diff --git a/Documentation/cpu-hotplug.txt b/Documentation/cpu-hotplug.txt
index a0b005d2bd95..f9ad5e048b11 100644
--- a/Documentation/cpu-hotplug.txt
+++ b/Documentation/cpu-hotplug.txt
@@ -108,7 +108,7 @@ Never use anything other than cpumask_t to represent bitmap of CPUs.
 	for_each_possible_cpu     - Iterate over cpu_possible_mask
 	for_each_online_cpu       - Iterate over cpu_online_mask
 	for_each_present_cpu      - Iterate over cpu_present_mask
-	for_each_cpu_mask(x,mask) - Iterate over some random collection of cpu mask.
+	for_each_cpu(x,mask)      - Iterate over some random collection of cpu mask.
 
 	#include <linux/cpu.h>
 	get_online_cpus() and put_online_cpus():
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index ffe8e1b814e0..714411f62391 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -636,7 +636,7 @@ void smp_send_stop(void)
 		cpumask_t mask;
 
 		cpumask_copy(&mask, cpu_online_mask);
-		cpu_clear(smp_processor_id(), mask);
+		cpumask_clear_cpu(smp_processor_id(), &mask);
 
 		smp_cross_call(&mask, IPI_CPU_STOP);
 	}
diff --git a/arch/blackfin/mach-bf561/smp.c b/arch/blackfin/mach-bf561/smp.c
index 11789beca75a..8c0c80fd1a45 100644
--- a/arch/blackfin/mach-bf561/smp.c
+++ b/arch/blackfin/mach-bf561/smp.c
@@ -124,7 +124,7 @@ void platform_send_ipi(cpumask_t callmap, int irq)
 	unsigned int cpu;
 	int offset = (irq == IRQ_SUPPLE_0) ? 6 : 8;
 
-	for_each_cpu_mask(cpu, callmap) {
+	for_each_cpu(cpu, &callmap) {
 		BUG_ON(cpu >= 2);
 		SSYNC();
 		bfin_write_SICB_SYSCR(bfin_read_SICB_SYSCR() | (1 << (offset + cpu)));
diff --git a/arch/ia64/include/asm/acpi.h b/arch/ia64/include/asm/acpi.h
index a1d91ab4c5ef..aa0fdf125aba 100644
--- a/arch/ia64/include/asm/acpi.h
+++ b/arch/ia64/include/asm/acpi.h
@@ -117,7 +117,7 @@ static inline void arch_acpi_set_pdc_bits(u32 *buf)
 #ifdef CONFIG_ACPI_NUMA
 extern cpumask_t early_cpu_possible_map;
 #define for_each_possible_early_cpu(cpu)  \
-	for_each_cpu_mask((cpu), early_cpu_possible_map)
+	for_each_cpu((cpu), &early_cpu_possible_map)
 
 static inline void per_cpu_scan_finalize(int min_cpus, int reserve_cpus)
 {
@@ -125,13 +125,13 @@ static inline void per_cpu_scan_finalize(int min_cpus, int reserve_cpus)
 	int cpu;
 	int next_nid = 0;
 
-	low_cpu = cpus_weight(early_cpu_possible_map);
+	low_cpu = cpumask_weight(&early_cpu_possible_map);
 
 	high_cpu = max(low_cpu, min_cpus);
 	high_cpu = min(high_cpu + reserve_cpus, NR_CPUS);
 
 	for (cpu = low_cpu; cpu < high_cpu; cpu++) {
-		cpu_set(cpu, early_cpu_possible_map);
+		cpumask_set_cpu(cpu, &early_cpu_possible_map);
 		if (node_cpuid[cpu].nid == NUMA_NO_NODE) {
 			node_cpuid[cpu].nid = next_nid;
 			next_nid++;
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 2c4498919d3c..35bf22cc71b7 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -483,7 +483,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
 	    (pa->apic_id << 8) | (pa->local_sapic_eid);
 	/* nid should be overridden as logical node id later */
 	node_cpuid[srat_num_cpus].nid = pxm;
-	cpu_set(srat_num_cpus, early_cpu_possible_map);
+	cpumask_set_cpu(srat_num_cpus, &early_cpu_possible_map);
 	srat_num_cpus++;
 }
 
diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c
index cd44a57c73be..bc9501e36e77 100644
--- a/arch/ia64/kernel/iosapic.c
+++ b/arch/ia64/kernel/iosapic.c
@@ -690,7 +690,7 @@ get_target_cpu (unsigned int gsi, int irq)
 	do {
 		if (++cpu >= nr_cpu_ids)
 			cpu = 0;
-	} while (!cpu_online(cpu) || !cpu_isset(cpu, domain));
+	} while (!cpu_online(cpu) || !cpumask_test_cpu(cpu, &domain));
 
 	return cpu_physical_id(cpu);
 #else  /* CONFIG_SMP */
diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c
index 698d8fefde6c..eaa3199f98c8 100644
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -109,13 +109,13 @@ static inline int find_unassigned_vector(cpumask_t domain)
 	int pos, vector;
 
 	cpumask_and(&mask, &domain, cpu_online_mask);
-	if (cpus_empty(mask))
+	if (cpumask_empty(&mask))
 		return -EINVAL;
 
 	for (pos = 0; pos < IA64_NUM_DEVICE_VECTORS; pos++) {
 		vector = IA64_FIRST_DEVICE_VECTOR + pos;
-		cpus_and(mask, domain, vector_table[vector]);
-		if (!cpus_empty(mask))
+		cpumask_and(&mask, &domain, &vector_table[vector]);
+		if (!cpumask_empty(&mask))
 			continue;
 		return vector;
 	}
@@ -132,18 +132,18 @@ static int __bind_irq_vector(int irq, int vector, cpumask_t domain)
 	BUG_ON((unsigned)vector >= IA64_NUM_VECTORS);
 
 	cpumask_and(&mask, &domain, cpu_online_mask);
-	if (cpus_empty(mask))
+	if (cpumask_empty(&mask))
 		return -EINVAL;
-	if ((cfg->vector == vector) && cpus_equal(cfg->domain, domain))
+	if ((cfg->vector == vector) && cpumask_equal(&cfg->domain, &domain))
 		return 0;
 	if (cfg->vector != IRQ_VECTOR_UNASSIGNED)
 		return -EBUSY;
-	for_each_cpu_mask(cpu, mask)
+	for_each_cpu(cpu, &mask)
 		per_cpu(vector_irq, cpu)[vector] = irq;
 	cfg->vector = vector;
 	cfg->domain = domain;
 	irq_status[irq] = IRQ_USED;
-	cpus_or(vector_table[vector], vector_table[vector], domain);
+	cpumask_or(&vector_table[vector], &vector_table[vector], &domain);
 	return 0;
 }
 
@@ -161,7 +161,6 @@ int bind_irq_vector(int irq, int vector, cpumask_t domain)
 static void __clear_irq_vector(int irq)
 {
 	int vector, cpu;
-	cpumask_t mask;
 	cpumask_t domain;
 	struct irq_cfg *cfg = &irq_cfg[irq];
 
@@ -169,13 +168,12 @@ static void __clear_irq_vector(int irq)
 	BUG_ON(cfg->vector == IRQ_VECTOR_UNASSIGNED);
 	vector = cfg->vector;
 	domain = cfg->domain;
-	cpumask_and(&mask, &cfg->domain, cpu_online_mask);
-	for_each_cpu_mask(cpu, mask)
+	for_each_cpu_and(cpu, &cfg->domain, cpu_online_mask)
 		per_cpu(vector_irq, cpu)[vector] = -1;
 	cfg->vector = IRQ_VECTOR_UNASSIGNED;
 	cfg->domain = CPU_MASK_NONE;
 	irq_status[irq] = IRQ_UNUSED;
-	cpus_andnot(vector_table[vector], vector_table[vector], domain);
+	cpumask_andnot(&vector_table[vector], &vector_table[vector], &domain);
 }
 
 static void clear_irq_vector(int irq)
@@ -244,7 +242,7 @@ void __setup_vector_irq(int cpu)
 		per_cpu(vector_irq, cpu)[vector] = -1;
 	/* Mark the inuse vectors */
 	for (irq = 0; irq < NR_IRQS; ++irq) {
-		if (!cpu_isset(cpu, irq_cfg[irq].domain))
+		if (!cpumask_test_cpu(cpu, &irq_cfg[irq].domain))
 			continue;
 		vector = irq_to_vector(irq);
 		per_cpu(vector_irq, cpu)[vector] = irq;
@@ -261,7 +259,7 @@ static enum vector_domain_type {
 static cpumask_t vector_allocation_domain(int cpu)
 {
 	if (vector_domain_type == VECTOR_DOMAIN_PERCPU)
-		return cpumask_of_cpu(cpu);
+		return *cpumask_of(cpu);
 	return CPU_MASK_ALL;
 }
 
