From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1761953Ab2COOCY (ORCPT ); Thu, 15 Mar 2012 10:02:24 -0400 Received: from terminus.zytor.com ([198.137.202.10]:56567 "EHLO mail.zytor.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752784Ab2COOCV (ORCPT ); Thu, 15 Mar 2012 10:02:21 -0400 Message-ID: <4F61F5E6.8060509@zytor.com> Date: Thu, 15 Mar 2012 07:00:06 -0700 From: "H. Peter Anvin" User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:10.0.1) Gecko/20120209 Thunderbird/10.0.1 MIME-Version: 1.0 To: Matthew Garrett CC: linux-kernel@vger.kernel.org, x86@kernel.org, matt.fleming@intel.com Subject: Re: [PATCH] EFI: Only set regions uncacheable if they support it References: <1331819798-1955-1-git-send-email-mjg@redhat.com> In-Reply-To: <1331819798-1955-1-git-send-email-mjg@redhat.com> X-Enigmail-Version: 1.4 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 03/15/2012 06:56 AM, Matthew Garrett wrote: > The EFI memory region attributes field indicates whether the region can > be mapped with various cache attributes. Our current implementation always > marks regions uncacheable if they don't have the writeback support flag. > This causes us to mark some regions uncacheable even if they don't > indicate support for being uncacheable, triggering a clflush that may cause > an MCE. Ensure we only do this for regions which support it. > > Signed-off-by: Matthew Garrett Could you be specific as to what you're seeing in the field? In particular, what *do* these memory regions claim to support? -hpa