Merge branch 'x86/numa' into x86/mm

Merge reason: consolidate it into the more generic x86/mm tree to prevent conflicts.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

34 files changed, 504 insertions, 488 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d5ed94d30aad..95c36c474766 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1705,7 +1705,7 @@ config HAVE_ARCH_EARLY_PFN_TO_NID
 	depends on NUMA
 
 config USE_PERCPU_NUMA_NODE_ID
-	def_bool X86_64
+	def_bool y
 	depends on NUMA
 
 menu "Power management and ACPI options"
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 5e3969c36d7f..ad30ca4b6fe9 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -306,8 +306,6 @@ struct apic {
 
 	void (*setup_apic_routing)(void);
 	int (*multi_timer_check)(int apic, int irq);
-	int (*apicid_to_node)(int logical_apicid);
-	int (*cpu_to_logical_apicid)(int cpu);
 	int (*cpu_present_to_apicid)(int mps_cpu);
 	void (*apicid_to_cpu_present)(int phys_apicid, physid_mask_t *retmap);
 	void (*setup_portio_remap)(void);
@@ -355,6 +353,23 @@ struct apic {
 	void (*icr_write)(u32 low, u32 high);
 	void (*wait_icr_idle)(void);
 	u32 (*safe_wait_icr_idle)(void);
+
+#ifdef CONFIG_X86_32
+	/*
+	 * Called very early during boot from get_smp_config().  It should
+	 * return the logical apicid.  x86_[bios]_cpu_to_apicid is
+	 * initialized before this function is called.
+	 *
+	 * If logical apicid can't be determined that early, the function
+	 * may return BAD_APICID.  Logical apicid will be configured after
+	 * init_apic_ldr() while bringing up CPUs.  Note that NUMA affinity
+	 * won't be applied properly during early boot in this case.
+	 */
+	int (*x86_32_early_logical_apicid)(int cpu);
+
+	/* determine CPU -> NUMA node mapping */
+	int (*x86_32_numa_cpu_node)(int cpu);
+#endif
 };
 
 /*
@@ -502,6 +517,11 @@ extern struct apic apic_noop;
 
 extern struct apic apic_default;
 
+static inline int noop_x86_32_early_logical_apicid(int cpu)
+{
+	return BAD_APICID;
+}
+
 /*
  * Set up the logical destination ID.
  *
@@ -521,7 +541,7 @@ static inline int default_phys_pkg_id(int cpuid_apic, int index_msb)
 	return cpuid_apic >> index_msb;
 }
 
-extern int default_apicid_to_node(int logical_apicid);
+extern int default_x86_32_numa_cpu_node(int cpu);
 
 #endif
 
@@ -557,12 +577,6 @@ static inline void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_ma
 	*retmap = *phys_map;
 }
 
-/* Mapping from cpu number to logical apicid */
-static inline int default_cpu_to_logical_apicid(int cpu)
-{
-	return 1 << cpu;
-}
-
 static inline int __default_cpu_present_to_apicid(int mps_cpu)
 {
 	if (mps_cpu < nr_cpu_ids && cpu_present(mps_cpu))
@@ -595,8 +609,4 @@ extern int default_check_phys_apicid_present(int phys_apicid);
 
 #endif /* CONFIG_X86_LOCAL_APIC */
 
-#ifdef CONFIG_X86_32
-extern u8 cpu_2_logical_apicid[NR_CPUS];
-#endif
-
 #endif /* _ASM_X86_APIC_H */
diff --git a/arch/x86/include/asm/ipi.h b/arch/x86/include/asm/ipi.h
index 0b7228268a63..615fa9061b57 100644
--- a/arch/x86/include/asm/ipi.h
+++ b/arch/x86/include/asm/ipi.h
@@ -123,10 +123,6 @@ extern void default_send_IPI_mask_sequence_phys(const struct cpumask *mask,
 						 int vector);
 extern void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask,
 							 int vector);
-extern void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
-							 int vector);
-extern void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask,
-							 int vector);
 
 /* Avoid include hell */
 #define NMI_VECTOR 0x02
@@ -150,6 +146,10 @@ static inline void __default_local_send_IPI_all(int vector)
 }
 
 #ifdef CONFIG_X86_32
+extern void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
+							 int vector);
+extern void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask,
+							 int vector);
 extern void default_send_IPI_mask_logical(const struct cpumask *mask,
 						 int vector);
 extern void default_send_IPI_allbutself(int vector);
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index 0c90dd9f0505..9c7d95f6174b 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -25,7 +25,6 @@ extern int pic_mode;
 #define MAX_IRQ_SOURCES		256
 
 extern unsigned int def_to_bigsmp;
-extern u8 apicid_2_node[];
 
 #ifdef CONFIG_X86_NUMAQ
 extern int mp_bus_id_to_node[MAX_MP_BUSSES];
@@ -33,8 +32,6 @@ extern int mp_bus_id_to_local[MAX_MP_BUSSES];
 extern int quad_local_to_mp_bus_id [NR_CPUS/4][4];
 #endif
 
-#define MAX_APICID		256
-
 #else /* CONFIG_X86_64: */
 
 #define MAX_MP_BUSSES		256
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index 27da400d3138..26fc6e2dd0fb 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -1,5 +1,54 @@
+#ifndef _ASM_X86_NUMA_H
+#define _ASM_X86_NUMA_H
+
+#include <asm/topology.h>
+#include <asm/apicdef.h>
+
+#ifdef CONFIG_NUMA
+/*
+ * __apicid_to_node[] stores the raw mapping between physical apicid and
+ * node and is used to initialize cpu_to_node mapping.
+ *
+ * The mapping may be overridden by apic->numa_cpu_node() on 32bit and thus
+ * should be accessed by the accessors - set_apicid_to_node() and
+ * numa_cpu_node().
+ */
+extern s16 __apicid_to_node[MAX_LOCAL_APIC];
+
+static inline void set_apicid_to_node(int apicid, s16 node)
+{
+	__apicid_to_node[apicid] = node;
+}
+#else	/* CONFIG_NUMA */
+static inline void set_apicid_to_node(int apicid, s16 node)
+{
+}
+#endif	/* CONFIG_NUMA */
+
 #ifdef CONFIG_X86_32
 # include "numa_32.h"
 #else
 # include "numa_64.h"
 #endif
+
+#ifdef CONFIG_NUMA
+extern void __cpuinit numa_set_node(int cpu, int node);
+extern void __cpuinit numa_clear_node(int cpu);
+extern void __init numa_init_array(void);
+extern void __init init_cpu_to_node(void);
+extern void __cpuinit numa_add_cpu(int cpu);
+extern void __cpuinit numa_remove_cpu(int cpu);
+#else	/* CONFIG_NUMA */
+static inline void numa_set_node(int cpu, int node)	{ }
+static inline void numa_clear_node(int cpu)		{ }
+static inline void numa_init_array(void)		{ }
+static inline void init_cpu_to_node(void)		{ }
+static inline void numa_add_cpu(int cpu)		{ }
+static inline void numa_remove_cpu(int cpu)		{ }
+#endif	/* CONFIG_NUMA */
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+struct cpumask __cpuinit *debug_cpumask_set_cpu(int cpu, int enable);
+#endif
+
+#endif	/* _ASM_X86_NUMA_H */
diff --git a/arch/x86/include/asm/numa_32.h b/arch/x86/include/asm/numa_32.h
index b0ef2b449a9d..c6beed1ef103 100644
--- a/arch/x86/include/asm/numa_32.h
+++ b/arch/x86/include/asm/numa_32.h
@@ -4,7 +4,12 @@
 extern int numa_off;
 
 extern int pxm_to_nid(int pxm);
-extern void numa_remove_cpu(int cpu);
+
+#ifdef CONFIG_NUMA
+extern int __cpuinit numa_cpu_node(int cpu);
+#else	/* CONFIG_NUMA */
+static inline int numa_cpu_node(int cpu)		{ return NUMA_NO_NODE; }
+#endif	/* CONFIG_NUMA */
 
 #ifdef CONFIG_HIGHMEM
 extern void set_highmem_pages_init(void);
diff --git a/arch/x86/include/asm/numa_64.h b/arch/x86/include/asm/numa_64.h
index 0493be39607c..2819afa33632 100644
--- a/arch/x86/include/asm/numa_64.h
+++ b/arch/x86/include/asm/numa_64.h
@@ -2,7 +2,6 @@
 #define _ASM_X86_NUMA_64_H
 
