Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754053AbcLBW4X (ORCPT ); Fri, 2 Dec 2016 17:56:23 -0500 Received: from mail-ua0-f180.google.com ([209.85.217.180]:34126 "EHLO mail-ua0-f180.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751950AbcLBW4V (ORCPT ); Fri, 2 Dec 2016 17:56:21 -0500 MIME-Version: 1.0 In-Reply-To: References: <0a21157c2233ba7d0781bbf07866b3f2d7e7c25d.1480638597.git.luto@kernel.org> <20161202180343.gehqor7lgtmzwqq3@pd.tnic> <20161202185008.tdziqrzi4a3axord@pd.tnic> <20161202192050.l5l3rcwems6hptub@pd.tnic> From: Andy Lutomirski Date: Fri, 2 Dec 2016 14:55:44 -0800 Message-ID: Subject: Re: [PATCH v2 5/6] x86/xen: Add a Xen-specific sync_core() implementation To: Linus Torvalds Cc: Borislav Petkov , Borislav Petkov , Andy Lutomirski , Peter Anvin , "the arch/x86 maintainers" , One Thousand Gnomes , "linux-kernel@vger.kernel.org" , Brian Gerst , Matthew Whitehead , Henrique de Moraes Holschuh , Peter Zijlstra , Andrew Cooper Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1174 Lines: 27 On Fri, Dec 2, 2016 at 1:10 PM, Linus Torvalds wrote: > On Fri, Dec 2, 2016 at 12:41 PM, Andy Lutomirski wrote: >> >> Because, if so, we should maybe serialize whenever we migrate a >> process to a different CPU. > > The intel docs are bad on this issue. > > Technically what we do could fall under the "cross-modifying code" > case, where one CPU does the write, and then we run it on another CPU. > > And no, we do *not* do a serializing instruction before returning to > user space. Sure, we might do an iret (which is serializing), but we > equally well might be doing a systret (which is not). > > Honestly, I think Intel should clean up their documentation. > I'm not sure I follow. If a user program gets migrated, it might end up doing cross-modification when it expects self-modification. If that trips the program up, is that a user bug or a kernel bug? Admittedly, I'd be very surprised if this happened in practice. Migration is *slow*, caches tend to get blown away, lots of code gets executed, etc. Presumably any prefetched / trace cached / decoded / i-cached user code is long gone when we migrate.