From: Tang Chen <tangchen@cn.fujitsu.com>
To: akpm@linux-foundation.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,
kosaki.motohiro@jp.fujitsu.com, isimatu.yasuaki@jp.fujitsu.com,
wujianguo@huawei.com, wency@cn.fujitsu.com,
tangchen@cn.fujitsu.com, hpa@zytor.com, linfeng@cn.fujitsu.com,
laijs@cn.fujitsu.com, mgorman@suse.de, yinghai@kernel.org
Cc: linux-s390@vger.kernel.org, linux-ia64@vger.kernel.org,
linux-acpi@vger.kernel.org, linux-sh@vger.kernel.org,
x86@kernel.org, linux-kernel@vger.kernel.org,
cmetcalf@tilera.com, linux-mm@kvack.org,
sparclinux@vger.kernel.org, linuxppc-dev@lists.ozlabs.org
Subject: [PATCH v5 12/14] memory-hotplug: memory_hotplug: clear zone when removing the memory
Date: Mon, 24 Dec 2012 20:09:22 +0800 [thread overview]
Message-ID: <1356350964-13437-13-git-send-email-tangchen@cn.fujitsu.com> (raw)
In-Reply-To: <1356350964-13437-1-git-send-email-tangchen@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 them
when the memory is removed.
The patch adds a new function __remove_zone() to do this.
Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
---
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 71cb656..a1b0632 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -430,8 +430,211 @@ 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))
+ 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))
+ 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 start_pfn;
+ int scn_nr;
int ret = -EINVAL;
if (!valid_section(ms))
@@ -441,6 +644,10 @@ 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);
+
sparse_remove_one_section(zone, ms);
return 0;
}
--
1.7.1
next prev parent reply other threads:[~2012-12-24 12:10 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-12-24 12:09 [PATCH v5 00/14] memory-hotplug: hot-remove physical memory Tang Chen
2012-12-24 12:09 ` [PATCH v5 01/14] memory-hotplug: try to offline the memory twice to avoid dependence Tang Chen
2012-12-25 8:35 ` Glauber Costa
2012-12-30 5:58 ` Wen Congyang
2013-01-09 15:09 ` Glauber Costa
2013-01-10 1:38 ` Tang Chen
2013-02-06 3:07 ` Tang Chen
2013-02-06 9:17 ` Tang Chen
2013-02-06 10:10 ` Tang Chen
2013-02-06 14:24 ` Glauber Costa
2013-02-07 7:56 ` Tang Chen
2012-12-26 3:02 ` Kamezawa Hiroyuki
2012-12-30 5:49 ` Wen Congyang
2012-12-24 12:09 ` [PATCH v5 02/14] memory-hotplug: check whether all memory blocks are offlined or not when removing memory Tang Chen
2012-12-26 3:10 ` Kamezawa Hiroyuki
2012-12-27 3:10 ` Tang Chen
2012-12-24 12:09 ` [PATCH v5 03/14] memory-hotplug: remove redundant codes Tang Chen
2012-12-26 3:20 ` Kamezawa Hiroyuki
2012-12-27 3:09 ` Tang Chen
2012-12-24 12:09 ` [PATCH v5 04/14] memory-hotplug: remove /sys/firmware/memmap/X sysfs Tang Chen
2012-12-26 3:30 ` Kamezawa Hiroyuki
2012-12-27 3:09 ` Tang Chen
2013-01-02 14:24 ` Christoph Lameter
2012-12-24 12:09 ` [PATCH v5 05/14] memory-hotplug: introduce new function arch_remove_memory() for removing page table depends on architecture Tang Chen
2012-12-26 3:37 ` Kamezawa Hiroyuki
2012-12-24 12:09 ` [PATCH v5 06/14] memory-hotplug: implement register_page_bootmem_info_section of sparse-vmemmap Tang Chen
2012-12-25 8:09 ` Jianguo Wu
2012-12-26 3:21 ` Tang Chen
2012-12-24 12:09 ` [PATCH v5 07/14] memory-hotplug: move pgdat_resize_lock into sparse_remove_one_section() Tang Chen
2012-12-26 3:47 ` Kamezawa Hiroyuki
2012-12-26 6:20 ` Tang Chen
2012-12-24 12:09 ` [PATCH v5 08/14] memory-hotplug: Common APIs to support page tables hot-remove Tang Chen
2012-12-25 8:17 ` Jianguo Wu
2012-12-26 2:49 ` Tang Chen
2012-12-26 3:11 ` Tang Chen
2012-12-26 3:19 ` Tang Chen
2012-12-24 12:09 ` [PATCH v5 09/14] memory-hotplug: remove page table of x86_64 architecture Tang Chen
2012-12-24 12:09 ` [PATCH v5 10/14] memory-hotplug: remove memmap of sparse-vmemmap Tang Chen
2012-12-24 12:09 ` [PATCH v5 11/14] memory-hotplug: Integrated __remove_section() of CONFIG_SPARSEMEM_VMEMMAP Tang Chen
2012-12-24 12:09 ` Tang Chen [this message]
2012-12-24 12:09 ` [PATCH v5 13/14] memory-hotplug: remove sysfs file of node Tang Chen
2012-12-24 12:09 ` [PATCH v5 14/14] memory-hotplug: free node_data when a node is offlined Tang Chen
2012-12-26 3:55 ` Kamezawa Hiroyuki
2012-12-27 12:16 ` Wen Congyang
2012-12-28 0:28 ` Kamezawa Hiroyuki
2012-12-30 6:02 ` Wen Congyang
2013-01-07 5:30 ` Kamezawa Hiroyuki
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=1356350964-13437-13-git-send-email-tangchen@cn.fujitsu.com \
--to=tangchen@cn.fujitsu.com \
--cc=akpm@linux-foundation.org \
--cc=benh@kernel.crashing.org \
--cc=cl@linux.com \
--cc=cmetcalf@tilera.com \
--cc=hpa@zytor.com \
--cc=isimatu.yasuaki@jp.fujitsu.com \
--cc=kosaki.motohiro@jp.fujitsu.com \
--cc=laijs@cn.fujitsu.com \
--cc=len.brown@intel.com \
--cc=linfeng@cn.fujitsu.com \
--cc=linux-acpi@vger.kernel.org \
--cc=linux-ia64@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-s390@vger.kernel.org \
--cc=linux-sh@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=liuj97@gmail.com \
--cc=mgorman@suse.de \
--cc=minchan.kim@gmail.com \
--cc=paulus@samba.org \
--cc=rientjes@google.com \
--cc=sparclinux@vger.kernel.org \
--cc=wency@cn.fujitsu.com \
--cc=wujianguo@huawei.com \
--cc=x86@kernel.org \
--cc=yinghai@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
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;
as well as URLs for NNTP newsgroup(s).