46 files changed, 260 insertions, 192 deletions

diff --git a/arch/alpha/include/asm/topology.h b/arch/alpha/include/asm/topology.h
index 149532e162c4..b4f284c72ff3 100644
--- a/arch/alpha/include/asm/topology.h
+++ b/arch/alpha/include/asm/topology.h
@@ -39,7 +39,24 @@ static inline cpumask_t node_to_cpumask(int node)
         return node_cpu_mask;
 }
 
+extern struct cpumask node_to_cpumask_map[];
+/* FIXME: This is dumb, recalculating every time.  But simple. */
+static const struct cpumask *cpumask_of_node(int node)
+{
+        int cpu;
+
+        cpumask_clear(&node_to_cpumask_map[node]);
+
+        for_each_online_cpu(cpu) {
+                if (cpu_to_node(cpu) == node)
+                        cpumask_set_cpu(cpu, node_to_cpumask_map[node]);
+        }
+
+        return &node_to_cpumask_map[node];
+}
+
 #define pcibus_to_cpumask(bus)  (cpu_online_map)
+#define cpumask_of_pcibus(bus)  (cpu_online_mask)
 
 #endif /* !CONFIG_NUMA */
 # include <asm-generic/topology.h>
diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c
index d0f1620007f7..703731accda6 100644
--- a/arch/alpha/kernel/irq.c
+++ b/arch/alpha/kernel/irq.c
@@ -50,7 +50,8 @@ int irq_select_affinity(unsigned int irq)
         if (!irq_desc[irq].chip->set_affinity || irq_user_affinity[irq])
                 return 1;
 
-        while (!cpu_possible(cpu) || !cpu_isset(cpu, irq_default_affinity))
+        while (!cpu_possible(cpu) ||
+               !cpumask_test_cpu(cpu, irq_default_affinity))
                 cpu = (cpu < (NR_CPUS-1) ? cpu + 1 : 0);
         last_cpu = cpu;
 
diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c
index a449e999027c..02bee6983ce2 100644
--- a/arch/alpha/kernel/setup.c
+++ b/arch/alpha/kernel/setup.c
@@ -79,6 +79,11 @@ int alpha_l3_cacheshape;
 unsigned long alpha_verbose_mcheck = CONFIG_VERBOSE_MCHECK_ON;
 #endif
 
+#ifdef CONFIG_NUMA
+struct cpumask node_to_cpumask_map[MAX_NUMNODES] __read_mostly;
+EXPORT_SYMBOL(node_to_cpumask_map);
+#endif
+
 /* Which processor we booted from.  */
 int boot_cpuid;
 
diff --git a/arch/avr32/include/asm/bitops.h b/arch/avr32/include/asm/bitops.h
index 1a50b69b1a19..f7dd5f71edf7 100644
--- a/arch/avr32/include/asm/bitops.h
+++ b/arch/avr32/include/asm/bitops.h
@@ -263,6 +263,11 @@ static inline int fls(unsigned long word)
         return 32 - result;
 }
 
+static inline int __fls(unsigned long word)
+{
+        return fls(word) - 1;
+}
+
 unsigned long find_first_zero_bit(const unsigned long *addr,
                                   unsigned long size);
 unsigned long find_next_zero_bit(const unsigned long *addr,
diff --git a/arch/blackfin/include/asm/bitops.h b/arch/blackfin/include/asm/bitops.h
index b39a175c79c1..c428e4106f89 100644
--- a/arch/blackfin/include/asm/bitops.h
+++ b/arch/blackfin/include/asm/bitops.h
@@ -213,6 +213,7 @@ static __inline__ int __test_bit(int nr, const void *addr)
 #endif                          /* __KERNEL__ */
 
 #include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>
 
 #endif                          /* _BLACKFIN_BITOPS_H */
diff --git a/arch/cris/include/asm/bitops.h b/arch/cris/include/asm/bitops.h
index c0e62f811e09..9e69cfb7f134 100644
--- a/arch/cris/include/asm/bitops.h
+++ b/arch/cris/include/asm/bitops.h
@@ -148,6 +148,7 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
 #define ffs kernel_ffs
 
 #include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>
 #include <asm-generic/bitops/hweight.h>
 #include <asm-generic/bitops/find.h>
diff --git a/arch/h8300/include/asm/bitops.h b/arch/h8300/include/asm/bitops.h
index cb18e3b0aa94..cb9ddf5fc54f 100644
--- a/arch/h8300/include/asm/bitops.h
+++ b/arch/h8300/include/asm/bitops.h
@@ -207,6 +207,7 @@ static __inline__ unsigned long __ffs(unsigned long word)
 #endif /* __KERNEL__ */
 
 #include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>
 
 #endif /* _H8300_BITOPS_H */
diff --git a/arch/ia64/include/asm/irq.h b/arch/ia64/include/asm/irq.h
index 3627116fb0e2..36429a532630 100644
--- a/arch/ia64/include/asm/irq.h
+++ b/arch/ia64/include/asm/irq.h
@@ -27,7 +27,7 @@ irq_canonicalize (int irq)
 }
 
 extern void set_irq_affinity_info (unsigned int irq, int dest, int redir);
-bool is_affinity_mask_valid(cpumask_t cpumask);
+bool is_affinity_mask_valid(cpumask_var_t cpumask);
 
 #define is_affinity_mask_valid is_affinity_mask_valid
 
diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
index a3cc9f65f954..76a33a91ca69 100644
--- a/arch/ia64/include/asm/topology.h
+++ b/arch/ia64/include/asm/topology.h
@@ -34,6 +34,7 @@
  * Returns a bitmask of CPUs on Node 'node'.
  */
 #define node_to_cpumask(node) (node_to_cpu_mask[node])
+#define cpumask_of_node(node) (&node_to_cpu_mask[node])
 
 /*
  * Returns the number of the node containing Node 'nid'.
@@ -45,7 +46,7 @@
 /*
  * Returns the number of the first CPU on Node 'node'.
  */
-#define node_to_first_cpu(node) (first_cpu(node_to_cpumask(node)))
+#define node_to_first_cpu(node) (cpumask_first(cpumask_of_node(node)))
 
 /*
  * Determines the node for a given pci bus
@@ -109,6 +110,8 @@ void build_cpu_to_node_map(void);
 #define topology_core_id(cpu)                   (cpu_data(cpu)->core_id)
 #define topology_core_siblings(cpu)             (cpu_core_map[cpu])
 #define topology_thread_siblings(cpu)           (per_cpu(cpu_sibling_map, cpu))
+#define topology_core_cpumask(cpu)              (&cpu_core_map[cpu])
+#define topology_thread_cpumask(cpu)            (&per_cpu(cpu_sibling_map, cpu))
 #define smt_capable()                           (smp_num_siblings > 1)
 #endif
 
@@ -119,6 +122,10 @@ extern void arch_fix_phys_package_id(int num, u32 slot);
                                         node_to_cpumask(pcibus_to_node(bus)) \
                                 )
 
