[PATCH 1/2] audit: don't free_chunk() after fsnotify_add_mark()

[Miklos Szeredi]

Al, your are the co-maintainer of audit, right?  Can you please apply
these patches as Eric is on vaction.

Thanks,
Miklos
----

From: Miklos Szeredi <mszeredi@xxxxxxx>

Don't do free_chunk() after fsnotify_add_mark().  That one does a delayed unref
via the destroy list and this results in use-after-free.

Signed-off-by: Miklos Szeredi <mszeredi@xxxxxxx>
Acked-by: Eric Paris <eparis@xxxxxxxxxx>
CC: stable@xxxxxxxxxxxxxxx
---
 kernel/audit_tree.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

Index: linux-2.6/kernel/audit_tree.c
===================================================================
--- linux-2.6.orig/kernel/audit_tree.c	2011-10-26 14:26:24.000000000 +0200
+++ linux-2.6/kernel/audit_tree.c	2012-05-30 16:56:04.000000000 +0200
@@ -259,7 +259,7 @@ static void untag_chunk(struct node *p)
 
 	fsnotify_duplicate_mark(&new->mark, entry);
 	if (fsnotify_add_mark(&new->mark, new->mark.group, new->mark.i.inode, NULL, 1)) {
-		free_chunk(new);
+		fsnotify_put_mark(&new->mark);
 		goto Fallback;
 	}
 
@@ -322,7 +322,7 @@ static int create_chunk(struct inode *in
 
 	entry = &chunk->mark;
 	if (fsnotify_add_mark(entry, audit_tree_group, inode, NULL, 0)) {
-		free_chunk(chunk);
+		fsnotify_put_mark(entry);
 		return -ENOSPC;
 	}
 
@@ -396,7 +396,7 @@ static int tag_chunk(struct inode *inode
 	fsnotify_duplicate_mark(chunk_entry, old_entry);
 	if (fsnotify_add_mark(chunk_entry, chunk_entry->group, chunk_entry->i.inode, NULL, 1)) {
 		spin_unlock(&old_entry->lock);
-		free_chunk(chunk);
+		fsnotify_put_mark(chunk_entry);
 		fsnotify_put_mark(old_entry);
 		return -ENOSPC;
 	}


--
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/