 #include <linux/nodemask.h>
-#include <asm/apicdef.h>
 
 struct bootnode {
 	u64 start;
@@ -14,11 +13,8 @@ extern int compute_hash_shift(struct bootnode *nodes, int numblks,
 
 #define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT))
 
-extern void numa_init_array(void);
 extern int numa_off;
 
-extern s16 apicid_to_node[MAX_LOCAL_APIC];
-
 extern unsigned long numa_free_all_bootmem(void);
 extern void setup_node_bootmem(int nodeid, unsigned long start,
 			       unsigned long end);
@@ -31,11 +27,7 @@ extern void setup_node_bootmem(int nodeid, unsigned long start,
  */
 #define NODE_MIN_SIZE (4*1024*1024)
 
-extern void __init init_cpu_to_node(void);
-extern void __cpuinit numa_set_node(int cpu, int node);
-extern void __cpuinit numa_clear_node(int cpu);
-extern void __cpuinit numa_add_cpu(int cpu);
-extern void __cpuinit numa_remove_cpu(int cpu);
+extern int __cpuinit numa_cpu_node(int cpu);
 
 #ifdef CONFIG_NUMA_EMU
 #define FAKE_NODE_MIN_SIZE	((u64)32 << 20)
@@ -43,11 +35,7 @@ extern void __cpuinit numa_remove_cpu(int cpu);
 void numa_emu_cmdline(char *);
 #endif /* CONFIG_NUMA_EMU */
 #else
-static inline void init_cpu_to_node(void)		{ }
-static inline void numa_set_node(int cpu, int node)	{ }
-static inline void numa_clear_node(int cpu)		{ }
-static inline void numa_add_cpu(int cpu, int node)	{ }
-static inline void numa_remove_cpu(int cpu)		{ }
+static inline int numa_cpu_node(int cpu)		{ return NUMA_NO_NODE; }
 #endif
 
 #endif /* _ASM_X86_NUMA_64_H */
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 1f4695136776..b296ca6f40bb 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -38,6 +38,9 @@ static inline struct cpumask *cpu_core_mask(int cpu)
 
 DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);
 DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32)
+DECLARE_EARLY_PER_CPU(int, x86_cpu_to_logical_apicid);
+#endif
 
 /* Static state in head.S used to set up a CPU */
 extern unsigned long stack_start; /* Initial stack pointer address */
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 21899cc31e52..b101c17861f5 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -47,21 +47,6 @@
 
 #include <asm/mpspec.h>
 
-#ifdef CONFIG_X86_32
-
-/* Mappings between logical cpu number and node number */
-extern int cpu_to_node_map[];
-
-/* Returns the number of the node containing CPU 'cpu' */
-static inline int __cpu_to_node(int cpu)
-{
-	return cpu_to_node_map[cpu];
-}
-#define early_cpu_to_node __cpu_to_node
-#define cpu_to_node __cpu_to_node
-
-#else /* CONFIG_X86_64 */
-
 /* Mappings between logical cpu number and node number */
 DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);
 
@@ -84,8 +69,6 @@ static inline int early_cpu_to_node(int cpu)
 
 #endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
 
-#endif /* CONFIG_X86_64 */
-
 /* Mappings between node number and cpus on that node. */
 extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
 
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index b3a71137983a..a2c512175395 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -589,14 +589,8 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
 	nid = acpi_get_node(handle);
 	if (nid == -1 || !node_online(nid))
 		return;
-#ifdef CONFIG_X86_64
-	apicid_to_node[physid] = nid;
+	set_apicid_to_node(physid, nid);
 	numa_set_node(cpu, nid);
-#else /* CONFIG_X86_32 */
-	apicid_2_node[physid] = nid;
-	cpu_to_node_map[cpu] = nid;
-#endif
-
 #endif
 }
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 06c196d7e59c..1390cf985afd 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -78,6 +78,15 @@ EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
 EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
 
 #ifdef CONFIG_X86_32
+
+/*
+ * On x86_32, the mapping between cpu and logical apicid may vary
+ * depending on apic in use.  The following early percpu variable is
+ * used for the mapping.  This is where the behaviors of x86_64 and 32
+ * actually diverge.  Let's keep it ugly for now.
+ */
+DEFINE_EARLY_PER_CPU(int, x86_cpu_to_logical_apicid, BAD_APICID);
+
 /*
  * Knob to control our willingness to enable the local APIC.
  *
@@ -1237,6 +1246,19 @@ void __cpuinit setup_local_APIC(void)
 	 */
 	apic->init_apic_ldr();
 
+#ifdef CONFIG_X86_32
+	/*
+	 * APIC LDR is initialized.  If logical_apicid mapping was
+	 * initialized during get_smp_config(), make sure it matches the
+	 * actual value.
+	 */
+	i = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
+	WARN_ON(i != BAD_APICID && i != logical_smp_processor_id());
+	/* always use the value from LDR */
+	early_per_cpu(x86_cpu_to_logical_apicid, cpu) =
+		logical_smp_processor_id();
+#endif
+
 	/*
 	 * Set Task Priority to 'accept all'. We never change this
 	 * later on.
@@ -1972,7 +1994,10 @@ void __cpuinit generic_processor_info(int apicid, int version)
 	early_per_cpu(x86_cpu_to_apicid, cpu) = apicid;
 	early_per_cpu(x86_bios_cpu_apicid, cpu) = apicid;
 #endif
-
+#ifdef CONFIG_X86_32
+	early_per_cpu(x86_cpu_to_logical_apicid, cpu) =
+		apic->x86_32_early_logical_apicid(cpu);
+#endif
 	set_cpu_possible(cpu, true);
 	set_cpu_present(cpu, true);
 }
@@ -1993,10 +2018,14 @@ void default_init_apic_ldr(void)
 }
 
 #ifdef CONFIG_X86_32
-int default_apicid_to_node(int logical_apicid)
+int default_x86_32_numa_cpu_node(int cpu)
 {
-#ifdef CONFIG_SMP
-	return apicid_2_node[hard_smp_processor_id()];
+#ifdef CONFIG_NUMA
+	int apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
+
+	if (apicid != BAD_APICID)
+		return __apicid_to_node[apicid];
+	return NUMA_NO_NODE;
 #else
 	return 0;
 #endif
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 09d3b17ce0c2..5652d31fe108 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -185,8 +185,6 @@ struct apic apic_flat =  {
 	.ioapic_phys_id_map		= NULL,
 	.setup_apic_routing		= NULL,
 	.multi_timer_check		= NULL,
-	.apicid_to_node			= NULL,
-	.cpu_to_logical_apicid		= NULL,
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= NULL,
 	.setup_portio_remap		= NULL,
@@ -337,8 +335,6 @@ struct apic apic_physflat =  {
 	.ioapic_phys_id_map		= NULL,
 	.setup_apic_routing		= NULL,
 	.multi_timer_check		= NULL,
-	.apicid_to_node			= NULL,
-	.cpu_to_logical_apicid		= NULL,
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= NULL,
 	.setup_portio_remap		= NULL,
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index e31b9ffe25f5..f1baa2dc087a 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -54,11 +54,6 @@ static u64 noop_apic_icr_read(void)
 	return 0;
 }
 
-static int noop_cpu_to_logical_apicid(int cpu)
-{
-	return 0;
-}
-
 static int noop_phys_pkg_id(int cpuid_apic, int index_msb)
 {
 	return 0;
@@ -113,12 +108,6 @@ static void noop_vector_allocation_domain(int cpu, struct cpumask *retmask)
 	cpumask_set_cpu(cpu, retmask);
 }
 
-int noop_apicid_to_node(int logical_apicid)
-{
-	/* we're always on node 0 */
-	return 0;
-}
-
 static u32 noop_apic_read(u32 reg)
 {
 	WARN_ON_ONCE((cpu_has_apic && !disable_apic));
@@ -130,6 +119,14 @@ static void noop_apic_write(u32 reg, u32 v)
 	WARN_ON_ONCE(cpu_has_apic && !disable_apic);
 }
 
