Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759311Ab2J2Pe6 (ORCPT ); Mon, 29 Oct 2012 11:34:58 -0400 Received: from mail-pa0-f46.google.com ([209.85.220.46]:44125 "EHLO mail-pa0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752348Ab2J2Pey (ORCPT ); Mon, 29 Oct 2012 11:34:54 -0400 Message-ID: <508EA207.2060205@gmail.com> Date: Mon, 29 Oct 2012 23:34:31 +0800 From: Jianguo Wu User-Agent: Mozilla/5.0 (Windows NT 6.1; rv:14.0) Gecko/20120713 Thunderbird/14.0 MIME-Version: 1.0 To: wency@cn.fujitsu.com CC: x86@kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, linux-acpi@vger.kernel.org, linux-s390@vger.kernel.org, linux-sh@vger.kernel.org, linux-ia64@vger.kernel.org, cmetcalf@tilera.com, sparclinux@vger.kernel.org, rientjes@google.com, liuj97@gmail.com, len.brown@intel.com, benh@kernel.crashing.org, paulus@samba.org, cl@linux.com, minchan.kim@gmail.com, akpm@linux-foundation.org, kosaki.motohiro@jp.fujitsu.com, isimatu.yasuaki@jp.fujitsu.com Subject: Re: [PATCH v2 10/12] memory-hotplug: memory_hotplug: clear zone when removing the memory References: <1350988250-31294-1-git-send-email-wency@cn.fujitsu.com> <1350988250-31294-11-git-send-email-wency@cn.fujitsu.com> In-Reply-To: <1350988250-31294-11-git-send-email-wency@cn.fujitsu.com> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 8228 Lines: 264 On 2012/10/23 18:30, wency@cn.fujitsu.com wrote: > From: Yasuaki Ishimatsu > > When a memory is added, we update zone's and pgdat's start_pfn and > spanned_pages in the function __add_zone(). So we should revert them > when the memory is removed. > > The patch adds a new function __remove_zone() to do this. > > CC: David Rientjes > CC: Jiang Liu > CC: Len Brown > CC: Christoph Lameter > Cc: Minchan Kim > CC: Andrew Morton > CC: KOSAKI Motohiro > Signed-off-by: Yasuaki Ishimatsu > Signed-off-by: Wen Congyang > --- > mm/memory_hotplug.c | 207 +++++++++++++++++++++++++++++++++++++++++++++++++++ > 1 files changed, 207 insertions(+), 0 deletions(-) > > diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c > index 03153cf..55a228d 100644 > --- a/mm/memory_hotplug.c > +++ b/mm/memory_hotplug.c > @@ -312,10 +312,213 @@ static int __meminit __add_section(int nid, struct zone *zone, > return register_new_memory(nid, __pfn_to_section(phys_start_pfn)); > } > > +/* find the smallest valid pfn in the range [start_pfn, end_pfn) */ > +static int find_smallest_section_pfn(int nid, struct zone *zone, > + unsigned long start_pfn, > + unsigned long end_pfn) > +{ > + struct mem_section *ms; > + > + for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SECTION) { > + ms = __pfn_to_section(start_pfn); > + > + if (unlikely(!valid_section(ms))) > + continue; > + > + if (unlikely(pfn_to_nid(start_pfn)) != nid) if (unlikely(pfn_to_nid(start_pfn) != nid)) > + continue; > + > + if (zone && zone != page_zone(pfn_to_page(start_pfn))) > + continue; > + > + return start_pfn; > + } > + > + return 0; > +} > + > +/* find the biggest valid pfn in the range [start_pfn, end_pfn). */ > +static int find_biggest_section_pfn(int nid, struct zone *zone, > + unsigned long start_pfn, > + unsigned long end_pfn) > +{ > + struct mem_section *ms; > + unsigned long pfn; > + > + /* pfn is the end pfn of a memory section. */ > + pfn = end_pfn - 1; > + for (; pfn >= start_pfn; pfn -= PAGES_PER_SECTION) { > + ms = __pfn_to_section(pfn); > + > + if (unlikely(!valid_section(ms))) > + continue; > + > + if (unlikely(pfn_to_nid(pfn)) != nid) if (unlikely(pfn_to_nid(pfn) != nid)) > + continue; > + > + if (zone && zone != page_zone(pfn_to_page(pfn))) > + continue; > + > + return pfn; > + } > + > + return 0; > +} > + > +static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, > + unsigned long end_pfn) > +{ > + unsigned long zone_start_pfn = zone->zone_start_pfn; > + unsigned long zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages; > + unsigned long pfn; > + struct mem_section *ms; > + int nid = zone_to_nid(zone); > + > + zone_span_writelock(zone); > + if (zone_start_pfn == start_pfn) { > + /* > + * If the section is smallest section in the zone, it need > + * shrink zone->zone_start_pfn and zone->zone_spanned_pages. > + * In this case, we find second smallest valid mem_section > + * for shrinking zone. > + */ > + pfn = find_smallest_section_pfn(nid, zone, end_pfn, > + zone_end_pfn); > + if (pfn) { > + zone->zone_start_pfn = pfn; > + zone->spanned_pages = zone_end_pfn - pfn; > + } > + } else