Merge branch 'cpus4096' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-x86 into cpus4096

38 files changed, 246 insertions, 336 deletions

diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h
index a7f3c75f8ad7..61c852fa346b 100644
--- a/arch/x86/include/asm/cpumask.h
+++ b/arch/x86/include/asm/cpumask.h
@@ -3,8 +3,6 @@
 #ifndef __ASSEMBLY__
 #include <linux/cpumask.h>
 
-#ifdef CONFIG_X86_64
-
 extern cpumask_var_t cpu_callin_mask;
 extern cpumask_var_t cpu_callout_mask;
 extern cpumask_var_t cpu_initialized_mask;
@@ -12,21 +10,5 @@ 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;
-extern cpumask_t cpu_callout_map;
-extern cpumask_t cpu_initialized;
-extern cpumask_t cpu_sibling_setup_map;
-
-#define cpu_callin_mask		((struct cpumask *)&cpu_callin_map)
-#define cpu_callout_mask	((struct cpumask *)&cpu_callout_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__ */
 #endif /* _ASM_X86_CPUMASK_H */
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index a977de23cb4d..93c8dc318111 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -109,11 +109,6 @@ static inline int __pcibus_to_node(const struct pci_bus *bus)
 	return sd->node;
 }
 
-static inline cpumask_t __pcibus_to_cpumask(struct pci_bus *bus)
-{
-	return node_to_cpumask(__pcibus_to_node(bus));
-}
-
 static inline const struct cpumask *
 cpumask_of_pcibus(const struct pci_bus *bus)
 {
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 76139506c3e4..d794d9483c56 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -94,7 +94,7 @@ struct cpuinfo_x86 {
 	unsigned long		loops_per_jiffy;
 #ifdef CONFIG_SMP
 	/* cpus sharing the last level cache: */
-	cpumask_t		llc_shared_map;
+	cpumask_var_t		llc_shared_map;
 #endif
 	/* cpuid returned max cores value: */
 	u16			 x86_max_cores;
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 47d0e21f2b9e..19e0d88b966d 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -21,19 +21,19 @@
 extern int smp_num_siblings;
 extern unsigned int num_processors;
 
-DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
-DECLARE_PER_CPU(cpumask_t, cpu_core_map);
+DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map);
+DECLARE_PER_CPU(cpumask_var_t, cpu_core_map);
 DECLARE_PER_CPU(u16, cpu_llc_id);
 DECLARE_PER_CPU(int, cpu_number);
 
 static inline struct cpumask *cpu_sibling_mask(int cpu)
 {
-	return &per_cpu(cpu_sibling_map, cpu);
+	return per_cpu(cpu_sibling_map, cpu);
 }
 
 static inline struct cpumask *cpu_core_mask(int cpu)
 {
-	return &per_cpu(cpu_core_map, cpu);
+	return per_cpu(cpu_core_map, cpu);
 }
 
 DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);
@@ -121,9 +121,10 @@ static inline void arch_send_call_function_single_ipi(int cpu)
 	smp_ops.send_call_func_single_ipi(cpu);
 }
 
-static inline void arch_send_call_function_ipi(cpumask_t mask)
+#define arch_send_call_function_ipi_mask arch_send_call_function_ipi_mask
+static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
-	smp_ops.send_call_func_ipi(&mask);
+	smp_ops.send_call_func_ipi(mask);
 }
 
 void cpu_disable_common(void);
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 77cfb2cfb386..e3f4198371a9 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -44,9 +44,6 @@
 
 #ifdef CONFIG_X86_32
 
-/* Mappings between node number and cpus on that node. */
-extern cpumask_t node_to_cpumask_map[];
-
 /* Mappings between logical cpu number and node number */
 extern int cpu_to_node_map[];
 
@@ -57,30 +54,8 @@ static inline int cpu_to_node(int cpu)
 }
 #define early_cpu_to_node(cpu)	cpu_to_node(cpu)
 
-/* 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
- * cpumask_of_node function should be used whenever possible.
- */
-static inline cpumask_t node_to_cpumask(int node)
-{
-	return node_to_cpumask_map[node];
-}
-
-/* Returns a bitmask of CPUs on Node 'node'. */
-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. */
-extern cpumask_t *node_to_cpumask_map;
-
 /* Mappings between logical cpu number and node number */
 DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);
 
@@ -91,8 +66,6 @@ DECLARE_PER_CPU(int, node_number);
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
 extern int cpu_to_node(int cpu);
 extern int early_cpu_to_node(int cpu);
-extern const cpumask_t *cpumask_of_node(int node);
-extern cpumask_t node_to_cpumask(int node);
 
 #else	/* !CONFIG_DEBUG_PER_CPU_MAPS */
 
@@ -108,42 +81,32 @@ static inline int early_cpu_to_node(int cpu)
 	return early_per_cpu(x86_cpu_to_node_map, cpu);
 }
 
-/* Returns a pointer to the cpumask of CPUs on Node 'node'. */
-static inline const cpumask_t *cpumask_of_node(int node)
-{
-	return &node_to_cpumask_map[node];
-}
+#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
+
+#endif /* CONFIG_X86_64 */
 
-/* Returns a bitmask of CPUs on Node 'node'. */
-static inline cpumask_t node_to_cpumask(int node)
+/* Mappings between node number and cpus on that node. */
+extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+extern const struct cpumask *cpumask_of_node(int node);
+#else
+/* Returns a pointer to the cpumask of CPUs on Node 'node'. */
+static inline const struct cpumask *cpumask_of_node(int node)
 {
 	return node_to_cpumask_map[node];
 }
-
-#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
+#endif
 
 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)"
- */
-#define node_to_cpumask_ptr(v, node)		\
-		const cpumask_t *v = cpumask_of_node(node)
-
-#define node_to_cpumask_ptr_next(v, node)	\
-			   v = cpumask_of_node(node)
-
-#endif /* CONFIG_X86_64 */
-
-/*
  * Returns the number of the node containing Node 'node'. This
  * architecture is flat, so it is a pretty simple function!
  */
 #define parent_node(node) (node)
 
 #define pcibus_to_node(bus) __pcibus_to_node(bus)
-#define pcibus_to_cpumask(bus) __pcibus_to_cpumask(bus)
 
 #ifdef CONFIG_X86_32
 extern unsigned long node_start_pfn[];
@@ -209,30 +172,17 @@ static inline int early_cpu_to_node(int cpu)
 	return 0;
 }
 
