linux.git/fs/f2fs, branch v6.11 Linux kernel source tree Merge tag 'f2fs-for-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs 2024-07-23T22:21:19+00:00 Linus Torvalds torvalds@linux-foundation.org 2024-07-23T22:21:19+00:00 5ad7ff8738b8bd238ca899df08badb1f61bcc39e Pull f2fs updates from Jaegeuk Kim: "A pretty small update including mostly minor bug fixes in zoned storage along with the large section support. Enhancements: - add support for FS_IOC_GETFSSYSFSPATH - enable atgc dynamically if conditions are met - use new ioprio Macro to get ckpt thread ioprio level - remove unreachable lazytime mount option parsing Bug fixes: - fix null reference error when checking end of zone - fix start segno of large section - fix to cover read extent cache access with lock - don't dirty inode for readonly filesystem - allocate a new section if curseg is not the first seg in its zone - only fragment segment in the same section - truncate preallocated blocks in f2fs_file_open() - fix to avoid use SSR allocate when do defragment - fix to force buffered IO on inline_data inode And some minor code clean-ups and sanity checks" * tag 'f2fs-for-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (26 commits) f2fs: clean up addrs_per_{inode,block}() f2fs: clean up F2FS_I() f2fs: use meta inode for GC of COW file f2fs: use meta inode for GC of atomic file f2fs: only fragment segment in the same section f2fs: fix to update user block counts in block_operations() f2fs: remove unreachable lazytime mount option parsing f2fs: fix null reference error when checking end of zone f2fs: fix start segno of large section f2fs: remove redundant sanity check in sanity_check_inode() f2fs: assign CURSEG_ALL_DATA_ATGC if blkaddr is valid f2fs: fix to use mnt_{want,drop}_write_file replace file_{start,end}_wrtie f2fs: clean up set REQ_RAHEAD given rac f2fs: enable atgc dynamically if conditions are met f2fs: fix to truncate preallocated blocks in f2fs_file_open() f2fs: fix to cover read extent cache access with lock f2fs: fix return value of f2fs_convert_inline_inode() f2fs: use new ioprio Macro to get ckpt thread ioprio level f2fs: fix to don't dirty inode for readonly filesystem f2fs: fix to avoid use SSR allocate when do defragment ... 
Pull f2fs updates from Jaegeuk Kim:
 "A pretty small update including mostly minor bug fixes in zoned
  storage along with the large section support.

  Enhancements:
   - add support for FS_IOC_GETFSSYSFSPATH
   - enable atgc dynamically if conditions are met
   - use new ioprio Macro to get ckpt thread ioprio level
   - remove unreachable lazytime mount option parsing

  Bug fixes:
   - fix null reference error when checking end of zone
   - fix start segno of large section
   - fix to cover read extent cache access with lock
   - don't dirty inode for readonly filesystem
   - allocate a new section if curseg is not the first seg in its zone
   - only fragment segment in the same section
   - truncate preallocated blocks in f2fs_file_open()
   - fix to avoid use SSR allocate when do defragment
   - fix to force buffered IO on inline_data inode

  And some minor code clean-ups and sanity checks"

