new file mode 100755
@@ -0,0 +1,123 @@
+#! /bin/bash
+# FSQA Test No. 098
+#
+# Test that if we fsync a file that got one extent partially cloned into a
+# lower file offset, after a power failure our file has the same content it
+# had before the power failure and after the extent cloning operation.
+#
+#-----------------------------------------------------------------------
+#
+# Copyright (C) 2015 SUSE Linux Products GmbH. All Rights Reserved.
+# Author: Filipe Manana <fdmanana@suse.com>
+#
+# This program is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public License as
+# published by the Free Software Foundation.
+#
+# This program is distributed in the hope that it would be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write the Free Software Foundation,
+# Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+#-----------------------------------------------------------------------
+#
+
+seq=`basename $0`
+seqres=$RESULT_DIR/$seq
+echo "QA output created by $seq"
+tmp=/tmp/$$
+status=1 # failure is the default!
+trap "_cleanup; exit \$status" 0 1 2 3 15
+
+_cleanup()
+{
+ _cleanup_flakey
+ rm -f $tmp.*
+}
+
+# get standard environment, filters and checks
+. ./common/rc
+. ./common/filter
+. ./common/dmflakey
+
+# real QA test starts here
+_need_to_be_root
+_supported_fs btrfs
+_supported_os Linux
+_require_scratch
+_require_dm_flakey
+_require_cloner
+_require_metadata_journaling $SCRATCH_DEV
+
+rm -f $seqres.full
+
+_scratch_mkfs >>$seqres.full 2>&1
+_init_flakey
+_mount_flakey
+
+# Create our test file with a single 100K extent starting at file offset 800K.
+# We fsync the file here to make the fsync log tree gets a single csum item that
+# covers the whole 100K extent, which causes the second fsync, done after the
+# cloning operation below, to not leave in the log tree two csum items covering
+# two sub-ranges ([0, 20K[ and [20K, 100K[)) of our extent.
+$XFS_IO_PROG -f -c "pwrite -S 0xaa 800K 100K" \
+ -c "fsync" \
+ $SCRATCH_MNT/foo | _filter_xfs_io
+
+# Now clone part of our extent into file offset 400K. This adds a file extent
+# item to our inode's metadata that points to the 100K extent we created before,
+# using a data offset of 20K and a data length of 20K, so that it refers to
+# the sub-range [20K, 40K[ of our original extent.
+$CLONER_PROG -s $((800 * 1024 + 20 * 1024)) -d $((400 * 1024)) \
+ -l $((20 * 1024)) $SCRATCH_MNT/foo $SCRATCH_MNT/foo
+
+# Now fsync our file to make sure the extent cloning is durably persisted. This
+# fsync will not add a second csum item to the log tree containing the checksums
+# for the blocks in the sub-range [20K, 40K[ of our extent, because there was
+# already a csum item in the log tree covering the whole extent, added by the
+# first fsync we did before.
+$XFS_IO_PROG -c "fsync" $SCRATCH_MNT/foo
+
+echo "File digest before power failure:"
+md5sum $SCRATCH_MNT/foo | _filter_scratch
+
+# Silently drop all writes and ummount to simulate a crash/power failure.
+_load_flakey_table $FLAKEY_DROP_WRITES
+_unmount_flakey
+
+# Allow writes again, mount to trigger log replay and validate file contents.
+# The fsync log replay first processes the file extent item corresponding to the
+# file offset 400K (the one which refers to the [20K, 40K[ sub-range of our 100K
+# extent) and then processes the file extent item for file offset 800K. It used
+# to happen that when processing the later, it erroneously left in the csum tree
+# 2 csum items that overlapped each other, 1 for the sub-range [20K, 40K[ and 1
+# for the whole range of our extent. This introduced a problem where subsequent
+# lookups for the checksums of blocks within the range [40K, 100K[ of our extent
+# would not find anything because lookups in the csum tree ended up looking only
+# at the smaller csum item, the one covering the subrange [20K, 40K[. This made
+# read requests assume an expected checksum with a value of 0 for those blocks,
+# which caused checksum verification failure when the read operations finished.
+# However those checksum failure did not result in read requests returning an
+# error to user space (like -EIO for e.g.) because the expected checksum value
+# had the special value 0, and in that case btrfs set all bytes of the
+# corresponding pages with the value 0x01 and produce the following warning in
+# dmesg/syslog:
+#
+# "BTRFS warning (device dm-0): csum failed ino 257 off 917504 csum 1322675045\
+# expected csum 0"
+#
+_load_flakey_table $FLAKEY_ALLOW_WRITES
+_mount_flakey
+
+echo "File digest after log replay:"
+# Must match the same digest he had after cloning the extent and before the
+# power failure happened.
+md5sum $SCRATCH_MNT/foo | _filter_scratch
+
+_unmount_flakey
+
+status=0
+exit
new file mode 100644
@@ -0,0 +1,7 @@
+QA output created by 098
+wrote 102400/102400 bytes at offset 819200
+XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+File digest before power failure:
+39b386375971248740ed8651d5a2ed9f SCRATCH_MNT/foo
+File digest after log replay:
+39b386375971248740ed8651d5a2ed9f SCRATCH_MNT/foo
@@ -100,3 +100,4 @@
095 auto quick metadata
096 auto quick clone
097 auto quick send clone
+098 auto quick metadata clone