-static inline const cpumask_t *cpumask_of_node(int node)
-{
-	return &cpu_online_map;
-}
-static inline cpumask_t node_to_cpumask(int node)
+static inline const struct cpumask *cpumask_of_node(int node)
 {
-	return cpu_online_map;
+	return cpu_online_mask;
 }
 static inline int node_to_first_cpu(int node)
 {
-	return first_cpu(cpu_online_map);
+	return cpumask_first(cpu_online_mask);
 }
 
 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)"
- */
-#define node_to_cpumask_ptr(v, node)		\
-		const cpumask_t *v = cpumask_of_node(node)
-
-#define node_to_cpumask_ptr_next(v, node)	\
-			   v = cpumask_of_node(node)
 #endif
 
 #include <asm-generic/topology.h>
@@ -245,16 +195,13 @@ static inline int node_to_first_cpu(int node)
 }
 #endif
 
-extern cpumask_t cpu_coregroup_map(int cpu);
 extern const struct cpumask *cpu_coregroup_mask(int cpu);
 
 #ifdef ENABLE_TOPO_DEFINES
 #define topology_physical_package_id(cpu)	(cpu_data(cpu).phys_proc_id)
 #define topology_core_id(cpu)			(cpu_data(cpu).cpu_core_id)
-#define topology_core_siblings(cpu)		(per_cpu(cpu_core_map, cpu))
-#define topology_thread_siblings(cpu)		(per_cpu(cpu_sibling_map, cpu))
-#define topology_core_cpumask(cpu)		(&per_cpu(cpu_core_map, cpu))
-#define topology_thread_cpumask(cpu)		(&per_cpu(cpu_sibling_map, cpu))
+#define topology_core_cpumask(cpu)		(per_cpu(cpu_core_map, cpu))
+#define topology_thread_cpumask(cpu)		(per_cpu(cpu_sibling_map, cpu))
 
 /* indicates that pointers to the topology cpumask_t maps are valid */
 #define arch_provides_topology_pointers		yes
@@ -268,7 +215,7 @@ struct pci_bus;
 void set_pci_bus_resources_arch_default(struct pci_bus *b);
 
 #ifdef CONFIG_SMP
-#define mc_capable()	(cpus_weight(per_cpu(cpu_core_map, 0)) != nr_cpu_ids)
+#define mc_capable()	(cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids)
 #define smt_capable()			(smp_num_siblings > 1)
 #endif
 
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index d806ecaa948f..676cdac385c0 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -26,12 +26,12 @@ static int bigsmp_apic_id_registered(void)
 	return 1;
 }
 
-static const cpumask_t *bigsmp_target_cpus(void)
+static const struct cpumask *bigsmp_target_cpus(void)
 {
 #ifdef CONFIG_SMP
-	return &cpu_online_map;
+	return cpu_online_mask;
 #else
-	return &cpumask_of_cpu(0);
+	return cpumask_of(0);
 #endif
 }
 
@@ -118,9 +118,9 @@ static int bigsmp_check_phys_apicid_present(int boot_cpu_physical_apicid)
 }
 
 /* As we are using single CPU as destination, pick only one CPU here */
-static unsigned int bigsmp_cpu_mask_to_apicid(const cpumask_t *cpumask)
+static unsigned int bigsmp_cpu_mask_to_apicid(const struct cpumask *cpumask)
 {
-	return bigsmp_cpu_to_logical_apicid(first_cpu(*cpumask));
+	return bigsmp_cpu_to_logical_apicid(cpumask_first(cpumask));
 }
 
 static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
@@ -188,10 +188,10 @@ static const struct dmi_system_id bigsmp_dmi_table[] = {
 	{ } /* NULL entry stops DMI scanning */
 };
 
-static void bigsmp_vector_allocation_domain(int cpu, cpumask_t *retmask)
+static void bigsmp_vector_allocation_domain(int cpu, struct cpumask *retmask)
 {
-	cpus_clear(*retmask);
-	cpu_set(cpu, *retmask);
+	cpumask_clear(retmask);
+	cpumask_set_cpu(cpu, retmask);
 }
 
 static int probe_bigsmp(void)
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
index 19588f2770ee..1c11b819f245 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/arch/x86/kernel/apic/es7000_32.c
@@ -410,7 +410,7 @@ static void es7000_enable_apic_mode(void)
 		WARN(1, "Command failed, status = %x\n", mip_status);
 }
 
-static void es7000_vector_allocation_domain(int cpu, cpumask_t *retmask)
+static void es7000_vector_allocation_domain(int cpu, struct cpumask *retmask)
 {
 	/* Careful. Some cpus do not strictly honor the set of cpus
 	 * specified in the interrupt destination when using lowest
@@ -420,7 +420,8 @@ static void es7000_vector_allocation_domain(int cpu, cpumask_t *retmask)
 	 * deliver interrupts to the wrong hyperthread when only one
 	 * hyperthread was specified in the interrupt desitination.
 	 */
-	*retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } };
+	cpumask_clear(retmask);
+	cpumask_bits(retmask)[0] = APIC_ALL_CPUS;
 }
 
 
@@ -455,14 +456,14 @@ static int es7000_apic_id_registered(void)
 	return 1;
 }
 
-static const cpumask_t *target_cpus_cluster(void)
+static const struct cpumask *target_cpus_cluster(void)
 {
-	return &CPU_MASK_ALL;
+	return cpu_all_mask;
 }
 
-static const cpumask_t *es7000_target_cpus(void)
+static const struct cpumask *es7000_target_cpus(void)
 {
-	return &cpumask_of_cpu(smp_processor_id());
+	return cpumask_of(smp_processor_id());
 }
 
 static unsigned long
@@ -517,7 +518,7 @@ static void es7000_setup_apic_routing(void)
 	  "Enabling APIC mode:  %s. Using %d I/O APICs, target cpus %lx\n",
 		(apic_version[apic] == 0x14) ?
 			"Physical Cluster" : "Logical Cluster",
-		nr_ioapics, cpus_addr(*es7000_target_cpus())[0]);
+		nr_ioapics, cpumask_bits(es7000_target_cpus())[0]);
 }
 
 static int es7000_apicid_to_node(int logical_apicid)
@@ -572,7 +573,7 @@ static int es7000_check_phys_apicid_present(int cpu_physical_apicid)
 	return 1;
 }
 
