKs so that we can use
+	 * the atomic extent swap helper functions to compute the correct
+	 * resource reservations.
+	 *
+	 * We still hold IOLOCK_EXCL (aka i_rwsem) which will prevent xattr
+	 * modifications, but there's nothing to prevent userspace from reading
+	 * the attributes until we're ready for the swap operation.  Reads will
+	 * return -EIO without shutting down the fs, so we're ok with that.
+	 */
+	error = xrep_trans_commit(sc);
+	if (error)
+		return error;
+
+	xchk_iunlock(sc, XFS_ILOCK_EXCL);
+
+	/*
+	 * Take the IOLOCK on the temporary file so that we can run xattr
+	 * operations with the same locks held as we would for a normal file.
+	 * We still hold sc->ip's IOLOCK.
+	 */
+	error = xrep_tempfile_iolock_polled(rx->sc);
+	if (error)
+		return error;
+
+	/* Allocate swapext transaction and lock both inodes. */
+	error = xrep_tempswap_trans_alloc(rx->sc, XFS_ATTR_FORK, &rx->tx);
+	if (error)
+		return error;
+
+	/*
+	 * Exchange the blocks mapped by the tempfile's attr fork with the file
+	 * being repaired.  The old attr blocks will then be attached to the
+	 * tempfile, so reap its attr fork.
+	 */
+	error = xrep_xattr_swap(sc, &rx->tx);
+	if (error)
+		return error;
+
+	error = xrep_xattr_reset_tempfile_fork(sc);
+	if (error)
+		return error;
+
+	/*
+	 * Roll to get a transaction without any inodes joined to it.  Then we
+	 * can drop the tempfile's ILOCK and IOLOCK before doing more work on
+	 * the scrub target file.
+	 */
+	error = xfs_trans_roll(&sc->tp);
+	if (error)
+		return error;
+
+	xrep_tempfile_iunlock(sc);
+	xrep_tempfile_iounlock(sc);
+
+forget_acls:
+	/* Invalidate cached ACLs now that we've reloaded all the xattrs. */
+	xfs_forget_acl(VFS_I(sc->ip), SGI_ACL_FILE);
+	xfs_forget_acl(VFS_I(sc->ip), SGI_ACL_DEFAULT);
+	return 0;
+}
+
+/* Tear down all the incore scan stuff we created. */
+STATIC void
+xrep_xattr_teardown(
+	struct xrep_xattr	*rx)
+{
+	xfblob_destroy(rx->xattr_blobs);
+	xfarray_destroy(rx->xattr_records);
+	kfree(rx);
+}
+
+/* Set up the filesystem scan so we can regenerate extended attributes. */
+STATIC int
+xrep_xattr_setup_scan(
+	struct xfs_scrub	*sc,
+	struct xrep_xattr	**rxp)
+{
+	struct xrep_xattr	*rx;
+	char			*descr;
+	int			max_len;
+	int			error;
+
+	rx = kzalloc(sizeof(struct xrep_xattr), XCHK_GFP_FLAGS);
+	if (!rx)
+		return -ENOMEM;
+	rx->sc = sc;
+
+	/*
+	 * Allocate enough memory to handle loading local attr values from the
+	 * xfblob data while flushing stashed attrs to the temporary file.
+	 * We only realloc the buffer when salvaging remote attr values.
+	 */
+	max_len = xfs_attr_leaf_entsize_local_max(sc->mp->m_attr_geo->blksize);
+	error = xchk_setup_xattr_buf(rx->sc, max_len);
+	if (error == -ENOMEM)
+		error = -EDEADLOCK;
+	if (error)
+		goto out_rx;
+
+	/* Set up some staging for salvaged attribute keys and values */
+	descr = xchk_xfile_ino_descr(sc, "xattr keys");
+	error = xfarray_create(descr, 0, sizeof(struct xrep_xattr_key),
+			&rx->xattr_records);
+	kfree(descr);
+	if (error)
+		goto out_rx;
+
+	descr = xchk_xfile_ino_descr(sc, "xattr names");
+	error = xfblob_create(descr, &rx->xattr_blobs);
+	kfree(descr);
+	if (error)
+		goto out_keys;
+
+	*rxp = rx;
+	return 0;
+out_keys:
+	xfarray_destroy(rx->xattr_records);
+out_rx:
+	kfree(rx);
+	return error;
+}
+
+/*
+ * Repair the extended attribute metadata.
+ *
+ * XXX: Remote attribute value buffers encompass the entire (up to 64k) buffer.
+ * The buffer cache in XFS can't handle aliased multiblock buffers, so this
+ * might misbehave if the attr fork is crosslinked with other filesystem
+ * metadata.
+ */
+int
+xrep_xattr(
+	struct xfs_scrub	*sc)
+{
+	struct xrep_xattr	*rx = NULL;
+	int			error;
+
+	if (!xfs_inode_hasattr(sc->ip))
+		return -ENOENT;
+
+	/* The rmapbt is required to reap the old attr fork. */
+	if (!xfs_has_rmapbt(sc->mp))
+		return -EOPNOTSUPP;
+
+	error = xrep_xattr_setup_scan(sc, &rx);
+	if (error)
+		return error;
+
+	ASSERT(sc->ilock_flags & XFS_ILOCK_EXCL);
+
+	error = xrep_xattr_salvage_attributes(rx);
+	if (error)
+		goto out_scan;
+
+	/* Last chance to abort before we start committing fixes. */
+	if (xchk_should_terminate(sc, &error))
+		goto out_scan;
+
+	error = xrep_xattr_rebuild_tree(rx);
+	if (error)
+		goto out_scan;
+
+out_scan:
+	xrep_xattr_teardown(rx);
+	return error;
+}
diff --git a/fs/xfs/scrub/attr_repair.h b/fs/xfs/scrub/attr_repair.h
new file mode 100644
index 0000000000000..0a9ffa7cfa906
--- /dev/null
+++ b/fs/xfs/scrub/attr_repair.h
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2018-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_ATTR_REPAIR_H__
+#define __XFS_SCRUB_ATTR_REPAIR_H__
+
+int xrep_xattr_reset_fork(struct xfs_scrub *sc);
+
+#endif /* __XFS_SCRUB_ATTR_REPAIR_H__ */
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 6490f064e091f..83b7aa48dec19 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -32,6 +32,9 @@
 #include "xfs_reflink.h"
 #include "xfs_health.h"
 #include "xfs_buf_xfile.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_attr.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
@@ -39,6 +42,7 @@
 #include "scrub/bitmap.h"
 #include "scrub/stats.h"
 #include "scrub/xfile.h"
+#include "scrub/attr_repair.h"
 
 /*
  * Attempt to repair some metadata, if the metadata is corrupt and userspace
@@ -1136,6 +1140,17 @@ xrep_metadata_inode_forks(
 			return error;
 	}
 
+	/* Clear the attr forks since metadata shouldn't have that. */
+	if (xfs_inode_hasattr(sc->ip)) {
+		if (!dirty) {
+			dirty = true;
+			xfs_trans_ijoin(sc->tp, sc->ip, 0);
+		}
+		error = xrep_xattr_reset_fork(sc);
+		if (error)
+			return error;
+	}
+
 	/*
 	 * If we modified the inode, roll the transaction but don't rejoin the
 	 * inode to the new transaction because xrep_bmap_data can do that.
@@ -1201,3 +1216,34 @@ xrep_trans_cancel_hook_dummy(
 	current->journal_info = *cookiep;
 	*cookiep = NULL;
 }
+
+/*
+ * See if this buffer can pass the given ->verify_struct() function.
+ *
+ * If the buffer already has ops attached and they're not the ones that were
+ * passed in, we reject the buffer.  Otherwise, we perform the structure test
+ * (note that we do not check CRCs) and return the outcome of the test.  The
+ * buffer ops and error state are left unchanged.
+ */
+bool
+xrep_buf_verify_struct(
+	struct xfs_buf			*bp,
+	const struct xfs_buf_ops	*ops)
+{
+	const struct xfs_buf_ops	*old_ops = bp->b_ops;
+	xfs_failaddr_t			fa;
+	int				old_error;
+
+	if (old_ops) {
+		if (old_ops != ops)
+			return false;
+	}
+
+	old_error = bp->b_error;
+	bp->b_ops = ops;
+	fa = bp->b_ops->verify_struct(bp);
+	bp->b_ops = old_ops;
+	bp->b_error = old_error;
+
+	return fa == NULL;
+}
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 06125d0a2c602..2bc5dd18d46f4 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -90,6 +90,7 @@ int xrep_bmap(struct xfs_scrub *sc, int whichfork, bool allow_unwritten);
 int xrep_metadata_inode_forks(struct xfs_scrub *sc);
 int xrep_setup_ag_rmapbt(struct xfs_scrub *sc);
 int xrep_setup_ag_refcountbt(struct xfs_scrub *sc);
+int xrep_setup_xattr(struct xfs_scrub *sc);
 
 /* Repair setup functions */
 int xrep_setup_ag_allocbt(struct xfs_scrub *sc);
@@ -123,6 +124,7 @@ int xrep_bmap_attr(struct xfs_scrub *sc);
 int xrep_bmap_cow(struct xfs_scrub *sc);
 int xrep_nlinks(struct xfs_scrub *sc);
 int xrep_fscounters(struct xfs_scrub *sc);
+int xrep_xattr(struct xfs_scrub *sc);
 
 #ifdef CONFIG_XFS_RT
 int xrep_rtbitmap(struct xfs_scrub *sc);
@@ -147,6 +149,8 @@ int xrep_trans_alloc_hook_dummy(struct xfs_mount *mp, void **cookiep,
 		struct xfs_trans **tpp);
 void xrep_trans_cancel_hook_dummy(void **cookiep, struct xfs_trans *tp);
 
+bool xrep_buf_verify_struct(struct xfs_buf *bp, const struct xfs_buf_ops *ops);
+
 #else
 
 #define xrep_ino_dqattach(sc)	(0)
@@ -190,6 +194,7 @@ xrep_setup_nothing(
 #define xrep_setup_ag_allocbt		xrep_setup_nothing
 #define xrep_setup_ag_rmapbt		xrep_setup_nothing
 #define xrep_setup_ag_refcountbt	xrep_setup_nothing
+#define xrep_setup_xattr		xrep_setup_nothing
 
 #define xrep_setup_inode(sc, imap)	((void)0)
 
@@ -215,6 +220,7 @@ xrep_setup_nothing(
 #define xrep_nlinks			xrep_notsupported
 #define xrep_fscounters			xrep_notsupported
 #define xrep_rtsummary			xrep_notsupported
+#define xrep_xattr			xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 9af91874e58b9..0b8fdd62055fe 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -334,7 +334,7 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.type	= ST_INODE,
 		.setup	= xchk_setup_xattr,
 		.scrub	= xchk_xattr,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_xattr,
 	},
 	[XFS_SCRUB_TYPE_SYMLINK] = {	/* symbolic link */
 		.type	= ST_INODE,
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 1f06c1ace5902..ba75a56b2e2de 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -2497,6 +2497,89 @@ TRACE_EVENT(xreap_bmapi_binval_scan,
 		  __entry->scan_blocks)
 );
 
+TRACE_EVENT(xrep_xattr_recover_leafblock,
+	TP_PROTO(struct xfs_inode *ip, xfs_dablk_t dabno, uint16_t magic),
+	TP_ARGS(ip, dabno, magic),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(xfs_dablk_t, dabno)
+		__field(uint16_t, magic)
+	),
+	TP_fast_assign(
+		__entry->dev = ip->i_mount->m_super->s_dev;
+		__entry->ino = ip->i_ino;
+		__entry->dabno = dabno;
+		__entry->magic = magic;
+	),
+	TP_printk("dev %d:%d ino 0x%llx dablk 0x%x magic 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->dabno,
+		  __entry->magic)
+);
+
+DECLARE_EVENT_CLASS(xrep_xattr_salvage_class,
+	TP_PROTO(struct xfs_inode *ip, unsigned int flags, char *name,
+		 unsigned int namelen, unsigned int valuelen),
+	TP_ARGS(ip, flags, name, namelen, valuelen),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(unsigned int, flags)
+		__field(unsigned int, namelen)
+		__dynamic_array(char, name, namelen)
+		__field(unsigned int, valuelen)
+	),
+	TP_fast_assign(
+		__entry->dev = ip->i_mount->m_super->s_dev;
+		__entry->ino = ip->i_ino;
+		__entry->flags = flags;
+		__entry->namelen = namelen;
+		memcpy(__get_str(name), name, namelen);
+		__entry->valuelen = valuelen;
+	),
+	TP_printk("dev %d:%d ino 0x%llx flags %s name '%.*s' valuelen 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		   __print_flags(__entry->flags, "|", XFS_ATTR_NAMESPACE_STR),
+		  __entry->namelen,
+		  __get_str(name),
+		  __entry->valuelen)
+);
+#define DEFINE_XREP_XATTR_SALVAGE_EVENT(name) \
+DEFINE_EVENT(xrep_xattr_salvage_class, name, \
+	TP_PROTO(struct xfs_inode *ip, unsigned int flags, char *name, \
+		 unsigned int namelen, unsigned int valuelen), \
+	TP_ARGS(ip, flags, name, namelen, valuelen))
+DEFINE_XREP_XATTR_SALVAGE_EVENT(xrep_xattr_salvage_rec);
+DEFINE_XREP_XATTR_SALVAGE_EVENT(xrep_xattr_insert_rec);
+
+TRACE_EVENT(xrep_xattr_class,
+	TP_PROTO(struct xfs_inode *ip, struct xfs_inode *arg_ip),
+	TP_ARGS(ip, arg_ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(xfs_ino_t, src_ino)
+	),
+	TP_fast_assign(
+		__entry->dev = ip->i_mount->m_super->s_dev;
+		__entry->ino = ip->i_ino;
+		__entry->src_ino = arg_ip->i_ino;
+	),
+	TP_printk("dev %d:%d ino 0x%llx src 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->src_ino)
+)
+#define DEFINE_XREP_XATTR_EVENT(name) \
+DEFINE_EVENT(xrep_xattr_class, name, \
+	TP_PROTO(struct xfs_inode *ip, struct xfs_inode *arg_ip), \
+	TP_ARGS(ip, arg_ip))
+DEFINE_XREP_XATTR_EVENT(xrep_xattr_rebuild_tree);
+DEFINE_XREP_XATTR_EVENT(xrep_xattr_reset_fork);
+
 #endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
 
 
diff --git a/fs/xfs/scrub/xfarray.c b/fs/xfs/scrub/xfarray.c
index f0f532c10a5ac..1bd690ac5d368 100644
--- a/fs/xfs/scrub/xfarray.c
+++ b/fs/xfs/scrub/xfarray.c
@@ -1081,3 +1081,20 @@ xfarray_sort(
 	kvfree(si);
 	return error;
 }
+
+/* How many bytes is this array consuming? */
+unsigned long long
+xfarray_bytes(
+	struct xfarray		*array)
+{
+	return xfile_bytes(array->xfile);
+}
+
+/* Empty the entire array. */
+void
+xfarray_truncate(
+	struct xfarray	*array)
+{
+	xfile_discard(array->xfile, 0, MAX_LFS_FILESIZE);
+	array->nr = 0;
+}
diff --git a/fs/xfs/scrub/xfarray.h b/fs/xfs/scrub/xfarray.h
index 0f1dac3aa1916..f06af7eb484ec 100644
--- a/fs/xfs/scrub/xfarray.h
+++ b/fs/xfs/scrub/xfarray.h
@@ -44,6 +44,8 @@ int xfarray_unset(struct xfarray *array, xfarray_idx_t idx);
 int xfarray_store(struct xfarray *array, xfarray_idx_t idx, const void *ptr);
 int xfarray_store_anywhere(struct xfarray *array, const void *ptr);
 bool xfarray_element_is_null(struct xfarray *array, const void *ptr);
+void xfarray_truncate(struct xfarray *array);
+unsigned long long xfarray_bytes(struct xfarray *array);
 
 /*
  * Load an array element, but zero the buffer if there's no data because we
diff --git a/fs/xfs/scrub/xfblob.c b/fs/xfs/scrub/xfblob.c
index 216f9cb2965a7..9c9ec90c69dbc 100644
--- a/fs/xfs/scrub/xfblob.c
+++ b/fs/xfs/scrub/xfblob.c
@@ -149,3 +149,20 @@ xfblob_free(
 	xfile_discard(blob->xfile, cookie, sizeof(key) + key.xb_size);
 	return 0;
 }
+
+/* How many bytes is this blob storage object consuming? */
+unsigned long long
+xfblob_bytes(
+	struct xfblob		*blob)
+{
+	return xfile_bytes(blob->xfile);
+}
+
+/* Drop all the blobs. */
+void
+xfblob_truncate(
+	struct xfblob	*blob)
+{
+	xfile_discard(blob->xfile, PAGE_SIZE, MAX_LFS_FILESIZE - PAGE_SIZE);
+	blob->last_offset = PAGE_SIZE;
+}
diff --git a/fs/xfs/scrub/xfblob.h b/fs/xfs/scrub/xfblob.h
index bd98647407f1d..78a67a06408f8 100644
--- a/fs/xfs/scrub/xfblob.h
+++ b/fs/xfs/scrub/xfblob.h
@@ -20,5 +20,7 @@ int xfblob_load(struct xfblob *blob, xfblob_cookie cookie, void *ptr,
 int xfblob_store(struct xfblob *blob, xfblob_cookie *cookie, const void *ptr,
 		uint32_t size);
 int xfblob_free(struct xfblob *blob, xfblob_cookie cookie);
+unsigned long long xfblob_bytes(struct xfblob *blob);
+void xfblob_truncate(struct xfblob *blob);
 
 #endif /* __XFS_SCRUB_XFBLOB_H__ */
diff --git a/fs/xfs/scrub/xfile.h b/fs/xfs/scrub/xfile.h
index 36061af2c1352..849f59da6a184 100644
--- a/fs/xfs/scrub/xfile.h
+++ b/fs/xfs/scrub/xfile.h
@@ -86,6 +86,18 @@ static inline loff_t xfile_size(struct xfile *xf)
 	return i_size_read(file_inode(xf->file));
 }
 
+static inline unsigned long long xfile_bytes(struct xfile *xf)
+{
+	struct xfile_stat	xs;
+	int			ret;
+
+	ret = xfile_stat(xf, &xs);
+	if (ret)
+		return 0;
+
+	return xs.bytes;
+}
+
 /* file block (aka system page size) to basic block conversions. */
 typedef unsigned long long	xfileoff_t;
 #define XFB_BLOCKSIZE		(PAGE_SIZE)
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index a61ad61cb9136..b62518968e784 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -481,6 +481,9 @@ _xfs_buf_obj_cmp(
 		 * it stale has not yet committed. i.e. we are
 		 * reallocating a busy extent. Skip this buffer and
 		 * continue searching for an exact match.
+		 *
+		 * Note: If we're scanning for incore buffers to stale, don't
+		 * complain if we find non-stale buffers.
 		 */
 		if (!(map->bm_flags & XBM_LIVESCAN))
 			ASSERT(bp->b_flags & XBF_STALE);
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index ee6f569c2f3d9..2c838b7471191 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -31,6 +31,8 @@
  * pos: file offset, in bytes
  * bytecount: number of bytes
  *
+ * dablk: directory or xattr block offset, in filesystem blocks
+ *
  * disize: ondisk file size, in bytes
  * isize: incore file size, in bytes
  *

[PATCH 4/6] xfs: scrub should set preen if attr leaf has holes

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If an attr block indicates that it could use compaction, set the preen
flag to have the attr fork rebuilt, since the attr fork rebuilder can
take care of that for us.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
---
 fs/xfs/scrub/attr.c    |    2 ++
 fs/xfs/scrub/dabtree.c |   16 ++++++++++++++++
 fs/xfs/scrub/dabtree.h |    1 +
 fs/xfs/scrub/trace.h   |    1 +
 4 files changed, 20 insertions(+)


diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c
index 692e1b2837bbb..7dccbc849b19b 100644
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -428,6 +428,8 @@ xchk_xattr_block(
 		xchk_da_set_corrupt(ds, level);
 	if (!xchk_xattr_set_map(ds->sc, ab->usedmap, 0, hdrsize))
 		xchk_da_set_corrupt(ds, level);
+	if (leafhdr.holes)
+		xchk_da_set_preen(ds, level);
 
 	if (ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		goto out;
diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c
index c71254088dffe..056de4819f866 100644
--- a/fs/xfs/scrub/dabtree.c
+++ b/fs/xfs/scrub/dabtree.c
@@ -78,6 +78,22 @@ xchk_da_set_corrupt(
 			__return_address);
 }
 
+/* Flag a da btree node in need of optimization. */
+void
+xchk_da_set_preen(
+	struct xchk_da_btree	*ds,
+	int			level)
+{
+	struct xfs_scrub	*sc = ds->sc;
+
+	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_PREEN;
+	trace_xchk_fblock_preen(sc, ds->dargs.whichfork,
+			xfs_dir2_da_to_db(ds->dargs.geo,
+				ds->state->path.blk[level].blkno),
+			__return_address);
+}
+
+/* Find an entry at a certain level in a da btree. */
 static struct xfs_da_node_entry *
 xchk_da_btree_node_entry(
 	struct xchk_da_btree		*ds,
diff --git a/fs/xfs/scrub/dabtree.h b/fs/xfs/scrub/dabtree.h
index 4f8c2138a1ec6..d654c125feb4d 100644
--- a/fs/xfs/scrub/dabtree.h
+++ b/fs/xfs/scrub/dabtree.h
@@ -35,6 +35,7 @@ bool xchk_da_process_error(struct xchk_da_btree *ds, int level, int *error);
 
 /* Check for da btree corruption. */
 void xchk_da_set_corrupt(struct xchk_da_btree *ds, int level);
+void xchk_da_set_preen(struct xchk_da_btree *ds, int level);
 
 int xchk_da_btree_hash(struct xchk_da_btree *ds, int level, __be32 *hashp);
 int xchk_da_btree(struct xfs_scrub *sc, int whichfork,
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index ba75a56b2e2de..87a68aee16bf5 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -367,6 +367,7 @@ DEFINE_EVENT(xchk_fblock_error_class, name, \
 
 DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xchk_fblock_error);
 DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xchk_fblock_warning);
+DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xchk_fblock_preen);
 
 #ifdef CONFIG_XFS_QUOTA
 DECLARE_EVENT_CLASS(xchk_dqiter_class,

[PATCH 5/6] xfs: flag empty xattr leaf blocks for optimization

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Empty xattr leaf blocks at offset zero are a waste of space but
otherwise harmless.  If we encounter one, flag it as an opportunity for
optimization.

If we encounter empty attr leaf blocks anywhere else in the attr fork,
that's corruption.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/attr.c    |   11 +++++++++++
 fs/xfs/scrub/dabtree.h |    2 ++
 2 files changed, 13 insertions(+)


diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c
index 7dccbc849b19b..07e8ca840745c 100644
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -420,6 +420,17 @@ xchk_xattr_block(
 	xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &leafhdr, leaf);
 	hdrsize = xfs_attr3_leaf_hdr_size(leaf);
 
+	/*
+	 * Empty xattr leaf blocks mapped at block 0 are probably a byproduct
+	 * of a race between setxattr and a log shutdown.  Anywhere else in the
+	 * attr fork is a corruption.
+	 */
+	if (leafhdr.count == 0) {
+		if (blk->blkno == 0)
+			xchk_da_set_preen(ds, level);
+		else
+			xchk_da_set_corrupt(ds, level);
+	}
 	if (leafhdr.usedbytes > mp->m_attr_geo->blksize)
 		xchk_da_set_corrupt(ds, level);
 	if (leafhdr.firstused > mp->m_attr_geo->blksize)
diff --git a/fs/xfs/scrub/dabtree.h b/fs/xfs/scrub/dabtree.h
index d654c125feb4d..de291e3b77dd8 100644
--- a/fs/xfs/scrub/dabtree.h
+++ b/fs/xfs/scrub/dabtree.h
@@ -37,6 +37,8 @@ bool xchk_da_process_error(struct xchk_da_btree *ds, int level, int *error);
 void xchk_da_set_corrupt(struct xchk_da_btree *ds, int level);
 void xchk_da_set_preen(struct xchk_da_btree *ds, int level);
 
+void xchk_da_set_preen(struct xchk_da_btree *ds, int level);
+
 int xchk_da_btree_hash(struct xchk_da_btree *ds, int level, __be32 *hashp);
 int xchk_da_btree(struct xfs_scrub *sc, int whichfork,
 		xchk_da_btree_rec_fn scrub_fn, void *private);

[PATCH 6/6] xfs: create an xattr iteration function for scrub

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a streamlined function to walk a file's xattrs, without all the
cursor management stuff in the regular listxattr.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Makefile           |    1 
 fs/xfs/scrub/attr.c       |  125 +++++++-----------
 fs/xfs/scrub/dab_bitmap.h |   37 +++++
 fs/xfs/scrub/listxattr.c  |  310 +++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/listxattr.h  |   17 ++
 5 files changed, 412 insertions(+), 78 deletions(-)
 create mode 100644 fs/xfs/scrub/dab_bitmap.h
 create mode 100644 fs/xfs/scrub/listxattr.c
 create mode 100644 fs/xfs/scrub/listxattr.h


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 9b227be3e28b6..be3dceb85e0f9 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -165,6 +165,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   ialloc.o \
 				   inode.o \
 				   iscan.o \
+				   listxattr.o \
 				   nlinks.o \
 				   parent.o \
 				   readdir.o \
diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c
index 07e8ca840745c..ff83051c79818 100644
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -21,6 +21,7 @@
 #include "scrub/common.h"
 #include "scrub/dabtree.h"
 #include "scrub/attr.h"
+#include "scrub/listxattr.h"
 #include "scrub/repair.h"
 
 /* Free the buffers linked from the xattr buffer. */
@@ -153,90 +154,81 @@ xchk_setup_xattr(
 
 /* Extended Attributes */
 
-struct xchk_xattr {
-	struct xfs_attr_list_context	context;
-	struct xfs_scrub		*sc;
-};
-
 /*
  * Check that an extended attribute key can be looked up by hash.
  *
- * We use the XFS attribute list iterator (i.e. xfs_attr_list_ilocked)
- * to call this function for every attribute key in an inode.  Once
- * we're here, we load the attribute value to see if any errors happen,
- * or if we get more or less data than we expected.
+ * We use the extended attribute walk helper to call this function for every
+ * attribute key in an inode.  Once we're here, we load the attribute value to
+ * see if any errors happen, or if we get more or less data than we expected.
  */
-static void
-xchk_xattr_listent(
-	struct xfs_attr_list_context	*context,
-	int				flags,
-	unsigned char			*name,
-	int				namelen,
-	int				valuelen)
+static int
+xchk_xattr_actor(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip,
+	unsigned int		attr_flags,
+	const unsigned char	*name,
+	unsigned int		namelen,
+	const void		*value,
+	unsigned int		valuelen,
+	void			*priv)
 {
 	struct xfs_da_args		args = {
 		.op_flags		= XFS_DA_OP_NOTIME,
-		.attr_filter		= flags & XFS_ATTR_NSP_ONDISK_MASK,
-		.geo			= context->dp->i_mount->m_attr_geo,
+		.attr_filter		= attr_flags & XFS_ATTR_NSP_ONDISK_MASK,
+		.geo			= sc->mp->m_attr_geo,
 		.whichfork		= XFS_ATTR_FORK,
-		.dp			= context->dp,
+		.dp			= ip,
 		.name			= name,
 		.namelen		= namelen,
 		.hashval		= xfs_da_hashname(name, namelen),
-		.trans			= context->tp,
+		.trans			= sc->tp,
 		.valuelen		= valuelen,
-		.owner			= context->dp->i_ino,
+		.owner			= ip->i_ino,
 	};
 	struct xchk_xattr_buf		*ab;
-	struct xchk_xattr		*sx;
 	int				error = 0;
 
-	sx = container_of(context, struct xchk_xattr, context);
-	ab = sx->sc->buf;
+	ab = sc->buf;
 
-	if (xchk_should_terminate(sx->sc, &error)) {
-		context->seen_enough = error;
-		return;
-	}
+	if (xchk_should_terminate(sc, &error))
+		return error;
 
-	if (flags & XFS_ATTR_INCOMPLETE) {
+	if (attr_flags & XFS_ATTR_INCOMPLETE) {
 		/* Incomplete attr key, just mark the inode for preening. */
-		xchk_ino_set_preen(sx->sc, context->dp->i_ino);
-		return;
+		xchk_ino_set_preen(sc, ip->i_ino);
+		return 0;
 	}
 
 	/* Only one namespace bit allowed. */
-	if (hweight32(flags & XFS_ATTR_NSP_ONDISK_MASK) > 1) {
-		xchk_fblock_set_corrupt(sx->sc, XFS_ATTR_FORK, args.blkno);
-		goto fail_xref;
+	if (hweight32(attr_flags & XFS_ATTR_NSP_ONDISK_MASK) > 1) {
+		xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, args.blkno);
+		return -ECANCELED;
 	}
 
 	/* Does this name make sense? */
 	if (!xfs_attr_namecheck(name, namelen)) {
-		xchk_fblock_set_corrupt(sx->sc, XFS_ATTR_FORK, args.blkno);
-		goto fail_xref;
+		xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, args.blkno);
+		return -ECANCELED;
 	}
 
 	/*
-	 * Local xattr values are stored in the attr leaf block, so we don't
-	 * need to retrieve the value from a remote block to detect corruption
-	 * problems.
+	 * Local and shortform xattr values are stored in the attr leaf block,
+	 * so we don't need to retrieve the value from a remote block to detect
+	 * corruption problems.
 	 */
-	if (flags & XFS_ATTR_LOCAL)
-		goto fail_xref;
+	if (value)
+		return 0;
 
 	/*
-	 * Try to allocate enough memory to extrat the attr value.  If that
-	 * doesn't work, we overload the seen_enough variable to convey
-	 * the error message back to the main scrub function.
+	 * Try to allocate enough memory to extract the attr value.  If that
+	 * doesn't work, return -EDEADLOCK as a signal to try again with a
+	 * maximally sized buffer.
 	 */
-	error = xchk_setup_xattr_buf(sx->sc, valuelen);
+	error = xchk_setup_xattr_buf(sc, valuelen);
 	if (error == -ENOMEM)
 		error = -EDEADLOCK;
-	if (error) {
-		context->seen_enough = error;
-		return;
-	}
+	if (error)
+		return error;
 
 	args.value = ab->value;
 
@@ -244,16 +236,13 @@ xchk_xattr_listent(
 	/* ENODATA means the hash lookup failed and the attr is bad */
 	if (error == -ENODATA)
 		error = -EFSCORRUPTED;
-	if (!xchk_fblock_process_error(sx->sc, XFS_ATTR_FORK, args.blkno,
+	if (!xchk_fblock_process_error(sc, XFS_ATTR_FORK, args.blkno,
 			&error))
-		goto fail_xref;
+		return error;
 	if (args.valuelen != valuelen)
-		xchk_fblock_set_corrupt(sx->sc, XFS_ATTR_FORK,
-					     args.blkno);
-fail_xref:
-	if (sx->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
-		context->seen_enough = 1;
-	return;
+		xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, args.blkno);
+
+	return 0;
 }
 
 /*
@@ -623,16 +612,6 @@ int
 xchk_xattr(
 	struct xfs_scrub		*sc)
 {
-	struct xchk_xattr		sx = {
-		.sc			= sc,
-		.context		= {
-			.dp		= sc->ip,
-			.tp		= sc->tp,
-			.resynch	= 1,
-			.put_listent	= xchk_xattr_listent,
-			.allow_incomplete = true,
-		},
-	};
 	xfs_dablk_t			last_checked = -1U;
 	int				error = 0;
 
@@ -661,12 +640,6 @@ xchk_xattr(
 	/*
 	 * Look up every xattr in this file by name and hash.
 	 *
-	 * Use the backend implementation of xfs_attr_list to call
-	 * xchk_xattr_listent on every attribute key in this inode.
-	 * In other words, we use the same iterator/callback mechanism
-	 * that listattr uses to scrub extended attributes, though in our
-	 * _listent function, we check the value of the attribute.
-	 *
 	 * The VFS only locks i_rwsem when modifying attrs, so keep all
 	 * three locks held because that's the only way to ensure we're
 	 * the only thread poking into the da btree.  We traverse the da
@@ -674,13 +647,9 @@ xchk_xattr(
 	 * iteration, which doesn't really follow the usual buffer
 	 * locking order.
 	 */
-	error = xfs_attr_list_ilocked(&sx.context);
+	error = xchk_xattr_walk(sc, sc->ip, xchk_xattr_actor, NULL);
 	if (!xchk_fblock_process_error(sc, XFS_ATTR_FORK, 0, &error))
 		return error;
 
-	/* Did our listent function try to return any errors? */
-	if (sx.context.seen_enough < 0)
-		return sx.context.seen_enough;
-
 	return 0;
 }
diff --git a/fs/xfs/scrub/dab_bitmap.h b/fs/xfs/scrub/dab_bitmap.h
new file mode 100644
index 0000000000000..0c6e3aad43954
--- /dev/null
+++ b/fs/xfs/scrub/dab_bitmap.h
@@ -0,0 +1,37 @@
+// 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_SCRUB_DAB_BITMAP_H__
+#define __XFS_SCRUB_DAB_BITMAP_H__
+
+/* Bitmaps, but for type-checked for xfs_dablk_t */
+
+struct xdab_bitmap {
+	struct xbitmap32	dabitmap;
+};
+
+static inline void xdab_bitmap_init(struct xdab_bitmap *bitmap)
+{
+	xbitmap32_init(&bitmap->dabitmap);
+}
+
+static inline void xdab_bitmap_destroy(struct xdab_bitmap *bitmap)
+{
+	xbitmap32_destroy(&bitmap->dabitmap);
+}
+
+static inline int xdab_bitmap_set(struct xdab_bitmap *bitmap,
+		xfs_dablk_t dabno, xfs_extlen_t len)
+{
+	return xbitmap32_set(&bitmap->dabitmap, dabno, len);
+}
+
+static inline bool xdab_bitmap_test(struct xdab_bitmap *bitmap,
+		xfs_dablk_t dabno, xfs_extlen_t *len)
+{
+	return xbitmap32_test(&bitmap->dabitmap, dabno, len);
+}
+
+#endif	/* __XFS_SCRUB_DAB_BITMAP_H__ */
diff --git a/fs/xfs/scrub/listxattr.c b/fs/xfs/scrub/listxattr.c
new file mode 100644
index 0000000000000..c8d7d7d723177
--- /dev/null
+++ b/fs/xfs/scrub/listxattr.c
@@ -0,0 +1,310 @@
+// 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_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_inode.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_attr.h"
+#include "xfs_attr_leaf.h"
+#include "xfs_attr_sf.h"
+#include "xfs_trans.h"
+#include "scrub/scrub.h"
+#include "scrub/bitmap.h"
+#include "scrub/dab_bitmap.h"
+#include "scrub/listxattr.h"
+
+/* Call a function for every entry in a shortform xattr structure. */
+STATIC int
+xchk_xattr_walk_sf(
+	struct xfs_scrub		*sc,
+	struct xfs_inode		*ip,
+	xchk_xattr_fn			attr_fn,
+	void				*priv)
+{
+	struct xfs_attr_shortform	*sf;
+	struct xfs_attr_sf_entry	*sfe;
+	unsigned int			i;
+	int				error;
+
+	sf = (struct xfs_attr_shortform *)ip->i_af.if_u1.if_data;
+	for (i = 0, sfe = &sf->list[0]; i < sf->hdr.count; i++) {
+		error = attr_fn(sc, ip, sfe->flags, sfe->nameval, sfe->namelen,
+				&sfe->nameval[sfe->namelen], sfe->valuelen,
+				priv);
+		if (error)
+			return error;
+
+		sfe = xfs_attr_sf_nextentry(sfe);
+	}
+
+	return 0;
+}
+
+/* Call a function for every entry in this xattr leaf block. */
+STATIC int
+xchk_xattr_walk_leaf_entries(
+	struct xfs_scrub		*sc,
+	struct xfs_inode		*ip,
+	xchk_xattr_fn			attr_fn,
+	struct xfs_buf			*bp,
+	void				*priv)
+{
+	struct xfs_attr3_icleaf_hdr	ichdr;
+	struct xfs_mount		*mp = sc->mp;
+	struct xfs_attr_leafblock	*leaf = bp->b_addr;
+	struct xfs_attr_leaf_entry	*entry;
+	unsigned int			i;
+	int				error;
+
+	xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf);
+	entry = xfs_attr3_leaf_entryp(leaf);
+
+	for (i = 0; i < ichdr.count; entry++, i++) {
+		void			*value;
+		unsigned char		*name;
+		unsigned int		namelen, valuelen;
+
+		if (entry->flags & XFS_ATTR_LOCAL) {
+			struct xfs_attr_leaf_name_local		*name_loc;
+
+			name_loc = xfs_attr3_leaf_name_local(leaf, i);
+			name = name_loc->nameval;
+			namelen = name_loc->namelen;
+			value = &name_loc->nameval[name_loc->namelen];
+			valuelen = be16_to_cpu(name_loc->valuelen);
+		} else {
+			struct xfs_attr_leaf_name_remote	*name_rmt;
+
+			name_rmt = xfs_attr3_leaf_name_remote(leaf, i);
+			name = name_rmt->name;
+			namelen = name_rmt->namelen;
+			value = NULL;
+			valuelen = be32_to_cpu(name_rmt->valuelen);
+		}
+
+		error = attr_fn(sc, ip, entry->flags, name, namelen, value,
+				valuelen, priv);
+		if (error)
+			return error;
+
+	}
+
+	return 0;
+}
+
+/*
+ * Call a function for every entry in a leaf-format xattr structure.  Avoid
+ * memory allocations for the loop detector since there's only one block.
+ */
+STATIC int
+xchk_xattr_walk_leaf(
+	struct xfs_scrub		*sc,
+	struct xfs_inode		*ip,
+	xchk_xattr_fn			attr_fn,
+	void				*priv)
+{
+	struct xfs_buf			*leaf_bp;
+	int				error;
+
+	error = xfs_attr3_leaf_read(sc->tp, ip, ip->i_ino, 0, &leaf_bp);
+	if (error)
+		return error;
+
+	error = xchk_xattr_walk_leaf_entries(sc, ip, attr_fn, leaf_bp, priv);
+	xfs_trans_brelse(sc->tp, leaf_bp);
+	return error;
+}
+
+/* Find the leftmost leaf in the xattr dabtree. */
+STATIC int
+xchk_xattr_find_leftmost_leaf(
+	struct xfs_scrub		*sc,
+	struct xfs_inode		*ip,
+	struct xdab_bitmap		*seen_dablks,
+	struct xfs_buf			**leaf_bpp)
+{
+	struct xfs_da3_icnode_hdr	nodehdr;
+	struct xfs_mount		*mp = sc->mp;
+	struct xfs_trans		*tp = sc->tp;
+	struct xfs_da_intnode		*node;
+	struct xfs_da_node_entry	*btree;
+	struct xfs_buf			*bp;
+	xfs_failaddr_t			fa;
+	xfs_dablk_t			blkno = 0;
+	unsigned int			expected_level = 0;
+	int				error;
+
+	for (;;) {
+		xfs_extlen_t		len = 1;
+		uint16_t		magic;
+
+		/* Make sure we haven't seen this new block already. */
+		if (xdab_bitmap_test(seen_dablks, blkno, &len))
+			return -EFSCORRUPTED;
+
+		error = xfs_da3_node_read(tp, ip, blkno, &bp, XFS_ATTR_FORK);
+		if (error)
+			return error;
+
+		node = bp->b_addr;
+		magic = be16_to_cpu(node->hdr.info.magic);
+		if (magic == XFS_ATTR_LEAF_MAGIC ||
+		    magic == XFS_ATTR3_LEAF_MAGIC)
+			break;
+
+		error = -EFSCORRUPTED;
+		if (magic != XFS_DA_NODE_MAGIC &&
+		    magic != XFS_DA3_NODE_MAGIC)
+			goto out_buf;
+
+		fa = xfs_da3_node_header_check(bp, ip->i_ino);
+		if (fa)
+			goto out_buf;
+
+		xfs_da3_node_hdr_from_disk(mp, &nodehdr, node);
+
+		if (nodehdr.count == 0 || nodehdr.level >= XFS_DA_NODE_MAXDEPTH)
+			goto out_buf;
+
+		/* Check the level from the root node. */
+		if (blkno == 0)
+			expected_level = nodehdr.level - 1;
+		else if (expected_level != nodehdr.level)
+			goto out_buf;
+		else
+			expected_level--;
+
+		/* Remember that we've seen this node. */
+		error = xdab_bitmap_set(seen_dablks, blkno, 1);
+		if (error)
+			goto out_buf;
+
+		/* Find the next level towards the leaves of the dabtree. */
+		btree = nodehdr.btree;
+		blkno = be32_to_cpu(btree->before);
+		xfs_trans_brelse(tp, bp);
+	}
+
+	error = -EFSCORRUPTED;
+	fa = xfs_attr3_leaf_header_check(bp, ip->i_ino);
+	if (fa)
+		goto out_buf;
+
+	if (expected_level != 0)
+		goto out_buf;
+
+	/* Remember that we've seen this leaf. */
+	error = xdab_bitmap_set(seen_dablks, blkno, 1);
+	if (error)
+		goto out_buf;
+
+	*leaf_bpp = bp;
+	return 0;
+
+out_buf:
+	xfs_trans_brelse(tp, bp);
+	return error;
+}
+
+/* Call a function for every entry in a node-format xattr structure. */
+STATIC int
+xchk_xattr_walk_node(
+	struct xfs_scrub		*sc,
+	struct xfs_inode		*ip,
+	xchk_xattr_fn			attr_fn,
+	void				*priv)
+{
+	struct xfs_attr3_icleaf_hdr	leafhdr;
+	struct xdab_bitmap		seen_dablks;
+	struct xfs_mount		*mp = sc->mp;
+	struct xfs_attr_leafblock	*leaf;
+	struct xfs_buf			*leaf_bp;
+	int				error;
+
+	xdab_bitmap_init(&seen_dablks);
+
+	error = xchk_xattr_find_leftmost_leaf(sc, ip, &seen_dablks, &leaf_bp);
+	if (error)
+		goto out_bitmap;
+
+	for (;;) {
+		xfs_extlen_t	len;
+
+		error = xchk_xattr_walk_leaf_entries(sc, ip, attr_fn, leaf_bp,
+				priv);
+		if (error)
+			goto out_leaf;
+
+		/* Find the right sibling of this leaf block. */
+		leaf = leaf_bp->b_addr;
+		xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &leafhdr, leaf);
+		if (leafhdr.forw == 0)
+			goto out_leaf;
+
+		xfs_trans_brelse(sc->tp, leaf_bp);
+
+		/* Make sure we haven't seen this new leaf already. */
+		len = 1;
+		if (xdab_bitmap_test(&seen_dablks, leafhdr.forw, &len))
+			goto out_bitmap;
+
+		error = xfs_attr3_leaf_read(sc->tp, ip, ip->i_ino,
+				leafhdr.forw, &leaf_bp);
+		if (error)
+			goto out_bitmap;
+
+		/* Remember that we've seen this new leaf. */
+		error = xdab_bitmap_set(&seen_dablks, leafhdr.forw, 1);
+		if (error)
+			goto out_leaf;
+	}
+
+out_leaf:
+	xfs_trans_brelse(sc->tp, leaf_bp);
+out_bitmap:
+	xdab_bitmap_destroy(&seen_dablks);
+	return error;
+}
+
+/*
+ * Call a function for every extended attribute in a file.
+ *
+ * Callers must hold the ILOCK.  No validation or cursor restarts allowed.
+ * Returns -EFSCORRUPTED on any problem, including loops in the dabtree.
+ */
+int
+xchk_xattr_walk(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip,
+	xchk_xattr_fn		attr_fn,
+	void			*priv)
+{
+	int			error;
+
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
+
+	if (!xfs_inode_hasattr(ip))
+		return 0;
+
+	if (ip->i_af.if_format == XFS_DINODE_FMT_LOCAL)
+		return xchk_xattr_walk_sf(sc, ip, attr_fn, priv);
+
+	/* attr functions require that the attr fork is loaded */
+	error = xfs_iread_extents(sc->tp, ip, XFS_ATTR_FORK);
+	if (error)
+		return error;
+
+	if (xfs_attr_is_leaf(ip))
+		return xchk_xattr_walk_leaf(sc, ip, attr_fn, priv);
+
+	return xchk_xattr_walk_node(sc, ip, attr_fn, priv);
+}
diff --git a/fs/xfs/scrub/listxattr.h b/fs/xfs/scrub/listxattr.h
new file mode 100644
index 0000000000000..48fe89d05946b
--- /dev/null
+++ b/fs/xfs/scrub/listxattr.h
@@ -0,0 +1,17 @@
+/* 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_SCRUB_LISTXATTR_H__
+#define __XFS_SCRUB_LISTXATTR_H__
+
+typedef int (*xchk_xattr_fn)(struct xfs_scrub *sc, struct xfs_inode *ip,
+		unsigned int attr_flags, const unsigned char *name,
+		unsigned int namelen, const void *value, unsigned int valuelen,
+		void *priv);
+
+int xchk_xattr_walk(struct xfs_scrub *sc, struct xfs_inode *ip,
+		xchk_xattr_fn attr_fn, void *priv);
+
+#endif /* __XFS_SCRUB_LISTXATTR_H__ */

[PATCH 1/2] xfs: ensure unlinked list state is consistent with nlink during scrub

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Now that we have the means to tell if an inode is on an unlinked inode
list or not, we can check that an inode with zero link count is on the
unlinked list; and an inode that has nonzero link count is not on that
list.  Make repair clean things up too.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/inode.c        |   19 ++++++++++++++++++
 fs/xfs/scrub/inode_repair.c |   45 +++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_inode.c          |    5 +----
 fs/xfs/xfs_inode.h          |    2 ++
 4 files changed, 67 insertions(+), 4 deletions(-)


diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index 6e2fe2d6250b3..d32716fb2fecf 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -739,6 +739,23 @@ xchk_inode_check_reflink_iflag(
 		xchk_ino_set_corrupt(sc, ino);
 }
 
+/*
+ * If this inode has zero link count, it must be on the unlinked list.  If
+ * it has nonzero link count, it must not be on the unlinked list.
+ */
+STATIC void
+xchk_inode_check_unlinked(
+	struct xfs_scrub	*sc)
+{
+	if (VFS_I(sc->ip)->i_nlink == 0) {
+		if (!xfs_inode_on_unlinked_list(sc->ip))
+			xchk_ino_set_corrupt(sc, sc->ip->i_ino);
+	} else {
+		if (xfs_inode_on_unlinked_list(sc->ip))
+			xchk_ino_set_corrupt(sc, sc->ip->i_ino);
+	}
+}
+
 /* Scrub an inode. */
 int
 xchk_inode(
@@ -771,6 +788,8 @@ xchk_inode(
 	if (S_ISREG(VFS_I(sc->ip)->i_mode))
 		xchk_inode_check_reflink_iflag(sc, sc->ip->i_ino);
 
+	xchk_inode_check_unlinked(sc);
+
 	xchk_inode_xref(sc, sc->ip->i_ino, &di);
 out:
 	return error;
diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c
index 549b66ef826a9..50bcc5a4c3df1 100644
--- a/fs/xfs/scrub/inode_repair.c
+++ b/fs/xfs/scrub/inode_repair.c
@@ -1697,6 +1697,46 @@ xrep_inode_problems(
 	return xrep_roll_trans(sc);
 }
 
+/*
+ * Make sure this inode's unlinked list pointers are consistent with its
+ * link count.
+ */
+STATIC int
+xrep_inode_unlinked(
+	struct xfs_scrub	*sc)
+{
+	unsigned int		nlink = VFS_I(sc->ip)->i_nlink;
+	int			error;
+
+	/*
+	 * If this inode is linked from the directory tree and on the unlinked
+	 * list, remove it from the unlinked list.
+	 */
+	if (nlink > 0 && xfs_inode_on_unlinked_list(sc->ip)) {
+		struct xfs_perag	*pag;
+		int			error;
+
+		pag = xfs_perag_get(sc->mp,
+				XFS_INO_TO_AGNO(sc->mp, sc->ip->i_ino));
+		error = xfs_iunlink_remove(sc->tp, pag, sc->ip);
+		xfs_perag_put(pag);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * If this inode is not linked from the directory tree yet not on the
+	 * unlinked list, put it on the unlinked list.
+	 */
+	if (nlink == 0 && !xfs_inode_on_unlinked_list(sc->ip)) {
+		error = xfs_iunlink(sc->tp, sc->ip);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
 /* Repair an inode's fields. */
 int
 xrep_inode(
@@ -1746,5 +1786,10 @@ xrep_inode(
 			return error;
 	}
 
+	/* Reconnect incore unlinked list */
+	error = xrep_inode_unlinked(sc);
+	if (error)
+		return error;
+
 	return xrep_defer_finish(sc);
 }
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 70705e2e30f79..970daeb160b24 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -42,9 +42,6 @@
 
 struct kmem_cache *xfs_inode_cache;
 
-STATIC int xfs_iunlink_remove(struct xfs_trans *tp, struct xfs_perag *pag,
-	struct xfs_inode *);
-
 /*
  * helper function to extract extent size hint from inode
  */
@@ -2254,7 +2251,7 @@ xfs_iunlink_remove_inode(
 /*
  * Pull the on-disk inode from the AGI unlinked list.
  */
-STATIC int
+int
 xfs_iunlink_remove(
 	struct xfs_trans	*tp,
 	struct xfs_perag	*pag,
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index b6f10ea725857..f11e91c6e2182 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -613,6 +613,8 @@ extern struct kmem_cache	*xfs_inode_cache;
 bool xfs_inode_needs_inactive(struct xfs_inode *ip);
 
 int xfs_iunlink(struct xfs_trans *tp, struct xfs_inode *ip);
+int xfs_iunlink_remove(struct xfs_trans *tp, struct xfs_perag *pag,
+		struct xfs_inode *ip);
 
 void xfs_end_io(struct work_struct *work);
 

[PATCH 2/2] xfs: update the unlinked list when repairing link counts

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

When we're repairing the link counts of a file, we must ensure either
that the file has zero link count and is on the unlinked list; or that
it has nonzero link count and is not on the unlinked list.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/nlinks_repair.c |   42 +++++++++++++++++++++++++++++++++---------
 1 file changed, 33 insertions(+), 9 deletions(-)


diff --git a/fs/xfs/scrub/nlinks_repair.c b/fs/xfs/scrub/nlinks_repair.c
index b87618322f55b..58cacb8e94c1b 100644
--- a/fs/xfs/scrub/nlinks_repair.c
+++ b/fs/xfs/scrub/nlinks_repair.c
@@ -17,6 +17,7 @@
 #include "xfs_iwalk.h"
 #include "xfs_ialloc.h"
 #include "xfs_sb.h"
+#include "xfs_ag.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/repair.h"
@@ -36,6 +37,20 @@
  * inode is locked.
  */
 
+/* Remove an inode from the unlinked list. */
+STATIC int
+xrep_nlinks_iunlink_remove(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_perag	*pag;
+	int			error;
+
+	pag = xfs_perag_get(sc->mp, XFS_INO_TO_AGNO(sc->mp, sc->ip->i_ino));
+	error = xfs_iunlink_remove(sc->tp, pag, sc->ip);
+	xfs_perag_put(pag);
+	return error;
+}
+
 /*
  * Correct the link count of the given inode.  Because we have to grab locks
  * and resources in a certain order, it's possible that this will be a no-op.
@@ -99,16 +114,25 @@ xrep_nlinks_repair_inode(
 	}
 
 	/*
-	 * We did not find any links to this inode.  If the inode agrees, we
-	 * have nothing further to do.  If not, the inode has a nonzero link
-	 * count and we don't have anywhere to graft the child onto.  Dropping
-	 * a live inode's link count to zero can cause unexpected shutdowns in
-	 * inactivation, so leave it alone.
+	 * If this inode is linked from the directory tree and on the unlinked
+	 * list, remove it from the unlinked list.
 	 */
-	if (total_links == 0) {
-		if (actual_nlink != 0)
-			trace_xrep_nlinks_unfixable_inode(mp, ip, &obs);
-		goto out_trans;
+	if (total_links > 0 && xfs_inode_on_unlinked_list(ip)) {
+		error = xrep_nlinks_iunlink_remove(sc);
+		if (error)
+			goto out_trans;
+		dirty = true;
+	}
+
+	/*
+	 * If this inode is not linked from the directory tree yet not on the
+	 * unlinked list, put it on the unlinked list.
+	 */
+	if (total_links == 0 && !xfs_inode_on_unlinked_list(ip)) {
+		error = xfs_iunlink(sc->tp, ip);
+		if (error)
+			goto out_trans;
+		dirty = true;
 	}
 
 	/* Commit the new link count if it changed. */

[PATCH 1/4] xfs: online repair of directories

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If a directory looks like it's in bad shape, try to sift through the
rubble to find whatever directory entries we can, scan the directory
tree for the parent (if needed), stage the new directory contents in a
temporary file and use the atomic extent swapping mechanism to commit
the results in bulk.  As a side effect of this patch, directory
inactivation will be able to purge any leftover dir blocks.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Makefile              |    1 
 fs/xfs/scrub/dir.c           |    9 
 fs/xfs/scrub/dir_repair.c    | 1346 ++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/inode_repair.c  |    5 
 fs/xfs/scrub/nlinks.c        |   23 +
 fs/xfs/scrub/nlinks_repair.c |    9 
 fs/xfs/scrub/parent.c        |    4 
 fs/xfs/scrub/readdir.c       |    7 
 fs/xfs/scrub/repair.c        |    1 
 fs/xfs/scrub/repair.h        |    4 
 fs/xfs/scrub/scrub.c         |    2 
 fs/xfs/scrub/tempfile.c      |   13 
 fs/xfs/scrub/tempfile.h      |    2 
 fs/xfs/scrub/trace.h         |  112 +++
 fs/xfs/xfs_inode.c           |   51 ++
 15 files changed, 1587 insertions(+), 2 deletions(-)
 create mode 100644 fs/xfs/scrub/dir_repair.c


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index be3dceb85e0f9..fd64a9043522c 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -198,6 +198,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   attr_repair.o \
 				   bmap_repair.o \
 				   cow_repair.o \
+				   dir_repair.o \
 				   fscounters_repair.o \
 				   ialloc_repair.o \
 				   inode_repair.o \
diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index 7bac74621af77..3fe6ffcf9c062 100644
--- a/fs/xfs/scrub/dir.c
+++ b/fs/xfs/scrub/dir.c
@@ -21,12 +21,21 @@
 #include "scrub/dabtree.h"
 #include "scrub/readdir.h"
 #include "scrub/health.h"
+#include "scrub/repair.h"
 
 /* Set us up to scrub directories. */
 int
 xchk_setup_directory(
 	struct xfs_scrub	*sc)
 {
+	int			error;
+
+	if (xchk_could_repair(sc)) {
+		error = xrep_setup_directory(sc);
+		if (error)
+			return error;
+	}
+
 	return xchk_setup_inode_contents(sc, 0);
 }
 
diff --git a/fs/xfs/scrub/dir_repair.c b/fs/xfs/scrub/dir_repair.c
new file mode 100644
index 0000000000000..0b320212da230
--- /dev/null
+++ b/fs/xfs/scrub/dir_repair.c
@@ -0,0 +1,1346 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2020-2024 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_defer.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_dir2.h"
+#include "xfs_dir2_priv.h"
+#include "xfs_bmap.h"
+#include "xfs_quota.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_trans_space.h"
+#include "xfs_bmap_util.h"
+#include "xfs_swapext.h"
+#include "xfs_xchgrange.h"
+#include "xfs_ag.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/tempfile.h"
+#include "scrub/tempswap.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
+#include "scrub/xfblob.h"
+#include "scrub/readdir.h"
+#include "scrub/reap.h"
+
+/*
+ * Directory Repair
+ * ================
+ *
+ * We repair directories by reading the directory data blocks looking for
+ * directory entries that look salvageable (name passes verifiers, entry points
+ * to a valid allocated inode, etc).  Each entry worth salvaging is stashed in
+ * memory, and the stashed entries are periodically replayed into a temporary
+ * directory to constrain memory use.  Batching the construction of the
+ * temporary directory in this fashion reduces lock cycling of the directory
+ * being repaired and the temporary directory, and will later become important
+ * for parent pointer scanning.
+ *
+ * Directory entries added to the temporary directory do not elevate the link
+ * counts of the inodes found.  When salvaging completes, the remaining stashed
+ * entries are replayed to the temporary directory.  An atomic extent swap is
+ * used to commit the new directory blocks to the directory being repaired.
+ * This will disrupt readdir cursors.
+ *
+ * Legacy Locking Issues
+ * ---------------------
+ *
+ * Prior to Linux 6.5, if /a, /a/b, and /c were all directories, the VFS would
+ * not take i_rwsem on /a/b for a "mv /a/b /c/" operation.  This meant that
+ * only b's ILOCK protected b's dotdot update.  b's IOLOCK was not taken,
+ * unlike every other dotdot update (link, remove, mkdir).  If the repair code
+ * dropped the ILOCK, we it was required either to revalidate the dotdot entry
+ * or to use dirent hooks to capture updates from other threads.
+ */
+
+/* Directory entry to be restored in the new directory. */
+struct xrep_dirent {
+	/* Cookie for retrieval of the dirent name. */
+	xfblob_cookie		name_cookie;
+
+	/* Target inode number. */
+	xfs_ino_t		ino;
+
+	/* Length of the dirent name. */
+	uint8_t			namelen;
+
+	/* File type of the dirent. */
+	uint8_t			ftype;
+};
+
+/*
+ * Stash up to 8 pages of recovered dirent data in dir_entries and dir_names
+ * before we write them to the temp dir.
+ */
+#define XREP_DIR_MAX_STASH_BYTES	(PAGE_SIZE * 8)
+
+struct xrep_dir {
+	struct xfs_scrub	*sc;
+
+	/* Fixed-size array of xrep_dirent structures. */
+	struct xfarray		*dir_entries;
+
+	/* Blobs containing directory entry names. */
+	struct xfblob		*dir_names;
+
+	/* Information for swapping data forks at the end. */
+	struct xrep_tempswap	tx;
+
+	/* Preallocated args struct for performing dir operations */
+	struct xfs_da_args	args;
+
+	/*
+	 * This is the parent that we're going to set on the reconstructed
+	 * directory.
+	 */
+	xfs_ino_t		parent_ino;
+
+	/* How many subdirectories did we find? */
+	uint64_t		subdirs;
+
+	/* How many dirents did we find? */
+	unsigned int		dirents;
+
+	/* Directory entry name, plus the trailing null. */
+	unsigned char		namebuf[MAXNAMELEN];
+};
+
+/* Tear down all the incore stuff we created. */
+static void
+xrep_dir_teardown(
+	struct xfs_scrub	*sc)
+{
+	struct xrep_dir		*rd = sc->buf;
+
+	xfblob_destroy(rd->dir_names);
+	xfarray_destroy(rd->dir_entries);
+}
+
+/* Set up for a directory repair. */
+int
+xrep_setup_directory(
+	struct xfs_scrub	*sc)
+{
+	struct xrep_dir		*rd;
+	int			error;
+
+	error = xrep_tempfile_create(sc, S_IFDIR);
+	if (error)
+		return error;
+
+	rd = kvzalloc(sizeof(struct xrep_dir), XCHK_GFP_FLAGS);
+	if (!rd)
+		return -ENOMEM;
+	rd->sc = sc;
+	sc->buf = rd;
+
+	return 0;
+}
+
+/*
+ * If we're the root of a directory tree, we are our own parent.  If we're an
+ * unlinked directory, the parent /won't/ have a link to us.  Set the parent
+ * directory to the root for both cases.  Returns NULLFSINO if we don't know
+ * what to do.
+ */
+static inline xfs_ino_t
+xrep_dir_self_parent(
+	struct xrep_dir		*rd)
+{
+	struct xfs_scrub	*sc = rd->sc;
+
+	if (sc->ip->i_ino == sc->mp->m_sb.sb_rootino)
+		return sc->mp->m_sb.sb_rootino;
+
+	if (VFS_I(sc->ip)->i_nlink == 0)
+		return sc->mp->m_sb.sb_rootino;
+
+	return NULLFSINO;
+}
+
+/*
+ * Look up the dotdot entry.  Returns NULLFSINO if we don't know what to do.
+ * The next patch will check this more carefully.
+ */
+static inline xfs_ino_t
+xrep_dir_lookup_parent(
+	struct xrep_dir		*rd)
+{
+	struct xfs_scrub	*sc = rd->sc;
+	xfs_ino_t		ino;
+	int			error;
+
+	error = xfs_dir_lookup(sc->tp, sc->ip, &xfs_name_dotdot, &ino, NULL);
+	if (error)
+		return NULLFSINO;
+	if (!xfs_verify_dir_ino(sc->mp, ino))
+		return NULLFSINO;
+
+	return ino;
+}
+
+/*
+ * Try to find the parent of the directory being repaired.
+ *
+ * NOTE: This function will someday be augmented by the directory parent repair
+ * code, which will know how to check the parent and scan the filesystem if
+ * we cannot find anything.  Inode scans will have to be done before we start
+ * salvaging directory entries, so we do this now.
+ */
+STATIC int
+xrep_dir_find_parent(
+	struct xrep_dir		*rd)
+{
+	xfs_ino_t		ino;
+
+	ino = xrep_dir_self_parent(rd);
+	if (ino != NULLFSINO) {
+		rd->parent_ino = ino;
+		return 0;
+	}
+
+	ino = xrep_dir_lookup_parent(rd);
+	if (ino != NULLFSINO) {
+		rd->parent_ino = ino;
+		return 0;
+	}
+
+	/* NOTE: A future patch will deal with moving orphans. */
+	return -EFSCORRUPTED;
+}
+
+/*
+ * Decide if we want to salvage this entry.  We don't bother with oversized
+ * names or the dot entry.
+ */
+STATIC int
+xrep_dir_want_salvage(
+	struct xrep_dir		*rd,
+	const char		*name,
+	int			namelen,
+	xfs_ino_t		ino)
+{
+	struct xfs_mount	*mp = rd->sc->mp;
+
+	/* No pointers to ourselves or to garbage. */
+	if (ino == rd->sc->ip->i_ino)
+		return false;
+	if (!xfs_verify_dir_ino(mp, ino))
+		return false;
+
+	/* No weird looking names or dot entries. */
+	if (namelen >= MAXNAMELEN || namelen <= 0)
+		return false;
+	if (namelen == 1 && name[0] == '.')
+		return false;
+
+	return true;
+}
+
+/*
+ * Remember that we want to create a dirent in the tempdir.  These stashed
+ * actions will be replayed later.
+ */
+STATIC int
+xrep_dir_stash_createname(
+	struct xrep_dir		*rd,
+	const struct xfs_name	*name,
+	xfs_ino_t		ino)
+{
+	struct xrep_dirent	dirent = {
+		.ino		= ino,
+		.namelen	= name->len,
+		.ftype		= name->type,
+	};
+	int			error;
+
+	trace_xrep_dir_stash_createname(rd->sc->tempip, name, ino);
+
+	error = xfblob_store(rd->dir_names, &dirent.name_cookie, name->name,
+			name->len);
+	if (error)
+		return error;
+
+	return xfarray_append(rd->dir_entries, &dirent);
+}
+
+/* Allocate an in-core record to hold entries while we rebuild the dir data. */
+STATIC int
+xrep_dir_salvage_entry(
+	struct xrep_dir		*rd,
+	unsigned char		*name,
+	unsigned int		namelen,
+	xfs_ino_t		ino)
+{
+	struct xfs_name		xname = {
+		.name		= name,
+	};
+	struct xfs_scrub	*sc = rd->sc;
+	struct xfs_inode	*ip;
+	unsigned int		i = 0;
+	int			error = 0;
+
+	if (xchk_should_terminate(sc, &error))
+		return error;
+
+	/*
+	 * Truncate the name to the first character that would trip namecheck.
+	 * If we no longer have a name after that, ignore this entry.
+	 */
+	while (i < namelen && name[i] != 0 && name[i] != '/')
+		i++;
+	if (i == 0)
+		return 0;
+	xname.len = i;
+
+	/* Ignore '..' entries; we already picked the new parent. */
+	if (xname.len == 2 && name[0] == '.' && name[1] == '.') {
+		trace_xrep_dir_salvaged_parent(sc->ip, ino);
+		return 0;
+	}
+
+	trace_xrep_dir_salvage_entry(sc->ip, &xname, ino);
+
+	/*
+	 * Compute the ftype or dump the entry if we can't.  We don't lock the
+	 * inode because inodes can't change type while we have a reference.
+	 */
+	error = xchk_iget(sc, ino, &ip);
+	if (error)
+		return 0;
+
+	xname.type = xfs_mode_to_ftype(VFS_I(ip)->i_mode);
+	xchk_irele(sc, ip);
+
+	return xrep_dir_stash_createname(rd, &xname, ino);
+}
+
+/* Record a shortform directory entry for later reinsertion. */
+STATIC int
+xrep_dir_salvage_sf_entry(
+	struct xrep_dir			*rd,
+	struct xfs_dir2_sf_hdr		*sfp,
+	struct xfs_dir2_sf_entry	*sfep)
+{
+	xfs_ino_t			ino;
+
+	ino = xfs_dir2_sf_get_ino(rd->sc->mp, sfp, sfep);
+	if (!xrep_dir_want_salvage(rd, sfep->name, sfep->namelen, ino))
+		return 0;
+
+	return xrep_dir_salvage_entry(rd, sfep->name, sfep->namelen, ino);
+}
+
+/* Record a regular directory entry for later reinsertion. */
+STATIC int
+xrep_dir_salvage_data_entry(
+	struct xrep_dir			*rd,
+	struct xfs_dir2_data_entry	*dep)
+{
+	xfs_ino_t			ino;
+
+	ino = be64_to_cpu(dep->inumber);
+	if (!xrep_dir_want_salvage(rd, dep->name, dep->namelen, ino))
+		return 0;
+
+	return xrep_dir_salvage_entry(rd, dep->name, dep->namelen, ino);
+}
+
+/* Try to recover block/data format directory entries. */
+STATIC int
+xrep_dir_recover_data(
+	struct xrep_dir		*rd,
+	struct xfs_buf		*bp)
+{
+	struct xfs_da_geometry	*geo = rd->sc->mp->m_dir_geo;
+	unsigned int		offset;
+	unsigned int		end;
+	int			error = 0;
+
+	/*
+	 * Loop over the data portion of the block.
+	 * Each object is a real entry (dep) or an unused one (dup).
+	 */
+	offset = geo->data_entry_offset;
+	end = min_t(unsigned int, BBTOB(bp->b_length),
+			xfs_dir3_data_end_offset(geo, bp->b_addr));
+
+	while (offset < end) {
+		struct xfs_dir2_data_unused	*dup = bp->b_addr + offset;
+		struct xfs_dir2_data_entry	*dep = bp->b_addr + offset;
+
+		if (xchk_should_terminate(rd->sc, &error))
+			return error;
+
+		/* Skip unused entries. */
+		if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
+			offset += be16_to_cpu(dup->length);
+			continue;
+		}
+
+		/* Don't walk off the end of the block. */
+		offset += xfs_dir2_data_entsize(rd->sc->mp, dep->namelen);
+		if (offset > end)
+			break;
+
+		/* Ok, let's save this entry. */
+		error = xrep_dir_salvage_data_entry(rd, dep);
+		if (error)
+			return error;
+
+	}
+
+	return 0;
+}
+
+/* Try to recover shortform directory entries. */
+STATIC int
+xrep_dir_recover_sf(
+	struct xrep_dir			*rd)
+{
+	struct xfs_dir2_sf_hdr		*sfp;
+	struct xfs_dir2_sf_entry	*sfep;
+	struct xfs_dir2_sf_entry	*next;
+	struct xfs_ifork		*ifp;
+	xfs_ino_t			ino;
+	unsigned char			*end;
+	int				error = 0;
+
+	ifp = xfs_ifork_ptr(rd->sc->ip, XFS_DATA_FORK);
+	sfp = (struct xfs_dir2_sf_hdr *)rd->sc->ip->i_df.if_u1.if_data;
+	end = (unsigned char *)ifp->if_u1.if_data + ifp->if_bytes;
+
+	ino = xfs_dir2_sf_get_parent_ino(sfp);
+	trace_xrep_dir_salvaged_parent(rd->sc->ip, ino);
+
+	sfep = xfs_dir2_sf_firstentry(sfp);
+	while ((unsigned char *)sfep < end) {
+		if (xchk_should_terminate(rd->sc, &error))
+			return error;
+
+		next = xfs_dir2_sf_nextentry(rd->sc->mp, sfp, sfep);
+		if ((unsigned char *)next > end)
+			break;
+
+		/* Ok, let's save this entry. */
+		error = xrep_dir_salvage_sf_entry(rd, sfp, sfep);
+		if (error)
+			return error;
+
+		sfep = next;
+	}
+
+	return 0;
+}
+
+/*
+ * Try to figure out the format of this directory from the data fork mappings
+ * and the directory size.  If we can be reasonably sure of format, we can be
+ * more aggressive in salvaging directory entries.  On return, @magic_guess
+ * will be set to DIR3_BLOCK_MAGIC if we think this is a "block format"
+ * directory; DIR3_DATA_MAGIC if we think this is a "data format" directory,
+ * and 0 if we can't tell.
+ */
+STATIC void
+xrep_dir_guess_format(
+	struct xrep_dir		*rd,
+	__be32			*magic_guess)
+{
+	struct xfs_inode	*dp = rd->sc->ip;
+	struct xfs_mount	*mp = rd->sc->mp;
+	struct xfs_da_geometry	*geo = mp->m_dir_geo;
+	xfs_fileoff_t		last;
+	int			error;
+
+	ASSERT(xfs_has_crc(mp));
+
+	*magic_guess = 0;
+
+	/*
+	 * If there's a single directory block and the directory size is
+	 * exactly one block, this has to be a single block format directory.
+	 */
+	error = xfs_bmap_last_offset(dp, &last, XFS_DATA_FORK);
+	if (!error && XFS_FSB_TO_B(mp, last) == geo->blksize &&
+	    dp->i_disk_size == geo->blksize) {
+		*magic_guess = cpu_to_be32(XFS_DIR3_BLOCK_MAGIC);
+		return;
+	}
+
+	/*
+	 * If the last extent before the leaf offset matches the directory
+	 * size and the directory size is larger than 1 block, this is a
+	 * data format directory.
+	 */
+	last = geo->leafblk;
+	error = xfs_bmap_last_before(rd->sc->tp, dp, &last, XFS_DATA_FORK);
+	if (!error &&
+	    XFS_FSB_TO_B(mp, last) > geo->blksize &&
+	    XFS_FSB_TO_B(mp, last) == dp->i_disk_size) {
+		*magic_guess = cpu_to_be32(XFS_DIR3_DATA_MAGIC);
+		return;
+	}
+}
+
+/* Recover directory entries from a specific directory block. */
+STATIC int
+xrep_dir_recover_dirblock(
+	struct xrep_dir		*rd,
+	__be32			magic_guess,
+	xfs_dablk_t		dabno)
+{
+	struct xfs_dir2_data_hdr *hdr;
+	struct xfs_buf		*bp;
+	__be32			oldmagic;
+	int			error;
+
+	/*
+	 * Try to read buffer.  We invalidate them in the next step so we don't
+	 * bother to set a buffer type or ops.
+	 */
+	error = xfs_da_read_buf(rd->sc->tp, rd->sc->ip, dabno,
+			XFS_DABUF_MAP_HOLE_OK, &bp, XFS_DATA_FORK, NULL);
+	if (error || !bp)
+		return error;
+
+	hdr = bp->b_addr;
+	oldmagic = hdr->magic;
+
+	trace_xrep_dir_recover_dirblock(rd->sc->ip, dabno,
+			be32_to_cpu(hdr->magic), be32_to_cpu(magic_guess));
+
+	/*
+	 * If we're sure of the block's format, proceed with the salvage
+	 * operation using the specified magic number.
+	 */
+	if (magic_guess) {
+		hdr->magic = magic_guess;
+		goto recover;
+	}
+
+	/*
+	 * If we couldn't guess what type of directory this is, then we will
+	 * only salvage entries from directory blocks that match the magic
+	 * number and pass verifiers.
+	 */
+	switch (hdr->magic) {
+	case cpu_to_be32(XFS_DIR2_BLOCK_MAGIC):
+	case cpu_to_be32(XFS_DIR3_BLOCK_MAGIC):
+		if (!xrep_buf_verify_struct(bp, &xfs_dir3_block_buf_ops))
+			goto out;
+		if (xfs_dir3_block_header_check(bp, rd->sc->ip->i_ino) != NULL)
+			goto out;
+		break;
+	case cpu_to_be32(XFS_DIR2_DATA_MAGIC):
+	case cpu_to_be32(XFS_DIR3_DATA_MAGIC):
+		if (!xrep_buf_verify_struct(bp, &xfs_dir3_data_buf_ops))
+			goto out;
+		if (xfs_dir3_data_header_check(bp, rd->sc->ip->i_ino) != NULL)
+			goto out;
+		break;
+	default:
+		goto out;
+	}
+
+recover:
+	error = xrep_dir_recover_data(rd, bp);
+
+out:
+	hdr->magic = oldmagic;
+	xfs_trans_brelse(rd->sc->tp, bp);
+	return error;
+}
+
+static inline void
+xrep_dir_init_args(
+	struct xrep_dir		*rd,
+	struct xfs_inode	*dp,
+	const struct xfs_name	*name)
+{
+	memset(&rd->args, 0, sizeof(struct xfs_da_args));
+	rd->args.geo = rd->sc->mp->m_dir_geo;
+	rd->args.whichfork = XFS_DATA_FORK;
+	rd->args.owner = rd->sc->ip->i_ino;
+	rd->args.trans = rd->sc->tp;
+	rd->args.dp = dp;
+	if (!name)
+		return;
+	rd->args.name = name->name;
+	rd->args.namelen = name->len;
+	rd->args.filetype = name->type;
+	rd->args.hashval = xfs_dir2_hashname(rd->sc->mp, name);
+}
+
+/* Replay a stashed createname into the temporary directory. */
+STATIC int
+xrep_dir_replay_createname(
+	struct xrep_dir		*rd,
+	const struct xfs_name	*name,
+	xfs_ino_t		inum,
+	xfs_extlen_t		total)
+{
+	struct xfs_scrub	*sc = rd->sc;
+	struct xfs_inode	*dp = rd->sc->tempip;
+	bool			is_block, is_leaf;
+	int			error;
+
+	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
+
+	error = xfs_dir_ino_validate(sc->mp, inum);
+	if (error)
+		return error;
+
+	trace_xrep_dir_replay_createname(dp, name, inum);
+
+	xrep_dir_init_args(rd, dp, name);
+	rd->args.inumber = inum;
+	rd->args.total = total;
+	rd->args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
+
+	if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL)
+		return xfs_dir2_sf_addname(&rd->args);
+
+	error = xfs_dir2_isblock(&rd->args, &is_block);
+	if (error)
+		return error;
+	if (is_block)
+		return xfs_dir2_block_addname(&rd->args);
+
+	error = xfs_dir2_isleaf(&rd->args, &is_leaf);
+	if (error)
+		return error;
+	if (is_leaf)
+		return xfs_dir2_leaf_addname(&rd->args);
+
+	return xfs_dir2_node_addname(&rd->args);
+}
+
+/*
+ * Add this stashed incore directory entry to the temporary directory.
+ * The caller must hold the tempdir's IOLOCK, must not hold any ILOCKs, and
+ * must not be in transaction context.
+ */
+STATIC int
+xrep_dir_replay_update(
+	struct xrep_dir			*rd,
+	const struct xrep_dirent	*dirent)
+{
+	struct xfs_name			name = {
+		.len			= dirent->namelen,
+		.type			= dirent->ftype,
+		.name			= rd->namebuf,
+	};
+	struct xfs_mount		*mp = rd->sc->mp;
+#ifdef DEBUG
+	xfs_ino_t			ino;
+#endif
+	uint				resblks;
+	int				error;
+
+	resblks = XFS_LINK_SPACE_RES(mp, dirent->namelen);
+	error = xchk_trans_alloc(rd->sc, resblks);
+	if (error)
+		return error;
+
+	/* Lock the temporary directory and join it to the transaction */
+	xrep_tempfile_ilock(rd->sc);
+	xfs_trans_ijoin(rd->sc->tp, rd->sc->tempip, 0);
+
+	/*
+	 * Create a replacement dirent in the temporary directory.  Note that
+	 * _createname doesn't check for existing entries.  There shouldn't be
+	 * any in the temporary dir, but we'll verify this in debug mode.
+	 */
+#ifdef DEBUG
+	error = xchk_dir_lookup(rd->sc, rd->sc->tempip, &name, &ino);
+	if (error != -ENOENT) {
+		ASSERT(error != -ENOENT);
+		goto out_cancel;
+	}
+#endif
+
+	error = xrep_dir_replay_createname(rd, &name, dirent->ino, resblks);
+	if (error)
+		goto out_cancel;
+
+	if (name.type == XFS_DIR3_FT_DIR)
+		rd->subdirs++;
+	rd->dirents++;
+
+	/* Commit and unlock. */
+	error = xrep_trans_commit(rd->sc);
+	if (error)
+		return error;
+
+	xrep_tempfile_iunlock(rd->sc);
+	return 0;
+out_cancel:
+	xchk_trans_cancel(rd->sc);
+	xrep_tempfile_iunlock(rd->sc);
+	return error;
+}
+
+/*
+ * Flush stashed incore dirent updates that have been recorded by the scanner.
+ * This is done to reduce the memory requirements of the directory rebuild,
+ * since directories can contain up to 32GB of directory data.
+ *
+ * Caller must not hold transactions or ILOCKs.  Caller must hold the tempdir
+ * IOLOCK.
+ */
+STATIC int
+xrep_dir_replay_updates(
+	struct xrep_dir		*rd)
+{
+	xfarray_idx_t		array_cur;
+	int			error;
+
+	/* Add all the salvaged dirents to the temporary directory. */
+	foreach_xfarray_idx(rd->dir_entries, array_cur) {
+		struct xrep_dirent	dirent;
+
+		error = xfarray_load(rd->dir_entries, array_cur, &dirent);
+		if (error)
+			return error;
+
+		/* The dirent name is stored in the in-core buffer. */
+		error = xfblob_load(rd->dir_names, dirent.name_cookie,
+				rd->namebuf, dirent.namelen);
+		if (error)
+			return error;
+		rd->namebuf[MAXNAMELEN - 1] = 0;
+
+		error = xrep_dir_replay_update(rd, &dirent);
+		if (error)
+			return error;
+	}
+
+	/* Empty out both arrays now that we've added the entries. */
+	xfarray_truncate(rd->dir_entries);
+	xfblob_truncate(rd->dir_names);
+	return 0;
+}
+
+/*
+ * Periodically flush stashed directory entries to the temporary dir.  This
+ * is done to reduce the memory requirements of the directory rebuild, since
+ * directories can contain up to 32GB of directory data.
+ */
+STATIC int
+xrep_dir_flush_stashed(
+	struct xrep_dir		*rd)
+{
+	int			error;
+
+	/*
+	 * Entering this function, the scrub context has a reference to the
+	 * inode being repaired, the temporary file, and a scrub transaction
+	 * that we use during dirent salvaging to avoid livelocking if there
+	 * are cycles in the directory structures.  We hold ILOCK_EXCL on both
+	 * the inode being repaired and the temporary file, though they are
+	 * not ijoined to the scrub transaction.
+	 *
+	 * To constrain kernel memory use, we occasionally write salvaged
+	 * dirents from the xfarray and xfblob structures into the temporary
+	 * directory in preparation for swapping the directory structures at
+	 * the end.  Updating the temporary file requires a transaction, so we
+	 * commit the scrub transaction and drop the two ILOCKs so that
+	 * we can allocate whatever transaction we want.
+	 *
+	 * We still hold IOLOCK_EXCL on the inode being repaired, which
+	 * prevents anyone from accessing the damaged directory data while we
+	 * repair it.
+	 */
+	error = xrep_trans_commit(rd->sc);
+	if (error)
+		return error;
+	xchk_iunlock(rd->sc, XFS_ILOCK_EXCL);
+
+	/*
+	 * Take the IOLOCK of the temporary file while we modify dirents.  This
+	 * isn't strictly required because the temporary file is never revealed
+	 * to userspace, but we follow the same locking rules.  We still hold
+	 * sc->ip's IOLOCK.
+	 */
+	error = xrep_tempfile_iolock_polled(rd->sc);
+	if (error)
+		return error;
+
+	/* Write to the tempdir all the updates that we've stashed. */
+	error = xrep_dir_replay_updates(rd);
+	xrep_tempfile_iounlock(rd->sc);
+	if (error)
+		return error;
+
+	/*
+	 * Recreate the salvage transaction and relock the dir we're salvaging.
+	 */
+	error = xchk_trans_alloc(rd->sc, 0);
+	if (error)
+		return error;
+	xchk_ilock(rd->sc, XFS_ILOCK_EXCL);
+	return 0;
+}
+
+/* Decide if we've stashed too much dirent data in memory. */
+static inline bool
+xrep_dir_want_flush_stashed(
+	struct xrep_dir		*rd)
+{
+	unsigned long long	bytes;
+
+	bytes = xfarray_bytes(rd->dir_entries) + xfblob_bytes(rd->dir_names);
+	return bytes > XREP_DIR_MAX_STASH_BYTES;
+}
+
+/* Extract as many directory entries as we can. */
+STATIC int
+xrep_dir_recover(
+	struct xrep_dir		*rd)
+{
+	struct xfs_bmbt_irec	got;
+	struct xfs_scrub	*sc = rd->sc;
+	struct xfs_da_geometry	*geo = sc->mp->m_dir_geo;
+	xfs_fileoff_t		offset;
+	xfs_dablk_t		dabno;
+	__be32			magic_guess;
+	int			nmap;
+	int			error;
+
+	xrep_dir_guess_format(rd, &magic_guess);
+
+	/* Iterate each directory data block in the data fork. */
+	for (offset = 0;
+	     offset < geo->leafblk;
+	     offset = got.br_startoff + got.br_blockcount) {
+		nmap = 1;
+		error = xfs_bmapi_read(sc->ip, offset, geo->leafblk - offset,
+				&got, &nmap, 0);
+		if (error)
+			return error;
+		if (nmap != 1)
+			return -EFSCORRUPTED;
+		if (!xfs_bmap_is_written_extent(&got))
+			continue;
+
+		for (dabno = round_up(got.br_startoff, geo->fsbcount);
+		     dabno < got.br_startoff + got.br_blockcount;
+		     dabno += geo->fsbcount) {
+			if (xchk_should_terminate(rd->sc, &error))
+				return error;
+
+			error = xrep_dir_recover_dirblock(rd,
+					magic_guess, dabno);
+			if (error)
+				return error;
+
+			/* Flush dirents to constrain memory usage. */
+			if (xrep_dir_want_flush_stashed(rd)) {
+				error = xrep_dir_flush_stashed(rd);
+				if (error)
+					return error;
+			}
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Find all the directory entries for this inode by scraping them out of the
+ * directory leaf blocks by hand, and flushing them into the temp dir.
+ */
+STATIC int
+xrep_dir_find_entries(
+	struct xrep_dir		*rd)
+{
+	struct xfs_inode	*dp = rd->sc->ip;
+	int			error;
+
+	/*
+	 * Salvage directory entries from the old directory, and write them to
+	 * the temporary directory.
+	 */
+	if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL) {
+		error = xrep_dir_recover_sf(rd);
+	} else {
+		error = xfs_iread_extents(rd->sc->tp, dp, XFS_DATA_FORK);
+		if (error)
+			return error;
+
+		error = xrep_dir_recover(rd);
+	}
+	if (error)
+		return error;
+
+	return xrep_dir_flush_stashed(rd);
+}
+
+/* Scan all files in the filesystem for dirents. */
+STATIC int
+xrep_dir_salvage_entries(
+	struct xrep_dir		*rd)
+{
+	struct xfs_scrub	*sc = rd->sc;
+	int			error;
+
+	/*
+	 * Drop the ILOCK on this directory so that we can scan for this
+	 * directory's parent.  Figure out who is going to be the parent of
+	 * this directory, then retake the ILOCK so that we can salvage
+	 * directory entries.
+	 */
+	xchk_iunlock(sc, XFS_ILOCK_EXCL);
+	error = xrep_dir_find_parent(rd);
+	xchk_ilock(sc, XFS_ILOCK_EXCL);
+	if (error)
+		return error;
+
+	/*
+	 * Collect directory entries by parsing raw leaf blocks to salvage
+	 * whatever we can.  When we're done, free the staging memory before
+	 * swapping the directories to reduce memory usage.
+	 */
+	error = xrep_dir_find_entries(rd);
+	if (error)
+		return error;
+
+	/*
+	 * Cancel the repair transaction and drop the ILOCK so that we can
+	 * (later) use the atomic extent swap helper functions to compute the
+	 * correct block reservations and re-lock the inodes.
+	 *
+	 * We still hold IOLOCK_EXCL (aka i_rwsem) which will prevent directory
+	 * modifications, but there's nothing to prevent userspace from reading
+	 * the directory until we're ready for the swap operation.  Reads will
+	 * return -EIO without shutting down the fs, so we're ok with that.
+	 */
+	error = xrep_trans_commit(sc);
+	if (error)
+		return error;
+
+	xchk_iunlock(sc, XFS_ILOCK_EXCL);
+	return 0;
+}
+
+
+/*
+ * Free all the directory blocks and reset the data fork.  The caller must
+ * join the inode to the transaction.  This function returns with the inode
+ * joined to a clean scrub transaction.
+ */
+STATIC int
+xrep_dir_reset_fork(
+	struct xrep_dir		*rd,
+	xfs_ino_t		parent_ino)
+{
+	struct xfs_scrub	*sc = rd->sc;
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(sc->tempip, XFS_DATA_FORK);
+	int			error;
+
+	/* Unmap all the directory buffers. */
+	if (xfs_ifork_has_extents(ifp)) {
+		error = xrep_reap_ifork(sc, sc->tempip, XFS_DATA_FORK);
+		if (error)
+			return error;
+	}
+
+	trace_xrep_dir_reset_fork(sc->tempip, parent_ino);
+
+	/* Reset the data fork to an empty data fork. */
+	xfs_idestroy_fork(ifp);
+	ifp->if_bytes = 0;
+	sc->tempip->i_disk_size = 0;
+
+	/* Reinitialize the short form directory. */
+	xrep_dir_init_args(rd, sc->tempip, NULL);
+	return xfs_dir2_sf_create(&rd->args, parent_ino);
+}
+
+/*
+ * Prepare both inodes' directory forks for extent swapping.  Promote the
+ * tempfile from short format to leaf format, and if the file being repaired
+ * has a short format data fork, turn it into an empty extent list.
+ */
+STATIC int
+xrep_dir_swap_prep(
+	struct xfs_scrub	*sc,
+	bool			temp_local,
+	bool			ip_local)
+{
+	int			error;
+
+	/*
+	 * If the tempfile's directory is in shortform format, convert that
+	 * to a single leaf extent so that we can use the atomic extent swap.
+	 */
+	if (temp_local) {
+		struct xfs_da_args	args = {
+			.dp		= sc->tempip,
+			.geo		= sc->mp->m_dir_geo,
+			.whichfork	= XFS_DATA_FORK,
+			.trans		= sc->tp,
+			.total		= 1,
+			.owner		= sc->ip->i_ino,
+		};
+
+		error = xfs_dir2_sf_to_block(&args);
+		if (error)
+			return error;
+
+		/*
+		 * Roll the deferred log items to get us back to a clean
+		 * transaction.
+		 */
+		error = xfs_defer_finish(&sc->tp);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * If the file being repaired had a shortform data fork, convert that
+	 * to an empty extent list in preparation for the atomic extent swap.
+	 */
+	if (ip_local) {
+		struct xfs_ifork	*ifp;
+
+		ifp = xfs_ifork_ptr(sc->ip, XFS_DATA_FORK);
+		xfs_idestroy_fork(ifp);
+		ifp->if_format = XFS_DINODE_FMT_EXTENTS;
+		ifp->if_nextents = 0;
+		ifp->if_bytes = 0;
+		ifp->if_u1.if_root = NULL;
+		ifp->if_height = 0;
+
+		xfs_trans_log_inode(sc->tp, sc->ip,
+				XFS_ILOG_CORE | XFS_ILOG_DDATA);
+	}
+
+	return 0;
+}
+
+/*
+ * Replace the inode number of a directory entry.
+ */
+static int
+xrep_dir_replace(
+	struct xrep_dir		*rd,
+	struct xfs_inode	*dp,
+	const struct xfs_name	*name,
+	xfs_ino_t		inum,
+	xfs_extlen_t		total)
+{
+	struct xfs_scrub	*sc = rd->sc;
+	bool			is_block, is_leaf;
+	int			error;
+
+	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
+
+	error = xfs_dir_ino_validate(sc->mp, inum);
+	if (error)
+		return error;
+
+	xrep_dir_init_args(rd, dp, name);
+	rd->args.inumber = inum;
+	rd->args.total = total;
+
+	if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL)
+		return xfs_dir2_sf_replace(&rd->args);
+
+	error = xfs_dir2_isblock(&rd->args, &is_block);
+	if (error)
+		return error;
+	if (is_block)
+		return xfs_dir2_block_replace(&rd->args);
+
+	error = xfs_dir2_isleaf(&rd->args, &is_leaf);
+	if (error)
+		return error;
+	if (is_leaf)
+		return xfs_dir2_leaf_replace(&rd->args);
+
+	return xfs_dir2_node_replace(&rd->args);
+}
+
+/*
+ * Reset the link count of this directory and adjust the unlinked list pointers
+ * as needed.
+ */
+STATIC int
+xrep_dir_set_nlink(
+	struct xrep_dir		*rd)
+{
+	struct xfs_scrub	*sc = rd->sc;
+	struct xfs_inode	*dp = sc->ip;
+	struct xfs_perag	*pag;
+	unsigned int		new_nlink = rd->subdirs + 2;
+	int			error;
+
+	/*
+	 * 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.
+	 */
+	if (!xfs_inode_on_unlinked_list(dp))
+		goto reset_nlink;
+
+	/*
+	 * The directory is on the unlinked list and we did not find any
+	 * dirents.  Set the link count to zero and let the directory
+	 * inactivate when the last reference drops.
+	 */
+	if (rd->dirents == 0) {
+		new_nlink = 0;
+		goto reset_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.
+	 */
+	pag = xfs_perag_get(sc->mp, XFS_INO_TO_AGNO(sc->mp, dp->i_ino));
+	if (!pag) {
+		ASSERT(0);
+		return -EFSCORRUPTED;
+	}
+
+	error = xfs_iunlink_remove(sc->tp, pag, dp);
+	xfs_perag_put(pag);
+	if (error)
+		return error;
+
+reset_nlink:
+	if (VFS_I(dp)->i_nlink != new_nlink)
+		set_nlink(VFS_I(dp), new_nlink);
+	return 0;
+}
+
+/* Swap the temporary directory's data fork with the one being repaired. */
+STATIC int
+xrep_dir_swap(
+	struct xrep_dir		*rd)
+{
+	struct xfs_scrub	*sc = rd->sc;
+	bool			ip_local, temp_local;
+	int			error = 0;
+
+	/*
+	 * If we found enough subdirs to overflow this directory's link count,
+	 * bail out to userspace before we modify anything.
+	 */
+	if (rd->subdirs + 2 > XFS_MAXLINK)
+		return -EFSCORRUPTED;
+
+	/*
+	 * Reset the temporary directory's '..' entry to point to the parent
+	 * that we found.  The temporary directory was created with the root
+	 * directory as the parent, so we can skip this if repairing a
+	 * subdirectory of the root.
+	 *
+	 * It's also possible that this replacement could also expand a sf
+	 * tempdir into block format.
+	 */
+	if (rd->parent_ino != sc->mp->m_rootip->i_ino) {
+		error = xrep_dir_replace(rd, rd->sc->tempip, &xfs_name_dotdot,
+				rd->parent_ino, rd->tx.req.resblks);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * Changing the dot and dotdot entries could have changed the shape of
+	 * the directory, so we recompute these.
+	 */
+	ip_local = sc->ip->i_df.if_format == XFS_DINODE_FMT_LOCAL;
+	temp_local = sc->tempip->i_df.if_format == XFS_DINODE_FMT_LOCAL;
+
+	/*
+	 * If the both files have a local format data fork and the rebuilt
+	 * directory data would fit in the repaired file's data fork, copy
+	 * the contents from the tempfile and update the directory link count.
+	 * We're done now.
+	 */
+	if (ip_local && temp_local &&
+	    sc->tempip->i_disk_size <= xfs_inode_data_fork_size(sc->ip)) {
+		xrep_tempfile_copyout_local(sc, XFS_DATA_FORK);
+		return xrep_dir_set_nlink(rd);
+	}
+
+	/* Clean the transaction before we start working on the extent swap. */
+	error = xrep_tempfile_roll_trans(rd->sc);
+	if (error)
+		return error;
+
+	/* Otherwise, make sure both data forks are in block-mapping mode. */
+	error = xrep_dir_swap_prep(sc, temp_local, ip_local);
+	if (error)
+		return error;
+
+	/*
+	 * Set nlink of the directory in the same transaction sequence that
+	 * (atomically) commits the new directory data.
+	 */
+	error = xrep_dir_set_nlink(rd);
+	if (error)
+		return error;
+
+	return xrep_tempswap_contents(sc, &rd->tx);
+}
+
+/*
+ * Swap the new directory contents (which we created in the tempfile) into the
+ * directory being repaired.
+ */
+STATIC int
+xrep_dir_rebuild_tree(
+	struct xrep_dir		*rd)
+{
+	struct xfs_scrub	*sc = rd->sc;
+	int			error;
+
+	trace_xrep_dir_rebuild_tree(sc->ip, rd->parent_ino);
+
+	/*
+	 * Take the IOLOCK on the temporary file so that we can run dir
+	 * operations with the same locks held as we would for a normal file.
+	 * We still hold sc->ip's IOLOCK.
+	 */
+	error = xrep_tempfile_iolock_polled(rd->sc);
+	if (error)
+		return error;
+
+	/* Allocate transaction and ILOCK the scrub file and the temp file. */
+	error = xrep_tempswap_trans_alloc(sc, XFS_DATA_FORK, &rd->tx);
+	if (error)
+		return error;
+
+	/*
+	 * Swap the tempdir's data fork with the file being repaired.  This
+	 * recreates the transaction and re-takes the ILOCK in the scrub
+	 * context.
+	 */
+	error = xrep_dir_swap(rd);
+	if (error)
+		return error;
+
+	/*
+	 * Release the old directory blocks and reset the data fork of the temp
+	 * directory to an empty shortform directory because inactivation does
+	 * nothing for directories.
+	 */
+	error = xrep_dir_reset_fork(rd, sc->mp->m_rootip->i_ino);
+	if (error)
+		return error;
+
+	/*
+	 * Roll to get a transaction without any inodes joined to it.  Then we
+	 * can drop the tempfile's ILOCK and IOLOCK before doing more work on
+	 * the scrub target directory.
+	 */
+	error = xfs_trans_roll(&sc->tp);
+	if (error)
+		return error;
+
+	xrep_tempfile_iunlock(sc);
+	xrep_tempfile_iounlock(sc);
+	return 0;
+}
+
+/* Set up the filesystem scan so we can regenerate directory entries. */
+STATIC int
+xrep_dir_setup_scan(
+	struct xrep_dir		*rd)
+{
+	struct xfs_scrub	*sc = rd->sc;
+	char			*descr;
+	int			error;
+
+	rd->parent_ino = NULLFSINO;
+
+	/* Set up some staging memory for salvaging dirents. */
+	descr = xchk_xfile_ino_descr(sc, "directory entries");
+	error = xfarray_create(descr, 0, sizeof(struct xrep_dirent),
+			&rd->dir_entries);
+	kfree(descr);
+	if (error)
+		return error;
+
+	descr = xchk_xfile_ino_descr(sc, "directory entry names");
+	error = xfblob_create(descr, &rd->dir_names);
+	kfree(descr);
+	if (error)
+		goto out_xfarray;
+
+	return 0;
+
+out_xfarray:
+	xfarray_destroy(rd->dir_entries);
+	rd->dir_entries = NULL;
+	return error;
+}
+
+/*
+ * Repair the directory metadata.
+ *
+ * XXX: Directory entry buffers can be multiple fsblocks in size.  The buffer
+ * cache in XFS can't handle aliased multiblock buffers, so this might
+ * misbehave if the directory blocks are crosslinked with other filesystem
+ * metadata.
+ *
+ * XXX: Is it necessary to check the dcache for this directory to make sure
+ * that we always recreate every cached entry?
+ */
+int
+xrep_directory(
+	struct xfs_scrub	*sc)
+{
+	struct xrep_dir		*rd = sc->buf;
+	int			error;
+
+	/* The rmapbt is required to reap the old data fork. */
+	if (!xfs_has_rmapbt(sc->mp))
+		return -EOPNOTSUPP;
+
+	error = xrep_dir_setup_scan(rd);
+	if (error)
+		return error;
+
+	error = xrep_dir_salvage_entries(rd);
+	if (error)
+		goto out_teardown;
+
+	/* Last chance to abort before we start committing fixes. */
+	if (xchk_should_terminate(sc, &error))
+		goto out_teardown;
+
+	error = xrep_dir_rebuild_tree(rd);
+	if (error)
+		goto out_teardown;
+
+out_teardown:
+	xrep_dir_teardown(sc);
+	return error;
+}
diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c
index 50bcc5a4c3df1..e46b1256b0851 100644
--- a/fs/xfs/scrub/inode_repair.c
+++ b/fs/xfs/scrub/inode_repair.c
@@ -46,6 +46,7 @@
 #include "scrub/repair.h"
 #include "scrub/iscan.h"
 #include "scrub/readdir.h"
+#include "scrub/tempfile.h"
 
 /*
  * Inode Record Repair
@@ -295,6 +296,10 @@ xrep_dinode_findmode_walk_directory(
 	unsigned int		lock_mode;
 	int			error = 0;
 
+	/* Ignore temporary repair directories. */
+	if (xrep_is_tempfile(dp))
+		return 0;
+
 	/*
 	 * Scan the directory to see if there it contains an entry pointing to
 	 * the directory that we are repairing.
diff --git a/fs/xfs/scrub/nlinks.c b/fs/xfs/scrub/nlinks.c
index 8eb0f96932866..a6d68d9eb3d7e 100644
--- a/fs/xfs/scrub/nlinks.c
+++ b/fs/xfs/scrub/nlinks.c
@@ -27,6 +27,7 @@
 #include "scrub/nlinks.h"
 #include "scrub/trace.h"
 #include "scrub/readdir.h"
+#include "scrub/tempfile.h"
 
 /*
  * Live Inode Link Count Checking
@@ -152,6 +153,13 @@ xchk_nlinks_live_update(
 
 	xnc = container_of(nb, struct xchk_nlink_ctrs, hooks.dirent_hook.nb);
 
+	/*
+	 * Ignore temporary directories being used to stage dir repairs, since
+	 * we don't bump the link counts of the children.
+	 */
+	if (xrep_is_tempfile(p->dp))
+		return NOTIFY_DONE;
+
 	trace_xchk_nlinks_live_update(xnc->sc->mp, p->dp, action, p->ip->i_ino,
 			p->delta, p->name->name, p->name->len);
 
@@ -303,6 +311,13 @@ xchk_nlinks_collect_dir(
 	unsigned int		lock_mode;
 	int			error = 0;
 
+	/*
+	 * Ignore temporary directories being used to stage dir repairs, since
+	 * we don't bump the link counts of the children.
+	 */
+	if (xrep_is_tempfile(dp))
+		return 0;
+
 	/* Prevent anyone from changing this directory while we walk it. */
 	xfs_ilock(dp, XFS_IOLOCK_SHARED);
 	lock_mode = xfs_ilock_data_map_shared(dp);
@@ -537,6 +552,14 @@ xchk_nlinks_compare_inode(
 	unsigned int		actual_nlink;
 	int			error;
 
+	/*
+	 * Ignore temporary files being used to stage repairs, since we assume
+	 * they're correct for non-directories, and the directory repair code
+	 * doesn't bump the link counts for the children.
+	 */
+	if (xrep_is_tempfile(ip))
+		return 0;
+
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
 	mutex_lock(&xnc->lock);
 
diff --git a/fs/xfs/scrub/nlinks_repair.c b/fs/xfs/scrub/nlinks_repair.c
index 58cacb8e94c1b..23eb08c4b5ad5 100644
--- a/fs/xfs/scrub/nlinks_repair.c
+++ b/fs/xfs/scrub/nlinks_repair.c
@@ -26,6 +26,7 @@
 #include "scrub/iscan.h"
 #include "scrub/nlinks.h"
 #include "scrub/trace.h"
+#include "scrub/tempfile.h"
 
 /*
  * Live Inode Link Count Repair
@@ -68,6 +69,14 @@ xrep_nlinks_repair_inode(
 	bool			dirty = false;
 	int			error;
 
+	/*
+	 * Ignore temporary files being used to stage repairs, since we assume
+	 * they're correct for non-directories, and the directory repair code
+	 * doesn't bump the link counts for the children.
+	 */
+	if (xrep_is_tempfile(ip))
+		return 0;
+
 	xchk_ilock(sc, XFS_IOLOCK_EXCL);
 
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_link, 0, 0, 0, &sc->tp);
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index 5da10ed1fe8ce..050a8e8914f6e 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -17,6 +17,7 @@
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/readdir.h"
+#include "scrub/tempfile.h"
 
 /* Set us up to scrub parents. */
 int
@@ -143,7 +144,8 @@ xchk_parent_validate(
 	}
 	if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
 		return error;
-	if (dp == sc->ip || dp == sc->tempip || !S_ISDIR(VFS_I(dp)->i_mode)) {
+	if (dp == sc->ip || xrep_is_tempfile(dp) ||
+	    !S_ISDIR(VFS_I(dp)->i_mode)) {
 		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out_rele;
 	}
diff --git a/fs/xfs/scrub/readdir.c b/fs/xfs/scrub/readdir.c
index d58a15c63a2dc..d70dbbd4c9040 100644
--- a/fs/xfs/scrub/readdir.c
+++ b/fs/xfs/scrub/readdir.c
@@ -335,6 +335,13 @@ xchk_dir_lookup(
 	if (xfs_is_shutdown(dp->i_mount))
 		return -EIO;
 
+	/*
+	 * A temporary directory's block headers are written with the owner
+	 * set to sc->ip, so we must switch the owner here for the lookup.
+	 */
+	if (dp == sc->tempip)
+		args.owner = sc->ip->i_ino;
+
 	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
 	ASSERT(xfs_isilocked(dp, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
 
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 83b7aa48dec19..ef17a08320782 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -35,6 +35,7 @@
 #include "xfs_da_format.h"
 #include "xfs_da_btree.h"
 #include "xfs_attr.h"
+#include "xfs_dir2.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 2bc5dd18d46f4..8fc582b286c0a 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -91,6 +91,7 @@ int xrep_metadata_inode_forks(struct xfs_scrub *sc);
 int xrep_setup_ag_rmapbt(struct xfs_scrub *sc);
 int xrep_setup_ag_refcountbt(struct xfs_scrub *sc);
 int xrep_setup_xattr(struct xfs_scrub *sc);
+int xrep_setup_directory(struct xfs_scrub *sc);
 
 /* Repair setup functions */
 int xrep_setup_ag_allocbt(struct xfs_scrub *sc);
@@ -125,6 +126,7 @@ int xrep_bmap_cow(struct xfs_scrub *sc);
 int xrep_nlinks(struct xfs_scrub *sc);
 int xrep_fscounters(struct xfs_scrub *sc);
 int xrep_xattr(struct xfs_scrub *sc);
+int xrep_directory(struct xfs_scrub *sc);
 
 #ifdef CONFIG_XFS_RT
 int xrep_rtbitmap(struct xfs_scrub *sc);
@@ -195,6 +197,7 @@ xrep_setup_nothing(
 #define xrep_setup_ag_rmapbt		xrep_setup_nothing
 #define xrep_setup_ag_refcountbt	xrep_setup_nothing
 #define xrep_setup_xattr		xrep_setup_nothing
+#define xrep_setup_directory		xrep_setup_nothing
 
 #define xrep_setup_inode(sc, imap)	((void)0)
 
@@ -221,6 +224,7 @@ xrep_setup_nothing(
 #define xrep_fscounters			xrep_notsupported
 #define xrep_rtsummary			xrep_notsupported
 #define xrep_xattr			xrep_notsupported
+#define xrep_directory			xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 0b8fdd62055fe..bda7a0c91e241 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -328,7 +328,7 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.type	= ST_INODE,
 		.setup	= xchk_setup_directory,
 		.scrub	= xchk_directory,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_directory,
 	},
 	[XFS_SCRUB_TYPE_XATTR] = {	/* extended attributes */
 		.type	= ST_INODE,
diff --git a/fs/xfs/scrub/tempfile.c b/fs/xfs/scrub/tempfile.c
index f1726822e18f7..49361e03ad8a4 100644
--- a/fs/xfs/scrub/tempfile.c
+++ b/fs/xfs/scrub/tempfile.c
@@ -853,3 +853,16 @@ xrep_tempfile_copyout_local(
 	ilog_flags |= xfs_ilog_fdata(whichfork);
 	xfs_trans_log_inode(sc->tp, sc->ip, ilog_flags);
 }
+
+/* Decide if a given XFS inode is a temporary file for a repair. */
+bool
+xrep_is_tempfile(
+	const struct xfs_inode	*ip)
+{
+	const struct inode	*inode = &ip->i_vnode;
+
+	if (IS_PRIVATE(inode) && !(inode->i_opflags & IOP_XATTR))
+		return true;
+
+	return false;
+}
diff --git a/fs/xfs/scrub/tempfile.h b/fs/xfs/scrub/tempfile.h
index d57e4f145a7c8..e51399f595fe9 100644
--- a/fs/xfs/scrub/tempfile.h
+++ b/fs/xfs/scrub/tempfile.h
@@ -35,11 +35,13 @@ int xrep_tempfile_set_isize(struct xfs_scrub *sc, unsigned long long isize);
 
 int xrep_tempfile_roll_trans(struct xfs_scrub *sc);
 void xrep_tempfile_copyout_local(struct xfs_scrub *sc, int whichfork);
+bool xrep_is_tempfile(const struct xfs_inode *ip);
 #else
 static inline void xrep_tempfile_iolock_both(struct xfs_scrub *sc)
 {
 	xchk_ilock(sc, XFS_IOLOCK_EXCL);
 }
+# define xrep_is_tempfile(ip)		(false)
 # define xrep_tempfile_rele(sc)
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 87a68aee16bf5..f8b7f0fc38051 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -2581,6 +2581,118 @@ DEFINE_EVENT(xrep_xattr_class, name, \
 DEFINE_XREP_XATTR_EVENT(xrep_xattr_rebuild_tree);
 DEFINE_XREP_XATTR_EVENT(xrep_xattr_reset_fork);
 
+TRACE_EVENT(xrep_dir_recover_dirblock,
+	TP_PROTO(struct xfs_inode *dp, xfs_dablk_t dabno, uint32_t magic,
+		 uint32_t magic_guess),
+	TP_ARGS(dp, dabno, magic, magic_guess),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, dir_ino)
+		__field(xfs_dablk_t, dabno)
+		__field(uint32_t, magic)
+		__field(uint32_t, magic_guess)
+	),
+	TP_fast_assign(
+		__entry->dev = dp->i_mount->m_super->s_dev;
+		__entry->dir_ino = dp->i_ino;
+		__entry->dabno = dabno;
+		__entry->magic = magic;
+		__entry->magic_guess = magic_guess;
+	),
+	TP_printk("dev %d:%d dir 0x%llx dablk 0x%x magic 0x%x magic_guess 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->dir_ino,
+		  __entry->dabno,
+		  __entry->magic,
+		  __entry->magic_guess)
+);
+
+DECLARE_EVENT_CLASS(xrep_dir_class,
+	TP_PROTO(struct xfs_inode *dp, xfs_ino_t parent_ino),
+	TP_ARGS(dp, parent_ino),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, dir_ino)
+		__field(xfs_ino_t, parent_ino)
+	),
+	TP_fast_assign(
+		__entry->dev = dp->i_mount->m_super->s_dev;
+		__entry->dir_ino = dp->i_ino;
+		__entry->parent_ino = parent_ino;
+	),
+	TP_printk("dev %d:%d dir 0x%llx parent 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->dir_ino,
+		  __entry->parent_ino)
+)
+#define DEFINE_XREP_DIR_EVENT(name) \
+DEFINE_EVENT(xrep_dir_class, name, \
+	TP_PROTO(struct xfs_inode *dp, xfs_ino_t parent_ino), \
+	TP_ARGS(dp, parent_ino))
+DEFINE_XREP_DIR_EVENT(xrep_dir_rebuild_tree);
+DEFINE_XREP_DIR_EVENT(xrep_dir_reset_fork);
+
+DECLARE_EVENT_CLASS(xrep_dirent_class,
+	TP_PROTO(struct xfs_inode *dp, const struct xfs_name *name,
+		 xfs_ino_t ino),
+	TP_ARGS(dp, name, ino),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, dir_ino)
+		__field(unsigned int, namelen)
+		__dynamic_array(char, name, name->len)
+		__field(xfs_ino_t, ino)
+		__field(uint8_t, ftype)
+	),
+	TP_fast_assign(
+		__entry->dev = dp->i_mount->m_super->s_dev;
+		__entry->dir_ino = dp->i_ino;
+		__entry->namelen = name->len;
+		memcpy(__get_str(name), name->name, name->len);
+		__entry->ino = ino;
+		__entry->ftype = name->type;
+	),
+	TP_printk("dev %d:%d dir 0x%llx ftype %s name '%.*s' ino 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->dir_ino,
+		  __print_symbolic(__entry->ftype, XFS_DIR3_FTYPE_STR),
+		  __entry->namelen,
+		  __get_str(name),
+		  __entry->ino)
+)
+#define DEFINE_XREP_DIRENT_EVENT(name) \
+DEFINE_EVENT(xrep_dirent_class, name, \
+	TP_PROTO(struct xfs_inode *dp, const struct xfs_name *name, \
+		 xfs_ino_t ino), \
+	TP_ARGS(dp, name, ino))
+DEFINE_XREP_DIRENT_EVENT(xrep_dir_salvage_entry);
+DEFINE_XREP_DIRENT_EVENT(xrep_dir_stash_createname);
+DEFINE_XREP_DIRENT_EVENT(xrep_dir_replay_createname);
+
+DECLARE_EVENT_CLASS(xrep_parent_salvage_class,
+	TP_PROTO(struct xfs_inode *dp, xfs_ino_t ino),
+	TP_ARGS(dp, ino),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, dir_ino)
+		__field(xfs_ino_t, ino)
+	),
+	TP_fast_assign(
+		__entry->dev = dp->i_mount->m_super->s_dev;
+		__entry->dir_ino = dp->i_ino;
+		__entry->ino = ino;
+	),
+	TP_printk("dev %d:%d dir 0x%llx parent 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->dir_ino,
+		  __entry->ino)
+)
+#define DEFINE_XREP_PARENT_SALVAGE_EVENT(name) \
+DEFINE_EVENT(xrep_parent_salvage_class, name, \
+	TP_PROTO(struct xfs_inode *dp, xfs_ino_t ino), \
+	TP_ARGS(dp, ino))
+DEFINE_XREP_PARENT_SALVAGE_EVENT(xrep_dir_salvaged_parent);
+
 #endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
 
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 970daeb160b24..0d7dcb128f857 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -16,6 +16,7 @@
 #include "xfs_inode.h"
 #include "xfs_dir2.h"
 #include "xfs_attr.h"
+#include "xfs_bit.h"
 #include "xfs_trans_space.h"
 #include "xfs_trans.h"
 #include "xfs_buf_item.h"
@@ -1553,6 +1554,51 @@ xfs_release(
 	return error;
 }
 
+/*
+ * Mark all the buffers attached to this directory stale.  In theory we should
+ * never be freeing a directory with any blocks at all, but this covers the
+ * case where we've recovered a directory swap with a "temporary" directory
+ * created by online repair and now need to dump it.
+ */
+STATIC void
+xfs_inactive_dir(
+	struct xfs_inode	*dp)
+{
+	struct xfs_iext_cursor	icur;
+	struct xfs_bmbt_irec	got;
+	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_da_geometry	*geo = mp->m_dir_geo;
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(dp, XFS_DATA_FORK);
+	xfs_fileoff_t		off;
+
+	/*
+	 * Invalidate each directory block.  All directory blocks are of
+	 * fsbcount length and alignment, so we only need to walk those same
+	 * offsets.  We hold the only reference to this inode, so we must wait
+	 * for the buffer locks.
+	 */
+	for_each_xfs_iext(ifp, &icur, &got) {
+		for (off = round_up(got.br_startoff, geo->fsbcount);
+		     off < got.br_startoff + got.br_blockcount;
+		     off += geo->fsbcount) {
+			struct xfs_buf	*bp = NULL;
+			xfs_fsblock_t	fsbno;
+			int		error;
+
+			fsbno = (off - got.br_startoff) + got.br_startblock;
+			error = xfs_buf_incore(mp->m_ddev_targp,
+					XFS_FSB_TO_DADDR(mp, fsbno),
+					XFS_FSB_TO_BB(mp, geo->fsbcount),
+					XBF_LIVESCAN, &bp);
+			if (error)
+				continue;
+
+			xfs_buf_stale(bp);
+			xfs_buf_relse(bp);
+		}
+	}
+}
+
 /*
  * xfs_inactive_truncate
  *
@@ -1863,6 +1909,11 @@ xfs_inactive(
 			goto out;
 	}
 
+	if (S_ISDIR(VFS_I(ip)->i_mode) && ip->i_df.if_nextents > 0) {
+		xfs_inactive_dir(ip);
+		truncate = 1;
+	}
+
 	if (S_ISLNK(VFS_I(ip)->i_mode))
 		error = xfs_inactive_symlink(ip);
 	else if (truncate)

[PATCH 2/4] xfs: scan the filesystem to repair a directory dotdot entry

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Teach the online directory repair code to scan the filesystem so that we
can set the dotdot entry when we're rebuilding a directory.  This
involves dropping ILOCK on the directory that we're repairing, which
means that the VFS can sneak in and tell us to update dotdot at any
time.  Deal with these races by using a dirent hook to absorb dotdot
updates, and be careful not to check the scan results until after we've
retaken the ILOCK.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Makefile           |    1 
 fs/xfs/scrub/dir_repair.c |   70 +++++---
 fs/xfs/scrub/findparent.c |  412 +++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/findparent.h |   49 +++++
 fs/xfs/scrub/iscan.c      |   18 ++
 fs/xfs/scrub/iscan.h      |    1 
 fs/xfs/scrub/trace.h      |    1 
 7 files changed, 528 insertions(+), 24 deletions(-)
 create mode 100644 fs/xfs/scrub/findparent.c
 create mode 100644 fs/xfs/scrub/findparent.h


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index fd64a9043522c..46f88c72ffd6a 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -199,6 +199,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   bmap_repair.o \
 				   cow_repair.o \
 				   dir_repair.o \
+				   findparent.o \
 				   fscounters_repair.o \
 				   ialloc_repair.o \
 				   inode_repair.o \
diff --git a/fs/xfs/scrub/dir_repair.c b/fs/xfs/scrub/dir_repair.c
index 0b320212da230..297935416aed6 100644
--- a/fs/xfs/scrub/dir_repair.c
+++ b/fs/xfs/scrub/dir_repair.c
@@ -38,8 +38,10 @@
 #include "scrub/xfile.h"
 #include "scrub/xfarray.h"
 #include "scrub/xfblob.h"
+#include "scrub/iscan.h"
 #include "scrub/readdir.h"
 #include "scrub/reap.h"
+#include "scrub/findparent.h"
 
 /*
  * Directory Repair
@@ -108,10 +110,10 @@ struct xrep_dir {
 	struct xfs_da_args	args;
 
 	/*
-	 * This is the parent that we're going to set on the reconstructed
-	 * directory.
+	 * Information used to scan the filesystem to find the inumber of the
+	 * dotdot entry for this directory.
 	 */
-	xfs_ino_t		parent_ino;
+	struct xrep_parent_scan_info pscan;
 
 	/* How many subdirectories did we find? */
 	uint64_t		subdirs;
@@ -130,6 +132,7 @@ xrep_dir_teardown(
 {
 	struct xrep_dir		*rd = sc->buf;
 
+	xrep_findparent_scan_teardown(&rd->pscan);
 	xfblob_destroy(rd->dir_names);
 	xfarray_destroy(rd->dir_entries);
 }
@@ -142,6 +145,8 @@ xrep_setup_directory(
 	struct xrep_dir		*rd;
 	int			error;
 
+	xchk_fsgates_enable(sc, XCHK_FSGATES_DIRENTS);
+
 	error = xrep_tempfile_create(sc, S_IFDIR);
 	if (error)
 		return error;
@@ -177,8 +182,8 @@ xrep_dir_self_parent(
 }
 
 /*
- * Look up the dotdot entry.  Returns NULLFSINO if we don't know what to do.
- * The next patch will check this more carefully.
+ * Look up the dotdot entry and confirm that it's really the parent.
+ * Returns NULLFSINO if we don't know what to do.
  */
 static inline xfs_ino_t
 xrep_dir_lookup_parent(
@@ -194,37 +199,39 @@ xrep_dir_lookup_parent(
 	if (!xfs_verify_dir_ino(sc->mp, ino))
 		return NULLFSINO;
 
+	error = xrep_findparent_confirm(sc, &ino);
+	if (error)
+		return NULLFSINO;
+
 	return ino;
 }
 
-/*
- * Try to find the parent of the directory being repaired.
- *
- * NOTE: This function will someday be augmented by the directory parent repair
- * code, which will know how to check the parent and scan the filesystem if
- * we cannot find anything.  Inode scans will have to be done before we start
- * salvaging directory entries, so we do this now.
- */
+/* Try to find the parent of the directory being repaired. */
 STATIC int
 xrep_dir_find_parent(
 	struct xrep_dir		*rd)
 {
 	xfs_ino_t		ino;
 
-	ino = xrep_dir_self_parent(rd);
+	ino = xrep_findparent_self_reference(rd->sc);
 	if (ino != NULLFSINO) {
-		rd->parent_ino = ino;
+		xrep_findparent_scan_finish_early(&rd->pscan, ino);
 		return 0;
 	}
 
 	ino = xrep_dir_lookup_parent(rd);
 	if (ino != NULLFSINO) {
-		rd->parent_ino = ino;
+		xrep_findparent_scan_finish_early(&rd->pscan, ino);
 		return 0;
 	}
 
-	/* NOTE: A future patch will deal with moving orphans. */
-	return -EFSCORRUPTED;
+	/*
+	 * A full filesystem scan is the last resort.  On a busy filesystem,
+	 * the scan can fail with -EBUSY if we cannot grab IOLOCKs.  That means
+	 * that we don't know what who the parent is, so we should return to
+	 * userspace.
+	 */
+	return xrep_findparent_scan(&rd->pscan);
 }
 
 /*
@@ -932,6 +939,10 @@ xrep_dir_salvage_entries(
 	 * modifications, but there's nothing to prevent userspace from reading
 	 * the directory until we're ready for the swap operation.  Reads will
 	 * return -EIO without shutting down the fs, so we're ok with that.
+	 *
+	 * The VFS can change dotdot on us, but the findparent scan will keep
+	 * our incore parent inode up to date.  See the note on locking issues
+	 * for more details.
 	 */
 	error = xrep_trans_commit(sc);
 	if (error)
@@ -1154,6 +1165,14 @@ xrep_dir_swap(
 	if (rd->subdirs + 2 > XFS_MAXLINK)
 		return -EFSCORRUPTED;
 
+	/*
+	 * If we never found the parent for this directory, we can't fix this
+	 * directory.
+	 */
+	ASSERT(sc->ilock_flags & XFS_ILOCK_EXCL);
+	if (rd->pscan.parent_ino == NULLFSINO)
+		return -EFSCORRUPTED;
+
 	/*
 	 * Reset the temporary directory's '..' entry to point to the parent
 	 * that we found.  The temporary directory was created with the root
@@ -1163,9 +1182,9 @@ xrep_dir_swap(
 	 * It's also possible that this replacement could also expand a sf
 	 * tempdir into block format.
 	 */
-	if (rd->parent_ino != sc->mp->m_rootip->i_ino) {
+	if (rd->pscan.parent_ino != sc->mp->m_rootip->i_ino) {
 		error = xrep_dir_replace(rd, rd->sc->tempip, &xfs_name_dotdot,
-				rd->parent_ino, rd->tx.req.resblks);
+				rd->pscan.parent_ino, rd->tx.req.resblks);
 		if (error)
 			return error;
 	}
@@ -1221,7 +1240,7 @@ xrep_dir_rebuild_tree(
 	struct xfs_scrub	*sc = rd->sc;
 	int			error;
 
-	trace_xrep_dir_rebuild_tree(sc->ip, rd->parent_ino);
+	trace_xrep_dir_rebuild_tree(sc->ip, rd->pscan.parent_ino);
 
 	/*
 	 * Take the IOLOCK on the temporary file so that we can run dir
@@ -1278,8 +1297,6 @@ xrep_dir_setup_scan(
 	char			*descr;
 	int			error;
 
-	rd->parent_ino = NULLFSINO;
-
 	/* Set up some staging memory for salvaging dirents. */
 	descr = xchk_xfile_ino_descr(sc, "directory entries");
 	error = xfarray_create(descr, 0, sizeof(struct xrep_dirent),
@@ -1294,8 +1311,15 @@ xrep_dir_setup_scan(
 	if (error)
 		goto out_xfarray;
 
+	error = xrep_findparent_scan_start(sc, &rd->pscan);
+	if (error)
+		goto out_xfblob;
+
 	return 0;
 
+out_xfblob:
+	xfblob_destroy(rd->dir_names);
+	rd->dir_names = NULL;
 out_xfarray:
 	xfarray_destroy(rd->dir_entries);
 	rd->dir_entries = NULL;
diff --git a/fs/xfs/scrub/findparent.c b/fs/xfs/scrub/findparent.c
new file mode 100644
index 0000000000000..b8716e881e62e
--- /dev/null
+++ b/fs/xfs/scrub/findparent.c
@@ -0,0 +1,412 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2020-2024 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_defer.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_dir2.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_dir2_priv.h"
+#include "xfs_trans_space.h"
+#include "xfs_health.h"
+#include "xfs_swapext.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/iscan.h"
+#include "scrub/findparent.h"
+#include "scrub/readdir.h"
+#include "scrub/tempfile.h"
+
+/*
+ * Finding the Parent of a Directory
+ * =================================
+ *
+ * Directories have parent pointers, in the sense that each directory contains
+ * a dotdot entry that points to the single allowed parent.  The brute force
+ * way to find the parent of a given directory is to scan every directory in
+ * the filesystem looking for a child dirent that references this directory.
+ *
+ * This module wraps the process of scanning the directory tree.  It requires
+ * that @sc->ip is the directory whose parent we want to find, and that the
+ * caller hold only the IOLOCK on that directory.  The scan itself needs to
+ * take the ILOCK of each directory visited.
+ *
+ * Because we cannot hold @sc->ip's ILOCK during a scan of the whole fs, it is
+ * necessary to use dirent hooks to update the parent scan results.  Callers
+ * must not read the scan results without re-taking @sc->ip's ILOCK.
+ *
+ * There are a few shortcuts that we can take to avoid scanning the entire
+ * filesystem, such as noticing directory tree roots.
+ */
+
+struct xrep_findparent_info {
+	/* The directory currently being scanned. */
+	struct xfs_inode	*dp;
+
+	/*
+	 * Scrub context.  We're looking for a @dp containing a directory
+	 * entry pointing to sc->ip->i_ino.
+	 */
+	struct xfs_scrub	*sc;
+
+	/* Optional scan information for a xrep_findparent_scan call. */
+	struct xrep_parent_scan_info *parent_scan;
+
+	/*
+	 * Parent that we've found for sc->ip.  If we're scanning the entire
+	 * directory tree, we need this to ensure that we only find /one/
+	 * parent directory.
+	 */
+	xfs_ino_t		found_parent;
+
+	/*
+	 * This is set to true if @found_parent was not observed directly from
+	 * the directory scan but by noticing a change in dotdot entries after
+	 * cycling the sc->ip IOLOCK.
+	 */
+	bool			parent_tentative;
+};
+
+/*
+ * 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_findparent_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_findparent_info	*fpi = priv;
+	int				error = 0;
+
+	if (xchk_should_terminate(fpi->sc, &error))
+		return error;
+
+	if (ino != fpi->sc->ip->i_ino)
+		return 0;
+
+	/* Ignore garbage directory entry names. */
+	if (name->len == 0 || !xfs_dir2_namecheck(name->name, name->len))
+		return -EFSCORRUPTED;
+
+	/*
+	 * Ignore dotdot and dot entries -- we're looking for parent -> child
+	 * links only.
+	 */
+	if (name->name[0] == '.' && (name->len == 1 ||
+				     (name->len == 2 && name->name[1] == '.')))
+		return 0;
+
+	/* Uhoh, more than one parent for a dir? */
+	if (fpi->found_parent != NULLFSINO &&
+	    !(fpi->parent_tentative && fpi->found_parent == fpi->dp->i_ino)) {
+		trace_xrep_findparent_dirent(fpi->sc->ip, 0);
+		return -EFSCORRUPTED;
+	}
+
+	/* We found a potential parent; remember this. */
+	trace_xrep_findparent_dirent(fpi->sc->ip, fpi->dp->i_ino);
+	fpi->found_parent = fpi->dp->i_ino;
+	fpi->parent_tentative = false;
+
+	if (fpi->parent_scan)
+		xrep_findparent_scan_found(fpi->parent_scan, fpi->dp->i_ino);
+
+	return 0;
+}
+
+/*
+ * If this is a directory, walk the dirents looking for any that point to the
+ * scrub target inode.
+ */
+STATIC int
+xrep_findparent_walk_directory(
+	struct xrep_findparent_info	*fpi)
+{
+	struct xfs_scrub		*sc = fpi->sc;
+	struct xfs_inode		*dp = fpi->dp;
+	unsigned int			lock_mode;
+	int				error = 0;
+
+	/*
+	 * The inode being scanned cannot be its own parent, nor can any
+	 * temporary directory we created to stage this repair.
+	 */
+	if (dp == sc->ip || dp == sc->tempip)
+		return 0;
+
+	/*
+	 * Similarly, temporary files created to stage a repair cannot be the
+	 * parent of this inode.
+	 */
+	if (xrep_is_tempfile(dp))
+		return 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_findparent_dirent, fpi);
+	if (error)
+		goto out_unlock;
+
+out_unlock:
+	xfs_iunlock(dp, lock_mode);
+	return error;
+}
+
+/*
+ * Update this directory's dotdot pointer based on ongoing dirent updates.
+ */
+STATIC int
+xrep_findparent_live_update(
+	struct notifier_block		*nb,
+	unsigned long			action,
+	void				*data)
+{
+	struct xfs_dir_update_params	*p = data;
+	struct xrep_parent_scan_info	*pscan;
+	struct xfs_scrub		*sc;
+
+	pscan = container_of(nb, struct xrep_parent_scan_info,
+			hooks.dirent_hook.nb);
+	sc = pscan->sc;
+
+	/*
+	 * If @p->ip is the subdirectory that we're interested in and we've
+	 * already scanned @p->dp, update the dotdot target inumber to the
+	 * parent inode.
+	 */
+	if (p->ip->i_ino == sc->ip->i_ino &&
+	    xchk_iscan_want_live_update(&pscan->iscan, p->dp->i_ino)) {
+		if (p->delta > 0) {
+			xrep_findparent_scan_found(pscan, p->dp->i_ino);
+		} else {
+			xrep_findparent_scan_found(pscan, NULLFSINO);
+		}
+	}
+
+	return NOTIFY_DONE;
+}
+
+/*
+ * Set up a scan to find the parent of a directory.  The provided dirent hook
+ * will be called when there is a dotdot update for the inode being repaired.
+ */
+int
+xrep_findparent_scan_start(
+	struct xfs_scrub		*sc,
+	struct xrep_parent_scan_info	*pscan)
+{
+	int				error;
+
+	if (!(sc->flags & XCHK_FSGATES_DIRENTS)) {
+		ASSERT(sc->flags & XCHK_FSGATES_DIRENTS);
+		return -EINVAL;
+	}
+
+	pscan->sc = sc;
+	pscan->parent_ino = NULLFSINO;
+
+	mutex_init(&pscan->lock);
+
+	xchk_iscan_start(sc, 30000, 100, &pscan->iscan);
+
+	/*
+	 * Hook into the dirent update code.  The hook only operates on inodes
+	 * that were already scanned, and the scanner thread takes each inode's
+	 * ILOCK, which means that any in-progress inode updates will finish
+	 * before we can scan the inode.
+	 */
+	xfs_hook_setup(&pscan->hooks.dirent_hook, xrep_findparent_live_update);
+	error = xfs_dir_hook_add(sc->mp, &pscan->hooks);
+	if (error)
+		goto out_iscan;
+
+	return 0;
+out_iscan:
+	xchk_iscan_teardown(&pscan->iscan);
+	mutex_destroy(&pscan->lock);
+	return error;
+}
+
+/*
+ * Scan the entire filesystem looking for a parent inode for the inode being
+ * scrubbed.  @sc->ip must not be the root of a directory tree.  Callers must
+ * not hold a dirty transaction or any lock that would interfere with taking
+ * an ILOCK.
+ *
+ * Returns 0 with @pscan->parent_ino set to the parent that we found.
+ * Returns 0 with @pscan->parent_ino set to NULLFSINO if we found no parents.
+ * Returns the usual negative errno if something else happened.
+ */
+int
+xrep_findparent_scan(
+	struct xrep_parent_scan_info	*pscan)
+{
+	struct xrep_findparent_info	fpi = {
+		.sc			= pscan->sc,
+		.found_parent		= NULLFSINO,
+		.parent_scan		= pscan,
+	};
+	struct xfs_scrub		*sc = pscan->sc;
+	int				ret;
+
+	ASSERT(S_ISDIR(VFS_IC(sc->ip)->i_mode));
+
+	while ((ret = xchk_iscan_iter(&pscan->iscan, &fpi.dp)) == 1) {
+		if (S_ISDIR(VFS_I(fpi.dp)->i_mode))
+			ret = xrep_findparent_walk_directory(&fpi);
+		else
+			ret = 0;
+		xchk_iscan_mark_visited(&pscan->iscan, fpi.dp);
+		xchk_irele(sc, fpi.dp);
+		if (ret)
+			break;
+
+		if (xchk_should_terminate(sc, &ret))
+			break;
+	}
+	xchk_iscan_iter_finish(&pscan->iscan);
+
+	return ret;
+}
+
+/* Tear down a parent scan. */
+void
+xrep_findparent_scan_teardown(
+	struct xrep_parent_scan_info	*pscan)
+{
+	xfs_dir_hook_del(pscan->sc->mp, &pscan->hooks);
+	xchk_iscan_teardown(&pscan->iscan);
+	mutex_destroy(&pscan->lock);
+}
+
+/* Finish a parent scan early. */
+void
+xrep_findparent_scan_finish_early(
+	struct xrep_parent_scan_info	*pscan,
+	xfs_ino_t			ino)
+{
+	xrep_findparent_scan_found(pscan, ino);
+	xchk_iscan_finish_early(&pscan->iscan);
+}
+
+/*
+ * Confirm that the directory @parent_ino actually contains a directory entry
+ * pointing to the child @sc->ip->ino.  This function returns one of several
+ * ways:
+ *
+ * Returns 0 with @parent_ino unchanged if the parent was confirmed.
+ * Returns 0 with @parent_ino set to NULLFSINO if the parent was not valid.
+ * Returns the usual negative errno if something else happened.
+ */
+int
+xrep_findparent_confirm(
+	struct xfs_scrub	*sc,
+	xfs_ino_t		*parent_ino)
+{
+	struct xrep_findparent_info fpi = {
+		.sc		= sc,
+		.found_parent	= NULLFSINO,
+	};
+	int			error;
+
+	/*
+	 * The root directory always points to itself.  Unlinked dirs can point
+	 * anywhere, so we point them at the root dir too.
+	 */
+	if (sc->ip == sc->mp->m_rootip || VFS_I(sc->ip)->i_nlink == 0) {
+		*parent_ino = sc->mp->m_sb.sb_rootino;
+		return 0;
+	}
+
+	/* Reject garbage parent inode numbers and self-referential parents. */
+	if (*parent_ino == NULLFSINO)
+	       return 0;
+	if (!xfs_verify_dir_ino(sc->mp, *parent_ino) ||
+	    *parent_ino == sc->ip->i_ino) {
+		*parent_ino = NULLFSINO;
+		return 0;
+	}
+
+	error = xchk_iget(sc, *parent_ino, &fpi.dp);
+	if (error)
+		return error;
+
+	if (!S_ISDIR(VFS_I(fpi.dp)->i_mode)) {
+		*parent_ino = NULLFSINO;
+		goto out_rele;
+	}
+
+	error = xrep_findparent_walk_directory(&fpi);
+	if (error)
+		goto out_rele;
+
+	*parent_ino = fpi.found_parent;
+out_rele:
+	xchk_irele(sc, fpi.dp);
+	return error;
+}
+
+/*
+ * If we're the root of a directory tree, we are our own parent.  If we're an
+ * unlinked directory, the parent /won't/ have a link to us.  Set the parent
+ * directory to the root for both cases.  Returns NULLFSINO if we don't know
+ * what to do.
+ */
+xfs_ino_t
+xrep_findparent_self_reference(
+	struct xfs_scrub	*sc)
+{
+	if (sc->ip->i_ino == sc->mp->m_sb.sb_rootino)
+		return sc->mp->m_sb.sb_rootino;
+
+	if (VFS_I(sc->ip)->i_nlink == 0)
+		return sc->mp->m_sb.sb_rootino;
+
+	return NULLFSINO;
+}
diff --git a/fs/xfs/scrub/findparent.h b/fs/xfs/scrub/findparent.h
new file mode 100644
index 0000000000000..5876bf661578e
--- /dev/null
+++ b/fs/xfs/scrub/findparent.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2020-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_FINDPARENT_H__
+#define __XFS_SCRUB_FINDPARENT_H__
+
+struct xrep_parent_scan_info {
+	struct xfs_scrub	*sc;
+
+	/* Inode scan cursor. */
+	struct xchk_iscan	iscan;
+
+	/* Hook to capture directory entry updates. */
+	struct xfs_dir_hook	hooks;
+
+	/* Lock protecting parent_ino. */
+	struct mutex		lock;
+
+	/* Parent inode that we've found. */
+	xfs_ino_t		parent_ino;
+
+	bool			lookup_parent;
+};
+
+int xrep_findparent_scan_start(struct xfs_scrub *sc,
+		struct xrep_parent_scan_info *pscan);
+int xrep_findparent_scan(struct xrep_parent_scan_info *pscan);
+void xrep_findparent_scan_teardown(struct xrep_parent_scan_info *pscan);
+
+static inline void
+xrep_findparent_scan_found(
+	struct xrep_parent_scan_info	*pscan,
+	xfs_ino_t			ino)
+{
+	mutex_lock(&pscan->lock);
+	pscan->parent_ino = ino;
+	mutex_unlock(&pscan->lock);
+}
+
+void xrep_findparent_scan_finish_early(struct xrep_parent_scan_info *pscan,
+		xfs_ino_t ino);
+
+int xrep_findparent_confirm(struct xfs_scrub *sc, xfs_ino_t *parent_ino);
+
+xfs_ino_t xrep_findparent_self_reference(struct xfs_scrub *sc);
+
+#endif /* __XFS_SCRUB_FINDPARENT_H__ */
diff --git a/fs/xfs/scrub/iscan.c b/fs/xfs/scrub/iscan.c
index bce8b34a460a1..bf55c90eb2cf3 100644
--- a/fs/xfs/scrub/iscan.c
+++ b/fs/xfs/scrub/iscan.c
@@ -243,6 +243,17 @@ xchk_iscan_finish(
 	mutex_unlock(&iscan->lock);
 }
 
+/* Mark an inode scan finished before we actually scan anything. */
+void
+xchk_iscan_finish_early(
+	struct xchk_iscan	*iscan)
+{
+	ASSERT(iscan->cursor_ino == iscan->scan_start_ino);
+	ASSERT(iscan->__visited_ino == iscan->scan_start_ino);
+
+	xchk_iscan_finish(iscan);
+}
+
 /*
  * Advance ino to the next inode that the inobt thinks is allocated, being
  * careful to jump to the next AG if we've reached the right end of this AG's
@@ -402,8 +413,13 @@ xchk_iscan_iget(
 		 * It's possible that this inode has lost all of its links but
 		 * hasn't yet been inactivated.  If we don't have a transaction
 		 * or it's not writable, flush the inodegc workers and wait.
+		 * If we have a non-empty transaction, we must not block on
+		 * inodegc, which allocates its own transactions.
 		 */
-		xfs_inodegc_flush(mp);
+		if (sc->tp && !(sc->tp->t_flags & XFS_TRANS_NO_WRITECOUNT))
+			xfs_inodegc_push(mp);
+		else
+			xfs_inodegc_flush(mp);
 		return xchk_iscan_iget_retry(iscan, true);
 	}
 
diff --git a/fs/xfs/scrub/iscan.h b/fs/xfs/scrub/iscan.h
index 71f657552dfac..4c442fce2d8f5 100644
--- a/fs/xfs/scrub/iscan.h
+++ b/fs/xfs/scrub/iscan.h
@@ -73,6 +73,7 @@ xchk_iscan_abort(struct xchk_iscan *iscan)
 
 void xchk_iscan_start(struct xfs_scrub *sc, unsigned int iget_timeout,
 		unsigned int iget_retry_delay, struct xchk_iscan *iscan);
+void xchk_iscan_finish_early(struct xchk_iscan *iscan);
 void xchk_iscan_teardown(struct xchk_iscan *iscan);
 
 int xchk_iscan_iter(struct xchk_iscan *iscan, struct xfs_inode **ipp);
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index f8b7f0fc38051..53ec302fe28b4 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -2692,6 +2692,7 @@ DEFINE_EVENT(xrep_parent_salvage_class, name, \
 	TP_PROTO(struct xfs_inode *dp, xfs_ino_t ino), \
 	TP_ARGS(dp, ino))
 DEFINE_XREP_PARENT_SALVAGE_EVENT(xrep_dir_salvaged_parent);
+DEFINE_XREP_PARENT_SALVAGE_EVENT(xrep_findparent_dirent);
 
 #endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
 

[PATCH 3/4] xfs: online repair of parent pointers

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Teach the online repair code to fix parent pointers for directories.
For now, this means correcting the dotdot entry of an existing directory
that is otherwise consistent.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Makefile              |    1 
 fs/xfs/scrub/parent.c        |   10 ++
 fs/xfs/scrub/parent_repair.c |  221 ++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/repair.h        |    4 +
 fs/xfs/scrub/scrub.c         |    2 
 fs/xfs/scrub/trace.h         |    1 
 6 files changed, 238 insertions(+), 1 deletion(-)
 create mode 100644 fs/xfs/scrub/parent_repair.c


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 46f88c72ffd6a..36e4cbbe21999 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -205,6 +205,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   inode_repair.o \
 				   newbt.o \
 				   nlinks_repair.o \
+				   parent_repair.o \
 				   rcbag_btree.o \
 				   rcbag.o \
 				   reap.o \
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index 050a8e8914f6e..acb6282c3d148 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -10,6 +10,7 @@
 #include "xfs_trans_resv.h"
 #include "xfs_mount.h"
 #include "xfs_log_format.h"
+#include "xfs_trans.h"
 #include "xfs_inode.h"
 #include "xfs_icache.h"
 #include "xfs_dir2.h"
@@ -18,12 +19,21 @@
 #include "scrub/common.h"
 #include "scrub/readdir.h"
 #include "scrub/tempfile.h"
+#include "scrub/repair.h"
 
 /* Set us up to scrub parents. */
 int
 xchk_setup_parent(
 	struct xfs_scrub	*sc)
 {
+	int			error;
+
+	if (xchk_could_repair(sc)) {
+		error = xrep_setup_parent(sc);
+		if (error)
+			return error;
+	}
+
 	return xchk_setup_inode_contents(sc, 0);
 }
 
diff --git a/fs/xfs/scrub/parent_repair.c b/fs/xfs/scrub/parent_repair.c
new file mode 100644
index 0000000000000..8b8bc7b1f5a5b
--- /dev/null
+++ b/fs/xfs/scrub/parent_repair.c
@@ -0,0 +1,221 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2020-2024 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_defer.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_dir2.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_dir2_priv.h"
+#include "xfs_trans_space.h"
+#include "xfs_health.h"
+#include "xfs_swapext.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/iscan.h"
+#include "scrub/findparent.h"
+#include "scrub/readdir.h"
+
+/*
+ * Repairing The Directory Parent Pointer
+ * ======================================
+ *
+ * Currently, only directories support parent pointers (in the form of '..'
+ * entries), so we simply scan the filesystem and update the '..' entry.
+ *
+ * Note that because the only parent pointer is the dotdot entry, we won't
+ * touch an unhealthy directory, since the directory repair code is perfectly
+ * capable of rebuilding a directory with the proper parent inode.
+ *
+ * See the section on locking issues in dir_repair.c for more information about
+ * conflicts with the VFS.  The findparent code wll keep our incore parent
+ * inode up to date.
+ */
+
+struct xrep_parent {
+	struct xfs_scrub	*sc;
+
+	/*
+	 * Information used to scan the filesystem to find the inumber of the
+	 * dotdot entry for this directory.
+	 */
+	struct xrep_parent_scan_info pscan;
+};
+
+/* Tear down all the incore stuff we created. */
+static void
+xrep_parent_teardown(
+	struct xrep_parent	*rp)
+{
+	xrep_findparent_scan_teardown(&rp->pscan);
+}
+
+/* Set up for a parent repair. */
+int
+xrep_setup_parent(
+	struct xfs_scrub	*sc)
+{
+	struct xrep_parent	*rp;
+
+	xchk_fsgates_enable(sc, XCHK_FSGATES_DIRENTS);
+
+	rp = kvzalloc(sizeof(struct xrep_parent), XCHK_GFP_FLAGS);
+	if (!rp)
+		return -ENOMEM;
+	rp->sc = sc;
+	sc->buf = rp;
+
+	return 0;
+}
+
+/*
+ * Scan all files in the filesystem for a child dirent that we can turn into
+ * the dotdot entry for this directory.
+ */
+STATIC int
+xrep_parent_find_dotdot(
+	struct xrep_parent	*rp)
+{
+	struct xfs_scrub	*sc = rp->sc;
+	xfs_ino_t		ino;
+	unsigned int		sick, checked;
+	int			error;
+
+	/*
+	 * Avoid sick directories.  There shouldn't be anyone else clearing the
+	 * directory's sick status.
+	 */
+	xfs_inode_measure_sickness(sc->ip, &sick, &checked);
+	if (sick & XFS_SICK_INO_DIR)
+		return -EFSCORRUPTED;
+
+	ino = xrep_findparent_self_reference(sc);
+	if (ino != NULLFSINO) {
+		xrep_findparent_scan_finish_early(&rp->pscan, ino);
+		return 0;
+	}
+
+	/*
+	 * Drop the ILOCK on this directory so that we can scan for the dotdot
+	 * entry.  Figure out who is going to be the parent of this directory,
+	 * then retake the ILOCK so that we can salvage directory entries.
+	 */
+	xchk_iunlock(sc, XFS_ILOCK_EXCL);
+	error = xrep_findparent_scan(&rp->pscan);
+	xchk_ilock(sc, XFS_ILOCK_EXCL);
+
+	return error;
+}
+
+/* Reset a directory's dotdot entry, if needed. */
+STATIC int
+xrep_parent_reset_dotdot(
+	struct xrep_parent	*rp)
+{
+	struct xfs_scrub	*sc = rp->sc;
+	xfs_ino_t		ino;
+	unsigned int		spaceres;
+	int			error = 0;
+
+	ASSERT(sc->ilock_flags & XFS_ILOCK_EXCL);
+
+	error = xchk_dir_lookup(sc, sc->ip, &xfs_name_dotdot, &ino);
+	if (error || ino == rp->pscan.parent_ino)
+		return error;
+
+	xfs_trans_ijoin(sc->tp, sc->ip, 0);
+
+	trace_xrep_parent_reset_dotdot(sc->ip, rp->pscan.parent_ino);
+
+	/*
+	 * Reserve more space just in case we have to expand the dir.  We're
+	 * allowed to exceed quota to repair inconsistent metadata.
+	 */
+	spaceres = XFS_RENAME_SPACE_RES(sc->mp, xfs_name_dotdot.len);
+	error = xfs_trans_reserve_more_inode(sc->tp, sc->ip, spaceres, 0,
+			true);
+	if (error)
+		return error;
+
+	error = xfs_dir_replace(sc->tp, sc->ip, &xfs_name_dotdot,
+			rp->pscan.parent_ino, spaceres);
+	if (error)
+		return error;
+
+	/*
+	 * Roll transaction to detach the inode from the transaction but retain
+	 * ILOCK_EXCL.
+	 */
+	return xfs_trans_roll(&sc->tp);
+}
+
+/*
+ * Commit the new parent pointer structure (currently only the dotdot entry) to
+ * the file that we're repairing.
+ */
+STATIC int
+xrep_parent_rebuild_tree(
+	struct xrep_parent	*rp)
+{
+	if (rp->pscan.parent_ino == NULLFSINO) {
+		/* Cannot fix orphaned directories yet. */
+		return -EFSCORRUPTED;
+	}
+
+	return xrep_parent_reset_dotdot(rp);
+}
+
+/* Set up the filesystem scan so we can look for parents. */
+STATIC int
+xrep_parent_setup_scan(
+	struct xrep_parent	*rp)
+{
+	struct xfs_scrub	*sc = rp->sc;
+
+	return xrep_findparent_scan_start(sc, &rp->pscan);
+}
+
+int
+xrep_parent(
+	struct xfs_scrub	*sc)
+{
+	struct xrep_parent	*rp = sc->buf;
+	int			error;
+
+	error = xrep_parent_setup_scan(rp);
+	if (error)
+		return error;
+
+	error = xrep_parent_find_dotdot(rp);
+	if (error)
+		goto out_teardown;
+
+	/* Last chance to abort before we start committing fixes. */
+	if (xchk_should_terminate(sc, &error))
+		goto out_teardown;
+
+	error = xrep_parent_rebuild_tree(rp);
+	if (error)
+		goto out_teardown;
+
+out_teardown:
+	xrep_parent_teardown(rp);
+	return error;
+}
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 8fc582b286c0a..bcb2e28cf1bbb 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -92,6 +92,7 @@ int xrep_setup_ag_rmapbt(struct xfs_scrub *sc);
 int xrep_setup_ag_refcountbt(struct xfs_scrub *sc);
 int xrep_setup_xattr(struct xfs_scrub *sc);
 int xrep_setup_directory(struct xfs_scrub *sc);
+int xrep_setup_parent(struct xfs_scrub *sc);
 
 /* Repair setup functions */
 int xrep_setup_ag_allocbt(struct xfs_scrub *sc);
@@ -127,6 +128,7 @@ int xrep_nlinks(struct xfs_scrub *sc);
 int xrep_fscounters(struct xfs_scrub *sc);
 int xrep_xattr(struct xfs_scrub *sc);
 int xrep_directory(struct xfs_scrub *sc);
+int xrep_parent(struct xfs_scrub *sc);
 
 #ifdef CONFIG_XFS_RT
 int xrep_rtbitmap(struct xfs_scrub *sc);
@@ -198,6 +200,7 @@ xrep_setup_nothing(
 #define xrep_setup_ag_refcountbt	xrep_setup_nothing
 #define xrep_setup_xattr		xrep_setup_nothing
 #define xrep_setup_directory		xrep_setup_nothing
+#define xrep_setup_parent		xrep_setup_nothing
 
 #define xrep_setup_inode(sc, imap)	((void)0)
 
@@ -225,6 +228,7 @@ xrep_setup_nothing(
 #define xrep_rtsummary			xrep_notsupported
 #define xrep_xattr			xrep_notsupported
 #define xrep_directory			xrep_notsupported
+#define xrep_parent			xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index bda7a0c91e241..f9455502b4170 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -346,7 +346,7 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.type	= ST_INODE,
 		.setup	= xchk_setup_parent,
 		.scrub	= xchk_parent,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_parent,
 	},
 	[XFS_SCRUB_TYPE_RTBITMAP] = {	/* realtime bitmap */
 		.type	= ST_FS,
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 53ec302fe28b4..7590fca158417 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -2631,6 +2631,7 @@ DEFINE_EVENT(xrep_dir_class, name, \
 	TP_ARGS(dp, parent_ino))
 DEFINE_XREP_DIR_EVENT(xrep_dir_rebuild_tree);
 DEFINE_XREP_DIR_EVENT(xrep_dir_reset_fork);
+DEFINE_XREP_DIR_EVENT(xrep_parent_reset_dotdot);
 
 DECLARE_EVENT_CLASS(xrep_dirent_class,
 	TP_PROTO(struct xfs_inode *dp, const struct xfs_name *name,

[PATCH 4/4] xfs: ask the dentry cache if it knows the parent of a directory

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

It's possible that the dentry cache can tell us the parent of a
directory.  Therefore, when repairing directory dot dot entries, query
the dcache as a last resort before scanning the entire filesystem.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/dir_repair.c    |   29 +++++++++++++++++++++++++++++
 fs/xfs/scrub/findparent.c    |   41 ++++++++++++++++++++++++++++++++++++++++-
 fs/xfs/scrub/findparent.h    |    1 +
 fs/xfs/scrub/parent_repair.c |   13 +++++++++++++
 fs/xfs/scrub/trace.h         |    1 +
 5 files changed, 84 insertions(+), 1 deletion(-)


diff --git a/fs/xfs/scrub/dir_repair.c b/fs/xfs/scrub/dir_repair.c
index 297935416aed6..b22fd59c2f8b3 100644
--- a/fs/xfs/scrub/dir_repair.c
+++ b/fs/xfs/scrub/dir_repair.c
@@ -206,6 +206,29 @@ xrep_dir_lookup_parent(
 	return ino;
 }
 
+/*
+ * Look up '..' in the dentry cache and confirm that it's really the parent.
+ * Returns NULLFSINO if the dcache misses or if the hit is implausible.
+ */
+static inline xfs_ino_t
+xrep_dir_dcache_parent(
+	struct xrep_dir		*rd)
+{
+	struct xfs_scrub	*sc = rd->sc;
+	xfs_ino_t		parent_ino;
+	int			error;
+
+	parent_ino = xrep_findparent_from_dcache(sc);
+	if (parent_ino == NULLFSINO)
+		return parent_ino;
+
+	error = xrep_findparent_confirm(sc, &parent_ino);
+	if (error)
+		return NULLFSINO;
+
+	return parent_ino;
+}
+
 /* Try to find the parent of the directory being repaired. */
 STATIC int
 xrep_dir_find_parent(
@@ -219,6 +242,12 @@ xrep_dir_find_parent(
 		return 0;
 	}
 
+	ino = xrep_dir_dcache_parent(rd);
+	if (ino != NULLFSINO) {
+		xrep_findparent_scan_finish_early(&rd->pscan, ino);
+		return 0;
+	}
+
 	ino = xrep_dir_lookup_parent(rd);
 	if (ino != NULLFSINO) {
 		xrep_findparent_scan_finish_early(&rd->pscan, ino);
diff --git a/fs/xfs/scrub/findparent.c b/fs/xfs/scrub/findparent.c
index b8716e881e62e..87047e9d49e47 100644
--- a/fs/xfs/scrub/findparent.c
+++ b/fs/xfs/scrub/findparent.c
@@ -53,7 +53,8 @@
  * must not read the scan results without re-taking @sc->ip's ILOCK.
  *
  * There are a few shortcuts that we can take to avoid scanning the entire
- * filesystem, such as noticing directory tree roots.
+ * filesystem, such as noticing directory tree roots and querying the dentry
+ * cache for parent information.
  */
 
 struct xrep_findparent_info {
@@ -410,3 +411,41 @@ xrep_findparent_self_reference(
 
 	return NULLFSINO;
 }
+
+/* Check the dentry cache to see if knows of a parent for the scrub target. */
+xfs_ino_t
+xrep_findparent_from_dcache(
+	struct xfs_scrub	*sc)
+{
+	struct inode		*pip = NULL;
+	struct dentry		*dentry, *parent;
+	xfs_ino_t		ret = NULLFSINO;
+
+	dentry = d_find_alias(VFS_I(sc->ip));
+	if (!dentry)
+		goto out;
+
+	parent = dget_parent(dentry);
+	if (!parent)
+		goto out_dput;
+
+	if (parent->d_sb != sc->ip->i_mount->m_super) {
+		dput(parent);
+		goto out_dput;
+	}
+
+	pip = igrab(d_inode(parent));
+	dput(parent);
+
+	if (S_ISDIR(pip->i_mode)) {
+		trace_xrep_findparent_from_dcache(sc->ip, XFS_I(pip)->i_ino);
+		ret = XFS_I(pip)->i_ino;
+	}
+
+	xchk_irele(sc, XFS_I(pip));
+
+out_dput:
+	dput(dentry);
+out:
+	return ret;
+}
diff --git a/fs/xfs/scrub/findparent.h b/fs/xfs/scrub/findparent.h
index 5876bf661578e..cb3a97f3fed48 100644
--- a/fs/xfs/scrub/findparent.h
+++ b/fs/xfs/scrub/findparent.h
@@ -45,5 +45,6 @@ void xrep_findparent_scan_finish_early(struct xrep_parent_scan_info *pscan,
 int xrep_findparent_confirm(struct xfs_scrub *sc, xfs_ino_t *parent_ino);
 
 xfs_ino_t xrep_findparent_self_reference(struct xfs_scrub *sc);
+xfs_ino_t xrep_findparent_from_dcache(struct xfs_scrub *sc);
 
 #endif /* __XFS_SCRUB_FINDPARENT_H__ */
diff --git a/fs/xfs/scrub/parent_repair.c b/fs/xfs/scrub/parent_repair.c
index 8b8bc7b1f5a5b..430f95171b50b 100644
--- a/fs/xfs/scrub/parent_repair.c
+++ b/fs/xfs/scrub/parent_repair.c
@@ -118,7 +118,20 @@ xrep_parent_find_dotdot(
 	 * then retake the ILOCK so that we can salvage directory entries.
 	 */
 	xchk_iunlock(sc, XFS_ILOCK_EXCL);
+
+	/* Does the VFS dcache have an answer for us? */
+	ino = xrep_findparent_from_dcache(sc);
+	if (ino != NULLFSINO) {
+		error = xrep_findparent_confirm(sc, &ino);
+		if (!error && ino != NULLFSINO) {
+			xrep_findparent_scan_finish_early(&rp->pscan, ino);
+			goto out_relock;
+		}
+	}
+
+	/* Scan the entire filesystem for a parent. */
 	error = xrep_findparent_scan(&rp->pscan);
+out_relock:
 	xchk_ilock(sc, XFS_ILOCK_EXCL);
 
 	return error;
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 7590fca158417..5ccb92214a80d 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -2694,6 +2694,7 @@ DEFINE_EVENT(xrep_parent_salvage_class, name, \
 	TP_ARGS(dp, ino))
 DEFINE_XREP_PARENT_SALVAGE_EVENT(xrep_dir_salvaged_parent);
 DEFINE_XREP_PARENT_SALVAGE_EVENT(xrep_findparent_dirent);
+DEFINE_XREP_PARENT_SALVAGE_EVENT(xrep_findparent_from_dcache);
 
 #endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
 

[PATCH 1/3] xfs: move orphan files to the orphanage

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

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>
---
 .../filesystems/xfs-online-fsck-design.rst         |   19 +
 fs/xfs/Makefile                                    |    1 
 fs/xfs/scrub/dir_repair.c                          |  130 +++++
 fs/xfs/scrub/orphanage.c                           |  499 ++++++++++++++++++++
 fs/xfs/scrub/orphanage.h                           |   75 +++
 fs/xfs/scrub/parent_repair.c                       |   98 ++++
 fs/xfs/scrub/scrub.c                               |    2 
 fs/xfs/scrub/scrub.h                               |    4 
 fs/xfs/scrub/trace.h                               |   28 +
 fs/xfs/xfs_inode.c                                 |    6 
 fs/xfs/xfs_inode.h                                 |    1 
 11 files changed, 843 insertions(+), 20 deletions(-)
 create mode 100644 fs/xfs/scrub/orphanage.c
 create mode 100644 fs/xfs/scrub/orphanage.h


diff --git a/Documentation/filesystems/xfs-online-fsck-design.rst b/Documentation/filesystems/xfs-online-fsck-design.rst
index a0678101a7d02..63c78e1e85e52 100644
--- a/Documentation/filesystems/xfs-online-fsck-design.rst
+++ b/Documentation/filesystems/xfs-online-fsck-design.rst
@@ -4777,14 +4777,21 @@ 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
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 36e4cbbe21999..49f12fb8480e1 100644
--- a/fs/xfs/Makefile
+++ b/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 \
diff --git a/fs/xfs/scrub/dir_repair.c b/fs/xfs/scrub/dir_repair.c
index b22fd59c2f8b3..141682e2477af 100644
--- a/fs/xfs/scrub/dir_repair.c
+++ b/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. */
 	unsigned char		namebuf[MAXNAMELEN];
 };
@@ -147,6 +157,10 @@ 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
+	 * swapping 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
@@ -1355,6 +1373,91 @@ 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->namebuf);
+	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.
  *
@@ -1393,6 +1496,15 @@ 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;
diff --git a/fs/xfs/scrub/orphanage.c b/fs/xfs/scrub/orphanage.c
new file mode 100644
index 0000000000000..0aedc5c70b632
--- /dev/null
+++ b/fs/xfs/scrub/orphanage.c
@@ -0,0 +1,499 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2021-2024 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_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_inode.h"
+#include "xfs_ialloc.h"
+#include "xfs_quota.h"
+#include "xfs_trans_space.h"
+#include "xfs_dir2.h"
+#include "xfs_icache.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_btree.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/repair.h"
+#include "scrub/trace.h"
+#include "scrub/orphanage.h"
+#include "scrub/readdir.h"
+
+#include <linux/namei.h>
+
+/*
+ * The Orphanage
+ * =============
+ *
+ * If the directory tree is damaged, children of that directory become
+ * inaccessible via that file path.  If a child has no other parents, the file
+ * is said to be orphaned.  xfs_repair fixes this situation by creating a
+ * orphanage directory (specifically, /lost+found) and creating a directory
+ * entry pointing to the orphaned file.
+ *
+ * Online repair follows this tactic by creating a root-owned /lost+found
+ * directory if one does not exist.  If an orphan is found, it will move that
+ * files into orphanage.
+ */
+
+/* Make the orphanage owned by root. */
+STATIC int
+xrep_chown_orphanage(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*dp)
+{
+	struct xfs_trans	*tp;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_dquot	*udqp = NULL, *gdqp = NULL, *pdqp = NULL;
+	struct xfs_dquot	*oldu = NULL, *oldg = NULL, *oldp = NULL;
+	struct inode		*inode = VFS_I(dp);
+	int			error;
+
+	error = xfs_qm_vop_dqalloc(dp, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, 0,
+			XFS_QMOPT_QUOTALL, &udqp, &gdqp, &pdqp);
+	if (error)
+		return error;
+
+	error = xfs_trans_alloc_ichange(dp, udqp, gdqp, pdqp, true, &tp);
+	if (error)
+		goto out_dqrele;
+
+	/*
+	 * Always clear setuid/setgid/sticky on the orphanage since we don't
+	 * normally want that functionality on this directory and xfs_repair
+	 * doesn't create it this way either.  Leave the other access bits
+	 * unchanged.
+	 */
+	inode->i_mode &= ~(S_ISUID | S_ISGID | S_ISVTX);
+
+	/*
+	 * Change the ownerships and register quota modifications
+	 * in the transaction.
+	 */
+	if (!uid_eq(inode->i_uid, GLOBAL_ROOT_UID)) {
+		if (XFS_IS_UQUOTA_ON(mp))
+			oldu = xfs_qm_vop_chown(tp, dp, &dp->i_udquot, udqp);
+		inode->i_uid = GLOBAL_ROOT_UID;
+	}
+	if (!gid_eq(inode->i_gid, GLOBAL_ROOT_GID)) {
+		if (XFS_IS_GQUOTA_ON(mp))
+			oldg = xfs_qm_vop_chown(tp, dp, &dp->i_gdquot, gdqp);
+		inode->i_gid = GLOBAL_ROOT_GID;
+	}
+	if (dp->i_projid != 0) {
+		if (XFS_IS_PQUOTA_ON(mp))
+			oldp = xfs_qm_vop_chown(tp, dp, &dp->i_pdquot, pdqp);
+		dp->i_projid = 0;
+	}
+
+	dp->i_diflags &= ~(XFS_DIFLAG_REALTIME | XFS_DIFLAG_RTINHERIT);
+	xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
+
+	XFS_STATS_INC(mp, xs_ig_attrchg);
+
+	if (xfs_has_wsync(mp))
+		xfs_trans_set_sync(tp);
+	error = xfs_trans_commit(tp);
+
+	xfs_qm_dqrele(oldu);
+	xfs_qm_dqrele(oldg);
+	xfs_qm_dqrele(oldp);
+
+out_dqrele:
+	xfs_qm_dqrele(udqp);
+	xfs_qm_dqrele(gdqp);
+	xfs_qm_dqrele(pdqp);
+	return error;
+}
+
+#define ORPHANAGE	"lost+found"
+
+/* Create the orphanage directory, and set sc->orphanage to it. */
+int
+xrep_orphanage_create(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_mount	*mp = sc->mp;
+	struct dentry		*root_dentry, *orphanage_dentry;
+	struct inode		*root_inode = VFS_I(sc->mp->m_rootip);
+	struct inode		*orphanage_inode;
+	int			error;
+
+	if (xfs_is_shutdown(mp))
+		return -EIO;
+	if (xfs_is_readonly(mp)) {
+		sc->orphanage = NULL;
+		return 0;
+	}
+
+	ASSERT(sc->tp == NULL);
+	ASSERT(sc->orphanage == NULL);
+
+	/* Find the dentry for the root directory... */
+	root_dentry = d_find_alias(root_inode);
+	if (!root_dentry) {
+		error = -EFSCORRUPTED;
+		goto out;
+	}
+
+	/* ...which is a directory, right? */
+	if (!d_is_dir(root_dentry)) {
+		error = -EFSCORRUPTED;
+		goto out_dput_root;
+	}
+
+	/* Try to find the orphanage directory. */
+	inode_lock_nested(root_inode, I_MUTEX_PARENT);
+	orphanage_dentry = lookup_one_len(ORPHANAGE, root_dentry,
+			strlen(ORPHANAGE));
+	if (IS_ERR(orphanage_dentry)) {
+		error = PTR_ERR(orphanage_dentry);
+		goto out_unlock_root;
+	}
+
+	/*
+	 * Nothing found?  Call mkdir to create the orphanage.  Create the
+	 * directory without other-user access because we're live and someone
+	 * could have been relying partly on minimal access to a parent
+	 * directory to control access to a file we put in here.
+	 */
+	if (d_really_is_negative(orphanage_dentry)) {
+		error = vfs_mkdir(&nop_mnt_idmap, root_inode, orphanage_dentry,
+				0750);
+		if (error)
+			goto out_dput_orphanage;
+	}
+
+	/* Not a directory? Bail out. */
+	if (!d_is_dir(orphanage_dentry)) {
+		error = -ENOTDIR;
+		goto out_dput_orphanage;
+	}
+
+	/*
+	 * Grab a reference to the orphanage.  This /should/ succeed since
+	 * we hold the root directory locked and therefore nobody can delete
+	 * the orphanage.
+	 */
+	orphanage_inode = igrab(d_inode(orphanage_dentry));
+	if (!orphanage_inode) {
+		error = -ENOENT;
+		goto out_dput_orphanage;
+	}
+
+	/* Make sure the orphanage is owned by root. */
+	error = xrep_chown_orphanage(sc, XFS_I(orphanage_inode));
+	if (error)
+		goto out_dput_orphanage;
+
+	/* Stash the reference for later and bail out. */
+	sc->orphanage = XFS_I(orphanage_inode);
+	sc->orphanage_ilock_flags = 0;
+
+out_dput_orphanage:
+	dput(orphanage_dentry);
+out_unlock_root:
+	inode_unlock(VFS_I(sc->mp->m_rootip));
+out_dput_root:
+	dput(root_dentry);
+out:
+	return error;
+}
+
+void
+xrep_orphanage_ilock(
+	struct xfs_scrub	*sc,
+	unsigned int		ilock_flags)
+{
+	sc->orphanage_ilock_flags |= ilock_flags;
+	xfs_ilock(sc->orphanage, ilock_flags);
+}
+
+bool
+xrep_orphanage_ilock_nowait(
+	struct xfs_scrub	*sc,
+	unsigned int		ilock_flags)
+{
+	if (xfs_ilock_nowait(sc->orphanage, ilock_flags)) {
+		sc->orphanage_ilock_flags |= ilock_flags;
+		return true;
+	}
+
+	return false;
+}
+
+void
+xrep_orphanage_iunlock(
+	struct xfs_scrub	*sc,
+	unsigned int		ilock_flags)
+{
+	xfs_iunlock(sc->orphanage, ilock_flags);
+	sc->orphanage_ilock_flags &= ~ilock_flags;
+}
+
+/* Grab the IOLOCK of the orphanage and sc->ip. */
+int
+xrep_orphanage_iolock_two(
+	struct xfs_scrub	*sc)
+{
+	int			error = 0;
+
+	while (true) {
+		if (xchk_should_terminate(sc, &error))
+			return error;
+
+		/*
+		 * Normal XFS takes the IOLOCK before grabbing a transaction.
+		 * Scrub holds a transaction, which means that we can't block
+		 * on either IOLOCK.
+		 */
+		if (xrep_orphanage_ilock_nowait(sc, XFS_IOLOCK_EXCL)) {
+			if (xchk_ilock_nowait(sc, XFS_IOLOCK_EXCL))
+				break;
+			xrep_orphanage_iunlock(sc, XFS_IOLOCK_EXCL);
+		}
+		delay(1);
+	}
+
+	return 0;
+}
+
+/* Release the orphanage. */
+void
+xrep_orphanage_rele(
+	struct xfs_scrub	*sc)
+{
+	if (!sc->orphanage)
+		return;
+
+	if (sc->orphanage_ilock_flags)
+		xfs_iunlock(sc->orphanage, sc->orphanage_ilock_flags);
+
+	xchk_irele(sc, sc->orphanage);
+	sc->orphanage = NULL;
+}
+
+/* Adoption moves a file into /lost+found */
+
+/* Can the orphanage adopt @sc->ip? */
+bool
+xrep_orphanage_can_adopt(
+	struct xfs_scrub	*sc)
+{
+	ASSERT(sc->ip != NULL);
+
+	if (!sc->orphanage)
+		return false;
+	if (sc->ip == sc->orphanage)
+		return false;
+	if (xfs_internal_inum(sc->mp, sc->ip->i_ino))
+		return false;
+	return true;
+}
+
+/*
+ * Create a new transaction to send a child to the orphanage.
+ *
+ * Allocate a new transaction with sufficient disk space to handle the
+ * adoption, take ILOCK_EXCL of the orphanage and sc->ip, joins them to the
+ * transaction, and reserve quota to reparent the latter.  Caller must hold the
+ * IOLOCK of the orphanage and sc->ip.
+ */
+int
+xrep_adoption_trans_alloc(
+	struct xfs_scrub	*sc,
+	struct xrep_adoption	*adopt)
+{
+	struct xfs_mount	*mp = sc->mp;
+	unsigned int		child_blkres = 0;
+	int			error;
+
+	ASSERT(sc->tp == NULL);
+	ASSERT(sc->ip != NULL);
+	ASSERT(sc->orphanage != NULL);
+	ASSERT(sc->ilock_flags & XFS_IOLOCK_EXCL);
+	ASSERT(sc->orphanage_ilock_flags & XFS_IOLOCK_EXCL);
+	ASSERT(!(sc->ilock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)));
+	ASSERT(!(sc->orphanage_ilock_flags &
+				(XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)));
+
+	/* Compute the worst case space reservation that we need. */
+	adopt->sc = sc;
+	adopt->orphanage_blkres = XFS_LINK_SPACE_RES(mp, MAXNAMELEN);
+	if (S_ISDIR(VFS_I(sc->ip)->i_mode))
+		child_blkres = XFS_RENAME_SPACE_RES(mp, xfs_name_dotdot.len);
+	adopt->child_blkres = child_blkres;
+
+	/*
+	 * Allocate a transaction to link the child into the parent, along with
+	 * enough disk space to handle expansion of both the orphanage and the
+	 * dotdot entry of a child directory.
+	 */
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_link,
+			adopt->orphanage_blkres + adopt->child_blkres, 0, 0,
+			&sc->tp);
+	if (error)
+		return error;
+
+	xfs_lock_two_inodes(sc->orphanage, XFS_ILOCK_EXCL,
+			    sc->ip, XFS_ILOCK_EXCL);
+	sc->ilock_flags |= XFS_ILOCK_EXCL;
+	sc->orphanage_ilock_flags |= XFS_ILOCK_EXCL;
+
+	xfs_trans_ijoin(sc->tp, sc->orphanage, 0);
+	xfs_trans_ijoin(sc->tp, sc->ip, 0);
+
+	/*
+	 * Reserve enough quota in the orphan directory to add the new name.
+	 * Normally the orphanage should have user/group/project ids of zero
+	 * and hence is not subject to quota enforcement, but we're allowed to
+	 * exceed quota to reattach disconnected parts of the directory tree.
+	 */
+	error = xfs_trans_reserve_quota_nblks(sc->tp, sc->orphanage,
+			adopt->orphanage_blkres, 0, true);
+	if (error)
+		goto out_cancel;
+
+	/*
+	 * Reserve enough quota in the child directory to change dotdot.
+	 * Here we're also allowed to exceed file quota to repair inconsistent
+	 * metadata.
+	 */
+	if (adopt->child_blkres) {
+		error = xfs_trans_reserve_quota_nblks(sc->tp, sc->ip,
+				adopt->child_blkres, 0, true);
+		if (error)
+			goto out_cancel;
+	}
+
+	return 0;
+out_cancel:
+	xchk_trans_cancel(sc);
+	xrep_orphanage_iunlock(sc, XFS_ILOCK_EXCL);
+	xrep_orphanage_iunlock(sc, XFS_IOLOCK_EXCL);
+	return error;
+}
+
+/*
+ * Compute the xfs_name for the directory entry that we're adding to the
+ * orphanage.  Caller must hold ILOCKs of sc->ip and the orphanage and must not
+ * reuse namebuf until the adoption completes or is dissolved.
+ */
+int
+xrep_adoption_compute_name(
+	struct xrep_adoption	*adopt,
+	unsigned char		*namebuf)
+{
+	struct xfs_name		*xname = &adopt->xname;
+	struct xfs_scrub	*sc = adopt->sc;
+	xfs_ino_t		ino;
+	unsigned int		incr = 0;
+	int			error = 0;
+
+	xname->name = namebuf;
+	xname->len = snprintf(namebuf, MAXNAMELEN, "%llu", sc->ip->i_ino);
+	xname->type = xfs_mode_to_ftype(VFS_I(sc->ip)->i_mode);
+
+	/* Make sure the filename is unique in the lost+found. */
+	error = xchk_dir_lookup(sc, sc->orphanage, xname, &ino);
+	while (error == 0 && incr < 10000) {
+		xname->len = snprintf(namebuf, MAXNAMELEN, "%llu.%u",
+				sc->ip->i_ino, ++incr);
+		error = xchk_dir_lookup(sc, sc->orphanage, xname, &ino);
+	}
+	if (error == 0) {
+		/* We already have 10,000 entries in the orphanage? */
+		return -EFSCORRUPTED;
+	}
+
+	if (error != -ENOENT)
+		return error;
+	return 0;
+}
+
+/*
+ * Move the current file to the orphanage under the computed name.
+ *
+ * Returns with a dirty transaction so that the caller can handle any other
+ * work, such as fixing up unlinked lists or resetting link counts.
+ */
+int
+xrep_adoption_move(
+	struct xrep_adoption	*adopt)
+{
+	struct xfs_scrub	*sc = adopt->sc;
+	struct xfs_name		*xname = &adopt->xname;
+	bool			isdir = S_ISDIR(VFS_I(sc->ip)->i_mode);
+	int			error;
+
+	trace_xrep_adoption_reparent(sc->orphanage, &adopt->xname,
+			sc->ip->i_ino);
+
+	/* Create the new name in the orphanage. */
+	error = xfs_dir_createname(sc->tp, sc->orphanage, xname, sc->ip->i_ino,
+			adopt->orphanage_blkres);
+	if (error)
+		return error;
+
+	/*
+	 * Bump the link count of the orphanage if we just added a
+	 * subdirectory, and update its timestamps.
+	 */
+	xfs_trans_ichgtime(sc->tp, sc->orphanage,
+			XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+	if (isdir)
+		xfs_bumplink(sc->tp, sc->orphanage);
+	xfs_trans_log_inode(sc->tp, sc->orphanage, XFS_ILOG_CORE);
+
+	/* Replace the dotdot entry if the child is a subdirectory. */
+	if (isdir) {
+		error = xfs_dir_replace(sc->tp, sc->ip, &xfs_name_dotdot,
+				sc->orphanage->i_ino, adopt->child_blkres);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * Notify dirent hooks that we moved the file to /lost+found, and
+	 * finish all the deferred work so that we know the adoption is fully
+	 * recorded in the log.
+	 */
+	xfs_dir_update_hook(sc->orphanage, sc->ip, 1, xname);
+	return 0;
+}
+
+/*
+ * Roll to a clean scrub transaction so that we can release the orphanage,
+ * even if xrep_adoption_move was not called.
+ *
+ * Commits all the work and deferred ops attached to an adoption request and
+ * rolls to a clean scrub transaction.  On success, returns 0 with the scrub
+ * context holding a clean transaction with no inodes joined.  On failure,
+ * returns negative errno with no scrub transaction.  All inode locks are
+ * still held after this function returns.
+ */
+int
+xrep_adoption_trans_roll(
+	struct xrep_adoption	*adopt)
+{
+	struct xfs_scrub	*sc = adopt->sc;
+	int			error;
+
+	trace_xrep_adoption_trans_roll(sc->orphanage, sc->ip,
+			!!(sc->tp->t_flags & XFS_TRANS_DIRTY));
+
+	/* Finish all the deferred ops to commit all repairs. */
+	error = xrep_defer_finish(sc);
+	if (error)
+		return error;
+
+	/* Roll the transaction once more to detach the inodes. */
+	return xfs_trans_roll(&sc->tp);
+}
diff --git a/fs/xfs/scrub/orphanage.h b/fs/xfs/scrub/orphanage.h
new file mode 100644
index 0000000000000..9d40992583b24
--- /dev/null
+++ b/fs/xfs/scrub/orphanage.h
@@ -0,0 +1,75 @@
+// 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 {
+	/* Name structure; caller must provide a buffer separately. */
+	struct xfs_name		xname;
+
+	struct xfs_scrub	*sc;
+
+	/* 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,
+		unsigned char *namebuf);
+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__ */
diff --git a/fs/xfs/scrub/parent_repair.c b/fs/xfs/scrub/parent_repair.c
index 430f95171b50b..2eb0dbde9c459 100644
--- a/fs/xfs/scrub/parent_repair.c
+++ b/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 +59,12 @@ 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. */
+	unsigned char		namebuf[MAXNAMELEN];
 };
 
 /* Tear down all the incore stuff we created. */
@@ -82,7 +90,7 @@ xrep_setup_parent(
 	rp->sc = sc;
 	sc->buf = rp;
 
-	return 0;
+	return xrep_orphanage_try_create(sc);
 }
 
 /*
@@ -179,6 +187,91 @@ 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->namebuf);
+	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 +281,8 @@ 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;
 	}
 
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index f9455502b4170..0d35f1f30d9be 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/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
@@ -220,6 +221,7 @@ xchk_teardown(
 	}
 
 	xrep_tempfile_rele(sc);
+	xrep_orphanage_rele(sc);
 	xchk_fsgates_disable(sc);
 	return error;
 }
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index 48b2fb8271499..09769af6b66a9 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/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;
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 5ccb92214a80d..10b8aa82c2fc8 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -2669,6 +2669,34 @@ 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),
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 0d7dcb128f857..9618c014615f5 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -936,10 +936,10 @@ 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);
 
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index f11e91c6e2182..9cee94a0de2c8 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -621,6 +621,7 @@ 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(

[PATCH 2/3] xfs: move files to orphanage instead of letting nlinks drop to zero

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If we encounter an inode with a nonzero link count but zero observed
links, move it to the orphanage.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 .../filesystems/xfs-online-fsck-design.rst         |    3 
 fs/xfs/scrub/nlinks.c                              |   11 ++
 fs/xfs/scrub/nlinks.h                              |    6 +
 fs/xfs/scrub/nlinks_repair.c                       |  124 ++++++++++++++++++--
 fs/xfs/scrub/repair.h                              |    2 
 fs/xfs/scrub/trace.c                               |    1 
 fs/xfs/scrub/trace.h                               |   26 ++++
 7 files changed, 158 insertions(+), 15 deletions(-)


diff --git a/Documentation/filesystems/xfs-online-fsck-design.rst b/Documentation/filesystems/xfs-online-fsck-design.rst
index 63c78e1e85e52..827fcd49fe6d5 100644
--- a/Documentation/filesystems/xfs-online-fsck-design.rst
+++ b/Documentation/filesystems/xfs-online-fsck-design.rst
@@ -4788,7 +4788,8 @@ Orphaned files are adopted by the orphanage as follows:
    cache.
 
 6. Call ``xrep_adoption_finish`` to commit any filesystem updates, release the
-   orphanage ILOCK, and clean the scrub transaction.
+   orphanage ILOCK, and clean the scrub transaction.  Call
+   ``xrep_adoption_commit`` to commit the updates and the scrub transaction.
 
 7. If a runtime error happens, call ``xrep_adoption_cancel`` to release all
    resources.
diff --git a/fs/xfs/scrub/nlinks.c b/fs/xfs/scrub/nlinks.c
index a6d68d9eb3d7e..7be2119ce283a 100644
--- a/fs/xfs/scrub/nlinks.c
+++ b/fs/xfs/scrub/nlinks.c
@@ -24,6 +24,7 @@
 #include "scrub/xfile.h"
 #include "scrub/xfarray.h"
 #include "scrub/iscan.h"
+#include "scrub/orphanage.h"
 #include "scrub/nlinks.h"
 #include "scrub/trace.h"
 #include "scrub/readdir.h"
@@ -44,9 +45,17 @@ int
 xchk_setup_nlinks(
 	struct xfs_scrub	*sc)
 {
+	int			error;
+
 	xchk_fsgates_enable(sc, XCHK_FSGATES_DIRENTS);
 
-	sc->buf = kzalloc(sizeof(struct xchk_nlink_ctrs), XCHK_GFP_FLAGS);
+	if (xchk_could_repair(sc)) {
+		error = xrep_setup_nlinks(sc);
+		if (error)
+			return error;
+	}
+
+	sc->buf = kvzalloc(sizeof(struct xchk_nlink_ctrs), XCHK_GFP_FLAGS);
 	if (!sc->buf)
 		return -ENOMEM;
 
diff --git a/fs/xfs/scrub/nlinks.h b/fs/xfs/scrub/nlinks.h
index 6b651ac0822e2..f4766e01b6469 100644
--- a/fs/xfs/scrub/nlinks.h
+++ b/fs/xfs/scrub/nlinks.h
@@ -28,6 +28,12 @@ struct xchk_nlink_ctrs {
 	 * from other writer threads.
 	 */
 	struct xfs_dir_hook	hooks;
+
+	/* Orphanage reparenting request. */
+	struct xrep_adoption	adoption;
+
+	/* Directory entry name, plus the trailing null. */
+	char			namebuf[MAXNAMELEN];
 };
 
 /*
diff --git a/fs/xfs/scrub/nlinks_repair.c b/fs/xfs/scrub/nlinks_repair.c
index 23eb08c4b5ad5..1345c07a95c62 100644
--- a/fs/xfs/scrub/nlinks_repair.c
+++ b/fs/xfs/scrub/nlinks_repair.c
@@ -24,6 +24,7 @@
 #include "scrub/xfile.h"
 #include "scrub/xfarray.h"
 #include "scrub/iscan.h"
+#include "scrub/orphanage.h"
 #include "scrub/nlinks.h"
 #include "scrub/trace.h"
 #include "scrub/tempfile.h"
@@ -38,6 +39,34 @@
  * inode is locked.
  */
 
+/* Set up to repair inode link counts. */
+int
+xrep_setup_nlinks(
+	struct xfs_scrub	*sc)
+{
+	return xrep_orphanage_try_create(sc);
+}
+
+/*
+ * Inodes that aren't the root directory or the orphanage, have a nonzero link
+ * count, and no observed parents should be moved to the orphanage.
+ */
+static inline bool
+xrep_nlinks_is_orphaned(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip,
+	unsigned int		actual_nlink,
+	const struct xchk_nlink	*obs)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+
+	if (obs->parents != 0)
+		return false;
+	if (ip == mp->m_rootip || ip == sc->orphanage)
+		return false;
+	return actual_nlink != 0;
+}
+
 /* Remove an inode from the unlinked list. */
 STATIC int
 xrep_nlinks_iunlink_remove(
@@ -66,6 +95,7 @@ xrep_nlinks_repair_inode(
 	struct xfs_inode	*ip = sc->ip;
 	uint64_t		total_links;
 	uint64_t		actual_nlink;
+	bool			orphanage_available = false;
 	bool			dirty = false;
 	int			error;
 
@@ -77,14 +107,41 @@ xrep_nlinks_repair_inode(
 	if (xrep_is_tempfile(ip))
 		return 0;
 
-	xchk_ilock(sc, XFS_IOLOCK_EXCL);
+	/*
+	 * If the filesystem has an orphanage attached to the scrub context,
+	 * prepare for a link count repair that could involve @ip being adopted
+	 * by the lost+found.
+	 */
+	if (xrep_orphanage_can_adopt(sc)) {
+		error = xrep_orphanage_iolock_two(sc);
+		if (error)
+			return error;
 
-	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_link, 0, 0, 0, &sc->tp);
-	if (error)
-		return error;
+		error = xrep_adoption_trans_alloc(sc, &xnc->adoption);
+		if (error) {
+			xchk_iunlock(sc, XFS_IOLOCK_EXCL);
+			xrep_orphanage_iunlock(sc, XFS_IOLOCK_EXCL);
+		} else {
+			orphanage_available = true;
+		}
+	}
 
-	xchk_ilock(sc, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(sc->tp, ip, 0);
+	/*
+	 * Either there is no orphanage or we couldn't allocate resources for
+	 * that kind of update.  Let's try again with only the resources we
+	 * need for a simple link count update, since that's much more common.
+	 */
+	if (!orphanage_available) {
+		xchk_ilock(sc, XFS_IOLOCK_EXCL);
+
+		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_link, 0, 0, 0,
+				&sc->tp);
+		if (error)
+			return error;
+
+		xchk_ilock(sc, XFS_ILOCK_EXCL);
+		xfs_trans_ijoin(sc->tp, ip, 0);
+	}
 
 	mutex_lock(&xnc->lock);
 
@@ -122,6 +179,42 @@ xrep_nlinks_repair_inode(
 		goto out_trans;
 	}
 
+	/*
+	 * Decide if we're going to move this file to the orphanage, and fix
+	 * up the incore link counts if we are.
+	 */
+	if (orphanage_available &&
+	    xrep_nlinks_is_orphaned(sc, ip, actual_nlink, &obs)) {
+		/* Figure out what name we're going to use here. */
+		error = xrep_adoption_compute_name(&xnc->adoption,
+				xnc->namebuf);
+		if (error)
+			goto out_trans;
+
+		/*
+		 * Reattach this file to the directory tree by moving it to
+		 * the orphanage per the adoption parameters that we already
+		 * computed.
+		 */
+		error = xrep_adoption_move(&xnc->adoption);
+		if (error)
+			goto out_trans;
+
+		/*
+		 * Re-read the link counts since the reparenting will have
+		 * updated our scan info.
+		 */
+		mutex_lock(&xnc->lock);
+		error = xfarray_load_sparse(xnc->nlinks, ip->i_ino, &obs);
+		mutex_unlock(&xnc->lock);
+		if (error)
+			goto out_trans;
+
+		total_links = xchk_nlink_total(ip, &obs);
+		actual_nlink = VFS_I(ip)->i_nlink;
+		dirty = true;
+	}
+
 	/*
 	 * If this inode is linked from the directory tree and on the unlinked
 	 * list, remove it from the unlinked list.
@@ -165,14 +258,19 @@ xrep_nlinks_repair_inode(
 	xfs_trans_log_inode(sc->tp, ip, XFS_ILOG_CORE);
 
 	error = xrep_trans_commit(sc);
-	xchk_iunlock(sc, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
-	return error;
+	goto out_unlock;
 
 out_scanlock:
 	mutex_unlock(&xnc->lock);
 out_trans:
 	xchk_trans_cancel(sc);
-	xchk_iunlock(sc, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+out_unlock:
+	xchk_iunlock(sc, XFS_ILOCK_EXCL);
+	if (orphanage_available) {
+		xrep_orphanage_iunlock(sc, XFS_ILOCK_EXCL);
+		xrep_orphanage_iunlock(sc, XFS_IOLOCK_EXCL);
+	}
+	xchk_iunlock(sc, XFS_IOLOCK_EXCL);
 	return error;
 }
 
@@ -205,10 +303,10 @@ xrep_nlinks(
 	/*
 	 * We need ftype for an accurate count of the number of child
 	 * subdirectory links.  Child subdirectories with a back link (dotdot
-	 * entry) but no forward link are unfixable, so we cannot repair the
-	 * link count of the parent directory based on the back link count
-	 * alone.  Filesystems without ftype support are rare (old V4) so we
-	 * just skip out here.
+	 * entry) but no forward link are moved to the orphanage, so we cannot
+	 * repair the link count of the parent directory based on the back link
+	 * count alone.  Filesystems without ftype support are rare (old V4) so
+	 * we just skip out here.
 	 */
 	if (!xfs_has_ftype(sc->mp))
 		return -EOPNOTSUPP;
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index bcb2e28cf1bbb..615137a2039ab 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -93,6 +93,7 @@ int xrep_setup_ag_refcountbt(struct xfs_scrub *sc);
 int xrep_setup_xattr(struct xfs_scrub *sc);
 int xrep_setup_directory(struct xfs_scrub *sc);
 int xrep_setup_parent(struct xfs_scrub *sc);
+int xrep_setup_nlinks(struct xfs_scrub *sc);
 
 /* Repair setup functions */
 int xrep_setup_ag_allocbt(struct xfs_scrub *sc);
@@ -201,6 +202,7 @@ xrep_setup_nothing(
 #define xrep_setup_xattr		xrep_setup_nothing
 #define xrep_setup_directory		xrep_setup_nothing
 #define xrep_setup_parent		xrep_setup_nothing
+#define xrep_setup_nlinks		xrep_setup_nothing
 
 #define xrep_setup_inode(sc, imap)	((void)0)
 
diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c
index ea41b5d9b3c6a..e127f6d492c35 100644
--- a/fs/xfs/scrub/trace.c
+++ b/fs/xfs/scrub/trace.c
@@ -25,6 +25,7 @@
 #include "scrub/xfarray.h"
 #include "scrub/quota.h"
 #include "scrub/iscan.h"
+#include "scrub/orphanage.h"
 #include "scrub/nlinks.h"
 #include "scrub/fscounters.h"
 #include "scrub/xfbtree.h"
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 10b8aa82c2fc8..9c90b078d021a 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -2724,6 +2724,32 @@ DEFINE_XREP_PARENT_SALVAGE_EVENT(xrep_dir_salvaged_parent);
 DEFINE_XREP_PARENT_SALVAGE_EVENT(xrep_findparent_dirent);
 DEFINE_XREP_PARENT_SALVAGE_EVENT(xrep_findparent_from_dcache);
 
+TRACE_EVENT(xrep_nlinks_set_record,
+	TP_PROTO(struct xfs_mount *mp, xfs_ino_t ino,
+		 const struct xchk_nlink *obs),
+	TP_ARGS(mp, ino, obs),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(xfs_nlink_t, parents)
+		__field(xfs_nlink_t, backrefs)
+		__field(xfs_nlink_t, children)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->ino = ino;
+		__entry->parents = obs->parents;
+		__entry->backrefs = obs->backrefs;
+		__entry->children = obs->children;
+	),
+	TP_printk("dev %d:%d ino 0x%llx parents %u backrefs %u children %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->parents,
+		  __entry->backrefs,
+		  __entry->children)
+);
+
 #endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
 
 

[PATCH 3/3] xfs: ensure dentry consistency when the orphanage adopts a file

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

When the orphanage adopts a file, that file becomes a child of the
orphanage.  The dentry cache may have entries for the orphanage
directory and the name we've chosen, so (1) make sure we abort if the
dcache has a positive entry because something's not right; and (2)
invalidate and purge negative dentries if the adoption goes through.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/orphanage.c |   88 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/trace.h     |   42 ++++++++++++++++++++++
 2 files changed, 130 insertions(+)


diff --git a/fs/xfs/scrub/orphanage.c b/fs/xfs/scrub/orphanage.c
index 0aedc5c70b632..e1024a7bc9e96 100644
--- a/fs/xfs/scrub/orphanage.c
+++ b/fs/xfs/scrub/orphanage.c
@@ -418,6 +418,87 @@ xrep_adoption_compute_name(
 	return 0;
 }
 
+/*
+ * Make sure the dcache does not have a positive dentry for the name we've
+ * chosen.  The caller should have checked with the ondisk directory, so any
+ * discrepancy is a sign that something is seriously wrong.
+ */
+static int
+xrep_adoption_check_dcache(
+	struct xrep_adoption	*adopt)
+{
+	struct qstr		qname = QSTR_INIT(adopt->xname.name,
+						  adopt->xname.len);
+	struct dentry		*d_orphanage, *d_child;
+	int			error = 0;
+
+	d_orphanage = d_find_alias(VFS_I(adopt->sc->orphanage));
+	if (!d_orphanage)
+		return 0;
+
+	d_child = d_hash_and_lookup(d_orphanage, &qname);
+	if (d_child) {
+		trace_xrep_adoption_check_child(adopt->sc->mp, d_child);
+
+		if (d_is_positive(d_child)) {
+			ASSERT(d_is_negative(d_child));
+			error = -EFSCORRUPTED;
+		}
+
+		dput(d_child);
+	}
+
+	dput(d_orphanage);
+	if (error)
+		return error;
+
+	/*
+	 * Do we need to update d_parent of the dentry for the file being
+	 * repaired?  In theory there shouldn't be one since the file had
+	 * nonzero nlink but wasn't connected to any parent dir.
+	 */
+	d_child = d_find_alias(VFS_I(adopt->sc->ip));
+	if (d_child) {
+		trace_xrep_adoption_check_alias(adopt->sc->mp, d_child);
+		ASSERT(d_child->d_parent == NULL);
+
+		dput(d_child);
+		return -EFSCORRUPTED;
+	}
+
+	return 0;
+}
+
+/*
+ * Remove all negative dentries from the dcache.  There should not be any
+ * positive entries, since we've maintained our lock on the orphanage
+ * directory.
+ */
+static void
+xrep_adoption_zap_dcache(
+	struct xrep_adoption	*adopt)
+{
+	struct qstr		qname = QSTR_INIT(adopt->xname.name,
+						  adopt->xname.len);
+	struct dentry		*d_orphanage, *d_child;
+
+	d_orphanage = d_find_alias(VFS_I(adopt->sc->orphanage));
+	if (!d_orphanage)
+		return;
+
+	d_child = d_hash_and_lookup(d_orphanage, &qname);
+	while (d_child != NULL) {
+		trace_xrep_adoption_invalidate_child(adopt->sc->mp, d_child);
+
+		ASSERT(d_is_negative(d_child));
+		d_invalidate(d_child);
+		dput(d_child);
+		d_child = d_lookup(d_orphanage, &qname);
+	}
+
+	dput(d_orphanage);
+}
+
 /*
  * Move the current file to the orphanage under the computed name.
  *
@@ -436,6 +517,10 @@ xrep_adoption_move(
 	trace_xrep_adoption_reparent(sc->orphanage, &adopt->xname,
 			sc->ip->i_ino);
 
+	error = xrep_adoption_check_dcache(adopt);
+	if (error)
+		return error;
+
 	/* Create the new name in the orphanage. */
 	error = xfs_dir_createname(sc->tp, sc->orphanage, xname, sc->ip->i_ino,
 			adopt->orphanage_blkres);
@@ -466,6 +551,9 @@ xrep_adoption_move(
 	 * recorded in the log.
 	 */
 	xfs_dir_update_hook(sc->orphanage, sc->ip, 1, xname);
+
+	/* Remove negative dentries from the lost+found's dcache */
+	xrep_adoption_zap_dcache(adopt);
 	return 0;
 }
 
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 9c90b078d021a..3766fffd7eb08 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -2750,6 +2750,48 @@ TRACE_EVENT(xrep_nlinks_set_record,
 		  __entry->children)
 );
 
+DECLARE_EVENT_CLASS(xrep_dentry_class,
+	TP_PROTO(struct xfs_mount *mp, const struct dentry *dentry),
+	TP_ARGS(mp, dentry),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(unsigned int, flags)
+		__field(unsigned long, ino)
+		__field(bool, positive)
+		__field(unsigned long, parent_ino)
+		__field(unsigned int, namelen)
+		__dynamic_array(char, name, dentry->d_name.len)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->flags = dentry->d_flags;
+		__entry->positive = d_is_positive(dentry);
+		if (dentry->d_parent && d_inode(dentry->d_parent))
+			__entry->parent_ino = d_inode(dentry->d_parent)->i_ino;
+		else
+			__entry->parent_ino = -1UL;
+		__entry->ino = d_inode(dentry) ? d_inode(dentry)->i_ino : 0;
+		__entry->namelen = dentry->d_name.len;
+		memcpy(__get_str(name), dentry->d_name.name, dentry->d_name.len);
+	),
+	TP_printk("dev %d:%d flags 0x%x positive? %d parent_ino 0x%lx ino 0x%lx name '%.*s'",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->flags,
+		  __entry->positive,
+		  __entry->parent_ino,
+		  __entry->ino,
+		  __entry->namelen,
+		  __get_str(name))
+);
+#define DEFINE_REPAIR_DENTRY_EVENT(name) \
+DEFINE_EVENT(xrep_dentry_class, name, \
+	TP_PROTO(struct xfs_mount *mp, const struct dentry *dentry), \
+	TP_ARGS(mp, dentry))
+DEFINE_REPAIR_DENTRY_EVENT(xrep_adoption_check_child);
+DEFINE_REPAIR_DENTRY_EVENT(xrep_adoption_check_alias);
+DEFINE_REPAIR_DENTRY_EVENT(xrep_adoption_check_dentry);
+DEFINE_REPAIR_DENTRY_EVENT(xrep_adoption_invalidate_child);
+
 #endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
 
 

[PATCH 1/1] xfs: online repair of symbolic links

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If a symbolic link target looks bad, try to sift through the rubble to
find as much of the target buffer that we can, and stage a new target
(short or remote format as needed) in a temporary file and use the
atomic extent swapping mechanism to commit the results.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/Makefile                    |    1 
 fs/xfs/libxfs/xfs_bmap.c           |   11 -
 fs/xfs/libxfs/xfs_bmap.h           |    6 
 fs/xfs/libxfs/xfs_symlink_remote.c |    9 -
 fs/xfs/libxfs/xfs_symlink_remote.h |   22 +-
 fs/xfs/scrub/repair.h              |    8 +
 fs/xfs/scrub/scrub.c               |    2 
 fs/xfs/scrub/symlink.c             |   13 +
 fs/xfs/scrub/symlink_repair.c      |  488 ++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/tempfile.c            |    5 
 fs/xfs/scrub/trace.h               |   46 +++
 11 files changed, 596 insertions(+), 15 deletions(-)
 create mode 100644 fs/xfs/scrub/symlink_repair.c


diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 49f12fb8480e1..09016465d4925 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -213,6 +213,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   refcount_repair.o \
 				   repair.o \
 				   rmap_repair.o \
+				   symlink_repair.o \
 				   tempfile.o \
 				   xfblob.o \
 				   xfbtree.o \
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 5a0e6cffb90d9..44b8c315c5978 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -761,7 +761,7 @@ xfs_bmap_local_to_extents_empty(
 }
 
 
-STATIC int				/* error */
+int					/* error */
 xfs_bmap_local_to_extents(
 	xfs_trans_t	*tp,		/* transaction pointer */
 	xfs_inode_t	*ip,		/* incore inode pointer */
@@ -771,7 +771,8 @@ xfs_bmap_local_to_extents(
 	void		(*init_fn)(struct xfs_trans *tp,
 				   struct xfs_buf *bp,
 				   struct xfs_inode *ip,
-				   struct xfs_ifork *ifp))
+				   struct xfs_ifork *ifp, void *priv),
+	void		*priv)
 {
 	int		error = 0;
 	int		flags;		/* logging flags returned */
@@ -832,7 +833,7 @@ xfs_bmap_local_to_extents(
 	 * log here. Note that init_fn must also set the buffer log item type
 	 * correctly.
 	 */
-	init_fn(tp, bp, ip, ifp);
+	init_fn(tp, bp, ip, ifp, priv);
 
 	/* account for the change in fork size */
 	xfs_idata_realloc(ip, -ifp->if_bytes, whichfork);
@@ -964,8 +965,8 @@ xfs_bmap_add_attrfork_local(
 
 	if (S_ISLNK(VFS_I(ip)->i_mode))
 		return xfs_bmap_local_to_extents(tp, ip, 1, flags,
-						 XFS_DATA_FORK,
-						 xfs_symlink_local_to_remote);
+				XFS_DATA_FORK, xfs_symlink_local_to_remote,
+				NULL);
 
 	/* should only be called for types that support local format data */
 	ASSERT(0);
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index ccd1ddcd78500..87633449c379a 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -177,6 +177,12 @@ unsigned int xfs_bmap_compute_attr_offset(struct xfs_mount *mp);
 int	xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
 void	xfs_bmap_local_to_extents_empty(struct xfs_trans *tp,
 		struct xfs_inode *ip, int whichfork);
+int xfs_bmap_local_to_extents(struct xfs_trans *tp, struct xfs_inode *ip,
+		xfs_extlen_t total, int *logflagsp, int whichfork,
+		void (*init_fn)(struct xfs_trans *tp, struct xfs_buf *bp,
+				struct xfs_inode *ip, struct xfs_ifork *ifp,
+				void *priv),
+		void *priv);
 void	xfs_bmap_compute_maxlevels(struct xfs_mount *mp, int whichfork);
 int	xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork);
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c
index c9c50b50d2114..3b86d1d27f43d 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.c
+++ b/fs/xfs/libxfs/xfs_symlink_remote.c
@@ -169,7 +169,8 @@ xfs_symlink_local_to_remote(
 	struct xfs_trans	*tp,
 	struct xfs_buf		*bp,
 	struct xfs_inode	*ip,
-	struct xfs_ifork	*ifp)
+	struct xfs_ifork	*ifp,
+	void			*priv)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	char			*buf;
@@ -307,9 +308,10 @@ xfs_symlink_remote_read(
 
 /* Write the symlink target into the inode. */
 int
-xfs_symlink_write_target(
+__xfs_symlink_write_target(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
+	xfs_ino_t		owner,
 	const char		*target_path,
 	int			pathlen,
 	xfs_fsblock_t		fs_blocks,
@@ -364,8 +366,7 @@ xfs_symlink_write_target(
 		byte_cnt = min(byte_cnt, pathlen);
 
 		buf = bp->b_addr;
-		buf += xfs_symlink_hdr_set(mp, ip->i_ino, offset, byte_cnt,
-				bp);
+		buf += xfs_symlink_hdr_set(mp, owner, offset, byte_cnt, bp);
 
 		memcpy(buf, cur_chunk, byte_cnt);
 
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.h b/fs/xfs/libxfs/xfs_symlink_remote.h
index ac3dac8f617ed..e409d68013360 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.h
+++ b/fs/xfs/libxfs/xfs_symlink_remote.h
@@ -16,12 +16,26 @@ int xfs_symlink_hdr_set(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
 bool xfs_symlink_hdr_ok(xfs_ino_t ino, uint32_t offset,
 			uint32_t size, struct xfs_buf *bp);
 void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
-				 struct xfs_inode *ip, struct xfs_ifork *ifp);
+				 struct xfs_inode *ip, struct xfs_ifork *ifp,
+				 void *priv);
 xfs_failaddr_t xfs_symlink_shortform_verify(void *sfp, int64_t size);
 int xfs_symlink_remote_read(struct xfs_inode *ip, char *link);
-int xfs_symlink_write_target(struct xfs_trans *tp, struct xfs_inode *ip,
-		const char *target_path, int pathlen, xfs_fsblock_t fs_blocks,
-		uint resblks);
+int __xfs_symlink_write_target(struct xfs_trans *tp, struct xfs_inode *ip,
+		xfs_ino_t owner, const char *target_path, int pathlen,
+		xfs_fsblock_t fs_blocks, uint resblks);
+
+static inline int
+xfs_symlink_write_target(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	const char		*target_path,
+	int			pathlen,
+	xfs_fsblock_t		fs_blocks,
+	uint			resblks)
+{
+	return __xfs_symlink_write_target(tp, ip, ip->i_ino, target_path,
+			pathlen, fs_blocks, resblks);
+}
 int xfs_symlink_remote_truncate(struct xfs_trans *tp, struct xfs_inode *ip);
 
 #endif /* __XFS_SYMLINK_REMOTE_H */
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 615137a2039ab..7ee5f7e5bffcb 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -94,6 +94,7 @@ int xrep_setup_xattr(struct xfs_scrub *sc);
 int xrep_setup_directory(struct xfs_scrub *sc);
 int xrep_setup_parent(struct xfs_scrub *sc);
 int xrep_setup_nlinks(struct xfs_scrub *sc);
+int xrep_setup_symlink(struct xfs_scrub *sc, unsigned int *resblks);
 
 /* Repair setup functions */
 int xrep_setup_ag_allocbt(struct xfs_scrub *sc);
@@ -130,6 +131,7 @@ int xrep_fscounters(struct xfs_scrub *sc);
 int xrep_xattr(struct xfs_scrub *sc);
 int xrep_directory(struct xfs_scrub *sc);
 int xrep_parent(struct xfs_scrub *sc);
+int xrep_symlink(struct xfs_scrub *sc);
 
 #ifdef CONFIG_XFS_RT
 int xrep_rtbitmap(struct xfs_scrub *sc);
@@ -206,6 +208,11 @@ xrep_setup_nothing(
 
 #define xrep_setup_inode(sc, imap)	((void)0)
 
+static inline int xrep_setup_symlink(struct xfs_scrub *sc, unsigned int *x)
+{
+	return 0;
+}
+
 #define xrep_revalidate_allocbt		(NULL)
 #define xrep_revalidate_iallocbt	(NULL)
 
@@ -231,6 +238,7 @@ xrep_setup_nothing(
 #define xrep_xattr			xrep_notsupported
 #define xrep_directory			xrep_notsupported
 #define xrep_parent			xrep_notsupported
+#define xrep_symlink			xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 0d35f1f30d9be..df6f5d3474048 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -342,7 +342,7 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.type	= ST_INODE,
 		.setup	= xchk_setup_symlink,
 		.scrub	= xchk_symlink,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_symlink,
 	},
 	[XFS_SCRUB_TYPE_PARENT] = {	/* parent pointers */
 		.type	= ST_INODE,
diff --git a/fs/xfs/scrub/symlink.c b/fs/xfs/scrub/symlink.c
index 7239590c9dd29..7d79ee4767696 100644
--- a/fs/xfs/scrub/symlink.c
+++ b/fs/xfs/scrub/symlink.c
@@ -10,6 +10,7 @@
 #include "xfs_trans_resv.h"
 #include "xfs_mount.h"
 #include "xfs_log_format.h"
+#include "xfs_trans.h"
 #include "xfs_inode.h"
 #include "xfs_symlink.h"
 #include "xfs_health.h"
@@ -17,18 +18,28 @@
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/health.h"
+#include "scrub/repair.h"
 
 /* Set us up to scrub a symbolic link. */
 int
 xchk_setup_symlink(
 	struct xfs_scrub	*sc)
 {
+	unsigned int		resblks = 0;
+	int			error;
+
 	/* Allocate the buffer without the inode lock held. */
 	sc->buf = kvzalloc(XFS_SYMLINK_MAXLEN + 1, XCHK_GFP_FLAGS);
 	if (!sc->buf)
 		return -ENOMEM;
 
-	return xchk_setup_inode_contents(sc, 0);
+	if (xchk_could_repair(sc)) {
+		error = xrep_setup_symlink(sc, &resblks);
+		if (error)
+			return error;
+	}
+
+	return xchk_setup_inode_contents(sc, resblks);
 }
 
 /* Symbolic links. */
diff --git a/fs/xfs/scrub/symlink_repair.c b/fs/xfs/scrub/symlink_repair.c
new file mode 100644
index 0000000000000..60246350ebfc9
--- /dev/null
+++ b/fs/xfs/scrub/symlink_repair.c
@@ -0,0 +1,488 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2018-2024 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_defer.h"
+#include "xfs_btree.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_inode_fork.h"
+#include "xfs_symlink.h"
+#include "xfs_bmap.h"
+#include "xfs_quota.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_trans_space.h"
+#include "xfs_symlink_remote.h"
+#include "xfs_swapext.h"
+#include "xfs_xchgrange.h"
+#include "xfs_health.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/tempfile.h"
+#include "scrub/tempswap.h"
+#include "scrub/reap.h"
+
+/*
+ * Symbolic Link Repair
+ * ====================
+ *
+ * We repair symbolic links by reading whatever target data we can find, up to
+ * the first NULL byte.  Zero length symlinks are turned into links to the
+ * current directory.  The new target is written into a private hidden
+ * temporary file, and then an atomic extent swap commits the new symlink
+ * target to the file being repaired.
+ */
+
+/* Set us up to repair the rtsummary file. */
+int
+xrep_setup_symlink(
+	struct xfs_scrub	*sc,
+	unsigned int		*resblks)
+{
+	struct xfs_mount	*mp = sc->mp;
+	unsigned long long	blocks;
+	int			error;
+
+	error = xrep_tempfile_create(sc, S_IFLNK);
+	if (error)
+		return error;
+
+	/*
+	 * If we're doing a repair, we reserve enough blocks to write out a
+	 * completely new symlink file, plus twice as many blocks as we would
+	 * need if we can only allocate one block per data fork mapping.  This
+	 * should cover the preallocation of the temporary file and swapping
+	 * the extent mappings.
+	 *
+	 * We cannot use xfs_swapext_estimate because we have not yet
+	 * constructed the replacement rtsummary and therefore do not know how
+	 * many extents it will use.  By the time we do, we will have a dirty
+	 * transaction (which we cannot drop because we cannot drop the
+	 * rtsummary ILOCK) and cannot ask for more reservation.
+	 */
+	blocks = xfs_symlink_blocks(sc->mp, XFS_SYMLINK_MAXLEN);
+	blocks += xfs_bmbt_calc_size(mp, blocks) * 2;
+	if (blocks > UINT_MAX)
+		return -EOPNOTSUPP;
+
+	*resblks += blocks;
+	return 0;
+}
+
+/*
+ * Try to salvage the pathname from remote blocks.  Returns the number of bytes
+ * salvaged or a negative errno.
+ */
+STATIC int
+xrep_symlink_salvage_remote(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_bmbt_irec	mval[XFS_SYMLINK_MAPS];
+	struct xfs_inode	*ip = sc->ip;
+	struct xfs_buf		*bp;
+	char			*target_buf = sc->buf;
+	xfs_failaddr_t		fa;
+	xfs_filblks_t		fsblocks;
+	xfs_daddr_t		d;
+	loff_t			len;
+	loff_t			offset = 0;
+	unsigned int		byte_cnt;
+	bool			magic_ok;
+	bool			hdr_ok;
+	int			n;
+	int			nmaps = XFS_SYMLINK_MAPS;
+	int			error;
+
+	/* We'll only read until the buffer is full. */
+	len = min_t(loff_t, ip->i_disk_size, XFS_SYMLINK_MAXLEN);
+	fsblocks = xfs_symlink_blocks(sc->mp, len);
+	error = xfs_bmapi_read(ip, 0, fsblocks, mval, &nmaps, 0);
+	if (error)
+		return error;
+
+	for (n = 0; n < nmaps; n++) {
+		struct xfs_dsymlink_hdr	*dsl;
+
+		d = XFS_FSB_TO_DADDR(sc->mp, mval[n].br_startblock);
+
+		/* Read the rmt block.  We'll run the verifiers manually. */
+		error = xfs_trans_read_buf(sc->mp, sc->tp, sc->mp->m_ddev_targp,
+				d, XFS_FSB_TO_BB(sc->mp, mval[n].br_blockcount),
+				0, &bp, NULL);
+		if (error)
+			return error;
+		bp->b_ops = &xfs_symlink_buf_ops;
+
+		/* How many bytes do we expect to get out of this buffer? */
+		byte_cnt = XFS_FSB_TO_B(sc->mp, mval[n].br_blockcount);
+		byte_cnt = XFS_SYMLINK_BUF_SPACE(sc->mp, byte_cnt);
+		byte_cnt = min_t(unsigned int, byte_cnt, len);
+
+		/*
+		 * See if the verifiers accept this block.  We're willing to
+		 * salvage if the if the offset/byte/ino are ok and either the
+		 * verifier passed or the magic is ok.  Anything else and we
+		 * stop dead in our tracks.
+		 */
+		fa = bp->b_ops->verify_struct(bp);
+		dsl = bp->b_addr;
+		magic_ok = dsl->sl_magic == cpu_to_be32(XFS_SYMLINK_MAGIC);
+		hdr_ok = xfs_symlink_hdr_ok(ip->i_ino, offset, byte_cnt, bp);
+		if (!hdr_ok || (fa != NULL && !magic_ok))
+			break;
+
+		memcpy(target_buf + offset, dsl + 1, byte_cnt);
+
+		len -= byte_cnt;
+		offset += byte_cnt;
+	}
+	return offset;
+}
+
+/*
+ * Try to salvage an inline symlink's contents.  Returns the number of bytes
+ * salvaged or a negative errno.
+ */
+STATIC int
+xrep_symlink_salvage_inline(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_inode	*ip = sc->ip;
+	char			*target_buf = sc->buf;
+	struct xfs_ifork	*ifp;
+	unsigned int		nr;
+
+	ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
+	if (!ifp->if_u1.if_data)
+		return 0;
+
+	/*
+	 * If inode repair zapped the link target, pretend that we didn't find
+	 * any bytes at all so that we can replace the (now totally lost) link
+	 * target with a warning message.
+	 */
+	if (xfs_inode_has_sickness(sc->ip, XFS_SICK_INO_SYMLINK_ZAPPED) &&
+	    sc->ip->i_disk_size == 1 && ifp->if_u1.if_data[0] == '?')
+		return 0;
+
+	nr = min(XFS_SYMLINK_MAXLEN, xfs_inode_data_fork_size(ip));
+	strncpy(target_buf, ifp->if_u1.if_data, nr);
+	return nr;
+}
+
+#define DUMMY_TARGET \
+	"The target of this symbolic link could not be recovered at all and " \
+	"has been replaced with this explanatory message.  To avoid " \
+	"accidentally pointing to an existing file path, this message is " \
+	"longer than the maximum supported file name length.  That is an " \
+	"acceptable length for a symlink target on XFS but will produce " \
+	"File Name Too Long errors if resolved."
+
+/* Salvage whatever we can of the target. */
+STATIC int
+xrep_symlink_salvage(
+	struct xfs_scrub	*sc)
+{
+	char			*target_buf = sc->buf;
+	int			ret;
+
+	BUILD_BUG_ON(sizeof(DUMMY_TARGET) - 1 <= NAME_MAX);
+
+	/* Find whatever we can of the link target. */
+	if (sc->ip->i_df.if_format == XFS_DINODE_FMT_LOCAL)
+		ret = xrep_symlink_salvage_inline(sc);
+	else
+		ret = xrep_symlink_salvage_remote(sc);
+	if (ret < 0)
+		return ret;
+	target_buf[ret] = 0;
+
+	/*
+	 * Change an empty target into a dummy target and clear the symlink
+	 * target zapped flag.
+	 */
+	if (target_buf[0] == 0) {
+		sc->sick_mask |= XFS_SICK_INO_SYMLINK_ZAPPED;
+		sprintf(target_buf, DUMMY_TARGET);
+	}
+
+	trace_xrep_symlink_salvage_target(sc->ip, target_buf,
+					  strlen(target_buf));
+	return 0;
+}
+
+STATIC void
+xrep_symlink_local_to_remote(
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp,
+	struct xfs_inode	*ip,
+	struct xfs_ifork	*ifp,
+	void			*priv)
+{
+	struct xfs_scrub	*sc = priv;
+	struct xfs_dsymlink_hdr	*dsl = bp->b_addr;
+
+	xfs_symlink_local_to_remote(tp, bp, ip, ifp, NULL);
+
+	if (!xfs_has_crc(sc->mp))
+		return;
+
+	dsl->sl_owner = cpu_to_be64(sc->ip->i_ino);
+	xfs_trans_log_buf(tp, bp, 0,
+			  sizeof(struct xfs_dsymlink_hdr) + ifp->if_bytes - 1);
+}
+
+/*
+ * Prepare both links' data forks for extent swapping.  Promote the tempfile
+ * from local format to extents format, and if the file being repaired has a
+ * short format data fork, turn it into an empty extent list.
+ */
+STATIC int
+xrep_symlink_swap_prep(
+	struct xfs_scrub	*sc,
+	bool			temp_local,
+	bool			ip_local)
+{
+	int			error;
+
+	/*
+	 * If the temp link is in shortform format, convert that to a remote
+	 * target so that we can use the atomic extent swap.
+	 */
+	if (temp_local) {
+		int		logflags = XFS_ILOG_CORE;
+
+		error = xfs_bmap_local_to_extents(sc->tp, sc->tempip, 1,
+				&logflags, XFS_DATA_FORK,
+				xrep_symlink_local_to_remote,
+				sc);
+		if (error)
+			return error;
+
+		xfs_trans_log_inode(sc->tp, sc->ip, 0);
+
+		error = xfs_defer_finish(&sc->tp);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * If the file being repaired had a shortform data fork, convert that
+	 * to an empty extent list in preparation for the atomic extent swap.
+	 */
+	if (ip_local) {
+		struct xfs_ifork	*ifp;
+
+		ifp = xfs_ifork_ptr(sc->ip, XFS_DATA_FORK);
+		xfs_idestroy_fork(ifp);
+		ifp->if_format = XFS_DINODE_FMT_EXTENTS;
+		ifp->if_nextents = 0;
+		ifp->if_bytes = 0;
+		ifp->if_u1.if_root = NULL;
+		ifp->if_height = 0;
+
+		xfs_trans_log_inode(sc->tp, sc->ip,
+				XFS_ILOG_CORE | XFS_ILOG_DDATA);
+	}
+
+	return 0;
+}
+
+/* Swap the temporary link's data fork with the one being repaired. */
+STATIC int
+xrep_symlink_swap(
+	struct xfs_scrub	*sc)
+{
+	struct xrep_tempswap	*tx = sc->buf;
+	bool			ip_local, temp_local;
+	int			error;
+
+	ip_local = sc->ip->i_df.if_format == XFS_DINODE_FMT_LOCAL;
+	temp_local = sc->tempip->i_df.if_format == XFS_DINODE_FMT_LOCAL;
+
+	/*
+	 * If the both links have a local format data fork and the rebuilt
+	 * remote data would fit in the repaired file's data fork, copy the
+	 * contents from the tempfile and declare ourselves done.
+	 */
+	if (ip_local && temp_local &&
+	    sc->tempip->i_disk_size <= xfs_inode_data_fork_size(sc->ip)) {
+		xrep_tempfile_copyout_local(sc, XFS_DATA_FORK);
+		return 0;
+	}
+
+	/* Otherwise, make sure both data forks are in block-mapping mode. */
+	error = xrep_symlink_swap_prep(sc, temp_local, ip_local);
+	if (error)
+		return error;
+
+	return xrep_tempswap_contents(sc, tx);
+}
+
+/*
+ * Free all the remote blocks and reset the data fork.  The caller must join
+ * the inode to the transaction.  This function returns with the inode joined
+ * to a clean scrub transaction.
+ */
+STATIC int
+xrep_symlink_reset_fork(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(sc->tempip, XFS_DATA_FORK);
+	int			error;
+
+	/* Unmap all the remote target buffers. */
+	if (xfs_ifork_has_extents(ifp)) {
+		error = xrep_reap_ifork(sc, sc->tempip, XFS_DATA_FORK);
+		if (error)
+			return error;
+	}
+
+	trace_xrep_symlink_reset_fork(sc->tempip);
+
+	/* Reset the temp symlink target to dummy content. */
+	xfs_idestroy_fork(ifp);
+	return xfs_symlink_write_target(sc->tp, sc->tempip, "?", 1, 0, 0);
+}
+
+/*
+ * Reinitialize a link target.  Caller must ensure the inode is joined to
+ * the transaction.
+ */
+STATIC int
+xrep_symlink_rebuild(
+	struct xfs_scrub	*sc)
+{
+	struct xrep_tempswap	*tx;
+	char			*target_buf = sc->buf;
+	xfs_fsblock_t		fs_blocks;
+	unsigned int		target_len;
+	unsigned int		resblks;
+	int			error;
+
+	/* How many blocks do we need? */
+	target_len = strlen(target_buf);
+	ASSERT(target_len != 0);
+	if (target_len == 0 || target_len > XFS_SYMLINK_MAXLEN)
+		return -EFSCORRUPTED;
+
+	trace_xrep_symlink_rebuild(sc->ip);
+
+	/*
+	 * In preparation to write the new symlink target to the temporary
+	 * file, drop the ILOCK of the file being repaired (it shouldn't be
+	 * joined) and take the ILOCK of the temporary file.
+	 *
+	 * The VFS does not take the IOLOCK while reading a symlink (and new
+	 * symlinks are hidden with INEW until they've been written) so it's
+	 * possible that a readlink() could see the old corrupted contents
+	 * while we're doing this.
+	 */
+	xchk_iunlock(sc, XFS_ILOCK_EXCL);
+	xrep_tempfile_ilock(sc);
+	xfs_trans_ijoin(sc->tp, sc->tempip, 0);
+
+	/*
+	 * Reserve resources to reinitialize the target.  We're allowed to
+	 * exceed file quota to repair inconsistent metadata, though this is
+	 * unlikely.
+	 */
+	fs_blocks = xfs_symlink_blocks(sc->mp, target_len);
+	resblks = XFS_SYMLINK_SPACE_RES(sc->mp, target_len, fs_blocks);
+	error = xfs_trans_reserve_quota_nblks(sc->tp, sc->tempip, resblks, 0,
+			true);
+	if (error)
+		return error;
+
+	/* Erase the dummy target set up by the tempfile initialization. */
+	xfs_idestroy_fork(&sc->tempip->i_df);
+	sc->tempip->i_df.if_bytes = 0;
+	sc->tempip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
+
+	/* Write the salvaged target to the temporary link. */
+	error = __xfs_symlink_write_target(sc->tp, sc->tempip, sc->ip->i_ino,
+			target_buf, target_len, fs_blocks, resblks);
+	if (error)
+		return error;
+
+	/*
+	 * Commit the repair transaction so that we can use the atomic extent
+	 * swap helper functions to compute the correct block reservations and
+	 * re-lock the inodes.
+	 */
+	target_buf = NULL;
+	error = xrep_trans_commit(sc);
+	if (error)
+		return error;
+
+	/* Last chance to abort before we start committing fixes. */
+	if (xchk_should_terminate(sc, &error))
+		return error;
+
+	xrep_tempfile_iunlock(sc);
+
+	/*
+	 * We're done with the temporary buffer, so we can reuse it for the
+	 * tempfile swap information.
+	 */
+	tx = sc->buf;
+	error = xrep_tempswap_trans_alloc(sc, XFS_DATA_FORK, tx);
+	if (error)
+		return error;
+
+	/*
+	 * Swap the temp link's data fork with the file being repaired.  This
+	 * recreates the transaction and takes the ILOCKs of the file being
+	 * repaired and the temporary file.
+	 */
+	error = xrep_symlink_swap(sc);
+	if (error)
+		return error;
+
+	/*
+	 * Release the old symlink blocks and reset the data fork of the temp
+	 * link to an empty shortform link.  This is the last repair action we
+	 * perform on the symlink, so we don't need to clean the transaction.
+	 */
+	return xrep_symlink_reset_fork(sc);
+}
+
+/* Repair a symbolic link. */
+int
+xrep_symlink(
+	struct xfs_scrub	*sc)
+{
+	int			error;
+
+	/* The rmapbt is required to reap the old data fork. */
+	if (!xfs_has_rmapbt(sc->mp))
+		return -EOPNOTSUPP;
+
+	ASSERT(sc->ilock_flags & XFS_ILOCK_EXCL);
+
+	error = xrep_symlink_salvage(sc);
+	if (error)
+		return error;
+
+	/* Now reset the target. */
+	error = xrep_symlink_rebuild(sc);
+	if (error)
+		return error;
+
+	return xrep_trans_commit(sc);
+}
diff --git a/fs/xfs/scrub/tempfile.c b/fs/xfs/scrub/tempfile.c
index 49361e03ad8a4..93d8a6b68f442 100644
--- a/fs/xfs/scrub/tempfile.c
+++ b/fs/xfs/scrub/tempfile.c
@@ -21,6 +21,7 @@
 #include "xfs_xchgrange.h"
 #include "xfs_swapext.h"
 #include "xfs_defer.h"
+#include "xfs_symlink_remote.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/repair.h"
@@ -109,6 +110,10 @@ xrep_tempfile_create(
 		error = xfs_dir_init(tp, sc->tempip, dp);
 		if (error)
 			goto out_trans_cancel;
+	} else if (S_ISLNK(VFS_I(sc->tempip)->i_mode)) {
+		error = xfs_symlink_write_target(tp, sc->tempip, ".", 1, 0, 0);
+		if (error)
+			goto out_trans_cancel;
 	}
 
 	/*
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 3766fffd7eb08..18c1a92c1901e 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -2792,6 +2792,52 @@ DEFINE_REPAIR_DENTRY_EVENT(xrep_adoption_check_alias);
 DEFINE_REPAIR_DENTRY_EVENT(xrep_adoption_check_dentry);
 DEFINE_REPAIR_DENTRY_EVENT(xrep_adoption_invalidate_child);
 
+TRACE_EVENT(xrep_symlink_salvage_target,
+	TP_PROTO(struct xfs_inode *ip, char *target, unsigned int targetlen),
+	TP_ARGS(ip, target, targetlen),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(unsigned int, targetlen)
+		__dynamic_array(char, target, targetlen + 1)
+	),
+	TP_fast_assign(
+		__entry->dev = ip->i_mount->m_super->s_dev;
+		__entry->ino = ip->i_ino;
+		__entry->targetlen = targetlen;
+		memcpy(__get_str(target), target, targetlen);
+		__get_str(target)[targetlen] = 0;
+	),
+	TP_printk("dev %d:%d ip 0x%llx target '%.*s'",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->targetlen,
+		  __get_str(target))
+);
+
+DECLARE_EVENT_CLASS(xrep_symlink_class,
+	TP_PROTO(struct xfs_inode *ip),
+	TP_ARGS(ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+	),
+	TP_fast_assign(
+		__entry->dev = ip->i_mount->m_super->s_dev;
+		__entry->ino = ip->i_ino;
+	),
+	TP_printk("dev %d:%d ip 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino)
+);
+
+#define DEFINE_XREP_SYMLINK_EVENT(name) \
+DEFINE_EVENT(xrep_symlink_class, name, \
+	TP_PROTO(struct xfs_inode *ip), \
+	TP_ARGS(ip))
+DEFINE_XREP_SYMLINK_EVENT(xrep_symlink_rebuild);
+DEFINE_XREP_SYMLINK_EVENT(xrep_symlink_reset_fork);
+
 #endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
 
 

[PATCH 1/3] xfs: check AGI unlinked inode buckets

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Look for corruptions in the AGI unlinked bucket chains.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/agheader.c |   40 ++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_inode.c      |    2 +-
 fs/xfs/xfs_inode.h      |    1 +
 3 files changed, 42 insertions(+), 1 deletion(-)


diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index 6c6e5eba42c8b..7fd89889d1d81 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -15,6 +15,7 @@
 #include "xfs_ialloc.h"
 #include "xfs_rmap.h"
 #include "xfs_ag.h"
+#include "xfs_inode.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 
@@ -865,6 +866,43 @@ xchk_agi_xref(
 	/* scrub teardown will take care of sc->sa for us */
 }
 
+/*
+ * Check the unlinked buckets for links to bad inodes.  We hold the AGI, so
+ * there cannot be any threads updating unlinked list pointers in this AG.
+ */
+STATIC void
+xchk_iunlink(
+	struct xfs_scrub	*sc,
+	struct xfs_agi		*agi)
+{
+	unsigned int		i;
+	struct xfs_inode	*ip;
+
+	for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) {
+		xfs_agino_t	agino = be32_to_cpu(agi->agi_unlinked[i]);
+
+		while (agino != NULLAGINO) {
+			if (agino % XFS_AGI_UNLINKED_BUCKETS != i) {
+				xchk_block_set_corrupt(sc, sc->sa.agi_bp);
+				return;
+			}
+
+			ip = xfs_iunlink_lookup(sc->sa.pag, agino);
+			if (!ip) {
+				xchk_block_set_corrupt(sc, sc->sa.agi_bp);
+				return;
+			}
+
+			if (!xfs_inode_on_unlinked_list(ip)) {
+				xchk_block_set_corrupt(sc, sc->sa.agi_bp);
+				return;
+			}
+
+			agino = ip->i_next_unlinked;
+		}
+	}
+}
+
 /* Scrub the AGI. */
 int
 xchk_agi(
@@ -949,6 +987,8 @@ xchk_agi(
 	if (pag->pagi_freecount != be32_to_cpu(agi->agi_freecount))
 		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
+	xchk_iunlink(sc, agi);
+
 	xchk_agi_xref(sc);
 out:
 	return error;
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 9618c014615f5..ea1b0bc9a3410 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1987,7 +1987,7 @@ xfs_inactive(
  * only unlinked, referenced inodes can be on the unlinked inode list.  If we
  * don't find the inode in cache, then let the caller handle the situation.
  */
-static struct xfs_inode *
+struct xfs_inode *
 xfs_iunlink_lookup(
 	struct xfs_perag	*pag,
 	xfs_agino_t		agino)
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 9cee94a0de2c8..8f0dccb0361d7 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -615,6 +615,7 @@ bool xfs_inode_needs_inactive(struct xfs_inode *ip);
 int xfs_iunlink(struct xfs_trans *tp, struct xfs_inode *ip);
 int xfs_iunlink_remove(struct xfs_trans *tp, struct xfs_perag *pag,
 		struct xfs_inode *ip);
+struct xfs_inode *xfs_iunlink_lookup(struct xfs_perag *pag, xfs_agino_t agino);
 
 void xfs_end_io(struct work_struct *work);
 

[PATCH 2/3] xfs: hoist AGI repair context to a heap object

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Save ~460 bytes of stack space by moving all the repair context to a
heap object.  We're going to add even more context data in the next
patch, which is why we really need to do this now.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/agheader_repair.c |  105 ++++++++++++++++++++++++----------------
 1 file changed, 63 insertions(+), 42 deletions(-)


diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c
index 26bd1ff68f1be..ca6df7a0b0721 100644
--- a/fs/xfs/scrub/agheader_repair.c
+++ b/fs/xfs/scrub/agheader_repair.c
@@ -810,15 +810,29 @@ enum {
 	XREP_AGI_MAX
 };
 
+struct xrep_agi {
+	struct xfs_scrub		*sc;
+
+	/* AGI buffer, tracked separately */
+	struct xfs_buf			*agi_bp;
+
+	/* context for finding btree roots */
+	struct xrep_find_ag_btree	fab[XREP_AGI_MAX];
+
+	/* old AGI contents in case we have to revert */
+	struct xfs_agi			old_agi;
+};
+
 /*
  * Given the inode btree roots described by *fab, find the roots, check them
  * for sanity, and pass the root data back out via *fab.
  */
 STATIC int
 xrep_agi_find_btrees(
-	struct xfs_scrub		*sc,
-	struct xrep_find_ag_btree	*fab)
+	struct xrep_agi			*ragi)
 {
+	struct xfs_scrub		*sc = ragi->sc;
+	struct xrep_find_ag_btree	*fab = ragi->fab;
 	struct xfs_buf			*agf_bp;
 	struct xfs_mount		*mp = sc->mp;
 	int				error;
@@ -851,10 +865,11 @@ xrep_agi_find_btrees(
  */
 STATIC void
 xrep_agi_init_header(
-	struct xfs_scrub	*sc,
-	struct xfs_buf		*agi_bp,
-	struct xfs_agi		*old_agi)
+	struct xrep_agi		*ragi)
 {
+	struct xfs_scrub	*sc = ragi->sc;
+	struct xfs_buf		*agi_bp = ragi->agi_bp;
+	struct xfs_agi		*old_agi = &ragi->old_agi;
 	struct xfs_agi		*agi = agi_bp->b_addr;
 	struct xfs_perag	*pag = sc->sa.pag;
 	struct xfs_mount	*mp = sc->mp;
@@ -882,10 +897,12 @@ xrep_agi_init_header(
 /* Set btree root information in an AGI. */
 STATIC void
 xrep_agi_set_roots(
-	struct xfs_scrub		*sc,
-	struct xfs_agi			*agi,
-	struct xrep_find_ag_btree	*fab)
+	struct xrep_agi			*ragi)
 {
+	struct xfs_scrub		*sc = ragi->sc;
+	struct xfs_agi			*agi = ragi->agi_bp->b_addr;
+	struct xrep_find_ag_btree	*fab = ragi->fab;
+
 	agi->agi_root = cpu_to_be32(fab[XREP_AGI_INOBT].root);
 	agi->agi_level = cpu_to_be32(fab[XREP_AGI_INOBT].height);
 
@@ -898,9 +915,10 @@ xrep_agi_set_roots(
 /* Update the AGI counters. */
 STATIC int
 xrep_agi_calc_from_btrees(
-	struct xfs_scrub	*sc,
-	struct xfs_buf		*agi_bp)
+	struct xrep_agi		*ragi)
 {
+	struct xfs_scrub	*sc = ragi->sc;
+	struct xfs_buf		*agi_bp = ragi->agi_bp;
 	struct xfs_btree_cur	*cur;
 	struct xfs_agi		*agi = agi_bp->b_addr;
 	struct xfs_mount	*mp = sc->mp;
@@ -946,9 +964,10 @@ xrep_agi_calc_from_btrees(
 /* Trigger reinitialization of the in-core data. */
 STATIC int
 xrep_agi_commit_new(
-	struct xfs_scrub	*sc,
-	struct xfs_buf		*agi_bp)
+	struct xrep_agi		*ragi)
 {
+	struct xfs_scrub	*sc = ragi->sc;
+	struct xfs_buf		*agi_bp = ragi->agi_bp;
 	struct xfs_perag	*pag;
 	struct xfs_agi		*agi = agi_bp->b_addr;
 
@@ -971,33 +990,36 @@ xrep_agi_commit_new(
 /* Repair the AGI. */
 int
 xrep_agi(
-	struct xfs_scrub		*sc)
+	struct xfs_scrub	*sc)
 {
-	struct xrep_find_ag_btree	fab[XREP_AGI_MAX] = {
-		[XREP_AGI_INOBT] = {
-			.rmap_owner = XFS_RMAP_OWN_INOBT,
-			.buf_ops = &xfs_inobt_buf_ops,
-			.maxlevels = M_IGEO(sc->mp)->inobt_maxlevels,
-		},
-		[XREP_AGI_FINOBT] = {
-			.rmap_owner = XFS_RMAP_OWN_INOBT,
-			.buf_ops = &xfs_finobt_buf_ops,
-			.maxlevels = M_IGEO(sc->mp)->inobt_maxlevels,
-		},
-		[XREP_AGI_END] = {
-			.buf_ops = NULL
-		},
-	};
-	struct xfs_agi			old_agi;
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_buf			*agi_bp;
-	struct xfs_agi			*agi;
-	int				error;
+	struct xrep_agi		*ragi;
+	struct xfs_mount	*mp = sc->mp;
+	int			error;
 
 	/* We require the rmapbt to rebuild anything. */
 	if (!xfs_has_rmapbt(mp))
 		return -EOPNOTSUPP;
 
+	sc->buf = kzalloc(sizeof(struct xrep_agi), XCHK_GFP_FLAGS);
+	if (!sc->buf)
+		return -ENOMEM;
+	ragi = sc->buf;
+	ragi->sc = sc;
+
+	ragi->fab[XREP_AGI_INOBT] = (struct xrep_find_ag_btree){
+		.rmap_owner	= XFS_RMAP_OWN_INOBT,
+		.buf_ops	= &xfs_inobt_buf_ops,
+		.maxlevels	= M_IGEO(sc->mp)->inobt_maxlevels,
+	};
+	ragi->fab[XREP_AGI_FINOBT] = (struct xrep_find_ag_btree){
+		.rmap_owner	= XFS_RMAP_OWN_INOBT,
+		.buf_ops	= &xfs_finobt_buf_ops,
+		.maxlevels	= M_IGEO(sc->mp)->inobt_maxlevels,
+	};
+	ragi->fab[XREP_AGI_END] = (struct xrep_find_ag_btree){
+		.buf_ops	= NULL,
+	};
+
 	/*
 	 * Make sure we have the AGI buffer, as scrub might have decided it
 	 * was corrupt after xfs_ialloc_read_agi failed with -EFSCORRUPTED.
@@ -1005,14 +1027,13 @@ xrep_agi(
 	error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, sc->sa.pag->pag_agno,
 						XFS_AGI_DADDR(mp)),
-			XFS_FSS_TO_BB(mp, 1), 0, &agi_bp, NULL);
+			XFS_FSS_TO_BB(mp, 1), 0, &ragi->agi_bp, NULL);
 	if (error)
 		return error;
-	agi_bp->b_ops = &xfs_agi_buf_ops;
-	agi = agi_bp->b_addr;
+	ragi->agi_bp->b_ops = &xfs_agi_buf_ops;
 
 	/* Find the AGI btree roots. */
-	error = xrep_agi_find_btrees(sc, fab);
+	error = xrep_agi_find_btrees(ragi);
 	if (error)
 		return error;
 
@@ -1021,18 +1042,18 @@ xrep_agi(
 		return error;
 
 	/* Start rewriting the header and implant the btrees we found. */
-	xrep_agi_init_header(sc, agi_bp, &old_agi);
-	xrep_agi_set_roots(sc, agi, fab);
-	error = xrep_agi_calc_from_btrees(sc, agi_bp);
+	xrep_agi_init_header(ragi);
+	xrep_agi_set_roots(ragi);
+	error = xrep_agi_calc_from_btrees(ragi);
 	if (error)
 		goto out_revert;
 
 	/* Reinitialize in-core state. */
-	return xrep_agi_commit_new(sc, agi_bp);
+	return xrep_agi_commit_new(ragi);
 
 out_revert:
 	/* Mark the incore AGI state stale and revert the AGI. */
 	clear_bit(XFS_AGSTATE_AGI_INIT, &sc->sa.pag->pag_opstate);
-	memcpy(agi, &old_agi, sizeof(old_agi));
+	memcpy(ragi->agi_bp->b_addr, &ragi->old_agi, sizeof(struct xfs_agi));
 	return error;
 }

[PATCH 3/3] xfs: repair AGI unlinked inode bucket lists

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Teach the AGI repair code to rebuild the unlinked buckets and lists.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/agheader_repair.c |  774 ++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/agino_bitmap.h    |   49 +++
 fs/xfs/scrub/trace.h           |  255 +++++++++++++
 3 files changed, 1074 insertions(+), 4 deletions(-)
 create mode 100644 fs/xfs/scrub/agino_bitmap.h


diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c
index ca6df7a0b0721..6249a24062b28 100644
--- a/fs/xfs/scrub/agheader_repair.c
+++ b/fs/xfs/scrub/agheader_repair.c
@@ -21,13 +21,18 @@
 #include "xfs_rmap_btree.h"
 #include "xfs_refcount_btree.h"
 #include "xfs_ag.h"
+#include "xfs_inode.h"
+#include "xfs_iunlink_item.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
 #include "scrub/repair.h"
 #include "scrub/bitmap.h"
 #include "scrub/agb_bitmap.h"
+#include "scrub/agino_bitmap.h"
 #include "scrub/reap.h"
+#include "scrub/xfile.h"
+#include "scrub/xfarray.h"
 
 /* Superblock */
 
@@ -810,6 +815,8 @@ enum {
 	XREP_AGI_MAX
 };
 
+#define XREP_AGI_LOOKUP_BATCH		32
+
 struct xrep_agi {
 	struct xfs_scrub		*sc;
 
@@ -821,8 +828,34 @@ struct xrep_agi {
 
 	/* old AGI contents in case we have to revert */
 	struct xfs_agi			old_agi;
+
+	/* bitmap of which inodes are unlinked */
+	struct xagino_bitmap		iunlink_bmp;
+
+	/* heads of the unlinked inode bucket lists */
+	xfs_agino_t			iunlink_heads[XFS_AGI_UNLINKED_BUCKETS];
+
+	/* scratchpad for batched lookups of the radix tree */
+	struct xfs_inode		*lookup_batch[XREP_AGI_LOOKUP_BATCH];
+
+	/* Map of ino -> next_ino for unlinked inode processing. */
+	struct xfarray			*iunlink_next;
+
+	/* Map of ino -> prev_ino for unlinked inode processing. */
+	struct xfarray			*iunlink_prev;
 };
 
+static void
+xrep_agi_buf_cleanup(
+	void		*buf)
+{
+	struct xrep_agi	*ragi = buf;
+
+	xfarray_destroy(ragi->iunlink_prev);
+	xfarray_destroy(ragi->iunlink_next);
+	xagino_bitmap_destroy(&ragi->iunlink_bmp);
+}
+
 /*
  * Given the inode btree roots described by *fab, find the roots, check them
  * for sanity, and pass the root data back out via *fab.
@@ -885,10 +918,6 @@ xrep_agi_init_header(
 	if (xfs_has_crc(mp))
 		uuid_copy(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid);
 
-	/* We don't know how to fix the unlinked list yet. */
-	memcpy(&agi->agi_unlinked, &old_agi->agi_unlinked,
-			sizeof(agi->agi_unlinked));
-
 	/* Mark the incore AGF data stale until we're done fixing things. */
 	ASSERT(xfs_perag_initialised_agi(pag));
 	clear_bit(XFS_AGSTATE_AGI_INIT, &pag->pag_opstate);
@@ -961,6 +990,714 @@ xrep_agi_calc_from_btrees(
 	return error;
 }
 
+/*
+ * Record a forwards unlinked chain pointer from agino -> next_agino in our
+ * staging information.
+ */
+static inline int
+xrep_iunlink_store_next(
+	struct xrep_agi		*ragi,
+	xfs_agino_t		agino,
+	xfs_agino_t		next_agino)
+{
+	ASSERT(next_agino != 0);
+
+	return xfarray_store(ragi->iunlink_next, agino, &next_agino);
+}
+
+/*
+ * Record a backwards unlinked chain pointer from prev_ino <- agino in our
+ * staging information.
+ */
+static inline int
+xrep_iunlink_store_prev(
+	struct xrep_agi		*ragi,
+	xfs_agino_t		agino,
+	xfs_agino_t		prev_agino)
+{
+	ASSERT(prev_agino != 0);
+
+	return xfarray_store(ragi->iunlink_prev, agino, &prev_agino);
+}
+
+/*
+ * Given an @agino, look up the next inode in the iunlink bucket.  Returns
+ * NULLAGINO if we're at the end of the chain, 0 if @agino is not in memory
+ * like it should be, or a per-AG inode number.
+ */
+static inline xfs_agino_t
+xrep_iunlink_next(
+	struct xfs_scrub	*sc,
+	xfs_agino_t		agino)
+{
+	struct xfs_inode	*ip;
+
+	ip = xfs_iunlink_lookup(sc->sa.pag, agino);
+	if (!ip)
+		return 0;
+
+	return ip->i_next_unlinked;
+}
+
+/*
+ * Load the inode @agino into memory, set its i_prev_unlinked, and drop the
+ * inode so it can be inactivated.  Returns NULLAGINO if we're at the end of
+ * the chain or if we should stop walking the chain due to corruption; or a
+ * per-AG inode number.
+ */
+STATIC xfs_agino_t
+xrep_iunlink_reload_next(
+	struct xrep_agi		*ragi,
+	xfs_agino_t		prev_agino,
+	xfs_agino_t		agino)
+{
+	struct xfs_scrub	*sc = ragi->sc;
+	struct xfs_inode	*ip;
+	xfs_ino_t		ino;
+	xfs_agino_t		ret = NULLAGINO;
+	int			error;
+
+	ino = XFS_AGINO_TO_INO(sc->mp, sc->sa.pag->pag_agno, agino);
+	error = xchk_iget(ragi->sc, ino, &ip);
+	if (error)
+		return ret;
+
+	trace_xrep_iunlink_reload_next(ip, prev_agino);
+
+	/* If this is a linked inode, stop processing the chain. */
+	if (VFS_I(ip)->i_nlink != 0) {
+		xrep_iunlink_store_next(ragi, agino, NULLAGINO);
+		goto rele;
+	}
+
+	ip->i_prev_unlinked = prev_agino;
+	ret = ip->i_next_unlinked;
+
+	/*
+	 * Drop the inode reference that we just took.  We hold the AGI, so
+	 * this inode cannot move off the unlinked list and hence cannot be
+	 * reclaimed.
+	 */
+rele:
+	xchk_irele(sc, ip);
+	return ret;
+}
+
+/*
+ * Walk an AGI unlinked bucket's list to load incore any unlinked inodes that
+ * still existed at mount time.  This can happen if iunlink processing fails
+ * during log recovery.
+ */
+STATIC int
+xrep_iunlink_walk_ondisk_bucket(
+	struct xrep_agi		*ragi,
+	unsigned int		bucket)
+{
+	struct xfs_scrub	*sc = ragi->sc;
+	struct xfs_agi		*agi = sc->sa.agi_bp->b_addr;
+	xfs_agino_t		prev_agino = NULLAGINO;
+	xfs_agino_t		next_agino;
+	int			error = 0;
+
+	next_agino = be32_to_cpu(agi->agi_unlinked[bucket]);
+	while (next_agino != NULLAGINO) {
+		xfs_agino_t	agino = next_agino;
+
+		if (xchk_should_terminate(ragi->sc, &error))
+			return error;
+
+		trace_xrep_iunlink_walk_ondisk_bucket(sc->sa.pag, bucket,
+				prev_agino, agino);
+
+		if (bucket != agino % XFS_AGI_UNLINKED_BUCKETS)
+			break;
+
+		next_agino = xrep_iunlink_next(sc, agino);
+		if (!next_agino)
+			next_agino = xrep_iunlink_reload_next(ragi, prev_agino,
+					agino);
+
+		prev_agino = agino;
+	}
+
+	return 0;
+}
+
+/* Decide if this is an unlinked inode in this AG. */
+STATIC bool
+xrep_iunlink_igrab(
+	struct xfs_perag	*pag,
+	struct xfs_inode	*ip)
+{
+	struct xfs_mount	*mp = pag->pag_mount;
+
+	if (XFS_INO_TO_AGNO(mp, ip->i_ino) != pag->pag_agno)
+		return false;
+
+	if (!xfs_inode_on_unlinked_list(ip))
+		return false;
+
+	return true;
+}
+
+/*
+ * Mark the given inode in the lookup batch in our unlinked inode bitmap, and
+ * remember if this inode is the start of the unlinked chain.
+ */
+STATIC int
+xrep_iunlink_visit(
+	struct xrep_agi		*ragi,
+	unsigned int		batch_idx)
+{
+	struct xfs_mount	*mp = ragi->sc->mp;
+	struct xfs_inode	*ip = ragi->lookup_batch[batch_idx];
+	xfs_agino_t		agino;
+	unsigned int		bucket;
+	int			error;
+
+	ASSERT(XFS_INO_TO_AGNO(mp, ip->i_ino) == ragi->sc->sa.pag->pag_agno);
+	ASSERT(xfs_inode_on_unlinked_list(ip));
+
+	agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
+	bucket = agino % XFS_AGI_UNLINKED_BUCKETS;
+
+	trace_xrep_iunlink_visit(ragi->sc->sa.pag, bucket,
+			ragi->iunlink_heads[bucket], ip);
+
+	error = xagino_bitmap_set(&ragi->iunlink_bmp, agino, 1);
+	if (error)
+		return error;
+
+	if (ip->i_prev_unlinked == NULLAGINO) {
+		if (ragi->iunlink_heads[bucket] == NULLAGINO)
+			ragi->iunlink_heads[bucket] = agino;
+	}
+
+	return 0;
+}
+
+/*
+ * Find all incore unlinked inodes so that we can rebuild the unlinked buckets.
+ * We hold the AGI so there should not be any modifications to the unlinked
+ * list.
+ */
+STATIC int
+xrep_iunlink_mark_incore(
+	struct xrep_agi		*ragi)
+{
+	struct xfs_perag	*pag = ragi->sc->sa.pag;
+	struct xfs_mount	*mp = pag->pag_mount;
+	uint32_t		first_index = 0;
+	bool			done = false;
+	unsigned int		nr_found = 0;
+
+	do {
+		unsigned int	i;
+		int		error = 0;
+
+		if (xchk_should_terminate(ragi->sc, &error))
+			return error;
+
+		rcu_read_lock();
+
+		nr_found = radix_tree_gang_lookup(&pag->pag_ici_root,
+				(void **)&ragi->lookup_batch, first_index,
+				XREP_AGI_LOOKUP_BATCH);
+		if (!nr_found) {
+			rcu_read_unlock();
+			return 0;
+		}
+
+		for (i = 0; i < nr_found; i++) {
+			struct xfs_inode *ip = ragi->lookup_batch[i];
+
+			if (done || !xrep_iunlink_igrab(pag, ip))
+				ragi->lookup_batch[i] = NULL;
+
+			/*
+			 * Update the index for the next lookup. Catch
+			 * overflows into the next AG range which can occur if
+			 * we have inodes in the last block of the AG and we
+			 * are currently pointing to the last inode.
+			 *
+			 * Because we may see inodes that are from the wrong AG
+			 * due to RCU freeing and reallocation, only update the
+			 * index if it lies in this AG. It was a race that lead
+			 * us to see this inode, so another lookup from the
+			 * same index will not find it again.
+			 */
+			if (XFS_INO_TO_AGNO(mp, ip->i_ino) != pag->pag_agno)
+				continue;
+			first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
+			if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino))
+				done = true;
+		}
+
+		/* unlock now we've grabbed the inodes. */
+		rcu_read_unlock();
+
+		for (i = 0; i < nr_found; i++) {
+			if (!ragi->lookup_batch[i])
+				continue;
+			error = xrep_iunlink_visit(ragi, i);
+			if (error)
+				return error;
+		}
+	} while (!done);
+
+	return 0;
+}
+
+/* Mark all the unlinked ondisk inodes in this inobt record in iunlink_bmp. */
+STATIC int
+xrep_iunlink_mark_ondisk_rec(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_rec	*rec,
+	void				*priv)
+{
+	struct xfs_inobt_rec_incore	irec;
+	struct xrep_agi			*ragi = priv;
+	struct xfs_scrub		*sc = ragi->sc;
+	struct xfs_mount		*mp = cur->bc_mp;
+	xfs_agino_t			agino;
+	unsigned int			i;
+	int				error = 0;
+
+	xfs_inobt_btrec_to_irec(mp, rec, &irec);
+
+	for (i = 0, agino = irec.ir_startino;
+	     i < XFS_INODES_PER_CHUNK;
+	     i++, agino++) {
+		struct xfs_inode	*ip;
+		unsigned int		len = 1;
+
+		/* Skip free inodes */
+		if (XFS_INOBT_MASK(i) & irec.ir_free)
+			continue;
+		/* Skip inodes we've seen before */
+		if (xagino_bitmap_test(&ragi->iunlink_bmp, agino, &len))
+			continue;
+
+		/*
+		 * Skip incore inodes; these were already picked up by
+		 * the _mark_incore step.
+		 */
+		rcu_read_lock();
+		ip = radix_tree_lookup(&sc->sa.pag->pag_ici_root, agino);
+		rcu_read_unlock();
+		if (ip)
+			continue;
+
+		/*
+		 * Try to look up this inode.  If we can't get it, just move
+		 * on because we haven't actually scrubbed the inobt or the
+		 * inodes yet.
+		 */
+		error = xchk_iget(ragi->sc,
+				XFS_AGINO_TO_INO(mp, sc->sa.pag->pag_agno,
+						 agino),
+				&ip);
+		if (error)
+			continue;
+
+		trace_xrep_iunlink_reload_ondisk(ip);
+
+		if (VFS_I(ip)->i_nlink == 0)
+			error = xagino_bitmap_set(&ragi->iunlink_bmp, agino, 1);
+		xchk_irele(sc, ip);
+		if (error)
+			break;
+	}
+
+	return error;
+}
+
+/*
+ * Find ondisk inodes that are unlinked and not in cache, and mark them in
+ * iunlink_bmp.   We haven't checked the inobt yet, so we don't error out if
+ * the btree is corrupt.
+ */
+STATIC void
+xrep_iunlink_mark_ondisk(
+	struct xrep_agi		*ragi)
+{
+	struct xfs_scrub	*sc = ragi->sc;
+	struct xfs_buf		*agi_bp = ragi->agi_bp;
+	struct xfs_btree_cur	*cur;
+	int			error;
+
+	cur = xfs_inobt_init_cursor(sc->sa.pag, sc->tp, agi_bp, XFS_BTNUM_INO);
+	error = xfs_btree_query_all(cur, xrep_iunlink_mark_ondisk_rec, ragi);
+	xfs_btree_del_cursor(cur, error);
+}
+
+/*
+ * Walk an iunlink bucket's inode list.  For each inode that should be on this
+ * chain, clear its entry in in iunlink_bmp because it's ok and we don't need
+ * to touch it further.
+ */
+STATIC int
+xrep_iunlink_resolve_bucket(
+	struct xrep_agi		*ragi,
+	unsigned int		bucket)
+{
+	struct xfs_scrub	*sc = ragi->sc;
+	struct xfs_inode	*ip;
+	xfs_agino_t		prev_agino = NULLAGINO;
+	xfs_agino_t		next_agino = ragi->iunlink_heads[bucket];
+	int			error = 0;
+
+	while (next_agino != NULLAGINO) {
+		if (xchk_should_terminate(ragi->sc, &error))
+			return error;
+
+		/* Find the next inode in the chain. */
+		ip = xfs_iunlink_lookup(sc->sa.pag, next_agino);
+		if (!ip) {
+			/* Inode not incore?  Terminate the chain. */
+			trace_xrep_iunlink_resolve_uncached(sc->sa.pag,
+					bucket, prev_agino, next_agino);
+
+			next_agino = NULLAGINO;
+			break;
+		}
+
+		if (next_agino % XFS_AGI_UNLINKED_BUCKETS != bucket) {
+			/*
+			 * Inode is in the wrong bucket.  Advance the list,
+			 * but pretend we didn't see this inode.
+			 */
+			trace_xrep_iunlink_resolve_wronglist(sc->sa.pag,
+					bucket, prev_agino, next_agino);
+
+			next_agino = ip->i_next_unlinked;
+			continue;
+		}
+
+		if (!xfs_inode_on_unlinked_list(ip)) {
+			/*
+			 * Incore inode doesn't think this inode is on an
+			 * unlinked list.  This is probably because we reloaded
+			 * it from disk.  Advance the list, but pretend we
+			 * didn't see this inode; we'll fix that later.
+			 */
+			trace_xrep_iunlink_resolve_nolist(sc->sa.pag,
+					bucket, prev_agino, next_agino);
+			next_agino = ip->i_next_unlinked;
+			continue;
+		}
+
+		trace_xrep_iunlink_resolve_ok(sc->sa.pag, bucket, prev_agino,
+				next_agino);
+
+		/*
+		 * Otherwise, this inode's unlinked pointers are ok.  Clear it
+		 * from the unlinked bitmap since we're done with it, and make
+		 * sure the chain is still correct.
+		 */
+		error = xagino_bitmap_clear(&ragi->iunlink_bmp, next_agino, 1);
+		if (error)
+			return error;
+
+		/* Remember the previous inode's next pointer. */
+		if (prev_agino != NULLAGINO) {
+			error = xrep_iunlink_store_next(ragi, prev_agino,
+					next_agino);
+			if (error)
+				return error;
+		}
+
+		/* Remember this inode's previous pointer. */
+		error = xrep_iunlink_store_prev(ragi, next_agino, prev_agino);
+		if (error)
+			return error;
+
+		/* Advance the list and remember this inode. */
+		prev_agino = next_agino;
+		next_agino = ip->i_next_unlinked;
+	}
+
+	/* Update the previous inode's next pointer. */
+	if (prev_agino != NULLAGINO) {
+		error = xrep_iunlink_store_next(ragi, prev_agino, next_agino);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+/* Reinsert this unlinked inode into the head of the staged bucket list. */
+STATIC int
+xrep_iunlink_add_to_bucket(
+	struct xrep_agi		*ragi,
+	xfs_agino_t		agino)
+{
+	xfs_agino_t		current_head;
+	unsigned int		bucket;
+	int			error;
+
+	bucket = agino % XFS_AGI_UNLINKED_BUCKETS;
+
+	/* Point this inode at the current head of the bucket list. */
+	current_head = ragi->iunlink_heads[bucket];
+
+	trace_xrep_iunlink_add_to_bucket(ragi->sc->sa.pag, bucket, agino,
+			current_head);
+
+	error = xrep_iunlink_store_next(ragi, agino, current_head);
+	if (error)
+		return error;
+
+	/* Remember the head inode's previous pointer. */
+	if (current_head != NULLAGINO) {
+		error = xrep_iunlink_store_prev(ragi, current_head, agino);
+		if (error)
+			return error;
+	}
+
+	ragi->iunlink_heads[bucket] = agino;
+	return 0;
+}
+
+/* Reinsert unlinked inodes into the staged iunlink buckets. */
+STATIC int
+xrep_iunlink_add_lost_inodes(
+	uint32_t		start,
+	uint32_t		len,
+	void			*priv)
+{
+	struct xrep_agi		*ragi = priv;
+	int			error;
+
+	for (; len > 0; start++, len--) {
+		error = xrep_iunlink_add_to_bucket(ragi, start);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+/*
+ * Figure out the iunlink bucket values and find inodes that need to be
+ * reinserted into the list.
+ */
+STATIC int
+xrep_iunlink_rebuild_buckets(
+	struct xrep_agi		*ragi)
+{
+	unsigned int		i;
+	int			error;
+
+	/*
+	 * Walk the ondisk AGI unlinked list to find inodes that are on the
+	 * list but aren't in memory.  This can happen if a past log recovery
+	 * tried to clear the iunlinked list but failed.  Our scan rebuilds the
+	 * unlinked list using incore inodes, so we must load and link them
+	 * properly.
+	 */
+	for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) {
+		error = xrep_iunlink_walk_ondisk_bucket(ragi, i);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * Record all the incore unlinked inodes in iunlink_bmp that we didn't
+	 * find by walking the ondisk iunlink buckets.  This shouldn't happen,
+	 * but we can't risk forgetting an inode somewhere.
+	 */
+	error = xrep_iunlink_mark_incore(ragi);
+	if (error)
+		return error;
+
+	/*
+	 * If there are ondisk inodes that are unlinked and are not been loaded
+	 * into cache, record them in iunlink_bmp.
+	 */
+	xrep_iunlink_mark_ondisk(ragi);
+
+	/*
+	 * Walk each iunlink bucket to (re)construct as much of the incore list
+	 * as would be correct.  For each inode that survives this step, mark
+	 * it clear in iunlink_bmp; we're done with those inodes.
+	 */
+	for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) {
+		error = xrep_iunlink_resolve_bucket(ragi, i);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * Any unlinked inodes that we didn't find through the bucket list
+	 * walk (or was ignored by the walk) must be inserted into the bucket
+	 * list.  Stage this in memory for now.
+	 */
+	return xagino_bitmap_walk(&ragi->iunlink_bmp,
+			xrep_iunlink_add_lost_inodes, ragi);
+}
+
+/* Update i_next_iunlinked for the inode @agino. */
+STATIC int
+xrep_iunlink_relink_next(
+	struct xrep_agi		*ragi,
+	xfarray_idx_t		idx,
+	xfs_agino_t		next_agino)
+{
+	struct xfs_scrub	*sc = ragi->sc;
+	struct xfs_perag	*pag = sc->sa.pag;
+	struct xfs_inode	*ip;
+	xfarray_idx_t		agino = idx - 1;
+	bool			want_rele = false;
+	int			error = 0;
+
+	ip = xfs_iunlink_lookup(pag, agino);
+	if (!ip) {
+		xfs_ino_t	ino;
+		xfs_agino_t	prev_agino;
+
+		/*
+		 * No inode exists in cache.  Load it off the disk so that we
+		 * can reinsert it into the incore unlinked list.
+		 */
+		ino = XFS_AGINO_TO_INO(sc->mp, pag->pag_agno, agino);
+		error = xchk_iget(sc, ino, &ip);
+		if (error)
+			return -EFSCORRUPTED;
+
+		want_rele = true;
+
+		/* Set the backward pointer since this just came off disk. */
+		error = xfarray_load(ragi->iunlink_prev, agino, &prev_agino);
+		if (error)
+			goto out_rele;
+
+		trace_xrep_iunlink_relink_prev(ip, prev_agino);
+		ip->i_prev_unlinked = prev_agino;
+	}
+
+	/* Update the forward pointer. */
+	if (ip->i_next_unlinked != next_agino) {
+		error = xfs_iunlink_log_inode(sc->tp, ip, pag, next_agino);
+		if (error)
+			goto out_rele;
+
+		trace_xrep_iunlink_relink_next(ip, next_agino);
+		ip->i_next_unlinked = next_agino;
+	}
+
+out_rele:
+	/*
+	 * The iunlink lookup doesn't igrab because we hold the AGI buffer lock
+	 * and the inode cannot be reclaimed.  However, if we used iget to load
+	 * a missing inode, we must irele it here.
+	 */
+	if (want_rele)
+		xchk_irele(sc, ip);
+	return error;
+}
+
+/* Update i_prev_iunlinked for the inode @agino. */
+STATIC int
+xrep_iunlink_relink_prev(
+	struct xrep_agi		*ragi,
+	xfarray_idx_t		idx,
+	xfs_agino_t		prev_agino)
+{
+	struct xfs_scrub	*sc = ragi->sc;
+	struct xfs_perag	*pag = sc->sa.pag;
+	struct xfs_inode	*ip;
+	xfarray_idx_t		agino = idx - 1;
+	bool			want_rele = false;
+	int			error = 0;
+
+	ASSERT(prev_agino != 0);
+
+	ip = xfs_iunlink_lookup(pag, agino);
+	if (!ip) {
+		xfs_ino_t	ino;
+		xfs_agino_t	next_agino;
+
+		/*
+		 * No inode exists in cache.  Load it off the disk so that we
+		 * can reinsert it into the incore unlinked list.
+		 */
+		ino = XFS_AGINO_TO_INO(sc->mp, pag->pag_agno, agino);
+		error = xchk_iget(sc, ino, &ip);
+		if (error)
+			return -EFSCORRUPTED;
+
+		want_rele = true;
+
+		/* Set the forward pointer since this just came off disk. */
+		error = xfarray_load(ragi->iunlink_prev, agino, &next_agino);
+		if (error)
+			goto out_rele;
+
+		error = xfs_iunlink_log_inode(sc->tp, ip, pag, next_agino);
+		if (error)
+			goto out_rele;
+
+		trace_xrep_iunlink_relink_next(ip, next_agino);
+		ip->i_next_unlinked = next_agino;
+	}
+
+	/* Update the backward pointer. */
+	if (ip->i_prev_unlinked != prev_agino) {
+		trace_xrep_iunlink_relink_prev(ip, prev_agino);
+		ip->i_prev_unlinked = prev_agino;
+	}
+
+out_rele:
+	/*
+	 * The iunlink lookup doesn't igrab because we hold the AGI buffer lock
+	 * and the inode cannot be reclaimed.  However, if we used iget to load
+	 * a missing inode, we must irele it here.
+	 */
+	if (want_rele)
+		xchk_irele(sc, ip);
+	return error;
+}
+
+/* Log all the iunlink updates we need to finish regenerating the AGI. */
+STATIC int
+xrep_iunlink_commit(
+	struct xrep_agi		*ragi)
+{
+	struct xfs_agi		*agi = ragi->agi_bp->b_addr;
+	xfarray_idx_t		idx = XFARRAY_CURSOR_INIT;
+	xfs_agino_t		agino;
+	unsigned int		i;
+	int			error;
+
+	/* Fix all the forward links */
+	while ((error = xfarray_iter(ragi->iunlink_next, &idx, &agino)) == 1) {
+		error = xrep_iunlink_relink_next(ragi, idx, agino);
+		if (error)
+			return error;
+	}
+
+	/* Fix all the back links */
+	idx = XFARRAY_CURSOR_INIT;
+	while ((error = xfarray_iter(ragi->iunlink_prev, &idx, &agino)) == 1) {
+		error = xrep_iunlink_relink_prev(ragi, idx, agino);
+		if (error)
+			return error;
+	}
+
+	/* Copy the staged iunlink buckets to the new AGI. */
+	for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) {
+		trace_xrep_iunlink_commit_bucket(ragi->sc->sa.pag, i,
+				be32_to_cpu(ragi->old_agi.agi_unlinked[i]),
+				ragi->iunlink_heads[i]);
+
+		agi->agi_unlinked[i] = cpu_to_be32(ragi->iunlink_heads[i]);
+	}
+
+	return 0;
+}
+
 /* Trigger reinitialization of the in-core data. */
 STATIC int
 xrep_agi_commit_new(
@@ -994,6 +1731,8 @@ xrep_agi(
 {
 	struct xrep_agi		*ragi;
 	struct xfs_mount	*mp = sc->mp;
+	char			*descr;
+	unsigned int		i;
 	int			error;
 
 	/* We require the rmapbt to rebuild anything. */
@@ -1020,6 +1759,26 @@ xrep_agi(
 		.buf_ops	= NULL,
 	};
 
+	for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++)
+		ragi->iunlink_heads[i] = NULLAGINO;
+
+	xagino_bitmap_init(&ragi->iunlink_bmp);
+	sc->buf_cleanup = xrep_agi_buf_cleanup;
+
+	descr = xchk_xfile_ag_descr(sc, "iunlinked next pointers");
+	error = xfarray_create(descr, 0, sizeof(xfs_agino_t),
+			&ragi->iunlink_next);
+	kfree(descr);
+	if (error)
+		return error;
+
+	descr = xchk_xfile_ag_descr(sc, "iunlinked prev pointers");
+	error = xfarray_create(descr, 0, sizeof(xfs_agino_t),
+			&ragi->iunlink_prev);
+	kfree(descr);
+	if (error)
+		return error;
+
 	/*
 	 * Make sure we have the AGI buffer, as scrub might have decided it
 	 * was corrupt after xfs_ialloc_read_agi failed with -EFSCORRUPTED.
@@ -1037,6 +1796,10 @@ xrep_agi(
 	if (error)
 		return error;
 
+	error = xrep_iunlink_rebuild_buckets(ragi);
+	if (error)
+		return error;
+
 	/* Last chance to abort before we start committing fixes. */
 	if (xchk_should_terminate(sc, &error))
 		return error;
@@ -1045,6 +1808,9 @@ xrep_agi(
 	xrep_agi_init_header(ragi);
 	xrep_agi_set_roots(ragi);
 	error = xrep_agi_calc_from_btrees(ragi);
+	if (error)
+		goto out_revert;
+	error = xrep_iunlink_commit(ragi);
 	if (error)
 		goto out_revert;
 
diff --git a/fs/xfs/scrub/agino_bitmap.h b/fs/xfs/scrub/agino_bitmap.h
new file mode 100644
index 0000000000000..56d7db5f16999
--- /dev/null
+++ b/fs/xfs/scrub/agino_bitmap.h
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2018-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SCRUB_AGINO_BITMAP_H__
+#define __XFS_SCRUB_AGINO_BITMAP_H__
+
+/* Bitmaps, but for type-checked for xfs_agino_t */
+
+struct xagino_bitmap {
+	struct xbitmap32	aginobitmap;
+};
+
+static inline void xagino_bitmap_init(struct xagino_bitmap *bitmap)
+{
+	xbitmap32_init(&bitmap->aginobitmap);
+}
+
+static inline void xagino_bitmap_destroy(struct xagino_bitmap *bitmap)
+{
+	xbitmap32_destroy(&bitmap->aginobitmap);
+}
+
+static inline int xagino_bitmap_clear(struct xagino_bitmap *bitmap,
+		xfs_agino_t agino, unsigned int len)
+{
+	return xbitmap32_clear(&bitmap->aginobitmap, agino, len);
+}
+
+static inline int xagino_bitmap_set(struct xagino_bitmap *bitmap,
+		xfs_agino_t agino, unsigned int len)
+{
+	return xbitmap32_set(&bitmap->aginobitmap, agino, len);
+}
+
+static inline bool xagino_bitmap_test(struct xagino_bitmap *bitmap,
+		xfs_agino_t agino, unsigned int *len)
+{
+	return xbitmap32_test(&bitmap->aginobitmap, agino, len);
+}
+
+static inline int xagino_bitmap_walk(struct xagino_bitmap *bitmap,
+		xbitmap32_walk_fn fn, void *priv)
+{
+	return xbitmap32_walk(&bitmap->aginobitmap, fn, priv);
+}
+
+#endif	/* __XFS_SCRUB_AGINO_BITMAP_H__ */
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 18c1a92c1901e..3aa1ef6a371dd 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -2838,6 +2838,261 @@ DEFINE_EVENT(xrep_symlink_class, name, \
 DEFINE_XREP_SYMLINK_EVENT(xrep_symlink_rebuild);
 DEFINE_XREP_SYMLINK_EVENT(xrep_symlink_reset_fork);
 
+TRACE_EVENT(xrep_iunlink_visit,
+	TP_PROTO(struct xfs_perag *pag, unsigned int bucket,
+		 xfs_agino_t bucket_agino, struct xfs_inode *ip),
+	TP_ARGS(pag, bucket, bucket_agino, ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agino_t, agino)
+		__field(unsigned int, bucket)
+		__field(xfs_agino_t, bucket_agino)
+		__field(xfs_agino_t, prev_agino)
+		__field(xfs_agino_t, next_agino)
+	),
+	TP_fast_assign(
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
+		__entry->agino = XFS_INO_TO_AGINO(pag->pag_mount, ip->i_ino);
+		__entry->bucket = bucket;
+		__entry->bucket_agino = bucket_agino;
+		__entry->prev_agino = ip->i_prev_unlinked;
+		__entry->next_agino = ip->i_next_unlinked;
+	),
+	TP_printk("dev %d:%d agno 0x%x bucket %u agino 0x%x bucket_agino 0x%x prev_agino 0x%x next_agino 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->bucket,
+		  __entry->agino,
+		  __entry->bucket_agino,
+		  __entry->prev_agino,
+		  __entry->next_agino)
+);
+
+TRACE_EVENT(xrep_iunlink_reload_next,
+	TP_PROTO(struct xfs_inode *ip, xfs_agino_t prev_agino),
+	TP_ARGS(ip, prev_agino),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agino_t, agino)
+		__field(xfs_agino_t, old_prev_agino)
+		__field(xfs_agino_t, prev_agino)
+		__field(xfs_agino_t, next_agino)
+		__field(unsigned int, nlink)
+	),
+	TP_fast_assign(
+		__entry->dev = ip->i_mount->m_super->s_dev;
+		__entry->agno = XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino);
+		__entry->agino = XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino);
+		__entry->old_prev_agino = ip->i_prev_unlinked;
+		__entry->prev_agino = prev_agino;
+		__entry->next_agino = ip->i_next_unlinked;
+		__entry->nlink = VFS_I(ip)->i_nlink;
+	),
+	TP_printk("dev %d:%d agno 0x%x bucket %u agino 0x%x nlink %u old_prev_agino %u prev_agino 0x%x next_agino 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->agino % XFS_AGI_UNLINKED_BUCKETS,
+		  __entry->agino,
+		  __entry->nlink,
+		  __entry->old_prev_agino,
+		  __entry->prev_agino,
+		  __entry->next_agino)
+);
+
+TRACE_EVENT(xrep_iunlink_reload_ondisk,
+	TP_PROTO(struct xfs_inode *ip),
+	TP_ARGS(ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agino_t, agino)
+		__field(unsigned int, nlink)
+		__field(xfs_agino_t, next_agino)
+	),
+	TP_fast_assign(
+		__entry->dev = ip->i_mount->m_super->s_dev;
+		__entry->agno = XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino);
+		__entry->agino = XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino);
+		__entry->nlink = VFS_I(ip)->i_nlink;
+		__entry->next_agino = ip->i_next_unlinked;
+	),
+	TP_printk("dev %d:%d agno 0x%x bucket %u agino 0x%x nlink %u next_agino 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->agino % XFS_AGI_UNLINKED_BUCKETS,
+		  __entry->agino,
+		  __entry->nlink,
+		  __entry->next_agino)
+);
+
+TRACE_EVENT(xrep_iunlink_walk_ondisk_bucket,
+	TP_PROTO(struct xfs_perag *pag, unsigned int bucket,
+		 xfs_agino_t prev_agino, xfs_agino_t next_agino),
+	TP_ARGS(pag, bucket, prev_agino, next_agino),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(unsigned int, bucket)
+		__field(xfs_agino_t, prev_agino)
+		__field(xfs_agino_t, next_agino)
+	),
+	TP_fast_assign(
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
+		__entry->bucket = bucket;
+		__entry->prev_agino = prev_agino;
+		__entry->next_agino = next_agino;
+	),
+	TP_printk("dev %d:%d agno 0x%x bucket %u prev_agino 0x%x next_agino 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->bucket,
+		  __entry->prev_agino,
+		  __entry->next_agino)
+);
+
+DECLARE_EVENT_CLASS(xrep_iunlink_resolve_class,
+	TP_PROTO(struct xfs_perag *pag, unsigned int bucket,
+		 xfs_agino_t prev_agino, xfs_agino_t next_agino),
+	TP_ARGS(pag, bucket, prev_agino, next_agino),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(unsigned int, bucket)
+		__field(xfs_agino_t, prev_agino)
+		__field(xfs_agino_t, next_agino)
+	),
+	TP_fast_assign(
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
+		__entry->bucket = bucket;
+		__entry->prev_agino = prev_agino;
+		__entry->next_agino = next_agino;
+	),
+	TP_printk("dev %d:%d agno 0x%x bucket %u prev_agino 0x%x next_agino 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->bucket,
+		  __entry->prev_agino,
+		  __entry->next_agino)
+);
+#define DEFINE_REPAIR_IUNLINK_RESOLVE_EVENT(name) \
+DEFINE_EVENT(xrep_iunlink_resolve_class, name, \
+	TP_PROTO(struct xfs_perag *pag, unsigned int bucket, \
+		 xfs_agino_t prev_agino, xfs_agino_t next_agino), \
+	TP_ARGS(pag, bucket, prev_agino, next_agino))
+DEFINE_REPAIR_IUNLINK_RESOLVE_EVENT(xrep_iunlink_resolve_uncached);
+DEFINE_REPAIR_IUNLINK_RESOLVE_EVENT(xrep_iunlink_resolve_wronglist);
+DEFINE_REPAIR_IUNLINK_RESOLVE_EVENT(xrep_iunlink_resolve_nolist);
+DEFINE_REPAIR_IUNLINK_RESOLVE_EVENT(xrep_iunlink_resolve_ok);
+
+TRACE_EVENT(xrep_iunlink_relink_next,
+	TP_PROTO(struct xfs_inode *ip, xfs_agino_t next_agino),
+	TP_ARGS(ip, next_agino),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agino_t, agino)
+		__field(xfs_agino_t, next_agino)
+		__field(xfs_agino_t, new_next_agino)
+	),
+	TP_fast_assign(
+		__entry->dev = ip->i_mount->m_super->s_dev;
+		__entry->agno = XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino);
+		__entry->agino = XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino);
+		__entry->next_agino = ip->i_next_unlinked;
+		__entry->new_next_agino = next_agino;
+	),
+	TP_printk("dev %d:%d agno 0x%x bucket %u agino 0x%x next_agino 0x%x -> 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->agino % XFS_AGI_UNLINKED_BUCKETS,
+		  __entry->agino,
+		  __entry->next_agino,
+		  __entry->new_next_agino)
+);
+
+TRACE_EVENT(xrep_iunlink_relink_prev,
+	TP_PROTO(struct xfs_inode *ip, xfs_agino_t prev_agino),
+	TP_ARGS(ip, prev_agino),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agino_t, agino)
+		__field(xfs_agino_t, prev_agino)
+		__field(xfs_agino_t, new_prev_agino)
+	),
+	TP_fast_assign(
+		__entry->dev = ip->i_mount->m_super->s_dev;
+		__entry->agno = XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino);
+		__entry->agino = XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino);
+		__entry->prev_agino = ip->i_prev_unlinked;
+		__entry->new_prev_agino = prev_agino;
+	),
+	TP_printk("dev %d:%d agno 0x%x bucket %u agino 0x%x prev_agino 0x%x -> 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->agino % XFS_AGI_UNLINKED_BUCKETS,
+		  __entry->agino,
+		  __entry->prev_agino,
+		  __entry->new_prev_agino)
+);
+
+TRACE_EVENT(xrep_iunlink_add_to_bucket,
+	TP_PROTO(struct xfs_perag *pag, unsigned int bucket,
+		 xfs_agino_t agino, xfs_agino_t curr_head),
+	TP_ARGS(pag, bucket, agino, curr_head),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(unsigned int, bucket)
+		__field(xfs_agino_t, agino)
+		__field(xfs_agino_t, next_agino)
+	),
+	TP_fast_assign(
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
+		__entry->bucket = bucket;
+		__entry->agino = agino;
+		__entry->next_agino = curr_head;
+	),
+	TP_printk("dev %d:%d agno 0x%x bucket %u agino 0x%x next_agino 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->bucket,
+		  __entry->agino,
+		  __entry->next_agino)
+);
+
+TRACE_EVENT(xrep_iunlink_commit_bucket,
+	TP_PROTO(struct xfs_perag *pag, unsigned int bucket,
+		 xfs_agino_t old_agino, xfs_agino_t agino),
+	TP_ARGS(pag, bucket, old_agino, agino),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(unsigned int, bucket)
+		__field(xfs_agino_t, old_agino)
+		__field(xfs_agino_t, agino)
+	),
+	TP_fast_assign(
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
+		__entry->bucket = bucket;
+		__entry->old_agino = old_agino;
+		__entry->agino = agino;
+	),
+	TP_printk("dev %d:%d agno 0x%x bucket %u agino 0x%x -> 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->bucket,
+		  __entry->old_agino,
+		  __entry->agino)
+);
+
 #endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
 
 

[PATCH 1/3] xfs: map xfile pages directly into xfs_buf

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Map the xfile pages directly into xfs_buf to reduce memory overhead.
It's silly to use memory to stage changes to shmem pages for ephemeral
btrees that don't care about transactionality.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_btree_mem.h  |    6 ++
 fs/xfs/libxfs/xfs_rmap_btree.c |    1 
 fs/xfs/scrub/rcbag_btree.c     |    1 
 fs/xfs/scrub/xfbtree.c         |   23 +++++-
 fs/xfs/xfs_buf.c               |  110 ++++++++++++++++++++++-------
 fs/xfs/xfs_buf.h               |   16 ++++
 fs/xfs/xfs_buf_xfile.c         |  152 ++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_buf_xfile.h         |   11 +++
 8 files changed, 292 insertions(+), 28 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_btree_mem.h b/fs/xfs/libxfs/xfs_btree_mem.h
index 1f961f3f55444..cfb30cb1aabc6 100644
--- a/fs/xfs/libxfs/xfs_btree_mem.h
+++ b/fs/xfs/libxfs/xfs_btree_mem.h
@@ -17,8 +17,14 @@ struct xfbtree_config {
 
 	/* Owner of this btree. */
 	unsigned long long		owner;
+
+	/* XFBTREE_* flags */
+	unsigned int			flags;
 };
 
+/* buffers should be directly mapped from memory */
+#define XFBTREE_DIRECT_MAP		(1U << 0)
+
 #ifdef CONFIG_XFS_BTREE_IN_XFILE
 unsigned int xfs_btree_mem_head_nlevels(struct xfs_buf *head_bp);
 
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index 23841ee6e2ff6..71d32f9fee14d 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -672,6 +672,7 @@ xfs_rmapbt_mem_create(
 		.btree_ops	= &xfs_rmapbt_mem_ops,
 		.target		= target,
 		.owner		= agno,
+		.flags		= XFBTREE_DIRECT_MAP,
 	};
 
 	return xfbtree_create(mp, &cfg, xfbtreep);
diff --git a/fs/xfs/scrub/rcbag_btree.c b/fs/xfs/scrub/rcbag_btree.c
index 3d66e80b7bc25..9807e08129fe4 100644
--- a/fs/xfs/scrub/rcbag_btree.c
+++ b/fs/xfs/scrub/rcbag_btree.c
@@ -233,6 +233,7 @@ rcbagbt_mem_create(
 	struct xfbtree_config	cfg = {
 		.btree_ops	= &rcbagbt_mem_ops,
 		.target		= target,
+		.flags		= XFBTREE_DIRECT_MAP,
 	};
 
 	return xfbtree_create(mp, &cfg, xfbtreep);
diff --git a/fs/xfs/scrub/xfbtree.c b/fs/xfs/scrub/xfbtree.c
index 016026947019a..9e557d87d1c9c 100644
--- a/fs/xfs/scrub/xfbtree.c
+++ b/fs/xfs/scrub/xfbtree.c
@@ -501,6 +501,9 @@ xfbtree_create(
 	if (!xfbt)
 		return -ENOMEM;
 	xfbt->target = cfg->target;
+	if (cfg->flags & XFBTREE_DIRECT_MAP)
+		xfbt->target->bt_flags |= XFS_BUFTARG_DIRECT_MAP;
+
 	xfboff_bitmap_init(&xfbt->freespace);
 
 	/* Set up min/maxrecs for this btree. */
@@ -753,7 +756,7 @@ xfbtree_trans_commit(
 
 		dirty = xfbtree_trans_bdetach(tp, bp);
 		if (dirty && !corrupt) {
-			xfs_failaddr_t	fa = bp->b_ops->verify_struct(bp);
+			xfs_failaddr_t	fa;
 
 			/*
 			 * Because this btree is ephemeral, validate the buffer
@@ -761,16 +764,30 @@ xfbtree_trans_commit(
 			 * corruption errors to the caller without shutting
 			 * down the filesystem.
 			 *
+			 * Buffers that are directly mapped to the xfile do not
+			 * need to be queued for IO at all.  Check if the DRAM
+			 * has been poisoned, however.
+			 *
 			 * If the buffer fails verification, log the failure
 			 * but continue walking the transaction items so that
 			 * we remove all ephemeral btree buffers.
 			 */
+			if (xfs_buf_check_poisoned(bp)) {
+				corrupt = true;
+				xfs_verifier_error(bp, -EFSCORRUPTED,
+						__this_address);
+				continue;
+			}
+
+			fa = bp->b_ops->verify_struct(bp);
 			if (fa) {
 				corrupt = true;
 				xfs_verifier_error(bp, -EFSCORRUPTED, fa);
-			} else {
+				continue;
+			}
+
+			if (!(bp->b_flags & _XBF_DIRECT_MAP))
 				xfs_buf_delwri_queue_here(bp, &buffer_list);
-			}
 		}
 
 		xfs_buf_relse(bp);
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index b62518968e784..ca7657d0ea592 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -280,19 +280,26 @@ xfs_buf_free_pages(
 
 	ASSERT(bp->b_flags & _XBF_PAGES);
 
-	if (xfs_buf_is_vmapped(bp))
-		vm_unmap_ram(bp->b_addr, bp->b_page_count);
-
 	for (i = 0; i < bp->b_page_count; i++) {
 		if (bp->b_pages[i])
 			__free_page(bp->b_pages[i]);
 	}
 	mm_account_reclaimed_pages(bp->b_page_count);
 
+	xfs_buf_free_page_array(bp);
+}
+
+void
+xfs_buf_free_page_array(
+	struct xfs_buf	*bp)
+{
+	ASSERT(bp->b_flags & _XBF_PAGES);
+
 	if (bp->b_pages != bp->b_page_array)
 		kmem_free(bp->b_pages);
 	bp->b_pages = NULL;
 	bp->b_flags &= ~_XBF_PAGES;
+	bp->b_page_count = 0;
 }
 
 static void
@@ -313,7 +320,12 @@ xfs_buf_free(
 
 	ASSERT(list_empty(&bp->b_lru));
 
-	if (bp->b_flags & _XBF_PAGES)
+	if (xfs_buf_is_vmapped(bp))
+		vm_unmap_ram(bp->b_addr, bp->b_page_count);
+
+	if (bp->b_flags & _XBF_DIRECT_MAP)
+		xfile_buf_unmap_pages(bp);
+	else if (bp->b_flags & _XBF_PAGES)
 		xfs_buf_free_pages(bp);
 	else if (bp->b_flags & _XBF_KMEM)
 		kmem_free(bp->b_addr);
@@ -352,20 +364,14 @@ xfs_buf_alloc_kmem(
 	return 0;
 }
 
-static int
-xfs_buf_alloc_pages(
+/* Make sure that we have a page list */
+int
+xfs_buf_alloc_page_array(
 	struct xfs_buf	*bp,
-	xfs_buf_flags_t	flags)
+	gfp_t		gfp_mask)
 {
-	gfp_t		gfp_mask = __GFP_NOWARN;
-	long		filled = 0;
+	ASSERT(!(bp->b_flags & _XBF_PAGES));
 
-	if (flags & XBF_READ_AHEAD)
-		gfp_mask |= __GFP_NORETRY;
-	else
-		gfp_mask |= GFP_NOFS;
-
-	/* Make sure that we have a page list */
 	bp->b_page_count = DIV_ROUND_UP(BBTOB(bp->b_length), PAGE_SIZE);
 	if (bp->b_page_count <= XB_PAGES) {
 		bp->b_pages = bp->b_page_array;
@@ -375,7 +381,28 @@ xfs_buf_alloc_pages(
 		if (!bp->b_pages)
 			return -ENOMEM;
 	}
+
 	bp->b_flags |= _XBF_PAGES;
+	return 0;
+}
+
+static int
+xfs_buf_alloc_pages(
+	struct xfs_buf	*bp,
+	xfs_buf_flags_t	flags)
+{
+	gfp_t		gfp_mask = __GFP_NOWARN;
+	long		filled = 0;
+	int		error;
+
+	if (flags & XBF_READ_AHEAD)
+		gfp_mask |= __GFP_NORETRY;
+	else
+		gfp_mask |= GFP_NOFS;
+
+	error = xfs_buf_alloc_page_array(bp, gfp_mask);
+	if (error)
+		return error;
 
 	/* Assure zeroed buffer for non-read cases. */
 	if (!(flags & XBF_READ))
@@ -418,7 +445,8 @@ _xfs_buf_map_pages(
 	struct xfs_buf		*bp,
 	xfs_buf_flags_t		flags)
 {
-	ASSERT(bp->b_flags & _XBF_PAGES);
+	ASSERT(bp->b_flags & (_XBF_PAGES | _XBF_DIRECT_MAP));
+
 	if (bp->b_page_count == 1) {
 		/* A single page buffer is always mappable */
 		bp->b_addr = page_address(bp->b_pages[0]);
@@ -569,7 +597,7 @@ xfs_buf_find_lock(
 			return -ENOENT;
 		}
 		ASSERT((bp->b_flags & _XBF_DELWRI_Q) == 0);
-		bp->b_flags &= _XBF_KMEM | _XBF_PAGES;
+		bp->b_flags &= _XBF_KMEM | _XBF_PAGES | _XBF_DIRECT_MAP;
 		bp->b_ops = NULL;
 	}
 	return 0;
@@ -628,18 +656,36 @@ xfs_buf_find_insert(
 		goto out_drop_pag;
 
 	/*
-	 * For buffers that fit entirely within a single page, first attempt to
-	 * allocate the memory from the heap to minimise memory usage. If we
-	 * can't get heap memory for these small buffers, we fall back to using
-	 * the page allocator.
+	 * If the caller is ok with direct maps to xfile pages, try that.
+	 * ENOTBLK is the magic code to fall back to allocating memory.
 	 */
-	if (BBTOB(new_bp->b_length) >= PAGE_SIZE ||
-	    xfs_buf_alloc_kmem(new_bp, flags) < 0) {
-		error = xfs_buf_alloc_pages(new_bp, flags);
-		if (error)
+	if (xfile_buftarg_can_direct_map(btp)) {
+		error = xfile_buf_map_pages(new_bp, flags);
+		if (error && error != -ENOTBLK)
 			goto out_free_buf;
+		if (!error)
+			goto insert;
 	}
 
+	/*
+	 * For buffers that fit entirely within a single page, first attempt to
+	 * allocate the memory from the heap to minimise memory usage.
+	 */
+	if (BBTOB(new_bp->b_length) < PAGE_SIZE) {
+		error = xfs_buf_alloc_kmem(new_bp, flags);
+		if (!error)
+			goto insert;
+	}
+
+	/*
+	 * For larger buffers or if we can't get heap memory for these small
+	 * buffers, fall back to using the page allocator.
+	 */
+	error = xfs_buf_alloc_pages(new_bp, flags);
+	if (error)
+		goto out_free_buf;
+
+insert:
 	spin_lock(&bch->bc_lock);
 	bp = rhashtable_lookup_get_insert_fast(&bch->bc_hash,
 			&new_bp->b_rhash_head, xfs_buf_hash_params);
@@ -1584,6 +1630,20 @@ xfs_buf_end_sync_io(
 		xfs_buf_ioend(bp);
 }
 
+bool
+xfs_buf_check_poisoned(
+	struct xfs_buf		*bp)
+{
+	unsigned int		i;
+
+	for (i = 0; i < bp->b_page_count; i++) {
+		if (PageHWPoison(bp->b_pages[i]))
+			return true;
+	}
+
+	return false;
+}
+
 STATIC void
 _xfs_buf_ioapply(
 	struct xfs_buf	*bp)
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 5a6cf3d5a9f53..9d05c376d9dd8 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -43,6 +43,11 @@ struct xfile;
 #define _XBF_PAGES	 (1u << 20)/* backed by refcounted pages */
 #define _XBF_KMEM	 (1u << 21)/* backed by heap memory */
 #define _XBF_DELWRI_Q	 (1u << 22)/* buffer on a delwri queue */
+#ifdef CONFIG_XFS_IN_MEMORY_FILE
+# define _XBF_DIRECT_MAP (1u << 23)/* pages directly mapped to storage */
+#else
+# define _XBF_DIRECT_MAP (0)
+#endif
 
 /* flags used only as arguments to access routines */
 /*
@@ -72,6 +77,7 @@ typedef unsigned int xfs_buf_flags_t;
 	{ _XBF_PAGES,		"PAGES" }, \
 	{ _XBF_KMEM,		"KMEM" }, \
 	{ _XBF_DELWRI_Q,	"DELWRI_Q" }, \
+	{ _XBF_DIRECT_MAP,	"DIRECT_MAP" }, \
 	/* The following interface flags should never be set */ \
 	{ XBF_LIVESCAN,		"LIVESCAN" }, \
 	{ XBF_INCORE,		"INCORE" }, \
@@ -131,8 +137,14 @@ typedef struct xfs_buftarg {
 #ifdef CONFIG_XFS_IN_MEMORY_FILE
 /* in-memory buftarg via bt_xfile */
 # define XFS_BUFTARG_XFILE	(1U << 0)
+/*
+ * Buffer pages are direct-mapped to the xfile; caller does not care about
+ * transactional updates.
+ */
+# define XFS_BUFTARG_DIRECT_MAP	(1U << 1)
 #else
 # define XFS_BUFTARG_XFILE	(0)
+# define XFS_BUFTARG_DIRECT_MAP	(0)
 #endif
 
 #define XB_PAGES	2
@@ -382,6 +394,9 @@ xfs_buf_update_cksum(struct xfs_buf *bp, unsigned long cksum_offset)
 			 cksum_offset);
 }
 
+int xfs_buf_alloc_page_array(struct xfs_buf *bp, gfp_t gfp_mask);
+void xfs_buf_free_page_array(struct xfs_buf *bp);
+
 /*
  *	Handling of buftargs.
  */
@@ -453,5 +468,6 @@ xfs_buftarg_verify_daddr(
 int xfs_buf_reverify(struct xfs_buf *bp, const struct xfs_buf_ops *ops);
 bool xfs_verify_magic(struct xfs_buf *bp, __be32 dmagic);
 bool xfs_verify_magic16(struct xfs_buf *bp, __be16 dmagic);
+bool xfs_buf_check_poisoned(struct xfs_buf *bp);
 
 #endif	/* __XFS_BUF_H__ */
diff --git a/fs/xfs/xfs_buf_xfile.c b/fs/xfs/xfs_buf_xfile.c
index 51c5c692156b1..be1e54be070ce 100644
--- a/fs/xfs/xfs_buf_xfile.c
+++ b/fs/xfs/xfs_buf_xfile.c
@@ -18,6 +18,11 @@ xfile_buf_ioapply(
 	loff_t			pos = BBTOB(xfs_buf_daddr(bp));
 	size_t			size = BBTOB(bp->b_length);
 
+	if (bp->b_target->bt_flags & XFS_BUFTARG_DIRECT_MAP) {
+		/* direct mapping means no io necessary */
+		return 0;
+	}
+
 	if (bp->b_map_count > 1) {
 		/* We don't need or support multi-map buffers. */
 		ASSERT(0);
@@ -95,3 +100,150 @@ xfile_buftarg_nr_sectors(
 {
 	return xfile_size(btp->bt_xfile) >> SECTOR_SHIFT;
 }
+
+/* Free an xfile page that was directly mapped into the buffer cache. */
+static int
+xfile_buf_put_page(
+	struct xfile		*xfile,
+	loff_t			pos,
+	struct page		*page)
+{
+	struct xfile_page	xfpage = {
+		.page		= page,
+		.pos		= round_down(pos, PAGE_SIZE),
+	};
+
+	lock_page(xfpage.page);
+
+	return xfile_put_page(xfile, &xfpage);
+}
+
+/* Grab the xfile page for this part of the xfile. */
+static int
+xfile_buf_get_page(
+	struct xfile		*xfile,
+	loff_t			pos,
+	unsigned int		len,
+	struct page		**pagep)
+{
+	struct xfile_page	xfpage = { NULL };
+	int			error;
+
+	error = xfile_get_page(xfile, pos, len, &xfpage);
+	if (error)
+		return error;
+
+	/*
+	 * Fall back to regular DRAM buffers if tmpfs gives us fsdata or the
+	 * page pos isn't what we were expecting.
+	 */
+	if (xfpage.fsdata || xfpage.pos != round_down(pos, PAGE_SIZE)) {
+		xfile_put_page(xfile, &xfpage);
+		return -ENOTBLK;
+	}
+
+	/* Unlock the page before we start using them for the buffer cache. */
+	ASSERT(PageUptodate(xfpage.page));
+	unlock_page(xfpage.page);
+
+	*pagep = xfpage.page;
+	return 0;
+}
+
+/*
+ * Try to map storage directly, if the target supports it.  Returns 0 for
+ * success, -ENOTBLK to mean "not supported", or the usual negative errno.
+ */
+int
+xfile_buf_map_pages(
+	struct xfs_buf		*bp,
+	xfs_buf_flags_t		flags)
+{
+	struct xfs_buf_map	*map;
+	gfp_t			gfp_mask = __GFP_NOWARN;
+	const unsigned int	page_align_mask = PAGE_SIZE - 1;
+	unsigned int		m, p, n;
+	int			error;
+
+	ASSERT(xfile_buftarg_can_direct_map(bp->b_target));
+
+	/* For direct-map buffers, each map has to be page aligned. */
+	for (m = 0, map = bp->b_maps; m < bp->b_map_count; m++, map++)
+		if (BBTOB(map->bm_bn | map->bm_len) & page_align_mask)
+			return -ENOTBLK;
+
+	if (flags & XBF_READ_AHEAD)
+		gfp_mask |= __GFP_NORETRY;
+	else
+		gfp_mask |= GFP_NOFS;
+
+	error = xfs_buf_alloc_page_array(bp, gfp_mask);
+	if (error)
+		return error;
+
+	/* Map in the xfile pages. */
+	for (m = 0, p = 0, map = bp->b_maps; m < bp->b_map_count; m++, map++) {
+		for (n = 0; n < map->bm_len; n += BTOBB(PAGE_SIZE)) {
+			unsigned int	len;
+
+			len = min_t(unsigned int, BBTOB(map->bm_len - n),
+					PAGE_SIZE);
+
+			error = xfile_buf_get_page(bp->b_target->bt_xfile,
+					BBTOB(map->bm_bn + n), len,
+					&bp->b_pages[p++]);
+			if (error)
+				goto fail;
+		}
+	}
+
+	bp->b_flags |= _XBF_DIRECT_MAP;
+	return 0;
+
+fail:
+	/*
+	 * Release all the xfile pages and free the page array, we're falling
+	 * back to a DRAM buffer, which could be pages or a slab allocation.
+	 */
+	for (m = 0, p = 0, map = bp->b_maps; m < bp->b_map_count; m++, map++) {
+		for (n = 0; n < map->bm_len; n += BTOBB(PAGE_SIZE)) {
+			if (bp->b_pages[p] == NULL)
+				continue;
+
+			xfile_buf_put_page(bp->b_target->bt_xfile,
+					BBTOB(map->bm_bn + n),
+					bp->b_pages[p++]);
+		}
+	}
+
+	xfs_buf_free_page_array(bp);
+	return error;
+}
+
+/* Unmap all the direct-mapped buffer pages. */
+void
+xfile_buf_unmap_pages(
+	struct xfs_buf		*bp)
+{
+	struct xfs_buf_map	*map;
+	unsigned int		m, p, n;
+	int			error = 0, err2;
+
+	ASSERT(xfile_buftarg_can_direct_map(bp->b_target));
+
+	for (m = 0, p = 0, map = bp->b_maps; m < bp->b_map_count; m++, map++) {
+		for (n = 0; n < map->bm_len; n += BTOBB(PAGE_SIZE)) {
+			err2 = xfile_buf_put_page(bp->b_target->bt_xfile,
+					BBTOB(map->bm_bn + n),
+					bp->b_pages[p++]);
+			if (!error && err2)
+				error = err2;
+		}
+	}
+
+	if (error)
+		xfs_err(bp->b_mount, "%s failed errno %d", __func__, error);
+
+	bp->b_flags &= ~_XBF_DIRECT_MAP;
+	xfs_buf_free_page_array(bp);
+}
diff --git a/fs/xfs/xfs_buf_xfile.h b/fs/xfs/xfs_buf_xfile.h
index c8d78d01ea5df..6ff2104780010 100644
--- a/fs/xfs/xfs_buf_xfile.h
+++ b/fs/xfs/xfs_buf_xfile.h
@@ -12,9 +12,20 @@ int xfile_alloc_buftarg(struct xfs_mount *mp, const char *descr,
 		struct xfs_buftarg **btpp);
 void xfile_free_buftarg(struct xfs_buftarg *btp);
 xfs_daddr_t xfile_buftarg_nr_sectors(struct xfs_buftarg *btp);
+int xfile_buf_map_pages(struct xfs_buf *bp, xfs_buf_flags_t flags);
+void xfile_buf_unmap_pages(struct xfs_buf *bp);
+
+static inline bool xfile_buftarg_can_direct_map(const struct xfs_buftarg *btp)
+{
+	return (btp->bt_flags & XFS_BUFTARG_XFILE) &&
+	       (btp->bt_flags & XFS_BUFTARG_DIRECT_MAP);
+}
 #else
 # define xfile_buf_ioapply(bp)			(-EOPNOTSUPP)
 # define xfile_buftarg_nr_sectors(btp)		(0)
+# define xfile_buf_map_pages(b,f)		(-ENOTBLK)
+# define xfile_buf_unmap_pages(bp)		((void)0)
+# define xfile_buftarg_can_direct_map(btp)	(false)
 #endif /* CONFIG_XFS_IN_MEMORY_FILE */
 
 #endif /* __XFS_BUF_XFILE_H__ */

[PATCH 2/3] xfs: use b_offset to support direct-mapping pages when blocksize < pagesize

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Support using directly-mapped pages in the buffer cache when the fs
blocksize is less than the page size.  This is not strictly necessary
since the only user of direct-map buffers always uses page-sized
buffers, but I included it here for completeness.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_buf.c       |    8 ++++++--
 fs/xfs/xfs_buf_xfile.c |   20 +++++++++++++++++---
 2 files changed, 23 insertions(+), 5 deletions(-)


diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index ca7657d0ea592..d86227e852b7f 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -321,7 +321,7 @@ xfs_buf_free(
 	ASSERT(list_empty(&bp->b_lru));
 
 	if (xfs_buf_is_vmapped(bp))
-		vm_unmap_ram(bp->b_addr, bp->b_page_count);
+		vm_unmap_ram(bp->b_addr - bp->b_offset, bp->b_page_count);
 
 	if (bp->b_flags & _XBF_DIRECT_MAP)
 		xfile_buf_unmap_pages(bp);
@@ -434,6 +434,8 @@ xfs_buf_alloc_pages(
 		XFS_STATS_INC(bp->b_mount, xb_page_retries);
 		memalloc_retry_wait(gfp_mask);
 	}
+
+	bp->b_offset = 0;
 	return 0;
 }
 
@@ -449,7 +451,7 @@ _xfs_buf_map_pages(
 
 	if (bp->b_page_count == 1) {
 		/* A single page buffer is always mappable */
-		bp->b_addr = page_address(bp->b_pages[0]);
+		bp->b_addr = page_address(bp->b_pages[0]) + bp->b_offset;
 	} else if (flags & XBF_UNMAPPED) {
 		bp->b_addr = NULL;
 	} else {
@@ -476,6 +478,8 @@ _xfs_buf_map_pages(
 
 		if (!bp->b_addr)
 			return -ENOMEM;
+
+		bp->b_addr += bp->b_offset;
 	}
 
 	return 0;
diff --git a/fs/xfs/xfs_buf_xfile.c b/fs/xfs/xfs_buf_xfile.c
index be1e54be070ce..58469a91e72bc 100644
--- a/fs/xfs/xfs_buf_xfile.c
+++ b/fs/xfs/xfs_buf_xfile.c
@@ -163,15 +163,27 @@ xfile_buf_map_pages(
 	gfp_t			gfp_mask = __GFP_NOWARN;
 	const unsigned int	page_align_mask = PAGE_SIZE - 1;
 	unsigned int		m, p, n;
+	unsigned int		first_page_offset;
 	int			error;
 
 	ASSERT(xfile_buftarg_can_direct_map(bp->b_target));
 
-	/* For direct-map buffers, each map has to be page aligned. */
-	for (m = 0, map = bp->b_maps; m < bp->b_map_count; m++, map++)
-		if (BBTOB(map->bm_bn | map->bm_len) & page_align_mask)
+	/*
+	 * For direct-map buffer targets with multiple mappings, the first map
+	 * must end on a page boundary and the rest of the mappings must start
+	 * and end on a page boundary.  For single-mapping buffers, we don't
+	 * care.
+	 */
+	if (bp->b_map_count > 1) {
+		map = &bp->b_maps[0];
+		if (BBTOB(map->bm_bn + map->bm_len) & page_align_mask)
 			return -ENOTBLK;
 
+		for (m = 1, map++; m < bp->b_map_count - 1; m++, map++)
+			if (BBTOB(map->bm_bn | map->bm_len) & page_align_mask)
+				return -ENOTBLK;
+	}
+
 	if (flags & XBF_READ_AHEAD)
 		gfp_mask |= __GFP_NORETRY;
 	else
@@ -182,6 +194,7 @@ xfile_buf_map_pages(
 		return error;
 
 	/* Map in the xfile pages. */
+	first_page_offset = offset_in_page(BBTOB(xfs_buf_daddr(bp)));
 	for (m = 0, p = 0, map = bp->b_maps; m < bp->b_map_count; m++, map++) {
 		for (n = 0; n < map->bm_len; n += BTOBB(PAGE_SIZE)) {
 			unsigned int	len;
@@ -198,6 +211,7 @@ xfile_buf_map_pages(
 	}
 
 	bp->b_flags |= _XBF_DIRECT_MAP;
+	bp->b_offset = first_page_offset;
 	return 0;
 
 fail:

[PATCH 3/3] xfile: implement write caching

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Mapping a page into the kernel's address space is expensive.  Since
the xfile contains an xfs_buf_cache object for xfbtrees and xfbtrees
aren't the only user of xfiles, we could reuse that space for a simple
MRU cache.

