x86, numa: Use near(er) online node instead of roundrobin for NUMA

CPU to node mapping is set via the following sequence:

 1. numa_init_array(): Set up roundrobin from cpu to online node

 2. init_cpu_to_node(): Set that according to apicid_to_node[]
			according to srat only handle the node that
			is online, and leave other cpu on node
			without ram (aka not online) to still
			roundrobin.

3. later call srat_detect_node for Intel/AMD, will use first_online
   node or nearby node.

Problem is that setup_per_cpu_areas() is not called between 2 and 3,
the per_cpu for cpu on node with ram is on different node, and could
put that on node with two hops away.

So try to optimize this and add find_near_online_node() and call
init_cpu_to_node().

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: David Rientjes <rientjes@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
LKML-Reference: <4B07A739.3030104@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/kernel/cpu/intel.c

@@ -263,8 +263,12 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
 	/* Don't do the funky fallback heuristics the AMD version employs
 	   for now. */
 	node = apicid_to_node[apicid];
-	if (node == NUMA_NO_NODE || !node_online(node))
+	if (node == NUMA_NO_NODE)
 		node = first_node(node_online_map);
+	else if (!node_online(node)) {
+		/* reuse the value from init_cpu_to_node() */
+		node = cpu_to_node(cpu);
+	}
 	numa_set_node(cpu, node);
 
 	printk(KERN_INFO "CPU %d/0x%x -> Node %d\n", cpu, apicid, node);

arch/x86/mm/numa_64.c

@@ -764,6 +764,25 @@ static __init int numa_setup(char *opt)
 early_param("numa", numa_setup);
 
 #ifdef CONFIG_NUMA
+
+static __init int find_near_online_node(int node)
+{
+	int n, val;
+	int min_val = INT_MAX;
+	int best_node = -1;
+
+	for_each_online_node(n) {
+		val = node_distance(node, n);
+
+		if (val < min_val) {
+			min_val = val;
+			best_node = n;
+		}
+	}
+
+	return best_node;
+}
+
 /*
  * Setup early cpu_to_node.
  *
@@ -795,7 +814,7 @@ void __init init_cpu_to_node(void)
 		if (node == NUMA_NO_NODE)
 			continue;
 		if (!node_online(node))
-			continue;
+			node = find_near_online_node(node);
 		numa_set_node(cpu, node);
 	}
 }