f2fs: fix to wait on block writeback for post_read case
Linux
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| Linux Linux |
| No fix yet |
Linux
| Product | Affected | Fixed in |
|---|---|---|
| Linux Linux |
| No fix yet |
| Linux Linux |
|
|
In the Linux kernel, the following vulnerability has been resolved:
f2fs: fix to wait on block writeback for post_read case
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
From the CVE record · Linux
The Linux kernel's f2fs filesystem can miss a writeback wait when writing a compressed but unencrypted inode. If garbage collection and an in-place write occur out of order, old data can overwrite new data. The input does not specify an attacker access requirement or user interaction.
Check systems running the Linux kernel with f2fs, especially those using compressed but unencrypted inodes; affected versions are not specified.