From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S965717AbXCMMLW (ORCPT ); Tue, 13 Mar 2007 08:11:22 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S965714AbXCMMLW (ORCPT ); Tue, 13 Mar 2007 08:11:22 -0400 Received: from smtp.osdl.org ([65.172.181.24]:43759 "EHLO smtp.osdl.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S965702AbXCMMLV (ORCPT ); Tue, 13 Mar 2007 08:11:21 -0400 Date: Tue, 13 Mar 2007 05:11:09 -0800 From: Andrew Morton To: Nick Piggin Cc: clameter@sgi.com, linux-mm@kvack.org, linux-kernel@vger.kernel.org Subject: Re: [QUICKLIST 0/4] Arch independent quicklists V2 Message-Id: <20070313051109.3215104b.akpm@linux-foundation.org> In-Reply-To: <45F69287.8040509@yahoo.com.au> References: <20070313071325.4920.82870.sendpatchset@schroedinger.engr.sgi.com> <20070313005334.853559ca.akpm@linux-foundation.org> <45F65ADA.9010501@yahoo.com.au> <20070313035250.f908a50e.akpm@linux-foundation.org> <45F685C6.8070806@yahoo.com.au> <20070313041551.565891b5.akpm@linux-foundation.org> <45F68B4B.9020200@yahoo.com.au> <20070313044756.b45649ac.akpm@linux-foundation.org> <45F69287.8040509@yahoo.com.au> X-Mailer: Sylpheed version 2.2.4 (GTK+ 2.8.19; i686-pc-linux-gnu) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org > On Tue, 13 Mar 2007 23:01:11 +1100 Nick Piggin wrote: > Andrew Morton wrote: > >>On Tue, 13 Mar 2007 22:30:19 +1100 Nick Piggin wrote: > >>We don't actually have to zap_pte_range the entire page table in > >>order to free it (IIRC we used to have to, before the 4lpt patches). > > > > > > I'm trying to remember why we ever would have needed to zero out the pagetable > > pages if we're taking down the whole mm? Maybe it's because "oh, the > > arch wants to put this page into a quicklist to recycle it", which is > > all rather circular. > > > > It would be interesting to look at a) leave the page full of random garbage > > if we're releasing the whole mm and b) return it straight to the page allocator. > > Well we have the 'fullmm' case, which avoids all the locked pte operations > (for those architectures where hardware pt walking requires atomicity). I suspect there are some tlb operations which could be skipped in that case too. > However we still have to visit those to-be-unmapped parts of the page table > to find the pages and free them. So we still at least need to bring it into > cache for the read... at which point, the store probably isn't a big burden. It means all that data has to be written back. Yes, I expect it'll prove to be less costly than the initial load.