Merge branch 'x86/mm' into core/percpu

Conflicts:
	arch/x86/mm/fault.c
diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index 45932ec..b41f3e5 100644
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -18,11 +18,11 @@
 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
index 703731a..7bc7489 100644
--- a/arch/alpha/kernel/irq.c
+++ b/arch/alpha/kernel/irq.c
@@ -55,7 +55,7 @@
 		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
index 7141cee..4bb723e 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -104,6 +104,11 @@
 	.lock = SPIN_LOCK_UNLOCKED
 };
 
+#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 @@
 		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 @@
 		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/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 0021607..85598f7 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -65,6 +65,7 @@
 #endif
 		. = ALIGN(4096);
 		__per_cpu_start = .;
+			*(.data.percpu.page_aligned)
 			*(.data.percpu)
 			*(.data.percpu.shared_aligned)
 		__per_cpu_end = .;
diff --git a/arch/arm/oprofile/op_model_mpcore.c b/arch/arm/oprofile/op_model_mpcore.c
index 6d6bd58..853d42b 100644
--- a/arch/arm/oprofile/op_model_mpcore.c
+++ b/arch/arm/oprofile/op_model_mpcore.c
@@ -263,7 +263,7 @@
 	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
index ab8209c..5780d6d 100644
--- a/arch/blackfin/kernel/irqchip.c
+++ b/arch/blackfin/kernel/irqchip.c
@@ -69,6 +69,11 @@
 #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)
 {
 	int i = *(loff_t *) v, j;
diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
index 32f3af1..3193f44 100644
--- a/arch/ia64/include/asm/topology.h
+++ b/arch/ia64/include/asm/topology.h
@@ -84,7 +84,7 @@
 	.child			= NULL,			\
 	.groups			= NULL,			\
 	.min_interval		= 8,			\
-	.max_interval		= 8*(min(num_online_cpus(), 32)), \
+	.max_interval		= 8*(min(num_online_cpus(), 32U)), \
 	.busy_factor		= 64,			\
 	.imbalance_pct		= 125,			\
 	.cache_nice_tries	= 2,			\
diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c
index 5cfd3d9..006ad36 100644
--- a/arch/ia64/kernel/iosapic.c
+++ b/arch/ia64/kernel/iosapic.c
@@ -880,7 +880,7 @@
 	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
index a58f64c..226233a 100644
--- a/arch/ia64/kernel/irq.c
+++ b/arch/ia64/kernel/irq.c
@@ -103,7 +103,7 @@
 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 @@
 		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
index 28d3d48..927ad02 100644
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -493,11 +493,13 @@
 	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 @@
 	  * 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
index 8903393..dcb6b7c 100644
--- a/arch/ia64/kernel/msi_ia64.c
+++ b/arch/ia64/kernel/msi_ia64.c
@@ -75,7 +75,7 @@
 	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 @@
 	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/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index 10a7d47e..f45e4e5 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -219,6 +219,7 @@
   .data.percpu PERCPU_ADDR : AT(__phys_per_cpu_start - LOAD_OFFSET)
 	{
 		__per_cpu_start = .;
+		*(.data.percpu.page_aligned)
 		*(.data.percpu)
 		*(.data.percpu.shared_aligned)
 		__per_cpu_end = .;
diff --git a/arch/ia64/sn/kernel/msi_sn.c b/arch/ia64/sn/kernel/msi_sn.c
index ca553b0..81e4289 100644
--- a/arch/ia64/sn/kernel/msi_sn.c
+++ b/arch/ia64/sn/kernel/msi_sn.c
@@ -205,7 +205,7 @@
 	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/include/asm/irq.h b/arch/mips/include/asm/irq.h
index abc62aa..3214ade 100644
--- a/arch/mips/include/asm/irq.h
+++ b/arch/mips/include/asm/irq.h
@@ -66,7 +66,7 @@
  */
 #define IRQ_AFFINITY_HOOK(irq)						\
 do {									\
-    if (!cpu_isset(smp_processor_id(), irq_desc[irq].affinity)) {	\
+    if (!cpumask_test_cpu(smp_processor_id(), irq_desc[irq].affinity)) {\
 	smtc_forward_irq(irq);						\
 	irq_exit();							\
 	return;								\
diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c
index 494a49a..87deb8f 100644
--- a/arch/mips/kernel/irq-gic.c
+++ b/arch/mips/kernel/irq-gic.c
@@ -187,7 +187,7 @@
 		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
index b6cca01..5f5af7d 100644
--- a/arch/mips/kernel/smtc.c
+++ b/arch/mips/kernel/smtc.c
@@ -686,7 +686,7 @@
 	 * 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 @@
 	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
index aabd727..5ba3188 100644
--- a/arch/mips/mti-malta/malta-smtc.c
+++ b/arch/mips/mti-malta/malta-smtc.c
@@ -116,7 +116,7 @@
 
 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 @@
 	 * 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
index f8b18af..0ecd5fe 100644
--- a/arch/mips/sgi-ip22/ip22-int.c
+++ b/arch/mips/sgi-ip22/ip22-int.c
@@ -155,7 +155,7 @@
 	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
index 3dcb27e..c8f7d23 100644
--- a/arch/mips/sgi-ip22/ip22-time.c
+++ b/arch/mips/sgi-ip22/ip22-time.c
@@ -122,7 +122,7 @@
 	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
index dddfda8..3146916 100644
--- a/arch/mips/sibyte/bcm1480/smp.c
+++ b/arch/mips/sibyte/bcm1480/smp.c
@@ -178,9 +178,10 @@
 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
index 5950a288..cad1400 100644
--- a/arch/mips/sibyte/sb1250/smp.c
+++ b/arch/mips/sibyte/sb1250/smp.c
@@ -166,9 +166,10 @@
 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
index 10811e9..2e370d8 100644
--- a/arch/mn10300/kernel/mn10300-watchdog.c
+++ b/arch/mn10300/kernel/mn10300-watchdog.c
@@ -130,6 +130,7 @@
 	 * 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 @@
 	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
index ac2c822..4948280 100644
--- a/arch/parisc/kernel/irq.c
+++ b/arch/parisc/kernel/irq.c
@@ -120,7 +120,7 @@
 	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 @@
 	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 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 @@
 	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
index 23b8b5e..ad1e5ac 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -231,7 +231,7 @@
 		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/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 161b9b9..295ccc5 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -184,6 +184,7 @@
 	. = ALIGN(PAGE_SIZE);
 	.data.percpu  : AT(ADDR(.data.percpu) - LOAD_OFFSET) {
 		__per_cpu_start = .;
+		*(.data.percpu.page_aligned)
 		*(.data.percpu)
 		*(.data.percpu.shared_aligned)
 		__per_cpu_end = .;
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index 84e058f..80b5134 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -153,9 +153,10 @@
 {
 	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 @@
 		       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
index a35297d..532e205 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -566,9 +566,10 @@
 #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
index cab8e028..4ac5c65 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -247,9 +247,10 @@
 #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);
@@ -854,7 +855,7 @@
 		    !(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
index 2db3c22..db310aa 100644
--- a/arch/sparc/kernel/time_64.c
+++ b/arch/sparc/kernel/time_64.c
@@ -729,7 +729,7 @@
 
 	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/Kconfig b/arch/x86/Kconfig
index 73f7fe8..ef27aed 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1340,13 +1340,17 @@
 
 	  If unsure, say Y. Only embedded should say N here.
 
+config CC_STACKPROTECTOR_ALL
+	bool
+
 config CC_STACKPROTECTOR
 	bool "Enable -fstack-protector buffer overflow detection (EXPERIMENTAL)"
-	depends on X86_64 && EXPERIMENTAL && BROKEN
+	depends on X86_64
+	select CC_STACKPROTECTOR_ALL
 	help
-         This option turns on the -fstack-protector GCC feature. This
-	  feature puts, at the beginning of critical functions, a canary
-	  value on the stack just before the return address, and validates
+          This option turns on the -fstack-protector GCC feature. This
+	  feature puts, at the beginning of functions, a canary value on
+	  the stack just before the return address, and validates
 	  the value just before actually returning.  Stack based buffer
 	  overflows (that need to overwrite this return address) now also
 	  overwrite the canary, which gets detected and the attack is then
@@ -1354,15 +1358,8 @@
 
 	  This feature requires gcc version 4.2 or above, or a distribution
 	  gcc with the feature backported. Older versions are automatically
-	  detected and for those versions, this configuration option is ignored.
-
-config CC_STACKPROTECTOR_ALL
-	bool "Use stack-protector for all functions"
-	depends on CC_STACKPROTECTOR
-	help
-	  Normally, GCC only inserts the canary value protection for
-	  functions that use large-ish on-stack buffers. By enabling
-	  this option, GCC will be asked to do this for ALL functions.
+	  detected and for those versions, this configuration option is
+	  ignored. (and a warning is printed during bootup)
 
 source kernel/Kconfig.hz
 
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 10d6cc3..28f1114 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -117,6 +117,7 @@
 config DEBUG_RODATA_TEST
 	bool "Testcase for the DEBUG_RODATA feature"
 	depends on DEBUG_RODATA
+	default y
 	help
 	  This option enables a testcase for the DEBUG_RODATA
 	  feature as well as for the change_page_attr() infrastructure.
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index d1a47ad..cacee98 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -73,7 +73,7 @@
 
         stackp := $(CONFIG_SHELL) $(srctree)/scripts/gcc-x86_64-has-stack-protector.sh
         stackp-$(CONFIG_CC_STACKPROTECTOR) := $(shell $(stackp) \
-                "$(CC)" -fstack-protector )
+                "$(CC)" "-fstack-protector -DGCC_HAS_SP" )
         stackp-$(CONFIG_CC_STACKPROTECTOR_ALL) += $(shell $(stackp) \
                 "$(CC)" -fstack-protector-all )
 
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 256b00b..9c79b24 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -112,8 +112,8 @@
 	CFI_DEF_CFA	rsp,0
 	CFI_REGISTER	rsp,rbp
 	SWAPGS_UNSAFE_STACK
-	movq	%gs:pda_kernelstack, %rsp
-	addq	$(PDA_STACKOFFSET),%rsp	
+	movq	PER_CPU_VAR(kernel_stack), %rsp
+	addq	$(KERNEL_STACK_OFFSET),%rsp
 	/*
 	 * No need to follow this irqs on/off section: the syscall
 	 * disabled irqs, here we enable it straight after entry:
@@ -273,13 +273,13 @@
 ENTRY(ia32_cstar_target)
 	CFI_STARTPROC32	simple
 	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA	rsp,PDA_STACKOFFSET
+	CFI_DEF_CFA	rsp,KERNEL_STACK_OFFSET
 	CFI_REGISTER	rip,rcx
 	/*CFI_REGISTER	rflags,r11*/
 	SWAPGS_UNSAFE_STACK
 	movl	%esp,%r8d
 	CFI_REGISTER	rsp,r8
-	movq	%gs:pda_kernelstack,%rsp
+	movq	PER_CPU_VAR(kernel_stack),%rsp
 	/*
 	 * No need to follow this irqs on/off section: the syscall
 	 * disabled irqs and here we enable it straight after entry:
diff --git a/arch/x86/include/asm/apicnum.h b/arch/x86/include/asm/apicnum.h
new file mode 100644
index 0000000..82f613c
--- /dev/null
+++ b/arch/x86/include/asm/apicnum.h
@@ -0,0 +1,12 @@
+#ifndef _ASM_X86_APICNUM_H
+#define _ASM_X86_APICNUM_H
+
+/* define MAX_IO_APICS */
+#ifdef CONFIG_X86_32
+# define MAX_IO_APICS 64
+#else
+# define MAX_IO_APICS 128
+# define MAX_LOCAL_APIC 32768
+#endif
+
+#endif /* _ASM_X86_APICNUM_H */
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index e02a359..02b47a6 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -3,6 +3,9 @@
 
 /*
  * Copyright 1992, Linus Torvalds.
+ *
+ * Note: inlines with more than a single statement should be marked
+ * __always_inline to avoid problems with older gcc's inlining heuristics.
  */
 
