From mboxrd@z Thu Jan  1 00:00:00 1970
Return-path: <ak@linux.intel.com>
Received: from mga03.intel.com ([134.134.136.65])
	by Galois.linutronix.de with esmtps (TLS1.2:DHE_RSA_AES_256_CBC_SHA256:256)
	(Exim 4.80)
	(envelope-from <ak@linux.intel.com>)
	id 1fBqsq-00066H-Vo
	for speck@linutronix.de; Fri, 27 Apr 2018 02:05:06 +0200
Date: Thu, 26 Apr 2018 17:05:01 -0700
From: Andi Kleen <ak@linux.intel.com>
Subject: [MODERATED] Re: [PATCH 1/6] Patch 1
Message-ID: <20180427000501.GB75137@tassilo.jf.intel.com>
References: <20180425181152.GK14273@tassilo.jf.intel.com>
 <alpine.LFD.2.21.999.1804251114010.31078@i7.lan>
 <20180425185140.GL14273@tassilo.jf.intel.com>
 <alpine.LFD.2.21.999.1804251313340.3798@i7.lan>
 <20180425211901.GN14273@tassilo.jf.intel.com>
 <alpine.LFD.2.21.999.1804251518570.31078@i7.lan>
 <20180425231238.GO14273@tassilo.jf.intel.com>
 <alpine.LFD.2.21.999.1804251618070.18170@i7.lan>
 <20180426135429.GT17484@dhcp22.suse.cz>
 <alpine.LFD.2.21.999.1804260949280.19565@i7.lan>
MIME-Version: 1.0
In-Reply-To: <alpine.LFD.2.21.999.1804260949280.19565@i7.lan>
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 7bit
To: speck@linutronix.de
List-ID: <speck.linutronix.de>

> That, in turn, means that if you have a desktop chip with only 40 bits of 
> physical addressing, now that the offset starts at bit 9, you still have 
> to have 30 bits of offset actually *in use* until bit 39 ends up being 
> clear.

Here are the cases for modern Intel CPUs:

    Nehalem Client                                  39      >=0.25TB
    Nehalem Server                                  44      >=8TB
    SandyBridge/IvyBridge/Haswell/Broadwell/Skylake 46      >=32TB

In general anything newer has 46 bits

> Anybody willing to test and/or double-check my math/logic?

I did some tests and it works and seems to do the right thing. I'll
use this patch in the next version of the patchkit. Thanks.

-Andi