Merge git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus

* git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus: (39 commits)
  cpumask: Move deprecated functions to end of header.
  cpumask: remove unused deprecated functions, avoid accusations of insanity
  cpumask: use new-style cpumask ops in mm/quicklist.
  cpumask: use mm_cpumask() wrapper: x86
  cpumask: use mm_cpumask() wrapper: um
  cpumask: use mm_cpumask() wrapper: mips
  cpumask: use mm_cpumask() wrapper: mn10300
  cpumask: use mm_cpumask() wrapper: m32r
  cpumask: use mm_cpumask() wrapper: arm
  cpumask: Use accessors for cpu_*_mask: um
  cpumask: Use accessors for cpu_*_mask: powerpc
  cpumask: Use accessors for cpu_*_mask: mips
  cpumask: Use accessors for cpu_*_mask: m32r
  cpumask: remove arch_send_call_function_ipi
  cpumask: arch_send_call_function_ipi_mask: s390
  cpumask: arch_send_call_function_ipi_mask: powerpc
  cpumask: arch_send_call_function_ipi_mask: mips
  cpumask: arch_send_call_function_ipi_mask: m32r
  cpumask: arch_send_call_function_ipi_mask: alpha
  cpumask: remove obsolete topology_core_siblings and topology_thread_siblings: ia64
  ...
diff --git a/arch/alpha/include/asm/smp.h b/arch/alpha/include/asm/smp.h
index 547e909..3f390e8 100644
--- a/arch/alpha/include/asm/smp.h
+++ b/arch/alpha/include/asm/smp.h
@@ -47,7 +47,7 @@
 extern int smp_num_cpus;
 
 extern void arch_send_call_function_single_ipi(int cpu);
-extern void arch_send_call_function_ipi(cpumask_t mask);
+extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
 #else /* CONFIG_SMP */
 
diff --git a/arch/alpha/include/asm/topology.h b/arch/alpha/include/asm/topology.h
index b4f284c..36b3a30 100644
--- a/arch/alpha/include/asm/topology.h
+++ b/arch/alpha/include/asm/topology.h
@@ -22,23 +22,6 @@
 	return node;
 }
 
-static inline cpumask_t node_to_cpumask(int node)
-{
-	cpumask_t node_cpu_mask = CPU_MASK_NONE;
-	int cpu;
-
-	for_each_online_cpu(cpu) {
-		if (cpu_to_node(cpu) == node)
-			cpu_set(cpu, node_cpu_mask);
-	}
-
-#ifdef DEBUG_NUMA
-	printk("node %d: cpu_mask: %016lx\n", node, node_cpu_mask);
-#endif
-
-	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)
@@ -55,7 +38,6 @@
 	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 */
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index b1fe567..42aa078 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -548,16 +548,16 @@
 
 
 static void
-send_ipi_message(cpumask_t to_whom, enum ipi_message_type operation)
+send_ipi_message(const struct cpumask *to_whom, enum ipi_message_type operation)
 {
 	int i;
 
 	mb();
-	for_each_cpu_mask(i, to_whom)
+	for_each_cpu(i, to_whom)
 		set_bit(operation, &ipi_data[i].bits);
 
 	mb();
-	for_each_cpu_mask(i, to_whom)
+	for_each_cpu(i, to_whom)
 		wripir(i);
 }
 
@@ -624,7 +624,7 @@
 		printk(KERN_WARNING
 		       "smp_send_reschedule: Sending IPI to self.\n");
 #endif
-	send_ipi_message(cpumask_of_cpu(cpu), IPI_RESCHEDULE);
+	send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
 }
 
 void
@@ -636,17 +636,17 @@
 	if (hard_smp_processor_id() != boot_cpu_id)
 		printk(KERN_WARNING "smp_send_stop: Not on boot cpu.\n");
 #endif
-	send_ipi_message(to_whom, IPI_CPU_STOP);
+	send_ipi_message(&to_whom, IPI_CPU_STOP);
 }
 
-void arch_send_call_function_ipi(cpumask_t mask)
+void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
 	send_ipi_message(mask, IPI_CALL_FUNC);
 }
 
 void arch_send_call_function_single_ipi(int cpu)
 {
-	send_ipi_message(cpumask_of_cpu(cpu), IPI_CALL_FUNC_SINGLE);
+	send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
 }
 
 static void
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 1a711ea..fd03fb6 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -334,14 +334,14 @@
 #ifndef CONFIG_CPU_CACHE_VIPT
 static inline void flush_cache_mm(struct mm_struct *mm)
 {
-	if (cpu_isset(smp_processor_id(), mm->cpu_vm_mask))
+	if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm)))
 		__cpuc_flush_user_all();
 }
 
 static inline void
 flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
 {
-	if (cpu_isset(smp_processor_id(), vma->vm_mm->cpu_vm_mask))
+	if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm)))
 		__cpuc_flush_user_range(start & PAGE_MASK, PAGE_ALIGN(end),
 					vma->vm_flags);
 }
@@ -349,7 +349,7 @@
 static inline void
 flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsigned long pfn)
 {
-	if (cpu_isset(smp_processor_id(), vma->vm_mm->cpu_vm_mask)) {
+	if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
 		unsigned long addr = user_addr & PAGE_MASK;
 		__cpuc_flush_user_range(addr, addr + PAGE_SIZE, vma->vm_flags);
 	}
@@ -360,7 +360,7 @@
 			 unsigned long uaddr, void *kaddr,
 			 unsigned long len, int write)
 {
-	if (cpu_isset(smp_processor_id(), vma->vm_mm->cpu_vm_mask)) {
+	if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
 		unsigned long addr = (unsigned long)kaddr;
 		__cpuc_coherent_kern_range(addr, addr + len);
 	}
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index bcdb929..de6cefb 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -103,14 +103,15 @@
 
 #ifdef CONFIG_SMP
 	/* check for possible thread migration */
-	if (!cpus_empty(next->cpu_vm_mask) && !cpu_isset(cpu, next->cpu_vm_mask))
+	if (!cpumask_empty(mm_cpumask(next)) &&
+	    !cpumask_test_cpu(cpu, mm_cpumask(next)))
 		__flush_icache_all();
 #endif
-	if (!cpu_test_and_set(cpu, next->cpu_vm_mask) || prev != next) {
+	if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next) {
 		check_context(next);
 		cpu_switch_mm(next->pgd, next);
 		if (cache_is_vivt())
-			cpu_clear(cpu, prev->cpu_vm_mask);
+			cpumask_clear_cpu(cpu, mm_cpumask(prev));
 	}
 #endif
 }
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index a06e735..e0d763b 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -93,7 +93,6 @@
 
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
-#define arch_send_call_function_ipi_mask arch_send_call_function_ipi_mask
 
 /*
  * show local interrupt info
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index c964f3f..a45ab5d 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -350,7 +350,7 @@
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	if (cpu_isset(smp_processor_id(), mm->cpu_vm_mask)) {
+	if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) {
 		if (tlb_flag(TLB_V3_FULL))
 			asm("mcr p15, 0, %0, c6, c0, 0" : : "r" (zero) : "cc");
 		if (tlb_flag(TLB_V4_U_FULL))
@@ -388,7 +388,7 @@
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	if (cpu_isset(smp_processor_id(), vma->vm_mm->cpu_vm_mask)) {
+	if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
 		if (tlb_flag(TLB_V3_PAGE))
 			asm("mcr p15, 0, %0, c6, c0, 0" : : "r" (uaddr) : "cc");
 		if (tlb_flag(TLB_V4_U_PAGE))
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index de885fd..e0d3277 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -189,7 +189,7 @@
 	read_lock(&tasklist_lock);
 	for_each_process(p) {
 		if (p->mm)
-			cpu_clear(cpu, p->mm->cpu_vm_mask);
+			cpumask_clear_cpu(cpu, mm_cpumask(p->mm));
 	}
 	read_unlock(&tasklist_lock);
 
@@ -257,7 +257,7 @@
 	atomic_inc(&mm->mm_users);
 	atomic_inc(&mm->mm_count);
 	current->active_mm = mm;
-	cpu_set(cpu, mm->cpu_vm_mask);
+	cpumask_set_cpu(cpu, mm_cpumask(mm));
 	cpu_switch_mm(mm->pgd, mm);
 	enter_lazy_tlb(mm, current);
 	local_flush_tlb_all();
@@ -643,7 +643,7 @@
 void flush_tlb_mm(struct mm_struct *mm)
 {
 	if (tlb_ops_need_broadcast())
-		on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, &mm->cpu_vm_mask);
+		on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, mm_cpumask(mm));
 	else
 		local_flush_tlb_mm(mm);
 }
@@ -654,7 +654,7 @@
 		struct tlb_args ta;
 		ta.ta_vma = vma;
 		ta.ta_start = uaddr;
-		on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, &vma->vm_mm->cpu_vm_mask);
+		on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, mm_cpumask(vma->vm_mm));
 	} else
 		local_flush_tlb_page(vma, uaddr);
 }
@@ -677,7 +677,7 @@
 		ta.ta_vma = vma;
 		ta.ta_start = start;
 		ta.ta_end = end;
-		on_each_cpu_mask(ipi_flush_tlb_range, &ta, 1, &vma->vm_mm->cpu_vm_mask);
+		on_each_cpu_mask(ipi_flush_tlb_range, &ta, 1, mm_cpumask(vma->vm_mm));
 	} else
 		local_flush_tlb_range(vma, start, end);
 }
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index fc84fcc..6bda76a 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -59,6 +59,6 @@
 	}
 	spin_unlock(&cpu_asid_lock);
 
-	mm->cpu_vm_mask = cpumask_of_cpu(smp_processor_id());
+	cpumask_copy(mm_cpumask(mm), cpumask_of(smp_processor_id()));
 	mm->context.id = asid;
 }
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 575f3ad..b279429 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -50,7 +50,7 @@
 void flush_cache_mm(struct mm_struct *mm)
 {
 	if (cache_is_vivt()) {
-		if (cpu_isset(smp_processor_id(), mm->cpu_vm_mask))
+		if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm)))
 			__cpuc_flush_user_all();
 		return;
 	}
@@ -73,7 +73,7 @@
 void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
 {
 	if (cache_is_vivt()) {
-		if (cpu_isset(smp_processor_id(), vma->vm_mm->cpu_vm_mask))
+		if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm)))
 			__cpuc_flush_user_range(start & PAGE_MASK, PAGE_ALIGN(end),
 						vma->vm_flags);
 		return;
@@ -97,7 +97,7 @@
 void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsigned long pfn)
 {
 	if (cache_is_vivt()) {
-		if (cpu_isset(smp_processor_id(), vma->vm_mm->cpu_vm_mask)) {
+		if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
 			unsigned long addr = user_addr & PAGE_MASK;
 			__cpuc_flush_user_range(addr, addr + PAGE_SIZE, vma->vm_flags);
 		}
@@ -113,7 +113,7 @@
 			 unsigned long len, int write)
 {
 	if (cache_is_vivt()) {
-		if (cpu_isset(smp_processor_id(), vma->vm_mm->cpu_vm_mask)) {
+		if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
 			unsigned long addr = (unsigned long)kaddr;
 			__cpuc_coherent_kern_range(addr, addr + len);
 		}
@@ -126,7 +126,7 @@
 	}
 
 	/* VIPT non-aliasing cache */
-	if (cpu_isset(smp_processor_id(), vma->vm_mm->cpu_vm_mask) &&
+	if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm)) &&
 	    vma->vm_flags & VM_EXEC) {
 		unsigned long addr = (unsigned long)kaddr;
 		/* only flushing the kernel mapping on non-aliasing VIPT */
diff --git a/arch/ia64/include/asm/smp.h b/arch/ia64/include/asm/smp.h
index d217d1d..0b3b399 100644
--- a/arch/ia64/include/asm/smp.h
+++ b/arch/ia64/include/asm/smp.h
@@ -127,7 +127,6 @@
 