-static unsigned int es7000_cpu_mask_to_apicid(const cpumask_t *cpumask)
+static unsigned int es7000_cpu_mask_to_apicid(const struct cpumask *cpumask)
 {
 	unsigned int round = 0;
 	int cpu, uninitialized_var(apicid);
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
index bdfad80c3cf1..d6bd62407152 100644
--- a/arch/x86/kernel/apic/nmi.c
+++ b/arch/x86/kernel/apic/nmi.c
@@ -39,7 +39,7 @@
 int unknown_nmi_panic;
 int nmi_watchdog_enabled;
 
-static cpumask_t backtrace_mask = CPU_MASK_NONE;
+static cpumask_var_t backtrace_mask;
 
 /* nmi_active:
  * >0: the lapic NMI watchdog is active, but can be disabled
@@ -138,6 +138,7 @@ int __init check_nmi_watchdog(void)
 	if (!prev_nmi_count)
 		goto error;
 
+	alloc_cpumask_var(&backtrace_mask, GFP_KERNEL);
 	printk(KERN_INFO "Testing NMI watchdog ... ");
 
 #ifdef CONFIG_SMP
@@ -413,14 +414,14 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
 		touched = 1;
 	}
 
-	if (cpu_isset(cpu, backtrace_mask)) {
+	if (cpumask_test_cpu(cpu, backtrace_mask)) {
 		static DEFINE_SPINLOCK(lock);	/* Serialise the printks */
 
 		spin_lock(&lock);
 		printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
 		dump_stack();
 		spin_unlock(&lock);
-		cpu_clear(cpu, backtrace_mask);
+		cpumask_clear_cpu(cpu, backtrace_mask);
 	}
 
 	/* Could check oops_in_progress here too, but it's safer not to */
@@ -554,10 +555,10 @@ void __trigger_all_cpu_backtrace(void)
 {
 	int i;
 
-	backtrace_mask = cpu_online_map;
+	cpumask_copy(backtrace_mask, cpu_online_mask);
 	/* Wait for up to 10 seconds for all CPUs to do the backtrace */
 	for (i = 0; i < 10 * 1000; i++) {
-		if (cpus_empty(backtrace_mask))
+		if (cpumask_empty(backtrace_mask))
 			break;
 		mdelay(1);
 	}
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index ba2fc6465534..533e59c6fc82 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -334,9 +334,9 @@ static inline void numaq_smp_callin_clear_local_apic(void)
 	clear_local_APIC();
 }
 
-static inline const cpumask_t *numaq_target_cpus(void)
+static inline const struct cpumask *numaq_target_cpus(void)
 {
-	return &CPU_MASK_ALL;
+	return cpu_all_mask;
 }
 
 static inline unsigned long
@@ -427,7 +427,7 @@ static inline int numaq_check_phys_apicid_present(int boot_cpu_physical_apicid)
  * We use physical apicids here, not logical, so just return the default
  * physical broadcast to stop people from breaking us
  */
-static inline unsigned int numaq_cpu_mask_to_apicid(const cpumask_t *cpumask)
+static unsigned int numaq_cpu_mask_to_apicid(const struct cpumask *cpumask)
 {
 	return 0x0F;
 }
@@ -462,7 +462,7 @@ static int probe_numaq(void)
 	return found_numaq;
 }
 
-static void numaq_vector_allocation_domain(int cpu, cpumask_t *retmask)
+static void numaq_vector_allocation_domain(int cpu, struct cpumask *retmask)
 {
 	/* Careful. Some cpus do not strictly honor the set of cpus
 	 * specified in the interrupt destination when using lowest
@@ -472,7 +472,8 @@ static void numaq_vector_allocation_domain(int cpu, cpumask_t *retmask)
 	 * deliver interrupts to the wrong hyperthread when only one
 	 * hyperthread was specified in the interrupt desitination.
 	 */
-	*retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } };
+	cpumask_clear(retmask);
+	cpumask_bits(retmask)[0] = APIC_ALL_CPUS;
 }
 
 static void numaq_setup_portio_remap(void)
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 141c99a1c264..01eda2ac65e4 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -83,7 +83,8 @@ static void default_vector_allocation_domain(int cpu, struct cpumask *retmask)
 	 * deliver interrupts to the wrong hyperthread when only one
 	 * hyperthread was specified in the interrupt desitination.
 	 */
-	*retmask = (cpumask_t) { { [0] = APIC_ALL_CPUS } };
+	cpumask_clear(retmask);
+	cpumask_bits(retmask)[0] = APIC_ALL_CPUS;
 }
 
 /* should be called last. */
diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c
index aac52fa873ff..9cfe1f415d81 100644
--- a/arch/x86/kernel/apic/summit_32.c
+++ b/arch/x86/kernel/apic/summit_32.c
@@ -53,23 +53,19 @@ static unsigned summit_get_apic_id(unsigned long x)
 	return (x >> 24) & 0xFF;
 }
 
-static inline void summit_send_IPI_mask(const cpumask_t *mask, int vector)
+static inline void summit_send_IPI_mask(const struct cpumask *mask, int vector)
 {
 	default_send_IPI_mask_sequence_logical(mask, vector);
 }
 
 static void summit_send_IPI_allbutself(int vector)
 {
-	cpumask_t mask = cpu_online_map;
-	cpu_clear(smp_processor_id(), mask);
-
-	if (!cpus_empty(mask))
-		summit_send_IPI_mask(&mask, vector);
+	default_send_IPI_mask_allbutself_logical(cpu_online_mask, vector);
 }
 
 static void summit_send_IPI_all(int vector)
 {
-	summit_send_IPI_mask(&cpu_online_map, vector);
+	summit_send_IPI_mask(cpu_online_mask, vector);
 }
 
 #include <asm/tsc.h>
@@ -186,13 +182,13 @@ static inline int is_WPEG(struct rio_detail *rio){
 
 #define SUMMIT_APIC_DFR_VALUE	(APIC_DFR_CLUSTER)
 
-static const cpumask_t *summit_target_cpus(void)
+static const struct cpumask *summit_target_cpus(void)
 {
 	/* CPU_MASK_ALL (0xff) has undefined behaviour with
 	 * dest_LowestPrio mode logical clustered apic interrupt routing
 	 * Just start on cpu 0.  IRQ balancing will spread load
 	 */
-	return &cpumask_of_cpu(0);
+	return cpumask_of(0);
 }
 
 static unsigned long summit_check_apicid_used(physid_mask_t bitmap, int apicid)
@@ -289,7 +285,7 @@ static int summit_check_phys_apicid_present(int boot_cpu_physical_apicid)
 	return 1;
 }
 
