linux/fs/btrfs/extent-io-tree.h

268 lines
8.8 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef BTRFS_EXTENT_IO_TREE_H
#define BTRFS_EXTENT_IO_TREE_H
struct extent_changeset;
struct io_failure_record;
/* Bits for the extent state */
#define EXTENT_DIRTY (1U << 0)
#define EXTENT_UPTODATE (1U << 1)
#define EXTENT_LOCKED (1U << 2)
#define EXTENT_NEW (1U << 3)
#define EXTENT_DELALLOC (1U << 4)
#define EXTENT_DEFRAG (1U << 5)
#define EXTENT_BOUNDARY (1U << 6)
#define EXTENT_NODATASUM (1U << 7)
#define EXTENT_CLEAR_META_RESV (1U << 8)
#define EXTENT_NEED_WAIT (1U << 9)
#define EXTENT_DAMAGED (1U << 10)
#define EXTENT_NORESERVE (1U << 11)
#define EXTENT_QGROUP_RESERVED (1U << 12)
#define EXTENT_CLEAR_DATA_RESV (1U << 13)
btrfs: update the number of bytes used by an inode atomically There are several occasions where we do not update the inode's number of used bytes atomically, resulting in a concurrent stat(2) syscall to report a value of used blocks that does not correspond to a valid value, that is, a value that does not match neither what we had before the operation nor what we get after the operation completes. In extreme cases it can result in stat(2) reporting zero used blocks, which can cause problems for some userspace tools where they can consider a file with a non-zero size and zero used blocks as completely sparse and skip reading data, as reported/discussed a long time ago in some threads like the following: https://lists.gnu.org/archive/html/bug-tar/2016-07/msg00001.html The cases where this can happen are the following: -> Case 1 If we do a write (buffered or direct IO) against a file region for which there is already an allocated extent (or multiple extents), then we have a short time window where we can report a number of used blocks to stat(2) that does not take into account the file region being overwritten. This short time window happens when completing the ordered extent(s). This happens because when we drop the extents in the write range we decrement the inode's number of bytes and later on when we insert the new extent(s) we increment the number of bytes in the inode, resulting in a short time window where a stat(2) syscall can get an incorrect number of used blocks. If we do writes that overwrite an entire file, then we have a short time window where we report 0 used blocks to stat(2). Example reproducer: $ cat reproducer-1.sh #!/bin/bash MNT=/mnt/sdi DEV=/dev/sdi stat_loop() { trap "wait; exit" SIGTERM local filepath=$1 local expected=$2 local got while :; do got=$(stat -c %b $filepath) if [ $got -ne $expected ]; then echo -n "ERROR: unexpected used blocks" echo " (got: $got expected: $expected)" fi done } mkfs.btrfs -f $DEV > /dev/null # mkfs.xfs -f $DEV > /dev/null # mkfs.ext4 -F $DEV > /dev/null # mkfs.f2fs -f $DEV > /dev/null # mkfs.reiserfs -f $DEV > /dev/null mount $DEV $MNT xfs_io -f -s -c "pwrite -b 64K 0 64K" $MNT/foobar >/dev/null expected=$(stat -c %b $MNT/foobar) # Create a process to keep calling stat(2) on the file and see if the # reported number of blocks used (disk space used) changes, it should # not because we are not increasing the file size nor punching holes. stat_loop $MNT/foobar $expected & loop_pid=$! for ((i = 0; i < 50000; i++)); do xfs_io -s -c "pwrite -b 64K 0 64K" $MNT/foobar >/dev/null done kill $loop_pid &> /dev/null wait umount $DEV $ ./reproducer-1.sh ERROR: unexpected used blocks (got: 0 expected: 128) ERROR: unexpected used blocks (got: 0 expected: 128) (...) Note that since this is a short time window where the race can happen, the reproducer may not be able to always trigger the bug in one run, or it may trigger it multiple times. -> Case 2 If we do a buffered write against a file region that does not have any allocated extents, like a hole or beyond EOF, then during ordered extent completion we have a short time window where a concurrent stat(2) syscall can report a number of used blocks that does not correspond to the value before or after the write operation, a value that is actually larger than the value after the write completes. This happens because once we start a buffered write into an unallocated file range we increment the inode's 'new_delalloc_bytes', to make sure any stat(2) call gets a correct used blocks value before delalloc is flushed and completes. However at ordered extent completion, after we inserted the new extent, we increment the inode's number of bytes used with the size of the new extent, and only later, when clearing the range in the inode's iotree, we decrement the inode's 'new_delalloc_bytes' counter with the size of the extent. So this results in a short time window where a concurrent stat(2) syscall can report a number of used blocks that accounts for the new extent twice. Example reproducer: $ cat reproducer-2.sh #!/bin/bash MNT=/mnt/sdi DEV=/dev/sdi stat_loop() { trap "wait; exit" SIGTERM local filepath=$1 local expected=$2 local got while :; do got=$(stat -c %b $filepath) if [ $got -ne $expected ]; then echo -n "ERROR: unexpected used blocks" echo " (got: $got expected: $expected)" fi done } mkfs.btrfs -f $DEV > /dev/null # mkfs.xfs -f $DEV > /dev/null # mkfs.ext4 -F $DEV > /dev/null # mkfs.f2fs -f $DEV > /dev/null # mkfs.reiserfs -f $DEV > /dev/null mount $DEV $MNT touch $MNT/foobar write_size=$((64 * 1024)) for ((i = 0; i < 16384; i++)); do offset=$(($i * $write_size)) xfs_io -c "pwrite -S 0xab $offset $write_size" $MNT/foobar >/dev/null blocks_used=$(stat -c %b $MNT/foobar) # Fsync the file to trigger writeback and keep calling stat(2) on it # to see if the number of blocks used changes. stat_loop $MNT/foobar $blocks_used & loop_pid=$! xfs_io -c "fsync" $MNT/foobar kill $loop_pid &> /dev/null wait $loop_pid done umount $DEV $ ./reproducer-2.sh ERROR: unexpected used blocks (got: 265472 expected: 265344) ERROR: unexpected used blocks (got: 284032 expected: 283904) (...) Note that since this is a short time window where the race can happen, the reproducer may not be able to always trigger the bug in one run, or it may trigger it multiple times. -> Case 3 Another case where such problems happen is during other operations that replace extents in a file range with other extents. Those operations are extent cloning, deduplication and fallocate's zero range operation. The cause of the problem is similar to the first case. When we drop the extents from a range, we decrement the inode's number of bytes, and later on, after inserting the new extents we increment it. Since this is not done atomically, a concurrent stat(2) call can see and return a number of used blocks that is smaller than it should be, does not match the number of used blocks before or after the clone/deduplication/zero operation. Like for the first case, when doing a clone, deduplication or zero range operation against an entire file, we end up having a time window where we can report 0 used blocks to a stat(2) call. Example reproducer: $ cat reproducer-3.sh #!