+#define cpumask_of_pcibus(bus)  (pcibus_to_node(bus) == -1 ?            \
+                                 cpu_all_mask :                         \
+                                 cpumask_from_node(pcibus_to_node(bus)))
+
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_IA64_TOPOLOGY_H */
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index bd7acc71e8a9..0553648b7595 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -202,7 +202,6 @@ char *__init __acpi_map_table(unsigned long phys_addr, unsigned long size)
                             Boot-time Table Parsing
    -------------------------------------------------------------------------- */
 
-static int total_cpus __initdata;
 static int available_cpus __initdata;
 struct acpi_table_madt *acpi_madt __initdata;
 static u8 has_8259;
@@ -1001,7 +1000,7 @@ acpi_map_iosapic(acpi_handle handle, u32 depth, void *context, void **ret)
         node = pxm_to_node(pxm);
 
         if (node >= MAX_NUMNODES || !node_online(node) ||
-            cpus_empty(node_to_cpumask(node)))
+            cpumask_empty(cpumask_of_node(node)))
                 return AE_OK;
 
         /* We know a gsi to node mapping! */
diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c
index c8adecd5b416..5cfd3d91001a 100644
--- a/arch/ia64/kernel/iosapic.c
+++ b/arch/ia64/kernel/iosapic.c
@@ -695,32 +695,31 @@ get_target_cpu (unsigned int gsi, int irq)
 #ifdef CONFIG_NUMA
         {
                 int num_cpus, cpu_index, iosapic_index, numa_cpu, i = 0;
-                cpumask_t cpu_mask;
+                const struct cpumask *cpu_mask;
 
                 iosapic_index = find_iosapic(gsi);
                 if (iosapic_index < 0 ||
                     iosapic_lists[iosapic_index].node == MAX_NUMNODES)
                         goto skip_numa_setup;
 
-                cpu_mask = node_to_cpumask(iosapic_lists[iosapic_index].node);
-                cpus_and(cpu_mask, cpu_mask, domain);
-                for_each_cpu_mask(numa_cpu, cpu_mask) {
-                        if (!cpu_online(numa_cpu))
-                                cpu_clear(numa_cpu, cpu_mask);
+                cpu_mask = cpumask_of_node(iosapic_lists[iosapic_index].node);
+                num_cpus = 0;
+                for_each_cpu_and(numa_cpu, cpu_mask, &domain) {
+                        if (cpu_online(numa_cpu))
+                                num_cpus++;
                 }
 
-                num_cpus = cpus_weight(cpu_mask);
-
                 if (!num_cpus)
                         goto skip_numa_setup;
 
                 /* Use irq assignment to distribute across cpus in node */
                 cpu_index = irq % num_cpus;
 
-                for (numa_cpu = first_cpu(cpu_mask) ; i < cpu_index ; i++)
-                        numa_cpu = next_cpu(numa_cpu, cpu_mask);
+                for_each_cpu_and(numa_cpu, cpu_mask, &domain)
+                        if (cpu_online(numa_cpu) && i++ >= cpu_index)
+                                break;
 
-                if (numa_cpu != NR_CPUS)
+                if (numa_cpu < nr_cpu_ids)
                         return cpu_physical_id(numa_cpu);
         }
 skip_numa_setup:
@@ -731,7 +730,7 @@ skip_numa_setup:
          * case of NUMA.)
          */
         do {
-                if (++cpu >= NR_CPUS)
+                if (++cpu >= nr_cpu_ids)
                         cpu = 0;
         } while (!cpu_online(cpu) || !cpu_isset(cpu, domain));
 
diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c
index 0b6db53fedcf..95ff16cb05d8 100644
--- a/arch/ia64/kernel/irq.c
+++ b/arch/ia64/kernel/irq.c
@@ -112,11 +112,11 @@ void set_irq_affinity_info (unsigned int irq, int hwid, int redir)
         }
 }
 
-bool is_affinity_mask_valid(cpumask_t cpumask)
+bool is_affinity_mask_valid(cpumask_var_t cpumask)
 {
         if (ia64_platform_is("sn2")) {
                 /* Only allow one CPU to be specified in the smp_affinity mask */
-                if (cpus_weight(cpumask) != 1)
+                if (cpumask_weight(cpumask) != 1)
                         return false;
         }
         return true;
diff --git a/arch/ia64/sn/kernel/sn2/sn_hwperf.c b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
index 636588e7e068..be339477f906 100644
--- a/arch/ia64/sn/kernel/sn2/sn_hwperf.c
+++ b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
@@ -385,7 +385,6 @@ static int sn_topology_show(struct seq_file *s, void *d)
         int j;
         const char *slabname;
         int ordinal;
-        cpumask_t cpumask;
         char slice;
         struct cpuinfo_ia64 *c;
         struct sn_hwperf_port_info *ptdata;
@@ -473,23 +472,21 @@ static int sn_topology_show(struct seq_file *s, void *d)
                  * CPUs on this node, if any
                  */
                 if (!SN_HWPERF_IS_IONODE(obj)) {
-                        cpumask = node_to_cpumask(ordinal);
-                        for_each_online_cpu(i) {
-                                if (cpu_isset(i, cpumask)) {
-                                        slice = 'a' + cpuid_to_slice(i);
-                                        c = cpu_data(i);
-                                        seq_printf(s, "cpu %d %s%c local"
-                                                " freq %luMHz, arch ia64",
-                                                i, obj->location, slice,
-                                                c->proc_freq / 1000000);
-                                        for_each_online_cpu(j) {
-                                                seq_printf(s, j ? ":%d" : ", dist %d",
-                                                        node_distance(
+                        for_each_cpu_and(i, cpu_online_mask,
+                                         cpumask_of_node(ordinal)) {
+                                slice = 'a' + cpuid_to_slice(i);
+                                c = cpu_data(i);
+                                seq_printf(s, "cpu %d %s%c local"
+                                           " freq %luMHz, arch ia64",
+                                           i, obj->location, slice,
+                                           c->proc_freq / 1000000);
+                                for_each_online_cpu(j) {
+                                        seq_printf(s, j ? ":%d" : ", dist %d",
+                                                   node_distance(
                                                         cpu_to_node(i),
                                                         cpu_to_node(j)));
-                                        }
-                                        seq_putc(s, '\n');
                                 }
+                                seq_putc(s, '\n');
                         }
                 }
         }
diff --git a/arch/m32r/kernel/smpboot.c b/arch/m32r/kernel/smpboot.c
index 0f06b3722e96..2547d6c4a827 100644
--- a/arch/m32r/kernel/smpboot.c
+++ b/arch/m32r/kernel/smpboot.c
@@ -592,7 +592,7 @@ int setup_profiling_timer(unsigned int multiplier)
          * accounting. At that time they also adjust their APIC timers
          * accordingly.
          */
-        for (i = 0; i < NR_CPUS; ++i)
+        for_each_possible_cpu(i)
                 per_cpu(prof_multiplier, i) = multiplier;
 
         return 0;
diff --git a/arch/m68knommu/include/asm/bitops.h b/arch/m68knommu/include/asm/bitops.h
index 6f3685eab44c..9d3cbe5fad1e 100644
--- a/arch/m68knommu/include/asm/bitops.h
+++ b/arch/m68knommu/include/asm/bitops.h
@@ -331,6 +331,7 @@ found_middle:
 #endif /* __KERNEL__ */
 