-static unsigned int summit_cpu_mask_to_apicid(const cpumask_t *cpumask)
+static unsigned int summit_cpu_mask_to_apicid(const struct cpumask *cpumask)
 {
 	unsigned int round = 0;
 	int cpu, apicid = 0;
@@ -346,7 +342,7 @@ static int probe_summit(void)
 	return 0;
 }
 
-static void summit_vector_allocation_domain(int cpu, cpumask_t *retmask)
+static void summit_vector_allocation_domain(int cpu, struct cpumask *retmask)
 {
 	/* Careful. Some cpus do not strictly honor the set of cpus
 	 * specified in the interrupt destination when using lowest
@@ -356,7 +352,8 @@ static void summit_vector_allocation_domain(int cpu, cpumask_t *retmask)
 	 * deliver interrupts to the wrong hyperthread when only one
 	 * hyperthread was specified in the interrupt desitination.
 	 */
-	*retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } };
+	cpumask_clear(retmask);
+	cpumask_bits(retmask)[0] = APIC_ALL_CPUS;
 }
 
 #ifdef CONFIG_X86_SUMMIT_NUMA
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 826d5c876278..82f6cc045ad0 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -41,8 +41,6 @@
 
 #include "cpu.h"
 
-#ifdef CONFIG_X86_64
-
 /* all of these masks are initialized in setup_cpu_local_masks() */
 cpumask_var_t cpu_callin_mask;
 cpumask_var_t cpu_callout_mask;
@@ -60,16 +58,6 @@ void __init setup_cpu_local_masks(void)
 	alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask);
 }
 
-#else /* CONFIG_X86_32 */
-
-cpumask_t cpu_callin_map;
-cpumask_t cpu_callout_map;
-cpumask_t cpu_initialized;
-cpumask_t cpu_sibling_setup_map;
-
-#endif /* CONFIG_X86_32 */
-
-
 static struct cpu_dev *this_cpu __cpuinitdata;
 
 DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
index 3178c3acd97e..d8341d17c189 100644
--- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
+++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
@@ -203,7 +203,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy)
 	unsigned int i;
 
 #ifdef CONFIG_SMP
-	cpumask_copy(policy->cpus, &per_cpu(cpu_sibling_map, policy->cpu));
+	cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
 #endif
 
 	/* Errata workaround */
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 6428aa17b40e..e8fd76f98883 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -56,7 +56,10 @@ static DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data);
 static int cpu_family = CPU_OPTERON;
 
 #ifndef CONFIG_SMP
-DEFINE_PER_CPU(cpumask_t, cpu_core_map);
+static inline const struct cpumask *cpu_core_mask(int cpu)
+{
+	return cpumask_of(0);
+}
 #endif
 
 /* Return a frequency in MHz, given an input fid */
@@ -654,7 +657,7 @@ static int fill_powernow_table(struct powernow_k8_data *data, struct pst_s *pst,
 
 	dprintk("cfid 0x%x, cvid 0x%x\n", data->currfid, data->currvid);
 	data->powernow_table = powernow_table;
-	if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu)
+	if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)
 		print_basics(data);
 
 	for (j = 0; j < data->numps; j++)
@@ -808,7 +811,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 
 	/* fill in data */
 	data->numps = data->acpi_data.state_count;
-	if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu)
+	if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)
 		print_basics(data);
 	powernow_k8_acpi_pst_values(data, 0);
 
@@ -1224,7 +1227,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 	if (cpu_family == CPU_HW_PSTATE)
 		cpumask_copy(pol->cpus, cpumask_of(pol->cpu));
 	else
-		cpumask_copy(pol->cpus, &per_cpu(cpu_core_map, pol->cpu));
+		cpumask_copy(pol->cpus, cpu_core_mask(pol->cpu));
 	data->available_cores = pol->cpus;
 
 	if (cpu_family == CPU_HW_PSTATE)
@@ -1286,7 +1289,7 @@ static unsigned int powernowk8_get (unsigned int cpu)
 	unsigned int khz = 0;
 	unsigned int first;
 
-	first = first_cpu(per_cpu(cpu_core_map, cpu));
+	first = cpumask_first(cpu_core_mask(cpu));
 	data = per_cpu(powernow_data, first);
 
 	if (!data)
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
index dedc1e98f168..1f0ec83d343b 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
@@ -322,7 +322,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy)
 
 	/* only run on CPU to be set, or on its sibling */
 #ifdef CONFIG_SMP
-	cpumask_copy(policy->cpus, &per_cpu(cpu_sibling_map, policy->cpu));
+	cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
 #endif
 
 	cpus_allowed = current->cpus_allowed;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index ca14604611ec..863f89568b1a 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -990,7 +990,7 @@ static struct sysdev_attribute *mce_attributes[] = {
 	NULL
 };
 
-static cpumask_t mce_device_initialized = CPU_MASK_NONE;
+static cpumask_var_t mce_device_initialized;
 
 /* Per cpu sysdev init.  All of the cpus still share the same ctl bank */
 static __cpuinit int mce_create_device(unsigned int cpu)
@@ -1021,7 +1021,7 @@ static __cpuinit int mce_create_device(unsigned int cpu)
 		if (err)
 			goto error2;
 	}
-	cpu_set(cpu, mce_device_initialized);
+	cpumask_set_cpu(cpu, mce_device_initialized);
 
 	return 0;
 error2:
@@ -1043,7 +1043,7 @@ static __cpuinit void mce_remove_device(unsigned int cpu)
 {
 	int i;
 
-	if (!cpu_isset(cpu, mce_device_initialized))
+	if (!cpumask_test_cpu(cpu, mce_device_initialized))
 		return;
 
 	for (i = 0; mce_attributes[i]; i++)
@@ -1053,7 +1053,7 @@ static __cpuinit void mce_remove_device(unsigned int cpu)
 		sysdev_remove_file(&per_cpu(device_mce, cpu),
 			&bank_attrs[i]);
 	sysdev_unregister(&per_cpu(device_mce,cpu));
-	cpu_clear(cpu, mce_device_initialized);
+	cpumask_clear_cpu(cpu, mce_device_initialized);
 }
 
 /* Make sure there are no machine checks on offlined CPUs. */
@@ -1162,6 +1162,8 @@ static __init int mce_init_device(void)
 	if (!mce_available(&boot_cpu_data))
 		return -EIO;
 
+	alloc_cpumask_var(&mce_device_initialized, GFP_KERNEL);
+
 	err = mce_init_banks();
 	if (err)
 		return err;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
index c5a32f92d07e..1f429ee3477d 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
@@ -477,7 +477,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 
 #ifdef CONFIG_SMP
 	if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) {	/* symlink */
-		i = cpumask_first(&per_cpu(cpu_core_map, cpu));
+		i = cpumask_first(cpu_core_mask(cpu));
 
