[PATCH] ext4/064: add regression test for delalloc remount leak

A delalloc filesystem rejects a remount with nodelalloc, but ext4 used to
apply the option change before rejecting the remount.  Concurrent buffered
writes and truncates can observe the transient nodelalloc state and fail to
release delayed allocation reservations.  The leaked reservations are then
reported when the inodes are evicted during unmount.

Add an ext4 regression test that starts concurrent write/truncate workers and
an expected-failing remount,nodelalloc worker, stops them after a short stress
window, and checks dmesg for leaked delayed allocation reservations.

The proposed kernel fix is still under review:
https://lore.kernel.org/linux-ext4/[email protected]/

Local validation showed that the test fails without the proposed kernel fix,
with i_reserved_data_blocks not cleared warnings during unmount, and passes
with the proposed fix applied.

Signed-off-by: guzebing <[email protected]>
---
 tests/ext4/064     | 216 +++++++++++++++++++++++++++++++++++++++++++++
 tests/ext4/064.out |   2 +
 2 files changed, 218 insertions(+)
 create mode 100755 tests/ext4/064
 create mode 100644 tests/ext4/064.out

diff --git a/tests/ext4/064 b/tests/ext4/064
new file mode 100755
index 00000000..5d43764c
--- /dev/null
+++ b/tests/ext4/064
@@ -0,0 +1,216 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2026 guzebing.  All Rights Reserved.
+#
+# FS QA Test No. ext4/064
+#
+# Exercise rejected delalloc to nodelalloc remounts while buffered writes and
+# truncates are active.  A remount used to clear EXT4_MOUNT_DELALLOC before
+# rejecting the transition, so a concurrent truncate could fail to release
+# delayed allocation reservations.  The leaked inode reservation is reported
+# when the inode is evicted during unmount.
+#
+# This is a regression test for the issue fixed by the proposed patch:
+# "ext4: reject delalloc to nodelalloc remount before applying options"
+# https://lore.kernel.org/linux-ext4/[email protected]/
+#
+. ./common/preamble
+_begin_fstest auto stress mount
+
+writer_pids=()
+remounter_pid=
+stop_file=$tmp.stop
+worker_error=$tmp.worker_error
+remounter_error=$tmp.remounter_error
+remounter_count=$tmp.remounter_count
+
+stop_workload()
+{
+	touch "$stop_file"
+	if [ -n "$remounter_pid" ]; then
+		wait "$remounter_pid" 2>/dev/null
+		remounter_pid=
+	fi
+	if [ "${#writer_pids[@]}" -gt 0 ]; then
+		wait "${writer_pids[@]}" 2>/dev/null
+		writer_pids=()
+	fi
+}
+
+# Override the default cleanup function.
+_cleanup()
+{
+	stop_workload
+	cd /
+	_is_dir_mountpoint "$SCRATCH_MNT" >/dev/null &&
+		_scratch_unmount >/dev/null 2>&1
+	rm -f "$stop_file" "$worker_error" "$worker_error".* \
+		"$tmp.xfs_io_error".* "$remounter_error" "$remounter_count"
+}
+
+# Import common functions.
+. ./common/filter
+
+_exclude_fs ext2
+_exclude_fs ext3
+_exclude_scratch_mount_option "data=journal" "dax" "nodelalloc"
+_require_check_dmesg
+_require_scratch_size $((2 * 1024 * 1024))
+_require_xfs_io_command "pwrite"
+_require_xfs_io_command "truncate"
+
+record_worker_error()
+{
+	local command=$1
+	local file=$2
+	local err=$3
+	local log=$worker_error.$BASHPID
+
+	{
+		echo "worker failed:"
+		echo "  command: $command"
+		echo "  file: $file"
+		echo "  stderr:"
+		if [ -s "$err" ]; then
+			sed 's/^/    /' "$err"
+		else
+			echo "    <empty>"
+		fi
+	} > "$log"
+	touch "$worker_error"
+}
+
+write_truncate_loop()
+{
+	local file=$1
+	local err=$tmp.xfs_io_error.$BASHPID
+
+	while [ ! -e "$stop_file" ]; do
