From owner-freebsd-net@FreeBSD.ORG Wed Oct 12 01:53:36 2011 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 5944C106566C; Wed, 12 Oct 2011 01:53:36 +0000 (UTC) (envelope-from s.dave.jones@gmail.com) Received: from mail-vw0-f54.google.com (mail-vw0-f54.google.com [209.85.212.54]) by mx1.freebsd.org (Postfix) with ESMTP id AD8AA8FC1C; Wed, 12 Oct 2011 01:53:35 +0000 (UTC) Received: by vws11 with SMTP id 11so234821vws.13 for ; Tue, 11 Oct 2011 18:53:34 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; bh=X7b9vV9zOx7fBHScqHlmx9uQUS+zW5AXkt0rmI7QaMg=; b=WtW8G2hSZ4Sy1JcOy3iIjLBhtQFkSzmFI2OwBLE9y29tHVmD1VJDRz88F5ilIpPAhK IgMUhEsMdJ3z7AQasUueNajuUGsCiayjzcAV1wnXsfAqqjRnISz3uE/UKDIvuGQpdimO rcNZw+dVb0qKv13lmBznmbURXnAvPZztyoWWM= MIME-Version: 1.0 Received: by 10.52.26.81 with SMTP id j17mr21111321vdg.101.1318384414714; Tue, 11 Oct 2011 18:53:34 -0700 (PDT) Received: by 10.52.186.170 with HTTP; Tue, 11 Oct 2011 18:53:34 -0700 (PDT) In-Reply-To: References: <8662kcigif.fsf@kopusha.home.net> <86y5x0ooik.fsf@in138.ua3> Date: Wed, 12 Oct 2011 09:53:34 +0800 Message-ID: From: dave jones To: Mikolaj Golub Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Cc: "freebsd-net@freebsd.org" , Adrian Chadd , Robert Watson , "K. Macy" , Arnaud Lacombe Subject: Re: Kernel panic on FreeBSD 9.0-beta2 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 12 Oct 2011 01:53:36 -0000 On Fri, Oct 7, 2011 at 9:12 AM, dave jones wrote: > 2011/10/4 Mikolaj Golub : >> >> On Sat, 1 Oct 2011 14:15:45 +0800 dave jones wrote: >> >> =A0dj> On Fri, Sep 30, 2011 at 9:41 PM, Robert Watson wrote: >> =A0>> >> =A0>> On Wed, 28 Sep 2011, Mikolaj Golub wrote: >> =A0>> >> =A0>>> On Mon, 26 Sep 2011 16:12:55 +0200 K. Macy wrote: >> =A0>>> >> =A0>>> KM> Sorry, didn't look at the images (limited bw), I've seen some= thing KM> >> =A0>>> like this before in timewait. This "can't happen" with UDP so wil= l be KM> >> =A0>>> interested in learning more about the bug. >> =A0>>> >> =A0>>> The panic can be easily triggered by this: >> =A0>> >> =A0>> Hi: >> =A0>> >> =A0>> Just catching up on this thread. =A0I think the analysis here is g= enerally >> =A0>> right: in 9.0, you're much more likely to see an inpcb with its in= _socket >> =A0>> pointer cleared in the hash list than in prior releases, and >> =A0>> in_pcbbind_setup() trips over this. >> =A0>> >> =A0>> However, at least on first glance (and from the perspective of inv= ariants >> =A0>> here), I think the bug is actualy that in_pcbbind_setup() is askin= g >> =A0>> in_pcblookup_local() for an inpcb and then access the returned inp= cb's >> =A0>> in_socket pointer without acquiring a lock on the inpcb. =A0Struct= urally, it >> =A0>> can't acquire this lock for lock order reasons -- it already holds= the lock >> =A0>> on its own inpcb. =A0Therefore, we should only access fields that = are safe to >> =A0>> follow in an inpcb when you hold a reference via the hash lock and= not a >> =A0>> lock on the inpcb itself, which appears generally OK (+/-) for all= the >> =A0>> fields in that clause but the t->inp_socket->so_options dereferenc= e. >> =A0>> >> =A0>> A preferred fix would cache the SO_REUSEPORT flag in an inpcb-laye= r field, >> =A0>> such as inp_flags2, giving us access to its value without having t= o walk >> =A0>> into the attached (or not) socket. >> =A0>> >> =A0>> This raises another structural question, which is whether we need = a new >> =A0>> inp_foo flags field that is protected explicitly by the hash lock,= and not >> =A0>> by the inpcb lock, which could hold fields relevant to address bin= ding. =A0I >> =A0>> don't think we need to solve that problem in this context, as a sl= ightly >> =A0>> race on SO_REUSEPORT is likely acceptable. >> =A0>> >> =A0>> The suggested fix does perform the desired function of explicitly = detaching >> =A0>> the inpcb from the hash list before the socket is disconnected fro= m the >> =A0>> inpcb. However, it's incomplete in that the invariant that's being= broken is >> =A0>> also relied on for other protocols (such as raw sockets). =A0The c= orrect >> =A0>> invariant is that inp_socket is safe to follow unconditionally if = an inpcb >> =A0>> is locked and INP_DROPPED isn't set -- the bug is in "locked" not = in >> =A0>> "INP_DROPPED", which is why I think this is the wrong fix, even th= ough it >> =A0>> prevents a panic :-). >> >> =A0dj> Hello Robert, >> >> =A0dj> Thank you for taking your valuable time to find out the problem. >> =A0dj> Since I don't have idea about network internals, would you have a= patch >> =A0dj> about this? I'd be glad to test it, thanks again. >> >> Here is the patch that implements what Robert suggests. >> >> Dave, could you test it? > > Sure. Thanks for cooking the patch. > Machines have been running two days now without panic. Is there any plan to commit your fix? Thank you. I'd upgrade to 9.0-release from beta-2 once it's released. Best regards, Dave.