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 S964878AbbESP7a (ORCPT <rfc822;w@1wt.eu>);
	Tue, 19 May 2015 11:59:30 -0400
Received: from mx1.redhat.com ([209.132.183.28]:39405 "EHLO mx1.redhat.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S964842AbbESP72 (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
	Tue, 19 May 2015 11:59:28 -0400
From: Vitaly Kuznetsov <vkuznets@redhat.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: devel@linuxdriverproject.org, "K. Y. Srinivasan" <kys@microsoft.com>,
        Haiyang Zhang <haiyangz@microsoft.com>, linux-kernel@vger.kernel.org,
        Dexuan Cui <decui@microsoft.com>, Ingo Molnar <mingo@kernel.org>,
        "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
        "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Radim =?utf-8?B?S3LEjW3DocWZ?= <rkrcmar@redhat.com>
Subject: Re: [PATCH 1/2] cpu-hotplug: export cpu_hotplug_enable/cpu_hotplug_disable
References: <1432037742-25923-1-git-send-email-vkuznets@redhat.com>
	<1432037742-25923-2-git-send-email-vkuznets@redhat.com>
	<20150519151939.GG3644@twins.programming.kicks-ass.net>
Date: Tue, 19 May 2015 17:58:47 +0200
In-Reply-To: <20150519151939.GG3644@twins.programming.kicks-ass.net> (Peter
	Zijlstra's message of "Tue, 19 May 2015 17:19:39 +0200")
Message-ID: <87vbfo4kzs.fsf@vitty.brq.redhat.com>
User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/24.3 (gnu/linux)
MIME-Version: 1.0
Content-Type: text/plain
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

Peter Zijlstra <peterz@infradead.org> writes:

> On Tue, May 19, 2015 at 02:15:41PM +0200, Vitaly Kuznetsov wrote:
>> Loaded Hyper-V module will use these functions to disable CPU hotplug
>> under certain circumstances.
>
> What's wrong with get_online_cpus() ?

We need to disable cpu offlining permanently (till the module is
unloaded but this is highly unlikely). If we do get_online_cpus()
instead we get

# echo 0 > /sys/devices/system/cpu/cpu1/online 
<nothing happens, pemanent hang followed by the following:>

[  240.247109] INFO: task bash:972 blocked for more than 120 seconds.
[  240.248937]       Not tainted 4.1.0-rc3_bug1167380_test_rkr+ #602
[  240.250515] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs"
disables this message.
[  240.252379] bash            D ffff880021b83c18     0   972    939
0x00000004
[  240.255068]  ffff880021b83c18 0000000000000001 0000000000000046
ffff880021b83be8
[  240.258140]  ffffffff81fdcdb0 ffff880037dbcfc0 ffff880037203bd0
ffffffff81fdcdb8
[  240.261275]  ffff880021b84000 0000000000000001 0000000000000000
0000000000000001
[  240.264402] Call Trace:
[  240.265423]  [<ffffffff81aecf77>] schedule+0x37/0x90
[  240.266748]  [<ffffffff81081872>] cpu_hotplug_begin+0xd2/0xe0
[  240.268210]  [<ffffffff810817a5>] ? cpu_hotplug_begin+0x5/0xe0
[  240.269675]  [<ffffffff810cb860>] ? prepare_to_wait_event+0xf0/0xf0
[  240.271285]  [<ffffffff81ad561a>] _cpu_down+0x8a/0x300
[  240.275294]  [<ffffffff81ad58c6>] cpu_down+0x36/0x50
[  240.276680]  [<ffffffff8160f954>] cpu_subsys_offline+0x14/0x20
[  240.278145]  [<ffffffff8160a505>] device_offline+0xa5/0xd0
[  240.279618]  [<ffffffff8160a620>] online_store+0x50/0xa0
[  240.280991]  [<ffffffff81607678>] dev_attr_store+0x18/0x30
...

And if we do the cpu_hotplug_disable() call we get:
# echo 0 > /sys/devices/system/cpu/cpu1/online 
-bash: echo: write error: Device or resource busy

This behavior is preferable.

-- 
  Vitaly