 		/* first core not up yet */
 		if (cpu_data(i).cpu_core_id)
@@ -497,7 +497,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 		if (err)
 			goto out;
 
-		cpumask_copy(b->cpus, &per_cpu(cpu_core_map, cpu));
+		cpumask_copy(b->cpus, cpu_core_mask(cpu));
 		per_cpu(threshold_banks, cpu)[bank] = b;
 		goto out;
 	}
@@ -521,7 +521,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 #ifndef CONFIG_SMP
 	cpumask_setall(b->cpus);
 #else
-	cpumask_copy(b->cpus, &per_cpu(cpu_core_map, cpu));
+	cpumask_copy(b->cpus, cpu_core_mask(cpu));
 #endif
 
 	per_cpu(threshold_banks, cpu)[bank] = b;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
index aaa7d9730938..96b2a85545aa 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
@@ -249,7 +249,7 @@ void cmci_rediscover(int dying)
 	for_each_online_cpu (cpu) {
 		if (cpu == dying)
 			continue;
-		if (set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)))
+		if (set_cpus_allowed_ptr(current, cpumask_of(cpu)))
 			continue;
 		/* Recheck banks in case CPUs don't all have the same */
 		if (cmci_supported(&banks))
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index d67e0e48bc2d..f93047fed791 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -14,7 +14,7 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c,
 	if (c->x86_max_cores * smp_num_siblings > 1) {
 		seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
 		seq_printf(m, "siblings\t: %d\n",
-			   cpus_weight(per_cpu(cpu_core_map, cpu)));
+			   cpumask_weight(cpu_sibling_mask(cpu)));
 		seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
 		seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
 		seq_printf(m, "apicid\t\t: %d\n", c->apicid);
@@ -143,9 +143,9 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 static void *c_start(struct seq_file *m, loff_t *pos)
 {
 	if (*pos == 0)	/* just in case, cpu 0 is not the first */
-		*pos = first_cpu(cpu_online_map);
+		*pos = cpumask_first(cpu_online_mask);
 	else
-		*pos = next_cpu_nr(*pos - 1, cpu_online_map);
+		*pos = cpumask_next(*pos - 1, cpu_online_mask);
 	if ((*pos) < nr_cpu_ids)
 		return &cpu_data(*pos);
 	return NULL;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 6afa5232dbb7..6638294cec8d 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -324,7 +324,7 @@ void stop_this_cpu(void *dummy)
 	/*
 	 * Remove this CPU:
 	 */
-	cpu_clear(smp_processor_id(), cpu_online_map);
+	set_cpu_online(smp_processor_id(), false);
 	disable_local_APIC();
 
 	for (;;) {
@@ -474,12 +474,12 @@ static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c)
 	return 1;
 }
 
-static cpumask_t c1e_mask = CPU_MASK_NONE;
+static cpumask_var_t c1e_mask;
 static int c1e_detected;
 
 void c1e_remove_cpu(int cpu)
 {
-	cpu_clear(cpu, c1e_mask);
+	cpumask_clear_cpu(cpu, c1e_mask);
 }
 
 /*
@@ -508,8 +508,8 @@ static void c1e_idle(void)
 	if (c1e_detected) {
 		int cpu = smp_processor_id();
 
-		if (!cpu_isset(cpu, c1e_mask)) {
-			cpu_set(cpu, c1e_mask);
+		if (!cpumask_test_cpu(cpu, c1e_mask)) {
+			cpumask_set_cpu(cpu, c1e_mask);
 			/*
 			 * Force broadcast so ACPI can not interfere. Needs
 			 * to run with interrupts enabled as it uses
@@ -556,6 +556,8 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
 		pm_idle = mwait_idle;
 	} else if (check_c1e_idle(c)) {
 		printk(KERN_INFO "using C1E aware idle routine\n");
+		alloc_cpumask_var(&c1e_mask, GFP_KERNEL);
+		cpumask_clear(c1e_mask);
 		pm_idle = c1e_idle;
 	} else
 		pm_idle = default_idle;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index ef7d10170c30..58d24ef917d8 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -101,11 +101,11 @@ EXPORT_SYMBOL(smp_num_siblings);
 DEFINE_PER_CPU(u16, cpu_llc_id) = BAD_APICID;
 
 /* representing HT siblings of each logical CPU */
-DEFINE_PER_CPU(cpumask_t, cpu_sibling_map);
+DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
 EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
 
 /* representing HT and core siblings of each logical CPU */
-DEFINE_PER_CPU(cpumask_t, cpu_core_map);
+DEFINE_PER_CPU(cpumask_var_t, cpu_core_map);
 EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 
 /* Per CPU bogomips and other parameters */
@@ -115,11 +115,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_info);
 atomic_t init_deasserted;
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_X86_32)
-
-/* which logical CPUs are on which nodes */
-cpumask_t node_to_cpumask_map[MAX_NUMNODES] __read_mostly =
-				{ [0 ... MAX_NUMNODES-1] = CPU_MASK_NONE };
-EXPORT_SYMBOL(node_to_cpumask_map);
 /* 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);
@@ -128,7 +123,7 @@ EXPORT_SYMBOL(cpu_to_node_map);
 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]);
+	cpumask_set_cpu(cpu, node_to_cpumask_map[node]);
 	cpu_to_node_map[cpu] = node;
 }
 
@@ -139,7 +134,7 @@ static void unmap_cpu_to_node(int cpu)
 
 	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]);
+		cpumask_clear_cpu(cpu, node_to_cpumask_map[node]);
 	cpu_to_node_map[cpu] = 0;
 }
 #else /* !(CONFIG_NUMA && CONFIG_X86_32) */
@@ -301,7 +296,7 @@ notrace static void __cpuinit start_secondary(void *unused)
 	__flush_tlb_all();
 #endif
 
-	/* This must be done before setting cpu_online_map */
+	/* This must be done before setting cpu_online_mask */
 	set_cpu_sibling_map(raw_smp_processor_id());
 	wmb();
 
@@ -334,6 +329,23 @@ notrace static void __cpuinit start_secondary(void *unused)
 	cpu_idle();
 }
 
