From: Herbert Xu <herbert@gondor.apana.org.au>
Subject: Re: [PATCH crypto] crypto: algboss: fix NULL pointer dereference
 in cryptomgr_probe
Date: Thu, 20 Jun 2013 21:33:35 +0800
Message-ID: <20130620133335.GA18773@gondor.apana.org.au>
References: <1371715221-27192-1-git-send-email-dborkman@redhat.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Cc: linux-crypto@vger.kernel.org, linux-sctp@vger.kernel.org,
	netdev@vger.kernel.org
To: Daniel Borkmann <dborkman@redhat.com>
Return-path: <linux-crypto-owner@vger.kernel.org>
Received: from ringil.hengli.com.au ([178.18.16.133]:48562 "EHLO
	fornost.hengli.com.au" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org
	with ESMTP id S1757864Ab3FTNdh (ORCPT
	<rfc822;linux-crypto@vger.kernel.org>);
	Thu, 20 Jun 2013 09:33:37 -0400
Content-Disposition: inline
In-Reply-To: <1371715221-27192-1-git-send-email-dborkman@redhat.com>
Sender: linux-crypto-owner@vger.kernel.org
List-ID: <linux-crypto.vger.kernel.org>

On Thu, Jun 20, 2013 at 10:00:21AM +0200, Daniel Borkmann wrote:
> After having fixed a NULL pointer dereference in SCTP 1abd165e ("net:
> sctp: fix NULL pointer dereference in socket destruction"), I ran into
> the following NULL pointer dereference in the crypto subsystem with
> the same reproducer, easily hit each time:
> 
> BUG: unable to handle kernel NULL pointer dereference at (null)
> IP: [<ffffffff81070321>] __wake_up_common+0x31/0x90
> PGD 0
> Oops: 0000 [#1] SMP
> Modules linked in: padlock_sha(F-) sha256_generic(F) sctp(F) libcrc32c(F) [..]
> CPU: 6 PID: 3326 Comm: cryptomgr_probe Tainted: GF            3.10.0-rc5+ #1
> Hardware name: Dell Inc. PowerEdge T410/0H19HD, BIOS 1.6.3 02/01/2011
> task: ffff88007b6cf4e0 ti: ffff88007b7cc000 task.ti: ffff88007b7cc000
> RIP: 0010:[<ffffffff81070321>]  [<ffffffff81070321>] __wake_up_common+0x31/0x90
> RSP: 0018:ffff88007b7cde08  EFLAGS: 00010082
> RAX: ffffffffffffffe8 RBX: ffff88003756c130 RCX: 0000000000000000
> RDX: 0000000000000000 RSI: 0000000000000003 RDI: ffff88003756c130
> RBP: ffff88007b7cde48 R08: 0000000000000000 R09: ffff88012b173200
> R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000282
> R13: ffff88003756c138 R14: 0000000000000000 R15: 0000000000000000
> FS:  0000000000000000(0000) GS:ffff88012fc60000(0000) knlGS:0000000000000000
> CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
> CR2: 0000000000000000 CR3: 0000000001a0b000 CR4: 00000000000007e0
> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
> Stack:
>  ffff88007b7cde28 0000000300000000 ffff88007b7cde28 ffff88003756c130
>  0000000000000282 ffff88003756c128 ffffffff81227670 0000000000000000
>  ffff88007b7cde78 ffffffff810722b7 ffff88007cdcf000 ffffffff81a90540
> Call Trace:
>  [<ffffffff81227670>] ? crypto_alloc_pcomp+0x20/0x20
>  [<ffffffff810722b7>] complete_all+0x47/0x60
>  [<ffffffff81227708>] cryptomgr_probe+0x98/0xc0
>  [<ffffffff81227670>] ? crypto_alloc_pcomp+0x20/0x20
>  [<ffffffff8106760e>] kthread+0xce/0xe0
>  [<ffffffff81067540>] ? kthread_freezable_should_stop+0x70/0x70
>  [<ffffffff815450dc>] ret_from_fork+0x7c/0xb0
>  [<ffffffff81067540>] ? kthread_freezable_should_stop+0x70/0x70
> Code: 41 56 41 55 41 54 53 48 83 ec 18 66 66 66 66 90 89 75 cc 89 55 c8
>       4c 8d 6f 08 48 8b 57 08 41 89 cf 4d 89 c6 48 8d 42 e
> RIP  [<ffffffff81070321>] __wake_up_common+0x31/0x90
>  RSP <ffff88007b7cde08>
> CR2: 0000000000000000
> ---[ end trace b495b19270a4d37e ]---
> 
> My assumption is that the following is happening: the minimal SCTP
> tool runs under ``echo 1 > /proc/sys/net/sctp/auth_enable'', hence
> it's making use of crypto_alloc_hash() via sctp_auth_init_hmacs().
> It forks itself, heavily allocates, binds, listens and waits in
> accept on sctp sockets, and then randomly kills some of them (no
> need for an actual client in this case to hit this). Then, again,
> allocating, binding, etc, and then killing child processes.
> 
> The problem that might be happening here is that cryptomgr requests
> the module to probe/load through cryptomgr_schedule_probe(), but
> before the thread handler cryptomgr_probe() returns, we return from
> the wait_for_completion_interruptible() function and probably already
> have cleared up larval, thus we run into a NULL pointer dereference
> when in cryptomgr_probe() complete_all() is being called.
> 
> If we wait with wait_for_completion() instead, this panic will not
> occur anymore. This is valid, because in case a signal is pending,
> cryptomgr_probe() returns from probing anyway with properly calling
> complete_all().

Thanks for the patch.  However I'm having trouble understanding
exactly why this is happening.  I deliberately used interruptible
just in case a bug somewhere causes it to hang indefinitely.  Thus
the code is *supposed* to handle the case of a premature return.

In any case, if the larval really was destroyed then that's a bug
regardless of whether we returned prematurely or not.  The calling
function is the only entity that should be able to destroy that
larval.

Cheers,
-- 
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt