diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5a29b792cb84542da0c4e9964d549b21cc9c41e6..d6218e6c9824163fd2c5a3f384128b68ba230686 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -133,7 +133,7 @@ config ARCH_HAS_CACHE_LINE_SIZE
 	def_bool y
 
 config HAVE_SETUP_PER_CPU_AREA
-	def_bool X86_64_SMP || (X86_SMP && !X86_VOYAGER)
+	def_bool y
 
 config HAVE_CPUMASK_OF_CPU_MAP
 	def_bool X86_64_SMP
diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h
index 26c6dad90479119f369aa5466464d15eb2b695c4..a7f3c75f8ad7cd9caa33f4965240dcf768ee481c 100644
--- a/arch/x86/include/asm/cpumask.h
+++ b/arch/x86/include/asm/cpumask.h
@@ -10,6 +10,8 @@ extern cpumask_var_t cpu_callout_mask;
 extern cpumask_var_t cpu_initialized_mask;
 extern cpumask_var_t cpu_sibling_setup_mask;
 
+extern void setup_cpu_local_masks(void);
+
 #else /* CONFIG_X86_32 */
 
 extern cpumask_t cpu_callin_map;
@@ -22,6 +24,8 @@ extern cpumask_t cpu_sibling_setup_map;
 #define cpu_initialized_mask	((struct cpumask *)&cpu_initialized)
 #define cpu_sibling_setup_mask	((struct cpumask *)&cpu_sibling_setup_map)
 
+static inline void setup_cpu_local_masks(void) { }
+
 #endif /* CONFIG_X86_32 */
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 48676b943b9210bde34a9022b22504d31b9911a8..befa20b4a68cc92da4fafaef5e0e0a2d30cb348b 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -394,14 +394,6 @@ union irq_stack_union {
 
 DECLARE_PER_CPU(union irq_stack_union, irq_stack_union);
 DECLARE_PER_CPU(char *, irq_stack_ptr);
-
-static inline void load_gs_base(int cpu)
-{
-	/* Memory clobbers used to order pda/percpu accesses */
-	mb();
-	wrmsrl(MSR_GS_BASE, (unsigned long)per_cpu(irq_stack_union.gs_base, cpu));
-	mb();
-}
 #endif
 
 extern void print_cpu_info(struct cpuinfo_x86 *);
@@ -778,7 +770,6 @@ extern struct desc_ptr		early_gdt_descr;
 extern void cpu_set_gdt(int);
 extern void switch_to_new_gdt(void);
 extern void cpu_init(void);
-extern void init_gdt(int cpu);
 
 static inline unsigned long get_debugctlmsr(void)
 {
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 10022ed3a4b6acdf99a518d04ff3e2d41de947fa..77cfb2cfb386d5b1a1727807b2a7c84ee8fc4c6c 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -74,6 +74,8 @@ static inline const struct cpumask *cpumask_of_node(int node)
 	return &node_to_cpumask_map[node];
 }
 
+static inline void setup_node_to_cpumask_map(void) { }
+
 #else /* CONFIG_X86_64 */
 
 /* Mappings between node number and cpus on that node. */
@@ -120,6 +122,8 @@ static inline cpumask_t node_to_cpumask(int node)
 
 #endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
 
+extern void setup_node_to_cpumask_map(void);
+
 /*
  * Replace default node_to_cpumask_ptr with optimized version
  * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)"
@@ -218,6 +222,8 @@ static inline int node_to_first_cpu(int node)
 	return first_cpu(cpu_online_map);
 }
 
