From mboxrd@z Thu Jan  1 00:00:00 1970
From: Tejun Heo <tj@kernel.org>
Subject: Re: WARNING: kernel/smp.c:292 smp_call_function_single [Was: mmotm
 2009-11-24-16-47 uploaded]
Date: Mon, 30 Nov 2009 19:45:34 +0900
Message-ID: <4B13A24E.1080100@kernel.org>
References: <200911250111.nAP1BFg5030254@imap1.linux-foundation.org>  <4B0FEA3E.5050108@gmail.com> <1259335036.6483.440.camel@laptop> <alpine.LFD.2.00.0911271730330.24119@localhost.localdomain> <4B1113C0.30505@redhat.com> <4B138950.9040905@kernel.org> <alpine.LFD.2.00.0911301055000.24119@localhost.localdomain>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Cc: Avi Kivity <avi@redhat.com>, Peter Zijlstra <peterz@infradead.org>,
	Jiri Slaby <jirislaby@gmail.com>, linux-kernel@vger.kernel.org,
	akpm@linux-foundation.org, mm-commits@vger.kernel.org,
	Marcelo Tosatti <mtosatti@redhat.com>, kvm@vger.kernel.org,
	the arch/x86 maintainers <x86@kernel.org>,
	Ingo Molnar <mingo@elte.hu>
To: Thomas Gleixner <tglx@linutronix.de>
Return-path: <linux-kernel-owner+glk-linux-kernel-3=40m.gmane.org-S1752854AbZK3Ksg@vger.kernel.org>
In-Reply-To: <alpine.LFD.2.00.0911301055000.24119@localhost.localdomain>
Sender: linux-kernel-owner@vger.kernel.org
List-Id: kvm.vger.kernel.org

Hello,

On 11/30/2009 07:02 PM, Thomas Gleixner wrote:
> No, it _CANNOT_ be preempted at that point:
> 
> schedule()
> {
> 	preempt_disable();
> 
> 	switch_to();
> 
> 	preempt_enable();
> }

Yes, you're right.

>> For the time being, maybe it's best to back out the fix given that the
>> only architecture which may be affected by the original bug is ia64
>> which is the only one with both kvm and the unlocked context switch.
> 
> Do you have a pointer to the original bug report ?

Nope, I was referring to the imaginary race condition, so there's no
bug to worry about.  The only problem is the asymmetry between in and
out callbacks.  Then again, it's not really possible to match them on
unlocked ctxsw archs anyway, so I guess the only thing to do is to
document the context difference between in and out.

Sorry about the fuss.  I'll send out patch to revert it and document
the difference.

Thanks.

-- 
tejun