---
 Documentation/cputopology.txt           |    6 +-
 arch/alpha/kernel/irq.c                 |    2 
 arch/arm/kernel/irq.c                   |   18 ++++--
 arch/arm/oprofile/op_model_mpcore.c     |    2 
 arch/blackfin/kernel/irqchip.c          |    5 +
 arch/ia64/kernel/iosapic.c              |    2 
 arch/ia64/kernel/irq.c                  |    4 -
 arch/ia64/kernel/irq_ia64.c             |   12 ++--
 arch/ia64/kernel/msi_ia64.c             |    4 -
 arch/ia64/sn/kernel/msi_sn.c            |    2 
 arch/mips/kernel/irq-gic.c              |    2 
 arch/mips/kernel/smtc.c                 |    6 +-
 arch/mips/mti-malta/malta-smtc.c        |    5 +
 arch/mips/sgi-ip22/ip22-int.c           |    2 
 arch/mips/sgi-ip22/ip22-time.c          |    2 
 arch/mips/sibyte/bcm1480/smp.c          |    3 -
 arch/mips/sibyte/sb1250/smp.c           |    3 -
 arch/mn10300/kernel/mn10300-watchdog.c  |    3 -
 arch/parisc/kernel/irq.c                |    8 +-
 arch/powerpc/kernel/irq.c               |    2 
 arch/powerpc/platforms/pseries/xics.c   |    5 +
 arch/powerpc/sysdev/mpic.c              |    3 -
 arch/sparc/kernel/irq_64.c              |    5 +
 arch/sparc/kernel/time_64.c             |    2 
 arch/x86/kernel/apic.c                  |    5 +
 arch/x86/kernel/cpu/intel_cacheinfo.c   |   63 ++++++++++++++++-------
 arch/x86/kernel/cpu/mcheck/mce_amd_64.c |   21 +++++--
 arch/x86/kernel/io_apic.c               |   38 ++++++++++----
 arch/x86/kernel/irq_32.c                |    2 
 arch/x86/kernel/irq_64.c                |    2 
 arch/x86/kernel/tlb_32.c                |   67 ++++++++++--------------
 arch/x86/kernel/tlb_64.c                |   63 +++++++++++++----------
 arch/x86/kernel/tlb_uv.c                |   16 ++---
 arch/x86/xen/enlighten.c                |   31 ++++-------
 drivers/base/cpu.c                      |    2 
 drivers/base/topology.c                 |   33 +++++-------
 drivers/misc/sgi-xp/xpc_main.c          |    2 
 drivers/net/sfc/efx.c                   |   17 ++++--
 drivers/oprofile/buffer_sync.c          |   22 ++++++--
 drivers/oprofile/buffer_sync.h          |    4 +
 drivers/oprofile/oprof.c                |    9 ++-
 drivers/xen/events.c                    |   26 +++++++--
 drivers/xen/manage.c                    |    2 
 include/linux/interrupt.h               |    1 
 include/linux/irq.h                     |   86 ++++++++++++++++++++++++++++++--
 include/linux/irqnr.h                   |    1 
 include/linux/topology.h                |    6 ++
 kernel/irq/chip.c                       |    5 +
 kernel/irq/handle.c                     |   57 +++++++++++++--------
 kernel/irq/internals.h                  |    7 ++
 kernel/irq/manage.c                     |   12 ++--
 kernel/irq/migration.c                  |   12 ++--
 kernel/irq/numa_migrate.c               |   19 +++++--
 kernel/irq/proc.c                       |    4 -
 kernel/softirq.c                        |    5 +
 55 files changed, 494 insertions(+), 254 deletions(-)

diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -18,11 +18,11 @@ these macros in include/asm-XXX/topology
 these macros in include/asm-XXX/topology.h:
 #define topology_physical_package_id(cpu)
 #define topology_core_id(cpu)
-#define topology_thread_siblings(cpu)
-#define topology_core_siblings(cpu)
+#define topology_thread_cpumask(cpu)
+#define topology_core_cpumask(cpu)
 
 The type of **_id is int.
-The type of siblings is cpumask_t.
+The type of siblings is (const) struct cpumask *.
 
 To be consistent on all architectures, include/linux/topology.h
 provides default definitions for any of the above macros that are
diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c
--- a/arch/alpha/kernel/irq.c
+++ b/arch/alpha/kernel/irq.c
@@ -55,7 +55,7 @@ int irq_select_affinity(unsigned int irq
 		cpu = (cpu < (NR_CPUS-1) ? cpu + 1 : 0);
 	last_cpu = cpu;
 
-	irq_desc[irq].affinity = cpumask_of_cpu(cpu);
+	cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu));
 	irq_desc[irq].chip->set_affinity(irq, cpumask_of(cpu));
 	return 0;
 }
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -104,6 +104,11 @@ static struct irq_desc bad_irq_desc = {
 	.lock = __SPIN_LOCK_UNLOCKED(bad_irq_desc.lock),
 };
 
+#ifdef CONFIG_CPUMASK_OFFSTACK
+/* We are not allocating bad_irq_desc.affinity or .pending_mask */
+#error "ARM architecture does not support CONFIG_CPUMASK_OFFSTACK."
+#endif
+
 /*
  * do_IRQ handles all hardware IRQ's.  Decoded IRQs should not
  * come via this function.  Instead, they should provide their
@@ -161,7 +166,7 @@ void __init init_IRQ(void)
 		irq_desc[irq].status |= IRQ_NOREQUEST | IRQ_NOPROBE;
 
 #ifdef CONFIG_SMP
-	bad_irq_desc.affinity = CPU_MASK_ALL;
+	cpumask_setall(bad_irq_desc.affinity);
 	bad_irq_desc.cpu = smp_processor_id();
 #endif
 	init_arch_irq();
@@ -191,15 +196,16 @@ void migrate_irqs(void)
 		struct irq_desc *desc = irq_desc + i;
 
 		if (desc->cpu == cpu) {
-			unsigned int newcpu = any_online_cpu(desc->affinity);
-
-			if (newcpu == NR_CPUS) {
+			unsigned int newcpu = cpumask_any_and(desc->affinity,
+							      cpu_online_mask);
+			if (newcpu >= nr_cpu_ids) {
 				if (printk_ratelimit())
 					printk(KERN_INFO "IRQ%u no longer affine to CPU%u\n",
 					       i, cpu);
 
-				cpus_setall(desc->affinity);
-				newcpu = any_online_cpu(desc->affinity);
+				cpumask_setall(desc->affinity);
+				newcpu = cpumask_any_and(desc->affinity,
+							 cpu_online_mask);
 			}
 
 			route_irq(desc, i, newcpu);
diff --git a/arch/arm/oprofile/op_model_mpcore.c b/arch/arm/oprofile/op_model_mpcore.c
--- a/arch/arm/oprofile/op_model_mpcore.c
+++ b/arch/arm/oprofile/op_model_mpcore.c
@@ -263,7 +263,7 @@ static void em_route_irq(int irq, unsign
 	const struct cpumask *mask = cpumask_of(cpu);
 
 	spin_lock_irq(&desc->lock);
-	desc->affinity = *mask;
+	cpumask_copy(desc->affinity, mask);
 	desc->chip->set_affinity(irq, mask);
 	spin_unlock_irq(&desc->lock);
 }
diff --git a/arch/blackfin/kernel/irqchip.c b/arch/blackfin/kernel/irqchip.c
--- a/arch/blackfin/kernel/irqchip.c
+++ b/arch/blackfin/kernel/irqchip.c
@@ -69,6 +69,11 @@ static struct irq_desc bad_irq_desc = {
 	.affinity = CPU_MASK_ALL
 #endif
 };
+
+#ifdef CONFIG_CPUMASK_OFFSTACK
+/* We are not allocating a variable-sized bad_irq_desc.affinity */
+#error "Blackfin architecture does not support CONFIG_CPUMASK_OFFSTACK."
+#endif
 
 int show_interrupts(struct seq_file *p, void *v)
 {
diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c
--- a/arch/ia64/kernel/iosapic.c
+++ b/arch/ia64/kernel/iosapic.c
@@ -880,7 +880,7 @@ iosapic_unregister_intr (unsigned int gs
 	if (iosapic_intr_info[irq].count == 0) {
 #ifdef CONFIG_SMP
 		/* Clear affinity */
-		cpus_setall(idesc->affinity);
+		cpumask_setall(idesc->affinity);
 #endif
 		/* Clear the interrupt information */
 		iosapic_intr_info[irq].dest = 0;
diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c
--- a/arch/ia64/kernel/irq.c
+++ b/arch/ia64/kernel/irq.c
@@ -103,7 +103,7 @@ void set_irq_affinity_info (unsigned int
 void set_irq_affinity_info (unsigned int irq, int hwid, int redir)
 {
 	if (irq < NR_IRQS) {
-		cpumask_copy(&irq_desc[irq].affinity,
+		cpumask_copy(irq_desc[irq].affinity,
 			     cpumask_of(cpu_logical_id(hwid)));
 		irq_redir[irq] = (char) (redir & 0xff);
 	}
@@ -148,7 +148,7 @@ static void migrate_irqs(void)
 		if (desc->status == IRQ_PER_CPU)
 			continue;
 
-		if (cpumask_any_and(&irq_desc[irq].affinity, cpu_online_mask)
+		if (cpumask_any_and(irq_desc[irq].affinity, cpu_online_mask)
 		    >= nr_cpu_ids) {
 			/*
 			 * Save it for phase 2 processing
diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -493,11 +493,13 @@ ia64_handle_irq (ia64_vector vector, str
 	saved_tpr = ia64_getreg(_IA64_REG_CR_TPR);
 	ia64_srlz_d();
 	while (vector != IA64_SPURIOUS_INT_VECTOR) {
+		struct irq_desc *desc = irq_to_desc(vector);
+
 		if (unlikely(IS_LOCAL_TLB_FLUSH(vector))) {
 			smp_local_flush_tlb();
-			kstat_this_cpu.irqs[vector]++;
+			kstat_incr_irqs_this_cpu(vector, desc);
 		} else if (unlikely(IS_RESCHEDULE(vector)))
-			kstat_this_cpu.irqs[vector]++;
+			kstat_incr_irqs_this_cpu(vector, desc);
 		else {
 			int irq = local_vector_to_irq(vector);
 
