The memory barrier (smp_mb()) at btrfs_sync_file() is completely redundant
now that fs_info->last_trans_committed is read using READ_ONCE(), with the
helper btrfs_get_last_trans_committed(), and written using WRITE_ONCE()
with the helper btrfs_set_last_trans_committed().
This barrier was introduced in 2011, by commit a4abeea41a ("Btrfs: kill
trans_mutex"), but even back then it was not correct since the writer side
(in btrfs_commit_transaction()), did not issue a pairing memory barrier
after it updated fs_info->last_trans_committed.
So remove this barrier.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Currently the last_trans_committed field of struct btrfs_fs_info is
modified and read without any locking or other protection. For example
early in the fsync path, skip_inode_logging() is called which reads
fs_info->last_trans_committed, but at the same time we can have a
transaction commit completing and updating that field.
In the case of an fsync this is harmless and any data race should be
rare and at most cause an unnecessary logging of an inode.
To avoid data race warnings from tools like KCSAN and other issues such
as load and store tearing (amongst others, see [1]), create helpers to
access the last_trans_committed field of struct btrfs_fs_info using
READ_ONCE() and WRITE_ONCE(), and use these helpers everywhere.
[1] https://lwn.net/Articles/793253/
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Currently the generation field of struct btrfs_fs_info is always modified
while holding fs_info->trans_lock locked. Most readers will access this
field without taking that lock but while holding a transaction handle,
which is safe to do due to the transaction life cycle.
However there are other readers that are neither holding the lock nor
holding a transaction handle open:
1) When reading an inode from disk, at btrfs_read_locked_inode();
2) When reading the generation to expose it to sysfs, at
btrfs_generation_show();
3) Early in the fsync path, at skip_inode_logging();
4) When creating a hole at btrfs_cont_expand(), during write paths,
truncate and reflinking;
5) In the fs_info ioctl (btrfs_ioctl_fs_info());
6) While mounting the filesystem, in the open_ctree() path. In these
cases it's safe to directly read fs_info->generation as no one
can concurrently start a transaction and update fs_info->generation.
In case of the fsync path, races here should be harmless, and in the worst
case they may cause a fsync to log an inode when it's not really needed,
so nothing bad from a functional perspective. In the other cases it's not
so clear if functional problems may arise, though in case 1 rare things
like a load/store tearing [1] may cause the BTRFS_INODE_NEEDS_FULL_SYNC
flag not being set on an inode and therefore result in incorrect logging
later on in case a fsync call is made.
To avoid data race warnings from tools like KCSAN and other issues such
as load and store tearing (amongst others, see [1]), create helpers to
access the generation field of struct btrfs_fs_info using READ_ONCE() and
WRITE_ONCE(), and use these helpers where needed.
[1] https://lwn.net/Articles/793253/
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The root argument for btrfs_update_inode() always matches the root of the
given inode, so remove the root argument and get it from the inode
argument.
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
While data extents require us to store additional inline refs to track
the original owner on free, this information is available implicitly for
metadata. It is found in the owner field of the header of the tree
block. Even if other trees refer to this block and the original ref goes
away, we will not rewrite that header field, so it will reliably give the
original owner.
In addition, there is a relocation case where a new data extent needs to
have an owning root separate from the referring root wired through
delayed refs.
To use it for recording simple quota deltas, we need to wire this root
id through from when we create the delayed ref until we fully process
it. Store it in the generic btrfs_ref struct of the delayed ref.
Signed-off-by: Boris Burkov <boris@bur.io>
Signed-off-by: David Sterba <dsterba@suse.com>
When marking an extent buffer as dirty, at btrfs_mark_buffer_dirty(),
we check if its generation matches the running transaction and if not we
just print a warning. Such mismatch is an indicator that something really
went wrong and only printing a warning message (and stack trace) is not
enough to prevent a corruption. Allowing a transaction to commit with such
an extent buffer will trigger an error if we ever try to read it from disk
due to a generation mismatch with its parent generation.
So abort the current transaction with -EUCLEAN if we notice a generation
mismatch. For this we need to pass a transaction handle to
btrfs_mark_buffer_dirty() which is always available except in test code,
in which case we can pass NULL since it operates on dummy extent buffers
and all test roots have a single node/leaf (root node at level 0).
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We use the iomap code in file.c, include it so we have our dependencies.
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
-----BEGIN PGP SIGNATURE-----
iHUEABYKAB0WIQRAhzRXHqcMeLMyaSiRxhvAZXjcogUCZQsZLQAKCRCRxhvAZXjc
op0vAP96hkSUnmXmxTr8GHId3yfElN8ZZ3aSfePeBdljjKEZVAEA2+cbHLy4GqRi
TpjP1HNIdmtbVSC2ZnrgqkbwGageQgg=
=s92y
-----END PGP SIGNATURE-----
Merge tag 'v6.6-rc3.vfs.ctime.revert' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs
Pull finegrained timestamp reverts from Christian Brauner:
"Earlier this week we sent a few minor fixes for the multi-grained
timestamp work in [1]. While we were polishing those up after Linus
realized that there might be a nicer way to fix them we received a
regression report in [2] that fine grained timestamps break gnulib
tests and thus possibly other tools.
The kernel will elide fine-grain timestamp updates when no one is
actively querying for them to avoid performance impacts. So a sequence
like write(f1) stat(f2) write(f2) stat(f2) write(f1) stat(f1) may
result in timestamp f1 to be older than the final f2 timestamp even
though f1 was last written too but the second write didn't update the
timestamp.
Such plotholes can lead to subtle bugs when programs compare
timestamps. For example, the nap() function in [2] will estimate that
it needs to wait one ns on a fine-grain timestamp enabled filesytem
between subsequent calls to observe a timestamp change. But in general
we don't update timestamps with more than one jiffie if we think that
no one is actively querying for fine-grain timestamps to avoid
performance impacts.
While discussing various fixes the decision was to go back to the
drawing board and ultimately to explore a solution that involves only
exposing such fine-grained timestamps to nfs internally and never to
userspace.
As there are multiple solutions discussed the honest thing to do here
is not to fix this up or disable it but to cleanly revert. The general
infrastructure will probably come back but there is no reason to keep
this code in mainline.
The general changes to timestamp handling are valid and a good cleanup
that will stay. The revert is fully bisectable"
Link: https://lore.kernel.org/all/20230918-hirte-neuzugang-4c2324e7bae3@brauner [1]
Link: https://lore.kernel.org/all/bf0524debb976627693e12ad23690094e4514303.camel@linuxfromscratch.org [2]
* tag 'v6.6-rc3.vfs.ctime.revert' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
Revert "fs: add infrastructure for multigrain timestamps"
Revert "btrfs: convert to multigrain timestamps"
Revert "ext4: switch to multigrain timestamps"
Revert "xfs: switch to multigrain timestamps"
Revert "tmpfs: add support for multigrain timestamps"
-----BEGIN PGP SIGNATURE-----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=0eEg
-----END PGP SIGNATURE-----
Merge tag 'for-6.6-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs fixes from David Sterba:
"A few more followup fixes to the directory listing.
People have noticed different behaviour compared to other filesystems
after changes in 6.5. This is now unified to more "logical" and
expected behaviour while still within POSIX. And a few more fixes for
stable.
- change behaviour of readdir()/rewinddir() when new directory
entries are created after opendir(), properly tracking the last
entry
- fix race in readdir when multiple threads can set the last entry
index for a directory
Additionally:
- use exclusive lock when direct io might need to drop privs and call
notify_change()
- don't clear uptodate bit on page after an error, this may lead to a
deadlock in subpage mode
- fix waiting pattern when multiple readers block on Merkle tree
data, switch to folios"
* tag 'for-6.6-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
btrfs: fix race between reading a directory and adding entries to it
btrfs: refresh dir last index during a rewinddir(3) call
btrfs: set last dir index to the current last index when opening dir
btrfs: don't clear uptodate on write errors
btrfs: file_remove_privs needs an exclusive lock in direct io write
btrfs: convert btrfs_read_merkle_tree_page() to use a folio
This reverts commit 50e9ceef1d.
Users reported regressions due to enabling multi-grained timestamps
unconditionally. As no clear consensus on a solution has come up and the
discussion has gone back to the drawing board revert the infrastructure
changes for. If it isn't code that's here to stay, make it go away.
Message-ID: <20230920-keine-eile-c9755b5825db@brauner>
Acked-by: Jan Kara <jack@suse.cz>
Acked-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
This was noticed by Miklos that file_remove_privs might call into
notify_change(), which requires to hold an exclusive lock. The problem
exists in FUSE and btrfs. We can fix it without any additional helpers
from VFS, in case the privileges would need to be dropped, change the
lock type to be exclusive and redo the loop.
Fixes: e9adabb971 ("btrfs: use shared lock for direct writes within EOF")
CC: Miklos Szeredi <miklos@szeredi.hu>
CC: stable@vger.kernel.org # 5.15+
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Bernd Schubert <bschubert@ddn.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
-----BEGIN PGP SIGNATURE-----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=N7Yn
-----END PGP SIGNATURE-----
Merge tag 'for-6.6-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs updates from David Sterba:
"No new features, the bulk of the changes are fixes, refactoring and
cleanups. The notable fix is the scrub performance restoration after
rewrite in 6.4, though still only partial.
Fixes:
- scrub performance drop due to rewrite in 6.4 partially restored:
- do IO grouping by blg_plug/blk_unplug again
- avoid unnecessary tree searches when processing stripes, in
extent and checksum trees
- the drop is noticeable on fast PCIe devices, -66% and restored
to -33% of the original
- backports to 6.4 planned
- handle more corner cases of transaction commit during orphan
cleanup or delayed ref processing
- use correct fsid/metadata_uuid when validating super block
- copy directory permissions and time when creating a stub subvolume
Core:
- debugging feature integrity checker deprecated, to be removed in
6.7
- in zoned mode, zones are activated just before the write, making
error handling easier, now the overcommit mechanism can be enabled
again which improves performance by avoiding more frequent flushing
- v0 extent handling completely removed, deprecated long time ago
- error handling improvements
- tests:
- extent buffer bitmap tests
- pinned extent splitting tests
- cleanups and refactoring:
- compression writeback
- extent buffer bitmap
- space flushing, ENOSPC handling"
* tag 'for-6.6-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (110 commits)
btrfs: zoned: skip splitting and logical rewriting on pre-alloc write
btrfs: tests: test invalid splitting when skipping pinned drop extent_map
btrfs: tests: add a test for btrfs_add_extent_mapping
btrfs: tests: add extent_map tests for dropping with odd layouts
btrfs: scrub: move write back of repaired sectors to scrub_stripe_read_repair_worker()
btrfs: scrub: don't go ordered workqueue for dev-replace
btrfs: scrub: fix grouping of read IO
btrfs: scrub: avoid unnecessary csum tree search preparing stripes
btrfs: scrub: avoid unnecessary extent tree search preparing stripes
btrfs: copy dir permission and time when creating a stub subvolume
btrfs: remove pointless empty list check when reading delayed dir indexes
btrfs: drop redundant check to use fs_devices::metadata_uuid
btrfs: compare the correct fsid/metadata_uuid in btrfs_validate_super
btrfs: use the correct superblock to compare fsid in btrfs_validate_super
btrfs: simplify memcpy either of metadata_uuid or fsid
btrfs: add a helper to read the superblock metadata_uuid
btrfs: remove v0 extent handling
btrfs: output extra debug info if we failed to find an inline backref
btrfs: move the !zoned assert into run_delalloc_cow
btrfs: consolidate the error handling in run_delalloc_nocow
...
* Make large writes to the page cache fill sparse parts of the cache
with large folios, then use large memcpy calls for the large folio.
* Track the per-block dirty state of each large folio so that a
buffered write to a single byte on a large folio does not result in a
(potentially) multi-megabyte writeback IO.
* Allow some directio completions to be performed in the initiating
task's context instead of punting through a workqueue. This will
reduce latency for some io_uring requests.
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
-----BEGIN PGP SIGNATURE-----
iHUEABYKAB0WIQQ2qTKExjcn+O1o2YRKO3ySh0YRpgUCZM0Z1AAKCRBKO3ySh0YR
pp7BAQCzkKejCM0185tNIH/faHjzidSisNQkJ5HoB4Opq9U66AEA6IPuAdlPlM/J
FPW1oPq33Yn7AV4wXjUNFfDLzVb/Fgg=
=dFBU
-----END PGP SIGNATURE-----
Merge tag 'iomap-6.6-merge-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux
Pull iomap updates from Darrick Wong:
"We've got some big changes for this release -- I'm very happy to be
landing willy's work to enable large folios for the page cache for
general read and write IOs when the fs can make contiguous space
allocations, and Ritesh's work to track sub-folio dirty state to
eliminate the write amplification problems inherent in using large
folios.
As a bonus, io_uring can now process write completions in the caller's
context instead of bouncing through a workqueue, which should reduce
io latency dramatically. IOWs, XFS should see a nice performance bump
for both IO paths.
Summary:
- Make large writes to the page cache fill sparse parts of the cache
with large folios, then use large memcpy calls for the large folio.
- Track the per-block dirty state of each large folio so that a
buffered write to a single byte on a large folio does not result in
a (potentially) multi-megabyte writeback IO.
- Allow some directio completions to be performed in the initiating
task's context instead of punting through a workqueue. This will
reduce latency for some io_uring requests"
* tag 'iomap-6.6-merge-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (26 commits)
iomap: support IOCB_DIO_CALLER_COMP
io_uring/rw: add write support for IOCB_DIO_CALLER_COMP
fs: add IOCB flags related to passing back dio completions
iomap: add IOMAP_DIO_INLINE_COMP
iomap: only set iocb->private for polled bio
iomap: treat a write through cache the same as FUA
iomap: use an unsigned type for IOMAP_DIO_* defines
iomap: cleanup up iomap_dio_bio_end_io()
iomap: Add per-block dirty state tracking to improve performance
iomap: Allocate ifs in ->write_begin() early
iomap: Refactor iomap_write_delalloc_punch() function out
iomap: Use iomap_punch_t typedef
iomap: Fix possible overflow condition in iomap_write_delalloc_scan
iomap: Add some uptodate state handling helpers for ifs state bitmap
iomap: Drop ifs argument from iomap_set_range_uptodate()
iomap: Rename iomap_page to iomap_folio_state and others
iomap: Copy larger chunks from userspace
iomap: Create large folios in the buffered write path
filemap: Allow __filemap_get_folio to allocate large folios
filemap: Add fgf_t typedef
...
Use LIST_HEAD() to initialize the list_head instead of open-coding it.
Signed-off-by: Ruan Jinjie <ruanjinjie@huawei.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Enable multigrain timestamps, which should ensure that there is an
apparent change to the timestamp whenever it has been written after
being actively observed via getattr.
Beyond enabling the FS_MGTIME flag, this patch eliminates
update_time_for_write, which goes to great pains to avoid in-memory
stores. Just have it overwrite the timestamps unconditionally.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Acked-by: David Sterba <dsterba@suse.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Message-Id: <20230807-mgctime-v7-13-d1dec143a704@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
Similarly to gfp_t, define fgf_t as its own type to prevent various
misuses and confusion. Leave the flags as FGP_* for now to reduce the
size of this patch; they will be converted to FGF_* later. Move the
documentation to the definition of the type insted of burying it in the
__filemap_get_folio() documentation.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Kent Overstreet <kent.overstreet@linux.dev>
In later patches, we're going to change how the inode's ctime field is
used. Switch to using accessor functions instead of raw accesses of
inode->i_ctime.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Message-Id: <20230705190309.579783-27-jlayton@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
- Yosry has also eliminated cgroup's atomic rstat flushing.
- Nhat Pham adds the new cachestat() syscall. It provides userspace
with the ability to query pagecache status - a similar concept to
mincore() but more powerful and with improved usability.
- Mel Gorman provides more optimizations for compaction, reducing the
prevalence of page rescanning.
- Lorenzo Stoakes has done some maintanance work on the get_user_pages()
interface.
- Liam Howlett continues with cleanups and maintenance work to the maple
tree code. Peng Zhang also does some work on maple tree.
- Johannes Weiner has done some cleanup work on the compaction code.
- David Hildenbrand has contributed additional selftests for
get_user_pages().
- Thomas Gleixner has contributed some maintenance and optimization work
for the vmalloc code.
- Baolin Wang has provided some compaction cleanups,
- SeongJae Park continues maintenance work on the DAMON code.
- Huang Ying has done some maintenance on the swap code's usage of
device refcounting.
- Christoph Hellwig has some cleanups for the filemap/directio code.
- Ryan Roberts provides two patch series which yield some
rationalization of the kernel's access to pte entries - use the provided
APIs rather than open-coding accesses.
- Lorenzo Stoakes has some fixes to the interaction between pagecache
and directio access to file mappings.
- John Hubbard has a series of fixes to the MM selftesting code.
- ZhangPeng continues the folio conversion campaign.
- Hugh Dickins has been working on the pagetable handling code, mainly
with a view to reducing the load on the mmap_lock.
- Catalin Marinas has reduced the arm64 kmalloc() minimum alignment from
128 to 8.
- Domenico Cerasuolo has improved the zswap reclaim mechanism by
reorganizing the LRU management.
- Matthew Wilcox provides some fixups to make gfs2 work better with the
buffer_head code.
- Vishal Moola also has done some folio conversion work.
- Matthew Wilcox has removed the remnants of the pagevec code - their
functionality is migrated over to struct folio_batch.
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZJejewAKCRDdBJ7gKXxA
joggAPwKMfT9lvDBEUnJagY7dbDPky1cSYZdJKxxM2cApGa42gEA6Cl8HRAWqSOh
J0qXCzqaaN8+BuEyLGDVPaXur9KirwY=
=B7yQ
-----END PGP SIGNATURE-----
Merge tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull mm updates from Andrew Morton:
- Yosry Ahmed brought back some cgroup v1 stats in OOM logs
- Yosry has also eliminated cgroup's atomic rstat flushing
- Nhat Pham adds the new cachestat() syscall. It provides userspace
with the ability to query pagecache status - a similar concept to
mincore() but more powerful and with improved usability
- Mel Gorman provides more optimizations for compaction, reducing the
prevalence of page rescanning
- Lorenzo Stoakes has done some maintanance work on the
get_user_pages() interface
- Liam Howlett continues with cleanups and maintenance work to the
maple tree code. Peng Zhang also does some work on maple tree
- Johannes Weiner has done some cleanup work on the compaction code
- David Hildenbrand has contributed additional selftests for
get_user_pages()
- Thomas Gleixner has contributed some maintenance and optimization
work for the vmalloc code
- Baolin Wang has provided some compaction cleanups,
- SeongJae Park continues maintenance work on the DAMON code
- Huang Ying has done some maintenance on the swap code's usage of
device refcounting
- Christoph Hellwig has some cleanups for the filemap/directio code
- Ryan Roberts provides two patch series which yield some
rationalization of the kernel's access to pte entries - use the
provided APIs rather than open-coding accesses
- Lorenzo Stoakes has some fixes to the interaction between pagecache
and directio access to file mappings
- John Hubbard has a series of fixes to the MM selftesting code
- ZhangPeng continues the folio conversion campaign
- Hugh Dickins has been working on the pagetable handling code, mainly
with a view to reducing the load on the mmap_lock
- Catalin Marinas has reduced the arm64 kmalloc() minimum alignment
from 128 to 8
- Domenico Cerasuolo has improved the zswap reclaim mechanism by
reorganizing the LRU management
- Matthew Wilcox provides some fixups to make gfs2 work better with the
buffer_head code
- Vishal Moola also has done some folio conversion work
- Matthew Wilcox has removed the remnants of the pagevec code - their
functionality is migrated over to struct folio_batch
* tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (380 commits)
mm/hugetlb: remove hugetlb_set_page_subpool()
mm: nommu: correct the range of mmap_sem_read_lock in task_mem()
hugetlb: revert use of page_cache_next_miss()
Revert "page cache: fix page_cache_next/prev_miss off by one"
mm/vmscan: fix root proactive reclaim unthrottling unbalanced node
mm: memcg: rename and document global_reclaim()
mm: kill [add|del]_page_to_lru_list()
mm: compaction: convert to use a folio in isolate_migratepages_block()
mm: zswap: fix double invalidate with exclusive loads
mm: remove unnecessary pagevec includes
mm: remove references to pagevec
mm: rename invalidate_mapping_pagevec to mapping_try_invalidate
mm: remove struct pagevec
net: convert sunrpc from pagevec to folio_batch
i915: convert i915_gpu_error to use a folio_batch
pagevec: rename fbatch_count()
mm: remove check_move_unevictable_pages()
drm: convert drm_gem_put_pages() to use a folio_batch
i915: convert shmem_sg_free_table() to use a folio_batch
scatterlist: add sg_set_folio()
...
-----BEGIN PGP SIGNATURE-----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=KhW4
-----END PGP SIGNATURE-----
Merge tag 'for-6.5/splice-2023-06-23' of git://git.kernel.dk/linux
Pull splice updates from Jens Axboe:
"This kills off ITER_PIPE to avoid a race between truncate,
iov_iter_revert() on the pipe and an as-yet incomplete DMA to a bio
with unpinned/unref'ed pages from an O_DIRECT splice read. This causes
memory corruption.
Instead, we either use (a) filemap_splice_read(), which invokes the
buffered file reading code and splices from the pagecache into the
pipe; (b) copy_splice_read(), which bulk-allocates a buffer, reads
into it and then pushes the filled pages into the pipe; or (c) handle
it in filesystem-specific code.
Summary:
- Rename direct_splice_read() to copy_splice_read()
- Simplify the calculations for the number of pages to be reclaimed
in copy_splice_read()
- Turn do_splice_to() into a helper, vfs_splice_read(), so that it
can be used by overlayfs and coda to perform the checks on the
lower fs
- Make vfs_splice_read() jump to copy_splice_read() to handle
direct-I/O and DAX
- Provide shmem with its own splice_read to handle non-existent pages
in the pagecache. We don't want a ->read_folio() as we don't want
to populate holes, but filemap_get_pages() requires it
- Provide overlayfs with its own splice_read to call down to a lower
layer as overlayfs doesn't provide ->read_folio()
- Provide coda with its own splice_read to call down to a lower layer
as coda doesn't provide ->read_folio()
- Direct ->splice_read to copy_splice_read() in tty, procfs, kernfs
and random files as they just copy to the output buffer and don't
splice pages
- Provide wrappers for afs, ceph, ecryptfs, ext4, f2fs, nfs, ntfs3,
ocfs2, orangefs, xfs and zonefs to do locking and/or revalidation
- Make cifs use filemap_splice_read()
- Replace pointers to generic_file_splice_read() with pointers to
filemap_splice_read() as DIO and DAX are handled in the caller;
filesystems can still provide their own alternate ->splice_read()
op
- Remove generic_file_splice_read()
- Remove ITER_PIPE and its paraphernalia as generic_file_splice_read
was the only user"
* tag 'for-6.5/splice-2023-06-23' of git://git.kernel.dk/linux: (31 commits)
splice: kdoc for filemap_splice_read() and copy_splice_read()
iov_iter: Kill ITER_PIPE
splice: Remove generic_file_splice_read()
splice: Use filemap_splice_read() instead of generic_file_splice_read()
cifs: Use filemap_splice_read()
trace: Convert trace/seq to use copy_splice_read()
zonefs: Provide a splice-read wrapper
xfs: Provide a splice-read wrapper
orangefs: Provide a splice-read wrapper
ocfs2: Provide a splice-read wrapper
ntfs3: Provide a splice-read wrapper
nfs: Provide a splice-read wrapper
f2fs: Provide a splice-read wrapper
ext4: Provide a splice-read wrapper
ecryptfs: Provide a splice-read wrapper
ceph: Provide a splice-read wrapper
afs: Provide a splice-read wrapper
9p: Add splice_read wrapper
net: Make sock_splice_read() use copy_splice_read() by default
tty, proc, kernfs, random: Use copy_splice_read()
...