@@ -275,7 +273,7 @@ static int __irq_prepare_move(int irq, int cpu)
 		return -EBUSY;
 	if (cfg->vector == IRQ_VECTOR_UNASSIGNED || !cpu_online(cpu))
 		return -EINVAL;
-	if (cpu_isset(cpu, cfg->domain))
+	if (cpumask_test_cpu(cpu, &cfg->domain))
 		return 0;
 	domain = vector_allocation_domain(cpu);
 	vector = find_unassigned_vector(domain);
@@ -309,12 +307,12 @@ void irq_complete_move(unsigned irq)
 	if (likely(!cfg->move_in_progress))
 		return;
 
-	if (unlikely(cpu_isset(smp_processor_id(), cfg->old_domain)))
+	if (unlikely(cpumask_test_cpu(smp_processor_id(), &cfg->old_domain)))
 		return;
 
 	cpumask_and(&cleanup_mask, &cfg->old_domain, cpu_online_mask);
-	cfg->move_cleanup_count = cpus_weight(cleanup_mask);
-	for_each_cpu_mask(i, cleanup_mask)
+	cfg->move_cleanup_count = cpumask_weight(&cleanup_mask);
+	for_each_cpu(i, &cleanup_mask)
 		platform_send_ipi(i, IA64_IRQ_MOVE_VECTOR, IA64_IPI_DM_INT, 0);
 	cfg->move_in_progress = 0;
 }
@@ -340,12 +338,12 @@ static irqreturn_t smp_irq_move_cleanup_interrupt(int irq, void *dev_id)
 		if (!cfg->move_cleanup_count)
 			goto unlock;
 
-		if (!cpu_isset(me, cfg->old_domain))
+		if (!cpumask_test_cpu(me, &cfg->old_domain))
 			goto unlock;
 
 		spin_lock_irqsave(&vector_lock, flags);
 		__this_cpu_write(vector_irq[vector], -1);
-		cpu_clear(me, vector_table[vector]);
+		cpumask_clear_cpu(me, &vector_table[vector]);
 		spin_unlock_irqrestore(&vector_lock, flags);
 		cfg->move_cleanup_count--;
 	unlock:
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index 8bfd36af46f8..dd5801eb4c69 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -1293,7 +1293,7 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw,
 		monarch_cpu = cpu;
 		sos->monarch = 1;
 	} else {
-		cpu_set(cpu, mca_cpu);
+		cpumask_set_cpu(cpu, &mca_cpu);
 		sos->monarch = 0;
 	}
 	mprintk(KERN_INFO "Entered OS MCA handler. PSP=%lx cpu=%d "
@@ -1316,7 +1316,7 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw,
 		 */
 		ia64_mca_wakeup_all();
 	} else {
-		while (cpu_isset(cpu, mca_cpu))
+		while (cpumask_test_cpu(cpu, &mca_cpu))
 			cpu_relax();	/* spin until monarch wakes us */
 	}
 
@@ -1355,9 +1355,9 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw,
 		 * and put this cpu in the rendez loop.
 		 */
 		for_each_online_cpu(i) {
-			if (cpu_isset(i, mca_cpu)) {
+			if (cpumask_test_cpu(i, &mca_cpu)) {
 				monarch_cpu = i;
-				cpu_clear(i, mca_cpu);	/* wake next cpu */
+				cpumask_clear_cpu(i, &mca_cpu);	/* wake next cpu */
 				while (monarch_cpu != -1)
 					cpu_relax();	/* spin until last cpu leaves */
 				set_curr_task(cpu, previous_current);
@@ -1822,7 +1822,7 @@ format_mca_init_stack(void *mca_data, unsigned long offset,
 	ti->cpu = cpu;
 	p->stack = ti;
 	p->state = TASK_UNINTERRUPTIBLE;
-	cpu_set(cpu, p->cpus_allowed);
+	cpumask_set_cpu(cpu, &p->cpus_allowed);
 	INIT_LIST_HEAD(&p->tasks);
 	p->parent = p->real_parent = p->group_leader = p;
 	INIT_LIST_HEAD(&p->children);
diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c
index 8ae36ea177d3..9dd7464f8c17 100644
--- a/arch/ia64/kernel/msi_ia64.c
+++ b/arch/ia64/kernel/msi_ia64.c
@@ -47,15 +47,14 @@ int ia64_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc)
 	struct msi_msg	msg;
 	unsigned long	dest_phys_id;
 	int	irq, vector;
-	cpumask_t mask;
 
 	irq = create_irq();
 	if (irq < 0)
 		return irq;
 
 	irq_set_msi_desc(irq, desc);
-	cpumask_and(&mask, &(irq_to_domain(irq)), cpu_online_mask);
-	dest_phys_id = cpu_physical_id(first_cpu(mask));
+	dest_phys_id = cpu_physical_id(cpumask_any_and(&(irq_to_domain(irq)),
+						       cpu_online_mask));
 	vector = irq_to_vector(irq);
 
 	msg.address_hi = 0;
@@ -171,10 +170,9 @@ msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
 {
 	struct irq_cfg *cfg = irq_cfg + irq;
 	unsigned dest;
-	cpumask_t mask;
 
-	cpumask_and(&mask, &(irq_to_domain(irq)), cpu_online_mask);
-	dest = cpu_physical_id(first_cpu(mask));
+	dest = cpu_physical_id(cpumask_first_and(&(irq_to_domain(irq)),
+						 cpu_online_mask));
 
 	msg->address_hi = 0;
 	msg->address_lo =
diff --git a/arch/ia64/kernel/numa.c b/arch/ia64/kernel/numa.c
index d288cde93606..92c376279c6d 100644
--- a/arch/ia64/kernel/numa.c
+++ b/arch/ia64/kernel/numa.c
@@ -39,7 +39,7 @@ void map_cpu_to_node(int cpu, int nid)
 	}
 	/* sanity check first */
 	oldnid = cpu_to_node_map[cpu];
-	if (cpu_isset(cpu, node_to_cpu_mask[oldnid])) {
+	if (cpumask_test_cpu(cpu, &node_to_cpu_mask[oldnid])) {
 		return; /* nothing to do */
 	}
 	/* we don't have cpu-driven node hot add yet...
@@ -47,16 +47,16 @@ void map_cpu_to_node(int cpu, int nid)
 	if (!node_online(nid))
 		nid = first_online_node;
 	cpu_to_node_map[cpu] = nid;
-	cpu_set(cpu, node_to_cpu_mask[nid]);
+	cpumask_set_cpu(cpu, &node_to_cpu_mask[nid]);
 	return;
 }
 
 void unmap_cpu_from_node(int cpu, int nid)
 {
-	WARN_ON(!cpu_isset(cpu, node_to_cpu_mask[nid]));
+	WARN_ON(!cpumask_test_cpu(cpu, &node_to_cpu_mask[nid]));
 	WARN_ON(cpu_to_node_map[cpu] != nid);
 	cpu_to_node_map[cpu] = 0;
-	cpu_clear(cpu, node_to_cpu_mask[nid]);
+	cpumask_clear_cpu(cpu, &node_to_cpu_mask[nid]);
 }
 
 
@@ -71,7 +71,7 @@ void __init build_cpu_to_node_map(void)
 	int cpu, i, node;
 
 	for(node=0; node < MAX_NUMNODES; node++)
-		cpus_clear(node_to_cpu_mask[node]);
+		cpumask_clear(&node_to_cpu_mask[node]);
 
 	for_each_possible_early_cpu(cpu) {
 		node = -1;
diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c
index ee9719eebb1e..1eeffb7fbb16 100644
--- a/arch/ia64/kernel/salinfo.c
+++ b/arch/ia64/kernel/salinfo.c
@@ -256,7 +256,7 @@ salinfo_log_wakeup(int type, u8 *buffer, u64 size, int irqsafe)
 			data_saved->buffer = buffer;
 		}
 	}
-	cpu_set(smp_processor_id(), data->cpu_event);
+	cpumask_set_cpu(smp_processor_id(), &data->cpu_event);
 	if (irqsafe) {
 		salinfo_work_to_do(data);
 		spin_unlock_irqrestore(&data_saved_lock, flags);
@@ -274,7 +274,7 @@ salinfo_timeout_check(struct salinfo_data *data)
 	unsigned long flags;
 	if (!data->open)
 		return;
-	if (!cpus_empty(data->cpu_event)) {
+	if (!cpumask_empty(&data->cpu_event)) {
 		spin_lock_irqsave(&data_saved_lock, flags);
 		salinfo_work_to_do(data);
 		spin_unlock_irqrestore(&data_saved_lock, flags);
@@ -308,7 +308,7 @@ salinfo_event_read(struct file *file, char __user *buffer, size_t count, loff_t
 	int i, n, cpu = -1;
 