@@ -551,11 +553,13 @@ void ia64_process_pending_intr(void)
 	  * Perform normal interrupt style processing
 	  */
 	while (vector != IA64_SPURIOUS_INT_VECTOR) {
+		struct irq_desc *desc = irq_to_desc(vector);
+
 		if (unlikely(IS_LOCAL_TLB_FLUSH(vector))) {
 			smp_local_flush_tlb();
-			kstat_this_cpu.irqs[vector]++;
+			kstat_incr_irqs_this_cpu(vector, desc);
 		} else if (unlikely(IS_RESCHEDULE(vector)))
-			kstat_this_cpu.irqs[vector]++;
+			kstat_incr_irqs_this_cpu(vector, desc);
 		else {
 			struct pt_regs *old_regs = set_irq_regs(NULL);
 			int irq = local_vector_to_irq(vector);
diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c
--- a/arch/ia64/kernel/msi_ia64.c
+++ b/arch/ia64/kernel/msi_ia64.c
@@ -75,7 +75,7 @@ static void ia64_set_msi_irq_affinity(un
 	msg.data = data;
 
 	write_msi_msg(irq, &msg);
-	irq_desc[irq].affinity = cpumask_of_cpu(cpu);
+	cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu));
 }
 #endif /* CONFIG_SMP */
 
@@ -187,7 +187,7 @@ static void dmar_msi_set_affinity(unsign
 	msg.address_lo |= MSI_ADDR_DESTID_CPU(cpu_physical_id(cpu));
 
 	dmar_msi_write(irq, &msg);
-	irq_desc[irq].affinity = *mask;
+	cpumask_copy(irq_desc[irq].affinity, mask);
 }
 #endif /* CONFIG_SMP */
 
diff --git a/arch/ia64/sn/kernel/msi_sn.c b/arch/ia64/sn/kernel/msi_sn.c
--- a/arch/ia64/sn/kernel/msi_sn.c
+++ b/arch/ia64/sn/kernel/msi_sn.c
@@ -205,7 +205,7 @@ static void sn_set_msi_irq_affinity(unsi
 	msg.address_lo = (u32)(bus_addr & 0x00000000ffffffff);
 
 	write_msi_msg(irq, &msg);
-	irq_desc[irq].affinity = *cpu_mask;
+	cpumask_copy(irq_desc[irq].affinity, cpu_mask);
 }
 #endif /* CONFIG_SMP */
 
diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c
--- a/arch/mips/kernel/irq-gic.c
+++ b/arch/mips/kernel/irq-gic.c
@@ -187,7 +187,7 @@ static void gic_set_affinity(unsigned in
 		set_bit(irq, pcpu_masks[first_cpu(tmp)].pcpu_mask);
 
 	}
-	irq_desc[irq].affinity = *cpumask;
+	cpumask_copy(irq_desc[irq].affinity, cpumask);
 	spin_unlock_irqrestore(&gic_lock, flags);
 
 }
diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c
--- a/arch/mips/kernel/smtc.c
+++ b/arch/mips/kernel/smtc.c
@@ -686,7 +686,7 @@ void smtc_forward_irq(unsigned int irq)
 	 * and efficiency, we just pick the easiest one to find.
 	 */
 
-	target = first_cpu(irq_desc[irq].affinity);
+	target = cpumask_first(irq_desc[irq].affinity);
 
 	/*
 	 * We depend on the platform code to have correctly processed
@@ -921,11 +921,13 @@ void ipi_decode(struct smtc_ipi *pipi)
 	struct clock_event_device *cd;
 	void *arg_copy = pipi->arg;
 	int type_copy = pipi->type;
+	int irq = MIPS_CPU_IRQ_BASE + 1;
+
 	smtc_ipi_nq(&freeIPIq, pipi);
 	switch (type_copy) {
 	case SMTC_CLOCK_TICK:
 		irq_enter();
-		kstat_this_cpu.irqs[MIPS_CPU_IRQ_BASE + 1]++;
+		kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
 		cd = &per_cpu(mips_clockevent_device, cpu);
 		cd->event_handler(cd);
 		irq_exit();
diff --git a/arch/mips/mti-malta/malta-smtc.c b/arch/mips/mti-malta/malta-smtc.c
--- a/arch/mips/mti-malta/malta-smtc.c
+++ b/arch/mips/mti-malta/malta-smtc.c
@@ -116,7 +116,7 @@ struct plat_smp_ops msmtc_smp_ops = {
 
 void plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity)
 {
-	cpumask_t tmask = *affinity;
+	cpumask_t tmask;
 	int cpu = 0;
 	void smtc_set_irq_affinity(unsigned int irq, cpumask_t aff);
 
@@ -139,11 +139,12 @@ void plat_set_irq_affinity(unsigned int 
 	 * be made to forward to an offline "CPU".
 	 */
 
+	cpumask_copy(&tmask, affinity);
 	for_each_cpu(cpu, affinity) {
 		if ((cpu_data[cpu].vpe_id != 0) || !cpu_online(cpu))
 			cpu_clear(cpu, tmask);
 	}
-	irq_desc[irq].affinity = tmask;
+	cpumask_copy(irq_desc[irq].affinity, &tmask);
 
 	if (cpus_empty(tmask))
 		/*
diff --git a/arch/mips/sgi-ip22/ip22-int.c b/arch/mips/sgi-ip22/ip22-int.c
--- a/arch/mips/sgi-ip22/ip22-int.c
+++ b/arch/mips/sgi-ip22/ip22-int.c
@@ -155,7 +155,7 @@ static void indy_buserror_irq(void)
 	int irq = SGI_BUSERR_IRQ;
 
 	irq_enter();
-	kstat_this_cpu.irqs[irq]++;
+	kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
 	ip22_be_interrupt(irq);
 	irq_exit();
 }
diff --git a/arch/mips/sgi-ip22/ip22-time.c b/arch/mips/sgi-ip22/ip22-time.c
--- a/arch/mips/sgi-ip22/ip22-time.c
+++ b/arch/mips/sgi-ip22/ip22-time.c
@@ -122,7 +122,7 @@ void indy_8254timer_irq(void)
 	char c;
 
 	irq_enter();
-	kstat_this_cpu.irqs[irq]++;
+	kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
 	printk(KERN_ALERT "Oops, got 8254 interrupt.\n");
 	ArcRead(0, &c, 1, &cnt);
 	ArcEnterInteractiveMode();
diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c
--- a/arch/mips/sibyte/bcm1480/smp.c
+++ b/arch/mips/sibyte/bcm1480/smp.c
@@ -178,9 +178,10 @@ void bcm1480_mailbox_interrupt(void)
 void bcm1480_mailbox_interrupt(void)
 {
 	int cpu = smp_processor_id();
+	int irq = K_BCM1480_INT_MBOX_0_0;
 	unsigned int action;
 
-	kstat_this_cpu.irqs[K_BCM1480_INT_MBOX_0_0]++;
+	kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
 	/* Load the mailbox register to figure out what we're supposed to do */
 	action = (__raw_readq(mailbox_0_regs[cpu]) >> 48) & 0xffff;
 
diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c
--- a/arch/mips/sibyte/sb1250/smp.c
+++ b/arch/mips/sibyte/sb1250/smp.c
@@ -166,9 +166,10 @@ void sb1250_mailbox_interrupt(void)
 void sb1250_mailbox_interrupt(void)
 {
 	int cpu = smp_processor_id();
+	int irq = K_INT_MBOX_0;
 	unsigned int action;
 
-	kstat_this_cpu.irqs[K_INT_MBOX_0]++;
+	kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
 	/* Load the mailbox register to figure out what we're supposed to do */
 	action = (____raw_readq(mailbox_regs[cpu]) >> 48) & 0xffff;
 
diff --git a/arch/mn10300/kernel/mn10300-watchdog.c b/arch/mn10300/kernel/mn10300-watchdog.c
--- a/arch/mn10300/kernel/mn10300-watchdog.c
+++ b/arch/mn10300/kernel/mn10300-watchdog.c
@@ -130,6 +130,7 @@ void watchdog_interrupt(struct pt_regs *
 	 * the stack NMI-atomically, it's safe to use smp_processor_id().
 	 */
 	int sum, cpu = smp_processor_id();
+	int irq = NMIIRQ;
 	u8 wdt, tmp;
 
 	wdt = WDCTR & ~WDCTR_WDCNE;
@@ -138,7 +139,7 @@ void watchdog_interrupt(struct pt_regs *
 	NMICR = NMICR_WDIF;
 
 	nmi_count(cpu)++;
-	kstat_this_cpu.irqs[NMIIRQ]++;
+	kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
 	sum = irq_stat[cpu].__irq_count;
 
 	if (last_irq_sums[cpu] == sum) {
diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c
--- a/arch/parisc/kernel/irq.c
+++ b/arch/parisc/kernel/irq.c
@@ -120,7 +120,7 @@ int cpu_check_affinity(unsigned int irq,
 	if (CHECK_IRQ_PER_CPU(irq)) {
 		/* Bad linux design decision.  The mask has already
 		 * been set; we must reset it */
-		irq_desc[irq].affinity = CPU_MASK_ALL;
+		cpumask_setall(irq_desc[irq].affinity);
 		return -EINVAL;
 	}
 
@@ -136,7 +136,7 @@ static void cpu_set_affinity_irq(unsigne
 	if (cpu_check_affinity(irq, dest))
 		return;
 
-	irq_desc[irq].affinity = *dest;
+	cpumask_copy(irq_desc[irq].affinity, dest);
 }
 #endif
 
@@ -295,7 +295,7 @@ unsigned long txn_affinity_addr(unsigned
 unsigned long txn_affinity_addr(unsigned int irq, int cpu)
 {
 #ifdef CONFIG_SMP
-	irq_desc[irq].affinity = cpumask_of_cpu(cpu);
+	cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu));
 #endif
 
 	return per_cpu(cpu_data, cpu).txn_addr;
@@ -352,7 +352,7 @@ void do_cpu_irq_mask(struct pt_regs *reg
 	irq = eirr_to_irq(eirr_val);
 
 #ifdef CONFIG_SMP
-	dest = irq_desc[irq].affinity;
+	cpumask_copy(&dest, irq_desc[irq].affinity);
 	if (CHECK_IRQ_PER_CPU(irq_desc[irq].status) &&
 	    !cpu_isset(smp_processor_id(), dest)) {
 		int cpu = first_cpu(dest);
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -231,7 +231,7 @@ void fixup_irqs(cpumask_t map)
 		if (irq_desc[irq].status & IRQ_PER_CPU)
 			continue;
 
-		cpus_and(mask, irq_desc[irq].affinity, map);
+		cpumask_and(&mask, irq_desc[irq].affinity, &map);
 		if (any_online_cpu(mask) == NR_CPUS) {
 			printk("Breaking affinity for irq %i\n", irq);
 			mask = map;
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -153,9 +153,10 @@ static int get_irq_server(unsigned int v
 {
 	int server;
 	/* For the moment only implement delivery to all cpus or one cpu */
-	cpumask_t cpumask = irq_desc[virq].affinity;
+	cpumask_t cpumask;
 	cpumask_t tmp = CPU_MASK_NONE;
 