* tag 'f2fs-for-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (26 commits)
  f2fs: clean up addrs_per_{inode,block}()
  f2fs: clean up F2FS_I()
  f2fs: use meta inode for GC of COW file
  f2fs: use meta inode for GC of atomic file
  f2fs: only fragment segment in the same section
  f2fs: fix to update user block counts in block_operations()
  f2fs: remove unreachable lazytime mount option parsing
  f2fs: fix null reference error when checking end of zone
  f2fs: fix start segno of large section
  f2fs: remove redundant sanity check in sanity_check_inode()
  f2fs: assign CURSEG_ALL_DATA_ATGC if blkaddr is valid
  f2fs: fix to use mnt_{want,drop}_write_file replace file_{start,end}_wrtie
  f2fs: clean up set REQ_RAHEAD given rac
  f2fs: enable atgc dynamically if conditions are met
  f2fs: fix to truncate preallocated blocks in f2fs_file_open()
  f2fs: fix to cover read extent cache access with lock
  f2fs: fix return value of f2fs_convert_inline_inode()
  f2fs: use new ioprio Macro to get ckpt thread ioprio level
  f2fs: fix to don't dirty inode for readonly filesystem
  f2fs: fix to avoid use SSR allocate when do defragment
  ...
Merge tag 'vfs-6.11.casefold' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs 2024-07-15T18:18:49+00:00 Linus Torvalds torvalds@linux-foundation.org 2024-07-15T18:18:49+00:00 4a051e4c21dfb1c65ef54c44a7a4d0e6845e24f6 Pull vfs casefolding updates from Christian Brauner: "This contains some work to simplify the handling of casefolded names: - Simplify the handling of casefolded names in f2fs and ext4 by keeping the names as a qstr to avoiding unnecessary conversions - Introduce a new generic_ci_match() libfs case-insensitive lookup helper and use it in both f2fs and ext4 allowing to remove the filesystem specific implementations - Remove a bunch of ifdefs by making the unicode build checks part of the code flow" * tag 'vfs-6.11.casefold' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: f2fs: Move CONFIG_UNICODE defguards into the code flow ext4: Move CONFIG_UNICODE defguards into the code flow f2fs: Reuse generic_ci_match for ci comparisons ext4: Reuse generic_ci_match for ci comparisons libfs: Introduce case-insensitive string comparison helper f2fs: Simplify the handling of cached casefolded names ext4: Simplify the handling of cached casefolded names 
Pull vfs casefolding updates from Christian Brauner:
 "This contains some work to simplify the handling of casefolded names:

   - Simplify the handling of casefolded names in f2fs and ext4 by
     keeping the names as a qstr to avoiding unnecessary conversions

   - Introduce a new generic_ci_match() libfs case-insensitive lookup
     helper and use it in both f2fs and ext4 allowing to remove the
     filesystem specific implementations

   - Remove a bunch of ifdefs by making the unicode build checks part of
     the code flow"

* tag 'vfs-6.11.casefold' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  f2fs: Move CONFIG_UNICODE defguards into the code flow
  ext4: Move CONFIG_UNICODE defguards into the code flow
  f2fs: Reuse generic_ci_match for ci comparisons
  ext4: Reuse generic_ci_match for ci comparisons
  libfs: Introduce case-insensitive string comparison helper
  f2fs: Simplify the handling of cached casefolded names
  ext4: Simplify the handling of cached casefolded names
f2fs: clean up addrs_per_{inode,block}() 2024-07-10T23:15:36+00:00 Chao Yu chao@kernel.org 2024-06-25T03:16:03+00:00 bed6b0317441d82c32506750ccd868d83850e6f4 Introduce a new help addrs_per_page() to wrap common code from addrs_per_inode() and addrs_per_block() for cleanup. Signed-off-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org> 
Introduce a new help addrs_per_page() to wrap common code
from addrs_per_inode() and addrs_per_block() for cleanup.

Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
f2fs: clean up F2FS_I() 2024-07-10T23:13:15+00:00 Chao Yu chao@kernel.org 2024-06-25T03:16:02+00:00 7309871c03be22bee843f6961dcce183f04d48a9 Use temporary variable instead of F2FS_I() for cleanup. Signed-off-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org> 
Use temporary variable instead of F2FS_I() for cleanup.

Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
f2fs: use meta inode for GC of COW file 2024-07-10T22:48:20+00:00 Sunmin Jeong s_min.jeong@samsung.com 2024-07-10T11:51:43+00:00 f18d0076933689775fe7faeeb10ee93ff01be6ab In case of the COW file, new updates and GC writes are already separated to page caches of the atomic file and COW file. As some cases that use the meta inode for GC, there are some race issues between a foreground thread and GC thread. To handle them, we need to take care when to invalidate and wait writeback of GC pages in COW files as the case of using the meta inode. Also, a pointer from the COW inode to the original inode is required to check the state of original pages. For the former, we can solve the problem by using the meta inode for GC of COW files. Then let's get a page from the original inode in move_data_block when GCing the COW file to avoid race condition. Fixes: 3db1de0e582c ("f2fs: change the current atomic write way") Cc: stable@vger.kernel.org #v5.19+ Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com> Reviewed-by: Yeongjin Gil <youngjin.gil@samsung.com> Signed-off-by: Sunmin Jeong <s_min.jeong@samsung.com> Reviewed-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org> 
In case of the COW file, new updates and GC writes are already
separated to page caches of the atomic file and COW file. As some cases
that use the meta inode for GC, there are some race issues between a
foreground thread and GC thread.