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
-#define arch_send_call_function_ipi_mask arch_send_call_function_ipi_mask
 
 #else /* CONFIG_SMP */
 
diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
index d0141fbf..3ddb4e7 100644
--- a/arch/ia64/include/asm/topology.h
+++ b/arch/ia64/include/asm/topology.h
@@ -33,7 +33,6 @@
 /*
  * 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])
 
 /*
@@ -104,8 +103,6 @@
 #ifdef CONFIG_SMP
 #define topology_physical_package_id(cpu)	(cpu_data(cpu)->socket_id)
 #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)
diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c
index 93ebfea..dabeefe2 100644
--- a/arch/ia64/kernel/smp.c
+++ b/arch/ia64/kernel/smp.c
@@ -302,7 +302,7 @@
 		return;
 	}
 
-	smp_call_function_mask(mm->cpu_vm_mask,
+	smp_call_function_many(mm_cpumask(mm),
 		(void (*)(void *))local_finish_flush_tlb_mm, mm, 1);
 	local_irq_disable();
 	local_finish_flush_tlb_mm(mm);
diff --git a/arch/m32r/include/asm/mmu_context.h b/arch/m32r/include/asm/mmu_context.h
index 91909e5..a70a3df 100644
--- a/arch/m32r/include/asm/mmu_context.h
+++ b/arch/m32r/include/asm/mmu_context.h
@@ -127,7 +127,7 @@
 
 	if (prev != next) {
 #ifdef CONFIG_SMP
-		cpu_set(cpu, next->cpu_vm_mask);
+		cpumask_set_cpu(cpu, mm_cpumask(next));
 #endif /* CONFIG_SMP */
 		/* Set MPTB = next->pgd */
 		*(volatile unsigned long *)MPTB = (unsigned long)next->pgd;
@@ -135,7 +135,7 @@
 	}
 #ifdef CONFIG_SMP
 	else
-		if (!cpu_test_and_set(cpu, next->cpu_vm_mask))
+		if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)))
 			activate_context(next);
 #endif /* CONFIG_SMP */
 }
diff --git a/arch/m32r/include/asm/smp.h b/arch/m32r/include/asm/smp.h
index b96a6d2..e67ded1 100644
--- a/arch/m32r/include/asm/smp.h
+++ b/arch/m32r/include/asm/smp.h
@@ -88,7 +88,7 @@
 extern unsigned long send_IPI_mask_phys(cpumask_t, int, int);
 
 extern void arch_send_call_function_single_ipi(int cpu);
-extern void arch_send_call_function_ipi(cpumask_t mask);
+extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
 #endif	/* not __ASSEMBLY__ */
 
diff --git a/arch/m32r/kernel/smp.c b/arch/m32r/kernel/smp.c
index 929e5c9d..1b7598e 100644
--- a/arch/m32r/kernel/smp.c
+++ b/arch/m32r/kernel/smp.c
@@ -85,7 +85,7 @@
 void smp_local_timer_interrupt(void);
 
 static void send_IPI_allbutself(int, int);
-static void send_IPI_mask(cpumask_t, int, int);
+static void send_IPI_mask(const struct cpumask *, int, int);
 unsigned long send_IPI_mask_phys(cpumask_t, int, int);
 
 /*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*/
@@ -113,7 +113,7 @@
 void smp_send_reschedule(int cpu_id)
 {
 	WARN_ON(cpu_is_offline(cpu_id));
-	send_IPI_mask(cpumask_of_cpu(cpu_id), RESCHEDULE_IPI, 1);
+	send_IPI_mask(cpumask_of(cpu_id), RESCHEDULE_IPI, 1);
 }
 
 /*==========================================================================*
@@ -168,7 +168,7 @@
 	spin_lock(&flushcache_lock);
 	mask=cpus_addr(cpumask);
 	atomic_set_mask(*mask, (atomic_t *)&flushcache_cpumask);
-	send_IPI_mask(cpumask, INVALIDATE_CACHE_IPI, 0);
+	send_IPI_mask(&cpumask, INVALIDATE_CACHE_IPI, 0);
 	_flush_cache_copyback_all();
 	while (flushcache_cpumask)
 		mb();
@@ -264,7 +264,7 @@
 	preempt_disable();
 	cpu_id = smp_processor_id();
 	mmc = &mm->context[cpu_id];
-	cpu_mask = mm->cpu_vm_mask;
+	cpu_mask = *mm_cpumask(mm);
 	cpu_clear(cpu_id, cpu_mask);
 
 	if (*mmc != NO_CONTEXT) {
@@ -273,7 +273,7 @@
 		if (mm == current->mm)
 			activate_context(mm);
 		else
-			cpu_clear(cpu_id, mm->cpu_vm_mask);
+			cpumask_clear_cpu(cpu_id, mm_cpumask(mm));
 		local_irq_restore(flags);
 	}
 	if (!cpus_empty(cpu_mask))
@@ -334,7 +334,7 @@
 	preempt_disable();
 	cpu_id = smp_processor_id();
 	mmc = &mm->context[cpu_id];
-	cpu_mask = mm->cpu_vm_mask;
+	cpu_mask = *mm_cpumask(mm);
 	cpu_clear(cpu_id, cpu_mask);
 
 #ifdef DEBUG_SMP
@@ -424,7 +424,7 @@
 	 * We have to send the IPI only to
 	 * CPUs affected.
 	 */
-	send_IPI_mask(cpumask, INVALIDATE_TLB_IPI, 0);
+	send_IPI_mask(&cpumask, INVALIDATE_TLB_IPI, 0);
 
 	while (!cpus_empty(flush_cpumask)) {
 		/* nothing. lockup detection does not belong here */
@@ -469,7 +469,7 @@
 		if (flush_mm == current->active_mm)
 			activate_context(flush_mm);
 		else
-			cpu_clear(cpu_id, flush_mm->cpu_vm_mask);
+			cpumask_clear_cpu(cpu_id, mm_cpumask(flush_mm));
 	} else {
 		unsigned long va = flush_va;
 
@@ -546,14 +546,14 @@
 	for ( ; ; );
 }
 
-void arch_send_call_function_ipi(cpumask_t mask)
+void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
 	send_IPI_mask(mask, CALL_FUNCTION_IPI, 0);
 }
 
 void arch_send_call_function_single_ipi(int cpu)
 {
-	send_IPI_mask(cpumask_of_cpu(cpu), CALL_FUNC_SINGLE_IPI, 0);
+	send_IPI_mask(cpumask_of(cpu), CALL_FUNC_SINGLE_IPI, 0);
 }
 
 /*==========================================================================*
@@ -729,7 +729,7 @@
 	cpumask = cpu_online_map;
 	cpu_clear(smp_processor_id(), cpumask);
 
-	send_IPI_mask(cpumask, ipi_num, try);
+	send_IPI_mask(&cpumask, ipi_num, try);
 }
 
 /*==========================================================================*
@@ -752,7 +752,7 @@
  * ---------- --- --------------------------------------------------------
  *
  *==========================================================================*/
-static void send_IPI_mask(cpumask_t cpumask, int ipi_num, int try)
+static void send_IPI_mask(const struct cpumask *cpumask, int ipi_num, int try)
 {
 	cpumask_t physid_mask, tmp;
 	int cpu_id, phys_id;
@@ -761,11 +761,11 @@
 	if (num_cpus <= 1)	/* NO MP */
 		return;
 
-	cpus_and(tmp, cpumask, cpu_online_map);
-	BUG_ON(!cpus_equal(cpumask, tmp));
+	cpumask_and(&tmp, cpumask, cpu_online_mask);
+	BUG_ON(!cpumask_equal(cpumask, &tmp));
 
 	physid_mask = CPU_MASK_NONE;
-	for_each_cpu_mask(cpu_id, cpumask){
+	for_each_cpu(cpu_id, cpumask) {
 		if ((phys_id = cpu_to_physid(cpu_id)) != -1)
 			cpu_set(phys_id, physid_mask);
 	}
diff --git a/arch/m32r/kernel/smpboot.c b/arch/m32r/kernel/smpboot.c
index 655ea1c..e034844 100644
--- a/arch/m32r/kernel/smpboot.c
+++ b/arch/m32r/kernel/smpboot.c
@@ -178,7 +178,7 @@
 	for (phys_id = 0 ; phys_id < nr_cpu ; phys_id++)
 		physid_set(phys_id, phys_cpu_present_map);
 #ifndef CONFIG_HOTPLUG_CPU
-	cpu_present_map = cpu_possible_map;
+	init_cpu_present(&cpu_possible_map);
 #endif
 
 	show_mp_info(nr_cpu);
diff --git a/arch/mips/alchemy/common/time.c b/arch/mips/alchemy/common/time.c
index f34ff86..379a664 100644
--- a/arch/mips/alchemy/common/time.c
+++ b/arch/mips/alchemy/common/time.c
@@ -88,7 +88,7 @@
 	.irq		= AU1000_RTC_MATCH2_INT,
 	.set_next_event	= au1x_rtcmatch2_set_next_event,
 	.set_mode	= au1x_rtcmatch2_set_mode,
-	.cpumask	= CPU_MASK_ALL_PTR,
+	.cpumask	= cpu_all_mask,
 };
 
 static struct irqaction au1x_rtcmatch2_irqaction = {
diff --git a/arch/mips/include/asm/mach-ip27/topology.h b/arch/mips/include/asm/mach-ip27/topology.h
index 2305917..f683742 100644
--- a/arch/mips/include/asm/mach-ip27/topology.h
+++ b/arch/mips/include/asm/mach-ip27/topology.h
@@ -24,12 +24,10 @@
 
 #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 cpumask_of_node(node)	(&hub_data(node)->h_cpus)
 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/mips/include/asm/mmu_context.h b/arch/mips/include/asm/mmu_context.h
index d3bea88..d974353 100644
--- a/arch/mips/include/asm/mmu_context.h
+++ b/arch/mips/include/asm/mmu_context.h
@@ -178,8 +178,8 @@
 	 * Mark current->active_mm as not "active" anymore.
 	 * We don't want to mislead possible IPI tlb flush routines.
 	 */
-	cpu_clear(cpu, prev->cpu_vm_mask);
-	cpu_set(cpu, next->cpu_vm_mask);
+	cpumask_clear_cpu(cpu, mm_cpumask(prev));
+	cpumask_set_cpu(cpu, mm_cpumask(next));
 
 	local_irq_restore(flags);
 }
@@ -235,8 +235,8 @@
 	TLBMISS_HANDLER_SETUP_PGD(next->pgd);
 
 	/* mark mmu ownership change */
-	cpu_clear(cpu, prev->cpu_vm_mask);
-	cpu_set(cpu, next->cpu_vm_mask);
+	cpumask_clear_cpu(cpu, mm_cpumask(prev));
+	cpumask_set_cpu(cpu, mm_cpumask(next));
 
 	local_irq_restore(flags);
 }
@@ -258,7 +258,7 @@
 
 	local_irq_save(flags);
 
