From owner-freebsd-hackers@FreeBSD.ORG  Sun May 20 07:01:51 2012
Return-Path: <owner-freebsd-hackers@FreeBSD.ORG>
Delivered-To: freebsd-hackers@freebsd.org
Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34])
	by hub.freebsd.org (Postfix) with ESMTP id 484E4106564A;
	Sun, 20 May 2012 07:01:51 +0000 (UTC) (envelope-from zec@fer.hr)
Received: from mail.zvne.fer.hr (mail.zvne.fer.hr [161.53.66.5])
	by mx1.freebsd.org (Postfix) with ESMTP id 8E7A78FC08;
	Sun, 20 May 2012 07:01:50 +0000 (UTC)
Received: from munja.zvne.fer.hr (161.53.66.248) by mail.zvne.fer.hr
	(161.53.66.5) with Microsoft SMTP Server id 14.2.298.4; Sun, 20 May 2012
	09:01:43 +0200
Received: from sluga.fer.hr ([161.53.66.244]) by munja.zvne.fer.hr with
	Microsoft SMTPSVC(6.0.3790.4675);	 Sun, 20 May 2012 09:01:43 +0200
Received: from localhost ([161.53.19.8]) by sluga.fer.hr with Microsoft
	SMTPSVC(6.0.3790.4675);	 Sun, 20 May 2012 09:01:42 +0200
From: Marko Zec <zec@fer.hr>
To: <freebsd-hackers@freebsd.org>
Date: Sun, 20 May 2012 09:01:32 +0200
User-Agent: KMail/1.9.10
MIME-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Content-Disposition: inline
Message-ID: <201205200901.32613.zec@fer.hr>
X-OriginalArrivalTime: 20 May 2012 07:01:42.0696 (UTC)
	FILETIME=[69658280:01CD3656]
Cc: freebsd-amd64@freebsd.org
Subject: superpages and kmem on amd64
X-BeenThere: freebsd-hackers@freebsd.org
X-Mailman-Version: 2.1.5
Precedence: list
List-Id: Technical Discussions relating to FreeBSD
	<freebsd-hackers.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-hackers>, 
	<mailto:freebsd-hackers-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-hackers>
List-Post: <mailto:freebsd-hackers@freebsd.org>
List-Help: <mailto:freebsd-hackers-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-hackers>,
	<mailto:freebsd-hackers-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Sun, 20 May 2012 07:01:51 -0000

Hi all,

I'm playing with an algorithm which makes use of large contiguous blocks of 
kernel memory (ranging from 1M to 1G in size), so it would be nice if those 
could be somehow forcibly mapped to superpages.  I was hoping that the VM 
system would automagically map (merge) contiguous 4k pages to superpages, but 
apparently it doesn't:

vm.pmap.pdpe.demotions: 2
vm.pmap.pde.promotions: 543
vm.pmap.pde.p_failures: 266253
vm.pmap.pde.mappings: 0
vm.pmap.pde.demotions: 31

I.e. I have 1G of kmem allocated using via 

malloc(1024 * 1024 * 1024, M_TEMP, M_NOWAIT);

but vm.pmap.pde.mappings: 0 suggests that no superpages are in use.

Is there an alternative kernel memory allocation method which might force 
superpages to be used for contiguous memory blocks?  And how do I find more 
details about page mappings for a given kmem virtual address?  I'm running 
8.3-STABLE on amd64.

Thanks,

Marko