From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755116Ab1E2SG6 (ORCPT ); Sun, 29 May 2011 14:06:58 -0400 Received: from fanny.its.uu.se ([130.238.4.241]:42581 "EHLO fanny.its.uu.se" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754421Ab1E2SG5 convert rfc822-to-8bit (ORCPT ); Sun, 29 May 2011 14:06:57 -0400 MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8BIT Message-ID: <19938.35645.288213.802394@pilspetsen.it.uu.se> Date: Sun, 29 May 2011 20:06:53 +0200 From: Mikael Pettersson To: Andrew Lutomirski Cc: Mikael Pettersson , Ingo Molnar , Thomas Gleixner , Linus Torvalds , Andrew Morton , x86@kernel.org, LKML Subject: Re: [GIT pull] x86 vdso updates In-Reply-To: References: <4DDEC589.3010201@mit.edu> <20110527061208.GB9260@elte.hu> <20110528153536.GB27104@elte.hu> <19938.23219.306163.24059@pilspetsen.it.uu.se> <19938.28108.250080.666938@pilspetsen.it.uu.se> X-Mailer: VM 7.17 under Emacs 20.7.1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Andrew Lutomirski writes: > On Sun, May 29, 2011 at 12:01 PM, Mikael Pettersson wrote: > > Andrew Lutomirski writes: > >  > On Sun, May 29, 2011 at 10:39 AM, Mikael Pettersson wrote: > >  > > Ingo Molnar writes: > >  > >  > > >  > >  > * Andrew Lutomirski wrote: > >  > >  > > >  > >  > > On Fri, May 27, 2011 at 7:36 AM, Andrew Lutomirski wrote: > >  > >  > > > 3. Add int 0xcc and use it from vgettimeofday.  It will SIGSEGV if > >  > >  > > > called from a user address (so it has no risk of ever becoming ABI) > >  > >  > > > and it will do gettimeofday if called from the right address.  (I like > >  > > ... > >  > >  > > Make it a real syscall but with extra constraints.  It would have the > >  > >  > > same calling convention as the syscall instruction, but it would turn > >  > >  > > into SIGKILL if the calling address isn't in the VSYSCALL page > >  > > > >  > > This will make things difficult for user-space dynamic binary instrumentation > >  > > applications, since these normally execute generated code at different > >  > > addresses than the original code. > >  > > > >  > > Is there a safe fallback for this particular vsyscall? > >  > > >  > All of the vsyscalls have vDSO versions that work like any other code. > > > > Easiest would be if we can simply map int $0xcc with rAX==FOO to syscall or > > int 0x80 with rAX==BAR. > > Yes and no. > > With the code I just posted (and am fixing up now) that will work. > But if we want to replace the entire vsyscall page with three int 0xcc > and 4090 int3 instructions, then we can't look at eax because it won't > contain anything meaningful. I can relatively easily also consider the original application rIP when decoding and translating these instructions. > > --Andy > > > > > We currently don't even know about the vDSO, it's all just user-space code > > to us. > > > >  > Alternatively, if the dynamic instrumentation code knew about > >  > vsyscalls, it could just not instrument addresses in the vsyscall > >  > page. > > > > Not instrumenting code is not an option, unless we can prove that the > > code in question has no relevant side-effects or unexpected control-flow. > > (Where "side-effects" relate both to the integrity of the instrumentation > > engine and the application-specific payload it's attaching to the code.) > > Calls to 0xffffffffff600000, 0xffffffffff600400, and > 0xffffffffff600800 are syscalls, as an (unfortunate) part of the ABI. > > > > >  > What existing applications would get broken? > > > > My concern is ThreadSpotter, but any user-space dynamic binary instrumentation > > engine that instruments down to the raw kernel interface (syscall/sysenter/int > > instructions) would have a problem with syscalls that only work at specific > > addresses. > > I'll look. > > > > > Anyway, if I can map that vsyscall to a plain proper syscall, then I'm OK. > > All three vsyscalls can be replaced with real syscalls without side > effects. Would it be possible to teach the instrumentation code to > deal with that? Yes, I just need to know how to identify them and what their equivalents are. E.g., an int3 at becomes syscall rAX=. Sounds like this change will be manageable after all. Thanks. /Mikael