/bin/bash MNT=/mnt/sdi DEV=/dev/sdi mkfs.btrfs -f $DEV > /dev/null # mkfs.xfs -f -m reflink=1 $DEV > /dev/null mount $DEV $MNT extent_size=$((64 * 1024)) num_extents=16384 file_size=$(($extent_size * $num_extents)) # File foo has many small extents. xfs_io -f -s -c "pwrite -S 0xab -b $extent_size 0 $file_size" $MNT/foo \ > /dev/null # File bar has much less extents and has exactly the same data as foo. xfs_io -f -c "pwrite -S 0xab 0 $file_size" $MNT/bar > /dev/null expected=$(stat -c %b $MNT/foo) # Now deduplicate bar into foo. While the deduplication is in progres, # the number of used blocks/file size reported by stat should not change xfs_io -c "dedupe $MNT/bar 0 0 $file_size" $MNT/foo > /dev/null & dedupe_pid=$! while [ -n "$(ps -p $dedupe_pid -o pid=)" ]; do used=$(stat -c %b $MNT/foo) if [ $used -ne $expected ]; then echo "Unexpected blocks used: $used (expected: $expected)" fi done umount $DEV $ ./reproducer-3.sh Unexpected blocks used: 2076800 (expected: 2097152) Unexpected blocks used: 2097024 (expected: 2097152) Unexpected blocks used: 2079872 (expected: 2097152) (...) Note that since this is a short time window where the race can happen, the reproducer may not be able to always trigger the bug in one run, or it may trigger it multiple times. So fix this by: 1) Making btrfs_drop_extents() not decrement the VFS inode's number of bytes, and instead return the number of bytes; 2) Making any code that drops extents and adds new extents update the inode's number of bytes atomically, while holding the btrfs inode's spinlock, which is also used by the stat(2) callback to get the inode's number of bytes; 3) For ranges in the inode's iotree that are marked as 'delalloc new', corresponding to previously unallocated ranges, increment the inode's number of bytes when clearing the 'delalloc new' bit from the range, in the same critical section that decrements the inode's 'new_delalloc_bytes' counter, delimited by the btrfs inode's spinlock. An alternative would be to have btrfs_getattr() wait for any IO (ordered extents in progress) and locking the whole range (0 to (u64)-1) while it it computes the number of blocks used. But that would mean blocking stat(2), which is a very used syscall and expected to be fast, waiting for writes, clone/dedupe, fallocate, page reads, fiemap, etc. CC: stable@vger.kernel.org # 5.4+ Reviewed-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: Filipe Manana <fdmanana@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-11-04 11:07:34 +00:00
/*
* Must be cleared only during ordered extent completion or on error paths if we
* did not manage to submit bios and create the ordered extents for the range.
* Should not be cleared during page release and page invalidation (if there is
* an ordered extent in flight), that is left for the ordered extent completion.
*/
#define EXTENT_DELALLOC_NEW (1U << 14)
btrfs: update the number of bytes used by an inode atomically There are several occasions where we do not update the inode's number of used bytes atomically, resulting in a concurrent stat(2) syscall to report a value of used blocks that does not correspond to a valid value, that is, a value that does not match neither what we had before the operation nor what we get after the operation completes. In extreme cases it can result in stat(2) reporting zero used blocks, which can cause problems for some userspace tools where they can consider a file with a non-zero size and zero used blocks as completely sparse and skip reading data, as reported/discussed a long time ago in some threads like the following: https://lists.gnu.org/archive/html/bug-tar/2016-07/msg00001.html The cases where this can happen are the following: -> Case 1 If we do a write (buffered or direct IO) against a file region for which there is already an allocated extent (or multiple extents), then we have a short time window where we can report a number of used blocks to stat(2) that does not take into account the file region being overwritten. This short time window happens when completing the ordered extent(s). This happens because when we drop the extents in the write range we decrement the inode's number of bytes and later on when we insert the new extent(s) we increment the number of bytes in the inode, resulting in a short time window where a stat(2) syscall can get an incorrect number of used blocks. If we do writes that overwrite an entire file, then we have a short time window where we report 0 used blocks to stat(2). Example reproducer: $ cat reproducer-1.sh #!/bin/bash MNT=/mnt/sdi DEV=/dev/sdi stat_loop() { trap "wait; exit" SIGTERM local filepath=$1 local expected=$2 local got while :; do got=$(stat -c %b $filepath) if [ $got -ne $expected ]; then echo -n "ERROR: unexpected used blocks" echo " (got: $got expected: $expected)" fi done } mkfs.btrfs -f $DEV > /dev/null # mkfs.xfs -f $DEV > /dev/null # mkfs.ext4 -F $DEV > /dev/null # mkfs.f2fs -f $DEV > /dev/null # mkfs.reiserfs -f $DEV > /dev/null mount $DEV $MNT xfs_io -f -s -c "pwrite -b 64K 0 64K" $MNT/foobar >/dev/null expected=$(stat -c %b $MNT/foobar) # Create a process to keep calling stat(2) on the file and see if the # reported number of blocks used (disk space used) changes, it should # not because we are not increasing the file size nor punching holes. stat_loop $MNT/foobar $expected & loop_pid=$! for ((i = 0; i < 50000; i++)); do xfs_io -s -c "pwrite -b 64K 0 64K" $MNT/foobar >/dev/null done kill $loop_pid &> /dev/null wait umount $DEV $ ./reproducer-1.sh ERROR: unexpected used blocks (got: 0 expected: 128) ERROR: unexpected used blocks (got: 0 expected: 128) (...) Note