public inbox for linuxppc-dev@ozlabs.org 
 help / color / mirror / Atom feed
From: Wen Congyang <wency@cn•fujitsu.com>
To: 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
Cc: len.brown@intel•com,
	Yasuaki ISIMATU <isimatu.yasuaki@jp•fujitsu.com>,
	paulus@samba•org, minchan.kim@gmail•com,
	kosaki.motohiro@jp•fujitsu.com, rientjes@google•com,
	cl@linux•com, akpm@linux-foundation•org, liuj97@gmail•com
Subject: [RFC PATCH v5 17/19] memory_hotplug: clear zone when the memory is removed
Date: Fri, 27 Jul 2012 18:35:22 +0800	[thread overview]
Message-ID: <50126EEA.4070209@cn.fujitsu.com> (raw)
In-Reply-To: <50126B83.3050201@cn.fujitsu.com>

From: Yasuaki Ishimatsu <isimatu.yasuaki@jp•fujitsu.com>

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 these when the memory is
removed. Add a new function __remove_zone() to do this.

CC: David Rientjes <rientjes@google•com>
CC: Jiang Liu <liuj97@gmail•com>
CC: Len Brown <len.brown@intel•com>
CC: Benjamin Herrenschmidt <benh@kernel•crashing.org>
CC: Paul Mackerras <paulus@samba•org>
CC: Christoph Lameter <cl@linux•com>
Cc: Minchan Kim <minchan.kim@gmail•com>
CC: Andrew Morton <akpm@linux-foundation•org>
CC: KOSAKI Motohiro <kosaki.motohiro@jp•fujitsu.com>
CC: Wen Congyang <wency@cn•fujitsu.com>
Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp•fujitsu.com>
---
 mm/memory_hotplug.c |  181 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 181 insertions(+), 0 deletions(-)

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 859425c..5ac035f 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -300,10 +300,187 @@ 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(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;
+
+		return start_pfn;
+	}
+
+	return 0;
+}
+
+/* find the biggest valid pfn in the range [start_pfn, end_pfn). */
+static int find_biggest_section_pfn(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;
+
+		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;
+
+	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(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(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 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;
+
+	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(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(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 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))
@@ -313,6 +490,10 @@ 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);
-- 
1.7.1

  parent reply	other threads:[~2012-07-27 10:30 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-07-27 10:20 [RFC PATCH v5 00/19] memory-hotplug: hot-remove physical memory Wen Congyang
2012-07-27 10:22 ` [RFC PATCH 0/19] firmware_map : unify argument of firmware_map_add_early/hotplug Wen Congyang
2012-07-27 10:24 ` [PATCH 0.5/19] remove memory info from list before freeing it Wen Congyang
2012-07-27 10:25 ` [RFC PATCH v5 01/19] memory-hotplug: rename remove_memory() to offline_memory()/offline_pages() Wen Congyang
2012-07-27 10:26 ` [RFC PATCH v5 02/19] memory-hotplug: implement offline_memory() Wen Congyang
2012-07-27 10:27 ` [RFC PATCH v5 03/19] memory-hotplug: store the node id in acpi_memory_device Wen Congyang
2012-07-27 10:27 ` [RFC PATCH v5 04/19] memory-hotplug: offline and remove memory when removing the memory device Wen Congyang
2012-07-27 10:28 ` [RFC PATCH v5 05/19] memory-hotplug: check whether memory is present or not Wen Congyang
2012-07-27 20:17   ` Tony Luck
2012-07-30  1:57     ` Wen Congyang
2012-07-27 10:28 ` [RFC PATCH v5 06/19] memory-hotplug: export the function acpi_bus_remove() Wen Congyang
2012-07-27 10:29 ` [RFC PATCH v5 07/19] memory-hotplug: call acpi_bus_remove() to remove memory device Wen Congyang
2012-07-27 10:30 ` [RFC PATCH v5 08/19] memory-hotplug: remove /sys/firmware/memmap/X sysfs Wen Congyang
2012-07-27 10:30 ` [RFC PATCH v5 09/19] memory-hotplug: does not release memory region in PAGES_PER_SECTION chunks Wen Congyang
2012-07-27 10:31 ` [RFC PATCH v5 10/19] memory-hotplug: add memory_block_release Wen Congyang
2012-07-27 10:31 ` [RFC PATCH v5 11/19] memory-hotplug: remove_memory calls __remove_pages Wen Congyang
2012-07-27 10:32 ` [RFC PATCH v5 12/19] memory-hotplug: introduce new function arch_remove_memory() Wen Congyang
2012-07-30 10:23   ` Heiko Carstens
2012-07-30 10:35     ` Wen Congyang
2012-07-31 12:40       ` Gerald Schaefer
2012-08-01  1:42         ` Wen Congyang
2012-08-01  2:44   ` jencce zhou
2012-08-01  6:06     ` Wen Congyang
2012-07-27 10:32 ` [RFC PATCH v5 13/19] memory-hotplug: check page type in get_page_bootmem Wen Congyang
2012-07-27 10:33 ` [RFC PATCH v5 14/19] memory-hotplug: move register_page_bootmem_info_node and put_page_bootmem for sparse-vmemmap Wen Congyang
2012-07-27 10:34 ` [RFC PATCH v5 15/19] memory-hotplug: implement register_page_bootmem_info_section of sparse-vmemmap Wen Congyang
2012-07-27 10:34 ` [RFC PATCH v5 16/19] memory-hotplug: free memmap " Wen Congyang
2012-07-31 12:22   ` Gerald Schaefer
2012-08-01  6:09     ` Wen Congyang
2012-07-27 10:35 ` Wen Congyang [this message]
2012-07-27 10:35 ` [RFC PATCH v5 00/19] memory-hotplug: hot-remove physical memory Yasuaki Ishimatsu
2012-07-27 10:35 ` [RFC PATCH v5 18/19] memory-hotplug: add node_device_release Wen Congyang
2012-07-27 10:36 ` [RFC PATCH v5 19/19] memory-hotplug: remove sysfs file of node Wen Congyang
2012-07-27 10:45   ` Yasuaki Ishimatsu
2012-07-30  2:03     ` Wen Congyang
2012-07-30  3:47     ` Wen Congyang

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=50126EEA.4070209@cn.fujitsu.com \
    --to=wency@cn$(echo .)fujitsu.com \
    --cc=akpm@linux-foundation$(echo .)org \
    --cc=cl@linux$(echo .)com \
    --cc=cmetcalf@tilera$(echo .)com \
    --cc=isimatu.yasuaki@jp$(echo .)fujitsu.com \
    --cc=kosaki.motohiro@jp$(echo .)fujitsu.com \
    --cc=len.brown@intel$(echo .)com \
    --cc=linux-acpi@vger$(echo .)kernel.org \
    --cc=linux-ia64@vger$(echo .)kernel.org \
    --cc=linux-kernel@vger$(echo .)kernel.org \
    --cc=linux-mm@kvack$(echo .)org \
    --cc=linux-s390@vger$(echo .)kernel.org \
    --cc=linux-sh@vger$(echo .)kernel.org \
    --cc=linuxppc-dev@lists$(echo .)ozlabs.org \
    --cc=liuj97@gmail$(echo .)com \
    --cc=minchan.kim@gmail$(echo .)com \
    --cc=paulus@samba$(echo .)org \
    --cc=rientjes@google$(echo .)com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox