fs-writeback: do not requeue a clean inode having skipped pages

When writing back an inode and performing an fsync on it concurrently, a
deadlock issue may arise as shown below. In each writeback iteration, a
clean inode is requeued to the wb->b_dirty queue due to non-zero
pages_skipped, without anything actually being written. This causes an
infinite loop and prevents the plug from being flushed, resulting in a
deadlock. We now avoid requeuing the clean inode to prevent this issue.

    wb_writeback        fsync (inode-Y)
blk_start_plug(&plug)
for (;;) {
  iter i-1: some reqs with page-X added into plug->mq_list // f2fs node page-X with PG_writeback
                        filemap_fdatawrite
                          __filemap_fdatawrite_range // write inode-Y with sync_mode WB_SYNC_ALL
                           do_writepages
                            f2fs_write_data_pages
                             __f2fs_write_data_pages // wb_sync_req[DATA]++ for WB_SYNC_ALL
                              f2fs_write_cache_pages
                               f2fs_write_single_data_page
                                f2fs_do_write_data_page
                                 f2fs_outplace_write_data
                                  f2fs_update_data_blkaddr
                                   f2fs_wait_on_page_writeback
                                     wait_on_page_writeback // wait for f2fs node page-X
  iter i:
    progress = __writeback_inodes_wb(wb, work)
    . writeback_sb_inodes
    .   __writeback_single_inode // write inode-Y with sync_mode WB_SYNC_NONE
    .   . do_writepages
    .   .   f2fs_write_data_pages
    .   .   .  __f2fs_write_data_pages // skip writepages due to (wb_sync_req[DATA]>0)
    .   .   .   wbc->pages_skipped += get_dirty_pages(inode) // wbc->pages_skipped = 1
    .   if (!(inode->i_state & I_DIRTY_ALL)) // i_state = I_SYNC | I_SYNC_QUEUED
    .    total_wrote++;  // total_wrote = 1
    .   requeue_inode // requeue inode-Y to wb->b_dirty queue due to non-zero pages_skipped
    if (progress) // progress = 1
      continue;
  iter i+1:
      queue_io
      // similar process with iter i, infinite for-loop !
}
blk_finish_plug(&plug)   // flush plug won't be called
Signed-off-by: Chunhai Guo <guochunhai@vivo.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Message-Id: <20230916045131.957929-1-guochunhai@vivo.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>

fs/fs-writeback.c

@@ -1535,10 +1535,15 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
 
 	if (wbc->pages_skipped) {
 		/*
-		 * writeback is not making progress due to locked
-		 * buffers. Skip this inode for now.
+		 * Writeback is not making progress due to locked buffers.
+		 * Skip this inode for now. Although having skipped pages
+		 * is odd for clean inodes, it can happen for some
+		 * filesystems so handle that gracefully.
 		 */
-		redirty_tail_locked(inode, wb);
+		if (inode->i_state & I_DIRTY_ALL)
+			redirty_tail_locked(inode, wb);
+		else
+			inode_cgwb_move_to_attached(inode, wb);
 		return;
 	}