When there's enough metadata records being put in an xfarray/xfblob and
the fsck scans aren't IO bound, this cuts the runtime of online fsck by
about 5%.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/trace.h   |   44 +++++++
 fs/xfs/scrub/xfile.c   |  307 +++++++++++++++++++++++++++++++-----------------
 fs/xfs/scrub/xfile.h   |   23 +++-
 fs/xfs/xfs_buf_xfile.c |    7 +
 4 files changed, 273 insertions(+), 108 deletions(-)


diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 3aa1ef6a371dd..8d863f4737e90 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -964,10 +964,52 @@ DEFINE_XFILE_EVENT(xfile_pread);
 DEFINE_XFILE_EVENT(xfile_pwrite);
 DEFINE_XFILE_EVENT(xfile_seek_data);
 DEFINE_XFILE_EVENT(xfile_get_page);
-DEFINE_XFILE_EVENT(xfile_put_page);
 DEFINE_XFILE_EVENT(xfile_discard);
 DEFINE_XFILE_EVENT(xfile_prealloc);
 
+DECLARE_EVENT_CLASS(xfile_page_class,
+	TP_PROTO(struct xfile *xf, loff_t pos, struct page *page),
+	TP_ARGS(xf, pos, page),
+	TP_STRUCT__entry(
+		__field(unsigned long, ino)
+		__field(unsigned long long, bytes_used)
+		__field(loff_t, pos)
+		__field(loff_t, size)
+		__field(unsigned long long, bytecount)
+		__field(pgoff_t, pgoff)
+	),
+	TP_fast_assign(
+		struct xfile_stat	statbuf;
+		int			ret;
+
+		ret = xfile_stat(xf, &statbuf);
+		if (!ret) {
+			__entry->bytes_used = statbuf.bytes;
+			__entry->size = statbuf.size;
+		} else {
+			__entry->bytes_used = -1;
+			__entry->size = -1;
+		}
+		__entry->ino = file_inode(xf->file)->i_ino;
+		__entry->pos = pos;
+		__entry->bytecount = page_size(page);
+		__entry->pgoff = page_offset(page);
+	),
+	TP_printk("xfino 0x%lx mem_bytes 0x%llx pos 0x%llx bytecount 0x%llx pgoff 0x%lx isize 0x%llx",
+		  __entry->ino,
+		  __entry->bytes_used,
+		  __entry->pos,
+		  __entry->bytecount,
+		  __entry->pgoff,
+		  __entry->size)
+);
+#define DEFINE_XFILE_PAGE_EVENT(name) \
+DEFINE_EVENT(xfile_page_class, name, \
+	TP_PROTO(struct xfile *xf, loff_t pos, struct page *page), \
+	TP_ARGS(xf, pos, page))
+DEFINE_XFILE_PAGE_EVENT(xfile_got_page);
+DEFINE_XFILE_PAGE_EVENT(xfile_put_page);
+
 TRACE_EVENT(xfarray_create,
 	TP_PROTO(struct xfarray *xfa, unsigned long long required_capacity),
 	TP_ARGS(xfa, required_capacity),
diff --git a/fs/xfs/scrub/xfile.c b/fs/xfs/scrub/xfile.c
index 9ab5d87963be2..ccef7fdcd7d9f 100644
--- a/fs/xfs/scrub/xfile.c
+++ b/fs/xfs/scrub/xfile.c
@@ -64,7 +64,7 @@ xfile_create(
 	struct xfile		*xf;
 	int			error = -ENOMEM;
 
-	xf = kmalloc(sizeof(struct xfile), XCHK_GFP_FLAGS);
+	xf = kzalloc(sizeof(struct xfile), XCHK_GFP_FLAGS);
 	if (!xf)
 		return -ENOMEM;
 
@@ -103,6 +103,129 @@ xfile_create(
 	return error;
 }
 
+/* Evict a cache entry and release the page. */
+static inline int
+xfile_cache_evict(
+	struct xfile		*xf,
+	struct xfile_cache	*entry)
+{
+	int			error;
+
+	if (!entry->xfpage.page)
+		return 0;
+
+	lock_page(entry->xfpage.page);
+	kunmap(entry->kaddr);
+
+	error = xfile_put_page(xf, &entry->xfpage);
+	memset(entry, 0, sizeof(struct xfile_cache));
+	return error;
+}
+
+/*
+ * Grab a page, map it into the kernel address space, and fill out the cache
+ * entry.
+ */
+static int
+xfile_cache_fill(
+	struct xfile		*xf,
+	loff_t			key,
+	struct xfile_cache	*entry)
+{
+	int			error;
+
+	error = xfile_get_page(xf, key, PAGE_SIZE, &entry->xfpage);
+	if (error)
+		return error;
+
+	entry->kaddr = kmap(entry->xfpage.page);
+	unlock_page(entry->xfpage.page);
+	return 0;
+}
+
+/*
+ * Return the kernel address of a cached position in the xfile.  If the cache
+ * misses, the relevant page will be brought into memory, mapped, and returned.
+ * If the cache is disabled, returns NULL.
+ */
+static void *
+xfile_cache_lookup(
+	struct xfile		*xf,
+	loff_t			pos)
+{
+	loff_t			key = round_down(pos, PAGE_SIZE);
+	unsigned int		i;
+	int			ret;
+
+	if (!(xf->flags & XFILE_INTERNAL_CACHE))
+		return NULL;
+
+	/* Is it already in the cache? */
+	for (i = 0; i < XFILE_CACHE_ENTRIES; i++) {
+		if (!xf->cached[i].xfpage.page)
+			continue;
+		if (page_offset(xf->cached[i].xfpage.page) != key)
+			continue;
+
+		goto found;
+	}
+
+	/* Find the least-used slot here so we can evict it. */
+	for (i = 0; i < XFILE_CACHE_ENTRIES; i++) {
+		if (!xf->cached[i].xfpage.page)
+			goto insert;
+	}
+	i = min_t(unsigned int, i, XFILE_CACHE_ENTRIES - 1);
+
+	ret = xfile_cache_evict(xf, &xf->cached[i]);
+	if (ret)
+		return ERR_PTR(ret);
+
+insert:
+	ret = xfile_cache_fill(xf, key, &xf->cached[i]);
+	if (ret)
+		return ERR_PTR(ret);
+
+found:
+	/* Stupid MRU moves this cache entry to the front. */
+	if (i != 0)
+		swap(xf->cached[0], xf->cached[i]);
+
+	return xf->cached[0].kaddr;
+}
+
+/* Drop all cached xfile pages. */
+static void
+xfile_cache_drop(
+	struct xfile		*xf)
+{
+	unsigned int		i;
+
+	if (!(xf->flags & XFILE_INTERNAL_CACHE))
+		return;
+
+	for (i = 0; i < XFILE_CACHE_ENTRIES; i++)
+		xfile_cache_evict(xf, &xf->cached[i]);
+}
+
+/* Enable the internal xfile cache. */
+void
+xfile_cache_enable(
+	struct xfile		*xf)
+{
+	xf->flags |= XFILE_INTERNAL_CACHE;
+	memset(xf->cached, 0, sizeof(struct xfile_cache) * XFILE_CACHE_ENTRIES);
+}
+
+/* Disable the internal xfile cache. */
+void
+xfile_cache_disable(
+	struct xfile		*xf)
+{
+	xfile_cache_drop(xf);
+	xf->flags &= ~XFILE_INTERNAL_CACHE;
+}
+
 /* Close the file and release all resources. */
 void
 xfile_destroy(
@@ -112,11 +235,41 @@ xfile_destroy(
 
 	trace_xfile_destroy(xf);
 
+	xfile_cache_drop(xf);
+
 	lockdep_set_class(&inode->i_rwsem, &inode->i_sb->s_type->i_mutex_key);
 	fput(xf->file);
 	kfree(xf);
 }
 
+/* Get a mapped page in the xfile, do not use internal cache. */
+static void *
+xfile_uncached_get(
+	struct xfile		*xf,
+	loff_t			pos,
+	struct xfile_page	*xfpage)
+{
+	loff_t			key = round_down(pos, PAGE_SIZE);
+	int			error;
+
+	error = xfile_get_page(xf, key, PAGE_SIZE, xfpage);
+	if (error)
+		return ERR_PTR(error);
+
+	return kmap_local_page(xfpage->page);
+}
+
+/* Release a mapped page that was obtained via xfile_uncached_get. */
+static int
+xfile_uncached_put(
+	struct xfile		*xf,
+	struct xfile_page	*xfpage,
+	void			*kaddr)
+{
+	kunmap_local(kaddr);
+	return xfile_put_page(xf, xfpage);
+}
+
 /*
  * Read a memory object directly from the xfile's page cache.  Unlike regular
  * pread, we return -E2BIG and -EFBIG for reads that are too large or at too
@@ -131,8 +284,6 @@ xfile_pread(
 	loff_t			pos)
 {
 	struct inode		*inode = file_inode(xf->file);
-	struct address_space	*mapping = inode->i_mapping;
-	struct page		*page = NULL;
 	ssize_t			read = 0;
 	unsigned int		pflags;
 	int			error = 0;
@@ -146,42 +297,32 @@ xfile_pread(
 
 	pflags = memalloc_nofs_save();
 	while (count > 0) {
+		struct xfile_page xfpage;
 		void		*p, *kaddr;
 		unsigned int	len;
+		bool		cached = true;
 
 		len = min_t(ssize_t, count, PAGE_SIZE - offset_in_page(pos));
 
-		/*
-		 * In-kernel reads of a shmem file cause it to allocate a page
-		 * if the mapping shows a hole.  Therefore, if we hit ENOMEM
-		 * we can continue by zeroing the caller's buffer.
-		 */
-		page = shmem_read_mapping_page_gfp(mapping, pos >> PAGE_SHIFT,
-				__GFP_NOWARN);
-		if (IS_ERR(page)) {
-			error = PTR_ERR(page);
-			if (error != -ENOMEM)
+		kaddr = xfile_cache_lookup(xf, pos);
+		if (!kaddr) {
+			cached = false;
+			kaddr = xfile_uncached_get(xf, pos, &xfpage);
+		}
+		if (IS_ERR(kaddr)) {
+			error = PTR_ERR(kaddr);
+			break;
+		}
+
+		p = kaddr + offset_in_page(pos);
+		memcpy(buf, p, len);
+
+		if (!cached) {
+			error = xfile_uncached_put(xf, &xfpage, kaddr);
+			if (error)
 				break;
-
-			memset(buf, 0, len);
-			goto advance;
-		}
-
-		if (PageUptodate(page)) {
-			/*
-			 * xfile pages must never be mapped into userspace, so
-			 * we skip the dcache flush.
-			 */
-			kaddr = kmap_local_page(page);
-			p = kaddr + offset_in_page(pos);
-			memcpy(buf, p, len);
-			kunmap_local(kaddr);
-		} else {
-			memset(buf, 0, len);
 		}
-		put_page(page);
 
-advance:
 		count -= len;
 		pos += len;
 		buf += len;
@@ -208,9 +349,6 @@ xfile_pwrite(
 	loff_t			pos)
 {
 	struct inode		*inode = file_inode(xf->file);
-	struct address_space	*mapping = inode->i_mapping;
-	const struct address_space_operations *aops = mapping->a_ops;
-	struct page		*page = NULL;
 	ssize_t			written = 0;
 	unsigned int		pflags;
 	int			error = 0;
@@ -224,52 +362,36 @@ xfile_pwrite(
 
 	pflags = memalloc_nofs_save();
 	while (count > 0) {
-		void		*fsdata = NULL;
+		struct xfile_page xfpage;
 		void		*p, *kaddr;
 		unsigned int	len;
-		int		ret;
+		bool		cached = true;
 
 		len = min_t(ssize_t, count, PAGE_SIZE - offset_in_page(pos));
 
-		/*
-		 * We call write_begin directly here to avoid all the freezer
-		 * protection lock-taking that happens in the normal path.
-		 * shmem doesn't support fs freeze, but lockdep doesn't know
-		 * that and will trip over that.
-		 */
-		error = aops->write_begin(NULL, mapping, pos, len, &page,
-				&fsdata);
-		if (error)
+		kaddr = xfile_cache_lookup(xf, pos);
+		if (!kaddr) {
+			cached = false;
+			kaddr = xfile_uncached_get(xf, pos, &xfpage);
+		}
+		if (IS_ERR(kaddr)) {
+			error = PTR_ERR(kaddr);
 			break;
-
-		/*
-		 * xfile pages must never be mapped into userspace, so we skip
-		 * the dcache flush.  If the page is not uptodate, zero it
-		 * before writing data.
-		 */
-		kaddr = kmap_local_page(page);
-		if (!PageUptodate(page)) {
-			memset(kaddr, 0, PAGE_SIZE);
-			SetPageUptodate(page);
 		}
+
 		p = kaddr + offset_in_page(pos);
 		memcpy(p, buf, len);
-		kunmap_local(kaddr);
 
-		ret = aops->write_end(NULL, mapping, pos, len, len, page,
-				fsdata);
-		if (ret < 0) {
-			error = ret;
-			break;
+		if (!cached) {
+			error = xfile_uncached_put(xf, &xfpage, kaddr);
+			if (error)
+				break;
 		}
 
-		written += ret;
-		if (ret != len)
-			break;
-
-		count -= ret;
-		pos += ret;
-		buf += ret;
+		written += len;
+		count -= len;
+		pos += len;
+		buf += len;
 	}
 	memalloc_nofs_restore(pflags);
 
@@ -286,6 +408,7 @@ xfile_discard(
 	u64			count)
 {
 	trace_xfile_discard(xf, pos, count);
+	xfile_cache_drop(xf);
 	shmem_truncate_range(file_inode(xf->file), pos, pos + count - 1);
 }
 
@@ -297,9 +420,6 @@ xfile_prealloc(
 	u64			count)
 {
 	struct inode		*inode = file_inode(xf->file);
-	struct address_space	*mapping = inode->i_mapping;
-	const struct address_space_operations *aops = mapping->a_ops;
-	struct page		*page = NULL;
 	unsigned int		pflags;
 	int			error = 0;
 
@@ -312,47 +432,22 @@ xfile_prealloc(
 
 	pflags = memalloc_nofs_save();
 	while (count > 0) {
-		void		*fsdata = NULL;
+		struct xfile_page xfpage;
+		void		*kaddr;
 		unsigned int	len;
-		int		ret;
 
 		len = min_t(ssize_t, count, PAGE_SIZE - offset_in_page(pos));
 
-		/*
-		 * We call write_begin directly here to avoid all the freezer
-		 * protection lock-taking that happens in the normal path.
-		 * shmem doesn't support fs freeze, but lockdep doesn't know
-		 * that and will trip over that.
-		 */
-		error = aops->write_begin(NULL, mapping, pos, len, &page,
-				&fsdata);
+		kaddr = xfile_uncached_get(xf, pos, &xfpage);
+		if (IS_ERR(kaddr)) {
+			error = PTR_ERR(kaddr);
+			break;
+		}
+
+		error = xfile_uncached_put(xf, &xfpage, kaddr);
 		if (error)
 			break;
 
-		/*
-		 * xfile pages must never be mapped into userspace, so we skip
-		 * the dcache flush.  If the page is not uptodate, zero it to
-		 * ensure we never go lacking for space here.
-		 */
-		if (!PageUptodate(page)) {
-			void	*kaddr = kmap_local_page(page);
-
-			memset(kaddr, 0, PAGE_SIZE);
-			SetPageUptodate(page);
-			kunmap_local(kaddr);
-		}
-
-		ret = aops->write_end(NULL, mapping, pos, len, len, page,
-				fsdata);
-		if (ret < 0) {
-			error = ret;
-			break;
-		}
-		if (ret != len) {
-			error = -EIO;
-			break;
-		}
-
 		count -= len;
 		pos += len;
 	}
@@ -483,7 +578,7 @@ xfile_put_page(
 	unsigned int		pflags;
 	int			ret;
 
-	trace_xfile_put_page(xf, xfpage->pos, PAGE_SIZE);
+	trace_xfile_put_page(xf, xfpage->pos, xfpage->page);
 
 	/* Give back the reference that we took in xfile_get_page. */
 	put_page(xfpage->page);
diff --git a/fs/xfs/scrub/xfile.h b/fs/xfs/scrub/xfile.h
index 849f59da6a184..4bb10829f7a07 100644
--- a/fs/xfs/scrub/xfile.h
+++ b/fs/xfs/scrub/xfile.h
@@ -24,11 +24,32 @@ static inline pgoff_t xfile_page_index(const struct xfile_page *xfpage)
 	return xfpage->page->index;
 }
 
+struct xfile_cache {
+	struct xfile_page	xfpage;
+	void			*kaddr;
+};
+
+#define XFILE_CACHE_ENTRIES	(sizeof(struct xfs_buf_cache) / \
+				 sizeof(struct xfile_cache))
+
 struct xfile {
 	struct file		*file;
-	struct xfs_buf_cache	bcache;
+
+	union {
+		struct xfs_buf_cache	bcache;
+		struct xfile_cache	cached[XFILE_CACHE_ENTRIES];
+	};
+
+	/* XFILE_* flags */
+	unsigned int		flags;
 };
 
+/* Use the internal cache for faster access. */
+#define XFILE_INTERNAL_CACHE	(1U << 0)
+
+void xfile_cache_enable(struct xfile *xf);
+void xfile_cache_disable(struct xfile *xf);
+
 int xfile_create(const char *description, loff_t isize, struct xfile **xfilep);
 void xfile_destroy(struct xfile *xf);
 
diff --git a/fs/xfs/xfs_buf_xfile.c b/fs/xfs/xfs_buf_xfile.c
index 58469a91e72bc..cc670e8bafc4a 100644
--- a/fs/xfs/xfs_buf_xfile.c
+++ b/fs/xfs/xfs_buf_xfile.c
@@ -49,6 +49,13 @@ xfile_alloc_buftarg(
 	if (error)
 		return error;
 
+	/*
+	 * We're hooking the xfile up to the buffer cache, so disable its
+	 * internal page caching because all callers should be using xfs_buf
+	 * functions.
+	 */
+	xfile_cache_disable(xfile);
+
 	error = xfs_buf_cache_init(&xfile->bcache);
 	if (error)
 		goto out_xfile;

[PATCH 1/4] xfs: check unused nlink fields in the ondisk inode

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

v2/v3 inodes use di_nlink and not di_onlink; and v1 inodes use di_onlink
and not di_nlink.  Whichever field is not in use, make sure its contents
are zero, and teach xfs_scrub to fix that if it is.

This clears a bunch of missing scrub failure errors in xfs/385 for
core.onlink.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_inode_buf.c |    8 ++++++++
 fs/xfs/scrub/inode_repair.c   |   12 ++++++++++++
 2 files changed, 20 insertions(+)


diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index d0dcce462bf42..d79002343d0b6 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -491,6 +491,14 @@ xfs_dinode_verify(
 			return __this_address;
 	}
 
+	if (dip->di_version > 1) {
+		if (dip->di_onlink)
+			return __this_address;
+	} else {
+		if (dip->di_nlink)
+			return __this_address;
+	}
+
 	/* don't allow invalid i_size */
 	di_size = be64_to_cpu(dip->di_size);
 	if (di_size & (1ULL << 63))
diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c
index e46b1256b0851..5867617c00cd8 100644
--- a/fs/xfs/scrub/inode_repair.c
+++ b/fs/xfs/scrub/inode_repair.c
@@ -468,6 +468,17 @@ xrep_dinode_mode(
 	return 0;
 }
 
+/* Fix unused link count fields having nonzero values. */
+STATIC void
+xrep_dinode_nlinks(
+	struct xfs_dinode	*dip)
+{
+	if (dip->di_version > 1)
+		dip->di_onlink = 0;
+	else
+		dip->di_nlink = 0;
+}
+
 /* Fix any conflicting flags that the verifiers complain about. */
 STATIC void
 xrep_dinode_flags(
@@ -1329,6 +1340,7 @@ xrep_dinode_core(
 	iget_error = xrep_dinode_mode(ri, dip);
 	if (iget_error)
 		goto write;
+	xrep_dinode_nlinks(dip);
 	xrep_dinode_flags(sc, dip, ri->rt_extents > 0);
 	xrep_dinode_size(ri, dip);
 	xrep_dinode_extsize_hints(sc, dip);

[PATCH 2/4] xfs: try to avoid allocating from sick inode clusters

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

I noticed that xfs/413 and xfs/375 occasionally failed while fuzzing
core.mode of an inode.  The root cause of these problems is that the
field we fuzzed (core.mode or core.magic, typically) causes the entire
inode cluster buffer verification to fail, which affects several inodes
at once.  The repair process tries to create either a /lost+found or a
temporary repair file, but regrettably it picks the same inode cluster
that we just corrupted, with the result that repair triggers the demise
of the filesystem.

Try avoid this by making the inode allocation path detect when the perag
health status indicates that someone has found bad inode cluster
buffers, and try to read the inode cluster buffer.  If the cluster
buffer fails the verifiers, try another AG.  This isn't foolproof and
can result in premature ENOSPC, but that might be better than shutting
down.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_ialloc.c |   40 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)


diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 1ff867075026d..8b38a1a87954f 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -1012,6 +1012,33 @@ xfs_inobt_first_free_inode(
 	return xfs_lowbit64(realfree);
 }
 
+/*
+ * If this AG has corrupt inodes, check if allocating this inode would fail
+ * with corruption errors.  Returns 0 if we're clear, or EAGAIN to try again
+ * somewhere else.
+ */
+static int
+xfs_dialloc_check_ino(
+	struct xfs_perag	*pag,
+	struct xfs_trans	*tp,
+	xfs_ino_t		ino)
+{
+	struct xfs_imap		imap;
+	struct xfs_buf		*bp;
+	int			error;
+
+	error = xfs_imap(pag, tp, ino, &imap, 0);
+	if (error)
+		return -EAGAIN;
+
+	error = xfs_imap_to_bp(pag->pag_mount, tp, &imap, &bp);
+	if (error)
+		return -EAGAIN;
+
+	xfs_trans_brelse(tp, bp);
+	return 0;
+}
+
 /*
  * Allocate an inode using the inobt-only algorithm.
  */
@@ -1264,6 +1291,13 @@ xfs_dialloc_ag_inobt(
 	ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) %
 				   XFS_INODES_PER_CHUNK) == 0);
 	ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, rec.ir_startino + offset);
+
+	if (xfs_ag_has_sickness(pag, XFS_SICK_AG_INODES)) {
+		error = xfs_dialloc_check_ino(pag, tp, ino);
+		if (error)
+			goto error0;
+	}
+
 	rec.ir_free &= ~XFS_INOBT_MASK(offset);
 	rec.ir_freecount--;
 	error = xfs_inobt_update(cur, &rec);
@@ -1539,6 +1573,12 @@ xfs_dialloc_ag(
 				   XFS_INODES_PER_CHUNK) == 0);
 	ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, rec.ir_startino + offset);
 
+	if (xfs_ag_has_sickness(pag, XFS_SICK_AG_INODES)) {
+		error = xfs_dialloc_check_ino(pag, tp, ino);
+		if (error)
+			goto error_cur;
+	}
+
 	/*
 	 * Modify or remove the finobt record.
 	 */

[PATCH 3/4] xfs: pin inodes that would otherwise overflow link count

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

The VFS inc_nlink function does not explicitly check for integer
overflows in the i_nlink field.  Instead, it checks the link count
against s_max_links in the vfs_{link,create,rename} functions.  XFS
sets the maximum link count to 2.1 billion, so integer overflows should
not be a problem.

However.  It's possible that online repair could find that a file has
more than four billion links, particularly if the link count got
corrupted while creating hardlinks to the file.  The di_nlinkv2 field is
not large enough to store a value larger than 2^32, so we ought to
define a magic pin value of ~0U which means that the inode never gets
deleted.  This will prevent a UAF error if the repair finds this
situation and users begin deleting links to the file.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_format.h   |    6 ++++++
 fs/xfs/scrub/dir_repair.c    |   11 +++--------
 fs/xfs/scrub/nlinks.c        |    4 +++-
 fs/xfs/scrub/nlinks_repair.c |    8 ++------
 fs/xfs/xfs_inode.c           |   33 ++++++++++++++++++++++-----------
 5 files changed, 36 insertions(+), 26 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 7861539ab8b68..ec25010b57797 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -912,6 +912,12 @@ static inline uint xfs_dinode_size(int version)
  */
 #define	XFS_MAXLINK		((1U << 31) - 1U)
 
+/*
+ * Any file that hits the maximum ondisk link count should be pinned to avoid
+ * a use-after-free situation.
+ */
+#define	XFS_NLINK_PINNED	(~0U)
+
 /*
  * Values for di_format
  *
diff --git a/fs/xfs/scrub/dir_repair.c b/fs/xfs/scrub/dir_repair.c
index 141682e2477af..48e30a9baeae0 100644
--- a/fs/xfs/scrub/dir_repair.c
+++ b/fs/xfs/scrub/dir_repair.c
@@ -1145,7 +1145,9 @@ xrep_dir_set_nlink(
 	struct xfs_scrub	*sc = rd->sc;
 	struct xfs_inode	*dp = sc->ip;
 	struct xfs_perag	*pag;
-	unsigned int		new_nlink = rd->subdirs + 2;
+	unsigned int		new_nlink = min_t(unsigned long long,
+						  rd->subdirs + 2,
+						  XFS_NLINK_PINNED);
 	int			error;
 
 	/*
@@ -1201,13 +1203,6 @@ xrep_dir_swap(
 	bool			ip_local, temp_local;
 	int			error = 0;
 
-	/*
-	 * If we found enough subdirs to overflow this directory's link count,
-	 * bail out to userspace before we modify anything.
-	 */
-	if (rd->subdirs + 2 > XFS_MAXLINK)
-		return -EFSCORRUPTED;
-
 	/*
 	 * 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
diff --git a/fs/xfs/scrub/nlinks.c b/fs/xfs/scrub/nlinks.c
index 7be2119ce283a..6f0b77da14dbb 100644
--- a/fs/xfs/scrub/nlinks.c
+++ b/fs/xfs/scrub/nlinks.c
@@ -603,9 +603,11 @@ xchk_nlinks_compare_inode(
 	 * this as a corruption.  The VFS won't let users increase the link
 	 * count, but it will let them decrease it.
 	 */
-	if (total_links > XFS_MAXLINK) {
+	if (total_links > XFS_NLINK_PINNED) {
 		xchk_ino_set_corrupt(sc, ip->i_ino);
 		goto out_corrupt;
+	} else if (total_links > XFS_MAXLINK) {
+		xchk_ino_set_warning(sc, ip->i_ino);
 	}
 
 	/* Link counts should match. */
diff --git a/fs/xfs/scrub/nlinks_repair.c b/fs/xfs/scrub/nlinks_repair.c
index 1345c07a95c62..87cb3400ff948 100644
--- a/fs/xfs/scrub/nlinks_repair.c
+++ b/fs/xfs/scrub/nlinks_repair.c
@@ -239,14 +239,10 @@ xrep_nlinks_repair_inode(
 
 	/* Commit the new link count if it changed. */
 	if (total_links != actual_nlink) {
-		if (total_links > XFS_MAXLINK) {
-			trace_xrep_nlinks_unfixable_inode(mp, ip, &obs);
-			goto out_trans;
-		}
-
 		trace_xrep_nlinks_update_inode(mp, ip, &obs);
 
-		set_nlink(VFS_I(ip), total_links);
+		set_nlink(VFS_I(ip), min_t(unsigned long long, total_links,
+					   XFS_NLINK_PINNED));
 		dirty = true;
 	}
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index ea1b0bc9a3410..71640afc3a8ee 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -912,22 +912,25 @@ xfs_init_new_inode(
  */
 static int			/* error */
 xfs_droplink(
-	xfs_trans_t *tp,
-	xfs_inode_t *ip)
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip)
 {
-	if (VFS_I(ip)->i_nlink == 0) {
-		xfs_alert(ip->i_mount,
-			  "%s: Attempt to drop inode (%llu) with nlink zero.",
-			  __func__, ip->i_ino);
-		return -EFSCORRUPTED;
-	}
+	struct inode		*inode = VFS_I(ip);
 
 	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
 
-	drop_nlink(VFS_I(ip));
+	if (inode->i_nlink == 0) {
+		xfs_info_ratelimited(tp->t_mountp,
+ "Inode 0x%llx link count dropped below zero.  Pinning link count.",
+				ip->i_ino);
+		set_nlink(inode, XFS_NLINK_PINNED);
+	}
+	if (inode->i_nlink != XFS_NLINK_PINNED)
+		drop_nlink(inode);
+
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
-	if (VFS_I(ip)->i_nlink)
+	if (inode->i_nlink)
 		return 0;
 
 	return xfs_iunlink(tp, ip);
@@ -941,9 +944,17 @@ xfs_bumplink(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*ip)
 {
+	struct inode		*inode = VFS_I(ip);
+
 	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
 
-	inc_nlink(VFS_I(ip));
+	if (inode->i_nlink == XFS_NLINK_PINNED - 1)
+		xfs_info_ratelimited(tp->t_mountp,
+ "Inode 0x%llx link count exceeded maximum.  Pinning link count.",
+				ip->i_ino);
+	if (inode->i_nlink != XFS_NLINK_PINNED)
+		inc_nlink(inode);
+
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 }
 

[PATCH 4/4] xfs: create subordinate scrub contexts for xchk_metadata_inode_subtype

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

When a file-based metadata structure is being scrubbed in
xchk_metadata_inode_subtype, we should create an entirely new scrub
context so that each scrubber doesn't trip over another's buffers.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/scrub/common.c |   23 +++--------------
 fs/xfs/scrub/repair.c |   67 ++++++++++---------------------------------------
 fs/xfs/scrub/scrub.c  |   63 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/scrub.h  |   11 ++++++++
 4 files changed, 91 insertions(+), 73 deletions(-)


diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index c16cd9774f525..9a8bd6f050af9 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -1201,27 +1201,12 @@ xchk_metadata_inode_subtype(
 	struct xfs_scrub	*sc,
 	unsigned int		scrub_type)
 {
-	__u32			smtype = sc->sm->sm_type;
-	unsigned int		sick_mask = sc->sick_mask;
+	struct xfs_scrub_subord	*sub;
 	int			error;
 
-	sc->sm->sm_type = scrub_type;
-
-	switch (scrub_type) {
-	case XFS_SCRUB_TYPE_INODE:
-		error = xchk_inode(sc);
-		break;
-	case XFS_SCRUB_TYPE_BMBTD:
-		error = xchk_bmap_data(sc);
-		break;
-	default:
-		ASSERT(0);
-		error = -EFSCORRUPTED;
-		break;
-	}
-
-	sc->sick_mask = sick_mask;
-	sc->sm->sm_type = smtype;
+	sub = xchk_scrub_create_subord(sc, scrub_type);
+	error = sub->sc.ops->scrub(&sub->sc);
+	xchk_scrub_free_subord(sub);
 	return error;
 }
 
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index ef17a08320782..b15eee680510c 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -1009,55 +1009,27 @@ xrep_metadata_inode_subtype(
 	struct xfs_scrub	*sc,
 	unsigned int		scrub_type)
 {
-	__u32			smtype = sc->sm->sm_type;
-	__u32			smflags = sc->sm->sm_flags;
-	unsigned int		sick_mask = sc->sick_mask;
+	struct xfs_scrub_subord	*sub;
 	int			error;
 
 	/*
-	 * Let's see if the inode needs repair.  We're going to open-code calls
-	 * to the scrub and repair functions so that we can hang on to the
+	 * Let's see if the inode needs repair.  Use a subordinate scrub context
+	 * to call the scrub and repair functions so that we can hang on to the
 	 * resources that we already acquired instead of using the standard
 	 * setup/teardown routines.
 	 */
-	sc->sm->sm_flags &= ~XFS_SCRUB_FLAGS_OUT;
-	sc->sm->sm_type = scrub_type;
-
-	switch (scrub_type) {
-	case XFS_SCRUB_TYPE_INODE:
-		error = xchk_inode(sc);
-		break;
-	case XFS_SCRUB_TYPE_BMBTD:
-		error = xchk_bmap_data(sc);
-		break;
-	case XFS_SCRUB_TYPE_BMBTA:
-		error = xchk_bmap_attr(sc);
-		break;
-	default:
-		ASSERT(0);
-		error = -EFSCORRUPTED;
-	}
+	sub = xchk_scrub_create_subord(sc, scrub_type);
+	error = sub->sc.ops->scrub(&sub->sc);
 	if (error)
 		goto out;
-
-	if (!xrep_will_attempt(sc))
+	if (!xrep_will_attempt(&sub->sc))
 		goto out;
 
 	/*
 	 * Repair some part of the inode.  This will potentially join the inode
 	 * to the transaction.
 	 */
-	switch (scrub_type) {
-	case XFS_SCRUB_TYPE_INODE:
-		error = xrep_inode(sc);
-		break;
-	case XFS_SCRUB_TYPE_BMBTD:
-		error = xrep_bmap(sc, XFS_DATA_FORK, false);
-		break;
-	case XFS_SCRUB_TYPE_BMBTA:
-		error = xrep_bmap(sc, XFS_ATTR_FORK, false);
-		break;
-	}
+	error = sub->sc.ops->repair(&sub->sc);
 	if (error)
 		goto out;
 
@@ -1066,10 +1038,10 @@ xrep_metadata_inode_subtype(
 	 * that the inode will not be joined to the transaction when we exit
 	 * the function.
 	 */
-	error = xfs_defer_finish(&sc->tp);
+	error = xfs_defer_finish(&sub->sc.tp);
 	if (error)
 		goto out;
-	error = xfs_trans_roll(&sc->tp);
+	error = xfs_trans_roll(&sub->sc.tp);
 	if (error)
 		goto out;
 
@@ -1077,31 +1049,18 @@ xrep_metadata_inode_subtype(
 	 * Clear the corruption flags and re-check the metadata that we just
 	 * repaired.
 	 */
-	sc->sm->sm_flags &= ~XFS_SCRUB_FLAGS_OUT;
-
-	switch (scrub_type) {
-	case XFS_SCRUB_TYPE_INODE:
-		error = xchk_inode(sc);
-		break;
-	case XFS_SCRUB_TYPE_BMBTD:
-		error = xchk_bmap_data(sc);
-		break;
-	case XFS_SCRUB_TYPE_BMBTA:
-		error = xchk_bmap_attr(sc);
-		break;
-	}
+	sub->sc.sm->sm_flags &= ~XFS_SCRUB_FLAGS_OUT;
+	error = sub->sc.ops->scrub(&sub->sc);
 	if (error)
 		goto out;
 
 	/* If corruption persists, the repair has failed. */
-	if (xchk_needs_repair(sc->sm)) {
+	if (xchk_needs_repair(sub->sc.sm)) {
 		error = -EFSCORRUPTED;
 		goto out;
 	}
 out:
-	sc->sick_mask = sick_mask;
-	sc->sm->sm_type = smtype;
-	sc->sm->sm_flags = smflags;
+	xchk_scrub_free_subord(sub);
 	return error;
 }
 
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index df6f5d3474048..440b8cb1957f4 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -180,6 +180,39 @@ xchk_fsgates_disable(
 }
 #undef FSGATES_MASK
 
+/* Free the resources associated with a scrub subtype. */
+void
+xchk_scrub_free_subord(
+	struct xfs_scrub_subord	*sub)
+{
+	struct xfs_scrub	*sc = sub->parent_sc;
+
+	ASSERT(sc->ip == sub->sc.ip);
+	ASSERT(sc->orphanage == sub->sc.orphanage);
+	ASSERT(sc->tempip == sub->sc.tempip);
+
+	sc->sm->sm_type = sub->old_smtype;
+	sc->sm->sm_flags = sub->old_smflags |
+				(sc->sm->sm_flags & XFS_SCRUB_FLAGS_OUT);
+	sc->tp = sub->sc.tp;
+
+	if (sub->sc.buf) {
+		if (sub->sc.buf_cleanup)
+			sub->sc.buf_cleanup(sub->sc.buf);
+		kvfree(sub->sc.buf);
+	}
+	if (sub->sc.xfile_buftarg)
+		xfile_free_buftarg(sub->sc.xfile_buftarg);
+	if (sub->sc.xfile)
+		xfile_destroy(sub->sc.xfile);
+
+	sc->ilock_flags = sub->sc.ilock_flags;
+	sc->orphanage_ilock_flags = sub->sc.orphanage_ilock_flags;
+	sc->temp_ilock_flags = sub->sc.temp_ilock_flags;
+
+	kfree(sub);
+}
+
 /* Free all the resources and finish the transactions. */
 STATIC int
 xchk_teardown(
@@ -508,6 +541,36 @@ static inline void xchk_postmortem(struct xfs_scrub *sc)
 }
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
+/*
+ * Create a new scrub context from an existing one, but with a different scrub
+ * type.
+ */
+struct xfs_scrub_subord *
+xchk_scrub_create_subord(
+	struct xfs_scrub	*sc,
+	unsigned int		subtype)
+{
+	struct xfs_scrub_subord	*sub;
+
+	sub = kzalloc(sizeof(*sub), XCHK_GFP_FLAGS);
+	if (!sub)
+		return ERR_PTR(-ENOMEM);
+
+	sub->old_smtype = sc->sm->sm_type;
+	sub->old_smflags = sc->sm->sm_flags;
+	sub->parent_sc = sc;
+	memcpy(&sub->sc, sc, sizeof(struct xfs_scrub));
+	sub->sc.ops = &meta_scrub_ops[subtype];
+	sub->sc.sm->sm_type = subtype;
+	sub->sc.sm->sm_flags &= ~XFS_SCRUB_FLAGS_OUT;
+	sub->sc.buf = NULL;
+	sub->sc.buf_cleanup = NULL;
+	sub->sc.xfile = NULL;
+	sub->sc.xfile_buftarg = NULL;
+
+	return sub;
+}
+
 /* Dispatch metadata scrubbing. */
 int
 xfs_scrub_metadata(
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index 09769af6b66a9..665da3e3c1af1 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -156,6 +156,17 @@ struct xfs_scrub {
  */
 #define XREP_FSGATES_ALL	(XREP_FSGATES_ATOMIC_XCHG)
 
+struct xfs_scrub_subord {
+	struct xfs_scrub	sc;
+	struct xfs_scrub	*parent_sc;
+	unsigned int		old_smtype;
+	unsigned int		old_smflags;
+};
+
+struct xfs_scrub_subord *xchk_scrub_create_subord(struct xfs_scrub *sc,
+		unsigned int subtype);
+void xchk_scrub_free_subord(struct xfs_scrub_subord *sub);
+
 /* Metadata scrubbers */
 int xchk_tester(struct xfs_scrub *sc);
 int xchk_superblock(struct xfs_scrub *sc);

[PATCH 1/1] xfs: fix severe performance problems when fstrimming a subset of an AG

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

XFS issues discard IOs while holding the free space btree and the AGF
buffers locked.  If the discard IOs are slow, this can lead to long
stalls for every other thread trying to access that AG.  On a 10TB high
performance flash storage device with a severely fragmented free space
btree in every AG, this results in many threads tripping the hangcheck
warnings while waiting for the AGF.  This happens even after we've run
fstrim a few times and waited for the nvme namespace utilization
counters to stabilize.

Strace for the entire 100TB looks like:
ioctl(3, FITRIM, {start=0x0, len=10995116277760, minlen=0}) = 0 <686.209839>

Reducing the size of the FITRIM requests to a single AG at a time
produces lower times for each individual call, but even this isn't quite
acceptable, because the lock hold times are still high enough to cause
stall warnings:

Strace for the first 4x 1TB AGs looks like (2):
ioctl(3, FITRIM, {start=0x0, len=1099511627776, minlen=0}) = 0 <68.352033>
ioctl(3, FITRIM, {start=0x10000000000, len=1099511627776, minlen=0}) = 0 <68.760323>
ioctl(3, FITRIM, {start=0x20000000000, len=1099511627776, minlen=0}) = 0 <67.235226>
ioctl(3, FITRIM, {start=0x30000000000, len=1099511627776, minlen=0}) = 0 <69.465744>

The fstrim code has to synchronize discards with block allocations, so
we must hold the AGF lock while issuing discard IOs.  Breaking up the
calls into smaller start/len segments ought to reduce the lock hold time
and allow other threads a chance to make progress.  Unfortunately, the
current fstrim implementation handles this poorly because it walks the
entire free space by length index (cntbt) and it's not clear if we can
cycle the AGF periodically to reduce latency because there's no
less-than btree lookup.

The first solution I thought of was to limit latency by scanning parts
of an AG at a time, but this doesn't solve the stalling problem when the
free space is heavily fragmented because each sub-AG scan has to walk
the entire cntbt to find free space that fits within the given range.
In fact, this dramatically increases the runtime!  This itself is a
problem, because sub-AG fstrim runtime is unnecessarily high.

For sub-AG scans, create a second implementation that will walk the
bnobt and perform the trims in block number order.  Since the cursor has
an obviously monotonically increasing value, it is easy to cycle the AGF
periodically to allow other threads to do work.  This implementation
avoids the worst problems of the original code, though it lacks the
desirable attribute of freeing the biggest chunks first.

On the other hand, this second implementation will be much easier to
constrain the locking latency, and makes it much easier to report fstrim
progress to anyone who's running xfs_scrub.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_discard.c |  164 +++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 162 insertions(+), 2 deletions(-)


diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 2ec6b99188a28..d235f60c166c6 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -286,6 +286,154 @@ xfs_trim_gather_extents(
 	return error;
 }
 
+/* Trim the free space in this AG by block number. */
+static inline int
+xfs_trim_gather_bybno(
+	struct xfs_perag	*pag,
+	xfs_daddr_t		start,
+	xfs_daddr_t		end,
+	xfs_daddr_t		minlen,
+	struct xfs_alloc_rec_incore *tcur,
+	struct xfs_busy_extents	*extents,
+	uint64_t		*blocks_trimmed)
+{
+	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_btree_cur	*cur;
+	struct xfs_buf		*agbp;
+	xfs_daddr_t		end_daddr;
+	xfs_agnumber_t		agno = pag->pag_agno;
+	xfs_agblock_t		start_agbno;
+	xfs_agblock_t		end_agbno;
+	xfs_extlen_t		minlen_fsb = XFS_BB_TO_FSB(mp, minlen);
+	int			i;
+	int			batch = 100;
+	int			error;
+
+	start = max(start, XFS_AGB_TO_DADDR(mp, agno, 0));
+	start_agbno = xfs_daddr_to_agbno(mp, start);
+
+	end_daddr = XFS_AGB_TO_DADDR(mp, agno, pag->block_count);
+	end = min(end, end_daddr - 1);
+	end_agbno = xfs_daddr_to_agbno(mp, end);
+
+	error = xfs_alloc_read_agf(pag, NULL, 0, &agbp);
+	if (error)
+		return error;
+
+	cur = xfs_allocbt_init_cursor(mp, NULL, agbp, pag, XFS_BTNUM_BNO);
+
+	/*
+	 * If this is our first time, look for any extent crossing start_agbno.
+	 * Otherwise, continue at the next extent after wherever we left off.
+	 */
+	if (tcur->ar_startblock == NULLAGBLOCK) {
+		error = xfs_alloc_lookup_le(cur, start_agbno, 0, &i);
+		if (error)
+			goto out_del_cursor;
+
+		/*
+		 * If we didn't find anything at or below start_agbno,
+		 * increment the cursor to see if there's another record above
+		 * it.
+		 */
+		if (!i)
+			error = xfs_btree_increment(cur, 0, &i);
+	} else {
+		error = xfs_alloc_lookup_ge(cur, tcur->ar_startblock, 0, &i);
+	}
+	if (error)
+		goto out_del_cursor;
+	if (!i) {
+		/* nothing left in the AG, we are done */
+		tcur->ar_blockcount = 0;
+		goto out_del_cursor;
+	}
+
+	/* Loop the entire range that was asked for. */
+	while (i) {
+		xfs_agblock_t	fbno;
+		xfs_extlen_t	flen;
+
+		error = xfs_alloc_get_rec(cur, &fbno, &flen, &i);
+		if (error)
+			break;
+		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
+			error = -EFSCORRUPTED;
+			break;
+		}
+
+		if (--batch <= 0) {
+			/*
+			 * Update the cursor to point at this extent so we
+			 * restart the next batch from this extent.
+			 */
+			tcur->ar_startblock = fbno;
+			tcur->ar_blockcount = flen;
+			break;
+		}
+
+		/* Exit on extents entirely outside of the range. */
+		if (fbno >= end_agbno) {
+			tcur->ar_blockcount = 0;
+			break;
+		}
+		if (fbno + flen < start_agbno)
+			goto next_extent;
+
+		/* Trim the extent returned to the range we want. */
+		if (fbno < start_agbno) {
+			flen -= start_agbno - fbno;
+			fbno = start_agbno;
+		}
+		if (fbno + flen > end_agbno + 1)
+			flen = end_agbno - fbno + 1;
+
+		/* Ignore too small. */
+		if (flen < minlen_fsb) {
+			trace_xfs_discard_toosmall(mp, agno, fbno, flen);
+			goto next_extent;
+		}
+
+		/*
+		 * If any blocks in the range are still busy, skip the
+		 * discard and try again the next time.
+		 */
+		if (xfs_extent_busy_search(mp, pag, fbno, flen)) {
+			trace_xfs_discard_busy(mp, agno, fbno, flen);
+			goto next_extent;
+		}
+
+		xfs_extent_busy_insert_discard(pag, fbno, flen,
+				&extents->extent_list);
+		*blocks_trimmed += flen;
+next_extent:
+		error = xfs_btree_increment(cur, 0, &i);
+		if (error)
+			break;
+
+		/*
+		 * If there's no more records in the tree, we are done. Set the
+		 * cursor block count to 0 to indicate to the caller that there
+		 * are no more extents to search.
+		 */
+		if (i == 0)
+			tcur->ar_blockcount = 0;
+	}
+
+	/*
+	 * If there was an error, release all the gathered busy extents because
+	 * we aren't going to issue a discard on them any more.
+	 */
+	if (error)
+		xfs_extent_busy_clear(mp, &extents->extent_list, false);
+
+out_del_cursor:
+	xfs_btree_del_cursor(cur, error);
+	xfs_buf_relse(agbp);
+	return error;
+}
+
 static bool
 xfs_trim_should_stop(void)
 {
@@ -309,8 +457,15 @@ xfs_trim_extents(
 		.ar_blockcount = pag->pagf_longest,
 		.ar_startblock = NULLAGBLOCK,
 	};
+	struct xfs_mount	*mp = pag->pag_mount;
+	bool			by_len = true;
 	int			error = 0;
 
+	/* Are we only trimming part of this AG? */
+	if (start > XFS_AGB_TO_DADDR(mp, pag->pag_agno, 0) ||
+	    end < XFS_AGB_TO_DADDR(mp, pag->pag_agno, pag->block_count - 1))
+		by_len = false;
+
 	do {
 		struct xfs_busy_extents	*extents;
 
@@ -324,8 +479,13 @@ xfs_trim_extents(
 		extents->owner = extents;
 		INIT_LIST_HEAD(&extents->extent_list);
 
-		error = xfs_trim_gather_extents(pag, start, end, minlen,
-				&tcur, extents, blocks_trimmed);
+		if (by_len)
+			error = xfs_trim_gather_extents(pag, start, end,
+					minlen, &tcur, extents,
+					blocks_trimmed);
+		else
+			error = xfs_trim_gather_bybno(pag, start, end, minlen,
+					&tcur, extents, blocks_trimmed);
 		if (error) {
 			kfree(extents);
 			break;

[PATCH 1/3] xfs_scrub: fix author and spdx headers on scrub/ files

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Fix the spdx tags to match current practice, and update the author
contact information.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/common.c         |    4 ++--
 scrub/common.h         |    4 ++--
 scrub/counter.c        |    4 ++--
 scrub/counter.h        |    4 ++--
 scrub/descr.c          |    2 +-
 scrub/descr.h          |    2 +-
 scrub/disk.c           |    4 ++--
 scrub/disk.h           |    4 ++--
 scrub/filemap.c        |    4 ++--
 scrub/filemap.h        |    4 ++--
 scrub/fscounters.c     |    4 ++--
 scrub/fscounters.h     |    4 ++--
 scrub/inodes.c         |    4 ++--
 scrub/inodes.h         |    4 ++--
 scrub/phase1.c         |    4 ++--
 scrub/phase2.c         |    4 ++--
 scrub/phase3.c         |    4 ++--
 scrub/phase4.c         |    4 ++--
 scrub/phase5.c         |    4 ++--
 scrub/phase6.c         |    4 ++--
 scrub/phase7.c         |    4 ++--
 scrub/progress.c       |    4 ++--
 scrub/progress.h       |    4 ++--
 scrub/read_verify.c    |    4 ++--
 scrub/read_verify.h    |    4 ++--
 scrub/repair.c         |    4 ++--
 scrub/repair.h         |    4 ++--
 scrub/scrub.c          |    4 ++--
 scrub/scrub.h          |    4 ++--
 scrub/spacemap.c       |    4 ++--
 scrub/spacemap.h       |    4 ++--
 scrub/unicrash.c       |    4 ++--
 scrub/unicrash.h       |    4 ++--
 scrub/vfs.c            |    4 ++--
 scrub/vfs.h            |    4 ++--
 scrub/xfs_scrub.c      |    4 ++--
 scrub/xfs_scrub.h      |    4 ++--
 scrub/xfs_scrub_all.in |    4 ++--
 38 files changed, 74 insertions(+), 74 deletions(-)


diff --git a/scrub/common.c b/scrub/common.c
index 49a87f412c4..25a398c5fe4 100644
--- a/scrub/common.c
+++ b/scrub/common.c
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
 #include <pthread.h>
diff --git a/scrub/common.h b/scrub/common.h
index 13b5f309955..26ef7c861c6 100644
--- a/scrub/common.h
+++ b/scrub/common.h
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_COMMON_H_
 #define XFS_SCRUB_COMMON_H_
diff --git a/scrub/counter.c b/scrub/counter.c
index 6d91eb6e015..b63ec721c34 100644
--- a/scrub/counter.c
+++ b/scrub/counter.c
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
 #include <stdint.h>
diff --git a/scrub/counter.h b/scrub/counter.h
index 01b65056a2e..77e380cc611 100644
--- a/scrub/counter.h
+++ b/scrub/counter.h
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_COUNTER_H_
 #define XFS_SCRUB_COUNTER_H_
diff --git a/scrub/descr.c b/scrub/descr.c
index e694d01d7b7..bf0c5717a11 100644
--- a/scrub/descr.c
+++ b/scrub/descr.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2019 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
 #include <assert.h>
diff --git a/scrub/descr.h b/scrub/descr.h
index f1899b67206..0f5d9067e5d 100644
--- a/scrub/descr.h
+++ b/scrub/descr.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2019 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_DESCR_H_
 #define XFS_SCRUB_DESCR_H_
diff --git a/scrub/disk.c b/scrub/disk.c
index a1ef798a025..740a7ac962f 100644
--- a/scrub/disk.c
+++ b/scrub/disk.c
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
 #include <stdint.h>
diff --git a/scrub/disk.h b/scrub/disk.h
index 36bfb8263d1..1f6c73aee3d 100644
--- a/scrub/disk.h
+++ b/scrub/disk.h
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_DISK_H_
 #define XFS_SCRUB_DISK_H_
diff --git a/scrub/filemap.c b/scrub/filemap.c
index d4905ace659..c1e520299ed 100644
--- a/scrub/filemap.c
+++ b/scrub/filemap.c
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
 #include <stdint.h>
diff --git a/scrub/filemap.h b/scrub/filemap.h
index 133e860bb82..d123537aaff 100644
--- a/scrub/filemap.h
+++ b/scrub/filemap.h
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_FILEMAP_H_
 #define XFS_SCRUB_FILEMAP_H_
diff --git a/scrub/fscounters.c b/scrub/fscounters.c
index 3ceae3715dc..6df0533a0b7 100644
--- a/scrub/fscounters.c
+++ b/scrub/fscounters.c
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
 #include <stdint.h>
diff --git a/scrub/fscounters.h b/scrub/fscounters.h
index 13bd9967f00..fb0923afe70 100644
--- a/scrub/fscounters.h
+++ b/scrub/fscounters.h
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_FSCOUNTERS_H_
 #define XFS_SCRUB_FSCOUNTERS_H_
diff --git a/scrub/inodes.c b/scrub/inodes.c
index 78f0914b8d9..d937915312d 100644
--- a/scrub/inodes.c
+++ b/scrub/inodes.c
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
 #include <stdint.h>
diff --git a/scrub/inodes.h b/scrub/inodes.h
index f03180458ab..40e1291d15e 100644
--- a/scrub/inodes.h
+++ b/scrub/inodes.h
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_INODES_H_
 #define XFS_SCRUB_INODES_H_
diff --git a/scrub/phase1.c b/scrub/phase1.c
index 2daf5c7bb38..9e838fad91f 100644
--- a/scrub/phase1.c
+++ b/scrub/phase1.c
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
 #include <unistd.h>
diff --git a/scrub/phase2.c b/scrub/phase2.c
index 8f82e2a6c04..48c9f589f7c 100644
--- a/scrub/phase2.c
+++ b/scrub/phase2.c
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
 #include <stdint.h>
diff --git a/scrub/phase3.c b/scrub/phase3.c
index 65e903f23d2..98742e0b72f 100644
--- a/scrub/phase3.c
+++ b/scrub/phase3.c
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
 #include <stdint.h>
diff --git a/scrub/phase4.c b/scrub/phase4.c
index ecd56056ca2..a67abd76a17 100644
--- a/scrub/phase4.c
+++ b/scrub/phase4.c
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
 #include <stdint.h>
diff --git a/scrub/phase5.c b/scrub/phase5.c
index 31405709657..4cf56ee591a 100644
--- a/scrub/phase5.c
+++ b/scrub/phase5.c
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
 #include <stdint.h>
diff --git a/scrub/phase6.c b/scrub/phase6.c
index afdb16b689c..e2de20c63c4 100644
--- a/scrub/phase6.c
+++ b/scrub/phase6.c
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
 #include <stdint.h>
diff --git a/scrub/phase7.c b/scrub/phase7.c
index 8d8034c36af..fe928d79eae 100644
--- a/scrub/phase7.c
+++ b/scrub/phase7.c
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
 #include <stdint.h>
diff --git a/scrub/progress.c b/scrub/progress.c
index a3d096f98e2..ffbf3ef3676 100644
--- a/scrub/progress.c
+++ b/scrub/progress.c
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
 #include <dirent.h>
diff --git a/scrub/progress.h b/scrub/progress.h
index c1a115cbe80..561695e2ac2 100644
--- a/scrub/progress.h
+++ b/scrub/progress.h
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_PROGRESS_H_
 #define XFS_SCRUB_PROGRESS_H_
diff --git a/scrub/read_verify.c b/scrub/read_verify.c
index be30f2688f9..435f54e2a84 100644
--- a/scrub/read_verify.c
+++ b/scrub/read_verify.c
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
 #include <stdint.h>
diff --git a/scrub/read_verify.h b/scrub/read_verify.h
index 650c46d447b..66f098954b6 100644
--- a/scrub/read_verify.h
+++ b/scrub/read_verify.h
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_READ_VERIFY_H_
 #define XFS_SCRUB_READ_VERIFY_H_
diff --git a/scrub/repair.c b/scrub/repair.c
index 5fc5ab836c7..107aa25a016 100644
--- a/scrub/repair.c
+++ b/scrub/repair.c
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
 #include <stdint.h>
diff --git a/scrub/repair.h b/scrub/repair.h
index 102e5779c70..b67c1ac95e6 100644
--- a/scrub/repair.h
+++ b/scrub/repair.h
@@ -1,7 +1,7 @@
-/* SPDX-License-Identifier: GPL-2.0+ */
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_REPAIR_H_
 #define XFS_SCRUB_REPAIR_H_
diff --git a/scrub/scrub.c b/scrub/scrub.c
index 1469058bd23..376dc1a1625 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
 #include <stdint.h>
diff --git a/scrub/scrub.h b/scrub/scrub.h
index 023069ee066..b3e2742a17b 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_SCRUB_H_
 #define XFS_SCRUB_SCRUB_H_
diff --git a/scrub/spacemap.c b/scrub/spacemap.c
index 03440d3a854..d0adae6780c 100644
--- a/scrub/spacemap.c
+++ b/scrub/spacemap.c
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
 #include <stdint.h>
diff --git a/scrub/spacemap.h b/scrub/spacemap.h
index 8a6d1e36158..787f4652fa2 100644
--- a/scrub/spacemap.h
+++ b/scrub/spacemap.h
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_SPACEMAP_H_
 #define XFS_SCRUB_SPACEMAP_H_
diff --git a/scrub/unicrash.c b/scrub/unicrash.c
index 24d4ea58211..dd0ec22feab 100644
--- a/scrub/unicrash.c
+++ b/scrub/unicrash.c
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
 #include <stdint.h>
diff --git a/scrub/unicrash.h b/scrub/unicrash.h
index 755afaef18c..6ac56e72176 100644
--- a/scrub/unicrash.h
+++ b/scrub/unicrash.h
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_UNICRASH_H_
 #define XFS_SCRUB_UNICRASH_H_
diff --git a/scrub/vfs.c b/scrub/vfs.c
index 3c1825a75e7..86e7910a1a6 100644
--- a/scrub/vfs.c
+++ b/scrub/vfs.c
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
 #include <stdint.h>
diff --git a/scrub/vfs.h b/scrub/vfs.h
index dc1099cf18d..24e04531227 100644
--- a/scrub/vfs.h
+++ b/scrub/vfs.h
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_VFS_H_
 #define XFS_SCRUB_VFS_H_
diff --git a/scrub/xfs_scrub.c b/scrub/xfs_scrub.c
index 597be59f9f9..1c409690736 100644
--- a/scrub/xfs_scrub.c
+++ b/scrub/xfs_scrub.c
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
 #include <pthread.h>
diff --git a/scrub/xfs_scrub.h b/scrub/xfs_scrub.h
index 0d6b9dad2c9..1c45f8753af 100644
--- a/scrub/xfs_scrub.h
+++ b/scrub/xfs_scrub.h
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2018 Oracle.  All Rights Reserved.
- * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_XFS_SCRUB_H_
 #define XFS_SCRUB_XFS_SCRUB_H_
diff --git a/scrub/xfs_scrub_all.in b/scrub/xfs_scrub_all.in
index 5b76b49adab..6276e32f515 100644
--- a/scrub/xfs_scrub_all.in
+++ b/scrub/xfs_scrub_all.in
@@ -1,9 +1,9 @@
 #!/usr/bin/python3
 
-# SPDX-License-Identifier: GPL-2.0+
+# SPDX-License-Identifier: GPL-2.0-or-later
 # Copyright (C) 2018 Oracle.  All rights reserved.
 #
-# Author: Darrick J. Wong <darrick.wong@oracle.com>
+# Author: Darrick J. Wong <djwong@kernel.org>
 
 # Run online scrubbers in parallel, but avoid thrashing.
 

[PATCH 2/3] xfs_scrub: add missing license and copyright information

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

These files are missing the required SPDX license and copyright
information.  Add them.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/xfs_scrub@.service.in      |    5 +++++
 scrub/xfs_scrub_all.cron.in      |    5 +++++
 scrub/xfs_scrub_all.service.in   |    5 +++++
 scrub/xfs_scrub_all.timer        |    5 +++++
 scrub/xfs_scrub_fail             |    5 +++++
 scrub/xfs_scrub_fail@.service.in |    5 +++++
 6 files changed, 30 insertions(+)


diff --git a/scrub/xfs_scrub@.service.in b/scrub/xfs_scrub@.service.in
index 6fb3f6ea2e9..d878eeda4fd 100644
--- a/scrub/xfs_scrub@.service.in
+++ b/scrub/xfs_scrub@.service.in
@@ -1,3 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
+# Author: Darrick J. Wong <djwong@kernel.org>
+
 [Unit]
 Description=Online XFS Metadata Check for %I
 OnFailure=xfs_scrub_fail@%i.service
diff --git a/scrub/xfs_scrub_all.cron.in b/scrub/xfs_scrub_all.cron.in
index 3dea9296077..c4d36958e76 100644
--- a/scrub/xfs_scrub_all.cron.in
+++ b/scrub/xfs_scrub_all.cron.in
@@ -1 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
+# Author: Darrick J. Wong <djwong@kernel.org>
+#
 10 3 * * 0 root test -e /run/systemd/system || @sbindir@/xfs_scrub_all
diff --git a/scrub/xfs_scrub_all.service.in b/scrub/xfs_scrub_all.service.in
index b1b80da40a3..4011ed271f9 100644
--- a/scrub/xfs_scrub_all.service.in
+++ b/scrub/xfs_scrub_all.service.in
@@ -1,3 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
+# Author: Darrick J. Wong <djwong@kernel.org>
+
 [Unit]
 Description=Online XFS Metadata Check for All Filesystems
 ConditionACPower=true
diff --git a/scrub/xfs_scrub_all.timer b/scrub/xfs_scrub_all.timer
index 2e4a33b1666..e6ba4215b43 100644
--- a/scrub/xfs_scrub_all.timer
+++ b/scrub/xfs_scrub_all.timer
@@ -1,3 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
+# Author: Darrick J. Wong <djwong@kernel.org>
+
 [Unit]
 Description=Periodic XFS Online Metadata Check for All Filesystems
 
diff --git a/scrub/xfs_scrub_fail b/scrub/xfs_scrub_fail
index 36dd50e9653..415efaa24d6 100755
--- a/scrub/xfs_scrub_fail
+++ b/scrub/xfs_scrub_fail
@@ -1,5 +1,10 @@
 #!/bin/bash
 
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
+# Author: Darrick J. Wong <djwong@kernel.org>
+
 # Email logs of failed xfs_scrub unit runs
 
 mailer=/usr/sbin/sendmail
diff --git a/scrub/xfs_scrub_fail@.service.in b/scrub/xfs_scrub_fail@.service.in
index 8d106e9ba4b..187adc17f6d 100644
--- a/scrub/xfs_scrub_fail@.service.in
+++ b/scrub/xfs_scrub_fail@.service.in
@@ -1,3 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
+# Author: Darrick J. Wong <djwong@kernel.org>
+
 [Unit]
 Description=Online XFS Metadata Check Failure Reporting for %I
 Documentation=man:xfs_scrub(8)

[PATCH 3/3] xfs_scrub: update copyright years for scrub/ files

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Update the copyright years in the scrub/ source code files.  This isn't
required, but it's helpful to remind myself just how long it's taken to
develop this feature.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/Makefile         |    2 +-
 scrub/common.c         |    2 +-
 scrub/common.h         |    2 +-
 scrub/counter.c        |    2 +-
 scrub/counter.h        |    2 +-
 scrub/descr.c          |    2 +-
 scrub/descr.h          |    2 +-
 scrub/disk.c           |    2 +-
 scrub/disk.h           |    2 +-
 scrub/filemap.c        |    2 +-
 scrub/filemap.h        |    2 +-
 scrub/fscounters.c     |    2 +-
 scrub/fscounters.h     |    2 +-
 scrub/inodes.c         |    2 +-
 scrub/inodes.h         |    2 +-
 scrub/phase1.c         |    2 +-
 scrub/phase2.c         |    2 +-
 scrub/phase3.c         |    2 +-
 scrub/phase4.c         |    2 +-
 scrub/phase5.c         |    2 +-
 scrub/phase6.c         |    2 +-
 scrub/phase7.c         |    2 +-
 scrub/progress.c       |    2 +-
 scrub/progress.h       |    2 +-
 scrub/read_verify.c    |    2 +-
 scrub/read_verify.h    |    2 +-
 scrub/repair.c         |    2 +-
 scrub/repair.h         |    2 +-
 scrub/scrub.c          |    2 +-
 scrub/scrub.h          |    2 +-
 scrub/spacemap.c       |    2 +-
 scrub/spacemap.h       |    2 +-
 scrub/unicrash.c       |    2 +-
 scrub/unicrash.h       |    2 +-
 scrub/vfs.c            |    2 +-
 scrub/vfs.h            |    2 +-
 scrub/xfs_scrub.c      |    2 +-
 scrub/xfs_scrub.h      |    2 +-
 scrub/xfs_scrub_all.in |    2 +-
 39 files changed, 39 insertions(+), 39 deletions(-)


diff --git a/scrub/Makefile b/scrub/Makefile
index 4ad54717833..24af9716120 100644
--- a/scrub/Makefile
+++ b/scrub/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-# Copyright (C) 2018 Oracle.  All Rights Reserved.
+# Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
 #
 
 TOPDIR = ..
diff --git a/scrub/common.c b/scrub/common.c
index 25a398c5fe4..283ac84e232 100644
--- a/scrub/common.c
+++ b/scrub/common.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
diff --git a/scrub/common.h b/scrub/common.h
index 26ef7c861c6..865c1caa446 100644
--- a/scrub/common.h
+++ b/scrub/common.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_COMMON_H_
diff --git a/scrub/counter.c b/scrub/counter.c
index b63ec721c34..2ee357f3a76 100644
--- a/scrub/counter.c
+++ b/scrub/counter.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
diff --git a/scrub/counter.h b/scrub/counter.h
index 77e380cc611..102d8bd8227 100644
--- a/scrub/counter.h
+++ b/scrub/counter.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_COUNTER_H_
diff --git a/scrub/descr.c b/scrub/descr.c
index bf0c5717a11..77d5378ec3f 100644
--- a/scrub/descr.c
+++ b/scrub/descr.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2019 Oracle.  All Rights Reserved.
+ * Copyright (C) 2019-2023 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
diff --git a/scrub/descr.h b/scrub/descr.h
index 0f5d9067e5d..0a014f5404b 100644
--- a/scrub/descr.h
+++ b/scrub/descr.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * Copyright (C) 2019 Oracle.  All Rights Reserved.
+ * Copyright (C) 2019-2023 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_DESCR_H_
diff --git a/scrub/disk.c b/scrub/disk.c
index 740a7ac962f..addb964d72f 100644
--- a/scrub/disk.c
+++ b/scrub/disk.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
diff --git a/scrub/disk.h b/scrub/disk.h
index 1f6c73aee3d..73c73ab57fb 100644
--- a/scrub/disk.h
+++ b/scrub/disk.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_DISK_H_
diff --git a/scrub/filemap.c b/scrub/filemap.c
index c1e520299ed..1fb69c38e3c 100644
--- a/scrub/filemap.c
+++ b/scrub/filemap.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
diff --git a/scrub/filemap.h b/scrub/filemap.h
index d123537aaff..062b42e597b 100644
--- a/scrub/filemap.h
+++ b/scrub/filemap.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_FILEMAP_H_
diff --git a/scrub/fscounters.c b/scrub/fscounters.c
index 6df0533a0b7..098bf87465e 100644
--- a/scrub/fscounters.c
+++ b/scrub/fscounters.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
diff --git a/scrub/fscounters.h b/scrub/fscounters.h
index fb0923afe70..a3dd6883702 100644
--- a/scrub/fscounters.h
+++ b/scrub/fscounters.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_FSCOUNTERS_H_
diff --git a/scrub/inodes.c b/scrub/inodes.c
index d937915312d..16c79cf495c 100644
--- a/scrub/inodes.c
+++ b/scrub/inodes.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
diff --git a/scrub/inodes.h b/scrub/inodes.h
index 40e1291d15e..9447fb56aa6 100644
--- a/scrub/inodes.h
+++ b/scrub/inodes.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_INODES_H_
diff --git a/scrub/phase1.c b/scrub/phase1.c
index 9e838fad91f..48ca8313b05 100644
--- a/scrub/phase1.c
+++ b/scrub/phase1.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
diff --git a/scrub/phase2.c b/scrub/phase2.c
index 48c9f589f7c..6b88384171f 100644
--- a/scrub/phase2.c
+++ b/scrub/phase2.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
diff --git a/scrub/phase3.c b/scrub/phase3.c
index 98742e0b72f..4235c228c0e 100644
--- a/scrub/phase3.c
+++ b/scrub/phase3.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
diff --git a/scrub/phase4.c b/scrub/phase4.c
index a67abd76a17..1228c7cb654 100644
--- a/scrub/phase4.c
+++ b/scrub/phase4.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
diff --git a/scrub/phase5.c b/scrub/phase5.c
index 4cf56ee591a..7e0eaca9042 100644
--- a/scrub/phase5.c
+++ b/scrub/phase5.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
diff --git a/scrub/phase6.c b/scrub/phase6.c
index e2de20c63c4..33c3c8bde3c 100644
--- a/scrub/phase6.c
+++ b/scrub/phase6.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
diff --git a/scrub/phase7.c b/scrub/phase7.c
index fe928d79eae..2fd96053f6c 100644
--- a/scrub/phase7.c
+++ b/scrub/phase7.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
diff --git a/scrub/progress.c b/scrub/progress.c
index ffbf3ef3676..f1bbade0828 100644
--- a/scrub/progress.c
+++ b/scrub/progress.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
diff --git a/scrub/progress.h b/scrub/progress.h
index 561695e2ac2..796939adb81 100644
--- a/scrub/progress.h
+++ b/scrub/progress.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_PROGRESS_H_
diff --git a/scrub/read_verify.c b/scrub/read_verify.c
index 435f54e2a84..29d7939549f 100644
--- a/scrub/read_verify.c
+++ b/scrub/read_verify.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
diff --git a/scrub/read_verify.h b/scrub/read_verify.h
index 66f098954b6..9d34d839c97 100644
--- a/scrub/read_verify.h
+++ b/scrub/read_verify.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_READ_VERIFY_H_
diff --git a/scrub/repair.c b/scrub/repair.c
index 107aa25a016..65b6dd89530 100644
--- a/scrub/repair.c
+++ b/scrub/repair.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
diff --git a/scrub/repair.h b/scrub/repair.h
index b67c1ac95e6..486617f1ce4 100644
--- a/scrub/repair.h
+++ b/scrub/repair.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_REPAIR_H_
diff --git a/scrub/scrub.c b/scrub/scrub.c
index 376dc1a1625..756f1915ab9 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
diff --git a/scrub/scrub.h b/scrub/scrub.h
index b3e2742a17b..f7e66bb614b 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_SCRUB_H_
diff --git a/scrub/spacemap.c b/scrub/spacemap.c
index d0adae6780c..b6fd411816b 100644
--- a/scrub/spacemap.c
+++ b/scrub/spacemap.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
diff --git a/scrub/spacemap.h b/scrub/spacemap.h
index 787f4652fa2..51975341b16 100644
--- a/scrub/spacemap.h
+++ b/scrub/spacemap.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_SPACEMAP_H_
diff --git a/scrub/unicrash.c b/scrub/unicrash.c
index dd0ec22feab..dd30164354e 100644
--- a/scrub/unicrash.c
+++ b/scrub/unicrash.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
diff --git a/scrub/unicrash.h b/scrub/unicrash.h
index 6ac56e72176..3b6f40540aa 100644
--- a/scrub/unicrash.h
+++ b/scrub/unicrash.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_UNICRASH_H_
diff --git a/scrub/vfs.c b/scrub/vfs.c
index 86e7910a1a6..9e459d6243f 100644
--- a/scrub/vfs.c
+++ b/scrub/vfs.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
diff --git a/scrub/vfs.h b/scrub/vfs.h
index 24e04531227..1ac41e5aac0 100644
--- a/scrub/vfs.h
+++ b/scrub/vfs.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_VFS_H_
diff --git a/scrub/xfs_scrub.c b/scrub/xfs_scrub.c
index 1c409690736..a1b67544391 100644
--- a/scrub/xfs_scrub.c
+++ b/scrub/xfs_scrub.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
diff --git a/scrub/xfs_scrub.h b/scrub/xfs_scrub.h
index 1c45f8753af..7aea79d9555 100644
--- a/scrub/xfs_scrub.h
+++ b/scrub/xfs_scrub.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #ifndef XFS_SCRUB_XFS_SCRUB_H_
diff --git a/scrub/xfs_scrub_all.in b/scrub/xfs_scrub_all.in
index 6276e32f515..5042321a738 100644
--- a/scrub/xfs_scrub_all.in
+++ b/scrub/xfs_scrub_all.in
@@ -1,7 +1,7 @@
 #!/usr/bin/python3
 
 # SPDX-License-Identifier: GPL-2.0-or-later
-# Copyright (C) 2018 Oracle.  All rights reserved.
+# Copyright (C) 2018-2024 Oracle.  All rights reserved.
 #
 # Author: Darrick J. Wong <djwong@kernel.org>
 

[PATCH 1/2] mkfs: allow sizing allocation groups for concurrency

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add a -d concurrency= option to mkfs so that sysadmins can configure the
filesystem so that there are enough allocation groups that the specified
number of threads can (in theory) can find an uncontended group to
allocate space from.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 man/man8/mkfs.xfs.8.in |   27 +++++++++
 mkfs/xfs_mkfs.c        |  150 +++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 173 insertions(+), 4 deletions(-)


diff --git a/man/man8/mkfs.xfs.8.in b/man/man8/mkfs.xfs.8.in
index c152546a47d..b18daa23395 100644
--- a/man/man8/mkfs.xfs.8.in
+++ b/man/man8/mkfs.xfs.8.in
@@ -504,6 +504,33 @@ directories.
 By default,
 .B mkfs.xfs
 will not enable DAX mode.
+.TP
+.BI concurrency= value
+Create enough allocation groups to handle the desired level of concurrency.
+The goal of this calculation scheme is to set the number of allocation groups
+to an integer multiple of the number of writer threads desired, to minimize
+contention of AG locks.
+This scheme will neither create fewer AGs than would be created by the default
+configuration, nor will it create AGs smaller than 4GB.
+This option is not compatible with the
+.B agcount
+or
+.B agsize
+options.
+The magic value
+.I nr_cpus
+or
+.I 1
+or no value at all will set this parameter to the number of active processors
+in the system.
+If the kernel advertises that the data device is a non-mechanical storage
+device,
+.B mkfs.xfs
+will use this new geometry calculation scheme.
+The magic value of
+.I 0
+forces use of the older AG geometry calculations that is used for mechanical
+storage.
 .RE
 .TP
 .B \-f
diff --git a/mkfs/xfs_mkfs.c b/mkfs/xfs_mkfs.c
index f29f902982d..fbe40b7edf1 100644
--- a/mkfs/xfs_mkfs.c
+++ b/mkfs/xfs_mkfs.c
@@ -77,6 +77,7 @@ enum {
 	D_EXTSZINHERIT,
 	D_COWEXTSIZE,
 	D_DAXINHERIT,
+	D_CONCURRENCY,
 	D_MAX_OPTS,
 };
 
@@ -318,11 +319,13 @@ static struct opt_params dopts = {
 		[D_EXTSZINHERIT] = "extszinherit",
 		[D_COWEXTSIZE] = "cowextsize",
 		[D_DAXINHERIT] = "daxinherit",
+		[D_CONCURRENCY] = "concurrency",
 		[D_MAX_OPTS] = NULL,
 	},
 	.subopt_params = {
 		{ .index = D_AGCOUNT,
 		  .conflicts = { { &dopts, D_AGSIZE },
+				 { &dopts, D_CONCURRENCY },
 				 { NULL, LAST_CONFLICT } },
 		  .minval = 1,
 		  .maxval = XFS_MAX_AGNUMBER,
@@ -365,6 +368,7 @@ static struct opt_params dopts = {
 		},
 		{ .index = D_AGSIZE,
 		  .conflicts = { { &dopts, D_AGCOUNT },
+				 { &dopts, D_CONCURRENCY },
 				 { NULL, LAST_CONFLICT } },
 		  .convert = true,
 		  .minval = XFS_AG_MIN_BYTES,
@@ -440,6 +444,14 @@ static struct opt_params dopts = {
 		  .maxval = 1,
 		  .defaultval = 1,
 		},
+		{ .index = D_CONCURRENCY,
+		  .conflicts = { { &dopts, D_AGCOUNT },
+				 { &dopts, D_AGSIZE },
+				 { NULL, LAST_CONFLICT } },
+		  .minval = 0,
+		  .maxval = INT_MAX,
+		  .defaultval = 1,
+		},
 	},
 };
 
@@ -891,6 +903,7 @@ struct cli_params {
 	int	lsunit;
 	int	is_supported;
 	int	proto_slashes_are_spaces;
+	int	data_concurrency;
 
 	/* parameters where 0 is not a valid value */
 	int64_t	agcount;
@@ -993,7 +1006,7 @@ usage( void )
 			    inobtcount=0|1,bigtime=0|1]\n\
 /* data subvol */	[-d agcount=n,agsize=n,file,name=xxx,size=num,\n\
 			    (sunit=value,swidth=value|su=num,sw=num|noalign),\n\
-			    sectsize=num\n\
+			    sectsize=num,concurrency=num]\n\
 /* force overwrite */	[-f]\n\
 /* inode size */	[-i perblock=n|size=num,maxpct=n,attr=0|1|2,\n\
 			    projid32bit=0|1,sparse=0|1,nrext64=0|1]\n\
@@ -1090,6 +1103,19 @@ invalid_cfgfile_opt(
 		filename, section, name, value);
 }
 
+static int
+nr_cpus(void)
+{
+	static long	cpus = -1;
+
+	if (cpus < 0)
+		cpus = sysconf(_SC_NPROCESSORS_ONLN);
+	if (cpus < 0)
+		return 0;
+
+	return min(INT_MAX, cpus);
+}
+
 static void
 check_device_type(
 	struct libxfs_dev	*dev,
@@ -1544,6 +1570,30 @@ cfgfile_opts_parser(
 	return 0;
 }
 
+static void
+set_data_concurrency(
+	struct opt_params	*opts,
+	int			subopt,
+	struct cli_params	*cli,
+	const char		*value)
+{
+	long long		optnum;
+
+	/*
+	 * "nr_cpus" or "1" means set the concurrency level to the CPU count.
+	 * If this cannot be determined, fall back to the default AG geometry.
+	 */
+	if (!strcmp(value, "nr_cpus"))
+		optnum = 1;
+	else
+		optnum = getnum(value, opts, subopt);
+
+	if (optnum == 1)
+		cli->data_concurrency = nr_cpus();
+	else
+		cli->data_concurrency = optnum;
+}
+
 static int
 data_opts_parser(
 	struct opt_params	*opts,
@@ -1615,6 +1665,9 @@ data_opts_parser(
 		else
 			cli->fsx.fsx_xflags &= ~FS_XFLAG_DAX;
 		break;
+	case D_CONCURRENCY:
+		set_data_concurrency(opts, subopt, cli, value);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -3034,12 +3087,98 @@ _("cannot have an rt subvolume with zero extents\n"));
 						NBBY * cfg->blocksize);
 }
 
+static bool
+ddev_is_solidstate(
+	struct libxfs_init	*xi)
+{
+	unsigned short		rotational = 1;
+	int			error;
+
+	error = ioctl(xi->data.fd, BLKROTATIONAL, &rotational);
+	if (error)
+		return false;
+
+	return rotational == 0;
+}
+
+static void
+calc_concurrency_ag_geometry(
+	struct mkfs_params	*cfg,
+	struct cli_params	*cli,
+	struct libxfs_init	*xi)
+{
+	uint64_t		try_agsize;
+	uint64_t		def_agsize;
+	uint64_t		def_agcount;
+	int			nr_threads = cli->data_concurrency;
+	int			try_threads;
+
+	calc_default_ag_geometry(cfg->blocklog, cfg->dblocks, cfg->dsunit,
+			&def_agsize, &def_agcount);
+	try_agsize = def_agsize;
+
+	/*
+	 * If the caller doesn't have a particular concurrency level in mind,
+	 * set it to the number of CPUs in the system.
+	 */
+	if (nr_threads < 0)
+		nr_threads = nr_cpus();
+
+	/*
+	 * Don't create fewer AGs than what we would create with the default
+	 * geometry calculation.
+	 */
+	if (!nr_threads || nr_threads < def_agcount)
+		goto out;
+
+	/*
+	 * Let's try matching the number of AGs to the number of CPUs.  If the
+	 * proposed geometry results in AGs smaller than 4GB, reduce the AG
+	 * count until we have 4GB AGs.  Don't let the thread count go below
+	 * the default geometry calculation.
+	 */
+	try_threads = nr_threads;
+	try_agsize = cfg->dblocks / try_threads;
+	if (try_agsize < GIGABYTES(4, cfg->blocklog)) {
+		do {
+			try_threads--;
+			if (try_threads <= def_agcount) {
+				try_agsize = def_agsize;
+				goto out;
+			}
+
+			try_agsize = cfg->dblocks / try_threads;
+		} while (try_agsize < GIGABYTES(4, cfg->blocklog));
+		goto out;
+	}
+
+	/*
+	 * For large filesystems we try to ensure that the AG count is a
+	 * multiple of the desired thread count.  Specifically, if the proposed
+	 * AG size is larger than both the maximum AG size and the AG size we
+	 * would have gotten with the defaults, add the thread count to the AG
+	 * count until we get an AG size below both of those factors.
+	 */
+	while (try_agsize > XFS_AG_MAX_BLOCKS(cfg->blocklog) &&
+	       try_agsize > def_agsize) {
+		try_threads += nr_threads;
+		try_agsize = cfg->dblocks / try_threads;
+	}
+
+out:
+	cfg->agsize = try_agsize;
+	cfg->agcount = howmany(cfg->dblocks, cfg->agsize);
+}
+
 static void
 calculate_initial_ag_geometry(
 	struct mkfs_params	*cfg,
-	struct cli_params	*cli)
+	struct cli_params	*cli,
+	struct libxfs_init	*xi)
 {
-	if (cli->agsize) {		/* User-specified AG size */
+	if (cli->data_concurrency > 0) {
+		calc_concurrency_ag_geometry(cfg, cli, xi);
+	} else if (cli->agsize) {	/* User-specified AG size */
 		cfg->agsize = getnum(cli->agsize, &dopts, D_AGSIZE);
 
 		/*
@@ -3059,6 +3198,8 @@ _("agsize (%s) not a multiple of fs blk size (%d)\n"),
 		cfg->agcount = cli->agcount;
 		cfg->agsize = cfg->dblocks / cfg->agcount +
 				(cfg->dblocks % cfg->agcount != 0);
+	} else if (cli->data_concurrency == -1 && ddev_is_solidstate(xi)) {
+		calc_concurrency_ag_geometry(cfg, cli, xi);
 	} else {
 		calc_default_ag_geometry(cfg->blocklog, cfg->dblocks,
 					 cfg->dsunit, &cfg->agsize,
@@ -4060,6 +4201,7 @@ main(
 		.xi = &xi,
 		.loginternal = 1,
 		.is_supported	= 1,
+		.data_concurrency = -1, /* auto detect non-mechanical storage */
 	};
 	struct mkfs_params	cfg = {};
 
@@ -4244,7 +4386,7 @@ main(
 	 * dependent on device sizes. Once calculated, make sure everything
 	 * aligns to device geometry correctly.
 	 */
-	calculate_initial_ag_geometry(&cfg, &cli);
+	calculate_initial_ag_geometry(&cfg, &cli, &xi);
 	align_ag_geometry(&cfg);
 
 	calculate_imaxpct(&cfg, &cli);

[PATCH 2/2] mkfs: allow sizing internal logs for concurrency

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add a -l option to mkfs so that sysadmins can configure the filesystem
so that the log can handle a certain number of transactions (front and
backend) without any threads contending for log grant space.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 man/man8/mkfs.xfs.8.in |   19 +++++++++
 mkfs/xfs_mkfs.c        |  104 +++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 120 insertions(+), 3 deletions(-)


diff --git a/man/man8/mkfs.xfs.8.in b/man/man8/mkfs.xfs.8.in
index b18daa23395..8060d342c2a 100644
--- a/man/man8/mkfs.xfs.8.in
+++ b/man/man8/mkfs.xfs.8.in
@@ -795,6 +795,25 @@ if you want to disable this feature for older kernels which don't support
 it.
 .IP
 This option is only tunable on the deprecated V4 format.
+.TP
+.BI concurrency= value
+Allocate a log that is estimated to be large enough to handle the desired level
+of concurrency without userspace program threads contending for log space.
+This scheme will neither create a log smaller than the minimum required,
+nor create a log larger than the maximum possible.
+This option is only valid for internal logs and is not compatible with the
+size option.
+This option is not compatible with the
+.B logdev
+or
+.B size
+options.
+The magic value
+.I nr_cpus
+or
+.I 1
+or no value at all will set this parameter to the number of active processors
+in the system.
 .RE
 .PP
 .PD 0
diff --git a/mkfs/xfs_mkfs.c b/mkfs/xfs_mkfs.c
index fbe40b7edf1..cb09c6466a6 100644
--- a/mkfs/xfs_mkfs.c
+++ b/mkfs/xfs_mkfs.c
@@ -105,6 +105,7 @@ enum {
 	L_FILE,
 	L_NAME,
 	L_LAZYSBCNTR,
+	L_CONCURRENCY,
 	L_MAX_OPTS,
 };
 
@@ -541,6 +542,7 @@ static struct opt_params lopts = {
 		[L_FILE] = "file",
 		[L_NAME] = "name",
 		[L_LAZYSBCNTR] = "lazy-count",
+		[L_CONCURRENCY] = "concurrency",
 		[L_MAX_OPTS] = NULL,
 	},
 	.subopt_params = {
@@ -561,7 +563,8 @@ static struct opt_params lopts = {
 		  .defaultval = 1,
 		},
 		{ .index = L_SIZE,
-		  .conflicts = { { NULL, LAST_CONFLICT } },
+		  .conflicts = { { &lopts, L_CONCURRENCY },
+				 { NULL, LAST_CONFLICT } },
 		  .convert = true,
 		  .minval = 2 * 1024 * 1024LL,	/* XXX: XFS_MIN_LOG_BYTES */
 		  .maxval = XFS_MAX_LOG_BYTES,
@@ -592,6 +595,7 @@ static struct opt_params lopts = {
 		  .conflicts = { { &lopts, L_AGNUM },
 				 { &lopts, L_NAME },
 				 { &lopts, L_INTERNAL },
+				 { &lopts, L_CONCURRENCY },
 				 { NULL, LAST_CONFLICT } },
 		  .defaultval = SUBOPT_NEEDS_VAL,
 		},
@@ -606,6 +610,7 @@ static struct opt_params lopts = {
 		},
 		{ .index = L_FILE,
 		  .conflicts = { { &lopts, L_INTERNAL },
+				 { &lopts, L_CONCURRENCY },
 				 { NULL, LAST_CONFLICT } },
 		  .minval = 0,
 		  .maxval = 1,
@@ -624,6 +629,15 @@ static struct opt_params lopts = {
 		  .maxval = 1,
 		  .defaultval = 1,
 		},
+		{ .index = L_CONCURRENCY,
+		  .conflicts = { { &lopts, L_SIZE },
+				 { &lopts, L_FILE },
+				 { &lopts, L_DEV },
+				 { NULL, LAST_CONFLICT } },
+		  .minval = 0,
+		  .maxval = INT_MAX,
+		  .defaultval = 1,
+		},
 	},
 };
 
@@ -904,6 +918,7 @@ struct cli_params {
 	int	is_supported;
 	int	proto_slashes_are_spaces;
 	int	data_concurrency;
+	int	log_concurrency;
 
 	/* parameters where 0 is not a valid value */
 	int64_t	agcount;
@@ -1012,7 +1027,8 @@ usage( void )
 			    projid32bit=0|1,sparse=0|1,nrext64=0|1]\n\
 /* no discard */	[-K]\n\
 /* log subvol */	[-l agnum=n,internal,size=num,logdev=xxx,version=n\n\
-			    sunit=value|su=num,sectsize=num,lazy-count=0|1]\n\
+			    sunit=value|su=num,sectsize=num,lazy-count=0|1,\n\
+			    concurrency=num]\n\
 /* label */		[-L label (maximum 12 characters)]\n\
 /* naming */		[-n size=num,version=2|ci,ftype=0|1]\n\
 /* no-op info only */	[-N]\n\
@@ -1712,6 +1728,30 @@ inode_opts_parser(
 	return 0;
 }
 
+static void
+set_log_concurrency(
+	struct opt_params	*opts,
+	int			subopt,
+	const char		*value,
+	struct cli_params	*cli)
+{
+	long long		optnum;
+
+	/*
+	 * "nr_cpus" or 1 means set the concurrency level to the CPU count.  If
+	 * this cannot be determined, fall back to the default computation.
+	 */
+	if (!strcmp(value, "nr_cpus"))
+		optnum = 1;
+	else
+		optnum = getnum(value, opts, subopt);
+
+	if (optnum == 1)
+		cli->log_concurrency = nr_cpus();
+	else
+		cli->log_concurrency = optnum;
+}
+
 static int
 log_opts_parser(
 	struct opt_params	*opts,
@@ -1752,6 +1792,9 @@ log_opts_parser(
 	case L_LAZYSBCNTR:
 		cli->sb_feat.lazy_sb_counters = getnum(value, opts, subopt);
 		break;
+	case L_CONCURRENCY:
+		set_log_concurrency(opts, subopt, value, cli);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -3607,15 +3650,59 @@ _("internal log size %lld too large, must be less than %d\n"),
 	cfg->logblocks = min(cfg->logblocks, *max_logblocks);
 }
 
+static uint64_t
+calc_concurrency_logblocks(
+	struct mkfs_params	*cfg,
+	struct cli_params	*cli,
+	struct libxfs_init	*xi,
+	unsigned int		max_tx_bytes)
+{
+	uint64_t		log_bytes;
+	uint64_t		logblocks = cfg->logblocks;
+	unsigned int		new_logblocks;
+
+	if (cli->log_concurrency < 0) {
+		if (!ddev_is_solidstate(xi))
+			goto out;
+
+		cli->log_concurrency = nr_cpus();
+	}
+	if (cli->log_concurrency == 0)
+		goto out;
+
+	/*
+	 * If this filesystem is smaller than a gigabyte, there's little to be
+	 * gained from making the log larger.
+	 */
+	if (cfg->dblocks < GIGABYTES(1, cfg->blocklog))
+		goto out;
+
+	/*
+	 * Create a log that is large enough to handle simultaneous maximally
+	 * sized transactions at the concurrency level specified by the user
+	 * without blocking for space.  Increase the figure by 50% so that
+	 * background threads can also run.
+	 */
+	log_bytes = max_tx_bytes * 3 * cli->log_concurrency / 2;
+	new_logblocks = min(XFS_MAX_LOG_BYTES >> cfg->blocklog,
+				log_bytes >> cfg->blocklog);
+
+	logblocks = max(logblocks, new_logblocks);
+out:
+	return logblocks;
+}
+
 static void
 calculate_log_size(
 	struct mkfs_params	*cfg,
 	struct cli_params	*cli,
+	struct libxfs_init	*xi,
 	struct xfs_mount	*mp)
 {
 	struct xfs_sb		*sbp = &mp->m_sb;
 	int			min_logblocks;	/* absolute minimum */
 	int			max_logblocks;	/* absolute max for this AG */
+	unsigned int		max_tx_bytes = 0;
 	struct xfs_mount	mount;
 	struct libxfs_init	dummy_init = { };
 
@@ -3624,6 +3711,12 @@ calculate_log_size(
 	mount.m_sb = *sbp;
 	libxfs_mount(&mount, &mp->m_sb, &dummy_init, 0);
 	min_logblocks = libxfs_log_calc_minimum_size(&mount);
+	if (cli->log_concurrency != 0) {
+		struct xfs_trans_res	res;
+
+		libxfs_log_get_max_trans_res(&mount, &res);
+		max_tx_bytes = res.tr_logres * res.tr_logcount;
+	}
 	libxfs_umount(&mount);
 
 	ASSERT(min_logblocks);
@@ -3681,6 +3774,10 @@ _("max log size %d smaller than min log size %d, filesystem is too small\n"),
 		cfg->logblocks = (cfg->dblocks << cfg->blocklog) / 2048;
 		cfg->logblocks = cfg->logblocks >> cfg->blocklog;
 
+		if (cli->log_concurrency != 0)
+			cfg->logblocks = calc_concurrency_logblocks(cfg, cli,
+							xi, max_tx_bytes);
+
 		/* But don't go below a reasonable size */
 		cfg->logblocks = max(cfg->logblocks,
 				XFS_MIN_REALISTIC_LOG_BLOCKS(cfg->blocklog));
@@ -4202,6 +4299,7 @@ main(
 		.loginternal = 1,
 		.is_supported	= 1,
 		.data_concurrency = -1, /* auto detect non-mechanical storage */
+		.log_concurrency = -1, /* auto detect non-mechanical ddev */
 	};
 	struct mkfs_params	cfg = {};
 
@@ -4403,7 +4501,7 @@ main(
 	 * With the mount set up, we can finally calculate the log size
 	 * constraints and do default size calculations and final validation
 	 */
-	calculate_log_size(&cfg, &cli, mp);
+	calculate_log_size(&cfg, &cli, &xi, mp);
 
 	finish_superblock_setup(&cfg, mp, sbp);
 

[PATCH 1/3] libfrog: rename XFROG_SCRUB_TYPE_* to XFROG_SCRUB_GROUP_*

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

I didn't do a good job of naming XFROG_SCRUB_TYPE when I created that
enumeration.  The goal of the enum is to group the scrub ioctl's
XFS_SCRUB_TYPE_* codes by principal filesystem object (AG, inode, etc.)
but for some dumb reason I chose to reuse "type".  This is confusing,
so fix this sin.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 io/scrub.c      |   12 ++++++------
 libfrog/scrub.c |   50 +++++++++++++++++++++++++-------------------------
 libfrog/scrub.h |   16 ++++++++--------
 scrub/scrub.c   |   54 +++++++++++++++++++++++++++---------------------------
 4 files changed, 66 insertions(+), 66 deletions(-)


diff --git a/io/scrub.c b/io/scrub.c
index 403b3a7282e..d6eda5bea53 100644
--- a/io/scrub.c
+++ b/io/scrub.c
@@ -166,23 +166,23 @@ parse_args(
 	meta->sm_type = type;
 	meta->sm_flags = flags;
 
-	switch (d->type) {
-	case XFROG_SCRUB_TYPE_INODE:
+	switch (d->group) {
+	case XFROG_SCRUB_GROUP_INODE:
 		if (!parse_inode(argc, argv, optind, &meta->sm_ino,
 						     &meta->sm_gen)) {
 			exitcode = 1;
 			return command_usage(cmdinfo);
 		}
 		break;
-	case XFROG_SCRUB_TYPE_AGHEADER:
-	case XFROG_SCRUB_TYPE_PERAG:
+	case XFROG_SCRUB_GROUP_AGHEADER:
+	case XFROG_SCRUB_GROUP_PERAG:
 		if (!parse_agno(argc, argv, optind, &meta->sm_agno)) {
 			exitcode = 1;
 			return command_usage(cmdinfo);
 		}
 		break;
-	case XFROG_SCRUB_TYPE_FS:
-	case XFROG_SCRUB_TYPE_NONE:
+	case XFROG_SCRUB_GROUP_FS:
+	case XFROG_SCRUB_GROUP_NONE:
 		if (!parse_none(argc, optind)) {
 			exitcode = 1;
 			return command_usage(cmdinfo);
diff --git a/libfrog/scrub.c b/libfrog/scrub.c
index d900bf2af63..90fc2b1a40c 100644
--- a/libfrog/scrub.c
+++ b/libfrog/scrub.c
@@ -12,127 +12,127 @@ const struct xfrog_scrub_descr xfrog_scrubbers[XFS_SCRUB_TYPE_NR] = {
 	[XFS_SCRUB_TYPE_PROBE] = {
 		.name	= "probe",
 		.descr	= "metadata",
-		.type	= XFROG_SCRUB_TYPE_NONE,
+		.group	= XFROG_SCRUB_GROUP_NONE,
 	},
 	[XFS_SCRUB_TYPE_SB] = {
 		.name	= "sb",
 		.descr	= "superblock",
-		.type	= XFROG_SCRUB_TYPE_AGHEADER,
+		.group	= XFROG_SCRUB_GROUP_AGHEADER,
 	},
 	[XFS_SCRUB_TYPE_AGF] = {
 		.name	= "agf",
 		.descr	= "free space header",
-		.type	= XFROG_SCRUB_TYPE_AGHEADER,
+		.group	= XFROG_SCRUB_GROUP_AGHEADER,
 	},
 	[XFS_SCRUB_TYPE_AGFL] = {
 		.name	= "agfl",
 		.descr	= "free list",
-		.type	= XFROG_SCRUB_TYPE_AGHEADER,
+		.group	= XFROG_SCRUB_GROUP_AGHEADER,
 	},
 	[XFS_SCRUB_TYPE_AGI] = {
 		.name	= "agi",
 		.descr	= "inode header",
-		.type	= XFROG_SCRUB_TYPE_AGHEADER,
+		.group	= XFROG_SCRUB_GROUP_AGHEADER,
 	},
 	[XFS_SCRUB_TYPE_BNOBT] = {
 		.name	= "bnobt",
 		.descr	= "freesp by block btree",
-		.type	= XFROG_SCRUB_TYPE_PERAG,
+		.group	= XFROG_SCRUB_GROUP_PERAG,
 	},
 	[XFS_SCRUB_TYPE_CNTBT] = {
 		.name	= "cntbt",
 		.descr	= "freesp by length btree",
-		.type	= XFROG_SCRUB_TYPE_PERAG,
+		.group	= XFROG_SCRUB_GROUP_PERAG,
 	},
 	[XFS_SCRUB_TYPE_INOBT] = {
 		.name	= "inobt",
 		.descr	= "inode btree",
-		.type	= XFROG_SCRUB_TYPE_PERAG,
+		.group	= XFROG_SCRUB_GROUP_PERAG,
 	},
 	[XFS_SCRUB_TYPE_FINOBT] = {
 		.name	= "finobt",
 		.descr	= "free inode btree",
-		.type	= XFROG_SCRUB_TYPE_PERAG,
+		.group	= XFROG_SCRUB_GROUP_PERAG,
 	},
 	[XFS_SCRUB_TYPE_RMAPBT] = {
 		.name	= "rmapbt",
 		.descr	= "reverse mapping btree",
-		.type	= XFROG_SCRUB_TYPE_PERAG,
+		.group	= XFROG_SCRUB_GROUP_PERAG,
 	},
 	[XFS_SCRUB_TYPE_REFCNTBT] = {
 		.name	= "refcountbt",
 		.descr	= "reference count btree",
-		.type	= XFROG_SCRUB_TYPE_PERAG,
+		.group	= XFROG_SCRUB_GROUP_PERAG,
 	},
 	[XFS_SCRUB_TYPE_INODE] = {
 		.name	= "inode",
 		.descr	= "inode record",
-		.type	= XFROG_SCRUB_TYPE_INODE,
+		.group	= XFROG_SCRUB_GROUP_INODE,
 	},
 	[XFS_SCRUB_TYPE_BMBTD] = {
 		.name	= "bmapbtd",
 		.descr	= "data block map",
-		.type	= XFROG_SCRUB_TYPE_INODE,
+		.group	= XFROG_SCRUB_GROUP_INODE,
 	},
 	[XFS_SCRUB_TYPE_BMBTA] = {
 		.name	= "bmapbta",
 		.descr	= "attr block map",
-		.type	= XFROG_SCRUB_TYPE_INODE,
+		.group	= XFROG_SCRUB_GROUP_INODE,
 	},
 	[XFS_SCRUB_TYPE_BMBTC] = {
 		.name	= "bmapbtc",
 		.descr	= "CoW block map",
-		.type	= XFROG_SCRUB_TYPE_INODE,
+		.group	= XFROG_SCRUB_GROUP_INODE,
 	},
 	[XFS_SCRUB_TYPE_DIR] = {
 		.name	= "directory",
 		.descr	= "directory entries",
-		.type	= XFROG_SCRUB_TYPE_INODE,
+		.group	= XFROG_SCRUB_GROUP_INODE,
 	},
 	[XFS_SCRUB_TYPE_XATTR] = {
 		.name	= "xattr",
 		.descr	= "extended attributes",
-		.type	= XFROG_SCRUB_TYPE_INODE,
+		.group	= XFROG_SCRUB_GROUP_INODE,
 	},
 	[XFS_SCRUB_TYPE_SYMLINK] = {
 		.name	= "symlink",
 		.descr	= "symbolic link",
-		.type	= XFROG_SCRUB_TYPE_INODE,
+		.group	= XFROG_SCRUB_GROUP_INODE,
 	},
 	[XFS_SCRUB_TYPE_PARENT] = {
 		.name	= "parent",
 		.descr	= "parent pointer",
-		.type	= XFROG_SCRUB_TYPE_INODE,
+		.group	= XFROG_SCRUB_GROUP_INODE,
 	},
 	[XFS_SCRUB_TYPE_RTBITMAP] = {
 		.name	= "rtbitmap",
 		.descr	= "realtime bitmap",
-		.type	= XFROG_SCRUB_TYPE_FS,
+		.group	= XFROG_SCRUB_GROUP_FS,
 	},
 	[XFS_SCRUB_TYPE_RTSUM] = {
 		.name	= "rtsummary",
 		.descr	= "realtime summary",
-		.type	= XFROG_SCRUB_TYPE_FS,
+		.group	= XFROG_SCRUB_GROUP_FS,
 	},
 	[XFS_SCRUB_TYPE_UQUOTA] = {
 		.name	= "usrquota",
 		.descr	= "user quotas",
-		.type	= XFROG_SCRUB_TYPE_FS,
+		.group	= XFROG_SCRUB_GROUP_FS,
 	},
 	[XFS_SCRUB_TYPE_GQUOTA] = {
 		.name	= "grpquota",
 		.descr	= "group quotas",
-		.type	= XFROG_SCRUB_TYPE_FS,
+		.group	= XFROG_SCRUB_GROUP_FS,
 	},
 	[XFS_SCRUB_TYPE_PQUOTA] = {
 		.name	= "prjquota",
 		.descr	= "project quotas",
-		.type	= XFROG_SCRUB_TYPE_FS,
+		.group	= XFROG_SCRUB_GROUP_FS,
 	},
 	[XFS_SCRUB_TYPE_FSCOUNTERS] = {
 		.name	= "fscounters",
 		.descr	= "filesystem summary counters",
-		.type	= XFROG_SCRUB_TYPE_FS,
+		.group	= XFROG_SCRUB_GROUP_FS,
 		.flags	= XFROG_SCRUB_DESCR_SUMMARY,
 	},
 };
diff --git a/libfrog/scrub.h b/libfrog/scrub.h
index e43d8c244e4..43a882321f9 100644
--- a/libfrog/scrub.h
+++ b/libfrog/scrub.h
@@ -6,20 +6,20 @@
 #ifndef __LIBFROG_SCRUB_H__
 #define __LIBFROG_SCRUB_H__
 
-/* Type info and names for the scrub types. */
-enum xfrog_scrub_type {
-	XFROG_SCRUB_TYPE_NONE,		/* not metadata */
-	XFROG_SCRUB_TYPE_AGHEADER,	/* per-AG header */
-	XFROG_SCRUB_TYPE_PERAG,		/* per-AG metadata */
-	XFROG_SCRUB_TYPE_FS,		/* per-FS metadata */
-	XFROG_SCRUB_TYPE_INODE,		/* per-inode metadata */
+/* Group the scrub types by principal filesystem object. */
+enum xfrog_scrub_group {
+	XFROG_SCRUB_GROUP_NONE,		/* not metadata */
+	XFROG_SCRUB_GROUP_AGHEADER,	/* per-AG header */
+	XFROG_SCRUB_GROUP_PERAG,	/* per-AG metadata */
+	XFROG_SCRUB_GROUP_FS,		/* per-FS metadata */
+	XFROG_SCRUB_GROUP_INODE,	/* per-inode metadata */
 };
 
 /* Catalog of scrub types and names, indexed by XFS_SCRUB_TYPE_* */
 struct xfrog_scrub_descr {
 	const char		*name;
 	const char		*descr;
-	enum xfrog_scrub_type	type;
+	enum xfrog_scrub_group	group;
 	unsigned int		flags;
 };
 
diff --git a/scrub/scrub.c b/scrub/scrub.c
index 756f1915ab9..cde9babc557 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -34,21 +34,21 @@ format_scrub_descr(
 	struct xfs_scrub_metadata	*meta = where;
 	const struct xfrog_scrub_descr	*sc = &xfrog_scrubbers[meta->sm_type];
 
-	switch (sc->type) {
-	case XFROG_SCRUB_TYPE_AGHEADER:
-	case XFROG_SCRUB_TYPE_PERAG:
+	switch (sc->group) {
+	case XFROG_SCRUB_GROUP_AGHEADER:
+	case XFROG_SCRUB_GROUP_PERAG:
 		return snprintf(buf, buflen, _("AG %u %s"), meta->sm_agno,
 				_(sc->descr));
 		break;
-	case XFROG_SCRUB_TYPE_INODE:
+	case XFROG_SCRUB_GROUP_INODE:
 		return scrub_render_ino_descr(ctx, buf, buflen,
 				meta->sm_ino, meta->sm_gen, "%s",
 				_(sc->descr));
 		break;
-	case XFROG_SCRUB_TYPE_FS:
+	case XFROG_SCRUB_GROUP_FS:
 		return snprintf(buf, buflen, _("%s"), _(sc->descr));
 		break;
-	case XFROG_SCRUB_TYPE_NONE:
+	case XFROG_SCRUB_GROUP_NONE:
 		assert(0);
 		break;
 	}
@@ -276,12 +276,12 @@ scrub_save_repair(
 	memset(aitem, 0, sizeof(*aitem));
 	aitem->type = meta->sm_type;
 	aitem->flags = meta->sm_flags;
-	switch (xfrog_scrubbers[meta->sm_type].type) {
-	case XFROG_SCRUB_TYPE_AGHEADER:
-	case XFROG_SCRUB_TYPE_PERAG:
+	switch (xfrog_scrubbers[meta->sm_type].group) {
+	case XFROG_SCRUB_GROUP_AGHEADER:
+	case XFROG_SCRUB_GROUP_PERAG:
 		aitem->agno = meta->sm_agno;
 		break;
-	case XFROG_SCRUB_TYPE_INODE:
+	case XFROG_SCRUB_GROUP_INODE:
 		aitem->ino = meta->sm_ino;
 		aitem->gen = meta->sm_gen;
 		break;
@@ -336,14 +336,14 @@ scrub_meta_type(
 }
 
 /*
- * Scrub all metadata types that are assigned to the given XFROG_SCRUB_TYPE_*,
+ * Scrub all metadata types that are assigned to the given XFROG_SCRUB_GROUP_*,
  * saving corruption reports for later.  This should not be used for
- * XFROG_SCRUB_TYPE_INODE or for checking summary metadata.
+ * XFROG_SCRUB_GROUP_INODE or for checking summary metadata.
  */
 static bool
-scrub_all_types(
+scrub_group(
 	struct scrub_ctx		*ctx,
-	enum xfrog_scrub_type		scrub_type,
+	enum xfrog_scrub_group		group,
 	xfs_agnumber_t			agno,
 	struct action_list		*alist)
 {
@@ -354,7 +354,7 @@ scrub_all_types(
 	for (type = 0; type < XFS_SCRUB_TYPE_NR; type++, sc++) {
 		int			ret;
 
-		if (sc->type != scrub_type)
+		if (sc->group != group)
 			continue;
 		if (sc->flags & XFROG_SCRUB_DESCR_SUMMARY)
 			continue;
@@ -388,7 +388,7 @@ scrub_ag_headers(
 	xfs_agnumber_t			agno,
 	struct action_list		*alist)
 {
-	return scrub_all_types(ctx, XFROG_SCRUB_TYPE_AGHEADER, agno, alist);
+	return scrub_group(ctx, XFROG_SCRUB_GROUP_AGHEADER, agno, alist);
 }
 
 /* Scrub each AG's metadata btrees. */
@@ -398,7 +398,7 @@ scrub_ag_metadata(
 	xfs_agnumber_t			agno,
 	struct action_list		*alist)
 {
-	return scrub_all_types(ctx, XFROG_SCRUB_TYPE_PERAG, agno, alist);
+	return scrub_group(ctx, XFROG_SCRUB_GROUP_PERAG, agno, alist);
 }
 
 /* Scrub whole-FS metadata btrees. */
@@ -407,7 +407,7 @@ scrub_fs_metadata(
 	struct scrub_ctx		*ctx,
 	struct action_list		*alist)
 {
-	return scrub_all_types(ctx, XFROG_SCRUB_TYPE_FS, 0, alist);
+	return scrub_group(ctx, XFROG_SCRUB_GROUP_FS, 0, alist);
 }
 
 /* Scrub FS summary metadata. */
@@ -430,12 +430,12 @@ scrub_estimate_ag_work(
 
 	sc = xfrog_scrubbers;
 	for (type = 0; type < XFS_SCRUB_TYPE_NR; type++, sc++) {
-		switch (sc->type) {
-		case XFROG_SCRUB_TYPE_AGHEADER:
-		case XFROG_SCRUB_TYPE_PERAG:
+		switch (sc->group) {
+		case XFROG_SCRUB_GROUP_AGHEADER:
+		case XFROG_SCRUB_GROUP_PERAG:
 			estimate += ctx->mnt.fsgeom.agcount;
 			break;
-		case XFROG_SCRUB_TYPE_FS:
+		case XFROG_SCRUB_GROUP_FS:
 			estimate++;
 			break;
 		default:
@@ -463,7 +463,7 @@ scrub_file(
 	enum check_outcome		fix;
 
 	assert(type < XFS_SCRUB_TYPE_NR);
-	assert(xfrog_scrubbers[type].type == XFROG_SCRUB_TYPE_INODE);
+	assert(xfrog_scrubbers[type].group == XFROG_SCRUB_GROUP_INODE);
 
 	meta.sm_type = type;
 	meta.sm_ino = bstat->bs_ino;
@@ -625,12 +625,12 @@ xfs_repair_metadata(
 	meta.sm_flags = aitem->flags | XFS_SCRUB_IFLAG_REPAIR;
 	if (use_force_rebuild)
 		meta.sm_flags |= XFS_SCRUB_IFLAG_FORCE_REBUILD;
-	switch (xfrog_scrubbers[aitem->type].type) {
-	case XFROG_SCRUB_TYPE_AGHEADER:
-	case XFROG_SCRUB_TYPE_PERAG:
+	switch (xfrog_scrubbers[aitem->type].group) {
+	case XFROG_SCRUB_GROUP_AGHEADER:
+	case XFROG_SCRUB_GROUP_PERAG:
 		meta.sm_agno = aitem->agno;
 		break;
-	case XFROG_SCRUB_TYPE_INODE:
+	case XFROG_SCRUB_GROUP_INODE:
 		meta.sm_ino = aitem->ino;
 		meta.sm_gen = aitem->gen;
 		break;

[PATCH 2/3] libfrog: promote XFROG_SCRUB_DESCR_SUMMARY to a scrub type

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

"Summary" metadata, at least in the scrub context, are metadata whose
values depend on some kind of computation and therefore can only be
checked after we've looked at all the other metadata.  Currently, the
superblock summary counters are the only thing that are like this, but
since they run in a totally separate xfs_scrub phase (7 vs. 2), make
them their own group and remove the group+flag mix.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 io/scrub.c      |    1 +
 libfrog/scrub.c |    3 +--
 libfrog/scrub.h |    8 +-------
 scrub/phase4.c  |    2 +-
 scrub/phase7.c  |    4 ++--
 scrub/scrub.c   |   16 ++++++++++++----
 scrub/scrub.h   |    3 ++-
 7 files changed, 20 insertions(+), 17 deletions(-)


diff --git a/io/scrub.c b/io/scrub.c
index d6eda5bea53..70301c0676c 100644
--- a/io/scrub.c
+++ b/io/scrub.c
@@ -183,6 +183,7 @@ parse_args(
 		break;
 	case XFROG_SCRUB_GROUP_FS:
 	case XFROG_SCRUB_GROUP_NONE:
+	case XFROG_SCRUB_GROUP_SUMMARY:
 		if (!parse_none(argc, optind)) {
 			exitcode = 1;
 			return command_usage(cmdinfo);
diff --git a/libfrog/scrub.c b/libfrog/scrub.c
index 90fc2b1a40c..5a5f522a425 100644
--- a/libfrog/scrub.c
+++ b/libfrog/scrub.c
@@ -132,8 +132,7 @@ const struct xfrog_scrub_descr xfrog_scrubbers[XFS_SCRUB_TYPE_NR] = {
 	[XFS_SCRUB_TYPE_FSCOUNTERS] = {
 		.name	= "fscounters",
 		.descr	= "filesystem summary counters",
-		.group	= XFROG_SCRUB_GROUP_FS,
-		.flags	= XFROG_SCRUB_DESCR_SUMMARY,
+		.group	= XFROG_SCRUB_GROUP_SUMMARY,
 	},
 };
 
diff --git a/libfrog/scrub.h b/libfrog/scrub.h
index 43a882321f9..68f1a968103 100644
--- a/libfrog/scrub.h
+++ b/libfrog/scrub.h
@@ -13,6 +13,7 @@ enum xfrog_scrub_group {
 	XFROG_SCRUB_GROUP_PERAG,	/* per-AG metadata */
 	XFROG_SCRUB_GROUP_FS,		/* per-FS metadata */
 	XFROG_SCRUB_GROUP_INODE,	/* per-inode metadata */
+	XFROG_SCRUB_GROUP_SUMMARY,	/* summary metadata */
 };
 
 /* Catalog of scrub types and names, indexed by XFS_SCRUB_TYPE_* */
@@ -20,15 +21,8 @@ struct xfrog_scrub_descr {
 	const char		*name;
 	const char		*descr;
 	enum xfrog_scrub_group	group;
-	unsigned int		flags;
 };
 
-/*
- * The type of metadata checked by this scrubber is a summary of other types
- * of metadata.  This scrubber should be run after all the others.
- */
-#define XFROG_SCRUB_DESCR_SUMMARY	(1 << 0)
-
 extern const struct xfrog_scrub_descr xfrog_scrubbers[XFS_SCRUB_TYPE_NR];
 
 int xfrog_scrub_metadata(struct xfs_fd *xfd, struct xfs_scrub_metadata *meta);
diff --git a/scrub/phase4.c b/scrub/phase4.c
index 1228c7cb654..5dfc3856b82 100644
--- a/scrub/phase4.c
+++ b/scrub/phase4.c
@@ -139,7 +139,7 @@ phase4_func(
 	 * counters, so counter repairs have to be put on the list now so that
 	 * they get fixed before we stop retrying unfixed metadata repairs.
 	 */
-	ret = scrub_fs_summary(ctx, &ctx->action_lists[0]);
+	ret = scrub_fs_counters(ctx, &ctx->action_lists[0]);
 	if (ret)
 		return ret;
 
diff --git a/scrub/phase7.c b/scrub/phase7.c
index 2fd96053f6c..93a074f1151 100644
--- a/scrub/phase7.c
+++ b/scrub/phase7.c
@@ -116,9 +116,9 @@ phase7_func(
 	int			ip;
 	int			error;
 
-	/* Check and fix the fs summary counters. */
+	/* Check and fix the summary metadata. */
 	action_list_init(&alist);
-	error = scrub_fs_summary(ctx, &alist);
+	error = scrub_summary_metadata(ctx, &alist);
 	if (error)
 		return error;
 	error = action_list_process(ctx, -1, &alist,
diff --git a/scrub/scrub.c b/scrub/scrub.c
index cde9babc557..c7ee074fd36 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -46,6 +46,7 @@ format_scrub_descr(
 				_(sc->descr));
 		break;
 	case XFROG_SCRUB_GROUP_FS:
+	case XFROG_SCRUB_GROUP_SUMMARY:
 		return snprintf(buf, buflen, _("%s"), _(sc->descr));
 		break;
 	case XFROG_SCRUB_GROUP_NONE:
@@ -356,8 +357,6 @@ scrub_group(
 
 		if (sc->group != group)
 			continue;
-		if (sc->flags & XFROG_SCRUB_DESCR_SUMMARY)
-			continue;
 
 		ret = scrub_meta_type(ctx, type, agno, alist);
 		if (ret)
@@ -410,9 +409,18 @@ scrub_fs_metadata(
 	return scrub_group(ctx, XFROG_SCRUB_GROUP_FS, 0, alist);
 }
 
-/* Scrub FS summary metadata. */
+/* Scrub all FS summary metadata. */
 int
-scrub_fs_summary(
+scrub_summary_metadata(
+	struct scrub_ctx		*ctx,
+	struct action_list		*alist)
+{
+	return scrub_group(ctx, XFROG_SCRUB_GROUP_SUMMARY, 0, alist);
+}
+
+/* Scrub /only/ the superblock summary counters. */
+int
+scrub_fs_counters(
 	struct scrub_ctx		*ctx,
 	struct action_list		*alist)
 {
diff --git a/scrub/scrub.h b/scrub/scrub.h
index f7e66bb614b..35d609f283a 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -23,7 +23,8 @@ int scrub_ag_headers(struct scrub_ctx *ctx, xfs_agnumber_t agno,
 int scrub_ag_metadata(struct scrub_ctx *ctx, xfs_agnumber_t agno,
 		struct action_list *alist);
 int scrub_fs_metadata(struct scrub_ctx *ctx, struct action_list *alist);
-int scrub_fs_summary(struct scrub_ctx *ctx, struct action_list *alist);
+int scrub_summary_metadata(struct scrub_ctx *ctx, struct action_list *alist);
+int scrub_fs_counters(struct scrub_ctx *ctx, struct action_list *alist);
 
 bool can_scrub_fs_metadata(struct scrub_ctx *ctx);
 bool can_scrub_inode(struct scrub_ctx *ctx);

[PATCH 3/3] xfs_scrub: scan whole-fs metadata files in parallel

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

The realtime bitmap and the three quota files are completely independent
of each other, which means that we ought to be able to scan them in
parallel.  Rework the phase2 code so that we can do this.  Note,
however, that the realtime summary file summarizes the contents of the
realtime bitmap, so we must coordinate the workqueue threads.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase2.c |  135 +++++++++++++++++++++++++++++++++++++++++++-------------
 scrub/scrub.c  |    7 ++-
 scrub/scrub.h  |    3 +
 3 files changed, 110 insertions(+), 35 deletions(-)


diff --git a/scrub/phase2.c b/scrub/phase2.c
index 6b88384171f..80c77b2876f 100644
--- a/scrub/phase2.c
+++ b/scrub/phase2.c
@@ -10,6 +10,8 @@
 #include "list.h"
 #include "libfrog/paths.h"
 #include "libfrog/workqueue.h"
+#include "libfrog/fsgeom.h"
+#include "libfrog/scrub.h"
 #include "xfs_scrub.h"
 #include "common.h"
 #include "scrub.h"
@@ -17,6 +19,18 @@
 
 /* Phase 2: Check internal metadata. */
 
+struct scan_ctl {
+	/*
+	 * Control mechanism to signal that the rt bitmap file scan is done and
+	 * wake up any waiters.
+	 */
+	pthread_cond_t		rbm_wait;
+	pthread_mutex_t		rbm_waitlock;
+	bool			rbm_done;
+
+	bool			aborted;
+};
+
 /* Scrub each AG's metadata btrees. */
 static void
 scan_ag_metadata(
@@ -25,7 +39,7 @@ scan_ag_metadata(
 	void				*arg)
 {
 	struct scrub_ctx		*ctx = (struct scrub_ctx *)wq->wq_ctx;
-	bool				*aborted = arg;
+	struct scan_ctl			*sctl = arg;
 	struct action_list		alist;
 	struct action_list		immediate_alist;
 	unsigned long long		broken_primaries;
@@ -33,7 +47,7 @@ scan_ag_metadata(
 	char				descr[DESCR_BUFSZ];
 	int				ret;
 
-	if (*aborted)
+	if (sctl->aborted)
 		return;
 
 	action_list_init(&alist);
@@ -89,32 +103,40 @@ _("Filesystem might not be repairable."));
 	action_list_defer(ctx, agno, &alist);
 	return;
 err:
-	*aborted = true;
+	sctl->aborted = true;
 }
 
-/* Scrub whole-FS metadata btrees. */
+/* Scan whole-fs metadata. */
 static void
 scan_fs_metadata(
-	struct workqueue		*wq,
-	xfs_agnumber_t			agno,
-	void				*arg)
+	struct workqueue	*wq,
+	xfs_agnumber_t		type,
+	void			*arg)
 {
-	struct scrub_ctx		*ctx = (struct scrub_ctx *)wq->wq_ctx;
-	bool				*aborted = arg;
-	struct action_list		alist;
-	int				ret;
+	struct action_list	alist;
+	struct scrub_ctx	*ctx = (struct scrub_ctx *)wq->wq_ctx;
+	struct scan_ctl		*sctl = arg;
+	int			ret;
 
-	if (*aborted)
-		return;
+	if (sctl->aborted)
+		goto out;
 
 	action_list_init(&alist);
-	ret = scrub_fs_metadata(ctx, &alist);
+	ret = scrub_fs_metadata(ctx, type, &alist);
 	if (ret) {
-		*aborted = true;
-		return;
+		sctl->aborted = true;
+		goto out;
 	}
 
-	action_list_defer(ctx, agno, &alist);
+	action_list_defer(ctx, 0, &alist);
+
+out:
+	if (type == XFS_SCRUB_TYPE_RTBITMAP) {
+		pthread_mutex_lock(&sctl->rbm_waitlock);
+		sctl->rbm_done = true;
+		pthread_cond_broadcast(&sctl->rbm_wait);
+		pthread_mutex_unlock(&sctl->rbm_waitlock);
+	}
 }
 
 /* Scan all filesystem metadata. */
@@ -122,17 +144,25 @@ int
 phase2_func(
 	struct scrub_ctx	*ctx)
 {
-	struct action_list	alist;
 	struct workqueue	wq;
+	struct scan_ctl		sctl = {
+		.aborted	= false,
+		.rbm_done	= false,
+	};
+	struct action_list	alist;
+	const struct xfrog_scrub_descr *sc = xfrog_scrubbers;
 	xfs_agnumber_t		agno;
-	bool			aborted = false;
+	unsigned int		type;
 	int			ret, ret2;
 
+	pthread_mutex_init(&sctl.rbm_waitlock, NULL);
+	pthread_cond_init(&sctl.rbm_wait, NULL);
+
 	ret = -workqueue_create(&wq, (struct xfs_mount *)ctx,
 			scrub_nproc_workqueue(ctx));
 	if (ret) {
 		str_liberror(ctx, ret, _("creating scrub workqueue"));
-		return ret;
+		goto out_wait;
 	}
 
 	/*
@@ -143,29 +173,67 @@ phase2_func(
 	action_list_init(&alist);
 	ret = scrub_primary_super(ctx, &alist);
 	if (ret)
-		goto out;
+		goto out_wq;
 	ret = action_list_process_or_defer(ctx, 0, &alist);
 	if (ret)
-		goto out;
+		goto out_wq;
 
-	for (agno = 0; !aborted && agno < ctx->mnt.fsgeom.agcount; agno++) {
-		ret = -workqueue_add(&wq, scan_ag_metadata, agno, &aborted);
+	/* Scan each AG in parallel. */
+	for (agno = 0;
+	     agno < ctx->mnt.fsgeom.agcount && !sctl.aborted;
+	     agno++) {
+		ret = -workqueue_add(&wq, scan_ag_metadata, agno, &sctl);
 		if (ret) {
 			str_liberror(ctx, ret, _("queueing per-AG scrub work"));
-			goto out;
+			goto out_wq;
 		}
 	}
 
-	if (aborted)
-		goto out;
+	if (sctl.aborted)
+		goto out_wq;
 
-	ret = -workqueue_add(&wq, scan_fs_metadata, 0, &aborted);
+	/*
+	 * Scan all of the whole-fs metadata objects: realtime bitmap, realtime
+	 * summary, and the three quota files.  Each of the metadata files can
+	 * be scanned in parallel except for the realtime summary file, which
+	 * must run after the realtime bitmap has been scanned.
+	 */
+	for (type = 0; type < XFS_SCRUB_TYPE_NR; type++, sc++) {
+		if (sc->group != XFROG_SCRUB_GROUP_FS)
+			continue;
+		if (type == XFS_SCRUB_TYPE_RTSUM)
+			continue;
+
+		ret = -workqueue_add(&wq, scan_fs_metadata, type, &sctl);
+		if (ret) {
+			str_liberror(ctx, ret,
+	_("queueing whole-fs scrub work"));
+			goto out_wq;
+		}
+	}
+
+	if (sctl.aborted)
+		goto out_wq;
+
+	/*
+	 * Wait for the rt bitmap to finish scanning, then scan the rt summary
+	 * since the summary can be regenerated completely from the bitmap.
+	 */
+	pthread_mutex_lock(&sctl.rbm_waitlock);
+	while (!sctl.rbm_done)
+		pthread_cond_wait(&sctl.rbm_wait, &sctl.rbm_waitlock);
+	pthread_mutex_unlock(&sctl.rbm_waitlock);
+
+	if (sctl.aborted)
+		goto out_wq;
+
+	ret = -workqueue_add(&wq, scan_fs_metadata, XFS_SCRUB_TYPE_RTSUM, &sctl);
 	if (ret) {
-		str_liberror(ctx, ret, _("queueing per-FS scrub work"));
-		goto out;
+		str_liberror(ctx, ret, _("queueing rtsummary scrub work"));
+		goto out_wq;
 	}
 
-out:
+out_wq:
 	ret2 = -workqueue_terminate(&wq);
 	if (ret2) {
 		str_liberror(ctx, ret2, _("finishing scrub work"));
@@ -173,8 +241,11 @@ phase2_func(
 			ret = ret2;
 	}
 	workqueue_destroy(&wq);
+out_wait:
+	pthread_cond_destroy(&sctl.rbm_wait);
+	pthread_mutex_destroy(&sctl.rbm_waitlock);
 
-	if (!ret && aborted)
+	if (!ret && sctl.aborted)
 		ret = ECANCELED;
 	return ret;
 }
diff --git a/scrub/scrub.c b/scrub/scrub.c
index c7ee074fd36..1c53260cc26 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -400,13 +400,16 @@ scrub_ag_metadata(
 	return scrub_group(ctx, XFROG_SCRUB_GROUP_PERAG, agno, alist);
 }
 
-/* Scrub whole-FS metadata btrees. */
+/* Scrub whole-filesystem metadata. */
 int
 scrub_fs_metadata(
 	struct scrub_ctx		*ctx,
+	unsigned int			type,
 	struct action_list		*alist)
 {
-	return scrub_group(ctx, XFROG_SCRUB_GROUP_FS, 0, alist);
+	ASSERT(xfrog_scrubbers[type].group == XFROG_SCRUB_GROUP_FS);
+
+	return scrub_meta_type(ctx, type, 0, alist);
 }
 
 /* Scrub all FS summary metadata. */
diff --git a/scrub/scrub.h b/scrub/scrub.h
index 35d609f283a..8a999da6a96 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -22,7 +22,8 @@ int scrub_ag_headers(struct scrub_ctx *ctx, xfs_agnumber_t agno,
 		struct action_list *alist);
 int scrub_ag_metadata(struct scrub_ctx *ctx, xfs_agnumber_t agno,
 		struct action_list *alist);
-int scrub_fs_metadata(struct scrub_ctx *ctx, struct action_list *alist);
+int scrub_fs_metadata(struct scrub_ctx *ctx, unsigned int scrub_type,
+		struct action_list *alist);
 int scrub_summary_metadata(struct scrub_ctx *ctx, struct action_list *alist);
 int scrub_fs_counters(struct scrub_ctx *ctx, struct action_list *alist);
 

[PATCH 1/3] xfs: create a static name for the dot entry too

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create an xfs_name_dot object so that upcoming scrub code can compare
against that.  Offline repair already has such an object, so we're
really just hoisting it to the kernel.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_dir2.c |    6 ++++++
 libxfs/xfs_dir2.h |    1 +
 repair/phase6.c   |    4 ----
 3 files changed, 7 insertions(+), 4 deletions(-)


diff --git a/libxfs/xfs_dir2.c b/libxfs/xfs_dir2.c
index c19684b3401..dcbc83c8b00 100644
--- a/libxfs/xfs_dir2.c
+++ b/libxfs/xfs_dir2.c
@@ -24,6 +24,12 @@ 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
  */
diff --git a/libxfs/xfs_dir2.h b/libxfs/xfs_dir2.h
index 19af22a16c4..7d7cd8d808e 100644
--- a/libxfs/xfs_dir2.h
+++ b/libxfs/xfs_dir2.h
@@ -22,6 +22,7 @@ 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;
 
 /*
  * Convert inode mode to directory entry filetype
diff --git a/repair/phase6.c b/repair/phase6.c
index fcb26d594b1..c681a69017d 100644
--- a/repair/phase6.c
+++ b/repair/phase6.c
@@ -23,10 +23,6 @@ static struct cred		zerocr;
 static struct fsxattr 		zerofsx;
 static xfs_ino_t		orphanage_ino;
 
-static struct xfs_name		xfs_name_dot = {(unsigned char *)".",
-						1,
-						XFS_DIR3_FT_DIR};
-
 /*
  * Data structures used to keep track of directories where the ".."
  * entries are updated. These must be rebuilt after the initial pass

[PATCH 2/3] xfs: create a predicate to determine if two xfs_names are the same

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a simple predicate to determine if two xfs_names are the same
objects or have the exact same name.  The comparison is always case
sensitive.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_dir2.h |    9 +++++++++
 1 file changed, 9 insertions(+)


diff --git a/libxfs/xfs_dir2.h b/libxfs/xfs_dir2.h
index 7d7cd8d808e..ac3c264402d 100644
--- a/libxfs/xfs_dir2.h
+++ b/libxfs/xfs_dir2.h
@@ -24,6 +24,15 @@ 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)
+{
+	return n1 == n2 || (n1->len == n2->len &&
+			    !memcmp(n1->name, n2->name, n1->len));
+}
+
 /*
  * Convert inode mode to directory entry filetype
  */

[PATCH 3/3] xfs: create a macro for decoding ftypes in tracepoints

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create the XFS_DIR3_FTYPE_STR macro so that we can report ftype as
strings instead of numbers in tracepoints.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_da_format.h |   11 +++++++++++
 1 file changed, 11 insertions(+)


diff --git a/libxfs/xfs_da_format.h b/libxfs/xfs_da_format.h
index f9015f88eca..44748f1640e 100644
--- a/libxfs/xfs_da_format.h
+++ b/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.
  */

[PATCH 1/3] xfs: report the health of quota counts

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Report the health of quota counts.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_fs.h                 |    1 +
 libxfs/xfs_health.h             |    4 +++-
 man/man2/ioctl_xfs_fsgeometry.2 |    3 +++
 spaceman/health.c               |    4 ++++
 4 files changed, 11 insertions(+), 1 deletion(-)


diff --git a/libxfs/xfs_fs.h b/libxfs/xfs_fs.h
index 6360073865d..711e0fc7efa 100644
--- a/libxfs/xfs_fs.h
+++ b/libxfs/xfs_fs.h
@@ -195,6 +195,7 @@ struct xfs_fsop_geom {
 #define XFS_FSOP_GEOM_SICK_PQUOTA	(1 << 3)  /* project quota */
 #define XFS_FSOP_GEOM_SICK_RT_BITMAP	(1 << 4)  /* realtime bitmap */
 #define XFS_FSOP_GEOM_SICK_RT_SUMMARY	(1 << 5)  /* realtime summary */
+#define XFS_FSOP_GEOM_SICK_QUOTACHECK	(1 << 6)  /* quota counts */
 
 /* Output for XFS_FS_COUNTS */
 typedef struct xfs_fsop_counts {
diff --git a/libxfs/xfs_health.h b/libxfs/xfs_health.h
index 6296993ff8f..5626e53b3f0 100644
--- a/libxfs/xfs_health.h
+++ b/libxfs/xfs_health.h
@@ -41,6 +41,7 @@ struct xfs_fsop_geom;
 #define XFS_SICK_FS_UQUOTA	(1 << 1)  /* user quota */
 #define XFS_SICK_FS_GQUOTA	(1 << 2)  /* group quota */
 #define XFS_SICK_FS_PQUOTA	(1 << 3)  /* project quota */
+#define XFS_SICK_FS_QUOTACHECK	(1 << 4)  /* quota counts */
 
 /* Observable health issues for realtime volume metadata. */
 #define XFS_SICK_RT_BITMAP	(1 << 0)  /* realtime bitmap */
@@ -77,7 +78,8 @@ struct xfs_fsop_geom;
 #define XFS_SICK_FS_PRIMARY	(XFS_SICK_FS_COUNTERS | \
 				 XFS_SICK_FS_UQUOTA | \
 				 XFS_SICK_FS_GQUOTA | \
-				 XFS_SICK_FS_PQUOTA)
+				 XFS_SICK_FS_PQUOTA | \
+				 XFS_SICK_FS_QUOTACHECK)
 
 #define XFS_SICK_RT_PRIMARY	(XFS_SICK_RT_BITMAP | \
 				 XFS_SICK_RT_SUMMARY)
diff --git a/man/man2/ioctl_xfs_fsgeometry.2 b/man/man2/ioctl_xfs_fsgeometry.2
index 6b7c83da758..f59a6e8a6a2 100644
--- a/man/man2/ioctl_xfs_fsgeometry.2
+++ b/man/man2/ioctl_xfs_fsgeometry.2
@@ -256,6 +256,9 @@ Free space bitmap for the realtime device.
 .TP
 .B XFS_FSOP_GEOM_SICK_RT_SUMMARY
 Free space summary for the realtime device.
+.TP
+.B XFS_FSOP_GEOM_SICK_QUOTACHECK
+Quota resource usage counters.
 .RE
 
 .SH RETURN VALUE
diff --git a/spaceman/health.c b/spaceman/health.c
index d83c5ccd90d..3318f9d1a7f 100644
--- a/spaceman/health.c
+++ b/spaceman/health.c
@@ -72,6 +72,10 @@ static const struct flag_map fs_flags[] = {
 		.descr = "realtime summary",
 		.has_fn = has_realtime,
 	},
+	{
+		.mask = XFS_FSOP_GEOM_SICK_QUOTACHECK,
+		.descr = "quota counts",
+	},
 	{0},
 };
 

[PATCH 2/3] libfrog: create a new scrub group for things requiring full inode scans

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Subsequent patches will add online fsck types (quotacheck, link counts)
that require us to walk every inode in the entire filesystem.  This
requires the AG metadata and the inodes to be in good enough shape to
complete the scan without hitting corruption errors.  As such, they
ought to run after phases 2-4 and before phase 7, which summarizes what
we've found.

Phase 5 seems like a reasonable place to do this, since it already walks
every xattr and directory entry in the filesystem to look for suspicious
looking names.  Add a new XFROG_SCRUB_GROUP, and add it to phase 5.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 io/scrub.c        |    1 +
 libfrog/scrub.h   |    1 +
 scrub/phase5.c    |   22 ++++++++++++++++++++--
 scrub/scrub.c     |   33 +++++++++++++++++++++++++++++++++
 scrub/scrub.h     |    1 +
 scrub/xfs_scrub.h |    1 +
 6 files changed, 57 insertions(+), 2 deletions(-)


diff --git a/io/scrub.c b/io/scrub.c
index 70301c0676c..a77cd872fed 100644
--- a/io/scrub.c
+++ b/io/scrub.c
@@ -184,6 +184,7 @@ parse_args(
 	case XFROG_SCRUB_GROUP_FS:
 	case XFROG_SCRUB_GROUP_NONE:
 	case XFROG_SCRUB_GROUP_SUMMARY:
+	case XFROG_SCRUB_GROUP_ISCAN:
 		if (!parse_none(argc, optind)) {
 			exitcode = 1;
 			return command_usage(cmdinfo);
diff --git a/libfrog/scrub.h b/libfrog/scrub.h
index 68f1a968103..27230c62f71 100644
--- a/libfrog/scrub.h
+++ b/libfrog/scrub.h
@@ -13,6 +13,7 @@ enum xfrog_scrub_group {
 	XFROG_SCRUB_GROUP_PERAG,	/* per-AG metadata */
 	XFROG_SCRUB_GROUP_FS,		/* per-FS metadata */
 	XFROG_SCRUB_GROUP_INODE,	/* per-inode metadata */
+	XFROG_SCRUB_GROUP_ISCAN,	/* metadata requiring full inode scan */
 	XFROG_SCRUB_GROUP_SUMMARY,	/* summary metadata */
 };
 
diff --git a/scrub/phase5.c b/scrub/phase5.c
index 7e0eaca9042..0a91e4f0640 100644
--- a/scrub/phase5.c
+++ b/scrub/phase5.c
@@ -16,6 +16,8 @@
 #include "list.h"
 #include "libfrog/paths.h"
 #include "libfrog/workqueue.h"
+#include "libfrog/fsgeom.h"
+#include "libfrog/scrub.h"
 #include "xfs_scrub.h"
 #include "common.h"
 #include "inodes.h"
@@ -23,8 +25,9 @@
 #include "scrub.h"
 #include "descr.h"
 #include "unicrash.h"
+#include "repair.h"
 
-/* Phase 5: Check directory connectivity. */
+/* Phase 5: Full inode scans and check directory connectivity. */
 
 /*
  * Warn about problematic bytes in a directory/attribute name.  That means
@@ -386,9 +389,24 @@ int
 phase5_func(
 	struct scrub_ctx	*ctx)
 {
+	struct action_list	alist;
 	bool			aborted = false;
 	int			ret;
 
+	/*
+	 * Check and fix anything that requires a full inode scan.  We do this
+	 * after we've checked all inodes and repaired anything that could get
+	 * in the way of a scan.
+	 */
+	action_list_init(&alist);
+	ret = scrub_iscan_metadata(ctx, &alist);
+	if (ret)
+		return ret;
+	ret = action_list_process(ctx, ctx->mnt.fd, &alist,
+			ALP_COMPLAIN_IF_UNFIXED | ALP_NOPROGRESS);
+	if (ret)
+		return ret;
+
 	if (ctx->corruptions_found || ctx->unfixable_errors) {
 		str_info(ctx, ctx->mntpoint,
 _("Filesystem has errors, skipping connectivity checks."));
@@ -417,7 +435,7 @@ phase5_estimate(
 	unsigned int		*nr_threads,
 	int			*rshift)
 {
-	*items = ctx->mnt_sv.f_files - ctx->mnt_sv.f_ffree;
+	*items = scrub_estimate_iscan_work(ctx);
 	*nr_threads = scrub_nproc(ctx);
 	*rshift = 0;
 	return 0;
diff --git a/scrub/scrub.c b/scrub/scrub.c
index 1c53260cc26..023cc2c2cd2 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -47,6 +47,7 @@ format_scrub_descr(
 		break;
 	case XFROG_SCRUB_GROUP_FS:
 	case XFROG_SCRUB_GROUP_SUMMARY:
+	case XFROG_SCRUB_GROUP_ISCAN:
 		return snprintf(buf, buflen, _("%s"), _(sc->descr));
 		break;
 	case XFROG_SCRUB_GROUP_NONE:
@@ -421,6 +422,15 @@ scrub_summary_metadata(
 	return scrub_group(ctx, XFROG_SCRUB_GROUP_SUMMARY, 0, alist);
 }
 
+/* Scrub all metadata requiring a full inode scan. */
+int
+scrub_iscan_metadata(
+	struct scrub_ctx		*ctx,
+	struct action_list		*alist)
+{
+	return scrub_group(ctx, XFROG_SCRUB_GROUP_ISCAN, 0, alist);
+}
+
 /* Scrub /only/ the superblock summary counters. */
 int
 scrub_fs_counters(
@@ -456,6 +466,29 @@ scrub_estimate_ag_work(
 	return estimate;
 }
 
+/*
+ * How many kernel calls will we make to scrub everything requiring a full
+ * inode scan?
+ */
+unsigned int
+scrub_estimate_iscan_work(
+	struct scrub_ctx		*ctx)
+{
+	const struct xfrog_scrub_descr	*sc;
+	int				type;
+	unsigned int			estimate;
+
+	estimate = ctx->mnt_sv.f_files - ctx->mnt_sv.f_ffree;
+
+	sc = xfrog_scrubbers;
+	for (type = 0; type < XFS_SCRUB_TYPE_NR; type++, sc++) {
+		if (sc->group == XFROG_SCRUB_GROUP_ISCAN)
+			estimate++;
+	}
+
+	return estimate;
+}
+
 /*
  * Scrub file metadata of some sort.  If errors occur, this function will log
  * them and return nonzero.
diff --git a/scrub/scrub.h b/scrub/scrub.h
index 8a999da6a96..0033fe7ed93 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -24,6 +24,7 @@ int scrub_ag_metadata(struct scrub_ctx *ctx, xfs_agnumber_t agno,
 		struct action_list *alist);
 int scrub_fs_metadata(struct scrub_ctx *ctx, unsigned int scrub_type,
 		struct action_list *alist);
+int scrub_iscan_metadata(struct scrub_ctx *ctx, struct action_list *alist);
 int scrub_summary_metadata(struct scrub_ctx *ctx, struct action_list *alist);
 int scrub_fs_counters(struct scrub_ctx *ctx, struct action_list *alist);
 
diff --git a/scrub/xfs_scrub.h b/scrub/xfs_scrub.h
index 7aea79d9555..34d850d8db3 100644
--- a/scrub/xfs_scrub.h
+++ b/scrub/xfs_scrub.h
@@ -99,6 +99,7 @@ int phase7_func(struct scrub_ctx *ctx);
 
 /* Progress estimator functions */
 unsigned int scrub_estimate_ag_work(struct scrub_ctx *ctx);
+unsigned int scrub_estimate_iscan_work(struct scrub_ctx *ctx);
 int phase2_estimate(struct scrub_ctx *ctx, uint64_t *items,
 		    unsigned int *nr_threads, int *rshift);
 int phase3_estimate(struct scrub_ctx *ctx, uint64_t *items,

[PATCH 3/3] xfs: implement live quotacheck inode scan

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a new trio of scrub functions to check quota counters.  While the
dquots themselves are filesystem metadata and should be checked early,
the dquot counter values are computed from other metadata and are
therefore summary counters.  We don't plug these into the scrub dispatch
just yet, because we still need to be able to watch quota updates while
doing our scan.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libfrog/scrub.c |    5 +++++
 libxfs/xfs_fs.h |    3 ++-
 scrub/phase4.c  |   17 +++++++++++++++++
 scrub/repair.c  |    3 +++
 scrub/scrub.c   |    9 +++++++++
 scrub/scrub.h   |    1 +
 6 files changed, 37 insertions(+), 1 deletion(-)


diff --git a/libfrog/scrub.c b/libfrog/scrub.c
index 5a5f522a425..53c47bc2b5d 100644
--- a/libfrog/scrub.c
+++ b/libfrog/scrub.c
@@ -134,6 +134,11 @@ const struct xfrog_scrub_descr xfrog_scrubbers[XFS_SCRUB_TYPE_NR] = {
 		.descr	= "filesystem summary counters",
 		.group	= XFROG_SCRUB_GROUP_SUMMARY,
 	},
+	[XFS_SCRUB_TYPE_QUOTACHECK] = {
+		.name	= "quotacheck",
+		.descr	= "quota counters",
+		.group	= XFROG_SCRUB_GROUP_ISCAN,
+	},
 };
 
 /* Invoke the scrub ioctl.  Returns zero or negative error code. */
diff --git a/libxfs/xfs_fs.h b/libxfs/xfs_fs.h
index 711e0fc7efa..07acbed9235 100644
--- a/libxfs/xfs_fs.h
+++ b/libxfs/xfs_fs.h
@@ -710,9 +710,10 @@ struct xfs_scrub_metadata {
 #define XFS_SCRUB_TYPE_GQUOTA	22	/* group quotas */
 #define XFS_SCRUB_TYPE_PQUOTA	23	/* project quotas */
 #define XFS_SCRUB_TYPE_FSCOUNTERS 24	/* fs summary counters */
+#define XFS_SCRUB_TYPE_QUOTACHECK 25	/* quota counters */
 
 /* Number of scrub subcommands. */
-#define XFS_SCRUB_TYPE_NR	25
+#define XFS_SCRUB_TYPE_NR	26
 
 /* i: Repair this metadata. */
 #define XFS_SCRUB_IFLAG_REPAIR		(1u << 0)
diff --git a/scrub/phase4.c b/scrub/phase4.c
index 5dfc3856b82..8807f147aed 100644
--- a/scrub/phase4.c
+++ b/scrub/phase4.c
@@ -128,6 +128,7 @@ int
 phase4_func(
 	struct scrub_ctx	*ctx)
 {
+	struct xfs_fsop_geom	fsgeom;
 	int			ret;
 
 	if (!have_action_items(ctx))
@@ -143,6 +144,22 @@ phase4_func(
 	if (ret)
 		return ret;
 
+	/*
+	 * Repair possibly bad quota counts before starting other repairs,
+	 * because wildly incorrect quota counts can cause shutdowns.
+	 * Quotacheck scans all inodes, so we only want to do it if we know
+	 * it's sick.
+	 */
+	ret = xfrog_geometry(ctx->mnt.fd, &fsgeom);
+	if (ret)
+		return ret;
+
+	if (fsgeom.sick & XFS_FSOP_GEOM_SICK_QUOTACHECK) {
+		ret = scrub_quotacheck(ctx, &ctx->action_lists[0]);
+		if (ret)
+			return ret;
+	}
+
 	ret = repair_everything(ctx);
 	if (ret)
 		return ret;
diff --git a/scrub/repair.c b/scrub/repair.c
index 65b6dd89530..3cb7224f7cc 100644
--- a/scrub/repair.c
+++ b/scrub/repair.c
@@ -84,6 +84,9 @@ xfs_action_item_priority(
 	case XFS_SCRUB_TYPE_GQUOTA:
 	case XFS_SCRUB_TYPE_PQUOTA:
 		return PRIO(aitem, XFS_SCRUB_TYPE_UQUOTA);
+	case XFS_SCRUB_TYPE_QUOTACHECK:
+		/* This should always go after [UGP]QUOTA no matter what. */
+		return PRIO(aitem, aitem->type);
 	case XFS_SCRUB_TYPE_FSCOUNTERS:
 		/* This should always go after AG headers no matter what. */
 		return PRIO(aitem, INT_MAX);
diff --git a/scrub/scrub.c b/scrub/scrub.c
index 023cc2c2cd2..a22633a8115 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -440,6 +440,15 @@ scrub_fs_counters(
 	return scrub_meta_type(ctx, XFS_SCRUB_TYPE_FSCOUNTERS, 0, alist);
 }
 
+/* Scrub /only/ the quota counters. */
+int
+scrub_quotacheck(
+	struct scrub_ctx		*ctx,
+	struct action_list		*alist)
+{
+	return scrub_meta_type(ctx, XFS_SCRUB_TYPE_QUOTACHECK, 0, alist);
+}
+
 /* How many items do we have to check? */
 unsigned int
 scrub_estimate_ag_work(
diff --git a/scrub/scrub.h b/scrub/scrub.h
index 0033fe7ed93..927f86de9ec 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -27,6 +27,7 @@ int scrub_fs_metadata(struct scrub_ctx *ctx, unsigned int scrub_type,
 int scrub_iscan_metadata(struct scrub_ctx *ctx, struct action_list *alist);
 int scrub_summary_metadata(struct scrub_ctx *ctx, struct action_list *alist);
 int scrub_fs_counters(struct scrub_ctx *ctx, struct action_list *alist);
+int scrub_quotacheck(struct scrub_ctx *ctx, struct action_list *alist);
 
 bool can_scrub_fs_metadata(struct scrub_ctx *ctx);
 bool can_scrub_inode(struct scrub_ctx *ctx);

[PATCH 1/3] xfs_repair: push inode buf and dinode pointers all the way to inode fork processing

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Currently, the process_dinode* family of functions assume that they have
the buffer backing the inodes locked, and therefore the dinode pointer
won't ever change.  However, the bmbt rebuilding code in the next patch
will violate that assumption, so we must pass pointers to the inobp and
the dinode pointer (that is to say, double pointers) all the way through
to process_inode_{data,attr}_fork so that we can regrab the buffer after
the rebuilding step finishes.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 repair/dino_chunks.c |    5 ++-
 repair/dinode.c      |   88 ++++++++++++++++++++++++++++----------------------
 repair/dinode.h      |    7 ++--
 3 files changed, 57 insertions(+), 43 deletions(-)


diff --git a/repair/dino_chunks.c b/repair/dino_chunks.c
index 171756818a6..19536133451 100644
--- a/repair/dino_chunks.c
+++ b/repair/dino_chunks.c
@@ -851,10 +851,11 @@ process_inode_chunk(
 		ino_dirty = 0;
 		parent = 0;
 
-		status = process_dinode(mp, dino, agno, agino,
+		status = process_dinode(mp, &dino, agno, agino,
 				is_inode_free(ino_rec, irec_offset),
 				&ino_dirty, &is_used,ino_discovery, check_dups,
-				extra_attr_check, &isa_dir, &parent);
+				extra_attr_check, &isa_dir, &parent,
+				&bplist[bp_index]);
 
 		ASSERT(is_used != 3);
 		if (ino_dirty) {
diff --git a/repair/dinode.c b/repair/dinode.c
index c1cfadc8833..3f826b3482f 100644
--- a/repair/dinode.c
+++ b/repair/dinode.c
@@ -1892,17 +1892,19 @@ _("nblocks (%" PRIu64 ") smaller than nextents for inode %" PRIu64 "\n"), nblock
  */
 static int
 process_inode_data_fork(
-	xfs_mount_t		*mp,
+	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno,
 	xfs_agino_t		ino,
-	struct xfs_dinode	*dino,
+	struct xfs_dinode	**dinop,
 	int			type,
 	int			*dirty,
 	xfs_rfsblock_t		*totblocks,
 	xfs_extnum_t		*nextents,
 	blkmap_t		**dblkmap,
-	int			check_dups)
+	int			check_dups,
+	struct xfs_buf		**ino_bpp)
 {
+	struct xfs_dinode	*dino = *dinop;
 	xfs_ino_t		lino = XFS_AGINO_TO_INO(mp, agno, ino);
 	int			err = 0;
 	xfs_extnum_t		nex, max_nex;
@@ -2004,20 +2006,22 @@ process_inode_data_fork(
  */
 static int
 process_inode_attr_fork(
-	xfs_mount_t		*mp,
+	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno,
 	xfs_agino_t		ino,
-	struct xfs_dinode	*dino,
+	struct xfs_dinode	**dinop,
 	int			type,
 	int			*dirty,
 	xfs_rfsblock_t		*atotblocks,
 	xfs_extnum_t		*anextents,
 	int			check_dups,
 	int			extra_attr_check,
-	int			*retval)
+	int			*retval,
+	struct xfs_buf		**ino_bpp)
 {
 	xfs_ino_t		lino = XFS_AGINO_TO_INO(mp, agno, ino);
-	blkmap_t		*ablkmap = NULL;
+	struct xfs_dinode	*dino = *dinop;
+	struct blkmap		*ablkmap = NULL;
 	int			repair = 0;
 	int			err;
 
@@ -2076,7 +2080,7 @@ process_inode_attr_fork(
 		 * XXX - put the inode onto the "move it" list and
 		 *	log the the attribute scrubbing
 		 */
-		do_warn(_("bad attribute fork in inode %" PRIu64), lino);
+		do_warn(_("bad attribute fork in inode %" PRIu64 "\n"), lino);
 
 		if (!no_modify)  {
 			do_warn(_(", clearing attr fork\n"));
@@ -2273,21 +2277,22 @@ _("Bad extent size hint %u on inode %" PRIu64 ", "),
  * for detailed, info, look at process_dinode() comments.
  */
 static int
-process_dinode_int(xfs_mount_t *mp,
-		struct xfs_dinode *dino,
-		xfs_agnumber_t agno,
-		xfs_agino_t ino,
-		int was_free,		/* 1 if inode is currently free */
-		int *dirty,		/* out == > 0 if inode is now dirty */
-		int *used,		/* out == 1 if inode is in use */
-		int verify_mode,	/* 1 == verify but don't modify inode */
-		int uncertain,		/* 1 == inode is uncertain */
-		int ino_discovery,	/* 1 == check dirs for unknown inodes */
-		int check_dups,		/* 1 == check if inode claims
-					 * duplicate blocks		*/
-		int extra_attr_check, /* 1 == do attribute format and value checks */
-		int *isa_dir,		/* out == 1 if inode is a directory */
-		xfs_ino_t *parent)	/* out -- parent if ino is a dir */
+process_dinode_int(
+	struct xfs_mount	*mp,
+	struct xfs_dinode	**dinop,
+	xfs_agnumber_t		agno,
+	xfs_agino_t		ino,
+	int			was_free,	/* 1 if inode is currently free */
+	int			*dirty,		/* out == > 0 if inode is now dirty */
+	int			*used,		/* out == 1 if inode is in use */
+	int			verify_mode,	/* 1 == verify but don't modify inode */
+	int			uncertain,	/* 1 == inode is uncertain */
+	int			ino_discovery,	/* 1 == check dirs for unknown inodes */
+	int			check_dups,	/* 1 == check if inode claims duplicate blocks */
+	int			extra_attr_check, /* 1 == do attribute format and value checks */
+	int			*isa_dir,	/* out == 1 if inode is a directory */
+	xfs_ino_t		*parent,	/* out -- parent if ino is a dir */
+	struct xfs_buf		**ino_bpp)
 {
 	xfs_rfsblock_t		totblocks = 0;
 	xfs_rfsblock_t		atotblocks = 0;
@@ -2300,6 +2305,7 @@ process_dinode_int(xfs_mount_t *mp,
 	const int		is_free = 0;
 	const int		is_used = 1;
 	blkmap_t		*dblkmap = NULL;
+	struct xfs_dinode	*dino = *dinop;
 	xfs_agino_t		unlinked_ino;
 	struct xfs_perag	*pag;
 
@@ -2323,6 +2329,7 @@ process_dinode_int(xfs_mount_t *mp,
 	 * If uncertain is set, verify_mode MUST be set.
 	 */
 	ASSERT(uncertain == 0 || verify_mode != 0);
+	ASSERT(ino_bpp != NULL || verify_mode != 0);
 
 	/*
 	 * This is the only valid point to check the CRC; after this we may have
@@ -2862,18 +2869,21 @@ _("Bad CoW extent size %u on inode %" PRIu64 ", "),
 	/*
 	 * check data fork -- if it's bad, clear the inode
 	 */
-	if (process_inode_data_fork(mp, agno, ino, dino, type, dirty,
-			&totblocks, &nextents, &dblkmap, check_dups) != 0)
+	if (process_inode_data_fork(mp, agno, ino, dinop, type, dirty,
+			&totblocks, &nextents, &dblkmap, check_dups,
+			ino_bpp) != 0)
 		goto bad_out;
+	dino = *dinop;
 
 	/*
 	 * check attribute fork if necessary.  attributes are
 	 * always stored in the regular filesystem.
 	 */
-	if (process_inode_attr_fork(mp, agno, ino, dino, type, dirty,
+	if (process_inode_attr_fork(mp, agno, ino, dinop, type, dirty,
 			&atotblocks, &anextents, check_dups, extra_attr_check,
-			&retval))
+			&retval, ino_bpp))
 		goto bad_out;
+	dino = *dinop;
 
 	/*
 	 * enforce totblocks is 0 for misc types
@@ -2991,8 +3001,8 @@ _("Bad CoW extent size %u on inode %" PRIu64 ", "),
 
 int
 process_dinode(
-	xfs_mount_t		*mp,
-	struct xfs_dinode	*dino,
+	struct xfs_mount	*mp,
+	struct xfs_dinode	**dinop,
 	xfs_agnumber_t		agno,
 	xfs_agino_t		ino,
 	int			was_free,
@@ -3002,7 +3012,8 @@ process_dinode(
 	int			check_dups,
 	int			extra_attr_check,
 	int			*isa_dir,
-	xfs_ino_t		*parent)
+	xfs_ino_t		*parent,
+	struct xfs_buf		**ino_bpp)
 {
 	const int		verify_mode = 0;
 	const int		uncertain = 0;
@@ -3010,9 +3021,10 @@ process_dinode(
 #ifdef XR_INODE_TRACE
 	fprintf(stderr, _("processing inode %d/%d\n"), agno, ino);
 #endif
-	return process_dinode_int(mp, dino, agno, ino, was_free, dirty, used,
-				verify_mode, uncertain, ino_discovery,
-				check_dups, extra_attr_check, isa_dir, parent);
+	return process_dinode_int(mp, dinop, agno, ino, was_free, dirty, used,
+			verify_mode, uncertain, ino_discovery,
+			check_dups, extra_attr_check, isa_dir, parent,
+			ino_bpp);
 }
 
 /*
@@ -3037,9 +3049,9 @@ verify_dinode(
 	const int		ino_discovery = 0;
 	const int		uncertain = 0;
 
-	return process_dinode_int(mp, dino, agno, ino, 0, &dirty, &used,
-				verify_mode, uncertain, ino_discovery,
-				check_dups, 0, &isa_dir, &parent);
+	return process_dinode_int(mp, &dino, agno, ino, 0, &dirty, &used,
+			verify_mode, uncertain, ino_discovery,
+			check_dups, 0, &isa_dir, &parent, NULL);
 }
 
 /*
@@ -3063,7 +3075,7 @@ verify_uncertain_dinode(
 	const int		ino_discovery = 0;
 	const int		uncertain = 1;
 
-	return process_dinode_int(mp, dino, agno, ino, 0, &dirty, &used,
+	return process_dinode_int(mp, &dino, agno, ino, 0, &dirty, &used,
 				verify_mode, uncertain, ino_discovery,
-				check_dups, 0, &isa_dir, &parent);
+				check_dups, 0, &isa_dir, &parent, NULL);
 }
diff --git a/repair/dinode.h b/repair/dinode.h
index 333d96d26a2..92df83da621 100644
--- a/repair/dinode.h
+++ b/repair/dinode.h
@@ -43,8 +43,8 @@ void
 update_rootino(xfs_mount_t *mp);
 
 int
-process_dinode(xfs_mount_t *mp,
-		struct xfs_dinode *dino,
+process_dinode(struct xfs_mount *mp,
+		struct xfs_dinode **dinop,
 		xfs_agnumber_t agno,
 		xfs_agino_t ino,
 		int was_free,
@@ -54,7 +54,8 @@ process_dinode(xfs_mount_t *mp,
 		int check_dups,
 		int extra_attr_check,
 		int *isa_dir,
-		xfs_ino_t *parent);
+		xfs_ino_t *parent,
+		struct xfs_buf **ino_bpp);
 
 int
 verify_dinode(xfs_mount_t *mp,

[PATCH 2/3] xfs_repair: sync bulkload data structures with kernel newbt code

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

A lot of the code in repair/bulkload.c was backwardsported from new code
that eventually turned into newbt.c in online repair.  Since the offline
repair version got merged upstream years before the online repair code,
we now need to bring the offline version up to date with the kernel
again.

Right now, the bulkload.c code is just a fancy way to track space
extents that are fed to it by its callers.  The only caller, of course,
is phase 5, which builds new btrees in AG space that wasn't claimed by
any other data structure.  Hence there's no need to allocate
reservations out of the bnobt or put them back there.

However, the next patch adds the ability to generate new file-based
btrees.  For that we need to reorganize the code to allocate and free
space for new file-based btrees.  Let's just crib from the kernel
version.  Make each bulkload space reservation hold a reference to an AG
and track the space reservation in terms of per-AG extents instead of
fsblock extents.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/libxfs_api_defs.h |    1 +
 repair/agbtree.c         |   22 +++++++++++-----
 repair/bulkload.c        |   63 +++++++++++++++++++++++++++++++++-------------
 repair/bulkload.h        |   12 +++++----
 repair/phase5.c          |    2 +
 5 files changed, 69 insertions(+), 31 deletions(-)


diff --git a/libxfs/libxfs_api_defs.h b/libxfs/libxfs_api_defs.h
index 33653d80bb1..0b89b503990 100644
--- a/libxfs/libxfs_api_defs.h
+++ b/libxfs/libxfs_api_defs.h
@@ -148,6 +148,7 @@
 #define xfs_log_sb			libxfs_log_sb
 #define xfs_mode_to_ftype		libxfs_mode_to_ftype
 #define xfs_perag_get			libxfs_perag_get
+#define xfs_perag_hold			libxfs_perag_hold
 #define xfs_perag_put			libxfs_perag_put
 #define xfs_prealloc_blocks		libxfs_prealloc_blocks
 
diff --git a/repair/agbtree.c b/repair/agbtree.c
index e014e216e0a..c6f0512fe7d 100644
--- a/repair/agbtree.c
+++ b/repair/agbtree.c
@@ -77,13 +77,17 @@ reserve_agblocks(
 	uint32_t		nr_blocks)
 {
 	struct extent_tree_node	*ext_ptr;
+	struct xfs_perag	*pag;
 	uint32_t		blocks_allocated = 0;
 	uint32_t		len;
 	int			error;
 
+	pag = libxfs_perag_get(mp, agno);
+	if (!pag)
+		do_error(_("could not open perag structure for agno 0x%x\n"),
+				agno);
+
 	while (blocks_allocated < nr_blocks)  {
-		xfs_fsblock_t	fsbno;
-
 		/*
 		 * Grab the smallest extent and use it up, then get the
 		 * next smallest.  This mimics the init_*_cursor code.
@@ -94,8 +98,8 @@ reserve_agblocks(
 
 		/* Use up the extent we've got. */
 		len = min(ext_ptr->ex_blockcount, nr_blocks - blocks_allocated);
-		fsbno = XFS_AGB_TO_FSB(mp, agno, ext_ptr->ex_startblock);
-		error = bulkload_add_blocks(&btr->newbt, fsbno, len);
+		error = bulkload_add_extent(&btr->newbt, pag,
+				ext_ptr->ex_startblock, len);
 		if (error)
 			do_error(_("could not set up btree reservation: %s\n"),
 				strerror(-error));
@@ -113,6 +117,7 @@ reserve_agblocks(
 	fprintf(stderr, "blocks_allocated = %d\n",
 		blocks_allocated);
 #endif
+	libxfs_perag_put(pag);
 	return blocks_allocated == nr_blocks;
 }
 
@@ -155,18 +160,21 @@ finish_rebuild(
 	int			error;
 
 	for_each_bulkload_reservation(&btr->newbt, resv, n) {
+		xfs_fsblock_t	fsbno;
+
 		if (resv->used == resv->len)
 			continue;
 
-		error = bitmap_set(lost_blocks, resv->fsbno + resv->used,
-				   resv->len - resv->used);
+		fsbno = XFS_AGB_TO_FSB(mp, resv->pag->pag_agno,
+				resv->agbno + resv->used);
+		error = bitmap_set(lost_blocks, fsbno, resv->len - resv->used);
 		if (error)
 			do_error(
 _("Insufficient memory saving lost blocks, err=%d.\n"), error);
 		resv->used = resv->len;
 	}
 
-	bulkload_destroy(&btr->newbt, 0);
+	bulkload_commit(&btr->newbt);
 }
 
 /*
diff --git a/repair/bulkload.c b/repair/bulkload.c
index 0117f69416c..18158c397f5 100644
--- a/repair/bulkload.c
+++ b/repair/bulkload.c
@@ -23,39 +23,64 @@ bulkload_init_ag(
 }
 
 /* Designate specific blocks to be used to build our new btree. */
-int
+static int
 bulkload_add_blocks(
-	struct bulkload		*bkl,
-	xfs_fsblock_t		fsbno,
-	xfs_extlen_t		len)
+	struct bulkload			*bkl,
+	struct xfs_perag		*pag,
+	const struct xfs_alloc_arg	*args)
 {
-	struct bulkload_resv	*resv;
+	struct xfs_mount		*mp = bkl->sc->mp;
+	struct bulkload_resv		*resv;
 
-	resv = kmem_alloc(sizeof(struct bulkload_resv), KM_MAYFAIL);
+	resv = kmalloc(sizeof(struct bulkload_resv), GFP_KERNEL);
 	if (!resv)
 		return ENOMEM;
 
 	INIT_LIST_HEAD(&resv->list);
-	resv->fsbno = fsbno;
-	resv->len = len;
+	resv->agbno = XFS_FSB_TO_AGBNO(mp, args->fsbno);
+	resv->len = args->len;
 	resv->used = 0;
+	resv->pag = libxfs_perag_hold(pag);
+
 	list_add_tail(&resv->list, &bkl->resv_list);
-	bkl->nr_reserved += len;
-
+	bkl->nr_reserved += args->len;
 	return 0;
 }
 
+/*
+ * Add an extent to the new btree reservation pool.  Callers are required to
+ * reap this reservation manually if the repair is cancelled.  @pag must be a
+ * passive reference.
+ */
+int
+bulkload_add_extent(
+	struct bulkload		*bkl,
+	struct xfs_perag	*pag,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
+{
+	struct xfs_mount	*mp = bkl->sc->mp;
+	struct xfs_alloc_arg	args = {
+		.tp		= NULL, /* no autoreap */
+		.oinfo		= bkl->oinfo,
+		.fsbno		= XFS_AGB_TO_FSB(mp, pag->pag_agno, agbno),
+		.len		= len,
+		.resv		= XFS_AG_RESV_NONE,
+	};
+
+	return bulkload_add_blocks(bkl, pag, &args);
+}
+
 /* Free all the accounting info and disk space we reserved for a new btree. */
 void
-bulkload_destroy(
-	struct bulkload		*bkl,
-	int			error)
+bulkload_commit(
+	struct bulkload		*bkl)
 {
 	struct bulkload_resv	*resv, *n;
 
 	list_for_each_entry_safe(resv, n, &bkl->resv_list, list) {
 		list_del(&resv->list);
-		kmem_free(resv);
+		kfree(resv);
 	}
 }
 
@@ -67,7 +92,8 @@ bulkload_claim_block(
 	union xfs_btree_ptr	*ptr)
 {
 	struct bulkload_resv	*resv;
-	xfs_fsblock_t		fsb;
+	struct xfs_mount	*mp = cur->bc_mp;
+	xfs_agblock_t		agbno;
 
 	/*
 	 * The first item in the list should always have a free block unless
@@ -84,7 +110,7 @@ bulkload_claim_block(
 	 * decreasing order, which hopefully results in leaf blocks ending up
 	 * together.
 	 */
-	fsb = resv->fsbno + resv->used;
+	agbno = resv->agbno + resv->used;
 	resv->used++;
 
 	/* If we used all the blocks in this reservation, move it to the end. */
@@ -92,9 +118,10 @@ bulkload_claim_block(
 		list_move_tail(&resv->list, &bkl->resv_list);
 
 	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
-		ptr->l = cpu_to_be64(fsb);
+		ptr->l = cpu_to_be64(XFS_AGB_TO_FSB(mp, resv->pag->pag_agno,
+								agbno));
 	else
-		ptr->s = cpu_to_be32(XFS_FSB_TO_AGBNO(cur->bc_mp, fsb));
+		ptr->s = cpu_to_be32(agbno);
 	return 0;
 }
 
diff --git a/repair/bulkload.h b/repair/bulkload.h
index a84e99b8c89..f4790e3b3de 100644
--- a/repair/bulkload.h
+++ b/repair/bulkload.h
@@ -17,8 +17,10 @@ struct bulkload_resv {
 	/* Link to list of extents that we've reserved. */
 	struct list_head	list;
 
-	/* FSB of the block we reserved. */
-	xfs_fsblock_t		fsbno;
+	struct xfs_perag	*pag;
+
+	/* AG block of the block we reserved. */
+	xfs_agblock_t		agbno;
 
 	/* Length of the reservation. */
 	xfs_extlen_t		len;
@@ -51,11 +53,11 @@ struct bulkload {
 
 void bulkload_init_ag(struct bulkload *bkl, struct repair_ctx *sc,
 		const struct xfs_owner_info *oinfo);
-int bulkload_add_blocks(struct bulkload *bkl, xfs_fsblock_t fsbno,
-		xfs_extlen_t len);
-void bulkload_destroy(struct bulkload *bkl, int error);
 int bulkload_claim_block(struct xfs_btree_cur *cur, struct bulkload *bkl,
 		union xfs_btree_ptr *ptr);
+int bulkload_add_extent(struct bulkload *bkl, struct xfs_perag *pag,
+		xfs_agblock_t agbno, xfs_extlen_t len);
+void bulkload_commit(struct bulkload *bkl);
 void bulkload_estimate_ag_slack(struct repair_ctx *sc,
 		struct xfs_btree_bload *bload, unsigned int free);
 
diff --git a/repair/phase5.c b/repair/phase5.c
index d6b8168ea77..b0e208f95af 100644
--- a/repair/phase5.c
+++ b/repair/phase5.c
@@ -194,7 +194,7 @@ fill_agfl(
 	for_each_bulkload_reservation(&btr->newbt, resv, n) {
 		xfs_agblock_t	bno;
 
-		bno = XFS_FSB_TO_AGBNO(mp, resv->fsbno + resv->used);
+		bno = resv->agbno + resv->used;
 		while (resv->used < resv->len &&
 		       *agfl_idx < libxfs_agfl_size(mp)) {
 			agfl_bnos[(*agfl_idx)++] = cpu_to_be32(bno++);

[PATCH 3/3] xfs_repair: rebuild block mappings from rmapbt data

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Use rmap records to rebuild corrupt inode forks instead of zapping
the whole inode if we think the rmap data is reasonably sane.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 include/xfs_trans.h      |    2 
 libxfs/libxfs_api_defs.h |   15 +
 libxfs/trans.c           |   48 +++
 repair/Makefile          |    2 
 repair/agbtree.c         |    2 
 repair/bmap_repair.c     |  749 ++++++++++++++++++++++++++++++++++++++++++++++
 repair/bmap_repair.h     |   13 +
 repair/bulkload.c        |  205 ++++++++++++-
 repair/bulkload.h        |   24 +
 repair/dinode.c          |   54 +++
 repair/rmap.c            |    2 
 repair/rmap.h            |    1 
 12 files changed, 1106 insertions(+), 11 deletions(-)
 create mode 100644 repair/bmap_repair.c
 create mode 100644 repair/bmap_repair.h


diff --git a/include/xfs_trans.h b/include/xfs_trans.h
index ab298ccfe55..ac82c3bc480 100644
--- a/include/xfs_trans.h
+++ b/include/xfs_trans.h
@@ -98,6 +98,8 @@ int	libxfs_trans_alloc_rollable(struct xfs_mount *mp, uint blocks,
 int	libxfs_trans_alloc_empty(struct xfs_mount *mp, struct xfs_trans **tpp);
 int	libxfs_trans_commit(struct xfs_trans *);
 void	libxfs_trans_cancel(struct xfs_trans *);
+int	libxfs_trans_reserve_more(struct xfs_trans *tp, uint blocks,
+			uint rtextents);
 
 /* cancel dfops associated with a transaction */
 void xfs_defer_cancel(struct xfs_trans *);
diff --git a/libxfs/libxfs_api_defs.h b/libxfs/libxfs_api_defs.h
index 0b89b503990..8495590966f 100644
--- a/libxfs/libxfs_api_defs.h
+++ b/libxfs/libxfs_api_defs.h
@@ -32,7 +32,7 @@
 #define xfs_alloc_fix_freelist		libxfs_alloc_fix_freelist
 #define xfs_alloc_min_freelist		libxfs_alloc_min_freelist
 #define xfs_alloc_read_agf		libxfs_alloc_read_agf
-#define xfs_alloc_vextent		libxfs_alloc_vextent
+#define xfs_alloc_vextent_start_ag	libxfs_alloc_vextent_start_ag
 
 #define xfs_ascii_ci_hashname		libxfs_ascii_ci_hashname
 
@@ -43,11 +43,18 @@
 #define xfs_attr_shortform_verify	libxfs_attr_shortform_verify
 
 #define __xfs_bmap_add_free		__libxfs_bmap_add_free
+#define xfs_bmap_validate_extent	libxfs_bmap_validate_extent
 #define xfs_bmapi_read			libxfs_bmapi_read
+#define xfs_bmapi_remap			libxfs_bmapi_remap
 #define xfs_bmapi_write			libxfs_bmapi_write
 #define xfs_bmap_last_offset		libxfs_bmap_last_offset
+#define xfs_bmbt_calc_size		libxfs_bmbt_calc_size
+#define xfs_bmbt_commit_staged_btree	libxfs_bmbt_commit_staged_btree
+#define xfs_bmbt_disk_get_startoff	libxfs_bmbt_disk_get_startoff
+#define xfs_bmbt_disk_set_all		libxfs_bmbt_disk_set_all
 #define xfs_bmbt_maxlevels_ondisk	libxfs_bmbt_maxlevels_ondisk
 #define xfs_bmbt_maxrecs		libxfs_bmbt_maxrecs
+#define xfs_bmbt_stage_cursor		libxfs_bmbt_stage_cursor
 #define xfs_bmdr_maxrecs		libxfs_bmdr_maxrecs
 
 #define xfs_btree_bload			libxfs_btree_bload
@@ -116,6 +123,7 @@
 
 #define xfs_finobt_calc_reserves	libxfs_finobt_calc_reserves
 #define xfs_free_extent			libxfs_free_extent
+#define xfs_free_extent_later		libxfs_free_extent_later
 #define xfs_free_perag			libxfs_free_perag
 #define xfs_fs_geometry			libxfs_fs_geometry
 #define xfs_highbit32			libxfs_highbit32
@@ -126,7 +134,10 @@
 #define xfs_ialloc_read_agi		libxfs_ialloc_read_agi
 #define xfs_idata_realloc		libxfs_idata_realloc
 #define xfs_idestroy_fork		libxfs_idestroy_fork
+#define xfs_iext_first			libxfs_iext_first
+#define xfs_iext_insert_raw		libxfs_iext_insert_raw
 #define xfs_iext_lookup_extent		libxfs_iext_lookup_extent
+#define xfs_iext_next			libxfs_iext_next
 #define xfs_ifork_zap_attr		libxfs_ifork_zap_attr
 #define xfs_imap_to_bp			libxfs_imap_to_bp
 #define xfs_initialize_perag		libxfs_initialize_perag
@@ -173,10 +184,12 @@
 #define xfs_rmapbt_stage_cursor		libxfs_rmapbt_stage_cursor
 #define xfs_rmap_compare		libxfs_rmap_compare
 #define xfs_rmap_get_rec		libxfs_rmap_get_rec
+#define xfs_rmap_ino_bmbt_owner		libxfs_rmap_ino_bmbt_owner
 #define xfs_rmap_irec_offset_pack	libxfs_rmap_irec_offset_pack
 #define xfs_rmap_irec_offset_unpack	libxfs_rmap_irec_offset_unpack
 #define xfs_rmap_lookup_le		libxfs_rmap_lookup_le
 #define xfs_rmap_lookup_le_range	libxfs_rmap_lookup_le_range
+#define xfs_rmap_query_all		libxfs_rmap_query_all
 #define xfs_rmap_query_range		libxfs_rmap_query_range
 
 #define xfs_rtbitmap_getword		libxfs_rtbitmap_getword
diff --git a/libxfs/trans.c b/libxfs/trans.c
index bd1186b24e6..8143a6a99f6 100644
--- a/libxfs/trans.c
+++ b/libxfs/trans.c
@@ -1143,3 +1143,51 @@ libxfs_trans_alloc_inode(
 	*tpp = tp;
 	return 0;
 }
+
+/*
+ * Try to reserve more blocks for a transaction.  The single use case we
+ * support is for offline repair -- use a transaction to gather data without
+ * fear of btree cycle deadlocks; calculate how many blocks we really need
+ * from that data; and only then start modifying data.  This can fail due to
+ * ENOSPC, so we have to be able to cancel the transaction.
+ */
+int
+libxfs_trans_reserve_more(
+	struct xfs_trans	*tp,
+	uint			blocks,
+	uint			rtextents)
+{
+	int			error = 0;
+
+	ASSERT(!(tp->t_flags & XFS_TRANS_DIRTY));
+
+	/*
+	 * Attempt to reserve the needed disk blocks by decrementing
+	 * the number needed from the number available.  This will
+	 * fail if the count would go below zero.
+	 */
+	if (blocks > 0) {
+		if (tp->t_mountp->m_sb.sb_fdblocks < blocks)
+			return -ENOSPC;
+		tp->t_blk_res += blocks;
+	}
+
+	/*
+	 * Attempt to reserve the needed realtime extents by decrementing
+	 * the number needed from the number available.  This will
+	 * fail if the count would go below zero.
+	 */
+	if (rtextents > 0) {
+		if (tp->t_mountp->m_sb.sb_rextents < rtextents) {
+			error = -ENOSPC;
+			goto out_blocks;
+		}
+	}
+
+	return 0;
+out_blocks:
+	if (blocks > 0)
+		tp->t_blk_res -= blocks;
+
+	return error;
+}
diff --git a/repair/Makefile b/repair/Makefile
index 2c40e59a30f..e5014deb0ce 100644
--- a/repair/Makefile
+++ b/repair/Makefile
@@ -16,6 +16,7 @@ HFILES = \
 	avl.h \
 	bulkload.h \
 	bmap.h \
+	bmap_repair.h \
 	btree.h \
 	da_util.h \
 	dinode.h \
@@ -41,6 +42,7 @@ CFILES = \
 	avl.c \
 	bulkload.c \
 	bmap.c \
+	bmap_repair.c \
 	btree.c \
 	da_util.c \
 	dino_chunks.c \
diff --git a/repair/agbtree.c b/repair/agbtree.c
index c6f0512fe7d..38f3f7b8fea 100644
--- a/repair/agbtree.c
+++ b/repair/agbtree.c
@@ -22,7 +22,7 @@ init_rebuild(
 {
 	memset(btr, 0, sizeof(struct bt_rebuild));
 
-	bulkload_init_ag(&btr->newbt, sc, oinfo);
+	bulkload_init_ag(&btr->newbt, sc, oinfo, NULLFSBLOCK);
 	btr->bload.max_dirty = XFS_B_TO_FSBT(sc->mp, 256U << 10); /* 256K */
 	bulkload_estimate_ag_slack(sc, &btr->bload, est_agfreeblocks);
 }
diff --git a/repair/bmap_repair.c b/repair/bmap_repair.c
new file mode 100644
index 00000000000..7705980621c
--- /dev/null
+++ b/repair/bmap_repair.c
@@ -0,0 +1,749 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2019-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include <libxfs.h>
+#include "btree.h"
+#include "err_protos.h"
+#include "libxlog.h"
+#include "incore.h"
+#include "globals.h"
+#include "dinode.h"
+#include "slab.h"
+#include "rmap.h"
+#include "bulkload.h"
+#include "bmap_repair.h"
+
+#define min_t(type, x, y) ( ((type)(x)) > ((type)(y)) ? ((type)(y)) : ((type)(x)) )
+
+/*
+ * Inode Fork Block Mapping (BMBT) Repair
+ * ======================================
+ *
+ * Gather all the rmap records for the inode and fork we're fixing, reset the
+ * incore fork, then recreate the btree.
+ */
+struct xrep_bmap {
+	/* List of new bmap records. */
+	struct xfs_slab		*bmap_records;
+	struct xfs_slab_cursor	*bmap_cursor;
+
+	/* New fork. */
+	struct bulkload		new_fork_info;
+	struct xfs_btree_bload	bmap_bload;
+
+	struct repair_ctx	*sc;
+
+	/* How many blocks did we find allocated to this file? */
+	xfs_rfsblock_t		nblocks;
+
+	/* How many bmbt blocks did we find for this fork? */
+	xfs_rfsblock_t		old_bmbt_block_count;
+
+	/* Which fork are we fixing? */
+	int			whichfork;
+};
+
+/* Remember this reverse-mapping as a series of bmap records. */
+STATIC int
+xrep_bmap_from_rmap(
+	struct xrep_bmap	*rb,
+	xfs_fileoff_t		startoff,
+	xfs_fsblock_t		startblock,
+	xfs_filblks_t		blockcount,
+	bool			unwritten)
+{
+	struct xfs_bmbt_rec	rbe;
+	struct xfs_bmbt_irec	irec;
+	int			error = 0;
+
+	irec.br_startoff = startoff;
+	irec.br_startblock = startblock;
+	irec.br_state = unwritten ? XFS_EXT_UNWRITTEN : XFS_EXT_NORM;
+
+	do {
+		xfs_failaddr_t	fa;
+
+		irec.br_blockcount = min_t(xfs_filblks_t, blockcount,
+				XFS_MAX_BMBT_EXTLEN);
+
+		fa = libxfs_bmap_validate_extent(rb->sc->ip, rb->whichfork,
+				&irec);
+		if (fa)
+			return -EFSCORRUPTED;
+
+		libxfs_bmbt_disk_set_all(&rbe, &irec);
+
+		error = slab_add(rb->bmap_records, &rbe);
+		if (error)
+			return error;
+
+		irec.br_startblock += irec.br_blockcount;
+		irec.br_startoff += irec.br_blockcount;
+		blockcount -= irec.br_blockcount;
+	} while (blockcount > 0);
+
+	return 0;
+}
+
+/* Check for any obvious errors or conflicts in the file mapping. */
+STATIC int
+xrep_bmap_check_fork_rmap(
+	struct xrep_bmap		*rb,
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*rec)
+{
+	struct repair_ctx		*sc = rb->sc;
+
+	/*
+	 * Data extents for rt files are never stored on the data device, but
+	 * everything else (xattrs, bmbt blocks) can be.
+	 */
+	if (XFS_IS_REALTIME_INODE(sc->ip) &&
+	    !(rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK)))
+		return EFSCORRUPTED;
+
+	/* Check that this is within the AG. */
+	if (!xfs_verify_agbext(cur->bc_ag.pag, rec->rm_startblock,
+				rec->rm_blockcount))
+		return EFSCORRUPTED;
+
+	/* No contradictory flags. */
+	if ((rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK)) &&
+	    (rec->rm_flags & XFS_RMAP_UNWRITTEN))
+		return EFSCORRUPTED;
+
+	/* Check the file offset range. */
+	if (!(rec->rm_flags & XFS_RMAP_BMBT_BLOCK) &&
+	    !xfs_verify_fileext(sc->mp, rec->rm_offset, rec->rm_blockcount))
+		return EFSCORRUPTED;
+
+	return 0;
+}
+
+/* Record extents that belong to this inode's fork. */
+STATIC int
+xrep_bmap_walk_rmap(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*rec,
+	void				*priv)
+{
+	struct xrep_bmap		*rb = priv;
+	struct xfs_mount		*mp = cur->bc_mp;
+	xfs_fsblock_t			fsbno;
+	int				error;
+
+	/* Skip extents which are not owned by this inode and fork. */
+	if (rec->rm_owner != rb->sc->ip->i_ino)
+		return 0;
+
+	error = xrep_bmap_check_fork_rmap(rb, cur, rec);
+	if (error)
+		return error;
+
+	/*
+	 * Record all blocks allocated to this file even if the extent isn't
+	 * for the fork we're rebuilding so that we can reset di_nblocks later.
+	 */
+	rb->nblocks += rec->rm_blockcount;
+
+	/* If this rmap isn't for the fork we want, we're done. */
+	if (rb->whichfork == XFS_DATA_FORK &&
+	    (rec->rm_flags & XFS_RMAP_ATTR_FORK))
+		return 0;
+	if (rb->whichfork == XFS_ATTR_FORK &&
+	    !(rec->rm_flags & XFS_RMAP_ATTR_FORK))
+		return 0;
+
+	fsbno = XFS_AGB_TO_FSB(mp, cur->bc_ag.pag->pag_agno,
+			rec->rm_startblock);
+
+	if (rec->rm_flags & XFS_RMAP_BMBT_BLOCK) {
+		rb->old_bmbt_block_count += rec->rm_blockcount;
+		return 0;
+	}
+
+	return xrep_bmap_from_rmap(rb, rec->rm_offset, fsbno,
+			rec->rm_blockcount,
+			rec->rm_flags & XFS_RMAP_UNWRITTEN);
+}
+
+/* Compare two bmap extents. */
+static int
+xrep_bmap_extent_cmp(
+	const void			*a,
+	const void			*b)
+{
+	xfs_fileoff_t			ao;
+	xfs_fileoff_t			bo;
+
+	ao = libxfs_bmbt_disk_get_startoff((struct xfs_bmbt_rec *)a);
+	bo = libxfs_bmbt_disk_get_startoff((struct xfs_bmbt_rec *)b);
+
+	if (ao > bo)
+		return 1;
+	else if (ao < bo)
+		return -1;
+	return 0;
+}
+
+/* Scan one AG for reverse mappings that we can turn into extent maps. */
+STATIC int
+xrep_bmap_scan_ag(
+	struct xrep_bmap	*rb,
+	struct xfs_perag	*pag)
+{
+	struct repair_ctx	*sc = rb->sc;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_buf		*agf_bp = NULL;
+	struct xfs_btree_cur	*cur;
+	int			error;
+
+	error = -libxfs_alloc_read_agf(pag, sc->tp, 0, &agf_bp);
+	if (error)
+		return error;
+	if (!agf_bp)
+		return ENOMEM;
+	cur = libxfs_rmapbt_init_cursor(mp, sc->tp, agf_bp, pag);
+	error = -libxfs_rmap_query_all(cur, xrep_bmap_walk_rmap, rb);
+	libxfs_btree_del_cursor(cur, error);
+	libxfs_trans_brelse(sc->tp, agf_bp);
+	return error;
+}
+
+/*
+ * Collect block mappings for this fork of this inode and decide if we have
+ * enough space to rebuild.  Caller is responsible for cleaning up the list if
+ * anything goes wrong.
+ */
+STATIC int
+xrep_bmap_find_mappings(
+	struct xrep_bmap	*rb)
+{
+	struct xfs_perag	*pag;
+	xfs_agnumber_t		agno;
+	int			error;
+
+	/* Iterate the rmaps for extents. */
+	for_each_perag(rb->sc->mp, agno, pag) {
+		error = xrep_bmap_scan_ag(rb, pag);
+		if (error) {
+			libxfs_perag_put(pag);
+			return error;
+		}
+	}
+
+	return 0;
+}
+
+/* Retrieve bmap data for bulk load. */
+STATIC int
+xrep_bmap_get_records(
+	struct xfs_btree_cur	*cur,
+	unsigned int		idx,
+	struct xfs_btree_block	*block,
+	unsigned int		nr_wanted,
+	void			*priv)
+{
+	struct xfs_bmbt_rec	*rec;
+	struct xfs_bmbt_irec	*irec = &cur->bc_rec.b;
+	struct xrep_bmap	*rb = priv;
+	union xfs_btree_rec	*block_rec;
+	unsigned int		loaded;
+
+	for (loaded = 0; loaded < nr_wanted; loaded++, idx++) {
+		rec = pop_slab_cursor(rb->bmap_cursor);
+		libxfs_bmbt_disk_get_all(rec, irec);
+
+		block_rec = libxfs_btree_rec_addr(cur, idx, block);
+		cur->bc_ops->init_rec_from_cur(cur, block_rec);
+	}
+
+	return loaded;
+}
+
+/* Feed one of the new btree blocks to the bulk loader. */
+STATIC int
+xrep_bmap_claim_block(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*ptr,
+	void			*priv)
+{
+	struct xrep_bmap        *rb = priv;
+
+	return bulkload_claim_block(cur, &rb->new_fork_info, ptr);
+}
+
+/* Figure out how much space we need to create the incore btree root block. */
+STATIC size_t
+xrep_bmap_iroot_size(
+	struct xfs_btree_cur	*cur,
+	unsigned int		level,
+	unsigned int		nr_this_level,
+	void			*priv)
+{
+	ASSERT(level > 0);
+
+	return XFS_BMAP_BROOT_SPACE_CALC(cur->bc_mp, nr_this_level);
+}
+
+/* Update the inode counters. */
+STATIC int
+xrep_bmap_reset_counters(
+	struct xrep_bmap	*rb)
+{
+	struct repair_ctx	*sc = rb->sc;
+	struct xbtree_ifakeroot	*ifake = &rb->new_fork_info.ifake;
+	int64_t			delta;
+
+	/*
+	 * Update the inode block counts to reflect the extents we found in the
+	 * rmapbt.
+	 */
+	delta = ifake->if_blocks - rb->old_bmbt_block_count;
+	sc->ip->i_nblocks = rb->nblocks + delta;
+	libxfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE);
+
+	/* Quotas don't exist so we're done. */
+	return 0;
+}
+
+/*
+ * Ensure that the inode being repaired is ready to handle a certain number of
+ * extents, or return EFSCORRUPTED.  Caller must hold the ILOCK of the inode
+ * being repaired and have joined it to the scrub transaction.
+ */
+static int
+xrep_ino_ensure_extent_count(
+	struct repair_ctx	*sc,
+	int			whichfork,
+	xfs_extnum_t		nextents)
+{
+	xfs_extnum_t		max_extents;
+	bool			large_extcount;
+
+	large_extcount = xfs_inode_has_large_extent_counts(sc->ip);
+	max_extents = xfs_iext_max_nextents(large_extcount, whichfork);
+	if (nextents <= max_extents)
+		return 0;
+	if (large_extcount)
+		return EFSCORRUPTED;
+	if (!xfs_has_large_extent_counts(sc->mp))
+		return EFSCORRUPTED;
+
+	max_extents = xfs_iext_max_nextents(true, whichfork);
+	if (nextents > max_extents)
+		return EFSCORRUPTED;
+
+	sc->ip->i_diflags2 |= XFS_DIFLAG2_NREXT64;
+	libxfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE);
+	return 0;
+}
+
+/*
+ * Create a new iext tree and load it with block mappings.  If the inode is
+ * in extents format, that's all we need to do to commit the new mappings.
+ * If it is in btree format, this takes care of preloading the incore tree.
+ */
+STATIC int
+xrep_bmap_extents_load(
+	struct xrep_bmap	*rb,
+	struct xfs_btree_cur	*bmap_cur,
+	uint64_t		nextents)
+{
+	struct xfs_iext_cursor	icur;
+	struct xbtree_ifakeroot	*ifake = &rb->new_fork_info.ifake;
+	struct xfs_ifork	*ifp = ifake->if_fork;
+	unsigned int		i;
+	int			error;
+
+	ASSERT(ifp->if_bytes == 0);
+
+	error = init_slab_cursor(rb->bmap_records, xrep_bmap_extent_cmp,
+			&rb->bmap_cursor);
+	if (error)
+		return error;
+
+	/* Add all the mappings to the incore extent tree. */
+	libxfs_iext_first(ifp, &icur);
+	for (i = 0; i < nextents; i++) {
+		struct xfs_bmbt_rec	*rec;
+
+		rec = pop_slab_cursor(rb->bmap_cursor);
+		libxfs_bmbt_disk_get_all(rec, &bmap_cur->bc_rec.b);
+		libxfs_iext_insert_raw(ifp, &icur, &bmap_cur->bc_rec.b);
+		ifp->if_nextents++;
+		libxfs_iext_next(ifp, &icur);
+	}
+	free_slab_cursor(&rb->bmap_cursor);
+
+	return xrep_ino_ensure_extent_count(rb->sc, rb->whichfork,
+			ifp->if_nextents);
+}
+
+/*
+ * Reserve new btree blocks, bulk load the bmap records into the ondisk btree,
+ * and load the incore extent tree.
+ */
+STATIC int
+xrep_bmap_btree_load(
+	struct xrep_bmap	*rb,
+	struct xfs_btree_cur	*bmap_cur,
+	uint64_t		nextents)
+{
+	struct repair_ctx	*sc = rb->sc;
+	int			error;
+
+	rb->bmap_bload.get_records = xrep_bmap_get_records;
+	rb->bmap_bload.claim_block = xrep_bmap_claim_block;
+	rb->bmap_bload.iroot_size = xrep_bmap_iroot_size;
+	rb->bmap_bload.max_dirty = XFS_B_TO_FSBT(sc->mp, 256U << 10); /* 256K */
+
+	/*
+	 * Always make the btree as small as possible, since we might need the
+	 * space to rebuild the space metadata btrees in later phases.
+	 */
+	rb->bmap_bload.leaf_slack = 0;
+	rb->bmap_bload.node_slack = 0;
+
+	/* Compute how many blocks we'll need. */
+	error = -libxfs_btree_bload_compute_geometry(bmap_cur, &rb->bmap_bload,
+			nextents);
+	if (error)
+		return error;
+
+	/*
+	 * Guess how many blocks we're going to need to rebuild an entire bmap
+	 * from the number of extents we found, and pump up our transaction to
+	 * have sufficient block reservation.
+	 */
+	error = -libxfs_trans_reserve_more(sc->tp, rb->bmap_bload.nr_blocks, 0);
+	if (error)
+		return error;
+
+	/* Reserve the space we'll need for the new btree. */
+	error = bulkload_alloc_file_blocks(&rb->new_fork_info,
+			rb->bmap_bload.nr_blocks);
+	if (error)
+		return error;
+
+	/* Add all observed bmap records. */
+	error = init_slab_cursor(rb->bmap_records, xrep_bmap_extent_cmp,
+			&rb->bmap_cursor);
+	if (error)
+		return error;
+	error = -libxfs_btree_bload(bmap_cur, &rb->bmap_bload, rb);
+	free_slab_cursor(&rb->bmap_cursor);
+	if (error)
+	       return error;
+
+	/*
+	 * Load the new bmap records into the new incore extent tree to
+	 * preserve delalloc reservations for regular files.  The directory
+	 * code loads the extent tree during xfs_dir_open and assumes
+	 * thereafter that it remains loaded, so we must not violate that
+	 * assumption.
+	 */
+	return xrep_bmap_extents_load(rb, bmap_cur, nextents);
+}
+
+/*
+ * Use the collected bmap information to stage a new bmap fork.  If this is
+ * successful we'll return with the new fork information logged to the repair
+ * transaction but not yet committed.
+ */
+STATIC int
+xrep_bmap_build_new_fork(
+	struct xrep_bmap	*rb)
+{
+	struct xfs_owner_info	oinfo;
+	struct repair_ctx	*sc = rb->sc;
+	struct xfs_btree_cur	*bmap_cur;
+	struct xbtree_ifakeroot	*ifake = &rb->new_fork_info.ifake;
+	uint64_t		nextents;
+	int			error;
+
+	/*
+	 * Sort the bmap extents by startblock to avoid btree splits when we
+	 * rebuild the bmbt btree.
+	 */
+	qsort_slab(rb->bmap_records, xrep_bmap_extent_cmp);
+
+	/*
+	 * Prepare to construct the new fork by initializing the new btree
+	 * structure and creating a fake ifork in the ifakeroot structure.
+	 */
+	libxfs_rmap_ino_bmbt_owner(&oinfo, sc->ip->i_ino, rb->whichfork);
+	bulkload_init_inode(&rb->new_fork_info, sc, rb->whichfork, &oinfo);
+	bmap_cur = libxfs_bmbt_stage_cursor(sc->mp, sc->ip, ifake);
+
+	/*
+	 * Figure out the size and format of the new fork, then fill it with
+	 * all the bmap records we've found.  Join the inode to the transaction
+	 * so that we can roll the transaction while holding the inode locked.
+	 */
+	libxfs_trans_ijoin(sc->tp, sc->ip, 0);
+	nextents = slab_count(rb->bmap_records);
+	if (nextents <= XFS_IFORK_MAXEXT(sc->ip, rb->whichfork)) {
+		ifake->if_fork->if_format = XFS_DINODE_FMT_EXTENTS;
+		error = xrep_bmap_extents_load(rb, bmap_cur, nextents);
+	} else {
+		ifake->if_fork->if_format = XFS_DINODE_FMT_BTREE;
+		error = xrep_bmap_btree_load(rb, bmap_cur, nextents);
+	}
+	if (error)
+		goto err_cur;
+
+	/*
+	 * Install the new fork in the inode.  After this point the old mapping
+	 * data are no longer accessible and the new tree is live.  We delete
+	 * the cursor immediately after committing the staged root because the
+	 * staged fork might be in extents format.
+	 */
+	libxfs_bmbt_commit_staged_btree(bmap_cur, sc->tp, rb->whichfork);
+	libxfs_btree_del_cursor(bmap_cur, 0);
+
+	/* Reset the inode counters now that we've changed the fork. */
+	error = xrep_bmap_reset_counters(rb);
+	if (error)
+		goto err_newbt;
+
+	/* Dispose of any unused blocks and the accounting infomation. */
+	error = bulkload_commit(&rb->new_fork_info);
+	if (error)
+		return error;
+
+	return -libxfs_trans_roll_inode(&sc->tp, sc->ip);
+err_cur:
+	if (bmap_cur)
+		libxfs_btree_del_cursor(bmap_cur, error);
+err_newbt:
+	bulkload_cancel(&rb->new_fork_info);
+	return error;
+}
+
+/* Check for garbage inputs.  Returns ECANCELED if there's nothing to do. */
+STATIC int
+xrep_bmap_check_inputs(
+	struct repair_ctx	*sc,
+	int			whichfork)
+{
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(sc->ip, whichfork);
+
+	ASSERT(whichfork == XFS_DATA_FORK || whichfork == XFS_ATTR_FORK);
+
+	if (!xfs_has_rmapbt(sc->mp))
+		return EOPNOTSUPP;
+
+	/* No fork means nothing to rebuild. */
+	if (!ifp)
+		return ECANCELED;
+
+	/*
+	 * We only know how to repair extent mappings, which is to say that we
+	 * only support extents and btree fork format.  Repairs to a local
+	 * format fork require a higher level repair function, so we do not
+	 * have any work to do here.
+	 */
+	switch (ifp->if_format) {
+	case XFS_DINODE_FMT_DEV:
+	case XFS_DINODE_FMT_LOCAL:
+	case XFS_DINODE_FMT_UUID:
+		return ECANCELED;
+	case XFS_DINODE_FMT_EXTENTS:
+	case XFS_DINODE_FMT_BTREE:
+		break;
+	default:
+		return EFSCORRUPTED;
+	}
+
+	if (whichfork == XFS_ATTR_FORK)
+		return 0;
+
+	/* Only files, symlinks, and directories get to have data forks. */
+	switch (VFS_I(sc->ip)->i_mode & S_IFMT) {
+	case S_IFREG:
+	case S_IFDIR:
+	case S_IFLNK:
+		/* ok */
+		break;
+	default:
+		return EINVAL;
+	}
+
+	/* Don't know how to rebuild realtime data forks. */
+	if (XFS_IS_REALTIME_INODE(sc->ip))
+		return EOPNOTSUPP;
+
+	return 0;
+}
+
+/* Repair an inode fork. */
+STATIC int
+xrep_bmap(
+	struct repair_ctx	*sc,
+	int			whichfork)
+{
+	struct xrep_bmap	*rb;
+	int			error = 0;
+
+	error = xrep_bmap_check_inputs(sc, whichfork);
+	if (error == ECANCELED)
+		return 0;
+	if (error)
+		return error;
+
+	rb = kmem_zalloc(sizeof(struct xrep_bmap), KM_NOFS | KM_MAYFAIL);
+	if (!rb)
+		return ENOMEM;
+	rb->sc = sc;
+	rb->whichfork = whichfork;
+
+	/* Set up some storage */
+	error = init_slab(&rb->bmap_records, sizeof(struct xfs_bmbt_rec));
+	if (error)
+		goto out_rb;
+
+	/* Collect all reverse mappings for this fork's extents. */
+	error = xrep_bmap_find_mappings(rb);
+	if (error)
+		goto out_bitmap;
+
+	/* Rebuild the bmap information. */
+	error = xrep_bmap_build_new_fork(rb);
+
+	/*
+	 * We don't need to free the old bmbt blocks because we're rebuilding
+	 * all the space metadata later.
+	 */
+
+out_bitmap:
+	free_slab(&rb->bmap_records);
+out_rb:
+	kmem_free(rb);
+	return error;
+}
+
+/* Rebuild some inode's bmap. */
+int
+rebuild_bmap(
+	struct xfs_mount	*mp,
+	xfs_ino_t		ino,
+	int			whichfork,
+	unsigned long		nr_extents,
+	struct xfs_buf		**ino_bpp,
+	struct xfs_dinode	**dinop,
+	int			*dirty)
+{
+	struct repair_ctx	sc = {
+		.mp		= mp,
+	};
+	const struct xfs_buf_ops *bp_ops;
+	unsigned long		boffset;
+	unsigned long long	resblks;
+	xfs_daddr_t		bp_bn;
+	int			bp_length;
+	int			error, err2;
+
+	bp_bn = xfs_buf_daddr(*ino_bpp);
+	bp_length = (*ino_bpp)->b_length;
+	bp_ops = (*ino_bpp)->b_ops;
+	boffset = (char *)(*dinop) - (char *)(*ino_bpp)->b_addr;
+
+	/*
+	 * Bail out if the inode didn't think it had extents.  Otherwise, zap
+	 * it back to a zero-extents fork so that we can rebuild it.
+	 */
+	switch (whichfork) {
+	case XFS_DATA_FORK:
+		if ((*dinop)->di_nextents == 0)
+			return 0;
+		(*dinop)->di_format = XFS_DINODE_FMT_EXTENTS;
+		(*dinop)->di_nextents = 0;
+		libxfs_dinode_calc_crc(mp, *dinop);
+		*dirty = 1;
+		break;
+	case XFS_ATTR_FORK:
+		if ((*dinop)->di_anextents == 0)
+			return 0;
+		(*dinop)->di_aformat = XFS_DINODE_FMT_EXTENTS;
+		(*dinop)->di_anextents = 0;
+		libxfs_dinode_calc_crc(mp, *dinop);
+		*dirty = 1;
+		break;
+	default:
+		return EINVAL;
+	}
+
+	resblks = libxfs_bmbt_calc_size(mp, nr_extents);
+	error = -libxfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, resblks, 0,
+			0, &sc.tp);
+	if (error)
+		return error;
+
+	/*
+	 * Repair magic: the caller passed us the inode cluster buffer for the
+	 * inode.  The _iget call grabs the buffer to load the incore inode, so
+	 * the buffer must be attached to the transaction to avoid recursing
+	 * the buffer lock.
+	 *
+	 * Unfortunately, the _iget call drops the buffer once the inode is
+	 * loaded, so if we've made any changes we have to log the buffer, hold
+	 * it, and roll the transaction.  This persists the caller's changes
+	 * and maintains our ownership of the cluster buffer.
+	 */
+	libxfs_trans_bjoin(sc.tp, *ino_bpp);
+	if (*dirty) {
+		unsigned int	end = BBTOB((*ino_bpp)->b_length) - 1;
+
+		libxfs_trans_log_buf(sc.tp, *ino_bpp, 0, end);
+		*dirty = 0;
+
+		libxfs_trans_bhold(sc.tp, *ino_bpp);
+		error = -libxfs_trans_roll(&sc.tp);
+		libxfs_trans_bjoin(sc.tp, *ino_bpp);
+		if (error)
+			goto out_cancel;
+	}
+
+	/* Grab the inode and fix the bmbt. */
+	error = -libxfs_iget(mp, sc.tp, ino, 0, &sc.ip);
+	if (error)
+		goto out_cancel;
+	error = xrep_bmap(&sc, whichfork);
+	if (error)
+		libxfs_trans_cancel(sc.tp);
+	else
+		error = -libxfs_trans_commit(sc.tp);
+
+	/*
+	 * Rebuilding the inode fork rolled the transaction, so we need to
+	 * re-grab the inode cluster buffer and dinode pointer for the caller.
+	 */
+	err2 = -libxfs_imap_to_bp(mp, NULL, &sc.ip->i_imap, ino_bpp);
+	if (err2)
+		do_error(
+ _("Unable to re-grab inode cluster buffer after failed repair of inode %llu, error %d.\n"),
+				(unsigned long long)ino, err2);
+	*dinop = xfs_buf_offset(*ino_bpp, sc.ip->i_imap.im_boffset);
+	libxfs_irele(sc.ip);
+
+	return error;
+
+out_cancel:
+	libxfs_trans_cancel(sc.tp);
+
+	/*
+	 * Try to regrab the old buffer so we have something to return to the
+	 * caller.
+	 */
+	err2 = -libxfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, bp_bn,
+			bp_length, 0, ino_bpp, bp_ops);
+	if (err2)
+		do_error(
+ _("Unable to re-grab inode cluster buffer after failed repair of inode %llu, error %d.\n"),
+				(unsigned long long)ino, err2);
+	*dinop = xfs_buf_offset(*ino_bpp, boffset);
+	return error;
+}
diff --git a/repair/bmap_repair.h b/repair/bmap_repair.h
new file mode 100644
index 00000000000..6d55359490a
--- /dev/null
+++ b/repair/bmap_repair.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2019-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef REBUILD_H_
+#define REBUILD_H_
+
+int rebuild_bmap(struct xfs_mount *mp, xfs_ino_t ino, int whichfork,
+		 unsigned long nr_extents, struct xfs_buf **ino_bpp,
+		 struct xfs_dinode **dinop, int *dirty);
+
+#endif /* REBUILD_H_ */
diff --git a/repair/bulkload.c b/repair/bulkload.c
index 18158c397f5..a97839f549d 100644
--- a/repair/bulkload.c
+++ b/repair/bulkload.c
@@ -14,14 +14,29 @@ void
 bulkload_init_ag(
 	struct bulkload			*bkl,
 	struct repair_ctx		*sc,
-	const struct xfs_owner_info	*oinfo)
+	const struct xfs_owner_info	*oinfo,
+	xfs_fsblock_t			alloc_hint)
 {
 	memset(bkl, 0, sizeof(struct bulkload));
 	bkl->sc = sc;
 	bkl->oinfo = *oinfo; /* structure copy */
+	bkl->alloc_hint = alloc_hint;
 	INIT_LIST_HEAD(&bkl->resv_list);
 }
 
+/* Initialize accounting resources for staging a new inode fork btree. */
+void
+bulkload_init_inode(
+	struct bulkload			*bkl,
+	struct repair_ctx		*sc,
+	int				whichfork,
+	const struct xfs_owner_info	*oinfo)
+{
+	bulkload_init_ag(bkl, sc, oinfo, XFS_INO_TO_FSB(sc->mp, sc->ip->i_ino));
+	bkl->ifake.if_fork = kmem_cache_zalloc(xfs_ifork_cache, 0);
+	bkl->ifake.if_fork_size = xfs_inode_fork_size(sc->ip, whichfork);
+}
+
 /* Designate specific blocks to be used to build our new btree. */
 static int
 bulkload_add_blocks(
@@ -71,17 +86,199 @@ bulkload_add_extent(
 	return bulkload_add_blocks(bkl, pag, &args);
 }
 
+/* Don't let our allocation hint take us beyond EOFS */
+static inline void
+bulkload_validate_file_alloc_hint(
+	struct bulkload		*bkl)
+{
+	struct repair_ctx	*sc = bkl->sc;
+
+	if (libxfs_verify_fsbno(sc->mp, bkl->alloc_hint))
+		return;
+
+	bkl->alloc_hint = XFS_AGB_TO_FSB(sc->mp, 0, XFS_AGFL_BLOCK(sc->mp) + 1);
+}
+
+/* Allocate disk space for our new file-based btree. */
+int
+bulkload_alloc_file_blocks(
+	struct bulkload		*bkl,
+	uint64_t		nr_blocks)
+{
+	struct repair_ctx	*sc = bkl->sc;
+	struct xfs_mount	*mp = sc->mp;
+	int			error = 0;
+
+	while (nr_blocks > 0) {
+		struct xfs_alloc_arg	args = {
+			.tp		= sc->tp,
+			.mp		= mp,
+			.oinfo		= bkl->oinfo,
+			.minlen		= 1,
+			.maxlen		= nr_blocks,
+			.prod		= 1,
+			.resv		= XFS_AG_RESV_NONE,
+		};
+		struct xfs_perag	*pag;
+		xfs_agnumber_t		agno;
+
+		bulkload_validate_file_alloc_hint(bkl);
+
+		error = -libxfs_alloc_vextent_start_ag(&args, bkl->alloc_hint);
+		if (error)
+			return error;
+		if (args.fsbno == NULLFSBLOCK)
+			return ENOSPC;
+
+		agno = XFS_FSB_TO_AGNO(mp, args.fsbno);
+
+		pag = libxfs_perag_get(mp, agno);
+		if (!pag) {
+			ASSERT(0);
+			return -EFSCORRUPTED;
+		}
+
+		error = bulkload_add_blocks(bkl, pag, &args);
+		libxfs_perag_put(pag);
+		if (error)
+			return error;
+
+		nr_blocks -= args.len;
+		bkl->alloc_hint = args.fsbno + args.len;
+
+		error = -libxfs_defer_finish(&sc->tp);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+/*
+ * Free the unused part of a space extent that was reserved for a new ondisk
+ * structure.  Returns the number of EFIs logged or a negative errno.
+ */
+static inline int
+bulkload_free_extent(
+	struct bulkload		*bkl,
+	struct bulkload_resv	*resv,
+	bool			btree_committed)
+{
+	struct repair_ctx	*sc = bkl->sc;
+	xfs_agblock_t		free_agbno = resv->agbno;
+	xfs_extlen_t		free_aglen = resv->len;
+	xfs_fsblock_t		fsbno;
+	int			error;
+
+	if (!btree_committed || resv->used == 0) {
+		/*
+		 * If we're not committing a new btree or we didn't use the
+		 * space reservation, free the entire space extent.
+		 */
+		goto free;
+	}
+
+	/*
+	 * We used space and committed the btree.  Remove the written blocks
+	 * from the reservation and possibly log a new EFI to free any unused
+	 * reservation space.
+	 */
+	free_agbno += resv->used;
+	free_aglen -= resv->used;
+
+	if (free_aglen == 0)
+		return 0;
+
+free:
+	/*
+	 * Use EFIs to free the reservations.  We don't need to use EFIs here
+	 * like the kernel, but we'll do it to keep the code matched.
+	 */
+	fsbno = XFS_AGB_TO_FSB(sc->mp, resv->pag->pag_agno, free_agbno);
+	error = -libxfs_free_extent_later(sc->tp, fsbno, free_aglen,
+			&bkl->oinfo, XFS_AG_RESV_NONE, true);
+	if (error)
+		return error;
+
+	return 1;
+}
+
 /* Free all the accounting info and disk space we reserved for a new btree. */
-void
-bulkload_commit(
-	struct bulkload		*bkl)
+static int
+bulkload_free(
+	struct bulkload		*bkl,
+	bool			btree_committed)
 {
+	struct repair_ctx	*sc = bkl->sc;
 	struct bulkload_resv	*resv, *n;
+	unsigned int		freed = 0;
+	int			error = 0;
 
 	list_for_each_entry_safe(resv, n, &bkl->resv_list, list) {
+		int		ret;
+
+		ret = bulkload_free_extent(bkl, resv, btree_committed);
 		list_del(&resv->list);
+		libxfs_perag_put(resv->pag);
 		kfree(resv);
+
+		if (ret < 0) {
+			error = ret;
+			goto junkit;
+		}
+
+		freed += ret;
+		if (freed >= XREP_MAX_ITRUNCATE_EFIS) {
+			error = -libxfs_defer_finish(&sc->tp);
+			if (error)
+				goto junkit;
+			freed = 0;
+		}
 	}
+
+	if (freed)
+		error = -libxfs_defer_finish(&sc->tp);
+junkit:
+	/*
+	 * If we still have reservations attached to @newbt, cleanup must have
+	 * failed and the filesystem is about to go down.  Clean up the incore
+	 * reservations.
+	 */
+	list_for_each_entry_safe(resv, n, &bkl->resv_list, list) {
+		list_del(&resv->list);
+		libxfs_perag_put(resv->pag);
+		kfree(resv);
+	}
+
+	if (sc->ip) {
+		kmem_cache_free(xfs_ifork_cache, bkl->ifake.if_fork);
+		bkl->ifake.if_fork = NULL;
+	}
+
+	return error;
+}
+
+/*
+ * Free all the accounting info and unused disk space allocations after
+ * committing a new btree.
+ */
+int
+bulkload_commit(
+	struct bulkload		*bkl)
+{
+	return bulkload_free(bkl, true);
+}
+
+/*
+ * Free all the accounting info and all of the disk space we reserved for a new
+ * btree that we're not going to commit.  We want to try to roll things back
+ * cleanly for things like ENOSPC midway through allocation.
+ */
+void
+bulkload_cancel(
+	struct bulkload		*bkl)
+{
+	bulkload_free(bkl, false);
 }
 
 /* Feed one of the reserved btree blocks to the bulk loader. */
diff --git a/repair/bulkload.h b/repair/bulkload.h
index f4790e3b3de..a88aafaa678 100644
--- a/repair/bulkload.h
+++ b/repair/bulkload.h
@@ -8,9 +8,17 @@
 
 extern int bload_leaf_slack;
 extern int bload_node_slack;
+/*
+ * This is the maximum number of deferred extent freeing item extents (EFIs)
+ * that we'll attach to a transaction without rolling the transaction to avoid
+ * overrunning a tr_itruncate reservation.
+ */
+#define XREP_MAX_ITRUNCATE_EFIS	(128)
 
 struct repair_ctx {
 	struct xfs_mount	*mp;
+	struct xfs_inode	*ip;
+	struct xfs_trans	*tp;
 };
 
 struct bulkload_resv {
@@ -36,7 +44,10 @@ struct bulkload {
 	struct list_head	resv_list;
 
 	/* Fake root for new btree. */
-	struct xbtree_afakeroot	afake;
+	union {
+		struct xbtree_afakeroot	afake;
+		struct xbtree_ifakeroot	ifake;
+	};
 
 	/* rmap owner of these blocks */
 	struct xfs_owner_info	oinfo;
@@ -44,6 +55,9 @@ struct bulkload {
 	/* The last reservation we allocated from. */
 	struct bulkload_resv	*last_resv;
 
+	/* Hint as to where we should allocate blocks. */
+	xfs_fsblock_t		alloc_hint;
+
 	/* Number of blocks reserved via resv_list. */
 	unsigned int		nr_reserved;
 };
@@ -52,12 +66,16 @@ struct bulkload {
 	list_for_each_entry_safe((resv), (n), &(bkl)->resv_list, list)
 
 void bulkload_init_ag(struct bulkload *bkl, struct repair_ctx *sc,
-		const struct xfs_owner_info *oinfo);
+		const struct xfs_owner_info *oinfo, xfs_fsblock_t alloc_hint);
+void bulkload_init_inode(struct bulkload *bkl, struct repair_ctx *sc,
+		int whichfork, const struct xfs_owner_info *oinfo);
 int bulkload_claim_block(struct xfs_btree_cur *cur, struct bulkload *bkl,
 		union xfs_btree_ptr *ptr);
 int bulkload_add_extent(struct bulkload *bkl, struct xfs_perag *pag,
 		xfs_agblock_t agbno, xfs_extlen_t len);
-void bulkload_commit(struct bulkload *bkl);
+int bulkload_alloc_file_blocks(struct bulkload *bkl, uint64_t nr_blocks);
+void bulkload_cancel(struct bulkload *bkl);
+int bulkload_commit(struct bulkload *bkl);
 void bulkload_estimate_ag_slack(struct repair_ctx *sc,
 		struct xfs_btree_bload *bload, unsigned int free);
 
diff --git a/repair/dinode.c b/repair/dinode.c
index 3f826b3482f..bd91ce14a36 100644
--- a/repair/dinode.c
+++ b/repair/dinode.c
@@ -20,6 +20,7 @@
 #include "threads.h"
 #include "slab.h"
 #include "rmap.h"
+#include "bmap_repair.h"
 
 /*
  * gettext lookups for translations of strings use mutexes internally to
@@ -1908,7 +1909,9 @@ process_inode_data_fork(
 	xfs_ino_t		lino = XFS_AGINO_TO_INO(mp, agno, ino);
 	int			err = 0;
 	xfs_extnum_t		nex, max_nex;
+	int			try_rebuild = -1; /* don't know yet */
 
+retry:
 	/*
 	 * extent count on disk is only valid for positive values. The kernel
 	 * uses negative values in memory. hence if we see negative numbers
@@ -1937,11 +1940,15 @@ process_inode_data_fork(
 		*totblocks = 0;
 		break;
 	case XFS_DINODE_FMT_EXTENTS:
+		if (!rmapbt_suspect && try_rebuild == -1)
+			try_rebuild = 1;
 		err = process_exinode(mp, agno, ino, dino, type, dirty,
 			totblocks, nextents, dblkmap, XFS_DATA_FORK,
 			check_dups);
 		break;
 	case XFS_DINODE_FMT_BTREE:
+		if (!rmapbt_suspect && try_rebuild == -1)
+			try_rebuild = 1;
 		err = process_btinode(mp, agno, ino, dino, type, dirty,
 			totblocks, nextents, dblkmap, XFS_DATA_FORK,
 			check_dups);
@@ -1957,8 +1964,28 @@ process_inode_data_fork(
 	if (err)  {
 		do_warn(_("bad data fork in inode %" PRIu64 "\n"), lino);
 		if (!no_modify)  {
+			if (try_rebuild == 1) {
+				do_warn(
+_("rebuilding inode %"PRIu64" data fork\n"),
+					lino);
+				try_rebuild = 0;
+				err = rebuild_bmap(mp, lino, XFS_DATA_FORK,
+						be32_to_cpu(dino->di_nextents),
+						ino_bpp, dinop, dirty);
+				dino = *dinop;
+				if (!err)
+					goto retry;
+				do_warn(
+_("inode %"PRIu64" data fork rebuild failed, error %d, clearing\n"),
+					lino, err);
+			}
 			clear_dinode(mp, dino, lino);
 			*dirty += 1;
+			ASSERT(*dirty > 0);
+		} else if (try_rebuild == 1) {
+			do_warn(
+_("would have tried to rebuild inode %"PRIu64" data fork\n"),
+					lino);
 		}
 		return 1;
 	}
@@ -2024,7 +2051,9 @@ process_inode_attr_fork(
 	struct blkmap		*ablkmap = NULL;
 	int			repair = 0;
 	int			err;
+	int			try_rebuild = -1; /* don't know yet */
 
+retry:
 	if (!dino->di_forkoff) {
 		*anextents = 0;
 		if (dino->di_aformat != XFS_DINODE_FMT_EXTENTS) {
@@ -2051,6 +2080,8 @@ process_inode_attr_fork(
 		err = process_lclinode(mp, agno, ino, dino, XFS_ATTR_FORK);
 		break;
 	case XFS_DINODE_FMT_EXTENTS:
+		if (!rmapbt_suspect && try_rebuild == -1)
+			try_rebuild = 1;
 		ablkmap = blkmap_alloc(*anextents, XFS_ATTR_FORK);
 		*anextents = 0;
 		err = process_exinode(mp, agno, ino, dino, type, dirty,
@@ -2058,6 +2089,8 @@ process_inode_attr_fork(
 				XFS_ATTR_FORK, check_dups);
 		break;
 	case XFS_DINODE_FMT_BTREE:
+		if (!rmapbt_suspect && try_rebuild == -1)
+			try_rebuild = 1;
 		ablkmap = blkmap_alloc(*anextents, XFS_ATTR_FORK);
 		*anextents = 0;
 		err = process_btinode(mp, agno, ino, dino, type, dirty,
@@ -2083,10 +2116,29 @@ process_inode_attr_fork(
 		do_warn(_("bad attribute fork in inode %" PRIu64 "\n"), lino);
 
 		if (!no_modify)  {
+			if (try_rebuild == 1) {
+				do_warn(
+_("rebuilding inode %"PRIu64" attr fork\n"),
+					lino);
+				try_rebuild = 0;
+				err = rebuild_bmap(mp, lino, XFS_ATTR_FORK,
+						be16_to_cpu(dino->di_anextents),
+						ino_bpp, dinop, dirty);
+				dino = *dinop;
+				if (!err)
+					goto retry;
+				do_warn(
+_("inode %"PRIu64" attr fork rebuild failed, error %d"),
+					lino, err);
+			}
 			do_warn(_(", clearing attr fork\n"));
 			*dirty += clear_dinode_attr(mp, dino, lino);
 			ASSERT(*dirty > 0);
-		} else  {
+		} else if (try_rebuild) {
+			do_warn(
+_("would have tried to rebuild inode %"PRIu64" attr fork or cleared it\n"),
+					lino);
+		} else {
 			do_warn(_(", would clear attr fork\n"));
 		}
 
diff --git a/repair/rmap.c b/repair/rmap.c
index 6bb77e08249..a2291c7b3b0 100644
--- a/repair/rmap.c
+++ b/repair/rmap.c
@@ -33,7 +33,7 @@ struct xfs_ag_rmap {
 };
 
 static struct xfs_ag_rmap *ag_rmaps;
-static bool rmapbt_suspect;
+bool rmapbt_suspect;
 static bool refcbt_suspect;
 
 static inline int rmap_compare(const void *a, const void *b)
diff --git a/repair/rmap.h b/repair/rmap.h
index 6004e9f68b6..1dad2f5890a 100644
--- a/repair/rmap.h
+++ b/repair/rmap.h
@@ -7,6 +7,7 @@
 #define RMAP_H_
 
 extern bool collect_rmaps;
+extern bool rmapbt_suspect;
 
 extern bool rmap_needs_work(struct xfs_mount *);
 

[PATCH 1/8] xfs_db: add a bmbt inflation command

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add a command to xfs_db to clone a data fork mapping over and over
again.  This will make it easier to exercise really high sharing counts.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 db/Makefile       |    4 
 db/bmap_inflate.c |  564 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 db/command.c      |    1 
 db/command.h      |    1 
 man/man8/xfs_db.8 |   23 ++
 5 files changed, 591 insertions(+), 2 deletions(-)
 create mode 100644 db/bmap_inflate.c


diff --git a/db/Makefile b/db/Makefile
index d00801ab473..1511d4a3968 100644
--- a/db/Makefile
+++ b/db/Makefile
@@ -14,8 +14,8 @@ HFILES = addr.h agf.h agfl.h agi.h attr.h attrshort.h bit.h block.h bmap.h \
 	io.h logformat.h malloc.h metadump.h output.h print.h quit.h sb.h \
 	sig.h strvec.h text.h type.h write.h attrset.h symlink.h fsmap.h \
 	fuzz.h obfuscate.h
-CFILES = $(HFILES:.h=.c) btdump.c btheight.c convert.c info.c iunlink.c namei.c \
-	timelimit.c
+CFILES = $(HFILES:.h=.c) bmap_inflate.c btdump.c btheight.c convert.c info.c \
+	iunlink.c namei.c timelimit.c
 LSRCFILES = xfs_admin.sh xfs_ncheck.sh xfs_metadump.sh
 
 LLDLIBS	= $(LIBXFS) $(LIBXLOG) $(LIBFROG) $(LIBUUID) $(LIBRT) $(LIBURCU) \
diff --git a/db/bmap_inflate.c b/db/bmap_inflate.c
new file mode 100644
index 00000000000..a3ad6ad3832
--- /dev/null
+++ b/db/bmap_inflate.c
@@ -0,0 +1,564 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2022-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "libxfs.h"
+#include "command.h"
+#include "init.h"
+#include "output.h"
+#include "io.h"
+#include "libfrog/convert.h"
+
+static void
+bmapinflate_help(void)
+{
+	dbprintf(_(
+"\n"
+" Make the bmbt really big by cloning the first data fork mapping over and over.\n"
+" -d     Constrain dirty buffers to this many bytes.\n"
+" -e     Print the size and height of the btree and exit.\n"
+" -n nr  Create this many copies of the mapping.\n"
+"\n"
+));
+
+}
+
+static int
+find_mapping(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	struct xfs_bmbt_irec	*irec)
+{
+	struct xfs_iext_cursor	icur;
+	int			error;
+
+	if (!xfs_has_reflink(ip->i_mount)) {
+		dbprintf(_("filesystem does not support reflink\n"));
+		return 1;
+	}
+
+	if (ip->i_df.if_nextents != 1) {
+		dbprintf(_("inode must have only one data fork mapping\n"));
+		return 1;
+	}
+
+	error = -libxfs_iread_extents(tp, ip, XFS_DATA_FORK);
+	if (error) {
+		dbprintf(_("could not read data fork, err %d\n"), error);
+		return 1;
+	}
+
+	libxfs_iext_first(&ip->i_df, &icur);
+	if (!xfs_iext_get_extent(&ip->i_df, &icur, irec)) {
+		dbprintf(_("could not read data fork mapping\n"));
+		return 1;
+	}
+
+	if (irec->br_state != XFS_EXT_NORM) {
+		dbprintf(_("cannot duplicate unwritten extent\n"));
+		return 1;
+	}
+
+	return 0;
+}
+
+static int
+set_nrext64(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	xfs_extnum_t		nextents)
+{
+	xfs_extnum_t		max_extents;
+	bool			large_extcount;
+
+	large_extcount = xfs_inode_has_large_extent_counts(ip);
+	max_extents = xfs_iext_max_nextents(large_extcount, XFS_DATA_FORK);
+	if (nextents <= max_extents)
+		return 0;
+	if (large_extcount)
+		return EFSCORRUPTED;
+	if (!xfs_has_large_extent_counts(ip->i_mount))
+		return EFSCORRUPTED;
+
+	max_extents = xfs_iext_max_nextents(true, XFS_DATA_FORK);
+	if (nextents > max_extents)
+		return EFSCORRUPTED;
+
+	ip->i_diflags2 |= XFS_DIFLAG2_NREXT64;
+	libxfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+	return 0;
+}
+
+static int
+populate_extents(
+	struct xfs_trans		*tp,
+	struct xfs_inode		*ip,
+	struct xbtree_ifakeroot		*ifake,
+	const struct xfs_bmbt_irec	*template,
+	xfs_extnum_t			nextents)
+{
+	struct xfs_bmbt_irec		irec = {
+		.br_startoff		= 0,
+		.br_startblock		= template->br_startblock,
+		.br_blockcount		= template->br_blockcount,
+		.br_state		= XFS_EXT_NORM,
+	};
+	struct xfs_iext_cursor		icur;
+	struct xfs_ifork		*ifp = ifake->if_fork;
+	unsigned long long		i;
+
+	/* Add all the mappings to the incore extent tree. */
+	libxfs_iext_first(ifp, &icur);
+	for (i = 0; i < nextents; i++) {
+		libxfs_iext_insert_raw(ifp, &icur, &irec);
+		ifp->if_nextents++;
+		libxfs_iext_next(ifp, &icur);
+
+#ifdef BORK
+		dbprintf(_("[%llu] 0x%lx 0x%lx 0x%lx\n"), i, irec.br_startoff,
+					irec.br_startblock,
+					irec.br_blockcount);
+#endif
+
+		irec.br_startoff += irec.br_blockcount;
+	}
+
+	ip->i_nblocks = template->br_blockcount * nextents;
+	libxfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+	return 0;
+}
+
+struct bmbt_resv {
+	struct list_head	list;
+	xfs_fsblock_t		fsbno;
+	xfs_extlen_t		len;
+	xfs_extlen_t		used;
+};
+
+struct bmbt_data {
+	struct xfs_bmbt_irec	irec;
+	struct list_head	resv_list;
+	unsigned long long	iblocks;
+	unsigned long long	nr;
+};
+
+static int
+alloc_bmbt_blocks(
+	struct xfs_trans	**tpp,
+	struct xfs_inode	*ip,
+	struct bmbt_data	*bd,
+	uint64_t		nr_blocks)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct list_head	*resv_list = &bd->resv_list;
+	int			error = 0;
+
+	while (nr_blocks > 0) {
+		struct xfs_alloc_arg	args = {
+			.tp		= *tpp,
+			.mp		= mp,
+			.minlen		= 1,
+			.maxlen		= nr_blocks,
+			.prod		= 1,
+			.resv		= XFS_AG_RESV_NONE,
+		};
+		struct bmbt_resv	*resv;
+		xfs_fsblock_t		target = 0;
+
+		if (xfs_has_rmapbt(mp)) {
+			xfs_agnumber_t		tgt_agno;
+
+			/*
+			 * Try to allocate bmbt blocks in a different AG so
+			 * that we don't blow up the rmapbt with the bmbt
+			 * records.
+			 */
+			tgt_agno = 1 + XFS_FSB_TO_AGNO(mp,
+							bd->irec.br_startblock);
+			if (tgt_agno >= mp->m_sb.sb_agcount)
+				tgt_agno = 0;
+			target = XFS_AGB_TO_FSB(mp, tgt_agno, 0);
+		}
+
+		libxfs_rmap_ino_bmbt_owner(&args.oinfo, ip->i_ino,
+				XFS_DATA_FORK);
+
+		error = -libxfs_alloc_vextent_start_ag(&args, target);
+		if (error)
+			return error;
+		if (args.fsbno == NULLFSBLOCK)
+			return ENOSPC;
+
+		resv = kmalloc(sizeof(struct bmbt_resv), 0);
+		if (!resv)
+			return ENOMEM;
+
+		INIT_LIST_HEAD(&resv->list);
+		resv->fsbno = args.fsbno;
+		resv->len = args.len;
+		resv->used = 0;
+		list_add_tail(&resv->list, resv_list);
+
+		nr_blocks -= args.len;
+
+		error = -libxfs_trans_roll_inode(tpp, ip);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+static int
+get_bmbt_records(
+	struct xfs_btree_cur	*cur,
+	unsigned int		idx,
+	struct xfs_btree_block	*block,
+	unsigned int		nr_wanted,
+	void			*priv)
+{
+	struct xfs_bmbt_irec	*irec = &cur->bc_rec.b;
+	struct bmbt_data	*bd = priv;
+	union xfs_btree_rec	*block_rec;
+	struct xfs_ifork	*ifp = cur->bc_ino.ifake->if_fork;
+	unsigned int		loaded;
+
+	for (loaded = 0; loaded < nr_wanted; loaded++, idx++) {
+		memcpy(irec, &bd->irec, sizeof(struct xfs_bmbt_irec));
+
+		block_rec = libxfs_btree_rec_addr(cur, idx, block);
+		cur->bc_ops->init_rec_from_cur(cur, block_rec);
+		ifp->if_nextents++;
+
+#ifdef BORK
+		dbprintf(_("[%llu] 0x%lx 0x%lx 0x%lx\n"), bd->nr++,
+					irec->br_startoff,
+					irec->br_startblock,
+					irec->br_blockcount);
+#endif
+
+		bd->irec.br_startoff += bd->irec.br_blockcount;
+	}
+
+	return loaded;
+}
+
+static int
+claim_block(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*ptr,
+	void			*priv)
+{
+	struct bmbt_data	*bd = priv;
+	struct bmbt_resv	*resv;
+	xfs_fsblock_t		fsb;
+
+	/*
+	 * The first item in the list should always have a free block unless
+	 * we're completely out.
+	 */
+	resv = list_first_entry(&bd->resv_list, struct bmbt_resv, list);
+	if (resv->used == resv->len)
+		return ENOSPC;
+
+	fsb = resv->fsbno + resv->used;
+	resv->used++;
+
+	/* If we used all the blocks in this reservation, move it to the end. */
+	if (resv->used == resv->len)
+		list_move_tail(&resv->list, &bd->resv_list);
+
+	ptr->l = cpu_to_be64(fsb);
+	bd->iblocks++;
+	return 0;
+}
+
+static size_t
+iroot_size(
+	struct xfs_btree_cur	*cur,
+	unsigned int		level,
+	unsigned int		nr_this_level,
+	void			*priv)
+{
+	return XFS_BMAP_BROOT_SPACE_CALC(cur->bc_mp, nr_this_level);
+}
+
+static int
+populate_btree(
+	struct xfs_trans		**tpp,
+	struct xfs_inode		*ip,
+	uint16_t			dirty_blocks,
+	struct xbtree_ifakeroot		*ifake,
+	struct xfs_btree_cur		*bmap_cur,
+	const struct xfs_bmbt_irec	*template,
+	xfs_extnum_t			nextents)
+{
+	struct xfs_btree_bload		bmap_bload = {
+		.get_records		= get_bmbt_records,
+		.claim_block		= claim_block,
+		.iroot_size		= iroot_size,
+		.max_dirty		= dirty_blocks,
+		.leaf_slack		= 1,
+		.node_slack		= 1,
+	};
+	struct bmbt_data		bd = {
+		.irec			= {
+			.br_startoff	= 0,
+			.br_startblock	= template->br_startblock,
+			.br_blockcount	= template->br_blockcount,
+			.br_state	= XFS_EXT_NORM,
+		},
+		.iblocks		= 0,
+	};
+	struct bmbt_resv		*resv, *n;
+	int				error;
+
+	error = -libxfs_btree_bload_compute_geometry(bmap_cur, &bmap_bload,
+			nextents);
+	if (error)
+		return error;
+
+	error = -libxfs_trans_reserve_more(*tpp, bmap_bload.nr_blocks, 0);
+	if (error)
+		return error;
+
+	INIT_LIST_HEAD(&bd.resv_list);
+	error = alloc_bmbt_blocks(tpp, ip, &bd, bmap_bload.nr_blocks);
+	if (error)
+		return error;
+
+	error = -libxfs_btree_bload(bmap_cur, &bmap_bload, &bd);
+	if (error)
+	       goto out_resv_list;
+
+	ip->i_nblocks = bd.iblocks + (template->br_blockcount * nextents);
+	libxfs_trans_log_inode(*tpp, ip, XFS_ILOG_CORE);
+
+out_resv_list:
+	/* Leak any unused blocks */
+	list_for_each_entry_safe(resv, n, &bd.resv_list, list) {
+		list_del(&resv->list);
+		kmem_free(resv);
+	}
+	return error;
+}
+
+static int
+build_new_datafork(
+	struct xfs_trans		**tpp,
+	struct xfs_inode		*ip,
+	uint16_t			dirty_blocks,
+	const struct xfs_bmbt_irec	*irec,
+	xfs_extnum_t			nextents)
+{
+	struct xbtree_ifakeroot		ifake;
+	struct xfs_btree_cur		*bmap_cur;
+	int				error;
+
+	error = set_nrext64(*tpp, ip, nextents);
+	if (error)
+		return error;
+
+	/* Set up staging for the new bmbt */
+	ifake.if_fork = kmem_cache_zalloc(xfs_ifork_cache, 0);
+	ifake.if_fork_size = xfs_inode_fork_size(ip, XFS_DATA_FORK);
+	bmap_cur = libxfs_bmbt_stage_cursor(ip->i_mount, ip, &ifake);
+
+	/*
+	 * Figure out the size and format of the new fork, then fill it with
+	 * the bmap record we want.
+	 */
+	if (nextents <= XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK)) {
+		ifake.if_fork->if_format = XFS_DINODE_FMT_EXTENTS;
+		error = populate_extents(*tpp, ip, &ifake, irec, nextents);
+	} else {
+		ifake.if_fork->if_format = XFS_DINODE_FMT_BTREE;
+		error = populate_btree(tpp, ip, dirty_blocks, &ifake, bmap_cur,
+				irec, nextents);
+	}
+	if (error) {
+		libxfs_btree_del_cursor(bmap_cur, 0);
+		goto err_ifork;
+	}
+
+	/* Install the new fork in the inode. */
+	libxfs_bmbt_commit_staged_btree(bmap_cur, *tpp, XFS_DATA_FORK);
+	libxfs_btree_del_cursor(bmap_cur, 0);
+
+	/* Mark filesystem as needsrepair */
+	dbprintf(_("filesystem is now inconsistent, xfs_repair required!\n"));
+	mp->m_sb.sb_features_incompat |= XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR;
+	libxfs_log_sb(*tpp);
+
+err_ifork:
+	kmem_cache_free(xfs_ifork_cache, ifake.if_fork);
+	return error;
+}
+
+static int
+estimate_size(
+	struct xfs_inode		*ip,
+	unsigned long long		dirty_blocks,
+	xfs_extnum_t			nextents)
+{
+	struct xfs_btree_bload		bmap_bload = {
+		.leaf_slack		= 1,
+		.node_slack		= 1,
+	};
+	struct xbtree_ifakeroot		ifake;
+	struct xfs_btree_cur		*bmap_cur;
+	int				error;
+
+	/* FMT_EXTENTS means we report zero btblocks and zero height */
+	if (nextents <= XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))
+		goto report;
+
+	ifake.if_fork = kmem_cache_zalloc(xfs_ifork_cache, 0);
+	ifake.if_fork_size = xfs_inode_fork_size(ip, XFS_DATA_FORK);
+
+	bmap_cur = libxfs_bmbt_stage_cursor(ip->i_mount, ip, &ifake);
+	error = -libxfs_btree_bload_compute_geometry(bmap_cur, &bmap_bload,
+			nextents);
+	libxfs_btree_del_cursor(bmap_cur, error);
+
+	kmem_cache_free(xfs_ifork_cache, ifake.if_fork);
+
+	if (error)
+		return error;
+
+report:
+	dbprintf(_("ino 0x%llx nextents %llu btblocks %llu btheight %u dirty %u\n"),
+			ip->i_ino, nextents, bmap_bload.nr_blocks,
+			bmap_bload.btree_height, dirty_blocks);
+
+	return 0;
+}
+
+static int
+bmapinflate_f(
+	int			argc,
+	char			**argv)
+{
+	struct xfs_bmbt_irec	irec;
+	struct xfs_inode	*ip;
+	struct xfs_trans	*tp;
+	char			*p;
+	unsigned long long	nextents = 0;
+	unsigned long long	dirty_bytes = 60U << 20; /* 60MiB */
+	unsigned long long	dirty_blocks;
+	unsigned int		resblks;
+	bool			estimate = false;
+	int			c, error;
+
+	if (iocur_top->ino == NULLFSINO) {
+		dbprintf(_("no current inode\n"));
+		return 0;
+	}
+
+	optind = 0;
+	while ((c = getopt(argc, argv, "d:en:")) != EOF) {
+		switch (c) {
+		case 'e':
+			estimate = true;
+			break;
+		case 'n':
+			errno = 0;
+			nextents = strtoull(optarg, &p, 0);
+			if (errno) {
+				perror(optarg);
+				return 1;
+			}
+			break;
+		case 'd':
+			errno = 0;
+			dirty_bytes = cvtnum(mp->m_sb.sb_blocksize,
+					     mp->m_sb.sb_sectsize, optarg);
+			if (errno) {
+				perror(optarg);
+				return 1;
+			}
+			break;
+		default:
+			dbprintf(_("bad option for bmap command\n"));
+			return 0;
+		}
+	}
+
+	dirty_blocks = XFS_B_TO_FSBT(mp, dirty_bytes);
+	if (dirty_blocks >= UINT16_MAX)
+		dirty_blocks = UINT16_MAX - 1;
+
+	error = -libxfs_iget(mp, NULL, iocur_top->ino, 0, &ip);
+	if (error) {
+		dbprintf(_("could not grab inode 0x%llx, err %d\n"),
+				iocur_top->ino, error);
+		return 1;
+	}
+
+	error = estimate_size(ip, dirty_blocks, nextents);
+	if (error)
+		goto out_irele;
+	if (estimate)
+		goto done;
+
+	resblks = libxfs_bmbt_calc_size(mp, nextents);
+	error = -libxfs_trans_alloc_inode(ip, &M_RES(mp)->tr_itruncate,
+			resblks, 0, false, &tp);
+	if (error) {
+		dbprintf(_("could not allocate transaction, err %d\n"),
+				error);
+		return 1;
+	}
+
+	error = find_mapping(tp, ip, &irec);
+	if (error)
+		goto out_cancel;
+
+	error = build_new_datafork(&tp, ip, dirty_blocks, &irec, nextents);
+	if (error) {
+		dbprintf(_("could not build new data fork, err %d\n"),
+				error);
+		exitcode = 1;
+		goto out_cancel;
+	}
+
+	error = -libxfs_trans_commit(tp);
+	if (error) {
+		dbprintf(_("could not commit transaction, err %d\n"),
+				error);
+		exitcode = 1;
+		return 1;
+	}
+
+done:
+	libxfs_irele(ip);
+	return 0;
+
+out_cancel:
+	libxfs_trans_cancel(tp);
+out_irele:
+	libxfs_irele(ip);
+	return 1;
+}
+
+static const struct cmdinfo bmapinflate_cmd = {
+	.name		= "bmapinflate",
+	.cfunc		= bmapinflate_f,
+	.argmin		= 0,
+	.argmax		= -1,
+	.canpush	= 0,
+	.args		= N_("[-n copies] [-e] [-d maxdirty]"),
+	.oneline	= N_("inflate bmbt by copying mappings"),
+	.help		= bmapinflate_help,
+};
+
+void
+bmapinflate_init(void)
+{
+	if (!expert_mode)
+		return;
+
+	add_command(&bmapinflate_cmd);
+}
diff --git a/db/command.c b/db/command.c
index 2bbd7b0b24f..6cda03e9856 100644
--- a/db/command.c
+++ b/db/command.c
@@ -142,4 +142,5 @@ init_commands(void)
 	fuzz_init();
 	timelimit_init();
 	iunlink_init();
+	bmapinflate_init();
 }
diff --git a/db/command.h b/db/command.h
index a89e71504f9..2c2926afd7b 100644
--- a/db/command.h
+++ b/db/command.h
@@ -35,3 +35,4 @@ extern void		btheight_init(void);
 extern void		timelimit_init(void);
 extern void		namei_init(void);
 extern void		iunlink_init(void);
+extern void		bmapinflate_init(void);
diff --git a/man/man8/xfs_db.8 b/man/man8/xfs_db.8
index f53ddd67d87..a7f6d55ed8b 100644
--- a/man/man8/xfs_db.8
+++ b/man/man8/xfs_db.8
@@ -388,6 +388,29 @@ and
 options are used to select the attribute or data
 area of the inode, if neither option is given then both areas are shown.
 .TP
+.BI "bmapinflate [\-d " dirty_bytes "] [-e] [\-n " nr "]
+Duplicates the first data fork mapping this many times, as if the mapping had
+been repeatedly reflinked.
+This is an expert-mode command for exercising high-refcount filesystems only.
+Existing data fork mappings will be forgotten and the refcount btree will not
+be updated.
+This command leaves at least the refcount btree and the inode inconsistent;
+.B xfs_repair
+must be run afterwards.
+.RS 1.0i
+.TP 0.4i
+.B \-d
+Constrain the memory consumption of new dirty btree blocks to this quantity.
+Defaults to 60MiB.
+.TP 0.4i
+.B \-e
+Estimate the number of blocks and height of the new data fork mapping
+structure and exit without changing anything.
+.TP 0.4i
+.B \-n
+Create this many copies of the first mapping.
+.RE
+.TP
 .B btdump [-a] [-i]
 If the cursor points to a btree node, dump the btree from that block downward.
 If instead the cursor points to an inode, dump the data fork block mapping btree if there is one.