-	if (cpu_isset(cpu, mm->cpu_vm_mask))  {
+	if (cpumask_test_cpu(cpu, mm_cpumask(mm)))  {
 		get_new_mmu_context(mm, cpu);
 #ifdef CONFIG_MIPS_MT_SMTC
 		/* See comments for similar code above */
diff --git a/arch/mips/include/asm/smp-ops.h b/arch/mips/include/asm/smp-ops.h
index fd54554..9e09af3 100644
--- a/arch/mips/include/asm/smp-ops.h
+++ b/arch/mips/include/asm/smp-ops.h
@@ -19,7 +19,7 @@
 
 struct plat_smp_ops {
 	void (*send_ipi_single)(int cpu, unsigned int action);
-	void (*send_ipi_mask)(cpumask_t mask, unsigned int action);
+	void (*send_ipi_mask)(const struct cpumask *mask, unsigned int action);
 	void (*init_secondary)(void);
 	void (*smp_finish)(void);
 	void (*cpus_done)(void);
diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h
index aaa2d4a..e15f11a 100644
--- a/arch/mips/include/asm/smp.h
+++ b/arch/mips/include/asm/smp.h
@@ -78,6 +78,6 @@
 extern asmlinkage void smp_call_function_interrupt(void);
 
 extern void arch_send_call_function_single_ipi(int cpu);
-extern void arch_send_call_function_ipi(cpumask_t mask);
+extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
 #endif /* __ASM_SMP_H */
diff --git a/arch/mips/kernel/smp-cmp.c b/arch/mips/kernel/smp-cmp.c
index ad0ff5d..cc81771 100644
--- a/arch/mips/kernel/smp-cmp.c
+++ b/arch/mips/kernel/smp-cmp.c
@@ -80,11 +80,11 @@
 	local_irq_restore(flags);
 }
 
-static void cmp_send_ipi_mask(cpumask_t mask, unsigned int action)
+static void cmp_send_ipi_mask(const struct cpumask *mask, unsigned int action)
 {
 	unsigned int i;
 
-	for_each_cpu_mask(i, mask)
+	for_each_cpu(i, mask)
 		cmp_send_ipi_single(i, action);
 }
 
@@ -171,7 +171,7 @@
 
 	for (i = 1; i < NR_CPUS; i++) {
 		if (amon_cpu_avail(i)) {
-			cpu_set(i, cpu_possible_map);
+			set_cpu_possible(i, true);
 			__cpu_number_map[i]	= ++ncpu;
 			__cpu_logical_map[ncpu]	= i;
 		}
diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c
index 6f7ee5a..43e7cdc5 100644
--- a/arch/mips/kernel/smp-mt.c
+++ b/arch/mips/kernel/smp-mt.c
@@ -70,7 +70,7 @@
 		write_vpe_c0_vpeconf0(tmp);
 
 		/* Record this as available CPU */
-		cpu_set(tc, cpu_possible_map);
+		set_cpu_possible(tc, true);
 		__cpu_number_map[tc]	= ++ncpu;
 		__cpu_logical_map[ncpu]	= tc;
 	}
@@ -141,11 +141,11 @@
 	local_irq_restore(flags);
 }
 
-static void vsmp_send_ipi_mask(cpumask_t mask, unsigned int action)
+static void vsmp_send_ipi_mask(const struct cpumask *mask, unsigned int action)
 {
 	unsigned int i;
 
-	for_each_cpu_mask(i, mask)
+	for_each_cpu(i, mask)
 		vsmp_send_ipi_single(i, action);
 }
 
diff --git a/arch/mips/kernel/smp-up.c b/arch/mips/kernel/smp-up.c
index 2508d55..00500fe 100644
--- a/arch/mips/kernel/smp-up.c
+++ b/arch/mips/kernel/smp-up.c
@@ -18,7 +18,8 @@
 	panic(KERN_ERR "%s called", __func__);
 }
 
-static inline void up_send_ipi_mask(cpumask_t mask, unsigned int action)
+static inline void up_send_ipi_mask(const struct cpumask *mask,
+				    unsigned int action)
 {
 	panic(KERN_ERR "%s called", __func__);
 }
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 64668a9..4eb106c 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -128,7 +128,7 @@
 	cpu_idle();
 }
 
-void arch_send_call_function_ipi(cpumask_t mask)
+void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
 	mp_ops->send_ipi_mask(mask, SMP_CALL_FUNCTION);
 }
@@ -183,15 +183,15 @@
 	mp_ops->prepare_cpus(max_cpus);
 	set_cpu_sibling_map(0);
 #ifndef CONFIG_HOTPLUG_CPU
-	cpu_present_map = cpu_possible_map;
+	init_cpu_present(&cpu_possible_map);
 #endif
 }
 
 /* preload SMP state for boot cpu */
 void __devinit smp_prepare_boot_cpu(void)
 {
-	cpu_set(0, cpu_possible_map);
-	cpu_set(0, cpu_online_map);
+	set_cpu_possible(0, true);
+	set_cpu_online(0, true);
 	cpu_set(0, cpu_callin_map);
 }
 
diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c
index 1a466ba..67153a0 100644
--- a/arch/mips/kernel/smtc.c
+++ b/arch/mips/kernel/smtc.c
@@ -305,7 +305,7 @@
 	 */
 	ntcs = ((read_c0_mvpconf0() & MVPCONF0_PTC) >> MVPCONF0_PTC_SHIFT) + 1;
 	for (i=start_cpu_slot; i<NR_CPUS && i<ntcs; i++) {
-		cpu_set(i, cpu_possible_map);
+		set_cpu_possible(i, true);
 		__cpu_number_map[i] = i;
 		__cpu_logical_map[i] = i;
 	}
@@ -525,8 +525,8 @@
 	 * Pull any physically present but unused TCs out of circulation.
 	 */
 	while (tc < (((val & MVPCONF0_PTC) >> MVPCONF0_PTC_SHIFT) + 1)) {
-		cpu_clear(tc, cpu_possible_map);
-		cpu_clear(tc, cpu_present_map);
+		set_cpu_possible(tc, false);
+		set_cpu_present(tc, false);
 		tc++;
 	}
 
diff --git a/arch/mips/mipssim/sim_smtc.c b/arch/mips/mipssim/sim_smtc.c
index d6e4f65..5da30b6 100644
--- a/arch/mips/mipssim/sim_smtc.c
+++ b/arch/mips/mipssim/sim_smtc.c
@@ -43,11 +43,12 @@
 	/* "CPU" may be TC of same VPE, VPE of same CPU, or different CPU */
 }
 
-static inline void ssmtc_send_ipi_mask(cpumask_t mask, unsigned int action)
+static inline void ssmtc_send_ipi_mask(const struct cpumask *mask,
+				       unsigned int action)
 {
 	unsigned int i;
 
-	for_each_cpu_mask(i, mask)
+	for_each_cpu(i, mask)
 		ssmtc_send_ipi_single(i, action);
 }
 
diff --git a/arch/mips/mm/c-octeon.c b/arch/mips/mm/c-octeon.c
index 10ab69f..94e05e5 100644
--- a/arch/mips/mm/c-octeon.c
+++ b/arch/mips/mm/c-octeon.c
@@ -79,7 +79,7 @@
 	 * cores it has been used on
 	 */
 	if (vma)
-		mask = vma->vm_mm->cpu_vm_mask;
+		mask = *mm_cpumask(vma->vm_mm);
 	else
 		mask = cpu_online_map;
 	cpu_clear(cpu, mask);
diff --git a/arch/mips/mti-malta/malta-smtc.c b/arch/mips/mti-malta/malta-smtc.c
index 499ffe5..192cfd2 100644
--- a/arch/mips/mti-malta/malta-smtc.c
+++ b/arch/mips/mti-malta/malta-smtc.c
@@ -21,11 +21,11 @@
 	smtc_send_ipi(cpu, LINUX_SMP_IPI, action);
 }
 
-static void msmtc_send_ipi_mask(cpumask_t mask, unsigned int action)
+static void msmtc_send_ipi_mask(const struct cpumask *mask, unsigned int action)
 {
 	unsigned int i;
 
-	for_each_cpu_mask(i, mask)
+	for_each_cpu(i, mask)
 		msmtc_send_ipi_single(i, action);
 }
 
diff --git a/arch/mips/pmc-sierra/yosemite/smp.c b/arch/mips/pmc-sierra/yosemite/smp.c
index 8ace277..326fe7a 100644
--- a/arch/mips/pmc-sierra/yosemite/smp.c
+++ b/arch/mips/pmc-sierra/yosemite/smp.c
@@ -97,11 +97,11 @@
 	}
 }
 
-static void yos_send_ipi_mask(cpumask_t mask, unsigned int action)
+static void yos_send_ipi_mask(const struct cpumask *mask, unsigned int action)
 {
 	unsigned int i;
 
-	for_each_cpu_mask(i, mask)
+	for_each_cpu(i, mask)
 		yos_send_ipi_single(i, action);
 }
 
diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c
index 060d853d7..f61c164 100644
--- a/arch/mips/sgi-ip27/ip27-memory.c
+++ b/arch/mips/sgi-ip27/ip27-memory.c
@@ -421,7 +421,7 @@
 
 /*
  * A node with nothing.  We use it to avoid any special casing in
- * node_to_cpumask
+ * cpumask_of_node
  */
 static struct node_data null_node = {
 	.hub = {
diff --git a/arch/mips/sgi-ip27/ip27-smp.c b/arch/mips/sgi-ip27/ip27-smp.c
index cbcd7eb..9aa8f29 100644
--- a/arch/mips/sgi-ip27/ip27-smp.c
+++ b/arch/mips/sgi-ip27/ip27-smp.c
@@ -165,11 +165,11 @@
 	REMOTE_HUB_SEND_INTR(COMPACT_TO_NASID_NODEID(cpu_to_node(destid)), irq);
 }
 
-static void ip27_send_ipi_mask(cpumask_t mask, unsigned int action)
+static void ip27_send_ipi(const struct cpumask *mask, unsigned int action)
 {
 	unsigned int i;
 
-	for_each_cpu_mask(i, mask)
+	for_each_cpu(i, mask)
 		ip27_send_ipi_single(i, action);
 }
 
diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c
index 3146916..47b347c 100644
--- a/arch/mips/sibyte/bcm1480/smp.c
+++ b/arch/mips/sibyte/bcm1480/smp.c
@@ -82,11 +82,12 @@
 	__raw_writeq((((u64)action)<< 48), mailbox_0_set_regs[cpu]);
 }
 
-static void bcm1480_send_ipi_mask(cpumask_t mask, unsigned int action)
+static void bcm1480_send_ipi_mask(const struct cpumask *mask,
+				  unsigned int action)
 {
 	unsigned int i;
 
-	for_each_cpu_mask(i, mask)
+	for_each_cpu(i, mask)
 		bcm1480_send_ipi_single(i, action);
 }
 
diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c
index cad1400..c00a5cb 100644
--- a/arch/mips/sibyte/sb1250/smp.c
+++ b/arch/mips/sibyte/sb1250/smp.c
@@ -70,11 +70,12 @@
 	__raw_writeq((((u64)action) << 48), mailbox_set_regs[cpu]);
 }
 
-static inline void sb1250_send_ipi_mask(cpumask_t mask, unsigned int action)
+static inline void sb1250_send_ipi_mask(const struct cpumask *mask,
+					unsigned int action)
 {
 	unsigned int i;
 
-	for_each_cpu_mask(i, mask)
+	for_each_cpu(i, mask)
 		sb1250_send_ipi_single(i, action);
 }
 
diff --git a/arch/mn10300/include/asm/mmu_context.h b/arch/mn10300/include/asm/mmu_context.h
index a9e2e34..cb294c2 100644
--- a/arch/mn10300/include/asm/mmu_context.h
+++ b/arch/mn10300/include/asm/mmu_context.h
@@ -38,13 +38,13 @@
 #define enter_lazy_tlb(mm, tsk)	do {} while (0)
 