Since commit a2ad63daa8 ("VFS: add FMODE_CAN_ODIRECT file flag") file
systems can just set the FMODE_CAN_ODIRECT flag at open time instead of
wiring up a dummy direct_IO method to indicate support for direct I/O.
Do that for btrfs so that noop_direct_IO can eventually be removed.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The writeback_control structure already passes down the information about
a writeback being synchronous from the core VM code, and thus information
is propagated into the bio REQ_SYNC flag through the wbc_to_write_flags
helper.
Use that information to decide if checksums calculation is offloaded to
a workqueue instead of btrfs_inode::sync_writers field that not only
bloats the inode but also has too wide scope, being inode wide instead
of limited to the actual writeback request.
The sync writes were set in:
- btrfs_do_write_iter - regular IO, sync status is set
- start_ordered_ops - ordered write start, writeback with WB_SYNC_ALL
mode
- btrfs_write_marked_extents - write marked extents, writeback with
WB_SYNC_ALL mode
Reviewed-by: Chris Mason <clm@fb.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: David Sterba <dsterba@suse.com>
[ update changelog ]
Signed-off-by: David Sterba <dsterba@suse.com>
Patch series "cleanup the filemap / direct I/O interaction", v4.
This series cleans up some of the generic write helper calling conventions
and the page cache writeback / invalidation for direct I/O. This is a
spinoff from the no-bufferhead kernel project, for which we'll want to an
use iomap based buffered write path in the block layer.
This patch (of 12):
The last user of current->backing_dev_info disappeared in commit
b9b1335e64 ("remove bdi_congested() and wb_congested() and related
functions"). Remove the field and all assignments to it.
Link: https://lkml.kernel.org/r/20230601145904.1385409-1-hch@lst.de
Link: https://lkml.kernel.org/r/20230601145904.1385409-2-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Acked-by: Theodore Ts'o <tytso@mit.edu>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andreas Gruenbacher <agruenba@redhat.com>
Cc: Anna Schumaker <anna@kernel.org>
Cc: Chao Yu <chao@kernel.org>
Cc: Ilya Dryomov <idryomov@gmail.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: Miklos Szeredi <mszeredi@redhat.com>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This returns a pointer to the current iovec entry in the iterator. Only
useful with ITER_IOVEC right now, but it prepares us to treat ITER_UBUF
and ITER_IOVEC identically for the first segment.
Rename struct iov_iter->iov to iov_iter->__iov to find any potentially
troublesome spots, and also to prevent anyone from adding new code that
accesses iter->iov directly.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Given that wait is always set to 1, so remove the argument.
Last use of wait with 0 was in 0c304304fe ("Btrfs: remove
csum_bytes_left").
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
During lseek, for SEEK_DATA and SEEK_HOLE modes, we access the disk_bytenr
of an extent without checking its type. However inline extents have their
data starting the offset of the disk_bytenr field, so accessing that field
when we have an inline extent can result in either of the following:
1) Interpret the inline extent's data as a disk_bytenr value;
2) In case the inline data is less than 8 bytes, we access part of some
other item in the leaf, or unused space in the leaf;
3) In case the inline data is less than 8 bytes and the extent item is
the first item in the leaf, we can access beyond the leaf's limit.
So fix this by not accessing the disk_bytenr field if we have an inline
extent.
Fixes: b6e833567e ("btrfs: make hole and data seeking a lot more efficient")
Reported-by: Matthias Schoepfer <matthias.schoepfer@googlemail.com>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=216908
Link: https://lore.kernel.org/linux-btrfs/7f25442f-b121-2a3a-5a3d-22bcaae83cd4@leemhuis.info/
CC: stable@vger.kernel.org # 6.1
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
During lseek, when searching for delalloc in a range that represents a
hole and that range has a length of 1 byte, we end up not doing the actual
delalloc search in the inode's io tree, resulting in not correctly
reporting the offset with data or a hole. This actually only happens when
the start offset is 0 because with any other start offset we round it down
by sector size.
Reproducer:
$ mkfs.btrfs -f /dev/sdc
$ mount /dev/sdc /mnt/sdc
$ xfs_io -f -c "pwrite -q 0 1" /mnt/sdc/foo
$ xfs_io -c "seek -d 0" /mnt/sdc/foo
Whence Result
DATA EOF
It should have reported an offset of 0 instead of EOF.
Fix this by updating btrfs_find_delalloc_in_range() and count_range_bits()
to deal with inclusive ranges properly. These functions are already
supposed to work with inclusive end offsets, they just got it wrong in a
couple places due to off-by-one mistakes.
A test case for fstests will be added later.
Reported-by: Joan Bruguera Micó <joanbrugueram@gmail.com>
Link: https://lore.kernel.org/linux-btrfs/20221223020509.457113-1-joanbrugueram@gmail.com/
Fixes: b6e833567e ("btrfs: make hole and data seeking a lot more efficient")
CC: stable@vger.kernel.org # 6.1
Tested-by: Joan Bruguera Micó <joanbrugueram@gmail.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
If we get -ENOMEM while dropping file extent items in a given range, at
btrfs_drop_extents(), due to failure to allocate memory when attempting to
increment the reference count for an extent or drop the reference count,
we handle it with a BUG_ON(). This is excessive, instead we can simply
abort the transaction and return the error to the caller. In fact most
callers of btrfs_drop_extents(), directly or indirectly, already abort
the transaction if btrfs_drop_extents() returns any error.
Also, we already have error paths at btrfs_drop_extents() that may return
-ENOMEM and in those cases we abort the transaction, like for example
anything that changes the b+tree may return -ENOMEM due to a failure to
allocate a new extent buffer when COWing an existing extent buffer, such
as a call to btrfs_duplicate_item() for example.
So replace the BUG_ON() calls with proper logic to abort the transaction
and return the error.
Reported-by: syzbot+0b1fb6b0108c27419f9f@syzkaller.appspotmail.com
Link: https://lore.kernel.org/linux-btrfs/00000000000089773e05ee4b9cb4@google.com/
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>
During lseek (SEEK_HOLE/DATA), whenever we find a hole or prealloc extent,
we will look for delalloc in that range, and one of the things we do for
that is to find out ranges in the inode's io_tree marked with
EXTENT_DELALLOC, using calls to count_range_bits().
Typically there's a single, or few, searches in the io_tree for delalloc
per lseek call. However it's common for applications to keep calling
lseek with SEEK_HOLE and SEEK_DATA to find where extents and holes are in
a file, read the extents and skip holes in order to avoid unnecessary IO
and save disk space by preserving holes.
One popular user is the cp utility from coreutils. Starting with coreutils
9.0, cp uses SEEK_HOLE and SEEK_DATA to iterate over the extents of a
file. Before 9.0, it used fiemap to figure out where holes and extents are
in the source file. Another popular user is the tar utility when used with
the --sparse / -S option to detect and preserve holes.
Given that the pattern is to keep calling lseek with a start offset that
matches the returned offset from the previous lseek call, we can benefit
from caching the last extent state visited in count_range_bits() and use
it for the next count_range_bits() from the next lseek call. Example,
the following strace excerpt from running tar:
$ strace tar cJSvf foo.tar.xz qemu_disk_file.raw
(...)
lseek(5, 125019574272, SEEK_HOLE) = 125024989184
lseek(5, 125024989184, SEEK_DATA) = 125024993280
lseek(5, 125024993280, SEEK_HOLE) = 125025239040
lseek(5, 125025239040, SEEK_DATA) = 125025255424
lseek(5, 125025255424, SEEK_HOLE) = 125025353728
lseek(5, 125025353728, SEEK_DATA) = 125025357824
lseek(5, 125025357824, SEEK_HOLE) = 125026766848
lseek(5, 125026766848, SEEK_DATA) = 125026770944
lseek(5, 125026770944, SEEK_HOLE) = 125027053568
(...)
Shows that pattern, which is the same as with cp from coreutils 9.0+.
So start using a cached state for the delalloc searches in lseek, and
store it in struct file's private data so that it can be reused across
lseek calls.
This change is part of a patchset that is comprised of the following
patches:
1/9 btrfs: remove leftover setting of EXTENT_UPTODATE state in an inode's io_tree
2/9 btrfs: add an early exit when searching for delalloc range for lseek/fiemap
3/9 btrfs: skip unnecessary delalloc searches during lseek/fiemap
4/9 btrfs: search for delalloc more efficiently during lseek/fiemap
5/9 btrfs: remove no longer used btrfs_next_extent_map()
6/9 btrfs: allow passing a cached state record to count_range_bits()
7/9 btrfs: update stale comment for count_range_bits()
8/9 btrfs: use cached state when looking for delalloc ranges with fiemap
9/9 btrfs: use cached state when looking for delalloc ranges with lseek
The following test was run before and after applying the whole patchset:
$ cat test-cp.sh
#!/bin/bash
DEV=/dev/sdh
MNT=/mnt/sdh
# coreutils 8.32, cp uses fiemap to detect holes and extents
#CP_PROG=/usr/bin/cp
# coreutils 9.1, cp uses SEEK_HOLE/DATA to detect holes and extents
CP_PROG=/home/fdmanana/git/hub/coreutils/src/cp
umount $DEV &> /dev/null
mkfs.btrfs -f $DEV
mount $DEV $MNT
FILE_SIZE=$((1024 * 1024 * 1024))
echo "Creating file with a size of $((FILE_SIZE / 1024 / 1024))M"
# Create a very sparse file, where each extent has a length of 4K and
# is preceded by a 4K hole and followed by another 4K hole.
start=$(date +%s%N)
echo -n > $MNT/foobar
for ((off = 0; off < $FILE_SIZE; off += 8192)); do
xfs_io -c "pwrite -S 0xab $off 4K" $MNT/foobar > /dev/null
echo -ne "\r$off / $FILE_SIZE ..."
done
end=$(date +%s%N)
echo -e "\nFile created ($(( (end - start) / 1000000 )) milliseconds)"
start=$(date +%s%N)
$CP_PROG $MNT/foobar /dev/null
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "cp took $dur milliseconds with data/metadata cached and delalloc"
# Flush all delalloc.
sync
start=$(date +%s%N)
$CP_PROG $MNT/foobar /dev/null
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "cp took $dur milliseconds with data/metadata cached and no delalloc"
# Unmount and mount again to test the case without any metadata
# loaded in memory.
umount $MNT
mount $DEV $MNT
start=$(date +%s%N)
$CP_PROG $MNT/foobar /dev/null
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "cp took $dur milliseconds without data/metadata cached and no delalloc"
umount $MNT
The results, running on a box with a non-debug kernel (Debian's default
kernel config), were the following:
128M file, before patchset:
cp took 16574 milliseconds with data/metadata cached and delalloc
cp took 122 milliseconds with data/metadata cached and no delalloc
cp took 20144 milliseconds without data/metadata cached and no delalloc
128M file, after patchset:
cp took 6277 milliseconds with data/metadata cached and delalloc
cp took 109 milliseconds with data/metadata cached and no delalloc
cp took 210 milliseconds without data/metadata cached and no delalloc
512M file, before patchset:
cp took 14369 milliseconds with data/metadata cached and delalloc
cp took 429 milliseconds with data/metadata cached and no delalloc
cp took 88034 milliseconds without data/metadata cached and no delalloc
512M file, after patchset:
cp took 12106 milliseconds with data/metadata cached and delalloc
cp took 427 milliseconds with data/metadata cached and no delalloc
cp took 824 milliseconds without data/metadata cached and no delalloc
1G file, before patchset:
cp took 10074 milliseconds with data/metadata cached and delalloc
cp took 886 milliseconds with data/metadata cached and no delalloc
cp took 181261 milliseconds without data/metadata cached and no delalloc
1G file, after patchset:
cp took 3320 milliseconds with data/metadata cached and delalloc
cp took 880 milliseconds with data/metadata cached and no delalloc
cp took 1801 milliseconds without data/metadata cached and no delalloc
Reported-by: Wang Yugui <wangyugui@e16-tech.com>
Link: https://lore.kernel.org/linux-btrfs/20221106073028.71F9.409509F4@e16-tech.com/
Link: https://lore.kernel.org/linux-btrfs/CAL3q7H5NSVicm7nYBJ7x8fFkDpno8z3PYt5aPU43Bajc1H0h1Q@mail.gmail.com/
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
During fiemap, whenever we find a hole or prealloc extent, we will look
for delalloc in that range, and one of the things we do for that is to
find out ranges in the inode's io_tree marked with EXTENT_DELALLOC, using
calls to count_range_bits().
Since we process file extents from left to right, if we have a file with
several holes or prealloc extents, we benefit from keeping a cached extent
state record for calls to count_range_bits(). Most of the time the last
extent state record we visited in one call to count_range_bits() matches
the first extent state record we will use in the next call to
count_range_bits(), so there's a benefit here. So use an extent state
record to cache results from count_range_bits() calls during fiemap.
This change is part of a patchset that has the goal to make performance
better for applications that use lseek's SEEK_HOLE and SEEK_DATA modes to
iterate over the extents of a file. Two examples are the cp program from
coreutils 9.0+ and the tar program (when using its --sparse / -S option).
A sample test and results are listed in the changelog of the last patch
in the series:
1/9 btrfs: remove leftover setting of EXTENT_UPTODATE state in an inode's io_tree
2/9 btrfs: add an early exit when searching for delalloc range for lseek/fiemap
3/9 btrfs: skip unnecessary delalloc searches during lseek/fiemap
4/9 btrfs: search for delalloc more efficiently during lseek/fiemap
5/9 btrfs: remove no longer used btrfs_next_extent_map()
6/9 btrfs: allow passing a cached state record to count_range_bits()
7/9 btrfs: update stale comment for count_range_bits()
8/9 btrfs: use cached state when looking for delalloc ranges with fiemap
9/9 btrfs: use cached state when looking for delalloc ranges with lseek
Reported-by: Wang Yugui <wangyugui@e16-tech.com>
Link: https://lore.kernel.org/linux-btrfs/20221106073028.71F9.409509F4@e16-tech.com/
Link: https://lore.kernel.org/linux-btrfs/CAL3q7H5NSVicm7nYBJ7x8fFkDpno8z3PYt5aPU43Bajc1H0h1Q@mail.gmail.com/
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
An inode's io_tree can be quite large and there are cases where due to
delalloc it can have thousands of extent state records, which makes the
red black tree have a depth of 10 or more, making the operation of
count_range_bits() slow if we repeatedly call it for a range that starts
where, or after, the previous one we called it for. Such use cases are
when searching for delalloc in a file range that corresponds to a hole or
a prealloc extent, which is done during lseek SEEK_HOLE/DATA and fiemap.
So introduce a cached state parameter to count_range_bits() which we use
to store the last extent state record we visited, and then allow the
caller to pass it again on its next call to count_range_bits(). The next
patches in the series will make fiemap and lseek use the new parameter.
This change is part of a patchset that has the goal to make performance
better for applications that use lseek's SEEK_HOLE and SEEK_DATA modes to
iterate over the extents of a file. Two examples are the cp program from
coreutils 9.0+ and the tar program (when using its --sparse / -S option).
A sample test and results are listed in the changelog of the last patch
in the series:
1/9 btrfs: remove leftover setting of EXTENT_UPTODATE state in an inode's io_tree
2/9 btrfs: add an early exit when searching for delalloc range for lseek/fiemap
3/9 btrfs: skip unnecessary delalloc searches during lseek/fiemap
4/9 btrfs: search for delalloc more efficiently during lseek/fiemap
5/9 btrfs: remove no longer used btrfs_next_extent_map()
6/9 btrfs: allow passing a cached state record to count_range_bits()
7/9 btrfs: update stale comment for count_range_bits()
8/9 btrfs: use cached state when looking for delalloc ranges with fiemap
9/9 btrfs: use cached state when looking for delalloc ranges with lseek
Reported-by: Wang Yugui <wangyugui@e16-tech.com>
Link: https://lore.kernel.org/linux-btrfs/20221106073028.71F9.409509F4@e16-tech.com/
Link: https://lore.kernel.org/linux-btrfs/CAL3q7H5NSVicm7nYBJ7x8fFkDpno8z3PYt5aPU43Bajc1H0h1Q@mail.gmail.com/
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
During lseek (SEEK_HOLE/DATA) and fiemap, when processing a file range
that corresponds to a hole or a prealloc extent, we have to check if
there's any delalloc in the range. We do it by searching for delalloc
ranges in the inode's io_tree (for unflushed delalloc) and in the inode's
extent map tree (for delalloc that is flushing).
We avoid searching the extent map tree if the number of outstanding
extents is 0, as in that case we can't have extent maps for our search
range in the tree that correspond to delalloc that is flushing. However
if we have any unflushed delalloc, due to buffered writes or mmap writes,
then the outstanding extents counter is not 0 and we'll search the extent
map tree. The tree may be large because it can have lots of extent maps
that were loaded by reads or created by previous writes, therefore taking
a significant time to search the tree, specially if have a file with a
lot of holes and/or prealloc extents.
We can improve on this by instead of searching the extent map tree,
searching the ordered extents tree of the inode, since when delalloc is
flushing we create an ordered extent along with the new extent map, while
holding the respective file range locked in the inode's io_tree. The
ordered extents tree is typically much smaller, since ordered extents have
a short life and get removed from the tree once they are completed, while
extent maps can stay for a very long time in the extent map tree, either
created by previous writes or loaded by read operations.
So use the ordered extents tree instead of the extent maps tree.
This change is part of a patchset that has the goal to make performance
better for applications that use lseek's SEEK_HOLE and SEEK_DATA modes to
iterate over the extents of a file. Two examples are the cp program from
coreutils 9.0+ and the tar program (when using its --sparse / -S option).
A sample test and results are listed in the changelog of the last patch
in the series:
1/9 btrfs: remove leftover setting of EXTENT_UPTODATE state in an inode's io_tree
2/9 btrfs: add an early exit when searching for delalloc range for lseek/fiemap
3/9 btrfs: skip unnecessary delalloc searches during lseek/fiemap
4/9 btrfs: search for delalloc more efficiently during lseek/fiemap
5/9 btrfs: remove no longer used btrfs_next_extent_map()
6/9 btrfs: allow passing a cached state record to count_range_bits()
7/9 btrfs: update stale comment for count_range_bits()
8/9 btrfs: use cached state when looking for delalloc ranges with fiemap
9/9 btrfs: use cached state when looking for delalloc ranges with lseek
Reported-by: Wang Yugui <wangyugui@e16-tech.com>
Link: https://lore.kernel.org/linux-btrfs/20221106073028.71F9.409509F4@e16-tech.com/
Link: https://lore.kernel.org/linux-btrfs/CAL3q7H5NSVicm7nYBJ7x8fFkDpno8z3PYt5aPU43Bajc1H0h1Q@mail.gmail.com/
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
During lseek (SEEK_HOLE/DATA) and fiemap, when processing a file range
that corresponds to a hole or a prealloc extent, if we find that there is
no delalloc marked in the inode's io_tree but there is delalloc due to
an extent map in the io tree, then on the next iteration that calls
find_delalloc_subrange() we can skip searching the io tree again, since
on the first call we had no delalloc in the io tree for the whole range.
This change is part of a patchset that has the goal to make performance
better for applications that use lseek's SEEK_HOLE and SEEK_DATA modes to
iterate over the extents of a file. Two examples are the cp program from
coreutils 9.0+ and the tar program (when using its --sparse / -S option).
A sample test and results are listed in the changelog of the last patch
in the series:
1/9 btrfs: remove leftover setting of EXTENT_UPTODATE state in an inode's io_tree
2/9 btrfs: add an early exit when searching for delalloc range for lseek/fiemap
3/9 btrfs: skip unnecessary delalloc searches during lseek/fiemap
4/9 btrfs: search for delalloc more efficiently during lseek/fiemap
5/9 btrfs: remove no longer used btrfs_next_extent_map()
6/9 btrfs: allow passing a cached state record to count_range_bits()
7/9 btrfs: update stale comment for count_range_bits()
8/9 btrfs: use cached state when looking for delalloc ranges with fiemap
9/9 btrfs: use cached state when looking for delalloc ranges with lseek
Reported-by: Wang Yugui <wangyugui@e16-tech.com>
Link: https://lore.kernel.org/linux-btrfs/20221106073028.71F9.409509F4@e16-tech.com/
Link: https://lore.kernel.org/linux-btrfs/CAL3q7H5NSVicm7nYBJ7x8fFkDpno8z3PYt5aPU43Bajc1H0h1Q@mail.gmail.com/
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
During fiemap and lseek (SEEK_HOLE/DATA), when looking for delalloc in a
range corresponding to a hole or a prealloc extent, if we found the whole
range marked as delalloc in the inode's io_tree, then we can terminate
immediately and avoid searching the extent map tree. If not, and if the
found delalloc starts at the same offset of our search start but ends
before our search range's end, then we can adjust the search range for
the search in the extent map tree. So implement those changes.
This change is part of a patchset that has the goal to make performance
better for applications that use lseek's SEEK_HOLE and SEEK_DATA modes to
iterate over the extents of a file. Two examples are the cp program from
coreutils 9.0+ and the tar program (when using its --sparse / -S option).
A sample test and results are listed in the changelog of the last patch
in the series:
1/9 btrfs: remove leftover setting of EXTENT_UPTODATE state in an inode's io_tree
2/9 btrfs: add an early exit when searching for delalloc range for lseek/fiemap
3/9 btrfs: skip unnecessary delalloc searches during lseek/fiemap
4/9 btrfs: search for delalloc more efficiently during lseek/fiemap
5/9 btrfs: remove no longer used btrfs_next_extent_map()
6/9 btrfs: allow passing a cached state record to count_range_bits()
7/9 btrfs: update stale comment for count_range_bits()
8/9 btrfs: use cached state when looking for delalloc ranges with fiemap
9/9 btrfs: use cached state when looking for delalloc ranges with lseek
Reported-by: Wang Yugui <wangyugui@e16-tech.com>
Link: https://lore.kernel.org/linux-btrfs/20221106073028.71F9.409509F4@e16-tech.com/
Link: https://lore.kernel.org/linux-btrfs/CAL3q7H5NSVicm7nYBJ7x8fFkDpno8z3PYt5aPU43Bajc1H0h1Q@mail.gmail.com/
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The function is for internal interfaces so we should use the
btrfs_inode.
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The function is for internal interfaces so we should use the
btrfs_inode.
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
If when doing a direct IO write we need to fallback to buffered IO, we
this comment at btrfs_direct_write() that says we can't directly fallback
to buffered IO if we have a NOWAIT iocb, because we have no support for
NOWAIT buffered writes. That is not true anymore, as support for NOWAIT
buffered writes was added recently in commit 926078b21d ("btrfs: enable
nowait async buffered writes").
However we still can't fallback to a buffered write in case we have a
NOWAIT iocb, because we'll need to flush delalloc and wait for it to
complete after doing the buffered write, and that can block for several
reasons, the main reason being waiting for IO to complete.
So update the comment to mention all that.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This will make syncing fs.h to user space a little easier if we can pull
the super block specific helpers out of fs.h and put them in super.h.
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Move these out of ctree.h into file.h to cut down on code in ctree.h.
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Move these out of ctree.h into ioctl.h to cut down on code in ctree.h.
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Move these prototypes out of ctree.h and into file-item.h.
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This currently exists in file.c, move it to the more natural location in
defrag.c.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
[ reformat comments ]
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Move all the extent tree related prototypes to extent-tree.h out of
ctree.h, and then go include it everywhere needed so everything
compiles.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This is a large patch, but because they're all macros it's impossible to
split up. Simply copy all of the item accessors in ctree.h and paste
them in accessors.h, and then update any files to include the header so
everything compiles.
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ reformat comments, style fixups ]
Signed-off-by: David Sterba <dsterba@suse.com>
We have several fs wide related helpers in ctree.h. The bulk of these
are the incompat flag test helpers, but there are things such as
btrfs_fs_closing() and the read only helpers that also aren't directly
related to the ctree code. Move these into a fs.h header, which will
serve as the location for file system wide related helpers.
