f2fs: prevent checkpoint once any IO failure is detected

This patch enhances the checkpoint routine to cope with IO errors.

Basically f2fs detects IO errors from end_io_write, and the errors are able to
be occurred during one of data, node, and meta page writes.

In the previous code, when an IO error is occurred during writes, f2fs sets a
flag, CP_ERROR_FLAG, in the raw ckeckpoint buffer which will be written to disk.
Afterwards, write_checkpoint() will check the flag and remount f2fs as a
read-only (ro) mode.

However, even once f2fs is remounted as a ro mode, dirty checkpoint pages are
freely able to be written to disk by flusher or kswapd in background.
In such a case, after cold reboot, f2fs would restore the checkpoint data having
CP_ERROR_FLAG, resulting in disabling write_checkpoint and remounting f2fs as
a ro mode again.

Therefore, let's prevent any checkpoint page (meta) writes once an IO error is
occurred, and remount f2fs as a ro mode right away at that moment.

Reported-by: Oliver Winker <oliver@oli1170.net>
Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
Reviewed-by: Namjae Jeon <namjae.jeon@samsung.com>

1 files changed, 19 insertions, 17 deletions

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index ff3c843..9c16271 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -72,22 +72,22 @@ static int f2fs_write_meta_page(struct page *page,
 {
 	struct inode *inode = page->mapping->host;
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
-	int err;
 
-	wait_on_page_writeback(page);
-
-	err = write_meta_page(sbi, page, wbc);
-	if (err) {
+	/* Should not write any meta pages, if any IO error was occurred */
+	if (wbc->for_reclaim ||
+			is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ERROR_FLAG)) {
+		dec_page_count(sbi, F2FS_DIRTY_META);
 		wbc->pages_skipped++;
 		set_page_dirty(page);
+		return AOP_WRITEPAGE_ACTIVATE;
 	}
 
-	dec_page_count(sbi, F2FS_DIRTY_META);
+	wait_on_page_writeback(page);
 
-	/* In this case, we should not unlock this page */
-	if (err != AOP_WRITEPAGE_ACTIVATE)
-		unlock_page(page);
-	return err;
+	write_meta_page(sbi, page);
+	dec_page_count(sbi, F2FS_DIRTY_META);
+	unlock_page(page);
+	return 0;
 }
 
 static int f2fs_write_meta_pages(struct address_space *mapping,
@@ -138,7 +138,10 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
 			BUG_ON(page->mapping != mapping);
 			BUG_ON(!PageDirty(page));
 			clear_page_dirty_for_io(page);
-			f2fs_write_meta_page(page, &wbc);
+			if (f2fs_write_meta_page(page, &wbc)) {
+				unlock_page(page);
+				break;
+			}
 			if (nwritten++ >= nr_to_write)
 				break;
 		}
@@ -717,13 +720,12 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 	sbi->alloc_valid_block_count = 0;
 
 	/* Here, we only have one bio having CP pack */
-	if (is_set_ckpt_flags(ckpt, CP_ERROR_FLAG))
-		sbi->sb->s_flags |= MS_RDONLY;
-	else
-		sync_meta_pages(sbi, META_FLUSH, LONG_MAX);
+	sync_meta_pages(sbi, META_FLUSH, LONG_MAX);
 
-	clear_prefree_segments(sbi);
-	F2FS_RESET_SB_DIRT(sbi);
+	if (!is_set_ckpt_flags(ckpt, CP_ERROR_FLAG)) {
+		clear_prefree_segments(sbi);
+		F2FS_RESET_SB_DIRT(sbi);
+	}
 }
 
 /*