 retry:
-	if (cpus_empty(data->cpu_event) && down_trylock(&data->mutex)) {
+	if (cpumask_empty(&data->cpu_event) && down_trylock(&data->mutex)) {
 		if (file->f_flags & O_NONBLOCK)
 			return -EAGAIN;
 		if (down_interruptible(&data->mutex))
@@ -317,9 +317,9 @@ salinfo_event_read(struct file *file, char __user *buffer, size_t count, loff_t
 
 	n = data->cpu_check;
 	for (i = 0; i < nr_cpu_ids; i++) {
-		if (cpu_isset(n, data->cpu_event)) {
+		if (cpumask_test_cpu(n, &data->cpu_event)) {
 			if (!cpu_online(n)) {
-				cpu_clear(n, data->cpu_event);
+				cpumask_clear_cpu(n, &data->cpu_event);
 				continue;
 			}
 			cpu = n;
@@ -451,7 +451,7 @@ salinfo_log_new_read(int cpu, struct salinfo_data *data)
 		call_on_cpu(cpu, salinfo_log_read_cpu, data);
 	if (!data->log_size) {
 		data->state = STATE_NO_DATA;
-		cpu_clear(cpu, data->cpu_event);
+		cpumask_clear_cpu(cpu, &data->cpu_event);
 	} else {
 		data->state = STATE_LOG_RECORD;
 	}
@@ -491,11 +491,11 @@ salinfo_log_clear(struct salinfo_data *data, int cpu)
 	unsigned long flags;
 	spin_lock_irqsave(&data_saved_lock, flags);
 	data->state = STATE_NO_DATA;
-	if (!cpu_isset(cpu, data->cpu_event)) {
+	if (!cpumask_test_cpu(cpu, &data->cpu_event)) {
 		spin_unlock_irqrestore(&data_saved_lock, flags);
 		return 0;
 	}
-	cpu_clear(cpu, data->cpu_event);
+	cpumask_clear_cpu(cpu, &data->cpu_event);
 	if (data->saved_num) {
 		shift1_data_saved(data, data->saved_num - 1);
 		data->saved_num = 0;
@@ -509,7 +509,7 @@ salinfo_log_clear(struct salinfo_data *data, int cpu)
 	salinfo_log_new_read(cpu, data);
 	if (data->state == STATE_LOG_RECORD) {
 		spin_lock_irqsave(&data_saved_lock, flags);
-		cpu_set(cpu, data->cpu_event);
+		cpumask_set_cpu(cpu, &data->cpu_event);
 		salinfo_work_to_do(data);
 		spin_unlock_irqrestore(&data_saved_lock, flags);
 	}
@@ -581,7 +581,7 @@ salinfo_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu
 		for (i = 0, data = salinfo_data;
 		     i < ARRAY_SIZE(salinfo_data);
 		     ++i, ++data) {
-			cpu_set(cpu, data->cpu_event);
+			cpumask_set_cpu(cpu, &data->cpu_event);
 			salinfo_work_to_do(data);
 		}
 		spin_unlock_irqrestore(&data_saved_lock, flags);
@@ -601,7 +601,7 @@ salinfo_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu
 					shift1_data_saved(data, j);
 				}
 			}
-			cpu_clear(cpu, data->cpu_event);
+			cpumask_clear_cpu(cpu, &data->cpu_event);
 		}
 		spin_unlock_irqrestore(&data_saved_lock, flags);
 		break;
@@ -659,7 +659,7 @@ salinfo_init(void)
 
 		/* we missed any events before now */
 		for_each_online_cpu(j)
-			cpu_set(j, data->cpu_event);
+			cpumask_set_cpu(j, &data->cpu_event);
 
 		*sdir++ = dir;
 	}
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index d86669bcdfb2..b9761389cb8d 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -562,8 +562,8 @@ setup_arch (char **cmdline_p)
 #  ifdef CONFIG_ACPI_HOTPLUG_CPU
 	prefill_possible_map();
 #  endif
-	per_cpu_scan_finalize((cpus_weight(early_cpu_possible_map) == 0 ?
-		32 : cpus_weight(early_cpu_possible_map)),
+	per_cpu_scan_finalize((cpumask_weight(&early_cpu_possible_map) == 0 ?
+		32 : cpumask_weight(&early_cpu_possible_map)),
 		additional_cpus > 0 ? additional_cpus : 0);
 # endif
 #endif /* CONFIG_APCI_BOOT */
@@ -702,7 +702,8 @@ show_cpuinfo (struct seq_file *m, void *v)
 		   c->itc_freq / 1000000, c->itc_freq % 1000000,
 		   lpj*HZ/500000, (lpj*HZ/5000) % 100);
 #ifdef CONFIG_SMP
-	seq_printf(m, "siblings   : %u\n", cpus_weight(cpu_core_map[cpunum]));
+	seq_printf(m, "siblings   : %u\n",
+		   cpumask_weight(&cpu_core_map[cpunum]));
 	if (c->socket_id != -1)
 		seq_printf(m, "physical id: %u\n", c->socket_id);
 	if (c->threads_per_core > 1 || c->cores_per_socket > 1)
@@ -933,8 +934,8 @@ cpu_init (void)
 	 * (must be done after per_cpu area is setup)
 	 */
 	if (smp_processor_id() == 0) {
-		cpu_set(0, per_cpu(cpu_sibling_map, 0));
-		cpu_set(0, cpu_core_map[0]);
+		cpumask_set_cpu(0, &per_cpu(cpu_sibling_map, 0));
+		cpumask_set_cpu(0, &cpu_core_map[0]);
 	} else {
 		/*
 		 * Set ar.k3 so that assembly code in MCA handler can compute
diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c
index 9fcd4e63048f..7f706d4f84f7 100644
--- a/arch/ia64/kernel/smp.c
+++ b/arch/ia64/kernel/smp.c
@@ -262,11 +262,11 @@ smp_flush_tlb_cpumask(cpumask_t xcpumask)
 	preempt_disable();
 	mycpu = smp_processor_id();
 
-	for_each_cpu_mask(cpu, cpumask)
+	for_each_cpu(cpu, &cpumask)
 		counts[cpu] = local_tlb_flush_counts[cpu].count & 0xffff;
 
 	mb();
-	for_each_cpu_mask(cpu, cpumask) {
+	for_each_cpu(cpu, &cpumask) {
 		if (cpu == mycpu)
 			flush_mycpu = 1;
 		else
@@ -276,7 +276,7 @@ smp_flush_tlb_cpumask(cpumask_t xcpumask)
 	if (flush_mycpu)
 		smp_local_flush_tlb();
 
-	for_each_cpu_mask(cpu, cpumask)
+	for_each_cpu(cpu, &cpumask)
 		while(counts[cpu] == (local_tlb_flush_counts[cpu].count & 0xffff))
 			udelay(FLUSH_DELAY);
 
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index 547a48d78bd7..15051e9c2c6f 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -434,7 +434,7 @@ smp_callin (void)
 	/*
 	 * Allow the master to continue.
 	 */
-	cpu_set(cpuid, cpu_callin_map);
+	cpumask_set_cpu(cpuid, &cpu_callin_map);
 	Dprintk("Stack on CPU %d at about %p\n",cpuid, &cpuid);
 }
 
@@ -475,13 +475,13 @@ do_boot_cpu (int sapicid, int cpu, struct task_struct *idle)
 	 */
 	Dprintk("Waiting on callin_map ...");
 	for (timeout = 0; timeout < 100000; timeout++) {
-		if (cpu_isset(cpu, cpu_callin_map))
+		if (cpumask_test_cpu(cpu, &cpu_callin_map))
 			break;  /* It has booted */
 		udelay(100);
 	}
 	Dprintk("\n");
 
-	if (!cpu_isset(cpu, cpu_callin_map)) {
+	if (!cpumask_test_cpu(cpu, &cpu_callin_map)) {
 		printk(KERN_ERR "Processor 0x%x/0x%x is stuck.\n", cpu, sapicid);
 		ia64_cpu_to_sapicid[cpu] = -1;
 		set_cpu_online(cpu, false);  /* was set in smp_callin() */
@@ -541,7 +541,7 @@ smp_prepare_cpus (unsigned int max_cpus)
 
 	smp_setup_percpu_timer();
 
-	cpu_set(0, cpu_callin_map);
+	cpumask_set_cpu(0, &cpu_callin_map);
 
 	local_cpu_data->loops_per_jiffy = loops_per_jiffy;
 	ia64_cpu_to_sapicid[0] = boot_cpu_id;
@@ -565,7 +565,7 @@ smp_prepare_cpus (unsigned int max_cpus)
 void smp_prepare_boot_cpu(void)
 {
 	set_cpu_online(smp_processor_id(), true);
-	cpu_set(smp_processor_id(), cpu_callin_map);
+	cpumask_set_cpu(smp_processor_id(), &cpu_callin_map);
 	set_numa_node(cpu_to_node_map[smp_processor_id()]);
 	per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
 	paravirt_post_smp_prepare_boot_cpu();
@@ -577,10 +577,10 @@ clear_cpu_sibling_map(int cpu)
 {
 	int i;
 