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
During fiemap and lseek (hole and data seeking), there's no point in
iterating the inode's io tree to count delalloc bits if the inode's
delalloc bytes counter has a value of zero, as that counter is updated
whenever we set a range for delalloc or clear a range from delalloc.
So skip the counting and io tree iteration if the inode's delalloc bytes
counter has a value of zero. This helps save time when processing a file
range corresponding to a hole or prealloc (unwritten) extent.
This patch is part of a series comprised of the following patches:
btrfs: get the next extent map during fiemap/lseek more efficiently
btrfs: skip unnecessary extent map searches during fiemap and lseek
btrfs: skip unnecessary delalloc search during fiemap and lseek
The following test was performed on a release kernel (Debian's default
kernel config) before and after applying those 3 patches.
# Wrapper to call fiemap in extent count only mode.
# (struct fiemap::fm_extent_count set to 0)
$ cat fiemap.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <errno.h>
#include <string.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
int main(int argc, char **argv)
{
struct fiemap fiemap = { 0 };
int fd;
if (argc != 2) {
printf("usage: %s <path>\n", argv[0]);
return 1;
}
fd = open(argv[1], O_RDONLY);
if (fd < 0) {
fprintf(stderr, "error opening file: %s\n",
strerror(errno));
return 1;
}
/* fiemap.fm_extent_count set to 0, to count extents only. */
fiemap.fm_length = FIEMAP_MAX_OFFSET;
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
fprintf(stderr, "fiemap error: %s\n",
strerror(errno));
return 1;
}
close(fd);
printf("fm_mapped_extents = %d\n", fiemap.fm_mapped_extents);
return 0;
}
$ gcc -o fiemap fiemap.c
And the wrapper shell script that creates a file with many holes and runs
fiemap against it:
$ cat test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount $DEV $MNT
FILE_SIZE=$((1 * 1024 * 1024 * 1024))
echo -n > $MNT/foobar
for ((off = 0; off < $FILE_SIZE; off += 8192)); do
xfs_io -c "pwrite -S 0xab $off 4K" $MNT/foobar > /dev/null
done
# flush all delalloc
sync
start=$(date +%s%N)
./fiemap $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds"
umount $MNT
Result before applying patchset:
fm_mapped_extents = 131072
fiemap took 63 milliseconds
Result after applying patchset:
fm_mapped_extents = 131072
fiemap took 39 milliseconds (-38.1%)
Running the same test for a 512M file instead of a 1G file, gave the
following results.
Result before applying patchset:
fm_mapped_extents = 65536
fiemap took 29 milliseconds
Result after applying patchset:
fm_mapped_extents = 65536
fiemap took 20 milliseconds (-31.0%)
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
If we have no outstanding extents it means we don't have any extent maps
corresponding to delalloc that is flushing, as when an ordered extent is
created we increment the number of outstanding extents to 1 and when we
remove the ordered extent we decrement them by 1. So skip extent map tree
searches if the number of outstanding ordered extents is 0, saving time as
the tree is not empty if we have previously made some reads or flushed
delalloc, as in those cases it can have a very large number of extent maps
for files with many extents.
This helps save time when processing a file range corresponding to a hole
or prealloc (unwritten) extent.
The next patch in the series has a performance test in its changelog and
its subject is:
"btrfs: skip unnecessary delalloc search during fiemap and lseek"
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
At find_delalloc_subrange(), when we need to get the next extent map, we
do a full search on the extent map tree (a red black tree). This is fine
but it's a lot more efficient to simply use rb_next(), which typically
requires iterating over less nodes of the tree and never needs to compare
the ranges of nodes with the one we are looking for.
So add a public helper to extent_map.{h,c} to get the extent map that
immediately follows another extent map, using rb_next(), and use that
helper at find_delalloc_subrange().
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Now that try_lock_extent() takes a cached_state, plumb the cached_state
through btrfs_try_lock_ordered_range() and then use a cached_state in
btrfs_check_nocow_lock everywhere to avoid extra tree searches on the
extent_io_tree.
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
With nowait becoming more pervasive throughout our codebase go ahead and
add a cached_state to try_lock_extent(). This allows us to be faster
about clearing the locked area if we have contention, and then gives us
the same optimization for unlock if we are able to lock the range.
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
During a nowait buffered write, if we fail to balance dirty pages we exit
btrfs_buffered_write() without releasing the delalloc space reserved for
an extent, resulting in leaking space from the inode's block reserve.
So fix that by releasing the delalloc space for the extent when balancing
dirty pages fails.
Reported-by: kernel test robot <yujie.liu@intel.com>
Link: https://lore.kernel.org/all/202210111304.d369bc32-yujie.liu@intel.com
Fixes: 965f47aeb5 ("btrfs: make btrfs_buffered_write nowait compatible")
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
If we are doing a buffered write in NOWAIT context and we can't reserve
metadata space due to -ENOSPC, then we should return -EAGAIN so that we
retry the write in a context allowed to block and do metadata reservation
with flushing, which might succeed this time due to the allowed flushing.
Returning -ENOSPC while in NOWAIT context simply makes some writes fail
with -ENOSPC when they would likely succeed after switching from NOWAIT
context to blocking context. That is unexpected behaviour and even fio
complains about it with a warning like this:
fio: io_u error on file /mnt/sdi/task_0.0.0: No space left on device: write offset=1535705088, buflen=65536
fio: pid=592630, err=28/file:io_u.c:1846, func=io_u error, error=No space left on device
The fio's job config is this:
[global]
bs=64K
ioengine=io_uring
iodepth=1
size=2236962133
nr_files=1
filesize=2236962133
direct=0
runtime=10
fallocate=posix
io_size=2236962133
group_reporting
time_based
[task_0]
rw=randwrite
directory=/mnt/sdi
numjobs=4
So fix this by returning -EAGAIN if we are in NOWAIT context and the
metadata reservation failed with -ENOSPC.
Fixes: 304e45acdb ("btrfs: plumb NOWAIT through the write path")
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When doing a direct IO write using a iocb with nowait and dsync set, we
end up not syncing the file once the write completes.
This is because we tell iomap to not call generic_write_sync(), which
would result in calling btrfs_sync_file(), in order to avoid a deadlock
since iomap can call it while we are holding the inode's lock and
btrfs_sync_file() needs to acquire the inode's lock. The deadlock happens
only if the write happens synchronously, when iomap_dio_rw() calls
iomap_dio_complete() before it returns. Instead we do the sync ourselves
at btrfs_do_write_iter().
For a nowait write however we can end up not doing the sync ourselves at
at btrfs_do_write_iter() because the write could have been queued, and
therefore we get -EIOCBQUEUED returned from iomap in such case. That makes
us skip the sync call at btrfs_do_write_iter(), as we don't do it for
any error returned from btrfs_direct_write(). We can't simply do the call
even if -EIOCBQUEUED is returned, since that would block the task waiting
for IO, both for the data since there are bios still in progress as well
as potentially blocking when joining a log transaction and when syncing
the log (writing log trees, super blocks, etc).
So let iomap do the sync call itself and in order to avoid deadlocks for
the case of synchronous writes (without nowait), use __iomap_dio_rw() and
have ourselves call iomap_dio_complete() after unlocking the inode.
A test case will later be sent for fstests, after this is fixed in Linus'
tree.
Fixes: 51bd9563b6 ("btrfs: fix deadlock due to page faults during direct IO reads and writes")
Reported-by: Марк Коренберг <socketpair@gmail.com>
Link: https://lore.kernel.org/linux-btrfs/CAEmTpZGRKbzc16fWPvxbr6AfFsQoLmz-Lcg-7OgJOZDboJ+SGQ@mail.gmail.com/
CC: stable@vger.kernel.org # 6.0+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We have several places that need to drop all the extent maps in a given
file range and then add a new extent map for that range. Currently they
call btrfs_drop_extent_map_range() to delete all extent maps in the range
and then keep trying to add the new extent map in a loop that keeps
retrying while the insertion of the new extent map fails with -EEXIST.
So instead of repeating this logic, add a helper to extent_map.c that
does these steps and name it btrfs_replace_extent_map_range(). Also add
a comment about why the retry loop is necessary.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The function btrfs_drop_extent_cache() doesn't really belong at file.c
because what it does is drop a range of extent maps for a file range.
It directly allocates and manipulates extent maps, by dropping,
splitting and replacing them in an extent map tree, so it should be
located at extent_map.c, where all manipulations of an extent map tree
and its extent maps are supposed to be done.
So move it out of file.c and into extent_map.c. Additionally do the
following changes:
1) Rename it into btrfs_drop_extent_map_range(), as this makes it more
clear about what it does. The term "cache" is a bit confusing as it's
not widely used, "extent maps" or "extent mapping" is much more common;
2) Change its 'skip_pinned' argument from int to bool;
3) Turn several of its local variables from int to bool, since they are
used as booleans;
4) Move the declaration of some variables out of the function's main
scope and into the scopes where they are used;
5) Remove pointless assignment of false to 'modified' early in the while
loop, as later that variable is set and it's not used before that
second assignment;
6) Remove checks for NULL before calling free_extent_map().
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When dropping extent maps for a range, through btrfs_drop_extent_cache(),
if we find an extent map that starts before our target range and/or ends
before the target range, and we are not able to allocate extent maps for
splitting that extent map, then we don't fail and simply remove the entire
extent map from the inode's extent map tree.
This is generally fine, because in case anyone needs to access the extent
map, it can just load it again later from the respective file extent
item(s) in the subvolume btree. However, if that extent map is new and is
in the list of modified extents, then a fast fsync will miss the parts of
the extent that were outside our range (that needed to be split),
therefore not logging them. Fix that by marking the inode for a full
fsync. This issue was introduced after removing BUG_ON()s triggered when
the split extent map allocations failed, done by commit 7014cdb493
("Btrfs: btrfs_drop_extent_cache should never fail"), back in 2012, and
the fast fsync path already existed but was very recent.
Also, in the case where we could allocate extent maps for the split
operations but then fail to add a split extent map to the tree, mark the
inode for a full fsync as well. This is not supposed to ever fail, and we
assert that, but in case assertions are disabled (CONFIG_BTRFS_ASSERT is
not set), it's the correct thing to do to make sure a fast fsync will not
miss a new extent.
CC: stable@vger.kernel.org # 5.15+
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Enable nowait async buffered writes in btrfs_do_write_iter() and
btrfs_file_open().
In this version encoded buffered writes have the optimization not
enabled. Encoded writes are enabled by using an ioctl. io_uring
currently does not support ioctls. This might be enabled in the future.
Performance results:
For fio the following results have been obtained with a queue depth of
1 and 4k block size (runtime 600 secs):
sequential writes:
without patch with patch libaio psync
iops: 55k 134k 117K 148K
bw: 221MB/s 538MB/s 469MB/s 592MB/s
clat: 15286ns 82ns 994ns 6340ns
For an io depth of 1, the new patch improves throughput by over two
times (compared to the existing behavior, where buffered writes are
processed by an io-worker process) and also the latency is considerably
reduced. To achieve the same or better performance with the existing
code an io depth of 4 is required. Increasing the iodepth further does
not lead to improvements.
The tests have been run like this:
./fio --name=seq-writers --ioengine=psync --iodepth=1 --rw=write \
--bs=4k --direct=0 --size=100000m --time_based --runtime=600 \
--numjobs=1 --filename=...
./fio --name=seq-writers --ioengine=io_uring --iodepth=1 --rw=write \
--bs=4k --direct=0 --size=100000m --time_based --runtime=600 \
--numjobs=1 --filename=...
./fio --name=seq-writers --ioengine=libaio --iodepth=1 --rw=write \
--bs=4k --direct=0 --size=100000m --time_based --runtime=600 \
--numjobs=1 --filename=...
Testing:
This patch has been tested with xfstests, fsx, fio. xfstests shows no new
diffs compared to running without the patch series.
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Stefan Roesch <shr@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We need to avoid unconditionally calling balance_dirty_pages_ratelimited
as it could wait for some reason. Use balance_dirty_pages_ratelimited_flags
with the BDP_ASYNC in case the buffered write is nowait, returning
EAGAIN eventually.
It also moves the function after the again label. This can cause the
function to be called a bit later, but this should have no impact in the
real world.
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Stefan Roesch <shr@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We have everywhere setup for nowait, plumb NOWAIT through the write path.
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Stefan Roesch <shr@fb.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Add the nowait parameter to lock_and_cleanup_extent_if_need(). If the
nowait parameter is specified we try to lock the extent in nowait mode.
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Stefan Roesch <shr@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Add nowait parameter to the prepare_pages function. In case nowait is
specified for an async buffered write request, do a nowait allocation or
return -EAGAIN.
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Stefan Roesch <shr@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Now all the helpers that btrfs_check_nocow_lock uses handle nowait, add
a nowait flag to btrfs_check_nocow_lock so it can be used by the write
path.
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Stefan Roesch <shr@fb.com>
Signed-off-by: David Sterba <dsterba@suse.com>
In order to accommodate NOWAIT IOCB's we need to be able to do NO_FLUSH
data reservations, so plumb this through the delalloc reservation
system.
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Stefan Roesch <shr@fb.com>
Signed-off-by: David Sterba <dsterba@suse.com>
If we have NOWAIT specified on our IOCB and we're writing into a
PREALLOC or NOCOW extent then we need to be able to tell
can_nocow_extent that we don't want to wait on any locks or metadata IO.
Fix can_nocow_extent to allow for NOWAIT.
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Stefan Roesch <shr@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This is defined in btrfs_inode.h, and dereferences btrfs_root and
btrfs_fs_info, both of which aren't defined in btrfs_inode.h.
Additionally, in many places we already have root or fs_info, so this
helper often makes the code harder to read. So delete the helper and
simply open code it in the few places that we use it.
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Instead of taking up a whole argument to indicate we're clearing
everything in a range, simply add another EXTENT bit to control this,
and then update all the callers to drop this argument from the
clear_extent_bit variants.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We have two variants of lock/unlock extent, one set that takes a cached
state, another that does not. This is slightly annoying, and generally
speaking there are only a few places where we don't have a cached state.
Simplify this by making lock_extent/unlock_extent the only variant and
make it take a cached state, then convert all the callers appropriately.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This is only used in the case that we are clearing EXTENT_LOCKED, so
infer this value from the bits passed in instead of taking it as an
argument.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The current fiemap implementation does not scale very well with the number
of extents a file has. This is both because the main algorithm to find out
the extents has a high algorithmic complexity and because for each extent
we have to check if it's shared. This second part, checking if an extent
is shared, is significantly improved by the two previous patches in this
patchset, while the first part is improved by this specific patch. Every
now and then we get reports from users mentioning fiemap is too slow or
even unusable for files with a very large number of extents, such as the
two recent reports referred to by the Link tags at the bottom of this
change log.
To understand why the part of finding which extents a file has is very
inefficient, consider the example of doing a full ranged fiemap against
a file that has over 100K extents (normal for example for a file with
more than 10G of data and using compression, which limits the extent size
to 128K). When we enter fiemap at extent_fiemap(), the following happens:
1) Before entering the main loop, we call get_extent_skip_holes() to get
the first extent map. This leads us to btrfs_get_extent_fiemap(), which
in turn calls btrfs_get_extent(), to find the first extent map that
covers the file range [0, LLONG_MAX).
btrfs_get_extent() will first search the inode's extent map tree, to
see if we have an extent map there that covers the range. If it does
not find one, then it will search the inode's subvolume b+tree for a
fitting file extent item. After finding the file extent item, it will
allocate an extent map, fill it in with information extracted from the
file extent item, and add it to the inode's extent map tree (which
requires a search for insertion in the tree).
2) Then we enter the main loop at extent_fiemap(), emit the details of
the extent, and call again get_extent_skip_holes(), with a start
offset matching the end of the extent map we previously processed.
We end up at btrfs_get_extent() again, will search the extent map tree
and then search the subvolume b+tree for a file extent item if we could
not find an extent map in the extent tree. We allocate an extent map,
fill it in with the details in the file extent item, and then insert
it into the extent map tree (yet another search in this tree).
3) The second step is repeated over and over, until we have processed the
whole file range. Each iteration ends at btrfs_get_extent(), which
does a red black tree search on the extent map tree, then searches the
subvolume b+tree, allocates an extent map and then does another search
in the extent map tree in order to insert the extent map.
In the best scenario we have all the extent maps already in the extent
tree, and so for each extent we do a single search on a red black tree,
so we have a complexity of O(n log n).
In the worst scenario we don't have any extent map already loaded in
the extent map tree, or have very few already there. In this case the
complexity is much higher since we do:
- A red black tree search on the extent map tree, which has O(log n)
complexity, initially very fast since the tree is empty or very
small, but as we end up allocating extent maps and adding them to
the tree when we don't find them there, each subsequent search on
the tree gets slower, since it's getting bigger and bigger after
each iteration.
- A search on the subvolume b+tree, also O(log n) complexity, but it
has items for all inodes in the subvolume, not just items for our
inode. Plus on a filesystem with concurrent operations on other
inodes, we can block doing the search due to lock contention on
b+tree nodes/leaves.
- Allocate an extent map - this can block, and can also fail if we
are under serious memory pressure.
- Do another search on the extent maps red black tree, with the goal
of inserting the extent map we just allocated. Again, after every
iteration this tree is getting bigger by 1 element, so after many
iterations the searches are slower and slower.
- We will not need the allocated extent map anymore, so it's pointless
to add it to the extent map tree. It's just wasting time and memory.
In short we end up searching the extent map tree multiple times, on a
tree that is growing bigger and bigger after each iteration. And
besides that we visit the same leaf of the subvolume b+tree many times,
since a leaf with the default size of 16K can easily have more than 200
file extent items.
This is very inefficient overall. This patch changes the algorithm to
instead iterate over the subvolume b+tree, visiting each leaf only once,
and only searching in the extent map tree for file ranges that have holes
or prealloc extents, in order to figure out if we have delalloc there.
It will never allocate an extent map and add it to the extent map tree.
This is very similar to what was previously done for the lseek's hole and
data seeking features.
Also, the current implementation relying on extent maps for figuring out
which extents we have is not correct. This is because extent maps can be
merged even if they represent different extents - we do this to minimize
memory utilization and keep extent map trees smaller. For example if we
have two extents that are contiguous on disk, once we load the two extent
maps, they get merged into a single one - however if only one of the
extents is shared, we end up reporting both as shared or both as not
shared, which is incorrect.
This reproducer triggers that bug:
$ cat fiemap-bug.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f $DEV
mount $DEV $MNT
# Create a file with two 256K extents.
# Since there is no other write activity, they will be contiguous,
# and their extent maps merged, despite having two distinct extents.
xfs_io -f -c "pwrite -S 0xab 0 256K" \
-c "fsync" \
-c "pwrite -S 0xcd 256K 256K" \
-c "fsync" \
$MNT/foo
# Now clone only the second extent into another file.
xfs_io -f -c "reflink $MNT/foo 256K 0 256K" $MNT/bar
# Filefrag will report a single 512K extent, and say it's not shared.
echo
filefrag -v $MNT/foo
umount $MNT
Running the reproducer:
$ ./fiemap-bug.sh
wrote 262144/262144 bytes at offset 0
256 KiB, 64 ops; 0.0038 sec (65.479 MiB/sec and 16762.7030 ops/sec)
wrote 262144/262144 bytes at offset 262144
256 KiB, 64 ops; 0.0040 sec (61.125 MiB/sec and 15647.9218 ops/sec)
linked 262144/262144 bytes at offset 0
256 KiB, 1 ops; 0.0002 sec (1.034 GiB/sec and 4237.2881 ops/sec)
Filesystem type is: 9123683e
File size of /mnt/sdj/foo is 524288 (128 blocks of 4096 bytes)
ext: logical_offset: physical_offset: length: expected: flags:
0: 0.. 127: 3328.. 3455: 128: last,eof
/mnt/sdj/foo: 1 extent found
We end up reporting that we have a single 512K that is not shared, however
we have two 256K extents, and the second one is shared. Changing the
reproducer to clone instead the first extent into file 'bar', makes us
report a single 512K extent that is shared, which is algo incorrect since
we have two 256K extents and only the first one is shared.
This patch is part of a larger patchset that is comprised of the following
patches:
btrfs: allow hole and data seeking to be interruptible
btrfs: make hole and data seeking a lot more efficient
btrfs: remove check for impossible block start for an extent map at fiemap
btrfs: remove zero length check when entering fiemap
btrfs: properly flush delalloc when entering fiemap
btrfs: allow fiemap to be interruptible
btrfs: rename btrfs_check_shared() to a more descriptive name
btrfs: speedup checking for extent sharedness during fiemap
btrfs: skip unnecessary extent buffer sharedness checks during fiemap
btrfs: make fiemap more efficient and accurate reporting extent sharedness
The patchset was tested on a machine running a non-debug kernel (Debian's
default config) and compared the tests below on a branch without the
patchset versus the same branch with the whole patchset applied.
The following test for a large compressed file without holes:
$ cat fiemap-perf-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 40G gives 327680 128K file extents (due to compression).
xfs_io -f -c "pwrite -S 0xab -b 1M 0 20G" $MNT/foobar
umount $MNT
mount -o compress=lzo $DEV $MNT
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata not cached)"
start=$(date +%s%N)
filefrag $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "fiemap took $dur milliseconds (metadata cached)"
umount $MNT
Before patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 3597 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 2107 milliseconds (metadata cached)
After patchset:
$ ./fiemap-perf-test.sh
(...)
/mnt/sdi/foobar: 327680 extents found
fiemap took 1214 milliseconds (metadata not cached)
/mnt/sdi/foobar: 327680 extents found
fiemap took 684 milliseconds (metadata cached)
That's a speedup of about 3x for both cases (no metadata cached and all
metadata cached).
The test provided by Pavel (first Link tag at the bottom), which uses
files with a large number of holes, was also used to measure the gains,
and it consists on a small C program and a shell script to invoke it.
The C program is the following:
$ cat pavels-test.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/ioctl.h>
#include <linux/fs.h>
#include <linux/fiemap.h>
#define FILE_INTERVAL (1<<13) /* 8Kb */
long long interval(struct timeval t1, struct timeval t2)
{
long long val = 0;
val += (t2.tv_usec - t1.tv_usec);
val += (t2.tv_sec - t1.tv_sec) * 1000 * 1000;
return val;
}
int main(int argc, char **argv)
{
struct fiemap fiemap = {};
struct timeval t1, t2;
char data = 'a';
struct stat st;
int fd, off, file_size = FILE_INTERVAL;
if (argc != 3 && argc != 2) {
printf("usage: %s <path> [size]\n", argv[0]);
return 1;
}
if (argc == 3)
file_size = atoi(argv[2]);
if (file_size < FILE_INTERVAL)
file_size = FILE_INTERVAL;
file_size -= file_size % FILE_INTERVAL;
fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0644);
if (fd < 0) {
perror("open");
return 1;
}
for (off = 0; off < file_size; off += FILE_INTERVAL) {
if (pwrite(fd, &data, 1, off) != 1) {
perror("pwrite");
close(fd);
return 1;
}
}
if (ftruncate(fd, file_size)) {
perror("ftruncate");
close(fd);
return 1;
}
if (fstat(fd, &st) < 0) {
perror("fstat");
close(fd);
return 1;
}
printf("size: %ld\n", st.st_size);
printf("actual size: %ld\n", st.st_blocks * 512);
fiemap.fm_length = FIEMAP_MAX_OFFSET;
gettimeofday(&t1, NULL);
if (ioctl(fd, FS_IOC_FIEMAP, &fiemap) < 0) {
perror("fiemap");
close(fd);
return 1;
}
gettimeofday(&t2, NULL);
printf("fiemap: fm_mapped_extents = %d\n",
fiemap.fm_mapped_extents);
printf("time = %lld us\n", interval(t1, t2));
close(fd);
return 0;
}
$ gcc -o pavels_test pavels_test.c
And the wrapper shell script:
$ cat fiemap-pavels-test.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f -O no-holes $DEV
mount $DEV $MNT
echo
echo "*********** 256M ***********"
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
./pavels-test $MNT/testfile $((1 << 28))
echo
echo "*********** 512M ***********"
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
./pavels-test $MNT/testfile $((1 << 29))
echo
echo "*********** 1G ***********"
echo
./pavels-test $MNT/testfile $((1 << 30))
echo
./pavels-test $MNT/testfile $((1 << 30))
umount $MNT
Running his reproducer before applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4003133 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 4895330 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 30123675 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 33450934 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 224924074 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 217239242 us
Running it after applying the patchset:
*********** 256M ***********
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29475 us
size: 268435456
actual size: 134217728
fiemap: fm_mapped_extents = 32768
time = 29307 us
*********** 512M ***********
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 58996 us
size: 536870912
actual size: 268435456
fiemap: fm_mapped_extents = 65536
time = 59115 us
*********** 1G ***********
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 116251
time = 124141 us
size: 1073741824
actual size: 536870912
fiemap: fm_mapped_extents = 131072
time = 119387 us
The speedup is massive, both on the first fiemap call and on the second
one as well, as his test creates files with many holes and small extents
(every extent follows a hole and precedes another hole).
