From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755004AbbCCI26 (ORCPT ); Tue, 3 Mar 2015 03:28:58 -0500 Received: from e28smtp07.in.ibm.com ([122.248.162.7]:49202 "EHLO e28smtp07.in.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754650AbbCCI2z (ORCPT ); Tue, 3 Mar 2015 03:28:55 -0500 From: "Aneesh Kumar K.V" To: Joonsoo Kim , Andrew Morton Cc: Rik van Riel , Johannes Weiner , Mel Gorman , Laura Abbott , Minchan Kim , Heesub Shin , Marek Szyprowski , Michal Nazarewicz , linux-mm@kvack.org, linux-kernel@vger.kernel.org, Hui Zhu , Gioh Kim , Bartlomiej Zolnierkiewicz , Ritesh Harjani , Vlastimil Babka , Joonsoo Kim Subject: Re: [RFC 13/16] mm/cma: populate ZONE_CMA and use this zone when GFP_HIGHUSERMOVABLE In-Reply-To: <1423726340-4084-14-git-send-email-iamjoonsoo.kim@lge.com> References: <1423726340-4084-1-git-send-email-iamjoonsoo.kim@lge.com> <1423726340-4084-14-git-send-email-iamjoonsoo.kim@lge.com> User-Agent: Notmuch/0.19+30~gd241a48 (http://notmuchmail.org) Emacs/24.3.1 (x86_64-pc-linux-gnu) Date: Tue, 03 Mar 2015 13:58:46 +0530 Message-ID: <87vbiia3i9.fsf@linux.vnet.ibm.com> MIME-Version: 1.0 Content-Type: text/plain X-TM-AS-MML: disable X-Content-Scanned: Fidelis XPS MAILER x-cbid: 15030308-0025-0000-0000-0000039BE3D7 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Joonsoo Kim writes: > Until now, reserved pages for CMA are managed altogether with normal > page in the same zone. This approach has numorous problems and fixing > them isn't easy. To fix this situation, ZONE_CMA is introduced in > previous patch, but, not yet populated. This patch implement population > of ZONE_CMA by stealing reserved pages from normal zones. This stealing > break one uncertain assumption on zone, that is, zone isn't overlapped. > In the early of this series, some check is inserted to every zone's span > iterator to handle zone overlap so there would be no problem with > this assumption break. > > To utilize this zone, user should use GFP_HIGHUSERMOVABLE, because > these pages are only applicable for movable type and ZONE_CMA could > contain highmem. > > Implementation itself is very easy to understand. Do steal when cma > area is initialized and recalculate values for per zone data structure. > > Signed-off-by: Joonsoo Kim > --- > include/linux/gfp.h | 10 ++++++++-- > include/linux/mm.h | 1 + > mm/cma.c | 23 ++++++++++++++++------- > mm/page_alloc.c | 42 +++++++++++++++++++++++++++++++++++++++--- > 4 files changed, 64 insertions(+), 12 deletions(-) > > diff --git a/include/linux/gfp.h b/include/linux/gfp.h > index 619eb20..d125440 100644 > --- a/include/linux/gfp.h > +++ b/include/linux/gfp.h > @@ -186,6 +186,12 @@ static inline int gfpflags_to_migratetype(const gfp_t gfp_flags) > #define OPT_ZONE_DMA32 ZONE_NORMAL > #endif > > +#ifdef CONFIG_CMA > +#define OPT_ZONE_CMA ZONE_CMA > +#else > +#define OPT_ZONE_CMA ZONE_MOVABLE > +#endif > + Does that mean with CONFIG_CMA we always try ZONE_CMA first and then fallback to ZONE_MOVABLE ? If so won't we hit termporary CMA allocation failures that can result with pinned movable pages ? -aneesh