2 files changed, 17 insertions, 9 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 089cc97aed3c..a4cfcdc00455 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -389,11 +389,6 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
         int nid;
         int ret;
         struct memory_notify arg;
-        /*
-         * mutex to protect zone->pageset when it's still shared
-         * in onlined_pages()
-         */
-        static DEFINE_MUTEX(zone_pageset_mutex);
 
         arg.start_pfn = pfn;
         arg.nr_pages = nr_pages;
@@ -420,14 +415,14 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
          * This means the page allocator ignores this zone.
          * So, zonelist must be updated after online.
          */
-        mutex_lock(&zone_pageset_mutex);
+        mutex_lock(&zonelists_mutex);
         if (!populated_zone(zone))
                 need_zonelists_rebuild = 1;
 
         ret = walk_system_ram_range(pfn, nr_pages, &onlined_pages,
                 online_pages_range);
         if (ret) {
-                mutex_unlock(&zone_pageset_mutex);
+                mutex_unlock(&zonelists_mutex);
                 printk(KERN_DEBUG "online_pages %lx at %lx failed\n",
                         nr_pages, pfn);
                 memory_notify(MEM_CANCEL_ONLINE, &arg);
@@ -441,7 +436,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
         else
                 zone_pcp_update(zone);
 
-        mutex_unlock(&zone_pageset_mutex);
+        mutex_unlock(&zonelists_mutex);
         setup_per_zone_wmarks();
         calculate_zone_inactive_ratio(zone);
         if (onlined_pages) {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 21c52d2d8624..08b349931ebc 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2571,8 +2571,11 @@ int numa_zonelist_order_handler(ctl_table *table, int write,
                         strncpy((char*)table->data, saved_string,
                                 NUMA_ZONELIST_ORDER_LEN);
                         user_zonelist_order = oldval;
-                } else if (oldval != user_zonelist_order)
+                } else if (oldval != user_zonelist_order) {
+                        mutex_lock(&zonelists_mutex);
                         build_all_zonelists(NULL);
+                        mutex_unlock(&zonelists_mutex);
+                }
         }
 out:
         mutex_unlock(&zl_order_mutex);
@@ -2924,6 +2927,12 @@ static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch);
 static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset);
 static void setup_zone_pageset(struct zone *zone);
 
+/*
+ * Global mutex to protect against size modification of zonelists
+ * as well as to serialize pageset setup for the new populated zone.
+ */
+DEFINE_MUTEX(zonelists_mutex);
+
 /* return values int ....just for stop_machine() */
 static __init_refok int __build_all_zonelists(void *data)
 {
@@ -2967,6 +2976,10 @@ static __init_refok int __build_all_zonelists(void *data)
         return 0;
 }
 
+/*
+ * Called with zonelists_mutex held always
+ * unless system_state == SYSTEM_BOOTING.
+ */
 void build_all_zonelists(void *data)
 {
         set_zonelist_order();