#! /bin/bash
# SPDX-License-Identifier: GPL-2.0
# Copyright (C) 2021 SUSE Linux Products GmbH. All Rights Reserved.
#
# FSQA Test No. 239
#
# Test a particular scenario where we fsync a directory, then move one of its
# children directories into another directory and then finally sync the log
# trees by fsyncing any other inode. We want to check that after a power failure
# we are able to mount the filesystem and that the moved directory exists only
# as a child of the directory we moved it into.
#
. ./common/preamble
_begin_fstest auto quick log

# Override the default cleanup function.
_cleanup()
{
	_cleanup_flakey
	cd /
	rm -f $tmp.*
}

. ./common/filter
. ./common/dmflakey

_require_scratch
_require_dm_target flakey

# The test requires a very specific layout of keys and items in the fs/subvolume
# btree to trigger a bug. So we want to make sure that on whatever platform we
# are, we have the same leaf/node size.
#
# Currently in btrfs the node/leaf size can not be smaller than the page
# size (but it can be greater than the page size). So use the largest
# supported node/leaf size (64K).
#
_scratch_mkfs "-n 65536" >>$seqres.full 2>&1
_require_metadata_journaling $SCRATCH_DEV
_init_flakey
_mount_flakey

# "testdir" is inode 257.
mkdir $SCRATCH_MNT/testdir
chmod 755 $SCRATCH_MNT/testdir

# Create several empty files to have the directory "testdir" with its items
# spread over several leaves (7 in this case).
for ((i = 1; i <= 1200; i++)); do
	echo -n > $SCRATCH_MNT/testdir/file$i
done

# Create our test directory "dira", inode number 1458, which gets all its items
# in leaf 7.
#
# The BTRFS_DIR_ITEM_KEY item for inode 257 ("testdir") that points to the entry
# named "dira" is in leaf 2, while the BTRFS_DIR_INDEX_KEY item that points to
# that entry is in leaf 3.
#
# For this particular filesystem node size (64K), file count and file names, we
# endup with the directory entry items from inode 257 in leaves 2 and 3, as
# previously mentioned - what matters for triggering the bug exercised by this
# test case is that those items are not placed in leaf 1, they must be placed in
# a leaf different from the one containing the inode item for inode 257.
#
# The corresponding BTRFS_DIR_ITEM_KEY and BTRFS_DIR_INDEX_KEY items for the
# parent inode (257) are the following:
#
#           item 460 key (257 DIR_ITEM 3724298081) itemoff 48344 itemsize 34
#                location key (1458 INODE_ITEM 0) type DIR
#                transid 6 data_len 0 name_len 4
#                name: dira
#
# and:
#
#           item 771 key (257 DIR_INDEX 1202) itemoff 36673 itemsize 34
#                location key (1458 INODE_ITEM 0) type DIR
#                transid 6 data_len 0 name_len 4
#                name: dira
#
mkdir $SCRATCH_MNT/testdir/dira

# This fsync is for the zoned mode. On the zoned mode, we use a dedicated block
# group for tree-log. That block group is created on-demand or assigned to a
# metadata block group if there is none. On the first mount of a file system, we
# need to create one because there is only one metadata block group available
# for the regular metadata. That creation of a new block group forces tree-log
# to be a full commit on that transaction, which prevents logging "testdir" and
# "dira" and screws up the result.
#
# Calling fsync here will create the dedicated block group, and let them be
# logged.
$XFS_IO_PROG -c "fsync" $SCRATCH_MNT

# Make sure everything done so far is durably persisted.
sync

# Now do a change to inode 257 ("testdir") that does not result in COWing leaves
# 2 and 3 - the leaves that contain the directory items pointing to inode 1458
# (directory "dira").
#
# Changing permissions, the owner/group, updating or adding a xattr, etc, will
# not change (COW) leaves 2 and 3. So for the sake of simplicity change the
# permissions of inode 257, which results in updating its inode item and
# therefore change (COW) only leaf 1.
#
chmod 700 $SCRATCH_MNT/testdir