-	for_each_cpu_mask(i, per_cpu(cpu_sibling_map, cpu))
-		cpu_clear(cpu, per_cpu(cpu_sibling_map, i));
-	for_each_cpu_mask(i, cpu_core_map[cpu])
-		cpu_clear(cpu, cpu_core_map[i]);
+	for_each_cpu(i, &per_cpu(cpu_sibling_map, cpu))
+		cpumask_clear_cpu(cpu, &per_cpu(cpu_sibling_map, i));
+	for_each_cpu(i, &cpu_core_map[cpu])
+		cpumask_clear_cpu(cpu, &cpu_core_map[i]);
 
 	per_cpu(cpu_sibling_map, cpu) = cpu_core_map[cpu] = CPU_MASK_NONE;
 }
@@ -592,12 +592,12 @@ remove_siblinginfo(int cpu)
 
 	if (cpu_data(cpu)->threads_per_core == 1 &&
 	    cpu_data(cpu)->cores_per_socket == 1) {
-		cpu_clear(cpu, cpu_core_map[cpu]);
-		cpu_clear(cpu, per_cpu(cpu_sibling_map, cpu));
+		cpumask_clear_cpu(cpu, &cpu_core_map[cpu]);
+		cpumask_clear_cpu(cpu, &per_cpu(cpu_sibling_map, cpu));
 		return;
 	}
 
-	last = (cpus_weight(cpu_core_map[cpu]) == 1 ? 1 : 0);
+	last = (cpumask_weight(&cpu_core_map[cpu]) == 1 ? 1 : 0);
 
 	/* remove it from all sibling map's */
 	clear_cpu_sibling_map(cpu);
@@ -673,7 +673,7 @@ int __cpu_disable(void)
 	remove_siblinginfo(cpu);
 	fixup_irqs();
 	local_flush_tlb_all();
-	cpu_clear(cpu, cpu_callin_map);
+	cpumask_clear_cpu(cpu, &cpu_callin_map);
 	return 0;
 }
 
@@ -718,11 +718,13 @@ static inline void set_cpu_sibling_map(int cpu)
 
 	for_each_online_cpu(i) {
 		if ((cpu_data(cpu)->socket_id == cpu_data(i)->socket_id)) {
-			cpu_set(i, cpu_core_map[cpu]);
-			cpu_set(cpu, cpu_core_map[i]);
+			cpumask_set_cpu(i, &cpu_core_map[cpu]);
+			cpumask_set_cpu(cpu, &cpu_core_map[i]);
 			if (cpu_data(cpu)->core_id == cpu_data(i)->core_id) {
-				cpu_set(i, per_cpu(cpu_sibling_map, cpu));
-				cpu_set(cpu, per_cpu(cpu_sibling_map, i));
+				cpumask_set_cpu(i,
+						&per_cpu(cpu_sibling_map, cpu));
+				cpumask_set_cpu(cpu,
+						&per_cpu(cpu_sibling_map, i));
 			}
 		}
 	}
@@ -742,7 +744,7 @@ __cpu_up(unsigned int cpu, struct task_struct *tidle)
 	 * Already booted cpu? not valid anymore since we dont
 	 * do idle loop tightspin anymore.
 	 */
-	if (cpu_isset(cpu, cpu_callin_map))
+	if (cpumask_test_cpu(cpu, &cpu_callin_map))
 		return -EINVAL;
 
 	per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
@@ -753,8 +755,8 @@ __cpu_up(unsigned int cpu, struct task_struct *tidle)
 
 	if (cpu_data(cpu)->threads_per_core == 1 &&
 	    cpu_data(cpu)->cores_per_socket == 1) {
-		cpu_set(cpu, per_cpu(cpu_sibling_map, cpu));
-		cpu_set(cpu, cpu_core_map[cpu]);
+		cpumask_set_cpu(cpu, &per_cpu(cpu_sibling_map, cpu));
+		cpumask_set_cpu(cpu, &cpu_core_map[cpu]);
 		return 0;
 	}
 
diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c
index 965ab42fabb0..c01fe8991244 100644
--- a/arch/ia64/kernel/topology.c
+++ b/arch/ia64/kernel/topology.c
@@ -148,7 +148,7 @@ static void cache_shared_cpu_map_setup(unsigned int cpu,
 
 	if (cpu_data(cpu)->threads_per_core <= 1 &&
 		cpu_data(cpu)->cores_per_socket <= 1) {
-		cpu_set(cpu, this_leaf->shared_cpu_map);
+		cpumask_set_cpu(cpu, &this_leaf->shared_cpu_map);
 		return;
 	}
 
@@ -164,7 +164,7 @@ static void cache_shared_cpu_map_setup(unsigned int cpu,
 			if (cpu_data(cpu)->socket_id == cpu_data(j)->socket_id
 				&& cpu_data(j)->core_id == csi.log1_cid
 				&& cpu_data(j)->thread_id == csi.log1_tid)
-				cpu_set(j, this_leaf->shared_cpu_map);
+				cpumask_set_cpu(j, &this_leaf->shared_cpu_map);
 
 		i++;
 	} while (i < num_shared &&
@@ -177,7 +177,7 @@ static void cache_shared_cpu_map_setup(unsigned int cpu,
 static void cache_shared_cpu_map_setup(unsigned int cpu,
 		struct cache_info * this_leaf)
 {
-	cpu_set(cpu, this_leaf->shared_cpu_map);
+	cpumask_set_cpu(cpu, &this_leaf->shared_cpu_map);
 	return;
 }
 #endif
diff --git a/arch/m32r/kernel/smpboot.c b/arch/m32r/kernel/smpboot.c
index bb21f4f63170..a468467542f4 100644
--- a/arch/m32r/kernel/smpboot.c
+++ b/arch/m32r/kernel/smpboot.c
@@ -376,7 +376,7 @@ void __init smp_cpus_done(unsigned int max_cpus)
 	if (!cpumask_equal(&cpu_callin_map, cpu_online_mask))
 		BUG();
 
-	for (cpu_id = 0 ; cpu_id < num_online_cpus() ; cpu_id++)
+	for_each_online_cpu(cpu_id)
 		show_cpu_info(cpu_id);
 
 	/*
diff --git a/arch/mips/bcm63xx/irq.c b/arch/mips/bcm63xx/irq.c
index b94bf44d8d8e..e3e808a6c542 100644
--- a/arch/mips/bcm63xx/irq.c
+++ b/arch/mips/bcm63xx/irq.c
@@ -58,9 +58,9 @@ static inline int enable_irq_for_cpu(int cpu, struct irq_data *d,
 
 #ifdef CONFIG_SMP
 	if (m)
-		enable &= cpu_isset(cpu, *m);
+		enable &= cpumask_test_cpu(cpu, m);
 	else if (irqd_affinity_was_set(d))
-		enable &= cpu_isset(cpu, *d->affinity);
+		enable &= cpumask_test_cpu(cpu, d->affinity);
 #endif
 	return enable;
 }
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index 8b1eeffa12ed..56f5d080ef9d 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -72,7 +72,7 @@ static inline void octeon_send_ipi_mask(const struct cpumask *mask,
 {
 	unsigned int i;
 
-	for_each_cpu_mask(i, *mask)
+	for_each_cpu(i, mask)
 		octeon_send_ipi_single(i, action);
 }
 
@@ -239,7 +239,7 @@ static int octeon_cpu_disable(void)
 		return -ENOTSUPP;
 
 	set_cpu_online(cpu, false);
-	cpu_clear(cpu, cpu_callin_map);
+	cpumask_clear_cpu(cpu, &cpu_callin_map);
 	octeon_fixup_irqs();
 
 	flush_cache_all();
diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h
index eacf865d21c2..bb02fac9b4fa 100644
--- a/arch/mips/include/asm/smp.h
+++ b/arch/mips/include/asm/smp.h
@@ -88,7 +88,7 @@ static inline void arch_send_call_function_single_ipi(int cpu)
 {
 	extern struct plat_smp_ops *mp_ops;	/* private */
 
