From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from pippin.tausq.org (gandalf.tausq.org [64.81.244.94]) by dsl2.external.hp.com (Postfix) with ESMTP id D04DE48A2 for ; Mon, 15 Mar 2004 00:43:46 -0700 (MST) Date: Sun, 14 Mar 2004 23:43:46 -0800 From: Randolph Chung To: Carlos O'Donell Subject: Re: [parisc-linux] Spinlock patch, take 2 Message-ID: <20040315074346.GD2384@tausq.org> References: <20040315063318.GC2384@tausq.org> <20040315073740.GA660@baldric.uwo.ca> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: <20040315073740.GA660@baldric.uwo.ca> Cc: parisc-linux@lists.parisc-linux.org Reply-To: Randolph Chung List-Id: parisc-linux developers list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , > Looks beautiful. Is it measurably faster, or just semantically more > correct than the existing implementation? :) i have not done any measurements. the spinlock_t stuff is needed since we've agreed that the attribute((aligned(16)) is not sufficient to guarantee correct alignment. the atomic-lock optimization is based on some discussions we had a few months ago. i'd like to actually try these, but we still don't have a bootable SMP kernel yet :( randolph -- Randolph Chung Debian GNU/Linux Developer, hppa/ia64 ports http://www.tausq.org/