From mboxrd@z Thu Jan  1 00:00:00 1970
From: Avi Kivity <avi.kivity@gmail.com>
Subject: Re: 2 CPU Conformance Issue in KVM/x86
Date: Tue, 10 Mar 2015 22:38:23 +0200
Message-ID: <54FF563F.1000309@gmail.com>
References: <A6F671BC-983C-4005-87E9-FCC68DEF0D30@gmail.com> <54F58471.7020906@redhat.com> <54FDD39C.9060908@gmail.com> <6073FF8F-E261-4DC3-817A-9F4A46B5C0DB@gmail.com> <54FDE50B.8040408@gmail.com> <13DCF857-5591-4499-9B0D-4165268E9CE8@gmail.com> <54FDF241.8080002@gmail.com> <54FDF6CB.8050209@redhat.com> <54FDF93F.7080502@gmail.com> <54FECBAD.9060809@redhat.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Transfer-Encoding: 7bit
Cc: kvm list <kvm@vger.kernel.org>,
	=?UTF-8?B?UmFkaW0gS3LEjW3DocWZ?= <rkrcmar@redhat.com>
To: Paolo Bonzini <pbonzini@redhat.com>,
	Nadav Amit <nadav.amit@gmail.com>
Return-path: <kvm-owner@vger.kernel.org>
Received: from mail-wi0-f174.google.com ([209.85.212.174]:43725 "EHLO
	mail-wi0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1752998AbbCJUi2 (ORCPT <rfc822;kvm@vger.kernel.org>);
	Tue, 10 Mar 2015 16:38:28 -0400
Received: by widem10 with SMTP id em10so6263429wid.2
        for <kvm@vger.kernel.org>; Tue, 10 Mar 2015 13:38:27 -0700 (PDT)
In-Reply-To: <54FECBAD.9060809@redhat.com>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

On 03/10/2015 12:47 PM, Paolo Bonzini wrote:
>
> On 09/03/2015 20:49, Avi Kivity wrote:
>>> Yes, and it checked that MAXPHYADDR != 52 before.  If you want to set
>>> only one bit, making that bit 51 makes sense anyway for simplicity, so
>>> it is still 99.9% academic.  Once processors appear with MAXPHYADDR =
>>> 52, the remaining 0.1% will become more relevant.
>>>
>>> The current limit is IIRC 46 or 48 (on Haswell Xeons).
>> It will be interesting to have processors with 52 bits of physical
>> address and 48 bits of virtual address. HIGHMEM for x86_64?  Or 5-level
>> page tables?
> I wonder why Intel chose exactly 52...  HIGHMEM seems more likely than
> 5-level page tables.  Certainly it wouldn't need hacks like Ingo's 4G-4G.

My bitcoins are on 5-level page tables.  HIGHMEM is too much pain.

>> 50 bits == 1 PiB.  That's quite an amount of RAM.
> Not that 64 TiB is not "quite an amount of RAM". :)
>
>

Depends on how many browser tabs you have open, I guess.