 #include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>
 
 #endif /* _M68KNOMMU_BITOPS_H */
diff --git a/arch/mips/include/asm/mach-ip27/topology.h b/arch/mips/include/asm/mach-ip27/topology.h
index 1fb959f98982..55d481569a1f 100644
--- a/arch/mips/include/asm/mach-ip27/topology.h
+++ b/arch/mips/include/asm/mach-ip27/topology.h
@@ -25,11 +25,13 @@ extern struct cpuinfo_ip27 sn_cpu_info[NR_CPUS];
 #define cpu_to_node(cpu)        (sn_cpu_info[(cpu)].p_nodeid)
 #define parent_node(node)       (node)
 #define node_to_cpumask(node)   (hub_data(node)->h_cpus)
-#define node_to_first_cpu(node) (first_cpu(node_to_cpumask(node)))
+#define cpumask_of_node(node)   (&hub_data(node)->h_cpus)
+#define node_to_first_cpu(node) (cpumask_first(cpumask_of_node(node)))
 struct pci_bus;
 extern int pcibus_to_node(struct pci_bus *);
 
 #define pcibus_to_cpumask(bus)  (cpu_online_map)
+#define cpumask_of_pcibus(bus)  (cpu_online_mask)
 
 extern unsigned char __node_distances[MAX_COMPACT_NODES][MAX_COMPACT_NODES];
 
diff --git a/arch/parisc/include/asm/smp.h b/arch/parisc/include/asm/smp.h
index 409e698f4361..6ef4b7867b1b 100644
--- a/arch/parisc/include/asm/smp.h
+++ b/arch/parisc/include/asm/smp.h
@@ -16,8 +16,6 @@
 #include <linux/cpumask.h>
 typedef unsigned long address_t;
 
-extern cpumask_t cpu_online_map;
-
 
 /*
  *      Private routines/data
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 373fca394a54..375258559ae6 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -22,11 +22,11 @@ static inline cpumask_t node_to_cpumask(int node)
         return numa_cpumask_lookup_table[node];
 }
 
+#define cpumask_of_node(node) (&numa_cpumask_lookup_table[node])
+
 static inline int node_to_first_cpu(int node)
 {
-        cpumask_t tmp;
-        tmp = node_to_cpumask(node);
-        return first_cpu(tmp);
+        return cpumask_first(cpumask_of_node(node));
 }
 
 int of_node_to_nid(struct device_node *device);
@@ -46,6 +46,10 @@ static inline int pcibus_to_node(struct pci_bus *bus)
                                         node_to_cpumask(pcibus_to_node(bus)) \
                                 )
 
+#define cpumask_of_pcibus(bus)  (pcibus_to_node(bus) == -1 ?            \
+                                 cpu_all_mask :                         \
+                                 cpumask_of_node(pcibus_to_node(bus)))
+
 /* sched_domains SD_NODE_INIT for PPC64 machines */
 #define SD_NODE_INIT (struct sched_domain) {            \
         .parent                 = NULL,                 \
@@ -108,6 +112,8 @@ static inline void sysfs_remove_device_from_node(struct sys_device *dev,
 
 #define topology_thread_siblings(cpu)   (per_cpu(cpu_sibling_map, cpu))
 #define topology_core_siblings(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_core_id(cpu)           (cpu_to_core_id(cpu))
 #endif
 #endif
diff --git a/arch/powerpc/platforms/cell/spu_priv1_mmio.c b/arch/powerpc/platforms/cell/spu_priv1_mmio.c
index 906a0a2a9fe1..1410443731eb 100644
--- a/arch/powerpc/platforms/cell/spu_priv1_mmio.c
+++ b/arch/powerpc/platforms/cell/spu_priv1_mmio.c
@@ -80,10 +80,10 @@ static void cpu_affinity_set(struct spu *spu, int cpu)
         u64 route;
 
         if (nr_cpus_node(spu->node)) {
-                cpumask_t spumask = node_to_cpumask(spu->node);
-                cpumask_t cpumask = node_to_cpumask(cpu_to_node(cpu));
+                const struct cpumask *spumask = cpumask_of_node(spu->node),
+                        *cpumask = cpumask_of_node(cpu_to_node(cpu));
 
-                if (!cpus_intersects(spumask, cpumask))
+                if (!cpumask_intersects(spumask, cpumask))
                         return;
         }
 
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 2ad914c47493..6a0ad196aeb3 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -166,9 +166,9 @@ void spu_update_sched_info(struct spu_context *ctx)
 static int __node_allowed(struct spu_context *ctx, int node)
 {
         if (nr_cpus_node(node)) {
-                cpumask_t mask = node_to_cpumask(node);
+                const struct cpumask *mask = cpumask_of_node(node);
 
-                if (cpus_intersects(mask, ctx->cpus_allowed))
+                if (cpumask_intersects(mask, &ctx->cpus_allowed))
                         return 1;
         }
 
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index d96c91643458..c93eb50e1d09 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -6,10 +6,12 @@
 #define mc_capable()    (1)
 
 cpumask_t cpu_coregroup_map(unsigned int cpu);
+const struct cpumask *cpu_coregroup_mask(unsigned int cpu);
 
 extern cpumask_t cpu_core_map[NR_CPUS];
 
 #define topology_core_siblings(cpu)     (cpu_core_map[cpu])
+#define topology_core_cpumask(cpu)      (&cpu_core_map[cpu])
 
 int topology_set_cpu_management(int fc);
 void topology_schedule_update(void);
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 90e9ba11eba1..cc362c9ea8f1 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -97,6 +97,11 @@ cpumask_t cpu_coregroup_map(unsigned int cpu)
         return mask;
 }
 
+const struct cpumask *cpu_coregroup_mask(unsigned int cpu)
+{
+        return &cpu_core_map[cpu];
+}
+
 static void add_cpus_to_core(struct tl_cpu *tl_cpu, struct core_info *core)
 {
         unsigned int cpu;
diff --git a/arch/sh/include/asm/topology.h b/arch/sh/include/asm/topology.h
index 279d9cc4a007..066f0fba590e 100644
--- a/arch/sh/include/asm/topology.h
+++ b/arch/sh/include/asm/topology.h
@@ -32,6 +32,7 @@
 #define parent_node(node)       ((void)(node),0)
 
 #define node_to_cpumask(node)   ((void)node, cpu_online_map)
+#define cpumask_of_node(node)   ((void)node, cpu_online_mask)
 #define node_to_first_cpu(node) ((void)(node),0)
 
