2 files changed, 26 insertions, 9 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 85eb4d342ac5..089cc97aed3c 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -389,6 +389,11 @@ 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;
@@ -415,12 +420,14 @@ 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);
         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);
                 printk(KERN_DEBUG "online_pages %lx at %lx failed\n",
                         nr_pages, pfn);
                 memory_notify(MEM_CANCEL_ONLINE, &arg);
@@ -429,8 +436,12 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
 
         zone->present_pages += onlined_pages;
         zone->zone_pgdat->node_present_pages += onlined_pages;
+        if (need_zonelists_rebuild)
+                build_all_zonelists(zone);
+        else
+                zone_pcp_update(zone);
 
-        zone_pcp_update(zone);
+        mutex_unlock(&zone_pageset_mutex);
         setup_per_zone_wmarks();
         calculate_zone_inactive_ratio(zone);
         if (onlined_pages) {
@@ -438,10 +449,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
                 node_set_state(zone_to_nid(zone), N_HIGH_MEMORY);
         }
 
-        if (need_zonelists_rebuild)
-                build_all_zonelists();
-        else
-                vm_total_pages = nr_free_pagecache_pages();
+        vm_total_pages = nr_free_pagecache_pages();
 
         writeback_set_ratelimit();
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 595d0ac211e2..21c52d2d8624 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2572,7 +2572,7 @@ int numa_zonelist_order_handler(ctl_table *table, int write,
                                 NUMA_ZONELIST_ORDER_LEN);
                         user_zonelist_order = oldval;
                 } else if (oldval != user_zonelist_order)
-                        build_all_zonelists();
+                        build_all_zonelists(NULL);
         }
 out:
         mutex_unlock(&zl_order_mutex);
@@ -2922,9 +2922,10 @@ static void build_zonelist_cache(pg_data_t *pgdat)
  */
 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);
 
 /* return values int ....just for stop_machine() */
-static int __build_all_zonelists(void *dummy)
+static __init_refok int __build_all_zonelists(void *data)
 {
         int nid;
         int cpu;
@@ -2939,6 +2940,14 @@ static int __build_all_zonelists(void *dummy)
                 build_zonelist_cache(pgdat);
         }
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+        /* Setup real pagesets for the new zone */
+        if (data) {
+                struct zone *zone = data;
+                setup_zone_pageset(zone);
+        }
+#endif
+
         /*
          * Initialize the boot_pagesets that are going to be used
          * for bootstrapping processors. The real pagesets for
@@ -2958,7 +2967,7 @@ static int __build_all_zonelists(void *dummy)
         return 0;
 }
 
-void build_all_zonelists(void)
+void build_all_zonelists(void *data)
 {
         set_zonelist_order();
 
@@ -2969,7 +2978,7 @@ void build_all_zonelists(void)
         } else {
                 /* we have to stop all cpus to guarantee there is no user
                    of zonelist */
-                stop_machine(__build_all_zonelists, NULL, NULL);
+                stop_machine(__build_all_zonelists, data, NULL);
                 /* cpuset refresh routine should be here */
         }
         vm_total_pages = nr_free_pagecache_pages();