xfs: check for COW overflows in i_delayed_blks

With the new copy on write functionality it's possible to reserve so
much COW space for a file that we end up overflowing i_delayed_blks.
The only user-visible effect of this is to cause totally wrong i_blocks
output in stat, so check for that.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Eryu Guan <guaneryu@gmail.com>
Signed-off-by: Eryu Guan <guaneryu@gmail.com>

tests/xfs/507

@@ -0,0 +1,199 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0+
+# Copyright (c) 2019 Oracle, Inc.  All Rights Reserved.
+#
+# FS QA Test No. 507
+#
+# Try to overflow i_delayed_blks by setting the largest cowextsize hint
+# possible, creating a sparse file with a single byte every cowextsize bytes,
+# reflinking it, and retouching every written byte to see if we can create
+# enough speculative COW reservations to overflow i_delayed_blks.
+#
+seq=`basename $0`
+seqres=$RESULT_DIR/$seq
+echo "QA output created by $seq"
+
+here=`pwd`
+tmp=/tmp/$$
+status=1	# failure is the default!
+trap "_cleanup; exit \$status" 0 1 2 3 7 15
+
+_cleanup()
+{
+	cd /
+	test -n "$loop_mount" && $UMOUNT_PROG $loop_mount > /dev/null 2>&1
+	test -n "$loop_dev" && _destroy_loop_device $loop_dev
+	rm -rf $tmp.*
+}
+
+# get standard environment, filters and checks
+. ./common/rc
+. ./common/reflink
+. ./common/filter
+
+# real QA test starts here
+_supported_os Linux
+_supported_fs xfs
+_require_scratch_reflink
+_require_cp_reflink
+_require_loop
+_require_xfs_debug	# needed for xfs_bmap -c
+
+MAXEXTLEN=2097151	# cowextsize can't be more than MAXEXTLEN
+
+echo "Format and mount"
+_scratch_mkfs > "$seqres.full" 2>&1
+_scratch_mount
+
+# Create a huge sparse filesystem on the scratch device because that's what
+# we're going to need to guarantee that we have enough blocks to overflow in
+# the first place.  We need to have at least enough free space on that huge fs
+# to handle one written block every MAXEXTLEN blocks and to reserve 2^32 blocks
+# in the COW fork.  There needs to be sufficient space in the scratch
+# filesystem to handle a 256M log, all the per-AG metadata, and all the data
+# written to the test file.
+#
+# Worst case, a 64k-block fs needs to be about 300TB.  Best case, a 1k block
+# filesystem needs ~5TB.  For the most common 4k case we only need a ~20TB fs.
+#
+# In practice, the author observed that the space required on the scratch fs
+# never exceeded ~800M even for a 300T 6k-block filesystem, so we'll just ask
+# for about 1.2GB.
+blksz=$(_get_file_block_size "$SCRATCH_MNT")
+nr_cows="$(( ((2 ** 32) / MAXEXTLEN) + 100 ))"
+blks_needed="$(( nr_cows * (1 + MAXEXTLEN) ))"
+loop_file_sz="$(( ((blksz * blks_needed) * 12 / 10) / 512 * 512 ))"
+_require_fs_space $SCRATCH_MNT 1234567
+
+loop_file=$SCRATCH_MNT/a.img
+loop_mount=$SCRATCH_MNT/a
+$XFS_IO_PROG -f -c "truncate $loop_file_sz" $loop_file
+loop_dev=$(_create_loop_device $loop_file)
+
+# Now we have to create the source file.  The goal is to overflow a 32-bit
+# i_delayed_blks, which means that we have to create at least that many delayed
+# allocation block reservations.  Take advantage of the fact that a cowextsize
+# hint causes creation of large speculative delalloc reservations in the cow
+# fork to reduce the amount of work we have to do.
+#
+# The maximum cowextsize can only be set to MAXEXTLEN fs blocks on a filesystem
+# whose AGs each have more than MAXEXTLEN * 2 blocks.  This we can do easily
+# with a multi-terabyte filesystem, so start by setting up the hint.  Note that
+# the current fsxattr interface specifies its u32 cowextsize hint in units of
+# bytes and therefore can't handle MAXEXTLEN * blksz on most filesystems, so we
+# set it via mkfs because mkfs takes units of fs blocks, not bytes.
+
+_mkfs_dev -d cowextsize=$MAXEXTLEN -l size=256m $loop_dev >> $seqres.full
+mkdir $loop_mount
+mount $loop_dev $loop_mount
+
+echo "Create crazy huge file"
+huge_file="$loop_mount/a"
+touch "$huge_file"
+blksz=$(_get_file_block_size "$loop_mount")
+extsize_bytes="$(( MAXEXTLEN * blksz ))"
+
+# Make sure it actually set a hint.
+curr_cowextsize_str="$($XFS_IO_PROG -c 'cowextsize' "$huge_file")"
