[PATCH v5 12/12] ext4: Atomic write test for extent split across leaf nodes

[Ojaswin Mujoo <ojaswin@linux.ibm.com>]

In ext4, even if an allocated range is physically and logically
contiguous, it can still be split into 2 extents. This is because ext4
does not merge extents across leaf nodes. This is an issue for atomic
writes since even for a continuous extent the map block could (in rare
cases) return a shorter map, hence tearning the write. This test creates
such a file and ensures that the atomic write handles this case
correctly

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Ojaswin Mujoo <ojaswin@linux.ibm.com>
---
 tests/ext4/063     | 129 +++++++++++++++++++++++++++++++++++++++++++++
 tests/ext4/063.out |   2 +
 2 files changed, 131 insertions(+)
 create mode 100755 tests/ext4/063
 create mode 100644 tests/ext4/063.out

diff --git a/tests/ext4/063 b/tests/ext4/063
new file mode 100755
index 00000000..19fb611b
--- /dev/null
+++ b/tests/ext4/063
@@ -0,0 +1,129 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2025 IBM Corporation. All Rights Reserved.
+#
+# In ext4, even if an allocated range is physically and logically contiguous,
+# it can still be split into 2 or more extents. This is because ext4 does not
+# merge extents across leaf nodes. This is an issue for atomic writes since
+# even for a continuous extent the map block could (in rare cases) return a
+# shorter map, hence tearing the write. This test creates such a file and
+# ensures that the atomic write handles this case correctly
+#
+. ./common/preamble
+. ./common/atomicwrites
+_begin_fstest auto atomicwrites
+
+_require_scratch_write_atomic_multi_fsblock
+_require_atomic_write_test_commands
+_require_command "$DEBUGFS_PROG" debugfs
+
+prep() {
+	local bs=`_get_block_size $SCRATCH_MNT`
+	local ex_hdr_bytes=12
+	local ex_entry_bytes=12
+	local entries_per_blk=$(( (bs - ex_hdr_bytes) / ex_entry_bytes ))
+
+	# fill the extent tree leaf with bs len extents at alternate offsets.
+	# The tree should look as follows
+	#
+	#                    +---------+---------+
+	#                    | index 1 | index 2 |
+	#                    +-----+---+-----+---+
+	#                   +------+         +-----------+
+	#                   |                            |
+	#      +-------+-------+---+---------+     +-----+----+
+	#      | ex 1  | ex 2  |   |  ex n   |     |  ex n+1  |
+	#      | off:0 | off:2 |...| off:678 |     |  off:680 |
+	#      | len:1 | len:1 |   |  len:1  |     |   len:1  |
+	#      +-------+-------+---+---------+     +----------+
+	#
+	for i in $(seq 0 $entries_per_blk)
+	do
+		$XFS_IO_PROG -fc "pwrite -b $bs $((i * 2 * bs)) $bs" $testfile > /dev/null
+	done
+	sync $testfile
+
+	echo >> $seqres.full
+	echo "Create file with extents spanning 2 leaves. Extents:">> $seqres.full
+	echo "...">> $seqres.full
+	$DEBUGFS_PROG -R "ex `basename $testfile`" $SCRATCH_DEV |& tail >> $seqres.full
+
+	# Now try to insert a new extent ex(new) between ex(n) and ex(n+1).
+	# Since this is a new FS the allocator would find continuous blocks
+	# such that ex(n) ex(new) ex(n+1) are physically(and logically)
+	# contiguous. However, since we don't merge extents across leaf we will
+	# end up with a tree as:
+	#
+	#                    +---------+---------+
+	#                    | index 1 | index 2 |
+	#                    +-----+---+-----+---+
+	#                   +------+         +------------+
+	#                   |                             |
+	#      +-------+-------+---+---------+     +------+-----------+
+	#      | ex 1  | ex 2  |   |  ex n   |     |  ex n+1 (merged) |
+	#      | off:0 | off:2 |...| off:678 |     |      off:679     |
+	#      | len:1 | len:1 |   |  len:1  |     |      len:2       |
+	#      +-------+-------+---+---------+     +------------------+
+	#
+	echo >> $seqres.full
+	torn_ex_offset=$((((entries_per_blk * 2) - 1) * bs))
+	$XFS_IO_PROG -c "pwrite $torn_ex_offset $bs" $testfile >> /dev/null
+	sync $testfile
+
+	echo >> $seqres.full
+	echo "Perform 1 block write at $torn_ex_offset to create torn extent. Extents:">> $seqres.full
+	echo "...">> $seqres.full
+	$DEBUGFS_PROG -R "ex `basename $testfile`" $SCRATCH_DEV |& tail >> $seqres.full
+
+	_scratch_cycle_mount
+}
+
+_scratch_mkfs >> $seqres.full
+_scratch_mount >> $seqres.full
+
+testfile=$SCRATCH_MNT/testfile
+touch $testfile
+awu_max=$(_get_atomic_write_unit_max $testfile)
+
+echo >> $seqres.full
+echo "# Prepping the file" >> $seqres.full
+prep
+
+torn_aw_offset=$((torn_ex_offset - (torn_ex_offset % awu_max)))
+
+echo >> $seqres.full
+echo "# Performing atomic IO on the torn extent range. Command: " >> $seqres.full
+echo $XFS_IO_PROG -c "open -fsd $testfile" -c "pwrite -S 0x61 -DA -V1 -b $awu_max $torn_aw_offset $awu_max" >> $seqres.full
+$XFS_IO_PROG -c "open -fsd $testfile" -c "pwrite -S 0x61 -DA -V1 -b $awu_max $torn_aw_offset $awu_max" >> $seqres.full
+
+echo >> $seqres.full
+echo "Extent state after atomic write:">> $seqres.full
+echo "...">> $seqres.full
+$DEBUGFS_PROG -R "ex `basename $testfile`" $SCRATCH_DEV |& tail >> $seqres.full
+
+echo >> $seqres.full
+echo "# Checking data integrity" >> $seqres.full
+
+# create a dummy file with expected data
+$XFS_IO_PROG -fc "pwrite -S 0x61 -b $awu_max 0 $awu_max" $testfile.exp >> /dev/null
+expected_data=$(od -An -t x1 -j 0 -N $awu_max $testfile.exp)
+
+# We ensure that the data after atomic writes should match the expected data
+actual_data=$(od -An -t x1 -j $torn_aw_offset -N $awu_max $testfile)
+if [[ "$actual_data" != "$expected_data" ]]
+then
+	echo "Checksum match failed at off: $torn_aw_offset size: $awu_max"
+	echo
+	echo "Expected: "
+	echo "$expected_data"
+	echo
+	echo "Actual contents: "
+	echo "$actual_data"
+
+	_fail
+fi
+
+echo -n "Data verification at offset $torn_aw_offset suceeded!" >> $seqres.full
+echo "Silence is golden"
+status=0
+exit
diff --git a/tests/ext4/063.out b/tests/ext4/063.out
new file mode 100644
index 00000000..de35fc52
--- /dev/null
+++ b/tests/ext4/063.out
@@ -0,0 +1,2 @@
+QA output created by 063
+Silence is golden
-- 
2.49.0