diff mbox series

[2/2] xfs: test that the needsrepair feature works as advertised

Message ID 161647324275.3431002.7749171899745288999.stgit@magnolia (mailing list archive)
State New
Headers show
Series fstests: make sure NEEDSREPAIR feature stops mounts | expand

Commit Message

Darrick J. Wong March 23, 2021, 4:20 a.m. UTC
From: Darrick J. Wong <djwong@kernel.org>

Make sure that the needsrepair feature flag can be cleared only by
repair and that mounts are prohibited when the feature is set.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 tests/xfs/768     |   84 ++++++++++++++++++++++++++++++++++++++++++++
 tests/xfs/768.out |    2 +
 tests/xfs/770     |  101 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 tests/xfs/770.out |    2 +
 tests/xfs/group   |    2 +
 5 files changed, 191 insertions(+)
 create mode 100755 tests/xfs/768
 create mode 100644 tests/xfs/768.out
 create mode 100755 tests/xfs/770
 create mode 100644 tests/xfs/770.out
diff mbox series

Patch

diff --git a/tests/xfs/768 b/tests/xfs/768
new file mode 100755
index 00000000..a6926731
--- /dev/null
+++ b/tests/xfs/768
@@ -0,0 +1,84 @@ 
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0-or-later
+# Copyright (c) 2021 Oracle.  All Rights Reserved.
+#
+# FS QA Test No. 768
+#
+# Make sure that the kernel won't mount a filesystem if repair forcibly sets
+# NEEDSREPAIR while fixing metadata.  Corrupt a directory in such a way as
+# to force repair to write an invalid dirent value as a sentinel to trigger a
+# repair activity in a later phase.  Use a debug knob in xfs_repair to abort
+# the repair immediately after forcing the flag on.
+
+seq=`basename $0`
+seqres=$RESULT_DIR/$seq
+echo "QA output created by $seq"
+
+here=`pwd`
+tmp=/tmp/$$
+status=1    # failure is the default!
+trap "_cleanup; exit \$status" 0 1 2 3 15
+
+_cleanup()
+{
+	cd /
+	rm -f $tmp.*
+}
+
+# get standard environment, filters and checks
+. ./common/rc
+. ./common/filter
+
+# real QA test starts here
+_supported_fs xfs
+_require_scratch
+grep -q LIBXFS_DEBUG_WRITE_CRASH $XFS_REPAIR_PROG || \
+		_notrun "libxfs write failure injection hook not detected?"
+
+rm -f $seqres.full
+
+# Set up a real filesystem for our actual test
+_scratch_mkfs -m crc=1 >> $seqres.full
+
+# Create a directory large enough to have a dir data block.  2k worth of
+# dirent names ought to do it.
+_scratch_mount
+mkdir -p $SCRATCH_MNT/fubar
+for i in $(seq 0 256 2048); do
+	fname=$(printf "%0255d" $i)
+	ln -s -f urk $SCRATCH_MNT/fubar/$fname
+done
+inum=$(stat -c '%i' $SCRATCH_MNT/fubar)
+_scratch_unmount
+
+# Fuzz the directory
+_scratch_xfs_db -x -c "inode $inum" -c "dblock 0" \
+	-c "fuzz -d bu[2].inumber add" >> $seqres.full
+
+# Try to repair the directory, force it to crash after setting needsrepair
+LIBXFS_DEBUG_WRITE_CRASH=ddev=2 _scratch_xfs_repair 2>> $seqres.full
+test $? -eq 137 || echo "repair should have been killed??"
+_scratch_xfs_db -c 'version' >> $seqres.full
+
+# We can't mount, right?
+_scratch_xfs_db -c 'version' | grep -q NEEDSREPAIR || \
+	echo "NEEDSREPAIR should be set on superblock"
+_try_scratch_mount &> $tmp.mount
+res=$?
+_filter_scratch < $tmp.mount
+if [ $res -eq 0 ]; then
+	echo "Should not be able to mount after needsrepair crash"
+	_scratch_unmount
+fi
+
+# Repair properly this time and retry the mount
+_scratch_xfs_repair 2>> $seqres.full
+_scratch_xfs_db -c 'version' >> $seqres.full
+_scratch_xfs_db -c 'version' | grep -q NEEDSREPAIR && \
+	echo "NEEDSREPAIR should not be set on superblock"
+
+_scratch_mount
+
+# success, all done
+status=0
+exit
diff --git a/tests/xfs/768.out b/tests/xfs/768.out
new file mode 100644
index 00000000..a7fec26a
--- /dev/null
+++ b/tests/xfs/768.out
@@ -0,0 +1,2 @@ 
+QA output created by 768
+mount: SCRATCH_MNT: mount(2) system call failed: Structure needs cleaning.