+static inline void setup_node_to_cpumask_map(void) { }
+
 /*
  * Replace default node_to_cpumask_ptr with optimized version
  * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)"
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index a99437c965cc049eaac23685ad28ae4d5220eb57..37fa30bada17e980abf3371dadde2a03bf8e448f 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -28,7 +28,7 @@ CFLAGS_paravirt.o	:= $(nostackp)
 obj-y			:= process_$(BITS).o signal.o entry_$(BITS).o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
 obj-y			+= time_$(BITS).o ioport.o ldt.o dumpstack.o
-obj-y			+= setup.o i8259.o irqinit_$(BITS).o setup_percpu.o
+obj-y			+= setup.o i8259.o irqinit_$(BITS).o
 obj-$(CONFIG_X86_VISWS)	+= visws_quirks.o
 obj-$(CONFIG_X86_32)	+= probe_roms_32.o
 obj-$(CONFIG_X86_32)	+= sys_i386_32.o i386_ksyms_32.o
@@ -59,8 +59,8 @@ apm-y				:= apm_32.o
 obj-$(CONFIG_APM)		+= apm.o
 obj-$(CONFIG_X86_SMP)		+= smp.o
 obj-$(CONFIG_X86_SMP)		+= smpboot.o tsc_sync.o ipi.o
-obj-$(CONFIG_X86_32_SMP)	+= smpcommon.o
-obj-$(CONFIG_X86_64_SMP)	+= tsc_sync.o smpcommon.o
+obj-$(CONFIG_SMP)		+= setup_percpu.o
+obj-$(CONFIG_X86_64_SMP)	+= tsc_sync.o
 obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline_$(BITS).o
 obj-$(CONFIG_X86_MPPARSE)	+= mpparse.o
 obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o nmi.o
diff --git a/arch/x86/kernel/apic.c b/arch/x86/kernel/apic.c
index 1df341a528a1fbb9b239bf20cedb0e3f6ced86bc..c6f15647eba923e3ae909f770ada7c01485edb45 100644
--- a/arch/x86/kernel/apic.c
+++ b/arch/x86/kernel/apic.c
@@ -60,6 +60,24 @@
 # error SPURIOUS_APIC_VECTOR definition error
 #endif
 
+unsigned int num_processors;
+unsigned disabled_cpus __cpuinitdata;
+/* Processor that is doing the boot up */
+unsigned int boot_cpu_physical_apicid = -1U;
+EXPORT_SYMBOL(boot_cpu_physical_apicid);
+unsigned int max_physical_apicid;
+
+/* Bitmask of physically existing CPUs */
+physid_mask_t phys_cpu_present_map;
+
+/*
+ * Map cpu index to physical APIC ID
+ */
+DEFINE_EARLY_PER_CPU(u16, x86_cpu_to_apicid, BAD_APICID);
+DEFINE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid, BAD_APICID);
+EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
+EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
+
 #ifdef CONFIG_X86_32
 /*
  * Knob to control our willingness to enable the local APIC.
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 99904f288d6ac29d51ab060253b63f243e184b0c..652fdc9a757a22d61a8222f3ec54c5d1d62c71fb 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -52,6 +52,15 @@ cpumask_var_t cpu_initialized_mask;
 /* representing cpus for which sibling maps can be computed */
 cpumask_var_t cpu_sibling_setup_mask;
 
+/* correctly size the local cpu masks */
+void __init setup_cpu_local_masks(void)
+{
+	alloc_bootmem_cpumask_var(&cpu_initialized_mask);
+	alloc_bootmem_cpumask_var(&cpu_callin_mask);
+	alloc_bootmem_cpumask_var(&cpu_callout_mask);
+	alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask);
+}
+
 #else /* CONFIG_X86_32 */
 
 cpumask_t cpu_callin_map;
@@ -249,12 +258,17 @@ __u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata;
 void switch_to_new_gdt(void)
 {
 	struct desc_ptr gdt_descr;
+	int cpu = smp_processor_id();
 
-	gdt_descr.address = (long)get_cpu_gdt_table(smp_processor_id());
+	gdt_descr.address = (long)get_cpu_gdt_table(cpu);
 	gdt_descr.size = GDT_SIZE - 1;
 	load_gdt(&gdt_descr);
+	/* Reload the per-cpu base */
 #ifdef CONFIG_X86_32
-	asm("mov %0, %%fs" : : "r" (__KERNEL_PERCPU) : "memory");
+	loadsegment(fs, __KERNEL_PERCPU);
+#else
+	loadsegment(gs, 0);
+	wrmsrl(MSR_GS_BASE, (unsigned long)per_cpu(irq_stack_union.gs_base, cpu));
 #endif
 }
 