+#ifdef CONFIG_X86_32
+static int noop_x86_32_numa_cpu_node(int cpu)
+{
+	/* we're always on node 0 */
+	return 0;
+}
+#endif
+
 struct apic apic_noop = {
 	.name				= "noop",
 	.probe				= noop_probe,
@@ -153,9 +150,7 @@ struct apic apic_noop = {
 	.ioapic_phys_id_map		= default_ioapic_phys_id_map,
 	.setup_apic_routing		= NULL,
 	.multi_timer_check		= NULL,
-	.apicid_to_node			= noop_apicid_to_node,
 
-	.cpu_to_logical_apicid		= noop_cpu_to_logical_apicid,
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= physid_set_mask_of_physid,
 
@@ -197,4 +192,9 @@ struct apic apic_noop = {
 	.icr_write			= noop_apic_icr_write,
 	.wait_icr_idle			= noop_apic_wait_icr_idle,
 	.safe_wait_icr_idle		= noop_safe_apic_wait_icr_idle,
+
+#ifdef CONFIG_X86_32
+	.x86_32_early_logical_apicid	= noop_x86_32_early_logical_apicid,
+	.x86_32_numa_cpu_node		= noop_x86_32_numa_cpu_node,
+#endif
 };
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index cb804c5091b9..541a2e431659 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -45,6 +45,12 @@ static unsigned long bigsmp_check_apicid_present(int bit)
 	return 1;
 }
 
+static int bigsmp_early_logical_apicid(int cpu)
+{
+	/* on bigsmp, logical apicid is the same as physical */
+	return early_per_cpu(x86_cpu_to_apicid, cpu);
+}
+
 static inline unsigned long calculate_ldr(int cpu)
 {
 	unsigned long val, id;
@@ -80,11 +86,6 @@ static void bigsmp_setup_apic_routing(void)
 		nr_ioapics);
 }
 
-static int bigsmp_apicid_to_node(int logical_apicid)
-{
-	return apicid_2_node[hard_smp_processor_id()];
-}
-
 static int bigsmp_cpu_present_to_apicid(int mps_cpu)
 {
 	if (mps_cpu < nr_cpu_ids)
@@ -93,14 +94,6 @@ static int bigsmp_cpu_present_to_apicid(int mps_cpu)
 	return BAD_APICID;
 }
 
-/* Mapping from cpu number to logical apicid */
-static inline int bigsmp_cpu_to_logical_apicid(int cpu)
-{
-	if (cpu >= nr_cpu_ids)
-		return BAD_APICID;
-	return cpu_physical_id(cpu);
-}
-
 static void bigsmp_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap)
 {
 	/* For clustered we don't have a good way to do this yet - hack */
@@ -115,7 +108,11 @@ static int bigsmp_check_phys_apicid_present(int phys_apicid)
 /* As we are using single CPU as destination, pick only one CPU here */
 static unsigned int bigsmp_cpu_mask_to_apicid(const struct cpumask *cpumask)
 {
-	return bigsmp_cpu_to_logical_apicid(cpumask_first(cpumask));
+	int cpu = cpumask_first(cpumask);
+
+	if (cpu < nr_cpu_ids)
+		return cpu_physical_id(cpu);
+	return BAD_APICID;
 }
 
 static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
@@ -129,9 +126,9 @@ static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
 	 */
 	for_each_cpu_and(cpu, cpumask, andmask) {
 		if (cpumask_test_cpu(cpu, cpu_online_mask))
-			break;
+			return cpu_physical_id(cpu);
 	}
-	return bigsmp_cpu_to_logical_apicid(cpu);
+	return BAD_APICID;
 }
 
 static int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb)
@@ -219,8 +216,6 @@ struct apic apic_bigsmp = {
 	.ioapic_phys_id_map		= bigsmp_ioapic_phys_id_map,
 	.setup_apic_routing		= bigsmp_setup_apic_routing,
 	.multi_timer_check		= NULL,
-	.apicid_to_node			= bigsmp_apicid_to_node,
-	.cpu_to_logical_apicid		= bigsmp_cpu_to_logical_apicid,
 	.cpu_present_to_apicid		= bigsmp_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= physid_set_mask_of_physid,
 	.setup_portio_remap		= NULL,
@@ -256,4 +251,7 @@ struct apic apic_bigsmp = {
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
 	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
+
+	.x86_32_early_logical_apicid	= bigsmp_early_logical_apicid,
+	.x86_32_numa_cpu_node		= default_x86_32_numa_cpu_node,
 };
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
index 8593582d8022..3e9de4854c5b 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/arch/x86/kernel/apic/es7000_32.c
@@ -460,6 +460,12 @@ static unsigned long es7000_check_apicid_present(int bit)
 	return physid_isset(bit, phys_cpu_present_map);
 }
 
+static int es7000_early_logical_apicid(int cpu)
+{
+	/* on es7000, logical apicid is the same as physical */
+	return early_per_cpu(x86_bios_cpu_apicid, cpu);
+}
+
 static unsigned long calculate_ldr(int cpu)
 {
 	unsigned long id = per_cpu(x86_bios_cpu_apicid, cpu);
@@ -504,12 +510,11 @@ static void es7000_setup_apic_routing(void)
 		nr_ioapics, cpumask_bits(es7000_target_cpus())[0]);
 }
 
-static int es7000_apicid_to_node(int logical_apicid)
+static int es7000_numa_cpu_node(int cpu)
 {
 	return 0;
 }
 
-
 static int es7000_cpu_present_to_apicid(int mps_cpu)
 {
 	if (!mps_cpu)
@@ -528,18 +533,6 @@ static void es7000_apicid_to_cpu_present(int phys_apicid, physid_mask_t *retmap)
 	++cpu_id;
 }
 
-/* Mapping from cpu number to logical apicid */
-static int es7000_cpu_to_logical_apicid(int cpu)
-{
-#ifdef CONFIG_SMP
-	if (cpu >= nr_cpu_ids)
-		return BAD_APICID;
-	return cpu_2_logical_apicid[cpu];
-#else
-	return logical_smp_processor_id();
-#endif
-}
-
 static void es7000_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap)
 {
 	/* For clustered we don't have a good way to do this yet - hack */
@@ -561,7 +554,7 @@ static unsigned int es7000_cpu_mask_to_apicid(const struct cpumask *cpumask)
 	 * The cpus in the mask must all be on the apic cluster.
 	 */
 	for_each_cpu(cpu, cpumask) {
-		int new_apicid = es7000_cpu_to_logical_apicid(cpu);
+		int new_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
 
 		if (round && APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) {
 			WARN(1, "Not a valid mask!");
@@ -578,7 +571,7 @@ static unsigned int
 es7000_cpu_mask_to_apicid_and(const struct cpumask *inmask,
 			      const struct cpumask *andmask)
 {
-	int apicid = es7000_cpu_to_logical_apicid(0);
+	int apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0);
 	cpumask_var_t cpumask;
 
 	if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC))
@@ -655,8 +648,6 @@ struct apic __refdata apic_es7000_cluster = {
 	.ioapic_phys_id_map		= es7000_ioapic_phys_id_map,
 	.setup_apic_routing		= es7000_setup_apic_routing,
 	.multi_timer_check		= NULL,
-	.apicid_to_node			= es7000_apicid_to_node,
-	.cpu_to_logical_apicid		= es7000_cpu_to_logical_apicid,
 	.cpu_present_to_apicid		= es7000_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= es7000_apicid_to_cpu_present,
 	.setup_portio_remap		= NULL,
@@ -695,6 +686,9 @@ struct apic __refdata apic_es7000_cluster = {
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
 	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
+
+	.x86_32_early_logical_apicid	= es7000_early_logical_apicid,
+	.x86_32_numa_cpu_node		= es7000_numa_cpu_node,
 };
 
 struct apic __refdata apic_es7000 = {
@@ -720,8 +714,6 @@ struct apic __refdata apic_es7000 = {
 	.ioapic_phys_id_map		= es7000_ioapic_phys_id_map,
 	.setup_apic_routing		= es7000_setup_apic_routing,
 	.multi_timer_check		= NULL,
-	.apicid_to_node			= es7000_apicid_to_node,
-	.cpu_to_logical_apicid		= es7000_cpu_to_logical_apicid,
 	.cpu_present_to_apicid		= es7000_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= es7000_apicid_to_cpu_present,
 	.setup_portio_remap		= NULL,
@@ -758,4 +750,7 @@ struct apic __refdata apic_es7000 = {
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
 	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
+
+	.x86_32_early_logical_apicid	= es7000_early_logical_apicid,
+	.x86_32_numa_cpu_node		= es7000_numa_cpu_node,
 };
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index 08385e090a6f..cce91bf26676 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -56,6 +56,8 @@ void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask,
 	local_irq_restore(flags);
 }
 
