x86: fix cpu_to_node references

In x86_64 and i386 architectures most arrays that are sized using
NR_CPUS lay in local memory on node 0.  Not only will most (99%?) of the
systems not use all the slots in these arrays, particularly when NR_CPUS
is increased to accommodate future very high cpu count systems, but a
number of cache lines are passed unnecessarily on the system bus when
these arrays are referenced by cpus on other nodes.

Typically, the values in these arrays are referenced by the cpu
accessing it's own values, though when passing IPI interrupts, the cpu
does access the data relevant to the targeted cpu/node.  Of course, if
the referencing cpu is not on node 0, then the reference will still
require cross node exchanges of cache lines.  A common use of this is
for an interrupt service routine to pass the interrupt to other cpus
local to that node.

Ideally, all the elements in these arrays should be moved to the per_cpu
data area.  In some cases (such as x86_cpu_to_apicid) the array is
referenced before the per_cpu data areas are setup.  In this case, a
static array is declared in the __initdata area and initialized by the
booting cpu (BSP).  The values are then moved to the per_cpu area after
it is initialized and the original static array is freed with the rest
of the __initdata.

This patch:

Fix four instances where cpu_to_node is referenced by array instead of
via the cpu_to_node macro.  This is preparation to moving it to the
per_cpu data area.
Signed-off-by: Mike Travis <travis@sgi.com>
Cc: Andi Kleen <ak@suse.de>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: "Siddha, Suresh B" <suresh.b.siddha@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

arch/x86/kernel/vsyscall_64.c

@@ -289,7 +289,7 @@ static void __cpuinit vsyscall_set_cpu(int cpu)
 	unsigned long *d;
 	unsigned long node = 0;
 #ifdef CONFIG_NUMA
-	node = cpu_to_node[cpu];
+	node = cpu_to_node(cpu);
 #endif
 	if (cpu_has(&cpu_data[cpu], X86_FEATURE_RDTSCP))
 		write_rdtscp_aux((node << 12) | cpu);

arch/x86/mm/numa_64.c

@@ -261,7 +261,7 @@ void __init numa_init_array(void)
 	   We round robin the existing nodes. */
 	rr = first_node(node_online_map);
 	for (i = 0; i < NR_CPUS; i++) {
-		if (cpu_to_node[i] != NUMA_NO_NODE)
+		if (cpu_to_node(i) != NUMA_NO_NODE)
 			continue;
  		numa_set_node(i, rr);
 		rr = next_node(rr, node_online_map);
@@ -543,7 +543,7 @@ __cpuinit void numa_add_cpu(int cpu)
 void __cpuinit numa_set_node(int cpu, int node)
 {
 	cpu_pda(cpu)->nodenumber = node;
-	cpu_to_node[cpu] = node;
+	cpu_to_node(cpu) = node;
 }
 
 unsigned long __init numa_free_all_bootmem(void) 

arch/x86/mm/srat_64.c

@@ -431,9 +431,9 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
 			setup_node_bootmem(i, nodes[i].start, nodes[i].end);
 
 	for (i = 0; i < NR_CPUS; i++) {
-		if (cpu_to_node[i] == NUMA_NO_NODE)
+		if (cpu_to_node(i) == NUMA_NO_NODE)
 			continue;
-		if (!node_isset(cpu_to_node[i], node_possible_map))
+		if (!node_isset(cpu_to_node(i), node_possible_map))
 			numa_set_node(i, NUMA_NO_NODE);
 	}
 	numa_init_array();