@@ -959,10 +973,6 @@ void __cpuinit cpu_init(void)
 	struct task_struct *me;
 	int i;
 
-	loadsegment(fs, 0);
-	loadsegment(gs, 0);
-	load_gs_base(cpu);
-
 #ifdef CONFIG_NUMA
 	if (cpu != 0 && percpu_read(node_number) == 0 &&
 	    cpu_to_node(cpu) != NUMA_NO_NODE)
@@ -984,6 +994,8 @@ void __cpuinit cpu_init(void)
 	 */
 
 	switch_to_new_gdt();
+	loadsegment(fs, 0);
+
 	load_idt((const struct desc_ptr *)&idt_descr);
 
 	memset(me->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8);
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index e553803cd2db87fa6edd78b5916034bb7ee34742..0d1e7ac439f41a2b7cceb22f3d23aa3358fb138f 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -15,6 +15,7 @@
 #include <asm/highmem.h>
 #include <asm/proto.h>
 #include <asm/cpumask.h>
+#include <asm/cpu.h>
 
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
 # define DBG(x...) printk(KERN_DEBUG x)
@@ -22,118 +23,36 @@
 # define DBG(x...)
 #endif
 
-/*
- * Could be inside CONFIG_HAVE_SETUP_PER_CPU_AREA with other stuff but
- * voyager wants cpu_number too.
- */
-#ifdef CONFIG_SMP
 DEFINE_PER_CPU(int, cpu_number);
 EXPORT_PER_CPU_SYMBOL(cpu_number);
-#endif
-
-#ifdef CONFIG_X86_LOCAL_APIC
-unsigned int num_processors;
-unsigned disabled_cpus __cpuinitdata;
-/* Processor that is doing the boot up */
-unsigned int boot_cpu_physical_apicid = -1U;
-EXPORT_SYMBOL(boot_cpu_physical_apicid);
-unsigned int max_physical_apicid;
-
-/* Bitmask of physically existing CPUs */
-physid_mask_t phys_cpu_present_map;
-#endif
-
-/*
- * Map cpu index to physical APIC ID
- */
-DEFINE_EARLY_PER_CPU(u16, x86_cpu_to_apicid, BAD_APICID);
-DEFINE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid, BAD_APICID);
-EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
-EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
-
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
-#define	X86_64_NUMA	1	/* (used later) */
-DEFINE_PER_CPU(int, node_number) = 0;
-EXPORT_PER_CPU_SYMBOL(node_number);
-
-/*
- * 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);
-
-/*
- * Which logical CPUs are on which nodes
- */
-cpumask_t *node_to_cpumask_map;
-EXPORT_SYMBOL(node_to_cpumask_map);
-
-/*
- * Setup node_to_cpumask_map
- */
-static void __init setup_node_to_cpumask_map(void);
 
+#ifdef CONFIG_X86_64
+#define BOOT_PERCPU_OFFSET ((unsigned long)__per_cpu_load)
 #else
-static inline void setup_node_to_cpumask_map(void) { }
+#define BOOT_PERCPU_OFFSET 0
 #endif
 
-#ifdef CONFIG_X86_64
-
-/* correctly size the local cpu masks */
-static void __init setup_cpu_local_masks(void)
-{
-	alloc_bootmem_cpumask_var(&cpu_initialized_mask);
-	alloc_bootmem_cpumask_var(&cpu_callin_mask);
-	alloc_bootmem_cpumask_var(&cpu_callout_mask);
-	alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask);
-}
-
-#else /* CONFIG_X86_32 */
-
-static inline void setup_cpu_local_masks(void)
-{
-}
+DEFINE_PER_CPU(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET;
+EXPORT_PER_CPU_SYMBOL(this_cpu_off);
 
-#endif /* CONFIG_X86_32 */
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = {
+	[0 ... NR_CPUS-1] = BOOT_PERCPU_OFFSET,
+};
+EXPORT_SYMBOL(__per_cpu_offset);
 