 #ifndef _LINUX_BITOPS_H
@@ -53,7 +56,8 @@
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void set_bit(unsigned int nr, volatile unsigned long *addr)
+static __always_inline void
+set_bit(unsigned int nr, volatile unsigned long *addr)
 {
 	if (IS_IMMEDIATE(nr)) {
 		asm volatile(LOCK_PREFIX "orb %1,%0"
@@ -90,7 +94,8 @@
  * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
  * in order to ensure changes are visible on other processors.
  */
-static inline void clear_bit(int nr, volatile unsigned long *addr)
+static __always_inline void
+clear_bit(int nr, volatile unsigned long *addr)
 {
 	if (IS_IMMEDIATE(nr)) {
 		asm volatile(LOCK_PREFIX "andb %1,%0"
@@ -204,7 +209,8 @@
  *
  * This is the same as test_and_set_bit on x86.
  */
-static inline int test_and_set_bit_lock(int nr, volatile unsigned long *addr)
+static __always_inline int
+test_and_set_bit_lock(int nr, volatile unsigned long *addr)
 {
 	return test_and_set_bit(nr, addr);
 }
@@ -300,7 +306,7 @@
 	return oldbit;
 }
 
-static inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr)
+static __always_inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr)
 {
 	return ((1UL << (nr % BITS_PER_LONG)) &
 		(((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index bae482d..f03b23e 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -7,6 +7,20 @@
 #include <linux/nodemask.h>
 #include <linux/percpu.h>
 
+#ifdef CONFIG_SMP
+
+extern void prefill_possible_map(void);
+
+#else /* CONFIG_SMP */
+
+static inline void prefill_possible_map(void) {}
+
+#define cpu_physical_id(cpu)			boot_cpu_physical_apicid
+#define safe_smp_processor_id()			0
+#define stack_smp_processor_id()		0
+
+#endif /* CONFIG_SMP */
+
 struct x86_cpu {
 	struct cpu cpu;
 };
@@ -17,4 +31,11 @@
 #endif
 
 DECLARE_PER_CPU(int, cpu_state);
+
+#ifdef CONFIG_X86_HAS_BOOT_CPU_ID
+extern unsigned char boot_cpu_id;
+#else
+#define boot_cpu_id				0
+#endif
+
 #endif /* _ASM_X86_CPU_H */
diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h
new file mode 100644
index 0000000..26c6dad
--- /dev/null
+++ b/arch/x86/include/asm/cpumask.h
@@ -0,0 +1,28 @@
+#ifndef _ASM_X86_CPUMASK_H
+#define _ASM_X86_CPUMASK_H
+#ifndef __ASSEMBLY__
+#include <linux/cpumask.h>
+
+#ifdef CONFIG_X86_64
+
+extern cpumask_var_t cpu_callin_mask;
+extern cpumask_var_t cpu_callout_mask;
+extern cpumask_var_t cpu_initialized_mask;
+extern cpumask_var_t cpu_sibling_setup_mask;
+
+#else /* CONFIG_X86_32 */
+
+extern cpumask_t cpu_callin_map;
+extern cpumask_t cpu_callout_map;
+extern cpumask_t cpu_initialized;
+extern cpumask_t cpu_sibling_setup_map;
+
+#define cpu_callin_mask		((struct cpumask *)&cpu_callin_map)
+#define cpu_callout_mask	((struct cpumask *)&cpu_callout_map)
+#define cpu_initialized_mask	((struct cpumask *)&cpu_initialized)
+#define cpu_sibling_setup_mask	((struct cpumask *)&cpu_sibling_setup_map)
+
+#endif /* CONFIG_X86_32 */
+
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_X86_CPUMASK_H */
diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index 0930b4f..c68c361 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -1,39 +1,21 @@
 #ifndef _ASM_X86_CURRENT_H
 #define _ASM_X86_CURRENT_H
 
-#ifdef CONFIG_X86_32
 #include <linux/compiler.h>
 #include <asm/percpu.h>
 
+#ifndef __ASSEMBLY__
 struct task_struct;
 
 DECLARE_PER_CPU(struct task_struct *, current_task);
-static __always_inline struct task_struct *get_current(void)
-{
-	return x86_read_percpu(current_task);
-}
-
-#else /* X86_32 */
-
-#ifndef __ASSEMBLY__
-#include <asm/pda.h>
-
-struct task_struct;
 
 static __always_inline struct task_struct *get_current(void)
 {
-	return read_pda(pcurrent);
+	return percpu_read(current_task);
 }
 
-#else /* __ASSEMBLY__ */
-
-#include <asm/asm-offsets.h>
-#define GET_CURRENT(reg) movq %gs:(pda_pcurrent),reg
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* X86_32 */
-
 #define current get_current()
 
+#endif /* __ASSEMBLY__ */
+
 #endif /* _ASM_X86_CURRENT_H */
diff --git a/arch/x86/include/asm/genapic_32.h b/arch/x86/include/asm/genapic_32.h
index 2c05b73..4334502 100644
--- a/arch/x86/include/asm/genapic_32.h
+++ b/arch/x86/include/asm/genapic_32.h
@@ -138,11 +138,4 @@
 extern struct genapic *genapic;
 extern void es7000_update_genapic_to_cluster(void);
 
-enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
-#define get_uv_system_type()		UV_NONE
-#define is_uv_system()			0
-#define uv_wakeup_secondary(a, b)	1
-#define uv_system_init()		do {} while (0)
-
-
 #endif /* _ASM_X86_GENAPIC_32_H */
diff --git a/arch/x86/include/asm/genapic_64.h b/arch/x86/include/asm/genapic_64.h
index adf32fb..7bb092c 100644
--- a/arch/x86/include/asm/genapic_64.h
+++ b/arch/x86/include/asm/genapic_64.h
@@ -51,15 +51,9 @@
 extern int acpi_madt_oem_check(char *, char *);
 
 extern void apic_send_IPI_self(int vector);
-enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
-extern enum uv_system_type get_uv_system_type(void);
-extern int is_uv_system(void);
 
 extern struct genapic apic_x2apic_uv_x;
 DECLARE_PER_CPU(int, x2apic_extra_bits);
-extern void uv_cpu_init(void);
-extern void uv_system_init(void);
-extern int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip);
 
 extern void setup_apic_routing(void);
 
diff --git a/arch/x86/include/asm/hardirq_32.h b/arch/x86/include/asm/hardirq_32.h
index cf7954d..d4b5d73 100644
--- a/arch/x86/include/asm/hardirq_32.h
+++ b/arch/x86/include/asm/hardirq_32.h
@@ -19,6 +19,9 @@
 
 DECLARE_PER_CPU(irq_cpustat_t, irq_stat);
 
+/* We can have at most NR_VECTORS irqs routed to a cpu at a time */
+#define MAX_HARDIRQS_PER_CPU NR_VECTORS
+
 #define __ARCH_IRQ_STAT
 #define __IRQ_STAT(cpu, member) (per_cpu(irq_stat, cpu).member)
 
diff --git a/arch/x86/include/asm/hardirq_64.h b/arch/x86/include/asm/hardirq_64.h
index b5a6b5d..a65bab2 100644
--- a/arch/x86/include/asm/hardirq_64.h
+++ b/arch/x86/include/asm/hardirq_64.h
@@ -3,22 +3,36 @@
 
 #include <linux/threads.h>
 #include <linux/irq.h>
-#include <asm/pda.h>
 #include <asm/apic.h>
 
+typedef struct {
+	unsigned int __softirq_pending;
+	unsigned int __nmi_count;	/* arch dependent */
+	unsigned int apic_timer_irqs;	/* arch dependent */
+	unsigned int irq0_irqs;
+	unsigned int irq_resched_count;
+	unsigned int irq_call_count;
+	unsigned int irq_tlb_count;
+	unsigned int irq_thermal_count;
+	unsigned int irq_spurious_count;
+	unsigned int irq_threshold_count;
+} ____cacheline_aligned irq_cpustat_t;
+
+DECLARE_PER_CPU(irq_cpustat_t, irq_stat);
+
 /* We can have at most NR_VECTORS irqs routed to a cpu at a time */
 #define MAX_HARDIRQS_PER_CPU NR_VECTORS
 
 #define __ARCH_IRQ_STAT 1
 
-#define inc_irq_stat(member)	add_pda(member, 1)
+#define inc_irq_stat(member)	percpu_add(irq_stat.member, 1)
 
-#define local_softirq_pending() read_pda(__softirq_pending)
+#define local_softirq_pending() percpu_read(irq_stat.__softirq_pending)
 
 #define __ARCH_SET_SOFTIRQ_PENDING 1
 
-#define set_softirq_pending(x) write_pda(__softirq_pending, (x))
-#define or_softirq_pending(x)  or_pda(__softirq_pending, (x))
+#define set_softirq_pending(x) percpu_write(irq_stat.__softirq_pending, (x))
+#define or_softirq_pending(x)  percpu_or(irq_stat.__softirq_pending, (x))
 
 extern void ack_bad_irq(unsigned int irq);
 
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 7a1f44a..08ec793 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -114,38 +114,16 @@
 extern int nr_ioapics;
 extern int nr_ioapic_registers[MAX_IO_APICS];
 
-/*
- * MP-BIOS irq configuration table structures:
- */
-
 #define MP_MAX_IOAPIC_PIN 127
 
-struct mp_config_ioapic {
-	unsigned long mp_apicaddr;
-	unsigned int mp_apicid;
-	unsigned char mp_type;
-	unsigned char mp_apicver;
-	unsigned char mp_flags;
-};
-
-struct mp_config_intsrc {
-	unsigned int mp_dstapic;
-	unsigned char mp_type;
-	unsigned char mp_irqtype;
-	unsigned short mp_irqflag;
-	unsigned char mp_srcbus;
-	unsigned char mp_srcbusirq;
-	unsigned char mp_dstirq;
-};
-
 /* I/O APIC entries */
-extern struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
+extern struct mpc_ioapic mp_ioapics[MAX_IO_APICS];
 
 /* # of MP IRQ source entries */
 extern int mp_irq_entries;
 
 /* MP IRQ source entries */
-extern struct mp_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
+extern struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES];
 
 /* non-0 if default (table-less) MP configuration */
 extern int mpc_default_type;
diff --git a/arch/x86/include/asm/irq_regs.h b/arch/x86/include/asm/irq_regs.h
index 89c898a..7784322 100644
--- a/arch/x86/include/asm/irq_regs.h
+++ b/arch/x86/include/asm/irq_regs.h
@@ -1,5 +1,31 @@
-#ifdef CONFIG_X86_32
-# include "irq_regs_32.h"
-#else
-# include "irq_regs_64.h"
-#endif
+/*
+ * Per-cpu current frame pointer - the location of the last exception frame on
+ * the stack, stored in the per-cpu area.
+ *
+ * Jeremy Fitzhardinge <jeremy@goop.org>
+ */
+#ifndef _ASM_X86_IRQ_REGS_H
+#define _ASM_X86_IRQ_REGS_H
+
+#include <asm/percpu.h>
+
+#define ARCH_HAS_OWN_IRQ_REGS
+
+DECLARE_PER_CPU(struct pt_regs *, irq_regs);
+
+static inline struct pt_regs *get_irq_regs(void)
+{
+	return percpu_read(irq_regs);
+}
+
+static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
+{
+	struct pt_regs *old_regs;
+
+	old_regs = get_irq_regs();
+	percpu_write(irq_regs, new_regs);
+
+	return old_regs;
+}
+
+#endif /* _ASM_X86_IRQ_REGS_32_H */
diff --git a/arch/x86/include/asm/irq_regs_32.h b/arch/x86/include/asm/irq_regs_32.h
deleted file mode 100644
index 86afd74..0000000
--- a/arch/x86/include/asm/irq_regs_32.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * Per-cpu current frame pointer - the location of the last exception frame on
- * the stack, stored in the per-cpu area.
- *
- * Jeremy Fitzhardinge <jeremy@goop.org>
- */
-#ifndef _ASM_X86_IRQ_REGS_32_H
-#define _ASM_X86_IRQ_REGS_32_H
-
-#include <asm/percpu.h>
-
-#define ARCH_HAS_OWN_IRQ_REGS
-
-DECLARE_PER_CPU(struct pt_regs *, irq_regs);
-
-static inline struct pt_regs *get_irq_regs(void)
-{
-	return x86_read_percpu(irq_regs);
-}
-
-static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
-{
-	struct pt_regs *old_regs;
-
-	old_regs = get_irq_regs();
-	x86_write_percpu(irq_regs, new_regs);
-
-	return old_regs;
-}
-
-#endif /* _ASM_X86_IRQ_REGS_32_H */
diff --git a/arch/x86/include/asm/irq_regs_64.h b/arch/x86/include/asm/irq_regs_64.h
deleted file mode 100644
index 3dd9c0b..0000000
--- a/arch/x86/include/asm/irq_regs_64.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/irq_regs.h>
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index f7ff650..9a83a10 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -49,31 +49,33 @@
  *  some of the following vectors are 'rare', they are merged
  *  into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
  *  TLB, reschedule and local APIC vectors are performance-critical.
- *
- *  Vectors 0xf0-0xfa are free (reserved for future Linux use).
  */
 #ifdef CONFIG_X86_32
 
 # define SPURIOUS_APIC_VECTOR		0xff
 # define ERROR_APIC_VECTOR		0xfe
-# define INVALIDATE_TLB_VECTOR		0xfd
-# define RESCHEDULE_VECTOR		0xfc
-# define CALL_FUNCTION_VECTOR		0xfb
-# define CALL_FUNCTION_SINGLE_VECTOR	0xfa
-# define THERMAL_APIC_VECTOR		0xf0
+# define RESCHEDULE_VECTOR		0xfd
+# define CALL_FUNCTION_VECTOR		0xfc
+# define CALL_FUNCTION_SINGLE_VECTOR	0xfb
+# define THERMAL_APIC_VECTOR		0xfa
+/* 0xf8 - 0xf9 : free */
+# define INVALIDATE_TLB_VECTOR_END	0xf7
+# define INVALIDATE_TLB_VECTOR_START	0xf0	/* f0-f7 used for TLB flush */
+
+# define NUM_INVALIDATE_TLB_VECTORS	8
 
 #else
 
-#define SPURIOUS_APIC_VECTOR		0xff
-#define ERROR_APIC_VECTOR		0xfe
-#define RESCHEDULE_VECTOR		0xfd
-#define CALL_FUNCTION_VECTOR		0xfc
-#define CALL_FUNCTION_SINGLE_VECTOR	0xfb
-#define THERMAL_APIC_VECTOR		0xfa
-#define THRESHOLD_APIC_VECTOR		0xf9
-#define UV_BAU_MESSAGE			0xf8
-#define INVALIDATE_TLB_VECTOR_END	0xf7
-#define INVALIDATE_TLB_VECTOR_START	0xf0	/* f0-f7 used for TLB flush */
+# define SPURIOUS_APIC_VECTOR		0xff
+# define ERROR_APIC_VECTOR		0xfe
+# define RESCHEDULE_VECTOR		0xfd
+# define CALL_FUNCTION_VECTOR		0xfc
+# define CALL_FUNCTION_SINGLE_VECTOR	0xfb
+# define THERMAL_APIC_VECTOR		0xfa
+# define THRESHOLD_APIC_VECTOR		0xf9
+# define UV_BAU_MESSAGE			0xf8
+# define INVALIDATE_TLB_VECTOR_END	0xf7
+# define INVALIDATE_TLB_VECTOR_START	0xf0	/* f0-f7 used for TLB flush */
 
 #define NUM_INVALIDATE_TLB_VECTORS	8
 
@@ -105,6 +107,8 @@
 
 #if defined(CONFIG_X86_IO_APIC) && !defined(CONFIG_X86_VOYAGER)
 
+#include <asm/apicnum.h>	/* need MAX_IO_APICS */
+
 #ifndef CONFIG_SPARSE_IRQ
 # if NR_CPUS < MAX_IO_APICS
 #  define NR_IRQS (NR_VECTORS + (32 * NR_CPUS))
@@ -112,11 +116,12 @@
 #  define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
 # endif
 #else
-# if (8 * NR_CPUS) > (32 * MAX_IO_APICS)
-#  define NR_IRQS (NR_VECTORS + (8 * NR_CPUS))
-# else
-#  define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
-# endif
+
+# define NR_IRQS					\
+	((8 * NR_CPUS) > (32 * MAX_IO_APICS) ?		\
+		(NR_VECTORS + (8 * NR_CPUS)) :		\
+		(NR_VECTORS + (32 * MAX_IO_APICS)))	\
+
 #endif
 
 #elif defined(CONFIG_X86_VOYAGER)
diff --git a/arch/x86/include/asm/mach-default/entry_arch.h b/arch/x86/include/asm/mach-default/entry_arch.h
index 6b1add8..6fa399a 100644
--- a/arch/x86/include/asm/mach-default/entry_arch.h
+++ b/arch/x86/include/asm/mach-default/entry_arch.h
@@ -11,10 +11,26 @@
  */
 #ifdef CONFIG_X86_SMP
 BUILD_INTERRUPT(reschedule_interrupt,RESCHEDULE_VECTOR)
-BUILD_INTERRUPT(invalidate_interrupt,INVALIDATE_TLB_VECTOR)
 BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR)
 BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR)
 BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR)
+
+BUILD_INTERRUPT3(invalidate_interrupt0,INVALIDATE_TLB_VECTOR_START+0,
+		 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt1,INVALIDATE_TLB_VECTOR_START+1,
+		 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt2,INVALIDATE_TLB_VECTOR_START+2,
+		 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt3,INVALIDATE_TLB_VECTOR_START+3,
+		 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt4,INVALIDATE_TLB_VECTOR_START+4,
+		 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt5,INVALIDATE_TLB_VECTOR_START+5,
+		 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt6,INVALIDATE_TLB_VECTOR_START+6,
+		 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt7,INVALIDATE_TLB_VECTOR_START+7,
+		 smp_invalidate_interrupt)
 #endif
 
 /*
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 8aeeb3f..52948df 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -21,11 +21,54 @@
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 void destroy_context(struct mm_struct *mm);
 
-#ifdef CONFIG_X86_32
-# include "mmu_context_32.h"
-#else
-# include "mmu_context_64.h"
+
+static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+#ifdef CONFIG_SMP
+	if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
+		percpu_write(cpu_tlbstate.state, TLBSTATE_LAZY);
 #endif
+}
+
+static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+			     struct task_struct *tsk)
+{
+	unsigned cpu = smp_processor_id();
+
+	if (likely(prev != next)) {
+		/* stop flush ipis for the previous mm */
+		cpu_clear(cpu, prev->cpu_vm_mask);
+#ifdef CONFIG_SMP
+		percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
+		percpu_write(cpu_tlbstate.active_mm, next);
+#endif
+		cpu_set(cpu, next->cpu_vm_mask);
+
+		/* Re-load page tables */
+		load_cr3(next->pgd);
+
+		/*
+		 * load the LDT, if the LDT is different:
+		 */
+		if (unlikely(prev->context.ldt != next->context.ldt))
+			load_LDT_nolock(&next->context);
+	}
+#ifdef CONFIG_SMP
+	else {
+		percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
+		BUG_ON(percpu_read(cpu_tlbstate.active_mm) != next);
+
+		if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
+			/* We were in lazy tlb mode and leave_mm disabled
+			 * tlb flush IPI delivery. We must reload CR3
+			 * to make sure to use no freed page tables.
+			 */
+			load_cr3(next->pgd);
+			load_LDT_nolock(&next->context);
+		}
+	}
+#endif
+}
 
 #define activate_mm(prev, next)			\
 do {						\
@@ -33,5 +76,17 @@
 	switch_mm((prev), (next), NULL);	\
 } while (0);
 
+#ifdef CONFIG_X86_32
+#define deactivate_mm(tsk, mm)			\
+do {						\
+	loadsegment(gs, 0);			\
+} while (0)
+#else
+#define deactivate_mm(tsk, mm)			\
+do {						\
+	load_gs_index(0);			\
+	loadsegment(fs, 0);			\
+} while (0)
+#endif
 
 #endif /* _ASM_X86_MMU_CONTEXT_H */
diff --git a/arch/x86/include/asm/mmu_context_32.h b/arch/x86/include/asm/mmu_context_32.h
deleted file mode 100644
index 7e98ce1..0000000
--- a/arch/x86/include/asm/mmu_context_32.h
+++ /dev/null
@@ -1,55 +0,0 @@
-#ifndef _ASM_X86_MMU_CONTEXT_32_H
-#define _ASM_X86_MMU_CONTEXT_32_H
-
-static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-#ifdef CONFIG_SMP
-	if (x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_OK)
-		x86_write_percpu(cpu_tlbstate.state, TLBSTATE_LAZY);
-#endif
-}
-
-static inline void switch_mm(struct mm_struct *prev,
-			     struct mm_struct *next,
-			     struct task_struct *tsk)
-{
-	int cpu = smp_processor_id();
-
-	if (likely(prev != next)) {
-		/* stop flush ipis for the previous mm */
-		cpu_clear(cpu, prev->cpu_vm_mask);
-#ifdef CONFIG_SMP
-		x86_write_percpu(cpu_tlbstate.state, TLBSTATE_OK);
-		x86_write_percpu(cpu_tlbstate.active_mm, next);
-#endif
-		cpu_set(cpu, next->cpu_vm_mask);
-
-		/* Re-load page tables */
-		load_cr3(next->pgd);
-
-		/*
-		 * load the LDT, if the LDT is different:
-		 */
-		if (unlikely(prev->context.ldt != next->context.ldt))
-			load_LDT_nolock(&next->context);
-	}
-#ifdef CONFIG_SMP
-	else {
-		x86_write_percpu(cpu_tlbstate.state, TLBSTATE_OK);
-		BUG_ON(x86_read_percpu(cpu_tlbstate.active_mm) != next);
-
-		if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
-			/* We were in lazy tlb mode and leave_mm disabled
-			 * tlb flush IPI delivery. We must reload %cr3.
-			 */
-			load_cr3(next->pgd);
-			load_LDT_nolock(&next->context);
-		}
-	}
-#endif
-}
-
-#define deactivate_mm(tsk, mm)			\
-	asm("movl %0,%%gs": :"r" (0));
-
-#endif /* _ASM_X86_MMU_CONTEXT_32_H */
diff --git a/arch/x86/include/asm/mmu_context_64.h b/arch/x86/include/asm/mmu_context_64.h
deleted file mode 100644
index 677d36e..0000000
--- a/arch/x86/include/asm/mmu_context_64.h
+++ /dev/null
@@ -1,54 +0,0 @@
-#ifndef _ASM_X86_MMU_CONTEXT_64_H
-#define _ASM_X86_MMU_CONTEXT_64_H
-
-#include <asm/pda.h>
-
-static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-#ifdef CONFIG_SMP
-	if (read_pda(mmu_state) == TLBSTATE_OK)
-		write_pda(mmu_state, TLBSTATE_LAZY);
-#endif
-}
-
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
-			     struct task_struct *tsk)
-{
-	unsigned cpu = smp_processor_id();
-	if (likely(prev != next)) {
-		/* stop flush ipis for the previous mm */
-		cpu_clear(cpu, prev->cpu_vm_mask);
-#ifdef CONFIG_SMP
-		write_pda(mmu_state, TLBSTATE_OK);
-		write_pda(active_mm, next);
-#endif
-		cpu_set(cpu, next->cpu_vm_mask);
-		load_cr3(next->pgd);
-
-		if (unlikely(next->context.ldt != prev->context.ldt))
-			load_LDT_nolock(&next->context);
-	}
-#ifdef CONFIG_SMP
-	else {
-		write_pda(mmu_state, TLBSTATE_OK);
-		if (read_pda(active_mm) != next)
-			BUG();
-		if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
-			/* We were in lazy tlb mode and leave_mm disabled
-			 * tlb flush IPI delivery. We must reload CR3
-			 * to make sure to use no freed page tables.
-			 */
-			load_cr3(next->pgd);
-			load_LDT_nolock(&next->context);
-		}
-	}
-#endif
-}
-
-#define deactivate_mm(tsk, mm)			\
-do {						\
-	load_gs_index(0);			\
-	asm volatile("movl %0,%%fs"::"r"(0));	\
-} while (0)
-
-#endif /* _ASM_X86_MMU_CONTEXT_64_H */
diff --git a/arch/x86/include/asm/mpspec_def.h b/arch/x86/include/asm/mpspec_def.h
index 59568bc..4a7f96d 100644
--- a/arch/x86/include/asm/mpspec_def.h
+++ b/arch/x86/include/asm/mpspec_def.h
@@ -24,17 +24,18 @@
 # endif
 #endif
 