To handle them, we need to take care when to invalidate and wait
writeback of GC pages in COW files as the case of using the meta inode.
Also, a pointer from the COW inode to the original inode is required to
check the state of original pages.

For the former, we can solve the problem by using the meta inode for GC
of COW files. Then let's get a page from the original inode in
move_data_block when GCing the COW file to avoid race condition.

Fixes: 3db1de0e582c ("f2fs: change the current atomic write way")
Cc: stable@vger.kernel.org #v5.19+
Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
Reviewed-by: Yeongjin Gil <youngjin.gil@samsung.com>
Signed-off-by: Sunmin Jeong <s_min.jeong@samsung.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
f2fs: use meta inode for GC of atomic file 2024-07-10T22:48:04+00:00 Sunmin Jeong s_min.jeong@samsung.com 2024-07-10T11:51:17+00:00 b40a2b00370931b0c50148681dd7364573e52e6b The page cache of the atomic file keeps new data pages which will be stored in the COW file. It can also keep old data pages when GCing the atomic file. In this case, new data can be overwritten by old data if a GC thread sets the old data page as dirty after new data page was evicted. Also, since all writes to the atomic file are redirected to COW inodes, GC for the atomic file is not working well as below. f2fs_gc(gc_type=FG_GC) - select A as a victim segment do_garbage_collect - iget atomic file's inode for block B move_data_page f2fs_do_write_data_page - use dn of cow inode - set fio->old_blkaddr from cow inode - seg_freed is 0 since block B is still valid - goto gc_more and A is selected as victim again To solve the problem, let's separate GC writes and updates in the atomic file by using the meta inode for GC writes. Fixes: 3db1de0e582c ("f2fs: change the current atomic write way") Cc: stable@vger.kernel.org #v5.19+ Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com> Reviewed-by: Yeongjin Gil <youngjin.gil@samsung.com> Signed-off-by: Sunmin Jeong <s_min.jeong@samsung.com> Reviewed-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org> 
The page cache of the atomic file keeps new data pages which will be
stored in the COW file. It can also keep old data pages when GCing the
atomic file. In this case, new data can be overwritten by old data if a
GC thread sets the old data page as dirty after new data page was
evicted.

Also, since all writes to the atomic file are redirected to COW inodes,
GC for the atomic file is not working well as below.

f2fs_gc(gc_type=FG_GC)
  - select A as a victim segment
  do_garbage_collect
    - iget atomic file's inode for block B
    move_data_page
      f2fs_do_write_data_page
        - use dn of cow inode
        - set fio->old_blkaddr from cow inode
    - seg_freed is 0 since block B is still valid
  - goto gc_more and A is selected as victim again

To solve the problem, let's separate GC writes and updates in the atomic
file by using the meta inode for GC writes.