-#ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
-/*
- * Copy data used in early init routines from the initial arrays to the
- * per cpu data areas.  These arrays then become expendable and the
- * *_early_ptr's are zeroed indicating that the static arrays are gone.
- */
-static void __init setup_per_cpu_maps(void)
+static inline void setup_percpu_segment(int cpu)
 {
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		per_cpu(x86_cpu_to_apicid, cpu) =
-				early_per_cpu_map(x86_cpu_to_apicid, cpu);
-		per_cpu(x86_bios_cpu_apicid, cpu) =
-				early_per_cpu_map(x86_bios_cpu_apicid, cpu);
-#ifdef X86_64_NUMA
-		per_cpu(x86_cpu_to_node_map, cpu) =
-				early_per_cpu_map(x86_cpu_to_node_map, cpu);
-#endif
-	}
+#ifdef CONFIG_X86_32
+	struct desc_struct gdt;
 
-	/* indicate the early static arrays will soon be gone */
-	early_per_cpu_ptr(x86_cpu_to_apicid) = NULL;
-	early_per_cpu_ptr(x86_bios_cpu_apicid) = NULL;
-#ifdef X86_64_NUMA
-	early_per_cpu_ptr(x86_cpu_to_node_map) = NULL;
+	pack_descriptor(&gdt, per_cpu_offset(cpu), 0xFFFFF,
+			0x2 | DESCTYPE_S, 0x8);
+	gdt.s = 1;
+	write_gdt_entry(get_cpu_gdt_table(cpu),
+			GDT_ENTRY_PERCPU, &gdt, DESCTYPE_S);
 #endif
 }
 
-#ifdef CONFIG_X86_64
-unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = {
-	[0] = (unsigned long)__per_cpu_load,
-};
-#else
-unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
-#endif
-EXPORT_SYMBOL(__per_cpu_offset);
-
 /*
  * Great future plan:
  * Declare PDA itself and support (irqstack,tss,pgd) as per cpu data.
@@ -141,15 +60,12 @@ EXPORT_SYMBOL(__per_cpu_offset);
  */
 void __init setup_per_cpu_areas(void)
 {
-	ssize_t size, old_size;
+	ssize_t size;
 	char *ptr;
 	int cpu;
-	unsigned long align = 1;
 
 	/* Copy section for each CPU (we discard the original) */
-	old_size = PERCPU_ENOUGH_ROOM;
-	align = max_t(unsigned long, PAGE_SIZE, align);
-	size = roundup(old_size, align);
+	size = roundup(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
 
 	pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%d nr_node_ids:%d\n",
 		NR_CPUS, nr_cpumask_bits, nr_cpu_ids, nr_node_ids);
@@ -158,20 +74,17 @@ void __init setup_per_cpu_areas(void)
 
 	for_each_possible_cpu(cpu) {
 #ifndef CONFIG_NEED_MULTIPLE_NODES
-		ptr = __alloc_bootmem(size, align,
-				 __pa(MAX_DMA_ADDRESS));
+		ptr = alloc_bootmem_pages(size);
 #else
 		int node = early_cpu_to_node(cpu);
 		if (!node_online(node) || !NODE_DATA(node)) {
-			ptr = __alloc_bootmem(size, align,
-					 __pa(MAX_DMA_ADDRESS));
+			ptr = alloc_bootmem_pages(size);
 			pr_info("cpu %d has no node %d or node-local memory\n",
 				cpu, node);
 			pr_debug("per cpu data for cpu%d at %016lx\n",
 				 cpu, __pa(ptr));
 		} else {
-			ptr = __alloc_bootmem_node(NODE_DATA(node), size, align,
-							__pa(MAX_DMA_ADDRESS));
+			ptr = alloc_bootmem_pages_node(NODE_DATA(node), size);
 			pr_debug("per cpu data for cpu%d on node%d at %016lx\n",
 				cpu, node, __pa(ptr));
 		}
@@ -181,22 +94,47 @@ void __init setup_per_cpu_areas(void)
 		per_cpu_offset(cpu) = ptr - __per_cpu_start;
 		per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu);
 		per_cpu(cpu_number, cpu) = cpu;
+		setup_percpu_segment(cpu);
+		/*
+		 * Copy data used in early init routines from the
+		 * initial arrays to the per cpu data areas.  These
+		 * arrays then become expendable and the *_early_ptr's
+		 * are zeroed indicating that the static arrays are
+		 * gone.
+		 */
+#ifdef CONFIG_X86_LOCAL_APIC
+		per_cpu(x86_cpu_to_apicid, cpu) =
+			early_per_cpu_map(x86_cpu_to_apicid, cpu);
+		per_cpu(x86_bios_cpu_apicid, cpu) =
+			early_per_cpu_map(x86_bios_cpu_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;
+			per_cpu(irq_stack_union.irq_stack, cpu) +
+			IRQ_STACK_SIZE - 64;
+#ifdef CONFIG_NUMA
+		per_cpu(x86_cpu_to_node_map, cpu) =
+			early_per_cpu_map(x86_cpu_to_node_map, cpu);
+#endif
+#endif
 		/*
-		 * Up to this point, CPU0 has been using .data.init
-		 * area.  Reload %gs offset for CPU0.
+		 * Up to this point, the boot CPU has been using .data.init
+		 * area.  Reload any changed state for the boot CPU.
 		 */
-		if (cpu == 0)
-			load_gs_base(cpu);
-#endif
+		if (cpu == boot_cpu_id)
+			switch_to_new_gdt();
 