For the 256M file we go from 4 seconds down to 29 milliseconds in the
first run, and then from 4.9 seconds down to 29 milliseconds again in the
second run, a speedup of 138x and 169x, respectively.
For the 512M file we go from 30.1 seconds down to 59 milliseconds in the
first run, and then from 33.5 seconds down to 59 milliseconds again in the
second run, a speedup of 510x and 568x, respectively.
For the 1G file, we go from 225 seconds down to 124 milliseconds in the
first run, and then from 217 seconds down to 119 milliseconds in the
second run, a speedup of 1815x and 1824x, respectively.
Reported-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Link: https://lore.kernel.org/linux-btrfs/21dd32c6-f1f9-f44a-466a-e18fdc6788a7@virtuozzo.com/
Reported-by: Dominique MARTINET <dominique.martinet@atmark-techno.com>
Link: https://lore.kernel.org/linux-btrfs/Ysace25wh5BbLd5f@atmark-techno.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The current implementation of hole and data seeking for llseek does not
scale well in regards to the number of extents and the distance between
the start offset and the next hole or extent. This is due to a very high
algorithmic complexity. Often we also get reports of btrfs' hole and data
seeking (llseek) being too slow, such as at 2017's LSFMM (see the Link
tag at the bottom).
In order to better understand it, lets consider the case where the start
offset is 0, we are seeking for a hole and the file size is 16G. Between
file offset 0 and the first hole in the file there are 100K extents - this
is common for large files, specially if we have compression enabled, since
the maximum extent size is limited to 128K. The steps take by the main
loop of the current algorithm are the following:
1) We start by calling btrfs_get_extent_fiemap(), for file offset 0, which
calls btrfs_get_extent(). This will first lookup for an extent map in
the inode's extent map tree (a red black tree). If the extent map is
not loaded in memory, then it will do a lookup for the corresponding
file extent item in the subvolume's b+tree, create an extent map based
on the contents of the file extent item and then add the extent map to
the extent map tree of the inode;
2) The second iteration calls btrfs_get_extent_fiemap() again, this time
with a start offset matching the end offset of the previous extent.
Again, btrfs_get_extent() will first search the extent map tree, and
if it doesn't find an extent map there, it will again search in the
b+tree of the subvolume for a matching file extent item, build an
extent map based on the file extent item, and add the extent map to
to the extent map tree of the inode;
3) This repeats over and over until we find the first hole (when seeking
for holes) or until we find the first extent (when seeking for data).
If there no extent maps loaded in memory for each iteration, then on
each iteration we do 1 extent map tree search, 1 b+tree search, plus
1 more extent map tree traversal to insert an extent map - plus we
allocate memory for the extent map.
On each iteration we are growing the size of the extent map tree,
making each future search slower, and also visiting the same b+tree
leaves over and over again - taking into account with the default leaf
size of 16K we can fit more than 200 file extent items in a leaf - so
we can visit the same b+tree leaf 200+ times, on each visit walking
down a path from the root to the leaf.
So it's easy to see that what we have now doesn't scale well. Also, it
loads an extent map for every file extent item into memory, which is not
efficient - we should add extents maps only when doing IO (writing or
reading file data).
This change implements a new algorithm which scales much better, and
works like this:
1) We iterate over the subvolume's b+tree, visiting each leaf that has
file extent items once and only once;
2) For any file extent items found, that don't represent holes or prealloc
extents, it will not search the extent map tree - there's no need at
all for that - an extent map is just an in-memory representation of a
file extent item;
3) When a hole is found, or a prealloc extent, it will check if there's
delalloc for its range. For this it will search for EXTENT_DELALLOC
bits in the inode's io tree and check the extent map tree - this is
for accounting for unflushed delalloc and for flushed delalloc (the
period between running delalloc and ordered extent completion),
respectively. This is similar to what the current implementation does
when it finds a hole or prealloc extent, but without creating extent
maps and adding them to the extent map tree in case they are not
loaded in memory;
4) It never allocates extent maps, or adds extent maps to the inode's
extent map tree. This not only saves memory and time (from the tree
insertions and allocations), but also eliminates the possibility of
-ENOMEM due to allocating too many extent maps.
Part of this new code will also be used later for fiemap (which also
suffers similar scalability problems).
The following test example can be used to quickly measure the efficiency
before and after this patch:
$ cat test-seek-hole.sh
#!/bin/bash
DEV=/dev/sdi
MNT=/mnt/sdi
mkfs.btrfs -f $DEV
mount -o compress=lzo $DEV $MNT
# 16G file -> 131073 compressed extents.
xfs_io -f -c "pwrite -S 0xab -b 1M 0 16G" $MNT/foobar
# Leave a 1M hole at file offset 15G.
xfs_io -c "fpunch 15G 1M" $MNT/foobar
# Unmount and mount again, so that we can test when there's no
# metadata cached in memory.
umount $MNT
mount -o compress=lzo $DEV $MNT
# Test seeking for hole from offset 0 (hole is at offset 15G).
start=$(date +%s%N)
xfs_io -c "seek -h 0" $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "Took $dur milliseconds to seek first hole (metadata not cached)"
echo
start=$(date +%s%N)
xfs_io -c "seek -h 0" $MNT/foobar
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "Took $dur milliseconds to seek first hole (metadata cached)"
echo
umount $MNT
Before this change:
$ ./test-seek-hole.sh
(...)
Whence Result
HOLE 16106127360
Took 176 milliseconds to seek first hole (metadata not cached)
Whence Result
HOLE 16106127360
Took 17 milliseconds to seek first hole (metadata cached)
After this change:
$ ./test-seek-hole.sh
(...)
Whence Result
HOLE 16106127360
Took 43 milliseconds to seek first hole (metadata not cached)
Whence Result
HOLE 16106127360
Took 13 milliseconds to seek first hole (metadata cached)
That's about 4x faster when no metadata is cached and about 30% faster
when all metadata is cached.
In practice the differences may often be significantly higher, either due
to a higher number of extents in a file or because the subvolume's b+tree
is much bigger than in this example, where we only have one file.
Link: https://lwn.net/Articles/718805/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Doing hole or data seeking on a file with a very large number of extents
can take a long time, and we have reports of it being too slow (such as
at LSFMM from 2017, see the Link below). So make it interruptible.
Link: https://lwn.net/Articles/718805/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When logging an inode, if we detect the inode has a reference that
conflicts with some other inode that got renamed, we log that other inode
while holding the log mutex of the current inode. We then find out if
there are other inodes that conflict with the first conflicting inode,
and log them while under the log mutex of the original inode. This is
fine because the recursion can only happen once.
For the upcoming work where we directly log delayed items without flushing
them first to the subvolume tree, this recursion adds a lot of complexity
and it's hard to keep lockdep happy about it.
So collect a list of conflicting inodes and then log the inodes after
unlocking the log mutex of the inode we started with.
Also limit the maximum number of conflict inodes we log to 10, to avoid
spending too much time logging (and maybe allocating too many list
elements too), as typically we don't have more than 1 or 2 conflicting
inodes - if we go over the limit, simply fallback to a transaction commit.
It is possible to have a very long list of conflicting inodes to be
intentionally created by a user if he/she creates a very long succession
of renames like this:
(...)
rename E to F
rename D to E
rename C to D
rename B to C
rename A to B
touch A (create a new file named A)
fsync A
If that happened for a sequence of hundreds or thousands of renames, it
could massively slow down the logging and cause other secondary effects
like for example blocking other fsync operations and transaction commits
for a very long time (assuming it wouldn't run into -ENOSPC or -ENOMEM
first). However such cases are very uncommon to happen in practice,
nevertheless it's better to be prepared for them and avoid chaos.
Such long sequence of conflicting inodes could be created before this
change.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
btrfs_insert_file_extent() is only ever used to insert holes, so rename
it and remove the redundant parameters.
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Omar Sandoval <osandov@osandov.com>
Signed-off-by: Sweet Tea Dorminy <sweettea-kernel@dorminy.me>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
With CONFIG_READ_ONLY_THP_FOR_FS, the Linux kernel supports using THPs for
read-only mmapped files, such as shared libraries. However, the kernel
makes no attempt to actually align those mappings on 2MB boundaries,
which makes it impossible to use those THPs most of the time. This issue
applies to general file mapping THP as well as existing setups using
CONFIG_READ_ONLY_THP_FOR_FS. This is easily fixed by using
thp_get_unmapped_area for the unmapped_area function in btrfs, which
is what ext2, ext4, fuse, and xfs all use.
Initially btrfs had been left out in commit 8c07fc452ac0 ("btrfs: fix
alignment of VMA for memory mapped files on THP") as btrfs does not support
DAX. However, commit 1854bc6e24 ("mm/readahead: Align file mappings
for non-DAX") removed the DAX requirement. We should now be able to call
thp_get_unmapped_area() for btrfs.
The problem can be seen in /proc/PID/smaps where THPeligible is set to 0
on mappings to eligible shared object files as shown below.
Before this patch:
7fc6a7e18000-7fc6a80cc000 r-xp 00000000 00:1e 199856
/usr/lib64/libcrypto.so.1.1.1k
Size: 2768 kB
THPeligible: 0
VmFlags: rd ex mr mw me
With this patch the library is mapped at a 2MB aligned address:
fbdfe200000-7fbdfe4b4000 r-xp 00000000 00:1e 199856
/usr/lib64/libcrypto.so.1.1.1k
Size: 2768 kB
THPeligible: 1
VmFlags: rd ex mr mw me
This fixes the alignment of VMAs for any mmap of a file that has the
rd and ex permissions and size >= 2MB. The VMA alignment and
THPeligible field for anonymous memory is handled separately and
is thus not effected by this change.
CC: stable@vger.kernel.org # 5.18+
Signed-off-by: Alexander Zhu <alexlzhu@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
-----BEGIN PGP SIGNATURE-----
iQIzBAABCgAdFiEE8rQSAMVO+zA4DBdWxWXV+ddtWDsFAmMLY9oACgkQxWXV+ddt
WDue/w/8C3ZF8nLAI/sMrUpef2vSD62bvkKRRS45wzR2uod6yc0Fle9upzBssJQZ
qO3mQ53+QV+imCq7dY5mmtmwCUJNmbV5gbiMoF1OoV9TYtpZb/NIDklSX8se2eJX
drdAWQr2pYwU2M4duA4IEW08TvQ2TFh0JiqMi0aYM5apyL80uv3WniOu+xpRipA3
CMFAnDqayIgQ5OIsedqNy2MBLBopodUL5PZv/H7/g6KSKIuAZP9zgg1eKPfaz2t3
HO183ubmMbVtxgxeu+EnvCkg/iQ5hQiuGmyi0FLYMs/A6/NglwBnIJU5jCMQhcp6
HO5+FSUn6lHQetVzt2uHb9Lo+gX4FtCaHqVv1bXT62lnmDsZO1D7RVSg1Fra+CY+
jJmi8vvIbfbYlSZPZlJANoWe8ODOMVPk+pM4SFHlxOWGAY6HViX2RfHnIjNj5x9O
iDSTGvH6++nBF1Wu2/Xja/VKZ1avxRyTu2srW8JOF62j/tTU/EoPJcO9rxXOBBmC
Hi4UmJ690p3h5xZeeiyE8CmaSlPtfdCcnc/97FnusEjBao9O7THX0PCDVJX6VBkm
hVk01Z6+az1UNcD18KecvCpKYF/At4WpjaUGgf7q+LBfJXuXA6jfzOVDJMKV3TFd
n1yMFg+duGj90l8gT0aa/VQiBlUlnzQKz6ceqyKkPccwveNis6I=
=p8YV
-----END PGP SIGNATURE-----
Merge tag 'for-6.0-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs fixes from David Sterba:
"Fixes:
- check that subvolume is writable when changing xattrs from security
namespace
- fix memory leak in device lookup helper
- update generation of hole file extent item when merging holes
- fix space cache corruption and potential double allocations; this
is a rare bug but can be serious once it happens, stable backports
and analysis tool will be provided
- fix error handling when deleting root references
- fix crash due to assert when attempting to cancel suspended device
replace, add message what to do if mount fails due to missing
replace item
Regressions:
- don't merge pages into bio if their page offset is not contiguous
- don't allow large NOWAIT direct reads, this could lead to short
reads eg. in io_uring"
* tag 'for-6.0-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
btrfs: add info when mount fails due to stale replace target
btrfs: replace: drop assert for suspended replace
btrfs: fix silent failure when deleting root reference
btrfs: fix space cache corruption and potential double allocations
btrfs: don't allow large NOWAIT direct reads
btrfs: don't merge pages into bio if their page offset is not contiguous
btrfs: update generation of hole file extent item when merging holes
btrfs: fix possible memory leak in btrfs_get_dev_args_from_path()
btrfs: check if root is readonly while setting security xattr
When punching a hole into a file range that is adjacent with a hole and we
are not using the no-holes feature, we expand the range of the adjacent
file extent item that represents a hole, to save metadata space.
However we don't update the generation of hole file extent item, which
means a full fsync will not log that file extent item if the fsync happens
in a later transaction (since commit 7f30c07288 ("btrfs: stop copying
old file extents when doing a full fsync")).
For example, if we do this:
$ mkfs.btrfs -f -O ^no-holes /dev/sdb
$ mount /dev/sdb /mnt
$ xfs_io -f -c "pwrite -S 0xab 2M 2M" /mnt/foobar
$ sync
We end up with 2 file extent items in our file:
1) One that represents the hole for the file range [0, 2M), with a
generation of 7;
2) Another one that represents an extent covering the range [2M, 4M).
After that if we do the following:
$ xfs_io -c "fpunch 2M 2M" /mnt/foobar
We end up with a single file extent item in the file, which represents a
hole for the range [0, 4M) and with a generation of 7 - because we end
dropping the data extent for range [2M, 4M) and then update the file
extent item that represented the hole at [0, 2M), by increasing
length from 2M to 4M.
Then doing a full fsync and power failing:
$ xfs_io -c "fsync" /mnt/foobar
<power failure>
will result in the full fsync not logging the file extent item that
represents the hole for the range [0, 4M), because its generation is 7,
which is lower than the generation of the current transaction (8).
As a consequence, after mounting again the filesystem (after log replay),
the region [2M, 4M) does not have a hole, it still points to the
previous data extent.
So fix this by always updating the generation of existing file extent
items representing holes when we merge/expand them. This solves the
problem and it's the same approach as when we merge prealloc extents that
got written (at btrfs_mark_extent_written()). Setting the generation to
the current transaction's generation is also what we do when merging
the new hole extent map with the previous one or the next one.
A test case for fstests, covering both cases of hole file extent item
merging (to the left and to the right), will be sent soon.
Fixes: 7f30c07288 ("btrfs: stop copying old file extents when doing a full fsync")
CC: stable@vger.kernel.org # 5.18+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
-----BEGIN PGP SIGNATURE-----
iQIzBAABCgAdFiEE8rQSAMVO+zA4DBdWxWXV+ddtWDsFAmLnyNUACgkQxWXV+ddt
WDt9vA/9HcF+v5EkknyW07tatTap/Hm/ZB86Z5OZi6ikwIEcHsWhp3rUICejm88e
GecDPIluDtCtyD6x4stuqkwOm22aDP5q2T9H6+gyw92ozyb436OV1Z8IrmftzXKY
EpZO70PHZT+E6E/WYvyoTmmoCrjib7YlqCWZZhSLUFpsqqlOInmHEH49PW6KvM4r
acUZ/RxHurKdmI3kNY6ECbAQl6CASvtTdYcVCx8fT2zN0azoLIQxpYa7n/9ca1R6
8WnYilCbLbNGtcUXvO2M3tMZ4/5kvxrwQsUn93ccCJYuiN0ASiDXbLZ2g4LZ+n56
JGu+y5v5oBwjpVf+46cuvnENP5BQ61594WPseiVjrqODWnPjN28XkcVC0XmPsiiZ
lszeHO2cuIrIFoCah8ELMl8usu8+qxfXmPxIXtPu9rEyKsDtOjxVYc8SMXqLp0qQ
qYtBoFm0JcZHqtZRpB+dhQ37/xXtH4ljUi/mI6x8iALVujeR273URs7yO9zgIdeW
uZoFtbwpHFLUk+TL7Ku82/zOXp3fCwtDpNmlYbxeMbea/be3ShjncM4+mYzvHYri
dYON2LFrq+mnRDqtIXTCaAYwX7zU8Y18Ev9QwlNll8dKlKwS89+jpqLoa+eVYy3c
/HitHFza70KxmOj4dvDVZlzDpPvl7kW1UBkmskg4u3jnNWzedkM=
=sS1q
-----END PGP SIGNATURE-----
Merge tag 'for-5.20-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs updates from David Sterba:
"This brings some long awaited changes, the send protocol bump,
otherwise lots of small improvements and fixes. The main core part is
reworking bio handling, cleaning up the submission and endio and
improving error handling.
There are some changes outside of btrfs adding helpers or updating
API, listed at the end of the changelog.
Features:
- sysfs:
- export chunk size, in debug mode add tunable for setting its size
- show zoned among features (was only in debug mode)
- show commit stats (number, last/max/total duration)
- send protocol updated to 2
- new commands:
- ability write larger data chunks than 64K
- send raw compressed extents (uses the encoded data ioctls),
ie. no decompression on send side, no compression needed on
receive side if supported
- send 'otime' (inode creation time) among other timestamps
- send file attributes (a.k.a file flags and xflags)
- this is first version bump, backward compatibility on send and
receive side is provided
- there are still some known and wanted commands that will be
implemented in the near future, another version bump will be
needed, however we want to minimize that to avoid causing
usability issues
- print checksum type and implementation at mount time
- don't print some messages at mount (mentioned as people asked about
it), we want to print messages namely for new features so let's
make some space for that
- big metadata - this has been supported for a long time and is
not a feature that's worth mentioning
- skinny metadata - same reason, set by default by mkfs
Performance improvements:
- reduced amount of reserved metadata for delayed items
- when inserted items can be batched into one leaf
- when deleting batched directory index items
- when deleting delayed items used for deletion
- overall improved count of files/sec, decreased subvolume lock
contention
- metadata item access bounds checker micro-optimized, with a few
percent of improved runtime for metadata-heavy operations
- increase direct io limit for read to 256 sectors, improved
throughput by 3x on sample workload
Notable fixes:
- raid56
- reduce parity writes, skip sectors of stripe when there are no
data updates
- restore reading from on-disk data instead of using stripe cache,
this reduces chances to damage correct data due to RMW cycle
- refuse to replay log with unknown incompat read-only feature bit
set
- zoned
- fix page locking when COW fails in the middle of allocation
- improved tracking of active zones, ZNS drives may limit the
number and there are ENOSPC errors due to that limit and not
actual lack of space
- adjust maximum extent size for zone append so it does not cause
late ENOSPC due to underreservation
- mirror reading error messages show the mirror number
- don't fallback to buffered IO for NOWAIT direct IO writes, we don't
have the NOWAIT semantics for buffered io yet
- send, fix sending link commands for existing file paths when there
are deleted and created hardlinks for same files
- repair all mirrors for profiles with more than 1 copy (raid1c34)
- fix repair of compressed extents, unify where error detection and
repair happen
Core changes:
- bio completion cleanups
- don't double defer compression bios
- simplify endio workqueues
- add more data to btrfs_bio to avoid allocation for read requests
- rework bio error handling so it's same what block layer does,
the submission works and errors are consumed in endio
- when asynchronous bio offload fails fall back to synchronous
checksum calculation to avoid errors under writeback or memory
pressure
- new trace points
- raid56 events
- ordered extent operations
- super block log_root_transid deprecated (never used)
- mixed_backref and big_metadata sysfs feature files removed, they've
been default for sufficiently long time, there are no known users
and mixed_backref could be confused with mixed_groups
Non-btrfs changes, API updates:
- minor highmem API update to cover const arguments
- switch all kmap/kmap_atomic to kmap_local
- remove redundant flush_dcache_page()
- address_space_operations::writepage callback removed
- add bdev_max_segments() helper"
* tag 'for-5.20-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (163 commits)
btrfs: don't call btrfs_page_set_checked in finish_compressed_bio_read
btrfs: fix repair of compressed extents
btrfs: remove the start argument to check_data_csum and export
btrfs: pass a btrfs_bio to btrfs_repair_one_sector
btrfs: simplify the pending I/O counting in struct compressed_bio
btrfs: repair all known bad mirrors
btrfs: merge btrfs_dev_stat_print_on_error with its only caller
btrfs: join running log transaction when logging new name
btrfs: simplify error handling in btrfs_lookup_dentry
btrfs: send: always use the rbtree based inode ref management infrastructure
btrfs: send: fix sending link commands for existing file paths
btrfs: send: introduce recorded_ref_alloc and recorded_ref_free
btrfs: zoned: wait until zone is finished when allocation didn't progress
btrfs: zoned: write out partially allocated region
btrfs: zoned: activate necessary block group
btrfs: zoned: activate metadata block group on flush_space
btrfs: zoned: disable metadata overcommit for zoned
btrfs: zoned: introduce space_info->active_total_bytes
btrfs: zoned: finish least available block group on data bg allocation
btrfs: let can_allocate_chunk return error
...
One of the goals is to reduce the overhead of using ->read_iter()
and ->write_iter() instead of ->read()/->write(); new_sync_{read,write}()
has a surprising amount of overhead, in particular inside iocb_flags().
That's why the beginning of the series is in this pile; it's not directly
iov_iter-related, but it's a part of the same work...
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQQqUNBr3gm4hGXdBJlZ7Krx/gZQ6wUCYurGOQAKCRBZ7Krx/gZQ
6ysyAP91lvBfMRepcxpd9kvtuzWkU8A3rfSziZZteEHANB9Q7QEAiPn2a2OjWkcZ
uAyUWfCkHCNx+dSMkEvUgR5okQ0exAM=
=9UCV
-----END PGP SIGNATURE-----
Merge tag 'pull-work.iov_iter-base' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs
Pull vfs iov_iter updates from Al Viro:
"Part 1 - isolated cleanups and optimizations.
One of the goals is to reduce the overhead of using ->read_iter() and
->write_iter() instead of ->read()/->write().
new_sync_{read,write}() has a surprising amount of overhead, in
particular inside iocb_flags(). That's the explanation for the
beginning of the series is in this pile; it's not directly
iov_iter-related, but it's a part of the same work..."