 #define pcibus_to_node(bus)     ((void)(bus), -1)
diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h
index 001c04027c82..b8a65b64e1df 100644
--- a/arch/sparc/include/asm/topology_64.h
+++ b/arch/sparc/include/asm/topology_64.h
@@ -16,8 +16,12 @@ static inline cpumask_t node_to_cpumask(int node)
 {
         return numa_cpumask_lookup_table[node];
 }
+#define cpumask_of_node(node) (&numa_cpumask_lookup_table[node])
 
-/* Returns a pointer to the cpumask of CPUs on Node 'node'. */
+/*
+ * Returns a pointer to the cpumask of CPUs on Node 'node'.
+ * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)"
+ */
 #define node_to_cpumask_ptr(v, node)            \
                 cpumask_t *v = &(numa_cpumask_lookup_table[node])
 
@@ -26,9 +30,7 @@ static inline cpumask_t node_to_cpumask(int node)
 
 static inline int node_to_first_cpu(int node)
 {
-        cpumask_t tmp;
-        tmp = node_to_cpumask(node);
-        return first_cpu(tmp);
+        return cpumask_first(cpumask_of_node(node));
 }
 
 struct pci_bus;
@@ -77,10 +79,13 @@ static inline int pcibus_to_node(struct pci_bus *pbus)
 #define topology_core_id(cpu)                   (cpu_data(cpu).core_id)
 #define topology_core_siblings(cpu)             (cpu_core_map[cpu])
 #define topology_thread_siblings(cpu)           (per_cpu(cpu_sibling_map, cpu))
+#define topology_core_cpumask(cpu)              (&cpu_core_map[cpu])
+#define topology_thread_cpumask(cpu)            (&per_cpu(cpu_sibling_map, cpu))
 #define mc_capable()                            (sparc64_multi_core)
 #define smt_capable()                           (sparc64_multi_core)
 #endif /* CONFIG_SMP */
 
 #define cpu_coregroup_map(cpu)                  (cpu_core_map[cpu])
+#define cpu_coregroup_mask(cpu)                 (&cpu_core_map[cpu])
 
 #endif /* _ASM_SPARC64_TOPOLOGY_H */
diff --git a/arch/sparc/kernel/of_device_64.c b/arch/sparc/kernel/of_device_64.c
index 322046cdf85f..4873f28905b0 100644
--- a/arch/sparc/kernel/of_device_64.c
+++ b/arch/sparc/kernel/of_device_64.c
@@ -778,7 +778,7 @@ static unsigned int __init build_one_device_irq(struct of_device *op,
 out:
         nid = of_node_to_nid(dp);
         if (nid != -1) {
-                cpumask_t numa_mask = node_to_cpumask(nid);
+                cpumask_t numa_mask = *cpumask_of_node(nid);
 
                 irq_set_affinity(irq, &numa_mask);
         }
diff --git a/arch/sparc/kernel/pci_msi.c b/arch/sparc/kernel/pci_msi.c
index 0d0cd815e83e..4ef282e81912 100644
--- a/arch/sparc/kernel/pci_msi.c
+++ b/arch/sparc/kernel/pci_msi.c
@@ -286,7 +286,7 @@ static int bringup_one_msi_queue(struct pci_pbm_info *pbm,
 
         nid = pbm->numa_node;
         if (nid != -1) {
-                cpumask_t numa_mask = node_to_cpumask(nid);
+                cpumask_t numa_mask = *cpumask_of_node(nid);
 
                 irq_set_affinity(irq, &numa_mask);
         }
diff --git a/arch/x86/include/asm/es7000/apic.h b/arch/x86/include/asm/es7000/apic.h
index 51ac1230294e..bc53d5ef1386 100644
--- a/arch/x86/include/asm/es7000/apic.h
+++ b/arch/x86/include/asm/es7000/apic.h
@@ -157,7 +157,7 @@ cpu_mask_to_apicid_cluster(const struct cpumask *cpumask)
 
         num_bits_set = cpumask_weight(cpumask);
         /* Return id to all */
-        if (num_bits_set == NR_CPUS)
+        if (num_bits_set == nr_cpu_ids)
                 return 0xFF;
         /*
          * The cpus in the mask must all be on the apic cluster.  If are not
@@ -190,7 +190,7 @@ static inline unsigned int cpu_mask_to_apicid(const cpumask_t *cpumask)
 
         num_bits_set = cpus_weight(*cpumask);
         /* Return id to all */
-        if (num_bits_set == NR_CPUS)
+        if (num_bits_set == nr_cpu_ids)
                 return cpu_to_logical_apicid(0);
         /*
          * The cpus in the mask must all be on the apic cluster.  If are not
@@ -218,9 +218,6 @@ static inline unsigned int cpu_mask_to_apicid(const cpumask_t *cpumask)
 static inline unsigned int cpu_mask_to_apicid_and(const struct cpumask *inmask,
                                                   const struct cpumask *andmask)
 {
-        int num_bits_set;
-        int cpus_found = 0;
-        int cpu;
         int apicid = cpu_to_logical_apicid(0);
         cpumask_var_t cpumask;
 
@@ -229,31 +226,8 @@ static inline unsigned int cpu_mask_to_apicid_and(const struct cpumask *inmask,
 
         cpumask_and(cpumask, inmask, andmask);
         cpumask_and(cpumask, cpumask, cpu_online_mask);
+        apicid = cpu_mask_to_apicid(cpumask);
 
-        num_bits_set = cpumask_weight(cpumask);
-        /* Return id to all */
-        if (num_bits_set == NR_CPUS)
-                goto exit;
-        /*
-         * The cpus in the mask must all be on the apic cluster.  If are not
-         * on the same apicid cluster return default value of TARGET_CPUS.
-         */
-        cpu = cpumask_first(cpumask);
-        apicid = cpu_to_logical_apicid(cpu);
-        while (cpus_found < num_bits_set) {
-                if (cpumask_test_cpu(cpu, cpumask)) {
-                        int new_apicid = cpu_to_logical_apicid(cpu);
-                        if (apicid_cluster(apicid) !=
-                                        apicid_cluster(new_apicid)){
-                                printk ("%s: Not a valid mask!\n", __func__);
-                                return cpu_to_logical_apicid(0);
-                        }
-                        apicid = new_apicid;
-                        cpus_found++;
-                }
-                cpu++;
-        }
-exit:
         free_cpumask_var(cpumask);
         return apicid;
 }
diff --git a/arch/x86/include/asm/lguest.h b/arch/x86/include/asm/lguest.h
index d28a507cef39..1caf57628b9c 100644
--- a/arch/x86/include/asm/lguest.h
+++ b/arch/x86/include/asm/lguest.h
@@ -15,7 +15,7 @@
 #define SHARED_SWITCHER_PAGES \
         DIV_ROUND_UP(end_switcher_text - start_switcher_text, PAGE_SIZE)
 /* Pages for switcher itself, then two pages per cpu */
-#define TOTAL_SWITCHER_PAGES (SHARED_SWITCHER_PAGES + 2 * NR_CPUS)
+#define TOTAL_SWITCHER_PAGES (SHARED_SWITCHER_PAGES + 2 * nr_cpu_ids)
 