 		DBG("PERCPU: cpu %4d %p\n", cpu, ptr);
 	}
 
-	/* Setup percpu data maps */
-	setup_per_cpu_maps();
+	/* indicate the early static arrays will soon be gone */
+#ifdef CONFIG_X86_LOCAL_APIC
+	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)
+	early_per_cpu_ptr(x86_cpu_to_node_map) = NULL;
+#endif
 
 	/* Setup node to cpumask map */
 	setup_node_to_cpumask_map();
@@ -204,207 +142,3 @@ void __init setup_per_cpu_areas(void)
 	/* Setup cpu initialized, callin, callout masks */
 	setup_cpu_local_masks();
 }
-
-#endif
-
-#ifdef X86_64_NUMA
-
-/*
- * Allocate node_to_cpumask_map based on number of available nodes
- * Requires node_possible_map to be valid.
- *
- * Note: node_to_cpumask() is not valid until after this is done.
- * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.)
- */
-static void __init setup_node_to_cpumask_map(void)
-{
-	unsigned int node, num = 0;
-	cpumask_t *map;
-
-	/* setup nr_node_ids if not done yet */
-	if (nr_node_ids == MAX_NUMNODES) {
-		for_each_node_mask(node, node_possible_map)
-			num = node;
-		nr_node_ids = num + 1;
-	}
-
-	/* allocate the map */
-	map = alloc_bootmem_low(nr_node_ids * sizeof(cpumask_t));
-	DBG("node_to_cpumask_map at %p for %d nodes\n", map, nr_node_ids);
-
-	pr_debug("Node to cpumask map at %p for %d nodes\n",
-		 map, nr_node_ids);
-
-	/* node_to_cpumask() will now work */
-	node_to_cpumask_map = 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 || !per_cpu_offset(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)
-		per_cpu(node_number, cpu) = node;
-}
-
-void __cpuinit numa_clear_node(int cpu)
-{
-	numa_set_node(cpu, NUMA_NO_NODE);
-}
-
-#ifndef CONFIG_DEBUG_PER_CPU_MAPS
-
-void __cpuinit numa_add_cpu(int cpu)
-{
-	cpu_set(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
-}
-
-void __cpuinit numa_remove_cpu(int cpu)
-{
-	cpu_clear(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
-}
-
-#else /* CONFIG_DEBUG_PER_CPU_MAPS */
-
-/*
- * --------- debug versions of the numa functions ---------
- */
-static void __cpuinit numa_set_cpumask(int cpu, int enable)
-{
-	int node = early_cpu_to_node(cpu);
-	cpumask_t *mask;
-	char buf[64];
-
-	if (node_to_cpumask_map == NULL) {
-		printk(KERN_ERR "node_to_cpumask_map NULL\n");
-		dump_stack();
-		return;
-	}
-
-	mask = &node_to_cpumask_map[node];
-	if (enable)
-		cpu_set(cpu, *mask);
-	else
-		cpu_clear(cpu, *mask);
-
-	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);
-}
-
-void __cpuinit numa_add_cpu(int cpu)
-{
-	numa_set_cpumask(cpu, 1);
-}
-
-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 (!per_cpu_offset(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);
-}
-
-
-/* empty cpumask */
-static const cpumask_t cpu_mask_none;
-
-/*
- * Returns a pointer to the bitmask of CPUs on Node 'node'.
- */
-const cpumask_t *cpumask_of_node(int node)
-{
-	if (node_to_cpumask_map == NULL) {
-		printk(KERN_WARNING
-			"cpumask_of_node(%d): no node_to_cpumask_map!\n",
-			node);
-		dump_stack();
-		return (const cpumask_t *)&cpu_online_map;
-	}
-	if (node >= nr_node_ids) {
-		printk(KERN_WARNING
-			"cpumask_of_node(%d): node > nr_node_ids(%d)\n",
-			node, nr_node_ids);
-		dump_stack();
-		return &cpu_mask_none;