that since this is a short time window where the race can happen, the reproducer may not be able to always trigger the bug in one run, or it may trigger it multiple times. -> Case 2 If we do a buffered write against a file region that does not have any allocated extents, like a hole or beyond EOF, then during ordered extent completion we have a short time window where a concurrent stat(2) syscall can report a number of used blocks that does not correspond to the value before or after the write operation, a value that is actually larger than the value after the write completes. This happens because once we start a buffered write into an unallocated file range we increment the inode's 'new_delalloc_bytes', to make sure any stat(2) call gets a correct used blocks value before delalloc is flushed and completes. However at ordered extent completion, after we inserted the new extent, we increment the inode's number of bytes used with the size of the new extent, and only later, when clearing the range in the inode's iotree, we decrement the inode's 'new_delalloc_bytes' counter with the size of the extent. So this results in a short time window where a concurrent stat(2) syscall can report a number of used blocks that accounts for the new extent twice. Example reproducer: $ cat reproducer-2.sh #!/bin/bash MNT=/mnt/sdi DEV=/dev/sdi stat_loop() { trap "wait; exit" SIGTERM local filepath=$1 local expected=$2 local got while :; do got=$(stat -c %b $filepath) if [ $got -ne $expected ]; then echo -n "ERROR: unexpected used blocks" echo " (got: $got expected: $expected)" fi done } mkfs.btrfs -f $DEV > /dev/null # mkfs.xfs -f $DEV > /dev/null # mkfs.ext4 -F $DEV > /dev/null # mkfs.f2fs -f $DEV > /dev/null # mkfs.reiserfs -f $DEV > /dev/null mount $DEV $MNT touch $MNT/foobar write_size=$((64 * 1024)) for ((i = 0; i < 16384; i++)); do offset=$(($i * $write_size)) xfs_io -c "pwrite -S 0xab $offset $write_size" $MNT/foobar >/dev/null blocks_used=$(stat -c %b $MNT/foobar) # Fsync the file to trigger writeback and keep calling stat(2) on it # to see if the number of blocks used changes. stat_loop $MNT/foobar $blocks_used & loop_pid=$! xfs_io -c "fsync" $MNT/foobar kill $loop_pid &> /dev/null wait $loop_pid done umount $DEV $ ./reproducer-2.sh ERROR: unexpected used blocks (got: 265472 expected: 265344) ERROR: unexpected used blocks (got: 284032 expected: 283904) (...) Note that since this is a short time window where the race can happen, the reproducer may not be able to always trigger the bug in one run, or it may trigger it multiple times. -> Case 3 Another case where such problems happen is during other operations that replace extents in a file range with other extents. Those operations are extent cloning, deduplication and fallocate's zero range operation. The cause of the problem is similar to the first case. When we drop the extents from a range, we decrement the inode's number of bytes, and later on, after inserting the new extents we increment it. Since this is not done atomically, a concurrent stat(2) call can see and return a number of used blocks that is smaller than it should be, does not match the number of used blocks before or after the clone/deduplication/zero operation. Like for the first case, when doing a clone, deduplication or zero range operation against an entire file, we end up having a time window where we can report 0 used blocks to a stat(2) call. Example reproducer: $ cat reproducer-3.sh #!/bin/bash MNT=/mnt/sdi DEV=/dev/sdi mkfs.btrfs -f $DEV > /dev/null # mkfs.xfs -f -m reflink=1 $DEV > /dev/null mount $DEV $MNT extent_size=$((64 * 1024)) num_extents=16384 file_size=$(($extent_size * $num_extents)) # File foo has many small extents. xfs_io -f -s -c "pwrite -S 0xab -b $extent_size 0 $file_size" $MNT/foo \ > /dev/null # File bar has much less extents and has exactly the same data as foo. xfs_io -f -c "pwrite -S 0xab 0 $file_size" $MNT/bar > /dev/null expected=$(stat -c %b $MNT/foo) # Now deduplicate bar into foo. While the deduplication is in progres, # the number of used blocks/file size reported by stat should not change xfs_io -c "dedupe $MNT/bar 0 0 $file_size" $MNT/foo > /dev/null & dedupe_pid=$! while [ -n "$(ps -p $dedupe_pid -o pid=)" ]; do used=$(stat -c %b $MNT/foo) if [ $used -ne $expected ]; then echo "Unexpected blocks used: $used (expected: $expected)" fi done umount $DEV $ ./reproducer-3.sh Unexpected blocks used: 2076800 (expected: 2097152) Unexpected blocks used: 2097024 (expected: 2097152) Unexpected blocks used: 2079872 (expected: 2097152) (...) Note that since this is a short time window where the race can happen, the reproducer may not be able to always trigger the bug in one run, or it may trigger it multiple times. So fix this by: 1) Making btrfs_drop_extents() not decrement the VFS inode's number of bytes, and instead return the number of bytes; 2) Making any code that drops extents and adds new extents update the inode's number of bytes atomically, while holding the btrfs inode's spinlock, which is also used by the stat(2) callback to get the inode's number of bytes; 3) For ranges in the inode's iotree that are marked as 'delalloc new', corresponding to previously unallocated ranges, increment the inode's number of bytes when clearing the 'delalloc new' bit from the range, in the same critical section that decrements the inode's 'new_delalloc_bytes' counter, delimited by the btrfs inode's spinlock. An alternative would be to have btrfs_getattr() wait for any IO (ordered extents in progress) and locking the whole range (0 to (u64)-1) while it it computes the number of blocks used. But that would mean blocking stat(2), which is a very used syscall and expected to be fast, waiting for writes, clone/dedupe, fallocate, page reads, fiemap, etc. CC: stable@vger.kernel.org # 5.4+ Reviewed-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: Filipe Manana <fdmanana@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-11-04 11:07:34 +00:00
/*
* When an ordered extent successfully completes for a region marked as a new
* delalloc range, use this flag when clearing a new delalloc range to indicate
* that the VFS' inode number of bytes should be incremented and the inode's new
* delalloc bytes decremented, in an atomic way to prevent races with stat(2).
