cpu: Fix node state for whether it contains CPU

In current kernel code, we only call node_set_state(cpu_to_node(cpu), N_CPU) when a cpu is hot plugged. But we do not set the node state for N_CPU when the cpus are brought online during boot.

So this could lead to failure when we check to see if a node contains cpu with node_state(node_id, N_CPU).

One use case is in the node_reclaime function:

/*
* Only run node reclaim on the local node or on nodes that do
* not
* have associated processors. This will favor the local
* processor
* over remote processors and spread off node memory allocations
* as wide as possible.
*/
if (node_state(pgdat->node_id, N_CPU) && pgdat->node_id !=
numa_node_id())
return NODE_RECLAIM_NOSCAN;

I instrumented the kernel to call this function after boot and it always returns 0 on a x86 desktop machine until I apply the attached patch.

int num_cpu_node(void)

{
       int i, nr_cpu_nodes = 0;

       for_each_node(i) {
               if (node_state(i, N_CPU))
                       ++ nr_cpu_nodes;
       }

       return nr_cpu_nodes;
}

Fix this by checking each node for online CPU when we initialize vmstat that's responsible for maintaining node state.

v2:
1. Fix the problem for all architectures in the generic path inside vmstat, not just for x86.

---
 mm/vmstat.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

index 89cec42..d83f953 100644
@@ -1794,6 +1794,16 @@ static void __init start_shepherd_timer(void)
 		round_jiffies_relative(sysctl_stat_interval));
 }
 
+static void __init init_cpu_node_state(void)
+{
+	int cpu;
+
+	get_online_cpus();
+	for_each_online_cpu(cpu)
+		node_set_state(cpu_to_node(cpu), N_CPU);
+	put_online_cpus();
+}
+
 static void vmstat_cpu_dead(int node)
 {
 	int cpu;

@@ -1851,6 +1861,7 @@ static int __init setup_vmstat(void)
 #ifdef CONFIG_SMP
 	cpu_notifier_register_begin();
 	__register_cpu_notifier(&vmstat_notifier);
+	init_cpu_node_state();
 
 	start_shepherd_timer();
 	cpu_notifier_register_done();

2.5.5

That would mean that when node_reclaim_mode is enabled that we weren't properly returning NODE_RECLAIM_NOSCAN if a remote node had its own cpus and PGDAT_RECLAIM_LOCKED wasn't already set, so this seems like it could result in a performance improvement.