-struct intel_mp_floating {
-	char mpf_signature[4];		/* "_MP_"			*/
-	unsigned int mpf_physptr;	/* Configuration table address	*/
-	unsigned char mpf_length;	/* Our length (paragraphs)	*/
-	unsigned char mpf_specification;/* Specification version	*/
-	unsigned char mpf_checksum;	/* Checksum (makes sum 0)	*/
-	unsigned char mpf_feature1;	/* Standard or configuration ?	*/
-	unsigned char mpf_feature2;	/* Bit7 set for IMCR|PIC	*/
-	unsigned char mpf_feature3;	/* Unused (0)			*/
-	unsigned char mpf_feature4;	/* Unused (0)			*/
-	unsigned char mpf_feature5;	/* Unused (0)			*/
+/* Intel MP Floating Pointer Structure */
+struct mpf_intel {
+	char signature[4];		/* "_MP_"			*/
+	unsigned int physptr;		/* Configuration table address	*/
+	unsigned char length;		/* Our length (paragraphs)	*/
+	unsigned char specification;	/* Specification version	*/
+	unsigned char checksum;		/* Checksum (makes sum 0)	*/
+	unsigned char feature1;		/* Standard or configuration ?	*/
+	unsigned char feature2;		/* Bit7 set for IMCR|PIC	*/
+	unsigned char feature3;		/* Unused (0)			*/
+	unsigned char feature4;		/* Unused (0)			*/
+	unsigned char feature5;		/* Unused (0)			*/
 };
 
 #define MPC_SIGNATURE "PCMP"
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index 5ebca29..e27fdbe 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -13,8 +13,8 @@
 #define DEBUG_STACK_ORDER (EXCEPTION_STACK_ORDER + 1)
 #define DEBUG_STKSZ (PAGE_SIZE << DEBUG_STACK_ORDER)
 
-#define IRQSTACK_ORDER 2
-#define IRQSTACKSIZE (PAGE_SIZE << IRQSTACK_ORDER)
+#define IRQ_STACK_ORDER 2
+#define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER)
 
 #define STACKFAULT_STACK 1
 #define DOUBLEFAULT_STACK 2
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index ba3e2ff..c26c6bf 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -244,7 +244,8 @@
 	void (*flush_tlb_user)(void);
 	void (*flush_tlb_kernel)(void);
 	void (*flush_tlb_single)(unsigned long addr);
-	void (*flush_tlb_others)(const cpumask_t *cpus, struct mm_struct *mm,
+	void (*flush_tlb_others)(const struct cpumask *cpus,
+				 struct mm_struct *mm,
 				 unsigned long va);
 
 	/* Hooks for allocating and freeing a pagetable top-level */
@@ -984,10 +985,11 @@
 	PVOP_VCALL1(pv_mmu_ops.flush_tlb_single, addr);
 }
 
-static inline void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
+static inline void flush_tlb_others(const struct cpumask *cpumask,
+				    struct mm_struct *mm,
 				    unsigned long va)
 {
-	PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, &cpumask, mm, va);
+	PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, cpumask, mm, va);
 }
 
 static inline int paravirt_pgd_alloc(struct mm_struct *mm)
diff --git a/arch/x86/include/asm/pda.h b/arch/x86/include/asm/pda.h
deleted file mode 100644
index 2fbfff8..0000000
--- a/arch/x86/include/asm/pda.h
+++ /dev/null
@@ -1,137 +0,0 @@
-#ifndef _ASM_X86_PDA_H
-#define _ASM_X86_PDA_H
-
-#ifndef __ASSEMBLY__
-#include <linux/stddef.h>
-#include <linux/types.h>
-#include <linux/cache.h>
-#include <asm/page.h>
-
-/* Per processor datastructure. %gs points to it while the kernel runs */
-struct x8664_pda {
-	struct task_struct *pcurrent;	/* 0  Current process */
-	unsigned long data_offset;	/* 8 Per cpu data offset from linker
-					   address */
-	unsigned long kernelstack;	/* 16 top of kernel stack for current */
-	unsigned long oldrsp;		/* 24 user rsp for system call */
-	int irqcount;			/* 32 Irq nesting counter. Starts -1 */
-	unsigned int cpunumber;		/* 36 Logical CPU number */
-#ifdef CONFIG_CC_STACKPROTECTOR
-	unsigned long stack_canary;	/* 40 stack canary value */
-					/* gcc-ABI: this canary MUST be at
-					   offset 40!!! */
-#endif
-	char *irqstackptr;
-	short nodenumber;		/* number of current node (32k max) */
-	short in_bootmem;		/* pda lives in bootmem */
-	unsigned int __softirq_pending;
-	unsigned int __nmi_count;	/* number of NMI on this CPUs */
-	short mmu_state;
-	short isidle;
-	struct mm_struct *active_mm;
-	unsigned apic_timer_irqs;
-	unsigned irq0_irqs;
-	unsigned irq_resched_count;
-	unsigned irq_call_count;
-	unsigned irq_tlb_count;
-	unsigned irq_thermal_count;
-	unsigned irq_threshold_count;
-	unsigned irq_spurious_count;
-} ____cacheline_aligned_in_smp;
-
-extern struct x8664_pda **_cpu_pda;
-extern void pda_init(int);
-
-#define cpu_pda(i) (_cpu_pda[i])
-
-/*
- * There is no fast way to get the base address of the PDA, all the accesses
- * have to mention %fs/%gs.  So it needs to be done this Torvaldian way.
- */
-extern void __bad_pda_field(void) __attribute__((noreturn));
-
-/*
- * proxy_pda doesn't actually exist, but tell gcc it is accessed for
- * all PDA accesses so it gets read/write dependencies right.
- */
-extern struct x8664_pda _proxy_pda;
-
-#define pda_offset(field) offsetof(struct x8664_pda, field)
-
-#define pda_to_op(op, field, val)					\
-do {									\
-	typedef typeof(_proxy_pda.field) T__;				\
-	if (0) { T__ tmp__; tmp__ = (val); }	/* type checking */	\
-	switch (sizeof(_proxy_pda.field)) {				\
-	case 2:								\
-		asm(op "w %1,%%gs:%c2" :				\
-		    "+m" (_proxy_pda.field) :				\
-		    "ri" ((T__)val),					\
-		    "i"(pda_offset(field)));				\
-		break;							\
-	case 4:								\
-		asm(op "l %1,%%gs:%c2" :				\
-		    "+m" (_proxy_pda.field) :				\
-		    "ri" ((T__)val),					\
-		    "i" (pda_offset(field)));				\
-		break;							\
-	case 8:								\
-		asm(op "q %1,%%gs:%c2":					\
-		    "+m" (_proxy_pda.field) :				\
-		    "ri" ((T__)val),					\
-		    "i"(pda_offset(field)));				\
-		break;							\
-	default:							\
-		__bad_pda_field();					\
-	}								\
-} while (0)
-
-#define pda_from_op(op, field)			\
-({						\
-	typeof(_proxy_pda.field) ret__;		\
-	switch (sizeof(_proxy_pda.field)) {	\
-	case 2:					\
-		asm(op "w %%gs:%c1,%0" :	\
-		    "=r" (ret__) :		\
-		    "i" (pda_offset(field)),	\
-		    "m" (_proxy_pda.field));	\
-		break;				\
-	case 4:					\
-		asm(op "l %%gs:%c1,%0":		\
-		    "=r" (ret__):		\
-		    "i" (pda_offset(field)),	\
-		    "m" (_proxy_pda.field));	\
-		break;				\
-	case 8:					\
-		asm(op "q %%gs:%c1,%0":		\
-		    "=r" (ret__) :		\
-		    "i" (pda_offset(field)),	\
-		    "m" (_proxy_pda.field));	\
-		break;				\
-	default:				\
-		__bad_pda_field();		\
-	}					\
-	ret__;					\
-})
-
-#define read_pda(field)		pda_from_op("mov", field)
-#define write_pda(field, val)	pda_to_op("mov", field, val)
-#define add_pda(field, val)	pda_to_op("add", field, val)
-#define sub_pda(field, val)	pda_to_op("sub", field, val)
-#define or_pda(field, val)	pda_to_op("or", field, val)
-
-/* This is not atomic against other CPUs -- CPU preemption needs to be off */
-#define test_and_clear_bit_pda(bit, field)				\
-({									\
-	int old__;							\
-	asm volatile("btr %2,%%gs:%c3\n\tsbbl %0,%0"			\
-		     : "=r" (old__), "+m" (_proxy_pda.field)		\
-		     : "dIr" (bit), "i" (pda_offset(field)) : "memory");\
-	old__;								\
-})
-
-#endif
-
-#define PDA_STACKOFFSET (5*8)
-
-#endif /* _ASM_X86_PDA_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index ece7205..0b64af4 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -2,53 +2,12 @@
 #define _ASM_X86_PERCPU_H
 
 #ifdef CONFIG_X86_64
-#include <linux/compiler.h>
-
-/* Same as asm-generic/percpu.h, except that we store the per cpu offset
-   in the PDA. Longer term the PDA and every per cpu variable
-   should be just put into a single section and referenced directly
-   from %gs */
-
-#ifdef CONFIG_SMP
-#include <asm/pda.h>
-
-#define __per_cpu_offset(cpu) (cpu_pda(cpu)->data_offset)
-#define __my_cpu_offset read_pda(data_offset)
-
-#define per_cpu_offset(x) (__per_cpu_offset(x))
-
+#define __percpu_seg		gs
+#define __percpu_mov_op		movq
+#else
+#define __percpu_seg		fs
+#define __percpu_mov_op		movl
 #endif
-#include <asm-generic/percpu.h>
-
-DECLARE_PER_CPU(struct x8664_pda, pda);
-
-/*
- * These are supposed to be implemented as a single instruction which
- * operates on the per-cpu data base segment.  x86-64 doesn't have
- * that yet, so this is a fairly inefficient workaround for the
- * meantime.  The single instruction is atomic with respect to
- * preemption and interrupts, so we need to explicitly disable
- * interrupts here to achieve the same effect.  However, because it
- * can be used from within interrupt-disable/enable, we can't actually
- * disable interrupts; disabling preemption is enough.
- */
-#define x86_read_percpu(var)						\
-	({								\
-		typeof(per_cpu_var(var)) __tmp;				\
-		preempt_disable();					\
-		__tmp = __get_cpu_var(var);				\
-		preempt_enable();					\
-		__tmp;							\
-	})
-
-#define x86_write_percpu(var, val)					\
-	do {								\
-		preempt_disable();					\
-		__get_cpu_var(var) = (val);				\
-		preempt_enable();					\
-	} while(0)
-
-#else /* CONFIG_X86_64 */
 
 #ifdef __ASSEMBLY__
 
@@ -65,47 +24,26 @@
  *    PER_CPU(cpu_gdt_descr, %ebx)
  */
 #ifdef CONFIG_SMP
-#define PER_CPU(var, reg)				\
-	movl %fs:per_cpu__##this_cpu_off, reg;		\
+#define PER_CPU(var, reg)						\
+	__percpu_mov_op %__percpu_seg:per_cpu__this_cpu_off, reg;	\
 	lea per_cpu__##var(reg), reg
-#define PER_CPU_VAR(var)	%fs:per_cpu__##var
+#define PER_CPU_VAR(var)	%__percpu_seg:per_cpu__##var
 #else /* ! SMP */
-#define PER_CPU(var, reg)			\
-	movl $per_cpu__##var, reg
+#define PER_CPU(var, reg)						\
+	__percpu_mov_op $per_cpu__##var, reg
 #define PER_CPU_VAR(var)	per_cpu__##var
 #endif	/* SMP */
 
 #else /* ...!ASSEMBLY */
 
-/*
- * PER_CPU finds an address of a per-cpu variable.
- *
- * Args:
- *    var - variable name
- *    cpu - 32bit register containing the current CPU number
- *
- * The resulting address is stored in the "cpu" argument.
- *
- * Example:
- *    PER_CPU(cpu_gdt_descr, %ebx)
- */
+#include <linux/stringify.h>
+
 #ifdef CONFIG_SMP
-
-#define __my_cpu_offset x86_read_percpu(this_cpu_off)
-
-/* fs segment starts at (positive) offset == __per_cpu_offset[cpu] */
-#define __percpu_seg "%%fs:"
-
-#else  /* !SMP */
-
-#define __percpu_seg ""
-
-#endif	/* SMP */
-
-#include <asm-generic/percpu.h>
-
-/* We can use this directly for local CPU (faster). */
-DECLARE_PER_CPU(unsigned long, this_cpu_off);
+#define __percpu_arg(x)		"%%"__stringify(__percpu_seg)":%P" #x
+#define __my_cpu_offset		percpu_read(this_cpu_off)
+#else
+#define __percpu_arg(x)		"%" #x
+#endif
 