* tag 'pull-work.iov_iter-base' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
first_iovec_segment(): just return address
iov_iter: massage calling conventions for first_{iovec,bvec}_segment()
iov_iter: first_{iovec,bvec}_segment() - simplify a bit
iov_iter: lift dealing with maxpages out of first_{iovec,bvec}_segment()
iov_iter_get_pages{,_alloc}(): cap the maxsize with MAX_RW_COUNT
iov_iter_bvec_advance(): don't bother with bvec_iter
copy_page_{to,from}_iter(): switch iovec variants to generic
keep iocb_flags() result cached in struct file
iocb: delay evaluation of IS_SYNC(...) until we want to check IOCB_DSYNC
struct file: use anonymous union member for rcuhead and llist
btrfs: use IOMAP_DIO_NOSYNC
teach iomap_dio_rw() to suppress dsync
No need of likely/unlikely on calls of check_copy_size()
Currently, for a direct IO write, if we need to fallback to buffered IO,
either to satisfy the whole write operation or just a part of it, we do
it in the current context even if it's a NOWAIT context. This is not ideal
because we currently don't have support for NOWAIT semantics in the
buffered IO path (we can block for several reasons), so we should instead
return -EAGAIN to the caller, so that it knows it should retry (the whole
operation or what's left of it) in a context where blocking is acceptable.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Use simple bool type for the block reserve failfast status, there's
short to save space as there used to be int but there's no reason for
that.
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The chained assignments may be convenient to write, but make readability
a bit worse as it's too easy to overlook that there are several values
set on the same line while this is rather an exception. Making it
consistent everywhere avoids surprises.
The pattern where inode times are initialized reuses the first value and
the order is mtime, ctime. In other blocks the assignments are expanded
so the order of variables is similar to the neighboring code.
Signed-off-by: David Sterba <dsterba@suse.com>
Currently we will return 1 or -EAGAIN if we decide we need to commit
the transaction rather than sync the log. In practice this doesn't
really matter, we interpret any !0 and !BTRFS_NO_LOG_SYNC as needing to
commit the transaction. However this makes it hard to figure out what
the correct thing to do is.
Fix this up by defining BTRFS_LOG_FORCE_COMMIT and using this in all the
places where we want to force the transaction to be committed.
CC: stable@vger.kernel.org # 5.15+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
-----BEGIN PGP SIGNATURE-----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=rUrf
-----END PGP SIGNATURE-----
Merge tag 'for-5.19-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs fixes from David Sterba:
- zoned relocation fixes:
- fix critical section end for extent writeback, this could lead
to out of order write
- prevent writing to previous data relocation block group if space
gets low
- reflink fixes:
- fix race between reflinking and ordered extent completion
- proper error handling when block reserve migration fails
- add missing inode iversion/mtime/ctime updates on each iteration
when replacing extents
- fix deadlock when running fsync/fiemap/commit at the same time
- fix false-positive KCSAN report regarding pid tracking for read locks
and data race
- minor documentation update and link to new site
* tag 'for-5.19-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
Documentation: update btrfs list of features and link to readthedocs.io
btrfs: fix deadlock with fsync+fiemap+transaction commit
btrfs: don't set lock_owner when locking extent buffer for reading
btrfs: zoned: fix critical section of relocation inode writeback
btrfs: zoned: prevent allocation from previous data relocation BG
btrfs: do not BUG_ON() on failure to migrate space when replacing extents
btrfs: add missing inode updates on each iteration when replacing extents
btrfs: fix race between reflinking and ordered extent completion
We are hitting the following deadlock in production occasionally
Task 1 Task 2 Task 3 Task 4 Task 5
fsync(A)
start trans
start commit
falloc(A)
lock 5m-10m
start trans
wait for commit
fiemap(A)
lock 0-10m
wait for 5m-10m
(have 0-5m locked)
have btrfs_need_log_full_commit
!full_sync
wait_ordered_extents
finish_ordered_io(A)
lock 0-5m
DEADLOCK
We have an existing dependency of file extent lock -> transaction.
However in fsync if we tried to do the fast logging, but then had to
fall back to committing the transaction, we will be forced to call
btrfs_wait_ordered_range() to make sure all of our extents are updated.
This creates a dependency of transaction -> file extent lock, because
btrfs_finish_ordered_io() will need to take the file extent lock in
order to run the ordered extents.
Fix this by stopping the transaction if we have to do the full commit
and we attempted to do the fast logging. Then attach to the transaction
and commit it if we need to.
CC: stable@vger.kernel.org # 5.15+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
At btrfs_replace_file_extents(), if we fail to migrate reserved metadata
space from the transaction block reserve into the local block reserve,
we trigger a BUG_ON(). This is because it should not be possible to have
a failure here, as we reserved more space when we started the transaction
than the space we want to migrate. However having a BUG_ON() is way too
drastic, we can perfectly handle the failure and return the error to the
caller. So just do that instead, and add a WARN_ON() to make it easier
to notice the failure if it ever happens (which is particularly useful
for fstests, and the warning will trigger a failure of a test case).
Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When replacing file extents, called during fallocate, hole punching,
clone and deduplication, we may not be able to replace/drop all the
target file extent items with a single transaction handle. We may get
-ENOSPC while doing it, in which case we release the transaction handle,
balance the dirty pages of the btree inode, flush delayed items and get
a new transaction handle to operate on what's left of the target range.
By dropping and replacing file extent items we have effectively modified
the inode, so we should bump its iversion and update its mtime/ctime
before we update the inode item. This is because if the transaction
we used for partially modifying the inode gets committed by someone after
we release it and before we finish the rest of the range, a power failure
happens, then after mounting the filesystem our inode has an outdated
iversion and mtime/ctime, corresponding to the values it had before we
changed it.
So add the missing iversion and mtime/ctime updates.
Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
New helper to be used instead of direct checks for IOCB_DSYNC:
iocb_is_dsync(iocb). Checks converted, which allows to avoid
the IS_SYNC(iocb->ki_filp->f_mapping->host) part (4 cache lines)
from iocb_flags() - it's checked in iocb_is_dsync() instead
Reviewed-by: Christian Brauner (Microsoft) <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
... instead of messing with iocb flags
Suggested-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Christian Brauner (Microsoft) <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
- Appoint myself page cache maintainer
- Fix how scsicam uses the page cache
- Use the memalloc_nofs_save() API to replace AOP_FLAG_NOFS
- Remove the AOP flags entirely
- Remove pagecache_write_begin() and pagecache_write_end()
- Documentation updates
- Convert several address_space operations to use folios:
- is_dirty_writeback
- readpage becomes read_folio
- releasepage becomes release_folio
- freepage becomes free_folio
- Change filler_t to require a struct file pointer be the first argument
like ->read_folio
-----BEGIN PGP SIGNATURE-----
iQEzBAABCgAdFiEEejHryeLBw/spnjHrDpNsjXcpgj4FAmKNMDUACgkQDpNsjXcp
gj4/mwf/bpHhXH4ZoNIvtUpTF6rZbqeffmc0VrbxCZDZ6igRnRPglxZ9H9v6L53O
7B0FBQIfxgNKHZpdqGdOkv8cjg/GMe/HJUbEy5wOakYPo4L9fZpHbDZ9HM2Eankj
xBqLIBgBJ7doKr+Y62DAN19TVD8jfRfVtli5mqXJoNKf65J7BkxljoTH1L3EXD9d
nhLAgyQjR67JQrT/39KMW+17GqLhGefLQ4YnAMONtB6TVwX/lZmigKpzVaCi4r26
bnk5vaR/3PdjtNxIoYvxdc71y2Eg05n2jEq9Wcy1AaDv/5vbyZUlZ2aBSaIVbtKX
WfrhN9O3L0bU5qS7p9PoyfLc9wpq8A==
=djLv
-----END PGP SIGNATURE-----
Merge tag 'folio-5.19' of git://git.infradead.org/users/willy/pagecache
Pull page cache updates from Matthew Wilcox:
- Appoint myself page cache maintainer
- Fix how scsicam uses the page cache
- Use the memalloc_nofs_save() API to replace AOP_FLAG_NOFS
- Remove the AOP flags entirely
- Remove pagecache_write_begin() and pagecache_write_end()
- Documentation updates
- Convert several address_space operations to use folios:
- is_dirty_writeback
- readpage becomes read_folio
- releasepage becomes release_folio
- freepage becomes free_folio
- Change filler_t to require a struct file pointer be the first
argument like ->read_folio
* tag 'folio-5.19' of git://git.infradead.org/users/willy/pagecache: (107 commits)
nilfs2: Fix some kernel-doc comments
Appoint myself page cache maintainer
fs: Remove aops->freepage
secretmem: Convert to free_folio
nfs: Convert to free_folio
orangefs: Convert to free_folio
fs: Add free_folio address space operation
fs: Convert drop_buffers() to use a folio
fs: Change try_to_free_buffers() to take a folio
jbd2: Convert release_buffer_page() to use a folio
jbd2: Convert jbd2_journal_try_to_free_buffers to take a folio
reiserfs: Convert release_buffer_page() to use a folio
fs: Remove last vestiges of releasepage
ubifs: Convert to release_folio
reiserfs: Convert to release_folio
orangefs: Convert to release_folio
ocfs2: Convert to release_folio
nilfs2: Remove comment about releasepage
nfs: Convert to release_folio
jfs: Convert to release_folio
...
Add a wrapper around iomap_dio_rw that keeps the direct I/O internals
isolated in inode.c.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When doing a NOWAIT direct IO write, if we can NOCOW then it means we can
proceed with the non-blocking, NOWAIT path. However reserving the metadata
space and qgroup meta space can often result in blocking - flushing
delalloc, wait for ordered extents to complete, trigger transaction
commits, etc, going against the semantics of a NOWAIT write.
So make the NOWAIT write path to try to reserve all the metadata it needs
without resulting in a blocking behaviour - if we get -ENOSPC or -EDQUOT
then return -EAGAIN to make the caller fallback to a blocking direct IO
write.
This is part of a patchset comprised of the following patches:
btrfs: avoid blocking on page locks with nowait dio on compressed range
btrfs: avoid blocking nowait dio when locking file range
btrfs: avoid double nocow check when doing nowait dio writes
btrfs: stop allocating a path when checking if cross reference exists
btrfs: free path at can_nocow_extent() before checking for checksum items
btrfs: release path earlier at can_nocow_extent()
btrfs: avoid blocking when allocating context for nowait dio read/write
btrfs: avoid blocking on space revervation when doing nowait dio writes
The following test was run before and after applying this patchset:
$ cat io-uring-nodatacow-test.sh
#!/bin/bash
DEV=/dev/sdc
MNT=/mnt/sdc
MOUNT_OPTIONS="-o ssd -o nodatacow"
MKFS_OPTIONS="-R free-space-tree -O no-holes"
NUM_JOBS=4
FILE_SIZE=8G
RUN_TIME=300
cat <<EOF > /tmp/fio-job.ini
[io_uring_rw]
rw=randrw
fsync=0
fallocate=posix
group_reporting=1
direct=1
ioengine=io_uring
iodepth=64
bssplit=4k/20:8k/20:16k/20:32k/10:64k/10:128k/5:256k/5:512k/5:1m/5
filesize=$FILE_SIZE
runtime=$RUN_TIME
time_based
filename=foobar
directory=$MNT
numjobs=$NUM_JOBS
thread
EOF
echo performance | \
tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
umount $MNT &> /dev/null
mkfs.btrfs -f $MKFS_OPTIONS $DEV &> /dev/null
mount $MOUNT_OPTIONS $DEV $MNT
fio /tmp/fio-job.ini
umount $MNT
The test was run a 12 cores box with 64G of ram, using a non-debug kernel
config (Debian's default config) and a spinning disk.
Result before the patchset:
READ: bw=407MiB/s (427MB/s), 407MiB/s-407MiB/s (427MB/s-427MB/s), io=119GiB (128GB), run=300175-300175msec
WRITE: bw=407MiB/s (427MB/s), 407MiB/s-407MiB/s (427MB/s-427MB/s), io=119GiB (128GB), run=300175-300175msec
Result after the patchset:
READ: bw=436MiB/s (457MB/s), 436MiB/s-436MiB/s (457MB/s-457MB/s), io=128GiB (137GB), run=300044-300044msec
WRITE: bw=435MiB/s (456MB/s), 435MiB/s-435MiB/s (456MB/s-456MB/s), io=128GiB (137GB), run=300044-300044msec
That's about +7.2% throughput for reads and +6.9% for writes.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When doing a NOWAIT direct IO write we are checking twice if we can COW
into the target file range using can_nocow_extent() - once at the very
beginning of the write path, at btrfs_write_check() via
check_nocow_nolock(), and later again at btrfs_get_blocks_direct_write().
The can_nocow_extent() function does a lot of expensive things - searching
for the file extent item in the inode's subvolume tree, searching for the
extent item in the extent tree, checking delayed references, etc, so it
isn't a very cheap call.
We can remove the first check at btrfs_write_check(), and add there a
quick check to verify if the inode has the NODATACOW or PREALLOC flags,
and quickly bail out if it doesn't have neither of those flags, as that
means we have to COW and therefore can't comply with the NOWAIT semantics.
After this we do only one call to can_nocow_extent(), while we are at
btrfs_get_blocks_direct_write(), where we have already locked the file
range and we did a try lock on the range before, at
btrfs_dio_iomap_begin() (since the previous patch in the series).
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We have four different scenarios where we don't expect to find ordered
extents after locking a file range:
1) During plain fallocate;
2) During hole punching;
3) During zero range;
4) During reflinks (both cloning and deduplication).
This is because in all these cases we follow the pattern:
1) Lock the inode's VFS lock in exclusive mode;
2) Lock the inode's i_mmap_lock in exclusive node, to serialize with
mmap writes;
3) Flush delalloc in a file range and wait for all ordered extents
to complete - both done through btrfs_wait_ordered_range();
4) Lock the file range in the inode's io_tree.
So add a helper that asserts that we don't have ordered extents for a
given range. Make the four scenarios listed above use this helper after
locking the respective file range.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
For hole punching and zero range we have this loop that checks if we have
ordered extents after locking the file range, and if so unlock the range,
wait for ordered extents, and retry until we don't find more ordered
extents.
This logic was needed in the past because:
1) Direct IO writes within the i_size boundary did not take the inode's
VFS lock. This was because that lock used to be a mutex, then some
years ago it was switched to a rw semaphore (commit 9902af79c0
("parallel lookups: actual switch to rwsem")), and then btrfs was
changed to take the VFS inode's lock in shared mode for writes that
don't cross the i_size boundary (commit e9adabb971 ("btrfs: use
shared lock for direct writes within EOF"));
2) We could race with memory mapped writes, because memory mapped writes
don't acquire the inode's VFS lock. We don't have that race anymore,
as we have a rw semaphore to synchronize memory mapped writes with
fallocate (and reflinking too). That change happened with commit
8d9b4a162a ("btrfs: exclude mmap from happening during all
fallocate operations").
So stop looking for ordered extents after locking the file range when
doing hole punching and zero range operations.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When doing hole punching we are flushing delalloc and waiting for ordered
extents to complete before locking the inode (VFS lock and the btrfs
specific i_mmap_lock). This is fine because even if a write happens after
we call btrfs_wait_ordered_range() and before we lock the inode (call
btrfs_inode_lock()), we will notice the write at
btrfs_punch_hole_lock_range() and flush delalloc and wait for its ordered
extent.
We can however make this simpler by locking first the inode an then call
btrfs_wait_ordered_range(), which will allow us to remove the ordered
extent lookup logic from btrfs_punch_hole_lock_range() in the next patch.
It also makes the behaviour the same as plain fallocate, hole punching
and reflinks.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
For fallocate() we have this loop that checks if we have ordered extents
after locking the file range, and if so unlock the range, wait for ordered
extents, and retry until we don't find more ordered extents.
This logic was needed in the past because:
1) Direct IO writes within the i_size boundary did not take the inode's
VFS lock. This was because that lock used to be a mutex, then some
years ago it was switched to a rw semaphore (commit 9902af79c0
("parallel lookups: actual switch to rwsem")), and then btrfs was
changed to take the VFS inode's lock in shared mode for writes that
don't cross the i_size boundary (commit e9adabb971 ("btrfs: use
shared lock for direct writes within EOF"));
2) We could race with memory mapped writes, because memory mapped writes
don't acquire the inode's VFS lock. We don't have that race anymore,
as we have a rw semaphore to synchronize memory mapped writes with
fallocate (and reflinking too). That change happened with commit
8d9b4a162a ("btrfs: exclude mmap from happening during all
fallocate operations").
So stop looking for ordered extents after locking the file range when
doing a plain fallocate.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When starting a fallocate zero range operation, before getting the first
extent map for the range, we make a call to inode_dio_wait().
This logic was needed in the past because direct IO writes within the
i_size boundary did not take the inode's VFS lock. This was because that
lock used to be a mutex, then some years ago it was switched to a rw
semaphore (by commit 9902af79c0 ("parallel lookups: actual switch to
rwsem")), and then btrfs was changed to take the VFS inode's lock in
shared mode for writes that don't cross the i_size boundary (done in
commit e9adabb971 ("btrfs: use shared lock for direct writes within
EOF")). The lockless direct IO writes could result in a race with the
zero range operation, resulting in the later getting a stale extent
map for the range.
So remove this no longer needed call to inode_dio_wait(), as fallocate
takes the inode's VFS lock in exclusive mode and direct IO writes within
i_size take that same lock in shared mode.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
During a plain fallocate, we always start by reserving an amount of data
space that matches the length of the range passed to fallocate. When we
already have extents allocated in that range, we may end up trying to
reserve a lot more data space then we need, which can result in several
undesired behaviours:
1) We fail with -ENOSPC. For example the passed range has a length
of 1G, but there's only one hole with a size of 1M in that range;
2) We temporarily reserve excessive data space that could be used by
other operations happening concurrently;
3) By reserving much more data space then we need, we can end up
doing expensive things like triggering dellaloc for other inodes,
waiting for the ordered extents to complete, trigger transaction
commits, allocate new block groups, etc.
Example:
$ cat test.sh
#!/bin/bash
DEV=/dev/sdj
MNT=/mnt/sdj
mkfs.btrfs -f -b 1g $DEV
mount $DEV $MNT
# Create a file with a size of 600M and two holes, one at [200M, 201M[
# and another at [401M, 402M[
xfs_io -f -c "pwrite -S 0xab 0 200M" \
-c "pwrite -S 0xcd 201M 200M" \
-c "pwrite -S 0xef 402M 198M" \
$MNT/foobar
# Now call fallocate against the whole file range, see if it fails
# with -ENOSPC or not - it shouldn't since we only need to allocate
# 2M of data space.
xfs_io -c "falloc 0 600M" $MNT/foobar
umount $MNT
$ ./test.sh
(...)
wrote 209715200/209715200 bytes at offset 0
200 MiB, 51200 ops; 0.8063 sec (248.026 MiB/sec and 63494.5831 ops/sec)
wrote 209715200/209715200 bytes at offset 210763776
200 MiB, 51200 ops; 0.8053 sec (248.329 MiB/sec and 63572.3172 ops/sec)
wrote 207618048/207618048 bytes at offset 421527552
198 MiB, 50688 ops; 0.7925 sec (249.830 MiB/sec and 63956.5548 ops/sec)
fallocate: No space left on device
$
So fix this by not allocating an amount of data space that matches the
length of the range passed to fallocate. Instead allocate an amount of
data space that corresponds to the sum of the sizes of each hole found
in the range. This reservation now happens after we have locked the file
range, which is safe since we know at this point there's no delalloc
in the range because we've taken the inode's VFS lock in exclusive mode,
we have taken the inode's i_mmap_lock in exclusive mode, we have flushed
delalloc and waited for all ordered extents in the range to complete.
This type of failure actually seems to happen in practice with systemd,
and we had at least one report about this in a very long thread which
is referenced by the Link tag below.
Link: https://lore.kernel.org/linux-btrfs/bdJVxLiFr_PyQSXRUbZJfFW_jAjsGgoMetqPHJMbg-hdy54Xt_ZHhRetmnJ6cJ99eBlcX76wy-AvWwV715c3YndkxneSlod11P1hlaADx0s=@protonmail.com/
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
I've only converted the outer layers of the btrfs release_folio paths
to use folios; the use of folios should be pushed further down into
btrfs from here.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
With all implementations of aops->readpage converted to aops->read_folio,
we can stop checking whether it's set and remove the member from aops.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
This is a "weak" conversion which converts straight back to using pages.
A full conversion should be performed at some point, hopefully by
someone familiar with the filesystem.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Change all the callers of ->readpage to call ->read_folio in preference,
if it exists. This is a transitional duplication, and will be removed
by the end of the series.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Since the initial introduction of (posix) fallocate back at the turn of
the century, it has been possible to use this syscall to change the
user-visible contents of files. This can happen by extending the file
size during a preallocation, or through any of the newer modes (punch,
zero range). Because the call can be used to change file contents, we
should treat it like we do any other modification to a file -- update
the mtime, and drop set[ug]id privileges/capabilities.
The VFS function file_modified() does all this for us if pass it a
locked inode, so let's make fallocate drop permissions correctly.
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: David Sterba <dsterba@suse.com>
When an inode has a last_reflink_trans matching the current transaction,
we have to take special care when logging its checksums in order to
avoid getting checksum items with overlapping ranges in a log tree,
which could result in missing checksums after log replay (more on that
in the changelogs of commit 40e046acbd ("Btrfs: fix missing data
checksums after replaying a log tree") and commit e289f03ea7 ("btrfs:
fix corrupt log due to concurrent fsync of inodes with shared extents")).
We also need to make sure a full fsync will copy all old file extent
items it finds in modified leaves, because they might have been copied
from some other inode.
However once we fsync an inode, we don't need to keep paying the price of
that extra special care in future fsyncs done in the same transaction,
unless the inode is used for another reflink operation or the full sync
flag is set on it (truncate, failure to allocate extent maps for holes,
and other exceptional and infrequent cases).
So after we fsync an inode reset its last_unlink_trans to zero. In case
another reflink happens, we continue to update the last_reflink_trans of
the inode, just as before. Also set last_reflink_trans to the generation
of the last transaction that modified the inode whenever we need to set
the full sync flag on the inode, just like when we need to load an inode
from disk after eviction.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The implementation resembles direct I/O: we have to flush any ordered
extents, invalidate the page cache, and do the io tree/delalloc/extent
map/ordered extent dance. From there, we can reuse the compression code
with a minor modification to distinguish the write from writeback. This
also creates inline extents when possible.
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Currently, we always reserve the same extent size in the file and extent
size on disk for delalloc because the former is the worst case for the
latter. For BTRFS_IOC_ENCODED_WRITE writes, we know the exact size of
the extent on disk, which may be less than or greater than (for
bookends) the size in the file. Add a disk_num_bytes parameter to
btrfs_delalloc_reserve_metadata() so that we can reserve the correct
amount of csum bytes. No functional change.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
At btrfs_drop_extents(), we try to replace a range of file extent items
with a new file extent in a single btree search, to avoid the need to do
a search for deletion, followed by a path release and followed by yet
another search for insertion.
When I originally added that optimization, in commit 1acae57b16
("Btrfs: faster file extent item replace operations"), I left a constraint
to do the fast replace only if we visited a single leaf. That was because
in the most common case we find all file extent items that need to be
deleted (or trimmed) in a single leaf, however it can work for other
common cases like when we need to delete a few file extent items located
at the end of a leaf and a few more located at the beginning of the next
leaf. The key for the new file extent item is greater than the key of
any deleted or trimmed file extent item from previous leaves, so we are
fine to use the last leaf that we found as long as we are holding a
write lock on it - even if the new key ends up at slot 0, as if that's
the case, the btree search has obtained a write lock on any upper nodes
that need to have a key pointer updated.
So removed the constraint that limits the optimization to the case where
we visited only a single leaf.
