From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from psmtp.com (na3sys010amx153.postini.com [74.125.245.153]) by kanga.kvack.org (Postfix) with SMTP id B2F446B004D for ; Tue, 13 Nov 2012 06:37:44 -0500 (EST) Date: Tue, 13 Nov 2012 11:37:39 +0000 From: Mel Gorman Subject: Re: [PATCH 06/19] mm: numa: teach gup_fast about pmd_numa Message-ID: <20121113113739.GX8218@suse.de> References: <1352193295-26815-1-git-send-email-mgorman@suse.de> <1352193295-26815-7-git-send-email-mgorman@suse.de> <20121113100735.GC21522@gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-15 Content-Disposition: inline In-Reply-To: <20121113100735.GC21522@gmail.com> Sender: owner-linux-mm@kvack.org List-ID: To: Ingo Molnar Cc: Peter Zijlstra , Andrea Arcangeli , Rik van Riel , Johannes Weiner , Hugh Dickins , Thomas Gleixner , Linus Torvalds , Andrew Morton , Linux-MM , LKML On Tue, Nov 13, 2012 at 11:07:36AM +0100, Ingo Molnar wrote: > > * Mel Gorman wrote: > > > From: Andrea Arcangeli > > > > When scanning pmds, the pmd may be of numa type (_PAGE_PRESENT not set), > > however the pte might be present. Therefore, gup_pmd_range() must return > > 0 in this case to avoid losing a NUMA hinting page fault during gup_fast. > > > > Note: gup_fast will skip over non present ptes (like numa > > types), so no explicit check is needed for the pte_numa case. > > [...] > > So, why not fix all architectures that choose to expose > pte_numa() and pmd_numa() methods - via the patch below? > I'll pick it up. Thanks. -- Mel Gorman SUSE Labs -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753425Ab2KMLhp (ORCPT ); Tue, 13 Nov 2012 06:37:45 -0500 Received: from cantor2.suse.de ([195.135.220.15]:50291 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752816Ab2KMLho (ORCPT ); Tue, 13 Nov 2012 06:37:44 -0500 Date: Tue, 13 Nov 2012 11:37:39 +0000 From: Mel Gorman To: Ingo Molnar Cc: Peter Zijlstra , Andrea Arcangeli , Rik van Riel , Johannes Weiner , Hugh Dickins , Thomas Gleixner , Linus Torvalds , Andrew Morton , Linux-MM , LKML Subject: Re: [PATCH 06/19] mm: numa: teach gup_fast about pmd_numa Message-ID: <20121113113739.GX8218@suse.de> References: <1352193295-26815-1-git-send-email-mgorman@suse.de> <1352193295-26815-7-git-send-email-mgorman@suse.de> <20121113100735.GC21522@gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-15 Content-Disposition: inline In-Reply-To: <20121113100735.GC21522@gmail.com> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Nov 13, 2012 at 11:07:36AM +0100, Ingo Molnar wrote: > > * Mel Gorman wrote: > > > From: Andrea Arcangeli > > > > When scanning pmds, the pmd may be of numa type (_PAGE_PRESENT not set), > > however the pte might be present. Therefore, gup_pmd_range() must return > > 0 in this case to avoid losing a NUMA hinting page fault during gup_fast. > > > > Note: gup_fast will skip over non present ptes (like numa > > types), so no explicit check is needed for the pte_numa case. > > [...] > > So, why not fix all architectures that choose to expose > pte_numa() and pmd_numa() methods - via the patch below? > I'll pick it up. Thanks. -- Mel Gorman SUSE Labs