 #ifdef CONFIG_SMP
-#define cpu_ran_vm(cpu, task) \
-	cpu_set((cpu), (task)->cpu_vm_mask)
-#define cpu_maybe_ran_vm(cpu, task) \
-	cpu_test_and_set((cpu), (task)->cpu_vm_mask)
+#define cpu_ran_vm(cpu, mm) \
+	cpumask_set_cpu((cpu), mm_cpumask(mm))
+#define cpu_maybe_ran_vm(cpu, mm) \
+	cpumask_test_and_set_cpu((cpu), mm_cpumask(mm))
 #else
-#define cpu_ran_vm(cpu, task)		do {} while (0)
-#define cpu_maybe_ran_vm(cpu, task)	true
+#define cpu_ran_vm(cpu, mm)		do {} while (0)
+#define cpu_maybe_ran_vm(cpu, mm)	true
 #endif /* CONFIG_SMP */
 
 /*
diff --git a/arch/parisc/include/asm/smp.h b/arch/parisc/include/asm/smp.h
index 21eb45a..2e73623 100644
--- a/arch/parisc/include/asm/smp.h
+++ b/arch/parisc/include/asm/smp.h
@@ -30,7 +30,6 @@
 
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
-#define arch_send_call_function_ipi_mask arch_send_call_function_ipi_mask
 
 #endif /* !ASSEMBLY */
 
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index c0d3b8a..d9ea8d3 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -146,7 +146,7 @@
 extern struct smp_ops_t *smp_ops;
 
 extern void arch_send_call_function_single_ipi(int cpu);
-extern void arch_send_call_function_ipi(cpumask_t mask);
+extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
 /* Definitions relative to the secondary CPU spin loop
  * and entry point. Not all of them exist on both 32 and
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 394edcb..22f738d 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -17,11 +17,6 @@
 
 #define parent_node(node)	(node)
 
-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])
 
 int of_node_to_nid(struct device_node *device);
@@ -36,11 +31,6 @@
 }
 #endif
 
-#define pcibus_to_cpumask(bus)	(pcibus_to_node(bus) == -1 ? \
-					CPU_MASK_ALL : \
-					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)))
@@ -104,8 +94,6 @@
 #ifdef CONFIG_PPC64
 #include <asm/smp.h>
 
-#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))
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 74cd1a7..4271f7a 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -431,9 +431,9 @@
 		for (j = 0; j < nthreads && cpu < NR_CPUS; j++) {
 			DBG("    thread %d -> cpu %d (hard id %d)\n",
 			    j, cpu, intserv[j]);
-			cpu_set(cpu, cpu_present_map);
+			set_cpu_present(cpu, true);
 			set_hard_smp_processor_id(cpu, intserv[j]);
-			cpu_set(cpu, cpu_possible_map);
+			set_cpu_possible(cpu, true);
 			cpu++;
 		}
 	}
@@ -479,7 +479,7 @@
 			       maxcpus);
 
 		for (cpu = 0; cpu < maxcpus; cpu++)
-			cpu_set(cpu, cpu_possible_map);
+			set_cpu_possible(cpu, true);
 	out:
 		of_node_put(dn);
 	}
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index d387b39..9b86a74 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -189,11 +189,11 @@
 	smp_ops->message_pass(cpu, PPC_MSG_CALL_FUNC_SINGLE);
 }
 
-void arch_send_call_function_ipi(cpumask_t mask)
+void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
 	unsigned int cpu;
 
-	for_each_cpu_mask(cpu, mask)
+	for_each_cpu(cpu, mask)
 		smp_ops->message_pass(cpu, PPC_MSG_CALL_FUNCTION);
 }
 
@@ -287,7 +287,7 @@
 {
 	BUG_ON(smp_processor_id() != boot_cpuid);
 
-	cpu_set(boot_cpuid, cpu_online_map);
+	set_cpu_online(boot_cpuid, true);
 	cpu_set(boot_cpuid, per_cpu(cpu_sibling_map, boot_cpuid));
 	cpu_set(boot_cpuid, per_cpu(cpu_core_map, boot_cpuid));
 #ifdef CONFIG_PPC64
@@ -307,7 +307,7 @@
 	if (cpu == boot_cpuid)
 		return -EBUSY;
 
-	cpu_clear(cpu, cpu_online_map);
+	set_cpu_online(cpu, false);
 #ifdef CONFIG_PPC64
 	vdso_data->processorCount--;
 	fixup_irqs(cpu_online_map);
@@ -361,7 +361,7 @@
 	smp_wmb();
 	while (__get_cpu_var(cpu_state) != CPU_UP_PREPARE)
 		cpu_relax();
-	cpu_set(cpu, cpu_online_map);
+	set_cpu_online(cpu, true);
 	local_irq_enable();
 }
 #endif
@@ -508,7 +508,7 @@
 
 	ipi_call_lock();
 	notify_cpu_starting(cpu);
-	cpu_set(cpu, cpu_online_map);
+	set_cpu_online(cpu, true);
 	/* Update sibling maps */
 	base = cpu_first_thread_in_core(cpu);
 	for (i = 0; i < threads_per_core; i++) {
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index 937a38e7..b40c22d 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -320,7 +320,7 @@
 	if (ncpus > NR_CPUS)
 		ncpus = NR_CPUS;
 	for (i = 1; i < ncpus ; ++i)
-		cpu_set(i, cpu_present_map);
+		set_cpu_present(i, true);
 
 	if (ppc_md.progress) ppc_md.progress("smp_psurge_probe - done", 0x352);
 
@@ -867,7 +867,7 @@
 
 int smp_core99_cpu_disable(void)
 {
-	cpu_clear(smp_processor_id(), cpu_online_map);
+	set_cpu_online(smp_processor_id(), false);
 
 	/* XXX reset cpu affinity here */
 	mpic_cpu_set_priority(0xf);
@@ -952,7 +952,7 @@
 		int cpu;
 
 		for (cpu = 1; cpu < 4 && cpu < NR_CPUS; ++cpu)
-			cpu_set(cpu, cpu_possible_map);
+			set_cpu_possible(cpu, true);
 		smp_ops = &psurge_smp_ops;
 	}
 #endif /* CONFIG_PPC32 */
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index a20ead8..ebff6d9 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -94,7 +94,7 @@
 {
 	int cpu = smp_processor_id();
 
-	cpu_clear(cpu, cpu_online_map);
+	set_cpu_online(cpu, false);
 	vdso_data->processorCount--;
 
 	/*fix boot_cpuid here*/
@@ -185,7 +185,7 @@
 
 	for_each_cpu_mask(cpu, tmp) {
 		BUG_ON(cpu_isset(cpu, cpu_present_map));
-		cpu_set(cpu, cpu_present_map);
+		set_cpu_present(cpu, true);
 		set_hard_smp_processor_id(cpu, *intserv++);
 	}
 	err = 0;
@@ -217,7 +217,7 @@
 			if (get_hard_smp_processor_id(cpu) != intserv[i])
 				continue;
 			BUG_ON(cpu_online(cpu));
-			cpu_clear(cpu, cpu_present_map);
+			set_cpu_present(cpu, false);
 			set_hard_smp_processor_id(cpu, -1);
 			break;
 		}
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index c991fe6..a868b27 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -62,7 +62,7 @@
 extern int smp_cpu_polarization[];
 
 extern void arch_send_call_function_single_ipi(int cpu);
-extern void arch_send_call_function_ipi(cpumask_t mask);
+extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
 #endif
 
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index 5e0ad61..6e7211a 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -9,7 +9,6 @@
 
 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);
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index b4b6396..c932caa 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -147,11 +147,11 @@
 		udelay(10);
 }
 
-void arch_send_call_function_ipi(cpumask_t mask)
+void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
 	int cpu;
 
-	for_each_cpu_mask(cpu, mask)
+	for_each_cpu(cpu, mask)
 		smp_ext_bitcall(cpu, ec_call_function);
 }
 
diff --git a/arch/sh/include/asm/smp.h b/arch/sh/include/asm/smp.h
index ca64f43..53ef26c 100644
--- a/arch/sh/include/asm/smp.h
+++ b/arch/sh/include/asm/smp.h
@@ -44,7 +44,6 @@
 
 void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
-#define arch_send_call_function_ipi_mask arch_send_call_function_ipi_mask
 
 #else
 
diff --git a/arch/sh/include/asm/topology.h b/arch/sh/include/asm/topology.h
index f8c40cc..65e7bd2 100644
--- a/arch/sh/include/asm/topology.h
+++ b/arch/sh/include/asm/topology.h
@@ -31,7 +31,6 @@
 #define cpu_to_node(cpu)	((void)(cpu),0)
 #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 pcibus_to_node(bus)	((void)(bus), -1)
diff --git a/arch/sparc/include/asm/smp_64.h b/arch/sparc/include/asm/smp_64.h
index becb6bf..f49e11c 100644
--- a/arch/sparc/include/asm/smp_64.h
+++ b/arch/sparc/include/asm/smp_64.h
@@ -36,7 +36,6 @@
 
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
-#define arch_send_call_function_ipi_mask arch_send_call_function_ipi_mask
 
 /*
  *	General functions that each host system must provide.
diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h
index 26cd25c..600a790 100644
--- a/arch/sparc/include/asm/topology_64.h
+++ b/arch/sparc/include/asm/topology_64.h
@@ -12,22 +12,8 @@
 
 #define parent_node(node)	(node)
 
-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'.
- * 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])
-
-#define node_to_cpumask_ptr_next(v, node)	\
-			   v = &(numa_cpumask_lookup_table[node])
-
 struct pci_bus;
 #ifdef CONFIG_PCI
 extern int pcibus_to_node(struct pci_bus *pbus);
@@ -71,8 +57,6 @@
 #ifdef CONFIG_SMP
 #define topology_physical_package_id(cpu)	(cpu_data(cpu).proc_id)
 #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)
diff --git a/arch/um/include/asm/mmu_context.h b/arch/um/include/asm/mmu_context.h
index 54f42e8..34d8130 100644
--- a/arch/um/include/asm/mmu_context.h
+++ b/arch/um/include/asm/mmu_context.h
@@ -35,8 +35,8 @@
 	unsigned cpu = smp_processor_id();
 
 	if(prev != next){
-		cpu_clear(cpu, prev->cpu_vm_mask);
-		cpu_set(cpu, next->cpu_vm_mask);
+		cpumask_clear_cpu(cpu, mm_cpumask(prev));
+		cpumask_set_cpu(cpu, mm_cpumask(next));
 		if(next != &init_mm)
 			__switch_mm(&next->context.id);
 	}
diff --git a/arch/um/kernel/smp.c b/arch/um/kernel/smp.c
index 98351c7..106bf27 100644
--- a/arch/um/kernel/smp.c
+++ b/arch/um/kernel/smp.c
@@ -111,7 +111,7 @@
 	int i;
 
 	for (i = 0; i < ncpus; ++i)
-		cpu_set(i, cpu_possible_map);
+		set_cpu_possible(i, true);
 
 	cpu_clear(me, cpu_online_map);
 	cpu_set(me, cpu_online_map);
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index f923203..4a2d4e0 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -37,12 +37,12 @@
 
 	if (likely(prev != next)) {
 		/* stop flush ipis for the previous mm */
-		cpu_clear(cpu, prev->cpu_vm_mask);
+		cpumask_clear_cpu(cpu, mm_cpumask(prev));
 #ifdef CONFIG_SMP
 		percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
 		percpu_write(cpu_tlbstate.active_mm, next);
 #endif
-		cpu_set(cpu, next->cpu_vm_mask);
+		cpumask_set_cpu(cpu, mm_cpumask(next));
 
 		/* Re-load page tables */
 		load_cr3(next->pgd);
@@ -58,7 +58,7 @@
 		percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
 		BUG_ON(percpu_read(cpu_tlbstate.active_mm) != next);
 
