From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner+w=401wt.eu-S1758458AbXKNDCu@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1758458AbXKNDCu (ORCPT <rfc822;w@1wt.eu>);
	Tue, 13 Nov 2007 22:02:50 -0500
Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754675AbXKNDCm
	(ORCPT <rfc822;linux-kernel-outgoing>);
	Tue, 13 Nov 2007 22:02:42 -0500
Received: from terminus.zytor.com ([198.137.202.10]:55437 "EHLO
	terminus.zytor.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1754534AbXKNDCl (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Tue, 13 Nov 2007 22:02:41 -0500
Message-ID: <473A6471.4040700@zytor.com>
Date: Tue, 13 Nov 2007 18:58:57 -0800
From: "H. Peter Anvin" <hpa@zytor.com>
User-Agent: Thunderbird 2.0.0.5 (X11/20070727)
MIME-Version: 1.0
To: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
CC: akpm@linux-foundation.org, linux-kernel@vger.kernel.org,
       Andi Kleen <ak@muc.de>, Chuck Ebbert <cebbert@redhat.com>,
       Christoph Hellwig <hch@infradead.org>,
       Jeremy Fitzhardinge <jeremy@goop.org>
Subject: Re: [patch 5/8] Immediate Values - x86 Optimization (update 2)
References: <20071113192445.GA1463@Krystal> <4739FCA0.4040702@zytor.com> <20071113194550.GA4400@Krystal> <473A017D.2030501@zytor.com> <20071113204033.GB7450@Krystal> <473A166E.3070708@zytor.com> <20071113220227.GB9057@Krystal> <473A26A2.7090007@zytor.com> <20071114003409.GA18032@Krystal> <473A4909.1020609@zytor.com> <20071114014445.GB19901@Krystal>
In-Reply-To: <20071114014445.GB19901@Krystal>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
X-Mailing-List: linux-kernel@vger.kernel.org

Mathieu Desnoyers wrote:
> Immediate Values - x86 Optimization
> 
> x86 optimization of the immediate values which uses a movl with code patching
> to set/unset the value used to populate the register used as variable source.
> 
> Changelog:
> - Use text_poke_early with cr0 WP save/restore to patch the bypass. We are doing
>   non atomic writes to a code region only touched by us (nobody can execute it
>   since we are protected by the immediate_mutex).
> - Put immediate_set and _immediate_set in the architecture independent header.
> - Use $0 instead of %2 with (0) operand.
> - Add x86_64 support, ready for i386+x86_64 -> x86 merge.
> - Use asm-x86/asm.h.
> 
> Ok, so the most flexible solution that I see, that should fit for both
> i386 and x86_64 would be :
> 1 byte  : "=Q" : Any register accessible as rh: a, b, c, and d.
> 2, 4 bytes : "=R" : Legacy register—the eight integer registers available
>                  on all i386 processors (a, b, c, d, si, di, bp, sp). 8
> bytes : (only for x86_64)
>           "=r" : A register operand is allowed provided that it is in a
>                  general register.
> That should make sure x86_64 won't try to use REX prefixed opcodes for
> 1, 2 and 4 bytes values.
> 

I just had a couple of utterly sick ideas.

Consider this variant (this example is for a 32-bit immediate on x86-64, 
but the obvious macroizations apply):

	.section __discard,"a",@progbits
1:	movl $0x12345678,%r9d
2:
	.previous

	.section __immediate,"a",@progbits
	.quad foo_immediate, (3f)-4, 4
	.previous
	
	.org . + ((-.-(2b-1b)) & 3), 0x90
	movl $0x12345678,%r9d
3:


The idea is that the instruction is emitted into a section, which is 
marked DISCARD in the linker script.  That lets us actually measure the 
length, and since we know the immediate is always at the end of the 
instruction... done!

	-hpa