Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S935991AbXHMWWh (ORCPT ); Mon, 13 Aug 2007 18:22:37 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755841AbXHMWW1 (ORCPT ); Mon, 13 Aug 2007 18:22:27 -0400 Received: from netops-testserver-4-out.sgi.com ([192.48.171.29]:47901 "EHLO relay.sgi.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1754705AbXHMWW0 (ORCPT ); Mon, 13 Aug 2007 18:22:26 -0400 Date: Mon, 13 Aug 2007 15:22:25 -0700 (PDT) From: Christoph Lameter X-X-Sender: clameter@schroedinger.engr.sgi.com To: Andi Kleen cc: Mel Gorman , Lee.Schermerhorn@hp.com, linux-kernel@vger.kernel.org, linux-mm@kvack.org Subject: Re: [PATCH 3/4] Embed zone_id information within the zonelist->zones pointer In-Reply-To: <20070813230801.GH3406@bingen.suse.de> Message-ID: References: <20070809210616.14702.73376.sendpatchset@skynet.skynet.ie> <200708102013.49170.ak@suse.de> <200708110304.55433.ak@suse.de> <20070813225020.GE3406@bingen.suse.de> <20070813225841.GG3406@bingen.suse.de> <20070813230801.GH3406@bingen.suse.de> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1486 Lines: 43 On Tue, 14 Aug 2007, Andi Kleen wrote: > > x86_64 is the only platforms that uses ZONE_DMA32. Ia64 and other 64 bit > > platforms use ZONE_DMA for <4GB allocs. > > Yes, but ZONE_DMA32 == ZONE_DMA. I am not sure what you mean by that. Ia64 ZONE_DMA == x86_84 ZONE_DMA32? > Also when the slab users of GFP_DMA are all gone ia64 won't need > the slab support anymore. So either you change your ifdef in slub or > switch to ZONE_DMA32 for IA64. If you have gotten rid of all slab users of GFP_DMA (and also all arch uses of it) then we can drop the code in SLAB. > The trouble is that this cannot be done globally, at least not > until s390 and a few other architures using GFP_DMA with slab > are all converted. The s390 arch code still contains GFP_DMA uses? No drivers elsewhere still use GFP_DMA? > > > I think s/ZONE_DMA32/ZONE_DMA would restore the one DMA zone thing which > > is good. We could drop all ZONE_DMA32 stuff that is only needed by a > > single arch. > > But it's not quite the same: GFP_DMA32 has no explicit slab support. Right. So we could 1. Drop sl?b support for GFP_DMA. 2. Drop GFP_DMA32 support. Then we only allow page allocator allocs using GFP_DMA? That may be the least invasive for arch code. - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/