 /* We map at -4M for ease of mapping into the guest (one PTE page). */
 #define SWITCHER_ADDR 0xFFC00000
diff --git a/arch/x86/include/asm/numaq/apic.h b/arch/x86/include/asm/numaq/apic.h
index c80f00d29965..bf37bc49bd8e 100644
--- a/arch/x86/include/asm/numaq/apic.h
+++ b/arch/x86/include/asm/numaq/apic.h
@@ -63,8 +63,8 @@ static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
 extern u8 cpu_2_logical_apicid[];
 static inline int cpu_to_logical_apicid(int cpu)
 {
-       if (cpu >= NR_CPUS)
-               return BAD_APICID;
+        if (cpu >= nr_cpu_ids)
+                return BAD_APICID;
         return (int)cpu_2_logical_apicid[cpu];
 }
 
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 66834c41c049..a977de23cb4d 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -102,9 +102,9 @@ extern void pci_iommu_alloc(void);
 
 #ifdef CONFIG_NUMA
 /* Returns the node based on pci bus */
-static inline int __pcibus_to_node(struct pci_bus *bus)
+static inline int __pcibus_to_node(const struct pci_bus *bus)
 {
-        struct pci_sysdata *sd = bus->sysdata;
+        const struct pci_sysdata *sd = bus->sysdata;
 
         return sd->node;
 }
@@ -113,6 +113,12 @@ 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)
+{
+        return cpumask_of_node(__pcibus_to_node(bus));
+}
 #endif
 
 #endif /* _ASM_X86_PCI_H */
diff --git a/arch/x86/include/asm/summit/apic.h b/arch/x86/include/asm/summit/apic.h
index 99327d1be49f..4bb5fb34f030 100644
--- a/arch/x86/include/asm/summit/apic.h
+++ b/arch/x86/include/asm/summit/apic.h
@@ -52,7 +52,7 @@ static inline void init_apic_ldr(void)
         int i;
 
         /* Create logical APIC IDs by counting CPUs already in cluster. */
-        for (count = 0, i = NR_CPUS; --i >= 0; ) {
+        for (count = 0, i = nr_cpu_ids; --i >= 0; ) {
                 lid = cpu_2_logical_apicid[i];
                 if (lid != BAD_APICID && apicid_cluster(lid) == my_cluster)
                         ++count;
@@ -97,8 +97,8 @@ static inline int apicid_to_node(int logical_apicid)
 static inline int cpu_to_logical_apicid(int cpu)
 {
 #ifdef CONFIG_SMP
-       if (cpu >= NR_CPUS)
-               return BAD_APICID;
+        if (cpu >= nr_cpu_ids)
+                return BAD_APICID;
         return (int)cpu_2_logical_apicid[cpu];
 #else
         return logical_smp_processor_id();
@@ -107,7 +107,7 @@ static inline int cpu_to_logical_apicid(int cpu)
 
 static inline int cpu_present_to_apicid(int mps_cpu)
 {
-        if (mps_cpu < NR_CPUS)
+        if (mps_cpu < nr_cpu_ids)
                 return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu);
         else
                 return BAD_APICID;
@@ -146,7 +146,7 @@ static inline unsigned int cpu_mask_to_apicid(const cpumask_t *cpumask)
 
         num_bits_set = cpus_weight(*cpumask);
         /* Return id to all */
-        if (num_bits_set == NR_CPUS)
+        if (num_bits_set >= nr_cpu_ids)
                 return (int) 0xFF;
         /*
          * The cpus in the mask must all be on the apic cluster.  If are not
@@ -173,42 +173,16 @@ static inline unsigned int cpu_mask_to_apicid(const cpumask_t *cpumask)
 static inline unsigned int cpu_mask_to_apicid_and(const struct cpumask *inmask,
                                                   const struct cpumask *andmask)
 {
-        int num_bits_set;
-        int cpus_found = 0;
-        int cpu;
-        int apicid = 0xFF;
+        int apicid = cpu_to_logical_apicid(0);
         cpumask_var_t cpumask;
 
         if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC))
-                return (int) 0xFF;
+                return apicid;
 
         cpumask_and(cpumask, inmask, andmask);
         cpumask_and(cpumask, cpumask, cpu_online_mask);
+        apicid = cpu_mask_to_apicid(cpumask);
 
-        num_bits_set = cpumask_weight(cpumask);
-        /* Return id to all */
-        if (num_bits_set == nr_cpu_ids)
-                goto exit;
-        /*
-         * The cpus in the mask must all be on the apic cluster.  If are not
-         * on the same apicid cluster return default value of TARGET_CPUS.
-         */
-        cpu = cpumask_first(cpumask);
-        apicid = cpu_to_logical_apicid(cpu);
-        while (cpus_found < num_bits_set) {
-                if (cpumask_test_cpu(cpu, cpumask)) {
-                        int new_apicid = cpu_to_logical_apicid(cpu);
-                        if (apicid_cluster(apicid) !=
-                                        apicid_cluster(new_apicid)){
-                                printk ("%s: Not a valid mask!\n", __func__);
-                                return 0xFF;
-                        }
-                        apicid = apicid | new_apicid;
-                        cpus_found++;
-                }
-                cpu++;
-        }
-exit:
         free_cpumask_var(cpumask);
         return apicid;
 }
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 79e31e9dcdda..4e2f2e0aab27 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -61,13 +61,19 @@ static inline int cpu_to_node(int cpu)
  *
  * 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_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];
+}
+
 #else /* CONFIG_X86_64 */
 
 /* Mappings between node number and cpus on that node. */
@@ -82,7 +88,7 @@ DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);
 #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 *_node_to_cpumask_ptr(int node);
+extern const cpumask_t *cpumask_of_node(int node);
 extern cpumask_t node_to_cpumask(int node);
 
 #else   /* !CONFIG_DEBUG_PER_CPU_MAPS */
@@ -103,7 +109,7 @@ static inline int early_cpu_to_node(int cpu)
 }
 
 /* Returns a pointer to the cpumask of CPUs on Node 'node'. */
-static inline const cpumask_t *_node_to_cpumask_ptr(int node)
+static inline const cpumask_t *cpumask_of_node(int node)
 {
         return &node_to_cpumask_map[node];
 }
@@ -116,12 +122,15 @@ static inline cpumask_t node_to_cpumask(int node)
 
 #endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
 
-/* Replace default node_to_cpumask_ptr with optimized version */
+/*
+ * 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 = _node_to_cpumask_ptr(node)
+                const cpumask_t *v = cpumask_of_node(node)
 