This change if part of a patchset that is comprised of the following
patches:
1/6 btrfs: remove unnecessary leaf free space checks when pushing items
2/6 btrfs: avoid unnecessary COW of leaves when deleting items from a leaf
3/6 btrfs: avoid unnecessary computation when deleting items from a leaf
4/6 btrfs: remove constraint on number of visited leaves when replacing extents
5/6 btrfs: remove useless path release in the fast fsync path
6/6 btrfs: prepare extents to be logged before locking a log tree path
The last patch in the series has some performance test result in its
changelog.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
There is a big gap between inode_should_defrag() and autodefrag extent
size threshold. For inode_should_defrag() it has a flexible
@small_write value. For compressed extent is 16K, and for non-compressed
extent it's 64K.
However for autodefrag extent size threshold, it's always fixed to the
default value (256K).
This means, the following write sequence will trigger autodefrag to
defrag ranges which didn't trigger autodefrag:
pwrite 0 8k
sync
pwrite 8k 128K
sync
The latter 128K write will also be considered as a defrag target (if
other conditions are met). While only that 8K write is really
triggering autodefrag.
Such behavior can cause extra IO for autodefrag.
Close the gap, by copying the @small_write value into inode_defrag, so
that later autodefrag can use the same @small_write value which
triggered autodefrag.
With the existing transid value, this allows autodefrag really to scan
the ranges which triggered autodefrag.
Although this behavior change is mostly reducing the extent_thresh value
for autodefrag, I believe in the future we should allow users to specify
the autodefrag extent threshold through mount options, but that's an
other problem to consider in the future.
CC: stable@vger.kernel.org # 5.16+
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Although we have btrfs_requeue_inode_defrag(), for autodefrag we are
still just exhausting all inode_defrag items in the tree.
This means, it doesn't make much difference to requeue an inode_defrag,
other than scan the inode from the beginning till its end.
Change the behaviour to always scan from offset 0 of an inode, and till
the end.
By this we get the following benefit:
- Straight-forward code
- No more re-queue related check
- Fewer members in inode_defrag
We still keep the same btrfs_get_fs_root() and btrfs_iget() check for
each loop, and added extra should_auto_defrag() check per-loop.
Note: the patch needs to be backported and is intentionally written
to minimize the diff size, code will be cleaned up later.
CC: stable@vger.kernel.org # 5.16
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
If we do a direct IO read or write when the buffer given by the user is
memory mapped to the file range we are going to do IO, we end up ending
in a deadlock. This is triggered by the new test case generic/647 from
fstests.
For a direct IO read we get a trace like this:
[967.872718] INFO: task mmap-rw-fault:12176 blocked for more than 120 seconds.
[967.874161] Not tainted 5.14.0-rc7-btrfs-next-95 #1
[967.874909] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[967.875983] task:mmap-rw-fault state:D stack: 0 pid:12176 ppid: 11884 flags:0x00000000
[967.875992] Call Trace:
[967.875999] __schedule+0x3ca/0xe10
[967.876015] schedule+0x43/0xe0
[967.876020] wait_extent_bit.constprop.0+0x1eb/0x260 [btrfs]
[967.876109] ? do_wait_intr_irq+0xb0/0xb0
[967.876118] lock_extent_bits+0x37/0x90 [btrfs]
[967.876150] btrfs_lock_and_flush_ordered_range+0xa9/0x120 [btrfs]
[967.876184] ? extent_readahead+0xa7/0x530 [btrfs]
[967.876214] extent_readahead+0x32d/0x530 [btrfs]
[967.876253] ? lru_cache_add+0x104/0x220
[967.876255] ? kvm_sched_clock_read+0x14/0x40
[967.876258] ? sched_clock_cpu+0xd/0x110
[967.876263] ? lock_release+0x155/0x4a0
[967.876271] read_pages+0x86/0x270
[967.876274] ? lru_cache_add+0x125/0x220
[967.876281] page_cache_ra_unbounded+0x1a3/0x220
[967.876291] filemap_fault+0x626/0xa20
[967.876303] __do_fault+0x36/0xf0
[967.876308] __handle_mm_fault+0x83f/0x15f0
[967.876322] handle_mm_fault+0x9e/0x260
[967.876327] __get_user_pages+0x204/0x620
[967.876332] ? get_user_pages_unlocked+0x69/0x340
[967.876340] get_user_pages_unlocked+0xd3/0x340
[967.876349] internal_get_user_pages_fast+0xbca/0xdc0
[967.876366] iov_iter_get_pages+0x8d/0x3a0
[967.876374] bio_iov_iter_get_pages+0x82/0x4a0
[967.876379] ? lock_release+0x155/0x4a0
[967.876387] iomap_dio_bio_actor+0x232/0x410
[967.876396] iomap_apply+0x12a/0x4a0
[967.876398] ? iomap_dio_rw+0x30/0x30
[967.876414] __iomap_dio_rw+0x29f/0x5e0
[967.876415] ? iomap_dio_rw+0x30/0x30
[967.876420] ? lock_acquired+0xf3/0x420
[967.876429] iomap_dio_rw+0xa/0x30
[967.876431] btrfs_file_read_iter+0x10b/0x140 [btrfs]
[967.876460] new_sync_read+0x118/0x1a0
[967.876472] vfs_read+0x128/0x1b0
[967.876477] __x64_sys_pread64+0x90/0xc0
[967.876483] do_syscall_64+0x3b/0xc0
[967.876487] entry_SYSCALL_64_after_hwframe+0x44/0xae
[967.876490] RIP: 0033:0x7fb6f2c038d6
[967.876493] RSP: 002b:00007fffddf586b8 EFLAGS: 00000246 ORIG_RAX: 0000000000000011
[967.876496] RAX: ffffffffffffffda RBX: 0000000000001000 RCX: 00007fb6f2c038d6
[967.876498] RDX: 0000000000001000 RSI: 00007fb6f2c17000 RDI: 0000000000000003
[967.876499] RBP: 0000000000001000 R08: 0000000000000003 R09: 0000000000000000
[967.876501] R10: 0000000000001000 R11: 0000000000000246 R12: 0000000000000003
[967.876502] R13: 0000000000000000 R14: 00007fb6f2c17000 R15: 0000000000000000
This happens because at btrfs_dio_iomap_begin() we lock the extent range
and return with it locked - we only unlock in the endio callback, at
end_bio_extent_readpage() -> endio_readpage_release_extent(). Then after
iomap called the btrfs_dio_iomap_begin() callback, it triggers the page
faults that resulting in reading the pages, through the readahead callback
btrfs_readahead(), and through there we end to attempt to lock again the
same extent range (or a subrange of what we locked before), resulting in
the deadlock.
For a direct IO write, the scenario is a bit different, and it results in
trace like this:
[1132.442520] run fstests generic/647 at 2021-08-31 18:53:35
[1330.349355] INFO: task mmap-rw-fault:184017 blocked for more than 120 seconds.
[1330.350540] Not tainted 5.14.0-rc7-btrfs-next-95 #1
[1330.351158] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[1330.351900] task:mmap-rw-fault state:D stack: 0 pid:184017 ppid:183725 flags:0x00000000
[1330.351906] Call Trace:
[1330.351913] __schedule+0x3ca/0xe10
[1330.351930] schedule+0x43/0xe0
[1330.351935] btrfs_start_ordered_extent+0x108/0x1c0 [btrfs]
[1330.352020] ? do_wait_intr_irq+0xb0/0xb0
[1330.352028] btrfs_lock_and_flush_ordered_range+0x8c/0x120 [btrfs]
[1330.352064] ? extent_readahead+0xa7/0x530 [btrfs]
[1330.352094] extent_readahead+0x32d/0x530 [btrfs]
[1330.352133] ? lru_cache_add+0x104/0x220
[1330.352135] ? kvm_sched_clock_read+0x14/0x40
[1330.352138] ? sched_clock_cpu+0xd/0x110
[1330.352143] ? lock_release+0x155/0x4a0
[1330.352151] read_pages+0x86/0x270
[1330.352155] ? lru_cache_add+0x125/0x220
[1330.352162] page_cache_ra_unbounded+0x1a3/0x220
[1330.352172] filemap_fault+0x626/0xa20
[1330.352176] ? filemap_map_pages+0x18b/0x660
[1330.352184] __do_fault+0x36/0xf0
[1330.352189] __handle_mm_fault+0x1253/0x15f0
[1330.352203] handle_mm_fault+0x9e/0x260
[1330.352208] __get_user_pages+0x204/0x620
[1330.352212] ? get_user_pages_unlocked+0x69/0x340
[1330.352220] get_user_pages_unlocked+0xd3/0x340
[1330.352229] internal_get_user_pages_fast+0xbca/0xdc0
[1330.352246] iov_iter_get_pages+0x8d/0x3a0
[1330.352254] bio_iov_iter_get_pages+0x82/0x4a0
[1330.352259] ? lock_release+0x155/0x4a0
[1330.352266] iomap_dio_bio_actor+0x232/0x410
[1330.352275] iomap_apply+0x12a/0x4a0
[1330.352278] ? iomap_dio_rw+0x30/0x30
[1330.352292] __iomap_dio_rw+0x29f/0x5e0
[1330.352294] ? iomap_dio_rw+0x30/0x30
[1330.352306] btrfs_file_write_iter+0x238/0x480 [btrfs]
[1330.352339] new_sync_write+0x11f/0x1b0
[1330.352344] ? NF_HOOK_LIST.constprop.0.cold+0x31/0x3e
[1330.352354] vfs_write+0x292/0x3c0
[1330.352359] __x64_sys_pwrite64+0x90/0xc0
[1330.352365] do_syscall_64+0x3b/0xc0
[1330.352369] entry_SYSCALL_64_after_hwframe+0x44/0xae
[1330.352372] RIP: 0033:0x7f4b0a580986
[1330.352379] RSP: 002b:00007ffd34d75418 EFLAGS: 00000246 ORIG_RAX: 0000000000000012
[1330.352382] RAX: ffffffffffffffda RBX: 0000000000001000 RCX: 00007f4b0a580986
[1330.352383] RDX: 0000000000001000 RSI: 00007f4b0a3a4000 RDI: 0000000000000003
[1330.352385] RBP: 00007f4b0a3a4000 R08: 0000000000000003 R09: 0000000000000000
[1330.352386] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000003
[1330.352387] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
Unlike for reads, at btrfs_dio_iomap_begin() we return with the extent
range unlocked, but later when the page faults are triggered and we try
to read the extents, we end up btrfs_lock_and_flush_ordered_range() where
we find the ordered extent for our write, created by the iomap callback
btrfs_dio_iomap_begin(), and we wait for it to complete, which makes us
deadlock since we can't complete the ordered extent without reading the
pages (the iomap code only submits the bio after the pages are faulted
in).
Fix this by setting the nofault attribute of the given iov_iter and retry
the direct IO read/write if we get an -EFAULT error returned from iomap.
For reads, also disable page faults completely, this is because when we
read from a hole or a prealloc extent, we can still trigger page faults
due to the call to iov_iter_zero() done by iomap - at the moment, it is
oblivious to the value of the ->nofault attribute of an iov_iter.
We also need to keep track of the number of bytes written or read, and
pass it to iomap_dio_rw(), as well as use the new flag IOMAP_DIO_PARTIAL.
This depends on the iov_iter and iomap changes introduced in commit
c03098d4b9 ("Merge tag 'gfs2-v5.15-rc5-mmap-fault' of
git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2").
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Functions gfs2_file_read_iter and gfs2_file_write_iter are both
accessing the user buffer to write to or read from while holding the
inode glock. In the most basic scenario, that buffer will not be
resident and it will be mapped to the same file. Accessing the buffer
will trigger a page fault, and gfs2 will deadlock trying to take the
same inode glock again while trying to handle that fault.
Fix that and similar, more complex scenarios by disabling page faults
while accessing user buffers. To make this work, introduce a small
amount of new infrastructure and fix some bugs that didn't trigger so
far, with page faults enabled.
-----BEGIN PGP SIGNATURE-----
iQJIBAABCAAyFiEEJZs3krPW0xkhLMTc1b+f6wMTZToFAmGBPisUHGFncnVlbmJh
QHJlZGhhdC5jb20ACgkQ1b+f6wMTZTpE6A/7BezUnGuNJxJrR8pC+vcLYA7xAgUU
6STQ6IN7w5UHRlSkNzZxZ2XPxW4uVQ4SxSEeaLqBsHZihepjcLNFZ/8MhQ6UPSD0
8noHOi7CoIcp6IuWQtCpxRM/xjjm2SlMt2XbVJZaiJcdzCV9gB6TU9EkBRq7Zm/X
9WFBbv1xZF0skn9ISCJvNtiiI+VyWKgMDUKxJUiTQjmJcklyyqHcVGmQi9BjqPz4
4s3F+WH6CoGbDKlmNk/6Y9wZ/2+sbvGswVscUxPwJVPoZWsR1xBBUdAeAmEMD1P4
BgE/Y1J8JXyVPYtyvZKq70XUhKdQkxB7RfX87YasOk9mY4Kjd5rIIGEykh+o2vC9
kDhCHvf2Mnw5I6Rum3B7UXyB1vemY+fECIHsXhgBnS+ztabRtcAdpCuWoqb43ymw
yEX1KwXyU4FpRYbrRvdZT42Fmh6ty8TW+N4swg8S2TrffirvgAi5yrcHZ4mPupYv
lyzvsCW7Wv8hPXn/twNObX+okRgJnsxcCdBXARdCnRXfA8tH23xmu88u8RA1Vdxh
nzTvv6Dx2EowwojuDWMx29Mw3fA2IqIfbOV+4FaRU7NZ2ZKtknL8yGl27qQUsMoJ
vYsHTmagasjQr+NDJ3vQRLCw+JQ6B1hENpdkmixFD9moo7X1ZFW3HBi/UL973Bv6
5CmgeXto8FRUFjI=
=WeNd
-----END PGP SIGNATURE-----
Merge tag 'gfs2-v5.15-rc5-mmap-fault' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2
Pull gfs2 mmap + page fault deadlocks fixes from Andreas Gruenbacher:
"Functions gfs2_file_read_iter and gfs2_file_write_iter are both
accessing the user buffer to write to or read from while holding the
inode glock.
In the most basic deadlock scenario, that buffer will not be resident
and it will be mapped to the same file. Accessing the buffer will
trigger a page fault, and gfs2 will deadlock trying to take the same
inode glock again while trying to handle that fault.
Fix that and similar, more complex scenarios by disabling page faults
while accessing user buffers. To make this work, introduce a small
amount of new infrastructure and fix some bugs that didn't trigger so
far, with page faults enabled"
* tag 'gfs2-v5.15-rc5-mmap-fault' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2:
gfs2: Fix mmap + page fault deadlocks for direct I/O
iov_iter: Introduce nofault flag to disable page faults
gup: Introduce FOLL_NOFAULT flag to disable page faults
iomap: Add done_before argument to iomap_dio_rw
iomap: Support partial direct I/O on user copy failures
iomap: Fix iomap_dio_rw return value for user copies
gfs2: Fix mmap + page fault deadlocks for buffered I/O
gfs2: Eliminate ip->i_gh
gfs2: Move the inode glock locking to gfs2_file_buffered_write
gfs2: Introduce flag for glock holder auto-demotion
gfs2: Clean up function may_grant
gfs2: Add wrapper for iomap_file_buffered_write
iov_iter: Introduce fault_in_iov_iter_writeable
iov_iter: Turn iov_iter_fault_in_readable into fault_in_iov_iter_readable
gup: Turn fault_in_pages_{readable,writeable} into fault_in_{readable,writeable}
powerpc/kvm: Fix kvm_use_magic_page
iov_iter: Fix iov_iter_get_pages{,_alloc} page fault return value
In order to make 'real_root' used only in ref-verify it's required to
have the necessary context to perform the same checks that this member
is used for. So add 'mod_root' which will contain the root on behalf of
which a delayed ref was created and a 'skip_group' parameter which
will contain callsite-specific override of skip_qgroup.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We have a few flags that are inconsistently used to describe the fs in
different states of failure. As of 5963ffcaf3 ("btrfs: always abort
the transaction if we abort a trans handle") we will always set
BTRFS_FS_STATE_ERROR if we abort, so we don't have to check both ABORTED
and ERROR to see if things have gone wrong. Add a helper to check
BTRFS_FS_STATE_ERROR and then convert all checkers of FS_STATE_ERROR to
use the helper.
The TRANS_ABORTED bit check was added in af72273381 ("Btrfs: clean up
resources during umount after trans is aborted") but is not actually
specific.
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Although in btrfs we have very limited usage of PageChecked flag, it's
still some page flag not yet subpage compatible.
Fix it by introducing btrfs_subpage::checked_offset to do the convert.
For most call sites, especially for free-space cache, COW fixup and
btrfs_invalidatepage(), they all work in full page mode anyway.
For other call sites, they work as subpage compatible mode.
Some call sites need extra modification:
- btrfs_drop_pages()
Needs extra parameter to get the real range we need to clear checked
flag.
Also since btrfs_drop_pages() will accept pages beyond the dirtied
range, update btrfs_subpage_clamp_range() to handle such case
by setting @len to 0 if the page is beyond target range.
- btrfs_invalidatepage()
We need to call subpage helper before calling __btrfs_releasepage(),
or it will trigger ASSERT() as page->private will be cleared.
- btrfs_verify_data_csum()
In theory we don't need the io_bio->csum check anymore, but it's
won't hurt. Just change the comment.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Since setup_items_for_insert() is not used anymore outside of ctree.c,
make it static and remove its prototype from ctree.h. This also requires
to move the definition of setup_item_for_insert() from ctree.h to ctree.c
and move down btrfs_duplicate_item() so that it's defined after
setup_items_for_insert().
Further, since setup_item_for_insert() is used outside ctree.c, rename it
to btrfs_setup_item_for_insert().
This patch is part of a small patchset that is comprised of the following
patches:
btrfs: loop only once over data sizes array when inserting an item batch
btrfs: unexport setup_items_for_insert()
btrfs: use single bulk copy operations when logging directories
This is patch 2/3 and performance results, and the specific tests, are
included in the changelog of patch 3/3.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When inserting a batch of items into a btree, we end up looping over the
data sizes array 3 times:
1) Once in the caller of btrfs_insert_empty_items(), when it populates the
array with the data sizes for each item;
2) Once at btrfs_insert_empty_items() to sum the elements of the data
sizes array and compute the total data size;
3) And then once again at setup_items_for_insert(), where we do exactly
the same as what we do at btrfs_insert_empty_items(), to compute the
total data size.
That is not bad for small arrays, but when the arrays have hundreds of
elements, the time spent on looping is not negligible. For example when
doing batch inserts of delayed items for dir index items or when logging
a directory, it's common to have 200 to 260 dir index items in a single
batch when using a leaf size of 16K and using file names between 8 and 12
characters. For a 64K leaf size, multiply that by 4. Taking into account
that during directory logging or when flushing delayed dir index items we
can have many of those large batches, the time spent on the looping adds
up quickly.
It's also more important to avoid it at setup_items_for_insert(), since
we are holding a write lock on a leaf and, in some cases, on upper nodes
of the btree, which causes us to block other tasks that want to access
the leaf and nodes for longer than necessary.
So change the code so that setup_items_for_insert() and
btrfs_insert_empty_items() no longer compute the total data size, and
instead rely on the caller to supply it. This makes us loop over the
array only once, where we can both populate the data size array and
compute the total data size, taking advantage of spatial and temporal
locality. To make this more manageable, use a structure to contain
all the relevant details for a batch of items (keys array, data sizes
array, total data size, number of items), and use it as an argument
for btrfs_insert_empty_items() and setup_items_for_insert().
This patch is part of a small patchset that is comprised of the following
patches:
btrfs: loop only once over data sizes array when inserting an item batch
btrfs: unexport setup_items_for_insert()
btrfs: use single bulk copy operations when logging directories
This is patch 1/3 and performance results, and the specific tests, are
included in the changelog of patch 3/3.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Add a done_before argument to iomap_dio_rw that indicates how much of
the request has already been transferred. When the request succeeds, we
report that done_before additional bytes were tranferred. This is
useful for finishing a request asynchronously when part of the request
has already been completed synchronously.
We'll use that to allow iomap_dio_rw to be used with page faults
disabled: when a page fault occurs while submitting a request, we
synchronously complete the part of the request that has already been
submitted. The caller can then take care of the page fault and call
iomap_dio_rw again for the rest of the request, passing in the number of
bytes already tranferred.
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Turn iov_iter_fault_in_readable into a function that returns the number
of bytes not faulted in, similar to copy_to_user, instead of returning a
non-zero value when any of the requested pages couldn't be faulted in.
This supports the existing users that require all pages to be faulted in
as well as new users that are happy if any pages can be faulted in.
Rename iov_iter_fault_in_readable to fault_in_iov_iter_readable to make
sure this change doesn't silently break things.
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Error injection testing uncovered a case where we'd end up with a
corrupt file system with a missing extent in the middle of a file. This
occurs because the if statement to decide if we should abort is wrong.
The only way we would abort in this case is if we got a ret !=
-EOPNOTSUPP and we called from the file clone code. However the
prealloc code uses this path too. Instead we need to abort if there is
an error, and the only error we _don't_ abort on is -EOPNOTSUPP and only
if we came from the clone file code.
CC: stable@vger.kernel.org # 5.10+
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
I hit a stuck relocation on btrfs/061 during my overnight testing. This
turned out to be because we had left over extent entries in our extent
root for a data reloc inode that no longer existed. This happened
because in btrfs_drop_extents() we only update refs if we have SHAREABLE
set or we are the tree_root. This regression was introduced by
aeb935a455 ("btrfs: don't set SHAREABLE flag for data reloc tree")
where we stopped setting SHAREABLE for the data reloc tree.
The problem here is we actually do want to update extent references for
data extents in the data reloc tree, in fact we only don't want to
update extent references if the file extents are in the log tree.
Update this check to only skip updating references in the case of the
log tree.
This is relatively rare, because you have to be running scrub at the
same time, which is what btrfs/061 does. The data reloc inode has its
extents pre-allocated, and then we copy the extent into the
pre-allocated chunks. We theoretically should never be calling
btrfs_drop_extents() on a data reloc inode. The exception of course is
with scrub, if our pre-allocated extent falls inside of the block group
we are scrubbing, then the block group will be marked read only and we
will be forced to cow that extent. This means we will call
btrfs_drop_extents() on that range when we COW that file extent.
This isn't really problematic if we do this, the data reloc inode
requires that our extent lengths match exactly with the extent we are
copying, thankfully we validate the extent is correct with
get_new_location(), so if we happen to COW only part of the extent we
won't link it in when we do the relocation, so we are safe from any
other shenanigans that arise because of this interaction with scrub.
Fixes: aeb935a455 ("btrfs: don't set SHAREABLE flag for data reloc tree")
CC: stable@vger.kernel.org # 5.8+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Add support for fsverity in btrfs. To support the generic interface in
fs/verity, we add two new item types in the fs tree for inodes with
verity enabled. One stores the per-file verity descriptor and btrfs
verity item and the other stores the Merkle tree data itself.
Verity checking is done in end_page_read just before a page is marked
uptodate. This naturally handles a variety of edge cases like holes,
preallocated extents, and inline extents. Some care needs to be taken to
not try to verity pages past the end of the file, which are accessed by
the generic buffered file reading code under some circumstances like
reading to the end of the last page and trying to read again. Direct IO
on a verity file falls back to buffered reads.
Verity relies on PageChecked for the Merkle tree data itself to avoid
re-walking up shared paths in the tree. For this reason, we need to
cache the Merkle tree data. Since the file is immutable after verity is
turned on, we can cache it at an index past EOF.
Use the new inode ro_flags to store verity on the inode item, so that we
can enable verity on a file, then rollback to an older kernel and still
mount the file system and read the file. Since we can't safely write the
file anymore without ruining the invariants of the Merkle tree, we mark
a ro_compat flag on the file system when a file has verity enabled.
Acked-by: Eric Biggers <ebiggers@google.com>
Co-developed-by: Chris Mason <clm@fb.com>
Signed-off-by: Chris Mason <clm@fb.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
[BUG]
There is a possible use-after-free bug when running generic/095.
