From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S262281AbUKQLsP (ORCPT ); Wed, 17 Nov 2004 06:48:15 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S262282AbUKQLsO (ORCPT ); Wed, 17 Nov 2004 06:48:14 -0500 Received: from mx1.redhat.com ([66.187.233.31]:51401 "EHLO mx1.redhat.com") by vger.kernel.org with ESMTP id S262281AbUKQLsN (ORCPT ); Wed, 17 Nov 2004 06:48:13 -0500 From: David Howells In-Reply-To: <20041116182841.4ff7f2e5.akpm@osdl.org> References: <20041116182841.4ff7f2e5.akpm@osdl.org> <2315.1100630906@redhat.com> To: Andrew Morton Cc: Linus Torvalds , hch@infradead.org, linux-kernel@vger.kernel.org Subject: Re: [RFC] Making compound pages mandatory User-Agent: EMH/1.14.1 SEMI/1.14.5 (Awara-Onsen) FLIM/1.14.5 (Demachiyanagi) APEL/10.6 Emacs/21.3 (i386-redhat-linux-gnu) MULE/5.0 (SAKAKI) MIME-Version: 1.0 (generated by SEMI 1.14.5 - "Awara-Onsen") Content-Type: text/plain; charset=US-ASCII Date: Wed, 17 Nov 2004 11:47:55 +0000 Message-ID: <17704.1100692075@redhat.com> Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org > Yes, it's just the single pointer chase. Probably that's the common case > now, because everyone will be enabling hugepages on lots of architectures. No, it's not just the single pointer chase. See my email to Linus. I would, however, be willing to endorse the use of PG_compound, especially under !MMU conditions for two reasons: (1) Safety. The current mechanism of managing intermediate pages is potentially fragile under uClinux. (2) put_page() and get_page() aren't actually called all that often compared to other things, especially under uClinux. David