+echo "$curr_cowextsize_str" >> $seqres.full
+cowextsize_bytes="$(echo "$curr_cowextsize_str" | sed -e 's/^.\([0-9]*\).*$/\1/g')"
+test "$cowextsize_bytes" -eq 0 && echo "could not set cowextsize?"
+
+# Now we have to seed the file with sparse contents.  Remember, the goal is to
+# create a little more than 2^32 delayed allocation blocks in the COW fork with
+# as little effort as possible.  We know that speculative COW preallocation
+# will create MAXEXTLEN-length reservations for us, so that means we should
+# be able to get away with touching a single byte every extsize_bytes.  We
+# do this backwards to avoid having to move EOF.
+seq $nr_cows -1 0 | while read n; do
+	off="$((n * extsize_bytes))"
+	$XFS_IO_PROG -c "pwrite $off 1" "$huge_file" > /dev/null
+done
+
+echo "Reflink crazy huge file"
+_cp_reflink "$huge_file" "$huge_file.b"
+
+# Now that we've shared all the blocks in the file, we touch them all again
+# to create speculative COW preallocations.
+echo "COW crazy huge file"
+seq $nr_cows -1 0 | while read n; do
+	off="$((n * extsize_bytes))"
+	$XFS_IO_PROG -c "pwrite $off 1" "$huge_file" > /dev/null
+done
+
+# Compare the number of blocks allocated to this file (as reported by stat)
+# against the number of blocks that are in the COW fork.  If either one is
+# less than 2^32 then we have evidence of an overflow problem.
+echo "Check crazy huge file"
+allocated_stat_blocks="$(stat -c %b "$huge_file")"
+stat_blksz="$(stat -c %B "$huge_file")"
+allocated_fsblocks=$(( allocated_stat_blocks * stat_blksz / blksz ))
+
+# Make sure we got enough COW reservations to overflow a 32-bit counter.
+
+# Return the number of delalloc & real blocks given bmap output for a fork of a
+# file.  Output is in units of 512-byte blocks.
+count_fork_blocks() {
+	$AWK_PROG "
+{
+	if (\$3 == \"delalloc\") {
+		x += \$4;
+	} else if (\$3 == \"hole\") {
+		;
+	} else {
+		x += \$6;
+	}
+}
+END {
+	print(x);
+}
+"
+}
+
+# Count the number of blocks allocated to a file based on the xfs_bmap output.
+# Output is in units of filesystem blocks.
+count_file_fork_blocks() {
+	local tag="$1"
+	local file="$2"
+	local args="$3"
+
+	$XFS_IO_PROG -c "bmap $args -l -p -v" "$huge_file" > $tmp.extents
+	echo "$tag fork map" >> $seqres.full
+	cat $tmp.extents >> $seqres.full
+	local sectors="$(count_fork_blocks < $tmp.extents)"
+	echo "$(( sectors / (blksz / 512) ))"
+}
+
+cowblocks=$(count_file_fork_blocks cow "$huge_file" "-c")
+attrblocks=$(count_file_fork_blocks attr "$huge_file" "-a")
+datablocks=$(count_file_fork_blocks data "$huge_file" "")
+
+# Did we create more than 2^32 blocks in the cow fork?
+# Make sure the test actually set us up for the overflow.
+echo "datablocks is $datablocks" >> $seqres.full
+echo "attrblocks is $attrblocks" >> $seqres.full
+echo "cowblocks is $cowblocks" >> $seqres.full
+test "$cowblocks" -lt $((2 ** 32)) && \
+	echo "cowblocks (${cowblocks}) should be more than 2^32!"
+
+# Does stat's block allocation count exceed 2^32?
+# This is how we detect the incore delalloc count overflow.
+echo "stat blocks is $allocated_fsblocks" >> $seqres.full
+test "$allocated_fsblocks" -lt $((2 ** 32)) && \
+	echo "stat blocks (${allocated_fsblocks}) should be more than 2^32!"
+
+# Finally, does st_blocks match what we computed from the forks?
+# Sanity check the values computed from the forks.
+expected_allocated_fsblocks=$((datablocks + cowblocks + attrblocks))
+echo "expected stat blocks is $expected_allocated_fsblocks" >> $seqres.full
+
+_within_tolerance "st_blocks" $allocated_fsblocks $expected_allocated_fsblocks 2% -v
+
+echo "Test done"
+# Quick check the large sparse fs, but skip xfs_db because it doesn't scale
+# well on a multi-terabyte filesystem.
+LARGE_SCRATCH_DEV=yes _check_xfs_filesystem $loop_dev none none
+
+# success, all done
+status=0
+exit

tests/xfs/507.out

@@ -0,0 +1,8 @@
+QA output created by 507
+Format and mount
+Create crazy huge file
+Reflink crazy huge file
+COW crazy huge file
+Check crazy huge file
+st_blocks is in range
+Test done

tests/xfs/group

@@ -504,3 +504,4 @@
 504 auto quick mkfs label
 505 auto quick spaceman
 506 auto quick health
+507 clone