Prev: [PATCH 1/3] mem-hotplug: separate setup_per_cpu_pageset() into separate functions
Next: btrfs failed to delete reference
From: Haicheng Li on 17 May 2010 04:30
Make "zone->present_pages gets increased" and "building zonelist" an
atomic operation to prevent possible race.

It is merely a theoretical race: after new zone gets populated,
its pages might be allocated by others before itself building zonelist.

Besides, atomic operation ensures alloc_percpu() will never fail since
there is a new fresh memory block added.

Signed-off-by: Haicheng Li <haicheng.li(a)linux.intel.com>
Signed-off-by: Wu Fengguang <fengguang.wu(a)intel.com>
Reviewed-by: Andi Kleen <andi.kleen(a)intel.com>
---
include/linux/memory_hotplug.h | 8 ++++++++
mm/memory_hotplug.c | 15 +++++++++------
mm/page_alloc.c | 20 ++++++++++++++++----
3 files changed, 33 insertions(+), 10 deletions(-)

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 35b07b7..42b1416 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -157,6 +157,14 @@ extern void register_page_bootmem_info_node(struct pglist_data *pgdat);
extern void put_page_bootmem(struct page *page);
#endif

+/* online_pages() will pass such zone info to build_all_zonelists()
+ * when it needs to initialize a new zone.
+ */
+struct zone_online_info {
+ struct zone *zone;
+ unsigned long onlined_pages;
+};
+
#else /* ! CONFIG_MEMORY_HOTPLUG */
/*
* Stub functions for when hotplug is off
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b564b6a..06738b2 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -389,6 +389,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
int nid;
int ret;
struct memory_notify arg;
+ struct zone_online_info zone_online_info;
/*
* mutex to protect zone->pageset when it's still shared
* in onlined_pages()
@@ -434,13 +435,15 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
return ret;
}

- zone->present_pages += onlined_pages;
- zone->zone_pgdat->node_present_pages += onlined_pages;
- if (need_zonelists_rebuild)
- build_all_zonelists(zone);
- else
+ if (need_zonelists_rebuild) {
+ zone_online_info.zone = zone;
+ zone_online_info.onlined_pages = onlined_pages;
+ build_all_zonelists(&zone_online_info);
+ } else {
+ zone->present_pages += onlined_pages;
+ zone->zone_pgdat->node_present_pages += onlined_pages;
zone_pcp_update(zone);
-
+ }
mutex_unlock(&zone_pageset_mutex);
setup_per_zone_wmarks();
calculate_zone_inactive_ratio(zone);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 72c1211..0729a82 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2783,6 +2783,20 @@ static __init_refok int __build_all_zonelists(void *data)
{
int nid;
int cpu;
+#ifdef CONFIG_MEMORY_HOTPLUG
+ struct zone_online_info *new = (struct zone_online_info *)data;
+
+ /*
+ * Populate the new zone before build zonelists, which could
+ * happen only when onlining a new node after system is booted.
+ */
+ if (new) {
+ /* We are expecting a new memory block here. */
+ WARN_ON(!new->onlined_pages);
+ new->zone->present_pages += new->onlined_pages;
+ new->zone->zone_pgdat->node_present_pages += new->onlined_pages;
+ }
+#endif

#ifdef CONFIG_NUMA
memset(node_load, 0, sizeof(node_load));
@@ -2796,10 +2810,8 @@ static __init_refok int __build_all_zonelists(void *data)

#ifdef CONFIG_MEMORY_HOTPLUG
/* Setup real pagesets for the new zone */
- if (data) {
- struct zone *zone = data;
- setup_zone_pageset(zone);
- }
+ if (new)
+ setup_zone_pageset(new->zone);
#endif

/*
--
1.6.0.rc1


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
 | 
Pages: 1
Prev: [PATCH 1/3] mem-hotplug: separate setup_per_cpu_pageset() into separate functions
Next: btrfs failed to delete reference