+#ifdef CONFIG_X86_32
+
 void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
 						 int vector)
 {
@@ -71,8 +73,8 @@ void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
 	local_irq_save(flags);
 	for_each_cpu(query_cpu, mask)
 		__default_send_IPI_dest_field(
-			apic->cpu_to_logical_apicid(query_cpu), vector,
-			apic->dest_logical);
+			early_per_cpu(x86_cpu_to_logical_apicid, query_cpu),
+			vector, apic->dest_logical);
 	local_irq_restore(flags);
 }
 
@@ -90,14 +92,12 @@ void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask,
 		if (query_cpu == this_cpu)
 			continue;
 		__default_send_IPI_dest_field(
-			apic->cpu_to_logical_apicid(query_cpu), vector,
-			apic->dest_logical);
+			early_per_cpu(x86_cpu_to_logical_apicid, query_cpu),
+			vector, apic->dest_logical);
 		}
 	local_irq_restore(flags);
 }
 
-#ifdef CONFIG_X86_32
-
 /*
  * This is only used on smaller machines.
  */
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index 960f26ab5c9f..6273eee5134b 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -373,13 +373,6 @@ static inline void numaq_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask
 	return physids_promote(0xFUL, retmap);
 }
 
-static inline int numaq_cpu_to_logical_apicid(int cpu)
-{
-	if (cpu >= nr_cpu_ids)
-		return BAD_APICID;
-	return cpu_2_logical_apicid[cpu];
-}
-
 /*
  * Supporting over 60 cpus on NUMA-Q requires a locality-dependent
  * cpu to APIC ID relation to properly interact with the intelligent
@@ -398,6 +391,15 @@ static inline int numaq_apicid_to_node(int logical_apicid)
 	return logical_apicid >> 4;
 }
 
+static int numaq_numa_cpu_node(int cpu)
+{
+	int logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
+
+	if (logical_apicid != BAD_APICID)
+		return numaq_apicid_to_node(logical_apicid);
+	return NUMA_NO_NODE;
+}
+
 static void numaq_apicid_to_cpu_present(int logical_apicid, physid_mask_t *retmap)
 {
 	int node = numaq_apicid_to_node(logical_apicid);
@@ -508,8 +510,6 @@ struct apic __refdata apic_numaq = {
 	.ioapic_phys_id_map		= numaq_ioapic_phys_id_map,
 	.setup_apic_routing		= numaq_setup_apic_routing,
 	.multi_timer_check		= numaq_multi_timer_check,
-	.apicid_to_node			= numaq_apicid_to_node,
-	.cpu_to_logical_apicid		= numaq_cpu_to_logical_apicid,
 	.cpu_present_to_apicid		= numaq_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= numaq_apicid_to_cpu_present,
 	.setup_portio_remap		= numaq_setup_portio_remap,
@@ -547,4 +547,7 @@ struct apic __refdata apic_numaq = {
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
 	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
+
+	.x86_32_early_logical_apicid	= noop_x86_32_early_logical_apicid,
+	.x86_32_numa_cpu_node		= numaq_numa_cpu_node,
 };
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 99d2fe016084..fc84c7b61108 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -77,6 +77,11 @@ void __init default_setup_apic_routing(void)
 		apic->setup_apic_routing();
 }
 
+static int default_x86_32_early_logical_apicid(int cpu)
+{
+	return 1 << cpu;
+}
+
 static void setup_apic_flat_routing(void)
 {
 #ifdef CONFIG_X86_IO_APIC
@@ -130,8 +135,6 @@ struct apic apic_default = {
 	.ioapic_phys_id_map		= default_ioapic_phys_id_map,
 	.setup_apic_routing		= setup_apic_flat_routing,
 	.multi_timer_check		= NULL,
-	.apicid_to_node			= default_apicid_to_node,
-	.cpu_to_logical_apicid		= default_cpu_to_logical_apicid,
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= physid_set_mask_of_physid,
 	.setup_portio_remap		= NULL,
@@ -167,6 +170,9 @@ struct apic apic_default = {
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
 	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
+
+	.x86_32_early_logical_apicid	= default_x86_32_early_logical_apicid,
+	.x86_32_numa_cpu_node		= default_x86_32_numa_cpu_node,
 };
 
 extern struct apic apic_numaq;
diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c
index 9b419263d90d..e4b8059b414a 100644
--- a/arch/x86/kernel/apic/summit_32.c
+++ b/arch/x86/kernel/apic/summit_32.c
@@ -194,11 +194,10 @@ static unsigned long summit_check_apicid_present(int bit)
 	return 1;
 }
 
-static void summit_init_apic_ldr(void)
+static int summit_early_logical_apicid(int cpu)
 {
-	unsigned long val, id;
 	int count = 0;
-	u8 my_id = (u8)hard_smp_processor_id();
+	u8 my_id = early_per_cpu(x86_cpu_to_apicid, cpu);
 	u8 my_cluster = APIC_CLUSTER(my_id);
 #ifdef CONFIG_SMP
 	u8 lid;
@@ -206,7 +205,7 @@ static void summit_init_apic_ldr(void)
 
 	/* Create logical APIC IDs by counting CPUs already in cluster. */
 	for (count = 0, i = nr_cpu_ids; --i >= 0; ) {
-		lid = cpu_2_logical_apicid[i];
+		lid = early_per_cpu(x86_cpu_to_logical_apicid, i);
 		if (lid != BAD_APICID && APIC_CLUSTER(lid) == my_cluster)
 			++count;
 	}
@@ -214,7 +213,15 @@ static void summit_init_apic_ldr(void)
 	/* We only have a 4 wide bitmap in cluster mode.  If a deranged
 	 * BIOS puts 5 CPUs in one APIC cluster, we're hosed. */
 	BUG_ON(count >= XAPIC_DEST_CPUS_SHIFT);
-	id = my_cluster | (1UL << count);
+	return my_cluster | (1UL << count);
+}
+
+static void summit_init_apic_ldr(void)
+{
+	int cpu = smp_processor_id();
+	unsigned long id = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
+	unsigned long val;
+
 	apic_write(APIC_DFR, SUMMIT_APIC_DFR_VALUE);
 	val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
 	val |= SET_APIC_LOGICAL_ID(id);
@@ -232,27 +239,6 @@ static void summit_setup_apic_routing(void)
 						nr_ioapics);
 }
 
-static int summit_apicid_to_node(int logical_apicid)
-{
-#ifdef CONFIG_SMP
-	return apicid_2_node[hard_smp_processor_id()];
-#else
-	return 0;
-#endif
-}
-
-/* Mapping from cpu number to logical apicid */
-static inline int summit_cpu_to_logical_apicid(int cpu)
-{
-#ifdef CONFIG_SMP
-	if (cpu >= nr_cpu_ids)
-		return BAD_APICID;
-	return cpu_2_logical_apicid[cpu];
-#else
-	return logical_smp_processor_id();
-#endif
-}
-
 static int summit_cpu_present_to_apicid(int mps_cpu)
 {
 	if (mps_cpu < nr_cpu_ids)
@@ -286,7 +272,7 @@ static unsigned int summit_cpu_mask_to_apicid(const struct cpumask *cpumask)
 	 * The cpus in the mask must all be on the apic cluster.
 	 */
 	for_each_cpu(cpu, cpumask) {
-		int new_apicid = summit_cpu_to_logical_apicid(cpu);
+		int new_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
 
 		if (round && APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) {
 			printk("%s: Not a valid mask!\n", __func__);
@@ -301,7 +287,7 @@ static unsigned int summit_cpu_mask_to_apicid(const struct cpumask *cpumask)
 static unsigned int summit_cpu_mask_to_apicid_and(const struct cpumask *inmask,
 			      const struct cpumask *andmask)
 {
-	int apicid = summit_cpu_to_logical_apicid(0);
+	int apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0);
 	cpumask_var_t cpumask;
 