Fixes: 3db1de0e582c ("f2fs: change the current atomic write way")
Cc: stable@vger.kernel.org #v5.19+
Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
Reviewed-by: Yeongjin Gil <youngjin.gil@samsung.com>
Signed-off-by: Sunmin Jeong <s_min.jeong@samsung.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
f2fs: only fragment segment in the same section 2024-07-10T22:47:58+00:00 Sheng Yong shengyong@oppo.com 2024-07-10T01:26:59+00:00 e3a19972a49f61775e5e11ac43a663f28cdfb8b2 When new_curseg() is allocating a new segment, if mode=fragment:xxx is switched on in large section scenario, __get_next_segno() will select the next segno randomly in the range of [0, maxsegno] in order to fragment segments. If the candidate segno is free, get_new_segment() will use it directly as the new segment. However, if the section of the candidate is not empty, and some other segments have already been used, and have a different type (e.g NODE) with the candidate (e.g DATA), GC will complain inconsistent segment type later. This could be reproduced by the following steps: dd if=/dev/zero of=test.img bs=1M count=10240 mkfs.f2fs -s 128 test.img mount -t f2fs test.img /mnt -o mode=fragment:block echo 1 > /sys/fs/f2fs/loop0/max_fragment_chunk echo 512 > /sys/fs/f2fs/loop0/max_fragment_hole dd if=/dev/zero of=/mnt/testfile bs=4K count=100 umount /mnt F2FS-fs (loop0): Inconsistent segment (4377) type [0, 1] in SSA and SIT In order to allow simulating segment fragmentation in large section scenario, this patch reduces the candidate range: * if curseg is the last segment in the section, return curseg->segno to make get_new_segment() itself find the next free segment. * if curseg is in the middle of the section, select candicate randomly in the range of [curseg + 1, last_seg_in_the_same_section] to keep type consistent. Reviewed-by: Chao Yu <chao@kernel.org> Signed-off-by: Sheng Yong <shengyong@oppo.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org> 
When new_curseg() is allocating a new segment, if mode=fragment:xxx is
switched on in large section scenario, __get_next_segno() will select
the next segno randomly in the range of [0, maxsegno] in order to
fragment segments.

If the candidate segno is free, get_new_segment() will use it directly
as the new segment.

However, if the section of the candidate is not empty, and some other
segments have already been used, and have a different type (e.g NODE)
with the candidate (e.g DATA), GC will complain inconsistent segment
type later.

This could be reproduced by the following steps:

  dd if=/dev/zero of=test.img bs=1M count=10240
  mkfs.f2fs -s 128 test.img
  mount -t f2fs test.img /mnt -o mode=fragment:block
  echo 1 > /sys/fs/f2fs/loop0/max_fragment_chunk
  echo 512 > /sys/fs/f2fs/loop0/max_fragment_hole
  dd if=/dev/zero of=/mnt/testfile bs=4K count=100
  umount /mnt

  F2FS-fs (loop0): Inconsistent segment (4377) type [0, 1] in SSA and SIT

In order to allow simulating segment fragmentation in large section
scenario, this patch reduces the candidate range:
 * if curseg is the last segment in the section, return curseg->segno
   to make get_new_segment() itself find the next free segment.
 * if curseg is in the middle of the section, select candicate randomly
   in the range of [curseg + 1, last_seg_in_the_same_section] to keep
   type consistent.

Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Sheng Yong <shengyong@oppo.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
f2fs: fix to update user block counts in block_operations() 2024-07-10T22:47:57+00:00 Chao Yu chao@kernel.org 2024-06-25T02:32:39+00:00 f06c0f82e38bbda7264d6ef3c90045ad2810e0f3 Commit 59c9081bc86e ("f2fs: allow write page cache when writting cp") allows write() to write data to page cache during checkpoint, so block count fields like .total_valid_block_count, .alloc_valid_block_count and .rf_node_block_count may encounter race condition as below: CP Thread A - write_checkpoint - block_operations - f2fs_down_write(&sbi->node_change) - __prepare_cp_block : ckpt->valid_block_count = .total_valid_block_count - f2fs_up_write(&sbi->node_change) - write - f2fs_preallocate_blocks - f2fs_map_blocks(,F2FS_GET_BLOCK_PRE_AIO) - f2fs_map_lock - f2fs_down_read(&sbi->node_change) - f2fs_reserve_new_blocks - inc_valid_block_count : percpu_counter_add(&sbi->alloc_valid_block_count, count) : sbi->total_valid_block_count += count - f2fs_up_read(&sbi->node_change) - do_checkpoint : sbi->last_valid_block_count = sbi->total_valid_block_count : percpu_counter_set(&sbi->alloc_valid_block_count, 0) : percpu_counter_set(&sbi->rf_node_block_count, 0) - fsync - need_do_checkpoint - f2fs_space_for_roll_forward : alloc_valid_block_count was reset to zero, so, it may missed last data during checkpoint Let's change to update .total_valid_block_count, .alloc_valid_block_count and .rf_node_block_count in block_operations(), then their access can be protected by .node_change and .cp_rwsem lock, so that it can avoid above race condition. Fixes: 59c9081bc86e ("f2fs: allow write page cache when writting cp") Cc: Yunlei He <heyunlei@oppo.com> Signed-off-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org> 
Commit 59c9081bc86e ("f2fs: allow write page cache when writting cp")
allows write() to write data to page cache during checkpoint, so block
count fields like .total_valid_block_count, .alloc_valid_block_count
and .rf_node_block_count may encounter race condition as below:

CP				Thread A
- write_checkpoint
 - block_operations
  - f2fs_down_write(&sbi->node_change)
  - __prepare_cp_block
  : ckpt->valid_block_count = .total_valid_block_count
  - f2fs_up_write(&sbi->node_change)
				- write
				 - f2fs_preallocate_blocks
				  - f2fs_map_blocks(,F2FS_GET_BLOCK_PRE_AIO)
				   - f2fs_map_lock
				    - f2fs_down_read(&sbi->node_change)
				   - f2fs_reserve_new_blocks
				    - inc_valid_block_count
				    : percpu_counter_add(&sbi->alloc_valid_block_count, count)
				    : sbi->total_valid_block_count += count
				    - f2fs_up_read(&sbi->node_change)
 - do_checkpoint
 : sbi->last_valid_block_count = sbi->total_valid_block_count
 : percpu_counter_set(&sbi->alloc_valid_block_count, 0)
 : percpu_counter_set(&sbi->rf_node_block_count, 0)
				- fsync
				 - need_do_checkpoint
				  - f2fs_space_for_roll_forward
				  : alloc_valid_block_count was reset to zero,
				    so, it may missed last data during checkpoint

Let's change to update .total_valid_block_count, .alloc_valid_block_count
and .rf_node_block_count in block_operations(), then their access can be
protected by .node_change and .cp_rwsem lock, so that it can avoid above
race condition.

Fixes: 59c9081bc86e ("f2fs: allow write page cache when writting cp")
Cc: Yunlei He <heyunlei@oppo.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
f2fs: remove unreachable lazytime mount option parsing 2024-07-10T22:47:57+00:00 Eric Sandeen sandeen@redhat.com 2024-06-29T04:38:17+00:00 54f43a10fa257ad4af02a1d157fefef6ebcfa7dc The lazytime/nolazytime options are now handled in the VFS, and are never seen in filesystem parsers, so remove handling of these options from f2fs. Note: when lazytime support was added in 6d94c74ab85f it made lazytime the default in default_options() - as a result, lazytime cannot be disabled (because Opt_nolazytime is never seen in f2fs parsing). If lazytime is desired to be configurable, and default off is OK, default_options() could be updated to stop setting it by default and allow mount option control. Signed-off-by: Eric Sandeen <sandeen@redhat.com> Reviewed-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org> 
The lazytime/nolazytime options are now handled in the VFS, and are
never seen in filesystem parsers, so remove handling of these
options from f2fs.

Note: when lazytime support was added in 6d94c74ab85f it made
lazytime the default in default_options() - as a result, lazytime
cannot be disabled (because Opt_nolazytime is never seen in f2fs
parsing).

If lazytime is desired to be configurable, and default off is OK,
default_options() could be updated to stop setting it by default
and allow mount option control.

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
f2fs: fix null reference error when checking end of zone 2024-07-10T22:47:57+00:00 Daejun Park daejun7.park@samsung.com 2024-07-04T01:01:21+00:00 c82bc1ab2a8a5e73d9728e80c4c2ed87e8921a38 This patch fixes a potentially null pointer being accessed by is_end_zone_blkaddr() that checks the last block of a zone when f2fs is mounted as a single device. Fixes: e067dc3c6b9c ("f2fs: maintain six open zones for zoned devices") Signed-off-by: Daejun Park <daejun7.park@samsung.com> Reviewed-by: Chao Yu <chao@kernel.org> Reviewed-by: Daeho Jeong <daehojeong@google.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org> 
This patch fixes a potentially null pointer being accessed by
is_end_zone_blkaddr() that checks the last block of a zone
when f2fs is mounted as a single device.

Fixes: e067dc3c6b9c ("f2fs: maintain six open zones for zoned devices")
Signed-off-by: Daejun Park <daejun7.park@samsung.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Reviewed-by: Daeho Jeong <daehojeong@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>