*/
#define EXTENT_ADD_INODE_BYTES (1U << 15)
#define EXTENT_DO_ACCOUNTING (EXTENT_CLEAR_META_RESV | \
EXTENT_CLEAR_DATA_RESV)
btrfs: update the number of bytes used by an inode atomically There are several occasions where we do not update the inode's number of used bytes atomically, resulting in a concurrent stat(2) syscall to report a value of used blocks that does not correspond to a valid value, that is, a value that does not match neither what we had before the operation nor what we get after the operation completes. In extreme cases it can result in stat(2) reporting zero used blocks, which can cause problems for some userspace tools where they can consider a file with a non-zero size and zero used blocks as completely sparse and skip reading data, as reported/discussed a long time ago in some threads like the following: https://lists.gnu.org/archive/html/bug-tar/2016-07/msg00001.html The cases where this can happen are the following: -> Case 1 If we do a write (buffered or direct IO) against a file region for which there is already an allocated extent (or multiple extents), then we have a short time window where we can report a number of used blocks to stat(2) that does not take into account the file region being overwritten. This short time window happens when completing the ordered extent(s). This happens because when we drop the extents in the write range we decrement the inode's number of bytes and later on when we insert the new extent(s) we increment the number of bytes in the inode, resulting in a short time window where a stat(2) syscall can get an incorrect number of used blocks. If we do writes that overwrite an entire file, then we have a short time window where we report 0 used blocks to stat(2). Example reproducer: $ cat reproducer-1.sh #!/bin/bash MNT=/mnt/sdi DEV=/dev/sdi stat_loop() { trap "wait; exit" SIGTERM local filepath=$1 local expected=$2 local got while :; do got=$(stat -c %b $filepath) if [ $got -ne $expected ]; then echo -n "ERROR: unexpected used blocks" echo " (got: $got expected: $expected)" fi done } mkfs.btrfs -f $DEV > /dev/null # mkfs.xfs -f $DEV > /dev/null # mkfs.ext4 -F $DEV > /dev/null # mkfs.f2fs -f $DEV > /dev/null # mkfs.reiserfs -f $DEV > /dev/null mount $DEV $MNT xfs_io -f -s -c "pwrite -b 64K 0 64K" $MNT/foobar >/dev/null expected=$(stat -c %b $MNT/foobar) # Create a process to keep calling stat(2) on the file and see if the # reported number of blocks used (disk space used) changes, it should # not because we are not increasing the file size nor punching holes. stat_loop $MNT/foobar $expected & loop_pid=$! for ((i = 0; i < 50000; i++)); do xfs_io -s -c "pwrite -b 64K 0 64K" $MNT/foobar >/dev/null done kill $loop_pid &> /dev/null wait umount $DEV $ ./reproducer-1.sh ERROR: unexpected used blocks (got: 0 expected: 128) ERROR: unexpected used blocks (got: 0 expected: 128) (...) Note that since this is a short time window where the race can happen, the reproducer may not be able to always trigger the bug in one run, or it may trigger it multiple times. -> Case 2 If we do a buffered write against a file region that does not have any allocated extents, like a hole or beyond EOF, then during ordered extent completion we have a short time window where a concurrent stat(2) syscall can report a number of used blocks that does not correspond to the value before or after the write operation, a value that is actually larger than the value after the write completes. This happens because once we start a buffered write into an unallocated file range we increment the inode's 'new_delalloc_bytes', to make sure any stat(2) call gets a correct used blocks value before delalloc is flushed and completes. However at ordered extent completion, after we inserted the new extent, we increment the inode's number of bytes used with the size of the new extent, and only later, when clearing the range in the inode's iotree, we decrement the inode's 'new_delalloc_bytes' counter with the size of the extent. So this results in a short time window where a concurrent stat(2) syscall can report a number of used blocks that accounts for the new extent twice. Example reproducer: $ cat reproducer-2.sh #!/bin/bash MNT=/mnt/sdi DEV=/dev/sdi stat_loop() { trap "wait; exit" SIGTERM local filepath=$1 local expected=$2 local got while :; do got=$(stat -c %b $filepath) if [ $got -ne $expected ]; then echo -n "ERROR: unexpected used blocks" echo " (got: $got expected: $expected)" fi done } mkfs.btrfs -f $DEV > /dev/null # mkfs.xfs -f $DEV > /dev/null # mkfs.ext4 -F $DEV > /dev/null # mkfs.f2fs -f $DEV > /dev/null # mkfs.reiserfs -f $DEV > /dev/null mount $DEV $MNT touch $MNT/foobar write_size=$((64 * 1024)) for ((i = 0; i < 16384; i++)); do offset=$(($i * $write_size)) xfs_io -c "pwrite -S 0xab $offset $write_size" $MNT/foobar >/dev/null blocks_used=$(stat -c %b $MNT/foobar) # Fsync the file to trigger writeback and keep calling stat(2) on it # to see if the number of blocks used changes. stat_loop $MNT/foobar $blocks_used & loop_pid=$! xfs_io -c "fsync" $MNT/foobar kill $loop_pid &> /dev/null wait $loop_pid done umount $DEV $ ./reproducer-2.sh ERROR: unexpected used blocks (got: 265472 expected: 265344) ERROR: unexpected used blocks (got: 284032 expected: 283904) (...) Note that since this is a short time window where