 #define node_to_cpumask_ptr_next(v, node)       \
-                           v = _node_to_cpumask_ptr(node)
+                           v = cpumask_of_node(node)
 
 #endif /* CONFIG_X86_64 */
 
@@ -187,7 +196,7 @@ extern int __node_distance(int, int);
 #define cpu_to_node(cpu)        0
 #define early_cpu_to_node(cpu)  0
 
-static inline const cpumask_t *_node_to_cpumask_ptr(int node)
+static inline const cpumask_t *cpumask_of_node(int node)
 {
         return &cpu_online_map;
 }
@@ -200,12 +209,15 @@ static inline int node_to_first_cpu(int node)
         return first_cpu(cpu_online_map);
 }
 
-/* Replace default node_to_cpumask_ptr with optimized version */
+/*
+ * 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 = _node_to_cpumask_ptr(node)
+                const cpumask_t *v = cpumask_of_node(node)
 
 #define node_to_cpumask_ptr_next(v, node)       \
-                           v = _node_to_cpumask_ptr(node)
+                           v = cpumask_of_node(node)
 #endif
 
 #include <asm-generic/topology.h>
@@ -214,12 +226,12 @@ static inline int node_to_first_cpu(int node)
 /* Returns the number of the first CPU on Node 'node'. */
 static inline int node_to_first_cpu(int node)
 {
-        node_to_cpumask_ptr(mask, node);
-        return first_cpu(*mask);
+        return cpumask_first(cpumask_of_node(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)
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 65d0b72777ea..29dc0c89d4af 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -538,9 +538,10 @@ static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu)
         struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
         union acpi_object *obj;
         struct acpi_madt_local_apic *lapic;
-        cpumask_t tmp_map, new_map;
+        cpumask_var_t tmp_map, new_map;
         u8 physid;
         int cpu;
+        int retval = -ENOMEM;
 
         if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer)))
                 return -EINVAL;
@@ -569,23 +570,37 @@ static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu)
         buffer.length = ACPI_ALLOCATE_BUFFER;
         buffer.pointer = NULL;
 
-        tmp_map = cpu_present_map;
+        if (!alloc_cpumask_var(&tmp_map, GFP_KERNEL))
+                goto out;
+
+        if (!alloc_cpumask_var(&new_map, GFP_KERNEL))
+                goto free_tmp_map;
+
+        cpumask_copy(tmp_map, cpu_present_mask);
         acpi_register_lapic(physid, lapic->lapic_flags & ACPI_MADT_ENABLED);
 
         /*
          * If mp_register_lapic successfully generates a new logical cpu
          * number, then the following will get us exactly what was mapped
          */
-        cpus_andnot(new_map, cpu_present_map, tmp_map);
-        if (cpus_empty(new_map)) {
+        cpumask_andnot(new_map, cpu_present_mask, tmp_map);
+        if (cpumask_empty(new_map)) {
                 printk ("Unable to map lapic to logical cpu number\n");
-                return -EINVAL;
+                retval = -EINVAL;
+                goto free_new_map;
         }
 
-        cpu = first_cpu(new_map);
+        cpu = cpumask_first(new_map);
 
         *pcpu = cpu;
-        return 0;
+        retval = 0;
+
+free_new_map:
+        free_cpumask_var(new_map);
+free_tmp_map:
+        free_cpumask_var(tmp_map);
+out:
+        return retval;
 }
 
 /* wrapper to silence section mismatch warning */
@@ -598,7 +613,7 @@ EXPORT_SYMBOL(acpi_map_lsapic);
 int acpi_unmap_lsapic(int cpu)
 {
         per_cpu(x86_cpu_to_apicid, cpu) = -1;
-        cpu_clear(cpu, cpu_present_map);
+        set_cpu_present(cpu, false);
         num_processors--;
 
         return (0);
diff --git a/arch/x86/kernel/apic.c b/arch/x86/kernel/apic.c
index d652515e2855..b13d3c4dbd42 100644
--- a/arch/x86/kernel/apic.c
+++ b/arch/x86/kernel/apic.c
@@ -140,7 +140,7 @@ static int lapic_next_event(unsigned long delta,
                             struct clock_event_device *evt);
 static void lapic_timer_setup(enum clock_event_mode mode,
                               struct clock_event_device *evt);
-static void lapic_timer_broadcast(const cpumask_t *mask);
+static void lapic_timer_broadcast(const struct cpumask *mask);
 static void apic_pm_activate(void);
 
 /*
@@ -453,7 +453,7 @@ static void lapic_timer_setup(enum clock_event_mode mode,
 /*
  * Local APIC timer broadcast function
  */
-static void lapic_timer_broadcast(const cpumask_t *mask)
+static void lapic_timer_broadcast(const struct cpumask *mask)
 {
 #ifdef CONFIG_SMP
         send_IPI_mask(mask, LOCAL_TIMER_VECTOR);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 42e0853030cb..3f95a40f718a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -355,7 +355,7 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c)
                 printk(KERN_INFO  "CPU: Hyper-Threading is disabled\n");
         } else if (smp_num_siblings > 1) {
 
-                if (smp_num_siblings > NR_CPUS) {
+                if (smp_num_siblings > nr_cpu_ids) {
                         printk(KERN_WARNING "CPU: Unsupported number of siblings %d",
                                         smp_num_siblings);
                         smp_num_siblings = 1;
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 88ea02dcb622..28102ad1a363 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -517,6 +517,17 @@ acpi_cpufreq_guess_freq(struct acpi_cpufreq_data *data, unsigned int cpu)
         }
 }
 
+static void free_acpi_perf_data(void)
+{
+        unsigned int i;
+
+        /* Freeing a NULL pointer is OK, and alloc_percpu zeroes. */
+        for_each_possible_cpu(i)
+                free_cpumask_var(per_cpu_ptr(acpi_perf_data, i)
+                                 ->shared_cpu_map);
+        free_percpu(acpi_perf_data);
+}
+
 /*
  * acpi_cpufreq_early_init - initialize ACPI P-States library
  *
@@ -527,6 +538,7 @@ acpi_cpufreq_guess_freq(struct acpi_cpufreq_data *data, unsigned int cpu)
  */
 static int __init acpi_cpufreq_early_init(void)
 {
+        unsigned int i;
         dprintk("acpi_cpufreq_early_init\n");
 
         acpi_perf_data = alloc_percpu(struct acpi_processor_performance);
@@ -534,6 +546,16 @@ static int __init acpi_cpufreq_early_init(void)
                 dprintk("Memory allocation error for acpi_perf_data.\n");
                 return -ENOMEM;
         }
+        for_each_possible_cpu(i) {
+                if (!alloc_cpumask_var_node(
+                        &per_cpu_ptr(acpi_perf_data, i)->shared_cpu_map,
+                        GFP_KERNEL, cpu_to_node(i))) {
+
+                        /* Freeing a NULL pointer is OK: alloc_percpu zeroes. */
+                        free_acpi_perf_data();
+                        return -ENOMEM;
+                }
+        }
 