+#ifdef CONFIG_CPUMASK_OFFSTACK
+/* In this case, llc_shared_map is a pointer to a cpumask. */
+static inline void copy_cpuinfo_x86(struct cpuinfo_x86 *dst,
+				    const struct cpuinfo_x86 *src)
+{
+	struct cpumask *llc = dst->llc_shared_map;
+	*dst = *src;
+	dst->llc_shared_map = llc;
+}
+#else
+static inline void copy_cpuinfo_x86(struct cpuinfo_x86 *dst,
+				    const struct cpuinfo_x86 *src)
+{
+	*dst = *src;
+}
+#endif /* CONFIG_CPUMASK_OFFSTACK */
+
 /*
  * The bootstrap kernel entry code has set these up. Save them for
  * a given CPU
@@ -343,7 +355,7 @@ void __cpuinit smp_store_cpu_info(int id)
 {
 	struct cpuinfo_x86 *c = &cpu_data(id);
 
-	*c = boot_cpu_data;
+	copy_cpuinfo_x86(c, &boot_cpu_data);
 	c->cpu_index = id;
 	if (id != 0)
 		identify_secondary_cpu(c);
@@ -367,15 +379,15 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 				cpumask_set_cpu(cpu, cpu_sibling_mask(i));
 				cpumask_set_cpu(i, cpu_core_mask(cpu));
 				cpumask_set_cpu(cpu, cpu_core_mask(i));
-				cpumask_set_cpu(i, &c->llc_shared_map);
-				cpumask_set_cpu(cpu, &o->llc_shared_map);
+				cpumask_set_cpu(i, c->llc_shared_map);
+				cpumask_set_cpu(cpu, o->llc_shared_map);
 			}
 		}
 	} else {
 		cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
 	}
 
-	cpumask_set_cpu(cpu, &c->llc_shared_map);
+	cpumask_set_cpu(cpu, c->llc_shared_map);
 
 	if (current_cpu_data.x86_max_cores == 1) {
 		cpumask_copy(cpu_core_mask(cpu), cpu_sibling_mask(cpu));
@@ -386,8 +398,8 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 	for_each_cpu(i, cpu_sibling_setup_mask) {
 		if (per_cpu(cpu_llc_id, cpu) != BAD_APICID &&
 		    per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) {
-			cpumask_set_cpu(i, &c->llc_shared_map);
-			cpumask_set_cpu(cpu, &cpu_data(i).llc_shared_map);
+			cpumask_set_cpu(i, c->llc_shared_map);
+			cpumask_set_cpu(cpu, cpu_data(i).llc_shared_map);
 		}
 		if (c->phys_proc_id == cpu_data(i).phys_proc_id) {
 			cpumask_set_cpu(i, cpu_core_mask(cpu));
@@ -425,12 +437,7 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
 	if (sched_mc_power_savings || sched_smt_power_savings)
 		return cpu_core_mask(cpu);
 	else
-		return &c->llc_shared_map;
-}
-
-cpumask_t cpu_coregroup_map(int cpu)
-{
-	return *cpu_coregroup_mask(cpu);
+		return c->llc_shared_map;
 }
 
 static void impress_friends(void)
@@ -897,9 +904,8 @@ int __cpuinit native_cpu_up(unsigned int cpu)
  */
 static __init void disable_smp(void)
 {
-	/* use the read/write pointers to the present and possible maps */
-	cpumask_copy(&cpu_present_map, cpumask_of(0));
-	cpumask_copy(&cpu_possible_map, cpumask_of(0));
+	init_cpu_present(cpumask_of(0));
+	init_cpu_possible(cpumask_of(0));
 	smpboot_clear_io_apic_irqs();
 
 	if (smp_found_config)
@@ -1031,6 +1037,8 @@ static void __init smp_cpu_index_default(void)
  */
 void __init native_smp_prepare_cpus(unsigned int max_cpus)
 {
+	unsigned int i;
+
 	preempt_disable();
 	smp_cpu_index_default();
 	current_cpu_data = boot_cpu_data;
@@ -1044,6 +1052,14 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	boot_cpu_logical_apicid = logical_smp_processor_id();
 #endif
 	current_thread_info()->cpu = 0;  /* needed? */
+	for_each_possible_cpu(i) {
+		alloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
+		alloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
+		alloc_cpumask_var(&cpu_data(i).llc_shared_map, GFP_KERNEL);
+		cpumask_clear(per_cpu(cpu_core_map, i));
+		cpumask_clear(per_cpu(cpu_sibling_map, i));
+		cpumask_clear(cpu_data(i).llc_shared_map);
+	}
 	set_cpu_sibling_map(0);
 
 	enable_IR_x2apic();
@@ -1132,11 +1148,11 @@ early_param("possible_cpus", _setup_possible_cpus);
 
 
 /*
- * cpu_possible_map should be static, it cannot change as cpu's
+ * cpu_possible_mask should be static, it cannot change as cpu's
  * are onlined, or offlined. The reason is per-cpu data-structures
  * are allocated by some modules at init time, and dont expect to
  * do this dynamically on cpu arrival/departure.
- * cpu_present_map on the other hand can change dynamically.
+ * cpu_present_mask on the other hand can change dynamically.
  * In case when cpu_hotplug is not compiled, then we resort to current
  * behaviour, which is cpu_possible == cpu_present.
  * - Ashok Raj
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index d038b9c45cf8..8afb69180c9b 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -275,6 +275,8 @@ const struct cpumask *uv_flush_send_and_wait(int cpu, int this_blade,
 	return NULL;
 }
 
+static DEFINE_PER_CPU(cpumask_var_t, uv_flush_tlb_mask);
+
 /**
  * uv_flush_tlb_others - globally purge translation cache of a virtual
  * address or all TLB's
@@ -304,8 +306,7 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 					  struct mm_struct *mm,
 					  unsigned long va, unsigned int cpu)
 {
-	static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask);
-	struct cpumask *flush_mask = &__get_cpu_var(flush_tlb_mask);
+	struct cpumask *flush_mask = __get_cpu_var(uv_flush_tlb_mask);
 	int i;
 	int bit;
 	int blade;
@@ -755,6 +756,10 @@ static int __init uv_bau_init(void)
 	if (!is_uv_system())
 		return 0;
 
+	for_each_possible_cpu(cur_cpu)
+		alloc_cpumask_var_node(&per_cpu(uv_flush_tlb_mask, cur_cpu),
+				       GFP_KERNEL, cpu_to_node(cur_cpu));
+
 	uv_bau_retry_limit = 1;
 	uv_nshift = uv_hub_info->n_val;
 	uv_mmask = (1UL << uv_hub_info->n_val) - 1;
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 08537747cb58..fdd30d08ab52 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -14,7 +14,7 @@ obj-$(CONFIG_MMIOTRACE)		+= mmiotrace.o
 mmiotrace-y			:= kmmio.o pf_in.o mmio-mod.o
 obj-$(CONFIG_MMIOTRACE_TEST)	+= testmmiotrace.o
 