-		if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
+		if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next))) {
 			/* We were in lazy tlb mode and leave_mm disabled
 			 * tlb flush IPI delivery. We must reload CR3
 			 * to make sure to use no freed page tables.
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 6a84ed1..1e79678 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -121,7 +121,6 @@
 	smp_ops.send_call_func_single_ipi(cpu);
 }
 
-#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);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 64970b9..dc69f28 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -227,17 +227,14 @@
 
 	cfg = kzalloc_node(sizeof(*cfg), GFP_ATOMIC, node);
 	if (cfg) {
-		if (!alloc_cpumask_var_node(&cfg->domain, GFP_ATOMIC, node)) {
+		if (!zalloc_cpumask_var_node(&cfg->domain, GFP_ATOMIC, node)) {
 			kfree(cfg);
 			cfg = NULL;
-		} else if (!alloc_cpumask_var_node(&cfg->old_domain,
+		} else if (!zalloc_cpumask_var_node(&cfg->old_domain,
 							  GFP_ATOMIC, node)) {
 			free_cpumask_var(cfg->domain);
 			kfree(cfg);
 			cfg = NULL;
-		} else {
-			cpumask_clear(cfg->domain);
-			cpumask_clear(cfg->old_domain);
 		}
 	}
 
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 71f1d99..ec6ef60 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -67,8 +67,8 @@
 #ifdef CONFIG_SMP
 		preempt_disable();
 		load_LDT(pc);
-		if (!cpus_equal(current->mm->cpu_vm_mask,
-				cpumask_of_cpu(smp_processor_id())))
+		if (!cpumask_equal(mm_cpumask(current->mm),
+				   cpumask_of(smp_processor_id())))
 			smp_call_function(flush_ldt, current->mm, 1);
 		preempt_enable();
 #else
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 847ab41..5284cd2 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -555,10 +555,8 @@
 void __init init_c1e_mask(void)
 {
 	/* If we're using c1e_idle, we need to allocate c1e_mask. */
-	if (pm_idle == c1e_idle) {
-		alloc_cpumask_var(&c1e_mask, GFP_KERNEL);
-		cpumask_clear(c1e_mask);
-	}
+	if (pm_idle == c1e_idle)
+		zalloc_cpumask_var(&c1e_mask, GFP_KERNEL);
 }
 
 static int __init idle_setup(char *str)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 09c5e07..565ebc6 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1059,12 +1059,9 @@
 #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);
+		zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
+		zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
+		zalloc_cpumask_var(&cpu_data(i).llc_shared_map, GFP_KERNEL);
 	}
 	set_cpu_sibling_map(0);
 
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index e293ac5..dcb00d2 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -93,7 +93,6 @@
 
 void __init setup_default_timer_irq(void)
 {
-	irq0.mask = cpumask_of_cpu(0);
 	setup_irq(0, &irq0);
 }
 
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index c814e14..36fe08e 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -59,7 +59,8 @@
 {
 	if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
 		BUG();
-	cpu_clear(cpu, percpu_read(cpu_tlbstate.active_mm)->cpu_vm_mask);
+	cpumask_clear_cpu(cpu,
+			  mm_cpumask(percpu_read(cpu_tlbstate.active_mm)));
 	load_cr3(swapper_pg_dir);
 }
 EXPORT_SYMBOL_GPL(leave_mm);
@@ -234,8 +235,8 @@
 	preempt_disable();
 
 	local_flush_tlb();
-	if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids)
-		flush_tlb_others(&mm->cpu_vm_mask, mm, TLB_FLUSH_ALL);
+	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
+		flush_tlb_others(mm_cpumask(mm), mm, TLB_FLUSH_ALL);
 	preempt_enable();
 }
 
@@ -249,8 +250,8 @@
 		else
 			leave_mm(smp_processor_id());
 	}
-	if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids)
-		flush_tlb_others(&mm->cpu_vm_mask, mm, TLB_FLUSH_ALL);
+	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
+		flush_tlb_others(mm_cpumask(mm), mm, TLB_FLUSH_ALL);
 
 	preempt_enable();
 }
@@ -268,8 +269,8 @@
 			leave_mm(smp_processor_id());
 	}
 
-	if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids)
-		flush_tlb_others(&mm->cpu_vm_mask, mm, va);
+	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
+		flush_tlb_others(mm_cpumask(mm), mm, va);
 
 	preempt_enable();
 }
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 093dd59..3bf7b1d 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1165,14 +1165,14 @@
 	/* Get the "official" set of cpus referring to our pagetable. */
 	if (!alloc_cpumask_var(&mask, GFP_ATOMIC)) {
 		for_each_online_cpu(cpu) {
-			if (!cpumask_test_cpu(cpu, &mm->cpu_vm_mask)
+			if (!cpumask_test_cpu(cpu, mm_cpumask(mm))
 			    && per_cpu(xen_current_cr3, cpu) != __pa(mm->pgd))
 				continue;
 			smp_call_function_single(cpu, drop_other_mm_ref, mm, 1);
 		}
 		return;
 	}
-	cpumask_copy(mask, &mm->cpu_vm_mask);
+	cpumask_copy(mask, mm_cpumask(mm));
 
 	/* It's possible that a vcpu may have a stale reference to our
 	   cr3, because its in lazy mode, and it hasn't yet flushed
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 56071b6..5633b86 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -193,7 +193,7 @@
 
 static void bind_to_cpu0(struct work_struct *work)
 {
-	set_cpus_allowed(current, cpumask_of_cpu(0));
+	set_cpus_allowed_ptr(current, cpumask_of(0));
 	kfree(work);
 }
 
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index 11088cf..8ba0ed0 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -511,7 +511,7 @@
 	struct acpi_processor *match_pr;
 	struct acpi_psd_package *match_pdomain;
 
-	if (!alloc_cpumask_var(&covered_cpus, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&covered_cpus, GFP_KERNEL))
 		return -ENOMEM;
 
 	mutex_lock(&performance_mutex);
@@ -558,7 +558,6 @@
 	 * Now that we have _PSD data from all CPUs, lets setup P-state 
 	 * domain info.
 	 */
-	cpumask_clear(covered_cpus);
 	for_each_possible_cpu(i) {
 		pr = per_cpu(processors, i);
 		if (!pr)
diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index ce7cf3b..4c6c14c 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -77,7 +77,7 @@
 	struct acpi_tsd_package *pdomain, *match_pdomain;
 	struct acpi_processor_throttling *pthrottling, *match_pthrottling;
 
-	if (!alloc_cpumask_var(&covered_cpus, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&covered_cpus, GFP_KERNEL))
 		return -ENOMEM;
 
 	/*
@@ -105,7 +105,6 @@
 	if (retval)
 		goto err_ret;
 
-	cpumask_clear(covered_cpus);
 	for_each_possible_cpu(i) {
 		pr = per_cpu(processors, i);
 		if (!pr)
diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c
index 07a7e4b..cc4b2f9 100644
--- a/drivers/net/sfc/efx.c
+++ b/drivers/net/sfc/efx.c
@@ -884,13 +884,12 @@
 	int count;
 	int cpu;
 
-	if (unlikely(!alloc_cpumask_var(&core_mask, GFP_KERNEL))) {
+	if (unlikely(!zalloc_cpumask_var(&core_mask, GFP_KERNEL))) {
 		printk(KERN_WARNING
 		       "sfc: RSS disabled due to allocation failure\n");
 		return 1;
 	}
 
-	cpumask_clear(core_mask);
 	count = 0;
 	for_each_online_cpu(cpu) {
 		if (!cpumask_test_cpu(cpu, core_mask)) {
diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c
index 8574622..c9e2ae9 100644
--- a/drivers/oprofile/buffer_sync.c
+++ b/drivers/oprofile/buffer_sync.c
@@ -154,9 +154,8 @@
 {
 	int err;
 
-	if (!alloc_cpumask_var(&marked_cpus, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&marked_cpus, GFP_KERNEL))
 		return -ENOMEM;
-	cpumask_clear(marked_cpus);
 
 	start_cpu_work();
 
diff --git a/include/asm-generic/topology.h b/include/asm-generic/topology.h
index 88bada2..510df36 100644
--- a/include/asm-generic/topology.h
+++ b/include/asm-generic/topology.h
@@ -37,9 +37,6 @@
 #ifndef parent_node
 #define parent_node(node)	((void)(node),0)
 #endif
-#ifndef node_to_cpumask
-#define node_to_cpumask(node)	((void)node, cpu_online_map)
-#endif
 #ifndef cpumask_of_node
 #define cpumask_of_node(node)	((void)node, cpu_online_mask)
 #endif
@@ -55,18 +52,4 @@
 
 #endif	/* CONFIG_NUMA */
 
-/*
- * returns pointer to cpumask for specified node
- * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)"
- */
-#ifndef node_to_cpumask_ptr
-
-#define	node_to_cpumask_ptr(v, node) 					\
-		cpumask_t _##v = node_to_cpumask(node);			\
-		const cpumask_t *v = &_##v
-
-#define node_to_cpumask_ptr_next(v, node)				\
-			  _##v = node_to_cpumask(node)
-#endif
-
 #endif /* _ASM_GENERIC_TOPOLOGY_H */
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 9b1d458..789cf5f 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -3,444 +3,37 @@
 
