From mboxrd@z Thu Jan  1 00:00:00 1970
From: Radim =?utf-8?B?S3LEjW3DocWZ?= <rkrcmar@redhat.com>
Subject: Re: [PATCH 10/10] kvm: vmx: handle VMEXIT from SGX Enclave
Date: Tue, 27 Jun 2017 17:29:17 +0200
Message-ID: <20170627152917.GB1503@potion>
References: <20170508052434.3627-1-kai.huang@linux.intel.com>
 <20170508052434.3627-11-kai.huang@linux.intel.com>
 <23e2cc83-8cbf-07f7-56c0-6fe422bac06e@redhat.com>
 <e5a61678-c37f-7919-c8e5-e977f51cf1e2@linux.intel.com>
 <0fe15915-1d2a-288e-bfec-9096412cc26f@linux.intel.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Cc: Paolo Bonzini <pbonzini@redhat.com>,
        Kai Huang <kaih.linux@gmail.com>, kvm@vger.kernel.org
To: "Huang, Kai" <kai.huang@linux.intel.com>
Return-path: <kvm-owner@vger.kernel.org>
Received: from mx1.redhat.com ([209.132.183.28]:51392 "EHLO mx1.redhat.com"
        rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
        id S1752481AbdF0P3W (ORCPT <rfc822;kvm@vger.kernel.org>);
        Tue, 27 Jun 2017 11:29:22 -0400
Content-Disposition: inline
In-Reply-To: <0fe15915-1d2a-288e-bfec-9096412cc26f@linux.intel.com>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

2017-06-19 17:02+1200, Huang, Kai:
> Hi Paolo, all,
> 
> Sorry for reply late.

I'm sorry as well,

> Do you think it is feasible to turn on PLE again on another further VMEXIT?
> Or another VMEXIT that is not from enclave?
> 
> Any suggestions so that I can improve in next version RFC?

KVM doesn't enable "PAUSE exiting", it enables "PAUSE loop exiting".
SDM recommends disabling "PAUSE exiting" because the VM exits
(fault-like) on every PAUSE and needs intervention in order to progress,
but SDM doesn't say to disable "PAUSE loop exiting".

Being inside an enclave doesn't change the usefulness of PLE (yielding
the CPU to a task that isn't blocked), so I think it would be best to do
nothing with it, thanks.