From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <gcc-patches-return-268507-listarch-gcc-patches=gcc.gnu.org@gcc.gnu.org>
Received: (qmail 1213 invoked by alias); 19 Jul 2010 16:16:09 -0000
Received: (qmail 1179 invoked by uid 22791); 19 Jul 2010 16:15:57 -0000
X-SWARE-Spam-Status: No, hits=-1.8 required=5.0	tests=AWL,BAYES_00,DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,FREEMAIL_FROM,RCVD_IN_DNSWL_NONE
X-Spam-Check-By: sourceware.org
Received: from mail-pz0-f47.google.com (HELO mail-pz0-f47.google.com) (209.85.210.47)    by sourceware.org (qpsmtpd/0.43rc1) with ESMTP; Mon, 19 Jul 2010 16:15:51 +0000
Received: by pzk2 with SMTP id 2so2097527pzk.20        for <gcc-patches@gcc.gnu.org>; Mon, 19 Jul 2010 09:15:49 -0700 (PDT)
MIME-Version: 1.0
Received: by 10.142.147.7 with SMTP id u7mr7206709wfd.219.1279556147866; Mon, 	19 Jul 2010 09:15:47 -0700 (PDT)
Received: by 10.142.226.18 with HTTP; Mon, 19 Jul 2010 09:15:47 -0700 (PDT)
In-Reply-To: <87oce3lagn.fsf@basil.nowhere.org>
References: <4C4035C3.9080305@codesourcery.com>	<4C40A5BD.9080208@redhat.com>	<4C40F005.3060507@codesourcery.com>	<AANLkTimnDbQ0XEbp-CLFUwQiJTX9OwTN9YvfczoxsPsp@mail.gmail.com>	<4C41BD52.5040905@codesourcery.com>	<4C447222.7080500@redhat.com>	<87oce3lagn.fsf@basil.nowhere.org>
Date: Mon, 19 Jul 2010 16:16:00 -0000
Message-ID: <AANLkTikviyUnzS9teiVUWxCJcW5NJJKYfRqGTp5tAZe1@mail.gmail.com>
Subject: Re: x86_64 varargs setup jump table
From: "H.J. Lu" <hjl.tools@gmail.com>
To: Andi Kleen <andi@firstfloor.org>
Cc: Richard Henderson <rth@redhat.com>, Bernd Schmidt <bernds@codesourcery.com>, 	GCC Patches <gcc-patches@gcc.gnu.org>, ubizjak@gmail.com
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable
X-IsSubscribed: yes
Mailing-List: contact gcc-patches-help@gcc.gnu.org; run by ezmlm
Precedence: bulk
List-Id: <gcc-patches.gcc.gnu.org>
List-Archive: <http://gcc.gnu.org/ml/gcc-patches/>
List-Post: <mailto:gcc-patches@gcc.gnu.org>
List-Help: <mailto:gcc-patches-help@gcc.gnu.org>
Sender: gcc-patches-owner@gcc.gnu.org
X-SW-Source: 2010-07/txt/msg01503.txt.bz2

On Mon, Jul 19, 2010 at 9:09 AM, Andi Kleen <andi@firstfloor.org> wrote:
> Richard Henderson <rth@redhat.com> writes:
>
>> On 07/17/2010 07:25 AM, Bernd Schmidt wrote:
>>> =A0 =A0 =A0leaq =A0 =A00(,%rax,4), %rcx
>>> =A0 =A0 =A0movl =A0 =A0$.L2, %eax
>>> =A0 =A0 =A0subq =A0 =A0%rcx, %rax
>>> =A0 =A0 =A0jmp =A0 =A0 *%rax
>>
>> I've often thought this was over-engineering in the x86_64 abi.
>> This jump table is trading memory bandwidth for unpredictability
>> in the branch target.
>
> The other problem with the jump is that if you misdeclare
> the prototype and nothing correct is passed in %eax

FWIW, we DON'T support varargs without correct prototype
on x86-64. See AVX support in x86-64 psABI for details.


--=20
H.J.