mm/hotplug: correctly setup fallback zonelists when creating new pgdat

When hotadd_new_pgdat() is called to create new pgdat for a new node, a
fallback zonelist should be created for the new node.  There's code to try
to achieve that in hotadd_new_pgdat() as below:

	/*
	 * The node we allocated has no zone fallback lists. For avoiding
	 * to access not-initialized zonelist, build here.
	 */
	mutex_lock(&zonelists_mutex);
	build_all_zonelists(pgdat, NULL);
	mutex_unlock(&zonelists_mutex);

But it doesn't work as expected.  When hotadd_new_pgdat() is called, the
new node is still in offline state because node_set_online(nid) hasn't
been called yet.  And build_all_zonelists() only builds zonelists for
online nodes as:

        for_each_online_node(nid) {
                pg_data_t *pgdat = NODE_DATA(nid);

                build_zonelists(pgdat);
                build_zonelist_cache(pgdat);
        }

Though we hope to create zonelist for the new pgdat, but it doesn't.  So
add a new parameter "pgdat" the build_all_zonelists() to build pgdat for
the new pgdat too.

Signed-off-by: Jiang Liu <liuj97@gmail.com>
Signed-off-by: Xishi Qiu <qiuxishi@huawei.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Tony Luck <tony.luck@intel.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Keping Chen <chenkeping@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 14 insertions, 7 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 427bb291dd0f..b8731040b9f9 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -513,7 +513,7 @@ int __ref 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);
+                build_all_zonelists(NULL, zone);
         else
                 zone_pcp_update(zone);
 
@@ -562,7 +562,7 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
          * to access not-initialized zonelist, build here.
          */
         mutex_lock(&zonelists_mutex);
-        build_all_zonelists(NULL);
+        build_all_zonelists(pgdat, NULL);
         mutex_unlock(&zonelists_mutex);
 
         return pgdat;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6c7e3bd93a85..9ad6866ac49c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3032,7 +3032,7 @@ int numa_zonelist_order_handler(ctl_table *table, int write,
                         user_zonelist_order = oldval;
                 } else if (oldval != user_zonelist_order) {
                         mutex_lock(&zonelists_mutex);
-                        build_all_zonelists(NULL);
+                        build_all_zonelists(NULL, NULL);
                         mutex_unlock(&zonelists_mutex);
                 }
         }
@@ -3415,10 +3415,17 @@ static __init_refok int __build_all_zonelists(void *data)
 {
         int nid;
         int cpu;
+        pg_data_t *self = data;
 
 #ifdef CONFIG_NUMA
         memset(node_load, 0, sizeof(node_load));
 #endif
+
+        if (self && !node_online(self->node_id)) {
+                build_zonelists(self);
+                build_zonelist_cache(self);
+        }
+
         for_each_online_node(nid) {
                 pg_data_t *pgdat = NODE_DATA(nid);
 
@@ -3463,7 +3470,7 @@ static __init_refok int __build_all_zonelists(void *data)
  * Called with zonelists_mutex held always
  * unless system_state == SYSTEM_BOOTING.
  */
-void __ref build_all_zonelists(void *data)
+void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone)
 {
         set_zonelist_order();
 
@@ -3475,10 +3482,10 @@ void __ref build_all_zonelists(void *data)
                 /* we have to stop all cpus to guarantee there is no user
                    of zonelist */
 #ifdef CONFIG_MEMORY_HOTPLUG
-                if (data)
-                        setup_zone_pageset((struct zone *)data);
+                if (zone)
+                        setup_zone_pageset(zone);
 #endif
-                stop_machine(__build_all_zonelists, NULL, NULL);
+                stop_machine(__build_all_zonelists, pgdat, NULL);
                 /* cpuset refresh routine should be here */
         }
         vm_total_pages = nr_free_pagecache_pages();