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 S1752284AbdBINf3 (ORCPT <rfc822;w@1wt.eu>);
        Thu, 9 Feb 2017 08:35:29 -0500
Received: from bombadil.infradead.org ([65.50.211.133]:57987 "EHLO
        bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1751289AbdBINfZ (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Thu, 9 Feb 2017 08:35:25 -0500
Date: Thu, 9 Feb 2017 13:14:58 +0100
From: Peter Zijlstra <peterz@infradead.org>
To: Uladzislau Rezki <urezki@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>, LKML <linux-kernel@vger.kernel.org>,
        Uladzislau 2 Rezki <uladzislau2.rezki@sonymobile.com>
Subject: Re: [RFC,v2 1/3] sched: set loop_max after rq lock is taken
Message-ID: <20170209121458.GC6500@twins.programming.kicks-ass.net>
References: <1486543409-11493-1-git-send-email-urezki@gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <1486543409-11493-1-git-send-email-urezki@gmail.com>
User-Agent: Mutt/1.5.23.1 (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

On Wed, Feb 08, 2017 at 09:43:27AM +0100, Uladzislau Rezki wrote:
> From: Uladzislau 2 Rezki <uladzislau2.rezki@sonymobile.com>
> 
> While doing a load balance there is a race in setting
> loop_max variable since nr_running can be changed causing
> incorect iteration loops.
> 
> As a result we may skip some candidates or check the same
> tasks again.

When doing the actual migration we'll drop this lock again and
nr_running can change again.

This cannot be done perfectly, all of load-balancing is riddled with
races like this, nobody cares.