 /*
  * Cpumasks provide a bitmap suitable for representing the
- * set of CPU's in a system, one bit position per CPU number.
- *
- * The new cpumask_ ops take a "struct cpumask *"; the old ones
- * use cpumask_t.
- *
- * See detailed comments in the file linux/bitmap.h describing the
- * data type on which these cpumasks are based.
- *
- * For details of cpumask_scnprintf() and cpumask_parse_user(),
- * see bitmap_scnprintf() and bitmap_parse_user() in lib/bitmap.c.
- * For details of cpulist_scnprintf() and cpulist_parse(), see
- * bitmap_scnlistprintf() and bitmap_parselist(), also in bitmap.c.
- * For details of cpu_remap(), see bitmap_bitremap in lib/bitmap.c
- * For details of cpus_remap(), see bitmap_remap in lib/bitmap.c.
- * For details of cpus_onto(), see bitmap_onto in lib/bitmap.c.
- * For details of cpus_fold(), see bitmap_fold in lib/bitmap.c.
- *
- * . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
- * Note: The alternate operations with the suffix "_nr" are used
- *       to limit the range of the loop to nr_cpu_ids instead of
- *       NR_CPUS when NR_CPUS > 64 for performance reasons.
- *       If NR_CPUS is <= 64 then most assembler bitmask
- *       operators execute faster with a constant range, so
- *       the operator will continue to use NR_CPUS.
- *
- *       Another consideration is that nr_cpu_ids is initialized
- *       to NR_CPUS and isn't lowered until the possible cpus are
- *       discovered (including any disabled cpus).  So early uses
- *       will span the entire range of NR_CPUS.
- * . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
- *
- * The obsolescent cpumask operations are:
- *
- * void cpu_set(cpu, mask)		turn on bit 'cpu' in mask
- * void cpu_clear(cpu, mask)		turn off bit 'cpu' in mask
- * void cpus_setall(mask)		set all bits
- * void cpus_clear(mask)		clear all bits
- * int cpu_isset(cpu, mask)		true iff bit 'cpu' set in mask
- * int cpu_test_and_set(cpu, mask)	test and set bit 'cpu' in mask
- *
- * int cpus_and(dst, src1, src2)	dst = src1 & src2  [intersection]
- * void cpus_or(dst, src1, src2)	dst = src1 | src2  [union]
- * void cpus_xor(dst, src1, src2)	dst = src1 ^ src2
- * int cpus_andnot(dst, src1, src2)	dst = src1 & ~src2
- * void cpus_complement(dst, src)	dst = ~src
- *
- * int cpus_equal(mask1, mask2)		Does mask1 == mask2?
- * int cpus_intersects(mask1, mask2)	Do mask1 and mask2 intersect?
- * int cpus_subset(mask1, mask2)	Is mask1 a subset of mask2?
- * int cpus_empty(mask)			Is mask empty (no bits sets)?
- * int cpus_full(mask)			Is mask full (all bits sets)?
- * int cpus_weight(mask)		Hamming weigh - number of set bits
- * int cpus_weight_nr(mask)		Same using nr_cpu_ids instead of NR_CPUS
- *
- * void cpus_shift_right(dst, src, n)	Shift right
- * void cpus_shift_left(dst, src, n)	Shift left
- *
- * int first_cpu(mask)			Number lowest set bit, or NR_CPUS
- * int next_cpu(cpu, mask)		Next cpu past 'cpu', or NR_CPUS
- * int next_cpu_nr(cpu, mask)		Next cpu past 'cpu', or nr_cpu_ids
- *
- * cpumask_t cpumask_of_cpu(cpu)	Return cpumask with bit 'cpu' set
- *					(can be used as an lvalue)
- * CPU_MASK_ALL				Initializer - all bits set
- * CPU_MASK_NONE			Initializer - no bits set
- * unsigned long *cpus_addr(mask)	Array of unsigned long's in mask
- *
- * CPUMASK_ALLOC kmalloc's a structure that is a composite of many cpumask_t
- * variables, and CPUMASK_PTR provides pointers to each field.
- *
- * The structure should be defined something like this:
- * struct my_cpumasks {
- *	cpumask_t mask1;
- *	cpumask_t mask2;
- * };
- *
- * Usage is then:
- *	CPUMASK_ALLOC(my_cpumasks);
- *	CPUMASK_PTR(mask1, my_cpumasks);
- *	CPUMASK_PTR(mask2, my_cpumasks);
- *
- *	--- DO NOT reference cpumask_t pointers until this check ---
- *	if (my_cpumasks == NULL)
- *		"kmalloc failed"...
- *
- * References are now pointers to the cpumask_t variables (*mask1, ...)
- *
- *if NR_CPUS > BITS_PER_LONG
- *   CPUMASK_ALLOC(m)			Declares and allocates struct m *m =
- *						kmalloc(sizeof(*m), GFP_KERNEL)
- *   CPUMASK_FREE(m)			Macro for kfree(m)
- *else
- *   CPUMASK_ALLOC(m)			Declares struct m _m, *m = &_m
- *   CPUMASK_FREE(m)			Nop
- *endif
- *   CPUMASK_PTR(v, m)			Declares cpumask_t *v = &(m->v)
- * ------------------------------------------------------------------------
- *
- * int cpumask_scnprintf(buf, len, mask) Format cpumask for printing
- * int cpumask_parse_user(ubuf, ulen, mask)	Parse ascii string as cpumask
- * int cpulist_scnprintf(buf, len, mask) Format cpumask as list for printing
- * int cpulist_parse(buf, map)		Parse ascii string as cpulist
- * int cpu_remap(oldbit, old, new)	newbit = map(old, new)(oldbit)
- * void cpus_remap(dst, src, old, new)	*dst = map(old, new)(src)
- * void cpus_onto(dst, orig, relmap)	*dst = orig relative to relmap
- * void cpus_fold(dst, orig, sz)	dst bits = orig bits mod sz
- *
- * for_each_cpu_mask(cpu, mask)		for-loop cpu over mask using NR_CPUS
- * for_each_cpu_mask_nr(cpu, mask)	for-loop cpu over mask using nr_cpu_ids
- *
- * int num_online_cpus()		Number of online CPUs
- * int num_possible_cpus()		Number of all possible CPUs
- * int num_present_cpus()		Number of present CPUs
- *
- * int cpu_online(cpu)			Is some cpu online?
- * int cpu_possible(cpu)		Is some cpu possible?
- * int cpu_present(cpu)			Is some cpu present (can schedule)?
- *
- * int any_online_cpu(mask)		First online cpu in mask
- *
- * for_each_possible_cpu(cpu)		for-loop cpu over cpu_possible_map
- * for_each_online_cpu(cpu)		for-loop cpu over cpu_online_map
- * for_each_present_cpu(cpu)		for-loop cpu over cpu_present_map
- *
- * Subtlety:
- * 1) The 'type-checked' form of cpu_isset() causes gcc (3.3.2, anyway)
- *    to generate slightly worse code.  Note for example the additional
- *    40 lines of assembly code compiling the "for each possible cpu"
- *    loops buried in the disk_stat_read() macros calls when compiling
- *    drivers/block/genhd.c (arch i386, CONFIG_SMP=y).  So use a simple
- *    one-line #define for cpu_isset(), instead of wrapping an inline
- *    inside a macro, the way we do the other calls.
+ * set of CPU's in a system, one bit position per CPU number.  In general,
+ * only nr_cpu_ids (<= NR_CPUS) bits are valid.
  */
-
 #include <linux/kernel.h>
 #include <linux/threads.h>
 #include <linux/bitmap.h>
 
 typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t;
-extern cpumask_t _unused_cpumask_arg_;
-
-#ifndef CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
-#define cpu_set(cpu, dst) __cpu_set((cpu), &(dst))
-static inline void __cpu_set(int cpu, volatile cpumask_t *dstp)
-{
-	set_bit(cpu, dstp->bits);
-}
-
-#define cpu_clear(cpu, dst) __cpu_clear((cpu), &(dst))
-static inline void __cpu_clear(int cpu, volatile cpumask_t *dstp)
-{
-	clear_bit(cpu, dstp->bits);
-}
-
-#define cpus_setall(dst) __cpus_setall(&(dst), NR_CPUS)
-static inline void __cpus_setall(cpumask_t *dstp, int nbits)
-{
-	bitmap_fill(dstp->bits, nbits);
-}
-
-#define cpus_clear(dst) __cpus_clear(&(dst), NR_CPUS)
-static inline void __cpus_clear(cpumask_t *dstp, int nbits)
-{
-	bitmap_zero(dstp->bits, nbits);
-}
-
-/* No static inline type checking - see Subtlety (1) above. */
-#define cpu_isset(cpu, cpumask) test_bit((cpu), (cpumask).bits)
-
-#define cpu_test_and_set(cpu, cpumask) __cpu_test_and_set((cpu), &(cpumask))
-static inline int __cpu_test_and_set(int cpu, cpumask_t *addr)
-{
-	return test_and_set_bit(cpu, addr->bits);
-}
-
-#define cpus_and(dst, src1, src2) __cpus_and(&(dst), &(src1), &(src2), NR_CPUS)
-static inline int __cpus_and(cpumask_t *dstp, const cpumask_t *src1p,
-					const cpumask_t *src2p, int nbits)
-{
-	return bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits);
-}
-
-#define cpus_or(dst, src1, src2) __cpus_or(&(dst), &(src1), &(src2), NR_CPUS)
-static inline void __cpus_or(cpumask_t *dstp, const cpumask_t *src1p,
-					const cpumask_t *src2p, int nbits)
-{
-	bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits);
-}
-
-#define cpus_xor(dst, src1, src2) __cpus_xor(&(dst), &(src1), &(src2), NR_CPUS)
-static inline void __cpus_xor(cpumask_t *dstp, const cpumask_t *src1p,
-					const cpumask_t *src2p, int nbits)
-{
-	bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits);
-}
-
-#define cpus_andnot(dst, src1, src2) \
-				__cpus_andnot(&(dst), &(src1), &(src2), NR_CPUS)
-static inline int __cpus_andnot(cpumask_t *dstp, const cpumask_t *src1p,
-					const cpumask_t *src2p, int nbits)
-{
-	return bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits);
-}
-
-#define cpus_complement(dst, src) __cpus_complement(&(dst), &(src), NR_CPUS)
-static inline void __cpus_complement(cpumask_t *dstp,
-					const cpumask_t *srcp, int nbits)
-{
-	bitmap_complement(dstp->bits, srcp->bits, nbits);
-}
-
-#define cpus_equal(src1, src2) __cpus_equal(&(src1), &(src2), NR_CPUS)
-static inline int __cpus_equal(const cpumask_t *src1p,
-					const cpumask_t *src2p, int nbits)
-{
-	return bitmap_equal(src1p->bits, src2p->bits, nbits);
-}
-
-#define cpus_intersects(src1, src2) __cpus_intersects(&(src1), &(src2), NR_CPUS)
-static inline int __cpus_intersects(const cpumask_t *src1p,
-					const cpumask_t *src2p, int nbits)
-{
-	return bitmap_intersects(src1p->bits, src2p->bits, nbits);
-}
-
-#define cpus_subset(src1, src2) __cpus_subset(&(src1), &(src2), NR_CPUS)
-static inline int __cpus_subset(const cpumask_t *src1p,
-					const cpumask_t *src2p, int nbits)
-{
-	return bitmap_subset(src1p->bits, src2p->bits, nbits);
-}
-
-#define cpus_empty(src) __cpus_empty(&(src), NR_CPUS)
-static inline int __cpus_empty(const cpumask_t *srcp, int nbits)
-{
-	return bitmap_empty(srcp->bits, nbits);
-}
-
-#define cpus_full(cpumask) __cpus_full(&(cpumask), NR_CPUS)
-static inline int __cpus_full(const cpumask_t *srcp, int nbits)
-{
-	return bitmap_full(srcp->bits, nbits);
-}
-
-#define cpus_weight(cpumask) __cpus_weight(&(cpumask), NR_CPUS)
-static inline int __cpus_weight(const cpumask_t *srcp, int nbits)
-{
-	return bitmap_weight(srcp->bits, nbits);
-}
-
-#define cpus_shift_right(dst, src, n) \
-			__cpus_shift_right(&(dst), &(src), (n), NR_CPUS)
-static inline void __cpus_shift_right(cpumask_t *dstp,
-					const cpumask_t *srcp, int n, int nbits)
-{
-	bitmap_shift_right(dstp->bits, srcp->bits, n, nbits);
-}
-
-#define cpus_shift_left(dst, src, n) \
-			__cpus_shift_left(&(dst), &(src), (n), NR_CPUS)
-static inline void __cpus_shift_left(cpumask_t *dstp,
-					const cpumask_t *srcp, int n, int nbits)
-{
-	bitmap_shift_left(dstp->bits, srcp->bits, n, nbits);
-}
-#endif /* !CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS */
 