         /* Do initialization in ACPI core */
         acpi_processor_preregister_performance(acpi_perf_data);
@@ -604,9 +626,9 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
          */
         if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL ||
             policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) {
-                policy->cpus = perf->shared_cpu_map;
+                cpumask_copy(&policy->cpus, perf->shared_cpu_map);
         }
-        policy->related_cpus = perf->shared_cpu_map;
+        cpumask_copy(&policy->related_cpus, perf->shared_cpu_map);
 
 #ifdef CONFIG_SMP
         dmi_check_system(sw_any_bug_dmi_table);
@@ -795,7 +817,7 @@ static int __init acpi_cpufreq_init(void)
 
         ret = cpufreq_register_driver(&acpi_cpufreq_driver);
         if (ret)
-                free_percpu(acpi_perf_data);
+                free_acpi_perf_data();
 
         return ret;
 }
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
index 7c7d56b43136..1b446d79a8fd 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
@@ -310,6 +310,12 @@ static int powernow_acpi_init(void)
                 goto err0;
         }
 
+        if (!alloc_cpumask_var(&acpi_processor_perf->shared_cpu_map,
+                                                                GFP_KERNEL)) {
+                retval = -ENOMEM;
+                goto err05;
+        }
+
         if (acpi_processor_register_performance(acpi_processor_perf, 0)) {
                 retval = -EIO;
                 goto err1;
@@ -412,6 +418,8 @@ static int powernow_acpi_init(void)
 err2:
         acpi_processor_unregister_performance(acpi_processor_perf, 0);
 err1:
+        free_cpumask_var(acpi_processor_perf->shared_cpu_map);
+err05:
         kfree(acpi_processor_perf);
 err0:
         printk(KERN_WARNING PFX "ACPI perflib can not be used in this platform\n");
@@ -652,6 +660,7 @@ static int powernow_cpu_exit (struct cpufreq_policy *policy) {
 #ifdef CONFIG_X86_POWERNOW_K7_ACPI
         if (acpi_processor_perf) {
                 acpi_processor_unregister_performance(acpi_processor_perf, 0);
+                free_cpumask_var(acpi_processor_perf->shared_cpu_map);
                 kfree(acpi_processor_perf);
         }
 #endif
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 7f05f44b97e9..c3c9adbaa26f 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -766,7 +766,7 @@ static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned
 static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 {
         struct cpufreq_frequency_table *powernow_table;
-        int ret_val;
+        int ret_val = -ENODEV;
 
         if (acpi_processor_register_performance(&data->acpi_data, data->cpu)) {
                 dprintk("register performance failed: bad ACPI data\n");
@@ -815,6 +815,13 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
         /* notify BIOS that we exist */
         acpi_processor_notify_smm(THIS_MODULE);
 
+        if (!alloc_cpumask_var(&data->acpi_data.shared_cpu_map, GFP_KERNEL)) {
+                printk(KERN_ERR PFX
+                                "unable to alloc powernow_k8_data cpumask\n");
+                ret_val = -ENOMEM;
+                goto err_out_mem;
+        }
+
         return 0;
 
 err_out_mem:
@@ -826,7 +833,7 @@ err_out:
         /* data->acpi_data.state_count informs us at ->exit() whether ACPI was used */
         data->acpi_data.state_count = 0;
 
-        return -ENODEV;
+        return ret_val;
 }
 
 static int fill_powernow_table_pstate(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table)
@@ -929,6 +936,7 @@ static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data)
 {
         if (data->acpi_data.state_count)
                 acpi_processor_unregister_performance(&data->acpi_data, data->cpu);
+        free_cpumask_var(data->acpi_data.shared_cpu_map);
 }
 
 #else
@@ -1134,7 +1142,8 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
         data->cpu = pol->cpu;
         data->currpstate = HW_PSTATE_INVALID;
 
-        if (powernow_k8_cpu_init_acpi(data)) {
+        rc = powernow_k8_cpu_init_acpi(data);
+        if (rc) {
                 /*
                  * Use the PSB BIOS structure. This is only availabe on
                  * an UP version, and is deprecated by AMD.
@@ -1152,20 +1161,17 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
                                "ACPI maintainers and complain to your BIOS "
                                "vendor.\n");
 #endif
-                        kfree(data);
-                        return -ENODEV;
+                        goto err_out;
                 }
                 if (pol->cpu != 0) {
                         printk(KERN_ERR FW_BUG PFX "No ACPI _PSS objects for "
                                "CPU other than CPU0. Complain to your BIOS "
                                "vendor.\n");
-                        kfree(data);
-                        return -ENODEV;
+                        goto err_out;
                 }
                 rc = find_psb_table(data);
                 if (rc) {
-                        kfree(data);
-                        return -ENODEV;
+                        goto err_out;
                 }
         }
 
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index c6ecda64f5f1..48533d77be78 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -534,7 +534,7 @@ static void __cpuinit free_cache_attributes(unsigned int cpu)
         per_cpu(cpuid4_info, cpu) = NULL;
 }
 
-static void get_cpu_leaves(void *_retval)
+static void __cpuinit get_cpu_leaves(void *_retval)
 {
         int j, *retval = _retval, cpu = smp_processor_id();
 
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 85d28d53f5d3..2ac1f0c2beb3 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -121,7 +121,7 @@ static int cpuid_open(struct inode *inode, struct file *file)
         lock_kernel();
 
         cpu = iminor(file->f_path.dentry->d_inode);
-        if (cpu >= NR_CPUS || !cpu_online(cpu)) {
+        if (cpu >= nr_cpu_ids || !cpu_online(cpu)) {
                 ret = -ENXIO;   /* No such CPU */
                 goto out;
         }
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index 69911722b9d3..3639442aa7a4 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -214,11 +214,11 @@ static struct irq_cfg *get_one_free_irq_cfg(int cpu)
 
         cfg = kzalloc_node(sizeof(*cfg), GFP_ATOMIC, node);
         if (cfg) {
-                /* FIXME: needs alloc_cpumask_var_node() */
-                if (!alloc_cpumask_var(&cfg->domain, GFP_ATOMIC)) {
+                if (!alloc_cpumask_var_node(&cfg->domain, GFP_ATOMIC, node)) {
                         kfree(cfg);
                         cfg = NULL;
-                } else if (!alloc_cpumask_var(&cfg->old_domain, GFP_ATOMIC)) {
+                } else if (!alloc_cpumask_var_node(&cfg->old_domain,
+                                                          GFP_ATOMIC, node)) {
                         free_cpumask_var(cfg->domain);
                         kfree(cfg);
                         cfg = NULL;
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 82a7c7ed6d45..726266695b2c 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -136,7 +136,7 @@ static int msr_open(struct inode *inode, struct file *file)
         lock_kernel();
         cpu = iminor(file->f_path.dentry->d_inode);
 
