linux-stable.git/fs/f2fs, branch v6.1.78

f2fs: add helper to check compression level

2024-02-16T18:06:31+00:00

commit c571fbb5b59a3741e48014faa92c2f14bc59fe50 upstream.

This patch adds a helper function to check if compression level is
valid.

Meanwhile, this patch fixes a reported issue [1]:

The issue is easily reproducible by:

1. dd if=/dev/zero of=test.img count=100 bs=1M
2. mkfs.f2fs -f -O compression,extra_attr ./test.img
3. mount -t f2fs -o compress_algorithm=zstd:6,compress_chksum,atgc,gc_merge,lazytime ./test.img /mnt

resulting in

[   60.789982] F2FS-fs (loop0): invalid zstd compress level: 6

A bugzilla report has been submitted in
https://bugzilla.kernel.org/show_bug.cgi?id=218471

[1] https://lore.kernel.org/lkml/ZcWDOjKEnPDxZ0Or@google.com/T/

The root cause is commit 00e120b5e4b5 ("f2fs: assign default compression
level") tries to check low boundary of compress level w/ zstd_min_clevel(),
however, since commit e0c1b49f5b67 ("lib: zstd: Upgrade to latest upstream
zstd version 1.4.10"), zstd supports negative compress level, it cast type
for negative value returned from zstd_min_clevel() to unsigned int in below
check condition, result in repored issue.

	if (level < zstd_min_clevel() || ...

This patch fixes this issue by casting type for level to int before
comparison.

Fixes: 00e120b5e4b5 ("f2fs: assign default compression level")
Signed-off-by: Sheng Yong 
Reviewed-by: Chao Yu 
Signed-off-by: Jaegeuk Kim 
Signed-off-by: Chao Yu 
Signed-off-by: Greg Kroah-Hartman

f2fs: fix to tag gcing flag on page during block migration

2024-02-05T20:12:56+00:00

[ Upstream commit 4961acdd65c956e97c1a000c82d91a8c1cdbe44b ]

It needs to add missing gcing flag on page during block migration,
in order to garantee migrated data be persisted during checkpoint,
otherwise out-of-order persistency between data and node may cause
data corruption after SPOR.

Similar issue was fixed by commit 2d1fe8a86bf5 ("f2fs: fix to tag
gcing flag on page during file defragment").

Signed-off-by: Chao Yu 
Signed-off-by: Jaegeuk Kim 
Signed-off-by: Sasha Levin

f2fs: fix write pointers on zoned device after roll forward

2024-02-05T20:12:55+00:00

[ Upstream commit 9dad4d964291295ef48243d4e03972b85138bc9f ]

1. do roll forward recovery
2. update current segments pointers
3. fix the entire zones' write pointers
4. do checkpoint

Reviewed-by: Daeho Jeong 
Signed-off-by: Jaegeuk Kim 
Signed-off-by: Sasha Levin

f2fs: fix to check return value of f2fs_reserve_new_block()

2024-02-05T20:12:54+00:00

[ Upstream commit 956fa1ddc132e028f3b7d4cf17e6bfc8cb36c7fd ]

Let's check return value of f2fs_reserve_new_block() in do_recover_data()
rather than letting it fails silently.

Also refactoring check condition on return value of f2fs_reserve_new_block()
as below:
- trigger f2fs_bug_on() only for ENOSPC case;
- use do-while statement to avoid redundant codes;

Signed-off-by: Chao Yu 
Signed-off-by: Jaegeuk Kim 
Signed-off-by: Sasha Levin

f2fs: fix to check return value of f2fs_recover_xattr_data

2024-01-25T23:27:36+00:00

[ Upstream commit 86d7d57a3f096c8349b32a0cd5f6f314e4416a6d ]

Should check return value of f2fs_recover_xattr_data in
__f2fs_setxattr rather than doing invalid retry if error happen.

Also just do set_page_dirty in f2fs_recover_xattr_data when
page is changed really.