[PATCH 2/8] xfs_repair: slab and bag structs need to track more than 2^32 items

[Darrick J. Wong]

From: Darrick J. Wong <djwong@djwong.org>

Currently, the xfs_slab data structure in xfs_repair is used to stage
incore reverse mapping and reference count records to build the ondisk
rmapbt and refcountbt during phase 5.

On a reflink filesystem, it's possible for there to be more than 2^32
forward mappings in an AG, which means that there could be more than
2^32 rmapbt records too.  Widen the size_t fields of xfs_slab to u64
accomodate this.

Similarly, the xfs_bag structure holds pointers to xfs_slab objects.
This abstraction tracks rmapbt records as we walk through the AG space
building refcount records.  It's possible for there to be more than 2^32
mappings to a piece of physical space, so we need to side the size_t
fields of xfs_bag to u64 as well.

In the next patch we'll fix all the users of these two structures; this
is merely the preparatory patch.

Signed-off-by: Darrick J. Wong <djwong@djwong.org>
---
 repair/slab.c |   36 ++++++++++++++++++------------------
 repair/slab.h |   36 +++++++++++++++++++-----------------
 2 files changed, 37 insertions(+), 35 deletions(-)


diff --git a/repair/slab.c b/repair/slab.c
index 165f97efd29..01bc4d426fe 100644
--- a/repair/slab.c
+++ b/repair/slab.c
@@ -41,18 +41,18 @@
 /* and cannot be larger than 128M */
 #define MAX_SLAB_SIZE		(128 * 1048576)
 struct xfs_slab_hdr {
-	size_t			sh_nr;
-	size_t			sh_inuse;	/* items in use */
+	uint32_t		sh_nr;
+	uint32_t		sh_inuse;	/* items in use */
 	struct xfs_slab_hdr	*sh_next;	/* next slab hdr */
 						/* objects follow */
 };
 
 struct xfs_slab {
-	size_t			s_item_sz;	/* item size */
-	size_t			s_nr_slabs;	/* # of slabs */
-	size_t			s_nr_items;	/* # of items */
+	uint64_t		s_nr_slabs;	/* # of slabs */
+	uint64_t		s_nr_items;	/* # of items */
 	struct xfs_slab_hdr	*s_first;	/* first slab header */
 	struct xfs_slab_hdr	*s_last;	/* last sh_next pointer */
+	size_t			s_item_sz;	/* item size */
 };
 
 /*
@@ -64,13 +64,13 @@ struct xfs_slab {
  */
 struct xfs_slab_hdr_cursor {
 	struct xfs_slab_hdr	*hdr;		/* a slab header */
-	size_t			loc;		/* where we are in the slab */
+	uint32_t		loc;		/* where we are in the slab */
 };
 
 typedef int (*xfs_slab_compare_fn)(const void *, const void *);
 
 struct xfs_slab_cursor {
-	size_t				nr;		/* # of per-slab cursors */
+	uint64_t			nr;		/* # of per-slab cursors */
 	struct xfs_slab			*slab;		/* pointer to the slab */
 	struct xfs_slab_hdr_cursor	*last_hcur;	/* last header we took from */
 	xfs_slab_compare_fn		compare_fn;	/* compare items */
@@ -83,8 +83,8 @@ struct xfs_slab_cursor {
  */
 #define MIN_BAG_SIZE	4096
 struct xfs_bag {
-	size_t			bg_nr;		/* number of pointers */
-	size_t			bg_inuse;	/* number of slots in use */
+	uint64_t		bg_nr;		/* number of pointers */
+	uint64_t		bg_inuse;	/* number of slots in use */
 	void			**bg_ptrs;	/* pointers */
 };
 #define BAG_END(bag)	(&(bag)->bg_ptrs[(bag)->bg_nr])
@@ -137,7 +137,7 @@ static void *
 slab_ptr(
 	struct xfs_slab		*slab,
 	struct xfs_slab_hdr	*hdr,
-	size_t			idx)
+	uint32_t		idx)
 {
 	char			*p;
 
@@ -155,12 +155,12 @@ slab_add(
 	struct xfs_slab		*slab,
 	void			*item)
 {
-	struct xfs_slab_hdr		*hdr;
+	struct xfs_slab_hdr	*hdr;
 	void			*p;
 
 	hdr = slab->s_last;
 	if (!hdr || hdr->sh_inuse == hdr->sh_nr) {
-		size_t n;
+		uint32_t	n;
 
 		n = (hdr ? hdr->sh_nr * 2 : MIN_SLAB_NR);
 		if (n * slab->s_item_sz > MAX_SLAB_SIZE)
@@ -308,7 +308,7 @@ peek_slab_cursor(
 	struct xfs_slab_hdr_cursor	*hcur;
 	void			*p = NULL;
 	void			*q;
-	size_t			i;
+	uint64_t		i;
 
 	cur->last_hcur = NULL;
 
@@ -370,7 +370,7 @@ pop_slab_cursor(
 /*
  * Return the number of items in the slab.
  */
-size_t
+uint64_t
 slab_count(
 	struct xfs_slab	*slab)
 {
@@ -429,7 +429,7 @@ bag_add(
 	p = &bag->bg_ptrs[bag->bg_inuse];
 	if (p == BAG_END(bag)) {
 		/* No free space, alloc more pointers */
-		size_t nr;
+		uint64_t	nr;
 
 		nr = bag->bg_nr * 2;
 		x = realloc(bag->bg_ptrs, nr * sizeof(void *));
@@ -450,7 +450,7 @@ bag_add(
 int
 bag_remove(
 	struct xfs_bag	*bag,
-	size_t		nr)
+	uint64_t	nr)
 {
 	ASSERT(nr < bag->bg_inuse);
 	memmove(&bag->bg_ptrs[nr], &bag->bg_ptrs[nr + 1],
@@ -462,7 +462,7 @@ bag_remove(
 /*
  * Return the number of items in a bag.
  */
-size_t
+uint64_t
 bag_count(
 	struct xfs_bag	*bag)
 {
@@ -475,7 +475,7 @@ bag_count(
 void *
 bag_item(
 	struct xfs_bag	*bag,
-	size_t		nr)
+	uint64_t	nr)
 {
 	if (nr >= bag->bg_inuse)
 		return NULL;
diff --git a/repair/slab.h b/repair/slab.h
index aab46ecf1f0..077b4582214 100644
--- a/repair/slab.h
+++ b/repair/slab.h
@@ -9,29 +9,31 @@
 struct xfs_slab;
 struct xfs_slab_cursor;
 
-extern int init_slab(struct xfs_slab **, size_t);
-extern void free_slab(struct xfs_slab **);
+int init_slab(struct xfs_slab **slabp, size_t item_sz);
+void free_slab(struct xfs_slab **slabp);
 
-extern int slab_add(struct xfs_slab *, void *);
-extern void qsort_slab(struct xfs_slab *, int (*)(const void *, const void *));
-extern size_t slab_count(struct xfs_slab *);
+int slab_add(struct xfs_slab *slab, void *item);
+void qsort_slab(struct xfs_slab *slab,
+		int (*compare)(const void *, const void *));
+uint64_t slab_count(struct xfs_slab *slab);
 
-extern int init_slab_cursor(struct xfs_slab *,
-	int (*)(const void *, const void *), struct xfs_slab_cursor **);
-extern void free_slab_cursor(struct xfs_slab_cursor **);
+int init_slab_cursor(struct xfs_slab *slab,
+		int (*compare)(const void *, const void *),
+		struct xfs_slab_cursor **curp);
+void free_slab_cursor(struct xfs_slab_cursor **curp);
 
-extern void *peek_slab_cursor(struct xfs_slab_cursor *);
-extern void advance_slab_cursor(struct xfs_slab_cursor *);
-extern void *pop_slab_cursor(struct xfs_slab_cursor *);
+void *peek_slab_cursor(struct xfs_slab_cursor *cur);
+void advance_slab_cursor(struct xfs_slab_cursor *cur);
+void *pop_slab_cursor(struct xfs_slab_cursor *cur);
 
 struct xfs_bag;
 
-extern int init_bag(struct xfs_bag **);
-extern void free_bag(struct xfs_bag **);
-extern int bag_add(struct xfs_bag *, void *);
-extern int bag_remove(struct xfs_bag *, size_t);
-extern size_t bag_count(struct xfs_bag *);
-extern void *bag_item(struct xfs_bag *, size_t);
+int init_bag(struct xfs_bag **bagp);
+void free_bag(struct xfs_bag **bagp);
+int bag_add(struct xfs_bag *bag, void *item);
+int bag_remove(struct xfs_bag *bag, uint64_t idx);
+uint64_t bag_count(struct xfs_bag *bag);
+void *bag_item(struct xfs_bag *bag, uint64_t idx);
 
 #define foreach_bag_ptr(bag, idx, ptr) \
 	for ((idx) = 0, (ptr) = bag_item((bag), (idx)); \

[PATCH 3/8] xfs_repair: support more than 2^32 rmapbt records per AG

[Darrick J. Wong]

From: Darrick J. Wong <djwong@djwong.org>

Now that the incore structures handle more than 2^32 records correctly,
fix the rmapbt generation code to handle that many records.  This fixes
the problem where an extremely large rmapbt cannot be rebuilt properly
because of integer truncation.

Signed-off-by: Darrick J. Wong <djwong@djwong.org>
---
 repair/rmap.c |    8 ++++----
 repair/rmap.h |    2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)


diff --git a/repair/rmap.c b/repair/rmap.c
index a2291c7b3b0..c908429c9bf 100644
--- a/repair/rmap.c
+++ b/repair/rmap.c
@@ -283,7 +283,7 @@ rmap_fold_raw_recs(
 {
 	struct xfs_slab_cursor	*cur = NULL;
 	struct xfs_rmap_irec	*prev, *rec;
-	size_t			old_sz;
+	uint64_t		old_sz;
 	int			error = 0;
 
 	old_sz = slab_count(ag_rmaps[agno].ar_rmaps);
@@ -690,7 +690,7 @@ mark_inode_rl(
 	struct xfs_rmap_irec	*rmap;
 	struct ino_tree_node	*irec;
 	int			off;
-	size_t			idx;
+	uint64_t		idx;
 	xfs_agino_t		ino;
 
 	if (bag_count(rmaps) < 2)
@@ -873,9 +873,9 @@ compute_refcounts(
 /*
  * Return the number of rmap objects for an AG.
  */
-size_t
+uint64_t
 rmap_record_count(
-	struct xfs_mount		*mp,
+	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno)
 {
 	return slab_count(ag_rmaps[agno].ar_rmaps);
diff --git a/repair/rmap.h b/repair/rmap.h
index 1dad2f5890a..b074e2e8786 100644
--- a/repair/rmap.h
+++ b/repair/rmap.h
@@ -26,7 +26,7 @@ extern bool rmaps_are_mergeable(struct xfs_rmap_irec *r1, struct xfs_rmap_irec *
 extern int rmap_add_fixed_ag_rec(struct xfs_mount *, xfs_agnumber_t);
 extern int rmap_store_ag_btree_rec(struct xfs_mount *, xfs_agnumber_t);
 
-extern size_t rmap_record_count(struct xfs_mount *, xfs_agnumber_t);
+uint64_t rmap_record_count(struct xfs_mount *mp, xfs_agnumber_t agno);
 extern int rmap_init_cursor(xfs_agnumber_t, struct xfs_slab_cursor **);
 extern void rmap_avoid_check(void);
 void rmaps_verify_btree(struct xfs_mount *mp, xfs_agnumber_t agno);

[PATCH 4/8] xfs_repair: support more than 2^32 owners per physical block

[Darrick J. Wong]

From: Darrick J. Wong <djwong@djwong.org>

Now that the incore structures handle more than 2^32 records correctly,
fix the refcountbt generation code to handle the case of that many rmap
records pointing to a piece of space in an AG.  This fixes the problem
where the refcountbt cannot be rebuilt properly because of integer
truncation if there are more than 4.3 billion owners of a piece of
space.

Signed-off-by: Darrick J. Wong <djwong@djwong.org>
---
 repair/rmap.c |   18 +++++++++---------
 repair/rmap.h |    2 +-
 2 files changed, 10 insertions(+), 10 deletions(-)


diff --git a/repair/rmap.c b/repair/rmap.c
index c908429c9bf..564e1cbf294 100644
--- a/repair/rmap.c
+++ b/repair/rmap.c
@@ -713,14 +713,13 @@ mark_inode_rl(
 /*
  * Emit a refcount object for refcntbt reconstruction during phase 5.
  */
-#define REFCOUNT_CLAMP(nr)	((nr) > MAXREFCOUNT ? MAXREFCOUNT : (nr))
 static void
 refcount_emit(
-	struct xfs_mount		*mp,
+	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno,
 	xfs_agblock_t		agbno,
 	xfs_extlen_t		len,
-	size_t			nr_rmaps)
+	uint64_t		nr_rmaps)
 {
 	struct xfs_refcount_irec	rlrec;
 	int			error;
@@ -733,7 +732,9 @@ refcount_emit(
 		agno, agbno, len, nr_rmaps);
 	rlrec.rc_startblock = agbno;
 	rlrec.rc_blockcount = len;
-	rlrec.rc_refcount = REFCOUNT_CLAMP(nr_rmaps);
+	if (nr_rmaps > MAXREFCOUNT)
+		nr_rmaps = MAXREFCOUNT;
+	rlrec.rc_refcount = nr_rmaps;
 	rlrec.rc_domain = XFS_REFC_DOMAIN_SHARED;
 
 	error = slab_add(rlslab, &rlrec);
@@ -741,7 +742,6 @@ refcount_emit(
 		do_error(
 _("Insufficient memory while recreating refcount tree."));
 }
-#undef REFCOUNT_CLAMP
 
 /*
  * Transform a pile of physical block mapping observations into refcount data
@@ -758,11 +758,11 @@ compute_refcounts(
 	struct xfs_slab_cursor	*rmaps_cur;
 	struct xfs_rmap_irec	*array_cur;
 	struct xfs_rmap_irec	*rmap;
+	uint64_t		n, idx;
+	uint64_t		old_stack_nr;
 	xfs_agblock_t		sbno;	/* first bno of this rmap set */
 	xfs_agblock_t		cbno;	/* first bno of this refcount set */
 	xfs_agblock_t		nbno;	/* next bno where rmap set changes */
-	size_t			n, idx;
-	size_t			old_stack_nr;
 	int			error;
 
 	if (!xfs_has_reflink(mp))
@@ -1312,9 +1312,9 @@ _("Unable to fix reflink flag on inode %"PRIu64".\n"),
 /*
  * Return the number of refcount objects for an AG.
  */
-size_t
+uint64_t
 refcount_record_count(
-	struct xfs_mount		*mp,
+	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno)
 {
 	return slab_count(ag_rmaps[agno].ar_refcount_items);
diff --git a/repair/rmap.h b/repair/rmap.h
index b074e2e8786..1bc8c127d0e 100644
--- a/repair/rmap.h
+++ b/repair/rmap.h
@@ -37,7 +37,7 @@ extern void rmap_high_key_from_rec(struct xfs_rmap_irec *rec,
 		struct xfs_rmap_irec *key);
 
 extern int compute_refcounts(struct xfs_mount *, xfs_agnumber_t);
-extern size_t refcount_record_count(struct xfs_mount *, xfs_agnumber_t);
+uint64_t refcount_record_count(struct xfs_mount *mp, xfs_agnumber_t agno);
 extern int init_refcount_cursor(xfs_agnumber_t, struct xfs_slab_cursor **);
 extern void refcount_avoid_check(void);
 void check_refcounts(struct xfs_mount *mp, xfs_agnumber_t agno);

[PATCH 5/8] xfs_repair: clean up lock resources

[Darrick J. Wong]

From: Darrick J. Wong <djwong@djwong.org>

When we free all the incore block mapping data, be sure to free the
locks too.

Signed-off-by: Darrick J. Wong <djwong@djwong.org>
---
 repair/incore.c |    9 +++++++++
 1 file changed, 9 insertions(+)


diff --git a/repair/incore.c b/repair/incore.c
index 2ed37a105ca..06edaf0d605 100644
--- a/repair/incore.c
+++ b/repair/incore.c
@@ -301,8 +301,17 @@ free_bmaps(xfs_mount_t *mp)
 {
 	xfs_agnumber_t i;
 
+	pthread_mutex_destroy(&rt_lock.lock);
+
+	for (i = 0; i < mp->m_sb.sb_agcount; i++)
+		pthread_mutex_destroy(&ag_locks[i].lock);
+
+	free(ag_locks);
+	ag_locks = NULL;
+
 	for (i = 0; i < mp->m_sb.sb_agcount; i++)
 		btree_destroy(ag_bmap[i]);
+
 	free(ag_bmap);
 	ag_bmap = NULL;
 

[PATCH 6/8] xfs_repair: constrain attr fork extent count

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Don't let the attr fork extent count exceed the maximum possible value.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 repair/dinode.c |    6 ++++++
 1 file changed, 6 insertions(+)


diff --git a/repair/dinode.c b/repair/dinode.c
index bd91ce14a36..a6a44b85424 100644
--- a/repair/dinode.c
+++ b/repair/dinode.c
@@ -2049,6 +2049,7 @@ process_inode_attr_fork(
 	xfs_ino_t		lino = XFS_AGINO_TO_INO(mp, agno, ino);
 	struct xfs_dinode	*dino = *dinop;
 	struct blkmap		*ablkmap = NULL;
+	xfs_extnum_t		max_nex;
 	int			repair = 0;
 	int			err;
 	int			try_rebuild = -1; /* don't know yet */
@@ -2070,6 +2071,11 @@ process_inode_attr_fork(
 	}
 
 	*anextents = xfs_dfork_attr_extents(dino);
+	max_nex = xfs_iext_max_nextents(
+			xfs_dinode_has_large_extent_counts(dino),
+			XFS_ATTR_FORK);
+	if (*anextents > max_nex)
+		*anextents = 1;
 	if (*anextents > be64_to_cpu(dino->di_nblocks))
 		*anextents = 1;
 

[PATCH 7/8] xfs_repair: don't create block maps for data files

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Repair only queries inode block maps for inode forks that map filesystem
metadata.  IOWs, it only uses it for directories, quota files, symlinks,
and extended attributes.  It doesn't use it for regular files or
realtime files, so exclude its use for these files to reduce processing
times for heavily fragmented regular files.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 repair/dinode.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)


diff --git a/repair/dinode.c b/repair/dinode.c
index a6a44b85424..f2961275cd1 100644
--- a/repair/dinode.c
+++ b/repair/dinode.c
@@ -1929,8 +1929,8 @@ process_inode_data_fork(
 	if (*nextents > be64_to_cpu(dino->di_nblocks))
 		*nextents = 1;
 
-
-	if (dino->di_format != XFS_DINODE_FMT_LOCAL && type != XR_INO_RTDATA)
+	if (dino->di_format != XFS_DINODE_FMT_LOCAL &&
+	    (type != XR_INO_RTDATA && type != XR_INO_DATA))
 		*dblkmap = blkmap_alloc(*nextents, XFS_DATA_FORK);
 	*nextents = 0;
 

[PATCH 8/8] xfs_repair: support more than INT_MAX block maps

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Now that it's possible to have more than INT_MAX block mappings attached
to a file fork, expand the counters used by this data structure so that
it can support all possible block mappings.

Note that in practice we're still never going to exceed 4 billion
extents because the previous patch switched off the block mappings for
regular files.  This is still twice as much as memory as previous, but
it's not totally unconstrained.  Hopefully few people bloat the xattr
structures that large.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 repair/bmap.c   |   26 ++++++++++++++------------
 repair/bmap.h   |    9 ++++-----
 repair/dinode.c |    2 +-
 repair/dir2.c   |    2 +-
 4 files changed, 20 insertions(+), 19 deletions(-)


diff --git a/repair/bmap.c b/repair/bmap.c
index cd1a8b07b30..9ae28686107 100644
--- a/repair/bmap.c
+++ b/repair/bmap.c
@@ -34,8 +34,9 @@ blkmap_alloc(
 
 	if (nex < 1)
 		nex = 1;
+	nex = min(nex, XFS_MAX_EXTCNT_DATA_FORK_LARGE);
 
-#if (BITS_PER_LONG == 32)	/* on 64-bit platforms this is never true */
+#ifdef BLKMAP_NEXTS_MAX
 	if (nex > BLKMAP_NEXTS_MAX) {
 		do_warn(
 	_("Number of extents requested in blkmap_alloc (%llu) overflows 32 bits.\n"
@@ -115,7 +116,7 @@ blkmap_get(
 	xfs_fileoff_t	o)
 {
 	bmap_ext_t	*ext = blkmap->exts;
-	int		i;
+	xfs_extnum_t	i;
 
 	for (i = 0; i < blkmap->nexts; i++, ext++) {
 		if (o >= ext->startoff && o < ext->startoff + ext->blockcount)
@@ -137,7 +138,7 @@ blkmap_getn(
 {
 	bmap_ext_t	*bmp = NULL;
 	bmap_ext_t	*ext;
-	int		i;
+	xfs_extnum_t	i;
 	int		nex;
 
 	if (nb == 1) {
@@ -233,7 +234,7 @@ xfs_fileoff_t
 blkmap_next_off(
 	blkmap_t	*blkmap,
 	xfs_fileoff_t	o,
-	int		*t)
+	xfs_extnum_t	*t)
 {
 	bmap_ext_t	*ext;
 
@@ -263,7 +264,7 @@ blkmap_grow(
 {
 	pthread_key_t	key = dblkmap_key;
 	blkmap_t	*new_blkmap;
-	int		new_naexts;
+	xfs_extnum_t	new_naexts;
 
 	/* reduce the number of reallocations for large files */
 	if (blkmap->naexts < 1000)
@@ -278,20 +279,21 @@ blkmap_grow(
 		ASSERT(pthread_getspecific(key) == blkmap);
 	}
 
-#if (BITS_PER_LONG == 32)	/* on 64-bit platforms this is never true */
+#ifdef BLKMAP_NEXTS_MAX
 	if (new_naexts > BLKMAP_NEXTS_MAX) {
 		do_error(
-	_("Number of extents requested in blkmap_grow (%d) overflows 32 bits.\n"
+	_("Number of extents requested in blkmap_grow (%llu) overflows 32 bits.\n"
 	  "You need a 64 bit system to repair this filesystem.\n"),
-			new_naexts);
+			(unsigned long long)new_naexts);
 		return NULL;
 	}
 #endif
-	if (new_naexts <= 0) {
+	if (new_naexts > XFS_MAX_EXTCNT_DATA_FORK_LARGE) {
 		do_error(
-	_("Number of extents requested in blkmap_grow (%d) overflowed the\n"
-	  "maximum number of supported extents (%d).\n"),
-			new_naexts, BLKMAP_NEXTS_MAX);
+	_("Number of extents requested in blkmap_grow (%llu) overflowed the\n"
+	  "maximum number of supported extents (%llu).\n"),
+			(unsigned long long)new_naexts,
+			(unsigned long long)XFS_MAX_EXTCNT_DATA_FORK_LARGE);
 		return NULL;
 	}
 
diff --git a/repair/bmap.h b/repair/bmap.h
index 4b588df8c86..3d6be94441c 100644
--- a/repair/bmap.h
+++ b/repair/bmap.h
@@ -20,8 +20,8 @@ typedef struct bmap_ext {
  * Block map.
  */
 typedef	struct blkmap {
-	int		naexts;
-	int		nexts;
+	xfs_extnum_t	naexts;
+	xfs_extnum_t	nexts;
 	bmap_ext_t	exts[1];
 } blkmap_t;
 
@@ -37,8 +37,6 @@ typedef	struct blkmap {
  */
 #if BITS_PER_LONG == 32
 #define BLKMAP_NEXTS_MAX	((INT_MAX / sizeof(bmap_ext_t)) - 1)
-#else
-#define BLKMAP_NEXTS_MAX	INT_MAX
 #endif
 
 extern pthread_key_t dblkmap_key;
@@ -56,6 +54,7 @@ int		blkmap_getn(blkmap_t *blkmap, xfs_fileoff_t o,
 			    xfs_filblks_t nb, bmap_ext_t **bmpp,
 			    bmap_ext_t *bmpp_single);
 xfs_fileoff_t	blkmap_last_off(blkmap_t *blkmap);
-xfs_fileoff_t	blkmap_next_off(blkmap_t *blkmap, xfs_fileoff_t o, int *t);
+xfs_fileoff_t	blkmap_next_off(blkmap_t *blkmap, xfs_fileoff_t o,
+				xfs_extnum_t *t);
 
 #endif /* _XFS_REPAIR_BMAP_H */
diff --git a/repair/dinode.c b/repair/dinode.c
index f2961275cd1..629440fe6de 100644
--- a/repair/dinode.c
+++ b/repair/dinode.c
@@ -1136,7 +1136,7 @@ process_quota_inode(
 	xfs_dqid_t		dqid;
 	xfs_fileoff_t		qbno;
 	int			i;
-	int			t = 0;
+	xfs_extnum_t		t = 0;
 	int			error;
 
 	switch (ino_type) {
diff --git a/repair/dir2.c b/repair/dir2.c
index 022b61b885f..e46ae9ae46f 100644
--- a/repair/dir2.c
+++ b/repair/dir2.c
@@ -1327,7 +1327,7 @@ process_leaf_node_dir2(
 	int			i;
 	xfs_fileoff_t		ndbno;
 	int			nex;
-	int			t;
+	xfs_extnum_t		t;
 	bmap_ext_t		lbmp;
 	int			dirty = 0;
 

[PATCH 1/3] xfs: report health of inode link counts

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Report on the health of the inode link counts.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_fs.h     |    1 +
 libxfs/xfs_health.h |    4 +++-
 spaceman/health.c   |    4 ++++
 3 files changed, 8 insertions(+), 1 deletion(-)


diff --git a/libxfs/xfs_fs.h b/libxfs/xfs_fs.h
index 07acbed9235..f10d0aa0e33 100644
--- a/libxfs/xfs_fs.h
+++ b/libxfs/xfs_fs.h
@@ -196,6 +196,7 @@ struct xfs_fsop_geom {
 #define XFS_FSOP_GEOM_SICK_RT_BITMAP	(1 << 4)  /* realtime bitmap */
 #define XFS_FSOP_GEOM_SICK_RT_SUMMARY	(1 << 5)  /* realtime summary */
 #define XFS_FSOP_GEOM_SICK_QUOTACHECK	(1 << 6)  /* quota counts */
+#define XFS_FSOP_GEOM_SICK_NLINKS	(1 << 7)  /* inode link counts */
 
 /* Output for XFS_FS_COUNTS */
 typedef struct xfs_fsop_counts {
diff --git a/libxfs/xfs_health.h b/libxfs/xfs_health.h
index 5626e53b3f0..2bfe2dc404a 100644
--- a/libxfs/xfs_health.h
+++ b/libxfs/xfs_health.h
@@ -42,6 +42,7 @@ struct xfs_fsop_geom;
 #define XFS_SICK_FS_GQUOTA	(1 << 2)  /* group quota */
 #define XFS_SICK_FS_PQUOTA	(1 << 3)  /* project quota */
 #define XFS_SICK_FS_QUOTACHECK	(1 << 4)  /* quota counts */
+#define XFS_SICK_FS_NLINKS	(1 << 5)  /* inode link counts */
 
 /* Observable health issues for realtime volume metadata. */
 #define XFS_SICK_RT_BITMAP	(1 << 0)  /* realtime bitmap */
@@ -79,7 +80,8 @@ struct xfs_fsop_geom;
 				 XFS_SICK_FS_UQUOTA | \
 				 XFS_SICK_FS_GQUOTA | \
 				 XFS_SICK_FS_PQUOTA | \
-				 XFS_SICK_FS_QUOTACHECK)
+				 XFS_SICK_FS_QUOTACHECK | \
+				 XFS_SICK_FS_NLINKS)
 
 #define XFS_SICK_RT_PRIMARY	(XFS_SICK_RT_BITMAP | \
 				 XFS_SICK_RT_SUMMARY)
diff --git a/spaceman/health.c b/spaceman/health.c
index 3318f9d1a7f..88b12c0b0ea 100644
--- a/spaceman/health.c
+++ b/spaceman/health.c
@@ -76,6 +76,10 @@ static const struct flag_map fs_flags[] = {
 		.mask = XFS_FSOP_GEOM_SICK_QUOTACHECK,
 		.descr = "quota counts",
 	},
+	{
+		.mask = XFS_FSOP_GEOM_SICK_NLINKS,
+		.descr = "inode link counts",
+	},
 	{0},
 };
 

[PATCH 2/3] xfs: teach scrub to check file nlinks

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create the necessary scrub code to walk the filesystem's directory tree
so that we can compute file link counts.  Similar to quotacheck, we
create an incore shadow array of link count information and then we walk
the filesystem a second time to compare the link counts.  We need live
updates to keep the information up to date during the lengthy scan, so
this scrubber remains disabled until the next patch.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libfrog/scrub.c                     |    5 +++++
 libxfs/xfs_fs.h                     |    3 ++-
 man/man2/ioctl_xfs_scrub_metadata.2 |    4 ++++
 3 files changed, 11 insertions(+), 1 deletion(-)


diff --git a/libfrog/scrub.c b/libfrog/scrub.c
index 53c47bc2b5d..b6b8ae042c4 100644
--- a/libfrog/scrub.c
+++ b/libfrog/scrub.c
@@ -139,6 +139,11 @@ const struct xfrog_scrub_descr xfrog_scrubbers[XFS_SCRUB_TYPE_NR] = {
 		.descr	= "quota counters",
 		.group	= XFROG_SCRUB_GROUP_ISCAN,
 	},
+	[XFS_SCRUB_TYPE_NLINKS] = {
+		.name	= "nlinks",
+		.descr	= "inode link counts",
+		.group	= XFROG_SCRUB_GROUP_ISCAN,
+	},
 };
 
 /* Invoke the scrub ioctl.  Returns zero or negative error code. */
diff --git a/libxfs/xfs_fs.h b/libxfs/xfs_fs.h
index f10d0aa0e33..515cd27d3b3 100644
--- a/libxfs/xfs_fs.h
+++ b/libxfs/xfs_fs.h
@@ -712,9 +712,10 @@ struct xfs_scrub_metadata {
 #define XFS_SCRUB_TYPE_PQUOTA	23	/* project quotas */
 #define XFS_SCRUB_TYPE_FSCOUNTERS 24	/* fs summary counters */
 #define XFS_SCRUB_TYPE_QUOTACHECK 25	/* quota counters */
+#define XFS_SCRUB_TYPE_NLINKS	26	/* inode link counts */
 
 /* Number of scrub subcommands. */
-#define XFS_SCRUB_TYPE_NR	26
+#define XFS_SCRUB_TYPE_NR	27
 
 /* i: Repair this metadata. */
 #define XFS_SCRUB_IFLAG_REPAIR		(1u << 0)
diff --git a/man/man2/ioctl_xfs_scrub_metadata.2 b/man/man2/ioctl_xfs_scrub_metadata.2
index 046e3e3657b..8e8bb72fb3b 100644
--- a/man/man2/ioctl_xfs_scrub_metadata.2
+++ b/man/man2/ioctl_xfs_scrub_metadata.2
@@ -164,6 +164,10 @@ Examine all user, group, or project quota records for corruption.
 .B XFS_SCRUB_TYPE_FSCOUNTERS
 Examine all filesystem summary counters (free blocks, inode count, free inode
 count) for errors.
+
+.TP
+.B XFS_SCRUB_TYPE_NLINKS
+Scan all inodes in the filesystem to verify each file's link count.
 .RE
 
 .PD 1

[PATCH 3/3] xfs_scrub: use multiple threads to run in-kernel metadata scrubs that scan inodes

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Instead of running the inode link count and quotacheck scanners in
serial, run them in parallel, with a slight delay to stagger the work to
reduce inode resource contention.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase5.c |  150 ++++++++++++++++++++++++++++++++++++++++++++++++++------
 scrub/scrub.c  |   18 +++----
 scrub/scrub.h  |    1 
 3 files changed, 145 insertions(+), 24 deletions(-)


diff --git a/scrub/phase5.c b/scrub/phase5.c
index 0a91e4f0640..b4c635d3452 100644
--- a/scrub/phase5.c
+++ b/scrub/phase5.c
@@ -384,26 +384,146 @@ check_fs_label(
 	return error;
 }
 
-/* Check directory connectivity. */
-int
-phase5_func(
-	struct scrub_ctx	*ctx)
-{
+typedef int (*fs_scan_item_fn)(struct scrub_ctx *, struct action_list *);
+
+struct fs_scan_item {
 	struct action_list	alist;
-	bool			aborted = false;
+	bool			*abortedp;
+	fs_scan_item_fn		scrub_fn;
+};
+
+/* Run one full-fs scan scrubber in this thread. */
+static void
+fs_scan_worker(
+	struct workqueue	*wq,
+	xfs_agnumber_t		nr,
+	void			*arg)
+{
+	struct timespec		tv;
+	struct fs_scan_item	*item = arg;
+	struct scrub_ctx	*ctx = wq->wq_ctx;
 	int			ret;
 
 	/*
-	 * Check and fix anything that requires a full inode scan.  We do this
-	 * after we've checked all inodes and repaired anything that could get
-	 * in the way of a scan.
+	 * Delay each successive fs scan by a second so that the threads are
+	 * less likely to contend on the inobt and inode buffers.
 	 */
-	action_list_init(&alist);
-	ret = scrub_iscan_metadata(ctx, &alist);
-	if (ret)
-		return ret;
-	ret = action_list_process(ctx, ctx->mnt.fd, &alist,
+	if (nr) {
+		tv.tv_sec = nr;
+		tv.tv_nsec = 0;
+		nanosleep(&tv, NULL);
+	}
+
+	ret = item->scrub_fn(ctx, &item->alist);
+	if (ret) {
+		str_liberror(ctx, ret, _("checking fs scan metadata"));
+		*item->abortedp = true;
+		goto out;
+	}
+
+	ret = action_list_process(ctx, ctx->mnt.fd, &item->alist,
 			ALP_COMPLAIN_IF_UNFIXED | ALP_NOPROGRESS);
+	if (ret) {
+		str_liberror(ctx, ret, _("repairing fs scan metadata"));
+		*item->abortedp = true;
+		goto out;
+	}
+
+out:
+	free(item);
+	return;
+}
+
+/* Queue one full-fs scan scrubber. */
+static int
+queue_fs_scan(
+	struct workqueue	*wq,
+	bool			*abortedp,
+	xfs_agnumber_t		nr,
+	fs_scan_item_fn		scrub_fn)
+{
+	struct fs_scan_item	*item;
+	struct scrub_ctx	*ctx = wq->wq_ctx;
+	int			ret;
+
+	item = malloc(sizeof(struct fs_scan_item));
+	if (!item) {
+		ret = ENOMEM;
+		str_liberror(ctx, ret, _("setting up fs scan"));
+		return ret;
+	}
+	action_list_init(&item->alist);
+	item->scrub_fn = scrub_fn;
+	item->abortedp = abortedp;
+
+	ret = -workqueue_add(wq, fs_scan_worker, nr, item);
+	if (ret)
+		str_liberror(ctx, ret, _("queuing fs scan work"));
+
+	return ret;
+}
+
+/* Run multiple full-fs scan scrubbers at the same time. */
+static int
+run_kernel_fs_scan_scrubbers(
+	struct scrub_ctx	*ctx)
+{
+	struct workqueue	wq_fs_scan;
+	unsigned int		nr_threads = scrub_nproc_workqueue(ctx);
+	xfs_agnumber_t		nr = 0;
+	bool			aborted = false;
+	int			ret, ret2;
+
+	ret = -workqueue_create(&wq_fs_scan, (struct xfs_mount *)ctx,
+			nr_threads);
+	if (ret) {
+		str_liberror(ctx, ret, _("setting up fs scan workqueue"));
+		return ret;
+	}
+
+	/*
+	 * The nlinks scanner is much faster than quotacheck because it only
+	 * walks directories, so we start it first.
+	 */
+	ret = queue_fs_scan(&wq_fs_scan, &aborted, nr, scrub_nlinks);
+	if (ret)
+		goto wait;
+
+	if (nr_threads > 1)
+		nr++;
+
+	ret = queue_fs_scan(&wq_fs_scan, &aborted, nr, scrub_quotacheck);
+	if (ret)
+		goto wait;
+
+wait:
+	ret2 = -workqueue_terminate(&wq_fs_scan);
+	if (ret2) {
+		str_liberror(ctx, ret2, _("joining fs scan workqueue"));
+		if (!ret)
+			ret = ret2;
+	}
+	if (aborted && !ret)
+		ret = ECANCELED;
+
+	workqueue_destroy(&wq_fs_scan);
+	return ret;
+}
+
+/* Check directory connectivity. */
+int
+phase5_func(
+	struct scrub_ctx	*ctx)
+{
+	bool			aborted = false;
+	int			ret;
+
+	/*
+	 * Check and fix anything that requires a full filesystem scan.  We do
+	 * this after we've checked all inodes and repaired anything that could
+	 * get in the way of a scan.
+	 */
+	ret = run_kernel_fs_scan_scrubbers(ctx);
 	if (ret)
 		return ret;
 
@@ -436,7 +556,7 @@ phase5_estimate(
 	int			*rshift)
 {
 	*items = scrub_estimate_iscan_work(ctx);
-	*nr_threads = scrub_nproc(ctx);
+	*nr_threads = scrub_nproc(ctx) * 2;
 	*rshift = 0;
 	return 0;
 }
diff --git a/scrub/scrub.c b/scrub/scrub.c
index a22633a8115..b7ec54c16a4 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -422,15 +422,6 @@ scrub_summary_metadata(
 	return scrub_group(ctx, XFROG_SCRUB_GROUP_SUMMARY, 0, alist);
 }
 
-/* Scrub all metadata requiring a full inode scan. */
-int
-scrub_iscan_metadata(
-	struct scrub_ctx		*ctx,
-	struct action_list		*alist)
-{
-	return scrub_group(ctx, XFROG_SCRUB_GROUP_ISCAN, 0, alist);
-}
-
 /* Scrub /only/ the superblock summary counters. */
 int
 scrub_fs_counters(
@@ -449,6 +440,15 @@ scrub_quotacheck(
 	return scrub_meta_type(ctx, XFS_SCRUB_TYPE_QUOTACHECK, 0, alist);
 }
 
+/* Scrub /only/ the file link counters. */
+int
+scrub_nlinks(
+	struct scrub_ctx		*ctx,
+	struct action_list		*alist)
+{
+	return scrub_meta_type(ctx, XFS_SCRUB_TYPE_NLINKS, 0, alist);
+}
+
 /* How many items do we have to check? */
 unsigned int
 scrub_estimate_ag_work(
diff --git a/scrub/scrub.h b/scrub/scrub.h
index 927f86de9ec..5e3f40bf1f4 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -28,6 +28,7 @@ int scrub_iscan_metadata(struct scrub_ctx *ctx, struct action_list *alist);
 int scrub_summary_metadata(struct scrub_ctx *ctx, struct action_list *alist);
 int scrub_fs_counters(struct scrub_ctx *ctx, struct action_list *alist);
 int scrub_quotacheck(struct scrub_ctx *ctx, struct action_list *alist);
+int scrub_nlinks(struct scrub_ctx *ctx, struct action_list *alist);
 
 bool can_scrub_fs_metadata(struct scrub_ctx *ctx);
 bool can_scrub_inode(struct scrub_ctx *ctx);

[PATCH 1/9] xfs: separate the marking of sick and checked metadata

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Split the setting of the sick and checked masks into separate functions
as part of preparing to add the ability for regular runtime fs code
(i.e. not scrub) to mark metadata structures sick when corruptions are
found.  Improve the documentation of libxfs' requirements for helper
behavior.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_health.h |   16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)


diff --git a/libxfs/xfs_health.h b/libxfs/xfs_health.h
index 2bfe2dc404a..2b40fe81657 100644
--- a/libxfs/xfs_health.h
+++ b/libxfs/xfs_health.h
@@ -111,24 +111,38 @@ struct xfs_fsop_geom;
 				 XFS_SICK_INO_DIR_ZAPPED | \
 				 XFS_SICK_INO_SYMLINK_ZAPPED)
 
-/* These functions must be provided by the xfs implementation. */
+/*
+ * These functions must be provided by the xfs implementation.  Function
+ * behavior with respect to the first argument should be as follows:
+ *
+ * xfs_*_mark_sick:    set the sick flags and do not set checked flags.
+ * xfs_*_mark_checked: set the checked flags.
+ * xfs_*_mark_healthy: clear the sick flags and set the checked flags.
+ *
+ * xfs_*_measure_sickness: return the sick and check status in the provided
+ * out parameters.
+ */
 
 void xfs_fs_mark_sick(struct xfs_mount *mp, unsigned int mask);
+void xfs_fs_mark_checked(struct xfs_mount *mp, unsigned int mask);
 void xfs_fs_mark_healthy(struct xfs_mount *mp, unsigned int mask);
 void xfs_fs_measure_sickness(struct xfs_mount *mp, unsigned int *sick,
 		unsigned int *checked);
 
 void xfs_rt_mark_sick(struct xfs_mount *mp, unsigned int mask);
+void xfs_rt_mark_checked(struct xfs_mount *mp, unsigned int mask);
 void xfs_rt_mark_healthy(struct xfs_mount *mp, unsigned int mask);
 void xfs_rt_measure_sickness(struct xfs_mount *mp, unsigned int *sick,
 		unsigned int *checked);
 
 void xfs_ag_mark_sick(struct xfs_perag *pag, unsigned int mask);
+void xfs_ag_mark_checked(struct xfs_perag *pag, unsigned int mask);
 void xfs_ag_mark_healthy(struct xfs_perag *pag, unsigned int mask);
 void xfs_ag_measure_sickness(struct xfs_perag *pag, unsigned int *sick,
 		unsigned int *checked);
 
 void xfs_inode_mark_sick(struct xfs_inode *ip, unsigned int mask);
+void xfs_inode_mark_checked(struct xfs_inode *ip, unsigned int mask);
 void xfs_inode_mark_healthy(struct xfs_inode *ip, unsigned int mask);
 void xfs_inode_measure_sickness(struct xfs_inode *ip, unsigned int *sick,
 		unsigned int *checked);

[PATCH 2/9] xfs: report fs corruption errors to the health tracking system

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Whenever we encounter corrupt fs metadata, we should report that to the
health monitoring system for later reporting.  A convenient program for
identifying places to insert xfs_*_mark_sick calls is as follows:

#!/bin/bash

# Detect missing calls to xfs_*_mark_sick

filter=cat
tty -s && filter=less

git grep -B3 EFSCORRUPTED fs/xfs/*.[ch] fs/xfs/libxfs/*.[ch] fs/xfs/scrub/*.[ch] | awk '
BEGIN {
	ignore = 0;
	lineno = 0;
	delete lines;
}
{
	if ($0 == "--") {
		if (!ignore) {
			for (i = 0; i < lineno; i++) {
				print(lines[i]);
			}
			printf("--\n");
		}
		delete lines;
		lineno = 0;
		ignore = 0;
	} else if ($0 ~ /mark_sick/) {
		ignore = 1;
	} else if ($0 ~ /if .fa/) {
		ignore = 1;
	} else if ($0 ~ /failaddr/) {
		ignore = 1;
	} else if ($0 ~ /_verifier_error/) {
		ignore = 1;
	} else if ($0 ~ /^ \* .*EFSCORRUPTED/) {
		ignore = 1;
	} else if ($0 ~ /== -EFSCORRUPTED/) {
		ignore = 1;
	} else if ($0 ~ /!= -EFSCORRUPTED/) {
		ignore = 1;
	} else {
		lines[lineno++] = $0;
	}
}
' | $filter

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/util.c   |    1 +
 libxfs/xfs_ag.c |    1 +
 2 files changed, 2 insertions(+)


diff --git a/libxfs/util.c b/libxfs/util.c
index e01edf0202d..931cb78eaef 100644
--- a/libxfs/util.c
+++ b/libxfs/util.c
@@ -728,3 +728,4 @@ xfs_fs_mark_healthy(
 }
 
 void xfs_ag_geom_health(struct xfs_perag *pag, struct xfs_ag_geometry *ageo) { }
+void xfs_fs_mark_sick(struct xfs_mount *mp, unsigned int mask) { }
diff --git a/libxfs/xfs_ag.c b/libxfs/xfs_ag.c
index bdb8a08bbea..9e638413df4 100644
--- a/libxfs/xfs_ag.c
+++ b/libxfs/xfs_ag.c
@@ -215,6 +215,7 @@ xfs_initialize_perag_data(
 	 */
 	if (fdblocks > sbp->sb_dblocks || ifree > ialloc) {
 		xfs_alert(mp, "AGF corruption. Please run xfs_repair.");
+		xfs_fs_mark_sick(mp, XFS_SICK_FS_COUNTERS);
 		error = -EFSCORRUPTED;
 		goto out;
 	}

[PATCH 3/9] xfs: report ag header corruption errors to the health tracking system

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Whenever we encounter a corrupt AG header, we should report that to the
health monitoring system for later reporting.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/util.c       |    3 +++
 libxfs/xfs_alloc.c  |    6 ++++++
 libxfs/xfs_health.h |   13 ++++++++++---
 libxfs/xfs_ialloc.c |    3 +++
 libxfs/xfs_sb.c     |    2 ++
 5 files changed, 24 insertions(+), 3 deletions(-)


diff --git a/libxfs/util.c b/libxfs/util.c
index 931cb78eaef..b2d4356fd41 100644
--- a/libxfs/util.c
+++ b/libxfs/util.c
@@ -729,3 +729,6 @@ xfs_fs_mark_healthy(
 
 void xfs_ag_geom_health(struct xfs_perag *pag, struct xfs_ag_geometry *ageo) { }
 void xfs_fs_mark_sick(struct xfs_mount *mp, unsigned int mask) { }
+void xfs_agno_mark_sick(struct xfs_mount *mp, xfs_agnumber_t agno,
+		unsigned int mask) { }
+void xfs_ag_mark_sick(struct xfs_perag *pag, unsigned int mask) { }
diff --git a/libxfs/xfs_alloc.c b/libxfs/xfs_alloc.c
index 352efbeca9f..1894a091380 100644
--- a/libxfs/xfs_alloc.c
+++ b/libxfs/xfs_alloc.c
@@ -22,6 +22,7 @@
 #include "xfs_ag.h"
 #include "xfs_ag_resv.h"
 #include "xfs_bmap.h"
+#include "xfs_health.h"
 
 struct kmem_cache	*xfs_extfree_item_cache;
 
@@ -751,6 +752,8 @@ xfs_alloc_read_agfl(
 			mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGFL_DADDR(mp)),
 			XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_agfl_buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL);
 	if (error)
 		return error;
 	xfs_buf_set_ref(bp, XFS_AGFL_REF);
@@ -772,6 +775,7 @@ xfs_alloc_update_counters(
 	if (unlikely(be32_to_cpu(agf->agf_freeblks) >
 		     be32_to_cpu(agf->agf_length))) {
 		xfs_buf_mark_corrupt(agbp);
+		xfs_ag_mark_sick(agbp->b_pag, XFS_SICK_AG_AGF);
 		return -EFSCORRUPTED;
 	}
 
@@ -3264,6 +3268,8 @@ xfs_read_agf(
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGF_DADDR(mp)),
 			XFS_FSS_TO_BB(mp, 1), flags, agfbpp, &xfs_agf_buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGF);
 	if (error)
 		return error;
 
diff --git a/libxfs/xfs_health.h b/libxfs/xfs_health.h
index 2b40fe81657..cd7a1370a1e 100644
--- a/libxfs/xfs_health.h
+++ b/libxfs/xfs_health.h
@@ -26,9 +26,11 @@
  * and the "sick" field tells us if that piece was found to need repairs.
  * Therefore we can conclude that for a given sick flag value:
  *
- *  - checked && sick  => metadata needs repair
- *  - checked && !sick => metadata is ok
- *  - !checked         => has not been examined since mount
+ *  - checked && sick   => metadata needs repair
+ *  - checked && !sick  => metadata is ok
+ *  - !checked && sick  => errors have been observed during normal operation,
+ *                         but the metadata has not been checked thoroughly
+ *  - !checked && !sick => has not been examined since mount
  */
 
 struct xfs_mount;
@@ -135,6 +137,8 @@ void xfs_rt_mark_healthy(struct xfs_mount *mp, unsigned int mask);
 void xfs_rt_measure_sickness(struct xfs_mount *mp, unsigned int *sick,
 		unsigned int *checked);
 
+void xfs_agno_mark_sick(struct xfs_mount *mp, xfs_agnumber_t agno,
+		unsigned int mask);
 void xfs_ag_mark_sick(struct xfs_perag *pag, unsigned int mask);
 void xfs_ag_mark_checked(struct xfs_perag *pag, unsigned int mask);
 void xfs_ag_mark_healthy(struct xfs_perag *pag, unsigned int mask);
@@ -215,4 +219,7 @@ void xfs_fsop_geom_health(struct xfs_mount *mp, struct xfs_fsop_geom *geo);
 void xfs_ag_geom_health(struct xfs_perag *pag, struct xfs_ag_geometry *ageo);
 void xfs_bulkstat_health(struct xfs_inode *ip, struct xfs_bulkstat *bs);
 
+#define xfs_metadata_is_sick(error) \
+	(unlikely((error) == -EFSCORRUPTED || (error) == -EFSBADCRC))
+
 #endif	/* __XFS_HEALTH_H__ */
diff --git a/libxfs/xfs_ialloc.c b/libxfs/xfs_ialloc.c
index 5ff09c8c943..c801250a33b 100644
--- a/libxfs/xfs_ialloc.c
+++ b/libxfs/xfs_ialloc.c
@@ -22,6 +22,7 @@
 #include "xfs_trace.h"
 #include "xfs_rmap.h"
 #include "xfs_ag.h"
+#include "xfs_health.h"
 
 /*
  * Lookup a record by ino in the btree given by cur.
@@ -2599,6 +2600,8 @@ xfs_read_agi(
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGI_DADDR(mp)),
 			XFS_FSS_TO_BB(mp, 1), 0, agibpp, &xfs_agi_buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
 	if (error)
 		return error;
 	if (tp)
diff --git a/libxfs/xfs_sb.c b/libxfs/xfs_sb.c
index 7a72d5a1791..30a6bc07d88 100644
--- a/libxfs/xfs_sb.c
+++ b/libxfs/xfs_sb.c
@@ -1288,6 +1288,8 @@ xfs_sb_read_secondary(
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
 			XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_sb_buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_agno_mark_sick(mp, agno, XFS_SICK_AG_SB);
 	if (error)
 		return error;
 	xfs_buf_set_ref(bp, XFS_SSB_REF);

[PATCH 4/9] xfs: report block map corruption errors to the health tracking system

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Whenever we encounter a corrupt block mapping, we should report that to
the health monitoring system for later reporting.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/util.c       |    1 +
 libxfs/xfs_bmap.c   |   35 +++++++++++++++++++++++++++++------
 libxfs/xfs_health.h |    1 +
 3 files changed, 31 insertions(+), 6 deletions(-)


diff --git a/libxfs/util.c b/libxfs/util.c
index b2d4356fd41..9c6a4a2c457 100644
--- a/libxfs/util.c
+++ b/libxfs/util.c
@@ -732,3 +732,4 @@ void xfs_fs_mark_sick(struct xfs_mount *mp, unsigned int mask) { }
 void xfs_agno_mark_sick(struct xfs_mount *mp, xfs_agnumber_t agno,
 		unsigned int mask) { }
 void xfs_ag_mark_sick(struct xfs_perag *pag, unsigned int mask) { }
+void xfs_bmap_mark_sick(struct xfs_inode *ip, int whichfork) { }
diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index 3520235b58a..ee11d89d813 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -30,6 +30,7 @@
 #include "xfs_ag_resv.h"
 #include "xfs_refcount.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_health.h"
 
 struct kmem_cache		*xfs_bmap_intent_cache;
 
@@ -954,6 +955,7 @@ xfs_bmap_add_attrfork_local(
 
 	/* should only be called for types that support local format data */
 	ASSERT(0);
+	xfs_bmap_mark_sick(ip, XFS_ATTR_FORK);
 	return -EFSCORRUPTED;
 }
 
@@ -1137,6 +1139,7 @@ xfs_iread_bmbt_block(
 				(unsigned long long)ip->i_ino);
 		xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, block,
 				sizeof(*block), __this_address);
+		xfs_bmap_mark_sick(ip, whichfork);
 		return -EFSCORRUPTED;
 	}
 
@@ -1152,6 +1155,7 @@ xfs_iread_bmbt_block(
 			xfs_inode_verifier_error(ip, -EFSCORRUPTED,
 					"xfs_iread_extents(2)", frp,
 					sizeof(*frp), fa);
+			xfs_bmap_mark_sick(ip, whichfork);
 			return xfs_bmap_complain_bad_rec(ip, whichfork, fa,
 					&new);
 		}
@@ -1207,6 +1211,8 @@ xfs_iread_extents(
 	smp_store_release(&ifp->if_needextents, 0);
 	return 0;
 out:
+	if (xfs_metadata_is_sick(error))
+		xfs_bmap_mark_sick(ip, whichfork);
 	xfs_iext_destroy(ifp);
 	return error;
 }
@@ -1286,6 +1292,7 @@ xfs_bmap_last_before(
 		break;
 	default:
 		ASSERT(0);
+		xfs_bmap_mark_sick(ip, whichfork);
 		return -EFSCORRUPTED;
 	}
 
@@ -3879,12 +3886,16 @@ xfs_bmapi_read(
 	ASSERT(!(flags & ~(XFS_BMAPI_ATTRFORK | XFS_BMAPI_ENTIRE)));
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED|XFS_ILOCK_EXCL));
 
-	if (WARN_ON_ONCE(!ifp))
+	if (WARN_ON_ONCE(!ifp)) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		return -EFSCORRUPTED;
+	}
 
 	if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) ||
-	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT))
+	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		return -EFSCORRUPTED;
+	}
 
 	if (xfs_is_shutdown(mp))
 		return -EIO;
@@ -4365,6 +4376,7 @@ xfs_bmapi_write(
 
 	if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) ||
 	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		return -EFSCORRUPTED;
 	}
 
@@ -4592,9 +4604,11 @@ xfs_bmapi_convert_delalloc(
 	error = -ENOSPC;
 	if (WARN_ON_ONCE(bma.blkno == NULLFSBLOCK))
 		goto out_finish;
-	error = -EFSCORRUPTED;
-	if (WARN_ON_ONCE(!xfs_valid_startblock(ip, bma.got.br_startblock)))
+	if (WARN_ON_ONCE(!xfs_valid_startblock(ip, bma.got.br_startblock))) {
+		xfs_bmap_mark_sick(ip, whichfork);
+		error = -EFSCORRUPTED;
 		goto out_finish;
+	}
 
 	XFS_STATS_ADD(mp, xs_xstrat_bytes, XFS_FSB_TO_B(mp, bma.length));
 	XFS_STATS_INC(mp, xs_xstrat_quick);
@@ -4653,6 +4667,7 @@ xfs_bmapi_remap(
 
 	if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) ||
 	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		return -EFSCORRUPTED;
 	}
 
@@ -5265,8 +5280,10 @@ __xfs_bunmapi(
 	whichfork = xfs_bmapi_whichfork(flags);
 	ASSERT(whichfork != XFS_COW_FORK);
 	ifp = xfs_ifork_ptr(ip, whichfork);
-	if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)))
+	if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp))) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		return -EFSCORRUPTED;
+	}
 	if (xfs_is_shutdown(mp))
 		return -EIO;
 
@@ -5737,6 +5754,7 @@ xfs_bmap_collapse_extents(
 
 	if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) ||
 	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		return -EFSCORRUPTED;
 	}
 
@@ -5852,6 +5870,7 @@ xfs_bmap_insert_extents(
 
 	if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) ||
 	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		return -EFSCORRUPTED;
 	}
 
@@ -5955,6 +5974,7 @@ xfs_bmap_split_extent(
 
 	if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) ||
 	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		return -EFSCORRUPTED;
 	}
 
@@ -6137,8 +6157,10 @@ xfs_bmap_finish_one(
 			bmap->br_startoff, bmap->br_blockcount,
 			bmap->br_state);
 
-	if (WARN_ON_ONCE(bi->bi_whichfork != XFS_DATA_FORK))
+	if (WARN_ON_ONCE(bi->bi_whichfork != XFS_DATA_FORK)) {
+		xfs_bmap_mark_sick(bi->bi_owner, bi->bi_whichfork);
 		return -EFSCORRUPTED;
+	}
 
 	if (XFS_TEST_ERROR(false, tp->t_mountp,
 			XFS_ERRTAG_BMAP_FINISH_ONE))
@@ -6156,6 +6178,7 @@ xfs_bmap_finish_one(
 		break;
 	default:
 		ASSERT(0);
+		xfs_bmap_mark_sick(bi->bi_owner, bi->bi_whichfork);
 		error = -EFSCORRUPTED;
 	}
 
diff --git a/libxfs/xfs_health.h b/libxfs/xfs_health.h
index cd7a1370a1e..50515920c95 100644
--- a/libxfs/xfs_health.h
+++ b/libxfs/xfs_health.h
@@ -152,6 +152,7 @@ void xfs_inode_measure_sickness(struct xfs_inode *ip, unsigned int *sick,
 		unsigned int *checked);
 
 void xfs_health_unmount(struct xfs_mount *mp);
+void xfs_bmap_mark_sick(struct xfs_inode *ip, int whichfork);
 
 /* Now some helpers. */
 

[PATCH 5/9] xfs: report btree block corruption errors to the health system

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Whenever we encounter corrupt btree blocks, we should report that to the
health monitoring system for later reporting.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/util.c         |    1 +
 libxfs/xfs_alloc.c    |    2 ++
 libxfs/xfs_bmap.c     |    6 ++++++
 libxfs/xfs_btree.c    |   25 ++++++++++++++++++++++---
 libxfs/xfs_health.h   |    2 ++
 libxfs/xfs_ialloc.c   |    1 +
 libxfs/xfs_refcount.c |    6 +++++-
 libxfs/xfs_rmap.c     |    6 +++++-
 8 files changed, 44 insertions(+), 5 deletions(-)


diff --git a/libxfs/util.c b/libxfs/util.c
index 9c6a4a2c457..3bbab38a391 100644
--- a/libxfs/util.c
+++ b/libxfs/util.c
@@ -733,3 +733,4 @@ void xfs_agno_mark_sick(struct xfs_mount *mp, xfs_agnumber_t agno,
 		unsigned int mask) { }
 void xfs_ag_mark_sick(struct xfs_perag *pag, unsigned int mask) { }
 void xfs_bmap_mark_sick(struct xfs_inode *ip, int whichfork) { }
+void xfs_btree_mark_sick(struct xfs_btree_cur *cur) { }
diff --git a/libxfs/xfs_alloc.c b/libxfs/xfs_alloc.c
index 1894a091380..aa084120c4c 100644
--- a/libxfs/xfs_alloc.c
+++ b/libxfs/xfs_alloc.c
@@ -271,6 +271,7 @@ xfs_alloc_complain_bad_rec(
 	xfs_warn(mp,
 		"start block 0x%x block count 0x%x", irec->ar_startblock,
 		irec->ar_blockcount);
+	xfs_btree_mark_sick(cur);
 	return -EFSCORRUPTED;
 }
 
@@ -2698,6 +2699,7 @@ xfs_exact_minlen_extent_available(
 		goto out;
 
 	if (*stat == 0) {
+		xfs_btree_mark_sick(cnt_cur);
 		error = -EFSCORRUPTED;
 		goto out;
 	}
diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index ee11d89d813..04d7566bc82 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -362,6 +362,8 @@ xfs_bmap_check_leaf_extents(
 			error = xfs_btree_read_bufl(mp, NULL, bno, &bp,
 						XFS_BMAP_BTREE_REF,
 						&xfs_bmbt_buf_ops);
+			if (xfs_metadata_is_sick(error))
+				xfs_btree_mark_sick(cur);
 			if (error)
 				goto error_norelse;
 		}
@@ -448,6 +450,8 @@ xfs_bmap_check_leaf_extents(
 			error = xfs_btree_read_bufl(mp, NULL, bno, &bp,
 						XFS_BMAP_BTREE_REF,
 						&xfs_bmbt_buf_ops);
+			if (xfs_metadata_is_sick(error))
+				xfs_btree_mark_sick(cur);
 			if (error)
 				goto error_norelse;
 		}
@@ -562,6 +566,8 @@ xfs_bmap_btree_to_extents(
 #endif
 	error = xfs_btree_read_bufl(mp, tp, cbno, &cbp, XFS_BMAP_BTREE_REF,
 				&xfs_bmbt_buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_btree_mark_sick(cur);
 	if (error)
 		return error;
 	cblock = XFS_BUF_TO_BLOCK(cbp);
diff --git a/libxfs/xfs_btree.c b/libxfs/xfs_btree.c
index 0022bb641be..691d8dda420 100644
--- a/libxfs/xfs_btree.c
+++ b/libxfs/xfs_btree.c
@@ -24,6 +24,7 @@
 #include "xfs_bmap_btree.h"
 #include "xfs_rmap_btree.h"
 #include "xfs_refcount_btree.h"
+#include "xfs_health.h"
 
 /*
  * Btree magic numbers.
@@ -174,6 +175,7 @@ xfs_btree_check_lblock(
 	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BTREE_CHECK_LBLOCK)) {
 		if (bp)
 			trace_xfs_btree_corrupt(bp, _RET_IP_);
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
 	}
 	return 0;
@@ -240,6 +242,7 @@ xfs_btree_check_sblock(
 	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BTREE_CHECK_SBLOCK)) {
 		if (bp)
 			trace_xfs_btree_corrupt(bp, _RET_IP_);
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
 	}
 	return 0;
@@ -315,6 +318,7 @@ xfs_btree_check_ptr(
 				level, index);
 	}
 
+	xfs_btree_mark_sick(cur);
 	return -EFSCORRUPTED;
 }
 
@@ -495,6 +499,8 @@ xfs_btree_dup_cursor(
 						   xfs_buf_daddr(bp), mp->m_bsize,
 						   0, &bp,
 						   cur->bc_ops->buf_ops);
+			if (xfs_metadata_is_sick(error))
+				xfs_btree_mark_sick(new);
 			if (error) {
 				xfs_btree_del_cursor(new, error);
 				*ncur = NULL;
@@ -1348,6 +1354,8 @@ xfs_btree_read_buf_block(
 	error = xfs_trans_read_buf(mp, cur->bc_tp, mp->m_ddev_targp, d,
 				   mp->m_bsize, flags, bpp,
 				   cur->bc_ops->buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_btree_mark_sick(cur);
 	if (error)
 		return error;
 
@@ -1658,6 +1666,7 @@ xfs_btree_increment(
 		if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
 			goto out0;
 		ASSERT(0);
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -1751,6 +1760,7 @@ xfs_btree_decrement(
 		if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
 			goto out0;
 		ASSERT(0);
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -1843,6 +1853,7 @@ xfs_btree_lookup_get_block(
 	*blkp = NULL;
 	xfs_buf_mark_corrupt(bp);
 	xfs_trans_brelse(cur->bc_tp, bp);
+	xfs_btree_mark_sick(cur);
 	return -EFSCORRUPTED;
 }
 
@@ -1889,8 +1900,10 @@ xfs_btree_lookup(
 	XFS_BTREE_STATS_INC(cur, lookup);
 
 	/* No such thing as a zero-level tree. */
-	if (XFS_IS_CORRUPT(cur->bc_mp, cur->bc_nlevels == 0))
+	if (XFS_IS_CORRUPT(cur->bc_mp, cur->bc_nlevels == 0)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	block = NULL;
 	keyno = 0;
@@ -1933,6 +1946,7 @@ xfs_btree_lookup(
 							XFS_ERRLEVEL_LOW,
 							cur->bc_mp, block,
 							sizeof(*block));
+					xfs_btree_mark_sick(cur);
 					return -EFSCORRUPTED;
 				}
 
@@ -4366,12 +4380,16 @@ xfs_btree_visit_block(
 	 */
 	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
 		if (be64_to_cpu(rptr.l) == XFS_DADDR_TO_FSB(cur->bc_mp,
-							xfs_buf_daddr(bp)))
+							xfs_buf_daddr(bp))) {
+			xfs_btree_mark_sick(cur);
 			return -EFSCORRUPTED;
+		}
 	} else {
 		if (be32_to_cpu(rptr.s) == xfs_daddr_to_agbno(cur->bc_mp,
-							xfs_buf_daddr(bp)))
+							xfs_buf_daddr(bp))) {
+			xfs_btree_mark_sick(cur);
 			return -EFSCORRUPTED;
+		}
 	}
 	return xfs_btree_lookup_get_block(cur, level, &rptr, &block);
 }
@@ -5230,6 +5248,7 @@ xfs_btree_goto_left_edge(
 		return error;
 	if (stat != 0) {
 		ASSERT(0);
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
 	}
 
diff --git a/libxfs/xfs_health.h b/libxfs/xfs_health.h
index 50515920c95..0876c767d9d 100644
--- a/libxfs/xfs_health.h
+++ b/libxfs/xfs_health.h
@@ -37,6 +37,7 @@ struct xfs_mount;
 struct xfs_perag;
 struct xfs_inode;
 struct xfs_fsop_geom;
+struct xfs_btree_cur;
 
 /* Observable health issues for metadata spanning the entire filesystem. */
 #define XFS_SICK_FS_COUNTERS	(1 << 0)  /* summary counters */
@@ -153,6 +154,7 @@ void xfs_inode_measure_sickness(struct xfs_inode *ip, unsigned int *sick,
 
 void xfs_health_unmount(struct xfs_mount *mp);
 void xfs_bmap_mark_sick(struct xfs_inode *ip, int whichfork);
+void xfs_btree_mark_sick(struct xfs_btree_cur *cur);
 
 /* Now some helpers. */
 
diff --git a/libxfs/xfs_ialloc.c b/libxfs/xfs_ialloc.c
index c801250a33b..92ca3d460e0 100644
--- a/libxfs/xfs_ialloc.c
+++ b/libxfs/xfs_ialloc.c
@@ -143,6 +143,7 @@ xfs_inobt_complain_bad_rec(
 "start inode 0x%x, count 0x%x, free 0x%x freemask 0x%llx, holemask 0x%x",
 		irec->ir_startino, irec->ir_count, irec->ir_freecount,
 		irec->ir_free, irec->ir_holemask);
+	xfs_btree_mark_sick(cur);
 	return -EFSCORRUPTED;
 }
 
diff --git a/libxfs/xfs_refcount.c b/libxfs/xfs_refcount.c
index de321ab9d91..3d66e89b00f 100644
--- a/libxfs/xfs_refcount.c
+++ b/libxfs/xfs_refcount.c
@@ -22,6 +22,7 @@
 #include "xfs_refcount.h"
 #include "xfs_rmap.h"
 #include "xfs_ag.h"
+#include "xfs_health.h"
 
 struct kmem_cache	*xfs_refcount_intent_cache;
 
@@ -155,6 +156,7 @@ xfs_refcount_complain_bad_rec(
 	xfs_warn(mp,
 		"Start block 0x%x, block count 0x%x, references 0x%x",
 		irec->rc_startblock, irec->rc_blockcount, irec->rc_refcount);
+	xfs_btree_mark_sick(cur);
 	return -EFSCORRUPTED;
 }
 
@@ -1888,8 +1890,10 @@ xfs_refcount_recover_extent(
 	struct xfs_refcount_recovery	*rr;
 
 	if (XFS_IS_CORRUPT(cur->bc_mp,
-			   be32_to_cpu(rec->refc.rc_refcount) != 1))
+			   be32_to_cpu(rec->refc.rc_refcount) != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	rr = kmalloc(sizeof(struct xfs_refcount_recovery),
 			GFP_KERNEL | __GFP_NOFAIL);
diff --git a/libxfs/xfs_rmap.c b/libxfs/xfs_rmap.c
index 4731e10d210..9373b1102fd 100644
--- a/libxfs/xfs_rmap.c
+++ b/libxfs/xfs_rmap.c
@@ -22,6 +22,7 @@
 #include "xfs_errortag.h"
 #include "xfs_inode.h"
 #include "xfs_ag.h"
+#include "xfs_health.h"
 
 struct kmem_cache	*xfs_rmap_intent_cache;
 
@@ -55,8 +56,10 @@ xfs_rmap_lookup_le(
 	error = xfs_rmap_get_rec(cur, irec, &get_stat);
 	if (error)
 		return error;
-	if (!get_stat)
+	if (!get_stat) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	return 0;
 }
@@ -276,6 +279,7 @@ xfs_rmap_complain_bad_rec(
 		"Owner 0x%llx, flags 0x%x, start block 0x%x block count 0x%x",
 		irec->rm_owner, irec->rm_flags, irec->rm_startblock,
 		irec->rm_blockcount);
+	xfs_btree_mark_sick(cur);
 	return -EFSCORRUPTED;
 }
 

[PATCH 6/9] xfs: report dir/attr block corruption errors to the health system

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Whenever we encounter corrupt directory or extended attribute blocks, we
should report that to the health monitoring system for later reporting.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/util.c            |    2 ++
 libxfs/xfs_attr_leaf.c   |    4 ++++
 libxfs/xfs_attr_remote.c |   27 ++++++++++++++++-----------
 libxfs/xfs_da_btree.c    |   37 ++++++++++++++++++++++++++++++++-----
 libxfs/xfs_dir2.c        |    5 ++++-
 libxfs/xfs_dir2_block.c  |    2 ++
 libxfs/xfs_dir2_data.c   |    3 +++
 libxfs/xfs_dir2_leaf.c   |    3 +++
 libxfs/xfs_dir2_node.c   |    7 +++++++
 libxfs/xfs_health.h      |    3 +++
 10 files changed, 76 insertions(+), 17 deletions(-)


diff --git a/libxfs/util.c b/libxfs/util.c
index 3bbab38a391..44b404d8d5d 100644
--- a/libxfs/util.c
+++ b/libxfs/util.c
@@ -734,3 +734,5 @@ void xfs_agno_mark_sick(struct xfs_mount *mp, xfs_agnumber_t agno,
 void xfs_ag_mark_sick(struct xfs_perag *pag, unsigned int mask) { }
 void xfs_bmap_mark_sick(struct xfs_inode *ip, int whichfork) { }
 void xfs_btree_mark_sick(struct xfs_btree_cur *cur) { }
+void xfs_dirattr_mark_sick(struct xfs_inode *ip, int whichfork) { }
+void xfs_da_mark_sick(struct xfs_da_args *args) { }
diff --git a/libxfs/xfs_attr_leaf.c b/libxfs/xfs_attr_leaf.c
index 8329348eb78..aa7aad36864 100644
--- a/libxfs/xfs_attr_leaf.c
+++ b/libxfs/xfs_attr_leaf.c
@@ -26,6 +26,7 @@
 #include "xfs_dir2.h"
 #include "xfs_ag.h"
 #include "xfs_errortag.h"
+#include "xfs_health.h"
 
 
 /*
@@ -2411,6 +2412,7 @@ xfs_attr3_leaf_lookup_int(
 	entries = xfs_attr3_leaf_entryp(leaf);
 	if (ichdr.count >= args->geo->blksize / 8) {
 		xfs_buf_mark_corrupt(bp);
+		xfs_da_mark_sick(args);
 		return -EFSCORRUPTED;
 	}
 
@@ -2430,10 +2432,12 @@ xfs_attr3_leaf_lookup_int(
 	}
 	if (!(probe >= 0 && (!ichdr.count || probe < ichdr.count))) {
 		xfs_buf_mark_corrupt(bp);
+		xfs_da_mark_sick(args);
 		return -EFSCORRUPTED;
 	}
 	if (!(span <= 4 || be32_to_cpu(entry->hashval) == hashval)) {
 		xfs_buf_mark_corrupt(bp);
+		xfs_da_mark_sick(args);
 		return -EFSCORRUPTED;
 	}
 
diff --git a/libxfs/xfs_attr_remote.c b/libxfs/xfs_attr_remote.c
index 4f2b93f81ba..a67caf5e86f 100644
--- a/libxfs/xfs_attr_remote.c
+++ b/libxfs/xfs_attr_remote.c
@@ -21,6 +21,7 @@
 #include "xfs_attr.h"
 #include "xfs_attr_remote.h"
 #include "xfs_trace.h"
+#include "xfs_health.h"
 
 #define ATTR_RMTVALUE_MAPSIZE	1	/* # of map entries at once */
 
@@ -275,17 +276,18 @@ xfs_attr3_rmt_hdr_set(
  */
 STATIC int
 xfs_attr_rmtval_copyout(
-	struct xfs_mount *mp,
-	struct xfs_buf	*bp,
-	xfs_ino_t	ino,
-	int		*offset,
-	int		*valuelen,
-	uint8_t		**dst)
+	struct xfs_mount	*mp,
+	struct xfs_buf		*bp,
+	struct xfs_inode	*dp,
+	int			*offset,
+	int			*valuelen,
+	uint8_t			**dst)
 {
-	char		*src = bp->b_addr;
-	xfs_daddr_t	bno = xfs_buf_daddr(bp);
-	int		len = BBTOB(bp->b_length);
-	int		blksize = mp->m_attr_geo->blksize;
+	char			*src = bp->b_addr;
+	xfs_ino_t		ino = dp->i_ino;
+	xfs_daddr_t		bno = xfs_buf_daddr(bp);
+	int			len = BBTOB(bp->b_length);
+	int			blksize = mp->m_attr_geo->blksize;
 
 	ASSERT(len >= blksize);
 
@@ -301,6 +303,7 @@ xfs_attr_rmtval_copyout(
 				xfs_alert(mp,
 "remote attribute header mismatch bno/off/len/owner (0x%llx/0x%x/Ox%x/0x%llx)",
 					bno, *offset, byte_cnt, ino);
+				xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
 				return -EFSCORRUPTED;
 			}
 			hdr_size = sizeof(struct xfs_attr3_rmt_hdr);
@@ -417,10 +420,12 @@ xfs_attr_rmtval_get(
 			dblkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount);
 			error = xfs_buf_read(mp->m_ddev_targp, dblkno, dblkcnt,
 					0, &bp, &xfs_attr3_rmt_buf_ops);
+			if (xfs_metadata_is_sick(error))
+				xfs_dirattr_mark_sick(args->dp, XFS_ATTR_FORK);
 			if (error)
 				return error;
 
-			error = xfs_attr_rmtval_copyout(mp, bp, args->dp->i_ino,
+			error = xfs_attr_rmtval_copyout(mp, bp, args->dp,
 							&offset, &valuelen,
 							&dst);
 			xfs_buf_relse(bp);
diff --git a/libxfs/xfs_da_btree.c b/libxfs/xfs_da_btree.c
index 0779bb6242c..87996c5da4f 100644
--- a/libxfs/xfs_da_btree.c
+++ b/libxfs/xfs_da_btree.c
@@ -19,6 +19,7 @@
 #include "xfs_bmap.h"
 #include "xfs_attr_leaf.h"
 #include "xfs_trace.h"
+#include "xfs_health.h"
 
 /*
  * xfs_da_btree.c
@@ -348,6 +349,8 @@ const struct xfs_buf_ops xfs_da3_node_buf_ops = {
 static int
 xfs_da3_node_set_type(
 	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
+	int			whichfork,
 	struct xfs_buf		*bp)
 {
 	struct xfs_da_blkinfo	*info = bp->b_addr;
@@ -369,6 +372,7 @@ xfs_da3_node_set_type(
 		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, tp->t_mountp,
 				info, sizeof(*info));
 		xfs_trans_brelse(tp, bp);
+		xfs_dirattr_mark_sick(dp, whichfork);
 		return -EFSCORRUPTED;
 	}
 }
@@ -387,7 +391,7 @@ xfs_da3_node_read(
 			&xfs_da3_node_buf_ops);
 	if (error || !*bpp || !tp)
 		return error;
-	return xfs_da3_node_set_type(tp, *bpp);
+	return xfs_da3_node_set_type(tp, dp, whichfork, *bpp);
 }
 
 int
@@ -404,6 +408,8 @@ xfs_da3_node_read_mapped(
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, mappedbno,
 			XFS_FSB_TO_BB(mp, xfs_dabuf_nfsb(mp, whichfork)), 0,
 			bpp, &xfs_da3_node_buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_dirattr_mark_sick(dp, whichfork);
 	if (error || !*bpp)
 		return error;
 
@@ -414,7 +420,7 @@ xfs_da3_node_read_mapped(
 
 	if (!tp)
 		return 0;
-	return xfs_da3_node_set_type(tp, *bpp);
+	return xfs_da3_node_set_type(tp, dp, whichfork, *bpp);
 }
 
 /*
@@ -627,6 +633,7 @@ xfs_da3_split(
 	if (node->hdr.info.forw) {
 		if (be32_to_cpu(node->hdr.info.forw) != addblk->blkno) {
 			xfs_buf_mark_corrupt(oldblk->bp);
+			xfs_da_mark_sick(state->args);
 			error = -EFSCORRUPTED;
 			goto out;
 		}
@@ -640,6 +647,7 @@ xfs_da3_split(
 	if (node->hdr.info.back) {
 		if (be32_to_cpu(node->hdr.info.back) != addblk->blkno) {
 			xfs_buf_mark_corrupt(oldblk->bp);
+			xfs_da_mark_sick(state->args);
 			error = -EFSCORRUPTED;
 			goto out;
 		}
@@ -1631,6 +1639,7 @@ xfs_da3_node_lookup_int(
 
 		if (magic != XFS_DA_NODE_MAGIC && magic != XFS_DA3_NODE_MAGIC) {
 			xfs_buf_mark_corrupt(blk->bp);
+			xfs_da_mark_sick(args);
 			return -EFSCORRUPTED;
 		}
 
@@ -1646,6 +1655,7 @@ xfs_da3_node_lookup_int(
 		/* Tree taller than we can handle; bail out! */
 		if (nodehdr.level >= XFS_DA_NODE_MAXDEPTH) {
 			xfs_buf_mark_corrupt(blk->bp);
+			xfs_da_mark_sick(args);
 			return -EFSCORRUPTED;
 		}
 
@@ -1654,6 +1664,7 @@ xfs_da3_node_lookup_int(
 			expected_level = nodehdr.level - 1;
 		else if (expected_level != nodehdr.level) {
 			xfs_buf_mark_corrupt(blk->bp);
+			xfs_da_mark_sick(args);
 			return -EFSCORRUPTED;
 		} else
 			expected_level--;
@@ -1705,12 +1716,16 @@ xfs_da3_node_lookup_int(
 		}
 
 		/* We can't point back to the root. */
-		if (XFS_IS_CORRUPT(dp->i_mount, blkno == args->geo->leafblk))
+		if (XFS_IS_CORRUPT(dp->i_mount, blkno == args->geo->leafblk)) {
+			xfs_da_mark_sick(args);
 			return -EFSCORRUPTED;
+		}
 	}
 
-	if (XFS_IS_CORRUPT(dp->i_mount, expected_level != 0))
+	if (XFS_IS_CORRUPT(dp->i_mount, expected_level != 0)) {
+		xfs_da_mark_sick(args);
 		return -EFSCORRUPTED;
+	}
 
 	/*
 	 * A leaf block that ends in the hashval that we are interested in
@@ -1728,6 +1743,7 @@ xfs_da3_node_lookup_int(
 			args->blkno = blk->blkno;
 		} else {
 			ASSERT(0);
+			xfs_da_mark_sick(args);
 			return -EFSCORRUPTED;
 		}
 		if (((retval == -ENOENT) || (retval == -ENOATTR)) &&
@@ -2293,8 +2309,10 @@ xfs_da3_swap_lastblock(
 	error = xfs_bmap_last_before(tp, dp, &lastoff, w);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(mp, lastoff == 0))
+	if (XFS_IS_CORRUPT(mp, lastoff == 0)) {
+		xfs_da_mark_sick(args);
 		return -EFSCORRUPTED;
+	}
 	/*
 	 * Read the last block in the btree space.
 	 */
@@ -2344,6 +2362,7 @@ xfs_da3_swap_lastblock(
 		if (XFS_IS_CORRUPT(mp,
 				   be32_to_cpu(sib_info->forw) != last_blkno ||
 				   sib_info->magic != dead_info->magic)) {
+			xfs_da_mark_sick(args);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -2364,6 +2383,7 @@ xfs_da3_swap_lastblock(
 		if (XFS_IS_CORRUPT(mp,
 				   be32_to_cpu(sib_info->back) != last_blkno ||
 				   sib_info->magic != dead_info->magic)) {
+			xfs_da_mark_sick(args);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -2386,6 +2406,7 @@ xfs_da3_swap_lastblock(
 		xfs_da3_node_hdr_from_disk(dp->i_mount, &par_hdr, par_node);
 		if (XFS_IS_CORRUPT(mp,
 				   level >= 0 && level != par_hdr.level + 1)) {
+			xfs_da_mark_sick(args);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -2397,6 +2418,7 @@ xfs_da3_swap_lastblock(
 		     entno++)
 			continue;
 		if (XFS_IS_CORRUPT(mp, entno == par_hdr.count)) {
+			xfs_da_mark_sick(args);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -2422,6 +2444,7 @@ xfs_da3_swap_lastblock(
 		xfs_trans_brelse(tp, par_buf);
 		par_buf = NULL;
 		if (XFS_IS_CORRUPT(mp, par_blkno == 0)) {
+			xfs_da_mark_sick(args);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -2431,6 +2454,7 @@ xfs_da3_swap_lastblock(
 		par_node = par_buf->b_addr;
 		xfs_da3_node_hdr_from_disk(dp->i_mount, &par_hdr, par_node);
 		if (XFS_IS_CORRUPT(mp, par_hdr.level != level)) {
+			xfs_da_mark_sick(args);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -2559,6 +2583,7 @@ xfs_dabuf_map(
 invalid_mapping:
 	/* Caller ok with no mapping. */
 	if (XFS_IS_CORRUPT(mp, !(flags & XFS_DABUF_MAP_HOLE_OK))) {
+		xfs_dirattr_mark_sick(dp, whichfork);
 		error = -EFSCORRUPTED;
 		if (xfs_error_level >= XFS_ERRLEVEL_LOW) {
 			xfs_alert(mp, "%s: bno %u inode %llu",
@@ -2640,6 +2665,8 @@ xfs_da_read_buf(
 
 	error = xfs_trans_read_buf_map(mp, tp, mp->m_ddev_targp, mapp, nmap, 0,
 			&bp, ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_dirattr_mark_sick(dp, whichfork);
 	if (error)
 		goto out_free;
 
diff --git a/libxfs/xfs_dir2.c b/libxfs/xfs_dir2.c
index dcbc83c8b00..e503bf8f92f 100644
--- a/libxfs/xfs_dir2.c
+++ b/libxfs/xfs_dir2.c
@@ -17,6 +17,7 @@
 #include "xfs_dir2_priv.h"
 #include "xfs_errortag.h"
 #include "xfs_trace.h"
+#include "xfs_health.h"
 
 const struct xfs_name xfs_name_dotdot = {
 	.name	= (const unsigned char *)"..",
@@ -631,8 +632,10 @@ xfs_dir2_isblock(
 		return 0;
 
 	*isblock = true;
-	if (XFS_IS_CORRUPT(mp, args->dp->i_disk_size != args->geo->blksize))
+	if (XFS_IS_CORRUPT(mp, args->dp->i_disk_size != args->geo->blksize)) {
+		xfs_da_mark_sick(args);
 		return -EFSCORRUPTED;
+	}
 	return 0;
 }
 
diff --git a/libxfs/xfs_dir2_block.c b/libxfs/xfs_dir2_block.c
index bb9301b7688..19fededab5d 100644
--- a/libxfs/xfs_dir2_block.c
+++ b/libxfs/xfs_dir2_block.c
@@ -17,6 +17,7 @@
 #include "xfs_dir2.h"
 #include "xfs_dir2_priv.h"
 #include "xfs_trace.h"
+#include "xfs_health.h"
 
 /*
  * Local function prototypes.
@@ -149,6 +150,7 @@ xfs_dir3_block_read(
 		__xfs_buf_mark_corrupt(*bpp, fa);
 		xfs_trans_brelse(tp, *bpp);
 		*bpp = NULL;
+		xfs_dirattr_mark_sick(dp, XFS_DATA_FORK);
 		return -EFSCORRUPTED;
 	}
 
diff --git a/libxfs/xfs_dir2_data.c b/libxfs/xfs_dir2_data.c
index 4e207986bc9..aaf3f62af91 100644
--- a/libxfs/xfs_dir2_data.c
+++ b/libxfs/xfs_dir2_data.c
@@ -15,6 +15,7 @@
 #include "xfs_dir2.h"
 #include "xfs_dir2_priv.h"
 #include "xfs_trans.h"
+#include "xfs_health.h"
 
 static xfs_failaddr_t xfs_dir2_data_freefind_verify(
 		struct xfs_dir2_data_hdr *hdr, struct xfs_dir2_data_free *bf,
@@ -430,6 +431,7 @@ xfs_dir3_data_read(
 		__xfs_buf_mark_corrupt(*bpp, fa);
 		xfs_trans_brelse(tp, *bpp);
 		*bpp = NULL;
+		xfs_dirattr_mark_sick(dp, XFS_DATA_FORK);
 		return -EFSCORRUPTED;
 	}
 
@@ -1195,6 +1197,7 @@ xfs_dir2_data_use_free(
 corrupt:
 	xfs_corruption_error(__func__, XFS_ERRLEVEL_LOW, args->dp->i_mount,
 			hdr, sizeof(*hdr), __FILE__, __LINE__, fa);
+	xfs_da_mark_sick(args);
 	return -EFSCORRUPTED;
 }
 
diff --git a/libxfs/xfs_dir2_leaf.c b/libxfs/xfs_dir2_leaf.c
index 5da66006cb5..80cea8a275d 100644
--- a/libxfs/xfs_dir2_leaf.c
+++ b/libxfs/xfs_dir2_leaf.c
@@ -17,6 +17,7 @@
 #include "xfs_dir2_priv.h"
 #include "xfs_trace.h"
 #include "xfs_trans.h"
+#include "xfs_health.h"
 
 /*
  * Local function declarations.
@@ -1391,8 +1392,10 @@ xfs_dir2_leaf_removename(
 	bestsp = xfs_dir2_leaf_bests_p(ltp);
 	if (be16_to_cpu(bestsp[db]) != oldbest) {
 		xfs_buf_mark_corrupt(lbp);
+		xfs_da_mark_sick(args);
 		return -EFSCORRUPTED;
 	}
+
 	/*
 	 * Mark the former data entry unused.
 	 */
diff --git a/libxfs/xfs_dir2_node.c b/libxfs/xfs_dir2_node.c
index c0eb335c300..44c8f3f2b07 100644
--- a/libxfs/xfs_dir2_node.c
+++ b/libxfs/xfs_dir2_node.c
@@ -17,6 +17,7 @@
 #include "xfs_dir2_priv.h"
 #include "xfs_trace.h"
 #include "xfs_trans.h"
+#include "xfs_health.h"
 
 /*
  * Function declarations.
@@ -228,6 +229,7 @@ __xfs_dir3_free_read(
 		__xfs_buf_mark_corrupt(*bpp, fa);
 		xfs_trans_brelse(tp, *bpp);
 		*bpp = NULL;
+		xfs_dirattr_mark_sick(dp, XFS_DATA_FORK);
 		return -EFSCORRUPTED;
 	}
 
@@ -440,6 +442,7 @@ xfs_dir2_leaf_to_node(
 	if (be32_to_cpu(ltp->bestcount) >
 				(uint)dp->i_disk_size / args->geo->blksize) {
 		xfs_buf_mark_corrupt(lbp);
+		xfs_da_mark_sick(args);
 		return -EFSCORRUPTED;
 	}
 
@@ -514,6 +517,7 @@ xfs_dir2_leafn_add(
 	 */
 	if (index < 0) {
 		xfs_buf_mark_corrupt(bp);
+		xfs_da_mark_sick(args);
 		return -EFSCORRUPTED;
 	}
 
@@ -733,6 +737,7 @@ xfs_dir2_leafn_lookup_for_addname(
 					   cpu_to_be16(NULLDATAOFF))) {
 				if (curfdb != newfdb)
 					xfs_trans_brelse(tp, curbp);
+				xfs_da_mark_sick(args);
 				return -EFSCORRUPTED;
 			}
 			curfdb = newfdb;
@@ -801,6 +806,7 @@ xfs_dir2_leafn_lookup_for_entry(
 	xfs_dir3_leaf_check(dp, bp);
 	if (leafhdr.count <= 0) {
 		xfs_buf_mark_corrupt(bp);
+		xfs_da_mark_sick(args);
 		return -EFSCORRUPTED;
 	}
 
@@ -1736,6 +1742,7 @@ xfs_dir2_node_add_datablk(
 			} else {
 				xfs_alert(mp, " ... fblk is NULL");
 			}
+			xfs_da_mark_sick(args);
 			return -EFSCORRUPTED;
 		}
 
diff --git a/libxfs/xfs_health.h b/libxfs/xfs_health.h
index 0876c767d9d..a5b346b377c 100644
--- a/libxfs/xfs_health.h
+++ b/libxfs/xfs_health.h
@@ -38,6 +38,7 @@ struct xfs_perag;
 struct xfs_inode;
 struct xfs_fsop_geom;
 struct xfs_btree_cur;
+struct xfs_da_args;
 
 /* Observable health issues for metadata spanning the entire filesystem. */
 #define XFS_SICK_FS_COUNTERS	(1 << 0)  /* summary counters */
@@ -155,6 +156,8 @@ void xfs_inode_measure_sickness(struct xfs_inode *ip, unsigned int *sick,
 void xfs_health_unmount(struct xfs_mount *mp);
 void xfs_bmap_mark_sick(struct xfs_inode *ip, int whichfork);
 void xfs_btree_mark_sick(struct xfs_btree_cur *cur);
+void xfs_dirattr_mark_sick(struct xfs_inode *ip, int whichfork);
+void xfs_da_mark_sick(struct xfs_da_args *args);
 
 /* Now some helpers. */
 

[PATCH 7/9] xfs: report inode corruption errors to the health system

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Whenever we encounter corrupt inode records, we should report that to
the health monitoring system for later reporting.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/util.c           |    1 +
 libxfs/xfs_ialloc.c     |    1 +
 libxfs/xfs_inode_buf.c  |   12 +++++++++---
 libxfs/xfs_inode_fork.c |    8 ++++++++
 4 files changed, 19 insertions(+), 3 deletions(-)


diff --git a/libxfs/util.c b/libxfs/util.c
index 44b404d8d5d..ddb98141210 100644
--- a/libxfs/util.c
+++ b/libxfs/util.c
@@ -736,3 +736,4 @@ void xfs_bmap_mark_sick(struct xfs_inode *ip, int whichfork) { }
 void xfs_btree_mark_sick(struct xfs_btree_cur *cur) { }
 void xfs_dirattr_mark_sick(struct xfs_inode *ip, int whichfork) { }
 void xfs_da_mark_sick(struct xfs_da_args *args) { }
+void xfs_inode_mark_sick(struct xfs_inode *ip, unsigned int mask) { }
diff --git a/libxfs/xfs_ialloc.c b/libxfs/xfs_ialloc.c
index 92ca3d460e0..63922f44ffe 100644
--- a/libxfs/xfs_ialloc.c
+++ b/libxfs/xfs_ialloc.c
@@ -2994,6 +2994,7 @@ xfs_ialloc_check_shrink(
 		goto out;
 
 	if (!has) {
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_INOBT);
 		error = -EFSCORRUPTED;
 		goto out;
 	}
diff --git a/libxfs/xfs_inode_buf.c b/libxfs/xfs_inode_buf.c
index fd351c252af..83d93698116 100644
--- a/libxfs/xfs_inode_buf.c
+++ b/libxfs/xfs_inode_buf.c
@@ -16,6 +16,7 @@
 #include "xfs_trans.h"
 #include "xfs_ialloc.h"
 #include "xfs_dir2.h"
+#include "xfs_health.h"
 
 
 /*
@@ -129,9 +130,14 @@ xfs_imap_to_bp(
 	struct xfs_imap		*imap,
 	struct xfs_buf		**bpp)
 {
-	return xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
-				   imap->im_len, XBF_UNMAPPED, bpp,
-				   &xfs_inode_buf_ops);
+	int			error;
+
+	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
+			imap->im_len, XBF_UNMAPPED, bpp, &xfs_inode_buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_agno_mark_sick(mp, xfs_daddr_to_agno(mp, imap->im_blkno),
+				XFS_SICK_AG_INOBT);
+	return error;
 }
 
 static inline struct timespec64 xfs_inode_decode_bigtime(uint64_t ts)
diff --git a/libxfs/xfs_inode_fork.c b/libxfs/xfs_inode_fork.c
index 80f4215d24b..d6478af46d6 100644
--- a/libxfs/xfs_inode_fork.c
+++ b/libxfs/xfs_inode_fork.c
@@ -23,6 +23,7 @@
 #include "xfs_attr_leaf.h"
 #include "xfs_types.h"
 #include "xfs_errortag.h"
+#include "xfs_health.h"
 
 struct kmem_cache *xfs_ifork_cache;
 
@@ -82,6 +83,7 @@ xfs_iformat_local(
 		xfs_inode_verifier_error(ip, -EFSCORRUPTED,
 				"xfs_iformat_local", dip, sizeof(*dip),
 				__this_address);
+		xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
 		return -EFSCORRUPTED;
 	}
 
@@ -119,6 +121,7 @@ xfs_iformat_extents(
 		xfs_inode_verifier_error(ip, -EFSCORRUPTED,
 				"xfs_iformat_extents(1)", dip, sizeof(*dip),
 				__this_address);
+		xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
 		return -EFSCORRUPTED;
 	}
 
@@ -138,6 +141,7 @@ xfs_iformat_extents(
 				xfs_inode_verifier_error(ip, -EFSCORRUPTED,
 						"xfs_iformat_extents(2)",
 						dp, sizeof(*dp), fa);
+				xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
 				return xfs_bmap_complain_bad_rec(ip, whichfork,
 						fa, &new);
 			}
@@ -196,6 +200,7 @@ xfs_iformat_btree(
 		xfs_inode_verifier_error(ip, -EFSCORRUPTED,
 				"xfs_iformat_btree", dfp, size,
 				__this_address);
+		xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
 		return -EFSCORRUPTED;
 	}
 
@@ -260,12 +265,14 @@ xfs_iformat_data_fork(
 		default:
 			xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__,
 					dip, sizeof(*dip), __this_address);
+			xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
 			return -EFSCORRUPTED;
 		}
 		break;
 	default:
 		xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip,
 				sizeof(*dip), __this_address);
+		xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
 		return -EFSCORRUPTED;
 	}
 }
@@ -338,6 +345,7 @@ xfs_iformat_attr_fork(
 	default:
 		xfs_inode_verifier_error(ip, error, __func__, dip,
 				sizeof(*dip), __this_address);
+		xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
 		error = -EFSCORRUPTED;
 		break;
 	}

[PATCH 8/9] xfs: report realtime metadata corruption errors to the health system

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Whenever we encounter corrupt realtime metadat blocks, we should report
that to the health monitoring system for later reporting.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/util.c         |    1 +
 libxfs/xfs_rtbitmap.c |    9 ++++++++-
 2 files changed, 9 insertions(+), 1 deletion(-)


diff --git a/libxfs/util.c b/libxfs/util.c
index ddb98141210..097362d488d 100644
--- a/libxfs/util.c
+++ b/libxfs/util.c
@@ -737,3 +737,4 @@ void xfs_btree_mark_sick(struct xfs_btree_cur *cur) { }
 void xfs_dirattr_mark_sick(struct xfs_inode *ip, int whichfork) { }
 void xfs_da_mark_sick(struct xfs_da_args *args) { }
 void xfs_inode_mark_sick(struct xfs_inode *ip, unsigned int mask) { }
+void xfs_rt_mark_sick(struct xfs_mount *mp, unsigned int mask) { }
diff --git a/libxfs/xfs_rtbitmap.c b/libxfs/xfs_rtbitmap.c
index 726543abb51..b4da1b07c73 100644
--- a/libxfs/xfs_rtbitmap.c
+++ b/libxfs/xfs_rtbitmap.c
@@ -15,6 +15,7 @@
 #include "xfs_bmap.h"
 #include "xfs_trans.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_health.h"
 
 /*
  * Realtime allocator bitmap functions shared with userspace.
@@ -113,13 +114,19 @@ xfs_rtbuf_get(
 	if (error)
 		return error;
 
-	if (XFS_IS_CORRUPT(mp, nmap == 0 || !xfs_bmap_is_written_extent(&map)))
+	if (XFS_IS_CORRUPT(mp, nmap == 0 || !xfs_bmap_is_written_extent(&map))) {
+		xfs_rt_mark_sick(mp, issum ? XFS_SICK_RT_SUMMARY :
+					     XFS_SICK_RT_BITMAP);
 		return -EFSCORRUPTED;
+	}
 
 	ASSERT(map.br_startblock != NULLFSBLOCK);
 	error = xfs_trans_read_buf(mp, args->tp, mp->m_ddev_targp,
 				   XFS_FSB_TO_DADDR(mp, map.br_startblock),
 				   mp->m_bsize, 0, &bp, &xfs_rtbuf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_rt_mark_sick(mp, issum ? XFS_SICK_RT_SUMMARY :
+					     XFS_SICK_RT_BITMAP);
 	if (error)
 		return error;
 

[PATCH 9/9] xfs: report XFS_IS_CORRUPT errors to the health system

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Whenever we encounter XFS_IS_CORRUPT failures, we should report that to
the health monitoring system for later reporting.

I started with this semantic patch and massaged everything until it
built:

@@
expression mp, test;
@@

- if (XFS_IS_CORRUPT(mp, test)) return -EFSCORRUPTED;
+ if (XFS_IS_CORRUPT(mp, test)) { xfs_btree_mark_sick(cur); return -EFSCORRUPTED; }

@@
expression mp, test;
identifier label, error;
@@

- if (XFS_IS_CORRUPT(mp, test)) { error = -EFSCORRUPTED; goto label; }
+ if (XFS_IS_CORRUPT(mp, test)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto label; }

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_ag.c          |    4 +-
 libxfs/xfs_alloc.c       |   97 ++++++++++++++++++++++++++++++++++++++--------
 libxfs/xfs_attr_remote.c |    8 +++-
 libxfs/xfs_bmap.c        |   94 ++++++++++++++++++++++++++++++++++++++++-----
 libxfs/xfs_btree.c       |   14 ++++++-
 libxfs/xfs_ialloc.c      |   52 ++++++++++++++++++++-----
 libxfs/xfs_refcount.c    |   37 +++++++++++++++++-
 libxfs/xfs_rmap.c        |   77 +++++++++++++++++++++++++++++++++++--
 8 files changed, 339 insertions(+), 44 deletions(-)


diff --git a/libxfs/xfs_ag.c b/libxfs/xfs_ag.c
index 9e638413df4..28a340d1122 100644
--- a/libxfs/xfs_ag.c
+++ b/libxfs/xfs_ag.c
@@ -929,8 +929,10 @@ xfs_ag_shrink_space(
 	agf = agfbp->b_addr;
 	aglen = be32_to_cpu(agi->agi_length);
 	/* some extra paranoid checks before we shrink the ag */
-	if (XFS_IS_CORRUPT(mp, agf->agf_length != agi->agi_length))
+	if (XFS_IS_CORRUPT(mp, agf->agf_length != agi->agi_length)) {
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGF);
 		return -EFSCORRUPTED;
+	}
 	if (delta >= aglen)
 		return -EINVAL;
 
diff --git a/libxfs/xfs_alloc.c b/libxfs/xfs_alloc.c
index aa084120c4c..3d7686eadab 100644
--- a/libxfs/xfs_alloc.c
+++ b/libxfs/xfs_alloc.c
@@ -495,14 +495,18 @@ xfs_alloc_fixup_trees(
 		if (XFS_IS_CORRUPT(mp,
 				   i != 1 ||
 				   nfbno1 != fbno ||
-				   nflen1 != flen))
+				   nflen1 != flen)) {
+			xfs_btree_mark_sick(cnt_cur);
 			return -EFSCORRUPTED;
+		}
 #endif
 	} else {
 		if ((error = xfs_alloc_lookup_eq(cnt_cur, fbno, flen, &i)))
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 1))
+		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			return -EFSCORRUPTED;
+		}
 	}
 	/*
 	 * Look up the record in the by-block tree if necessary.
@@ -514,14 +518,18 @@ xfs_alloc_fixup_trees(
 		if (XFS_IS_CORRUPT(mp,
 				   i != 1 ||
 				   nfbno1 != fbno ||
-				   nflen1 != flen))
+				   nflen1 != flen)) {
+			xfs_btree_mark_sick(bno_cur);
 			return -EFSCORRUPTED;
+		}
 #endif
 	} else {
 		if ((error = xfs_alloc_lookup_eq(bno_cur, fbno, flen, &i)))
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 1))
+		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(bno_cur);
 			return -EFSCORRUPTED;
+		}
 	}
 
 #ifdef DEBUG
@@ -534,8 +542,10 @@ xfs_alloc_fixup_trees(
 
 		if (XFS_IS_CORRUPT(mp,
 				   bnoblock->bb_numrecs !=
-				   cntblock->bb_numrecs))
+				   cntblock->bb_numrecs)) {
+			xfs_btree_mark_sick(bno_cur);
 			return -EFSCORRUPTED;
+		}
 	}
 #endif
 
@@ -565,30 +575,40 @@ xfs_alloc_fixup_trees(
 	 */
 	if ((error = xfs_btree_delete(cnt_cur, &i)))
 		return error;
-	if (XFS_IS_CORRUPT(mp, i != 1))
+	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cnt_cur);
 		return -EFSCORRUPTED;
+	}
 	/*
 	 * Add new by-size btree entry(s).
 	 */
 	if (nfbno1 != NULLAGBLOCK) {
 		if ((error = xfs_alloc_lookup_eq(cnt_cur, nfbno1, nflen1, &i)))
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 0))
+		if (XFS_IS_CORRUPT(mp, i != 0)) {
+			xfs_btree_mark_sick(cnt_cur);
 			return -EFSCORRUPTED;
+		}
 		if ((error = xfs_btree_insert(cnt_cur, &i)))
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 1))
+		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			return -EFSCORRUPTED;
+		}
 	}
 	if (nfbno2 != NULLAGBLOCK) {
 		if ((error = xfs_alloc_lookup_eq(cnt_cur, nfbno2, nflen2, &i)))
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 0))
+		if (XFS_IS_CORRUPT(mp, i != 0)) {
+			xfs_btree_mark_sick(cnt_cur);
 			return -EFSCORRUPTED;
+		}
 		if ((error = xfs_btree_insert(cnt_cur, &i)))
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 1))
+		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			return -EFSCORRUPTED;
+		}
 	}
 	/*
 	 * Fix up the by-block btree entry(s).
@@ -599,8 +619,10 @@ xfs_alloc_fixup_trees(
 		 */
 		if ((error = xfs_btree_delete(bno_cur, &i)))
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 1))
+		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(bno_cur);
 			return -EFSCORRUPTED;
+		}
 	} else {
 		/*
 		 * Update the by-block entry to start later|be shorter.
@@ -614,12 +636,16 @@ xfs_alloc_fixup_trees(
 		 */
 		if ((error = xfs_alloc_lookup_eq(bno_cur, nfbno2, nflen2, &i)))
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 0))
+		if (XFS_IS_CORRUPT(mp, i != 0)) {
+			xfs_btree_mark_sick(bno_cur);
 			return -EFSCORRUPTED;
+		}
 		if ((error = xfs_btree_insert(bno_cur, &i)))
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 1))
+		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(bno_cur);
 			return -EFSCORRUPTED;
+		}
 	}
 	return 0;
 }
@@ -892,8 +918,10 @@ xfs_alloc_cur_check(
 	error = xfs_alloc_get_rec(cur, &bno, &len, &i);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(args->mp, i != 1))
+	if (XFS_IS_CORRUPT(args->mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	/*
 	 * Check minlen and deactivate a cntbt cursor if out of acceptable size
@@ -1099,6 +1127,7 @@ xfs_alloc_ag_vextent_small(
 		if (error)
 			goto error;
 		if (XFS_IS_CORRUPT(args->mp, i != 1)) {
+			xfs_btree_mark_sick(ccur);
 			error = -EFSCORRUPTED;
 			goto error;
 		}
@@ -1133,6 +1162,7 @@ xfs_alloc_ag_vextent_small(
 	*fbnop = args->agbno = fbno;
 	*flenp = args->len = 1;
 	if (XFS_IS_CORRUPT(args->mp, fbno >= be32_to_cpu(agf->agf_length))) {
+		xfs_btree_mark_sick(ccur);
 		error = -EFSCORRUPTED;
 		goto error;
 	}
@@ -1219,6 +1249,7 @@ xfs_alloc_ag_vextent_exact(
 	if (error)
 		goto error0;
 	if (XFS_IS_CORRUPT(args->mp, i != 1)) {
+		xfs_btree_mark_sick(bno_cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -1498,8 +1529,10 @@ xfs_alloc_ag_vextent_lastblock(
 			error = xfs_alloc_get_rec(acur->cnt, bno, len, &i);
 			if (error)
 				return error;
-			if (XFS_IS_CORRUPT(args->mp, i != 1))
+			if (XFS_IS_CORRUPT(args->mp, i != 1)) {
+				xfs_btree_mark_sick(acur->cnt);
 				return -EFSCORRUPTED;
+			}
 			if (*len >= args->minlen)
 				break;
 			error = xfs_btree_increment(acur->cnt, 0, &i);
@@ -1711,6 +1744,7 @@ xfs_alloc_ag_vextent_size(
 			if (error)
 				goto error0;
 			if (XFS_IS_CORRUPT(args->mp, i != 1)) {
+				xfs_btree_mark_sick(cnt_cur);
 				error = -EFSCORRUPTED;
 				goto error0;
 			}
@@ -1757,6 +1791,7 @@ xfs_alloc_ag_vextent_size(
 			   rlen != 0 &&
 			   (rlen > flen ||
 			    rbno + rlen > fbno + flen))) {
+		xfs_btree_mark_sick(cnt_cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -1779,6 +1814,7 @@ xfs_alloc_ag_vextent_size(
 					&i)))
 				goto error0;
 			if (XFS_IS_CORRUPT(args->mp, i != 1)) {
+				xfs_btree_mark_sick(cnt_cur);
 				error = -EFSCORRUPTED;
 				goto error0;
 			}
@@ -1791,6 +1827,7 @@ xfs_alloc_ag_vextent_size(
 					   rlen != 0 &&
 					   (rlen > flen ||
 					    rbno + rlen > fbno + flen))) {
+				xfs_btree_mark_sick(cnt_cur);
 				error = -EFSCORRUPTED;
 				goto error0;
 			}
@@ -1807,6 +1844,7 @@ xfs_alloc_ag_vextent_size(
 				&i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(args->mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -1845,6 +1883,7 @@ xfs_alloc_ag_vextent_size(
 
 	rlen = args->len;
 	if (XFS_IS_CORRUPT(args->mp, rlen > flen)) {
+		xfs_btree_mark_sick(cnt_cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -1864,6 +1903,7 @@ xfs_alloc_ag_vextent_size(
 	if (XFS_IS_CORRUPT(args->mp,
 			   args->agbno + args->len >
 			   be32_to_cpu(agf->agf_length))) {
+		xfs_ag_mark_sick(args->pag, XFS_SICK_AG_BNOBT);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -1939,6 +1979,7 @@ xfs_free_ag_extent(
 		if ((error = xfs_alloc_get_rec(bno_cur, &ltbno, &ltlen, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(bno_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -1954,6 +1995,7 @@ xfs_free_ag_extent(
 			 * Very bad.
 			 */
 			if (XFS_IS_CORRUPT(mp, ltbno + ltlen > bno)) {
+				xfs_btree_mark_sick(bno_cur);
 				error = -EFSCORRUPTED;
 				goto error0;
 			}
@@ -1972,6 +2014,7 @@ xfs_free_ag_extent(
 		if ((error = xfs_alloc_get_rec(bno_cur, &gtbno, &gtlen, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(bno_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -1987,6 +2030,7 @@ xfs_free_ag_extent(
 			 * Very bad.
 			 */
 			if (XFS_IS_CORRUPT(mp, bno + len > gtbno)) {
+				xfs_btree_mark_sick(bno_cur);
 				error = -EFSCORRUPTED;
 				goto error0;
 			}
@@ -2007,12 +2051,14 @@ xfs_free_ag_extent(
 		if ((error = xfs_alloc_lookup_eq(cnt_cur, ltbno, ltlen, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
 		if ((error = xfs_btree_delete(cnt_cur, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -2022,12 +2068,14 @@ xfs_free_ag_extent(
 		if ((error = xfs_alloc_lookup_eq(cnt_cur, gtbno, gtlen, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
 		if ((error = xfs_btree_delete(cnt_cur, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -2037,6 +2085,7 @@ xfs_free_ag_extent(
 		if ((error = xfs_btree_delete(bno_cur, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(bno_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -2046,6 +2095,7 @@ xfs_free_ag_extent(
 		if ((error = xfs_btree_decrement(bno_cur, 0, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(bno_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -2065,6 +2115,7 @@ xfs_free_ag_extent(
 					   i != 1 ||
 					   xxbno != ltbno ||
 					   xxlen != ltlen)) {
+				xfs_btree_mark_sick(bno_cur);
 				error = -EFSCORRUPTED;
 				goto error0;
 			}
@@ -2089,12 +2140,14 @@ xfs_free_ag_extent(
 		if ((error = xfs_alloc_lookup_eq(cnt_cur, ltbno, ltlen, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
 		if ((error = xfs_btree_delete(cnt_cur, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -2105,6 +2158,7 @@ xfs_free_ag_extent(
 		if ((error = xfs_btree_decrement(bno_cur, 0, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(bno_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -2124,12 +2178,14 @@ xfs_free_ag_extent(
 		if ((error = xfs_alloc_lookup_eq(cnt_cur, gtbno, gtlen, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
 		if ((error = xfs_btree_delete(cnt_cur, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cnt_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -2152,6 +2208,7 @@ xfs_free_ag_extent(
 		if ((error = xfs_btree_insert(bno_cur, &i)))
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(bno_cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -2164,12 +2221,14 @@ xfs_free_ag_extent(
 	if ((error = xfs_alloc_lookup_eq(cnt_cur, nbno, nlen, &i)))
 		goto error0;
 	if (XFS_IS_CORRUPT(mp, i != 0)) {
+		xfs_btree_mark_sick(cnt_cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
 	if ((error = xfs_btree_insert(cnt_cur, &i)))
 		goto error0;
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cnt_cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -3899,17 +3958,23 @@ __xfs_free_extent(
 		return -EIO;
 
 	error = xfs_free_extent_fix_freelist(tp, pag, &agbp);
-	if (error)
+	if (error) {
+		if (xfs_metadata_is_sick(error))
+			xfs_ag_mark_sick(pag, XFS_SICK_AG_BNOBT);
 		return error;
+	}
+
 	agf = agbp->b_addr;
 
 	if (XFS_IS_CORRUPT(mp, agbno >= mp->m_sb.sb_agblocks)) {
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_BNOBT);
 		error = -EFSCORRUPTED;
 		goto err_release;
 	}
 
 	/* validate the extent size is legal now we have the agf locked */
 	if (XFS_IS_CORRUPT(mp, agbno + len > be32_to_cpu(agf->agf_length))) {
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_BNOBT);
 		error = -EFSCORRUPTED;
 		goto err_release;
 	}
diff --git a/libxfs/xfs_attr_remote.c b/libxfs/xfs_attr_remote.c
index a67caf5e86f..f1c7cd31459 100644
--- a/libxfs/xfs_attr_remote.c
+++ b/libxfs/xfs_attr_remote.c
@@ -552,8 +552,10 @@ xfs_attr_rmtval_stale(
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 
 	if (XFS_IS_CORRUPT(mp, map->br_startblock == DELAYSTARTBLOCK) ||
-	    XFS_IS_CORRUPT(mp, map->br_startblock == HOLESTARTBLOCK))
+	    XFS_IS_CORRUPT(mp, map->br_startblock == HOLESTARTBLOCK)) {
+		xfs_bmap_mark_sick(ip, XFS_ATTR_FORK);
 		return -EFSCORRUPTED;
+	}
 
 	error = xfs_buf_incore(mp->m_ddev_targp,
 			XFS_FSB_TO_DADDR(mp, map->br_startblock),
@@ -663,8 +665,10 @@ xfs_attr_rmtval_invalidate(
 				       blkcnt, &map, &nmap, XFS_BMAPI_ATTRFORK);
 		if (error)
 			return error;
-		if (XFS_IS_CORRUPT(args->dp->i_mount, nmap != 1))
+		if (XFS_IS_CORRUPT(args->dp->i_mount, nmap != 1)) {
+			xfs_bmap_mark_sick(args->dp, XFS_ATTR_FORK);
 			return -EFSCORRUPTED;
+		}
 		error = xfs_attr_rmtval_stale(args->dp, &map, XBF_TRYLOCK);
 		if (error)
 			return error;
diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index 04d7566bc82..51bb4972f03 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -380,6 +380,7 @@ xfs_bmap_check_leaf_extents(
 		pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
 		bno = be64_to_cpu(*pp);
 		if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbno(mp, bno))) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -561,8 +562,10 @@ xfs_bmap_btree_to_extents(
 	pp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, ifp->if_broot_bytes);
 	cbno = be64_to_cpu(*pp);
 #ifdef DEBUG
-	if (XFS_IS_CORRUPT(cur->bc_mp, !xfs_btree_check_lptr(cur, cbno, 1)))
+	if (XFS_IS_CORRUPT(cur->bc_mp, !xfs_btree_check_lptr(cur, cbno, 1))) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 #endif
 	error = xfs_btree_read_bufl(mp, tp, cbno, &cbp, XFS_BMAP_BTREE_REF,
 				&xfs_bmbt_buf_ops);
@@ -879,6 +882,7 @@ xfs_bmap_add_attrfork_btree(
 			goto error0;
 		/* must be at least one entry */
 		if (XFS_IS_CORRUPT(mp, stat != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -1205,6 +1209,7 @@ xfs_iread_extents(
 		goto out;
 
 	if (XFS_IS_CORRUPT(mp, ir.loaded != ifp->if_nextents)) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		error = -EFSCORRUPTED;
 		goto out;
 	}
@@ -1395,8 +1400,10 @@ xfs_bmap_last_offset(
 	if (ifp->if_format == XFS_DINODE_FMT_LOCAL)
 		return 0;
 
-	if (XFS_IS_CORRUPT(ip->i_mount, !xfs_ifork_has_extents(ifp)))
+	if (XFS_IS_CORRUPT(ip->i_mount, !xfs_ifork_has_extents(ifp))) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		return -EFSCORRUPTED;
+	}
 
 	error = xfs_bmap_last_extent(NULL, ip, whichfork, &rec, &is_empty);
 	if (error || is_empty)
@@ -1535,6 +1542,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1542,6 +1550,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1549,6 +1558,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1578,6 +1588,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1611,6 +1622,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1639,6 +1651,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 0)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1646,6 +1659,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1680,6 +1694,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1705,6 +1720,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 0)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1712,6 +1728,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1756,6 +1773,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1792,6 +1810,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 0)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1799,6 +1818,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1878,6 +1898,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 0)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -1885,6 +1906,7 @@ xfs_bmap_add_extent_delay_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(bma->cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2081,30 +2103,35 @@ xfs_bmap_add_extent_unwritten_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
 			if ((error = xfs_btree_delete(cur, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
 			if ((error = xfs_btree_decrement(cur, 0, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
 			if ((error = xfs_btree_delete(cur, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
 			if ((error = xfs_btree_decrement(cur, 0, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2133,18 +2160,21 @@ xfs_bmap_add_extent_unwritten_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
 			if ((error = xfs_btree_delete(cur, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
 			if ((error = xfs_btree_decrement(cur, 0, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2176,18 +2206,21 @@ xfs_bmap_add_extent_unwritten_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
 			if ((error = xfs_btree_delete(cur, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
 			if ((error = xfs_btree_decrement(cur, 0, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2214,6 +2247,7 @@ xfs_bmap_add_extent_unwritten_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2247,6 +2281,7 @@ xfs_bmap_add_extent_unwritten_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2284,6 +2319,7 @@ xfs_bmap_add_extent_unwritten_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2294,6 +2330,7 @@ xfs_bmap_add_extent_unwritten_real(
 			if ((error = xfs_btree_insert(cur, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2324,6 +2361,7 @@ xfs_bmap_add_extent_unwritten_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2360,6 +2398,7 @@ xfs_bmap_add_extent_unwritten_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2370,12 +2409,14 @@ xfs_bmap_add_extent_unwritten_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 0)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
 			if ((error = xfs_btree_insert(cur, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2412,6 +2453,7 @@ xfs_bmap_add_extent_unwritten_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2424,6 +2466,7 @@ xfs_bmap_add_extent_unwritten_real(
 			if ((error = xfs_btree_insert(cur, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2436,6 +2479,7 @@ xfs_bmap_add_extent_unwritten_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 0)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2443,6 +2487,7 @@ xfs_bmap_add_extent_unwritten_real(
 			if ((error = xfs_btree_insert(cur, &i)))
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2728,6 +2773,7 @@ xfs_bmap_add_extent_hole_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2735,6 +2781,7 @@ xfs_bmap_add_extent_hole_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2742,6 +2789,7 @@ xfs_bmap_add_extent_hole_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2771,6 +2819,7 @@ xfs_bmap_add_extent_hole_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2801,6 +2850,7 @@ xfs_bmap_add_extent_hole_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2827,6 +2877,7 @@ xfs_bmap_add_extent_hole_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 0)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -2834,6 +2885,7 @@ xfs_bmap_add_extent_hole_real(
 			if (error)
 				goto done;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto done;
 			}
@@ -5088,8 +5140,10 @@ xfs_bmap_del_extent_real(
 		error = xfs_bmbt_lookup_eq(cur, &got, &i);
 		if (error)
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 1))
+		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			return -EFSCORRUPTED;
+		}
 	}
 
 	if (got.br_startoff == del->br_startoff)
@@ -5113,8 +5167,10 @@ xfs_bmap_del_extent_real(
 		}
 		if ((error = xfs_btree_delete(cur, &i)))
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 1))
+		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			return -EFSCORRUPTED;
+		}
 		break;
 	case BMAP_LEFT_FILLING:
 		/*
@@ -5186,8 +5242,10 @@ xfs_bmap_del_extent_real(
 				error = xfs_bmbt_lookup_eq(cur, &got, &i);
 				if (error)
 					return error;
-				if (XFS_IS_CORRUPT(mp, i != 1))
+				if (XFS_IS_CORRUPT(mp, i != 1)) {
+					xfs_btree_mark_sick(cur);
 					return -EFSCORRUPTED;
+				}
 				/*
 				 * Update the btree record back
 				 * to the original value.
@@ -5203,8 +5261,10 @@ xfs_bmap_del_extent_real(
 				*logflagsp = 0;
 				return -ENOSPC;
 			}
-			if (XFS_IS_CORRUPT(mp, i != 1))
+			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				return -EFSCORRUPTED;
+			}
 		} else
 			*logflagsp |= xfs_ilog_fext(whichfork);
 
@@ -5659,21 +5719,27 @@ xfs_bmse_merge(
 	error = xfs_bmbt_lookup_eq(cur, got, &i);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(mp, i != 1))
+	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	error = xfs_btree_delete(cur, &i);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(mp, i != 1))
+	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	/* lookup and update size of the previous extent */
 	error = xfs_bmbt_lookup_eq(cur, left, &i);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(mp, i != 1))
+	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	error = xfs_bmbt_update(cur, &new);
 	if (error)
@@ -5721,8 +5787,10 @@ xfs_bmap_shift_update_extent(
 		error = xfs_bmbt_lookup_eq(cur, &prev, &i);
 		if (error)
 			return error;
-		if (XFS_IS_CORRUPT(mp, i != 1))
+		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			return -EFSCORRUPTED;
+		}
 
 		error = xfs_bmbt_update(cur, got);
 		if (error)
@@ -5783,6 +5851,7 @@ xfs_bmap_collapse_extents(
 		goto del_cursor;
 	}
 	if (XFS_IS_CORRUPT(mp, isnullstartblock(got.br_startblock))) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		error = -EFSCORRUPTED;
 		goto del_cursor;
 	}
@@ -5908,11 +5977,13 @@ xfs_bmap_insert_extents(
 		}
 	}
 	if (XFS_IS_CORRUPT(mp, isnullstartblock(got.br_startblock))) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		error = -EFSCORRUPTED;
 		goto del_cursor;
 	}
 
 	if (XFS_IS_CORRUPT(mp, stop_fsb > got.br_startoff)) {
+		xfs_bmap_mark_sick(ip, whichfork);
 		error = -EFSCORRUPTED;
 		goto del_cursor;
 	}
@@ -6012,6 +6083,7 @@ xfs_bmap_split_extent(
 		if (error)
 			goto del_cursor;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto del_cursor;
 		}
@@ -6039,6 +6111,7 @@ xfs_bmap_split_extent(
 		if (error)
 			goto del_cursor;
 		if (XFS_IS_CORRUPT(mp, i != 0)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto del_cursor;
 		}
@@ -6046,6 +6119,7 @@ xfs_bmap_split_extent(
 		if (error)
 			goto del_cursor;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto del_cursor;
 		}
diff --git a/libxfs/xfs_btree.c b/libxfs/xfs_btree.c
index 691d8dda420..4b4099c5635 100644
--- a/libxfs/xfs_btree.c
+++ b/libxfs/xfs_btree.c
@@ -2023,8 +2023,10 @@ xfs_btree_lookup(
 			error = xfs_btree_increment(cur, 0, &i);
 			if (error)
 				goto error0;
-			if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+			if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				return -EFSCORRUPTED;
+			}
 			*stat = 1;
 			return 0;
 		}
@@ -2477,6 +2479,7 @@ xfs_btree_lshift(
 			goto error0;
 		i = xfs_btree_firstrec(tcur, level);
 		if (XFS_IS_CORRUPT(tcur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -2647,6 +2650,7 @@ xfs_btree_rshift(
 		goto error0;
 	i = xfs_btree_lastrec(tcur, level);
 	if (XFS_IS_CORRUPT(tcur->bc_mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -3535,6 +3539,7 @@ xfs_btree_insert(
 		}
 
 		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -3942,6 +3947,7 @@ xfs_btree_delrec(
 		 */
 		i = xfs_btree_lastrec(tcur, level);
 		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -3950,12 +3956,14 @@ xfs_btree_delrec(
 		if (error)
 			goto error0;
 		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
 
 		i = xfs_btree_lastrec(tcur, level);
 		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -4003,6 +4011,7 @@ xfs_btree_delrec(
 		if (!xfs_btree_ptr_is_null(cur, &lptr)) {
 			i = xfs_btree_firstrec(tcur, level);
 			if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto error0;
 			}
@@ -4011,6 +4020,7 @@ xfs_btree_delrec(
 			if (error)
 				goto error0;
 			if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto error0;
 			}
@@ -4028,6 +4038,7 @@ xfs_btree_delrec(
 		 */
 		i = xfs_btree_firstrec(tcur, level);
 		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -4037,6 +4048,7 @@ xfs_btree_delrec(
 			goto error0;
 		i = xfs_btree_firstrec(tcur, level);
 		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
diff --git a/libxfs/xfs_ialloc.c b/libxfs/xfs_ialloc.c
index 63922f44ffe..21577a50f65 100644
--- a/libxfs/xfs_ialloc.c
+++ b/libxfs/xfs_ialloc.c
@@ -568,6 +568,7 @@ xfs_inobt_insert_sprec(
 		if (error)
 			goto error;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error;
 		}
@@ -584,10 +585,12 @@ xfs_inobt_insert_sprec(
 		if (error)
 			goto error;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error;
 		}
 		if (XFS_IS_CORRUPT(mp, rec.ir_startino != nrec->ir_startino)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error;
 		}
@@ -597,6 +600,7 @@ xfs_inobt_insert_sprec(
 		 * cannot merge, something is seriously wrong.
 		 */
 		if (XFS_IS_CORRUPT(mp, !__xfs_inobt_can_merge(nrec, &rec))) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error;
 		}
@@ -946,8 +950,10 @@ xfs_ialloc_next_rec(
 		error = xfs_inobt_get_rec(cur, rec, &i);
 		if (error)
 			return error;
-		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			return -EFSCORRUPTED;
+		}
 	}
 
 	return 0;
@@ -971,8 +977,10 @@ xfs_ialloc_get_rec(
 		error = xfs_inobt_get_rec(cur, rec, &i);
 		if (error)
 			return error;
-		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			return -EFSCORRUPTED;
+		}
 	}
 
 	return 0;
@@ -1050,6 +1058,7 @@ xfs_dialloc_ag_inobt(
 		if (error)
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -1058,6 +1067,7 @@ xfs_dialloc_ag_inobt(
 		if (error)
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, j != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -1216,6 +1226,7 @@ xfs_dialloc_ag_inobt(
 	if (error)
 		goto error0;
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -1225,6 +1236,7 @@ xfs_dialloc_ag_inobt(
 		if (error)
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -1234,6 +1246,7 @@ xfs_dialloc_ag_inobt(
 		if (error)
 			goto error0;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error0;
 		}
@@ -1294,8 +1307,10 @@ xfs_dialloc_ag_finobt_near(
 		error = xfs_inobt_get_rec(lcur, rec, &i);
 		if (error)
 			return error;
-		if (XFS_IS_CORRUPT(lcur->bc_mp, i != 1))
+		if (XFS_IS_CORRUPT(lcur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(lcur);
 			return -EFSCORRUPTED;
+		}
 
 		/*
 		 * See if we've landed in the parent inode record. The finobt
@@ -1319,12 +1334,14 @@ xfs_dialloc_ag_finobt_near(
 		if (error)
 			goto error_rcur;
 		if (XFS_IS_CORRUPT(lcur->bc_mp, j != 1)) {
+			xfs_btree_mark_sick(lcur);
 			error = -EFSCORRUPTED;
 			goto error_rcur;
 		}
 	}
 
 	if (XFS_IS_CORRUPT(lcur->bc_mp, i != 1 && j != 1)) {
+		xfs_btree_mark_sick(lcur);
 		error = -EFSCORRUPTED;
 		goto error_rcur;
 	}
@@ -1380,8 +1397,10 @@ xfs_dialloc_ag_finobt_newino(
 			error = xfs_inobt_get_rec(cur, rec, &i);
 			if (error)
 				return error;
-			if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+			if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				return -EFSCORRUPTED;
+			}
 			return 0;
 		}
 	}
@@ -1392,14 +1411,18 @@ xfs_dialloc_ag_finobt_newino(
 	error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &i);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	error = xfs_inobt_get_rec(cur, rec, &i);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	return 0;
 }
@@ -1421,14 +1444,18 @@ xfs_dialloc_ag_update_inobt(
 	error = xfs_inobt_lookup(cur, frec->ir_startino, XFS_LOOKUP_EQ, &i);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	error = xfs_inobt_get_rec(cur, &rec, &i);
 	if (error)
 		return error;
-	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 	ASSERT((XFS_AGINO_TO_OFFSET(cur->bc_mp, rec.ir_startino) %
 				   XFS_INODES_PER_CHUNK) == 0);
 
@@ -1437,8 +1464,10 @@ xfs_dialloc_ag_update_inobt(
 
 	if (XFS_IS_CORRUPT(cur->bc_mp,
 			   rec.ir_free != frec->ir_free ||
-			   rec.ir_freecount != frec->ir_freecount))
+			   rec.ir_freecount != frec->ir_freecount)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	return xfs_inobt_update(cur, &rec);
 }
@@ -1955,6 +1984,7 @@ xfs_difree_inobt(
 		goto error0;
 	}
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -1965,6 +1995,7 @@ xfs_difree_inobt(
 		goto error0;
 	}
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -2077,6 +2108,7 @@ xfs_difree_finobt(
 		 * something is out of sync.
 		 */
 		if (XFS_IS_CORRUPT(mp, ibtrec->ir_freecount != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto error;
 		}
@@ -2103,6 +2135,7 @@ xfs_difree_finobt(
 	if (error)
 		goto error;
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error;
 	}
@@ -2113,6 +2146,7 @@ xfs_difree_finobt(
 	if (XFS_IS_CORRUPT(mp,
 			   rec.ir_free != ibtrec->ir_free ||
 			   rec.ir_freecount != ibtrec->ir_freecount)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error;
 	}
diff --git a/libxfs/xfs_refcount.c b/libxfs/xfs_refcount.c
index 3d66e89b00f..fe63b9eec8a 100644
--- a/libxfs/xfs_refcount.c
+++ b/libxfs/xfs_refcount.c
@@ -239,6 +239,7 @@ xfs_refcount_insert(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, *i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -269,12 +270,14 @@ xfs_refcount_delete(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
 	trace_xfs_refcount_delete(cur->bc_mp, cur->bc_ag.pag->pag_agno, &irec);
 	error = xfs_btree_delete(cur, i);
 	if (XFS_IS_CORRUPT(cur->bc_mp, *i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -399,6 +402,7 @@ xfs_refcount_split_extent(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -426,6 +430,7 @@ xfs_refcount_split_extent(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -471,6 +476,7 @@ xfs_refcount_merge_center_extents(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -479,6 +485,7 @@ xfs_refcount_merge_center_extents(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -488,6 +495,7 @@ xfs_refcount_merge_center_extents(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -499,6 +507,7 @@ xfs_refcount_merge_center_extents(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -543,6 +552,7 @@ xfs_refcount_merge_left_extent(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -551,6 +561,7 @@ xfs_refcount_merge_left_extent(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -562,6 +573,7 @@ xfs_refcount_merge_left_extent(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -609,6 +621,7 @@ xfs_refcount_merge_right_extent(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -617,6 +630,7 @@ xfs_refcount_merge_right_extent(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -628,6 +642,7 @@ xfs_refcount_merge_right_extent(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -675,6 +690,7 @@ xfs_refcount_find_left_extents(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -694,6 +710,7 @@ xfs_refcount_find_left_extents(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -768,6 +785,7 @@ xfs_refcount_find_right_extents(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -787,6 +805,7 @@ xfs_refcount_find_right_extents(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -1143,6 +1162,7 @@ xfs_refcount_adjust_extents(
 					goto out_error;
 				if (XFS_IS_CORRUPT(cur->bc_mp,
 						   found_tmp != 1)) {
+					xfs_btree_mark_sick(cur);
 					error = -EFSCORRUPTED;
 					goto out_error;
 				}
@@ -1181,6 +1201,7 @@ xfs_refcount_adjust_extents(
 		 */
 		if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount == 0) ||
 		    XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount > *aglen)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -1204,6 +1225,7 @@ xfs_refcount_adjust_extents(
 			if (error)
 				goto out_error;
 			if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto out_error;
 			}
@@ -1328,8 +1350,10 @@ xfs_refcount_continue_op(
 	struct xfs_perag		*pag = cur->bc_ag.pag;
 
 	if (XFS_IS_CORRUPT(mp, !xfs_verify_agbext(pag, new_agbno,
-					ri->ri_blockcount)))
+					ri->ri_blockcount))) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	ri->ri_startblock = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno);
 
@@ -1536,6 +1560,7 @@ xfs_refcount_find_shared(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -1553,6 +1578,7 @@ xfs_refcount_find_shared(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -1586,6 +1612,7 @@ xfs_refcount_find_shared(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -1683,6 +1710,7 @@ xfs_refcount_adjust_cow_extents(
 		goto out_error;
 	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec &&
 				ext.rc_domain != XFS_REFC_DOMAIN_COW)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -1698,6 +1726,7 @@ xfs_refcount_adjust_cow_extents(
 		/* Adding a CoW reservation, there should be nothing here. */
 		if (XFS_IS_CORRUPT(cur->bc_mp,
 				   agbno + aglen > ext.rc_startblock)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -1715,6 +1744,7 @@ xfs_refcount_adjust_cow_extents(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, found_tmp != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -1722,14 +1752,17 @@ xfs_refcount_adjust_cow_extents(
 	case XFS_REFCOUNT_ADJUST_COW_FREE:
 		/* Removing a CoW reservation, there should be one extent. */
 		if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_startblock != agbno)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
 		if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount != aglen)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
 		if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_refcount != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -1741,6 +1774,7 @@ xfs_refcount_adjust_cow_extents(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -1903,6 +1937,7 @@ xfs_refcount_recover_extent(
 	if (xfs_refcount_check_irec(cur->bc_ag.pag, &rr->rr_rrec) != NULL ||
 	    XFS_IS_CORRUPT(cur->bc_mp,
 			   rr->rr_rrec.rc_domain != XFS_REFC_DOMAIN_COW)) {
+		xfs_btree_mark_sick(cur);
 		kfree(rr);
 		return -EFSCORRUPTED;
 	}
diff --git a/libxfs/xfs_rmap.c b/libxfs/xfs_rmap.c
index 9373b1102fd..0b462d17838 100644
--- a/libxfs/xfs_rmap.c
+++ b/libxfs/xfs_rmap.c
@@ -134,6 +134,7 @@ xfs_rmap_insert(
 	if (error)
 		goto done;
 	if (XFS_IS_CORRUPT(rcur->bc_mp, i != 0)) {
+		xfs_btree_mark_sick(rcur);
 		error = -EFSCORRUPTED;
 		goto done;
 	}
@@ -147,6 +148,7 @@ xfs_rmap_insert(
 	if (error)
 		goto done;
 	if (XFS_IS_CORRUPT(rcur->bc_mp, i != 1)) {
+		xfs_btree_mark_sick(rcur);
 		error = -EFSCORRUPTED;
 		goto done;
 	}
@@ -176,6 +178,7 @@ xfs_rmap_delete(
 	if (error)
 		goto done;
 	if (XFS_IS_CORRUPT(rcur->bc_mp, i != 1)) {
+		xfs_btree_mark_sick(rcur);
 		error = -EFSCORRUPTED;
 		goto done;
 	}
@@ -184,6 +187,7 @@ xfs_rmap_delete(
 	if (error)
 		goto done;
 	if (XFS_IS_CORRUPT(rcur->bc_mp, i != 1)) {
+		xfs_btree_mark_sick(rcur);
 		error = -EFSCORRUPTED;
 		goto done;
 	}
@@ -515,7 +519,7 @@ xfs_rmap_lookup_le_range(
  */
 static int
 xfs_rmap_free_check_owner(
-	struct xfs_mount	*mp,
+	struct xfs_btree_cur	*cur,
 	uint64_t		ltoff,
 	struct xfs_rmap_irec	*rec,
 	xfs_filblks_t		len,
@@ -523,6 +527,7 @@ xfs_rmap_free_check_owner(
 	uint64_t		offset,
 	unsigned int		flags)
 {
+	struct xfs_mount	*mp = cur->bc_mp;
 	int			error = 0;
 
 	if (owner == XFS_RMAP_OWN_UNKNOWN)
@@ -532,12 +537,14 @@ xfs_rmap_free_check_owner(
 	if (XFS_IS_CORRUPT(mp,
 			   (flags & XFS_RMAP_UNWRITTEN) !=
 			   (rec->rm_flags & XFS_RMAP_UNWRITTEN))) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out;
 	}
 
 	/* Make sure the owner matches what we expect to find in the tree. */
 	if (XFS_IS_CORRUPT(mp, owner != rec->rm_owner)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out;
 	}
@@ -549,16 +556,19 @@ xfs_rmap_free_check_owner(
 	if (flags & XFS_RMAP_BMBT_BLOCK) {
 		if (XFS_IS_CORRUPT(mp,
 				   !(rec->rm_flags & XFS_RMAP_BMBT_BLOCK))) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out;
 		}
 	} else {
 		if (XFS_IS_CORRUPT(mp, rec->rm_offset > offset)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out;
 		}
 		if (XFS_IS_CORRUPT(mp,
 				   offset + len > ltoff + rec->rm_blockcount)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out;
 		}
@@ -621,6 +631,7 @@ xfs_rmap_unmap(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -642,6 +653,7 @@ xfs_rmap_unmap(
 		if (XFS_IS_CORRUPT(mp,
 				   bno <
 				   ltrec.rm_startblock + ltrec.rm_blockcount)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -668,6 +680,7 @@ xfs_rmap_unmap(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -680,12 +693,13 @@ xfs_rmap_unmap(
 			   ltrec.rm_startblock > bno ||
 			   ltrec.rm_startblock + ltrec.rm_blockcount <
 			   bno + len)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
 
 	/* Check owner information. */
-	error = xfs_rmap_free_check_owner(mp, ltoff, &ltrec, len, owner,
+	error = xfs_rmap_free_check_owner(cur, ltoff, &ltrec, len, owner,
 			offset, flags);
 	if (error)
 		goto out_error;
@@ -700,6 +714,7 @@ xfs_rmap_unmap(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -903,6 +918,7 @@ xfs_rmap_map(
 	if (XFS_IS_CORRUPT(mp,
 			   have_lt != 0 &&
 			   ltrec.rm_startblock + ltrec.rm_blockcount > bno)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -920,10 +936,12 @@ xfs_rmap_map(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(mp, have_gt != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
 		if (XFS_IS_CORRUPT(mp, bno + len > gtrec.rm_startblock)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -977,6 +995,7 @@ xfs_rmap_map(
 			if (error)
 				goto out_error;
 			if (XFS_IS_CORRUPT(mp, i != 1)) {
+				xfs_btree_mark_sick(cur);
 				error = -EFSCORRUPTED;
 				goto out_error;
 			}
@@ -1024,6 +1043,7 @@ xfs_rmap_map(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -1119,6 +1139,7 @@ xfs_rmap_convert(
 	if (error)
 		goto done;
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto done;
 	}
@@ -1156,12 +1177,14 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
 		if (XFS_IS_CORRUPT(mp,
 				   LEFT.rm_startblock + LEFT.rm_blockcount >
 				   bno)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1184,6 +1207,7 @@ xfs_rmap_convert(
 	if (error)
 		goto done;
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto done;
 	}
@@ -1196,10 +1220,12 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
 		if (XFS_IS_CORRUPT(mp, bno + len > RIGHT.rm_startblock)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1230,6 +1256,7 @@ xfs_rmap_convert(
 	if (error)
 		goto done;
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto done;
 	}
@@ -1249,6 +1276,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1260,6 +1288,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1267,6 +1296,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1278,6 +1308,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1285,6 +1316,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1308,6 +1340,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1315,6 +1348,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1334,6 +1368,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1345,6 +1380,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1352,6 +1388,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1422,6 +1459,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1464,6 +1502,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 0)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1479,6 +1518,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1512,6 +1552,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1525,6 +1566,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 0)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1537,6 +1579,7 @@ xfs_rmap_convert(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1609,6 +1652,7 @@ xfs_rmap_convert_shared(
 	if (error)
 		goto done;
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto done;
 	}
@@ -1637,6 +1681,7 @@ xfs_rmap_convert_shared(
 		if (XFS_IS_CORRUPT(mp,
 				   LEFT.rm_startblock + LEFT.rm_blockcount >
 				   bno)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1655,10 +1700,12 @@ xfs_rmap_convert_shared(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
 		if (XFS_IS_CORRUPT(mp, bno + len > RIGHT.rm_startblock)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1709,6 +1756,7 @@ xfs_rmap_convert_shared(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1735,6 +1783,7 @@ xfs_rmap_convert_shared(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1761,6 +1810,7 @@ xfs_rmap_convert_shared(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1784,6 +1834,7 @@ xfs_rmap_convert_shared(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1819,6 +1870,7 @@ xfs_rmap_convert_shared(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1864,6 +1916,7 @@ xfs_rmap_convert_shared(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1899,6 +1952,7 @@ xfs_rmap_convert_shared(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -1937,6 +1991,7 @@ xfs_rmap_convert_shared(
 		if (error)
 			goto done;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto done;
 		}
@@ -2026,6 +2081,7 @@ xfs_rmap_unmap_shared(
 	if (error)
 		goto out_error;
 	if (XFS_IS_CORRUPT(mp, i != 1)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -2036,12 +2092,14 @@ xfs_rmap_unmap_shared(
 			   ltrec.rm_startblock > bno ||
 			   ltrec.rm_startblock + ltrec.rm_blockcount <
 			   bno + len)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
 
 	/* Make sure the owner matches what we expect to find in the tree. */
 	if (XFS_IS_CORRUPT(mp, owner != ltrec.rm_owner)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -2050,16 +2108,19 @@ xfs_rmap_unmap_shared(
 	if (XFS_IS_CORRUPT(mp,
 			   (flags & XFS_RMAP_UNWRITTEN) !=
 			   (ltrec.rm_flags & XFS_RMAP_UNWRITTEN))) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
 
 	/* Check the offset. */
 	if (XFS_IS_CORRUPT(mp, ltrec.rm_offset > offset)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
 	if (XFS_IS_CORRUPT(mp, offset > ltoff + ltrec.rm_blockcount)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto out_error;
 	}
@@ -2116,6 +2177,7 @@ xfs_rmap_unmap_shared(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -2145,6 +2207,7 @@ xfs_rmap_unmap_shared(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -2224,6 +2287,7 @@ xfs_rmap_map_shared(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(mp, have_gt != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -2276,6 +2340,7 @@ xfs_rmap_map_shared(
 		if (error)
 			goto out_error;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			goto out_error;
 		}
@@ -2479,10 +2544,14 @@ xfs_rmap_finish_one(
 		 * allocate blocks.
 		 */
 		error = xfs_free_extent_fix_freelist(tp, ri->ri_pag, &agbp);
-		if (error)
+		if (error) {
+			xfs_ag_mark_sick(ri->ri_pag, XFS_SICK_AG_AGFL);
 			return error;
-		if (XFS_IS_CORRUPT(tp->t_mountp, !agbp))
+		}
+		if (XFS_IS_CORRUPT(tp->t_mountp, !agbp)) {
+			xfs_ag_mark_sick(ri->ri_pag, XFS_SICK_AG_AGFL);
 			return -EFSCORRUPTED;
+		}
 
 		rcur = xfs_rmapbt_init_cursor(mp, tp, agbp, ri->ri_pag);
 	}

[PATCH 1/4] xfs: add secondary and indirect classes to the health tracking system

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Establish two more classes of health tracking bits:

 * Indirect problems, which suggest problems in other health domains
   that we weren't able to preserve.

 * Secondary problems, which track state that's related to primary
   evidence of health problems; and

The first class we'll use in an upcoming patch to record in the AG
health status the fact that we ran out of memory and had to inactivate
an inode with defective metadata.  The second class we use to indicate
that repair knows that an inode is bad and we need to fix it later.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_health.h |   43 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)


diff --git a/libxfs/xfs_health.h b/libxfs/xfs_health.h
index a5b346b377c..26a2661571b 100644
--- a/libxfs/xfs_health.h
+++ b/libxfs/xfs_health.h
@@ -31,6 +31,19 @@
  *  - !checked && sick  => errors have been observed during normal operation,
  *                         but the metadata has not been checked thoroughly
  *  - !checked && !sick => has not been examined since mount
+ *
+ * Evidence of health problems can be sorted into three basic categories:
+ *
+ * a) Primary evidence, which signals that something is defective within the
+ *    general grouping of metadata.
+ *
+ * b) Secondary evidence, which are side effects of primary problem but are
+ *    not themselves problems.  These can be forgotten when the primary
+ *    health problems are addressed.
+ *
+ * c) Indirect evidence, which points to something being wrong in another
+ *    group, but we had to release resources and this is all that's left of
+ *    that state.
  */
 
 struct xfs_mount;
@@ -115,6 +128,36 @@ struct xfs_da_args;
 				 XFS_SICK_INO_DIR_ZAPPED | \
 				 XFS_SICK_INO_SYMLINK_ZAPPED)
 
+/* Secondary state related to (but not primary evidence of) health problems. */
+#define XFS_SICK_FS_SECONDARY	(0)
+#define XFS_SICK_RT_SECONDARY	(0)
+#define XFS_SICK_AG_SECONDARY	(0)
+#define XFS_SICK_INO_SECONDARY	(0)
+
+/* Evidence of health problems elsewhere. */
+#define XFS_SICK_FS_INDIRECT	(0)
+#define XFS_SICK_RT_INDIRECT	(0)
+#define XFS_SICK_AG_INDIRECT	(0)
+#define XFS_SICK_INO_INDIRECT	(0)
+
+/* All health masks. */
+#define XFS_SICK_FS_ALL	(XFS_SICK_FS_PRIMARY | \
+				 XFS_SICK_FS_SECONDARY | \
+				 XFS_SICK_FS_INDIRECT)
+
+#define XFS_SICK_RT_ALL	(XFS_SICK_RT_PRIMARY | \
+				 XFS_SICK_RT_SECONDARY | \
+				 XFS_SICK_RT_INDIRECT)
+
+#define XFS_SICK_AG_ALL	(XFS_SICK_AG_PRIMARY | \
+				 XFS_SICK_AG_SECONDARY | \
+				 XFS_SICK_AG_INDIRECT)
+
+#define XFS_SICK_INO_ALL	(XFS_SICK_INO_PRIMARY | \
+				 XFS_SICK_INO_SECONDARY | \
+				 XFS_SICK_INO_INDIRECT | \
+				 XFS_SICK_INO_ZAPPED)
+
 /*
  * These functions must be provided by the xfs implementation.  Function
  * behavior with respect to the first argument should be as follows:

[PATCH 2/4] xfs: remember sick inodes that get inactivated

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If an unhealthy inode gets inactivated, remember this fact in the
per-fs health summary.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_fs.h        |    1 +
 libxfs/xfs_health.h    |    8 ++++++--
 libxfs/xfs_inode_buf.c |    2 +-
 spaceman/health.c      |    4 ++++
 4 files changed, 12 insertions(+), 3 deletions(-)


diff --git a/libxfs/xfs_fs.h b/libxfs/xfs_fs.h
index 515cd27d3b3..b5c8da7e6aa 100644
--- a/libxfs/xfs_fs.h
+++ b/libxfs/xfs_fs.h
@@ -294,6 +294,7 @@ struct xfs_ag_geometry {
 #define XFS_AG_GEOM_SICK_FINOBT	(1 << 7)  /* free inode index */
 #define XFS_AG_GEOM_SICK_RMAPBT	(1 << 8)  /* reverse mappings */
 #define XFS_AG_GEOM_SICK_REFCNTBT (1 << 9)  /* reference counts */
+#define XFS_AG_GEOM_SICK_INODES	(1 << 10) /* bad inodes were seen */
 
 /*
  * Structures for XFS_IOC_FSGROWFSDATA, XFS_IOC_FSGROWFSLOG & XFS_IOC_FSGROWFSRT
diff --git a/libxfs/xfs_health.h b/libxfs/xfs_health.h
index 26a2661571b..df07c5877ba 100644
--- a/libxfs/xfs_health.h
+++ b/libxfs/xfs_health.h
@@ -76,6 +76,7 @@ struct xfs_da_args;
 #define XFS_SICK_AG_FINOBT	(1 << 7)  /* free inode index */
 #define XFS_SICK_AG_RMAPBT	(1 << 8)  /* reverse mappings */
 #define XFS_SICK_AG_REFCNTBT	(1 << 9)  /* reference counts */
+#define XFS_SICK_AG_INODES	(1 << 10) /* inactivated bad inodes */
 
 /* Observable health issues for inode metadata. */
 #define XFS_SICK_INO_CORE	(1 << 0)  /* inode core */
@@ -92,6 +93,9 @@ struct xfs_da_args;
 #define XFS_SICK_INO_DIR_ZAPPED		(1 << 10) /* directory erased */
 #define XFS_SICK_INO_SYMLINK_ZAPPED	(1 << 11) /* symlink erased */
 
+/* Don't propagate sick status to ag health summary during inactivation */
+#define XFS_SICK_INO_FORGET	(1 << 12)
+
 /* Primary evidence of health problems in a given group. */
 #define XFS_SICK_FS_PRIMARY	(XFS_SICK_FS_COUNTERS | \
 				 XFS_SICK_FS_UQUOTA | \
@@ -132,12 +136,12 @@ struct xfs_da_args;
 #define XFS_SICK_FS_SECONDARY	(0)
 #define XFS_SICK_RT_SECONDARY	(0)
 #define XFS_SICK_AG_SECONDARY	(0)
-#define XFS_SICK_INO_SECONDARY	(0)
+#define XFS_SICK_INO_SECONDARY	(XFS_SICK_INO_FORGET)
 
 /* Evidence of health problems elsewhere. */
 #define XFS_SICK_FS_INDIRECT	(0)
 #define XFS_SICK_RT_INDIRECT	(0)
-#define XFS_SICK_AG_INDIRECT	(0)
+#define XFS_SICK_AG_INDIRECT	(XFS_SICK_AG_INODES)
 #define XFS_SICK_INO_INDIRECT	(0)
 
 /* All health masks. */
diff --git a/libxfs/xfs_inode_buf.c b/libxfs/xfs_inode_buf.c
index 83d93698116..82cf64db938 100644
--- a/libxfs/xfs_inode_buf.c
+++ b/libxfs/xfs_inode_buf.c
@@ -136,7 +136,7 @@ xfs_imap_to_bp(
 			imap->im_len, XBF_UNMAPPED, bpp, &xfs_inode_buf_ops);
 	if (xfs_metadata_is_sick(error))
 		xfs_agno_mark_sick(mp, xfs_daddr_to_agno(mp, imap->im_blkno),
-				XFS_SICK_AG_INOBT);
+				XFS_SICK_AG_INODES);
 	return error;
 }
 
diff --git a/spaceman/health.c b/spaceman/health.c
index 88b12c0b0ea..12fb67bab28 100644
--- a/spaceman/health.c
+++ b/spaceman/health.c
@@ -127,6 +127,10 @@ static const struct flag_map ag_flags[] = {
 		.descr = "reference count btree",
 		.has_fn = has_reflink,
 	},
+	{
+		.mask = XFS_AG_GEOM_SICK_INODES,
+		.descr = "overall inode state",
+	},
 	{0},
 };
 

[PATCH 3/4] xfs: update health status if we get a clean bill of health

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If scrub finds that everything is ok with the filesystem, we need a way
to tell the health tracking that it can let go of indirect health flags,
since indirect flags only mean that at some point in the past we lost
some context.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libfrog/scrub.c                     |    5 +++++
 libxfs/xfs_fs.h                     |    3 ++-
 man/man2/ioctl_xfs_scrub_metadata.2 |    6 ++++++
 scrub/scrub.c                       |    7 +------
 4 files changed, 14 insertions(+), 7 deletions(-)


diff --git a/libfrog/scrub.c b/libfrog/scrub.c
index b6b8ae042c4..1df2965fe2d 100644
--- a/libfrog/scrub.c
+++ b/libfrog/scrub.c
@@ -144,6 +144,11 @@ const struct xfrog_scrub_descr xfrog_scrubbers[XFS_SCRUB_TYPE_NR] = {
 		.descr	= "inode link counts",
 		.group	= XFROG_SCRUB_GROUP_ISCAN,
 	},
+	[XFS_SCRUB_TYPE_HEALTHY] = {
+		.name	= "healthy",
+		.descr	= "retained health records",
+		.group	= XFROG_SCRUB_GROUP_NONE,
+	},
 };
 
 /* Invoke the scrub ioctl.  Returns zero or negative error code. */
diff --git a/libxfs/xfs_fs.h b/libxfs/xfs_fs.h
index b5c8da7e6aa..ca1b17d0143 100644
--- a/libxfs/xfs_fs.h
+++ b/libxfs/xfs_fs.h
@@ -714,9 +714,10 @@ struct xfs_scrub_metadata {
 #define XFS_SCRUB_TYPE_FSCOUNTERS 24	/* fs summary counters */
 #define XFS_SCRUB_TYPE_QUOTACHECK 25	/* quota counters */
 #define XFS_SCRUB_TYPE_NLINKS	26	/* inode link counts */
+#define XFS_SCRUB_TYPE_HEALTHY	27	/* everything checked out ok */
 
 /* Number of scrub subcommands. */
-#define XFS_SCRUB_TYPE_NR	27
+#define XFS_SCRUB_TYPE_NR	28
 
 /* i: Repair this metadata. */
 #define XFS_SCRUB_IFLAG_REPAIR		(1u << 0)
diff --git a/man/man2/ioctl_xfs_scrub_metadata.2 b/man/man2/ioctl_xfs_scrub_metadata.2
index 8e8bb72fb3b..9963f1913e6 100644
--- a/man/man2/ioctl_xfs_scrub_metadata.2
+++ b/man/man2/ioctl_xfs_scrub_metadata.2
@@ -168,6 +168,12 @@ count) for errors.
 .TP
 .B XFS_SCRUB_TYPE_NLINKS
 Scan all inodes in the filesystem to verify each file's link count.
+
+.TP
+.B XFS_SCRUB_TYPE_HEALTHY
+Mark everything healthy after a clean scrub run.
+This clears out all the indirect health problem markers that might remain
+in the system.
 .RE
 
 .PD 1
diff --git a/scrub/scrub.c b/scrub/scrub.c
index b7ec54c16a4..cf056779526 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -39,20 +39,15 @@ format_scrub_descr(
 	case XFROG_SCRUB_GROUP_PERAG:
 		return snprintf(buf, buflen, _("AG %u %s"), meta->sm_agno,
 				_(sc->descr));
-		break;
 	case XFROG_SCRUB_GROUP_INODE:
 		return scrub_render_ino_descr(ctx, buf, buflen,
 				meta->sm_ino, meta->sm_gen, "%s",
 				_(sc->descr));
-		break;
 	case XFROG_SCRUB_GROUP_FS:
 	case XFROG_SCRUB_GROUP_SUMMARY:
 	case XFROG_SCRUB_GROUP_ISCAN:
-		return snprintf(buf, buflen, _("%s"), _(sc->descr));
-		break;
 	case XFROG_SCRUB_GROUP_NONE:
-		assert(0);
-		break;
+		return snprintf(buf, buflen, _("%s"), _(sc->descr));
 	}
 	return -1;
 }

[PATCH 4/4] xfs_scrub: upload clean bills of health

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If scrub terminates with a clean bill of health, tell the kernel that
the result of the scan is that everything's healthy.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase1.c |   38 ++++++++++++++++++++++++++++++++++++++
 scrub/repair.c |   15 +++++++++++++++
 scrub/repair.h |    1 +
 scrub/scrub.c  |    9 +++++++++
 scrub/scrub.h  |    1 +
 5 files changed, 64 insertions(+)


diff --git a/scrub/phase1.c b/scrub/phase1.c
index 48ca8313b05..96138e03e71 100644
--- a/scrub/phase1.c
+++ b/scrub/phase1.c
@@ -44,6 +44,40 @@ xfs_shutdown_fs(
 		str_errno(ctx, ctx->mntpoint);
 }
 
+/*
+ * If we haven't found /any/ problems at all, tell the kernel that we're giving
+ * the filesystem a clean bill of health.
+ */
+static int
+report_to_kernel(
+	struct scrub_ctx	*ctx)
+{
+	struct action_list	alist;
+	int			ret;
+
+	if (!ctx->scrub_setup_succeeded || ctx->corruptions_found ||
+	    ctx->runtime_errors || ctx->unfixable_errors ||
+	    ctx->warnings_found)
+		return 0;
+
+	action_list_init(&alist);
+	ret = scrub_clean_health(ctx, &alist);
+	if (ret)
+		return ret;
+
+	/*
+	 * Complain if we cannot fail the clean bill of health, unless we're
+	 * just testing repairs.
+	 */
+	if (action_list_length(&alist) > 0 &&
+	    !debug_tweak_on("XFS_SCRUB_FORCE_REPAIR")) {
+		str_info(ctx, _("Couldn't upload clean bill of health."), NULL);
+		action_list_discard(&alist);
+	}
+
+	return 0;
+}
+
 /* Clean up the XFS-specific state data. */
 int
 scrub_cleanup(
@@ -51,6 +85,10 @@ scrub_cleanup(
 {
 	int			error;
 
+	error = report_to_kernel(ctx);
+	if (error)
+		return error;
+
 	action_lists_free(&ctx->action_lists);
 	if (ctx->fshandle)
 		free_handle(ctx->fshandle, ctx->fshandle_len);
diff --git a/scrub/repair.c b/scrub/repair.c
index 3cb7224f7cc..9ade805e1b6 100644
--- a/scrub/repair.c
+++ b/scrub/repair.c
@@ -172,6 +172,21 @@ action_lists_alloc(
 	return 0;
 }
 
+/* Discard repair list contents. */
+void
+action_list_discard(
+	struct action_list		*alist)
+{
+	struct action_item		*aitem;
+	struct action_item		*n;
+
+	list_for_each_entry_safe(aitem, n, &alist->list, list) {
+		alist->nr--;
+		list_del(&aitem->list);
+		free(aitem);
+	}
+}
+
 /* Free the repair lists. */
 void
 action_lists_free(
diff --git a/scrub/repair.h b/scrub/repair.h
index 486617f1ce4..aa3ea13615f 100644
--- a/scrub/repair.h
+++ b/scrub/repair.h
@@ -24,6 +24,7 @@ static inline bool action_list_empty(const struct action_list *alist)
 
 unsigned long long action_list_length(struct action_list *alist);
 void action_list_add(struct action_list *dest, struct action_item *item);
+void action_list_discard(struct action_list *alist);
 void action_list_splice(struct action_list *dest, struct action_list *src);
 
 void action_list_find_mustfix(struct action_list *actions,
diff --git a/scrub/scrub.c b/scrub/scrub.c
index cf056779526..7cb94af3d15 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -444,6 +444,15 @@ scrub_nlinks(
 	return scrub_meta_type(ctx, XFS_SCRUB_TYPE_NLINKS, 0, alist);
 }
 
+/* Update incore health records if we were clean. */
+int
+scrub_clean_health(
+	struct scrub_ctx		*ctx,
+	struct action_list		*alist)
+{
+	return scrub_meta_type(ctx, XFS_SCRUB_TYPE_HEALTHY, 0, alist);
+}
+
 /* How many items do we have to check? */
 unsigned int
 scrub_estimate_ag_work(
diff --git a/scrub/scrub.h b/scrub/scrub.h
index 5e3f40bf1f4..cb33ddb46f3 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -29,6 +29,7 @@ int scrub_summary_metadata(struct scrub_ctx *ctx, struct action_list *alist);
 int scrub_fs_counters(struct scrub_ctx *ctx, struct action_list *alist);
 int scrub_quotacheck(struct scrub_ctx *ctx, struct action_list *alist);
 int scrub_nlinks(struct scrub_ctx *ctx, struct action_list *alist);
+int scrub_clean_health(struct scrub_ctx *ctx, struct action_list *alist);
 
 bool can_scrub_fs_metadata(struct scrub_ctx *ctx);
 bool can_scrub_inode(struct scrub_ctx *ctx);

[PATCH 01/10] libxfs: clean up xfs_da_unmount usage

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Replace the open-coded xfs_da_unmount usage in libxfs_umount and teach
libxfs_mount not to leak the dir/attr geometry structures when the mount
attempt fails.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/init.c |   17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)


diff --git a/libxfs/init.c b/libxfs/init.c
index 1e035c48f57..f15ac48a21d 100644
--- a/libxfs/init.c
+++ b/libxfs/init.c
@@ -716,7 +716,7 @@ libxfs_mount(
 	if (error) {
 		fprintf(stderr, _("%s: data size check failed\n"), progname);
 		if (!xfs_is_debugger(mp))
-			return NULL;
+			goto out_da;
 	} else
 		libxfs_buf_relse(bp);
 
@@ -730,7 +730,7 @@ libxfs_mount(
 			fprintf(stderr, _("%s: log size checks failed\n"),
 					progname);
 			if (!xfs_is_debugger(mp))
-				return NULL;
+				goto out_da;
 		}
 		if (bp)
 			libxfs_buf_relse(bp);
@@ -741,8 +741,8 @@ libxfs_mount(
 	/* Initialize realtime fields in the mount structure */
 	if (rtmount_init(mp)) {
 		fprintf(stderr, _("%s: realtime device init failed\n"),
-			progname);
-			return NULL;
+				progname);
+			goto out_da;
 	}
 
 	/*
@@ -760,7 +760,7 @@ libxfs_mount(
 			fprintf(stderr, _("%s: read of AG %u failed\n"),
 						progname, sbp->sb_agcount);
 			if (!xfs_is_debugger(mp))
-				return NULL;
+				goto out_da;
 			fprintf(stderr, _("%s: limiting reads to AG 0\n"),
 								progname);
 			sbp->sb_agcount = 1;
@@ -778,6 +778,9 @@ libxfs_mount(
 	xfs_set_perag_data_loaded(mp);
 
 	return mp;
+out_da:
+	xfs_da_unmount(mp);
+	return NULL;
 }
 
 void
@@ -900,9 +903,7 @@ libxfs_umount(
 	if (xfs_is_perag_data_loaded(mp))
 		libxfs_free_perag(mp);
 
-	kmem_free(mp->m_attr_geo);
-	kmem_free(mp->m_dir_geo);
-
+	xfs_da_unmount(mp);
 	kmem_free(mp->m_rtdev_targp);
 	if (mp->m_logdev_targp != mp->m_ddev_targp)
 		kmem_free(mp->m_logdev_targp);

[PATCH 02/10] libxfs: teach buftargs to maintain their own buffer hashtable

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Currently, cached buffers are indexed with a single global bcache
structure.  This works ok for the limited use case where we only support
reading from the data device, but will fail badly when we want to
support buffers from in-memory btrees.  Move the bcache structure into
the buftarg.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 include/libxfs.h    |    1 -
 libxfs/init.c       |   48 +++++++++++++++++++++---------------------------
 libxfs/libxfs_io.h  |   10 ++++++----
 libxfs/rdwr.c       |   40 +++++++++++++++++++++++++++-------------
 mkfs/xfs_mkfs.c     |    2 +-
 repair/prefetch.c   |   12 ++++++++----
 repair/prefetch.h   |    1 +
 repair/progress.c   |   14 +++++++++-----
 repair/progress.h   |    2 +-
 repair/scan.c       |    2 +-
 repair/xfs_repair.c |   32 +++++++++++++++++---------------
 11 files changed, 92 insertions(+), 72 deletions(-)


diff --git a/include/libxfs.h b/include/libxfs.h
index db7394aec77..5251475cf15 100644
--- a/include/libxfs.h
+++ b/include/libxfs.h
@@ -146,7 +146,6 @@ int		libxfs_init(struct libxfs_init *);
 void		libxfs_destroy(struct libxfs_init *li);
 
 extern int	libxfs_device_alignment (void);
-extern void	libxfs_report(FILE *);
 
 /* check or write log footer: specify device, log size in blocks & uuid */
 typedef char	*(libxfs_get_block_t)(char *, int, void *);
diff --git a/libxfs/init.c b/libxfs/init.c
index f15ac48a21d..c776a9b07f5 100644
--- a/libxfs/init.c
+++ b/libxfs/init.c
@@ -36,7 +36,6 @@ pthread_mutex_t	atomic64_lock = PTHREAD_MUTEX_INITIALIZER;
 
 char *progname = "libxfs";	/* default, changed by each tool */
 
-struct cache *libxfs_bcache;	/* global buffer cache */
 int libxfs_bhash_size;		/* #buckets in bcache */
 
 int	use_xfs_buf_lock;	/* global flag: use xfs_buf locks for MT */
@@ -267,8 +266,6 @@ libxfs_init(struct libxfs_init *a)
 
 	if (!libxfs_bhash_size)
 		libxfs_bhash_size = LIBXFS_BHASHSIZE(sbp);
-	libxfs_bcache = cache_init(a->bcache_flags, libxfs_bhash_size,
-				   &libxfs_bcache_operations);
 	use_xfs_buf_lock = a->flags & LIBXFS_USEBUFLOCK;
 	xfs_dir_startup();
 	init_caches();
@@ -451,6 +448,7 @@ xfs_set_inode_alloc(
 static struct xfs_buftarg *
 libxfs_buftarg_alloc(
 	struct xfs_mount	*mp,
+	struct libxfs_init	*xi,
 	struct libxfs_dev	*dev,
 	unsigned long		write_fails)
 {
@@ -472,6 +470,9 @@ libxfs_buftarg_alloc(
 	}
 	pthread_mutex_init(&btp->lock, NULL);
 
+	btp->bcache = cache_init(xi->bcache_flags, libxfs_bhash_size,
+			&libxfs_bcache_operations);
+
 	return btp;
 }
 
@@ -568,12 +569,13 @@ libxfs_buftarg_init(
 		return;
 	}
 
-	mp->m_ddev_targp = libxfs_buftarg_alloc(mp, &xi->data, dfail);
+	mp->m_ddev_targp = libxfs_buftarg_alloc(mp, xi, &xi->data, dfail);
 	if (!xi->log.dev || xi->log.dev == xi->data.dev)
 		mp->m_logdev_targp = mp->m_ddev_targp;
 	else
-		mp->m_logdev_targp = libxfs_buftarg_alloc(mp, &xi->log, lfail);
-	mp->m_rtdev_targp = libxfs_buftarg_alloc(mp, &xi->rt, rfail);
+		mp->m_logdev_targp = libxfs_buftarg_alloc(mp, xi, &xi->log,
+				lfail);
+	mp->m_rtdev_targp = libxfs_buftarg_alloc(mp, xi, &xi->rt, rfail);
 }
 
 /* Compute maximum possible height for per-AG btree types for this fs. */
@@ -851,7 +853,7 @@ libxfs_flush_mount(
 	 * LOST_WRITE flag to be set in the buftarg.  Once that's done,
 	 * instruct the disks to persist their write caches.
 	 */
-	libxfs_bcache_flush();
+	libxfs_bcache_flush(mp);
 
 	/* Flush all kernel and disk write caches, and report failures. */
 	if (mp->m_ddev_targp) {
@@ -877,6 +879,14 @@ libxfs_flush_mount(
 	return error;
 }
 
+static void
+libxfs_buftarg_free(
+	struct xfs_buftarg	*btp)
+{
+	cache_destroy(btp->bcache);
+	kmem_free(btp);
+}
+
 /*
  * Release any resource obtained during a mount.
  */
@@ -893,7 +903,7 @@ libxfs_umount(
 	 * all incore buffers, then pick up the outcome when we tell the disks
 	 * to persist their write caches.
 	 */
-	libxfs_bcache_purge();
+	libxfs_bcache_purge(mp);
 	error = libxfs_flush_mount(mp);
 
 	/*
@@ -904,10 +914,10 @@ libxfs_umount(
 		libxfs_free_perag(mp);
 
 	xfs_da_unmount(mp);
-	kmem_free(mp->m_rtdev_targp);
+	libxfs_buftarg_free(mp->m_rtdev_targp);
 	if (mp->m_logdev_targp != mp->m_ddev_targp)
-		kmem_free(mp->m_logdev_targp);
-	kmem_free(mp->m_ddev_targp);
+		libxfs_buftarg_free(mp->m_logdev_targp);
+	libxfs_buftarg_free(mp->m_ddev_targp);
 
 	return error;
 }
@@ -923,10 +933,7 @@ libxfs_destroy(
 
 	libxfs_close_devices(li);
 
-	/* Free everything from the buffer cache before freeing buffer cache */
-	libxfs_bcache_purge();
 	libxfs_bcache_free();
-	cache_destroy(libxfs_bcache);
 	leaked = destroy_caches();
 	rcu_unregister_thread();
 	if (getenv("LIBXFS_LEAK_CHECK") && leaked)
@@ -938,16 +945,3 @@ libxfs_device_alignment(void)
 {
 	return platform_align_blockdev();
 }
-
-void
-libxfs_report(FILE *fp)
-{
-	time_t t;
-	char *c;
-
-	cache_report(fp, "libxfs_bcache", libxfs_bcache);
-
-	t = time(NULL);
-	c = asctime(localtime(&t));
-	fprintf(fp, "%s", c);
-}
diff --git a/libxfs/libxfs_io.h b/libxfs/libxfs_io.h
index 259c6a7cf77..7877e17685b 100644
--- a/libxfs/libxfs_io.h
+++ b/libxfs/libxfs_io.h
@@ -28,6 +28,7 @@ struct xfs_buftarg {
 	dev_t			bt_bdev;
 	int			bt_bdev_fd;
 	unsigned int		flags;
+	struct cache		*bcache;	/* buffer cache */
 };
 
 /* We purged a dirty buffer and lost a write. */
@@ -36,6 +37,8 @@ struct xfs_buftarg {
 #define XFS_BUFTARG_CORRUPT_WRITE	(1 << 1)
 /* Simulate failure after a certain number of writes. */
 #define XFS_BUFTARG_INJECT_WRITE_FAIL	(1 << 2)
+/* purge buffers when lookups find a size mismatch */
+#define XFS_BUFTARG_MISCOMPARE_PURGE	(1 << 3)
 
 /* Simulate the system crashing after a certain number of writes. */
 static inline void
@@ -140,7 +143,6 @@ int libxfs_buf_priority(struct xfs_buf *bp);
 
 /* Buffer Cache Interfaces */
 
-extern struct cache	*libxfs_bcache;
 extern struct cache_operations	libxfs_bcache_operations;
 
 #define LIBXFS_GETBUF_TRYLOCK	(1 << 0)
@@ -184,10 +186,10 @@ libxfs_buf_read(
 
 int libxfs_readbuf_verify(struct xfs_buf *bp, const struct xfs_buf_ops *ops);
 struct xfs_buf *libxfs_getsb(struct xfs_mount *mp);
-extern void	libxfs_bcache_purge(void);
+extern void	libxfs_bcache_purge(struct xfs_mount *mp);
 extern void	libxfs_bcache_free(void);
-extern void	libxfs_bcache_flush(void);
-extern int	libxfs_bcache_overflowed(void);
+extern void	libxfs_bcache_flush(struct xfs_mount *mp);
+extern int	libxfs_bcache_overflowed(struct xfs_mount *mp);
 
 /* Buffer (Raw) Interfaces */
 int		libxfs_bwrite(struct xfs_buf *bp);
diff --git a/libxfs/rdwr.c b/libxfs/rdwr.c
index 0e332110b68..f791136c982 100644
--- a/libxfs/rdwr.c
+++ b/libxfs/rdwr.c
@@ -198,18 +198,21 @@ libxfs_bhash(cache_key_t key, unsigned int hashsize, unsigned int hashshift)
 }
 
 static int
-libxfs_bcompare(struct cache_node *node, cache_key_t key)
+libxfs_bcompare(
+	struct cache_node	*node,
+	cache_key_t		key)
 {
 	struct xfs_buf		*bp = container_of(node, struct xfs_buf,
 						   b_node);
 	struct xfs_bufkey	*bkey = (struct xfs_bufkey *)key;
+	struct cache		*bcache = bkey->buftarg->bcache;
 
 	if (bp->b_target->bt_bdev == bkey->buftarg->bt_bdev &&
 	    bp->b_cache_key == bkey->blkno) {
 		if (bp->b_length == bkey->bblen)
 			return CACHE_HIT;
 #ifdef IO_BCOMPARE_CHECK
-		if (!(libxfs_bcache->c_flags & CACHE_MISCOMPARE_PURGE)) {
+		if (!(bcache->c_flags & CACHE_MISCOMPARE_PURGE)) {
 			fprintf(stderr,
 	"%lx: Badness in key lookup (length)\n"
 	"bp=(bno 0x%llx, len %u bytes) key=(bno 0x%llx, len %u bytes)\n",
@@ -399,11 +402,12 @@ __cache_lookup(
 	struct xfs_buf		**bpp)
 {
 	struct cache_node	*cn = NULL;
+	struct cache		*bcache = key->buftarg->bcache;
 	struct xfs_buf		*bp;
 
 	*bpp = NULL;
 
-	cache_node_get(libxfs_bcache, key, &cn);
+	cache_node_get(bcache, key, &cn);
 	if (!cn)
 		return -ENOMEM;
 	bp = container_of(cn, struct xfs_buf, b_node);
@@ -415,7 +419,7 @@ __cache_lookup(
 		if (ret) {
 			ASSERT(ret == EAGAIN);
 			if (flags & LIBXFS_GETBUF_TRYLOCK) {
-				cache_node_put(libxfs_bcache, cn);
+				cache_node_put(bcache, cn);
 				return -EAGAIN;
 			}
 
@@ -434,7 +438,7 @@ __cache_lookup(
 		bp->b_holder = pthread_self();
 	}
 
-	cache_node_set_priority(libxfs_bcache, cn,
+	cache_node_set_priority(bcache, cn,
 			cache_node_get_priority(cn) - CACHE_PREFETCH_PRIORITY);
 	*bpp = bp;
 	return 0;
@@ -550,7 +554,7 @@ libxfs_buf_relse(
 	}
 
 	if (!list_empty(&bp->b_node.cn_hash))
-		cache_node_put(libxfs_bcache, &bp->b_node);
+		cache_node_put(bp->b_target->bcache, &bp->b_node);
 	else if (--bp->b_node.cn_count == 0) {
 		if (bp->b_flags & LIBXFS_B_DIRTY)
 			libxfs_bwrite(bp);
@@ -1003,21 +1007,31 @@ libxfs_bflush(
 }
 
 void
-libxfs_bcache_purge(void)
+libxfs_bcache_purge(struct xfs_mount *mp)
 {
-	cache_purge(libxfs_bcache);
+	if (!mp)
+		return;
+	cache_purge(mp->m_ddev_targp->bcache);
+	cache_purge(mp->m_logdev_targp->bcache);
+	cache_purge(mp->m_rtdev_targp->bcache);
 }
 
 void
-libxfs_bcache_flush(void)
+libxfs_bcache_flush(struct xfs_mount *mp)
 {
-	cache_flush(libxfs_bcache);
+	if (!mp)
+		return;
+	cache_flush(mp->m_ddev_targp->bcache);
+	cache_flush(mp->m_logdev_targp->bcache);
+	cache_flush(mp->m_rtdev_targp->bcache);
 }
 
 int
-libxfs_bcache_overflowed(void)
+libxfs_bcache_overflowed(struct xfs_mount *mp)
 {
-	return cache_overflowed(libxfs_bcache);
+	return cache_overflowed(mp->m_ddev_targp->bcache) ||
+		cache_overflowed(mp->m_logdev_targp->bcache) ||
+		cache_overflowed(mp->m_rtdev_targp->bcache);
 }
 
 struct cache_operations libxfs_bcache_operations = {
@@ -1466,7 +1480,7 @@ libxfs_buf_set_priority(
 	struct xfs_buf	*bp,
 	int		priority)
 {
-	cache_node_set_priority(libxfs_bcache, &bp->b_node, priority);
+	cache_node_set_priority(bp->b_target->bcache, &bp->b_node, priority);
 }
 
 int
diff --git a/mkfs/xfs_mkfs.c b/mkfs/xfs_mkfs.c
index cb09c6466a6..8b0fbe97ddc 100644
--- a/mkfs/xfs_mkfs.c
+++ b/mkfs/xfs_mkfs.c
@@ -4613,7 +4613,7 @@ main(
 	 * Need to drop references to inodes we still hold, first.
 	 */
 	libxfs_rtmount_destroy(mp);
-	libxfs_bcache_purge();
+	libxfs_bcache_purge(mp);
 
 	/*
 	 * Mark the filesystem ok.
diff --git a/repair/prefetch.c b/repair/prefetch.c
index 78c1e397433..58fc2dac1a8 100644
--- a/repair/prefetch.c
+++ b/repair/prefetch.c
@@ -886,10 +886,12 @@ init_prefetch(
 
 prefetch_args_t *
 start_inode_prefetch(
+	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno,
 	int			dirs_only,
 	prefetch_args_t		*prev_args)
 {
+	struct cache		*bcache = mp->m_ddev_targp->bcache;
 	prefetch_args_t		*args;
 	long			max_queue;
 	struct xfs_ino_geometry	*igeo = M_IGEO(mp);
@@ -914,7 +916,7 @@ start_inode_prefetch(
 	 * and not any other associated metadata like directories
 	 */
 
-	max_queue = libxfs_bcache->c_maxcount / thread_count / 8;
+	max_queue = bcache->c_maxcount / thread_count / 8;
 	if (igeo->inode_cluster_size > mp->m_sb.sb_blocksize)
 		max_queue = max_queue * igeo->blocks_per_cluster /
 				igeo->ialloc_blks;
@@ -970,14 +972,16 @@ prefetch_ag_range(
 	void			(*func)(struct workqueue *,
 					xfs_agnumber_t, void *))
 {
+	struct xfs_mount	*mp = work->wq_ctx;
 	int			i;
 	struct prefetch_args	*pf_args[2];
 
-	pf_args[start_ag & 1] = start_inode_prefetch(start_ag, dirs_only, NULL);
+	pf_args[start_ag & 1] = start_inode_prefetch(mp, start_ag, dirs_only,
+			NULL);
 	for (i = start_ag; i < end_ag; i++) {
 		/* Don't prefetch end_ag */
 		if (i + 1 < end_ag)
-			pf_args[(~i) & 1] = start_inode_prefetch(i + 1,
+			pf_args[(~i) & 1] = start_inode_prefetch(mp, i + 1,
 						dirs_only, pf_args[i & 1]);
 		func(work, i, pf_args[i & 1]);
 	}
@@ -1027,7 +1031,7 @@ do_inode_prefetch(
 	 * filesystem - it's all in the cache. In that case, run a thread per
 	 * CPU to maximise parallelism of the queue to be processed.
 	 */
-	if (check_cache && !libxfs_bcache_overflowed()) {
+	if (check_cache && !libxfs_bcache_overflowed(mp)) {
 		queue.wq_ctx = mp;
 		create_work_queue(&queue, mp, platform_nproc());
 		for (i = 0; i < mp->m_sb.sb_agcount; i++)
diff --git a/repair/prefetch.h b/repair/prefetch.h
index 54ece48ad22..a8c52a1195b 100644
--- a/repair/prefetch.h
+++ b/repair/prefetch.h
@@ -39,6 +39,7 @@ init_prefetch(
 
 prefetch_args_t *
 start_inode_prefetch(
+	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno,
 	int			dirs_only,
 	prefetch_args_t		*prev_args);
diff --git a/repair/progress.c b/repair/progress.c
index f6c4d988444..625dc41c289 100644
--- a/repair/progress.c
+++ b/repair/progress.c
@@ -383,14 +383,18 @@ timediff(int phase)
 **  array.
 */
 char *
-timestamp(int end, int phase, char *buf)
+timestamp(
+	struct xfs_mount	*mp,
+	int			end,
+	int			phase,
+	char			*buf)
 {
 
-	time_t    now;
-	struct tm *tmp;
+	time_t			now;
+	struct tm		*tmp;
 
-	if (verbose > 1)
-		cache_report(stderr, "libxfs_bcache", libxfs_bcache);
+	if (verbose > 1 && mp && mp->m_ddev_targp)
+		cache_report(stderr, "libxfs_bcache", mp->m_ddev_targp->bcache);
 
 	now = time(NULL);
 
diff --git a/repair/progress.h b/repair/progress.h
index 2c1690db1b1..75b751b783b 100644
--- a/repair/progress.h
+++ b/repair/progress.h
@@ -37,7 +37,7 @@ extern void stop_progress_rpt(void);
 extern void summary_report(void);
 extern int  set_progress_msg(int report, uint64_t total);
 extern uint64_t print_final_rpt(void);
-extern char *timestamp(int end, int phase, char *buf);
+extern char *timestamp(struct xfs_mount *mp, int end, int phase, char *buf);
 extern char *duration(int val, char *buf);
 extern int do_parallel;
 
diff --git a/repair/scan.c b/repair/scan.c
index 0a77dd67913..bda2be24af3 100644
--- a/repair/scan.c
+++ b/repair/scan.c
@@ -42,7 +42,7 @@ struct aghdr_cnts {
 void
 set_mp(xfs_mount_t *mpp)
 {
-	libxfs_bcache_purge();
+	libxfs_bcache_purge(mp);
 	mp = mpp;
 }
 
diff --git a/repair/xfs_repair.c b/repair/xfs_repair.c
index ba9d28330d8..d4f99f36f71 100644
--- a/repair/xfs_repair.c
+++ b/repair/xfs_repair.c
@@ -942,9 +942,11 @@ repair_capture_writeback(
 }
 
 static inline void
-phase_end(int phase)
+phase_end(
+	struct xfs_mount	*mp,
+	int			phase)
 {
-	timestamp(PHASE_END, phase, NULL);
+	timestamp(mp, PHASE_END, phase, NULL);
 
 	/* Fail if someone injected an post-phase error. */
 	if (fail_after_phase && phase == fail_after_phase)
@@ -979,8 +981,8 @@ main(int argc, char **argv)
 
 	msgbuf = malloc(DURATION_BUF_SIZE);
 
-	timestamp(PHASE_START, 0, NULL);
-	phase_end(0);
+	timestamp(temp_mp, PHASE_START, 0, NULL);
+	phase_end(temp_mp, 0);
 
 	/* -f forces this, but let's be nice and autodetect it, as well. */
 	if (!isa_file) {
@@ -1002,7 +1004,7 @@ main(int argc, char **argv)
 
 	/* do phase1 to make sure we have a superblock */
 	phase1(temp_mp);
-	phase_end(1);
+	phase_end(temp_mp, 1);
 
 	if (no_modify && primary_sb_modified)  {
 		do_warn(_("Primary superblock would have been modified.\n"
@@ -1139,8 +1141,8 @@ main(int argc, char **argv)
 		unsigned long	max_mem;
 		struct rlimit	rlim;
 
-		libxfs_bcache_purge();
-		cache_destroy(libxfs_bcache);
+		libxfs_bcache_purge(mp);
+		cache_destroy(mp->m_ddev_targp->bcache);
 
 		mem_used = (mp->m_sb.sb_icount >> (10 - 2)) +
 					(mp->m_sb.sb_dblocks >> (10 + 1)) +
@@ -1200,7 +1202,7 @@ main(int argc, char **argv)
 			do_log(_("        - block cache size set to %d entries\n"),
 				libxfs_bhash_size * HASH_CACHE_RATIO);
 
-		libxfs_bcache = cache_init(0, libxfs_bhash_size,
+		mp->m_ddev_targp->bcache = cache_init(0, libxfs_bhash_size,
 						&libxfs_bcache_operations);
 	}
 
@@ -1228,16 +1230,16 @@ main(int argc, char **argv)
 
 	/* make sure the per-ag freespace maps are ok so we can mount the fs */
 	phase2(mp, phase2_threads);
-	phase_end(2);
+	phase_end(mp, 2);
 
 	if (do_prefetch)
 		init_prefetch(mp);
 
 	phase3(mp, phase2_threads);
-	phase_end(3);
+	phase_end(mp, 3);
 
 	phase4(mp);
-	phase_end(4);
+	phase_end(mp, 4);
 
 	if (no_modify) {
 		printf(_("No modify flag set, skipping phase 5\n"));
@@ -1247,7 +1249,7 @@ main(int argc, char **argv)
 	} else {
 		phase5(mp);
 	}
-	phase_end(5);
+	phase_end(mp, 5);
 
 	/*
 	 * Done with the block usage maps, toss them...
@@ -1257,10 +1259,10 @@ main(int argc, char **argv)
 
 	if (!bad_ino_btree)  {
 		phase6(mp);
-		phase_end(6);
+		phase_end(mp, 6);
 
 		phase7(mp, phase2_threads);
-		phase_end(7);
+		phase_end(mp, 7);
 	} else  {
 		do_warn(
 _("Inode allocation btrees are too corrupted, skipping phases 6 and 7\n"));
@@ -1385,7 +1387,7 @@ _("Note - stripe unit (%d) and width (%d) were copied from a backup superblock.\
 	 * verifiers are run (where we discover the max metadata LSN), reformat
 	 * the log if necessary and unmount.
 	 */
-	libxfs_bcache_flush();
+	libxfs_bcache_flush(mp);
 	format_log_max_lsn(mp);
 
 	if (xfs_sb_version_needsrepair(&mp->m_sb))

[PATCH 03/10] libxfs: add xfile support

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Port the xfile functionality (anonymous pageable file-index memory) from
the kernel.  In userspace, we try to use memfd() to create tmpfs files
that are not in any namespace, matching the kernel.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 configure.ac          |    4 +
 include/builddefs.in  |    4 +
 libxfs/Makefile       |   15 +++
 libxfs/xfile.c        |  265 +++++++++++++++++++++++++++++++++++++++++++++++++
 libxfs/xfile.h        |   56 ++++++++++
 m4/package_libcdev.m4 |   66 ++++++++++++
 repair/xfs_repair.c   |   15 +++
 7 files changed, 425 insertions(+)
 create mode 100644 libxfs/xfile.c
 create mode 100644 libxfs/xfile.h


diff --git a/configure.ac b/configure.ac
index 2034f02e59e..38b62619a7a 100644
--- a/configure.ac
+++ b/configure.ac
@@ -253,6 +253,10 @@ AC_CHECK_SIZEOF([char *])
 AC_TYPE_UMODE_T
 AC_MANUAL_FORMAT
 AC_HAVE_LIBURCU_ATOMIC64
+AC_HAVE_MEMFD_CLOEXEC
+AC_HAVE_MEMFD_NOEXEC_SEAL
+AC_HAVE_O_TMPFILE
+AC_HAVE_MKOSTEMP_CLOEXEC
 
 AC_CONFIG_FILES([include/builddefs])
 AC_OUTPUT
diff --git a/include/builddefs.in b/include/builddefs.in
index 43025ba4fcc..eb7f6ba4f03 100644
--- a/include/builddefs.in
+++ b/include/builddefs.in
@@ -130,6 +130,10 @@ CROND_DIR = @crond_dir@
 HAVE_UDEV = @have_udev@
 UDEV_RULE_DIR = @udev_rule_dir@
 HAVE_LIBURCU_ATOMIC64 = @have_liburcu_atomic64@
+HAVE_MEMFD_CLOEXEC = @have_memfd_cloexec@
+HAVE_MEMFD_NOEXEC_SEAL = @have_memfd_noexec_seal@
+HAVE_O_TMPFILE = @have_o_tmpfile@
+HAVE_MKOSTEMP_CLOEXEC = @have_mkostemp_cloexec@
 
 GCCFLAGS = -funsigned-char -fno-strict-aliasing -Wall
 #	   -Wbitwise -Wno-transparent-union -Wno-old-initializer -Wno-decl
diff --git a/libxfs/Makefile b/libxfs/Makefile
index 6f688c0ad25..68b366072da 100644
--- a/libxfs/Makefile
+++ b/libxfs/Makefile
@@ -26,6 +26,7 @@ HFILES = \
 	libxfs_priv.h \
 	linux-err.h \
 	topology.h \
+	xfile.h \
 	xfs_ag_resv.h \
 	xfs_alloc.h \
 	xfs_alloc_btree.h \
@@ -66,6 +67,7 @@ CFILES = cache.c \
 	topology.c \
 	trans.c \
 	util.c \
+	xfile.c \
 	xfs_ag.c \
 	xfs_ag_resv.c \
 	xfs_alloc.c \
@@ -112,6 +114,19 @@ CFILES = cache.c \
 #
 #LCFLAGS +=
 
+ifeq ($(HAVE_MEMFD_CLOEXEC),yes)
+	LCFLAGS += -DHAVE_MEMFD_CLOEXEC
+endif
+ifeq ($(HAVE_MEMFD_NOEXEC_SEAL),yes)
+	LCFLAGS += -DHAVE_MEMFD_NOEXEC_SEAL
+endif
+ifeq ($(HAVE_O_TMPFILE),yes)
+	LCFLAGS += -DHAVE_O_TMPFILE
+endif
+ifeq ($(HAVE_MKOSTEMP_CLOEXEC),yes)
+	LCFLAGS += -DHAVE_MKOSTEMP_CLOEXEC
+endif
+
 FCFLAGS = -I.
 
 LTLIBS = $(LIBPTHREAD) $(LIBRT)
diff --git a/libxfs/xfile.c b/libxfs/xfile.c
new file mode 100644
index 00000000000..57694d33498
--- /dev/null
+++ b/libxfs/xfile.c
@@ -0,0 +1,265 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2021-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "libxfs_priv.h"
+#include "libxfs.h"
+#include "libxfs/xfile.h"
+#ifdef HAVE_MEMFD_NOEXEC_SEAL
+# include <linux/memfd.h>
+#endif
+#include <sys/mman.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+
+/*
+ * Swappable Temporary Memory
+ * ==========================
+ *
+ * Offline checking sometimes needs to be able to stage a large amount of data
+ * in memory.  This information might not fit in the available memory and it
+ * doesn't all need to be accessible at all times.  In other words, we want an
+ * indexed data buffer to store data that can be paged out.
+ *
+ * memfd files meet those requirements.  Therefore, the xfile mechanism uses
+ * one to store our staging data.  The xfile must be freed with xfile_destroy.
+ *
+ * xfiles assume that the caller will handle all required concurrency
+ * management; file locks are not taken.
+ */
+
+/*
+ * Open a memory-backed fd to back an xfile.  We require close-on-exec here,
+ * because these memfd files function as windowed RAM and hence should never
+ * be shared with other processes.
+ */
+static int
+xfile_create_fd(
+	const char		*description)
+{
+	int			fd = -1;
+	int			ret;
+
+#ifdef HAVE_MEMFD_CLOEXEC
+
+# ifdef HAVE_MEMFD_NOEXEC_SEAL
+	/*
+	 * Starting with Linux 6.3, there's a new MFD_NOEXEC_SEAL flag that
+	 * disables the longstanding memfd behavior that files are created with
+	 * the executable bit set, and seals the file against it being turned
+	 * back on.  Using this bit on older kernels produces EINVAL, so we
+	 * try this twice.
+	 */
+	fd = memfd_create(description, MFD_CLOEXEC | MFD_NOEXEC_SEAL);
+	if (fd >= 0)
+		goto got_fd;
+# endif /* HAVE_MEMFD_NOEXEC_SEAL */
+
+	/* memfd_create exists in kernel 3.17 (2014) and glibc 2.27 (2018). */
+	fd = memfd_create(description, MFD_CLOEXEC);
+	if (fd >= 0)
+		goto got_fd;
+#endif /* HAVE_MEMFD_CLOEXEC */
+
+#ifdef HAVE_O_TMPFILE
+	/*
+	 * O_TMPFILE exists as of kernel 3.11 (2013), which means that if we
+	 * find it, we're pretty safe in assuming O_CLOEXEC exists too.
+	 */
+	fd = open("/dev/shm", O_TMPFILE | O_CLOEXEC | O_RDWR, 0600);
+	if (fd >= 0)
+		goto got_fd;
+
+	fd = open("/tmp", O_TMPFILE | O_CLOEXEC | O_RDWR, 0600);
+	if (fd >= 0)
+		goto got_fd;
+#endif
+
+#ifdef HAVE_MKOSTEMP_CLOEXEC
+	/*
+	 * mkostemp exists as of glibc 2.7 (2007) and O_CLOEXEC exists as of
+	 * kernel 2.6.23 (2007).
+	 */
+	fd = mkostemp("libxfsXXXXXX", O_CLOEXEC);
+	if (fd >= 0)
+		goto got_fd;
+#endif
+
+#if !defined(HAVE_MEMFD_CLOEXEC) && \
+    !defined(HAVE_O_TMPFILE) && \
+    !defined(HAVE_MKOSTEMP_CLOEXEC)
+# error System needs memfd_create, O_TMPFILE, or O_CLOEXEC to build!
+#endif
+
+	if (!errno)
+		errno = EOPNOTSUPP;
+	return -1;
+got_fd:
+	/*
+	 * Turn off mode bits we don't want -- group members and others should
+	 * not have access to the xfile, nor it be executable.  memfds are
+	 * created with mode 0777, but we'll be careful just in case the other
+	 * implementations fail to set 0600.
+	 */
+	ret = fchmod(fd, 0600);
+	if (ret)
+		perror("disabling xfile executable bit");
+
+	return fd;
+}
+
+/*
+ * Create an xfile of the given size.  The description will be used in the
+ * trace output.
+ */
+int
+xfile_create(
+	const char		*description,
+	struct xfile		**xfilep)
+{
+	struct xfile		*xf;
+	int			error;
+
+	xf = kmem_alloc(sizeof(struct xfile), KM_MAYFAIL);
+	if (!xf)
+		return -ENOMEM;
+
+	xf->fd = xfile_create_fd(description);
+	if (xf->fd < 0) {
+		error = -errno;
+		kmem_free(xf);
+		return error;
+	}
+
+	*xfilep = xf;
+	return 0;
+}
+
+/* Close the file and release all resources. */
+void
+xfile_destroy(
+	struct xfile		*xf)
+{
+	close(xf->fd);
+	kmem_free(xf);
+}
+
+static inline loff_t
+xfile_maxbytes(
+	struct xfile		*xf)
+{
+	if (sizeof(loff_t) == 8)
+		return LLONG_MAX;
+	return LONG_MAX;
+}
+
+/*
+ * Read a memory object directly from the xfile's page cache.  Unlike regular
+ * pread, we return -E2BIG and -EFBIG for reads that are too large or at too
+ * high an offset, instead of truncating the read.  Otherwise, we return
+ * bytes read or an error code, like regular pread.
+ */
+ssize_t
+xfile_pread(
+	struct xfile		*xf,
+	void			*buf,
+	size_t			count,
+	loff_t			pos)
+{
+	ssize_t			ret;
+
+	if (count > INT_MAX)
+		return -E2BIG;
+	if (xfile_maxbytes(xf) - pos < count)
+		return -EFBIG;
+
+	ret = pread(xf->fd, buf, count, pos);
+	if (ret >= 0)
+		return ret;
+	return -errno;
+}
+
+/*
+ * Write a memory object directly to the xfile's page cache.  Unlike regular
+ * pwrite, we return -E2BIG and -EFBIG for writes that are too large or at too
+ * high an offset, instead of truncating the write.  Otherwise, we return
+ * bytes written or an error code, like regular pwrite.
+ */
+ssize_t
+xfile_pwrite(
+	struct xfile		*xf,
+	const void		*buf,
+	size_t			count,
+	loff_t			pos)
+{
+	ssize_t			ret;
+
+	if (count > INT_MAX)
+		return -E2BIG;
+	if (xfile_maxbytes(xf) - pos < count)
+		return -EFBIG;
+
+	ret = pwrite(xf->fd, buf, count, pos);
+	if (ret >= 0)
+		return ret;
+	return -errno;
+}
+
+/* Compute the number of bytes used by a xfile. */
+unsigned long long
+xfile_bytes(
+	struct xfile		*xf)
+{
+	struct xfile_stat	xs;
+	int			ret;
+
+	ret = xfile_stat(xf, &xs);
+	if (ret)
+		return 0;
+
+	return xs.bytes;
+}
+
+/* Query stat information for an xfile. */
+int
+xfile_stat(
+	struct xfile		*xf,
+	struct xfile_stat	*statbuf)
+{
+	struct stat		ks;
+	int			error;
+
+	error = fstat(xf->fd, &ks);
+	if (error)
+		return -errno;
+
+	statbuf->size = ks.st_size;
+	statbuf->bytes = (unsigned long long)ks.st_blocks << 9;
+	return 0;
+}
+
+/* Dump an xfile to stdout. */
+int
+xfile_dump(
+	struct xfile		*xf)
+{
+	char			*argv[] = {"od", "-tx1", "-Ad", "-c", NULL};
+	pid_t			child;
+	int			i;
+
+	child = fork();
+	if (child != 0) {
+		int		wstatus;
+
+		wait(&wstatus);
+		return wstatus == 0 ? 0 : -EIO;
+	}
+
+	/* reroute our xfile to stdin and shut everything else */
+	dup2(xf->fd, 0);
+	for (i = 3; i < 1024; i++)
+		close(i);
+
+	return execvp("od", argv);
+}
diff --git a/libxfs/xfile.h b/libxfs/xfile.h
new file mode 100644
index 00000000000..4218c17e8bf
--- /dev/null
+++ b/libxfs/xfile.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2021-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __LIBXFS_XFILE_H__
+#define __LIBXFS_XFILE_H__
+
+struct xfile {
+	int		fd;
+};
+
+int xfile_create(const char *description, struct xfile **xfilep);
+void xfile_destroy(struct xfile *xf);
+
+ssize_t xfile_pread(struct xfile *xf, void *buf, size_t count, loff_t pos);
+ssize_t xfile_pwrite(struct xfile *xf, const void *buf, size_t count, loff_t pos);
+
+/*
+ * Load an object.  Since we're treating this file as "memory", any error or
+ * short IO is treated as a failure to allocate memory.
+ */
+static inline int
+xfile_obj_load(struct xfile *xf, void *buf, size_t count, loff_t pos)
+{
+	ssize_t	ret = xfile_pread(xf, buf, count, pos);
+
+	if (ret < 0 || ret != count)
+		return -ENOMEM;
+	return 0;
+}
+
+/*
+ * Store an object.  Since we're treating this file as "memory", any error or
+ * short IO is treated as a failure to allocate memory.
+ */
+static inline int
+xfile_obj_store(struct xfile *xf, const void *buf, size_t count, loff_t pos)
+{
+	ssize_t	ret = xfile_pwrite(xf, buf, count, pos);
+
+	if (ret < 0 || ret != count)
+		return -ENOMEM;
+	return 0;
+}
+
+struct xfile_stat {
+	loff_t			size;
+	unsigned long long	bytes;
+};
+
+int xfile_stat(struct xfile *xf, struct xfile_stat *statbuf);
+unsigned long long xfile_bytes(struct xfile *xf);
+int xfile_dump(struct xfile *xf);
+
+#endif /* __LIBXFS_XFILE_H__ */
diff --git a/m4/package_libcdev.m4 b/m4/package_libcdev.m4
index 174070651ec..c81a7a031d2 100644
--- a/m4/package_libcdev.m4
+++ b/m4/package_libcdev.m4
@@ -531,3 +531,69 @@ AC_DEFUN([AC_PACKAGE_CHECK_LTO],
     AC_SUBST(lto_cflags)
     AC_SUBST(lto_ldflags)
   ])
+
+#
+# Check if we have a memfd_create syscall with a MFD_CLOEXEC flag
+#
+AC_DEFUN([AC_HAVE_MEMFD_CLOEXEC],
+  [ AC_MSG_CHECKING([for memfd_fd and MFD_CLOEXEC])
+    AC_LINK_IFELSE([AC_LANG_PROGRAM([[
+#define _GNU_SOURCE
+#include <sys/mman.h>
+    ]], [[
+         return memfd_create("xfs", MFD_CLOEXEC);
+    ]])],[have_memfd_cloexec=yes
+       AC_MSG_RESULT(yes)],[AC_MSG_RESULT(no)])
+    AC_SUBST(have_memfd_cloexec)
+  ])
+
+#
+# Check if we have a memfd_create syscall with a MFD_NOEXEC_SEAL flag
+#
+AC_DEFUN([AC_HAVE_MEMFD_NOEXEC_SEAL],
+  [ AC_MSG_CHECKING([for memfd_fd and MFD_NOEXEC_SEAL])
+    AC_LINK_IFELSE([AC_LANG_PROGRAM([[
+#define _GNU_SOURCE
+#include <linux/memfd.h>
+#include <sys/mman.h>
+    ]], [[
+         return memfd_create("xfs", MFD_NOEXEC_SEAL);
+    ]])],[have_memfd_noexec_seal=yes
+       AC_MSG_RESULT(yes)],[AC_MSG_RESULT(no)])
+    AC_SUBST(have_memfd_noexec_seal)
+  ])
+
+#
+# Check if we have the O_TMPFILE flag
+#
+AC_DEFUN([AC_HAVE_O_TMPFILE],
+  [ AC_MSG_CHECKING([for O_TMPFILE])
+    AC_LINK_IFELSE([AC_LANG_PROGRAM([[
+#define _GNU_SOURCE
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+    ]], [[
+         return open("nowhere", O_TMPFILE, 0600);
+    ]])],[have_o_tmpfile=yes
+       AC_MSG_RESULT(yes)],[AC_MSG_RESULT(no)])
+    AC_SUBST(have_o_tmpfile)
+  ])
+
+#
+# Check if we have mkostemp with the O_CLOEXEC flag
+#
+AC_DEFUN([AC_HAVE_MKOSTEMP_CLOEXEC],
+  [ AC_MSG_CHECKING([for mkostemp and O_CLOEXEC])
+    AC_LINK_IFELSE([AC_LANG_PROGRAM([[
+#define _GNU_SOURCE
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <stdlib.h>
+    ]], [[
+         return mkostemp("nowhere", O_TMPFILE);
+    ]])],[have_mkostemp_cloexec=yes
+       AC_MSG_RESULT(yes)],[AC_MSG_RESULT(no)])
+    AC_SUBST(have_mkostemp_cloexec)
+  ])
diff --git a/repair/xfs_repair.c b/repair/xfs_repair.c
index d4f99f36f71..01f92e841f2 100644
--- a/repair/xfs_repair.c
+++ b/repair/xfs_repair.c
@@ -953,6 +953,20 @@ phase_end(
 		platform_crash();
 }
 
+/* Try to allow as many memfds as possible. */
+static void
+bump_max_fds(void)
+{
+	struct rlimit	rlim = { };
+	int		ret;
+
+	ret = getrlimit(RLIMIT_NOFILE, &rlim);
+	if (!ret) {
+		rlim.rlim_cur = rlim.rlim_max;
+		setrlimit(RLIMIT_NOFILE, &rlim);
+	}
+}
+
 int
 main(int argc, char **argv)
 {
@@ -972,6 +986,7 @@ main(int argc, char **argv)
 	bindtextdomain(PACKAGE, LOCALEDIR);
 	textdomain(PACKAGE);
 	dinode_bmbt_translation_init();
+	bump_max_fds();
 
 	temp_mp = &xfs_m;
 	setbuf(stdout, NULL);

[PATCH 04/10] xfs: teach buftargs to maintain their own buffer hashtable

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Currently, cached buffers are indexed by per-AG hashtables.  This works
great for the data device, but won't work for in-memory btrees.  Make it
so that buftargs can index buffers too.

We accomplish this by hoisting the rhashtable and its lock into a
separate xfs_buf_cache structure and reworking various functions to use
it.  Next, we introduce to the buftarg a new XFS_BUFTARG_SELF_CACHED
flag to indicate that the buftarg's cache is active (vs. the per-ag
cache for the regular filesystem).

Finally, make it so that each xfs_buf points to its cache if there is
one.  This is how we distinguish uncached buffers from now on.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/libxfs_priv.h |    4 ++--
 libxfs/xfs_ag.c      |    6 +++---
 libxfs/xfs_ag.h      |    4 +---
 3 files changed, 6 insertions(+), 8 deletions(-)


diff --git a/libxfs/libxfs_priv.h b/libxfs/libxfs_priv.h
index 89e55dda511..9310752a9b2 100644
--- a/libxfs/libxfs_priv.h
+++ b/libxfs/libxfs_priv.h
@@ -546,8 +546,8 @@ unsigned int hweight8(unsigned int w);
 unsigned int hweight32(unsigned int w);
 unsigned int hweight64(__u64 w);
 
-static inline int xfs_buf_hash_init(struct xfs_perag *pag) { return 0; }
-static inline void xfs_buf_hash_destroy(struct xfs_perag *pag) { }
+#define xfs_buf_cache_init(bch)		(0)
+#define xfs_buf_cache_destroy(bch)	((void)0)
 
 static inline int xfs_iunlink_init(struct xfs_perag *pag) { return 0; }
 static inline void xfs_iunlink_destroy(struct xfs_perag *pag) { }
diff --git a/libxfs/xfs_ag.c b/libxfs/xfs_ag.c
index 28a340d1122..8e40026436a 100644
--- a/libxfs/xfs_ag.c
+++ b/libxfs/xfs_ag.c
@@ -262,7 +262,7 @@ xfs_free_perag(
 		xfs_defer_drain_free(&pag->pag_intents_drain);
 
 		cancel_delayed_work_sync(&pag->pag_blockgc_work);
-		xfs_buf_hash_destroy(pag);
+		xfs_buf_cache_destroy(&pag->pag_bcache);
 
 		/* drop the mount's active reference */
 		xfs_perag_rele(pag);
@@ -392,7 +392,7 @@ xfs_initialize_perag(
 		pag->pagb_tree = RB_ROOT;
 #endif /* __KERNEL__ */
 
-		error = xfs_buf_hash_init(pag);
+		error = xfs_buf_cache_init(&pag->pag_bcache);
 		if (error)
 			goto out_remove_pag;
 
@@ -432,7 +432,7 @@ xfs_initialize_perag(
 		pag = radix_tree_delete(&mp->m_perag_tree, index);
 		if (!pag)
 			break;
-		xfs_buf_hash_destroy(pag);
+		xfs_buf_cache_destroy(&pag->pag_bcache);
 		xfs_defer_drain_free(&pag->pag_intents_drain);
 		kmem_free(pag);
 	}
diff --git a/libxfs/xfs_ag.h b/libxfs/xfs_ag.h
index 67c3260ee78..fe5852873b8 100644
--- a/libxfs/xfs_ag.h
+++ b/libxfs/xfs_ag.h
@@ -104,9 +104,7 @@ struct xfs_perag {
 	int		pag_ici_reclaimable;	/* reclaimable inodes */
 	unsigned long	pag_ici_reclaim_cursor;	/* reclaim restart point */
 
-	/* buffer cache index */
-	spinlock_t	pag_buf_lock;	/* lock for pag_buf_hash */
-	struct rhashtable pag_buf_hash;
+	struct xfs_buf_cache	pag_bcache;
 
 	/* background prealloc block trimming */
 	struct delayed_work	pag_blockgc_work;

[PATCH 05/10] libxfs: support in-memory buffer cache targets

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Allow the buffer cache to target in-memory files by connecting it to
xfiles.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/libxfs_io.h |    3 +++
 libxfs/rdwr.c      |   40 ++++++++++++++++++++++++++++++++++++++--
 2 files changed, 41 insertions(+), 2 deletions(-)


diff --git a/libxfs/libxfs_io.h b/libxfs/libxfs_io.h
index 7877e17685b..a20e78338dd 100644
--- a/libxfs/libxfs_io.h
+++ b/libxfs/libxfs_io.h
@@ -27,6 +27,7 @@ struct xfs_buftarg {
 	unsigned long		writes_left;
 	dev_t			bt_bdev;
 	int			bt_bdev_fd;
+	struct xfile		*bt_xfile;
 	unsigned int		flags;
 	struct cache		*bcache;	/* buffer cache */
 };
@@ -39,6 +40,8 @@ struct xfs_buftarg {
 #define XFS_BUFTARG_INJECT_WRITE_FAIL	(1 << 2)
 /* purge buffers when lookups find a size mismatch */
 #define XFS_BUFTARG_MISCOMPARE_PURGE	(1 << 3)
+/* use bt_xfile instead of bt_bdev/bt_bdev_fd */
+#define XFS_BUFTARG_XFILE		(1 << 4)
 
 /* Simulate the system crashing after a certain number of writes. */
 static inline void
diff --git a/libxfs/rdwr.c b/libxfs/rdwr.c
index f791136c982..645c4b7838d 100644
--- a/libxfs/rdwr.c
+++ b/libxfs/rdwr.c
@@ -18,7 +18,7 @@
 #include "xfs_inode.h"
 #include "xfs_trans.h"
 #include "libfrog/platform.h"
-
+#include "libxfs/xfile.h"
 #include "libxfs.h"
 
 static void libxfs_brelse(struct cache_node *node);
@@ -69,6 +69,9 @@ libxfs_device_zero(struct xfs_buftarg *btp, xfs_daddr_t start, uint len)
 	char		*z;
 	int		error;
 
+	if (btp->flags & XFS_BUFTARG_XFILE)
+		return -EOPNOTSUPP;
+
 	start_offset = LIBXFS_BBTOOFF64(start);
 
 	/* try to use special zeroing methods, fall back to writes if needed */
@@ -578,6 +581,31 @@ libxfs_balloc(
 	return &bp->b_node;
 }
 
+static inline int
+libxfs_buf_ioapply_in_memory(
+	struct xfs_buf		*bp,
+	bool			is_write)
+{
+	struct xfile		*xfile = bp->b_target->bt_xfile;
+	loff_t			pos = BBTOB(xfs_buf_daddr(bp));
+	size_t			size = BBTOB(bp->b_length);
+	int			error;
+
+	if (bp->b_nmaps > 1) {
+		/* We don't need or support multi-map buffers. */
+		ASSERT(0);
+		error = -EIO;
+	} else if (is_write) {
+		error = xfile_obj_store(xfile, bp->b_addr, size, pos);
+	} else {
+		error = xfile_obj_load(xfile, bp->b_addr, size, pos);
+	}
+	if (error)
+		bp->b_error = error;
+	else if (!is_write)
+		bp->b_flags |= LIBXFS_B_UPTODATE;
+	return error;
+}
 
 static int
 __read_buf(int fd, void *buf, int len, off64_t offset, int flags)
@@ -608,6 +636,9 @@ libxfs_readbufr(struct xfs_buftarg *btp, xfs_daddr_t blkno, struct xfs_buf *bp,
 
 	ASSERT(len <= bp->b_length);
 
+	if (bp->b_target->flags & XFS_BUFTARG_XFILE)
+		return libxfs_buf_ioapply_in_memory(bp, false);
+
 	error = __read_buf(fd, bp->b_addr, bytes, LIBXFS_BBTOOFF64(blkno), flags);
 	if (!error &&
 	    bp->b_target->bt_bdev == btp->bt_bdev &&
@@ -640,6 +671,9 @@ libxfs_readbufr_map(struct xfs_buftarg *btp, struct xfs_buf *bp, int flags)
 	void	*buf;
 	int	i;
 
+	if (bp->b_target->flags & XFS_BUFTARG_XFILE)
+		return libxfs_buf_ioapply_in_memory(bp, false);
+
 	buf = bp->b_addr;
 	for (i = 0; i < bp->b_nmaps; i++) {
 		off64_t	offset = LIBXFS_BBTOOFF64(bp->b_maps[i].bm_bn);
@@ -858,7 +892,9 @@ libxfs_bwrite(
 		}
 	}
 
-	if (!(bp->b_flags & LIBXFS_B_DISCONTIG)) {
+	if (bp->b_target->flags & XFS_BUFTARG_XFILE) {
+		libxfs_buf_ioapply_in_memory(bp, true);
+	} else if (!(bp->b_flags & LIBXFS_B_DISCONTIG)) {
 		bp->b_error = __write_buf(fd, bp->b_addr, BBTOB(bp->b_length),
 				    LIBXFS_BBTOOFF64(xfs_buf_daddr(bp)),
 				    bp->b_flags);

[PATCH 06/10] xfs: consolidate btree block freeing tracepoints

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Don't waste tracepoint segment memory on per-btree block freeing
tracepoints when we can do it from the generic btree code.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 include/xfs_trace.h         |    3 +--
 libxfs/xfs_btree.c          |    2 ++
 libxfs/xfs_refcount_btree.c |    2 --
 libxfs/xfs_rmap_btree.c     |    2 --
 4 files changed, 3 insertions(+), 6 deletions(-)


diff --git a/include/xfs_trace.h b/include/xfs_trace.h
index f172b61d6a5..98819653bcb 100644
--- a/include/xfs_trace.h
+++ b/include/xfs_trace.h
@@ -68,6 +68,7 @@
 #define trace_xfs_btree_commit_ifakeroot(a)	((void) 0)
 #define trace_xfs_btree_bload_level_geometry(a,b,c,d,e,f,g) ((void) 0)
 #define trace_xfs_btree_bload_block(a,b,c,d,e,f) ((void) 0)
+#define trace_xfs_btree_free_block(...)		((void) 0)
 
 #define trace_xfs_free_extent(a,b,c,d,e,f,g)	((void) 0)
 #define trace_xfs_agf(a,b,c,d)			((void) 0)
@@ -256,7 +257,6 @@
 #define trace_xfs_rmap_find_left_neighbor_result(...)	((void) 0)
 #define trace_xfs_rmap_lookup_le_range_result(...)	((void) 0)
 
-#define trace_xfs_rmapbt_free_block(...)	((void) 0)
 #define trace_xfs_rmapbt_alloc_block(...)	((void) 0)
 
 #define trace_xfs_ag_resv_critical(...)		((void) 0)
@@ -276,7 +276,6 @@
 #define trace_xfs_refcount_insert_error(...)	((void) 0)
 #define trace_xfs_refcount_delete(...)		((void) 0)
 #define trace_xfs_refcount_delete_error(...)	((void) 0)
-#define trace_xfs_refcountbt_free_block(...)	((void) 0)
 #define trace_xfs_refcountbt_alloc_block(...)	((void) 0)
 #define trace_xfs_refcount_rec_order_error(...)	((void) 0)
 
diff --git a/libxfs/xfs_btree.c b/libxfs/xfs_btree.c
index 4b4099c5635..14587e52840 100644
--- a/libxfs/xfs_btree.c
+++ b/libxfs/xfs_btree.c
@@ -411,6 +411,8 @@ xfs_btree_free_block(
 {
 	int			error;
 
+	trace_xfs_btree_free_block(cur, bp);
+
 	error = cur->bc_ops->free_block(cur, bp);
 	if (!error) {
 		xfs_trans_binval(cur->bc_tp, bp);
diff --git a/libxfs/xfs_refcount_btree.c b/libxfs/xfs_refcount_btree.c
index ac1c3ab868e..67551df02bd 100644
--- a/libxfs/xfs_refcount_btree.c
+++ b/libxfs/xfs_refcount_btree.c
@@ -106,8 +106,6 @@ xfs_refcountbt_free_block(
 	struct xfs_agf		*agf = agbp->b_addr;
 	xfs_fsblock_t		fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp));
 
-	trace_xfs_refcountbt_free_block(cur->bc_mp, cur->bc_ag.pag->pag_agno,
-			XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1);
 	be32_add_cpu(&agf->agf_refcount_blocks, -1);
 	xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_REFCOUNT_BLOCKS);
 	return xfs_free_extent_later(cur->bc_tp, fsbno, 1,
diff --git a/libxfs/xfs_rmap_btree.c b/libxfs/xfs_rmap_btree.c
index d6e2fc0a3f9..7966a3e6a47 100644
--- a/libxfs/xfs_rmap_btree.c
+++ b/libxfs/xfs_rmap_btree.c
@@ -123,8 +123,6 @@ xfs_rmapbt_free_block(
 	int			error;
 
 	bno = xfs_daddr_to_agbno(cur->bc_mp, xfs_buf_daddr(bp));
-	trace_xfs_rmapbt_free_block(cur->bc_mp, pag->pag_agno,
-			bno, 1);
 	be32_add_cpu(&agf->agf_rmap_blocks, -1);
 	xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_RMAP_BLOCKS);
 	error = xfs_alloc_put_freelist(pag, cur->bc_tp, agbp, NULL, bno, 1);

[PATCH 07/10] xfs: consolidate btree block allocation tracepoints

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Don't waste tracepoint segment memory on per-btree block allocation
tracepoints when we can do it from the generic btree code.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 include/xfs_trace.h         |    4 +---
 libxfs/xfs_btree.c          |   20 +++++++++++++++++---
 libxfs/xfs_refcount_btree.c |    2 --
 libxfs/xfs_rmap_btree.c     |    2 --
 4 files changed, 18 insertions(+), 10 deletions(-)


diff --git a/include/xfs_trace.h b/include/xfs_trace.h
index 98819653bcb..e7cbd0d9d41 100644
--- a/include/xfs_trace.h
+++ b/include/xfs_trace.h
@@ -69,6 +69,7 @@
 #define trace_xfs_btree_bload_level_geometry(a,b,c,d,e,f,g) ((void) 0)
 #define trace_xfs_btree_bload_block(a,b,c,d,e,f) ((void) 0)
 #define trace_xfs_btree_free_block(...)		((void) 0)
+#define trace_xfs_btree_alloc_block(...)	((void) 0)
 
 #define trace_xfs_free_extent(a,b,c,d,e,f,g)	((void) 0)
 #define trace_xfs_agf(a,b,c,d)			((void) 0)
@@ -257,8 +258,6 @@
 #define trace_xfs_rmap_find_left_neighbor_result(...)	((void) 0)
 #define trace_xfs_rmap_lookup_le_range_result(...)	((void) 0)
 
-#define trace_xfs_rmapbt_alloc_block(...)	((void) 0)
-
 #define trace_xfs_ag_resv_critical(...)		((void) 0)
 #define trace_xfs_ag_resv_needed(...)		((void) 0)
 #define trace_xfs_ag_resv_free(...)		((void) 0)
@@ -276,7 +275,6 @@
 #define trace_xfs_refcount_insert_error(...)	((void) 0)
 #define trace_xfs_refcount_delete(...)		((void) 0)
 #define trace_xfs_refcount_delete_error(...)	((void) 0)
-#define trace_xfs_refcountbt_alloc_block(...)	((void) 0)
 #define trace_xfs_refcount_rec_order_error(...)	((void) 0)
 
 #define trace_xfs_refcount_lookup(...)		((void) 0)
diff --git a/libxfs/xfs_btree.c b/libxfs/xfs_btree.c
index 14587e52840..d47847db3db 100644
--- a/libxfs/xfs_btree.c
+++ b/libxfs/xfs_btree.c
@@ -2690,6 +2690,20 @@ xfs_btree_rshift(
 	return error;
 }
 
+static inline int
+xfs_btree_alloc_block(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_ptr	*hint_block,
+	union xfs_btree_ptr		*new_block,
+	int				*stat)
+{
+	int				error;
+
+	error = cur->bc_ops->alloc_block(cur, hint_block, new_block, stat);
+	trace_xfs_btree_alloc_block(cur, new_block, *stat, error);
+	return error;
+}
+
 /*
  * Split cur/level block in half.
  * Return new block number and the key to its first
@@ -2733,7 +2747,7 @@ __xfs_btree_split(
 	xfs_btree_buf_to_ptr(cur, lbp, &lptr);
 
 	/* Allocate the new block. If we can't do it, we're toast. Give up. */
-	error = cur->bc_ops->alloc_block(cur, &lptr, &rptr, stat);
+	error = xfs_btree_alloc_block(cur, &lptr, &rptr, stat);
 	if (error)
 		goto error0;
 	if (*stat == 0)
@@ -3013,7 +3027,7 @@ xfs_btree_new_iroot(
 	pp = xfs_btree_ptr_addr(cur, 1, block);
 
 	/* Allocate the new block. If we can't do it, we're toast. Give up. */
-	error = cur->bc_ops->alloc_block(cur, pp, &nptr, stat);
+	error = xfs_btree_alloc_block(cur, pp, &nptr, stat);
 	if (error)
 		goto error0;
 	if (*stat == 0)
@@ -3113,7 +3127,7 @@ xfs_btree_new_root(
 	cur->bc_ops->init_ptr_from_cur(cur, &rptr);
 
 	/* Allocate the new block. If we can't do it, we're toast. Give up. */
-	error = cur->bc_ops->alloc_block(cur, &rptr, &lptr, stat);
+	error = xfs_btree_alloc_block(cur, &rptr, &lptr, stat);
 	if (error)
 		goto error0;
 	if (*stat == 0)
diff --git a/libxfs/xfs_refcount_btree.c b/libxfs/xfs_refcount_btree.c
index 67551df02bd..9a3c2270c25 100644
--- a/libxfs/xfs_refcount_btree.c
+++ b/libxfs/xfs_refcount_btree.c
@@ -76,8 +76,6 @@ xfs_refcountbt_alloc_block(
 					xfs_refc_block(args.mp)));
 	if (error)
 		goto out_error;
-	trace_xfs_refcountbt_alloc_block(cur->bc_mp, cur->bc_ag.pag->pag_agno,
-			args.agbno, 1);
 	if (args.fsbno == NULLFSBLOCK) {
 		*stat = 0;
 		return 0;
diff --git a/libxfs/xfs_rmap_btree.c b/libxfs/xfs_rmap_btree.c
index 7966a3e6a47..e894a22e087 100644
--- a/libxfs/xfs_rmap_btree.c
+++ b/libxfs/xfs_rmap_btree.c
@@ -92,8 +92,6 @@ xfs_rmapbt_alloc_block(
 				       &bno, 1);
 	if (error)
 		return error;
-
-	trace_xfs_rmapbt_alloc_block(cur->bc_mp, pag->pag_agno, bno, 1);
 	if (bno == NULLAGBLOCK) {
 		*stat = 0;
 		return 0;

[PATCH 08/10] xfs: support in-memory btrees

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Adapt the generic btree cursor code to be able to create a btree whose
buffers come from a (presumably in-memory) buftarg with a header block
that's specific to in-memory btrees.  We'll connect this to other parts
of online scrub in the next patches.