+	cpumask_copy(&cpumask, irq_desc[virq].affinity);
 	if (!distribute_irqs)
 		return default_server;
 
@@ -869,7 +870,7 @@ void xics_migrate_irqs_away(void)
 		       virq, cpu);
 
 		/* Reset affinity to all cpus */
-		irq_desc[virq].affinity = CPU_MASK_ALL;
+		cpumask_setall(irq_desc[virq].affinity);
 		desc->chip->set_affinity(virq, cpu_all_mask);
 unlock:
 		spin_unlock_irqrestore(&desc->lock, flags);
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -566,9 +566,10 @@ static void __init mpic_scan_ht_pics(str
 #ifdef CONFIG_SMP
 static int irq_choose_cpu(unsigned int virt_irq)
 {
-	cpumask_t mask = irq_desc[virt_irq].affinity;
+	cpumask_t mask;
 	int cpuid;
 
+	cpumask_copy(&mask, irq_desc[virt_irq].affinity);
 	if (cpus_equal(mask, CPU_MASK_ALL)) {
 		static int irq_rover;
 		static DEFINE_SPINLOCK(irq_rover_lock);
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -252,9 +252,10 @@ struct irq_handler_data {
 #ifdef CONFIG_SMP
 static int irq_choose_cpu(unsigned int virt_irq)
 {
-	cpumask_t mask = irq_desc[virt_irq].affinity;
+	cpumask_t mask;
 	int cpuid;
 
+	cpumask_copy(&mask, irq_desc[virt_irq].affinity);
 	if (cpus_equal(mask, CPU_MASK_ALL)) {
 		static int irq_rover;
 		static DEFINE_SPINLOCK(irq_rover_lock);
@@ -796,7 +797,7 @@ void fixup_irqs(void)
 		    !(irq_desc[irq].status & IRQ_PER_CPU)) {
 			if (irq_desc[irq].chip->set_affinity)
 				irq_desc[irq].chip->set_affinity(irq,
-					&irq_desc[irq].affinity);
+					irq_desc[irq].affinity);
 		}
 		spin_unlock_irqrestore(&irq_desc[irq].lock, flags);
 	}
diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c
--- a/arch/sparc/kernel/time_64.c
+++ b/arch/sparc/kernel/time_64.c
@@ -729,7 +729,7 @@ void timer_interrupt(int irq, struct pt_
 
 	irq_enter();
 
-	kstat_this_cpu.irqs[0]++;
+	kstat_incr_irqs_this_cpu(0, irq_to_desc(0));
 
 	if (unlikely(!evt->event_handler)) {
 		printk(KERN_WARNING
diff --git a/arch/x86/kernel/apic.c b/arch/x86/kernel/apic.c
--- a/arch/x86/kernel/apic.c
+++ b/arch/x86/kernel/apic.c
@@ -1842,6 +1842,11 @@ void __cpuinit generic_processor_info(in
 			"ACPI: apic version mismatch, bootcpu: %x cpu %d: %x\n",
 			apic_version[boot_cpu_physical_apicid], cpu, version);
 
+	if (version != apic_version[boot_cpu_physical_apicid])
+		WARN_ONCE(1,
+			"ACPI: apic version mismatch, bootcpu: %x cpu %d: %x\n",
+			apic_version[boot_cpu_physical_apicid], cpu, version);
+
 	physid_set(apicid, phys_cpu_present_map);
 	if (apicid == boot_cpu_physical_apicid) {
 		/*
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -147,7 +147,16 @@ struct _cpuid4_info {
 	union _cpuid4_leaf_ecx ecx;
 	unsigned long size;
 	unsigned long can_disable;
-	cpumask_t shared_cpu_map;	/* future?: only cpus/node is needed */
+	DECLARE_BITMAP(shared_cpu_map, NR_CPUS);
+};
+
+/* subset of above _cpuid4_info w/o shared_cpu_map */
+struct _cpuid4_info_regs {
+	union _cpuid4_leaf_eax eax;
+	union _cpuid4_leaf_ebx ebx;
+	union _cpuid4_leaf_ecx ecx;
+	unsigned long size;
+	unsigned long can_disable;
 };
 
 #ifdef CONFIG_PCI
@@ -278,7 +287,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_
 }
 
 static void __cpuinit
-amd_check_l3_disable(int index, struct _cpuid4_info *this_leaf)
+amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
 {
 	if (index < 3)
 		return;
@@ -286,7 +295,8 @@ amd_check_l3_disable(int index, struct _
 }
 
 static int
-__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
+__cpuinit cpuid4_cache_lookup_regs(int index,
+				   struct _cpuid4_info_regs *this_leaf)
 {
 	union _cpuid4_leaf_eax 	eax;
 	union _cpuid4_leaf_ebx 	ebx;
@@ -312,6 +322,15 @@ __cpuinit cpuid4_cache_lookup(int index,
 			  (ebx.split.physical_line_partition + 1) *
 			  (ebx.split.ways_of_associativity   + 1);
 	return 0;
+}
+
+static int
+__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
+{
+	struct _cpuid4_info_regs *leaf_regs =
+		(struct _cpuid4_info_regs *)this_leaf;
+
+	return cpuid4_cache_lookup_regs(index, leaf_regs);
 }
 
 static int __cpuinit find_num_cache_leaves(void)
@@ -353,11 +372,10 @@ unsigned int __cpuinit init_intel_cachei
 		 * parameters cpuid leaf to find the cache details
 		 */
 		for (i = 0; i < num_cache_leaves; i++) {
-			struct _cpuid4_info this_leaf;
-
+			struct _cpuid4_info_regs this_leaf;
 			int retval;
 
-			retval = cpuid4_cache_lookup(i, &this_leaf);
+			retval = cpuid4_cache_lookup_regs(i, &this_leaf);
 			if (retval >= 0) {
 				switch(this_leaf.eax.split.level) {
 				    case 1:
@@ -506,17 +524,20 @@ static void __cpuinit cache_shared_cpu_m
 	num_threads_sharing = 1 + this_leaf->eax.split.num_threads_sharing;
 
 	if (num_threads_sharing == 1)
-		cpu_set(cpu, this_leaf->shared_cpu_map);
+		cpumask_set_cpu(cpu, to_cpumask(this_leaf->shared_cpu_map));
 	else {
 		index_msb = get_count_order(num_threads_sharing);
 
 		for_each_online_cpu(i) {
 			if (cpu_data(i).apicid >> index_msb ==
 			    c->apicid >> index_msb) {
-				cpu_set(i, this_leaf->shared_cpu_map);
+				cpumask_set_cpu(i,
+					to_cpumask(this_leaf->shared_cpu_map));
 				if (i != cpu && per_cpu(cpuid4_info, i))  {
-					sibling_leaf = CPUID4_INFO_IDX(i, index);
-					cpu_set(cpu, sibling_leaf->shared_cpu_map);
+					sibling_leaf =
+						CPUID4_INFO_IDX(i, index);
+					cpumask_set_cpu(cpu, to_cpumask(
+						sibling_leaf->shared_cpu_map));
 				}
 			}
 		}
@@ -528,9 +549,10 @@ static void __cpuinit cache_remove_share
 	int sibling;
 
 	this_leaf = CPUID4_INFO_IDX(cpu, index);
-	for_each_cpu_mask_nr(sibling, this_leaf->shared_cpu_map) {
+	for_each_cpu(sibling, to_cpumask(this_leaf->shared_cpu_map)) {
 		sibling_leaf = CPUID4_INFO_IDX(sibling, index);
-		cpu_clear(cpu, sibling_leaf->shared_cpu_map);
+		cpumask_clear_cpu(cpu,
+				  to_cpumask(sibling_leaf->shared_cpu_map));
 	}
 }
 #else
@@ -635,8 +657,9 @@ static ssize_t show_shared_cpu_map_func(
 	int n = 0;
 
 	if (len > 1) {
-		cpumask_t *mask = &this_leaf->shared_cpu_map;
+		const struct cpumask *mask;
 
+		mask = to_cpumask(this_leaf->shared_cpu_map);
 		n = type?
 			cpulist_scnprintf(buf, len-2, mask) :
 			cpumask_scnprintf(buf, len-2, mask);
@@ -699,7 +722,8 @@ static struct pci_dev *get_k8_northbridg
 
 static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf)
 {
-	int node = cpu_to_node(first_cpu(this_leaf->shared_cpu_map));
+	const struct cpumask *mask = to_cpumask(this_leaf->shared_cpu_map);
+	int node = cpu_to_node(cpumask_first(mask));
 	struct pci_dev *dev = NULL;
 	ssize_t ret = 0;
 	int i;
@@ -733,7 +757,8 @@ store_cache_disable(struct _cpuid4_info 
 store_cache_disable(struct _cpuid4_info *this_leaf, const char *buf,
 		    size_t count)
 {
-	int node = cpu_to_node(first_cpu(this_leaf->shared_cpu_map));
+	const struct cpumask *mask = to_cpumask(this_leaf->shared_cpu_map);
+	int node = cpu_to_node(cpumask_first(mask));
 	struct pci_dev *dev = NULL;
 	unsigned int ret, index, val;
 
@@ -878,7 +903,7 @@ err_out:
 	return -ENOMEM;
 }
 
-static cpumask_t cache_dev_map = CPU_MASK_NONE;
+static DECLARE_BITMAP(cache_dev_map, NR_CPUS);
 
 /* Add/Remove cache interface for CPU device */
 static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
@@ -918,7 +943,7 @@ static int __cpuinit cache_add_dev(struc
 		}
 		kobject_uevent(&(this_object->kobj), KOBJ_ADD);
 	}
-	cpu_set(cpu, cache_dev_map);
+	cpumask_set_cpu(cpu, to_cpumask(cache_dev_map));
 
 	kobject_uevent(per_cpu(cache_kobject, cpu), KOBJ_ADD);
 	return 0;
@@ -931,9 +956,9 @@ static void __cpuinit cache_remove_dev(s
 
 	if (per_cpu(cpuid4_info, cpu) == NULL)
 		return;
-	if (!cpu_isset(cpu, cache_dev_map))
+	if (!cpumask_test_cpu(cpu, to_cpumask(cache_dev_map)))
 		return;
-	cpu_clear(cpu, cache_dev_map);
+	cpumask_clear_cpu(cpu, to_cpumask(cache_dev_map));
 
 	for (i = 0; i < num_cache_leaves; i++)
 		kobject_put(&(INDEX_KOBJECT_PTR(cpu,i)->kobj));
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
--- a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
@@ -67,7 +67,7 @@ struct threshold_bank {
 struct threshold_bank {
 	struct kobject *kobj;
 	struct threshold_block *blocks;
-	cpumask_t cpus;
+	cpumask_var_t cpus;
 };
 static DEFINE_PER_CPU(struct threshold_bank *, threshold_banks[NR_BANKS]);
 