 /**
- * to_cpumask - convert an NR_CPUS bitmap to a struct cpumask *
- * @bitmap: the bitmap
+ * cpumask_bits - get the bits in a cpumask
+ * @maskp: the struct cpumask *
  *
- * There are a few places where cpumask_var_t isn't appropriate and
- * static cpumasks must be used (eg. very early boot), yet we don't
- * expose the definition of 'struct cpumask'.
- *
- * This does the conversion, and can be used as a constant initializer.
+ * You should only assume nr_cpu_ids bits of this mask are valid.  This is
+ * a macro so it's const-correct.
  */
-#define to_cpumask(bitmap)						\
-	((struct cpumask *)(1 ? (bitmap)				\
-			    : (void *)sizeof(__check_is_bitmap(bitmap))))
-
-static inline int __check_is_bitmap(const unsigned long *bitmap)
-{
-	return 1;
-}
-
-/*
- * Special-case data structure for "single bit set only" constant CPU masks.
- *
- * We pre-generate all the 64 (or 32) possible bit positions, with enough
- * padding to the left and the right, and return the constant pointer
- * appropriately offset.
- */
-extern const unsigned long
-	cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)];
-
-static inline const struct cpumask *get_cpu_mask(unsigned int cpu)
-{
-	const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG];
-	p -= cpu / BITS_PER_LONG;
-	return to_cpumask(p);
-}
-
-#ifndef CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
-/*
- * In cases where we take the address of the cpumask immediately,
- * gcc optimizes it out (it's a constant) and there's no huge stack
- * variable created:
- */
-#define cpumask_of_cpu(cpu) (*get_cpu_mask(cpu))
-
-
-#define CPU_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(NR_CPUS)
-
-#if NR_CPUS <= BITS_PER_LONG
-
-#define CPU_MASK_ALL							\
-(cpumask_t) { {								\
-	[BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD			\
-} }
-
-#define CPU_MASK_ALL_PTR	(&CPU_MASK_ALL)
-
-#else
-
-#define CPU_MASK_ALL							\
-(cpumask_t) { {								\
-	[0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL,			\
-	[BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD			\
-} }
-
-/* cpu_mask_all is in init/main.c */
-extern cpumask_t cpu_mask_all;
-#define CPU_MASK_ALL_PTR	(&cpu_mask_all)
-
-#endif
-
-#define CPU_MASK_NONE							\
-(cpumask_t) { {								\
-	[0 ... BITS_TO_LONGS(NR_CPUS)-1] =  0UL				\
-} }
-
-#define CPU_MASK_CPU0							\
-(cpumask_t) { {								\
-	[0] =  1UL							\
-} }
-
-#define cpus_addr(src) ((src).bits)
-
-#if NR_CPUS > BITS_PER_LONG
-#define	CPUMASK_ALLOC(m)	struct m *m = kmalloc(sizeof(*m), GFP_KERNEL)
-#define	CPUMASK_FREE(m)		kfree(m)
-#else
-#define	CPUMASK_ALLOC(m)	struct m _m, *m = &_m
-#define	CPUMASK_FREE(m)
-#endif
-#define	CPUMASK_PTR(v, m) 	cpumask_t *v = &(m->v)
-
-#define cpu_remap(oldbit, old, new) \
-		__cpu_remap((oldbit), &(old), &(new), NR_CPUS)
-static inline int __cpu_remap(int oldbit,
-		const cpumask_t *oldp, const cpumask_t *newp, int nbits)
-{
-	return bitmap_bitremap(oldbit, oldp->bits, newp->bits, nbits);
-}
-
-#define cpus_remap(dst, src, old, new) \
-		__cpus_remap(&(dst), &(src), &(old), &(new), NR_CPUS)
-static inline void __cpus_remap(cpumask_t *dstp, const cpumask_t *srcp,
-		const cpumask_t *oldp, const cpumask_t *newp, int nbits)
-{
-	bitmap_remap(dstp->bits, srcp->bits, oldp->bits, newp->bits, nbits);
-}
-
-#define cpus_onto(dst, orig, relmap) \
-		__cpus_onto(&(dst), &(orig), &(relmap), NR_CPUS)
-static inline void __cpus_onto(cpumask_t *dstp, const cpumask_t *origp,
-		const cpumask_t *relmapp, int nbits)
-{
-	bitmap_onto(dstp->bits, origp->bits, relmapp->bits, nbits);
-}
-
-#define cpus_fold(dst, orig, sz) \
-		__cpus_fold(&(dst), &(orig), sz, NR_CPUS)
-static inline void __cpus_fold(cpumask_t *dstp, const cpumask_t *origp,
-		int sz, int nbits)
-{
-	bitmap_fold(dstp->bits, origp->bits, sz, nbits);
-}
-#endif /* !CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS */
+#define cpumask_bits(maskp) ((maskp)->bits)
 
 #if NR_CPUS == 1
-
 #define nr_cpu_ids		1
-#ifndef CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
-#define first_cpu(src)		({ (void)(src); 0; })
-#define next_cpu(n, src)	({ (void)(src); 1; })
-#define any_online_cpu(mask)	0
-#define for_each_cpu_mask(cpu, mask)	\
-	for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask)
-#endif /* !CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS */
-#else /* NR_CPUS > 1 */
-
+#else
 extern int nr_cpu_ids;
-#ifndef CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
-int __first_cpu(const cpumask_t *srcp);
-int __next_cpu(int n, const cpumask_t *srcp);
-int __any_online_cpu(const cpumask_t *mask);
-
-#define first_cpu(src)		__first_cpu(&(src))
-#define next_cpu(n, src)	__next_cpu((n), &(src))
-#define any_online_cpu(mask) __any_online_cpu(&(mask))
-#define for_each_cpu_mask(cpu, mask)			\
-	for ((cpu) = -1;				\
-		(cpu) = next_cpu((cpu), (mask)),	\
-		(cpu) < NR_CPUS; )
-#endif /* !CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS */
 #endif
 
-#ifndef CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
-#if NR_CPUS <= 64
-
-#define next_cpu_nr(n, src)		next_cpu(n, src)
-#define cpus_weight_nr(cpumask)		cpus_weight(cpumask)
-#define for_each_cpu_mask_nr(cpu, mask)	for_each_cpu_mask(cpu, mask)
-
-#else /* NR_CPUS > 64 */
-
-int __next_cpu_nr(int n, const cpumask_t *srcp);
-#define next_cpu_nr(n, src)	__next_cpu_nr((n), &(src))
-#define cpus_weight_nr(cpumask)	__cpus_weight(&(cpumask), nr_cpu_ids)
-#define for_each_cpu_mask_nr(cpu, mask)			\
-	for ((cpu) = -1;				\
-		(cpu) = next_cpu_nr((cpu), (mask)),	\
-		(cpu) < nr_cpu_ids; )
-
-#endif /* NR_CPUS > 64 */
-#endif /* !CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS */
+#ifdef CONFIG_CPUMASK_OFFSTACK
+/* Assuming NR_CPUS is huge, a runtime limit is more efficient.  Also,
+ * not all bits may be allocated. */
+#define nr_cpumask_bits	nr_cpu_ids
+#else
+#define nr_cpumask_bits	NR_CPUS
+#endif
 
 /*
  * The following particular system cpumasks and operations manage
@@ -487,12 +80,6 @@
 extern const struct cpumask *const cpu_present_mask;
 extern const struct cpumask *const cpu_active_mask;
 
-/* These strip const, as traditionally they weren't const. */
-#define cpu_possible_map	(*(cpumask_t *)cpu_possible_mask)
-#define cpu_online_map		(*(cpumask_t *)cpu_online_mask)
-#define cpu_present_map		(*(cpumask_t *)cpu_present_mask)
-#define cpu_active_map		(*(cpumask_t *)cpu_active_mask)
-
 #if NR_CPUS > 1
 #define num_online_cpus()	cpumask_weight(cpu_online_mask)
 #define num_possible_cpus()	cpumask_weight(cpu_possible_mask)
@@ -511,35 +98,6 @@
 #define cpu_active(cpu)		((cpu) == 0)
 #endif
 