 	if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC))
@@ -528,8 +514,6 @@ struct apic apic_summit = {
 	.ioapic_phys_id_map		= summit_ioapic_phys_id_map,
 	.setup_apic_routing		= summit_setup_apic_routing,
 	.multi_timer_check		= NULL,
-	.apicid_to_node			= summit_apicid_to_node,
-	.cpu_to_logical_apicid		= summit_cpu_to_logical_apicid,
 	.cpu_present_to_apicid		= summit_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= summit_apicid_to_cpu_present,
 	.setup_portio_remap		= NULL,
@@ -565,4 +549,7 @@ struct apic apic_summit = {
 	.icr_write			= native_apic_icr_write,
 	.wait_icr_idle			= native_apic_wait_icr_idle,
 	.safe_wait_icr_idle		= native_safe_apic_wait_icr_idle,
+
+	.x86_32_early_logical_apicid	= summit_early_logical_apicid,
+	.x86_32_numa_cpu_node		= default_x86_32_numa_cpu_node,
 };
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index cf69c59f4910..90949bbd566d 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -206,8 +206,6 @@ struct apic apic_x2apic_cluster = {
 	.ioapic_phys_id_map		= NULL,
 	.setup_apic_routing		= NULL,
 	.multi_timer_check		= NULL,
-	.apicid_to_node			= NULL,
-	.cpu_to_logical_apicid		= NULL,
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= NULL,
 	.setup_portio_remap		= NULL,
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 8972f38c5ced..c7e6d6645bf4 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -195,8 +195,6 @@ struct apic apic_x2apic_phys = {
 	.ioapic_phys_id_map		= NULL,
 	.setup_apic_routing		= NULL,
 	.multi_timer_check		= NULL,
-	.apicid_to_node			= NULL,
-	.cpu_to_logical_apicid		= NULL,
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= NULL,
 	.setup_portio_remap		= NULL,
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index bd16b58b8850..3c289281394c 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -338,8 +338,6 @@ struct apic __refdata apic_x2apic_uv_x = {
 	.ioapic_phys_id_map		= NULL,
 	.setup_apic_routing		= NULL,
 	.multi_timer_check		= NULL,
-	.apicid_to_node			= NULL,
-	.cpu_to_logical_apicid		= NULL,
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= NULL,
 	.setup_portio_remap		= NULL,
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 7c7bedb83c5a..77858fd64620 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -233,18 +233,22 @@ static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c)
 }
 #endif
 
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+#ifdef CONFIG_NUMA
+/*
+ * To workaround broken NUMA config.  Read the comment in
+ * srat_detect_node().
+ */
 static int __cpuinit nearby_node(int apicid)
 {
 	int i, node;
 
 	for (i = apicid - 1; i >= 0; i--) {
-		node = apicid_to_node[i];
+		node = __apicid_to_node[i];
 		if (node != NUMA_NO_NODE && node_online(node))
 			return node;
 	}
 	for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) {
-		node = apicid_to_node[i];
+		node = __apicid_to_node[i];
 		if (node != NUMA_NO_NODE && node_online(node))
 			return node;
 	}
@@ -334,31 +338,40 @@ EXPORT_SYMBOL_GPL(amd_get_nb_id);
 
 static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
 {
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+#ifdef CONFIG_NUMA
 	int cpu = smp_processor_id();
 	int node;
 	unsigned apicid = c->apicid;
 
-	node = per_cpu(cpu_llc_id, cpu);
+	node = numa_cpu_node(cpu);
+	if (node == NUMA_NO_NODE)
+		node = per_cpu(cpu_llc_id, cpu);
 
-	if (apicid_to_node[apicid] != NUMA_NO_NODE)
-		node = apicid_to_node[apicid];
 	if (!node_online(node)) {
-		/* Two possibilities here:
-		   - The CPU is missing memory and no node was created.
-		   In that case try picking one from a nearby CPU
-		   - The APIC IDs differ from the HyperTransport node IDs
-		   which the K8 northbridge parsing fills in.
-		   Assume they are all increased by a constant offset,
-		   but in the same order as the HT nodeids.
-		   If that doesn't result in a usable node fall back to the
-		   path for the previous case.  */
-
+		/*
+		 * Two possibilities here:
+		 *
+		 * - The CPU is missing memory and no node was created.  In
+		 *   that case try picking one from a nearby CPU.
+		 *
+		 * - The APIC IDs differ from the HyperTransport node IDs
+		 *   which the K8 northbridge parsing fills in.  Assume
+		 *   they are all increased by a constant offset, but in
+		 *   the same order as the HT nodeids.  If that doesn't
+		 *   result in a usable node fall back to the path for the
+		 *   previous case.
+		 *
+		 * This workaround operates directly on the mapping between
+		 * APIC ID and NUMA node, assuming certain relationship
+		 * between APIC ID, HT node ID and NUMA topology.  As going
+		 * through CPU mapping may alter the outcome, directly
+		 * access __apicid_to_node[].
+		 */
 		int ht_nodeid = c->initial_apicid;
 
 		if (ht_nodeid >= 0 &&
-		    apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
-			node = apicid_to_node[ht_nodeid];
+		    __apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
+			node = __apicid_to_node[ht_nodeid];
 		/* Pick a nearby node */
 		if (!node_online(node))
 			node = nearby_node(apicid);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 1d59834396bd..a2559c3ed500 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -869,7 +869,7 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 
 	select_idle_routine(c);
 
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+#ifdef CONFIG_NUMA
 	numa_add_cpu(smp_processor_id());
 #endif
 }
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index d16c2c53d6bf..df86bc8c859d 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -276,14 +276,13 @@ static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c)
 
 static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
 {
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+#ifdef CONFIG_NUMA
 	unsigned node;
 	int cpu = smp_processor_id();
-	int apicid = cpu_has_apic ? hard_smp_processor_id() : c->apicid;
 
 	/* Don't do the funky fallback heuristics the AMD version employs
 	   for now. */
-	node = apicid_to_node[apicid];
+	node = numa_cpu_node(cpu);
 	if (node == NUMA_NO_NODE || !node_online(node)) {
 		/* reuse the value from init_cpu_to_node() */
 		node = cpu_to_node(cpu);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 6b286d879a25..ac909ba297b9 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1047,9 +1047,7 @@ void __init setup_arch(char **cmdline_p)
 
 	prefill_possible_map();
 
-#ifdef CONFIG_X86_64
 	init_cpu_to_node();
-#endif
 
 	init_apic_mappings();
 	ioapic_and_gsi_init();
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 002b79685f73..71f4727da373 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -225,10 +225,15 @@ void __init setup_per_cpu_areas(void)
 		per_cpu(x86_bios_cpu_apicid, cpu) =
 			early_per_cpu_map(x86_bios_cpu_apicid, cpu);
 #endif
+#ifdef CONFIG_X86_32
+		per_cpu(x86_cpu_to_logical_apicid, cpu) =
+			early_per_cpu_map(x86_cpu_to_logical_apicid, cpu);
+#endif
 #ifdef CONFIG_X86_64
 		per_cpu(irq_stack_ptr, cpu) =
 			per_cpu(irq_stack_union.irq_stack, cpu) +
 			IRQ_STACK_SIZE - 64;
+#endif
 #ifdef CONFIG_NUMA
 		per_cpu(x86_cpu_to_node_map, cpu) =
 			early_per_cpu_map(x86_cpu_to_node_map, cpu);
@@ -242,7 +247,6 @@ void __init setup_per_cpu_areas(void)
 		 */
 		set_cpu_numa_node(cpu, early_cpu_to_node(cpu));
 #endif
-#endif
 		/*
 		 * Up to this point, the boot CPU has been using .init.data
 		 * area.  Reload any changed state for the boot CPU.
@@ -256,7 +260,10 @@ void __init setup_per_cpu_areas(void)
 	early_per_cpu_ptr(x86_cpu_to_apicid) = NULL;
 	early_per_cpu_ptr(x86_bios_cpu_apicid) = NULL;
 #endif
-#if defined(CONFIG_X86_64) && defined(CONFIG_NUMA)
+#ifdef CONFIG_X86_32
+	early_per_cpu_ptr(x86_cpu_to_logical_apicid) = NULL;
+#endif
+#ifdef CONFIG_NUMA
 	early_per_cpu_ptr(x86_cpu_to_node_map) = NULL;
 #endif
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 03273b6c272c..8886ef36d5dd 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -71,10 +71,6 @@
 #include <asm/smpboot_hooks.h>
 #include <asm/i8259.h>
 