the race can happen, the reproducer may not be able to always trigger the bug in one run, or it may trigger it multiple times. -> Case 3 Another case where such problems happen is during other operations that replace extents in a file range with other extents. Those operations are extent cloning, deduplication and fallocate's zero range operation. The cause of the problem is similar to the first case. When we drop the extents from a range, we decrement the inode's number of bytes, and later on, after inserting the new extents we increment it. Since this is not done atomically, a concurrent stat(2) call can see and return a number of used blocks that is smaller than it should be, does not match the number of used blocks before or after the clone/deduplication/zero operation. Like for the first case, when doing a clone, deduplication or zero range operation against an entire file, we end up having a time window where we can report 0 used blocks to a stat(2) call. Example reproducer: $ cat reproducer-3.sh #!/bin/bash MNT=/mnt/sdi DEV=/dev/sdi mkfs.btrfs -f $DEV > /dev/null # mkfs.xfs -f -m reflink=1 $DEV > /dev/null mount $DEV $MNT extent_size=$((64 * 1024)) num_extents=16384 file_size=$(($extent_size * $num_extents)) # File foo has many small extents. xfs_io -f -s -c "pwrite -S 0xab -b $extent_size 0 $file_size" $MNT/foo \ > /dev/null # File bar has much less extents and has exactly the same data as foo. xfs_io -f -c "pwrite -S 0xab 0 $file_size" $MNT/bar > /dev/null expected=$(stat -c %b $MNT/foo) # Now deduplicate bar into foo. While the deduplication is in progres, # the number of used blocks/file size reported by stat should not change xfs_io -c "dedupe $MNT/bar 0 0 $file_size" $MNT/foo > /dev/null & dedupe_pid=$! while [ -n "$(ps -p $dedupe_pid -o pid=)" ]; do used=$(stat -c %b $MNT/foo) if [ $used -ne $expected ]; then echo "Unexpected blocks used: $used (expected: $expected)" fi done umount $DEV $ ./reproducer-3.sh Unexpected blocks used: 2076800 (expected: 2097152) Unexpected blocks used: 2097024 (expected: 2097152) Unexpected blocks used: 2079872 (expected: 2097152) (...) Note that since this is a short time window where the race can happen, the reproducer may not be able to always trigger the bug in one run, or it may trigger it multiple times. So fix this by: 1) Making btrfs_drop_extents() not decrement the VFS inode's number of bytes, and instead return the number of bytes; 2) Making any code that drops extents and adds new extents update the inode's number of bytes atomically, while holding the btrfs inode's spinlock, which is also used by the stat(2) callback to get the inode's number of bytes; 3) For ranges in the inode's iotree that are marked as 'delalloc new', corresponding to previously unallocated ranges, increment the inode's number of bytes when clearing the 'delalloc new' bit from the range, in the same critical section that decrements the inode's 'new_delalloc_bytes' counter, delimited by the btrfs inode's spinlock. An alternative would be to have btrfs_getattr() wait for any IO (ordered extents in progress) and locking the whole range (0 to (u64)-1) while it it computes the number of blocks used. But that would mean blocking stat(2), which is a very used syscall and expected to be fast, waiting for writes, clone/dedupe, fallocate, page reads, fiemap, etc. CC: stable@vger.kernel.org # 5.4+ Reviewed-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: Filipe Manana <fdmanana@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-11-04 11:07:34 +00:00
#define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING | \
EXTENT_ADD_INODE_BYTES)
/*
* Redefined bits above which are used only in the device allocation tree,
* shouldn't be using EXTENT_LOCKED / EXTENT_BOUNDARY / EXTENT_CLEAR_META_RESV
* / EXTENT_CLEAR_DATA_RESV because they have special meaning to the bit
* manipulation functions
*/
#define CHUNK_ALLOCATED EXTENT_DIRTY
#define CHUNK_TRIMMED EXTENT_DEFRAG
btrfs: trim: fix underflow in trim length to prevent access beyond device boundary [BUG] The following script can lead to tons of beyond device boundary access: mkfs.btrfs -f $dev -b 10G mount $dev $mnt trimfs $mnt btrfs filesystem resize 1:-1G $mnt trimfs $mnt [CAUSE] Since commit 929be17a9b49 ("btrfs: Switch btrfs_trim_free_extents to find_first_clear_extent_bit"), we try to avoid trimming ranges that's already trimmed. So we check device->alloc_state by finding the first range which doesn't have CHUNK_TRIMMED and CHUNK_ALLOCATED not set. But if we shrunk the device, that bits are not cleared, thus we could easily got a range starts beyond the shrunk device size. This results the returned @start and @end are all beyond device size, then we call "end = min(end, device->total_bytes -1);" making @end smaller than device size. Then finally we goes "len = end - start + 1", totally underflow the result, and lead to the beyond-device-boundary access. [FIX] This patch will fix the problem in two ways: - Clear CHUNK_TRIMMED | CHUNK_ALLOCATED bits when shrinking device This is the root fix - Add extra safety check when trimming free device extents We check and warn if the returned range is already beyond current device. Link: https://github.com/kdave/btrfs-progs/issues/282 Fixes: 929be17a9b49 ("btrfs: Switch btrfs_trim_free_extents to find_first_clear_extent_bit") CC: stable@vger.kernel.org # 5.4+ Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-07-31 11:29:11 +00:00