+		$XFS_IO_PROG -f -c "pwrite -q 0 32m" "$file" \
+			>/dev/null 2>"$err" || {
+			record_worker_error \
+				'xfs_io -f -c "pwrite -q 0 32m"' "$file" "$err"
+			break
+		}
+		$XFS_IO_PROG -c "truncate 256k" "$file" \
+			>/dev/null 2>"$err" || {
+			record_worker_error \
+				'xfs_io -c "truncate 256k"' "$file" "$err"
+			break
+		}
+	done
+	rm -f "$err"
+}
+
+log_worker_errors()
+{
+	local log
+
+	test -e "$worker_error" || return 0
+
+	echo "write/truncate worker failure details:" >> "$seqres.full"
+	for log in "$worker_error".*; do
+		test -f "$log" || continue
+		cat "$log" >> "$seqres.full"
+	done
+}
+
+remount_loop()
+{
+	local count=0
+
+	while [ ! -e "$stop_file" ]; do
+		# This remount is expected to fail.  The bug is that ext4 used
+		# to expose the transient nodelalloc state before failing it.
+		if $MOUNT_PROG -o remount,nodelalloc "$SCRATCH_DEV" "$SCRATCH_MNT" \
+			>/dev/null 2>&1; then
+			echo "delalloc to nodelalloc remount unexpectedly succeeded" \
+				> "$remounter_error"
+			touch "$stop_file"
+			break
+		fi
+		count=$((count + 1))
+	done
+	echo "$count" > "$remounter_count"
+}
+
+log_remount_result()
+{
+	local remounts=0
+
+	if [ -s "$remounter_count" ]; then
+		read -r remounts < "$remounter_count"
+	fi
+	echo "rejected remounts: $remounts" >> "$seqres.full"
+
+	if [ -s "$remounter_error" ]; then
+		echo "remount worker failure details:" >> "$seqres.full"
+		sed 's/^/  /' "$remounter_error" >> "$seqres.full"
+	fi
+}
+
+sleep_msg_ratelimit_interval()
+{
+	local dev=$(_short_dev "$SCRATCH_DEV")
+	local interval_file=/sys/fs/ext4/$dev/msg_ratelimit_interval_ms
+	local interval_ms=0
+	local sleep_secs
+
+	if [ -r "$interval_file" ]; then
+		read -r interval_ms < "$interval_file"
+	fi
+	case "$interval_ms" in
+	''|*[!0-9]*)
+		interval_ms=0
+		;;
+	esac
+
+	sleep_secs=$(((interval_ms + 999) / 1000 + 1))
+	# Repeated expected remount failures can consume ext4's message
+	# ratelimit budget.  Wait one interval plus one second before
+	# unmount so "i_reserved_data_blocks .* not cleared!" is not
+	# filtered out by the ratelimit.
+	echo "sleeping ${sleep_secs}s for ext4 msg ratelimit interval" \
+		"(${interval_ms}ms)" >> "$seqres.full"
+	sleep "$sleep_secs"
+}
+
+echo "Silence is golden"
+
+_scratch_mkfs >> "$seqres.full" 2>&1
+_scratch_mount -o delalloc
+
+options_file=/proc/fs/ext4/$(_short_dev "$SCRATCH_DEV")/options
+grep -qw delalloc "$options_file" ||
+	_fail "scratch filesystem is not mounted with delalloc"
+
+for ((i = 0; i < 16; i++)); do
+	write_truncate_loop "$SCRATCH_MNT/file-$i" &
+	writer_pids+=("$!")
+done
+
+remount_loop &
+remounter_pid=$!
+
+runtime=$((30 * TIME_FACTOR))
+sleep "$runtime"
+
+stop_workload
+log_worker_errors
+log_remount_result
+
+sleep_msg_ratelimit_interval
+_scratch_unmount || _fail "scratch filesystem unmount failed"
+
+warning="i_reserved_data_blocks .* not cleared!"
+if _check_dmesg_for "$warning"; then
+	_dmesg_since_test_start | grep -E "$warning" >> "$seqres.full"
+	_fail "delayed allocation reservations leaked during rejected remount"
+fi
+test ! -e "$remounter_error" ||
+	_fail "delalloc to nodelalloc remount unexpectedly succeeded"
+test ! -e "$worker_error" || _fail "write/truncate worker failed"
+
+# success, all done
+status=0
+exit
diff --git a/tests/ext4/064.out b/tests/ext4/064.out
new file mode 100644
index 00000000..d9076546
--- /dev/null
+++ b/tests/ext4/064.out
@@ -0,0 +1,2 @@
+QA output created by 064
+Silence is golden

base-commit: acb6d4cb84205a8e3f19ca470cfcf7bf6d93a509
-- 
2.20.1