From mboxrd@z Thu Jan 1 00:00:00 1970 From: Will Deacon Subject: Re: [PATCH 2/4] locking/qrwlock: Reduce reader/writer to reader lock transfer latency Date: Wed, 8 Jul 2015 18:19:49 +0100 Message-ID: <20150708171949.GE6348@arm.com> References: <20150706182353.GC1607@arm.com> <559ADBCD.6020803@hp.com> <20150707091711.GA23879@arm.com> <20150707111731.GQ3644@twins.programming.kicks-ass.net> <20150707114918.GG23879@arm.com> <559BE27E.6060901@hp.com> <20150707172718.GJ23879@arm.com> <20150707181002.GK23879@arm.com> <559C44CE.7070701@hp.com> <20150708095248.GZ3644@twins.programming.kicks-ass.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from foss.arm.com ([217.140.101.70]:42594 "EHLO foss.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1759028AbbGHRTy (ORCPT ); Wed, 8 Jul 2015 13:19:54 -0400 Content-Disposition: inline In-Reply-To: <20150708095248.GZ3644@twins.programming.kicks-ass.net> Sender: linux-arch-owner@vger.kernel.org List-ID: To: Peter Zijlstra Cc: Waiman Long , Ingo Molnar , Arnd Bergmann , Thomas Gleixner , "linux-arch@vger.kernel.org" , "linux-kernel@vger.kernel.org" , Scott J Norton , Douglas Hatch On Wed, Jul 08, 2015 at 10:52:48AM +0100, Peter Zijlstra wrote: > On Tue, Jul 07, 2015 at 05:29:50PM -0400, Waiman Long wrote: > > I prefer the current setting as you won't know if the writer has the > > lock or not when you take a snapshot of the value of the lock. You > > need the whole time sequence in this case to figure it out and so will > > be more prone to error. > > I still need to wake up, but I suspect we need to change > queue_read_{try,}lock() to use cmpxchg/inc_not_zero like things, which > is fine for ARM, but not so much for x86. > > So I think I agree with Waiman, but am willing to be shown differently. That's fine; I just wanted to make sure I wasn't going round the twist! Will