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>

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;
+
+	/* 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;
+	}
 
 	wait_on_page_writeback(page);
 
-	err = write_meta_page(sbi, page, wbc);
-	if (err) {
-		wbc->pages_skipped++;
-		set_page_dirty(page);
-	}
-
+	write_meta_page(sbi, page);
 	dec_page_count(sbi, F2FS_DIRTY_META);
-
-	/* In this case, we should not unlock this page */
-	if (err != AOP_WRITEPAGE_ACTIVATE)
-		unlock_page(page);
-	return err;
+	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);
+	}
 }
 
 /*

fs/f2fs/f2fs.h

@@ -929,8 +929,7 @@ void allocate_new_segments(struct f2fs_sb_info *);
 struct page *get_sum_page(struct f2fs_sb_info *, unsigned int);
 struct bio *f2fs_bio_alloc(struct block_device *, int);
 void f2fs_submit_bio(struct f2fs_sb_info *, enum page_type, bool sync);
-int write_meta_page(struct f2fs_sb_info *, struct page *,
-					struct writeback_control *);
+void write_meta_page(struct f2fs_sb_info *, struct page *);
 void write_node_page(struct f2fs_sb_info *, struct page *, unsigned int,
 					block_t, block_t *);
 void write_data_page(struct inode *, struct page *, struct dnode_of_data*,

fs/f2fs/segment.c

@@ -600,6 +600,7 @@ static void f2fs_end_io_write(struct bio *bio, int err)
 			if (page->mapping)
 				set_bit(AS_EIO, &page->mapping->flags);
 			set_ckpt_flags(p->sbi->ckpt, CP_ERROR_FLAG);
+			p->sbi->sb->s_flags |= MS_RDONLY;
 		}
 		end_page_writeback(page);
 		dec_page_count(p->sbi, F2FS_WRITEBACK);
@@ -815,15 +816,10 @@ static void do_write_page(struct f2fs_sb_info *sbi, struct page *page,
 	mutex_unlock(&curseg->curseg_mutex);
 }
 
-int write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
-			struct writeback_control *wbc)
+void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
 {
-	if (wbc->for_reclaim)
-		return AOP_WRITEPAGE_ACTIVATE;
-
 	set_page_writeback(page);
 	submit_write_page(sbi, page, page->index, META);
-	return 0;
 }
 
 void write_node_page(struct f2fs_sb_info *sbi, struct page *page,

fs/f2fs/super.c

@@ -387,10 +387,11 @@ static int sanity_check_raw_super(struct super_block *sb,
 	return 0;
 }
 
-static int sanity_check_ckpt(struct f2fs_super_block *raw_super,
-				struct f2fs_checkpoint *ckpt)
+static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 {
 	unsigned int total, fsmeta;
+	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
+	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
 
 	total = le32_to_cpu(raw_super->segment_count);
 	fsmeta = le32_to_cpu(raw_super->segment_count_ckpt);
@@ -401,6 +402,11 @@ static int sanity_check_ckpt(struct f2fs_super_block *raw_super,
 
 	if (fsmeta >= total)
 		return 1;
+
+	if (is_set_ckpt_flags(ckpt, CP_ERROR_FLAG)) {
+		f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck");
+		return 1;
+	}
 	return 0;
 }
 
@@ -525,7 +531,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 
 	/* sanity checking of checkpoint */
 	err = -EINVAL;
-	if (sanity_check_ckpt(raw_super, sbi->ckpt)) {
+	if (sanity_check_ckpt(sbi)) {
 		f2fs_msg(sb, KERN_ERR, "Invalid F2FS checkpoint");
 		goto free_cp;
 	}