BUG: Unable to handle kernel data access on write at 0x6b6b6b6b6b6b725b
Faulting instruction address: 0xc000000000283654
c000000000283078 do_raw_spin_unlock+0x88/0x230
c0000000012b1e14 _raw_spin_unlock_irqrestore+0x44/0x90
c000000000a918dc btrfs_subpage_clear_writeback+0xac/0xe0
c0000000009e0458 end_bio_extent_writepage+0x158/0x270
c000000000b6fd14 bio_endio+0x254/0x270
c0000000009fc0f0 btrfs_end_bio+0x1a0/0x200
c000000000b6fd14 bio_endio+0x254/0x270
c000000000b781fc blk_update_request+0x46c/0x670
c000000000b8b394 blk_mq_end_request+0x34/0x1d0
c000000000d82d1c lo_complete_rq+0x11c/0x140
c000000000b880a4 blk_complete_reqs+0x84/0xb0
c0000000012b2ca4 __do_softirq+0x334/0x680
c0000000001dd878 irq_exit+0x148/0x1d0
c000000000016f4c do_IRQ+0x20c/0x240
c000000000009240 hardware_interrupt_common_virt+0x1b0/0x1c0
[CAUSE]
There is very small race window like the following in generic/095.
Thread 1 | Thread 2
--------------------------------+------------------------------------
end_bio_extent_writepage() | btrfs_releasepage()
|- spin_lock_irqsave() | |
|- end_page_writeback() | |
| | |- if (PageWriteback() ||...)
| | |- clear_page_extent_mapped()
| | |- kfree(subpage);
|- spin_unlock_irqrestore().
The race can also happen between writeback and btrfs_invalidatepage(),
although that would be much harder as btrfs_invalidatepage() has much
more work to do before the clear_page_extent_mapped() call.
[FIX]
Here we "wait" for the subapge spinlock to be released before we detach
subpage structure.
So this patch will introduce a new function, wait_subpage_spinlock(), to
do the "wait" by acquiring the spinlock and release it.
Since the caller has ensured the page is not dirty nor writeback, and
page is already locked, the only way to hold the subpage spinlock is
from endio function.
Thus we only need to acquire the spinlock to wait for any existing
holder.
Reported-by: Ritesh Harjani <riteshh@linux.ibm.com>
Tested-by: Ritesh Harjani <riteshh@linux.ibm.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
[BUG]
When running generic/095, there is a high chance to crash with subpage
data RW support:
assertion failed: PagePrivate(page) && page->private
------------[ cut here ]------------
kernel BUG at fs/btrfs/ctree.h:3403!
Internal error: Oops - BUG: 0 [#1] SMP
CPU: 1 PID: 3567 Comm: fio Tainted: 5.12.0-rc7-custom+ #17
Hardware name: Khadas VIM3 (DT)
Call trace:
assertfail.constprop.0+0x28/0x2c [btrfs]
btrfs_subpage_assert+0x80/0xa0 [btrfs]
btrfs_subpage_set_uptodate+0x34/0xec [btrfs]
btrfs_page_clamp_set_uptodate+0x74/0xa4 [btrfs]
btrfs_dirty_pages+0x160/0x270 [btrfs]
btrfs_buffered_write+0x444/0x630 [btrfs]
btrfs_direct_write+0x1cc/0x2d0 [btrfs]
btrfs_file_write_iter+0xc0/0x160 [btrfs]
new_sync_write+0xe8/0x180
vfs_write+0x1b4/0x210
ksys_pwrite64+0x7c/0xc0
__arm64_sys_pwrite64+0x24/0x30
el0_svc_common.constprop.0+0x70/0x140
do_el0_svc+0x28/0x90
el0_svc+0x2c/0x54
el0_sync_handler+0x1a8/0x1ac
el0_sync+0x170/0x180
Code: f0000160 913be042 913c4000 955444bc (d4210000)
---[ end trace 3fdd39f4cccedd68 ]---
[CAUSE]
Although prepare_pages() calls find_or_create_page(), which returns the
page locked, but in later prepare_uptodate_page() calls, we may call
btrfs_readpage() which will unlock the page before it returns.
This leaves a window where btrfs_releasepage() can sneak in and release
the page, clearing page->private and causing above ASSERT().
[FIX]
In prepare_uptodate_page(), we should not only check page->mapping, but
also PagePrivate() to ensure we are still holding the correct page which
has proper fs context setup.
Reported-by: Ritesh Harjani <riteshh@linux.ibm.com>
Tested-by: Ritesh Harjani <riteshh@linux.ibm.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Pull iov_iter updates from Al Viro:
"iov_iter cleanups and fixes.
There are followups, but this is what had sat in -next this cycle. IMO
the macro forest in there became much thinner and easier to follow..."
* 'work.iov_iter' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (37 commits)
csum_and_copy_to_pipe_iter(): leave handling of csum_state to caller
clean up copy_mc_pipe_to_iter()
pipe_zero(): we don't need no stinkin' kmap_atomic()...
iov_iter: clean csum_and_copy_...() primitives up a bit
copy_page_from_iter(): don't need kmap_atomic() for kvec/bvec cases
copy_page_to_iter(): don't bother with kmap_atomic() for bvec/kvec cases
iterate_xarray(): only of the first iteration we might get offset != 0
pull handling of ->iov_offset into iterate_{iovec,bvec,xarray}
iov_iter: make iterator callbacks use base and len instead of iovec
iov_iter: make the amount already copied available to iterator callbacks
iov_iter: get rid of separate bvec and xarray callbacks
iov_iter: teach iterate_{bvec,xarray}() about possible short copies
iterate_bvec(): expand bvec.h macro forest, massage a bit
iov_iter: unify iterate_iovec and iterate_kvec
iov_iter: massage iterate_iovec and iterate_kvec to logics similar to iterate_bvec
iterate_and_advance(): get rid of magic in case when n is 0
csum_and_copy_to_iter(): massage into form closer to csum_and_copy_from_iter()
iov_iter: replace iov_iter_copy_from_user_atomic() with iterator-advancing variant
[xarray] iov_iter_npages(): just use DIV_ROUND_UP()
iov_iter_npages(): don't bother with iterate_all_kinds()
...
By way of inverting the list_empty conditional the insert label can be
eliminated, making the function's flow entirely linear.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
[BUG]
With current subpage RW support, the following script can hang the fs
with 64K page size.
# mkfs.btrfs -f -s 4k $dev
# mount $dev -o nospace_cache $mnt
# fsstress -w -n 50 -p 1 -s 1607749395 -d $mnt
The kernel will do an infinite loop in btrfs_punch_hole_lock_range().
[CAUSE]
In btrfs_punch_hole_lock_range() we:
- Truncate page cache range
- Lock extent io tree
- Wait any ordered extents in the range.
We exit the loop until we meet all the following conditions:
- No ordered extent in the lock range
- No page is in the lock range
The latter condition has a pitfall, it only works for sector size ==
PAGE_SIZE case.
While can't handle the following subpage case:
0 32K 64K 96K 128K
| |///////||//////| ||
lockstart=32K
lockend=96K - 1
In this case, although the range crosses 2 pages,
truncate_pagecache_range() will invalidate no page at all, but only zero
the [32K, 96K) range of the two pages.
Thus filemap_range_has_page(32K, 96K-1) will always return true, thus we
will never meet the loop exit condition.
[FIX]
Fix the problem by doing page alignment for the lock range.
Function filemap_range_has_page() has already handled lend < lstart
case, we only need to round up @lockstart, and round_down @lockend for
truncate_pagecache_range().
This modification should not change any thing for sector size ==
PAGE_SIZE case, as in that case our range is already page aligned.
Tested-by: Ritesh Harjani <riteshh@linux.ibm.com> # [ppc64]
Tested-by: Anand Jain <anand.jain@oracle.com> # [aarch64]
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Since the extent io tree operations in btrfs_dirty_pages() are already
subpage compatible, we only need to make the page status update to use
subpage helpers.
Tested-by: Ritesh Harjani <riteshh@linux.ibm.com> # [ppc64]
Tested-by: Anand Jain <anand.jain@oracle.com> # [aarch64]
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Instead of calling list_entry with head->prev simply call
list_last_entry which makes it obvious which member of the list is
being referred. This allows to remove the extra 'prev' pointer.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Replacement is called copy_page_from_iter_atomic(); unlike the old primitive the
callers do *not* need to do iov_iter_advance() after it. In case when they end
up consuming less than they'd been given they need to do iov_iter_revert() on
everything they had not consumed. That, however, needs to be done only on slow
paths.
All in-tree callers converted. And that kills the last user of iterate_all_kinds()
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
We always return 0 even in case of an error in btrfs_mark_extent_written().
Fix it to return proper error value in case of a failure. All callers
handle it.
CC: stable@vger.kernel.org # 4.4+
Signed-off-by: Ritesh Harjani <riteshh@linux.ibm.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When doing a fast fsync on a file, there is a race which can result in the
fsync returning success to user space without logging the inode and without
durably persisting new data.
The following example shows one possible scenario for this:
$ mkfs.btrfs -f /dev/sdc
$ mount /dev/sdc /mnt
$ touch /mnt/bar
$ xfs_io -f -c "pwrite -S 0xab 0 1M" -c "fsync" /mnt/baz
# Now we have:
# file bar == inode 257
# file baz == inode 258
$ mv /mnt/baz /mnt/foo
# Now we have:
# file bar == inode 257
# file foo == inode 258
$ xfs_io -c "pwrite -S 0xcd 0 1M" /mnt/foo
# fsync bar before foo, it is important to trigger the race.
$ xfs_io -c "fsync" /mnt/bar
$ xfs_io -c "fsync" /mnt/foo
# After this:
# inode 257, file bar, is empty
# inode 258, file foo, has 1M filled with 0xcd
<power failure>
# Replay the log:
$ mount /dev/sdc /mnt
# After this point file foo should have 1M filled with 0xcd and not 0xab
The following steps explain how the race happens:
1) Before the first fsync of inode 258, when it has the "baz" name, its
->logged_trans is 0, ->last_sub_trans is 0 and ->last_log_commit is -1.
The inode also has the full sync flag set;
2) After the first fsync, we set inode 258 ->logged_trans to 6, which is
the generation of the current transaction, and set ->last_log_commit
to 0, which is the current value of ->last_sub_trans (done at
btrfs_log_inode()).
The full sync flag is cleared from the inode during the fsync.
The log sub transaction that was committed had an ID of 0 and when we
synced the log, at btrfs_sync_log(), we incremented root->log_transid
from 0 to 1;
3) During the rename:
We update inode 258, through btrfs_update_inode(), and that causes its
->last_sub_trans to be set to 1 (the current log transaction ID), and
->last_log_commit remains with a value of 0.
After updating inode 258, because we have previously logged the inode
in the previous fsync, we log again the inode through the call to
btrfs_log_new_name(). This results in updating the inode's
->last_log_commit from 0 to 1 (the current value of its
->last_sub_trans).
The ->last_sub_trans of inode 257 is updated to 1, which is the ID of
the next log transaction;
4) Then a buffered write against inode 258 is made. This leaves the value
of ->last_sub_trans as 1 (the ID of the current log transaction, stored
at root->log_transid);
5) Then an fsync against inode 257 (or any other inode other than 258),
happens. This results in committing the log transaction with ID 1,
which results in updating root->last_log_commit to 1 and bumping
root->log_transid from 1 to 2;
6) Then an fsync against inode 258 starts. We flush delalloc and wait only
for writeback to complete, since the full sync flag is not set in the
inode's runtime flags - we do not wait for ordered extents to complete.
Then, at btrfs_sync_file(), we call btrfs_inode_in_log() before the
ordered extent completes. The call returns true:
static inline bool btrfs_inode_in_log(...)
{
bool ret = false;
spin_lock(&inode->lock);
if (inode->logged_trans == generation &&
inode->last_sub_trans <= inode->last_log_commit &&
inode->last_sub_trans <= inode->root->last_log_commit)
ret = true;
spin_unlock(&inode->lock);
return ret;
}
generation has a value of 6 (fs_info->generation), ->logged_trans also
has a value of 6 (set when we logged the inode during the first fsync
and when logging it during the rename), ->last_sub_trans has a value
of 1, set during the rename (step 3), ->last_log_commit also has a
value of 1 (set in step 3) and root->last_log_commit has a value of 1,
which was set in step 5 when fsyncing inode 257.
As a consequence we don't log the inode, any new extents and do not
sync the log, resulting in a data loss if a power failure happens
after the fsync and before the current transaction commits.
Also, because we do not log the inode, after a power failure the mtime
and ctime of the inode do not match those we had before.
When the ordered extent completes before we call btrfs_inode_in_log(),
then the call returns false and we log the inode and sync the log,
since at the end of ordered extent completion we update the inode and
set ->last_sub_trans to 2 (the value of root->log_transid) and
->last_log_commit to 1.
This problem is found after removing the check for the emptiness of the
inode's list of modified extents in the recent commit 209ecbb858
("btrfs: remove stale comment and logic from btrfs_inode_in_log()"),
added in the 5.13 merge window. However checking the emptiness of the
list is not really the way to solve this problem, and was never intended
to, because while that solves the problem for COW writes, the problem
persists for NOCOW writes because in that case the list is always empty.
In the case of NOCOW writes, even though we wait for the writeback to
complete before returning from btrfs_sync_file(), we end up not logging
the inode, which has a new mtime/ctime, and because we don't sync the log,
we never issue disk barriers (send REQ_PREFLUSH to the device) since that
only happens when we sync the log (when we write super blocks at
btrfs_sync_log()). So effectively, for a NOCOW case, when we return from
btrfs_sync_file() to user space, we are not guaranteeing that the data is
durably persisted on disk.
Also, while the example above uses a rename exchange to show how the
problem happens, it is not the only way to trigger it. An alternative
could be adding a new hard link to inode 258, since that also results
in calling btrfs_log_new_name() and updating the inode in the log.
An example reproducer using the addition of a hard link instead of a
rename operation:
$ mkfs.btrfs -f /dev/sdc
$ mount /dev/sdc /mnt
$ touch /mnt/bar
$ xfs_io -f -c "pwrite -S 0xab 0 1M" -c "fsync" /mnt/foo
$ ln /mnt/foo /mnt/foo_link
$ xfs_io -c "pwrite -S 0xcd 0 1M" /mnt/foo
$ xfs_io -c "fsync" /mnt/bar
$ xfs_io -c "fsync" /mnt/foo
<power failure>
# Replay the log:
$ mount /dev/sdc /mnt
# After this point file foo often has 1M filled with 0xab and not 0xcd
The reasons leading to the final fsync of file foo, inode 258, not
persisting the new data are the same as for the previous example with
a rename operation.
So fix by never skipping logging and log syncing when there are still any
ordered extents in flight. To avoid making the conditional if statement
that checks if logging an inode is needed harder to read, place all the
logic into an helper function with separate if statements to make it more
manageable and easier to read.
A test case for fstests will follow soon.
For NOCOW writes, the problem existed before commit b5e6c3e170
("btrfs: always wait on ordered extents at fsync time"), introduced in
kernel 4.19, then it went away with that commit since we started to always
wait for ordered extent completion before logging.
The problem came back again once the fast fsync path was changed again to
avoid waiting for ordered extent completion, in commit 487781796d
("btrfs: make fast fsyncs wait only for writeback"), added in kernel 5.10.
However, for COW writes, the race only happens after the recent
commit 209ecbb858 ("btrfs: remove stale comment and logic from
btrfs_inode_in_log()"), introduced in the 5.13 merge window. For NOCOW
writes, the bug existed before that commit. So tag 5.10+ as the release
for stable backports.
CC: stable@vger.kernel.org # 5.10+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
In commit d77815461f ("btrfs: Avoid trucating page or punching hole
in a already existed hole."), existing holes can be skipped by calling
find_first_non_hole() to adjust start and len. However, if the given len
is invalid and large, when an EXTENT_MAP_HOLE extent is found, len will
not be set to zero because (em->start + em->len) is less than
(start + len). Then the ret will be 1 but len will not be set to 0.
The propagated non-zero ret will result in fallocate failure.
In the while-loop of btrfs_replace_file_extents(), len is not updated
every time before it calls find_first_non_hole(). That is, after
btrfs_drop_extents() successfully drops the last non-hole file extent,
it may fail with ENOSPC when attempting to drop a file extent item
representing a hole. The problem can happen. After it calls
find_first_non_hole(), the cur_offset will be adjusted to be larger
than or equal to end. However, since the len is not set to zero, the
break-loop condition (ret && !len) will not be met. After it leaves the
while-loop, fallocate will return 1, which is an unexpected return
value.
We're not able to construct a reproducible way to let
btrfs_drop_extents() fail with ENOSPC after it drops the last non-hole
file extent but with remaining holes left. However, it's quite easy to
fix. We just need to update and check the len every time before we call
find_first_non_hole(). To make the while loop more readable, we also
pull the variable updates to the bottom of loop like this:
while (cur_offset < end) {
...
// update cur_offset & len
// advance cur_offset & len in hole-punching case if needed
}
Reported-by: Robbie Ko <robbieko@synology.com>
Fixes: d77815461f ("btrfs: Avoid trucating page or punching hole in a already existed hole.")
CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Robbie Ko <robbieko@synology.com>
Reviewed-by: Chung-Chiang Cheng <cccheng@synology.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: BingJing Chang <bingjingc@synology.com>
Signed-off-by: David Sterba <dsterba@suse.com>
There is a comment at btrfs_replace_file_extents() that mentions that we
set the full sync flag on an inode when cloning into a file with a size
greater than or equals to 16MiB, through try_release_extent_mapping() when
we truncate the page cache after replacing file extents during a clone
operation.
That is not true anymore since commit 5e548b3201 ("btrfs: do not set
the full sync flag on the inode during page release"), so update the
comment to remove that part and rephrase it slightly to make it more
clear why the full sync flag is set at btrfs_replace_file_extents().
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
We have a race between marking that an inode needs to be logged, either
at btrfs_set_inode_last_trans() or at btrfs_page_mkwrite(), and between
btrfs_sync_log(). The following steps describe how the race happens.
1) We are at transaction N;
2) Inode I was previously fsynced in the current transaction so it has:
inode->logged_trans set to N;
3) The inode's root currently has:
root->log_transid set to 1
root->last_log_commit set to 0
Which means only one log transaction was committed to far, log
transaction 0. When a log tree is created we set ->log_transid and
->last_log_commit of its parent root to 0 (at btrfs_add_log_tree());
4) One more range of pages is dirtied in inode I;
5) Some task A starts an fsync against some other inode J (same root), and
so it joins log transaction 1.
Before task A calls btrfs_sync_log()...
6) Task B starts an fsync against inode I, which currently has the full
sync flag set, so it starts delalloc and waits for the ordered extent
to complete before calling btrfs_inode_in_log() at btrfs_sync_file();
7) During ordered extent completion we have btrfs_update_inode() called
against inode I, which in turn calls btrfs_set_inode_last_trans(),
which does the following:
spin_lock(&inode->lock);
inode->last_trans = trans->transaction->transid;
inode->last_sub_trans = inode->root->log_transid;
inode->last_log_commit = inode->root->last_log_commit;
spin_unlock(&inode->lock);
So ->last_trans is set to N and ->last_sub_trans set to 1.
But before setting ->last_log_commit...
8) Task A is at btrfs_sync_log():
- it increments root->log_transid to 2
- starts writeback for all log tree extent buffers
- waits for the writeback to complete
- writes the super blocks
- updates root->last_log_commit to 1
It's a lot of slow steps between updating root->log_transid and
root->last_log_commit;
9) The task doing the ordered extent completion, currently at
btrfs_set_inode_last_trans(), then finally runs:
inode->last_log_commit = inode->root->last_log_commit;
spin_unlock(&inode->lock);
Which results in inode->last_log_commit being set to 1.
The ordered extent completes;
10) Task B is resumed, and it calls btrfs_inode_in_log() which returns
true because we have all the following conditions met:
inode->logged_trans == N which matches fs_info->generation &&
inode->last_subtrans (1) <= inode->last_log_commit (1) &&
inode->last_subtrans (1) <= root->last_log_commit (1) &&
list inode->extent_tree.modified_extents is empty
And as a consequence we return without logging the inode, so the
existing logged version of the inode does not point to the extent
that was written after the previous fsync.
It should be impossible in practice for one task be able to do so much
progress in btrfs_sync_log() while another task is at
btrfs_set_inode_last_trans() right after it reads root->log_transid and
before it reads root->last_log_commit. Even if kernel preemption is enabled
we know the task at btrfs_set_inode_last_trans() can not be preempted
because it is holding the inode's spinlock.
However there is another place where we do the same without holding the
spinlock, which is in the memory mapped write path at:
vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
{
(...)
BTRFS_I(inode)->last_trans = fs_info->generation;
BTRFS_I(inode)->last_sub_trans = BTRFS_I(inode)->root->log_transid;
BTRFS_I(inode)->last_log_commit = BTRFS_I(inode)->root->last_log_commit;
(...)
So with preemption happening after setting ->last_sub_trans and before
setting ->last_log_commit, it is less of a stretch to have another task
do enough progress at btrfs_sync_log() such that the task doing the memory
mapped write ends up with ->last_sub_trans and ->last_log_commit set to
the same value. It is still a big stretch to get there, as the task doing
btrfs_sync_log() has to start writeback, wait for its completion and write
the super blocks.
So fix this in two different ways:
1) For btrfs_set_inode_last_trans(), simply set ->last_log_commit to the
value of ->last_sub_trans minus 1;
2) For btrfs_page_mkwrite() only set the inode's ->last_sub_trans, just
like we do for buffered and direct writes at btrfs_file_write_iter(),
which is all we need to make sure multiple writes and fsyncs to an
inode in the same transaction never result in an fsync missing that
the inode changed and needs to be logged. Turn this into a helper
function and use it both at btrfs_page_mkwrite() and at
btrfs_file_write_iter() - this also fixes the problem that at
btrfs_page_mkwrite() we were setting those fields without the
protection of the inode's spinlock.
This is an extremely unlikely race to happen in practice.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
When doing an fsync we flush all delalloc, lock the inode (VFS lock), flush
any new delalloc that might have been created before taking the lock and
then wait either for the ordered extents to complete or just for the
writeback to complete (depending on whether the full sync flag is set or
not). We then start logging the inode and assume that while we are doing it
no one else is touching the inode's file extent items (or adding new ones).
That is generally true because all operations that modify an inode acquire
the inode's lock first, including buffered and direct IO writes. However
there is one exception: memory mapped writes, which do not and can not
acquire the inode's lock.
This can cause two types of issues: ending up logging file extent items
with overlapping ranges, which is detected by the tree checker and will
result in aborting the transaction when starting writeback for a log
tree's extent buffers, or a silent corruption where we log a version of
the file that never existed.
Scenario 1 - logging overlapping extents
The following steps explain how we can end up with file extents items with
overlapping ranges in a log tree due to a race between a fsync and memory
mapped writes:
1) Task A starts an fsync on inode X, which has the full sync runtime flag
set. First it starts by flushing all delalloc for the inode;
2) Task A then locks the inode and flushes any other delalloc that might
have been created after the previous flush and waits for all ordered
extents to complete;
3) In the inode's root we have the following leaf:
Leaf N, generation == current transaction id:
---------------------------------------------------------
| (...) [ file extent item, offset 640K, length 128K ] |
---------------------------------------------------------
The last file extent item in leaf N covers the file range from 640K to
768K;
4) Task B does a memory mapped write for the page corresponding to the
file range from 764K to 768K;
5) Task A starts logging the inode. At copy_inode_items_to_log() it uses
btrfs_search_forward() to search for leafs modified in the current
transaction that contain items for the inode. It finds leaf N and copies
all the inode items from that leaf into the log tree.
Now the log tree has a copy of the last file extent item from leaf N.
