From: Theodore Ts'o <tytso@mit.edu>
Date: Mon, 15 Jun 2009 07:41:23 +0000 (-0400)
Subject: ext4: Don't update ctime for non-extent-mapped inodes
X-Git-Tag: v2.6.31-rc1~138^2~1
X-Git-Url: https://git.karo-electronics.de/?a=commitdiff_plain;h=4159175058987cb68aefd0e9eec2598b795363b4;p=karo-tx-linux.git

ext4: Don't update ctime for non-extent-mapped inodes

The VFS handles updating ctime, so we don't need to update the inode's
ctime in ext4_splace_branch() to update the direct or indirect blocks.
This was harmless when we did this in ext3, but in ext4, thanks to
delayed allocation, updating the ctime in ext4_splice_branch() can
cause the ctime to mysteriously jump when the blocks are finally
allocated.

Thanks to Björn Steinbrink for pointing out this problem on the git
mailing list.

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 8d0908afbd5b..7c17ae275af4 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -856,10 +856,6 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode,
 	}
 
 	/* We are done with atomic stuff, now do the rest of housekeeping */
-
-	inode->i_ctime = ext4_current_time(inode);
-	ext4_mark_inode_dirty(handle, inode);
-
 	/* had we spliced it onto indirect block? */
 	if (where->bh) {
 		/*
@@ -878,8 +874,8 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode,
 	} else {
 		/*
 		 * OK, we spliced it into the inode itself on a direct block.
-		 * Inode was dirtied above.
 		 */
+		ext4_mark_inode_dirty(handle, inode);
 		jbd_debug(5, "splicing direct\n");
 	}
 	return err;