@@ -481,7 +481,7 @@ static __cpuinit int threshold_create_ba
 
 #ifdef CONFIG_SMP
 	if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) {	/* symlink */
-		i = first_cpu(per_cpu(cpu_core_map, cpu));
+		i = cpumask_first(&per_cpu(cpu_core_map, cpu));
 
 		/* first core not up yet */
 		if (cpu_data(i).cpu_core_id)
@@ -501,7 +501,7 @@ static __cpuinit int threshold_create_ba
 		if (err)
 			goto out;
 
-		b->cpus = per_cpu(cpu_core_map, cpu);
+		cpumask_copy(b->cpus, &per_cpu(cpu_core_map, cpu));
 		per_cpu(threshold_banks, cpu)[bank] = b;
 		goto out;
 	}
@@ -512,15 +512,20 @@ static __cpuinit int threshold_create_ba
 		err = -ENOMEM;
 		goto out;
 	}
+	if (!alloc_cpumask_var(&b->cpus, GFP_KERNEL)) {
+		kfree(b);
+		err = -ENOMEM;
+		goto out;
+	}
 
 	b->kobj = kobject_create_and_add(name, &per_cpu(device_mce, cpu).kobj);
 	if (!b->kobj)
 		goto out_free;
 
 #ifndef CONFIG_SMP
-	b->cpus = CPU_MASK_ALL;
+	cpumask_setall(b->cpus);
 #else
-	b->cpus = per_cpu(cpu_core_map, cpu);
+	cpumask_copy(b->cpus, &per_cpu(cpu_core_map, cpu));
 #endif
 
 	per_cpu(threshold_banks, cpu)[bank] = b;
@@ -529,7 +534,7 @@ static __cpuinit int threshold_create_ba
 	if (err)
 		goto out_free;
 
-	for_each_cpu_mask_nr(i, b->cpus) {
+	for_each_cpu(i, b->cpus) {
 		if (i == cpu)
 			continue;
 
@@ -545,6 +550,7 @@ static __cpuinit int threshold_create_ba
 
 out_free:
 	per_cpu(threshold_banks, cpu)[bank] = NULL;
+	free_cpumask_var(b->cpus);
 	kfree(b);
 out:
 	return err;
@@ -619,7 +625,7 @@ static void threshold_remove_bank(unsign
 #endif
 
 	/* remove all sibling symlinks before unregistering */
-	for_each_cpu_mask_nr(i, b->cpus) {
+	for_each_cpu(i, b->cpus) {
 		if (i == cpu)
 			continue;
 
@@ -632,6 +638,7 @@ free_out:
 free_out:
 	kobject_del(b->kobj);
 	kobject_put(b->kobj);
+	free_cpumask_var(b->cpus);
 	kfree(b);
 	per_cpu(threshold_banks, cpu)[bank] = NULL;
 }
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -356,7 +356,7 @@ set_extra_move_desc(struct irq_desc *des
 
 	if (!cfg->move_in_progress) {
 		/* it means that domain is not changed */
-		if (!cpumask_intersects(&desc->affinity, mask))
+		if (!cpumask_intersects(desc->affinity, mask))
 			cfg->move_desc_pending = 1;
 	}
 }
@@ -579,9 +579,9 @@ set_desc_affinity(struct irq_desc *desc,
 	if (assign_irq_vector(irq, cfg, mask))
 		return BAD_APICID;
 
-	cpumask_and(&desc->affinity, cfg->domain, mask);
+	cpumask_and(desc->affinity, cfg->domain, mask);
 	set_extra_move_desc(desc, mask);
-	return cpu_mask_to_apicid_and(&desc->affinity, cpu_online_mask);
+	return cpu_mask_to_apicid_and(desc->affinity, cpu_online_mask);
 }
 
 static void
@@ -2383,7 +2383,7 @@ migrate_ioapic_irq_desc(struct irq_desc 
 	if (cfg->move_in_progress)
 		send_cleanup_vector(cfg);
 
-	cpumask_copy(&desc->affinity, mask);
+	cpumask_copy(desc->affinity, mask);
 }
 
 static int migrate_irq_remapped_level_desc(struct irq_desc *desc)
@@ -2405,11 +2405,11 @@ static int migrate_irq_remapped_level_de
 	}
 
 	/* everthing is clear. we have right of way */
-	migrate_ioapic_irq_desc(desc, &desc->pending_mask);
+	migrate_ioapic_irq_desc(desc, desc->pending_mask);
 
 	ret = 0;
 	desc->status &= ~IRQ_MOVE_PENDING;
-	cpumask_clear(&desc->pending_mask);
+	cpumask_clear(desc->pending_mask);
 
 unmask:
 	unmask_IO_APIC_irq_desc(desc);
@@ -2434,7 +2434,7 @@ static void ir_irq_migration(struct work
 				continue;
 			}
 
-			desc->chip->set_affinity(irq, &desc->pending_mask);
+			desc->chip->set_affinity(irq, desc->pending_mask);
 			spin_unlock_irqrestore(&desc->lock, flags);
 		}
 	}
@@ -2448,7 +2448,7 @@ static void set_ir_ioapic_affinity_irq_d
 {
 	if (desc->status & IRQ_LEVEL) {
 		desc->status |= IRQ_MOVE_PENDING;
-		cpumask_copy(&desc->pending_mask, mask);
+		cpumask_copy(desc->pending_mask, mask);
 		migrate_irq_remapped_level_desc(desc);
 		return;
 	}
@@ -2516,7 +2516,7 @@ static void irq_complete_move(struct irq
 
 		/* domain has not changed, but affinity did */
 		me = smp_processor_id();
-		if (cpu_isset(me, desc->affinity)) {
+		if (cpumask_test_cpu(me, desc->affinity)) {
 			*descp = desc = move_irq_desc(desc, me);
 			/* get the new one */
 			cfg = desc->chip_data;
@@ -3184,7 +3184,7 @@ unsigned int create_irq_nr(unsigned int 
 
 	irq = 0;
 	spin_lock_irqsave(&vector_lock, flags);
-	for (new = irq_want; new < NR_IRQS; new++) {
+	for (new = irq_want; new < nr_irqs; new++) {
 		if (platform_legacy_irq(new))
 			continue;
 
@@ -3851,6 +3851,22 @@ void __init probe_nr_irqs_gsi(void)
 		nr_irqs_gsi = nr;
 }
 
+#ifdef CONFIG_SPARSE_IRQ
+int __init arch_probe_nr_irqs(void)
+{
+	int nr;
+
+	nr = ((8 * nr_cpu_ids) > (32 * nr_ioapics) ?
+		(NR_VECTORS + (8 * nr_cpu_ids)) :
+		(NR_VECTORS + (32 * nr_ioapics)));
+
+	if (nr < nr_irqs && nr > nr_irqs_gsi)
+		nr_irqs = nr;
+
+	return 0;
+}
+#endif
+
 /* --------------------------------------------------------------------------
                           ACPI-based IOAPIC Configuration
    -------------------------------------------------------------------------- */
@@ -4040,7 +4056,7 @@ void __init setup_ioapic_dest(void)
 			 */
 			if (desc->status &
 			    (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
-				mask = &desc->affinity;
+				mask = desc->affinity;
 			else
 				mask = TARGET_CPUS;
 
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -248,7 +248,7 @@ void fixup_irqs(void)
 		if (irq == 2)
 			continue;
 
-		affinity = &desc->affinity;
+		affinity = desc->affinity;
 		if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
 			printk("Breaking affinity for irq %i\n", irq);
 			affinity = cpu_all_mask;
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -100,7 +100,7 @@ void fixup_irqs(void)
 		/* interrupt's are disabled at this point */
 		spin_lock(&desc->lock);
 
-		affinity = &desc->affinity;
+		affinity = desc->affinity;
 		if (!irq_has_action(irq) ||
 		    cpumask_equal(affinity, cpu_online_mask)) {
 			spin_unlock(&desc->lock);
diff --git a/arch/x86/kernel/tlb_32.c b/arch/x86/kernel/tlb_32.c
--- a/arch/x86/kernel/tlb_32.c
+++ b/arch/x86/kernel/tlb_32.c
@@ -20,7 +20,7 @@ DEFINE_PER_CPU(struct tlb_state, cpu_tlb
  *	Optimizations Manfred Spraul <manfred@colorfullife.com>
  */
 
-static cpumask_t flush_cpumask;
+static cpumask_var_t flush_cpumask;
 static struct mm_struct *flush_mm;
 static unsigned long flush_va;
 static DEFINE_SPINLOCK(tlbstate_lock);
@@ -92,7 +92,7 @@ void smp_invalidate_interrupt(struct pt_
 
 	cpu = get_cpu();
 
-	if (!cpu_isset(cpu, flush_cpumask))
+	if (!cpumask_test_cpu(cpu, flush_cpumask))
 		goto out;
 		/*
 		 * This was a BUG() but until someone can quote me the
@@ -114,34 +114,21 @@ void smp_invalidate_interrupt(struct pt_
 	}
 	ack_APIC_irq();
 	smp_mb__before_clear_bit();
-	cpu_clear(cpu, flush_cpumask);
+	cpumask_clear_cpu(cpu, flush_cpumask);
 	smp_mb__after_clear_bit();
 out:
 	put_cpu_no_resched();
 	inc_irq_stat(irq_tlb_count);
 }
 
-void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm,
-			     unsigned long va)
+void native_flush_tlb_others(const struct cpumask *cpumask,
+			     struct mm_struct *mm, unsigned long va)
 {
-	cpumask_t cpumask = *cpumaskp;
-
 	/*
-	 * A couple of (to be removed) sanity checks:
-	 *
-	 * - current CPU must not be in mask
 	 * - mask must exist :)
 	 */
-	BUG_ON(cpus_empty(cpumask));
-	BUG_ON(cpu_isset(smp_processor_id(), cpumask));
+	BUG_ON(cpumask_empty(cpumask));
 	BUG_ON(!mm);
-
-#ifdef CONFIG_HOTPLUG_CPU
-	/* If a CPU which we ran on has gone down, OK. */
-	cpus_and(cpumask, cpumask, cpu_online_map);
-	if (unlikely(cpus_empty(cpumask)))
-		return;
-#endif
 
 	/*
 	 * i'm not happy about this global shared spinlock in the
@@ -150,9 +137,17 @@ void native_flush_tlb_others(const cpuma
 	 */
 	spin_lock(&tlbstate_lock);
 
