Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755153AbZJCWzD (ORCPT ); Sat, 3 Oct 2009 18:55:03 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753715AbZJCWzC (ORCPT ); Sat, 3 Oct 2009 18:55:02 -0400 Received: from mail-bw0-f210.google.com ([209.85.218.210]:40698 "EHLO mail-bw0-f210.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753472AbZJCWzB (ORCPT ); Sat, 3 Oct 2009 18:55:01 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:from:date:message-id:subject:to :cc:content-type; b=LncuscPl6/ZvXUdH6g36zA7K6dojME6T3suviVjvVkJPyDqfKV1ETnqKnPzrpU/6JS 239jKgXRBj+RVcd1iReLhFVc2WH4kbUu0h1dPRcRKXRh6VmW2IaakUzSWAjEffDgG1sv gdnifrK5WW+LJPP8jvbzNXafk6mS9bhhg0KNg= MIME-Version: 1.0 In-Reply-To: <20091003223210.GA4193@boogie.lpds.sztaki.hu> References: <40101cc30910021912r17b3a08bue1b9412e4fa47d89@mail.gmail.com> <20091003110546.78958508@infradead.org> <40101cc30910031504pa9f8536k82dbd7668dfa643d@mail.gmail.com> <20091003223210.GA4193@boogie.lpds.sztaki.hu> From: Matteo Croce Date: Sun, 4 Oct 2009 00:54:03 +0200 Message-ID: <40101cc30910031554w40a0f93ata5decac55cbcba5c@mail.gmail.com> Subject: Re: i686 quirk for AMD Geode To: Gabor Gombas Cc: Arjan van de Ven , "H. Peter Anvin" , linux-kernel@vger.kernel.org Content-Type: text/plain; charset=ISO-8859-1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1004 Lines: 21 On Sun, Oct 4, 2009 at 12:32 AM, Gabor Gombas wrote: > On Sun, Oct 04, 2009 at 12:04:03AM +0200, Matteo Croce wrote: > >> yes cmov and i686 are unrelated but some distros (Debian & co.) >> compiles libraries for two archs: >> i486 and i686-cmov so only i686 machines does benefit from cmov. >> This is why I cared about having an i686 aware userspace but it seems >> that for a missing instruction I can't do that > > You could emulate the missing instruction. As long as it is not really > used, the performance cost of the emulation should not matter. Of course > if userspace starts to use long NOPs extensively then it becomes a > problem. Emulate? I can replace it with two plain NOPs. How can I do the "emulation"? trapping SIGILL? -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/