#define CHUNK_STATE_MASK (CHUNK_ALLOCATED | \
CHUNK_TRIMMED)
enum {
IO_TREE_FS_PINNED_EXTENTS,
IO_TREE_FS_EXCLUDED_EXTENTS,
IO_TREE_BTREE_INODE_IO,
IO_TREE_INODE_IO,
IO_TREE_INODE_IO_FAILURE,
IO_TREE_RELOC_BLOCKS,
IO_TREE_TRANS_DIRTY_PAGES,
IO_TREE_ROOT_DIRTY_LOG_PAGES,
IO_TREE_INODE_FILE_EXTENT,
btrfs: fix corrupt log due to concurrent fsync of inodes with shared extents When we have extents shared amongst different inodes in the same subvolume, if we fsync them in parallel we can end up with checksum items in the log tree that represent ranges which overlap. For example, consider we have inodes A and B, both sharing an extent that covers the logical range from X to X + 64KiB: 1) Task A starts an fsync on inode A; 2) Task B starts an fsync on inode B; 3) Task A calls btrfs_csum_file_blocks(), and the first search in the log tree, through btrfs_lookup_csum(), returns -EFBIG because it finds an existing checksum item that covers the range from X - 64KiB to X; 4) Task A checks that the checksum item has not reached the maximum possible size (MAX_CSUM_ITEMS) and then releases the search path before it does another path search for insertion (through a direct call to btrfs_search_slot()); 5) As soon as task A releases the path and before it does the search for insertion, task B calls btrfs_csum_file_blocks() and gets -EFBIG too, because there is an existing checksum item that has an end offset that matches the start offset (X) of the checksum range we want to log; 6) Task B releases the path; 7) Task A does the path search for insertion (through btrfs_search_slot()) and then verifies that the checksum item that ends at offset X still exists and extends its size to insert the checksums for the range from X to X + 64KiB; 8) Task A releases the path and returns from btrfs_csum_file_blocks(), having inserted the checksums into an existing checksum item that got its size extended. At this point we have one checksum item in the log tree that covers the logical range from X - 64KiB to X + 64KiB; 9) Task B now does a search for insertion using btrfs_search_slot() too, but it finds that the previous checksum item no longer ends at the offset X, it now ends at an of offset X + 64KiB, so it leaves that item untouched. Then it releases the path and calls btrfs_insert_empty_item() that inserts a checksum item with a key offset corresponding to X and a size for inserting a single checksum (4 bytes in case of crc32c). Subsequent iterations end up extending this new checksum item so that it contains the checksums for the range from X to X + 64KiB. So after task B returns from btrfs_csum_file_blocks() we end up with two checksum items in the log tree that have overlapping ranges, one for the range from X - 64KiB to X + 64KiB, and another for the range from X to X + 64KiB. Having checksum items that represent ranges which overlap, regardless of being in the log tree or in the chekcsums tree, can lead to problems where checksums for a file range end up not being found. This type of problem has happened a few times in the past and the following commits fixed them and explain in detail why having checksum items with overlapping ranges is problematic: 27b9a8122ff71a "Btrfs: fix csum tree corruption, duplicate and outdated checksums" b84b8390d6009c "Btrfs: fix file read corruption after extent cloning and fsync" 40e046acbd2f36 "Btrfs: fix missing data checksums after replaying a log tree" Since this specific instance of the problem can only happen when logging inodes, because it is the only case where concurrent attempts to insert checksums for the same range can happen, fix the issue by using an extent io tree as a range lock to serialize checksum insertion during inode logging. This issue could often be reproduced by the test case generic/457 from fstests. When it happens it produces the following trace: BTRFS critical (device dm-0): corrupt leaf: root=18446744073709551610 block=30625792 slot=42, csum end range (15020032) goes beyond the start range (15015936) of the next csum item BTRFS info (device dm-0): leaf 30625792 gen 7 total ptrs 49 free space 2402 owner 18446744073709551610 BTRFS info (device dm-0): refs 1 lock (w:0 r:0 bw:0 br:0 sw:0 sr:0) lock_owner 0 current 15884 item 0 key (18446744073709551606 128 13979648) itemoff 3991 itemsize 4 item 1 key (18446744073709551606 128 13983744) itemoff 3987 itemsize 4 item 2 key (18446744073709551606 128 13987840) itemoff 3983 itemsize 4 item 3 key (18446744073709551606 128 13991936) itemoff 3979 itemsize 4 item 4 key (18446744073709551606 128 13996032) itemoff 3975 itemsize 4 item 5 key (18446744073709551606 128 14000128) itemoff 3971 itemsize 4 (...) BTRFS error (device dm-0): block=30625792 write time tree block corruption detected ------------[ cut here ]------------ WARNING: CPU: 1 PID: 15884 at fs/btrfs/disk-io.c:539 btree_csum_one_bio+0x268/0x2d0 [btrfs] Modules linked in: btrfs dm_thin_pool ... CPU: 1 PID: 15884 Comm: fsx Tainted: G W 5.6.0-rc7-btrfs-next-58 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 RIP: 0010:btree_csum_one_bio+0x268/0x2d0 [btrfs] Code: c7 c7 ... RSP: 0018:ffffbb0109e6f8e0 EFLAGS: 00010296 RAX: 0000000000000000 RBX: ffffe1c0847b6080 