-obj-$(CONFIG_NUMA)		+= numa_$(BITS).o
+obj-$(CONFIG_NUMA)		+= numa.o numa_$(BITS).o
 obj-$(CONFIG_K8_NUMA)		+= k8topology_64.o
 obj-$(CONFIG_ACPI_NUMA)		+= srat_$(BITS).o
 
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
new file mode 100644
index 000000000000..ce255e32a593
--- /dev/null
+++ b/arch/x86/mm/numa.c
@@ -0,0 +1,67 @@
+/* Common code for 32 and 64-bit NUMA */
+#include <linux/topology.h>
+#include <linux/module.h>
+#include <linux/bootmem.h>
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+# define DBG(x...) printk(KERN_DEBUG x)
+#else
+# define DBG(x...)
+#endif
+
+/*
+ * Which logical CPUs are on which nodes
+ */
+cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+EXPORT_SYMBOL(node_to_cpumask_map);
+
+/*
+ * 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;
+
+	/* 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 */
+	for (node = 0; node < nr_node_ids; node++)
+		alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
+
+	/* cpumask_of_node() will now work */
+	pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
+}
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+/*
+ * Returns a pointer to the bitmask of CPUs on Node 'node'.
+ */
+const struct cpumask *cpumask_of_node(int node)
+{
+	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_none_mask;
+	}
+	if (node_to_cpumask_map[node] == NULL) {
+		printk(KERN_WARNING
+			"cpumask_of_node(%d): no node_to_cpumask_map!\n",
+			node);
+		dump_stack();
+		return cpu_online_mask;
+	}
+	return &node_to_cpumask_map[node];
+}
+EXPORT_SYMBOL(cpumask_of_node);
+#endif
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 64c9cf043cdd..d73aaa892371 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -20,12 +20,6 @@
 #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);
 
@@ -49,12 +43,6 @@ 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 :
  * 1 if OK
@@ -661,36 +649,6 @@ 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);
@@ -723,12 +681,12 @@ void __cpuinit numa_clear_node(int cpu)
 
 void __cpuinit numa_add_cpu(int cpu)
 {
-	cpu_set(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
+	cpumask_set_cpu(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)]);
+	cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
 }
 
 #else /* CONFIG_DEBUG_PER_CPU_MAPS */
@@ -739,20 +697,20 @@ void __cpuinit numa_remove_cpu(int cpu)
 static void __cpuinit numa_set_cpumask(int cpu, int enable)
 {
 	int node = early_cpu_to_node(cpu);
-	cpumask_t *mask;
+	struct cpumask *mask;
 	char buf[64];
 
-	if (node_to_cpumask_map == NULL) {
-		printk(KERN_ERR "node_to_cpumask_map NULL\n");
+	mask = node_to_cpumask_map[node];
+	if (mask == NULL) {
+		printk(KERN_ERR "node_to_cpumask_map[%i] NULL\n", node);
 		dump_stack();
 		return;
 	}
 
-	mask = &node_to_cpumask_map[node];
 	if (enable)
-		cpu_set(cpu, *mask);
+		cpumask_set_cpu(cpu, mask);
 	else
-		cpu_clear(cpu, *mask);
+		cpumask_clear_cpu(cpu, mask);
 
 	cpulist_scnprintf(buf, sizeof(buf), mask);
 	printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
@@ -799,59 +757,6 @@ int early_cpu_to_node(int cpu)
 	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 ---------
  */
diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c
index 4c4a51c90bc2..819b131fd752 100644
--- a/arch/x86/oprofile/op_model_p4.c
+++ b/arch/x86/oprofile/op_model_p4.c
@@ -380,7 +380,7 @@ static unsigned int get_stagger(void)
 {
 #ifdef CONFIG_SMP
 	int cpu = smp_processor_id();
-	return (cpu != first_cpu(per_cpu(cpu_sibling_map, cpu)));
+	return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map));
 #endif
 	return 0;
 }
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 8d470562ffc9..585a6e330837 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -158,7 +158,7 @@ static void __init xen_fill_possible_map(void)
 		rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL);
 		if (rc >= 0) {
 			num_processors++;
-			cpu_set(i, cpu_possible_map);
+			set_cpu_possible(i, true);
 		}
 	}
 }
@@ -197,7 +197,7 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
 	while ((num_possible_cpus() > 1) && (num_possible_cpus() > max_cpus)) {
 		for (cpu = nr_cpu_ids - 1; !cpu_possible(cpu); cpu--)
 			continue;
-		cpu_clear(cpu, cpu_possible_map);
+		set_cpu_possible(cpu, false);
 	}
 
 	for_each_possible_cpu (cpu) {
@@ -210,7 +210,7 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
 		if (IS_ERR(idle))
 			panic("failed fork for CPU %d", cpu);
 
-		cpu_set(cpu, cpu_present_map);
+		set_cpu_present(cpu, true);
 	}
 }
 
diff --git a/block/blk.h b/block/blk.h
index 0dce92c37496..3ee94358b43d 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -102,7 +102,7 @@ static inline int blk_cpu_to_group(int cpu)
 	const struct cpumask *mask = cpu_coregroup_mask(cpu);
 	return cpumask_first(mask);
 #elif defined(CONFIG_SCHED_SMT)
-	return first_cpu(per_cpu(cpu_sibling_map, cpu));
+	return cpumask_first(topology_thread_cpumask(cpu));
 #else
 	return cpu;
 #endif
diff --git a/drivers/base/node.c b/drivers/base/node.c
index f8f578a71b25..40b809742a1c 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -24,7 +24,7 @@ static struct sysdev_class node_class = {
 static ssize_t node_read_cpumap(struct sys_device *dev, int type, char *buf)
 {
 	struct node *node_dev = to_node(dev);
-	node_to_cpumask_ptr(mask, node_dev->sysdev.id);
+	const struct cpumask *mask = cpumask_of_node(node_dev->sysdev.id);
 	int len;
 