-#ifdef CONFIG_X86_32
-u8 apicid_2_node[MAX_APICID];
-#endif
-
 /* State of each CPU */
 DEFINE_PER_CPU(int, cpu_state) = { 0 };
 
@@ -136,62 +132,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_info);
 
 atomic_t init_deasserted;
 
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_32)
-/* which node each logical CPU is on */
-int cpu_to_node_map[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = 0 };
-EXPORT_SYMBOL(cpu_to_node_map);
-
-/* set up a mapping between cpu and node. */
-static void map_cpu_to_node(int cpu, int node)
-{
-	printk(KERN_INFO "Mapping cpu %d to node %d\n", cpu, node);
-	cpumask_set_cpu(cpu, node_to_cpumask_map[node]);
-	cpu_to_node_map[cpu] = node;
-}
-
-/* undo a mapping between cpu and node. */
-static void unmap_cpu_to_node(int cpu)
-{
-	int node;
-
-	printk(KERN_INFO "Unmapping cpu %d from all nodes\n", cpu);
-	for (node = 0; node < MAX_NUMNODES; node++)
-		cpumask_clear_cpu(cpu, node_to_cpumask_map[node]);
-	cpu_to_node_map[cpu] = 0;
-}
-#else /* !(CONFIG_NUMA && CONFIG_X86_32) */
-#define map_cpu_to_node(cpu, node)	({})
-#define unmap_cpu_to_node(cpu)	({})
-#endif
-
-#ifdef CONFIG_X86_32
-static int boot_cpu_logical_apicid;
-
-u8 cpu_2_logical_apicid[NR_CPUS] __read_mostly =
-					{ [0 ... NR_CPUS-1] = BAD_APICID };
-
-static void map_cpu_to_logical_apicid(void)
-{
-	int cpu = smp_processor_id();
-	int apicid = logical_smp_processor_id();
-	int node = apic->apicid_to_node(apicid);
-
-	if (!node_online(node))
-		node = first_online_node;
-
-	cpu_2_logical_apicid[cpu] = apicid;
-	map_cpu_to_node(cpu, node);
-}
-
-void numa_remove_cpu(int cpu)
-{
-	cpu_2_logical_apicid[cpu] = BAD_APICID;
-	unmap_cpu_to_node(cpu);
-}
-#else
-#define map_cpu_to_logical_apicid()  do {} while (0)
-#endif
-
 /*
  * Report back to the Boot Processor.
  * Running on AP.
@@ -259,7 +199,6 @@ static void __cpuinit smp_callin(void)
 		apic->smp_callin_clear_local_apic();
 	setup_local_APIC();
 	end_local_APIC_setup();
-	map_cpu_to_logical_apicid();
 
 	/*
 	 * Need to setup vector mappings before we enable interrupts.
@@ -960,7 +899,6 @@ static __init void disable_smp(void)
 		physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
 	else
 		physid_set_mask_of_physid(0, &phys_cpu_present_map);
-	map_cpu_to_logical_apicid();
 	cpumask_set_cpu(0, cpu_sibling_mask(0));
 	cpumask_set_cpu(0, cpu_core_mask(0));
 }
@@ -1096,9 +1034,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	 * Setup boot CPU information
 	 */
 	smp_store_cpu_info(0); /* Final full version of the data */
-#ifdef CONFIG_X86_32
-	boot_cpu_logical_apicid = logical_smp_processor_id();
-#endif
+
 	current_thread_info()->cpu = 0;  /* needed? */
 	for_each_possible_cpu(i) {
 		zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
@@ -1139,8 +1075,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 
 	end_local_APIC_setup();
 
-	map_cpu_to_logical_apicid();
-
 	if (apic->setup_portio_remap)
 		apic->setup_portio_remap();
 
diff --git a/arch/x86/mm/amdtopology_64.c b/arch/x86/mm/amdtopology_64.c
index 49b334cdd64c..2523c3554de5 100644
--- a/arch/x86/mm/amdtopology_64.c
+++ b/arch/x86/mm/amdtopology_64.c
@@ -247,7 +247,7 @@ void __init amd_fake_nodes(const struct bootnode *nodes, int nr_nodes)
 		__acpi_map_pxm_to_node(nid, i);
 #endif
 	}
-	memcpy(apicid_to_node, fake_apicid_to_node, sizeof(apicid_to_node));
+	memcpy(__apicid_to_node, fake_apicid_to_node, sizeof(__apicid_to_node));
 }
 #endif /* CONFIG_NUMA_EMU */
 
@@ -287,7 +287,7 @@ int __init amd_scan_nodes(void)
 		int j;
 
 		for (j = apicid_base; j < cores + apicid_base; j++)
-			apicid_to_node[(i << bits) + j] = i;
+			set_apicid_to_node((i << bits) + j, i);
 		setup_node_bootmem(i, nodes[i].start, nodes[i].end);
 	}
 
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index ebf6d7887a38..9559d360fde7 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -26,12 +26,50 @@ static __init int numa_setup(char *opt)
 early_param("numa", numa_setup);
 
 /*
- * Which logical CPUs are on which nodes
+ * apicid, cpu, node mappings
  */
+s16 __apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = {
+	[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
+};
+
 cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
 EXPORT_SYMBOL(node_to_cpumask_map);
 
 /*
+ * Map cpu index to node index
+ */
+DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE);
+EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map);
+
+void __cpuinit numa_set_node(int cpu, int node)
+{
+	int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);
+
+	/* early setting, no percpu area yet */
+	if (cpu_to_node_map) {
+		cpu_to_node_map[cpu] = node;
+		return;
+	}
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+	if (cpu >= nr_cpu_ids || !cpu_possible(cpu)) {
+		printk(KERN_ERR "numa_set_node: invalid cpu# (%d)\n", cpu);
+		dump_stack();
+		return;
+	}
+#endif
+	per_cpu(x86_cpu_to_node_map, cpu) = node;
+
+	if (node != NUMA_NO_NODE)
+		set_cpu_numa_node(cpu, node);
+}
+
+void __cpuinit numa_clear_node(int cpu)
+{
+	numa_set_node(cpu, NUMA_NO_NODE);
+}
+
+/*
  * Allocate node_to_cpumask_map based on number of available nodes
  * Requires node_possible_map to be valid.
  *
@@ -57,7 +95,174 @@ void __init setup_node_to_cpumask_map(void)
 	pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
 }
 
