xfs: test for metadata corruption error reporting via healthmon

Check if we can detect runtime metadata corruptions via the health
monitor.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Zorro Lang <zlang@redhat.com>
Signed-off-by: Zorro Lang <zlang@kernel.org>

diff --git a/tests/xfs/655 b/tests/xfs/655
new file mode 100755 (executable)
index 0000000..a4162d7
--- /dev/null
+++ b/tests/xfs/655
@@ -0,0 +1,98 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2024-2026 Oracle.  All Rights Reserved.
+#
+# FS QA Test No. 655
+#
+# Corrupt some metadata and try to access it with the health monitoring program
+# running.  Check that healthmon observes a metadata error.
+#
+. ./common/preamble
+_begin_fstest auto quick eio selfhealing
+
+_cleanup()
+{
+       cd /
+       test -n "$healer_pid" && kill $healer_pid &>/dev/null
+       wait
+       rm -rf $tmp.* $testdir
+}
+
+. ./common/filter
+
+_require_scratch_nocheck
+_require_scratch_xfs_crc # can't detect minor corruption w/o crc
+_require_xfs_io_command healthmon
+
+# Disable the scratch rt device to avoid test failures relating to the rt
+# bitmap consuming all the free space in our small data device.
+unset SCRATCH_RTDEV
+
+echo "Format and mount"
+_scratch_mkfs -d agcount=1 | _filter_mkfs 2> $tmp.mkfs >> $seqres.full
+. $tmp.mkfs
+_scratch_mount
+mkdir $SCRATCH_MNT/a/
+# Enough entries to get to a single block directory
+for ((i = 0; i < ( (isize + 255) / 256); i++)); do
+       path="$(printf "%s/a/%0255d" "$SCRATCH_MNT" "$i")"
+       touch "$path"
+done
+inum="$(stat -c %i "$SCRATCH_MNT/a")"
+_scratch_unmount
+
+# Fuzz the directory block so that the touch below will be guaranteed to trip
+# a runtime sickness report in exactly the manner we desire.
+_scratch_xfs_db -x -c "inode $inum" -c "dblock 0" -c 'fuzz bhdr.hdr.owner add' -c print &>> $seqres.full
+
+# Try to allocate space to trigger a metadata corruption event
+echo "Runtime corruption detection"
+_scratch_mount
+$XFS_IO_PROG -c 'healthmon -c -v' $SCRATCH_MNT > $tmp.healthmon &
+healer_pid=$!
+sleep 1        # wait for program to start up
+touch $SCRATCH_MNT/a/farts &>> $seqres.full
+_scratch_unmount
+
+wait   # for healthmon to finish
+unset healer_pid
+
+# Did we get errors?
+check_healthmon()
+{
+       cat $tmp.healthmon >> $seqres.full
+       _filter_scratch < $tmp.healthmon | \
+               grep -E '(sick|corrupt)' | \
+               sed -e 's|SCRATCH_MNT/a|VICTIM|g' \
+                   -e 's|SCRATCH_MNT ino [0-9]* gen 0x[0-9a-f]*|VICTIM|g' | \
+               sort | \
+               uniq
+}
+check_healthmon
+
+# Run scrub to trigger a health event from there too.
+echo "Scrub corruption detection"
+_scratch_mount
+if _supports_xfs_scrub $SCRATCH_MNT $SCRATCH_DEV; then
+       $XFS_IO_PROG -c 'healthmon -c -v' $SCRATCH_MNT > $tmp.healthmon &
+       healer_pid=$!
+       sleep 1 # wait for program to start up
+       $XFS_SCRUB_PROG -n $SCRATCH_MNT &>> $seqres.full
+       _scratch_unmount
+
+       wait    # for healthmon to finish
+       unset healer_pid
+
+       # Did we get errors?
+       check_healthmon
+else
+       # mock the output since we don't support scrub
+       _scratch_unmount
+       cat << ENDL
+VICTIM directory: corrupt
+VICTIM directory: sick
+VICTIM parent: corrupt
+ENDL
+fi
+
+_exit 0

diff --git a/tests/xfs/655.out b/tests/xfs/655.out
new file mode 100644 (file)
index 0000000..f46d7fa
--- /dev/null
+++ b/tests/xfs/655.out
@@ -0,0 +1,8 @@
+QA output created by 655
+Format and mount
+Runtime corruption detection
+VICTIM directory: sick
+Scrub corruption detection
+VICTIM directory: corrupt
+VICTIM directory: sick
+VICTIM parent: corrupt