# Now fsync directory inode 257.
#
# Since only the first leaf was changed/COWed, we log the inode item of inode 257
# and only the entries found in the first leaf, all with a key of type
# BTRFS_DIR_ITEM_KEY, and no keys of type BTRFS_DIR_INDEX_KEY, because they sort
# after the former type and none exist in the first leaf.
#
# We also log 3 items that represent ranges for dir items and dir indexes for
# which the log is authoritative:
#
# 1) a key of type BTRFS_DIR_LOG_ITEM_KEY, which indicates the log is
#    authoritative for all BTRFS_DIR_ITEM_KEY keys that have an offset in the
#    range [0, 2285968570] (the offset here is the crc32c of the dentry's
#    name). The value 2285968570 corresponds to the offset of the first key
#    of leaf 2 (which is of type BTRFS_DIR_ITEM_KEY);
#
# 2) a key of type BTRFS_DIR_LOG_ITEM_KEY, which indicates the log is
#    authoritative for all BTRFS_DIR_ITEM_KEY keys that have an offset in the
#    range [4293818216, (u64)-1] (the offset here is the crc32c of the dentry's
#    name). The value 4293818216 corresponds to the offset of the highest key
#    of type BTRFS_DIR_ITEM_KEY plus 1 (4293818215 + 1), which is located in
#    leaf 2;
#
# 3) a key of type BTRFS_DIR_LOG_INDEX_KEY, with an offset of 1203, which
#    indicates the log is authoritative for all keys of type BTRFS_DIR_INDEX_KEY
#    that have an offset in the range [1203, (u64)-1]. The value 1203 corresponds
#    to the offset of the last key of type BTRFS_DIR_INDEX_KEY plus 1 (1202 + 1),
#    which is located in leaf 3;
#
# Also, because "testdir" is a directory and inode 1458 ("dira") is a child
# directory, we log inode 1458 too.
#
$XFS_IO_PROG -c "fsync" $SCRATCH_MNT/testdir

# Now move "dira", inode 1458, to be a child of the root directory (inode 256).
#
# Because this inode was previously logged, when "testdir" was fsynced, the
# log is updated so that the old inode reference, referring to inode 257 as
# the parent, is deleted and the new inode reference, referring to inode 256
# as the parent, is added to the log.
#
mv $SCRATCH_MNT/testdir/dira $SCRATCH_MNT/

# Now change some file and fsync it. This guarantees the log changes made by
# the previous move/rename operation are persisted. We do not need to do any
# special modification to the file, just any change to any file and sync the
# log.
$XFS_IO_PROG -c "pwrite -S 0xab 0 64K" \
	     -c "fsync" \
	     $SCRATCH_MNT/testdir/file1 >>$seqres.full

# Simulate a power failure and then mount again the filesystem to replay the log
# tree. We want to verify that we are able to mount the filesystem, meaning log
# replay was successful, and that directory inode 1458 ("dira") only has inode
# 256 (the filesystem's root) as its parent (and no longer a child of inode 257).
#
# It used to happen that during log replay we would end up having inode 1458
# (directory "dira") with 2 hard links, being a child of inode 257 ("testdir")
# and inode 256 (the filesystem's root). This resulted in the tree checker
# detecting the issue and causing the mount operation to fail (with -EIO).
#
# This happened because in the log we have the new name/parent for inode 1458,
# which results in adding the new dentry with inode 256 as the parent, but the
# previous dentry, under inode 257 was never removed - this is because the
# ranges for dir items and dir indexes of inode 257 for which the log is
# authoritative do not include the old dir item and dir index for the dentry
# of inode 257 referring to inode 1458:
#
# - for dir items, the log is authoritative for the ranges [0, 2285968570] and
#   [4293818216, (u64)-1]. The dir item at inode 257 pointing to inode 1458 has
#   a key of (257 DIR_ITEM 3724298081), as previously mentioned, so the dir item
#   is not deleted when the log replay procedure processes the authoritative
#   ranges, as 3724298081 is outside both ranges;
#
# - for dir indexes, the log is authoritative for the range [1203, (u64)-1], and
#   the dir index item of inode 257 pointing to inode 1458 has a key of
#   (257 DIR_INDEX 1202), as previously mentioned, so the dir index item is not
#   deleted when the log replay procedure processes the authoritative range.
#
_flakey_drop_and_remount

[ -d $SCRATCH_MNT/testdir/dira ] && echo "/testdir/dira still exists"
[ -d $SCRATCH_MNT/dira ] || echo "/dira does not exists"

# While at it also check that the data we wrote was not lost, just for the sake
# of completeness.
echo "File $SCRATCH_MNT/testdir/file1 data:" | _filter_scratch
od -A d -t x1 $SCRATCH_MNT/testdir/file1

_unmount_flakey

status=0
exit
