cpuset: update top cpuset's mems after adding a node

After adding a node into the machine, top cpuset's mems isn't updated.

By reviewing the code, we found that the update function

  cpuset_track_online_nodes()

was invoked after node_states[N_ONLINE] changes.  It is wrong because
N_ONLINE just means node has pgdat, and if node has/added memory, we use
N_HIGH_MEMORY.  So, We should invoke the update function after
node_states[N_HIGH_MEMORY] changes, just like its commit says.

This patch fixes it.  And we use notifier of memory hotplug instead of
direct calling of cpuset_track_online_nodes().

Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Acked-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Paul Menage <menage@google.com
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 16 insertions, 10 deletions

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 2691926fb506..8e540d32c9fe 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -74,8 +74,6 @@ static inline int cpuset_do_slab_mem_spread(void)
         return current->flags & PF_SPREAD_SLAB;
 }
 
-extern void cpuset_track_online_nodes(void);
-
 extern int current_cpuset_is_being_rebound(void);
 
 extern void rebuild_sched_domains(void);
@@ -151,8 +149,6 @@ static inline int cpuset_do_slab_mem_spread(void)
         return 0;
 }
 
-static inline void cpuset_track_online_nodes(void) {}
-
 static inline int current_cpuset_is_being_rebound(void)
 {
         return 0;
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 81fc6791a296..da7ff6137f37 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -36,6 +36,7 @@
 #include <linux/list.h>
 #include <linux/mempolicy.h>
 #include <linux/mm.h>
+#include <linux/memory.h>
 #include <linux/module.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
@@ -2015,12 +2016,23 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
  * Call this routine anytime after node_states[N_HIGH_MEMORY] changes.
  * See also the previous routine cpuset_track_online_cpus().
  */
-void cpuset_track_online_nodes(void)
+static int cpuset_track_online_nodes(struct notifier_block *self,
+                                unsigned long action, void *arg)
 {
         cgroup_lock();
-        top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
-        scan_for_empty_cpusets(&top_cpuset);
+        switch (action) {
+        case MEM_ONLINE:
+                top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
+                break;
+        case MEM_OFFLINE:
+                top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
+                scan_for_empty_cpusets(&top_cpuset);
+                break;
+        default:
+                break;
+        }
         cgroup_unlock();
+        return NOTIFY_OK;
 }
 #endif
 
@@ -2036,6 +2048,7 @@ void __init cpuset_init_smp(void)
         top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
 
         hotcpu_notifier(cpuset_track_online_cpus, 0);
+        hotplug_memory_notifier(cpuset_track_online_nodes, 10);
 }
 
 /**
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 6837a1014372..b5b2b15085a8 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -22,7 +22,6 @@
 #include <linux/highmem.h>
 #include <linux/vmalloc.h>
 #include <linux/ioport.h>
-#include <linux/cpuset.h>
 #include <linux/delay.h>
 #include <linux/migrate.h>
 #include <linux/page-isolation.h>
@@ -498,8 +497,6 @@ int add_memory(int nid, u64 start, u64 size)
         /* we online node here. we can't roll back from here. */
         node_set_online(nid);
 
-        cpuset_track_online_nodes();
-
         if (new_pgdat) {
                 ret = register_one_node(nid);
                 /*