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffffaa963988 RDI: 0000000000000001 RBP: ffff956a4f4d2000 R08: 0000000000000000 R09: 0000000000000001 R10: 0000000000000526 R11: 0000000000000000 R12: ffff956a5cd28bb0 R13: 0000000000000000 R14: ffff956a649c9388 R15: 000000011ed82000 FS: 00007fb419959e80(0000) GS:ffff956a7aa00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000fe6d54 CR3: 0000000138696005 CR4: 00000000003606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: btree_submit_bio_hook+0x67/0xc0 [btrfs] submit_one_bio+0x31/0x50 [btrfs] btree_write_cache_pages+0x2db/0x4b0 [btrfs] ? __filemap_fdatawrite_range+0xb1/0x110 do_writepages+0x23/0x80 __filemap_fdatawrite_range+0xd2/0x110 btrfs_write_marked_extents+0x15e/0x180 [btrfs] btrfs_sync_log+0x206/0x10a0 [btrfs] ? kmem_cache_free+0x315/0x3b0 ? btrfs_log_inode+0x1e8/0xf90 [btrfs] ? __mutex_unlock_slowpath+0x45/0x2a0 ? lockref_put_or_lock+0x9/0x30 ? dput+0x2d/0x580 ? dput+0xb5/0x580 ? btrfs_sync_file+0x464/0x4d0 [btrfs] btrfs_sync_file+0x464/0x4d0 [btrfs] do_fsync+0x38/0x60 __x64_sys_fsync+0x10/0x20 do_syscall_64+0x5c/0x280 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7fb41953a6d0 Code: 48 3d ... RSP: 002b:00007ffcc86bd218 EFLAGS: 00000246 ORIG_RAX: 000000000000004a RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007fb41953a6d0 RDX: 0000000000000009 RSI: 0000000000040000 RDI: 0000000000000003 RBP: 0000000000040000 R08: 0000000000000001 R09: 0000000000000009 R10: 0000000000000064 R11: 0000000000000246 R12: 0000556cf4b2c060 R13: 0000000000000100 R14: 0000000000000000 R15: 0000556cf322b420 irq event stamp: 0 hardirqs last enabled at (0): [<0000000000000000>] 0x0 hardirqs last disabled at (0): [<ffffffffa96bdedf>] copy_process+0x74f/0x2020 softirqs last enabled at (0): [<ffffffffa96bdedf>] copy_process+0x74f/0x2020 softirqs last disabled at (0): [<0000000000000000>] 0x0 ---[ end trace d543fc76f5ad7fd8 ]--- In that trace the tree checker detected the overlapping checksum items at the time when we triggered writeback for the log tree when syncing the log. Another trace that can happen is due to BUG_ON() when deleting checksum items while logging an inode: BTRFS critical (device dm-0): slot 81 key (18446744073709551606 128 13635584) new key (18446744073709551606 128 13635584) BTRFS info (device dm-0): leaf 30949376 gen 7 total ptrs 98 free space 8527 owner 18446744073709551610 BTRFS info (device dm-0): refs 4 lock (w:1 r:0 bw:0 br:0 sw:1 sr:0) lock_owner 13473 current 13473 item 0 key (257 1 0) itemoff 16123 itemsize 160 inode generation 7 size 262144 mode 100600 item 1 key (257 12 256) itemoff 16103 itemsize 20 item 2 key (257 108 0) itemoff 16050 itemsize 53 extent data disk bytenr 13631488 nr 4096 extent data offset 0 nr 131072 ram 131072 (...) ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.c:3153! invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC PTI CPU: 1 PID: 13473 Comm: fsx Not tainted 5.6.0-rc7-btrfs-next-58 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 RIP: 0010:btrfs_set_item_key_safe+0x1ea/0x270 [btrfs] Code: 0f b6 ... RSP: 0018:ffff95e3889179d0 EFLAGS: 00010282 RAX: 0000000000000000 RBX: 0000000000000051 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffffb7763988 RDI: 0000000000000001 RBP: fffffffffffffff6 R08: 0000000000000000 R09: 0000000000000001 R10: 00000000000009ef R11: 0000000000000000 R12: ffff8912a8ba5a08 R13: ffff95e388917a06 R14: ffff89138dcf68c8 R15: ffff95e388917ace FS: 00007fe587084e80(0000) GS:ffff8913baa00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fe587091000 CR3: 0000000126dac005 CR4: 00000000003606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: btrfs_del_csums+0x2f4/0x540 [btrfs] copy_items+0x4b5/0x560 [btrfs] btrfs_log_inode+0x910/0xf90 [btrfs] btrfs_log_inode_parent+0x2a0/0xe40 [btrfs] ? dget_parent+0x5/0x370 btrfs_log_dentry_safe+0x4a/0x70 [btrfs] btrfs_sync_file+0x42b/0x4d0 [btrfs] __x64_sys_msync+0x199/0x200 do_syscall_64+0x5c/0x280 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7fe586c65760 Code: 00 f7 ... RSP: 002b:00007ffe250f98b8 EFLAGS: 00000246 ORIG_RAX: 000000000000001a RAX: ffffffffffffffda RBX: 00000000000040e1 RCX: 00007fe586c65760 RDX: 0000000000000004 RSI: 0000000000006b51 RDI: 00007fe58708b000 RBP: 0000000000006a70 R08: 0000000000000003 R09: 00007fe58700cb61 R10: 0000000000000100 R11: 0000000000000246 R12: 00000000000000e1 R13: 00007fe58708b000 R14: 0000000000006b51 R15: 0000558de021a420 Modules linked in: dm_log_writes ... ---[ end trace c92a7f447a8515f5 ]--- CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-05-18 11:14:50 +00:00
IO_TREE_LOG_CSUM_RANGE,
IO_TREE_SELFTEST,
IO_TREE_DEVICE_ALLOC_STATE,
};
struct extent_io_tree {
struct rb_root state;
struct btrfs_fs_info *fs_info;
void *private_data;
u64 dirty_bytes;
bool track_uptodate;
/* Who owns this io tree, should be one of IO_TREE_* */
u8 owner;
spinlock_t lock;
};
struct extent_state {
u64 start;
u64 end; /* inclusive */
struct rb_node rb_node;
/* ADD NEW ELEMENTS AFTER THIS */
wait_queue_head_t wq;
refcount_t refs;
u32 state;
struct io_failure_record *failrec;
#ifdef CONFIG_BTRFS_DEBUG
struct list_head leak_list;
#endif
};
int __init extent_state_cache_init(void);
void __cold extent_state_cache_exit(void);
void extent_io_tree_init(struct btrfs_fs_info *fs_info,
struct extent_io_tree *tree, unsigned int owner,
