From mboxrd@z Thu Jan 1 00:00:00 1970 From: Marcelo Tosatti Subject: Re: [PATCH 0/5] Fix some mmu/emulator atomicity issues (v2) Date: Tue, 16 Mar 2010 16:33:29 -0300 Message-ID: <20100316193329.GA13101@amt.cnet> References: <1268654397-6650-1-git-send-email-avi@redhat.com> <20100316163649.GA9718@amt.cnet> <17398A15-DD8E-469C-BFFA-97AECADB3328@suse.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Avi Kivity , kvm@vger.kernel.org To: Alexander Graf Return-path: Received: from mx1.redhat.com ([209.132.183.28]:62023 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755426Ab0CPTeS (ORCPT ); Tue, 16 Mar 2010 15:34:18 -0400 Content-Disposition: inline In-Reply-To: <17398A15-DD8E-469C-BFFA-97AECADB3328@suse.de> Sender: kvm-owner@vger.kernel.org List-ID: On Tue, Mar 16, 2010 at 07:22:55PM +0100, Alexander Graf wrote: > > On 16.03.2010, at 17:36, Marcelo Tosatti wrote: > > > On Mon, Mar 15, 2010 at 01:59:52PM +0200, Avi Kivity wrote: > >> Currently when we emulate a locked operation into a shadowed guest page > >> table, we perform a write rather than a true atomic. This is indicated > >> by the "emulating exchange as write" message that shows up in dmesg. > >> > >> In addition, the pte prefetch operation during invlpg suffered from a > >> race. This was fixed by removing the operation. > >> > >> This patchset fixes both issues and reinstates pte prefetch on invlpg. > >> > >> v3: > >> - rebase against next branch (resolves conflicts via hypercall patch) > >> > >> v2: > >> - fix truncated description for patch 1 > >> - add new patch 4, which fixes a bug in patch 5 > > > > Applied, thanks. > > How relevant is this for -stable? Races don't sound good to me :) The race mentioned above is not existant on -stable since prefetch is disabled for invlpg. The atomic fixes seem like a candidate, since lack of them can trigger pagetable corruption. Avi?