+	cpumask_andnot(flush_cpumask, cpumask, cpumask_of(smp_processor_id()));
+#ifdef CONFIG_HOTPLUG_CPU
+	/* If a CPU which we ran on has gone down, OK. */
+	cpumask_and(flush_cpumask, flush_cpumask, cpu_online_mask);
+	if (unlikely(cpumask_empty(flush_cpumask))) {
+		spin_unlock(&tlbstate_lock);
+		return;
+	}
+#endif
 	flush_mm = mm;
 	flush_va = va;
-	cpus_or(flush_cpumask, cpumask, flush_cpumask);
 
 	/*
 	 * Make the above memory operations globally visible before
@@ -163,9 +158,9 @@ void native_flush_tlb_others(const cpuma
 	 * We have to send the IPI only to
 	 * CPUs affected.
 	 */
-	send_IPI_mask(&cpumask, INVALIDATE_TLB_VECTOR);
+	send_IPI_mask(flush_cpumask, INVALIDATE_TLB_VECTOR);
 
-	while (!cpus_empty(flush_cpumask))
+	while (!cpumask_empty(flush_cpumask))
 		/* nothing. lockup detection does not belong here */
 		cpu_relax();
 
@@ -177,25 +172,19 @@ void flush_tlb_current_task(void)
 void flush_tlb_current_task(void)
 {
 	struct mm_struct *mm = current->mm;
-	cpumask_t cpu_mask;
 
 	preempt_disable();
-	cpu_mask = mm->cpu_vm_mask;
-	cpu_clear(smp_processor_id(), cpu_mask);
 
 	local_flush_tlb();
-	if (!cpus_empty(cpu_mask))
-		flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL);
+	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);
 	preempt_enable();
 }
 
 void flush_tlb_mm(struct mm_struct *mm)
 {
-	cpumask_t cpu_mask;
 
 	preempt_disable();
-	cpu_mask = mm->cpu_vm_mask;
-	cpu_clear(smp_processor_id(), cpu_mask);
 
 	if (current->active_mm == mm) {
 		if (current->mm)
@@ -203,8 +192,8 @@ void flush_tlb_mm(struct mm_struct *mm)
 		else
 			leave_mm(smp_processor_id());
 	}
-	if (!cpus_empty(cpu_mask))
-		flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL);
+	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);
 
 	preempt_enable();
 }
@@ -212,11 +201,8 @@ void flush_tlb_page(struct vm_area_struc
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long va)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	cpumask_t cpu_mask;
 
 	preempt_disable();
-	cpu_mask = mm->cpu_vm_mask;
-	cpu_clear(smp_processor_id(), cpu_mask);
 
 	if (current->active_mm == mm) {
 		if (current->mm)
@@ -225,9 +211,8 @@ void flush_tlb_page(struct vm_area_struc
 			leave_mm(smp_processor_id());
 	}
 
-	if (!cpus_empty(cpu_mask))
-		flush_tlb_others(cpu_mask, mm, va);
-
+	if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids)
+		flush_tlb_others(&mm->cpu_vm_mask, mm, va);
 	preempt_enable();
 }
 EXPORT_SYMBOL(flush_tlb_page);
@@ -254,3 +239,9 @@ void reset_lazy_tlbstate(void)
 	per_cpu(cpu_tlbstate, cpu).active_mm = &init_mm;
 }
 
+static int init_flush_cpumask(void)
+{
+	alloc_cpumask_var(&flush_cpumask, GFP_KERNEL);
+	return 0;
+}
+early_initcall(init_flush_cpumask);
diff --git a/arch/x86/kernel/tlb_64.c b/arch/x86/kernel/tlb_64.c
--- a/arch/x86/kernel/tlb_64.c
+++ b/arch/x86/kernel/tlb_64.c
@@ -43,10 +43,10 @@
 
 union smp_flush_state {
 	struct {
-		cpumask_t flush_cpumask;
 		struct mm_struct *flush_mm;
 		unsigned long flush_va;
 		spinlock_t tlbstate_lock;
+		DECLARE_BITMAP(flush_cpumask, NR_CPUS);
 	};
 	char pad[SMP_CACHE_BYTES];
 } ____cacheline_aligned;
@@ -131,7 +131,7 @@ asmlinkage void smp_invalidate_interrupt
 	sender = ~regs->orig_ax - INVALIDATE_TLB_VECTOR_START;
 	f = &per_cpu(flush_state, sender);
 
-	if (!cpu_isset(cpu, f->flush_cpumask))
+	if (!cpumask_test_cpu(cpu, to_cpumask(f->flush_cpumask)))
 		goto out;
 		/*
 		 * This was a BUG() but until someone can quote me the
@@ -153,19 +153,15 @@ asmlinkage void smp_invalidate_interrupt
 	}
 out:
 	ack_APIC_irq();
-	cpu_clear(cpu, f->flush_cpumask);
+	cpumask_clear_cpu(cpu, to_cpumask(f->flush_cpumask));
 	inc_irq_stat(irq_tlb_count);
 }
 
-void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm,
-			     unsigned long va)
+static void flush_tlb_others_ipi(const struct cpumask *cpumask,
+				 struct mm_struct *mm, unsigned long va)
 {
 	int sender;
 	union smp_flush_state *f;
-	cpumask_t cpumask = *cpumaskp;
-
-	if (is_uv_system() && uv_flush_tlb_others(&cpumask, mm, va))
-		return;
 
 	/* Caller has disabled preemption */
 	sender = smp_processor_id() % NUM_INVALIDATE_TLB_VECTORS;
@@ -180,7 +176,8 @@ void native_flush_tlb_others(const cpuma
 
 	f->flush_mm = mm;
 	f->flush_va = va;
-	cpus_or(f->flush_cpumask, cpumask, f->flush_cpumask);
+	cpumask_andnot(to_cpumask(f->flush_cpumask),
+		       cpumask, cpumask_of(smp_processor_id()));
 
 	/*
 	 * Make the above memory operations globally visible before
@@ -191,14 +188,34 @@ void native_flush_tlb_others(const cpuma
 	 * We have to send the IPI only to
 	 * CPUs affected.
 	 */
-	send_IPI_mask(&cpumask, INVALIDATE_TLB_VECTOR_START + sender);
+	send_IPI_mask(to_cpumask(f->flush_cpumask),
+		      INVALIDATE_TLB_VECTOR_START + sender);
 
-	while (!cpus_empty(f->flush_cpumask))
+	while (!cpumask_empty(to_cpumask(f->flush_cpumask)))
 		cpu_relax();
 
 	f->flush_mm = NULL;
 	f->flush_va = 0;
 	spin_unlock(&f->tlbstate_lock);
+}
+
+void native_flush_tlb_others(const struct cpumask *cpumask,
+			     struct mm_struct *mm, unsigned long va)
+{
+	if (is_uv_system()) {
+		/* FIXME: could be an percpu_alloc'd thing */
+		static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask);
+		struct cpumask *after_uv_flush = &get_cpu_var(flush_tlb_mask);
+
+		cpumask_andnot(after_uv_flush, cpumask,
+			       cpumask_of(smp_processor_id()));
+		if (!uv_flush_tlb_others(after_uv_flush, mm, va))
+			flush_tlb_others_ipi(after_uv_flush, mm, va);
+
+		put_cpu_var(flush_tlb_uv_cpumask);
+		return;
+	}
+	flush_tlb_others_ipi(cpumask, mm, va);
 }
 
 static int __cpuinit init_smp_flush(void)
@@ -215,25 +232,18 @@ void flush_tlb_current_task(void)
 void flush_tlb_current_task(void)
 {
 	struct mm_struct *mm = current->mm;
-	cpumask_t cpu_mask;
 
 	preempt_disable();
-	cpu_mask = mm->cpu_vm_mask;
-	cpu_clear(smp_processor_id(), cpu_mask);
 
 	local_flush_tlb();
-	if (!cpus_empty(cpu_mask))
-		flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL);
+	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);
 	preempt_enable();
 }
 
 void flush_tlb_mm(struct mm_struct *mm)
 {
-	cpumask_t cpu_mask;
-
 	preempt_disable();
-	cpu_mask = mm->cpu_vm_mask;
-	cpu_clear(smp_processor_id(), cpu_mask);
 
 	if (current->active_mm == mm) {
 		if (current->mm)
@@ -241,8 +251,8 @@ void flush_tlb_mm(struct mm_struct *mm)
 		else
 			leave_mm(smp_processor_id());
 	}
-	if (!cpus_empty(cpu_mask))
-		flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL);
+	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);
 
 	preempt_enable();
 }
@@ -250,11 +260,8 @@ void flush_tlb_page(struct vm_area_struc
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long va)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	cpumask_t cpu_mask;
 
 	preempt_disable();
-	cpu_mask = mm->cpu_vm_mask;
-	cpu_clear(smp_processor_id(), cpu_mask);
 
 	if (current->active_mm == mm) {
 		if (current->mm)
@@ -263,8 +270,8 @@ void flush_tlb_page(struct vm_area_struc
 			leave_mm(smp_processor_id());
 	}
 
-	if (!cpus_empty(cpu_mask))
-		flush_tlb_others(cpu_mask, mm, va);
+	if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids)
+		flush_tlb_others(&mm->cpu_vm_mask, mm, va);
 
 	preempt_enable();
 }
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -213,11 +213,11 @@ static int uv_wait_completion(struct bau
  * The cpumaskp mask contains the cpus the broadcast was sent to.
  *
  * Returns 1 if all remote flushing was done. The mask is zeroed.
- * Returns 0 if some remote flushing remains to be done. The mask is left
- * unchanged.
+ * Returns 0 if some remote flushing remains to be done. The mask will have
+ * some bits still set.
  */
 int uv_flush_send_and_wait(int cpu, int this_blade, struct bau_desc *bau_desc,
-			   cpumask_t *cpumaskp)
+			   struct cpumask *cpumaskp)
 {
 	int completion_status = 0;
 	int right_shift;
@@ -264,13 +264,13 @@ int uv_flush_send_and_wait(int cpu, int 
 	 * Success, so clear the remote cpu's from the mask so we don't
 	 * use the IPI method of shootdown on them.
 	 */
-	for_each_cpu_mask(bit, *cpumaskp) {
+	for_each_cpu(bit, cpumaskp) {
 		blade = uv_cpu_to_blade_id(bit);
 		if (blade == this_blade)
 			continue;
-		cpu_clear(bit, *cpumaskp);
+		cpumask_clear_cpu(bit, cpumaskp);
 	}
-	if (!cpus_empty(*cpumaskp))
+	if (!cpumask_empty(cpumaskp))
 		return 0;
 	return 1;
 }
@@ -297,7 +297,7 @@ int uv_flush_send_and_wait(int cpu, int 
  * Returns 1 if all remote flushing was done.
  * Returns 0 if some remote flushing remains to be done.
  */
-int uv_flush_tlb_others(cpumask_t *cpumaskp, struct mm_struct *mm,
+int uv_flush_tlb_others(struct cpumask *cpumaskp, struct mm_struct *mm,
 			unsigned long va)
 {
 	int i;
@@ -316,7 +316,7 @@ int uv_flush_tlb_others(cpumask_t *cpuma
 	bau_nodes_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE);
 
 	i = 0;
-	for_each_cpu_mask(bit, *cpumaskp) {
+	for_each_cpu(bit, cpumaskp) {
 		blade = uv_cpu_to_blade_id(bit);
 		BUG_ON(blade > (UV_DISTRIBUTION_SIZE - 1));
 		if (blade == this_blade) {
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -634,35 +634,27 @@ static void xen_flush_tlb_single(unsigne
 	preempt_enable();
 }
 
