[PATCH] f2fs: fix roll-forward missing scenarios

[Jaegeuk Kim]

We can summarize the roll forward recovery scenarios as follows.

[Term] F: fsync_mark, D: dentry_mark

1. inode(x) | CP | inode(x) | dnode(F)
-> Update the latest inode(x).

2. inode(x) | CP | inode(F) | dnode(F)
-> No problem.

3. inode(x) | CP | dnode(F) | inode(x)
-> Impossible, but recover latest dnode(F)

4. inode(x) | CP | dnode(F) | inode(F)
-> No problem.

5. CP | inode(x) | dnode(F)
-> Impossible. Write inode(DF) with dnode(F) by f2fs_sync_file.

6. CP | inode(DF) | dnode(F)
-> No problem.

7. CP | dnode(F) | inode(DF)
-> If f2fs_iget fails, then goto next to find inode(DF).

8. CP | dnode(F) | inode(x)
-> If f2fs_iget fails, then goto next. But, this is an impossible scenario.
   Drop this dnode(F).

So, this patch adds some missing points such as #1, #5, #7, and #8.

Signed-off-by: Jaegeuk Kim <jaegeuk@xxxxxxxxxx>
---
 fs/f2fs/file.c     | 10 ++++++++
 fs/f2fs/recovery.c | 70 +++++++++++++++++++++++++++++++++++++++++++++---------
 2 files changed, 69 insertions(+), 11 deletions(-)

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 5cde363..2660af2 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -207,6 +207,16 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 			up_write(&fi->i_sem);
 		}
 	} else {
+		/*
+		 * CP | inode(x) | dnode(F)
+		 * We need to remain inode(DF) for roll-forward recovery.
+		 */
+		if (fsync_mark_done(sbi, inode->i_ino) &&
+			!is_checkpointed_node(sbi, F2FS_I(inode)->i_pino)) {
+			mark_inode_dirty_sync(inode);
+			f2fs_write_inode(inode, NULL);
+		}
+
 		/* if there is no written node page, write its inode page */
 		while (!sync_node_pages(sbi, inode->i_ino, &wbc)) {
 			if (fsync_mark_done(sbi, inode->i_ino))
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 6c5a74a..8e69b9d 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -14,6 +14,36 @@
 #include "node.h"
 #include "segment.h"
 
+/*
+ * Roll forward recovery scenarios.
+ *
+ * [Term] F: fsync_mark, D: dentry_mark
+ *
+ * 1. inode(x) | CP | inode(x) | dnode(F)
+ * -> Update the latest inode(x).
+ *
+ * 2. inode(x) | CP | inode(F) | dnode(F)
+ * -> No problem.
+ *
+ * 3. inode(x) | CP | dnode(F) | inode(x)
+ * -> Impossible, but recover latest dnode(F)
+ *
+ * 4. inode(x) | CP | dnode(F) | inode(F)
+ * -> No problem.
+ *
+ * 5. CP | inode(x) | dnode(F)
+ * -> Impossible. Write inode(DF) with dnode(F) by f2fs_sync_file.
+ *
+ * 6. CP | inode(DF) | dnode(F)
+ * -> No problem.
+ *
+ * 7. CP | dnode(F) | inode(DF)
+ * -> If f2fs_iget fails, then goto next to find inode(DF).
+ *
+ * 8. CP | dnode(F) | inode(x)
+ * -> If f2fs_iget fails, then goto next. But, this is an impossible scenario.
+ *    Drop this dnode(F).
+ */
 static struct kmem_cache *fsync_entry_slab;
 
 bool space_for_roll_forward(struct f2fs_sb_info *sbi)
@@ -110,27 +140,32 @@ out:
 	return err;
 }
 
-static int recover_inode(struct inode *inode, struct page *node_page)
+static void __recover_inode(struct inode *inode, struct page *page)
 {
-	struct f2fs_inode *raw_inode = F2FS_INODE(node_page);
+	struct f2fs_inode *raw = F2FS_INODE(page);
+
+	inode->i_mode = le16_to_cpu(raw->i_mode);
+	i_size_write(inode, le64_to_cpu(raw->i_size));
+	inode->i_atime.tv_sec = le64_to_cpu(raw->i_mtime);
+	inode->i_ctime.tv_sec = le64_to_cpu(raw->i_ctime);
+	inode->i_mtime.tv_sec = le64_to_cpu(raw->i_mtime);
+	inode->i_atime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec);
+	inode->i_ctime.tv_nsec = le32_to_cpu(raw->i_ctime_nsec);
+	inode->i_mtime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec);
+}
 
+static int recover_inode(struct inode *inode, struct page *node_page)
+{
 	if (!IS_INODE(node_page))
 		return 0;
 
-	inode->i_mode = le16_to_cpu(raw_inode->i_mode);
-	i_size_write(inode, le64_to_cpu(raw_inode->i_size));
-	inode->i_atime.tv_sec = le64_to_cpu(raw_inode->i_mtime);
-	inode->i_ctime.tv_sec = le64_to_cpu(raw_inode->i_ctime);
-	inode->i_mtime.tv_sec = le64_to_cpu(raw_inode->i_mtime);
-	inode->i_atime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
-	inode->i_ctime.tv_nsec = le32_to_cpu(raw_inode->i_ctime_nsec);
-	inode->i_mtime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
+	__recover_inode(inode, node_page);
 
 	if (is_dent_dnode(node_page))
 		return recover_dentry(node_page, inode);
 
 	f2fs_msg(inode->i_sb, KERN_NOTICE, "recover_inode: ino = %x, name = %s",
-			ino_of_node(node_page), raw_inode->i_name);
+			ino_of_node(node_page), F2FS_INODE(node_page)->i_name);
 	return 0;
 }
 
@@ -186,10 +221,16 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 				break;
 			}
 
+			/*
+			 * CP | dnode(F) | inode(DF)
+			 * For this case, we should not give up now.
+			 */
 			entry->inode = f2fs_iget(sbi->sb, ino_of_node(page));
 			if (IS_ERR(entry->inode)) {
 				err = PTR_ERR(entry->inode);
 				kmem_cache_free(fsync_entry_slab, entry);
+				if (PTR_ERR(entry->inode) == -ENOENT)
+					goto next;
 				break;
 			}
 			list_add_tail(&entry->list, head);
@@ -416,6 +457,13 @@ static int recover_data(struct f2fs_sb_info *sbi,
 		entry = get_fsync_inode(head, ino_of_node(page));
 		if (!entry)
 			goto next;
+		/*
+		 * inode(x) | CP | inode(x) | dnode(F)
+		 * In this case, we can lose the latest inode(x).
+		 * So, call __recover_inode for the inode update.
+		 */
+		if (IS_INODE(page))
+			__recover_inode(entry->inode, page);
 
 		err = do_recover_data(sbi, entry->inode, page, blkaddr);
 		if (err)
-- 
1.8.5.2 (Apple Git-48)

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/