[PATCH] x86_64: Speed up numa_node_id by putting it directly into the PDA

Not go from the CPU number to an mapping array.
Mode number is often used now in fast paths.

This also adds a generic numa_node_id to all the topology includes

Suggested by Eric Dumazet

Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c
index 18e86e2..4bf6458 100644
--- a/arch/x86_64/mm/numa.c
+++ b/arch/x86_64/mm/numa.c
@@ -156,7 +156,7 @@
 	for (i = 0; i < NR_CPUS; i++) {
 		if (cpu_to_node[i] != NUMA_NO_NODE)
 			continue;
-		cpu_to_node[i] = rr;
+ 		numa_set_node(i, rr);
 		rr = next_node(rr, node_online_map);
 		if (rr == MAX_NUMNODES)
 			rr = first_node(node_online_map);
@@ -242,7 +242,7 @@
 	nodes_clear(node_online_map);
 	node_set_online(0);
 	for (i = 0; i < NR_CPUS; i++)
-		cpu_to_node[i] = 0;
+		numa_set_node(i, 0);
 	node_to_cpumask[0] = cpumask_of_cpu(0);
 	setup_node_bootmem(0, start_pfn << PAGE_SHIFT, end_pfn << PAGE_SHIFT);
 }
@@ -252,6 +252,12 @@
 	set_bit(cpu, &node_to_cpumask[cpu_to_node(cpu)]);
 } 
 
+void __cpuinit numa_set_node(int cpu, int node)
+{
+	cpu_pda[cpu].nodenumber = node;
+	cpu_to_node[cpu] = node;
+}
+
 unsigned long __init numa_free_all_bootmem(void) 
 { 
 	int i;