From mboxrd@z Thu Jan  1 00:00:00 1970
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Subject: Re: [RFC PATCH kernel] vfio-pci: Allow write combining
Date: Wed, 18 Oct 2017 16:21:12 +0200
Message-ID: <1508336472.25065.305.camel@kernel.crashing.org>
References: <20171009025000.39435-1-aik@ozlabs.ru>
         <20171010155515.39a0c5fe@t450s.home>
         <ba3257c6-b15c-b5ce-9015-53e5e2be65d6@ozlabs.ru>
         <20171010204256.309715ce@t450s.home>
         <26fbe3b7-c54b-87a5-799d-22f4f043edd2@ozlabs.ru>
         <1507736107.25065.222.camel@kernel.crashing.org>
         <7ad2ee73-80dc-69ef-c98a-63b020f2f48b@ozlabs.ru>
         <20171016060043.GC2776@umbus.fritz.box>
         <67742d45-a267-0363-7448-7f8945f84c95@ozlabs.ru>
         <1508143098.25065.277.camel@kernel.crashing.org>
         <9111f1d5-98cc-4e02-cc34-c4a69f091df2@ozlabs.ru>
         <1508312024.25065.300.camel@kernel.crashing.org>
         <da06ea87-6f31-d6b7-eb70-be5915ade62a@ozlabs.ru>
Mime-Version: 1.0
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: 7bit
Cc: Alex Williamson <alex.williamson@redhat.com>, kvm@vger.kernel.org,
        Eric Auger <eric.auger@redhat.com>,
        Paul Mackerras <paulus@samba.org>
To: Alexey Kardashevskiy <aik@ozlabs.ru>,
        David Gibson <david@gibson.dropbear.id.au>
Return-path: <kvm-owner@vger.kernel.org>
Received: from gate.crashing.org ([63.228.1.57]:34282 "EHLO gate.crashing.org"
        rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
        id S1751136AbdJROVj (ORCPT <rfc822;kvm@vger.kernel.org>);
        Wed, 18 Oct 2017 10:21:39 -0400
In-Reply-To: <da06ea87-6f31-d6b7-eb70-be5915ade62a@ozlabs.ru>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

On Wed, 2017-10-18 at 20:00 +1100, Alexey Kardashevskiy wrote:
> > 
> > With radix, the HW will honor the G bit set in the guest page tables.
> 
> 
> I am sure that you know better, Paul just pointed me to this:
> 
> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/arch/powerpc/kvm/book3s_64_mmu_radix.c?h=v4.13#n403

It's in the architecture somewhere, if you look at 3.0B in the radix
section about nested radix, there's a table for the nesting of
attributes.

Here you'll see that regardless of the G bit value set by the host,
the HW will use the G bit value set by the guest.

However, we should still provide a way to exploit WC if anything for
things like DPDK.

Cheers,
Ben.