-	}
-	return &node_to_cpumask_map[node];
-}
-EXPORT_SYMBOL(cpumask_of_node);
-
-/*
- * Returns a bitmask of CPUs on Node 'node'.
- *
- * Side note: this function creates the returned cpumask on the stack
- * so with a high NR_CPUS count, excessive stack space is used.  The
- * node_to_cpumask_ptr function should be used whenever possible.
- */
-cpumask_t node_to_cpumask(int node)
-{
-	if (node_to_cpumask_map == NULL) {
-		printk(KERN_WARNING
-			"node_to_cpumask(%d): no node_to_cpumask_map!\n", node);
-		dump_stack();
-		return cpu_online_map;
-	}
-	if (node >= nr_node_ids) {
-		printk(KERN_WARNING
-			"node_to_cpumask(%d): node > nr_node_ids(%d)\n",
-			node, nr_node_ids);
-		dump_stack();
-		return cpu_mask_none;
-	}
-	return node_to_cpumask_map[node];
-}
-EXPORT_SYMBOL(node_to_cpumask);
-
-/*
- * --------- end of debug versions of the numa functions ---------
- */
-
-#endif /* CONFIG_DEBUG_PER_CPU_MAPS */
-
-#endif /* X86_64_NUMA */
-
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index def770b57b5a0309af4c8dff32dfe34555013bd3..f9dbcff4354646c73d850f539e1287c66d355020 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -793,7 +793,6 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu)
 do_rest:
 	per_cpu(current_task, cpu) = c_idle.idle;
 #ifdef CONFIG_X86_32
-	init_gdt(cpu);
 	/* Stack for startup_32 can be just as for start_secondary onwards */
 	irq_ctx_init(cpu);
 #else
@@ -1186,9 +1185,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 void __init native_smp_prepare_boot_cpu(void)
 {
 	int me = smp_processor_id();
-#ifdef CONFIG_X86_32
-	init_gdt(me);
-#endif
 	switch_to_new_gdt();
 	/* already set me in cpu_online_mask in boot_cpu_init() */
 	cpumask_set_cpu(me, cpu_callout_mask);
diff --git a/arch/x86/kernel/smpcommon.c b/arch/x86/kernel/smpcommon.c
deleted file mode 100644
index add36b4e37c92d00eabe22f25ab0148febfcb2e2..0000000000000000000000000000000000000000
--- a/arch/x86/kernel/smpcommon.c
+++ /dev/null
@@ -1,32 +0,0 @@
-/*
- * SMP stuff which is common to all sub-architectures.
- */
-#include <linux/module.h>
-#include <asm/smp.h>
-#include <asm/sections.h>
-
-#ifdef CONFIG_X86_64
-DEFINE_PER_CPU(unsigned long, this_cpu_off) = (unsigned long)__per_cpu_load;
-#else
-DEFINE_PER_CPU(unsigned long, this_cpu_off);
-#endif
-EXPORT_PER_CPU_SYMBOL(this_cpu_off);
-
-#ifdef CONFIG_X86_32
-/*
- * Initialize the CPU's GDT.  This is either the boot CPU doing itself
- * (still using the master per-cpu area), or a CPU doing it for a
- * secondary which will soon come up.
- */
-__cpuinit void init_gdt(int cpu)
-{
-	struct desc_struct gdt;
-
-	pack_descriptor(&gdt, __per_cpu_offset[cpu], 0xFFFFF,
-			0x2 | DESCTYPE_S, 0x8);
-	gdt.s = 1;
-
-	write_gdt_entry(get_cpu_gdt_table(cpu),
-			GDT_ENTRY_PERCPU, &gdt, DESCTYPE_S);
-}
-#endif
diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c
index 96f15b09a4c59143b1cbca1cbda5b422f27a639a..331cd6d5648371de3080576d4a6f3cce8b9030d3 100644
--- a/arch/x86/mach-voyager/voyager_smp.c
+++ b/arch/x86/mach-voyager/voyager_smp.c
@@ -530,8 +530,6 @@ static void __init do_boot_cpu(__u8 cpu)
 	/* init_tasks (in sched.c) is indexed logically */
 	stack_start.sp = (void *)idle->thread.sp;
 
