From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754968Ab0JNIcG (ORCPT ); Thu, 14 Oct 2010 04:32:06 -0400 Received: from fgwmail6.fujitsu.co.jp ([192.51.44.36]:43220 "EHLO fgwmail6.fujitsu.co.jp" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754935Ab0JNIcE (ORCPT ); Thu, 14 Oct 2010 04:32:04 -0400 X-SecurityPolicyCheck-FJ: OK by FujitsuOutboundMailChecker v1.3.1 From: KOSAKI Motohiro To: Andrew Morton Subject: Re: [patch] x86: allow ZONE_DMA to be configurable Cc: kosaki.motohiro@jp.fujitsu.com, David Rientjes , Ingo Molnar , "H. Peter Anvin" , Thomas Gleixner , Casey Dahlin , x86@kernel.org, linux-kernel@vger.kernel.org In-Reply-To: <20101014011056.a58bac55.akpm@linux-foundation.org> References: <20101014011056.a58bac55.akpm@linux-foundation.org> Message-Id: <20101014172022.F9F2.A69D9226@jp.fujitsu.com> MIME-Version: 1.0 Content-Type: text/plain; charset="US-ASCII" Content-Transfer-Encoding: 7bit X-Mailer: Becky! ver. 2.50.07 [ja] Date: Thu, 14 Oct 2010 17:32:00 +0900 (JST) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org > On Wed, 13 Oct 2010 17:15:04 -0700 (PDT) David Rientjes wrote: > > > ZONE_DMA is unnecessary for a large number of machines that do not > > require addressing in the lower 16MB of memory because they do not use > > ISA devices with 16-bit address registers (plus one page byte register). > > > > This patch allows users to disable ZONE_DMA for x86 if they know they > > will not be using such devices with their kernel. > > > > This prevents the VM from unnecessarily reserving a ratio of memory > > (defaulting to 1/256th of system capacity) with lowmem_reserve_ratio > > for such allocations when it will never be used. > > > > I wonder how hard it would be to do this at runtime, probably with a > boot parameter. > > I'd be a little concerned at the effects of this on page reclaim and > the page allocator - it might expose weird pre-existing bugs or > inefficiencies. But we can cross that bridge when we fall off it, I > guess. In this case, completely ZONE disablling is not required. 16MB saving is not big matter. To prevent userland process use lower zone is necessary. I have such patch, because 32bit highmem system has similar requirement. (user process want to only use ZONE_HIGHMEM, otherwize ZONE_NORMAL easily exshost) I'll prepare to post them if necessary.