Note that in-memory btrees always have a block size matching the system
memory page size for efficiency reasons.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 include/libxfs.h       |    1 
 libxfs/Makefile        |    3 
 libxfs/init.c          |    2 
 libxfs/libxfs_io.h     |   10 +
 libxfs/libxfs_priv.h   |    1 
 libxfs/rdwr.c          |   29 ++++
 libxfs/xfbtree.c       |  343 ++++++++++++++++++++++++++++++++++++++++++++++++
 libxfs/xfbtree.h       |   36 +++++
 libxfs/xfile.c         |   18 +++
 libxfs/xfile.h         |   50 +++++++
 libxfs/xfs_btree.c     |  151 +++++++++++++++++----
 libxfs/xfs_btree.h     |   17 ++
 libxfs/xfs_btree_mem.h |   87 ++++++++++++
 13 files changed, 720 insertions(+), 28 deletions(-)
 create mode 100644 libxfs/xfbtree.c
 create mode 100644 libxfs/xfbtree.h
 create mode 100644 libxfs/xfs_btree_mem.h


diff --git a/include/libxfs.h b/include/libxfs.h
index 5251475cf15..43fb5425796 100644
--- a/include/libxfs.h
+++ b/include/libxfs.h
@@ -8,6 +8,7 @@
 #define __LIBXFS_H__
 
 #define CONFIG_XFS_RT
+#define CONFIG_XFS_BTREE_IN_XFILE
 
 #include "libxfs_api_defs.h"
 #include "platform_defs.h"
diff --git a/libxfs/Makefile b/libxfs/Makefile
index 68b366072da..8e6b2dfdfe1 100644
--- a/libxfs/Makefile
+++ b/libxfs/Makefile
@@ -26,6 +26,7 @@ HFILES = \
 	libxfs_priv.h \
 	linux-err.h \
 	topology.h \
+	xfbtree.h \
 	xfile.h \
 	xfs_ag_resv.h \
 	xfs_alloc.h \
@@ -36,6 +37,7 @@ HFILES = \
 	xfs_bmap.h \
 	xfs_bmap_btree.h \
 	xfs_btree.h \
+	xfs_btree_mem.h \
 	xfs_btree_staging.h \
 	xfs_attr_remote.h \
 	xfs_cksum.h \
@@ -67,6 +69,7 @@ CFILES = cache.c \
 	topology.c \
 	trans.c \
 	util.c \
+	xfbtree.c \
 	xfile.c \
 	xfs_ag.c \
 	xfs_ag_resv.c \
diff --git a/libxfs/init.c b/libxfs/init.c
index c776a9b07f5..6d088125f5d 100644
--- a/libxfs/init.c
+++ b/libxfs/init.c
@@ -22,6 +22,7 @@
 #include "xfs_rmap_btree.h"
 #include "xfs_refcount_btree.h"
 #include "libfrog/platform.h"
+#include "xfile.h"
 
 #include "xfs_format.h"
 #include "xfs_da_format.h"
@@ -253,6 +254,7 @@ int
 libxfs_init(struct libxfs_init *a)
 {
 	xfs_check_ondisk_structs();
+	xfile_libinit();
 	rcu_init();
 	rcu_register_thread();
 	radix_tree_init();
diff --git a/libxfs/libxfs_io.h b/libxfs/libxfs_io.h
index a20e78338dd..8a99955ee73 100644
--- a/libxfs/libxfs_io.h
+++ b/libxfs/libxfs_io.h
@@ -263,4 +263,14 @@ xfs_buf_delwri_queue_here(struct xfs_buf *bp, struct list_head *buffer_list)
 int xfs_buf_delwri_submit(struct list_head *buffer_list);
 void xfs_buf_delwri_cancel(struct list_head *list);
 
+xfs_daddr_t xfs_buftarg_nr_sectors(struct xfs_buftarg *btp);
+
+static inline bool
+xfs_buftarg_verify_daddr(
+	struct xfs_buftarg	*btp,
+	xfs_daddr_t		daddr)
+{
+	return daddr < xfs_buftarg_nr_sectors(btp);
+}
+
 #endif	/* __LIBXFS_IO_H__ */
diff --git a/libxfs/libxfs_priv.h b/libxfs/libxfs_priv.h
index 9310752a9b2..e3d9b70cc17 100644
--- a/libxfs/libxfs_priv.h
+++ b/libxfs/libxfs_priv.h
@@ -38,6 +38,7 @@
 #define __LIBXFS_INTERNAL_XFS_H__
 
 #define CONFIG_XFS_RT
+#define CONFIG_XFS_BTREE_IN_XFILE
 
 #include "libxfs_api_defs.h"
 #include "platform_defs.h"
diff --git a/libxfs/rdwr.c b/libxfs/rdwr.c
index 645c4b7838d..f352225f23d 100644
--- a/libxfs/rdwr.c
+++ b/libxfs/rdwr.c
@@ -1547,3 +1547,32 @@ __xfs_buf_mark_corrupt(
 	xfs_buf_corruption_error(bp, fa);
 	xfs_buf_stale(bp);
 }
+
+/* Return the number of sectors for a buffer target. */
+xfs_daddr_t
+xfs_buftarg_nr_sectors(
+	struct xfs_buftarg	*btp)
+{
+	struct stat		sb;
+	int			fd = btp->bt_bdev_fd;
+	int			ret;
+
+	if (btp->flags & XFS_BUFTARG_XFILE)
+		return xfile_size(btp->bt_xfile) >> BBSHIFT;
+
+	ret = fstat(fd, &sb);
+	if (ret)
+		return 0;
+
+	if (S_ISBLK(sb.st_mode)) {
+		uint64_t	sz;
+
+		ret = ioctl(fd, BLKGETSIZE64, &sz);
+		if (ret)
+			return 0;
+
+		return sz >> BBSHIFT;
+	}
+
+	return sb.st_size >> BBSHIFT;
+}
diff --git a/libxfs/xfbtree.c b/libxfs/xfbtree.c
new file mode 100644
index 00000000000..79585dd3a23
--- /dev/null
+++ b/libxfs/xfbtree.c
@@ -0,0 +1,343 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2021-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "libxfs_priv.h"
+#include "libxfs.h"
+#include "xfile.h"
+#include "xfbtree.h"
+#include "xfs_btree_mem.h"
+
+/* btree ops functions for in-memory btrees. */
+
+static xfs_failaddr_t
+xfs_btree_mem_head_verify(
+	struct xfs_buf			*bp)
+{
+	struct xfs_btree_mem_head	*mhead = bp->b_addr;
+	struct xfs_mount		*mp = bp->b_mount;
+
+	if (!xfs_verify_magic(bp, mhead->mh_magic))
+		return __this_address;
+	if (be32_to_cpu(mhead->mh_nlevels) == 0)
+		return __this_address;
+	if (!uuid_equal(&mhead->mh_uuid, &mp->m_sb.sb_meta_uuid))
+		return __this_address;
+
+	return NULL;
+}
+
+static void
+xfs_btree_mem_head_read_verify(
+	struct xfs_buf		*bp)
+{
+	xfs_failaddr_t		fa = xfs_btree_mem_head_verify(bp);
+
+	if (fa)
+		xfs_verifier_error(bp, -EFSCORRUPTED, fa);
+}
+
+static void
+xfs_btree_mem_head_write_verify(
+	struct xfs_buf		*bp)
+{
+	xfs_failaddr_t		fa = xfs_btree_mem_head_verify(bp);
+
+	if (fa)
+		xfs_verifier_error(bp, -EFSCORRUPTED, fa);
+}
+
+static const struct xfs_buf_ops xfs_btree_mem_head_buf_ops = {
+	.name			= "xfs_btree_mem_head",
+	.magic			= { cpu_to_be32(XFS_BTREE_MEM_HEAD_MAGIC),
+				    cpu_to_be32(XFS_BTREE_MEM_HEAD_MAGIC) },
+	.verify_read		= xfs_btree_mem_head_read_verify,
+	.verify_write		= xfs_btree_mem_head_write_verify,
+	.verify_struct		= xfs_btree_mem_head_verify,
+};
+
+/* Initialize the header block for an in-memory btree. */
+static inline void
+xfs_btree_mem_head_init(
+	struct xfs_buf			*head_bp,
+	unsigned long long		owner,
+	xfileoff_t			leaf_xfoff)
+{
+	struct xfs_btree_mem_head	*mhead = head_bp->b_addr;
+	struct xfs_mount		*mp = head_bp->b_mount;
+
+	mhead->mh_magic = cpu_to_be32(XFS_BTREE_MEM_HEAD_MAGIC);
+	mhead->mh_nlevels = cpu_to_be32(1);
+	mhead->mh_owner = cpu_to_be64(owner);
+	mhead->mh_root = cpu_to_be64(leaf_xfoff);
+	uuid_copy(&mhead->mh_uuid, &mp->m_sb.sb_meta_uuid);
+
+	head_bp->b_ops = &xfs_btree_mem_head_buf_ops;
+}
+
+/* Return tree height from the in-memory btree head. */
+unsigned int
+xfs_btree_mem_head_nlevels(
+	struct xfs_buf			*head_bp)
+{
+	struct xfs_btree_mem_head	*mhead = head_bp->b_addr;
+
+	return be32_to_cpu(mhead->mh_nlevels);
+}
+
+/* Extract the buftarg target for this xfile btree. */
+struct xfs_buftarg *
+xfbtree_target(struct xfbtree *xfbtree)
+{
+	return xfbtree->target;
+}
+
+/* Is this daddr (sector offset) contained within the buffer target? */
+static inline bool
+xfbtree_verify_buftarg_xfileoff(
+	struct xfs_buftarg	*btp,
+	xfileoff_t		xfoff)
+{
+	xfs_daddr_t		xfoff_daddr = xfo_to_daddr(xfoff);
+
+	return xfs_buftarg_verify_daddr(btp, xfoff_daddr);
+}
+
+/* Is this btree xfile offset contained within the xfile? */
+bool
+xfbtree_verify_xfileoff(
+	struct xfs_btree_cur	*cur,
+	unsigned long long	xfoff)
+{
+	struct xfs_buftarg	*btp = xfbtree_target(cur->bc_mem.xfbtree);
+
+	return xfbtree_verify_buftarg_xfileoff(btp, xfoff);
+}
+
+/* Check if a btree pointer is reasonable. */
+int
+xfbtree_check_ptr(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_ptr	*ptr,
+	int				index,
+	int				level)
+{
+	xfileoff_t			bt_xfoff;
+	xfs_failaddr_t			fa = NULL;
+
+	ASSERT(cur->bc_flags & XFS_BTREE_IN_XFILE);
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+		bt_xfoff = be64_to_cpu(ptr->l);
+	else
+		bt_xfoff = be32_to_cpu(ptr->s);
+
+	if (!xfbtree_verify_xfileoff(cur, bt_xfoff))
+		fa = __this_address;
+
+	if (fa) {
+		xfs_err(cur->bc_mp,
+"In-memory: Corrupt btree %d flags 0x%x pointer at level %d index %d fa %pS.",
+				cur->bc_btnum, cur->bc_flags, level, index,
+				fa);
+		return -EFSCORRUPTED;
+	}
+	return 0;
+}
+
+/* Convert a btree pointer to a daddr */
+xfs_daddr_t
+xfbtree_ptr_to_daddr(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_ptr	*ptr)
+{
+	xfileoff_t			bt_xfoff;
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+		bt_xfoff = be64_to_cpu(ptr->l);
+	else
+		bt_xfoff = be32_to_cpu(ptr->s);
+	return xfo_to_daddr(bt_xfoff);
+}
+
+/* Set the pointer to point to this buffer. */
+void
+xfbtree_buf_to_ptr(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp,
+	union xfs_btree_ptr	*ptr)
+{
+	xfileoff_t		xfoff = xfs_daddr_to_xfo(xfs_buf_daddr(bp));
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+		ptr->l = cpu_to_be64(xfoff);
+	else
+		ptr->s = cpu_to_be32(xfoff);
+}
+
+/* Return the in-memory btree block size, in units of 512 bytes. */
+unsigned int xfbtree_bbsize(void)
+{
+	return xfo_to_daddr(1);
+}
+
+/* Set the root of an in-memory btree. */
+void
+xfbtree_set_root(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_ptr	*ptr,
+	int				inc)
+{
+	struct xfs_buf			*head_bp = cur->bc_mem.head_bp;
+	struct xfs_btree_mem_head	*mhead = head_bp->b_addr;
+
+	ASSERT(cur->bc_flags & XFS_BTREE_IN_XFILE);
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+		mhead->mh_root = ptr->l;
+	} else {
+		uint32_t		root = be32_to_cpu(ptr->s);
+
+		mhead->mh_root = cpu_to_be64(root);
+	}
+	be32_add_cpu(&mhead->mh_nlevels, inc);
+	xfs_trans_log_buf(cur->bc_tp, head_bp, 0, sizeof(*mhead) - 1);
+}
+
+/* Initialize a pointer from the in-memory btree header. */
+void
+xfbtree_init_ptr_from_cur(
+	struct xfs_btree_cur		*cur,
+	union xfs_btree_ptr		*ptr)
+{
+	struct xfs_buf			*head_bp = cur->bc_mem.head_bp;
+	struct xfs_btree_mem_head	*mhead = head_bp->b_addr;
+
+	ASSERT(cur->bc_flags & XFS_BTREE_IN_XFILE);
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+		ptr->l = mhead->mh_root;
+	} else {
+		uint64_t		root = be64_to_cpu(mhead->mh_root);
+
+		ptr->s = cpu_to_be32(root);
+	}
+}
+
+/* Duplicate an in-memory btree cursor. */
+struct xfs_btree_cur *
+xfbtree_dup_cursor(
+	struct xfs_btree_cur		*cur)
+{
+	struct xfs_btree_cur		*ncur;
+
+	ASSERT(cur->bc_flags & XFS_BTREE_IN_XFILE);
+
+	ncur = xfs_btree_alloc_cursor(cur->bc_mp, cur->bc_tp, cur->bc_btnum,
+			cur->bc_maxlevels, cur->bc_cache);
+	ncur->bc_flags = cur->bc_flags;
+	ncur->bc_nlevels = cur->bc_nlevels;
+	ncur->bc_statoff = cur->bc_statoff;
+	ncur->bc_ops = cur->bc_ops;
+	memcpy(&ncur->bc_mem, &cur->bc_mem, sizeof(cur->bc_mem));
+
+	if (cur->bc_mem.pag)
+		ncur->bc_mem.pag = xfs_perag_hold(cur->bc_mem.pag);
+
+	return ncur;
+}
+
+/* Check the owner of an in-memory btree block. */
+xfs_failaddr_t
+xfbtree_check_block_owner(
+	struct xfs_btree_cur	*cur,
+	struct xfs_btree_block	*block)
+{
+	struct xfbtree		*xfbt = cur->bc_mem.xfbtree;
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+		if (be64_to_cpu(block->bb_u.l.bb_owner) != xfbt->owner)
+			return __this_address;
+
+		return NULL;
+	}
+
+	if (be32_to_cpu(block->bb_u.s.bb_owner) != xfbt->owner)
+		return __this_address;
+
+	return NULL;
+}
+
+/* Return the owner of this in-memory btree. */
+unsigned long long
+xfbtree_owner(
+	struct xfs_btree_cur	*cur)
+{
+	return cur->bc_mem.xfbtree->owner;
+}
+
+/* Return the xfile offset (in blocks) of a btree buffer. */
+unsigned long long
+xfbtree_buf_to_xfoff(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp)
+{
+	ASSERT(cur->bc_flags & XFS_BTREE_IN_XFILE);
+
+	return xfs_daddr_to_xfo(xfs_buf_daddr(bp));
+}
+
+/* Verify a long-format btree block. */
+xfs_failaddr_t
+xfbtree_lblock_verify(
+	struct xfs_buf		*bp,
+	unsigned int		max_recs)
+{
+	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
+	struct xfs_buftarg	*btp = bp->b_target;
+
+	/* numrecs verification */
+	if (be16_to_cpu(block->bb_numrecs) > max_recs)
+		return __this_address;
+
+	/* sibling pointer verification */
+	if (block->bb_u.l.bb_leftsib != cpu_to_be64(NULLFSBLOCK) &&
+	    !xfbtree_verify_buftarg_xfileoff(btp,
+				be64_to_cpu(block->bb_u.l.bb_leftsib)))
+		return __this_address;
+
+	if (block->bb_u.l.bb_rightsib != cpu_to_be64(NULLFSBLOCK) &&
+	    !xfbtree_verify_buftarg_xfileoff(btp,
+				be64_to_cpu(block->bb_u.l.bb_rightsib)))
+		return __this_address;
+
+	return NULL;
+}
+
+/* Verify a short-format btree block. */
+xfs_failaddr_t
+xfbtree_sblock_verify(
+	struct xfs_buf		*bp,
+	unsigned int		max_recs)
+{
+	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
+	struct xfs_buftarg	*btp = bp->b_target;
+
+	/* numrecs verification */
+	if (be16_to_cpu(block->bb_numrecs) > max_recs)
+		return __this_address;
+
+	/* sibling pointer verification */
+	if (block->bb_u.s.bb_leftsib != cpu_to_be32(NULLAGBLOCK) &&
+	    !xfbtree_verify_buftarg_xfileoff(btp,
+				be32_to_cpu(block->bb_u.s.bb_leftsib)))
+		return __this_address;
+
+	if (block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK) &&
+	    !xfbtree_verify_buftarg_xfileoff(btp,
+				be32_to_cpu(block->bb_u.s.bb_rightsib)))
+		return __this_address;
+
+	return NULL;
+}
diff --git a/libxfs/xfbtree.h b/libxfs/xfbtree.h
new file mode 100644
index 00000000000..292bade32d2
--- /dev/null
+++ b/libxfs/xfbtree.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2021-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __LIBXFS_XFBTREE_H__
+#define __LIBXFS_XFBTREE_H__
+
+#ifdef CONFIG_XFS_BTREE_IN_XFILE
+
+/* Root block for an in-memory btree. */
+struct xfs_btree_mem_head {
+	__be32				mh_magic;
+	__be32				mh_nlevels;
+	__be64				mh_owner;
+	__be64				mh_root;
+	uuid_t				mh_uuid;
+};
+
+#define XFS_BTREE_MEM_HEAD_MAGIC	0x4341544D	/* "CATM" */
+
+/* in-memory btree header is always block 0 in the backing store */
+#define XFS_BTREE_MEM_HEAD_DADDR	0
+
+/* xfile-backed in-memory btrees */
+
+struct xfbtree {
+	struct xfs_buftarg		*target;
+
+	/* Owner of this btree. */
+	unsigned long long		owner;
+};
+
+#endif /* CONFIG_XFS_BTREE_IN_XFILE */
+
+#endif /* __LIBXFS_XFBTREE_H__ */
diff --git a/libxfs/xfile.c b/libxfs/xfile.c
index 57694d33498..d6eefadae69 100644
--- a/libxfs/xfile.c
+++ b/libxfs/xfile.c
@@ -6,6 +6,7 @@
 #include "libxfs_priv.h"
 #include "libxfs.h"
 #include "libxfs/xfile.h"
+#include "libfrog/util.h"
 #ifdef HAVE_MEMFD_NOEXEC_SEAL
 # include <linux/memfd.h>
 #endif
@@ -29,6 +30,23 @@
  * management; file locks are not taken.
  */
 
+/* Figure out the xfile block size here */
+unsigned int		XFB_BLOCKSIZE;
+unsigned int		XFB_BSHIFT;
+
+void
+xfile_libinit(void)
+{
+	long		ret = sysconf(_SC_PAGESIZE);
+
+	/* If we don't find a power-of-two page size, go with 4k. */
+	if (ret < 0 || !is_power_of_2(ret))
+		ret = 4096;
+
+	XFB_BLOCKSIZE = ret;
+	XFB_BSHIFT = libxfs_highbit32(XFB_BLOCKSIZE);
+}
+
 /*
  * Open a memory-backed fd to back an xfile.  We require close-on-exec here,
  * because these memfd files function as windowed RAM and hence should never
diff --git a/libxfs/xfile.h b/libxfs/xfile.h
index 4218c17e8bf..e762e392caa 100644
--- a/libxfs/xfile.h
+++ b/libxfs/xfile.h
@@ -10,6 +10,8 @@ struct xfile {
 	int		fd;
 };
 
+void xfile_libinit(void);
+
 int xfile_create(const char *description, struct xfile **xfilep);
 void xfile_destroy(struct xfile *xf);
 
@@ -53,4 +55,52 @@ int xfile_stat(struct xfile *xf, struct xfile_stat *statbuf);
 unsigned long long xfile_bytes(struct xfile *xf);
 int xfile_dump(struct xfile *xf);
 
+static inline loff_t xfile_size(struct xfile *xf)
+{
+	struct xfile_stat	xs;
+	int			ret;
+
+	ret = xfile_stat(xf, &xs);
+	if (ret)
+		return 0;
+
+	return xs.size;
+}
+
+/* file block (aka system page size) to basic block conversions. */
+typedef unsigned long long	xfileoff_t;
+extern unsigned int		XFB_BLOCKSIZE;
+extern unsigned int		XFB_BSHIFT;
+#define XFB_SHIFT		(XFB_BSHIFT - BBSHIFT)
+
+static inline loff_t xfo_to_b(xfileoff_t xfoff)
+{
+	return xfoff << XFB_BSHIFT;
+}
+
+static inline xfileoff_t b_to_xfo(loff_t pos)
+{
+	return (pos + (XFB_BLOCKSIZE - 1)) >> XFB_BSHIFT;
+}
+
+static inline xfileoff_t b_to_xfot(loff_t pos)
+{
+	return pos >> XFB_BSHIFT;
+}
+
+static inline xfs_daddr_t xfo_to_daddr(xfileoff_t xfoff)
+{
+	return xfoff << XFB_SHIFT;
+}
+
+static inline xfileoff_t xfs_daddr_to_xfo(xfs_daddr_t bb)
+{
+	return (bb + (xfo_to_daddr(1) - 1)) >> XFB_SHIFT;
+}
+
+static inline xfileoff_t xfs_daddr_to_xfot(xfs_daddr_t bb)
+{
+	return bb >> XFB_SHIFT;
+}
+
 #endif /* __LIBXFS_XFILE_H__ */
diff --git a/libxfs/xfs_btree.c b/libxfs/xfs_btree.c
index d47847db3db..14f0f017759 100644
--- a/libxfs/xfs_btree.c
+++ b/libxfs/xfs_btree.c
@@ -25,6 +25,9 @@
 #include "xfs_rmap_btree.h"
 #include "xfs_refcount_btree.h"
 #include "xfs_health.h"
+#include "xfile.h"
+#include "xfbtree.h"
+#include "xfs_btree_mem.h"
 
 /*
  * Btree magic numbers.
@@ -79,6 +82,9 @@ xfs_btree_check_lblock_siblings(
 	if (level >= 0) {
 		if (!xfs_btree_check_lptr(cur, sibling, level + 1))
 			return __this_address;
+	} else if (cur && (cur->bc_flags & XFS_BTREE_IN_XFILE)) {
+		if (!xfbtree_verify_xfileoff(cur, sibling))
+			return __this_address;
 	} else {
 		if (!xfs_verify_fsbno(mp, sibling))
 			return __this_address;
@@ -106,6 +112,9 @@ xfs_btree_check_sblock_siblings(
 	if (level >= 0) {
 		if (!xfs_btree_check_sptr(cur, sibling, level + 1))
 			return __this_address;
+	} else if (cur && (cur->bc_flags & XFS_BTREE_IN_XFILE)) {
+		if (!xfbtree_verify_xfileoff(cur, sibling))
+			return __this_address;
 	} else {
 		if (!xfs_verify_agbno(pag, sibling))
 			return __this_address;
@@ -148,7 +157,9 @@ __xfs_btree_check_lblock(
 	    cur->bc_ops->get_maxrecs(cur, level))
 		return __this_address;
 
-	if (bp)
+	if ((cur->bc_flags & XFS_BTREE_IN_XFILE) && bp)
+		fsb = xfbtree_buf_to_xfoff(cur, bp);
+	else if (bp)
 		fsb = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp));
 
 	fa = xfs_btree_check_lblock_siblings(mp, cur, level, fsb,
@@ -215,8 +226,12 @@ __xfs_btree_check_sblock(
 	    cur->bc_ops->get_maxrecs(cur, level))
 		return __this_address;
 
-	if (bp)
+	if ((cur->bc_flags & XFS_BTREE_IN_XFILE) && bp) {
+		pag = NULL;
+		agbno = xfbtree_buf_to_xfoff(cur, bp);
+	} else if (bp) {
 		agbno = xfs_daddr_to_agbno(mp, xfs_buf_daddr(bp));
+	}
 
 	fa = xfs_btree_check_sblock_siblings(pag, cur, level, agbno,
 			block->bb_u.s.bb_leftsib);
@@ -273,6 +288,8 @@ xfs_btree_check_lptr(
 {
 	if (level <= 0)
 		return false;
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		return xfbtree_verify_xfileoff(cur, fsbno);
 	return xfs_verify_fsbno(cur->bc_mp, fsbno);
 }
 
@@ -285,6 +302,8 @@ xfs_btree_check_sptr(
 {
 	if (level <= 0)
 		return false;
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		return xfbtree_verify_xfileoff(cur, agbno);
 	return xfs_verify_agbno(cur->bc_ag.pag, agbno);
 }
 
@@ -299,6 +318,9 @@ xfs_btree_check_ptr(
 	int				index,
 	int				level)
 {
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		return xfbtree_check_ptr(cur, ptr, index, level);
+
 	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
 		if (xfs_btree_check_lptr(cur, be64_to_cpu((&ptr->l)[index]),
 				level))
@@ -455,11 +477,36 @@ xfs_btree_del_cursor(
 	       xfs_is_shutdown(cur->bc_mp) || error != 0);
 	if (unlikely(cur->bc_flags & XFS_BTREE_STAGING))
 		kmem_free(cur->bc_ops);
-	if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS) && cur->bc_ag.pag)
+	if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS) &&
+	    !(cur->bc_flags & XFS_BTREE_IN_XFILE) && cur->bc_ag.pag)
 		xfs_perag_put(cur->bc_ag.pag);
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE) {
+		if (cur->bc_mem.pag)
+			xfs_perag_put(cur->bc_mem.pag);
+	}
 	kmem_cache_free(cur->bc_cache, cur);
 }
 
+/* Return the buffer target for this btree's buffer. */
+static inline struct xfs_buftarg *
+xfs_btree_buftarg(
+	struct xfs_btree_cur	*cur)
+{
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		return xfbtree_target(cur->bc_mem.xfbtree);
+	return cur->bc_mp->m_ddev_targp;
+}
+
+/* Return the block size (in units of 512b sectors) for this btree. */
+static inline unsigned int
+xfs_btree_bbsize(
+	struct xfs_btree_cur	*cur)
+{
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		return xfbtree_bbsize();
+	return cur->bc_mp->m_bsize;
+}
+
 /*
  * Duplicate the btree cursor.
  * Allocate a new one, copy the record, re-get the buffers.
@@ -497,10 +544,11 @@ xfs_btree_dup_cursor(
 		new->bc_levels[i].ra = cur->bc_levels[i].ra;
 		bp = cur->bc_levels[i].bp;
 		if (bp) {
-			error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
-						   xfs_buf_daddr(bp), mp->m_bsize,
-						   0, &bp,
-						   cur->bc_ops->buf_ops);
+			error = xfs_trans_read_buf(mp, tp,
+					xfs_btree_buftarg(cur),
+					xfs_buf_daddr(bp),
+					xfs_btree_bbsize(cur), 0, &bp,
+					cur->bc_ops->buf_ops);
 			if (xfs_metadata_is_sick(error))
 				xfs_btree_mark_sick(new);
 			if (error) {
@@ -941,6 +989,9 @@ xfs_btree_readahead_lblock(
 	xfs_fsblock_t		left = be64_to_cpu(block->bb_u.l.bb_leftsib);
 	xfs_fsblock_t		right = be64_to_cpu(block->bb_u.l.bb_rightsib);
 
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		return 0;
+
 	if ((lr & XFS_BTCUR_LEFTRA) && left != NULLFSBLOCK) {
 		xfs_btree_reada_bufl(cur->bc_mp, left, 1,
 				     cur->bc_ops->buf_ops);
@@ -966,6 +1017,8 @@ xfs_btree_readahead_sblock(
 	xfs_agblock_t		left = be32_to_cpu(block->bb_u.s.bb_leftsib);
 	xfs_agblock_t		right = be32_to_cpu(block->bb_u.s.bb_rightsib);
 
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		return 0;
 
 	if ((lr & XFS_BTCUR_LEFTRA) && left != NULLAGBLOCK) {
 		xfs_btree_reada_bufs(cur->bc_mp, cur->bc_ag.pag->pag_agno,
@@ -1027,6 +1080,11 @@ xfs_btree_ptr_to_daddr(
 	if (error)
 		return error;
 
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE) {
+		*daddr = xfbtree_ptr_to_daddr(cur, ptr);
+		return 0;
+	}
+
 	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
 		fsbno = be64_to_cpu(ptr->l);
 		*daddr = XFS_FSB_TO_DADDR(cur->bc_mp, fsbno);
@@ -1055,8 +1113,9 @@ xfs_btree_readahead_ptr(
 
 	if (xfs_btree_ptr_to_daddr(cur, ptr, &daddr))
 		return;
-	xfs_buf_readahead(cur->bc_mp->m_ddev_targp, daddr,
-			  cur->bc_mp->m_bsize * count, cur->bc_ops->buf_ops);
+	xfs_buf_readahead(xfs_btree_buftarg(cur), daddr,
+			xfs_btree_bbsize(cur) * count,
+			cur->bc_ops->buf_ops);
 }
 
 /*
@@ -1230,7 +1289,9 @@ xfs_btree_init_block_cur(
 	 * change in future, but is safe for current users of the generic btree
 	 * code.
 	 */
-	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		owner = xfbtree_owner(cur);
+	else if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
 		owner = cur->bc_ino.ip->i_ino;
 	else
 		owner = cur->bc_ag.pag->pag_agno;
@@ -1270,6 +1331,11 @@ xfs_btree_buf_to_ptr(
 	struct xfs_buf		*bp,
 	union xfs_btree_ptr	*ptr)
 {
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE) {
+		xfbtree_buf_to_ptr(cur, bp, ptr);
+		return;
+	}
+
 	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
 		ptr->l = cpu_to_be64(XFS_DADDR_TO_FSB(cur->bc_mp,
 					xfs_buf_daddr(bp)));
@@ -1314,15 +1380,14 @@ xfs_btree_get_buf_block(
 	struct xfs_btree_block		**block,
 	struct xfs_buf			**bpp)
 {
-	struct xfs_mount	*mp = cur->bc_mp;
-	xfs_daddr_t		d;
-	int			error;
+	xfs_daddr_t			d;
+	int				error;
 
 	error = xfs_btree_ptr_to_daddr(cur, ptr, &d);
 	if (error)
 		return error;
-	error = xfs_trans_get_buf(cur->bc_tp, mp->m_ddev_targp, d, mp->m_bsize,
-			0, bpp);
+	error = xfs_trans_get_buf(cur->bc_tp, xfs_btree_buftarg(cur), d,
+			xfs_btree_bbsize(cur), 0, bpp);
 	if (error)
 		return error;
 
@@ -1353,9 +1418,9 @@ xfs_btree_read_buf_block(
 	error = xfs_btree_ptr_to_daddr(cur, ptr, &d);
 	if (error)
 		return error;
-	error = xfs_trans_read_buf(mp, cur->bc_tp, mp->m_ddev_targp, d,
-				   mp->m_bsize, flags, bpp,
-				   cur->bc_ops->buf_ops);
+	error = xfs_trans_read_buf(mp, cur->bc_tp, xfs_btree_buftarg(cur), d,
+			xfs_btree_bbsize(cur), flags, bpp,
+			cur->bc_ops->buf_ops);
 	if (xfs_metadata_is_sick(error))
 		xfs_btree_mark_sick(cur);
 	if (error)
@@ -1795,6 +1860,37 @@ xfs_btree_decrement(
 	return error;
 }
 
+/*
+ * Check the btree block owner now that we have the context to know who the
+ * real owner is.
+ */
+static inline xfs_failaddr_t
+xfs_btree_check_block_owner(
+	struct xfs_btree_cur	*cur,
+	struct xfs_btree_block	*block)
+{
+	if (!xfs_has_crc(cur->bc_mp))
+		return NULL;
+
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		return xfbtree_check_block_owner(cur, block);
+
+	if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS)) {
+		if (be32_to_cpu(block->bb_u.s.bb_owner) !=
+						cur->bc_ag.pag->pag_agno)
+			return __this_address;
+		return NULL;
+	}
+
+	if (cur->bc_ino.flags & XFS_BTCUR_BMBT_INVALID_OWNER)
+		return NULL;
+
+	if (be64_to_cpu(block->bb_u.l.bb_owner) != cur->bc_ino.ip->i_ino)
+		return __this_address;
+
+	return NULL;
+}
+
 int
 xfs_btree_lookup_get_block(
 	struct xfs_btree_cur		*cur,	/* btree cursor */
@@ -1833,11 +1929,7 @@ xfs_btree_lookup_get_block(
 		return error;
 
 	/* Check the inode owner since the verifiers don't. */
-	if (xfs_has_crc(cur->bc_mp) &&
-	    !(cur->bc_ino.flags & XFS_BTCUR_BMBT_INVALID_OWNER) &&
-	    (cur->bc_flags & XFS_BTREE_LONG_PTRS) &&
-	    be64_to_cpu((*blkp)->bb_u.l.bb_owner) !=
-			cur->bc_ino.ip->i_ino)
+	if (xfs_btree_check_block_owner(cur, *blkp) != NULL)
 		goto out_bad;
 
 	/* Did we get the level we were looking for? */
@@ -4383,7 +4475,7 @@ xfs_btree_visit_block(
 {
 	struct xfs_btree_block		*block;
 	struct xfs_buf			*bp;
-	union xfs_btree_ptr		rptr;
+	union xfs_btree_ptr		rptr, bufptr;
 	int				error;
 
 	/* do right sibling readahead */
@@ -4406,15 +4498,14 @@ xfs_btree_visit_block(
 	 * return the same block without checking if the right sibling points
 	 * back to us and creates a cyclic reference in the btree.
 	 */
+	xfs_btree_buf_to_ptr(cur, bp, &bufptr);
 	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
-		if (be64_to_cpu(rptr.l) == XFS_DADDR_TO_FSB(cur->bc_mp,
-							xfs_buf_daddr(bp))) {
+		if (rptr.l == bufptr.l) {
 			xfs_btree_mark_sick(cur);
 			return -EFSCORRUPTED;
 		}
 	} else {
-		if (be32_to_cpu(rptr.s) == xfs_daddr_to_agbno(cur->bc_mp,
-							xfs_buf_daddr(bp))) {
+		if (rptr.s == bufptr.s) {
 			xfs_btree_mark_sick(cur);
 			return -EFSCORRUPTED;
 		}
@@ -4596,6 +4687,8 @@ xfs_btree_lblock_verify(
 	xfs_fsblock_t		fsb;
 	xfs_failaddr_t		fa;
 
+	ASSERT(!(bp->b_target->bt_flags & XFS_BUFTARG_XFILE));
+
 	/* numrecs verification */
 	if (be16_to_cpu(block->bb_numrecs) > max_recs)
 		return __this_address;
@@ -4651,6 +4744,8 @@ xfs_btree_sblock_verify(
 	xfs_agblock_t		agbno;
 	xfs_failaddr_t		fa;
 
+	ASSERT(!(bp->b_target->bt_flags & XFS_BUFTARG_XFILE));
+
 	/* numrecs verification */
 	if (be16_to_cpu(block->bb_numrecs) > max_recs)
 		return __this_address;
diff --git a/libxfs/xfs_btree.h b/libxfs/xfs_btree.h
index d906324e25c..3e6bdbc5070 100644
--- a/libxfs/xfs_btree.h
+++ b/libxfs/xfs_btree.h
@@ -248,6 +248,15 @@ struct xfs_btree_cur_ino {
 #define	XFS_BTCUR_BMBT_INVALID_OWNER	(1 << 1)
 };
 
+/* In-memory btree information */
+struct xfbtree;
+
+struct xfs_btree_cur_mem {
+	struct xfbtree			*xfbtree;
+	struct xfs_buf			*head_bp;
+	struct xfs_perag		*pag;
+};
+
 struct xfs_btree_level {
 	/* buffer pointer */
 	struct xfs_buf		*bp;
@@ -287,6 +296,7 @@ struct xfs_btree_cur
 	union {
 		struct xfs_btree_cur_ag	bc_ag;
 		struct xfs_btree_cur_ino bc_ino;
+		struct xfs_btree_cur_mem bc_mem;
 	};
 
 	/* Must be at the end of the struct! */
@@ -317,6 +327,13 @@ xfs_btree_cur_sizeof(unsigned int nlevels)
  */
 #define XFS_BTREE_STAGING		(1<<5)
 
+/* btree stored in memory; not compatible with ROOT_IN_INODE */
+#ifdef CONFIG_XFS_BTREE_IN_XFILE
+# define XFS_BTREE_IN_XFILE		(1<<7)
+#else
+# define XFS_BTREE_IN_XFILE		(0)
+#endif
+
 #define	XFS_BTREE_NOERROR	0
 #define	XFS_BTREE_ERROR		1
 
diff --git a/libxfs/xfs_btree_mem.h b/libxfs/xfs_btree_mem.h
new file mode 100644
index 00000000000..2c42ca85c58
--- /dev/null
+++ b/libxfs/xfs_btree_mem.h
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2021-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_BTREE_MEM_H__
+#define __XFS_BTREE_MEM_H__
+
+struct xfbtree;
+
+#ifdef CONFIG_XFS_BTREE_IN_XFILE
+unsigned int xfs_btree_mem_head_nlevels(struct xfs_buf *head_bp);
+
+struct xfs_buftarg *xfbtree_target(struct xfbtree *xfbtree);
+int xfbtree_check_ptr(struct xfs_btree_cur *cur,
+		const union xfs_btree_ptr *ptr, int index, int level);
+xfs_daddr_t xfbtree_ptr_to_daddr(struct xfs_btree_cur *cur,
+		const union xfs_btree_ptr *ptr);
+void xfbtree_buf_to_ptr(struct xfs_btree_cur *cur, struct xfs_buf *bp,
+		union xfs_btree_ptr *ptr);
+
+unsigned int xfbtree_bbsize(void);
+
+void xfbtree_set_root(struct xfs_btree_cur *cur,
+		const union xfs_btree_ptr *ptr, int inc);
+void xfbtree_init_ptr_from_cur(struct xfs_btree_cur *cur,
+		union xfs_btree_ptr *ptr);
+struct xfs_btree_cur *xfbtree_dup_cursor(struct xfs_btree_cur *cur);
+bool xfbtree_verify_xfileoff(struct xfs_btree_cur *cur,
+		unsigned long long xfoff);
+xfs_failaddr_t xfbtree_check_block_owner(struct xfs_btree_cur *cur,
+		struct xfs_btree_block *block);
+unsigned long long xfbtree_owner(struct xfs_btree_cur *cur);
+xfs_failaddr_t xfbtree_lblock_verify(struct xfs_buf *bp, unsigned int max_recs);
+xfs_failaddr_t xfbtree_sblock_verify(struct xfs_buf *bp, unsigned int max_recs);
+unsigned long long xfbtree_buf_to_xfoff(struct xfs_btree_cur *cur,
+		struct xfs_buf *bp);
+#else
+static inline unsigned int xfs_btree_mem_head_nlevels(struct xfs_buf *head_bp)
+{
+	return 0;
+}
+
+static inline struct xfs_buftarg *
+xfbtree_target(struct xfbtree *xfbtree)
+{
+	return NULL;
+}
+
+static inline int
+xfbtree_check_ptr(struct xfs_btree_cur *cur, const union xfs_btree_ptr *ptr,
+		  int index, int level)
+{
+	return 0;
+}
+
+static inline xfs_daddr_t
+xfbtree_ptr_to_daddr(struct xfs_btree_cur *cur, const union xfs_btree_ptr *ptr)
+{
+	return 0;
+}
+
+static inline void
+xfbtree_buf_to_ptr(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp,
+	union xfs_btree_ptr	*ptr)
+{
+	memset(ptr, 0xFF, sizeof(*ptr));
+}
+
+static inline unsigned int xfbtree_bbsize(void)
+{
+	return 0;
+}
+
+#define xfbtree_set_root			NULL
+#define xfbtree_init_ptr_from_cur		NULL
+#define xfbtree_dup_cursor			NULL
+#define xfbtree_verify_xfileoff(cur, xfoff)	(false)
+#define xfbtree_check_block_owner(cur, block)	NULL
+#define xfbtree_owner(cur)			(0ULL)
+#define xfbtree_buf_to_xfoff(cur, bp)		(-1)
+
+#endif /* CONFIG_XFS_BTREE_IN_XFILE */
+
+#endif /* __XFS_BTREE_MEM_H__ */

[PATCH 09/10] xfs: connect in-memory btrees to xfiles

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add to our stubbed-out in-memory btrees the ability to connect them with
an actual in-memory backing file (aka xfiles) and the necessary pieces
to track free space in the xfile and flush dirty xfbtree buffers on
demand, which we'll need for online repair.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 include/xfs_mount.h    |   10 +
 include/xfs_trace.h    |    8 +
 include/xfs_trans.h    |    1 
 libfrog/bitmap.c       |   64 ++++++-
 libfrog/bitmap.h       |    3 
 libxfs/init.c          |   56 ++++++
 libxfs/trans.c         |   40 ++++
 libxfs/xfbtree.c       |  459 ++++++++++++++++++++++++++++++++++++++++++++++++
 libxfs/xfbtree.h       |   27 +++
 libxfs/xfile.c         |   16 ++
 libxfs/xfile.h         |    2 
 libxfs/xfs_btree_mem.h |   41 ++++
 12 files changed, 716 insertions(+), 11 deletions(-)


diff --git a/include/xfs_mount.h b/include/xfs_mount.h
index 98d5b199de8..80e40e7c60e 100644
--- a/include/xfs_mount.h
+++ b/include/xfs_mount.h
@@ -301,4 +301,14 @@ struct xfs_defer_drain { /* empty */ };
 static inline void xfs_perag_intent_hold(struct xfs_perag *pag) {}
 static inline void xfs_perag_intent_rele(struct xfs_perag *pag) {}
 
+static inline void libxfs_buftarg_drain(struct xfs_buftarg *btp)
+{
+	cache_purge(btp->bcache);
+}
+void libxfs_buftarg_free(struct xfs_buftarg *btp);
+
+int xfile_alloc_buftarg(struct xfs_mount *mp, const char *descr,
+		struct xfs_buftarg **btpp);
+void xfile_free_buftarg(struct xfs_buftarg *btp);
+
 #endif	/* __XFS_MOUNT_H__ */
diff --git a/include/xfs_trace.h b/include/xfs_trace.h
index e7cbd0d9d41..57661f36d7c 100644
--- a/include/xfs_trace.h
+++ b/include/xfs_trace.h
@@ -6,6 +6,13 @@
 #ifndef __TRACE_H__
 #define __TRACE_H__
 
+#define trace_xfbtree_create(...)		((void) 0)
+#define trace_xfbtree_create_root_buf(...)	((void) 0)
+#define trace_xfbtree_alloc_block(...)		((void) 0)
+#define trace_xfbtree_free_block(...)		((void) 0)
+#define trace_xfbtree_trans_cancel_buf(...)	((void) 0)
+#define trace_xfbtree_trans_commit_buf(...)	((void) 0)
+
 #define trace_xfs_agfl_reset(a,b,c,d)		((void) 0)
 #define trace_xfs_agfl_free_defer(a,b,c,d,e)	((void) 0)
 #define trace_xfs_alloc_cur_check(a,b,c,d,e,f)	((void) 0)
@@ -204,6 +211,7 @@
 #define trace_xfs_trans_cancel(a,b)		((void) 0)
 #define trace_xfs_trans_brelse(a)		((void) 0)
 #define trace_xfs_trans_binval(a)		((void) 0)
+#define trace_xfs_trans_bdetach(a)		((void) 0)
 #define trace_xfs_trans_bjoin(a)		((void) 0)
 #define trace_xfs_trans_bhold(a)		((void) 0)
 #define trace_xfs_trans_bhold_release(a)	((void) 0)
diff --git a/include/xfs_trans.h b/include/xfs_trans.h
index ac82c3bc480..b7f01ff073c 100644
--- a/include/xfs_trans.h
+++ b/include/xfs_trans.h
@@ -114,6 +114,7 @@ int	libxfs_trans_roll_inode (struct xfs_trans **, struct xfs_inode *);
 void	libxfs_trans_brelse(struct xfs_trans *, struct xfs_buf *);
 void	libxfs_trans_binval(struct xfs_trans *, struct xfs_buf *);
 void	libxfs_trans_bjoin(struct xfs_trans *, struct xfs_buf *);
+void	libxfs_trans_bdetach(struct xfs_trans *tp, struct xfs_buf *bp);
 void	libxfs_trans_bhold(struct xfs_trans *, struct xfs_buf *);
 void	libxfs_trans_bhold_release(struct xfs_trans *, struct xfs_buf *);
 void	libxfs_trans_dirty_buf(struct xfs_trans *, struct xfs_buf *);
diff --git a/libfrog/bitmap.c b/libfrog/bitmap.c
index 5af5ab8dd6b..e1f3a5e1c84 100644
--- a/libfrog/bitmap.c
+++ b/libfrog/bitmap.c
@@ -233,10 +233,9 @@ bitmap_set(
 	return res;
 }
 
-#if 0	/* Unused, provided for completeness. */
 /* Clear a region of bits. */
-int
-bitmap_clear(
+static int
+__bitmap_clear(
 	struct bitmap		*bmap,
 	uint64_t		start,
 	uint64_t		len)
@@ -251,8 +250,8 @@ bitmap_clear(
 	uint64_t		new_length;
 	struct avl64node	*node;
 	int			stat;
+	int			ret = 0;
 
-	pthread_mutex_lock(&bmap->bt_lock);
 	/* Find any existing nodes over that range. */
 	avl64_findranges(bmap->bt_tree, start, start + len, &firstn, &lastn);
 
@@ -312,10 +311,24 @@ bitmap_clear(
 	}
 
 out:
-	pthread_mutex_unlock(&bmap->bt_lock);
 	return ret;
 }
-#endif
+
+/* Clear a region of bits. */
+int
+bitmap_clear(
+	struct bitmap		*bmap,
+	uint64_t		start,
+	uint64_t		length)
+{
+	int			res;
+
+	pthread_mutex_lock(&bmap->bt_lock);
+	res = __bitmap_clear(bmap, start, length);
+	pthread_mutex_unlock(&bmap->bt_lock);
+
+	return res;
+}
 
 /* Iterate the set regions of this bitmap. */
 int
@@ -438,3 +451,42 @@ bitmap_dump(
 	printf("BITMAP DUMP DONE\n");
 }
 #endif
+
+/*
+ * Find the first set bit in this bitmap, clear it, and return the index of
+ * that bit in @valp.  Returns -ENODATA if no bits were set, or the usual
+ * negative errno.
+ */
+int
+bitmap_take_first_set(
+	struct bitmap		*bmap,
+	uint64_t		start,
+	uint64_t		last,
+	uint64_t		*valp)
+{
+	struct avl64node	*firstn;
+	struct avl64node	*lastn;
+	struct bitmap_node	*ext;
+	uint64_t		val;
+	int			error;
+
+	pthread_mutex_lock(&bmap->bt_lock);
+
+	avl64_findranges(bmap->bt_tree, start, last + 1, &firstn, &lastn);
+
+	if (firstn == NULL && lastn == NULL) {
+		error = -ENODATA;
+		goto out;
+	}
+
+	ext = container_of(firstn, struct bitmap_node, btn_node);
+	val = ext->btn_start;
+	error = __bitmap_clear(bmap, val, 1);
+	if (error)
+		goto out;
+
+	*valp = val;
+out:
+	pthread_mutex_unlock(&bmap->bt_lock);
+	return error;
+}
diff --git a/libfrog/bitmap.h b/libfrog/bitmap.h
index 043b77eece6..896ae01f8f4 100644
--- a/libfrog/bitmap.h
+++ b/libfrog/bitmap.h
@@ -14,6 +14,7 @@ struct bitmap {
 int bitmap_alloc(struct bitmap **bmap);
 void bitmap_free(struct bitmap **bmap);
 int bitmap_set(struct bitmap *bmap, uint64_t start, uint64_t length);
+int bitmap_clear(struct bitmap *bmap, uint64_t start, uint64_t length);
 int bitmap_iterate(struct bitmap *bmap, int (*fn)(uint64_t, uint64_t, void *),
 		void *arg);
 int bitmap_iterate_range(struct bitmap *bmap, uint64_t start, uint64_t length,
@@ -22,5 +23,7 @@ bool bitmap_test(struct bitmap *bmap, uint64_t start,
 		uint64_t len);
 bool bitmap_empty(struct bitmap *bmap);
 void bitmap_dump(struct bitmap *bmap);
+int bitmap_take_first_set(struct bitmap *bmap, uint64_t start, uint64_t last,
+		uint64_t *valp);
 
 #endif /* __LIBFROG_BITMAP_H__ */
diff --git a/libxfs/init.c b/libxfs/init.c
index 6d088125f5d..72650447f1b 100644
--- a/libxfs/init.c
+++ b/libxfs/init.c
@@ -478,6 +478,60 @@ libxfs_buftarg_alloc(
 	return btp;
 }
 
+/* Allocate a buffer cache target for a memory-backed file. */
+int
+xfile_alloc_buftarg(
+	struct xfs_mount	*mp,
+	const char		*descr,
+	struct xfs_buftarg	**btpp)
+{
+	struct xfs_buftarg	*btp;
+	struct xfile		*xfile;
+	int			error;
+
+	error = xfile_create(descr, &xfile);
+	if (error)
+		return error;
+
+	btp = malloc(sizeof(*btp));
+	if (!btp) {
+		error = -ENOMEM;
+		goto out_xfile;
+	}
+
+	btp->bt_mount = mp;
+	btp->bt_xfile = xfile;
+	btp->flags = XFS_BUFTARG_XFILE;
+	btp->writes_left = 0;
+	pthread_mutex_init(&btp->lock, NULL);
+
+	/*
+	 * Keep the bucket count small because the only anticipated caller is
+	 * per-AG in-memory btrees, for which we don't need to scale to handle
+	 * an entire filesystem.
+	 */
+	btp->bcache = cache_init(0, 63, &libxfs_bcache_operations);
+
+	*btpp = btp;
+	return 0;
+out_xfile:
+	xfile_destroy(xfile);
+	return error;
+}
+
+/* Free a buffer cache target for a memory-backed file. */
+void
+xfile_free_buftarg(
+	struct xfs_buftarg	*btp)
+{
+	struct xfile		*xfile = btp->bt_xfile;
+
+	ASSERT(btp->flags & XFS_BUFTARG_XFILE);
+
+	libxfs_buftarg_free(btp);
+	xfile_destroy(xfile);
+}
+
 enum libxfs_write_failure_nums {
 	WF_DATA = 0,
 	WF_LOG,
@@ -881,7 +935,7 @@ libxfs_flush_mount(
 	return error;
 }
 
-static void
+void
 libxfs_buftarg_free(
 	struct xfs_buftarg	*btp)
 {
diff --git a/libxfs/trans.c b/libxfs/trans.c
index 8143a6a99f6..7fec2caff49 100644
--- a/libxfs/trans.c
+++ b/libxfs/trans.c
@@ -614,6 +614,46 @@ libxfs_trans_brelse(
 	libxfs_buf_relse(bp);
 }
 
+/*
+ * Forcibly detach a buffer previously joined to the transaction.  The caller
+ * will retain its locked reference to the buffer after this function returns.
+ * The buffer must be completely clean and must not be held to the transaction.
+ */
+void
+libxfs_trans_bdetach(
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp)
+{
+	struct xfs_buf_log_item	*bip = bp->b_log_item;
+
+	ASSERT(tp != NULL);
+	ASSERT(bp->b_transp == tp);
+	ASSERT(bip->bli_item.li_type == XFS_LI_BUF);
+
+	trace_xfs_trans_bdetach(bip);
+
+	/*
+	 * Erase all recursion count, since we're removing this buffer from the
+	 * transaction.
+	 */
+	bip->bli_recur = 0;
+
+	/*
+	 * The buffer must be completely clean.  Specifically, it had better
+	 * not be dirty, stale, logged, ordered, or held to the transaction.
+	 */
+	ASSERT(!test_bit(XFS_LI_DIRTY, &bip->bli_item.li_flags));
+	ASSERT(!(bip->bli_flags & XFS_BLI_DIRTY));
+	ASSERT(!(bip->bli_flags & XFS_BLI_HOLD));
+	ASSERT(!(bip->bli_flags & XFS_BLI_ORDERED));
+	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
+
+	/* Unlink the log item from the transaction and drop the log item. */
+	xfs_trans_del_item(&bip->bli_item);
+	xfs_buf_item_put(bip);
+	bp->b_transp = NULL;
+}
+
 /*
  * Mark the buffer as not needing to be unlocked when the buf item's
  * iop_unlock() routine is called.  The buffer must already be locked
diff --git a/libxfs/xfbtree.c b/libxfs/xfbtree.c
index 79585dd3a23..3cca7b5494c 100644
--- a/libxfs/xfbtree.c
+++ b/libxfs/xfbtree.c
@@ -8,6 +8,7 @@
 #include "xfile.h"
 #include "xfbtree.h"
 #include "xfs_btree_mem.h"
+#include "libfrog/bitmap.h"
 
 /* btree ops functions for in-memory btrees. */
 
@@ -133,9 +134,18 @@ xfbtree_check_ptr(
 	else
 		bt_xfoff = be32_to_cpu(ptr->s);
 
-	if (!xfbtree_verify_xfileoff(cur, bt_xfoff))
+	if (!xfbtree_verify_xfileoff(cur, bt_xfoff)) {
 		fa = __this_address;
+		goto done;
+	}
 
+	/* Can't point to the head or anything before it */
+	if (bt_xfoff < XFBTREE_INIT_LEAF_BLOCK) {
+		fa = __this_address;
+		goto done;
+	}
+
+done:
 	if (fa) {
 		xfs_err(cur->bc_mp,
 "In-memory: Corrupt btree %d flags 0x%x pointer at level %d index %d fa %pS.",
@@ -341,3 +351,450 @@ xfbtree_sblock_verify(
 
 	return NULL;
 }
+
+/* Close the btree xfile and release all resources. */
+void
+xfbtree_destroy(
+	struct xfbtree		*xfbt)
+{
+	bitmap_free(&xfbt->freespace);
+	kmem_free(xfbt->freespace);
+	libxfs_buftarg_drain(xfbt->target);
+	kmem_free(xfbt);
+}
+
+/* Compute the number of bytes available for records. */
+static inline unsigned int
+xfbtree_rec_bytes(
+	struct xfs_mount		*mp,
+	const struct xfbtree_config	*cfg)
+{
+	unsigned int			blocklen = xfo_to_b(1);
+
+	if (cfg->flags & XFBTREE_CREATE_LONG_PTRS) {
+		if (xfs_has_crc(mp))
+			return blocklen - XFS_BTREE_LBLOCK_CRC_LEN;
+
+		return blocklen - XFS_BTREE_LBLOCK_LEN;
+	}
+
+	if (xfs_has_crc(mp))
+		return blocklen - XFS_BTREE_SBLOCK_CRC_LEN;
+
+	return blocklen - XFS_BTREE_SBLOCK_LEN;
+}
+
+/* Initialize an empty leaf block as the btree root. */
+STATIC int
+xfbtree_init_leaf_block(
+	struct xfs_mount		*mp,
+	struct xfbtree			*xfbt,
+	const struct xfbtree_config	*cfg)
+{
+	struct xfs_buf			*bp;
+	xfs_daddr_t			daddr;
+	int				error;
+	unsigned int			bc_flags = 0;
+
+	if (cfg->flags & XFBTREE_CREATE_LONG_PTRS)
+		bc_flags |= XFS_BTREE_LONG_PTRS;
+
+	daddr = xfo_to_daddr(XFBTREE_INIT_LEAF_BLOCK);
+	error = xfs_buf_get(xfbt->target, daddr, xfbtree_bbsize(), &bp);
+	if (error)
+		return error;
+
+	trace_xfbtree_create_root_buf(xfbt, bp);
+
+	bp->b_ops = cfg->btree_ops->buf_ops;
+	xfs_btree_init_block_int(mp, bp->b_addr, daddr, cfg->btnum, 0, 0,
+			cfg->owner, bc_flags);
+	error = xfs_bwrite(bp);
+	xfs_buf_relse(bp);
+	if (error)
+		return error;
+
+	xfbt->xf_used++;
+	return 0;
+}
+
+/* Initialize the in-memory btree header block. */
+STATIC int
+xfbtree_init_head(
+	struct xfbtree		*xfbt)
+{
+	struct xfs_buf		*bp;
+	xfs_daddr_t		daddr;
+	int			error;
+
+	daddr = xfo_to_daddr(XFBTREE_HEAD_BLOCK);
+	error = xfs_buf_get(xfbt->target, daddr, xfbtree_bbsize(), &bp);
+	if (error)
+		return error;
+
+	xfs_btree_mem_head_init(bp, xfbt->owner, XFBTREE_INIT_LEAF_BLOCK);
+	error = xfs_bwrite(bp);
+	xfs_buf_relse(bp);
+	if (error)
+		return error;
+
+	xfbt->xf_used++;
+	return 0;
+}
+
+/* Create an xfile btree backing thing that can be used for in-memory btrees. */
+int
+xfbtree_create(
+	struct xfs_mount		*mp,
+	const struct xfbtree_config	*cfg,
+	struct xfbtree			**xfbtreep)
+{
+	struct xfbtree			*xfbt;
+	unsigned int			blocklen = xfbtree_rec_bytes(mp, cfg);
+	unsigned int			keyptr_len = cfg->btree_ops->key_len;
+	int				error;
+
+	/* Requires an xfile-backed buftarg. */
+	if (!(cfg->target->flags & XFS_BUFTARG_XFILE)) {
+		ASSERT(cfg->target->flags & XFS_BUFTARG_XFILE);
+		return -EINVAL;
+	}
+
+	xfbt = kmem_zalloc(sizeof(struct xfbtree), KM_NOFS | KM_MAYFAIL);
+	if (!xfbt)
+		return -ENOMEM;
+
+	/* Assign our memory file and the free space bitmap. */
+	xfbt->target = cfg->target;
+	error = bitmap_alloc(&xfbt->freespace);
+	if (error)
+		goto err_buftarg;
+
+	/* Set up min/maxrecs for this btree. */
+	if (cfg->flags & XFBTREE_CREATE_LONG_PTRS)
+		keyptr_len += sizeof(__be64);
+	else
+		keyptr_len += sizeof(__be32);
+	xfbt->maxrecs[0] = blocklen / cfg->btree_ops->rec_len;
+	xfbt->maxrecs[1] = blocklen / keyptr_len;
+	xfbt->minrecs[0] = xfbt->maxrecs[0] / 2;
+	xfbt->minrecs[1] = xfbt->maxrecs[1] / 2;
+	xfbt->owner = cfg->owner;
+
+	/* Initialize the empty btree. */
+	error = xfbtree_init_leaf_block(mp, xfbt, cfg);
+	if (error)
+		goto err_freesp;
+
+	error = xfbtree_init_head(xfbt);
+	if (error)
+		goto err_freesp;
+
+	trace_xfbtree_create(mp, cfg, xfbt);
+
+	*xfbtreep = xfbt;
+	return 0;
+
+err_freesp:
+	bitmap_free(&xfbt->freespace);
+	kmem_free(xfbt->freespace);
+err_buftarg:
+	libxfs_buftarg_drain(xfbt->target);
+	kmem_free(xfbt);
+	return error;
+}
+
+/* Read the in-memory btree head. */
+int
+xfbtree_head_read_buf(
+	struct xfbtree		*xfbt,
+	struct xfs_trans	*tp,
+	struct xfs_buf		**bpp)
+{
+	struct xfs_buftarg	*btp = xfbt->target;
+	struct xfs_mount	*mp = btp->bt_mount;
+	struct xfs_btree_mem_head *mhead;
+	struct xfs_buf		*bp;
+	xfs_daddr_t		daddr;
+	int			error;
+
+	daddr = xfo_to_daddr(XFBTREE_HEAD_BLOCK);
+	error = xfs_trans_read_buf(mp, tp, btp, daddr, xfbtree_bbsize(), 0,
+			&bp, &xfs_btree_mem_head_buf_ops);
+	if (error)
+		return error;
+
+	mhead = bp->b_addr;
+	if (be64_to_cpu(mhead->mh_owner) != xfbt->owner) {
+		xfs_verifier_error(bp, -EFSCORRUPTED, __this_address);
+		xfs_trans_brelse(tp, bp);
+		return -EFSCORRUPTED;
+	}
+
+	*bpp = bp;
+	return 0;
+}
+
+static inline struct xfile *xfbtree_xfile(struct xfbtree *xfbt)
+{
+	return xfbt->target->bt_xfile;
+}
+
+/* Allocate a block to our in-memory btree. */
+int
+xfbtree_alloc_block(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_ptr	*start,
+	union xfs_btree_ptr		*new,
+	int				*stat)
+{
+	struct xfbtree			*xfbt = cur->bc_mem.xfbtree;
+	uint64_t			bt_xfoff;
+	loff_t				pos;
+	int				error;
+
+	ASSERT(cur->bc_flags & XFS_BTREE_IN_XFILE);
+
+	/*
+	 * Find the first free block in the free space bitmap and take it.  If
+	 * none are found, seek to end of the file.
+	 */
+	error = bitmap_take_first_set(xfbt->freespace, 0, -1ULL, &bt_xfoff);
+	if (error == -ENODATA) {
+		bt_xfoff = xfbt->xf_used;
+		xfbt->xf_used++;
+	} else if (error) {
+		return error;
+	}
+
+	trace_xfbtree_alloc_block(xfbt, cur, bt_xfoff);
+
+	/* Fail if the block address exceeds the maximum for short pointers. */
+	if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS) && bt_xfoff >= INT_MAX) {
+		*stat = 0;
+		return 0;
+	}
+
+	/* Make sure we actually can write to the block before we return it. */
+	pos = xfo_to_b(bt_xfoff);
+	error = xfile_prealloc(xfbtree_xfile(xfbt), pos, xfo_to_b(1));
+	if (error)
+		return error;
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+		new->l = cpu_to_be64(bt_xfoff);
+	else
+		new->s = cpu_to_be32(bt_xfoff);
+
+	*stat = 1;
+	return 0;
+}
+
+/* Free a block from our in-memory btree. */
+int
+xfbtree_free_block(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp)
+{
+	struct xfbtree		*xfbt = cur->bc_mem.xfbtree;
+	xfileoff_t		bt_xfoff, bt_xflen;
+
+	ASSERT(cur->bc_flags & XFS_BTREE_IN_XFILE);
+
+	bt_xfoff = xfs_daddr_to_xfot(xfs_buf_daddr(bp));
+	bt_xflen = xfs_daddr_to_xfot(bp->b_length);
+
+	trace_xfbtree_free_block(xfbt, cur, bt_xfoff);
+
+	return bitmap_set(xfbt->freespace, bt_xfoff, bt_xflen);
+}
+
+/* Return the minimum number of records for a btree block. */
+int
+xfbtree_get_minrecs(
+	struct xfs_btree_cur	*cur,
+	int			level)
+{
+	struct xfbtree		*xfbt = cur->bc_mem.xfbtree;
+
+	return xfbt->minrecs[level != 0];
+}
+
+/* Return the maximum number of records for a btree block. */
+int
+xfbtree_get_maxrecs(
+	struct xfs_btree_cur	*cur,
+	int			level)
+{
+	struct xfbtree		*xfbt = cur->bc_mem.xfbtree;
+
+	return xfbt->maxrecs[level != 0];
+}
+
+/* If this log item is a buffer item that came from the xfbtree, return it. */
+static inline struct xfs_buf *
+xfbtree_buf_match(
+	struct xfbtree			*xfbt,
+	const struct xfs_log_item	*lip)
+{
+	const struct xfs_buf_log_item	*bli;
+	struct xfs_buf			*bp;
+
+	if (lip->li_type != XFS_LI_BUF)
+		return NULL;
+
+	bli = container_of(lip, struct xfs_buf_log_item, bli_item);
+	bp = bli->bli_buf;
+	if (bp->b_target != xfbt->target)
+		return NULL;
+
+	return bp;
+}
+
+/*
+ * Detach this (probably dirty) xfbtree buffer from the transaction by any
+ * means necessary.  Returns true if the buffer needs to be written.
+ */
+STATIC bool
+xfbtree_trans_bdetach(
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp)
+{
+	struct xfs_buf_log_item	*bli = bp->b_log_item;
+	bool			dirty;
+
+	ASSERT(bli != NULL);
+
+	dirty = bli->bli_flags & (XFS_BLI_DIRTY | XFS_BLI_ORDERED);
+
+	bli->bli_flags &= ~(XFS_BLI_DIRTY | XFS_BLI_ORDERED |
+			    XFS_BLI_STALE);
+	clear_bit(XFS_LI_DIRTY, &bli->bli_item.li_flags);
+
+	while (bp->b_log_item != NULL)
+		libxfs_trans_bdetach(tp, bp);
+
+	return dirty;
+}
+
+/*
+ * Commit changes to the incore btree immediately by writing all dirty xfbtree
+ * buffers to the backing xfile.  This detaches all xfbtree buffers from the
+ * transaction, even on failure.  The buffer locks are dropped between the
+ * delwri queue and submit, so the caller must synchronize btree access.
+ *
+ * Normally we'd let the buffers commit with the transaction and get written to
+ * the xfile via the log, but online repair stages ephemeral btrees in memory
+ * and uses the btree_staging functions to write new btrees to disk atomically.
+ * The in-memory btree (and its backing store) are discarded at the end of the
+ * repair phase, which means that xfbtree buffers cannot commit with the rest
+ * of a transaction.
+ *
+ * In other words, online repair only needs the transaction to collect buffer
+ * pointers and to avoid buffer deadlocks, not to guarantee consistency of
+ * updates.
+ */
+int
+xfbtree_trans_commit(
+	struct xfbtree		*xfbt,
+	struct xfs_trans	*tp)
+{
+	LIST_HEAD(buffer_list);
+	struct xfs_log_item	*lip, *n;
+	bool			corrupt = false;
+	bool			tp_dirty = false;
+
+	/*
+	 * For each xfbtree buffer attached to the transaction, write the dirty
+	 * buffers to the xfile and release them.
+	 */
+	list_for_each_entry_safe(lip, n, &tp->t_items, li_trans) {
+		struct xfs_buf	*bp = xfbtree_buf_match(xfbt, lip);
+		bool		dirty;
+
+		if (!bp) {
+			if (test_bit(XFS_LI_DIRTY, &lip->li_flags))
+				tp_dirty |= true;
+			continue;
+		}
+
+		trace_xfbtree_trans_commit_buf(xfbt, bp);
+
+		dirty = xfbtree_trans_bdetach(tp, bp);
+		if (dirty && !corrupt) {
+			xfs_failaddr_t	fa = bp->b_ops->verify_struct(bp);
+
+			/*
+			 * Because this btree is ephemeral, validate the buffer
+			 * structure before delwri_submit so that we can return
+			 * corruption errors to the caller without shutting
+			 * down the filesystem.
+			 *
+			 * If the buffer fails verification, log the failure
+			 * but continue walking the transaction items so that
+			 * we remove all ephemeral btree buffers.
+			 */
+			if (fa) {
+				corrupt = true;
+				xfs_verifier_error(bp, -EFSCORRUPTED, fa);
+			} else {
+				xfs_buf_delwri_queue_here(bp, &buffer_list);
+			}
+		}
+
+		xfs_buf_relse(bp);
+	}
+
+	/*
+	 * Reset the transaction's dirty flag to reflect the dirty state of the
+	 * log items that are still attached.
+	 */
+	tp->t_flags = (tp->t_flags & ~XFS_TRANS_DIRTY) |
+			(tp_dirty ? XFS_TRANS_DIRTY : 0);
+
+	if (corrupt) {
+		xfs_buf_delwri_cancel(&buffer_list);
+		return -EFSCORRUPTED;
+	}
+
+	if (list_empty(&buffer_list))
+		return 0;
+
+	return xfs_buf_delwri_submit(&buffer_list);
+}
+
+/*
+ * Cancel changes to the incore btree by detaching all the xfbtree buffers.
+ * Changes are not written to the backing store.  This is needed for online
+ * repair btrees, which are by nature ephemeral.
+ */
+void
+xfbtree_trans_cancel(
+	struct xfbtree		*xfbt,
+	struct xfs_trans	*tp)
+{
+	struct xfs_log_item	*lip, *n;
+	bool			tp_dirty = false;
+
+	list_for_each_entry_safe(lip, n, &tp->t_items, li_trans) {
+		struct xfs_buf	*bp = xfbtree_buf_match(xfbt, lip);
+
+		if (!bp) {
+			if (test_bit(XFS_LI_DIRTY, &lip->li_flags))
+				tp_dirty |= true;
+			continue;
+		}
+
+		trace_xfbtree_trans_cancel_buf(xfbt, bp);
+
+		xfbtree_trans_bdetach(tp, bp);
+		xfs_buf_relse(bp);
+	}
+
+	/*
+	 * Reset the transaction's dirty flag to reflect the dirty state of the
+	 * log items that are still attached.
+	 */
+	tp->t_flags = (tp->t_flags & ~XFS_TRANS_DIRTY) |
+			(tp_dirty ? XFS_TRANS_DIRTY : 0);
+}
diff --git a/libxfs/xfbtree.h b/libxfs/xfbtree.h
index 292bade32d2..ac6d499afe5 100644
--- a/libxfs/xfbtree.h
+++ b/libxfs/xfbtree.h
@@ -19,18 +19,39 @@ struct xfs_btree_mem_head {
 
 #define XFS_BTREE_MEM_HEAD_MAGIC	0x4341544D	/* "CATM" */
 
-/* in-memory btree header is always block 0 in the backing store */
-#define XFS_BTREE_MEM_HEAD_DADDR	0
-
 /* xfile-backed in-memory btrees */
 
 struct xfbtree {
+	/* buffer cache target for the xfile backing this in-memory btree */
 	struct xfs_buftarg		*target;
 
+	/* Bitmap of free space from pos to used */
+	struct bitmap			*freespace;
+
+	/* Number of xfile blocks actually used by this xfbtree. */
+	xfileoff_t			xf_used;
+
 	/* Owner of this btree. */
 	unsigned long long		owner;
+
+	/* Minimum and maximum records per block. */
+	unsigned int			maxrecs[2];
+	unsigned int			minrecs[2];
 };
 
+/* The head of the in-memory btree is always at block 0 */
+#define XFBTREE_HEAD_BLOCK		0
+
+/* in-memory btrees are always created with an empty leaf block at block 1 */
+#define XFBTREE_INIT_LEAF_BLOCK		1
+
+int xfbtree_head_read_buf(struct xfbtree *xfbt, struct xfs_trans *tp,
+		struct xfs_buf **bpp);
+
+void xfbtree_destroy(struct xfbtree *xfbt);
+int xfbtree_trans_commit(struct xfbtree *xfbt, struct xfs_trans *tp);
+void xfbtree_trans_cancel(struct xfbtree *xfbt, struct xfs_trans *tp);
+
 #endif /* CONFIG_XFS_BTREE_IN_XFILE */
 
 #endif /* __LIBXFS_XFBTREE_H__ */
diff --git a/libxfs/xfile.c b/libxfs/xfile.c
index d6eefadae69..b7199091f05 100644
--- a/libxfs/xfile.c
+++ b/libxfs/xfile.c
@@ -281,3 +281,19 @@ xfile_dump(
 
 	return execvp("od", argv);
 }
+
+/* Ensure that there is storage backing the given range. */
+int
+xfile_prealloc(
+	struct xfile	*xf,
+	loff_t		pos,
+	uint64_t	count)
+{
+	int		error;
+
+	count = min(count, xfile_maxbytes(xf) - pos);
+	error = fallocate(xf->fd, 0, pos, count);
+	if (error)
+		return -errno;
+	return 0;
+}
diff --git a/libxfs/xfile.h b/libxfs/xfile.h
index e762e392caa..0d15351d697 100644
--- a/libxfs/xfile.h
+++ b/libxfs/xfile.h
@@ -46,6 +46,8 @@ xfile_obj_store(struct xfile *xf, const void *buf, size_t count, loff_t pos)
 	return 0;
 }
 
+int xfile_prealloc(struct xfile *xf, loff_t pos, uint64_t count);
+
 struct xfile_stat {
 	loff_t			size;
 	unsigned long long	bytes;
diff --git a/libxfs/xfs_btree_mem.h b/libxfs/xfs_btree_mem.h
index 2c42ca85c58..29f97c50304 100644
--- a/libxfs/xfs_btree_mem.h
+++ b/libxfs/xfs_btree_mem.h
@@ -8,6 +8,26 @@
 
 struct xfbtree;
 
+struct xfbtree_config {
+	/* Buffer ops for the btree root block */
+	const struct xfs_btree_ops	*btree_ops;
+
+	/* Buffer target for the xfile backing this btree. */
+	struct xfs_buftarg		*target;
+
+	/* Owner of this btree. */
+	unsigned long long		owner;
+
+	/* Btree type number */
+	xfs_btnum_t			btnum;
+
+	/* XFBTREE_CREATE_* flags */
+	unsigned int			flags;
+};
+
+/* btree has long pointers */
+#define XFBTREE_CREATE_LONG_PTRS	(1U << 0)
+
 #ifdef CONFIG_XFS_BTREE_IN_XFILE
 unsigned int xfs_btree_mem_head_nlevels(struct xfs_buf *head_bp);
 
@@ -35,6 +55,16 @@ xfs_failaddr_t xfbtree_lblock_verify(struct xfs_buf *bp, unsigned int max_recs);
 xfs_failaddr_t xfbtree_sblock_verify(struct xfs_buf *bp, unsigned int max_recs);
 unsigned long long xfbtree_buf_to_xfoff(struct xfs_btree_cur *cur,
 		struct xfs_buf *bp);
+
+int xfbtree_get_minrecs(struct xfs_btree_cur *cur, int level);
+int xfbtree_get_maxrecs(struct xfs_btree_cur *cur, int level);
+
+int xfbtree_create(struct xfs_mount *mp, const struct xfbtree_config *cfg,
+		struct xfbtree **xfbtreep);
+int xfbtree_alloc_block(struct xfs_btree_cur *cur,
+		const union xfs_btree_ptr *start, union xfs_btree_ptr *ptr,
+		int *stat);
+int xfbtree_free_block(struct xfs_btree_cur *cur, struct xfs_buf *bp);
 #else
 static inline unsigned int xfs_btree_mem_head_nlevels(struct xfs_buf *head_bp)
 {
@@ -77,11 +107,22 @@ static inline unsigned int xfbtree_bbsize(void)
 #define xfbtree_set_root			NULL
 #define xfbtree_init_ptr_from_cur		NULL
 #define xfbtree_dup_cursor			NULL
+#define xfbtree_get_minrecs			NULL
+#define xfbtree_get_maxrecs			NULL
+#define xfbtree_alloc_block			NULL
+#define xfbtree_free_block			NULL
 #define xfbtree_verify_xfileoff(cur, xfoff)	(false)
 #define xfbtree_check_block_owner(cur, block)	NULL
 #define xfbtree_owner(cur)			(0ULL)
 #define xfbtree_buf_to_xfoff(cur, bp)		(-1)
 
+static inline int
+xfbtree_create(struct xfs_mount *mp, const struct xfbtree_config *cfg,
+		struct xfbtree **xfbtreep)
+{
+	return -EOPNOTSUPP;
+}
+
 #endif /* CONFIG_XFS_BTREE_IN_XFILE */
 
 #endif /* __XFS_BTREE_MEM_H__ */

[PATCH 10/10] xfbtree: let the buffer cache flush dirty buffers to the xfile

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

As a performance optimization, when we're committing xfbtree updates,
let the buffer cache flush the dirty buffers to disk when it's ready
instead of writing everything at every transaction commit.  This is a
bit sketchy but it's an ephemeral tree so we can play fast and loose.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfbtree.c |   17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)


diff --git a/libxfs/xfbtree.c b/libxfs/xfbtree.c
index 3cca7b5494c..c4dd706f4f7 100644
--- a/libxfs/xfbtree.c
+++ b/libxfs/xfbtree.c
@@ -699,7 +699,6 @@ xfbtree_trans_commit(
 	struct xfbtree		*xfbt,
 	struct xfs_trans	*tp)
 {
-	LIST_HEAD(buffer_list);
 	struct xfs_log_item	*lip, *n;
 	bool			corrupt = false;
 	bool			tp_dirty = false;
@@ -733,12 +732,16 @@ xfbtree_trans_commit(
 			 * If the buffer fails verification, log the failure
 			 * but continue walking the transaction items so that
 			 * we remove all ephemeral btree buffers.
+			 *
+			 * Since the userspace buffer cache supports marking
+			 * buffers dirty and flushing them later, use this to
+			 * reduce the number of writes to the xfile.
 			 */
 			if (fa) {
 				corrupt = true;
 				xfs_verifier_error(bp, -EFSCORRUPTED, fa);
 			} else {
-				xfs_buf_delwri_queue_here(bp, &buffer_list);
+				libxfs_buf_mark_dirty(bp);
 			}
 		}
 
@@ -752,15 +755,9 @@ xfbtree_trans_commit(
 	tp->t_flags = (tp->t_flags & ~XFS_TRANS_DIRTY) |
 			(tp_dirty ? XFS_TRANS_DIRTY : 0);
 
-	if (corrupt) {
-		xfs_buf_delwri_cancel(&buffer_list);
+	if (corrupt)
 		return -EFSCORRUPTED;
-	}
-
-	if (list_empty(&buffer_list))
-		return 0;
-
-	return xfs_buf_delwri_submit(&buffer_list);
+	return 0;
 }
 
 /*

[PATCH 1/4] xfs: create a helper to decide if a file mapping targets the rt volume

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a helper so that we can stop open-coding this decision
everywhere.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_bmap.c       |    6 +++---
 libxfs/xfs_inode_fork.c |    9 +++++++++
 libxfs/xfs_inode_fork.h |    1 +
 3 files changed, 13 insertions(+), 3 deletions(-)


diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index 51bb4972f03..b764b7f79c4 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -4883,7 +4883,7 @@ xfs_bmap_del_extent_delay(
 
 	XFS_STATS_INC(mp, xs_del_exlist);
 
-	isrt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(ip);
+	isrt = xfs_ifork_is_realtime(ip, whichfork);
 	del_endoff = del->br_startoff + del->br_blockcount;
 	got_endoff = got->br_startoff + got->br_blockcount;
 	da_old = startblockval(got->br_startblock);
@@ -5119,7 +5119,7 @@ xfs_bmap_del_extent_real(
 		return -ENOSPC;
 
 	*logflagsp = XFS_ILOG_CORE;
-	if (whichfork == XFS_DATA_FORK && XFS_IS_REALTIME_INODE(ip)) {
+	if (xfs_ifork_is_realtime(ip, whichfork)) {
 		if (!(bflags & XFS_BMAPI_REMAP)) {
 			error = xfs_rtfree_blocks(tp, del->br_startblock,
 					del->br_blockcount);
@@ -5366,7 +5366,7 @@ __xfs_bunmapi(
 		return 0;
 	}
 	XFS_STATS_INC(mp, xs_blk_unmap);
-	isrt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(ip);
+	isrt = xfs_ifork_is_realtime(ip, whichfork);
 	end = start + len;
 
 	if (!xfs_iext_lookup_extent_before(ip, ifp, &end, &icur, &got)) {
diff --git a/libxfs/xfs_inode_fork.c b/libxfs/xfs_inode_fork.c
index d6478af46d6..5f45a1f1240 100644
--- a/libxfs/xfs_inode_fork.c
+++ b/libxfs/xfs_inode_fork.c
@@ -818,3 +818,12 @@ xfs_iext_count_upgrade(
 
 	return 0;
 }
+
+/* Decide if a file mapping is on the realtime device or not. */
+bool
+xfs_ifork_is_realtime(
+	struct xfs_inode	*ip,
+	int			whichfork)
+{
+	return XFS_IS_REALTIME_INODE(ip) && whichfork != XFS_ATTR_FORK;
+}
diff --git a/libxfs/xfs_inode_fork.h b/libxfs/xfs_inode_fork.h
index 535be5c0368..ebeb925be09 100644
--- a/libxfs/xfs_inode_fork.h
+++ b/libxfs/xfs_inode_fork.h
@@ -262,6 +262,7 @@ int xfs_iext_count_may_overflow(struct xfs_inode *ip, int whichfork,
 		int nr_to_add);
 int xfs_iext_count_upgrade(struct xfs_trans *tp, struct xfs_inode *ip,
 		uint nr_to_add);
+bool xfs_ifork_is_realtime(struct xfs_inode *ip, int whichfork);
 
 /* returns true if the fork has extents but they are not read in yet. */
 static inline bool xfs_need_iread_extents(const struct xfs_ifork *ifp)

[PATCH 2/4] xfs: repair the rmapbt

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Rebuild the reverse mapping btree from all primary metadata.  This first
patch establishes the bare mechanics of finding records and putting
together a new ondisk tree; more complex pieces are needed to make it
work properly.

Link: https://docs.kernel.org/filesystems/xfs-online-fsck-design.html#case-study-rebuilding-reverse-mapping-records
Link: https://docs.kernel.org/filesystems/xfs-online-fsck-design.html#case-study-reaping-after-repairing-reverse-mapping-btrees
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_bmap.c       |   43 +++++++++++++++++++++++++++++++++++++++++++
 libxfs/xfs_bmap.h       |    8 ++++++++
 libxfs/xfs_rmap.c       |   12 ++++++------
 libxfs/xfs_rmap.h       |    2 +-
 libxfs/xfs_rmap_btree.c |   13 ++++++++++++-
 5 files changed, 70 insertions(+), 8 deletions(-)


diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index b764b7f79c4..cfc4350d18e 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -6356,3 +6356,46 @@ xfs_bunmapi_range(
 out:
 	return error;
 }
+
+struct xfs_bmap_query_range {
+	xfs_bmap_query_range_fn	fn;
+	void			*priv;
+};
+
+/* Format btree record and pass to our callback. */
+STATIC int
+xfs_bmap_query_range_helper(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_rec	*rec,
+	void				*priv)
+{
+	struct xfs_bmap_query_range	*query = priv;
+	struct xfs_bmbt_irec		irec;
+	xfs_failaddr_t			fa;
+
+	xfs_bmbt_disk_get_all(&rec->bmbt, &irec);
+	fa = xfs_bmap_validate_extent(cur->bc_ino.ip, cur->bc_ino.whichfork,
+			&irec);
+	if (fa) {
+		xfs_btree_mark_sick(cur);
+		return xfs_bmap_complain_bad_rec(cur->bc_ino.ip,
+				cur->bc_ino.whichfork, fa, &irec);
+	}
+
+	return query->fn(cur, &irec, query->priv);
+}
+
+/* Find all bmaps. */
+int
+xfs_bmap_query_all(
+	struct xfs_btree_cur		*cur,
+	xfs_bmap_query_range_fn		fn,
+	void				*priv)
+{
+	struct xfs_bmap_query_range	query = {
+		.priv			= priv,
+		.fn			= fn,
+	};
+
+	return xfs_btree_query_all(cur, xfs_bmap_query_range_helper, &query);
+}
diff --git a/libxfs/xfs_bmap.h b/libxfs/xfs_bmap.h
index 4b83f6148e0..9dd631bc2dc 100644
--- a/libxfs/xfs_bmap.h
+++ b/libxfs/xfs_bmap.h
@@ -278,4 +278,12 @@ extern struct kmem_cache	*xfs_bmap_intent_cache;
 int __init xfs_bmap_intent_init_cache(void);
 void xfs_bmap_intent_destroy_cache(void);
 
+typedef int (*xfs_bmap_query_range_fn)(
+	struct xfs_btree_cur	*cur,
+	struct xfs_bmbt_irec	*rec,
+	void			*priv);
+
+int xfs_bmap_query_all(struct xfs_btree_cur *cur, xfs_bmap_query_range_fn fn,
+		void *priv);
+
 #endif	/* __XFS_BMAP_H__ */
diff --git a/libxfs/xfs_rmap.c b/libxfs/xfs_rmap.c
index 0b462d17838..cec1c4e6efe 100644
--- a/libxfs/xfs_rmap.c
+++ b/libxfs/xfs_rmap.c
@@ -214,10 +214,10 @@ xfs_rmap_btrec_to_irec(
 /* Simple checks for rmap records. */
 xfs_failaddr_t
 xfs_rmap_check_irec(
-	struct xfs_btree_cur		*cur,
+	struct xfs_perag		*pag,
 	const struct xfs_rmap_irec	*irec)
 {
-	struct xfs_mount		*mp = cur->bc_mp;
+	struct xfs_mount		*mp = pag->pag_mount;
 	bool				is_inode;
 	bool				is_unwritten;
 	bool				is_bmbt;
@@ -232,8 +232,8 @@ xfs_rmap_check_irec(
 			return __this_address;
 	} else {
 		/* check for valid extent range, including overflow */
-		if (!xfs_verify_agbext(cur->bc_ag.pag, irec->rm_startblock,
-						       irec->rm_blockcount))
+		if (!xfs_verify_agbext(pag, irec->rm_startblock,
+					    irec->rm_blockcount))
 			return __this_address;
 	}
 
@@ -306,7 +306,7 @@ xfs_rmap_get_rec(
 
 	fa = xfs_rmap_btrec_to_irec(rec, irec);
 	if (!fa)
-		fa = xfs_rmap_check_irec(cur, irec);
+		fa = xfs_rmap_check_irec(cur->bc_ag.pag, irec);
 	if (fa)
 		return xfs_rmap_complain_bad_rec(cur, fa, irec);
 
@@ -2441,7 +2441,7 @@ xfs_rmap_query_range_helper(
 
 	fa = xfs_rmap_btrec_to_irec(rec, &irec);
 	if (!fa)
-		fa = xfs_rmap_check_irec(cur, &irec);
+		fa = xfs_rmap_check_irec(cur->bc_ag.pag, &irec);
 	if (fa)
 		return xfs_rmap_complain_bad_rec(cur, fa, &irec);
 
diff --git a/libxfs/xfs_rmap.h b/libxfs/xfs_rmap.h
index 3c98d9d50af..58c67896d12 100644
--- a/libxfs/xfs_rmap.h
+++ b/libxfs/xfs_rmap.h
@@ -195,7 +195,7 @@ int xfs_rmap_compare(const struct xfs_rmap_irec *a,
 union xfs_btree_rec;
 xfs_failaddr_t xfs_rmap_btrec_to_irec(const union xfs_btree_rec *rec,
 		struct xfs_rmap_irec *irec);
-xfs_failaddr_t xfs_rmap_check_irec(struct xfs_btree_cur *cur,
+xfs_failaddr_t xfs_rmap_check_irec(struct xfs_perag *pag,
 		const struct xfs_rmap_irec *irec);
 
 int xfs_rmap_has_records(struct xfs_btree_cur *cur, xfs_agblock_t bno,
diff --git a/libxfs/xfs_rmap_btree.c b/libxfs/xfs_rmap_btree.c
index e894a22e087..6924f7e49d9 100644
--- a/libxfs/xfs_rmap_btree.c
+++ b/libxfs/xfs_rmap_btree.c
@@ -340,7 +340,18 @@ xfs_rmapbt_verify(
 
 	level = be16_to_cpu(block->bb_level);
 	if (pag && xfs_perag_initialised_agf(pag)) {
-		if (level >= pag->pagf_levels[XFS_BTNUM_RMAPi])
+		unsigned int	maxlevel = pag->pagf_levels[XFS_BTNUM_RMAPi];
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+		/*
+		 * Online repair could be rewriting the free space btrees, so
+		 * we'll validate against the larger of either tree while this
+		 * is going on.
+		 */
+		maxlevel = max_t(unsigned int, maxlevel,
+				pag->pagf_repair_levels[XFS_BTNUM_RMAPi]);
+#endif
+		if (level >= maxlevel)
 			return __this_address;
 	} else if (level >= mp->m_rmap_maxlevels)
 		return __this_address;

[PATCH 3/4] xfs: create a shadow rmap btree during rmap repair

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create an in-memory btree of rmap records instead of an array.  This
enables us to do live record collection instead of freezing the fs.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_rmap.c       |   37 +++++++++-----
 libxfs/xfs_rmap_btree.c |  123 +++++++++++++++++++++++++++++++++++++++++++++++
 libxfs/xfs_rmap_btree.h |    9 +++
 3 files changed, 156 insertions(+), 13 deletions(-)


diff --git a/libxfs/xfs_rmap.c b/libxfs/xfs_rmap.c
index cec1c4e6efe..b4a1f7e5189 100644
--- a/libxfs/xfs_rmap.c
+++ b/libxfs/xfs_rmap.c
@@ -268,6 +268,16 @@ xfs_rmap_check_irec(
 	return NULL;
 }
 
+static inline xfs_failaddr_t
+xfs_rmap_check_btrec(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*irec)
+{
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		return xfs_rmap_check_irec(cur->bc_mem.pag, irec);
+	return xfs_rmap_check_irec(cur->bc_ag.pag, irec);
+}
+
 static inline int
 xfs_rmap_complain_bad_rec(
 	struct xfs_btree_cur		*cur,
@@ -276,9 +286,13 @@ xfs_rmap_complain_bad_rec(
 {
 	struct xfs_mount		*mp = cur->bc_mp;
 
-	xfs_warn(mp,
-		"Reverse Mapping BTree record corruption in AG %d detected at %pS!",
-		cur->bc_ag.pag->pag_agno, fa);
+	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
+		xfs_warn(mp,
+ "In-Memory Reverse Mapping BTree record corruption detected at %pS!", fa);
+	else
+		xfs_warn(mp,
+ "Reverse Mapping BTree record corruption in AG %d detected at %pS!",
+			cur->bc_ag.pag->pag_agno, fa);
 	xfs_warn(mp,
 		"Owner 0x%llx, flags 0x%x, start block 0x%x block count 0x%x",
 		irec->rm_owner, irec->rm_flags, irec->rm_startblock,
@@ -306,7 +320,7 @@ xfs_rmap_get_rec(
 
 	fa = xfs_rmap_btrec_to_irec(rec, irec);
 	if (!fa)
-		fa = xfs_rmap_check_irec(cur->bc_ag.pag, irec);
+		fa = xfs_rmap_check_btrec(cur, irec);
 	if (fa)
 		return xfs_rmap_complain_bad_rec(cur, fa, irec);
 
@@ -2403,15 +2417,12 @@ xfs_rmap_map_raw(
 {
 	struct xfs_owner_info	oinfo;
 
-	oinfo.oi_owner = rmap->rm_owner;
-	oinfo.oi_offset = rmap->rm_offset;
-	oinfo.oi_flags = 0;
-	if (rmap->rm_flags & XFS_RMAP_ATTR_FORK)
-		oinfo.oi_flags |= XFS_OWNER_INFO_ATTR_FORK;
-	if (rmap->rm_flags & XFS_RMAP_BMBT_BLOCK)
-		oinfo.oi_flags |= XFS_OWNER_INFO_BMBT_BLOCK;
+	xfs_owner_info_pack(&oinfo, rmap->rm_owner, rmap->rm_offset,
+			rmap->rm_flags);
 
-	if (rmap->rm_flags || XFS_RMAP_NON_INODE_OWNER(rmap->rm_owner))
+	if ((rmap->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK |
+			       XFS_RMAP_UNWRITTEN)) ||
+	    XFS_RMAP_NON_INODE_OWNER(rmap->rm_owner))
 		return xfs_rmap_map(cur, rmap->rm_startblock,
 				rmap->rm_blockcount,
 				rmap->rm_flags & XFS_RMAP_UNWRITTEN,
@@ -2441,7 +2452,7 @@ xfs_rmap_query_range_helper(
 
 	fa = xfs_rmap_btrec_to_irec(rec, &irec);
 	if (!fa)
-		fa = xfs_rmap_check_irec(cur->bc_ag.pag, &irec);
+		fa = xfs_rmap_check_btrec(cur, &irec);
 	if (fa)
 		return xfs_rmap_complain_bad_rec(cur, fa, &irec);
 
diff --git a/libxfs/xfs_rmap_btree.c b/libxfs/xfs_rmap_btree.c
index 6924f7e49d9..f1bcb0b9bd2 100644
--- a/libxfs/xfs_rmap_btree.c
+++ b/libxfs/xfs_rmap_btree.c
@@ -19,6 +19,9 @@
 #include "xfs_trace.h"
 #include "xfs_ag.h"
 #include "xfs_ag_resv.h"
+#include "xfile.h"
+#include "xfbtree.h"
+#include "xfs_btree_mem.h"
 
 static struct kmem_cache	*xfs_rmapbt_cur_cache;
 
@@ -553,6 +556,126 @@ xfs_rmapbt_stage_cursor(
 	return cur;
 }
 
+#ifdef CONFIG_XFS_BTREE_IN_XFILE
+/*
+ * Validate an in-memory rmap btree block.  Callers are allowed to generate an
+ * in-memory btree even if the ondisk feature is not enabled.
+ */
+static xfs_failaddr_t
+xfs_rmapbt_mem_verify(
+	struct xfs_buf		*bp)
+{
+	struct xfs_mount	*mp = bp->b_mount;
+	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
+	xfs_failaddr_t		fa;
+	unsigned int		level;
+
+	if (!xfs_verify_magic(bp, block->bb_magic))
+		return __this_address;
+
+	fa = xfs_btree_sblock_v5hdr_verify(bp);
+	if (fa)
+		return fa;
+
+	level = be16_to_cpu(block->bb_level);
+	if (xfs_has_rmapbt(mp)) {
+		if (level >= mp->m_rmap_maxlevels)
+			return __this_address;
+	} else {
+		if (level >= xfs_rmapbt_maxlevels_ondisk())
+			return __this_address;
+	}
+
+	return xfbtree_sblock_verify(bp,
+			xfs_rmapbt_maxrecs(xfo_to_b(1), level == 0));
+}
+
+static void
+xfs_rmapbt_mem_rw_verify(
+	struct xfs_buf	*bp)
+{
+	xfs_failaddr_t	fa = xfs_rmapbt_mem_verify(bp);
+
+	if (fa)
+		xfs_verifier_error(bp, -EFSCORRUPTED, fa);
+}
+
+/* skip crc checks on in-memory btrees to save time */
+static const struct xfs_buf_ops xfs_rmapbt_mem_buf_ops = {
+	.name			= "xfs_rmapbt_mem",
+	.magic			= { 0, cpu_to_be32(XFS_RMAP_CRC_MAGIC) },
+	.verify_read		= xfs_rmapbt_mem_rw_verify,
+	.verify_write		= xfs_rmapbt_mem_rw_verify,
+	.verify_struct		= xfs_rmapbt_mem_verify,
+};
+
+static const struct xfs_btree_ops xfs_rmapbt_mem_ops = {
+	.rec_len		= sizeof(struct xfs_rmap_rec),
+	.key_len		= 2 * sizeof(struct xfs_rmap_key),
+
+	.dup_cursor		= xfbtree_dup_cursor,
+	.set_root		= xfbtree_set_root,
+	.alloc_block		= xfbtree_alloc_block,
+	.free_block		= xfbtree_free_block,
+	.get_minrecs		= xfbtree_get_minrecs,
+	.get_maxrecs		= xfbtree_get_maxrecs,
+	.init_key_from_rec	= xfs_rmapbt_init_key_from_rec,
+	.init_high_key_from_rec	= xfs_rmapbt_init_high_key_from_rec,
+	.init_rec_from_cur	= xfs_rmapbt_init_rec_from_cur,
+	.init_ptr_from_cur	= xfbtree_init_ptr_from_cur,
+	.key_diff		= xfs_rmapbt_key_diff,
+	.buf_ops		= &xfs_rmapbt_mem_buf_ops,
+	.diff_two_keys		= xfs_rmapbt_diff_two_keys,
+	.keys_inorder		= xfs_rmapbt_keys_inorder,
+	.recs_inorder		= xfs_rmapbt_recs_inorder,
+	.keys_contiguous	= xfs_rmapbt_keys_contiguous,
+};
+
+/* Create a cursor for an in-memory btree. */
+struct xfs_btree_cur *
+xfs_rmapbt_mem_cursor(
+	struct xfs_perag	*pag,
+	struct xfs_trans	*tp,
+	struct xfs_buf		*head_bp,
+	struct xfbtree		*xfbtree)
+{
+	struct xfs_btree_cur	*cur;
+	struct xfs_mount	*mp = pag->pag_mount;
+
+	/* Overlapping btree; 2 keys per pointer. */
+	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_RMAP,
+			mp->m_rmap_maxlevels, xfs_rmapbt_cur_cache);
+	cur->bc_flags = XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING |
+			XFS_BTREE_IN_XFILE;
+	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_rmap_2);
+	cur->bc_ops = &xfs_rmapbt_mem_ops;
+	cur->bc_mem.xfbtree = xfbtree;
+	cur->bc_mem.head_bp = head_bp;
+	cur->bc_nlevels = xfs_btree_mem_head_nlevels(head_bp);
+
+	cur->bc_mem.pag = xfs_perag_hold(pag);
+	return cur;
+}
+
+/* Create an in-memory rmap btree. */
+int
+xfs_rmapbt_mem_create(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno,
+	struct xfs_buftarg	*target,
+	struct xfbtree		**xfbtreep)
+{
+	struct xfbtree_config	cfg = {
+		.btree_ops	= &xfs_rmapbt_mem_ops,
+		.target		= target,
+		.btnum		= XFS_BTNUM_RMAP,
+		.owner		= agno,
+	};
+
+	return xfbtree_create(mp, &cfg, xfbtreep);
+}
+#endif /* CONFIG_XFS_BTREE_IN_XFILE */
+
 /*
  * Install a new reverse mapping btree root.  Caller is responsible for
  * invalidating and freeing the old btree blocks.
diff --git a/libxfs/xfs_rmap_btree.h b/libxfs/xfs_rmap_btree.h
index 3244715dd11..5d0454fd052 100644
--- a/libxfs/xfs_rmap_btree.h
+++ b/libxfs/xfs_rmap_btree.h
@@ -64,4 +64,13 @@ unsigned int xfs_rmapbt_maxlevels_ondisk(void);
 int __init xfs_rmapbt_init_cur_cache(void);
 void xfs_rmapbt_destroy_cur_cache(void);
 
+#ifdef CONFIG_XFS_BTREE_IN_XFILE
+struct xfbtree;
+struct xfs_btree_cur *xfs_rmapbt_mem_cursor(struct xfs_perag *pag,
+		struct xfs_trans *tp, struct xfs_buf *head_bp,
+		struct xfbtree *xfbtree);
+int xfs_rmapbt_mem_create(struct xfs_mount *mp, xfs_agnumber_t agno,
+		struct xfs_buftarg *target, struct xfbtree **xfbtreep);
+#endif /* CONFIG_XFS_BTREE_IN_XFILE */
+
 #endif /* __XFS_RMAP_BTREE_H__ */

[PATCH 4/4] xfs: hook live rmap operations during a repair operation

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Hook the regular rmap code when an rmapbt repair operation is running so
that we can unlock the AGF buffer to scan the filesystem and keep the
in-memory btree up to date during the scan.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 include/xfs_mount.h |    6 ++
 libxfs/xfs_ag.c     |    1 
 libxfs/xfs_ag.h     |    3 +
 libxfs/xfs_rmap.c   |  145 +++++++++++++++++++++++++++++++++++++++------------
 libxfs/xfs_rmap.h   |   28 ++++++++++
 5 files changed, 150 insertions(+), 33 deletions(-)


diff --git a/include/xfs_mount.h b/include/xfs_mount.h
index 80e40e7c60e..8a2ffa4e7cc 100644
--- a/include/xfs_mount.h
+++ b/include/xfs_mount.h
@@ -24,6 +24,12 @@ enum {
 	XFS_LOWSP_MAX,
 };
 
+/* Stubbed-out functionality from the kernel. */
+struct xfs_hook_chain {
+};
+#define xfs_hook_init(chain)		((void)0)
+#define xfs_hook_call(chain, val, priv)	(0)
+
 /*
  * Define a user-level mount structure with all we need
  * in order to make use of the numerous XFS_* macros.
diff --git a/libxfs/xfs_ag.c b/libxfs/xfs_ag.c
index 8e40026436a..1ba23ab533b 100644
--- a/libxfs/xfs_ag.c
+++ b/libxfs/xfs_ag.c
@@ -390,6 +390,7 @@ xfs_initialize_perag(
 		init_waitqueue_head(&pag->pag_active_wq);
 		pag->pagb_count = 0;
 		pag->pagb_tree = RB_ROOT;
+		xfs_hooks_init(&pag->pag_rmap_update_hooks);
 #endif /* __KERNEL__ */
 
 		error = xfs_buf_cache_init(&pag->pag_bcache);
diff --git a/libxfs/xfs_ag.h b/libxfs/xfs_ag.h
index fe5852873b8..06506e09a82 100644
--- a/libxfs/xfs_ag.h
+++ b/libxfs/xfs_ag.h
@@ -117,6 +117,9 @@ struct xfs_perag {
 	 * inconsistencies.
 	 */
 	struct xfs_defer_drain	pag_intents_drain;
+
+	/* Hook to feed rmapbt updates to an active online repair. */
+	struct xfs_hooks	pag_rmap_update_hooks;
 #endif /* __KERNEL__ */
 };
 
diff --git a/libxfs/xfs_rmap.c b/libxfs/xfs_rmap.c
index b4a1f7e5189..8df591840dc 100644
--- a/libxfs/xfs_rmap.c
+++ b/libxfs/xfs_rmap.c
@@ -820,6 +820,77 @@ xfs_rmap_unmap(
 	return error;
 }
 
+#ifdef CONFIG_XFS_LIVE_HOOKS
+/*
+ * Use a static key here to reduce the overhead of rmapbt live updates.  If
+ * the compiler supports jump labels, the static branch will be replaced by a
+ * nop sled when there are no hook users.  Online fsck is currently the only
+ * caller, so this is a reasonable tradeoff.
+ *
+ * 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_STATIC_XFS_HOOK_SWITCH(xfs_rmap_hooks_switch);
+
+void
+xfs_rmap_hook_disable(void)
+{
+	xfs_hooks_switch_off(&xfs_rmap_hooks_switch);
+}
+
+void
+xfs_rmap_hook_enable(void)
+{
+	xfs_hooks_switch_on(&xfs_rmap_hooks_switch);
+}
+
+/* Call downstream hooks for a reverse mapping update. */
+static inline void
+xfs_rmap_update_hook(
+	struct xfs_trans		*tp,
+	struct xfs_perag		*pag,
+	enum xfs_rmap_intent_type	op,
+	xfs_agblock_t			startblock,
+	xfs_extlen_t			blockcount,
+	bool				unwritten,
+	const struct xfs_owner_info	*oinfo)
+{
+	if (xfs_hooks_switched_on(&xfs_rmap_hooks_switch)) {
+		struct xfs_rmap_update_params	p = {
+			.startblock	= startblock,
+			.blockcount	= blockcount,
+			.unwritten	= unwritten,
+			.oinfo		= *oinfo, /* struct copy */
+		};
+
+		if (pag)
+			xfs_hooks_call(&pag->pag_rmap_update_hooks, op, &p);
+	}
+}
+
+/* Call the specified function during a reverse mapping update. */
+int
+xfs_rmap_hook_add(
+	struct xfs_perag	*pag,
+	struct xfs_rmap_hook	*hook)
+{
+	return xfs_hooks_add(&pag->pag_rmap_update_hooks, &hook->update_hook);
+}
+
+/* Stop calling the specified function during a reverse mapping update. */
+void
+xfs_rmap_hook_del(
+	struct xfs_perag	*pag,
+	struct xfs_rmap_hook	*hook)
+{
+	xfs_hooks_del(&pag->pag_rmap_update_hooks, &hook->update_hook);
+}
+#else
+# define xfs_rmap_update_hook(t, p, o, s, b, u, oi)	do { } while (0)
+#endif /* CONFIG_XFS_LIVE_HOOKS */
+
 /*
  * Remove a reference to an extent in the rmap btree.
  */
@@ -840,7 +911,7 @@ xfs_rmap_free(
 		return 0;
 
 	cur = xfs_rmapbt_init_cursor(mp, tp, agbp, pag);
-
+	xfs_rmap_update_hook(tp, pag, XFS_RMAP_UNMAP, bno, len, false, oinfo);
 	error = xfs_rmap_unmap(cur, bno, len, false, oinfo);
 
 	xfs_btree_del_cursor(cur, error);
@@ -1092,6 +1163,7 @@ xfs_rmap_alloc(
 		return 0;
 
 	cur = xfs_rmapbt_init_cursor(mp, tp, agbp, pag);
+	xfs_rmap_update_hook(tp, pag, XFS_RMAP_MAP, bno, len, false, oinfo);
 	error = xfs_rmap_map(cur, bno, len, false, oinfo);
 
 	xfs_btree_del_cursor(cur, error);
@@ -2507,6 +2579,38 @@ xfs_rmap_finish_one_cleanup(
 		xfs_trans_brelse(tp, agbp);
 }
 
+/* Commit an rmap operation into the ondisk tree. */
+int
+__xfs_rmap_finish_intent(
+	struct xfs_btree_cur		*rcur,
+	enum xfs_rmap_intent_type	op,
+	xfs_agblock_t			bno,
+	xfs_extlen_t			len,
+	const struct xfs_owner_info	*oinfo,
+	bool				unwritten)
+{
+	switch (op) {
+	case XFS_RMAP_ALLOC:
+	case XFS_RMAP_MAP:
+		return xfs_rmap_map(rcur, bno, len, unwritten, oinfo);
+	case XFS_RMAP_MAP_SHARED:
+		return xfs_rmap_map_shared(rcur, bno, len, unwritten, oinfo);
+	case XFS_RMAP_FREE:
+	case XFS_RMAP_UNMAP:
+		return xfs_rmap_unmap(rcur, bno, len, unwritten, oinfo);
+	case XFS_RMAP_UNMAP_SHARED:
+		return xfs_rmap_unmap_shared(rcur, bno, len, unwritten, oinfo);
+	case XFS_RMAP_CONVERT:
+		return xfs_rmap_convert(rcur, bno, len, !unwritten, oinfo);
+	case XFS_RMAP_CONVERT_SHARED:
+		return xfs_rmap_convert_shared(rcur, bno, len, !unwritten,
+				oinfo);
+	default:
+		ASSERT(0);
+		return -EFSCORRUPTED;
+	}
+}
+
 /*
  * Process one of the deferred rmap operations.  We pass back the
  * btree cursor to maintain our lock on the rmapbt between calls.
@@ -2573,39 +2677,14 @@ xfs_rmap_finish_one(
 	unwritten = ri->ri_bmap.br_state == XFS_EXT_UNWRITTEN;
 	bno = XFS_FSB_TO_AGBNO(rcur->bc_mp, ri->ri_bmap.br_startblock);
 
-	switch (ri->ri_type) {
-	case XFS_RMAP_ALLOC:
-	case XFS_RMAP_MAP:
-		error = xfs_rmap_map(rcur, bno, ri->ri_bmap.br_blockcount,
-				unwritten, &oinfo);
-		break;
-	case XFS_RMAP_MAP_SHARED:
-		error = xfs_rmap_map_shared(rcur, bno,
-				ri->ri_bmap.br_blockcount, unwritten, &oinfo);
-		break;
-	case XFS_RMAP_FREE:
-	case XFS_RMAP_UNMAP:
-		error = xfs_rmap_unmap(rcur, bno, ri->ri_bmap.br_blockcount,
-				unwritten, &oinfo);
-		break;
-	case XFS_RMAP_UNMAP_SHARED:
-		error = xfs_rmap_unmap_shared(rcur, bno,
-				ri->ri_bmap.br_blockcount, unwritten, &oinfo);
-		break;
-	case XFS_RMAP_CONVERT:
-		error = xfs_rmap_convert(rcur, bno, ri->ri_bmap.br_blockcount,
-				!unwritten, &oinfo);
-		break;
-	case XFS_RMAP_CONVERT_SHARED:
-		error = xfs_rmap_convert_shared(rcur, bno,
-				ri->ri_bmap.br_blockcount, !unwritten, &oinfo);
-		break;
-	default:
-		ASSERT(0);
-		error = -EFSCORRUPTED;
-	}
+	error = __xfs_rmap_finish_intent(rcur, ri->ri_type, bno,
+			ri->ri_bmap.br_blockcount, &oinfo, unwritten);
+	if (error)
+		return error;
 
-	return error;
+	xfs_rmap_update_hook(tp, ri->ri_pag, ri->ri_type, bno,
+			ri->ri_bmap.br_blockcount, unwritten, &oinfo);
+	return 0;
 }
 
 /*
diff --git a/libxfs/xfs_rmap.h b/libxfs/xfs_rmap.h
index 58c67896d12..3a153b4801b 100644
--- a/libxfs/xfs_rmap.h
+++ b/libxfs/xfs_rmap.h
@@ -186,6 +186,10 @@ void xfs_rmap_finish_one_cleanup(struct xfs_trans *tp,
 		struct xfs_btree_cur *rcur, int error);
 int xfs_rmap_finish_one(struct xfs_trans *tp, struct xfs_rmap_intent *ri,
 		struct xfs_btree_cur **pcur);
+int __xfs_rmap_finish_intent(struct xfs_btree_cur *rcur,
+		enum xfs_rmap_intent_type op, xfs_agblock_t bno,
+		xfs_extlen_t len, const struct xfs_owner_info *oinfo,
+		bool unwritten);
 
 int xfs_rmap_lookup_le_range(struct xfs_btree_cur *cur, xfs_agblock_t bno,
 		uint64_t owner, uint64_t offset, unsigned int flags,
@@ -235,4 +239,28 @@ extern struct kmem_cache	*xfs_rmap_intent_cache;
 int __init xfs_rmap_intent_init_cache(void);
 void xfs_rmap_intent_destroy_cache(void);
 
+/*
+ * Parameters for tracking reverse mapping changes.  The hook function arg
+ * parameter is enum xfs_rmap_intent_type, and the rest is below.
+ */
+struct xfs_rmap_update_params {
+	xfs_agblock_t			startblock;
+	xfs_extlen_t			blockcount;
+	struct xfs_owner_info		oinfo;
+	bool				unwritten;
+};
+
+#ifdef CONFIG_XFS_LIVE_HOOKS
+
+struct xfs_rmap_hook {
+	struct xfs_hook			update_hook;
+};
+
+void xfs_rmap_hook_disable(void);
+void xfs_rmap_hook_enable(void);
+
+int xfs_rmap_hook_add(struct xfs_perag *pag, struct xfs_rmap_hook *hook);
+void xfs_rmap_hook_del(struct xfs_perag *pag, struct xfs_rmap_hook *hook);
+#endif
+
 #endif	/* __XFS_RMAP_H__ */

[PATCH 1/6] libxfs: partition memfd files to avoid using too many fds

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Make it so that we can partition a memfd file to avoid running out of
file descriptors.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 include/xfs_mount.h |    2 -
 libxfs/init.c       |    3 +
 libxfs/xfile.c      |  200 +++++++++++++++++++++++++++++++++++++++++++++++++--
 libxfs/xfile.h      |    9 ++
 4 files changed, 201 insertions(+), 13 deletions(-)


diff --git a/include/xfs_mount.h b/include/xfs_mount.h
index 8a2ffa4e7cc..ec63c525fd4 100644
--- a/include/xfs_mount.h
+++ b/include/xfs_mount.h
@@ -314,7 +314,7 @@ static inline void libxfs_buftarg_drain(struct xfs_buftarg *btp)
 void libxfs_buftarg_free(struct xfs_buftarg *btp);
 
 int xfile_alloc_buftarg(struct xfs_mount *mp, const char *descr,
-		struct xfs_buftarg **btpp);
+		unsigned long long maxrange, struct xfs_buftarg **btpp);
 void xfile_free_buftarg(struct xfs_buftarg *btp);
 
 #endif	/* __XFS_MOUNT_H__ */
diff --git a/libxfs/init.c b/libxfs/init.c
index 72650447f1b..2e59ba0d0a2 100644
--- a/libxfs/init.c
+++ b/libxfs/init.c
@@ -483,13 +483,14 @@ int
 xfile_alloc_buftarg(
 	struct xfs_mount	*mp,
 	const char		*descr,
+	unsigned long long	maxrange,
 	struct xfs_buftarg	**btpp)
 {
 	struct xfs_buftarg	*btp;
 	struct xfile		*xfile;
 	int			error;
 
-	error = xfile_create(descr, &xfile);
+	error = xfile_create(descr, maxrange, &xfile);
 	if (error)
 		return error;
 
diff --git a/libxfs/xfile.c b/libxfs/xfile.c
index b7199091f05..7f785feb125 100644
--- a/libxfs/xfile.c
+++ b/libxfs/xfile.c
@@ -127,6 +127,146 @@ xfile_create_fd(
 	return fd;
 }
 
+struct xfile_fcb {
+	struct list_head	fcb_list;
+	int			fd;
+	unsigned int		refcount;
+};
+
+static LIST_HEAD(fcb_list);
+static pthread_mutex_t fcb_mutex = PTHREAD_MUTEX_INITIALIZER;
+
+/* Create a new memfd. */
+static inline int
+xfile_fcb_create(
+	const char		*description,
+	struct xfile_fcb	**fcbp)
+{
+	struct xfile_fcb	*fcb;
+	int			fd;
+
+	fd = xfile_create_fd(description);
+	if (fd < 0)
+		return -errno;
+
+	fcb = malloc(sizeof(struct xfile_fcb));
+	if (!fcb) {
+		close(fd);
+		return -ENOMEM;
+	}
+
+	list_head_init(&fcb->fcb_list);
+	fcb->fd = fd;
+	fcb->refcount = 1;
+
+	*fcbp = fcb;
+	return 0;
+}
+
+/* Release an xfile control block */
+static void
+xfile_fcb_irele(
+	struct xfile_fcb	*fcb,
+	loff_t			pos,
+	uint64_t		len)
+{
+	/*
+	 * If this memfd is linked only to itself, it's private, so we can
+	 * close it without taking any locks.
+	 */
+	if (list_empty(&fcb->fcb_list)) {
+		close(fcb->fd);
+		free(fcb);
+		return;
+	}
+
+	pthread_mutex_lock(&fcb_mutex);
+	if (--fcb->refcount == 0) {
+		/* If we're the last user of this memfd file, kill it fast. */
+		list_del(&fcb->fcb_list);
+		close(fcb->fd);
+		free(fcb);
+	} else if (len > 0) {
+		struct stat	statbuf;
+		int		ret;
+
+		/*
+		 * If we were using the end of a partitioned file, free the
+		 * address space.  IOWs, bonus points if you delete these in
+		 * reverse-order of creation.
+		 */
+		ret = fstat(fcb->fd, &statbuf);
+		if (!ret && statbuf.st_size == pos + len) {
+			ret = ftruncate(fcb->fd, pos);
+		}
+	}
+	pthread_mutex_unlock(&fcb_mutex);
+}
+
+/*
+ * Find an memfd that can accomodate the given amount of address space.
+ */
+static int
+xfile_fcb_find(
+	const char		*description,
+	uint64_t		maxrange,
+	loff_t			*pos,
+	struct xfile_fcb	**fcbp)
+{
+	struct xfile_fcb	*fcb;
+	int			ret;
+	int			error;
+
+	/* No maximum range means that the caller gets a private memfd. */
+	if (maxrange == 0) {
+		*pos = 0;
+		return xfile_fcb_create(description, fcbp);
+	}
+
+	pthread_mutex_lock(&fcb_mutex);
+
+	/*
+	 * If we only need a certain number of byte range, look for one with
+	 * available file range.
+	 */
+	list_for_each_entry(fcb, &fcb_list, fcb_list) {
+		struct stat	statbuf;
+
+		ret = fstat(fcb->fd, &statbuf);
+		if (ret)
+			continue;
+
+		ret = ftruncate(fcb->fd, statbuf.st_size + maxrange);
+		if (ret)
+			continue;
+
+		fcb->refcount++;
+		*pos = statbuf.st_size;
+		*fcbp = fcb;
+		goto out_unlock;
+	}
+
+	/* Otherwise, open a new memfd and add it to our list. */
+	error = xfile_fcb_create(description, &fcb);
+	if (error)
+		return error;
+
+	ret = ftruncate(fcb->fd, maxrange);
+	if (ret) {
+		error = -errno;
+		xfile_fcb_irele(fcb, 0, maxrange);
+		return error;
+	}
+
+	list_add_tail(&fcb->fcb_list, &fcb_list);
+	*pos = 0;
+	*fcbp = fcb;
+
+out_unlock:
+	pthread_mutex_unlock(&fcb_mutex);
+	return error;
+}
+
 /*
  * Create an xfile of the given size.  The description will be used in the
  * trace output.
@@ -134,6 +274,7 @@ xfile_create_fd(
 int
 xfile_create(
 	const char		*description,
+	unsigned long long	maxrange,
 	struct xfile		**xfilep)
 {
 	struct xfile		*xf;
@@ -143,13 +284,14 @@ xfile_create(
 	if (!xf)
 		return -ENOMEM;
 
-	xf->fd = xfile_create_fd(description);
-	if (xf->fd < 0) {
-		error = -errno;
+	error = xfile_fcb_find(description, maxrange, &xf->partition_pos,
+			&xf->fcb);
+	if (error) {
 		kmem_free(xf);
 		return error;
 	}
 
+	xf->partition_bytes = maxrange;
 	*xfilep = xf;
 	return 0;
 }
@@ -159,7 +301,7 @@ void
 xfile_destroy(
 	struct xfile		*xf)
 {
-	close(xf->fd);
+	xfile_fcb_irele(xf->fcb, xf->partition_pos, xf->partition_bytes);
 	kmem_free(xf);
 }
 
@@ -167,6 +309,9 @@ static inline loff_t
 xfile_maxbytes(
 	struct xfile		*xf)
 {
+	if (xf->partition_bytes > 0)
+		return xf->partition_bytes;
+
 	if (sizeof(loff_t) == 8)
 		return LLONG_MAX;
 	return LONG_MAX;
@@ -192,7 +337,7 @@ xfile_pread(
 	if (xfile_maxbytes(xf) - pos < count)
 		return -EFBIG;
 
-	ret = pread(xf->fd, buf, count, pos);
+	ret = pread(xf->fcb->fd, buf, count, pos + xf->partition_pos);
 	if (ret >= 0)
 		return ret;
 	return -errno;
@@ -218,7 +363,7 @@ xfile_pwrite(
 	if (xfile_maxbytes(xf) - pos < count)
 		return -EFBIG;
 
-	ret = pwrite(xf->fd, buf, count, pos);
+	ret = pwrite(xf->fcb->fd, buf, count, pos + xf->partition_pos);
 	if (ret >= 0)
 		return ret;
 	return -errno;
@@ -232,6 +377,37 @@ xfile_bytes(
 	struct xfile_stat	xs;
 	int			ret;
 
+	if (xf->partition_bytes > 0) {
+		loff_t		data_pos = xf->partition_pos;
+		loff_t		stop_pos = data_pos + xf->partition_bytes;
+		loff_t		hole_pos;
+		unsigned long long bytes = 0;
+
+		data_pos = lseek(xf->fcb->fd, data_pos, SEEK_DATA);
+		while (data_pos >= 0 && data_pos < stop_pos) {
+			hole_pos = lseek(xf->fcb->fd, data_pos, SEEK_HOLE);
+			if (hole_pos < 0) {
+				/* save error, break */
+				data_pos = hole_pos;
+				break;
+			}
+			if (hole_pos >= stop_pos) {
+				bytes += stop_pos - data_pos;
+				return bytes;
+			}
+			bytes += hole_pos - data_pos;
+
+			data_pos = lseek(xf->fcb->fd, hole_pos, SEEK_DATA);
+		}
+		if (data_pos < 0) {
+			if (errno == ENXIO)
+				return bytes;
+			return xf->partition_bytes;
+		}
+
+		return bytes;
+	}
+
 	ret = xfile_stat(xf, &xs);
 	if (ret)
 		return 0;
@@ -248,7 +424,13 @@ xfile_stat(
 	struct stat		ks;
 	int			error;
 
-	error = fstat(xf->fd, &ks);
+	if (xf->partition_bytes > 0) {
+		statbuf->size = xf->partition_bytes;
+		statbuf->bytes = xf->partition_bytes;
+		return 0;
+	}
+
+	error = fstat(xf->fcb->fd, &ks);
 	if (error)
 		return -errno;
 
@@ -275,7 +457,7 @@ xfile_dump(
 	}
 
 	/* reroute our xfile to stdin and shut everything else */
-	dup2(xf->fd, 0);
+	dup2(xf->fcb->fd, 0);
 	for (i = 3; i < 1024; i++)
 		close(i);
 
@@ -292,7 +474,7 @@ xfile_prealloc(
 	int		error;
 
 	count = min(count, xfile_maxbytes(xf) - pos);
-	error = fallocate(xf->fd, 0, pos, count);
+	error = fallocate(xf->fcb->fd, 0, pos + xf->partition_pos, count);
 	if (error)
 		return -errno;
 	return 0;
diff --git a/libxfs/xfile.h b/libxfs/xfile.h
index 0d15351d697..ac368432382 100644
--- a/libxfs/xfile.h
+++ b/libxfs/xfile.h
@@ -6,13 +6,18 @@
 #ifndef __LIBXFS_XFILE_H__
 #define __LIBXFS_XFILE_H__
 
+struct xfile_fcb;
+
 struct xfile {
-	int		fd;
+	struct xfile_fcb	*fcb;
+	loff_t			partition_pos;
+	uint64_t		partition_bytes;
 };
 
 void xfile_libinit(void);
 
-int xfile_create(const char *description, struct xfile **xfilep);
+int xfile_create(const char *description, unsigned long long maxrange,
+		struct xfile **xfilep);
 void xfile_destroy(struct xfile *xf);
 
 ssize_t xfile_pread(struct xfile *xf, void *buf, size_t count, loff_t pos);

[PATCH 2/6] xfs_repair: convert regular rmap repair to use in-memory btrees

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Convert the rmap btree repair code to use in-memory rmap btrees to store
the observed reverse mapping records.  This will eliminate the need for
a separate record sorting step, as well as eliminate the need for all
the code that turns multiple consecutive bmap records into a single rmap
record.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libfrog/linux.c          |   33 ++++++
 libfrog/platform.h       |    3 +
 libxfs/libxfs_api_defs.h |    9 ++
 libxfs/xfbtree.c         |    8 +
 libxfs/xfbtree.h         |    1 
 repair/agbtree.c         |   18 ++-
 repair/agbtree.h         |    1 
 repair/phase5.c          |    2 
 repair/rmap.c            |  257 +++++++++++++++++++++++++++++++++++++++++++---
 repair/rmap.h            |   16 +++
 repair/xfs_repair.c      |    6 +
 11 files changed, 329 insertions(+), 25 deletions(-)


diff --git a/libfrog/linux.c b/libfrog/linux.c
index 46a5ff39e2e..be174a52396 100644
--- a/libfrog/linux.c
+++ b/libfrog/linux.c
@@ -274,3 +274,36 @@ platform_physmem(void)
 	}
 	return (si.totalram >> 10) * si.mem_unit;	/* kilobytes */
 }
+
+char *kvasprintf(const char *fmt, va_list ap)
+{
+	unsigned int first, second;
+	char *p;
+	va_list aq;
+
+	va_copy(aq, ap);
+	first = vsnprintf(NULL, 0, fmt, aq);
+	va_end(aq);
+
+	p = malloc(first + 1);
+	if (!p)
+		return NULL;
+
+	second = vsnprintf(p, first + 1, fmt, ap);
+	if (first != second) /* shut up gcc */
+		assert(first == second);
+
+	return p;
+}
+
+char *kasprintf(const char *fmt, ...)
+{
+	va_list ap;
+	char *p;
+
+	va_start(ap, fmt);
+	p = kvasprintf(fmt, ap);
+	va_end(ap);
+
+	return p;
+}
diff --git a/libfrog/platform.h b/libfrog/platform.h
index 20f9bdf5ce5..003e22bf2d8 100644
--- a/libfrog/platform.h
+++ b/libfrog/platform.h
@@ -21,4 +21,7 @@ int platform_nproc(void);
 
 void platform_findsizes(char *path, int fd, long long *sz, int *bsz);
 
+char *kvasprintf(const char *fmt, va_list ap);
+char *kasprintf(const char *fmt, ...);
+
 #endif /* __LIBFROG_PLATFORM_H__ */
diff --git a/libxfs/libxfs_api_defs.h b/libxfs/libxfs_api_defs.h
index 8495590966f..bafb05a2f23 100644
--- a/libxfs/libxfs_api_defs.h
+++ b/libxfs/libxfs_api_defs.h
@@ -60,8 +60,13 @@
 #define xfs_btree_bload			libxfs_btree_bload
 #define xfs_btree_bload_compute_geometry libxfs_btree_bload_compute_geometry
 #define xfs_btree_del_cursor		libxfs_btree_del_cursor
+#define xfs_btree_get_block		libxfs_btree_get_block
+#define xfs_btree_goto_left_edge	libxfs_btree_goto_left_edge
+#define xfs_btree_increment		libxfs_btree_increment
 #define xfs_btree_init_block		libxfs_btree_init_block
+#define xfs_btree_mem_head_read_buf	libxfs_btree_mem_head_read_buf
 #define xfs_btree_rec_addr		libxfs_btree_rec_addr
+#define xfs_btree_visit_blocks		libxfs_btree_visit_blocks
 #define xfs_buf_delwri_submit		libxfs_buf_delwri_submit
 #define xfs_buf_get			libxfs_buf_get
 #define xfs_buf_get_uncached		libxfs_buf_get_uncached
@@ -181,6 +186,8 @@
 #define xfs_rmapbt_init_cursor		libxfs_rmapbt_init_cursor
 #define xfs_rmapbt_maxlevels_ondisk	libxfs_rmapbt_maxlevels_ondisk
 #define xfs_rmapbt_maxrecs		libxfs_rmapbt_maxrecs
+#define xfs_rmapbt_mem_create		libxfs_rmapbt_mem_create
+#define xfs_rmapbt_mem_cursor		libxfs_rmapbt_mem_cursor
 #define xfs_rmapbt_stage_cursor		libxfs_rmapbt_stage_cursor
 #define xfs_rmap_compare		libxfs_rmap_compare
 #define xfs_rmap_get_rec		libxfs_rmap_get_rec
@@ -189,6 +196,7 @@
 #define xfs_rmap_irec_offset_unpack	libxfs_rmap_irec_offset_unpack
 #define xfs_rmap_lookup_le		libxfs_rmap_lookup_le
 #define xfs_rmap_lookup_le_range	libxfs_rmap_lookup_le_range
+#define xfs_rmap_map_raw		libxfs_rmap_map_raw
 #define xfs_rmap_query_all		libxfs_rmap_query_all
 #define xfs_rmap_query_range		libxfs_rmap_query_range
 
@@ -244,6 +252,7 @@
 
 #define xfs_validate_stripe_geometry	libxfs_validate_stripe_geometry
 #define xfs_verify_agbno		libxfs_verify_agbno
+#define xfs_verify_agbext		libxfs_verify_agbext
 #define xfs_verify_agino		libxfs_verify_agino
 #define xfs_verify_cksum		libxfs_verify_cksum
 #define xfs_verify_dir_ino		libxfs_verify_dir_ino
diff --git a/libxfs/xfbtree.c b/libxfs/xfbtree.c
index c4dd706f4f7..7521566fd15 100644
--- a/libxfs/xfbtree.c
+++ b/libxfs/xfbtree.c
@@ -795,3 +795,11 @@ xfbtree_trans_cancel(
 	tp->t_flags = (tp->t_flags & ~XFS_TRANS_DIRTY) |
 			(tp_dirty ? XFS_TRANS_DIRTY : 0);
 }
+
+/* How many bytes does this xfbtree consume? */
+unsigned long long
+xfbtree_bytes(
+	struct xfbtree	*xfbt)
+{
+	return xfile_bytes(xfbt->target->bt_xfile);
+}
diff --git a/libxfs/xfbtree.h b/libxfs/xfbtree.h
index ac6d499afe5..b7a9c321b3e 100644
--- a/libxfs/xfbtree.h
+++ b/libxfs/xfbtree.h
@@ -51,6 +51,7 @@ int xfbtree_head_read_buf(struct xfbtree *xfbt, struct xfs_trans *tp,
 void xfbtree_destroy(struct xfbtree *xfbt);
 int xfbtree_trans_commit(struct xfbtree *xfbt, struct xfs_trans *tp);
 void xfbtree_trans_cancel(struct xfbtree *xfbt, struct xfs_trans *tp);
+unsigned long long xfbtree_bytes(struct xfbtree *xfbt);
 
 #endif /* CONFIG_XFS_BTREE_IN_XFILE */
 
diff --git a/repair/agbtree.c b/repair/agbtree.c
index 38f3f7b8fea..dccb15f9667 100644
--- a/repair/agbtree.c
+++ b/repair/agbtree.c
@@ -104,7 +104,8 @@ reserve_agblocks(
 			do_error(_("could not set up btree reservation: %s\n"),
 				strerror(-error));
 
-		error = rmap_add_ag_rec(mp, agno, ext_ptr->ex_startblock, len,
+		error = rmap_add_agbtree_mapping(mp, agno,
+				ext_ptr->ex_startblock, len,
 				btr->newbt.oinfo.oi_owner);
 		if (error)
 			do_error(_("could not set up btree rmaps: %s\n"),
@@ -601,14 +602,19 @@ get_rmapbt_records(
 	unsigned int			nr_wanted,
 	void				*priv)
 {
-	struct xfs_rmap_irec		*rec;
 	struct bt_rebuild		*btr = priv;
 	union xfs_btree_rec		*block_rec;
 	unsigned int			loaded;
+	int				ret;
 
 	for (loaded = 0; loaded < nr_wanted; loaded++, idx++) {
-		rec = pop_slab_cursor(btr->slab_cursor);
-		memcpy(&cur->bc_rec.r, rec, sizeof(struct xfs_rmap_irec));
+		ret = rmap_get_mem_rec(&btr->rmapbt_cursor, &cur->bc_rec.r);
+		if (ret < 0)
+			return ret;
+		if (ret == 0)
+			do_error(
+ _("ran out of records while rebuilding AG %u rmap btree\n"),
+					cur->bc_ag.pag->pag_agno);
 
 		block_rec = libxfs_btree_rec_addr(cur, idx, block);
 		cur->bc_ops->init_rec_from_cur(cur, block_rec);
@@ -656,7 +662,7 @@ build_rmap_tree(
 {
 	int			error;
 
-	error = rmap_init_cursor(agno, &btr->slab_cursor);
+	error = rmap_init_mem_cursor(sc->mp, NULL, agno, &btr->rmapbt_cursor);
 	if (error)
 		do_error(
 _("Insufficient memory to construct rmap cursor.\n"));
@@ -669,7 +675,7 @@ _("Error %d while creating rmap btree for AG %u.\n"), error, agno);
 
 	/* Since we're not writing the AGF yet, no need to commit the cursor */
 	libxfs_btree_del_cursor(btr->cur, 0);
-	free_slab_cursor(&btr->slab_cursor);
+	rmap_free_mem_cursor(NULL, &btr->rmapbt_cursor, 0);
 }
 
 /* rebuild the refcount tree */
diff --git a/repair/agbtree.h b/repair/agbtree.h
index 714d8e68716..7b12b9da74e 100644
--- a/repair/agbtree.h
+++ b/repair/agbtree.h
@@ -20,6 +20,7 @@ struct bt_rebuild {
 	/* Tree-specific data. */
 	union {
 		struct xfs_slab_cursor	*slab_cursor;
+		struct rmap_mem_cur	rmapbt_cursor;
 		struct {
 			struct extent_tree_node	*bno_rec;
 			unsigned int		freeblks;
diff --git a/repair/phase5.c b/repair/phase5.c
index b0e208f95af..d7bacb18b84 100644
--- a/repair/phase5.c
+++ b/repair/phase5.c
@@ -714,7 +714,7 @@ phase5(xfs_mount_t *mp)
 	 * the superblock counters.
 	 */
 	for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
-		error = rmap_store_ag_btree_rec(mp, agno);
+		error = rmap_commit_agbtree_mappings(mp, agno);
 		if (error)
 			do_error(
 _("unable to add AG %u reverse-mapping data to btree.\n"), agno);
diff --git a/repair/rmap.c b/repair/rmap.c
index 564e1cbf294..53b8ac6fcf9 100644
--- a/repair/rmap.c
+++ b/repair/rmap.c
@@ -13,6 +13,9 @@
 #include "slab.h"
 #include "rmap.h"
 #include "libfrog/bitmap.h"
+#include "libfrog/platform.h"
+#include "libxfs/xfile.h"
+#include "libxfs/xfbtree.h"
 
 #undef RMAP_DEBUG
 
@@ -24,6 +27,7 @@
 
 /* per-AG rmap object anchor */
 struct xfs_ag_rmap {
+	struct xfbtree	*ar_xfbtree;		/* rmap observations */
 	struct xfs_slab	*ar_rmaps;		/* rmap observations, p4 */
 	struct xfs_slab	*ar_raw_rmaps;		/* unmerged rmaps */
 	int		ar_flcount;		/* agfl entries from leftover */
@@ -53,6 +57,61 @@ rmap_needs_work(
 	       xfs_has_rmapbt(mp);
 }
 
+/* Destroy an in-memory rmap btree. */
+STATIC void
+rmaps_destroy(
+	struct xfs_mount	*mp,
+	struct xfs_ag_rmap	*ag_rmap)
+{
+	struct xfs_buftarg	*target;
+
+	free_slab(&ag_rmap->ar_refcount_items);
+
+	if (!ag_rmap->ar_xfbtree)
+		return;
+
+	target = ag_rmap->ar_xfbtree->target;
+
+	xfbtree_destroy(ag_rmap->ar_xfbtree);
+	xfile_free_buftarg(target);
+}
+
+/* Initialize the in-memory rmap btree for collecting per-AG rmap records. */
+STATIC void
+rmaps_init_ag(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno,
+	struct xfs_ag_rmap	*ag_rmap)
+{
+	struct xfs_buftarg	*target;
+	char			*descr;
+	unsigned long long	maxbytes;
+	int			error;
+
+	maxbytes = XFS_FSB_TO_B(mp, mp->m_sb.sb_agblocks);
+	descr = kasprintf("xfs_repair (%s): AG %u rmap records",
+			mp->m_fsname, agno);
+	error = -xfile_alloc_buftarg(mp, descr, maxbytes, &target);
+	kfree(descr);
+	if (error)
+		goto nomem;
+
+	error = -libxfs_rmapbt_mem_create(mp, agno, target,
+			&ag_rmap->ar_xfbtree);
+	if (error)
+		goto nomem;
+
+	error = init_slab(&ag_rmap->ar_refcount_items,
+			  sizeof(struct xfs_refcount_irec));
+	if (error)
+		goto nomem;
+
+	return;
+nomem:
+	do_error(
+_("Insufficient memory while allocating realtime reverse mapping btree."));
+}
+
 /*
  * Initialize per-AG reverse map data.
  */
@@ -71,6 +130,8 @@ rmaps_init(
 		do_error(_("couldn't allocate per-AG reverse map roots\n"));
 
 	for (i = 0; i < mp->m_sb.sb_agcount; i++) {
+		rmaps_init_ag(mp, i, &ag_rmaps[i]);
+
 		error = init_slab(&ag_rmaps[i].ar_rmaps,
 				sizeof(struct xfs_rmap_irec));
 		if (error)
@@ -82,11 +143,6 @@ _("Insufficient memory while allocating reverse mapping slabs."));
 			do_error(
 _("Insufficient memory while allocating raw metadata reverse mapping slabs."));
 		ag_rmaps[i].ar_last_rmap.rm_owner = XFS_RMAP_OWN_UNKNOWN;
-		error = init_slab(&ag_rmaps[i].ar_refcount_items,
-				  sizeof(struct xfs_refcount_irec));
-		if (error)
-			do_error(
-_("Insufficient memory while allocating refcount item slabs."));
 	}
 }
 
@@ -105,7 +161,7 @@ rmaps_free(
 	for (i = 0; i < mp->m_sb.sb_agcount; i++) {
 		free_slab(&ag_rmaps[i].ar_rmaps);
 		free_slab(&ag_rmaps[i].ar_raw_rmaps);
-		free_slab(&ag_rmaps[i].ar_refcount_items);
+		rmaps_destroy(mp, &ag_rmaps[i]);
 	}
 	free(ag_rmaps);
 	ag_rmaps = NULL;
@@ -136,6 +192,103 @@ rmaps_are_mergeable(
 	return r1->rm_offset + r1->rm_blockcount == r2->rm_offset;
 }
 
+int
+rmap_init_mem_cursor(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	xfs_agnumber_t		agno,
+	struct rmap_mem_cur	*rmcur)
+{
+	struct xfbtree		*xfbt;
+	struct xfs_perag	*pag;
+	int			error;
+
+	xfbt = ag_rmaps[agno].ar_xfbtree;
+	error = -xfbtree_head_read_buf(xfbt, tp, &rmcur->mhead_bp);
+	if (error)
+		return error;
+
+	pag = libxfs_perag_get(mp, agno);
+	rmcur->mcur = libxfs_rmapbt_mem_cursor(pag, tp, rmcur->mhead_bp, xfbt);
+
+	error = -libxfs_btree_goto_left_edge(rmcur->mcur);
+	if (error)
+		rmap_free_mem_cursor(tp, rmcur, error);
+
+	libxfs_perag_put(pag);
+	return error;
+}
+
+void
+rmap_free_mem_cursor(
+	struct xfs_trans	*tp,
+	struct rmap_mem_cur	*rmcur,
+	int			error)
+{
+	libxfs_btree_del_cursor(rmcur->mcur, error);
+	libxfs_trans_brelse(tp, rmcur->mhead_bp);
+	rmcur->mcur = NULL;
+	rmcur->mhead_bp = NULL;
+}
+
+/*
+ * Retrieve the next record from the in-memory rmap btree.  Returns 1 if irec
+ * has been filled out, 0 if there aren't any more records, or a negative errno
+ * value if an error happened.
+ */
+int
+rmap_get_mem_rec(
+	struct rmap_mem_cur	*rmcur,
+	struct xfs_rmap_irec	*irec)
+{
+	int			stat = 0;
+	int			error;
+
+	error = -libxfs_btree_increment(rmcur->mcur, 0, &stat);
+	if (error)
+		return -error;
+	if (!stat)
+		return 0;
+
+	error = -libxfs_rmap_get_rec(rmcur->mcur, irec, &stat);
+	if (error)
+		return -error;
+
+	return stat;
+}
+
+static void
+rmap_add_mem_rec(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno,
+	struct xfs_rmap_irec	*rmap)
+{
+	struct rmap_mem_cur	rmcur;
+	struct xfbtree		*xfbt;
+	struct xfs_trans	*tp;
+	int			error;
+
+	xfbt = ag_rmaps[agno].ar_xfbtree;
+	error = -libxfs_trans_alloc_empty(mp, &tp);
+	if (error)
+		do_error(_("allocating tx for in-memory rmap update\n"));
+
+	error = rmap_init_mem_cursor(mp, tp, agno, &rmcur);
+	if (error)
+		do_error(_("reading in-memory rmap btree head\n"));
+
+	error = -libxfs_rmap_map_raw(rmcur.mcur, rmap);
+	if (error)
+		do_error(_("adding rmap to in-memory btree, err %d\n"), error);
+	rmap_free_mem_cursor(tp, &rmcur, 0);
+
+	error = xfbtree_trans_commit(xfbt, tp);
+	if (error)
+		do_error(_("committing in-memory rmap record\n"));
+
+	libxfs_trans_cancel(tp);
+}
+
 /*
  * Add an observation about a block mapping in an inode's data or attribute
  * fork for later btree reconstruction.
@@ -173,6 +326,9 @@ rmap_add_rec(
 	rmap.rm_blockcount = irec->br_blockcount;
 	if (irec->br_state == XFS_EXT_UNWRITTEN)
 		rmap.rm_flags |= XFS_RMAP_UNWRITTEN;
+
+	rmap_add_mem_rec(mp, agno, &rmap);
+
 	last_rmap = &ag_rmaps[agno].ar_last_rmap;
 	if (last_rmap->rm_owner == XFS_RMAP_OWN_UNKNOWN)
 		*last_rmap = rmap;
@@ -223,6 +379,8 @@ __rmap_add_raw_rec(
 		rmap.rm_flags |= XFS_RMAP_BMBT_BLOCK;
 	rmap.rm_startblock = agbno;
 	rmap.rm_blockcount = len;
+
+	rmap_add_mem_rec(mp, agno, &rmap);
 	return slab_add(ag_rmaps[agno].ar_raw_rmaps, &rmap);
 }
 
@@ -273,6 +431,36 @@ rmap_add_ag_rec(
 	return __rmap_add_raw_rec(mp, agno, agbno, len, owner, false, false);
 }
 
+/*
+ * Add a reverse mapping for a per-AG btree extent.  These are /not/ tracked
+ * in the in-memory rmap btree because they can only be added to the rmap
+ * data after the in-memory btrees have been written to disk.
+ */
+int
+rmap_add_agbtree_mapping(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len,
+	uint64_t		owner)
+{
+	struct xfs_rmap_irec	rmap = {
+		.rm_owner	= owner,
+		.rm_startblock	= agbno,
+		.rm_blockcount	= len,
+	};
+	struct xfs_perag	*pag;
+
+	if (!rmap_needs_work(mp))
+		return 0;
+
+	pag = libxfs_perag_get(mp, agno);
+	assert(libxfs_verify_agbext(pag, agbno, len));
+	libxfs_perag_put(pag);
+
+	return slab_add(ag_rmaps[agno].ar_raw_rmaps, &rmap);
+}
+
 /*
  * Merge adjacent raw rmaps and add them to the main rmap list.
  */
@@ -441,7 +629,7 @@ rmap_add_fixed_ag_rec(
  * the rmapbt, after which it is fully regenerated.
  */
 int
-rmap_store_ag_btree_rec(
+rmap_commit_agbtree_mappings(
 	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno)
 {
@@ -536,7 +724,7 @@ rmap_store_ag_btree_rec(
 	if (error)
 		goto err;
 
-	/* Create cursors to refcount structures */
+	/* Create cursors to rmap structures */
 	error = init_slab_cursor(ag_rmap->ar_rmaps, rmap_compare, &rm_cur);
 	if (error)
 		goto err;
@@ -870,6 +1058,21 @@ compute_refcounts(
 }
 #undef RMAP_END
 
+static int
+count_btree_records(
+	struct xfs_btree_cur	*cur,
+	int			level,
+	void			*data)
+{
+	uint64_t		*nr = data;
+	struct xfs_btree_block	*block;
+	struct xfs_buf		*bp;
+
+	block = libxfs_btree_get_block(cur, level, &bp);
+	*nr += be16_to_cpu(block->bb_numrecs);
+	return 0;
+}
+
 /*
  * Return the number of rmap objects for an AG.
  */
@@ -878,7 +1081,26 @@ rmap_record_count(
 	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno)
 {
-	return slab_count(ag_rmaps[agno].ar_rmaps);
+	struct rmap_mem_cur	rmcur;
+	uint64_t		nr = 0;
+	int			error;
+
+	if (ag_rmaps[agno].ar_xfbtree == NULL)
+		return 0;
+
+	error = rmap_init_mem_cursor(mp, NULL, agno, &rmcur);
+	if (error)
+		do_error(_("%s while reading in-memory rmap btree\n"),
+				strerror(error));
+
+	error = -libxfs_btree_visit_blocks(rmcur.mcur, count_btree_records,
+			XFS_BTREE_VISIT_RECORDS, &nr);
+	if (error)
+		do_error(_("%s while counting in-memory rmap records\n"),
+				strerror(error));
+
+	rmap_free_mem_cursor(NULL, &rmcur, 0);
+	return nr;
 }
 
 /*
@@ -1544,17 +1766,18 @@ estimate_rmapbt_blocks(
 	if (!rmap_needs_work(mp) || !xfs_has_rmapbt(mp))
 		return 0;
 
+	x = &ag_rmaps[pag->pag_agno];
+	if (!x->ar_xfbtree)
+		return 0;
+
 	/*
 	 * Overestimate the amount of space needed by pretending that every
-	 * record in the incore slab will become rmapbt records.
+	 * byte in the incore tree is used to store rmapbt records.  This
+	 * means we can use SEEK_DATA/HOLE on the xfile, which is faster than
+	 * walking the entire btree.
 	 */
-	x = &ag_rmaps[pag->pag_agno];
-	if (x->ar_rmaps)
-		nr_recs += slab_count(x->ar_rmaps);
-	if (x->ar_raw_rmaps)
-		nr_recs += slab_count(x->ar_raw_rmaps);
-
-	return libxfs_rmapbt_calc_size(mp, nr_recs);
+	nr_recs = xfbtree_bytes(x->ar_xfbtree) / sizeof(struct xfs_rmap_rec);
+	return libxfs_rmapbt_calc_size(pag->pag_mount, nr_recs);
 }
 
 /* Estimate the size of the ondisk refcountbt from the incore data. */
diff --git a/repair/rmap.h b/repair/rmap.h
index 1bc8c127d0e..2abd37d14e5 100644
--- a/repair/rmap.h
+++ b/repair/rmap.h
@@ -24,7 +24,10 @@ extern int rmap_fold_raw_recs(struct xfs_mount *mp, xfs_agnumber_t agno);
 extern bool rmaps_are_mergeable(struct xfs_rmap_irec *r1, struct xfs_rmap_irec *r2);
 
 extern int rmap_add_fixed_ag_rec(struct xfs_mount *, xfs_agnumber_t);
-extern int rmap_store_ag_btree_rec(struct xfs_mount *, xfs_agnumber_t);
+
+int rmap_add_agbtree_mapping(struct xfs_mount *mp, xfs_agnumber_t agno,
+		xfs_agblock_t agbno, xfs_extlen_t len, uint64_t owner);
+int rmap_commit_agbtree_mappings(struct xfs_mount *mp, xfs_agnumber_t agno);
 
 uint64_t rmap_record_count(struct xfs_mount *mp, xfs_agnumber_t agno);
 extern int rmap_init_cursor(xfs_agnumber_t, struct xfs_slab_cursor **);
@@ -52,4 +55,15 @@ extern void rmap_store_agflcount(struct xfs_mount *, xfs_agnumber_t, int);
 xfs_extlen_t estimate_rmapbt_blocks(struct xfs_perag *pag);
 xfs_extlen_t estimate_refcountbt_blocks(struct xfs_perag *pag);
 
+struct rmap_mem_cur {
+	struct xfs_btree_cur	*mcur;
+	struct xfs_buf		*mhead_bp;
+};
+
+int rmap_init_mem_cursor(struct xfs_mount *mp, struct xfs_trans *tp,
+		xfs_agnumber_t agno, struct rmap_mem_cur *rmcur);
+void rmap_free_mem_cursor(struct xfs_trans *tp, struct rmap_mem_cur *rmcur,
+		int error);
+int rmap_get_mem_rec(struct rmap_mem_cur *rmcur, struct xfs_rmap_irec *irec);
+
 #endif /* RMAP_H_ */
diff --git a/repair/xfs_repair.c b/repair/xfs_repair.c
index 01f92e841f2..ba78dc0b8ea 100644
--- a/repair/xfs_repair.c
+++ b/repair/xfs_repair.c
@@ -911,6 +911,12 @@ repair_capture_writeback(
 	struct xfs_mount	*mp = bp->b_mount;
 	static pthread_mutex_t	wb_mutex = PTHREAD_MUTEX_INITIALIZER;
 
+	/* We only care about ondisk metadata. */
+	if (bp->b_target != mp->m_ddev_targp &&
+	    bp->b_target != mp->m_logdev_targp &&
+	    bp->b_target != mp->m_rtdev_targp)
+		return;
+
 	/*
 	 * This write hook ignores any buffer that looks like a superblock to
 	 * avoid hook recursion when setting NEEDSREPAIR.  Higher level code

[PATCH 3/6] xfs_repair: verify on-disk rmap btrees with in-memory btree data

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Check the on-disk reverse mappings with the observations we've recorded
in the in-memory btree during the filesystem walk.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 repair/rmap.c |   58 +++++++++++++++++++++++++++------------------------------
 1 file changed, 27 insertions(+), 31 deletions(-)


diff --git a/repair/rmap.c b/repair/rmap.c
index 53b8ac6fcf9..785431b94d7 100644
--- a/repair/rmap.c
+++ b/repair/rmap.c
@@ -1197,11 +1197,11 @@ rmaps_verify_btree(
 	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno)
 {
+	struct rmap_mem_cur	rm_cur;
+	struct xfs_rmap_irec	rm_rec;
 	struct xfs_rmap_irec	tmp;
-	struct xfs_slab_cursor	*rm_cur;
 	struct xfs_btree_cur	*bt_cur = NULL;
 	struct xfs_buf		*agbp = NULL;
-	struct xfs_rmap_irec	*rm_rec;
 	struct xfs_perag	*pag = NULL;
 	int			have;
 	int			error;
@@ -1214,8 +1214,8 @@ rmaps_verify_btree(
 		return;
 	}
 
-	/* Create cursors to refcount structures */
-	error = rmap_init_cursor(agno, &rm_cur);
+	/* Create cursors to rmap structures */
+	error = rmap_init_mem_cursor(mp, NULL, agno, &rm_cur);
 	if (error) {
 		do_warn(_("Not enough memory to check reverse mappings.\n"));
 		return;
@@ -1238,13 +1238,12 @@ rmaps_verify_btree(
 		goto err_agf;
 	}
 
-	rm_rec = pop_slab_cursor(rm_cur);
-	while (rm_rec) {
-		error = rmap_lookup(bt_cur, rm_rec, &tmp, &have);
+	while ((error = rmap_get_mem_rec(&rm_cur, &rm_rec)) == 1) {
+		error = rmap_lookup(bt_cur, &rm_rec, &tmp, &have);
 		if (error) {
 			do_warn(
 _("Could not read reverse-mapping record for (%u/%u).\n"),
-					agno, rm_rec->rm_startblock);
+					agno, rm_rec.rm_startblock);
 			goto err_cur;
 		}
 
@@ -1254,13 +1253,13 @@ _("Could not read reverse-mapping record for (%u/%u).\n"),
 		 * match the observed rmap.
 		 */
 		if (xfs_has_reflink(bt_cur->bc_mp) &&
-				(!have || !rmap_is_good(rm_rec, &tmp))) {
-			error = rmap_lookup_overlapped(bt_cur, rm_rec,
+				(!have || !rmap_is_good(&rm_rec, &tmp))) {
+			error = rmap_lookup_overlapped(bt_cur, &rm_rec,
 					&tmp, &have);
 			if (error) {
 				do_warn(
 _("Could not read reverse-mapping record for (%u/%u).\n"),
-						agno, rm_rec->rm_startblock);
+						agno, rm_rec.rm_startblock);
 				goto err_cur;
 			}
 		}
@@ -1268,21 +1267,21 @@ _("Could not read reverse-mapping record for (%u/%u).\n"),
 			do_warn(
 _("Missing reverse-mapping record for (%u/%u) %slen %u owner %"PRId64" \
 %s%soff %"PRIu64"\n"),
-				agno, rm_rec->rm_startblock,
-				(rm_rec->rm_flags & XFS_RMAP_UNWRITTEN) ?
+				agno, rm_rec.rm_startblock,
+				(rm_rec.rm_flags & XFS_RMAP_UNWRITTEN) ?
 					_("unwritten ") : "",
-				rm_rec->rm_blockcount,
-				rm_rec->rm_owner,
-				(rm_rec->rm_flags & XFS_RMAP_ATTR_FORK) ?
+				rm_rec.rm_blockcount,
+				rm_rec.rm_owner,
+				(rm_rec.rm_flags & XFS_RMAP_ATTR_FORK) ?
 					_("attr ") : "",
-				(rm_rec->rm_flags & XFS_RMAP_BMBT_BLOCK) ?
+				(rm_rec.rm_flags & XFS_RMAP_BMBT_BLOCK) ?
 					_("bmbt ") : "",
-				rm_rec->rm_offset);
-			goto next_loop;
+				rm_rec.rm_offset);
+			continue;
 		}
 
 		/* Compare each refcount observation against the btree's */
-		if (!rmap_is_good(rm_rec, &tmp)) {
+		if (!rmap_is_good(&rm_rec, &tmp)) {
 			do_warn(
 _("Incorrect reverse-mapping: saw (%u/%u) %slen %u owner %"PRId64" %s%soff \
 %"PRIu64"; should be (%u/%u) %slen %u owner %"PRId64" %s%soff %"PRIu64"\n"),
@@ -1296,20 +1295,17 @@ _("Incorrect reverse-mapping: saw (%u/%u) %slen %u owner %"PRId64" %s%soff \
 				(tmp.rm_flags & XFS_RMAP_BMBT_BLOCK) ?
 					_("bmbt ") : "",
 				tmp.rm_offset,
-				agno, rm_rec->rm_startblock,
-				(rm_rec->rm_flags & XFS_RMAP_UNWRITTEN) ?
+				agno, rm_rec.rm_startblock,
+				(rm_rec.rm_flags & XFS_RMAP_UNWRITTEN) ?
 					_("unwritten ") : "",
-				rm_rec->rm_blockcount,
-				rm_rec->rm_owner,
-				(rm_rec->rm_flags & XFS_RMAP_ATTR_FORK) ?
+				rm_rec.rm_blockcount,
+				rm_rec.rm_owner,
+				(rm_rec.rm_flags & XFS_RMAP_ATTR_FORK) ?
 					_("attr ") : "",
-				(rm_rec->rm_flags & XFS_RMAP_BMBT_BLOCK) ?
+				(rm_rec.rm_flags & XFS_RMAP_BMBT_BLOCK) ?
 					_("bmbt ") : "",
-				rm_rec->rm_offset);
-			goto next_loop;
+				rm_rec.rm_offset);
 		}
-next_loop:
-		rm_rec = pop_slab_cursor(rm_cur);
 	}
 
 err_cur:
@@ -1318,7 +1314,7 @@ _("Incorrect reverse-mapping: saw (%u/%u) %slen %u owner %"PRId64" %s%soff \
 	libxfs_buf_relse(agbp);
 err_pag:
 	libxfs_perag_put(pag);
-	free_slab_cursor(&rm_cur);
+	rmap_free_mem_cursor(NULL, &rm_cur, error);
 }
 
 /*

[PATCH 4/6] xfs_repair: compute refcount data from in-memory rmap btrees

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Use the in-memory rmap btrees to compute the reference count
information.  Convert the bag implementation to hold actual records
instead of pointers to slab objects.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/libxfs_api_defs.h |    4 +
 repair/phase4.c          |    2 
 repair/rmap.c            |  230 ++++++++++++++++++++++++++++++++++++----------
 repair/slab.c            |   49 ++++++----
 repair/slab.h            |    2 
 5 files changed, 216 insertions(+), 71 deletions(-)


diff --git a/libxfs/libxfs_api_defs.h b/libxfs/libxfs_api_defs.h
index bafb05a2f23..91165d77bc7 100644
--- a/libxfs/libxfs_api_defs.h
+++ b/libxfs/libxfs_api_defs.h
@@ -59,9 +59,11 @@
 
 #define xfs_btree_bload			libxfs_btree_bload
 #define xfs_btree_bload_compute_geometry libxfs_btree_bload_compute_geometry
+#define xfs_btree_decrement		libxfs_btree_decrement
 #define xfs_btree_del_cursor		libxfs_btree_del_cursor
 #define xfs_btree_get_block		libxfs_btree_get_block
 #define xfs_btree_goto_left_edge	libxfs_btree_goto_left_edge
+#define xfs_btree_has_more_records	libxfs_btree_has_more_records
 #define xfs_btree_increment		libxfs_btree_increment
 #define xfs_btree_init_block		libxfs_btree_init_block
 #define xfs_btree_mem_head_read_buf	libxfs_btree_mem_head_read_buf
@@ -157,6 +159,8 @@
 #define xfs_inode_validate_cowextsize	libxfs_inode_validate_cowextsize
 #define xfs_inode_validate_extsize	libxfs_inode_validate_extsize
 
+#define xfs_internal_inum		libxfs_internal_inum
+
 #define xfs_iread_extents		libxfs_iread_extents
 #define xfs_irele			libxfs_irele
 #define xfs_log_calc_minimum_size	libxfs_log_calc_minimum_size
diff --git a/repair/phase4.c b/repair/phase4.c
index e4c0e616ffd..f267149abf7 100644
--- a/repair/phase4.c
+++ b/repair/phase4.c
@@ -188,7 +188,7 @@ compute_ag_refcounts(
 	if (error)
 		do_error(
 _("%s while computing reference count records.\n"),
-			 strerror(-error));
+			 strerror(error));
 }
 
 static void
diff --git a/repair/rmap.c b/repair/rmap.c
index 785431b94d7..686ac9c92ff 100644
--- a/repair/rmap.c
+++ b/repair/rmap.c
@@ -931,66 +931,196 @@ refcount_emit(
 _("Insufficient memory while recreating refcount tree."));
 }
 
+#define RMAP_NEXT(r)	((r)->rm_startblock + (r)->rm_blockcount)
+
+/* Decide if an rmap could describe a shared extent. */
+static inline bool
+rmap_shareable(
+	struct xfs_mount		*mp,
+	const struct xfs_rmap_irec	*rmap)
+{
+	/* AG metadata are never sharable */
+	if (XFS_RMAP_NON_INODE_OWNER(rmap->rm_owner))
+		return false;
+
+	/* Metadata in files are never shareable */
+	if (libxfs_internal_inum(mp, rmap->rm_owner))
+		return false;
+
+	/* Metadata and unwritten file blocks are not shareable. */
+	if (rmap->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK |
+			      XFS_RMAP_UNWRITTEN))
+		return false;
+
+	return true;
+}
+
+/* Grab the rmap for the next possible shared extent. */
+STATIC int
+refcount_walk_rmaps(
+	struct xfs_btree_cur	*cur,
+	struct xfs_rmap_irec	*rmap,
+	bool			*have_rec)
+{
+	struct xfs_mount	*mp = cur->bc_mp;
+	int			have_gt;
+	int			error = 0;
+
+	*have_rec = false;
+
+	/*
+	 * Loop through the remaining rmaps.  Remember CoW staging
+	 * extents and the refcountbt blocks from the old tree for later
+	 * disposal.  We can only share written data fork extents, so
+	 * keep looping until we find an rmap for one.
+	 */
+	do {
+		error = -libxfs_btree_increment(cur, 0, &have_gt);
+		if (error)
+			return error;
+		if (!have_gt)
+			return 0;
+
+		error = -libxfs_rmap_get_rec(cur, rmap, &have_gt);
+		if (error)
+			return error;
+		if (!have_gt)
+			return EFSCORRUPTED;
+	} while (!rmap_shareable(mp, rmap));
+
+	*have_rec = true;
+	return 0;
+}
+
+/*
+ * Find the next block where the refcount changes, given the next rmap we
+ * looked at and the ones we're already tracking.
+ */
+static inline int
+next_refcount_edge(
+	struct xfs_bag		*stack_top,
+	struct xfs_rmap_irec	*next_rmap,
+	bool			next_valid,
+	xfs_agblock_t		*nbnop)
+{
+	struct xfs_rmap_irec	*rmap;
+	uint64_t		idx;
+	xfs_agblock_t		nbno = NULLAGBLOCK;
+
+	if (next_valid)
+		nbno = next_rmap->rm_startblock;
+
+	foreach_bag_ptr(stack_top, idx, rmap)
+		nbno = min(nbno, RMAP_NEXT(rmap));
+
+	/*
+	 * We should have found /something/ because either next_rrm is the next
+	 * interesting rmap to look at after emitting this refcount extent, or
+	 * there are other rmaps in rmap_bag contributing to the current
+	 * sharing count.  But if something is seriously wrong, bail out.
+	 */
+	if (nbno == NULLAGBLOCK)
+		return EFSCORRUPTED;
+
+	*nbnop = nbno;
+	return 0;
+}
+
+/*
+ * Walk forward through the rmap btree to collect all rmaps starting at
+ * @bno in @rmap_bag.  These represent the file(s) that share ownership of
+ * the current block.  Upon return, the rmap cursor points to the last record
+ * satisfying the startblock constraint.
+ */
+static int
+refcount_push_rmaps_at(
+	struct rmap_mem_cur	*rmcur,
+	xfs_agnumber_t		agno,
+	struct xfs_bag		*stack_top,
+	xfs_agblock_t		bno,
+	struct xfs_rmap_irec	*irec,
+	bool			*have,
+	const char		*tag)
+{
+	int			have_gt;
+	int			error;
+
+	while (*have && irec->rm_startblock == bno) {
+		rmap_dump(tag, agno, irec);
+		error = bag_add(stack_top, irec);
+		if (error)
+			return error;
+		error = refcount_walk_rmaps(rmcur->mcur, irec, have);
+		if (error)
+			return error;
+	}
+
+	error = -libxfs_btree_decrement(rmcur->mcur, 0, &have_gt);
+	if (error)
+		return error;
+	if (!have_gt)
+		return EFSCORRUPTED;
+
+	return 0;
+}
+
 /*
  * Transform a pile of physical block mapping observations into refcount data
  * for eventual rebuilding of the btrees.
  */
-#define RMAP_END(r)	((r)->rm_startblock + (r)->rm_blockcount)
 int
 compute_refcounts(
 	struct xfs_mount		*mp,
 	xfs_agnumber_t		agno)
 {
+	struct rmap_mem_cur	rmcur;
+	struct xfs_rmap_irec	irec;
 	struct xfs_bag		*stack_top = NULL;
-	struct xfs_slab		*rmaps;
-	struct xfs_slab_cursor	*rmaps_cur;
-	struct xfs_rmap_irec	*array_cur;
 	struct xfs_rmap_irec	*rmap;
-	uint64_t		n, idx;
+	uint64_t		idx;
 	uint64_t		old_stack_nr;
 	xfs_agblock_t		sbno;	/* first bno of this rmap set */
 	xfs_agblock_t		cbno;	/* first bno of this refcount set */
 	xfs_agblock_t		nbno;	/* next bno where rmap set changes */
+	bool			have;
 	int			error;
 
 	if (!xfs_has_reflink(mp))
 		return 0;
 
-	rmaps = ag_rmaps[agno].ar_rmaps;
-
-	error = init_slab_cursor(rmaps, rmap_compare, &rmaps_cur);
+	error = rmap_init_mem_cursor(mp, NULL, agno, &rmcur);
 	if (error)
 		return error;
 
-	error = init_bag(&stack_top);
+	error = init_bag(&stack_top, sizeof(struct xfs_rmap_irec));
 	if (error)
-		goto err;
+		goto out_cur;
 
-	/* While there are rmaps to be processed... */
-	n = 0;
-	while (n < slab_count(rmaps)) {
-		array_cur = peek_slab_cursor(rmaps_cur);
-		sbno = cbno = array_cur->rm_startblock;
+	/* Start the rmapbt cursor to the left of all records. */
+	error = -libxfs_btree_goto_left_edge(rmcur.mcur);
+	if (error)
+		goto out_bag;
+
+
+	/* Process reverse mappings into refcount data. */
+	while (libxfs_btree_has_more_records(rmcur.mcur)) {
 		/* Push all rmaps with pblk == sbno onto the stack */
-		for (;
-		     array_cur && array_cur->rm_startblock == sbno;
-		     array_cur = peek_slab_cursor(rmaps_cur)) {
-			advance_slab_cursor(rmaps_cur); n++;
-			rmap_dump("push0", agno, array_cur);
-			error = bag_add(stack_top, array_cur);
-			if (error)
-				goto err;
-		}
+		error = refcount_walk_rmaps(rmcur.mcur, &irec, &have);
+		if (error)
+			goto out_bag;
+		if (!have)
+			break;
+		sbno = cbno = irec.rm_startblock;
+		error = refcount_push_rmaps_at(&rmcur, agno, stack_top, sbno,
+				&irec, &have, "push0");
+		if (error)
+			goto out_bag;
 		mark_inode_rl(mp, stack_top);
 
 		/* Set nbno to the bno of the next refcount change */
-		if (n < slab_count(rmaps) && array_cur)
-			nbno = array_cur->rm_startblock;
-		else
-			nbno = NULLAGBLOCK;
-		foreach_bag_ptr(stack_top, idx, rmap) {
-			nbno = min(nbno, RMAP_END(rmap));
-		}
+		error = next_refcount_edge(stack_top, &irec, have, &nbno);
+		if (error)
+			goto out_bag;
 
 		/* Emit reverse mappings, if needed */
 		ASSERT(nbno > sbno);
@@ -1000,23 +1130,24 @@ compute_refcounts(
 		while (bag_count(stack_top)) {
 			/* Pop all rmaps that end at nbno */
 			foreach_bag_ptr_reverse(stack_top, idx, rmap) {
-				if (RMAP_END(rmap) != nbno)
+				if (RMAP_NEXT(rmap) != nbno)
 					continue;
 				rmap_dump("pop", agno, rmap);
 				error = bag_remove(stack_top, idx);
 				if (error)
-					goto err;
+					goto out_bag;
 			}
 
 			/* Push array items that start at nbno */
-			for (;
-			     array_cur && array_cur->rm_startblock == nbno;
-			     array_cur = peek_slab_cursor(rmaps_cur)) {
-				advance_slab_cursor(rmaps_cur); n++;
-				rmap_dump("push1", agno, array_cur);
-				error = bag_add(stack_top, array_cur);
+			error = refcount_walk_rmaps(rmcur.mcur, &irec, &have);
+			if (error)
+				goto out_bag;
+			if (have) {
+				error = refcount_push_rmaps_at(&rmcur, agno,
+						stack_top, nbno, &irec, &have,
+						"push1");
 				if (error)
-					goto err;
+					goto out_bag;
 			}
 			mark_inode_rl(mp, stack_top);
 
@@ -1038,25 +1169,22 @@ compute_refcounts(
 			sbno = nbno;
 
 			/* Set nbno to the bno of the next refcount change */
-			if (n < slab_count(rmaps))
-				nbno = array_cur->rm_startblock;
-			else
-				nbno = NULLAGBLOCK;
-			foreach_bag_ptr(stack_top, idx, rmap) {
-				nbno = min(nbno, RMAP_END(rmap));
-			}
+			error = next_refcount_edge(stack_top, &irec, have,
+					&nbno);
+			if (error)
+				goto out_bag;
 
 			/* Emit reverse mappings, if needed */
 			ASSERT(nbno > sbno);
 		}
 	}
-err:
+out_bag:
 	free_bag(&stack_top);
-	free_slab_cursor(&rmaps_cur);
-
+out_cur:
+	rmap_free_mem_cursor(NULL, &rmcur, error);
 	return error;
 }
-#undef RMAP_END
+#undef RMAP_NEXT
 
 static int
 count_btree_records(
diff --git a/repair/slab.c b/repair/slab.c
index 01bc4d426fe..44ca0468eda 100644
--- a/repair/slab.c
+++ b/repair/slab.c
@@ -78,16 +78,26 @@ struct xfs_slab_cursor {
 };
 
 /*
- * Bags -- each bag is an array of pointers items; when a bag fills up, we
- * resize it.
+ * Bags -- each bag is an array of record items; when a bag fills up, we resize
+ * it and hope we don't run out of memory.
  */
 #define MIN_BAG_SIZE	4096
 struct xfs_bag {
 	uint64_t		bg_nr;		/* number of pointers */
 	uint64_t		bg_inuse;	/* number of slots in use */
-	void			**bg_ptrs;	/* pointers */
+	char			*bg_items;	/* pointer to block of items */
+	size_t			bg_item_sz;	/* size of each item */
 };
-#define BAG_END(bag)	(&(bag)->bg_ptrs[(bag)->bg_nr])
+
+static inline void *bag_ptr(struct xfs_bag *bag, uint64_t idx)
+{
+	return &bag->bg_items[bag->bg_item_sz * idx];
+}
+
+static inline void *bag_end(struct xfs_bag *bag)
+{
+	return bag_ptr(bag, bag->bg_nr);
+}
 
 /*
  * Create a slab to hold some objects of a particular size.
@@ -382,15 +392,17 @@ slab_count(
  */
 int
 init_bag(
-	struct xfs_bag	**bag)
+	struct xfs_bag	**bag,
+	size_t		item_sz)
 {
 	struct xfs_bag	*ptr;
 
 	ptr = calloc(1, sizeof(struct xfs_bag));
 	if (!ptr)
 		return -ENOMEM;
-	ptr->bg_ptrs = calloc(MIN_BAG_SIZE, sizeof(void *));
-	if (!ptr->bg_ptrs) {
+	ptr->bg_item_sz = item_sz;
+	ptr->bg_items = calloc(MIN_BAG_SIZE, item_sz);
+	if (!ptr->bg_items) {
 		free(ptr);
 		return -ENOMEM;
 	}
@@ -411,7 +423,7 @@ free_bag(
 	ptr = *bag;
 	if (!ptr)
 		return;
-	free(ptr->bg_ptrs);
+	free(ptr->bg_items);
 	free(ptr);
 	*bag = NULL;
 }
@@ -424,22 +436,23 @@ bag_add(
 	struct xfs_bag	*bag,
 	void		*ptr)
 {
-	void		**p, **x;
+	void		*p, *x;
 
-	p = &bag->bg_ptrs[bag->bg_inuse];
-	if (p == BAG_END(bag)) {
+	p = bag_ptr(bag, bag->bg_inuse);
+	if (p == bag_end(bag)) {
 		/* No free space, alloc more pointers */
 		uint64_t	nr;
 
 		nr = bag->bg_nr * 2;
-		x = realloc(bag->bg_ptrs, nr * sizeof(void *));
+		x = realloc(bag->bg_items, nr * bag->bg_item_sz);
 		if (!x)
 			return -ENOMEM;
-		bag->bg_ptrs = x;
-		memset(BAG_END(bag), 0, bag->bg_nr * sizeof(void *));
+		bag->bg_items = x;
+		memset(bag_end(bag), 0, bag->bg_nr * bag->bg_item_sz);
 		bag->bg_nr = nr;
+		p = bag_ptr(bag, bag->bg_inuse);
 	}
-	bag->bg_ptrs[bag->bg_inuse] = ptr;
+	memcpy(p, ptr, bag->bg_item_sz);
 	bag->bg_inuse++;
 	return 0;
 }
@@ -453,8 +466,8 @@ bag_remove(
 	uint64_t	nr)
 {
 	ASSERT(nr < bag->bg_inuse);
-	memmove(&bag->bg_ptrs[nr], &bag->bg_ptrs[nr + 1],
-		(bag->bg_inuse - nr - 1) * sizeof(void *));
+	memmove(bag_ptr(bag, nr), bag_ptr(bag, nr + 1),
+		(bag->bg_inuse - nr - 1) * bag->bg_item_sz);
 	bag->bg_inuse--;
 	return 0;
 }
@@ -479,5 +492,5 @@ bag_item(
 {
 	if (nr >= bag->bg_inuse)
 		return NULL;
-	return bag->bg_ptrs[nr];
+	return bag_ptr(bag, nr);
 }
diff --git a/repair/slab.h b/repair/slab.h
index 077b4582214..019b169024d 100644
--- a/repair/slab.h
+++ b/repair/slab.h
@@ -28,7 +28,7 @@ void *pop_slab_cursor(struct xfs_slab_cursor *cur);
 
 struct xfs_bag;
 
-int init_bag(struct xfs_bag **bagp);
+int init_bag(struct xfs_bag **bagp, size_t itemsz);
 void free_bag(struct xfs_bag **bagp);
 int bag_add(struct xfs_bag *bag, void *item);
 int bag_remove(struct xfs_bag *bag, uint64_t idx);

[PATCH 5/6] xfs_repair: reduce rmap bag memory usage when creating refcounts

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

The algorithm that computes reference count records uses a "bag"
structure to remember the rmap records corresponding to the current
block.  In the previous patch we converted the bag structure to store
actual rmap records instead of pointers to rmap records owned by another
structure as part of preparing for converting this algorithm to use
in-memory rmap btrees.

However, the memory usage of the bag structure is now excessive -- we
only need the physical extent and inode owner information to generate
refcount records and mark inodes that require the reflink flag.  IOWs,
the flags and offset fields are unnecessary.  Create a custom structure
for the bag, which halves its memory usage.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 repair/rmap.c |   74 ++++++++++++++++++++++++++++++++++-----------------------
 1 file changed, 44 insertions(+), 30 deletions(-)


diff --git a/repair/rmap.c b/repair/rmap.c
index 686ac9c92ff..6b01db77010 100644
--- a/repair/rmap.c
+++ b/repair/rmap.c
@@ -36,6 +36,13 @@ struct xfs_ag_rmap {
 	struct xfs_slab	*ar_refcount_items;	/* refcount items, p4-5 */
 };
 
+/* Only the parts of struct xfs_rmap_irec that we need to compute refcounts. */
+struct rmap_for_refcount {
+	xfs_agblock_t	rm_startblock;
+	xfs_extlen_t	rm_blockcount;
+	uint64_t	rm_owner;
+};
+
 static struct xfs_ag_rmap *ag_rmaps;
 bool rmapbt_suspect;
 static bool refcbt_suspect;
@@ -783,16 +790,14 @@ static void
 rmap_dump(
 	const char		*msg,
 	xfs_agnumber_t		agno,
-	struct xfs_rmap_irec	*rmap)
+	const struct rmap_for_refcount *rfr)
 {
-	printf("%s: %p agno=%u pblk=%llu own=%lld lblk=%llu len=%u flags=0x%x\n",
-		msg, rmap,
+	printf("%s: %p agno=%u agbno=%llu owner=%lld fsbcount=%u\n",
+		msg, rfr,
 		(unsigned int)agno,
-		(unsigned long long)rmap->rm_startblock,
-		(unsigned long long)rmap->rm_owner,
-		(unsigned long long)rmap->rm_offset,
-		(unsigned int)rmap->rm_blockcount,
-		(unsigned int)rmap->rm_flags);
+		(unsigned long long)rfr->rm_startblock,
+		(unsigned long long)rfr->rm_owner,
+		(unsigned int)rfr->rm_blockcount);
 }
 #else
 # define rmap_dump(m, a, r)
@@ -871,30 +876,33 @@ rmap_dump(
  */
 static void
 mark_inode_rl(
-	struct xfs_mount		*mp,
+	struct xfs_mount	*mp,
 	struct xfs_bag		*rmaps)
 {
-	xfs_agnumber_t		iagno;
-	struct xfs_rmap_irec	*rmap;
+	struct rmap_for_refcount *rfr;
 	struct ino_tree_node	*irec;
 	int			off;
 	uint64_t		idx;
-	xfs_agino_t		ino;
 
 	if (bag_count(rmaps) < 2)
 		return;
 
 	/* Reflink flag accounting */
-	foreach_bag_ptr(rmaps, idx, rmap) {
-		ASSERT(!XFS_RMAP_NON_INODE_OWNER(rmap->rm_owner));
-		iagno = XFS_INO_TO_AGNO(mp, rmap->rm_owner);
-		ino = XFS_INO_TO_AGINO(mp, rmap->rm_owner);
-		pthread_mutex_lock(&ag_locks[iagno].lock);
-		irec = find_inode_rec(mp, iagno, ino);
-		off = get_inode_offset(mp, rmap->rm_owner, irec);
+	foreach_bag_ptr(rmaps, idx, rfr) {
+		xfs_agnumber_t	agno;
+		xfs_agino_t	agino;
+
+		ASSERT(!XFS_RMAP_NON_INODE_OWNER(rfr->rm_owner));
+
+		agno = XFS_INO_TO_AGNO(mp, rfr->rm_owner);
+		agino = XFS_INO_TO_AGINO(mp, rfr->rm_owner);
+
+		pthread_mutex_lock(&ag_locks[agno].lock);
+		irec = find_inode_rec(mp, agno, agino);
+		off = get_inode_offset(mp, rfr->rm_owner, irec);
 		/* lock here because we might go outside this ag */
 		set_inode_is_rl(irec, off);
-		pthread_mutex_unlock(&ag_locks[iagno].lock);
+		pthread_mutex_unlock(&ag_locks[agno].lock);
 	}
 }
 
@@ -1003,15 +1011,15 @@ next_refcount_edge(
 	bool			next_valid,
 	xfs_agblock_t		*nbnop)
 {
-	struct xfs_rmap_irec	*rmap;
+	struct rmap_for_refcount *rfr;
 	uint64_t		idx;
 	xfs_agblock_t		nbno = NULLAGBLOCK;
 
 	if (next_valid)
 		nbno = next_rmap->rm_startblock;
 
-	foreach_bag_ptr(stack_top, idx, rmap)
-		nbno = min(nbno, RMAP_NEXT(rmap));
+	foreach_bag_ptr(stack_top, idx, rfr)
+		nbno = min(nbno, RMAP_NEXT(rfr));
 
 	/*
 	 * We should have found /something/ because either next_rrm is the next
@@ -1046,8 +1054,14 @@ refcount_push_rmaps_at(
 	int			error;
 
 	while (*have && irec->rm_startblock == bno) {
-		rmap_dump(tag, agno, irec);
-		error = bag_add(stack_top, irec);
+		struct rmap_for_refcount	rfr = {
+			.rm_startblock		= irec->rm_startblock,
+			.rm_blockcount		= irec->rm_blockcount,
+			.rm_owner		= irec->rm_owner,
+		};
+
+		rmap_dump(tag, agno, &rfr);
+		error = bag_add(stack_top, &rfr);
 		if (error)
 			return error;
 		error = refcount_walk_rmaps(rmcur->mcur, irec, have);
@@ -1076,7 +1090,7 @@ compute_refcounts(
 	struct rmap_mem_cur	rmcur;
 	struct xfs_rmap_irec	irec;
 	struct xfs_bag		*stack_top = NULL;
-	struct xfs_rmap_irec	*rmap;
+	struct rmap_for_refcount *rfr;
 	uint64_t		idx;
 	uint64_t		old_stack_nr;
 	xfs_agblock_t		sbno;	/* first bno of this rmap set */
@@ -1092,7 +1106,7 @@ compute_refcounts(
 	if (error)
 		return error;
 
-	error = init_bag(&stack_top, sizeof(struct xfs_rmap_irec));
+	error = init_bag(&stack_top, sizeof(struct rmap_for_refcount));
 	if (error)
 		goto out_cur;
 
@@ -1129,10 +1143,10 @@ compute_refcounts(
 		/* While stack isn't empty... */
 		while (bag_count(stack_top)) {
 			/* Pop all rmaps that end at nbno */
-			foreach_bag_ptr_reverse(stack_top, idx, rmap) {
-				if (RMAP_NEXT(rmap) != nbno)
+			foreach_bag_ptr_reverse(stack_top, idx, rfr) {
+				if (RMAP_NEXT(rfr) != nbno)
 					continue;
-				rmap_dump("pop", agno, rmap);
+				rmap_dump("pop", agno, rfr);
 				error = bag_remove(stack_top, idx);
 				if (error)
 					goto out_bag;

[PATCH 6/6] xfs_repair: remove the old rmap collection slabs

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Now that we've switched the offline repair code to use an in-memory
rmap btree for everything except recording the rmaps for the newly
generated per-AG btrees, get rid of all the old code.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 repair/dinode.c |    9 +--
 repair/phase4.c |   23 -------
 repair/rmap.c   |  189 +++++++++----------------------------------------------
 repair/rmap.h   |   16 ++---
 repair/scan.c   |    7 --
 5 files changed, 42 insertions(+), 202 deletions(-)


diff --git a/repair/dinode.c b/repair/dinode.c
index 629440fe6de..f2da4325d5e 100644
--- a/repair/dinode.c
+++ b/repair/dinode.c
@@ -628,13 +628,8 @@ _("illegal state %d in block map %" PRIu64 "\n"),
 				break;
 			}
 		}
-		if (collect_rmaps) { /* && !check_dups */
-			error = rmap_add_rec(mp, ino, whichfork, &irec);
-			if (error)
-				do_error(
-_("couldn't add reverse mapping\n")
-					);
-		}
+		if (collect_rmaps) /* && !check_dups */
+			rmap_add_rec(mp, ino, whichfork, &irec);
 		*tot += irec.br_blockcount;
 	}
 	error = 0;
diff --git a/repair/phase4.c b/repair/phase4.c
index f267149abf7..5e5d8c3c7d9 100644
--- a/repair/phase4.c
+++ b/repair/phase4.c
@@ -142,17 +142,7 @@ static void
 process_ags(
 	xfs_mount_t		*mp)
 {
-	xfs_agnumber_t		i;
-	int			error;
-
 	do_inode_prefetch(mp, ag_stride, process_ag_func, true, false);
-	for (i = 0; i < mp->m_sb.sb_agcount; i++) {
-		error = rmap_finish_collecting_fork_recs(mp, i);
-		if (error)
-			do_error(
-_("unable to finish adding attr/data fork reverse-mapping data for AG %u.\n"),
-				i);
-	}
 }
 
 static void
@@ -161,18 +151,7 @@ check_rmap_btrees(
 	xfs_agnumber_t	agno,
 	void		*arg)
 {
-	int		error;
-
-	error = rmap_add_fixed_ag_rec(wq->wq_ctx, agno);
-	if (error)
-		do_error(
-_("unable to add AG %u metadata reverse-mapping data.\n"), agno);
-
-	error = rmap_fold_raw_recs(wq->wq_ctx, agno);
-	if (error)
-		do_error(
-_("unable to merge AG %u metadata reverse-mapping data.\n"), agno);
-
+	rmap_add_fixed_ag_rec(wq->wq_ctx, agno);
 	rmaps_verify_btree(wq->wq_ctx, agno);
 }
 
diff --git a/repair/rmap.c b/repair/rmap.c
index 6b01db77010..b338cdc3bea 100644
--- a/repair/rmap.c
+++ b/repair/rmap.c
@@ -28,11 +28,9 @@
 /* per-AG rmap object anchor */
 struct xfs_ag_rmap {
 	struct xfbtree	*ar_xfbtree;		/* rmap observations */
-	struct xfs_slab	*ar_rmaps;		/* rmap observations, p4 */
-	struct xfs_slab	*ar_raw_rmaps;		/* unmerged rmaps */
+	struct xfs_slab	*ar_agbtree_rmaps;	/* rmaps for rebuilt ag btrees */
 	int		ar_flcount;		/* agfl entries from leftover */
 						/* agbt allocations */
-	struct xfs_rmap_irec	ar_last_rmap;	/* last rmap seen */
 	struct xfs_slab	*ar_refcount_items;	/* refcount items, p4-5 */
 };
 
@@ -72,6 +70,7 @@ rmaps_destroy(
 {
 	struct xfs_buftarg	*target;
 
+	free_slab(&ag_rmap->ar_agbtree_rmaps);
 	free_slab(&ag_rmap->ar_refcount_items);
 
 	if (!ag_rmap->ar_xfbtree)
@@ -113,6 +112,11 @@ rmaps_init_ag(
 	if (error)
 		goto nomem;
 
+	error = init_slab(&ag_rmap->ar_agbtree_rmaps,
+			sizeof(struct xfs_rmap_irec));
+	if (error)
+		goto nomem;
+
 	return;
 nomem:
 	do_error(
@@ -127,7 +131,6 @@ rmaps_init(
 	struct xfs_mount	*mp)
 {
 	xfs_agnumber_t		i;
-	int			error;
 
 	if (!rmap_needs_work(mp))
 		return;
@@ -136,21 +139,8 @@ rmaps_init(
 	if (!ag_rmaps)
 		do_error(_("couldn't allocate per-AG reverse map roots\n"));
 
-	for (i = 0; i < mp->m_sb.sb_agcount; i++) {
+	for (i = 0; i < mp->m_sb.sb_agcount; i++)
 		rmaps_init_ag(mp, i, &ag_rmaps[i]);
-
-		error = init_slab(&ag_rmaps[i].ar_rmaps,
-				sizeof(struct xfs_rmap_irec));
-		if (error)
-			do_error(
-_("Insufficient memory while allocating reverse mapping slabs."));
-		error = init_slab(&ag_rmaps[i].ar_raw_rmaps,
-				  sizeof(struct xfs_rmap_irec));
-		if (error)
-			do_error(
-_("Insufficient memory while allocating raw metadata reverse mapping slabs."));
-		ag_rmaps[i].ar_last_rmap.rm_owner = XFS_RMAP_OWN_UNKNOWN;
-	}
 }
 
 /*
@@ -165,11 +155,8 @@ rmaps_free(
 	if (!rmap_needs_work(mp))
 		return;
 
-	for (i = 0; i < mp->m_sb.sb_agcount; i++) {
-		free_slab(&ag_rmaps[i].ar_rmaps);
-		free_slab(&ag_rmaps[i].ar_raw_rmaps);
+	for (i = 0; i < mp->m_sb.sb_agcount; i++)
 		rmaps_destroy(mp, &ag_rmaps[i]);
-	}
 	free(ag_rmaps);
 	ag_rmaps = NULL;
 }
@@ -300,7 +287,7 @@ rmap_add_mem_rec(
  * Add an observation about a block mapping in an inode's data or attribute
  * fork for later btree reconstruction.
  */
-int
+void
 rmap_add_rec(
 	struct xfs_mount	*mp,
 	xfs_ino_t		ino,
@@ -310,11 +297,9 @@ rmap_add_rec(
 	struct xfs_rmap_irec	rmap;
 	xfs_agnumber_t		agno;
 	xfs_agblock_t		agbno;
-	struct xfs_rmap_irec	*last_rmap;
-	int			error = 0;
 
 	if (!rmap_needs_work(mp))
-		return 0;
+		return;
 
 	agno = XFS_FSB_TO_AGNO(mp, irec->br_startblock);
 	agbno = XFS_FSB_TO_AGBNO(mp, irec->br_startblock);
@@ -335,36 +320,10 @@ rmap_add_rec(
 		rmap.rm_flags |= XFS_RMAP_UNWRITTEN;
 
 	rmap_add_mem_rec(mp, agno, &rmap);
-
-	last_rmap = &ag_rmaps[agno].ar_last_rmap;
-	if (last_rmap->rm_owner == XFS_RMAP_OWN_UNKNOWN)
-		*last_rmap = rmap;
-	else if (rmaps_are_mergeable(last_rmap, &rmap))
-		last_rmap->rm_blockcount += rmap.rm_blockcount;
-	else {
-		error = slab_add(ag_rmaps[agno].ar_rmaps, last_rmap);
-		if (error)
-			return error;
-		*last_rmap = rmap;
-	}
-
-	return error;
-}
-
-/* Finish collecting inode data/attr fork rmaps. */
-int
-rmap_finish_collecting_fork_recs(
-	struct xfs_mount	*mp,
-	xfs_agnumber_t		agno)
-{
-	if (!rmap_needs_work(mp) ||
-	    ag_rmaps[agno].ar_last_rmap.rm_owner == XFS_RMAP_OWN_UNKNOWN)
-		return 0;
-	return slab_add(ag_rmaps[agno].ar_rmaps, &ag_rmaps[agno].ar_last_rmap);
 }
 
 /* add a raw rmap; these will be merged later */
-static int
+static void
 __rmap_add_raw_rec(
 	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno,
@@ -388,13 +347,12 @@ __rmap_add_raw_rec(
 	rmap.rm_blockcount = len;
 
 	rmap_add_mem_rec(mp, agno, &rmap);
-	return slab_add(ag_rmaps[agno].ar_raw_rmaps, &rmap);
 }
 
 /*
  * Add a reverse mapping for an inode fork's block mapping btree block.
  */
-int
+void
 rmap_add_bmbt_rec(
 	struct xfs_mount	*mp,
 	xfs_ino_t		ino,
@@ -405,7 +363,7 @@ rmap_add_bmbt_rec(
 	xfs_agblock_t		agbno;
 
 	if (!rmap_needs_work(mp))
-		return 0;
+		return;
 
 	agno = XFS_FSB_TO_AGNO(mp, fsbno);
 	agbno = XFS_FSB_TO_AGBNO(mp, fsbno);
@@ -413,14 +371,14 @@ rmap_add_bmbt_rec(
 	ASSERT(agno < mp->m_sb.sb_agcount);
 	ASSERT(agbno + 1 <= mp->m_sb.sb_agblocks);
 
-	return __rmap_add_raw_rec(mp, agno, agbno, 1, ino,
-			whichfork == XFS_ATTR_FORK, true);
+	__rmap_add_raw_rec(mp, agno, agbno, 1, ino, whichfork == XFS_ATTR_FORK,
+			true);
 }
 
 /*
  * Add a reverse mapping for a per-AG fixed metadata extent.
  */
-int
+STATIC void
 rmap_add_ag_rec(
 	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno,
@@ -429,13 +387,13 @@ rmap_add_ag_rec(
 	uint64_t		owner)
 {
 	if (!rmap_needs_work(mp))
-		return 0;
+		return;
 
 	ASSERT(agno != NULLAGNUMBER);
 	ASSERT(agno < mp->m_sb.sb_agcount);
 	ASSERT(agbno + len <= mp->m_sb.sb_agblocks);
 
-	return __rmap_add_raw_rec(mp, agno, agbno, len, owner, false, false);
+	__rmap_add_raw_rec(mp, agno, agbno, len, owner, false, false);
 }
 
 /*
@@ -465,62 +423,7 @@ rmap_add_agbtree_mapping(
 	assert(libxfs_verify_agbext(pag, agbno, len));
 	libxfs_perag_put(pag);
 
-	return slab_add(ag_rmaps[agno].ar_raw_rmaps, &rmap);
-}
-
-/*
- * Merge adjacent raw rmaps and add them to the main rmap list.
- */
-int
-rmap_fold_raw_recs(
-	struct xfs_mount	*mp,
-	xfs_agnumber_t		agno)
-{
-	struct xfs_slab_cursor	*cur = NULL;
-	struct xfs_rmap_irec	*prev, *rec;
-	uint64_t		old_sz;
-	int			error = 0;
-
-	old_sz = slab_count(ag_rmaps[agno].ar_rmaps);
-	if (slab_count(ag_rmaps[agno].ar_raw_rmaps) == 0)
-		goto no_raw;
-	qsort_slab(ag_rmaps[agno].ar_raw_rmaps, rmap_compare);
-	error = init_slab_cursor(ag_rmaps[agno].ar_raw_rmaps, rmap_compare,
-			&cur);
-	if (error)
-		goto err;
-
-	prev = pop_slab_cursor(cur);
-	rec = pop_slab_cursor(cur);
-	while (prev && rec) {
-		if (rmaps_are_mergeable(prev, rec)) {
-			prev->rm_blockcount += rec->rm_blockcount;
-			rec = pop_slab_cursor(cur);
-			continue;
-		}
-		error = slab_add(ag_rmaps[agno].ar_rmaps, prev);
-		if (error)
-			goto err;
-		prev = rec;
-		rec = pop_slab_cursor(cur);
-	}
-	if (prev) {
-		error = slab_add(ag_rmaps[agno].ar_rmaps, prev);
-		if (error)
-			goto err;
-	}
-	free_slab(&ag_rmaps[agno].ar_raw_rmaps);
-	error = init_slab(&ag_rmaps[agno].ar_raw_rmaps,
-			sizeof(struct xfs_rmap_irec));
-	if (error)
-		do_error(
-_("Insufficient memory while allocating raw metadata reverse mapping slabs."));
-no_raw:
-	if (old_sz)
-		qsort_slab(ag_rmaps[agno].ar_rmaps, rmap_compare);
-err:
-	free_slab_cursor(&cur);
-	return error;
+	return slab_add(ag_rmaps[agno].ar_agbtree_rmaps, &rmap);
 }
 
 static int
@@ -557,7 +460,7 @@ popcnt(
  * Add an allocation group's fixed metadata to the rmap list.  This includes
  * sb/agi/agf/agfl headers, inode chunks, and the log.
  */
-int
+void
 rmap_add_fixed_ag_rec(
 	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno)
@@ -566,18 +469,14 @@ rmap_add_fixed_ag_rec(
 	xfs_agblock_t		agbno;
 	ino_tree_node_t		*ino_rec;
 	xfs_agino_t		agino;
-	int			error;
 	int			startidx;
 	int			nr;
 
 	if (!rmap_needs_work(mp))
-		return 0;
+		return;
 
 	/* sb/agi/agf/agfl headers */
-	error = rmap_add_ag_rec(mp, agno, 0, XFS_BNO_BLOCK(mp),
-			XFS_RMAP_OWN_FS);
-	if (error)
-		goto out;
+	rmap_add_ag_rec(mp, agno, 0, XFS_BNO_BLOCK(mp), XFS_RMAP_OWN_FS);
 
 	/* inodes */
 	ino_rec = findfirst_inode_rec(agno);
@@ -595,10 +494,8 @@ rmap_add_fixed_ag_rec(
 		agino = ino_rec->ino_startnum + startidx;
 		agbno = XFS_AGINO_TO_AGBNO(mp, agino);
 		if (XFS_AGINO_TO_OFFSET(mp, agino) == 0) {
-			error = rmap_add_ag_rec(mp, agno, agbno, nr,
+			rmap_add_ag_rec(mp, agno, agbno, nr,
 					XFS_RMAP_OWN_INODES);
-			if (error)
-				goto out;
 		}
 	}
 
@@ -606,13 +503,9 @@ rmap_add_fixed_ag_rec(
 	fsbno = mp->m_sb.sb_logstart;
 	if (fsbno && XFS_FSB_TO_AGNO(mp, fsbno) == agno) {
 		agbno = XFS_FSB_TO_AGBNO(mp, mp->m_sb.sb_logstart);
-		error = rmap_add_ag_rec(mp, agno, agbno, mp->m_sb.sb_logblocks,
+		rmap_add_ag_rec(mp, agno, agbno, mp->m_sb.sb_logblocks,
 				XFS_RMAP_OWN_LOG);
-		if (error)
-			goto out;
 	}
-out:
-	return error;
 }
 
 /*
@@ -653,12 +546,6 @@ rmap_commit_agbtree_mappings(
 	if (!xfs_has_rmapbt(mp))
 		return 0;
 
-	/* Release the ar_rmaps; they were put into the rmapbt during p5. */
-	free_slab(&ag_rmap->ar_rmaps);
-	error = init_slab(&ag_rmap->ar_rmaps, sizeof(struct xfs_rmap_irec));
-	if (error)
-		goto err;
-
 	/* Add the AGFL blocks to the rmap list */
 	error = -libxfs_trans_read_buf(
 			mp, NULL, mp->m_ddev_targp,
@@ -682,7 +569,8 @@ rmap_commit_agbtree_mappings(
 	 * space btree blocks, so we must be careful not to create those
 	 * records again.  Create a bitmap of already-recorded OWN_AG rmaps.
 	 */
-	error = init_slab_cursor(ag_rmap->ar_raw_rmaps, rmap_compare, &rm_cur);
+	error = init_slab_cursor(ag_rmap->ar_agbtree_rmaps, rmap_compare,
+			&rm_cur);
 	if (error)
 		goto err;
 	error = -bitmap_alloc(&own_ag_bitmap);
@@ -715,7 +603,7 @@ rmap_commit_agbtree_mappings(
 
 		agbno = be32_to_cpu(*b);
 		if (!bitmap_test(own_ag_bitmap, agbno, 1)) {
-			error = rmap_add_ag_rec(mp, agno, agbno, 1,
+			error = rmap_add_agbtree_mapping(mp, agno, agbno, 1,
 					XFS_RMAP_OWN_AG);
 			if (error)
 				goto err;
@@ -726,13 +614,9 @@ rmap_commit_agbtree_mappings(
 	agflbp = NULL;
 	bitmap_free(&own_ag_bitmap);
 
-	/* Merge all the raw rmaps into the main list */
-	error = rmap_fold_raw_recs(mp, agno);
-	if (error)
-		goto err;
-
 	/* Create cursors to rmap structures */
-	error = init_slab_cursor(ag_rmap->ar_rmaps, rmap_compare, &rm_cur);
+	error = init_slab_cursor(ag_rmap->ar_agbtree_rmaps, rmap_compare,
+			&rm_cur);
 	if (error)
 		goto err;
 
@@ -1101,6 +985,8 @@ compute_refcounts(
 
 	if (!xfs_has_reflink(mp))
 		return 0;
+	if (ag_rmaps[agno].ar_xfbtree == NULL)
+		return 0;
 
 	error = rmap_init_mem_cursor(mp, NULL, agno, &rmcur);
 	if (error)
@@ -1245,17 +1131,6 @@ rmap_record_count(
 	return nr;
 }
 
-/*
- * Return a slab cursor that will return rmap objects in order.
- */
-int
-rmap_init_cursor(
-	xfs_agnumber_t		agno,
-	struct xfs_slab_cursor	**cur)
-{
-	return init_slab_cursor(ag_rmaps[agno].ar_rmaps, rmap_compare, cur);
-}
-
 /*
  * Disable the refcount btree check.
  */
diff --git a/repair/rmap.h b/repair/rmap.h
index 2abd37d14e5..50268b2f8ca 100644
--- a/repair/rmap.h
+++ b/repair/rmap.h
@@ -14,23 +14,19 @@ extern bool rmap_needs_work(struct xfs_mount *);
 extern void rmaps_init(struct xfs_mount *);
 extern void rmaps_free(struct xfs_mount *);
 
-extern int rmap_add_rec(struct xfs_mount *, xfs_ino_t, int, struct xfs_bmbt_irec *);
-extern int rmap_finish_collecting_fork_recs(struct xfs_mount *mp,
-		xfs_agnumber_t agno);
-extern int rmap_add_ag_rec(struct xfs_mount *, xfs_agnumber_t agno,
-		xfs_agblock_t agbno, xfs_extlen_t len, uint64_t owner);
-extern int rmap_add_bmbt_rec(struct xfs_mount *, xfs_ino_t, int, xfs_fsblock_t);
-extern int rmap_fold_raw_recs(struct xfs_mount *mp, xfs_agnumber_t agno);
-extern bool rmaps_are_mergeable(struct xfs_rmap_irec *r1, struct xfs_rmap_irec *r2);
+void rmap_add_rec(struct xfs_mount *mp, xfs_ino_t ino, int whichfork,
+		struct xfs_bmbt_irec *irec);
+void rmap_add_bmbt_rec(struct xfs_mount *mp, xfs_ino_t ino, int whichfork,
+		xfs_fsblock_t fsbno);
+bool rmaps_are_mergeable(struct xfs_rmap_irec *r1, struct xfs_rmap_irec *r2);
 
-extern int rmap_add_fixed_ag_rec(struct xfs_mount *, xfs_agnumber_t);
+void rmap_add_fixed_ag_rec(struct xfs_mount *mp, xfs_agnumber_t agno);
 
 int rmap_add_agbtree_mapping(struct xfs_mount *mp, xfs_agnumber_t agno,
 		xfs_agblock_t agbno, xfs_extlen_t len, uint64_t owner);
 int rmap_commit_agbtree_mappings(struct xfs_mount *mp, xfs_agnumber_t agno);
 
 uint64_t rmap_record_count(struct xfs_mount *mp, xfs_agnumber_t agno);
-extern int rmap_init_cursor(xfs_agnumber_t, struct xfs_slab_cursor **);
 extern void rmap_avoid_check(void);
 void rmaps_verify_btree(struct xfs_mount *mp, xfs_agnumber_t agno);
 
diff --git a/repair/scan.c b/repair/scan.c
index bda2be24af3..fbe1916ac6c 100644
--- a/repair/scan.c
+++ b/repair/scan.c
@@ -224,7 +224,6 @@ scan_bmapbt(
 	xfs_agnumber_t		agno;
 	xfs_agblock_t		agbno;
 	int			state;
-	int			error;
 
 	/*
 	 * unlike the ag freeblock btrees, if anything looks wrong
@@ -415,12 +414,8 @@ _("bad state %d, inode %" PRIu64 " bmap block 0x%" PRIx64 "\n"),
 	if (check_dups && collect_rmaps) {
 		agno = XFS_FSB_TO_AGNO(mp, bno);
 		pthread_mutex_lock(&ag_locks[agno].lock);
-		error = rmap_add_bmbt_rec(mp, ino, whichfork, bno);
+		rmap_add_bmbt_rec(mp, ino, whichfork, bno);
 		pthread_mutex_unlock(&ag_locks[agno].lock);
-		if (error)
-			do_error(
-_("couldn't add inode %"PRIu64" bmbt block %"PRIu64" reverse-mapping data."),
-				ino, bno);
 	}
 
 	if (level == 0) {

[PATCH 1/9] xfs: set the btree cursor bc_ops in xfs_btree_alloc_cursor

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

This is a precursor to putting more static data in the btree ops structure.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfbtree.c            |    3 +--
 libxfs/xfs_alloc_btree.c    |   11 +++++------
 libxfs/xfs_bmap_btree.c     |    3 +--
 libxfs/xfs_btree.h          |    2 ++
 libxfs/xfs_ialloc_btree.c   |   10 ++++++----
 libxfs/xfs_refcount_btree.c |    4 ++--
 libxfs/xfs_rmap_btree.c     |    7 +++----
 7 files changed, 20 insertions(+), 20 deletions(-)


diff --git a/libxfs/xfbtree.c b/libxfs/xfbtree.c
index 7521566fd15..69539635046 100644
--- a/libxfs/xfbtree.c
+++ b/libxfs/xfbtree.c
@@ -245,11 +245,10 @@ xfbtree_dup_cursor(
 	ASSERT(cur->bc_flags & XFS_BTREE_IN_XFILE);
 
 	ncur = xfs_btree_alloc_cursor(cur->bc_mp, cur->bc_tp, cur->bc_btnum,
-			cur->bc_maxlevels, cur->bc_cache);
+			cur->bc_ops, cur->bc_maxlevels, cur->bc_cache);
 	ncur->bc_flags = cur->bc_flags;
 	ncur->bc_nlevels = cur->bc_nlevels;
 	ncur->bc_statoff = cur->bc_statoff;
-	ncur->bc_ops = cur->bc_ops;
 	memcpy(&ncur->bc_mem, &cur->bc_mem, sizeof(cur->bc_mem));
 
 	if (cur->bc_mem.pag)
diff --git a/libxfs/xfs_alloc_btree.c b/libxfs/xfs_alloc_btree.c
index a472ec6d21a..16f683e1dc8 100644
--- a/libxfs/xfs_alloc_btree.c
+++ b/libxfs/xfs_alloc_btree.c
@@ -510,18 +510,17 @@ xfs_allocbt_init_common(
 
 	ASSERT(btnum == XFS_BTNUM_BNO || btnum == XFS_BTNUM_CNT);
 
-	cur = xfs_btree_alloc_cursor(mp, tp, btnum, mp->m_alloc_maxlevels,
-			xfs_allocbt_cur_cache);
-	cur->bc_ag.abt.active = false;
-
 	if (btnum == XFS_BTNUM_CNT) {
-		cur->bc_ops = &xfs_cntbt_ops;
+		cur = xfs_btree_alloc_cursor(mp, tp, btnum, &xfs_cntbt_ops,
+				mp->m_alloc_maxlevels, xfs_allocbt_cur_cache);
 		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtc_2);
 		cur->bc_flags = XFS_BTREE_LASTREC_UPDATE;
 	} else {
-		cur->bc_ops = &xfs_bnobt_ops;
+		cur = xfs_btree_alloc_cursor(mp, tp, btnum, &xfs_bnobt_ops,
+				mp->m_alloc_maxlevels, xfs_allocbt_cur_cache);
 		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtb_2);
 	}
+	cur->bc_ag.abt.active = false;
 
 	cur->bc_ag.pag = xfs_perag_hold(pag);
 
diff --git a/libxfs/xfs_bmap_btree.c b/libxfs/xfs_bmap_btree.c
index 73ba067df06..cfb0684f7b2 100644
--- a/libxfs/xfs_bmap_btree.c
+++ b/libxfs/xfs_bmap_btree.c
@@ -547,11 +547,10 @@ xfs_bmbt_init_common(
 
 	ASSERT(whichfork != XFS_COW_FORK);
 
-	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_BMAP,
+	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_BMAP, &xfs_bmbt_ops,
 			mp->m_bm_maxlevels[whichfork], xfs_bmbt_cur_cache);
 	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_bmbt_2);
 
-	cur->bc_ops = &xfs_bmbt_ops;
 	cur->bc_flags = XFS_BTREE_LONG_PTRS | XFS_BTREE_ROOT_IN_INODE;
 	if (xfs_has_crc(mp))
 		cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
diff --git a/libxfs/xfs_btree.h b/libxfs/xfs_btree.h
index 3e6bdbc5070..ed138889031 100644
--- a/libxfs/xfs_btree.h
+++ b/libxfs/xfs_btree.h
@@ -737,12 +737,14 @@ xfs_btree_alloc_cursor(
 	struct xfs_mount	*mp,
 	struct xfs_trans	*tp,
 	xfs_btnum_t		btnum,
+	const struct xfs_btree_ops *ops,
 	uint8_t			maxlevels,
 	struct kmem_cache	*cache)
 {
 	struct xfs_btree_cur	*cur;
 
 	cur = kmem_cache_zalloc(cache, GFP_NOFS | __GFP_NOFAIL);
+	cur->bc_ops = ops;
 	cur->bc_tp = tp;
 	cur->bc_mp = mp;
 	cur->bc_btnum = btnum;
diff --git a/libxfs/xfs_ialloc_btree.c b/libxfs/xfs_ialloc_btree.c
index 593cb1fcc1d..5ea08cca25b 100644
--- a/libxfs/xfs_ialloc_btree.c
+++ b/libxfs/xfs_ialloc_btree.c
@@ -453,14 +453,16 @@ xfs_inobt_init_common(
 	struct xfs_mount	*mp = pag->pag_mount;
 	struct xfs_btree_cur	*cur;
 
-	cur = xfs_btree_alloc_cursor(mp, tp, btnum,
-			M_IGEO(mp)->inobt_maxlevels, xfs_inobt_cur_cache);
 	if (btnum == XFS_BTNUM_INO) {
+		cur = xfs_btree_alloc_cursor(mp, tp, btnum, &xfs_inobt_ops,
+				M_IGEO(mp)->inobt_maxlevels,
+				xfs_inobt_cur_cache);
 		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_ibt_2);
-		cur->bc_ops = &xfs_inobt_ops;
 	} else {
+		cur = xfs_btree_alloc_cursor(mp, tp, btnum, &xfs_finobt_ops,
+				M_IGEO(mp)->inobt_maxlevels,
+				xfs_inobt_cur_cache);
 		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_fibt_2);
-		cur->bc_ops = &xfs_finobt_ops;
 	}
 
 	if (xfs_has_crc(mp))
diff --git a/libxfs/xfs_refcount_btree.c b/libxfs/xfs_refcount_btree.c
index 9a3c2270c25..561b732b474 100644
--- a/libxfs/xfs_refcount_btree.c
+++ b/libxfs/xfs_refcount_btree.c
@@ -352,7 +352,8 @@ xfs_refcountbt_init_common(
 	ASSERT(pag->pag_agno < mp->m_sb.sb_agcount);
 
 	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_REFC,
-			mp->m_refc_maxlevels, xfs_refcountbt_cur_cache);
+			&xfs_refcountbt_ops, mp->m_refc_maxlevels,
+			xfs_refcountbt_cur_cache);
 	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_refcbt_2);
 
 	cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
@@ -360,7 +361,6 @@ xfs_refcountbt_init_common(
 	cur->bc_ag.pag = xfs_perag_hold(pag);
 	cur->bc_ag.refc.nr_ops = 0;
 	cur->bc_ag.refc.shape_changes = 0;
-	cur->bc_ops = &xfs_refcountbt_ops;
 	return cur;
 }
 
diff --git a/libxfs/xfs_rmap_btree.c b/libxfs/xfs_rmap_btree.c
index f1bcb0b9bd2..c4085a1befb 100644
--- a/libxfs/xfs_rmap_btree.c
+++ b/libxfs/xfs_rmap_btree.c
@@ -515,11 +515,10 @@ xfs_rmapbt_init_common(
 	struct xfs_btree_cur	*cur;
 
 	/* Overlapping btree; 2 keys per pointer. */
-	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_RMAP,
+	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_RMAP, &xfs_rmapbt_ops,
 			mp->m_rmap_maxlevels, xfs_rmapbt_cur_cache);
 	cur->bc_flags = XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING;
 	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_rmap_2);
-	cur->bc_ops = &xfs_rmapbt_ops;
 
 	cur->bc_ag.pag = xfs_perag_hold(pag);
 	return cur;
@@ -644,11 +643,11 @@ xfs_rmapbt_mem_cursor(
 
 	/* Overlapping btree; 2 keys per pointer. */
 	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_RMAP,
-			mp->m_rmap_maxlevels, xfs_rmapbt_cur_cache);
+			&xfs_rmapbt_mem_ops, mp->m_rmap_maxlevels,
+			xfs_rmapbt_cur_cache);
 	cur->bc_flags = XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING |
 			XFS_BTREE_IN_XFILE;
 	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_rmap_2);
-	cur->bc_ops = &xfs_rmapbt_mem_ops;
 	cur->bc_mem.xfbtree = xfbtree;
 	cur->bc_mem.head_bp = head_bp;
 	cur->bc_nlevels = xfs_btree_mem_head_nlevels(head_bp);

[PATCH 2/9] xfs: encode the default bc_flags in the btree ops structure

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Certain btree flags never change for the life of a btree cursor because
they describe the geometry of the btree itself.  Encode these in the
btree ops structure and reduce the amount of code required in each btree
type's init_cursor functions.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_alloc_btree.c    |    8 ++------
 libxfs/xfs_bmap_btree.c     |    5 +----
 libxfs/xfs_btree.h          |    6 ++++++
 libxfs/xfs_ialloc_btree.c   |    3 ---
 libxfs/xfs_refcount_btree.c |    2 --
 libxfs/xfs_rmap_btree.c     |    6 +++---
 6 files changed, 12 insertions(+), 18 deletions(-)


diff --git a/libxfs/xfs_alloc_btree.c b/libxfs/xfs_alloc_btree.c
index 16f683e1dc8..2d33e0e66d5 100644
--- a/libxfs/xfs_alloc_btree.c
+++ b/libxfs/xfs_alloc_btree.c
@@ -478,6 +478,7 @@ static const struct xfs_btree_ops xfs_bnobt_ops = {
 static const struct xfs_btree_ops xfs_cntbt_ops = {
 	.rec_len		= sizeof(xfs_alloc_rec_t),
 	.key_len		= sizeof(xfs_alloc_key_t),
+	.geom_flags		= XFS_BTREE_LASTREC_UPDATE,
 
 	.dup_cursor		= xfs_allocbt_dup_cursor,
 	.set_root		= xfs_allocbt_set_root,
@@ -514,19 +515,14 @@ xfs_allocbt_init_common(
 		cur = xfs_btree_alloc_cursor(mp, tp, btnum, &xfs_cntbt_ops,
 				mp->m_alloc_maxlevels, xfs_allocbt_cur_cache);
 		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtc_2);
-		cur->bc_flags = XFS_BTREE_LASTREC_UPDATE;
 	} else {
 		cur = xfs_btree_alloc_cursor(mp, tp, btnum, &xfs_bnobt_ops,
 				mp->m_alloc_maxlevels, xfs_allocbt_cur_cache);
 		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtb_2);
 	}
-	cur->bc_ag.abt.active = false;
 
 	cur->bc_ag.pag = xfs_perag_hold(pag);
-
-	if (xfs_has_crc(mp))
-		cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
-
+	cur->bc_ag.abt.active = false;
 	return cur;
 }
 
diff --git a/libxfs/xfs_bmap_btree.c b/libxfs/xfs_bmap_btree.c
index cfb0684f7b2..020b8274c47 100644
--- a/libxfs/xfs_bmap_btree.c
+++ b/libxfs/xfs_bmap_btree.c
@@ -516,6 +516,7 @@ xfs_bmbt_keys_contiguous(
 static const struct xfs_btree_ops xfs_bmbt_ops = {
 	.rec_len		= sizeof(xfs_bmbt_rec_t),
 	.key_len		= sizeof(xfs_bmbt_key_t),
+	.geom_flags		= XFS_BTREE_LONG_PTRS | XFS_BTREE_ROOT_IN_INODE,
 
 	.dup_cursor		= xfs_bmbt_dup_cursor,
 	.update_cursor		= xfs_bmbt_update_cursor,
@@ -551,10 +552,6 @@ xfs_bmbt_init_common(
 			mp->m_bm_maxlevels[whichfork], xfs_bmbt_cur_cache);
 	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_bmbt_2);
 
-	cur->bc_flags = XFS_BTREE_LONG_PTRS | XFS_BTREE_ROOT_IN_INODE;
-	if (xfs_has_crc(mp))
-		cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
-
 	cur->bc_ino.ip = ip;
 	cur->bc_ino.allocated = 0;
 	cur->bc_ino.flags = 0;
diff --git a/libxfs/xfs_btree.h b/libxfs/xfs_btree.h
index ed138889031..2c2d5db94b1 100644
--- a/libxfs/xfs_btree.h
+++ b/libxfs/xfs_btree.h
@@ -116,6 +116,9 @@ struct xfs_btree_ops {
 	size_t	key_len;
 	size_t	rec_len;
 
+	/* XFS_BTREE_* flags that determine the geometry of the btree */
+	unsigned int	geom_flags;
+
 	/* cursor operations */
 	struct xfs_btree_cur *(*dup_cursor)(struct xfs_btree_cur *);
 	void	(*update_cursor)(struct xfs_btree_cur *src,
@@ -750,6 +753,9 @@ xfs_btree_alloc_cursor(
 	cur->bc_btnum = btnum;
 	cur->bc_maxlevels = maxlevels;
 	cur->bc_cache = cache;
+	cur->bc_flags = ops->geom_flags;
+	if (xfs_has_crc(mp))
+		cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
 
 	return cur;
 }
diff --git a/libxfs/xfs_ialloc_btree.c b/libxfs/xfs_ialloc_btree.c
index 5ea08cca25b..dea661afc4d 100644
--- a/libxfs/xfs_ialloc_btree.c
+++ b/libxfs/xfs_ialloc_btree.c
@@ -465,9 +465,6 @@ xfs_inobt_init_common(
 		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_fibt_2);
 	}
 
-	if (xfs_has_crc(mp))
-		cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
-
 	cur->bc_ag.pag = xfs_perag_hold(pag);
 	return cur;
 }
diff --git a/libxfs/xfs_refcount_btree.c b/libxfs/xfs_refcount_btree.c
index 561b732b474..1ecd670a9eb 100644
--- a/libxfs/xfs_refcount_btree.c
+++ b/libxfs/xfs_refcount_btree.c
@@ -356,8 +356,6 @@ xfs_refcountbt_init_common(
 			xfs_refcountbt_cur_cache);
 	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_refcbt_2);
 
-	cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
-
 	cur->bc_ag.pag = xfs_perag_hold(pag);
 	cur->bc_ag.refc.nr_ops = 0;
 	cur->bc_ag.refc.shape_changes = 0;
diff --git a/libxfs/xfs_rmap_btree.c b/libxfs/xfs_rmap_btree.c
index c4085a1befb..bedadb8b5bc 100644
--- a/libxfs/xfs_rmap_btree.c
+++ b/libxfs/xfs_rmap_btree.c
@@ -487,6 +487,7 @@ xfs_rmapbt_keys_contiguous(
 static const struct xfs_btree_ops xfs_rmapbt_ops = {
 	.rec_len		= sizeof(struct xfs_rmap_rec),
 	.key_len		= 2 * sizeof(struct xfs_rmap_key),
+	.geom_flags		= XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING,
 
 	.dup_cursor		= xfs_rmapbt_dup_cursor,
 	.set_root		= xfs_rmapbt_set_root,
@@ -517,7 +518,6 @@ xfs_rmapbt_init_common(
 	/* Overlapping btree; 2 keys per pointer. */
 	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_RMAP, &xfs_rmapbt_ops,
 			mp->m_rmap_maxlevels, xfs_rmapbt_cur_cache);
-	cur->bc_flags = XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING;
 	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_rmap_2);
 
 	cur->bc_ag.pag = xfs_perag_hold(pag);
@@ -611,6 +611,8 @@ static const struct xfs_buf_ops xfs_rmapbt_mem_buf_ops = {
 static const struct xfs_btree_ops xfs_rmapbt_mem_ops = {
 	.rec_len		= sizeof(struct xfs_rmap_rec),
 	.key_len		= 2 * sizeof(struct xfs_rmap_key),
+	.geom_flags		= XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING |
+				  XFS_BTREE_IN_XFILE,
 
 	.dup_cursor		= xfbtree_dup_cursor,
 	.set_root		= xfbtree_set_root,
@@ -645,8 +647,6 @@ xfs_rmapbt_mem_cursor(
 	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_RMAP,
 			&xfs_rmapbt_mem_ops, mp->m_rmap_maxlevels,
 			xfs_rmapbt_cur_cache);
-	cur->bc_flags = XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING |
-			XFS_BTREE_IN_XFILE;
 	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_rmap_2);
 	cur->bc_mem.xfbtree = xfbtree;
 	cur->bc_mem.head_bp = head_bp;

[PATCH 3/9] xfs: export some of the btree ops structures

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Export these btree ops structures so that we can reference them in the
AG initialization code in the next patch.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_alloc_btree.c    |    4 ++--
 libxfs/xfs_bmap_btree.c     |    2 +-
 libxfs/xfs_ialloc_btree.c   |    4 ++--
 libxfs/xfs_refcount_btree.c |    2 +-
 libxfs/xfs_rmap_btree.c     |    2 +-
 libxfs/xfs_shared.h         |    9 +++++++++
 6 files changed, 16 insertions(+), 7 deletions(-)


diff --git a/libxfs/xfs_alloc_btree.c b/libxfs/xfs_alloc_btree.c
index 2d33e0e66d5..97d19203550 100644
--- a/libxfs/xfs_alloc_btree.c
+++ b/libxfs/xfs_alloc_btree.c
@@ -452,7 +452,7 @@ xfs_allocbt_keys_contiguous(
 				 be32_to_cpu(key2->alloc.ar_startblock));
 }
 
-static const struct xfs_btree_ops xfs_bnobt_ops = {
+const struct xfs_btree_ops xfs_bnobt_ops = {
 	.rec_len		= sizeof(xfs_alloc_rec_t),
 	.key_len		= sizeof(xfs_alloc_key_t),
 
@@ -475,7 +475,7 @@ static const struct xfs_btree_ops xfs_bnobt_ops = {
 	.keys_contiguous	= xfs_allocbt_keys_contiguous,
 };
 
-static const struct xfs_btree_ops xfs_cntbt_ops = {
+const struct xfs_btree_ops xfs_cntbt_ops = {
 	.rec_len		= sizeof(xfs_alloc_rec_t),
 	.key_len		= sizeof(xfs_alloc_key_t),
 	.geom_flags		= XFS_BTREE_LASTREC_UPDATE,
diff --git a/libxfs/xfs_bmap_btree.c b/libxfs/xfs_bmap_btree.c
index 020b8274c47..aa19b214ad6 100644
--- a/libxfs/xfs_bmap_btree.c
+++ b/libxfs/xfs_bmap_btree.c
@@ -513,7 +513,7 @@ xfs_bmbt_keys_contiguous(
 				 be64_to_cpu(key2->bmbt.br_startoff));
 }
 
-static const struct xfs_btree_ops xfs_bmbt_ops = {
+const struct xfs_btree_ops xfs_bmbt_ops = {
 	.rec_len		= sizeof(xfs_bmbt_rec_t),
 	.key_len		= sizeof(xfs_bmbt_key_t),
 	.geom_flags		= XFS_BTREE_LONG_PTRS | XFS_BTREE_ROOT_IN_INODE,
diff --git a/libxfs/xfs_ialloc_btree.c b/libxfs/xfs_ialloc_btree.c
index dea661afc4d..52cc00e4ff1 100644
--- a/libxfs/xfs_ialloc_btree.c
+++ b/libxfs/xfs_ialloc_btree.c
@@ -397,7 +397,7 @@ xfs_inobt_keys_contiguous(
 				 be32_to_cpu(key2->inobt.ir_startino));
 }
 
-static const struct xfs_btree_ops xfs_inobt_ops = {
+const struct xfs_btree_ops xfs_inobt_ops = {
 	.rec_len		= sizeof(xfs_inobt_rec_t),
 	.key_len		= sizeof(xfs_inobt_key_t),
 
@@ -419,7 +419,7 @@ static const struct xfs_btree_ops xfs_inobt_ops = {
 	.keys_contiguous	= xfs_inobt_keys_contiguous,
 };
 
-static const struct xfs_btree_ops xfs_finobt_ops = {
+const struct xfs_btree_ops xfs_finobt_ops = {
 	.rec_len		= sizeof(xfs_inobt_rec_t),
 	.key_len		= sizeof(xfs_inobt_key_t),
 
diff --git a/libxfs/xfs_refcount_btree.c b/libxfs/xfs_refcount_btree.c
index 1ecd670a9eb..2f91c7b62ef 100644
--- a/libxfs/xfs_refcount_btree.c
+++ b/libxfs/xfs_refcount_btree.c
@@ -316,7 +316,7 @@ xfs_refcountbt_keys_contiguous(
 				 be32_to_cpu(key2->refc.rc_startblock));
 }
 
-static const struct xfs_btree_ops xfs_refcountbt_ops = {
+const struct xfs_btree_ops xfs_refcountbt_ops = {
 	.rec_len		= sizeof(struct xfs_refcount_rec),
 	.key_len		= sizeof(struct xfs_refcount_key),
 
diff --git a/libxfs/xfs_rmap_btree.c b/libxfs/xfs_rmap_btree.c
index bedadb8b5bc..f1325586433 100644
--- a/libxfs/xfs_rmap_btree.c
+++ b/libxfs/xfs_rmap_btree.c
@@ -484,7 +484,7 @@ xfs_rmapbt_keys_contiguous(
 				 be32_to_cpu(key2->rmap.rm_startblock));
 }
 
-static const struct xfs_btree_ops xfs_rmapbt_ops = {
+const struct xfs_btree_ops xfs_rmapbt_ops = {
 	.rec_len		= sizeof(struct xfs_rmap_rec),
 	.key_len		= 2 * sizeof(struct xfs_rmap_key),
 	.geom_flags		= XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING,
diff --git a/libxfs/xfs_shared.h b/libxfs/xfs_shared.h
index 4220d3584c1..518ea9456eb 100644
--- a/libxfs/xfs_shared.h
+++ b/libxfs/xfs_shared.h
@@ -43,6 +43,15 @@ extern const struct xfs_buf_ops xfs_sb_buf_ops;
 extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops;
 extern const struct xfs_buf_ops xfs_symlink_buf_ops;
 
+/* btree ops */
+extern const struct xfs_btree_ops xfs_bnobt_ops;
+extern const struct xfs_btree_ops xfs_cntbt_ops;
+extern const struct xfs_btree_ops xfs_inobt_ops;
+extern const struct xfs_btree_ops xfs_finobt_ops;
+extern const struct xfs_btree_ops xfs_bmbt_ops;
+extern const struct xfs_btree_ops xfs_refcountbt_ops;
+extern const struct xfs_btree_ops xfs_rmapbt_ops;
+
 /* log size calculation functions */
 int	xfs_log_calc_unit_res(struct xfs_mount *mp, int unit_bytes);
 int	xfs_log_calc_minimum_size(struct xfs_mount *);

[PATCH 4/9] xfs: initialize btree blocks using btree_ops structure

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Notice now that the btree ops structure encodes btree geometry flags and
the magic number through the buffer ops.  Refactor the btree block
initialization functions to use the btree ops so that we no longer have
to open code all that.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfbtree.c           |    8 ++-----
 libxfs/xfs_ag.c            |   33 +++++++++++----------------
 libxfs/xfs_ag.h            |    2 +-
 libxfs/xfs_bmap.c          |   10 +++-----
 libxfs/xfs_bmap_btree.c    |    5 ++--
 libxfs/xfs_btree.c         |   53 +++++++++++++++++---------------------------
 libxfs/xfs_btree.h         |   28 +++++++----------------
 libxfs/xfs_btree_staging.c |    5 ++--
 8 files changed, 53 insertions(+), 91 deletions(-)


diff --git a/libxfs/xfbtree.c b/libxfs/xfbtree.c
index 69539635046..97edb4a2b2b 100644
--- a/libxfs/xfbtree.c
+++ b/libxfs/xfbtree.c
@@ -393,10 +393,6 @@ xfbtree_init_leaf_block(
 	struct xfs_buf			*bp;
 	xfs_daddr_t			daddr;
 	int				error;
-	unsigned int			bc_flags = 0;
-
-	if (cfg->flags & XFBTREE_CREATE_LONG_PTRS)
-		bc_flags |= XFS_BTREE_LONG_PTRS;
 
 	daddr = xfo_to_daddr(XFBTREE_INIT_LEAF_BLOCK);
 	error = xfs_buf_get(xfbt->target, daddr, xfbtree_bbsize(), &bp);
@@ -406,8 +402,8 @@ xfbtree_init_leaf_block(
 	trace_xfbtree_create_root_buf(xfbt, bp);
 
 	bp->b_ops = cfg->btree_ops->buf_ops;
-	xfs_btree_init_block_int(mp, bp->b_addr, daddr, cfg->btnum, 0, 0,
-			cfg->owner, bc_flags);
+	xfs_btree_init_block_int(mp, bp->b_addr, cfg->btree_ops, daddr, 0, 0,
+			cfg->owner);
 	error = xfs_bwrite(bp);
 	xfs_buf_relse(bp);
 	if (error)
diff --git a/libxfs/xfs_ag.c b/libxfs/xfs_ag.c
index 1ba23ab533b..9ac49e0a66b 100644
--- a/libxfs/xfs_ag.c
+++ b/libxfs/xfs_ag.c
@@ -471,7 +471,7 @@ xfs_btroot_init(
 	struct xfs_buf		*bp,
 	struct aghdr_init_data	*id)
 {
-	xfs_btree_init_block(mp, bp, id->type, 0, 0, id->agno);
+	xfs_btree_init_block(mp, bp, id->bc_ops, 0, 0, id->agno);
 }
 
 /* Finish initializing a free space btree. */
@@ -529,7 +529,7 @@ xfs_freesp_init_recs(
 }
 
 /*
- * Alloc btree root block init functions
+ * bnobt/cntbt btree root block init functions
  */
 static void
 xfs_bnoroot_init(
@@ -537,17 +537,7 @@ xfs_bnoroot_init(
 	struct xfs_buf		*bp,
 	struct aghdr_init_data	*id)
 {
-	xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 0, id->agno);
-	xfs_freesp_init_recs(mp, bp, id);
-}
-
-static void
-xfs_cntroot_init(
-	struct xfs_mount	*mp,
-	struct xfs_buf		*bp,
-	struct aghdr_init_data	*id)
-{
-	xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 0, id->agno);
+	xfs_btree_init_block(mp, bp, id->bc_ops, 0, 0, id->agno);
 	xfs_freesp_init_recs(mp, bp, id);
 }
 
@@ -563,7 +553,7 @@ xfs_rmaproot_init(
 	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
 	struct xfs_rmap_rec	*rrec;
 
-	xfs_btree_init_block(mp, bp, XFS_BTNUM_RMAP, 0, 4, id->agno);
+	xfs_btree_init_block(mp, bp, id->bc_ops, 0, 4, id->agno);
 
 	/*
 	 * mark the AG header regions as static metadata The BNO
@@ -776,7 +766,7 @@ struct xfs_aghdr_grow_data {
 	size_t			numblks;
 	const struct xfs_buf_ops *ops;
 	aghdr_init_work_f	work;
-	xfs_btnum_t		type;
+	const struct xfs_btree_ops *bc_ops;
 	bool			need_init;
 };
 
@@ -830,13 +820,15 @@ xfs_ag_init_headers(
 		.numblks = BTOBB(mp->m_sb.sb_blocksize),
 		.ops = &xfs_bnobt_buf_ops,
 		.work = &xfs_bnoroot_init,
+		.bc_ops = &xfs_bnobt_ops,
 		.need_init = true
 	},
 	{ /* CNT root block */
 		.daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_CNT_BLOCK(mp)),
 		.numblks = BTOBB(mp->m_sb.sb_blocksize),
 		.ops = &xfs_cntbt_buf_ops,
-		.work = &xfs_cntroot_init,
+		.work = &xfs_bnoroot_init,
+		.bc_ops = &xfs_cntbt_ops,
 		.need_init = true
 	},
 	{ /* INO root block */
@@ -844,7 +836,7 @@ xfs_ag_init_headers(
 		.numblks = BTOBB(mp->m_sb.sb_blocksize),
 		.ops = &xfs_inobt_buf_ops,
 		.work = &xfs_btroot_init,
-		.type = XFS_BTNUM_INO,
+		.bc_ops = &xfs_inobt_ops,
 		.need_init = true
 	},
 	{ /* FINO root block */
@@ -852,7 +844,7 @@ xfs_ag_init_headers(
 		.numblks = BTOBB(mp->m_sb.sb_blocksize),
 		.ops = &xfs_finobt_buf_ops,
 		.work = &xfs_btroot_init,
-		.type = XFS_BTNUM_FINO,
+		.bc_ops = &xfs_finobt_ops,
 		.need_init =  xfs_has_finobt(mp)
 	},
 	{ /* RMAP root block */
@@ -860,6 +852,7 @@ xfs_ag_init_headers(
 		.numblks = BTOBB(mp->m_sb.sb_blocksize),
 		.ops = &xfs_rmapbt_buf_ops,
 		.work = &xfs_rmaproot_init,
+		.bc_ops = &xfs_rmapbt_ops,
 		.need_init = xfs_has_rmapbt(mp)
 	},
 	{ /* REFC root block */
@@ -867,7 +860,7 @@ xfs_ag_init_headers(
 		.numblks = BTOBB(mp->m_sb.sb_blocksize),
 		.ops = &xfs_refcountbt_buf_ops,
 		.work = &xfs_btroot_init,
-		.type = XFS_BTNUM_REFC,
+		.bc_ops = &xfs_refcountbt_ops,
 		.need_init = xfs_has_reflink(mp)
 	},
 	{ /* NULL terminating block */
@@ -885,7 +878,7 @@ xfs_ag_init_headers(
 
 		id->daddr = dp->daddr;
 		id->numblks = dp->numblks;
-		id->type = dp->type;
+		id->bc_ops = dp->bc_ops;
 		error = xfs_ag_init_hdr(mp, id, dp->work, dp->ops);
 		if (error)
 			break;
diff --git a/libxfs/xfs_ag.h b/libxfs/xfs_ag.h
index 06506e09a82..79017fcd3df 100644
--- a/libxfs/xfs_ag.h
+++ b/libxfs/xfs_ag.h
@@ -330,7 +330,7 @@ struct aghdr_init_data {
 	/* per header data */
 	xfs_daddr_t		daddr;		/* header location */
 	size_t			numblks;	/* size of header */
-	xfs_btnum_t		type;		/* type of btree root block */
+	const struct xfs_btree_ops *bc_ops;	/* btree ops */
 };
 
 int xfs_ag_init_headers(struct xfs_mount *mp, struct aghdr_init_data *id);
diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index cfc4350d18e..e7c39ec72f0 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -638,9 +638,8 @@ xfs_bmap_extents_to_btree(
 	 * Fill in the root.
 	 */
 	block = ifp->if_broot;
-	xfs_btree_init_block_int(mp, block, XFS_BUF_DADDR_NULL,
-				 XFS_BTNUM_BMAP, 1, 1, ip->i_ino,
-				 XFS_BTREE_LONG_PTRS);
+	xfs_btree_init_block_int(mp, block, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL,
+			1, 1, ip->i_ino);
 	/*
 	 * Need a cursor.  Can't allocate until bb_level is filled in.
 	 */
@@ -685,9 +684,8 @@ xfs_bmap_extents_to_btree(
 	 */
 	abp->b_ops = &xfs_bmbt_buf_ops;
 	ablock = XFS_BUF_TO_BLOCK(abp);
-	xfs_btree_init_block_int(mp, ablock, xfs_buf_daddr(abp),
-				XFS_BTNUM_BMAP, 0, 0, ip->i_ino,
-				XFS_BTREE_LONG_PTRS);
+	xfs_btree_init_block_int(mp, ablock, &xfs_bmbt_ops, xfs_buf_daddr(abp),
+			0, 0, ip->i_ino);
 
 	for_each_xfs_iext(ifp, &icur, &rec) {
 		if (isnullstartblock(rec.br_startblock))
diff --git a/libxfs/xfs_bmap_btree.c b/libxfs/xfs_bmap_btree.c
index aa19b214ad6..b599201d97a 100644
--- a/libxfs/xfs_bmap_btree.c
+++ b/libxfs/xfs_bmap_btree.c
@@ -42,9 +42,8 @@ xfs_bmdr_to_bmbt(
 	xfs_bmbt_key_t		*tkp;
 	__be64			*tpp;
 
-	xfs_btree_init_block_int(mp, rblock, XFS_BUF_DADDR_NULL,
-				 XFS_BTNUM_BMAP, 0, 0, ip->i_ino,
-				 XFS_BTREE_LONG_PTRS);
+	xfs_btree_init_block_int(mp, rblock, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL,
+			0, 0, ip->i_ino);
 	rblock->bb_level = dblock->bb_level;
 	ASSERT(be16_to_cpu(rblock->bb_level) > 0);
 	rblock->bb_numrecs = dblock->bb_numrecs;
diff --git a/libxfs/xfs_btree.c b/libxfs/xfs_btree.c
index 14f0f017759..d3b2b903def 100644
--- a/libxfs/xfs_btree.c
+++ b/libxfs/xfs_btree.c
@@ -32,24 +32,17 @@
 /*
  * Btree magic numbers.
  */
-static const uint32_t xfs_magics[2][XFS_BTNUM_MAX] = {
-	{ XFS_ABTB_MAGIC, XFS_ABTC_MAGIC, 0, XFS_BMAP_MAGIC, XFS_IBT_MAGIC,
-	  XFS_FIBT_MAGIC, 0 },
-	{ XFS_ABTB_CRC_MAGIC, XFS_ABTC_CRC_MAGIC, XFS_RMAP_CRC_MAGIC,
-	  XFS_BMAP_CRC_MAGIC, XFS_IBT_CRC_MAGIC, XFS_FIBT_CRC_MAGIC,
-	  XFS_REFC_CRC_MAGIC }
-};
-
 uint32_t
 xfs_btree_magic(
-	int			crc,
-	xfs_btnum_t		btnum)
+	struct xfs_mount		*mp,
+	const struct xfs_btree_ops	*ops)
 {
-	uint32_t		magic = xfs_magics[crc][btnum];
+	int				idx = xfs_has_crc(mp) ? 1 : 0;
+	__be32				magic = ops->buf_ops->magic[idx];
 
 	/* Ensure we asked for crc for crc-only magics. */
 	ASSERT(magic != 0);
-	return magic;
+	return be32_to_cpu(magic);
 }
 
 /*
@@ -134,7 +127,6 @@ __xfs_btree_check_lblock(
 	struct xfs_buf		*bp)
 {
 	struct xfs_mount	*mp = cur->bc_mp;
-	xfs_btnum_t		btnum = cur->bc_btnum;
 	int			crc = xfs_has_crc(mp);
 	xfs_failaddr_t		fa;
 	xfs_fsblock_t		fsb = NULLFSBLOCK;
@@ -149,7 +141,7 @@ __xfs_btree_check_lblock(
 			return __this_address;
 	}
 
-	if (be32_to_cpu(block->bb_magic) != xfs_btree_magic(crc, btnum))
+	if (be32_to_cpu(block->bb_magic) != xfs_btree_magic(mp, cur->bc_ops))
 		return __this_address;
 	if (be16_to_cpu(block->bb_level) != level)
 		return __this_address;
@@ -205,7 +197,6 @@ __xfs_btree_check_sblock(
 {
 	struct xfs_mount	*mp = cur->bc_mp;
 	struct xfs_perag	*pag = cur->bc_ag.pag;
-	xfs_btnum_t		btnum = cur->bc_btnum;
 	int			crc = xfs_has_crc(mp);
 	xfs_failaddr_t		fa;
 	xfs_agblock_t		agbno = NULLAGBLOCK;
@@ -218,7 +209,7 @@ __xfs_btree_check_sblock(
 			return __this_address;
 	}
 
-	if (be32_to_cpu(block->bb_magic) != xfs_btree_magic(crc, btnum))
+	if (be32_to_cpu(block->bb_magic) != xfs_btree_magic(mp, cur->bc_ops))
 		return __this_address;
 	if (be16_to_cpu(block->bb_level) != level)
 		return __this_address;
@@ -1222,21 +1213,20 @@ void
 xfs_btree_init_block_int(
 	struct xfs_mount	*mp,
 	struct xfs_btree_block	*buf,
+	const struct xfs_btree_ops *ops,
 	xfs_daddr_t		blkno,
-	xfs_btnum_t		btnum,
 	__u16			level,
 	__u16			numrecs,
-	__u64			owner,
-	unsigned int		flags)
+	__u64			owner)
 {
 	int			crc = xfs_has_crc(mp);
-	__u32			magic = xfs_btree_magic(crc, btnum);
+	__u32			magic = xfs_btree_magic(mp, ops);
 
 	buf->bb_magic = cpu_to_be32(magic);
 	buf->bb_level = cpu_to_be16(level);
 	buf->bb_numrecs = cpu_to_be16(numrecs);
 
-	if (flags & XFS_BTREE_LONG_PTRS) {
+	if (ops->geom_flags & XFS_BTREE_LONG_PTRS) {
 		buf->bb_u.l.bb_leftsib = cpu_to_be64(NULLFSBLOCK);
 		buf->bb_u.l.bb_rightsib = cpu_to_be64(NULLFSBLOCK);
 		if (crc) {
@@ -1263,15 +1253,15 @@ xfs_btree_init_block_int(
 
 void
 xfs_btree_init_block(
-	struct xfs_mount *mp,
-	struct xfs_buf	*bp,
-	xfs_btnum_t	btnum,
-	__u16		level,
-	__u16		numrecs,
-	__u64		owner)
+	struct xfs_mount		*mp,
+	struct xfs_buf			*bp,
+	const struct xfs_btree_ops	*ops,
+	__u16				level,
+	__u16				numrecs,
+	__u64				owner)
 {
-	xfs_btree_init_block_int(mp, XFS_BUF_TO_BLOCK(bp), xfs_buf_daddr(bp),
-				 btnum, level, numrecs, owner, 0);
+	xfs_btree_init_block_int(mp, XFS_BUF_TO_BLOCK(bp), ops,
+			xfs_buf_daddr(bp), level, numrecs, owner);
 }
 
 void
@@ -1296,9 +1286,8 @@ xfs_btree_init_block_cur(
 	else
 		owner = cur->bc_ag.pag->pag_agno;
 
-	xfs_btree_init_block_int(cur->bc_mp, XFS_BUF_TO_BLOCK(bp),
-				xfs_buf_daddr(bp), cur->bc_btnum, level,
-				numrecs, owner, cur->bc_flags);
+	xfs_btree_init_block_int(cur->bc_mp, XFS_BUF_TO_BLOCK(bp), cur->bc_ops,
+			xfs_buf_daddr(bp), level, numrecs, owner);
 }
 
 /*
diff --git a/libxfs/xfs_btree.h b/libxfs/xfs_btree.h
index 2c2d5db94b1..4ee3f13625e 100644
--- a/libxfs/xfs_btree.h
+++ b/libxfs/xfs_btree.h
@@ -63,7 +63,8 @@ union xfs_btree_rec {
 #define	XFS_BTNUM_RMAP	((xfs_btnum_t)XFS_BTNUM_RMAPi)
 #define	XFS_BTNUM_REFC	((xfs_btnum_t)XFS_BTNUM_REFCi)
 
-uint32_t xfs_btree_magic(int crc, xfs_btnum_t btnum);
+struct xfs_btree_ops;
+uint32_t xfs_btree_magic(struct xfs_mount *mp, const struct xfs_btree_ops *ops);
 
 /*
  * For logging record fields.
@@ -450,25 +451,12 @@ xfs_btree_reada_bufs(
 /*
  * Initialise a new btree block header
  */
-void
-xfs_btree_init_block(
-	struct xfs_mount *mp,
-	struct xfs_buf	*bp,
-	xfs_btnum_t	btnum,
-	__u16		level,
-	__u16		numrecs,
-	__u64		owner);
-
-void
-xfs_btree_init_block_int(
-	struct xfs_mount	*mp,
-	struct xfs_btree_block	*buf,
-	xfs_daddr_t		blkno,
-	xfs_btnum_t		btnum,
-	__u16			level,
-	__u16			numrecs,
-	__u64			owner,
-	unsigned int		flags);
+void xfs_btree_init_block(struct xfs_mount *mp, struct xfs_buf *bp,
+		const struct xfs_btree_ops *ops, __u16 level, __u16 numrecs,
+		__u64 owner);
+void xfs_btree_init_block_int(struct xfs_mount *mp,
+		struct xfs_btree_block *buf, const struct xfs_btree_ops *ops,
+		xfs_daddr_t blkno, __u16 level, __u16 numrecs, __u64 owner);
 
 /*
  * Common btree core entry points.
diff --git a/libxfs/xfs_btree_staging.c b/libxfs/xfs_btree_staging.c
index 0ea44dcf14f..e535d10e13f 100644
--- a/libxfs/xfs_btree_staging.c
+++ b/libxfs/xfs_btree_staging.c
@@ -411,9 +411,8 @@ xfs_btree_bload_prep_block(
 
 		/* Initialize it and send it out. */
 		xfs_btree_init_block_int(cur->bc_mp, ifp->if_broot,
-				XFS_BUF_DADDR_NULL, cur->bc_btnum, level,
-				nr_this_block, cur->bc_ino.ip->i_ino,
-				cur->bc_flags);
+				cur->bc_ops, XFS_BUF_DADDR_NULL, level,
+				nr_this_block, cur->bc_ino.ip->i_ino);
 
 		*bpp = NULL;
 		*blockp = ifp->if_broot;

[PATCH 5/9] xfs: rename btree block/buffer init functions

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Rename xfs_btree_init_block_int to xfs_btree_init_block, and
xfs_btree_init_block to xfs_btree_init_buf so that the name suggests the
type that caller are supposed to pass in.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfbtree.c           |    2 +-
 libxfs/xfs_ag.c            |    6 +++---
 libxfs/xfs_bmap.c          |    6 +++---
 libxfs/xfs_bmap_btree.c    |    2 +-
 libxfs/xfs_btree.c         |    8 ++++----
 libxfs/xfs_btree.h         |    4 ++--
 libxfs/xfs_btree_staging.c |    2 +-
 7 files changed, 15 insertions(+), 15 deletions(-)


diff --git a/libxfs/xfbtree.c b/libxfs/xfbtree.c
index 97edb4a2b2b..ad4e42d6b2a 100644
--- a/libxfs/xfbtree.c
+++ b/libxfs/xfbtree.c
@@ -402,7 +402,7 @@ xfbtree_init_leaf_block(
 	trace_xfbtree_create_root_buf(xfbt, bp);
 
 	bp->b_ops = cfg->btree_ops->buf_ops;
-	xfs_btree_init_block_int(mp, bp->b_addr, cfg->btree_ops, daddr, 0, 0,
+	xfs_btree_init_block(mp, bp->b_addr, cfg->btree_ops, daddr, 0, 0,
 			cfg->owner);
 	error = xfs_bwrite(bp);
 	xfs_buf_relse(bp);
diff --git a/libxfs/xfs_ag.c b/libxfs/xfs_ag.c
index 9ac49e0a66b..ddd5584f23e 100644
--- a/libxfs/xfs_ag.c
+++ b/libxfs/xfs_ag.c
@@ -471,7 +471,7 @@ xfs_btroot_init(
 	struct xfs_buf		*bp,
 	struct aghdr_init_data	*id)
 {
-	xfs_btree_init_block(mp, bp, id->bc_ops, 0, 0, id->agno);
+	xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 0, id->agno);
 }
 
 /* Finish initializing a free space btree. */
@@ -537,7 +537,7 @@ xfs_bnoroot_init(
 	struct xfs_buf		*bp,
 	struct aghdr_init_data	*id)
 {
-	xfs_btree_init_block(mp, bp, id->bc_ops, 0, 0, id->agno);
+	xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 0, id->agno);
 	xfs_freesp_init_recs(mp, bp, id);
 }
 
@@ -553,7 +553,7 @@ xfs_rmaproot_init(
 	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
 	struct xfs_rmap_rec	*rrec;
 
-	xfs_btree_init_block(mp, bp, id->bc_ops, 0, 4, id->agno);
+	xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 4, id->agno);
 
 	/*
 	 * mark the AG header regions as static metadata The BNO
diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index e7c39ec72f0..5e3a973e490 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -638,8 +638,8 @@ xfs_bmap_extents_to_btree(
 	 * Fill in the root.
 	 */
 	block = ifp->if_broot;
-	xfs_btree_init_block_int(mp, block, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL,
-			1, 1, ip->i_ino);
+	xfs_btree_init_block(mp, block, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL, 1,
+			1, ip->i_ino);
 	/*
 	 * Need a cursor.  Can't allocate until bb_level is filled in.
 	 */
@@ -684,7 +684,7 @@ xfs_bmap_extents_to_btree(
 	 */
 	abp->b_ops = &xfs_bmbt_buf_ops;
 	ablock = XFS_BUF_TO_BLOCK(abp);
-	xfs_btree_init_block_int(mp, ablock, &xfs_bmbt_ops, xfs_buf_daddr(abp),
+	xfs_btree_init_block(mp, ablock, &xfs_bmbt_ops, xfs_buf_daddr(abp),
 			0, 0, ip->i_ino);
 
 	for_each_xfs_iext(ifp, &icur, &rec) {
diff --git a/libxfs/xfs_bmap_btree.c b/libxfs/xfs_bmap_btree.c
index b599201d97a..ea6bd791eff 100644
--- a/libxfs/xfs_bmap_btree.c
+++ b/libxfs/xfs_bmap_btree.c
@@ -42,7 +42,7 @@ xfs_bmdr_to_bmbt(
 	xfs_bmbt_key_t		*tkp;
 	__be64			*tpp;
 
-	xfs_btree_init_block_int(mp, rblock, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL,
+	xfs_btree_init_block(mp, rblock, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL,
 			0, 0, ip->i_ino);
 	rblock->bb_level = dblock->bb_level;
 	ASSERT(be16_to_cpu(rblock->bb_level) > 0);
diff --git a/libxfs/xfs_btree.c b/libxfs/xfs_btree.c
index d3b2b903def..452ebd7095d 100644
--- a/libxfs/xfs_btree.c
+++ b/libxfs/xfs_btree.c
@@ -1210,7 +1210,7 @@ xfs_btree_set_sibling(
 }
 
 void
-xfs_btree_init_block_int(
+xfs_btree_init_block(
 	struct xfs_mount	*mp,
 	struct xfs_btree_block	*buf,
 	const struct xfs_btree_ops *ops,
@@ -1252,7 +1252,7 @@ xfs_btree_init_block_int(
 }
 
 void
-xfs_btree_init_block(
+xfs_btree_init_buf(
 	struct xfs_mount		*mp,
 	struct xfs_buf			*bp,
 	const struct xfs_btree_ops	*ops,
@@ -1260,7 +1260,7 @@ xfs_btree_init_block(
 	__u16				numrecs,
 	__u64				owner)
 {
-	xfs_btree_init_block_int(mp, XFS_BUF_TO_BLOCK(bp), ops,
+	xfs_btree_init_block(mp, XFS_BUF_TO_BLOCK(bp), ops,
 			xfs_buf_daddr(bp), level, numrecs, owner);
 }
 
@@ -1286,7 +1286,7 @@ xfs_btree_init_block_cur(
 	else
 		owner = cur->bc_ag.pag->pag_agno;
 
-	xfs_btree_init_block_int(cur->bc_mp, XFS_BUF_TO_BLOCK(bp), cur->bc_ops,
+	xfs_btree_init_block(cur->bc_mp, XFS_BUF_TO_BLOCK(bp), cur->bc_ops,
 			xfs_buf_daddr(bp), level, numrecs, owner);
 }
 
diff --git a/libxfs/xfs_btree.h b/libxfs/xfs_btree.h
index 4ee3f13625e..6a27c34e68c 100644
--- a/libxfs/xfs_btree.h
+++ b/libxfs/xfs_btree.h
@@ -451,10 +451,10 @@ xfs_btree_reada_bufs(
 /*
  * Initialise a new btree block header
  */
-void xfs_btree_init_block(struct xfs_mount *mp, struct xfs_buf *bp,
+void xfs_btree_init_buf(struct xfs_mount *mp, struct xfs_buf *bp,
 		const struct xfs_btree_ops *ops, __u16 level, __u16 numrecs,
 		__u64 owner);
-void xfs_btree_init_block_int(struct xfs_mount *mp,
+void xfs_btree_init_block(struct xfs_mount *mp,
 		struct xfs_btree_block *buf, const struct xfs_btree_ops *ops,
 		xfs_daddr_t blkno, __u16 level, __u16 numrecs, __u64 owner);
 
diff --git a/libxfs/xfs_btree_staging.c b/libxfs/xfs_btree_staging.c
index e535d10e13f..c2f39702b7b 100644
--- a/libxfs/xfs_btree_staging.c
+++ b/libxfs/xfs_btree_staging.c
@@ -410,7 +410,7 @@ xfs_btree_bload_prep_block(
 		ifp->if_broot_bytes = (int)new_size;
 
 		/* Initialize it and send it out. */
-		xfs_btree_init_block_int(cur->bc_mp, ifp->if_broot,
+		xfs_btree_init_block(cur->bc_mp, ifp->if_broot,
 				cur->bc_ops, XFS_BUF_DADDR_NULL, level,
 				nr_this_block, cur->bc_ino.ip->i_ino);
 

[PATCH 6/9] xfs: btree convert xfs_btree_init_block to xfs_btree_init_buf calls

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Convert any place we call xfs_btree_init_block with a buffer to use the
_init_buf function.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfbtree.c   |    3 +--
 libxfs/xfs_bmap.c  |    3 +--
 libxfs/xfs_btree.c |    3 +--
 3 files changed, 3 insertions(+), 6 deletions(-)


diff --git a/libxfs/xfbtree.c b/libxfs/xfbtree.c
index ad4e42d6b2a..7310f29a8c2 100644
--- a/libxfs/xfbtree.c
+++ b/libxfs/xfbtree.c
@@ -402,8 +402,7 @@ xfbtree_init_leaf_block(
 	trace_xfbtree_create_root_buf(xfbt, bp);
 
 	bp->b_ops = cfg->btree_ops->buf_ops;
-	xfs_btree_init_block(mp, bp->b_addr, cfg->btree_ops, daddr, 0, 0,
-			cfg->owner);
+	xfs_btree_init_buf(mp, bp, cfg->btree_ops, 0, 0, cfg->owner);
 	error = xfs_bwrite(bp);
 	xfs_buf_relse(bp);
 	if (error)
diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index 5e3a973e490..1c53204e1d5 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -684,8 +684,7 @@ xfs_bmap_extents_to_btree(
 	 */
 	abp->b_ops = &xfs_bmbt_buf_ops;
 	ablock = XFS_BUF_TO_BLOCK(abp);
-	xfs_btree_init_block(mp, ablock, &xfs_bmbt_ops, xfs_buf_daddr(abp),
-			0, 0, ip->i_ino);
+	xfs_btree_init_buf(mp, abp, &xfs_bmbt_ops, 0, 0, ip->i_ino);
 
 	for_each_xfs_iext(ifp, &icur, &rec) {
 		if (isnullstartblock(rec.br_startblock))
diff --git a/libxfs/xfs_btree.c b/libxfs/xfs_btree.c
index 452ebd7095d..c8bbda80b40 100644
--- a/libxfs/xfs_btree.c
+++ b/libxfs/xfs_btree.c
@@ -1286,8 +1286,7 @@ xfs_btree_init_block_cur(
 	else
 		owner = cur->bc_ag.pag->pag_agno;
 
-	xfs_btree_init_block(cur->bc_mp, XFS_BUF_TO_BLOCK(bp), cur->bc_ops,
-			xfs_buf_daddr(bp), level, numrecs, owner);
+	xfs_btree_init_buf(cur->bc_mp, bp, cur->bc_ops, level, numrecs, owner);
 }
 
 /*

[PATCH 7/9] xfs: remove the unnecessary daddr paramter to _init_block

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Now that all of the callers pass XFS_BUF_DADDR_NULL as the daddr
parameter, we can elide that too.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_bmap.c          |    3 +--
 libxfs/xfs_bmap_btree.c    |    3 +--
 libxfs/xfs_btree.c         |   19 ++++++++++++++++---
 libxfs/xfs_btree.h         |    2 +-
 libxfs/xfs_btree_staging.c |    5 ++---
 5 files changed, 21 insertions(+), 11 deletions(-)


diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index 1c53204e1d5..46551021755 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -638,8 +638,7 @@ xfs_bmap_extents_to_btree(
 	 * Fill in the root.
 	 */
 	block = ifp->if_broot;
-	xfs_btree_init_block(mp, block, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL, 1,
-			1, ip->i_ino);
+	xfs_btree_init_block(mp, block, &xfs_bmbt_ops, 1, 1, ip->i_ino);
 	/*
 	 * Need a cursor.  Can't allocate until bb_level is filled in.
 	 */
diff --git a/libxfs/xfs_bmap_btree.c b/libxfs/xfs_bmap_btree.c
index ea6bd791eff..1dd85d4d41c 100644
--- a/libxfs/xfs_bmap_btree.c
+++ b/libxfs/xfs_bmap_btree.c
@@ -42,8 +42,7 @@ xfs_bmdr_to_bmbt(
 	xfs_bmbt_key_t		*tkp;
 	__be64			*tpp;
 
-	xfs_btree_init_block(mp, rblock, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL,
-			0, 0, ip->i_ino);
+	xfs_btree_init_block(mp, rblock, &xfs_bmbt_ops, 0, 0, ip->i_ino);
 	rblock->bb_level = dblock->bb_level;
 	ASSERT(be16_to_cpu(rblock->bb_level) > 0);
 	rblock->bb_numrecs = dblock->bb_numrecs;
diff --git a/libxfs/xfs_btree.c b/libxfs/xfs_btree.c
index c8bbda80b40..218e96d7976 100644
--- a/libxfs/xfs_btree.c
+++ b/libxfs/xfs_btree.c
@@ -1209,8 +1209,8 @@ xfs_btree_set_sibling(
 	}
 }
 
-void
-xfs_btree_init_block(
+static void
+__xfs_btree_init_block(
 	struct xfs_mount	*mp,
 	struct xfs_btree_block	*buf,
 	const struct xfs_btree_ops *ops,
@@ -1251,6 +1251,19 @@ xfs_btree_init_block(
 	}
 }
 
+void
+xfs_btree_init_block(
+	struct xfs_mount	*mp,
+	struct xfs_btree_block	*block,
+	const struct xfs_btree_ops *ops,
+	__u16			level,
+	__u16			numrecs,
+	__u64			owner)
+{
+	__xfs_btree_init_block(mp, block, ops, XFS_BUF_DADDR_NULL, level,
+			numrecs, owner);
+}
+
 void
 xfs_btree_init_buf(
 	struct xfs_mount		*mp,
@@ -1260,7 +1273,7 @@ xfs_btree_init_buf(
 	__u16				numrecs,
 	__u64				owner)
 {
-	xfs_btree_init_block(mp, XFS_BUF_TO_BLOCK(bp), ops,
+	__xfs_btree_init_block(mp, XFS_BUF_TO_BLOCK(bp), ops,
 			xfs_buf_daddr(bp), level, numrecs, owner);
 }
 
diff --git a/libxfs/xfs_btree.h b/libxfs/xfs_btree.h
index 6a27c34e68c..41000bd6ccc 100644
--- a/libxfs/xfs_btree.h
+++ b/libxfs/xfs_btree.h
@@ -456,7 +456,7 @@ void xfs_btree_init_buf(struct xfs_mount *mp, struct xfs_buf *bp,
 		__u64 owner);
 void xfs_btree_init_block(struct xfs_mount *mp,
 		struct xfs_btree_block *buf, const struct xfs_btree_ops *ops,
-		xfs_daddr_t blkno, __u16 level, __u16 numrecs, __u64 owner);
+		__u16 level, __u16 numrecs, __u64 owner);
 
 /*
  * Common btree core entry points.
diff --git a/libxfs/xfs_btree_staging.c b/libxfs/xfs_btree_staging.c
index c2f39702b7b..ec496915433 100644
--- a/libxfs/xfs_btree_staging.c
+++ b/libxfs/xfs_btree_staging.c
@@ -410,9 +410,8 @@ xfs_btree_bload_prep_block(
 		ifp->if_broot_bytes = (int)new_size;
 
 		/* Initialize it and send it out. */
-		xfs_btree_init_block(cur->bc_mp, ifp->if_broot,
-				cur->bc_ops, XFS_BUF_DADDR_NULL, level,
-				nr_this_block, cur->bc_ino.ip->i_ino);
+		xfs_btree_init_block(cur->bc_mp, ifp->if_broot, cur->bc_ops,
+				level, nr_this_block, cur->bc_ino.ip->i_ino);
 
 		*bpp = NULL;
 		*blockp = ifp->if_broot;

[PATCH 8/9] xfs: set btree block buffer ops in _init_buf

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Set the btree block buffer ops in xfs_btree_init_buf since we already
have access to that information through the btree ops.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfbtree.c   |    1 -
 libxfs/xfs_bmap.c  |    1 -
 libxfs/xfs_btree.c |    1 +
 3 files changed, 1 insertion(+), 2 deletions(-)


diff --git a/libxfs/xfbtree.c b/libxfs/xfbtree.c
index 7310f29a8c2..d76b3d5ea70 100644
--- a/libxfs/xfbtree.c
+++ b/libxfs/xfbtree.c
@@ -401,7 +401,6 @@ xfbtree_init_leaf_block(
 
 	trace_xfbtree_create_root_buf(xfbt, bp);
 
-	bp->b_ops = cfg->btree_ops->buf_ops;
 	xfs_btree_init_buf(mp, bp, cfg->btree_ops, 0, 0, cfg->owner);
 	error = xfs_bwrite(bp);
 	xfs_buf_relse(bp);
diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index 46551021755..9a2cb5662d1 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -681,7 +681,6 @@ xfs_bmap_extents_to_btree(
 	/*
 	 * Fill in the child block.
 	 */
-	abp->b_ops = &xfs_bmbt_buf_ops;
 	ablock = XFS_BUF_TO_BLOCK(abp);
 	xfs_btree_init_buf(mp, abp, &xfs_bmbt_ops, 0, 0, ip->i_ino);
 
diff --git a/libxfs/xfs_btree.c b/libxfs/xfs_btree.c
index 218e96d7976..6705a6d83f3 100644
--- a/libxfs/xfs_btree.c
+++ b/libxfs/xfs_btree.c
@@ -1275,6 +1275,7 @@ xfs_btree_init_buf(
 {
 	__xfs_btree_init_block(mp, XFS_BUF_TO_BLOCK(bp), ops,
 			xfs_buf_daddr(bp), level, numrecs, owner);
+	bp->b_ops = ops->buf_ops;
 }
 
 void

[PATCH 9/9] xfs: remove unnecessary fields in xfbtree_config

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Remove these fields now that we get all the info we need from the btree
ops.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfbtree.c        |    4 ++--
 libxfs/xfs_btree_mem.h  |    9 ---------
 libxfs/xfs_rmap_btree.c |    1 -
 3 files changed, 2 insertions(+), 12 deletions(-)


diff --git a/libxfs/xfbtree.c b/libxfs/xfbtree.c
index d76b3d5ea70..b4762393b3a 100644
--- a/libxfs/xfbtree.c
+++ b/libxfs/xfbtree.c
@@ -370,7 +370,7 @@ xfbtree_rec_bytes(
 {
 	unsigned int			blocklen = xfo_to_b(1);
 
-	if (cfg->flags & XFBTREE_CREATE_LONG_PTRS) {
+	if (cfg->btree_ops->geom_flags & XFS_BTREE_LONG_PTRS) {
 		if (xfs_has_crc(mp))
 			return blocklen - XFS_BTREE_LBLOCK_CRC_LEN;
 
@@ -464,7 +464,7 @@ xfbtree_create(
 		goto err_buftarg;
 
 	/* Set up min/maxrecs for this btree. */
-	if (cfg->flags & XFBTREE_CREATE_LONG_PTRS)
+	if (cfg->btree_ops->geom_flags & XFS_BTREE_LONG_PTRS)
 		keyptr_len += sizeof(__be64);
 	else
 		keyptr_len += sizeof(__be32);
diff --git a/libxfs/xfs_btree_mem.h b/libxfs/xfs_btree_mem.h
index 29f97c50304..1f961f3f554 100644
--- a/libxfs/xfs_btree_mem.h
+++ b/libxfs/xfs_btree_mem.h
@@ -17,17 +17,8 @@ struct xfbtree_config {
 
 	/* Owner of this btree. */
 	unsigned long long		owner;
-
-	/* Btree type number */
-	xfs_btnum_t			btnum;
-
-	/* XFBTREE_CREATE_* flags */
-	unsigned int			flags;
 };
 
-/* btree has long pointers */
-#define XFBTREE_CREATE_LONG_PTRS	(1U << 0)
-
 #ifdef CONFIG_XFS_BTREE_IN_XFILE
 unsigned int xfs_btree_mem_head_nlevels(struct xfs_buf *head_bp);
 
diff --git a/libxfs/xfs_rmap_btree.c b/libxfs/xfs_rmap_btree.c
index f1325586433..e36237bf750 100644
--- a/libxfs/xfs_rmap_btree.c
+++ b/libxfs/xfs_rmap_btree.c
@@ -667,7 +667,6 @@ xfs_rmapbt_mem_create(
 	struct xfbtree_config	cfg = {
 		.btree_ops	= &xfs_rmapbt_mem_ops,
 		.target		= target,
-		.btnum		= XFS_BTNUM_RMAP,
 		.owner		= agno,
 	};
 

[PATCH 1/6] xfs: move lru refs to the btree ops structure

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Move the btree buffer LRU refcount to the btree ops structure so that we
can eliminate the last bc_btnum switch in the generic btree code.  We're
about to create repair-specific btree types, and we don't want that
stuff cluttering up libxfs.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_alloc_btree.c    |    2 ++
 libxfs/xfs_bmap_btree.c     |    1 +
 libxfs/xfs_btree.c          |   24 ++----------------------
 libxfs/xfs_btree.h          |    3 +++
 libxfs/xfs_ialloc_btree.c   |    2 ++
 libxfs/xfs_refcount_btree.c |    1 +
 libxfs/xfs_rmap_btree.c     |    2 ++
 7 files changed, 13 insertions(+), 22 deletions(-)


diff --git a/libxfs/xfs_alloc_btree.c b/libxfs/xfs_alloc_btree.c
index 97d19203550..93faa832e5b 100644
--- a/libxfs/xfs_alloc_btree.c
+++ b/libxfs/xfs_alloc_btree.c
@@ -455,6 +455,7 @@ xfs_allocbt_keys_contiguous(
 const struct xfs_btree_ops xfs_bnobt_ops = {
 	.rec_len		= sizeof(xfs_alloc_rec_t),
 	.key_len		= sizeof(xfs_alloc_key_t),
+	.lru_refs		= XFS_ALLOC_BTREE_REF,
 
 	.dup_cursor		= xfs_allocbt_dup_cursor,
 	.set_root		= xfs_allocbt_set_root,
@@ -478,6 +479,7 @@ const struct xfs_btree_ops xfs_bnobt_ops = {
 const struct xfs_btree_ops xfs_cntbt_ops = {
 	.rec_len		= sizeof(xfs_alloc_rec_t),
 	.key_len		= sizeof(xfs_alloc_key_t),
+	.lru_refs		= XFS_ALLOC_BTREE_REF,
 	.geom_flags		= XFS_BTREE_LASTREC_UPDATE,
 
 	.dup_cursor		= xfs_allocbt_dup_cursor,
diff --git a/libxfs/xfs_bmap_btree.c b/libxfs/xfs_bmap_btree.c
index 1dd85d4d41c..160f7b08ffd 100644
--- a/libxfs/xfs_bmap_btree.c
+++ b/libxfs/xfs_bmap_btree.c
@@ -514,6 +514,7 @@ xfs_bmbt_keys_contiguous(
 const struct xfs_btree_ops xfs_bmbt_ops = {
 	.rec_len		= sizeof(xfs_bmbt_rec_t),
 	.key_len		= sizeof(xfs_bmbt_key_t),
+	.lru_refs		= XFS_BMAP_BTREE_REF,
 	.geom_flags		= XFS_BTREE_LONG_PTRS | XFS_BTREE_ROOT_IN_INODE,
 
 	.dup_cursor		= xfs_bmbt_dup_cursor,
diff --git a/libxfs/xfs_btree.c b/libxfs/xfs_btree.c
index 6705a6d83f3..7cc6379a113 100644
--- a/libxfs/xfs_btree.c
+++ b/libxfs/xfs_btree.c
@@ -1347,32 +1347,12 @@ xfs_btree_buf_to_ptr(
 	}
 }
 
-STATIC void
+static inline void
 xfs_btree_set_refs(
 	struct xfs_btree_cur	*cur,
 	struct xfs_buf		*bp)
 {
-	switch (cur->bc_btnum) {
-	case XFS_BTNUM_BNO:
-	case XFS_BTNUM_CNT:
-		xfs_buf_set_ref(bp, XFS_ALLOC_BTREE_REF);
-		break;
-	case XFS_BTNUM_INO:
-	case XFS_BTNUM_FINO:
-		xfs_buf_set_ref(bp, XFS_INO_BTREE_REF);
-		break;
-	case XFS_BTNUM_BMAP:
-		xfs_buf_set_ref(bp, XFS_BMAP_BTREE_REF);
-		break;
-	case XFS_BTNUM_RMAP:
-		xfs_buf_set_ref(bp, XFS_RMAP_BTREE_REF);
-		break;
-	case XFS_BTNUM_REFC:
-		xfs_buf_set_ref(bp, XFS_REFC_BTREE_REF);
-		break;
-	default:
-		ASSERT(0);
-	}
+	xfs_buf_set_ref(bp, cur->bc_ops->lru_refs);
 }
 
 int
diff --git a/libxfs/xfs_btree.h b/libxfs/xfs_btree.h
index 41000bd6ccc..edbcd4f0e98 100644
--- a/libxfs/xfs_btree.h
+++ b/libxfs/xfs_btree.h
@@ -120,6 +120,9 @@ struct xfs_btree_ops {
 	/* XFS_BTREE_* flags that determine the geometry of the btree */
 	unsigned int	geom_flags;
 
+	/* LRU refcount to set on each btree buffer created */
+	int	lru_refs;
+
 	/* cursor operations */
 	struct xfs_btree_cur *(*dup_cursor)(struct xfs_btree_cur *);
 	void	(*update_cursor)(struct xfs_btree_cur *src,
diff --git a/libxfs/xfs_ialloc_btree.c b/libxfs/xfs_ialloc_btree.c
index 52cc00e4ff1..4275244b15c 100644
--- a/libxfs/xfs_ialloc_btree.c
+++ b/libxfs/xfs_ialloc_btree.c
@@ -400,6 +400,7 @@ xfs_inobt_keys_contiguous(
 const struct xfs_btree_ops xfs_inobt_ops = {
 	.rec_len		= sizeof(xfs_inobt_rec_t),
 	.key_len		= sizeof(xfs_inobt_key_t),
+	.lru_refs		= XFS_INO_BTREE_REF,
 
 	.dup_cursor		= xfs_inobt_dup_cursor,
 	.set_root		= xfs_inobt_set_root,
@@ -422,6 +423,7 @@ const struct xfs_btree_ops xfs_inobt_ops = {
 const struct xfs_btree_ops xfs_finobt_ops = {
 	.rec_len		= sizeof(xfs_inobt_rec_t),
 	.key_len		= sizeof(xfs_inobt_key_t),
+	.lru_refs		= XFS_INO_BTREE_REF,
 
 	.dup_cursor		= xfs_inobt_dup_cursor,
 	.set_root		= xfs_finobt_set_root,
diff --git a/libxfs/xfs_refcount_btree.c b/libxfs/xfs_refcount_btree.c
index 2f91c7b62ef..ab8925051a9 100644
--- a/libxfs/xfs_refcount_btree.c
+++ b/libxfs/xfs_refcount_btree.c
@@ -319,6 +319,7 @@ xfs_refcountbt_keys_contiguous(
 const struct xfs_btree_ops xfs_refcountbt_ops = {
 	.rec_len		= sizeof(struct xfs_refcount_rec),
 	.key_len		= sizeof(struct xfs_refcount_key),
+	.lru_refs		= XFS_REFC_BTREE_REF,
 
 	.dup_cursor		= xfs_refcountbt_dup_cursor,
 	.set_root		= xfs_refcountbt_set_root,
diff --git a/libxfs/xfs_rmap_btree.c b/libxfs/xfs_rmap_btree.c
index e36237bf750..a378bd5daf8 100644
--- a/libxfs/xfs_rmap_btree.c
+++ b/libxfs/xfs_rmap_btree.c
@@ -487,6 +487,7 @@ xfs_rmapbt_keys_contiguous(
 const struct xfs_btree_ops xfs_rmapbt_ops = {
 	.rec_len		= sizeof(struct xfs_rmap_rec),
 	.key_len		= 2 * sizeof(struct xfs_rmap_key),
+	.lru_refs		= XFS_RMAP_BTREE_REF,
 	.geom_flags		= XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING,
 
 	.dup_cursor		= xfs_rmapbt_dup_cursor,
@@ -611,6 +612,7 @@ static const struct xfs_buf_ops xfs_rmapbt_mem_buf_ops = {
 static const struct xfs_btree_ops xfs_rmapbt_mem_ops = {
 	.rec_len		= sizeof(struct xfs_rmap_rec),
 	.key_len		= 2 * sizeof(struct xfs_rmap_key),
+	.lru_refs		= XFS_RMAP_BTREE_REF,
 	.geom_flags		= XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING |
 				  XFS_BTREE_IN_XFILE,
 

[PATCH 2/6] xfs: define an in-memory btree for storing refcount bag info during repairs

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a new in-memory btree type so that we can store refcount bag info
in a much more memory-efficient format.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_btree.h |    1 +
 libxfs/xfs_types.h |    6 ++++--
 2 files changed, 5 insertions(+), 2 deletions(-)


diff --git a/libxfs/xfs_btree.h b/libxfs/xfs_btree.h
index edbcd4f0e98..339b5561e5b 100644
--- a/libxfs/xfs_btree.h
+++ b/libxfs/xfs_btree.h
@@ -62,6 +62,7 @@ union xfs_btree_rec {
 #define	XFS_BTNUM_FINO	((xfs_btnum_t)XFS_BTNUM_FINOi)
 #define	XFS_BTNUM_RMAP	((xfs_btnum_t)XFS_BTNUM_RMAPi)
 #define	XFS_BTNUM_REFC	((xfs_btnum_t)XFS_BTNUM_REFCi)
+#define	XFS_BTNUM_RCBAG	((xfs_btnum_t)XFS_BTNUM_RCBAGi)
 
 struct xfs_btree_ops;
 uint32_t xfs_btree_magic(struct xfs_mount *mp, const struct xfs_btree_ops *ops);
diff --git a/libxfs/xfs_types.h b/libxfs/xfs_types.h
index 035bf703d71..5556615a2ff 100644
--- a/libxfs/xfs_types.h
+++ b/libxfs/xfs_types.h
@@ -121,7 +121,8 @@ typedef enum {
  */
 typedef enum {
 	XFS_BTNUM_BNOi, XFS_BTNUM_CNTi, XFS_BTNUM_RMAPi, XFS_BTNUM_BMAPi,
-	XFS_BTNUM_INOi, XFS_BTNUM_FINOi, XFS_BTNUM_REFCi, XFS_BTNUM_MAX
+	XFS_BTNUM_INOi, XFS_BTNUM_FINOi, XFS_BTNUM_REFCi, XFS_BTNUM_RCBAGi,
+	XFS_BTNUM_MAX
 } xfs_btnum_t;
 
 #define XFS_BTNUM_STRINGS \
@@ -131,7 +132,8 @@ typedef enum {
 	{ XFS_BTNUM_BMAPi,	"bmbt" }, \
 	{ XFS_BTNUM_INOi,	"inobt" }, \
 	{ XFS_BTNUM_FINOi,	"finobt" }, \
-	{ XFS_BTNUM_REFCi,	"refcbt" }
+	{ XFS_BTNUM_REFCi,	"refcbt" }, \
+	{ XFS_BTNUM_RCBAGi,	"rcbagbt" }
 
 struct xfs_name {
 	const unsigned char	*name;

[PATCH 3/6] xfs_repair: define an in-memory btree for storing refcount bag info

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a new in-memory btree type so that we can store refcount bag info
in a much more memory-efficient format.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/libxfs_api_defs.h |    3 
 repair/Makefile          |    2 
 repair/rcbag_btree.c     |  335 ++++++++++++++++++++++++++++++++++++++++++++++
 repair/rcbag_btree.h     |   71 ++++++++++
 4 files changed, 411 insertions(+)
 create mode 100644 repair/rcbag_btree.c
 create mode 100644 repair/rcbag_btree.h


diff --git a/libxfs/libxfs_api_defs.h b/libxfs/libxfs_api_defs.h
index 91165d77bc7..97945f995fc 100644
--- a/libxfs/libxfs_api_defs.h
+++ b/libxfs/libxfs_api_defs.h
@@ -59,6 +59,7 @@
 
 #define xfs_btree_bload			libxfs_btree_bload
 #define xfs_btree_bload_compute_geometry libxfs_btree_bload_compute_geometry
+#define xfs_btree_calc_size		libxfs_btree_calc_size
 #define xfs_btree_decrement		libxfs_btree_decrement
 #define xfs_btree_del_cursor		libxfs_btree_del_cursor
 #define xfs_btree_get_block		libxfs_btree_get_block
@@ -66,8 +67,10 @@
 #define xfs_btree_has_more_records	libxfs_btree_has_more_records
 #define xfs_btree_increment		libxfs_btree_increment
 #define xfs_btree_init_block		libxfs_btree_init_block
+#define xfs_btree_mem_head_nlevels	libxfs_btree_mem_head_nlevels
 #define xfs_btree_mem_head_read_buf	libxfs_btree_mem_head_read_buf
 #define xfs_btree_rec_addr		libxfs_btree_rec_addr
+#define xfs_btree_space_to_height	libxfs_btree_space_to_height
 #define xfs_btree_visit_blocks		libxfs_btree_visit_blocks
 #define xfs_buf_delwri_submit		libxfs_buf_delwri_submit
 #define xfs_buf_get			libxfs_buf_get
diff --git a/repair/Makefile b/repair/Makefile
index e5014deb0ce..5ea8d9618e7 100644
--- a/repair/Makefile
+++ b/repair/Makefile
@@ -28,6 +28,7 @@ HFILES = \
 	progress.h \
 	protos.h \
 	quotacheck.h \
+	rcbag_btree.h \
 	rmap.h \
 	rt.h \
 	scan.h \
@@ -64,6 +65,7 @@ CFILES = \
 	prefetch.c \
 	progress.c \
 	quotacheck.c \
+	rcbag_btree.c \
 	rmap.c \
 	rt.c \
 	sb.c \
diff --git a/repair/rcbag_btree.c b/repair/rcbag_btree.c
new file mode 100644
index 00000000000..0a80852ced3
--- /dev/null
+++ b/repair/rcbag_btree.c
@@ -0,0 +1,335 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2022-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "libxfs.h"
+#include "btree.h"
+#include "err_protos.h"
+#include "libxlog.h"
+#include "incore.h"
+#include "globals.h"
+#include "dinode.h"
+#include "slab.h"
+#include "libfrog/bitmap.h"
+#include "libxfs/xfile.h"
+#include "libxfs/xfbtree.h"
+#include "libxfs/xfs_btree_mem.h"
+#include "rcbag_btree.h"
+
+static struct kmem_cache	*rcbagbt_cur_cache;
+
+STATIC void
+rcbagbt_init_key_from_rec(
+	union xfs_btree_key		*key,
+	const union xfs_btree_rec	*rec)
+{
+	struct rcbag_key	*bag_key = (struct rcbag_key *)key;
+	const struct rcbag_rec	*bag_rec = (const struct rcbag_rec *)rec;
+
+	BUILD_BUG_ON(sizeof(struct rcbag_key) > sizeof(union xfs_btree_key));
+	BUILD_BUG_ON(sizeof(struct rcbag_rec) > sizeof(union xfs_btree_rec));
+
+	bag_key->rbg_startblock = bag_rec->rbg_startblock;
+	bag_key->rbg_blockcount = bag_rec->rbg_blockcount;
+	bag_key->rbg_ino = bag_rec->rbg_ino;
+}
+
+STATIC void
+rcbagbt_init_rec_from_cur(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_rec	*rec)
+{
+	struct rcbag_rec	*bag_rec = (struct rcbag_rec *)rec;
+	struct rcbag_rec	*bag_irec = (struct rcbag_rec *)&cur->bc_rec;
+
+	bag_rec->rbg_startblock = bag_irec->rbg_startblock;
+	bag_rec->rbg_blockcount = bag_irec->rbg_blockcount;
+	bag_rec->rbg_ino = bag_irec->rbg_ino;
+	bag_rec->rbg_refcount = bag_irec->rbg_refcount;
+}
+
+STATIC int64_t
+rcbagbt_key_diff(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_key	*key)
+{
+	struct rcbag_rec		*rec = (struct rcbag_rec *)&cur->bc_rec;
+	const struct rcbag_key		*kp = (const struct rcbag_key *)key;
+
+	if (kp->rbg_startblock > rec->rbg_startblock)
+		return 1;
+	if (kp->rbg_startblock < rec->rbg_startblock)
+		return -1;
+
+	if (kp->rbg_blockcount > rec->rbg_blockcount)
+		return 1;
+	if (kp->rbg_blockcount < rec->rbg_blockcount)
+		return -1;
+
+	if (kp->rbg_ino > rec->rbg_ino)
+		return 1;
+	if (kp->rbg_ino < rec->rbg_ino)
+		return -1;
+
+	return 0;
+}
+
+STATIC int64_t
+rcbagbt_diff_two_keys(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_key	*k1,
+	const union xfs_btree_key	*k2,
+	const union xfs_btree_key	*mask)
+{
+	const struct rcbag_key		*kp1 = (const struct rcbag_key *)k1;
+	const struct rcbag_key		*kp2 = (const struct rcbag_key *)k2;
+
+	ASSERT(mask == NULL);
+
+	if (kp1->rbg_startblock > kp2->rbg_startblock)
+		return 1;
+	if (kp1->rbg_startblock < kp2->rbg_startblock)
+		return -1;
+
+	if (kp1->rbg_blockcount > kp2->rbg_blockcount)
+		return 1;
+	if (kp1->rbg_blockcount < kp2->rbg_blockcount)
+		return -1;
+
+	if (kp1->rbg_ino > kp2->rbg_ino)
+		return 1;
+	if (kp1->rbg_ino < kp2->rbg_ino)
+		return -1;
+
+	return 0;
+}
+
+STATIC int
+rcbagbt_keys_inorder(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_key	*k1,
+	const union xfs_btree_key	*k2)
+{
+	const struct rcbag_key		*kp1 = (const struct rcbag_key *)k1;
+	const struct rcbag_key		*kp2 = (const struct rcbag_key *)k2;
+
+	if (kp1->rbg_startblock > kp2->rbg_startblock)
+		return 0;
+	if (kp1->rbg_startblock < kp2->rbg_startblock)
+		return 1;
+
+	if (kp1->rbg_blockcount > kp2->rbg_blockcount)
+		return 0;
+	if (kp1->rbg_blockcount < kp2->rbg_blockcount)
+		return 1;
+
+	if (kp1->rbg_ino > kp2->rbg_ino)
+		return 0;
+	if (kp1->rbg_ino < kp2->rbg_ino)
+		return 1;
+
+	return 0;
+}
+
+STATIC int
+rcbagbt_recs_inorder(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_rec	*r1,
+	const union xfs_btree_rec	*r2)
+{
+	const struct rcbag_rec		*rp1 = (const struct rcbag_rec *)r1;
+	const struct rcbag_rec		*rp2 = (const struct rcbag_rec *)r2;
+
+	if (rp1->rbg_startblock > rp2->rbg_startblock)
+		return 0;
+	if (rp1->rbg_startblock < rp2->rbg_startblock)
+		return 1;
+
+	if (rp1->rbg_blockcount > rp2->rbg_blockcount)
+		return 0;
+	if (rp1->rbg_blockcount < rp2->rbg_blockcount)
+		return 1;
+
+	if (rp1->rbg_ino > rp2->rbg_ino)
+		return 0;
+	if (rp1->rbg_ino < rp2->rbg_ino)
+		return 1;
+
+	return 0;
+}
+
+static xfs_failaddr_t
+rcbagbt_verify(
+	struct xfs_buf		*bp)
+{
+	struct xfs_mount	*mp = bp->b_mount;
+	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
+	xfs_failaddr_t		fa;
+	unsigned int		level;
+
+	if (!xfs_verify_magic(bp, block->bb_magic))
+		return __this_address;
+
+	fa = xfs_btree_lblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN);
+	if (fa)
+		return fa;
+
+	level = be16_to_cpu(block->bb_level);
+	if (level >= rcbagbt_maxlevels_possible())
+		return __this_address;
+
+	return xfbtree_lblock_verify(bp,
+			rcbagbt_maxrecs(mp, xfo_to_b(1), level == 0));
+}
+
+static void
+rcbagbt_rw_verify(
+	struct xfs_buf	*bp)
+{
+	xfs_failaddr_t	fa = rcbagbt_verify(bp);
+
+	if (fa)
+		do_error(_("refcount bag btree block 0x%llx corrupted at %p\n"),
+				(unsigned long long)xfs_buf_daddr(bp), fa);
+}
+
+/* skip crc checks on in-memory btrees to save time */
+static const struct xfs_buf_ops rcbagbt_mem_buf_ops = {
+	.name			= "rcbagbt_mem",
+	.magic			= { 0, cpu_to_be32(RCBAG_MAGIC) },
+	.verify_read		= rcbagbt_rw_verify,
+	.verify_write		= rcbagbt_rw_verify,
+	.verify_struct		= rcbagbt_verify,
+};
+
+static const struct xfs_btree_ops rcbagbt_mem_ops = {
+	.rec_len		= sizeof(struct rcbag_rec),
+	.key_len		= sizeof(struct rcbag_key),
+	.geom_flags		= XFS_BTREE_CRC_BLOCKS | XFS_BTREE_LONG_PTRS |
+				  XFS_BTREE_IN_XFILE,
+
+	.dup_cursor		= xfbtree_dup_cursor,
+	.set_root		= xfbtree_set_root,
+	.alloc_block		= xfbtree_alloc_block,
+	.free_block		= xfbtree_free_block,
+	.get_minrecs		= xfbtree_get_minrecs,
+	.get_maxrecs		= xfbtree_get_maxrecs,
+	.init_key_from_rec	= rcbagbt_init_key_from_rec,
+	.init_rec_from_cur	= rcbagbt_init_rec_from_cur,
+	.init_ptr_from_cur	= xfbtree_init_ptr_from_cur,
+	.key_diff		= rcbagbt_key_diff,
+	.buf_ops		= &rcbagbt_mem_buf_ops,
+	.diff_two_keys		= rcbagbt_diff_two_keys,
+	.keys_inorder		= rcbagbt_keys_inorder,
+	.recs_inorder		= rcbagbt_recs_inorder,
+};
+
+/* Create a cursor for an in-memory btree. */
+struct xfs_btree_cur *
+rcbagbt_mem_cursor(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	struct xfs_buf		*head_bp,
+	struct xfbtree		*xfbtree)
+{
+	struct xfs_btree_cur	*cur;
+
+	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_RCBAG, &rcbagbt_mem_ops,
+			rcbagbt_maxlevels_possible(), rcbagbt_cur_cache);
+
+	cur->bc_mem.xfbtree = xfbtree;
+	cur->bc_mem.head_bp = head_bp;
+	cur->bc_nlevels = libxfs_btree_mem_head_nlevels(head_bp);
+	return cur;
+}
+
+/* Create an in-memory refcount bag btree. */
+int
+rcbagbt_mem_create(
+	struct xfs_mount	*mp,
+	struct xfs_buftarg	*target,
+	struct xfbtree		**xfbtreep)
+{
+	struct xfbtree_config	cfg = {
+		.btree_ops	= &rcbagbt_mem_ops,
+		.target		= target,
+	};
+
+	return -xfbtree_create(mp, &cfg, xfbtreep);
+}
+
+/* Calculate number of records in a refcount bag btree block. */
+static inline unsigned int
+rcbagbt_block_maxrecs(
+	unsigned int		blocklen,
+	bool			leaf)
+{
+	if (leaf)
+		return blocklen / sizeof(struct rcbag_rec);
+	return blocklen /
+		(sizeof(struct rcbag_key) + sizeof(rcbag_ptr_t));
+}
+
+/*
+ * Calculate number of records in an refcount bag btree block.
+ */
+unsigned int
+rcbagbt_maxrecs(
+	struct xfs_mount	*mp,
+	unsigned int		blocklen,
+	bool			leaf)
+{
+	blocklen -= RCBAG_BLOCK_LEN;
+	return rcbagbt_block_maxrecs(blocklen, leaf);
+}
+
+#define RCBAGBT_INIT_MINRECS(minrecs) \
+	do { \
+		unsigned int		blocklen; \
+\
+		blocklen = getpagesize() - XFS_BTREE_LBLOCK_CRC_LEN; \
+\
+		minrecs[0] = rcbagbt_block_maxrecs(blocklen, true) / 2; \
+		minrecs[1] = rcbagbt_block_maxrecs(blocklen, false) / 2; \
+	} while (0)
+
+/* Compute the max possible height for refcount bag btrees. */
+unsigned int
+rcbagbt_maxlevels_possible(void)
+{
+	unsigned int		minrecs[2];
+
+	RCBAGBT_INIT_MINRECS(minrecs);
+	return libxfs_btree_space_to_height(minrecs, ULLONG_MAX);
+}
+
+/* Calculate the refcount bag btree size for some records. */
+unsigned long long
+rcbagbt_calc_size(
+	unsigned long long	nr_records)
+{
+	unsigned int		minrecs[2];
+
+	RCBAGBT_INIT_MINRECS(minrecs);
+	return libxfs_btree_calc_size(minrecs, nr_records);
+}
+
+int __init
+rcbagbt_init_cur_cache(void)
+{
+	rcbagbt_cur_cache = kmem_cache_create("rcbagbt_cur",
+			xfs_btree_cur_sizeof(rcbagbt_maxlevels_possible()),
+			0, 0, NULL);
+
+	if (!rcbagbt_cur_cache)
+		return ENOMEM;
+	return 0;
+}
+
+void
+rcbagbt_destroy_cur_cache(void)
+{
+	kmem_cache_destroy(rcbagbt_cur_cache);
+	rcbagbt_cur_cache = NULL;
+}
diff --git a/repair/rcbag_btree.h b/repair/rcbag_btree.h
new file mode 100644
index 00000000000..14a09a3f1a1
--- /dev/null
+++ b/repair/rcbag_btree.h
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2022-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __RCBAG_BTREE_H__
+#define __RCBAG_BTREE_H__
+
+struct xfs_buf;
+struct xfs_btree_cur;
+struct xfs_mount;
+
+#define RCBAG_MAGIC	0x74826671	/* 'JRBG' */
+
+struct rcbag_key {
+	uint32_t	rbg_startblock;
+	uint32_t	rbg_blockcount;
+	uint64_t	rbg_ino;
+};
+
+struct rcbag_rec {
+	uint32_t	rbg_startblock;
+	uint32_t	rbg_blockcount;
+	uint64_t	rbg_ino;
+	uint64_t	rbg_refcount;
+};
+
+typedef __be64 rcbag_ptr_t;
+
+/* reflinks only exist on crc enabled filesystems */
+#define RCBAG_BLOCK_LEN	XFS_BTREE_LBLOCK_CRC_LEN
+
+/*
+ * Record, key, and pointer address macros for btree blocks.
+ *
+ * (note that some of these may appear unused, but they are used in userspace)
+ */
+#define RCBAG_REC_ADDR(block, index) \
+	((struct rcbag_rec *) \
+		((char *)(block) + RCBAG_BLOCK_LEN + \
+		 (((index) - 1) * sizeof(struct rcbag_rec))))
+
+#define RCBAG_KEY_ADDR(block, index) \
+	((struct rcbag_key *) \
+		((char *)(block) + RCBAG_BLOCK_LEN + \
+		 ((index) - 1) * sizeof(struct rcbag_key)))
+
+#define RCBAG_PTR_ADDR(block, index, maxrecs) \
+	((rcbag_ptr_t *) \
+		((char *)(block) + RCBAG_BLOCK_LEN + \
+		 (maxrecs) * sizeof(struct rcbag_key) + \
+		 ((index) - 1) * sizeof(rcbag_ptr_t)))
+
+unsigned int rcbagbt_maxrecs(struct xfs_mount *mp, unsigned int blocklen,
+		bool leaf);
+
+unsigned long long rcbagbt_calc_size(unsigned long long nr_records);
+
+unsigned int rcbagbt_maxlevels_possible(void);
+
+int __init rcbagbt_init_cur_cache(void);
+void rcbagbt_destroy_cur_cache(void);
+
+struct xfbtree;
+struct xfs_btree_cur *rcbagbt_mem_cursor(struct xfs_mount *mp,
+		struct xfs_trans *tp, struct xfs_buf *head_bp,
+		struct xfbtree *xfbtree);
+int rcbagbt_mem_create(struct xfs_mount *mp, struct xfs_buftarg *target,
+		struct xfbtree **xfbtreep);
+
+#endif /* __RCBAG_BTREE_H__ */

[PATCH 4/6] xfs_repair: create refcount bag

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a bag structure for refcount information that uses the refcount
bag btree defined in the previous patch.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/libxfs_api_defs.h |    5 +
 repair/Makefile          |    2 
 repair/rcbag.c           |  396 ++++++++++++++++++++++++++++++++++++++++++++++
 repair/rcbag.h           |   33 ++++
 repair/rcbag_btree.c     |   59 +++++++
 repair/rcbag_btree.h     |    7 +
 6 files changed, 502 insertions(+)
 create mode 100644 repair/rcbag.c
 create mode 100644 repair/rcbag.h


diff --git a/libxfs/libxfs_api_defs.h b/libxfs/libxfs_api_defs.h
index 97945f995fc..2a8e09db0bf 100644
--- a/libxfs/libxfs_api_defs.h
+++ b/libxfs/libxfs_api_defs.h
@@ -62,14 +62,19 @@
 #define xfs_btree_calc_size		libxfs_btree_calc_size
 #define xfs_btree_decrement		libxfs_btree_decrement
 #define xfs_btree_del_cursor		libxfs_btree_del_cursor
+#define xfs_btree_delete		libxfs_btree_delete
 #define xfs_btree_get_block		libxfs_btree_get_block
+#define xfs_btree_get_rec		libxfs_btree_get_rec
 #define xfs_btree_goto_left_edge	libxfs_btree_goto_left_edge
 #define xfs_btree_has_more_records	libxfs_btree_has_more_records
 #define xfs_btree_increment		libxfs_btree_increment
 #define xfs_btree_init_block		libxfs_btree_init_block
+#define xfs_btree_insert		libxfs_btree_insert
+#define xfs_btree_lookup		libxfs_btree_lookup
 #define xfs_btree_mem_head_nlevels	libxfs_btree_mem_head_nlevels
 #define xfs_btree_mem_head_read_buf	libxfs_btree_mem_head_read_buf
 #define xfs_btree_rec_addr		libxfs_btree_rec_addr
+#define xfs_btree_update		libxfs_btree_update
 #define xfs_btree_space_to_height	libxfs_btree_space_to_height
 #define xfs_btree_visit_blocks		libxfs_btree_visit_blocks
 #define xfs_buf_delwri_submit		libxfs_buf_delwri_submit
diff --git a/repair/Makefile b/repair/Makefile
index 5ea8d9618e7..250c86cca2d 100644
--- a/repair/Makefile
+++ b/repair/Makefile
@@ -29,6 +29,7 @@ HFILES = \
 	protos.h \
 	quotacheck.h \
 	rcbag_btree.h \
+	rcbag.h \
 	rmap.h \
 	rt.h \
 	scan.h \
@@ -66,6 +67,7 @@ CFILES = \
 	progress.c \
 	quotacheck.c \
 	rcbag_btree.c \
+	rcbag.c \
 	rmap.c \
 	rt.c \
 	sb.c \
diff --git a/repair/rcbag.c b/repair/rcbag.c
new file mode 100644
index 00000000000..5faa0dc8029
--- /dev/null
+++ b/repair/rcbag.c
@@ -0,0 +1,396 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2022-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "libxfs.h"
+#include "btree.h"
+#include "err_protos.h"
+#include "libxlog.h"
+#include "incore.h"
+#include "globals.h"
+#include "dinode.h"
+#include "slab.h"
+#include "libfrog/bitmap.h"
+#include "libfrog/platform.h"
+#include "libxfs/xfile.h"
+#include "libxfs/xfbtree.h"
+#include "libxfs/xfs_btree_mem.h"
+#include "rcbag_btree.h"
+#include "rcbag.h"
+
+struct rcbag {
+	struct xfs_mount	*mp;
+	struct xfbtree		*xfbtree;
+	uint64_t		nr_items;
+};
+
+int
+rcbag_init(
+	struct xfs_mount	*mp,
+	uint64_t		max_rmaps,
+	struct rcbag		**bagp)
+{
+	struct xfs_buftarg	*target;
+	struct rcbag		*bag;
+	char			*descr;
+	unsigned long long	maxbytes;
+	int			error;
+
+	bag = malloc(sizeof(struct rcbag));
+	if (!bag)
+		return ENOMEM;
+
+	bag->nr_items = 0;
+	bag->mp = mp;
+
+	/* Need to save space for the head block */
+	maxbytes = (1 + rcbagbt_calc_size(max_rmaps)) * getpagesize();
+	descr = kasprintf("xfs_repair (%s): refcount bag", mp->m_fsname);
+	error = -xfile_alloc_buftarg(mp, descr, maxbytes, &target);
+	kfree(descr);
+	if (error)
+		goto out_bag;
+
+	error = rcbagbt_mem_create(mp, target, &bag->xfbtree);
+	if (error)
+		goto out_buftarg;
+
+	*bagp = bag;
+	return 0;
+
+out_buftarg:
+	xfile_free_buftarg(target);
+out_bag:
+	free(bag);
+	return error;
+}
+
+void
+rcbag_free(
+	struct rcbag		**bagp)
+{
+	struct rcbag		*bag = *bagp;
+	struct xfs_buftarg	*target = bag->xfbtree->target;
+
+	xfbtree_destroy(bag->xfbtree);
+	xfile_free_buftarg(target);
+
+	free(bag);
+	*bagp = NULL;
+}
+
+/* Track an rmap in the refcount bag. */
+void
+rcbag_add(
+	struct rcbag			*bag,
+	const struct xfs_rmap_irec	*rmap)
+{
+	struct rcbag_rec		bagrec;
+	struct xfs_mount		*mp = bag->mp;
+	struct xfs_trans		*tp;
+	struct xfs_buf			*head_bp;
+	struct xfs_btree_cur		*cur;
+	int				has;
+	int				error;
+
+	error = -libxfs_trans_alloc_empty(mp, &tp);
+	if (error)
+		do_error(_("allocating tx for refcount bag update\n"));
+
+	error = -xfbtree_head_read_buf(bag->xfbtree, tp, &head_bp);
+	if (error)
+		do_error(_("reading refcount bag header\n"));
+
+	cur = rcbagbt_mem_cursor(mp, tp, head_bp, bag->xfbtree);
+	error = rcbagbt_lookup_eq(cur, rmap, &has);
+	if (error)
+		do_error(_("looking up refcount bag records\n"));
+
+	if (has) {
+		error = rcbagbt_get_rec(cur, &bagrec, &has);
+		if (error || !has)
+			do_error(_("reading refcount bag records\n"));
+
+		bagrec.rbg_refcount++;
+		error = rcbagbt_update(cur, &bagrec);
+		if (error)
+			do_error(_("updating refcount bag record\n"));
+	} else {
+		bagrec.rbg_startblock = rmap->rm_startblock;
+		bagrec.rbg_blockcount = rmap->rm_blockcount;
+		bagrec.rbg_ino = rmap->rm_owner;
+		bagrec.rbg_refcount = 1;
+
+		error = rcbagbt_insert(cur, &bagrec, &has);
+		if (error || !has)
+			do_error(_("adding refcount bag record, err %d\n"),
+					error);
+	}
+
+	libxfs_btree_del_cursor(cur, error);
+	libxfs_trans_brelse(tp, head_bp);
+
+	error = -xfbtree_trans_commit(bag->xfbtree, tp);
+	if (error)
+		do_error(_("committing refcount bag record\n"));
+
+	libxfs_trans_cancel(tp);
+	bag->nr_items++;
+}
+
+uint64_t
+rcbag_count(
+	const struct rcbag	*rcbag)
+{
+	return rcbag->nr_items;
+}
+
+#define BAGREC_NEXT(r)	((r)->rbg_startblock + (r)->rbg_blockcount)
+
+/*
+ * Find the next block where the refcount changes, given the next rmap we
+ * looked at and the ones we're already tracking.
+ */
+void
+rcbag_next_edge(
+	struct rcbag			*bag,
+	const struct xfs_rmap_irec	*next_rmap,
+	bool				next_valid,
+	uint32_t			*next_bnop)
+{
+	struct rcbag_rec		bagrec;
+	struct xfs_mount		*mp = bag->mp;
+	struct xfs_buf			*head_bp;
+	struct xfs_btree_cur		*cur;
+	uint32_t			next_bno = NULLAGBLOCK;
+	int				has;
+	int				error;
+
+	if (next_valid)
+		next_bno = next_rmap->rm_startblock;
+
+	error = -xfbtree_head_read_buf(bag->xfbtree, NULL, &head_bp);
+	if (error)
+		do_error(_("reading refcount bag header\n"));
+
+	cur = rcbagbt_mem_cursor(mp, NULL, head_bp, bag->xfbtree);
+	error = -libxfs_btree_goto_left_edge(cur);
+	if (error)
+		do_error(_("seeking refcount bag btree cursor\n"));
+
+	while (true) {
+		error = -libxfs_btree_increment(cur, 0, &has);
+		if (error)
+			do_error(_("incrementing refcount bag btree cursor\n"));
+		if (!has)
+			break;
+
+		error = rcbagbt_get_rec(cur, &bagrec, &has);
+		if (error)
+			do_error(_("reading refcount bag btree record\n"));
+		if (!has)
+			do_error(_("refcount bag btree record disappeared?\n"));
+
+		next_bno = min(next_bno, BAGREC_NEXT(&bagrec));
+	}
+
+	/*
+	 * We should have found /something/ because either next_rrm is the next
+	 * interesting rmap to look at after emitting this refcount extent, or
+	 * there are other rmaps in rmap_bag contributing to the current
+	 * sharing count.  But if something is seriously wrong, bail out.
+	 */
+	if (next_bno == NULLAGBLOCK)
+		do_error(_("next refcount bag edge not found?\n"));
+
+	*next_bnop = next_bno;
+
+	libxfs_btree_del_cursor(cur, error);
+	libxfs_trans_brelse(NULL, head_bp);
+}
+
+/* Pop all refcount bag records that end at next_bno */
+void
+rcbag_remove_ending_at(
+	struct rcbag		*bag,
+	uint32_t		next_bno)
+{
+	struct rcbag_rec	bagrec;
+	struct xfs_mount	*mp = bag->mp;
+	struct xfs_trans	*tp;
+	struct xfs_buf		*head_bp;
+	struct xfs_btree_cur	*cur;
+	int			has;
+	int			error;
+
+	error = -libxfs_trans_alloc_empty(mp, &tp);
+	if (error)
+		do_error(_("allocating tx for refcount bag update\n"));
+
+	error = -xfbtree_head_read_buf(bag->xfbtree, tp, &head_bp);
+	if (error)
+		do_error(_("reading refcount bag header\n"));
+
+	/* go to the right edge of the tree */
+	cur = rcbagbt_mem_cursor(mp, tp, head_bp, bag->xfbtree);
+	memset(&cur->bc_rec, 0xFF, sizeof(cur->bc_rec));
+	error = -libxfs_btree_lookup(cur, XFS_LOOKUP_GE, &has);
+	if (error)
+		do_error(_("seeking refcount bag btree cursor\n"));
+
+	while (true) {
+		error = -libxfs_btree_decrement(cur, 0, &has);
+		if (error)
+			do_error(_("decrementing refcount bag btree cursor\n"));
+		if (!has)
+			break;
+
+		error = rcbagbt_get_rec(cur, &bagrec, &has);
+		if (error)
+			do_error(_("reading refcount bag btree record\n"));
+		if (!has)
+			do_error(_("refcount bag btree record disappeared?\n"));
+
+		if (BAGREC_NEXT(&bagrec) != next_bno)
+			continue;
+
+		error = -libxfs_btree_delete(cur, &has);
+		if (error)
+			do_error(_("deleting refcount bag btree record, err %d\n"),
+					error);
+		if (!has)
+			do_error(_("couldn't delete refcount bag record?\n"));
+
+		bag->nr_items -= bagrec.rbg_refcount;
+	}
+
+	libxfs_btree_del_cursor(cur, error);
+	libxfs_trans_brelse(tp, head_bp);
+
+	error = -xfbtree_trans_commit(bag->xfbtree, tp);
+	if (error)
+		do_error(_("committing refcount bag deletions\n"));
+
+	libxfs_trans_cancel(tp);
+}
+
+/* Prepare to iterate the shared inodes tracked by the refcount bag. */
+void
+rcbag_ino_iter_start(
+	struct rcbag		*bag,
+	struct rcbag_iter	*iter)
+{
+	struct xfs_mount	*mp = bag->mp;
+	int			error;
+
+	memset(iter, 0, sizeof(struct rcbag_iter));
+
+	if (bag->nr_items < 2)
+		return;
+
+	error = -xfbtree_head_read_buf(bag->xfbtree, NULL, &iter->head_bp);
+	if (error)
+		do_error(_("reading refcount bag header\n"));
+
+	iter->cur = rcbagbt_mem_cursor(mp, NULL, iter->head_bp, bag->xfbtree);
+	error = -libxfs_btree_goto_left_edge(iter->cur);
+	if (error)
+		do_error(_("seeking refcount bag btree cursor\n"));
+}
+
+/* Tear down an iteration. */
+void
+rcbag_ino_iter_stop(
+	struct rcbag		*bag,
+	struct rcbag_iter	*iter)
+{
+	if (iter->cur)
+		libxfs_btree_del_cursor(iter->cur, XFS_BTREE_NOERROR);
+	if (iter->head_bp)
+		libxfs_trans_brelse(NULL, iter->head_bp);
+	iter->cur = NULL;
+	iter->head_bp = NULL;
+}
+
+/*
+ * Walk all the shared inodes tracked by the refcount bag.  Returns 1 when
+ * returning a valid iter.ino, and 0 if iteration has completed.  The iter
+ * should be initialized to zeroes before the first call.
+ */
+int
+rcbag_ino_iter(
+	struct rcbag		*bag,
+	struct rcbag_iter	*iter)
+{
+	struct rcbag_rec	bagrec;
+	int			has;
+	int			error;
+
+	if (bag->nr_items < 2)
+		return 0;
+
+	do {
+		error = -libxfs_btree_increment(iter->cur, 0, &has);
+		if (error)
+			do_error(_("incrementing refcount bag btree cursor\n"));
+		if (!has)
+			return 0;
+
+		error = rcbagbt_get_rec(iter->cur, &bagrec, &has);
+		if (error)
+			do_error(_("reading refcount bag btree record\n"));
+		if (!has)
+			do_error(_("refcount bag btree record disappeared?\n"));
+	} while (iter->ino == bagrec.rbg_ino);
+
+	iter->ino = bagrec.rbg_ino;
+	return 1;
+}
+
+/* Dump the rcbag. */
+void
+rcbag_dump(
+	struct rcbag			*bag)
+{
+	struct rcbag_rec		bagrec;
+	struct xfs_mount		*mp = bag->mp;
+	struct xfs_buf			*head_bp;
+	struct xfs_btree_cur		*cur;
+	unsigned long long		nr = 0;
+	int				has;
+	int				error;
+
+	error = -xfbtree_head_read_buf(bag->xfbtree, NULL, &head_bp);
+	if (error)
+		do_error(_("reading refcount bag header\n"));
+
+	cur = rcbagbt_mem_cursor(mp, NULL, head_bp, bag->xfbtree);
+	error = -libxfs_btree_goto_left_edge(cur);
+	if (error)
+		do_error(_("seeking refcount bag btree cursor\n"));
+
+	while (true) {
+		error = -libxfs_btree_increment(cur, 0, &has);
+		if (error)
+			do_error(_("incrementing refcount bag btree cursor\n"));
+		if (!has)
+			break;
+
+		error = rcbagbt_get_rec(cur, &bagrec, &has);
+		if (error)
+			do_error(_("reading refcount bag btree record\n"));
+		if (!has)
+			do_error(_("refcount bag btree record disappeared?\n"));
+
+		printf("[%llu]: bno 0x%x fsbcount 0x%x ino 0x%llx refcount 0x%llx\n",
+				nr++,
+				(unsigned int)bagrec.rbg_startblock,
+				(unsigned int)bagrec.rbg_blockcount,
+				(unsigned long long)bagrec.rbg_ino,
+				(unsigned long long)bagrec.rbg_refcount);
+	}
+
+	libxfs_btree_del_cursor(cur, error);
+	libxfs_trans_brelse(NULL, head_bp);
+}
diff --git a/repair/rcbag.h b/repair/rcbag.h
new file mode 100644
index 00000000000..a5b2d8456bf
--- /dev/null
+++ b/repair/rcbag.h
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2022-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __RCBAG_H__
+#define __RCBAG_H__
+
+struct xfs_mount;
+struct rcbag;
+
+int rcbag_init(struct xfs_mount *mp, uint64_t max_rmaps, struct rcbag **bagp);
+void rcbag_free(struct rcbag **bagp);
+void rcbag_add(struct rcbag *bag, const struct xfs_rmap_irec *rmap);
+uint64_t rcbag_count(const struct rcbag *bag);
+
+void rcbag_next_edge(struct rcbag *bag, const struct xfs_rmap_irec *next_rmap,
+		bool next_valid, uint32_t *next_bnop);
+void rcbag_remove_ending_at(struct rcbag *bag, uint32_t next_bno);
+
+struct rcbag_iter {
+	struct xfs_buf		*head_bp;
+	struct xfs_btree_cur	*cur;
+	uint64_t		ino;
+};
+
+void rcbag_ino_iter_start(struct rcbag *bag, struct rcbag_iter *iter);
+void rcbag_ino_iter_stop(struct rcbag *bag, struct rcbag_iter *iter);
+int rcbag_ino_iter(struct rcbag *bag, struct rcbag_iter *iter);
+
+void rcbag_dump(struct rcbag *bag);
+
+#endif /* __RCBAG_H__ */
diff --git a/repair/rcbag_btree.c b/repair/rcbag_btree.c
index 0a80852ced3..507839b4535 100644
--- a/repair/rcbag_btree.c
+++ b/repair/rcbag_btree.c
@@ -333,3 +333,62 @@ rcbagbt_destroy_cur_cache(void)
 	kmem_cache_destroy(rcbagbt_cur_cache);
 	rcbagbt_cur_cache = NULL;
 }
+
+/* Look up the refcount bag record corresponding to this reverse mapping. */
+int
+rcbagbt_lookup_eq(
+	struct xfs_btree_cur		*cur,
+	const struct xfs_rmap_irec	*rmap,
+	int				*success)
+{
+	struct rcbag_rec		*rec = (struct rcbag_rec *)&cur->bc_rec;
+
+	rec->rbg_startblock = rmap->rm_startblock;
+	rec->rbg_blockcount = rmap->rm_blockcount;
+	rec->rbg_ino = rmap->rm_owner;
+
+	return -libxfs_btree_lookup(cur, XFS_LOOKUP_EQ, success);
+}
+
+/* Get the data from the pointed-to record. */
+int
+rcbagbt_get_rec(
+	struct xfs_btree_cur	*cur,
+	struct rcbag_rec	*rec,
+	int			*has)
+{
+	union xfs_btree_rec	*btrec;
+	int			error;
+
+	error = -libxfs_btree_get_rec(cur, &btrec, has);
+	if (error || !(*has))
+		return error;
+
+	memcpy(rec, btrec, sizeof(struct rcbag_rec));
+	return 0;
+}
+
+/* Update the record referred to by cur to the value given. */
+int
+rcbagbt_update(
+	struct xfs_btree_cur	*cur,
+	const struct rcbag_rec	*rec)
+{
+	union xfs_btree_rec	btrec;
+
+	memcpy(&btrec, rec, sizeof(struct rcbag_rec));
+	return -libxfs_btree_update(cur, &btrec);
+}
+
+/* Update the record referred to by cur to the value given. */
+int
+rcbagbt_insert(
+	struct xfs_btree_cur	*cur,
+	const struct rcbag_rec	*rec,
+	int			*success)
+{
+	struct rcbag_rec	*btrec = (struct rcbag_rec *)&cur->bc_rec;
+
+	memcpy(btrec, rec, sizeof(struct rcbag_rec));
+	return -libxfs_btree_insert(cur, success);
+}
diff --git a/repair/rcbag_btree.h b/repair/rcbag_btree.h
index 14a09a3f1a1..3cb44090826 100644
--- a/repair/rcbag_btree.h
+++ b/repair/rcbag_btree.h
@@ -68,4 +68,11 @@ struct xfs_btree_cur *rcbagbt_mem_cursor(struct xfs_mount *mp,
 int rcbagbt_mem_create(struct xfs_mount *mp, struct xfs_buftarg *target,
 		struct xfbtree **xfbtreep);
 
+int rcbagbt_lookup_eq(struct xfs_btree_cur *cur,
+		const struct xfs_rmap_irec *rmap, int *success);
+int rcbagbt_get_rec(struct xfs_btree_cur *cur, struct rcbag_rec *rec, int *has);
+int rcbagbt_update(struct xfs_btree_cur *cur, const struct rcbag_rec *rec);
+int rcbagbt_insert(struct xfs_btree_cur *cur, const struct rcbag_rec *rec,
+		int *success);
+
 #endif /* __RCBAG_BTREE_H__ */

[PATCH 5/6] xfs_repair: port to the new refcount bag structure

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Port the refcount record generating code to use the new refcount bag
data structure.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 repair/rmap.c       |  152 +++++++++++++++------------------------------------
 repair/xfs_repair.c |    6 ++
 2 files changed, 52 insertions(+), 106 deletions(-)


diff --git a/repair/rmap.c b/repair/rmap.c
index b338cdc3bea..cc1312c5d1c 100644
--- a/repair/rmap.c
+++ b/repair/rmap.c
@@ -16,6 +16,7 @@
 #include "libfrog/platform.h"
 #include "libxfs/xfile.h"
 #include "libxfs/xfbtree.h"
+#include "rcbag.h"
 
 #undef RMAP_DEBUG
 
@@ -759,35 +760,32 @@ rmap_dump(
  * reflink inode flag, if the stack depth is greater than 1.
  */
 static void
-mark_inode_rl(
+mark_reflink_inodes(
 	struct xfs_mount	*mp,
-	struct xfs_bag		*rmaps)
+	struct rcbag		*rcstack)
 {
-	struct rmap_for_refcount *rfr;
+	struct rcbag_iter	rciter;
 	struct ino_tree_node	*irec;
-	int			off;
-	uint64_t		idx;
 
-	if (bag_count(rmaps) < 2)
-		return;
-
-	/* Reflink flag accounting */
-	foreach_bag_ptr(rmaps, idx, rfr) {
+	rcbag_ino_iter_start(rcstack, &rciter);
+	while (rcbag_ino_iter(rcstack, &rciter) == 1) {
 		xfs_agnumber_t	agno;
 		xfs_agino_t	agino;
+		int		off;
 
-		ASSERT(!XFS_RMAP_NON_INODE_OWNER(rfr->rm_owner));
+		ASSERT(!XFS_RMAP_NON_INODE_OWNER(rciter.ino));
 
-		agno = XFS_INO_TO_AGNO(mp, rfr->rm_owner);
-		agino = XFS_INO_TO_AGINO(mp, rfr->rm_owner);
+		agno = XFS_INO_TO_AGNO(mp, rciter.ino);
+		agino = XFS_INO_TO_AGINO(mp, rciter.ino);
 
 		pthread_mutex_lock(&ag_locks[agno].lock);
 		irec = find_inode_rec(mp, agno, agino);
-		off = get_inode_offset(mp, rfr->rm_owner, irec);
+		off = get_inode_offset(mp, rciter.ino, irec);
 		/* lock here because we might go outside this ag */
 		set_inode_is_rl(irec, off);
 		pthread_mutex_unlock(&ag_locks[agno].lock);
 	}
+	rcbag_ino_iter_stop(rcstack, &rciter);
 }
 
 /*
@@ -823,8 +821,6 @@ refcount_emit(
 _("Insufficient memory while recreating refcount tree."));
 }
 
-#define RMAP_NEXT(r)	((r)->rm_startblock + (r)->rm_blockcount)
-
 /* Decide if an rmap could describe a shared extent. */
 static inline bool
 rmap_shareable(
@@ -884,40 +880,6 @@ refcount_walk_rmaps(
 	return 0;
 }
 
-/*
- * Find the next block where the refcount changes, given the next rmap we
- * looked at and the ones we're already tracking.
- */
-static inline int
-next_refcount_edge(
-	struct xfs_bag		*stack_top,
-	struct xfs_rmap_irec	*next_rmap,
-	bool			next_valid,
-	xfs_agblock_t		*nbnop)
-{
-	struct rmap_for_refcount *rfr;
-	uint64_t		idx;
-	xfs_agblock_t		nbno = NULLAGBLOCK;
-
-	if (next_valid)
-		nbno = next_rmap->rm_startblock;
-
-	foreach_bag_ptr(stack_top, idx, rfr)
-		nbno = min(nbno, RMAP_NEXT(rfr));
-
-	/*
-	 * We should have found /something/ because either next_rrm is the next
-	 * interesting rmap to look at after emitting this refcount extent, or
-	 * there are other rmaps in rmap_bag contributing to the current
-	 * sharing count.  But if something is seriously wrong, bail out.
-	 */
-	if (nbno == NULLAGBLOCK)
-		return EFSCORRUPTED;
-
-	*nbnop = nbno;
-	return 0;
-}
-
 /*
  * Walk forward through the rmap btree to collect all rmaps starting at
  * @bno in @rmap_bag.  These represent the file(s) that share ownership of
@@ -927,28 +889,19 @@ next_refcount_edge(
 static int
 refcount_push_rmaps_at(
 	struct rmap_mem_cur	*rmcur,
-	xfs_agnumber_t		agno,
-	struct xfs_bag		*stack_top,
+	struct rcbag		*stack,
 	xfs_agblock_t		bno,
-	struct xfs_rmap_irec	*irec,
+	struct xfs_rmap_irec	*rmap,
 	bool			*have,
 	const char		*tag)
 {
 	int			have_gt;
 	int			error;
 
-	while (*have && irec->rm_startblock == bno) {
-		struct rmap_for_refcount	rfr = {
-			.rm_startblock		= irec->rm_startblock,
-			.rm_blockcount		= irec->rm_blockcount,
-			.rm_owner		= irec->rm_owner,
-		};
+	while (*have && rmap->rm_startblock == bno) {
+		rcbag_add(stack, rmap);
 
-		rmap_dump(tag, agno, &rfr);
-		error = bag_add(stack_top, &rfr);
-		if (error)
-			return error;
-		error = refcount_walk_rmaps(rmcur->mcur, irec, have);
+		error = refcount_walk_rmaps(rmcur->mcur, rmap, have);
 		if (error)
 			return error;
 	}
@@ -968,15 +921,14 @@ refcount_push_rmaps_at(
  */
 int
 compute_refcounts(
-	struct xfs_mount		*mp,
+	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno)
 {
+	struct rcbag		*rcstack;
 	struct rmap_mem_cur	rmcur;
-	struct xfs_rmap_irec	irec;
-	struct xfs_bag		*stack_top = NULL;
-	struct rmap_for_refcount *rfr;
-	uint64_t		idx;
-	uint64_t		old_stack_nr;
+	struct xfs_rmap_irec	rmap;
+	uint64_t		nr_rmaps;
+	uint64_t		old_stack_height;
 	xfs_agblock_t		sbno;	/* first bno of this rmap set */
 	xfs_agblock_t		cbno;	/* first bno of this refcount set */
 	xfs_agblock_t		nbno;	/* next bno where rmap set changes */
@@ -988,11 +940,13 @@ compute_refcounts(
 	if (ag_rmaps[agno].ar_xfbtree == NULL)
 		return 0;
 
+	nr_rmaps = rmap_record_count(mp, agno);
+
 	error = rmap_init_mem_cursor(mp, NULL, agno, &rmcur);
 	if (error)
 		return error;
 
-	error = init_bag(&stack_top, sizeof(struct rmap_for_refcount));
+	error = rcbag_init(mp, nr_rmaps, &rcstack);
 	if (error)
 		goto out_cur;
 
@@ -1005,86 +959,72 @@ compute_refcounts(
 	/* Process reverse mappings into refcount data. */
 	while (libxfs_btree_has_more_records(rmcur.mcur)) {
 		/* Push all rmaps with pblk == sbno onto the stack */
-		error = refcount_walk_rmaps(rmcur.mcur, &irec, &have);
+		error = refcount_walk_rmaps(rmcur.mcur, &rmap, &have);
 		if (error)
 			goto out_bag;
 		if (!have)
 			break;
-		sbno = cbno = irec.rm_startblock;
-		error = refcount_push_rmaps_at(&rmcur, agno, stack_top, sbno,
-				&irec, &have, "push0");
+		sbno = cbno = rmap.rm_startblock;
+		error = refcount_push_rmaps_at(&rmcur, rcstack, sbno, &rmap,
+				&have, "push0");
 		if (error)
 			goto out_bag;
-		mark_inode_rl(mp, stack_top);
+		mark_reflink_inodes(mp, rcstack);
 
 		/* Set nbno to the bno of the next refcount change */
-		error = next_refcount_edge(stack_top, &irec, have, &nbno);
-		if (error)
-			goto out_bag;
+		rcbag_next_edge(rcstack, &rmap, have, &nbno);
 
 		/* Emit reverse mappings, if needed */
 		ASSERT(nbno > sbno);
-		old_stack_nr = bag_count(stack_top);
+		old_stack_height = rcbag_count(rcstack);
 
 		/* While stack isn't empty... */
-		while (bag_count(stack_top)) {
+		while (rcbag_count(rcstack) > 0) {
 			/* Pop all rmaps that end at nbno */
-			foreach_bag_ptr_reverse(stack_top, idx, rfr) {
-				if (RMAP_NEXT(rfr) != nbno)
-					continue;
-				rmap_dump("pop", agno, rfr);
-				error = bag_remove(stack_top, idx);
-				if (error)
-					goto out_bag;
-			}
+			rcbag_remove_ending_at(rcstack, nbno);
 
 			/* Push array items that start at nbno */
-			error = refcount_walk_rmaps(rmcur.mcur, &irec, &have);
+			error = refcount_walk_rmaps(rmcur.mcur, &rmap, &have);
 			if (error)
 				goto out_bag;
 			if (have) {
-				error = refcount_push_rmaps_at(&rmcur, agno,
-						stack_top, nbno, &irec, &have,
-						"push1");
+				error = refcount_push_rmaps_at(&rmcur, rcstack,
+						nbno, &rmap, &have, "push1");
 				if (error)
 					goto out_bag;
 			}
-			mark_inode_rl(mp, stack_top);
+			mark_reflink_inodes(mp, rcstack);
 
 			/* Emit refcount if necessary */
 			ASSERT(nbno > cbno);
-			if (bag_count(stack_top) != old_stack_nr) {
-				if (old_stack_nr > 1) {
+			if (rcbag_count(rcstack) != old_stack_height) {
+				if (old_stack_height > 1) {
 					refcount_emit(mp, agno, cbno,
-						      nbno - cbno,
-						      old_stack_nr);
+							nbno - cbno,
+							old_stack_height);
 				}
 				cbno = nbno;
 			}
 
 			/* Stack empty, go find the next rmap */
-			if (bag_count(stack_top) == 0)
+			if (rcbag_count(rcstack) == 0)
 				break;
-			old_stack_nr = bag_count(stack_top);
+			old_stack_height = rcbag_count(rcstack);
 			sbno = nbno;
 
 			/* Set nbno to the bno of the next refcount change */
-			error = next_refcount_edge(stack_top, &irec, have,
-					&nbno);
-			if (error)
-				goto out_bag;
+			rcbag_next_edge(rcstack, &rmap, have, &nbno);
 
 			/* Emit reverse mappings, if needed */
 			ASSERT(nbno > sbno);
 		}
 	}
 out_bag:
-	free_bag(&stack_top);
+	rcbag_free(&rcstack);
 out_cur:
 	rmap_free_mem_cursor(NULL, &rmcur, error);
 	return error;
 }
-#undef RMAP_NEXT
 
 static int
 count_btree_records(
diff --git a/repair/xfs_repair.c b/repair/xfs_repair.c
index ba78dc0b8ea..bf02beba375 100644
--- a/repair/xfs_repair.c
+++ b/repair/xfs_repair.c
@@ -26,6 +26,7 @@
 #include "libfrog/platform.h"
 #include "bulkload.h"
 #include "quotacheck.h"
+#include "rcbag_btree.h"
 
 /*
  * option tables for getsubopt calls
@@ -1259,6 +1260,10 @@ main(int argc, char **argv)
 	phase3(mp, phase2_threads);
 	phase_end(mp, 3);
 
+	error = rcbagbt_init_cur_cache();
+	if (error)
+		do_error(_("could not allocate btree cursor memory\n"));
+
 	phase4(mp);
 	phase_end(mp, 4);
 
@@ -1271,6 +1276,7 @@ main(int argc, char **argv)
 		phase5(mp);
 	}
 	phase_end(mp, 5);
+	rcbagbt_destroy_cur_cache();
 
 	/*
 	 * Done with the block usage maps, toss them...

