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 S1161627Ab3DKSH6 (ORCPT <rfc822;w@1wt.eu>);
	Thu, 11 Apr 2013 14:07:58 -0400
Received: from www.sr71.net ([198.145.64.142]:48940 "EHLO blackbird.sr71.net"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1161570Ab3DKSH4 (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
	Thu, 11 Apr 2013 14:07:56 -0400
Message-ID: <5166FBFB.2030703@sr71.net>
Date: Thu, 11 Apr 2013 11:07:55 -0700
From: Dave Hansen <dave@sr71.net>
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:17.0) Gecko/20130329 Thunderbird/17.0.5
MIME-Version: 1.0
To: Thomas Gleixner <tglx@linutronix.de>
CC: Borislav Petkov <bp@alien8.de>,
        "Srivatsa S. Bhat" <srivatsa.bhat@linux.vnet.ibm.com>,
        LKML <linux-kernel@vger.kernel.org>, Dave Jones <davej@redhat.com>,
        dhillf@gmail.com, Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@kernel.org>
Subject: Re: [PATCH] kthread: Prevent unpark race which puts threads on the
 wrong cpu
References: <515F457E.5050505@sr71.net> <515FCAC6.8090806@linux.vnet.ibm.com> <alpine.LFD.2.02.1304061019000.21884@ionos> <alpine.LFD.2.02.1304071119100.21884@ionos> <20130407095025.GA31307@pd.tnic> <alpine.LFD.2.02.1304081122040.21884@ionos> <20130408115553.GA4395@pd.tnic> <alpine.LFD.2.02.1304081415570.21884@ionos> <alpine.LFD.2.02.1304091635430.21884@ionos> <516439DF.3050901@sr71.net> <alpine.LFD.2.02.1304092036431.21884@ionos> <alpine.LFD.2.02.1304092126150.21884@ionos> <51647C30.3050109@sr71.net> <alpine.LFD.2.02.1304101024010.21884@ionos> <alpine.LFD.2.02.1304101250320.21884@ionos> <5165C087.4060404@sr71.net> <alpine.LFD.2.02.1304111020520.21884@ionos>
In-Reply-To: <alpine.LFD.2.02.1304111020520.21884@ionos>
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On 04/11/2013 03:19 AM, Thomas Gleixner wrote:
> --- linux-2.6.orig/kernel/smpboot.c
> +++ linux-2.6/kernel/smpboot.c
> @@ -185,8 +185,18 @@ __smpboot_create_thread(struct smp_hotpl
>  	}
>  	get_task_struct(tsk);
>  	*per_cpu_ptr(ht->store, cpu) = tsk;
> -	if (ht->create)
> -		ht->create(cpu);
> +	if (ht->create) {
> +		/*
> +		 * Make sure that the task has actually scheduled out
> +		 * into park position, before calling the create
> +		 * callback. At least the migration thread callback
> +		 * requires that the task is off the runqueue.
> +		 */
> +		if (!wait_task_inactive(tsk, TASK_PARKED))
> +			WARN_ON(1);
> +		else
> +			ht->create(cpu);
> +	}
>  	return 0;
>  }

This one appears to be doing the trick.  I'll run the cpus in an
online/offline loop for a bit and make sure it's stable.  It's passed
several round so far, which is way more than it's done up to this point,
though.