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 S1751252AbdJBOOC (ORCPT <rfc822;w@1wt.eu>);
        Mon, 2 Oct 2017 10:14:02 -0400
Received: from foss.arm.com ([217.140.101.70]:37574 "EHLO foss.arm.com"
        rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
        id S1751065AbdJBOOA (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
        Mon, 2 Oct 2017 10:14:00 -0400
Date: Mon, 2 Oct 2017 15:14:00 +0100
From: Will Deacon <will.deacon@arm.com>
To: qiaozhou <qiaozhou@asrmicro.com>
Cc: Vikram Mulukutla <markivx@codeaurora.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        John Stultz <john.stultz@linaro.org>, sboyd@codeaurora.org,
        LKML <linux-kernel@vger.kernel.org>,
        Wang Wilbur <wilburwang@asrmicro.com>,
        Marc Zyngier <marc.zyngier@arm.com>,
        Peter Zijlstra <peterz@infradead.org>,
        linux-kernel-owner@vger.kernel.org, sudeep.holla@arm.com
Subject: Re: [Question]: try to fix contention between expire_timers and
 try_to_del_timer_sync
Message-ID: <20171002141400.GB12847@arm.com>
References: <dcb18367-c747-96a8-9927-d8ba6954c496@asrmicro.com>
 <e1cc02c5e7dfd4d6bec937b6dc97bfc7@codeaurora.org>
 <20170728092831.GA24839@arm.com>
 <2aa9684cf9c889ee9fdc8550b4388af6@codeaurora.org>
 <20170731131321.GB1737@arm.com>
 <a858eaf3973979d0759ee016d39887e3@codeaurora.org>
 <20170815184039.GE10801@arm.com>
 <9f86bd426bbaede9de6d38cb047bd6fa@codeaurora.org>
 <e3812c7a1202ee79101406e7003dff9a@codeaurora.org>
 <8817730a-9581-240c-8de0-e6c96c20e9ec@asrmicro.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <8817730a-9581-240c-8de0-e6c96c20e9ec@asrmicro.com>
User-Agent: Mutt/1.5.23 (2014-03-12)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

Hi Qiao,

On Mon, Sep 25, 2017 at 07:02:03PM +0800, qiaozhou wrote:
> Will this bodging patch be merged? It can solve the livelock issue on arm64
> platforms(at least improve a lot).

Whilst it seemed to help in some cases, I'm not keen to merge it until
we've identified a sensible way to parameterise the threshold and also
explain why it doens't appear to help at all on some platforms. I guess
I could respin a version that takes the threshold on the cmdline and
also checks to see that the event stream is enabled, since that might
help with further benchmarking.

Would that be useful?

Will