diff --git a/tests/xfs/770 b/tests/xfs/770
new file mode 100755
index 00000000..b53dd0b1
--- /dev/null
+++ b/tests/xfs/770
@@ -0,0 +1,101 @@ 
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0-or-later
+# Copyright (c) 2021 Oracle.  All Rights Reserved.
+#
+# FS QA Test No. 770
+#
+# Populate a filesystem with all types of metadata, then run repair with the
+# libxfs write failure trigger set to go after a single write.  Check that the
+# injected error trips, causing repair to abort, that needsrepair is set on the
+# fs, the kernel won't mount; and that a non-injecting repair run clears
+# needsrepair and makes the filesystem mountable again.
+#
+# Repeat with the trip point set to successively higher numbers of writes until
+# we hit ~200 writes or repair manages to run to completion without tripping.
+
+seq=`basename $0`
+seqres=$RESULT_DIR/$seq
+echo "QA output created by $seq"
+
+here=`pwd`
+tmp=/tmp/$$
+status=1    # failure is the default!
+trap "_cleanup; exit \$status" 0 1 2 3 15
+
+_cleanup()
+{
+	cd /
+	rm -f $tmp.*
+}
+
+# get standard environment, filters and checks
+. ./common/rc
+. ./common/populate
+. ./common/filter
+
+# real QA test starts here
+_supported_fs xfs
+
+_require_scratch_xfs_crc		# needsrepair only exists for v5
+_require_populate_commands
+
+rm -f ${RESULT_DIR}/require_scratch	# we take care of checking the fs
+rm -f $seqres.full
+
+max_writes=200			# 200 loops should be enough for anyone
+nr_incr=$((13 / TIME_FACTOR))
+test $nr_incr -lt 1 && nr_incr=1
+for ((nr_writes = 1; nr_writes < max_writes; nr_writes += nr_incr)); do
+	test -w /dev/ttyprintk && \
+		echo "fail after $nr_writes writes" >> /dev/ttyprintk
+	echo "fail after $nr_writes writes" >> $seqres.full
+
+	# Populate the filesystem
+	_scratch_populate_cached nofill >> $seqres.full 2>&1
+
+	# Start a repair and force it to abort after some number of writes
+	LIBXFS_DEBUG_WRITE_CRASH=ddev=$nr_writes _scratch_xfs_repair 2>> $seqres.full
+	res=$?
+	if [ $res -ne 0 ] && [ $res -ne 137 ]; then
+		echo "repair failed with $res??"
+		break
+	elif [ $res -eq 0 ]; then
+		[ $nr_writes -eq 1 ] && \
+			echo "ran to completion on the first try?"
+		break
+	fi
+
+	_scratch_xfs_db -c 'version' >> $seqres.full
+	if _scratch_xfs_db -c 'version' | grep -q NEEDSREPAIR; then
+		# NEEDSREPAIR is set, so check that we can't mount.
+		_try_scratch_mount &>> $seqres.full
+		if [ $? -eq 0 ]; then
+			echo "Should not be able to mount after repair crash"
+			_scratch_unmount
+		fi
+	elif _scratch_xfs_repair -n &>> $seqres.full; then
+		# NEEDSREPAIR was not set, but repair -n didn't find problems.
+		# It's possible that the write failure injector triggered on
+		# the write that clears NEEDSREPAIR.
+		true
+	else
+		# NEEDSREPAIR was not set, but there are errors!
+		echo "NEEDSREPAIR should be set on corrupt fs"
+	fi
+
+	# Repair properly this time and retry the mount
+	_scratch_xfs_repair 2>> $seqres.full
+	_scratch_xfs_db -c 'version' >> $seqres.full
+	_scratch_xfs_db -c 'version' | grep -q NEEDSREPAIR && \
+		echo "NEEDSREPAIR should not be set on superblock"
+
+	# Make sure all the checking tools think this fs is ok
+	_scratch_mount
+	_check_scratch_fs
+	_scratch_unmount
+done
+
+# success, all done
+echo Silence is golden.
+status=0
+exit
diff --git a/tests/xfs/770.out b/tests/xfs/770.out
new file mode 100644
index 00000000..725d740b
--- /dev/null
+++ b/tests/xfs/770.out
@@ -0,0 +1,2 @@ 
+QA output created by 770
+Silence is golden.
diff --git a/tests/xfs/group b/tests/xfs/group
index 45628739..6aa7883e 100644
--- a/tests/xfs/group
+++ b/tests/xfs/group
@@ -517,5 +517,7 @@ 
 538 auto stress
 759 auto quick rw realtime
 760 auto quick rw realtime collapse insert unshare zero prealloc
+768 auto quick repair
+770 auto repair
 917 auto quick db
 918 auto quick db