From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753124AbXCaOfU (ORCPT ); Sat, 31 Mar 2007 10:35:20 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753107AbXCaOfT (ORCPT ); Sat, 31 Mar 2007 10:35:19 -0400 Received: from ns1.suse.de ([195.135.220.2]:60968 "EHLO mx1.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753124AbXCaOfS (ORCPT ); Sat, 31 Mar 2007 10:35:18 -0400 From: Andi Kleen Organization: SUSE Linux Products GmbH, Nuernberg, GF: Markus Rex, HRB 16746 (AG Nuernberg) To: Zachary Amsden Subject: Re: [PATCH] VMI paravirt-ops bugfix for 2.6.21 Date: Sat, 31 Mar 2007 16:35:01 +0200 User-Agent: KMail/1.9.5 Cc: Andrew Morton , Linus Torvalds , Jeremy Fitzhardinge , Linux Kernel Mailing List References: <460E1FC7.5030107@vmware.com> In-Reply-To: <460E1FC7.5030107@vmware.com> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-15" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200703311635.01776.ak@suse.de> Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Saturday 31 March 2007 10:45, Zachary Amsden wrote: > So lazy MMU mode is vulnerable to interrupts coming in and issuing > kmap_atomic, which does not work when under lazy MMU mode. The window > for this is small, but it means highmem kernels, especially with heavy > network, USB, or AIO workloads are vulnerable to getting invariably > fatal pagefaults in interrupt handlers. For now, the best fix is to > simply disable and re-enable interrupts when entering and exiting lazy > mode (which, btw, is already guaranteed to have preempt disabled). For > the future, a better fix is to simply exit lazy mode when issuing > kmap_atomic, but I do not want to touch any generic code now for 2.6.21. I think I would prefer you touch the generic code. This new hook is ugly. And the lazy mode is currently only used by VMI anyways, isn't it? So you shouldn't impact anybody else -Andi