f2fs: fix fsck inconsistency caused by incorrect nat_entry flag usage

commit 019f9dda7f66e55eb94cd32e1d3fff5835f73fbc upstream.

f2fs_need_dentry_mark() reads nat_entry flags without mutual exclusion
with the checkpoint path, which can result in an incorrect inode block
marking state. The scenario is as follows:

create & write & fsync 'file A'                 write checkpoint
- f2fs_do_sync_file // inline inode
 - f2fs_write_inode // inode folio is dirty
                                                - f2fs_write_checkpoint
                                                 - f2fs_flush_merged_writes
                                                 - f2fs_sync_node_pages
 - f2fs_fsync_node_pages // no dirty node
 - f2fs_need_inode_block_update // return true
 - f2fs_fsync_node_pages // inode dirtied
  - f2fs_need_dentry_mark //return true
                                                 - f2fs_flush_nat_entries
                                                - f2fs_write_checkpoint end
  - __write_node_folio // inode with DENT_BIT_SHIFT set
  SPO, "fsck --dry-run" find inode has already checkpointed but still
  with DENT_BIT_SHIFT set

The state observed by f2fs_need_dentry_mark() can differ from the state
observed in __write_node_folio() after acquiring sbi->node_write. The
root cause is that the semantics of IS_CHECKPOINTED and
HAS_FSYNCED_INODE are only guaranteed after the checkpoint write has
fully completed.

This patch moves set_dentry_mark() into __write_node_folio() and
protects it with the sbi->node_write lock.

Cc: stable@kernel.org
Fixes: 88bd02c9472a ("f2fs: fix conditions to remain recovery information in f2fs_sync_file")
Signed-off-by: Yongpeng Yang <yangyongpeng@xiaomi.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 74992fd9c9b660eeb8dcca569b657acc3041470a..c3842035253c55977ffe1f7bccf24c40b192f20b 100644 (file)
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1801,13 +1801,12 @@ static bool __write_node_folio(struct folio *folio, bool atomic, bool *submitted
                goto redirty_out;
        }
 
-       if (atomic) {
-               if (!test_opt(sbi, NOBARRIER))
-                       fio.op_flags |= REQ_PREFLUSH | REQ_FUA;
-               if (IS_INODE(folio))
-                       set_dentry_mark(folio,
+       if (atomic && !test_opt(sbi, NOBARRIER))
+               fio.op_flags |= REQ_PREFLUSH | REQ_FUA;
+
+       if (IS_INODE(folio) && (atomic || is_fsync_dnode(folio)))
+               set_dentry_mark(folio,
                                f2fs_need_dentry_mark(sbi, ino_of_node(folio)));
-       }
 
        /* should add to global list before clearing PAGECACHE status */
        if (f2fs_in_warm_node_list(sbi, folio)) {
@@ -1948,9 +1947,6 @@ continue_unlock:
                                        if (is_inode_flag_set(inode,
                                                                FI_DIRTY_INODE))
                                                f2fs_update_inode(inode, folio);
-                                       if (!atomic)
-                                               set_dentry_mark(folio,
-                                                       f2fs_need_dentry_mark(sbi, ino));
                                }
                                /* may be written by other thread */
                                if (!folio_test_dirty(folio))