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 S932471AbcDAKzI (ORCPT <rfc822;w@1wt.eu>);
	Fri, 1 Apr 2016 06:55:08 -0400
Received: from bombadil.infradead.org ([198.137.202.9]:55980 "EHLO
	bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S932450AbcDAKzE (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Fri, 1 Apr 2016 06:55:04 -0400
Date: Fri, 1 Apr 2016 12:54:57 +0200
From: Peter Zijlstra <peterz@infradead.org>
To: Will Deacon <will.deacon@arm.com>
Cc: Waiman Long <waiman.long@hpe.com>, Ingo Molnar <mingo@redhat.com>,
        linux-kernel@vger.kernel.org, Scott J Norton <scott.norton@hpe.com>,
        Douglas Hatch <doug.hatch@hpe.com>
Subject: Re: [PATCH] locking/qrwlock: Allow multiple spinning readers
Message-ID: <20160401105457.GO3430@twins.programming.kicks-ass.net>
References: <1458444079-59601-1-git-send-email-Waiman.Long@hpe.com>
 <20160329202050.GN3408@twins.programming.kicks-ass.net>
 <56FDA0D6.4090904@hpe.com>
 <20160401103143.GJ3448@twins.programming.kicks-ass.net>
 <20160401104119.GA3604@arm.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20160401104119.GA3604@arm.com>
User-Agent: Mutt/1.5.21 (2012-12-30)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Fri, Apr 01, 2016 at 11:41:19AM +0100, Will Deacon wrote:
> On Fri, Apr 01, 2016 at 12:31:43PM +0200, Peter Zijlstra wrote:
> > On Thu, Mar 31, 2016 at 06:12:38PM -0400, Waiman Long wrote:
> > > >>However, if we allow a limited number of readers to spin on the
> > > >>lock simultaneously, we can eliminates some of the reader-to-reader
> > > >>latencies at the expense of a bit more cacheline contention and
> > > >>probably more power consumption.
> > > >So the embedded people might not like that much.
> > > 
> > > It could be. It is always a compromise.
> > 
> > So ARM is the only one that currently waits without spinning and could
> > care; so Will might have an opinion. One 'solution' would be to make
> > this an optional feature.
> 
> Well, perhaps we could built this using the cmp-and-wait structure we spoke
> about a couple of months back. What happened with that? Is there something I
> need to go implement for ARM/arm64?

Ah, yes, I forgot about that. Lemme go find that discussions and see
what I can do there.