-#define cpu_is_offline(cpu)	unlikely(!cpu_online(cpu))
-
-/* These are the new versions of the cpumask operators: passed by pointer.
- * The older versions will be implemented in terms of these, then deleted. */
-#define cpumask_bits(maskp) ((maskp)->bits)
-
-#if NR_CPUS <= BITS_PER_LONG
-#define CPU_BITS_ALL						\
-{								\
-	[BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD	\
-}
-
-#else /* NR_CPUS > BITS_PER_LONG */
-
-#define CPU_BITS_ALL						\
-{								\
-	[0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL,		\
-	[BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD		\
-}
-#endif /* NR_CPUS > BITS_PER_LONG */
-
-#ifdef CONFIG_CPUMASK_OFFSTACK
-/* Assuming NR_CPUS is huge, a runtime limit is more efficient.  Also,
- * not all bits may be allocated. */
-#define nr_cpumask_bits	nr_cpu_ids
-#else
-#define nr_cpumask_bits	NR_CPUS
-#endif
-
 /* verify cpu argument to cpumask_* operators */
 static inline unsigned int cpumask_check(unsigned int cpu)
 {
@@ -1100,4 +658,241 @@
 void init_cpu_present(const struct cpumask *src);
 void init_cpu_possible(const struct cpumask *src);
 void init_cpu_online(const struct cpumask *src);
+
+/**
+ * to_cpumask - convert an NR_CPUS bitmap to a struct cpumask *
+ * @bitmap: the bitmap
+ *
+ * There are a few places where cpumask_var_t isn't appropriate and
+ * static cpumasks must be used (eg. very early boot), yet we don't
+ * expose the definition of 'struct cpumask'.
+ *
+ * This does the conversion, and can be used as a constant initializer.
+ */
+#define to_cpumask(bitmap)						\
+	((struct cpumask *)(1 ? (bitmap)				\
+			    : (void *)sizeof(__check_is_bitmap(bitmap))))
+
+static inline int __check_is_bitmap(const unsigned long *bitmap)
+{
+	return 1;
+}
+
+/*
+ * Special-case data structure for "single bit set only" constant CPU masks.
+ *
+ * We pre-generate all the 64 (or 32) possible bit positions, with enough
+ * padding to the left and the right, and return the constant pointer
+ * appropriately offset.
+ */
+extern const unsigned long
+	cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)];
+
+static inline const struct cpumask *get_cpu_mask(unsigned int cpu)
+{
+	const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG];
+	p -= cpu / BITS_PER_LONG;
+	return to_cpumask(p);
+}
+
+#define cpu_is_offline(cpu)	unlikely(!cpu_online(cpu))
+
+#if NR_CPUS <= BITS_PER_LONG
+#define CPU_BITS_ALL						\
+{								\
+	[BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD	\
+}
+
+#else /* NR_CPUS > BITS_PER_LONG */
+
+#define CPU_BITS_ALL						\
+{								\
+	[0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL,		\
+	[BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD		\
+}
+#endif /* NR_CPUS > BITS_PER_LONG */
+
+/*
+ *
+ * From here down, all obsolete.  Use cpumask_ variants!
+ *
+ */
+#ifndef CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
+/* These strip const, as traditionally they weren't const. */
+#define cpu_possible_map	(*(cpumask_t *)cpu_possible_mask)
+#define cpu_online_map		(*(cpumask_t *)cpu_online_mask)
+#define cpu_present_map		(*(cpumask_t *)cpu_present_mask)
+#define cpu_active_map		(*(cpumask_t *)cpu_active_mask)
+
+#define cpumask_of_cpu(cpu) (*get_cpu_mask(cpu))
+
+#define CPU_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(NR_CPUS)
+
+#if NR_CPUS <= BITS_PER_LONG
+
+#define CPU_MASK_ALL							\
+(cpumask_t) { {								\
+	[BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD			\
+} }
+
+#else
+
+#define CPU_MASK_ALL							\
+(cpumask_t) { {								\
+	[0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL,			\
+	[BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD			\
+} }
+
+#endif
+
+#define CPU_MASK_NONE							\
+(cpumask_t) { {								\
+	[0 ... BITS_TO_LONGS(NR_CPUS)-1] =  0UL				\
+} }
+
+#define CPU_MASK_CPU0							\
+(cpumask_t) { {								\
+	[0] =  1UL							\
+} }
+
+#if NR_CPUS == 1
+#define first_cpu(src)		({ (void)(src); 0; })
+#define next_cpu(n, src)	({ (void)(src); 1; })
+#define any_online_cpu(mask)	0
+#define for_each_cpu_mask(cpu, mask)	\
+	for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask)
+#else /* NR_CPUS > 1 */
+int __first_cpu(const cpumask_t *srcp);
+int __next_cpu(int n, const cpumask_t *srcp);
+int __any_online_cpu(const cpumask_t *mask);
+
+#define first_cpu(src)		__first_cpu(&(src))
+#define next_cpu(n, src)	__next_cpu((n), &(src))
+#define any_online_cpu(mask) __any_online_cpu(&(mask))
+#define for_each_cpu_mask(cpu, mask)			\
+	for ((cpu) = -1;				\
+		(cpu) = next_cpu((cpu), (mask)),	\
+		(cpu) < NR_CPUS; )
+#endif /* SMP */
+
+#if NR_CPUS <= 64
+
+#define for_each_cpu_mask_nr(cpu, mask)	for_each_cpu_mask(cpu, mask)
+
+#else /* NR_CPUS > 64 */
+
+int __next_cpu_nr(int n, const cpumask_t *srcp);
+#define for_each_cpu_mask_nr(cpu, mask)			\
+	for ((cpu) = -1;				\
+		(cpu) = __next_cpu_nr((cpu), &(mask)),	\
+		(cpu) < nr_cpu_ids; )
+
+#endif /* NR_CPUS > 64 */
+
+#define cpus_addr(src) ((src).bits)
+
+#define cpu_set(cpu, dst) __cpu_set((cpu), &(dst))
+static inline void __cpu_set(int cpu, volatile cpumask_t *dstp)
+{
+	set_bit(cpu, dstp->bits);
+}
+
+#define cpu_clear(cpu, dst) __cpu_clear((cpu), &(dst))
+static inline void __cpu_clear(int cpu, volatile cpumask_t *dstp)
+{
+	clear_bit(cpu, dstp->bits);
+}
+
+#define cpus_setall(dst) __cpus_setall(&(dst), NR_CPUS)
+static inline void __cpus_setall(cpumask_t *dstp, int nbits)
+{
+	bitmap_fill(dstp->bits, nbits);
+}
+
+#define cpus_clear(dst) __cpus_clear(&(dst), NR_CPUS)
+static inline void __cpus_clear(cpumask_t *dstp, int nbits)
+{
+	bitmap_zero(dstp->bits, nbits);
+}
+
+/* No static inline type checking - see Subtlety (1) above. */
+#define cpu_isset(cpu, cpumask) test_bit((cpu), (cpumask).bits)
+
+#define cpu_test_and_set(cpu, cpumask) __cpu_test_and_set((cpu), &(cpumask))
+static inline int __cpu_test_and_set(int cpu, cpumask_t *addr)
+{
+	return test_and_set_bit(cpu, addr->bits);
+}
+
+#define cpus_and(dst, src1, src2) __cpus_and(&(dst), &(src1), &(src2), NR_CPUS)
+static inline int __cpus_and(cpumask_t *dstp, const cpumask_t *src1p,
+					const cpumask_t *src2p, int nbits)
+{
+	return bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits);
+}
+
+#define cpus_or(dst, src1, src2) __cpus_or(&(dst), &(src1), &(src2), NR_CPUS)
+static inline void __cpus_or(cpumask_t *dstp, const cpumask_t *src1p,
+					const cpumask_t *src2p, int nbits)
+{
+	bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits);
+}
+
+#define cpus_xor(dst, src1, src2) __cpus_xor(&(dst), &(src1), &(src2), NR_CPUS)
+static inline void __cpus_xor(cpumask_t *dstp, const cpumask_t *src1p,
+					const cpumask_t *src2p, int nbits)
+{
+	bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits);
+}
+
+#define cpus_andnot(dst, src1, src2) \
+				__cpus_andnot(&(dst), &(src1), &(src2), NR_CPUS)
+static inline int __cpus_andnot(cpumask_t *dstp, const cpumask_t *src1p,
+					const cpumask_t *src2p, int nbits)
+{
+	return bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits);
+}
+
+#define cpus_equal(src1, src2) __cpus_equal(&(src1), &(src2), NR_CPUS)
+static inline int __cpus_equal(const cpumask_t *src1p,
+					const cpumask_t *src2p, int nbits)
+{
+	return bitmap_equal(src1p->bits, src2p->bits, nbits);
+}
+
+#define cpus_intersects(src1, src2) __cpus_intersects(&(src1), &(src2), NR_CPUS)
+static inline int __cpus_intersects(const cpumask_t *src1p,
+					const cpumask_t *src2p, int nbits)
+{
+	return bitmap_intersects(src1p->bits, src2p->bits, nbits);
+}
+
+#define cpus_subset(src1, src2) __cpus_subset(&(src1), &(src2), NR_CPUS)
+static inline int __cpus_subset(const cpumask_t *src1p,
+					const cpumask_t *src2p, int nbits)
+{
+	return bitmap_subset(src1p->bits, src2p->bits, nbits);
+}
+
+#define cpus_empty(src) __cpus_empty(&(src), NR_CPUS)
+static inline int __cpus_empty(const cpumask_t *srcp, int nbits)
+{
+	return bitmap_empty(srcp->bits, nbits);
+}
+
+#define cpus_weight(cpumask) __cpus_weight(&(cpumask), NR_CPUS)
+static inline int __cpus_weight(const cpumask_t *srcp, int nbits)
+{
+	return bitmap_weight(srcp->bits, nbits);
+}
+
+#define cpus_shift_left(dst, src, n) \
+			__cpus_shift_left(&(dst), &(src), (n), NR_CPUS)
+static inline void __cpus_shift_left(cpumask_t *dstp,
+					const cpumask_t *srcp, int n, int nbits)
+{
+	bitmap_shift_left(dstp->bits, srcp->bits, n, nbits);
+}
+#endif /* !CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS */
+
 #endif /* __LINUX_CPUMASK_H */
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 8e9e151..b78cf81 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -84,7 +84,6 @@
  * struct irqaction - per interrupt action descriptor
  * @handler:	interrupt handler function
  * @flags:	flags (see IRQF_* above)
- * @mask:	no comment as it is useless and about to be removed
  * @name:	name of the device
  * @dev_id:	cookie to identify the device
  * @next:	pointer to the next irqaction for shared interrupts
@@ -97,7 +96,6 @@
 struct irqaction {
 	irq_handler_t handler;
 	unsigned long flags;
-	cpumask_t mask;
 	const char *name;
 	void *dev_id;
 	struct irqaction *next;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index cbf2a3b..848d1f2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1817,10 +1817,13 @@
 	return 0;
 }
 #endif
+
+#ifndef CONFIG_CPUMASK_OFFSTACK
 static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
 {
 	return set_cpus_allowed_ptr(p, &new_mask);
 }
+#endif
 
 /*
  * Architectures can set this to 1 if they have specified
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 9e3d8af..39c64ba 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -73,15 +73,6 @@
 void smp_call_function_many(const struct cpumask *mask,
 			    void (*func)(void *info), void *info, bool wait);
 
-/* Deprecated: Use smp_call_function_many which takes a pointer to the mask. */
-static inline int
-smp_call_function_mask(cpumask_t mask, void(*func)(void *info), void *info,
-		       int wait)
-{
-	smp_call_function_many(&mask, func, info, wait);
-	return 0;
-}
-
 void __smp_call_function_single(int cpuid, struct call_single_data *data,
 				int wait);
 
@@ -144,8 +135,6 @@
 static inline void smp_send_reschedule(int cpu) { }
 #define num_booting_cpus()			1
 #define smp_prepare_boot_cpu()			do {} while (0)
-#define smp_call_function_mask(mask, func, info, wait) \
-			(up_smp_call_function(func, info))
 #define smp_call_function_many(mask, func, info, wait) \
 			(up_smp_call_function(func, info))
 static inline void init_call_single_data(void)
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 809b26c..fc0bf3e 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -211,12 +211,6 @@
 #ifndef topology_core_id
 #define topology_core_id(cpu)			((void)(cpu), 0)
 #endif
-#ifndef topology_thread_siblings
-#define topology_thread_siblings(cpu)		cpumask_of_cpu(cpu)
-#endif
-#ifndef topology_core_siblings
-#define topology_core_siblings(cpu)		cpumask_of_cpu(cpu)
-#endif
 #ifndef topology_thread_cpumask
 #define topology_thread_cpumask(cpu)		cpumask_of(cpu)
 #endif
diff --git a/init/main.c b/init/main.c
index 76961db..7449819 100644
--- a/init/main.c
+++ b/init/main.c
@@ -359,11 +359,6 @@
 
 #else
 
-#if NR_CPUS > BITS_PER_LONG
-cpumask_t cpu_mask_all __read_mostly = CPU_MASK_ALL;
-EXPORT_SYMBOL(cpu_mask_all);
-#endif
-
 /* Setup number of possible processor ids */
 int nr_cpu_ids __read_mostly = NR_CPUS;
 EXPORT_SYMBOL(nr_cpu_ids);
diff --git a/kernel/smp.c b/kernel/smp.c
index fd47a25..c9d1c78 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -347,13 +347,6 @@
 	generic_exec_single(cpu, data, wait);
 }
 
-/* Deprecated: shim for archs using old arch_send_call_function_ipi API. */
-
-#ifndef arch_send_call_function_ipi_mask
-# define arch_send_call_function_ipi_mask(maskp) \
-	 arch_send_call_function_ipi(*(maskp))
-#endif
-
 /**
  * smp_call_function_many(): Run a function on a set of other CPUs.
  * @mask: The set of cpus to run on (only runs on online subset).
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 6c0f6a8..411af37 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1984,11 +1984,9 @@
 	if (current_trace)
 		*iter->trace = *current_trace;
 
-	if (!alloc_cpumask_var(&iter->started, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL))
 		goto fail;
 
-	cpumask_clear(iter->started);
-
 	if (current_trace && current_trace->print_max)
 		iter->tr = &max_tr;
 	else
@@ -4389,7 +4387,7 @@
 	if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL))
 		goto out_free_buffer_mask;
 
-	if (!alloc_cpumask_var(&tracing_reader_cpumask, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&tracing_reader_cpumask, GFP_KERNEL))
 		goto out_free_tracing_cpumask;
 
 	/* To save memory, keep the ring buffer size to its minimum */
@@ -4400,7 +4398,6 @@
 
 	cpumask_copy(tracing_buffer_mask, cpu_possible_mask);
 	cpumask_copy(tracing_cpumask, cpu_all_mask);
-	cpumask_clear(tracing_reader_cpumask);
 
 	/* TODO: make the number of buffers hot pluggable with CPUS */
 	global_trace.buffer = ring_buffer_alloc(ring_buf_size,
diff --git a/mm/quicklist.c b/mm/quicklist.c
index 6eedf7e..6633965 100644
--- a/mm/quicklist.c
+++ b/mm/quicklist.c
@@ -29,7 +29,6 @@
 	int node = numa_node_id();
 	struct zone *zones = NODE_DATA(node)->node_zones;
 	int num_cpus_on_node;
-	const struct cpumask *cpumask_on_node = cpumask_of_node(node);
 
 	node_free_pages =
 #ifdef CONFIG_ZONE_DMA
@@ -42,7 +41,7 @@
 
 	max = node_free_pages / FRACTION_OF_NODE_MEM;
 
-	num_cpus_on_node = cpus_weight_nr(*cpumask_on_node);
+	num_cpus_on_node = cpumask_weight(cpumask_of_node(node));
 	max /= num_cpus_on_node;
 
 	return max(max, min_pages);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 897bff3..034a798 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -738,8 +738,7 @@
 	bool called = true;
 	struct kvm_vcpu *vcpu;
 
-	if (alloc_cpumask_var(&cpus, GFP_ATOMIC))
-		cpumask_clear(cpus);
+	zalloc_cpumask_var(&cpus, GFP_ATOMIC);
 
 	spin_lock(&kvm->requests_lock);
 	me = smp_processor_id();