-	mp_ops->send_ipi_mask(&cpumask_of_cpu(cpu), SMP_CALL_FUNCTION);
+	mp_ops->send_ipi_mask(cpumask_of(cpu), SMP_CALL_FUNCTION);
 }
 
 static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask)
diff --git a/arch/mips/kernel/crash.c b/arch/mips/kernel/crash.c
index d21264681e97..d434d5d5ae6e 100644
--- a/arch/mips/kernel/crash.c
+++ b/arch/mips/kernel/crash.c
@@ -25,9 +25,9 @@ static void crash_shutdown_secondary(void *ignore)
 		return;
 
 	local_irq_disable();
-	if (!cpu_isset(cpu, cpus_in_crash))
+	if (!cpumask_test_cpu(cpu, &cpus_in_crash))
 		crash_save_cpu(regs, cpu);
-	cpu_set(cpu, cpus_in_crash);
+	cpumask_set_cpu(cpu, &cpus_in_crash);
 
 	while (!atomic_read(&kexec_ready_to_reboot))
 		cpu_relax();
@@ -50,7 +50,7 @@ static void crash_kexec_prepare_cpus(void)
 	 */
 	pr_emerg("Sending IPI to other cpus...\n");
 	msecs = 10000;
-	while ((cpus_weight(cpus_in_crash) < ncpus) && (--msecs > 0)) {
+	while ((cpumask_weight(&cpus_in_crash) < ncpus) && (--msecs > 0)) {
 		cpu_relax();
 		mdelay(1);
 	}
@@ -66,5 +66,5 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
 	crashing_cpu = smp_processor_id();
 	crash_save_cpu(regs, crashing_cpu);
 	crash_kexec_prepare_cpus();
-	cpu_set(crashing_cpu, cpus_in_crash);
+	cpumask_set_cpu(crashing_cpu, &cpus_in_crash);
 }
diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c
index 362bb3707e62..3e4491aa6d6b 100644
--- a/arch/mips/kernel/mips-mt-fpaff.c
+++ b/arch/mips/kernel/mips-mt-fpaff.c
@@ -114,8 +114,8 @@ asmlinkage long mipsmt_sys_sched_setaffinity(pid_t pid, unsigned int len,
 	/* Compute new global allowed CPU set if necessary */
 	ti = task_thread_info(p);
 	if (test_ti_thread_flag(ti, TIF_FPUBOUND) &&
-	    cpus_intersects(*new_mask, mt_fpu_cpumask)) {
-		cpus_and(*effective_mask, *new_mask, mt_fpu_cpumask);
+	    cpumask_intersects(new_mask, &mt_fpu_cpumask)) {
+		cpumask_and(effective_mask, new_mask, &mt_fpu_cpumask);
 		retval = set_cpus_allowed_ptr(p, effective_mask);
 	} else {
 		cpumask_copy(effective_mask, new_mask);
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index d295bd1e4996..f2975d4d1e44 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -49,7 +49,7 @@
 void arch_cpu_idle_dead(void)
 {
 	/* What the heck is this check doing ? */
-	if (!cpu_isset(smp_processor_id(), cpu_callin_map))
+	if (!cpumask_test_cpu(smp_processor_id(), &cpu_callin_map))
 		play_dead();
 }
 #endif
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index b8bd9340c9c7..fd528d7ea278 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -362,7 +362,7 @@ static int bmips_cpu_disable(void)
 	pr_info("SMP: CPU%d is offline\n", cpu);
 
 	set_cpu_online(cpu, false);
-	cpu_clear(cpu, cpu_callin_map);
+	cpumask_clear_cpu(cpu, &cpu_callin_map);
 	clear_c0_status(IE_IRQ5);
 
 	local_flush_tlb_all();
diff --git a/arch/mips/kernel/smp-cmp.c b/arch/mips/kernel/smp-cmp.c
index e36a859af666..d5e0f949dc48 100644
--- a/arch/mips/kernel/smp-cmp.c
+++ b/arch/mips/kernel/smp-cmp.c
@@ -66,7 +66,7 @@ static void cmp_smp_finish(void)
 #ifdef CONFIG_MIPS_MT_FPAFF
 	/* If we have an FPU, enroll ourselves in the FPU-full mask */
 	if (cpu_has_fpu)
-		cpu_set(smp_processor_id(), mt_fpu_cpumask);
+		cpumask_set_cpu(smp_processor_id(), &mt_fpu_cpumask);
 #endif /* CONFIG_MIPS_MT_FPAFF */
 
 	local_irq_enable();
@@ -110,7 +110,7 @@ void __init cmp_smp_setup(void)
 #ifdef CONFIG_MIPS_MT_FPAFF
 	/* If we have an FPU, enroll ourselves in the FPU-full mask */
 	if (cpu_has_fpu)
-		cpu_set(0, mt_fpu_cpumask);
+		cpumask_set_cpu(0, &mt_fpu_cpumask);
 #endif /* CONFIG_MIPS_MT_FPAFF */
 
 	for (i = 1; i < NR_CPUS; i++) {
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index d5589bedd0a4..7e011f95bb8e 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -290,7 +290,7 @@ static void cps_smp_finish(void)
 #ifdef CONFIG_MIPS_MT_FPAFF
 	/* If we have an FPU, enroll ourselves in the FPU-full mask */
 	if (cpu_has_fpu)
-		cpu_set(smp_processor_id(), mt_fpu_cpumask);
+		cpumask_set_cpu(smp_processor_id(), &mt_fpu_cpumask);
 #endif /* CONFIG_MIPS_MT_FPAFF */
 
 	local_irq_enable();
@@ -313,7 +313,7 @@ static int cps_cpu_disable(void)
 	atomic_sub(1 << cpu_vpe_id(&current_cpu_data), &core_cfg->vpe_mask);
 	smp_mb__after_atomic();
 	set_cpu_online(cpu, false);
-	cpu_clear(cpu, cpu_callin_map);
+	cpumask_clear_cpu(cpu, &cpu_callin_map);
 
 	return 0;
 }
diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c
index 17ea705f6c40..86311a164ef1 100644
--- a/arch/mips/kernel/smp-mt.c
+++ b/arch/mips/kernel/smp-mt.c
@@ -178,7 +178,7 @@ static void vsmp_smp_finish(void)
 #ifdef CONFIG_MIPS_MT_FPAFF
 	/* If we have an FPU, enroll ourselves in the FPU-full mask */
 	if (cpu_has_fpu)
-		cpu_set(smp_processor_id(), mt_fpu_cpumask);
+		cpumask_set_cpu(smp_processor_id(), &mt_fpu_cpumask);
 #endif /* CONFIG_MIPS_MT_FPAFF */
 
 	local_irq_enable();
@@ -239,7 +239,7 @@ static void __init vsmp_smp_setup(void)
 #ifdef CONFIG_MIPS_MT_FPAFF
 	/* If we have an FPU, enroll ourselves in the FPU-full mask */
 	if (cpu_has_fpu)
-		cpu_set(0, mt_fpu_cpumask);
+		cpumask_set_cpu(0, &mt_fpu_cpumask);
 #endif /* CONFIG_MIPS_MT_FPAFF */
 	if (!cpu_has_mipsmt)
 		return;
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 5b020bda3e05..193ace7955fb 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -75,30 +75,30 @@ static inline void set_cpu_sibling_map(int cpu)
 {
 	int i;
 
-	cpu_set(cpu, cpu_sibling_setup_map);
+	cpumask_set_cpu(cpu, &cpu_sibling_setup_map);
 
 	if (smp_num_siblings > 1) {
-		for_each_cpu_mask(i, cpu_sibling_setup_map) {
+		for_each_cpu(i, &cpu_sibling_setup_map) {
 			if (cpu_data[cpu].package == cpu_data[i].package &&
 				    cpu_data[cpu].core == cpu_data[i].core) {
-				cpu_set(i, cpu_sibling_map[cpu]);
-				cpu_set(cpu, cpu_sibling_map[i]);
+				cpumask_set_cpu(i, &cpu_sibling_map[cpu]);
+				cpumask_set_cpu(cpu, &cpu_sibling_map[i]);
 			}
 		}
 	} else
-		cpu_set(cpu, cpu_sibling_map[cpu]);
+		cpumask_set_cpu(cpu, &cpu_sibling_map[cpu]);
 }
 
 static inline void set_cpu_core_map(int cpu)
 {
 	int i;
 
-	cpu_set(cpu, cpu_core_setup_map);
+	cpumask_set_cpu(cpu, &cpu_core_setup_map);
 
-	for_each_cpu_mask(i, cpu_core_setup_map) {
+	for_each_cpu(i, &cpu_core_setup_map) {
 		if (cpu_data[cpu].package == cpu_data[i].package) {
-			cpu_set(i, cpu_core_map[cpu]);
-			cpu_set(cpu, cpu_core_map[i]);
+			cpumask_set_cpu(i, &cpu_core_map[cpu]);
+			cpumask_set_cpu(cpu, &cpu_core_map[i]);
 		}
 	}
 }
@@ -138,7 +138,7 @@ asmlinkage void start_secondary(void)
 	cpu = smp_processor_id();
 	cpu_data[cpu].udelay_val = loops_per_jiffy;
 