[PATCH 6/6] xfs_repair: remove the old bag implementation

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Remove the old bag implementation.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 repair/rmap.c |    7 ---
 repair/slab.c |  130 ---------------------------------------------------------
 repair/slab.h |   19 --------
 3 files changed, 156 deletions(-)


diff --git a/repair/rmap.c b/repair/rmap.c
index cc1312c5d1c..8895377aa2a 100644
--- a/repair/rmap.c
+++ b/repair/rmap.c
@@ -35,13 +35,6 @@ struct xfs_ag_rmap {
 	struct xfs_slab	*ar_refcount_items;	/* refcount items, p4-5 */
 };
 
-/* Only the parts of struct xfs_rmap_irec that we need to compute refcounts. */
-struct rmap_for_refcount {
-	xfs_agblock_t	rm_startblock;
-	xfs_extlen_t	rm_blockcount;
-	uint64_t	rm_owner;
-};
-
 static struct xfs_ag_rmap *ag_rmaps;
 bool rmapbt_suspect;
 static bool refcbt_suspect;
diff --git a/repair/slab.c b/repair/slab.c
index 44ca0468eda..a0114ac2373 100644
--- a/repair/slab.c
+++ b/repair/slab.c
@@ -77,28 +77,6 @@ struct xfs_slab_cursor {
 	struct xfs_slab_hdr_cursor	hcur[0];	/* per-slab cursors */
 };
 
-/*
- * Bags -- each bag is an array of record items; when a bag fills up, we resize
- * it and hope we don't run out of memory.
- */
-#define MIN_BAG_SIZE	4096
-struct xfs_bag {
-	uint64_t		bg_nr;		/* number of pointers */
-	uint64_t		bg_inuse;	/* number of slots in use */
-	char			*bg_items;	/* pointer to block of items */
-	size_t			bg_item_sz;	/* size of each item */
-};
-
-static inline void *bag_ptr(struct xfs_bag *bag, uint64_t idx)
-{
-	return &bag->bg_items[bag->bg_item_sz * idx];
-}
-
-static inline void *bag_end(struct xfs_bag *bag)
-{
-	return bag_ptr(bag, bag->bg_nr);
-}
-
 /*
  * Create a slab to hold some objects of a particular size.
  */
@@ -386,111 +364,3 @@ slab_count(
 {
 	return slab->s_nr_items;
 }
-
-/*
- * Create a bag to point to some objects.
- */
-int
-init_bag(
-	struct xfs_bag	**bag,
-	size_t		item_sz)
-{
-	struct xfs_bag	*ptr;
-
-	ptr = calloc(1, sizeof(struct xfs_bag));
-	if (!ptr)
-		return -ENOMEM;
-	ptr->bg_item_sz = item_sz;
-	ptr->bg_items = calloc(MIN_BAG_SIZE, item_sz);
-	if (!ptr->bg_items) {
-		free(ptr);
-		return -ENOMEM;
-	}
-	ptr->bg_nr = MIN_BAG_SIZE;
-	*bag = ptr;
-	return 0;
-}
-
-/*
- * Free a bag of pointers.
- */
-void
-free_bag(
-	struct xfs_bag	**bag)
-{
-	struct xfs_bag	*ptr;
-
-	ptr = *bag;
-	if (!ptr)
-		return;
-	free(ptr->bg_items);
-	free(ptr);
-	*bag = NULL;
-}
-
-/*
- * Add an object to the pointer bag.
- */
-int
-bag_add(
-	struct xfs_bag	*bag,
-	void		*ptr)
-{
-	void		*p, *x;
-
-	p = bag_ptr(bag, bag->bg_inuse);
-	if (p == bag_end(bag)) {
-		/* No free space, alloc more pointers */
-		uint64_t	nr;
-
-		nr = bag->bg_nr * 2;
-		x = realloc(bag->bg_items, nr * bag->bg_item_sz);
-		if (!x)
-			return -ENOMEM;
-		bag->bg_items = x;
-		memset(bag_end(bag), 0, bag->bg_nr * bag->bg_item_sz);
-		bag->bg_nr = nr;
-		p = bag_ptr(bag, bag->bg_inuse);
-	}
-	memcpy(p, ptr, bag->bg_item_sz);
-	bag->bg_inuse++;
-	return 0;
-}
-
-/*
- * Remove a pointer from a bag.
- */
-int
-bag_remove(
-	struct xfs_bag	*bag,
-	uint64_t	nr)
-{
-	ASSERT(nr < bag->bg_inuse);
-	memmove(bag_ptr(bag, nr), bag_ptr(bag, nr + 1),
-		(bag->bg_inuse - nr - 1) * bag->bg_item_sz);
-	bag->bg_inuse--;
-	return 0;
-}
-
-/*
- * Return the number of items in a bag.
- */
-uint64_t
-bag_count(
-	struct xfs_bag	*bag)
-{
-	return bag->bg_inuse;
-}
-
-/*
- * Return the nth item in a bag.
- */
-void *
-bag_item(
-	struct xfs_bag	*bag,
-	uint64_t	nr)
-{
-	if (nr >= bag->bg_inuse)
-		return NULL;
-	return bag_ptr(bag, nr);
-}
diff --git a/repair/slab.h b/repair/slab.h
index 019b169024d..77fb32163d5 100644
--- a/repair/slab.h
+++ b/repair/slab.h
@@ -26,23 +26,4 @@ void *peek_slab_cursor(struct xfs_slab_cursor *cur);
 void advance_slab_cursor(struct xfs_slab_cursor *cur);
 void *pop_slab_cursor(struct xfs_slab_cursor *cur);
 
-struct xfs_bag;
-
-int init_bag(struct xfs_bag **bagp, size_t itemsz);
-void free_bag(struct xfs_bag **bagp);
-int bag_add(struct xfs_bag *bag, void *item);
-int bag_remove(struct xfs_bag *bag, uint64_t idx);
-uint64_t bag_count(struct xfs_bag *bag);
-void *bag_item(struct xfs_bag *bag, uint64_t idx);
-
-#define foreach_bag_ptr(bag, idx, ptr) \
-	for ((idx) = 0, (ptr) = bag_item((bag), (idx)); \
-	     (idx) < bag_count(bag); \
-	     (idx)++, (ptr) = bag_item((bag), (idx)))
-
-#define foreach_bag_ptr_reverse(bag, idx, ptr) \
-	for ((idx) = bag_count(bag) - 1, (ptr) = bag_item((bag), (idx)); \
-	     (ptr) != NULL; \
-	     (idx)--, (ptr) = bag_item((bag), (idx)))
-
 #endif /* SLAB_H_ */

[PATCH 1/5] xfs: clean up bmap log intent item tracepoint callsites

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Pass the incore bmap structure to the tracepoints instead of open-coding
the argument passing.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_bmap.c |   19 +++----------------
 libxfs/xfs_bmap.h |    4 ++++
 2 files changed, 7 insertions(+), 16 deletions(-)


diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index 9a2cb5662d1..6b0d6d2e635 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -6163,15 +6163,6 @@ __xfs_bmap_add(
 {
 	struct xfs_bmap_intent		*bi;
 
-	trace_xfs_bmap_defer(tp->t_mountp,
-			XFS_FSB_TO_AGNO(tp->t_mountp, bmap->br_startblock),
-			type,
-			XFS_FSB_TO_AGBNO(tp->t_mountp, bmap->br_startblock),
-			ip->i_ino, whichfork,
-			bmap->br_startoff,
-			bmap->br_blockcount,
-			bmap->br_state);
-
 	bi = kmem_cache_alloc(xfs_bmap_intent_cache, GFP_NOFS | __GFP_NOFAIL);
 	INIT_LIST_HEAD(&bi->bi_list);
 	bi->bi_type = type;
@@ -6179,6 +6170,8 @@ __xfs_bmap_add(
 	bi->bi_whichfork = whichfork;
 	bi->bi_bmap = *bmap;
 
+	trace_xfs_bmap_defer(bi);
+
 	xfs_bmap_update_get_group(tp->t_mountp, bi);
 	xfs_defer_add(tp, &bi->bi_list, &xfs_bmap_update_defer_type);
 	return 0;
@@ -6224,13 +6217,7 @@ xfs_bmap_finish_one(
 
 	ASSERT(tp->t_highest_agno == NULLAGNUMBER);
 
-	trace_xfs_bmap_deferred(tp->t_mountp,
-			XFS_FSB_TO_AGNO(tp->t_mountp, bmap->br_startblock),
-			bi->bi_type,
-			XFS_FSB_TO_AGBNO(tp->t_mountp, bmap->br_startblock),
-			bi->bi_owner->i_ino, bi->bi_whichfork,
-			bmap->br_startoff, bmap->br_blockcount,
-			bmap->br_state);
+	trace_xfs_bmap_deferred(bi);
 
 	if (WARN_ON_ONCE(bi->bi_whichfork != XFS_DATA_FORK)) {
 		xfs_bmap_mark_sick(bi->bi_owner, bi->bi_whichfork);
diff --git a/libxfs/xfs_bmap.h b/libxfs/xfs_bmap.h
index 9dd631bc2dc..b477f92c850 100644
--- a/libxfs/xfs_bmap.h
+++ b/libxfs/xfs_bmap.h
@@ -230,6 +230,10 @@ enum xfs_bmap_intent_type {
 	XFS_BMAP_UNMAP,
 };
 
+#define XFS_BMAP_INTENT_STRINGS \
+	{ XFS_BMAP_MAP,		"map" }, \
+	{ XFS_BMAP_UNMAP,	"unmap" }
+
 struct xfs_bmap_intent {
 	struct list_head			bi_list;
 	enum xfs_bmap_intent_type		bi_type;

[PATCH 2/5] xfs: add a bi_entry helper

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add a helper to translate from the item list head to the bmap_intent
structure and use it so shorten assignments and avoid the need for extra
local variables.

Inspired-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/defer_item.c |   18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)


diff --git a/libxfs/defer_item.c b/libxfs/defer_item.c
index 014589f82ec..8e3ec056ed7 100644
--- a/libxfs/defer_item.c
+++ b/libxfs/defer_item.c
@@ -438,6 +438,11 @@ const struct xfs_defer_op_type xfs_refcount_update_defer_type = {
 
 /* Inode Block Mapping */
 
+static inline struct xfs_bmap_intent *bi_entry(const struct list_head *e)
+{
+	return list_entry(e, struct xfs_bmap_intent, bi_list);
+}
+
 /* Sort bmap intents by inode. */
 static int
 xfs_bmap_update_diff_items(
@@ -445,11 +450,9 @@ xfs_bmap_update_diff_items(
 	const struct list_head		*a,
 	const struct list_head		*b)
 {
-	const struct xfs_bmap_intent	*ba;
-	const struct xfs_bmap_intent	*bb;
+	struct xfs_bmap_intent		*ba = bi_entry(a);
+	struct xfs_bmap_intent		*bb = bi_entry(b);
 
-	ba = container_of(a, struct xfs_bmap_intent, bi_list);
-	bb = container_of(b, struct xfs_bmap_intent, bi_list);
 	return ba->bi_owner->i_ino - bb->bi_owner->i_ino;
 }
 
@@ -514,10 +517,9 @@ xfs_bmap_update_finish_item(
 	struct list_head		*item,
 	struct xfs_btree_cur		**state)
 {
-	struct xfs_bmap_intent		*bi;
+	struct xfs_bmap_intent		*bi = bi_entry(item);
 	int				error;
 
-	bi = container_of(item, struct xfs_bmap_intent, bi_list);
 	error = xfs_bmap_finish_one(tp, bi);
 	if (!error && bi->bi_bmap.br_blockcount > 0) {
 		ASSERT(bi->bi_type == XFS_BMAP_UNMAP);
@@ -541,9 +543,7 @@ STATIC void
 xfs_bmap_update_cancel_item(
 	struct list_head		*item)
 {
-	struct xfs_bmap_intent		*bi;
-
-	bi = container_of(item, struct xfs_bmap_intent, bi_list);
+	struct xfs_bmap_intent		*bi = bi_entry(item);
 
 	xfs_bmap_update_put_group(bi);
 	kmem_cache_free(xfs_bmap_intent_cache, bi);

[PATCH 3/5] xfs: reuse xfs_bmap_update_cancel_item

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Reuse xfs_bmap_update_cancel_item to put the AG/RTG and free the item in
a few places that currently open code the logic.

Inspired-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/defer_item.c |   25 ++++++++++++-------------
 1 file changed, 12 insertions(+), 13 deletions(-)


diff --git a/libxfs/defer_item.c b/libxfs/defer_item.c
index 8e3ec056ed7..78de8491bb5 100644
--- a/libxfs/defer_item.c
+++ b/libxfs/defer_item.c
@@ -509,6 +509,17 @@ xfs_bmap_update_put_group(
 	xfs_perag_intent_put(bi->bi_pag);
 }
 
+/* Cancel a deferred rmap update. */
+STATIC void
+xfs_bmap_update_cancel_item(
+	struct list_head		*item)
+{
+	struct xfs_bmap_intent		*bi = bi_entry(item);
+
+	xfs_bmap_update_put_group(bi);
+	kmem_cache_free(xfs_bmap_intent_cache, bi);
+}
+
 /* Process a deferred rmap update. */
 STATIC int
 xfs_bmap_update_finish_item(
@@ -526,8 +537,7 @@ xfs_bmap_update_finish_item(
 		return -EAGAIN;
 	}
 
-	xfs_bmap_update_put_group(bi);
-	kmem_cache_free(xfs_bmap_intent_cache, bi);
+	xfs_bmap_update_cancel_item(item);
 	return error;
 }
 
@@ -538,17 +548,6 @@ xfs_bmap_update_abort_intent(
 {
 }
 
-/* Cancel a deferred rmap update. */
-STATIC void
-xfs_bmap_update_cancel_item(
-	struct list_head		*item)
-{
-	struct xfs_bmap_intent		*bi = bi_entry(item);
-
-	xfs_bmap_update_put_group(bi);
-	kmem_cache_free(xfs_bmap_intent_cache, bi);
-}
-
 const struct xfs_defer_op_type xfs_bmap_update_defer_type = {
 	.name		= "bmap",
 	.create_intent	= xfs_bmap_update_create_intent,

[PATCH 4/5] xfs: move xfs_bmap_defer_add to xfs_bmap_item.c

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Move the code that adds the incore xfs_bmap_item deferred work data to a
transaction live with the BUI log item code.  This means that the file
mapping code no longer has to know about the inner workings of the BUI
log items.

As a consequence, we can hide the _get_group helper.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/Makefile     |    1 +
 libxfs/defer_item.c |   15 ++++++++++++++-
 libxfs/defer_item.h |   13 +++++++++++++
 libxfs/xfs_bmap.c   |    6 ++----
 libxfs/xfs_bmap.h   |    3 ---
 5 files changed, 30 insertions(+), 8 deletions(-)
 create mode 100644 libxfs/defer_item.h


diff --git a/libxfs/Makefile b/libxfs/Makefile
index 8e6b2dfdfe1..e1248c2b3ca 100644
--- a/libxfs/Makefile
+++ b/libxfs/Makefile
@@ -20,6 +20,7 @@ PKGHFILES = xfs_fs.h \
 	xfs_log_format.h
 
 HFILES = \
+	defer_item.h \
 	libxfs_io.h \
 	libxfs_api_defs.h \
 	init.h \
diff --git a/libxfs/defer_item.c b/libxfs/defer_item.c
index 78de8491bb5..c9502d30860 100644
--- a/libxfs/defer_item.c
+++ b/libxfs/defer_item.c
@@ -24,6 +24,7 @@
 #include "xfs_da_btree.h"
 #include "xfs_attr.h"
 #include "libxfs.h"
+#include "defer_item.h"
 
 /* Dummy defer item ops, since we don't do logging. */
 
@@ -482,7 +483,7 @@ xfs_bmap_update_create_done(
 }
 
 /* Take an active ref to the AG containing the space we're mapping. */
-void
+static inline void
 xfs_bmap_update_get_group(
 	struct xfs_mount	*mp,
 	struct xfs_bmap_intent	*bi)
@@ -501,6 +502,18 @@ xfs_bmap_update_get_group(
 	bi->bi_pag = xfs_perag_intent_get(mp, agno);
 }
 
+/* Add this deferred BUI to the transaction. */
+void
+xfs_bmap_defer_add(
+	struct xfs_trans	*tp,
+	struct xfs_bmap_intent	*bi)
+{
+	trace_xfs_bmap_defer(bi);
+
+	xfs_bmap_update_get_group(tp->t_mountp, bi);
+	xfs_defer_add(tp, &bi->bi_list, &xfs_bmap_update_defer_type);
+}
+
 /* Release an active AG ref after finishing mapping work. */
 static inline void
 xfs_bmap_update_put_group(
diff --git a/libxfs/defer_item.h b/libxfs/defer_item.h
new file mode 100644
index 00000000000..6d3abf1589c
--- /dev/null
+++ b/libxfs/defer_item.h
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2023-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef	__LIBXFS_DEFER_ITEM_H_
+#define	__LIBXFS_DEFER_ITEM_H_
+
+struct xfs_bmap_intent;
+
+void xfs_bmap_defer_add(struct xfs_trans *tp, struct xfs_bmap_intent *bi);
+
+#endif /* __LIBXFS_DEFER_ITEM_H_ */
diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index 6b0d6d2e635..69ed4150c5e 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -31,6 +31,7 @@
 #include "xfs_refcount.h"
 #include "xfs_rtbitmap.h"
 #include "xfs_health.h"
+#include "defer_item.h"
 
 struct kmem_cache		*xfs_bmap_intent_cache;
 
@@ -6170,10 +6171,7 @@ __xfs_bmap_add(
 	bi->bi_whichfork = whichfork;
 	bi->bi_bmap = *bmap;
 
-	trace_xfs_bmap_defer(bi);
-
-	xfs_bmap_update_get_group(tp->t_mountp, bi);
-	xfs_defer_add(tp, &bi->bi_list, &xfs_bmap_update_defer_type);
+	xfs_bmap_defer_add(tp, bi);
 	return 0;
 }
 
diff --git a/libxfs/xfs_bmap.h b/libxfs/xfs_bmap.h
index b477f92c850..a5e37ef7b75 100644
--- a/libxfs/xfs_bmap.h
+++ b/libxfs/xfs_bmap.h
@@ -243,9 +243,6 @@ struct xfs_bmap_intent {
 	struct xfs_bmbt_irec			bi_bmap;
 };
 
-void xfs_bmap_update_get_group(struct xfs_mount *mp,
-		struct xfs_bmap_intent *bi);
-
 int	xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_bmap_intent *bi);
 void	xfs_bmap_map_extent(struct xfs_trans *tp, struct xfs_inode *ip,
 		struct xfs_bmbt_irec *imap);

[PATCH 5/5] xfs: add a xattr_entry helper

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add a helper to translate from the item list head to the attr_intent
item structure and use it so shorten assignments and avoid the need for
extra local variables.

Inspired-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/defer_item.c |   15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)


diff --git a/libxfs/defer_item.c b/libxfs/defer_item.c
index c9502d30860..e9875f3e208 100644
--- a/libxfs/defer_item.c
+++ b/libxfs/defer_item.c
@@ -570,6 +570,13 @@ const struct xfs_defer_op_type xfs_bmap_update_defer_type = {
 	.cancel_item	= xfs_bmap_update_cancel_item,
 };
 
+/* Logged extended attributes */
+
+static inline struct xfs_attr_intent *attri_entry(const struct list_head *e)
+{
+	return list_entry(e, struct xfs_attr_intent, xattri_list);
+}
+
 /* Get an ATTRI. */
 static struct xfs_log_item *
 xfs_attr_create_intent(
@@ -618,11 +625,10 @@ xfs_attr_finish_item(
 	struct list_head	*item,
 	struct xfs_btree_cur	**state)
 {
-	struct xfs_attr_intent	*attr;
-	int			error;
+	struct xfs_attr_intent	*attr = attri_entry(item);
 	struct xfs_da_args	*args;
+	int			error;
 
-	attr = container_of(item, struct xfs_attr_intent, xattri_list);
 	args = attr->xattri_da_args;
 
 	/*
@@ -651,9 +657,8 @@ static void
 xfs_attr_cancel_item(
 	struct list_head	*item)
 {
-	struct xfs_attr_intent	*attr;
+	struct xfs_attr_intent	*attr = attri_entry(item);
 
-	attr = container_of(item, struct xfs_attr_intent, xattri_list);
 	xfs_attr_free_item(attr);
 }
 

[PATCH 1/2] xfs: fix xfs_bunmapi to allow unmapping of partial rt extents

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

When XFS_BMAPI_REMAP is passed to bunmapi, that means that we want to
remove part of a block mapping without touching the allocator.  For
realtime files with rtextsize > 1, that also means that we should skip
all the code that changes a partial remove request into an unwritten
extent conversion.  IOWs, bunmapi in this mode should handle removing
the mapping from the rt file and nothing else.

Note that XFS_BMAPI_REMAP callers are required to decrement the
reference count and/or free the space manually.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_bmap.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)


diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index 69ed4150c5e..b0747e57e90 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -5425,7 +5425,7 @@ __xfs_bunmapi(
 		if (del.br_startoff + del.br_blockcount > end + 1)
 			del.br_blockcount = end + 1 - del.br_startoff;
 
-		if (!isrt)
+		if (!isrt || (flags & XFS_BMAPI_REMAP))
 			goto delete;
 
 		mod = xfs_rtb_to_rtxoff(mp,
@@ -5443,7 +5443,7 @@ __xfs_bunmapi(
 				 * This piece is unwritten, or we're not
 				 * using unwritten extents.  Skip over it.
 				 */
-				ASSERT(end >= mod);
+				ASSERT((flags & XFS_BMAPI_REMAP) || end >= mod);
 				end -= mod > del.br_blockcount ?
 					del.br_blockcount : mod;
 				if (end < got.br_startoff &&

[PATCH 2/2] xfs: add a realtime flag to the bmap update log redo items

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Extend the bmap update (BUI) log items with a new realtime flag that
indicates that the updates apply against a realtime file's data fork.
We'll wire up the actual code later.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/defer_item.c     |    6 ++++++
 libxfs/xfs_log_format.h |    4 +++-
 2 files changed, 9 insertions(+), 1 deletion(-)


diff --git a/libxfs/defer_item.c b/libxfs/defer_item.c
index e9875f3e208..e7d64be014d 100644
--- a/libxfs/defer_item.c
+++ b/libxfs/defer_item.c
@@ -490,6 +490,9 @@ xfs_bmap_update_get_group(
 {
 	xfs_agnumber_t		agno;
 
+	if (xfs_ifork_is_realtime(bi->bi_owner, bi->bi_whichfork))
+		return;
+
 	agno = XFS_FSB_TO_AGNO(mp, bi->bi_bmap.br_startblock);
 
 	/*
@@ -519,6 +522,9 @@ static inline void
 xfs_bmap_update_put_group(
 	struct xfs_bmap_intent	*bi)
 {
+	if (xfs_ifork_is_realtime(bi->bi_owner, bi->bi_whichfork))
+		return;
+
 	xfs_perag_intent_put(bi->bi_pag);
 }
 
diff --git a/libxfs/xfs_log_format.h b/libxfs/xfs_log_format.h
index 269573c8280..16872972e1e 100644
--- a/libxfs/xfs_log_format.h
+++ b/libxfs/xfs_log_format.h
@@ -838,10 +838,12 @@ struct xfs_cud_log_format {
 
 #define XFS_BMAP_EXTENT_ATTR_FORK	(1U << 31)
 #define XFS_BMAP_EXTENT_UNWRITTEN	(1U << 30)
+#define XFS_BMAP_EXTENT_REALTIME	(1U << 29)
 
 #define XFS_BMAP_EXTENT_FLAGS		(XFS_BMAP_EXTENT_TYPE_MASK | \
 					 XFS_BMAP_EXTENT_ATTR_FORK | \
-					 XFS_BMAP_EXTENT_UNWRITTEN)
+					 XFS_BMAP_EXTENT_UNWRITTEN | \
+					 XFS_BMAP_EXTENT_REALTIME)
 
 /*
  * This is the structure used to lay out an bui log item in the

[PATCH 1/2] xfs: support deferred bmap updates on the attr fork

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

The deferred bmap update log item has always supported the attr fork, so
plumb this in so that higher layers can access this.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_bmap.c |   47 +++++++++++++++++++----------------------------
 libxfs/xfs_bmap.h |    4 ++--
 2 files changed, 21 insertions(+), 30 deletions(-)


diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index b0747e57e90..b7a9f541d30 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -6144,17 +6144,8 @@ xfs_bmap_split_extent(
 	return error;
 }
 
-/* Deferred mapping is only for real extents in the data fork. */
-static bool
-xfs_bmap_is_update_needed(
-	struct xfs_bmbt_irec	*bmap)
-{
-	return  bmap->br_startblock != HOLESTARTBLOCK &&
-		bmap->br_startblock != DELAYSTARTBLOCK;
-}
-
 /* Record a bmap intent. */
-static int
+static inline void
 __xfs_bmap_add(
 	struct xfs_trans		*tp,
 	enum xfs_bmap_intent_type	type,
@@ -6164,6 +6155,11 @@ __xfs_bmap_add(
 {
 	struct xfs_bmap_intent		*bi;
 
+	if ((whichfork != XFS_DATA_FORK && whichfork != XFS_ATTR_FORK) ||
+	    bmap->br_startblock == HOLESTARTBLOCK ||
+	    bmap->br_startblock == DELAYSTARTBLOCK)
+		return;
+
 	bi = kmem_cache_alloc(xfs_bmap_intent_cache, GFP_NOFS | __GFP_NOFAIL);
 	INIT_LIST_HEAD(&bi->bi_list);
 	bi->bi_type = type;
@@ -6172,7 +6168,6 @@ __xfs_bmap_add(
 	bi->bi_bmap = *bmap;
 
 	xfs_bmap_defer_add(tp, bi);
-	return 0;
 }
 
 /* Map an extent into a file. */
@@ -6180,12 +6175,10 @@ void
 xfs_bmap_map_extent(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
+	int			whichfork,
 	struct xfs_bmbt_irec	*PREV)
 {
-	if (!xfs_bmap_is_update_needed(PREV))
-		return;
-
-	__xfs_bmap_add(tp, XFS_BMAP_MAP, ip, XFS_DATA_FORK, PREV);
+	__xfs_bmap_add(tp, XFS_BMAP_MAP, ip, whichfork, PREV);
 }
 
 /* Unmap an extent out of a file. */
@@ -6193,12 +6186,10 @@ void
 xfs_bmap_unmap_extent(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
+	int			whichfork,
 	struct xfs_bmbt_irec	*PREV)
 {
-	if (!xfs_bmap_is_update_needed(PREV))
-		return;
-
-	__xfs_bmap_add(tp, XFS_BMAP_UNMAP, ip, XFS_DATA_FORK, PREV);
+	__xfs_bmap_add(tp, XFS_BMAP_UNMAP, ip, whichfork, PREV);
 }
 
 /*
@@ -6212,29 +6203,29 @@ xfs_bmap_finish_one(
 {
 	struct xfs_bmbt_irec		*bmap = &bi->bi_bmap;
 	int				error = 0;
+	int				flags = 0;
+
+	if (bi->bi_whichfork == XFS_ATTR_FORK)
+		flags |= XFS_BMAPI_ATTRFORK;
 
 	ASSERT(tp->t_highest_agno == NULLAGNUMBER);
 
 	trace_xfs_bmap_deferred(bi);
 
-	if (WARN_ON_ONCE(bi->bi_whichfork != XFS_DATA_FORK)) {
-		xfs_bmap_mark_sick(bi->bi_owner, bi->bi_whichfork);
-		return -EFSCORRUPTED;
-	}
-
-	if (XFS_TEST_ERROR(false, tp->t_mountp,
-			XFS_ERRTAG_BMAP_FINISH_ONE))
+	if (XFS_TEST_ERROR(false, tp->t_mountp, XFS_ERRTAG_BMAP_FINISH_ONE))
 		return -EIO;
 
 	switch (bi->bi_type) {
 	case XFS_BMAP_MAP:
 		error = xfs_bmapi_remap(tp, bi->bi_owner, bmap->br_startoff,
-				bmap->br_blockcount, bmap->br_startblock, 0);
+				bmap->br_blockcount, bmap->br_startblock,
+				flags);
 		bmap->br_blockcount = 0;
 		break;
 	case XFS_BMAP_UNMAP:
 		error = __xfs_bunmapi(tp, bi->bi_owner, bmap->br_startoff,
-				&bmap->br_blockcount, XFS_BMAPI_REMAP, 1);
+				&bmap->br_blockcount, flags | XFS_BMAPI_REMAP,
+				1);
 		break;
 	default:
 		ASSERT(0);
diff --git a/libxfs/xfs_bmap.h b/libxfs/xfs_bmap.h
index a5e37ef7b75..1eee606f392 100644
--- a/libxfs/xfs_bmap.h
+++ b/libxfs/xfs_bmap.h
@@ -245,9 +245,9 @@ struct xfs_bmap_intent {
 
 int	xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_bmap_intent *bi);
 void	xfs_bmap_map_extent(struct xfs_trans *tp, struct xfs_inode *ip,
-		struct xfs_bmbt_irec *imap);
+		int whichfork, struct xfs_bmbt_irec *imap);
 void	xfs_bmap_unmap_extent(struct xfs_trans *tp, struct xfs_inode *ip,
-		struct xfs_bmbt_irec *imap);
+		int whichfork, struct xfs_bmbt_irec *imap);
 
 static inline uint32_t xfs_bmap_fork_to_state(int whichfork)
 {

[PATCH 2/2] xfs: xfs_bmap_finish_one should map unwritten extents properly

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

The deferred bmap work state and the log item can transmit unwritten
state, so the XFS_BMAP_MAP handler must map in extents with that
unwritten state.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_bmap.c |    2 ++
 1 file changed, 2 insertions(+)


diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index b7a9f541d30..d6cb466d63f 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -6217,6 +6217,8 @@ xfs_bmap_finish_one(
 
 	switch (bi->bi_type) {
 	case XFS_BMAP_MAP:
+		if (bi->bi_bmap.br_state == XFS_EXT_UNWRITTEN)
+			flags |= XFS_BMAPI_PREALLOC;
 		error = xfs_bmapi_remap(tp, bi->bi_owner, bmap->br_startoff,
 				bmap->br_blockcount, bmap->br_startblock,
 				flags);

[PATCH 1/4] xfs: move xfs_symlink_remote.c declarations to xfs_symlink_remote.h

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Move declarations for libxfs symlink functions into a separate header
file like we do for most everything else.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 include/libxfs.h            |    1 +
 libxfs/xfs_bmap.c           |    1 +
 libxfs/xfs_inode_fork.c     |    1 +
 libxfs/xfs_shared.h         |   13 -------------
 libxfs/xfs_symlink_remote.c |    2 +-
 libxfs/xfs_symlink_remote.h |   22 ++++++++++++++++++++++
 6 files changed, 26 insertions(+), 14 deletions(-)
 create mode 100644 libxfs/xfs_symlink_remote.h


diff --git a/include/libxfs.h b/include/libxfs.h
index 43fb5425796..16667b9d8b3 100644
--- a/include/libxfs.h
+++ b/include/libxfs.h
@@ -84,6 +84,7 @@ struct iomap;
 #include "xfs_refcount.h"
 #include "xfs_btree_staging.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_symlink_remote.h"
 
 #ifndef ARRAY_SIZE
 #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index d6cb466d63f..54db35bc398 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -32,6 +32,7 @@
 #include "xfs_rtbitmap.h"
 #include "xfs_health.h"
 #include "defer_item.h"
+#include "xfs_symlink_remote.h"
 
 struct kmem_cache		*xfs_bmap_intent_cache;
 
diff --git a/libxfs/xfs_inode_fork.c b/libxfs/xfs_inode_fork.c
index 5f45a1f1240..46da5edfb11 100644
--- a/libxfs/xfs_inode_fork.c
+++ b/libxfs/xfs_inode_fork.c
@@ -24,6 +24,7 @@
 #include "xfs_types.h"
 #include "xfs_errortag.h"
 #include "xfs_health.h"
+#include "xfs_symlink_remote.h"
 
 struct kmem_cache *xfs_ifork_cache;
 
diff --git a/libxfs/xfs_shared.h b/libxfs/xfs_shared.h
index 518ea9456eb..7509c1406a3 100644
--- a/libxfs/xfs_shared.h
+++ b/libxfs/xfs_shared.h
@@ -137,19 +137,6 @@ void	xfs_log_get_max_trans_res(struct xfs_mount *mp,
 #define	XFS_ICHGTIME_CHG	0x2	/* inode field change timestamp */
 #define	XFS_ICHGTIME_CREATE	0x4	/* inode create timestamp */
 
-
-/*
- * Symlink decoding/encoding functions
- */
-int xfs_symlink_blocks(struct xfs_mount *mp, int pathlen);
-int xfs_symlink_hdr_set(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
-			uint32_t size, struct xfs_buf *bp);
-bool xfs_symlink_hdr_ok(xfs_ino_t ino, uint32_t offset,
-			uint32_t size, struct xfs_buf *bp);
-void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
-				 struct xfs_inode *ip, struct xfs_ifork *ifp);
-xfs_failaddr_t xfs_symlink_shortform_verify(void *sfp, int64_t size);
-
 /* Computed inode geometry for the filesystem. */
 struct xfs_ino_geometry {
 	/* Maximum inode count in this filesystem. */
diff --git a/libxfs/xfs_symlink_remote.c b/libxfs/xfs_symlink_remote.c
index cf894b5276a..a989ce2f3f2 100644
--- a/libxfs/xfs_symlink_remote.c
+++ b/libxfs/xfs_symlink_remote.c
@@ -13,7 +13,7 @@
 #include "xfs_mount.h"
 #include "xfs_inode.h"
 #include "xfs_trans.h"
-
+#include "xfs_symlink_remote.h"
 
 /*
  * Each contiguous block has a header, so it is not just a simple pathlen
diff --git a/libxfs/xfs_symlink_remote.h b/libxfs/xfs_symlink_remote.h
new file mode 100644
index 00000000000..c6f621a0ec0
--- /dev/null
+++ b/libxfs/xfs_symlink_remote.h
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2000-2005 Silicon Graphics, Inc.
+ * Copyright (c) 2013 Red Hat, Inc.
+ * All Rights Reserved.
+ */
+#ifndef __XFS_SYMLINK_REMOTE_H
+#define __XFS_SYMLINK_REMOTE_H
+
+/*
+ * Symlink decoding/encoding functions
+ */
+int xfs_symlink_blocks(struct xfs_mount *mp, int pathlen);
+int xfs_symlink_hdr_set(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
+			uint32_t size, struct xfs_buf *bp);
+bool xfs_symlink_hdr_ok(xfs_ino_t ino, uint32_t offset,
+			uint32_t size, struct xfs_buf *bp);
+void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
+				 struct xfs_inode *ip, struct xfs_ifork *ifp);
+xfs_failaddr_t xfs_symlink_shortform_verify(void *sfp, int64_t size);
+
+#endif /* __XFS_SYMLINK_REMOTE_H */

[PATCH 2/4] xfs: move remote symlink target read function to libxfs

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Move xfs_readlink_bmap_ilocked to xfs_symlink_remote.c so that the
swapext code can use it to convert a remote format symlink back to
shortform format after a metadata repair.  While we're at it, fix a
broken printf prefix.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_symlink_remote.c |   77 +++++++++++++++++++++++++++++++++++++++++++
 libxfs/xfs_symlink_remote.h |    1 +
 2 files changed, 78 insertions(+)


diff --git a/libxfs/xfs_symlink_remote.c b/libxfs/xfs_symlink_remote.c
index a989ce2f3f2..8f251ae6799 100644
--- a/libxfs/xfs_symlink_remote.c
+++ b/libxfs/xfs_symlink_remote.c
@@ -14,6 +14,9 @@
 #include "xfs_inode.h"
 #include "xfs_trans.h"
 #include "xfs_symlink_remote.h"
+#include "xfs_bit.h"
+#include "xfs_bmap.h"
+#include "xfs_health.h"
 
 /*
  * Each contiguous block has a header, so it is not just a simple pathlen
@@ -224,3 +227,77 @@ xfs_symlink_shortform_verify(
 		return __this_address;
 	return NULL;
 }
+
+/* Read a remote symlink target into the buffer. */
+int
+xfs_symlink_remote_read(
+	struct xfs_inode	*ip,
+	char			*link)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_bmbt_irec	mval[XFS_SYMLINK_MAPS];
+	struct xfs_buf		*bp;
+	xfs_daddr_t		d;
+	char			*cur_chunk;
+	int			pathlen = ip->i_disk_size;
+	int			nmaps = XFS_SYMLINK_MAPS;
+	int			byte_cnt;
+	int			n;
+	int			error = 0;
+	int			fsblocks = 0;
+	int			offset;
+
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
+
+	fsblocks = xfs_symlink_blocks(mp, pathlen);
+	error = xfs_bmapi_read(ip, 0, fsblocks, mval, &nmaps, 0);
+	if (error)
+		goto out;
+
+	offset = 0;
+	for (n = 0; n < nmaps; n++) {
+		d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
+		byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
+
+		error = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt), 0,
+				&bp, &xfs_symlink_buf_ops);
+		if (xfs_metadata_is_sick(error))
+			xfs_inode_mark_sick(ip, XFS_SICK_INO_SYMLINK);
+		if (error)
+			return error;
+		byte_cnt = XFS_SYMLINK_BUF_SPACE(mp, byte_cnt);
+		if (pathlen < byte_cnt)
+			byte_cnt = pathlen;
+
+		cur_chunk = bp->b_addr;
+		if (xfs_has_crc(mp)) {
+			if (!xfs_symlink_hdr_ok(ip->i_ino, offset,
+							byte_cnt, bp)) {
+				xfs_inode_mark_sick(ip, XFS_SICK_INO_SYMLINK);
+				error = -EFSCORRUPTED;
+				xfs_alert(mp,
+"symlink header does not match required off/len/owner (0x%x/0x%x,0x%llx)",
+					offset, byte_cnt, ip->i_ino);
+				xfs_buf_relse(bp);
+				goto out;
+
+			}
+
+			cur_chunk += sizeof(struct xfs_dsymlink_hdr);
+		}
+
+		memcpy(link + offset, cur_chunk, byte_cnt);
+
+		pathlen -= byte_cnt;
+		offset += byte_cnt;
+
+		xfs_buf_relse(bp);
+	}
+	ASSERT(pathlen == 0);
+
+	link[ip->i_disk_size] = '\0';
+	error = 0;
+
+ out:
+	return error;
+}
diff --git a/libxfs/xfs_symlink_remote.h b/libxfs/xfs_symlink_remote.h
index c6f621a0ec0..bb83a8b8dfa 100644
--- a/libxfs/xfs_symlink_remote.h
+++ b/libxfs/xfs_symlink_remote.h
@@ -18,5 +18,6 @@ bool xfs_symlink_hdr_ok(xfs_ino_t ino, uint32_t offset,
 void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
 				 struct xfs_inode *ip, struct xfs_ifork *ifp);
 xfs_failaddr_t xfs_symlink_shortform_verify(void *sfp, int64_t size);
+int xfs_symlink_remote_read(struct xfs_inode *ip, char *link);
 
 #endif /* __XFS_SYMLINK_REMOTE_H */

[PATCH 3/4] xfs: move symlink target write function to libxfs

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Move xfs_symlink_write_target to xfs_symlink_remote.c so that kernel and
mkfs can share the same function.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_symlink_remote.c |   76 +++++++++++++++++++++++++++++++++++++++++++
 libxfs/xfs_symlink_remote.h |    3 ++
 2 files changed, 79 insertions(+)


diff --git a/libxfs/xfs_symlink_remote.c b/libxfs/xfs_symlink_remote.c
index 8f251ae6799..2f3aca8d02b 100644
--- a/libxfs/xfs_symlink_remote.c
+++ b/libxfs/xfs_symlink_remote.c
@@ -301,3 +301,79 @@ xfs_symlink_remote_read(
  out:
 	return error;
 }
+
+/* Write the symlink target into the inode. */
+int
+xfs_symlink_write_target(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	const char		*target_path,
+	int			pathlen,
+	xfs_fsblock_t		fs_blocks,
+	uint			resblks)
+{
+	struct xfs_bmbt_irec	mval[XFS_SYMLINK_MAPS];
+	struct xfs_mount	*mp = tp->t_mountp;
+	const char		*cur_chunk;
+	struct xfs_buf		*bp;
+	xfs_daddr_t		d;
+	int			byte_cnt;
+	int			nmaps;
+	int			offset = 0;
+	int			n;
+	int			error;
+
+	/*
+	 * If the symlink will fit into the inode, write it inline.
+	 */
+	if (pathlen <= xfs_inode_data_fork_size(ip)) {
+		xfs_init_local_fork(ip, XFS_DATA_FORK, target_path, pathlen);
+
+		ip->i_disk_size = pathlen;
+		ip->i_df.if_format = XFS_DINODE_FMT_LOCAL;
+		xfs_trans_log_inode(tp, ip, XFS_ILOG_DDATA | XFS_ILOG_CORE);
+		return 0;
+	}
+
+	nmaps = XFS_SYMLINK_MAPS;
+	error = xfs_bmapi_write(tp, ip, 0, fs_blocks, XFS_BMAPI_METADATA,
+			resblks, mval, &nmaps);
+	if (error)
+		return error;
+
+	ip->i_disk_size = pathlen;
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+	cur_chunk = target_path;
+	offset = 0;
+	for (n = 0; n < nmaps; n++) {
+		char	*buf;
+
+		d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
+		byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
+		error = xfs_trans_get_buf(tp, mp->m_ddev_targp, d,
+				BTOBB(byte_cnt), 0, &bp);
+		if (error)
+			return error;
+		bp->b_ops = &xfs_symlink_buf_ops;
+
+		byte_cnt = XFS_SYMLINK_BUF_SPACE(mp, byte_cnt);
+		byte_cnt = min(byte_cnt, pathlen);
+
+		buf = bp->b_addr;
+		buf += xfs_symlink_hdr_set(mp, ip->i_ino, offset, byte_cnt,
+				bp);
+
+		memcpy(buf, cur_chunk, byte_cnt);
+
+		cur_chunk += byte_cnt;
+		pathlen -= byte_cnt;
+		offset += byte_cnt;
+
+		xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SYMLINK_BUF);
+		xfs_trans_log_buf(tp, bp, 0, (buf + byte_cnt - 1) -
+						(char *)bp->b_addr);
+	}
+	ASSERT(pathlen == 0);
+	return 0;
+}
diff --git a/libxfs/xfs_symlink_remote.h b/libxfs/xfs_symlink_remote.h
index bb83a8b8dfa..a63bd38ae4f 100644
--- a/libxfs/xfs_symlink_remote.h
+++ b/libxfs/xfs_symlink_remote.h
@@ -19,5 +19,8 @@ void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
 				 struct xfs_inode *ip, struct xfs_ifork *ifp);
 xfs_failaddr_t xfs_symlink_shortform_verify(void *sfp, int64_t size);
 int xfs_symlink_remote_read(struct xfs_inode *ip, char *link);
+int xfs_symlink_write_target(struct xfs_trans *tp, struct xfs_inode *ip,
+		const char *target_path, int pathlen, xfs_fsblock_t fs_blocks,
+		uint resblks);
 
 #endif /* __XFS_SYMLINK_REMOTE_H */

[PATCH 4/4] mkfs: use libxfs to create symlinks

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Now that we've grabbed the kernel-side symlink writing function, use it
to create symbolic links from protofiles.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/libxfs_api_defs.h |    1 +
 mkfs/proto.c             |   72 ++++++++++++++++++++++++----------------------
 2 files changed, 39 insertions(+), 34 deletions(-)


diff --git a/libxfs/libxfs_api_defs.h b/libxfs/libxfs_api_defs.h
index 2a8e09db0bf..a5b3baaa476 100644
--- a/libxfs/libxfs_api_defs.h
+++ b/libxfs/libxfs_api_defs.h
@@ -228,6 +228,7 @@
 #define xfs_sb_version_to_features	libxfs_sb_version_to_features
 #define xfs_symlink_blocks		libxfs_symlink_blocks
 #define xfs_symlink_hdr_ok		libxfs_symlink_hdr_ok
+#define xfs_symlink_write_target	libxfs_symlink_write_target
 
 #define xfs_trans_add_item		libxfs_trans_add_item
 #define xfs_trans_alloc_empty		libxfs_trans_alloc_empty
diff --git a/mkfs/proto.c b/mkfs/proto.c
index f8e00c4b56f..0f2facbc32e 100644
--- a/mkfs/proto.c
+++ b/mkfs/proto.c
@@ -16,8 +16,6 @@ static char *getstr(char **pp);
 static void fail(char *msg, int i);
 static struct xfs_trans * getres(struct xfs_mount *mp, uint blocks);
 static void rsvfile(xfs_mount_t *mp, xfs_inode_t *ip, long long len);
-static int newfile(xfs_trans_t *tp, xfs_inode_t *ip, int symlink, int logit,
-			char *buf, int len);
 static char *newregfile(char **pp, int *len);
 static void rtinit(xfs_mount_t *mp);
 static void rtfreesp_init(struct xfs_mount *mp);
@@ -243,31 +241,42 @@ rsvfile(
 		fail(_("committing space for a file failed"), error);
 }
 
-static int
-newfile(
-	xfs_trans_t	*tp,
-	xfs_inode_t	*ip,
-	int		symlink,
-	int		logit,
-	char		*buf,
-	int		len)
+static void
+writesymlink(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	char			*buf,
+	int			len)
 {
-	struct xfs_buf	*bp;
-	xfs_daddr_t	d;
-	int		error;
-	int		flags;
-	xfs_bmbt_irec_t	map;
-	xfs_mount_t	*mp;
-	xfs_extlen_t	nb;
-	int		nmap;
+	struct xfs_mount	*mp = tp->t_mountp;
+	xfs_extlen_t		nb = XFS_B_TO_FSB(mp, len);
+	int			error;
+
+	error = -libxfs_symlink_write_target(tp, ip, buf, len, nb, nb);
+	if (error) {
+		fprintf(stderr,
+	_("%s: error %d creating symlink to '%s'.\n"), progname, error, buf);
+		exit(1);
+	}
+}
+
+static void
+writefile(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	char			*buf,
+	int			len)
+{
+	struct xfs_bmbt_irec	map;
+	struct xfs_mount	*mp;
+	struct xfs_buf		*bp;
+	xfs_daddr_t		d;
+	xfs_extlen_t		nb;
+	int			nmap;
+	int			error;
 
-	flags = 0;
 	mp = ip->i_mount;
-	if (symlink && len <= xfs_inode_data_fork_size(ip)) {
-		libxfs_init_local_fork(ip, XFS_DATA_FORK, buf, len);
-		ip->i_df.if_format = XFS_DINODE_FMT_LOCAL;
-		flags = XFS_ILOG_DDATA;
-	} else if (len > 0) {
+	if (len > 0) {
 		int	bcount;
 
 		nb = XFS_B_TO_FSB(mp, len);
@@ -289,7 +298,7 @@ newfile(
 			exit(1);
 		}
 		d = XFS_FSB_TO_DADDR(mp, map.br_startblock);
-		error = -libxfs_trans_get_buf(logit ? tp : NULL, mp->m_dev, d,
+		error = -libxfs_trans_get_buf(NULL, mp->m_dev, d,
 				nb << mp->m_blkbb_log, 0, &bp);
 		if (error) {
 			fprintf(stderr,
@@ -301,15 +310,10 @@ newfile(
 		bcount = BBTOB(bp->b_length);
 		if (len < bcount)
 			memset((char *)bp->b_addr + len, 0, bcount - len);
-		if (logit)
-			libxfs_trans_log_buf(tp, bp, 0, bcount - 1);
-		else {
-			libxfs_buf_mark_dirty(bp);
-			libxfs_buf_relse(bp);
-		}
+		libxfs_buf_mark_dirty(bp);
+		libxfs_buf_relse(bp);
 	}
 	ip->i_disk_size = len;
-	return flags;
 }
 
 static char *
@@ -491,7 +495,7 @@ parseproto(
 					   &creds, fsxp, &ip);
 		if (error)
 			fail(_("Inode allocation failed"), error);
-		flags |= newfile(tp, ip, 0, 0, buf, len);
+		writefile(tp, ip, buf, len);
 		if (buf)
 			free(buf);
 		libxfs_trans_ijoin(tp, pip, 0);
@@ -575,7 +579,7 @@ parseproto(
 				&creds, fsxp, &ip);
 		if (error)
 			fail(_("Inode allocation failed"), error);
-		flags |= newfile(tp, ip, 1, 1, buf, len);
+		writesymlink(tp, ip, buf, len);
 		libxfs_trans_ijoin(tp, pip, 0);
 		xname.type = XFS_DIR3_FT_SYMLINK;
 		newdirent(mp, tp, pip, &xname, ip->i_ino);

[PATCH 01/20] xfs: add a libxfs header file for staging new ioctls

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a new xfs_fs_staging.h header where we can land experimental
ioctls without committing them to any stable interfaces anywhere.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 include/libxfs.h        |    1 +
 include/xfs.h           |    1 +
 libxfs/Makefile         |    1 +
 libxfs/libxfs_priv.h    |    1 +
 libxfs/xfs_fs_staging.h |   18 ++++++++++++++++++
 5 files changed, 22 insertions(+)
 create mode 100644 libxfs/xfs_fs_staging.h


diff --git a/include/libxfs.h b/include/libxfs.h
index 16667b9d8b3..9e8596bedf9 100644
--- a/include/libxfs.h
+++ b/include/libxfs.h
@@ -27,6 +27,7 @@
 
 #include "xfs_types.h"
 #include "xfs_fs.h"
+#include "xfs_fs_staging.h"
 #include "xfs_arch.h"
 
 #include "xfs_shared.h"
diff --git a/include/xfs.h b/include/xfs.h
index e97158c8d22..c4a95bec9a9 100644
--- a/include/xfs.h
+++ b/include/xfs.h
@@ -44,5 +44,6 @@ extern int xfs_assert_largefile[sizeof(off_t)-8];
 /* Include deprecated/compat pre-vfs xfs-specific symbols */
 #include <xfs/xfs_fs_compat.h>
 #include <xfs/xfs_fs.h>
+#include <xfs/xfs_fs_staging.h>
 
 #endif	/* __XFS_H__ */
diff --git a/libxfs/Makefile b/libxfs/Makefile
index e1248c2b3ca..ed22f5c873e 100644
--- a/libxfs/Makefile
+++ b/libxfs/Makefile
@@ -14,6 +14,7 @@ LTLDFLAGS += -static
 
 # headers to install in include/xfs
 PKGHFILES = xfs_fs.h \
+	xfs_fs_staging.h \
 	xfs_types.h \
 	xfs_da_format.h \
 	xfs_format.h \
diff --git a/libxfs/libxfs_priv.h b/libxfs/libxfs_priv.h
index e3d9b70cc17..4d9c49091bc 100644
--- a/libxfs/libxfs_priv.h
+++ b/libxfs/libxfs_priv.h
@@ -60,6 +60,7 @@
 #include "xfs_arch.h"
 
 #include "xfs_fs.h"
+#include "xfs_fs_staging.h"
 #include "libfrog/crc32c.h"
 
 #include <sys/xattr.h>
diff --git a/libxfs/xfs_fs_staging.h b/libxfs/xfs_fs_staging.h
new file mode 100644
index 00000000000..d220790d5b5
--- /dev/null
+++ b/libxfs/xfs_fs_staging.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+/*
+ * Copyright (c) 2020-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_FS_STAGING_H__
+#define __XFS_FS_STAGING_H__
+
+/*
+ * Experimental system calls, ioctls and data structures supporting them.
+ * Nothing in here should be considered part of a stable interface of any kind.
+ *
+ * If you add an ioctl here, please leave a comment in xfs_fs.h marking it
+ * reserved.  If you promote anything out of this file, please leave a comment
+ * explaining where it went.
+ */
+
+#endif /* __XFS_FS_STAGING_H__ */

[PATCH 02/20] xfs: introduce new file range exchange ioctl

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Introduce a new ioctl to handle swapping ranges of bytes between files.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_fs.h                     |    1 
 libxfs/xfs_fs_staging.h             |   89 +++++++++++
 man/man2/ioctl_xfs_exchange_range.2 |  296 +++++++++++++++++++++++++++++++++++
 3 files changed, 386 insertions(+)
 create mode 100644 man/man2/ioctl_xfs_exchange_range.2


diff --git a/libxfs/xfs_fs.h b/libxfs/xfs_fs.h
index ca1b17d0143..ec92e6ded6b 100644
--- a/libxfs/xfs_fs.h
+++ b/libxfs/xfs_fs.h
@@ -843,6 +843,7 @@ struct xfs_scrub_metadata {
 #define XFS_IOC_FSGEOMETRY	     _IOR ('X', 126, struct xfs_fsop_geom)
 #define XFS_IOC_BULKSTAT	     _IOR ('X', 127, struct xfs_bulkstat_req)
 #define XFS_IOC_INUMBERS	     _IOR ('X', 128, struct xfs_inumbers_req)
+/*	XFS_IOC_EXCHANGE_RANGE -------- staging 129	 */
 /*	XFS_IOC_GETFSUUID ---------- deprecated 140	 */
 
 
diff --git a/libxfs/xfs_fs_staging.h b/libxfs/xfs_fs_staging.h
index d220790d5b5..e3d9f3b32b0 100644
--- a/libxfs/xfs_fs_staging.h
+++ b/libxfs/xfs_fs_staging.h
@@ -15,4 +15,93 @@
  * explaining where it went.
  */
 
+/*
+ * Exchange part of file1 with part of the file that this ioctl that is being
+ * called against (which we'll call file2).  Filesystems must be able to
+ * restart and complete the operation even after the system goes down.
+ */
+struct xfs_exch_range {
+	__s64		file1_fd;
+	__s64		file1_offset;	/* file1 offset, bytes */
+	__s64		file2_offset;	/* file2 offset, bytes */
+	__u64		length;		/* bytes to exchange */
+
+	__u64		flags;		/* see XFS_EXCH_RANGE_* below */
+
+	/* file2 metadata for optional freshness checks */
+	__s64		file2_ino;	/* inode number */
+	__s64		file2_mtime;	/* modification time */
+	__s64		file2_ctime;	/* change time */
+	__s32		file2_mtime_nsec; /* mod time, nsec */
+	__s32		file2_ctime_nsec; /* change time, nsec */
+
+	__u64		pad[6];		/* must be zeroes */
+};
+
+/*
+ * Atomic exchange operations are not required.  This relaxes the requirement
+ * that the filesystem must be able to complete the operation after a crash.
+ */
+#define XFS_EXCH_RANGE_NONATOMIC	(1 << 0)
+
+/*
+ * Check that file2's inode number, mtime, and ctime against the values
+ * provided, and return -EBUSY if there isn't an exact match.
+ */
+#define XFS_EXCH_RANGE_FILE2_FRESH	(1 << 1)
+
+/*
+ * Check that the file1's length is equal to file1_offset + length, and that
+ * file2's length is equal to file2_offset + length.  Returns -EDOM if there
+ * isn't an exact match.
+ */
+#define XFS_EXCH_RANGE_FULL_FILES	(1 << 2)
+
+/*
+ * Exchange file data all the way to the ends of both files, and then exchange
+ * the file sizes.  This flag can be used to replace a file's contents with a
+ * different amount of data.  length will be ignored.
+ */
+#define XFS_EXCH_RANGE_TO_EOF		(1 << 3)
+
+/* Flush all changes in file data and file metadata to disk before returning. */
+#define XFS_EXCH_RANGE_FSYNC		(1 << 4)
+
+/* Dry run; do all the parameter verification but do not change anything. */
+#define XFS_EXCH_RANGE_DRY_RUN		(1 << 5)
+
+/*
+ * Exchange only the parts of the two files where the file allocation units
+ * mapped to file1's range have been written to.  This can accelerate
+ * scatter-gather atomic writes with a temp file if all writes are aligned to
+ * the file allocation unit.
+ */
+#define XFS_EXCH_RANGE_FILE1_WRITTEN	(1 << 6)
+
+/*
+ * Commit the contents of file1 into file2 if file2 has the same inode number,
+ * mtime, and ctime as the arguments provided to the call.  The old contents of
+ * file2 will be moved to file1.
+ *
+ * With this flag, all committed information can be retrieved even if the
+ * system crashes or is rebooted.  This includes writing through or flushing a
+ * disk cache if present.  The call blocks until the device reports that the
+ * commit is complete.
+ *
+ * This flag should not be combined with NONATOMIC.  It can be combined with
+ * FILE1_WRITTEN.
+ */
+#define XFS_EXCH_RANGE_COMMIT		(XFS_EXCH_RANGE_FILE2_FRESH | \
+					 XFS_EXCH_RANGE_FSYNC)
+
+#define XFS_EXCH_RANGE_ALL_FLAGS	(XFS_EXCH_RANGE_NONATOMIC | \
+					 XFS_EXCH_RANGE_FILE2_FRESH | \
+					 XFS_EXCH_RANGE_FULL_FILES | \
+					 XFS_EXCH_RANGE_TO_EOF | \
+					 XFS_EXCH_RANGE_FSYNC | \
+					 XFS_EXCH_RANGE_DRY_RUN | \
+					 XFS_EXCH_RANGE_FILE1_WRITTEN)
+
+#define XFS_IOC_EXCHANGE_RANGE	_IOWR('X', 129, struct xfs_exch_range)
+
 #endif /* __XFS_FS_STAGING_H__ */
diff --git a/man/man2/ioctl_xfs_exchange_range.2 b/man/man2/ioctl_xfs_exchange_range.2
new file mode 100644
index 00000000000..a292d8e9641
--- /dev/null
+++ b/man/man2/ioctl_xfs_exchange_range.2
@@ -0,0 +1,296 @@
+.\" Copyright (c) 2020-2024 Oracle.  All rights reserved.
+.\"
+.\" %%%LICENSE_START(GPLv2+_DOC_FULL)
+.\" This is free documentation; you can redistribute it and/or
+.\" modify it under the terms of the GNU General Public License as
+.\" published by the Free Software Foundation; either version 2 of
+.\" the License, or (at your option) any later version.
+.\"
+.\" The GNU General Public License's references to "object code"
+.\" and "executables" are to be interpreted as the output of any
+.\" document formatting or typesetting system, including
+.\" intermediate and printed output.
+.\"
+.\" This manual is distributed in the hope that it will be useful,
+.\" but WITHOUT ANY WARRANTY; without even the implied warranty of
+.\" MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+.\" GNU General Public License for more details.
+.\"
+.\" You should have received a copy of the GNU General Public
+.\" License along with this manual; if not, see
+.\" <http://www.gnu.org/licenses/>.
+.\" %%%LICENSE_END
+.TH IOCTL-XFS-EXCHANGE-RANGE 2  2023-05-08 "XFS"
+.SH NAME
+ioctl_xfs_exchange_range \- exchange the contents of parts of two files
+.SH SYNOPSIS
+.br
+.B #include <sys/ioctl.h>
+.br
+.B #include <xfs/xfs_fs_staging.h>
+.PP
+.BI "int ioctl(int " file2_fd ", XFS_IOC_EXCHANGE_RANGE, struct xfs_exch_range *" arg );
+.SH DESCRIPTION
+Given a range of bytes in a first file
+.B file1_fd
+and a second range of bytes in a second file
+.BR file2_fd ,
+this
+.BR ioctl (2)
+exchanges the contents of the two ranges.
+.PP
+Exchanges are atomic with regards to concurrent file operations, so no
+userspace-level locks need to be taken to obtain consistent results.
+Implementations must guarantee that readers see either the old contents or the
+new contents in their entirety, even if the system fails.
+.PP
+The exchange parameters are conveyed in a structure of the following form:
+.PP
+.in +4n
+.EX
+struct xfs_exch_range {
+    __s64    file1_fd;
+    __s64    file1_offset;
+    __s64    file2_offset;
+    __s64    length;
+
+    __u64    flags;
+
+    __s64    file2_ino;
+    __s64    file2_mtime;
+    __s64    file2_ctime;
+    __s32    file2_mtime_nsec;
+    __s32    file2_ctime_nsec;
+
+    __u64    pad[6];
+};
+.EE
+.in
+.PP
+The field
+.I pad
+must be zero.
+.PP
+The fields
+.IR file1_fd ", " file1_offset ", and " length
+define the first range of bytes to be exchanged.
+.PP
+The fields
+.IR file2_fd ", " file2_offset ", and " length
+define the second range of bytes to be exchanged.
+.PP
+Both files must be from the same filesystem mount.
+If the two file descriptors represent the same file, the byte ranges must not
+overlap.
+Most disk-based filesystems require that the starts of both ranges must be
+aligned to the file block size.
+If this is the case, the ends of the ranges must also be so aligned unless the
+.B XFS_EXCH_RANGE_TO_EOF
+flag is set.
+
+.PP
+The field
+.I flags
+control the behavior of the exchange operation.
+.RS 0.4i
+.TP
+.B XFS_EXCH_RANGE_FILE2_FRESH
+Check the freshness of
+.I file2_fd
+after locking the file but before exchanging the contents.
+The supplied
+.IR file2_ino " field"
+must match file2's inode number, and the supplied
+.IR file2_mtime ", " file2_mtime_nsec ", " file2_ctime ", and " file2_ctime_nsec
+fields must match the modification time and change time of file2.
+If they do not match,
+.B EBUSY
+will be returned.
+.TP
+.B XFS_EXCH_RANGE_TO_EOF
+Ignore the
+.I length
+parameter.
+All bytes in
+.I file1_fd
+from
+.I file1_offset
+to EOF are moved to
+.IR file2_fd ,
+and file2's size is set to
+.RI ( file2_offset "+(" file1_length - file1_offset )).
+Meanwhile, all bytes in file2 from
+.I file2_offset
+to EOF are moved to file1 and file1's size is set to
+.RI ( file1_offset "+(" file2_length - file2_offset )).
+This option is not compatible with
+.BR XFS_EXCH_RANGE_FULL_FILES .
+.TP
+.B XFS_EXCH_RANGE_FSYNC
+Ensure that all modified in-core data in both file ranges and all metadata
+updates pertaining to the exchange operation are flushed to persistent storage
+before the call returns.
+Opening either file descriptor with
+.BR O_SYNC " or " O_DSYNC
+will have the same effect.
+.TP
+.B XFS_EXCH_RANGE_FILE1_WRITTEN
+Only exchange sub-ranges of
+.I file1_fd
+that are known to contain data written by application software.
+Each sub-range may be expanded (both upwards and downwards) to align with the
+file allocation unit.
+For files on the data device, this is one filesystem block.
+For files on the realtime device, this is the realtime extent size.
+This facility can be used to implement fast atomic scatter-gather writes of any
+complexity for software-defined storage targets if all writes are aligned to
+the file allocation unit.
+.TP
+.B XFS_EXCH_RANGE_DRY_RUN
+Check the parameters and the feasibility of the operation, but do not change
+anything.
+.TP
+.B XFS_EXCH_RANGE_COMMIT
+This flag is a combination of
+.BR XFS_EXCH_RANGE_FILE2_FRESH " | " XFS_EXCH_RANGE_FSYNC
+and can be used to commit changes to
+.I file2_fd
+to persistent storage if and only if file2 has not changed.
+.TP
+.B XFS_EXCH_RANGE_FULL_FILES
+Require that
+.IR file1_offset " and " file2_offset
+are zero, and that the
+.I length
+field matches the lengths of both files.
+If not,
+.B EDOM
+will be returned.
+This option is not compatible with
+.BR XFS_EXCH_RANGE_TO_EOF .
+.TP
+.B XFS_EXCH_RANGE_NONATOMIC
+This flag relaxes the requirement that readers see only the old contents or
+the new contents in their entirety.
+If the system fails before all modified in-core data and metadata updates
+are persisted to disk, the contents of both file ranges after recovery are not
+defined and may be a mix of both.
+
+Do not use this flag unless the contents of both ranges are known to be
+identical and there are no other writers.
+.RE
+.PP
+.SH RETURN VALUE
+On error, \-1 is returned, and
+.I errno
+is set to indicate the error.
+.PP
+.SH ERRORS
+Error codes can be one of, but are not limited to, the following:
+.TP
+.B EBADF
+.IR file1_fd
+is not open for reading and writing or is open for append-only writes; or
+.IR file2_fd
+is not open for reading and writing or is open for append-only writes.
+.TP
+.B EBUSY
+The inode number and timestamps supplied do not match
+.IR file2_fd
+and
+.B XFS_EXCH_RANGE_FILE2_FRESH
+was set in
+.IR flags .
+.TP
+.B EDOM
+The ranges do not cover the entirety of both files, and
+.B XFS_EXCH_RANGE_FULL_FILES
+was set in
+.IR flags .
+.TP
+.B EINVAL
+The parameters are not correct for these files.
+This error can also appear if either file descriptor represents
+a device, FIFO, or socket.
+Disk filesystems generally require the offset and length arguments
+to be aligned to the fundamental block sizes of both files.
+.TP
+.B EIO
+An I/O error occurred.
+.TP
+.B EISDIR
+One of the files is a directory.
+.TP
+.B ENOMEM
+The kernel was unable to allocate sufficient memory to perform the
+operation.
+.TP
+.B ENOSPC
+There is not enough free space in the filesystem exchange the contents safely.
+.TP
+.B EOPNOTSUPP
+The filesystem does not support exchanging bytes between the two
+files.
+.TP
+.B EPERM
+.IR file1_fd " or " file2_fd
+are immutable.
+.TP
+.B ETXTBSY
+One of the files is a swap file.
+.TP
+.B EUCLEAN
+The filesystem is corrupt.
+.TP
+.B EXDEV
+.IR file1_fd " and " file2_fd
+are not on the same mounted filesystem.
+.SH CONFORMING TO
+This API is XFS-specific.
+.SH USE CASES
+.PP
+Three use cases are imagined for this system call.
+.PP
+The first is a filesystem defragmenter, which copies the contents of a file
+into another file and wishes to exchange the space mappings of the two files,
+provided that the original file has not changed.  The flags
+.BR NONATOMIC " and " FILE2_FRESH
+are recommended for this application.
+.PP
+The second is a data storage program that wants to commit non-contiguous updates
+to a file atomically.  This can be done by creating a temporary file, calling
+.BR FICLONE (2)
+to share the contents, and staging the updates into the temporary file.
+Either of the
+.BR FULL_FILES " or " TO_EOF
+flags are recommended, along with
+.BR FSYNC .
+Depending on the application's locking design, the flags
+.BR FILE2_FRESH " or " COMMIT
+may be applicable here.
+The temporary file can be deleted or punched out afterwards.
+.PP
+The third is a software-defined storage host (e.g. a disk jukebox) which
+implements an atomic scatter-gather write command.
+Provided the exported disk's logical block size matches the file's allocation
+unit size, this can be done by creating a temporary file and writing the data
+at the appropriate offsets.
+It is recommended that the temporary file be truncated to the size of the
+regular file before any writes are staged to the temporary file to avoid issues
+with zeroing during EOF extension.
+Use this call with the
+.B FILE1_WRITTEN
+flag to exchange only the file allocation units involved in the emulated
+device's write command.
+The use of the
+.B FSYNC
+flag is recommended here.
+The temporary file should be deleted or punched out completely before being
+reused to stage another write.
+.B
+.SH NOTES
+.PP
+Some filesystems may limit the amount of data or the number of extents that can
+be exchanged in a single call.
+.SH SEE ALSO
+.BR ioctl (2)

[PATCH 03/20] xfs: parameterize all the incompat log feature helpers

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

We're about to define a new XFS_SB_FEAT_INCOMPAT_LOG_ bit, which means
that callers will soon require the ability to toggle on and off
different log incompat feature bits.  Parameterize the
xlog_{use,drop}_incompat_feat and xfs_sb_remove_incompat_log_features
functions so that callers can specify which feature they're trying to
use and so that we can clear individual log incompat bits as needed.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_format.h |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)


diff --git a/libxfs/xfs_format.h b/libxfs/xfs_format.h
index e6ca188e227..4baafff6197 100644
--- a/libxfs/xfs_format.h
+++ b/libxfs/xfs_format.h
@@ -404,9 +404,10 @@ xfs_sb_has_incompat_log_feature(
 
 static inline void
 xfs_sb_remove_incompat_log_features(
-	struct xfs_sb	*sbp)
+	struct xfs_sb	*sbp,
+	uint32_t	feature)
 {
-	sbp->sb_features_log_incompat &= ~XFS_SB_FEAT_INCOMPAT_LOG_ALL;
+	sbp->sb_features_log_incompat &= ~feature;
 }
 
 static inline void

[PATCH 04/20] xfs: create a log incompat flag for atomic extent swapping

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a log incompat flag so that we only attempt to process swap
extent log items if the filesystem supports it, and a geometry flag to
advertise support if it's present.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_format.h             |    6 +++
 libxfs/xfs_fs.h                 |    3 ++
 libxfs/xfs_sb.c                 |    3 ++
 libxfs/xfs_swapext.h            |   75 +++++++++++++++++++++++++++++++++++++++
 man/man2/ioctl_xfs_fsgeometry.2 |    3 ++
 5 files changed, 90 insertions(+)
 create mode 100644 libxfs/xfs_swapext.h


diff --git a/libxfs/xfs_format.h b/libxfs/xfs_format.h
index 4baafff6197..c0209bd21db 100644
--- a/libxfs/xfs_format.h
+++ b/libxfs/xfs_format.h
@@ -391,6 +391,12 @@ xfs_sb_has_incompat_feature(
 }
 
 #define XFS_SB_FEAT_INCOMPAT_LOG_XATTRS   (1 << 0)	/* Delayed Attributes */
+
+/*
+ * Log contains SXI log intent items which are not otherwise protected by
+ * an INCOMPAT/RO_COMPAT feature flag.
+ */
+#define XFS_SB_FEAT_INCOMPAT_LOG_SWAPEXT  (1U << 31)
 #define XFS_SB_FEAT_INCOMPAT_LOG_ALL \
 	(XFS_SB_FEAT_INCOMPAT_LOG_XATTRS)
 #define XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN	~XFS_SB_FEAT_INCOMPAT_LOG_ALL
diff --git a/libxfs/xfs_fs.h b/libxfs/xfs_fs.h
index ec92e6ded6b..63a145e5035 100644
--- a/libxfs/xfs_fs.h
+++ b/libxfs/xfs_fs.h
@@ -240,6 +240,9 @@ typedef struct xfs_fsop_resblks {
 #define XFS_FSOP_GEOM_FLAGS_INOBTCNT	(1 << 22) /* inobt btree counter */
 #define XFS_FSOP_GEOM_FLAGS_NREXT64	(1 << 23) /* large extent counters */
 
+/* atomic file extent swap available to userspace */
+#define XFS_FSOP_GEOM_FLAGS_ATOMIC_SWAP	(1U << 31)
+
 /*
  * Minimum and maximum sizes need for growth checks.
  *
diff --git a/libxfs/xfs_sb.c b/libxfs/xfs_sb.c
index 30a6bc07d88..fd017d18cda 100644
--- a/libxfs/xfs_sb.c
+++ b/libxfs/xfs_sb.c
@@ -24,6 +24,7 @@
 #include "xfs_health.h"
 #include "xfs_ag.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_swapext.h"
 
 /*
  * Physical superblock buffer manipulations. Shared with libxfs in userspace.
@@ -1256,6 +1257,8 @@ xfs_fs_geometry(
 	}
 	if (xfs_has_large_extent_counts(mp))
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_NREXT64;
+	if (xfs_atomic_swap_supported(mp))
+		geo->flags |= XFS_FSOP_GEOM_FLAGS_ATOMIC_SWAP;
 	geo->rtsectsize = sbp->sb_blocksize;
 	geo->dirblocksize = xfs_dir2_dirblock_bytes(sbp);
 
diff --git a/libxfs/xfs_swapext.h b/libxfs/xfs_swapext.h
new file mode 100644
index 00000000000..01bb3271f64
--- /dev/null
+++ b/libxfs/xfs_swapext.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2020-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_SWAPEXT_H_
+#define __XFS_SWAPEXT_H_ 1
+
+/*
+ * Decide if this filesystem supports the minimum feature set required to use
+ * the swapext iteration code in non-atomic swap mode.  This mode uses the
+ * BUI log items introduced for the rmapbt and reflink features, but does not
+ * use swapext log items to track progress over a file range.
+ */
+static inline bool
+xfs_swapext_supports_nonatomic(
+	struct xfs_mount	*mp)
+{
+	return xfs_has_reflink(mp) || xfs_has_rmapbt(mp);
+}
+
+/*
+ * Decide if this filesystem has a new enough permanent feature set to protect
+ * swapext log items from being replayed on a kernel that does not have
+ * XFS_SB_FEAT_INCOMPAT_LOG_SWAPEXT set.
+ */
+static inline bool
+xfs_swapext_can_use_without_log_assistance(
+	struct xfs_mount	*mp)
+{
+	if (!xfs_sb_is_v5(&mp->m_sb))
+		return false;
+
+	if (xfs_sb_has_incompat_feature(&mp->m_sb,
+				~(XFS_SB_FEAT_INCOMPAT_FTYPE |
+				  XFS_SB_FEAT_INCOMPAT_SPINODES |
+				  XFS_SB_FEAT_INCOMPAT_META_UUID |
+				  XFS_SB_FEAT_INCOMPAT_BIGTIME |
+				  XFS_SB_FEAT_INCOMPAT_NREXT64)))
+		return true;
+
+	return false;
+}
+
+/*
+ * Decide if atomic extent swapping could be used on this filesystem.  This
+ * does not say anything about the filesystem's readiness to do that.
+ */
+static inline bool
+xfs_atomic_swap_supported(
+	struct xfs_mount	*mp)
+{
+	/*
+	 * In theory, we could support atomic extent swapping by setting
+	 * XFS_SB_FEAT_INCOMPAT_LOG_SWAPEXT on any filesystem and that would be
+	 * sufficient to protect the swapext log items that would be created.
+	 * However, we don't want to enable new features on a really old
+	 * filesystem, so we'll only advertise atomic swap support on the ones
+	 * that support BUI log items.
+	 */
+	if (xfs_swapext_supports_nonatomic(mp))
+		return true;
+
+	/*
+	 * If the filesystem has an RO_COMPAT or INCOMPAT bit that we don't
+	 * recognize, then it's new enough not to need INCOMPAT_LOG_SWAPEXT
+	 * to protect swapext log items.
+	 */
+	if (xfs_swapext_can_use_without_log_assistance(mp))
+		return true;
+
+	return false;
+}
+
+#endif /* __XFS_SWAPEXT_H_ */
diff --git a/man/man2/ioctl_xfs_fsgeometry.2 b/man/man2/ioctl_xfs_fsgeometry.2
index f59a6e8a6a2..4c7ff9a270b 100644
--- a/man/man2/ioctl_xfs_fsgeometry.2
+++ b/man/man2/ioctl_xfs_fsgeometry.2
@@ -211,6 +211,9 @@ Filesystem stores reverse mappings of blocks to owners.
 .TP
 .B XFS_FSOP_GEOM_FLAGS_REFLINK
 Filesystem supports sharing blocks between files.
+.TP
+.B XFS_FSOP_GEOM_FLAGS_ATOMICSWAP
+Filesystem can exchange file contents atomically via XFS_IOC_EXCHANGE_RANGE.
 .RE
 .SH XFS METADATA HEALTH REPORTING
 .PP

[PATCH 05/20] xfs: introduce a swap-extent log intent item

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Introduce a new intent log item to handle swapping extents.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_log_format.h |   51 ++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 48 insertions(+), 3 deletions(-)


diff --git a/libxfs/xfs_log_format.h b/libxfs/xfs_log_format.h
index 16872972e1e..24c3d5dc361 100644
--- a/libxfs/xfs_log_format.h
+++ b/libxfs/xfs_log_format.h
@@ -117,8 +117,9 @@ struct xfs_unmount_log_format {
 #define XLOG_REG_TYPE_ATTRD_FORMAT	28
 #define XLOG_REG_TYPE_ATTR_NAME	29
 #define XLOG_REG_TYPE_ATTR_VALUE	30
-#define XLOG_REG_TYPE_MAX		30
-
+#define XLOG_REG_TYPE_SXI_FORMAT	31
+#define XLOG_REG_TYPE_SXD_FORMAT	32
+#define XLOG_REG_TYPE_MAX		32
 
 /*
  * Flags to log operation header
@@ -243,6 +244,8 @@ typedef struct xfs_trans_header {
 #define	XFS_LI_BUD		0x1245
 #define	XFS_LI_ATTRI		0x1246  /* attr set/remove intent*/
 #define	XFS_LI_ATTRD		0x1247  /* attr set/remove done */
+#define	XFS_LI_SXI		0x1248  /* extent swap intent */
+#define	XFS_LI_SXD		0x1249  /* extent swap done */
 
 #define XFS_LI_TYPE_DESC \
 	{ XFS_LI_EFI,		"XFS_LI_EFI" }, \
@@ -260,7 +263,9 @@ typedef struct xfs_trans_header {
 	{ XFS_LI_BUI,		"XFS_LI_BUI" }, \
 	{ XFS_LI_BUD,		"XFS_LI_BUD" }, \
 	{ XFS_LI_ATTRI,		"XFS_LI_ATTRI" }, \
-	{ XFS_LI_ATTRD,		"XFS_LI_ATTRD" }
+	{ XFS_LI_ATTRD,		"XFS_LI_ATTRD" }, \
+	{ XFS_LI_SXI,		"XFS_LI_SXI" }, \
+	{ XFS_LI_SXD,		"XFS_LI_SXD" }
 
 /*
  * Inode Log Item Format definitions.
@@ -878,6 +883,46 @@ struct xfs_bud_log_format {
 	uint64_t		bud_bui_id;	/* id of corresponding bui */
 };
 
+/*
+ * SXI/SXD (extent swapping) log format definitions
+ */
+
+struct xfs_swap_extent {
+	uint64_t		sx_inode1;
+	uint64_t		sx_inode2;
+	uint64_t		sx_startoff1;
+	uint64_t		sx_startoff2;
+	uint64_t		sx_blockcount;
+	uint64_t		sx_flags;
+	int64_t			sx_isize1;
+	int64_t			sx_isize2;
+};
+
+#define XFS_SWAP_EXT_FLAGS		(0)
+
+#define XFS_SWAP_EXT_STRINGS
+
+/* This is the structure used to lay out an sxi log item in the log. */
+struct xfs_sxi_log_format {
+	uint16_t		sxi_type;	/* sxi log item type */
+	uint16_t		sxi_size;	/* size of this item */
+	uint32_t		__pad;		/* must be zero */
+	uint64_t		sxi_id;		/* sxi identifier */
+	struct xfs_swap_extent	sxi_extent;	/* extent to swap */
+};
+
+/*
+ * This is the structure used to lay out an sxd log item in the
+ * log.  The sxd_extents array is a variable size array whose
+ * size is given by sxd_nextents;
+ */
+struct xfs_sxd_log_format {
+	uint16_t		sxd_type;	/* sxd log item type */
+	uint16_t		sxd_size;	/* size of this item */
+	uint32_t		__pad;
+	uint64_t		sxd_sxi_id;	/* id of corresponding bui */
+};
+
 /*
  * Dquot Log format definitions.
  *

[PATCH 06/20] xfs: create deferred log items for extent swapping

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Now that we've created the skeleton of a log intent item to track and
restart extent swap operations, add the upper level logic to commit
intent items and turn them into concrete work recorded in the log.  We
use the deferred item "multihop" feature that was introduced a few
patches ago to constrain the number of active swap operations to one per
thread.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 include/xfs_trace.h      |   14 +
 libxfs/Makefile          |    2 
 libxfs/defer_item.c      |   91 ++++
 libxfs/defer_item.h      |    4 
 libxfs/libxfs_priv.h     |   30 +
 libxfs/xfs_bmap.h        |    2 
 libxfs/xfs_defer.c       |    6 
 libxfs/xfs_defer.h       |    2 
 libxfs/xfs_format.h      |    6 
 libxfs/xfs_log_format.h  |   31 +
 libxfs/xfs_swapext.c     | 1028 ++++++++++++++++++++++++++++++++++++++++++++++
 libxfs/xfs_swapext.h     |  143 ++++++
 libxfs/xfs_trans_space.h |    4 
 13 files changed, 1359 insertions(+), 4 deletions(-)
 create mode 100644 libxfs/xfs_swapext.c


diff --git a/include/xfs_trace.h b/include/xfs_trace.h
index 57661f36d7c..a8f3ecac7f6 100644
--- a/include/xfs_trace.h
+++ b/include/xfs_trace.h
@@ -329,6 +329,9 @@
 #define trace_xfs_refcount_cow_decrease(...)	((void) 0)
 #define trace_xfs_refcount_recover_extent(...)	((void) 0)
 
+#define trace_xfs_reflink_set_inode_flag(...)	((void) 0)
+#define trace_xfs_reflink_unset_inode_flag(...)	((void) 0)
+
 #define trace_xfs_rmap_find_left_neighbor_candidate(...)	((void) 0)
 #define trace_xfs_rmap_find_left_neighbor_query(...)	((void) 0)
 #define trace_xfs_rmap_find_left_neighbor_result(...)	((void) 0)
@@ -342,6 +345,17 @@
 #define trace_xfs_rmap_map_error(...)		((void) 0)
 #define trace_xfs_rmap_delete_error(...)	((void) 0)
 
+#define trace_xfs_swapext_defer(...)		((void) 0)
+#define trace_xfs_swapext_delta_nextents(...)	((void) 0)
+#define trace_xfs_swapext_delta_nextents_step(...)	((void) 0)
+#define trace_xfs_swapext_extent1_skip(...)	((void) 0)
+#define trace_xfs_swapext_extent1(...)		((void) 0)
+#define trace_xfs_swapext_extent2(...)		((void) 0)
+#define trace_xfs_swapext_final_estimate(...)	((void) 0)
+#define trace_xfs_swapext_initial_estimate(...)	((void) 0)
+#define trace_xfs_swapext_overhead(...)		((void) 0)
+#define trace_xfs_swapext_update_inode_size(...) ((void) 0)
+
 #define trace_xfs_fs_mark_healthy(a,b)		((void) 0)
 
 #define trace_xlog_intent_recovery_failed(...)	((void) 0)
diff --git a/libxfs/Makefile b/libxfs/Makefile
index ed22f5c873e..0fb8f7b39bc 100644
--- a/libxfs/Makefile
+++ b/libxfs/Makefile
@@ -58,6 +58,7 @@ HFILES = \
 	xfs_rtbitmap.h \
 	xfs_sb.h \
 	xfs_shared.h \
+	xfs_swapext.h \
 	xfs_trans_resv.h \
 	xfs_trans_space.h \
 	xfs_dir2_priv.h
@@ -106,6 +107,7 @@ CFILES = cache.c \
 	xfs_rmap_btree.c \
 	xfs_rtbitmap.c \
 	xfs_sb.c \
+	xfs_swapext.c \
 	xfs_symlink_remote.c \
 	xfs_trans_inode.c \
 	xfs_trans_resv.c \
diff --git a/libxfs/defer_item.c b/libxfs/defer_item.c
index e7d64be014d..49e6cf02dc8 100644
--- a/libxfs/defer_item.c
+++ b/libxfs/defer_item.c
@@ -25,6 +25,8 @@
 #include "xfs_attr.h"
 #include "libxfs.h"
 #include "defer_item.h"
+#include "xfs_ag.h"
+#include "xfs_swapext.h"
 
 /* Dummy defer item ops, since we don't do logging. */
 
@@ -677,3 +679,92 @@ const struct xfs_defer_op_type xfs_attr_defer_type = {
 	.finish_item	= xfs_attr_finish_item,
 	.cancel_item	= xfs_attr_cancel_item,
 };
+
+/* Atomic Swapping of File Ranges */
+
+STATIC struct xfs_log_item *
+xfs_swapext_create_intent(
+	struct xfs_trans		*tp,
+	struct list_head		*items,
+	unsigned int			count,
+	bool				sort)
+{
+	return NULL;
+}
+STATIC struct xfs_log_item *
+xfs_swapext_create_done(
+	struct xfs_trans		*tp,
+	struct xfs_log_item		*intent,
+	unsigned int			count)
+{
+	return NULL;
+}
+
+/* Add this deferred SXI to the transaction. */
+void
+xfs_swapext_defer_add(
+	struct xfs_trans		*tp,
+	struct xfs_swapext_intent	*sxi)
+{
+	trace_xfs_swapext_defer(tp->t_mountp, sxi);
+
+	xfs_defer_add(tp, &sxi->sxi_list, &xfs_swapext_defer_type);
+}
+
+static inline struct xfs_swapext_intent *sxi_entry(const struct list_head *e)
+{
+	return list_entry(e, struct xfs_swapext_intent, sxi_list);
+}
+
+/* Process a deferred swapext update. */
+STATIC int
+xfs_swapext_finish_item(
+	struct xfs_trans		*tp,
+	struct xfs_log_item		*done,
+	struct list_head		*item,
+	struct xfs_btree_cur		**state)
+{
+	struct xfs_swapext_intent	*sxi = sxi_entry(item);
+	int				error;
+
+	/*
+	 * Swap one more extent between the two files.  If there's still more
+	 * work to do, we want to requeue ourselves after all other pending
+	 * deferred operations have finished.  This includes all of the dfops
+	 * that we queued directly as well as any new ones created in the
+	 * process of finishing the others.  Doing so prevents us from queuing
+	 * a large number of SXI log items in kernel memory, which in turn
+	 * prevents us from pinning the tail of the log (while logging those
+	 * new SXI items) until the first SXI items can be processed.
+	 */
+	error = xfs_swapext_finish_one(tp, sxi);
+	if (error != -EAGAIN)
+		kmem_cache_free(xfs_swapext_intent_cache, sxi);
+	return error;
+}
+
+/* Abort all pending SXIs. */
+STATIC void
+xfs_swapext_abort_intent(
+	struct xfs_log_item		*intent)
+{
+}
+
+/* Cancel a deferred swapext update. */
+STATIC void
+xfs_swapext_cancel_item(
+	struct list_head		*item)
+{
+	struct xfs_swapext_intent	*sxi = sxi_entry(item);
+
+	kmem_cache_free(xfs_swapext_intent_cache, sxi);
+}
+
+const struct xfs_defer_op_type xfs_swapext_defer_type = {
+	.name		= "swapext",
+	.create_intent	= xfs_swapext_create_intent,
+	.abort_intent	= xfs_swapext_abort_intent,
+	.create_done	= xfs_swapext_create_done,
+	.finish_item	= xfs_swapext_finish_item,
+	.cancel_item	= xfs_swapext_cancel_item,
+};
diff --git a/libxfs/defer_item.h b/libxfs/defer_item.h
index 6d3abf1589c..a3ef9e079d0 100644
--- a/libxfs/defer_item.h
+++ b/libxfs/defer_item.h
@@ -10,4 +10,8 @@ struct xfs_bmap_intent;
 
 void xfs_bmap_defer_add(struct xfs_trans *tp, struct xfs_bmap_intent *bi);
 
+struct xfs_swapext_intent;
+
+void xfs_swapext_defer_add(struct xfs_trans *tp, struct xfs_swapext_intent *sxi);
+
 #endif /* __LIBXFS_DEFER_ITEM_H_ */
diff --git a/libxfs/libxfs_priv.h b/libxfs/libxfs_priv.h
index 4d9c49091bc..ef29d7e5eb7 100644
--- a/libxfs/libxfs_priv.h
+++ b/libxfs/libxfs_priv.h
@@ -220,6 +220,35 @@ static inline bool WARN_ON(bool expr) {
 	(inode)->i_version = (version);	\
 } while (0)
 
+#define __must_check	__attribute__((__warn_unused_result__))
+
+/*
+ * Allows for effectively applying __must_check to a macro so we can have
+ * both the type-agnostic benefits of the macros while also being able to
+ * enforce that the return value is, in fact, checked.
+ */
+static inline bool __must_check __must_check_overflow(bool overflow)
+{
+	return unlikely(overflow);
+}
+
+/*
+ * For simplicity and code hygiene, the fallback code below insists on
+ * a, b and *d having the same type (similar to the min() and max()
+ * macros), whereas gcc's type-generic overflow checkers accept
+ * different types. Hence we don't just make check_add_overflow an
+ * alias for __builtin_add_overflow, but add type checks similar to
+ * below.
+ */
+#define check_add_overflow(a, b, d) __must_check_overflow(({	\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	typeof(d) __d = (d);			\
+	(void) (&__a == &__b);			\
+	(void) (&__a == __d);			\
+	__builtin_add_overflow(__a, __b, __d);	\
+}))
+
 #define min_t(type,x,y) \
 	({ type __x = (x); type __y = (y); __x < __y ? __x: __y; })
 #define max_t(type,x,y) \
@@ -535,6 +564,7 @@ void xfs_log_item_init(struct xfs_mount *mp, struct xfs_log_item *lip, int type,
 #define xfs_log_in_recovery(mp)		(false)
 
 /* xfs_icache.c */
+#define xfs_inode_clear_cowblocks_tag(ip)	do { } while (0)
 #define xfs_inode_set_cowblocks_tag(ip)	do { } while (0)
 #define xfs_inode_set_eofblocks_tag(ip)	do { } while (0)
 
diff --git a/libxfs/xfs_bmap.h b/libxfs/xfs_bmap.h
index 1eee606f392..ccd1ddcd785 100644
--- a/libxfs/xfs_bmap.h
+++ b/libxfs/xfs_bmap.h
@@ -156,7 +156,7 @@ static inline bool xfs_bmap_is_real_extent(const struct xfs_bmbt_irec *irec)
  * Return true if the extent is a real, allocated extent, or false if it is  a
  * delayed allocation, and unwritten extent or a hole.
  */
-static inline bool xfs_bmap_is_written_extent(struct xfs_bmbt_irec *irec)
+static inline bool xfs_bmap_is_written_extent(const struct xfs_bmbt_irec *irec)
 {
 	return xfs_bmap_is_real_extent(irec) &&
 	       irec->br_state != XFS_EXT_UNWRITTEN;
diff --git a/libxfs/xfs_defer.c b/libxfs/xfs_defer.c
index 077e9929807..7782eea458e 100644
--- a/libxfs/xfs_defer.c
+++ b/libxfs/xfs_defer.c
@@ -21,6 +21,7 @@
 #include "xfs_da_format.h"
 #include "xfs_da_btree.h"
 #include "xfs_attr.h"
+#include "xfs_swapext.h"
 
 static struct kmem_cache	*xfs_defer_pending_cache;
 
@@ -1174,6 +1175,10 @@ xfs_defer_init_item_caches(void)
 	error = xfs_attr_intent_init_cache();
 	if (error)
 		goto err;
+	error = xfs_swapext_intent_init_cache();
+	if (error)
+		goto err;
+
 	return 0;
 err:
 	xfs_defer_destroy_item_caches();
@@ -1184,6 +1189,7 @@ xfs_defer_init_item_caches(void)
 void
 xfs_defer_destroy_item_caches(void)
 {
+	xfs_swapext_intent_destroy_cache();
 	xfs_attr_intent_destroy_cache();
 	xfs_extfree_intent_destroy_cache();
 	xfs_bmap_intent_destroy_cache();
diff --git a/libxfs/xfs_defer.h b/libxfs/xfs_defer.h
index 18a9fb92dde..e3cf81bafca 100644
--- a/libxfs/xfs_defer.h
+++ b/libxfs/xfs_defer.h
@@ -72,7 +72,7 @@ extern const struct xfs_defer_op_type xfs_rmap_update_defer_type;
 extern const struct xfs_defer_op_type xfs_extent_free_defer_type;
 extern const struct xfs_defer_op_type xfs_agfl_free_defer_type;
 extern const struct xfs_defer_op_type xfs_attr_defer_type;
-
+extern const struct xfs_defer_op_type xfs_swapext_defer_type;
 
 /*
  * Deferred operation item relogging limits.
diff --git a/libxfs/xfs_format.h b/libxfs/xfs_format.h
index c0209bd21db..8b34754a579 100644
--- a/libxfs/xfs_format.h
+++ b/libxfs/xfs_format.h
@@ -430,6 +430,12 @@ static inline bool xfs_sb_version_haslogxattrs(struct xfs_sb *sbp)
 		 XFS_SB_FEAT_INCOMPAT_LOG_XATTRS);
 }
 
+static inline bool xfs_sb_version_haslogswapext(struct xfs_sb *sbp)
+{
+	return xfs_sb_is_v5(sbp) && (sbp->sb_features_log_incompat &
+		 XFS_SB_FEAT_INCOMPAT_LOG_SWAPEXT);
+}
+
 static inline bool
 xfs_is_quota_inode(struct xfs_sb *sbp, xfs_ino_t ino)
 {
diff --git a/libxfs/xfs_log_format.h b/libxfs/xfs_log_format.h
index 24c3d5dc361..3341792cf43 100644
--- a/libxfs/xfs_log_format.h
+++ b/libxfs/xfs_log_format.h
@@ -898,9 +898,36 @@ struct xfs_swap_extent {
 	int64_t			sx_isize2;
 };
 
-#define XFS_SWAP_EXT_FLAGS		(0)
+/* Swap extents between extended attribute forks. */
+#define XFS_SWAP_EXT_ATTR_FORK		(1ULL << 0)
 
-#define XFS_SWAP_EXT_STRINGS
+/* Set the file sizes when finished. */
+#define XFS_SWAP_EXT_SET_SIZES		(1ULL << 1)
+
+/*
+ * Swap only the extents of the two files where the file allocation units
+ * mapped to file1's range have been written to.
+ */
+#define XFS_SWAP_EXT_INO1_WRITTEN	(1ULL << 2)
+
+/* Clear the reflink flag from inode1 after the operation. */
+#define XFS_SWAP_EXT_CLEAR_INO1_REFLINK	(1ULL << 3)
+
+/* Clear the reflink flag from inode2 after the operation. */
+#define XFS_SWAP_EXT_CLEAR_INO2_REFLINK	(1ULL << 4)
+
+#define XFS_SWAP_EXT_FLAGS		(XFS_SWAP_EXT_ATTR_FORK | \
+					 XFS_SWAP_EXT_SET_SIZES | \
+					 XFS_SWAP_EXT_INO1_WRITTEN | \
+					 XFS_SWAP_EXT_CLEAR_INO1_REFLINK | \
+					 XFS_SWAP_EXT_CLEAR_INO2_REFLINK)
+
+#define XFS_SWAP_EXT_STRINGS \
+	{ XFS_SWAP_EXT_ATTR_FORK,		"ATTRFORK" }, \
+	{ XFS_SWAP_EXT_SET_SIZES,		"SETSIZES" }, \
+	{ XFS_SWAP_EXT_INO1_WRITTEN,		"INO1_WRITTEN" }, \
+	{ XFS_SWAP_EXT_CLEAR_INO1_REFLINK,	"CLEAR_INO1_REFLINK" }, \
+	{ XFS_SWAP_EXT_CLEAR_INO2_REFLINK,	"CLEAR_INO2_REFLINK" }
 
 /* This is the structure used to lay out an sxi log item in the log. */
 struct xfs_sxi_log_format {
diff --git a/libxfs/xfs_swapext.c b/libxfs/xfs_swapext.c
new file mode 100644
index 00000000000..2462657c1f4
--- /dev/null
+++ b/libxfs/xfs_swapext.c
@@ -0,0 +1,1028 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2020-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "libxfs_priv.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_inode.h"
+#include "xfs_trans.h"
+#include "xfs_bmap.h"
+#include "xfs_swapext.h"
+#include "xfs_trace.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_trans_space.h"
+#include "xfs_quota_defs.h"
+#include "xfs_health.h"
+#include "defer_item.h"
+
+struct kmem_cache	*xfs_swapext_intent_cache;
+
+/* bmbt mappings adjacent to a pair of records. */
+struct xfs_swapext_adjacent {
+	struct xfs_bmbt_irec		left1;
+	struct xfs_bmbt_irec		right1;
+	struct xfs_bmbt_irec		left2;
+	struct xfs_bmbt_irec		right2;
+};
+
+#define ADJACENT_INIT { \
+	.left1  = { .br_startblock = HOLESTARTBLOCK }, \
+	.right1 = { .br_startblock = HOLESTARTBLOCK }, \
+	.left2  = { .br_startblock = HOLESTARTBLOCK }, \
+	.right2 = { .br_startblock = HOLESTARTBLOCK }, \
+}
+
+/* Information to help us reset reflink flag / CoW fork state after a swap. */
+
+/* Previous state of the two inodes' reflink flags. */
+#define XFS_REFLINK_STATE_IP1		(1U << 0)
+#define XFS_REFLINK_STATE_IP2		(1U << 1)
+
+/*
+ * If the reflink flag is set on either inode, make sure it has an incore CoW
+ * fork, since all reflink inodes must have them.  If there's a CoW fork and it
+ * has extents in it, make sure the inodes are tagged appropriately so that
+ * speculative preallocations can be GC'd if we run low of space.
+ */
+static inline void
+xfs_swapext_ensure_cowfork(
+	struct xfs_inode	*ip)
+{
+	struct xfs_ifork	*cfork;
+
+	if (xfs_is_reflink_inode(ip))
+		xfs_ifork_init_cow(ip);
+
+	cfork = xfs_ifork_ptr(ip, XFS_COW_FORK);
+	if (!cfork)
+		return;
+	if (cfork->if_bytes > 0)
+		xfs_inode_set_cowblocks_tag(ip);
+	else
+		xfs_inode_clear_cowblocks_tag(ip);
+}
+
+/*
+ * Adjust the on-disk inode size upwards if needed so that we never map extents
+ * into the file past EOF.  This is crucial so that log recovery won't get
+ * confused by the sudden appearance of post-eof extents.
+ */
+STATIC void
+xfs_swapext_update_size(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	struct xfs_bmbt_irec	*imap,
+	xfs_fsize_t		new_isize)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+	xfs_fsize_t		len;
+
+	if (new_isize < 0)
+		return;
+
+	len = min(XFS_FSB_TO_B(mp, imap->br_startoff + imap->br_blockcount),
+		  new_isize);
+
+	if (len <= ip->i_disk_size)
+		return;
+
+	trace_xfs_swapext_update_inode_size(ip, len);
+
+	ip->i_disk_size = len;
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+}
+
+static inline bool
+sxi_has_more_swap_work(const struct xfs_swapext_intent *sxi)
+{
+	return sxi->sxi_blockcount > 0;
+}
+
+static inline bool
+sxi_has_postop_work(const struct xfs_swapext_intent *sxi)
+{
+	return sxi->sxi_flags & (XFS_SWAP_EXT_CLEAR_INO1_REFLINK |
+				 XFS_SWAP_EXT_CLEAR_INO2_REFLINK);
+}
+
+static inline void
+sxi_advance(
+	struct xfs_swapext_intent	*sxi,
+	const struct xfs_bmbt_irec	*irec)
+{
+	sxi->sxi_startoff1 += irec->br_blockcount;
+	sxi->sxi_startoff2 += irec->br_blockcount;
+	sxi->sxi_blockcount -= irec->br_blockcount;
+}
+
+/* Check all extents to make sure we can actually swap them. */
+int
+xfs_swapext_check_extents(
+	struct xfs_mount		*mp,
+	const struct xfs_swapext_req	*req)
+{
+	struct xfs_ifork		*ifp1, *ifp2;
+
+	/* No fork? */
+	ifp1 = xfs_ifork_ptr(req->ip1, req->whichfork);
+	ifp2 = xfs_ifork_ptr(req->ip2, req->whichfork);
+	if (!ifp1 || !ifp2)
+		return -EINVAL;
+
+	/* We don't know how to swap local format forks. */
+	if (ifp1->if_format == XFS_DINODE_FMT_LOCAL ||
+	    ifp2->if_format == XFS_DINODE_FMT_LOCAL)
+		return -EINVAL;
+
+	/* We don't support realtime data forks yet. */
+	if (!XFS_IS_REALTIME_INODE(req->ip1))
+		return 0;
+	if (req->whichfork == XFS_ATTR_FORK)
+		return 0;
+	return -EINVAL;
+}
+
+#ifdef CONFIG_XFS_QUOTA
+/* Log the actual updates to the quota accounting. */
+static inline void
+xfs_swapext_update_quota(
+	struct xfs_trans		*tp,
+	struct xfs_swapext_intent	*sxi,
+	struct xfs_bmbt_irec		*irec1,
+	struct xfs_bmbt_irec		*irec2)
+{
+	int64_t				ip1_delta = 0, ip2_delta = 0;
+	unsigned int			qflag;
+
+	qflag = XFS_IS_REALTIME_INODE(sxi->sxi_ip1) ? XFS_TRANS_DQ_RTBCOUNT :
+						      XFS_TRANS_DQ_BCOUNT;
+
+	if (xfs_bmap_is_real_extent(irec1)) {
+		ip1_delta -= irec1->br_blockcount;
+		ip2_delta += irec1->br_blockcount;
+	}
+
+	if (xfs_bmap_is_real_extent(irec2)) {
+		ip1_delta += irec2->br_blockcount;
+		ip2_delta -= irec2->br_blockcount;
+	}
+
+	xfs_trans_mod_dquot_byino(tp, sxi->sxi_ip1, qflag, ip1_delta);
+	xfs_trans_mod_dquot_byino(tp, sxi->sxi_ip2, qflag, ip2_delta);
+}
+#else
+# define xfs_swapext_update_quota(tp, sxi, irec1, irec2)	((void)0)
+#endif
+
+/* Decide if we want to skip this mapping from file1. */
+static inline bool
+xfs_swapext_can_skip_mapping(
+	struct xfs_swapext_intent	*sxi,
+	struct xfs_bmbt_irec		*irec)
+{
+	/* Do not skip this mapping if the caller did not tell us to. */
+	if (!(sxi->sxi_flags & XFS_SWAP_EXT_INO1_WRITTEN))
+		return false;
+
+	/* Do not skip mapped, written extents. */
+	if (xfs_bmap_is_written_extent(irec))
+		return false;
+
+	/*
+	 * The mapping is unwritten or a hole.  It cannot be a delalloc
+	 * reservation because we already excluded those.  It cannot be an
+	 * unwritten extent with dirty page cache because we flushed the page
+	 * cache.  We don't support realtime files yet, so we needn't (yet)
+	 * deal with them.
+	 */
+	return true;
+}
+
+/*
+ * Walk forward through the file ranges in @sxi until we find two different
+ * mappings to exchange.  If there is work to do, return the mappings;
+ * otherwise we've reached the end of the range and sxi_blockcount will be
+ * zero.
+ *
+ * If the walk skips over a pair of mappings to the same storage, save them as
+ * the left records in @adj (if provided) so that the simulation phase can
+ * avoid an extra lookup.
+  */
+static int
+xfs_swapext_find_mappings(
+	struct xfs_swapext_intent	*sxi,
+	struct xfs_bmbt_irec		*irec1,
+	struct xfs_bmbt_irec		*irec2,
+	struct xfs_swapext_adjacent	*adj)
+{
+	int				nimaps;
+	int				bmap_flags;
+	int				error;
+
+	bmap_flags = xfs_bmapi_aflag(xfs_swapext_whichfork(sxi));
+
+	for (; sxi_has_more_swap_work(sxi); sxi_advance(sxi, irec1)) {
+		/* Read extent from the first file */
+		nimaps = 1;
+		error = xfs_bmapi_read(sxi->sxi_ip1, sxi->sxi_startoff1,
+				sxi->sxi_blockcount, irec1, &nimaps,
+				bmap_flags);
+		if (error)
+			return error;
+		if (nimaps != 1 ||
+		    irec1->br_startblock == DELAYSTARTBLOCK ||
+		    irec1->br_startoff != sxi->sxi_startoff1) {
+			/*
+			 * We should never get no mapping or a delalloc extent
+			 * or something that doesn't match what we asked for,
+			 * since the caller flushed both inodes and we hold the
+			 * ILOCKs for both inodes.
+			 */
+			ASSERT(0);
+			return -EINVAL;
+		}
+
+		if (xfs_swapext_can_skip_mapping(sxi, irec1)) {
+			trace_xfs_swapext_extent1_skip(sxi->sxi_ip1, irec1);
+			continue;
+		}
+
+		/* Read extent from the second file */
+		nimaps = 1;
+		error = xfs_bmapi_read(sxi->sxi_ip2, sxi->sxi_startoff2,
+				irec1->br_blockcount, irec2, &nimaps,
+				bmap_flags);
+		if (error)
+			return error;
+		if (nimaps != 1 ||
+		    irec2->br_startblock == DELAYSTARTBLOCK ||
+		    irec2->br_startoff != sxi->sxi_startoff2) {
+			/*
+			 * We should never get no mapping or a delalloc extent
+			 * or something that doesn't match what we asked for,
+			 * since the caller flushed both inodes and we hold the
+			 * ILOCKs for both inodes.
+			 */
+			ASSERT(0);
+			return -EINVAL;
+		}
+
+		/*
+		 * We can only swap as many blocks as the smaller of the two
+		 * extent maps.
+		 */
+		irec1->br_blockcount = min(irec1->br_blockcount,
+					   irec2->br_blockcount);
+
+		trace_xfs_swapext_extent1(sxi->sxi_ip1, irec1);
+		trace_xfs_swapext_extent2(sxi->sxi_ip2, irec2);
+
+		/* We found something to swap, so return it. */
+		if (irec1->br_startblock != irec2->br_startblock)
+			return 0;
+
+		/*
+		 * Two extents mapped to the same physical block must not have
+		 * different states; that's filesystem corruption.  Move on to
+		 * the next extent if they're both holes or both the same
+		 * physical extent.
+		 */
+		if (irec1->br_state != irec2->br_state) {
+			xfs_bmap_mark_sick(sxi->sxi_ip1,
+					xfs_swapext_whichfork(sxi));
+			xfs_bmap_mark_sick(sxi->sxi_ip2,
+					xfs_swapext_whichfork(sxi));
+			return -EFSCORRUPTED;
+		}
+
+		/*
+		 * Save the mappings if we're estimating work and skipping
+		 * these identical mappings.
+		 */
+		if (adj) {
+			memcpy(&adj->left1, irec1, sizeof(*irec1));
+			memcpy(&adj->left2, irec2, sizeof(*irec2));
+		}
+	}
+
+	return 0;
+}
+
+/* Exchange these two mappings. */
+static void
+xfs_swapext_exchange_mappings(
+	struct xfs_trans		*tp,
+	struct xfs_swapext_intent	*sxi,
+	struct xfs_bmbt_irec		*irec1,
+	struct xfs_bmbt_irec		*irec2)
+{
+	int				whichfork = xfs_swapext_whichfork(sxi);
+
+	xfs_swapext_update_quota(tp, sxi, irec1, irec2);
+
+	/* Remove both mappings. */
+	xfs_bmap_unmap_extent(tp, sxi->sxi_ip1, whichfork, irec1);
+	xfs_bmap_unmap_extent(tp, sxi->sxi_ip2, whichfork, irec2);
+
+	/*
+	 * Re-add both mappings.  We swap the file offsets between the two maps
+	 * and add the opposite map, which has the effect of filling the
+	 * logical offsets we just unmapped, but with with the physical mapping
+	 * information swapped.
+	 */
+	swap(irec1->br_startoff, irec2->br_startoff);
+	xfs_bmap_map_extent(tp, sxi->sxi_ip1, whichfork, irec2);
+	xfs_bmap_map_extent(tp, sxi->sxi_ip2, whichfork, irec1);
+
+	/* Make sure we're not mapping extents past EOF. */
+	if (whichfork == XFS_DATA_FORK) {
+		xfs_swapext_update_size(tp, sxi->sxi_ip1, irec2,
+				sxi->sxi_isize1);
+		xfs_swapext_update_size(tp, sxi->sxi_ip2, irec1,
+				sxi->sxi_isize2);
+	}
+
+	/*
+	 * Advance our cursor and exit.   The caller (either defer ops or log
+	 * recovery) will log the SXD item, and if *blockcount is nonzero, it
+	 * will log a new SXI item for the remainder and call us back.
+	 */
+	sxi_advance(sxi, irec1);
+}
+
+static inline void
+xfs_swapext_clear_reflink(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip)
+{
+	trace_xfs_reflink_unset_inode_flag(ip);
+
+	ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+}
+
+/* Finish whatever work might come after a swap operation. */
+static int
+xfs_swapext_do_postop_work(
+	struct xfs_trans		*tp,
+	struct xfs_swapext_intent	*sxi)
+{
+	if (sxi->sxi_flags & XFS_SWAP_EXT_CLEAR_INO1_REFLINK) {
+		xfs_swapext_clear_reflink(tp, sxi->sxi_ip1);
+		sxi->sxi_flags &= ~XFS_SWAP_EXT_CLEAR_INO1_REFLINK;
+	}
+
+	if (sxi->sxi_flags & XFS_SWAP_EXT_CLEAR_INO2_REFLINK) {
+		xfs_swapext_clear_reflink(tp, sxi->sxi_ip2);
+		sxi->sxi_flags &= ~XFS_SWAP_EXT_CLEAR_INO2_REFLINK;
+	}
+
+	return 0;
+}
+
+/* Finish one extent swap, possibly log more. */
+int
+xfs_swapext_finish_one(
+	struct xfs_trans		*tp,
+	struct xfs_swapext_intent	*sxi)
+{
+	struct xfs_bmbt_irec		irec1, irec2;
+	int				error;
+
+	if (sxi_has_more_swap_work(sxi)) {
+		/*
+		 * If the operation state says that some range of the files
+		 * have not yet been swapped, look for extents in that range to
+		 * swap.  If we find some extents, swap them.
+		 */
+		error = xfs_swapext_find_mappings(sxi, &irec1, &irec2, NULL);
+		if (error)
+			return error;
+
+		if (sxi_has_more_swap_work(sxi))
+			xfs_swapext_exchange_mappings(tp, sxi, &irec1, &irec2);
+
+		/*
+		 * If the caller asked us to exchange the file sizes after the
+		 * swap and either we just swapped the last extents in the
+		 * range or we didn't find anything to swap, update the ondisk
+		 * file sizes.
+		 */
+		if ((sxi->sxi_flags & XFS_SWAP_EXT_SET_SIZES) &&
+		    !sxi_has_more_swap_work(sxi)) {
+			sxi->sxi_ip1->i_disk_size = sxi->sxi_isize1;
+			sxi->sxi_ip2->i_disk_size = sxi->sxi_isize2;
+
+			xfs_trans_log_inode(tp, sxi->sxi_ip1, XFS_ILOG_CORE);
+			xfs_trans_log_inode(tp, sxi->sxi_ip2, XFS_ILOG_CORE);
+		}
+	} else if (sxi_has_postop_work(sxi)) {
+		/*
+		 * Now that we're finished with the swap operation, complete
+		 * the post-op cleanup work.
+		 */
+		error = xfs_swapext_do_postop_work(tp, sxi);
+		if (error)
+			return error;
+	}
+
+	/* If we still have work to do, ask for a new transaction. */
+	if (sxi_has_more_swap_work(sxi) || sxi_has_postop_work(sxi)) {
+		trace_xfs_swapext_defer(tp->t_mountp, sxi);
+		return -EAGAIN;
+	}
+
+	/*
+	 * If we reach here, we've finished all the swapping work and the post
+	 * operation work.  The last thing we need to do before returning to
+	 * the caller is to make sure that COW forks are set up correctly.
+	 */
+	if (!(sxi->sxi_flags & XFS_SWAP_EXT_ATTR_FORK)) {
+		xfs_swapext_ensure_cowfork(sxi->sxi_ip1);
+		xfs_swapext_ensure_cowfork(sxi->sxi_ip2);
+	}
+
+	return 0;
+}
+
+/*
+ * Compute the amount of bmbt blocks we should reserve for each file.  In the
+ * worst case, each exchange will fill a hole with a new mapping, which could
+ * result in a btree split every time we add a new leaf block.
+ */
+static inline uint64_t
+xfs_swapext_bmbt_blocks(
+	struct xfs_mount		*mp,
+	const struct xfs_swapext_req	*req)
+{
+	return howmany_64(req->nr_exchanges,
+					XFS_MAX_CONTIG_BMAPS_PER_BLOCK(mp)) *
+			XFS_EXTENTADD_SPACE_RES(mp, req->whichfork);
+}
+
+static inline uint64_t
+xfs_swapext_rmapbt_blocks(
+	struct xfs_mount		*mp,
+	const struct xfs_swapext_req	*req)
+{
+	if (!xfs_has_rmapbt(mp))
+		return 0;
+	if (XFS_IS_REALTIME_INODE(req->ip1))
+		return 0;
+
+	return howmany_64(req->nr_exchanges,
+					XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)) *
+			XFS_RMAPADD_SPACE_RES(mp);
+}
+
+/* Estimate the bmbt and rmapbt overhead required to exchange extents. */
+static int
+xfs_swapext_estimate_overhead(
+	struct xfs_swapext_req	*req)
+{
+	struct xfs_mount	*mp = req->ip1->i_mount;
+	xfs_filblks_t		bmbt_blocks;
+	xfs_filblks_t		rmapbt_blocks;
+	xfs_filblks_t		resblks = req->resblks;
+
+	/*
+	 * Compute the number of bmbt and rmapbt blocks we might need to handle
+	 * the estimated number of exchanges.
+	 */
+	bmbt_blocks = xfs_swapext_bmbt_blocks(mp, req);
+	rmapbt_blocks = xfs_swapext_rmapbt_blocks(mp, req);
+
+	trace_xfs_swapext_overhead(mp, bmbt_blocks, rmapbt_blocks);
+
+	/* Make sure the change in file block count doesn't overflow. */
+	if (check_add_overflow(req->ip1_bcount, bmbt_blocks, &req->ip1_bcount))
+		return -EFBIG;
+	if (check_add_overflow(req->ip2_bcount, bmbt_blocks, &req->ip2_bcount))
+		return -EFBIG;
+
+	/*
+	 * Add together the number of blocks we need to handle btree growth,
+	 * then add it to the number of blocks we need to reserve to this
+	 * transaction.
+	 */
+	if (check_add_overflow(resblks, bmbt_blocks, &resblks))
+		return -ENOSPC;
+	if (check_add_overflow(resblks, bmbt_blocks, &resblks))
+		return -ENOSPC;
+	if (check_add_overflow(resblks, rmapbt_blocks, &resblks))
+		return -ENOSPC;
+	if (check_add_overflow(resblks, rmapbt_blocks, &resblks))
+		return -ENOSPC;
+
+	/* Can't actually reserve more than UINT_MAX blocks. */
+	if (req->resblks > UINT_MAX)
+		return -ENOSPC;
+
+	req->resblks = resblks;
+	trace_xfs_swapext_final_estimate(req);
+	return 0;
+}
+
+/* Decide if we can merge two real extents. */
+static inline bool
+can_merge(
+	const struct xfs_bmbt_irec	*b1,
+	const struct xfs_bmbt_irec	*b2)
+{
+	/* Don't merge holes. */
+	if (b1->br_startblock == HOLESTARTBLOCK ||
+	    b2->br_startblock == HOLESTARTBLOCK)
+		return false;
+
+	/* We don't merge holes. */
+	if (!xfs_bmap_is_real_extent(b1) || !xfs_bmap_is_real_extent(b2))
+		return false;
+
+	if (b1->br_startoff   + b1->br_blockcount == b2->br_startoff &&
+	    b1->br_startblock + b1->br_blockcount == b2->br_startblock &&
+	    b1->br_state			  == b2->br_state &&
+	    b1->br_blockcount + b2->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
+		return true;
+
+	return false;
+}
+
+#define CLEFT_CONTIG	0x01
+#define CRIGHT_CONTIG	0x02
+#define CHOLE		0x04
+#define CBOTH_CONTIG	(CLEFT_CONTIG | CRIGHT_CONTIG)
+
+#define NLEFT_CONTIG	0x10
+#define NRIGHT_CONTIG	0x20
+#define NHOLE		0x40
+#define NBOTH_CONTIG	(NLEFT_CONTIG | NRIGHT_CONTIG)
+
+/* Estimate the effect of a single swap on extent count. */
+static inline int
+delta_nextents_step(
+	struct xfs_mount		*mp,
+	const struct xfs_bmbt_irec	*left,
+	const struct xfs_bmbt_irec	*curr,
+	const struct xfs_bmbt_irec	*new,
+	const struct xfs_bmbt_irec	*right)
+{
+	bool				lhole, rhole, chole, nhole;
+	unsigned int			state = 0;
+	int				ret = 0;
+
+	lhole = left->br_startblock == HOLESTARTBLOCK;
+	rhole = right->br_startblock == HOLESTARTBLOCK;
+	chole = curr->br_startblock == HOLESTARTBLOCK;
+	nhole = new->br_startblock == HOLESTARTBLOCK;
+
+	if (chole)
+		state |= CHOLE;
+	if (!lhole && !chole && can_merge(left, curr))
+		state |= CLEFT_CONTIG;
+	if (!rhole && !chole && can_merge(curr, right))
+		state |= CRIGHT_CONTIG;
+	if ((state & CBOTH_CONTIG) == CBOTH_CONTIG &&
+	    left->br_startblock + curr->br_startblock +
+					right->br_startblock > XFS_MAX_BMBT_EXTLEN)
+		state &= ~CRIGHT_CONTIG;
+
+	if (nhole)
+		state |= NHOLE;
+	if (!lhole && !nhole && can_merge(left, new))
+		state |= NLEFT_CONTIG;
+	if (!rhole && !nhole && can_merge(new, right))
+		state |= NRIGHT_CONTIG;
+	if ((state & NBOTH_CONTIG) == NBOTH_CONTIG &&
+	    left->br_startblock + new->br_startblock +
+					right->br_startblock > XFS_MAX_BMBT_EXTLEN)
+		state &= ~NRIGHT_CONTIG;
+
+	switch (state & (CLEFT_CONTIG | CRIGHT_CONTIG | CHOLE)) {
+	case CLEFT_CONTIG | CRIGHT_CONTIG:
+		/*
+		 * left/curr/right are the same extent, so deleting curr causes
+		 * 2 new extents to be created.
+		 */
+		ret += 2;
+		break;
+	case 0:
+		/*
+		 * curr is not contiguous with any extent, so we remove curr
+		 * completely
+		 */
+		ret--;
+		break;
+	case CHOLE:
+		/* hole, do nothing */
+		break;
+	case CLEFT_CONTIG:
+	case CRIGHT_CONTIG:
+		/* trim either left or right, no change */
+		break;
+	}
+
+	switch (state & (NLEFT_CONTIG | NRIGHT_CONTIG | NHOLE)) {
+	case NLEFT_CONTIG | NRIGHT_CONTIG:
+		/*
+		 * left/curr/right will become the same extent, so adding
+		 * curr causes the deletion of right.
+		 */
+		ret--;
+		break;
+	case 0:
+		/* new is not contiguous with any extent */
+		ret++;
+		break;
+	case NHOLE:
+		/* hole, do nothing. */
+		break;
+	case NLEFT_CONTIG:
+	case NRIGHT_CONTIG:
+		/* new is absorbed into left or right, no change */
+		break;
+	}
+
+	trace_xfs_swapext_delta_nextents_step(mp, left, curr, new, right, ret,
+			state);
+	return ret;
+}
+
+/* Make sure we don't overflow the extent counters. */
+static inline int
+ensure_delta_nextents(
+	struct xfs_swapext_req	*req,
+	struct xfs_inode	*ip,
+	int64_t			delta)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, req->whichfork);
+	xfs_extnum_t		max_extents;
+	bool			large_extcount;
+
+	if (delta < 0)
+		return 0;
+
+	if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_REDUCE_MAX_IEXTENTS)) {
+		if (ifp->if_nextents + delta > 10)
+			return -EFBIG;
+	}
+
+	if (req->req_flags & XFS_SWAP_REQ_NREXT64)
+		large_extcount = true;
+	else
+		large_extcount = xfs_inode_has_large_extent_counts(ip);
+
+	max_extents = xfs_iext_max_nextents(large_extcount, req->whichfork);
+	if (ifp->if_nextents + delta <= max_extents)
+		return 0;
+	if (large_extcount)
+		return -EFBIG;
+	if (!xfs_has_large_extent_counts(mp))
+		return -EFBIG;
+
+	max_extents = xfs_iext_max_nextents(true, req->whichfork);
+	if (ifp->if_nextents + delta > max_extents)
+		return -EFBIG;
+
+	req->req_flags |= XFS_SWAP_REQ_NREXT64;
+	return 0;
+}
+
+/* Find the next extent after irec. */
+static inline int
+get_next_ext(
+	struct xfs_inode		*ip,
+	int				bmap_flags,
+	const struct xfs_bmbt_irec	*irec,
+	struct xfs_bmbt_irec		*nrec)
+{
+	xfs_fileoff_t			off;
+	xfs_filblks_t			blockcount;
+	int				nimaps = 1;
+	int				error;
+
+	off = irec->br_startoff + irec->br_blockcount;
+	blockcount = XFS_MAX_FILEOFF - off;
+	error = xfs_bmapi_read(ip, off, blockcount, nrec, &nimaps, bmap_flags);
+	if (error)
+		return error;
+	if (nrec->br_startblock == DELAYSTARTBLOCK ||
+	    nrec->br_startoff != off) {
+		/*
+		 * If we don't get the extent we want, return a zero-length
+		 * mapping, which our estimator function will pretend is a hole.
+		 * We shouldn't get delalloc reservations.
+		 */
+		nrec->br_startblock = HOLESTARTBLOCK;
+	}
+
+	return 0;
+}
+
+int __init
+xfs_swapext_intent_init_cache(void)
+{
+	xfs_swapext_intent_cache = kmem_cache_create("xfs_swapext_intent",
+			sizeof(struct xfs_swapext_intent),
+			0, 0, NULL);
+
+	return xfs_swapext_intent_cache != NULL ? 0 : -ENOMEM;
+}
+
+void
+xfs_swapext_intent_destroy_cache(void)
+{
+	kmem_cache_destroy(xfs_swapext_intent_cache);
+	xfs_swapext_intent_cache = NULL;
+}
+
+/*
+ * Decide if we will swap the reflink flags between the two files after the
+ * swap.  The only time we want to do this is if we're exchanging all extents
+ * under EOF and the inode reflink flags have different states.
+ */
+static inline bool
+sxi_can_exchange_reflink_flags(
+	const struct xfs_swapext_req	*req,
+	unsigned int			reflink_state)
+{
+	struct xfs_mount		*mp = req->ip1->i_mount;
+
+	if (hweight32(reflink_state) != 1)
+		return false;
+	if (req->startoff1 != 0 || req->startoff2 != 0)
+		return false;
+	if (req->blockcount != XFS_B_TO_FSB(mp, req->ip1->i_disk_size))
+		return false;
+	if (req->blockcount != XFS_B_TO_FSB(mp, req->ip2->i_disk_size))
+		return false;
+	return true;
+}
+
+
+/* Allocate and initialize a new incore intent item from a request. */
+struct xfs_swapext_intent *
+xfs_swapext_init_intent(
+	const struct xfs_swapext_req	*req,
+	unsigned int			*reflink_state)
+{
+	struct xfs_swapext_intent	*sxi;
+	unsigned int			rs = 0;
+
+	sxi = kmem_cache_zalloc(xfs_swapext_intent_cache,
+			GFP_NOFS | __GFP_NOFAIL);
+	INIT_LIST_HEAD(&sxi->sxi_list);
+	sxi->sxi_ip1 = req->ip1;
+	sxi->sxi_ip2 = req->ip2;
+	sxi->sxi_startoff1 = req->startoff1;
+	sxi->sxi_startoff2 = req->startoff2;
+	sxi->sxi_blockcount = req->blockcount;
+	sxi->sxi_isize1 = sxi->sxi_isize2 = -1;
+
+	if (req->whichfork == XFS_ATTR_FORK)
+		sxi->sxi_flags |= XFS_SWAP_EXT_ATTR_FORK;
+
+	if (req->whichfork == XFS_DATA_FORK &&
+	    (req->req_flags & XFS_SWAP_REQ_SET_SIZES)) {
+		sxi->sxi_flags |= XFS_SWAP_EXT_SET_SIZES;
+		sxi->sxi_isize1 = req->ip2->i_disk_size;
+		sxi->sxi_isize2 = req->ip1->i_disk_size;
+	}
+
+	if (req->req_flags & XFS_SWAP_REQ_INO1_WRITTEN)
+		sxi->sxi_flags |= XFS_SWAP_EXT_INO1_WRITTEN;
+
+	if (req->req_flags & XFS_SWAP_REQ_LOGGED)
+		sxi->sxi_op_flags |= XFS_SWAP_EXT_OP_LOGGED;
+	if (req->req_flags & XFS_SWAP_REQ_NREXT64)
+		sxi->sxi_op_flags |= XFS_SWAP_EXT_OP_NREXT64;
+
+	if (req->whichfork == XFS_DATA_FORK) {
+		/*
+		 * Record the state of each inode's reflink flag before the
+		 * operation.
+		 */
+		if (xfs_is_reflink_inode(req->ip1))
+			rs |= XFS_REFLINK_STATE_IP1;
+		if (xfs_is_reflink_inode(req->ip2))
+			rs |= XFS_REFLINK_STATE_IP2;
+
+		/*
+		 * Figure out if we're clearing the reflink flags (which
+		 * effectively swaps them) after the operation.
+		 */
+		if (sxi_can_exchange_reflink_flags(req, rs)) {
+			if (rs & XFS_REFLINK_STATE_IP1)
+				sxi->sxi_flags |=
+						XFS_SWAP_EXT_CLEAR_INO1_REFLINK;
+			if (rs & XFS_REFLINK_STATE_IP2)
+				sxi->sxi_flags |=
+						XFS_SWAP_EXT_CLEAR_INO2_REFLINK;
+		}
+	}
+
+	if (reflink_state)
+		*reflink_state = rs;
+	return sxi;
+}
+
+/*
+ * Estimate the number of exchange operations and the number of file blocks
+ * in each file that will be affected by the exchange operation.
+ */
+int
+xfs_swapext_estimate(
+	struct xfs_swapext_req		*req)
+{
+	struct xfs_swapext_intent	*sxi;
+	struct xfs_bmbt_irec		irec1, irec2;
+	struct xfs_swapext_adjacent	adj = ADJACENT_INIT;
+	xfs_filblks_t			ip1_blocks = 0, ip2_blocks = 0;
+	int64_t				d_nexts1, d_nexts2;
+	int				bmap_flags;
+	int				error;
+
+	ASSERT(!(req->req_flags & ~XFS_SWAP_REQ_FLAGS));
+
+	bmap_flags = xfs_bmapi_aflag(req->whichfork);
+	sxi = xfs_swapext_init_intent(req, NULL);
+
+	/*
+	 * To guard against the possibility of overflowing the extent counters,
+	 * we have to estimate an upper bound on the potential increase in that
+	 * counter.  We can split the extent at each end of the range, and for
+	 * each step of the swap we can split the extent that we're working on
+	 * if the extents do not align.
+	 */
+	d_nexts1 = d_nexts2 = 3;
+
+	while (sxi_has_more_swap_work(sxi)) {
+		/*
+		 * Walk through the file ranges until we find something to
+		 * swap.  Because we're simulating the swap, pass in adj to
+		 * capture skipped mappings for correct estimation of bmbt
+		 * record merges.
+		 */
+		error = xfs_swapext_find_mappings(sxi, &irec1, &irec2, &adj);
+		if (error)
+			goto out_free;
+		if (!sxi_has_more_swap_work(sxi))
+			break;
+
+		/* Update accounting. */
+		if (xfs_bmap_is_real_extent(&irec1))
+			ip1_blocks += irec1.br_blockcount;
+		if (xfs_bmap_is_real_extent(&irec2))
+			ip2_blocks += irec2.br_blockcount;
+		req->nr_exchanges++;
+
+		/* Read the next extents from both files. */
+		error = get_next_ext(req->ip1, bmap_flags, &irec1, &adj.right1);
+		if (error)
+			goto out_free;
+
+		error = get_next_ext(req->ip2, bmap_flags, &irec2, &adj.right2);
+		if (error)
+			goto out_free;
+
+		/* Update extent count deltas. */
+		d_nexts1 += delta_nextents_step(req->ip1->i_mount,
+				&adj.left1, &irec1, &irec2, &adj.right1);
+
+		d_nexts2 += delta_nextents_step(req->ip1->i_mount,
+				&adj.left2, &irec2, &irec1, &adj.right2);
+
+		/* Now pretend we swapped the extents. */
+		if (can_merge(&adj.left2, &irec1))
+			adj.left2.br_blockcount += irec1.br_blockcount;
+		else
+			memcpy(&adj.left2, &irec1, sizeof(irec1));
+
+		if (can_merge(&adj.left1, &irec2))
+			adj.left1.br_blockcount += irec2.br_blockcount;
+		else
+			memcpy(&adj.left1, &irec2, sizeof(irec2));
+
+		sxi_advance(sxi, &irec1);
+	}
+
+	/* Account for the blocks that are being exchanged. */
+	if (XFS_IS_REALTIME_INODE(req->ip1) &&
+	    req->whichfork == XFS_DATA_FORK) {
+		req->ip1_rtbcount = ip1_blocks;
+		req->ip2_rtbcount = ip2_blocks;
+	} else {
+		req->ip1_bcount = ip1_blocks;
+		req->ip2_bcount = ip2_blocks;
+	}
+
+	/*
+	 * Make sure that both forks have enough slack left in their extent
+	 * counters that the swap operation will not overflow.
+	 */
+	trace_xfs_swapext_delta_nextents(req, d_nexts1, d_nexts2);
+	if (req->ip1 == req->ip2) {
+		error = ensure_delta_nextents(req, req->ip1,
+				d_nexts1 + d_nexts2);
+	} else {
+		error = ensure_delta_nextents(req, req->ip1, d_nexts1);
+		if (error)
+			goto out_free;
+		error = ensure_delta_nextents(req, req->ip2, d_nexts2);
+	}
+	if (error)
+		goto out_free;
+
+	trace_xfs_swapext_initial_estimate(req);
+	error = xfs_swapext_estimate_overhead(req);
+out_free:
+	kmem_cache_free(xfs_swapext_intent_cache, sxi);
+	return error;
+}
+
+static inline void
+xfs_swapext_set_reflink(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip)
+{
+	trace_xfs_reflink_set_inode_flag(ip);
+
+	ip->i_diflags2 |= XFS_DIFLAG2_REFLINK;
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+}
+
+/*
+ * If either file has shared blocks and we're swapping data forks, we must flag
+ * the other file as having shared blocks so that we get the shared-block rmap
+ * functions if we need to fix up the rmaps.
+ */
+void
+xfs_swapext_ensure_reflink(
+	struct xfs_trans		*tp,
+	const struct xfs_swapext_intent	*sxi,
+	unsigned int			reflink_state)
+{
+	if ((reflink_state & XFS_REFLINK_STATE_IP1) &&
+	    !xfs_is_reflink_inode(sxi->sxi_ip2))
+		xfs_swapext_set_reflink(tp, sxi->sxi_ip2);
+
+	if ((reflink_state & XFS_REFLINK_STATE_IP2) &&
+	    !xfs_is_reflink_inode(sxi->sxi_ip1))
+		xfs_swapext_set_reflink(tp, sxi->sxi_ip1);
+}
+
+/* Widen the extent counts of both inodes if necessary. */
+static inline void
+xfs_swapext_upgrade_extent_counts(
+	struct xfs_trans		*tp,
+	const struct xfs_swapext_intent	*sxi)
+{
+	if (!(sxi->sxi_op_flags & XFS_SWAP_EXT_OP_NREXT64))
+		return;
+
+	sxi->sxi_ip1->i_diflags2 |= XFS_DIFLAG2_NREXT64;
+	xfs_trans_log_inode(tp, sxi->sxi_ip1, XFS_ILOG_CORE);
+
+	sxi->sxi_ip2->i_diflags2 |= XFS_DIFLAG2_NREXT64;
+	xfs_trans_log_inode(tp, sxi->sxi_ip2, XFS_ILOG_CORE);
+}
+
+/*
+ * Schedule a swap a range of extents from one inode to another.  If the atomic
+ * swap feature is enabled, then the operation progress can be resumed even if
+ * the system goes down.  The caller must commit the transaction to start the
+ * work.
+ *
+ * The caller must ensure the inodes must be joined to the transaction and
+ * ILOCKd; they will still be joined to the transaction at exit.
+ */
+void
+xfs_swapext(
+	struct xfs_trans		*tp,
+	const struct xfs_swapext_req	*req)
+{
+	struct xfs_swapext_intent	*sxi;
+	unsigned int			reflink_state;
+
+	ASSERT(xfs_isilocked(req->ip1, XFS_ILOCK_EXCL));
+	ASSERT(xfs_isilocked(req->ip2, XFS_ILOCK_EXCL));
+	ASSERT(req->whichfork != XFS_COW_FORK);
+	ASSERT(!(req->req_flags & ~XFS_SWAP_REQ_FLAGS));
+	if (req->req_flags & XFS_SWAP_REQ_SET_SIZES)
+		ASSERT(req->whichfork == XFS_DATA_FORK);
+
+	if (req->blockcount == 0)
+		return;
+
+	sxi = xfs_swapext_init_intent(req, &reflink_state);
+	xfs_swapext_defer_add(tp, sxi);
+	xfs_swapext_ensure_reflink(tp, sxi, reflink_state);
+	xfs_swapext_upgrade_extent_counts(tp, sxi);
+}
diff --git a/libxfs/xfs_swapext.h b/libxfs/xfs_swapext.h
index 01bb3271f64..fa786bc9352 100644
--- a/libxfs/xfs_swapext.h
+++ b/libxfs/xfs_swapext.h
@@ -72,4 +72,147 @@ xfs_atomic_swap_supported(
 	return false;
 }
 
+/*
+ * In-core information about an extent swap request between ranges of two
+ * inodes.
+ */
+struct xfs_swapext_intent {
+	/* List of other incore deferred work. */
+	struct list_head	sxi_list;
+
+	/* Inodes participating in the operation. */
+	struct xfs_inode	*sxi_ip1;
+	struct xfs_inode	*sxi_ip2;
+
+	/* File offset range information. */
+	xfs_fileoff_t		sxi_startoff1;
+	xfs_fileoff_t		sxi_startoff2;
+	xfs_filblks_t		sxi_blockcount;
+
+	/* Set these file sizes after the operation, unless negative. */
+	xfs_fsize_t		sxi_isize1;
+	xfs_fsize_t		sxi_isize2;
+
+	/* XFS_SWAP_EXT_* log operation flags */
+	unsigned int		sxi_flags;
+
+	/* XFS_SWAP_EXT_OP_* flags */
+	unsigned int		sxi_op_flags;
+};
+
+/* Use log intent items to track and restart the entire operation. */
+#define XFS_SWAP_EXT_OP_LOGGED	(1U << 0)
+
+/* Upgrade files to have large extent counts before proceeding. */
+#define XFS_SWAP_EXT_OP_NREXT64	(1U << 1)
+
+#define XFS_SWAP_EXT_OP_STRINGS \
+	{ XFS_SWAP_EXT_OP_LOGGED,		"LOGGED" }, \
+	{ XFS_SWAP_EXT_OP_NREXT64,		"NREXT64" }
+
+static inline int
+xfs_swapext_whichfork(const struct xfs_swapext_intent *sxi)
+{
+	if (sxi->sxi_flags & XFS_SWAP_EXT_ATTR_FORK)
+		return XFS_ATTR_FORK;
+	return XFS_DATA_FORK;
+}
+
+/* Parameters for a swapext request. */
+struct xfs_swapext_req {
+	/* Inodes participating in the operation. */
+	struct xfs_inode	*ip1;
+	struct xfs_inode	*ip2;
+
+	/* File offset range information. */
+	xfs_fileoff_t		startoff1;
+	xfs_fileoff_t		startoff2;
+	xfs_filblks_t		blockcount;
+
+	/* Data or attr fork? */
+	int			whichfork;
+
+	/* XFS_SWAP_REQ_* operation flags */
+	unsigned int		req_flags;
+
+	/*
+	 * Fields below this line are filled out by xfs_swapext_estimate;
+	 * callers should initialize this part of the struct to zero.
+	 */
+
+	/*
+	 * Data device blocks to be moved out of ip1, and free space needed to
+	 * handle the bmbt changes.
+	 */
+	xfs_filblks_t		ip1_bcount;
+
+	/*
+	 * Data device blocks to be moved out of ip2, and free space needed to
+	 * handle the bmbt changes.
+	 */
+	xfs_filblks_t		ip2_bcount;
+
+	/* rt blocks to be moved out of ip1. */
+	xfs_filblks_t		ip1_rtbcount;
+
+	/* rt blocks to be moved out of ip2. */
+	xfs_filblks_t		ip2_rtbcount;
+
+	/* Free space needed to handle the bmbt changes */
+	unsigned long long	resblks;
+
+	/* Number of extent swaps needed to complete the operation */
+	unsigned long long	nr_exchanges;
+};
+
+/* Caller has permission to use log intent items for the swapext operation. */
+#define XFS_SWAP_REQ_LOGGED		(1U << 0)
+
+/* Set the file sizes when finished. */
+#define XFS_SWAP_REQ_SET_SIZES		(1U << 1)
+
+/*
+ * Swap only the parts of the two files where the file allocation units
+ * mapped to file1's range have been written to.
+ */
+#define XFS_SWAP_REQ_INO1_WRITTEN	(1U << 2)
+
+/* Files need to be upgraded to have large extent counts. */
+#define XFS_SWAP_REQ_NREXT64		(1U << 3)
+
+#define XFS_SWAP_REQ_FLAGS		(XFS_SWAP_REQ_LOGGED | \
+					 XFS_SWAP_REQ_SET_SIZES | \
+					 XFS_SWAP_REQ_INO1_WRITTEN | \
+					 XFS_SWAP_REQ_NREXT64)
+
+#define XFS_SWAP_REQ_STRINGS \
+	{ XFS_SWAP_REQ_LOGGED,		"LOGGED" }, \
+	{ XFS_SWAP_REQ_SET_SIZES,	"SETSIZES" }, \
+	{ XFS_SWAP_REQ_INO1_WRITTEN,	"INO1_WRITTEN" }, \
+	{ XFS_SWAP_REQ_NREXT64,		"NREXT64" }
+
+unsigned int xfs_swapext_reflink_prep(const struct xfs_swapext_req *req);
+void xfs_swapext_reflink_finish(struct xfs_trans *tp,
+		const struct xfs_swapext_req *req, unsigned int reflink_state);
+
+int xfs_swapext_estimate(struct xfs_swapext_req *req);
+
+extern struct kmem_cache	*xfs_swapext_intent_cache;
+
+int __init xfs_swapext_intent_init_cache(void);
+void xfs_swapext_intent_destroy_cache(void);
+
+struct xfs_swapext_intent *xfs_swapext_init_intent(
+		const struct xfs_swapext_req *req, unsigned int *reflink_state);
+void xfs_swapext_ensure_reflink(struct xfs_trans *tp,
+		const struct xfs_swapext_intent *sxi, unsigned int reflink_state);
+
+int xfs_swapext_finish_one(struct xfs_trans *tp,
+		struct xfs_swapext_intent *sxi);
+
+int xfs_swapext_check_extents(struct xfs_mount *mp,
+		const struct xfs_swapext_req *req);
+
+void xfs_swapext(struct xfs_trans *tp, const struct xfs_swapext_req *req);
+
 #endif /* __XFS_SWAPEXT_H_ */
diff --git a/libxfs/xfs_trans_space.h b/libxfs/xfs_trans_space.h
index 87b31c69a77..9640fc232c1 100644
--- a/libxfs/xfs_trans_space.h
+++ b/libxfs/xfs_trans_space.h
@@ -10,6 +10,10 @@
  * Components of space reservations.
  */
 
+/* Worst case number of bmaps that can be held in a block. */
+#define XFS_MAX_CONTIG_BMAPS_PER_BLOCK(mp)    \
+		(((mp)->m_bmap_dmxr[0]) - ((mp)->m_bmap_dmnr[0]))
+
 /* Worst case number of rmaps that can be held in a block. */
 #define XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)    \
 		(((mp)->m_rmap_mxr[0]) - ((mp)->m_rmap_mnr[0]))

[PATCH 07/20] xfs: add error injection to test swapext recovery

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add an errortag so that we can test recovery of swapext log items.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 io/inject.c           |    1 +
 libxfs/xfs_errortag.h |    4 +++-
 libxfs/xfs_swapext.c  |    4 ++++
 3 files changed, 8 insertions(+), 1 deletion(-)


diff --git a/io/inject.c b/io/inject.c
index 6ef1fc8d2f4..4b0cd76005c 100644
--- a/io/inject.c
+++ b/io/inject.c
@@ -63,6 +63,7 @@ error_tag(char *name)
 		{ XFS_ERRTAG_ATTR_LEAF_TO_NODE,		"attr_leaf_to_node" },
 		{ XFS_ERRTAG_WB_DELAY_MS,		"wb_delay_ms" },
 		{ XFS_ERRTAG_WRITE_DELAY_MS,		"write_delay_ms" },
+		{ XFS_ERRTAG_SWAPEXT_FINISH_ONE,	"swapext_finish_one" },
 		{ XFS_ERRTAG_MAX,			NULL }
 	};
 	int	count;
diff --git a/libxfs/xfs_errortag.h b/libxfs/xfs_errortag.h
index 01a9e86b303..263d62a8d70 100644
--- a/libxfs/xfs_errortag.h
+++ b/libxfs/xfs_errortag.h
@@ -63,7 +63,8 @@
 #define XFS_ERRTAG_ATTR_LEAF_TO_NODE			41
 #define XFS_ERRTAG_WB_DELAY_MS				42
 #define XFS_ERRTAG_WRITE_DELAY_MS			43
-#define XFS_ERRTAG_MAX					44
+#define XFS_ERRTAG_SWAPEXT_FINISH_ONE			44
+#define XFS_ERRTAG_MAX					45
 
 /*
  * Random factors for above tags, 1 means always, 2 means 1/2 time, etc.
@@ -111,5 +112,6 @@
 #define XFS_RANDOM_ATTR_LEAF_TO_NODE			1
 #define XFS_RANDOM_WB_DELAY_MS				3000
 #define XFS_RANDOM_WRITE_DELAY_MS			3000
+#define XFS_RANDOM_SWAPEXT_FINISH_ONE			1
 
 #endif /* __XFS_ERRORTAG_H_ */
diff --git a/libxfs/xfs_swapext.c b/libxfs/xfs_swapext.c
index 2462657c1f4..5de586c6816 100644
--- a/libxfs/xfs_swapext.c
+++ b/libxfs/xfs_swapext.c
@@ -21,6 +21,7 @@
 #include "xfs_quota_defs.h"
 #include "xfs_health.h"
 #include "defer_item.h"
+#include "xfs_errortag.h"
 
 struct kmem_cache	*xfs_swapext_intent_cache;
 
@@ -433,6 +434,9 @@ xfs_swapext_finish_one(
 			return error;
 	}
 
+	if (XFS_TEST_ERROR(false, tp->t_mountp, XFS_ERRTAG_SWAPEXT_FINISH_ONE))
+		return -EIO;
+
 	/* If we still have work to do, ask for a new transaction. */
 	if (sxi_has_more_swap_work(sxi) || sxi_has_postop_work(sxi)) {
 		trace_xfs_swapext_defer(tp->t_mountp, sxi);

[PATCH 08/20] xfs: condense extended attributes after an atomic swap

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add a new swapext flag that enables us to perform post-swap processing
on file2 once we're done swapping the extent maps.  If we were swapping
the extended attributes, we want to be able to convert file2's attr fork
from block to inline format.

This isn't used anywhere right now, but we need to have the basic ondisk
flags in place so that a future online xattr repair feature can create
salvaged attrs in a temporary file and swap the attr forks when ready.
If one file is in extents format and the other is inline, we will have to
promote both to extents format to perform the swap.  After the swap, we
can try to condense the fixed file's attr fork back down to inline
format if possible.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_log_format.h |    9 ++++++--
 libxfs/xfs_swapext.c    |   51 ++++++++++++++++++++++++++++++++++++++++++++++-
 libxfs/xfs_swapext.h    |    9 ++++++--
 3 files changed, 64 insertions(+), 5 deletions(-)


diff --git a/libxfs/xfs_log_format.h b/libxfs/xfs_log_format.h
index 3341792cf43..d4531060b6b 100644
--- a/libxfs/xfs_log_format.h
+++ b/libxfs/xfs_log_format.h
@@ -916,18 +916,23 @@ struct xfs_swap_extent {
 /* Clear the reflink flag from inode2 after the operation. */
 #define XFS_SWAP_EXT_CLEAR_INO2_REFLINK	(1ULL << 4)
 
+/* Try to convert inode2 from block to short format at the end, if possible. */
+#define XFS_SWAP_EXT_CVT_INO2_SF	(1ULL << 5)
+
 #define XFS_SWAP_EXT_FLAGS		(XFS_SWAP_EXT_ATTR_FORK | \
 					 XFS_SWAP_EXT_SET_SIZES | \
 					 XFS_SWAP_EXT_INO1_WRITTEN | \
 					 XFS_SWAP_EXT_CLEAR_INO1_REFLINK | \
-					 XFS_SWAP_EXT_CLEAR_INO2_REFLINK)
+					 XFS_SWAP_EXT_CLEAR_INO2_REFLINK | \
+					 XFS_SWAP_EXT_CVT_INO2_SF)
 
 #define XFS_SWAP_EXT_STRINGS \
 	{ XFS_SWAP_EXT_ATTR_FORK,		"ATTRFORK" }, \
 	{ XFS_SWAP_EXT_SET_SIZES,		"SETSIZES" }, \
 	{ XFS_SWAP_EXT_INO1_WRITTEN,		"INO1_WRITTEN" }, \
 	{ XFS_SWAP_EXT_CLEAR_INO1_REFLINK,	"CLEAR_INO1_REFLINK" }, \
-	{ XFS_SWAP_EXT_CLEAR_INO2_REFLINK,	"CLEAR_INO2_REFLINK" }
+	{ XFS_SWAP_EXT_CLEAR_INO2_REFLINK,	"CLEAR_INO2_REFLINK" }, \
+	{ XFS_SWAP_EXT_CVT_INO2_SF,		"CVT_INO2_SF" }
 
 /* This is the structure used to lay out an sxi log item in the log. */
 struct xfs_sxi_log_format {
diff --git a/libxfs/xfs_swapext.c b/libxfs/xfs_swapext.c
index 5de586c6816..d643cb870c7 100644
--- a/libxfs/xfs_swapext.c
+++ b/libxfs/xfs_swapext.c
@@ -22,6 +22,10 @@
 #include "xfs_health.h"
 #include "defer_item.h"
 #include "xfs_errortag.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_attr_leaf.h"
+#include "xfs_attr.h"
 
 struct kmem_cache	*xfs_swapext_intent_cache;
 
@@ -110,7 +114,8 @@ static inline bool
 sxi_has_postop_work(const struct xfs_swapext_intent *sxi)
 {
 	return sxi->sxi_flags & (XFS_SWAP_EXT_CLEAR_INO1_REFLINK |
-				 XFS_SWAP_EXT_CLEAR_INO2_REFLINK);
+				 XFS_SWAP_EXT_CLEAR_INO2_REFLINK |
+				 XFS_SWAP_EXT_CVT_INO2_SF);
 }
 
 static inline void
@@ -358,6 +363,36 @@ xfs_swapext_exchange_mappings(
 	sxi_advance(sxi, irec1);
 }
 
+/* Convert inode2's leaf attr fork back to shortform, if possible.. */
+STATIC int
+xfs_swapext_attr_to_sf(
+	struct xfs_trans		*tp,
+	struct xfs_swapext_intent	*sxi)
+{
+	struct xfs_da_args	args = {
+		.dp		= sxi->sxi_ip2,
+		.geo		= tp->t_mountp->m_attr_geo,
+		.whichfork	= XFS_ATTR_FORK,
+		.trans		= tp,
+	};
+	struct xfs_buf		*bp;
+	int			forkoff;
+	int			error;
+
+	if (!xfs_attr_is_leaf(sxi->sxi_ip2))
+		return 0;
+
+	error = xfs_attr3_leaf_read(tp, sxi->sxi_ip2, 0, &bp);
+	if (error)
+		return error;
+
+	forkoff = xfs_attr_shortform_allfit(bp, sxi->sxi_ip2);
+	if (forkoff == 0)
+		return 0;
+
+	return xfs_attr3_leaf_to_shortform(bp, &args, forkoff);
+}
+
 static inline void
 xfs_swapext_clear_reflink(
 	struct xfs_trans	*tp,
@@ -375,6 +410,16 @@ xfs_swapext_do_postop_work(
 	struct xfs_trans		*tp,
 	struct xfs_swapext_intent	*sxi)
 {
+	if (sxi->sxi_flags & XFS_SWAP_EXT_CVT_INO2_SF) {
+		int			error = 0;
+
+		if (sxi->sxi_flags & XFS_SWAP_EXT_ATTR_FORK)
+			error = xfs_swapext_attr_to_sf(tp, sxi);
+		sxi->sxi_flags &= ~XFS_SWAP_EXT_CVT_INO2_SF;
+		if (error)
+			return error;
+	}
+
 	if (sxi->sxi_flags & XFS_SWAP_EXT_CLEAR_INO1_REFLINK) {
 		xfs_swapext_clear_reflink(tp, sxi->sxi_ip1);
 		sxi->sxi_flags &= ~XFS_SWAP_EXT_CLEAR_INO1_REFLINK;
@@ -802,6 +847,8 @@ xfs_swapext_init_intent(
 
 	if (req->req_flags & XFS_SWAP_REQ_INO1_WRITTEN)
 		sxi->sxi_flags |= XFS_SWAP_EXT_INO1_WRITTEN;
+	if (req->req_flags & XFS_SWAP_REQ_CVT_INO2_SF)
+		sxi->sxi_flags |= XFS_SWAP_EXT_CVT_INO2_SF;
 
 	if (req->req_flags & XFS_SWAP_REQ_LOGGED)
 		sxi->sxi_op_flags |= XFS_SWAP_EXT_OP_LOGGED;
@@ -1021,6 +1068,8 @@ xfs_swapext(
 	ASSERT(!(req->req_flags & ~XFS_SWAP_REQ_FLAGS));
 	if (req->req_flags & XFS_SWAP_REQ_SET_SIZES)
 		ASSERT(req->whichfork == XFS_DATA_FORK);
+	if (req->req_flags & XFS_SWAP_REQ_CVT_INO2_SF)
+		ASSERT(req->whichfork == XFS_ATTR_FORK);
 
 	if (req->blockcount == 0)
 		return;
diff --git a/libxfs/xfs_swapext.h b/libxfs/xfs_swapext.h
index fa786bc9352..37842a4ee9a 100644
--- a/libxfs/xfs_swapext.h
+++ b/libxfs/xfs_swapext.h
@@ -180,16 +180,21 @@ struct xfs_swapext_req {
 /* Files need to be upgraded to have large extent counts. */
 #define XFS_SWAP_REQ_NREXT64		(1U << 3)
 
+/* Try to convert inode2's fork to local format, if possible. */
+#define XFS_SWAP_REQ_CVT_INO2_SF	(1U << 4)
+
 #define XFS_SWAP_REQ_FLAGS		(XFS_SWAP_REQ_LOGGED | \
 					 XFS_SWAP_REQ_SET_SIZES | \
 					 XFS_SWAP_REQ_INO1_WRITTEN | \
-					 XFS_SWAP_REQ_NREXT64)
+					 XFS_SWAP_REQ_NREXT64 | \
+					 XFS_SWAP_REQ_CVT_INO2_SF)
 
 #define XFS_SWAP_REQ_STRINGS \
 	{ XFS_SWAP_REQ_LOGGED,		"LOGGED" }, \
 	{ XFS_SWAP_REQ_SET_SIZES,	"SETSIZES" }, \
 	{ XFS_SWAP_REQ_INO1_WRITTEN,	"INO1_WRITTEN" }, \
-	{ XFS_SWAP_REQ_NREXT64,		"NREXT64" }
+	{ XFS_SWAP_REQ_NREXT64,		"NREXT64" }, \
+	{ XFS_SWAP_REQ_CVT_INO2_SF,	"CVT_INO2_SF" }
 
 unsigned int xfs_swapext_reflink_prep(const struct xfs_swapext_req *req);
 void xfs_swapext_reflink_finish(struct xfs_trans *tp,

[PATCH 09/20] xfs: condense directories after an atomic swap

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

The previous commit added a new swapext flag that enables us to perform
post-swap processing on file2 once we're done swapping the extent maps.
Now add this ability for directories.

This isn't used anywhere right now, but we need to have the basic ondisk
flags in place so that a future online directory repair feature can
create salvaged dirents in a temporary directory and swap the data forks
when ready.  If one file is in extents format and the other is inline,
we will have to promote both to extents format to perform the swap.
After the swap, we can try to condense the fixed directory down to
inline format if possible.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_swapext.c |   44 +++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 43 insertions(+), 1 deletion(-)


diff --git a/libxfs/xfs_swapext.c b/libxfs/xfs_swapext.c
index d643cb870c7..c5d404cfa56 100644
--- a/libxfs/xfs_swapext.c
+++ b/libxfs/xfs_swapext.c
@@ -26,6 +26,8 @@
 #include "xfs_da_btree.h"
 #include "xfs_attr_leaf.h"
 #include "xfs_attr.h"
+#include "xfs_dir2_priv.h"
+#include "xfs_dir2.h"
 
 struct kmem_cache	*xfs_swapext_intent_cache;
 
@@ -393,6 +395,42 @@ xfs_swapext_attr_to_sf(
 	return xfs_attr3_leaf_to_shortform(bp, &args, forkoff);
 }
 
+/* Convert inode2's block dir fork back to shortform, if possible.. */
+STATIC int
+xfs_swapext_dir_to_sf(
+	struct xfs_trans		*tp,
+	struct xfs_swapext_intent	*sxi)
+{
+	struct xfs_da_args	args = {
+		.dp		= sxi->sxi_ip2,
+		.geo		= tp->t_mountp->m_dir_geo,
+		.whichfork	= XFS_DATA_FORK,
+		.trans		= tp,
+	};
+	struct xfs_dir2_sf_hdr	sfh;
+	struct xfs_buf		*bp;
+	bool			isblock;
+	int			size;
+	int			error;
+
+	error = xfs_dir2_isblock(&args, &isblock);
+	if (error)
+		return error;
+
+	if (!isblock)
+		return 0;
+
+	error = xfs_dir3_block_read(tp, sxi->sxi_ip2, &bp);
+	if (error)
+		return error;
+
+	size = xfs_dir2_block_sfsize(sxi->sxi_ip2, bp->b_addr, &sfh);
+	if (size > xfs_inode_data_fork_size(sxi->sxi_ip2))
+		return 0;
+
+	return xfs_dir2_block_to_sf(&args, bp, size, &sfh);
+}
+
 static inline void
 xfs_swapext_clear_reflink(
 	struct xfs_trans	*tp,
@@ -415,6 +453,8 @@ xfs_swapext_do_postop_work(
 
 		if (sxi->sxi_flags & XFS_SWAP_EXT_ATTR_FORK)
 			error = xfs_swapext_attr_to_sf(tp, sxi);
+		else if (S_ISDIR(VFS_I(sxi->sxi_ip2)->i_mode))
+			error = xfs_swapext_dir_to_sf(tp, sxi);
 		sxi->sxi_flags &= ~XFS_SWAP_EXT_CVT_INO2_SF;
 		if (error)
 			return error;
@@ -1069,7 +1109,9 @@ xfs_swapext(
 	if (req->req_flags & XFS_SWAP_REQ_SET_SIZES)
 		ASSERT(req->whichfork == XFS_DATA_FORK);
 	if (req->req_flags & XFS_SWAP_REQ_CVT_INO2_SF)
-		ASSERT(req->whichfork == XFS_ATTR_FORK);
+		ASSERT(req->whichfork == XFS_ATTR_FORK ||
+		       (req->whichfork == XFS_DATA_FORK &&
+			S_ISDIR(VFS_I(req->ip2)->i_mode)));
 
 	if (req->blockcount == 0)
 		return;

[PATCH 10/20] xfs: condense symbolic links after an atomic swap

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

The previous commit added a new swapext flag that enables us to perform
post-swap processing on file2 once we're done swapping the extent maps.
Now add this ability for symlinks.

This isn't used anywhere right now, but we need to have the basic ondisk
flags in place so that a future online symlink repair feature can
salvage the remote target in a temporary link and swap the data forks
when ready.  If one file is in extents format and the other is inline,
we will have to promote both to extents format to perform the swap.
After the swap, we can try to condense the fixed symlink down to inline
format if possible.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_swapext.c        |   48 ++++++++++++++++++++++++++++++++++++++++++-
 libxfs/xfs_symlink_remote.c |   47 ++++++++++++++++++++++++++++++++++++++++++
 libxfs/xfs_symlink_remote.h |    1 +
 3 files changed, 95 insertions(+), 1 deletion(-)


diff --git a/libxfs/xfs_swapext.c b/libxfs/xfs_swapext.c
index c5d404cfa56..364ae16252d 100644
--- a/libxfs/xfs_swapext.c
+++ b/libxfs/xfs_swapext.c
@@ -28,6 +28,7 @@
 #include "xfs_attr.h"
 #include "xfs_dir2_priv.h"
 #include "xfs_dir2.h"
+#include "xfs_symlink_remote.h"
 
 struct kmem_cache	*xfs_swapext_intent_cache;
 
@@ -431,6 +432,48 @@ xfs_swapext_dir_to_sf(
 	return xfs_dir2_block_to_sf(&args, bp, size, &sfh);
 }
 
+/* Convert inode2's remote symlink target back to shortform, if possible. */
+STATIC int
+xfs_swapext_link_to_sf(
+	struct xfs_trans		*tp,
+	struct xfs_swapext_intent	*sxi)
+{
+	struct xfs_inode		*ip = sxi->sxi_ip2;
+	struct xfs_ifork		*ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
+	char				*buf;
+	int				error;
+
+	if (ifp->if_format == XFS_DINODE_FMT_LOCAL ||
+	    ip->i_disk_size > xfs_inode_data_fork_size(ip))
+		return 0;
+
+	/* Read the current symlink target into a buffer. */
+	buf = kmem_alloc(ip->i_disk_size + 1, KM_NOFS);
+	if (!buf) {
+		ASSERT(0);
+		return -ENOMEM;
+	}
+
+	error = xfs_symlink_remote_read(ip, buf);
+	if (error)
+		goto free;
+
+	/* Remove the blocks. */
+	error = xfs_symlink_remote_truncate(tp, ip);
+	if (error)
+		goto free;
+
+	/* Convert fork to local format and log our changes. */
+	xfs_idestroy_fork(ifp);
+	ifp->if_bytes = 0;
+	ifp->if_format = XFS_DINODE_FMT_LOCAL;
+	xfs_init_local_fork(ip, XFS_DATA_FORK, buf, ip->i_disk_size);
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_DDATA | XFS_ILOG_CORE);
+free:
+	kmem_free(buf);
+	return error;
+}
+
 static inline void
 xfs_swapext_clear_reflink(
 	struct xfs_trans	*tp,
@@ -455,6 +498,8 @@ xfs_swapext_do_postop_work(
 			error = xfs_swapext_attr_to_sf(tp, sxi);
 		else if (S_ISDIR(VFS_I(sxi->sxi_ip2)->i_mode))
 			error = xfs_swapext_dir_to_sf(tp, sxi);
+		else if (S_ISLNK(VFS_I(sxi->sxi_ip2)->i_mode))
+			error = xfs_swapext_link_to_sf(tp, sxi);
 		sxi->sxi_flags &= ~XFS_SWAP_EXT_CVT_INO2_SF;
 		if (error)
 			return error;
@@ -1111,7 +1156,8 @@ xfs_swapext(
 	if (req->req_flags & XFS_SWAP_REQ_CVT_INO2_SF)
 		ASSERT(req->whichfork == XFS_ATTR_FORK ||
 		       (req->whichfork == XFS_DATA_FORK &&
-			S_ISDIR(VFS_I(req->ip2)->i_mode)));
+			(S_ISDIR(VFS_I(req->ip2)->i_mode) ||
+			 S_ISLNK(VFS_I(req->ip2)->i_mode))));
 
 	if (req->blockcount == 0)
 		return;
diff --git a/libxfs/xfs_symlink_remote.c b/libxfs/xfs_symlink_remote.c
index 2f3aca8d02b..a4a242bc3d4 100644
--- a/libxfs/xfs_symlink_remote.c
+++ b/libxfs/xfs_symlink_remote.c
@@ -377,3 +377,50 @@ xfs_symlink_write_target(
 	ASSERT(pathlen == 0);
 	return 0;
 }
+
+/* Remove all the blocks from a symlink and invalidate buffers. */
+int
+xfs_symlink_remote_truncate(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip)
+{
+	struct xfs_bmbt_irec	mval[XFS_SYMLINK_MAPS];
+	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_buf		*bp;
+	int			nmaps = XFS_SYMLINK_MAPS;
+	int			done = 0;
+	int			i;
+	int			error;
+
+	/* Read mappings and invalidate buffers. */
+	error = xfs_bmapi_read(ip, 0, XFS_MAX_FILEOFF, mval, &nmaps, 0);
+	if (error)
+		return error;
+
+	for (i = 0; i < nmaps; i++) {
+		if (!xfs_bmap_is_real_extent(&mval[i]))
+			break;
+
+		error = xfs_trans_get_buf(tp, mp->m_ddev_targp,
+				XFS_FSB_TO_DADDR(mp, mval[i].br_startblock),
+				XFS_FSB_TO_BB(mp, mval[i].br_blockcount), 0,
+				&bp);
+		if (error)
+			return error;
+
+		xfs_trans_binval(tp, bp);
+	}
+
+	/* Unmap the remote blocks. */
+	error = xfs_bunmapi(tp, ip, 0, XFS_MAX_FILEOFF, 0, nmaps, &done);
+	if (error)
+		return error;
+	if (!done) {
+		ASSERT(done);
+		xfs_inode_mark_sick(ip, XFS_SICK_INO_SYMLINK);
+		return -EFSCORRUPTED;
+	}
+
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+	return 0;
+}
diff --git a/libxfs/xfs_symlink_remote.h b/libxfs/xfs_symlink_remote.h
index a63bd38ae4f..ac3dac8f617 100644
--- a/libxfs/xfs_symlink_remote.h
+++ b/libxfs/xfs_symlink_remote.h
@@ -22,5 +22,6 @@ int xfs_symlink_remote_read(struct xfs_inode *ip, char *link);
 int xfs_symlink_write_target(struct xfs_trans *tp, struct xfs_inode *ip,
 		const char *target_path, int pathlen, xfs_fsblock_t fs_blocks,
 		uint resblks);
+int xfs_symlink_remote_truncate(struct xfs_trans *tp, struct xfs_inode *ip);
 
 #endif /* __XFS_SYMLINK_REMOTE_H */

[PATCH 11/20] xfs: make atomic extent swapping support realtime files

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Now that bmap items support the realtime device, we can add the
necessary pieces to the atomic extent swapping code to support such
things.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 include/xfs_inode.h  |    5 ++
 libxfs/xfs_swapext.c |  165 +++++++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 161 insertions(+), 9 deletions(-)


diff --git a/include/xfs_inode.h b/include/xfs_inode.h
index bcac3a09c6b..302df4c6f7e 100644
--- a/include/xfs_inode.h
+++ b/include/xfs_inode.h
@@ -325,6 +325,11 @@ static inline bool xfs_inode_has_large_extent_counts(struct xfs_inode *ip)
 	return ip->i_diflags2 & XFS_DIFLAG2_NREXT64;
 }
 
+static inline bool xfs_inode_has_bigallocunit(struct xfs_inode *ip)
+{
+	return XFS_IS_REALTIME_INODE(ip) && ip->i_mount->m_sb.sb_rextsize > 1;
+}
+
 /* Always set the child's GID to this value, even if the parent is setgid. */
 #define CRED_FORCE_GID	(1U << 0)
 struct cred {
diff --git a/libxfs/xfs_swapext.c b/libxfs/xfs_swapext.c
index 364ae16252d..92d2f8fa133 100644
--- a/libxfs/xfs_swapext.c
+++ b/libxfs/xfs_swapext.c
@@ -29,6 +29,7 @@
 #include "xfs_dir2_priv.h"
 #include "xfs_dir2.h"
 #include "xfs_symlink_remote.h"
+#include "xfs_rtbitmap.h"
 
 struct kmem_cache	*xfs_swapext_intent_cache;
 
@@ -131,6 +132,102 @@ sxi_advance(
 	sxi->sxi_blockcount -= irec->br_blockcount;
 }
 
+#ifdef DEBUG
+/*
+ * If we're going to do a BUI-only extent swap, ensure that all mappings are
+ * aligned to the realtime extent size.
+ */
+static inline int
+xfs_swapext_check_rt_extents(
+	struct xfs_mount		*mp,
+	const struct xfs_swapext_req	*req)
+{
+	struct xfs_bmbt_irec		irec1, irec2;
+	xfs_fileoff_t			startoff1 = req->startoff1;
+	xfs_fileoff_t			startoff2 = req->startoff2;
+	xfs_filblks_t			blockcount = req->blockcount;
+	uint32_t			mod;
+	int				nimaps;
+	int				error;
+
+	/* xattrs don't live on the rt device */
+	if (req->whichfork == XFS_ATTR_FORK)
+		return 0;
+
+	/*
+	 * Caller got permission to use SXI log items, so log recovery will
+	 * finish the swap and not leave us with partially swapped rt extents
+	 * exposed to userspace.
+	 */
+	if (req->req_flags & XFS_SWAP_REQ_LOGGED)
+		return 0;
+
+	/*
+	 * Allocation units must be fully mapped to a file range.  For files
+	 * with a single-fsblock allocation unit, this is trivial.
+	 */
+	if (!xfs_inode_has_bigallocunit(req->ip2))
+		return 0;
+
+	/*
+	 * For multi-fsblock allocation units, we must check the alignment of
+	 * every single mapping.
+	 */
+	while (blockcount > 0) {
+		/* Read extent from the first file */
+		nimaps = 1;
+		error = xfs_bmapi_read(req->ip1, startoff1, blockcount,
+				&irec1, &nimaps, 0);
+		if (error)
+			return error;
+		ASSERT(nimaps == 1);
+
+		/* Read extent from the second file */
+		nimaps = 1;
+		error = xfs_bmapi_read(req->ip2, startoff2,
+				irec1.br_blockcount, &irec2, &nimaps,
+				0);
+		if (error)
+			return error;
+		ASSERT(nimaps == 1);
+
+		/*
+		 * We can only swap as many blocks as the smaller of the two
+		 * extent maps.
+		 */
+		irec1.br_blockcount = min(irec1.br_blockcount,
+					  irec2.br_blockcount);
+
+		/* Both mappings must be aligned to the realtime extent size. */
+		mod = xfs_rtb_to_rtxoff(mp, irec1.br_startoff);
+		if (mod) {
+			ASSERT(mod == 0);
+			return -EINVAL;
+		}
+
+		mod = xfs_rtb_to_rtxoff(mp, irec1.br_startoff);
+		if (mod) {
+			ASSERT(mod == 0);
+			return -EINVAL;
+		}
+
+		mod = xfs_rtb_to_rtxoff(mp, irec1.br_blockcount);
+		if (mod) {
+			ASSERT(mod == 0);
+			return -EINVAL;
+		}
+
+		startoff1 += irec1.br_blockcount;
+		startoff2 += irec1.br_blockcount;
+		blockcount -= irec1.br_blockcount;
+	}
+
+	return 0;
+}
+#else
+# define xfs_swapext_check_rt_extents(mp, req)		(0)
+#endif
+
 /* Check all extents to make sure we can actually swap them. */
 int
 xfs_swapext_check_extents(
@@ -150,12 +247,7 @@ xfs_swapext_check_extents(
 	    ifp2->if_format == XFS_DINODE_FMT_LOCAL)
 		return -EINVAL;
 
-	/* We don't support realtime data forks yet. */
-	if (!XFS_IS_REALTIME_INODE(req->ip1))
-		return 0;
-	if (req->whichfork == XFS_ATTR_FORK)
-		return 0;
-	return -EINVAL;
+	return xfs_swapext_check_rt_extents(mp, req);
 }
 
 #ifdef CONFIG_XFS_QUOTA
@@ -196,6 +288,8 @@ xfs_swapext_can_skip_mapping(
 	struct xfs_swapext_intent	*sxi,
 	struct xfs_bmbt_irec		*irec)
 {
+	struct xfs_mount		*mp = sxi->sxi_ip1->i_mount;
+
 	/* Do not skip this mapping if the caller did not tell us to. */
 	if (!(sxi->sxi_flags & XFS_SWAP_EXT_INO1_WRITTEN))
 		return false;
@@ -208,10 +302,63 @@ xfs_swapext_can_skip_mapping(
 	 * The mapping is unwritten or a hole.  It cannot be a delalloc
 	 * reservation because we already excluded those.  It cannot be an
 	 * unwritten extent with dirty page cache because we flushed the page
-	 * cache.  We don't support realtime files yet, so we needn't (yet)
-	 * deal with them.
+	 * cache.  For files where the allocation unit is 1FSB (files on the
+	 * data dev, rt files if the extent size is 1FSB), we can safely
+	 * skip this mapping.
 	 */
-	return true;
+	if (!xfs_inode_has_bigallocunit(sxi->sxi_ip1))
+		return true;
+
+	/*
+	 * For a realtime file with a multi-fsb allocation unit, the decision
+	 * is trickier because we can only swap full allocation units.
+	 * Unwritten mappings can appear in the middle of an rtx if the rtx is
+	 * partially written, but they can also appear for preallocations.
+	 *
+	 * If the mapping is a hole, skip it entirely.  Holes should align with
+	 * rtx boundaries.
+	 */
+	if (!xfs_bmap_is_real_extent(irec))
+		return true;
+
+	/*
+	 * All mappings below this point are unwritten.
+	 *
+	 * - If the beginning is not aligned to an rtx, trim the end of the
+	 *   mapping so that it does not cross an rtx boundary, and swap it.
+	 *
+	 * - If both ends are aligned to an rtx, skip the entire mapping.
+	 */
+	if (!isaligned_64(irec->br_startoff, mp->m_sb.sb_rextsize)) {
+		xfs_fileoff_t	new_end;
+
+		new_end = roundup_64(irec->br_startoff, mp->m_sb.sb_rextsize);
+		irec->br_blockcount = min(irec->br_blockcount,
+					  new_end - irec->br_startoff);
+		return false;
+	}
+	if (isaligned_64(irec->br_blockcount, mp->m_sb.sb_rextsize))
+		return true;
+
+	/*
+	 * All mappings below this point are unwritten, start on an rtx
+	 * boundary, and do not end on an rtx boundary.
+	 *
+	 * - If the mapping is longer than one rtx, trim the end of the mapping
+	 *   down to an rtx boundary and skip it.
+	 *
+	 * - The mapping is shorter than one rtx.  Swap it.
+	 */
+	if (irec->br_blockcount > mp->m_sb.sb_rextsize) {
+		xfs_fileoff_t	new_end;
+
+		new_end = rounddown_64(irec->br_startoff + irec->br_blockcount,
+				mp->m_sb.sb_rextsize);
+		irec->br_blockcount = new_end - irec->br_startoff;
+		return true;
+	}
+
+	return false;
 }
 
 /*

[PATCH 12/20] xfs: enable atomic swapext feature

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add the atomic swapext feature to the set of features that we will
permit.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_format.h |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)


diff --git a/libxfs/xfs_format.h b/libxfs/xfs_format.h
index 8b34754a579..7861539ab8b 100644
--- a/libxfs/xfs_format.h
+++ b/libxfs/xfs_format.h
@@ -398,7 +398,8 @@ xfs_sb_has_incompat_feature(
  */
 #define XFS_SB_FEAT_INCOMPAT_LOG_SWAPEXT  (1U << 31)
 #define XFS_SB_FEAT_INCOMPAT_LOG_ALL \
-	(XFS_SB_FEAT_INCOMPAT_LOG_XATTRS)
+		(XFS_SB_FEAT_INCOMPAT_LOG_XATTRS | \
+		 XFS_SB_FEAT_INCOMPAT_LOG_SWAPEXT)
 #define XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN	~XFS_SB_FEAT_INCOMPAT_LOG_ALL
 static inline bool
 xfs_sb_has_incompat_log_feature(

[PATCH 13/20] libhandle: add support for bulkstat v5

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add support to libhandle for generating file handles with bulkstat v5
structures.  xfs_fsr will need this to be able to interface with the new
vfs range swap ioctl, and other client programs will probably want this
over time.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 include/jdm.h   |   24 +++++++++++
 libhandle/jdm.c |  117 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 141 insertions(+)


diff --git a/include/jdm.h b/include/jdm.h
index c57fcae7fca..445737a6b5f 100644
--- a/include/jdm.h
+++ b/include/jdm.h
@@ -11,6 +11,7 @@ typedef void	jdm_fshandle_t;		/* filesystem handle */
 typedef void	jdm_filehandle_t;	/* filehandle */
 
 struct xfs_bstat;
+struct xfs_bulkstat;
 struct attrlist_cursor;
 struct parent;
 
@@ -23,6 +24,9 @@ jdm_new_filehandle( jdm_filehandle_t **handlep,	/* new filehandle */
 		    jdm_fshandle_t *fshandlep,	/* filesystem filehandle */
 		    struct xfs_bstat *sp);	/* bulkstat info */
 
+extern void jdm_new_filehandle_v5(jdm_filehandle_t **handlep, size_t *hlen,
+		jdm_fshandle_t *fshandlep, struct xfs_bulkstat *sp);
+
 extern void
 jdm_delete_filehandle( jdm_filehandle_t *handlep,/* filehandle to delete */
 		       size_t hlen);		/* filehandle size */
@@ -32,35 +36,55 @@ jdm_open( jdm_fshandle_t *fshandlep,
 	  struct xfs_bstat *sp,
 	  intgen_t oflags);
 
+extern intgen_t jdm_open_v5(jdm_fshandle_t *fshandlep, struct xfs_bulkstat *sp,
+		intgen_t oflags);
+
 extern intgen_t
 jdm_readlink( jdm_fshandle_t *fshandlep,
 	      struct xfs_bstat *sp,
 	      char *bufp,
 	      size_t bufsz);
 
+extern intgen_t jdm_readlink_v5(jdm_fshandle_t *fshandlep,
+		struct xfs_bulkstat *sp, char *bufp, size_t bufsz);
+
 extern intgen_t
 jdm_attr_multi(	jdm_fshandle_t *fshp,
 		struct xfs_bstat *statp,
 		char *bufp, int rtrvcnt, int flags);
 
+extern intgen_t jdm_attr_multi_v5(jdm_fshandle_t *fshp,
+		struct xfs_bulkstat *statp, char *bufp, int rtrvcnt,
+		int flags);
+
 extern intgen_t
 jdm_attr_list(	jdm_fshandle_t *fshp,
 		struct xfs_bstat *statp,
 		char *bufp, size_t bufsz, int flags,
 		struct attrlist_cursor *cursor);
 
+extern intgen_t jdm_attr_list_v5(jdm_fshandle_t *fshp,
+		struct xfs_bulkstat *statp, char *bufp, size_t bufsz, int
+		flags, struct attrlist_cursor *cursor);
+
 extern int
 jdm_parents( jdm_fshandle_t *fshp,
 		struct xfs_bstat *statp,
 		struct parent *bufp, size_t bufsz,
 		unsigned int *count);
 
+extern int jdm_parents_v5(jdm_fshandle_t *fshp, struct xfs_bulkstat *statp,
+		struct parent *bufp, size_t bufsz, unsigned int *count);
+
 extern int
 jdm_parentpaths( jdm_fshandle_t *fshp,
 		struct xfs_bstat *statp,
 		struct parent *bufp, size_t bufsz,
 		unsigned int *count);
 
+extern int jdm_parentpaths_v5(jdm_fshandle_t *fshp, struct xfs_bulkstat *statp,
+		struct parent *bufp, size_t bufsz, unsigned int *count);
+
 /* macro for determining the size of a structure member */
 #define sizeofmember( t, m )	sizeof( ( ( t * )0 )->m )
 
diff --git a/libhandle/jdm.c b/libhandle/jdm.c
index 07b0c60985e..e21aff2b2c1 100644
--- a/libhandle/jdm.c
+++ b/libhandle/jdm.c
@@ -41,6 +41,19 @@ jdm_fill_filehandle( filehandle_t *handlep,
 	handlep->fh_ino = statp->bs_ino;
 }
 
+static void
+jdm_fill_filehandle_v5(
+	struct filehandle	*handlep,
+	struct fshandle		*fshandlep,
+	struct xfs_bulkstat	*statp)
+{
+	handlep->fh_fshandle = *fshandlep;
+	handlep->fh_sz_following = FILEHANDLE_SZ_FOLLOWING;
+	memset(handlep->fh_pad, 0, FILEHANDLE_SZ_PAD);
+	handlep->fh_gen = statp->bs_gen;
+	handlep->fh_ino = statp->bs_ino;
+}
+
 jdm_fshandle_t *
 jdm_getfshandle( char *mntpnt )
 {
@@ -90,6 +103,22 @@ jdm_new_filehandle( jdm_filehandle_t **handlep,
 		jdm_fill_filehandle(*handlep, (fshandle_t *) fshandlep, statp);
 }
 
+void
+jdm_new_filehandle_v5(
+	jdm_filehandle_t	**handlep,
+	size_t			*hlen,
+	jdm_fshandle_t		*fshandlep,
+	struct xfs_bulkstat	*statp)
+{
+	/* allocate and fill filehandle */
+	*hlen = sizeof(filehandle_t);
+	*handlep = (filehandle_t *) malloc(*hlen);
+	if (!*handlep)
+		return;
+
+	jdm_fill_filehandle_v5(*handlep, (struct fshandle *)fshandlep, statp);
+}
+
 /* ARGSUSED */
 void
 jdm_delete_filehandle( jdm_filehandle_t *handlep, size_t hlen )
@@ -111,6 +140,19 @@ jdm_open( jdm_fshandle_t *fshp, struct xfs_bstat *statp, intgen_t oflags )
 	return fd;
 }
 
+intgen_t
+jdm_open_v5(
+	jdm_fshandle_t		*fshp,
+	struct xfs_bulkstat	*statp,
+	intgen_t		oflags)
+{
+	struct fshandle		*fshandlep = (struct fshandle *)fshp;
+	struct filehandle	filehandle;
+
+	jdm_fill_filehandle_v5(&filehandle, fshandlep, statp);
+	return open_by_fshandle(&filehandle, sizeof(filehandle), oflags);
+}
+
 intgen_t
 jdm_readlink( jdm_fshandle_t *fshp,
 	      struct xfs_bstat *statp,
@@ -128,6 +170,20 @@ jdm_readlink( jdm_fshandle_t *fshp,
 	return rval;
 }
 
+intgen_t
+jdm_readlink_v5(
+	jdm_fshandle_t		*fshp,
+	struct xfs_bulkstat	*statp,
+	char			*bufp,
+	size_t			bufsz)
+{
+	struct fshandle		*fshandlep = (struct fshandle *)fshp;
+	struct filehandle	filehandle;
+
+	jdm_fill_filehandle_v5(&filehandle, fshandlep, statp);
+	return readlink_by_handle(&filehandle, sizeof(filehandle), bufp, bufsz);
+}
+
 int
 jdm_attr_multi(	jdm_fshandle_t *fshp,
 		struct xfs_bstat *statp,
@@ -145,6 +201,22 @@ jdm_attr_multi(	jdm_fshandle_t *fshp,
 	return rval;
 }
 
+int
+jdm_attr_multi_v5(
+	jdm_fshandle_t		*fshp,
+	struct xfs_bulkstat	*statp,
+	char			*bufp,
+	int			rtrvcnt,
+	int			flags)
+{
+	struct fshandle		*fshandlep = (struct fshandle *)fshp;
+	struct filehandle	filehandle;
+
+	jdm_fill_filehandle_v5(&filehandle, fshandlep, statp);
+	return attr_multi_by_handle(&filehandle, sizeof(filehandle), bufp,
+			rtrvcnt, flags);
+}
+
 int
 jdm_attr_list(	jdm_fshandle_t *fshp,
 		struct xfs_bstat *statp,
@@ -166,6 +238,27 @@ jdm_attr_list(	jdm_fshandle_t *fshp,
 	return rval;
 }
 
+int
+jdm_attr_list_v5(
+	jdm_fshandle_t		*fshp,
+	struct xfs_bulkstat	*statp,
+	char			*bufp,
+	size_t			bufsz,
+	int			flags,
+	struct attrlist_cursor	*cursor)
+{
+	struct fshandle		*fshandlep = (struct fshandle *)fshp;
+	struct filehandle	filehandle;
+
+	/* prevent needless EINVAL from the kernel */
+	if (bufsz > XFS_XATTR_LIST_MAX)
+		bufsz = XFS_XATTR_LIST_MAX;
+
+	jdm_fill_filehandle_v5(&filehandle, fshandlep, statp);
+	return attr_list_by_handle(&filehandle, sizeof(filehandle), bufp,
+			bufsz, flags, cursor);
+}
+
 int
 jdm_parents( jdm_fshandle_t *fshp,
 		struct xfs_bstat *statp,
@@ -176,6 +269,18 @@ jdm_parents( jdm_fshandle_t *fshp,
 	return -1;
 }
 
+int
+jdm_parents_v5(
+	jdm_fshandle_t		*fshp,
+	struct xfs_bulkstat	*statp,
+	struct parent		*bufp,
+	size_t			bufsz,
+	unsigned int		*count)
+{
+	errno = EOPNOTSUPP;
+	return -1;
+}
+
 int
 jdm_parentpaths( jdm_fshandle_t *fshp,
 		struct xfs_bstat *statp,
@@ -185,3 +290,15 @@ jdm_parentpaths( jdm_fshandle_t *fshp,
 	errno = EOPNOTSUPP;
 	return -1;
 }
+
+int
+jdm_parentpaths_v5(
+	jdm_fshandle_t		*fshp,
+	struct xfs_bulkstat	*statp,
+	struct parent		*bufp,
+	size_t			bufsz,
+	unsigned int		*count)
+{
+	errno = EOPNOTSUPP;
+	return -1;
+}

[PATCH 14/20] libfrog: convert xfs_io swapext command to use new libfrog wrapper

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create an abstraction layer for the two swapext ioctls and port xfs_io
to use it.  Now we're insulated from the differences between the XFS v0
ioctl and the new vfs ioctl.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 io/swapext.c            |   54 ++++++++-------
 libfrog/Makefile        |    2 +
 libfrog/file_exchange.c |  169 +++++++++++++++++++++++++++++++++++++++++++++++
 libfrog/file_exchange.h |   14 ++++
 libfrog/fsgeom.h        |    6 ++
 5 files changed, 218 insertions(+), 27 deletions(-)
 create mode 100644 libfrog/file_exchange.c
 create mode 100644 libfrog/file_exchange.h


diff --git a/io/swapext.c b/io/swapext.c
index a4153bb7d42..15ed3559398 100644
--- a/io/swapext.c
+++ b/io/swapext.c
@@ -10,7 +10,7 @@
 #include "io.h"
 #include "libfrog/logging.h"
 #include "libfrog/fsgeom.h"
-#include "libfrog/bulkstat.h"
+#include "libfrog/file_exchange.h"
 
 static cmdinfo_t swapext_cmd;
 
@@ -28,47 +28,47 @@ swapext_f(
 	int			argc,
 	char			**argv)
 {
-	struct xfs_fd		fxfd = XFS_FD_INIT(file->fd);
-	struct xfs_bulkstat	bulkstat;
-	int			fd;
-	int			error;
-	struct xfs_swapext	sx;
+	struct xfs_fd		xfd = XFS_FD_INIT(file->fd);
+	struct xfs_exch_range	fxr;
 	struct stat		stat;
+	uint64_t		flags = XFS_EXCH_RANGE_FILE2_FRESH |
+					XFS_EXCH_RANGE_FULL_FILES;
+	int			fd;
+	int			ret;
 
 	/* open the donor file */
 	fd = openfile(argv[1], NULL, 0, 0, NULL);
 	if (fd < 0)
 		return 0;
 
-	/*
-	 * stat the target file to get the inode number and use the latter to
-	 * get the bulkstat info for the swapext cmd.
-	 */
-	error = fstat(file->fd, &stat);
-	if (error) {
+	ret = -xfd_prepare_geometry(&xfd);
+	if (ret) {
+		xfrog_perror(ret, "xfd_prepare_geometry");
+		exitcode = 1;
+		goto out;
+	}
+
+	ret = fstat(file->fd, &stat);
+	if (ret) {
 		perror("fstat");
+		exitcode = 1;
 		goto out;
 	}
 
-	error = -xfrog_bulkstat_single(&fxfd, stat.st_ino, 0, &bulkstat);
-	if (error) {
-		xfrog_perror(error, "bulkstat");
+	ret = xfrog_file_exchange_prep(&xfd, flags, 0, fd, 0, stat.st_size,
+			&fxr);
+	if (ret) {
+		xfrog_perror(ret, "xfrog_file_exchange_prep");
+		exitcode = 1;
 		goto out;
 	}
-	error = -xfrog_bulkstat_v5_to_v1(&fxfd, &sx.sx_stat, &bulkstat);
-	if (error) {
-		xfrog_perror(error, "bulkstat conversion");
+
+	ret = xfrog_file_exchange(&xfd, &fxr);
+	if (ret) {
+		xfrog_perror(ret, "swapext");
+		exitcode = 1;
 		goto out;
 	}
-	sx.sx_version = XFS_SX_VERSION;
-	sx.sx_fdtarget = file->fd;
-	sx.sx_fdtmp = fd;
-	sx.sx_offset = 0;
-	sx.sx_length = stat.st_size;
-	error = ioctl(file->fd, XFS_IOC_SWAPEXT, &sx);
-	if (error)
-		perror("swapext");
-
 out:
 	close(fd);
 	return 0;
diff --git a/libfrog/Makefile b/libfrog/Makefile
index dcfd1fb8a93..f8bb39f2712 100644
--- a/libfrog/Makefile
+++ b/libfrog/Makefile
@@ -18,6 +18,7 @@ bitmap.c \
 bulkstat.c \
 convert.c \
 crc32.c \
+file_exchange.c \
 fsgeom.c \
 list_sort.c \
 linux.c \
@@ -42,6 +43,7 @@ crc32defs.h \
 crc32table.h \
 dahashselftest.h \
 div64.h \
+file_exchange.h \
 fsgeom.h \
 logging.h \
 paths.h \
diff --git a/libfrog/file_exchange.c b/libfrog/file_exchange.c
new file mode 100644
index 00000000000..4a66aa752fc
--- /dev/null
+++ b/libfrog/file_exchange.c
@@ -0,0 +1,169 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2020-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/ioctl.h>
+#include <unistd.h>
+#include <string.h>
+#include "xfs.h"
+#include "fsgeom.h"
+#include "bulkstat.h"
+#include "file_exchange.h"
+
+/* Prepare the freshness component of a swapext request. */
+static int
+xfrog_file_exchange_prep_freshness(
+	struct xfs_fd		*dest,
+	struct xfs_exch_range	*req)
+{
+	struct stat		stat;
+	struct xfs_bulkstat	bulkstat;
+	int			error;
+
+	error = fstat(dest->fd, &stat);
+	if (error)
+		return -errno;
+	req->file2_ino = stat.st_ino;
+
+	/*
+	 * Try to fill out the [cm]time data from bulkstat.  We prefer this
+	 * approach because bulkstat v5 gives us 64-bit time even on 32-bit.
+	 *
+	 * However, we'll take our chances on the C library if the filesystem
+	 * supports 64-bit time but we ended up with bulkstat v5 emulation.
+	 */
+	error = xfrog_bulkstat_single(dest, stat.st_ino, 0, &bulkstat);
+	if (!error &&
+	    !((dest->fsgeom.flags & XFS_FSOP_GEOM_FLAGS_BIGTIME) &&
+	      bulkstat.bs_version < XFS_BULKSTAT_VERSION_V5)) {
+		req->file2_mtime = bulkstat.bs_mtime;
+		req->file2_ctime = bulkstat.bs_ctime;
+		req->file2_mtime_nsec = bulkstat.bs_mtime_nsec;
+		req->file2_ctime_nsec = bulkstat.bs_ctime_nsec;
+		return 0;
+	}
+
+	/* Otherwise, use the stat information and hope for the best. */
+	req->file2_mtime = stat.st_mtime;
+	req->file2_ctime = stat.st_ctime;
+	req->file2_mtime_nsec = stat.st_mtim.tv_nsec;
+	req->file2_ctime_nsec = stat.st_ctim.tv_nsec;
+	return 0;
+}
+
+/* Prepare an extent swap request. */
+int
+xfrog_file_exchange_prep(
+	struct xfs_fd		*dest,
+	uint64_t		flags,
+	int64_t			file2_offset,
+	int			file1_fd,
+	int64_t			file1_offset,
+	int64_t			length,
+	struct xfs_exch_range	*req)
+{
+	memset(req, 0, sizeof(*req));
+	req->file1_fd = file1_fd;
+	req->file1_offset = file1_offset;
+	req->length = length;
+	req->file2_offset = file2_offset;
+	req->flags = flags;
+
+	if (flags & XFS_EXCH_RANGE_FILE2_FRESH)
+		return xfrog_file_exchange_prep_freshness(dest, req);
+
+	return 0;
+}
+
+/* Swap two files' extents with the new exchange range ioctl. */
+static int
+xfrog_file_exchange_range(
+	struct xfs_fd		*xfd,
+	struct xfs_exch_range	*req)
+{
+	int			ret;
+
+	ret = ioctl(xfd->fd, XFS_IOC_EXCHANGE_RANGE, req);
+	if (ret) {
+		/* the old swapext ioctl returned EFAULT for bad length */
+		if (errno == EDOM)
+			return -EFAULT;
+		return -errno;
+	}
+	return 0;
+}
+
+/*
+ * The old swapext ioctl did not provide atomic swap; it required that the
+ * supplied offset and length matched both files' lengths; and it also required
+ * that the sx_stat information match the dest file.  It doesn't support any
+ * other flags.
+ */
+#define XFS_EXCH_RANGE_SWAPEXT	(XFS_EXCH_RANGE_NONATOMIC | \
+				 XFS_EXCH_RANGE_FULL_FILES | \
+				 XFS_EXCH_RANGE_FILE2_FRESH)
+
+/* Swap two files' extents with the old xfs swapext ioctl. */
+static int
+xfrog_file_exchange_swapext(
+	struct xfs_fd		*xfd,
+	struct xfs_exch_range	*req)
+{
+	struct xfs_swapext	sx = {
+		.sx_version	= XFS_SX_VERSION,
+		.sx_fdtarget	= xfd->fd,
+		.sx_fdtmp	= req->file1_fd,
+		.sx_length	= req->length,
+	};
+	int			ret;
+
+	if (req->file1_offset != req->file2_offset)
+		return -EINVAL;
+	if (req->flags != XFS_EXCH_RANGE_SWAPEXT)
+		return -EOPNOTSUPP;
+
+	sx.sx_stat.bs_ino = req->file2_ino;
+	sx.sx_stat.bs_ctime.tv_sec = req->file2_ctime;
+	sx.sx_stat.bs_ctime.tv_nsec = req->file2_ctime_nsec;
+	sx.sx_stat.bs_mtime.tv_sec = req->file2_mtime;
+	sx.sx_stat.bs_mtime.tv_nsec = req->file2_mtime_nsec;
+
+	ret = ioctl(xfd->fd, XFS_IOC_SWAPEXT, &sx);
+	if (ret)
+		return -errno;
+	return 0;
+}
+
+/* Swap extents between an XFS file and a donor fd. */
+int
+xfrog_file_exchange(
+	struct xfs_fd		*xfd,
+	struct xfs_exch_range	*req)
+{
+	int			error;
+
+	if (xfd->flags & XFROG_FLAG_FORCE_SWAPEXT)
+		goto try_swapext;
+
+	error = xfrog_file_exchange_range(xfd, req);
+	if ((error != -ENOTTY && error != -EOPNOTSUPP) ||
+	    (xfd->flags & XFROG_FLAG_FORCE_EXCH_RANGE))
+		return error;
+
+	/*
+	 * If the new exchange range ioctl wasn't found, punt to the old
+	 * swapext ioctl.
+	 */
+	switch (error) {
+	case -EOPNOTSUPP:
+	case -ENOTTY:
+		xfd->flags |= XFROG_FLAG_FORCE_SWAPEXT;
+		break;
+	}
+
+try_swapext:
+	return xfrog_file_exchange_swapext(xfd, req);
+}
diff --git a/libfrog/file_exchange.h b/libfrog/file_exchange.h
new file mode 100644
index 00000000000..7b6ce11810b
--- /dev/null
+++ b/libfrog/file_exchange.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2020-2024 Oracle.  All rights reserved.
+ * All Rights Reserved.
+ */
+#ifndef __LIBFROG_FILE_EXCHANGE_H__
+#define __LIBFROG_FILE_EXCHANGE_H__
+
+int xfrog_file_exchange_prep(struct xfs_fd *file2, uint64_t flags,
+		int64_t file2_offset, int file1_fd, int64_t file1_offset,
+		int64_t length, struct xfs_exch_range *req);
+int xfrog_file_exchange(struct xfs_fd *xfd, struct xfs_exch_range *req);
+
+#endif	/* __LIBFROG_FILE_EXCHANGE_H__ */
diff --git a/libfrog/fsgeom.h b/libfrog/fsgeom.h
index ca38324e853..2ff748caaf4 100644
--- a/libfrog/fsgeom.h
+++ b/libfrog/fsgeom.h
@@ -50,6 +50,12 @@ struct xfs_fd {
 /* Only use v5 bulkstat/inumbers ioctls. */
 #define XFROG_FLAG_BULKSTAT_FORCE_V5	(1 << 1)
 
+/* Only use XFS_IOC_SWAPEXT for file data exchanges. */
+#define XFROG_FLAG_FORCE_SWAPEXT	(1 << 2)
+
+/* Only use XFS_IOC_EXCHANGE_RANGE for file data exchanges. */
+#define XFROG_FLAG_FORCE_EXCH_RANGE	(1 << 3)
+
 /* Static initializers */
 #define XFS_FD_INIT(_fd)	{ .fd = (_fd), }
 #define XFS_FD_INIT_EMPTY	XFS_FD_INIT(-1)

[PATCH 15/20] xfs_logprint: support dumping swapext log items

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Support dumping swapext log items.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 logprint/log_misc.c      |   11 ++++
 logprint/log_print_all.c |   12 ++++
 logprint/log_redo.c      |  128 ++++++++++++++++++++++++++++++++++++++++++++++
 logprint/logprint.h      |    6 ++
 4 files changed, 157 insertions(+)


diff --git a/logprint/log_misc.c b/logprint/log_misc.c
index 836156e0d58..565e7b76284 100644
--- a/logprint/log_misc.c
+++ b/logprint/log_misc.c
@@ -1052,6 +1052,17 @@ xlog_print_record(
 					be32_to_cpu(op_head->oh_len));
 			break;
 		    }
+		    case XFS_LI_SXI: {
+			skip = xlog_print_trans_sxi(&ptr,
+					be32_to_cpu(op_head->oh_len),
+					continued);
+			break;
+		    }
+		    case XFS_LI_SXD: {
+			skip = xlog_print_trans_sxd(&ptr,
+					be32_to_cpu(op_head->oh_len));
+			break;
+		    }
 		    case XFS_LI_QUOTAOFF: {
 			skip = xlog_print_trans_qoff(&ptr,
 					be32_to_cpu(op_head->oh_len));
diff --git a/logprint/log_print_all.c b/logprint/log_print_all.c
index 8d3ede190e5..6e528fcd097 100644
--- a/logprint/log_print_all.c
+++ b/logprint/log_print_all.c
@@ -440,6 +440,12 @@ xlog_recover_print_logitem(
 	case XFS_LI_BUI:
 		xlog_recover_print_bui(item);
 		break;
+	case XFS_LI_SXD:
+		xlog_recover_print_sxd(item);
+		break;
+	case XFS_LI_SXI:
+		xlog_recover_print_sxi(item);
+		break;
 	case XFS_LI_DQUOT:
 		xlog_recover_print_dquot(item);
 		break;
@@ -498,6 +504,12 @@ xlog_recover_print_item(
 	case XFS_LI_BUI:
 		printf("BUI");
 		break;
+	case XFS_LI_SXD:
+		printf("SXD");
+		break;
+	case XFS_LI_SXI:
+		printf("SXI");
+		break;
 	case XFS_LI_DQUOT:
 		printf("DQ ");
 		break;
diff --git a/logprint/log_redo.c b/logprint/log_redo.c
index edf7e0fbfa9..770485df75d 100644
--- a/logprint/log_redo.c
+++ b/logprint/log_redo.c
@@ -847,3 +847,131 @@ xlog_recover_print_attrd(
 		f->alfd_size,
 		(unsigned long long)f->alfd_alf_id);
 }
+
+/* Atomic Extent Swapping Items */
+
+static int
+xfs_sxi_copy_format(
+	struct xfs_sxi_log_format *sxi,
+	uint			  len,
+	struct xfs_sxi_log_format *dst_fmt,
+	int			  continued)
+{
+	if (len == sizeof(struct xfs_sxi_log_format) || continued) {
+		memcpy(dst_fmt, sxi, len);
+		return 0;
+	}
+	fprintf(stderr, _("%s: bad size of SXI format: %u; expected %zu\n"),
+		progname, len, sizeof(struct xfs_sxi_log_format));
+	return 1;
+}
+
+int
+xlog_print_trans_sxi(
+	char			**ptr,
+	uint			src_len,
+	int			continued)
+{
+	struct xfs_sxi_log_format *src_f, *f = NULL;
+	struct xfs_swap_extent	*ex;
+	int			error = 0;
+
+	src_f = malloc(src_len);
+	if (src_f == NULL) {
+		fprintf(stderr, _("%s: %s: malloc failed\n"),
+			progname, __func__);
+		exit(1);
+	}
+	memcpy(src_f, *ptr, src_len);
+	*ptr += src_len;
+
+	/* convert to native format */
+	if (continued && src_len < sizeof(struct xfs_sxi_log_format)) {
+		printf(_("SXI: Not enough data to decode further\n"));
+		error = 1;
+		goto error;
+	}
+
+	f = malloc(sizeof(struct xfs_sxi_log_format));
+	if (f == NULL) {
+		fprintf(stderr, _("%s: %s: malloc failed\n"),
+			progname, __func__);
+		exit(1);
+	}
+	if (xfs_sxi_copy_format(src_f, src_len, f, continued)) {
+		error = 1;
+		goto error;
+	}
+
+	printf(_("SXI:  #regs: %d	num_extents: 1  id: 0x%llx\n"),
+		f->sxi_size, (unsigned long long)f->sxi_id);
+
+	if (continued) {
+		printf(_("SXI extent data skipped (CONTINUE set, no space)\n"));
+		goto error;
+	}
+
+	ex = &f->sxi_extent;
+	printf("(ino1: 0x%llx, ino2: 0x%llx, off1: %lld, off2: %lld, len: %lld, flags: 0x%llx)\n",
+		(unsigned long long)ex->sx_inode1,
+		(unsigned long long)ex->sx_inode2,
+		(unsigned long long)ex->sx_startoff1,
+		(unsigned long long)ex->sx_startoff2,
+		(unsigned long long)ex->sx_blockcount,
+		(unsigned long long)ex->sx_flags);
+error:
+	free(src_f);
+	free(f);
+	return error;
+}
+
+void
+xlog_recover_print_sxi(
+	struct xlog_recover_item	*item)
+{
+	char				*src_f;
+	uint				src_len;
+
+	src_f = item->ri_buf[0].i_addr;
+	src_len = item->ri_buf[0].i_len;
+
+	xlog_print_trans_sxi(&src_f, src_len, 0);
+}
+
+int
+xlog_print_trans_sxd(
+	char				**ptr,
+	uint				len)
+{
+	struct xfs_sxd_log_format	*f;
+	struct xfs_sxd_log_format	lbuf;
+
+	/* size without extents at end */
+	uint core_size = sizeof(struct xfs_sxd_log_format);
+
+	memcpy(&lbuf, *ptr, min(core_size, len));
+	f = &lbuf;
+	*ptr += len;
+	if (len >= core_size) {
+		printf(_("SXD:  #regs: %d	                 id: 0x%llx\n"),
+			f->sxd_size,
+			(unsigned long long)f->sxd_sxi_id);
+
+		/* don't print extents as they are not used */
+
+		return 0;
+	} else {
+		printf(_("SXD: Not enough data to decode further\n"));
+		return 1;
+	}
+}
+
+void
+xlog_recover_print_sxd(
+	struct xlog_recover_item	*item)
+{
+	char				*f;
+
+	f = item->ri_buf[0].i_addr;
+	xlog_print_trans_sxd(&f, sizeof(struct xfs_sxd_log_format));
+}
diff --git a/logprint/logprint.h b/logprint/logprint.h
index b4479c240d9..892b280b548 100644
--- a/logprint/logprint.h
+++ b/logprint/logprint.h
@@ -65,4 +65,10 @@ extern void xlog_recover_print_attri(struct xlog_recover_item *item);
 extern int xlog_print_trans_attrd(char **ptr, uint len);
 extern void xlog_recover_print_attrd(struct xlog_recover_item *item);
 extern void xlog_print_op_header(xlog_op_header_t *op_head, int i, char **ptr);
+
+extern int xlog_print_trans_sxi(char **ptr, uint src_len, int continued);
+extern void xlog_recover_print_sxi(struct xlog_recover_item *item);
+extern int xlog_print_trans_sxd(char **ptr, uint len);
+extern void xlog_recover_print_sxd(struct xlog_recover_item *item);
+
 #endif	/* LOGPRINT_H */

[PATCH 16/20] xfs_fsr: convert to bulkstat v5 ioctls

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Now that libhandle can, er, handle bulkstat information coming from the
v5 bulkstat ioctl, port xfs_fsr to use the new interfaces instead of
repeatedly converting things back and forth.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fsr/xfs_fsr.c    |  148 ++++++++++++++++++++++++++++++------------------------
 libfrog/fsgeom.c |   45 ++++++++++++----
 libfrog/fsgeom.h |    1 
 3 files changed, 117 insertions(+), 77 deletions(-)


diff --git a/fsr/xfs_fsr.c b/fsr/xfs_fsr.c
index ba02506d8e4..8e916faee94 100644
--- a/fsr/xfs_fsr.c
+++ b/fsr/xfs_fsr.c
@@ -65,10 +65,10 @@ static int	pagesize;
 
 void usage(int ret);
 static int  fsrfile(char *fname, xfs_ino_t ino);
-static int  fsrfile_common( char *fname, char *tname, char *mnt,
-                            int fd, struct xfs_bstat *statp);
-static int  packfile(char *fname, char *tname, int fd,
-                     struct xfs_bstat *statp, struct fsxattr *fsxp);
+static int  fsrfile_common(char *fname, char *tname, char *mnt,
+			   struct xfs_fd *file_fd, struct xfs_bulkstat *statp);
+static int  packfile(char *fname, char *tname, struct xfs_fd *file_fd,
+                     struct xfs_bulkstat *statp, struct fsxattr *fsxp);
 static void fsrdir(char *dirname);
 static int  fsrfs(char *mntdir, xfs_ino_t ino, int targetrange);
 static void initallfs(char *mtab);
@@ -80,7 +80,7 @@ int xfs_getrt(int fd, struct statvfs *sfbp);
 char * gettmpname(char *fname);
 char * getparent(char *fname);
 int fsrprintf(const char *fmt, ...);
-int read_fd_bmap(int, struct xfs_bstat *, int *);
+int read_fd_bmap(int, struct xfs_bulkstat *, int *);
 static void tmp_init(char *mnt);
 static char * tmp_next(char *mnt);
 static void tmp_close(char *mnt);
@@ -102,6 +102,26 @@ static int	nfrags = 0;	/* Debug option: Coerse into specific number
 				 * of extents */
 static int	openopts = O_CREAT|O_EXCL|O_RDWR|O_DIRECT;
 
+/*
+ * Open a file on an XFS filesystem from file handle components and fs geometry
+ * data.  Returns zero or a negative error code.
+ */
+static int
+open_handle(
+	struct xfs_fd		*xfd,
+	jdm_fshandle_t		*fshandle,
+	struct xfs_bulkstat	*bulkstat,
+	struct xfs_fsop_geom	*fsgeom,
+	int			flags)
+{
+	xfd->fd = jdm_open_v5(fshandle, bulkstat, flags);
+	if (xfd->fd < 0)
+		return errno;
+
+	xfd_install_geometry(xfd, fsgeom);
+	return 0;
+}
+
 static int
 xfs_swapext(int fd, xfs_swapext_t *sx)
 {
@@ -600,7 +620,6 @@ static int
 fsrfs(char *mntdir, xfs_ino_t startino, int targetrange)
 {
 	struct xfs_fd	fsxfd = XFS_FD_INIT_EMPTY;
-	int	fd;
 	int	count = 0;
 	int	ret;
 	char	fname[64];
@@ -638,10 +657,10 @@ fsrfs(char *mntdir, xfs_ino_t startino, int targetrange)
 	}
 
 	while ((ret = -xfrog_bulkstat(&fsxfd, breq) == 0)) {
-		struct xfs_bstat	bs1;
 		struct xfs_bulkstat	*buf = breq->bulkstat;
 		struct xfs_bulkstat	*p;
 		struct xfs_bulkstat	*endp;
+		struct xfs_fd		file_fd = XFS_FD_INIT_EMPTY;
 		uint32_t		buflenout = breq->hdr.ocount;
 
 		if (buflenout == 0)
@@ -658,15 +677,9 @@ fsrfs(char *mntdir, xfs_ino_t startino, int targetrange)
 			     (p->bs_extents64 < 2))
 				continue;
 
-			ret = -xfrog_bulkstat_v5_to_v1(&fsxfd, &bs1, p);
+			ret = open_handle(&file_fd, fshandlep, p,
+					&fsxfd.fsgeom, O_RDWR | O_DIRECT);
 			if (ret) {
-				fsrprintf(_("bstat conversion error: %s\n"),
-						strerror(ret));
-				continue;
-			}
-
-			fd = jdm_open(fshandlep, &bs1, O_RDWR | O_DIRECT);
-			if (fd < 0) {
 				/* This probably means the file was
 				 * removed while in progress of handling
 				 * it.  Just quietly ignore this file.
@@ -683,11 +696,12 @@ fsrfs(char *mntdir, xfs_ino_t startino, int targetrange)
 			/* Get a tmp file name */
 			tname = tmp_next(mntdir);
 
-			ret = fsrfile_common(fname, tname, mntdir, fd, &bs1);
+			ret = fsrfile_common(fname, tname, mntdir, &file_fd,
+					p);
 
 			leftoffino = p->bs_ino;
 
-			close(fd);
+			xfd_close(&file_fd);
 
 			if (ret == 0) {
 				if (--count <= 0)
@@ -735,9 +749,8 @@ fsrfile(
 {
 	struct xfs_fd		fsxfd = XFS_FD_INIT_EMPTY;
 	struct xfs_bulkstat	bulkstat;
-	struct xfs_bstat	statbuf;
+	struct xfs_fd		file_fd = XFS_FD_INIT_EMPTY;
 	jdm_fshandle_t		*fshandlep;
-	int			fd = -1;
 	int			error = -1;
 	char			*tname;
 
@@ -765,17 +778,12 @@ fsrfile(
 			fname, strerror(error));
 		goto out;
 	}
-	error = -xfrog_bulkstat_v5_to_v1(&fsxfd, &statbuf, &bulkstat);
-	if (error) {
-		fsrprintf(_("bstat conversion error on %s: %s\n"),
-			fname, strerror(error));
-		goto out;
-	}
 
-	fd = jdm_open(fshandlep, &statbuf, O_RDWR|O_DIRECT);
-	if (fd < 0) {
+	error = open_handle(&file_fd, fshandlep, &bulkstat, &fsxfd.fsgeom,
+			O_RDWR | O_DIRECT);
+	if (error) {
 		fsrprintf(_("unable to open handle %s: %s\n"),
-			fname, strerror(errno));
+			fname, strerror(error));
 		goto out;
 	}
 
@@ -783,14 +791,13 @@ fsrfile(
 	memcpy(&fsgeom, &fsxfd.fsgeom, sizeof(fsgeom));
 
 	tname = gettmpname(fname);
-
 	if (tname)
-		error = fsrfile_common(fname, tname, NULL, fd, &statbuf);
+		error = fsrfile_common(fname, tname, NULL, &file_fd,
+				&bulkstat);
 
 out:
 	xfd_close(&fsxfd);
-	if (fd >= 0)
-		close(fd);
+	xfd_close(&file_fd);
 	free(fshandlep);
 
 	return error;
@@ -816,8 +823,8 @@ fsrfile_common(
 	char		*fname,
 	char		*tname,
 	char		*fsname,
-	int		fd,
-	struct xfs_bstat *statp)
+	struct xfs_fd	*file_fd,
+	struct xfs_bulkstat *statp)
 {
 	int		error;
 	struct statvfs  vfss;
@@ -827,7 +834,7 @@ fsrfile_common(
 	if (vflag)
 		fsrprintf("%s\n", fname);
 
-	if (fsync(fd) < 0) {
+	if (fsync(file_fd->fd) < 0) {
 		fsrprintf(_("sync failed: %s: %s\n"), fname, strerror(errno));
 		return -1;
 	}
@@ -851,7 +858,7 @@ fsrfile_common(
 		fl.l_whence = SEEK_SET;
 		fl.l_start = (off_t)0;
 		fl.l_len = 0;
-		if ((fcntl(fd, F_GETLK, &fl)) < 0 ) {
+		if ((fcntl(file_fd->fd, F_GETLK, &fl)) < 0 ) {
 			if (vflag)
 				fsrprintf(_("locking check failed: %s\n"),
 					fname);
@@ -869,7 +876,7 @@ fsrfile_common(
 	/*
 	 * Check if there is room to copy the file.
 	 *
-	 * Note that xfs_bstat.bs_blksize returns the filesystem blocksize,
+	 * Note that xfs_bulkstat.bs_blksize returns the filesystem blocksize,
 	 * not the optimal I/O size as struct stat.
 	 */
 	if (statvfs(fsname ? fsname : fname, &vfss) < 0) {
@@ -886,7 +893,7 @@ fsrfile_common(
 		return 1;
 	}
 
-	if ((ioctl(fd, FS_IOC_FSGETXATTR, &fsx)) < 0) {
+	if ((ioctl(file_fd->fd, FS_IOC_FSGETXATTR, &fsx)) < 0) {
 		fsrprintf(_("failed to get inode attrs: %s\n"), fname);
 		return(-1);
 	}
@@ -902,7 +909,7 @@ fsrfile_common(
 		return(0);
 	}
 	if (fsx.fsx_xflags & FS_XFLAG_REALTIME) {
-		if (xfs_getrt(fd, &vfss) < 0) {
+		if (xfs_getrt(file_fd->fd, &vfss) < 0) {
 			fsrprintf(_("cannot get realtime geometry for: %s\n"),
 				fname);
 			return(-1);
@@ -928,7 +935,7 @@ fsrfile_common(
 	 * file we're defragging, in packfile().
 	 */
 
-	if ((error = packfile(fname, tname, fd, statp, &fsx)))
+	if ((error = packfile(fname, tname, file_fd, statp, &fsx)))
 		return error;
 	return -1; /* no error */
 }
@@ -952,7 +959,7 @@ static int
 fsr_setup_attr_fork(
 	int		fd,
 	int		tfd,
-	struct xfs_bstat *bstatp)
+	struct xfs_bulkstat *bstatp)
 {
 #ifdef HAVE_FSETXATTR
 	struct xfs_fd	txfd = XFS_FD_INIT(tfd);
@@ -1136,23 +1143,28 @@ fsr_setup_attr_fork(
  *  1: No change / No Error
  */
 static int
-packfile(char *fname, char *tname, int fd,
-	 struct xfs_bstat *statp, struct fsxattr *fsxp)
+packfile(
+	char			*fname,
+	char			*tname,
+	struct xfs_fd		*file_fd,
+	struct xfs_bulkstat	*statp,
+	struct fsxattr		*fsxp)
 {
-	int 		tfd = -1;
-	int		srval;
-	int		retval = -1;	/* Failure is the default */
-	int		nextents, extent, cur_nextents, new_nextents;
-	unsigned	blksz_dio;
-	unsigned	dio_min;
-	struct dioattr	dio;
-	static xfs_swapext_t   sx;
-	struct xfs_flock64  space;
-	off64_t 	cnt, pos;
-	void 		*fbuf = NULL;
-	int 		ct, wc, wc_b4;
-	char		ffname[SMBUFSZ];
-	int		ffd = -1;
+	int			tfd = -1;
+	int			srval;
+	int			retval = -1;	/* Failure is the default */
+	int			nextents, extent, cur_nextents, new_nextents;
+	unsigned		blksz_dio;
+	unsigned		dio_min;
+	struct dioattr		dio;
+	static xfs_swapext_t	sx;
+	struct xfs_flock64	space;
+	off64_t			cnt, pos;
+	void			*fbuf = NULL;
+	int			ct, wc, wc_b4;
+	char			ffname[SMBUFSZ];
+	int			ffd = -1;
+	int			error;
 
 	/*
 	 * Work out the extent map - nextents will be set to the
@@ -1160,7 +1172,7 @@ packfile(char *fname, char *tname, int fd,
 	 * into account holes), cur_nextents is the current number
 	 * of extents.
 	 */
-	nextents = read_fd_bmap(fd, statp, &cur_nextents);
+	nextents = read_fd_bmap(file_fd->fd, statp, &cur_nextents);
 
 	if (cur_nextents == 1 || cur_nextents <= nextents) {
 		if (vflag)
@@ -1183,7 +1195,7 @@ packfile(char *fname, char *tname, int fd,
 	unlink(tname);
 
 	/* Setup extended attributes */
-	if (fsr_setup_attr_fork(fd, tfd, statp) != 0) {
+	if (fsr_setup_attr_fork(file_fd->fd, tfd, statp) != 0) {
 		fsrprintf(_("failed to set ATTR fork on tmp: %s:\n"), tname);
 		goto out;
 	}
@@ -1301,7 +1313,7 @@ packfile(char *fname, char *tname, int fd,
 				   tname, strerror(errno));
 				goto out;
 			}
-			if (lseek(fd, outmap[extent].bmv_length, SEEK_CUR) < 0) {
+			if (lseek(file_fd->fd, outmap[extent].bmv_length, SEEK_CUR) < 0) {
 				fsrprintf(_("could not lseek in file: %s : %s\n"),
 				   fname, strerror(errno));
 				goto out;
@@ -1321,7 +1333,7 @@ packfile(char *fname, char *tname, int fd,
 				ct = min(cnt + dio_min - (cnt % dio_min),
 					blksz_dio);
 			}
-			ct = read(fd, fbuf, ct);
+			ct = read(file_fd->fd, fbuf, ct);
 			if (ct == 0) {
 				/* EOF, stop trying to read */
 				extent = nextents;
@@ -1392,9 +1404,15 @@ packfile(char *fname, char *tname, int fd,
 		goto out;
 	}
 
-	sx.sx_stat     = *statp; /* struct copy */
+	error = -xfrog_bulkstat_v5_to_v1(file_fd, &sx.sx_stat, statp);
+	if (error) {
+		fsrprintf(_("bstat conversion error on %s: %s\n"),
+				fname, strerror(error));
+		goto out;
+	}
+
 	sx.sx_version  = XFS_SX_VERSION;
-	sx.sx_fdtarget = fd;
+	sx.sx_fdtarget = file_fd->fd;
 	sx.sx_fdtmp    = tfd;
 	sx.sx_offset   = 0;
 	sx.sx_length   = statp->bs_size;
@@ -1408,7 +1426,7 @@ packfile(char *fname, char *tname, int fd,
         }
 
 	/* Swap the extents */
-	srval = xfs_swapext(fd, &sx);
+	srval = xfs_swapext(file_fd->fd, &sx);
 	if (srval < 0) {
 		if (errno == ENOTSUP) {
 			if (vflag || dflag)
@@ -1504,7 +1522,7 @@ getparent(char *fname)
 #define MAPSIZE	128
 #define	OUTMAP_SIZE_INCREMENT	MAPSIZE
 
-int	read_fd_bmap(int fd, struct xfs_bstat *sin, int *cur_nextents)
+int	read_fd_bmap(int fd, struct xfs_bulkstat *sin, int *cur_nextents)
 {
 	int		i, cnt;
 	struct getbmap	map[MAPSIZE];
diff --git a/libfrog/fsgeom.c b/libfrog/fsgeom.c
index 3e7f0797d8b..6980d3ffab6 100644
--- a/libfrog/fsgeom.c
+++ b/libfrog/fsgeom.c
@@ -102,29 +102,50 @@ xfrog_geometry(
 	return -errno;
 }
 
-/*
- * Prepare xfs_fd structure for future ioctl operations by computing the xfs
- * geometry for @xfd->fd.  Returns zero or a negative error code.
- */
-int
-xfd_prepare_geometry(
+/* Compute conversion factors of an xfs_fd structure. */
+static void
+xfd_compute_conversion_factors(
 	struct xfs_fd		*xfd)
 {
-	int			ret;
-
-	ret = xfrog_geometry(xfd->fd, &xfd->fsgeom);
-	if (ret)
-		return ret;
-
 	xfd->agblklog = log2_roundup(xfd->fsgeom.agblocks);
 	xfd->blocklog = highbit32(xfd->fsgeom.blocksize);
 	xfd->inodelog = highbit32(xfd->fsgeom.inodesize);
 	xfd->inopblog = xfd->blocklog - xfd->inodelog;
 	xfd->aginolog = xfd->agblklog + xfd->inopblog;
 	xfd->blkbb_log = xfd->blocklog - BBSHIFT;
+}
+
+/*
+ * Prepare xfs_fd structure for future ioctl operations by computing the xfs
+ * geometry for @xfd->fd.  Returns zero or a negative error code.
+ */
+int
+xfd_prepare_geometry(
+	struct xfs_fd		*xfd)
+{
+	int			ret;
+
+	ret = xfrog_geometry(xfd->fd, &xfd->fsgeom);
+	if (ret)
+		return ret;
+
+	xfd_compute_conversion_factors(xfd);
 	return 0;
 }
 
+/*
+ * Prepare xfs_fd structure for future ioctl operations by computing the xfs
+ * geometry for @xfd->fd.  Returns zero or a negative error code.
+ */
+void
+xfd_install_geometry(
+	struct xfs_fd		*xfd,
+	struct xfs_fsop_geom	*fsgeom)
+{
+	memcpy(&xfd->fsgeom, fsgeom, sizeof(*fsgeom));
+	xfd_compute_conversion_factors(xfd);
+}
+
 /* Open a file on an XFS filesystem.  Returns zero or a negative error code. */
 int
 xfd_open(
diff --git a/libfrog/fsgeom.h b/libfrog/fsgeom.h
index 2ff748caaf4..7e002c5137a 100644
--- a/libfrog/fsgeom.h
+++ b/libfrog/fsgeom.h
@@ -61,6 +61,7 @@ struct xfs_fd {
 #define XFS_FD_INIT_EMPTY	XFS_FD_INIT(-1)
 
 int xfd_prepare_geometry(struct xfs_fd *xfd);
+void xfd_install_geometry(struct xfs_fd *xfd, struct xfs_fsop_geom *fsgeom);
 int xfd_open(struct xfs_fd *xfd, const char *pathname, int flags);
 int xfd_close(struct xfs_fd *xfd);
 

[PATCH 17/20] xfs_fsr: port to new swapext library function

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Port fsr to use the new libfrog library functions to handle swapext.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fsr/xfs_fsr.c           |   79 +++++++++++++++++++++++------------------------
 libfrog/file_exchange.c |   17 ++++++++++
 libfrog/file_exchange.h |    2 +
 3 files changed, 58 insertions(+), 40 deletions(-)


diff --git a/fsr/xfs_fsr.c b/fsr/xfs_fsr.c
index 8e916faee94..37cacffa0fd 100644
--- a/fsr/xfs_fsr.c
+++ b/fsr/xfs_fsr.c
@@ -13,6 +13,7 @@
 #include "libfrog/paths.h"
 #include "libfrog/fsgeom.h"
 #include "libfrog/bulkstat.h"
+#include "libfrog/file_exchange.h"
 
 #include <fcntl.h>
 #include <errno.h>
@@ -122,12 +123,6 @@ open_handle(
 	return 0;
 }
 
-static int
-xfs_swapext(int fd, xfs_swapext_t *sx)
-{
-    return ioctl(fd, XFS_IOC_SWAPEXT, sx);
-}
-
 static int
 xfs_fscounts(int fd, xfs_fsop_counts_t *counts)
 {
@@ -1150,14 +1145,13 @@ packfile(
 	struct xfs_bulkstat	*statp,
 	struct fsxattr		*fsxp)
 {
+	struct xfs_exch_range	fxr;
 	int			tfd = -1;
-	int			srval;
 	int			retval = -1;	/* Failure is the default */
 	int			nextents, extent, cur_nextents, new_nextents;
 	unsigned		blksz_dio;
 	unsigned		dio_min;
 	struct dioattr		dio;
-	static xfs_swapext_t	sx;
 	struct xfs_flock64	space;
 	off64_t			cnt, pos;
 	void			*fbuf = NULL;
@@ -1194,6 +1188,20 @@ packfile(
 	}
 	unlink(tname);
 
+	/*
+	 * Set up everything in the swap request except for the destination
+	 * freshness check, which we'll do separately since we already have
+	 * a bulkstat.
+	 */
+	error = xfrog_file_exchange_prep(file_fd,
+			XFS_EXCH_RANGE_NONATOMIC | XFS_EXCH_RANGE_FULL_FILES,
+			0, tfd, 0, statp->bs_size, &fxr);
+	if (error) {
+		fsrprintf(_("error %d setting up swapext request\n"), error);
+		goto out;
+	}
+	xfrog_file_exchange_require_file2_fresh(&fxr, statp);
+
 	/* Setup extended attributes */
 	if (fsr_setup_attr_fork(file_fd->fd, tfd, statp) != 0) {
 		fsrprintf(_("failed to set ATTR fork on tmp: %s:\n"), tname);
@@ -1404,19 +1412,6 @@ packfile(
 		goto out;
 	}
 
-	error = -xfrog_bulkstat_v5_to_v1(file_fd, &sx.sx_stat, statp);
-	if (error) {
-		fsrprintf(_("bstat conversion error on %s: %s\n"),
-				fname, strerror(error));
-		goto out;
-	}
-
-	sx.sx_version  = XFS_SX_VERSION;
-	sx.sx_fdtarget = file_fd->fd;
-	sx.sx_fdtmp    = tfd;
-	sx.sx_offset   = 0;
-	sx.sx_length   = statp->bs_size;
-
 	/* switch to the owner's id, to keep quota in line */
         if (fchown(tfd, statp->bs_uid, statp->bs_gid) < 0) {
                 if (vflag)
@@ -1426,25 +1421,29 @@ packfile(
         }
 
 	/* Swap the extents */
-	srval = xfs_swapext(file_fd->fd, &sx);
-	if (srval < 0) {
-		if (errno == ENOTSUP) {
-			if (vflag || dflag)
-			   fsrprintf(_("%s: file type not supported\n"), fname);
-		} else if (errno == EFAULT) {
-			/* The file has changed since we started the copy */
-			if (vflag || dflag)
-			   fsrprintf(_("%s: file modified defrag aborted\n"),
-				     fname);
-		} else if (errno == EBUSY) {
-			/* Timestamp has changed or mmap'ed file */
-			if (vflag || dflag)
-			   fsrprintf(_("%s: file busy\n"), fname);
-		} else {
-			fsrprintf(_("XFS_IOC_SWAPEXT failed: %s: %s\n"),
-				  fname, strerror(errno));
-		}
-		goto out;
+	error = xfrog_file_exchange(file_fd, &fxr);
+	switch (error) {
+		case 0:
+			break;
+	case ENOTSUP:
+		if (vflag || dflag)
+			fsrprintf(_("%s: file type not supported\n"), fname);
+		break;
+	case EFAULT:
+	case EDOM:
+		/* The file has changed since we started the copy */
+		if (vflag || dflag)
+			fsrprintf(_("%s: file modified defrag aborted\n"),
+					fname);
+		break;
+	case EBUSY:
+		/* Timestamp has changed or mmap'ed file */
+		if (vflag || dflag)
+			fsrprintf(_("%s: file busy\n"), fname);
+		break;
+	default:
+		fsrprintf(_("XFS_IOC_SWAPEXT failed: %s: %s\n"),
+			  fname, strerror(error));
 	}
 
 	/* Report progress */
diff --git a/libfrog/file_exchange.c b/libfrog/file_exchange.c
index 4a66aa752fc..5a527489aa5 100644
--- a/libfrog/file_exchange.c
+++ b/libfrog/file_exchange.c
@@ -54,6 +54,23 @@ xfrog_file_exchange_prep_freshness(
 	return 0;
 }
 
+/*
+ * Enable checking that the target (or destination) file has not been modified
+ * since a particular point in time.
+ */
+void
+xfrog_file_exchange_require_file2_fresh(
+	struct xfs_exch_range	*req,
+	struct xfs_bulkstat	*bulkstat)
+{
+	req->flags |= XFS_EXCH_RANGE_FILE2_FRESH;
+	req->file2_ino = bulkstat->bs_ino;
+	req->file2_mtime = bulkstat->bs_mtime;
+	req->file2_ctime = bulkstat->bs_ctime;
+	req->file2_mtime_nsec = bulkstat->bs_mtime_nsec;
+	req->file2_ctime_nsec = bulkstat->bs_ctime_nsec;
+}
+
 /* Prepare an extent swap request. */
 int
 xfrog_file_exchange_prep(
diff --git a/libfrog/file_exchange.h b/libfrog/file_exchange.h
index 7b6ce11810b..63dedf46a2f 100644
--- a/libfrog/file_exchange.h
+++ b/libfrog/file_exchange.h
@@ -6,6 +6,8 @@
 #ifndef __LIBFROG_FILE_EXCHANGE_H__
 #define __LIBFROG_FILE_EXCHANGE_H__
 
+void xfrog_file_exchange_require_file2_fresh(struct xfs_exch_range *req,
+		struct xfs_bulkstat *bulkstat);
 int xfrog_file_exchange_prep(struct xfs_fd *file2, uint64_t flags,
 		int64_t file2_offset, int file1_fd, int64_t file1_offset,
 		int64_t length, struct xfs_exch_range *req);

[PATCH 18/20] xfs_fsr: skip the xattr/forkoff levering with the newer swapext implementations

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

The newer swapext implementations in the kernel run at a high enough
level (above the bmap layer) that it's no longer required to manipulate
bs_forkoff by creating garbage xattrs to get the extent tree that we
want.  If we detect the newer algorithms, skip this error prone step.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fsr/xfs_fsr.c |   16 ++++++++++++++++
 1 file changed, 16 insertions(+)


diff --git a/fsr/xfs_fsr.c b/fsr/xfs_fsr.c
index 37cacffa0fd..44fc46dd2b1 100644
--- a/fsr/xfs_fsr.c
+++ b/fsr/xfs_fsr.c
@@ -968,6 +968,22 @@ fsr_setup_attr_fork(
 	if (!(bstatp->bs_xflags & FS_XFLAG_HASATTR))
 		return 0;
 
+	/*
+	 * If the filesystem has the ability to perform atomic extent swaps or
+	 * has the reverse mapping btree enabled, the file extent swap
+	 * implementation uses a higher level algorithm that calls into the
+	 * bmap code instead of playing games with swapping the extent forks.
+	 *
+	 * The newer bmap implementation does not require specific values of
+	 * bs_forkoff, unlike the old fork swap code.  Therefore, leave the
+	 * extended attributes alone if we know we're not using the old fork
+	 * swap strategy.  This eliminates a major source of runtime errors
+	 * in fsr.
+	 */
+	if (fsgeom.flags & (XFS_FSOP_GEOM_FLAGS_ATOMIC_SWAP |
+			    XFS_FSOP_GEOM_FLAGS_RMAPBT))
+		return 0;
+
 	/*
 	 * use the old method if we have attr1 or the kernel does not yet
 	 * support passing the fork offset in the bulkstat data.

