f2fs: avoid node page to be written twice in gc_node_segment

In gc_node_segment, if node page gc is run concurrently with node page
writeback, and check_valid_map and get_node_page run after page locked
and before cur_valid_map is updated as below, it is possible for the
page to be written twice unnecessarily.

			sync_node_pages
			  try_lock_page
			  ...
check_valid_map		  f2fs_write_node_page
			    ...
			    write_node_page
			      do_write_page
			        allocate_data_block
				  ...
				  refresh_sit_entry /* update cur_valid_map */
				  ...
			    ...
			    unlock_page
get_node_page
...
set_page_dirty
...
f2fs_put_page
  unlock_page

This can be solved via calling check_valid_map after get_node_page again.

Signed-off-by: Huang, Ying <ying.huang@intel.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 943a31d..075ea1e 100644 (file)
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -423,6 +423,12 @@ next_step:
                if (IS_ERR(node_page))
                        continue;
 
+               /* block may become invalid during get_node_page */
+               if (check_valid_map(sbi, segno, off) == 0) {
+                       f2fs_put_page(node_page, 1);
+                       continue;
+               }
+
                /* set page dirty and write it */
                if (gc_type == FG_GC) {
                        f2fs_wait_on_page_writeback(node_page, NODE);