-	cpu_set(cpu, cpu_coherent_mask);
+	cpumask_set_cpu(cpu, &cpu_coherent_mask);
 	notify_cpu_starting(cpu);
 
 	set_cpu_online(cpu, true);
@@ -146,7 +146,7 @@ asmlinkage void start_secondary(void)
 	set_cpu_sibling_map(cpu);
 	set_cpu_core_map(cpu);
 
-	cpu_set(cpu, cpu_callin_map);
+	cpumask_set_cpu(cpu, &cpu_callin_map);
 
 	synchronise_count_slave(cpu);
 
@@ -208,7 +208,7 @@ void smp_prepare_boot_cpu(void)
 {
 	set_cpu_possible(0, true);
 	set_cpu_online(0, true);
-	cpu_set(0, cpu_callin_map);
+	cpumask_set_cpu(0, &cpu_callin_map);
 }
 
 int __cpu_up(unsigned int cpu, struct task_struct *tidle)
@@ -218,7 +218,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 	/*
 	 * Trust is futile.  We should really have timeouts ...
 	 */
-	while (!cpu_isset(cpu, cpu_callin_map))
+	while (!cpumask_test_cpu(cpu, &cpu_callin_map))
 		udelay(100);
 
 	synchronise_count_master(cpu);
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index e334c641a81b..ba32e48d4697 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -1153,13 +1153,13 @@ static void mt_ase_fp_affinity(void)
 		 * restricted the allowed set to exclude any CPUs with FPUs,
 		 * we'll skip the procedure.
 		 */
-		if (cpus_intersects(current->cpus_allowed, mt_fpu_cpumask)) {
+		if (cpumask_intersects(&current->cpus_allowed, &mt_fpu_cpumask)) {
 			cpumask_t tmask;
 
 			current->thread.user_cpus_allowed
 				= current->cpus_allowed;
-			cpus_and(tmask, current->cpus_allowed,
-				mt_fpu_cpumask);
+			cpumask_and(&tmask, &current->cpus_allowed,
+				    &mt_fpu_cpumask);
 			set_cpus_allowed_ptr(current, &tmask);
 			set_thread_flag(TIF_FPUBOUND);
 		}
diff --git a/arch/mips/loongson/loongson-3/numa.c b/arch/mips/loongson/loongson-3/numa.c
index 6cae0e75de27..12d14ed48778 100644
--- a/arch/mips/loongson/loongson-3/numa.c
+++ b/arch/mips/loongson/loongson-3/numa.c
@@ -233,7 +233,7 @@ static __init void prom_meminit(void)
 		if (node_online(node)) {
 			szmem(node);
 			node_mem_init(node);
-			cpus_clear(__node_data[(node)]->cpumask);
+			cpumask_clear(&__node_data[(node)]->cpumask);
 		}
 	}
 	for (cpu = 0; cpu < loongson_sysconf.nr_cpus; cpu++) {
@@ -244,7 +244,7 @@ static __init void prom_meminit(void)
 		if (loongson_sysconf.reserved_cpus_mask & (1<<cpu))
 			continue;
 
-		cpu_set(active_cpu, __node_data[(node)]->cpumask);
+		cpumask_set_cpu(active_cpu, &__node_data[(node)]->cpumask);
 		pr_info("NUMA: set cpumask cpu %d on node %d\n", active_cpu, node);
 
 		active_cpu++;
diff --git a/arch/mips/loongson/loongson-3/smp.c b/arch/mips/loongson/loongson-3/smp.c
index e2eb688b5434..e3c68b5da18d 100644
--- a/arch/mips/loongson/loongson-3/smp.c
+++ b/arch/mips/loongson/loongson-3/smp.c
@@ -408,7 +408,7 @@ static int loongson3_cpu_disable(void)
 		return -EBUSY;
 
 	set_cpu_online(cpu, false);
-	cpu_clear(cpu, cpu_callin_map);
+	cpumask_clear_cpu(cpu, &cpu_callin_map);
 	local_irq_save(flags);
 	fixup_irqs();
 	local_irq_restore(flags);
diff --git a/arch/mips/paravirt/paravirt-smp.c b/arch/mips/paravirt/paravirt-smp.c
index 0164b0c48352..42181c7105df 100644
--- a/arch/mips/paravirt/paravirt-smp.c
+++ b/arch/mips/paravirt/paravirt-smp.c
@@ -75,7 +75,7 @@ static void paravirt_send_ipi_mask(const struct cpumask *mask, unsigned int acti
 {
 	unsigned int cpu;
 
-	for_each_cpu_mask(cpu, *mask)
+	for_each_cpu(cpu, mask)
 		paravirt_send_ipi_single(cpu, action);
 }
 
diff --git a/arch/mips/sgi-ip27/ip27-init.c b/arch/mips/sgi-ip27/ip27-init.c
index ee736bd103f8..570098bfdf87 100644
--- a/arch/mips/sgi-ip27/ip27-init.c
+++ b/arch/mips/sgi-ip27/ip27-init.c
@@ -60,7 +60,7 @@ static void per_hub_init(cnodeid_t cnode)
 	nasid_t nasid = COMPACT_TO_NASID_NODEID(cnode);
 	int i;
 
-	cpu_set(smp_processor_id(), hub->h_cpus);
+	cpumask_set_cpu(smp_processor_id(), &hub->h_cpus);
 
 	if (test_and_set_bit(cnode, hub_init_mask))
 		return;
diff --git a/arch/mips/sgi-ip27/ip27-klnuma.c b/arch/mips/sgi-ip27/ip27-klnuma.c
index ecbb62f339c5..bda90cf87e8c 100644
--- a/arch/mips/sgi-ip27/ip27-klnuma.c
+++ b/arch/mips/sgi-ip27/ip27-klnuma.c
@@ -29,8 +29,8 @@ static cpumask_t ktext_repmask;
 void __init setup_replication_mask(void)
 {
 	/* Set only the master cnode's bit.  The master cnode is always 0. */
-	cpus_clear(ktext_repmask);
-	cpu_set(0, ktext_repmask);
+	cpumask_clear(&ktext_repmask);
+	cpumask_set_cpu(0, &ktext_repmask);
 
 #ifdef CONFIG_REPLICATE_KTEXT
 #ifndef CONFIG_MAPPED_KERNEL
@@ -43,7 +43,7 @@ void __init setup_replication_mask(void)
 			if (cnode == 0)
 				continue;
 			/* Advertise that we have a copy of the kernel */
-			cpu_set(cnode, ktext_repmask);
+			cpumask_set_cpu(cnode, &ktext_repmask);
 		}
 	}
 #endif
@@ -99,7 +99,7 @@ void __init replicate_kernel_text()
 		client_nasid = COMPACT_TO_NASID_NODEID(cnode);
 
 		/* Check if this node should get a copy of the kernel */
-		if (cpu_isset(cnode, ktext_repmask)) {
+		if (cpumask_test_cpu(cnode, &ktext_repmask)) {
 			server_nasid = client_nasid;
 			copy_kernel(server_nasid);
 		}
@@ -124,7 +124,7 @@ unsigned long node_getfirstfree(cnodeid_t cnode)
 	loadbase += 16777216;
 #endif
 	offset = PAGE_ALIGN((unsigned long)(&_end)) - loadbase;
-	if ((cnode == 0) || (cpu_isset(cnode, ktext_repmask)))
+	if ((cnode == 0) || (cpumask_test_cpu(cnode, &ktext_repmask)))
 		return TO_NODE(nasid, offset) >> PAGE_SHIFT;
 	else
 		return KDM_TO_PHYS(PAGE_ALIGN(SYMMON_STK_ADDR(nasid, 0))) >> PAGE_SHIFT;
diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c
index 0b68469e063f..8d0eb2643248 100644
--- a/arch/mips/sgi-ip27/ip27-memory.c
+++ b/arch/mips/sgi-ip27/ip27-memory.c
@@ -404,7 +404,7 @@ static void __init node_mem_init(cnodeid_t node)
 	NODE_DATA(node)->node_start_pfn = start_pfn;
 	NODE_DATA(node)->node_spanned_pages = end_pfn - start_pfn;
 