if (zone_end_pfn == end_pfn) { > + /* > + * If the section is biggest section in the zone, it need > + * shrink zone->spanned_pages. > + * In this case, we find second biggest valid mem_section for > + * shrinking zone. > + */ > + pfn = find_biggest_section_pfn(nid, zone, zone_start_pfn, > + start_pfn); > + if (pfn) > + zone->spanned_pages = pfn - zone_start_pfn + 1; > + } > + > + /* > + * The section is not biggest or smallest mem_section in the zone, it > + * only creates a hole in the zone. So in this case, we need not > + * change the zone. But perhaps, the zone has only hole data. Thus > + * it check the zone has only hole or not. > + */ > + pfn = zone_start_pfn; > + for (; pfn < zone_end_pfn; pfn += PAGES_PER_SECTION) { > + ms = __pfn_to_section(pfn); > + > + if (unlikely(!valid_section(ms))) > + continue; > + > + if (page_zone(pfn_to_page(pfn)) != zone) > + continue; > + > + /* If the section is current section, it continues the loop */ > + if (start_pfn == pfn) > + continue; > + > + /* If we find valid section, we have nothing to do */ > + zone_span_writeunlock(zone); > + return; > + } > + > + /* The zone has no valid section */ > + zone->zone_start_pfn = 0; > + zone->spanned_pages = 0; > + zone_span_writeunlock(zone); > +} > + > +static void shrink_pgdat_span(struct pglist_data *pgdat, > + unsigned long start_pfn, unsigned long end_pfn) > +{ > + unsigned long pgdat_start_pfn = pgdat->node_start_pfn; > + unsigned long pgdat_end_pfn = > + pgdat->node_start_pfn + pgdat->node_spanned_pages; > + unsigned long pfn; > + struct mem_section *ms; > + int nid = pgdat->node_id; > + > + if (pgdat_start_pfn == start_pfn) { > + /* > + * If the section is smallest section in the pgdat, it need > + * shrink pgdat->node_start_pfn and pgdat->node_spanned_pages. > + * In this case, we find second smallest valid mem_section > + * for shrinking zone. > + */ > + pfn = find_smallest_section_pfn(nid, NULL, end_pfn, > + pgdat_end_pfn); > + if (pfn) { > + pgdat->node_start_pfn = pfn; > + pgdat->node_spanned_pages = pgdat_end_pfn - pfn; > + } > + } else if (pgdat_end_pfn == end_pfn) { > + /* > + * If the section is biggest section in the pgdat, it need > + * shrink pgdat->node_spanned_pages. > + * In this case, we find second biggest valid mem_section for > + * shrinking zone. > + */ > + pfn = find_biggest_section_pfn(nid, NULL, pgdat_start_pfn, > + start_pfn); > + if (pfn) > + pgdat->node_spanned_pages = pfn - pgdat_start_pfn + 1; > + } > + > + /* > + * If the section is not biggest or smallest mem_section in the pgdat, > + * it only creates a hole in the pgdat. So in this case, we need not > + * change the pgdat. > + * But perhaps, the pgdat has only hole data. Thus it check the pgdat > + * has only hole or not. > + */ > + pfn = pgdat_start_pfn; > + for (; pfn < pgdat_end_pfn; pfn += PAGES_PER_SECTION) { > + ms = __pfn_to_section(pfn); > + > + if (unlikely(!valid_section(ms))) > + continue; > + > + if (pfn_to_nid(pfn) != nid) > + continue; > + > + /* If the section is current section, it continues the loop */ > + if (start_pfn == pfn) > + continue; > + > + /* If we find valid section, we have nothing to do */ > + return; > + } > + > + /* The pgdat has no valid section */ > + pgdat->node_start_pfn = 0; > + pgdat->node_spanned_pages = 0; > +} > + > +static void __remove_zone(struct zone *zone, unsigned long start_pfn) > +{ > + struct pglist_data *pgdat = zone->zone_pgdat; > + int nr_pages = PAGES_PER_SECTION; > + int zone_type; > + unsigned long flags; > + > + zone_type = zone - pgdat->node_zones; > + > + pgdat_resize_lock(zone->zone_pgdat, &flags); > + shrink_zone_span(zone, start_pfn, start_pfn + nr_pages); > + shrink_pgdat_span(pgdat, start_pfn, start_pfn + nr_pages); > + pgdat_resize_unlock(zone->zone_pgdat, &flags); > +} > + > static int __remove_section(struct zone *zone, struct mem_section *ms) > { > unsigned long flags; > struct pglist_data *pgdat = zone->zone_pgdat; > + unsigned long start_pfn; > + int scn_nr; > int ret = -EINVAL; > > if (!valid_section(ms)) > @@ -325,6 +528,10 @@ static int __remove_section(struct zone *zone, struct mem_section *ms) > if (ret) > return ret; > > + scn_nr = __section_nr(ms); > + start_pfn = section_nr_to_pfn(scn_nr); > + __remove_zone(zone, start_pfn); > + > pgdat_resize_lock(pgdat, &flags); > sparse_remove_one_section(zone, ms); > pgdat_resize_unlock(pgdat, &flags); > -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/