-        if (cpu >= NR_CPUS || !cpu_online(cpu)) {
+        if (cpu >= nr_cpu_ids || !cpu_online(cpu)) {
                 ret = -ENXIO;   /* No such CPU */
                 goto out;
         }
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index bf088c61fa40..2b46eb41643b 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -501,7 +501,7 @@ void native_machine_shutdown(void)
 
 #ifdef CONFIG_X86_32
         /* See if there has been given a command line override */
-        if ((reboot_cpu != -1) && (reboot_cpu < NR_CPUS) &&
+        if ((reboot_cpu != -1) && (reboot_cpu < nr_cpu_ids) &&
                 cpu_online(reboot_cpu))
                 reboot_cpu_id = reboot_cpu;
 #endif
@@ -511,7 +511,7 @@ void native_machine_shutdown(void)
                 reboot_cpu_id = smp_processor_id();
 
         /* Make certain I only run on the appropriate processor */
-        set_cpus_allowed_ptr(current, &cpumask_of_cpu(reboot_cpu_id));
+        set_cpus_allowed_ptr(current, cpumask_of(reboot_cpu_id));
 
         /* O.K Now that I'm on the appropriate processor,
          * stop all of the others.
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 0b63b08e7530..a4b619c33106 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -153,12 +153,10 @@ void __init setup_per_cpu_areas(void)
         align = max_t(unsigned long, PAGE_SIZE, align);
         size = roundup(old_size, align);
 
-        printk(KERN_INFO
-                "NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%d nr_node_ids:%d\n",
+        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);
 
-        printk(KERN_INFO "PERCPU: Allocating %zd bytes of per cpu data\n",
-                          size);
+        pr_info("PERCPU: Allocating %zd bytes of per cpu data\n", size);
 
         for_each_possible_cpu(cpu) {
 #ifndef CONFIG_NEED_MULTIPLE_NODES
@@ -169,22 +167,15 @@ void __init setup_per_cpu_areas(void)
                 if (!node_online(node) || !NODE_DATA(node)) {
                         ptr = __alloc_bootmem(size, align,
                                          __pa(MAX_DMA_ADDRESS));
-                        printk(KERN_INFO
-                               "cpu %d has no node %d or node-local memory\n",
+                        pr_info("cpu %d has no node %d or node-local memory\n",
                                 cpu, node);
-                        if (ptr)
-                                printk(KERN_DEBUG
-                                        "per cpu data for cpu%d at %016lx\n",
-                                         cpu, __pa(ptr));
-                }
-                else {
+                        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));
-                        if (ptr)
-                                printk(KERN_DEBUG
-                                        "per cpu data for cpu%d on node%d "
-                                        "at %016lx\n",
-                                        cpu, node, __pa(ptr));
+                        pr_debug("per cpu data for cpu%d on node%d at %016lx\n",
+                                cpu, node, __pa(ptr));
                 }
 #endif
                 per_cpu_offset(cpu) = ptr - __per_cpu_start;
@@ -339,25 +330,25 @@ static const cpumask_t cpu_mask_none;
 /*
  * Returns a pointer to the bitmask of CPUs on Node 'node'.
  */
-const cpumask_t *_node_to_cpumask_ptr(int node)
+const cpumask_t *cpumask_of_node(int node)
 {
         if (node_to_cpumask_map == NULL) {
                 printk(KERN_WARNING
-                        "_node_to_cpumask_ptr(%d): no node_to_cpumask_map!\n",
+                        "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
-                        "_node_to_cpumask_ptr(%d): node > nr_node_ids(%d)\n",
+                        "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(_node_to_cpumask_ptr);
+EXPORT_SYMBOL(cpumask_of_node);
 
 /*
  * Returns a bitmask of CPUs on Node 'node'.
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 31869bf5fabd..6bd4d9b73870 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -496,7 +496,7 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 }
 
 /* maps the cpu to the sched domain representing multi-core */
-cpumask_t cpu_coregroup_map(int cpu)
+const struct cpumask *cpu_coregroup_mask(int cpu)
 {
         struct cpuinfo_x86 *c = &cpu_data(cpu);
         /*
@@ -504,9 +504,14 @@ cpumask_t cpu_coregroup_map(int cpu)
          * And for power savings, we return cpu_core_map
          */
         if (sched_mc_power_savings || sched_smt_power_savings)
-                return per_cpu(cpu_core_map, cpu);
+                return &per_cpu(cpu_core_map, cpu);
         else
-                return c->llc_shared_map;
+                return &c->llc_shared_map;
+}
+
+cpumask_t cpu_coregroup_map(int cpu)
+{
+        return *cpu_coregroup_mask(cpu);
 }
 
 static void impress_friends(void)
@@ -1149,7 +1154,7 @@ static void __init smp_cpu_index_default(void)
         for_each_possible_cpu(i) {
                 c = &cpu_data(i);
                 /* mark all to hotplug */
-                c->cpu_index = NR_CPUS;
+                c->cpu_index = nr_cpu_ids;
         }
 }
 
@@ -1293,6 +1298,8 @@ __init void prefill_possible_map(void)
         else
                 possible = setup_possible_cpus;
 
+        total_cpus = max_t(int, possible, num_processors + disabled_cpus);
+
         if (possible > CONFIG_NR_CPUS) {
                 printk(KERN_WARNING
                         "%d Processors exceeds NR_CPUS limit of %d\n",
diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c
index a5bc05492b1e..9840b7ec749a 100644
--- a/arch/x86/mach-voyager/voyager_smp.c
+++ b/arch/x86/mach-voyager/voyager_smp.c
@@ -357,9 +357,8 @@ void __init find_smp_config(void)
         printk("VOYAGER SMP: Boot cpu is %d\n", boot_cpu_id);
 
         /* initialize the CPU structures (moved from smp_boot_cpus) */
-        for (i = 0; i < NR_CPUS; i++) {
+        for (i = 0; i < nr_cpu_ids; i++)
                 cpu_irq_affinity[i] = ~0;
-        }
         cpu_online_map = cpumask_of_cpu(boot_cpu_id);
 
         /* The boot CPU must be extended */
@@ -1227,7 +1226,7 @@ int setup_profiling_timer(unsigned int multiplier)
          * new values until the next timer interrupt in which they do process
          * accounting.
          */
-        for (i = 0; i < NR_CPUS; ++i)
+        for (i = 0; i < nr_cpu_ids; ++i)
                 per_cpu(prof_multiplier, i) = multiplier;
 
         return 0;
@@ -1257,7 +1256,7 @@ void __init voyager_smp_intr_init(void)
         int i;
 
         /* initialize the per cpu irq mask to all disabled */
-        for (i = 0; i < NR_CPUS; i++)
+        for (i = 0; i < nr_cpu_ids; i++)
                 vic_irq_mask[i] = 0xFFFF;
 
         VIC_SET_GATE(VIC_CPI_LEVEL0, vic_cpi_interrupt);