4 files changed, 37 insertions, 8 deletions

diff --git a/Documentation/cpusets.txt b/Documentation/cpusets.txt
index 76b44290c154..842f0d1ab216 100644
--- a/Documentation/cpusets.txt
+++ b/Documentation/cpusets.txt
@@ -217,11 +217,11 @@ exclusive cpuset.  Also, the use of a Linux virtual file system (vfs)
 to represent the cpuset hierarchy provides for a familiar permission
 and name space for cpusets, with a minimum of additional kernel code.
 
-The cpus file in the root (top_cpuset) cpuset is read-only.
-It automatically tracks the value of cpu_online_map, using a CPU
-hotplug notifier.  If and when memory nodes can be hotplugged,
-we expect to make the mems file in the root cpuset read-only
-as well, and have it track the value of node_online_map.
+The cpus and mems files in the root (top_cpuset) cpuset are
+read-only.  The cpus file automatically tracks the value of
+cpu_online_map using a CPU hotplug notifier, and the mems file
+automatically tracks the value of node_online_map using the
+cpuset_track_online_nodes() hook.
 
 
 1.4 What are exclusive cpusets ?
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 9354722a9217..4d8adf663681 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -63,6 +63,8 @@ static inline int cpuset_do_slab_mem_spread(void)
         return current->flags & PF_SPREAD_SLAB;
 }
 
+extern void cpuset_track_online_nodes(void);
+
 #else /* !CONFIG_CPUSETS */
 
 static inline int cpuset_init_early(void) { return 0; }
@@ -126,6 +128,8 @@ static inline int cpuset_do_slab_mem_spread(void)
         return 0;
 }
 
+static inline void cpuset_track_online_nodes(void) {}
+
 #endif /* !CONFIG_CPUSETS */
 
 #endif /* _LINUX_CPUSET_H */
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 584bb4e6c042..794af5024c2f 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -912,6 +912,10 @@ static int update_nodemask(struct cpuset *cs, char *buf)
         int fudge;
         int retval;
 
+        /* top_cpuset.mems_allowed tracks node_online_map; it's read-only */
+        if (cs == &top_cpuset)
+                return -EACCES;
+
         trialcs = *cs;
         retval = nodelist_parse(buf, trialcs.mems_allowed);
         if (retval < 0)
@@ -2042,9 +2046,8 @@ out:
  * (of no affect) on systems that are actively using CPU hotplug
  * but making no active use of cpusets.
  *
- * This handles CPU hotplug (cpuhp) events.  If someday Memory
- * Nodes can be hotplugged (dynamically changing node_online_map)
- * then we should handle that too, perhaps in a similar way.
+ * This routine ensures that top_cpuset.cpus_allowed tracks
+ * cpu_online_map on each CPU hotplug (cpuhp) event.
  */
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -2063,6 +2066,25 @@ static int cpuset_handle_cpuhp(struct notifier_block *nb,
 }
 #endif
 
+/*
+ * Keep top_cpuset.mems_allowed tracking node_online_map.
+ * Call this routine anytime after you change node_online_map.
+ * See also the previous routine cpuset_handle_cpuhp().
+ */
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+void cpuset_track_online_nodes()
+{
+        mutex_lock(&manage_mutex);
+        mutex_lock(&callback_mutex);
+
+        top_cpuset.mems_allowed = node_online_map;
+
+        mutex_unlock(&callback_mutex);
+        mutex_unlock(&manage_mutex);
+}
+#endif
+
 /**
  * cpuset_init_smp - initialize cpus_allowed
  *
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c37319542b70..9576ed920c0a 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -21,6 +21,7 @@
 #include <linux/highmem.h>
 #include <linux/vmalloc.h>
 #include <linux/ioport.h>
+#include <linux/cpuset.h>
 
 #include <asm/tlbflush.h>
 
@@ -283,6 +284,8 @@ 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);
                 /*