Thread (2 messages) 2 messages, 2 authors, 2012-07-06

Re: [PATCH 1/3] audit: don't free_chunk() after fsnotify_add_mark()

From: Eric Paris <eparis@redhat.com>
Date: 2012-07-06 18:13:34
Also in: lkml

On Mon, 2012-06-25 at 19:46 +0200, Miklos Szeredi wrote:
From: Miklos Szeredi <redacted>

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 <redacted>
CC: stable@vger.kernel.org
Al, can you send these along?  I am not going to see a computer again
for a month.  Hurray!

Acked-by: Eric Paris <eparis@redhat.com>
quoted hunk ↗ jump to hunk
---
 kernel/audit_tree.c |    6 +++---
 1 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 5bf0790..d52d247 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -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 *inode, struct audit_tree *tree)
 
 	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, struct audit_tree *tree)
 	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;
 	}
  
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help