-	init_gdt(cpu);
-	per_cpu(this_cpu_off, cpu) = __per_cpu_offset[cpu];
 	per_cpu(current_task, cpu) = idle;
 	early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
 	irq_ctx_init(cpu);
@@ -1748,8 +1746,6 @@ static void __init voyager_smp_prepare_cpus(unsigned int max_cpus)
 
 static void __cpuinit voyager_smp_prepare_boot_cpu(void)
 {
-	init_gdt(smp_processor_id());
-	per_cpu(this_cpu_off, cpu) = __per_cpu_offset[cpu];
 	switch_to_new_gdt();
 
 	cpu_set(smp_processor_id(), cpu_online_map);
@@ -1782,7 +1778,6 @@ static void __init voyager_smp_cpus_done(unsigned int max_cpus)
 void __init smp_setup_processor_id(void)
 {
 	current_thread_info()->cpu = hard_smp_processor_id();
-	percpu_write(cpu_number, hard_smp_processor_id());
 }
 
 static void voyager_send_call_func(cpumask_t callmask)
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 71a14f89f89e7367c72f2de85da6708acc83c069..08d140fbc31b760b419c721e6c174b6d679e4f79 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -20,6 +20,12 @@
 #include <asm/acpi.h>
 #include <asm/k8.h>
 
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+# define DBG(x...) printk(KERN_DEBUG x)
+#else
+# define DBG(x...)
+#endif
+
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
 
@@ -33,6 +39,21 @@ int numa_off __initdata;
 static unsigned long __initdata nodemap_addr;
 static unsigned long __initdata nodemap_size;
 
+DEFINE_PER_CPU(int, node_number) = 0;
+EXPORT_PER_CPU_SYMBOL(node_number);
+
+/*
+ * 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);
+
+/*
+ * Which logical CPUs are on which nodes
+ */
+cpumask_t *node_to_cpumask_map;
+EXPORT_SYMBOL(node_to_cpumask_map);
+
 /*
  * Given a shift value, try to populate memnodemap[]
  * Returns :
@@ -640,3 +661,199 @@ void __init init_cpu_to_node(void)
 #endif
 