 /* For arch-specific code, we can use direct single-insn ops (they
  * don't give an lvalue though). */
@@ -120,20 +58,25 @@
 	}						\
 	switch (sizeof(var)) {				\
 	case 1:						\
-		asm(op "b %1,"__percpu_seg"%0"		\
+		asm(op "b %1,"__percpu_arg(0)		\
 		    : "+m" (var)			\
 		    : "ri" ((T__)val));			\
 		break;					\
 	case 2:						\
-		asm(op "w %1,"__percpu_seg"%0"		\
+		asm(op "w %1,"__percpu_arg(0)		\
 		    : "+m" (var)			\
 		    : "ri" ((T__)val));			\
 		break;					\
 	case 4:						\
-		asm(op "l %1,"__percpu_seg"%0"		\
+		asm(op "l %1,"__percpu_arg(0)		\
 		    : "+m" (var)			\
 		    : "ri" ((T__)val));			\
 		break;					\
+	case 8:						\
+		asm(op "q %1,"__percpu_arg(0)		\
+		    : "+m" (var)			\
+		    : "re" ((T__)val));			\
+		break;					\
 	default: __bad_percpu_size();			\
 	}						\
 } while (0)
@@ -143,17 +86,22 @@
 	typeof(var) ret__;				\
 	switch (sizeof(var)) {				\
 	case 1:						\
-		asm(op "b "__percpu_seg"%1,%0"		\
+		asm(op "b "__percpu_arg(1)",%0"		\
 		    : "=r" (ret__)			\
 		    : "m" (var));			\
 		break;					\
 	case 2:						\
-		asm(op "w "__percpu_seg"%1,%0"		\
+		asm(op "w "__percpu_arg(1)",%0"		\
 		    : "=r" (ret__)			\
 		    : "m" (var));			\
 		break;					\
 	case 4:						\
-		asm(op "l "__percpu_seg"%1,%0"		\
+		asm(op "l "__percpu_arg(1)",%0"		\
+		    : "=r" (ret__)			\
+		    : "m" (var));			\
+		break;					\
+	case 8:						\
+		asm(op "q "__percpu_arg(1)",%0"		\
 		    : "=r" (ret__)			\
 		    : "m" (var));			\
 		break;					\
@@ -162,13 +110,30 @@
 	ret__;						\
 })
 
-#define x86_read_percpu(var) percpu_from_op("mov", per_cpu__##var)
-#define x86_write_percpu(var, val) percpu_to_op("mov", per_cpu__##var, val)
-#define x86_add_percpu(var, val) percpu_to_op("add", per_cpu__##var, val)
-#define x86_sub_percpu(var, val) percpu_to_op("sub", per_cpu__##var, val)
-#define x86_or_percpu(var, val) percpu_to_op("or", per_cpu__##var, val)
+#define percpu_read(var)	percpu_from_op("mov", per_cpu__##var)
+#define percpu_write(var, val)	percpu_to_op("mov", per_cpu__##var, val)
+#define percpu_add(var, val)	percpu_to_op("add", per_cpu__##var, val)
+#define percpu_sub(var, val)	percpu_to_op("sub", per_cpu__##var, val)
+#define percpu_and(var, val)	percpu_to_op("and", per_cpu__##var, val)
+#define percpu_or(var, val)	percpu_to_op("or", per_cpu__##var, val)
+#define percpu_xor(var, val)	percpu_to_op("xor", per_cpu__##var, val)
+
+/* This is not atomic against other CPUs -- CPU preemption needs to be off */
+#define x86_test_and_clear_bit_percpu(bit, var)				\
+({									\
+	int old__;							\
+	asm volatile("btr %2,"__percpu_arg(1)"\n\tsbbl %0,%0"		\
+		     : "=r" (old__), "+m" (per_cpu__##var)		\
+		     : "dIr" (bit));					\
+	old__;								\
+})
+
+#include <asm-generic/percpu.h>
+
+/* We can use this directly for local CPU (faster). */
+DECLARE_PER_CPU(unsigned long, this_cpu_off);
+
 #endif /* !__ASSEMBLY__ */
-#endif /* !CONFIG_X86_64 */
 
 #ifdef CONFIG_SMP
 
@@ -195,9 +160,9 @@
 #define	early_per_cpu_ptr(_name) (_name##_early_ptr)
 #define	early_per_cpu_map(_name, _idx) (_name##_early_map[_idx])
 #define	early_per_cpu(_name, _cpu) 				\
-	(early_per_cpu_ptr(_name) ?				\
-		early_per_cpu_ptr(_name)[_cpu] :		\
-		per_cpu(_name, _cpu))
+	*(early_per_cpu_ptr(_name) ?				\
+		&early_per_cpu_ptr(_name)[_cpu] :		\
+		&per_cpu(_name, _cpu))
 
 #else	/* !CONFIG_SMP */
 #define	DEFINE_EARLY_PER_CPU(_type, _name, _initvalue)		\
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index ba09289..1df9637 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -11,7 +11,6 @@
 #include <asm/processor.h>
 #include <linux/bitops.h>
 #include <linux/threads.h>
-#include <asm/pda.h>
 
 extern pud_t level3_kernel_pgt[512];
 extern pud_t level3_ident_pgt[512];
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 091cd88..48676b9 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -378,6 +378,30 @@
 
 #ifdef CONFIG_X86_64
 DECLARE_PER_CPU(struct orig_ist, orig_ist);
+
+union irq_stack_union {
+	char irq_stack[IRQ_STACK_SIZE];
+	/*
+	 * GCC hardcodes the stack canary as %gs:40.  Since the
+	 * irq_stack is the object at %gs:0, we reserve the bottom
+	 * 48 bytes of the irq stack for the canary.
+	 */
+	struct {
+		char gs_base[40];
+		unsigned long stack_canary;
+	};
+};
+
+DECLARE_PER_CPU(union irq_stack_union, irq_stack_union);
+DECLARE_PER_CPU(char *, irq_stack_ptr);
+
+static inline void load_gs_base(int cpu)
+{
+	/* Memory clobbers used to order pda/percpu accesses */
+	mb();
+	wrmsrl(MSR_GS_BASE, (unsigned long)per_cpu(irq_stack_union.gs_base, cpu));
+	mb();
+}
 #endif
 
 extern void print_cpu_info(struct cpuinfo_x86 *);
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index ebe858c..5369497 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -100,7 +100,6 @@
 extern unsigned long init_pg_tables_end;
 
 #else
-void __init x86_64_init_pda(void);
 void __init x86_64_start_kernel(char *real_mode);
 void __init x86_64_start_reservations(char *real_mode_data);
 
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 19953df..45ef8a1b 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -15,34 +15,8 @@
 #  include <asm/io_apic.h>
 # endif
 #endif
-#include <asm/pda.h>
 #include <asm/thread_info.h>
-
-#ifdef CONFIG_X86_64
-
-extern cpumask_var_t cpu_callin_mask;
-extern cpumask_var_t cpu_callout_mask;
-extern cpumask_var_t cpu_initialized_mask;
-extern cpumask_var_t cpu_sibling_setup_mask;
-
-#else /* CONFIG_X86_32 */
-
-extern cpumask_t cpu_callin_map;
-extern cpumask_t cpu_callout_map;
-extern cpumask_t cpu_initialized;
-extern cpumask_t cpu_sibling_setup_map;
-
-#define cpu_callin_mask		((struct cpumask *)&cpu_callin_map)
-#define cpu_callout_mask	((struct cpumask *)&cpu_callout_map)
-#define cpu_initialized_mask	((struct cpumask *)&cpu_initialized)
-#define cpu_sibling_setup_mask	((struct cpumask *)&cpu_sibling_setup_map)
-
-#endif /* CONFIG_X86_32 */
-
-extern void (*mtrr_hook)(void);
-extern void zap_low_mappings(void);
-
-extern int __cpuinit get_local_pda(int cpu);
+#include <asm/cpumask.h>
 
 extern int smp_num_siblings;
 extern unsigned int num_processors;
@@ -50,9 +24,7 @@
 DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
 DECLARE_PER_CPU(cpumask_t, cpu_core_map);
 DECLARE_PER_CPU(u16, cpu_llc_id);
-#ifdef CONFIG_X86_32
 DECLARE_PER_CPU(int, cpu_number);
-#endif
 
 static inline struct cpumask *cpu_sibling_mask(int cpu)
 {
@@ -167,8 +139,6 @@
 void native_send_call_func_ipi(const struct cpumask *mask);
 void native_send_call_func_single_ipi(int cpu);
 
-extern void prefill_possible_map(void);
-
 void smp_store_cpu_info(int id);
 #define cpu_physical_id(cpu)	per_cpu(x86_cpu_to_apicid, cpu)
 
@@ -177,10 +147,6 @@
 {
 	return cpumask_weight(cpu_callout_mask);
 }
-#else
-static inline void prefill_possible_map(void)
-{
-}
 #endif /* CONFIG_SMP */
 
 extern unsigned disabled_cpus __cpuinitdata;
@@ -191,11 +157,11 @@
  * from the initial startup. We map APIC_BASE very early in page_setup(),
  * so this is correct in the x86 case.
  */
-#define raw_smp_processor_id() (x86_read_percpu(cpu_number))
+#define raw_smp_processor_id() (percpu_read(cpu_number))
 extern int safe_smp_processor_id(void);
 
 #elif defined(CONFIG_X86_64_SMP)
-#define raw_smp_processor_id()	read_pda(cpunumber)
+#define raw_smp_processor_id() (percpu_read(cpu_number))
 
 #define stack_smp_processor_id()					\
 ({								\
@@ -205,10 +171,6 @@
 })
 #define safe_smp_processor_id()		smp_processor_id()
 
-#else /* !CONFIG_X86_32_SMP && !CONFIG_X86_64_SMP */
-#define cpu_physical_id(cpu)		boot_cpu_physical_apicid
-#define safe_smp_processor_id()		0
-#define stack_smp_processor_id() 	0
 #endif
 
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -251,11 +213,5 @@
 
 #endif /* CONFIG_X86_LOCAL_APIC */
 
-#ifdef CONFIG_X86_HAS_BOOT_CPU_ID
-extern unsigned char boot_cpu_id;
-#else
-#define boot_cpu_id	0
-#endif
-
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_SMP_H */
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
new file mode 100644
index 0000000..36a700a
--- /dev/null
+++ b/arch/x86/include/asm/stackprotector.h
@@ -0,0 +1,38 @@
+#ifndef _ASM_STACKPROTECTOR_H
+#define _ASM_STACKPROTECTOR_H 1
+
+#include <asm/tsc.h>
+#include <asm/processor.h>
+
+/*
+ * Initialize the stackprotector canary value.
+ *
+ * NOTE: this must only be called from functions that never return,
+ * and it must always be inlined.
+ */
+static __always_inline void boot_init_stack_canary(void)
+{
+	u64 canary;
+	u64 tsc;
+
+	/*
+	 * Build time only check to make sure the stack_canary is at
+	 * offset 40 in the pda; this is a gcc ABI requirement
+	 */
+	BUILD_BUG_ON(offsetof(union irq_stack_union, stack_canary) != 40);
+
+	/*
+	 * We both use the random pool and the current TSC as a source
+	 * of randomness. The TSC only matters for very early init,
+	 * there it already has some randomness on most systems. Later
+	 * on during the bootup the random pool has true entropy too.
+	 */
+	get_random_bytes(&canary, sizeof(canary));
+	tsc = __native_read_tsc();
+	canary += tsc + (tsc << 32UL);
+
+	current->stack_canary = canary;
+	percpu_write(irq_stack_union.stack_canary, canary);
+}
+
+#endif
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index 8e626ea..2fcc70b 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -86,27 +86,44 @@
 	, "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
 	  "r12", "r13", "r14", "r15"
 
