apfstests/tests/xfs/070

#! /bin/bash
# SPDX-License-Identifier: GPL-2.0
# Copyright (c) 2015 Red Hat, Inc. All Rights Reserved.
#
# FS QA Test No. 070
#
# As part of superblock verification, xfs_repair checks the primary sb and
# verifies all secondary sb's against the primary. In the event of geometry
# inconsistency, repair uses a heuristic that tracks the most frequently
# occurring settings across the set of N (agcount) superblocks.
#
# xfs_repair was subject to a bug that disregards this heuristic in the event
# that the last secondary superblock in the fs is corrupt. The side effect is an
# unnecessary and potentially time consuming brute force superblock scan.
#
# This is a regression test for the aforementioned xfs_repair bug. We
# intentionally corrupt the last superblock in the fs, run xfs_repair and
# verify it repairs the fs correctly. We explicitly detect a brute force scan
# and abort the repair to save time in the failure case.
#
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.*
	$KILLALL_PROG -9 $XFS_REPAIR_PROG > /dev/null 2>&1
	wait > /dev/null 2>&1
}

# Start and monitor an xfs_repair of the scratch device. This test can induce a
# time consuming brute force superblock scan. Since a brute force scan means
# test failure, detect it and end the repair.
_xfs_repair_noscan()
{
	# invoke repair directly so we can kill the process if need be
	[ "$USE_EXTERNAL" = yes -a ! -z "$SCRATCH_LOGDEV" ] && \
		log_repair_opts="-l $SCRATCH_LOGDEV"
	[ "$USE_EXTERNAL" = yes ] && [ -n "$SCRATCH_RTDEV" ] && \
		rt_repair_opts="-r $SCRATCH_RTDEV"
	$XFS_REPAIR_PROG $log_repair_opts $rt_repair_opts $SCRATCH_DEV 2>&1 |
		tee -a $seqres.full > $tmp.repair &
	repair_pid=$!

	# monitor progress for as long as it is running
	while [ `pgrep xfs_repair` ]; do
		grep "couldn't verify primary superblock" $tmp.repair \
			> /dev/null 2>&1
		if [ $? == 0 ]; then
			# we've started a brute force scan. kill repair and
			# fail the test
			kill -9 $repair_pid >> $seqres.full 2>&1
			wait >> $seqres.full 2>&1

			_fail "xfs_repair resorted to brute force scan"
		fi

		sleep 1
	done

	wait

	cat $tmp.repair | _filter_repair
}

rm -f $seqres.full

# get standard environment, filters and checks
. ./common/rc
. ./common/filter
. ./common/repair

# real QA test starts here

# Modify as appropriate.
_supported_fs xfs
_require_scratch_nocheck
_require_command "$KILLALL_PROG" killall

_scratch_mkfs | _filter_mkfs > /dev/null 2> $tmp.mkfs || _fail "mkfs failed"

. $tmp.mkfs # import agcount

# corrupt the last secondary sb in the fs
_scratch_xfs_db -x -c "sb $((agcount - 1))" -c "type data" \
	-c "write fill 0xff 0 512"

# attempt to repair
_xfs_repair_noscan

# success, all done
status=0
exit