 	/* 2008/04/07: buf currently PAGE_SIZE, need 9 chars per 32 bits. */
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 93eac1423585..b522f883d674 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -212,10 +212,9 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
 	node = dev_to_node(&dev->dev);
 	if (node >= 0) {
 		int cpu;
-		node_to_cpumask_ptr(nodecpumask, node);
 
 		get_online_cpus();
-		cpu = cpumask_any_and(nodecpumask, cpu_online_mask);
+		cpu = cpumask_any_and(cpumask_of_node(node), cpu_online_mask);
 		if (cpu < nr_cpu_ids)
 			error = work_on_cpu(cpu, local_pci_probe, &ddi);
 		else
diff --git a/drivers/xen/cpu_hotplug.c b/drivers/xen/cpu_hotplug.c
index 974f56d1ebe1..5f54c01c1568 100644
--- a/drivers/xen/cpu_hotplug.c
+++ b/drivers/xen/cpu_hotplug.c
@@ -10,7 +10,7 @@ static void enable_hotplug_cpu(int cpu)
 	if (!cpu_present(cpu))
 		arch_register_cpu(cpu);
 
-	cpu_set(cpu, cpu_present_map);
+	set_cpu_present(cpu, true);
 }
 
 static void disable_hotplug_cpu(int cpu)
@@ -18,7 +18,7 @@ static void disable_hotplug_cpu(int cpu)
 	if (cpu_present(cpu))
 		arch_unregister_cpu(cpu);
 
-	cpu_clear(cpu, cpu_present_map);
+	set_cpu_present(cpu, false);
 }
 
 static void vcpu_hotplug(unsigned int cpu)
diff --git a/include/linux/topology.h b/include/linux/topology.h
index a16b9e06f2e5..16b7d6896ce9 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -38,11 +38,7 @@
 #endif
 
 #ifndef nr_cpus_node
-#define nr_cpus_node(node)				\
-	({						\
-		node_to_cpumask_ptr(__tmp__, node);	\
-		cpus_weight(*__tmp__);			\
-	})
+#define nr_cpus_node(node) cpumask_weight(cpumask_of_node(node))
 #endif
 
 #define for_each_node_with_cpus(node)			\
diff --git a/kernel/sched.c b/kernel/sched.c
index 0a76d0b6f215..5dabd80c3c15 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -7249,7 +7249,7 @@ cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
 {
 	int group;
 
-	cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map);
+	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
 	group = cpumask_first(mask);
 	if (sg)
 		*sg = &per_cpu(sched_group_core, group).sg;
@@ -7278,7 +7278,7 @@ cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
 	cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
 	group = cpumask_first(mask);
 #elif defined(CONFIG_SCHED_SMT)
-	cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map);
+	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
 	group = cpumask_first(mask);
 #else
 	group = cpu;
@@ -7621,7 +7621,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 		SD_INIT(sd, SIBLING);
 		set_domain_attribute(sd, attr);
 		cpumask_and(sched_domain_span(sd),
-			    &per_cpu(cpu_sibling_map, i), cpu_map);
+			    topology_thread_cpumask(i), cpu_map);
 		sd->parent = p;
 		p->child = sd;
 		cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask);
@@ -7632,7 +7632,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 	/* Set up CPU (sibling) groups */
 	for_each_cpu(i, cpu_map) {
 		cpumask_and(this_sibling_map,
-			    &per_cpu(cpu_sibling_map, i), cpu_map);
+			    topology_thread_cpumask(i), cpu_map);
 		if (i != cpumask_first(this_sibling_map))
 			continue;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5c44ed49ca93..a92b0975b9a5 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2134,7 +2134,7 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask)
 	int n, val;
 	int min_val = INT_MAX;
 	int best_node = -1;
-	node_to_cpumask_ptr(tmp, 0);
+	const struct cpumask *tmp = cpumask_of_node(0);
 
 	/* Use the local node if we haven't already */
 	if (!node_isset(node, *used_node_mask)) {
@@ -2155,8 +2155,8 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask)
 		val += (n < node);
 
 		/* Give preference to headless and unused nodes */
-		node_to_cpumask_ptr_next(tmp, n);
-		if (!cpus_empty(*tmp))
+		tmp = cpumask_of_node(n);
+		if (!cpumask_empty(tmp))
 			val += PENALTY_FOR_NODE_WITH_CPUS;
 
 		/* Slight preference for less loaded node */
diff --git a/mm/quicklist.c b/mm/quicklist.c
index 8dbb6805ef35..e66d07d1b4ff 100644
--- a/mm/quicklist.c
+++ b/mm/quicklist.c
@@ -29,7 +29,7 @@ static unsigned long max_pages(unsigned long min_pages)
 	int node = numa_node_id();
 	struct zone *zones = NODE_DATA(node)->node_zones;
 	int num_cpus_on_node;
-	node_to_cpumask_ptr(cpumask_on_node, node);
+	const struct cpumask *cpumask_on_node = cpumask_of_node(node);
 
 	node_free_pages =
 #ifdef CONFIG_ZONE_DMA
diff --git a/mm/slab.c b/mm/slab.c
index 4d00855629c4..2daaca0b4541 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1160,7 +1160,7 @@ static void __cpuinit cpuup_canceled(long cpu)
 	struct kmem_cache *cachep;
 	struct kmem_list3 *l3 = NULL;
 	int node = cpu_to_node(cpu);
-	node_to_cpumask_ptr(mask, node);
+	const struct cpumask *mask = cpumask_of_node(node);
 
 	list_for_each_entry(cachep, &cache_chain, next) {
 		struct array_cache *nc;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e89517141657..592bb9619f75 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1963,7 +1963,7 @@ static int kswapd(void *p)
 	struct reclaim_state reclaim_state = {
 		.reclaimed_slab = 0,
 	};
-	node_to_cpumask_ptr(cpumask, pgdat->node_id);
+	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
 
 	if (!cpumask_empty(cpumask))
 		set_cpus_allowed_ptr(tsk, cpumask);
@@ -2198,7 +2198,9 @@ static int __devinit cpu_callback(struct notifier_block *nfb,
 	if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
 		for_each_node_state(nid, N_HIGH_MEMORY) {
 			pg_data_t *pgdat = NODE_DATA(nid);
-			node_to_cpumask_ptr(mask, pgdat->node_id);
+			const struct cpumask *mask;
+
+			mask = cpumask_of_node(pgdat->node_id);
 
 			if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
 				/* One of our CPUs online: restore mask */
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index c51fed4d1af1..3bdd5bffaca8 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -317,8 +317,7 @@ svc_pool_map_set_cpumask(struct task_struct *task, unsigned int pidx)
 	}
 	case SVC_POOL_PERNODE:
 	{
-		node_to_cpumask_ptr(nodecpumask, node);
-		set_cpus_allowed_ptr(task, nodecpumask);
+		set_cpus_allowed_ptr(task, cpumask_of_node(node));
 		break;
 	}
 	}