[PATCH 19/20] xfs_io: enhance swapext to take advantage of new api

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Enhance the swapext command so that we can take advantage of the new
API's features and print some timing information.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 io/swapext.c      |  156 +++++++++++++++++++++++++++++++++++++++++++++++++----
 man/man8/xfs_io.8 |   54 ++++++++++++++++++
 2 files changed, 197 insertions(+), 13 deletions(-)


diff --git a/io/swapext.c b/io/swapext.c
index 15ed3559398..22476ec7563 100644
--- a/io/swapext.c
+++ b/io/swapext.c
@@ -20,7 +20,36 @@ swapext_help(void)
 	printf(_(
 "\n"
 " Swaps extents between the open file descriptor and the supplied filename.\n"
-"\n"));
+"\n"
+" -a   -- Use atomic extent swapping\n"
+" -C   -- Print timing information in a condensed format\n"
+" -d N -- Start swapping extents at this offset in the open file\n"
+" -e   -- Swap extents to the ends of both files, including the file sizes\n"
+" -f   -- Flush changed file data and metadata to disk\n"
+" -h   -- Only swap written ranges in the supplied file\n"
+" -l N -- Swap this many bytes between the two files\n"
+" -n   -- Dry run; do all the parameter validation but do not change anything.\n"
+" -s N -- Start swapping extents at this offset in the supplied file\n"
+" -t   -- Print timing information\n"
+" -u   -- Do not compare the open file's timestamps\n"
+" -v   -- 'swapext' for XFS_IOC_SWAPEXT, or 'exchrange' for XFS_IOC_EXCHANGE_RANGE\n"));
+}
+
+static void
+set_xfd_flags(
+	struct xfs_fd	*xfd,
+	int		api_ver)
+{
+	switch (api_ver) {
+	case 0:
+		xfd->flags |= XFROG_FLAG_FORCE_SWAPEXT;
+		break;
+	case 1:
+		xfd->flags |= XFROG_FLAG_FORCE_EXCH_RANGE;
+		break;
+	default:
+		break;
+	}
 }
 
 static int
@@ -31,13 +60,101 @@ swapext_f(
 	struct xfs_fd		xfd = XFS_FD_INIT(file->fd);
 	struct xfs_exch_range	fxr;
 	struct stat		stat;
-	uint64_t		flags = XFS_EXCH_RANGE_FILE2_FRESH |
+	struct timeval		t1, t2;
+	uint64_t		flags = XFS_EXCH_RANGE_NONATOMIC |
+					XFS_EXCH_RANGE_FILE2_FRESH |
 					XFS_EXCH_RANGE_FULL_FILES;
+	int64_t			src_offset = 0;
+	int64_t			dest_offset = 0;
+	int64_t			length = -1;
+	size_t			fsblocksize, fssectsize;
+	int			condensed = 0, quiet_flag = 1;
+	int			api_ver = -1;
+	int			c;
 	int			fd;
 	int			ret;
 
+	init_cvtnum(&fsblocksize, &fssectsize);
+	while ((c = getopt(argc, argv, "Cad:efhl:ns:tuv:")) != -1) {
+		switch (c) {
+		case 'C':
+			condensed = 1;
+			break;
+		case 'a':
+			flags &= ~XFS_EXCH_RANGE_NONATOMIC;
+			break;
+		case 'd':
+			dest_offset = cvtnum(fsblocksize, fssectsize, optarg);
+			if (dest_offset < 0) {
+				printf(
+			_("non-numeric open file offset argument -- %s\n"),
+						optarg);
+				return 0;
+			}
+			flags &= ~XFS_EXCH_RANGE_FULL_FILES;
+			break;
+		case 'e':
+			flags |= XFS_EXCH_RANGE_TO_EOF;
+			flags &= ~XFS_EXCH_RANGE_FULL_FILES;
+			break;
+		case 'f':
+			flags |= XFS_EXCH_RANGE_FSYNC;
+			break;
+		case 'h':
+			flags |= XFS_EXCH_RANGE_FILE1_WRITTEN;
+			break;
+		case 'l':
+			length = cvtnum(fsblocksize, fssectsize, optarg);
+			if (length < 0) {
+				printf(
+			_("non-numeric length argument -- %s\n"),
+						optarg);
+				return 0;
+			}
+			flags &= ~XFS_EXCH_RANGE_FULL_FILES;
+			break;
+		case 'n':
+			flags |= XFS_EXCH_RANGE_DRY_RUN;
+			break;
+		case 's':
+			src_offset = cvtnum(fsblocksize, fssectsize, optarg);
+			if (src_offset < 0) {
+				printf(
+			_("non-numeric supplied file offset argument -- %s\n"),
+						optarg);
+				return 0;
+			}
+			flags &= ~XFS_EXCH_RANGE_FULL_FILES;
+			break;
+		case 't':
+			quiet_flag = 0;
+			break;
+		case 'u':
+			flags &= ~XFS_EXCH_RANGE_FILE2_FRESH;
+			break;
+		case 'v':
+			if (!strcmp(optarg, "swapext"))
+				api_ver = 0;
+			else if (!strcmp(optarg, "exchrange"))
+				api_ver = 1;
+			else {
+				fprintf(stderr,
+			_("version must be 'swapext' or 'exchrange'.\n"));
+				return 1;
+			}
+			break;
+		default:
+			swapext_help();
+			return 0;
+		}
+	}
+	if (optind != argc - 1) {
+		swapext_help();
+		return 0;
+	}
+
 	/* open the donor file */
-	fd = openfile(argv[1], NULL, 0, 0, NULL);
+	fd = openfile(argv[optind], NULL, 0, 0, NULL);
 	if (fd < 0)
 		return 0;
 
@@ -48,27 +165,42 @@ swapext_f(
 		goto out;
 	}
 
-	ret = fstat(file->fd, &stat);
-	if (ret) {
-		perror("fstat");
-		exitcode = 1;
-		goto out;
+	if (length < 0) {
+		ret = fstat(file->fd, &stat);
+		if (ret) {
+			perror("fstat");
+			exitcode = 1;
+			goto out;
+		}
+
+		length = stat.st_size;
 	}
 
-	ret = xfrog_file_exchange_prep(&xfd, flags, 0, fd, 0, stat.st_size,
-			&fxr);
+	ret = xfrog_file_exchange_prep(&xfd, flags, dest_offset, fd, src_offset,
+			length, &fxr);
 	if (ret) {
 		xfrog_perror(ret, "xfrog_file_exchange_prep");
 		exitcode = 1;
 		goto out;
 	}
 
+	set_xfd_flags(&xfd, api_ver);
+
+	gettimeofday(&t1, NULL);
 	ret = xfrog_file_exchange(&xfd, &fxr);
 	if (ret) {
 		xfrog_perror(ret, "swapext");
 		exitcode = 1;
 		goto out;
 	}
+	if (quiet_flag)
+		goto out;
+
+	gettimeofday(&t2, NULL);
+	t2 = tsub(t2, t1);
+
+	report_io_times("swapext", &t2, dest_offset, length, length, 1,
+			condensed);
 out:
 	close(fd);
 	return 0;
@@ -80,9 +212,9 @@ swapext_init(void)
 	swapext_cmd.name = "swapext";
 	swapext_cmd.cfunc = swapext_f;
 	swapext_cmd.argmin = 1;
-	swapext_cmd.argmax = 1;
+	swapext_cmd.argmax = -1;
 	swapext_cmd.flags = CMD_NOMAP_OK;
-	swapext_cmd.args = _("<donorfile>");
+	swapext_cmd.args = _("[-a] [-e] [-f] [-u] [-d dest_offset] [-s src_offset] [-l length] [-v swapext|exchrange] <donorfile>");
 	swapext_cmd.oneline = _("Swap extents between files.");
 	swapext_cmd.help = swapext_help;
 
diff --git a/man/man8/xfs_io.8 b/man/man8/xfs_io.8
index 56abe000f23..34f9ffe9433 100644
--- a/man/man8/xfs_io.8
+++ b/man/man8/xfs_io.8
@@ -708,10 +708,62 @@ bytes of data.
 .RE
 .PD
 .TP
-.BI swapext " donor_file "
+.BI "swapext [OPTIONS]" " donor_file "
 Swaps extent forks between files. The current open file is the target. The donor
 file is specified by path. Note that file data is not copied (file content moves
 with the fork(s)).
+Options include:
+.RS 1.0i
+.PD 0
+.TP 0.4i
+.B \-a
+Swap extent forks atomically.
+The filesystem must be able to complete the operation even if the system goes
+down.
+.TP
+.B \-C
+Print timing information in a condensed format.
+.TP
+.BI \-d " dest_offset"
+Swap extents with open file beginning at
+.IR dest_offset .
+.TP
+.B \-e
+Swap extents to the ends of both files, including the file sizes.
+.TP
+.B \-f
+Flush changed file data and file metadata to disk.
+.TP
+.B \-h
+Only swap written ranges in the supplied file.
+.TP
+.BI \-l " length"
+Swap up to
+.I length
+bytes of data.
+.TP
+.B \-n
+Perform all the parameter validation checks but don't change anything.
+.TP
+.BI \-s " src_offset"
+Swap extents with donor file beginning at
+.IR src_offset .
+.TP
+.B \-t
+Print timing information.
+.TP
+.B \-u
+Do not snapshot and compare the open file's timestamps.
+.TP
+.B \-v
+Use a particular version of the kernel interface.
+Currently supported values are
+.I xfs
+for the old XFS_IOC_SWAPEXT ioctl, and
+.I vfs
+for the new XFS_IOC_EXCHANGE_RANGE ioctl.
+.RE
+.PD
 .TP
 .BI "set_encpolicy [ \-c " mode " ] [ \-n " mode " ] [ \-f " flags " ] [ \-s " log2_dusize " ] [ \-v " version " ] [ " keyspec " ]"
 On filesystems that support encryption, assign an encryption policy to the

[PATCH 20/20] xfs_io: add atomic update commands to exercise extent swapping

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add three commands to xfs_io so that we can exercise atomic file updates
as provided by reflink and atomic swapext.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 io/Makefile       |    2 
 io/atomicupdate.c |  386 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 io/init.c         |    1 
 io/io.h           |    5 +
 io/open.c         |   27 +++-
 man/man8/xfs_io.8 |   32 ++++
 6 files changed, 446 insertions(+), 7 deletions(-)
 create mode 100644 io/atomicupdate.c


diff --git a/io/Makefile b/io/Makefile
index 53fef09e899..1be6ab77d87 100644
--- a/io/Makefile
+++ b/io/Makefile
@@ -13,7 +13,7 @@ CFILES = init.c \
 	file.c freeze.c fsuuid.c fsync.c getrusage.c imap.c inject.c label.c \
 	link.c mmap.c open.c parent.c pread.c prealloc.c pwrite.c reflink.c \
 	resblks.c scrub.c seek.c shutdown.c stat.c swapext.c sync.c \
-	truncate.c utimes.c
+	truncate.c utimes.c atomicupdate.c
 
 LLDLIBS = $(LIBXCMD) $(LIBHANDLE) $(LIBFROG) $(LIBPTHREAD) $(LIBUUID)
 LTDEPENDENCIES = $(LIBXCMD) $(LIBHANDLE) $(LIBFROG)
diff --git a/io/atomicupdate.c b/io/atomicupdate.c
new file mode 100644
index 00000000000..07957b32c19
--- /dev/null
+++ b/io/atomicupdate.c
@@ -0,0 +1,386 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2020-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "platform_defs.h"
+#include "command.h"
+#include "init.h"
+#include "io.h"
+#include "input.h"
+#include "libfrog/logging.h"
+#include "libfrog/fsgeom.h"
+#include "libfrog/file_exchange.h"
+
+struct update_info {
+	/* File object for the file that we're updating. */
+	struct xfs_fd		file_fd;
+
+	/* XFS_IOC_EXCHANGE_RANGE request to commit the changes. */
+	struct xfs_exch_range	xchg_req;
+
+	/* Name of the file we're updating. */
+	char			*old_fname;
+
+	/* fd we're using to stage the updates. */
+	int			temp_fd;
+};
+
+enum finish_how	{
+	FINISH_ABORT,
+	FINISH_COMMIT,
+	FINISH_CHECK
+};
+
+static struct update_info *updates;
+static unsigned int nr_updates;
+
+static void
+startupdate_help(void)
+{
+	printf(_(
+"\n"
+" Prepare for an atomic file update, if supported by the filesystem.\n"
+" A temporary file will be opened for writing and inserted into the file\n"
+" table.  The current file will be changed to this temporary file.  Neither\n"
+" file can be closed for the duration of the update.\n"
+"\n"
+" -e   -- Start with an empty file\n"
+"\n"));
+}
+
+static int
+startupdate_f(
+	int			argc,
+	char			*argv[])
+{
+	struct fsxattr		attr;
+	struct xfs_fsop_geom	fsgeom;
+	struct fs_path		fspath;
+	struct stat		stat;
+	struct update_info	*p;
+	char			*fname;
+	char			*path = NULL, *d;
+	size_t			fname_len;
+	int			flags = IO_TMPFILE | IO_ATOMICUPDATE;
+	int			temp_fd = -1;
+	bool			clone_file = true;
+	int			c;
+	int			ret;
+
+	while ((c = getopt(argc, argv, "e")) != -1) {
+		switch (c) {
+		case 'e':
+			clone_file = false;
+			break;
+		default:
+			startupdate_help();
+			return 0;
+		}
+	}
+	if (optind != argc) {
+		startupdate_help();
+		return 0;
+	}
+
+	/* Allocate a new slot. */
+	p = realloc(updates, (++nr_updates) * sizeof(*p));
+	if (!p) {
+		perror("startupdate realloc");
+		goto fail;
+	}
+	updates = p;
+
+	/* Fill out the update information so that we can commit later. */
+	p = &updates[nr_updates - 1];
+	memset(p, 0, sizeof(*p));
+	p->file_fd.fd = file->fd;
+	ret = xfd_prepare_geometry(&p->file_fd);
+	if (ret) {
+		xfrog_perror(ret, file->name);
+		goto fail;
+	}
+
+	ret = fstat(file->fd, &stat);
+	if (ret) {
+		perror(file->name);
+		goto fail;
+	}
+
+	/* Is the current file realtime?  If so, the temp file must match. */
+	ret = ioctl(file->fd, FS_IOC_FSGETXATTR, &attr);
+	if (ret == 0 && attr.fsx_xflags & FS_XFLAG_REALTIME)
+		flags |= IO_REALTIME;
+
+	/* Compute path to the directory that the current file is in. */
+	path = strdup(file->name);
+	d = strrchr(path, '/');
+	if (!d) {
+		fprintf(stderr, _("%s: cannot compute dirname?"), path);
+		goto fail;
+	}
+	*d = 0;
+
+	/* Open a temporary file to stage the extents. */
+	temp_fd = openfile(path, &fsgeom, flags, 0600, &fspath);
+	if (temp_fd < 0) {
+		perror(path);
+		goto fail;
+	}
+
+	/*
+	 * Snapshot the original file metadata in anticipation of the later
+	 * extent swap request.
+	 */
+	ret = xfrog_file_exchange_prep(&p->file_fd, XFS_EXCH_RANGE_COMMIT, 0,
+			temp_fd, 0, stat.st_size, &p->xchg_req);
+	if (ret) {
+		perror("update prep");
+		goto fail;
+	}
+
+	/* Clone all the data from the original file into the temporary file. */
+	if (clone_file) {
+		ret = ioctl(temp_fd, XFS_IOC_CLONE, p->file_fd.fd);
+		if (ret) {
+			perror(path);
+			goto fail;
+		}
+	}
+
+	/* Prepare a new path string for the duration of the update. */
+#define FILEUPDATE_STR	" (fileupdate)"
+	fname_len = strlen(file->name) + strlen(FILEUPDATE_STR);
+	fname = malloc(fname_len + 1);
+	if (!fname) {
+		perror("new path");
+		goto fail;
+	}
+	snprintf(fname, fname_len + 1, "%s%s", file->name, FILEUPDATE_STR);
+
+	/*
+	 * Install the temporary file into the same slot of the file table as
+	 * the original file.  Ensure that the original file cannot be closed.
+	 */
+	file->flags |= IO_ATOMICUPDATE;
+	p->old_fname = file->name;
+	file->name = fname;
+	p->temp_fd = file->fd = temp_fd;
+
+	free(path);
+	return 0;
+fail:
+	if (temp_fd >= 0)
+		close(temp_fd);
+	free(path);
+	nr_updates--;
+	exitcode = 1;
+	return 1;
+}
+
+static long long
+finish_update(
+	enum finish_how		how,
+	uint64_t		flags,
+	long long		*offset)
+{
+	struct update_info	*p;
+	long long		committed_bytes = 0;
+	size_t			length;
+	unsigned int		i;
+	unsigned int		upd_offset;
+	int			temp_fd;
+	int			ret;
+
+	/* Find our update descriptor. */
+	for (i = 0, p = updates; i < nr_updates; i++, p++) {
+		if (p->temp_fd == file->fd)
+			break;
+	}
+
+	if (i == nr_updates) {
+		fprintf(stderr,
+	_("Current file is not the staging file for an atomic update.\n"));
+		exitcode = 1;
+		return -1;
+	}
+
+	p->xchg_req.flags |= flags;
+
+	/*
+	 * Commit our changes, if desired.  If the extent swap fails, we stop
+	 * processing immediately so that we can run more xfs_io commands.
+	 */
+	switch (how) {
+	case FINISH_CHECK:
+		p->xchg_req.flags |= XFS_EXCH_RANGE_DRY_RUN;
+		fallthrough;
+	case FINISH_COMMIT:
+		ret = xfrog_file_exchange(&p->file_fd, &p->xchg_req);
+		if (ret) {
+			xfrog_perror(ret, _("committing update"));
+			exitcode = 1;
+			return -1;
+		}
+		printf(_("Committed updates to '%s'.\n"), p->old_fname);
+		*offset = p->xchg_req.file2_offset;
+		committed_bytes = p->xchg_req.length;
+		break;
+	case FINISH_ABORT:
+		printf(_("Cancelled updates to '%s'.\n"), p->old_fname);
+		break;
+	}
+
+	/*
+	 * Reset the filetable to point to the original file, and close the
+	 * temporary file.
+	 */
+	free(file->name);
+	file->name = p->old_fname;
+	file->flags &= ~IO_ATOMICUPDATE;
+	temp_fd = file->fd;
+	file->fd = p->file_fd.fd;
+	ret = close(temp_fd);
+	if (ret)
+		perror(_("closing temporary file"));
+
+	/* Remove the atomic update context, shifting things down. */
+	upd_offset = p - updates;
+	length = nr_updates * sizeof(struct update_info);
+	length -= (upd_offset + 1) * sizeof(struct update_info);
+	if (length)
+		memmove(p, p + 1, length);
+
+	nr_updates--;
+	return committed_bytes;
+}
+
+static void
+cancelupdate_help(void)
+{
+	printf(_(
+"\n"
+" Cancels an atomic file update.  The temporary file will be closed, and the\n"
+" current file set back to the original file.\n"
+"\n"));
+}
+
+static int
+cancelupdate_f(
+	int		argc,
+	char		*argv[])
+{
+	return finish_update(FINISH_ABORT, 0, NULL);
+}
+
+static void
+commitupdate_help(void)
+{
+	printf(_(
+"\n"
+" Commits an atomic file update.  File contents written to the temporary file\n"
+" will be swapped atomically with the corresponding range in the original\n"
+" file.  The temporary file will be closed, and the current file set back to\n"
+" the original file.\n"
+"\n"
+" -C   -- Print timing information in a condensed format.\n"
+" -h   -- Only swap written ranges in the temporary file.\n"
+" -k   -- Do not change file size.\n"
+" -n   -- Check parameters but do not change anything.\n"
+" -q   -- Do not print timing information at all.\n"));
+}
+
+static int
+commitupdate_f(
+	int		argc,
+	char		*argv[])
+{
+	struct timeval	t1, t2;
+	enum finish_how	how = FINISH_COMMIT;
+	uint64_t	flags = XFS_EXCH_RANGE_TO_EOF;
+	long long	offset, len;
+	int		condensed = 0, quiet_flag = 0;
+	int		c;
+
+	while ((c = getopt(argc, argv, "Chknq")) != -1) {
+		switch (c) {
+		case 'C':
+			condensed = 1;
+			break;
+		case 'h':
+			flags |= XFS_EXCH_RANGE_FILE1_WRITTEN;
+			break;
+		case 'k':
+			flags &= ~XFS_EXCH_RANGE_TO_EOF;
+			break;
+		case 'n':
+			how = FINISH_CHECK;
+			break;
+		case 'q':
+			quiet_flag = 1;
+			break;
+		default:
+			commitupdate_help();
+			return 0;
+		}
+	}
+	if (optind != argc) {
+		commitupdate_help();
+		return 0;
+	}
+
+	gettimeofday(&t1, NULL);
+	len = finish_update(how, flags, &offset);
+	if (len < 0)
+		return 1;
+	if (quiet_flag)
+		return 0;
+
+	gettimeofday(&t2, NULL);
+	t2 = tsub(t2, t1);
+	report_io_times("commitupdate", &t2, offset, len, len, 1, condensed);
+	return 0;
+}
+
+static struct cmdinfo startupdate_cmd = {
+	.name		= "startupdate",
+	.cfunc		= startupdate_f,
+	.argmin		= 0,
+	.argmax		= -1,
+	.flags		= CMD_FLAG_ONESHOT | CMD_NOMAP_OK,
+	.help		= startupdate_help,
+};
+
+static struct cmdinfo cancelupdate_cmd = {
+	.name		= "cancelupdate",
+	.cfunc		= cancelupdate_f,
+	.argmin		= 0,
+	.argmax		= 0,
+	.flags		= CMD_FLAG_ONESHOT | CMD_NOMAP_OK,
+	.help		= cancelupdate_help,
+};
+
+static struct cmdinfo commitupdate_cmd = {
+	.name		= "commitupdate",
+	.cfunc		= commitupdate_f,
+	.argmin		= 0,
+	.argmax		= -1,
+	.flags		= CMD_FLAG_ONESHOT | CMD_NOMAP_OK,
+	.help		= commitupdate_help,
+};
+
+void
+atomicupdate_init(void)
+{
+	startupdate_cmd.oneline = _("start an atomic update of a file");
+	startupdate_cmd.args = _("[-e]");
+
+	cancelupdate_cmd.oneline = _("cancel an atomic update");
+
+	commitupdate_cmd.oneline = _("commit a file update atomically");
+	commitupdate_cmd.args = _("[-C] [-h] [-n] [-q]");
+
+	add_command(&startupdate_cmd);
+	add_command(&cancelupdate_cmd);
+	add_command(&commitupdate_cmd);
+}
diff --git a/io/init.c b/io/init.c
index 104cd2c1215..a6c3d0cf147 100644
--- a/io/init.c
+++ b/io/init.c
@@ -44,6 +44,7 @@ init_cvtnum(
 static void
 init_commands(void)
 {
+	atomicupdate_init();
 	attr_init();
 	bmap_init();
 	bulkstat_init();
diff --git a/io/io.h b/io/io.h
index fe474faf4ad..a30b96401a7 100644
--- a/io/io.h
+++ b/io/io.h
@@ -31,6 +31,9 @@
 #define IO_PATH		(1<<10)
 #define IO_NOFOLLOW	(1<<11)
 
+/* undergoing atomic update, do not close */
+#define IO_ATOMICUPDATE	(1<<12)
+
 /*
  * Regular file I/O control
  */
@@ -74,6 +77,7 @@ extern int		openfile(char *, struct xfs_fsop_geom *, int, mode_t,
 				 struct fs_path *);
 extern int		addfile(char *, int , struct xfs_fsop_geom *, int,
 				struct fs_path *);
+extern int		closefile(void);
 extern void		printxattr(uint, int, int, const char *, int, int);
 
 extern unsigned int	recurse_all;
@@ -185,3 +189,4 @@ extern void		scrub_init(void);
 extern void		repair_init(void);
 extern void		crc32cselftest_init(void);
 extern void		bulkstat_init(void);
+extern void		atomicupdate_init(void);
diff --git a/io/open.c b/io/open.c
index 15850b5557b..a30dd89a1fd 100644
--- a/io/open.c
+++ b/io/open.c
@@ -338,14 +338,19 @@ open_f(
 	return 0;
 }
 
-static int
-close_f(
-	int		argc,
-	char		**argv)
+int
+closefile(void)
 {
 	size_t		length;
 	unsigned int	offset;
 
+	if (file->flags & IO_ATOMICUPDATE) {
+		fprintf(stderr,
+	_("%s: atomic update in progress, cannot close.\n"),
+			file->name);
+		exitcode = 1;
+		return 0;
+	}
 	if (close(file->fd) < 0) {
 		perror("close");
 		exitcode = 1;
@@ -371,7 +376,19 @@ close_f(
 		free(filetable);
 		file = filetable = NULL;
 	}
-	filelist_f();
+	return 0;
+}
+
+static int
+close_f(
+	int		argc,
+	char		**argv)
+{
+	int		ret;
+
+	ret = closefile();
+	if (!ret)
+		filelist_f();
 	return 0;
 }
 
diff --git a/man/man8/xfs_io.8 b/man/man8/xfs_io.8
index 34f9ffe9433..6ebb479a344 100644
--- a/man/man8/xfs_io.8
+++ b/man/man8/xfs_io.8
@@ -1045,7 +1045,37 @@ sec uses UNIX timestamp notation and is the seconds elapsed since
 nsec is the nanoseconds since the sec. This value needs to be in
 the range 0-999999999 with UTIME_NOW and UTIME_OMIT being exceptions.
 Each (sec, nsec) pair constitutes a single timestamp value.
-
+.TP
+.BI "startupdate [ " -e ]
+Create a temporary clone of a file in which to stage file updates.
+The
+.B \-e
+option creates an empty staging file.
+.TP
+.B cancelupdate
+Abandon changes from a update staging file.
+.TP
+.BI "commitupdate [" OPTIONS ]
+Commit changes from a update staging file to the real file.
+.RS 1.0i
+.PD 0
+.TP 0.4i
+.B \-C
+Print timing information in a condensed format.
+.TP 0.4i
+.B \-h
+Only swap ranges in the update staging file that were actually written.
+.TP 0.4i
+.B \-k
+Do not change file size.
+.TP 0.4i
+.B \-n
+Check parameters without changing anything.
+.TP 0.4i
+.B \-q
+Do not print timing information at all.
+.PD
+.RE
 
 .SH MEMORY MAPPED I/O COMMANDS
 .TP

[PATCH 1/9] xfs: add an explicit owner field to xfs_da_args

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add an explicit owner field to xfs_da_args, which will make it easier
for online fsck to set the owner field of the temporary directory and
xattr structures that it builds to repair damaged metadata.

Note: I hopefully found all the xfs_da_args definitions by looking for
automatic stack variable declarations and xfs_da_args.dp assignments:

git grep -E '(args.*dp =|struct xfs_da_args[[:space:]]*[a-z0-9][a-z0-9]*)'

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 db/attrset.c           |    2 ++
 db/namei.c             |    1 +
 libxfs/xfs_attr_leaf.c |    2 ++
 libxfs/xfs_bmap.c      |    1 +
 libxfs/xfs_da_btree.h  |    1 +
 libxfs/xfs_dir2.c      |    5 +++++
 libxfs/xfs_swapext.c   |    2 ++
 repair/phase6.c        |    3 +++
 8 files changed, 17 insertions(+)


diff --git a/db/attrset.c b/db/attrset.c
index 0d8d70a8429..2b6cdb5f5c3 100644
--- a/db/attrset.c
+++ b/db/attrset.c
@@ -161,6 +161,7 @@ attr_set_f(
 			(unsigned long long)iocur_top->ino);
 		goto out;
 	}
+	args.owner = iocur_top->ino;
 
 	if (libxfs_attr_set(&args)) {
 		dbprintf(_("failed to set attr %s on inode %llu\n"),
@@ -247,6 +248,7 @@ attr_remove_f(
 			(unsigned long long)iocur_top->ino);
 		goto out;
 	}
+	args.owner = iocur_top->ino;
 
 	if (libxfs_attr_set(&args)) {
 		dbprintf(_("failed to remove attr %s from inode %llu\n"),
diff --git a/db/namei.c b/db/namei.c
index 063721ca98f..eb09288b490 100644
--- a/db/namei.c
+++ b/db/namei.c
@@ -448,6 +448,7 @@ listdir(
 	struct xfs_da_args	args = {
 		.dp		= dp,
 		.geo		= dp->i_mount->m_dir_geo,
+		.owner		= dp->i_ino,
 	};
 	int			error;
 	bool			isblock;
diff --git a/libxfs/xfs_attr_leaf.c b/libxfs/xfs_attr_leaf.c
index aa7aad36864..e3e9c265fab 100644
--- a/libxfs/xfs_attr_leaf.c
+++ b/libxfs/xfs_attr_leaf.c
@@ -972,6 +972,7 @@ xfs_attr_shortform_to_leaf(
 	nargs.whichfork = XFS_ATTR_FORK;
 	nargs.trans = args->trans;
 	nargs.op_flags = XFS_DA_OP_OKNOENT;
+	nargs.owner = args->owner;
 
 	sfe = &sf->list[0];
 	for (i = 0; i < sf->hdr.count; i++) {
@@ -1175,6 +1176,7 @@ xfs_attr3_leaf_to_shortform(
 	nargs.whichfork = XFS_ATTR_FORK;
 	nargs.trans = args->trans;
 	nargs.op_flags = XFS_DA_OP_OKNOENT;
+	nargs.owner = args->owner;
 
 	for (i = 0; i < ichdr.count; entry++, i++) {
 		if (entry->flags & XFS_ATTR_INCOMPLETE)
diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index 54db35bc398..296e7d85f63 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -952,6 +952,7 @@ xfs_bmap_add_attrfork_local(
 		dargs.total = dargs.geo->fsbcount;
 		dargs.whichfork = XFS_DATA_FORK;
 		dargs.trans = tp;
+		dargs.owner = ip->i_ino;
 		return xfs_dir2_sf_to_block(&dargs);
 	}
 
diff --git a/libxfs/xfs_da_btree.h b/libxfs/xfs_da_btree.h
index 706baf36e17..7fb13f26eda 100644
--- a/libxfs/xfs_da_btree.h
+++ b/libxfs/xfs_da_btree.h
@@ -79,6 +79,7 @@ typedef struct xfs_da_args {
 	int		rmtvaluelen2;	/* remote attr value length in bytes */
 	uint32_t	op_flags;	/* operation flags */
 	enum xfs_dacmp	cmpresult;	/* name compare result for lookups */
+	xfs_ino_t	owner;		/* inode that owns the dir/attr data */
 } xfs_da_args_t;
 
 /*
diff --git a/libxfs/xfs_dir2.c b/libxfs/xfs_dir2.c
index e503bf8f92f..79b6ec893fd 100644
--- a/libxfs/xfs_dir2.c
+++ b/libxfs/xfs_dir2.c
@@ -249,6 +249,7 @@ xfs_dir_init(
 	args->geo = dp->i_mount->m_dir_geo;
 	args->dp = dp;
 	args->trans = tp;
+	args->owner = dp->i_ino;
 	error = xfs_dir2_sf_create(args, pdp->i_ino);
 	kmem_free(args);
 	return error;
@@ -294,6 +295,7 @@ xfs_dir_createname(
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
 	args->op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
+	args->owner = dp->i_ino;
 	if (!inum)
 		args->op_flags |= XFS_DA_OP_JUSTCHECK;
 
@@ -388,6 +390,7 @@ xfs_dir_lookup(
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
 	args->op_flags = XFS_DA_OP_OKNOENT;
+	args->owner = dp->i_ino;
 	if (ci_name)
 		args->op_flags |= XFS_DA_OP_CILOOKUP;
 
@@ -461,6 +464,7 @@ xfs_dir_removename(
 	args->total = total;
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
+	args->owner = dp->i_ino;
 
 	if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL) {
 		rval = xfs_dir2_sf_removename(args);
@@ -522,6 +526,7 @@ xfs_dir_replace(
 	args->total = total;
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
+	args->owner = dp->i_ino;
 
 	if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL) {
 		rval = xfs_dir2_sf_replace(args);
diff --git a/libxfs/xfs_swapext.c b/libxfs/xfs_swapext.c
index 92d2f8fa133..5c96ad8a203 100644
--- a/libxfs/xfs_swapext.c
+++ b/libxfs/xfs_swapext.c
@@ -524,6 +524,7 @@ xfs_swapext_attr_to_sf(
 		.geo		= tp->t_mountp->m_attr_geo,
 		.whichfork	= XFS_ATTR_FORK,
 		.trans		= tp,
+		.owner		= sxi->sxi_ip2->i_ino,
 	};
 	struct xfs_buf		*bp;
 	int			forkoff;
@@ -554,6 +555,7 @@ xfs_swapext_dir_to_sf(
 		.geo		= tp->t_mountp->m_dir_geo,
 		.whichfork	= XFS_DATA_FORK,
 		.trans		= tp,
+		.owner		= sxi->sxi_ip2->i_ino,
 	};
 	struct xfs_dir2_sf_hdr	sfh;
 	struct xfs_buf		*bp;
diff --git a/repair/phase6.c b/repair/phase6.c
index c681a69017d..ac037cf80ad 100644
--- a/repair/phase6.c
+++ b/repair/phase6.c
@@ -1393,6 +1393,7 @@ dir2_kill_block(
 	args.trans = tp;
 	args.whichfork = XFS_DATA_FORK;
 	args.geo = mp->m_dir_geo;
+	args.owner = ip->i_ino;
 	if (da_bno >= mp->m_dir_geo->leafblk && da_bno < mp->m_dir_geo->freeblk)
 		error = -libxfs_da_shrink_inode(&args, da_bno, bp);
 	else
@@ -1496,6 +1497,7 @@ longform_dir2_entry_check_data(
 	struct xfs_da_args	da = {
 		.dp = ip,
 		.geo = mp->m_dir_geo,
+		.owner = ip->i_ino,
 	};
 
 
@@ -2284,6 +2286,7 @@ longform_dir2_entry_check(
 	/* is this a block, leaf, or node directory? */
 	args.dp = ip;
 	args.geo = mp->m_dir_geo;
+	args.owner = ip->i_ino;
 	libxfs_dir2_isblock(&args, &isblock);
 	libxfs_dir2_isleaf(&args, &isleaf);
 

[PATCH 2/9] xfs: use the xfs_da_args owner field to set new dir/attr block owner

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

When we're creating leaf, data, freespace, or dabtree blocks for
directories and xattrs, use the explicit owner field (instead of the
xfs_inode) to set the owner field.  This will enable online repair to
construct replacement data structures in a temporary file without having
to change the owner fields prior to swapping the new and old structures.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_attr_leaf.c   |    2 +-
 libxfs/xfs_attr_remote.c |    4 ++--
 libxfs/xfs_da_btree.c    |    2 +-
 libxfs/xfs_dir2_block.c  |   19 ++++++++++---------
 libxfs/xfs_dir2_data.c   |    2 +-
 libxfs/xfs_dir2_leaf.c   |   11 +++++------
 libxfs/xfs_dir2_node.c   |    2 +-
 7 files changed, 21 insertions(+), 21 deletions(-)


diff --git a/libxfs/xfs_attr_leaf.c b/libxfs/xfs_attr_leaf.c
index e3e9c265fab..1e87c8243f7 100644
--- a/libxfs/xfs_attr_leaf.c
+++ b/libxfs/xfs_attr_leaf.c
@@ -1308,7 +1308,7 @@ xfs_attr3_leaf_create(
 		ichdr.magic = XFS_ATTR3_LEAF_MAGIC;
 
 		hdr3->blkno = cpu_to_be64(xfs_buf_daddr(bp));
-		hdr3->owner = cpu_to_be64(dp->i_ino);
+		hdr3->owner = cpu_to_be64(args->owner);
 		uuid_copy(&hdr3->uuid, &mp->m_sb.sb_meta_uuid);
 
 		ichdr.freemap[0].base = sizeof(struct xfs_attr3_leaf_hdr);
diff --git a/libxfs/xfs_attr_remote.c b/libxfs/xfs_attr_remote.c
index f1c7cd31459..bc58dc6fa34 100644
--- a/libxfs/xfs_attr_remote.c
+++ b/libxfs/xfs_attr_remote.c
@@ -521,8 +521,8 @@ xfs_attr_rmtval_set_value(
 			return error;
 		bp->b_ops = &xfs_attr3_rmt_buf_ops;
 
-		xfs_attr_rmtval_copyin(mp, bp, args->dp->i_ino, &offset,
-				       &valuelen, &src);
+		xfs_attr_rmtval_copyin(mp, bp, args->owner, &offset, &valuelen,
+				&src);
 
 		error = xfs_bwrite(bp);	/* GROT: NOTE: synchronous write */
 		xfs_buf_relse(bp);
diff --git a/libxfs/xfs_da_btree.c b/libxfs/xfs_da_btree.c
index 87996c5da4f..672dc8aa433 100644
--- a/libxfs/xfs_da_btree.c
+++ b/libxfs/xfs_da_btree.c
@@ -481,7 +481,7 @@ xfs_da3_node_create(
 		memset(hdr3, 0, sizeof(struct xfs_da3_node_hdr));
 		ichdr.magic = XFS_DA3_NODE_MAGIC;
 		hdr3->info.blkno = cpu_to_be64(xfs_buf_daddr(bp));
-		hdr3->info.owner = cpu_to_be64(args->dp->i_ino);
+		hdr3->info.owner = cpu_to_be64(args->owner);
 		uuid_copy(&hdr3->info.uuid, &mp->m_sb.sb_meta_uuid);
 	} else {
 		ichdr.magic = XFS_DA_NODE_MAGIC;
diff --git a/libxfs/xfs_dir2_block.c b/libxfs/xfs_dir2_block.c
index 19fededab5d..1f6a88091e7 100644
--- a/libxfs/xfs_dir2_block.c
+++ b/libxfs/xfs_dir2_block.c
@@ -160,12 +160,13 @@ xfs_dir3_block_read(
 
 static void
 xfs_dir3_block_init(
-	struct xfs_mount	*mp,
-	struct xfs_trans	*tp,
-	struct xfs_buf		*bp,
-	struct xfs_inode	*dp)
+	struct xfs_da_args	*args,
+	struct xfs_buf		*bp)
 {
-	struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;
+	struct xfs_trans	*tp = args->trans;
+	struct xfs_inode	*dp = args->dp;
+	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_dir3_blk_hdr	*hdr3 = bp->b_addr;
 
 	bp->b_ops = &xfs_dir3_block_buf_ops;
 	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DIR_BLOCK_BUF);
@@ -174,7 +175,7 @@ xfs_dir3_block_init(
 		memset(hdr3, 0, sizeof(*hdr3));
 		hdr3->magic = cpu_to_be32(XFS_DIR3_BLOCK_MAGIC);
 		hdr3->blkno = cpu_to_be64(xfs_buf_daddr(bp));
-		hdr3->owner = cpu_to_be64(dp->i_ino);
+		hdr3->owner = cpu_to_be64(args->owner);
 		uuid_copy(&hdr3->uuid, &mp->m_sb.sb_meta_uuid);
 		return;
 
@@ -1006,7 +1007,7 @@ xfs_dir2_leaf_to_block(
 	/*
 	 * Start converting it to block form.
 	 */
-	xfs_dir3_block_init(mp, tp, dbp, dp);
+	xfs_dir3_block_init(args, dbp);
 
 	needlog = 1;
 	needscan = 0;
@@ -1128,7 +1129,7 @@ xfs_dir2_sf_to_block(
 	error = xfs_dir3_data_init(args, blkno, &bp);
 	if (error)
 		goto out_free;
-	xfs_dir3_block_init(mp, tp, bp, dp);
+	xfs_dir3_block_init(args, bp);
 	hdr = bp->b_addr;
 
 	/*
@@ -1168,7 +1169,7 @@ xfs_dir2_sf_to_block(
 	 * Create entry for .
 	 */
 	dep = bp->b_addr + offset;
-	dep->inumber = cpu_to_be64(dp->i_ino);
+	dep->inumber = cpu_to_be64(args->owner);
 	dep->namelen = 1;
 	dep->name[0] = '.';
 	xfs_dir2_data_put_ftype(mp, dep, XFS_DIR3_FT_DIR);
diff --git a/libxfs/xfs_dir2_data.c b/libxfs/xfs_dir2_data.c
index aaf3f62af91..6f3ccfeb69f 100644
--- a/libxfs/xfs_dir2_data.c
+++ b/libxfs/xfs_dir2_data.c
@@ -722,7 +722,7 @@ xfs_dir3_data_init(
 		memset(hdr3, 0, sizeof(*hdr3));
 		hdr3->magic = cpu_to_be32(XFS_DIR3_DATA_MAGIC);
 		hdr3->blkno = cpu_to_be64(xfs_buf_daddr(bp));
-		hdr3->owner = cpu_to_be64(dp->i_ino);
+		hdr3->owner = cpu_to_be64(args->owner);
 		uuid_copy(&hdr3->uuid, &mp->m_sb.sb_meta_uuid);
 
 	} else
diff --git a/libxfs/xfs_dir2_leaf.c b/libxfs/xfs_dir2_leaf.c
index 80cea8a275d..8fbda22508d 100644
--- a/libxfs/xfs_dir2_leaf.c
+++ b/libxfs/xfs_dir2_leaf.c
@@ -302,12 +302,12 @@ xfs_dir3_leafn_read(
  */
 static void
 xfs_dir3_leaf_init(
-	struct xfs_mount	*mp,
-	struct xfs_trans	*tp,
+	struct xfs_da_args	*args,
 	struct xfs_buf		*bp,
-	xfs_ino_t		owner,
 	uint16_t		type)
 {
+	struct xfs_mount	*mp = args->dp->i_mount;
+	struct xfs_trans	*tp = args->trans;
 	struct xfs_dir2_leaf	*leaf = bp->b_addr;
 
 	ASSERT(type == XFS_DIR2_LEAF1_MAGIC || type == XFS_DIR2_LEAFN_MAGIC);
@@ -321,7 +321,7 @@ xfs_dir3_leaf_init(
 					 ? cpu_to_be16(XFS_DIR3_LEAF1_MAGIC)
 					 : cpu_to_be16(XFS_DIR3_LEAFN_MAGIC);
 		leaf3->info.blkno = cpu_to_be64(xfs_buf_daddr(bp));
-		leaf3->info.owner = cpu_to_be64(owner);
+		leaf3->info.owner = cpu_to_be64(args->owner);
 		uuid_copy(&leaf3->info.uuid, &mp->m_sb.sb_meta_uuid);
 	} else {
 		memset(leaf, 0, sizeof(*leaf));
@@ -354,7 +354,6 @@ xfs_dir3_leaf_get_buf(
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_trans	*tp = args->trans;
-	struct xfs_mount	*mp = dp->i_mount;
 	struct xfs_buf		*bp;
 	int			error;
 
@@ -367,7 +366,7 @@ xfs_dir3_leaf_get_buf(
 	if (error)
 		return error;
 
-	xfs_dir3_leaf_init(mp, tp, bp, dp->i_ino, magic);
+	xfs_dir3_leaf_init(args, bp, magic);
 	xfs_dir3_leaf_log_header(args, bp);
 	if (magic == XFS_DIR2_LEAF1_MAGIC)
 		xfs_dir3_leaf_log_tail(args, bp);
diff --git a/libxfs/xfs_dir2_node.c b/libxfs/xfs_dir2_node.c
index 44c8f3f2b07..b00f783877e 100644
--- a/libxfs/xfs_dir2_node.c
+++ b/libxfs/xfs_dir2_node.c
@@ -346,7 +346,7 @@ xfs_dir3_free_get_buf(
 		hdr.magic = XFS_DIR3_FREE_MAGIC;
 
 		hdr3->hdr.blkno = cpu_to_be64(xfs_buf_daddr(bp));
-		hdr3->hdr.owner = cpu_to_be64(dp->i_ino);
+		hdr3->hdr.owner = cpu_to_be64(args->owner);
 		uuid_copy(&hdr3->hdr.uuid, &mp->m_sb.sb_meta_uuid);
 	} else
 		hdr.magic = XFS_DIR2_FREE_MAGIC;

[PATCH 3/9] xfs: validate attr leaf buffer owners

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a leaf block header checking function to validate the owner field
of xattr leaf blocks.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/libxfs_api_defs.h |    3 +++
 libxfs/xfs_attr.c        |   10 ++++----
 libxfs/xfs_attr_leaf.c   |   55 ++++++++++++++++++++++++++++++++++++++--------
 libxfs/xfs_attr_leaf.h   |    4 +++
 libxfs/xfs_da_btree.c    |   42 +++++++++++++++++++++++++++++++++++
 libxfs/xfs_da_btree.h    |    1 +
 libxfs/xfs_swapext.c     |    3 ++-
 7 files changed, 102 insertions(+), 16 deletions(-)


diff --git a/libxfs/libxfs_api_defs.h b/libxfs/libxfs_api_defs.h
index a5b3baaa476..eba9a8386d2 100644
--- a/libxfs/libxfs_api_defs.h
+++ b/libxfs/libxfs_api_defs.h
@@ -277,4 +277,7 @@
 
 /* Please keep this list alphabetized. */
 
+/* XXX remove this */
+#define dump_stack() do { } while(0)
+
 #endif /* __LIBXFS_API_DEFS_H__ */
diff --git a/libxfs/xfs_attr.c b/libxfs/xfs_attr.c
index cb6c8d081fd..985989b5ade 100644
--- a/libxfs/xfs_attr.c
+++ b/libxfs/xfs_attr.c
@@ -645,8 +645,8 @@ xfs_attr_leaf_remove_attr(
 	int				forkoff;
 	int				error;
 
-	error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno,
-				   &bp);
+	error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner,
+			args->blkno, &bp);
 	if (error)
 		return error;
 
@@ -677,7 +677,7 @@ xfs_attr_leaf_shrink(
 	if (!xfs_attr_is_leaf(dp))
 		return 0;
 
-	error = xfs_attr3_leaf_read(args->trans, args->dp, 0, &bp);
+	error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, 0, &bp);
 	if (error)
 		return error;
 
@@ -1158,7 +1158,7 @@ xfs_attr_leaf_try_add(
 	struct xfs_buf		*bp;
 	int			error;
 
-	error = xfs_attr3_leaf_read(args->trans, args->dp, 0, &bp);
+	error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, 0, &bp);
 	if (error)
 		return error;
 
@@ -1206,7 +1206,7 @@ xfs_attr_leaf_hasname(
 {
 	int                     error = 0;
 
-	error = xfs_attr3_leaf_read(args->trans, args->dp, 0, bp);
+	error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, 0, bp);
 	if (error)
 		return error;
 
diff --git a/libxfs/xfs_attr_leaf.c b/libxfs/xfs_attr_leaf.c
index 1e87c8243f7..3d798828833 100644
--- a/libxfs/xfs_attr_leaf.c
+++ b/libxfs/xfs_attr_leaf.c
@@ -385,6 +385,26 @@ xfs_attr3_leaf_verify(
 	return NULL;
 }
 
+xfs_failaddr_t
+xfs_attr3_leaf_header_check(
+	struct xfs_buf		*bp,
+	xfs_ino_t		owner)
+{
+	struct xfs_mount	*mp = bp->b_mount;
+
+	if (xfs_has_crc(mp)) {
+		struct xfs_attr3_leafblock *hdr3 = bp->b_addr;
+
+		ASSERT(hdr3->hdr.info.hdr.magic ==
+				cpu_to_be16(XFS_ATTR3_LEAF_MAGIC));
+
+		if (be64_to_cpu(hdr3->hdr.info.owner) != owner)
+			return __this_address;
+	}
+
+	return NULL;
+}
+
 static void
 xfs_attr3_leaf_write_verify(
 	struct xfs_buf	*bp)
@@ -445,16 +465,30 @@ int
 xfs_attr3_leaf_read(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*dp,
+	xfs_ino_t		owner,
 	xfs_dablk_t		bno,
 	struct xfs_buf		**bpp)
 {
+	xfs_failaddr_t		fa;
 	int			err;
 
 	err = xfs_da_read_buf(tp, dp, bno, 0, bpp, XFS_ATTR_FORK,
 			&xfs_attr3_leaf_buf_ops);
-	if (!err && tp && *bpp)
+	if (err || !(*bpp))
+		return err;
+
+	fa = xfs_attr3_leaf_header_check(*bpp, owner);
+	if (fa) {
+		__xfs_buf_mark_corrupt(*bpp, fa);
+		xfs_trans_brelse(tp, *bpp);
+		*bpp = NULL;
+		xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
+		return -EFSCORRUPTED;
+	}
+
+	if (tp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_ATTR_LEAF_BUF);
-	return err;
+	return 0;
 }
 
 /*========================================================================
@@ -1229,7 +1263,7 @@ xfs_attr3_leaf_to_node(
 	error = xfs_da_grow_inode(args, &blkno);
 	if (error)
 		goto out;
-	error = xfs_attr3_leaf_read(args->trans, dp, 0, &bp1);
+	error = xfs_attr3_leaf_read(args->trans, dp, args->owner, 0, &bp1);
 	if (error)
 		goto out;
 
@@ -2064,7 +2098,7 @@ xfs_attr3_leaf_toosmall(
 		if (blkno == 0)
 			continue;
 		error = xfs_attr3_leaf_read(state->args->trans, state->args->dp,
-					blkno, &bp);
+					state->args->owner, blkno, &bp);
 		if (error)
 			return error;
 
@@ -2785,7 +2819,8 @@ xfs_attr3_leaf_clearflag(
 	/*
 	 * Set up the operation.
 	 */
-	error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, &bp);
+	error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner,
+			args->blkno, &bp);
 	if (error)
 		return error;
 
@@ -2849,7 +2884,8 @@ xfs_attr3_leaf_setflag(
 	/*
 	 * Set up the operation.
 	 */
-	error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, &bp);
+	error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner,
+			args->blkno, &bp);
 	if (error)
 		return error;
 
@@ -2908,7 +2944,8 @@ xfs_attr3_leaf_flipflags(
 	/*
 	 * Read the block containing the "old" attr
 	 */
-	error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno, &bp1);
+	error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner,
+			args->blkno, &bp1);
 	if (error)
 		return error;
 
@@ -2916,8 +2953,8 @@ xfs_attr3_leaf_flipflags(
 	 * Read the block containing the "new" attr, if it is different
 	 */
 	if (args->blkno2 != args->blkno) {
-		error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno2,
-					   &bp2);
+		error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner,
+				args->blkno2, &bp2);
 		if (error)
 			return error;
 	} else {
diff --git a/libxfs/xfs_attr_leaf.h b/libxfs/xfs_attr_leaf.h
index ce6743463c8..70edddedd1a 100644
--- a/libxfs/xfs_attr_leaf.h
+++ b/libxfs/xfs_attr_leaf.h
@@ -101,12 +101,14 @@ int	xfs_attr_leaf_order(struct xfs_buf *leaf1_bp,
 				   struct xfs_buf *leaf2_bp);
 int	xfs_attr_leaf_newentsize(struct xfs_da_args *args, int *local);
 int	xfs_attr3_leaf_read(struct xfs_trans *tp, struct xfs_inode *dp,
-			xfs_dablk_t bno, struct xfs_buf **bpp);
+			xfs_ino_t owner, xfs_dablk_t bno, struct xfs_buf **bpp);
 void	xfs_attr3_leaf_hdr_from_disk(struct xfs_da_geometry *geo,
 				     struct xfs_attr3_icleaf_hdr *to,
 				     struct xfs_attr_leafblock *from);
 void	xfs_attr3_leaf_hdr_to_disk(struct xfs_da_geometry *geo,
 				   struct xfs_attr_leafblock *to,
 				   struct xfs_attr3_icleaf_hdr *from);
+xfs_failaddr_t xfs_attr3_leaf_header_check(struct xfs_buf *bp,
+		xfs_ino_t owner);
 
 #endif	/* __XFS_ATTR_LEAF_H__ */
diff --git a/libxfs/xfs_da_btree.c b/libxfs/xfs_da_btree.c
index 672dc8aa433..a33c4acbd1d 100644
--- a/libxfs/xfs_da_btree.c
+++ b/libxfs/xfs_da_btree.c
@@ -247,6 +247,25 @@ xfs_da3_node_verify(
 	return NULL;
 }
 
+xfs_failaddr_t
+xfs_da3_header_check(
+	struct xfs_buf		*bp,
+	xfs_ino_t		owner)
+{
+	struct xfs_mount	*mp = bp->b_mount;
+	struct xfs_da_blkinfo	*hdr = bp->b_addr;
+
+	if (!xfs_has_crc(mp))
+		return NULL;
+
+	switch (hdr->magic) {
+	case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC):
+		return xfs_attr3_leaf_header_check(bp, owner);
+	}
+
+	return NULL;
+}
+
 static void
 xfs_da3_node_write_verify(
 	struct xfs_buf	*bp)
@@ -1586,6 +1605,7 @@ xfs_da3_node_lookup_int(
 	struct xfs_da_node_entry *btree;
 	struct xfs_da3_icnode_hdr nodehdr;
 	struct xfs_da_args	*args;
+	xfs_failaddr_t		fa;
 	xfs_dablk_t		blkno;
 	xfs_dahash_t		hashval;
 	xfs_dahash_t		btreehashval;
@@ -1624,6 +1644,12 @@ xfs_da3_node_lookup_int(
 
 		if (magic == XFS_ATTR_LEAF_MAGIC ||
 		    magic == XFS_ATTR3_LEAF_MAGIC) {
+			fa = xfs_attr3_leaf_header_check(blk->bp, args->owner);
+			if (fa) {
+				__xfs_buf_mark_corrupt(blk->bp, fa);
+				xfs_da_mark_sick(args);
+				return -EFSCORRUPTED;
+			}
 			blk->magic = XFS_ATTR_LEAF_MAGIC;
 			blk->hashval = xfs_attr_leaf_lasthash(blk->bp, NULL);
 			break;
@@ -1991,6 +2017,7 @@ xfs_da3_path_shift(
 	struct xfs_da_node_entry *btree;
 	struct xfs_da3_icnode_hdr nodehdr;
 	struct xfs_buf		*bp;
+	xfs_failaddr_t		fa;
 	xfs_dablk_t		blkno = 0;
 	int			level;
 	int			error;
@@ -2082,6 +2109,12 @@ xfs_da3_path_shift(
 			break;
 		case XFS_ATTR_LEAF_MAGIC:
 		case XFS_ATTR3_LEAF_MAGIC:
+			fa = xfs_attr3_leaf_header_check(blk->bp, args->owner);
+			if (fa) {
+				__xfs_buf_mark_corrupt(blk->bp, fa);
+				xfs_da_mark_sick(args);
+				return -EFSCORRUPTED;
+			}
 			blk->magic = XFS_ATTR_LEAF_MAGIC;
 			ASSERT(level == path->active-1);
 			blk->index = 0;
@@ -2284,6 +2317,7 @@ xfs_da3_swap_lastblock(
 	struct xfs_buf		*last_buf;
 	struct xfs_buf		*sib_buf;
 	struct xfs_buf		*par_buf;
+	xfs_failaddr_t		fa;
 	xfs_dahash_t		dead_hash;
 	xfs_fileoff_t		lastoff;
 	xfs_dablk_t		dead_blkno;
@@ -2320,6 +2354,14 @@ xfs_da3_swap_lastblock(
 	error = xfs_da3_node_read(tp, dp, last_blkno, &last_buf, w);
 	if (error)
 		return error;
+	fa = xfs_da3_header_check(last_buf, args->owner);
+	if (fa) {
+		__xfs_buf_mark_corrupt(last_buf, fa);
+		xfs_trans_brelse(tp, last_buf);
+		xfs_da_mark_sick(args);
+		return -EFSCORRUPTED;
+	}
+
 	/*
 	 * Copy the last block into the dead buffer and log it.
 	 */
diff --git a/libxfs/xfs_da_btree.h b/libxfs/xfs_da_btree.h
index 7fb13f26eda..99618e0c8a7 100644
--- a/libxfs/xfs_da_btree.h
+++ b/libxfs/xfs_da_btree.h
@@ -236,6 +236,7 @@ void	xfs_da3_node_hdr_from_disk(struct xfs_mount *mp,
 		struct xfs_da3_icnode_hdr *to, struct xfs_da_intnode *from);
 void	xfs_da3_node_hdr_to_disk(struct xfs_mount *mp,
 		struct xfs_da_intnode *to, struct xfs_da3_icnode_hdr *from);
+xfs_failaddr_t xfs_da3_header_check(struct xfs_buf *bp, xfs_ino_t owner);
 
 extern struct kmem_cache	*xfs_da_state_cache;
 
diff --git a/libxfs/xfs_swapext.c b/libxfs/xfs_swapext.c
index 5c96ad8a203..eae4f6b7310 100644
--- a/libxfs/xfs_swapext.c
+++ b/libxfs/xfs_swapext.c
@@ -533,7 +533,8 @@ xfs_swapext_attr_to_sf(
 	if (!xfs_attr_is_leaf(sxi->sxi_ip2))
 		return 0;
 
-	error = xfs_attr3_leaf_read(tp, sxi->sxi_ip2, 0, &bp);
+	error = xfs_attr3_leaf_read(tp, sxi->sxi_ip2, sxi->sxi_ip2->i_ino, 0,
+			&bp);
 	if (error)
 		return error;
 

[PATCH 4/9] xfs: validate attr remote value buffer owners

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Check the owner field of xattr remote value blocks.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_attr_remote.c |    9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)


diff --git a/libxfs/xfs_attr_remote.c b/libxfs/xfs_attr_remote.c
index bc58dc6fa34..f4d71430df4 100644
--- a/libxfs/xfs_attr_remote.c
+++ b/libxfs/xfs_attr_remote.c
@@ -279,12 +279,12 @@ xfs_attr_rmtval_copyout(
 	struct xfs_mount	*mp,
 	struct xfs_buf		*bp,
 	struct xfs_inode	*dp,
+	xfs_ino_t		owner,
 	int			*offset,
 	int			*valuelen,
 	uint8_t			**dst)
 {
 	char			*src = bp->b_addr;
-	xfs_ino_t		ino = dp->i_ino;
 	xfs_daddr_t		bno = xfs_buf_daddr(bp);
 	int			len = BBTOB(bp->b_length);
 	int			blksize = mp->m_attr_geo->blksize;
@@ -298,11 +298,11 @@ xfs_attr_rmtval_copyout(
 		byte_cnt = min(*valuelen, byte_cnt);
 
 		if (xfs_has_crc(mp)) {
-			if (xfs_attr3_rmt_hdr_ok(src, ino, *offset,
+			if (xfs_attr3_rmt_hdr_ok(src, owner, *offset,
 						  byte_cnt, bno)) {
 				xfs_alert(mp,
 "remote attribute header mismatch bno/off/len/owner (0x%llx/0x%x/Ox%x/0x%llx)",
-					bno, *offset, byte_cnt, ino);
+					bno, *offset, byte_cnt, owner);
 				xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
 				return -EFSCORRUPTED;
 			}
@@ -426,8 +426,7 @@ xfs_attr_rmtval_get(
 				return error;
 
 			error = xfs_attr_rmtval_copyout(mp, bp, args->dp,
-							&offset, &valuelen,
-							&dst);
+					args->owner, &offset, &valuelen, &dst);
 			xfs_buf_relse(bp);
 			if (error)
 				return error;

[PATCH 5/9] xfs: validate dabtree node buffer owners

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Check the owner field of dabtree node blocks.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_da_btree.c |  108 +++++++++++++++++++++++++++++++++++++++++++++++++
 libxfs/xfs_da_btree.h |    1 
 2 files changed, 109 insertions(+)


diff --git a/libxfs/xfs_da_btree.c b/libxfs/xfs_da_btree.c
index a33c4acbd1d..92eae433a5a 100644
--- a/libxfs/xfs_da_btree.c
+++ b/libxfs/xfs_da_btree.c
@@ -247,6 +247,25 @@ xfs_da3_node_verify(
 	return NULL;
 }
 
+xfs_failaddr_t
+xfs_da3_node_header_check(
+	struct xfs_buf		*bp,
+	xfs_ino_t		owner)
+{
+	struct xfs_mount	*mp = bp->b_mount;
+
+	if (xfs_has_crc(mp)) {
+		struct xfs_da3_blkinfo *hdr3 = bp->b_addr;
+
+		ASSERT(hdr3->hdr.magic == cpu_to_be16(XFS_DA3_NODE_MAGIC));
+
+		if (be64_to_cpu(hdr3->owner) != owner)
+			return __this_address;
+	}
+
+	return NULL;
+}
+
 xfs_failaddr_t
 xfs_da3_header_check(
 	struct xfs_buf		*bp,
@@ -261,6 +280,8 @@ xfs_da3_header_check(
 	switch (hdr->magic) {
 	case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC):
 		return xfs_attr3_leaf_header_check(bp, owner);
+	case cpu_to_be16(XFS_DA3_NODE_MAGIC):
+		return xfs_da3_node_header_check(bp, owner);
 	}
 
 	return NULL;
@@ -1213,6 +1234,7 @@ xfs_da3_root_join(
 	struct xfs_da3_icnode_hdr oldroothdr;
 	int			error;
 	struct xfs_inode	*dp = state->args->dp;
+	xfs_failaddr_t		fa;
 
 	trace_xfs_da_root_join(state->args);
 
@@ -1239,6 +1261,13 @@ xfs_da3_root_join(
 	error = xfs_da3_node_read(args->trans, dp, child, &bp, args->whichfork);
 	if (error)
 		return error;
+	fa = xfs_da3_header_check(bp, args->owner);
+	if (fa) {
+		__xfs_buf_mark_corrupt(bp, fa);
+		xfs_trans_brelse(args->trans, bp);
+		xfs_da_mark_sick(args);
+		return -EFSCORRUPTED;
+	}
 	xfs_da_blkinfo_onlychild_validate(bp->b_addr, oldroothdr.level);
 
 	/*
@@ -1273,6 +1302,7 @@ xfs_da3_node_toosmall(
 	struct xfs_da_blkinfo	*info;
 	xfs_dablk_t		blkno;
 	struct xfs_buf		*bp;
+	xfs_failaddr_t		fa;
 	struct xfs_da3_icnode_hdr nodehdr;
 	int			count;
 	int			forward;
@@ -1347,6 +1377,13 @@ xfs_da3_node_toosmall(
 				state->args->whichfork);
 		if (error)
 			return error;
+		fa = xfs_da3_node_header_check(bp, state->args->owner);
+		if (fa) {
+			__xfs_buf_mark_corrupt(bp, fa);
+			xfs_trans_brelse(state->args->trans, bp);
+			xfs_da_mark_sick(state->args);
+			return -EFSCORRUPTED;
+		}
 
 		node = bp->b_addr;
 		xfs_da3_node_hdr_from_disk(dp->i_mount, &thdr, node);
@@ -1669,6 +1706,13 @@ xfs_da3_node_lookup_int(
 			return -EFSCORRUPTED;
 		}
 
+		fa = xfs_da3_node_header_check(blk->bp, args->owner);
+		if (fa) {
+			__xfs_buf_mark_corrupt(blk->bp, fa);
+			xfs_da_mark_sick(args);
+			return -EFSCORRUPTED;
+		}
+
 		blk->magic = XFS_DA_NODE_MAGIC;
 
 		/*
@@ -1841,6 +1885,7 @@ xfs_da3_blk_link(
 	struct xfs_da_blkinfo	*tmp_info;
 	struct xfs_da_args	*args;
 	struct xfs_buf		*bp;
+	xfs_failaddr_t		fa;
 	int			before = 0;
 	int			error;
 	struct xfs_inode	*dp = state->args->dp;
@@ -1884,6 +1929,13 @@ xfs_da3_blk_link(
 						&bp, args->whichfork);
 			if (error)
 				return error;
+			fa = xfs_da3_header_check(bp, args->owner);
+			if (fa) {
+				__xfs_buf_mark_corrupt(bp, fa);
+				xfs_trans_brelse(args->trans, bp);
+				xfs_da_mark_sick(args);
+				return -EFSCORRUPTED;
+			}
 			ASSERT(bp != NULL);
 			tmp_info = bp->b_addr;
 			ASSERT(tmp_info->magic == old_info->magic);
@@ -1905,6 +1957,13 @@ xfs_da3_blk_link(
 						&bp, args->whichfork);
 			if (error)
 				return error;
+			fa = xfs_da3_header_check(bp, args->owner);
+			if (fa) {
+				__xfs_buf_mark_corrupt(bp, fa);
+				xfs_trans_brelse(args->trans, bp);
+				xfs_da_mark_sick(args);
+				return -EFSCORRUPTED;
+			}
 			ASSERT(bp != NULL);
 			tmp_info = bp->b_addr;
 			ASSERT(tmp_info->magic == old_info->magic);
@@ -1934,6 +1993,7 @@ xfs_da3_blk_unlink(
 	struct xfs_da_blkinfo	*tmp_info;
 	struct xfs_da_args	*args;
 	struct xfs_buf		*bp;
+	xfs_failaddr_t		fa;
 	int			error;
 
 	/*
@@ -1964,6 +2024,13 @@ xfs_da3_blk_unlink(
 						&bp, args->whichfork);
 			if (error)
 				return error;
+			fa = xfs_da3_header_check(bp, args->owner);
+			if (fa) {
+				__xfs_buf_mark_corrupt(bp, fa);
+				xfs_trans_brelse(args->trans, bp);
+				xfs_da_mark_sick(args);
+				return -EFSCORRUPTED;
+			}
 			ASSERT(bp != NULL);
 			tmp_info = bp->b_addr;
 			ASSERT(tmp_info->magic == save_info->magic);
@@ -1981,6 +2048,13 @@ xfs_da3_blk_unlink(
 						&bp, args->whichfork);
 			if (error)
 				return error;
+			fa = xfs_da3_header_check(bp, args->owner);
+			if (fa) {
+				__xfs_buf_mark_corrupt(bp, fa);
+				xfs_trans_brelse(args->trans, bp);
+				xfs_da_mark_sick(args);
+				return -EFSCORRUPTED;
+			}
 			ASSERT(bp != NULL);
 			tmp_info = bp->b_addr;
 			ASSERT(tmp_info->magic == save_info->magic);
@@ -2096,6 +2170,12 @@ xfs_da3_path_shift(
 		switch (be16_to_cpu(info->magic)) {
 		case XFS_DA_NODE_MAGIC:
 		case XFS_DA3_NODE_MAGIC:
+			fa = xfs_da3_node_header_check(blk->bp, args->owner);
+			if (fa) {
+				__xfs_buf_mark_corrupt(blk->bp, fa);
+				xfs_da_mark_sick(args);
+				return -EFSCORRUPTED;
+			}
 			blk->magic = XFS_DA_NODE_MAGIC;
 			xfs_da3_node_hdr_from_disk(dp->i_mount, &nodehdr,
 						   bp->b_addr);
@@ -2400,6 +2480,13 @@ xfs_da3_swap_lastblock(
 		error = xfs_da3_node_read(tp, dp, sib_blkno, &sib_buf, w);
 		if (error)
 			goto done;
+		fa = xfs_da3_header_check(sib_buf, args->owner);
+		if (fa) {
+			__xfs_buf_mark_corrupt(sib_buf, fa);
+			xfs_da_mark_sick(args);
+			error = -EFSCORRUPTED;
+			goto done;
+		}
 		sib_info = sib_buf->b_addr;
 		if (XFS_IS_CORRUPT(mp,
 				   be32_to_cpu(sib_info->forw) != last_blkno ||
@@ -2421,6 +2508,13 @@ xfs_da3_swap_lastblock(
 		error = xfs_da3_node_read(tp, dp, sib_blkno, &sib_buf, w);
 		if (error)
 			goto done;
+		fa = xfs_da3_header_check(sib_buf, args->owner);
+		if (fa) {
+			__xfs_buf_mark_corrupt(sib_buf, fa);
+			xfs_da_mark_sick(args);
+			error = -EFSCORRUPTED;
+			goto done;
+		}
 		sib_info = sib_buf->b_addr;
 		if (XFS_IS_CORRUPT(mp,
 				   be32_to_cpu(sib_info->back) != last_blkno ||
@@ -2444,6 +2538,13 @@ xfs_da3_swap_lastblock(
 		error = xfs_da3_node_read(tp, dp, par_blkno, &par_buf, w);
 		if (error)
 			goto done;
+		fa = xfs_da3_node_header_check(par_buf, args->owner);
+		if (fa) {
+			__xfs_buf_mark_corrupt(par_buf, fa);
+			xfs_da_mark_sick(args);
+			error = -EFSCORRUPTED;
+			goto done;
+		}
 		par_node = par_buf->b_addr;
 		xfs_da3_node_hdr_from_disk(dp->i_mount, &par_hdr, par_node);
 		if (XFS_IS_CORRUPT(mp,
@@ -2493,6 +2594,13 @@ xfs_da3_swap_lastblock(
 		error = xfs_da3_node_read(tp, dp, par_blkno, &par_buf, w);
 		if (error)
 			goto done;
+		fa = xfs_da3_node_header_check(par_buf, args->owner);
+		if (fa) {
+			__xfs_buf_mark_corrupt(par_buf, fa);
+			xfs_da_mark_sick(args);
+			error = -EFSCORRUPTED;
+			goto done;
+		}
 		par_node = par_buf->b_addr;
 		xfs_da3_node_hdr_from_disk(dp->i_mount, &par_hdr, par_node);
 		if (XFS_IS_CORRUPT(mp, par_hdr.level != level)) {
diff --git a/libxfs/xfs_da_btree.h b/libxfs/xfs_da_btree.h
index 99618e0c8a7..7a004786ee0 100644
--- a/libxfs/xfs_da_btree.h
+++ b/libxfs/xfs_da_btree.h
@@ -237,6 +237,7 @@ void	xfs_da3_node_hdr_from_disk(struct xfs_mount *mp,
 void	xfs_da3_node_hdr_to_disk(struct xfs_mount *mp,
 		struct xfs_da_intnode *to, struct xfs_da3_icnode_hdr *from);
 xfs_failaddr_t xfs_da3_header_check(struct xfs_buf *bp, xfs_ino_t owner);
+xfs_failaddr_t xfs_da3_node_header_check(struct xfs_buf *bp, xfs_ino_t owner);
 
 extern struct kmem_cache	*xfs_da_state_cache;
 

[PATCH 6/9] xfs: validate directory leaf buffer owners

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Check the owner field of directory leaf blocks.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_da_btree.c  |   16 ++++++++++++
 libxfs/xfs_dir2.h      |    2 ++
 libxfs/xfs_dir2_leaf.c |   64 ++++++++++++++++++++++++++++++++++++++++++++----
 libxfs/xfs_dir2_node.c |    3 ++
 libxfs/xfs_dir2_priv.h |    4 ++-
 5 files changed, 80 insertions(+), 9 deletions(-)


diff --git a/libxfs/xfs_da_btree.c b/libxfs/xfs_da_btree.c
index 92eae433a5a..207fec9e287 100644
--- a/libxfs/xfs_da_btree.c
+++ b/libxfs/xfs_da_btree.c
@@ -282,8 +282,12 @@ xfs_da3_header_check(
 		return xfs_attr3_leaf_header_check(bp, owner);
 	case cpu_to_be16(XFS_DA3_NODE_MAGIC):
 		return xfs_da3_node_header_check(bp, owner);
+	case cpu_to_be16(XFS_DIR3_LEAF1_MAGIC):
+	case cpu_to_be16(XFS_DIR3_LEAFN_MAGIC):
+		return xfs_dir3_leaf_header_check(bp, owner);
 	}
 
+	ASSERT(0);
 	return NULL;
 }
 
@@ -1694,6 +1698,12 @@ xfs_da3_node_lookup_int(
 
 		if (magic == XFS_DIR2_LEAFN_MAGIC ||
 		    magic == XFS_DIR3_LEAFN_MAGIC) {
+			fa = xfs_dir3_leaf_header_check(blk->bp, args->owner);
+			if (fa) {
+				__xfs_buf_mark_corrupt(blk->bp, fa);
+				xfs_da_mark_sick(args);
+				return -EFSCORRUPTED;
+			}
 			blk->magic = XFS_DIR2_LEAFN_MAGIC;
 			blk->hashval = xfs_dir2_leaf_lasthash(args->dp,
 							      blk->bp, NULL);
@@ -2202,6 +2212,12 @@ xfs_da3_path_shift(
 			break;
 		case XFS_DIR2_LEAFN_MAGIC:
 		case XFS_DIR3_LEAFN_MAGIC:
+			fa = xfs_dir3_leaf_header_check(blk->bp, args->owner);
+			if (fa) {
+				__xfs_buf_mark_corrupt(blk->bp, fa);
+				xfs_da_mark_sick(args);
+				return -EFSCORRUPTED;
+			}
 			blk->magic = XFS_DIR2_LEAFN_MAGIC;
 			ASSERT(level == path->active-1);
 			blk->index = 0;
diff --git a/libxfs/xfs_dir2.h b/libxfs/xfs_dir2.h
index ac3c264402d..0b01dd6ccf1 100644
--- a/libxfs/xfs_dir2.h
+++ b/libxfs/xfs_dir2.h
@@ -98,6 +98,8 @@ extern struct xfs_dir2_data_free *xfs_dir2_data_freefind(
 
 extern int xfs_dir_ino_validate(struct xfs_mount *mp, xfs_ino_t ino);
 
+xfs_failaddr_t xfs_dir3_leaf_header_check(struct xfs_buf *bp, xfs_ino_t owner);
+
 extern const struct xfs_buf_ops xfs_dir3_block_buf_ops;
 extern const struct xfs_buf_ops xfs_dir3_leafn_buf_ops;
 extern const struct xfs_buf_ops xfs_dir3_leaf1_buf_ops;
diff --git a/libxfs/xfs_dir2_leaf.c b/libxfs/xfs_dir2_leaf.c
index 8fbda22508d..14449a23502 100644
--- a/libxfs/xfs_dir2_leaf.c
+++ b/libxfs/xfs_dir2_leaf.c
@@ -206,6 +206,28 @@ xfs_dir3_leaf_verify(
 	return xfs_dir3_leaf_check_int(mp, &leafhdr, bp->b_addr, true);
 }
 
+xfs_failaddr_t
+xfs_dir3_leaf_header_check(
+	struct xfs_buf		*bp,
+	xfs_ino_t		owner)
+{
+	struct xfs_mount	*mp = bp->b_mount;
+
+	if (xfs_has_crc(mp)) {
+		struct xfs_dir3_leaf *hdr3 = bp->b_addr;
+
+		ASSERT(hdr3->hdr.info.hdr.magic ==
+					cpu_to_be16(XFS_DIR3_LEAF1_MAGIC) ||
+		       hdr3->hdr.info.hdr.magic ==
+					cpu_to_be16(XFS_DIR3_LEAFN_MAGIC));
+
+		if (be64_to_cpu(hdr3->hdr.info.owner) != owner)
+			return __this_address;
+	}
+
+	return NULL;
+}
+
 static void
 xfs_dir3_leaf_read_verify(
 	struct xfs_buf  *bp)
@@ -269,32 +291,60 @@ int
 xfs_dir3_leaf_read(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*dp,
+	xfs_ino_t		owner,
 	xfs_dablk_t		fbno,
 	struct xfs_buf		**bpp)
 {
+	xfs_failaddr_t		fa;
 	int			err;
 
 	err = xfs_da_read_buf(tp, dp, fbno, 0, bpp, XFS_DATA_FORK,
 			&xfs_dir3_leaf1_buf_ops);
-	if (!err && tp && *bpp)
+	if (err || !(*bpp))
+		return err;
+
+	fa = xfs_dir3_leaf_header_check(*bpp, owner);
+	if (fa) {
+		__xfs_buf_mark_corrupt(*bpp, fa);
+		xfs_trans_brelse(tp, *bpp);
+		*bpp = NULL;
+		xfs_dirattr_mark_sick(dp, XFS_DATA_FORK);
+		return -EFSCORRUPTED;
+	}
+
+	if (tp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAF1_BUF);
-	return err;
+	return 0;
 }
 
 int
 xfs_dir3_leafn_read(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*dp,
+	xfs_ino_t		owner,
 	xfs_dablk_t		fbno,
 	struct xfs_buf		**bpp)
 {
+	xfs_failaddr_t		fa;
 	int			err;
 
 	err = xfs_da_read_buf(tp, dp, fbno, 0, bpp, XFS_DATA_FORK,
 			&xfs_dir3_leafn_buf_ops);
-	if (!err && tp && *bpp)
+	if (err || !(*bpp))
+		return err;
+
+	fa = xfs_dir3_leaf_header_check(*bpp, owner);
+	if (fa) {
+		__xfs_buf_mark_corrupt(*bpp, fa);
+		xfs_trans_brelse(tp, *bpp);
+		*bpp = NULL;
+		xfs_dirattr_mark_sick(dp, XFS_DATA_FORK);
+		return -EFSCORRUPTED;
+	}
+
+	if (tp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAFN_BUF);
-	return err;
+	return 0;
 }
 
 /*
@@ -644,7 +694,8 @@ xfs_dir2_leaf_addname(
 
 	trace_xfs_dir2_leaf_addname(args);
 
-	error = xfs_dir3_leaf_read(tp, dp, args->geo->leafblk, &lbp);
+	error = xfs_dir3_leaf_read(tp, dp, args->owner, args->geo->leafblk,
+			&lbp);
 	if (error)
 		return error;
 
@@ -1235,7 +1286,8 @@ xfs_dir2_leaf_lookup_int(
 	tp = args->trans;
 	mp = dp->i_mount;
 
-	error = xfs_dir3_leaf_read(tp, dp, args->geo->leafblk, &lbp);
+	error = xfs_dir3_leaf_read(tp, dp, args->owner, args->geo->leafblk,
+			&lbp);
 	if (error)
 		return error;
 
diff --git a/libxfs/xfs_dir2_node.c b/libxfs/xfs_dir2_node.c
index b00f783877e..c0160d725e5 100644
--- a/libxfs/xfs_dir2_node.c
+++ b/libxfs/xfs_dir2_node.c
@@ -1559,7 +1559,8 @@ xfs_dir2_leafn_toosmall(
 		/*
 		 * Read the sibling leaf block.
 		 */
-		error = xfs_dir3_leafn_read(state->args->trans, dp, blkno, &bp);
+		error = xfs_dir3_leafn_read(state->args->trans, dp,
+				state->args->owner, blkno, &bp);
 		if (error)
 			return error;
 
diff --git a/libxfs/xfs_dir2_priv.h b/libxfs/xfs_dir2_priv.h
index 1db2e60ba82..2f0e3ad47b3 100644
--- a/libxfs/xfs_dir2_priv.h
+++ b/libxfs/xfs_dir2_priv.h
@@ -95,9 +95,9 @@ void xfs_dir2_leaf_hdr_from_disk(struct xfs_mount *mp,
 void xfs_dir2_leaf_hdr_to_disk(struct xfs_mount *mp, struct xfs_dir2_leaf *to,
 		struct xfs_dir3_icleaf_hdr *from);
 int xfs_dir3_leaf_read(struct xfs_trans *tp, struct xfs_inode *dp,
-		xfs_dablk_t fbno, struct xfs_buf **bpp);
+		xfs_ino_t owner, xfs_dablk_t fbno, struct xfs_buf **bpp);
 int xfs_dir3_leafn_read(struct xfs_trans *tp, struct xfs_inode *dp,
-		xfs_dablk_t fbno, struct xfs_buf **bpp);
+		xfs_ino_t owner, xfs_dablk_t fbno, struct xfs_buf **bpp);
 extern int xfs_dir2_block_to_leaf(struct xfs_da_args *args,
 		struct xfs_buf *dbp);
 extern int xfs_dir2_leaf_addname(struct xfs_da_args *args);

[PATCH 7/9] xfs: validate explicit directory data buffer owners

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Port the existing directory data header checking function to accept an
owner number instead of an xfs_inode, then update the callsites to use
xfs_da_args.owner when possible.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 db/namei.c              |    3 ++-
 libxfs/xfs_dir2.h       |    1 +
 libxfs/xfs_dir2_block.c |    3 ++-
 libxfs/xfs_dir2_data.c  |   15 +++++++++------
 libxfs/xfs_dir2_leaf.c  |   21 +++++++++++----------
 libxfs/xfs_dir2_node.c  |    7 +++----
 libxfs/xfs_dir2_priv.h  |    3 ++-
 7 files changed, 30 insertions(+), 23 deletions(-)


diff --git a/db/namei.c b/db/namei.c
index eb09288b490..d7bf489cd53 100644
--- a/db/namei.c
+++ b/db/namei.c
@@ -400,7 +400,8 @@ list_leafdir(
 		libxfs_trim_extent(&map, dabno, geo->leafblk - dabno);
 
 		/* Read the directory block of that first mapping. */
-		error = xfs_dir3_data_read(NULL, dp, map.br_startoff, 0, &bp);
+		error = xfs_dir3_data_read(NULL, dp, args->owner,
+				map.br_startoff, 0, &bp);
 		if (error)
 			break;
 
diff --git a/libxfs/xfs_dir2.h b/libxfs/xfs_dir2.h
index 0b01dd6ccf1..537596b9de4 100644
--- a/libxfs/xfs_dir2.h
+++ b/libxfs/xfs_dir2.h
@@ -99,6 +99,7 @@ extern struct xfs_dir2_data_free *xfs_dir2_data_freefind(
 extern int xfs_dir_ino_validate(struct xfs_mount *mp, xfs_ino_t ino);
 
 xfs_failaddr_t xfs_dir3_leaf_header_check(struct xfs_buf *bp, xfs_ino_t owner);
+xfs_failaddr_t xfs_dir3_data_header_check(struct xfs_buf *bp, xfs_ino_t owner);
 
 extern const struct xfs_buf_ops xfs_dir3_block_buf_ops;
 extern const struct xfs_buf_ops xfs_dir3_leafn_buf_ops;
diff --git a/libxfs/xfs_dir2_block.c b/libxfs/xfs_dir2_block.c
index 1f6a88091e7..86e49fbc2b7 100644
--- a/libxfs/xfs_dir2_block.c
+++ b/libxfs/xfs_dir2_block.c
@@ -979,7 +979,8 @@ xfs_dir2_leaf_to_block(
 	 * Read the data block if we don't already have it, give up if it fails.
 	 */
 	if (!dbp) {
-		error = xfs_dir3_data_read(tp, dp, args->geo->datablk, 0, &dbp);
+		error = xfs_dir3_data_read(tp, dp, args->owner,
+				args->geo->datablk, 0, &dbp);
 		if (error)
 			return error;
 	}
diff --git a/libxfs/xfs_dir2_data.c b/libxfs/xfs_dir2_data.c
index 6f3ccfeb69f..9ce0039d6ac 100644
--- a/libxfs/xfs_dir2_data.c
+++ b/libxfs/xfs_dir2_data.c
@@ -392,17 +392,19 @@ static const struct xfs_buf_ops xfs_dir3_data_reada_buf_ops = {
 	.verify_write = xfs_dir3_data_write_verify,
 };
 
-static xfs_failaddr_t
+xfs_failaddr_t
 xfs_dir3_data_header_check(
-	struct xfs_inode	*dp,
-	struct xfs_buf		*bp)
+	struct xfs_buf		*bp,
+	xfs_ino_t		owner)
 {
-	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_mount	*mp = bp->b_mount;
 
 	if (xfs_has_crc(mp)) {
 		struct xfs_dir3_data_hdr *hdr3 = bp->b_addr;
 
-		if (be64_to_cpu(hdr3->hdr.owner) != dp->i_ino)
+		ASSERT(hdr3->hdr.magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC));
+
+		if (be64_to_cpu(hdr3->hdr.owner) != owner)
 			return __this_address;
 	}
 
@@ -413,6 +415,7 @@ int
 xfs_dir3_data_read(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*dp,
+	xfs_ino_t		owner,
 	xfs_dablk_t		bno,
 	unsigned int		flags,
 	struct xfs_buf		**bpp)
@@ -426,7 +429,7 @@ xfs_dir3_data_read(
 		return err;
 
 	/* Check things that we can't do in the verifier. */
-	fa = xfs_dir3_data_header_check(dp, *bpp);
+	fa = xfs_dir3_data_header_check(*bpp, owner);
 	if (fa) {
 		__xfs_buf_mark_corrupt(*bpp, fa);
 		xfs_trans_brelse(tp, *bpp);
diff --git a/libxfs/xfs_dir2_leaf.c b/libxfs/xfs_dir2_leaf.c
index 14449a23502..dd2bb2bc8b6 100644
--- a/libxfs/xfs_dir2_leaf.c
+++ b/libxfs/xfs_dir2_leaf.c
@@ -882,9 +882,9 @@ xfs_dir2_leaf_addname(
 		 * Already had space in some data block.
 		 * Just read that one in.
 		 */
-		error = xfs_dir3_data_read(tp, dp,
-				   xfs_dir2_db_to_da(args->geo, use_block),
-				   0, &dbp);
+		error = xfs_dir3_data_read(tp, dp, args->owner,
+				xfs_dir2_db_to_da(args->geo, use_block), 0,
+				&dbp);
 		if (error) {
 			xfs_trans_brelse(tp, lbp);
 			return error;
@@ -1325,9 +1325,9 @@ xfs_dir2_leaf_lookup_int(
 		if (newdb != curdb) {
 			if (dbp)
 				xfs_trans_brelse(tp, dbp);
-			error = xfs_dir3_data_read(tp, dp,
-					   xfs_dir2_db_to_da(args->geo, newdb),
-					   0, &dbp);
+			error = xfs_dir3_data_read(tp, dp, args->owner,
+					xfs_dir2_db_to_da(args->geo, newdb), 0,
+					&dbp);
 			if (error) {
 				xfs_trans_brelse(tp, lbp);
 				return error;
@@ -1367,9 +1367,9 @@ xfs_dir2_leaf_lookup_int(
 		ASSERT(cidb != -1);
 		if (cidb != curdb) {
 			xfs_trans_brelse(tp, dbp);
-			error = xfs_dir3_data_read(tp, dp,
-					   xfs_dir2_db_to_da(args->geo, cidb),
-					   0, &dbp);
+			error = xfs_dir3_data_read(tp, dp, args->owner,
+					xfs_dir2_db_to_da(args->geo, cidb), 0,
+					&dbp);
 			if (error) {
 				xfs_trans_brelse(tp, lbp);
 				return error;
@@ -1663,7 +1663,8 @@ xfs_dir2_leaf_trim_data(
 	/*
 	 * Read the offending data block.  We need its buffer.
 	 */
-	error = xfs_dir3_data_read(tp, dp, xfs_dir2_db_to_da(geo, db), 0, &dbp);
+	error = xfs_dir3_data_read(tp, dp, args->owner,
+			xfs_dir2_db_to_da(geo, db), 0, &dbp);
 	if (error)
 		return error;
 
diff --git a/libxfs/xfs_dir2_node.c b/libxfs/xfs_dir2_node.c
index c0160d725e5..69040737418 100644
--- a/libxfs/xfs_dir2_node.c
+++ b/libxfs/xfs_dir2_node.c
@@ -860,7 +860,7 @@ xfs_dir2_leafn_lookup_for_entry(
 				ASSERT(state->extravalid);
 				curbp = state->extrablk.bp;
 			} else {
-				error = xfs_dir3_data_read(tp, dp,
+				error = xfs_dir3_data_read(tp, dp, args->owner,
 						xfs_dir2_db_to_da(args->geo,
 								  newdb),
 						0, &curbp);
@@ -1946,9 +1946,8 @@ xfs_dir2_node_addname_int(
 						  &freehdr, &findex);
 	} else {
 		/* Read the data block in. */
-		error = xfs_dir3_data_read(tp, dp,
-					   xfs_dir2_db_to_da(args->geo, dbno),
-					   0, &dbp);
+		error = xfs_dir3_data_read(tp, dp, args->owner,
+				xfs_dir2_db_to_da(args->geo, dbno), 0, &dbp);
 	}
 	if (error)
 		return error;
diff --git a/libxfs/xfs_dir2_priv.h b/libxfs/xfs_dir2_priv.h
index 2f0e3ad47b3..879aa2e9fd7 100644
--- a/libxfs/xfs_dir2_priv.h
+++ b/libxfs/xfs_dir2_priv.h
@@ -78,7 +78,8 @@ extern void xfs_dir3_data_check(struct xfs_inode *dp, struct xfs_buf *bp);
 extern xfs_failaddr_t __xfs_dir3_data_check(struct xfs_inode *dp,
 		struct xfs_buf *bp);
 int xfs_dir3_data_read(struct xfs_trans *tp, struct xfs_inode *dp,
-		xfs_dablk_t bno, unsigned int flags, struct xfs_buf **bpp);
+		xfs_ino_t owner, xfs_dablk_t bno, unsigned int flags,
+		struct xfs_buf **bpp);
 int xfs_dir3_data_readahead(struct xfs_inode *dp, xfs_dablk_t bno,
 		unsigned int flags);
 

[PATCH 8/9] xfs: validate explicit directory block buffer owners

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Port the existing directory block header checking function to accept an
owner number instead of an xfs_inode, then update the callsites to use
xfs_da_args.owner when possible.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 db/namei.c              |    2 +-
 libxfs/xfs_dir2.h       |    1 +
 libxfs/xfs_dir2_block.c |   22 ++++++++++++++--------
 libxfs/xfs_dir2_priv.h  |    2 +-
 libxfs/xfs_swapext.c    |    2 +-
 5 files changed, 18 insertions(+), 11 deletions(-)


diff --git a/db/namei.c b/db/namei.c
index d7bf489cd53..a8577b97222 100644
--- a/db/namei.c
+++ b/db/namei.c
@@ -339,7 +339,7 @@ list_blockdir(
 	unsigned int		end;
 	int			error;
 
-	error = xfs_dir3_block_read(NULL, dp, &bp);
+	error = xfs_dir3_block_read(NULL, dp, args->owner, &bp);
 	if (error)
 		return error;
 
diff --git a/libxfs/xfs_dir2.h b/libxfs/xfs_dir2.h
index 537596b9de4..f99788a1f3e 100644
--- a/libxfs/xfs_dir2.h
+++ b/libxfs/xfs_dir2.h
@@ -100,6 +100,7 @@ extern int xfs_dir_ino_validate(struct xfs_mount *mp, xfs_ino_t ino);
 
 xfs_failaddr_t xfs_dir3_leaf_header_check(struct xfs_buf *bp, xfs_ino_t owner);
 xfs_failaddr_t xfs_dir3_data_header_check(struct xfs_buf *bp, xfs_ino_t owner);
+xfs_failaddr_t xfs_dir3_block_header_check(struct xfs_buf *bp, xfs_ino_t owner);
 
 extern const struct xfs_buf_ops xfs_dir3_block_buf_ops;
 extern const struct xfs_buf_ops xfs_dir3_leafn_buf_ops;
diff --git a/libxfs/xfs_dir2_block.c b/libxfs/xfs_dir2_block.c
index 86e49fbc2b7..370f4df0c72 100644
--- a/libxfs/xfs_dir2_block.c
+++ b/libxfs/xfs_dir2_block.c
@@ -112,18 +112,23 @@ const struct xfs_buf_ops xfs_dir3_block_buf_ops = {
 	.verify_struct = xfs_dir3_block_verify,
 };
 
-static xfs_failaddr_t
+xfs_failaddr_t
 xfs_dir3_block_header_check(
-	struct xfs_inode	*dp,
-	struct xfs_buf		*bp)
+	struct xfs_buf		*bp,
+	xfs_ino_t		owner)
 {
-	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_mount	*mp = bp->b_mount;
 
 	if (xfs_has_crc(mp)) {
 		struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;
 
-		if (be64_to_cpu(hdr3->owner) != dp->i_ino)
+		ASSERT(hdr3->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
+
+		if (be64_to_cpu(hdr3->owner) != owner) {
+			xfs_err(NULL, "dir block owner 0x%llx doesnt match block 0x%llx", owner, be64_to_cpu(hdr3->owner));
+			dump_stack();
 			return __this_address;
+		}
 	}
 
 	return NULL;
@@ -133,6 +138,7 @@ int
 xfs_dir3_block_read(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*dp,
+	xfs_ino_t		owner,
 	struct xfs_buf		**bpp)
 {
 	struct xfs_mount	*mp = dp->i_mount;
@@ -145,7 +151,7 @@ xfs_dir3_block_read(
 		return err;
 
 	/* Check things that we can't do in the verifier. */
-	fa = xfs_dir3_block_header_check(dp, *bpp);
+	fa = xfs_dir3_block_header_check(*bpp, owner);
 	if (fa) {
 		__xfs_buf_mark_corrupt(*bpp, fa);
 		xfs_trans_brelse(tp, *bpp);
@@ -380,7 +386,7 @@ xfs_dir2_block_addname(
 	tp = args->trans;
 
 	/* Read the (one and only) directory block into bp. */
-	error = xfs_dir3_block_read(tp, dp, &bp);
+	error = xfs_dir3_block_read(tp, dp, args->owner, &bp);
 	if (error)
 		return error;
 
@@ -695,7 +701,7 @@ xfs_dir2_block_lookup_int(
 	dp = args->dp;
 	tp = args->trans;
 
-	error = xfs_dir3_block_read(tp, dp, &bp);
+	error = xfs_dir3_block_read(tp, dp, args->owner, &bp);
 	if (error)
 		return error;
 
diff --git a/libxfs/xfs_dir2_priv.h b/libxfs/xfs_dir2_priv.h
index 879aa2e9fd7..969e36a03fe 100644
--- a/libxfs/xfs_dir2_priv.h
+++ b/libxfs/xfs_dir2_priv.h
@@ -51,7 +51,7 @@ extern int xfs_dir_cilookup_result(struct xfs_da_args *args,
 
 /* xfs_dir2_block.c */
 extern int xfs_dir3_block_read(struct xfs_trans *tp, struct xfs_inode *dp,
-			       struct xfs_buf **bpp);
+			       xfs_ino_t owner, struct xfs_buf **bpp);
 extern int xfs_dir2_block_addname(struct xfs_da_args *args);
 extern int xfs_dir2_block_lookup(struct xfs_da_args *args);
 extern int xfs_dir2_block_removename(struct xfs_da_args *args);
diff --git a/libxfs/xfs_swapext.c b/libxfs/xfs_swapext.c
index eae4f6b7310..f396593a5c8 100644
--- a/libxfs/xfs_swapext.c
+++ b/libxfs/xfs_swapext.c
@@ -571,7 +571,7 @@ xfs_swapext_dir_to_sf(
 	if (!isblock)
 		return 0;
 
-	error = xfs_dir3_block_read(tp, sxi->sxi_ip2, &bp);
+	error = xfs_dir3_block_read(tp, sxi->sxi_ip2, sxi->sxi_ip2->i_ino, &bp);
 	if (error)
 		return error;
 

[PATCH 9/9] xfs: validate explicit directory free block owners

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Port the existing directory freespace block header checking function to
accept an owner number instead of an xfs_inode, then update the
callsites to use xfs_da_args.owner when possible.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_dir2_leaf.c |    3 ++-
 libxfs/xfs_dir2_node.c |   32 ++++++++++++++++++--------------
 libxfs/xfs_dir2_priv.h |    2 +-
 3 files changed, 21 insertions(+), 16 deletions(-)


diff --git a/libxfs/xfs_dir2_leaf.c b/libxfs/xfs_dir2_leaf.c
index dd2bb2bc8b6..77eca816c66 100644
--- a/libxfs/xfs_dir2_leaf.c
+++ b/libxfs/xfs_dir2_leaf.c
@@ -1803,7 +1803,8 @@ xfs_dir2_node_to_leaf(
 	/*
 	 * Read the freespace block.
 	 */
-	error = xfs_dir2_free_read(tp, dp,  args->geo->freeblk, &fbp);
+	error = xfs_dir2_free_read(tp, dp, args->owner, args->geo->freeblk,
+			&fbp);
 	if (error)
 		return error;
 	xfs_dir2_free_hdr_from_disk(mp, &freehdr, fbp->b_addr);
diff --git a/libxfs/xfs_dir2_node.c b/libxfs/xfs_dir2_node.c
index 69040737418..c94d00eb99c 100644
--- a/libxfs/xfs_dir2_node.c
+++ b/libxfs/xfs_dir2_node.c
@@ -172,11 +172,11 @@ const struct xfs_buf_ops xfs_dir3_free_buf_ops = {
 /* Everything ok in the free block header? */
 static xfs_failaddr_t
 xfs_dir3_free_header_check(
-	struct xfs_inode	*dp,
-	xfs_dablk_t		fbno,
-	struct xfs_buf		*bp)
+	struct xfs_buf		*bp,
+	xfs_ino_t		owner,
+	xfs_dablk_t		fbno)
 {
-	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_mount	*mp = bp->b_mount;
 	int			maxbests = mp->m_dir_geo->free_max_bests;
 	unsigned int		firstdb;
 
@@ -192,7 +192,7 @@ xfs_dir3_free_header_check(
 			return __this_address;
 		if (be32_to_cpu(hdr3->nvalid) < be32_to_cpu(hdr3->nused))
 			return __this_address;
-		if (be64_to_cpu(hdr3->hdr.owner) != dp->i_ino)
+		if (be64_to_cpu(hdr3->hdr.owner) != owner)
 			return __this_address;
 	} else {
 		struct xfs_dir2_free_hdr *hdr = bp->b_addr;
@@ -211,6 +211,7 @@ static int
 __xfs_dir3_free_read(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*dp,
+	xfs_ino_t		owner,
 	xfs_dablk_t		fbno,
 	unsigned int		flags,
 	struct xfs_buf		**bpp)
@@ -224,7 +225,7 @@ __xfs_dir3_free_read(
 		return err;
 
 	/* Check things that we can't do in the verifier. */
-	fa = xfs_dir3_free_header_check(dp, fbno, *bpp);
+	fa = xfs_dir3_free_header_check(*bpp, owner, fbno);
 	if (fa) {
 		__xfs_buf_mark_corrupt(*bpp, fa);
 		xfs_trans_brelse(tp, *bpp);
@@ -296,20 +297,23 @@ int
 xfs_dir2_free_read(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*dp,
+	xfs_ino_t		owner,
 	xfs_dablk_t		fbno,
 	struct xfs_buf		**bpp)
 {
-	return __xfs_dir3_free_read(tp, dp, fbno, 0, bpp);
+	return __xfs_dir3_free_read(tp, dp, owner, fbno, 0, bpp);
 }
 
 static int
 xfs_dir2_free_try_read(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*dp,
+	xfs_ino_t		owner,
 	xfs_dablk_t		fbno,
 	struct xfs_buf		**bpp)
 {
-	return __xfs_dir3_free_read(tp, dp, fbno, XFS_DABUF_MAP_HOLE_OK, bpp);
+	return __xfs_dir3_free_read(tp, dp, owner, fbno, XFS_DABUF_MAP_HOLE_OK,
+			bpp);
 }
 
 static int
@@ -714,7 +718,7 @@ xfs_dir2_leafn_lookup_for_addname(
 				if (curbp)
 					xfs_trans_brelse(tp, curbp);
 
-				error = xfs_dir2_free_read(tp, dp,
+				error = xfs_dir2_free_read(tp, dp, args->owner,
 						xfs_dir2_db_to_da(args->geo,
 								  newfdb),
 						&curbp);
@@ -1353,8 +1357,8 @@ xfs_dir2_leafn_remove(
 		 * read in the free block.
 		 */
 		fdb = xfs_dir2_db_to_fdb(geo, db);
-		error = xfs_dir2_free_read(tp, dp, xfs_dir2_db_to_da(geo, fdb),
-					   &fbp);
+		error = xfs_dir2_free_read(tp, dp, args->owner,
+				xfs_dir2_db_to_da(geo, fdb), &fbp);
 		if (error)
 			return error;
 		free = fbp->b_addr;
@@ -1713,7 +1717,7 @@ xfs_dir2_node_add_datablk(
 	 * that was just allocated.
 	 */
 	fbno = xfs_dir2_db_to_fdb(args->geo, *dbno);
-	error = xfs_dir2_free_try_read(tp, dp,
+	error = xfs_dir2_free_try_read(tp, dp, args->owner,
 			       xfs_dir2_db_to_da(args->geo, fbno), &fbp);
 	if (error)
 		return error;
@@ -1860,7 +1864,7 @@ xfs_dir2_node_find_freeblk(
 		 * so this might not succeed.  This should be really rare, so
 		 * there's no reason to avoid it.
 		 */
-		error = xfs_dir2_free_try_read(tp, dp,
+		error = xfs_dir2_free_try_read(tp, dp, args->owner,
 				xfs_dir2_db_to_da(args->geo, fbno),
 				&fbp);
 		if (error)
@@ -2299,7 +2303,7 @@ xfs_dir2_node_trim_free(
 	/*
 	 * Read the freespace block.
 	 */
-	error = xfs_dir2_free_try_read(tp, dp, fo, &bp);
+	error = xfs_dir2_free_try_read(tp, dp, args->owner, fo, &bp);
 	if (error)
 		return error;
 	/*
diff --git a/libxfs/xfs_dir2_priv.h b/libxfs/xfs_dir2_priv.h
index 969e36a03fe..f9bc280e8c2 100644
--- a/libxfs/xfs_dir2_priv.h
+++ b/libxfs/xfs_dir2_priv.h
@@ -156,7 +156,7 @@ extern int xfs_dir2_node_replace(struct xfs_da_args *args);
 extern int xfs_dir2_node_trim_free(struct xfs_da_args *args, xfs_fileoff_t fo,
 		int *rvalp);
 extern int xfs_dir2_free_read(struct xfs_trans *tp, struct xfs_inode *dp,
-		xfs_dablk_t fbno, struct xfs_buf **bpp);
+		xfs_ino_t owner, xfs_dablk_t fbno, struct xfs_buf **bpp);
 
 /* xfs_dir2_sf.c */
 xfs_ino_t xfs_dir2_sf_get_ino(struct xfs_mount *mp, struct xfs_dir2_sf_hdr *hdr,

[PATCH 1/1] xfs: repair extended attributes

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If the extended attributes look bad, try to sift through the rubble to
find whatever keys/values we can, stage a new attribute structure in a
temporary file and use the atomic extent swapping mechanism to commit
the results in bulk.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_attr.c      |    2 +-
 libxfs/xfs_attr.h      |    2 ++
 libxfs/xfs_da_format.h |    5 +++++
 libxfs/xfs_swapext.c   |    2 +-
 libxfs/xfs_swapext.h   |    1 +
 5 files changed, 10 insertions(+), 2 deletions(-)


diff --git a/libxfs/xfs_attr.c b/libxfs/xfs_attr.c
index 985989b5ade..8f527ac9292 100644
--- a/libxfs/xfs_attr.c
+++ b/libxfs/xfs_attr.c
@@ -1045,7 +1045,7 @@ xfs_attr_set(
  * External routines when attribute list is inside the inode
  *========================================================================*/
 
-static inline int xfs_attr_sf_totsize(struct xfs_inode *dp)
+int xfs_attr_sf_totsize(struct xfs_inode *dp)
 {
 	struct xfs_attr_shortform *sf;
 
diff --git a/libxfs/xfs_attr.h b/libxfs/xfs_attr.h
index 81be9b3e400..e4f55008552 100644
--- a/libxfs/xfs_attr.h
+++ b/libxfs/xfs_attr.h
@@ -618,4 +618,6 @@ extern struct kmem_cache *xfs_attr_intent_cache;
 int __init xfs_attr_intent_init_cache(void);
 void xfs_attr_intent_destroy_cache(void);
 
+int xfs_attr_sf_totsize(struct xfs_inode *dp);
+
 #endif	/* __XFS_ATTR_H__ */
diff --git a/libxfs/xfs_da_format.h b/libxfs/xfs_da_format.h
index 44748f1640e..0e1ada44f21 100644
--- a/libxfs/xfs_da_format.h
+++ b/libxfs/xfs_da_format.h
@@ -716,6 +716,11 @@ struct xfs_attr3_leafblock {
 #define XFS_ATTR_INCOMPLETE	(1u << XFS_ATTR_INCOMPLETE_BIT)
 #define XFS_ATTR_NSP_ONDISK_MASK	(XFS_ATTR_ROOT | XFS_ATTR_SECURE)
 
+#define XFS_ATTR_NAMESPACE_STR \
+	{ XFS_ATTR_LOCAL,	"local" }, \
+	{ XFS_ATTR_ROOT,	"root" }, \
+	{ XFS_ATTR_SECURE,	"secure" }
+
 /*
  * Alignment for namelist and valuelist entries (since they are mixed
  * there can be only one alignment value)
diff --git a/libxfs/xfs_swapext.c b/libxfs/xfs_swapext.c
index f396593a5c8..1f7fbe76a89 100644
--- a/libxfs/xfs_swapext.c
+++ b/libxfs/xfs_swapext.c
@@ -767,7 +767,7 @@ xfs_swapext_rmapbt_blocks(
 }
 
 /* Estimate the bmbt and rmapbt overhead required to exchange extents. */
-static int
+int
 xfs_swapext_estimate_overhead(
 	struct xfs_swapext_req	*req)
 {
diff --git a/libxfs/xfs_swapext.h b/libxfs/xfs_swapext.h
index 37842a4ee9a..a4768eddc9c 100644
--- a/libxfs/xfs_swapext.h
+++ b/libxfs/xfs_swapext.h
@@ -200,6 +200,7 @@ unsigned int xfs_swapext_reflink_prep(const struct xfs_swapext_req *req);
 void xfs_swapext_reflink_finish(struct xfs_trans *tp,
 		const struct xfs_swapext_req *req, unsigned int reflink_state);
 
+int xfs_swapext_estimate_overhead(struct xfs_swapext_req *req);
 int xfs_swapext_estimate(struct xfs_swapext_req *req);
 
 extern struct kmem_cache	*xfs_swapext_intent_cache;

[PATCH 1/1] xfs: online repair of symbolic links

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If a symbolic link target looks bad, try to sift through the rubble to
find as much of the target buffer that we can, and stage a new target
(short or remote format as needed) in a temporary file and use the
atomic extent swapping mechanism to commit the results.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_bmap.c           |   11 ++++++-----
 libxfs/xfs_bmap.h           |    6 ++++++
 libxfs/xfs_symlink_remote.c |    9 +++++----
 libxfs/xfs_symlink_remote.h |   22 ++++++++++++++++++----
 4 files changed, 35 insertions(+), 13 deletions(-)


diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index 296e7d85f63..c6f2f4ace53 100644
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -755,7 +755,7 @@ xfs_bmap_local_to_extents_empty(
 }
 
 
-STATIC int				/* error */
+int					/* error */
 xfs_bmap_local_to_extents(
 	xfs_trans_t	*tp,		/* transaction pointer */
 	xfs_inode_t	*ip,		/* incore inode pointer */
@@ -765,7 +765,8 @@ xfs_bmap_local_to_extents(
 	void		(*init_fn)(struct xfs_trans *tp,
 				   struct xfs_buf *bp,
 				   struct xfs_inode *ip,
-				   struct xfs_ifork *ifp))
+				   struct xfs_ifork *ifp, void *priv),
+	void		*priv)
 {
 	int		error = 0;
 	int		flags;		/* logging flags returned */
@@ -826,7 +827,7 @@ xfs_bmap_local_to_extents(
 	 * log here. Note that init_fn must also set the buffer log item type
 	 * correctly.
 	 */
-	init_fn(tp, bp, ip, ifp);
+	init_fn(tp, bp, ip, ifp, priv);
 
 	/* account for the change in fork size */
 	xfs_idata_realloc(ip, -ifp->if_bytes, whichfork);
@@ -958,8 +959,8 @@ xfs_bmap_add_attrfork_local(
 
 	if (S_ISLNK(VFS_I(ip)->i_mode))
 		return xfs_bmap_local_to_extents(tp, ip, 1, flags,
-						 XFS_DATA_FORK,
-						 xfs_symlink_local_to_remote);
+				XFS_DATA_FORK, xfs_symlink_local_to_remote,
+				NULL);
 
 	/* should only be called for types that support local format data */
 	ASSERT(0);
diff --git a/libxfs/xfs_bmap.h b/libxfs/xfs_bmap.h
index ccd1ddcd785..87633449c37 100644
--- a/libxfs/xfs_bmap.h
+++ b/libxfs/xfs_bmap.h
@@ -177,6 +177,12 @@ unsigned int xfs_bmap_compute_attr_offset(struct xfs_mount *mp);
 int	xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
 void	xfs_bmap_local_to_extents_empty(struct xfs_trans *tp,
 		struct xfs_inode *ip, int whichfork);
+int xfs_bmap_local_to_extents(struct xfs_trans *tp, struct xfs_inode *ip,
+		xfs_extlen_t total, int *logflagsp, int whichfork,
+		void (*init_fn)(struct xfs_trans *tp, struct xfs_buf *bp,
+				struct xfs_inode *ip, struct xfs_ifork *ifp,
+				void *priv),
+		void *priv);
 void	xfs_bmap_compute_maxlevels(struct xfs_mount *mp, int whichfork);
 int	xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork);
diff --git a/libxfs/xfs_symlink_remote.c b/libxfs/xfs_symlink_remote.c
index a4a242bc3d4..276e3069190 100644
--- a/libxfs/xfs_symlink_remote.c
+++ b/libxfs/xfs_symlink_remote.c
@@ -166,7 +166,8 @@ xfs_symlink_local_to_remote(
 	struct xfs_trans	*tp,
 	struct xfs_buf		*bp,
 	struct xfs_inode	*ip,
-	struct xfs_ifork	*ifp)
+	struct xfs_ifork	*ifp,
+	void			*priv)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	char			*buf;
@@ -304,9 +305,10 @@ xfs_symlink_remote_read(
 
 /* Write the symlink target into the inode. */
 int
-xfs_symlink_write_target(
+__xfs_symlink_write_target(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
+	xfs_ino_t		owner,
 	const char		*target_path,
 	int			pathlen,
 	xfs_fsblock_t		fs_blocks,
@@ -361,8 +363,7 @@ xfs_symlink_write_target(
 		byte_cnt = min(byte_cnt, pathlen);
 
 		buf = bp->b_addr;
-		buf += xfs_symlink_hdr_set(mp, ip->i_ino, offset, byte_cnt,
-				bp);
+		buf += xfs_symlink_hdr_set(mp, owner, offset, byte_cnt, bp);
 
 		memcpy(buf, cur_chunk, byte_cnt);
 
diff --git a/libxfs/xfs_symlink_remote.h b/libxfs/xfs_symlink_remote.h
index ac3dac8f617..e409d680133 100644
--- a/libxfs/xfs_symlink_remote.h
+++ b/libxfs/xfs_symlink_remote.h
@@ -16,12 +16,26 @@ int xfs_symlink_hdr_set(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
 bool xfs_symlink_hdr_ok(xfs_ino_t ino, uint32_t offset,
 			uint32_t size, struct xfs_buf *bp);
 void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
-				 struct xfs_inode *ip, struct xfs_ifork *ifp);
+				 struct xfs_inode *ip, struct xfs_ifork *ifp,
+				 void *priv);
 xfs_failaddr_t xfs_symlink_shortform_verify(void *sfp, int64_t size);
 int xfs_symlink_remote_read(struct xfs_inode *ip, char *link);
-int xfs_symlink_write_target(struct xfs_trans *tp, struct xfs_inode *ip,
-		const char *target_path, int pathlen, xfs_fsblock_t fs_blocks,
-		uint resblks);
+int __xfs_symlink_write_target(struct xfs_trans *tp, struct xfs_inode *ip,
+		xfs_ino_t owner, const char *target_path, int pathlen,
+		xfs_fsblock_t fs_blocks, uint resblks);
+
+static inline int
+xfs_symlink_write_target(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	const char		*target_path,
+	int			pathlen,
+	xfs_fsblock_t		fs_blocks,
+	uint			resblks)
+{
+	return __xfs_symlink_write_target(tp, ip, ip->i_ino, target_path,
+			pathlen, fs_blocks, resblks);
+}
 int xfs_symlink_remote_truncate(struct xfs_trans *tp, struct xfs_inode *ip);
 
 #endif /* __XFS_SYMLINK_REMOTE_H */

[PATCH 1/1] xfs: map xfile pages directly into xfs_buf

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Map the xfile pages directly into xfs_buf to reduce memory overhead.
It's silly to use memory to stage changes to shmem pages for ephemeral
btrees that don't care about transactionality.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_btree_mem.h  |    6 ++++++
 libxfs/xfs_rmap_btree.c |    1 +
 2 files changed, 7 insertions(+)


diff --git a/libxfs/xfs_btree_mem.h b/libxfs/xfs_btree_mem.h
index 1f961f3f554..cfb30cb1aab 100644
--- a/libxfs/xfs_btree_mem.h
+++ b/libxfs/xfs_btree_mem.h
@@ -17,8 +17,14 @@ struct xfbtree_config {
 
 	/* Owner of this btree. */
 	unsigned long long		owner;
+
+	/* XFBTREE_* flags */
+	unsigned int			flags;
 };
 
+/* buffers should be directly mapped from memory */
+#define XFBTREE_DIRECT_MAP		(1U << 0)
+
 #ifdef CONFIG_XFS_BTREE_IN_XFILE
 unsigned int xfs_btree_mem_head_nlevels(struct xfs_buf *head_bp);
 
diff --git a/libxfs/xfs_rmap_btree.c b/libxfs/xfs_rmap_btree.c
index a378bd5daf8..7342623ed5e 100644
--- a/libxfs/xfs_rmap_btree.c
+++ b/libxfs/xfs_rmap_btree.c
@@ -670,6 +670,7 @@ xfs_rmapbt_mem_create(
 		.btree_ops	= &xfs_rmapbt_mem_ops,
 		.target		= target,
 		.owner		= agno,
+		.flags		= XFBTREE_DIRECT_MAP,
 	};
 
 	return xfbtree_create(mp, &cfg, xfbtreep);

[PATCH 1/4] xfs: check unused nlink fields in the ondisk inode

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

v2/v3 inodes use di_nlink and not di_onlink; and v1 inodes use di_onlink
and not di_nlink.  Whichever field is not in use, make sure its contents
are zero, and teach xfs_scrub to fix that if it is.

This clears a bunch of missing scrub failure errors in xfs/385 for
core.onlink.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/xfs_inode_buf.c |    8 ++++++++
 1 file changed, 8 insertions(+)


diff --git a/libxfs/xfs_inode_buf.c b/libxfs/xfs_inode_buf.c
index 82cf64db938..aee581d53c8 100644
--- a/libxfs/xfs_inode_buf.c
+++ b/libxfs/xfs_inode_buf.c
@@ -488,6 +488,14 @@ xfs_dinode_verify(
 			return __this_address;
 	}
 
+	if (dip->di_version > 1) {
+		if (dip->di_onlink)
+			return __this_address;
+	} else {
+		if (dip->di_nlink)
+			return __this_address;
+	}
+
 	/* don't allow invalid i_size */
 	di_size = be64_to_cpu(dip->di_size);
 	if (di_size & (1ULL << 63))

[PATCH 2/4] xfs: try to avoid allocating from sick inode clusters

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

I noticed that xfs/413 and xfs/375 occasionally failed while fuzzing
core.mode of an inode.  The root cause of these problems is that the
field we fuzzed (core.mode or core.magic, typically) causes the entire
inode cluster buffer verification to fail, which affects several inodes
at once.  The repair process tries to create either a /lost+found or a
temporary repair file, but regrettably it picks the same inode cluster
that we just corrupted, with the result that repair triggers the demise
of the filesystem.

Try avoid this by making the inode allocation path detect when the perag
health status indicates that someone has found bad inode cluster
buffers, and try to read the inode cluster buffer.  If the cluster
buffer fails the verifiers, try another AG.  This isn't foolproof and
can result in premature ENOSPC, but that might be better than shutting
down.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/util.c       |    6 ++++++
 libxfs/xfs_ialloc.c |   40 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 46 insertions(+)


diff --git a/libxfs/util.c b/libxfs/util.c
index 097362d488d..c1ddaf92c8a 100644
--- a/libxfs/util.c
+++ b/libxfs/util.c
@@ -732,6 +732,12 @@ void xfs_fs_mark_sick(struct xfs_mount *mp, unsigned int mask) { }
 void xfs_agno_mark_sick(struct xfs_mount *mp, xfs_agnumber_t agno,
 		unsigned int mask) { }
 void xfs_ag_mark_sick(struct xfs_perag *pag, unsigned int mask) { }
+void xfs_ag_measure_sickness(struct xfs_perag *pag, unsigned int *sick,
+		unsigned int *checked)
+{
+	*sick = 0;
+	*checked = 0;
+}
 void xfs_bmap_mark_sick(struct xfs_inode *ip, int whichfork) { }
 void xfs_btree_mark_sick(struct xfs_btree_cur *cur) { }
 void xfs_dirattr_mark_sick(struct xfs_inode *ip, int whichfork) { }
diff --git a/libxfs/xfs_ialloc.c b/libxfs/xfs_ialloc.c
index 21577a50f65..46d4515baba 100644
--- a/libxfs/xfs_ialloc.c
+++ b/libxfs/xfs_ialloc.c
@@ -1007,6 +1007,33 @@ xfs_inobt_first_free_inode(
 	return xfs_lowbit64(realfree);
 }
 
+/*
+ * If this AG has corrupt inodes, check if allocating this inode would fail
+ * with corruption errors.  Returns 0 if we're clear, or EAGAIN to try again
+ * somewhere else.
+ */
+static int
+xfs_dialloc_check_ino(
+	struct xfs_perag	*pag,
+	struct xfs_trans	*tp,
+	xfs_ino_t		ino)
+{
+	struct xfs_imap		imap;
+	struct xfs_buf		*bp;
+	int			error;
+
+	error = xfs_imap(pag, tp, ino, &imap, 0);
+	if (error)
+		return -EAGAIN;
+
+	error = xfs_imap_to_bp(pag->pag_mount, tp, &imap, &bp);
+	if (error)
+		return -EAGAIN;
+
+	xfs_trans_brelse(tp, bp);
+	return 0;
+}
+
 /*
  * Allocate an inode using the inobt-only algorithm.
  */
@@ -1259,6 +1286,13 @@ xfs_dialloc_ag_inobt(
 	ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) %
 				   XFS_INODES_PER_CHUNK) == 0);
 	ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, rec.ir_startino + offset);
+
+	if (xfs_ag_has_sickness(pag, XFS_SICK_AG_INODES)) {
+		error = xfs_dialloc_check_ino(pag, tp, ino);
+		if (error)
+			goto error0;
+	}
+
 	rec.ir_free &= ~XFS_INOBT_MASK(offset);
 	rec.ir_freecount--;
 	error = xfs_inobt_update(cur, &rec);
@@ -1534,6 +1568,12 @@ xfs_dialloc_ag(
 				   XFS_INODES_PER_CHUNK) == 0);
 	ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, rec.ir_startino + offset);
 
+	if (xfs_ag_has_sickness(pag, XFS_SICK_AG_INODES)) {
+		error = xfs_dialloc_check_ino(pag, tp, ino);
+		if (error)
+			goto error_cur;
+	}
+
 	/*
 	 * Modify or remove the finobt record.
 	 */

[PATCH 3/4] libxfs: port the bumplink function from the kernel

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Port the xfs_bumplink function from the kernel and use it to replace raw
calls to inc_nlink.  The next patch will need this common function to
prevent integer overflows in the link count.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 include/xfs_inode.h |    2 ++
 libxfs/util.c       |   17 +++++++++++++++++
 mkfs/proto.c        |    4 ++--
 repair/phase6.c     |   10 +++++-----
 4 files changed, 26 insertions(+), 7 deletions(-)


diff --git a/include/xfs_inode.h b/include/xfs_inode.h
index 302df4c6f7e..47959314811 100644
--- a/include/xfs_inode.h
+++ b/include/xfs_inode.h
@@ -348,6 +348,8 @@ extern void	libxfs_trans_ichgtime(struct xfs_trans *,
 				struct xfs_inode *, int);
 extern int	libxfs_iflush_int (struct xfs_inode *, struct xfs_buf *);
 
+void libxfs_bumplink(struct xfs_trans *tp, struct xfs_inode *ip);
+
 /* Inode Cache Interfaces */
 extern int	libxfs_iget(struct xfs_mount *, struct xfs_trans *, xfs_ino_t,
 				uint, struct xfs_inode **);
diff --git a/libxfs/util.c b/libxfs/util.c
index c1ddaf92c8a..11978529ed6 100644
--- a/libxfs/util.c
+++ b/libxfs/util.c
@@ -240,6 +240,23 @@ xfs_inode_propagate_flags(
 	ip->i_diflags |= di_flags;
 }
 
+/*
+ * Increment the link count on an inode & log the change.
+ */
+void
+libxfs_bumplink(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip)
+{
+	struct inode		*inode = VFS_I(ip);
+
+	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
+
+	inc_nlink(inode);
+
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+}
+
 /*
  * Initialise a newly allocated inode and return the in-core inode to the
  * caller locked exclusively.
diff --git a/mkfs/proto.c b/mkfs/proto.c
index 0f2facbc32e..457899ac178 100644
--- a/mkfs/proto.c
+++ b/mkfs/proto.c
@@ -590,7 +590,7 @@ parseproto(
 				&creds, fsxp, &ip);
 		if (error)
 			fail(_("Inode allocation failed"), error);
-		inc_nlink(VFS_I(ip));		/* account for . */
+		libxfs_bumplink(tp, ip);		/* account for . */
 		if (!pip) {
 			pip = ip;
 			mp->m_sb.sb_rootino = ip->i_ino;
@@ -600,7 +600,7 @@ parseproto(
 			libxfs_trans_ijoin(tp, pip, 0);
 			xname.type = XFS_DIR3_FT_DIR;
 			newdirent(mp, tp, pip, &xname, ip->i_ino);
-			inc_nlink(VFS_I(pip));
+			libxfs_bumplink(tp, pip);
 			libxfs_trans_log_inode(tp, pip, XFS_ILOG_CORE);
 		}
 		newdirectory(mp, tp, ip, pip);
diff --git a/repair/phase6.c b/repair/phase6.c
index ac037cf80ad..75391378291 100644
--- a/repair/phase6.c
+++ b/repair/phase6.c
@@ -944,7 +944,7 @@ mk_orphanage(xfs_mount_t *mp)
 		do_error(_("%s inode allocation failed %d\n"),
 			ORPHANAGE, error);
 	}
-	inc_nlink(VFS_I(ip));		/* account for . */
+	libxfs_bumplink(tp, ip);		/* account for . */
 	ino = ip->i_ino;
 
 	irec = find_inode_rec(mp,
@@ -996,7 +996,7 @@ mk_orphanage(xfs_mount_t *mp)
 	 * for .. in the new directory, and update the irec copy of the
 	 * on-disk nlink so we don't fail the link count check later.
 	 */
-	inc_nlink(VFS_I(pip));
+	libxfs_bumplink(tp, pip);
 	irec = find_inode_rec(mp, XFS_INO_TO_AGNO(mp, mp->m_sb.sb_rootino),
 				  XFS_INO_TO_AGINO(mp, mp->m_sb.sb_rootino));
 	add_inode_ref(irec, 0);
@@ -1090,7 +1090,7 @@ mv_orphanage(
 			if (irec)
 				add_inode_ref(irec, ino_offset);
 			else
-				inc_nlink(VFS_I(orphanage_ip));
+				libxfs_bumplink(tp, orphanage_ip);
 			libxfs_trans_log_inode(tp, orphanage_ip, XFS_ILOG_CORE);
 
 			err = -libxfs_dir_createname(tp, ino_p, &xfs_name_dotdot,
@@ -1099,7 +1099,7 @@ mv_orphanage(
 				do_error(
 	_("creation of .. entry failed (%d)\n"), err);
 
-			inc_nlink(VFS_I(ino_p));
+			libxfs_bumplink(tp, ino_p);
 			libxfs_trans_log_inode(tp, ino_p, XFS_ILOG_CORE);
 			err = -libxfs_trans_commit(tp);
 			if (err)
@@ -1124,7 +1124,7 @@ mv_orphanage(
 			if (irec)
 				add_inode_ref(irec, ino_offset);
 			else
-				inc_nlink(VFS_I(orphanage_ip));
+				libxfs_bumplink(tp, orphanage_ip);
 			libxfs_trans_log_inode(tp, orphanage_ip, XFS_ILOG_CORE);
 
 			/*

[PATCH 4/4] xfs: pin inodes that would otherwise overflow link count

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

The VFS inc_nlink function does not explicitly check for integer
overflows in the i_nlink field.  Instead, it checks the link count
against s_max_links in the vfs_{link,create,rename} functions.  XFS
sets the maximum link count to 2.1 billion, so integer overflows should
not be a problem.

However.  It's possible that online repair could find that a file has
more than four billion links, particularly if the link count got
corrupted while creating hardlinks to the file.  The di_nlinkv2 field is
not large enough to store a value larger than 2^32, so we ought to
define a magic pin value of ~0U which means that the inode never gets
deleted.  This will prevent a UAF error if the repair finds this
situation and users begin deleting links to the file.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libxfs/util.c       |    3 ++-
 libxfs/xfs_format.h |    6 ++++++
 repair/incore_ino.c |    3 ++-
 3 files changed, 10 insertions(+), 2 deletions(-)


diff --git a/libxfs/util.c b/libxfs/util.c
index 11978529ed6..03191ebcd08 100644
--- a/libxfs/util.c
+++ b/libxfs/util.c
@@ -252,7 +252,8 @@ libxfs_bumplink(
 
 	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
 
-	inc_nlink(inode);
+	if (inode->i_nlink != XFS_NLINK_PINNED)
+		inc_nlink(inode);
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 }
diff --git a/libxfs/xfs_format.h b/libxfs/xfs_format.h
index 7861539ab8b..ec25010b577 100644
--- a/libxfs/xfs_format.h
+++ b/libxfs/xfs_format.h
@@ -912,6 +912,12 @@ static inline uint xfs_dinode_size(int version)
  */
 #define	XFS_MAXLINK		((1U << 31) - 1U)
 
+/*
+ * Any file that hits the maximum ondisk link count should be pinned to avoid
+ * a use-after-free situation.
+ */
+#define	XFS_NLINK_PINNED	(~0U)
+
 /*
  * Values for di_format
  *
diff --git a/repair/incore_ino.c b/repair/incore_ino.c
index 0dd7a2f060f..b0b41a2cc5c 100644
--- a/repair/incore_ino.c
+++ b/repair/incore_ino.c
@@ -108,7 +108,8 @@ void add_inode_ref(struct ino_tree_node *irec, int ino_offset)
 		nlink_grow_16_to_32(irec);
 		/*FALLTHRU*/
 	case sizeof(uint32_t):
-		irec->ino_un.ex_data->counted_nlinks.un32[ino_offset]++;
+		if (irec->ino_un.ex_data->counted_nlinks.un32[ino_offset] != XFS_NLINK_PINNED)
+			irec->ino_un.ex_data->counted_nlinks.un32[ino_offset]++;
 		break;
 	default:
 		ASSERT(0);

[PATCH 1/7] xfs_scrub: flush stdout after printing to it

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Make sure we flush stdout after printf'ing to it, especially before we
start any operation that could take a while to complete.  Most of scrub
already does this, but we missed a couple of spots.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/xfs_scrub.c |    2 ++
 1 file changed, 2 insertions(+)


diff --git a/scrub/xfs_scrub.c b/scrub/xfs_scrub.c
index a1b67544391..752180d646b 100644
--- a/scrub/xfs_scrub.c
+++ b/scrub/xfs_scrub.c
@@ -535,6 +535,7 @@ _("%s: repairs made: %llu.\n"),
 		fprintf(stdout,
 _("%s: optimizations made: %llu.\n"),
 				ctx->mntpoint, ctx->preens);
+	fflush(stdout);
 }
 
 static void
@@ -620,6 +621,7 @@ main(
 	int			error;
 
 	fprintf(stdout, "EXPERIMENTAL xfs_scrub program in use! Use at your own risk!\n");
+	fflush(stdout);
 
 	progname = basename(argv[0]);
 	setlocale(LC_ALL, "");

[PATCH 2/7] xfs_scrub: don't report media errors for space with unknowable owner

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

On filesystems that don't have the reverse mapping feature enabled, the
GETFSMAP call cannot tell us much about the owner of a space extent --
we're limited to static fs metadata, free space, or "unknown".  In this
case, nothing is corrupt, so str_corrupt is not an appropriate logging
function.  Relax this to str_info so that the user sees a notice that
media errors have been found so that the user knows something bad
happened even if the directory tree walker cannot find the file owning
the space where the media error was found.

Filesystems with rmap enabled are never supposed to return OWN_UNKNOWN
from a GETFSMAP report, so continue to report that as a corruption.
This fixes a regression in xfs/556.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase6.c |   13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)


diff --git a/scrub/phase6.c b/scrub/phase6.c
index 33c3c8bde3c..99a32bc7962 100644
--- a/scrub/phase6.c
+++ b/scrub/phase6.c
@@ -397,7 +397,18 @@ report_ioerr_fsmap(
 		snprintf(buf, DESCR_BUFSZ, _("disk offset %"PRIu64),
 				(uint64_t)map->fmr_physical + err_off);
 		type = decode_special_owner(map->fmr_owner);
-		str_corrupt(ctx, buf, _("media error in %s."), type);
+		/*
+		 * On filesystems that don't store reverse mappings, the
+		 * GETFSMAP call returns OWNER_UNKNOWN for allocated space.
+		 * We'll have to let the directory tree walker find the file
+		 * that lost data.
+		 */
+		if (!(ctx->mnt.fsgeom.flags & XFS_FSOP_GEOM_FLAGS_RMAPBT) &&
+		    map->fmr_owner == XFS_FMR_OWN_UNKNOWN) {
+			str_info(ctx, buf, _("media error detected."));
+		} else {
+			str_corrupt(ctx, buf, _("media error in %s."), type);
+		}
 	}
 
 	/* Report extent maps */

[PATCH 3/7] xfs_scrub: remove ALP_* flags namespace

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

In preparation to move all the repair code to repair.[ch], remove the
ALP_* flags namespace since it mostly overlaps with XRM_*.  Rename the
clunky "COMPLAIN_IF_UNFIXED" flag to "FINAL_WARNING", because that's
what it really means.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase3.c |    2 +-
 scrub/phase4.c |    2 +-
 scrub/phase5.c |    2 +-
 scrub/phase7.c |    2 +-
 scrub/repair.c |    4 ++--
 scrub/repair.h |   16 ++++++++++++----
 scrub/scrub.c  |   10 +++++-----
 scrub/scrub.h  |   10 ----------
 8 files changed, 23 insertions(+), 25 deletions(-)


diff --git a/scrub/phase3.c b/scrub/phase3.c
index 4235c228c0e..9a26b92036c 100644
--- a/scrub/phase3.c
+++ b/scrub/phase3.c
@@ -88,7 +88,7 @@ try_inode_repair(
 		return 0;
 
 	ret = action_list_process(ictx->ctx, fd, alist,
-			ALP_REPAIR_ONLY | ALP_NOPROGRESS);
+			XRM_REPAIR_ONLY | XRM_NOPROGRESS);
 	if (ret)
 		return ret;
 
diff --git a/scrub/phase4.c b/scrub/phase4.c
index 8807f147aed..d42e67637d8 100644
--- a/scrub/phase4.c
+++ b/scrub/phase4.c
@@ -54,7 +54,7 @@ repair_ag(
 	} while (unfixed > 0);
 
 	/* Try once more, but this time complain if we can't fix things. */
-	flags |= ALP_COMPLAIN_IF_UNFIXED;
+	flags |= XRM_FINAL_WARNING;
 	ret = action_list_process(ctx, -1, alist, flags);
 	if (ret)
 		*aborted = true;
diff --git a/scrub/phase5.c b/scrub/phase5.c
index b4c635d3452..940e434c3cd 100644
--- a/scrub/phase5.c
+++ b/scrub/phase5.c
@@ -422,7 +422,7 @@ fs_scan_worker(
 	}
 
 	ret = action_list_process(ctx, ctx->mnt.fd, &item->alist,
-			ALP_COMPLAIN_IF_UNFIXED | ALP_NOPROGRESS);
+			XRM_FINAL_WARNING | XRM_NOPROGRESS);
 	if (ret) {
 		str_liberror(ctx, ret, _("repairing fs scan metadata"));
 		*item->abortedp = true;
diff --git a/scrub/phase7.c b/scrub/phase7.c
index 93a074f1151..820a68f99a4 100644
--- a/scrub/phase7.c
+++ b/scrub/phase7.c
@@ -122,7 +122,7 @@ phase7_func(
 	if (error)
 		return error;
 	error = action_list_process(ctx, -1, &alist,
-			ALP_COMPLAIN_IF_UNFIXED | ALP_NOPROGRESS);
+			XRM_FINAL_WARNING | XRM_NOPROGRESS);
 	if (error)
 		return error;
 
diff --git a/scrub/repair.c b/scrub/repair.c
index 9ade805e1b6..61d62ab6b49 100644
--- a/scrub/repair.c
+++ b/scrub/repair.c
@@ -274,7 +274,7 @@ action_list_process(
 		fix = xfs_repair_metadata(ctx, xfdp, aitem, repair_flags);
 		switch (fix) {
 		case CHECK_DONE:
-			if (!(repair_flags & ALP_NOPROGRESS))
+			if (!(repair_flags & XRM_NOPROGRESS))
 				progress_add(1);
 			alist->nr--;
 			list_del(&aitem->list);
@@ -316,7 +316,7 @@ action_list_process_or_defer(
 	int				ret;
 
 	ret = action_list_process(ctx, -1, alist,
-			ALP_REPAIR_ONLY | ALP_NOPROGRESS);
+			XRM_REPAIR_ONLY | XRM_NOPROGRESS);
 	if (ret)
 		return ret;
 
diff --git a/scrub/repair.h b/scrub/repair.h
index aa3ea13615f..6b6f64691a3 100644
--- a/scrub/repair.h
+++ b/scrub/repair.h
@@ -32,10 +32,18 @@ void action_list_find_mustfix(struct action_list *actions,
 		unsigned long long *broken_primaries,
 		unsigned long long *broken_secondaries);
 
-/* Passed through to xfs_repair_metadata() */
-#define ALP_REPAIR_ONLY		(XRM_REPAIR_ONLY)
-#define ALP_COMPLAIN_IF_UNFIXED	(XRM_COMPLAIN_IF_UNFIXED)
-#define ALP_NOPROGRESS		(1U << 31)
+/*
+ * Only ask the kernel to repair this object if the kernel directly told us it
+ * was corrupt.  Objects that are only flagged as having cross-referencing
+ * errors or flagged as eligible for optimization are left for later.
+ */
+#define XRM_REPAIR_ONLY		(1U << 0)
+
+/* This is the last repair attempt; complain if still broken even after fix. */
+#define XRM_FINAL_WARNING	(1U << 1)
+
+/* Don't call progress_add after repairing an item. */
+#define XRM_NOPROGRESS		(1U << 2)
 
 int action_list_process(struct scrub_ctx *ctx, int fd,
 		struct action_list *alist, unsigned int repair_flags);
diff --git a/scrub/scrub.c b/scrub/scrub.c
index 7cb94af3d15..f4b152a1c9c 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -743,7 +743,7 @@ _("Filesystem is shut down, aborting."));
 		 * could fix this, it's at least worth trying the scan
 		 * again to see if another repair fixed it.
 		 */
-		if (!(repair_flags & XRM_COMPLAIN_IF_UNFIXED))
+		if (!(repair_flags & XRM_FINAL_WARNING))
 			return CHECK_RETRY;
 		fallthrough;
 	case EINVAL:
@@ -773,13 +773,13 @@ _("Read-only filesystem; cannot make changes."));
 		 * to requeue the repair for later and don't say a
 		 * thing.  Otherwise, print error and bail out.
 		 */
-		if (!(repair_flags & XRM_COMPLAIN_IF_UNFIXED))
+		if (!(repair_flags & XRM_FINAL_WARNING))
 			return CHECK_RETRY;
 		str_liberror(ctx, error, descr_render(&dsc));
 		return CHECK_DONE;
 	}
 
-	if (repair_flags & XRM_COMPLAIN_IF_UNFIXED)
+	if (repair_flags & XRM_FINAL_WARNING)
 		scrub_warn_incomplete_scrub(ctx, &dsc, &meta);
 	if (needs_repair(&meta)) {
 		/*
@@ -787,7 +787,7 @@ _("Read-only filesystem; cannot make changes."));
 		 * just requeue this and try again later.  Otherwise we
 		 * log the error loudly and don't try again.
 		 */
-		if (!(repair_flags & XRM_COMPLAIN_IF_UNFIXED))
+		if (!(repair_flags & XRM_FINAL_WARNING))
 			return CHECK_RETRY;
 		str_corrupt(ctx, descr_render(&dsc),
 _("Repair unsuccessful; offline repair required."));
@@ -799,7 +799,7 @@ _("Repair unsuccessful; offline repair required."));
 		 * caller to run xfs_repair; otherwise, we'll keep trying to
 		 * reverify the cross-referencing as repairs progress.
 		 */
-		if (repair_flags & XRM_COMPLAIN_IF_UNFIXED) {
+		if (repair_flags & XRM_FINAL_WARNING) {
 			str_info(ctx, descr_render(&dsc),
  _("Seems correct but cross-referencing failed; offline repair recommended."));
 		} else {
diff --git a/scrub/scrub.h b/scrub/scrub.h
index cb33ddb46f3..5359548b06f 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -54,16 +54,6 @@ struct action_item {
 	__u32			agno;
 };
 
-/*
- * Only ask the kernel to repair this object if the kernel directly told us it
- * was corrupt.  Objects that are only flagged as having cross-referencing
- * errors or flagged as eligible for optimization are left for later.
- */
-#define XRM_REPAIR_ONLY		(1U << 0)
-
-/* Complain if still broken even after fix. */
-#define XRM_COMPLAIN_IF_UNFIXED	(1U << 1)
-
 enum check_outcome xfs_repair_metadata(struct scrub_ctx *ctx,
 		struct xfs_fd *xfdp, struct action_item *aitem,
 		unsigned int repair_flags);

[PATCH 4/7] xfs_scrub: move repair functions to repair.c

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Move all the repair functions to repair.c.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase1.c        |    2 
 scrub/repair.c        |  169 +++++++++++++++++++++++++++++++++++++++++
 scrub/scrub.c         |  204 +------------------------------------------------
 scrub/scrub.h         |    6 -
 scrub/scrub_private.h |   55 +++++++++++++
 5 files changed, 230 insertions(+), 206 deletions(-)
 create mode 100644 scrub/scrub_private.h


diff --git a/scrub/phase1.c b/scrub/phase1.c
index 96138e03e71..81b0918a1c8 100644
--- a/scrub/phase1.c
+++ b/scrub/phase1.c
@@ -210,7 +210,7 @@ _("Kernel metadata scrubbing facility is not available."));
 	}
 
 	/* Do we need kernel-assisted metadata repair? */
-	if (ctx->mode != SCRUB_MODE_DRY_RUN && !xfs_can_repair(ctx)) {
+	if (ctx->mode != SCRUB_MODE_DRY_RUN && !can_repair(ctx)) {
 		str_error(ctx, ctx->mntpoint,
 _("Kernel metadata repair facility is not available.  Use -n to scrub."));
 		return ECANCELED;
diff --git a/scrub/repair.c b/scrub/repair.c
index 61d62ab6b49..54bd09575c0 100644
--- a/scrub/repair.c
+++ b/scrub/repair.c
@@ -10,11 +10,180 @@
 #include <sys/statvfs.h>
 #include "list.h"
 #include "libfrog/paths.h"
+#include "libfrog/fsgeom.h"
+#include "libfrog/scrub.h"
 #include "xfs_scrub.h"
 #include "common.h"
 #include "scrub.h"
 #include "progress.h"
 #include "repair.h"
+#include "descr.h"
+#include "scrub_private.h"
+
+/* General repair routines. */
+
+/* Repair some metadata. */
+static enum check_outcome
+xfs_repair_metadata(
+	struct scrub_ctx		*ctx,
+	struct xfs_fd			*xfdp,
+	struct action_item		*aitem,
+	unsigned int			repair_flags)
+{
+	struct xfs_scrub_metadata	meta = { 0 };
+	struct xfs_scrub_metadata	oldm;
+	DEFINE_DESCR(dsc, ctx, format_scrub_descr);
+	int				error;
+
+	assert(aitem->type < XFS_SCRUB_TYPE_NR);
+	assert(!debug_tweak_on("XFS_SCRUB_NO_KERNEL"));
+	meta.sm_type = aitem->type;
+	meta.sm_flags = aitem->flags | XFS_SCRUB_IFLAG_REPAIR;
+	if (use_force_rebuild)
+		meta.sm_flags |= XFS_SCRUB_IFLAG_FORCE_REBUILD;
+	switch (xfrog_scrubbers[aitem->type].group) {
+	case XFROG_SCRUB_GROUP_AGHEADER:
+	case XFROG_SCRUB_GROUP_PERAG:
+		meta.sm_agno = aitem->agno;
+		break;
+	case XFROG_SCRUB_GROUP_INODE:
+		meta.sm_ino = aitem->ino;
+		meta.sm_gen = aitem->gen;
+		break;
+	default:
+		break;
+	}
+
+	if (!is_corrupt(&meta) && (repair_flags & XRM_REPAIR_ONLY))
+		return CHECK_RETRY;
+
+	memcpy(&oldm, &meta, sizeof(oldm));
+	descr_set(&dsc, &oldm);
+
+	if (needs_repair(&meta))
+		str_info(ctx, descr_render(&dsc), _("Attempting repair."));
+	else if (debug || verbose)
+		str_info(ctx, descr_render(&dsc),
+				_("Attempting optimization."));
+
+	error = -xfrog_scrub_metadata(xfdp, &meta);
+	switch (error) {
+	case 0:
+		/* No operational errors encountered. */
+		break;
+	case EDEADLOCK:
+	case EBUSY:
+		/* Filesystem is busy, try again later. */
+		if (debug || verbose)
+			str_info(ctx, descr_render(&dsc),
+_("Filesystem is busy, deferring repair."));
+		return CHECK_RETRY;
+	case ESHUTDOWN:
+		/* Filesystem is already shut down, abort. */
+		str_error(ctx, descr_render(&dsc),
+_("Filesystem is shut down, aborting."));
+		return CHECK_ABORT;
+	case ENOTTY:
+	case EOPNOTSUPP:
+		/*
+		 * If the kernel cannot perform the optimization that we
+		 * requested; or we forced a repair but the kernel doesn't know
+		 * how to perform the repair, don't requeue the request.  Mark
+		 * it done and move on.
+		 */
+		if (is_unoptimized(&oldm) ||
+		    debug_tweak_on("XFS_SCRUB_FORCE_REPAIR"))
+			return CHECK_DONE;
+		/*
+		 * If we're in no-complain mode, requeue the check for
+		 * later.  It's possible that an error in another
+		 * component caused us to flag an error in this
+		 * component.  Even if the kernel didn't think it
+		 * could fix this, it's at least worth trying the scan
+		 * again to see if another repair fixed it.
+		 */
+		if (!(repair_flags & XRM_FINAL_WARNING))
+			return CHECK_RETRY;
+		fallthrough;
+	case EINVAL:
+		/* Kernel doesn't know how to repair this? */
+		str_corrupt(ctx, descr_render(&dsc),
+_("Don't know how to fix; offline repair required."));
+		return CHECK_DONE;
+	case EROFS:
+		/* Read-only filesystem, can't fix. */
+		if (verbose || debug || needs_repair(&oldm))
+			str_error(ctx, descr_render(&dsc),
+_("Read-only filesystem; cannot make changes."));
+		return CHECK_ABORT;
+	case ENOENT:
+		/* Metadata not present, just skip it. */
+		return CHECK_DONE;
+	case ENOMEM:
+	case ENOSPC:
+		/* Don't care if preen fails due to low resources. */
+		if (is_unoptimized(&oldm) && !needs_repair(&oldm))
+			return CHECK_DONE;
+		fallthrough;
+	default:
+		/*
+		 * Operational error.  If the caller doesn't want us
+		 * to complain about repair failures, tell the caller
+		 * to requeue the repair for later and don't say a
+		 * thing.  Otherwise, print error and bail out.
+		 */
+		if (!(repair_flags & XRM_FINAL_WARNING))
+			return CHECK_RETRY;
+		str_liberror(ctx, error, descr_render(&dsc));
+		return CHECK_DONE;
+	}
+
+	if (repair_flags & XRM_FINAL_WARNING)
+		scrub_warn_incomplete_scrub(ctx, &dsc, &meta);
+	if (needs_repair(&meta)) {
+		/*
+		 * Still broken; if we've been told not to complain then we
+		 * just requeue this and try again later.  Otherwise we
+		 * log the error loudly and don't try again.
+		 */
+		if (!(repair_flags & XRM_FINAL_WARNING))
+			return CHECK_RETRY;
+		str_corrupt(ctx, descr_render(&dsc),
+_("Repair unsuccessful; offline repair required."));
+	} else if (xref_failed(&meta)) {
+		/*
+		 * This metadata object itself looks ok, but we still noticed
+		 * inconsistencies when comparing it with the other filesystem
+		 * metadata.  If we're in "final warning" mode, advise the
+		 * caller to run xfs_repair; otherwise, we'll keep trying to
+		 * reverify the cross-referencing as repairs progress.
+		 */
+		if (repair_flags & XRM_FINAL_WARNING) {
+			str_info(ctx, descr_render(&dsc),
+ _("Seems correct but cross-referencing failed; offline repair recommended."));
+		} else {
+			if (verbose)
+				str_info(ctx, descr_render(&dsc),
+ _("Seems correct but cross-referencing failed; will keep checking."));
+			return CHECK_RETRY;
+		}
+	} else {
+		/* Clean operation, no corruption detected. */
+		if (is_corrupt(&oldm))
+			record_repair(ctx, descr_render(&dsc),
+ _("Repairs successful."));
+		else if (xref_disagrees(&oldm))
+			record_repair(ctx, descr_render(&dsc),
+ _("Repairs successful after discrepancy in cross-referencing."));
+		else if (xref_failed(&oldm))
+			record_repair(ctx, descr_render(&dsc),
+ _("Repairs successful after cross-referencing failure."));
+		else
+			record_preen(ctx, descr_render(&dsc),
+ _("Optimization successful."));
+	}
+	return CHECK_DONE;
+}
 
 /*
  * Prioritize action items in order of how long we can wait.
diff --git a/scrub/scrub.c b/scrub/scrub.c
index f4b152a1c9c..59583913031 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -20,11 +20,12 @@
 #include "scrub.h"
 #include "repair.h"
 #include "descr.h"
+#include "scrub_private.h"
 
 /* Online scrub and repair wrappers. */
 
 /* Format a scrub description. */
-static int
+int
 format_scrub_descr(
 	struct scrub_ctx		*ctx,
 	char				*buf,
@@ -52,46 +53,8 @@ format_scrub_descr(
 	return -1;
 }
 
-/* Predicates for scrub flag state. */
-
-static inline bool is_corrupt(struct xfs_scrub_metadata *sm)
-{
-	return sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT;
-}
-
-static inline bool is_unoptimized(struct xfs_scrub_metadata *sm)
-{
-	return sm->sm_flags & XFS_SCRUB_OFLAG_PREEN;
-}
-
-static inline bool xref_failed(struct xfs_scrub_metadata *sm)
-{
-	return sm->sm_flags & XFS_SCRUB_OFLAG_XFAIL;
-}
-
-static inline bool xref_disagrees(struct xfs_scrub_metadata *sm)
-{
-	return sm->sm_flags & XFS_SCRUB_OFLAG_XCORRUPT;
-}
-
-static inline bool is_incomplete(struct xfs_scrub_metadata *sm)
-{
-	return sm->sm_flags & XFS_SCRUB_OFLAG_INCOMPLETE;
-}
-
-static inline bool is_suspicious(struct xfs_scrub_metadata *sm)
-{
-	return sm->sm_flags & XFS_SCRUB_OFLAG_WARNING;
-}
-
-/* Should we fix it? */
-static inline bool needs_repair(struct xfs_scrub_metadata *sm)
-{
-	return is_corrupt(sm) || xref_disagrees(sm);
-}
-
 /* Warn about strange circumstances after scrub. */
-static inline void
+void
 scrub_warn_incomplete_scrub(
 	struct scrub_ctx		*ctx,
 	struct descr			*dsc,
@@ -647,7 +610,7 @@ can_scrub_parent(
 }
 
 bool
-xfs_can_repair(
+can_repair(
 	struct scrub_ctx	*ctx)
 {
 	return __scrub_test(ctx, XFS_SCRUB_TYPE_PROBE, XFS_SCRUB_IFLAG_REPAIR);
@@ -660,162 +623,3 @@ can_force_rebuild(
 	return __scrub_test(ctx, XFS_SCRUB_TYPE_PROBE,
 			XFS_SCRUB_IFLAG_REPAIR | XFS_SCRUB_IFLAG_FORCE_REBUILD);
 }
-
-/* General repair routines. */
-
-/* Repair some metadata. */
-enum check_outcome
-xfs_repair_metadata(
-	struct scrub_ctx		*ctx,
-	struct xfs_fd			*xfdp,
-	struct action_item		*aitem,
-	unsigned int			repair_flags)
-{
-	struct xfs_scrub_metadata	meta = { 0 };
-	struct xfs_scrub_metadata	oldm;
-	DEFINE_DESCR(dsc, ctx, format_scrub_descr);
-	int				error;
-
-	assert(aitem->type < XFS_SCRUB_TYPE_NR);
-	assert(!debug_tweak_on("XFS_SCRUB_NO_KERNEL"));
-	meta.sm_type = aitem->type;
-	meta.sm_flags = aitem->flags | XFS_SCRUB_IFLAG_REPAIR;
-	if (use_force_rebuild)
-		meta.sm_flags |= XFS_SCRUB_IFLAG_FORCE_REBUILD;
-	switch (xfrog_scrubbers[aitem->type].group) {
-	case XFROG_SCRUB_GROUP_AGHEADER:
-	case XFROG_SCRUB_GROUP_PERAG:
-		meta.sm_agno = aitem->agno;
-		break;
-	case XFROG_SCRUB_GROUP_INODE:
-		meta.sm_ino = aitem->ino;
-		meta.sm_gen = aitem->gen;
-		break;
-	default:
-		break;
-	}
-
-	if (!is_corrupt(&meta) && (repair_flags & XRM_REPAIR_ONLY))
-		return CHECK_RETRY;
-
-	memcpy(&oldm, &meta, sizeof(oldm));
-	descr_set(&dsc, &oldm);
-
-	if (needs_repair(&meta))
-		str_info(ctx, descr_render(&dsc), _("Attempting repair."));
-	else if (debug || verbose)
-		str_info(ctx, descr_render(&dsc),
-				_("Attempting optimization."));
-
-	error = -xfrog_scrub_metadata(xfdp, &meta);
-	switch (error) {
-	case 0:
-		/* No operational errors encountered. */
-		break;
-	case EDEADLOCK:
-	case EBUSY:
-		/* Filesystem is busy, try again later. */
-		if (debug || verbose)
-			str_info(ctx, descr_render(&dsc),
-_("Filesystem is busy, deferring repair."));
-		return CHECK_RETRY;
-	case ESHUTDOWN:
-		/* Filesystem is already shut down, abort. */
-		str_error(ctx, descr_render(&dsc),
-_("Filesystem is shut down, aborting."));
-		return CHECK_ABORT;
-	case ENOTTY:
-	case EOPNOTSUPP:
-		/*
-		 * If the kernel cannot perform the optimization that we
-		 * requested; or we forced a repair but the kernel doesn't know
-		 * how to perform the repair, don't requeue the request.  Mark
-		 * it done and move on.
-		 */
-		if (is_unoptimized(&oldm) ||
-		    debug_tweak_on("XFS_SCRUB_FORCE_REPAIR"))
-			return CHECK_DONE;
-		/*
-		 * If we're in no-complain mode, requeue the check for
-		 * later.  It's possible that an error in another
-		 * component caused us to flag an error in this
-		 * component.  Even if the kernel didn't think it
-		 * could fix this, it's at least worth trying the scan
-		 * again to see if another repair fixed it.
-		 */
-		if (!(repair_flags & XRM_FINAL_WARNING))
-			return CHECK_RETRY;
-		fallthrough;
-	case EINVAL:
-		/* Kernel doesn't know how to repair this? */
-		str_corrupt(ctx, descr_render(&dsc),
-_("Don't know how to fix; offline repair required."));
-		return CHECK_DONE;
-	case EROFS:
-		/* Read-only filesystem, can't fix. */
-		if (verbose || debug || needs_repair(&oldm))
-			str_error(ctx, descr_render(&dsc),
-_("Read-only filesystem; cannot make changes."));
-		return CHECK_ABORT;
-	case ENOENT:
-		/* Metadata not present, just skip it. */
-		return CHECK_DONE;
-	case ENOMEM:
-	case ENOSPC:
-		/* Don't care if preen fails due to low resources. */
-		if (is_unoptimized(&oldm) && !needs_repair(&oldm))
-			return CHECK_DONE;
-		fallthrough;
-	default:
-		/*
-		 * Operational error.  If the caller doesn't want us
-		 * to complain about repair failures, tell the caller
-		 * to requeue the repair for later and don't say a
-		 * thing.  Otherwise, print error and bail out.
-		 */
-		if (!(repair_flags & XRM_FINAL_WARNING))
-			return CHECK_RETRY;
-		str_liberror(ctx, error, descr_render(&dsc));
-		return CHECK_DONE;
-	}
-
-	if (repair_flags & XRM_FINAL_WARNING)
-		scrub_warn_incomplete_scrub(ctx, &dsc, &meta);
-	if (needs_repair(&meta)) {
-		/*
-		 * Still broken; if we've been told not to complain then we
-		 * just requeue this and try again later.  Otherwise we
-		 * log the error loudly and don't try again.
-		 */
-		if (!(repair_flags & XRM_FINAL_WARNING))
-			return CHECK_RETRY;
-		str_corrupt(ctx, descr_render(&dsc),
-_("Repair unsuccessful; offline repair required."));
-	} else if (xref_failed(&meta)) {
-		/*
-		 * This metadata object itself looks ok, but we still noticed
-		 * inconsistencies when comparing it with the other filesystem
-		 * metadata.  If we're in "final warning" mode, advise the
-		 * caller to run xfs_repair; otherwise, we'll keep trying to
-		 * reverify the cross-referencing as repairs progress.
-		 */
-		if (repair_flags & XRM_FINAL_WARNING) {
-			str_info(ctx, descr_render(&dsc),
- _("Seems correct but cross-referencing failed; offline repair recommended."));
-		} else {
-			if (verbose)
-				str_info(ctx, descr_render(&dsc),
- _("Seems correct but cross-referencing failed; will keep checking."));
-			return CHECK_RETRY;
-		}
-	} else {
-		/* Clean operation, no corruption detected. */
-		if (needs_repair(&oldm))
-			record_repair(ctx, descr_render(&dsc),
-					_("Repairs successful."));
-		else
-			record_preen(ctx, descr_render(&dsc),
-					_("Optimization successful."));
-	}
-	return CHECK_DONE;
-}
diff --git a/scrub/scrub.h b/scrub/scrub.h
index 5359548b06f..133445e8da6 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -38,7 +38,7 @@ bool can_scrub_dir(struct scrub_ctx *ctx);
 bool can_scrub_attr(struct scrub_ctx *ctx);
 bool can_scrub_symlink(struct scrub_ctx *ctx);
 bool can_scrub_parent(struct scrub_ctx *ctx);
-bool xfs_can_repair(struct scrub_ctx *ctx);
+bool can_repair(struct scrub_ctx *ctx);
 bool can_force_rebuild(struct scrub_ctx *ctx);
 
 int scrub_file(struct scrub_ctx *ctx, int fd, const struct xfs_bulkstat *bstat,
@@ -54,8 +54,4 @@ struct action_item {
 	__u32			agno;
 };
 
-enum check_outcome xfs_repair_metadata(struct scrub_ctx *ctx,
-		struct xfs_fd *xfdp, struct action_item *aitem,
-		unsigned int repair_flags);
-
 #endif /* XFS_SCRUB_SCRUB_H_ */
diff --git a/scrub/scrub_private.h b/scrub/scrub_private.h
new file mode 100644
index 00000000000..a24d485a286
--- /dev/null
+++ b/scrub/scrub_private.h
@@ -0,0 +1,55 @@
+// 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_SCRUB_PRIVATE_H_
+#define XFS_SCRUB_SCRUB_PRIVATE_H_
+
+/* Shared code between scrub.c and repair.c. */
+
+int format_scrub_descr(struct scrub_ctx *ctx, char *buf, size_t buflen,
+		void *where);
+
+/* Predicates for scrub flag state. */
+
+static inline bool is_corrupt(struct xfs_scrub_metadata *sm)
+{
+	return sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT;
+}
+
+static inline bool is_unoptimized(struct xfs_scrub_metadata *sm)
+{
+	return sm->sm_flags & XFS_SCRUB_OFLAG_PREEN;
+}
+
+static inline bool xref_failed(struct xfs_scrub_metadata *sm)
+{
+	return sm->sm_flags & XFS_SCRUB_OFLAG_XFAIL;
+}
+
+static inline bool xref_disagrees(struct xfs_scrub_metadata *sm)
+{
+	return sm->sm_flags & XFS_SCRUB_OFLAG_XCORRUPT;
+}
+
+static inline bool is_incomplete(struct xfs_scrub_metadata *sm)
+{
+	return sm->sm_flags & XFS_SCRUB_OFLAG_INCOMPLETE;
+}
+
+static inline bool is_suspicious(struct xfs_scrub_metadata *sm)
+{
+	return sm->sm_flags & XFS_SCRUB_OFLAG_WARNING;
+}
+
+/* Should we fix it? */
+static inline bool needs_repair(struct xfs_scrub_metadata *sm)
+{
+	return is_corrupt(sm) || xref_disagrees(sm);
+}
+
+void scrub_warn_incomplete_scrub(struct scrub_ctx *ctx, struct descr *dsc,
+		struct xfs_scrub_metadata *meta);
+
+#endif /* XFS_SCRUB_SCRUB_PRIVATE_H_ */

[PATCH 5/7] xfs_scrub: log when a repair was unnecessary

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If the kernel tells us that a filesystem object didn't need repairs, we
should log that with a message specific to that outcome.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/repair.c |    4 ++++
 1 file changed, 4 insertions(+)


diff --git a/scrub/repair.c b/scrub/repair.c
index 54bd09575c0..50f168d24fe 100644
--- a/scrub/repair.c
+++ b/scrub/repair.c
@@ -167,6 +167,10 @@ _("Repair unsuccessful; offline repair required."));
  _("Seems correct but cross-referencing failed; will keep checking."));
 			return CHECK_RETRY;
 		}
+	} else if (meta.sm_flags & XFS_SCRUB_OFLAG_NO_REPAIR_NEEDED) {
+		if (verbose)
+			str_info(ctx, descr_render(&dsc),
+					_("No modification needed."));
 	} else {
 		/* Clean operation, no corruption detected. */
 		if (is_corrupt(&oldm))

[PATCH 6/7] xfs_scrub: require primary superblock repairs to complete before proceeding

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Phase 2 of the xfs_scrub program calls the kernel to check the primary
superblock before scanning the rest of the filesystem.  Though doing so
is a no-op now (since the primary super must pass all checks as a
prerequisite for mounting), the goal of this code is to enable future
kernel code to intercept an xfs_scrub run before it actually does
anything.  If this some day involves fixing the primary superblock, it
seems reasonable to require that /all/ repairs complete successfully
before moving on to the rest of the filesystem.

Unfortunately, that's not what xfs_scrub does now -- primary super
repairs that fail are theoretically deferred to phase 4!  So make this
mandatory.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase2.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)


diff --git a/scrub/phase2.c b/scrub/phase2.c
index 80c77b2876f..2d49c604eae 100644
--- a/scrub/phase2.c
+++ b/scrub/phase2.c
@@ -174,7 +174,8 @@ phase2_func(
 	ret = scrub_primary_super(ctx, &alist);
 	if (ret)
 		goto out_wq;
-	ret = action_list_process_or_defer(ctx, 0, &alist);
+	ret = action_list_process(ctx, -1, &alist,
+			XRM_FINAL_WARNING | XRM_NOPROGRESS);
 	if (ret)
 		goto out_wq;
 

[PATCH 7/7] xfs_scrub: actually try to fix summary counters ahead of repairs

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

A while ago, I decided to make phase 4 check the summary counters before
it starts any other repairs, having observed that repairs of primary
metadata can fail because the summary counters (incorrectly) claim that
there aren't enough free resources in the filesystem.  However, if
problems are found in the summary counters, the repair work will be run
as part of the AG 0 repairs, which means that it runs concurrently with
other scrubbers.  This doesn't quite get us to the intended goal, so try
to fix the scrubbers ahead of time.  If that fails, tough, we'll get
back to it in phase 7 if scrub gets that far.

Fixes: cbaf1c9d91a0 ("xfs_scrub: check summary counters")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase4.c |   20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)


diff --git a/scrub/phase4.c b/scrub/phase4.c
index d42e67637d8..0c67abf64a3 100644
--- a/scrub/phase4.c
+++ b/scrub/phase4.c
@@ -129,6 +129,7 @@ phase4_func(
 	struct scrub_ctx	*ctx)
 {
 	struct xfs_fsop_geom	fsgeom;
+	struct action_list	alist;
 	int			ret;
 
 	if (!have_action_items(ctx))
@@ -136,11 +137,13 @@ phase4_func(
 
 	/*
 	 * Check the summary counters early.  Normally we do this during phase
-	 * seven, but some of the cross-referencing requires fairly-accurate
-	 * counters, so counter repairs have to be put on the list now so that
-	 * they get fixed before we stop retrying unfixed metadata repairs.
+	 * seven, but some of the cross-referencing requires fairly accurate
+	 * summary counters.  Check and try to repair them now to minimize the
+	 * chance that repairs of primary metadata fail due to secondary
+	 * metadata.  If repairs fails, we'll come back during phase 7.
 	 */
-	ret = scrub_fs_counters(ctx, &ctx->action_lists[0]);
+	action_list_init(&alist);
+	ret = scrub_fs_counters(ctx, &alist);
 	if (ret)
 		return ret;
 
@@ -155,11 +158,18 @@ phase4_func(
 		return ret;
 
 	if (fsgeom.sick & XFS_FSOP_GEOM_SICK_QUOTACHECK) {
-		ret = scrub_quotacheck(ctx, &ctx->action_lists[0]);
+		ret = scrub_quotacheck(ctx, &alist);
 		if (ret)
 			return ret;
 	}
 
+	/* Repair counters before starting on the rest. */
+	ret = action_list_process(ctx, -1, &alist,
+			XRM_REPAIR_ONLY | XRM_NOPROGRESS);
+	if (ret)
+		return ret;
+	action_list_discard(&alist);
+
 	ret = repair_everything(ctx);
 	if (ret)
 		return ret;

[PATCH 1/8] xfs_scrub: fix missing scrub coverage for broken inodes

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If INUMBERS says that an inode is allocated, but BULKSTAT skips over the
inode and BULKSTAT_SINGLE errors out when loading the inumber, there are
two possibilities: One, we're racing with ifree; or two, the inode is
corrupt and iget failed.

When this happens, the scrub_scan_all_inodes code will insert a dummy
bulkstat record with all fields zeroed except bs_ino and bs_blksize.
Hence the use of i_mode switches in phase3 to schedule file content
scrubbing are not entirely correct -- bs_mode==0 means "type unknown",
which ought to mean "schedule all scrubbers".

Unfortunately, the current code doesn't do that, so instead we schedule
no content scrubs.  If the broken file was actually a directory, we fail
to check the directory contents for further corruptions.

Found by using fuzzing with xfs/385 and core.format = 0.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase3.c |   21 +++++++++++++++++----
 1 file changed, 17 insertions(+), 4 deletions(-)


diff --git a/scrub/phase3.c b/scrub/phase3.c
index 9a26b92036c..b03b55250a3 100644
--- a/scrub/phase3.c
+++ b/scrub/phase3.c
@@ -166,16 +166,29 @@ scrub_inode(
 	if (error)
 		goto out;
 
-	if (S_ISLNK(bstat->bs_mode)) {
+	/*
+	 * Check file data contents, e.g. symlink and directory entries.
+	 *
+	 * Note: bs_mode==0 occurs when inumbers says an inode is allocated,
+	 * bulkstat skips the inode, and bulkstat_single errors out when
+	 * loading the inode.  This could be due to racing with ifree, but it
+	 * could be a corrupt inode.  Either way, schedule all the data fork
+	 * content scrubbers.  Better to have them return -ENOENT than miss
+	 * some coverage.
+	 */
+	if (S_ISLNK(bstat->bs_mode) || !bstat->bs_mode) {
 		/* Check symlink contents. */
 		error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_SYMLINK,
 				&alist);
-	} else if (S_ISDIR(bstat->bs_mode)) {
+		if (error)
+			goto out;
+	}
+	if (S_ISDIR(bstat->bs_mode) || !bstat->bs_mode) {
 		/* Check the directory entries. */
 		error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_DIR, &alist);
+		if (error)
+			goto out;
 	}
-	if (error)
-		goto out;
 
 	/* Check all the extended attributes. */
 	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_XATTR, &alist);

[PATCH 2/8] xfs_scrub: collapse trivial superblock scrub helpers

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Remove the trivial primary super scrub helper function since it makes
tracing code paths difficult and will become annoying in the patches
that follow.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase2.c |    9 +++++----
 scrub/scrub.c  |   16 +---------------
 scrub/scrub.h  |    3 ++-
 3 files changed, 8 insertions(+), 20 deletions(-)


diff --git a/scrub/phase2.c b/scrub/phase2.c
index 2d49c604eae..ec72bb5b71a 100644
--- a/scrub/phase2.c
+++ b/scrub/phase2.c
@@ -166,12 +166,13 @@ phase2_func(
 	}
 
 	/*
-	 * In case we ever use the primary super scrubber to perform fs
-	 * upgrades (followed by a full scrub), do that before we launch
-	 * anything else.
+	 * Scrub primary superblock.  This will be useful if we ever need to
+	 * hook a filesystem-wide pre-scrub activity (e.g. enable filesystem
+	 * upgrades) off of the sb 0 scrubber (which currently does nothing).
+	 * If errors occur, this function will log them and return nonzero.
 	 */
 	action_list_init(&alist);
-	ret = scrub_primary_super(ctx, &alist);
+	ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_SB, 0, &alist);
 	if (ret)
 		goto out_wq;
 	ret = action_list_process(ctx, -1, &alist,
diff --git a/scrub/scrub.c b/scrub/scrub.c
index 59583913031..c2e56e5f1cb 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -259,7 +259,7 @@ scrub_save_repair(
  * Returns 0 for success.  If errors occur, this function will log them and
  * return a positive error code.
  */
-static int
+int
 scrub_meta_type(
 	struct scrub_ctx		*ctx,
 	unsigned int			type,
@@ -325,20 +325,6 @@ scrub_group(
 	return 0;
 }
 
-/*
- * Scrub primary superblock.  This will be useful if we ever need to hook
- * a filesystem-wide pre-scrub activity off of the sb 0 scrubber (which
- * currently does nothing).  If errors occur, this function will log them and
- * return nonzero.
- */
-int
-scrub_primary_super(
-	struct scrub_ctx		*ctx,
-	struct action_list		*alist)
-{
-	return scrub_meta_type(ctx, XFS_SCRUB_TYPE_SB, 0, alist);
-}
-
 /* Scrub each AG's header blocks. */
 int
 scrub_ag_headers(
diff --git a/scrub/scrub.h b/scrub/scrub.h
index 133445e8da6..fef8a596049 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -17,7 +17,6 @@ enum check_outcome {
 struct action_item;
 
 void scrub_report_preen_triggers(struct scrub_ctx *ctx);
-int scrub_primary_super(struct scrub_ctx *ctx, struct action_list *alist);
 int scrub_ag_headers(struct scrub_ctx *ctx, xfs_agnumber_t agno,
 		struct action_list *alist);
 int scrub_ag_metadata(struct scrub_ctx *ctx, xfs_agnumber_t agno,
@@ -30,6 +29,8 @@ int scrub_fs_counters(struct scrub_ctx *ctx, struct action_list *alist);
 int scrub_quotacheck(struct scrub_ctx *ctx, struct action_list *alist);
 int scrub_nlinks(struct scrub_ctx *ctx, struct action_list *alist);
 int scrub_clean_health(struct scrub_ctx *ctx, struct action_list *alist);
+int scrub_meta_type(struct scrub_ctx *ctx, unsigned int type,
+		xfs_agnumber_t agno, struct action_list *alist);
 
 bool can_scrub_fs_metadata(struct scrub_ctx *ctx);
 bool can_scrub_inode(struct scrub_ctx *ctx);

[PATCH 3/8] xfs_scrub: get rid of trivial fs metadata scanner helpers

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Get rid of these pointless wrappers.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase1.c |    2 +-
 scrub/phase4.c |    9 +++++----
 scrub/phase5.c |   15 +++++++--------
 scrub/scrub.c  |   36 ------------------------------------
 scrub/scrub.h  |    4 ----
 5 files changed, 13 insertions(+), 53 deletions(-)


diff --git a/scrub/phase1.c b/scrub/phase1.c
index 81b0918a1c8..a61e154a84a 100644
--- a/scrub/phase1.c
+++ b/scrub/phase1.c
@@ -61,7 +61,7 @@ report_to_kernel(
 		return 0;
 
 	action_list_init(&alist);
-	ret = scrub_clean_health(ctx, &alist);
+	ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_HEALTHY, 0, &alist);
 	if (ret)
 		return ret;
 
diff --git a/scrub/phase4.c b/scrub/phase4.c
index 0c67abf64a3..d01dc89f44f 100644
--- a/scrub/phase4.c
+++ b/scrub/phase4.c
@@ -136,14 +136,14 @@ phase4_func(
 		goto maybe_trim;
 
 	/*
-	 * Check the summary counters early.  Normally we do this during phase
-	 * seven, but some of the cross-referencing requires fairly accurate
+	 * Check the resource usage counters early.  Normally we do this during
+	 * phase 7, but some of the cross-referencing requires fairly accurate
 	 * summary counters.  Check and try to repair them now to minimize the
 	 * chance that repairs of primary metadata fail due to secondary
 	 * metadata.  If repairs fails, we'll come back during phase 7.
 	 */
 	action_list_init(&alist);
-	ret = scrub_fs_counters(ctx, &alist);
+	ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_FSCOUNTERS, 0, &alist);
 	if (ret)
 		return ret;
 
@@ -158,7 +158,8 @@ phase4_func(
 		return ret;
 
 	if (fsgeom.sick & XFS_FSOP_GEOM_SICK_QUOTACHECK) {
-		ret = scrub_quotacheck(ctx, &alist);
+		ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_QUOTACHECK, 0,
+				&alist);
 		if (ret)
 			return ret;
 	}
diff --git a/scrub/phase5.c b/scrub/phase5.c
index 940e434c3cd..68d35cd5852 100644
--- a/scrub/phase5.c
+++ b/scrub/phase5.c
@@ -384,12 +384,10 @@ check_fs_label(
 	return error;
 }
 
-typedef int (*fs_scan_item_fn)(struct scrub_ctx *, struct action_list *);
-
 struct fs_scan_item {
 	struct action_list	alist;
 	bool			*abortedp;
-	fs_scan_item_fn		scrub_fn;
+	unsigned int		scrub_type;
 };
 
 /* Run one full-fs scan scrubber in this thread. */
@@ -414,7 +412,7 @@ fs_scan_worker(
 		nanosleep(&tv, NULL);
 	}
 
-	ret = item->scrub_fn(ctx, &item->alist);
+	ret = scrub_meta_type(ctx, item->scrub_type, 0, &item->alist);
 	if (ret) {
 		str_liberror(ctx, ret, _("checking fs scan metadata"));
 		*item->abortedp = true;
@@ -440,7 +438,7 @@ queue_fs_scan(
 	struct workqueue	*wq,
 	bool			*abortedp,
 	xfs_agnumber_t		nr,
-	fs_scan_item_fn		scrub_fn)
+	unsigned int		scrub_type)
 {
 	struct fs_scan_item	*item;
 	struct scrub_ctx	*ctx = wq->wq_ctx;
@@ -453,7 +451,7 @@ queue_fs_scan(
 		return ret;
 	}
 	action_list_init(&item->alist);
-	item->scrub_fn = scrub_fn;
+	item->scrub_type = scrub_type;
 	item->abortedp = abortedp;
 
 	ret = -workqueue_add(wq, fs_scan_worker, nr, item);
@@ -485,14 +483,15 @@ run_kernel_fs_scan_scrubbers(
 	 * The nlinks scanner is much faster than quotacheck because it only
 	 * walks directories, so we start it first.
 	 */
-	ret = queue_fs_scan(&wq_fs_scan, &aborted, nr, scrub_nlinks);
+	ret = queue_fs_scan(&wq_fs_scan, &aborted, nr, XFS_SCRUB_TYPE_NLINKS);
 	if (ret)
 		goto wait;
 
 	if (nr_threads > 1)
 		nr++;
 
-	ret = queue_fs_scan(&wq_fs_scan, &aborted, nr, scrub_quotacheck);
+	ret = queue_fs_scan(&wq_fs_scan, &aborted, nr,
+			XFS_SCRUB_TYPE_QUOTACHECK);
 	if (ret)
 		goto wait;
 
diff --git a/scrub/scrub.c b/scrub/scrub.c
index c2e56e5f1cb..6e857c79dfb 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -366,42 +366,6 @@ scrub_summary_metadata(
 	return scrub_group(ctx, XFROG_SCRUB_GROUP_SUMMARY, 0, alist);
 }
 
-/* Scrub /only/ the superblock summary counters. */
-int
-scrub_fs_counters(
-	struct scrub_ctx		*ctx,
-	struct action_list		*alist)
-{
-	return scrub_meta_type(ctx, XFS_SCRUB_TYPE_FSCOUNTERS, 0, alist);
-}
-
-/* Scrub /only/ the quota counters. */
-int
-scrub_quotacheck(
-	struct scrub_ctx		*ctx,
-	struct action_list		*alist)
-{
-	return scrub_meta_type(ctx, XFS_SCRUB_TYPE_QUOTACHECK, 0, alist);
-}
-
-/* Scrub /only/ the file link counters. */
-int
-scrub_nlinks(
-	struct scrub_ctx		*ctx,
-	struct action_list		*alist)
-{
-	return scrub_meta_type(ctx, XFS_SCRUB_TYPE_NLINKS, 0, alist);
-}
-
-/* Update incore health records if we were clean. */
-int
-scrub_clean_health(
-	struct scrub_ctx		*ctx,
-	struct action_list		*alist)
-{
-	return scrub_meta_type(ctx, XFS_SCRUB_TYPE_HEALTHY, 0, alist);
-}
-
 /* How many items do we have to check? */
 unsigned int
 scrub_estimate_ag_work(
diff --git a/scrub/scrub.h b/scrub/scrub.h
index fef8a596049..98819a25b62 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -25,10 +25,6 @@ int scrub_fs_metadata(struct scrub_ctx *ctx, unsigned int scrub_type,
 		struct action_list *alist);
 int scrub_iscan_metadata(struct scrub_ctx *ctx, struct action_list *alist);
 int scrub_summary_metadata(struct scrub_ctx *ctx, struct action_list *alist);
-int scrub_fs_counters(struct scrub_ctx *ctx, struct action_list *alist);
-int scrub_quotacheck(struct scrub_ctx *ctx, struct action_list *alist);
-int scrub_nlinks(struct scrub_ctx *ctx, struct action_list *alist);
-int scrub_clean_health(struct scrub_ctx *ctx, struct action_list *alist);
 int scrub_meta_type(struct scrub_ctx *ctx, unsigned int type,
 		xfs_agnumber_t agno, struct action_list *alist);
 

[PATCH 4/8] xfs_scrub: split up the mustfix repairs and difficulty assessment functions

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Currently, action_list_find_mustfix does two things -- it figures out
which repairs must be tried during phase 2 to enable the inode scan in
phase 3; and it figures out if xfs_scrub should warn about secondary and
primary metadata corruption that might make repair difficult.

Split these into separate functions to make each more coherent.  A long
time from now we'll need this to enable warnings about difficult rt
repairs, but for now this is merely a code cleanup.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase2.c |   15 +++++++--------
 scrub/repair.c |   38 +++++++++++++++++++++++++++-----------
 scrub/repair.h |   10 +++++++---
 3 files changed, 41 insertions(+), 22 deletions(-)


diff --git a/scrub/phase2.c b/scrub/phase2.c
index ec72bb5b71a..4c0d20a8e2b 100644
--- a/scrub/phase2.c
+++ b/scrub/phase2.c
@@ -42,9 +42,8 @@ scan_ag_metadata(
 	struct scan_ctl			*sctl = arg;
 	struct action_list		alist;
 	struct action_list		immediate_alist;
-	unsigned long long		broken_primaries;
-	unsigned long long		broken_secondaries;
 	char				descr[DESCR_BUFSZ];
+	unsigned int			difficulty;
 	int				ret;
 
 	if (sctl->aborted)
@@ -79,12 +78,12 @@ scan_ag_metadata(
 	 * the inobt from rmapbt data, but if the rmapbt is broken even
 	 * at this early phase then we are sunk.
 	 */
-	broken_secondaries = 0;
-	broken_primaries = 0;
-	action_list_find_mustfix(&alist, &immediate_alist,
-			&broken_primaries, &broken_secondaries);
-	if (broken_secondaries && !debug_tweak_on("XFS_SCRUB_FORCE_REPAIR")) {
-		if (broken_primaries)
+	difficulty = action_list_difficulty(&alist);
+	action_list_find_mustfix(&alist, &immediate_alist);
+
+	if ((difficulty & REPAIR_DIFFICULTY_SECONDARY) &&
+	    !debug_tweak_on("XFS_SCRUB_FORCE_REPAIR")) {
+		if (difficulty & REPAIR_DIFFICULTY_PRIMARY)
 			str_info(ctx, descr,
 _("Corrupt primary and secondary block mapping metadata."));
 		else
diff --git a/scrub/repair.c b/scrub/repair.c
index 50f168d24fe..8ee9102ab58 100644
--- a/scrub/repair.c
+++ b/scrub/repair.c
@@ -290,9 +290,7 @@ xfs_action_item_compare(
 void
 action_list_find_mustfix(
 	struct action_list		*alist,
-	struct action_list		*immediate_alist,
-	unsigned long long		*broken_primaries,
-	unsigned long long		*broken_secondaries)
+	struct action_list		*immediate_alist)
 {
 	struct action_item		*n;
 	struct action_item		*aitem;
@@ -301,25 +299,43 @@ action_list_find_mustfix(
 		if (!(aitem->flags & XFS_SCRUB_OFLAG_CORRUPT))
 			continue;
 		switch (aitem->type) {
-		case XFS_SCRUB_TYPE_RMAPBT:
-			(*broken_secondaries)++;
-			break;
 		case XFS_SCRUB_TYPE_FINOBT:
 		case XFS_SCRUB_TYPE_INOBT:
 			alist->nr--;
 			list_move_tail(&aitem->list, &immediate_alist->list);
 			immediate_alist->nr++;
-			fallthrough;
+			break;
+		}
+	}
+}
+
+/* Determine if primary or secondary metadata are inconsistent. */
+unsigned int
+action_list_difficulty(
+	const struct action_list	*alist)
+{
+	struct action_item		*aitem, *n;
+	unsigned int			ret = 0;
+
+	list_for_each_entry_safe(aitem, n, &alist->list, list) {
+		if (!(aitem->flags & XFS_SCRUB_OFLAG_CORRUPT))
+			continue;
+
+		switch (aitem->type) {
+		case XFS_SCRUB_TYPE_RMAPBT:
+			ret |= REPAIR_DIFFICULTY_SECONDARY;
+			break;
+		case XFS_SCRUB_TYPE_FINOBT:
+		case XFS_SCRUB_TYPE_INOBT:
 		case XFS_SCRUB_TYPE_BNOBT:
 		case XFS_SCRUB_TYPE_CNTBT:
 		case XFS_SCRUB_TYPE_REFCNTBT:
-			(*broken_primaries)++;
-			break;
-		default:
-			abort();
+			ret |= REPAIR_DIFFICULTY_PRIMARY;
 			break;
 		}
 	}
+
+	return ret;
 }
 
 /*
diff --git a/scrub/repair.h b/scrub/repair.h
index 6b6f64691a3..b61bd29c860 100644
--- a/scrub/repair.h
+++ b/scrub/repair.h
@@ -28,9 +28,13 @@ void action_list_discard(struct action_list *alist);
 void action_list_splice(struct action_list *dest, struct action_list *src);
 
 void action_list_find_mustfix(struct action_list *actions,
-		struct action_list *immediate_alist,
-		unsigned long long *broken_primaries,
-		unsigned long long *broken_secondaries);
+		struct action_list *immediate_alist);
+
+/* Primary metadata is corrupt */
+#define REPAIR_DIFFICULTY_PRIMARY	(1U << 0)
+/* Secondary metadata is corrupt */
+#define REPAIR_DIFFICULTY_SECONDARY	(1U << 1)
+unsigned int action_list_difficulty(const struct action_list *actions);
 
 /*
  * Only ask the kernel to repair this object if the kernel directly told us it

[PATCH 5/8] xfs_scrub: add missing repair types to the mustfix and difficulty assessment

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add a few scrub types that ought to trigger a mustfix (such as AGI
corruption) and all the AG space metadata to the repair difficulty
assessment.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/repair.c |    7 +++++++
 1 file changed, 7 insertions(+)


diff --git a/scrub/repair.c b/scrub/repair.c
index 8ee9102ab58..33a8031103c 100644
--- a/scrub/repair.c
+++ b/scrub/repair.c
@@ -299,6 +299,7 @@ action_list_find_mustfix(
 		if (!(aitem->flags & XFS_SCRUB_OFLAG_CORRUPT))
 			continue;
 		switch (aitem->type) {
+		case XFS_SCRUB_TYPE_AGI:
 		case XFS_SCRUB_TYPE_FINOBT:
 		case XFS_SCRUB_TYPE_INOBT:
 			alist->nr--;
@@ -325,11 +326,17 @@ action_list_difficulty(
 		case XFS_SCRUB_TYPE_RMAPBT:
 			ret |= REPAIR_DIFFICULTY_SECONDARY;
 			break;
+		case XFS_SCRUB_TYPE_SB:
+		case XFS_SCRUB_TYPE_AGF:
+		case XFS_SCRUB_TYPE_AGFL:
+		case XFS_SCRUB_TYPE_AGI:
 		case XFS_SCRUB_TYPE_FINOBT:
 		case XFS_SCRUB_TYPE_INOBT:
 		case XFS_SCRUB_TYPE_BNOBT:
 		case XFS_SCRUB_TYPE_CNTBT:
 		case XFS_SCRUB_TYPE_REFCNTBT:
+		case XFS_SCRUB_TYPE_RTBITMAP:
+		case XFS_SCRUB_TYPE_RTSUM:
 			ret |= REPAIR_DIFFICULTY_PRIMARY;
 			break;
 		}

[PATCH 6/8] xfs_scrub: any inconsistency in metadata should trigger difficulty warnings

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Any inconsistency in the space metadata can be a sign that repairs will
be difficult, so set off the warning if there were cross referencing
problems too.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/repair.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)


diff --git a/scrub/repair.c b/scrub/repair.c
index 33a8031103c..30817d268d6 100644
--- a/scrub/repair.c
+++ b/scrub/repair.c
@@ -319,7 +319,9 @@ action_list_difficulty(
 	unsigned int			ret = 0;
 
 	list_for_each_entry_safe(aitem, n, &alist->list, list) {
-		if (!(aitem->flags & XFS_SCRUB_OFLAG_CORRUPT))
+		if (!(aitem->flags & (XFS_SCRUB_OFLAG_CORRUPT |
+				      XFS_SCRUB_OFLAG_XCORRUPT |
+				      XFS_SCRUB_OFLAG_XFAIL)))
 			continue;
 
 		switch (aitem->type) {

[PATCH 7/8] xfs_scrub: warn about difficult repairs to rt and quota metadata

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Warn the user if there are problems with the rt or quota metadata that
might make repairs difficult.  For now there aren't any corruption
conditions that would trigger this, but we don't want to leave a gap.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase2.c |   37 +++++++++++++++++++++++++------------
 1 file changed, 25 insertions(+), 12 deletions(-)


diff --git a/scrub/phase2.c b/scrub/phase2.c
index 4c0d20a8e2b..3e88c969b43 100644
--- a/scrub/phase2.c
+++ b/scrub/phase2.c
@@ -31,6 +31,25 @@ struct scan_ctl {
 	bool			aborted;
 };
 
+/* Warn about the types of mutual inconsistencies that may make repairs hard. */
+static inline void
+warn_repair_difficulties(
+	struct scrub_ctx	*ctx,
+	unsigned int		difficulty,
+	const char		*descr)
+{
+	if (!(difficulty & REPAIR_DIFFICULTY_SECONDARY))
+		return;
+	if (debug_tweak_on("XFS_SCRUB_FORCE_REPAIR"))
+		return;
+
+	if (difficulty & REPAIR_DIFFICULTY_PRIMARY)
+		str_info(ctx, descr, _("Corrupt primary and secondary metadata."));
+	else
+		str_info(ctx, descr, _("Corrupt secondary metadata."));
+	str_info(ctx, descr, _("Filesystem might not be repairable."));
+}
+
 /* Scrub each AG's metadata btrees. */
 static void
 scan_ag_metadata(
@@ -80,18 +99,7 @@ scan_ag_metadata(
 	 */
 	difficulty = action_list_difficulty(&alist);
 	action_list_find_mustfix(&alist, &immediate_alist);
-
-	if ((difficulty & REPAIR_DIFFICULTY_SECONDARY) &&
-	    !debug_tweak_on("XFS_SCRUB_FORCE_REPAIR")) {
-		if (difficulty & REPAIR_DIFFICULTY_PRIMARY)
-			str_info(ctx, descr,
-_("Corrupt primary and secondary block mapping metadata."));
-		else
-			str_info(ctx, descr,
-_("Corrupt secondary block mapping metadata."));
-		str_info(ctx, descr,
-_("Filesystem might not be repairable."));
-	}
+	warn_repair_difficulties(ctx, difficulty, descr);
 
 	/* Repair (inode) btree damage. */
 	ret = action_list_process_or_defer(ctx, agno, &immediate_alist);
@@ -115,6 +123,7 @@ scan_fs_metadata(
 	struct action_list	alist;
 	struct scrub_ctx	*ctx = (struct scrub_ctx *)wq->wq_ctx;
 	struct scan_ctl		*sctl = arg;
+	unsigned int		difficulty;
 	int			ret;
 
 	if (sctl->aborted)
@@ -127,6 +136,10 @@ scan_fs_metadata(
 		goto out;
 	}
 
+	/* Complain about metadata corruptions that might not be fixable. */
+	difficulty = action_list_difficulty(&alist);
+	warn_repair_difficulties(ctx, difficulty, xfrog_scrubbers[type].descr);
+
 	action_list_defer(ctx, 0, &alist);
 
 out:

[PATCH 8/8] xfs_scrub: enable users to bump information messages to warnings

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add a -o iwarn option that enables users to specify that informational
messages (such as incomplete scans, or confusing names) should be
treated as warnings.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 man/man8/xfs_scrub.8 |   19 +++++++++++++++++++
 scrub/common.c       |    2 ++
 scrub/xfs_scrub.c    |   45 ++++++++++++++++++++++++++++++++++++++++++++-
 scrub/xfs_scrub.h    |    1 +
 4 files changed, 66 insertions(+), 1 deletion(-)


diff --git a/man/man8/xfs_scrub.8 b/man/man8/xfs_scrub.8
index e881ae76acb..404baba696e 100644
--- a/man/man8/xfs_scrub.8
+++ b/man/man8/xfs_scrub.8
@@ -85,6 +85,25 @@ Search this file for mounted filesystems instead of /etc/mtab.
 .B \-n
 Only check filesystem metadata.
 Do not repair or optimize anything.
+.HP
+.B \-o
+.I subopt\c
+[\c
+.B =\c
+.IR value ]
+.BR
+Override what the program might conclude about the filesystem
+if left to its own devices.
+.IP
+The
+.IR subopt ions
+supported are:
+.RS 1.0i
+.TP
+.BI iwarn
+Treat informational messages as warnings.
+This will result in a nonzero return code, and a higher logging level.
+.RE
 .TP
 .BI \-T
 Print timing and memory usage information for each phase.
diff --git a/scrub/common.c b/scrub/common.c
index 283ac84e232..aca59648711 100644
--- a/scrub/common.c
+++ b/scrub/common.c
@@ -110,6 +110,8 @@ __str_out(
 	/* print strerror or format of choice but not both */
 	assert(!(error && format));
 
+	if (level == S_INFO && info_is_warning)
+		level = S_WARN;
 	if (level >= S_INFO)
 		stream = stdout;
 
diff --git a/scrub/xfs_scrub.c b/scrub/xfs_scrub.c
index 752180d646b..aa68c23c62e 100644
--- a/scrub/xfs_scrub.c
+++ b/scrub/xfs_scrub.c
@@ -160,6 +160,9 @@ bool				is_service;
 /* Set to true if the kernel supports XFS_SCRUB_IFLAG_FORCE_REBUILD */
 bool				use_force_rebuild;
 
+/* Should we count informational messages as warnings? */
+bool				info_is_warning;
+
 #define SCRUB_RET_SUCCESS	(0)	/* no problems left behind */
 #define SCRUB_RET_CORRUPT	(1)	/* corruption remains on fs */
 #define SCRUB_RET_UNOPTIMIZED	(2)	/* fs could be optimized */
@@ -604,6 +607,43 @@ report_outcome(
 # define XFS_SCRUB_HAVE_UNICODE	"-"
 #endif
 
+/*
+ * -o: user-supplied override options
+ */
+enum o_opt_nums {
+	IWARN = 0,
+	O_MAX_OPTS,
+};
+
+static char *o_opts[] = {
+	[IWARN]			= "iwarn",
+	[O_MAX_OPTS]		= NULL,
+};
+
+static void
+parse_o_opts(
+	struct scrub_ctx	*ctx,
+	char			*p)
+{
+	while (*p != '\0')  {
+		char		*val;
+
+		switch (getsubopt(&p, o_opts, &val))  {
+		case IWARN:
+			if (val) {
+				fprintf(stderr,
+ _("iwarn does not take an argument\n"));
+				usage();
+			}
+			info_is_warning = true;
+			break;
+		default:
+			usage();
+			break;
+		}
+	}
+}
+
 int
 main(
 	int			argc,
@@ -637,7 +677,7 @@ main(
 	pthread_mutex_init(&ctx.lock, NULL);
 	ctx.mode = SCRUB_MODE_REPAIR;
 	ctx.error_action = ERRORS_CONTINUE;
-	while ((c = getopt(argc, argv, "a:bC:de:km:nTvxV")) != EOF) {
+	while ((c = getopt(argc, argv, "a:bC:de:km:no:TvxV")) != EOF) {
 		switch (c) {
 		case 'a':
 			ctx.max_errors = cvt_u64(optarg, 10);
@@ -687,6 +727,9 @@ main(
 		case 'n':
 			ctx.mode = SCRUB_MODE_DRY_RUN;
 			break;
+		case 'o':
+			parse_o_opts(&ctx, optarg);
+			break;
 		case 'T':
 			display_rusage = true;
 			break;
diff --git a/scrub/xfs_scrub.h b/scrub/xfs_scrub.h
index 34d850d8db3..1151ee9ff3a 100644
--- a/scrub/xfs_scrub.h
+++ b/scrub/xfs_scrub.h
@@ -22,6 +22,7 @@ extern bool			stderr_isatty;
 extern bool			stdout_isatty;
 extern bool			is_service;
 extern bool			use_force_rebuild;
+extern bool			info_is_warning;
 
 enum scrub_mode {
 	SCRUB_MODE_DRY_RUN,

[PATCH 1/9] xfs_scrub: track repair items by principal, not by individual repairs

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a new structure to track scrub and repair state by principal
filesystem object (e.g. ag number or inode number/generation) so that we
can more easily examine and ensure that we satisfy repair order
dependencies.  This transposition will eventually enable bulk scrub
operations and will also save a lot of memory if a given object needs a
lot of work.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase1.c        |    4 ++
 scrub/phase2.c        |   14 ++++++--
 scrub/phase3.c        |   19 ++++++-----
 scrub/phase4.c        |    6 ++--
 scrub/phase5.c        |    5 ++-
 scrub/phase7.c        |    4 ++
 scrub/scrub.c         |   68 ++++++++++++++++++++++++++++++++--------
 scrub/scrub.h         |   83 +++++++++++++++++++++++++++++++++++++++++++++----
 scrub/scrub_private.h |   19 +++++++++++
 9 files changed, 185 insertions(+), 37 deletions(-)


diff --git a/scrub/phase1.c b/scrub/phase1.c
index a61e154a84a..9920f29a693 100644
--- a/scrub/phase1.c
+++ b/scrub/phase1.c
@@ -52,6 +52,7 @@ static int
 report_to_kernel(
 	struct scrub_ctx	*ctx)
 {
+	struct scrub_item	sri;
 	struct action_list	alist;
 	int			ret;
 
@@ -60,8 +61,9 @@ report_to_kernel(
 	    ctx->warnings_found)
 		return 0;
 
+	scrub_item_init_fs(&sri);
 	action_list_init(&alist);
-	ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_HEALTHY, 0, &alist);
+	ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_HEALTHY, 0, &alist, &sri);
 	if (ret)
 		return ret;
 
diff --git a/scrub/phase2.c b/scrub/phase2.c
index 3e88c969b43..518923d6628 100644
--- a/scrub/phase2.c
+++ b/scrub/phase2.c
@@ -57,6 +57,7 @@ scan_ag_metadata(
 	xfs_agnumber_t			agno,
 	void				*arg)
 {
+	struct scrub_item		sri;
 	struct scrub_ctx		*ctx = (struct scrub_ctx *)wq->wq_ctx;
 	struct scan_ctl			*sctl = arg;
 	struct action_list		alist;
@@ -68,6 +69,7 @@ scan_ag_metadata(
 	if (sctl->aborted)
 		return;
 
+	scrub_item_init_ag(&sri, agno);
 	action_list_init(&alist);
 	action_list_init(&immediate_alist);
 	snprintf(descr, DESCR_BUFSZ, _("AG %u"), agno);
@@ -76,7 +78,7 @@ scan_ag_metadata(
 	 * First we scrub and fix the AG headers, because we need
 	 * them to work well enough to check the AG btrees.
 	 */
-	ret = scrub_ag_headers(ctx, agno, &alist);
+	ret = scrub_ag_headers(ctx, agno, &alist, &sri);
 	if (ret)
 		goto err;
 
@@ -86,7 +88,7 @@ scan_ag_metadata(
 		goto err;
 
 	/* Now scrub the AG btrees. */
-	ret = scrub_ag_metadata(ctx, agno, &alist);
+	ret = scrub_ag_metadata(ctx, agno, &alist, &sri);
 	if (ret)
 		goto err;
 
@@ -120,6 +122,7 @@ scan_fs_metadata(
 	xfs_agnumber_t		type,
 	void			*arg)
 {
+	struct scrub_item	sri;
 	struct action_list	alist;
 	struct scrub_ctx	*ctx = (struct scrub_ctx *)wq->wq_ctx;
 	struct scan_ctl		*sctl = arg;
@@ -129,8 +132,9 @@ scan_fs_metadata(
 	if (sctl->aborted)
 		goto out;
 
+	scrub_item_init_fs(&sri);
 	action_list_init(&alist);
-	ret = scrub_fs_metadata(ctx, type, &alist);
+	ret = scrub_fs_metadata(ctx, type, &alist, &sri);
 	if (ret) {
 		sctl->aborted = true;
 		goto out;
@@ -162,6 +166,7 @@ phase2_func(
 		.rbm_done	= false,
 	};
 	struct action_list	alist;
+	struct scrub_item	sri;
 	const struct xfrog_scrub_descr *sc = xfrog_scrubbers;
 	xfs_agnumber_t		agno;
 	unsigned int		type;
@@ -183,8 +188,9 @@ phase2_func(
 	 * upgrades) off of the sb 0 scrubber (which currently does nothing).
 	 * If errors occur, this function will log them and return nonzero.
 	 */
+	scrub_item_init_ag(&sri, 0);
 	action_list_init(&alist);
-	ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_SB, 0, &alist);
+	ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_SB, 0, &alist, &sri);
 	if (ret)
 		goto out_wq;
 	ret = action_list_process(ctx, -1, &alist,
diff --git a/scrub/phase3.c b/scrub/phase3.c
index b03b55250a3..642b8406e5b 100644
--- a/scrub/phase3.c
+++ b/scrub/phase3.c
@@ -105,12 +105,14 @@ scrub_inode(
 	void			*arg)
 {
 	struct action_list	alist;
+	struct scrub_item	sri;
 	struct scrub_inode_ctx	*ictx = arg;
 	struct ptcounter	*icount = ictx->icount;
 	xfs_agnumber_t		agno;
 	int			fd = -1;
 	int			error;
 
+	scrub_item_init_file(&sri, bstat);
 	action_list_init(&alist);
 	agno = cvt_ino_to_agno(&ctx->mnt, bstat->bs_ino);
 	background_sleep();
@@ -143,7 +145,7 @@ scrub_inode(
 		fd = scrub_open_handle(handle);
 
 	/* Scrub the inode. */
-	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_INODE, &alist);
+	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_INODE, &alist, &sri);
 	if (error)
 		goto out;
 
@@ -152,13 +154,13 @@ scrub_inode(
 		goto out;
 
 	/* Scrub all block mappings. */
-	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_BMBTD, &alist);
+	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_BMBTD, &alist, &sri);
 	if (error)
 		goto out;
-	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_BMBTA, &alist);
+	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_BMBTA, &alist, &sri);
 	if (error)
 		goto out;
-	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_BMBTC, &alist);
+	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_BMBTC, &alist, &sri);
 	if (error)
 		goto out;
 
@@ -179,24 +181,25 @@ scrub_inode(
 	if (S_ISLNK(bstat->bs_mode) || !bstat->bs_mode) {
 		/* Check symlink contents. */
 		error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_SYMLINK,
-				&alist);
+				&alist, &sri);
 		if (error)
 			goto out;
 	}
 	if (S_ISDIR(bstat->bs_mode) || !bstat->bs_mode) {
 		/* Check the directory entries. */
-		error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_DIR, &alist);
+		error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_DIR, &alist,
+				&sri);
 		if (error)
 			goto out;
 	}
 
 	/* Check all the extended attributes. */
-	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_XATTR, &alist);
+	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_XATTR, &alist, &sri);
 	if (error)
 		goto out;
 
 	/* Check parent pointers. */
-	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_PARENT, &alist);
+	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_PARENT, &alist, &sri);
 	if (error)
 		goto out;
 
diff --git a/scrub/phase4.c b/scrub/phase4.c
index d01dc89f44f..1c4aab996ab 100644
--- a/scrub/phase4.c
+++ b/scrub/phase4.c
@@ -130,6 +130,7 @@ phase4_func(
 {
 	struct xfs_fsop_geom	fsgeom;
 	struct action_list	alist;
+	struct scrub_item	sri;
 	int			ret;
 
 	if (!have_action_items(ctx))
@@ -142,8 +143,9 @@ phase4_func(
 	 * chance that repairs of primary metadata fail due to secondary
 	 * metadata.  If repairs fails, we'll come back during phase 7.
 	 */
+	scrub_item_init_fs(&sri);
 	action_list_init(&alist);
-	ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_FSCOUNTERS, 0, &alist);
+	ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_FSCOUNTERS, 0, &alist, &sri);
 	if (ret)
 		return ret;
 
@@ -159,7 +161,7 @@ phase4_func(
 
 	if (fsgeom.sick & XFS_FSOP_GEOM_SICK_QUOTACHECK) {
 		ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_QUOTACHECK, 0,
-				&alist);
+				&alist, &sri);
 		if (ret)
 			return ret;
 	}
diff --git a/scrub/phase5.c b/scrub/phase5.c
index 68d35cd5852..ace6c3a9843 100644
--- a/scrub/phase5.c
+++ b/scrub/phase5.c
@@ -385,6 +385,7 @@ check_fs_label(
 }
 
 struct fs_scan_item {
+	struct scrub_item	sri;
 	struct action_list	alist;
 	bool			*abortedp;
 	unsigned int		scrub_type;
@@ -412,7 +413,8 @@ fs_scan_worker(
 		nanosleep(&tv, NULL);
 	}
 
-	ret = scrub_meta_type(ctx, item->scrub_type, 0, &item->alist);
+	ret = scrub_meta_type(ctx, item->scrub_type, 0, &item->alist,
+			&item->sri);
 	if (ret) {
 		str_liberror(ctx, ret, _("checking fs scan metadata"));
 		*item->abortedp = true;
@@ -450,6 +452,7 @@ queue_fs_scan(
 		str_liberror(ctx, ret, _("setting up fs scan"));
 		return ret;
 	}
+	scrub_item_init_fs(&item->sri);
 	action_list_init(&item->alist);
 	item->scrub_type = scrub_type;
 	item->abortedp = abortedp;
diff --git a/scrub/phase7.c b/scrub/phase7.c
index 820a68f99a4..314a886b091 100644
--- a/scrub/phase7.c
+++ b/scrub/phase7.c
@@ -99,6 +99,7 @@ phase7_func(
 	struct scrub_ctx	*ctx)
 {
 	struct summary_counts	totalcount = {0};
+	struct scrub_item	sri;
 	struct action_list	alist;
 	struct ptvar		*ptvar;
 	unsigned long long	used_data;
@@ -117,8 +118,9 @@ phase7_func(
 	int			error;
 
 	/* Check and fix the summary metadata. */
+	scrub_item_init_fs(&sri);
 	action_list_init(&alist);
-	error = scrub_summary_metadata(ctx, &alist);
+	error = scrub_summary_metadata(ctx, &alist, &sri);
 	if (error)
 		return error;
 	error = action_list_process(ctx, -1, &alist,
diff --git a/scrub/scrub.c b/scrub/scrub.c
index 6e857c79dfb..e242e38ed0c 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -264,7 +264,8 @@ scrub_meta_type(
 	struct scrub_ctx		*ctx,
 	unsigned int			type,
 	xfs_agnumber_t			agno,
-	struct action_list		*alist)
+	struct action_list		*alist,
+	struct scrub_item		*sri)
 {
 	struct xfs_scrub_metadata	meta = {
 		.sm_type		= type,
@@ -283,11 +284,13 @@ scrub_meta_type(
 	case CHECK_ABORT:
 		return ECANCELED;
 	case CHECK_REPAIR:
+		scrub_item_save_state(sri, type, meta.sm_flags);
 		ret = scrub_save_repair(ctx, alist, &meta);
 		if (ret)
 			return ret;
 		fallthrough;
 	case CHECK_DONE:
+		scrub_item_clean_state(sri, type);
 		return 0;
 	default:
 		/* CHECK_RETRY should never happen. */
@@ -305,7 +308,8 @@ scrub_group(
 	struct scrub_ctx		*ctx,
 	enum xfrog_scrub_group		group,
 	xfs_agnumber_t			agno,
-	struct action_list		*alist)
+	struct action_list		*alist,
+	struct scrub_item		*sri)
 {
 	const struct xfrog_scrub_descr	*sc;
 	unsigned int			type;
@@ -317,7 +321,7 @@ scrub_group(
 		if (sc->group != group)
 			continue;
 
-		ret = scrub_meta_type(ctx, type, agno, alist);
+		ret = scrub_meta_type(ctx, type, agno, alist, sri);
 		if (ret)
 			return ret;
 	}
@@ -330,9 +334,10 @@ int
 scrub_ag_headers(
 	struct scrub_ctx		*ctx,
 	xfs_agnumber_t			agno,
-	struct action_list		*alist)
+	struct action_list		*alist,
+	struct scrub_item		*sri)
 {
-	return scrub_group(ctx, XFROG_SCRUB_GROUP_AGHEADER, agno, alist);
+	return scrub_group(ctx, XFROG_SCRUB_GROUP_AGHEADER, agno, alist, sri);
 }
 
 /* Scrub each AG's metadata btrees. */
@@ -340,9 +345,10 @@ int
 scrub_ag_metadata(
 	struct scrub_ctx		*ctx,
 	xfs_agnumber_t			agno,
-	struct action_list		*alist)
+	struct action_list		*alist,
+	struct scrub_item		*sri)
 {
-	return scrub_group(ctx, XFROG_SCRUB_GROUP_PERAG, agno, alist);
+	return scrub_group(ctx, XFROG_SCRUB_GROUP_PERAG, agno, alist, sri);
 }
 
 /* Scrub whole-filesystem metadata. */
@@ -350,20 +356,22 @@ int
 scrub_fs_metadata(
 	struct scrub_ctx		*ctx,
 	unsigned int			type,
-	struct action_list		*alist)
+	struct action_list		*alist,
+	struct scrub_item		*sri)
 {
 	ASSERT(xfrog_scrubbers[type].group == XFROG_SCRUB_GROUP_FS);
 
-	return scrub_meta_type(ctx, type, 0, alist);
+	return scrub_meta_type(ctx, type, 0, alist, sri);
 }
 
 /* Scrub all FS summary metadata. */
 int
 scrub_summary_metadata(
 	struct scrub_ctx		*ctx,
-	struct action_list		*alist)
+	struct action_list		*alist,
+	struct scrub_item		*sri)
 {
-	return scrub_group(ctx, XFROG_SCRUB_GROUP_SUMMARY, 0, alist);
+	return scrub_group(ctx, XFROG_SCRUB_GROUP_SUMMARY, 0, alist, sri);
 }
 
 /* How many items do we have to check? */
@@ -425,7 +433,8 @@ scrub_file(
 	int				fd,
 	const struct xfs_bulkstat	*bstat,
 	unsigned int			type,
-	struct action_list		*alist)
+	struct action_list		*alist,
+	struct scrub_item		*sri)
 {
 	struct xfs_scrub_metadata	meta = {0};
 	struct xfs_fd			xfd;
@@ -454,12 +463,45 @@ scrub_file(
 	fix = xfs_check_metadata(ctx, xfdp, &meta, true);
 	if (fix == CHECK_ABORT)
 		return ECANCELED;
-	if (fix == CHECK_DONE)
+	if (fix == CHECK_DONE) {
+		scrub_item_clean_state(sri, type);
 		return 0;
+	}
 
+	scrub_item_save_state(sri, type, meta.sm_flags);
 	return scrub_save_repair(ctx, alist, &meta);
 }
 
+/* Dump a scrub item for debugging purposes. */
+void
+scrub_item_dump(
+	struct scrub_item	*sri,
+	unsigned int		group_mask,
+	const char		*tag)
+{
+	unsigned int		i;
+
+	if (group_mask == 0)
+		group_mask = -1U;
+
+	printf("DUMP SCRUB ITEM FOR %s\n", tag);
+	if (sri->sri_ino != -1ULL)
+		printf("ino 0x%llx gen %u\n", (unsigned long long)sri->sri_ino,
+				sri->sri_gen);
+	if (sri->sri_agno != -1U)
+		printf("agno %u\n", sri->sri_agno);
+
+	foreach_scrub_type(i) {
+		unsigned int	g = 1U << xfrog_scrubbers[i].group;
+
+		if (g & group_mask)
+			printf("[%u]: type '%s' state 0x%x\n", i,
+					xfrog_scrubbers[i].name,
+					sri->sri_state[i]);
+	}
+	fflush(stdout);
+}
+
 /*
  * Test the availability of a kernel scrub command.  If errors occur (or the
  * scrub ioctl is rejected) the errors will be logged and this function will
diff --git a/scrub/scrub.h b/scrub/scrub.h
index 98819a25b62..21ea4147e0f 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -16,17 +16,85 @@ enum check_outcome {
 
 struct action_item;
 
+/*
+ * These flags record the metadata object state that the kernel returned.
+ * We want to remember if the object was corrupt, if the cross-referencing
+ * revealed inconsistencies (xcorrupt), if the cross referencing itself failed
+ * (xfail) or if the object is correct but could be optimised (preen).
+ */
+#define SCRUB_ITEM_CORRUPT	(XFS_SCRUB_OFLAG_CORRUPT)	/* (1 << 1) */
+#define SCRUB_ITEM_PREEN	(XFS_SCRUB_OFLAG_PREEN)		/* (1 << 2) */
+#define SCRUB_ITEM_XFAIL	(XFS_SCRUB_OFLAG_XFAIL)		/* (1 << 3) */
+#define SCRUB_ITEM_XCORRUPT	(XFS_SCRUB_OFLAG_XCORRUPT)	/* (1 << 4) */
+
+/* All of the state flags that we need to prioritize repair work. */
+#define SCRUB_ITEM_REPAIR_ANY	(SCRUB_ITEM_CORRUPT | \
+				 SCRUB_ITEM_PREEN | \
+				 SCRUB_ITEM_XFAIL | \
+				 SCRUB_ITEM_XCORRUPT)
+
+struct scrub_item {
+	/*
+	 * Information we need to call the scrub and repair ioctls.  Per-AG
+	 * items should set the ino/gen fields to -1; per-inode items should
+	 * set sri_agno to -1; and per-fs items should set all three fields to
+	 * -1.  Or use the macros below.
+	 */
+	__u64			sri_ino;
+	__u32			sri_gen;
+	__u32			sri_agno;
+
+	/* Scrub item state flags, one for each XFS_SCRUB_TYPE. */
+	__u8			sri_state[XFS_SCRUB_TYPE_NR];
+};
+
+#define foreach_scrub_type(loopvar) \
+	for ((loopvar) = 0; (loopvar) < XFS_SCRUB_TYPE_NR; (loopvar)++)
+
+static inline void
+scrub_item_init_ag(struct scrub_item *sri, xfs_agnumber_t agno)
+{
+	memset(sri, 0, sizeof(*sri));
+	sri->sri_agno = agno;
+	sri->sri_ino = -1ULL;
+	sri->sri_gen = -1U;
+}
+
+static inline void
+scrub_item_init_fs(struct scrub_item *sri)
+{
+	memset(sri, 0, sizeof(*sri));
+	sri->sri_agno = -1U;
+	sri->sri_ino = -1ULL;
+	sri->sri_gen = -1U;
+}
+
+static inline void
+scrub_item_init_file(struct scrub_item *sri, const struct xfs_bulkstat *bstat)
+{
+	memset(sri, 0, sizeof(*sri));
+	sri->sri_agno = -1U;
+	sri->sri_ino = bstat->bs_ino;
+	sri->sri_gen = bstat->bs_gen;
+}
+
+void scrub_item_dump(struct scrub_item *sri, unsigned int group_mask,
+		const char *tag);
+
 void scrub_report_preen_triggers(struct scrub_ctx *ctx);
 int scrub_ag_headers(struct scrub_ctx *ctx, xfs_agnumber_t agno,
-		struct action_list *alist);
+		struct action_list *alist, struct scrub_item *sri);
 int scrub_ag_metadata(struct scrub_ctx *ctx, xfs_agnumber_t agno,
-		struct action_list *alist);
+		struct action_list *alist, struct scrub_item *sri);
 int scrub_fs_metadata(struct scrub_ctx *ctx, unsigned int scrub_type,
-		struct action_list *alist);
-int scrub_iscan_metadata(struct scrub_ctx *ctx, struct action_list *alist);
-int scrub_summary_metadata(struct scrub_ctx *ctx, struct action_list *alist);
+		struct action_list *alist, struct scrub_item *sri);
+int scrub_iscan_metadata(struct scrub_ctx *ctx, struct action_list *alist,
+		struct scrub_item *sri);
+int scrub_summary_metadata(struct scrub_ctx *ctx, struct action_list *alist,
+		struct scrub_item *sri);
 int scrub_meta_type(struct scrub_ctx *ctx, unsigned int type,
-		xfs_agnumber_t agno, struct action_list *alist);
+		xfs_agnumber_t agno, struct action_list *alist,
+		struct scrub_item *sri);
 
 bool can_scrub_fs_metadata(struct scrub_ctx *ctx);
 bool can_scrub_inode(struct scrub_ctx *ctx);
@@ -39,7 +107,8 @@ bool can_repair(struct scrub_ctx *ctx);
 bool can_force_rebuild(struct scrub_ctx *ctx);
 
 int scrub_file(struct scrub_ctx *ctx, int fd, const struct xfs_bulkstat *bstat,
-		unsigned int type, struct action_list *alist);
+		unsigned int type, struct action_list *alist,
+		struct scrub_item *sri);
 
 /* Repair parameters are the scrub inputs and retry count. */
 struct action_item {
diff --git a/scrub/scrub_private.h b/scrub/scrub_private.h
index a24d485a286..090efb54c0a 100644
--- a/scrub/scrub_private.h
+++ b/scrub/scrub_private.h
@@ -52,4 +52,23 @@ static inline bool needs_repair(struct xfs_scrub_metadata *sm)
 void scrub_warn_incomplete_scrub(struct scrub_ctx *ctx, struct descr *dsc,
 		struct xfs_scrub_metadata *meta);
 
+/* Scrub item functions */
+
+static inline void
+scrub_item_save_state(
+	struct scrub_item		*sri,
+	unsigned  int			scrub_type,
+	unsigned  int			scrub_flags)
+{
+	sri->sri_state[scrub_type] = scrub_flags & SCRUB_ITEM_REPAIR_ANY;
+}
+
+static inline void
+scrub_item_clean_state(
+	struct scrub_item		*sri,
+	unsigned  int			scrub_type)
+{
+	sri->sri_state[scrub_type] = 0;
+}
+
 #endif /* XFS_SCRUB_SCRUB_PRIVATE_H_ */

[PATCH 2/9] xfs_scrub: use repair_item to direct repair activities

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Now that the new scrub_item tracks the state of any filesystem object
needing any kind of repair, use it to drive filesystem repairs and
updates to the in-kernel health status when repair finishes.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase1.c |    2 
 scrub/phase2.c |   24 ++--
 scrub/phase3.c |   57 ++++----
 scrub/phase4.c |    7 -
 scrub/phase5.c |    2 
 scrub/phase7.c |    3 
 scrub/repair.c |  381 +++++++++++++++++++++++++++++++-------------------------
 scrub/repair.h |   45 +++++--
 scrub/scrub.c  |   44 ------
 scrub/scrub.h  |   12 --
 10 files changed, 298 insertions(+), 279 deletions(-)


diff --git a/scrub/phase1.c b/scrub/phase1.c
index 9920f29a693..b1bbc694e64 100644
--- a/scrub/phase1.c
+++ b/scrub/phase1.c
@@ -71,7 +71,7 @@ report_to_kernel(
 	 * Complain if we cannot fail the clean bill of health, unless we're
 	 * just testing repairs.
 	 */
-	if (action_list_length(&alist) > 0 &&
+	if (repair_item_count_needsrepair(&sri) != 0 &&
 	    !debug_tweak_on("XFS_SCRUB_FORCE_REPAIR")) {
 		str_info(ctx, _("Couldn't upload clean bill of health."), NULL);
 		action_list_discard(&alist);
diff --git a/scrub/phase2.c b/scrub/phase2.c
index 518923d6628..26ce5818030 100644
--- a/scrub/phase2.c
+++ b/scrub/phase2.c
@@ -58,6 +58,7 @@ scan_ag_metadata(
 	void				*arg)
 {
 	struct scrub_item		sri;
+	struct scrub_item		fix_now;
 	struct scrub_ctx		*ctx = (struct scrub_ctx *)wq->wq_ctx;
 	struct scan_ctl			*sctl = arg;
 	struct action_list		alist;
@@ -83,7 +84,7 @@ scan_ag_metadata(
 		goto err;
 
 	/* Repair header damage. */
-	ret = action_list_process_or_defer(ctx, agno, &alist);
+	ret = repair_item_corruption(ctx, &sri);
 	if (ret)
 		goto err;
 
@@ -99,17 +100,19 @@ scan_ag_metadata(
 	 * the inobt from rmapbt data, but if the rmapbt is broken even
 	 * at this early phase then we are sunk.
 	 */
-	difficulty = action_list_difficulty(&alist);
-	action_list_find_mustfix(&alist, &immediate_alist);
+	difficulty = repair_item_difficulty(&sri);
+	repair_item_mustfix(&sri, &fix_now);
 	warn_repair_difficulties(ctx, difficulty, descr);
 
 	/* Repair (inode) btree damage. */
-	ret = action_list_process_or_defer(ctx, agno, &immediate_alist);
+	ret = repair_item_corruption(ctx, &fix_now);
 	if (ret)
 		goto err;
 
 	/* Everything else gets fixed during phase 4. */
-	action_list_defer(ctx, agno, &alist);
+	ret = repair_item_defer(ctx, &sri);
+	if (ret)
+		goto err;
 	return;
 err:
 	sctl->aborted = true;
@@ -141,10 +144,14 @@ scan_fs_metadata(
 	}
 
 	/* Complain about metadata corruptions that might not be fixable. */
-	difficulty = action_list_difficulty(&alist);
+	difficulty = repair_item_difficulty(&sri);
 	warn_repair_difficulties(ctx, difficulty, xfrog_scrubbers[type].descr);
 
-	action_list_defer(ctx, 0, &alist);
+	ret = repair_item_defer(ctx, &sri);
+	if (ret) {
+		sctl->aborted = true;
+		goto out;
+	}
 
 out:
 	if (type == XFS_SCRUB_TYPE_RTBITMAP) {
@@ -193,8 +200,7 @@ phase2_func(
 	ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_SB, 0, &alist, &sri);
 	if (ret)
 		goto out_wq;
-	ret = action_list_process(ctx, -1, &alist,
-			XRM_FINAL_WARNING | XRM_NOPROGRESS);
+	ret = repair_item_completely(ctx, &sri);
 	if (ret)
 		goto out_wq;
 
diff --git a/scrub/phase3.c b/scrub/phase3.c
index 642b8406e5b..e602d8c7ec4 100644
--- a/scrub/phase3.c
+++ b/scrub/phase3.c
@@ -55,45 +55,48 @@ report_close_error(
  * Defer all the repairs until phase 4, being careful about locking since the
  * inode scrub threads are not per-AG.
  */
-static void
+static int
 defer_inode_repair(
-	struct scrub_inode_ctx	*ictx,
-	xfs_agnumber_t		agno,
-	struct action_list	*alist)
+	struct scrub_inode_ctx		*ictx,
+	const struct xfs_bulkstat	*bstat,
+	struct scrub_item		*sri)
 {
-	if (alist->nr == 0)
-		return;
+	struct action_item		*aitem = NULL;
+	xfs_agnumber_t			agno;
+	int				ret;
 
+	ret = repair_item_to_action_item(ictx->ctx, sri, &aitem);
+	if (ret || !aitem)
+		return ret;
+
+	agno = cvt_ino_to_agno(&ictx->ctx->mnt, bstat->bs_ino);
 	pthread_mutex_lock(&ictx->locks[agno]);
-	action_list_defer(ictx->ctx, agno, alist);
+	action_list_add(&ictx->ctx->action_lists[agno], aitem);
 	pthread_mutex_unlock(&ictx->locks[agno]);
+	return 0;
 }
 
-/* Run repair actions now and defer unfinished items for later. */
+/* Run repair actions now and leave unfinished items for later. */
 static int
 try_inode_repair(
-	struct scrub_inode_ctx	*ictx,
-	int			fd,
-	xfs_agnumber_t		agno,
-	struct action_list	*alist)
+	struct scrub_inode_ctx		*ictx,
+	struct scrub_item		*sri,
+	int				fd,
+	const struct xfs_bulkstat	*bstat)
 {
-	int			ret;
-
 	/*
 	 * If at the start of phase 3 we already had ag/rt metadata repairs
 	 * queued up for phase 4, leave the action list untouched so that file
-	 * metadata repairs will be deferred in scan order until phase 4.
+	 * metadata repairs will be deferred until phase 4.
 	 */
 	if (ictx->always_defer_repairs)
 		return 0;
 
-	ret = action_list_process(ictx->ctx, fd, alist,
-			XRM_REPAIR_ONLY | XRM_NOPROGRESS);
-	if (ret)
-		return ret;
-
-	defer_inode_repair(ictx, agno, alist);
-	return 0;
+	/*
+	 * Try to repair the file metadata.  Unfixed metadata will remain in
+	 * the scrub item state to be queued as a single action item.
+	 */
+	return repair_file_corruption(ictx->ctx, sri, fd);
 }
 
 /* Verify the contents, xattrs, and extent maps of an inode. */
@@ -108,13 +111,11 @@ scrub_inode(
 	struct scrub_item	sri;
 	struct scrub_inode_ctx	*ictx = arg;
 	struct ptcounter	*icount = ictx->icount;
-	xfs_agnumber_t		agno;
 	int			fd = -1;
 	int			error;
 
 	scrub_item_init_file(&sri, bstat);
 	action_list_init(&alist);
-	agno = cvt_ino_to_agno(&ctx->mnt, bstat->bs_ino);
 	background_sleep();
 
 	/*
@@ -149,7 +150,7 @@ scrub_inode(
 	if (error)
 		goto out;
 
-	error = try_inode_repair(ictx, fd, agno, &alist);
+	error = try_inode_repair(ictx, &sri, fd, bstat);
 	if (error)
 		goto out;
 
@@ -164,7 +165,7 @@ scrub_inode(
 	if (error)
 		goto out;
 
-	error = try_inode_repair(ictx, fd, agno, &alist);
+	error = try_inode_repair(ictx, &sri, fd, bstat);
 	if (error)
 		goto out;
 
@@ -204,7 +205,7 @@ scrub_inode(
 		goto out;
 
 	/* Try to repair the file while it's open. */
-	error = try_inode_repair(ictx, fd, agno, &alist);
+	error = try_inode_repair(ictx, &sri, fd, bstat);
 	if (error)
 		goto out;
 
@@ -221,7 +222,7 @@ scrub_inode(
 	progress_add(1);
 
 	if (!error && !ictx->aborted)
-		defer_inode_repair(ictx, agno, &alist);
+		error = defer_inode_repair(ictx, bstat, &sri);
 
 	if (fd >= 0) {
 		int	err2;
diff --git a/scrub/phase4.c b/scrub/phase4.c
index 1c4aab996ab..98518635b2b 100644
--- a/scrub/phase4.c
+++ b/scrub/phase4.c
@@ -40,7 +40,7 @@ repair_ag(
 
 	/* Repair anything broken until we fail to make progress. */
 	do {
-		ret = action_list_process(ctx, -1, alist, flags);
+		ret = action_list_process(ctx, alist, flags);
 		if (ret) {
 			*aborted = true;
 			return;
@@ -55,7 +55,7 @@ repair_ag(
 
 	/* Try once more, but this time complain if we can't fix things. */
 	flags |= XRM_FINAL_WARNING;
-	ret = action_list_process(ctx, -1, alist, flags);
+	ret = action_list_process(ctx, alist, flags);
 	if (ret)
 		*aborted = true;
 }
@@ -167,8 +167,7 @@ phase4_func(
 	}
 
 	/* Repair counters before starting on the rest. */
-	ret = action_list_process(ctx, -1, &alist,
-			XRM_REPAIR_ONLY | XRM_NOPROGRESS);
+	ret = repair_item_corruption(ctx, &sri);
 	if (ret)
 		return ret;
 	action_list_discard(&alist);
diff --git a/scrub/phase5.c b/scrub/phase5.c
index ace6c3a9843..79bfea8f6b5 100644
--- a/scrub/phase5.c
+++ b/scrub/phase5.c
@@ -421,7 +421,7 @@ fs_scan_worker(
 		goto out;
 	}
 
-	ret = action_list_process(ctx, ctx->mnt.fd, &item->alist,
+	ret = action_list_process(ctx, &item->alist,
 			XRM_FINAL_WARNING | XRM_NOPROGRESS);
 	if (ret) {
 		str_liberror(ctx, ret, _("repairing fs scan metadata"));
diff --git a/scrub/phase7.c b/scrub/phase7.c
index 314a886b091..404bfb82243 100644
--- a/scrub/phase7.c
+++ b/scrub/phase7.c
@@ -123,8 +123,7 @@ phase7_func(
 	error = scrub_summary_metadata(ctx, &alist, &sri);
 	if (error)
 		return error;
-	error = action_list_process(ctx, -1, &alist,
-			XRM_FINAL_WARNING | XRM_NOPROGRESS);
+	error = repair_item_completely(ctx, &sri);
 	if (error)
 		return error;
 
diff --git a/scrub/repair.c b/scrub/repair.c
index 30817d268d6..6e09c592ed4 100644
--- a/scrub/repair.c
+++ b/scrub/repair.c
@@ -27,7 +27,8 @@ static enum check_outcome
 xfs_repair_metadata(
 	struct scrub_ctx		*ctx,
 	struct xfs_fd			*xfdp,
-	struct action_item		*aitem,
+	unsigned int			scrub_type,
+	struct scrub_item		*sri,
 	unsigned int			repair_flags)
 {
 	struct xfs_scrub_metadata	meta = { 0 };
@@ -35,20 +36,20 @@ xfs_repair_metadata(
 	DEFINE_DESCR(dsc, ctx, format_scrub_descr);
 	int				error;
 
-	assert(aitem->type < XFS_SCRUB_TYPE_NR);
+	assert(scrub_type < XFS_SCRUB_TYPE_NR);
 	assert(!debug_tweak_on("XFS_SCRUB_NO_KERNEL"));
-	meta.sm_type = aitem->type;
-	meta.sm_flags = aitem->flags | XFS_SCRUB_IFLAG_REPAIR;
+	meta.sm_type = scrub_type;
+	meta.sm_flags = XFS_SCRUB_IFLAG_REPAIR;
 	if (use_force_rebuild)
 		meta.sm_flags |= XFS_SCRUB_IFLAG_FORCE_REBUILD;
-	switch (xfrog_scrubbers[aitem->type].group) {
+	switch (xfrog_scrubbers[scrub_type].group) {
 	case XFROG_SCRUB_GROUP_AGHEADER:
 	case XFROG_SCRUB_GROUP_PERAG:
-		meta.sm_agno = aitem->agno;
+		meta.sm_agno = sri->sri_agno;
 		break;
 	case XFROG_SCRUB_GROUP_INODE:
-		meta.sm_ino = aitem->ino;
-		meta.sm_gen = aitem->gen;
+		meta.sm_ino = sri->sri_ino;
+		meta.sm_gen = sri->sri_gen;
 		break;
 	default:
 		break;
@@ -58,9 +59,10 @@ xfs_repair_metadata(
 		return CHECK_RETRY;
 
 	memcpy(&oldm, &meta, sizeof(oldm));
+	oldm.sm_flags = sri->sri_state[scrub_type] & SCRUB_ITEM_REPAIR_ANY;
 	descr_set(&dsc, &oldm);
 
-	if (needs_repair(&meta))
+	if (needs_repair(&oldm))
 		str_info(ctx, descr_render(&dsc), _("Attempting repair."));
 	else if (debug || verbose)
 		str_info(ctx, descr_render(&dsc),
@@ -92,8 +94,10 @@ _("Filesystem is shut down, aborting."));
 		 * it done and move on.
 		 */
 		if (is_unoptimized(&oldm) ||
-		    debug_tweak_on("XFS_SCRUB_FORCE_REPAIR"))
+		    debug_tweak_on("XFS_SCRUB_FORCE_REPAIR")) {
+			scrub_item_clean_state(sri, scrub_type);
 			return CHECK_DONE;
+		}
 		/*
 		 * If we're in no-complain mode, requeue the check for
 		 * later.  It's possible that an error in another
@@ -109,6 +113,7 @@ _("Filesystem is shut down, aborting."));
 		/* Kernel doesn't know how to repair this? */
 		str_corrupt(ctx, descr_render(&dsc),
 _("Don't know how to fix; offline repair required."));
+		scrub_item_clean_state(sri, scrub_type);
 		return CHECK_DONE;
 	case EROFS:
 		/* Read-only filesystem, can't fix. */
@@ -118,23 +123,28 @@ _("Read-only filesystem; cannot make changes."));
 		return CHECK_ABORT;
 	case ENOENT:
 		/* Metadata not present, just skip it. */
+		scrub_item_clean_state(sri, scrub_type);
 		return CHECK_DONE;
 	case ENOMEM:
 	case ENOSPC:
 		/* Don't care if preen fails due to low resources. */
-		if (is_unoptimized(&oldm) && !needs_repair(&oldm))
+		if (is_unoptimized(&oldm) && !needs_repair(&oldm)) {
+			scrub_item_clean_state(sri, scrub_type);
 			return CHECK_DONE;
+		}
 		fallthrough;
 	default:
 		/*
-		 * Operational error.  If the caller doesn't want us
-		 * to complain about repair failures, tell the caller
-		 * to requeue the repair for later and don't say a
-		 * thing.  Otherwise, print error and bail out.
+		 * Operational error.  If the caller doesn't want us to
+		 * complain about repair failures, tell the caller to requeue
+		 * the repair for later and don't say a thing.  Otherwise,
+		 * print an error, mark the item clean because we're done with
+		 * trying to repair it, and bail out.
 		 */
 		if (!(repair_flags & XRM_FINAL_WARNING))
 			return CHECK_RETRY;
 		str_liberror(ctx, error, descr_render(&dsc));
+		scrub_item_clean_state(sri, scrub_type);
 		return CHECK_DONE;
 	}
 
@@ -186,12 +196,13 @@ _("Repair unsuccessful; offline repair required."));
 			record_preen(ctx, descr_render(&dsc),
  _("Optimization successful."));
 	}
+
+	scrub_item_clean_state(sri, scrub_type);
 	return CHECK_DONE;
 }
 
 /*
  * Prioritize action items in order of how long we can wait.
- * 0 = do it now, 10000 = do it later.
  *
  * To minimize the amount of repair work, we want to prioritize metadata
  * objects by perceived corruptness.  If CORRUPT is set, the fields are
@@ -207,104 +218,34 @@ _("Repair unsuccessful; offline repair required."));
  * in order.
  */
 
-/* Sort action items in severity order. */
-static int
-PRIO(
-	const struct action_item *aitem,
-	int			order)
-{
-	if (aitem->flags & XFS_SCRUB_OFLAG_CORRUPT)
-		return order;
-	else if (aitem->flags & XFS_SCRUB_OFLAG_XCORRUPT)
-		return 100 + order;
-	else if (aitem->flags & XFS_SCRUB_OFLAG_XFAIL)
-		return 200 + order;
-	else if (aitem->flags & XFS_SCRUB_OFLAG_PREEN)
-		return 300 + order;
-	abort();
-}
-
-/* Sort the repair items in dependency order. */
-static int
-xfs_action_item_priority(
-	const struct action_item	*aitem)
-{
-	switch (aitem->type) {
-	case XFS_SCRUB_TYPE_SB:
-	case XFS_SCRUB_TYPE_AGF:
-	case XFS_SCRUB_TYPE_AGFL:
-	case XFS_SCRUB_TYPE_AGI:
-	case XFS_SCRUB_TYPE_BNOBT:
-	case XFS_SCRUB_TYPE_CNTBT:
-	case XFS_SCRUB_TYPE_INOBT:
-	case XFS_SCRUB_TYPE_FINOBT:
-	case XFS_SCRUB_TYPE_REFCNTBT:
-	case XFS_SCRUB_TYPE_RMAPBT:
-	case XFS_SCRUB_TYPE_INODE:
-	case XFS_SCRUB_TYPE_BMBTD:
-	case XFS_SCRUB_TYPE_BMBTA:
-	case XFS_SCRUB_TYPE_BMBTC:
-		return PRIO(aitem, aitem->type - 1);
-	case XFS_SCRUB_TYPE_DIR:
-	case XFS_SCRUB_TYPE_XATTR:
-	case XFS_SCRUB_TYPE_SYMLINK:
-	case XFS_SCRUB_TYPE_PARENT:
-		return PRIO(aitem, XFS_SCRUB_TYPE_DIR);
-	case XFS_SCRUB_TYPE_RTBITMAP:
-	case XFS_SCRUB_TYPE_RTSUM:
-		return PRIO(aitem, XFS_SCRUB_TYPE_RTBITMAP);
-	case XFS_SCRUB_TYPE_UQUOTA:
-	case XFS_SCRUB_TYPE_GQUOTA:
-	case XFS_SCRUB_TYPE_PQUOTA:
-		return PRIO(aitem, XFS_SCRUB_TYPE_UQUOTA);
-	case XFS_SCRUB_TYPE_QUOTACHECK:
-		/* This should always go after [UGP]QUOTA no matter what. */
-		return PRIO(aitem, aitem->type);
-	case XFS_SCRUB_TYPE_FSCOUNTERS:
-		/* This should always go after AG headers no matter what. */
-		return PRIO(aitem, INT_MAX);
-	}
-	abort();
-}
-
-/* Make sure that btrees get repaired before headers. */
-static int
-xfs_action_item_compare(
-	void				*priv,
-	const struct list_head		*a,
-	const struct list_head		*b)
-{
-	const struct action_item	*ra;
-	const struct action_item	*rb;
-
-	ra = container_of(a, struct action_item, list);
-	rb = container_of(b, struct action_item, list);
-
-	return xfs_action_item_priority(ra) - xfs_action_item_priority(rb);
-}
+struct action_item {
+	struct list_head	list;
+	struct scrub_item	sri;
+};
 
 /*
  * Figure out which AG metadata must be fixed before we can move on
  * to the inode scan.
  */
 void
-action_list_find_mustfix(
-	struct action_list		*alist,
-	struct action_list		*immediate_alist)
+repair_item_mustfix(
+	struct scrub_item	*sri,
+	struct scrub_item	*fix_now)
 {
-	struct action_item		*n;
-	struct action_item		*aitem;
+	unsigned int		scrub_type;
 
-	list_for_each_entry_safe(aitem, n, &alist->list, list) {
-		if (!(aitem->flags & XFS_SCRUB_OFLAG_CORRUPT))
+	assert(sri->sri_agno != -1U);
+	scrub_item_init_ag(fix_now, sri->sri_agno);
+
+	foreach_scrub_type(scrub_type) {
+		if (!(sri->sri_state[scrub_type] & SCRUB_ITEM_CORRUPT))
 			continue;
-		switch (aitem->type) {
+
+		switch (scrub_type) {
 		case XFS_SCRUB_TYPE_AGI:
 		case XFS_SCRUB_TYPE_FINOBT:
 		case XFS_SCRUB_TYPE_INOBT:
-			alist->nr--;
-			list_move_tail(&aitem->list, &immediate_alist->list);
-			immediate_alist->nr++;
+			fix_now->sri_state[scrub_type] |= SCRUB_ITEM_CORRUPT;
 			break;
 		}
 	}
@@ -312,19 +253,19 @@ action_list_find_mustfix(
 
 /* Determine if primary or secondary metadata are inconsistent. */
 unsigned int
-action_list_difficulty(
-	const struct action_list	*alist)
+repair_item_difficulty(
+	const struct scrub_item	*sri)
 {
-	struct action_item		*aitem, *n;
-	unsigned int			ret = 0;
+	unsigned int		scrub_type;
+	unsigned int		ret = 0;
 
-	list_for_each_entry_safe(aitem, n, &alist->list, list) {
-		if (!(aitem->flags & (XFS_SCRUB_OFLAG_CORRUPT |
-				      XFS_SCRUB_OFLAG_XCORRUPT |
-				      XFS_SCRUB_OFLAG_XFAIL)))
+	foreach_scrub_type(scrub_type) {
+		if (!(sri->sri_state[scrub_type] & (XFS_SCRUB_OFLAG_CORRUPT |
+						    XFS_SCRUB_OFLAG_XCORRUPT |
+						    XFS_SCRUB_OFLAG_XFAIL)))
 			continue;
 
-		switch (aitem->type) {
+		switch (scrub_type) {
 		case XFS_SCRUB_TYPE_RMAPBT:
 			ret |= REPAIR_DIFFICULTY_SECONDARY;
 			break;
@@ -404,13 +345,19 @@ action_list_init(
 	alist->sorted = false;
 }
 
-/* Number of repairs in this list. */
+/* Number of pending repairs in this list. */
 unsigned long long
 action_list_length(
 	struct action_list		*alist)
 {
-	return alist->nr;
-};
+	struct action_item		*aitem;
+	unsigned long long		ret = 0;
+
+	list_for_each_entry(aitem, &alist->list, list)
+		ret += repair_item_count_needsrepair(&aitem->sri);
+
+	return ret;
+}
 
 /* Add to the list of repairs. */
 void
@@ -423,60 +370,78 @@ action_list_add(
 	alist->sorted = false;
 }
 
-/* Splice two repair lists. */
-void
-action_list_splice(
-	struct action_list		*dest,
-	struct action_list		*src)
-{
-	if (src->nr == 0)
-		return;
-
-	list_splice_tail_init(&src->list, &dest->list);
-	dest->nr += src->nr;
-	src->nr = 0;
-	dest->sorted = false;
-}
-
 /* Repair everything on this list. */
 int
 action_list_process(
 	struct scrub_ctx		*ctx,
-	int				fd,
 	struct action_list		*alist,
 	unsigned int			repair_flags)
+{
+	struct action_item		*aitem;
+	struct action_item		*n;
+	int				ret;
+
+	list_for_each_entry_safe(aitem, n, &alist->list, list) {
+		if (scrub_excessive_errors(ctx))
+			return ECANCELED;
+
+		ret = repair_item(ctx, &aitem->sri, repair_flags);
+		if (ret)
+			break;
+
+		if (repair_item_count_needsrepair(&aitem->sri) == 0) {
+			list_del(&aitem->list);
+			free(aitem);
+		}
+	}
+
+	return ret;
+}
+
+/*
+ * For a given filesystem object, perform all repairs of a given class
+ * (corrupt, xcorrupt, xfail, preen) if the repair item says it's needed.
+ */
+static int
+repair_item_class(
+	struct scrub_ctx		*ctx,
+	struct scrub_item		*sri,
+	int				override_fd,
+	uint8_t				repair_mask,
+	unsigned int			flags)
 {
 	struct xfs_fd			xfd;
 	struct xfs_fd			*xfdp = &ctx->mnt;
-	struct action_item		*aitem;
-	struct action_item		*n;
-	enum check_outcome		fix;
+	unsigned int			scrub_type;
+
+	if (ctx->mode < SCRUB_MODE_REPAIR)
+		return 0;
 
 	/*
 	 * If the caller passed us a file descriptor for a scrub, use it
 	 * instead of scrub-by-handle because this enables the kernel to skip
 	 * costly inode btree lookups.
 	 */
-	if (fd >= 0) {
+	if (override_fd >= 0) {
 		memcpy(&xfd, xfdp, sizeof(xfd));
-		xfd.fd = fd;
+		xfd.fd = override_fd;
 		xfdp = &xfd;
 	}
 
-	if (!alist->sorted) {
-		list_sort(NULL, &alist->list, xfs_action_item_compare);
-		alist->sorted = true;
-	}
+	foreach_scrub_type(scrub_type) {
+		enum check_outcome	fix;
 
-	list_for_each_entry_safe(aitem, n, &alist->list, list) {
-		fix = xfs_repair_metadata(ctx, xfdp, aitem, repair_flags);
+		if (scrub_excessive_errors(ctx))
+			return ECANCELED;
+
+		if (!(sri->sri_state[scrub_type] & repair_mask))
+			continue;
+
+		fix = xfs_repair_metadata(ctx, xfdp, scrub_type, sri, flags);
 		switch (fix) {
 		case CHECK_DONE:
-			if (!(repair_flags & XRM_NOPROGRESS))
+			if (!(flags & XRM_NOPROGRESS))
 				progress_add(1);
-			alist->nr--;
-			list_del(&aitem->list);
-			free(aitem);
 			continue;
 		case CHECK_ABORT:
 			return ECANCELED;
@@ -487,37 +452,113 @@ action_list_process(
 		}
 	}
 
-	if (scrub_excessive_errors(ctx))
-		return ECANCELED;
+	return 0;
+}
+
+/*
+ * Repair all parts (i.e. scrub types) of this filesystem object for which
+ * corruption has been observed directly.  Other types of repair work (fixing
+ * cross referencing problems and preening) are deferred.
+ *
+ * This function should only be called to perform spot repairs of fs objects
+ * during phase 2 and 3 while we still have open handles to those objects.
+ */
+int
+repair_item_corruption(
+	struct scrub_ctx	*ctx,
+	struct scrub_item	*sri)
+{
+	return repair_item_class(ctx, sri, -1, SCRUB_ITEM_CORRUPT,
+			XRM_REPAIR_ONLY | XRM_NOPROGRESS);
+}
+
+/* Repair all parts of this file, similar to repair_item_corruption. */
+int
+repair_file_corruption(
+	struct scrub_ctx	*ctx,
+	struct scrub_item	*sri,
+	int			override_fd)
+{
+	return repair_item_class(ctx, sri, override_fd, SCRUB_ITEM_CORRUPT,
+			XRM_REPAIR_ONLY | XRM_NOPROGRESS);
+}
+
+/*
+ * Repair everything in this filesystem object that needs it.  This includes
+ * cross-referencing and preening.
+ */
+int
+repair_item(
+	struct scrub_ctx	*ctx,
+	struct scrub_item	*sri,
+	unsigned int		flags)
+{
+	int			ret;
+
+	ret = repair_item_class(ctx, sri, -1, SCRUB_ITEM_CORRUPT, flags);
+	if (ret)
+		return ret;
+
+	ret = repair_item_class(ctx, sri, -1, SCRUB_ITEM_XCORRUPT, flags);
+	if (ret)
+		return ret;
+
+	ret = repair_item_class(ctx, sri, -1, SCRUB_ITEM_XFAIL, flags);
+	if (ret)
+		return ret;
+
+	return repair_item_class(ctx, sri, -1, SCRUB_ITEM_PREEN, flags);
+}
+
+/* Create an action item around a scrub item that needs repairs. */
+int
+repair_item_to_action_item(
+	struct scrub_ctx	*ctx,
+	const struct scrub_item	*sri,
+	struct action_item	**aitemp)
+{
+	struct action_item	*aitem;
+
+	if (repair_item_count_needsrepair(sri) == 0)
+		return 0;
+
+	aitem = malloc(sizeof(struct action_item));
+	if (!aitem) {
+		int		error = errno;
+
+		str_liberror(ctx, error, _("creating repair action item"));
+		return error;
+	}
+
+	INIT_LIST_HEAD(&aitem->list);
+	memcpy(&aitem->sri, sri, sizeof(struct scrub_item));
+
+	*aitemp = aitem;
 	return 0;
 }
 
 /* Defer all the repairs until phase 4. */
-void
-action_list_defer(
-	struct scrub_ctx		*ctx,
-	xfs_agnumber_t			agno,
-	struct action_list		*alist)
+int
+repair_item_defer(
+	struct scrub_ctx	*ctx,
+	const struct scrub_item	*sri)
 {
+	struct action_item	*aitem = NULL;
+	unsigned int		agno;
+	int			error;
+
+	error = repair_item_to_action_item(ctx, sri, &aitem);
+	if (error || !aitem)
+		return error;
+
+	if (sri->sri_agno != -1U)
+		agno = sri->sri_agno;
+	else if (sri->sri_ino != -1ULL && sri->sri_gen != -1U)
+		agno = cvt_ino_to_agno(&ctx->mnt, sri->sri_ino);
+	else
+		agno = 0;
 	ASSERT(agno < ctx->mnt.fsgeom.agcount);
 
-	action_list_splice(&ctx->action_lists[agno], alist);
-}
-
-/* Run actions now and defer unfinished items for later. */
-int
-action_list_process_or_defer(
-	struct scrub_ctx		*ctx,
-	xfs_agnumber_t			agno,
-	struct action_list		*alist)
-{
-	int				ret;
-
-	ret = action_list_process(ctx, -1, alist,
-			XRM_REPAIR_ONLY | XRM_NOPROGRESS);
-	if (ret)
-		return ret;
-
-	action_list_defer(ctx, agno, alist);
+	action_list_add(&ctx->action_lists[agno], aitem);
 	return 0;
 }
diff --git a/scrub/repair.h b/scrub/repair.h
index b61bd29c860..463a3f9bfef 100644
--- a/scrub/repair.h
+++ b/scrub/repair.h
@@ -12,6 +12,8 @@ struct action_list {
 	bool			sorted;
 };
 
+struct action_item;
+
 int action_lists_alloc(size_t nr, struct action_list **listsp);
 void action_lists_free(struct action_list **listsp);
 
@@ -25,16 +27,14 @@ static inline bool action_list_empty(const struct action_list *alist)
 unsigned long long action_list_length(struct action_list *alist);
 void action_list_add(struct action_list *dest, struct action_item *item);
 void action_list_discard(struct action_list *alist);
-void action_list_splice(struct action_list *dest, struct action_list *src);
 
-void action_list_find_mustfix(struct action_list *actions,
-		struct action_list *immediate_alist);
+void repair_item_mustfix(struct scrub_item *sri, struct scrub_item *fix_now);
 
 /* Primary metadata is corrupt */
 #define REPAIR_DIFFICULTY_PRIMARY	(1U << 0)
 /* Secondary metadata is corrupt */
 #define REPAIR_DIFFICULTY_SECONDARY	(1U << 1)
-unsigned int action_list_difficulty(const struct action_list *actions);
+unsigned int repair_item_difficulty(const struct scrub_item *sri);
 
 /*
  * Only ask the kernel to repair this object if the kernel directly told us it
@@ -49,11 +49,36 @@ unsigned int action_list_difficulty(const struct action_list *actions);
 /* Don't call progress_add after repairing an item. */
 #define XRM_NOPROGRESS		(1U << 2)
 
-int action_list_process(struct scrub_ctx *ctx, int fd,
-		struct action_list *alist, unsigned int repair_flags);
-void action_list_defer(struct scrub_ctx *ctx, xfs_agnumber_t agno,
-		struct action_list *alist);
-int action_list_process_or_defer(struct scrub_ctx *ctx, xfs_agnumber_t agno,
-		struct action_list *alist);
+int action_list_process(struct scrub_ctx *ctx, struct action_list *alist,
+		unsigned int repair_flags);
+int repair_item_corruption(struct scrub_ctx *ctx, struct scrub_item *sri);
+int repair_file_corruption(struct scrub_ctx *ctx, struct scrub_item *sri,
+		int override_fd);
+int repair_item(struct scrub_ctx *ctx, struct scrub_item *sri,
+		unsigned int repair_flags);
+int repair_item_to_action_item(struct scrub_ctx *ctx,
+		const struct scrub_item *sri, struct action_item **aitemp);
+int repair_item_defer(struct scrub_ctx *ctx, const struct scrub_item *sri);
+
+static inline unsigned int
+repair_item_count_needsrepair(
+	const struct scrub_item	*sri)
+{
+	unsigned int		scrub_type;
+	unsigned int		nr = 0;
+
+	foreach_scrub_type(scrub_type)
+		if (sri->sri_state[scrub_type] & SCRUB_ITEM_REPAIR_ANY)
+			nr++;
+	return nr;
+}
+
+static inline int
+repair_item_completely(
+	struct scrub_ctx	*ctx,
+	struct scrub_item	*sri)
+{
+	return repair_item(ctx, sri, XRM_FINAL_WARNING | XRM_NOPROGRESS);
+}
 
 #endif /* XFS_SCRUB_REPAIR_H_ */
diff --git a/scrub/scrub.c b/scrub/scrub.c
index e242e38ed0c..54f397fb92a 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -217,42 +217,6 @@ _("Optimizations of %s are possible."), _(xfrog_scrubbers[i].descr));
 	}
 }
 
-/* Save a scrub context for later repairs. */
-static int
-scrub_save_repair(
-	struct scrub_ctx		*ctx,
-	struct action_list		*alist,
-	struct xfs_scrub_metadata	*meta)
-{
-	struct action_item		*aitem;
-
-	/* Schedule this item for later repairs. */
-	aitem = malloc(sizeof(struct action_item));
-	if (!aitem) {
-		str_errno(ctx, _("adding item to repair list"));
-		return errno;
-	}
-
-	memset(aitem, 0, sizeof(*aitem));
-	aitem->type = meta->sm_type;
-	aitem->flags = meta->sm_flags;
-	switch (xfrog_scrubbers[meta->sm_type].group) {
-	case XFROG_SCRUB_GROUP_AGHEADER:
-	case XFROG_SCRUB_GROUP_PERAG:
-		aitem->agno = meta->sm_agno;
-		break;
-	case XFROG_SCRUB_GROUP_INODE:
-		aitem->ino = meta->sm_ino;
-		aitem->gen = meta->sm_gen;
-		break;
-	default:
-		break;
-	}
-
-	action_list_add(alist, aitem);
-	return 0;
-}
-
 /*
  * Scrub a single XFS_SCRUB_TYPE_*, saving corruption reports for later.
  *
@@ -272,7 +236,6 @@ scrub_meta_type(
 		.sm_agno		= agno,
 	};
 	enum check_outcome		fix;
-	int				ret;
 
 	background_sleep();
 
@@ -285,10 +248,7 @@ scrub_meta_type(
 		return ECANCELED;
 	case CHECK_REPAIR:
 		scrub_item_save_state(sri, type, meta.sm_flags);
-		ret = scrub_save_repair(ctx, alist, &meta);
-		if (ret)
-			return ret;
-		fallthrough;
+		return 0;
 	case CHECK_DONE:
 		scrub_item_clean_state(sri, type);
 		return 0;
@@ -469,7 +429,7 @@ scrub_file(
 	}
 
 	scrub_item_save_state(sri, type, meta.sm_flags);
-	return scrub_save_repair(ctx, alist, &meta);
+	return 0;
 }
 
 /* Dump a scrub item for debugging purposes. */
diff --git a/scrub/scrub.h b/scrub/scrub.h
index 21ea4147e0f..0d6825a5a95 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -14,8 +14,6 @@ enum check_outcome {
 	CHECK_RETRY,	/* repair failed, try again later */
 };
 
-struct action_item;
-
 /*
  * These flags record the metadata object state that the kernel returned.
  * We want to remember if the object was corrupt, if the cross-referencing
@@ -110,14 +108,4 @@ int scrub_file(struct scrub_ctx *ctx, int fd, const struct xfs_bulkstat *bstat,
 		unsigned int type, struct action_list *alist,
 		struct scrub_item *sri);
 
-/* Repair parameters are the scrub inputs and retry count. */
-struct action_item {
-	struct list_head	list;
-	__u64			ino;
-	__u32			type;
-	__u32			flags;
-	__u32			gen;
-	__u32			agno;
-};
-
 #endif /* XFS_SCRUB_SCRUB_H_ */

[PATCH 3/9] xfs_scrub: remove action lists from phaseX code

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Now that we track repair schedules by filesystem object (and not
individual repairs) we can get rid of all the onstack list heads and
whatnot in the phaseX code.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase1.c |    5 +----
 scrub/phase2.c |   16 ++++------------
 scrub/phase3.c |   19 ++++++++-----------
 scrub/phase4.c |    8 ++------
 scrub/phase5.c |    8 ++------
 scrub/phase7.c |    4 +---
 scrub/scrub.c  |   37 ++++++++++++++++++++-----------------
 scrub/scrub.h  |   16 +++++-----------
 8 files changed, 43 insertions(+), 70 deletions(-)


diff --git a/scrub/phase1.c b/scrub/phase1.c
index b1bbc694e64..1e56f9fb1ee 100644
--- a/scrub/phase1.c
+++ b/scrub/phase1.c
@@ -53,7 +53,6 @@ report_to_kernel(
 	struct scrub_ctx	*ctx)
 {
 	struct scrub_item	sri;
-	struct action_list	alist;
 	int			ret;
 
 	if (!ctx->scrub_setup_succeeded || ctx->corruptions_found ||
@@ -62,8 +61,7 @@ report_to_kernel(
 		return 0;
 
 	scrub_item_init_fs(&sri);
-	action_list_init(&alist);
-	ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_HEALTHY, 0, &alist, &sri);
+	ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_HEALTHY, &sri);
 	if (ret)
 		return ret;
 
@@ -74,7 +72,6 @@ report_to_kernel(
 	if (repair_item_count_needsrepair(&sri) != 0 &&
 	    !debug_tweak_on("XFS_SCRUB_FORCE_REPAIR")) {
 		str_info(ctx, _("Couldn't upload clean bill of health."), NULL);
-		action_list_discard(&alist);
 	}
 
 	return 0;
diff --git a/scrub/phase2.c b/scrub/phase2.c
index 26ce5818030..4d4552d8477 100644
--- a/scrub/phase2.c
+++ b/scrub/phase2.c
@@ -61,8 +61,6 @@ scan_ag_metadata(
 	struct scrub_item		fix_now;
 	struct scrub_ctx		*ctx = (struct scrub_ctx *)wq->wq_ctx;
 	struct scan_ctl			*sctl = arg;
-	struct action_list		alist;
-	struct action_list		immediate_alist;
 	char				descr[DESCR_BUFSZ];
 	unsigned int			difficulty;
 	int				ret;
@@ -71,15 +69,13 @@ scan_ag_metadata(
 		return;
 
 	scrub_item_init_ag(&sri, agno);
-	action_list_init(&alist);
-	action_list_init(&immediate_alist);
 	snprintf(descr, DESCR_BUFSZ, _("AG %u"), agno);
 
 	/*
 	 * First we scrub and fix the AG headers, because we need
 	 * them to work well enough to check the AG btrees.
 	 */
-	ret = scrub_ag_headers(ctx, agno, &alist, &sri);
+	ret = scrub_ag_headers(ctx, &sri);
 	if (ret)
 		goto err;
 
@@ -89,7 +85,7 @@ scan_ag_metadata(
 		goto err;
 
 	/* Now scrub the AG btrees. */
-	ret = scrub_ag_metadata(ctx, agno, &alist, &sri);
+	ret = scrub_ag_metadata(ctx, &sri);
 	if (ret)
 		goto err;
 
@@ -126,7 +122,6 @@ scan_fs_metadata(
 	void			*arg)
 {
 	struct scrub_item	sri;
-	struct action_list	alist;
 	struct scrub_ctx	*ctx = (struct scrub_ctx *)wq->wq_ctx;
 	struct scan_ctl		*sctl = arg;
 	unsigned int		difficulty;
@@ -136,8 +131,7 @@ scan_fs_metadata(
 		goto out;
 
 	scrub_item_init_fs(&sri);
-	action_list_init(&alist);
-	ret = scrub_fs_metadata(ctx, type, &alist, &sri);
+	ret = scrub_fs_metadata(ctx, type, &sri);
 	if (ret) {
 		sctl->aborted = true;
 		goto out;
@@ -172,7 +166,6 @@ phase2_func(
 		.aborted	= false,
 		.rbm_done	= false,
 	};
-	struct action_list	alist;
 	struct scrub_item	sri;
 	const struct xfrog_scrub_descr *sc = xfrog_scrubbers;
 	xfs_agnumber_t		agno;
@@ -196,8 +189,7 @@ phase2_func(
 	 * If errors occur, this function will log them and return nonzero.
 	 */
 	scrub_item_init_ag(&sri, 0);
-	action_list_init(&alist);
-	ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_SB, 0, &alist, &sri);
+	ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_SB, &sri);
 	if (ret)
 		goto out_wq;
 	ret = repair_item_completely(ctx, &sri);
diff --git a/scrub/phase3.c b/scrub/phase3.c
index e602d8c7ec4..fa2eef4dea1 100644
--- a/scrub/phase3.c
+++ b/scrub/phase3.c
@@ -107,7 +107,6 @@ scrub_inode(
 	struct xfs_bulkstat	*bstat,
 	void			*arg)
 {
-	struct action_list	alist;
 	struct scrub_item	sri;
 	struct scrub_inode_ctx	*ictx = arg;
 	struct ptcounter	*icount = ictx->icount;
@@ -115,7 +114,6 @@ scrub_inode(
 	int			error;
 
 	scrub_item_init_file(&sri, bstat);
-	action_list_init(&alist);
 	background_sleep();
 
 	/*
@@ -146,7 +144,7 @@ scrub_inode(
 		fd = scrub_open_handle(handle);
 
 	/* Scrub the inode. */
-	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_INODE, &alist, &sri);
+	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_INODE, &sri);
 	if (error)
 		goto out;
 
@@ -155,13 +153,13 @@ scrub_inode(
 		goto out;
 
 	/* Scrub all block mappings. */
-	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_BMBTD, &alist, &sri);
+	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_BMBTD, &sri);
 	if (error)
 		goto out;
-	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_BMBTA, &alist, &sri);
+	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_BMBTA, &sri);
 	if (error)
 		goto out;
-	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_BMBTC, &alist, &sri);
+	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_BMBTC, &sri);
 	if (error)
 		goto out;
 
@@ -182,25 +180,24 @@ scrub_inode(
 	if (S_ISLNK(bstat->bs_mode) || !bstat->bs_mode) {
 		/* Check symlink contents. */
 		error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_SYMLINK,
-				&alist, &sri);
+				&sri);
 		if (error)
 			goto out;
 	}
 	if (S_ISDIR(bstat->bs_mode) || !bstat->bs_mode) {
 		/* Check the directory entries. */
-		error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_DIR, &alist,
-				&sri);
+		error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_DIR, &sri);
 		if (error)
 			goto out;
 	}
 
 	/* Check all the extended attributes. */
-	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_XATTR, &alist, &sri);
+	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_XATTR, &sri);
 	if (error)
 		goto out;
 
 	/* Check parent pointers. */
-	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_PARENT, &alist, &sri);
+	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_PARENT, &sri);
 	if (error)
 		goto out;
 
diff --git a/scrub/phase4.c b/scrub/phase4.c
index 98518635b2b..230c559f07f 100644
--- a/scrub/phase4.c
+++ b/scrub/phase4.c
@@ -129,7 +129,6 @@ phase4_func(
 	struct scrub_ctx	*ctx)
 {
 	struct xfs_fsop_geom	fsgeom;
-	struct action_list	alist;
 	struct scrub_item	sri;
 	int			ret;
 
@@ -144,8 +143,7 @@ phase4_func(
 	 * metadata.  If repairs fails, we'll come back during phase 7.
 	 */
 	scrub_item_init_fs(&sri);
-	action_list_init(&alist);
-	ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_FSCOUNTERS, 0, &alist, &sri);
+	ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_FSCOUNTERS, &sri);
 	if (ret)
 		return ret;
 
@@ -160,8 +158,7 @@ phase4_func(
 		return ret;
 
 	if (fsgeom.sick & XFS_FSOP_GEOM_SICK_QUOTACHECK) {
-		ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_QUOTACHECK, 0,
-				&alist, &sri);
+		ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_QUOTACHECK, &sri);
 		if (ret)
 			return ret;
 	}
@@ -170,7 +167,6 @@ phase4_func(
 	ret = repair_item_corruption(ctx, &sri);
 	if (ret)
 		return ret;
-	action_list_discard(&alist);
 
 	ret = repair_everything(ctx);
 	if (ret)
diff --git a/scrub/phase5.c b/scrub/phase5.c
index 79bfea8f6b5..6c9a518db4d 100644
--- a/scrub/phase5.c
+++ b/scrub/phase5.c
@@ -386,7 +386,6 @@ check_fs_label(
 
 struct fs_scan_item {
 	struct scrub_item	sri;
-	struct action_list	alist;
 	bool			*abortedp;
 	unsigned int		scrub_type;
 };
@@ -413,16 +412,14 @@ fs_scan_worker(
 		nanosleep(&tv, NULL);
 	}
 
-	ret = scrub_meta_type(ctx, item->scrub_type, 0, &item->alist,
-			&item->sri);
+	ret = scrub_meta_type(ctx, item->scrub_type, &item->sri);
 	if (ret) {
 		str_liberror(ctx, ret, _("checking fs scan metadata"));
 		*item->abortedp = true;
 		goto out;
 	}
 
-	ret = action_list_process(ctx, &item->alist,
-			XRM_FINAL_WARNING | XRM_NOPROGRESS);
+	ret = repair_item_completely(ctx, &item->sri);
 	if (ret) {
 		str_liberror(ctx, ret, _("repairing fs scan metadata"));
 		*item->abortedp = true;
@@ -453,7 +450,6 @@ queue_fs_scan(
 		return ret;
 	}
 	scrub_item_init_fs(&item->sri);
-	action_list_init(&item->alist);
 	item->scrub_type = scrub_type;
 	item->abortedp = abortedp;
 
diff --git a/scrub/phase7.c b/scrub/phase7.c
index 404bfb82243..02da6b42beb 100644
--- a/scrub/phase7.c
+++ b/scrub/phase7.c
@@ -100,7 +100,6 @@ phase7_func(
 {
 	struct summary_counts	totalcount = {0};
 	struct scrub_item	sri;
-	struct action_list	alist;
 	struct ptvar		*ptvar;
 	unsigned long long	used_data;
 	unsigned long long	used_rt;
@@ -119,8 +118,7 @@ phase7_func(
 
 	/* Check and fix the summary metadata. */
 	scrub_item_init_fs(&sri);
-	action_list_init(&alist);
-	error = scrub_summary_metadata(ctx, &alist, &sri);
+	error = scrub_summary_metadata(ctx, &sri);
 	if (error)
 		return error;
 	error = repair_item_completely(ctx, &sri);
diff --git a/scrub/scrub.c b/scrub/scrub.c
index 54f397fb92a..ca3eea42ece 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -219,6 +219,7 @@ _("Optimizations of %s are possible."), _(xfrog_scrubbers[i].descr));
 
 /*
  * Scrub a single XFS_SCRUB_TYPE_*, saving corruption reports for later.
+ * Do not call this function to repair file metadata.
  *
  * Returns 0 for success.  If errors occur, this function will log them and
  * return a positive error code.
@@ -227,18 +228,29 @@ int
 scrub_meta_type(
 	struct scrub_ctx		*ctx,
 	unsigned int			type,
-	xfs_agnumber_t			agno,
-	struct action_list		*alist,
 	struct scrub_item		*sri)
 {
 	struct xfs_scrub_metadata	meta = {
 		.sm_type		= type,
-		.sm_agno		= agno,
 	};
 	enum check_outcome		fix;
 
 	background_sleep();
 
+	switch (xfrog_scrubbers[type].group) {
+	case XFROG_SCRUB_GROUP_AGHEADER:
+	case XFROG_SCRUB_GROUP_PERAG:
+		meta.sm_agno = sri->sri_agno;
+		break;
+	case XFROG_SCRUB_GROUP_FS:
+	case XFROG_SCRUB_GROUP_SUMMARY:
+	case XFROG_SCRUB_GROUP_NONE:
+		break;
+	default:
+		assert(0);
+		break;
+	}
+
 	/* Check the item. */
 	fix = xfs_check_metadata(ctx, &ctx->mnt, &meta, false);
 	progress_add(1);
@@ -267,8 +279,6 @@ static bool
 scrub_group(
 	struct scrub_ctx		*ctx,
 	enum xfrog_scrub_group		group,
-	xfs_agnumber_t			agno,
-	struct action_list		*alist,
 	struct scrub_item		*sri)
 {
 	const struct xfrog_scrub_descr	*sc;
@@ -281,7 +291,7 @@ scrub_group(
 		if (sc->group != group)
 			continue;
 
-		ret = scrub_meta_type(ctx, type, agno, alist, sri);
+		ret = scrub_meta_type(ctx, type, sri);
 		if (ret)
 			return ret;
 	}
@@ -293,22 +303,18 @@ scrub_group(
 int
 scrub_ag_headers(
 	struct scrub_ctx		*ctx,
-	xfs_agnumber_t			agno,
-	struct action_list		*alist,
 	struct scrub_item		*sri)
 {
-	return scrub_group(ctx, XFROG_SCRUB_GROUP_AGHEADER, agno, alist, sri);
+	return scrub_group(ctx, XFROG_SCRUB_GROUP_AGHEADER, sri);
 }
 
 /* Scrub each AG's metadata btrees. */
 int
 scrub_ag_metadata(
 	struct scrub_ctx		*ctx,
-	xfs_agnumber_t			agno,
-	struct action_list		*alist,
 	struct scrub_item		*sri)
 {
-	return scrub_group(ctx, XFROG_SCRUB_GROUP_PERAG, agno, alist, sri);
+	return scrub_group(ctx, XFROG_SCRUB_GROUP_PERAG, sri);
 }
 
 /* Scrub whole-filesystem metadata. */
@@ -316,22 +322,20 @@ int
 scrub_fs_metadata(
 	struct scrub_ctx		*ctx,
 	unsigned int			type,
-	struct action_list		*alist,
 	struct scrub_item		*sri)
 {
 	ASSERT(xfrog_scrubbers[type].group == XFROG_SCRUB_GROUP_FS);
 
-	return scrub_meta_type(ctx, type, 0, alist, sri);
+	return scrub_meta_type(ctx, type, sri);
 }
 
 /* Scrub all FS summary metadata. */
 int
 scrub_summary_metadata(
 	struct scrub_ctx		*ctx,
-	struct action_list		*alist,
 	struct scrub_item		*sri)
 {
-	return scrub_group(ctx, XFROG_SCRUB_GROUP_SUMMARY, 0, alist, sri);
+	return scrub_group(ctx, XFROG_SCRUB_GROUP_SUMMARY, sri);
 }
 
 /* How many items do we have to check? */
@@ -393,7 +397,6 @@ scrub_file(
 	int				fd,
 	const struct xfs_bulkstat	*bstat,
 	unsigned int			type,
-	struct action_list		*alist,
 	struct scrub_item		*sri)
 {
 	struct xfs_scrub_metadata	meta = {0};
diff --git a/scrub/scrub.h b/scrub/scrub.h
index 0d6825a5a95..b2e91efac70 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -80,18 +80,13 @@ void scrub_item_dump(struct scrub_item *sri, unsigned int group_mask,
 		const char *tag);
 
 void scrub_report_preen_triggers(struct scrub_ctx *ctx);
-int scrub_ag_headers(struct scrub_ctx *ctx, xfs_agnumber_t agno,
-		struct action_list *alist, struct scrub_item *sri);
-int scrub_ag_metadata(struct scrub_ctx *ctx, xfs_agnumber_t agno,
-		struct action_list *alist, struct scrub_item *sri);
+int scrub_ag_headers(struct scrub_ctx *ctx, struct scrub_item *sri);
+int scrub_ag_metadata(struct scrub_ctx *ctx, struct scrub_item *sri);
 int scrub_fs_metadata(struct scrub_ctx *ctx, unsigned int scrub_type,
-		struct action_list *alist, struct scrub_item *sri);
-int scrub_iscan_metadata(struct scrub_ctx *ctx, struct action_list *alist,
-		struct scrub_item *sri);
-int scrub_summary_metadata(struct scrub_ctx *ctx, struct action_list *alist,
 		struct scrub_item *sri);
+int scrub_iscan_metadata(struct scrub_ctx *ctx, struct scrub_item *sri);
+int scrub_summary_metadata(struct scrub_ctx *ctx, struct scrub_item *sri);
 int scrub_meta_type(struct scrub_ctx *ctx, unsigned int type,
-		xfs_agnumber_t agno, struct action_list *alist,
 		struct scrub_item *sri);
 
 bool can_scrub_fs_metadata(struct scrub_ctx *ctx);
@@ -105,7 +100,6 @@ bool can_repair(struct scrub_ctx *ctx);
 bool can_force_rebuild(struct scrub_ctx *ctx);
 
 int scrub_file(struct scrub_ctx *ctx, int fd, const struct xfs_bulkstat *bstat,
-		unsigned int type, struct action_list *alist,
-		struct scrub_item *sri);
+		unsigned int type, struct scrub_item *sri);
 
 #endif /* XFS_SCRUB_SCRUB_H_ */

[PATCH 4/9] xfs_scrub: remove scrub_metadata_file

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Collapse this function with scrub_meta_type.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase2.c |    2 +-
 scrub/scrub.c  |   12 ------------
 scrub/scrub.h  |    2 --
 3 files changed, 1 insertion(+), 15 deletions(-)


diff --git a/scrub/phase2.c b/scrub/phase2.c
index 4d4552d8477..4d90291ed14 100644
--- a/scrub/phase2.c
+++ b/scrub/phase2.c
@@ -131,7 +131,7 @@ scan_fs_metadata(
 		goto out;
 
 	scrub_item_init_fs(&sri);
-	ret = scrub_fs_metadata(ctx, type, &sri);
+	ret = scrub_meta_type(ctx, type, &sri);
 	if (ret) {
 		sctl->aborted = true;
 		goto out;
diff --git a/scrub/scrub.c b/scrub/scrub.c
index ca3eea42ece..5c14ed2092e 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -317,18 +317,6 @@ scrub_ag_metadata(
 	return scrub_group(ctx, XFROG_SCRUB_GROUP_PERAG, sri);
 }
 
-/* Scrub whole-filesystem metadata. */
-int
-scrub_fs_metadata(
-	struct scrub_ctx		*ctx,
-	unsigned int			type,
-	struct scrub_item		*sri)
-{
-	ASSERT(xfrog_scrubbers[type].group == XFROG_SCRUB_GROUP_FS);
-
-	return scrub_meta_type(ctx, type, sri);
-}
-
 /* Scrub all FS summary metadata. */
 int
 scrub_summary_metadata(
diff --git a/scrub/scrub.h b/scrub/scrub.h
index b2e91efac70..874e1fe1319 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -82,8 +82,6 @@ void scrub_item_dump(struct scrub_item *sri, unsigned int group_mask,
 void scrub_report_preen_triggers(struct scrub_ctx *ctx);
 int scrub_ag_headers(struct scrub_ctx *ctx, struct scrub_item *sri);
 int scrub_ag_metadata(struct scrub_ctx *ctx, struct scrub_item *sri);
-int scrub_fs_metadata(struct scrub_ctx *ctx, unsigned int scrub_type,
-		struct scrub_item *sri);
 int scrub_iscan_metadata(struct scrub_ctx *ctx, struct scrub_item *sri);
 int scrub_summary_metadata(struct scrub_ctx *ctx, struct scrub_item *sri);
 int scrub_meta_type(struct scrub_ctx *ctx, unsigned int type,

[PATCH 5/9] xfs_scrub: boost the repair priority of dependencies of damaged items

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

In XFS, certain types of metadata objects depend on the correctness of
lower level metadata objects.  For example, directory blocks are stored
in the data fork of directory files, which means that any issues with
the inode core and the data fork should be dealt with before we try to
repair a directory.

xfs_scrub prioritises repairs by the severity of what the kernel scrub
function reports -- anything directly observed to be corrupt get
repaired first, then anything that had trouble with cross referencing,
and finally anything that was correct but could be further optimised.
Returning to the above example, if a directory data fork mapping offset
is off by a bit flip, scrub will mark that as failing cross referencing,
but it'll mark the directory as corrupt.  Repair should check out the
mapping problem before it tackles the directory.

