From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from e35.co.us.ibm.com ([32.97.110.153]:33592 "EHLO e35.co.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S965985AbXDBWFM (ORCPT ); Mon, 2 Apr 2007 18:05:12 -0400 Subject: Re: [PATCH 1/2] Generic Virtual Memmap suport for SPARSEMEM From: Dave Hansen In-Reply-To: References: <20070401071024.23757.4113.sendpatchset@schroedinger.engr.sgi.com> <1175547000.22373.89.camel@localhost.localdomain> <1175548924.22373.109.camel@localhost.localdomain> <1175550151.22373.116.camel@localhost.localdomain> Content-Type: text/plain Date: Mon, 02 Apr 2007 15:05:05 -0700 Message-Id: <1175551505.22373.126.camel@localhost.localdomain> Mime-Version: 1.0 Content-Transfer-Encoding: 7bit Sender: linux-arch-owner@vger.kernel.org To: Christoph Lameter Cc: linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org, Martin Bligh , linux-mm@kvack.org, Andi Kleen , KAMEZAWA Hiroyuki List-ID: On Mon, 2007-04-02 at 14:53 -0700, Christoph Lameter wrote: > > > Well think about how to handle the case that the allocatiopn of a page > > > table page or a vmemmap block fails. Once we have that sorted out then we > > > can cleanup the higher layers. > > > > I think it is best to just completely replace > > sparse_early_mem_map_alloc() for the vmemmap case. It really is a > > completely different beast. You'd never, for instance, have > > alloc_remap() come into play. > > What is the purpose of alloc_remap? Could not figure that one out. That's what we use on i386 to get some lowmem area for non-zero NUMA nodes. Otherwise, all of ZONE_NORMAL is on node 0. It's a bit hokey, and stuff like virt_to_phys() probably doesn't work on it, but it has worked pretty well for a long time. -- Dave