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; }