From mboxrd@z Thu Jan  1 00:00:00 1970
From: Avi Kivity <avi@redhat.com>
Subject: Re: [PATCH] KVM:VMX: Add support for Pause-Loop Exiting
Date: Wed, 08 Jul 2009 07:43:56 +0300
Message-ID: <4A54240C.3050407@redhat.com>
References: <20090708033235.GA577@edwin-srv.sh.intel.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
Cc: kvm@vger.kernel.org
To: "Zhai, Edwin" <edwin.zhai@intel.com>
Return-path: <kvm-owner@vger.kernel.org>
Received: from mx2.redhat.com ([66.187.237.31]:47045 "EHLO mx2.redhat.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1751149AbZGHEnl (ORCPT <rfc822;kvm@vger.kernel.org>);
	Wed, 8 Jul 2009 00:43:41 -0400
In-Reply-To: <20090708033235.GA577@edwin-srv.sh.intel.com>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

On 07/08/2009 06:32 AM, Zhai, Edwin wrote:
>
>   /*
> + * Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE
> + * exiting, so only get here on cpu with PAUSE-Loop-Exiting.
> + */
> +static int handle_pause(struct kvm_vcpu *vcpu,
> +				struct kvm_run *kvm_run)
> +{
> +	skip_emulated_instruction(vcpu);
> +	yield();
> +	return 1;
> +}
> +
>    

yield() does nothing in Linux.  Please look at 
http://lkml.org/lkml/2009/5/11/294 for what needs to be added to the 
scheduler (that message is part of a thread discussing the same feature 
for svm).

-- 
I have a truly marvellous patch that fixes the bug which this
signature is too narrow to contain.