From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id ; Mon, 17 Sep 2001 13:06:26 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id ; Mon, 17 Sep 2001 13:06:17 -0400 Received: from intranet.resilience.com ([209.245.157.33]:21889 "EHLO intranet.resilience.com") by vger.kernel.org with ESMTP id ; Mon, 17 Sep 2001 13:06:04 -0400 Mime-Version: 1.0 Message-Id: In-Reply-To: In-Reply-To: Date: Mon, 17 Sep 2001 10:06:21 -0700 To: linux-kernel@vger.kernel.org From: Jonathan Lundell Subject: Re: [Q] Implementation of spin_lock on i386: why "rep;nop" ? Content-Type: text/plain; charset="us-ascii" ; format="flowed" Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org At 12:42 PM -0400 2001-09-17, Richard B. Johnson wrote: > > What is the intent behind this "rep;nop" ? Does it really rely on an > > undocumented behaviour ? > >Well it's now documented although you have to search a web-site to >find it. Basically, it runs the CPU at low clock-speed when it's >busy-waiting. Since most all spin-locks lock for mere microseconds >it's unlikely that it does anything useful, but it can't hurt. Sounds like a good opportunity for a comment.... -- /Jonathan Lundell.