-#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+/*
+ * There are unfortunately some poorly designed mainboards around that
+ * only connect memory to a single CPU. This breaks the 1:1 cpu->node
+ * mapping. To avoid this fill in the mapping for all possible CPUs,
+ * as the number of CPUs is not known yet. We round robin the existing
+ * nodes.
+ */
+void __init numa_init_array(void)
+{
+	int rr, i;
+
+	rr = first_node(node_online_map);
+	for (i = 0; i < nr_cpu_ids; i++) {
+		if (early_cpu_to_node(i) != NUMA_NO_NODE)
+			continue;
+		numa_set_node(i, rr);
+		rr = next_node(rr, node_online_map);
+		if (rr == MAX_NUMNODES)
+			rr = first_node(node_online_map);
+	}
+}
+
+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.
+ *
+ * Populate cpu_to_node[] only if x86_cpu_to_apicid[],
+ * and apicid_to_node[] tables have valid entries for a CPU.
+ * This means we skip cpu_to_node[] initialisation for NUMA
+ * emulation and faking node case (when running a kernel compiled
+ * for NUMA on a non NUMA box), which is OK as cpu_to_node[]
+ * is already initialized in a round robin manner at numa_init_array,
+ * prior to this call, and this initialization is good enough
+ * for the fake NUMA cases.
+ *
+ * Called before the per_cpu areas are setup.
+ */
+void __init init_cpu_to_node(void)
+{
+	int cpu;
+	u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
+
+	BUG_ON(cpu_to_apicid == NULL);
+
+	for_each_possible_cpu(cpu) {
+		int node = numa_cpu_node(cpu);
+
+		if (node == NUMA_NO_NODE)
+			continue;
+		if (!node_online(node))
+			node = find_near_online_node(node);
+		numa_set_node(cpu, node);
+	}
+}
+
+#ifndef CONFIG_DEBUG_PER_CPU_MAPS
+
+# ifndef CONFIG_NUMA_EMU
+void __cpuinit numa_add_cpu(int cpu)
+{
+	cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
+}
+
+void __cpuinit numa_remove_cpu(int cpu)
+{
+	cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
+}
+# endif	/* !CONFIG_NUMA_EMU */
+
+#else	/* !CONFIG_DEBUG_PER_CPU_MAPS */
+
+int __cpu_to_node(int cpu)
+{
+	if (early_per_cpu_ptr(x86_cpu_to_node_map)) {
+		printk(KERN_WARNING
+			"cpu_to_node(%d): usage too early!\n", cpu);
+		dump_stack();
+		return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
+	}
+	return per_cpu(x86_cpu_to_node_map, cpu);
+}
+EXPORT_SYMBOL(__cpu_to_node);
+
+/*
+ * Same function as cpu_to_node() but used if called before the
+ * per_cpu areas are setup.
+ */
+int early_cpu_to_node(int cpu)
+{
+	if (early_per_cpu_ptr(x86_cpu_to_node_map))
+		return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
+
+	if (!cpu_possible(cpu)) {
+		printk(KERN_WARNING
+			"early_cpu_to_node(%d): no per_cpu area!\n", cpu);
+		dump_stack();
+		return NUMA_NO_NODE;
+	}
+	return per_cpu(x86_cpu_to_node_map, cpu);
+}
+
+struct cpumask __cpuinit *debug_cpumask_set_cpu(int cpu, int enable)
+{
+	int node = early_cpu_to_node(cpu);
+	struct cpumask *mask;
+	char buf[64];
+
+	if (node == NUMA_NO_NODE) {
+		/* early_cpu_to_node() already emits a warning and trace */
+		return NULL;
+	}
+	mask = node_to_cpumask_map[node];
+	if (!mask) {
+		pr_err("node_to_cpumask_map[%i] NULL\n", node);
+		dump_stack();
+		return NULL;
+	}
+
+	cpulist_scnprintf(buf, sizeof(buf), mask);
+	printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
+		enable ? "numa_add_cpu" : "numa_remove_cpu",
+		cpu, node, buf);
+	return mask;
+}
+
+# ifndef CONFIG_NUMA_EMU
+static void __cpuinit numa_set_cpumask(int cpu, int enable)
+{
+	struct cpumask *mask;
+
+	mask = debug_cpumask_set_cpu(cpu, enable);
+	if (!mask)
+		return;
+
+	if (enable)
+		cpumask_set_cpu(cpu, mask);
+	else
+		cpumask_clear_cpu(cpu, mask);
+}
+
+void __cpuinit numa_add_cpu(int cpu)
+{
+	numa_set_cpumask(cpu, 1);
+}
+
+void __cpuinit numa_remove_cpu(int cpu)
+{
+	numa_set_cpumask(cpu, 0);
+}
+# endif	/* !CONFIG_NUMA_EMU */
+
 /*
  * Returns a pointer to the bitmask of CPUs on Node 'node'.
  */
@@ -80,4 +285,5 @@ const struct cpumask *cpumask_of_node(int node)
 	return node_to_cpumask_map[node];
 }
 EXPORT_SYMBOL(cpumask_of_node);
-#endif
+
+#endif	/* !CONFIG_DEBUG_PER_CPU_MAPS */
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 84a3e4c9f277..505bb04654b5 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -110,6 +110,12 @@ void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
 
 static unsigned long kva_start_pfn;
 static unsigned long kva_pages;
+
+int __cpuinit numa_cpu_node(int cpu)
+{
+	return apic->x86_32_numa_cpu_node(cpu);
+}
+
 /*
  * FLAT - support for basic PC memory model with discontig enabled, essentially
  *        a single node with all available processors in it with a flat
@@ -361,6 +367,7 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 	 */
 
 	get_memcfg_numa();
+	numa_init_array();
 
 	kva_pages = roundup(calculate_numa_remap_pages(), PTRS_PER_PTE);
 
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 62cb634b5cf8..43ad3273561a 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -26,20 +26,10 @@ EXPORT_SYMBOL(node_data);
 
 struct memnode memnode;
 
-s16 apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = {
-	[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
-};
-
 static unsigned long __initdata nodemap_addr;
 static unsigned long __initdata nodemap_size;
 
 /*
- * Map cpu index to node index
- */
-DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE);
-EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map);
-
-/*
  * Given a shift value, try to populate memnodemap[]
  * Returns :
  * 1 if OK
@@ -234,28 +224,6 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 	node_set_online(nodeid);
 }
 
-/*
- * There are unfortunately some poorly designed mainboards around that
- * only connect memory to a single CPU. This breaks the 1:1 cpu->node
- * mapping. To avoid this fill in the mapping for all possible CPUs,
- * as the number of CPUs is not known yet. We round robin the existing
- * nodes.
- */
-void __init numa_init_array(void)
-{
-	int rr, i;
-
-	rr = first_node(node_online_map);
-	for (i = 0; i < nr_cpu_ids; i++) {
-		if (early_cpu_to_node(i) != NUMA_NO_NODE)
-			continue;
-		numa_set_node(i, rr);
-		rr = next_node(rr, node_online_map);
-		if (rr == MAX_NUMNODES)
-			rr = first_node(node_online_map);
-	}
-}
-
 #ifdef CONFIG_NUMA_EMU
 /* Numa emulation */
 static struct bootnode nodes[MAX_NUMNODES] __initdata;
@@ -676,115 +644,33 @@ unsigned long __init numa_free_all_bootmem(void)
 	return pages;
 }
 
-#ifdef CONFIG_NUMA
-
-static __init int find_near_online_node(int node)
+int __cpuinit numa_cpu_node(int cpu)
 {
-	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;
-		}
-	}
+	int apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
 
-	return best_node;
+	if (apicid != BAD_APICID)
+		return __apicid_to_node[apicid];
+	return NUMA_NO_NODE;
 }
 
 /*
- * Setup early cpu_to_node.
+ * UGLINESS AHEAD: Currently, CONFIG_NUMA_EMU is 64bit only and makes use
+ * of 64bit specific data structures.  The distinction is artificial and
+ * should be removed.  numa_{add|remove}_cpu() are implemented in numa.c
+ * for both 32 and 64bit when CONFIG_NUMA_EMU is disabled but here when
+ * enabled.
  *
- * Populate cpu_to_node[] only if x86_cpu_to_apicid[],
- * and apicid_to_node[] tables have valid entries for a CPU.
- * This means we skip cpu_to_node[] initialisation for NUMA
- * emulation and faking node case (when running a kernel compiled
- * for NUMA on a non NUMA box), which is OK as cpu_to_node[]
- * is already initialized in a round robin manner at numa_init_array,
- * prior to this call, and this initialization is good enough
- * for the fake NUMA cases.
- *
- * Called before the per_cpu areas are setup.
+ * NUMA emulation is planned to be made generic and the following and other
+ * related code should be moved to numa.c.
  */
-void __init init_cpu_to_node(void)
-{
-	int cpu;
-	u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
-
-	BUG_ON(cpu_to_apicid == NULL);
-
-	for_each_possible_cpu(cpu) {
-		int node;
-		u16 apicid = cpu_to_apicid[cpu];
-
-		if (apicid == BAD_APICID)
-			continue;
-		node = apicid_to_node[apicid];
-		if (node == NUMA_NO_NODE)
-			continue;
-		if (!node_online(node))
-			node = find_near_online_node(node);
-		numa_set_node(cpu, node);
-	}
-}
-#endif
-
-
-void __cpuinit numa_set_node(int cpu, int node)
-{
-	int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);
-
-	/* early setting, no percpu area yet */
-	if (cpu_to_node_map) {
-		cpu_to_node_map[cpu] = node;
-		return;
-	}
-
-#ifdef CONFIG_DEBUG_PER_CPU_MAPS
-	if (cpu >= nr_cpu_ids || !cpu_possible(cpu)) {
-		printk(KERN_ERR "numa_set_node: invalid cpu# (%d)\n", cpu);
-		dump_stack();
-		return;
-	}
-#endif
-	per_cpu(x86_cpu_to_node_map, cpu) = node;
-
-	if (node != NUMA_NO_NODE)
-		set_cpu_numa_node(cpu, node);
-}
-
-void __cpuinit numa_clear_node(int cpu)
-{
-	numa_set_node(cpu, NUMA_NO_NODE);
-}
-
-#ifndef CONFIG_DEBUG_PER_CPU_MAPS
-
-#ifndef CONFIG_NUMA_EMU
-void __cpuinit numa_add_cpu(int cpu)
-{
-	cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
-}
-
-void __cpuinit numa_remove_cpu(int cpu)
-{
-	cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
-}
-#else
+#ifdef CONFIG_NUMA_EMU
+# ifndef CONFIG_DEBUG_PER_CPU_MAPS
 void __cpuinit numa_add_cpu(int cpu)
 {
 	unsigned long addr;
-	u16 apicid;
-	int physnid;
-	int nid = NUMA_NO_NODE;
+	int physnid, nid;
 
