From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753026AbYCJVuK (ORCPT ); Mon, 10 Mar 2008 17:50:10 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751075AbYCJVt6 (ORCPT ); Mon, 10 Mar 2008 17:49:58 -0400 Received: from one.firstfloor.org ([213.235.205.2]:58829 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751803AbYCJVt4 (ORCPT ); Mon, 10 Mar 2008 17:49:56 -0400 Date: Mon, 10 Mar 2008 22:51:45 +0100 From: Andi Kleen To: Stephan Diestelhorst Cc: Andi Kleen , Ingo Molnar , davej@codemonkey.org.uk, cpufreq@lists.linux.org.uk, linux-kernel@vger.kernel.org Subject: Re: [PATCH 1/1] Speedfreq-SMI call clobbers ECX Message-ID: <20080310215145.GB9246@one.firstfloor.org> References: <200803051559.09962.langer_mann@web.de> <200803101605.42251.langer_mann@web.de> <87iqzu8r2q.fsf@basil.nowhere.org> <200803102226.39044.langer_mann@web.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <200803102226.39044.langer_mann@web.de> User-Agent: Mutt/1.4.2.1i Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org > Please also note that these are not clobbers in the strict inline asm > syntax, but rather dummy output values that correspond to actual Outputs/Inputs are as bad as clobbers in triggering gcc reload ICEs. > input parameters. I'd consider this a serious compiler flaw, if not > bug, if these would not work. But let's not get into GCC vs. It is, and it's (mostly) fixed in newer versions, but we're stuck with supporting the older compiler versions unfortunately. > > For asms with so many clobbers explicit push/pop is usually safer. > > Yes, but it is unneccessary overhead as the compiler can (should!) > find more elegant ways to get those registers back if needed. This code is not performance critical at all. Safer beats faster any time in such cases. -Andi