MIME-Version: 1.0
In-Reply-To: <20130107024827.GZ27530@wantstofly.org>
References: <1357522042-39255-1-git-send-email-nickolai@csail.mit.edu> <20130107024827.GZ27530@wantstofly.org>
From: Nickolai Zeldovich <nickolai@csail.mit.edu>
Date: Sun, 6 Jan 2013 22:02:14 -0500
Message-ID: <CADGQE7EYbYqSkZZJfg-b0sF4w7GPrsGtXk+VBdWZ12Z7Xv7tcg@mail.gmail.com> (sfid-20130107_040256_416010_7B0C62A1)
Subject: Re: [PATCH] drivers/net/wireless/mwl8k.c: avoid use-after-free
To: Lennert Buytenhek <buytenh@wantstofly.org>
Cc: "John W. Linville" <linville@tuxdriver.com>,
	linux-wireless@vger.kernel.org, linux-kernel@vger.kernel.org
Content-Type: text/plain; charset=UTF-8
Sender: linux-wireless-owner@vger.kernel.org

On Sun, Jan 6, 2013 at 9:48 PM, Lennert Buytenhek
<buytenh@wantstofly.org> wrote:
> Good catch, but the patch would be better titled "mwl8k.c: avoid
> having a working driver", as the station_id return code _is_ needed
> by the caller in case of success.

I'm not quite sure what you mean -- is there something subtle going on
here?  I believe my patch preserves the semantics of the original
code: it returns the value of p->station_id if mwl8k_post_cmd()
returned 0, but it just does so by reading p->station_id first before
calling kfree(cmd).

Nickolai.