-static void xen_flush_tlb_others(const cpumask_t *cpus, struct mm_struct *mm,
-				 unsigned long va)
+static void xen_flush_tlb_others(const struct cpumask *cpus,
+				 struct mm_struct *mm, unsigned long va)
 {
 	struct {
 		struct mmuext_op op;
-		cpumask_t mask;
+		DECLARE_BITMAP(mask, NR_CPUS);
 	} *args;
-	cpumask_t cpumask = *cpus;
 	struct multicall_space mcs;
 
-	/*
-	 * A couple of (to be removed) sanity checks:
-	 *
-	 * - current CPU must not be in mask
-	 * - mask must exist :)
-	 */
-	BUG_ON(cpus_empty(cpumask));
-	BUG_ON(cpu_isset(smp_processor_id(), cpumask));
+	BUG_ON(cpumask_empty(cpus));
 	BUG_ON(!mm);
-
-	/* If a CPU which we ran on has gone down, OK. */
-	cpus_and(cpumask, cpumask, cpu_online_map);
-	if (cpus_empty(cpumask))
-		return;
 
 	mcs = xen_mc_entry(sizeof(*args));
 	args = mcs.args;
-	args->mask = cpumask;
-	args->op.arg2.vcpumask = &args->mask;
+	args->op.arg2.vcpumask = to_cpumask(args->mask);
+
+	/* Remove us, and any offline CPUS. */
+	cpumask_and(to_cpumask(args->mask), cpus, cpu_online_mask);
+	cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask));
+	if (unlikely(cpumask_empty(to_cpumask(args->mask))))
+		goto issue;
 
 	if (va == TLB_FLUSH_ALL) {
 		args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
@@ -673,6 +665,7 @@ static void xen_flush_tlb_others(const c
 
 	MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF);
 
+issue:
 	xen_mc_issue(PARAVIRT_LAZY_MMU);
 }
 
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -107,7 +107,7 @@ static SYSDEV_ATTR(crash_notes, 0400, sh
 /*
  * Print cpu online, possible, present, and system maps
  */
-static ssize_t print_cpus_map(char *buf, cpumask_t *map)
+static ssize_t print_cpus_map(char *buf, const struct cpumask *map)
 {
 	int n = cpulist_scnprintf(buf, PAGE_SIZE-2, map);
 
diff --git a/drivers/base/topology.c b/drivers/base/topology.c
--- a/drivers/base/topology.c
+++ b/drivers/base/topology.c
@@ -31,7 +31,10 @@
 #include <linux/hardirq.h>
 #include <linux/topology.h>
 
-#define define_one_ro(_name) 		\
+#define define_one_ro_named(_name, _func)				\
+static SYSDEV_ATTR(_name, 0444, _func, NULL)
+
+#define define_one_ro(_name)				\
 static SYSDEV_ATTR(_name, 0444, show_##_name, NULL)
 
 #define define_id_show_func(name)				\
@@ -42,8 +45,8 @@ static ssize_t show_##name(struct sys_de
 	return sprintf(buf, "%d\n", topology_##name(cpu));	\
 }
 
-#if defined(topology_thread_siblings) || defined(topology_core_siblings)
-static ssize_t show_cpumap(int type, cpumask_t *mask, char *buf)
+#if defined(topology_thread_cpumask) || defined(topology_core_cpumask)
+static ssize_t show_cpumap(int type, const struct cpumask *mask, char *buf)
 {
 	ptrdiff_t len = PTR_ALIGN(buf + PAGE_SIZE - 1, PAGE_SIZE) - buf;
 	int n = 0;
@@ -65,7 +68,7 @@ static ssize_t show_##name(struct sys_de
 			   struct sysdev_attribute *attr, char *buf)	\
 {									\
 	unsigned int cpu = dev->id;					\
-	return show_cpumap(0, &(topology_##name(cpu)), buf);		\
+	return show_cpumap(0, topology_##name(cpu), buf);		\
 }
 
 #define define_siblings_show_list(name)					\
@@ -74,7 +77,7 @@ static ssize_t show_##name##_list(struct
 				  char *buf)				\
 {									\
 	unsigned int cpu = dev->id;					\
-	return show_cpumap(1, &(topology_##name(cpu)), buf);		\
+	return show_cpumap(1, topology_##name(cpu), buf);		\
 }
 
 #else
@@ -82,9 +85,7 @@ static ssize_t show_##name(struct sys_de
 static ssize_t show_##name(struct sys_device *dev,			\
 			   struct sysdev_attribute *attr, char *buf)	\
 {									\
-	unsigned int cpu = dev->id;					\
-	cpumask_t mask = topology_##name(cpu);				\
-	return show_cpumap(0, &mask, buf);				\
+	return show_cpumap(0, topology_##name(dev->id), buf);		\
 }
 
 #define define_siblings_show_list(name)					\
@@ -92,9 +93,7 @@ static ssize_t show_##name##_list(struct
 				  struct sysdev_attribute *attr,	\
 				  char *buf)				\
 {									\
-	unsigned int cpu = dev->id;					\
-	cpumask_t mask = topology_##name(cpu);				\
-	return show_cpumap(1, &mask, buf);				\
+	return show_cpumap(1, topology_##name(dev->id), buf);		\
 }
 #endif
 
@@ -107,13 +106,13 @@ define_id_show_func(core_id);
 define_id_show_func(core_id);
 define_one_ro(core_id);
 
-define_siblings_show_func(thread_siblings);
-define_one_ro(thread_siblings);
-define_one_ro(thread_siblings_list);
+define_siblings_show_func(thread_cpumask);
+define_one_ro_named(thread_siblings, show_thread_cpumask);
+define_one_ro_named(thread_siblings_list, show_thread_cpumask_list);
 
-define_siblings_show_func(core_siblings);
-define_one_ro(core_siblings);
-define_one_ro(core_siblings_list);
+define_siblings_show_func(core_cpumask);
+define_one_ro_named(core_siblings, show_core_cpumask);
+define_one_ro_named(core_siblings_list, show_core_cpumask_list);
 
 static struct attribute *default_attrs[] = {
 	&attr_physical_package_id.attr,
diff --git a/drivers/misc/sgi-xp/xpc_main.c b/drivers/misc/sgi-xp/xpc_main.c
--- a/drivers/misc/sgi-xp/xpc_main.c
+++ b/drivers/misc/sgi-xp/xpc_main.c
@@ -318,7 +318,7 @@ xpc_hb_checker(void *ignore)
 
 	/* this thread was marked active by xpc_hb_init() */
 
-	set_cpus_allowed_ptr(current, &cpumask_of_cpu(XPC_HB_CHECK_CPU));
+	set_cpus_allowed_ptr(current, cpumask_of(XPC_HB_CHECK_CPU));
 
 	/* set our heartbeating to other partitions into motion */
 	xpc_hb_check_timeout = jiffies + (xpc_hb_check_interval * HZ);
diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c
--- a/drivers/net/sfc/efx.c
+++ b/drivers/net/sfc/efx.c
@@ -854,20 +854,27 @@ static void efx_fini_io(struct efx_nic *
  * interrupts across them. */
 static int efx_wanted_rx_queues(void)
 {
-	cpumask_t core_mask;
+	cpumask_var_t core_mask;
 	int count;
 	int cpu;
 
-	cpus_clear(core_mask);
+	if (!alloc_cpumask_var(&core_mask, GFP_KERNEL)) {
+		printk(KERN_WARNING
+		       "efx.c: allocation failure, irq balancing hobbled\n");
+		return 1;
+	}
+
+	cpumask_clear(core_mask);
 	count = 0;
 	for_each_online_cpu(cpu) {
-		if (!cpu_isset(cpu, core_mask)) {
+		if (!cpumask_test_cpu(cpu, core_mask)) {
 			++count;
-			cpus_or(core_mask, core_mask,
-				topology_core_siblings(cpu));
+			cpumask_or(core_mask, core_mask,
+				   topology_core_cpumask(cpu));
 		}
 	}
 
+	free_cpumask_var(core_mask);
 	return count;
 }
 
diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c
--- a/drivers/oprofile/buffer_sync.c
+++ b/drivers/oprofile/buffer_sync.c
@@ -38,7 +38,7 @@
 
 static LIST_HEAD(dying_tasks);
 static LIST_HEAD(dead_tasks);
-static cpumask_t marked_cpus = CPU_MASK_NONE;
+static cpumask_var_t marked_cpus;
 static DEFINE_SPINLOCK(task_mortuary);
 static void process_task_mortuary(void);
 
@@ -456,10 +456,10 @@ static void mark_done(int cpu)
 {
 	int i;
 
-	cpu_set(cpu, marked_cpus);
+	cpumask_set_cpu(cpu, marked_cpus);
 
 	for_each_online_cpu(i) {
-		if (!cpu_isset(i, marked_cpus))
+		if (!cpumask_test_cpu(i, marked_cpus))
 			return;
 	}
 
@@ -468,7 +468,7 @@ static void mark_done(int cpu)
 	 */
 	process_task_mortuary();
 
-	cpus_clear(marked_cpus);
+	cpumask_clear(marked_cpus);
 }
 
 
@@ -565,6 +565,20 @@ void sync_buffer(int cpu)
 	mutex_unlock(&buffer_mutex);
 }
 
+int __init buffer_sync_init(void)
+{
+	if (!alloc_cpumask_var(&marked_cpus, GFP_KERNEL))
+		return -ENOMEM;
+
+	cpumask_clear(marked_cpus);
+		return 0;
+}
+
+void __exit buffer_sync_cleanup(void)
+{
+	free_cpumask_var(marked_cpus);
+}
+
 /* The function can be used to add a buffer worth of data directly to
  * the kernel buffer. The buffer is assumed to be a circular buffer.
  * Take the entries from index start and end at index end, wrapping
diff --git a/drivers/oprofile/buffer_sync.h b/drivers/oprofile/buffer_sync.h
--- a/drivers/oprofile/buffer_sync.h
+++ b/drivers/oprofile/buffer_sync.h
@@ -19,4 +19,8 @@ void sync_stop(void);
 /* sync the given CPU's buffer */
 void sync_buffer(int cpu);
 
