From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1761876AbXFTH5g (ORCPT ); Wed, 20 Jun 2007 03:57:36 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1758051AbXFTH53 (ORCPT ); Wed, 20 Jun 2007 03:57:29 -0400 Received: from il.qumranet.com ([82.166.9.18]:42946 "EHLO il.qumranet.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755794AbXFTH52 (ORCPT ); Wed, 20 Jun 2007 03:57:28 -0400 Message-ID: <4678DB8C.4040200@qumranet.com> Date: Wed, 20 Jun 2007 10:47:24 +0300 From: Avi Kivity User-Agent: Thunderbird 2.0.0.4 (X11/20070615) MIME-Version: 1.0 To: Luca Tettamanti CC: kvm-devel@lists.sourceforge.net, linux-kernel@vger.kernel.org Subject: Re: [PATCH 1/2] kvm: Fix x86 emulator writeback References: <68676e00706141627s3cb87391sa0ee6711d2f7933f@mail.gmail.com> <467256AA.1040001@qumranet.com> <20070615214915.GA10536@dreamland.darkstar.lan> <4673949B.1070505@qumranet.com> <20070617151452.GA21971@dreamland.darkstar.lan> <4675523C.9020703@qumranet.com> <20070617165201.GA23885@dreamland.darkstar.lan> <46765954.60102@qumranet.com> <46766D57.8040206@qumranet.com> <20070619202524.GA17672@dreamland.darkstar.lan> <20070619204120.GA18800@dreamland.darkstar.lan> In-Reply-To: <20070619204120.GA18800@dreamland.darkstar.lan> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-3.0 (firebolt.argo.co.il [0.0.0.0]); Wed, 20 Jun 2007 10:47:24 +0300 (IDT) Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Luca Tettamanti wrote: > When the old value and new one are the same the emulator skips the > write; this is undesiderable when the destination is a MMIO area and the > write shall be performed regardless of the previous value. This > optimization breaks e.g. a Linux guest APIC compiled without > X86_GOOD_APIC. > > Remove the check and perform the writeback stage in the emulation unless > it's explicitly disabled (currently push and some 2 bytes instructions > may disable the writeback). > > Applied both, thanks. -- Do not meddle in the internals of kernels, for they are subtle and quick to panic.