x86: change NR_CPUS arrays in numa_64 fixup

Change the following static arrays sized by NR_CPUS to
per_cpu data variables:

	char cpu_to_node_map[NR_CPUS];

fixup:

  - Split cpu_to_node function into "early" and "late" versions
    so that x86_cpu_to_node_map_early_ptr is not EXPORT'ed and
    the cpu_to_node inline function is more streamlined.

  - This also involves setting up the percpu maps as early as possible.

  - Fix X86_32 NUMA build errors that previous version of this
    patch caused.

V2->V3:
    - add early_cpu_to_node function to keep cpu_to_node efficient
    - move and rename smp_set_apicids() to setup_percpu_maps()
    - call setup_percpu_maps() as early as possible

V1->V2:
    - Removed extraneous casts
    - Fix !NUMA builds with '#ifdef CONFIG_NUMA"

Signed-off-by: Mike Travis <travis@sgi.com>
Reviewed-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

1 files changed, 39 insertions, 2 deletions

diff --git a/arch/x86/kernel/setup64.c b/arch/x86/kernel/setup64.c
index 8fa0de810d0..855ec82e4f7 100644
--- a/arch/x86/kernel/setup64.c
+++ b/arch/x86/kernel/setup64.c
@@ -84,6 +84,40 @@ static int __init nonx32_setup(char *str)
 __setup("noexec32=", nonx32_setup);
 
 /*
+ * Copy data used in early init routines from the initial arrays to the
+ * per cpu data areas.  These arrays then become expendable and the *_ptrs
+ * are zeroed indicating that the static arrays are gone.
+ */
+void __init setup_percpu_maps(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+#ifdef CONFIG_SMP
+		if (per_cpu_offset(cpu)) {
+#endif
+			per_cpu(x86_cpu_to_apicid, cpu) =
+						x86_cpu_to_apicid_init[cpu];
+#ifdef CONFIG_NUMA
+			per_cpu(x86_cpu_to_node_map, cpu) =
+						x86_cpu_to_node_map_init[cpu];
+#endif
+#ifdef CONFIG_SMP
+		}
+		else
+			printk(KERN_NOTICE "per_cpu_offset zero for cpu %d\n",
+									cpu);
+#endif
+	}
+
+	/* indicate the early static arrays are gone */
+	x86_cpu_to_apicid_early_ptr = NULL;
+#ifdef CONFIG_NUMA
+	x86_cpu_to_node_map_early_ptr = NULL;
+#endif
+}
+
+/*
  * Great future plan:
  * Declare PDA itself and support (irqstack,tss,pgd) as per cpu data.
  * Always point %gs to its beginning
@@ -104,18 +138,21 @@ void __init setup_per_cpu_areas(void)
 	for_each_cpu_mask (i, cpu_possible_map) {
 		char *ptr;
 
-		if (!NODE_DATA(cpu_to_node(i))) {
+		if (!NODE_DATA(early_cpu_to_node(i))) {
 			printk("cpu with no node %d, num_online_nodes %d\n",
 			       i, num_online_nodes());
 			ptr = alloc_bootmem_pages(size);
 		} else { 
-			ptr = alloc_bootmem_pages_node(NODE_DATA(cpu_to_node(i)), size);
+			ptr = alloc_bootmem_pages_node(NODE_DATA(early_cpu_to_node(i)), size);
 		}
 		if (!ptr)
 			panic("Cannot allocate cpu data for CPU %d\n", i);
 		cpu_pda(i)->data_offset = ptr - __per_cpu_start;
 		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
 	}
+
+	/* setup percpu data maps early */
+	setup_percpu_maps();
 } 
 
 void pda_init(int cpu)