-	apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
-	if (apicid != BAD_APICID)
-		nid = apicid_to_node[apicid];
+	nid = numa_cpu_node(cpu);
 	if (nid == NUMA_NO_NODE)
 		nid = early_cpu_to_node(cpu);
 	BUG_ON(nid == NUMA_NO_NODE || !node_online(nid));
@@ -818,53 +704,17 @@ void __cpuinit numa_remove_cpu(int cpu)
 	for_each_online_node(i)
 		cpumask_clear_cpu(cpu, node_to_cpumask_map[i]);
 }
-#endif /* !CONFIG_NUMA_EMU */
-
-#else /* CONFIG_DEBUG_PER_CPU_MAPS */
-static struct cpumask __cpuinit *debug_cpumask_set_cpu(int cpu, int enable)
-{
-	int node = early_cpu_to_node(cpu);
-	struct cpumask *mask;
-	char buf[64];
-
-	mask = node_to_cpumask_map[node];
-	if (!mask) {
-		pr_err("node_to_cpumask_map[%i] NULL\n", node);
-		dump_stack();
-		return NULL;
-	}
-
-	cpulist_scnprintf(buf, sizeof(buf), mask);
-	printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
-		enable ? "numa_add_cpu" : "numa_remove_cpu",
-		cpu, node, buf);
-	return mask;
-}
-
-/*
- * --------- debug versions of the numa functions ---------
- */
-#ifndef CONFIG_NUMA_EMU
-static void __cpuinit numa_set_cpumask(int cpu, int enable)
-{
-	struct cpumask *mask;
-
-	mask = debug_cpumask_set_cpu(cpu, enable);
-	if (!mask)
-		return;
-
-	if (enable)
-		cpumask_set_cpu(cpu, mask);
-	else
-		cpumask_clear_cpu(cpu, mask);
-}
-#else
+# else	/* !CONFIG_DEBUG_PER_CPU_MAPS */
 static void __cpuinit numa_set_cpumask(int cpu, int enable)
 {
 	int node = early_cpu_to_node(cpu);
 	struct cpumask *mask;
 	int i;
 
+	if (node == NUMA_NO_NODE) {
+		/* early_cpu_to_node() already emits a warning and trace */
+		return;
+	}
 	for_each_online_node(i) {
 		unsigned long addr;
 
@@ -882,7 +732,6 @@ static void __cpuinit numa_set_cpumask(int cpu, int enable)
 			cpumask_clear_cpu(cpu, mask);
 	}
 }
-#endif /* CONFIG_NUMA_EMU */
 
 void __cpuinit numa_add_cpu(int cpu)
 {
@@ -893,39 +742,5 @@ void __cpuinit numa_remove_cpu(int cpu)
 {
 	numa_set_cpumask(cpu, 0);
 }
-
-int __cpu_to_node(int cpu)
-{
-	if (early_per_cpu_ptr(x86_cpu_to_node_map)) {
-		printk(KERN_WARNING
-			"cpu_to_node(%d): usage too early!\n", cpu);
-		dump_stack();
-		return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
-	}
-	return per_cpu(x86_cpu_to_node_map, cpu);
-}
-EXPORT_SYMBOL(__cpu_to_node);
-
-/*
- * Same function as cpu_to_node() but used if called before the
- * per_cpu areas are setup.
- */
-int early_cpu_to_node(int cpu)
-{
-	if (early_per_cpu_ptr(x86_cpu_to_node_map))
-		return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
-
-	if (!cpu_possible(cpu)) {
-		printk(KERN_WARNING
-			"early_cpu_to_node(%d): no per_cpu area!\n", cpu);
-		dump_stack();
-		return NUMA_NO_NODE;
-	}
-	return per_cpu(x86_cpu_to_node_map, cpu);
-}
-
-/*
- * --------- end of debug versions of the numa functions ---------
- */
-
-#endif /* CONFIG_DEBUG_PER_CPU_MAPS */
+# endif	/* !CONFIG_DEBUG_PER_CPU_MAPS */
+#endif	/* CONFIG_NUMA_EMU */
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index ae96e7b8051d..48651c6f657d 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -57,7 +57,7 @@ struct node_memory_chunk_s {
 static struct node_memory_chunk_s __initdata node_memory_chunk[MAXCHUNKS];
 
 static int __initdata num_memory_chunks; /* total number of memory chunks */
-static u8 __initdata apicid_to_pxm[MAX_APICID];
+static u8 __initdata apicid_to_pxm[MAX_LOCAL_APIC];
 
 int acpi_numa __initdata;
 
@@ -254,8 +254,8 @@ int __init get_memcfg_from_srat(void)
 	printk(KERN_DEBUG "Number of memory chunks in system = %d\n",
 			 num_memory_chunks);
 
-	for (i = 0; i < MAX_APICID; i++)
-		apicid_2_node[i] = pxm_to_node(apicid_to_pxm[i]);
+	for (i = 0; i < MAX_LOCAL_APIC; i++)
+		set_apicid_to_node(i, pxm_to_node(apicid_to_pxm[i]));
 
 	for (j = 0; j < num_memory_chunks; j++){
 		struct node_memory_chunk_s * chunk = &node_memory_chunk[j];
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 4c03e13da138..23498f8b09a2 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -79,7 +79,7 @@ static __init void bad_srat(void)
 	printk(KERN_ERR "SRAT: SRAT not used.\n");
 	acpi_numa = -1;
 	for (i = 0; i < MAX_LOCAL_APIC; i++)
-		apicid_to_node[i] = NUMA_NO_NODE;
+		set_apicid_to_node(i, NUMA_NO_NODE);
 	for (i = 0; i < MAX_NUMNODES; i++) {
 		nodes[i].start = nodes[i].end = 0;
 		nodes_add[i].start = nodes_add[i].end = 0;
@@ -138,7 +138,7 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
 		printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u skipped apicid that is too big\n", pxm, apic_id, node);
 		return;
 	}
-	apicid_to_node[apic_id] = node;
+	set_apicid_to_node(apic_id, node);
 	node_set(node, cpu_nodes_parsed);
 	acpi_numa = 1;
 	printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u\n",
@@ -178,7 +178,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
 		return;
 	}
 
-	apicid_to_node[apic_id] = node;
+	set_apicid_to_node(apic_id, node);
 	node_set(node, cpu_nodes_parsed);
 	acpi_numa = 1;
 	printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%02x -> Node %u\n",
@@ -523,7 +523,7 @@ void __init acpi_fake_nodes(const struct bootnode *fake_nodes, int num_nodes)
 		 * node, it must now point to the fake node ID.
 		 */
 		for (j = 0; j < MAX_LOCAL_APIC; j++)
-			if (apicid_to_node[j] == nid &&
+			if (__apicid_to_node[j] == nid &&
 			    fake_apicid_to_node[j] == NUMA_NO_NODE)
 				fake_apicid_to_node[j] = i;
 	}
@@ -534,13 +534,13 @@ void __init acpi_fake_nodes(const struct bootnode *fake_nodes, int num_nodes)
 	 * value.
 	 */
 	for (i = 0; i < MAX_LOCAL_APIC; i++)
-		if (apicid_to_node[i] != NUMA_NO_NODE &&
+		if (__apicid_to_node[i] != NUMA_NO_NODE &&
 		    fake_apicid_to_node[i] == NUMA_NO_NODE)
 			fake_apicid_to_node[i] = 0;
 
 	for (i = 0; i < num_nodes; i++)
 		__acpi_map_pxm_to_node(fake_node_to_pxm_map[i], i);
-	memcpy(apicid_to_node, fake_apicid_to_node, sizeof(apicid_to_node));
+	memcpy(__apicid_to_node, fake_apicid_to_node, sizeof(__apicid_to_node));
 
 	nodes_clear(nodes_parsed);
 	for (i = 0; i < num_nodes; i++)