-	cpus_clear(hub_data(node)->h_cpus);
+	cpumask_clear(&hub_data(node)->h_cpus);
 
 	slot_freepfn += PFN_UP(sizeof(struct pglist_data) +
 			       sizeof(struct hub_data));
diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c
index cfe056fe7f5c..f3191db6e2e9 100644
--- a/arch/parisc/kernel/irq.c
+++ b/arch/parisc/kernel/irq.c
@@ -525,8 +525,8 @@ void do_cpu_irq_mask(struct pt_regs *regs)
 	desc = irq_to_desc(irq);
 	cpumask_copy(&dest, desc->irq_data.affinity);
 	if (irqd_is_per_cpu(&desc->irq_data) &&
-	    !cpu_isset(smp_processor_id(), dest)) {
-		int cpu = first_cpu(dest);
+	    !cpumask_test_cpu(smp_processor_id(), &dest)) {
+		int cpu = cpumask_first(&dest);
 
 		printk(KERN_DEBUG "redirecting irq %d from CPU %d to %d\n",
 		       irq, smp_processor_id(), cpu);
diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h
index 4c8ad592ae33..5be6c4753667 100644
--- a/arch/powerpc/include/asm/cputhreads.h
+++ b/arch/powerpc/include/asm/cputhreads.h
@@ -25,7 +25,7 @@ extern cpumask_t threads_core_mask;
 #define threads_per_core	1
 #define threads_per_subcore	1
 #define threads_shift		0
-#define threads_core_mask	(CPU_MASK_CPU0)
+#define threads_core_mask	(*get_cpu_mask(0))
 #endif
 
 /* cpu_thread_mask_to_cores - Return a cpumask of one per cores
diff --git a/arch/sh/include/asm/mmu_context.h b/arch/sh/include/asm/mmu_context.h
index b9d9489a5012..9f417feaf6e8 100644
--- a/arch/sh/include/asm/mmu_context.h
+++ b/arch/sh/include/asm/mmu_context.h
@@ -99,7 +99,7 @@ static inline int init_new_context(struct task_struct *tsk,
 {
 	int i;
 
-	for (i = 0; i < num_online_cpus(); i++)
+	for_each_online_cpu(i)
 		cpu_context(i, mm) = NO_CONTEXT;
 
 	return 0;
diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c
index fc5acfc93c92..de6be008fc01 100644
--- a/arch/sh/kernel/smp.c
+++ b/arch/sh/kernel/smp.c
@@ -363,7 +363,7 @@ void flush_tlb_mm(struct mm_struct *mm)
 		smp_call_function(flush_tlb_mm_ipi, (void *)mm, 1);
 	} else {
 		int i;
-		for (i = 0; i < num_online_cpus(); i++)
+		for_each_online_cpu(i)
 			if (smp_processor_id() != i)
 				cpu_context(i, mm) = 0;
 	}
@@ -400,7 +400,7 @@ void flush_tlb_range(struct vm_area_struct *vma,
 		smp_call_function(flush_tlb_range_ipi, (void *)&fd, 1);
 	} else {
 		int i;
-		for (i = 0; i < num_online_cpus(); i++)
+		for_each_online_cpu(i)
 			if (smp_processor_id() != i)
 				cpu_context(i, mm) = 0;
 	}
@@ -443,7 +443,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
 		smp_call_function(flush_tlb_page_ipi, (void *)&fd, 1);
 	} else {
 		int i;
-		for (i = 0; i < num_online_cpus(); i++)
+		for_each_online_cpu(i)
 			if (smp_processor_id() != i)
 				cpu_context(i, vma->vm_mm) = 0;
 	}
diff --git a/arch/sparc/kernel/time_32.c b/arch/sparc/kernel/time_32.c
index 18147a5523d9..8caf45ee81d9 100644
--- a/arch/sparc/kernel/time_32.c
+++ b/arch/sparc/kernel/time_32.c
@@ -194,7 +194,7 @@ static __init int setup_timer_cs(void)
 static void percpu_ce_setup(enum clock_event_mode mode,
 			struct clock_event_device *evt)
 {
-	int cpu = __first_cpu(evt->cpumask);
+	int cpu = cpumask_first(evt->cpumask);
 
 	switch (mode) {
 		case CLOCK_EVT_MODE_PERIODIC:
@@ -214,7 +214,7 @@ static void percpu_ce_setup(enum clock_event_mode mode,
 static int percpu_ce_set_next_event(unsigned long delta,
 				    struct clock_event_device *evt)
 {
-	int cpu = __first_cpu(evt->cpumask);
+	int cpu = cpumask_first(evt->cpumask);
 	unsigned int next = (unsigned int)delta;
 
 	sparc_config.load_profile_irq(cpu, next);
diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c
index 7833b2ccdfbc..6873f006f7d0 100644
--- a/arch/tile/kernel/setup.c
+++ b/arch/tile/kernel/setup.c
@@ -774,7 +774,7 @@ static void __init zone_sizes_init(void)
 		 * though, there'll be no lowmem, so we just alloc_bootmem
 		 * the memmap.  There will be no percpu memory either.
 		 */
-		if (i != 0 && cpu_isset(i, isolnodes)) {
+		if (i != 0 && cpumask_test_cpu(i, &isolnodes)) {
 			node_memmap_pfn[i] =
 				alloc_bootmem_pfn(0, memmap_size, 0);
 			BUG_ON(node_percpu[i] != 0);
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index d9d0bd2faaf4..ab3219b3fbda 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -171,8 +171,8 @@ update_clusterinfo(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		for_each_online_cpu(cpu) {
 			if (x2apic_cluster(this_cpu) != x2apic_cluster(cpu))
 				continue;
-			__cpu_clear(this_cpu, per_cpu(cpus_in_cluster, cpu));
-			__cpu_clear(cpu, per_cpu(cpus_in_cluster, this_cpu));
+			cpumask_clear_cpu(this_cpu, per_cpu(cpus_in_cluster, cpu));
+			cpumask_clear_cpu(cpu, per_cpu(cpus_in_cluster, this_cpu));
 		}
 		free_cpumask_var(per_cpu(cpus_in_cluster, this_cpu));
 		free_cpumask_var(per_cpu(ipi_mask, this_cpu));
diff --git a/drivers/clocksource/dw_apb_timer.c b/drivers/clocksource/dw_apb_timer.c
index f3656a6b0382..35a88097af3c 100644
--- a/drivers/clocksource/dw_apb_timer.c
+++ b/drivers/clocksource/dw_apb_timer.c
@@ -117,7 +117,8 @@ static void apbt_set_mode(enum clock_event_mode mode,
 	unsigned long period;
 	struct dw_apb_clock_event_device *dw_ced = ced_to_dw_apb_ced(evt);
 
-	pr_debug("%s CPU %d mode=%d\n", __func__, first_cpu(*evt->cpumask),
+	pr_debug("%s CPU %d mode=%d\n", __func__,
+		 cpumask_first(evt->cpumask),
 		 mode);
 
 	switch (mode) {
diff --git a/drivers/cpuidle/coupled.c b/drivers/cpuidle/coupled.c
index 73fe2f8d7f96..7936dce4b878 100644
--- a/drivers/cpuidle/coupled.c
+++ b/drivers/cpuidle/coupled.c
@@ -292,7 +292,7 @@ static inline int cpuidle_coupled_get_state(struct cpuidle_device *dev,
 	 */
 	smp_rmb();
 
-	for_each_cpu_mask(i, coupled->coupled_cpus)
+	for_each_cpu(i, &coupled->coupled_cpus)
 		if (cpu_online(i) && coupled->requested_state[i] < state)
 			state = coupled->requested_state[i];
 
@@ -338,7 +338,7 @@ static void cpuidle_coupled_poke_others(int this_cpu,
 {
 	int cpu;
 
-	for_each_cpu_mask(cpu, coupled->coupled_cpus)
+	for_each_cpu(cpu, &coupled->coupled_cpus)
 		if (cpu != this_cpu && cpu_online(cpu))
 			cpuidle_coupled_poke(cpu);
 }
@@ -638,7 +638,7 @@ int cpuidle_coupled_register_device(struct cpuidle_device *dev)
 	if (cpumask_empty(&dev->coupled_cpus))
 		return 0;
 
-	for_each_cpu_mask(cpu, dev->coupled_cpus) {
+	for_each_cpu(cpu, &dev->coupled_cpus) {
 		other_dev = per_cpu(cpuidle_devices, cpu);
 		if (other_dev && other_dev->coupled) {
 			coupled = other_dev->coupled;
diff --git a/drivers/crypto/n2_core.c b/drivers/crypto/n2_core.c
index afd136b45f49..10a9aeff1666 100644
--- a/drivers/crypto/n2_core.c
+++ b/drivers/crypto/n2_core.c
@@ -1754,7 +1754,7 @@ static int spu_mdesc_walk_arcs(struct mdesc_handle *mdesc,
 				dev->dev.of_node->full_name);
 			return -EINVAL;
 		}
-		cpu_set(*id, p->sharing);
+		cpumask_set_cpu(*id, &p->sharing);
 		table[*id] = p;
 	}
 	return 0;
@@ -1776,7 +1776,7 @@ static int handle_exec_unit(struct spu_mdesc_info *ip, struct list_head *list,
 		return -ENOMEM;
 	}
 
