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 S932559AbbFWRZj (ORCPT <rfc822;w@1wt.eu>);
	Tue, 23 Jun 2015 13:25:39 -0400
Received: from mx1.redhat.com ([209.132.183.28]:39015 "EHLO mx1.redhat.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1754936AbbFWRZc (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
	Tue, 23 Jun 2015 13:25:32 -0400
Date: Tue, 23 Jun 2015 19:24:16 +0200
From: Oleg Nesterov <oleg@redhat.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: paulmck@linux.vnet.ibm.com, tj@kernel.org, mingo@redhat.com,
        linux-kernel@vger.kernel.org, der.herr@hofr.at, dave@stgolabs.net,
        riel@redhat.com, viro@ZenIV.linux.org.uk,
        torvalds@linux-foundation.org
Subject: Re: [RFC][PATCH 12/13] stop_machine: Remove lglock
Message-ID: <20150623172416.GA27505@redhat.com>
References: <20150622121623.291363374@infradead.org> <20150622122256.765619039@infradead.org> <20150622222152.GA4460@redhat.com> <20150623100932.GB3644@twins.programming.kicks-ass.net> <20150623162024.GA23714@redhat.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20150623162024.GA23714@redhat.com>
User-Agent: Mutt/1.5.18 (2008-05-17)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On 06/23, Oleg Nesterov wrote:
>
>
> It would be nice to remove stop_cpus_mutex, it actually protects
> stop_cpus_work... Then probably stop_two_cpus() can just use
> stop_cpus(). We could simply make stop_cpus_mutex per-cpu too,
> but this doesn't look nice.

IOW. Suppose we add ->work_mutex into struct cpu_stopper. Btw,
I think we should move all per-cpu variables there...

Now,

	lock_stop_cpus_works(cpumask)
	{
		for_each_cpu(cpu, cpumask)
			mutex_lock(per_cpu(cpu_stopper_task, cpu).work_mutex);
	}

	unlock_stop_cpus_works(cpumask)
	{
		for_each_cpu(cpu, cpumask)
			mutex_lock(...);
	}

which should be used instead of stop_cpus_mutex. After this change
stop_two_cpus() can just use stop_cpus().


Off-topic. Can't we make __stop_machine() static? The only caller,
_cpu_down() can safely call stop_machine(), get_online_cpus() is
fine under cpu_hotplug_begin().

Oleg.