From owner-freebsd-net@FreeBSD.ORG Fri Sep 7 13:24:50 2012 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 4D0AC106566C; Fri, 7 Sep 2012 13:24:50 +0000 (UTC) (envelope-from glebius@FreeBSD.org) Received: from cell.glebius.int.ru (glebius.int.ru [81.19.64.117]) by mx1.freebsd.org (Postfix) with ESMTP id BA1198FC12; Fri, 7 Sep 2012 13:24:49 +0000 (UTC) Received: from cell.glebius.int.ru (localhost [127.0.0.1]) by cell.glebius.int.ru (8.14.5/8.14.5) with ESMTP id q87DOm8S048041; Fri, 7 Sep 2012 17:24:48 +0400 (MSK) (envelope-from glebius@FreeBSD.org) Received: (from glebius@localhost) by cell.glebius.int.ru (8.14.5/8.14.5/Submit) id q87DOm8V048040; Fri, 7 Sep 2012 17:24:48 +0400 (MSK) (envelope-from glebius@FreeBSD.org) X-Authentication-Warning: cell.glebius.int.ru: glebius set sender to glebius@FreeBSD.org using -f Date: Fri, 7 Sep 2012 17:24:48 +0400 From: Gleb Smirnoff To: sbruno@FreeBSD.org Message-ID: <20120907132448.GI44854@FreeBSD.org> References: <1347003353.3109.12.camel@powernoodle> MIME-Version: 1.0 Content-Type: text/plain; charset=koi8-r Content-Disposition: inline In-Reply-To: <1347003353.3109.12.camel@powernoodle> User-Agent: Mutt/1.5.21 (2010-09-15) Cc: "freebsd-net@freebsd.org" Subject: Re: stable/9 igb(4) panic, udp_append 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: Fri, 07 Sep 2012 13:24:50 -0000 On Fri, Sep 07, 2012 at 12:35:53AM -0700, Sean Bruno wrote: S> Just noted this happened today, running stable/9 ish from august 10th. S> It looks like I got a good and valid crashdump off of this if anyone is S> interested. ... S> --- trap 0xc, rip = 0xffffffff80731312, rsp = 0xffffff846c8977d0, rbp = S> 0xffffff846c897860 --- S> udp_append() at udp_append+0x62 S> udp_input() at udp_input+0x4c8 S> ip_input() at ip_input+0xbd I guess I know this one. The problem is a race in in_pcblookup_*() when two threads want to acquire a pcb read-locked and third thread detaches it. I have reported this to Robert and now waiting for reply. -- Totus tuus, Glebius.