Do this by embedding a dependency table and using it to boost the
priority of the repair_item fields as needed.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libfrog/scrub.c       |    1 
 scrub/repair.c        |   99 ++++++++++++++++++++++++++++++++++++++++++++++++-
 scrub/scrub.h         |   12 ++++++
 scrub/scrub_private.h |    8 ++++
 4 files changed, 117 insertions(+), 3 deletions(-)


diff --git a/libfrog/scrub.c b/libfrog/scrub.c
index 1df2965fe2d..baaa4b4d940 100644
--- a/libfrog/scrub.c
+++ b/libfrog/scrub.c
@@ -150,6 +150,7 @@ const struct xfrog_scrub_descr xfrog_scrubbers[XFS_SCRUB_TYPE_NR] = {
 		.group	= XFROG_SCRUB_GROUP_NONE,
 	},
 };
+#undef DEP
 
 /* Invoke the scrub ioctl.  Returns zero or negative error code. */
 int
diff --git a/scrub/repair.c b/scrub/repair.c
index 6e09c592ed4..5f13f3c7a5f 100644
--- a/scrub/repair.c
+++ b/scrub/repair.c
@@ -22,6 +22,29 @@
 
 /* General repair routines. */
 
+/*
+ * Bitmap showing the correctness dependencies between scrub types for repairs.
+ * There are no edges between AG btrees and AG headers because we can't mount
+ * the filesystem if the btree root pointers in the AG headers are wrong.
+ * Dependencies cannot cross scrub groups.
+ */
+#define DEP(x) (1U << (x))
+static const unsigned int repair_deps[XFS_SCRUB_TYPE_NR] = {
+	[XFS_SCRUB_TYPE_BMBTD]		= DEP(XFS_SCRUB_TYPE_INODE),
+	[XFS_SCRUB_TYPE_BMBTA]		= DEP(XFS_SCRUB_TYPE_INODE),
+	[XFS_SCRUB_TYPE_BMBTC]		= DEP(XFS_SCRUB_TYPE_INODE),
+	[XFS_SCRUB_TYPE_DIR]		= DEP(XFS_SCRUB_TYPE_BMBTD),
+	[XFS_SCRUB_TYPE_XATTR]		= DEP(XFS_SCRUB_TYPE_BMBTA),
+	[XFS_SCRUB_TYPE_SYMLINK]	= DEP(XFS_SCRUB_TYPE_BMBTD),
+	[XFS_SCRUB_TYPE_PARENT]		= DEP(XFS_SCRUB_TYPE_DIR) |
+					  DEP(XFS_SCRUB_TYPE_XATTR),
+	[XFS_SCRUB_TYPE_QUOTACHECK]	= DEP(XFS_SCRUB_TYPE_UQUOTA) |
+					  DEP(XFS_SCRUB_TYPE_GQUOTA) |
+					  DEP(XFS_SCRUB_TYPE_PQUOTA),
+	[XFS_SCRUB_TYPE_RTSUM]		= DEP(XFS_SCRUB_TYPE_RTBITMAP),
+};
+#undef DEP
+
 /* Repair some metadata. */
 static enum check_outcome
 xfs_repair_metadata(
@@ -34,8 +57,16 @@ xfs_repair_metadata(
 	struct xfs_scrub_metadata	meta = { 0 };
 	struct xfs_scrub_metadata	oldm;
 	DEFINE_DESCR(dsc, ctx, format_scrub_descr);
+	bool				repair_only;
 	int				error;
 
+	/*
+	 * If the caller boosted the priority of this scrub type on behalf of a
+	 * higher level repair by setting IFLAG_REPAIR, turn off REPAIR_ONLY.
+	 */
+	repair_only = (repair_flags & XRM_REPAIR_ONLY) &&
+			scrub_item_type_boosted(sri, scrub_type);
+
 	assert(scrub_type < XFS_SCRUB_TYPE_NR);
 	assert(!debug_tweak_on("XFS_SCRUB_NO_KERNEL"));
 	meta.sm_type = scrub_type;
@@ -55,7 +86,7 @@ xfs_repair_metadata(
 		break;
 	}
 
-	if (!is_corrupt(&meta) && (repair_flags & XRM_REPAIR_ONLY))
+	if (!is_corrupt(&meta) && repair_only)
 		return CHECK_RETRY;
 
 	memcpy(&oldm, &meta, sizeof(oldm));
@@ -223,6 +254,60 @@ struct action_item {
 	struct scrub_item	sri;
 };
 
+/*
+ * The operation of higher level metadata objects depends on the correctness of
+ * lower level metadata objects.  This means that if X depends on Y, we must
+ * investigate and correct all the observed issues with Y before we try to make
+ * a correction to X.  For all scheduled repair activity on X, boost the
+ * priority of repairs on all the Ys to ensure this correctness.
+ */
+static void
+repair_item_boost_priorities(
+	struct scrub_item		*sri)
+{
+	unsigned int			scrub_type;
+
+	foreach_scrub_type(scrub_type) {
+		unsigned int		dep_mask = repair_deps[scrub_type];
+		unsigned int		b;
+
+		if (repair_item_count_needsrepair(sri) == 0 || !dep_mask)
+			continue;
+
+		/*
+		 * Check if the repairs for this scrub type depend on any other
+		 * scrub types that have been flagged with cross-referencing
+		 * errors and are not already tagged for the highest priority
+		 * repair (SCRUB_ITEM_CORRUPT).  If so, boost the priority of
+		 * that scrub type (via SCRUB_ITEM_BOOST_REPAIR) so that any
+		 * problems with the dependencies will (hopefully) be fixed
+		 * before we start repairs on this scrub type.
+		 *
+		 * So far in the history of xfs_scrub we have maintained that
+		 * lower numbered scrub types do not depend on higher numbered
+		 * scrub types, so we need only process the bit mask once.
+		 */
+		for (b = 0; b < XFS_SCRUB_TYPE_NR; b++, dep_mask >>= 1) {
+			if (!dep_mask)
+				break;
+			if (!(dep_mask & 1))
+				continue;
+			if (!(sri->sri_state[b] & SCRUB_ITEM_REPAIR_XREF))
+				continue;
+			if (sri->sri_state[b] & SCRUB_ITEM_CORRUPT)
+				continue;
+			sri->sri_state[b] |= SCRUB_ITEM_BOOST_REPAIR;
+		}
+	}
+}
+
+/*
+ * These are the scrub item state bits that must be copied when scheduling
+ * a (per-AG) scrub type for immediate repairs.  The original state tracking
+ * bits are left untouched to force a rescan in phase 4.
+ */
+#define MUSTFIX_STATES	(SCRUB_ITEM_CORRUPT | \
+			 SCRUB_ITEM_BOOST_REPAIR)
 /*
  * Figure out which AG metadata must be fixed before we can move on
  * to the inode scan.
@@ -235,17 +320,21 @@ repair_item_mustfix(
 	unsigned int		scrub_type;
 
 	assert(sri->sri_agno != -1U);
+	repair_item_boost_priorities(sri);
 	scrub_item_init_ag(fix_now, sri->sri_agno);
 
 	foreach_scrub_type(scrub_type) {
-		if (!(sri->sri_state[scrub_type] & SCRUB_ITEM_CORRUPT))
+		unsigned int	state;
+
+		state = sri->sri_state[scrub_type] & MUSTFIX_STATES;
+		if (!state)
 			continue;
 
 		switch (scrub_type) {
 		case XFS_SCRUB_TYPE_AGI:
 		case XFS_SCRUB_TYPE_FINOBT:
 		case XFS_SCRUB_TYPE_INOBT:
-			fix_now->sri_state[scrub_type] |= SCRUB_ITEM_CORRUPT;
+			fix_now->sri_state[scrub_type] = state;
 			break;
 		}
 	}
@@ -479,6 +568,8 @@ repair_file_corruption(
 	struct scrub_item	*sri,
 	int			override_fd)
 {
+	repair_item_boost_priorities(sri);
+
 	return repair_item_class(ctx, sri, override_fd, SCRUB_ITEM_CORRUPT,
 			XRM_REPAIR_ONLY | XRM_NOPROGRESS);
 }
@@ -495,6 +586,8 @@ repair_item(
 {
 	int			ret;
 
+	repair_item_boost_priorities(sri);
+
 	ret = repair_item_class(ctx, sri, -1, SCRUB_ITEM_CORRUPT, flags);
 	if (ret)
 		return ret;
diff --git a/scrub/scrub.h b/scrub/scrub.h
index 874e1fe1319..f22a952629e 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -14,6 +14,14 @@ enum check_outcome {
 	CHECK_RETRY,	/* repair failed, try again later */
 };
 
+/*
+ * This flag boosts the repair priority of a scrub item when a dependent scrub
+ * item is scheduled for repair.  Use a separate flag to preserve the
+ * corruption state that we got from the kernel.  Priority boost is cleared the
+ * next time xfs_repair_metadata is called.
+ */
+#define SCRUB_ITEM_BOOST_REPAIR	(1 << 0)
+
 /*
  * These flags record the metadata object state that the kernel returned.
  * We want to remember if the object was corrupt, if the cross-referencing
@@ -31,6 +39,10 @@ enum check_outcome {
 				 SCRUB_ITEM_XFAIL | \
 				 SCRUB_ITEM_XCORRUPT)
 
+/* Cross-referencing failures only. */
+#define SCRUB_ITEM_REPAIR_XREF	(SCRUB_ITEM_XFAIL | \
+				 SCRUB_ITEM_XCORRUPT)
+
 struct scrub_item {
 	/*
 	 * Information we need to call the scrub and repair ioctls.  Per-AG
diff --git a/scrub/scrub_private.h b/scrub/scrub_private.h
index 090efb54c0a..08b9130cbc9 100644
--- a/scrub/scrub_private.h
+++ b/scrub/scrub_private.h
@@ -71,4 +71,12 @@ scrub_item_clean_state(
 	sri->sri_state[scrub_type] = 0;
 }
 
+static inline bool
+scrub_item_type_boosted(
+	struct scrub_item		*sri,
+	unsigned  int			scrub_type)
+{
+	return sri->sri_state[scrub_type] & SCRUB_ITEM_BOOST_REPAIR;
+}
+
 #endif /* XFS_SCRUB_SCRUB_PRIVATE_H_ */

[PATCH 6/9] xfs_scrub: clean up repair_item_difficulty a little

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Document the flags handling in repair_item_difficulty.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/repair.c |   16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)


diff --git a/scrub/repair.c b/scrub/repair.c
index 5f13f3c7a5f..d4521f50c68 100644
--- a/scrub/repair.c
+++ b/scrub/repair.c
@@ -340,6 +340,15 @@ repair_item_mustfix(
 	}
 }
 
+/*
+ * These scrub item states correspond to metadata that is inconsistent in some
+ * way and must be repaired.  If too many metadata objects share these states,
+ * this can make repairs difficult.
+ */
+#define HARDREPAIR_STATES	(SCRUB_ITEM_CORRUPT | \
+				 SCRUB_ITEM_XCORRUPT | \
+				 SCRUB_ITEM_XFAIL)
+
 /* Determine if primary or secondary metadata are inconsistent. */
 unsigned int
 repair_item_difficulty(
@@ -349,9 +358,10 @@ repair_item_difficulty(
 	unsigned int		ret = 0;
 
 	foreach_scrub_type(scrub_type) {
-		if (!(sri->sri_state[scrub_type] & (XFS_SCRUB_OFLAG_CORRUPT |
-						    XFS_SCRUB_OFLAG_XCORRUPT |
-						    XFS_SCRUB_OFLAG_XFAIL)))
+		unsigned int	state;
+
+		state = sri->sri_state[scrub_type] & HARDREPAIR_STATES;
+		if (!state)
 			continue;
 
 		switch (scrub_type) {

[PATCH 7/9] xfs_scrub: check dependencies of a scrub type before repairing

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Now that we have a map of a scrub type to its dependent scrub types, use
this information to avoid trying to fix higher level metadata before the
lower levels have passed.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/repair.c |   32 ++++++++++++++++++++++++++++++++
 scrub/scrub.h  |    5 +++++
 2 files changed, 37 insertions(+)


diff --git a/scrub/repair.c b/scrub/repair.c
index d4521f50c68..9b4b5d01626 100644
--- a/scrub/repair.c
+++ b/scrub/repair.c
@@ -497,6 +497,29 @@ action_list_process(
 	return ret;
 }
 
+/* Decide if the dependent scrub types of the given scrub type are ok. */
+static bool
+repair_item_dependencies_ok(
+	const struct scrub_item	*sri,
+	unsigned int		scrub_type)
+{
+	unsigned int		dep_mask = repair_deps[scrub_type];
+	unsigned int		b;
+
+	for (b = 0; dep_mask && b < XFS_SCRUB_TYPE_NR; b++, dep_mask >>= 1) {
+		if (!(dep_mask & 1))
+			continue;
+		/*
+		 * If this lower level object also needs repair, we can't fix
+		 * the higher level item.
+		 */
+		if (sri->sri_state[b] & SCRUB_ITEM_NEEDSREPAIR)
+			return false;
+	}
+
+	return true;
+}
+
 /*
  * For a given filesystem object, perform all repairs of a given class
  * (corrupt, xcorrupt, xfail, preen) if the repair item says it's needed.
@@ -536,6 +559,15 @@ repair_item_class(
 		if (!(sri->sri_state[scrub_type] & repair_mask))
 			continue;
 
+		/*
+		 * Don't try to repair higher level items if their lower-level
+		 * dependencies haven't been verified, unless this is our last
+		 * chance to fix things without complaint.
+		 */
+		if (!(flags & XRM_FINAL_WARNING) &&
+		    !repair_item_dependencies_ok(sri, scrub_type))
+			continue;
+
 		fix = xfs_repair_metadata(ctx, xfdp, scrub_type, sri, flags);
 		switch (fix) {
 		case CHECK_DONE:
diff --git a/scrub/scrub.h b/scrub/scrub.h
index f22a952629e..3ae0bfd2952 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -43,6 +43,11 @@ enum check_outcome {
 #define SCRUB_ITEM_REPAIR_XREF	(SCRUB_ITEM_XFAIL | \
 				 SCRUB_ITEM_XCORRUPT)
 
+/* Mask of bits signalling that a piece of metadata requires attention. */
+#define SCRUB_ITEM_NEEDSREPAIR	(SCRUB_ITEM_CORRUPT | \
+				 SCRUB_ITEM_XFAIL | \
+				 SCRUB_ITEM_XCORRUPT)
+
 struct scrub_item {
 	/*
 	 * Information we need to call the scrub and repair ioctls.  Per-AG

[PATCH 8/9] xfs_scrub: retry incomplete repairs

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If a repair says it didn't do anything on account of not being able to
complete a scan of the metadata, retry the repair a few times; if even
that doesn't work, we can delay it to phase 4.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/repair.c        |   15 ++++++++++++++-
 scrub/scrub.c         |    3 +--
 scrub/scrub_private.h |   10 ++++++++++
 3 files changed, 25 insertions(+), 3 deletions(-)


diff --git a/scrub/repair.c b/scrub/repair.c
index 9b4b5d01626..2b863bb4195 100644
--- a/scrub/repair.c
+++ b/scrub/repair.c
@@ -58,6 +58,7 @@ xfs_repair_metadata(
 	struct xfs_scrub_metadata	oldm;
 	DEFINE_DESCR(dsc, ctx, format_scrub_descr);
 	bool				repair_only;
+	unsigned int			tries = 0;
 	int				error;
 
 	/*
@@ -99,6 +100,7 @@ xfs_repair_metadata(
 		str_info(ctx, descr_render(&dsc),
 				_("Attempting optimization."));
 
+retry:
 	error = -xfrog_scrub_metadata(xfdp, &meta);
 	switch (error) {
 	case 0:
@@ -179,9 +181,20 @@ _("Read-only filesystem; cannot make changes."));
 		return CHECK_DONE;
 	}
 
+	/*
+	 * If the kernel says the repair was incomplete or that there was a
+	 * cross-referencing discrepancy but no obvious corruption, we'll try
+	 * the repair again, just in case the fs was busy.  Only retry so many
+	 * times.
+	 */
+	if (want_retry(&meta) && tries < 10) {
+		tries++;
+		goto retry;
+	}
+
 	if (repair_flags & XRM_FINAL_WARNING)
 		scrub_warn_incomplete_scrub(ctx, &dsc, &meta);
-	if (needs_repair(&meta)) {
+	if (needs_repair(&meta) || is_incomplete(&meta)) {
 		/*
 		 * Still broken; if we've been told not to complain then we
 		 * just requeue this and try again later.  Otherwise we
diff --git a/scrub/scrub.c b/scrub/scrub.c
index 5c14ed2092e..5fc549f9728 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -137,8 +137,7 @@ _("Filesystem is shut down, aborting."));
 	 * we'll try the scan again, just in case the fs was busy.
 	 * Only retry so many times.
 	 */
-	if (tries < 10 && (is_incomplete(meta) ||
-			   (xref_disagrees(meta) && !is_corrupt(meta)))) {
+	if (want_retry(meta) && tries < 10) {
 		tries++;
 		goto retry;
 	}
diff --git a/scrub/scrub_private.h b/scrub/scrub_private.h
index 08b9130cbc9..53372e1f322 100644
--- a/scrub/scrub_private.h
+++ b/scrub/scrub_private.h
@@ -49,6 +49,16 @@ static inline bool needs_repair(struct xfs_scrub_metadata *sm)
 	return is_corrupt(sm) || xref_disagrees(sm);
 }
 
+/*
+ * We want to retry an operation if the kernel says it couldn't complete the
+ * scan/repair; or if there were cross-referencing problems but the object was
+ * not obviously corrupt.
+ */
+static inline bool want_retry(struct xfs_scrub_metadata *sm)
+{
+	return is_incomplete(sm) || (xref_disagrees(sm) && !is_corrupt(sm));
+}
+
 void scrub_warn_incomplete_scrub(struct scrub_ctx *ctx, struct descr *dsc,
 		struct xfs_scrub_metadata *meta);
 

[PATCH 9/9] xfs_scrub: remove unused action_list fields

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Remove some fields since we don't need them anymore.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/repair.c |    5 -----
 scrub/repair.h |    2 --
 2 files changed, 7 deletions(-)


diff --git a/scrub/repair.c b/scrub/repair.c
index 2b863bb4195..a3a8fb311d0 100644
--- a/scrub/repair.c
+++ b/scrub/repair.c
@@ -432,7 +432,6 @@ action_list_discard(
 	struct action_item		*n;
 
 	list_for_each_entry_safe(aitem, n, &alist->list, list) {
-		alist->nr--;
 		list_del(&aitem->list);
 		free(aitem);
 	}
@@ -453,8 +452,6 @@ action_list_init(
 	struct action_list		*alist)
 {
 	INIT_LIST_HEAD(&alist->list);
-	alist->nr = 0;
-	alist->sorted = false;
 }
 
 /* Number of pending repairs in this list. */
@@ -478,8 +475,6 @@ action_list_add(
 	struct action_item		*aitem)
 {
 	list_add_tail(&aitem->list, &alist->list);
-	alist->nr++;
-	alist->sorted = false;
 }
 
 /* Repair everything on this list. */
diff --git a/scrub/repair.h b/scrub/repair.h
index 463a3f9bfef..a38cdd5e6df 100644
--- a/scrub/repair.h
+++ b/scrub/repair.h
@@ -8,8 +8,6 @@
 
 struct action_list {
 	struct list_head	list;
-	unsigned long long	nr;
-	bool			sorted;
 };
 
 struct action_item;

[PATCH 1/5] xfs_scrub: start tracking scrub state in scrub_item

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Start using the scrub_item to track which metadata objects need
checking by adding a new flag to the scrub_item state set.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase1.c |    3 +
 scrub/phase2.c |   12 +++--
 scrub/phase3.c |   41 +++++-----------
 scrub/phase4.c |   16 +++---
 scrub/phase5.c |    5 +-
 scrub/phase7.c |    5 ++
 scrub/scrub.c  |  147 +++++++++++++++++++-------------------------------------
 scrub/scrub.h  |   28 ++++++++---
 8 files changed, 108 insertions(+), 149 deletions(-)


diff --git a/scrub/phase1.c b/scrub/phase1.c
index 1e56f9fb1ee..60a8db5724e 100644
--- a/scrub/phase1.c
+++ b/scrub/phase1.c
@@ -61,7 +61,8 @@ report_to_kernel(
 		return 0;
 
 	scrub_item_init_fs(&sri);
-	ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_HEALTHY, &sri);
+	scrub_item_schedule(&sri, XFS_SCRUB_TYPE_HEALTHY);
+	ret = scrub_item_check(ctx, &sri);
 	if (ret)
 		return ret;
 
diff --git a/scrub/phase2.c b/scrub/phase2.c
index 4d90291ed14..79b33dd04db 100644
--- a/scrub/phase2.c
+++ b/scrub/phase2.c
@@ -75,7 +75,8 @@ scan_ag_metadata(
 	 * First we scrub and fix the AG headers, because we need
 	 * them to work well enough to check the AG btrees.
 	 */
-	ret = scrub_ag_headers(ctx, &sri);
+	scrub_item_schedule_group(&sri, XFROG_SCRUB_GROUP_AGHEADER);
+	ret = scrub_item_check(ctx, &sri);
 	if (ret)
 		goto err;
 
@@ -85,7 +86,8 @@ scan_ag_metadata(
 		goto err;
 
 	/* Now scrub the AG btrees. */
-	ret = scrub_ag_metadata(ctx, &sri);
+	scrub_item_schedule_group(&sri, XFROG_SCRUB_GROUP_PERAG);
+	ret = scrub_item_check(ctx, &sri);
 	if (ret)
 		goto err;
 
@@ -131,7 +133,8 @@ scan_fs_metadata(
 		goto out;
 
 	scrub_item_init_fs(&sri);
-	ret = scrub_meta_type(ctx, type, &sri);
+	scrub_item_schedule(&sri, type);
+	ret = scrub_item_check(ctx, &sri);
 	if (ret) {
 		sctl->aborted = true;
 		goto out;
@@ -189,7 +192,8 @@ phase2_func(
 	 * If errors occur, this function will log them and return nonzero.
 	 */
 	scrub_item_init_ag(&sri, 0);
-	ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_SB, &sri);
+	scrub_item_schedule(&sri, XFS_SCRUB_TYPE_SB);
+	ret = scrub_item_check(ctx, &sri);
 	if (ret)
 		goto out_wq;
 	ret = repair_item_completely(ctx, &sri);
diff --git a/scrub/phase3.c b/scrub/phase3.c
index fa2eef4dea1..09347c977b5 100644
--- a/scrub/phase3.c
+++ b/scrub/phase3.c
@@ -144,7 +144,8 @@ scrub_inode(
 		fd = scrub_open_handle(handle);
 
 	/* Scrub the inode. */
-	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_INODE, &sri);
+	scrub_item_schedule(&sri, XFS_SCRUB_TYPE_INODE);
+	error = scrub_item_check_file(ctx, &sri, fd);
 	if (error)
 		goto out;
 
@@ -153,13 +154,10 @@ scrub_inode(
 		goto out;
 
 	/* Scrub all block mappings. */
-	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_BMBTD, &sri);
-	if (error)
-		goto out;
-	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_BMBTA, &sri);
-	if (error)
-		goto out;
-	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_BMBTC, &sri);
+	scrub_item_schedule(&sri, XFS_SCRUB_TYPE_BMBTD);
+	scrub_item_schedule(&sri, XFS_SCRUB_TYPE_BMBTA);
+	scrub_item_schedule(&sri, XFS_SCRUB_TYPE_BMBTC);
+	error = scrub_item_check_file(ctx, &sri, fd);
 	if (error)
 		goto out;
 
@@ -177,27 +175,14 @@ scrub_inode(
 	 * content scrubbers.  Better to have them return -ENOENT than miss
 	 * some coverage.
 	 */
-	if (S_ISLNK(bstat->bs_mode) || !bstat->bs_mode) {
-		/* Check symlink contents. */
-		error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_SYMLINK,
-				&sri);
-		if (error)
-			goto out;
-	}
-	if (S_ISDIR(bstat->bs_mode) || !bstat->bs_mode) {
-		/* Check the directory entries. */
-		error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_DIR, &sri);
-		if (error)
-			goto out;
-	}
+	if (S_ISLNK(bstat->bs_mode) || !bstat->bs_mode)
+		scrub_item_schedule(&sri, XFS_SCRUB_TYPE_SYMLINK);
+	if (S_ISDIR(bstat->bs_mode) || !bstat->bs_mode)
+		scrub_item_schedule(&sri, XFS_SCRUB_TYPE_DIR);
 
-	/* Check all the extended attributes. */
-	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_XATTR, &sri);
-	if (error)
-		goto out;
-
-	/* Check parent pointers. */
-	error = scrub_file(ctx, fd, bstat, XFS_SCRUB_TYPE_PARENT, &sri);
+	scrub_item_schedule(&sri, XFS_SCRUB_TYPE_XATTR);
+	scrub_item_schedule(&sri, XFS_SCRUB_TYPE_PARENT);
+	error = scrub_item_check_file(ctx, &sri, fd);
 	if (error)
 		goto out;
 
diff --git a/scrub/phase4.c b/scrub/phase4.c
index 230c559f07f..3c51b38a55e 100644
--- a/scrub/phase4.c
+++ b/scrub/phase4.c
@@ -143,9 +143,7 @@ phase4_func(
 	 * metadata.  If repairs fails, we'll come back during phase 7.
 	 */
 	scrub_item_init_fs(&sri);
-	ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_FSCOUNTERS, &sri);
-	if (ret)
-		return ret;
+	scrub_item_schedule(&sri, XFS_SCRUB_TYPE_FSCOUNTERS);
 
 	/*
 	 * Repair possibly bad quota counts before starting other repairs,
@@ -157,13 +155,13 @@ phase4_func(
 	if (ret)
 		return ret;
 
-	if (fsgeom.sick & XFS_FSOP_GEOM_SICK_QUOTACHECK) {
-		ret = scrub_meta_type(ctx, XFS_SCRUB_TYPE_QUOTACHECK, &sri);
-		if (ret)
-			return ret;
-	}
+	if (fsgeom.sick & XFS_FSOP_GEOM_SICK_QUOTACHECK)
+		scrub_item_schedule(&sri, XFS_SCRUB_TYPE_QUOTACHECK);
 
-	/* Repair counters before starting on the rest. */
+	/* Check and repair counters before starting on the rest. */
+	ret = scrub_item_check(ctx, &sri);
+	if (ret)
+		return ret;
 	ret = repair_item_corruption(ctx, &sri);
 	if (ret)
 		return ret;
diff --git a/scrub/phase5.c b/scrub/phase5.c
index 6c9a518db4d..0df8c46e9f5 100644
--- a/scrub/phase5.c
+++ b/scrub/phase5.c
@@ -387,7 +387,6 @@ check_fs_label(
 struct fs_scan_item {
 	struct scrub_item	sri;
 	bool			*abortedp;
-	unsigned int		scrub_type;
 };
 
 /* Run one full-fs scan scrubber in this thread. */
@@ -412,7 +411,7 @@ fs_scan_worker(
 		nanosleep(&tv, NULL);
 	}
 
-	ret = scrub_meta_type(ctx, item->scrub_type, &item->sri);
+	ret = scrub_item_check(ctx, &item->sri);
 	if (ret) {
 		str_liberror(ctx, ret, _("checking fs scan metadata"));
 		*item->abortedp = true;
@@ -450,7 +449,7 @@ queue_fs_scan(
 		return ret;
 	}
 	scrub_item_init_fs(&item->sri);
-	item->scrub_type = scrub_type;
+	scrub_item_schedule(&item->sri, scrub_type);
 	item->abortedp = abortedp;
 
 	ret = -workqueue_add(wq, fs_scan_worker, nr, item);
diff --git a/scrub/phase7.c b/scrub/phase7.c
index 02da6b42beb..cd4501f72b7 100644
--- a/scrub/phase7.c
+++ b/scrub/phase7.c
@@ -10,6 +10,8 @@
 #include <linux/fsmap.h>
 #include "libfrog/paths.h"
 #include "libfrog/ptvar.h"
+#include "libfrog/fsgeom.h"
+#include "libfrog/scrub.h"
 #include "list.h"
 #include "xfs_scrub.h"
 #include "common.h"
@@ -118,7 +120,8 @@ phase7_func(
 
 	/* Check and fix the summary metadata. */
 	scrub_item_init_fs(&sri);
-	error = scrub_summary_metadata(ctx, &sri);
+	scrub_item_schedule_group(&sri, XFROG_SCRUB_GROUP_SUMMARY);
+	error = scrub_item_check(ctx, &sri);
 	if (error)
 		return error;
 	error = repair_item_completely(ctx, &sri);
diff --git a/scrub/scrub.c b/scrub/scrub.c
index 5fc549f9728..5aa36a96499 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -86,9 +86,11 @@ xfs_check_metadata(
 	bool				is_inode)
 {
 	DEFINE_DESCR(dsc, ctx, format_scrub_descr);
+	enum xfrog_scrub_group		group;
 	unsigned int			tries = 0;
 	int				error;
 
+	group = xfrog_scrubbers[meta->sm_type].group;
 	assert(!debug_tweak_on("XFS_SCRUB_NO_KERNEL"));
 	assert(meta->sm_type < XFS_SCRUB_TYPE_NR);
 	descr_set(&dsc, meta);
@@ -165,7 +167,7 @@ _("Repairs are required."));
 	 */
 	if (is_unoptimized(meta)) {
 		if (ctx->mode != SCRUB_MODE_REPAIR) {
-			if (!is_inode) {
+			if (group != XFROG_SCRUB_GROUP_INODE) {
 				/* AG or FS metadata, always warn. */
 				str_info(ctx, descr_render(&dsc),
 _("Optimization is possible."));
@@ -223,9 +225,10 @@ _("Optimizations of %s are possible."), _(xfrog_scrubbers[i].descr));
  * Returns 0 for success.  If errors occur, this function will log them and
  * return a positive error code.
  */
-int
+static int
 scrub_meta_type(
 	struct scrub_ctx		*ctx,
+	struct xfs_fd			*xfdp,
 	unsigned int			type,
 	struct scrub_item		*sri)
 {
@@ -243,16 +246,20 @@ scrub_meta_type(
 		break;
 	case XFROG_SCRUB_GROUP_FS:
 	case XFROG_SCRUB_GROUP_SUMMARY:
+	case XFROG_SCRUB_GROUP_ISCAN:
 	case XFROG_SCRUB_GROUP_NONE:
 		break;
-	default:
-		assert(0);
+	case XFROG_SCRUB_GROUP_INODE:
+		meta.sm_ino = sri->sri_ino;
+		meta.sm_gen = sri->sri_gen;
 		break;
 	}
 
 	/* Check the item. */
-	fix = xfs_check_metadata(ctx, &ctx->mnt, &meta, false);
-	progress_add(1);
+	fix = xfs_check_metadata(ctx, xfdp, &meta, false);
+
+	if (xfrog_scrubbers[type].group != XFROG_SCRUB_GROUP_INODE)
+		progress_add(1);
 
 	switch (fix) {
 	case CHECK_ABORT:
@@ -269,60 +276,54 @@ scrub_meta_type(
 	}
 }
 
-/*
- * Scrub all metadata types that are assigned to the given XFROG_SCRUB_GROUP_*,
- * saving corruption reports for later.  This should not be used for
- * XFROG_SCRUB_GROUP_INODE or for checking summary metadata.
- */
-static bool
-scrub_group(
-	struct scrub_ctx		*ctx,
-	enum xfrog_scrub_group		group,
-	struct scrub_item		*sri)
+/* Schedule scrub for all metadata of a given group. */
+void
+scrub_item_schedule_group(
+	struct scrub_item		*sri,
+	enum xfrog_scrub_group		group)
 {
-	const struct xfrog_scrub_descr	*sc;
-	unsigned int			type;
-
-	sc = xfrog_scrubbers;
-	for (type = 0; type < XFS_SCRUB_TYPE_NR; type++, sc++) {
-		int			ret;
+	unsigned int			scrub_type;
 
-		if (sc->group != group)
+	foreach_scrub_type(scrub_type) {
+		if (xfrog_scrubbers[scrub_type].group != group)
 			continue;
-
-		ret = scrub_meta_type(ctx, type, sri);
-		if (ret)
-			return ret;
+		scrub_item_schedule(sri, scrub_type);
 	}
-
-	return 0;
 }
 
-/* Scrub each AG's header blocks. */
+/* Run all the incomplete scans on this scrub principal. */
 int
-scrub_ag_headers(
+scrub_item_check_file(
 	struct scrub_ctx		*ctx,
-	struct scrub_item		*sri)
+	struct scrub_item		*sri,
+	int				override_fd)
 {
-	return scrub_group(ctx, XFROG_SCRUB_GROUP_AGHEADER, sri);
-}
+	struct xfs_fd			xfd;
+	struct xfs_fd			*xfdp = &ctx->mnt;
+	unsigned int			scrub_type;
+	int				error;
 
-/* Scrub each AG's metadata btrees. */
-int
-scrub_ag_metadata(
-	struct scrub_ctx		*ctx,
-	struct scrub_item		*sri)
-{
-	return scrub_group(ctx, XFROG_SCRUB_GROUP_PERAG, sri);
-}
+	/*
+	 * If the caller passed us a file descriptor for a scrub, use it
+	 * instead of scrub-by-handle because this enables the kernel to skip
+	 * costly inode btree lookups.
+	 */
+	if (override_fd >= 0) {
+		memcpy(&xfd, xfdp, sizeof(xfd));
+		xfd.fd = override_fd;
+		xfdp = &xfd;
+	}
 
-/* Scrub all FS summary metadata. */
-int
-scrub_summary_metadata(
-	struct scrub_ctx		*ctx,
-	struct scrub_item		*sri)
-{
-	return scrub_group(ctx, XFROG_SCRUB_GROUP_SUMMARY, sri);
+	foreach_scrub_type(scrub_type) {
+		if (!(sri->sri_state[scrub_type] & SCRUB_ITEM_NEEDSCHECK))
+			continue;
+
+		error = scrub_meta_type(ctx, xfdp, scrub_type, sri);
+		if (error)
+			break;
+	}
+
+	return error;
 }
 
 /* How many items do we have to check? */
@@ -374,54 +375,6 @@ scrub_estimate_iscan_work(
 	return estimate;
 }
 
-/*
- * Scrub file metadata of some sort.  If errors occur, this function will log
- * them and return nonzero.
- */
-int
-scrub_file(
-	struct scrub_ctx		*ctx,
-	int				fd,
-	const struct xfs_bulkstat	*bstat,
-	unsigned int			type,
-	struct scrub_item		*sri)
-{
-	struct xfs_scrub_metadata	meta = {0};
-	struct xfs_fd			xfd;
-	struct xfs_fd			*xfdp = &ctx->mnt;
-	enum check_outcome		fix;
-
-	assert(type < XFS_SCRUB_TYPE_NR);
-	assert(xfrog_scrubbers[type].group == XFROG_SCRUB_GROUP_INODE);
-
-	meta.sm_type = type;
-	meta.sm_ino = bstat->bs_ino;
-	meta.sm_gen = bstat->bs_gen;
-
-	/*
-	 * If the caller passed us a file descriptor for a scrub, use it
-	 * instead of scrub-by-handle because this enables the kernel to skip
-	 * costly inode btree lookups.
-	 */
-	if (fd >= 0) {
-		memcpy(&xfd, xfdp, sizeof(xfd));
-		xfd.fd = fd;
-		xfdp = &xfd;
-	}
-
-	/* Scrub the piece of metadata. */
-	fix = xfs_check_metadata(ctx, xfdp, &meta, true);
-	if (fix == CHECK_ABORT)
-		return ECANCELED;
-	if (fix == CHECK_DONE) {
-		scrub_item_clean_state(sri, type);
-		return 0;
-	}
-
-	scrub_item_save_state(sri, type, meta.sm_flags);
-	return 0;
-}
-
 /* Dump a scrub item for debugging purposes. */
 void
 scrub_item_dump(
diff --git a/scrub/scrub.h b/scrub/scrub.h
index 3ae0bfd2952..1ac0d8aed20 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -6,6 +6,8 @@
 #ifndef XFS_SCRUB_SCRUB_H_
 #define XFS_SCRUB_SCRUB_H_
 
+enum xfrog_scrub_group;
+
 /* Online scrub and repair. */
 enum check_outcome {
 	CHECK_DONE,	/* no further processing needed */
@@ -33,6 +35,9 @@ enum check_outcome {
 #define SCRUB_ITEM_XFAIL	(XFS_SCRUB_OFLAG_XFAIL)		/* (1 << 3) */
 #define SCRUB_ITEM_XCORRUPT	(XFS_SCRUB_OFLAG_XCORRUPT)	/* (1 << 4) */
 
+/* This scrub type needs to be checked. */
+#define SCRUB_ITEM_NEEDSCHECK	(1 << 5)
+
 /* All of the state flags that we need to prioritize repair work. */
 #define SCRUB_ITEM_REPAIR_ANY	(SCRUB_ITEM_CORRUPT | \
 				 SCRUB_ITEM_PREEN | \
@@ -96,13 +101,24 @@ scrub_item_init_file(struct scrub_item *sri, const struct xfs_bulkstat *bstat)
 void scrub_item_dump(struct scrub_item *sri, unsigned int group_mask,
 		const char *tag);
 
+static inline void
+scrub_item_schedule(struct scrub_item *sri, unsigned int scrub_type)
+{
+	sri->sri_state[scrub_type] = SCRUB_ITEM_NEEDSCHECK;
+}
+
+void scrub_item_schedule_group(struct scrub_item *sri,
+		enum xfrog_scrub_group group);
+int scrub_item_check_file(struct scrub_ctx *ctx, struct scrub_item *sri,
+		int override_fd);
+
+static inline int
+scrub_item_check(struct scrub_ctx *ctx, struct scrub_item *sri)
+{
+	return scrub_item_check_file(ctx, sri, -1);
+}
+
 void scrub_report_preen_triggers(struct scrub_ctx *ctx);
-int scrub_ag_headers(struct scrub_ctx *ctx, struct scrub_item *sri);
-int scrub_ag_metadata(struct scrub_ctx *ctx, struct scrub_item *sri);
-int scrub_iscan_metadata(struct scrub_ctx *ctx, struct scrub_item *sri);
-int scrub_summary_metadata(struct scrub_ctx *ctx, struct scrub_item *sri);
-int scrub_meta_type(struct scrub_ctx *ctx, unsigned int type,
-		struct scrub_item *sri);
 
 bool can_scrub_fs_metadata(struct scrub_ctx *ctx);
 bool can_scrub_inode(struct scrub_ctx *ctx);

[PATCH 2/5] xfs_scrub: remove enum check_outcome

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Get rid of this enumeration, and just do what we will directly.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/repair.c |   56 ++++++++++++++++++++++----------------------------
 scrub/scrub.c  |   63 +++++++++++++++++++++++++++++---------------------------
 scrub/scrub.h  |    8 -------
 3 files changed, 58 insertions(+), 69 deletions(-)


diff --git a/scrub/repair.c b/scrub/repair.c
index a3a8fb311d0..f888441aad0 100644
--- a/scrub/repair.c
+++ b/scrub/repair.c
@@ -46,7 +46,7 @@ static const unsigned int repair_deps[XFS_SCRUB_TYPE_NR] = {
 #undef DEP
 
 /* Repair some metadata. */
-static enum check_outcome
+static int
 xfs_repair_metadata(
 	struct scrub_ctx		*ctx,
 	struct xfs_fd			*xfdp,
@@ -88,7 +88,7 @@ xfs_repair_metadata(
 	}
 
 	if (!is_corrupt(&meta) && repair_only)
-		return CHECK_RETRY;
+		return 0;
 
 	memcpy(&oldm, &meta, sizeof(oldm));
 	oldm.sm_flags = sri->sri_state[scrub_type] & SCRUB_ITEM_REPAIR_ANY;
@@ -112,12 +112,12 @@ xfs_repair_metadata(
 		if (debug || verbose)
 			str_info(ctx, descr_render(&dsc),
 _("Filesystem is busy, deferring repair."));
-		return CHECK_RETRY;
+		return 0;
 	case ESHUTDOWN:
 		/* Filesystem is already shut down, abort. */
 		str_error(ctx, descr_render(&dsc),
 _("Filesystem is shut down, aborting."));
-		return CHECK_ABORT;
+		return ECANCELED;
 	case ENOTTY:
 	case EOPNOTSUPP:
 		/*
@@ -129,7 +129,7 @@ _("Filesystem is shut down, aborting."));
 		if (is_unoptimized(&oldm) ||
 		    debug_tweak_on("XFS_SCRUB_FORCE_REPAIR")) {
 			scrub_item_clean_state(sri, scrub_type);
-			return CHECK_DONE;
+			return 0;
 		}
 		/*
 		 * If we're in no-complain mode, requeue the check for
@@ -140,30 +140,30 @@ _("Filesystem is shut down, aborting."));
 		 * again to see if another repair fixed it.
 		 */
 		if (!(repair_flags & XRM_FINAL_WARNING))
-			return CHECK_RETRY;
+			return 0;
 		fallthrough;
 	case EINVAL:
 		/* Kernel doesn't know how to repair this? */
 		str_corrupt(ctx, descr_render(&dsc),
 _("Don't know how to fix; offline repair required."));
 		scrub_item_clean_state(sri, scrub_type);
-		return CHECK_DONE;
+		return 0;
 	case EROFS:
 		/* Read-only filesystem, can't fix. */
 		if (verbose || debug || needs_repair(&oldm))
 			str_error(ctx, descr_render(&dsc),
 _("Read-only filesystem; cannot make changes."));
-		return CHECK_ABORT;
+		return ECANCELED;
 	case ENOENT:
 		/* Metadata not present, just skip it. */
 		scrub_item_clean_state(sri, scrub_type);
-		return CHECK_DONE;
+		return 0;
 	case ENOMEM:
 	case ENOSPC:
 		/* Don't care if preen fails due to low resources. */
 		if (is_unoptimized(&oldm) && !needs_repair(&oldm)) {
 			scrub_item_clean_state(sri, scrub_type);
-			return CHECK_DONE;
+			return 0;
 		}
 		fallthrough;
 	default:
@@ -175,10 +175,10 @@ _("Read-only filesystem; cannot make changes."));
 		 * trying to repair it, and bail out.
 		 */
 		if (!(repair_flags & XRM_FINAL_WARNING))
-			return CHECK_RETRY;
+			return 0;
 		str_liberror(ctx, error, descr_render(&dsc));
 		scrub_item_clean_state(sri, scrub_type);
-		return CHECK_DONE;
+		return 0;
 	}
 
 	/*
@@ -201,7 +201,7 @@ _("Read-only filesystem; cannot make changes."));
 		 * log the error loudly and don't try again.
 		 */
 		if (!(repair_flags & XRM_FINAL_WARNING))
-			return CHECK_RETRY;
+			return 0;
 		str_corrupt(ctx, descr_render(&dsc),
 _("Repair unsuccessful; offline repair required."));
 	} else if (xref_failed(&meta)) {
@@ -219,7 +219,7 @@ _("Repair unsuccessful; offline repair required."));
 			if (verbose)
 				str_info(ctx, descr_render(&dsc),
  _("Seems correct but cross-referencing failed; will keep checking."));
-			return CHECK_RETRY;
+			return 0;
 		}
 	} else if (meta.sm_flags & XFS_SCRUB_OFLAG_NO_REPAIR_NEEDED) {
 		if (verbose)
@@ -242,7 +242,7 @@ _("Repair unsuccessful; offline repair required."));
 	}
 
 	scrub_item_clean_state(sri, scrub_type);
-	return CHECK_DONE;
+	return 0;
 }
 
 /*
@@ -543,6 +543,7 @@ repair_item_class(
 	struct xfs_fd			xfd;
 	struct xfs_fd			*xfdp = &ctx->mnt;
 	unsigned int			scrub_type;
+	int				error = 0;
 
 	if (ctx->mode < SCRUB_MODE_REPAIR)
 		return 0;
@@ -559,8 +560,6 @@ repair_item_class(
 	}
 
 	foreach_scrub_type(scrub_type) {
-		enum check_outcome	fix;
-
 		if (scrub_excessive_errors(ctx))
 			return ECANCELED;
 
@@ -576,22 +575,17 @@ repair_item_class(
 		    !repair_item_dependencies_ok(sri, scrub_type))
 			continue;
 
-		fix = xfs_repair_metadata(ctx, xfdp, scrub_type, sri, flags);
-		switch (fix) {
-		case CHECK_DONE:
-			if (!(flags & XRM_NOPROGRESS))
-				progress_add(1);
-			continue;
-		case CHECK_ABORT:
-			return ECANCELED;
-		case CHECK_RETRY:
-			continue;
-		case CHECK_REPAIR:
-			abort();
-		}
+		error = xfs_repair_metadata(ctx, xfdp, scrub_type, sri, flags);
+		if (error)
+			break;
+
+		/* Maybe update progress if we fixed the problem. */
+		if (!(flags & XRM_NOPROGRESS) &&
+		    !(sri->sri_state[scrub_type] & SCRUB_ITEM_REPAIR_ANY))
+			progress_add(1);
 	}
 
-	return 0;
+	return error;
 }
 
 /*
diff --git a/scrub/scrub.c b/scrub/scrub.c
index 5aa36a96499..2c47542ee0c 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -78,12 +78,12 @@ scrub_warn_incomplete_scrub(
 }
 
 /* Do a read-only check of some metadata. */
-static enum check_outcome
+static int
 xfs_check_metadata(
 	struct scrub_ctx		*ctx,
 	struct xfs_fd			*xfdp,
 	struct xfs_scrub_metadata	*meta,
-	bool				is_inode)
+	struct scrub_item		*sri)
 {
 	DEFINE_DESCR(dsc, ctx, format_scrub_descr);
 	enum xfrog_scrub_group		group;
@@ -106,17 +106,18 @@ xfs_check_metadata(
 		break;
 	case ENOENT:
 		/* Metadata not present, just skip it. */
-		return CHECK_DONE;
+		scrub_item_clean_state(sri, meta->sm_type);
+		return 0;
 	case ESHUTDOWN:
 		/* FS already crashed, give up. */
 		str_error(ctx, descr_render(&dsc),
 _("Filesystem is shut down, aborting."));
-		return CHECK_ABORT;
+		return ECANCELED;
 	case EIO:
 	case ENOMEM:
 		/* Abort on I/O errors or insufficient memory. */
 		str_liberror(ctx, error, descr_render(&dsc));
-		return CHECK_ABORT;
+		return ECANCELED;
 	case EDEADLOCK:
 	case EBUSY:
 	case EFSBADCRC:
@@ -124,13 +125,16 @@ _("Filesystem is shut down, aborting."));
 		/*
 		 * The first two should never escape the kernel,
 		 * and the other two should be reported via sm_flags.
+		 * Log it and move on.
 		 */
 		str_liberror(ctx, error, _("Kernel bug"));
-		return CHECK_DONE;
+		scrub_item_clean_state(sri, meta->sm_type);
+		return 0;
 	default:
-		/* Operational error. */
+		/* Operational error.  Log it and move on. */
 		str_liberror(ctx, error, descr_render(&dsc));
-		return CHECK_DONE;
+		scrub_item_clean_state(sri, meta->sm_type);
+		return 0;
 	}
 
 	/*
@@ -153,12 +157,16 @@ _("Filesystem is shut down, aborting."));
 	 */
 	if (is_corrupt(meta) || xref_disagrees(meta)) {
 		if (ctx->mode < SCRUB_MODE_REPAIR) {
+			/* Dry-run mode, so log an error and forget it. */
 			str_corrupt(ctx, descr_render(&dsc),
 _("Repairs are required."));
-			return CHECK_DONE;
+			scrub_item_clean_state(sri, meta->sm_type);
+			return 0;
 		}
 
-		return CHECK_REPAIR;
+		/* Schedule repairs. */
+		scrub_item_save_state(sri, meta->sm_type, meta->sm_flags);
+		return 0;
 	}
 
 	/*
@@ -167,6 +175,7 @@ _("Repairs are required."));
 	 */
 	if (is_unoptimized(meta)) {
 		if (ctx->mode != SCRUB_MODE_REPAIR) {
+			/* Dry-run mode, so log an error and forget it. */
 			if (group != XFROG_SCRUB_GROUP_INODE) {
 				/* AG or FS metadata, always warn. */
 				str_info(ctx, descr_render(&dsc),
@@ -178,10 +187,13 @@ _("Optimization is possible."));
 					ctx->preen_triggers[meta->sm_type] = true;
 				pthread_mutex_unlock(&ctx->lock);
 			}
-			return CHECK_DONE;
+			scrub_item_clean_state(sri, meta->sm_type);
+			return 0;
 		}
 
-		return CHECK_REPAIR;
+		/* Schedule optimizations. */
+		scrub_item_save_state(sri, meta->sm_type, meta->sm_flags);
+		return 0;
 	}
 
 	/*
@@ -191,11 +203,14 @@ _("Optimization is possible."));
 	 * re-examine the object as repairs progress to see if the kernel will
 	 * deem it completely consistent at some point.
 	 */
-	if (xref_failed(meta) && ctx->mode == SCRUB_MODE_REPAIR)
-		return CHECK_REPAIR;
+	if (xref_failed(meta) && ctx->mode == SCRUB_MODE_REPAIR) {
+		scrub_item_save_state(sri, meta->sm_type, meta->sm_flags);
+		return 0;
+	}
 
 	/* Everything is ok. */
-	return CHECK_DONE;
+	scrub_item_clean_state(sri, meta->sm_type);
+	return 0;
 }
 
 /* Bulk-notify user about things that could be optimized. */
@@ -235,7 +250,7 @@ scrub_meta_type(
 	struct xfs_scrub_metadata	meta = {
 		.sm_type		= type,
 	};
-	enum check_outcome		fix;
+	int				error;
 
 	background_sleep();
 
@@ -256,24 +271,12 @@ scrub_meta_type(
 	}
 
 	/* Check the item. */
-	fix = xfs_check_metadata(ctx, xfdp, &meta, false);
+	error = xfs_check_metadata(ctx, xfdp, &meta, sri);
 
 	if (xfrog_scrubbers[type].group != XFROG_SCRUB_GROUP_INODE)
 		progress_add(1);
 
-	switch (fix) {
-	case CHECK_ABORT:
-		return ECANCELED;
-	case CHECK_REPAIR:
-		scrub_item_save_state(sri, type, meta.sm_flags);
-		return 0;
-	case CHECK_DONE:
-		scrub_item_clean_state(sri, type);
-		return 0;
-	default:
-		/* CHECK_RETRY should never happen. */
-		abort();
-	}
+	return error;
 }
 
 /* Schedule scrub for all metadata of a given group. */
diff --git a/scrub/scrub.h b/scrub/scrub.h
index 1ac0d8aed20..24fb2444943 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -8,14 +8,6 @@
 
 enum xfrog_scrub_group;
 
-/* Online scrub and repair. */
-enum check_outcome {
-	CHECK_DONE,	/* no further processing needed */
-	CHECK_REPAIR,	/* schedule this for repairs */
-	CHECK_ABORT,	/* end program */
-	CHECK_RETRY,	/* repair failed, try again later */
-};
-
 /*
  * This flag boosts the repair priority of a scrub item when a dependent scrub
  * item is scheduled for repair.  Use a separate flag to preserve the

[PATCH 3/5] xfs_scrub: refactor scrub_meta_type out of existence

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Remove this helper function since it's trivial now.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/scrub.c |  124 ++++++++++++++++++++++++---------------------------------
 1 file changed, 53 insertions(+), 71 deletions(-)


diff --git a/scrub/scrub.c b/scrub/scrub.c
index 2c47542ee0c..5f0cacbde67 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -82,31 +82,51 @@ static int
 xfs_check_metadata(
 	struct scrub_ctx		*ctx,
 	struct xfs_fd			*xfdp,
-	struct xfs_scrub_metadata	*meta,
+	unsigned int			scrub_type,
 	struct scrub_item		*sri)
 {
 	DEFINE_DESCR(dsc, ctx, format_scrub_descr);
+	struct xfs_scrub_metadata	meta = { };
 	enum xfrog_scrub_group		group;
 	unsigned int			tries = 0;
 	int				error;
 
-	group = xfrog_scrubbers[meta->sm_type].group;
+	background_sleep();
+
+	group = xfrog_scrubbers[scrub_type].group;
+	meta.sm_type = scrub_type;
+	switch (group) {
+	case XFROG_SCRUB_GROUP_AGHEADER:
+	case XFROG_SCRUB_GROUP_PERAG:
+		meta.sm_agno = sri->sri_agno;
+		break;
+	case XFROG_SCRUB_GROUP_FS:
+	case XFROG_SCRUB_GROUP_SUMMARY:
+	case XFROG_SCRUB_GROUP_ISCAN:
+	case XFROG_SCRUB_GROUP_NONE:
+		break;
+	case XFROG_SCRUB_GROUP_INODE:
+		meta.sm_ino = sri->sri_ino;
+		meta.sm_gen = sri->sri_gen;
+		break;
+	}
+
 	assert(!debug_tweak_on("XFS_SCRUB_NO_KERNEL"));
-	assert(meta->sm_type < XFS_SCRUB_TYPE_NR);
-	descr_set(&dsc, meta);
+	assert(scrub_type < XFS_SCRUB_TYPE_NR);
+	descr_set(&dsc, &meta);
 
-	dbg_printf("check %s flags %xh\n", descr_render(&dsc), meta->sm_flags);
+	dbg_printf("check %s flags %xh\n", descr_render(&dsc), meta.sm_flags);
 retry:
-	error = -xfrog_scrub_metadata(xfdp, meta);
+	error = -xfrog_scrub_metadata(xfdp, &meta);
 	if (debug_tweak_on("XFS_SCRUB_FORCE_REPAIR") && !error)
-		meta->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
+		meta.sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
 	switch (error) {
 	case 0:
 		/* No operational errors encountered. */
 		break;
 	case ENOENT:
 		/* Metadata not present, just skip it. */
-		scrub_item_clean_state(sri, meta->sm_type);
+		scrub_item_clean_state(sri, scrub_type);
 		return 0;
 	case ESHUTDOWN:
 		/* FS already crashed, give up. */
@@ -128,12 +148,12 @@ _("Filesystem is shut down, aborting."));
 		 * Log it and move on.
 		 */
 		str_liberror(ctx, error, _("Kernel bug"));
-		scrub_item_clean_state(sri, meta->sm_type);
+		scrub_item_clean_state(sri, scrub_type);
 		return 0;
 	default:
 		/* Operational error.  Log it and move on. */
 		str_liberror(ctx, error, descr_render(&dsc));
-		scrub_item_clean_state(sri, meta->sm_type);
+		scrub_item_clean_state(sri, scrub_type);
 		return 0;
 	}
 
@@ -143,29 +163,29 @@ _("Filesystem is shut down, aborting."));
 	 * we'll try the scan again, just in case the fs was busy.
 	 * Only retry so many times.
 	 */
-	if (want_retry(meta) && tries < 10) {
+	if (want_retry(&meta) && tries < 10) {
 		tries++;
 		goto retry;
 	}
 
 	/* Complain about incomplete or suspicious metadata. */
-	scrub_warn_incomplete_scrub(ctx, &dsc, meta);
+	scrub_warn_incomplete_scrub(ctx, &dsc, &meta);
 
 	/*
 	 * If we need repairs or there were discrepancies, schedule a
 	 * repair if desired, otherwise complain.
 	 */
-	if (is_corrupt(meta) || xref_disagrees(meta)) {
+	if (is_corrupt(&meta) || xref_disagrees(&meta)) {
 		if (ctx->mode < SCRUB_MODE_REPAIR) {
 			/* Dry-run mode, so log an error and forget it. */
 			str_corrupt(ctx, descr_render(&dsc),
 _("Repairs are required."));
-			scrub_item_clean_state(sri, meta->sm_type);
+			scrub_item_clean_state(sri, scrub_type);
 			return 0;
 		}
 
 		/* Schedule repairs. */
-		scrub_item_save_state(sri, meta->sm_type, meta->sm_flags);
+		scrub_item_save_state(sri, scrub_type, meta.sm_flags);
 		return 0;
 	}
 
@@ -173,26 +193,26 @@ _("Repairs are required."));
 	 * If we could optimize, schedule a repair if desired,
 	 * otherwise complain.
 	 */
-	if (is_unoptimized(meta)) {
+	if (is_unoptimized(&meta)) {
 		if (ctx->mode != SCRUB_MODE_REPAIR) {
 			/* Dry-run mode, so log an error and forget it. */
 			if (group != XFROG_SCRUB_GROUP_INODE) {
 				/* AG or FS metadata, always warn. */
 				str_info(ctx, descr_render(&dsc),
 _("Optimization is possible."));
-			} else if (!ctx->preen_triggers[meta->sm_type]) {
+			} else if (!ctx->preen_triggers[scrub_type]) {
 				/* File metadata, only warn once per type. */
 				pthread_mutex_lock(&ctx->lock);
-				if (!ctx->preen_triggers[meta->sm_type])
-					ctx->preen_triggers[meta->sm_type] = true;
+				if (!ctx->preen_triggers[scrub_type])
+					ctx->preen_triggers[scrub_type] = true;
 				pthread_mutex_unlock(&ctx->lock);
 			}
-			scrub_item_clean_state(sri, meta->sm_type);
+			scrub_item_clean_state(sri, scrub_type);
 			return 0;
 		}
 
 		/* Schedule optimizations. */
-		scrub_item_save_state(sri, meta->sm_type, meta->sm_flags);
+		scrub_item_save_state(sri, scrub_type, meta.sm_flags);
 		return 0;
 	}
 
@@ -203,13 +223,13 @@ _("Optimization is possible."));
 	 * re-examine the object as repairs progress to see if the kernel will
 	 * deem it completely consistent at some point.
 	 */
-	if (xref_failed(meta) && ctx->mode == SCRUB_MODE_REPAIR) {
-		scrub_item_save_state(sri, meta->sm_type, meta->sm_flags);
+	if (xref_failed(&meta) && ctx->mode == SCRUB_MODE_REPAIR) {
+		scrub_item_save_state(sri, scrub_type, meta.sm_flags);
 		return 0;
 	}
 
 	/* Everything is ok. */
-	scrub_item_clean_state(sri, meta->sm_type);
+	scrub_item_clean_state(sri, scrub_type);
 	return 0;
 }
 
@@ -233,52 +253,6 @@ _("Optimizations of %s are possible."), _(xfrog_scrubbers[i].descr));
 	}
 }
 
-/*
- * Scrub a single XFS_SCRUB_TYPE_*, saving corruption reports for later.
- * Do not call this function to repair file metadata.
- *
- * Returns 0 for success.  If errors occur, this function will log them and
- * return a positive error code.
- */
-static int
-scrub_meta_type(
-	struct scrub_ctx		*ctx,
-	struct xfs_fd			*xfdp,
-	unsigned int			type,
-	struct scrub_item		*sri)
-{
-	struct xfs_scrub_metadata	meta = {
-		.sm_type		= type,
-	};
-	int				error;
-
-	background_sleep();
-
-	switch (xfrog_scrubbers[type].group) {
-	case XFROG_SCRUB_GROUP_AGHEADER:
-	case XFROG_SCRUB_GROUP_PERAG:
-		meta.sm_agno = sri->sri_agno;
-		break;
-	case XFROG_SCRUB_GROUP_FS:
-	case XFROG_SCRUB_GROUP_SUMMARY:
-	case XFROG_SCRUB_GROUP_ISCAN:
-	case XFROG_SCRUB_GROUP_NONE:
-		break;
-	case XFROG_SCRUB_GROUP_INODE:
-		meta.sm_ino = sri->sri_ino;
-		meta.sm_gen = sri->sri_gen;
-		break;
-	}
-
-	/* Check the item. */
-	error = xfs_check_metadata(ctx, xfdp, &meta, sri);
-
-	if (xfrog_scrubbers[type].group != XFROG_SCRUB_GROUP_INODE)
-		progress_add(1);
-
-	return error;
-}
-
 /* Schedule scrub for all metadata of a given group. */
 void
 scrub_item_schedule_group(
@@ -321,7 +295,15 @@ scrub_item_check_file(
 		if (!(sri->sri_state[scrub_type] & SCRUB_ITEM_NEEDSCHECK))
 			continue;
 
-		error = scrub_meta_type(ctx, xfdp, scrub_type, sri);
+		error = xfs_check_metadata(ctx, xfdp, scrub_type, sri);
+
+		/*
+		 * Progress is counted by the inode for inode metadata; for
+		 * everything else, it's counted for each scrub call.
+		 */
+		if (sri->sri_ino == -1ULL)
+			progress_add(1);
+
 		if (error)
 			break;
 	}

[PATCH 4/5] xfs_scrub: hoist repair retry loop to repair_item_class

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

For metadata repair calls, move the ioctl retry and freeze permission
tracking into scrub_item.  This enables us to move the repair retry loop
out of xfs_repair_metadata and into its caller to remove a long
backwards jump, and gets us closer to vectorizing scrub calls.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/repair.c        |   21 ++++++++++++---------
 scrub/scrub.c         |   32 ++++++++++++++++++++++++++++++--
 scrub/scrub.h         |    6 ++++++
 scrub/scrub_private.h |   14 ++++++++++++++
 4 files changed, 62 insertions(+), 11 deletions(-)


diff --git a/scrub/repair.c b/scrub/repair.c
index f888441aad0..c427e6e95f0 100644
--- a/scrub/repair.c
+++ b/scrub/repair.c
@@ -58,7 +58,6 @@ xfs_repair_metadata(
 	struct xfs_scrub_metadata	oldm;
 	DEFINE_DESCR(dsc, ctx, format_scrub_descr);
 	bool				repair_only;
-	unsigned int			tries = 0;
 	int				error;
 
 	/*
@@ -100,7 +99,6 @@ xfs_repair_metadata(
 		str_info(ctx, descr_render(&dsc),
 				_("Attempting optimization."));
 
-retry:
 	error = -xfrog_scrub_metadata(xfdp, &meta);
 	switch (error) {
 	case 0:
@@ -187,10 +185,8 @@ _("Read-only filesystem; cannot make changes."));
 	 * the repair again, just in case the fs was busy.  Only retry so many
 	 * times.
 	 */
-	if (want_retry(&meta) && tries < 10) {
-		tries++;
-		goto retry;
-	}
+	if (want_retry(&meta) && scrub_item_schedule_retry(sri, scrub_type))
+		return 0;
 
 	if (repair_flags & XRM_FINAL_WARNING)
 		scrub_warn_incomplete_scrub(ctx, &dsc, &meta);
@@ -541,6 +537,7 @@ repair_item_class(
 	unsigned int			flags)
 {
 	struct xfs_fd			xfd;
+	struct scrub_item		old_sri;
 	struct xfs_fd			*xfdp = &ctx->mnt;
 	unsigned int			scrub_type;
 	int				error = 0;
@@ -575,9 +572,15 @@ repair_item_class(
 		    !repair_item_dependencies_ok(sri, scrub_type))
 			continue;
 
-		error = xfs_repair_metadata(ctx, xfdp, scrub_type, sri, flags);
-		if (error)
-			break;
+		sri->sri_tries[scrub_type] = SCRUB_ITEM_MAX_RETRIES;
+		do {
+			memcpy(&old_sri, sri, sizeof(old_sri));
+			error = xfs_repair_metadata(ctx, xfdp, scrub_type, sri,
+					flags);
+			if (error)
+				return error;
+		} while (scrub_item_call_kernel_again(sri, scrub_type,
+					repair_mask, &old_sri));
 
 		/* Maybe update progress if we fixed the problem. */
 		if (!(flags & XRM_NOPROGRESS) &&
diff --git a/scrub/scrub.c b/scrub/scrub.c
index 5f0cacbde67..8c6bf845fd9 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -268,6 +268,34 @@ scrub_item_schedule_group(
 	}
 }
 
+/* Decide if we call the kernel again to finish scrub/repair activity. */
+bool
+scrub_item_call_kernel_again(
+	struct scrub_item	*sri,
+	unsigned int		scrub_type,
+	uint8_t			work_mask,
+	const struct scrub_item	*old)
+{
+	uint8_t			statex;
+
+	/* If there's nothing to do, we're done. */
+	if (!(sri->sri_state[scrub_type] & work_mask))
+		return false;
+
+	/*
+	 * We are willing to go again if the last call had any effect on the
+	 * state of the scrub item that the caller cares about, if the freeze
+	 * flag got set, or if the kernel asked us to try again...
+	 */
+	statex = sri->sri_state[scrub_type] ^ old->sri_state[scrub_type];
+	if (statex & work_mask)
+		return true;
+	if (sri->sri_tries[scrub_type] != old->sri_tries[scrub_type])
+		return true;
+
+	return false;
+}
+
 /* Run all the incomplete scans on this scrub principal. */
 int
 scrub_item_check_file(
@@ -383,9 +411,9 @@ scrub_item_dump(
 		unsigned int	g = 1U << xfrog_scrubbers[i].group;
 
 		if (g & group_mask)
-			printf("[%u]: type '%s' state 0x%x\n", i,
+			printf("[%u]: type '%s' state 0x%x tries %u\n", i,
 					xfrog_scrubbers[i].name,
-					sri->sri_state[i]);
+					sri->sri_state[i], sri->sri_tries[i]);
 	}
 	fflush(stdout);
 }
diff --git a/scrub/scrub.h b/scrub/scrub.h
index 24fb2444943..246c923f490 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -45,6 +45,9 @@ enum xfrog_scrub_group;
 				 SCRUB_ITEM_XFAIL | \
 				 SCRUB_ITEM_XCORRUPT)
 
+/* Maximum number of times we'll retry a scrub ioctl call. */
+#define SCRUB_ITEM_MAX_RETRIES	10
+
 struct scrub_item {
 	/*
 	 * Information we need to call the scrub and repair ioctls.  Per-AG
@@ -58,6 +61,9 @@ struct scrub_item {
 
 	/* Scrub item state flags, one for each XFS_SCRUB_TYPE. */
 	__u8			sri_state[XFS_SCRUB_TYPE_NR];
+
+	/* Track scrub and repair call retries for each scrub type. */
+	__u8			sri_tries[XFS_SCRUB_TYPE_NR];
 };
 
 #define foreach_scrub_type(loopvar) \
diff --git a/scrub/scrub_private.h b/scrub/scrub_private.h
index 53372e1f322..234b30ef2b8 100644
--- a/scrub/scrub_private.h
+++ b/scrub/scrub_private.h
@@ -89,4 +89,18 @@ scrub_item_type_boosted(
 	return sri->sri_state[scrub_type] & SCRUB_ITEM_BOOST_REPAIR;
 }
 
+/* Decide if we want to retry this operation and update bookkeeping if yes. */
+static inline bool
+scrub_item_schedule_retry(struct scrub_item *sri, unsigned int scrub_type)
+{
+	if (sri->sri_tries[scrub_type] == 0)
+		return false;
+	sri->sri_tries[scrub_type]--;
+	return true;
+}
+
+bool scrub_item_call_kernel_again(struct scrub_item *sri,
+		unsigned int scrub_type, uint8_t work_mask,
+		const struct scrub_item *old);
+
 #endif /* XFS_SCRUB_SCRUB_PRIVATE_H_ */

[PATCH 5/5] xfs_scrub: hoist scrub retry loop to scrub_item_check_file

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

For metadata check calls, use the ioctl retry and freeze permission
tracking in scrub_item that we created in the last patch.  This enables
us to move the check retry loop out of xfs_scrub_metadata and into its
caller to remove a long backwards jump, and gets us closer to
vectorizing scrub calls.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/scrub.c |   19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)


diff --git a/scrub/scrub.c b/scrub/scrub.c
index 8c6bf845fd9..69dfb1eb84d 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -88,7 +88,6 @@ xfs_check_metadata(
 	DEFINE_DESCR(dsc, ctx, format_scrub_descr);
 	struct xfs_scrub_metadata	meta = { };
 	enum xfrog_scrub_group		group;
-	unsigned int			tries = 0;
 	int				error;
 
 	background_sleep();
@@ -116,7 +115,7 @@ xfs_check_metadata(
 	descr_set(&dsc, &meta);
 
 	dbg_printf("check %s flags %xh\n", descr_render(&dsc), meta.sm_flags);
-retry:
+
 	error = -xfrog_scrub_metadata(xfdp, &meta);
 	if (debug_tweak_on("XFS_SCRUB_FORCE_REPAIR") && !error)
 		meta.sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
@@ -163,10 +162,8 @@ _("Filesystem is shut down, aborting."));
 	 * we'll try the scan again, just in case the fs was busy.
 	 * Only retry so many times.
 	 */
-	if (want_retry(&meta) && tries < 10) {
-		tries++;
-		goto retry;
-	}
+	if (want_retry(&meta) && scrub_item_schedule_retry(sri, scrub_type))
+		return 0;
 
 	/* Complain about incomplete or suspicious metadata. */
 	scrub_warn_incomplete_scrub(ctx, &dsc, &meta);
@@ -304,6 +301,7 @@ scrub_item_check_file(
 	int				override_fd)
 {
 	struct xfs_fd			xfd;
+	struct scrub_item		old_sri;
 	struct xfs_fd			*xfdp = &ctx->mnt;
 	unsigned int			scrub_type;
 	int				error;
@@ -323,7 +321,14 @@ scrub_item_check_file(
 		if (!(sri->sri_state[scrub_type] & SCRUB_ITEM_NEEDSCHECK))
 			continue;
 
-		error = xfs_check_metadata(ctx, xfdp, scrub_type, sri);
+		sri->sri_tries[scrub_type] = SCRUB_ITEM_MAX_RETRIES;
+		do {
+			memcpy(&old_sri, sri, sizeof(old_sri));
+			error = xfs_check_metadata(ctx, xfdp, scrub_type, sri);
+			if (error)
+				return error;
+		} while (scrub_item_call_kernel_again(sri, scrub_type,
+					SCRUB_ITEM_NEEDSCHECK, &old_sri));
 
 		/*
 		 * Progress is counted by the inode for inode metadata; for

[PATCH 1/4] libfrog: enhance ptvar to support initializer functions

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Modify the per-thread variable code to support passing in an initializer
function that will set up each thread's variable space when it is
claimed.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libfrog/ptvar.c     |    9 ++++++++-
 libfrog/ptvar.h     |    4 +++-
 scrub/counter.c     |    2 +-
 scrub/descr.c       |    2 +-
 scrub/phase7.c      |    2 +-
 scrub/read_verify.c |    2 +-
 6 files changed, 15 insertions(+), 6 deletions(-)


diff --git a/libfrog/ptvar.c b/libfrog/ptvar.c
index 7ac8c541862..9d5ae6bc8e3 100644
--- a/libfrog/ptvar.c
+++ b/libfrog/ptvar.c
@@ -26,6 +26,7 @@
 struct ptvar {
 	pthread_key_t	key;
 	pthread_mutex_t	lock;
+	ptvar_init_fn	init_fn;
 	size_t		nr_used;
 	size_t		nr_counters;
 	size_t		data_size;
@@ -38,6 +39,7 @@ int
 ptvar_alloc(
 	size_t		nr,
 	size_t		size,
+	ptvar_init_fn	init_fn,
 	struct ptvar	**pptv)
 {
 	struct ptvar	*ptv;
@@ -58,6 +60,7 @@ ptvar_alloc(
 	ptv->data_size = size;
 	ptv->nr_counters = nr;
 	ptv->nr_used = 0;
+	ptv->init_fn = init_fn;
 	memset(ptv->data, 0, nr * size);
 	ret = -pthread_mutex_init(&ptv->lock, NULL);
 	if (ret)
@@ -98,11 +101,15 @@ ptvar_get(
 	if (!p) {
 		pthread_mutex_lock(&ptv->lock);
 		assert(ptv->nr_used < ptv->nr_counters);
-		p = &ptv->data[(ptv->nr_used++) * ptv->data_size];
+		p = &ptv->data[ptv->nr_used * ptv->data_size];
 		ret = -pthread_setspecific(ptv->key, p);
 		if (ret)
 			goto out_unlock;
+		ptv->nr_used++;
 		pthread_mutex_unlock(&ptv->lock);
+
+		if (ptv->init_fn)
+			ptv->init_fn(p);
 	}
 	*retp = 0;
 	return p;
diff --git a/libfrog/ptvar.h b/libfrog/ptvar.h
index b7d02d6269e..e4a181ffe76 100644
--- a/libfrog/ptvar.h
+++ b/libfrog/ptvar.h
@@ -8,7 +8,9 @@
 
 struct ptvar;
 
-int ptvar_alloc(size_t nr, size_t size, struct ptvar **pptv);
+typedef void (*ptvar_init_fn)(void *data);
+int ptvar_alloc(size_t nr, size_t size, ptvar_init_fn init_fn,
+		struct ptvar **pptv);
 void ptvar_free(struct ptvar *ptv);
 void *ptvar_get(struct ptvar *ptv, int *ret);
 
diff --git a/scrub/counter.c b/scrub/counter.c
index 2ee357f3a76..c903454c0dc 100644
--- a/scrub/counter.c
+++ b/scrub/counter.c
@@ -38,7 +38,7 @@ ptcounter_alloc(
 	p = malloc(sizeof(struct ptcounter));
 	if (!p)
 		return errno;
-	ret = -ptvar_alloc(nr, sizeof(uint64_t), &p->var);
+	ret = -ptvar_alloc(nr, sizeof(uint64_t), NULL, &p->var);
 	if (ret) {
 		free(p);
 		return ret;
diff --git a/scrub/descr.c b/scrub/descr.c
index 77d5378ec3f..88ca5d95a78 100644
--- a/scrub/descr.c
+++ b/scrub/descr.c
@@ -89,7 +89,7 @@ descr_init_phase(
 	int			ret;
 
 	assert(descr_ptvar == NULL);
-	ret = -ptvar_alloc(nr_threads, DESCR_BUFSZ, &descr_ptvar);
+	ret = -ptvar_alloc(nr_threads, DESCR_BUFSZ, NULL, &descr_ptvar);
 	if (ret)
 		str_liberror(ctx, ret, _("creating description buffer"));
 
diff --git a/scrub/phase7.c b/scrub/phase7.c
index cd4501f72b7..cce5ede0012 100644
--- a/scrub/phase7.c
+++ b/scrub/phase7.c
@@ -136,7 +136,7 @@ phase7_func(
 	}
 
 	error = -ptvar_alloc(scrub_nproc(ctx), sizeof(struct summary_counts),
-			&ptvar);
+			NULL, &ptvar);
 	if (error) {
 		str_liberror(ctx, error, _("setting up block counter"));
 		return error;
diff --git a/scrub/read_verify.c b/scrub/read_verify.c
index 29d7939549f..52348274be2 100644
--- a/scrub/read_verify.c
+++ b/scrub/read_verify.c
@@ -120,7 +120,7 @@ read_verify_pool_alloc(
 	rvp->disk = disk;
 	rvp->ioerr_fn = ioerr_fn;
 	ret = -ptvar_alloc(submitter_threads, sizeof(struct read_verify),
-			&rvp->rvstate);
+			NULL, &rvp->rvstate);
 	if (ret)
 		goto out_counter;
 	ret = -workqueue_create(&rvp->wq, (struct xfs_mount *)rvp,

[PATCH 2/4] xfs_scrub: improve thread scheduling repair items during phase 4

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

As it stands, xfs_scrub doesn't do a good job of scheduling repair items
during phase 4.  The repair lists are sharded by AG, and one repair
worker is started for each per-AG repair list.  Consequently, if one AG
requires considerably more work than the others (e.g. inodes are not
spread evenly among the AGs) then phase 4 can stall waiting for that one
worker thread when there's still plenty of CPU power available.

While our initial assumptions were that repairs would be vanishingly
scarce, the reality is that "repairs" can be triggered for optimizations
like gaps in the xattr structures, or clearing the inode reflink flag on
inodes that no longer share data.  In real world testing scenarios, the
lack of balance leads to complaints about excessive runtime of
xfs_scrub.

To fix these balance problems, we replace the per-AG repair item lists
in the scrub context with a single repair item list.  Phase 4 will be
redesigned as follows:

The repair worker will grab a repair item from the main list, try to
repair it, record whether the repair attempt made any progress, and
requeue the item if it was not fully fixed.  A separate repair scheduler
function starts the repair workers, and waits for them all to complete.
Requeued repairs are merged back into the main repair list.  If we made
any forward progress, we'll start another round of repairs with the
repair workers.  Phase 4 retains the behavior that if the pool stops
making forward progress, it will try all the repairs one last time,
serially.

To facilitate this new design, phase 2 will queue repairs of space
metadata items directly to the main list.  Phase 3's worker threads will
queue repair items to per-thread lists and splice those lists into the
main list at the end.

On a filesystem crafted to put all the inodes in a single AG, this
restores xfs_scrub's ability to parallelize repairs.  There seems to be
a slight performance hit for the evenly-spread case, but avoiding a
performance cliff due to an unbalanced fs is more important here.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase1.c    |    8 +-
 scrub/phase2.c    |   23 +++++
 scrub/phase3.c    |  106 ++++++++++++++++--------
 scrub/phase4.c    |  230 ++++++++++++++++++++++++++++++++++++++---------------
 scrub/repair.c    |  135 +++++++++++++++++--------------
 scrub/repair.h    |   37 +++++++--
 scrub/xfs_scrub.h |    2 
 7 files changed, 367 insertions(+), 174 deletions(-)


diff --git a/scrub/phase1.c b/scrub/phase1.c
index 60a8db5724e..78769a57bf1 100644
--- a/scrub/phase1.c
+++ b/scrub/phase1.c
@@ -89,7 +89,8 @@ scrub_cleanup(
 	if (error)
 		return error;
 
-	action_lists_free(&ctx->action_lists);
+	action_list_free(&ctx->action_list);
+
 	if (ctx->fshandle)
 		free_handle(ctx->fshandle, ctx->fshandle_len);
 	if (ctx->rtdev)
@@ -185,10 +186,9 @@ _("Not an XFS filesystem."));
 		return error;
 	}
 
-	error = action_lists_alloc(ctx->mnt.fsgeom.agcount,
-			&ctx->action_lists);
+	error = action_list_alloc(&ctx->action_list);
 	if (error) {
-		str_liberror(ctx, error, _("allocating action lists"));
+		str_liberror(ctx, error, _("allocating repair list"));
 		return error;
 	}
 
diff --git a/scrub/phase2.c b/scrub/phase2.c
index 79b33dd04db..5803d8c645a 100644
--- a/scrub/phase2.c
+++ b/scrub/phase2.c
@@ -50,6 +50,25 @@ warn_repair_difficulties(
 	str_info(ctx, descr, _("Filesystem might not be repairable."));
 }
 
+/* Add a scrub item that needs more work to fs metadata repair list. */
+static int
+defer_fs_repair(
+	struct scrub_ctx	*ctx,
+	const struct scrub_item	*sri)
+{
+	struct action_item	*aitem = NULL;
+	int			error;
+
+	error = repair_item_to_action_item(ctx, sri, &aitem);
+	if (error || !aitem)
+		return error;
+
+	pthread_mutex_lock(&ctx->lock);
+	action_list_add(ctx->action_list, aitem);
+	pthread_mutex_unlock(&ctx->lock);
+	return 0;
+}
+
 /* Scrub each AG's metadata btrees. */
 static void
 scan_ag_metadata(
@@ -108,7 +127,7 @@ scan_ag_metadata(
 		goto err;
 
 	/* Everything else gets fixed during phase 4. */
-	ret = repair_item_defer(ctx, &sri);
+	ret = defer_fs_repair(ctx, &sri);
 	if (ret)
 		goto err;
 	return;
@@ -144,7 +163,7 @@ scan_fs_metadata(
 	difficulty = repair_item_difficulty(&sri);
 	warn_repair_difficulties(ctx, difficulty, xfrog_scrubbers[type].descr);
 
-	ret = repair_item_defer(ctx, &sri);
+	ret = defer_fs_repair(ctx, &sri);
 	if (ret) {
 		sctl->aborted = true;
 		goto out;
diff --git a/scrub/phase3.c b/scrub/phase3.c
index 09347c977b5..1a71d4ace48 100644
--- a/scrub/phase3.c
+++ b/scrub/phase3.c
@@ -10,6 +10,7 @@
 #include "list.h"
 #include "libfrog/paths.h"
 #include "libfrog/workqueue.h"
+#include "libfrog/ptvar.h"
 #include "xfs_scrub.h"
 #include "common.h"
 #include "counter.h"
@@ -26,8 +27,8 @@ struct scrub_inode_ctx {
 	/* Number of inodes scanned. */
 	struct ptcounter	*icount;
 
-	/* per-AG locks to protect the repair lists */
-	pthread_mutex_t		*locks;
+	/* Per-thread lists of file repair items. */
+	struct ptvar		*repair_ptlists;
 
 	/* Set to true to abort all threads. */
 	bool			aborted;
@@ -51,28 +52,28 @@ report_close_error(
 	str_errno(ctx, descr);
 }
 
-/*
- * Defer all the repairs until phase 4, being careful about locking since the
- * inode scrub threads are not per-AG.
- */
+/* Defer all the repairs until phase 4. */
 static int
 defer_inode_repair(
 	struct scrub_inode_ctx		*ictx,
-	const struct xfs_bulkstat	*bstat,
-	struct scrub_item		*sri)
+	const struct scrub_item		*sri)
 {
+	struct action_list		*alist;
 	struct action_item		*aitem = NULL;
-	xfs_agnumber_t			agno;
 	int				ret;
 
 	ret = repair_item_to_action_item(ictx->ctx, sri, &aitem);
 	if (ret || !aitem)
 		return ret;
 
-	agno = cvt_ino_to_agno(&ictx->ctx->mnt, bstat->bs_ino);
-	pthread_mutex_lock(&ictx->locks[agno]);
-	action_list_add(&ictx->ctx->action_lists[agno], aitem);
-	pthread_mutex_unlock(&ictx->locks[agno]);
+	alist = ptvar_get(ictx->repair_ptlists, &ret);
+	if (ret) {
+		str_liberror(ictx->ctx, ret,
+ _("getting per-thread inode repair list"));
+		return ret;
+	}
+
+	action_list_add(alist, aitem);
 	return 0;
 }
 
@@ -81,8 +82,7 @@ static int
 try_inode_repair(
 	struct scrub_inode_ctx		*ictx,
 	struct scrub_item		*sri,
-	int				fd,
-	const struct xfs_bulkstat	*bstat)
+	int				fd)
 {
 	/*
 	 * If at the start of phase 3 we already had ag/rt metadata repairs
@@ -149,7 +149,7 @@ scrub_inode(
 	if (error)
 		goto out;
 
-	error = try_inode_repair(ictx, &sri, fd, bstat);
+	error = try_inode_repair(ictx, &sri, fd);
 	if (error)
 		goto out;
 
@@ -161,7 +161,7 @@ scrub_inode(
 	if (error)
 		goto out;
 
-	error = try_inode_repair(ictx, &sri, fd, bstat);
+	error = try_inode_repair(ictx, &sri, fd);
 	if (error)
 		goto out;
 
@@ -187,7 +187,7 @@ scrub_inode(
 		goto out;
 
 	/* Try to repair the file while it's open. */
-	error = try_inode_repair(ictx, &sri, fd, bstat);
+	error = try_inode_repair(ictx, &sri, fd);
 	if (error)
 		goto out;
 
@@ -204,7 +204,7 @@ scrub_inode(
 	progress_add(1);
 
 	if (!error && !ictx->aborted)
-		error = defer_inode_repair(ictx, bstat, &sri);
+		error = defer_inode_repair(ictx, &sri);
 
 	if (fd >= 0) {
 		int	err2;
@@ -221,6 +221,33 @@ scrub_inode(
 	return error;
 }
 
+/*
+ * Collect all the inode repairs in the file repair list.  No need for locks
+ * here, since we're single-threaded.
+ */
+static int
+collect_repairs(
+	struct ptvar		*ptv,
+	void			*data,
+	void			*foreach_arg)
+{
+	struct scrub_ctx	*ctx = foreach_arg;
+	struct action_list	*alist = data;
+
+	action_list_merge(ctx->action_list, alist);
+	return 0;
+}
+
+/* Initialize this per-thread file repair item list. */
+static void
+action_ptlist_init(
+	void			*priv)
+{
+	struct action_list	*alist = priv;
+
+	action_list_init(alist);
+}
+
 /* Verify all the inodes in a filesystem. */
 int
 phase3_func(
@@ -231,17 +258,18 @@ phase3_func(
 	xfs_agnumber_t		agno;
 	int			err;
 
+	err = -ptvar_alloc(scrub_nproc(ctx), sizeof(struct action_list),
+			action_ptlist_init, &ictx.repair_ptlists);
+	if (err) {
+		str_liberror(ctx, err,
+	_("creating per-thread file repair item lists"));
+		return err;
+	}
+
 	err = ptcounter_alloc(scrub_nproc(ctx), &ictx.icount);
 	if (err) {
 		str_liberror(ctx, err, _("creating scanned inode counter"));
-		return err;
-	}
-
-	ictx.locks = calloc(ctx->mnt.fsgeom.agcount, sizeof(pthread_mutex_t));
-	if (!ictx.locks) {
-		str_errno(ctx, _("creating per-AG repair list locks"));
-		err = ENOMEM;
-		goto out_ptcounter;
+		goto out_ptvar;
 	}
 
 	/*
@@ -250,9 +278,7 @@ phase3_func(
 	 * to repair the space metadata.
 	 */
 	for (agno = 0; agno < ctx->mnt.fsgeom.agcount; agno++) {
-		pthread_mutex_init(&ictx.locks[agno], NULL);
-
-		if (!action_list_empty(&ctx->action_lists[agno]))
+		if (!action_list_empty(ctx->action_list))
 			ictx.always_defer_repairs = true;
 	}
 
@@ -260,22 +286,30 @@ phase3_func(
 	if (!err && ictx.aborted)
 		err = ECANCELED;
 	if (err)
-		goto out_locks;
+		goto out_ptcounter;
+
+	/*
+	 * Combine all of the file repair items into the main repair list.
+	 * We don't need locks here since we're the only thread running now.
+	 */
+	err = -ptvar_foreach(ictx.repair_ptlists, collect_repairs, ctx);
+	if (err) {
+		str_liberror(ctx, err, _("collecting inode repair lists"));
+		goto out_ptcounter;
+	}
 
 	scrub_report_preen_triggers(ctx);
 	err = ptcounter_value(ictx.icount, &val);
 	if (err) {
 		str_liberror(ctx, err, _("summing scanned inode counter"));
-		goto out_locks;
+		goto out_ptcounter;
 	}
 
 	ctx->inodes_checked = val;
-out_locks:
-	for (agno = 0; agno < ctx->mnt.fsgeom.agcount; agno++)
-		pthread_mutex_destroy(&ictx.locks[agno]);
-	free(ictx.locks);
 out_ptcounter:
 	ptcounter_free(ictx.icount);
+out_ptvar:
+	ptvar_free(ictx.repair_ptlists);
 	return err;
 }
 
diff --git a/scrub/phase4.c b/scrub/phase4.c
index 3c51b38a55e..564ccb82704 100644
--- a/scrub/phase4.c
+++ b/scrub/phase4.c
@@ -17,57 +17,170 @@
 #include "scrub.h"
 #include "repair.h"
 #include "vfs.h"
+#include "atomic.h"
 
 /* Phase 4: Repair filesystem. */
 
-/* Fix all the problems in our per-AG list. */
+struct repair_list_schedule {
+	struct action_list		*repair_list;
+
+	/* Action items that we could not resolve and want to try again. */
+	struct action_list		requeue_list;
+
+	pthread_mutex_t			lock;
+
+	/* Workers use this to signal the scheduler when all work is done. */
+	pthread_cond_t			done;
+
+	/* Number of workers that are still running. */
+	unsigned int			workers;
+
+	/* Or should we all abort? */
+	bool				aborted;
+
+	/* Did we make any progress this round? */
+	bool				made_progress;
+};
+
+/* Try to repair as many things on our list as we can. */
 static void
-repair_ag(
+repair_list_worker(
 	struct workqueue		*wq,
 	xfs_agnumber_t			agno,
 	void				*priv)
 {
+	struct repair_list_schedule	*rls = priv;
 	struct scrub_ctx		*ctx = (struct scrub_ctx *)wq->wq_ctx;
-	bool				*aborted = priv;
-	struct action_list		*alist;
-	unsigned long long		unfixed;
-	unsigned long long		new_unfixed;
-	unsigned int			flags = 0;
-	int				ret;
-
-	alist = &ctx->action_lists[agno];
-	unfixed = action_list_length(alist);
-
-	/* Repair anything broken until we fail to make progress. */
-	do {
-		ret = action_list_process(ctx, alist, flags);
+
+	pthread_mutex_lock(&rls->lock);
+	while (!rls->aborted) {
+		struct action_item	*aitem;
+		enum tryrepair_outcome	outcome;
+		int			ret;
+
+		aitem = action_list_pop(rls->repair_list);
+		if (!aitem)
+			break;
+
+		pthread_mutex_unlock(&rls->lock);
+		ret = action_item_try_repair(ctx, aitem, &outcome);
+		pthread_mutex_lock(&rls->lock);
+
 		if (ret) {
-			*aborted = true;
-			return;
+			rls->aborted = true;
+			free(aitem);
+			break;
 		}
-		new_unfixed = action_list_length(alist);
-		if (new_unfixed == unfixed)
+
+		switch (outcome) {
+		case TR_REQUEUE:
+			/*
+			 * Partial progress.  Make a note of that and requeue
+			 * this item for the next round.
+			 */
+			rls->made_progress = true;
+			action_list_add(&rls->requeue_list, aitem);
+			break;
+		case TR_NOPROGRESS:
+			/*
+			 * No progress.  Requeue this item for a later round,
+			 * which could happen if something else makes progress.
+			 */
+			action_list_add(&rls->requeue_list, aitem);
 			break;
-		unfixed = new_unfixed;
-		if (*aborted)
-			return;
-	} while (unfixed > 0);
-
-	/* Try once more, but this time complain if we can't fix things. */
-	flags |= XRM_FINAL_WARNING;
-	ret = action_list_process(ctx, alist, flags);
-	if (ret)
-		*aborted = true;
+		case TR_REPAIRED:
+			/*
+			 * All repairs for this item completed.  Free the item,
+			 * and remember that progress was made.
+			 */
+			rls->made_progress = true;
+			free(aitem);
+			break;
+		}
+	}
+
+	rls->workers--;
+	if (rls->workers == 0)
+		pthread_cond_broadcast(&rls->done);
+	pthread_mutex_unlock(&rls->lock);
+}
+
+/*
+ * Schedule repair list workers.  Returns 1 if we made progress, 0 if we
+ * did not, or -1 if we need to abort everything.
+ */
+static int
+repair_list_schedule(
+	struct scrub_ctx		*ctx,
+	struct workqueue		*wq,
+	struct action_list		*repair_list)
+{
+	struct repair_list_schedule	rls = {
+		.lock			= PTHREAD_MUTEX_INITIALIZER,
+		.done			= PTHREAD_COND_INITIALIZER,
+		.repair_list		= repair_list,
+	};
+	unsigned int			i;
+	unsigned int			nr_workers = scrub_nproc(ctx);
+	bool				made_any_progress = false;
+	int				ret = 0;
+
+	if (action_list_empty(repair_list))
+		return 0;
+
+	action_list_init(&rls.requeue_list);
+
+	/*
+	 * Use the workers to run through the entire repair list once.  Requeue
+	 * anything that did not make progress, and keep trying as long as the
+	 * workers made any kind of progress.
+	 */
+	do {
+		rls.made_progress = false;
+
+		/* Start all the worker threads. */
+		for (i = 0; i < nr_workers; i++) {
+			pthread_mutex_lock(&rls.lock);
+			rls.workers++;
+			pthread_mutex_unlock(&rls.lock);
+
+			ret = -workqueue_add(wq, repair_list_worker, 0, &rls);
+			if (ret) {
+				str_liberror(ctx, ret,
+ _("queueing repair list worker"));
+				pthread_mutex_lock(&rls.lock);
+				rls.workers--;
+				pthread_mutex_unlock(&rls.lock);
+				break;
+			}
+		}
+
+		/* Wait for all worker functions to return. */
+		pthread_mutex_lock(&rls.lock);
+		while (rls.workers > 0)
+			pthread_cond_wait(&rls.done, &rls.lock);
+		pthread_mutex_unlock(&rls.lock);
+
+		action_list_merge(repair_list, &rls.requeue_list);
+
+		if (ret || rls.aborted)
+			return -1;
+		if (rls.made_progress)
+			made_any_progress = true;
+	} while (rls.made_progress && !action_list_empty(repair_list));
+
+	if (made_any_progress)
+	       return 1;
+	return 0;
 }
 
-/* Process all the action items. */
+/* Process both repair lists. */
 static int
 repair_everything(
 	struct scrub_ctx		*ctx)
 {
 	struct workqueue		wq;
-	xfs_agnumber_t			agno;
-	bool				aborted = false;
+	int				fixed_anything;
 	int				ret;
 
 	ret = -workqueue_create(&wq, (struct xfs_mount *)ctx,
@@ -76,41 +189,32 @@ repair_everything(
 		str_liberror(ctx, ret, _("creating repair workqueue"));
 		return ret;
 	}
-	for (agno = 0; !aborted && agno < ctx->mnt.fsgeom.agcount; agno++) {
-		if (action_list_length(&ctx->action_lists[agno]) == 0)
-			continue;
 
-		ret = -workqueue_add(&wq, repair_ag, agno, &aborted);
-		if (ret) {
-			str_liberror(ctx, ret, _("queueing repair work"));
+	/*
+	 * Try to fix everything on the space metadata repair list and then the
+	 * file repair list until we stop making progress.  These repairs can
+	 * be threaded, if the user desires.
+	 */
+	do {
+		fixed_anything = 0;
+
+		ret = repair_list_schedule(ctx, &wq, ctx->action_list);
+		if (ret < 0)
 			break;
-		}
-	}
+		if (ret == 1)
+			fixed_anything++;
+	} while (fixed_anything > 0);
 
 	ret = -workqueue_terminate(&wq);
 	if (ret)
 		str_liberror(ctx, ret, _("finishing repair work"));
 	workqueue_destroy(&wq);
 
-	if (aborted)
-		return ECANCELED;
+	if (ret < 0)
+		return ret;
 
-	return 0;
-}
-
-/* Decide if we have any repair work to do. */
-static inline bool
-have_action_items(
-	struct scrub_ctx	*ctx)
-{
-	xfs_agnumber_t		agno;
-
-	for (agno = 0; agno < ctx->mnt.fsgeom.agcount; agno++) {
-		if (action_list_length(&ctx->action_lists[agno]) > 0)
-			return true;
-	}
-
-	return false;
+	/* Repair everything serially.  Last chance to fix things. */
+	return action_list_process(ctx, ctx->action_list, XRM_FINAL_WARNING);
 }
 
 /* Trim the unused areas of the filesystem if the caller asked us to. */
@@ -132,7 +236,7 @@ phase4_func(
 	struct scrub_item	sri;
 	int			ret;
 
-	if (!have_action_items(ctx))
+	if (action_list_empty(ctx->action_list))
 		goto maybe_trim;
 
 	/*
@@ -190,12 +294,12 @@ phase4_estimate(
 	unsigned int		*nr_threads,
 	int			*rshift)
 {
-	xfs_agnumber_t		agno;
-	unsigned long long	need_fixing = 0;
+	unsigned long long	need_fixing;
 
-	for (agno = 0; agno < ctx->mnt.fsgeom.agcount; agno++)
-		need_fixing += action_list_length(&ctx->action_lists[agno]);
+	/* Everything on the repair list plus FSTRIM. */
+	need_fixing = action_list_length(ctx->action_list);
 	need_fixing++;
+
 	*items = need_fixing;
 	*nr_threads = scrub_nproc(ctx) + 1;
 	*rshift = 0;
diff --git a/scrub/repair.c b/scrub/repair.c
index c427e6e95f0..eba936e1fd1 100644
--- a/scrub/repair.c
+++ b/scrub/repair.c
@@ -396,58 +396,41 @@ repair_item_difficulty(
 	return ret;
 }
 
-/*
- * Allocate a certain number of repair lists for the scrub context.  Returns
- * zero or a positive error number.
- */
+/* Create a new repair action list. */
 int
-action_lists_alloc(
-	size_t				nr,
-	struct action_list		**listsp)
+action_list_alloc(
+	struct action_list		**listp)
 {
-	struct action_list		*lists;
-	xfs_agnumber_t			agno;
+	struct action_list		*alist;
 
-	lists = calloc(nr, sizeof(struct action_list));
-	if (!lists)
+	alist = malloc(sizeof(struct action_list));
+	if (!alist)
 		return errno;
 
-	for (agno = 0; agno < nr; agno++)
-		action_list_init(&lists[agno]);
-	*listsp = lists;
-
+	action_list_init(alist);
+	*listp = alist;
 	return 0;
 }
 
-/* Discard repair list contents. */
+/* Free the repair lists. */
 void
-action_list_discard(
-	struct action_list		*alist)
+action_list_free(
+	struct action_list		**listp)
 {
+	struct action_list		*alist = *listp;
 	struct action_item		*aitem;
 	struct action_item		*n;
 
+	if (!(*listp))
+		return;
+
 	list_for_each_entry_safe(aitem, n, &alist->list, list) {
 		list_del(&aitem->list);
 		free(aitem);
 	}
-}
 
-/* Free the repair lists. */
-void
-action_lists_free(
-	struct action_list		**listsp)
-{
-	free(*listsp);
-	*listsp = NULL;
-}
-
-/* Initialize repair list */
-void
-action_list_init(
-	struct action_list		*alist)
-{
-	INIT_LIST_HEAD(&alist->list);
+	free(alist);
+	*listp = NULL;
 }
 
 /* Number of pending repairs in this list. */
@@ -464,7 +447,23 @@ action_list_length(
 	return ret;
 }
 
-/* Add to the list of repairs. */
+/* Remove the first action item from the action list. */
+struct action_item *
+action_list_pop(
+	struct action_list		*alist)
+{
+	struct action_item		*aitem;
+
+	aitem = list_first_entry_or_null(&alist->list, struct action_item,
+			list);
+	if (!aitem)
+		return NULL;
+
+	list_del_init(&aitem->list);
+	return aitem;
+}
+
+/* Add an action item to the end of a list. */
 void
 action_list_add(
 	struct action_list		*alist,
@@ -473,6 +472,46 @@ action_list_add(
 	list_add_tail(&aitem->list, &alist->list);
 }
 
+/*
+ * Try to repair a filesystem object and let the caller know what it should do
+ * with the action item.  The caller must be able to requeue action items, so
+ * we don't complain if repairs are not totally successful.
+ */
+int
+action_item_try_repair(
+	struct scrub_ctx	*ctx,
+	struct action_item	*aitem,
+	enum tryrepair_outcome	*outcome)
+{
+	struct scrub_item	*sri = &aitem->sri;
+	unsigned int		before, after;
+	int			ret;
+
+	before = repair_item_count_needsrepair(sri);
+
+	ret = repair_item(ctx, sri, 0);
+	if (ret)
+		return ret;
+
+	after = repair_item_count_needsrepair(sri);
+	if (after > 0) {
+		/*
+		 * The kernel did not complete all of the repairs requested.
+		 * If it made some progress we'll requeue; otherwise, let the
+		 * caller know that nothing got fixed.
+		 */
+		if (before != after)
+			*outcome = TR_REQUEUE;
+		else
+			*outcome = TR_NOPROGRESS;
+		return 0;
+	}
+
+	/* Repairs complete. */
+	*outcome = TR_REPAIRED;
+	return 0;
+}
+
 /* Repair everything on this list. */
 int
 action_list_process(
@@ -676,29 +715,3 @@ repair_item_to_action_item(
 	*aitemp = aitem;
 	return 0;
 }
-
-/* Defer all the repairs until phase 4. */
-int
-repair_item_defer(
-	struct scrub_ctx	*ctx,
-	const struct scrub_item	*sri)
-{
-	struct action_item	*aitem = NULL;
-	unsigned int		agno;
-	int			error;
-
-	error = repair_item_to_action_item(ctx, sri, &aitem);
-	if (error || !aitem)
-		return error;
-
-	if (sri->sri_agno != -1U)
-		agno = sri->sri_agno;
-	else if (sri->sri_ino != -1ULL && sri->sri_gen != -1U)
-		agno = cvt_ino_to_agno(&ctx->mnt, sri->sri_ino);
-	else
-		agno = 0;
-	ASSERT(agno < ctx->mnt.fsgeom.agcount);
-
-	action_list_add(&ctx->action_lists[agno], aitem);
-	return 0;
-}
diff --git a/scrub/repair.h b/scrub/repair.h
index a38cdd5e6df..a685e90374c 100644
--- a/scrub/repair.h
+++ b/scrub/repair.h
@@ -12,19 +12,43 @@ struct action_list {
 
 struct action_item;
 
-int action_lists_alloc(size_t nr, struct action_list **listsp);
-void action_lists_free(struct action_list **listsp);
+int action_list_alloc(struct action_list **listp);
+void action_list_free(struct action_list **listp);
+static inline void action_list_init(struct action_list *alist)
+{
+	INIT_LIST_HEAD(&alist->list);
+}
 
-void action_list_init(struct action_list *alist);
+unsigned long long action_list_length(struct action_list *alist);
+
+/* Move all the items of @src to the tail of @dst, and reinitialize @src. */
+static inline void
+action_list_merge(
+	struct action_list	*dst,
+	struct action_list	*src)
+{
+	list_splice_tail_init(&src->list, &dst->list);
+}
+
+struct action_item *action_list_pop(struct action_list *alist);
+void action_list_add(struct action_list *alist, struct action_item *aitem);
 
 static inline bool action_list_empty(const struct action_list *alist)
 {
 	return list_empty(&alist->list);
 }
 
-unsigned long long action_list_length(struct action_list *alist);
-void action_list_add(struct action_list *dest, struct action_item *item);
-void action_list_discard(struct action_list *alist);
+enum tryrepair_outcome {
+	/* No progress was made on repairs at all. */
+	TR_NOPROGRESS = 0,
+	/* Some progress was made on repairs; try again soon. */
+	TR_REQUEUE,
+	/* Repairs completely successful. */
+	TR_REPAIRED,
+};
+
+int action_item_try_repair(struct scrub_ctx *ctx, struct action_item *aitem,
+		enum tryrepair_outcome *outcome);
 
 void repair_item_mustfix(struct scrub_item *sri, struct scrub_item *fix_now);
 
@@ -56,7 +80,6 @@ int repair_item(struct scrub_ctx *ctx, struct scrub_item *sri,
 		unsigned int repair_flags);
 int repair_item_to_action_item(struct scrub_ctx *ctx,
 		const struct scrub_item *sri, struct action_item **aitemp);
-int repair_item_defer(struct scrub_ctx *ctx, const struct scrub_item *sri);
 
 static inline unsigned int
 repair_item_count_needsrepair(
diff --git a/scrub/xfs_scrub.h b/scrub/xfs_scrub.h
index 1151ee9ff3a..a339c4d6348 100644
--- a/scrub/xfs_scrub.h
+++ b/scrub/xfs_scrub.h
@@ -72,7 +72,7 @@ struct scrub_ctx {
 
 	/* Mutable scrub state; use lock. */
 	pthread_mutex_t		lock;
-	struct action_list	*action_lists;
+	struct action_list	*action_list;
 	unsigned long long	max_errors;
 	unsigned long long	runtime_errors;
 	unsigned long long	corruptions_found;

[PATCH 3/4] xfs_scrub: recheck entire metadata objects after corruption repairs

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

When we've finished making repairs to some domain of filesystem metadata
(file, AG, etc.) to correct an inconsistency, we should recheck all the
other metadata types within that domain to make sure that we neither
made things worse nor introduced more cross-referencing problems.  If we
did, requeue the item to make the repairs.  If the only changes we made
were optimizations, don't bother.

The XFS_SCRUB_TYPE_ values are getting close to the max for a u32, so
I chose u64 for sri_selected.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/repair.c        |   37 +++++++++++++++++++++++++++++++++++++
 scrub/scrub.c         |    5 +++--
 scrub/scrub.h         |   10 ++++++++++
 scrub/scrub_private.h |    2 ++
 4 files changed, 52 insertions(+), 2 deletions(-)


diff --git a/scrub/repair.c b/scrub/repair.c
index eba936e1fd1..19f5c9052af 100644
--- a/scrub/repair.c
+++ b/scrub/repair.c
@@ -485,8 +485,10 @@ action_item_try_repair(
 {
 	struct scrub_item	*sri = &aitem->sri;
 	unsigned int		before, after;
+	unsigned int		scrub_type;
 	int			ret;
 
+	BUILD_BUG_ON(sizeof(sri->sri_selected) * NBBY < XFS_SCRUB_TYPE_NR);
 	before = repair_item_count_needsrepair(sri);
 
 	ret = repair_item(ctx, sri, 0);
@@ -507,6 +509,41 @@ action_item_try_repair(
 		return 0;
 	}
 
+	/*
+	 * Nothing in this fs object was marked inconsistent.  This means we
+	 * were merely optimizing metadata and there is no revalidation work to
+	 * be done.
+	 */
+	if (!sri->sri_inconsistent) {
+		*outcome = TR_REPAIRED;
+		return 0;
+	}
+
+	/*
+	 * We fixed inconsistent metadata, so reschedule the entire object for
+	 * immediate revalidation to see if anything else went wrong.
+	 */
+	foreach_scrub_type(scrub_type)
+		if (sri->sri_selected & (1ULL << scrub_type))
+			sri->sri_state[scrub_type] = SCRUB_ITEM_NEEDSCHECK;
+	sri->sri_inconsistent = false;
+	sri->sri_revalidate = true;
+
+	ret = scrub_item_check(ctx, sri);
+	if (ret)
+		return ret;
+
+	after = repair_item_count_needsrepair(sri);
+	if (after > 0) {
+		/*
+		 * Uhoh, we found something else broken.  Tell the caller that
+		 * this item needs to be queued for more repairs.
+		 */
+		sri->sri_revalidate = false;
+		*outcome = TR_REQUEUE;
+		return 0;
+	}
+
 	/* Repairs complete. */
 	*outcome = TR_REPAIRED;
 	return 0;
diff --git a/scrub/scrub.c b/scrub/scrub.c
index 69dfb1eb84d..2b6b6274e38 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -117,11 +117,12 @@ xfs_check_metadata(
 	dbg_printf("check %s flags %xh\n", descr_render(&dsc), meta.sm_flags);
 
 	error = -xfrog_scrub_metadata(xfdp, &meta);
-	if (debug_tweak_on("XFS_SCRUB_FORCE_REPAIR") && !error)
-		meta.sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
 	switch (error) {
 	case 0:
 		/* No operational errors encountered. */
+		if (!sri->sri_revalidate &&
+		    debug_tweak_on("XFS_SCRUB_FORCE_REPAIR"))
+			meta.sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
 		break;
 	case ENOENT:
 		/* Metadata not present, just skip it. */
diff --git a/scrub/scrub.h b/scrub/scrub.h
index 246c923f490..90578108a1c 100644
--- a/scrub/scrub.h
+++ b/scrub/scrub.h
@@ -59,11 +59,20 @@ struct scrub_item {
 	__u32			sri_gen;
 	__u32			sri_agno;
 
+	/* Bitmask of scrub types that were scheduled here. */
+	__u64			sri_selected;
+
 	/* Scrub item state flags, one for each XFS_SCRUB_TYPE. */
 	__u8			sri_state[XFS_SCRUB_TYPE_NR];
 
 	/* Track scrub and repair call retries for each scrub type. */
 	__u8			sri_tries[XFS_SCRUB_TYPE_NR];
+
+	/* Were there any corruption repairs needed? */
+	bool			sri_inconsistent:1;
+
+	/* Are we revalidating after repairs? */
+	bool			sri_revalidate:1;
 };
 
 #define foreach_scrub_type(loopvar) \
@@ -103,6 +112,7 @@ static inline void
 scrub_item_schedule(struct scrub_item *sri, unsigned int scrub_type)
 {
 	sri->sri_state[scrub_type] = SCRUB_ITEM_NEEDSCHECK;
+	sri->sri_selected |= (1ULL << scrub_type);
 }
 
 void scrub_item_schedule_group(struct scrub_item *sri,
diff --git a/scrub/scrub_private.h b/scrub/scrub_private.h
index 234b30ef2b8..bcfabda16be 100644
--- a/scrub/scrub_private.h
+++ b/scrub/scrub_private.h
@@ -71,6 +71,8 @@ scrub_item_save_state(
 	unsigned  int			scrub_flags)
 {
 	sri->sri_state[scrub_type] = scrub_flags & SCRUB_ITEM_REPAIR_ANY;
+	if (scrub_flags & SCRUB_ITEM_NEEDSREPAIR)
+		sri->sri_inconsistent = true;
 }
 
 static inline void

[PATCH 4/4] xfs_scrub: try to repair space metadata before file metadata

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Phase 4 (metadata repairs) of xfs_scrub has suffered a mild race
condition since the beginning of its existence.  Repair functions for
higher level metadata such as directories build the new directory blocks
in an unlinked temporary file and use atomic extent swapping to commit
the corrected directory contents into the existing directory.  Atomic
extent swapping requires consistent filesystem space metadata, but phase
4 has never enforced correctness dependencies between space and file
metadata repairs.

Before the previous patch eliminated the per-AG repair lists, this error
was not often hit in testing scenarios because the allocator generally
succeeds in placing file data blocks in the same AG as the inode.  With
pool threads now able to pop file repairs from the repair list before
space repairs complete, this error became much more obvious.

Fortunately, the new phase 4 design makes it easy to try to enforce the
consistency requirements of higher level file metadata repairs.  Split
the repair list into one for space metadata and another for file
metadata.  Phase 4 will now try to fix the space metadata until it stops
making progress on that, and only then will it try to fix file metadata.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase1.c    |   13 ++++++++++---
 scrub/phase2.c    |    2 +-
 scrub/phase3.c    |    4 ++--
 scrub/phase4.c    |   22 +++++++++++++++++-----
 scrub/xfs_scrub.h |    3 ++-
 5 files changed, 32 insertions(+), 12 deletions(-)


diff --git a/scrub/phase1.c b/scrub/phase1.c
index 78769a57bf1..1b3f6e8eb4f 100644
--- a/scrub/phase1.c
+++ b/scrub/phase1.c
@@ -89,7 +89,8 @@ scrub_cleanup(
 	if (error)
 		return error;
 
-	action_list_free(&ctx->action_list);
+	action_list_free(&ctx->file_repair_list);
+	action_list_free(&ctx->fs_repair_list);
 
 	if (ctx->fshandle)
 		free_handle(ctx->fshandle, ctx->fshandle_len);
@@ -186,9 +187,15 @@ _("Not an XFS filesystem."));
 		return error;
 	}
 
-	error = action_list_alloc(&ctx->action_list);
+	error = action_list_alloc(&ctx->fs_repair_list);
 	if (error) {
-		str_liberror(ctx, error, _("allocating repair list"));
+		str_liberror(ctx, error, _("allocating fs repair list"));
+		return error;
+	}
+
+	error = action_list_alloc(&ctx->file_repair_list);
+	if (error) {
+		str_liberror(ctx, error, _("allocating file repair list"));
 		return error;
 	}
 
diff --git a/scrub/phase2.c b/scrub/phase2.c
index 5803d8c645a..57c6d0ef213 100644
--- a/scrub/phase2.c
+++ b/scrub/phase2.c
@@ -64,7 +64,7 @@ defer_fs_repair(
 		return error;
 
 	pthread_mutex_lock(&ctx->lock);
-	action_list_add(ctx->action_list, aitem);
+	action_list_add(ctx->fs_repair_list, aitem);
 	pthread_mutex_unlock(&ctx->lock);
 	return 0;
 }
diff --git a/scrub/phase3.c b/scrub/phase3.c
index 1a71d4ace48..98e5c5a1f9f 100644
--- a/scrub/phase3.c
+++ b/scrub/phase3.c
@@ -234,7 +234,7 @@ collect_repairs(
 	struct scrub_ctx	*ctx = foreach_arg;
 	struct action_list	*alist = data;
 
-	action_list_merge(ctx->action_list, alist);
+	action_list_merge(ctx->file_repair_list, alist);
 	return 0;
 }
 
@@ -278,7 +278,7 @@ phase3_func(
 	 * to repair the space metadata.
 	 */
 	for (agno = 0; agno < ctx->mnt.fsgeom.agcount; agno++) {
-		if (!action_list_empty(ctx->action_list))
+		if (!action_list_empty(ctx->fs_repair_list))
 			ictx.always_defer_repairs = true;
 	}
 
diff --git a/scrub/phase4.c b/scrub/phase4.c
index 564ccb82704..9080d38818f 100644
--- a/scrub/phase4.c
+++ b/scrub/phase4.c
@@ -198,7 +198,13 @@ repair_everything(
 	do {
 		fixed_anything = 0;
 
-		ret = repair_list_schedule(ctx, &wq, ctx->action_list);
+		ret = repair_list_schedule(ctx, &wq, ctx->fs_repair_list);
+		if (ret < 0)
+			break;
+		if (ret == 1)
+			fixed_anything++;
+
+		ret = repair_list_schedule(ctx, &wq, ctx->file_repair_list);
 		if (ret < 0)
 			break;
 		if (ret == 1)
@@ -213,8 +219,12 @@ repair_everything(
 	if (ret < 0)
 		return ret;
 
-	/* Repair everything serially.  Last chance to fix things. */
-	return action_list_process(ctx, ctx->action_list, XRM_FINAL_WARNING);
+	/*
+	 * Combine both repair lists and repair everything serially.  This is
+	 * the last chance to fix things.
+	 */
+	action_list_merge(ctx->fs_repair_list, ctx->file_repair_list);
+	return action_list_process(ctx, ctx->fs_repair_list, XRM_FINAL_WARNING);
 }
 
 /* Trim the unused areas of the filesystem if the caller asked us to. */
@@ -236,7 +246,8 @@ phase4_func(
 	struct scrub_item	sri;
 	int			ret;
 
-	if (action_list_empty(ctx->action_list))
+	if (action_list_empty(ctx->fs_repair_list) &&
+	    action_list_empty(ctx->file_repair_list))
 		goto maybe_trim;
 
 	/*
@@ -297,7 +308,8 @@ phase4_estimate(
 	unsigned long long	need_fixing;
 
 	/* Everything on the repair list plus FSTRIM. */
-	need_fixing = action_list_length(ctx->action_list);
+	need_fixing = action_list_length(ctx->fs_repair_list) +
+		      action_list_length(ctx->file_repair_list);
 	need_fixing++;
 
 	*items = need_fixing;
diff --git a/scrub/xfs_scrub.h b/scrub/xfs_scrub.h
index a339c4d6348..ed86d0093db 100644
--- a/scrub/xfs_scrub.h
+++ b/scrub/xfs_scrub.h
@@ -72,7 +72,8 @@ struct scrub_ctx {
 
 	/* Mutable scrub state; use lock. */
 	pthread_mutex_t		lock;
-	struct action_list	*action_list;
+	struct action_list	*fs_repair_list;
+	struct action_list	*file_repair_list;
 	unsigned long long	max_errors;
 	unsigned long long	runtime_errors;
 	unsigned long long	corruptions_found;

[PATCH 01/13] xfs_scrub: use proper UChar string iterators

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

For code that wants to examine a UChar string, use libicu's string
iterators to walk UChar strings, instead of the open-coded U16_NEXT*
macros that perform no typechecking.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/unicrash.c |    7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)


diff --git a/scrub/unicrash.c b/scrub/unicrash.c
index dd30164354e..02a1b94efb4 100644
--- a/scrub/unicrash.c
+++ b/scrub/unicrash.c
@@ -330,13 +330,12 @@ name_entry_examine(
 	struct name_entry	*entry,
 	unsigned int		*badflags)
 {
+	UCharIterator		uiter;
 	UChar32			uchr;
-	int32_t			i;
 	uint8_t			mask = 0;
 
-	for (i = 0; i < entry->normstrlen;) {
-		U16_NEXT_UNSAFE(entry->normstr, i, uchr);
-
+	uiter_setString(&uiter, entry->normstr, entry->normstrlen);
+	while ((uchr = uiter_next32(&uiter)) != U_SENTINEL) {
 		/* zero width character sequences */
 		switch (uchr) {
 		case 0x200B:	/* zero width space */

[PATCH 02/13] xfs_scrub: hoist code that removes ignorable characters

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Hoist the loop that removes "ignorable" code points from the skeleton
string into a separate function and give the UChar cursors names that
are easier to understand.  Convert the code to use the safe versions of
the U16_ accessor functions.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/unicrash.c |   39 ++++++++++++++++++++++++++-------------
 1 file changed, 26 insertions(+), 13 deletions(-)


diff --git a/scrub/unicrash.c b/scrub/unicrash.c
index 02a1b94efb4..96e20114c48 100644
--- a/scrub/unicrash.c
+++ b/scrub/unicrash.c
@@ -145,6 +145,31 @@ is_utf8_locale(void)
 	return answer;
 }
 
+/*
+ * Remove control/formatting characters from this string and return its new
+ * length.  UChar32 is required for U16_NEXT, despite the name.
+ */
+static int32_t
+remove_ignorable(
+	UChar		*ustr,
+	int32_t		ustrlen)
+{
+	UChar32		uchr;
+	int32_t		src, dest;
+
+	for (src = 0, dest = 0; src < ustrlen; dest = src) {
+		U16_NEXT(ustr, src, ustrlen, uchr);
+		if (!u_isIDIgnorable(uchr))
+			continue;
+		memmove(&ustr[dest], &ustr[src],
+				(ustrlen - src + 1) * sizeof(UChar));
+		ustrlen -= (src - dest);
+		src = dest;
+	}
+
+	return dest;
+}
+
 /*
  * Generate normalized form and skeleton of the name.  If this fails, just
  * forget everything and return false; this is an advisory checker.
@@ -160,9 +185,6 @@ name_entry_compute_checknames(
 	int32_t			normstrlen;
 	int32_t			unistrlen;
 	int32_t			skelstrlen;
-	UChar32			uchr;
-	int32_t			i, j;
-
 	UErrorCode		uerr = U_ZERO_ERROR;
 
 	/* Convert bytestr to unistr for normalization */
@@ -206,16 +228,7 @@ name_entry_compute_checknames(
 	if (U_FAILURE(uerr))
 		goto out_skelstr;
 
-	/* Remove control/formatting characters from skeleton. */
-	for (i = 0, j = 0; i < skelstrlen; j = i) {
-		U16_NEXT_UNSAFE(skelstr, i, uchr);
-		if (!u_isIDIgnorable(uchr))
-			continue;
-		memmove(&skelstr[j], &skelstr[i],
-				(skelstrlen - i + 1) * sizeof(UChar));
-		skelstrlen -= (i - j);
-		i = j;
-	}
+	skelstrlen = remove_ignorable(skelstr, skelstrlen);
 
 	entry->skelstr = skelstr;
 	entry->skelstrlen = skelstrlen;

[PATCH 03/13] xfs_scrub: add a couple of omitted invisible code points

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

I missed a few non-rendering code points in the "zero width"
classification code.  Add them now, and sort the list.

$ wget https://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt
$ grep -E '(zero width|invisible|joiner|application)' -i UnicodeData.txt

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/unicrash.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)


diff --git a/scrub/unicrash.c b/scrub/unicrash.c
index 96e20114c48..fc1adb2caab 100644
--- a/scrub/unicrash.c
+++ b/scrub/unicrash.c
@@ -351,15 +351,17 @@ name_entry_examine(
 	while ((uchr = uiter_next32(&uiter)) != U_SENTINEL) {
 		/* zero width character sequences */
 		switch (uchr) {
+		case 0x034F:	/* combining grapheme joiner */
 		case 0x200B:	/* zero width space */
 		case 0x200C:	/* zero width non-joiner */
 		case 0x200D:	/* zero width joiner */
-		case 0xFEFF:	/* zero width non breaking space */
 		case 0x2060:	/* word joiner */
 		case 0x2061:	/* function application */
 		case 0x2062:	/* invisible times (multiply) */
 		case 0x2063:	/* invisible separator (comma) */
 		case 0x2064:	/* invisible plus (addition) */
+		case 0x2D7F:	/* tifinagh consonant joiner */
+		case 0xFEFF:	/* zero width non breaking space */
 			*badflags |= UNICRASH_ZERO_WIDTH;
 			break;
 		}

[PATCH 04/13] xfs_scrub: avoid potential UAF after freeing a duplicate name entry

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Change the function declaration of unicrash_add to set the caller's
@new_entry to NULL if we detect an updated name entry and do not wish to
continue processing.  This avoids a theoretical UAF if the unicrash_add
caller were to accidentally continue using the pointer.

This isn't an /actual/ UAF because the function formerly set @badflags
to zero, but let's be a little defensive.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/unicrash.c |    9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)


diff --git a/scrub/unicrash.c b/scrub/unicrash.c
index fc1adb2caab..5a61d69705b 100644
--- a/scrub/unicrash.c
+++ b/scrub/unicrash.c
@@ -626,10 +626,11 @@ _("Unicode name \"%s\" in %s could be confused with \"%s\"."),
 static void
 unicrash_add(
 	struct unicrash		*uc,
-	struct name_entry	*new_entry,
+	struct name_entry	**new_entryp,
 	unsigned int		*badflags,
 	struct name_entry	**existing_entry)
 {
+	struct name_entry	*new_entry = *new_entryp;
 	struct name_entry	*entry;
 	size_t			bucket;
 	xfs_dahash_t		hash;
@@ -652,7 +653,7 @@ unicrash_add(
 			entry->ino = new_entry->ino;
 			uc->buckets[bucket] = new_entry->next;
 			name_entry_free(new_entry);
-			*badflags = 0;
+			*new_entryp = NULL;
 			return;
 		}
 
@@ -695,8 +696,8 @@ __unicrash_check_name(
 		return 0;
 
 	name_entry_examine(new_entry, &badflags);
-	unicrash_add(uc, new_entry, &badflags, &dup_entry);
-	if (badflags)
+	unicrash_add(uc, &new_entry, &badflags, &dup_entry);
+	if (new_entry && badflags)
 		unicrash_complain(uc, dsc, namedescr, new_entry, badflags,
 				dup_entry);
 

[PATCH 05/13] xfs_scrub: guard against libicu returning negative buffer lengths

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

The libicu functions u_strFromUTF8, unorm2_normalize, and
uspoof_getSkeleton return int32_t values.  Guard against negative return
values, even though the library itself never does this.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/unicrash.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)


diff --git a/scrub/unicrash.c b/scrub/unicrash.c
index 5a61d69705b..1c0597e52f7 100644
--- a/scrub/unicrash.c
+++ b/scrub/unicrash.c
@@ -189,7 +189,7 @@ name_entry_compute_checknames(
 
 	/* Convert bytestr to unistr for normalization */
 	u_strFromUTF8(NULL, 0, &unistrlen, entry->name, entry->namelen, &uerr);
-	if (uerr != U_BUFFER_OVERFLOW_ERROR)
+	if (uerr != U_BUFFER_OVERFLOW_ERROR || unistrlen < 0)
 		return false;
 	uerr = U_ZERO_ERROR;
 	unistr = calloc(unistrlen + 1, sizeof(UChar));
@@ -203,7 +203,7 @@ name_entry_compute_checknames(
 	/* Normalize the string. */
 	normstrlen = unorm2_normalize(uc->normalizer, unistr, unistrlen, NULL,
 			0, &uerr);
-	if (uerr != U_BUFFER_OVERFLOW_ERROR)
+	if (uerr != U_BUFFER_OVERFLOW_ERROR || normstrlen < 0)
 		goto out_unistr;
 	uerr = U_ZERO_ERROR;
 	normstr = calloc(normstrlen + 1, sizeof(UChar));
@@ -217,7 +217,7 @@ name_entry_compute_checknames(
 	/* Compute skeleton. */
 	skelstrlen = uspoof_getSkeleton(uc->spoof, 0, unistr, unistrlen, NULL,
 			0, &uerr);
-	if (uerr != U_BUFFER_OVERFLOW_ERROR)
+	if (uerr != U_BUFFER_OVERFLOW_ERROR || skelstrlen < 0)
 		goto out_normstr;
 	uerr = U_ZERO_ERROR;
 	skelstr = calloc(skelstrlen + 1, sizeof(UChar));

[PATCH 06/13] xfs_scrub: hoist non-rendering character predicate

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Hoist this predicate code into its own function; we're going to use it
elsewhere later on.  While we're at it, document how we generated this
list in the first place.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/unicrash.c |   45 ++++++++++++++++++++++++++++++---------------
 1 file changed, 30 insertions(+), 15 deletions(-)


diff --git a/scrub/unicrash.c b/scrub/unicrash.c
index 1c0597e52f7..385e42c6acc 100644
--- a/scrub/unicrash.c
+++ b/scrub/unicrash.c
@@ -170,6 +170,34 @@ remove_ignorable(
 	return dest;
 }
 
+/*
+ * Certain unicode codepoints are formatting hints that are not themselves
+ * supposed to be rendered by a display system.  These codepoints can be
+ * encoded in file names to try to confuse users.
+ *
+ * Download https://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt and
+ * $ grep -E '(zero width|invisible|joiner|application)' -i UnicodeData.txt
+ */
+static inline bool is_nonrendering(UChar32 uchr)
+{
+	switch (uchr) {
+	case 0x034F:	/* combining grapheme joiner */
+	case 0x200B:	/* zero width space */
+	case 0x200C:	/* zero width non-joiner */
+	case 0x200D:	/* zero width joiner */
+	case 0x2060:	/* word joiner */
+	case 0x2061:	/* function application */
+	case 0x2062:	/* invisible times (multiply) */
+	case 0x2063:	/* invisible separator (comma) */
+	case 0x2064:	/* invisible plus (addition) */
+	case 0x2D7F:	/* tifinagh consonant joiner */
+	case 0xFEFF:	/* zero width non breaking space */
+		return true;
+	}
+
+	return false;
+}
+
 /*
  * Generate normalized form and skeleton of the name.  If this fails, just
  * forget everything and return false; this is an advisory checker.
@@ -349,22 +377,9 @@ name_entry_examine(
 
 	uiter_setString(&uiter, entry->normstr, entry->normstrlen);
 	while ((uchr = uiter_next32(&uiter)) != U_SENTINEL) {
-		/* zero width character sequences */
-		switch (uchr) {
-		case 0x034F:	/* combining grapheme joiner */
-		case 0x200B:	/* zero width space */
-		case 0x200C:	/* zero width non-joiner */
-		case 0x200D:	/* zero width joiner */
-		case 0x2060:	/* word joiner */
-		case 0x2061:	/* function application */
-		case 0x2062:	/* invisible times (multiply) */
-		case 0x2063:	/* invisible separator (comma) */
-		case 0x2064:	/* invisible plus (addition) */
-		case 0x2D7F:	/* tifinagh consonant joiner */
-		case 0xFEFF:	/* zero width non breaking space */
+		/* characters are invisible */
+		if (is_nonrendering(uchr))
 			*badflags |= UNICRASH_ZERO_WIDTH;
-			break;
-		}
 
 		/* control characters */
 		if (u_iscntrl(uchr))

[PATCH 07/13] xfs_scrub: store bad flags with the name entry

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

When scrub is checking unicode names, there are certain properties of
the directory/attribute/label name itself that it can complain about.
Store these in struct name_entry so that the confusable names detector
can pick this up later.

This restructuring enables a subsequent patch to detect suspicious
sequences in the NFC normalized form of the name without needing to hang
on to that NFC form until the end of processing.  IOWs, it's a memory
usage optimization.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/unicrash.c |  122 ++++++++++++++++++++++++++++--------------------------
 1 file changed, 64 insertions(+), 58 deletions(-)


diff --git a/scrub/unicrash.c b/scrub/unicrash.c
index 385e42c6acc..a770d0d7aae 100644
--- a/scrub/unicrash.c
+++ b/scrub/unicrash.c
@@ -69,6 +69,9 @@ struct name_entry {
 
 	xfs_ino_t		ino;
 
+	/* Everything that we don't like about this name. */
+	unsigned int		badflags;
+
 	/* Raw dirent name */
 	size_t			namelen;
 	char			name[0];
@@ -274,6 +277,55 @@ name_entry_compute_checknames(
 	return false;
 }
 
+/*
+ * Check a name for suspicious elements that have appeared in filename
+ * spoofing attacks.  This includes names that mixed directions or contain
+ * direction overrides control characters, both of which have appeared in
+ * filename spoofing attacks.
+ */
+static unsigned int
+name_entry_examine(
+	const struct name_entry	*entry)
+{
+	UCharIterator		uiter;
+	UChar32			uchr;
+	uint8_t			mask = 0;
+	unsigned int		ret = 0;
+
+	uiter_setString(&uiter, entry->normstr, entry->normstrlen);
+	while ((uchr = uiter_next32(&uiter)) != U_SENTINEL) {
+	/* characters are invisible */
+		if (is_nonrendering(uchr))
+			ret |= UNICRASH_ZERO_WIDTH;
+
+		/* control characters */
+		if (u_iscntrl(uchr))
+			ret |= UNICRASH_CONTROL_CHAR;
+
+		switch (u_charDirection(uchr)) {
+		case U_LEFT_TO_RIGHT:
+			mask |= 0x01;
+			break;
+		case U_RIGHT_TO_LEFT:
+			mask |= 0x02;
+			break;
+		case U_RIGHT_TO_LEFT_OVERRIDE:
+			ret |= UNICRASH_BIDI_OVERRIDE;
+			break;
+		case U_LEFT_TO_RIGHT_OVERRIDE:
+			ret |= UNICRASH_BIDI_OVERRIDE;
+			break;
+		default:
+			break;
+		}
+	}
+
+	/* mixing left-to-right and right-to-left chars */
+	if (mask == 0x3)
+		ret |= UNICRASH_BIDI_MIXED;
+	return ret;
+}
+
 /* Create a new name entry, returns false if we could not succeed. */
 static bool
 name_entry_create(
@@ -299,6 +351,7 @@ name_entry_create(
 	if (!name_entry_compute_checknames(uc, new_entry))
 		goto out;
 
+	new_entry->badflags = name_entry_examine(new_entry);
 	*entry = new_entry;
 	return true;
 
@@ -360,54 +413,6 @@ name_entry_hash(
 	}
 }
 
-/*
- * Check a name for suspicious elements that have appeared in filename
- * spoofing attacks.  This includes names that mixed directions or contain
- * direction overrides control characters, both of which have appeared in
- * filename spoofing attacks.
- */
-static void
-name_entry_examine(
-	struct name_entry	*entry,
-	unsigned int		*badflags)
-{
-	UCharIterator		uiter;
-	UChar32			uchr;
-	uint8_t			mask = 0;
-
-	uiter_setString(&uiter, entry->normstr, entry->normstrlen);
-	while ((uchr = uiter_next32(&uiter)) != U_SENTINEL) {
-		/* characters are invisible */
-		if (is_nonrendering(uchr))
-			*badflags |= UNICRASH_ZERO_WIDTH;
-
-		/* control characters */
-		if (u_iscntrl(uchr))
-			*badflags |= UNICRASH_CONTROL_CHAR;
-
-		switch (u_charDirection(uchr)) {
-		case U_LEFT_TO_RIGHT:
-			mask |= 0x01;
-			break;
-		case U_RIGHT_TO_LEFT:
-			mask |= 0x02;
-			break;
-		case U_RIGHT_TO_LEFT_OVERRIDE:
-			*badflags |= UNICRASH_BIDI_OVERRIDE;
-			break;
-		case U_LEFT_TO_RIGHT_OVERRIDE:
-			*badflags |= UNICRASH_BIDI_OVERRIDE;
-			break;
-		default:
-			break;
-		}
-	}
-
-	/* mixing left-to-right and right-to-left chars */
-	if (mask == 0x3)
-		*badflags |= UNICRASH_BIDI_MIXED;
-}
-
 /* Initialize the collision detector. */
 static int
 unicrash_init(
@@ -638,17 +643,17 @@ _("Unicode name \"%s\" in %s could be confused with \"%s\"."),
  * must be skeletonized according to Unicode TR39 to detect names that
  * could be visually confused with each other.
  */
-static void
+static unsigned int
 unicrash_add(
 	struct unicrash		*uc,
 	struct name_entry	**new_entryp,
-	unsigned int		*badflags,
 	struct name_entry	**existing_entry)
 {
 	struct name_entry	*new_entry = *new_entryp;
 	struct name_entry	*entry;
 	size_t			bucket;
 	xfs_dahash_t		hash;
+	unsigned int		badflags = new_entry->badflags;
 
 	/* Store name in hashtable. */
 	hash = name_entry_hash(new_entry);
@@ -669,28 +674,30 @@ unicrash_add(
 			uc->buckets[bucket] = new_entry->next;
 			name_entry_free(new_entry);
 			*new_entryp = NULL;
-			return;
+			return 0;
 		}
 
 		/* Same normalization? */
 		if (new_entry->normstrlen == entry->normstrlen &&
 		    !u_strcmp(new_entry->normstr, entry->normstr) &&
 		    (uc->compare_ino ? entry->ino != new_entry->ino : true)) {
-			*badflags |= UNICRASH_NOT_UNIQUE;
+			badflags |= UNICRASH_NOT_UNIQUE;
 			*existing_entry = entry;
-			return;
+			break;
 		}
 
 		/* Confusable? */
 		if (new_entry->skelstrlen == entry->skelstrlen &&
 		    !u_strcmp(new_entry->skelstr, entry->skelstr) &&
 		    (uc->compare_ino ? entry->ino != new_entry->ino : true)) {
-			*badflags |= UNICRASH_CONFUSABLE;
+			badflags |= UNICRASH_CONFUSABLE;
 			*existing_entry = entry;
-			return;
+			break;
 		}
 		entry = entry->next;
 	}
+
+	return badflags;
 }
 
 /* Check a name for unicode normalization problems or collisions. */
@@ -704,14 +711,13 @@ __unicrash_check_name(
 {
 	struct name_entry	*dup_entry = NULL;
 	struct name_entry	*new_entry = NULL;
-	unsigned int		badflags = 0;
+	unsigned int		badflags;
 
 	/* If we can't create entry data, just skip it. */
 	if (!name_entry_create(uc, name, ino, &new_entry))
 		return 0;
 
-	name_entry_examine(new_entry, &badflags);
-	unicrash_add(uc, &new_entry, &badflags, &dup_entry);
+	badflags = unicrash_add(uc, &new_entry, &dup_entry);
 	if (new_entry && badflags)
 		unicrash_complain(uc, dsc, namedescr, new_entry, badflags,
 				dup_entry);

[PATCH 08/13] xfs_scrub: rename UNICRASH_ZERO_WIDTH to UNICRASH_INVISIBLE

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

"Zero width" doesn't fully describe what the flag represents -- it gets
set for any codepoint that doesn't render.  Rename it accordingly.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/unicrash.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)


diff --git a/scrub/unicrash.c b/scrub/unicrash.c
index a770d0d7aae..b2baa47ad6c 100644
--- a/scrub/unicrash.c
+++ b/scrub/unicrash.c
@@ -109,7 +109,7 @@ struct unicrash {
 #define UNICRASH_CONTROL_CHAR	(1 << 3)
 
 /* Invisible characters.  Only a problem if we have collisions. */
-#define UNICRASH_ZERO_WIDTH	(1 << 4)
+#define UNICRASH_INVISIBLE	(1 << 4)
 
 /* Multiple names resolve to the same skeleton string. */
 #define UNICRASH_CONFUSABLE	(1 << 5)
@@ -296,7 +296,7 @@ name_entry_examine(
 	while ((uchr = uiter_next32(&uiter)) != U_SENTINEL) {
 	/* characters are invisible */
 		if (is_nonrendering(uchr))
-			ret |= UNICRASH_ZERO_WIDTH;
+			ret |= UNICRASH_INVISIBLE;
 
 		/* control characters */
 		if (u_iscntrl(uchr))
@@ -580,7 +580,7 @@ _("Unicode name \"%s\" in %s renders identically to \"%s\"."),
 	 * confused with another name as a result, we should complain.
 	 * "moo<zerowidthspace>cow" and "moocow" are misleading.
 	 */
-	if ((badflags & UNICRASH_ZERO_WIDTH) &&
+	if ((badflags & UNICRASH_INVISIBLE) &&
 	    (badflags & UNICRASH_CONFUSABLE)) {
 		str_warn(uc->ctx, descr_render(dsc),
 _("Unicode name \"%s\" in %s could be confused with '%s' due to invisible characters."),

[PATCH 09/13] xfs_scrub: type-coerce the UNICRASH_* flags

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Promote this type to something that we can type-check.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/unicrash.c |   30 ++++++++++++++++++------------
 1 file changed, 18 insertions(+), 12 deletions(-)


diff --git a/scrub/unicrash.c b/scrub/unicrash.c
index b2baa47ad6c..25f562b0a36 100644
--- a/scrub/unicrash.c
+++ b/scrub/unicrash.c
@@ -4,6 +4,7 @@
  * Author: Darrick J. Wong <djwong@kernel.org>
  */
 #include "xfs.h"
+#include "xfs_arch.h"
 #include <stdint.h>
 #include <stdlib.h>
 #include <dirent.h>
@@ -56,6 +57,8 @@
  * In other words, skel = remove_invisible(nfd(remap_confusables(nfd(name)))).
  */
 
+typedef unsigned int __bitwise	badname_t;
+
 struct name_entry {
 	struct name_entry	*next;
 
@@ -70,7 +73,7 @@ struct name_entry {
 	xfs_ino_t		ino;
 
 	/* Everything that we don't like about this name. */
-	unsigned int		badflags;
+	badname_t		badflags;
 
 	/* Raw dirent name */
 	size_t			namelen;
@@ -93,26 +96,29 @@ struct unicrash {
 
 /* Things to complain about in Unicode naming. */
 
+/* Everything is ok */
+#define UNICRASH_OK		((__force badname_t)0)
+
 /*
  * Multiple names resolve to the same normalized string and therefore render
  * identically.
  */
-#define UNICRASH_NOT_UNIQUE	(1 << 0)
+#define UNICRASH_NOT_UNIQUE	((__force badname_t)(1U << 0))
 
 /* Name contains directional overrides. */
-#define UNICRASH_BIDI_OVERRIDE	(1 << 1)
+#define UNICRASH_BIDI_OVERRIDE	((__force badname_t)(1U << 1))
 
 /* Name mixes left-to-right and right-to-left characters. */
-#define UNICRASH_BIDI_MIXED	(1 << 2)
+#define UNICRASH_BIDI_MIXED	((__force badname_t)(1U << 2))
 
 /* Control characters in name. */
-#define UNICRASH_CONTROL_CHAR	(1 << 3)
+#define UNICRASH_CONTROL_CHAR	((__force badname_t)(1U << 3))
 
 /* Invisible characters.  Only a problem if we have collisions. */
-#define UNICRASH_INVISIBLE	(1 << 4)
+#define UNICRASH_INVISIBLE	((__force badname_t)(1U << 4))
 
 /* Multiple names resolve to the same skeleton string. */
-#define UNICRASH_CONFUSABLE	(1 << 5)
+#define UNICRASH_CONFUSABLE	((__force badname_t)(1U << 5))
 
 /*
  * We only care about validating utf8 collisions if the underlying
@@ -540,7 +546,7 @@ unicrash_complain(
 	struct descr		*dsc,
 	const char		*what,
 	struct name_entry	*entry,
-	unsigned int		badflags,
+	badname_t		badflags,
 	struct name_entry	*dup_entry)
 {
 	char			*bad1 = NULL;
@@ -643,7 +649,7 @@ _("Unicode name \"%s\" in %s could be confused with \"%s\"."),
  * must be skeletonized according to Unicode TR39 to detect names that
  * could be visually confused with each other.
  */
-static unsigned int
+static badname_t
 unicrash_add(
 	struct unicrash		*uc,
 	struct name_entry	**new_entryp,
@@ -653,7 +659,7 @@ unicrash_add(
 	struct name_entry	*entry;
 	size_t			bucket;
 	xfs_dahash_t		hash;
-	unsigned int		badflags = new_entry->badflags;
+	badname_t		badflags = new_entry->badflags;
 
 	/* Store name in hashtable. */
 	hash = name_entry_hash(new_entry);
@@ -711,14 +717,14 @@ __unicrash_check_name(
 {
 	struct name_entry	*dup_entry = NULL;
 	struct name_entry	*new_entry = NULL;
-	unsigned int		badflags;
+	badname_t		badflags;
 
 	/* If we can't create entry data, just skip it. */
 	if (!name_entry_create(uc, name, ino, &new_entry))
 		return 0;
 
 	badflags = unicrash_add(uc, &new_entry, &dup_entry);
-	if (new_entry && badflags)
+	if (new_entry && badflags != UNICRASH_OK)
 		unicrash_complain(uc, dsc, namedescr, new_entry, badflags,
 				dup_entry);
 

[PATCH 10/13] xfs_scrub: reduce size of struct name_entry

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

libicu doesn't support processing strings longer than 2GB in length, and
we never feed the unicrash code a name longer than about 300 bytes.
Rearrange the structure to reduce the head structure size from 56 bytes
to 44 bytes.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/unicrash.c |   16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)


diff --git a/scrub/unicrash.c b/scrub/unicrash.c
index 25f562b0a36..dfa798b09b0 100644
--- a/scrub/unicrash.c
+++ b/scrub/unicrash.c
@@ -57,18 +57,20 @@
  * In other words, skel = remove_invisible(nfd(remap_confusables(nfd(name)))).
  */
 
-typedef unsigned int __bitwise	badname_t;
+typedef uint16_t __bitwise	badname_t;
 
 struct name_entry {
 	struct name_entry	*next;
 
 	/* NFKC normalized name */
 	UChar			*normstr;
-	size_t			normstrlen;
 
 	/* Unicode skeletonized name */
 	UChar			*skelstr;
-	size_t			skelstrlen;
+
+	/* Lengths for normstr and skelstr */
+	int32_t			normstrlen;
+	int32_t			skelstrlen;
 
 	xfs_ino_t		ino;
 
@@ -76,7 +78,7 @@ struct name_entry {
 	badname_t		badflags;
 
 	/* Raw dirent name */
-	size_t			namelen;
+	uint16_t		namelen;
 	char			name[0];
 };
 #define NAME_ENTRY_SZ(nl)	(sizeof(struct name_entry) + 1 + \
@@ -343,6 +345,12 @@ name_entry_create(
 	struct name_entry	*new_entry;
 	size_t			namelen = strlen(name);
 
+	/* should never happen */
+	if (namelen > UINT16_MAX) {
+		ASSERT(namelen <= UINT16_MAX);
+		return false;
+	}
+
 	/* Create new entry */
 	new_entry = calloc(NAME_ENTRY_SZ(namelen), 1);
 	if (!new_entry)

[PATCH 11/13] xfs_scrub: rename struct unicrash.normalizer

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

We're about to introduce a second normalizer, so change the name of the
existing one to reflect the algorithm that you'll get if you use it.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/unicrash.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)


diff --git a/scrub/unicrash.c b/scrub/unicrash.c
index dfa798b09b0..f6b53276c05 100644
--- a/scrub/unicrash.c
+++ b/scrub/unicrash.c
@@ -87,7 +87,7 @@ struct name_entry {
 struct unicrash {
 	struct scrub_ctx	*ctx;
 	USpoofChecker		*spoof;
-	const UNormalizer2	*normalizer;
+	const UNormalizer2	*nfkc;
 	bool			compare_ino;
 	bool			is_only_root_writeable;
 	size_t			nr_buckets;
@@ -240,7 +240,7 @@ name_entry_compute_checknames(
 		goto out_unistr;
 
 	/* Normalize the string. */
-	normstrlen = unorm2_normalize(uc->normalizer, unistr, unistrlen, NULL,
+	normstrlen = unorm2_normalize(uc->nfkc, unistr, unistrlen, NULL,
 			0, &uerr);
 	if (uerr != U_BUFFER_OVERFLOW_ERROR || normstrlen < 0)
 		goto out_unistr;
@@ -248,7 +248,7 @@ name_entry_compute_checknames(
 	normstr = calloc(normstrlen + 1, sizeof(UChar));
 	if (!normstr)
 		goto out_unistr;
-	unorm2_normalize(uc->normalizer, unistr, unistrlen, normstr, normstrlen,
+	unorm2_normalize(uc->nfkc, unistr, unistrlen, normstr, normstrlen,
 			&uerr);
 	if (U_FAILURE(uerr))
 		goto out_normstr;
@@ -455,7 +455,7 @@ unicrash_init(
 	p->ctx = ctx;
 	p->nr_buckets = nr_buckets;
 	p->compare_ino = compare_ino;
-	p->normalizer = unorm2_getNFKCInstance(&uerr);
+	p->nfkc = unorm2_getNFKCInstance(&uerr);
 	if (U_FAILURE(uerr))
 		goto out_free;
 	p->spoof = uspoof_open(&uerr);

[PATCH 12/13] xfs_scrub: report deceptive file extensions

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Earlier this year, ESET revealed that Linux users had been tricked into
opening executables containing malware payloads.  The trickery came in
the form of a malicious zip file containing a filename with the string
"job offer․pdf".  Note that the filename does *not* denote a real pdf
file, since the last four codepoints in the file name are "ONE DOT
LEADER", p, d, and f.  Not period (ok, FULL STOP), p, d, f like you'd
normally expect.

Teach xfs_scrub to look for codepoints that could be confused with a
period followed by alphanumerics.

Link: https://www.welivesecurity.com/2023/04/20/linux-malware-strengthens-links-lazarus-3cx-supply-chain-attack/
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/unicrash.c |  215 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 214 insertions(+), 1 deletion(-)


diff --git a/scrub/unicrash.c b/scrub/unicrash.c
index f6b53276c05..e895afe32aa 100644
--- a/scrub/unicrash.c
+++ b/scrub/unicrash.c
@@ -88,6 +88,7 @@ struct unicrash {
 	struct scrub_ctx	*ctx;
 	USpoofChecker		*spoof;
 	const UNormalizer2	*nfkc;
+	const UNormalizer2	*nfc;
 	bool			compare_ino;
 	bool			is_only_root_writeable;
 	size_t			nr_buckets;
@@ -122,6 +123,12 @@ struct unicrash {
 /* Multiple names resolve to the same skeleton string. */
 #define UNICRASH_CONFUSABLE	((__force badname_t)(1U << 5))
 
+/* Possible phony file extension. */
+#define UNICRASH_PHONY_EXTENSION ((__force badname_t)(1U << 6))
+
+/* FULL STOP (aka period), 0x2E */
+#define UCHAR_PERIOD		((UChar32)'.')
+
 /*
  * We only care about validating utf8 collisions if the underlying
  * system configuration says we're using utf8.  If the language
@@ -209,6 +216,193 @@ static inline bool is_nonrendering(UChar32 uchr)
 	return false;
 }
 
+/*
+ * Decide if this unicode codepoint looks similar enough to a period (".")
+ * to fool users into thinking that any subsequent alphanumeric sequence is
+ * the file extension.  Most of the fullstop characters do not do this.
+ *
+ * $ grep -i 'full stop' UnicodeData.txt
+ */
+static inline bool is_fullstop_lookalike(UChar32 uchr)
+{
+	switch (uchr) {
+	case 0x0701:	/* syriac supralinear full stop */
+	case 0x0702:	/* syriac sublinear full stop */
+	case 0x2024:	/* one dot leader */
+	case 0xA4F8:	/* lisu letter tone mya ti */
+	case 0xFE52:	/* small full stop */
+	case 0xFF61:	/* haflwidth ideographic full stop */
+	case 0xFF0E:	/* fullwidth full stop */
+		return true;
+	}
+
+	return false;
+}
+
+/* How many UChar do we need to fit a full UChar32 codepoint? */
+#define UCHAR_PER_UCHAR32	2
+
+/* Format this UChar32 into a UChar buffer. */
+static inline int32_t
+uchar32_to_uchar(
+	UChar32		uchr,
+	UChar		*buf)
+{
+	int32_t		i = 0;
+	bool		err = false;
+
+	U16_APPEND(buf, i, UCHAR_PER_UCHAR32, uchr, err);
+	if (err)
+		return 0;
+	return i;
+}
+
+/* Extract a single UChar32 code point from this UChar string. */
+static inline UChar32
+uchar_to_uchar32(
+	UChar		*buf,
+	int32_t		buflen)
+{
+	UChar32		ret;
+	int32_t		i = 0;
+
+	U16_NEXT(buf, i, buflen, ret);
+	return ret;
+}
+
+/*
+ * For characters that are not themselves a full stop (0x2E), let's see if the
+ * compatibility normalization (NFKC) will turn it into a full stop.  If so,
+ * then this could be the start of a phony file extension.
+ */
+static bool
+is_period_lookalike(
+	struct unicrash	*uc,
+	UChar32		uchr)
+{
+	UChar		uchrstr[UCHAR_PER_UCHAR32];
+	UChar		nfkcstr[UCHAR_PER_UCHAR32];
+	int32_t		uchrstrlen, nfkcstrlen;
+	UChar32		nfkc_uchr;
+	UErrorCode	uerr = U_ZERO_ERROR;
+
+	if (uchr == UCHAR_PERIOD)
+		return false;
+
+	uchrstrlen = uchar32_to_uchar(uchr, uchrstr);
+	if (!uchrstrlen)
+		return false;
+
+	/*
+	 * Normalize the UChar string to NFKC form, which does all the
+	 * compatibility transformations.
+	 */
+	nfkcstrlen = unorm2_normalize(uc->nfkc, uchrstr, uchrstrlen, NULL,
+			0, &uerr);
+	if (uerr == U_BUFFER_OVERFLOW_ERROR)
+		return false;
+
+	uerr = U_ZERO_ERROR;
+	unorm2_normalize(uc->nfkc, uchrstr, uchrstrlen, nfkcstr, nfkcstrlen,
+			&uerr);
+	if (U_FAILURE(uerr))
+		return false;
+
+	nfkc_uchr = uchar_to_uchar32(nfkcstr, nfkcstrlen);
+	return nfkc_uchr == UCHAR_PERIOD;
+}
+
+/*
+ * Detect directory entry names that contain deceptive sequences that look like
+ * file extensions but are not.  This we define as a sequence that begins with
+ * a code point that renders like a period ("full stop" in unicode parlance)
+ * but is not actually a period, followed by any number of alphanumeric code
+ * points or a period, all the way to the end.
+ *
+ * The 3cx attack used a zip file containing an executable file named "job
+ * offer․pdf".  Note that the dot mark in the extension is /not/ a period but
+ * the Unicode codepoint "leader dot".  The file was also marked executable
+ * inside the zip file, which meant that naïve file explorers could inflate
+ * the file and restore the execute bit.  If a user double-clicked on the file,
+ * the binary would open a decoy pdf while infecting the system.
+ *
+ * For this check, we need to normalize with canonical (and not compatibility)
+ * decomposition, because compatibility mode will turn certain code points
+ * (e.g. one dot leader, 0x2024) into actual periods (0x2e).  The NFC
+ * composition is not needed after this, so we save some memory by keeping this
+ * a separate function from name_entry_examine.
+ */
+static badname_t
+name_entry_phony_extension(
+	struct unicrash	*uc,
+	const UChar	*unistr,
+	int32_t		unistrlen)
+{
+	UCharIterator	uiter;
+	UChar		*nfcstr;
+	int32_t		nfcstrlen;
+	UChar32		uchr;
+	bool		maybe_phony_extension = false;
+	badname_t	ret = UNICRASH_OK;
+	UErrorCode	uerr = U_ZERO_ERROR;
+
+	/* Normalize with NFC. */
+	nfcstrlen = unorm2_normalize(uc->nfc, unistr, unistrlen, NULL,
+			0, &uerr);
+	if (uerr != U_BUFFER_OVERFLOW_ERROR || nfcstrlen < 0)
+		return ret;
+	uerr = U_ZERO_ERROR;
+	nfcstr = calloc(nfcstrlen + 1, sizeof(UChar));
+	if (!nfcstr)
+		return ret;
+	unorm2_normalize(uc->nfc, unistr, unistrlen, nfcstr, nfcstrlen,
+			&uerr);
+	if (U_FAILURE(uerr))
+		goto out_nfcstr;
+
+	/* Examine the NFC normalized string... */
+	uiter_setString(&uiter, nfcstr, nfcstrlen);
+	while ((uchr = uiter_next32(&uiter)) != U_SENTINEL) {
+		/*
+		 * If this *looks* like, but is not, a full stop (0x2E), this
+		 * could be the start of a phony file extension.
+		 */
+		if (is_period_lookalike(uc, uchr)) {
+			maybe_phony_extension = true;
+			continue;
+		}
+
+		if (is_fullstop_lookalike(uchr)) {
+			/*
+			 * The normalizer above should catch most of these
+			 * codepoints that look like periods, but record the
+			 * ones known to have been used in attacks.
+			 */
+			maybe_phony_extension = true;
+		} else if (uchr == UCHAR_PERIOD) {
+			/*
+			 * Due to the propensity of file explores to obscure
+			 * file extensions in the name of "user friendliness",
+			 * this classifier ignores periods.
+			 */
+		} else {
+			/*
+			 * File extensions (as far as the author knows) tend
+			 * only to use ascii alphanumerics.
+			 */
+			if (maybe_phony_extension &&
+			    !u_isalnum(uchr) && !is_nonrendering(uchr))
+				maybe_phony_extension = false;
+		}
+	}
+	if (maybe_phony_extension)
+		ret |= UNICRASH_PHONY_EXTENSION;
+
+out_nfcstr:
+	free(nfcstr);
+	return ret;
+}
+
 /*
  * Generate normalized form and skeleton of the name.  If this fails, just
  * forget everything and return false; this is an advisory checker.
@@ -269,6 +463,11 @@ name_entry_compute_checknames(
 
 	skelstrlen = remove_ignorable(skelstr, skelstrlen);
 
+	/* Check for deceptive file extensions in directory entry names. */
+	if (entry->ino)
+		entry->badflags |= name_entry_phony_extension(uc, unistr,
+						unistrlen);
+
 	entry->skelstr = skelstr;
 	entry->skelstrlen = skelstrlen;
 	entry->normstr = normstr;
@@ -365,7 +564,7 @@ name_entry_create(
 	if (!name_entry_compute_checknames(uc, new_entry))
 		goto out;
 
-	new_entry->badflags = name_entry_examine(new_entry);
+	new_entry->badflags |= name_entry_examine(new_entry);
 	*entry = new_entry;
 	return true;
 
@@ -456,6 +655,9 @@ unicrash_init(
 	p->nr_buckets = nr_buckets;
 	p->compare_ino = compare_ino;
 	p->nfkc = unorm2_getNFKCInstance(&uerr);
+	if (U_FAILURE(uerr))
+		goto out_free;
+	p->nfc = unorm2_getNFCInstance(&uerr);
 	if (U_FAILURE(uerr))
 		goto out_free;
 	p->spoof = uspoof_open(&uerr);
@@ -602,6 +804,17 @@ _("Unicode name \"%s\" in %s could be confused with '%s' due to invisible charac
 		goto out;
 	}
 
+	/*
+	 * Fake looking file extensions have tricked Linux users into thinking
+	 * that an executable is actually a pdf.  See Lazarus 3cx attack.
+	 */
+	if (badflags & UNICRASH_PHONY_EXTENSION) {
+		str_warn(uc->ctx, descr_render(dsc),
+_("Unicode name \"%s\" in %s contains a possibly deceptive file extension."),
+				bad1, what);
+		goto out;
+	}
+
 	/*
 	 * Unfiltered control characters can mess up your terminal and render
 	 * invisibly in filechooser UIs.

[PATCH 13/13] xfs_scrub: dump unicode points

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add some debug functions to make it easier to query unicode character
properties.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/unicrash.c |   59 ++++++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 57 insertions(+), 2 deletions(-)


diff --git a/scrub/unicrash.c b/scrub/unicrash.c
index e895afe32aa..119656b0b9d 100644
--- a/scrub/unicrash.c
+++ b/scrub/unicrash.c
@@ -5,6 +5,7 @@
  */
 #include "xfs.h"
 #include "xfs_arch.h"
+#include "list.h"
 #include <stdint.h>
 #include <stdlib.h>
 #include <dirent.h>
@@ -1001,14 +1002,68 @@ unicrash_check_fs_label(
 			label, 0);
 }
 
+/* Dump a unicode code point and its properties. */
+static inline void dump_uchar32(UChar32 c)
+{
+	UChar		uchrstr[UCHAR_PER_UCHAR32];
+	const char	*descr;
+	char		buf[16];
+	int32_t		uchrstrlen, buflen;
+	UProperty	p;
+	UErrorCode	uerr = U_ZERO_ERROR;
+
+	printf("Unicode point 0x%x:", c);
+
+	/* Convert UChar32 to UTF8 representation. */
+	uchrstrlen = uchar32_to_uchar(c, uchrstr);
+	if (!uchrstrlen)
+		return;
+
+	u_strToUTF8(buf, sizeof(buf), &buflen, uchrstr, uchrstrlen, &uerr);
+	if (!U_FAILURE(uerr) && buflen > 0) {
+		int32_t	i;
+
+		printf(" \"");
+		for (i = 0; i < buflen; i++)
+			printf("\\x%02x", buf[i]);
+		printf("\"");
+	}
+	printf("\n");
+
+	for (p = 0; p < UCHAR_BINARY_LIMIT; p++) {
+		int	has;
+
+		descr = u_getPropertyName(p, U_LONG_PROPERTY_NAME);
+		if (!descr)
+			descr = u_getPropertyName(p, U_SHORT_PROPERTY_NAME);
+
+		has = u_hasBinaryProperty(c, p) ? 1 : 0;
+		if (descr) {
+			printf("  %s(%u) = %d\n", descr, p, has);
+		} else {
+			printf("  ?(%u) = %d\n", p, has);
+		}
+	}
+}
+
 /* Load libicu and initialize it. */
 bool
 unicrash_load(void)
 {
-	UErrorCode		uerr = U_ZERO_ERROR;
+	char		*dbgstr;
+	UChar32		uchr;
+	UErrorCode	uerr = U_ZERO_ERROR;
 
 	u_init(&uerr);
-	return U_FAILURE(uerr);
+	if (U_FAILURE(uerr))
+		return true;
+
+	dbgstr = getenv("XFS_SCRUB_DUMP_CHAR");
+	if (dbgstr) {
+		uchr = strtol(dbgstr, NULL, 0);
+		dump_uchar32(uchr);
+	}
+	return false;
 }
 
 /* Unload libicu once we're done with it. */

[PATCH 1/8] xfs_scrub: move FITRIM to phase 8

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Issuing discards against the filesystem should be the *last* thing that
xfs_scrub does, after everything else has been checked, repaired, and
found to be clean.  If we can't satisfy all those conditions, we have no
business telling the storage to discard itself.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/Makefile    |    1 +
 scrub/phase4.c    |   30 ++----------------------
 scrub/phase8.c    |   66 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 scrub/xfs_scrub.h |    3 ++
 4 files changed, 73 insertions(+), 27 deletions(-)
 create mode 100644 scrub/phase8.c


diff --git a/scrub/Makefile b/scrub/Makefile
index 24af9716120..af94cf0d684 100644
--- a/scrub/Makefile
+++ b/scrub/Makefile
@@ -65,6 +65,7 @@ phase4.c \
 phase5.c \
 phase6.c \
 phase7.c \
+phase8.c \
 progress.c \
 read_verify.c \
 repair.c \
diff --git a/scrub/phase4.c b/scrub/phase4.c
index 9080d38818f..451101811c9 100644
--- a/scrub/phase4.c
+++ b/scrub/phase4.c
@@ -227,16 +227,6 @@ repair_everything(
 	return action_list_process(ctx, ctx->fs_repair_list, XRM_FINAL_WARNING);
 }
 
-/* Trim the unused areas of the filesystem if the caller asked us to. */
-static void
-trim_filesystem(
-	struct scrub_ctx	*ctx)
-{
-	if (want_fstrim)
-		fstrim(ctx);
-	progress_add(1);
-}
-
 /* Fix everything that needs fixing. */
 int
 phase4_func(
@@ -248,7 +238,7 @@ phase4_func(
 
 	if (action_list_empty(ctx->fs_repair_list) &&
 	    action_list_empty(ctx->file_repair_list))
-		goto maybe_trim;
+		return 0;
 
 	/*
 	 * Check the resource usage counters early.  Normally we do this during
@@ -281,20 +271,7 @@ phase4_func(
 	if (ret)
 		return ret;
 
-	ret = repair_everything(ctx);
-	if (ret)
-		return ret;
-
-	/*
-	 * If errors remain on the filesystem, do not trim anything.  We don't
-	 * have any threads running, so it's ok to skip the ctx lock here.
-	 */
-	if (ctx->corruptions_found || ctx->unfixable_errors != 0)
-		return 0;
-
-maybe_trim:
-	trim_filesystem(ctx);
-	return 0;
+	return repair_everything(ctx);
 }
 
 /* Estimate how much work we're going to do. */
@@ -307,10 +284,9 @@ phase4_estimate(
 {
 	unsigned long long	need_fixing;
 
-	/* Everything on the repair list plus FSTRIM. */
+	/* Everything on the repair lis. */
 	need_fixing = action_list_length(ctx->fs_repair_list) +
 		      action_list_length(ctx->file_repair_list);
-	need_fixing++;
 
 	*items = need_fixing;
 	*nr_threads = scrub_nproc(ctx) + 1;
diff --git a/scrub/phase8.c b/scrub/phase8.c
new file mode 100644
index 00000000000..07726b5b869
--- /dev/null
+++ b/scrub/phase8.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2018-2024 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include <stdint.h>
+#include <dirent.h>
+#include <sys/types.h>
+#include <sys/statvfs.h>
+#include "list.h"
+#include "libfrog/paths.h"
+#include "libfrog/workqueue.h"
+#include "xfs_scrub.h"
+#include "common.h"
+#include "progress.h"
+#include "scrub.h"
+#include "repair.h"
+#include "vfs.h"
+#include "atomic.h"
+
+/* Phase 8: Trim filesystem. */
+
+/* Trim the unused areas of the filesystem if the caller asked us to. */
+static void
+trim_filesystem(
+	struct scrub_ctx	*ctx)
+{
+	fstrim(ctx);
+	progress_add(1);
+}
+
+/* Trim the filesystem, if desired. */
+int
+phase8_func(
+	struct scrub_ctx	*ctx)
+{
+	if (action_list_empty(ctx->fs_repair_list) &&
+	    action_list_empty(ctx->file_repair_list))
+		goto maybe_trim;
+
+	/*
+	 * If errors remain on the filesystem, do not trim anything.  We don't
+	 * have any threads running, so it's ok to skip the ctx lock here.
+	 */
+	if (ctx->corruptions_found || ctx->unfixable_errors != 0)
+		return 0;
+
+maybe_trim:
+	trim_filesystem(ctx);
+	return 0;
+}
+
+/* Estimate how much work we're going to do. */
+int
+phase8_estimate(
+	struct scrub_ctx	*ctx,
+	uint64_t		*items,
+	unsigned int		*nr_threads,
+	int			*rshift)
+{
+	*items = 1;
+	*nr_threads = 1;
+	*rshift = 0;
+	return 0;
+}
diff --git a/scrub/xfs_scrub.h b/scrub/xfs_scrub.h
index ed86d0093db..6272a36879e 100644
--- a/scrub/xfs_scrub.h
+++ b/scrub/xfs_scrub.h
@@ -98,6 +98,7 @@ int phase4_func(struct scrub_ctx *ctx);
 int phase5_func(struct scrub_ctx *ctx);
 int phase6_func(struct scrub_ctx *ctx);
 int phase7_func(struct scrub_ctx *ctx);
+int phase8_func(struct scrub_ctx *ctx);
 
 /* Progress estimator functions */
 unsigned int scrub_estimate_ag_work(struct scrub_ctx *ctx);
@@ -112,5 +113,7 @@ int phase5_estimate(struct scrub_ctx *ctx, uint64_t *items,
 		    unsigned int *nr_threads, int *rshift);
 int phase6_estimate(struct scrub_ctx *ctx, uint64_t *items,
 		    unsigned int *nr_threads, int *rshift);
+int phase8_estimate(struct scrub_ctx *ctx, uint64_t *items,
+		    unsigned int *nr_threads, int *rshift);
 
 #endif /* XFS_SCRUB_XFS_SCRUB_H_ */

[PATCH 2/8] xfs_scrub: ignore phase 8 if the user disabled fstrim

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If the user told us to skip trimming the filesystem, don't run the phase
at all.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/xfs_scrub.c |   11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)


diff --git a/scrub/xfs_scrub.c b/scrub/xfs_scrub.c
index aa68c23c62e..23b2e03865b 100644
--- a/scrub/xfs_scrub.c
+++ b/scrub/xfs_scrub.c
@@ -249,6 +249,7 @@ struct phase_rusage {
 /* Operations for each phase. */
 #define DATASCAN_DUMMY_FN	((void *)1)
 #define REPAIR_DUMMY_FN		((void *)2)
+#define FSTRIM_DUMMY_FN		((void *)3)
 struct phase_ops {
 	char		*descr;
 	int		(*fn)(struct scrub_ctx *ctx);
@@ -429,6 +430,11 @@ run_scrub_phases(
 			.fn = phase7_func,
 			.must_run = true,
 		},
+		{
+			.descr = _("Trim filesystem storage."),
+			.fn = FSTRIM_DUMMY_FN,
+			.estimate_work = phase8_estimate,
+		},
 		{
 			NULL
 		},
@@ -449,6 +455,8 @@ run_scrub_phases(
 		/* Turn on certain phases if user said to. */
 		if (sp->fn == DATASCAN_DUMMY_FN && scrub_data) {
 			sp->fn = phase6_func;
+		} else if (sp->fn == FSTRIM_DUMMY_FN && want_fstrim) {
+			sp->fn = phase8_func;
 		} else if (sp->fn == REPAIR_DUMMY_FN &&
 			   ctx->mode == SCRUB_MODE_REPAIR) {
 			sp->descr = _("Repair filesystem.");
@@ -458,7 +466,8 @@ run_scrub_phases(
 
 		/* Skip certain phases unless they're turned on. */
 		if (sp->fn == REPAIR_DUMMY_FN ||
-		    sp->fn == DATASCAN_DUMMY_FN)
+		    sp->fn == DATASCAN_DUMMY_FN ||
+		    sp->fn == FSTRIM_DUMMY_FN)
 			continue;
 
 		/* Allow debug users to force a particular phase. */

[PATCH 3/8] xfs_scrub: collapse trim_filesystem

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Collapse this two-line helper into the main function since it's trivial.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase8.c |   12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)


diff --git a/scrub/phase8.c b/scrub/phase8.c
index 07726b5b869..e577260a93d 100644
--- a/scrub/phase8.c
+++ b/scrub/phase8.c
@@ -21,15 +21,6 @@
 
 /* Phase 8: Trim filesystem. */
 
-/* Trim the unused areas of the filesystem if the caller asked us to. */
-static void
-trim_filesystem(
-	struct scrub_ctx	*ctx)
-{
-	fstrim(ctx);
-	progress_add(1);
-}
-
 /* Trim the filesystem, if desired. */
 int
 phase8_func(
@@ -47,7 +38,8 @@ phase8_func(
 		return 0;
 
 maybe_trim:
-	trim_filesystem(ctx);
+	fstrim(ctx);
+	progress_add(1);
 	return 0;
 }
 

[PATCH 4/8] xfs_scrub: fix the work estimation for phase 8

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If there are latent errors on the filesystem, we aren't going to do any
work during phase 8 and it makes no sense to add that into the work
estimate for the progress bar.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase8.c |   36 ++++++++++++++++++++++++++----------
 1 file changed, 26 insertions(+), 10 deletions(-)


diff --git a/scrub/phase8.c b/scrub/phase8.c
index e577260a93d..dfe62e8d97b 100644
--- a/scrub/phase8.c
+++ b/scrub/phase8.c
@@ -21,23 +21,35 @@
 
 /* Phase 8: Trim filesystem. */
 
-/* Trim the filesystem, if desired. */
-int
-phase8_func(
+static inline bool
+fstrim_ok(
 	struct scrub_ctx	*ctx)
 {
-	if (action_list_empty(ctx->fs_repair_list) &&
-	    action_list_empty(ctx->file_repair_list))
-		goto maybe_trim;
-
 	/*
 	 * If errors remain on the filesystem, do not trim anything.  We don't
 	 * have any threads running, so it's ok to skip the ctx lock here.
 	 */
-	if (ctx->corruptions_found || ctx->unfixable_errors != 0)
+	if (!action_list_empty(ctx->fs_repair_list))
+		return false;
+	if (!action_list_empty(ctx->file_repair_list))
+		return false;
+
+	if (ctx->corruptions_found != 0)
+		return false;
+	if (ctx->unfixable_errors != 0)
+		return false;
+
+	return true;
+}
+
+/* Trim the filesystem, if desired. */
+int
+phase8_func(
+	struct scrub_ctx	*ctx)
+{
+	if (!fstrim_ok(ctx))
 		return 0;
 
-maybe_trim:
 	fstrim(ctx);
 	progress_add(1);
 	return 0;
@@ -51,7 +63,11 @@ phase8_estimate(
 	unsigned int		*nr_threads,
 	int			*rshift)
 {
-	*items = 1;
+	*items = 0;
+
+	if (fstrim_ok(ctx))
+		*items = 1;
+
 	*nr_threads = 1;
 	*rshift = 0;
 	return 0;

[PATCH 5/8] xfs_scrub: report FITRIM errors properly

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Move the error reporting for the FITRIM ioctl out of vfs.c and into
phase8.c.  This makes it so that IO errors encountered during trim are
counted as runtime errors instead of being dropped silently.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase8.c |   12 +++++++++++-
 scrub/vfs.c    |   12 +++++++-----
 scrub/vfs.h    |    2 +-
 3 files changed, 19 insertions(+), 7 deletions(-)


diff --git a/scrub/phase8.c b/scrub/phase8.c
index dfe62e8d97b..288800a76cf 100644
--- a/scrub/phase8.c
+++ b/scrub/phase8.c
@@ -47,10 +47,20 @@ int
 phase8_func(
 	struct scrub_ctx	*ctx)
 {
+	int			error;
+
 	if (!fstrim_ok(ctx))
 		return 0;
 
-	fstrim(ctx);
+	error = fstrim(ctx);
+	if (error == EOPNOTSUPP)
+		return 0;
+
+	if (error) {
+		str_liberror(ctx, error, _("fstrim"));
+		return error;
+	}
+
 	progress_add(1);
 	return 0;
 }
diff --git a/scrub/vfs.c b/scrub/vfs.c
index 9e459d6243f..bcfd4f42ca8 100644
--- a/scrub/vfs.c
+++ b/scrub/vfs.c
@@ -296,15 +296,17 @@ struct fstrim_range {
 #endif
 
 /* Call FITRIM to trim all the unused space in a filesystem. */
-void
+int
 fstrim(
 	struct scrub_ctx	*ctx)
 {
 	struct fstrim_range	range = {0};
-	int			error;
 
 	range.len = ULLONG_MAX;
-	error = ioctl(ctx->mnt.fd, FITRIM, &range);
-	if (error && errno != EOPNOTSUPP && errno != ENOTTY)
-		perror(_("fstrim"));
+	if (ioctl(ctx->mnt.fd, FITRIM, &range) == 0)
+		return 0;
+	if (errno == EOPNOTSUPP || errno == ENOTTY)
+		return EOPNOTSUPP;
+
+	return errno;
 }
diff --git a/scrub/vfs.h b/scrub/vfs.h
index 1ac41e5aac0..a8a4d72e290 100644
--- a/scrub/vfs.h
+++ b/scrub/vfs.h
@@ -24,6 +24,6 @@ typedef int (*scan_fs_tree_dirent_fn)(struct scrub_ctx *, const char *,
 int scan_fs_tree(struct scrub_ctx *ctx, scan_fs_tree_dir_fn dir_fn,
 		scan_fs_tree_dirent_fn dirent_fn, void *arg);
 
-void fstrim(struct scrub_ctx *ctx);
+int fstrim(struct scrub_ctx *ctx);
 
 #endif /* XFS_SCRUB_VFS_H_ */

[PATCH 6/8] xfs_scrub: don't call FITRIM after runtime errors

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Don't call FITRIM if there have been runtime errors -- we don't want to
touch anything after any kind of unfixable problem.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase8.c |    3 +++
 1 file changed, 3 insertions(+)


diff --git a/scrub/phase8.c b/scrub/phase8.c
index 288800a76cf..75400c96859 100644
--- a/scrub/phase8.c
+++ b/scrub/phase8.c
@@ -39,6 +39,9 @@ fstrim_ok(
 	if (ctx->unfixable_errors != 0)
 		return false;
 
+	if (ctx->runtime_errors != 0)
+		return false;
+
 	return true;
 }
 

[PATCH 7/8] xfs_scrub: don't trim the first agbno of each AG for better performance

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

XFS issues discard IOs while holding the free space btree and the AGF
buffers locked.  If the discard IOs are slow or the free space is
extremely fragmented, this can lead to long stalls for every other
thread trying to access that AG.  On a 10TB high performance flash
storage device with a severely fragmented free space btree in every AG,
this results in many threads tripping the hangcheck warnings while
waiting for the AGF.  This happens even after we've run fstrim a few
times and waited for the nvme namespace utilization counters to
stabilize.

Strace for the entire 10TB looks like:
ioctl(3, FITRIM, {start=0x0, len=10995116277760, minlen=0}) = 0 <686.209839>

Reducing the size of the FITRIM requests to a single AG at a time
produces lower times for each individual call, but even this isn't quite
acceptable, because the lock hold times are still high enough to cause
stall warnings:

Strace for the first 4x 1TB AGs looks like (2):
ioctl(3, FITRIM, {start=0x0, len=1099511627776, minlen=0}) = 0 <68.352033>
ioctl(3, FITRIM, {start=0x10000000000, len=1099511627776, minlen=0}) = 0 <68.760323>
ioctl(3, FITRIM, {start=0x20000000000, len=1099511627776, minlen=0}) = 0 <67.235226>
ioctl(3, FITRIM, {start=0x30000000000, len=1099511627776, minlen=0}) = 0 <69.465744>

The fstrim code has to synchronize discards with block allocations, so
we must hold the AGF lock while issuing discard IOs.  Breaking up the
calls into smaller start/len segments ought to reduce the lock hold time
and allow other threads a chance to make progress.  Unfortunately, the
current fstrim implementation handles this poorly because it walks the
entire free space by length index (cntbt) and it's not clear if we can
cycle the AGF periodically to reduce latency because there's no
less-than btree lookup.

The first solution I thought of was to limit latency by scanning parts
of an AG at a time, but this doesn't solve the stalling problem when the
free space is heavily fragmented because each sub-AG scan has to walk
the entire cntbt to find free space that fits within the given range.
In fact, this dramatically increases the runtime!

Ultimately, I forked the kernel implementations -- for full AG fstrims,
it still trims by length.  However, for a sub-AG scan, it will walk the
bnobt and perform the trims in block number order.  Since the cursor
has an obviously monotonically increasing value, it is easy to cycle the
AGF periodically to allow other threads to do work.  This implementation
avoids the worst problems of the original code, though it lacks the
desirable attribute of freeing the biggest chunks first.

This second algorithm is what we want for xfs_scrub, which generally
runs as a background service.  Skip the first block of each AG to ensure
that we get the sub-AG algorithm,

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase8.c |   63 +++++++++++++++++++++++++++++++++++++++++++++++---------
 scrub/vfs.c    |   10 ++++++---
 scrub/vfs.h    |    2 +-
 3 files changed, 61 insertions(+), 14 deletions(-)


diff --git a/scrub/phase8.c b/scrub/phase8.c
index 75400c96859..570083be9d8 100644
--- a/scrub/phase8.c
+++ b/scrub/phase8.c
@@ -45,29 +45,72 @@ fstrim_ok(
 	return true;
 }
 
-/* Trim the filesystem, if desired. */
-int
-phase8_func(
-	struct scrub_ctx	*ctx)
+/* Trim a certain range of the filesystem. */
+static int
+fstrim_fsblocks(
+	struct scrub_ctx	*ctx,
+	uint64_t		start_fsb,
+	uint64_t		fsbcount)
 {
+	uint64_t		start = cvt_off_fsb_to_b(&ctx->mnt, start_fsb);
+	uint64_t		len = cvt_off_fsb_to_b(&ctx->mnt, fsbcount);
 	int			error;
 
-	if (!fstrim_ok(ctx))
-		return 0;
-
-	error = fstrim(ctx);
+	error = fstrim(ctx, start, len);
 	if (error == EOPNOTSUPP)
 		return 0;
-
 	if (error) {
-		str_liberror(ctx, error, _("fstrim"));
+		char		descr[DESCR_BUFSZ];
+
+		snprintf(descr, sizeof(descr) - 1,
+				_("fstrim start 0x%llx len 0x%llx"),
+				(unsigned long long)start,
+				(unsigned long long)len);
+		str_liberror(ctx, error, descr);
 		return error;
 	}
 
+	return 0;
+}
+
+/* Trim each AG on the data device. */
+static int
+fstrim_datadev(
+	struct scrub_ctx	*ctx)
+{
+	struct xfs_fsop_geom	*geo = &ctx->mnt.fsgeom;
+	uint64_t		fsbno;
+	int			error;
+
+	for (fsbno = 0; fsbno < geo->datablocks; fsbno += geo->agblocks) {
+		uint64_t	fsbcount;
+
+		/*
+		 * Skip the first block of each AG to ensure that we get the
+		 * partial-AG discard implementation, which cycles the AGF lock
+		 * to prevent foreground threads from stalling.
+		 */
+		fsbcount = min(geo->datablocks - fsbno + 1, geo->agblocks);
+		error = fstrim_fsblocks(ctx, fsbno + 1, fsbcount);
+		if (error)
+			return error;
+	}
+
 	progress_add(1);
 	return 0;
 }
 
+/* Trim the filesystem, if desired. */
+int
+phase8_func(
+	struct scrub_ctx	*ctx)
+{
+	if (!fstrim_ok(ctx))
+		return 0;
+
+	return fstrim_datadev(ctx);
+}
+
 /* Estimate how much work we're going to do. */
 int
 phase8_estimate(
diff --git a/scrub/vfs.c b/scrub/vfs.c
index bcfd4f42ca8..cc958ba9438 100644
--- a/scrub/vfs.c
+++ b/scrub/vfs.c
@@ -298,11 +298,15 @@ struct fstrim_range {
 /* Call FITRIM to trim all the unused space in a filesystem. */
 int
 fstrim(
-	struct scrub_ctx	*ctx)
+	struct scrub_ctx	*ctx,
+	uint64_t		start,
+	uint64_t		len)
 {
-	struct fstrim_range	range = {0};
+	struct fstrim_range	range = {
+		.start		= start,
+		.len		= len,
+	};
 
-	range.len = ULLONG_MAX;
 	if (ioctl(ctx->mnt.fd, FITRIM, &range) == 0)
 		return 0;
 	if (errno == EOPNOTSUPP || errno == ENOTTY)
diff --git a/scrub/vfs.h b/scrub/vfs.h
index a8a4d72e290..1af8d80d1de 100644
--- a/scrub/vfs.h
+++ b/scrub/vfs.h
@@ -24,6 +24,6 @@ typedef int (*scan_fs_tree_dirent_fn)(struct scrub_ctx *, const char *,
 int scan_fs_tree(struct scrub_ctx *ctx, scan_fs_tree_dir_fn dir_fn,
 		scan_fs_tree_dirent_fn dirent_fn, void *arg);
 
-int fstrim(struct scrub_ctx *ctx);
+int fstrim(struct scrub_ctx *ctx, uint64_t start, uint64_t len);
 
 #endif /* XFS_SCRUB_VFS_H_ */

[PATCH 8/8] xfs_scrub: improve progress meter for phase 8 fstrimming

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Currently, progress reporting in phase 8 is awful, because we stall at
0% until jumping to 100%.  Since we're now performing sub-AG fstrim
calls to limit the latency impacts to the rest of the system, we might
as well limit the FSTRIM scan size so that we can report status updates
to the user more regularly.  Doing so also facilitates CPU usage control
during phase 8.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase8.c |   59 ++++++++++++++++++++++++++++++++++++++------------------
 1 file changed, 40 insertions(+), 19 deletions(-)


diff --git a/scrub/phase8.c b/scrub/phase8.c
index 570083be9d8..f1a854a3e56 100644
--- a/scrub/phase8.c
+++ b/scrub/phase8.c
@@ -45,6 +45,13 @@ fstrim_ok(
 	return true;
 }
 
+/*
+ * Limit the amount of fstrim scanning that we let the kernel do in a single
+ * call so that we can implement decent progress reporting and CPU resource
+ * control.  Pick a prime number of gigabytes for interest.
+ */
+#define FSTRIM_MAX_BYTES	(11ULL << 30)
+
 /* Trim a certain range of the filesystem. */
 static int
 fstrim_fsblocks(
@@ -56,18 +63,31 @@ fstrim_fsblocks(
 	uint64_t		len = cvt_off_fsb_to_b(&ctx->mnt, fsbcount);
 	int			error;
 
-	error = fstrim(ctx, start, len);
-	if (error == EOPNOTSUPP)
-		return 0;
-	if (error) {
-		char		descr[DESCR_BUFSZ];
-
-		snprintf(descr, sizeof(descr) - 1,
-				_("fstrim start 0x%llx len 0x%llx"),
-				(unsigned long long)start,
-				(unsigned long long)len);
-		str_liberror(ctx, error, descr);
-		return error;
+	while (len > 0) {
+		uint64_t	run;
+
+		run = min(len, FSTRIM_MAX_BYTES);
+
+		error = fstrim(ctx, start, run);
+		if (error == EOPNOTSUPP) {
+			/* Pretend we finished all the work. */
+			progress_add(len);
+			return 0;
+		}
+		if (error) {
+			char		descr[DESCR_BUFSZ];
+
+			snprintf(descr, sizeof(descr) - 1,
+					_("fstrim start 0x%llx run 0x%llx"),
+					(unsigned long long)start,
+					(unsigned long long)run);
+			str_liberror(ctx, error, descr);
+			return error;
+		}
+
+		progress_add(run);
+		len -= run;
+		start += run;
 	}
 
 	return 0;
@@ -90,13 +110,13 @@ fstrim_datadev(
 		 * partial-AG discard implementation, which cycles the AGF lock
 		 * to prevent foreground threads from stalling.
 		 */
+		progress_add(geo->blocksize);
 		fsbcount = min(geo->datablocks - fsbno + 1, geo->agblocks);
 		error = fstrim_fsblocks(ctx, fsbno + 1, fsbcount);
 		if (error)
 			return error;
 	}
 
-	progress_add(1);
 	return 0;
 }
 
@@ -119,12 +139,13 @@ phase8_estimate(
 	unsigned int		*nr_threads,
 	int			*rshift)
 {
-	*items = 0;
-
-	if (fstrim_ok(ctx))
-		*items = 1;
-
+	if (fstrim_ok(ctx)) {
+		*items = cvt_off_fsb_to_b(&ctx->mnt,
+				ctx->mnt.fsgeom.datablocks);
+	} else {
+		*items = 0;
+	}
 	*nr_threads = 1;
-	*rshift = 0;
+	*rshift = 30; /* GiB */
 	return 0;
 }

[PATCH 1/7] libfrog: hoist free space histogram code

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Combine the two free space histograms in xfs_db and xfs_spaceman into a
single implementation.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 db/freesp.c         |   83 +++++--------------------------
 libfrog/Makefile    |    2 +
 libfrog/histogram.c |  135 +++++++++++++++++++++++++++++++++++++++++++++++++++
 libfrog/histogram.h |   50 +++++++++++++++++++
 spaceman/freesp.c   |   93 +++++++++--------------------------
 5 files changed, 225 insertions(+), 138 deletions(-)
 create mode 100644 libfrog/histogram.c
 create mode 100644 libfrog/histogram.h


diff --git a/db/freesp.c b/db/freesp.c
index 6f234666584..7e71bf47a16 100644
--- a/db/freesp.c
+++ b/db/freesp.c
@@ -12,14 +12,7 @@
 #include "output.h"
 #include "init.h"
 #include "malloc.h"
-
-typedef struct histent
-{
-	int		low;
-	int		high;
-	long long	count;
-	long long	blocks;
-} histent_t;
+#include "libfrog/histogram.h"
 
 static void	addhistent(int h);
 static void	addtohist(xfs_agnumber_t agno, xfs_agblock_t agbno,
@@ -46,13 +39,10 @@ static int		alignment;
 static int		countflag;
 static int		dumpflag;
 static int		equalsize;
-static histent_t	*hist;
-static int		histcount;
+static struct histogram	freesp_hist;
 static int		multsize;
 static int		seen1;
 static int		summaryflag;
-static long long	totblocks;
-static long long	totexts;
 
 static const cmdinfo_t	freesp_cmd =
 	{ "freesp", NULL, freesp_f, 0, -1, 0,
@@ -93,18 +83,13 @@ freesp_f(
 		if (inaglist(agno))
 			scan_ag(agno);
 	}
-	if (histcount)
+	if (hist_buckets(&freesp_hist))
 		printhist();
-	if (summaryflag) {
-		dbprintf(_("total free extents %lld\n"), totexts);
-		dbprintf(_("total free blocks %lld\n"), totblocks);
-		dbprintf(_("average free extent size %g\n"),
-			(double)totblocks / (double)totexts);
-	}
+	if (summaryflag)
+		hist_summarize(&freesp_hist);
 	if (aglist)
 		xfree(aglist);
-	if (hist)
-		xfree(hist);
+	hist_free(&freesp_hist);
 	return 0;
 }
 
@@ -132,10 +117,9 @@ init(
 	int		speced = 0;
 
 	agcount = countflag = dumpflag = equalsize = multsize = optind = 0;
-	histcount = seen1 = summaryflag = 0;
-	totblocks = totexts = 0;
+	seen1 = summaryflag = 0;
 	aglist = NULL;
-	hist = NULL;
+
 	while ((c = getopt(argc, argv, "A:a:bcde:h:m:s")) != EOF) {
 		switch (c) {
 		case 'A':
@@ -163,7 +147,7 @@ init(
 			speced = 1;
 			break;
 		case 'h':
-			if (speced && !histcount)
+			if (speced && hist_buckets(&freesp_hist) == 0)
 				return usage();
 			addhistent(atoi(optarg));
 			speced = 1;
@@ -339,14 +323,7 @@ static void
 addhistent(
 	int	h)
 {
-	hist = xrealloc(hist, (histcount + 1) * sizeof(*hist));
-	if (h == 0)
-		h = 1;
-	hist[histcount].low = h;
-	hist[histcount].count = hist[histcount].blocks = 0;
-	histcount++;
-	if (h == 1)
-		seen1 = 1;
+	hist_add_bucket(&freesp_hist, h);
 }
 
 static void
@@ -355,30 +332,12 @@ addtohist(
 	xfs_agblock_t	agbno,
 	xfs_extlen_t	len)
 {
-	int		i;
-
 	if (alignment && (XFS_AGB_TO_FSB(mp,agno,agbno) % alignment))
 		return;
 
 	if (dumpflag)
 		dbprintf("%8d %8d %8d\n", agno, agbno, len);
-	totexts++;
-	totblocks += len;
-	for (i = 0; i < histcount; i++) {
-		if (hist[i].high >= len) {
-			hist[i].count++;
-			hist[i].blocks += len;
-			break;
-		}
-	}
-}
-
-static int
-hcmp(
-	const void	*a,
-	const void	*b)
-{
-	return ((histent_t *)a)->low - ((histent_t *)b)->low;
+	hist_add(&freesp_hist, len);
 }
 
 static void
@@ -387,6 +346,7 @@ histinit(
 {
 	int	i;
 
+	hist_init(&freesp_hist);
 	if (equalsize) {
 		for (i = 1; i < maxlen; i += equalsize)
 			addhistent(i);
@@ -396,27 +356,12 @@ histinit(
 	} else {
 		if (!seen1)
 			addhistent(1);
-		qsort(hist, histcount, sizeof(*hist), hcmp);
-	}
-	for (i = 0; i < histcount; i++) {
-		if (i < histcount - 1)
-			hist[i].high = hist[i + 1].low - 1;
-		else
-			hist[i].high = maxlen;
 	}
+	hist_prepare(&freesp_hist, maxlen);
 }
 
 static void
 printhist(void)
 {
-	int	i;
-
-	dbprintf("%7s %7s %7s %7s %6s\n",
-		_("from"), _("to"), _("extents"), _("blocks"), _("pct"));
-	for (i = 0; i < histcount; i++) {
-		if (hist[i].count)
-			dbprintf("%7d %7d %7lld %7lld %6.2f\n", hist[i].low,
-				hist[i].high, hist[i].count, hist[i].blocks,
-				hist[i].blocks * 100.0 / totblocks);
-	}
+	hist_print(&freesp_hist);
 }
diff --git a/libfrog/Makefile b/libfrog/Makefile
index f8bb39f2712..bbc5b887cd3 100644
--- a/libfrog/Makefile
+++ b/libfrog/Makefile
@@ -20,6 +20,7 @@ convert.c \
 crc32.c \
 file_exchange.c \
 fsgeom.c \
+histogram.c \
 list_sort.c \
 linux.c \
 logging.c \
@@ -45,6 +46,7 @@ dahashselftest.h \
 div64.h \
 file_exchange.h \
 fsgeom.h \
+histogram.h \
 logging.h \
 paths.h \
 projects.h \
diff --git a/libfrog/histogram.c b/libfrog/histogram.c
new file mode 100644
index 00000000000..553ba3d7c6e
--- /dev/null
+++ b/libfrog/histogram.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2000-2001,2005 Silicon Graphics, Inc.
+ * Copyright (c) 2012 Red Hat, Inc.
+ * Copyright (c) 2017-2024 Oracle.
+ * All Rights Reserved.
+ */
+#include "xfs.h"
+#include <stdlib.h>
+#include <string.h>
+#include "platform_defs.h"
+#include "libfrog/histogram.h"
+
+/* Create a new bucket with the given low value. */
+int
+hist_add_bucket(
+	struct histogram	*hs,
+	long long		bucket_low)
+{
+	struct histent		*buckets;
+
+	if (hs->nr_buckets == INT_MAX)
+		return EFBIG;
+
+	buckets = realloc(hs->buckets,
+			(hs->nr_buckets + 1) * sizeof(struct histent));
+	if (!buckets)
+		return errno;
+
+	hs->buckets = buckets;
+	hs->buckets[hs->nr_buckets].low = bucket_low;
+	hs->buckets[hs->nr_buckets].count = buckets[hs->nr_buckets].blocks = 0;
+	hs->nr_buckets++;
+	return 0;
+}
+
+/* Add an observation to the histogram. */
+void
+hist_add(
+	struct histogram	*hs,
+	long long		len)
+{
+	unsigned int		i;
+
+	hs->totexts++;
+	hs->totblocks += len;
+	for (i = 0; i < hs->nr_buckets; i++) {
+		if (hs->buckets[i].high >= len) {
+			hs->buckets[i].count++;
+			hs->buckets[i].blocks += len;
+			break;
+		}
+	}
+}
+
+static int
+histent_cmp(
+	const void		*a,
+	const void		*b)
+{
+	const struct histent	*ha = a;
+	const struct histent	*hb = b;
+
+	if (ha->low < hb->low)
+		return -1;
+	if (ha->low > hb->low)
+		return 1;
+	return 0;
+}
+
+/* Prepare a histogram for bucket configuration. */
+void
+hist_init(
+	struct histogram	*hs)
+{
+	memset(hs, 0, sizeof(struct histogram));
+}
+
+/* Prepare a histogram to receive data observations. */
+void
+hist_prepare(
+	struct histogram	*hs,
+	long long		maxlen)
+{
+	unsigned int		i;
+
+	qsort(hs->buckets, hs->nr_buckets, sizeof(struct histent), histent_cmp);
+
+	for (i = 0; i < hs->nr_buckets; i++) {
+		if (i < hs->nr_buckets - 1)
+			hs->buckets[i].high = hs->buckets[i + 1].low - 1;
+		else
+			hs->buckets[i].high = maxlen;
+	}
+}
+
+/* Free all data associated with a histogram. */
+void
+hist_free(
+	struct histogram	*hs)
+{
+	free(hs->buckets);
+	memset(hs, 0, sizeof(struct histogram));
+}
+
+/* Dump a histogram to stdout. */
+void
+hist_print(
+	const struct histogram	*hs)
+{
+	unsigned int		i;
+
+	printf("%7s %7s %7s %7s %6s\n",
+		_("from"), _("to"), _("extents"), _("blocks"), _("pct"));
+	for (i = 0; i < hs->nr_buckets; i++) {
+		if (hs->buckets[i].count == 0)
+			continue;
+
+		printf("%7lld %7lld %7lld %7lld %6.2f\n",
+				hs->buckets[i].low, hs->buckets[i].high,
+				hs->buckets[i].count, hs->buckets[i].blocks,
+				hs->buckets[i].blocks * 100.0 / hs->totblocks);
+	}
+}
+
+/* Summarize the contents of the histogram. */
+void
+hist_summarize(
+	const struct histogram	*hs)
+{
+	printf(_("total free extents %lld\n"), hs->totexts);
+	printf(_("total free blocks %lld\n"), hs->totblocks);
+	printf(_("average free extent size %g\n"),
+			(double)hs->totblocks / (double)hs->totexts);
+}
diff --git a/libfrog/histogram.h b/libfrog/histogram.h
new file mode 100644
index 00000000000..2e2b169a79b
--- /dev/null
+++ b/libfrog/histogram.h
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2000-2001,2005 Silicon Graphics, Inc.
+ * Copyright (c) 2012 Red Hat, Inc.
+ * Copyright (c) 2017-2024 Oracle.
+ * All Rights Reserved.
+ */
+#ifndef __LIBFROG_HISTOGRAM_H__
+#define __LIBFROG_HISTOGRAM_H__
+
+struct histent
+{
+	/* Low and high size of this bucket */
+	long long	low;
+	long long	high;
+
+	/* Count of observations recorded */
+	long long	count;
+
+	/* Sum of blocks recorded */
+	long long	blocks;
+};
+
+struct histogram {
+	/* Sum of all blocks recorded */
+	long long	totblocks;
+
+	/* Count of all observations recorded */
+	long long	totexts;
+
+	struct histent	*buckets;
+
+	/* Number of buckets */
+	unsigned int	nr_buckets;
+};
+
+int hist_add_bucket(struct histogram *hs, long long bucket_low);
+void hist_add(struct histogram *hs, long long len);
+void hist_init(struct histogram *hs);
+void hist_prepare(struct histogram *hs, long long maxlen);
+void hist_free(struct histogram *hs);
+void hist_print(const struct histogram *hs);
+void hist_summarize(const struct histogram *hs);
+
+static inline unsigned int hist_buckets(const struct histogram *hs)
+{
+	return hs->nr_buckets;
+}
+
+#endif /* __LIBFROG_HISTOGRAM_H__ */
diff --git a/spaceman/freesp.c b/spaceman/freesp.c
index 70dcdb5c923..996cbb7e2c0 100644
--- a/spaceman/freesp.c
+++ b/spaceman/freesp.c
@@ -15,76 +15,52 @@
 #include "libfrog/paths.h"
 #include "space.h"
 #include "input.h"
-
-struct histent
-{
-	long long	low;
-	long long	high;
-	long long	count;
-	long long	blocks;
-};
+#include "libfrog/histogram.h"
 
 static int		agcount;
 static xfs_agnumber_t	*aglist;
-static struct histent	*hist;
+static struct histogram	freesp_hist;
 static int		dumpflag;
 static long long	equalsize;
 static long long	multsize;
-static int		histcount;
 static int		seen1;
 static int		summaryflag;
 static int		gflag;
 static bool		rtflag;
-static long long	totblocks;
-static long long	totexts;
 
 static cmdinfo_t freesp_cmd;
 
-static void
+static inline void
 addhistent(
 	long long	h)
 {
-	if (histcount == INT_MAX) {
+	int		error;
+
+	error = hist_add_bucket(&freesp_hist, h);
+	if (error == EFBIG) {
 		printf(_("Too many histogram buckets.\n"));
 		return;
 	}
-	hist = realloc(hist, (histcount + 1) * sizeof(*hist));
+	if (error) {
+		printf("%s\n", strerror(error));
+		return;
+	}
+
 	if (h == 0)
 		h = 1;
-	hist[histcount].low = h;
-	hist[histcount].count = hist[histcount].blocks = 0;
-	histcount++;
 	if (h == 1)
 		seen1 = 1;
 }
 
-static void
+static inline void
 addtohist(
 	xfs_agnumber_t	agno,
 	xfs_agblock_t	agbno,
 	off64_t		len)
 {
-	long		i;
-
 	if (dumpflag)
 		printf("%8d %8d %8"PRId64"\n", agno, agbno, len);
-	totexts++;
-	totblocks += len;
-	for (i = 0; i < histcount; i++) {
-		if (hist[i].high >= len) {
-			hist[i].count++;
-			hist[i].blocks += len;
-			break;
-		}
-	}
-}
-
-static int
-hcmp(
-	const void	*a,
-	const void	*b)
-{
-	return ((struct histent *)a)->low - ((struct histent *)b)->low;
+	hist_add(&freesp_hist, len);
 }
 
 static void
@@ -93,6 +69,7 @@ histinit(
 {
 	long long	i;
 
+	hist_init(&freesp_hist);
 	if (equalsize) {
 		for (i = 1; i < maxlen; i += equalsize)
 			addhistent(i);
@@ -102,29 +79,14 @@ histinit(
 	} else {
 		if (!seen1)
 			addhistent(1);
-		qsort(hist, histcount, sizeof(*hist), hcmp);
-	}
-	for (i = 0; i < histcount; i++) {
-		if (i < histcount - 1)
-			hist[i].high = hist[i + 1].low - 1;
-		else
-			hist[i].high = maxlen;
 	}
+	hist_prepare(&freesp_hist, maxlen);
 }
 
-static void
+static inline void
 printhist(void)
 {
-	int	i;
-
-	printf("%7s %7s %7s %7s %6s\n",
-		_("from"), _("to"), _("extents"), _("blocks"), _("pct"));
-	for (i = 0; i < histcount; i++) {
-		if (hist[i].count)
-			printf("%7lld %7lld %7lld %7lld %6.2f\n", hist[i].low,
-				hist[i].high, hist[i].count, hist[i].blocks,
-				hist[i].blocks * 100.0 / totblocks);
-	}
+	hist_print(&freesp_hist);
 }
 
 static int
@@ -255,10 +217,8 @@ init(
 	int			speced = 0;	/* only one of -b -e -h or -m */
 
 	agcount = dumpflag = equalsize = multsize = optind = gflag = 0;
-	histcount = seen1 = summaryflag = 0;
-	totblocks = totexts = 0;
+	seen1 = summaryflag = 0;
 	aglist = NULL;
-	hist = NULL;
 	rtflag = false;
 
 	while ((c = getopt(argc, argv, "a:bde:gh:m:rs")) != EOF) {
@@ -287,7 +247,7 @@ init(
 			gflag++;
 			break;
 		case 'h':
-			if (speced && !histcount)
+			if (speced && hist_buckets(&freesp_hist) == 0)
 				goto many_spec;
 			/* addhistent increments histcount */
 			x = cvt_s64(optarg, 0);
@@ -345,18 +305,13 @@ freesp_f(
 		if (inaglist(agno))
 			scan_ag(agno);
 	}
-	if (histcount && !gflag)
+	if (hist_buckets(&freesp_hist) > 0 && !gflag)
 		printhist();
-	if (summaryflag) {
-		printf(_("total free extents %lld\n"), totexts);
-		printf(_("total free blocks %lld\n"), totblocks);
-		printf(_("average free extent size %g\n"),
-			(double)totblocks / (double)totexts);
-	}
+	if (summaryflag)
+		hist_summarize(&freesp_hist);
 	if (aglist)
 		free(aglist);
-	if (hist)
-		free(hist);
+	hist_free(&freesp_hist);
 	return 0;
 }
 

[PATCH 2/7] libfrog: print wider columns for free space histogram

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

The values reported here can reach very large values, so compute the
column width dynamically.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libfrog/histogram.c |   34 +++++++++++++++++++++++++++++-----
 1 file changed, 29 insertions(+), 5 deletions(-)


diff --git a/libfrog/histogram.c b/libfrog/histogram.c
index 553ba3d7c6e..5053d5eafc2 100644
--- a/libfrog/histogram.c
+++ b/libfrog/histogram.c
@@ -108,17 +108,41 @@ void
 hist_print(
 	const struct histogram	*hs)
 {
+	unsigned int		from_w, to_w, extents_w, blocks_w;
 	unsigned int		i;
 
-	printf("%7s %7s %7s %7s %6s\n",
-		_("from"), _("to"), _("extents"), _("blocks"), _("pct"));
+	from_w = to_w = extents_w = blocks_w = 7;
+	for (i = 0; i < hs->nr_buckets; i++) {
+		char buf[256];
+
+		if (!hs->buckets[i].count)
+			continue;
+
+		snprintf(buf, sizeof(buf) - 1, "%lld", hs->buckets[i].low);
+		from_w = max(from_w, strlen(buf));
+
+		snprintf(buf, sizeof(buf) - 1, "%lld", hs->buckets[i].high);
+		to_w = max(to_w, strlen(buf));
+
+		snprintf(buf, sizeof(buf) - 1, "%lld", hs->buckets[i].count);
+		extents_w = max(extents_w, strlen(buf));
+
+		snprintf(buf, sizeof(buf) - 1, "%lld", hs->buckets[i].blocks);
+		blocks_w = max(blocks_w, strlen(buf));
+	}
+
+	printf("%*s %*s %*s %*s %6s\n",
+		from_w, _("from"), to_w, _("to"), extents_w, _("extents"),
+		blocks_w, _("blocks"), _("pct"));
 	for (i = 0; i < hs->nr_buckets; i++) {
 		if (hs->buckets[i].count == 0)
 			continue;
 
-		printf("%7lld %7lld %7lld %7lld %6.2f\n",
-				hs->buckets[i].low, hs->buckets[i].high,
-				hs->buckets[i].count, hs->buckets[i].blocks,
+		printf("%*lld %*lld %*lld %*lld %6.2f\n",
+				from_w, hs->buckets[i].low,
+				to_w, hs->buckets[i].high,
+				extents_w, hs->buckets[i].count,
+				blocks_w, hs->buckets[i].blocks,
 				hs->buckets[i].blocks * 100.0 / hs->totblocks);
 	}
 }

[PATCH 3/7] libfrog: print cdf of free space buckets

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Print the cumulative distribution function of the free space buckets in
reverse order.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libfrog/histogram.c |   63 ++++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 59 insertions(+), 4 deletions(-)


diff --git a/libfrog/histogram.c b/libfrog/histogram.c
index 5053d5eafc2..bed79e35b02 100644
--- a/libfrog/histogram.c
+++ b/libfrog/histogram.c
@@ -103,13 +103,64 @@ hist_free(
 	memset(hs, 0, sizeof(struct histogram));
 }
 
+/*
+ * Compute the CDF of the free space in decreasing order of extent length.
+ * This enables users to determine how much free space is not in the long tail
+ * of small extents, e.g. 98% of the free space extents are larger than 31
+ * blocks.
+ */
+static int
+hist_cdf(
+	const struct histogram	*hs,
+	struct histogram	*cdf)
+{
+	struct histent		*buckets;
+	int			i = hs->nr_buckets - 1;
+
+	ASSERT(cdf->nr_buckets == 0);
+	ASSERT(hs->nr_buckets < INT_MAX);
+
+	if (hs->nr_buckets == 0)
+		return 0;
+
+	buckets = calloc(hs->nr_buckets, sizeof(struct histent));
+	if (!buckets)
+		return errno;
+
+	memset(cdf, 0, sizeof(struct histogram));
+	cdf->buckets = buckets;
+
+	cdf->buckets[i].count = hs->buckets[i].count;
+	cdf->buckets[i].blocks = hs->buckets[i].blocks;
+	i--;
+
+	while (i >= 0) {
+		cdf->buckets[i].count = hs->buckets[i].count +
+				       cdf->buckets[i + 1].count;
+
+		cdf->buckets[i].blocks = hs->buckets[i].blocks +
+					cdf->buckets[i + 1].blocks;
+		i--;
+	}
+
+	return 0;
+}
+
 /* Dump a histogram to stdout. */
 void
 hist_print(
 	const struct histogram	*hs)
 {
+	struct histogram	cdf = { };
 	unsigned int		from_w, to_w, extents_w, blocks_w;
 	unsigned int		i;
+	int			error;
+
+	error = hist_cdf(hs, &cdf);
+	if (error) {
+		printf(_("histogram cdf: %s\n"), strerror(error));
+		return;
+	}
 
 	from_w = to_w = extents_w = blocks_w = 7;
 	for (i = 0; i < hs->nr_buckets; i++) {
@@ -131,20 +182,24 @@ hist_print(
 		blocks_w = max(blocks_w, strlen(buf));
 	}
 
-	printf("%*s %*s %*s %*s %6s\n",
+	printf("%*s %*s %*s %*s %6s %6s %6s\n",
 		from_w, _("from"), to_w, _("to"), extents_w, _("extents"),
-		blocks_w, _("blocks"), _("pct"));
+		blocks_w, _("blocks"), _("pct"), _("blkcdf"), _("extcdf"));
 	for (i = 0; i < hs->nr_buckets; i++) {
 		if (hs->buckets[i].count == 0)
 			continue;
 
-		printf("%*lld %*lld %*lld %*lld %6.2f\n",
+		printf("%*lld %*lld %*lld %*lld %6.2f %6.2f %6.2f\n",
 				from_w, hs->buckets[i].low,
 				to_w, hs->buckets[i].high,
 				extents_w, hs->buckets[i].count,
 				blocks_w, hs->buckets[i].blocks,
-				hs->buckets[i].blocks * 100.0 / hs->totblocks);
+				hs->buckets[i].blocks * 100.0 / hs->totblocks,
+				cdf.buckets[i].blocks * 100.0 / hs->totblocks,
+				cdf.buckets[i].count * 100.0 / hs->totexts);
 	}
+
+	hist_free(&cdf);
 }
 
 /* Summarize the contents of the histogram. */

[PATCH 4/7] xfs_scrub: don't close stdout when closing the progress bar

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

When we're tearing down the progress bar file stream, check that it's
not an alias of stdout before closing it.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/xfs_scrub.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)


diff --git a/scrub/xfs_scrub.c b/scrub/xfs_scrub.c
index 23b2e03865b..70c2d163f72 100644
--- a/scrub/xfs_scrub.c
+++ b/scrub/xfs_scrub.c
@@ -878,7 +878,7 @@ main(
 	if (ctx.runtime_errors)
 		ret |= SCRUB_RET_OPERROR;
 	phase_end(&all_pi, 0);
-	if (progress_fp)
+	if (progress_fp && fileno(progress_fp) != 1)
 		fclose(progress_fp);
 	unicrash_unload();
 

[PATCH 5/7] xfs_scrub: remove pointless spacemap.c arguments

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Remove unused parameters from the full-device spacemap scan functions.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/spacemap.c |   11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)


diff --git a/scrub/spacemap.c b/scrub/spacemap.c
index b6fd411816b..f20ecfeac5d 100644
--- a/scrub/spacemap.c
+++ b/scrub/spacemap.c
@@ -132,7 +132,6 @@ scan_ag_rmaps(
 static void
 scan_dev_rmaps(
 	struct scrub_ctx	*ctx,
-	int			idx,
 	dev_t			dev,
 	struct scan_blocks	*sbx)
 {
@@ -170,7 +169,7 @@ scan_rt_rmaps(
 {
 	struct scrub_ctx	*ctx = (struct scrub_ctx *)wq->wq_ctx;
 
-	scan_dev_rmaps(ctx, agno, ctx->fsinfo.fs_rtdev, arg);
+	scan_dev_rmaps(ctx, ctx->fsinfo.fs_rtdev, arg);
 }
 
 /* Iterate all the reverse mappings of the log device. */
@@ -182,7 +181,7 @@ scan_log_rmaps(
 {
 	struct scrub_ctx	*ctx = (struct scrub_ctx *)wq->wq_ctx;
 
-	scan_dev_rmaps(ctx, agno, ctx->fsinfo.fs_logdev, arg);
+	scan_dev_rmaps(ctx, ctx->fsinfo.fs_logdev, arg);
 }
 
 /*
@@ -210,8 +209,7 @@ scrub_scan_all_spacemaps(
 		return ret;
 	}
 	if (ctx->fsinfo.fs_rt) {
-		ret = -workqueue_add(&wq, scan_rt_rmaps,
-				ctx->mnt.fsgeom.agcount + 1, &sbx);
+		ret = -workqueue_add(&wq, scan_rt_rmaps, 0, &sbx);
 		if (ret) {
 			sbx.aborted = true;
 			str_liberror(ctx, ret, _("queueing rtdev fsmap work"));
@@ -219,8 +217,7 @@ scrub_scan_all_spacemaps(
 		}
 	}
 	if (ctx->fsinfo.fs_log) {
-		ret = -workqueue_add(&wq, scan_log_rmaps,
-				ctx->mnt.fsgeom.agcount + 2, &sbx);
+		ret = -workqueue_add(&wq, scan_log_rmaps, 0, &sbx);
 		if (ret) {
 			sbx.aborted = true;
 			str_liberror(ctx, ret, _("queueing logdev fsmap work"));

[PATCH 6/7] xfs_scrub: collect free space histograms during phase 7

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Collect a histogram of free space observed during phase 7.  We'll put
this information to use in the next patch.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libfrog/histogram.c |   38 ++++++++++++++++++++++++++++++++++++++
 libfrog/histogram.h |    3 +++
 scrub/phase7.c      |   47 +++++++++++++++++++++++++++++++++++++++++++++--
 scrub/xfs_scrub.c   |    5 +++++
 scrub/xfs_scrub.h   |    4 ++++
 5 files changed, 95 insertions(+), 2 deletions(-)


diff --git a/libfrog/histogram.c b/libfrog/histogram.c
index bed79e35b02..54e2bac0f73 100644
--- a/libfrog/histogram.c
+++ b/libfrog/histogram.c
@@ -212,3 +212,41 @@ hist_summarize(
 	printf(_("average free extent size %g\n"),
 			(double)hs->totblocks / (double)hs->totexts);
 }
+
+/* Copy the contents of src to dest. */
+void
+hist_import(
+	struct histogram	*dest,
+	const struct histogram	*src)
+{
+	unsigned int		i;
+
+	ASSERT(dest->nr_buckets == src->nr_buckets);
+
+	dest->totblocks += src->totblocks;
+	dest->totexts += src->totexts;
+
+	for (i = 0; i < dest->nr_buckets; i++) {
+		ASSERT(dest->buckets[i].low == src->buckets[i].low);
+		ASSERT(dest->buckets[i].high == src->buckets[i].high);
+
+		dest->buckets[i].count += src->buckets[i].count;
+		dest->buckets[i].blocks += src->buckets[i].blocks;
+	}
+}
+
+/*
+ * Move the contents of src to dest and reinitialize src.  dst must not
+ * contain any observations or buckets.
+ */
+void
+hist_move(
+	struct histogram	*dest,
+	struct histogram	*src)
+{
+	ASSERT(dest->nr_buckets == 0);
+	ASSERT(dest->totexts == 0);
+
+	memcpy(dest, src, sizeof(struct histogram));
+	hist_init(src);
+}
diff --git a/libfrog/histogram.h b/libfrog/histogram.h
index 2e2b169a79b..ec788344d4c 100644
--- a/libfrog/histogram.h
+++ b/libfrog/histogram.h
@@ -47,4 +47,7 @@ static inline unsigned int hist_buckets(const struct histogram *hs)
 	return hs->nr_buckets;
 }
 
+void hist_import(struct histogram *dest, const struct histogram *src);
+void hist_move(struct histogram *dest, struct histogram *src);
+
 #endif /* __LIBFROG_HISTOGRAM_H__ */
diff --git a/scrub/phase7.c b/scrub/phase7.c
index cce5ede0012..475d8f157ee 100644
--- a/scrub/phase7.c
+++ b/scrub/phase7.c
@@ -12,6 +12,7 @@
 #include "libfrog/ptvar.h"
 #include "libfrog/fsgeom.h"
 #include "libfrog/scrub.h"
+#include "libfrog/histogram.h"
 #include "list.h"
 #include "xfs_scrub.h"
 #include "common.h"
@@ -27,8 +28,36 @@ struct summary_counts {
 	unsigned long long	rbytes;		/* rt dev bytes */
 	unsigned long long	next_phys;	/* next phys bytes we see? */
 	unsigned long long	agbytes;	/* freespace bytes */
+
+	/* Free space histogram, in fsb */
+	struct histogram	datadev_hist;
 };
 
+/*
+ * Initialize a free space histogram.  Unsharded realtime volumes can be up to
+ * 2^52 blocks long, so we allocate enough buckets to handle that.
+ */
+static inline void
+init_freesp_hist(
+	struct histogram	*hs)
+{
+	unsigned int		i;
+
+	hist_init(hs);
+	for (i = 0; i < 53; i++)
+		hist_add_bucket(hs, 1ULL << i);
+	hist_prepare(hs, 1ULL << 53);
+}
+
+static void
+summary_count_init(
+	void			*data)
+{
+	struct summary_counts	*counts = data;
+
+	init_freesp_hist(&counts->datadev_hist);
+}
+
 /* Record block usage. */
 static int
 count_block_summary(
@@ -48,8 +77,14 @@ count_block_summary(
 	if (fsmap->fmr_device == ctx->fsinfo.fs_logdev)
 		return 0;
 	if ((fsmap->fmr_flags & FMR_OF_SPECIAL_OWNER) &&
-	    fsmap->fmr_owner == XFS_FMR_OWN_FREE)
+	    fsmap->fmr_owner == XFS_FMR_OWN_FREE) {
+		uint64_t	blocks;
+
+		blocks = cvt_b_to_off_fsbt(&ctx->mnt, fsmap->fmr_length);
+		if (fsmap->fmr_device == ctx->fsinfo.fs_datadev)
+			hist_add(&counts->datadev_hist, blocks);
 		return 0;
+	}
 
 	len = fsmap->fmr_length;
 
@@ -87,6 +122,9 @@ add_summaries(
 	total->dbytes += item->dbytes;
 	total->rbytes += item->rbytes;
 	total->agbytes += item->agbytes;
+
+	hist_import(&total->datadev_hist, &item->datadev_hist);
+	hist_free(&item->datadev_hist);
 	return 0;
 }
 
@@ -118,6 +156,8 @@ phase7_func(
 	int			ip;
 	int			error;
 
+	summary_count_init(&totalcount);
+
 	/* Check and fix the summary metadata. */
 	scrub_item_init_fs(&sri);
 	scrub_item_schedule_group(&sri, XFROG_SCRUB_GROUP_SUMMARY);
@@ -136,7 +176,7 @@ phase7_func(
 	}
 
 	error = -ptvar_alloc(scrub_nproc(ctx), sizeof(struct summary_counts),
-			NULL, &ptvar);
+			summary_count_init, &ptvar);
 	if (error) {
 		str_liberror(ctx, error, _("setting up block counter"));
 		return error;
@@ -153,6 +193,9 @@ phase7_func(
 	}
 	ptvar_free(ptvar);
 
+	/* Preserve free space histograms for phase 8. */
+	hist_move(&ctx->datadev_hist, &totalcount.datadev_hist);
+
 	/* Scan the whole fs. */
 	error = scrub_count_all_inodes(ctx, &counted_inodes);
 	if (error) {
diff --git a/scrub/xfs_scrub.c b/scrub/xfs_scrub.c
index 70c2d163f72..c66469a0703 100644
--- a/scrub/xfs_scrub.c
+++ b/scrub/xfs_scrub.c
@@ -18,6 +18,7 @@
 #include "descr.h"
 #include "unicrash.h"
 #include "progress.h"
+#include "libfrog/histogram.h"
 
 /*
  * XFS Online Metadata Scrub (and Repair)
@@ -669,6 +670,8 @@ main(
 	int			ret = SCRUB_RET_SUCCESS;
 	int			error;
 
+	hist_init(&ctx.datadev_hist);
+
 	fprintf(stdout, "EXPERIMENTAL xfs_scrub program in use! Use at your own risk!\n");
 	fflush(stdout);
 
@@ -882,6 +885,8 @@ main(
 		fclose(progress_fp);
 	unicrash_unload();
 
+	hist_free(&ctx.datadev_hist);
+
 	/*
 	 * If we're being run as a service, the return code must fit the LSB
 	 * init script action error guidelines, which is to say that we
diff --git a/scrub/xfs_scrub.h b/scrub/xfs_scrub.h
index 6272a36879e..1a28f0cc847 100644
--- a/scrub/xfs_scrub.h
+++ b/scrub/xfs_scrub.h
@@ -7,6 +7,7 @@
 #define XFS_SCRUB_XFS_SCRUB_H_
 
 #include "libfrog/fsgeom.h"
+#include "libfrog/histogram.h"
 
 extern char *progname;
 
@@ -86,6 +87,9 @@ struct scrub_ctx {
 	unsigned long long	preens;
 	bool			scrub_setup_succeeded;
 	bool			preen_triggers[XFS_SCRUB_TYPE_NR];
+
+	/* Free space histograms, in fsb */
+	struct histogram	datadev_hist;
 };
 
 /* Phase helper functions */

[PATCH 7/7] xfs_scrub: tune fstrim minlen parameter based on free space histograms

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Currently, phase 8 runs very slowly on filesystems with a lot of small
free space extents.  To reduce the amount of time spent on fstrim
activities during phase 8, we want to balance estimated runtime against
completeness of the trim.  In short, the goal is to reduce runtime by
avoiding small trim requests.

At the start of phase 8, a CDF is computed in decreasing order of extent
length from the histogram buckets created during the fsmap scan in phase
7.  A point corresponding to the fstrim percentage target is chosen from
the CDF and mapped back to a histogram bucket, and free space extents
smaller than that amount are ommitted from fstrim.

On my aging /home filesystem, the free space histogram reported by
xfs_spaceman looks like this:

   from      to extents    blocks    pct blkcdf extcdf
      1       1  121953    121953   0.04 100.00 100.00
      2       3  124741    299694   0.09  99.96  81.16
      4       7  113492    593763   0.18  99.87  61.89
      8      15  109215   1179524   0.36  99.69  44.36
     16      31   76972   1695455   0.52  99.33  27.48
     32      63   48655   2219667   0.68  98.82  15.59
     64     127   31398   2876898   0.88  98.14   8.08
    128     255    8014   1447920   0.44  97.27   3.23
    256     511    4142   1501758   0.46  96.82   1.99
    512    1023    2433   1768732   0.54  96.37   1.35
   1024    2047    1795   2648460   0.81  95.83   0.97
   2048    4095    1429   4206103   1.28  95.02   0.69
   4096    8191    1045   6162111   1.88  93.74   0.47
   8192   16383     791   9242745   2.81  91.87   0.31
  16384   32767     473  10883977   3.31  89.06   0.19
  32768   65535     272  12385566   3.77  85.74   0.12
  65536  131071     192  18098739   5.51  81.98   0.07
 131072  262143     108  20675199   6.29  76.47   0.04
 262144  524287      80  29061285   8.84  70.18   0.03
 524288 1048575      39  29002829   8.83  61.33   0.02
1048576 2097151      25  36824985  11.21  52.51   0.01
2097152 4194303      32 101727192  30.95  41.30   0.01
4194304 8388607       7  34007410  10.35  10.35   0.00

From this table, we see that free space extents that are 16 blocks or
longer constitute 99.3% of the free space in the filesystem but only
27.5% of the extents.  If we set the fstrim minlen parameter to 16
blocks, that means that we can trim over 99% of the space in one third
of the time it would take to trim everything.

Add a new -o fstrim_pct= option to xfs_scrub just in case there are
users out there who want a different percentage.  For example, accepting
a 95% trim would net us a speed increase of nearly two orders of
magnitude, ignoring system call overhead.  Setting it to 100% will trim
everything, just like fstrim(8).

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 libfrog/histogram.c  |    2 +
 libfrog/histogram.h  |    1 +
 man/man8/xfs_scrub.8 |   16 +++++++++++
 scrub/phase8.c       |   75 +++++++++++++++++++++++++++++++++++++++++++++++---
 scrub/vfs.c          |    4 ++-
 scrub/vfs.h          |    2 +
 scrub/xfs_scrub.c    |   38 +++++++++++++++++++++++++
 scrub/xfs_scrub.h    |   12 ++++++++
 8 files changed, 141 insertions(+), 9 deletions(-)


diff --git a/libfrog/histogram.c b/libfrog/histogram.c
index 54e2bac0f73..61ecda16ffe 100644
--- a/libfrog/histogram.c
+++ b/libfrog/histogram.c
@@ -109,7 +109,7 @@ hist_free(
  * of small extents, e.g. 98% of the free space extents are larger than 31
  * blocks.
  */
-static int
+int
 hist_cdf(
 	const struct histogram	*hs,
 	struct histogram	*cdf)
diff --git a/libfrog/histogram.h b/libfrog/histogram.h
index ec788344d4c..ecac66d240d 100644
--- a/libfrog/histogram.h
+++ b/libfrog/histogram.h
@@ -39,6 +39,7 @@ void hist_add(struct histogram *hs, long long len);
 void hist_init(struct histogram *hs);
 void hist_prepare(struct histogram *hs, long long maxlen);
 void hist_free(struct histogram *hs);
+int hist_cdf(const struct histogram *hs, struct histogram *cdf);
 void hist_print(const struct histogram *hs);
 void hist_summarize(const struct histogram *hs);
 
diff --git a/man/man8/xfs_scrub.8 b/man/man8/xfs_scrub.8
index 404baba696e..b9f253e1b07 100644
--- a/man/man8/xfs_scrub.8
+++ b/man/man8/xfs_scrub.8
@@ -100,6 +100,22 @@ The
 supported are:
 .RS 1.0i
 .TP
+.BI fstrim_pct= percentage
+To constrain the amount of time spent on fstrim activities during phase 8,
+this program tries to balance estimated runtime against completeness of the
+trim.
+In short, the program avoids small trim requests to save time.
+
+During phase 7, a log-scale histogram of free space extents is constructed.
+At the start of phase 8, a CDF is computed in decreasing order of extent
+length from the histogram buckets.
+A point corresponding to the fstrim percentage target is chosen from the CDF
+and mapped back to a histogram bucket.
+Free space extents at least as long as the bucket size are trimmed.
+Smaller extents are ignored.
+
+By default, the percentage threshold is 99%.
+.TP
 .BI iwarn
 Treat informational messages as warnings.
 This will result in a nonzero return code, and a higher logging level.
diff --git a/scrub/phase8.c b/scrub/phase8.c
index f1a854a3e56..c6845555579 100644
--- a/scrub/phase8.c
+++ b/scrub/phase8.c
@@ -11,6 +11,7 @@
 #include "list.h"
 #include "libfrog/paths.h"
 #include "libfrog/workqueue.h"
+#include "libfrog/histogram.h"
 #include "xfs_scrub.h"
 #include "common.h"
 #include "progress.h"
@@ -57,10 +58,12 @@ static int
 fstrim_fsblocks(
 	struct scrub_ctx	*ctx,
 	uint64_t		start_fsb,
-	uint64_t		fsbcount)
+	uint64_t		fsbcount,
+	uint64_t		minlen_fsb)
 {
 	uint64_t		start = cvt_off_fsb_to_b(&ctx->mnt, start_fsb);
 	uint64_t		len = cvt_off_fsb_to_b(&ctx->mnt, fsbcount);
+	uint64_t		minlen = cvt_off_fsb_to_b(&ctx->mnt, minlen_fsb);
 	int			error;
 
 	while (len > 0) {
@@ -68,7 +71,7 @@ fstrim_fsblocks(
 
 		run = min(len, FSTRIM_MAX_BYTES);
 
-		error = fstrim(ctx, start, run);
+		error = fstrim(ctx, start, run, minlen);
 		if (error == EOPNOTSUPP) {
 			/* Pretend we finished all the work. */
 			progress_add(len);
@@ -78,9 +81,10 @@ fstrim_fsblocks(
 			char		descr[DESCR_BUFSZ];
 
 			snprintf(descr, sizeof(descr) - 1,
-					_("fstrim start 0x%llx run 0x%llx"),
+					_("fstrim start 0x%llx run 0x%llx minlen 0x%llx"),
 					(unsigned long long)start,
-					(unsigned long long)run);
+					(unsigned long long)run,
+					(unsigned long long)minlen);
 			str_liberror(ctx, error, descr);
 			return error;
 		}
@@ -93,6 +97,64 @@ fstrim_fsblocks(
 	return 0;
 }
 
+/* Compute a suitable minlen parameter for fstrim. */
+static uint64_t
+fstrim_compute_minlen(
+	const struct scrub_ctx	*ctx,
+	const struct histogram	*freesp_hist)
+{
+	struct histogram	cdf;
+	uint64_t		ret = 0;
+	double			blk_threshold = 0;
+	unsigned int		i;
+	unsigned int		ag_max_usable;
+	int			error;
+
+	/*
+	 * The kernel will reject a minlen that's larger than m_ag_max_usable.
+	 * We can't calculate or query that value directly, so we guesstimate
+	 * that it's 95% of the AG size.
+	 */
+	ag_max_usable = ctx->mnt.fsgeom.agblocks * 95 / 100;
+
+	if (freesp_hist->totexts == 0)
+		goto out;
+
+	if (debug > 1)
+		hist_print(freesp_hist);
+
+	/* Insufficient samples to make a meaningful histogram */
+	if (freesp_hist->totexts < freesp_hist->nr_buckets * 10)
+		goto out;
+
+	hist_init(&cdf);
+	error = hist_cdf(freesp_hist, &cdf);
+	if (error)
+		goto out_free;
+
+	blk_threshold = freesp_hist->totblocks * ctx->fstrim_block_pct;
+	for (i = 1; i < freesp_hist->nr_buckets; i++) {
+		if (cdf.buckets[i].blocks < blk_threshold) {
+			ret = freesp_hist->buckets[i - 1].low;
+			break;
+		}
+	}
+
+out_free:
+	hist_free(&cdf);
+out:
+	if (debug > 1)
+		printf(_("fstrim minlen %lld threshold %lld ag_max_usable %u\n"),
+				(unsigned long long)ret,
+				(unsigned long long)blk_threshold,
+				ag_max_usable);
+	if (ret > ag_max_usable)
+		ret = ag_max_usable;
+	if (ret == 1)
+		ret = 0;
+	return ret;
+}
+
 /* Trim each AG on the data device. */
 static int
 fstrim_datadev(
@@ -100,8 +162,11 @@ fstrim_datadev(
 {
 	struct xfs_fsop_geom	*geo = &ctx->mnt.fsgeom;
 	uint64_t		fsbno;
+	uint64_t		minlen_fsb;
 	int			error;
 
+	minlen_fsb = fstrim_compute_minlen(ctx, &ctx->datadev_hist);
+
 	for (fsbno = 0; fsbno < geo->datablocks; fsbno += geo->agblocks) {
 		uint64_t	fsbcount;
 
@@ -112,7 +177,7 @@ fstrim_datadev(
 		 */
 		progress_add(geo->blocksize);
 		fsbcount = min(geo->datablocks - fsbno + 1, geo->agblocks);
-		error = fstrim_fsblocks(ctx, fsbno + 1, fsbcount);
+		error = fstrim_fsblocks(ctx, fsbno + 1, fsbcount, minlen_fsb);
 		if (error)
 			return error;
 	}
diff --git a/scrub/vfs.c b/scrub/vfs.c
index cc958ba9438..22c19485a2d 100644
--- a/scrub/vfs.c
+++ b/scrub/vfs.c
@@ -300,11 +300,13 @@ int
 fstrim(
 	struct scrub_ctx	*ctx,
 	uint64_t		start,
-	uint64_t		len)
+	uint64_t		len,
+	uint64_t		minlen)
 {
 	struct fstrim_range	range = {
 		.start		= start,
 		.len		= len,
+		.minlen		= minlen,
 	};
 
 	if (ioctl(ctx->mnt.fd, FITRIM, &range) == 0)
diff --git a/scrub/vfs.h b/scrub/vfs.h
index 1af8d80d1de..f0cfd53c27b 100644
--- a/scrub/vfs.h
+++ b/scrub/vfs.h
@@ -24,6 +24,6 @@ typedef int (*scan_fs_tree_dirent_fn)(struct scrub_ctx *, const char *,
 int scan_fs_tree(struct scrub_ctx *ctx, scan_fs_tree_dir_fn dir_fn,
 		scan_fs_tree_dirent_fn dirent_fn, void *arg);
 
-int fstrim(struct scrub_ctx *ctx, uint64_t start, uint64_t len);
+int fstrim(struct scrub_ctx *ctx, uint64_t start, uint64_t len, uint64_t minlen);
 
 #endif /* XFS_SCRUB_VFS_H_ */
diff --git a/scrub/xfs_scrub.c b/scrub/xfs_scrub.c
index c66469a0703..37b95aa1e67 100644
--- a/scrub/xfs_scrub.c
+++ b/scrub/xfs_scrub.c
@@ -622,11 +622,13 @@ report_outcome(
  */
 enum o_opt_nums {
 	IWARN = 0,
+	FSTRIM_PCT,
 	O_MAX_OPTS,
 };
 
 static char *o_opts[] = {
 	[IWARN]			= "iwarn",
+	[FSTRIM_PCT]		= "fstrim_pct",
 	[O_MAX_OPTS]		= NULL,
 };
 
@@ -635,8 +637,11 @@ parse_o_opts(
 	struct scrub_ctx	*ctx,
 	char			*p)
 {
+	double			dval;
+
 	while (*p != '\0')  {
 		char		*val;
+		char		*endp;
 
 		switch (getsubopt(&p, o_opts, &val))  {
 		case IWARN:
@@ -647,6 +652,35 @@ parse_o_opts(
 			}
 			info_is_warning = true;
 			break;
+		case FSTRIM_PCT:
+			if (!val) {
+				fprintf(stderr,
+ _("-o fstrim_pct requires a parameter\n"));
+				usage();
+			}
+
+			errno = 0;
+			dval = strtod(val, &endp);
+
+			if (*endp) {
+				fprintf(stderr,
+ _("-o fstrim_pct must be a floating point number\n"));
+				usage();
+			}
+			if (errno) {
+				fprintf(stderr,
+ _("-o fstrim_pct: %s\n"),
+						strerror(errno));
+				usage();
+			}
+			if (dval <= 0 || dval > 100) {
+				fprintf(stderr,
+ _("-o fstrim_pct must be larger than 0 and less than 100\n"));
+				usage();
+			}
+
+			ctx->fstrim_block_pct = dval / 100.0;
+			break;
 		default:
 			usage();
 			break;
@@ -659,7 +693,9 @@ main(
 	int			argc,
 	char			**argv)
 {
-	struct scrub_ctx	ctx = {0};
+	struct scrub_ctx	ctx = {
+		.fstrim_block_pct = FSTRIM_BLOCK_PCT_DEFAULT,
+	};
 	struct phase_rusage	all_pi;
 	char			*mtab = NULL;
 	FILE			*progress_fp = NULL;
diff --git a/scrub/xfs_scrub.h b/scrub/xfs_scrub.h
index 1a28f0cc847..7d48f4bad9c 100644
--- a/scrub/xfs_scrub.h
+++ b/scrub/xfs_scrub.h
@@ -90,8 +90,20 @@ struct scrub_ctx {
 
 	/* Free space histograms, in fsb */
 	struct histogram	datadev_hist;
+
+	/*
+	 * Pick the largest value for fstrim minlen such that we trim at least
+	 * this much space per volume.
+	 */
+	double			fstrim_block_pct;
 };
 
+/*
+ * Trim only enough free space extents (in order of decreasing length) to
+ * ensure that this percentage of the free space is trimmed.
+ */
+#define FSTRIM_BLOCK_PCT_DEFAULT	(99.0 / 100.0)
+
 /* Phase helper functions */
 void xfs_shutdown_fs(struct scrub_ctx *ctx);
 int scrub_cleanup(struct scrub_ctx *ctx);

[PATCH 1/9] debian: install scrub services with dh_installsystemd

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Use dh_installsystemd to handle the installation and activation of the
scrub systemd services.  This requires bumping the compat version to 11.
Note that the services are /not/ activated on installation.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 debian/rules |    1 +
 1 file changed, 1 insertion(+)


diff --git a/debian/rules b/debian/rules
index 95df4835b25..57baad625c5 100755
--- a/debian/rules
+++ b/debian/rules
@@ -108,6 +108,7 @@ binary-arch: checkroot built
 	dh_compress
 	dh_fixperms
 	dh_makeshlibs
+	dh_installsystemd -p xfsprogs --no-enable --no-start --no-restart-after-upgrade --no-stop-on-upgrade
 	dh_installdeb
 	dh_shlibdeps
 	dh_gencontrol

[PATCH 2/9] xfs_scrub_all: escape service names consistently

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

This program is not consistent as to whether or not it escapes the
pathname that is being used as the xfs_scrub service instance name.
Fix it to be consistent, and to fall back to direct invocation if
escaping doesn't work.  The escaping itself is also broken, but we'll
fix that in the next patch.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 scrub/xfs_scrub_all.in |   30 ++++++++++++++++--------------
 1 file changed, 16 insertions(+), 14 deletions(-)


diff --git a/scrub/xfs_scrub_all.in b/scrub/xfs_scrub_all.in
index 5042321a738..85f95f135cc 100644
--- a/scrub/xfs_scrub_all.in
+++ b/scrub/xfs_scrub_all.in
@@ -93,19 +93,19 @@ def run_killable(cmd, stdout, killfuncs, kill_fn):
 # that log messages from the service units preserve the full path and users can
 # look up log messages using full paths.  However, for "/" the escaping rules
 # do /not/ drop the initial slash, so we have to special-case that here.
-def systemd_escape(path):
+def path_to_service(path):
 	'''Escape a path to avoid mangled systemd mangling.'''
 
 	if path == '/':
-		return '-'
+		return 'xfs_scrub@-'
 	cmd = ['systemd-escape', '--path', path]
 	try:
 		proc = subprocess.Popen(cmd, stdout = subprocess.PIPE)
 		proc.wait()
 		for line in proc.stdout:
-			return '-' + line.decode(sys.stdout.encoding).strip()
+			return 'xfs_scrub@-%s' % line.decode(sys.stdout.encoding).strip()
 	except:
-		return path
+		return None
 
 def run_scrub(mnt, cond, running_devs, mntdevs, killfuncs):
 	'''Run a scrub process.'''
@@ -119,17 +119,19 @@ def run_scrub(mnt, cond, running_devs, mntdevs, killfuncs):
 			return
 
 		# Try it the systemd way
-		cmd=['systemctl', 'start', 'xfs_scrub@%s' % systemd_escape(mnt)]
-		ret = run_killable(cmd, DEVNULL(), killfuncs, \
-				lambda proc: kill_systemd('xfs_scrub@%s' % mnt, proc))
-		if ret == 0 or ret == 1:
-			print("Scrubbing %s done, (err=%d)" % (mnt, ret))
-			sys.stdout.flush()
-			retcode |= ret
-			return
+		svcname = path_to_service(path)
+		if svcname is not None:
+			cmd=['systemctl', 'start', svcname]
+			ret = run_killable(cmd, DEVNULL(), killfuncs, \
+					lambda proc: kill_systemd(svcname, proc))
+			if ret == 0 or ret == 1:
+				print("Scrubbing %s done, (err=%d)" % (mnt, ret))
+				sys.stdout.flush()
+				retcode |= ret
+				return
 
-		if terminate:
-			return
+			if terminate:
+				return
 
 		# Invoke xfs_scrub manually
 		cmd=['@sbindir@/xfs_scrub', '@scrub_args@', mnt]

[PATCH 3/9] xfs_scrub: fix pathname escaping across all service definitions

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

systemd services provide an "instance name" that can be associated with
a particular invocation of a service.  This allows service users to
invoke multiple copies of a service, each with a unique string.  For
xfs_scrub, we pass the mountpoint of the filesystem as the instance
name.  However, systemd services aren't supposed to have slashes in
them, so we're supposed to escape them.

The canonical escaping scheme for pathnames is defined by the
systemd-escape --path command.  Unfortunately, we've been adding our own
opinionated sauce for years, to work around the fact that --path didn't
exist in systemd before January 2017.  The special sauce is incorrect,
and we no longer care about systemd of 7 years past.

Clean up this mess by following the systemd escaping scheme throughout
the service units.  Now we can use the '%f' specifier in them, which
makes things a lot less complicated.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 scrub/Makefile                   |   19 +++++++++++++++----
 scrub/xfs_scrub@.service.in      |    6 +++---
 scrub/xfs_scrub_all.in           |   33 +++++++++++----------------------
 scrub/xfs_scrub_fail.in          |    5 ++++-
 scrub/xfs_scrub_fail@.service.in |    4 ++--
 5 files changed, 35 insertions(+), 32 deletions(-)
 rename scrub/{xfs_scrub_fail => xfs_scrub_fail.in} (75%)


diff --git a/scrub/Makefile b/scrub/Makefile
index af94cf0d684..fd47b893956 100644
--- a/scrub/Makefile
+++ b/scrub/Makefile
@@ -8,14 +8,17 @@ include $(builddefs)
 
 SCRUB_PREREQS=$(HAVE_OPENAT)$(HAVE_FSTATAT)$(HAVE_GETFSMAP)
 
+scrub_svcname=xfs_scrub@.service
+
 ifeq ($(SCRUB_PREREQS),yesyesyes)
 LTCOMMAND = xfs_scrub
 INSTALL_SCRUB = install-scrub
 XFS_SCRUB_ALL_PROG = xfs_scrub_all
+XFS_SCRUB_FAIL_PROG = xfs_scrub_fail
 XFS_SCRUB_ARGS = -b -n
 ifeq ($(HAVE_SYSTEMD),yes)
 INSTALL_SCRUB += install-systemd
-SYSTEMD_SERVICES = xfs_scrub@.service xfs_scrub_all.service xfs_scrub_all.timer xfs_scrub_fail@.service
+SYSTEMD_SERVICES = $(scrub_svcname) xfs_scrub_all.service xfs_scrub_all.timer xfs_scrub_fail@.service
 OPTIONAL_TARGETS += $(SYSTEMD_SERVICES)
 endif
 ifeq ($(HAVE_CROND),yes)
@@ -108,17 +111,25 @@ ifeq ($(HAVE_HDIO_GETGEO),yes)
 LCFLAGS += -DHAVE_HDIO_GETGEO
 endif
 
-LDIRT = $(XFS_SCRUB_ALL_PROG) *.service *.cron
+LDIRT = $(XFS_SCRUB_ALL_PROG) $(XFS_SCRUB_FAIL_PROG) *.service *.cron
 
-default: depend $(LTCOMMAND) $(XFS_SCRUB_ALL_PROG) $(OPTIONAL_TARGETS)
+default: depend $(LTCOMMAND) $(XFS_SCRUB_ALL_PROG) $(XFS_SCRUB_FAIL_PROG) $(OPTIONAL_TARGETS)
 
 xfs_scrub_all: xfs_scrub_all.in $(builddefs)
 	@echo "    [SED]    $@"
 	$(Q)$(SED) -e "s|@sbindir@|$(PKG_SBIN_DIR)|g" \
+		   -e "s|@scrub_svcname@|$(scrub_svcname)|g" \
 		   -e "s|@pkg_version@|$(PKG_VERSION)|g" \
 		   -e "s|@scrub_args@|$(XFS_SCRUB_ARGS)|g" < $< > $@
 	$(Q)chmod a+x $@
 
+xfs_scrub_fail: xfs_scrub_fail.in $(builddefs)
+	@echo "    [SED]    $@"
+	$(Q)$(SED) -e "s|@sbindir@|$(PKG_SBIN_DIR)|g" \
+		   -e "s|@scrub_svcname@|$(scrub_svcname)|g" \
+		   -e "s|@pkg_version@|$(PKG_VERSION)|g"  < $< > $@
+	$(Q)chmod a+x $@
+
 phase5.o unicrash.o xfs.o: $(builddefs)
 
 include $(BUILDRULES)
@@ -141,7 +152,7 @@ install-systemd: default $(SYSTEMD_SERVICES)
 	$(INSTALL) -m 755 -d $(SYSTEMD_SYSTEM_UNIT_DIR)
 	$(INSTALL) -m 644 $(SYSTEMD_SERVICES) $(SYSTEMD_SYSTEM_UNIT_DIR)
 	$(INSTALL) -m 755 -d $(PKG_LIB_SCRIPT_DIR)/$(PKG_NAME)
-	$(INSTALL) -m 755 xfs_scrub_fail $(PKG_LIB_SCRIPT_DIR)/$(PKG_NAME)
+	$(INSTALL) -m 755 $(XFS_SCRUB_FAIL_PROG) $(PKG_LIB_SCRIPT_DIR)/$(PKG_NAME)
 
 install-crond: default $(CRONTABS)
 	$(INSTALL) -m 755 -d $(CROND_DIR)
diff --git a/scrub/xfs_scrub@.service.in b/scrub/xfs_scrub@.service.in
index d878eeda4fd..043aad12f20 100644
--- a/scrub/xfs_scrub@.service.in
+++ b/scrub/xfs_scrub@.service.in
@@ -4,7 +4,7 @@
 # Author: Darrick J. Wong <djwong@kernel.org>
 
 [Unit]
-Description=Online XFS Metadata Check for %I
+Description=Online XFS Metadata Check for %f
 OnFailure=xfs_scrub_fail@%i.service
 Documentation=man:xfs_scrub(8)
 
@@ -13,7 +13,7 @@ Type=oneshot
 PrivateNetwork=true
 ProtectSystem=full
 ProtectHome=read-only
-# Disable private /tmp just in case %i is a path under /tmp.
+# Disable private /tmp just in case %f is a path under /tmp.
 PrivateTmp=no
 AmbientCapabilities=CAP_SYS_ADMIN CAP_FOWNER CAP_DAC_OVERRIDE CAP_DAC_READ_SEARCH CAP_SYS_RAWIO
 NoNewPrivileges=yes
@@ -21,5 +21,5 @@ User=nobody
 IOSchedulingClass=idle
 CPUSchedulingPolicy=idle
 Environment=SERVICE_MODE=1
-ExecStart=@sbindir@/xfs_scrub @scrub_args@ %I
+ExecStart=@sbindir@/xfs_scrub @scrub_args@ %f
 SyslogIdentifier=%N
diff --git a/scrub/xfs_scrub_all.in b/scrub/xfs_scrub_all.in
index 85f95f135cc..d7d36e1bdb0 100644
--- a/scrub/xfs_scrub_all.in
+++ b/scrub/xfs_scrub_all.in
@@ -81,29 +81,18 @@ def run_killable(cmd, stdout, killfuncs, kill_fn):
 		return -1
 
 # systemd doesn't like unit instance names with slashes in them, so it
-# replaces them with dashes when it invokes the service.  However, it's not
-# smart enough to convert the dashes to something else, so when it unescapes
-# the instance name to feed to xfs_scrub, it turns all dashes into slashes.
-# "/moo-cow" becomes "-moo-cow" becomes "/moo/cow", which is wrong.  systemd
-# actually /can/ escape the dashes correctly if it is told that this is a path
-# (and not a unit name), but it didn't do this prior to January 2017, so fix
-# this for them.
-#
-# systemd path escaping also drops the initial slash so we add that back in so
-# that log messages from the service units preserve the full path and users can
-# look up log messages using full paths.  However, for "/" the escaping rules
-# do /not/ drop the initial slash, so we have to special-case that here.
-def path_to_service(path):
-	'''Escape a path to avoid mangled systemd mangling.'''
+# replaces them with dashes when it invokes the service.  Filesystem paths
+# need a special --path argument so that dashes do not get mangled.
+def path_to_serviceunit(path):
+	'''Convert a pathname into a systemd service unit name.'''
 
-	if path == '/':
-		return 'xfs_scrub@-'
-	cmd = ['systemd-escape', '--path', path]
+	cmd = ['systemd-escape', '--template', '@scrub_svcname@',
+	       '--path', path]
 	try:
 		proc = subprocess.Popen(cmd, stdout = subprocess.PIPE)
 		proc.wait()
 		for line in proc.stdout:
-			return 'xfs_scrub@-%s' % line.decode(sys.stdout.encoding).strip()
+			return line.decode(sys.stdout.encoding).strip()
 	except:
 		return None
 
@@ -119,11 +108,11 @@ def run_scrub(mnt, cond, running_devs, mntdevs, killfuncs):
 			return
 
 		# Try it the systemd way
-		svcname = path_to_service(path)
-		if svcname is not None:
-			cmd=['systemctl', 'start', svcname]
+		unitname = path_to_serviceunit(path)
+		if unitname is not None:
+			cmd=['systemctl', 'start', unitname]
 			ret = run_killable(cmd, DEVNULL(), killfuncs, \
-					lambda proc: kill_systemd(svcname, proc))
+					lambda proc: kill_systemd(unitname, proc))
 			if ret == 0 or ret == 1:
 				print("Scrubbing %s done, (err=%d)" % (mnt, ret))
 				sys.stdout.flush()
diff --git a/scrub/xfs_scrub_fail b/scrub/xfs_scrub_fail.in
similarity index 75%
rename from scrub/xfs_scrub_fail
rename to scrub/xfs_scrub_fail.in
index 415efaa24d6..0bceda6403d 100755
--- a/scrub/xfs_scrub_fail
+++ b/scrub/xfs_scrub_fail.in
@@ -19,6 +19,9 @@ if [ ! -x "${mailer}" ]; then
 	exit 1
 fi
 
+# Turn the mountpoint into a properly escaped systemd instance name
+scrub_svc="$(systemd-escape --template "@scrub_svcname@" --path "${mntpoint}")"
+
 (cat << ENDL
 To: $1
 From: <xfs_scrub@${hostname}>
@@ -28,4 +31,4 @@ So sorry, the automatic xfs_scrub of ${mntpoint} on ${hostname} failed.
 
 A log of what happened follows:
 ENDL
-systemctl status --full --lines 4294967295 "xfs_scrub@${mntpoint}") | "${mailer}" -t -i
+systemctl status --full --lines 4294967295 "${scrub_svc}") | "${mailer}" -t -i
diff --git a/scrub/xfs_scrub_fail@.service.in b/scrub/xfs_scrub_fail@.service.in
index 187adc17f6d..048b5732459 100644
--- a/scrub/xfs_scrub_fail@.service.in
+++ b/scrub/xfs_scrub_fail@.service.in
@@ -4,13 +4,13 @@
 # Author: Darrick J. Wong <djwong@kernel.org>
 
 [Unit]
-Description=Online XFS Metadata Check Failure Reporting for %I
+Description=Online XFS Metadata Check Failure Reporting for %f
 Documentation=man:xfs_scrub(8)
 
 [Service]
 Type=oneshot
 Environment=EMAIL_ADDR=root
-ExecStart=@pkg_lib_dir@/@pkg_name@/xfs_scrub_fail "${EMAIL_ADDR}" %I
+ExecStart=@pkg_lib_dir@/@pkg_name@/xfs_scrub_fail "${EMAIL_ADDR}" %f
 User=mail
 Group=mail
 SupplementaryGroups=systemd-journal

[PATCH 4/9] xfs_scrub_fail: fix sendmail detection

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

This script emails the results of failed scrub runs to root.  We
shouldn't be hardcoding the path to the mailer program because distros
can change the path according to their whim.  Modify this script to use
command -v to find the program.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 scrub/xfs_scrub_fail.in |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)


diff --git a/scrub/xfs_scrub_fail.in b/scrub/xfs_scrub_fail.in
index 0bceda6403d..d6a3d92159b 100755
--- a/scrub/xfs_scrub_fail.in
+++ b/scrub/xfs_scrub_fail.in
@@ -7,13 +7,14 @@
 
 # Email logs of failed xfs_scrub unit runs
 
-mailer=/usr/sbin/sendmail
 recipient="$1"
 test -z "${recipient}" && exit 0
 mntpoint="$2"
 test -z "${mntpoint}" && exit 0
 hostname="$(hostname -f 2>/dev/null)"
 test -z "${hostname}" && hostname="${HOSTNAME}"
+
+mailer="$(command -v sendmail)"
 if [ ! -x "${mailer}" ]; then
 	echo "${mailer}: Mailer program not found."
 	exit 1

[PATCH 5/9] xfs_scrub_fail: return the failure status of the mailer program

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

We should return the exit code of the mailer program sending the scrub
failure reports, since that's much more important to anyone watching the
system.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 scrub/xfs_scrub_fail.in |    1 +
 1 file changed, 1 insertion(+)


diff --git a/scrub/xfs_scrub_fail.in b/scrub/xfs_scrub_fail.in
index d6a3d92159b..d3275f9897c 100755
--- a/scrub/xfs_scrub_fail.in
+++ b/scrub/xfs_scrub_fail.in
@@ -33,3 +33,4 @@ So sorry, the automatic xfs_scrub of ${mntpoint} on ${hostname} failed.
 A log of what happened follows:
 ENDL
 systemctl status --full --lines 4294967295 "${scrub_svc}") | "${mailer}" -t -i
+exit "${PIPESTATUS[1]}"

[PATCH 6/9] xfs_scrub_fail: add content type header to failure emails

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add content type and encoding metadata so that these emails display
correctly.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/xfs_scrub_fail.in |    2 ++
 1 file changed, 2 insertions(+)


diff --git a/scrub/xfs_scrub_fail.in b/scrub/xfs_scrub_fail.in
index d3275f9897c..baa9d32d94c 100755
--- a/scrub/xfs_scrub_fail.in
+++ b/scrub/xfs_scrub_fail.in
@@ -27,6 +27,8 @@ scrub_svc="$(systemd-escape --template "@scrub_svcname@" --path "${mntpoint}")"
 To: $1
 From: <xfs_scrub@${hostname}>
 Subject: xfs_scrub failure on ${mntpoint}
+Content-Transfer-Encoding: 8bit
+Content-Type: text/plain; charset=UTF-8
 
 So sorry, the automatic xfs_scrub of ${mntpoint} on ${hostname} failed.
 

[PATCH 7/9] xfs_scrub_fail: advise recipients not to reply

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Advise recipients of the service failure emails that they should not try
to reply to the automated service message.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/xfs_scrub_fail.in |    1 +
 1 file changed, 1 insertion(+)


diff --git a/scrub/xfs_scrub_fail.in b/scrub/xfs_scrub_fail.in
index baa9d32d94c..5dffb541798 100755
--- a/scrub/xfs_scrub_fail.in
+++ b/scrub/xfs_scrub_fail.in
@@ -31,6 +31,7 @@ Content-Transfer-Encoding: 8bit
 Content-Type: text/plain; charset=UTF-8
 
 So sorry, the automatic xfs_scrub of ${mntpoint} on ${hostname} failed.
+Please do not reply to this mesage.
 
 A log of what happened follows:
 ENDL

[PATCH 8/9] xfs_scrub_fail: move executable script to /usr/libexec

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Per FHS 3.0, non-PATH executable binaries are supposed to live under
/usr/libexec, not /usr/lib.  xfs_scrub_fail is an executable script,
so move it to libexec in case some distro some day tries to mount
/usr/lib as noexec or something.

Cc: Neal Gompa <neal@gompa.dev>
Link: https://refspecs.linuxfoundation.org/FHS_3.0/fhs/ch04s07.html
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 include/builddefs.in             |    1 +
 scrub/Makefile                   |    7 +++----
 scrub/xfs_scrub_fail@.service.in |    2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)


diff --git a/include/builddefs.in b/include/builddefs.in
index eb7f6ba4f03..9d0f9c3bf7c 100644
--- a/include/builddefs.in
+++ b/include/builddefs.in
@@ -52,6 +52,7 @@ PKG_ROOT_SBIN_DIR = @root_sbindir@
 PKG_ROOT_LIB_DIR= @root_libdir@@libdirsuffix@
 PKG_LIB_DIR	= @libdir@@libdirsuffix@
 PKG_LIB_SCRIPT_DIR	= @libdir@
+PKG_LIBEXEC_DIR	= @libexecdir@/@pkg_name@
 PKG_INC_DIR	= @includedir@/xfs
 DK_INC_DIR	= @includedir@/disk
 PKG_MAN_DIR	= @mandir@
diff --git a/scrub/Makefile b/scrub/Makefile
index fd47b893956..8fb366c922c 100644
--- a/scrub/Makefile
+++ b/scrub/Makefile
@@ -140,8 +140,7 @@ install: $(INSTALL_SCRUB)
 	@echo "    [SED]    $@"
 	$(Q)$(SED) -e "s|@sbindir@|$(PKG_SBIN_DIR)|g" \
 		   -e "s|@scrub_args@|$(XFS_SCRUB_ARGS)|g" \
-		   -e "s|@pkg_lib_dir@|$(PKG_LIB_SCRIPT_DIR)|g" \
-		   -e "s|@pkg_name@|$(PKG_NAME)|g" \
+		   -e "s|@pkg_libexec_dir@|$(PKG_LIBEXEC_DIR)|g" \
 		   < $< > $@
 
 %.cron: %.cron.in $(builddefs)
@@ -151,8 +150,8 @@ install: $(INSTALL_SCRUB)
 install-systemd: default $(SYSTEMD_SERVICES)
 	$(INSTALL) -m 755 -d $(SYSTEMD_SYSTEM_UNIT_DIR)
 	$(INSTALL) -m 644 $(SYSTEMD_SERVICES) $(SYSTEMD_SYSTEM_UNIT_DIR)
-	$(INSTALL) -m 755 -d $(PKG_LIB_SCRIPT_DIR)/$(PKG_NAME)
-	$(INSTALL) -m 755 $(XFS_SCRUB_FAIL_PROG) $(PKG_LIB_SCRIPT_DIR)/$(PKG_NAME)
+	$(INSTALL) -m 755 -d $(PKG_LIBEXEC_DIR)
+	$(INSTALL) -m 755 $(XFS_SCRUB_FAIL_PROG) $(PKG_LIBEXEC_DIR)
 
 install-crond: default $(CRONTABS)
 	$(INSTALL) -m 755 -d $(CROND_DIR)
diff --git a/scrub/xfs_scrub_fail@.service.in b/scrub/xfs_scrub_fail@.service.in
index 048b5732459..48a0f25b5f1 100644
--- a/scrub/xfs_scrub_fail@.service.in
+++ b/scrub/xfs_scrub_fail@.service.in
@@ -10,7 +10,7 @@ Documentation=man:xfs_scrub(8)
 [Service]
 Type=oneshot
 Environment=EMAIL_ADDR=root
-ExecStart=@pkg_lib_dir@/@pkg_name@/xfs_scrub_fail "${EMAIL_ADDR}" %f
+ExecStart=@pkg_libexec_dir@/xfs_scrub_fail "${EMAIL_ADDR}" %f
 User=mail
 Group=mail
 SupplementaryGroups=systemd-journal

[PATCH 9/9] xfs_scrub_all.cron: move to package data directory

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

cron jobs don't belong in /usr/lib.  Since the cron job is also
secondary to the systemd timer, it's really only provided as a courtesy
for distributions that don't use systemd.  Move it to @datadir@, aka
/usr/share/xfsprogs.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 include/builddefs.in |    1 -
 scrub/Makefile       |    2 +-
 2 files changed, 1 insertion(+), 2 deletions(-)


diff --git a/include/builddefs.in b/include/builddefs.in
index 9d0f9c3bf7c..f5138b5098f 100644
--- a/include/builddefs.in
+++ b/include/builddefs.in
@@ -51,7 +51,6 @@ PKG_SBIN_DIR	= @sbindir@
 PKG_ROOT_SBIN_DIR = @root_sbindir@
 PKG_ROOT_LIB_DIR= @root_libdir@@libdirsuffix@
 PKG_LIB_DIR	= @libdir@@libdirsuffix@
-PKG_LIB_SCRIPT_DIR	= @libdir@
 PKG_LIBEXEC_DIR	= @libexecdir@/@pkg_name@
 PKG_INC_DIR	= @includedir@/xfs
 DK_INC_DIR	= @includedir@/disk
diff --git a/scrub/Makefile b/scrub/Makefile
index 8fb366c922c..472df48a720 100644
--- a/scrub/Makefile
+++ b/scrub/Makefile
@@ -26,7 +26,7 @@ INSTALL_SCRUB += install-crond
 CRONTABS = xfs_scrub_all.cron
 OPTIONAL_TARGETS += $(CRONTABS)
 # Don't enable the crontab by default for now
-CROND_DIR = $(PKG_LIB_SCRIPT_DIR)/$(PKG_NAME)
+CROND_DIR = $(PKG_DATA_DIR)
 endif
 
 endif	# scrub_prereqs

[PATCH 1/4] xfs_scrub_all: fix argument passing when invoking xfs_scrub manually

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Currently, xfs_scrub_all will try to invoke xfs_scrub with argv[1] being
"-n -x".  This of course is recognized by C getopt as a weird looking
string, not two individual arguments, and causes the child process to
exit with complaints about CLI usage.

What we really want is to split the string into a proper array and then
add them to the xfs_scrub command line.  The code here isn't strictly
correct, but as @scrub_args@ is controlled by us in the Makefile, it'll
do for now.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 scrub/xfs_scrub_all.in |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)


diff --git a/scrub/xfs_scrub_all.in b/scrub/xfs_scrub_all.in
index d7d36e1bdb0..671d588177a 100644
--- a/scrub/xfs_scrub_all.in
+++ b/scrub/xfs_scrub_all.in
@@ -123,7 +123,9 @@ def run_scrub(mnt, cond, running_devs, mntdevs, killfuncs):
 				return
 
 		# Invoke xfs_scrub manually
-		cmd=['@sbindir@/xfs_scrub', '@scrub_args@', mnt]
+		cmd = ['@sbindir@/xfs_scrub']
+		cmd += '@scrub_args@'.split()
+		cmd += [mnt]
 		ret = run_killable(cmd, None, killfuncs, \
 				lambda proc: proc.terminate())
 		if ret >= 0:

[PATCH 2/4] xfs_scrub_all: survive systemd restarts when waiting for services

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

If xfs_scrub_all detects a running systemd, it will use it to invoke
xfs_scrub subprocesses in a sandboxed and resource-controlled
environment.  Unfortunately, if you happen to restart dbus or systemd
while it's running, you get this:

systemd[1]: Reexecuting.
xfs_scrub_all[9958]: Warning! D-Bus connection terminated.
xfs_scrub_all[9956]: Warning! D-Bus connection terminated.
xfs_scrub_all[9956]: Failed to wait for response: Connection reset by peer
xfs_scrub_all[9958]: Failed to wait for response: Connection reset by peer
xfs_scrub_all[9930]: Scrubbing / done, (err=1)
xfs_scrub_all[9930]: Scrubbing /storage done, (err=1)

The xfs_scrub units themselves are still running, it's just that the
`systemctl start' command that xfs_scrub_all uses to start and wait for
the unit lost its connection to dbus and hence is no longer monitoring
sub-services.

When this happens, we don't have great options -- systemctl doesn't have
a command to wait on an activating (aka running) unit.  Emulate the
functionality we normally get by polling the failed/active statuses.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 scrub/xfs_scrub_all.in |   78 ++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 65 insertions(+), 13 deletions(-)


diff --git a/scrub/xfs_scrub_all.in b/scrub/xfs_scrub_all.in
index 671d588177a..ab9b491fb4e 100644
--- a/scrub/xfs_scrub_all.in
+++ b/scrub/xfs_scrub_all.in
@@ -14,6 +14,7 @@ import time
 import sys
 import os
 import argparse
+from io import TextIOWrapper
 
 retcode = 0
 terminate = False
@@ -58,12 +59,18 @@ def find_mounts():
 
 	return fs
 
-def kill_systemd(unit, proc):
-	'''Kill systemd unit.'''
-	proc.terminate()
-	cmd=['systemctl', 'stop', unit]
-	x = subprocess.Popen(cmd)
-	x.wait()
+def backtick(cmd):
+	'''Generator function that yields lines of a program's stdout.'''
+	p = subprocess.Popen(cmd, stdout = subprocess.PIPE)
+	for line in TextIOWrapper(p.stdout, encoding="utf-8"):
+		yield line.strip()
+
+def remove_killfunc(killfuncs, fn):
+	'''Ensure fn is not in killfuncs.'''
+	try:
+		killfuncs.remove(fn)
+	except:
+		pass
 
 def run_killable(cmd, stdout, killfuncs, kill_fn):
 	'''Run a killable program.  Returns program retcode or -1 if we can't start it.'''
@@ -72,10 +79,7 @@ def run_killable(cmd, stdout, killfuncs, kill_fn):
 		real_kill_fn = lambda: kill_fn(proc)
 		killfuncs.add(real_kill_fn)
 		proc.wait()
-		try:
-			killfuncs.remove(real_kill_fn)
-		except:
-			pass
+		remove_killfunc(killfuncs, real_kill_fn)
 		return proc.returncode
 	except:
 		return -1
@@ -96,6 +100,56 @@ def path_to_serviceunit(path):
 	except:
 		return None
 
+def systemctl_stop(unitname):
+	'''Stop a systemd unit.'''
+	cmd = ['systemctl', 'stop', unitname]
+	x = subprocess.Popen(cmd)
+	x.wait()
+
+def systemctl_start(unitname, killfuncs):
+	'''Start a systemd unit and wait for it to complete.'''
+	stop_fn = None
+	cmd = ['systemctl', 'start', unitname]
+	try:
+		proc = subprocess.Popen(cmd, stdout = DEVNULL())
+		stop_fn = lambda: systemctl_stop(unitname)
+		killfuncs.add(stop_fn)
+		proc.wait()
+		ret = proc.returncode
+	except:
+		if stop_fn is not None:
+			remove_killfunc(killfuncs, stop_fn)
+		return -1
+
+	if ret != 1:
+		remove_killfunc(killfuncs, stop_fn)
+		return ret
+
+	# If systemctl-start returns 1, it's possible that the service failed
+	# or that dbus/systemd restarted and the client program lost its
+	# connection -- according to the systemctl man page, 1 means "unit not
+	# failed".
+	#
+	# Either way, we switch to polling the service status to try to wait
+	# for the service to end.  As of systemd 249, the is-active command
+	# returns any of the following states: active, reloading, inactive,
+	# failed, activating, deactivating, or maintenance.  Apparently these
+	# strings are not localized.
+	while True:
+		try:
+			for l in backtick(['systemctl', 'is-active', unitname]):
+				if l == 'failed':
+					remove_killfunc(killfuncs, stop_fn)
+					return 1
+				if l == 'inactive':
+					remove_killfunc(killfuncs, stop_fn)
+					return 0
+		except:
+			remove_killfunc(killfuncs, stop_fn)
+			return -1
+
+		time.sleep(1)
+
 def run_scrub(mnt, cond, running_devs, mntdevs, killfuncs):
 	'''Run a scrub process.'''
 	global retcode, terminate
@@ -110,9 +164,7 @@ def run_scrub(mnt, cond, running_devs, mntdevs, killfuncs):
 		# Try it the systemd way
 		unitname = path_to_serviceunit(path)
 		if unitname is not None:
-			cmd=['systemctl', 'start', unitname]
-			ret = run_killable(cmd, DEVNULL(), killfuncs, \
-					lambda proc: kill_systemd(unitname, proc))
+			ret = systemctl_start(unitname, killfuncs)
 			if ret == 0 or ret == 1:
 				print("Scrubbing %s done, (err=%d)" % (mnt, ret))
 				sys.stdout.flush()

[PATCH 3/4] xfs_scrub_all: simplify cleanup of run_killable

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Get rid of the nested lambda functions to simplify the code.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 scrub/xfs_scrub_all.in |   13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)


diff --git a/scrub/xfs_scrub_all.in b/scrub/xfs_scrub_all.in
index ab9b491fb4e..2c20b91fdbe 100644
--- a/scrub/xfs_scrub_all.in
+++ b/scrub/xfs_scrub_all.in
@@ -72,14 +72,14 @@ def remove_killfunc(killfuncs, fn):
 	except:
 		pass
 
-def run_killable(cmd, stdout, killfuncs, kill_fn):
-	'''Run a killable program.  Returns program retcode or -1 if we can't start it.'''
+def run_killable(cmd, stdout, killfuncs):
+	'''Run a killable program.  Returns program retcode or -1 if we can't
+	start it.'''
 	try:
 		proc = subprocess.Popen(cmd, stdout = stdout)
-		real_kill_fn = lambda: kill_fn(proc)
-		killfuncs.add(real_kill_fn)
+		killfuncs.add(proc.terminate)
 		proc.wait()
-		remove_killfunc(killfuncs, real_kill_fn)
+		remove_killfunc(killfuncs, proc.terminate)
 		return proc.returncode
 	except:
 		return -1
@@ -178,8 +178,7 @@ def run_scrub(mnt, cond, running_devs, mntdevs, killfuncs):
 		cmd = ['@sbindir@/xfs_scrub']
 		cmd += '@scrub_args@'.split()
 		cmd += [mnt]
-		ret = run_killable(cmd, None, killfuncs, \
-				lambda proc: proc.terminate())
+		ret = run_killable(cmd, None, killfuncs)
 		if ret >= 0:
 			print("Scrubbing %s done, (err=%d)" % (mnt, ret))
 			sys.stdout.flush()

[PATCH 4/4] xfs_scrub_all: fix termination signal handling

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Currently, xfs_scrub_all does not handle termination signals well.
SIGTERM and SIGINT are left to their default handlers, which are
immediate termination of the process group in the case of SIGTERM and
raising KeyboardInterrupt in the case of SIGINT.

Terminating the process group is fine when the xfs_scrub processes are
direct children, but this completely doesn't work if we're farming the
work out to systemd services since we don't terminate the child service.
Instead, they keep going.

Raising KeyboardInterrupt doesn't work because once the main thread
calls sys.exit at the bottom of main(), it blocks in the python runtime
waiting for child threads to terminate.  There's no longer any context
to handle an exception, so the signal is ignored and no child processes
are killed.

In other words, if you try to kill a running xfs_scrub_all, chances are
good it won't kill the child xfs_scrub processes.  This is undesirable
and egregious since we actually have the ability to track and kill all
the subprocesses that we create.

Solve the subproblem of getting stuck in the python runtime by calling
it repeatedly until we no longer have subprocesses.  This means that the
main thread loops until all threads have exited.

Solve the subproblem of the signals doing the wrong thing by setting up
our own signal handler that can wake up the main thread and initiate
subprocess shutdown, no matter whether the subprocesses are systemd
services or directly fork/exec'd.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 scrub/xfs_scrub_all.in |   64 +++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 52 insertions(+), 12 deletions(-)


diff --git a/scrub/xfs_scrub_all.in b/scrub/xfs_scrub_all.in
index 2c20b91fdbe..d0ab27fd306 100644
--- a/scrub/xfs_scrub_all.in
+++ b/scrub/xfs_scrub_all.in
@@ -14,6 +14,7 @@ import time
 import sys
 import os
 import argparse
+import signal
 from io import TextIOWrapper
 
 retcode = 0
@@ -196,6 +197,45 @@ def run_scrub(mnt, cond, running_devs, mntdevs, killfuncs):
 		cond.notify()
 		cond.release()
 
+def signal_scrubs(signum, cond):
+	'''Handle termination signals by killing xfs_scrub children.'''
+	global debug, terminate
+
+	if debug:
+		print('Signal handler called with signal', signum)
+		sys.stdout.flush()
+
+	terminate = True
+	cond.acquire()
+	cond.notify()
+	cond.release()
+
+def wait_for_termination(cond, killfuncs):
+	'''Wait for a child thread to terminate.  Returns True if we should
+	abort the program, False otherwise.'''
+	global debug, terminate
+
+	if debug:
+		print('waiting for threads to terminate')
+		sys.stdout.flush()
+
+	cond.acquire()
+	try:
+		cond.wait()
+	except KeyboardInterrupt:
+		terminate = True
+	cond.release()
+
+	if not terminate:
+		return False
+
+	print("Terminating...")
+	sys.stdout.flush()
+	while len(killfuncs) > 0:
+		fn = killfuncs.pop()
+		fn()
+	return True
+
 def main():
 	'''Find mounts, schedule scrub runs.'''
 	def thr(mnt, devs):
@@ -231,6 +271,10 @@ def main():
 	running_devs = set()
 	killfuncs = set()
 	cond = threading.Condition()
+
+	signal.signal(signal.SIGINT, lambda s, f: signal_scrubs(s, cond))
+	signal.signal(signal.SIGTERM, lambda s, f: signal_scrubs(s, cond))
+
 	while len(fs) > 0:
 		if len(running_devs) == 0:
 			mnt, devs = fs.popitem()
@@ -250,18 +294,14 @@ def main():
 				thr(mnt, devs)
 		for p in poppers:
 			fs.pop(p)
-		cond.acquire()
-		try:
-			cond.wait()
-		except KeyboardInterrupt:
-			terminate = True
-			print("Terminating...")
-			sys.stdout.flush()
-			while len(killfuncs) > 0:
-				fn = killfuncs.pop()
-				fn()
-			fs = []
-		cond.release()
+
+		# Wait for one thread to finish
+		if wait_for_termination(cond, killfuncs):
+			break
+
+	# Wait for the rest of the threads to finish
+	while len(killfuncs) > 0:
+		wait_for_termination(cond, killfuncs)
 
 	if journalthread is not None:
 		journalthread.terminate()

[PATCH 1/6] xfs_scrub: allow auxiliary pathnames for sandboxing

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

In the next patch, we'll tighten up the security on the xfs_scrub
service so that it can't escape.  However, sandboxing the service
involves making the host filesystem as inaccessible as possible, with
the filesystem to scrub bind mounted onto a known location within the
sandbox.  Hence we need one path for reporting and a new -M argument to
tell scrub what it should actually be trying to open.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 man/man8/xfs_scrub.8 |    9 ++++++++-
 scrub/phase1.c       |    4 ++--
 scrub/vfs.c          |    2 +-
 scrub/xfs_scrub.c    |   11 ++++++++---
 scrub/xfs_scrub.h    |    5 ++++-
 5 files changed, 23 insertions(+), 8 deletions(-)


diff --git a/man/man8/xfs_scrub.8 b/man/man8/xfs_scrub.8
index b9f253e1b07..6154011271e 100644
--- a/man/man8/xfs_scrub.8
+++ b/man/man8/xfs_scrub.8
@@ -4,7 +4,7 @@ xfs_scrub \- check and repair the contents of a mounted XFS filesystem
 .SH SYNOPSIS
 .B xfs_scrub
 [
-.B \-abCemnTvx
+.B \-abCeMmnTvx
 ]
 .I mount-point
 .br
@@ -79,6 +79,13 @@ behavior.
 .B \-k
 Do not call TRIM on the free space.
 .TP
+.BI \-M " real-mount-point"
+Open the this path for issuing scrub system calls to the kernel.
+The positional
+.I mount-point
+parameter will be used for displaying informational messages and logging.
+This parameter exists to enable process sandboxing for service mode.
+.TP
 .BI \-m " file"
 Search this file for mounted filesystems instead of /etc/mtab.
 .TP
diff --git a/scrub/phase1.c b/scrub/phase1.c
index 1b3f6e8eb4f..516d929d626 100644
--- a/scrub/phase1.c
+++ b/scrub/phase1.c
@@ -146,7 +146,7 @@ phase1_func(
 	 * CAP_SYS_ADMIN, which we probably need to do anything fancy
 	 * with the (XFS driver) kernel.
 	 */
-	error = -xfd_open(&ctx->mnt, ctx->mntpoint,
+	error = -xfd_open(&ctx->mnt, ctx->actual_mntpoint,
 			O_RDONLY | O_NOATIME | O_DIRECTORY);
 	if (error) {
 		if (error == EPERM)
@@ -199,7 +199,7 @@ _("Not an XFS filesystem."));
 		return error;
 	}
 
-	error = path_to_fshandle(ctx->mntpoint, &ctx->fshandle,
+	error = path_to_fshandle(ctx->actual_mntpoint, &ctx->fshandle,
 			&ctx->fshandle_len);
 	if (error) {
 		str_errno(ctx, _("getting fshandle"));
diff --git a/scrub/vfs.c b/scrub/vfs.c
index 22c19485a2d..fca9a4cf356 100644
--- a/scrub/vfs.c
+++ b/scrub/vfs.c
@@ -249,7 +249,7 @@ scan_fs_tree(
 		goto out_cond;
 	}
 
-	ret = queue_subdir(ctx, &sft, &wq, ctx->mntpoint, true);
+	ret = queue_subdir(ctx, &sft, &wq, ctx->actual_mntpoint, true);
 	if (ret) {
 		str_liberror(ctx, ret, _("queueing directory scan"));
 		goto out_wq;
diff --git a/scrub/xfs_scrub.c b/scrub/xfs_scrub.c
index 37b95aa1e67..4912333219d 100644
--- a/scrub/xfs_scrub.c
+++ b/scrub/xfs_scrub.c
@@ -725,7 +725,7 @@ main(
 	pthread_mutex_init(&ctx.lock, NULL);
 	ctx.mode = SCRUB_MODE_REPAIR;
 	ctx.error_action = ERRORS_CONTINUE;
-	while ((c = getopt(argc, argv, "a:bC:de:km:no:TvxV")) != EOF) {
+	while ((c = getopt(argc, argv, "a:bC:de:kM:m:no:TvxV")) != EOF) {
 		switch (c) {
 		case 'a':
 			ctx.max_errors = cvt_u64(optarg, 10);
@@ -769,6 +769,9 @@ main(
 		case 'k':
 			want_fstrim = false;
 			break;
+		case 'M':
+			ctx.actual_mntpoint = optarg;
+			break;
 		case 'm':
 			mtab = optarg;
 			break;
@@ -823,6 +826,8 @@ main(
 		usage();
 
 	ctx.mntpoint = argv[optind];
+	if (!ctx.actual_mntpoint)
+		ctx.actual_mntpoint = ctx.mntpoint;
 
 	stdout_isatty = isatty(STDOUT_FILENO);
 	stderr_isatty = isatty(STDERR_FILENO);
@@ -840,7 +845,7 @@ main(
 		return SCRUB_RET_OPERROR;
 
 	/* Find the mount record for the passed-in argument. */
-	if (stat(argv[optind], &ctx.mnt_sb) < 0) {
+	if (stat(ctx.actual_mntpoint, &ctx.mnt_sb) < 0) {
 		fprintf(stderr,
 			_("%s: could not stat: %s: %s\n"),
 			progname, argv[optind], strerror(errno));
@@ -863,7 +868,7 @@ main(
 	}
 
 	fs_table_initialise(0, NULL, 0, NULL);
-	fsp = fs_table_lookup_mount(ctx.mntpoint);
+	fsp = fs_table_lookup_mount(ctx.actual_mntpoint);
 	if (!fsp) {
 		fprintf(stderr, _("%s: Not a XFS mount point.\n"),
 				ctx.mntpoint);
diff --git a/scrub/xfs_scrub.h b/scrub/xfs_scrub.h
index 7d48f4bad9c..b0aa9fcc67b 100644
--- a/scrub/xfs_scrub.h
+++ b/scrub/xfs_scrub.h
@@ -38,9 +38,12 @@ enum error_action {
 struct scrub_ctx {
 	/* Immutable scrub state. */
 
-	/* Strings we need for presentation */
+	/* Mountpoint we use for presentation */
 	char			*mntpoint;
 
+	/* Actual VFS path to the filesystem */
+	char			*actual_mntpoint;
+
 	/* Mountpoint info */
 	struct stat		mnt_sb;
 	struct statvfs		mnt_sv;

[PATCH 2/6] xfs_scrub.service: reduce CPU usage to 60% when possible

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Currently, the xfs_scrub background service is configured to use -b,
which means that the program runs completely serially.  However, even
using 100% of one CPU with idle priority may be enough to cause thermal
throttling and unwanted fan noise on smaller systems (e.g. laptops) with
fast IO systems.

Let's try to avoid this (at least on systemd) by using cgroups to limit
the program's usage to 60% of one CPU and lowering the nice priority in
the scheduler.  What we /really/ want is to run steadily on an
efficiency core, but there doesn't seem to be a means to ask the
scheduler not to ramp up the CPU frequency for a particular task.

While we're at it, group the resource limit directives together.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 scrub/Makefile                   |    7 ++++++-
 scrub/system-xfs_scrub.slice     |   30 ++++++++++++++++++++++++++++++
 scrub/xfs_scrub@.service.in      |   12 ++++++++++--
 scrub/xfs_scrub_all.service.in   |    4 ++++
 scrub/xfs_scrub_fail@.service.in |    4 ++++
 5 files changed, 54 insertions(+), 3 deletions(-)
 create mode 100644 scrub/system-xfs_scrub.slice


diff --git a/scrub/Makefile b/scrub/Makefile
index 472df48a720..42b27bfcad7 100644
--- a/scrub/Makefile
+++ b/scrub/Makefile
@@ -18,7 +18,12 @@ XFS_SCRUB_FAIL_PROG = xfs_scrub_fail
 XFS_SCRUB_ARGS = -b -n
 ifeq ($(HAVE_SYSTEMD),yes)
 INSTALL_SCRUB += install-systemd
-SYSTEMD_SERVICES = $(scrub_svcname) xfs_scrub_all.service xfs_scrub_all.timer xfs_scrub_fail@.service
+SYSTEMD_SERVICES=\
+	$(scrub_svcname) \
+	xfs_scrub_fail@.service \
+	xfs_scrub_all.service \
+	xfs_scrub_all.timer \
+	system-xfs_scrub.slice
 OPTIONAL_TARGETS += $(SYSTEMD_SERVICES)
 endif
 ifeq ($(HAVE_CROND),yes)
diff --git a/scrub/system-xfs_scrub.slice b/scrub/system-xfs_scrub.slice
new file mode 100644
index 00000000000..95cd4f74526
--- /dev/null
+++ b/scrub/system-xfs_scrub.slice
@@ -0,0 +1,30 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2022-2024 Oracle.  All Rights Reserved.
+# Author: Darrick J. Wong <djwong@kernel.org>
+
+[Unit]
+Description=xfs_scrub background service slice
+Before=slices.target
+
+[Slice]
+
+# If the CPU usage cgroup controller is available, don't use more than 60% of a
+# single core for all background processes.
+CPUQuota=60%
+CPUAccounting=true
+
+[Install]
+# As of systemd 249, the systemd cgroupv2 configuration code will drop resource
+# controllers from the root and system.slice cgroups at startup if it doesn't
+# find any direct dependencies that require a given controller.  Newly
+# activated units with resource control directives are created under the system
+# slice but do not cause a reconfiguration of the slice's resource controllers.
+# Hence we cannot put CPUQuota= into the xfs_scrub service units directly.
+#
+# For the CPUQuota directive to have any effect, we must therefore create an
+# explicit definition file for the slice that systemd creates to contain the
+# xfs_scrub instance units (e.g. xfs_scrub@.service) and we must configure this
+# slice as a dependency of the system slice to establish the direct dependency
+# relation.
+WantedBy=system.slice
diff --git a/scrub/xfs_scrub@.service.in b/scrub/xfs_scrub@.service.in
index 043aad12f20..7306e173ebe 100644
--- a/scrub/xfs_scrub@.service.in
+++ b/scrub/xfs_scrub@.service.in
@@ -18,8 +18,16 @@ PrivateTmp=no
 AmbientCapabilities=CAP_SYS_ADMIN CAP_FOWNER CAP_DAC_OVERRIDE CAP_DAC_READ_SEARCH CAP_SYS_RAWIO
 NoNewPrivileges=yes
 User=nobody
-IOSchedulingClass=idle
-CPUSchedulingPolicy=idle
 Environment=SERVICE_MODE=1
 ExecStart=@sbindir@/xfs_scrub @scrub_args@ %f
 SyslogIdentifier=%N
+
+# Run scrub with minimal CPU and IO priority so that nothing else will starve.
+IOSchedulingClass=idle
+CPUSchedulingPolicy=idle
+CPUAccounting=true
+Nice=19
+
+# Create the service underneath the scrub background service slice so that we
+# can control resource usage.
+Slice=system-xfs_scrub.slice
diff --git a/scrub/xfs_scrub_all.service.in b/scrub/xfs_scrub_all.service.in
index 4011ed271f9..0f4bddf740a 100644
--- a/scrub/xfs_scrub_all.service.in
+++ b/scrub/xfs_scrub_all.service.in
@@ -14,3 +14,7 @@ Type=oneshot
 Environment=SERVICE_MODE=1
 ExecStart=@sbindir@/xfs_scrub_all
 SyslogIdentifier=xfs_scrub_all
+
+# Create the service underneath the scrub background service slice so that we
+# can control resource usage.
+Slice=system-xfs_scrub.slice
diff --git a/scrub/xfs_scrub_fail@.service.in b/scrub/xfs_scrub_fail@.service.in
index 48a0f25b5f1..dfbbd3b8218 100644
--- a/scrub/xfs_scrub_fail@.service.in
+++ b/scrub/xfs_scrub_fail@.service.in
@@ -14,3 +14,7 @@ ExecStart=@pkg_libexec_dir@/xfs_scrub_fail "${EMAIL_ADDR}" %f
 User=mail
 Group=mail
 SupplementaryGroups=systemd-journal
+
+# Create the service underneath the scrub background service slice so that we
+# can control resource usage.
+Slice=system-xfs_scrub.slice

[PATCH 3/6] xfs_scrub: use dynamic users when running as a systemd service

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Five years ago, systemd introduced the DynamicUser directive that
allocates a new unique user/group id, runs a service with those ids, and
deletes them after the service exits.  This is a good replacement for
User=nobody, since it eliminates the threat of nobody-services messing
with each other.

Make this transition ahead of all the other security tightenings that
will land in the next few patches, and add credits for the people who
suggested the change and reviewed it.

Link: https://0pointer.net/blog/dynamic-users-with-systemd.html
Suggested-by: Helle Vaanzinn <glitsj16@riseup.net>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/xfs_scrub@.service.in |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)


diff --git a/scrub/xfs_scrub@.service.in b/scrub/xfs_scrub@.service.in
index 7306e173ebe..504d3606985 100644
--- a/scrub/xfs_scrub@.service.in
+++ b/scrub/xfs_scrub@.service.in
@@ -17,7 +17,6 @@ ProtectHome=read-only
 PrivateTmp=no
 AmbientCapabilities=CAP_SYS_ADMIN CAP_FOWNER CAP_DAC_OVERRIDE CAP_DAC_READ_SEARCH CAP_SYS_RAWIO
 NoNewPrivileges=yes
-User=nobody
 Environment=SERVICE_MODE=1
 ExecStart=@sbindir@/xfs_scrub @scrub_args@ %f
 SyslogIdentifier=%N
@@ -31,3 +30,6 @@ Nice=19
 # Create the service underneath the scrub background service slice so that we
 # can control resource usage.
 Slice=system-xfs_scrub.slice
+
+# Dynamically create a user that isn't root
+DynamicUser=true

[PATCH 4/6] xfs_scrub: tighten up the security on the background systemd service

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Currently, xfs_scrub has to run with some elevated privileges.  Minimize
the risk of xfs_scrub escaping its service container or contaminating
the rest of the system by using systemd's sandboxing controls to
prohibit as much access as possible.

The directives added by this patch were recommended by the command
'systemd-analyze security xfs_scrub@.service' in systemd 249.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 scrub/xfs_scrub@.service.in |   81 +++++++++++++++++++++++++++++++++++++++----
 1 file changed, 73 insertions(+), 8 deletions(-)


diff --git a/scrub/xfs_scrub@.service.in b/scrub/xfs_scrub@.service.in
index 504d3606985..d834f26bd53 100644
--- a/scrub/xfs_scrub@.service.in
+++ b/scrub/xfs_scrub@.service.in
@@ -8,17 +8,21 @@ Description=Online XFS Metadata Check for %f
 OnFailure=xfs_scrub_fail@%i.service
 Documentation=man:xfs_scrub(8)
 
+# Explicitly require the capabilities that this program needs
+ConditionCapability=CAP_SYS_ADMIN
+ConditionCapability=CAP_FOWNER
+ConditionCapability=CAP_DAC_OVERRIDE
+ConditionCapability=CAP_DAC_READ_SEARCH
+ConditionCapability=CAP_SYS_RAWIO
+
+# Must be a mountpoint
+ConditionPathIsMountPoint=%f
+RequiresMountsFor=%f
+
 [Service]
 Type=oneshot
-PrivateNetwork=true
-ProtectSystem=full
-ProtectHome=read-only
-# Disable private /tmp just in case %f is a path under /tmp.
-PrivateTmp=no
-AmbientCapabilities=CAP_SYS_ADMIN CAP_FOWNER CAP_DAC_OVERRIDE CAP_DAC_READ_SEARCH CAP_SYS_RAWIO
-NoNewPrivileges=yes
 Environment=SERVICE_MODE=1
-ExecStart=@sbindir@/xfs_scrub @scrub_args@ %f
+ExecStart=@sbindir@/xfs_scrub @scrub_args@ -M /tmp/scrub/ %f
 SyslogIdentifier=%N
 
 # Run scrub with minimal CPU and IO priority so that nothing else will starve.
@@ -31,5 +35,66 @@ Nice=19
 # can control resource usage.
 Slice=system-xfs_scrub.slice
 
+# No realtime CPU scheduling
+RestrictRealtime=true
+
 # Dynamically create a user that isn't root
 DynamicUser=true
+
+# Make the entire filesystem readonly and /home inaccessible, then bind mount
+# the filesystem we're supposed to be checking into our private /tmp dir.
+# 'norbind' means that we don't bind anything under that original mount.
+ProtectSystem=strict
+ProtectHome=yes
+PrivateTmp=true
+BindPaths=%f:/tmp/scrub:norbind
+
+# Don't let scrub complain about paths in /etc/projects that have been hidden
+# by our sandboxing.  scrub doesn't care about project ids anyway.
+InaccessiblePaths=-/etc/projects
+
+# No network access
+PrivateNetwork=true
+ProtectHostname=true
+RestrictAddressFamilies=none
+IPAddressDeny=any
+
+# Don't let the program mess with the kernel configuration at all
+ProtectKernelLogs=true
+ProtectKernelModules=true
+ProtectKernelTunables=true
+ProtectControlGroups=true
+ProtectProc=invisible
+RestrictNamespaces=true
+
+# Hide everything in /proc, even /proc/mounts
+ProcSubset=pid
+
+# Only allow the default personality Linux
+LockPersonality=true
+
+# No writable memory pages
+MemoryDenyWriteExecute=true
+
+# Don't let our mounts leak out to the host
+PrivateMounts=true
+
+# Restrict system calls to the native arch and only enough to get things going
+SystemCallArchitectures=native
+SystemCallFilter=@system-service
+SystemCallFilter=~@privileged
+SystemCallFilter=~@resources
+SystemCallFilter=~@mount
+
+# xfs_scrub needs these privileges to run, and no others
+CapabilityBoundingSet=CAP_SYS_ADMIN CAP_FOWNER CAP_DAC_OVERRIDE CAP_DAC_READ_SEARCH CAP_SYS_RAWIO
+AmbientCapabilities=CAP_SYS_ADMIN CAP_FOWNER CAP_DAC_OVERRIDE CAP_DAC_READ_SEARCH CAP_SYS_RAWIO
+NoNewPrivileges=true
+
+# xfs_scrub doesn't create files
+UMask=7777
+
+# No access to hardware /dev files except for block devices
+ProtectClock=true
+DevicePolicy=closed
+DeviceAllow=block-*

[PATCH 5/6] xfs_scrub_fail: tighten up the security on the background systemd service

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Currently, xfs_scrub_fail has to run with enough privileges to access
the journal contents for a given scrub run and to send a report via
email.  Minimize the risk of xfs_scrub_fail escaping its service
container or contaminating the rest of the system by using systemd's
sandboxing controls to prohibit as much access as possible.

The directives added by this patch were recommended by the command
'systemd-analyze security xfs_scrub_fail@.service' in systemd 249.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/xfs_scrub_fail@.service.in |   55 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)


diff --git a/scrub/xfs_scrub_fail@.service.in b/scrub/xfs_scrub_fail@.service.in
index dfbbd3b8218..4a40f3bdc85 100644
--- a/scrub/xfs_scrub_fail@.service.in
+++ b/scrub/xfs_scrub_fail@.service.in
@@ -18,3 +18,58 @@ SupplementaryGroups=systemd-journal
 # Create the service underneath the scrub background service slice so that we
 # can control resource usage.
 Slice=system-xfs_scrub.slice
+
+# No realtime scheduling
+RestrictRealtime=true
+
+# Make the entire filesystem readonly and /home inaccessible.
+ProtectSystem=full
+ProtectHome=yes
+PrivateTmp=true
+RestrictSUIDSGID=true
+
+# Emailing reports requires network access, but not the ability to change the
+# hostname.
+ProtectHostname=true
+
+# Don't let the program mess with the kernel configuration at all
+ProtectKernelLogs=true
+ProtectKernelModules=true
+ProtectKernelTunables=true
+ProtectControlGroups=true
+ProtectProc=invisible
+RestrictNamespaces=true
+
+# Can't hide /proc because journalctl needs it to find various pieces of log
+# information
+#ProcSubset=pid
+
+# Only allow the default personality Linux
+LockPersonality=true
+
+# No writable memory pages
+MemoryDenyWriteExecute=true
+
+# Don't let our mounts leak out to the host
+PrivateMounts=true
+
+# Restrict system calls to the native arch and only enough to get things going
+SystemCallArchitectures=native
+SystemCallFilter=@system-service
+SystemCallFilter=~@privileged
+SystemCallFilter=~@resources
+SystemCallFilter=~@mount
+
+# xfs_scrub needs these privileges to run, and no others
+CapabilityBoundingSet=
+NoNewPrivileges=true
+
+# Failure reporting shouldn't create world-readable files
+UMask=0077
+
+# Clean up any IPC objects when this unit stops
+RemoveIPC=true
+
+# No access to hardware device files
+PrivateDevices=true
+ProtectClock=true

[PATCH 6/6] xfs_scrub_all: tighten up the security on the background systemd service

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Currently, xfs_scrub_all has to run with enough privileges to find
mounted XFS filesystems and the device associated with that mount and to
start xfs_scrub@<mountpoint> sub-services.  Minimize the risk of
xfs_scrub_all escaping its service container or contaminating the rest
of the system by using systemd's sandboxing controls to prohibit as much
access as possible.

The directives added by this patch were recommended by the command
'systemd-analyze security xfs_scrub_all.service' in systemd 249.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/xfs_scrub_all.service.in |   62 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 62 insertions(+)


diff --git a/scrub/xfs_scrub_all.service.in b/scrub/xfs_scrub_all.service.in
index 0f4bddf740a..f746f7b69f6 100644
--- a/scrub/xfs_scrub_all.service.in
+++ b/scrub/xfs_scrub_all.service.in
@@ -18,3 +18,65 @@ SyslogIdentifier=xfs_scrub_all
 # Create the service underneath the scrub background service slice so that we
 # can control resource usage.
 Slice=system-xfs_scrub.slice
+
+# Run scrub_all with minimal CPU and IO priority so that nothing will starve.
+IOSchedulingClass=idle
+CPUSchedulingPolicy=idle
+CPUAccounting=true
+Nice=19
+
+# No realtime scheduling
+RestrictRealtime=true
+
+# No special privileges, but we still have to run as root so that we can
+# contact the service manager to start the sub-units.
+CapabilityBoundingSet=
+NoNewPrivileges=true
+RestrictSUIDSGID=true
+
+# Make the entire filesystem readonly.  We don't want to hide anything because
+# we need to find all mounted XFS filesystems in the host.
+ProtectSystem=strict
+ProtectHome=read-only
+PrivateTmp=false
+
+# No network access except to the systemd control socket
+PrivateNetwork=true
+ProtectHostname=true
+RestrictAddressFamilies=AF_UNIX
+IPAddressDeny=any
+
+# Don't let the program mess with the kernel configuration at all
+ProtectKernelLogs=true
+ProtectKernelModules=true
+ProtectKernelTunables=true
+ProtectControlGroups=true
+ProtectProc=invisible
+RestrictNamespaces=true
+
+# Hide everything in /proc, even /proc/mounts
+ProcSubset=pid
+
+# Only allow the default personality Linux
+LockPersonality=true
+
+# No writable memory pages
+MemoryDenyWriteExecute=true
+
+# Don't let our mounts leak out to the host
+PrivateMounts=true
+
+# Restrict system calls to the native arch and only enough to get things going
+SystemCallArchitectures=native
+SystemCallFilter=@system-service
+SystemCallFilter=~@privileged
+SystemCallFilter=~@resources
+SystemCallFilter=~@mount
+
+# Media scan stamp file shouldn't be readable by regular users
+UMask=0077
+
+# lsblk ignores mountpoints if it can't find the device files, so we cannot
+# hide them
+#ProtectClock=true
+#PrivateDevices=true

[PATCH 1/6] xfs_scrub_all: only use the xfs_scrub@ systemd services in service mode

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Since the per-mount xfs_scrub@.service definition includes a bunch of
resource usage constraints, we no longer want to use those services if
xfs_scrub_all is being run directly by the sysadmin (aka not in service
mode) on the presumption that sysadmins want answers as quickly as
possible.

Therefore, only try to call the systemd service from xfs_scrub_all if
SERVICE_MODE is set in the environment.  If reaching out to systemd
fails and we're in service mode, we still want to run xfs_scrub
directly.  Split the makefile variables as necessary so that we only
pass -b to xfs_scrub in service mode.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/Makefile              |    5 ++++-
 scrub/xfs_scrub@.service.in |    2 +-
 scrub/xfs_scrub_all.in      |   11 ++++++++---
 3 files changed, 13 insertions(+), 5 deletions(-)


diff --git a/scrub/Makefile b/scrub/Makefile
index 42b27bfcad7..53a83ff8efb 100644
--- a/scrub/Makefile
+++ b/scrub/Makefile
@@ -15,7 +15,8 @@ LTCOMMAND = xfs_scrub
 INSTALL_SCRUB = install-scrub
 XFS_SCRUB_ALL_PROG = xfs_scrub_all
 XFS_SCRUB_FAIL_PROG = xfs_scrub_fail
-XFS_SCRUB_ARGS = -b -n
+XFS_SCRUB_ARGS = -n
+XFS_SCRUB_SERVICE_ARGS = -b
 ifeq ($(HAVE_SYSTEMD),yes)
 INSTALL_SCRUB += install-systemd
 SYSTEMD_SERVICES=\
@@ -125,6 +126,7 @@ xfs_scrub_all: xfs_scrub_all.in $(builddefs)
 	$(Q)$(SED) -e "s|@sbindir@|$(PKG_SBIN_DIR)|g" \
 		   -e "s|@scrub_svcname@|$(scrub_svcname)|g" \
 		   -e "s|@pkg_version@|$(PKG_VERSION)|g" \
+		   -e "s|@scrub_service_args@|$(XFS_SCRUB_SERVICE_ARGS)|g" \
 		   -e "s|@scrub_args@|$(XFS_SCRUB_ARGS)|g" < $< > $@
 	$(Q)chmod a+x $@
 
@@ -144,6 +146,7 @@ install: $(INSTALL_SCRUB)
 %.service: %.service.in $(builddefs)
 	@echo "    [SED]    $@"
 	$(Q)$(SED) -e "s|@sbindir@|$(PKG_SBIN_DIR)|g" \
+		   -e "s|@scrub_service_args@|$(XFS_SCRUB_SERVICE_ARGS)|g" \
 		   -e "s|@scrub_args@|$(XFS_SCRUB_ARGS)|g" \
 		   -e "s|@pkg_libexec_dir@|$(PKG_LIBEXEC_DIR)|g" \
 		   < $< > $@
diff --git a/scrub/xfs_scrub@.service.in b/scrub/xfs_scrub@.service.in
index d834f26bd53..10cc135e691 100644
--- a/scrub/xfs_scrub@.service.in
+++ b/scrub/xfs_scrub@.service.in
@@ -22,7 +22,7 @@ RequiresMountsFor=%f
 [Service]
 Type=oneshot
 Environment=SERVICE_MODE=1
-ExecStart=@sbindir@/xfs_scrub @scrub_args@ -M /tmp/scrub/ %f
+ExecStart=@sbindir@/xfs_scrub @scrub_service_args@ @scrub_args@ -M /tmp/scrub/ %f
 SyslogIdentifier=%N
 
 # Run scrub with minimal CPU and IO priority so that nothing else will starve.
diff --git a/scrub/xfs_scrub_all.in b/scrub/xfs_scrub_all.in
index d0ab27fd306..f27251fa543 100644
--- a/scrub/xfs_scrub_all.in
+++ b/scrub/xfs_scrub_all.in
@@ -162,9 +162,10 @@ def run_scrub(mnt, cond, running_devs, mntdevs, killfuncs):
 		if terminate:
 			return
 
-		# Try it the systemd way
+		# Run per-mount systemd xfs_scrub service only if we ourselves
+		# are running as a systemd service.
 		unitname = path_to_serviceunit(path)
-		if unitname is not None:
+		if unitname is not None and 'SERVICE_MODE' in os.environ:
 			ret = systemctl_start(unitname, killfuncs)
 			if ret == 0 or ret == 1:
 				print("Scrubbing %s done, (err=%d)" % (mnt, ret))
@@ -175,8 +176,12 @@ def run_scrub(mnt, cond, running_devs, mntdevs, killfuncs):
 			if terminate:
 				return
 
-		# Invoke xfs_scrub manually
+		# Invoke xfs_scrub manually if we're running in the foreground.
+		# We also permit this if we're running as a cronjob where
+		# systemd services are unavailable.
 		cmd = ['@sbindir@/xfs_scrub']
+		if 'SERVICE_MODE' in os.environ:
+			cmd += '@scrub_service_args@'.split()
 		cmd += '@scrub_args@'.split()
 		cmd += [mnt]
 		ret = run_killable(cmd, None, killfuncs)

[PATCH 2/6] xfs_scrub_all: remove journalctl background process

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Now that we only start systemd services if we're running in service
mode, there's no need for the background journalctl process that only
ran if we had started systemd services in non-service mode.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/xfs_scrub_all.in |   14 --------------
 1 file changed, 14 deletions(-)


diff --git a/scrub/xfs_scrub_all.in b/scrub/xfs_scrub_all.in
index f27251fa543..fc7a2e637ef 100644
--- a/scrub/xfs_scrub_all.in
+++ b/scrub/xfs_scrub_all.in
@@ -261,17 +261,6 @@ def main():
 
 	fs = find_mounts()
 
-	# Tail the journal if we ourselves aren't a service...
-	journalthread = None
-	if 'SERVICE_MODE' not in os.environ:
-		try:
-			cmd=['journalctl', '--no-pager', '-q', '-S', 'now', \
-					'-f', '-u', 'xfs_scrub@*', '-o', \
-					'cat']
-			journalthread = subprocess.Popen(cmd)
-		except:
-			pass
-
 	# Schedule scrub jobs...
 	running_devs = set()
 	killfuncs = set()
@@ -308,9 +297,6 @@ def main():
 	while len(killfuncs) > 0:
 		wait_for_termination(cond, killfuncs)
 
-	if journalthread is not None:
-		journalthread.terminate()
-
 	# See the service mode comments in xfs_scrub.c for why we do this.
 	if 'SERVICE_MODE' in os.environ:
 		time.sleep(2)

[PATCH 3/6] xfs_scrub_all: support metadata+media scans of all filesystems

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add the necessary systemd services and control bits so that
xfs_scrub_all can kick off a metadata+media scan of a filesystem.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 man/man8/xfs_scrub_all.8               |    5 +-
 scrub/Makefile                         |    4 +
 scrub/xfs_scrub_all.in                 |   23 +++++--
 scrub/xfs_scrub_fail.in                |   13 +++-
 scrub/xfs_scrub_fail@.service.in       |    2 -
 scrub/xfs_scrub_media@.service.in      |  100 ++++++++++++++++++++++++++++++++
 scrub/xfs_scrub_media_fail@.service.in |   76 ++++++++++++++++++++++++
 7 files changed, 210 insertions(+), 13 deletions(-)
 create mode 100644 scrub/xfs_scrub_media@.service.in
 create mode 100644 scrub/xfs_scrub_media_fail@.service.in


diff --git a/man/man8/xfs_scrub_all.8 b/man/man8/xfs_scrub_all.8
index 74548802eda..86a9b3eced2 100644
--- a/man/man8/xfs_scrub_all.8
+++ b/man/man8/xfs_scrub_all.8
@@ -4,7 +4,7 @@ xfs_scrub_all \- scrub all mounted XFS filesystems
 .SH SYNOPSIS
 .B xfs_scrub_all
 [
-.B \-hV
+.B \-hxV
 ]
 .SH DESCRIPTION
 .B xfs_scrub_all
@@ -21,6 +21,9 @@ the same device simultaneously.
 .B \-h
 Display help.
 .TP
+.B \-x
+Read all file data extents to look for disk errors.
+.TP
 .B \-V
 Prints the version number and exits.
 .SH EXIT CODE
diff --git a/scrub/Makefile b/scrub/Makefile
index 53a83ff8efb..fb909c55eb5 100644
--- a/scrub/Makefile
+++ b/scrub/Makefile
@@ -9,6 +9,7 @@ include $(builddefs)
 SCRUB_PREREQS=$(HAVE_OPENAT)$(HAVE_FSTATAT)$(HAVE_GETFSMAP)
 
 scrub_svcname=xfs_scrub@.service
+scrub_media_svcname=xfs_scrub_media@.service
 
 ifeq ($(SCRUB_PREREQS),yesyesyes)
 LTCOMMAND = xfs_scrub
@@ -22,6 +23,8 @@ INSTALL_SCRUB += install-systemd
 SYSTEMD_SERVICES=\
 	$(scrub_svcname) \
 	xfs_scrub_fail@.service \
+	$(scrub_media_svcname) \
+	xfs_scrub_media_fail@.service \
 	xfs_scrub_all.service \
 	xfs_scrub_all.timer \
 	system-xfs_scrub.slice
@@ -125,6 +128,7 @@ xfs_scrub_all: xfs_scrub_all.in $(builddefs)
 	@echo "    [SED]    $@"
 	$(Q)$(SED) -e "s|@sbindir@|$(PKG_SBIN_DIR)|g" \
 		   -e "s|@scrub_svcname@|$(scrub_svcname)|g" \
+		   -e "s|@scrub_media_svcname@|$(scrub_media_svcname)|g" \
 		   -e "s|@pkg_version@|$(PKG_VERSION)|g" \
 		   -e "s|@scrub_service_args@|$(XFS_SCRUB_SERVICE_ARGS)|g" \
 		   -e "s|@scrub_args@|$(XFS_SCRUB_ARGS)|g" < $< > $@
diff --git a/scrub/xfs_scrub_all.in b/scrub/xfs_scrub_all.in
index fc7a2e637ef..afba0dbe891 100644
--- a/scrub/xfs_scrub_all.in
+++ b/scrub/xfs_scrub_all.in
@@ -19,6 +19,7 @@ from io import TextIOWrapper
 
 retcode = 0
 terminate = False
+scrub_media = False
 
 def DEVNULL():
 	'''Return /dev/null in subprocess writable format.'''
@@ -88,11 +89,15 @@ def run_killable(cmd, stdout, killfuncs):
 # systemd doesn't like unit instance names with slashes in them, so it
 # replaces them with dashes when it invokes the service.  Filesystem paths
 # need a special --path argument so that dashes do not get mangled.
-def path_to_serviceunit(path):
+def path_to_serviceunit(path, scrub_media):
 	'''Convert a pathname into a systemd service unit name.'''
 
-	cmd = ['systemd-escape', '--template', '@scrub_svcname@',
-	       '--path', path]
+	if scrub_media:
+		svcname = '@scrub_media_svcname@'
+	else:
+		svcname = '@scrub_svcname@'
+	cmd = ['systemd-escape', '--template', svcname, '--path', path]
+
 	try:
 		proc = subprocess.Popen(cmd, stdout = subprocess.PIPE)
 		proc.wait()
@@ -153,7 +158,7 @@ def systemctl_start(unitname, killfuncs):
 
 def run_scrub(mnt, cond, running_devs, mntdevs, killfuncs):
 	'''Run a scrub process.'''
-	global retcode, terminate
+	global retcode, terminate, scrub_media
 
 	print("Scrubbing %s..." % mnt)
 	sys.stdout.flush()
@@ -164,7 +169,7 @@ def run_scrub(mnt, cond, running_devs, mntdevs, killfuncs):
 
 		# Run per-mount systemd xfs_scrub service only if we ourselves
 		# are running as a systemd service.
-		unitname = path_to_serviceunit(path)
+		unitname = path_to_serviceunit(path, scrub_media)
 		if unitname is not None and 'SERVICE_MODE' in os.environ:
 			ret = systemctl_start(unitname, killfuncs)
 			if ret == 0 or ret == 1:
@@ -183,6 +188,8 @@ def run_scrub(mnt, cond, running_devs, mntdevs, killfuncs):
 		if 'SERVICE_MODE' in os.environ:
 			cmd += '@scrub_service_args@'.split()
 		cmd += '@scrub_args@'.split()
+		if scrub_media:
+			cmd += '-x'
 		cmd += [mnt]
 		ret = run_killable(cmd, None, killfuncs)
 		if ret >= 0:
@@ -247,18 +254,22 @@ def main():
 		a = (mnt, cond, running_devs, devs, killfuncs)
 		thr = threading.Thread(target = run_scrub, args = a)
 		thr.start()
-	global retcode, terminate
+	global retcode, terminate, scrub_media
 
 	parser = argparse.ArgumentParser( \
 			description = "Scrub all mounted XFS filesystems.")
 	parser.add_argument("-V", help = "Report version and exit.", \
 			action = "store_true")
+	parser.add_argument("-x", help = "Scrub file data after filesystem metadata.", \
+			action = "store_true")
 	args = parser.parse_args()
 
 	if args.V:
 		print("xfs_scrub_all version @pkg_version@")
 		sys.exit(0)
 
+	scrub_media = args.x
+
 	fs = find_mounts()
 
 	# Schedule scrub jobs...
diff --git a/scrub/xfs_scrub_fail.in b/scrub/xfs_scrub_fail.in
index 5dffb541798..ff5f20b45d8 100755
--- a/scrub/xfs_scrub_fail.in
+++ b/scrub/xfs_scrub_fail.in
@@ -9,8 +9,11 @@
 
 recipient="$1"
 test -z "${recipient}" && exit 0
-mntpoint="$2"
+service="$2"
+test -z "${service}" && exit 0
+mntpoint="$3"
 test -z "${mntpoint}" && exit 0
+
 hostname="$(hostname -f 2>/dev/null)"
 test -z "${hostname}" && hostname="${HOSTNAME}"
 
@@ -21,16 +24,16 @@ if [ ! -x "${mailer}" ]; then
 fi
 
 # Turn the mountpoint into a properly escaped systemd instance name
-scrub_svc="$(systemd-escape --template "@scrub_svcname@" --path "${mntpoint}")"
+scrub_svc="$(systemd-escape --template "${service}@.service" --path "${mntpoint}")"
 
 (cat << ENDL
 To: $1
-From: <xfs_scrub@${hostname}>
-Subject: xfs_scrub failure on ${mntpoint}
+From: <${service}@${hostname}>
+Subject: ${service} failure on ${mntpoint}
 Content-Transfer-Encoding: 8bit
 Content-Type: text/plain; charset=UTF-8
 
-So sorry, the automatic xfs_scrub of ${mntpoint} on ${hostname} failed.
+So sorry, the automatic ${service} of ${mntpoint} on ${hostname} failed.
 Please do not reply to this mesage.
 
 A log of what happened follows:
diff --git a/scrub/xfs_scrub_fail@.service.in b/scrub/xfs_scrub_fail@.service.in
index 4a40f3bdc85..68edbbc2aef 100644
--- a/scrub/xfs_scrub_fail@.service.in
+++ b/scrub/xfs_scrub_fail@.service.in
@@ -10,7 +10,7 @@ Documentation=man:xfs_scrub(8)
 [Service]
 Type=oneshot
 Environment=EMAIL_ADDR=root
-ExecStart=@pkg_libexec_dir@/xfs_scrub_fail "${EMAIL_ADDR}" %f
+ExecStart=@pkg_libexec_dir@/xfs_scrub_fail "${EMAIL_ADDR}" xfs_scrub %f
 User=mail
 Group=mail
 SupplementaryGroups=systemd-journal
diff --git a/scrub/xfs_scrub_media@.service.in b/scrub/xfs_scrub_media@.service.in
new file mode 100644
index 00000000000..e670748ced5
--- /dev/null
+++ b/scrub/xfs_scrub_media@.service.in
@@ -0,0 +1,100 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2018-2024 Oracle.  All Rights Reserved.
+# Author: Darrick J. Wong <djwong@kernel.org>
+
+[Unit]
+Description=Online XFS Metadata and Media Check for %f
+OnFailure=xfs_scrub_media_fail@%i.service
+Documentation=man:xfs_scrub(8)
+
+# Explicitly require the capabilities that this program needs
+ConditionCapability=CAP_SYS_ADMIN
+ConditionCapability=CAP_FOWNER
+ConditionCapability=CAP_DAC_OVERRIDE
+ConditionCapability=CAP_DAC_READ_SEARCH
+ConditionCapability=CAP_SYS_RAWIO
+
+# Must be a mountpoint
+ConditionPathIsMountPoint=%f
+RequiresMountsFor=%f
+
+[Service]
+Type=oneshot
+Environment=SERVICE_MODE=1
+ExecStart=@sbindir@/xfs_scrub @scrub_service_args@ @scrub_args@ -M /tmp/scrub/ -x %f
+SyslogIdentifier=%N
+
+# Run scrub with minimal CPU and IO priority so that nothing else will starve.
+IOSchedulingClass=idle
+CPUSchedulingPolicy=idle
+CPUAccounting=true
+Nice=19
+
+# Create the service underneath the scrub background service slice so that we
+# can control resource usage.
+Slice=system-xfs_scrub.slice
+
+# No realtime CPU scheduling
+RestrictRealtime=true
+
+# Dynamically create a user that isn't root
+DynamicUser=true
+
+# Make the entire filesystem readonly and /home inaccessible, then bind mount
+# the filesystem we're supposed to be checking into our private /tmp dir.
+# 'norbind' means that we don't bind anything under that original mount.
+ProtectSystem=strict
+ProtectHome=yes
+PrivateTmp=true
+BindPaths=%f:/tmp/scrub:norbind
+
+# Don't let scrub complain about paths in /etc/projects that have been hidden
+# by our sandboxing.  scrub doesn't care about project ids anyway.
+InaccessiblePaths=-/etc/projects
+
+# No network access
+PrivateNetwork=true
+ProtectHostname=true
+RestrictAddressFamilies=none
+IPAddressDeny=any
+
+# Don't let the program mess with the kernel configuration at all
+ProtectKernelLogs=true
+ProtectKernelModules=true
+ProtectKernelTunables=true
+ProtectControlGroups=true
+ProtectProc=invisible
+RestrictNamespaces=true
+
+# Hide everything in /proc, even /proc/mounts
+ProcSubset=pid
+
+# Only allow the default personality Linux
+LockPersonality=true
+
+# No writable memory pages
+MemoryDenyWriteExecute=true
+
+# Don't let our mounts leak out to the host
+PrivateMounts=true
+
+# Restrict system calls to the native arch and only enough to get things going
+SystemCallArchitectures=native
+SystemCallFilter=@system-service
+SystemCallFilter=~@privileged
+SystemCallFilter=~@resources
+SystemCallFilter=~@mount
+
+# xfs_scrub needs these privileges to run, and no others
+CapabilityBoundingSet=CAP_SYS_ADMIN CAP_FOWNER CAP_DAC_OVERRIDE CAP_DAC_READ_SEARCH CAP_SYS_RAWIO
+AmbientCapabilities=CAP_SYS_ADMIN CAP_FOWNER CAP_DAC_OVERRIDE CAP_DAC_READ_SEARCH CAP_SYS_RAWIO
+NoNewPrivileges=true
+
+# xfs_scrub doesn't create files
+UMask=7777
+
+# No access to hardware /dev files except for block devices
+ProtectClock=true
+DevicePolicy=closed
+DeviceAllow=block-*
diff --git a/scrub/xfs_scrub_media_fail@.service.in b/scrub/xfs_scrub_media_fail@.service.in
new file mode 100644
index 00000000000..97c0e090721
--- /dev/null
+++ b/scrub/xfs_scrub_media_fail@.service.in
@@ -0,0 +1,76 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2018-2024 Oracle.  All Rights Reserved.
+# Author: Darrick J. Wong <djwong@kernel.org>
+
+[Unit]
+Description=Online XFS Metadata and Media Check Failure Reporting for %f
+Documentation=man:xfs_scrub(8)
+
+[Service]
+Type=oneshot
+Environment=EMAIL_ADDR=root
+ExecStart=@pkg_libexec_dir@/xfs_scrub_fail "${EMAIL_ADDR}" xfs_scrub_media %f
+User=mail
+Group=mail
+SupplementaryGroups=systemd-journal
+
+# Create the service underneath the scrub background service slice so that we
+# can control resource usage.
+Slice=system-xfs_scrub.slice
+
+# No realtime scheduling
+RestrictRealtime=true
+
+# Make the entire filesystem readonly and /home inaccessible, then bind mount
+# the filesystem we're supposed to be checking into our private /tmp dir.
+ProtectSystem=full
+ProtectHome=yes
+PrivateTmp=true
+RestrictSUIDSGID=true
+
+# Emailing reports requires network access, but not the ability to change the
+# hostname.
+ProtectHostname=true
+
+# Don't let the program mess with the kernel configuration at all
+ProtectKernelLogs=true
+ProtectKernelModules=true
+ProtectKernelTunables=true
+ProtectControlGroups=true
+ProtectProc=invisible
+RestrictNamespaces=true
+
+# Can't hide /proc because journalctl needs it to find various pieces of log
+# information
+#ProcSubset=pid
+
+# Only allow the default personality Linux
+LockPersonality=true
+
+# No writable memory pages
+MemoryDenyWriteExecute=true
+
+# Don't let our mounts leak out to the host
+PrivateMounts=true
+
+# Restrict system calls to the native arch and only enough to get things going
+SystemCallArchitectures=native
+SystemCallFilter=@system-service
+SystemCallFilter=~@privileged
+SystemCallFilter=~@resources
+SystemCallFilter=~@mount
+
+# xfs_scrub needs these privileges to run, and no others
+CapabilityBoundingSet=
+NoNewPrivileges=true
+
+# Failure reporting shouldn't create world-readable files
+UMask=0077
+
+# Clean up any IPC objects when this unit stops
+RemoveIPC=true
+
+# No access to hardware device files
+PrivateDevices=true
+ProtectClock=true

[PATCH 4/6] xfs_scrub_all: enable periodic file data scrubs automatically

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Enhance xfs_scrub_all with the ability to initiate a file data scrub
periodically.  The user must specify the period, and they may optionally
specify the path to a file that will record the last time the file data
was scrubbed.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 debian/rules                   |    3 +-
 include/builddefs.in           |    3 ++
 man/man8/Makefile              |    7 +++-
 man/man8/xfs_scrub_all.8.in    |   15 ++++++++
 scrub/Makefile                 |    3 ++
 scrub/xfs_scrub_all.in         |   76 +++++++++++++++++++++++++++++++++++++++-
 scrub/xfs_scrub_all.service.in |    6 ++-
 7 files changed, 108 insertions(+), 5 deletions(-)
 rename man/man8/{xfs_scrub_all.8 => xfs_scrub_all.8.in} (63%)


diff --git a/debian/rules b/debian/rules
index 57baad625c5..97fbbbfa1ab 100755
--- a/debian/rules
+++ b/debian/rules
@@ -34,7 +34,8 @@ configure_options = \
 	--disable-ubsan \
 	--disable-addrsan \
 	--disable-threadsan \
-	--enable-lto
+	--enable-lto \
+	--localstatedir=/var
 
 options = export DEBUG=-DNDEBUG DISTRIBUTION=debian \
 	  INSTALL_USER=root INSTALL_GROUP=root \
diff --git a/include/builddefs.in b/include/builddefs.in
index f5138b5098f..daac1b5d18a 100644
--- a/include/builddefs.in
+++ b/include/builddefs.in
@@ -59,6 +59,9 @@ PKG_DOC_DIR	= @datadir@/doc/@pkg_name@
 PKG_LOCALE_DIR	= @datadir@/locale
 PKG_DATA_DIR	= @datadir@/@pkg_name@
 MKFS_CFG_DIR	= @datadir@/@pkg_name@/mkfs
+PKG_STATE_DIR	= @localstatedir@/lib/@pkg_name@
+
+XFS_SCRUB_ALL_AUTO_MEDIA_SCAN_STAMP=$(PKG_STATE_DIR)/xfs_scrub_all_media.stamp
 
 CC		= @cc@
 BUILD_CC	= @BUILD_CC@
diff --git a/man/man8/Makefile b/man/man8/Makefile
index 272e45aebc2..5be76ab727a 100644
--- a/man/man8/Makefile
+++ b/man/man8/Makefile
@@ -11,11 +11,12 @@ ifneq ("$(ENABLE_SCRUB)","yes")
   MAN_PAGES = $(filter-out xfs_scrub%,$(shell echo *.$(MAN_SECTION)))
 else
   MAN_PAGES = $(shell echo *.$(MAN_SECTION))
+  MAN_PAGES += xfs_scrub_all.8
 endif
 MAN_PAGES	+= mkfs.xfs.8
 MAN_DEST	= $(PKG_MAN_DIR)/man$(MAN_SECTION)
 LSRCFILES	= $(MAN_PAGES)
-DIRT		= mkfs.xfs.8
+DIRT		= mkfs.xfs.8 xfs_scrub_all.8
 
 default : $(MAN_PAGES)
 
@@ -29,4 +30,8 @@ mkfs.xfs.8: mkfs.xfs.8.in
 	@echo "    [SED]    $@"
 	$(Q)$(SED) -e 's|@mkfs_cfg_dir@|$(MKFS_CFG_DIR)|g' < $^ > $@
 
+xfs_scrub_all.8: xfs_scrub_all.8.in
+	@echo "    [SED]    $@"
+	$(Q)$(SED) -e 's|@stampfile@|$(XFS_SCRUB_ALL_AUTO_MEDIA_SCAN_STAMP)|g' < $^ > $@
+
 install-dev :
diff --git a/man/man8/xfs_scrub_all.8 b/man/man8/xfs_scrub_all.8.in
similarity index 63%
rename from man/man8/xfs_scrub_all.8
rename to man/man8/xfs_scrub_all.8.in
index 86a9b3eced2..0aa87e23716 100644
--- a/man/man8/xfs_scrub_all.8
+++ b/man/man8/xfs_scrub_all.8.in
@@ -18,6 +18,21 @@ operations can be run in parallel so long as no two scrubbers access
 the same device simultaneously.
 .SH OPTIONS
 .TP
+.B \--auto-media-scan-interval
+Automatically enable the file data scan (i.e. the
+.B -x
+flag) if it has not been run in the specified interval.
+The interval must be a floating point number with an optional unit suffix.
+Supported unit suffixes are
+.IR y ", " q ", " mo ", " w ", " d ", " h ", " m ", and " s
+for years, 90-day quarters, 30-day months, weeks, days, hours, minutes, and
+seconds, respectively.
+If no units are specified, the default is seconds.
+.TP
+.B \--auto-media-scan-stamp
+Path to a file that will record the last time the media scan was run.
+Defaults to @stampfile@.
+.TP
 .B \-h
 Display help.
 .TP
diff --git a/scrub/Makefile b/scrub/Makefile
index fb909c55eb5..4c7bbb30d20 100644
--- a/scrub/Makefile
+++ b/scrub/Makefile
@@ -130,6 +130,7 @@ xfs_scrub_all: xfs_scrub_all.in $(builddefs)
 		   -e "s|@scrub_svcname@|$(scrub_svcname)|g" \
 		   -e "s|@scrub_media_svcname@|$(scrub_media_svcname)|g" \
 		   -e "s|@pkg_version@|$(PKG_VERSION)|g" \
+		   -e "s|@stampfile@|$(XFS_SCRUB_ALL_AUTO_MEDIA_SCAN_STAMP)|g" \
 		   -e "s|@scrub_service_args@|$(XFS_SCRUB_SERVICE_ARGS)|g" \
 		   -e "s|@scrub_args@|$(XFS_SCRUB_ARGS)|g" < $< > $@
 	$(Q)chmod a+x $@
@@ -153,6 +154,7 @@ install: $(INSTALL_SCRUB)
 		   -e "s|@scrub_service_args@|$(XFS_SCRUB_SERVICE_ARGS)|g" \
 		   -e "s|@scrub_args@|$(XFS_SCRUB_ARGS)|g" \
 		   -e "s|@pkg_libexec_dir@|$(PKG_LIBEXEC_DIR)|g" \
+		   -e "s|@pkg_state_dir@|$(PKG_STATE_DIR)|g" \
 		   < $< > $@
 
 %.cron: %.cron.in $(builddefs)
@@ -173,6 +175,7 @@ install-scrub: default
 	$(INSTALL) -m 755 -d $(PKG_SBIN_DIR)
 	$(LTINSTALL) -m 755 $(LTCOMMAND) $(PKG_SBIN_DIR)
 	$(INSTALL) -m 755 $(XFS_SCRUB_ALL_PROG) $(PKG_SBIN_DIR)
+	$(INSTALL) -m 755 -d $(PKG_STATE_DIR)
 
 install-udev: $(UDEV_RULES)
 	$(INSTALL) -m 755 -d $(UDEV_RULE_DIR)
diff --git a/scrub/xfs_scrub_all.in b/scrub/xfs_scrub_all.in
index afba0dbe891..9d5cbd2a648 100644
--- a/scrub/xfs_scrub_all.in
+++ b/scrub/xfs_scrub_all.in
@@ -16,6 +16,10 @@ import os
 import argparse
 import signal
 from io import TextIOWrapper
+from pathlib import Path
+from datetime import timedelta
+from datetime import datetime
+from datetime import timezone
 
 retcode = 0
 terminate = False
@@ -248,6 +252,65 @@ def wait_for_termination(cond, killfuncs):
 		fn()
 	return True
 
+def scan_interval(string):
+	'''Convert a textual scan interval argument into a time delta.'''
+
+	if string.endswith('y'):
+		year = timedelta(seconds = 31556952)
+		return year * float(string[:-1])
+	if string.endswith('q'):
+		return timedelta(days = 90 * float(string[:-1]))
+	if string.endswith('mo'):
+		return timedelta(days = 30 * float(string[:-2]))
+	if string.endswith('w'):
+		return timedelta(weeks = float(string[:-1]))
+	if string.endswith('d'):
+		return timedelta(days = float(string[:-1]))
+	if string.endswith('h'):
+		return timedelta(hours = float(string[:-1]))
+	if string.endswith('m'):
+		return timedelta(minutes = float(string[:-1]))
+	if string.endswith('s'):
+		return timedelta(seconds = float(string[:-1]))
+	return timedelta(seconds = int(string))
+
+def utcnow():
+	'''Create a representation of the time right now, in UTC.'''
+
+	dt = datetime.utcnow()
+	return dt.replace(tzinfo = timezone.utc)
+
+def enable_automatic_media_scan(args):
+	'''Decide if we enable media scanning automatically.'''
+	already_enabled = args.x
+
+	try:
+		interval = scan_interval(args.auto_media_scan_interval)
+	except Exception as e:
+		raise Exception('%s: Invalid media scan interval.' % \
+				args.auto_media_scan_interval)
+
+	p = Path(args.auto_media_scan_stamp)
+	if already_enabled:
+		res = True
+	else:
+		try:
+			last_run = p.stat().st_mtime
+			now = utcnow().timestamp()
+			res = last_run + interval.total_seconds() < now
+		except FileNotFoundError:
+			res = True
+
+	if res:
+		# Truncate the stamp file to update its mtime
+		with p.open('w') as f:
+			pass
+		if not already_enabled:
+			print('Automatically enabling file data scrub.')
+			sys.stdout.flush()
+
+	return res
+
 def main():
 	'''Find mounts, schedule scrub runs.'''
 	def thr(mnt, devs):
@@ -262,13 +325,24 @@ def main():
 			action = "store_true")
 	parser.add_argument("-x", help = "Scrub file data after filesystem metadata.", \
 			action = "store_true")
+	parser.add_argument("--auto-media-scan-interval", help = "Automatically scrub file data at this interval.", \
+			default = None)
+	parser.add_argument("--auto-media-scan-stamp", help = "Stamp file for automatic file data scrub.", \
+			default = '@stampfile@')
 	args = parser.parse_args()
 
 	if args.V:
 		print("xfs_scrub_all version @pkg_version@")
 		sys.exit(0)
 
-	scrub_media = args.x
+	if args.auto_media_scan_interval is not None:
+		try:
+			scrub_media = enable_automatic_media_scan(args)
+		except Exception as e:
+			print(e)
+			sys.exit(16)
+	else:
+		scrub_media = args.x
 
 	fs = find_mounts()
 
diff --git a/scrub/xfs_scrub_all.service.in b/scrub/xfs_scrub_all.service.in
index f746f7b69f6..2042c9b987d 100644
--- a/scrub/xfs_scrub_all.service.in
+++ b/scrub/xfs_scrub_all.service.in
@@ -34,11 +34,13 @@ CapabilityBoundingSet=
 NoNewPrivileges=true
 RestrictSUIDSGID=true
 
-# Make the entire filesystem readonly.  We don't want to hide anything because
-# we need to find all mounted XFS filesystems in the host.
+# Make the entire filesystem readonly except for the media scan stamp file
+# directory.  We don't want to hide anything because we need to find all
+# mounted XFS filesystems in the host.
 ProtectSystem=strict
 ProtectHome=read-only
 PrivateTmp=false
+BindPaths=@pkg_state_dir@
 
 # No network access except to the systemd control socket
 PrivateNetwork=true

[PATCH 5/6] xfs_scrub_all: trigger automatic media scans once per month

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Teach the xfs_scrub_all background service to trigger an automatic scan
of all file data once per month.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/Makefile                 |    8 +++++++-
 scrub/xfs_scrub_all.cron.in    |    2 +-
 scrub/xfs_scrub_all.service.in |    2 +-
 3 files changed, 9 insertions(+), 3 deletions(-)


diff --git a/scrub/Makefile b/scrub/Makefile
index 4c7bbb30d20..7bd3a355478 100644
--- a/scrub/Makefile
+++ b/scrub/Makefile
@@ -120,6 +120,9 @@ ifeq ($(HAVE_HDIO_GETGEO),yes)
 LCFLAGS += -DHAVE_HDIO_GETGEO
 endif
 
+# Automatically trigger a media scan once per month
+XFS_SCRUB_ALL_AUTO_MEDIA_SCAN_INTERVAL=1mo
+
 LDIRT = $(XFS_SCRUB_ALL_PROG) $(XFS_SCRUB_FAIL_PROG) *.service *.cron
 
 default: depend $(LTCOMMAND) $(XFS_SCRUB_ALL_PROG) $(XFS_SCRUB_FAIL_PROG) $(OPTIONAL_TARGETS)
@@ -155,11 +158,14 @@ install: $(INSTALL_SCRUB)
 		   -e "s|@scrub_args@|$(XFS_SCRUB_ARGS)|g" \
 		   -e "s|@pkg_libexec_dir@|$(PKG_LIBEXEC_DIR)|g" \
 		   -e "s|@pkg_state_dir@|$(PKG_STATE_DIR)|g" \
+		   -e "s|@media_scan_interval@|$(XFS_SCRUB_ALL_AUTO_MEDIA_SCAN_INTERVAL)|g" \
 		   < $< > $@
 
 %.cron: %.cron.in $(builddefs)
 	@echo "    [SED]    $@"
-	$(Q)$(SED) -e "s|@sbindir@|$(PKG_SBIN_DIR)|g" < $< > $@
+	$(Q)$(SED) -e "s|@sbindir@|$(PKG_SBIN_DIR)|g" \
+		   -e "s|@media_scan_interval@|$(XFS_SCRUB_ALL_AUTO_MEDIA_SCAN_INTERVAL)|g" \
+		   < $< > $@
 
 install-systemd: default $(SYSTEMD_SERVICES)
 	$(INSTALL) -m 755 -d $(SYSTEMD_SYSTEM_UNIT_DIR)
diff --git a/scrub/xfs_scrub_all.cron.in b/scrub/xfs_scrub_all.cron.in
index c4d36958e76..650e0ca92b8 100644
--- a/scrub/xfs_scrub_all.cron.in
+++ b/scrub/xfs_scrub_all.cron.in
@@ -3,4 +3,4 @@
 # Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
 # Author: Darrick J. Wong <djwong@kernel.org>
 #
-10 3 * * 0 root test -e /run/systemd/system || @sbindir@/xfs_scrub_all
+10 3 * * 0 root test -e /run/systemd/system || @sbindir@/xfs_scrub_all --auto-media-scan-interval @media_scan_interval@
diff --git a/scrub/xfs_scrub_all.service.in b/scrub/xfs_scrub_all.service.in
index 2042c9b987d..7cfe3a1bc42 100644
--- a/scrub/xfs_scrub_all.service.in
+++ b/scrub/xfs_scrub_all.service.in
@@ -12,7 +12,7 @@ After=paths.target multi-user.target network.target network-online.target system
 [Service]
 Type=oneshot
 Environment=SERVICE_MODE=1
-ExecStart=@sbindir@/xfs_scrub_all
+ExecStart=@sbindir@/xfs_scrub_all --auto-media-scan-interval @media_scan_interval@
 SyslogIdentifier=xfs_scrub_all
 
 # Create the service underneath the scrub background service slice so that we

[PATCH 6/6] xfs_scrub_all: failure reporting for the xfs_scrub_all job

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Create a failure reporting service for when xfs_scrub_all fails.  This
shouldn't happen often, but let's report anyways.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/Makefile                      |    1 
 scrub/xfs_scrub_all.service.in      |    1 
 scrub/xfs_scrub_all_fail.service.in |   71 +++++++++++++++++++++++++++++++++++
 scrub/xfs_scrub_fail.in             |   35 ++++++++++++++---
 4 files changed, 101 insertions(+), 7 deletions(-)
 create mode 100644 scrub/xfs_scrub_all_fail.service.in


diff --git a/scrub/Makefile b/scrub/Makefile
index 7bd3a355478..7e14d82ad66 100644
--- a/scrub/Makefile
+++ b/scrub/Makefile
@@ -26,6 +26,7 @@ SYSTEMD_SERVICES=\
 	$(scrub_media_svcname) \
 	xfs_scrub_media_fail@.service \
 	xfs_scrub_all.service \
+	xfs_scrub_all_fail.service \
 	xfs_scrub_all.timer \
 	system-xfs_scrub.slice
 OPTIONAL_TARGETS += $(SYSTEMD_SERVICES)
diff --git a/scrub/xfs_scrub_all.service.in b/scrub/xfs_scrub_all.service.in
index 7cfe3a1bc42..2165494e64a 100644
--- a/scrub/xfs_scrub_all.service.in
+++ b/scrub/xfs_scrub_all.service.in
@@ -5,6 +5,7 @@
 
 [Unit]
 Description=Online XFS Metadata Check for All Filesystems
+OnFailure=xfs_scrub_all_fail.service
 ConditionACPower=true
 Documentation=man:xfs_scrub_all(8)
 After=paths.target multi-user.target network.target network-online.target systemd-networkd.service NetworkManager.service connman.service
diff --git a/scrub/xfs_scrub_all_fail.service.in b/scrub/xfs_scrub_all_fail.service.in
new file mode 100644
index 00000000000..53479db8477
--- /dev/null
+++ b/scrub/xfs_scrub_all_fail.service.in
@@ -0,0 +1,71 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2018-2024 Oracle.  All Rights Reserved.
+# Author: Darrick J. Wong <djwong@kernel.org>
+
+[Unit]
+Description=Online XFS Metadata Check for All Filesystems Failure Reporting
+Documentation=man:xfs_scrub_all(8)
+
+[Service]
+Type=oneshot
+Environment=EMAIL_ADDR=root
+ExecStart=@pkg_libexec_dir@/xfs_scrub_fail "${EMAIL_ADDR}" xfs_scrub_all
+User=mail
+Group=mail
+SupplementaryGroups=systemd-journal
+
+# No realtime scheduling
+RestrictRealtime=true
+
+# Make the entire filesystem readonly and /home inaccessible.
+ProtectSystem=full
+ProtectHome=yes
+PrivateTmp=true
+RestrictSUIDSGID=true
+
+# Emailing reports requires network access, but not the ability to change the
+# hostname.
+ProtectHostname=true
+
+# Don't let the program mess with the kernel configuration at all
+ProtectKernelLogs=true
+ProtectKernelModules=true
+ProtectKernelTunables=true
+ProtectControlGroups=true
+ProtectProc=invisible
+RestrictNamespaces=true
+
+# Can't hide /proc because journalctl needs it to find various pieces of log
+# information
+#ProcSubset=pid
+
+# Only allow the default personality Linux
+LockPersonality=true
+
+# No writable memory pages
+MemoryDenyWriteExecute=true
+
+# Don't let our mounts leak out to the host
+PrivateMounts=true
+
+# Restrict system calls to the native arch and only enough to get things going
+SystemCallArchitectures=native
+SystemCallFilter=@system-service
+SystemCallFilter=~@privileged
+SystemCallFilter=~@resources
+SystemCallFilter=~@mount
+
+# xfs_scrub needs these privileges to run, and no others
+CapabilityBoundingSet=
+NoNewPrivileges=true
+
+# Failure reporting shouldn't create world-readable files
+UMask=0077
+
+# Clean up any IPC objects when this unit stops
+RemoveIPC=true
+
+# No access to hardware device files
+PrivateDevices=true
+ProtectClock=true
diff --git a/scrub/xfs_scrub_fail.in b/scrub/xfs_scrub_fail.in
index ff5f20b45d8..5665f83f325 100755
--- a/scrub/xfs_scrub_fail.in
+++ b/scrub/xfs_scrub_fail.in
@@ -5,14 +5,13 @@
 # Copyright (C) 2018-2024 Oracle.  All Rights Reserved.
 # Author: Darrick J. Wong <djwong@kernel.org>
 
-# Email logs of failed xfs_scrub unit runs
+# Email logs of failed xfs_scrub and xfs_scrub_all unit runs
 
 recipient="$1"
 test -z "${recipient}" && exit 0
 service="$2"
 test -z "${service}" && exit 0
 mntpoint="$3"
-test -z "${mntpoint}" && exit 0
 
 hostname="$(hostname -f 2>/dev/null)"
 test -z "${hostname}" && hostname="${HOSTNAME}"
@@ -23,11 +22,13 @@ if [ ! -x "${mailer}" ]; then
 	exit 1
 fi
 
-# Turn the mountpoint into a properly escaped systemd instance name
-scrub_svc="$(systemd-escape --template "${service}@.service" --path "${mntpoint}")"
+fail_mail_mntpoint() {
+	local scrub_svc
 
-(cat << ENDL
-To: $1
+	# Turn the mountpoint into a properly escaped systemd instance name
+	scrub_svc="$(systemd-escape --template "${service}@.service" --path "${mntpoint}")"
+	cat << ENDL
+To: ${recipient}
 From: <${service}@${hostname}>
 Subject: ${service} failure on ${mntpoint}
 Content-Transfer-Encoding: 8bit
@@ -38,5 +39,25 @@ Please do not reply to this mesage.
 
 A log of what happened follows:
 ENDL
-systemctl status --full --lines 4294967295 "${scrub_svc}") | "${mailer}" -t -i
+	systemctl status --full --lines 4294967295 "${scrub_svc}"
+}
+
+fail_mail() {
+	cat << ENDL
+To: ${recipient}
+From: <${service}@${hostname}>
+Subject: ${service} failure
+
+So sorry, the automatic ${service} on ${hostname} failed.
+
+A log of what happened follows:
+ENDL
+	systemctl status --full --lines 4294967295 "${service}"
+}
+
+if [ -n "${mntpoint}" ]; then
+	fail_mail_mntpoint | "${mailer}" -t -i
+else
+	fail_mail | "${mailer}" -t -i
+fi
 exit "${PIPESTATUS[1]}"

[PATCH 1/5] xfs_scrub_all: encapsulate all the subprocess code in an object

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Move all the xfs_scrub subprocess handling code to an object so that we
can contain all the details in a single place.  This also simplifies the
background state management.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/xfs_scrub_all.in |   68 ++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 54 insertions(+), 14 deletions(-)


diff --git a/scrub/xfs_scrub_all.in b/scrub/xfs_scrub_all.in
index 9d5cbd2a648..001c49a7012 100644
--- a/scrub/xfs_scrub_all.in
+++ b/scrub/xfs_scrub_all.in
@@ -78,15 +78,62 @@ def remove_killfunc(killfuncs, fn):
 	except:
 		pass
 
-def run_killable(cmd, stdout, killfuncs):
+class scrub_control(object):
+	'''Control object for xfs_scrub.'''
+	def __init__(self):
+		pass
+
+	def start(self):
+		'''Start scrub and wait for it to complete.  Returns -1 if the
+		service was not started, 0 if it succeeded, or 1 if it
+		failed.'''
+		assert False
+
+	def stop(self):
+		'''Stop scrub.'''
+		assert False
+
+class scrub_subprocess(scrub_control):
+	'''Control object for xfs_scrub subprocesses.'''
+	def __init__(self, mnt, scrub_media):
+		cmd = ['@sbindir@/xfs_scrub']
+		if 'SERVICE_MODE' in os.environ:
+			cmd += '@scrub_service_args@'.split()
+		cmd += '@scrub_args@'.split()
+		if scrub_media:
+			cmd += '-x'
+		cmd += [mnt]
+		self.cmdline = cmd
+		self.proc = None
+
+	def start(self):
+		'''Start xfs_scrub and wait for it to complete.  Returns -1 if
+		the service was not started, 0 if it succeeded, or 1 if it
+		failed.'''
+		try:
+			self.proc = subprocess.Popen(self.cmdline)
+			self.proc.wait()
+		except:
+			return -1
+
+		proc = self.proc
+		self.proc = None
+		return proc.returncode
+
+	def stop(self):
+		'''Stop xfs_scrub.'''
+		if self.proc is not None:
+			self.proc.terminate()
+
+def run_subprocess(mnt, scrub_media, killfuncs):
 	'''Run a killable program.  Returns program retcode or -1 if we can't
 	start it.'''
 	try:
-		proc = subprocess.Popen(cmd, stdout = stdout)
-		killfuncs.add(proc.terminate)
-		proc.wait()
-		remove_killfunc(killfuncs, proc.terminate)
-		return proc.returncode
+		p = scrub_subprocess(mnt, scrub_media)
+		killfuncs.add(p.stop)
+		ret = p.start()
+		remove_killfunc(killfuncs, p.stop)
+		return ret
 	except:
 		return -1
 
@@ -188,14 +235,7 @@ def run_scrub(mnt, cond, running_devs, mntdevs, killfuncs):
 		# Invoke xfs_scrub manually if we're running in the foreground.
 		# We also permit this if we're running as a cronjob where
 		# systemd services are unavailable.
-		cmd = ['@sbindir@/xfs_scrub']
-		if 'SERVICE_MODE' in os.environ:
-			cmd += '@scrub_service_args@'.split()
-		cmd += '@scrub_args@'.split()
-		if scrub_media:
-			cmd += '-x'
-		cmd += [mnt]
-		ret = run_killable(cmd, None, killfuncs)
+		ret = run_subprocess(mnt, scrub_media, killfuncs)
 		if ret >= 0:
 			print("Scrubbing %s done, (err=%d)" % (mnt, ret))
 			sys.stdout.flush()

[PATCH 2/5] xfs_scrub_all: encapsulate all the systemctl code in an object

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Move all the systemd service handling code to an object so that we can
contain all the insanity^Wdetails in a single place.  This also makes
the killfuncs handling similar to starting background processes.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/xfs_scrub_all.in |  113 ++++++++++++++++++++++++++----------------------
 1 file changed, 61 insertions(+), 52 deletions(-)


diff --git a/scrub/xfs_scrub_all.in b/scrub/xfs_scrub_all.in
index 001c49a7012..09fedff9d96 100644
--- a/scrub/xfs_scrub_all.in
+++ b/scrub/xfs_scrub_all.in
@@ -149,63 +149,73 @@ def path_to_serviceunit(path, scrub_media):
 		svcname = '@scrub_svcname@'
 	cmd = ['systemd-escape', '--template', svcname, '--path', path]
 
-	try:
-		proc = subprocess.Popen(cmd, stdout = subprocess.PIPE)
-		proc.wait()
-		for line in proc.stdout:
-			return line.decode(sys.stdout.encoding).strip()
-	except:
-		return None
+	proc = subprocess.Popen(cmd, stdout = subprocess.PIPE)
+	proc.wait()
+	for line in proc.stdout:
+		return line.decode(sys.stdout.encoding).strip()
 
-def systemctl_stop(unitname):
-	'''Stop a systemd unit.'''
-	cmd = ['systemctl', 'stop', unitname]
-	x = subprocess.Popen(cmd)
-	x.wait()
+class scrub_service(scrub_control):
+	'''Control object for xfs_scrub systemd service.'''
+	def __init__(self, mnt, scrub_media):
+		self.unitname = path_to_serviceunit(mnt, scrub_media)
 
-def systemctl_start(unitname, killfuncs):
-	'''Start a systemd unit and wait for it to complete.'''
-	stop_fn = None
-	cmd = ['systemctl', 'start', unitname]
-	try:
-		proc = subprocess.Popen(cmd, stdout = DEVNULL())
-		stop_fn = lambda: systemctl_stop(unitname)
-		killfuncs.add(stop_fn)
-		proc.wait()
-		ret = proc.returncode
-	except:
-		if stop_fn is not None:
-			remove_killfunc(killfuncs, stop_fn)
-		return -1
+	def wait(self, interval = 1):
+		'''Wait until the service finishes.'''
 
-	if ret != 1:
-		remove_killfunc(killfuncs, stop_fn)
-		return ret
+		# As of systemd 249, the is-active command returns any of the
+		# following states: active, reloading, inactive, failed,
+		# activating, deactivating, or maintenance.  Apparently these
+		# strings are not localized.
+		while True:
+			try:
+				for l in backtick(['systemctl', 'is-active', self.unitname]):
+					if l == 'failed':
+						return 1
+					if l == 'inactive':
+						return 0
+			except:
+				return -1
 
-	# If systemctl-start returns 1, it's possible that the service failed
-	# or that dbus/systemd restarted and the client program lost its
-	# connection -- according to the systemctl man page, 1 means "unit not
-	# failed".
-	#
-	# Either way, we switch to polling the service status to try to wait
-	# for the service to end.  As of systemd 249, the is-active command
-	# returns any of the following states: active, reloading, inactive,
-	# failed, activating, deactivating, or maintenance.  Apparently these
-	# strings are not localized.
-	while True:
+			time.sleep(interval)
+
+	def start(self):
+		'''Start the service and wait for it to complete.  Returns -1
+		if the service was not started, 0 if it succeeded, or 1 if it
+		failed.'''
+		cmd = ['systemctl', 'start', self.unitname]
 		try:
-			for l in backtick(['systemctl', 'is-active', unitname]):
-				if l == 'failed':
-					remove_killfunc(killfuncs, stop_fn)
-					return 1
-				if l == 'inactive':
-					remove_killfunc(killfuncs, stop_fn)
-					return 0
+			proc = subprocess.Popen(cmd, stdout = DEVNULL())
+			proc.wait()
+			ret = proc.returncode
 		except:
-			remove_killfunc(killfuncs, stop_fn)
 			return -1
 
-		time.sleep(1)
+		if ret != 1:
+			return ret
+
+		# If systemctl-start returns 1, it's possible that the service
+		# failed or that dbus/systemd restarted and the client program
+		# lost its connection -- according to the systemctl man page, 1
+		# means "unit not failed".
+		return self.wait()
+
+	def stop(self):
+		'''Stop the service.'''
+		cmd = ['systemctl', 'stop', self.unitname]
+		x = subprocess.Popen(cmd)
+		x.wait()
+
+def run_service(mnt, scrub_media, killfuncs):
+	'''Run scrub as a service.'''
+	try:
+		svc = scrub_service(mnt, scrub_media)
+	except:
+		return -1
+
+	killfuncs.add(svc.stop)
+	retcode = svc.start()
+	remove_killfunc(killfuncs, svc.stop)
+	return retcode
 
 def run_scrub(mnt, cond, running_devs, mntdevs, killfuncs):
 	'''Run a scrub process.'''
@@ -220,9 +230,8 @@ def run_scrub(mnt, cond, running_devs, mntdevs, killfuncs):
 
 		# Run per-mount systemd xfs_scrub service only if we ourselves
 		# are running as a systemd service.
-		unitname = path_to_serviceunit(path, scrub_media)
-		if unitname is not None and 'SERVICE_MODE' in os.environ:
-			ret = systemctl_start(unitname, killfuncs)
+		if 'SERVICE_MODE' in os.environ:
+			ret = run_service(mnt, scrub_media, killfuncs)
 			if ret == 0 or ret == 1:
 				print("Scrubbing %s done, (err=%d)" % (mnt, ret))
 				sys.stdout.flush()

[PATCH 3/5] xfs_scrub_all: add CLI option for easier debugging

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add a new CLI argument to make it easier to figure out what exactly the
program is doing.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/xfs_scrub_all.in |   25 ++++++++++++++++++++++++-
 1 file changed, 24 insertions(+), 1 deletion(-)


diff --git a/scrub/xfs_scrub_all.in b/scrub/xfs_scrub_all.in
index 09fedff9d96..d5d1d13a255 100644
--- a/scrub/xfs_scrub_all.in
+++ b/scrub/xfs_scrub_all.in
@@ -24,6 +24,7 @@ from datetime import timezone
 retcode = 0
 terminate = False
 scrub_media = False
+debug = False
 
 def DEVNULL():
 	'''Return /dev/null in subprocess writable format.'''
@@ -110,6 +111,11 @@ class scrub_subprocess(scrub_control):
 		'''Start xfs_scrub and wait for it to complete.  Returns -1 if
 		the service was not started, 0 if it succeeded, or 1 if it
 		failed.'''
+		global debug
+
+		if debug:
+			print('run ', ' '.join(self.cmdline))
+
 		try:
 			self.proc = subprocess.Popen(self.cmdline)
 			self.proc.wait()
@@ -122,6 +128,10 @@ class scrub_subprocess(scrub_control):
 
 	def stop(self):
 		'''Stop xfs_scrub.'''
+		global debug
+
+		if debug:
+			print('kill ', ' '.join(self.cmdline))
 		if self.proc is not None:
 			self.proc.terminate()
 
@@ -182,8 +192,12 @@ class scrub_service(scrub_control):
 		'''Start the service and wait for it to complete.  Returns -1
 		if the service was not started, 0 if it succeeded, or 1 if it
 		failed.'''
+		global debug
+
 		cmd = ['systemctl', 'start', self.unitname]
 		try:
+			if debug:
+				print(' '.join(cmd))
 			proc = subprocess.Popen(cmd, stdout = DEVNULL())
 			proc.wait()
 			ret = proc.returncode
@@ -201,7 +215,11 @@ class scrub_service(scrub_control):
 
 	def stop(self):
 		'''Stop the service.'''
+		global debug
+
 		cmd = ['systemctl', 'stop', self.unitname]
+		if debug:
+			print(' '.join(cmd))
 		x = subprocess.Popen(cmd)
 		x.wait()
 
@@ -366,10 +384,12 @@ def main():
 		a = (mnt, cond, running_devs, devs, killfuncs)
 		thr = threading.Thread(target = run_scrub, args = a)
 		thr.start()
-	global retcode, terminate, scrub_media
+	global retcode, terminate, scrub_media, debug
 
 	parser = argparse.ArgumentParser( \
 			description = "Scrub all mounted XFS filesystems.")
+	parser.add_argument("--debug", help = "Enabling debugging messages.", \
+			action = "store_true")
 	parser.add_argument("-V", help = "Report version and exit.", \
 			action = "store_true")
 	parser.add_argument("-x", help = "Scrub file data after filesystem metadata.", \
@@ -384,6 +404,9 @@ def main():
 		print("xfs_scrub_all version @pkg_version@")
 		sys.exit(0)
 
+	if args.debug:
+		debug = True
+
 	if args.auto_media_scan_interval is not None:
 		try:
 			scrub_media = enable_automatic_media_scan(args)

[PATCH 4/5] xfs_scrub_all: convert systemctl calls to dbus

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Convert the systemctl invocations to direct dbus calls, which decouples
us from the CLI in favor of direct API calls.  This spares us from some
of the insanity of divining service state from program outputs.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 debian/control         |    2 +
 scrub/xfs_scrub_all.in |   96 +++++++++++++++++++++++++++++++-----------------
 2 files changed, 63 insertions(+), 35 deletions(-)


diff --git a/debian/control b/debian/control
index 344466de016..31773e53a19 100644
--- a/debian/control
+++ b/debian/control
@@ -8,7 +8,7 @@ Standards-Version: 4.0.0
 Homepage: https://xfs.wiki.kernel.org/
 
 Package: xfsprogs
-Depends: ${shlibs:Depends}, ${misc:Depends}, python3:any
+Depends: ${shlibs:Depends}, ${misc:Depends}, python3-dbus, python3:any
 Provides: fsck-backend
 Suggests: xfsdump, acl, attr, quota
 Breaks: xfsdump (<< 3.0.0)
diff --git a/scrub/xfs_scrub_all.in b/scrub/xfs_scrub_all.in
index d5d1d13a255..a09566efdcd 100644
--- a/scrub/xfs_scrub_all.in
+++ b/scrub/xfs_scrub_all.in
@@ -15,6 +15,7 @@ import sys
 import os
 import argparse
 import signal
+import dbus
 from io import TextIOWrapper
 from pathlib import Path
 from datetime import timedelta
@@ -168,25 +169,57 @@ class scrub_service(scrub_control):
 	'''Control object for xfs_scrub systemd service.'''
 	def __init__(self, mnt, scrub_media):
 		self.unitname = path_to_serviceunit(mnt, scrub_media)
+		self.prop = None
+		self.unit = None
+		self.bind()
+
+	def bind(self):
+		'''Bind to the dbus proxy object for this service.'''
+		sysbus = dbus.SystemBus()
+		systemd1 = sysbus.get_object('org.freedesktop.systemd1',
+					    '/org/freedesktop/systemd1')
+		manager = dbus.Interface(systemd1,
+				'org.freedesktop.systemd1.Manager')
+		path = manager.LoadUnit(self.unitname)
+
+		svc_obj = sysbus.get_object('org.freedesktop.systemd1', path)
+		self.prop = dbus.Interface(svc_obj,
+				'org.freedesktop.DBus.Properties')
+		self.unit = dbus.Interface(svc_obj,
+				'org.freedesktop.systemd1.Unit')
+
+	def state(self):
+		'''Retrieve the active state for a systemd service.  As of
+		systemd 249, this is supposed to be one of the following:
+		"active", "reloading", "inactive", "failed", "activating",
+		or "deactivating".  These strings are not localized.'''
+		global debug
+
+		try:
+			return self.prop.Get('org.freedesktop.systemd1.Unit', 'ActiveState')
+		except Exception as e:
+			if debug:
+				print(e, file = sys.stderr)
+			return 'failed'
 
 	def wait(self, interval = 1):
 		'''Wait until the service finishes.'''
+		global debug
 
-		# As of systemd 249, the is-active command returns any of the
-		# following states: active, reloading, inactive, failed,
-		# activating, deactivating, or maintenance.  Apparently these
-		# strings are not localized.
-		while True:
-			try:
-				for l in backtick(['systemctl', 'is-active', self.unitname]):
-					if l == 'failed':
-						return 1
-					if l == 'inactive':
-						return 0
-			except:
-				return -1
-
+		# Use a poll/sleep loop to wait for the service to finish.
+		# Avoid adding a dependency on python3 glib, which is required
+		# to use an event loop to receive a dbus signal.
+		s = self.state()
+		while s not in ['failed', 'inactive']:
+			if debug:
+				print('waiting %s %s' % (self.unitname, s))
 			time.sleep(interval)
+			s = self.state()
+		if debug:
+			print('waited %s %s' % (self.unitname, s))
+		if s == 'failed':
+			return 1
+		return 0
 
 	def start(self):
 		'''Start the service and wait for it to complete.  Returns -1
@@ -194,34 +227,29 @@ class scrub_service(scrub_control):
 		failed.'''
 		global debug
 
-		cmd = ['systemctl', 'start', self.unitname]
+		if debug:
+			print('starting %s' % self.unitname)
+
 		try:
-			if debug:
-				print(' '.join(cmd))
-			proc = subprocess.Popen(cmd, stdout = DEVNULL())
-			proc.wait()
-			ret = proc.returncode
-		except:
+			self.unit.Start('replace')
+			return self.wait()
+		except Exception as e:
+			print(e, file = sys.stderr)
 			return -1
 
-		if ret != 1:
-			return ret
-
-		# If systemctl-start returns 1, it's possible that the service
-		# failed or that dbus/systemd restarted and the client program
-		# lost its connection -- according to the systemctl man page, 1
-		# means "unit not failed".
-		return self.wait()
-
 	def stop(self):
 		'''Stop the service.'''
 		global debug
 
-		cmd = ['systemctl', 'stop', self.unitname]
 		if debug:
-			print(' '.join(cmd))
-		x = subprocess.Popen(cmd)
-		x.wait()
+			print('stopping %s' % self.unitname)
+
+		try:
+			self.unit.Stop('replace')
+			return self.wait()
+		except Exception as e:
+			print(e, file = sys.stderr)
+			return -1
 
 def run_service(mnt, scrub_media, killfuncs):
 	'''Run scrub as a service.'''

[PATCH 5/5] xfs_scrub_all: implement retry and backoff for dbus calls

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Calls to systemd across dbus are remote procedure calls, which means
that they're subject to transitory connection failures (e.g. systemd
re-exec itself).  We don't want to fail at the *first* sign of what
could be temporary trouble, so implement a limited retry with fibonacci
backoff before we resort to invoking xfs_scrub as a subprocess.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/xfs_scrub_all.in |   43 ++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 40 insertions(+), 3 deletions(-)


diff --git a/scrub/xfs_scrub_all.in b/scrub/xfs_scrub_all.in
index a09566efdcd..71726cdf36d 100644
--- a/scrub/xfs_scrub_all.in
+++ b/scrub/xfs_scrub_all.in
@@ -165,6 +165,22 @@ def path_to_serviceunit(path, scrub_media):
 	for line in proc.stdout:
 		return line.decode(sys.stdout.encoding).strip()
 
+def fibonacci(max_ret):
+	'''Yield fibonacci sequence up to but not including max_ret.'''
+	if max_ret < 1:
+		return
+
+	x = 0
+	y = 1
+	yield 1
+
+	z = x + y
+	while z <= max_ret:
+		yield z
+		x = y
+		y = z
+		z = x + y
+
 class scrub_service(scrub_control):
 	'''Control object for xfs_scrub systemd service.'''
 	def __init__(self, mnt, scrub_media):
@@ -188,6 +204,25 @@ class scrub_service(scrub_control):
 		self.unit = dbus.Interface(svc_obj,
 				'org.freedesktop.systemd1.Unit')
 
+	def __dbusrun(self, lambda_fn):
+		'''Call the lambda function to execute something on dbus.  dbus
+		exceptions result in retries with Fibonacci backoff, and the
+		bindings will be rebuilt every time.'''
+		global debug
+
+		fatal_ex = None
+
+		for i in fibonacci(30):
+			try:
+				return lambda_fn()
+			except dbus.exceptions.DBusException as e:
+				if debug:
+					print(e)
+				fatal_ex = e
+				time.sleep(i)
+				self.bind()
+		raise fatal_ex
+
 	def state(self):
 		'''Retrieve the active state for a systemd service.  As of
 		systemd 249, this is supposed to be one of the following:
@@ -195,8 +230,10 @@ class scrub_service(scrub_control):
 		or "deactivating".  These strings are not localized.'''
 		global debug
 
+		l = lambda: self.prop.Get('org.freedesktop.systemd1.Unit',
+				'ActiveState')
 		try:
-			return self.prop.Get('org.freedesktop.systemd1.Unit', 'ActiveState')
+			return self.__dbusrun(l)
 		except Exception as e:
 			if debug:
 				print(e, file = sys.stderr)
@@ -231,7 +268,7 @@ class scrub_service(scrub_control):
 			print('starting %s' % self.unitname)
 
 		try:
-			self.unit.Start('replace')
+			self.__dbusrun(lambda: self.unit.Start('replace'))
 			return self.wait()
 		except Exception as e:
 			print(e, file = sys.stderr)
@@ -245,7 +282,7 @@ class scrub_service(scrub_control):
 			print('stopping %s' % self.unitname)
 
 		try:
-			self.unit.Stop('replace')
+			self.__dbusrun(lambda: self.unit.Stop('replace'))
 			return self.wait()
 		except Exception as e:
 			print(e, file = sys.stderr)

[PATCH 1/3] xfs_scrub: automatic downgrades to dry-run mode in service mode

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

When service mode is enabled, xfs_scrub is being run within the context
of a systemd service.  The service description language doesn't have any
particularly good constructs for adding in a '-n' argument if the
filesystem is readonly, which means that xfs_scrub is passed a path, and
needs to switch to dry-run mode on its own if the fs is mounted
readonly or the kernel doesn't support repairs.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 scrub/phase1.c |   13 +++++++++++++
 scrub/repair.c |   33 +++++++++++++++++++++++++++++++++
 scrub/repair.h |    2 ++
 3 files changed, 48 insertions(+)


diff --git a/scrub/phase1.c b/scrub/phase1.c
index 516d929d626..095c045915a 100644
--- a/scrub/phase1.c
+++ b/scrub/phase1.c
@@ -216,6 +216,19 @@ _("Kernel metadata scrubbing facility is not available."));
 		return ECANCELED;
 	}
 
+	/*
+	 * Normally, callers are required to pass -n if the provided path is a
+	 * readonly filesystem or the kernel wasn't built with online repair
+	 * enabled.  However, systemd services are not scripts and cannot
+	 * determine either of these conditions programmatically.  Change the
+	 * behavior to dry-run mode if either condition is detected.
+	 */
+	if (repair_want_service_downgrade(ctx)) {
+		str_info(ctx, ctx->mntpoint,
+_("Filesystem cannot be repaired in service mode, downgrading to dry-run mode."));
+		ctx->mode = SCRUB_MODE_DRY_RUN;
+	}
+
 	/* Do we need kernel-assisted metadata repair? */
 	if (ctx->mode != SCRUB_MODE_DRY_RUN && !can_repair(ctx)) {
 		str_error(ctx, ctx->mntpoint,
diff --git a/scrub/repair.c b/scrub/repair.c
index 19f5c9052af..2883f98af4a 100644
--- a/scrub/repair.c
+++ b/scrub/repair.c
@@ -45,6 +45,39 @@ static const unsigned int repair_deps[XFS_SCRUB_TYPE_NR] = {
 };
 #undef DEP
 
+/*
+ * Decide if we want an automatic downgrade to dry-run mode.  This is only
+ * for service mode, where we are fed a path and have to figure out if the fs
+ * is repairable or not.
+ */
+bool
+repair_want_service_downgrade(
+	struct scrub_ctx		*ctx)
+{
+	struct xfs_scrub_metadata	meta = {
+		.sm_type		= XFS_SCRUB_TYPE_PROBE,
+		.sm_flags		= XFS_SCRUB_IFLAG_REPAIR,
+	};
+	int				error;
+
+	if (ctx->mode == SCRUB_MODE_DRY_RUN)
+		return false;
+	if (!is_service)
+		return false;
+	if (debug_tweak_on("XFS_SCRUB_NO_KERNEL"))
+		return false;
+
+	error = -xfrog_scrub_metadata(&ctx->mnt, &meta);
+	switch (error) {
+	case EROFS:
+	case ENOTRECOVERABLE:
+	case EOPNOTSUPP:
+		return true;
+	}
+
+	return false;
+}
+
 /* Repair some metadata. */
 static int
 xfs_repair_metadata(
diff --git a/scrub/repair.h b/scrub/repair.h
index a685e90374c..411a379f6fa 100644
--- a/scrub/repair.h
+++ b/scrub/repair.h
@@ -102,4 +102,6 @@ repair_item_completely(
 	return repair_item(ctx, sri, XRM_FINAL_WARNING | XRM_NOPROGRESS);
 }
 
+bool repair_want_service_downgrade(struct scrub_ctx *ctx);
+
 #endif /* XFS_SCRUB_REPAIR_H_ */

[PATCH 2/3] xfs_scrub: add an optimization-only mode

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Add a "preen" mode in which we only optimize filesystem metadata.
Repairs will result in early exits.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 man/man8/xfs_scrub.8 |    6 +++++-
 scrub/Makefile       |    2 +-
 scrub/phase4.c       |    6 ++++++
 scrub/repair.c       |    4 +++-
 scrub/scrub.c        |    4 ++--
 scrub/xfs_scrub.c    |   21 +++++++++++++++++++--
 scrub/xfs_scrub.h    |    1 +
 7 files changed, 37 insertions(+), 7 deletions(-)


diff --git a/man/man8/xfs_scrub.8 b/man/man8/xfs_scrub.8
index 6154011271e..1fd122f2a24 100644
--- a/man/man8/xfs_scrub.8
+++ b/man/man8/xfs_scrub.8
@@ -4,7 +4,7 @@ xfs_scrub \- check and repair the contents of a mounted XFS filesystem
 .SH SYNOPSIS
 .B xfs_scrub
 [
-.B \-abCeMmnTvx
+.B \-abCeMmnpTvx
 ]
 .I mount-point
 .br
@@ -128,6 +128,10 @@ Treat informational messages as warnings.
 This will result in a nonzero return code, and a higher logging level.
 .RE
 .TP
+.B \-p
+Only optimize filesystem metadata.
+If repairs are required, report them and exit.
+.TP
 .BI \-T
 Print timing and memory usage information for each phase.
 .TP
diff --git a/scrub/Makefile b/scrub/Makefile
index 7e14d82ad66..c0fc927f427 100644
--- a/scrub/Makefile
+++ b/scrub/Makefile
@@ -16,7 +16,7 @@ LTCOMMAND = xfs_scrub
 INSTALL_SCRUB = install-scrub
 XFS_SCRUB_ALL_PROG = xfs_scrub_all
 XFS_SCRUB_FAIL_PROG = xfs_scrub_fail
-XFS_SCRUB_ARGS = -n
+XFS_SCRUB_ARGS = -p
 XFS_SCRUB_SERVICE_ARGS = -b
 ifeq ($(HAVE_SYSTEMD),yes)
 INSTALL_SCRUB += install-systemd
diff --git a/scrub/phase4.c b/scrub/phase4.c
index 451101811c9..88cb53aeac9 100644
--- a/scrub/phase4.c
+++ b/scrub/phase4.c
@@ -240,6 +240,12 @@ phase4_func(
 	    action_list_empty(ctx->file_repair_list))
 		return 0;
 
+	if (ctx->mode == SCRUB_MODE_PREEN && ctx->corruptions_found) {
+		str_info(ctx, ctx->mntpoint,
+ _("Corruptions found; will not optimize.  Re-run without -p.\n"));
+		return 0;
+	}
+
 	/*
 	 * Check the resource usage counters early.  Normally we do this during
 	 * phase 7, but some of the cross-referencing requires fairly accurate
diff --git a/scrub/repair.c b/scrub/repair.c
index 2883f98af4a..0258210722b 100644
--- a/scrub/repair.c
+++ b/scrub/repair.c
@@ -651,7 +651,9 @@ repair_item_class(
 	unsigned int			scrub_type;
 	int				error = 0;
 
-	if (ctx->mode < SCRUB_MODE_REPAIR)
+	if (ctx->mode == SCRUB_MODE_DRY_RUN)
+		return 0;
+	if (ctx->mode == SCRUB_MODE_PREEN && !(repair_mask & SCRUB_ITEM_PREEN))
 		return 0;
 
 	/*
diff --git a/scrub/scrub.c b/scrub/scrub.c
index 2b6b6274e38..1b0609e7418 100644
--- a/scrub/scrub.c
+++ b/scrub/scrub.c
@@ -174,7 +174,7 @@ _("Filesystem is shut down, aborting."));
 	 * repair if desired, otherwise complain.
 	 */
 	if (is_corrupt(&meta) || xref_disagrees(&meta)) {
-		if (ctx->mode < SCRUB_MODE_REPAIR) {
+		if (ctx->mode != SCRUB_MODE_REPAIR) {
 			/* Dry-run mode, so log an error and forget it. */
 			str_corrupt(ctx, descr_render(&dsc),
 _("Repairs are required."));
@@ -192,7 +192,7 @@ _("Repairs are required."));
 	 * otherwise complain.
 	 */
 	if (is_unoptimized(&meta)) {
-		if (ctx->mode != SCRUB_MODE_REPAIR) {
+		if (ctx->mode == SCRUB_MODE_DRY_RUN) {
 			/* Dry-run mode, so log an error and forget it. */
 			if (group != XFROG_SCRUB_GROUP_INODE) {
 				/* AG or FS metadata, always warn. */
diff --git a/scrub/xfs_scrub.c b/scrub/xfs_scrub.c
index 4912333219d..7c73e4d3cca 100644
--- a/scrub/xfs_scrub.c
+++ b/scrub/xfs_scrub.c
@@ -183,6 +183,7 @@ usage(void)
 	fprintf(stderr, _("  -k           Do not FITRIM the free space.\n"));
 	fprintf(stderr, _("  -m path      Path to /etc/mtab.\n"));
 	fprintf(stderr, _("  -n           Dry run.  Do not modify anything.\n"));
+	fprintf(stderr, _("  -p           Only optimize, do not fix corruptions.\n"));
 	fprintf(stderr, _("  -T           Display timing/usage information.\n"));
 	fprintf(stderr, _("  -v           Verbose output.\n"));
 	fprintf(stderr, _("  -V           Print version.\n"));
@@ -463,6 +464,11 @@ run_scrub_phases(
 			sp->descr = _("Repair filesystem.");
 			sp->fn = phase4_func;
 			sp->must_run = true;
+		} else if (sp->fn == REPAIR_DUMMY_FN &&
+			   ctx->mode == SCRUB_MODE_PREEN) {
+			sp->descr = _("Optimize filesystem.");
+			sp->fn = phase4_func;
+			sp->must_run = true;
 		}
 
 		/* Skip certain phases unless they're turned on. */
@@ -601,7 +607,7 @@ report_outcome(
 	if (ctx->scrub_setup_succeeded && actionable_errors > 0) {
 		char		*msg;
 
-		if (ctx->mode == SCRUB_MODE_DRY_RUN)
+		if (ctx->mode != SCRUB_MODE_REPAIR)
 			msg = _("%s: Re-run xfs_scrub without -n.\n");
 		else
 			msg = _("%s: Unmount and run xfs_repair.\n");
@@ -725,7 +731,7 @@ main(
 	pthread_mutex_init(&ctx.lock, NULL);
 	ctx.mode = SCRUB_MODE_REPAIR;
 	ctx.error_action = ERRORS_CONTINUE;
-	while ((c = getopt(argc, argv, "a:bC:de:kM:m:no:TvxV")) != EOF) {
+	while ((c = getopt(argc, argv, "a:bC:de:kM:m:no:pTvxV")) != EOF) {
 		switch (c) {
 		case 'a':
 			ctx.max_errors = cvt_u64(optarg, 10);
@@ -776,11 +782,22 @@ main(
 			mtab = optarg;
 			break;
 		case 'n':
+			if (ctx.mode != SCRUB_MODE_REPAIR) {
+				fprintf(stderr, _("Cannot use -n with -p.\n"));
+				usage();
+			}
 			ctx.mode = SCRUB_MODE_DRY_RUN;
 			break;
 		case 'o':
 			parse_o_opts(&ctx, optarg);
 			break;
+		case 'p':
+			if (ctx.mode != SCRUB_MODE_REPAIR) {
+				fprintf(stderr, _("Cannot use -p with -n.\n"));
+				usage();
+			}
+			ctx.mode = SCRUB_MODE_PREEN;
+			break;
 		case 'T':
 			display_rusage = true;
 			break;
diff --git a/scrub/xfs_scrub.h b/scrub/xfs_scrub.h
index b0aa9fcc67b..4d9a028921b 100644
--- a/scrub/xfs_scrub.h
+++ b/scrub/xfs_scrub.h
@@ -27,6 +27,7 @@ extern bool			info_is_warning;
 
 enum scrub_mode {
 	SCRUB_MODE_DRY_RUN,
+	SCRUB_MODE_PREEN,
 	SCRUB_MODE_REPAIR,
 };
 

[PATCH 3/3] debian: enable xfs_scrub systemd services by default

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Now that we're finished building online fsck, enable the background
services by default.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 debian/rules |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)


diff --git a/debian/rules b/debian/rules
index 97fbbbfa1ab..c040b460c44 100755
--- a/debian/rules
+++ b/debian/rules
@@ -109,7 +109,7 @@ binary-arch: checkroot built
 	dh_compress
 	dh_fixperms
 	dh_makeshlibs
-	dh_installsystemd -p xfsprogs --no-enable --no-start --no-restart-after-upgrade --no-stop-on-upgrade
+	dh_installsystemd -p xfsprogs
 	dh_installdeb
 	dh_shlibdeps
 	dh_gencontrol

[PATCH 1/4] xfs_repair: check free space requirements before allowing upgrades

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Currently, the V5 feature upgrades permitted by xfs_repair do not affect
filesystem space usage, so we haven't needed to verify the geometry.

However, this will change once we start to allow the sysadmin to add new
metadata indexes to existing filesystems.  Add all the infrastructure we
need to ensure that there's enough space for metadata space reservations
and per-AG reservations the next time the filesystem will be mounted.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandan.babu@oracle.com>
[david: Recompute transaction reservation values; Exit with error if upgrade fails]
Signed-off-by: Dave Chinner <david@fromorbit.com>
[djwong: Refuse to upgrade if any part of the fs has < 10% free]
---
 include/libxfs.h |    1 
 repair/phase2.c  |  134 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 135 insertions(+)


diff --git a/include/libxfs.h b/include/libxfs.h
index 9e8596bedf9..77ecfda4bc7 100644
--- a/include/libxfs.h
+++ b/include/libxfs.h
@@ -86,6 +86,7 @@ struct iomap;
 #include "xfs_btree_staging.h"
 #include "xfs_rtbitmap.h"
 #include "xfs_symlink_remote.h"
+#include "xfs_ag_resv.h"
 
 #ifndef ARRAY_SIZE
 #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
diff --git a/repair/phase2.c b/repair/phase2.c
index 06374817964..36eb0c21de5 100644
--- a/repair/phase2.c
+++ b/repair/phase2.c
@@ -221,6 +221,137 @@ install_new_state(
 	libxfs_trans_init(mp);
 }
 
+#define GIGABYTES(count, blog)     ((uint64_t)(count) << (30 - (blog)))
+static inline bool
+check_free_space(
+	struct xfs_mount	*mp,
+	unsigned long long	avail,
+	unsigned long long	total)
+{
+	/* Ok if there's more than 10% free. */
+	if (avail >= total / 10)
+		return true;
+
+	/* Not ok if there's less than 5% free. */
+	if (avail < total / 5)
+		return false;
+
+	/* Let it slide if there's at least 10GB free. */
+	return avail > GIGABYTES(10, mp->m_sb.sb_blocklog);
+}
+
+static void
+check_fs_free_space(
+	struct xfs_mount		*mp,
+	const struct check_state	*old,
+	struct xfs_sb			*new_sb)
+{
+	struct xfs_perag		*pag;
+	xfs_agnumber_t			agno;
+	int				error;
+
+	/* Make sure we have enough space for per-AG reservations. */
+	for_each_perag(mp, agno, pag) {
+		struct xfs_trans	*tp;
+		struct xfs_agf		*agf;
+		struct xfs_buf		*agi_bp, *agf_bp;
+		unsigned int		avail, agblocks;
+
+		/* Put back the old super so that we can read AG headers. */
+		restore_old_state(mp, old);
+
+		/*
+		 * Create a dummy transaction so that we can load the AGI and
+		 * AGF buffers in memory with the old fs geometry and pin them
+		 * there while we try to make a per-AG reservation with the new
+		 * geometry.
+		 */
+		error = -libxfs_trans_alloc_empty(mp, &tp);
+		if (error)
+			do_error(
+	_("Cannot reserve resources for upgrade check, err=%d.\n"),
+					error);
+
+		error = -libxfs_ialloc_read_agi(pag, tp, &agi_bp);
+		if (error)
+			do_error(
+	_("Cannot read AGI %u for upgrade check, err=%d.\n"),
+					pag->pag_agno, error);
+
+		error = -libxfs_alloc_read_agf(pag, tp, 0, &agf_bp);
+		if (error)
+			do_error(
+	_("Cannot read AGF %u for upgrade check, err=%d.\n"),
+					pag->pag_agno, error);
+		agf = agf_bp->b_addr;
+		agblocks = be32_to_cpu(agf->agf_length);
+
+		/*
+		 * Install the new superblock and try to make a per-AG space
+		 * reservation with the new geometry.  We pinned the AG header
+		 * buffers to the transaction, so we shouldn't hit any
+		 * corruption errors on account of the new geometry.
+		 */
+		install_new_state(mp, new_sb);
+
+		error = -libxfs_ag_resv_init(pag, tp);
+		if (error == ENOSPC) {
+			printf(
+	_("Not enough free space would remain in AG %u for metadata.\n"),
+					pag->pag_agno);
+			exit(1);
+		}
+		if (error)
+			do_error(
+	_("Error %d while checking AG %u space reservation.\n"),
+					error, pag->pag_agno);
+
+		/*
+		 * Would the post-upgrade filesystem have enough free space in
+		 * this AG after making per-AG reservations?
+		 */
+		avail = pag->pagf_freeblks + pag->pagf_flcount;
+		avail -= pag->pag_meta_resv.ar_reserved;
+		avail -= pag->pag_rmapbt_resv.ar_asked;
+
+		if (!check_free_space(mp, avail, agblocks)) {
+			printf(
+	_("AG %u will be low on space after upgrade.\n"),
+					pag->pag_agno);
+			exit(1);
+		}
+		libxfs_trans_cancel(tp);
+	}
+
+	/*
+	 * Would the post-upgrade filesystem have enough free space on the data
+	 * device after making per-AG reservations?
+	 */
+	if (!check_free_space(mp, mp->m_sb.sb_fdblocks, mp->m_sb.sb_dblocks)) {
+		printf(_("Filesystem will be low on space after upgrade.\n"));
+		exit(1);
+	}
+
+	/*
+	 * Release the per-AG reservations and mark the per-AG structure as
+	 * uninitialized so that we don't trip over stale cached counters
+	 * after the upgrade/
+	 */
+	for_each_perag(mp, agno, pag) {
+		libxfs_ag_resv_free(pag);
+		clear_bit(XFS_AGSTATE_AGF_INIT, &pag->pag_opstate);
+		clear_bit(XFS_AGSTATE_AGI_INIT, &pag->pag_opstate);
+	}
+}
+
+static bool
+need_check_fs_free_space(
+	struct xfs_mount		*mp,
+	const struct check_state	*old)
+{
+	return false;
+}
+
 /*
  * Make sure we can actually upgrade this (v5) filesystem without running afoul
  * of root inode or log size requirements that would prevent us from mounting
@@ -263,6 +394,9 @@ install_new_geometry(
 		exit(1);
 	}
 
+	if (need_check_fs_free_space(mp, &old))
+		check_fs_free_space(mp, &old, new_sb);
+
 	/*
 	 * Restore the old state to get everything back to a clean state,
 	 * upgrade the featureset one more time, and recompute the btree max

[PATCH 2/4] xfs_repair: allow sysadmins to add free inode btree indexes

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Allow the sysadmin to use xfs_repair to upgrade an existing filesystem
to support the free inode btree.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 man/man8/xfs_admin.8 |    7 +++++++
 repair/globals.c     |    1 +
 repair/globals.h     |    1 +
 repair/phase2.c      |   26 ++++++++++++++++++++++++++
 repair/xfs_repair.c  |   11 +++++++++++
 5 files changed, 46 insertions(+)


diff --git a/man/man8/xfs_admin.8 b/man/man8/xfs_admin.8
index 4794d6774ed..efe2ce45fc2 100644
--- a/man/man8/xfs_admin.8
+++ b/man/man8/xfs_admin.8
@@ -156,6 +156,13 @@ data fork extent count will be 2^48 - 1, while the maximum attribute fork
 extent count will be 2^32 - 1. The filesystem cannot be downgraded after this
 feature is enabled. Once enabled, the filesystem will not be mountable by
 older kernels.  This feature was added to Linux 5.19.
+.TP 0.4i
+.B finobt
+Track free inodes through a separate free inode btree index to speed up inode
+allocation on old filesystems.
+This upgrade can fail if any AG has less than 1% free space remaining.
+The filesystem cannot be downgraded after this feature is enabled.
+This feature was added to Linux 3.16.
 .RE
 .TP
 .BI \-U " uuid"
diff --git a/repair/globals.c b/repair/globals.c
index a68929bdc01..960dff28fba 100644
--- a/repair/globals.c
+++ b/repair/globals.c
@@ -52,6 +52,7 @@ bool	features_changed;	/* did we change superblock feature bits? */
 bool	add_inobtcount;		/* add inode btree counts to AGI */
 bool	add_bigtime;		/* add support for timestamps up to 2486 */
 bool	add_nrext64;
+bool	add_finobt;		/* add free inode btrees */
 
 /* misc status variables */
 
diff --git a/repair/globals.h b/repair/globals.h
index a67e384a626..4ec68ecd896 100644
--- a/repair/globals.h
+++ b/repair/globals.h
@@ -93,6 +93,7 @@ extern bool	features_changed;	/* did we change superblock feature bits? */
 extern bool	add_inobtcount;		/* add inode btree counts to AGI */
 extern bool	add_bigtime;		/* add support for timestamps up to 2486 */
 extern bool	add_nrext64;
+extern bool	add_finobt;		/* add free inode btrees */
 
 /* misc status variables */
 
diff --git a/repair/phase2.c b/repair/phase2.c
index 36eb0c21de5..5d2bb859514 100644
--- a/repair/phase2.c
+++ b/repair/phase2.c
@@ -182,6 +182,28 @@ set_nrext64(
 	return true;
 }
 
+static bool
+set_finobt(
+	struct xfs_mount	*mp,
+	struct xfs_sb		*new_sb)
+{
+	if (xfs_has_finobt(mp)) {
+		printf(_("Filesystem already supports free inode btrees.\n"));
+		exit(0);
+	}
+
+	if (!xfs_has_crc(mp)) {
+		printf(
+	_("Free inode btree feature only supported on V5 filesystems.\n"));
+		exit(0);
+	}
+
+	printf(_("Adding free inode btrees to filesystem.\n"));
+	new_sb->sb_features_ro_compat |= XFS_SB_FEAT_RO_COMPAT_FINOBT;
+	new_sb->sb_features_incompat |= XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR;
+	return true;
+}
+
 struct check_state {
 	struct xfs_sb		sb;
 	uint64_t		features;
@@ -349,6 +371,8 @@ need_check_fs_free_space(
 	struct xfs_mount		*mp,
 	const struct check_state	*old)
 {
+	if (xfs_has_finobt(mp) && !(old->features & XFS_FEAT_FINOBT))
+		return true;
 	return false;
 }
 
@@ -424,6 +448,8 @@ upgrade_filesystem(
 		dirty |= set_bigtime(mp, &new_sb);
 	if (add_nrext64)
 		dirty |= set_nrext64(mp, &new_sb);
+	if (add_finobt)
+		dirty |= set_finobt(mp, &new_sb);
 	if (!dirty)
 		return;
 
diff --git a/repair/xfs_repair.c b/repair/xfs_repair.c
index bf02beba375..b61af185c38 100644
--- a/repair/xfs_repair.c
+++ b/repair/xfs_repair.c
@@ -69,6 +69,7 @@ enum c_opt_nums {
 	CONVERT_INOBTCOUNT,
 	CONVERT_BIGTIME,
 	CONVERT_NREXT64,
+	CONVERT_FINOBT,
 	C_MAX_OPTS,
 };
 
@@ -77,6 +78,7 @@ static char *c_opts[] = {
 	[CONVERT_INOBTCOUNT]	= "inobtcount",
 	[CONVERT_BIGTIME]	= "bigtime",
 	[CONVERT_NREXT64]	= "nrext64",
+	[CONVERT_FINOBT]	= "finobt",
 	[C_MAX_OPTS]		= NULL,
 };
 
@@ -336,6 +338,15 @@ process_args(int argc, char **argv)
 		_("-c nrext64 only supports upgrades\n"));
 					add_nrext64 = true;
 					break;
+				case CONVERT_FINOBT:
+					if (!val)
+						do_abort(
+		_("-c finobt requires a parameter\n"));
+					if (strtol(val, NULL, 0) != 1)
+						do_abort(
+		_("-c finobt only supports upgrades\n"));
+					add_finobt = true;
+					break;
 				default:
 					unknown('c', val);
 					break;

[PATCH 3/4] xfs_repair: allow sysadmins to add reflink

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Allow the sysadmin to use xfs_repair to upgrade an existing filesystem
to support the reference count btree, and therefore reflink.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 man/man8/xfs_admin.8 |    6 ++++++
 repair/globals.c     |    1 +
 repair/globals.h     |    1 +
 repair/phase2.c      |   31 +++++++++++++++++++++++++++++++
 repair/rmap.c        |    4 ++--
 repair/xfs_repair.c  |   11 +++++++++++
 6 files changed, 52 insertions(+), 2 deletions(-)


diff --git a/man/man8/xfs_admin.8 b/man/man8/xfs_admin.8
index efe2ce45fc2..3af201cadc3 100644
--- a/man/man8/xfs_admin.8
+++ b/man/man8/xfs_admin.8
@@ -163,6 +163,12 @@ allocation on old filesystems.
 This upgrade can fail if any AG has less than 1% free space remaining.
 The filesystem cannot be downgraded after this feature is enabled.
 This feature was added to Linux 3.16.
+.TP 0.4i
+.B reflink
+Enable sharing of file data blocks.
+This upgrade can fail if any AG has less than 2% free space remaining.
+The filesystem cannot be downgraded after this feature is enabled.
+This feature was added to Linux 4.9.
 .RE
 .TP
 .BI \-U " uuid"
diff --git a/repair/globals.c b/repair/globals.c
index 960dff28fba..f0754393ba2 100644
--- a/repair/globals.c
+++ b/repair/globals.c
@@ -53,6 +53,7 @@ bool	add_inobtcount;		/* add inode btree counts to AGI */
 bool	add_bigtime;		/* add support for timestamps up to 2486 */
 bool	add_nrext64;
 bool	add_finobt;		/* add free inode btrees */
+bool	add_reflink;		/* add reference count btrees */
 
 /* misc status variables */
 
diff --git a/repair/globals.h b/repair/globals.h
index 4ec68ecd896..4013d8f0d24 100644
--- a/repair/globals.h
+++ b/repair/globals.h
@@ -94,6 +94,7 @@ extern bool	add_inobtcount;		/* add inode btree counts to AGI */
 extern bool	add_bigtime;		/* add support for timestamps up to 2486 */
 extern bool	add_nrext64;
 extern bool	add_finobt;		/* add free inode btrees */
+extern bool	add_reflink;		/* add reference count btrees */
 
 /* misc status variables */
 
diff --git a/repair/phase2.c b/repair/phase2.c
index 5d2bb859514..9a8bf411333 100644
--- a/repair/phase2.c
+++ b/repair/phase2.c
@@ -204,6 +204,33 @@ set_finobt(
 	return true;
 }
 
+static bool
+set_reflink(
+	struct xfs_mount	*mp,
+	struct xfs_sb		*new_sb)
+{
+	if (xfs_has_reflink(mp)) {
+		printf(_("Filesystem already supports reflink.\n"));
+		exit(0);
+	}
+
+	if (!xfs_has_crc(mp)) {
+		printf(
+	_("Reflink feature only supported on V5 filesystems.\n"));
+		exit(0);
+	}
+
+	if (xfs_has_realtime(mp)) {
+		printf(_("Reflink feature not supported with realtime.\n"));
+		exit(0);
+	}
+
+	printf(_("Adding reflink support to filesystem.\n"));
+	new_sb->sb_features_ro_compat |= XFS_SB_FEAT_RO_COMPAT_REFLINK;
+	new_sb->sb_features_incompat |= XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR;
+	return true;
+}
+
 struct check_state {
 	struct xfs_sb		sb;
 	uint64_t		features;
@@ -373,6 +400,8 @@ need_check_fs_free_space(
 {
 	if (xfs_has_finobt(mp) && !(old->features & XFS_FEAT_FINOBT))
 		return true;
+	if (xfs_has_reflink(mp) && !(old->features & XFS_FEAT_REFLINK))
+		return true;
 	return false;
 }
 
@@ -450,6 +479,8 @@ upgrade_filesystem(
 		dirty |= set_nrext64(mp, &new_sb);
 	if (add_finobt)
 		dirty |= set_finobt(mp, &new_sb);
+	if (add_reflink)
+		dirty |= set_reflink(mp, &new_sb);
 	if (!dirty)
 		return;
 
diff --git a/repair/rmap.c b/repair/rmap.c
index 8895377aa2a..91a87d418e2 100644
--- a/repair/rmap.c
+++ b/repair/rmap.c
@@ -52,7 +52,7 @@ bool
 rmap_needs_work(
 	struct xfs_mount	*mp)
 {
-	return xfs_has_reflink(mp) ||
+	return xfs_has_reflink(mp) || add_reflink ||
 	       xfs_has_rmapbt(mp);
 }
 
@@ -1526,7 +1526,7 @@ check_refcounts(
 	int				i;
 	int				error;
 
-	if (!xfs_has_reflink(mp))
+	if (!xfs_has_reflink(mp) || add_reflink)
 		return;
 	if (refcbt_suspect) {
 		if (no_modify && agno == 0)
diff --git a/repair/xfs_repair.c b/repair/xfs_repair.c
index b61af185c38..d53db25e618 100644
--- a/repair/xfs_repair.c
+++ b/repair/xfs_repair.c
@@ -70,6 +70,7 @@ enum c_opt_nums {
 	CONVERT_BIGTIME,
 	CONVERT_NREXT64,
 	CONVERT_FINOBT,
+	CONVERT_REFLINK,
 	C_MAX_OPTS,
 };
 
@@ -79,6 +80,7 @@ static char *c_opts[] = {
 	[CONVERT_BIGTIME]	= "bigtime",
 	[CONVERT_NREXT64]	= "nrext64",
 	[CONVERT_FINOBT]	= "finobt",
+	[CONVERT_REFLINK]	= "reflink",
 	[C_MAX_OPTS]		= NULL,
 };
 
@@ -347,6 +349,15 @@ process_args(int argc, char **argv)
 		_("-c finobt only supports upgrades\n"));
 					add_finobt = true;
 					break;
+				case CONVERT_REFLINK:
+					if (!val)
+						do_abort(
+		_("-c reflink requires a parameter\n"));
+					if (strtol(val, NULL, 0) != 1)
+						do_abort(
+		_("-c reflink only supports upgrades\n"));
+					add_reflink = true;
+					break;
 				default:
 					unknown('c', val);
 					break;

[PATCH 4/4] xfs_repair: allow sysadmins to add reverse mapping indexes

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Allow the sysadmin to use xfs_repair to upgrade an existing filesystem
to support the reverse mapping btree index.  This is needed for online
fsck.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 man/man8/xfs_admin.8 |    8 ++++++++
 repair/globals.c     |    1 +
 repair/globals.h     |    1 +
 repair/phase2.c      |   38 ++++++++++++++++++++++++++++++++++++++
 repair/rmap.c        |    4 ++--
 repair/xfs_repair.c  |   11 +++++++++++
 6 files changed, 61 insertions(+), 2 deletions(-)


diff --git a/man/man8/xfs_admin.8 b/man/man8/xfs_admin.8
index 3af201cadc3..467fb2dfd0a 100644
--- a/man/man8/xfs_admin.8
+++ b/man/man8/xfs_admin.8
@@ -169,6 +169,14 @@ Enable sharing of file data blocks.
 This upgrade can fail if any AG has less than 2% free space remaining.
 The filesystem cannot be downgraded after this feature is enabled.
 This feature was added to Linux 4.9.
+.TP 0.4i
+.B rmapbt
+Store an index of the owners of on-disk blocks.
+This enables much stronger cross-referencing of various metadata structures
+and online repairs to space usage metadata.
+The filesystem cannot be downgraded after this feature is enabled.
+This upgrade can fail if any AG has less than 5% free space remaining.
+This feature was added to Linux 4.8.
 .RE
 .TP
 .BI \-U " uuid"
diff --git a/repair/globals.c b/repair/globals.c
index f0754393ba2..cff620e8f0e 100644
--- a/repair/globals.c
+++ b/repair/globals.c
@@ -54,6 +54,7 @@ bool	add_bigtime;		/* add support for timestamps up to 2486 */
 bool	add_nrext64;
 bool	add_finobt;		/* add free inode btrees */
 bool	add_reflink;		/* add reference count btrees */
+bool	add_rmapbt;		/* add reverse mapping btrees */
 
 /* misc status variables */
 
diff --git a/repair/globals.h b/repair/globals.h
index 4013d8f0d24..76d22fd3b2c 100644
--- a/repair/globals.h
+++ b/repair/globals.h
@@ -95,6 +95,7 @@ extern bool	add_bigtime;		/* add support for timestamps up to 2486 */
 extern bool	add_nrext64;
 extern bool	add_finobt;		/* add free inode btrees */
 extern bool	add_reflink;		/* add reference count btrees */
+extern bool	add_rmapbt;		/* add reverse mapping btrees */
 
 /* misc status variables */
 
diff --git a/repair/phase2.c b/repair/phase2.c
index 9a8bf411333..be0d791a8b5 100644
--- a/repair/phase2.c
+++ b/repair/phase2.c
@@ -231,6 +231,40 @@ set_reflink(
 	return true;
 }
 
+static bool
+set_rmapbt(
+	struct xfs_mount	*mp,
+	struct xfs_sb		*new_sb)
+{
+	if (xfs_has_rmapbt(mp)) {
+		printf(_("Filesystem already supports reverse mapping btrees.\n"));
+		exit(0);
+	}
+
+	if (!xfs_has_crc(mp)) {
+		printf(
+	_("Reverse mapping btree feature only supported on V5 filesystems.\n"));
+		exit(0);
+	}
+
+	if (xfs_has_realtime(mp)) {
+		printf(
+	_("Reverse mapping btree feature not supported with realtime.\n"));
+		exit(0);
+	}
+
+	if (xfs_has_reflink(mp)) {
+		printf(
+	_("Reverse mapping btrees cannot be added when reflink is enabled.\n"));
+		exit(0);
+	}
+
+	printf(_("Adding reverse mapping btrees to filesystem.\n"));
+	new_sb->sb_features_ro_compat |= XFS_SB_FEAT_RO_COMPAT_RMAPBT;
+	new_sb->sb_features_incompat |= XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR;
+	return true;
+}
+
 struct check_state {
 	struct xfs_sb		sb;
 	uint64_t		features;
@@ -402,6 +436,8 @@ need_check_fs_free_space(
 		return true;
 	if (xfs_has_reflink(mp) && !(old->features & XFS_FEAT_REFLINK))
 		return true;
+	if (xfs_has_rmapbt(mp) && !(old->features & XFS_FEAT_RMAPBT))
+		return true;
 	return false;
 }
 
@@ -481,6 +517,8 @@ upgrade_filesystem(
 		dirty |= set_finobt(mp, &new_sb);
 	if (add_reflink)
 		dirty |= set_reflink(mp, &new_sb);
+	if (add_rmapbt)
+		dirty |= set_rmapbt(mp, &new_sb);
 	if (!dirty)
 		return;
 
diff --git a/repair/rmap.c b/repair/rmap.c
index 91a87d418e2..37fcf923644 100644
--- a/repair/rmap.c
+++ b/repair/rmap.c
@@ -53,7 +53,7 @@ rmap_needs_work(
 	struct xfs_mount	*mp)
 {
 	return xfs_has_reflink(mp) || add_reflink ||
-	       xfs_has_rmapbt(mp);
+	       xfs_has_rmapbt(mp) || add_rmapbt;
 }
 
 /* Destroy an in-memory rmap btree. */
@@ -1156,7 +1156,7 @@ rmaps_verify_btree(
 	int			have;
 	int			error;
 
-	if (!xfs_has_rmapbt(mp))
+	if (!xfs_has_rmapbt(mp) || add_rmapbt)
 		return;
 	if (rmapbt_suspect) {
 		if (no_modify && agno == 0)
diff --git a/repair/xfs_repair.c b/repair/xfs_repair.c
index d53db25e618..e94b0a79378 100644
--- a/repair/xfs_repair.c
+++ b/repair/xfs_repair.c
@@ -71,6 +71,7 @@ enum c_opt_nums {
 	CONVERT_NREXT64,
 	CONVERT_FINOBT,
 	CONVERT_REFLINK,
+	CONVERT_RMAPBT,
 	C_MAX_OPTS,
 };
 
@@ -81,6 +82,7 @@ static char *c_opts[] = {
 	[CONVERT_NREXT64]	= "nrext64",
 	[CONVERT_FINOBT]	= "finobt",
 	[CONVERT_REFLINK]	= "reflink",
+	[CONVERT_RMAPBT]	= "rmapbt",
 	[C_MAX_OPTS]		= NULL,
 };
 
@@ -358,6 +360,15 @@ process_args(int argc, char **argv)
 		_("-c reflink only supports upgrades\n"));
 					add_reflink = true;
 					break;
+				case CONVERT_RMAPBT:
+					if (!val)
+						do_abort(
+		_("-c rmapbt requires a parameter\n"));
+					if (strtol(val, NULL, 0) != 1)
+						do_abort(
+		_("-c rmapbt only supports upgrades\n"));
+					add_rmapbt = true;
+					break;
 				default:
 					unknown('c', val);
 					break;

Re: [PATCH 1/9] xfs: dump xfiles for debugging purposes

[Matthew Wilcox]

On Sun, Dec 31, 2023 at 12:13:49PM -0800, Darrick J. Wong wrote:
> +	error = xfile_stat(xf, &sb);
> +	if (error)
> +		return error;
> +
> +	printk(KERN_ALERT "xfile ino 0x%lx isize 0x%llx dump:", inode->i_ino,
> +			sb.size);
> +	pflags = memalloc_nofs_save();

Hm, why?  What makes it a bad idea to call back into the filesysteam at
this point?

> +			page = shmem_read_mapping_page_gfp(mapping,
> +					datapos >> PAGE_SHIFT, __GFP_NOWARN);

This GFP flag looks wrong.  Why can't we use GFP_KERNEL here?

I'm also not thrilled about the use of page APIs instead of folio APIs,
but given how long this patchset has been in development, I understand why
you didn't start out with folio APIs.  It's not a blocker by any means.

I can come through and convert it later when I decide that it's finally
time to get rid of shmem_read_mapping_page_gfp(), which is going to take
a big gulp because it now means touching GPU drivers ...

Re: [PATCH 9/9] xfs: connect in-memory btrees to xfiles

[Matthew Wilcox]

On Sun, Dec 31, 2023 at 12:15:54PM -0800, Darrick J. Wong wrote:
> +/* Ensure that there is storage backing the given range. */
> +int
> +xfile_prealloc(
> +	struct xfile		*xf,
> +	loff_t			pos,
> +	u64			count)
> +{
> +	struct inode		*inode = file_inode(xf->file);
> +	struct address_space	*mapping = inode->i_mapping;
> +	const struct address_space_operations *aops = mapping->a_ops;
> +	struct page		*page = NULL;
> +	unsigned int		pflags;
> +	int			error = 0;
> +
> +	if (count > MAX_RW_COUNT)
> +		return -E2BIG;
> +	if (inode->i_sb->s_maxbytes - pos < count)
> +		return -EFBIG;
> +
> +	trace_xfile_prealloc(xf, pos, count);
> +
> +	pflags = memalloc_nofs_save();
> +	while (count > 0) {
> +		void		*fsdata = NULL;
> +		unsigned int	len;
> +		int		ret;
> +
> +		len = min_t(ssize_t, count, PAGE_SIZE - offset_in_page(pos));
> +
> +		/*
> +		 * We call write_begin directly here to avoid all the freezer
> +		 * protection lock-taking that happens in the normal path.
> +		 * shmem doesn't support fs freeze, but lockdep doesn't know
> +		 * that and will trip over that.
> +		 */
> +		error = aops->write_begin(NULL, mapping, pos, len, &page,
> +				&fsdata);
> +		if (error)
> +			break;
> +
> +		/*
> +		 * xfile pages must never be mapped into userspace, so we skip
> +		 * the dcache flush.  If the page is not uptodate, zero it to
> +		 * ensure we never go lacking for space here.
> +		 */
> +		if (!PageUptodate(page)) {
> +			void	*kaddr = kmap_local_page(page);
> +
> +			memset(kaddr, 0, PAGE_SIZE);
> +			SetPageUptodate(page);
> +			kunmap_local(kaddr);
> +		}

Does the xfiles implementation prevent THPs from being created?
If not, this could lead to an entire THP being marked uptodate even
though we've only zeroed one page of it.

Re: [PATCH 8/9] xfs_scrub_fail: move executable script to /usr/libexec

[Neal Gompa]

On Sun, Dec 31, 2023 at 5:54 PM Darrick J. Wong <djwong@kernel.org> wrote:
>
> From: Darrick J. Wong <djwong@kernel.org>
>
> Per FHS 3.0, non-PATH executable binaries are supposed to live under
> /usr/libexec, not /usr/lib.  xfs_scrub_fail is an executable script,
> so move it to libexec in case some distro some day tries to mount
> /usr/lib as noexec or something.
>
> Cc: Neal Gompa <neal@gompa.dev>
> Link: https://refspecs.linuxfoundation.org/FHS_3.0/fhs/ch04s07.html
> Signed-off-by: Darrick J. Wong <djwong@kernel.org>
> ---
>  include/builddefs.in             |    1 +
>  scrub/Makefile                   |    7 +++----
>  scrub/xfs_scrub_fail@.service.in |    2 +-
>  3 files changed, 5 insertions(+), 5 deletions(-)
>
>
> diff --git a/include/builddefs.in b/include/builddefs.in
> index eb7f6ba4f03..9d0f9c3bf7c 100644
> --- a/include/builddefs.in
> +++ b/include/builddefs.in
> @@ -52,6 +52,7 @@ PKG_ROOT_SBIN_DIR = @root_sbindir@
>  PKG_ROOT_LIB_DIR= @root_libdir@@libdirsuffix@
>  PKG_LIB_DIR    = @libdir@@libdirsuffix@
>  PKG_LIB_SCRIPT_DIR     = @libdir@
> +PKG_LIBEXEC_DIR        = @libexecdir@/@pkg_name@
>  PKG_INC_DIR    = @includedir@/xfs
>  DK_INC_DIR     = @includedir@/disk
>  PKG_MAN_DIR    = @mandir@
> diff --git a/scrub/Makefile b/scrub/Makefile
> index fd47b893956..8fb366c922c 100644
> --- a/scrub/Makefile
> +++ b/scrub/Makefile
> @@ -140,8 +140,7 @@ install: $(INSTALL_SCRUB)
>         @echo "    [SED]    $@"
>         $(Q)$(SED) -e "s|@sbindir@|$(PKG_SBIN_DIR)|g" \
>                    -e "s|@scrub_args@|$(XFS_SCRUB_ARGS)|g" \
> -                  -e "s|@pkg_lib_dir@|$(PKG_LIB_SCRIPT_DIR)|g" \
> -                  -e "s|@pkg_name@|$(PKG_NAME)|g" \
> +                  -e "s|@pkg_libexec_dir@|$(PKG_LIBEXEC_DIR)|g" \
>                    < $< > $@
>
>  %.cron: %.cron.in $(builddefs)
> @@ -151,8 +150,8 @@ install: $(INSTALL_SCRUB)
>  install-systemd: default $(SYSTEMD_SERVICES)
>         $(INSTALL) -m 755 -d $(SYSTEMD_SYSTEM_UNIT_DIR)
>         $(INSTALL) -m 644 $(SYSTEMD_SERVICES) $(SYSTEMD_SYSTEM_UNIT_DIR)
> -       $(INSTALL) -m 755 -d $(PKG_LIB_SCRIPT_DIR)/$(PKG_NAME)
> -       $(INSTALL) -m 755 $(XFS_SCRUB_FAIL_PROG) $(PKG_LIB_SCRIPT_DIR)/$(PKG_NAME)
> +       $(INSTALL) -m 755 -d $(PKG_LIBEXEC_DIR)
> +       $(INSTALL) -m 755 $(XFS_SCRUB_FAIL_PROG) $(PKG_LIBEXEC_DIR)
>
>  install-crond: default $(CRONTABS)
>         $(INSTALL) -m 755 -d $(CROND_DIR)
> diff --git a/scrub/xfs_scrub_fail@.service.in b/scrub/xfs_scrub_fail@.service.in
> index 048b5732459..48a0f25b5f1 100644
> --- a/scrub/xfs_scrub_fail@.service.in
> +++ b/scrub/xfs_scrub_fail@.service.in
> @@ -10,7 +10,7 @@ Documentation=man:xfs_scrub(8)
>  [Service]
>  Type=oneshot
>  Environment=EMAIL_ADDR=root
> -ExecStart=@pkg_lib_dir@/@pkg_name@/xfs_scrub_fail "${EMAIL_ADDR}" %f
> +ExecStart=@pkg_libexec_dir@/xfs_scrub_fail "${EMAIL_ADDR}" %f
>  User=mail
>  Group=mail
>  SupplementaryGroups=systemd-journal
>

Looks great to me.

Reviewed-by: Neal Gompa <neal@gompa.dev>



--
真実はいつも一つ！/ Always, there's only one truth!

Re: [PATCH 1/7] xfs: speed up xfs_iwalk_adjust_start a little bit

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 12:04:42PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Replace the open-coded loop that recomputes freecount with a single call
> to a bit weight function.

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 4/7] xfs: allow blocking notifier chains with filesystem hooks

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 12:05:29PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Make it so that we can switch between notifier chain implementations for
> testing purposes.  On the author's test system, calling an empty srcu
> notifier chain cost about 19ns per call, vs. 4ns for a blocking notifier
> chain.  Hm.  Might we actually want regular blocking notifiers?

Sounds like it.  But what is important is that we really shouldn't
provide both and punt the decision to the user..

Re: [PATCH 4/4] xfs: repair file modes by scanning for a dirent pointing to us

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 12:07:18PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> An earlier version of this patch ("xfs: repair obviously broken inode
> modes") tried to reset the di_mode of a file by guessing it from the
> data fork format and/or data block 0 contents.  Christoph didn't like
> this approach because it opens the possibility that users could craft a
> file to look like a directory and trick online repair into turning the
> mode into S_IFDIR.

I find the commit message here really weird.  What I want doesn't
matter.  If what I say makes sense (I hope it does, if it doesn't please
push back) then we should document thing based on the cross-checked
facts and assumptions I provided.  If not we should not be doing this
at at all.

Re: [PATCH 1/5] xfs: report the health of quota counts

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 1/9] xfs: set the btree cursor bc_ops in xfs_btree_alloc_cursor

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 2/9] xfs: encode the default bc_flags in the btree ops structure

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 12:17:28PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Certain btree flags never change for the life of a btree cursor because
> they describe the geometry of the btree itself.  Encode these in the
> btree ops structure and reduce the amount of code required in each btree
> type's init_cursor functions.

I like the idea, but why are the geom_flags mirrored into bc_flags
instead of beeing kept entirely separate and accessed as
cur->bc_ops->geom_flags which would be a lot easier to follow?

Re: [PATCH 3/9] xfs: export some of the btree ops structures

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 12:17:44PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Export these btree ops structures so that we can reference them in the
> AG initialization code in the next patch.

Fortunately not export, just not marked static :)  The being said
this would be easier to follow if simple squashed into the next patch.

Otherwise:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 4/9] xfs: initialize btree blocks using btree_ops structure

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 5/9] xfs: rename btree block/buffer init functions

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 6/9] xfs: btree convert xfs_btree_init_block to xfs_btree_init_buf calls

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 7/9] xfs: remove the unnecessary daddr paramter to _init_block

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 8/9] xfs: set btree block buffer ops in _init_buf

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 9/9] xfs: remove unnecessary fields in xfbtree_config

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 12:19:17PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Remove these fields now that we get all the info we need from the btree
> ops.

It would be great if this series could just be moved forwared to before
adding xfbtree_config so that it wouldn't need adding in the first
place?

Otherwise looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 1/4] xfs: move lru refs to the btree ops structure

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 12:19:33PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Move the btree buffer LRU refcount to the btree ops structure so that we
> can eliminate the last bc_btnum switch in the generic btree code.  We're
> about to create repair-specific btree types, and we don't want that

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 2/4] xfs: define an in-memory btree for storing refcount bag info during repairs

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 12:19:49PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Create a new in-memory btree type so that we can store refcount bag info
> in a much more memory-efficient format.

Can you add a cursory explanation of what 'bag info' is?  It took me
quite a while to figure this out by looking at the refcount_repair.c
file, and future readers or the commit log might be a lot less savy
in finding that information.  The source file could also really use a
comment explaining the bag term and what is actually stored in it.

Re: [PATCH 3/4] xfs: create refcount bag structure for btree repairs

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 12:20:04PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Create a bag structure for refcount information that uses the refcount
> bag btree defined in the previous patch.

Same commit log information comment as for the previous patch here.

Re: [PATCH 4/4] xfs: port refcount repair to the new refcount bag structure

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 12:20:20PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Port the refcount record generating code to use the new refcount bag
> data structure.

This could again use some comments on why you're doing that.  My strong
suspicion is that it will be a lot faster and/or memory efficient, but
please document this for future readers of the commit logs.

Re: [PATCH 1/7] xfs: split tracepoint classes for deferred items

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 2/7] xfs: clean up bmap log intent item tracepoint callsites

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 3/7] xfs: remove xfs_trans_set_bmap_flags

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 4/7] xfs: add a bi_entry helper

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 5/7] xfs: reuse xfs_bmap_update_cancel_item

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 12:21:38PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Reuse xfs_bmap_update_cancel_item to put the AG/RTG and free the item in
> a few places that currently open code the logic.
> 
> Inspired-by: Christoph Hellwig <hch@lst.de>
> Signed-off-by: Darrick J. Wong <djwong@kernel.org>

Isn't this actually pretty much exactly my patch?

Either way this looks (obviously :)) good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 6/7] xfs: move xfs_bmap_defer_add to xfs_bmap_item.c

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 7/7] xfs: add a xattr_entry helper

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 1/3] xfs: fix xfs_bunmapi to allow unmapping of partial rt extents

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 2/3] xfs: add a realtime flag to the bmap update log redo items

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 3/3] xfs: support recovering bmap intent items targetting realtime extents

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCHSET v29.0 34/40] xfs_scrub: fixes for systemd services

[Christoph Hellwig]

Can we somehow expedite these plumbing fixes for the next xfsprogs
release instead of just hiding them in the giant patchbomb?

Re: [PATCH 1/4] xfs: create a static name for the dot entry too

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 2/4] xfs: create a predicate to determine if two xfs_names are the same

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 12:06:47PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Create a simple predicate to determine if two xfs_names are the same
> objects or have the exact same name.  The comparison is always case
> sensitive.
> 
> Signed-off-by: Darrick J. Wong <djwong@kernel.org>
> ---
>  fs/xfs/libxfs/xfs_dir2.h |    9 +++++++++
>  fs/xfs/scrub/dir.c       |    4 ++--
>  2 files changed, 11 insertions(+), 2 deletions(-)
> 
> 
> diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h
> index 7d7cd8d808e4d..ac3c264402dda 100644
> --- a/fs/xfs/libxfs/xfs_dir2.h
> +++ b/fs/xfs/libxfs/xfs_dir2.h
> @@ -24,6 +24,15 @@ 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)
> +{
> +	return n1 == n2 || (n1->len == n2->len &&
> +			    !memcmp(n1->name, n2->name, n1->len));

Nit, but to me the formatting looks weird, why not:

	return n1 == n2 ||
		(n1->len == n2->len && !memcmp(n1->name, n2->name, n1->len));

Or even more verbose:

	if (n1 == n2)
		return true;
	if (n1->len != n2->len)
		return false;
	return !memcmp(n1->name, n2->name, n1->len);

Otherwise this looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 3/4] xfs: create a macro for decoding ftypes in tracepoints

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 12:07:03PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Create the XFS_DIR3_FTYPE_STR macro so that we can report ftype as
> strings instead of numbers in tracepoints.

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

But why not fold this into the patch actually using the macro?

Re: [PATCH 2/7] xfs: implement live inode scan for scrub

[Christoph Hellwig]

> +	trace_xchk_iscan_iget(iscan, error);
> +
> +	if (error == -ENOENT || error == -EAGAIN) {
> +		/*¬

This has a weird character on the opening comment line.

Otherwise looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 3/7] xfs: allow scrub to hook metadata updates in other writers

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 12:05:13PM -0800, Darrick J. Wong wrote:
> On the author's computer, calling an empty srcu notifier chain was
> observed to have an overhead averaging ~40ns with a maximum of 60ns.
> Adding a no-op notifier function increased the average to ~58ns and
> 66ns.  When the quotacheck live update notifier is attached, the average
> increases to ~322ns with a max of 372ns to update scrub's in-memory
> observation data, assuming no lock contention.
> 
> With jump labels enabled, calls to empty srcu notifier chains are elided
> from the call sites when there are no hooks registered, which means that
> the overhead is 0.36ns when fsck is not running.  For compilers that do
> not support jump labels (all major architectures do), the overhead of a
> no-op notifier call is less bad (on a many-cpu system) than the atomic
> counter ops, so we make the hook switch itself a nop.

Based on the next patch it seems like blocking notifier are the way
to go and thus this patch should switch to using them and the above
needs updates.

> Note: This new code is also split out as a separate patch from its
> initial user so that the author can move patches around his tree with
> ease.

For the final merge candidate at least this comment should go away,
and maybe also the split..

> +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

I'm a bit confused by all the extra Kconfig options here.
Why do we need XFS_LIVE_HOOKS, or the existing XFS_DRAIN_INTENTS
instead of just switching the ifdefs to XFS_ONLINE_SCRUB and
selecting JUMP_LABEL if HAVE_ARCH_JUMP_LABEL from
XFS_ONLINE_SCRUB?

Also while I'm at random Kconfig critique, n is the default default
and the default n here can be dropped.  I might just send a patch for
that instead of bothering you once this series is in, though.

Otherwise this looks good except for the choice of which notifier
type to use.

Re: [PATCH 5/7] xfs: stagger the starting AG of scrub iscans to reduce contention

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 6/7] xfs: cache a bunch of inodes for repair scans

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 7/7] xfs: iscan batching should handle unallocated inodes too

[Christoph Hellwig]

Any reason to not just fold this into the previous patch?

Otherwise looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 2/4] xfs: create a predicate to determine if two xfs_names are the same

[Darrick J. Wong]

On Tue, Jan 02, 2024 at 03:13:05AM -0800, Christoph Hellwig wrote:
> On Sun, Dec 31, 2023 at 12:06:47PM -0800, Darrick J. Wong wrote:
> > From: Darrick J. Wong <djwong@kernel.org>
> > 
> > Create a simple predicate to determine if two xfs_names are the same
> > objects or have the exact same name.  The comparison is always case
> > sensitive.
> > 
> > Signed-off-by: Darrick J. Wong <djwong@kernel.org>
> > ---
> >  fs/xfs/libxfs/xfs_dir2.h |    9 +++++++++
> >  fs/xfs/scrub/dir.c       |    4 ++--
> >  2 files changed, 11 insertions(+), 2 deletions(-)
> > 
> > 
> > diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h
> > index 7d7cd8d808e4d..ac3c264402dda 100644
> > --- a/fs/xfs/libxfs/xfs_dir2.h
> > +++ b/fs/xfs/libxfs/xfs_dir2.h
> > @@ -24,6 +24,15 @@ 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)
> > +{
> > +	return n1 == n2 || (n1->len == n2->len &&
> > +			    !memcmp(n1->name, n2->name, n1->len));
> 
> Nit, but to me the formatting looks weird, why not:
> 
> 	return n1 == n2 ||
> 		(n1->len == n2->len && !memcmp(n1->name, n2->name, n1->len));
> 
> Or even more verbose:
> 
> 	if (n1 == n2)
> 		return true;
> 	if (n1->len != n2->len)
> 		return false;
> 	return !memcmp(n1->name, n2->name, n1->len);

Yeah, I'll do that instead of the multiline thing.

> Otherwise this looks good:
> 
> Reviewed-by: Christoph Hellwig <hch@lst.de>

Thanks!

--D

Re: [PATCH 3/4] xfs: create a macro for decoding ftypes in tracepoints

[Darrick J. Wong]

On Tue, Jan 02, 2024 at 03:13:30AM -0800, Christoph Hellwig wrote:
> On Sun, Dec 31, 2023 at 12:07:03PM -0800, Darrick J. Wong wrote:
> > From: Darrick J. Wong <djwong@kernel.org>
> > 
> > Create the XFS_DIR3_FTYPE_STR macro so that we can report ftype as
> > strings instead of numbers in tracepoints.
> 
> Looks good:
> 
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> 
> But why not fold this into the patch actually using the macro?

That patch has slowly been jumping ahead of other patches in djwong-dev
as I've wanted it for symbolic decoding of ftypes.  After a couple times
of carefully cutting out that hunk of the patch to paste it into another
earlier patch I decided it would be much easier to do:

$ stg export -d foopatches/
$ vi foopatches/series

Change:

	xfs-patch-001
	xfs-patch-002
	...
	xfs-patch-300
	xfs-dir2-create-ftype-strings-for-ftrace
	xfs-patch-301

Into:

	xfs-patch-001
	xfs-dir2-create-ftype-strings-for-ftrace
	xfs-patch-002
	...
	xfs-patch-300
	xfs-patch-301
:wq

$ stg float -s foopatches/series
$ <patch stack reordered with minimal work on my part>

--D

Re: [PATCH 3/7] xfs: allow scrub to hook metadata updates in other writers

[Darrick J. Wong]

On Tue, Jan 02, 2024 at 03:30:17AM -0800, Christoph Hellwig wrote:
> On Sun, Dec 31, 2023 at 12:05:13PM -0800, Darrick J. Wong wrote:
> > On the author's computer, calling an empty srcu notifier chain was
> > observed to have an overhead averaging ~40ns with a maximum of 60ns.
> > Adding a no-op notifier function increased the average to ~58ns and
> > 66ns.  When the quotacheck live update notifier is attached, the average
> > increases to ~322ns with a max of 372ns to update scrub's in-memory
> > observation data, assuming no lock contention.
> > 
> > With jump labels enabled, calls to empty srcu notifier chains are elided
> > from the call sites when there are no hooks registered, which means that
> > the overhead is 0.36ns when fsck is not running.  For compilers that do
> > not support jump labels (all major architectures do), the overhead of a
> > no-op notifier call is less bad (on a many-cpu system) than the atomic
> > counter ops, so we make the hook switch itself a nop.
> 
> Based on the next patch it seems like blocking notifier are the way
> to go and thus this patch should switch to using them and the above
> needs updates.

I'll address the srcu vs. blocking choice in the thread for the next
patch.

> > Note: This new code is also split out as a separate patch from its
> > initial user so that the author can move patches around his tree with
> > ease.
> 
> For the final merge candidate at least this comment should go away,
> and maybe also the split..
> 
> > +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
> 
> I'm a bit confused by all the extra Kconfig options here.
> Why do we need XFS_LIVE_HOOKS, or the existing XFS_DRAIN_INTENTS
> instead of just switching the ifdefs to XFS_ONLINE_SCRUB and
> selecting JUMP_LABEL if HAVE_ARCH_JUMP_LABEL from
> XFS_ONLINE_SCRUB?

I have plans to use the live hooks for more than just online scrub.
If we ever get around to reimplementing xfs_reno (see patchriver #4 for
a somewhat racy userspace version) in the kernel, it would be helpful
for reno to be able to keep an eye on any other directory link changes
while we're trying to renumber things.

As for DRAIN_INTENTS, userspace takes advantage of some of the
XFS_ONLINE_SCRUB code but doesn't need the intent drain because libxfs
isn't properly multithreaded.

> Also while I'm at random Kconfig critique, n is the default default
> and the default n here can be dropped.  I might just send a patch for
> that instead of bothering you once this series is in, though.

You could even send it now; I don't think there's much chance that
Chandan will merge this patchset for 6.8, whereas I think the kconfig
cleanup would be fine for the merge window.

> Otherwise this looks good except for the choice of which notifier
> type to use.

<nod>

--D

Re: [PATCH 4/7] xfs: allow blocking notifier chains with filesystem hooks

[Darrick J. Wong]

On Tue, Jan 02, 2024 at 02:28:04AM -0800, Christoph Hellwig wrote:
> On Sun, Dec 31, 2023 at 12:05:29PM -0800, Darrick J. Wong wrote:
> > From: Darrick J. Wong <djwong@kernel.org>
> > 
> > Make it so that we can switch between notifier chain implementations for
> > testing purposes.  On the author's test system, calling an empty srcu
> > notifier chain cost about 19ns per call, vs. 4ns for a blocking notifier
> > chain.  Hm.  Might we actually want regular blocking notifiers?
> 
> Sounds like it.  But what is important is that we really shouldn't
> provide both and punt the decision to the user..

How about this for a commit message:

"Originally, I selected srcu notifiers to implement live hooks because
they seemed to have fewer impacts to scalability.  The per-call cost of
srcu_notifier_call_chain is lower (19ns) than blocking_notifier_ (4ns),
but the latter takes an rwsem.  IIRC, rwsems have scalability problems
when the cpu count gets high due to all the cacheline bouncing and
atomic operations.  I didn't want regular xfs operations to suffer
memory contention on the blocking notifiers for the sake of something
that won't be running most of the time.

"Therefore, I stuck with srcu notifiers, despite trading off single
threaded performance for multithreaded performance.  I wasn't thrilled
with the very high teardown time for srcu notifiers, since the caller
has to wait for the next rcu grace period.

"Then I discovered static branches.

"Now suddenly I had a tool to reduce the pain of a high-contention rwsem
to zero except in the case where scrub is running.  This seemed a lot
better to me -- zero runtime overhead when scrub is not running; low
setup and teardown overhead for scrub; and cacheline bouncing problems
only when there are a lot of threads running through the notifier call
code *and* scrub is running.

"This seems perfect, but static branches aren't supported on all the
architectures that Linux supports.  Further, I haven't really tested the
impacts of scrub on big iron.  This makes me hesitant to get rid of the
SRCU notifier implementation while online fsck is still experimental.

"Note that Kconfig automatically selects the best option for a
particular architecture.  Kernel builders should take the defaults."

I dunno.  Do you want me to rip out the srcu implementation and only
provide the blocking notifiers?  That's easy to do, though hard to undo
once I've done it.

Hmm.  How many arches support static branches today?

$ grep HAVE_ARCH_JUMP_LABEL arch/
arch/arc/Kconfig:52:    select HAVE_ARCH_JUMP_LABEL if ISA_ARCV2 && !CPU_ENDIAN_BE32
arch/arm/Kconfig:77:    select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
arch/arm64/Kconfig:163: select HAVE_ARCH_JUMP_LABEL
arch/arm64/Kconfig:164: select HAVE_ARCH_JUMP_LABEL_RELATIVE
arch/csky/Kconfig:71:   select HAVE_ARCH_JUMP_LABEL if !CPU_CK610
arch/csky/Kconfig:72:   select HAVE_ARCH_JUMP_LABEL_RELATIVE
arch/mips/Kconfig:53:   select HAVE_ARCH_JUMP_LABEL
arch/parisc/Kconfig:60: select HAVE_ARCH_JUMP_LABEL
arch/parisc/Kconfig:61: select HAVE_ARCH_JUMP_LABEL_RELATIVE
arch/powerpc/Kconfig:212:       select HAVE_ARCH_JUMP_LABEL
arch/powerpc/Kconfig:213:       select HAVE_ARCH_JUMP_LABEL_RELATIVE
arch/riscv/Kconfig:96:  select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
arch/riscv/Kconfig:97:  select HAVE_ARCH_JUMP_LABEL_RELATIVE if !XIP_KERNEL
arch/s390/Kconfig:151:  select HAVE_ARCH_JUMP_LABEL
arch/s390/Kconfig:152:  select HAVE_ARCH_JUMP_LABEL_RELATIVE
arch/sparc/Kconfig:31:  select HAVE_ARCH_JUMP_LABEL if SPARC64
arch/x86/Kconfig:176:   select HAVE_ARCH_JUMP_LABEL
arch/x86/Kconfig:177:   select HAVE_ARCH_JUMP_LABEL_RELATIVE
arch/xtensa/Kconfig:33: select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
arch/loongarch/Kconfig:94:      select HAVE_ARCH_JUMP_LABEL
arch/loongarch/Kconfig:95:      select HAVE_ARCH_JUMP_LABEL_RELATIVE

The main arches that xfs really cares about are arm64, ppc64, riscv,
s390x, and x86_64, right?  Perhaps there's a stronger case for only
providing blocking notifiers and jump labels since there aren't many
m68k xfs users, right?

--D

Re: [PATCH 7/7] xfs: iscan batching should handle unallocated inodes too

[Darrick J. Wong]

On Tue, Jan 02, 2024 at 03:40:24AM -0800, Christoph Hellwig wrote:
> Any reason to not just fold this into the previous patch?

It's a performance optimization over the code provided in the previous
patch, so I kept it separate both for bisectability and to preserve the
incremental improvements that I've added to online fsck over the years.

> Otherwise looks good:
> 
> Reviewed-by: Christoph Hellwig <hch@lst.de>

Thanks!

--D

Re: [PATCH 2/9] xfs: encode the default bc_flags in the btree ops structure

[Darrick J. Wong]

On Tue, Jan 02, 2024 at 02:33:34AM -0800, Christoph Hellwig wrote:
> On Sun, Dec 31, 2023 at 12:17:28PM -0800, Darrick J. Wong wrote:
> > From: Darrick J. Wong <djwong@kernel.org>
> > 
> > Certain btree flags never change for the life of a btree cursor because
> > they describe the geometry of the btree itself.  Encode these in the
> > btree ops structure and reduce the amount of code required in each btree
> > type's init_cursor functions.
> 
> I like the idea, but why are the geom_flags mirrored into bc_flags
> instead of beeing kept entirely separate and accessed as
> cur->bc_ops->geom_flags which would be a lot easier to follow?

Oh!  That hadn't occurred to me.  Let me take a look at that.

--D

Re: [PATCH 5/7] xfs: reuse xfs_bmap_update_cancel_item

[Darrick J. Wong]

On Tue, Jan 02, 2024 at 02:45:11AM -0800, Christoph Hellwig wrote:
> On Sun, Dec 31, 2023 at 12:21:38PM -0800, Darrick J. Wong wrote:
> > From: Darrick J. Wong <djwong@kernel.org>
> > 
> > Reuse xfs_bmap_update_cancel_item to put the AG/RTG and free the item in
> > a few places that currently open code the logic.
> > 
> > Inspired-by: Christoph Hellwig <hch@lst.de>
> > Signed-off-by: Darrick J. Wong <djwong@kernel.org>
> 
> Isn't this actually pretty much exactly my patch?

Yeah, but with some non-trivial alterations, so that's why I went with
the tagset presented here.

> Either way this looks (obviously :)) good:
> 
> Reviewed-by: Christoph Hellwig <hch@lst.de>

Thanks!

--D

Re: [PATCHSET v29.0 34/40] xfs_scrub: fixes for systemd services

[Darrick J. Wong]

On Sun, Dec 31, 2023 at 03:25:41PM -0500, Neal Gompa wrote:
> On Sun, Dec 31, 2023 at 2:48 PM Darrick J. Wong <djwong@kernel.org> wrote:
> >
> > Hi all,
> >
> > This series fixes deficiencies in the systemd services that were created
> > to manage background scans.  First, improve the debian packaging so that
> > services get installed at package install time.  Next, fix copyright and
> > spdx header omissions.
> >
> > Finally, fix bugs in the mailer scripts so that scrub failures are
> > reported effectively.  Finally, fix xfs_scrub_all to deal with systemd
> > restarts causing it to think that a scrub has finished before the
> > service actually finishes.
> >
> > If you're going to start using this code, I strongly recommend pulling
> > from my git trees, which are linked below.
> >
> > This has been running on the djcloud for months with no problems.  Enjoy!
> > Comments and questions are, as always, welcome.
> >
> > --D
> >
> > xfsprogs git tree:
> > https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h=scrub-service-fixes
> > ---
> >  debian/rules                     |    1 +
> >  include/builddefs.in             |    2 +-
> >  scrub/Makefile                   |   26 ++++++++++++++------
> >  scrub/xfs_scrub@.service.in      |    6 ++---
> >  scrub/xfs_scrub_all.in           |   49 ++++++++++++++++----------------------
> >  scrub/xfs_scrub_fail.in          |   12 ++++++++-
> >  scrub/xfs_scrub_fail@.service.in |    4 ++-
> >  7 files changed, 55 insertions(+), 45 deletions(-)
> >  rename scrub/{xfs_scrub_fail => xfs_scrub_fail.in} (62%)
> >
> 
> In your Makefile changes, you should be able to drop
> PKG_LIB_SCRIPT_DIR entirely from your Makefiles since it should be
> unused now, can you fold that into
> https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfsprogs-dev.git/commit/?h=scrub-service-fixes&id=1e0dce5c54270f1813f5661c266989917f08baf8
> ?

Already done in:

https://lore.kernel.org/linux-xfs/170405001964.1800712.10514067731814883862.stgit@frogsfrogsfrogs/

Sorry I forgot to cc you there.

--D

> 
> 
> -- 
> 真実はいつも一つ！/ Always, there's only one truth!
> 

Re: [PATCHSET v29.0 34/40] xfs_scrub: fixes for systemd services

[Darrick J. Wong]

On Tue, Jan 02, 2024 at 11:48:04AM +0100, Christoph Hellwig wrote:
> Can we somehow expedite these plumbing fixes for the next xfsprogs
> release instead of just hiding them in the giant patchbomb?

I was planning to do that, though I don't think cem has merged any of
the 4 pull requests I've already sent him for xfsprogs 6.6. :/

(Granted everyone has been on vacation for weeks, myself included, so I
wasn't expecting much progress...)

--D

Re: [PATCH 8/9] xfs_scrub_fail: move executable script to /usr/libexec

[Darrick J. Wong]

On Sun, Dec 31, 2023 at 07:24:04PM -0500, Neal Gompa wrote:
> On Sun, Dec 31, 2023 at 5:54 PM Darrick J. Wong <djwong@kernel.org> wrote:
> >
> > From: Darrick J. Wong <djwong@kernel.org>
> >
> > Per FHS 3.0, non-PATH executable binaries are supposed to live under
> > /usr/libexec, not /usr/lib.  xfs_scrub_fail is an executable script,
> > so move it to libexec in case some distro some day tries to mount
> > /usr/lib as noexec or something.
> >
> > Cc: Neal Gompa <neal@gompa.dev>
> > Link: https://refspecs.linuxfoundation.org/FHS_3.0/fhs/ch04s07.html
> > Signed-off-by: Darrick J. Wong <djwong@kernel.org>
> > ---
> >  include/builddefs.in             |    1 +
> >  scrub/Makefile                   |    7 +++----
> >  scrub/xfs_scrub_fail@.service.in |    2 +-
> >  3 files changed, 5 insertions(+), 5 deletions(-)
> >
> >
> > diff --git a/include/builddefs.in b/include/builddefs.in
> > index eb7f6ba4f03..9d0f9c3bf7c 100644
> > --- a/include/builddefs.in
> > +++ b/include/builddefs.in
> > @@ -52,6 +52,7 @@ PKG_ROOT_SBIN_DIR = @root_sbindir@
> >  PKG_ROOT_LIB_DIR= @root_libdir@@libdirsuffix@
> >  PKG_LIB_DIR    = @libdir@@libdirsuffix@
> >  PKG_LIB_SCRIPT_DIR     = @libdir@
> > +PKG_LIBEXEC_DIR        = @libexecdir@/@pkg_name@
> >  PKG_INC_DIR    = @includedir@/xfs
> >  DK_INC_DIR     = @includedir@/disk
> >  PKG_MAN_DIR    = @mandir@
> > diff --git a/scrub/Makefile b/scrub/Makefile
> > index fd47b893956..8fb366c922c 100644
> > --- a/scrub/Makefile
> > +++ b/scrub/Makefile
> > @@ -140,8 +140,7 @@ install: $(INSTALL_SCRUB)
> >         @echo "    [SED]    $@"
> >         $(Q)$(SED) -e "s|@sbindir@|$(PKG_SBIN_DIR)|g" \
> >                    -e "s|@scrub_args@|$(XFS_SCRUB_ARGS)|g" \
> > -                  -e "s|@pkg_lib_dir@|$(PKG_LIB_SCRIPT_DIR)|g" \
> > -                  -e "s|@pkg_name@|$(PKG_NAME)|g" \
> > +                  -e "s|@pkg_libexec_dir@|$(PKG_LIBEXEC_DIR)|g" \
> >                    < $< > $@
> >
> >  %.cron: %.cron.in $(builddefs)
> > @@ -151,8 +150,8 @@ install: $(INSTALL_SCRUB)
> >  install-systemd: default $(SYSTEMD_SERVICES)
> >         $(INSTALL) -m 755 -d $(SYSTEMD_SYSTEM_UNIT_DIR)
> >         $(INSTALL) -m 644 $(SYSTEMD_SERVICES) $(SYSTEMD_SYSTEM_UNIT_DIR)
> > -       $(INSTALL) -m 755 -d $(PKG_LIB_SCRIPT_DIR)/$(PKG_NAME)
> > -       $(INSTALL) -m 755 $(XFS_SCRUB_FAIL_PROG) $(PKG_LIB_SCRIPT_DIR)/$(PKG_NAME)
> > +       $(INSTALL) -m 755 -d $(PKG_LIBEXEC_DIR)
> > +       $(INSTALL) -m 755 $(XFS_SCRUB_FAIL_PROG) $(PKG_LIBEXEC_DIR)
> >
> >  install-crond: default $(CRONTABS)
> >         $(INSTALL) -m 755 -d $(CROND_DIR)
> > diff --git a/scrub/xfs_scrub_fail@.service.in b/scrub/xfs_scrub_fail@.service.in
> > index 048b5732459..48a0f25b5f1 100644
> > --- a/scrub/xfs_scrub_fail@.service.in
> > +++ b/scrub/xfs_scrub_fail@.service.in
> > @@ -10,7 +10,7 @@ Documentation=man:xfs_scrub(8)
> >  [Service]
> >  Type=oneshot
> >  Environment=EMAIL_ADDR=root
> > -ExecStart=@pkg_lib_dir@/@pkg_name@/xfs_scrub_fail "${EMAIL_ADDR}" %f
> > +ExecStart=@pkg_libexec_dir@/xfs_scrub_fail "${EMAIL_ADDR}" %f
> >  User=mail
> >  Group=mail
> >  SupplementaryGroups=systemd-journal
> >
> 
> Looks great to me.
> 
> Reviewed-by: Neal Gompa <neal@gompa.dev>

Thanks!

--D

> 
> 
> 
> --
> 真実はいつも一つ！/ Always, there's only one truth!
> 

Re: [PATCH 1/9] xfs: dump xfiles for debugging purposes

[Darrick J. Wong]

On Mon, Jan 01, 2024 at 12:02:56AM +0000, Matthew Wilcox wrote:
> On Sun, Dec 31, 2023 at 12:13:49PM -0800, Darrick J. Wong wrote:
> > +	error = xfile_stat(xf, &sb);
> > +	if (error)
> > +		return error;
> > +
> > +	printk(KERN_ALERT "xfile ino 0x%lx isize 0x%llx dump:", inode->i_ino,
> > +			sb.size);
> > +	pflags = memalloc_nofs_save();
> 
> Hm, why?  What makes it a bad idea to call back into the filesysteam at
> this point?

I don't want xfile_dump to invoke direct reclaim which will then call
back into xfs because scrub (or any xfile caller) might already be
holding the an ILOCK.

Granted it's /probably/ redundant since the scrub transaction will have
already memalloc_nofs_save'd.  But as this is a debug function, I
figured it was better to burn an unsigned long to prevent making
problems worse...

> > +			page = shmem_read_mapping_page_gfp(mapping,
> > +					datapos >> PAGE_SHIFT, __GFP_NOWARN);
> 
> This GFP flag looks wrong.  Why can't we use GFP_KERNEL here?

I think that's an omission.

> I'm also not thrilled about the use of page APIs instead of folio APIs,
> but given how long this patchset has been in development, I understand why
> you didn't start out with folio APIs.  It's not a blocker by any means.

Heh.  Yeah, I really wish xfiles had been merged before you started the
folioization instead of adding to legacy code creeping.

> I can come through and convert it later when I decide that it's finally
> time to get rid of shmem_read_mapping_page_gfp(), which is going to take
> a big gulp because it now means touching GPU drivers ...

Hehhehee yep.

--D

Re: [PATCH 9/9] xfs_scrub_all.cron: move to package data directory

[Neal Gompa]

On Tue, Jan 2, 2024 at 8:23 PM Darrick J. Wong <djwong@kernel.org> wrote:
>
> From: Darrick J. Wong <djwong@kernel.org>
>
> cron jobs don't belong in /usr/lib.  Since the cron job is also
> secondary to the systemd timer, it's really only provided as a courtesy
> for distributions that don't use systemd.  Move it to @datadir@, aka
> /usr/share/xfsprogs.
>
> Signed-off-by: Darrick J. Wong <djwong@kernel.org>
> ---
>  include/builddefs.in |    1 -
>  scrub/Makefile       |    2 +-
>  2 files changed, 1 insertion(+), 2 deletions(-)
>
>
> diff --git a/include/builddefs.in b/include/builddefs.in
> index 9d0f9c3bf7c..f5138b5098f 100644
> --- a/include/builddefs.in
> +++ b/include/builddefs.in
> @@ -51,7 +51,6 @@ PKG_SBIN_DIR  = @sbindir@
>  PKG_ROOT_SBIN_DIR = @root_sbindir@
>  PKG_ROOT_LIB_DIR= @root_libdir@@libdirsuffix@
>  PKG_LIB_DIR    = @libdir@@libdirsuffix@
> -PKG_LIB_SCRIPT_DIR     = @libdir@
>  PKG_LIBEXEC_DIR        = @libexecdir@/@pkg_name@
>  PKG_INC_DIR    = @includedir@/xfs
>  DK_INC_DIR     = @includedir@/disk
> diff --git a/scrub/Makefile b/scrub/Makefile
> index 8fb366c922c..472df48a720 100644
> --- a/scrub/Makefile
> +++ b/scrub/Makefile
> @@ -26,7 +26,7 @@ INSTALL_SCRUB += install-crond
>  CRONTABS = xfs_scrub_all.cron
>  OPTIONAL_TARGETS += $(CRONTABS)
>  # Don't enable the crontab by default for now
> -CROND_DIR = $(PKG_LIB_SCRIPT_DIR)/$(PKG_NAME)
> +CROND_DIR = $(PKG_DATA_DIR)
>  endif
>
>  endif  # scrub_prereqs
>
>

Looks good to me.

Reviewed-by: Neal Gompa <neal@gompa.dev>


-- 
真実はいつも一つ！/ Always, there's only one truth!

Re: [PATCH 9/9] xfs: connect in-memory btrees to xfiles

[Darrick J. Wong]

On Mon, Jan 01, 2024 at 12:18:48AM +0000, Matthew Wilcox wrote:
> On Sun, Dec 31, 2023 at 12:15:54PM -0800, Darrick J. Wong wrote:
> > +/* Ensure that there is storage backing the given range. */
> > +int
> > +xfile_prealloc(
> > +	struct xfile		*xf,
> > +	loff_t			pos,
> > +	u64			count)
> > +{
> > +	struct inode		*inode = file_inode(xf->file);
> > +	struct address_space	*mapping = inode->i_mapping;
> > +	const struct address_space_operations *aops = mapping->a_ops;
> > +	struct page		*page = NULL;
> > +	unsigned int		pflags;
> > +	int			error = 0;
> > +
> > +	if (count > MAX_RW_COUNT)
> > +		return -E2BIG;
> > +	if (inode->i_sb->s_maxbytes - pos < count)
> > +		return -EFBIG;
> > +
> > +	trace_xfile_prealloc(xf, pos, count);
> > +
> > +	pflags = memalloc_nofs_save();
> > +	while (count > 0) {
> > +		void		*fsdata = NULL;
> > +		unsigned int	len;
> > +		int		ret;
> > +
> > +		len = min_t(ssize_t, count, PAGE_SIZE - offset_in_page(pos));
> > +
> > +		/*
> > +		 * We call write_begin directly here to avoid all the freezer
> > +		 * protection lock-taking that happens in the normal path.
> > +		 * shmem doesn't support fs freeze, but lockdep doesn't know
> > +		 * that and will trip over that.
> > +		 */
> > +		error = aops->write_begin(NULL, mapping, pos, len, &page,
> > +				&fsdata);
> > +		if (error)
> > +			break;
> > +
> > +		/*
> > +		 * xfile pages must never be mapped into userspace, so we skip
> > +		 * the dcache flush.  If the page is not uptodate, zero it to
> > +		 * ensure we never go lacking for space here.
> > +		 */
> > +		if (!PageUptodate(page)) {
> > +			void	*kaddr = kmap_local_page(page);
> > +
> > +			memset(kaddr, 0, PAGE_SIZE);
> > +			SetPageUptodate(page);
> > +			kunmap_local(kaddr);
> > +		}
> 
> Does the xfiles implementation prevent THPs from being created?
> If not, this could lead to an entire THP being marked uptodate even
> though we've only zeroed one page of it.

No.  How does one prevent THPs from being created for a specific tmpfs
file?  It's probably time you and I burned a 1x1 on straightening out
some of xfile.c's folio-idiocy. ;)

--D

Re: [PATCH 2/4] xfs: define an in-memory btree for storing refcount bag info during repairs

[Darrick J. Wong]

On Tue, Jan 02, 2024 at 02:41:40AM -0800, Christoph Hellwig wrote:
> On Sun, Dec 31, 2023 at 12:19:49PM -0800, Darrick J. Wong wrote:
> > From: Darrick J. Wong <djwong@kernel.org>
> > 
> > Create a new in-memory btree type so that we can store refcount bag info
> > in a much more memory-efficient format.
> 
> Can you add a cursory explanation of what 'bag info' is?  It took me
> quite a while to figure this out by looking at the refcount_repair.c
> file, and future readers or the commit log might be a lot less savy
> in finding that information.  The source file could also really use a
> comment explaining the bag term and what is actually stored in it.

In the original refcount recordset regenerator in xfs_repair, refcount
records are generated from rmap records.  Let's say that the rmap
records are:

{agbno: 10, length: 40...}
{agbno: 11, length: 3...}
{agbno: 12, length: 20...}
{agbno: 15, length: 1...}

It would be convenient to have a data structure that could quickly tell
us the refcount for an arbitrary agbno without wasting memory.  An array
or a list could do that pretty easily.  List suck because of the pointer
overhead.  xfarrays are a lot more compact, but we want to minimize
sparse holes in the xfarray to constrain memory usage.  Maintaining
order isn't critical for correctness, so I created the "rcbag", which is
shorthand for an unordered list of (excerpted) reverse mappings.

So we add the first rmap to the rcbag, and it looks like:

0: {agbno: 10, length: 40}

The refcount for agbno 10 is 1.  Then we move on to block 11, so we add
the second rmap:

0: {agbno: 10, length: 40}
1: {agbno: 11, length: 3}

The refcount for agbno 11 is 2.  We move on to block 12, so we add the
third:

0: {agbno: 10, length: 40}
1: {agbno: 11, length: 3}
2: {agbno: 12, length: 20}

The refcount for agbno 12 and 13 is 3.  We move on to block 14, and
remove the second rmap:

0: {agbno: 10, length: 40}
1: NULL
2: {agbno: 12, length: 20}

The refcount for agbno 14 is 2.  We move on to block 15, and add the
last rmap.  But we don't care where it is and we don't want to expand
the array so we put it in slot 1:

0: {agbno: 10, length: 40}
1: {agbno: 15, length: 1}
2: {agbno: 12, length: 20}

The refcount for block 15 is 3.  Notice how order doesn't matter in this
list?  That's why repair uses an unordered list, or "bag".

That said, adding and removing specific items is now an O(n) operation
because we have no idea where that item might be in the list.  Overall,
the runtime is O(n^2) which is bad.

I realized that I could easily refactor the btree code and reimplement
the refcount bag with an xfbtree.  Adding and removing is now O(log2 n),
so the runtime is at least O(n log2 n), which is much faster.  In the
end, the rcbag becomes a sorted list, but that's merely a detail of the
implementation.  The repair code doesn't care.

(Note: That horrible xfs_db bmap_inflate command can be used to exercise
this sort of rcbag insanity by cranking up refcounts quickly.)

--D

Re: [PATCH 4/4] xfs: port refcount repair to the new refcount bag structure

[Darrick J. Wong]

On Tue, Jan 02, 2024 at 02:43:47AM -0800, Christoph Hellwig wrote:
> On Sun, Dec 31, 2023 at 12:20:20PM -0800, Darrick J. Wong wrote:
> > From: Darrick J. Wong <djwong@kernel.org>
> > 
> > Port the refcount record generating code to use the new refcount bag
> > data structure.
> 
> This could again use some comments on why you're doing that.  My strong
> suspicion is that it will be a lot faster and/or memory efficient, but
> please document this for future readers of the commit logs.

The new implementation is less memory efficient (because now we have
btree headers and internal nodes) but makes it a lot faster.  If I turn
my reply to patch #2 into the commit message, will that work?

--D

Re: [PATCH 4/4] xfs: repair file modes by scanning for a dirent pointing to us

[Darrick J. Wong]

On Tue, Jan 02, 2024 at 02:29:42AM -0800, Christoph Hellwig wrote:
> On Sun, Dec 31, 2023 at 12:07:18PM -0800, Darrick J. Wong wrote:
> > From: Darrick J. Wong <djwong@kernel.org>
> > 
> > An earlier version of this patch ("xfs: repair obviously broken inode
> > modes") tried to reset the di_mode of a file by guessing it from the
> > data fork format and/or data block 0 contents.  Christoph didn't like
> > this approach because it opens the possibility that users could craft a
> > file to look like a directory and trick online repair into turning the
> > mode into S_IFDIR.
> 
> I find the commit message here really weird.  What I want doesn't
> matter.  If what I say makes sense (I hope it does, if it doesn't please
> push back) then we should document thing based on the cross-checked
> facts and assumptions I provided.  If not we should not be doing this
> at at all.

What you said back at [1] makes sense -- user controlled data blocks
should not be used to guess the inode mode.  I yanked that patch and
replaced it with this one, which scans the inodes looking for a dirent
pointing down to the busted inode, and uses that to decide if the busted
file is S_IFDIR.

How about I rephrase the whole commit message like this:

"xfs: repair file modes by scanning for a dirent pointing to us

"Repair might encounter an inode with a totally garbage i_mode.  To fix
this problem, we have to figure out if the file was a regular file, a
directory, or a special file.  One way to figure this out is to check if
there are any directories with entries pointing down to the busted file.

"This patch recovers the file mode by scanning every directory entry on
the filesystem to see if there are any that point to the busted file.
If the ftype of all such dirents are consistent, the mode is recovered
from the ftype.  If no dirents are found, the file becomes a regular
file.  In all cases, ACLs are canceled and the file is made accessible
only by root.

"A previous patch attempted to guess the mode by reading the beginning
of the file data.  This was rejected by Christoph on the grounds that we
cannot trust user-controlled data blocks.  Users do not have direct
control over the ondisk contents of directory links, so this method
should be much safer."

--D

[1] https://lore.kernel.org/linux-xfs/ZXFhuNaLx1C8yYV+@infradead.org/

Re: [PATCH 9/9] xfs: remove unnecessary fields in xfbtree_config

[Darrick J. Wong]

On Tue, Jan 02, 2024 at 02:39:33AM -0800, Christoph Hellwig wrote:
> On Sun, Dec 31, 2023 at 12:19:17PM -0800, Darrick J. Wong wrote:
> > From: Darrick J. Wong <djwong@kernel.org>
> > 
> > Remove these fields now that we get all the info we need from the btree
> > ops.
> 
> It would be great if this series could just be moved forwared to before
> adding xfbtree_config so that it wouldn't need adding in the first
> place?

I can look into that, but jumping this series ahead by 15 patches might
be a lot of work.

> Otherwise looks good:
> 
> Reviewed-by: Christoph Hellwig <hch@lst.de>

Thanks!

--D

Re: [PATCH 4/7] xfs: allow blocking notifier chains with filesystem hooks

[Christoph Hellwig]

On Tue, Jan 02, 2024 at 05:07:47PM -0800, Darrick J. Wong wrote:
> The main arches that xfs really cares about are arm64, ppc64, riscv,
> s390x, and x86_64, right?  Perhaps there's a stronger case for only
> providing blocking notifiers and jump labels since there aren't many
> m68k xfs users, right?

Yes.  And if there are m68k xfs users, they are even more unlikely to run
with online repair enabled as they'd be very memory constrained.

So I suspect always using blocking notifiers would be best to keep
the complexity down.  In fact I suspect we should simply make online
repair depend on jump labels instead of selecting it when available
to remove anoher rarely tested build combination.

Re: [PATCH 4/4] xfs: repair file modes by scanning for a dirent pointing to us

[Christoph Hellwig]

With the updated commit message:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 9/9] xfs: remove unnecessary fields in xfbtree_config

[Christoph Hellwig]

On Tue, Jan 02, 2024 at 06:51:59PM -0800, Darrick J. Wong wrote:
> I can look into that, but jumping this series ahead by 15 patches might
> be a lot of work.

Skip it if it's too much work.

Re: [PATCH 1/1] xfs: map xfile pages directly into xfs_buf

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 02:35:23PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Map the xfile pages directly into xfs_buf to reduce memory overhead.
> It's silly to use memory to stage changes to shmem pages for ephemeral
> btrees that don't care about transactionality.

Looking at the users if seems like this is in fact the online use
case - PAGE_SIZE sized btree blocks, which by nature of coming from
shmem must be aligned.  So I'd suggest we remove the non-mapped
file path and just always use this one with sufficient sanity checks
to trip over early if that assumption doesn't hold true.

The users also alway just has a single map per buffer, and a single
page per buffer so it really shouldn't support anything else.

Writing it directly to shmemfs will probably simply things as well
as it just needs to do a shmem_read_mapping_page_gfp to read the one
page per buffer, and then a set_page_dirty on the locked page when
releasing it.

Talking about relasing it:  this now gets us back to the old pagebuf
problem of competing LRUs, one for the xfs_buf, and then anothr for
the shmemfs page in the page cache.  I suspect not putting the shmemfs
backed buffers onto the LRU at all might be a good thing, but that
requires careful benchmarking.

Re: [PATCH 1/1] xfs: map xfile pages directly into xfs_buf

[Christoph Hellwig]

This comment should have been for the kernel version and not the
userspace artefact patch.

Re: [PATCH 2/3] xfs: use b_offset to support direct-mapping pages when blocksize < pagesize

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 12:40:24PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Support using directly-mapped pages in the buffer cache when the fs
> blocksize is less than the page size.  This is not strictly necessary
> since the only user of direct-map buffers always uses page-sized
> buffers, but I included it here for completeness.

As mentioned on the main shmem mapping patch - let's not add code
that is guaranteed to be unused.

Re: [PATCH 3/3] xfile: implement write caching

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 12:40:40PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Mapping a page into the kernel's address space is expensive.

What do you mean with mapping into the kernel's address space?

Mormally that owuld point to the kmap* family of helpers, but those
are complete no-ops on the typical xfs setups without highmem.  But
even with highmem at least kmap_local_page isn't too expensive.

My xfile diet patches actually change the xfile mapping to never
allocate highmem, which simplifies things a bit (and fixes a bug
in the xfs_buf use that just uses page_address instead of a kmap).

So I suspect this is something else and more about looking up pages?

Re: [PATCH 1/9] xfs: dump xfiles for debugging purposes

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 12:13:49PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Add a debug function to dump an xfile's contents for debug purposes.

This doesn't actually seem to ever get used in the entire patch bomb.

Re: [PATCH 3/9] xfs: create buftarg helpers to abstract block_device operations

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 12:14:20PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> In the next few patches, we're going into introduce buffer targets that
> are not block devices.  Introduce block_device helpers so that the
> compiler can check that we're not feeding an xfile object to something
> expecting a block device.

I don't see how these helpers allow the compiler to check anything.
I also don't see any other good reason for the helpers, but maybe I'm
just missing something.

Re: [PATCH 4/9] xfs: make GFP_ usage consistent when allocating buftargs

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 6/9] xfs: consolidate btree block freeing tracepoints

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 12:15:07PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Don't waste tracepoint segment memory on per-btree block freeing
> tracepoints when we can do it from the generic btree code.

The patch looks good, but what is "tracepoint segment memory"?

Re: [PATCH 4/7] xfs: allow blocking notifier chains with filesystem hooks

[Darrick J. Wong]

On Tue, Jan 02, 2024 at 11:37:41PM -0800, Christoph Hellwig wrote:
> On Tue, Jan 02, 2024 at 05:07:47PM -0800, Darrick J. Wong wrote:
> > The main arches that xfs really cares about are arm64, ppc64, riscv,
> > s390x, and x86_64, right?  Perhaps there's a stronger case for only
> > providing blocking notifiers and jump labels since there aren't many
> > m68k xfs users, right?
> 
> Yes.  And if there are m68k xfs users, they are even more unlikely to run
> with online repair enabled as they'd be very memory constrained.
> 
> So I suspect always using blocking notifiers would be best to keep
> the complexity down.  In fact I suspect we should simply make online
> repair depend on jump labels instead of selecting it when available
> to remove anoher rarely tested build combination.

Later on in the online fsck patch series, scrub will start using
LIVE_HOOKS for some of its scanning functionality.  I don't know that
anyone will really want to use online fsck on weird old systems like you
said, but while it's EXPERIMENTAL I don't want to lose the option
entirely.

That said, static branches do have a fallback for !HAVE_ARCH_JUMP_LABEL
case, which is raw_atomic_read.

I'll get rid of the srcu notifier chain xfs_hook implementation to
reduce the complexity within xfs.  Online fsck will always use static
branches + blocking rwsem notifiers.  For modern arches like x64 there
will be almost zero runtime cost due to the nop sled.  For m68k and
friends, they can kick the tires on xfs_scrub, but if the performance
sucks due to the READ_ONCE then oh well.

--D

Re: [PATCH 3/9] xfs: create buftarg helpers to abstract block_device operations

[Darrick J. Wong]

On Wed, Jan 03, 2024 at 12:51:55AM -0800, Christoph Hellwig wrote:
> On Sun, Dec 31, 2023 at 12:14:20PM -0800, Darrick J. Wong wrote:
> > From: Darrick J. Wong <djwong@kernel.org>
> > 
> > In the next few patches, we're going into introduce buffer targets that
> > are not block devices.  Introduce block_device helpers so that the
> > compiler can check that we're not feeding an xfile object to something
> > expecting a block device.
> 
> I don't see how these helpers allow the compiler to check anything.
> I also don't see any other good reason for the helpers, but maybe I'm
> just missing something.

Oh, right -- originally, this patch made struct xfs_buftarg do this:

struct xfs_buftarg {
	dev_t			bt_dev;
	union {
		struct block_device	*bt_bdev;
		struct xfile		*bt_xfile;
	};
	struct dax_device	*bt_daxdev;

Dereferencing bt_bdev/bt_xfile was controlled through a buftarg flag.
IOWs, it employed the tagged union pattern.

When bt_bdev_handle came about, I gave up on the tagged union and simply
added another pointer to struct xfs_buftarg.  There aren't that many of
them floating around in the system, so the extra 8 bytes isn't a giant
drain on resources.

struct xfs_buftarg {
	dev_t			bt_dev;
	struct bdev_handle	*bt_bdev_handle;
	struct block_device	*bt_bdev;
	struct dax_device	*bt_daxdev;
	struct xfile		*bt_xfile;

Now we don't need these wrappers since we can't accidentally dereference
bt_xfile as a struct block_device.  I'll drop this one.

--D

Re: [PATCH 3/9] xfs: create buftarg helpers to abstract block_device operations

[Christoph Hellwig]

On Wed, Jan 03, 2024 at 11:26:35AM -0800, Darrick J. Wong wrote:
> Now we don't need these wrappers since we can't accidentally dereference
> bt_xfile as a struct block_device.  I'll drop this one.

And Christian posted a ptch to make the bdev_handle a file, so we might
end up using files a lot more here :)

Re: [PATCH 6/9] xfs: consolidate btree block freeing tracepoints

[Darrick J. Wong]

On Wed, Jan 03, 2024 at 12:53:17AM -0800, Christoph Hellwig wrote:
> On Sun, Dec 31, 2023 at 12:15:07PM -0800, Darrick J. Wong wrote:
> > From: Darrick J. Wong <djwong@kernel.org>
> > 
> > Don't waste tracepoint segment memory on per-btree block freeing
> > tracepoints when we can do it from the generic btree code.
> 
> The patch looks good, but what is "tracepoint segment memory"?

The size of the ELF segments where the ftrace strings/code/etc are
stored.  With this and the next patch applied, the output of:

$ objdump -x fs/xfs/xfs.ko | grep tracepoint

Before:

 10 __tracepoints_ptrs 00000b38  0000000000000000  0000000000000000  001418b0  2**2
 14 __tracepoints_strings 00005433  0000000000000000  0000000000000000  00168f60  2**5
 29 __tracepoints 00010d30  0000000000000000  0000000000000000  00240080  2**5

After:

 10 __tracepoints_ptrs 00000b30  0000000000000000  0000000000000000  00142170  2**2
 14 __tracepoints_strings 000053f3  0000000000000000  0000000000000000  00169860  2**5
 29 __tracepoints 00010c70  0000000000000000  0000000000000000  00241180  2**5

Removing these two tracepoints reduces the size of the ELF segments by
264 bytes.  I'll add this note to the commit message.

--D

Re: [PATCH 2/9] xfs: encode the default bc_flags in the btree ops structure

[Darrick J. Wong]

On Tue, Jan 02, 2024 at 05:15:11PM -0800, Darrick J. Wong wrote:
> On Tue, Jan 02, 2024 at 02:33:34AM -0800, Christoph Hellwig wrote:
> > On Sun, Dec 31, 2023 at 12:17:28PM -0800, Darrick J. Wong wrote:
> > > From: Darrick J. Wong <djwong@kernel.org>
> > > 
> > > Certain btree flags never change for the life of a btree cursor because
> > > they describe the geometry of the btree itself.  Encode these in the
> > > btree ops structure and reduce the amount of code required in each btree
> > > type's init_cursor functions.
> > 
> > I like the idea, but why are the geom_flags mirrored into bc_flags
> > instead of beeing kept entirely separate and accessed as
> > cur->bc_ops->geom_flags which would be a lot easier to follow?
> 
> Oh!  That hadn't occurred to me.  Let me take a look at that.

Eeeeyugh, this became kind of a mess.  These XFS_BTREE_ flags describe
btree geometry, are set in the bc_ops->geom_flags, and never change:

1. XFS_BTREE_LONG_PTRS
2. XFS_BTREE_ROOT_IN_INODE
3. XFS_BTREE_IROOT_RECORDS		/* rt rmap patchset */
4. XFS_BTREE_IN_XFILE
5. XFS_BTREE_OVERLAPPING

This one flag describes geometry but is set dynamically by
xfs_btree_alloc_cursor.  Some of the geom_flags (rmap, refcount) can set
it directly too, since they don't exist in V4 filesystems:

6. XFS_BTREE_CRC_BLOCKS

This one flag doesn't describe btree geometry but never changes and
could be set in bc_ops->geom_flags:

7. XFS_BTREE_LASTREC_UPDATE

The remaining flag actually describes per-cursor state:

8. XFS_BTREE_STAGING

Flags 1-5 can be referenced directly from geom_flags.

Flag 6 could be replaced by an xfs_has_crc call, though I'd bet it's
cheaper to test a cursor variable than to walk to the xfs_mount and
test_bit.  But this feels weird.

Flag 7 is set in geom_flags as it should be.

Flag 8 is really a runtime flag, so it can stay in bc_flags.

*or* I could rename geom_flags to default_bcflags and make it clearer
that it's used to seed cur->bc_flags?

--D

Re: [PATCH 2/9] xfs: encode the default bc_flags in the btree ops structure

[Darrick J. Wong]

On Wed, Jan 03, 2024 at 11:58:26AM -0800, Darrick J. Wong wrote:
> On Tue, Jan 02, 2024 at 05:15:11PM -0800, Darrick J. Wong wrote:
> > On Tue, Jan 02, 2024 at 02:33:34AM -0800, Christoph Hellwig wrote:
> > > On Sun, Dec 31, 2023 at 12:17:28PM -0800, Darrick J. Wong wrote:
> > > > From: Darrick J. Wong <djwong@kernel.org>
> > > > 
> > > > Certain btree flags never change for the life of a btree cursor because
> > > > they describe the geometry of the btree itself.  Encode these in the
> > > > btree ops structure and reduce the amount of code required in each btree
> > > > type's init_cursor functions.
> > > 
> > > I like the idea, but why are the geom_flags mirrored into bc_flags
> > > instead of beeing kept entirely separate and accessed as
> > > cur->bc_ops->geom_flags which would be a lot easier to follow?
> > 
> > Oh!  That hadn't occurred to me.  Let me take a look at that.
> 
> Eeeeyugh, this became kind of a mess.  These XFS_BTREE_ flags describe
> btree geometry, are set in the bc_ops->geom_flags, and never change:
> 
> 1. XFS_BTREE_LONG_PTRS
> 2. XFS_BTREE_ROOT_IN_INODE
> 3. XFS_BTREE_IROOT_RECORDS		/* rt rmap patchset */
> 4. XFS_BTREE_IN_XFILE
> 5. XFS_BTREE_OVERLAPPING
> 
> This one flag describes geometry but is set dynamically by
> xfs_btree_alloc_cursor.  Some of the geom_flags (rmap, refcount) can set
> it directly too, since they don't exist in V4 filesystems:
> 
> 6. XFS_BTREE_CRC_BLOCKS
> 
> This one flag doesn't describe btree geometry but never changes and
> could be set in bc_ops->geom_flags:
> 
> 7. XFS_BTREE_LASTREC_UPDATE
> 
> The remaining flag actually describes per-cursor state:
> 
> 8. XFS_BTREE_STAGING
> 
> Flags 1-5 can be referenced directly from geom_flags.
> 
> Flag 6 could be replaced by an xfs_has_crc call, though I'd bet it's
> cheaper to test a cursor variable than to walk to the xfs_mount and
> test_bit.  But this feels weird.
> 
> Flag 7 is set in geom_flags as it should be.
> 
> Flag 8 is really a runtime flag, so it can stay in bc_flags.
> 
> *or* I could rename geom_flags to default_bcflags and make it clearer
> that it's used to seed cur->bc_flags?

*or* I could define a separate struct xfs_btree_ops for the
bnobt/cntbt/inobt/bmbt for V4 filesystems.

--D

> 
> --D
> 

Re: [PATCH 2/9] xfs: encode the default bc_flags in the btree ops structure

[Christoph Hellwig]

On Wed, Jan 03, 2024 at 12:00:50PM -0800, Darrick J. Wong wrote:
> *or* I could define a separate struct xfs_btree_ops for the
> bnobt/cntbt/inobt/bmbt for V4 filesystems.

That actually sounds nice, and might allow for some pre-calculation
of maxrec/minxrec eventually.

Re: [PATCH 2/3] xfs: use b_offset to support direct-mapping pages when blocksize < pagesize

[Darrick J. Wong]

On Wed, Jan 03, 2024 at 12:45:48AM -0800, Christoph Hellwig wrote:
> On Sun, Dec 31, 2023 at 12:40:24PM -0800, Darrick J. Wong wrote:
> > From: Darrick J. Wong <djwong@kernel.org>
> > 
> > Support using directly-mapped pages in the buffer cache when the fs
> > blocksize is less than the page size.  This is not strictly necessary
> > since the only user of direct-map buffers always uses page-sized
> > buffers, but I included it here for completeness.
> 
> As mentioned on the main shmem mapping patch - let's not add code
> that is guaranteed to be unused.

Ok.  I'll drop this one then.

--D

Re: [PATCH 3/3] xfile: implement write caching

[Darrick J. Wong]

On Wed, Jan 03, 2024 at 12:48:21AM -0800, Christoph Hellwig wrote:
> On Sun, Dec 31, 2023 at 12:40:40PM -0800, Darrick J. Wong wrote:
> > From: Darrick J. Wong <djwong@kernel.org>
> > 
> > Mapping a page into the kernel's address space is expensive.
> 
> What do you mean with mapping into the kernel's address space?
> 
> Mormally that owuld point to the kmap* family of helpers, but those
> are complete no-ops on the typical xfs setups without highmem.  But
> even with highmem at least kmap_local_page isn't too expensive.
> 
> My xfile diet patches actually change the xfile mapping to never
> allocate highmem, which simplifies things a bit (and fixes a bug
> in the xfs_buf use that just uses page_address instead of a kmap).
> 
> So I suspect this is something else and more about looking up pages?

Sort of both.  For xfbtrees (or anything mapping a xfs_buftarg atop an
xfile) we can't use the cheap(er) kmap_local_page and have to use kmap,
which ... is expensive, isn't it?

Granted, forbidding highmem like you posted today makes all of this
/much/ simpler so I think it's probably worth the increased chances of
ENOMEM on i386.

That said, why not avoid a trip through shmem_get_folio_gfp aka
filemap_get_entry if we can?  Even if we can use page_address directly
now?

--D

Re: [PATCH 6/9] xfs: consolidate btree block freeing tracepoints

[Christoph Hellwig]

On Wed, Jan 03, 2024 at 11:37:05AM -0800, Darrick J. Wong wrote:
> Removing these two tracepoints reduces the size of the ELF segments by
> 264 bytes.  I'll add this note to the commit message.

Yeah.  Maybe just say memory usage - segment size feels awfully specific
to an implementation detail.

Re: [PATCH 3/3] xfile: implement write caching

[Christoph Hellwig]

On Wed, Jan 03, 2024 at 05:33:56PM -0800, Darrick J. Wong wrote:
> Sort of both.  For xfbtrees (or anything mapping a xfs_buftarg atop an
> xfile) we can't use the cheap(er) kmap_local_page and have to use kmap,
> which ... is expensive, isn't it?

A little, but not really enough to explain the numbers you quoted..

> Granted, forbidding highmem like you posted today makes all of this
> /much/ simpler so I think it's probably worth the increased chances of
> ENOMEM on i386.
> 
> That said, why not avoid a trip through shmem_get_folio_gfp aka
> filemap_get_entry if we can?  Even if we can use page_address directly
> now?

Sure, I just suspect the commit message is wrong and it's not about
mapping the page into the kernel address space but something else.

Re: [PATCH 8/9] xfs: support in-memory btrees

[Christoph Hellwig]

> -	if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS) && cur->bc_ag.pag)
> +	if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS) &&
> +	    !(cur->bc_flags & XFS_BTREE_IN_XFILE) && cur->bc_ag.pag)
>  		xfs_perag_put(cur->bc_ag.pag);
> +	if (cur->bc_flags & XFS_BTREE_IN_XFILE) {
> +		if (cur->bc_mem.pag)
> +			xfs_perag_put(cur->bc_mem.pag);
> +	}

Btw, one thing I noticed is that we have a lot of confusion on what
part of the bc_ino/ag/mem union is used for a given btree.  For
On-disk inodes we abuse the long ptrs flag, and then we through in
the xfile flags.  If you're fine with it I can try to sort it out.
It's not really a blocker, but I think it would be a lot claner if
we used the chance to sort it out.  This will become even more
important with the rt rmap/reflink trees that will further increase
the confusion here.

> +	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
> +		return xfbtree_bbsize();
> +	return cur->bc_mp->m_bsize;
> +}

One thing I've been wondering is if we should split
a strut xfs_btree outof struct xfbtree that contains most of the
fields from it minuts the space allocation (and the new fake header
from my patches) and also use that for the on-disk btrees.

That means xfs_btree.c can use the target from it, and the owner
and we can remove the indirect calls for calculcating maxrecs/minrecs,
and then also add a field for the block size like this one and remove
a lof of the XFS_BTREE_IN_XFILE checks.

> +	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
> +		return 0;
> +
>  	if ((lr & XFS_BTCUR_LEFTRA) && left != NULLFSBLOCK) {
>  		xfs_btree_reada_bufl(cur->bc_mp, left, 1,

Should the xfile check go into  xfs_buf_readahead instead?  That would
execute a little more useles code for in-memory btrees, but keep this
check in one place (where we could also write a nice comment explaining
it :))

> +	xfs_btree_buf_to_ptr(cur, bp, &bufptr);
>  	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
> -		if (be64_to_cpu(rptr.l) == XFS_DADDR_TO_FSB(cur->bc_mp,
> -							xfs_buf_daddr(bp))) {
> +		if (rptr.l == bufptr.l) {
>  			xfs_btree_mark_sick(cur);
>  			return -EFSCORRUPTED;
>  		}
>  	} else {
> -		if (be32_to_cpu(rptr.s) == xfs_daddr_to_agbno(cur->bc_mp,
> -							xfs_buf_daddr(bp))) {
> +		if (rptr.s == bufptr.s) {

This almost screams for a xfs_btree_ptr_cmp helper, even if this
seems to be the only user so far..

> +static inline loff_t xfile_size(struct xfile *xf)
> +{
> +	return i_size_read(file_inode(xf->file));
> +}

Despite looking over the whole patch for a while I only noticed
this one, and I think I could add it in my xfile diet series
instea dof open coding it in trace.h.

In general it would be really nice to split out patches that add
infrastructure in other parts of the XFS codebase to make them stick
out a bit more.

> +/* file block (aka system page size) to basic block conversions. */
> +typedef unsigned long long	xfileoff_t;
> +#define XFB_BLOCKSIZE		(PAGE_SIZE)
> +#define XFB_BSHIFT		(PAGE_SHIFT)
> +#define XFB_SHIFT		(XFB_BSHIFT - BBSHIFT)
> +
> +static inline loff_t xfo_to_b(xfileoff_t xfoff)
> +{
> +	return xfoff << XFB_BSHIFT;
> +}

...

xfile.h feels like the wrong place for this - the encoding only really
makes sense fo the xfbtree.  And in a way it feels redundant over
just using pgoff_t and the PAGE_* constants directly which should be
pretty obvious to everyone knowning the Linux MM and page cache APIs.

> +/* Return the number of sectors for a buffer target. */
> +xfs_daddr_t
> +xfs_buftarg_nr_sectors(
> +	struct xfs_buftarg	*btp)
> +{
> +	if (btp->bt_flags & XFS_BUFTARG_XFILE)
> +		return xfile_buftarg_nr_sectors(btp);

If we didn't add an ifdef around the struct xfile definition, this could
just be open coded and rely on the compiler eliminating dead code when
XFS_BUFTARG_XFILE isn't defined.

Re: [PATCH 9/9] xfs: connect in-memory btrees to xfiles

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 12:15:54PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Add to our stubbed-out in-memory btrees the ability to connect them with
> an actual in-memory backing file (aka xfiles) and the necessary pieces
> to track free space in the xfile and flush dirty xfbtree buffers on
> demand, which we'll need for online repair.

I guess this is is split from the last patch because of the size of
the changes?   Because it feels they relong belong together.  Maybe with
my patches for the diet and splitting out the new helpers outside the
btree code these could now become a single commit?

> +#ifdef CONFIG_XFS_BTREE_IN_XFILE
> +static inline unsigned long
> +xfbtree_ino(
> +	struct xfbtree		*xfbt)
> +{
> +	return file_inode(xfbt->target->bt_xfile->file)->i_ino;
> +}
> +#endif /* CONFIG_XFS_BTREE_IN_XFILE */

This should probably move to xfile.h?

> +	/* Make sure we actually can write to the block before we return it. */
> +	pos = xfo_to_b(bt_xfoff);
> +	error = xfile_prealloc(xfbtree_xfile(xfbt), pos, xfo_to_b(1));
> +	if (error)
> +		return error;

IFF we stick to always backing the buffers directly by the shmem
pages this won't be needed - the btree code does a buf_get right after
calling into ->alloc_blocks that will allocate the page.

> +int
> +xfbtree_free_block(
> +	struct xfs_btree_cur	*cur,
> +	struct xfs_buf		*bp)
> +{
> +	struct xfbtree		*xfbt = cur->bc_mem.xfbtree;
> +	xfileoff_t		bt_xfoff, bt_xflen;
> +
> +	ASSERT(cur->bc_flags & XFS_BTREE_IN_XFILE);
> +
> +	bt_xfoff = xfs_daddr_to_xfot(xfs_buf_daddr(bp));
> +	bt_xflen = xfs_daddr_to_xfot(bp->b_length);
> +
> +	trace_xfbtree_free_block(xfbt, cur, bt_xfoff);
> +
> +	return xfboff_bitmap_set(&xfbt->freespace, bt_xfoff, bt_xflen);

Any reason this doesn't actually remove the page from shmem?

> +int
> +xfbtree_trans_commit(
> +	struct xfbtree		*xfbt,
> +	struct xfs_trans	*tp)
> +{
> +	LIST_HEAD(buffer_list);
> +	struct xfs_log_item	*lip, *n;
> +	bool			corrupt = false;
> +	bool			tp_dirty = false;

Can we have some sort of flag on the xfs_trans structure that marks it
as fake for xfbtree, and assert it gets fed here, and add ansother
assert it desn't get fed to xfs_trans_commit/cancel?

> +/* Discard pages backing a range of the xfile. */
> +void
> +xfile_discard(
> +	struct xfile		*xf,
> +	loff_t			pos,
> +	u64			count)
> +{
> +	trace_xfile_discard(xf, pos, count);
> +	shmem_truncate_range(file_inode(xf->file), pos, pos + count - 1);
> +}

This doesn't end up being used.

> +/* Ensure that there is storage backing the given range. */
> +int
> +xfile_prealloc(
> +	struct xfile		*xf,
> +	loff_t			pos,
> +	u64			count)

If we end up needing this somewhere else in the end (and it really
should be a separate patch), we should be able to replace it with
a simple xfile_get_page/xfile_put_page pair.

Re: [PATCH 6/9] xfs: consolidate btree block freeing tracepoints

[Darrick J. Wong]

On Wed, Jan 03, 2024 at 10:19:29PM -0800, Christoph Hellwig wrote:
> On Wed, Jan 03, 2024 at 11:37:05AM -0800, Darrick J. Wong wrote:
> > Removing these two tracepoints reduces the size of the ELF segments by
> > 264 bytes.  I'll add this note to the commit message.
> 
> Yeah.  Maybe just say memory usage - segment size feels awfully specific
> to an implementation detail.

Done.

--D

Re: [PATCH 3/3] xfile: implement write caching

[Darrick J. Wong]

On Wed, Jan 03, 2024 at 10:20:34PM -0800, Christoph Hellwig wrote:
> On Wed, Jan 03, 2024 at 05:33:56PM -0800, Darrick J. Wong wrote:
> > Sort of both.  For xfbtrees (or anything mapping a xfs_buftarg atop an
> > xfile) we can't use the cheap(er) kmap_local_page and have to use kmap,
> > which ... is expensive, isn't it?
> 
> A little, but not really enough to explain the numbers you quoted..
> 
> > Granted, forbidding highmem like you posted today makes all of this
> > /much/ simpler so I think it's probably worth the increased chances of
> > ENOMEM on i386.
> > 
> > That said, why not avoid a trip through shmem_get_folio_gfp aka
> > filemap_get_entry if we can?  Even if we can use page_address directly
> > now?
> 
> Sure, I just suspect the commit message is wrong and it's not about
> mapping the page into the kernel address space but something else.

Yeah, I only did A/B testing of before and after this patch, so it's
quite plausible that it's the lookup that's slowing us down.

"xfile: implement write caching

"Cache a few of the most recently used pages in the hopes of saving
ourselves a few trips through shmem_get_folio_gfp.  There's enough time
savings to shave a few percent off the runtime of fstests with online
fsck enabled."

How about that?  I guess I could modify this patch in djwong-wtf not to
cache kmappings and retest, but that seems like a lot for a patch that
is pretty simple after it goes on a diet. :)

--D

Re: [PATCH 8/9] xfs: support in-memory btrees

[Darrick J. Wong]

On Wed, Jan 03, 2024 at 10:47:46PM -0800, Christoph Hellwig wrote:
> > -	if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS) && cur->bc_ag.pag)
> > +	if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS) &&
> > +	    !(cur->bc_flags & XFS_BTREE_IN_XFILE) && cur->bc_ag.pag)
> >  		xfs_perag_put(cur->bc_ag.pag);
> > +	if (cur->bc_flags & XFS_BTREE_IN_XFILE) {
> > +		if (cur->bc_mem.pag)
> > +			xfs_perag_put(cur->bc_mem.pag);
> > +	}
> 
> Btw, one thing I noticed is that we have a lot of confusion on what
> part of the bc_ino/ag/mem union is used for a given btree.  For
> On-disk inodes we abuse the long ptrs flag, and then we through in
> the xfile flags.  If you're fine with it I can try to sort it out.
> It's not really a blocker, but I think it would be a lot claner if
> we used the chance to sort it out.  This will become even more
> important with the rt rmap/reflink trees that will further increase
> the confusion here.

Go for it! :)

> > +	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
> > +		return xfbtree_bbsize();
> > +	return cur->bc_mp->m_bsize;
> > +}
> 
> One thing I've been wondering is if we should split
> a strut xfs_btree outof struct xfbtree that contains most of the
> fields from it minuts the space allocation (and the new fake header
> from my patches) and also use that for the on-disk btrees.
> 
> That means xfs_btree.c can use the target from it, and the owner
> and we can remove the indirect calls for calculcating maxrecs/minrecs,
> and then also add a field for the block size like this one and remove
> a lof of the XFS_BTREE_IN_XFILE checks.

Sounds like a good idea.

> > +	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
> > +		return 0;
> > +
> >  	if ((lr & XFS_BTCUR_LEFTRA) && left != NULLFSBLOCK) {
> >  		xfs_btree_reada_bufl(cur->bc_mp, left, 1,
> 
> Should the xfile check go into  xfs_buf_readahead instead?  That would
> execute a little more useles code for in-memory btrees, but keep this
> check in one place (where we could also write a nice comment explaining
> it :))

Sure, why not?  It's too bad that readahead to an xfile can't
asynchronously call xfile_get_page; maybe we wouldn't need so much
caching.

> > +	xfs_btree_buf_to_ptr(cur, bp, &bufptr);
> >  	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
> > -		if (be64_to_cpu(rptr.l) == XFS_DADDR_TO_FSB(cur->bc_mp,
> > -							xfs_buf_daddr(bp))) {
> > +		if (rptr.l == bufptr.l) {
> >  			xfs_btree_mark_sick(cur);
> >  			return -EFSCORRUPTED;
> >  		}
> >  	} else {
> > -		if (be32_to_cpu(rptr.s) == xfs_daddr_to_agbno(cur->bc_mp,
> > -							xfs_buf_daddr(bp))) {
> > +		if (rptr.s == bufptr.s) {
> 
> This almost screams for a xfs_btree_ptr_cmp helper, even if this
> seems to be the only user so far..

<nod>

> > +static inline loff_t xfile_size(struct xfile *xf)
> > +{
> > +	return i_size_read(file_inode(xf->file));
> > +}
> 
> Despite looking over the whole patch for a while I only noticed
> this one, and I think I could add it in my xfile diet series
> instea dof open coding it in trace.h.
> 
> In general it would be really nice to split out patches that add
> infrastructure in other parts of the XFS codebase to make them stick
> out a bit more.

<nod>

> > +/* file block (aka system page size) to basic block conversions. */
> > +typedef unsigned long long	xfileoff_t;
> > +#define XFB_BLOCKSIZE		(PAGE_SIZE)
> > +#define XFB_BSHIFT		(PAGE_SHIFT)
> > +#define XFB_SHIFT		(XFB_BSHIFT - BBSHIFT)
> > +
> > +static inline loff_t xfo_to_b(xfileoff_t xfoff)
> > +{
> > +	return xfoff << XFB_BSHIFT;
> > +}
> 
> ...
> 
> xfile.h feels like the wrong place for this - the encoding only really
> makes sense fo the xfbtree.  And in a way it feels redundant over
> just using pgoff_t and the PAGE_* constants directly which should be
> pretty obvious to everyone knowning the Linux MM and page cache APIs.

Especially if it ends up in the xfs_btree stub object that you were
talking about above.  Just be careful not to make the userspace xfile.c
and xfbtree.c too weird -- some of the quirky apis here are a result of
me trying to keep things similar between kernel and xfsprogs.

(and the userspace xfile is weird because we're constrained by the size
of the fd table and hence have to partition memfds)

> > +/* Return the number of sectors for a buffer target. */
> > +xfs_daddr_t
> > +xfs_buftarg_nr_sectors(
> > +	struct xfs_buftarg	*btp)
> > +{
> > +	if (btp->bt_flags & XFS_BUFTARG_XFILE)
> > +		return xfile_buftarg_nr_sectors(btp);
> 
> If we didn't add an ifdef around the struct xfile definition, this could
> just be open coded and rely on the compiler eliminating dead code when
> XFS_BUFTARG_XFILE isn't defined.

Ok.

--D

Re: [PATCH 3/3] xfile: implement write caching

[Christoph Hellwig]

On Wed, Jan 03, 2024 at 11:20:50PM -0800, Darrick J. Wong wrote:
> > Sure, I just suspect the commit message is wrong and it's not about
> > mapping the page into the kernel address space but something else.
> 
> Yeah, I only did A/B testing of before and after this patch, so it's
> quite plausible that it's the lookup that's slowing us down.

Can we re-rerun the test once the pending xfile changes are in?
I'd be kinda surprised if the fairly simply xarray lookup for the
page is so expensive.  If it is the patch is a good bandaid for that,
I'd just like to ensure it actually is still needed.

Re: [PATCH 8/9] xfs: support in-memory btrees

[Christoph Hellwig]

On Wed, Jan 03, 2024 at 11:27:52PM -0800, Darrick J. Wong wrote:
> > Btw, one thing I noticed is that we have a lot of confusion on what
> > part of the bc_ino/ag/mem union is used for a given btree.  For
> > On-disk inodes we abuse the long ptrs flag, and then we through in
> > the xfile flags.  If you're fine with it I can try to sort it out.
> > It's not really a blocker, but I think it would be a lot claner if
> > we used the chance to sort it out.  This will become even more
> > important with the rt rmap/reflink trees that will further increase
> > the confusion here.
> 
> Go for it! :)

Happy to do it you don't complain about all the rebase pain it'll
cause..

> > That means xfs_btree.c can use the target from it, and the owner
> > and we can remove the indirect calls for calculcating maxrecs/minrecs,
> > and then also add a field for the block size like this one and remove
> > a lof of the XFS_BTREE_IN_XFILE checks.
> 
> Sounds like a good idea.

Same here.

> 
> > > +	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
> > > +		return 0;
> > > +
> > >  	if ((lr & XFS_BTCUR_LEFTRA) && left != NULLFSBLOCK) {
> > >  		xfs_btree_reada_bufl(cur->bc_mp, left, 1,
> > 
> > Should the xfile check go into  xfs_buf_readahead instead?  That would
> > execute a little more useles code for in-memory btrees, but keep this
> > check in one place (where we could also write a nice comment explaining
> > it :))
> 
> Sure, why not?  It's too bad that readahead to an xfile can't
> asynchronously call xfile_get_page; maybe we wouldn't need so much
> caching.

Actualy page lookup or allocation never is async, so this would only
be about reading swap from disk.  And given what a mess the swap code
is I don't think we'll have an async read for that any time soon.

Re: [PATCH 9/9] xfs: connect in-memory btrees to xfiles

[Darrick J. Wong]

On Wed, Jan 03, 2024 at 10:54:14PM -0800, Christoph Hellwig wrote:
> On Sun, Dec 31, 2023 at 12:15:54PM -0800, Darrick J. Wong wrote:
> > From: Darrick J. Wong <djwong@kernel.org>
> > 
> > Add to our stubbed-out in-memory btrees the ability to connect them with
> > an actual in-memory backing file (aka xfiles) and the necessary pieces
> > to track free space in the xfile and flush dirty xfbtree buffers on
> > demand, which we'll need for online repair.
> 
> I guess this is is split from the last patch because of the size of
> the changes?   Because it feels they relong belong together.  Maybe with
> my patches for the diet and splitting out the new helpers outside the
> btree code these could now become a single commit?

Yep.

> > +#ifdef CONFIG_XFS_BTREE_IN_XFILE
> > +static inline unsigned long
> > +xfbtree_ino(
> > +	struct xfbtree		*xfbt)
> > +{
> > +	return file_inode(xfbt->target->bt_xfile->file)->i_ino;
> > +}
> > +#endif /* CONFIG_XFS_BTREE_IN_XFILE */
> 
> This should probably move to xfile.h?
> 
> > +	/* Make sure we actually can write to the block before we return it. */
> > +	pos = xfo_to_b(bt_xfoff);
> > +	error = xfile_prealloc(xfbtree_xfile(xfbt), pos, xfo_to_b(1));
> > +	if (error)
> > +		return error;
> 
> IFF we stick to always backing the buffers directly by the shmem
> pages this won't be needed - the btree code does a buf_get right after
> calling into ->alloc_blocks that will allocate the page.

Yep, that would make things much simpler.

> > +int
> > +xfbtree_free_block(
> > +	struct xfs_btree_cur	*cur,
> > +	struct xfs_buf		*bp)
> > +{
> > +	struct xfbtree		*xfbt = cur->bc_mem.xfbtree;
> > +	xfileoff_t		bt_xfoff, bt_xflen;
> > +
> > +	ASSERT(cur->bc_flags & XFS_BTREE_IN_XFILE);
> > +
> > +	bt_xfoff = xfs_daddr_to_xfot(xfs_buf_daddr(bp));
> > +	bt_xflen = xfs_daddr_to_xfot(bp->b_length);
> > +
> > +	trace_xfbtree_free_block(xfbt, cur, bt_xfoff);
> > +
> > +	return xfboff_bitmap_set(&xfbt->freespace, bt_xfoff, bt_xflen);
> 
> Any reason this doesn't actually remove the page from shmem?

I think I skipped the shmem_truncate_range call because the next btree
block allocation will re-use the page immediately.

> > +int
> > +xfbtree_trans_commit(
> > +	struct xfbtree		*xfbt,
> > +	struct xfs_trans	*tp)
> > +{
> > +	LIST_HEAD(buffer_list);
> > +	struct xfs_log_item	*lip, *n;
> > +	bool			corrupt = false;
> > +	bool			tp_dirty = false;
> 
> Can we have some sort of flag on the xfs_trans structure that marks it
> as fake for xfbtree, and assert it gets fed here, and add ansother
> assert it desn't get fed to xfs_trans_commit/cancel?

Use an "empty" transaction?

> > +/* Discard pages backing a range of the xfile. */
> > +void
> > +xfile_discard(
> > +	struct xfile		*xf,
> > +	loff_t			pos,
> > +	u64			count)
> > +{
> > +	trace_xfile_discard(xf, pos, count);
> > +	shmem_truncate_range(file_inode(xf->file), pos, pos + count - 1);
> > +}
> 
> This doesn't end up being used.

I'll remove it then.

> > +/* Ensure that there is storage backing the given range. */
> > +int
> > +xfile_prealloc(
> > +	struct xfile		*xf,
> > +	loff_t			pos,
> > +	u64			count)
> 
> If we end up needing this somewhere else in the end (and it really
> should be a separate patch), we should be able to replace it with
> a simple xfile_get_page/xfile_put_page pair.

I think the only place it gets used is btree block allocation to make
sure a page has been stuffed into the xfile/memfd recently.  Probably it
could go away since a write failure will be noticed quickly anyway.

--D

Re: [PATCH 8/9] xfs: support in-memory btrees

[Darrick J. Wong]

On Wed, Jan 03, 2024 at 11:30:27PM -0800, Christoph Hellwig wrote:
> On Wed, Jan 03, 2024 at 11:27:52PM -0800, Darrick J. Wong wrote:
> > > Btw, one thing I noticed is that we have a lot of confusion on what
> > > part of the bc_ino/ag/mem union is used for a given btree.  For
> > > On-disk inodes we abuse the long ptrs flag, and then we through in
> > > the xfile flags.  If you're fine with it I can try to sort it out.
> > > It's not really a blocker, but I think it would be a lot claner if
> > > we used the chance to sort it out.  This will become even more
> > > important with the rt rmap/reflink trees that will further increase
> > > the confusion here.
> > 
> > Go for it! :)
> 
> Happy to do it you don't complain about all the rebase pain it'll
> cause..

You might want to wait a bit for my XFS_BTREE_ -> XFS_BTGEO_ change to
finish testing so I can repost.  That alone will cause a fair amount of
rebasing.

> > > That means xfs_btree.c can use the target from it, and the owner
> > > and we can remove the indirect calls for calculcating maxrecs/minrecs,
> > > and then also add a field for the block size like this one and remove
> > > a lof of the XFS_BTREE_IN_XFILE checks.
> > 
> > Sounds like a good idea.
> 
> Same here.
> 
> > 
> > > > +	if (cur->bc_flags & XFS_BTREE_IN_XFILE)
> > > > +		return 0;
> > > > +
> > > >  	if ((lr & XFS_BTCUR_LEFTRA) && left != NULLFSBLOCK) {
> > > >  		xfs_btree_reada_bufl(cur->bc_mp, left, 1,
> > > 
> > > Should the xfile check go into  xfs_buf_readahead instead?  That would
> > > execute a little more useles code for in-memory btrees, but keep this
> > > check in one place (where we could also write a nice comment explaining
> > > it :))
> > 
> > Sure, why not?  It's too bad that readahead to an xfile can't
> > asynchronously call xfile_get_page; maybe we wouldn't need so much
> > caching.
> 
> Actualy page lookup or allocation never is async, so this would only
> be about reading swap from disk.  And given what a mess the swap code
> is I don't think we'll have an async read for that any time soon.

Yeah, I was afraid you were gonna say that. :(

--D

Re: [PATCH 3/3] xfile: implement write caching

[Darrick J. Wong]

On Wed, Jan 03, 2024 at 11:28:21PM -0800, Christoph Hellwig wrote:
> On Wed, Jan 03, 2024 at 11:20:50PM -0800, Darrick J. Wong wrote:
> > > Sure, I just suspect the commit message is wrong and it's not about
> > > mapping the page into the kernel address space but something else.
> > 
> > Yeah, I only did A/B testing of before and after this patch, so it's
> > quite plausible that it's the lookup that's slowing us down.
> 
> Can we re-rerun the test once the pending xfile changes are in?
> I'd be kinda surprised if the fairly simply xarray lookup for the
> page is so expensive.  If it is the patch is a good bandaid for that,
> I'd just like to ensure it actually is still needed.

Ok, I'll do that.  Were you planning to send that first series to
Chandan for 6.8?

--D

Re: [PATCH 3/3] xfile: implement write caching

[Christoph Hellwig]

On Wed, Jan 03, 2024 at 11:34:12PM -0800, Darrick J. Wong wrote:
> Ok, I'll do that.  Were you planning to send that first series to
> Chandan for 6.8?

If you're fine with that and I get reviews from Hugh for the small shmem
bits I'd like to get it included ASAP.

Re: [PATCH 8/9] xfs: support in-memory btrees

[Christoph Hellwig]

On Wed, Jan 03, 2024 at 11:33:31PM -0800, Darrick J. Wong wrote:
> > Happy to do it you don't complain about all the rebase pain it'll
> > cause..
> 
> You might want to wait a bit for my XFS_BTREE_ -> XFS_BTGEO_ change to
> finish testing so I can repost.  That alone will cause a fair amount of
> rebasing.

Good idea.

Re: [PATCH 9/9] xfs: connect in-memory btrees to xfiles

[Christoph Hellwig]

On Wed, Jan 03, 2024 at 11:32:17PM -0800, Darrick J. Wong wrote:
> > Any reason this doesn't actually remove the page from shmem?
> 
> I think I skipped the shmem_truncate_range call because the next btree
> block allocation will re-use the page immediately.

Maybe add a comment explaining that?  Note that shmemfs pages once
dirties will keep space allocated for them in memory/swap until
explicitly punched out.

Re: [PATCH 3/3] xfile: implement write caching

[Darrick J. Wong]

On Wed, Jan 03, 2024 at 11:39:58PM -0800, Christoph Hellwig wrote:
> On Wed, Jan 03, 2024 at 11:34:12PM -0800, Darrick J. Wong wrote:
> > Ok, I'll do that.  Were you planning to send that first series to
> > Chandan for 6.8?
> 
> If you're fine with that and I get reviews from Hugh for the small shmem
> bits I'd like to get it included ASAP.

Ok by me, though I also would like to hear from Hugh that the shmem.c
modifications make sense.

--D

Re: [PATCH 1/3] xfs_scrub: fix author and spdx headers on scrub/ files

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 2/3] xfs_scrub: add missing license and copyright information

[Christoph Hellwig]

Given that the last patch moved to the -or-later SPDX variant shouldn't
this also pick on of -only or -or-later?

Re: [PATCH 3/3] xfs_scrub: update copyright years for scrub/ files

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 1/2] mkfs: allow sizing allocation groups for concurrency

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 2/2] mkfs: allow sizing internal logs for concurrency

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 02:05:09PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Add a -l option to mkfs so that sysadmins can configure the filesystem
> so that the log can handle a certain number of transactions (front and
> backend) without any threads contending for log grant space.

Looks good in general, although without support for > 2GB logs we're
going to hit the ceiling pretty much all the time :)


Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 1/3] libfrog: rename XFROG_SCRUB_TYPE_* to XFROG_SCRUB_GROUP_*

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 2/3] libfrog: promote XFROG_SCRUB_DESCR_SUMMARY to a scrub type

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 3/3] xfs_scrub: scan whole-fs metadata files in parallel

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 1/7] xfs_scrub: flush stdout after printing to it

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 02:36:41PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Make sure we flush stdout after printf'ing to it, especially before we
> start any operation that could take a while to complete.  Most of scrub
> already does this, but we missed a couple of spots.

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 2/7] xfs_scrub: don't report media errors for space with unknowable owner

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 3/7] xfs_scrub: remove ALP_* flags namespace

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 4/7] xfs_scrub: move repair functions to repair.c

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 5/7] xfs_scrub: log when a repair was unnecessary

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 6/7] xfs_scrub: require primary superblock repairs to complete before proceeding

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 7/7] xfs_scrub: actually try to fix summary counters ahead of repairs

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 1/8] xfs_scrub: fix missing scrub coverage for broken inodes

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 2/8] xfs_scrub: collapse trivial superblock scrub helpers

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 3/8] xfs_scrub: get rid of trivial fs metadata scanner helpers

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 4/8] xfs_scrub: split up the mustfix repairs and difficulty assessment functions

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 5/8] xfs_scrub: add missing repair types to the mustfix and difficulty assessment

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 6/8] xfs_scrub: any inconsistency in metadata should trigger difficulty warnings

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 7/8] xfs_scrub: warn about difficult repairs to rt and quota metadata

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 8/8] xfs_scrub: enable users to bump information messages to warnings

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 1/9] xfs_scrub: track repair items by principal, not by individual repairs

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 2/9] xfs_scrub: use repair_item to direct repair activities

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 3/9] xfs_scrub: remove action lists from phaseX code

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 4/9] xfs_scrub: remove scrub_metadata_file

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 5/9] xfs_scrub: boost the repair priority of dependencies of damaged items

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 6/9] xfs_scrub: clean up repair_item_difficulty a little

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 7/9] xfs_scrub: check dependencies of a scrub type before repairing

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 8/9] xfs_scrub: retry incomplete repairs

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 9/9] xfs_scrub: remove unused action_list fields

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 1/5] xfs_scrub: start tracking scrub state in scrub_item

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 2/5] xfs_scrub: remove enum check_outcome

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 3/5] xfs_scrub: refactor scrub_meta_type out of existence

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 4/5] xfs_scrub: hoist repair retry loop to repair_item_class

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 5/5] xfs_scrub: hoist scrub retry loop to scrub_item_check_file

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 1/4] libfrog: enhance ptvar to support initializer functions

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 2/4] xfs_scrub: improve thread scheduling repair items during phase 4

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 3/4] xfs_scrub: recheck entire metadata objects after corruption repairs

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 4/4] xfs_scrub: try to repair space metadata before file metadata

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 6/9] xfs_scrub_fail: add content type header to failure emails

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 7/9] xfs_scrub_fail: advise recipients not to reply

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 8/9] xfs_scrub_fail: move executable script to /usr/libexec

[Christoph Hellwig]

Oh, libexec is back, that gives me strong 4.4-BSD vibes..

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 9/9] xfs_scrub_all.cron: move to package data directory

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 02:54:41PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> cron jobs don't belong in /usr/lib.  Since the cron job is also
> secondary to the systemd timer, it's really only provided as a courtesy
> for distributions that don't use systemd.  Move it to @datadir@, aka
> /usr/share/xfsprogs.

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 2/5] xfs: implement live quotacheck inode scan

[Christoph Hellwig]

Looks good,

but a few nitpick below:

> +int
> +xchk_trans_alloc_empty(
> +	struct xfs_scrub	*sc)
> +{
> +	return xfs_trans_alloc_empty(sc->mp, &sc->tp);
> +}

Can this and the conversion of an existing not quota related caller
of xfs_trans_alloc_empty be split into a separate patch that also
documents why this pretty trivial helper is useful?

> +#ifdef CONFIG_XFS_QUOTA
> +void xchk_qcheck_set_corrupt(struct xfs_scrub *sc, unsigned int dqtype,
> +		xfs_dqid_t id);
> +#endif /* CONFIG_XFS_QUOTA */

No need for the ifdef here.

> +	/* Figure out the data / rt device block counts. */
> +	xfs_ilock(ip, XFS_IOLOCK_SHARED);
> +	if (isreg)
> +		xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
> +	if (XFS_IS_REALTIME_INODE(ip)) {
> +		ilock_flags = xfs_ilock_data_map_shared(ip);
> +		error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
> +		if (error)
> +			goto out_incomplete;
> +	} else {
> +		ilock_flags = XFS_ILOCK_SHARED;
> +		xfs_ilock(ip, XFS_ILOCK_SHARED);
> +	}

The need to call xfs_iread_extents only for RT inodes here look good,
but I guess it is explained by the logic in xfs_inode_count_blocks.
Maybe add a comment?


> +/*
> + * Load an array element, but zero the buffer if there's no data because we
> + * haven't stored to that array element yet.
> + */
> +static inline int
> +xfarray_load_sparse(
> +	struct xfarray	*array,
> +	uint64_t	idx,
> +	void		*rec)
> +{
> +	int		error = xfarray_load(array, idx, rec);
> +
> +	if (error == -ENODATA) {
> +		memset(rec, 0, array->obj_size);
> +		return 0;
> +	}
> +	return error;
> +}

Please split this into a separate prep patch.

> +/* Compute the number of data and realtime blocks used by a file. */
> +void
> +xfs_inode_count_blocks(
> +	struct xfs_trans	*tp,
> +	struct xfs_inode	*ip,
> +	xfs_filblks_t		*dblocks,
> +	xfs_filblks_t		*rblocks)
> +{
> +	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
> +
> +	if (!XFS_IS_REALTIME_INODE(ip)) {
> +		*dblocks = ip->i_nblocks;
> +		*rblocks = 0;
> +		return;
> +	}
> +
> +	*rblocks = 0;
> +	xfs_bmap_count_leaves(ifp, rblocks);
> +	*dblocks = ip->i_nblocks - *rblocks;
> +}

Same for this one.  The flow here also reads a little odd to me,
what speaks against:

	*rblocks = 0;
	if (XFS_IS_REALTIME_INODE(ip))
		xfs_bmap_count_leaves(&ip->i_df, rblocks);
	*dblocks = ip->i_nblocks - *rblocks;

Re: [PATCH 3/5] xfs: track quota updates during live quotacheck

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 4/5] xfs: repair cannot update the summary counters when logging quota flags

[Christoph Hellwig]

> +	bp = xfs_trans_getsb(sc->tp);
> +	xfs_sb_to_disk(bp->b_addr, &mp->m_sb);
> +	xfs_trans_buf_set_type(sc->tp, bp, XFS_BLFT_SB_BUF);
> +	xfs_trans_log_buf(sc->tp, bp, 0, sizeof(struct xfs_dsb) - 1);

We now have a multiple copies of this code sequence and it would probably
be good to have a helper for it.  Given that the current xfs_log_sb
is a bit misnamed I'd be alsmost tempted to use the name just for
this and split the lazy counter updates into a separate helper.
That also makes it very clear that we'd need to explicitly opt into
syncing them and prvent accidental bugs like this one.  But I'd also
be fine with another name instead of duplicating it here and in the
pending imeta code.

Re: [PATCH 5/5] xfs: repair dquots based on live quotacheck results

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 1/4] xfs: report health of inode link counts

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 2/4] xfs: teach scrub to check file nlinks

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 3/4] xfs: track directory entry updates during live nlinks fsck

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 4/4] xfs: teach repair to fix file nlinks

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 01/11] xfs: separate the marking of sick and checked metadata

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 02/11] xfs: report fs corruption errors to the health tracking system

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 03/11] xfs: report ag header corruption errors to the health tracking system

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 04/11] xfs: report block map corruption errors to the health tracking system

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 05/11] xfs: report btree block corruption errors to the health system

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 06/11] xfs: report dir/attr block corruption errors to the health system

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 07/11] xfs: report symlink block corruption errors to the health system

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 08/11] xfs: report inode corruption errors to the health system

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 09/11] xfs: report quota block corruption errors to the health system

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 10/11] xfs: report realtime metadata corruption errors to the health system

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 11/11] xfs: report XFS_IS_CORRUPT errors to the health system

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 1/3] xfs: add secondary and indirect classes to the health tracking system

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 2/3] xfs: remember sick inodes that get inactivated

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 3/3] xfs: update health status if we get a clean bill of health

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 1/1] xfs: repair summary counters

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 1/4] xfs: create a helper to decide if a file mapping targets the rt volume

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 12:16:10PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Create a helper so that we can stop open-coding this decision
> everywhere.

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 1/2] xfs: support deferred bmap updates on the attr fork

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 2/2] xfs: xfs_bmap_finish_one should map unwritten extents properly

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 1/3] xfs: move xfs_symlink_remote.c declarations to xfs_symlink_remote.h

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 2/3] xfs: move remote symlink target read function to libxfs

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 3/3] xfs: move symlink target write function to libxfs

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 1/6] xfs: create a blob array data structure

[Christoph Hellwig]

On Sun, Dec 31, 2023 at 12:35:11PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@kernel.org>
> 
> Create a simple 'blob array' data structure for storage of arbitrarily
> sized metadata objects that will be used to reconstruct metadata.  For
> the intended usage (temporarily storing extended attribute names and
> values) we only have to support storing objects and retrieving them.
> Use the xfile abstraction to store the attribute information in memory
> that can be swapped out.

Can't this simply be supported by xfiles directly?  Just add a
xfile_append that writes at i_size and retuns the offset and we're done?

Re: [PATCH 2/3] xfs_scrub: add missing license and copyright information

[Darrick J. Wong]

On Thu, Jan 04, 2024 at 08:50:08PM -0800, Christoph Hellwig wrote:
> Given that the last patch moved to the -or-later SPDX variant shouldn't
> this also pick on of -only or -or-later?

Yeah, I suppose they should be licensed the same way as the rest of the
files.  Will fix.

--D

Re: [PATCH 2/5] xfs: implement live quotacheck inode scan

[Darrick J. Wong]

On Thu, Jan 04, 2024 at 09:29:16PM -0800, Christoph Hellwig wrote:
> Looks good,
> 
> but a few nitpick below:
> 
> > +int
> > +xchk_trans_alloc_empty(
> > +	struct xfs_scrub	*sc)
> > +{
> > +	return xfs_trans_alloc_empty(sc->mp, &sc->tp);
> > +}
> 
> Can this and the conversion of an existing not quota related caller
> of xfs_trans_alloc_empty be split into a separate patch that also
> documents why this pretty trivial helper is useful?

Done.

> > +#ifdef CONFIG_XFS_QUOTA
> > +void xchk_qcheck_set_corrupt(struct xfs_scrub *sc, unsigned int dqtype,
> > +		xfs_dqid_t id);
> > +#endif /* CONFIG_XFS_QUOTA */
> 
> No need for the ifdef here.

Fixed.

> > +	/* Figure out the data / rt device block counts. */
> > +	xfs_ilock(ip, XFS_IOLOCK_SHARED);
> > +	if (isreg)
> > +		xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
> > +	if (XFS_IS_REALTIME_INODE(ip)) {
> > +		ilock_flags = xfs_ilock_data_map_shared(ip);
> > +		error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
> > +		if (error)
> > +			goto out_incomplete;
> > +	} else {
> > +		ilock_flags = XFS_ILOCK_SHARED;
> > +		xfs_ilock(ip, XFS_ILOCK_SHARED);
> > +	}
> 
> The need to call xfs_iread_extents only for RT inodes here look good,
> but I guess it is explained by the logic in xfs_inode_count_blocks.
> Maybe add a comment?

		/*
		 * Read in the data fork for rt files so that _count_blocks
		 * can count the number of blocks allocated from the rt volume.
		 * Inodes do not track that separately.
		 */

> > +/*
> > + * Load an array element, but zero the buffer if there's no data because we
> > + * haven't stored to that array element yet.
> > + */
> > +static inline int
> > +xfarray_load_sparse(
> > +	struct xfarray	*array,
> > +	uint64_t	idx,
> > +	void		*rec)
> > +{
> > +	int		error = xfarray_load(array, idx, rec);
> > +
> > +	if (error == -ENODATA) {
> > +		memset(rec, 0, array->obj_size);
> > +		return 0;
> > +	}
> > +	return error;
> > +}
> 
> Please split this into a separate prep patch.

Done.

> > +/* Compute the number of data and realtime blocks used by a file. */
> > +void
> > +xfs_inode_count_blocks(
> > +	struct xfs_trans	*tp,
> > +	struct xfs_inode	*ip,
> > +	xfs_filblks_t		*dblocks,
> > +	xfs_filblks_t		*rblocks)
> > +{
> > +	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
> > +
> > +	if (!XFS_IS_REALTIME_INODE(ip)) {
> > +		*dblocks = ip->i_nblocks;
> > +		*rblocks = 0;
> > +		return;
> > +	}
> > +
> > +	*rblocks = 0;
> > +	xfs_bmap_count_leaves(ifp, rblocks);
> > +	*dblocks = ip->i_nblocks - *rblocks;
> > +}
> 
> Same for this one.  The flow here also reads a little odd to me,
> what speaks against:
> 
> 	*rblocks = 0;
> 	if (XFS_IS_REALTIME_INODE(ip))
> 		xfs_bmap_count_leaves(&ip->i_df, rblocks);
> 	*dblocks = ip->i_nblocks - *rblocks;

Yeah, that is more tidy.  Thanks for the suggestion, I'll incorporate
that.

--D

Re: [PATCH 1/6] xfs: create a blob array data structure

[Darrick J. Wong]

On Thu, Jan 04, 2024 at 09:53:33PM -0800, Christoph Hellwig wrote:
> On Sun, Dec 31, 2023 at 12:35:11PM -0800, Darrick J. Wong wrote:
> > From: Darrick J. Wong <djwong@kernel.org>
> > 
> > Create a simple 'blob array' data structure for storage of arbitrarily
> > sized metadata objects that will be used to reconstruct metadata.  For
> > the intended usage (temporarily storing extended attribute names and
> > values) we only have to support storing objects and retrieving them.
> > Use the xfile abstraction to store the attribute information in memory
> > that can be swapped out.
> 
> Can't this simply be supported by xfiles directly?  Just add a
> xfile_append that writes at i_size and retuns the offset and we're done?

Yeah, xfile could just do an "append and tell me where you wrote it".
That said, i_size_read is less direct than reading a u64 out of a
struct.

Another speedbump with doing that is that eventually xfs_repair ports
the xfblob to userspace to support parent pointers.  For that, a statx
call is much more expensive, so I decided that both implementations
should just have their own private u64 write pointer.

(Unless you want to sponsor a pwrite variant that actually does "append
and tell me where"? ;))

--D

Re: [PATCH 1/6] xfs: create a blob array data structure

[Christoph Hellwig]

On Fri, Jan 05, 2024 at 05:33:16PM -0800, Darrick J. Wong wrote:
> (Unless you want to sponsor a pwrite variant that actually does "append
> and tell me where"? ;))

Damien and I have adding that on our TODO list (through io_uring) to
better support zonefs and programming models like this one on regular
files.

But I somehow doubt you'd want xfs_repair to depend on it..

Re: [PATCH 4/5] xfs: repair cannot update the summary counters when logging quota flags

[Darrick J. Wong]

On Thu, Jan 04, 2024 at 09:35:28PM -0800, Christoph Hellwig wrote:
> > +	bp = xfs_trans_getsb(sc->tp);
> > +	xfs_sb_to_disk(bp->b_addr, &mp->m_sb);
> > +	xfs_trans_buf_set_type(sc->tp, bp, XFS_BLFT_SB_BUF);
> > +	xfs_trans_log_buf(sc->tp, bp, 0, sizeof(struct xfs_dsb) - 1);
> 
> We now have a multiple copies of this code sequence and it would probably
> be good to have a helper for it.  Given that the current xfs_log_sb
> is a bit misnamed I'd be alsmost tempted to use the name just for
> this and split the lazy counter updates into a separate helper.

Since we're really only updating feature flags, how about these three
lines become a new xfs_trans_log_sb_featureset() helper?

That's not a totally precise name since we're logging everything
/except/ the lazysbcount fields though.

> That also makes it very clear that we'd need to explicitly opt into
> syncing them and prvent accidental bugs like this one.  But I'd also
> be fine with another name instead of duplicating it here and in the
> pending imeta code.

If we go ahead with your suggestion not to update the superblock under
the hood in the xfs_imeta.[ch] for !metadir filesystems then there won't
be a third caller.

--D

Re: [PATCH 1/6] xfs: create a blob array data structure

[Darrick J. Wong]

On Fri, Jan 05, 2024 at 10:42:01PM -0800, Christoph Hellwig wrote:
> On Fri, Jan 05, 2024 at 05:33:16PM -0800, Darrick J. Wong wrote:
> > (Unless you want to sponsor a pwrite variant that actually does "append
> > and tell me where"? ;))
> 
> Damien and I have adding that on our TODO list (through io_uring) to
> better support zonefs and programming models like this one on regular
> files.
> 
> But I somehow doubt you'd want xfs_repair to depend on it..

Well in theory some day Dave might come back with his libaio patches for
xfsprogs.  After this much time it's a fair question if we'd be better
off aiming for io_uring. <shrug>

https://lore.kernel.org/linux-xfs/20201015072155.1631135-1-david@fromorbit.com/

--D

Re: [PATCH 1/6] xfs: create a blob array data structure

[Darrick J. Wong]

On Fri, Jan 05, 2024 at 10:42:01PM -0800, Christoph Hellwig wrote:
> On Fri, Jan 05, 2024 at 05:33:16PM -0800, Darrick J. Wong wrote:
> > (Unless you want to sponsor a pwrite variant that actually does "append
> > and tell me where"? ;))
> 
> Damien and I have adding that on our TODO list (through io_uring) to
> better support zonefs and programming models like this one on regular
> files.
> 
> But I somehow doubt you'd want xfs_repair to depend on it..

Nope, not for a few years anyway. :)

--D

Re: [PATCH 2/5] xfs: implement live quotacheck inode scan

[Darrick J. Wong]

On Fri, Jan 05, 2024 at 05:16:50PM -0800, Darrick J. Wong wrote:
> On Thu, Jan 04, 2024 at 09:29:16PM -0800, Christoph Hellwig wrote:
> > Looks good,
> > 
> > but a few nitpick below:
> > 
> > > +int
> > > +xchk_trans_alloc_empty(
> > > +	struct xfs_scrub	*sc)
> > > +{
> > > +	return xfs_trans_alloc_empty(sc->mp, &sc->tp);
> > > +}
> > 
> > Can this and the conversion of an existing not quota related caller
> > of xfs_trans_alloc_empty be split into a separate patch that also
> > documents why this pretty trivial helper is useful?
> 
> Done.
> 
> > > +#ifdef CONFIG_XFS_QUOTA
> > > +void xchk_qcheck_set_corrupt(struct xfs_scrub *sc, unsigned int dqtype,
> > > +		xfs_dqid_t id);
> > > +#endif /* CONFIG_XFS_QUOTA */
> > 
> > No need for the ifdef here.
> 
> Fixed.

...and reverted because I forgot to remove the #ifdef around the
tracepoint in that function.  I tried to fix that, and got a ton of
macro spew over ... something not being defined.  In the end, I decided
that it was better not to waste memory on !CONFIG_XFS_QUOTA and not to
waste time on minor things like this.

(I spent all day rebasing to for-next again because I didn't realize
that Chandan had pulled in a bunch more of your cleanups.)

--D

> > > +	/* Figure out the data / rt device block counts. */
> > > +	xfs_ilock(ip, XFS_IOLOCK_SHARED);
> > > +	if (isreg)
> > > +		xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
> > > +	if (XFS_IS_REALTIME_INODE(ip)) {
> > > +		ilock_flags = xfs_ilock_data_map_shared(ip);
> > > +		error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
> > > +		if (error)
> > > +			goto out_incomplete;
> > > +	} else {
> > > +		ilock_flags = XFS_ILOCK_SHARED;
> > > +		xfs_ilock(ip, XFS_ILOCK_SHARED);
> > > +	}
> > 
> > The need to call xfs_iread_extents only for RT inodes here look good,
> > but I guess it is explained by the logic in xfs_inode_count_blocks.
> > Maybe add a comment?
> 
> 		/*
> 		 * Read in the data fork for rt files so that _count_blocks
> 		 * can count the number of blocks allocated from the rt volume.
> 		 * Inodes do not track that separately.
> 		 */
> 
> > > +/*
> > > + * Load an array element, but zero the buffer if there's no data because we
> > > + * haven't stored to that array element yet.
> > > + */
> > > +static inline int
> > > +xfarray_load_sparse(
> > > +	struct xfarray	*array,
> > > +	uint64_t	idx,
> > > +	void		*rec)
> > > +{
> > > +	int		error = xfarray_load(array, idx, rec);
> > > +
> > > +	if (error == -ENODATA) {
> > > +		memset(rec, 0, array->obj_size);
> > > +		return 0;
> > > +	}
> > > +	return error;
> > > +}
> > 
> > Please split this into a separate prep patch.
> 
> Done.
> 
> > > +/* Compute the number of data and realtime blocks used by a file. */
> > > +void
> > > +xfs_inode_count_blocks(
> > > +	struct xfs_trans	*tp,
> > > +	struct xfs_inode	*ip,
> > > +	xfs_filblks_t		*dblocks,
> > > +	xfs_filblks_t		*rblocks)
> > > +{
> > > +	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
> > > +
> > > +	if (!XFS_IS_REALTIME_INODE(ip)) {
> > > +		*dblocks = ip->i_nblocks;
> > > +		*rblocks = 0;
> > > +		return;
> > > +	}
> > > +
> > > +	*rblocks = 0;
> > > +	xfs_bmap_count_leaves(ifp, rblocks);
> > > +	*dblocks = ip->i_nblocks - *rblocks;
> > > +}
> > 
> > Same for this one.  The flow here also reads a little odd to me,
> > what speaks against:
> > 
> > 	*rblocks = 0;
> > 	if (XFS_IS_REALTIME_INODE(ip))
> > 		xfs_bmap_count_leaves(&ip->i_df, rblocks);
> > 	*dblocks = ip->i_nblocks - *rblocks;
> 
> Yeah, that is more tidy.  Thanks for the suggestion, I'll incorporate
> that.
> 
> --D
> 

Re: [PATCH 2/5] xfs: implement live quotacheck inode scan

[Christoph Hellwig]

On Mon, Jan 08, 2024 at 05:23:46PM -0800, Darrick J. Wong wrote:
> > > > +#ifdef CONFIG_XFS_QUOTA
> > > > +void xchk_qcheck_set_corrupt(struct xfs_scrub *sc, unsigned int dqtype,
> > > > +		xfs_dqid_t id);
> > > > +#endif /* CONFIG_XFS_QUOTA */
> > > 
> > > No need for the ifdef here.
> > 
> > Fixed.
> 
> ...and reverted because I forgot to remove the #ifdef around the
> tracepoint in that function.  I tried to fix that, and got a ton of
> macro spew over ... something not being defined.  In the end, I decided
> that it was better not to waste memory on !CONFIG_XFS_QUOTA and not to
> waste time on minor things like this.

Note that I only meant the ifdef on the declaration in the header, not
for the function itself anyway, sorry.

[PATCH 5/9] xfs: rename btree block/buffer init functions

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Rename xfs_btree_init_block_int to xfs_btree_init_block, and
xfs_btree_init_block to xfs_btree_init_buf so that the name suggests the
type that caller are supposed to pass in.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_ag.c            |    6 +++---
 fs/xfs/libxfs/xfs_bmap.c          |    6 +++---
 fs/xfs/libxfs/xfs_bmap_btree.c    |    2 +-
 fs/xfs/libxfs/xfs_btree.c         |    8 ++++----
 fs/xfs/libxfs/xfs_btree.h         |    4 ++--
 fs/xfs/libxfs/xfs_btree_staging.c |    2 +-
 fs/xfs/scrub/xfbtree.c            |    2 +-
 7 files changed, 15 insertions(+), 15 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 02aef7334b67..5ee3ec70edbe 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -473,7 +473,7 @@ xfs_btroot_init(
 	struct xfs_buf		*bp,
 	struct aghdr_init_data	*id)
 {
-	xfs_btree_init_block(mp, bp, id->bc_ops, 0, 0, id->agno);
+	xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 0, id->agno);
 }
 
 /* Finish initializing a free space btree. */
@@ -539,7 +539,7 @@ xfs_bnoroot_init(
 	struct xfs_buf		*bp,
 	struct aghdr_init_data	*id)
 {
-	xfs_btree_init_block(mp, bp, id->bc_ops, 0, 0, id->agno);
+	xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 0, id->agno);
 	xfs_freesp_init_recs(mp, bp, id);
 }
 
@@ -555,7 +555,7 @@ xfs_rmaproot_init(
 	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
 	struct xfs_rmap_rec	*rrec;
 
-	xfs_btree_init_block(mp, bp, id->bc_ops, 0, 4, id->agno);
+	xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 4, id->agno);
 
 	/*
 	 * mark the AG header regions as static metadata The BNO
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 2836e9887736..c58aa644a0b3 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -639,8 +639,8 @@ xfs_bmap_extents_to_btree(
 	 * Fill in the root.
 	 */
 	block = ifp->if_broot;
-	xfs_btree_init_block_int(mp, block, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL,
-			1, 1, ip->i_ino);
+	xfs_btree_init_block(mp, block, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL, 1,
+			1, ip->i_ino);
 	/*
 	 * Need a cursor.  Can't allocate until bb_level is filled in.
 	 */
@@ -685,7 +685,7 @@ xfs_bmap_extents_to_btree(
 	 */
 	abp->b_ops = &xfs_bmbt_buf_ops;
 	ablock = XFS_BUF_TO_BLOCK(abp);
-	xfs_btree_init_block_int(mp, ablock, &xfs_bmbt_ops, xfs_buf_daddr(abp),
+	xfs_btree_init_block(mp, ablock, &xfs_bmbt_ops, xfs_buf_daddr(abp),
 			0, 0, ip->i_ino);
 
 	for_each_xfs_iext(ifp, &icur, &rec) {
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 3683080296ef..904971502dc6 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -44,7 +44,7 @@ xfs_bmdr_to_bmbt(
 	xfs_bmbt_key_t		*tkp;
 	__be64			*tpp;
 
-	xfs_btree_init_block_int(mp, rblock, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL,
+	xfs_btree_init_block(mp, rblock, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL,
 			0, 0, ip->i_ino);
 	rblock->bb_level = dblock->bb_level;
 	ASSERT(be16_to_cpu(rblock->bb_level) > 0);
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index bb2a7473fe05..742e24b24ba2 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -1213,7 +1213,7 @@ xfs_btree_set_sibling(
 }
 
 void
-xfs_btree_init_block_int(
+xfs_btree_init_block(
 	struct xfs_mount	*mp,
 	struct xfs_btree_block	*buf,
 	const struct xfs_btree_ops *ops,
@@ -1255,7 +1255,7 @@ xfs_btree_init_block_int(
 }
 
 void
-xfs_btree_init_block(
+xfs_btree_init_buf(
 	struct xfs_mount		*mp,
 	struct xfs_buf			*bp,
 	const struct xfs_btree_ops	*ops,
@@ -1263,7 +1263,7 @@ xfs_btree_init_block(
 	__u16				numrecs,
 	__u64				owner)
 {
-	xfs_btree_init_block_int(mp, XFS_BUF_TO_BLOCK(bp), ops,
+	xfs_btree_init_block(mp, XFS_BUF_TO_BLOCK(bp), ops,
 			xfs_buf_daddr(bp), level, numrecs, owner);
 }
 
@@ -1289,7 +1289,7 @@ xfs_btree_init_block_cur(
 	else
 		owner = cur->bc_ag.pag->pag_agno;
 
-	xfs_btree_init_block_int(cur->bc_mp, XFS_BUF_TO_BLOCK(bp), cur->bc_ops,
+	xfs_btree_init_block(cur->bc_mp, XFS_BUF_TO_BLOCK(bp), cur->bc_ops,
 			xfs_buf_daddr(bp), level, numrecs, owner);
 }
 
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 06c89fc415b5..925bcd245bcf 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -451,10 +451,10 @@ xfs_btree_reada_bufs(
 /*
  * Initialise a new btree block header
  */
-void xfs_btree_init_block(struct xfs_mount *mp, struct xfs_buf *bp,
+void xfs_btree_init_buf(struct xfs_mount *mp, struct xfs_buf *bp,
 		const struct xfs_btree_ops *ops, __u16 level, __u16 numrecs,
 		__u64 owner);
-void xfs_btree_init_block_int(struct xfs_mount *mp,
+void xfs_btree_init_block(struct xfs_mount *mp,
 		struct xfs_btree_block *buf, const struct xfs_btree_ops *ops,
 		xfs_daddr_t blkno, __u16 level, __u16 numrecs, __u64 owner);
 
diff --git a/fs/xfs/libxfs/xfs_btree_staging.c b/fs/xfs/libxfs/xfs_btree_staging.c
index 0bf20472dd27..de17d333ffb3 100644
--- a/fs/xfs/libxfs/xfs_btree_staging.c
+++ b/fs/xfs/libxfs/xfs_btree_staging.c
@@ -404,7 +404,7 @@ xfs_btree_bload_prep_block(
 		ifp->if_broot_bytes = (int)new_size;
 
 		/* Initialize it and send it out. */
-		xfs_btree_init_block_int(cur->bc_mp, ifp->if_broot,
+		xfs_btree_init_block(cur->bc_mp, ifp->if_broot,
 				cur->bc_ops, XFS_BUF_DADDR_NULL, level,
 				nr_this_block, cur->bc_ino.ip->i_ino);
 
diff --git a/fs/xfs/scrub/xfbtree.c b/fs/xfs/scrub/xfbtree.c
index 7f13110ef67b..1260c29c426c 100644
--- a/fs/xfs/scrub/xfbtree.c
+++ b/fs/xfs/scrub/xfbtree.c
@@ -416,7 +416,7 @@ xfbtree_init_leaf_block(
 	trace_xfbtree_create_root_buf(xfbt, bp);
 
 	bp->b_ops = cfg->btree_ops->buf_ops;
-	xfs_btree_init_block_int(mp, bp->b_addr, cfg->btree_ops, daddr, 0, 0,
+	xfs_btree_init_block(mp, bp->b_addr, cfg->btree_ops, daddr, 0, 0,
 			cfg->owner);
 	error = xfs_bwrite(bp);
 	xfs_buf_relse(bp);

[PATCH 5/9] xfs: rename btree block/buffer init functions

[Darrick J. Wong]

From: Darrick J. Wong <djwong@kernel.org>

Rename xfs_btree_init_block_int to xfs_btree_init_block, and
xfs_btree_init_block to xfs_btree_init_buf so that the name suggests the
type that caller are supposed to pass in.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/libxfs/xfs_ag.c            |    6 +++---
 fs/xfs/libxfs/xfs_bmap.c          |    6 +++---
 fs/xfs/libxfs/xfs_bmap_btree.c    |    2 +-
 fs/xfs/libxfs/xfs_btree.c         |    8 ++++----
 fs/xfs/libxfs/xfs_btree.h         |    4 ++--
 fs/xfs/libxfs/xfs_btree_staging.c |    2 +-
 fs/xfs/scrub/xfbtree.c            |    2 +-
 7 files changed, 15 insertions(+), 15 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index f9e9e6879d53..05d0a97e08c3 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -412,7 +412,7 @@ xfs_btroot_init(
 	struct xfs_buf		*bp,
 	struct aghdr_init_data	*id)
 {
-	xfs_btree_init_block(mp, bp, id->bc_ops, 0, 0, id->agno);
+	xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 0, id->agno);
 }
 
 /* Finish initializing a free space btree. */
@@ -479,7 +479,7 @@ xfs_bnoroot_init(
 	struct xfs_buf		*bp,
 	struct aghdr_init_data	*id)
 {
-	xfs_btree_init_block(mp, bp, id->bc_ops, 0, 1, id->agno);
+	xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 1, id->agno);
 	xfs_freesp_init_recs(mp, bp, id);
 }
 
@@ -495,7 +495,7 @@ xfs_rmaproot_init(
 	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
 	struct xfs_rmap_rec	*rrec;
 
-	xfs_btree_init_block(mp, bp, id->bc_ops, 0, 4, id->agno);
+	xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 4, id->agno);
 
 	/*
 	 * mark the AG header regions as static metadata The BNO
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index b91f273ccbec..3ff3202e6e91 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -639,8 +639,8 @@ xfs_bmap_extents_to_btree(
 	 * Fill in the root.
 	 */
 	block = ifp->if_broot;
-	xfs_btree_init_block_int(mp, block, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL,
-			1, 1, ip->i_ino);
+	xfs_btree_init_block(mp, block, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL, 1,
+			1, ip->i_ino);
 	/*
 	 * Need a cursor.  Can't allocate until bb_level is filled in.
 	 */
@@ -696,7 +696,7 @@ xfs_bmap_extents_to_btree(
 	 */
 	abp->b_ops = &xfs_bmbt_buf_ops;
 	ablock = XFS_BUF_TO_BLOCK(abp);
-	xfs_btree_init_block_int(mp, ablock, &xfs_bmbt_ops, xfs_buf_daddr(abp),
+	xfs_btree_init_block(mp, ablock, &xfs_bmbt_ops, xfs_buf_daddr(abp),
 			0, 0, ip->i_ino);
 
 	for_each_xfs_iext(ifp, &icur, &rec) {
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 2cf6459b7bca..f70194293f54 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -43,7 +43,7 @@ xfs_bmdr_to_bmbt(
 	xfs_bmbt_key_t		*tkp;
 	__be64			*tpp;
 
-	xfs_btree_init_block_int(mp, rblock, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL,
+	xfs_btree_init_block(mp, rblock, &xfs_bmbt_ops, XFS_BUF_DADDR_NULL,
 			0, 0, ip->i_ino);
 	rblock->bb_level = dblock->bb_level;
 	ASSERT(be16_to_cpu(rblock->bb_level) > 0);
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 78c18c027575..fe2f21fa7b21 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -1213,7 +1213,7 @@ xfs_btree_set_sibling(
 }
 
 void
-xfs_btree_init_block_int(
+xfs_btree_init_block(
 	struct xfs_mount	*mp,
 	struct xfs_btree_block	*buf,
 	const struct xfs_btree_ops *ops,
@@ -1255,7 +1255,7 @@ xfs_btree_init_block_int(
 }
 
 void
-xfs_btree_init_block(
+xfs_btree_init_buf(
 	struct xfs_mount		*mp,
 	struct xfs_buf			*bp,
 	const struct xfs_btree_ops	*ops,
@@ -1263,7 +1263,7 @@ xfs_btree_init_block(
 	__u16				numrecs,
 	__u64				owner)
 {
-	xfs_btree_init_block_int(mp, XFS_BUF_TO_BLOCK(bp), ops,
+	xfs_btree_init_block(mp, XFS_BUF_TO_BLOCK(bp), ops,
 			xfs_buf_daddr(bp), level, numrecs, owner);
 }
 
@@ -1289,7 +1289,7 @@ xfs_btree_init_block_cur(
 	else
 		owner = cur->bc_ag.pag->pag_agno;
 
-	xfs_btree_init_block_int(cur->bc_mp, XFS_BUF_TO_BLOCK(bp), cur->bc_ops,
+	xfs_btree_init_block(cur->bc_mp, XFS_BUF_TO_BLOCK(bp), cur->bc_ops,
 			xfs_buf_daddr(bp), level, numrecs, owner);
 }
 
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 3145d7e61cb4..5557aa4148e6 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -451,10 +451,10 @@ xfs_btree_reada_bufs(
 /*
  * Initialise a new btree block header
  */
-void xfs_btree_init_block(struct xfs_mount *mp, struct xfs_buf *bp,
+void xfs_btree_init_buf(struct xfs_mount *mp, struct xfs_buf *bp,
 		const struct xfs_btree_ops *ops, __u16 level, __u16 numrecs,
 		__u64 owner);
-void xfs_btree_init_block_int(struct xfs_mount *mp,
+void xfs_btree_init_block(struct xfs_mount *mp,
 		struct xfs_btree_block *buf, const struct xfs_btree_ops *ops,
 		xfs_daddr_t blkno, __u16 level, __u16 numrecs, __u64 owner);
 
diff --git a/fs/xfs/libxfs/xfs_btree_staging.c b/fs/xfs/libxfs/xfs_btree_staging.c
index 0bf20472dd27..de17d333ffb3 100644
--- a/fs/xfs/libxfs/xfs_btree_staging.c
+++ b/fs/xfs/libxfs/xfs_btree_staging.c
@@ -404,7 +404,7 @@ xfs_btree_bload_prep_block(
 		ifp->if_broot_bytes = (int)new_size;
 
 		/* Initialize it and send it out. */
-		xfs_btree_init_block_int(cur->bc_mp, ifp->if_broot,
+		xfs_btree_init_block(cur->bc_mp, ifp->if_broot,
 				cur->bc_ops, XFS_BUF_DADDR_NULL, level,
 				nr_this_block, cur->bc_ino.ip->i_ino);
 
diff --git a/fs/xfs/scrub/xfbtree.c b/fs/xfs/scrub/xfbtree.c
index 052fbc1086dc..95cbdd6738ec 100644
--- a/fs/xfs/scrub/xfbtree.c
+++ b/fs/xfs/scrub/xfbtree.c
@@ -416,7 +416,7 @@ xfbtree_init_leaf_block(
 	trace_xfbtree_create_root_buf(xfbt, bp);
 
 	bp->b_ops = cfg->btree_ops->buf_ops;
-	xfs_btree_init_block_int(mp, bp->b_addr, cfg->btree_ops, daddr, 0, 0,
+	xfs_btree_init_block(mp, bp->b_addr, cfg->btree_ops, daddr, 0, 0,
 			cfg->owner);
 	error = xfs_bwrite(bp);
 	xfs_buf_relse(bp);