Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S964905AbeAJMCD (ORCPT + 1 other); Wed, 10 Jan 2018 07:02:03 -0500 Received: from mx1.redhat.com ([209.132.183.28]:36996 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932218AbeAJMCB (ORCPT ); Wed, 10 Jan 2018 07:02:01 -0500 Date: Wed, 10 Jan 2018 13:01:58 +0100 From: Andrea Arcangeli To: David Woodhouse Cc: Peter Zijlstra , Dave Hansen , Thomas Gleixner , LKML , Linus Torvalds , x86@kernel.org, Borislav Petkov , Tim Chen , Andi Kleen , Greg KH , Andy Lutomirski , Arjan Van De Ven Subject: Re: [patch RFC 5/5] x86/speculation: Add basic speculation control code Message-ID: <20180110120158.GB9706@redhat.com> References: <20180110010652.404145126@linutronix.de> <20180110011350.855878109@linutronix.de> <20180110092234.GY29822@worktop.programming.kicks-ass.net> <1515576479.22302.81.camel@infradead.org> <20180110115419.GA9706@redhat.com> <1515585534.22302.122.camel@infradead.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1515585534.22302.122.camel@infradead.org> User-Agent: Mutt/1.9.2 (2017-12-15) X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.31]); Wed, 10 Jan 2018 12:02:01 +0000 (UTC) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Return-Path: On Wed, Jan 10, 2018 at 11:58:54AM +0000, David Woodhouse wrote: > On Wed, 2018-01-10 at 12:54 +0100, Andrea Arcangeli wrote: > > On Wed, Jan 10, 2018 at 09:27:59AM +0000, David Woodhouse wrote: > > > I don't know why you're calling that 'IBRS=2'; are you getting > > confused > > > by Andrea's distro horridness? > > > > Eh, yes he's got confused. ibrs_enabled 2 simply means to leave IBRS > > set in SPEC_CTLR 100% of the time, except in guest mode. > > On all current hardware, if you only set IBRS when you exit a guest, > then you are not protecting yourself from userspace at all. IBRS acts > as a *barrier* in all current hardware. Kernel memory is 100% protected if you set only IBRS at vmexit. Once IBRS is set, there's no way any userland (nor host nor guest) can attack the kernel memory through spectre variant#2. What is not protected is host userland from guest userland which is point 3 in the email I posted earlier and I already provided all details there on how to fix that purely theoretical issue not part of the PoC with the provided debugfs tunables, so I won't repeat here.