Fixes: 50a472bbc79f ("f2fs: do not return EFSCORRUPTED, but try to run online repair")
Signed-off-by: Zhiguo Niu 
Reviewed-by: Chao Yu 
Signed-off-by: Jaegeuk Kim 
Signed-off-by: Sasha Levin

f2fs: fix to update iostat correctly in f2fs_filemap_fault()

2024-01-25T23:27:34+00:00

[ Upstream commit bb34cc6ca87ff78f9fb5913d7619dc1389554da6 ]

In f2fs_filemap_fault(), it fixes to update iostat info only if
VM_FAULT_LOCKED is tagged in return value of filemap_fault().

Fixes: 8b83ac81f428 ("f2fs: support read iostat")
Signed-off-by: Chao Yu 
Signed-off-by: Jaegeuk Kim 
Signed-off-by: Sasha Levin

f2fs: fix to check compress file in f2fs_move_file_range()

2024-01-25T23:27:34+00:00

[ Upstream commit fb9b65340c818875ea86464faf3c744bdce0055c ]

f2fs_move_file_range() doesn't support migrating compressed cluster
data, let's add the missing check condition and return -EOPNOTSUPP
for the case until we support it.

Fixes: 4c8ff7095bef ("f2fs: support data compression")
Signed-off-by: Chao Yu 
Signed-off-by: Jaegeuk Kim 
Signed-off-by: Sasha Levin

f2fs: fix to wait on block writeback for post_read case

2024-01-25T23:27:34+00:00

[ Upstream commit 55fdc1c24a1d6229fe0ecf31335fb9a2eceaaa00 ]

If inode is compressed, but not encrypted, it missed to call
f2fs_wait_on_block_writeback() to wait for GCed page writeback
in IPU write path.

Thread A				GC-Thread
					- f2fs_gc
					 - do_garbage_collect
					  - gc_data_segment
					   - move_data_block
					    - f2fs_submit_page_write
					     migrate normal cluster's block via
					     meta_inode's page cache
- f2fs_write_single_data_page
 - f2fs_do_write_data_page
  - f2fs_inplace_write_data
   - f2fs_submit_page_bio

IRQ
- f2fs_read_end_io
					IRQ
					old data overrides new data due to
					out-of-order GC and common IO.
					- f2fs_read_end_io

Fixes: 4c8ff7095bef ("f2fs: support data compression")
Signed-off-by: Chao Yu 
Signed-off-by: Jaegeuk Kim 
Signed-off-by: Sasha Levin

f2fs: fix to avoid dirent corruption

2024-01-25T23:27:32+00:00

[ Upstream commit 53edb549565f55ccd0bdf43be3d66ce4c2d48b28 ]

As Al reported in link[1]:

f2fs_rename()
...
	if (old_dir != new_dir && !whiteout)
		f2fs_set_link(old_inode, old_dir_entry,
					old_dir_page, new_dir);
	else
		f2fs_put_page(old_dir_page, 0);

You want correct inumber in the ".." link.  And cross-directory
rename does move the source to new parent, even if you'd been asked
to leave a whiteout in the old place.

[1] https://lore.kernel.org/all/20231017055040.GN800259@ZenIV/

With below testcase, it may cause dirent corruption, due to it missed
to call f2fs_set_link() to update ".." link to new directory.
- mkdir -p dir/foo
- renameat2 -w dir/foo bar

[ASSERT] (__chk_dots_dentries:1421)  --> Bad inode number[0x4] for '..', parent parent ino is [0x3]
[FSCK] other corrupted bugs                           [Fail]

Fixes: 7e01e7ad746b ("f2fs: support RENAME_WHITEOUT")
Cc: Jan Kara 
Reported-by: Al Viro 
Signed-off-by: Chao Yu 
Reviewed-by: Jan Kara 
Signed-off-by: Jaegeuk Kim 
Signed-off-by: Sasha Levin

f2fs: explicitly null-terminate the xattr list

2024-01-20T10:50:03+00:00

commit e26b6d39270f5eab0087453d9b544189a38c8564 upstream.

When setting an xattr, explicitly null-terminate the xattr list.  This
eliminates the fragile assumption that the unused xattr space is always
zeroed.

Signed-off-by: Eric Biggers 
Reviewed-by: Chao Yu 
Signed-off-by: Jaegeuk Kim 
Signed-off-by: Greg Kroah-Hartman