+#ifdef CONFIG_CC_STACKPROTECTOR
+#define __switch_canary							  \
+	"movq %P[task_canary](%%rsi),%%r8\n\t"				  \
+	"movq %%r8,"__percpu_arg([gs_canary])"\n\t"
+#define __switch_canary_oparam						  \
+	, [gs_canary] "=m" (per_cpu_var(irq_stack_union.stack_canary))
+#define __switch_canary_iparam						  \
+	, [task_canary] "i" (offsetof(struct task_struct, stack_canary))
+#else	/* CC_STACKPROTECTOR */
+#define __switch_canary
+#define __switch_canary_oparam
+#define __switch_canary_iparam
+#endif	/* CC_STACKPROTECTOR */
+
 /* Save restore flags to clear handle leaking NT */
 #define switch_to(prev, next, last) \
-	asm volatile(SAVE_CONTEXT						    \
+	asm volatile(SAVE_CONTEXT					  \
 	     "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */	  \
 	     "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */	  \
 	     "call __switch_to\n\t"					  \
 	     ".globl thread_return\n"					  \
 	     "thread_return:\n\t"					  \
-	     "movq %%gs:%P[pda_pcurrent],%%rsi\n\t"			  \
+	     "movq "__percpu_arg([current_task])",%%rsi\n\t"		  \
+	     __switch_canary						  \
 	     "movq %P[thread_info](%%rsi),%%r8\n\t"			  \
 	     LOCK_PREFIX "btr  %[tif_fork],%P[ti_flags](%%r8)\n\t"	  \
 	     "movq %%rax,%%rdi\n\t" 					  \
 	     "jc   ret_from_fork\n\t"					  \
 	     RESTORE_CONTEXT						  \
 	     : "=a" (last)					  	  \
+	       __switch_canary_oparam					  \
 	     : [next] "S" (next), [prev] "D" (prev),			  \
 	       [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \
 	       [ti_flags] "i" (offsetof(struct thread_info, flags)),	  \
 	       [tif_fork] "i" (TIF_FORK),			  	  \
 	       [thread_info] "i" (offsetof(struct task_struct, stack)),   \
-	       [pda_pcurrent] "i" (offsetof(struct x8664_pda, pcurrent))  \
+	       [current_task] "m" (per_cpu_var(current_task))		  \
+	       __switch_canary_iparam					  \
 	     : "memory", "cc" __EXTRA_CLOBBER)
 #endif
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 9878964..b46f8ca 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -194,25 +194,21 @@
 
 #else /* X86_32 */
 
-#include <asm/pda.h>
+#include <asm/percpu.h>
+#define KERNEL_STACK_OFFSET (5*8)
 
 /*
  * macros/functions for gaining access to the thread information structure
  * preempt_count needs to be 1 initially, until the scheduler is functional.
  */
 #ifndef __ASSEMBLY__
+DECLARE_PER_CPU(unsigned long, kernel_stack);
+
 static inline struct thread_info *current_thread_info(void)
 {
 	struct thread_info *ti;
-	ti = (void *)(read_pda(kernelstack) + PDA_STACKOFFSET - THREAD_SIZE);
-	return ti;
-}
-
-/* do not use in interrupt context */
-static inline struct thread_info *stack_thread_info(void)
-{
-	struct thread_info *ti;
-	asm("andq %%rsp,%0; " : "=r" (ti) : "0" (~(THREAD_SIZE - 1)));
+	ti = (void *)(percpu_read(kernel_stack) +
+		      KERNEL_STACK_OFFSET - THREAD_SIZE);
 	return ti;
 }
 
@@ -220,8 +216,8 @@
 
 /* how to get the thread information struct from ASM */
 #define GET_THREAD_INFO(reg) \
-	movq %gs:pda_kernelstack,reg ; \
-	subq $(THREAD_SIZE-PDA_STACKOFFSET),reg
+	movq PER_CPU_VAR(kernel_stack),reg ; \
+	subq $(THREAD_SIZE-KERNEL_STACK_OFFSET),reg
 
 #endif
 
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 0e7bbb5..d3539f9 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -113,7 +113,7 @@
 		__flush_tlb();
 }
 
-static inline void native_flush_tlb_others(const cpumask_t *cpumask,
+static inline void native_flush_tlb_others(const struct cpumask *cpumask,
 					   struct mm_struct *mm,
 					   unsigned long va)
 {
@@ -142,31 +142,28 @@
 	flush_tlb_mm(vma->vm_mm);
 }
 
-void native_flush_tlb_others(const cpumask_t *cpumask, struct mm_struct *mm,
-			     unsigned long va);
+void native_flush_tlb_others(const struct cpumask *cpumask,
+			     struct mm_struct *mm, unsigned long va);
 
 #define TLBSTATE_OK	1
 #define TLBSTATE_LAZY	2
 
-#ifdef CONFIG_X86_32
 struct tlb_state {
 	struct mm_struct *active_mm;
 	int state;
-	char __cacheline_padding[L1_CACHE_BYTES-8];
 };
 DECLARE_PER_CPU(struct tlb_state, cpu_tlbstate);
 
-void reset_lazy_tlbstate(void);
-#else
 static inline void reset_lazy_tlbstate(void)
 {
+	percpu_write(cpu_tlbstate.state, 0);
+	percpu_write(cpu_tlbstate.active_mm, &init_mm);
 }
-#endif
 
 #endif	/* SMP */
 
 #ifndef CONFIG_PARAVIRT
-#define flush_tlb_others(mask, mm, va)	native_flush_tlb_others(&mask, mm, va)
+#define flush_tlb_others(mask, mm, va)	native_flush_tlb_others(mask, mm, va)
 #endif
 
 static inline void flush_tlb_kernel_range(unsigned long start,
@@ -175,4 +172,6 @@
 	flush_tlb_all();
 }
 
+extern void zap_low_mappings(void);
+
 #endif /* _ASM_X86_TLBFLUSH_H */
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 4e2f2e0..10022ed 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -83,7 +83,8 @@
 DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);
 
 /* Returns the number of the current Node. */
-#define numa_node_id()		read_pda(nodenumber)
+DECLARE_PER_CPU(int, node_number);
+#define numa_node_id()		percpu_read(node_number)
 
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
 extern int cpu_to_node(int cpu);
@@ -102,10 +103,7 @@
 /* Same function but used if called before per_cpu areas are setup */
 static inline int early_cpu_to_node(int cpu)
 {
-	if (early_per_cpu_ptr(x86_cpu_to_node_map))
-		return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
-
-	return per_cpu(x86_cpu_to_node_map, cpu);
+	return early_per_cpu(x86_cpu_to_node_map, cpu);
 }
 
 /* Returns a pointer to the cpumask of CPUs on Node 'node'. */
@@ -192,9 +190,20 @@
 
 #else /* !CONFIG_NUMA */
 
-#define numa_node_id()		0
-#define	cpu_to_node(cpu)	0
-#define	early_cpu_to_node(cpu)	0
+static inline int numa_node_id(void)
+{
+	return 0;
+}
+
+static inline int cpu_to_node(int cpu)
+{
+	return 0;
+}
+
+static inline int early_cpu_to_node(int cpu)
+{
+	return 0;
+}
 
 static inline const cpumask_t *cpumask_of_node(int node)
 {
diff --git a/arch/x86/include/asm/trampoline.h b/arch/x86/include/asm/trampoline.h
index 780ba0a..90f06c2 100644
--- a/arch/x86/include/asm/trampoline.h
+++ b/arch/x86/include/asm/trampoline.h
@@ -13,6 +13,7 @@
 
 extern unsigned long init_rsp;
 extern unsigned long initial_code;
+extern unsigned long initial_gs;
 
 #define TRAMPOLINE_SIZE roundup(trampoline_end - trampoline_data, PAGE_SIZE)
 #define TRAMPOLINE_BASE 0x6000
diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h
new file mode 100644
index 0000000..dce5fe3
--- /dev/null
+++ b/arch/x86/include/asm/uv/uv.h
@@ -0,0 +1,33 @@
+#ifndef _ASM_X86_UV_UV_H
+#define _ASM_X86_UV_UV_H
+
+enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
+
+#ifdef CONFIG_X86_64
+
+extern enum uv_system_type get_uv_system_type(void);
+extern int is_uv_system(void);
+extern void uv_cpu_init(void);
+extern void uv_system_init(void);
+extern int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip);
+extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
+						 struct mm_struct *mm,
+						 unsigned long va,
+						 unsigned int cpu);
+
+#else	/* X86_64 */
+
+static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; }
+static inline int is_uv_system(void)	{ return 0; }
+static inline void uv_cpu_init(void)	{ }
+static inline void uv_system_init(void)	{ }
+static inline int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip)
+{ return 1; }
+static inline const struct cpumask *
+uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm,
+		    unsigned long va, unsigned int cpu)
+{ return cpumask; }
+
+#endif	/* X86_64 */
+
+#endif	/* _ASM_X86_UV_UV_H */
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 50423c7..9b0e61b 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -325,7 +325,6 @@
 #define cpubit_isset(cpu, bau_local_cpumask) \
 	test_bit((cpu), (bau_local_cpumask).bits)
 
-extern int uv_flush_tlb_others(cpumask_t *, struct mm_struct *, unsigned long);
 extern void uv_bau_message_intr1(void);
 extern void uv_bau_timeout_intr1(void);
 
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index d364df0..0b3272f 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -23,6 +23,7 @@
 CFLAGS_vsyscall_64.o	:= $(PROFILING) -g0 $(nostackp)
 CFLAGS_hpet.o		:= $(nostackp)
 CFLAGS_tsc.o		:= $(nostackp)
+CFLAGS_paravirt.o	:= $(nostackp)
 
 obj-y			:= process_$(BITS).o signal.o entry_$(BITS).o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
@@ -57,7 +58,7 @@
 apm-y				:= apm_32.o
 obj-$(CONFIG_APM)		+= apm.o
 obj-$(CONFIG_X86_SMP)		+= smp.o
-obj-$(CONFIG_X86_SMP)		+= smpboot.o tsc_sync.o ipi.o tlb_$(BITS).o
+obj-$(CONFIG_X86_SMP)		+= smpboot.o tsc_sync.o ipi.o
 obj-$(CONFIG_X86_32_SMP)	+= smpcommon.o
 obj-$(CONFIG_X86_64_SMP)	+= tsc_sync.o smpcommon.o
 obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline_$(BITS).o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index d37593c..4cb5964 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -912,8 +912,8 @@
 	DECLARE_BITMAP(used, 256);
 	bitmap_zero(used, 256);
 	for (i = 0; i < nr_ioapics; i++) {
-		struct mp_config_ioapic *ia = &mp_ioapics[i];
-		__set_bit(ia->mp_apicid, used);
+		struct mpc_ioapic *ia = &mp_ioapics[i];
+		__set_bit(ia->apicid, used);
 	}
 	if (!test_bit(id, used))
 		return id;
@@ -945,47 +945,47 @@
 
 	idx = nr_ioapics;
 
-	mp_ioapics[idx].mp_type = MP_IOAPIC;
-	mp_ioapics[idx].mp_flags = MPC_APIC_USABLE;
-	mp_ioapics[idx].mp_apicaddr = address;
+	mp_ioapics[idx].type = MP_IOAPIC;
+	mp_ioapics[idx].flags = MPC_APIC_USABLE;
+	mp_ioapics[idx].apicaddr = address;
 
 	set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
-	mp_ioapics[idx].mp_apicid = uniq_ioapic_id(id);
+	mp_ioapics[idx].apicid = uniq_ioapic_id(id);
 #ifdef CONFIG_X86_32
-	mp_ioapics[idx].mp_apicver = io_apic_get_version(idx);
+	mp_ioapics[idx].apicver = io_apic_get_version(idx);
 #else
-	mp_ioapics[idx].mp_apicver = 0;
+	mp_ioapics[idx].apicver = 0;
 #endif
 	/*
 	 * Build basic GSI lookup table to facilitate gsi->io_apic lookups
 	 * and to prevent reprogramming of IOAPIC pins (PCI GSIs).
 	 */
-	mp_ioapic_routing[idx].apic_id = mp_ioapics[idx].mp_apicid;
+	mp_ioapic_routing[idx].apic_id = mp_ioapics[idx].apicid;
 	mp_ioapic_routing[idx].gsi_base = gsi_base;
 	mp_ioapic_routing[idx].gsi_end = gsi_base +
 	    io_apic_get_redir_entries(idx);
 
