From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759142AbZDXIkr (ORCPT ); Fri, 24 Apr 2009 04:40:47 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753817AbZDXIkj (ORCPT ); Fri, 24 Apr 2009 04:40:39 -0400 Received: from one.firstfloor.org ([213.235.205.2]:51432 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750927AbZDXIki (ORCPT ); Fri, 24 Apr 2009 04:40:38 -0400 Date: Fri, 24 Apr 2009 10:44:19 +0200 From: Andi Kleen To: Joe Damato Cc: "H. Peter Anvin" , Andi Kleen , Ingo Molnar , Jeff Garzik , Linus Torvalds , LKML , Thomas Gleixner , Ingo Molnar , x86@kernel.org Subject: Re: [PATCH] X86-32: Let gcc decide whether to inline memcpy was Re: New x86 warning Message-ID: <20090424084419.GH13896@one.firstfloor.org> References: <49EEBD3C.3060009@garzik.org> <20090422070157.GA28438@elte.hu> <8763gxoz50.fsf_-_@basil.nowhere.org> <3605561d0904221649n169dc579xb0694297154d97fa@mail.gmail.com> <49EFC8FE.7010403@zytor.com> <3605561d0904231422s57bd4cedl722be1dabf27428f@mail.gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <3605561d0904231422s57bd4cedl722be1dabf27428f@mail.gmail.com> User-Agent: Mutt/1.4.2.1i Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org > gcc 4.2.4 - withOUT memset patch: 20 > gcc 4.2.4 - with memset patch: 365 > > gcc 3.4 - withOUT memset patch: 17 > gcc 3.4 - with memset patch: 349 Yes it sounds like 3.4 is worse on that than 3.2. Too bad. > I'm guessing this is probably not acceptable, so I won't bother It depends if the calls are in critical code. Or how big they are (for a 1K memset it's totally fine to have it out of line). For example for any memsets in __init functions we wouldn't care. You could filter those out. And perhaps eyeball the code. -Andi -- ak@linux.intel.com -- Speaking for myself only.