void *private_data);
void extent_io_tree_release(struct extent_io_tree *tree);
int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
struct extent_state **cached);
static inline int lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
{
return lock_extent_bits(tree, start, end, NULL);
}
int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
int __init extent_io_init(void);
void __cold extent_io_exit(void);
u64 count_range_bits(struct extent_io_tree *tree,
u64 *start, u64 search_end,
u64 max_bytes, u32 bits, int contig);
void free_extent_state(struct extent_state *state);
int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
u32 bits, int filled, struct extent_state *cached_state);
int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
u32 bits, struct extent_changeset *changeset);
int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
u32 bits, int wake, int delete,
struct extent_state **cached);
int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
u32 bits, int wake, int delete,
struct extent_state **cached, gfp_t mask,
struct extent_changeset *changeset);
static inline int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end)
{
return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, NULL);
}
static inline int unlock_extent_cached(struct extent_io_tree *tree, u64 start,
u64 end, struct extent_state **cached)
{
return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
GFP_NOFS, NULL);
}
static inline int unlock_extent_cached_atomic(struct extent_io_tree *tree,
u64 start, u64 end, struct extent_state **cached)
{
return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
GFP_ATOMIC, NULL);
}
static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start,
u64 end, u32 bits)
{
int wake = 0;
if (bits & EXTENT_LOCKED)
wake = 1;
return clear_extent_bit(tree, start, end, bits, wake, 0, NULL);
}
int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
u32 bits, struct extent_changeset *changeset);
int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
u32 bits, unsigned exclusive_bits, u64 *failed_start,
struct extent_state **cached_state, gfp_t mask,
struct extent_changeset *changeset);
int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start, u64 end,
u32 bits);
static inline int set_extent_bits(struct extent_io_tree *tree, u64 start,
u64 end, u32 bits)
{
return set_extent_bit(tree, start, end, bits, 0, NULL, NULL, GFP_NOFS,
NULL);
}
static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
u64 end, struct extent_state **cached_state)
{
return __clear_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, 0,
cached_state, GFP_NOFS, NULL);
}
static inline int set_extent_dirty(struct extent_io_tree *tree, u64 start,
u64 end, gfp_t mask)
{
return set_extent_bit(tree, start, end, EXTENT_DIRTY, 0, NULL, NULL,
mask, NULL);
}
static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start,
u64 end, struct extent_state **cached)
{
return clear_extent_bit(tree, start, end,
EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_DO_ACCOUNTING, 0, 0, cached);
}
int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
u32 bits, u32 clear_bits,
struct extent_state **cached_state);
static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start,
u64 end, u32 extra_bits,
struct extent_state **cached_state)
{
return set_extent_bit(tree, start, end,
EXTENT_DELALLOC | EXTENT_UPTODATE | extra_bits,
0, NULL, cached_state, GFP_NOFS, NULL);
}
static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start,
u64 end, struct extent_state **cached_state)
{
return set_extent_bit(tree, start, end,
EXTENT_DELALLOC | EXTENT_UPTODATE | EXTENT_DEFRAG,
0, NULL, cached_state, GFP_NOFS, NULL);
}
static inline int set_extent_new(struct extent_io_tree *tree, u64 start,
u64 end)
{
return set_extent_bit(tree, start, end, EXTENT_NEW, 0, NULL, NULL,
GFP_NOFS, NULL);
}
static inline int set_extent_uptodate(struct extent_io_tree *tree, u64 start,
u64 end, struct extent_state **cached_state, gfp_t mask)
{
return set_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, NULL,
cached_state, mask, NULL);
}
int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
u64 *start_ret, u64 *end_ret, u32 bits,
struct extent_state **cached_state);
void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start,
u64 *start_ret, u64 *end_ret, u32 bits);
int find_contiguous_extent_bit(struct extent_io_tree *tree, u64 start,
u64 *start_ret, u64 *end_ret, u32 bits);
int extent_invalidate_folio(struct extent_io_tree *tree,
struct folio *folio, size_t offset);
bool btrfs_find_delalloc_range(struct extent_io_tree *tree, u64 *start,
u64 *end, u64 max_bytes,
struct extent_state **cached_state);
/* This should be reworked in the future and put elsewhere. */
struct io_failure_record *get_state_failrec(struct extent_io_tree *tree, u64 start);
int set_state_failrec(struct extent_io_tree *tree, u64 start,
struct io_failure_record *failrec);
void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start,
u64 end);
int free_io_failure(struct extent_io_tree *failure_tree,
struct extent_io_tree *io_tree,
struct io_failure_record *rec);
int clean_io_failure(struct btrfs_fs_info *fs_info,
struct extent_io_tree *failure_tree,
struct extent_io_tree *io_tree, u64 start,
struct page *page, u64 ino, unsigned int pg_offset);
#endif /* BTRFS_EXTENT_IO_TREE_H */