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 S1752737AbdJaIMN (ORCPT <rfc822;w@1wt.eu>);
        Tue, 31 Oct 2017 04:12:13 -0400
Received: from mail-pf0-f196.google.com ([209.85.192.196]:44107 "EHLO
        mail-pf0-f196.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1751378AbdJaIMJ (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Tue, 31 Oct 2017 04:12:09 -0400
X-Google-Smtp-Source: ABhQp+T5Mt5WJ/ghkt92lr/ZvmsSv011ehn/X5hghe3iPKzYjs4qF3ua0Q6zVSx2Qhsp6e+tA2xLPw==
Subject: Re: [PATCH 0/3] KVM: MMU: fix kvm_is_mmio_pfn()
To: Haozhong Zhang <haozhong.zhang@intel.com>, kvm@vger.kernel.org,
        x86@kernel.org
Cc: linux-kernel@vger.kernel.org, Paolo Bonzini <pbonzini@redhat.com>,
        rkrcmar@redhat.com, Xiao Guangrong <xiaoguangrong.eric@gmail.com>,
        Dan Williams <dan.j.williams@intel.com>,
        ivan.d.cuevas.escareno@intel.com, karthik.kumar@intel.com,
        Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@redhat.com>,
        "H. Peter Anvin" <hpa@zytor.com>, Borislav Petkov <bp@suse.de>,
        Mikulas Patocka <mpatocka@redhat.com>,
        Tom Lendacky <thomas.lendacky@amd.com>
References: <20171027022524.22589-1-haozhong.zhang@intel.com>
From: Xiao Guangrong <guangrong.xiao@gmail.com>
Message-ID: <6828fd44-f883-3f90-3e7c-1246300f4c41@gmail.com>
Date: Tue, 31 Oct 2017 16:12:29 +0800
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101
 Thunderbird/52.3.0
MIME-Version: 1.0
In-Reply-To: <20171027022524.22589-1-haozhong.zhang@intel.com>
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Language: en-US
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 10/27/2017 10:25 AM, Haozhong Zhang wrote:
> [I just copy the commit message from patch 3]
> 
> By default, KVM treats a reserved page as for MMIO purpose, and maps
> it to guest with UC memory type.  However, some reserved pages are not
> for MMIO, such as pages of DAX device (e.g., /dev/daxX.Y). Mapping
> them with UC memory type will harm the performance.  In order to
> exclude those cases, we check the host cache mode in addition and only
> treat UC/UC- pages as MMIO.
> 

I am afraid that is not only a performance issue but also a architecture
bug - it could trigger MCE as there is alias memory mapping (a page mapped
as both WB and UC).

It may hurt mdev device as well as the device memory may be both mapped
at host and VM.