At the end of the while loop at copy_inode_items_to_log(), we have the
minimum key set to:
min_key.objectid = <inode X number>
min_key.type = BTRFS_EXTENT_DATA_KEY
min_key.offset = 640K
Then we increment the key's offset by 1 so that the next call to
btrfs_search_forward() leaves us at the first key greater than the key
we just processed.
But before btrfs_search_forward() is called again...
6) Dellaloc for the page at offset 764K, dirtied by task B, is started.
It can be started for several reasons:
- The async reclaim task is attempting to satisfy metadata or data
reservation requests, and it has reached a point where it decided
to flush delalloc;
- Due to memory pressure the VMM triggers writeback of dirty pages;
- The system call sync_file_range(2) is called from user space.
7) When the respective ordered extent completes, it trims the length of
the existing file extent item for file offset 640K from 128K to 124K,
and a new file extent item is added with a key offset of 764K and a
length of 4K;
8) Task A calls btrfs_search_forward(), which returns us a path pointing
to the leaf (can be leaf N or some other) containing the new file extent
item for file offset 764K.
We end up copying this item to the log tree, which overlaps with the
last copied file extent item, which covers the file range from 640K to
768K.
When writeback is triggered for log tree's extent buffers, the issue
will be detected by the tree checker which will dump a trace and an
error message on dmesg/syslog. If the writeback is triggered when
syncing the log, which typically is, then we also end up aborting the
current transaction.
This is the same type of problem fixed in 0c713cbab6 ("Btrfs: fix race
between ranged fsync and writeback of adjacent ranges").
Scenario 2 - logging a version of the file that never existed
This scenario only happens when using the NO_HOLES feature and results in
a silent corruption, in the sense that is not detectable by 'btrfs check'
or the tree checker:
1) We have an inode I with a size of 1M and two file extent items, one
covering an extent with disk_bytenr == X for the file range [0, 512K)
and another one covering another extent with disk_bytenr == Y for the
file range [512K, 1M);
2) A hole is punched for the file range [512K, 1M);
3) Task A starts an fsync of inode I, which has the full sync runtime flag
set. It starts by flushing all existing delalloc, locks the inode (VFS
lock), starts any new delalloc that might have been created before
taking the lock and waits for all ordered extents to complete;
4) Some other task does a memory mapped write for the page corresponding to
the file range [640K, 644K) for example;
5) Task A then logs all items of the inode with the call to
copy_inode_items_to_log();
6) In the meanwhile delalloc for the range [640K, 644K) is started. It can
be started for several reasons:
- The async reclaim task is attempting to satisfy metadata or data
reservation requests, and it has reached a point where it decided
to flush delalloc;
- Due to memory pressure the VMM triggers writeback of dirty pages;
- The system call sync_file_range(2) is called from user space.
7) The ordered extent for the range [640K, 644K) completes and a file
extent item for that range is added to the subvolume tree, pointing
to a 4K extent with a disk_bytenr == Z;
8) Task A then calls btrfs_log_holes(), to scan for implicit holes in
the subvolume tree. It finds two implicit holes:
- one for the file range [512K, 640K)
- one for the file range [644K, 1M)
As a result we end up neither logging a hole for the range [640K, 644K)
nor logging the file extent item with a disk_bytenr == Z.
This means that if we have a power failure and replay the log tree we
end up getting the following file extent layout:
[ disk_bytenr X ] [ hole ] [ disk_bytenr Y ] [ hole ]
0 512K 512K 640K 640K 644K 644K 1M
Which does not corresponding to any layout the file ever had before
the power failure. The only two valid layouts would be:
[ disk_bytenr X ] [ hole ]
0 512K 512K 1M
and
[ disk_bytenr X ] [ hole ] [ disk_bytenr Z ] [ hole ]
0 512K 512K 640K 640K 644K 644K 1M
This can be fixed by serializing memory mapped writes with fsync, and there
are two ways to do it:
1) Make a fsync lock the entire file range, from 0 to (u64)-1 / LLONG_MAX
in the inode's io tree. This prevents the race but also blocks any reads
during the duration of the fsync, which has a negative impact for many
common workloads;
2) Make an fsync write lock the i_mmap_lock semaphore in the inode. This
semaphore was recently added by Josef's patch set:
btrfs: add a i_mmap_lock to our inode
btrfs: cleanup inode_lock/inode_unlock uses
btrfs: exclude mmaps while doing remap
btrfs: exclude mmap from happening during all fallocate operations
and is used to solve races between memory mapped writes and
clone/dedupe/fallocate. This also makes us have the same behaviour we
have regarding other writes (buffered and direct IO) and fsync - block
them while the inode logging is in progress.
This change uses the second approach due to the performance impact of the
first one.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
There's a small window where a deadlock can happen between fallocate and
mmap. This is described in detail by Filipe:
"""
When doing a fallocate operation we lock the inode, flush delalloc within
the target range, wait for any ordered extents to complete and then lock
the file range. Before we lock the range and after we flush delalloc,
there is a time window where another task can come in and do a memory
mapped write for a page within the fallocate range.
This means that after fallocate locks the range, there can be a dirty page
in the range. More often than not, this does not cause any problem.
The exception is when we are low on available metadata space, because an
fallocate operation needs to start a transaction while holding the file
range locked, either through btrfs_prealloc_file_range() or through the
call to btrfs_fallocate_update_isize(). If that's the case, we can end up
in a deadlock. The following list of steps explains how that happens:
1) A fallocate operation starts, locks the inode, flushes delalloc in the
range and waits for ordered extents in the range to complete;
2) Before the fallocate task locks the file range, another task does a
memory mapped write for a page in the fallocate target range. This is
possible since memory mapped writes do not (and can not) lock the
inode;
3) The fallocate task locks the file range. At this point there is one
dirty page in the range (due to the memory mapped write);
4) When the fallocate task attempts to start a transaction, it blocks when
attempting to reserve metadata space, since we are low on available
metadata space. Before blocking (wait on its reservation ticket), it
starts the async reclaim task (if not running already);
5) The async reclaim task is not able to release space through any other
means, so it decides to flush delalloc for inodes with dirty pages.
It finds that the inode used in the fallocate operation has a dirty
page and therefore queues a job (fs_info->flush_workers workqueue) to
flush delalloc for that inode and waits on that job to complete;
6) The flush job blocks when attempting to lock the file range because
it is currently locked by the fallocate task;
7) The fallocate task keeps waiting for its metadata reservation, waiting
for a wakeup on its reservation ticket. The async reclaim task is
waiting on the flush job, which in turn is waiting for locking the file
range that is currently locked by the fallocate task. So unless some
other task is able to release enough metadata space, for example an
ordered extent for some other inode completes, we end up in a deadlock
between all these tasks.
When this happens stack traces like the following show up in dmesg/syslog:
INFO: task kworker/u16:11:1810830 blocked for more than 120 seconds.
Tainted: G B W 5.10.0-rc4-btrfs-next-73 #1
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:kworker/u16:11 state:D stack: 0 pid:1810830 ppid: 2 flags:0x00004000
Workqueue: btrfs-flush_delalloc btrfs_work_helper [btrfs]
Call Trace:
__schedule+0x5d1/0xcf0
schedule+0x45/0xe0
lock_extent_bits+0x1e6/0x2d0 [btrfs]
? finish_wait+0x90/0x90
btrfs_invalidatepage+0x32c/0x390 [btrfs]
? __mod_memcg_state+0x8e/0x160
__extent_writepage+0x2d4/0x400 [btrfs]
extent_write_cache_pages+0x2b2/0x500 [btrfs]
? lock_release+0x20e/0x4c0
? trace_hardirqs_on+0x1b/0xf0
extent_writepages+0x43/0x90 [btrfs]
? lock_acquire+0x1a3/0x490
do_writepages+0x43/0xe0
? __filemap_fdatawrite_range+0xa4/0x100
__filemap_fdatawrite_range+0xc5/0x100
btrfs_run_delalloc_work+0x17/0x40 [btrfs]
btrfs_work_helper+0xf1/0x600 [btrfs]
process_one_work+0x24e/0x5e0
worker_thread+0x50/0x3b0
? process_one_work+0x5e0/0x5e0
kthread+0x153/0x170
? kthread_mod_delayed_work+0xc0/0xc0
ret_from_fork+0x22/0x30
INFO: task kworker/u16:1:2426217 blocked for more than 120 seconds.
Tainted: G B W 5.10.0-rc4-btrfs-next-73 #1
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:kworker/u16:1 state:D stack: 0 pid:2426217 ppid: 2 flags:0x00004000
Workqueue: events_unbound btrfs_async_reclaim_metadata_space [btrfs]
Call Trace:
__schedule+0x5d1/0xcf0
? kvm_clock_read+0x14/0x30
? wait_for_completion+0x81/0x110
schedule+0x45/0xe0
schedule_timeout+0x30c/0x580
? _raw_spin_unlock_irqrestore+0x3c/0x60
? lock_acquire+0x1a3/0x490
? try_to_wake_up+0x7a/0xa20
? lock_release+0x20e/0x4c0
? lock_acquired+0x199/0x490
? wait_for_completion+0x81/0x110
wait_for_completion+0xab/0x110
start_delalloc_inodes+0x2af/0x390 [btrfs]
btrfs_start_delalloc_roots+0x12d/0x250 [btrfs]
flush_space+0x24f/0x660 [btrfs]
btrfs_async_reclaim_metadata_space+0x1bb/0x480 [btrfs]
process_one_work+0x24e/0x5e0
worker_thread+0x20f/0x3b0
? process_one_work+0x5e0/0x5e0
kthread+0x153/0x170
? kthread_mod_delayed_work+0xc0/0xc0
ret_from_fork+0x22/0x30
(...)
several tasks waiting for the inode lock held by the fallocate task below
(...)
RIP: 0033:0x7f61efe73fff
Code: Unable to access opcode bytes at RIP 0x7f61efe73fd5.
RSP: 002b:00007ffc3371bbe8 EFLAGS: 00000202 ORIG_RAX: 000000000000013c
RAX: ffffffffffffffda RBX: 00007ffc3371bea0 RCX: 00007f61efe73fff
RDX: 00000000ffffff9c RSI: 0000560fbd5d90a0 RDI: 00000000ffffff9c
RBP: 00007ffc3371beb0 R08: 0000000000000001 R09: 0000000000000003
R10: 0000560fbd5d7ad0 R11: 0000000000000202 R12: 0000000000000001
R13: 000000000000005e R14: 00007ffc3371bea0 R15: 00007ffc3371beb0
task:fdm-stress state:D stack: 0 pid:2508243 ppid:2508153 flags:0x00000000
Call Trace:
__schedule+0x5d1/0xcf0
? _raw_spin_unlock_irqrestore+0x3c/0x60
schedule+0x45/0xe0
__reserve_bytes+0x4a4/0xb10 [btrfs]
? finish_wait+0x90/0x90
btrfs_reserve_metadata_bytes+0x29/0x190 [btrfs]
btrfs_block_rsv_add+0x1f/0x50 [btrfs]
start_transaction+0x2d1/0x760 [btrfs]
btrfs_replace_file_extents+0x120/0x930 [btrfs]
? btrfs_fallocate+0xdcf/0x1260 [btrfs]
btrfs_fallocate+0xdfb/0x1260 [btrfs]
? filename_lookup+0xf1/0x180
vfs_fallocate+0x14f/0x440
ioctl_preallocate+0x92/0xc0
do_vfs_ioctl+0x66b/0x750
? __do_sys_newfstat+0x53/0x60
__x64_sys_ioctl+0x62/0xb0
do_syscall_64+0x33/0x80
entry_SYSCALL_64_after_hwframe+0x44/0xa9
"""
Fix this by disallowing mmaps from happening while we're doing any of
the fallocate operations on this inode.
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
A few places we intermix btrfs_inode_lock with a inode_unlock, and some
places we just use inode_lock/inode_unlock instead of btrfs_inode_lock.
None of these places are using this incorrectly, but as we adjust some
of these callers it would be nice to keep everything consistent, so
convert everybody to use btrfs_inode_lock/btrfs_inode_unlock.
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
-----BEGIN PGP SIGNATURE-----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=tlU3
-----END PGP SIGNATURE-----
Merge tag 'for-5.12-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs fixes from David Sterba:
"More regression fixes and stabilization.
Regressions:
- zoned mode
- count zone sizes in wider int types
- fix space accounting for read-only block groups
- subpage: fix page tail zeroing
Fixes:
- fix spurious warning when remounting with free space tree
- fix warning when creating a directory with smack enabled
- ioctl checks for qgroup inheritance when creating a snapshot
- qgroup
- fix missing unlock on error path in zero range
- fix amount of released reservation on error
- fix flushing from unsafe context with open transaction,
potentially deadlocking
- minor build warning fixes"
* tag 'for-5.12-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
btrfs: zoned: do not account freed region of read-only block group as zone_unusable
btrfs: zoned: use sector_t for zone sectors
btrfs: subpage: fix the false data csum mismatch error
btrfs: fix warning when creating a directory with smack enabled
btrfs: don't flush from btrfs_delayed_inode_reserve_metadata
btrfs: export and rename qgroup_reserve_meta
btrfs: free correct amount of space in btrfs_delayed_inode_reserve_metadata
btrfs: fix spurious free_space_tree remount warning
btrfs: validate qgroup inherit for SNAP_CREATE_V2 ioctl
btrfs: unlock extents in btrfs_zero_range in case of quota reservation errors
btrfs: ref-verify: use 'inline void' keyword ordering
If btrfs_qgroup_reserve_data returns an error (i.e quota limit reached)
the handling logic directly goes to the 'out' label without first
unlocking the extent range between lockstart, lockend. This results in
deadlocks as other processes try to lock the same extent.
Fixes: a7f8b1c2ac ("btrfs: file: reserve qgroup space after the hole punch range is locked")
CC: stable@vger.kernel.org # 5.10+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Rename generic_file_buffered_read to match the naming of filemap_fault,
also update the written parameter to a more descriptive name and improve
the kerneldoc comment.
Link: https://lkml.kernel.org/r/20210122160140.223228-18-willy@infradead.org
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Kent Overstreet <kent.overstreet@gmail.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
- Adjust the final parameter of iomap_dio_rw.
- Add a new flag to request that iomap directio writes return EAGAIN if
the write is not a pure overwrite within EOF; this will be used to
reduce lock contention with unaligned direct writes on XFS.
- Amend XFS' directio code to eliminate exclusive locking for unaligned
direct writes if the circumstances permit
-----BEGIN PGP SIGNATURE-----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=AR07
-----END PGP SIGNATURE-----
Merge tag 'iomap-5.12-merge-2' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux
Pull iomap updates from Darrick Wong:
"The big change in this cycle is some new code to make it possible for
XFS to try unaligned directio overwrites without taking locks. If the
block is fully written and within EOF (i.e. doesn't require any
further fs intervention) then we can let the unlocked write proceed.
If not, we fall back to synchronizing direct writes.
Summary:
- Adjust the final parameter of iomap_dio_rw.
- Add a new flag to request that iomap directio writes return EAGAIN
if the write is not a pure overwrite within EOF; this will be used
to reduce lock contention with unaligned direct writes on XFS.
- Amend XFS' directio code to eliminate exclusive locking for
unaligned direct writes if the circumstances permit"
* tag 'iomap-5.12-merge-2' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
xfs: reduce exclusive locking on unaligned dio
xfs: split the unaligned DIO write code out
xfs: improve the reflink_bounce_dio_write tracepoint
xfs: simplify the read/write tracepoints
xfs: remove the buffered I/O fallback assert
xfs: cleanup the read/write helper naming
xfs: make xfs_file_aio_write_checks IOCB_NOWAIT-aware
xfs: factor out a xfs_ilock_iocb helper
iomap: add a IOMAP_DIO_OVERWRITE_ONLY flag
iomap: pass a flags argument to iomap_dio_rw
iomap: rename the flags variable in __iomap_dio_rw
Enable zone append writing for zoned mode. When using zone append, a
bio is issued to the start of a target zone and the device decides to
place it inside the zone. Upon completion the device reports the actual
written position back to the host.
Three parts are necessary to enable zone append mode. First, modify the
bio to use REQ_OP_ZONE_APPEND in btrfs_submit_bio_hook() and adjust the
bi_sector to point the beginning of the zone.
Second, record the returned physical address (and disk/partno) to the
ordered extent in end_bio_extent_writepage() after the bio has been
completed. We cannot resolve the physical address to the logical address
because we can neither take locks nor allocate a buffer in this end_bio
context. So, we need to record the physical address to resolve it later
in btrfs_finish_ordered_io().
And finally, rewrite the logical addresses of the extent mapping and
checksum data according to the physical address using btrfs_rmap_block.
If the returned address matches the originally allocated address, we can
skip this rewriting process.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
To support subpage sector size, data also need extra info to make sure
which sectors in a page are uptodate/dirty/...
This patch will make pages for data inodes get btrfs_subpage structure
attached, and detached when the page is freed.
This patch also slightly changes the timing when
set_page_extent_mapped() is called to make sure:
- We have page->mapping set
page->mapping->host is used to grab btrfs_fs_info, thus we can only
call this function after page is mapped to an inode.
One call site attaches pages to inode manually, thus we have to modify
the timing of set_page_extent_mapped() a bit.
- As soon as possible, before other operations
Since memory allocation can fail, we have to do extra error handling.
Calling set_page_extent_mapped() as soon as possible can simply the
error handling for several call sites.
The idea is pretty much the same as iomap_page, but with more bitmaps
for btrfs specific cases.
Currently the plan is to switch iomap if iomap can provide sector
aligned write back (only write back dirty sectors, but not the full
page, data balance require this feature).
So we will stick to btrfs specific bitmap for now.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Often an fsync needs to fallback to a transaction commit for several
reasons (to ensure consistency after a power failure, a new block group
was allocated or a temporary error such as ENOMEM or ENOSPC happened).
In that case the log is marked as needing a full commit and any concurrent
tasks attempting to log inodes or commit the log will also fallback to the
transaction commit. When this happens they all wait for the task that first
started the transaction commit to finish the transaction commit - however
they wait until the full transaction commit happens, which is not needed,
as they only need to wait for the superblocks to be persisted and not for
unpinning all the extents pinned during the transaction's lifetime, which
even for short lived transactions can be a few thousand and take some
significant amount of time to complete - for dbench workloads I have
observed up to 4~5 milliseconds of time spent unpinning extents in the
worst cases, and the number of pinned extents was between 2 to 3 thousand.
So allow fsync tasks to skip waiting for the unpinning of extents when
they call btrfs_commit_transaction() and they were not the task that
started the transaction commit (that one has to do it, the alternative
would be to offload the transaction commit to another task so that it
could avoid waiting for the extent unpinning or offload the extent
unpinning to another task).
This patch is part of a patchset comprised of the following patches:
btrfs: remove unnecessary directory inode item update when deleting dir entry
btrfs: stop setting nbytes when filling inode item for logging
btrfs: avoid logging new ancestor inodes when logging new inode
btrfs: skip logging directories already logged when logging all parents
btrfs: skip logging inodes already logged when logging new entries
btrfs: remove unnecessary check_parent_dirs_for_sync()
btrfs: make concurrent fsyncs wait less when waiting for a transaction commit
After applying the entire patchset, dbench shows improvements in respect
to throughput and latency. The script used to measure it is the following:
$ cat dbench-test.sh
#!/bin/bash
DEV=/dev/sdk
MNT=/mnt/sdk
MOUNT_OPTIONS="-o ssd"
MKFS_OPTIONS="-m single -d single"
echo "performance" | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
umount $DEV &> /dev/null
mkfs.btrfs -f $MKFS_OPTIONS $DEV
mount $MOUNT_OPTIONS $DEV $MNT
dbench -D $MNT -t 300 64
umount $MNT
The test was run on a physical machine with 12 cores (Intel corei7), 64G
of ram, using a NVMe device and a non-debug kernel configuration (Debian's
default configuration).
Before applying patchset, 32 clients:
Operation Count AvgLat MaxLat
----------------------------------------
NTCreateX 9627107 0.153 61.938
Close 7072076 0.001 3.175
Rename 407633 1.222 44.439
Unlink 1943895 0.658 44.440
Deltree 256 17.339 110.891
Mkdir 128 0.003 0.009
Qpathinfo 8725406 0.064 17.850
Qfileinfo 1529516 0.001 2.188
Qfsinfo 1599884 0.002 1.457
Sfileinfo 784200 0.005 3.562
Find 3373513 0.411 30.312
WriteX 4802132 0.053 29.054
ReadX 15089959 0.002 5.801
LockX 31344 0.002 0.425
UnlockX 31344 0.001 0.173
Flush 674724 5.952 341.830
Throughput 1008.02 MB/sec 32 clients 32 procs max_latency=341.833 ms
After applying patchset, 32 clients:
After patchset, with 32 clients:
Operation Count AvgLat MaxLat
----------------------------------------
NTCreateX 9931568 0.111 25.597
Close 7295730 0.001 2.171
Rename 420549 0.982 49.714
Unlink 2005366 0.497 39.015
Deltree 256 11.149 89.242
Mkdir 128 0.002 0.014
Qpathinfo 9001863 0.049 20.761
Qfileinfo 1577730 0.001 2.546
Qfsinfo 1650508 0.002 3.531
Sfileinfo 809031 0.005 5.846
Find 3480259 0.309 23.977
WriteX 4952505 0.043 41.283
ReadX 15568127 0.002 5.476
LockX 32338 0.002 0.978
UnlockX 32338 0.001 2.032
Flush 696017 7.485 228.835
Throughput 1049.91 MB/sec 32 clients 32 procs max_latency=228.847 ms
--> +4.1% throughput, -39.6% max latency
Before applying patchset, 64 clients:
Operation Count AvgLat MaxLat
----------------------------------------
NTCreateX 8956748 0.342 108.312
Close 6579660 0.001 3.823
Rename 379209 2.396 81.897
Unlink 1808625 1.108 131.148
Deltree 256 25.632 172.176
Mkdir 128 0.003 0.018
Qpathinfo 8117615 0.131 55.916
Qfileinfo 1423495 0.001 2.635
Qfsinfo 1488496 0.002 5.412
Sfileinfo 729472 0.007 8.643
Find 3138598 0.855 78.321
WriteX 4470783 0.102 79.442
ReadX 14038139 0.002 7.578
LockX 29158 0.002 0.844
UnlockX 29158 0.001 0.567
Flush 627746 14.168 506.151
Throughput 924.738 MB/sec 64 clients 64 procs max_latency=506.154 ms
After applying patchset, 64 clients:
Operation Count AvgLat MaxLat
----------------------------------------
NTCreateX 9069003 0.303 43.193
Close 6662328 0.001 3.888
Rename 383976 2.194 46.418
Unlink 1831080 1.022 43.873
Deltree 256 24.037 155.763
Mkdir 128 0.002 0.005
Qpathinfo 8219173 0.137 30.233
Qfileinfo 1441203 0.001 3.204
Qfsinfo 1507092 0.002 4.055
Sfileinfo 738775 0.006 5.431
Find 3177874 0.936 38.170
WriteX 4526152 0.084 39.518
ReadX 14213562 0.002 24.760
LockX 29522 0.002 1.221
UnlockX 29522 0.001 0.694
Flush 635652 14.358 422.039
Throughput 990.13 MB/sec 64 clients 64 procs max_latency=422.043 ms
--> +6.8% throughput, -18.1% max latency
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
The original comment is from the initial merge, which has several
problems:
- No holes check any more
- No inline decision is made
Update the out-of-date comment with more correct one.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
First replace all inode instances with a pointer to btrfs_inode. This
removes multiple invocations of the BTRFS_I macro, subsequently remove
2 local variables as they are called only once and simply refer to
them directly.
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Pass a set of flags to iomap_dio_rw instead of the boolean
wait_for_completion argument. The IOMAP_DIO_FORCE_WAIT flag
replaces the wait_for_completion, but only needs to be passed
when the iocb isn't synchronous to start with to simplify the
callers.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
[djwong: rework xfs_file.c so that we can push iomap changes separately]
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