+/* initialize/destroy the buffer system. */
+int buffer_sync_init(void);
+void buffer_sync_cleanup(void);
+
 #endif /* OPROFILE_BUFFER_SYNC_H */
diff --git a/drivers/oprofile/oprof.c b/drivers/oprofile/oprof.c
--- a/drivers/oprofile/oprof.c
+++ b/drivers/oprofile/oprof.c
@@ -183,6 +183,10 @@ static int __init oprofile_init(void)
 {
 	int err;
 
+	err = buffer_sync_init();
+	if (err)
+		return err;
+
 	err = oprofile_arch_init(&oprofile_ops);
 
 	if (err < 0 || timer) {
@@ -191,8 +195,10 @@ static int __init oprofile_init(void)
 	}
 
 	err = oprofilefs_register();
-	if (err)
+	if (err) {
 		oprofile_arch_exit();
+		buffer_sync_cleanup();
+	}
 
 	return err;
 }
@@ -202,6 +208,7 @@ static void __exit oprofile_exit(void)
 {
 	oprofilefs_unregister();
 	oprofile_arch_exit();
+	buffer_sync_cleanup();
 }
 
 
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -26,6 +26,7 @@
 #include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/string.h>
+#include <linux/bootmem.h>
 
 #include <asm/ptrace.h>
 #include <asm/irq.h>
@@ -75,7 +76,14 @@ static int evtchn_to_irq[NR_EVENT_CHANNE
 static int evtchn_to_irq[NR_EVENT_CHANNELS] = {
 	[0 ... NR_EVENT_CHANNELS-1] = -1
 };
-static unsigned long cpu_evtchn_mask[NR_CPUS][NR_EVENT_CHANNELS/BITS_PER_LONG];
+struct cpu_evtchn_s {
+	unsigned long bits[NR_EVENT_CHANNELS/BITS_PER_LONG];
+};
+static struct cpu_evtchn_s *cpu_evtchn_mask_p;
+static inline unsigned long *cpu_evtchn_mask(int cpu)
+{
+	return cpu_evtchn_mask_p[cpu].bits;
+}
 static u8 cpu_evtchn[NR_EVENT_CHANNELS];
 
 /* Reference counts for bindings to IRQs. */
@@ -115,7 +123,7 @@ static inline unsigned long active_evtch
 					   unsigned int idx)
 {
 	return (sh->evtchn_pending[idx] &
-		cpu_evtchn_mask[cpu][idx] &
+		cpu_evtchn_mask(cpu)[idx] &
 		~sh->evtchn_mask[idx]);
 }
 
@@ -125,11 +133,11 @@ static void bind_evtchn_to_cpu(unsigned 
 
 	BUG_ON(irq == -1);
 #ifdef CONFIG_SMP
-	irq_to_desc(irq)->affinity = cpumask_of_cpu(cpu);
+	cpumask_copy(irq_to_desc(irq)->affinity, cpumask_of(cpu));
 #endif
 
-	__clear_bit(chn, cpu_evtchn_mask[cpu_evtchn[chn]]);
-	__set_bit(chn, cpu_evtchn_mask[cpu]);
+	__clear_bit(chn, cpu_evtchn_mask(cpu_evtchn[chn]));
+	__set_bit(chn, cpu_evtchn_mask(cpu));
 
 	cpu_evtchn[chn] = cpu;
 }
@@ -142,12 +150,12 @@ static void init_evtchn_cpu_bindings(voi
 
 	/* By default all event channels notify CPU#0. */
 	for_each_irq_desc(i, desc) {
-		desc->affinity = cpumask_of_cpu(0);
+		cpumask_copy(desc->affinity, cpumask_of(0));
 	}
 #endif
 
 	memset(cpu_evtchn, 0, sizeof(cpu_evtchn));
-	memset(cpu_evtchn_mask[0], ~0, sizeof(cpu_evtchn_mask[0]));
+	memset(cpu_evtchn_mask(0), ~0, sizeof(cpu_evtchn_mask(0)));
 }
 
 static inline unsigned int cpu_from_evtchn(unsigned int evtchn)
@@ -822,6 +830,10 @@ void __init xen_init_IRQ(void)
 void __init xen_init_IRQ(void)
 {
 	int i;
+	size_t size = nr_cpu_ids * sizeof(struct cpu_evtchn_s);
+
+	cpu_evtchn_mask_p = alloc_bootmem(size);
+	BUG_ON(cpu_evtchn_mask_p == NULL);
 
 	init_evtchn_cpu_bindings();
 
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -100,7 +100,7 @@ static void do_suspend(void)
 	/* XXX use normal device tree? */
 	xenbus_suspend();
 
-	err = stop_machine(xen_suspend, &cancelled, &cpumask_of_cpu(0));
+	err = stop_machine(xen_suspend, &cancelled, cpumask_of(0));
 	if (err) {
 		printk(KERN_ERR "failed to start xen_suspend: %d\n", err);
 		goto out;
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -467,6 +467,7 @@ struct irq_desc;
 struct irq_desc;
 
 extern int early_irq_init(void);
+extern int arch_probe_nr_irqs(void);
 extern int arch_early_irq_init(void);
 extern int arch_init_chip_data(struct irq_desc *desc, int cpu);
 
diff --git a/include/linux/irq.h b/include/linux/irq.h
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -182,11 +182,11 @@ struct irq_desc {
 	unsigned int		irqs_unhandled;
 	spinlock_t		lock;
 #ifdef CONFIG_SMP
-	cpumask_t		affinity;
+	cpumask_var_t		affinity;
 	unsigned int		cpu;
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	cpumask_var_t		pending_mask;
 #endif
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-	cpumask_t		pending_mask;
 #endif
 #ifdef CONFIG_PROC_FS
 	struct proc_dir_entry	*dir;
@@ -422,4 +422,84 @@ extern int set_irq_msi(unsigned int irq,
 
 #endif /* !CONFIG_S390 */
 
+#ifdef CONFIG_SMP
+/**
+ * init_alloc_desc_masks - allocate cpumasks for irq_desc
+ * @desc:	pointer to irq_desc struct
+ * @cpu:	cpu which will be handling the cpumasks
+ * @boot:	true if need bootmem
+ *
+ * Allocates affinity and pending_mask cpumask if required.
+ * Returns true if successful (or not required).
+ * Side effect: affinity has all bits set, pending_mask has all bits clear.
+ */
+static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
+								bool boot)
+{
+	int node;
+
+	if (boot) {
+		alloc_bootmem_cpumask_var(&desc->affinity);
+		cpumask_setall(desc->affinity);
+
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+		alloc_bootmem_cpumask_var(&desc->pending_mask);
+		cpumask_clear(desc->pending_mask);
+#endif
+		return true;
+	}
+
+	node = cpu_to_node(cpu);
+
+	if (!alloc_cpumask_var_node(&desc->affinity, GFP_ATOMIC, node))
+		return false;
+	cpumask_setall(desc->affinity);
+
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	if (!alloc_cpumask_var_node(&desc->pending_mask, GFP_ATOMIC, node)) {
+		free_cpumask_var(desc->affinity);
+		return false;
+	}
+	cpumask_clear(desc->pending_mask);
+#endif
+	return true;
+}
+
+/**
+ * init_copy_desc_masks - copy cpumasks for irq_desc
+ * @old_desc:	pointer to old irq_desc struct
+ * @new_desc:	pointer to new irq_desc struct
+ *
+ * Insures affinity and pending_masks are copied to new irq_desc.
+ * If !CONFIG_CPUMASKS_OFFSTACK the cpumasks are embedded in the
+ * irq_desc struct so the copy is redundant.
+ */
+
+static inline void init_copy_desc_masks(struct irq_desc *old_desc,
+					struct irq_desc *new_desc)
+{
+#ifdef CONFIG_CPUMASKS_OFFSTACK
+	cpumask_copy(new_desc->affinity, old_desc->affinity);
+
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	cpumask_copy(new_desc->pending_mask, old_desc->pending_mask);
+#endif
+#endif
+}
+
+#else /* !CONFIG_SMP */
+
+static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
+								bool boot)
+{
+	return true;
+}
+
+static inline void init_copy_desc_masks(struct irq_desc *old_desc,
+					struct irq_desc *new_desc)
+{
+}
+
+#endif	/* CONFIG_SMP */
+
 #endif /* _LINUX_IRQ_H */
diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h
--- a/include/linux/irqnr.h
+++ b/include/linux/irqnr.h
@@ -20,6 +20,7 @@
 
 # define for_each_irq_desc_reverse(irq, desc)                          \
 	for (irq = nr_irqs - 1; irq >= 0; irq--)
+
 #else /* CONFIG_GENERIC_HARDIRQS */
 
 extern int nr_irqs;
diff --git a/include/linux/topology.h b/include/linux/topology.h
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -193,5 +193,11 @@ int arch_update_cpu_topology(void);
 #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
+#ifndef topology_core_cpumask
+#define topology_core_cpumask(cpu)		cpumask_of(cpu)
+#endif
 
 #endif /* _LINUX_TOPOLOGY_H */
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -46,7 +46,10 @@ void dynamic_irq_init(unsigned int irq)
 	desc->irq_count = 0;
 	desc->irqs_unhandled = 0;
 #ifdef CONFIG_SMP
-	cpumask_setall(&desc->affinity);
+	cpumask_setall(desc->affinity);
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	cpumask_clear(desc->pending_mask);
+#endif
 #endif
 	spin_unlock_irqrestore(&desc->lock, flags);
 }
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -17,6 +17,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/rculist.h>
 #include <linux/hash.h>
+#include <linux/bootmem.h>
 
 #include "internals.h"
 
@@ -69,6 +70,7 @@ EXPORT_SYMBOL_GPL(nr_irqs);
 EXPORT_SYMBOL_GPL(nr_irqs);
 
 #ifdef CONFIG_SPARSE_IRQ
+
 static struct irq_desc irq_desc_init = {
 	.irq	    = -1,
 	.status	    = IRQ_DISABLED,
@@ -76,9 +78,6 @@ static struct irq_desc irq_desc_init = {
 	.handle_irq = handle_bad_irq,
 	.depth      = 1,
 	.lock       = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
-#ifdef CONFIG_SMP
-	.affinity   = CPU_MASK_ALL
-#endif
 };
 
 void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr)
@@ -113,6 +112,10 @@ static void init_one_irq_desc(int irq, s
 		printk(KERN_ERR "can not alloc kstat_irqs\n");
 		BUG_ON(1);
 	}
+	if (!init_alloc_desc_masks(desc, cpu, false)) {
+		printk(KERN_ERR "can not alloc irq_desc cpumasks\n");
+		BUG_ON(1);
+	}
 	arch_init_chip_data(desc, cpu);
 }
 
