cpu-hotplug,memory-hotplug: clear cpu_to_node() when offlining the node

When the node is offlined, there is no memory/cpu on the node.  If a
sleep task runs on a cpu of this node, it will be migrated to the cpu on
the other node.  So we can clear cpu-to-node mapping.

[akpm@linux-foundation.org: numa_clear_node() and numa_set_node() can no longer be __cpuinit]
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jiang Liu <liuj97@gmail.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 33 insertions, 5 deletions

diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index 52560a2038e1..1b99ee5c9f00 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -57,8 +57,8 @@ static inline int numa_cpu_node(int cpu)
 #endif
 
 #ifdef CONFIG_NUMA
-extern void __cpuinit numa_set_node(int cpu, int node);
-extern void __cpuinit numa_clear_node(int cpu);
+extern void numa_set_node(int cpu, int node);
+extern void numa_clear_node(int cpu);
 extern void __init init_cpu_to_node(void);
 extern void __cpuinit numa_add_cpu(int cpu);
 extern void __cpuinit numa_remove_cpu(int cpu);
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index f22680bf69ec..a713d081b59c 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -78,7 +78,7 @@ EXPORT_SYMBOL(node_to_cpumask_map);
 DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE);
 EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map);
 
-void __cpuinit numa_set_node(int cpu, int node)
+void numa_set_node(int cpu, int node)
 {
         int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);
 
@@ -101,7 +101,7 @@ void __cpuinit numa_set_node(int cpu, int node)
                 set_cpu_numa_node(cpu, node);
 }
 
-void __cpuinit numa_clear_node(int cpu)
+void numa_clear_node(int cpu)
 {
         numa_set_node(cpu, NUMA_NO_NODE);
 }
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 17e1447077ab..a9072a16a160 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1705,6 +1705,34 @@ static int check_cpu_on_node(void *data)
         return 0;
 }
 
+static void unmap_cpu_on_node(void *data)
+{
+#ifdef CONFIG_ACPI_NUMA
+        struct pglist_data *pgdat = data;
+        int cpu;
+
+        for_each_possible_cpu(cpu)
+                if (cpu_to_node(cpu) == pgdat->node_id)
+                        numa_clear_node(cpu);
+#endif
+}
+
+static int check_and_unmap_cpu_on_node(void *data)
+{
+        int ret = check_cpu_on_node(data);
+
+        if (ret)
+                return ret;
+
+        /*
+         * the node will be offlined when we come here, so we can clear
+         * the cpu_to_node() now.
+         */
+
+        unmap_cpu_on_node(data);
+        return 0;
+}
+
 /* offline the node if all memory sections of this node are removed */
 void try_offline_node(int nid)
 {
@@ -1731,7 +1759,7 @@ void try_offline_node(int nid)
                 return;
         }
 
-        if (stop_machine(check_cpu_on_node, pgdat, NULL))
+        if (stop_machine(check_and_unmap_cpu_on_node, pgdat, NULL))
                 return;
 
         /*