-	printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%lx, "
-	       "GSI %d-%d\n", idx, mp_ioapics[idx].mp_apicid,
-	       mp_ioapics[idx].mp_apicver, mp_ioapics[idx].mp_apicaddr,
+	printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%x, "
+	       "GSI %d-%d\n", idx, mp_ioapics[idx].apicid,
+	       mp_ioapics[idx].apicver, mp_ioapics[idx].apicaddr,
 	       mp_ioapic_routing[idx].gsi_base, mp_ioapic_routing[idx].gsi_end);
 
 	nr_ioapics++;
 }
 
-static void assign_to_mp_irq(struct mp_config_intsrc *m,
-				    struct mp_config_intsrc *mp_irq)
+static void assign_to_mp_irq(struct mpc_intsrc *m,
+				    struct mpc_intsrc *mp_irq)
 {
-	memcpy(mp_irq, m, sizeof(struct mp_config_intsrc));
+	memcpy(mp_irq, m, sizeof(struct mpc_intsrc));
 }
 
-static int mp_irq_cmp(struct mp_config_intsrc *mp_irq,
-				struct mp_config_intsrc *m)
+static int mp_irq_cmp(struct mpc_intsrc *mp_irq,
+				struct mpc_intsrc *m)
 {
-	return memcmp(mp_irq, m, sizeof(struct mp_config_intsrc));
+	return memcmp(mp_irq, m, sizeof(struct mpc_intsrc));
 }
 
-static void save_mp_irq(struct mp_config_intsrc *m)
+static void save_mp_irq(struct mpc_intsrc *m)
 {
 	int i;
 
@@ -1003,7 +1003,7 @@
 {
 	int ioapic;
 	int pin;
-	struct mp_config_intsrc mp_irq;
+	struct mpc_intsrc mp_irq;
 
 	/*
 	 * Convert 'gsi' to 'ioapic.pin'.
@@ -1021,13 +1021,13 @@
 	if ((bus_irq == 0) && (trigger == 3))
 		trigger = 1;
 
-	mp_irq.mp_type = MP_INTSRC;
-	mp_irq.mp_irqtype = mp_INT;
-	mp_irq.mp_irqflag = (trigger << 2) | polarity;
-	mp_irq.mp_srcbus = MP_ISA_BUS;
-	mp_irq.mp_srcbusirq = bus_irq;	/* IRQ */
-	mp_irq.mp_dstapic = mp_ioapics[ioapic].mp_apicid; /* APIC ID */
-	mp_irq.mp_dstirq = pin;	/* INTIN# */
+	mp_irq.type = MP_INTSRC;
+	mp_irq.irqtype = mp_INT;
+	mp_irq.irqflag = (trigger << 2) | polarity;
+	mp_irq.srcbus = MP_ISA_BUS;
+	mp_irq.srcbusirq = bus_irq;	/* IRQ */
+	mp_irq.dstapic = mp_ioapics[ioapic].apicid; /* APIC ID */
+	mp_irq.dstirq = pin;	/* INTIN# */
 
 	save_mp_irq(&mp_irq);
 }
@@ -1037,7 +1037,7 @@
 	int i;
 	int ioapic;
 	unsigned int dstapic;
-	struct mp_config_intsrc mp_irq;
+	struct mpc_intsrc mp_irq;
 
 #if defined (CONFIG_MCA) || defined (CONFIG_EISA)
 	/*
@@ -1062,7 +1062,7 @@
 	ioapic = mp_find_ioapic(0);
 	if (ioapic < 0)
 		return;
-	dstapic = mp_ioapics[ioapic].mp_apicid;
+	dstapic = mp_ioapics[ioapic].apicid;
 
 	/*
 	 * Use the default configuration for the IRQs 0-15.  Unless
@@ -1072,16 +1072,14 @@
 		int idx;
 
 		for (idx = 0; idx < mp_irq_entries; idx++) {
-			struct mp_config_intsrc *irq = mp_irqs + idx;
+			struct mpc_intsrc *irq = mp_irqs + idx;
 
 			/* Do we already have a mapping for this ISA IRQ? */
-			if (irq->mp_srcbus == MP_ISA_BUS
-			    && irq->mp_srcbusirq == i)
+			if (irq->srcbus == MP_ISA_BUS && irq->srcbusirq == i)
 				break;
 
 			/* Do we already have a mapping for this IOAPIC pin */
-			if (irq->mp_dstapic == dstapic &&
-			    irq->mp_dstirq == i)
+			if (irq->dstapic == dstapic && irq->dstirq == i)
 				break;
 		}
 
@@ -1090,13 +1088,13 @@
 			continue;	/* IRQ already used */
 		}
 
-		mp_irq.mp_type = MP_INTSRC;
-		mp_irq.mp_irqflag = 0;	/* Conforming */
-		mp_irq.mp_srcbus = MP_ISA_BUS;
-		mp_irq.mp_dstapic = dstapic;
-		mp_irq.mp_irqtype = mp_INT;
-		mp_irq.mp_srcbusirq = i; /* Identity mapped */
-		mp_irq.mp_dstirq = i;
+		mp_irq.type = MP_INTSRC;
+		mp_irq.irqflag = 0;	/* Conforming */
+		mp_irq.srcbus = MP_ISA_BUS;
+		mp_irq.dstapic = dstapic;
+		mp_irq.irqtype = mp_INT;
+		mp_irq.srcbusirq = i; /* Identity mapped */
+		mp_irq.dstirq = i;
 
 		save_mp_irq(&mp_irq);
 	}
@@ -1207,22 +1205,22 @@
 			u32 gsi, int triggering, int polarity)
 {
 #ifdef CONFIG_X86_MPPARSE
-	struct mp_config_intsrc mp_irq;
+	struct mpc_intsrc mp_irq;
 	int ioapic;
 
 	if (!acpi_ioapic)
 		return 0;
 
 	/* print the entry should happen on mptable identically */
-	mp_irq.mp_type = MP_INTSRC;
-	mp_irq.mp_irqtype = mp_INT;
-	mp_irq.mp_irqflag = (triggering == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) |
+	mp_irq.type = MP_INTSRC;
+	mp_irq.irqtype = mp_INT;
+	mp_irq.irqflag = (triggering == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) |
 				(polarity == ACPI_ACTIVE_HIGH ? 1 : 3);
-	mp_irq.mp_srcbus = number;
-	mp_irq.mp_srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3);
+	mp_irq.srcbus = number;
+	mp_irq.srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3);
 	ioapic = mp_find_ioapic(gsi);
-	mp_irq.mp_dstapic = mp_ioapic_routing[ioapic].apic_id;
-	mp_irq.mp_dstirq = gsi - mp_ioapic_routing[ioapic].gsi_base;
+	mp_irq.dstapic = mp_ioapic_routing[ioapic].apic_id;
+	mp_irq.dstirq = gsi - mp_ioapic_routing[ioapic].gsi_base;
 
 	save_mp_irq(&mp_irq);
 #endif
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 707c1f6..4abff45 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -101,6 +101,7 @@
 	stack_start.sp = temp_stack + sizeof(temp_stack);
 	early_gdt_descr.address =
 			(unsigned long)get_cpu_gdt_table(smp_processor_id());
+	initial_gs = per_cpu_offset(smp_processor_id());
 #endif
 	initial_code = (unsigned long)wakeup_long64;
 	saved_magic = 0x123456789abcdef0;
diff --git a/arch/x86/kernel/apic.c b/arch/x86/kernel/apic.c
index 0f830e4..1df341a 100644
--- a/arch/x86/kernel/apic.c
+++ b/arch/x86/kernel/apic.c
@@ -895,6 +895,10 @@
 {
 	unsigned int value;
 
+	/* APIC hasn't been mapped yet */
+	if (!apic_phys)
+		return;
+
 	clear_local_APIC();
 
 	/*
@@ -1126,6 +1130,13 @@
 	unsigned int value;
 	int i, j;
 
+	if (disable_apic) {
+#ifdef CONFIG_X86_IO_APIC
+		disable_ioapic_setup();
+#endif
+		return;
+	}
+
 #ifdef CONFIG_X86_32
 	/* Pound the ESR really hard over the head with a big hammer - mbligh */
 	if (lapic_is_integrated() && esr_disable) {
@@ -1566,11 +1577,11 @@
 
 int __init APIC_init_uniprocessor(void)
 {
-#ifdef CONFIG_X86_64
 	if (disable_apic) {
 		pr_info("Apic disabled\n");
 		return -1;
 	}
+#ifdef CONFIG_X86_64
 	if (!cpu_has_apic) {
 		disable_apic = 1;
 		pr_info("Apic disabled by BIOS\n");
@@ -1833,6 +1844,11 @@
 	num_processors++;
 	cpu = cpumask_next_zero(-1, cpu_present_mask);
 
+	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) {
 		/*
@@ -1868,17 +1884,8 @@
 #endif
 
 #if defined(CONFIG_X86_SMP) || defined(CONFIG_X86_64)
-	/* are we being called early in kernel startup? */
-	if (early_per_cpu_ptr(x86_cpu_to_apicid)) {
-		u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
-		u16 *bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid);
-
-		cpu_to_apicid[cpu] = apicid;
-		bios_cpu_apicid[cpu] = apicid;
-	} else {
-		per_cpu(x86_cpu_to_apicid, cpu) = apicid;
-		per_cpu(x86_bios_cpu_apicid, cpu) = apicid;
-	}
+	early_per_cpu(x86_cpu_to_apicid, cpu) = apicid;
+	early_per_cpu(x86_bios_cpu_apicid, cpu) = apicid;
 #endif
 
 	set_cpu_possible(cpu, true);
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 1d41d3f..8793ab3 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -11,7 +11,6 @@
 #include <linux/hardirq.h>
 #include <linux/suspend.h>
 #include <linux/kbuild.h>
-#include <asm/pda.h>
 #include <asm/processor.h>
 #include <asm/segment.h>
 #include <asm/thread_info.h>
@@ -48,16 +47,6 @@
 #endif
 	BLANK();
 #undef ENTRY
-#define ENTRY(entry) DEFINE(pda_ ## entry, offsetof(struct x8664_pda, entry))
-	ENTRY(kernelstack); 
-	ENTRY(oldrsp); 
-	ENTRY(pcurrent); 
-	ENTRY(irqcount);
-	ENTRY(cpunumber);
-	ENTRY(irqstackptr);
-	ENTRY(data_offset);
-	BLANK();
-#undef ENTRY
 #ifdef CONFIG_PARAVIRT
 	BLANK();
 	OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 83492b1..99904f2 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -21,14 +21,16 @@
 #include <asm/asm.h>
 #include <asm/numa.h>
 #include <asm/smp.h>
+#include <asm/cpu.h>
+#include <asm/cpumask.h>
 #ifdef CONFIG_X86_LOCAL_APIC
 #include <asm/mpspec.h>
 #include <asm/apic.h>
 #include <mach_apic.h>
 #include <asm/genapic.h>
+#include <asm/uv/uv.h>
 #endif
 
-#include <asm/pda.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/desc.h>
@@ -62,23 +64,23 @@
 
 static struct cpu_dev *this_cpu __cpuinitdata;
 
+DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
 #ifdef CONFIG_X86_64
-/* We need valid kernel segments for data and code in long mode too
- * IRET will check the segment types  kkeil 2000/10/28
- * Also sysret mandates a special GDT layout
- */
-/* The TLS descriptors are currently at a different place compared to i386.
-   Hopefully nobody expects them at a fixed place (Wine?) */
-DEFINE_PER_CPU(struct gdt_page, gdt_page) = { .gdt = {
+	/*
+	 * We need valid kernel segments for data and code in long mode too
+	 * IRET will check the segment types  kkeil 2000/10/28
+	 * Also sysret mandates a special GDT layout
+	 *
+	 * The TLS descriptors are currently at a different place compared to i386.
+	 * Hopefully nobody expects them at a fixed place (Wine?)
+	 */
 	[GDT_ENTRY_KERNEL32_CS] = { { { 0x0000ffff, 0x00cf9b00 } } },
 	[GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00af9b00 } } },
 	[GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9300 } } },
 	[GDT_ENTRY_DEFAULT_USER32_CS] = { { { 0x0000ffff, 0x00cffb00 } } },
 	[GDT_ENTRY_DEFAULT_USER_DS] = { { { 0x0000ffff, 0x00cff300 } } },
 	[GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00affb00 } } },
-} };
 #else
-DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
 	[GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00cf9a00 } } },
 	[GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9200 } } },
 	[GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00cffa00 } } },
@@ -110,9 +112,9 @@
 	[GDT_ENTRY_APMBIOS_BASE+2] = { { { 0x0000ffff, 0x00409200 } } },
 
