From 7633a7387eb4d0259d6bea945e1d3469cd135bbc Mon Sep 17 00:00:00 2001 From: Yongpeng Yang Date: Tue, 6 Jan 2026 20:12:11 +0800 Subject: [PATCH] f2fs: fix IS_CHECKPOINTED flag inconsistency issue caused by concurrent atomic commit and checkpoint writes During SPO tests, when mounting F2FS, an -EINVAL error was returned from f2fs_recover_inode_page. The issue occurred under the following scenario Thread A Thread B f2fs_ioc_commit_atomic_write - f2fs_do_sync_file // atomic = true - f2fs_fsync_node_pages : last_folio = inode folio : schedule before folio_lock(last_folio) f2fs_write_checkpoint - block_operations// writeback last_folio - schedule before f2fs_flush_nat_entries : set_fsync_mark(last_folio, 1) : set_dentry_mark(last_folio, 1) : folio_mark_dirty(last_folio) - __write_node_folio(last_folio) : f2fs_down_read(&sbi->node_write)//block - f2fs_flush_nat_entries : {struct nat_entry}->flag |= BIT(IS_CHECKPOINTED) - unblock_operations : f2fs_up_write(&sbi->node_write) f2fs_write_checkpoint//return : f2fs_do_write_node_page() f2fs_ioc_commit_atomic_write//return SPO Thread A calls f2fs_need_dentry_mark(sbi, ino), and the last_folio has already been written once. However, the {struct nat_entry}->flag did not have the IS_CHECKPOINTED set, causing set_dentry_mark(last_folio, 1) and write last_folio again after Thread B finishes f2fs_write_checkpoint. After SPO and reboot, it was detected that {struct node_info}->blk_addr was not NULL_ADDR because Thread B successfully write the checkpoint. This issue only occurs in atomic write scenarios. For regular file fsync operations, the folio must be dirty. If block_operations->f2fs_sync_node_pages successfully submit the folio write, this path will not be executed. Otherwise, the f2fs_write_checkpoint will need to wait for the folio write submission to complete, as sbi->nr_pages[F2FS_DIRTY_NODES] > 0. Therefore, the situation where f2fs_need_dentry_mark checks that the {struct nat_entry}->flag /wo the IS_CHECKPOINTED flag, but the folio write has already been submitted, will not occur. Therefore, for atomic file fsync, sbi->node_write should be acquired through __write_node_folio to ensure that the IS_CHECKPOINTED flag correctly indicates that the checkpoint write has been completed. Fixes: 608514deba38 ("f2fs: set fsync mark only for the last dnode") Cc: stable@kernel.org Signed-off-by: Sheng Yong Signed-off-by: Jinbao Liu Signed-off-by: Yongpeng Yang Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/node.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index d378549010e6..99e425e8c00a 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1786,8 +1786,13 @@ static bool __write_node_folio(struct folio *folio, bool atomic, bool *submitted goto redirty_out; } - if (atomic && !test_opt(sbi, NOBARRIER)) - fio.op_flags |= REQ_PREFLUSH | REQ_FUA; + if (atomic) { + if (!test_opt(sbi, NOBARRIER)) + fio.op_flags |= REQ_PREFLUSH | REQ_FUA; + if (IS_INODE(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)) { @@ -1928,8 +1933,9 @@ continue_unlock: if (is_inode_flag_set(inode, FI_DIRTY_INODE)) f2fs_update_inode(inode, folio); - set_dentry_mark(folio, - f2fs_need_dentry_mark(sbi, ino)); + if (!atomic) + set_dentry_mark(folio, + f2fs_need_dentry_mark(sbi, ino)); } /* may be written by other thread */ if (!folio_test_dirty(folio)) -- 2.47.3