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 S1759361AbcILNG3 (ORCPT <rfc822;w@1wt.eu>);
        Mon, 12 Sep 2016 09:06:29 -0400
Received: from mx1.redhat.com ([209.132.183.28]:47950 "EHLO mx1.redhat.com"
        rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
        id S1758472AbcILNG0 (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
        Mon, 12 Sep 2016 09:06:26 -0400
Date: Mon, 12 Sep 2016 15:05:38 +0200
From: Oleg Nesterov <oleg@redhat.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Cheng Chao <cs.os.kernel@gmail.com>, mingo@kernel.org, tj@kernel.org,
        akpm@linux-foundation.org, chris@chris-wilson.co.uk,
        linux-kernel@vger.kernel.org
Subject: Re: [PATCH v3] stop_machine: Make migration_cpu_stop() does useful
        works for CONFIG_PREEMPT_NONE
Message-ID: <20160912130537.GB7984@redhat.com>
References: <1473408834-6122-1-git-send-email-chengchao@kedacom.com> <1473497532-5440-1-git-send-email-cs.os.kernel@gmail.com> <20160912113727.GQ10153@twins.programming.kicks-ass.net> <20160912114108.GP10168@twins.programming.kicks-ass.net>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20160912114108.GP10168@twins.programming.kicks-ass.net>
User-Agent: Mutt/1.5.18 (2008-05-17)
X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.25]); Mon, 12 Sep 2016 13:06:25 +0000 (UTC)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On 09/12, Peter Zijlstra wrote:
>
> --- a/kernel/stop_machine.c
> +++ b/kernel/stop_machine.c
> @@ -121,6 +121,11 @@ int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
>  	cpu_stop_init_done(&done, 1);
>  	if (!cpu_stop_queue_work(cpu, &work))
>  		return -ENOENT;
> +	/*
> +	 * In case @cpu == smp_proccessor_id() we can avoid a sleep+wakeup
> +	 * by doing a preemption.
> +	 */
> +	cond_resched();

Yes, this is what I tried to suggest too.

But this leads to the question which I wanted to ask many times.

Why cond_resched() is not NOP if CONFIG_PREEMPT=y ?

Perhaps we have some users like, just for example,

	preempt_enable_no_resched();
	cond_resched();

which actually want the should_resched() check even if CONFIG_PREEMPT,
but most callers do not?

Oleg.