 
+/*
+ * Allocate node_to_cpumask_map based on number of available nodes
+ * Requires node_possible_map to be valid.
+ *
+ * Note: node_to_cpumask() is not valid until after this is done.
+ * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.)
+ */
+void __init setup_node_to_cpumask_map(void)
+{
+	unsigned int node, num = 0;
+	cpumask_t *map;
+
+	/* setup nr_node_ids if not done yet */
+	if (nr_node_ids == MAX_NUMNODES) {
+		for_each_node_mask(node, node_possible_map)
+			num = node;
+		nr_node_ids = num + 1;
+	}
+
+	/* allocate the map */
+	map = alloc_bootmem_low(nr_node_ids * sizeof(cpumask_t));
+	DBG("node_to_cpumask_map at %p for %d nodes\n", map, nr_node_ids);
+
+	pr_debug("Node to cpumask map at %p for %d nodes\n",
+		 map, nr_node_ids);
+
+	/* node_to_cpumask() will now work */
+	node_to_cpumask_map = 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 || !per_cpu_offset(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)
+		per_cpu(node_number, cpu) = node;
+}
+
+void __cpuinit numa_clear_node(int cpu)
+{
+	numa_set_node(cpu, NUMA_NO_NODE);
+}
+
+#ifndef CONFIG_DEBUG_PER_CPU_MAPS
+
+void __cpuinit numa_add_cpu(int cpu)
+{
+	cpu_set(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
+}
+
+void __cpuinit numa_remove_cpu(int cpu)
+{
+	cpu_clear(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
+}
+
+#else /* CONFIG_DEBUG_PER_CPU_MAPS */
+
+/*
+ * --------- debug versions of the numa functions ---------
+ */
+static void __cpuinit numa_set_cpumask(int cpu, int enable)
+{
+	int node = early_cpu_to_node(cpu);
+	cpumask_t *mask;
+	char buf[64];
+
+	if (node_to_cpumask_map == NULL) {
+		printk(KERN_ERR "node_to_cpumask_map NULL\n");
+		dump_stack();
+		return;
+	}
+
+	mask = &node_to_cpumask_map[node];
+	if (enable)
+		cpu_set(cpu, *mask);
+	else
+		cpu_clear(cpu, *mask);
+
+	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);
+}
+
+void __cpuinit numa_add_cpu(int cpu)
+{
+	numa_set_cpumask(cpu, 1);
+}
+
+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 (!per_cpu_offset(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);
+}
+
+
+/* empty cpumask */
+static const cpumask_t cpu_mask_none;
+
+/*
+ * Returns a pointer to the bitmask of CPUs on Node 'node'.
+ */
+const cpumask_t *cpumask_of_node(int node)
+{
+	if (node_to_cpumask_map == NULL) {
+		printk(KERN_WARNING
+			"cpumask_of_node(%d): no node_to_cpumask_map!\n",
+			node);
+		dump_stack();
+		return (const cpumask_t *)&cpu_online_map;
+	}
+	if (node >= nr_node_ids) {
+		printk(KERN_WARNING
+			"cpumask_of_node(%d): node > nr_node_ids(%d)\n",
+			node, nr_node_ids);
+		dump_stack();
+		return &cpu_mask_none;
+	}
+	return &node_to_cpumask_map[node];
+}
+EXPORT_SYMBOL(cpumask_of_node);
+
+/*
+ * Returns a bitmask of CPUs on Node 'node'.
+ *
+ * Side note: this function creates the returned cpumask on the stack
+ * so with a high NR_CPUS count, excessive stack space is used.  The
+ * node_to_cpumask_ptr function should be used whenever possible.
+ */
+cpumask_t node_to_cpumask(int node)
+{
+	if (node_to_cpumask_map == NULL) {
+		printk(KERN_WARNING
+			"node_to_cpumask(%d): no node_to_cpumask_map!\n", node);
+		dump_stack();
+		return cpu_online_map;
+	}
+	if (node >= nr_node_ids) {
+		printk(KERN_WARNING
+			"node_to_cpumask(%d): node > nr_node_ids(%d)\n",
+			node, nr_node_ids);
+		dump_stack();
+		return cpu_mask_none;
+	}
+	return node_to_cpumask_map[node];
+}
+EXPORT_SYMBOL(node_to_cpumask);
+
+/*
+ * --------- end of debug versions of the numa functions ---------
+ */
+
+#endif /* CONFIG_DEBUG_PER_CPU_MAPS */
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 72c2eb9b64cd356722ff8f581d69b4901bb1bf40..7735e3dd359c5351ef33ef818368dff5ac16f6d8 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -281,7 +281,6 @@ static int __cpuinit xen_cpu_up(unsigned int cpu)
 
 	per_cpu(current_task, cpu) = idle;
 #ifdef CONFIG_X86_32
-	init_gdt(cpu);
 	irq_ctx_init(cpu);
 #else
 	clear_tsk_thread_flag(idle, TIF_FORK);