-	cpus_clear(p->sharing);
+	cpumask_clear(&p->sharing);
 	spin_lock_init(&p->lock);
 	p->q_type = q_type;
 	INIT_LIST_HEAD(&p->jobs);
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 4f2fb62e6f37..49875adb6b44 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -567,7 +567,7 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 	 */
 	smp_wmb();
 
-	for_each_cpu_mask(cpu, *mask) {
+	for_each_cpu(cpu, mask) {
 		u64 cluster_id = cpu_logical_map(cpu) & ~0xffUL;
 		u16 tlist;
 
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index bc48b7dc89ec..57f09cb54464 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -389,19 +389,19 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *cpumask,
 	int		i;
 
 	cpumask_and(&tmp, cpumask, cpu_online_mask);
-	if (cpus_empty(tmp))
+	if (cpumask_empty(&tmp))
 		return -EINVAL;
 
 	/* Assumption : cpumask refers to a single CPU */
 	spin_lock_irqsave(&gic_lock, flags);
 
 	/* Re-route this IRQ */
-	gic_map_to_vpe(irq, first_cpu(tmp));
+	gic_map_to_vpe(irq, cpumask_first(&tmp));
 
 	/* Update the pcpu_masks */
 	for (i = 0; i < NR_CPUS; i++)
 		clear_bit(irq, pcpu_masks[i].pcpu_mask);
-	set_bit(irq, pcpu_masks[first_cpu(tmp)].pcpu_mask);
+	set_bit(irq, pcpu_masks[cpumask_first(&tmp)].pcpu_mask);
 
 	cpumask_copy(d->affinity, cpumask);
 	spin_unlock_irqrestore(&gic_lock, flags);
diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c
index a789a2054388..a3f7610002aa 100644
--- a/drivers/net/ethernet/tile/tilegx.c
+++ b/drivers/net/ethernet/tile/tilegx.c
@@ -1123,7 +1123,7 @@ static int alloc_percpu_mpipe_resources(struct net_device *dev,
 			addr + i * sizeof(struct tile_net_comps);
 
 	/* If this is a network cpu, create an iqueue. */
-	if (cpu_isset(cpu, network_cpus_map)) {
+	if (cpumask_test_cpu(cpu, &network_cpus_map)) {
 		order = get_order(NOTIF_RING_SIZE);
 		page = homecache_alloc_pages(GFP_KERNEL, order, cpu);
 		if (page == NULL) {
@@ -1299,7 +1299,7 @@ static int tile_net_init_mpipe(struct net_device *dev)
 	int first_ring, ring;
 	int instance = mpipe_instance(dev);
 	struct mpipe_data *md = &mpipe_data[instance];
-	int network_cpus_count = cpus_weight(network_cpus_map);
+	int network_cpus_count = cpumask_weight(&network_cpus_map);
 
 	if (!hash_default) {
 		netdev_err(dev, "Networking requires hash_default!\n");
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index a1cfbd3dda47..8eab107b53fb 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -6632,14 +6632,12 @@ static void fail_all_outstanding_cmds(struct ctlr_info *h)
 
 static void set_lockup_detected_for_all_cpus(struct ctlr_info *h, u32 value)
 {
-	int i, cpu;
+	int cpu;
 
-	cpu = cpumask_first(cpu_online_mask);
-	for (i = 0; i < num_online_cpus(); i++) {
+	for_each_online_cpu(cpu) {
 		u32 *lockup_detected;
 		lockup_detected = per_cpu_ptr(h->lockup_detected, cpu);
 		*lockup_detected = value;
-		cpu = cpumask_next(cpu, cpu_online_mask);
 	}
 	wmb(); /* be sure the per-cpu variables are out to memory */
 }
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 086549a665e2..27e285b92b5f 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -11,6 +11,7 @@
 #include <linux/bitmap.h>
 #include <linux/bug.h>
 
+/* Don't assign or return these: may not be this big! */
 typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t;
 
 /**
@@ -289,11 +290,11 @@ static inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp)
  * @cpumask: the cpumask pointer
  *
  * Returns 1 if @cpu is set in @cpumask, else returns 0
- *
- * No static inline type checking - see Subtlety (1) above.
  */
-#define cpumask_test_cpu(cpu, cpumask) \
-	test_bit(cpumask_check(cpu), cpumask_bits((cpumask)))
+static inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask)
+{
+	return test_bit(cpumask_check(cpu), cpumask_bits((cpumask)));
+}
 
 /**
  * cpumask_test_and_set_cpu - atomically test and set a cpu in a cpumask
@@ -609,9 +610,7 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp)
  */
 static inline size_t cpumask_size(void)
 {
-	/* FIXME: Once all cpumask assignments are eliminated, this
-	 * can be nr_cpumask_bits */
-	return BITS_TO_LONGS(NR_CPUS) * sizeof(long);
+	return BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long);
 }
 
 /*
@@ -768,7 +767,7 @@ static inline const struct cpumask *get_cpu_mask(unsigned int cpu)
 #if NR_CPUS <= BITS_PER_LONG
 #define CPU_BITS_ALL						\
 {								\
-	[BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD	\
+	[BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS)	\
 }
 
 #else /* NR_CPUS > BITS_PER_LONG */
@@ -776,7 +775,7 @@ static inline const struct cpumask *get_cpu_mask(unsigned int cpu)
 #define CPU_BITS_ALL						\
 {								\
 	[0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL,		\
-	[BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD		\
+	[BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS)	\
 }
 #endif /* NR_CPUS > BITS_PER_LONG */
 
@@ -797,32 +796,18 @@ cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask)
 				      nr_cpu_ids);
 }
 
-/*
- *
- * From here down, all obsolete.  Use cpumask_ variants!
- *
- */
-#ifndef CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
-#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			\
+	[BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS)	\
 } }
-
 #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			\
+	[BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS)	\
 } }
-
-#endif
+#endif /* NR_CPUS > BITS_PER_LONG */
 
 #define CPU_MASK_NONE							\
 (cpumask_t) { {								\
@@ -834,143 +819,4 @@ cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask)
 	[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);
-
-#define first_cpu(src)		__first_cpu(&(src))
-#define next_cpu(n, src)	__next_cpu((n), &(src))
-#define any_online_cpu(mask) cpumask_any_and(&mask, cpu_online_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, unsigned int nbits)
-{
-	bitmap_fill(dstp->bits, nbits);
-}
-
-#define cpus_clear(dst) __cpus_clear(&(dst), NR_CPUS)
-static inline void __cpus_clear(cpumask_t *dstp, unsigned 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, unsigned 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, unsigned 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, unsigned 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, unsigned 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, unsigned 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, unsigned 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, unsigned 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, unsigned 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, unsigned 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/lib/Kconfig b/lib/Kconfig
index f5440221d929..601965a948e8 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -396,10 +396,6 @@ config CPUMASK_OFFSTACK
 	  them on the stack.  This is a bit more expensive, but avoids
 	  stack overflow.
 
-config DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
-       bool "Disable obsolete cpumask functions" if DEBUG_PER_CPU_MAPS
-       depends on BROKEN
-
 config CPU_RMAP
 	bool
 	depends on SMP
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 5ab1553fd076..830dd5dec40f 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -5,27 +5,6 @@
 #include <linux/export.h>
 #include <linux/bootmem.h>
 
-int __first_cpu(const cpumask_t *srcp)
-{
-	return min_t(int, NR_CPUS, find_first_bit(srcp->bits, NR_CPUS));
-}
-EXPORT_SYMBOL(__first_cpu);
-
-int __next_cpu(int n, const cpumask_t *srcp)
-{
-	return min_t(int, NR_CPUS, find_next_bit(srcp->bits, NR_CPUS, n+1));
-}
-EXPORT_SYMBOL(__next_cpu);
-
-#if NR_CPUS > 64
-int __next_cpu_nr(int n, const cpumask_t *srcp)
-{
-	return min_t(int, nr_cpu_ids,
-				find_next_bit(srcp->bits, nr_cpu_ids, n+1));
-}
-EXPORT_SYMBOL(__next_cpu_nr);
-#endif
-
 /**
  * cpumask_next_and - get the next cpu in *src1p & *src2p
  * @n: the cpu prior to the place to search (ie. return will be > @n)
@@ -90,13 +69,6 @@ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
 		dump_stack();
 	}
 #endif
-	/* FIXME: Bandaid to save us from old primitives which go to NR_CPUS. */
-	if (*mask) {
-		unsigned char *ptr = (unsigned char *)cpumask_bits(*mask);
-		unsigned int tail;
-		tail = BITS_TO_LONGS(NR_CPUS - nr_cpumask_bits) * sizeof(long);
-		memset(ptr + cpumask_size() - tail, 0, tail);
-	}
 
 	return *mask != NULL;
 }