@@ -121,7 +124,7 @@ static void init_one_irq_desc(int irq, s
  */
 DEFINE_SPINLOCK(sparse_irq_lock);
 
-struct irq_desc *irq_desc_ptrs[NR_IRQS] __read_mostly;
+struct irq_desc **irq_desc_ptrs __read_mostly;
 
 static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = {
 	[0 ... NR_IRQS_LEGACY-1] = {
@@ -131,14 +134,10 @@ static struct irq_desc irq_desc_legacy[N
 		.handle_irq = handle_bad_irq,
 		.depth	    = 1,
 		.lock	    = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
-#ifdef CONFIG_SMP
-		.affinity   = CPU_MASK_ALL
-#endif
 	}
 };
 
-/* FIXME: use bootmem alloc ...*/
-static unsigned int kstat_irqs_legacy[NR_IRQS_LEGACY][NR_CPUS];
+static unsigned int *kstat_irqs_legacy;
 
 int __init early_irq_init(void)
 {
@@ -148,18 +147,30 @@ int __init early_irq_init(void)
 
 	init_irq_default_affinity();
 
+	 /* initialize nr_irqs based on nr_cpu_ids */
+	arch_probe_nr_irqs();
+	printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d\n", NR_IRQS, nr_irqs);
+
 	desc = irq_desc_legacy;
 	legacy_count = ARRAY_SIZE(irq_desc_legacy);
 
+	/* allocate irq_desc_ptrs array based on nr_irqs */
+	irq_desc_ptrs = alloc_bootmem(nr_irqs * sizeof(void *));
+
+	/* allocate based on nr_cpu_ids */
+	/* FIXME: invert kstat_irgs, and it'd be a per_cpu_alloc'd thing */
+	kstat_irqs_legacy = alloc_bootmem(NR_IRQS_LEGACY * nr_cpu_ids *
+					  sizeof(int));
+
 	for (i = 0; i < legacy_count; i++) {
 		desc[i].irq = i;
-		desc[i].kstat_irqs = kstat_irqs_legacy[i];
+		desc[i].kstat_irqs = kstat_irqs_legacy + i * nr_cpu_ids;
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
-
+		init_alloc_desc_masks(&desc[i], 0, true);
 		irq_desc_ptrs[i] = desc + i;
 	}
 
-	for (i = legacy_count; i < NR_IRQS; i++)
+	for (i = legacy_count; i < nr_irqs; i++)
 		irq_desc_ptrs[i] = NULL;
 
 	return arch_early_irq_init();
@@ -167,7 +178,10 @@ int __init early_irq_init(void)
 
 struct irq_desc *irq_to_desc(unsigned int irq)
 {
-	return (irq < NR_IRQS) ? irq_desc_ptrs[irq] : NULL;
+	if (irq_desc_ptrs && irq < nr_irqs)
+		return irq_desc_ptrs[irq];
+
+	return NULL;
 }
 
 struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
@@ -176,10 +190,9 @@ struct irq_desc *irq_to_desc_alloc_cpu(u
 	unsigned long flags;
 	int node;
 
-	if (irq >= NR_IRQS) {
-		printk(KERN_WARNING "irq >= NR_IRQS in irq_to_desc_alloc: %d %d\n",
-				irq, NR_IRQS);
-		WARN_ON(1);
+	if (irq >= nr_irqs) {
+		WARN(1, "irq (%d) >= nr_irqs (%d) in irq_to_desc_alloc\n",
+			irq, nr_irqs);
 		return NULL;
 	}
 
@@ -221,9 +234,6 @@ struct irq_desc irq_desc[NR_IRQS] __cach
 		.handle_irq = handle_bad_irq,
 		.depth = 1,
 		.lock = __SPIN_LOCK_UNLOCKED(irq_desc->lock),
-#ifdef CONFIG_SMP
-		.affinity = CPU_MASK_ALL
-#endif
 	}
 };
 
@@ -235,12 +245,15 @@ int __init early_irq_init(void)
 
 	init_irq_default_affinity();
 
+	printk(KERN_INFO "NR_IRQS:%d\n", NR_IRQS);
+
 	desc = irq_desc;
 	count = ARRAY_SIZE(irq_desc);
 
-	for (i = 0; i < count; i++)
+	for (i = 0; i < count; i++) {
 		desc[i].irq = i;
-
+		init_alloc_desc_masks(&desc[i], 0, true);
+	}
 	return arch_early_irq_init();
 }
 
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -16,7 +16,14 @@ extern struct lock_class_key irq_desc_lo
 extern struct lock_class_key irq_desc_lock_class;
 extern void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr);
 extern spinlock_t sparse_irq_lock;
+
+#ifdef CONFIG_SPARSE_IRQ
+/* irq_desc_ptrs allocated at boot time */
+extern struct irq_desc **irq_desc_ptrs;
+#else
+/* irq_desc_ptrs is a fixed size array */
 extern struct irq_desc *irq_desc_ptrs[NR_IRQS];
+#endif
 
 #ifdef CONFIG_PROC_FS
 extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -90,14 +90,14 @@ int irq_set_affinity(unsigned int irq, c
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	if (desc->status & IRQ_MOVE_PCNTXT || desc->status & IRQ_DISABLED) {
-		cpumask_copy(&desc->affinity, cpumask);
+		cpumask_copy(desc->affinity, cpumask);
 		desc->chip->set_affinity(irq, cpumask);
 	} else {
 		desc->status |= IRQ_MOVE_PENDING;
-		cpumask_copy(&desc->pending_mask, cpumask);
+		cpumask_copy(desc->pending_mask, cpumask);
 	}
 #else
-	cpumask_copy(&desc->affinity, cpumask);
+	cpumask_copy(desc->affinity, cpumask);
 	desc->chip->set_affinity(irq, cpumask);
 #endif
 	desc->status |= IRQ_AFFINITY_SET;
@@ -119,16 +119,16 @@ int do_irq_select_affinity(unsigned int 
 	 * one of the targets is online.
 	 */
 	if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) {
-		if (cpumask_any_and(&desc->affinity, cpu_online_mask)
+		if (cpumask_any_and(desc->affinity, cpu_online_mask)
 		    < nr_cpu_ids)
 			goto set_affinity;
 		else
 			desc->status &= ~IRQ_AFFINITY_SET;
 	}
 
-	cpumask_and(&desc->affinity, cpu_online_mask, irq_default_affinity);
+	cpumask_and(desc->affinity, cpu_online_mask, irq_default_affinity);
 set_affinity:
-	desc->chip->set_affinity(irq, &desc->affinity);
+	desc->chip->set_affinity(irq, desc->affinity);
 
 	return 0;
 }
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -18,7 +18,7 @@ void move_masked_irq(int irq)
 
 	desc->status &= ~IRQ_MOVE_PENDING;
 
-	if (unlikely(cpumask_empty(&desc->pending_mask)))
+	if (unlikely(cpumask_empty(desc->pending_mask)))
 		return;
 
 	if (!desc->chip->set_affinity)
@@ -38,13 +38,13 @@ void move_masked_irq(int irq)
 	 * For correct operation this depends on the caller
 	 * masking the irqs.
 	 */
-	if (likely(cpumask_any_and(&desc->pending_mask, cpu_online_mask)
+	if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask)
 		   < nr_cpu_ids)) {
-		cpumask_and(&desc->affinity,
-			    &desc->pending_mask, cpu_online_mask);
-		desc->chip->set_affinity(irq, &desc->affinity);
+		cpumask_and(desc->affinity,
+			    desc->pending_mask, cpu_online_mask);
+		desc->chip->set_affinity(irq, desc->affinity);
 	}
-	cpumask_clear(&desc->pending_mask);
+	cpumask_clear(desc->pending_mask);
 }
 
 void move_native_irq(int irq)
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -38,15 +38,22 @@ static void free_kstat_irqs(struct irq_d
 	old_desc->kstat_irqs = NULL;
 }
 
-static void init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
+static bool init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
 		 struct irq_desc *desc, int cpu)
 {
 	memcpy(desc, old_desc, sizeof(struct irq_desc));
+	if (!init_alloc_desc_masks(desc, cpu, false)) {
+		printk(KERN_ERR "irq %d: can not get new irq_desc cpumask "
+				"for migration.\n", irq);
+		return false;
+	}
 	spin_lock_init(&desc->lock);
 	desc->cpu = cpu;
 	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
 	init_copy_kstat_irqs(old_desc, desc, cpu, nr_cpu_ids);
+	init_copy_desc_masks(old_desc, desc);
 	arch_init_copy_chip_data(old_desc, desc, cpu);
+	return true;
 }
 
 static void free_one_irq_desc(struct irq_desc *old_desc, struct irq_desc *desc)
@@ -76,12 +83,18 @@ static struct irq_desc *__real_move_irq_
 	node = cpu_to_node(cpu);
 	desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
 	if (!desc) {
-		printk(KERN_ERR "irq %d: can not get new irq_desc for migration.\n", irq);
+		printk(KERN_ERR "irq %d: can not get new irq_desc "
+				"for migration.\n", irq);
 		/* still use old one */
 		desc = old_desc;
 		goto out_unlock;
 	}
-	init_copy_one_irq_desc(irq, old_desc, desc, cpu);
+	if (!init_copy_one_irq_desc(irq, old_desc, desc, cpu)) {
+		/* still use old one */
+		kfree(desc);
+		desc = old_desc;
+		goto out_unlock;
+	}
 
 	irq_desc_ptrs[irq] = desc;
 	spin_unlock_irqrestore(&sparse_irq_lock, flags);
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -20,11 +20,11 @@ static int irq_affinity_proc_show(struct
 static int irq_affinity_proc_show(struct seq_file *m, void *v)
 {
 	struct irq_desc *desc = irq_to_desc((long)m->private);
-	const struct cpumask *mask = &desc->affinity;
+	const struct cpumask *mask = desc->affinity;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	if (desc->status & IRQ_MOVE_PENDING)
-		mask = &desc->pending_mask;
+		mask = desc->pending_mask;
 #endif
 	seq_cpumask(m, mask);
 	seq_putc(m, '\n');
diff --git a/kernel/softirq.c b/kernel/softirq.c
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -795,6 +795,11 @@ int __init __weak early_irq_init(void)
 	return 0;
 }
 
+int __init __weak arch_probe_nr_irqs(void)
+{
+	return 0;
+}
+
 int __init __weak arch_early_irq_init(void)
 {
 	return 0;