From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id <S263433AbRFNRcr>; Thu, 14 Jun 2001 13:32:47 -0400
Received: (majordomo@vger.kernel.org) by vger.kernel.org
	id <S263435AbRFNRci>; Thu, 14 Jun 2001 13:32:38 -0400
Received: from pizda.ninka.net ([216.101.162.242]:58545 "EHLO pizda.ninka.net")
	by vger.kernel.org with ESMTP id <S263432AbRFNRcU>;
	Thu, 14 Jun 2001 13:32:20 -0400
From: "David S. Miller" <davem@redhat.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Message-ID: <15144.62749.724491.941190@pizda.ninka.net>
Date: Thu, 14 Jun 2001 10:32:13 -0700 (PDT)
To: root@chaos.analogic.com
Cc: Linux kernel <linux-kernel@vger.kernel.org>
Subject: Re: SMP spin-locks
In-Reply-To: <Pine.LNX.3.95.1010614132506.10137B-100000@chaos.analogic.com>
In-Reply-To: <Pine.LNX.3.95.1010614132506.10137B-100000@chaos.analogic.com>
X-Mailer: VM 6.75 under 21.1 (patch 13) "Crater Lake" XEmacs Lucid
Sender: linux-kernel-owner@vger.kernel.org
X-Mailing-List: linux-kernel@vger.kernel.org


Richard B. Johnson writes:
 > Spin-locks now transfer control to the .text.lock segment.
 > This is a separate segment that can be at an offset that
 > is far away from the currently executing code. That may
 > cause the cache to be reloaded. Further, each spin-lock
 > invocation generates separate code within that segment.
 > 
 > Question 1: Why?

Because this increases the code density of the common
case, getting the lock immediately.

 > Question 2: What is the purpose of the code sequence, "repz nop" 
 > generated by the spin-lock code? Is this a processor BUG work-around?
 > `as` doesn't "like" this sequence and, Intel doesn't seem to
 > document it.

It is a hint to the processor that we are executing a spinlock loop
(it does something wrt. keeping the cacheline of the lock in shared
state when possible).

I believe it is documented in the Pentium 4 manuals, previous chips
ignore this sequence and treat it as a pure nop from what I understand.

Later,
David S. Miller
davem@redhat.com