 	[GDT_ENTRY_ESPFIX_SS] = { { { 0x00000000, 0x00c09200 } } },
-	[GDT_ENTRY_PERCPU] = { { { 0x00000000, 0x00000000 } } },
-} };
+	[GDT_ENTRY_PERCPU] = { { { 0x0000ffff, 0x00cf9200 } } },
 #endif
+} };
 EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
 
 #ifdef CONFIG_X86_32
@@ -877,54 +879,26 @@
 __setup("clearcpuid=", setup_disablecpuid);
 
 #ifdef CONFIG_X86_64
-struct x8664_pda **_cpu_pda __read_mostly;
-EXPORT_SYMBOL(_cpu_pda);
-
 struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
 
-static char boot_cpu_stack[IRQSTACKSIZE] __page_aligned_bss;
+DEFINE_PER_CPU_FIRST(union irq_stack_union,
+		     irq_stack_union) __aligned(PAGE_SIZE);
+#ifdef CONFIG_SMP
+DEFINE_PER_CPU(char *, irq_stack_ptr);	/* will be set during per cpu init */
+#else
+DEFINE_PER_CPU(char *, irq_stack_ptr) =
+	per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64;
+#endif
 
-void __cpuinit pda_init(int cpu)
-{
-	struct x8664_pda *pda = cpu_pda(cpu);
+DEFINE_PER_CPU(unsigned long, kernel_stack) =
+	(unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE;
+EXPORT_PER_CPU_SYMBOL(kernel_stack);
 
-	/* Setup up data that may be needed in __get_free_pages early */
-	loadsegment(fs, 0);
-	loadsegment(gs, 0);
-	/* Memory clobbers used to order PDA accessed */
-	mb();
-	wrmsrl(MSR_GS_BASE, pda);
-	mb();
+DEFINE_PER_CPU(unsigned int, irq_count) = -1;
 
-	pda->cpunumber = cpu;
-	pda->irqcount = -1;
-	pda->kernelstack = (unsigned long)stack_thread_info() -
-				 PDA_STACKOFFSET + THREAD_SIZE;
-	pda->active_mm = &init_mm;
-	pda->mmu_state = 0;
-
-	if (cpu == 0) {
-		/* others are initialized in smpboot.c */
-		pda->pcurrent = &init_task;
-		pda->irqstackptr = boot_cpu_stack;
-		pda->irqstackptr += IRQSTACKSIZE - 64;
-	} else {
-		if (!pda->irqstackptr) {
-			pda->irqstackptr = (char *)
-				__get_free_pages(GFP_ATOMIC, IRQSTACK_ORDER);
-			if (!pda->irqstackptr)
-				panic("cannot allocate irqstack for cpu %d",
-				      cpu);
-			pda->irqstackptr += IRQSTACKSIZE - 64;
-		}
-
-		if (pda->nodenumber == 0 && cpu_to_node(cpu) != NUMA_NO_NODE)
-			pda->nodenumber = cpu_to_node(cpu);
-	}
-}
-
-static char boot_exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ +
-				  DEBUG_STKSZ] __page_aligned_bss;
+static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
+	[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ])
+	__aligned(PAGE_SIZE);
 
 extern asmlinkage void ignore_sysret(void);
 
@@ -982,15 +956,18 @@
 	struct tss_struct *t = &per_cpu(init_tss, cpu);
 	struct orig_ist *orig_ist = &per_cpu(orig_ist, cpu);
 	unsigned long v;
-	char *estacks = NULL;
 	struct task_struct *me;
 	int i;
 
-	/* CPU 0 is initialised in head64.c */
-	if (cpu != 0)
-		pda_init(cpu);
-	else
-		estacks = boot_exception_stacks;
+	loadsegment(fs, 0);
+	loadsegment(gs, 0);
+	load_gs_base(cpu);
+
+#ifdef CONFIG_NUMA
+	if (cpu != 0 && percpu_read(node_number) == 0 &&
+	    cpu_to_node(cpu) != NUMA_NO_NODE)
+		percpu_write(node_number, cpu_to_node(cpu));
+#endif
 
 	me = current;
 
@@ -1024,18 +1001,13 @@
 	 * set up and load the per-CPU TSS
 	 */
 	if (!orig_ist->ist[0]) {
-		static const unsigned int order[N_EXCEPTION_STACKS] = {
-		  [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STACK_ORDER,
-		  [DEBUG_STACK - 1] = DEBUG_STACK_ORDER
+		static const unsigned int sizes[N_EXCEPTION_STACKS] = {
+		  [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ,
+		  [DEBUG_STACK - 1] = DEBUG_STKSZ
 		};
+		char *estacks = per_cpu(exception_stacks, cpu);
 		for (v = 0; v < N_EXCEPTION_STACKS; v++) {
-			if (cpu) {
-				estacks = (char *)__get_free_pages(GFP_ATOMIC, order[v]);
-				if (!estacks)
-					panic("Cannot allocate exception "
-					      "stack %ld %d\n", v, cpu);
-			}
-			estacks += PAGE_SIZE << order[v];
+			estacks += sizes[v];
 			orig_ist->ist[v] = t->x86_tss.ist[v] =
 					(unsigned long)estacks;
 		}
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 6f11e02..4b1c319 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -145,13 +145,14 @@
 
 struct drv_cmd {
 	unsigned int type;
-	cpumask_var_t mask;
+	const struct cpumask *mask;
 	drv_addr_union addr;
 	u32 val;
 };
 
-static void do_drv_read(struct drv_cmd *cmd)
+static long do_drv_read(void *_cmd)
 {
+	struct drv_cmd *cmd = _cmd;
 	u32 h;
 
 	switch (cmd->type) {
@@ -166,10 +167,12 @@
 	default:
 		break;
 	}
+	return 0;
 }
 
-static void do_drv_write(struct drv_cmd *cmd)
+static long do_drv_write(void *_cmd)
 {
+	struct drv_cmd *cmd = _cmd;
 	u32 lo, hi;
 
 	switch (cmd->type) {
@@ -186,30 +189,23 @@
 	default:
 		break;
 	}
+	return 0;
 }
 
 static void drv_read(struct drv_cmd *cmd)
 {
-	cpumask_t saved_mask = current->cpus_allowed;
 	cmd->val = 0;
 
-	set_cpus_allowed_ptr(current, cmd->mask);
-	do_drv_read(cmd);
-	set_cpus_allowed_ptr(current, &saved_mask);
+	work_on_cpu(cpumask_any(cmd->mask), do_drv_read, cmd);
 }
 
 static void drv_write(struct drv_cmd *cmd)
 {
-	cpumask_t saved_mask = current->cpus_allowed;
 	unsigned int i;
 
 	for_each_cpu(i, cmd->mask) {
-		set_cpus_allowed_ptr(current, cpumask_of(i));
-		do_drv_write(cmd);
+		work_on_cpu(i, do_drv_write, cmd);
 	}
-
-	set_cpus_allowed_ptr(current, &saved_mask);
-	return;
 }
 
 static u32 get_cur_val(const struct cpumask *mask)
@@ -235,8 +231,7 @@
 		return 0;
 	}
 
-	cpumask_copy(cmd.mask, mask);
-
+	cmd.mask = mask;
 	drv_read(&cmd);
 
 	dprintk("get_cur_val = %u\n", cmd.val);
@@ -368,7 +363,7 @@
 	return freq;
 }
 
-static unsigned int check_freqs(const cpumask_t *mask, unsigned int freq,
+static unsigned int check_freqs(const struct cpumask *mask, unsigned int freq,
 				struct acpi_cpufreq_data *data)
 {
 	unsigned int cur_freq;
@@ -403,9 +398,6 @@
 		return -ENODEV;
 	}
 
-	if (unlikely(!alloc_cpumask_var(&cmd.mask, GFP_KERNEL)))
-		return -ENOMEM;
-
 	perf = data->acpi_data;
 	result = cpufreq_frequency_table_target(policy,
 						data->freq_table,
@@ -450,9 +442,9 @@
 
 	/* cpufreq holds the hotplug lock, so we are safe from here on */
 	if (policy->shared_type != CPUFREQ_SHARED_TYPE_ANY)
-		cpumask_and(cmd.mask, cpu_online_mask, policy->cpus);
+		cmd.mask = policy->cpus;
 	else
-		cpumask_copy(cmd.mask, cpumask_of(policy->cpu));
+		cmd.mask = cpumask_of(policy->cpu);
 
 	freqs.old = perf->states[perf->state].core_frequency * 1000;
 	freqs.new = data->freq_table[next_state].frequency;
@@ -479,7 +471,6 @@
 	perf->state = next_perf_state;
 
 out:
-	free_cpumask_var(cmd.mask);
 	return result;
 }
 
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 48533d7..58527a9 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -132,7 +132,16 @@
 	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
@@ -263,7 +272,7 @@
 }
 
 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;
@@ -271,7 +280,8 @@
 }
 
 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;
@@ -299,6 +309,15 @@
 	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)
 {
 	unsigned int		eax, ebx, ecx, edx;
@@ -338,11 +357,10 @@
 		 * 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:
@@ -491,17 +509,20 @@
 	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));
 				}
 			}
 		}
@@ -513,9 +534,10 @@
 	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
@@ -620,8 +642,9 @@
 	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);
@@ -684,7 +707,8 @@
 
 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;
@@ -718,7 +742,8 @@
 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;
 
@@ -863,7 +888,7 @@
 	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)
@@ -903,7 +928,7 @@
 		}
 		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;
@@ -916,9 +941,9 @@
 
 	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
index 8ae8c4f..4772e91 100644
--- 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 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 @@
 
 #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 @@
 		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 @@
 		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 @@
 	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 @@
 
 out_free:
 	per_cpu(threshold_banks, cpu)[bank] = NULL;
+	free_cpumask_var(b->cpus);
 	kfree(b);
 out:
 	return err;
@@ -619,7 +625,7 @@
 #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:
 	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/crash.c b/arch/x86/kernel/crash.c
index c689d19..11b93ca 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -24,7 +24,7 @@
 #include <asm/apic.h>
 #include <asm/hpet.h>
 #include <linux/kdebug.h>
-#include <asm/smp.h>
+#include <asm/cpu.h>
 #include <asm/reboot.h>
 #include <asm/virtext.h>
 
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index c302d07..d35db59 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -106,7 +106,8 @@
 		const struct stacktrace_ops *ops, void *data)
 {
 	const unsigned cpu = get_cpu();
-	unsigned long *irqstack_end = (unsigned long *)cpu_pda(cpu)->irqstackptr;
+	unsigned long *irq_stack_end =
+		(unsigned long *)per_cpu(irq_stack_ptr, cpu);
 	unsigned used = 0;
 	struct thread_info *tinfo;
 	int graph = 0;
@@ -160,23 +161,23 @@
 			stack = (unsigned long *) estack_end[-2];
 			continue;
 		}
-		if (irqstack_end) {
-			unsigned long *irqstack;
-			irqstack = irqstack_end -
-				(IRQSTACKSIZE - 64) / sizeof(*irqstack);
+		if (irq_stack_end) {
+			unsigned long *irq_stack;
+			irq_stack = irq_stack_end -
+				(IRQ_STACK_SIZE - 64) / sizeof(*irq_stack);
 
-			if (stack >= irqstack && stack < irqstack_end) {
+			if (stack >= irq_stack && stack < irq_stack_end) {
 				if (ops->stack(data, "IRQ") < 0)
 					break;
 				bp = print_context_stack(tinfo, stack, bp,
-					ops, data, irqstack_end, &graph);
+					ops, data, irq_stack_end, &graph);
 				/*
 				 * We link to the next stack (which would be
 				 * the process stack normally) the last
 				 * pointer (index -1 to end) in the IRQ stack:
 				 */
-				stack = (unsigned long *) (irqstack_end[-1]);
-				irqstack_end = NULL;
+				stack = (unsigned long *) (irq_stack_end[-1]);
+				irq_stack_end = NULL;
 				ops->stack(data, "EOI");
 				continue;
 			}
@@ -199,10 +200,10 @@
 	unsigned long *stack;
 	int i;
 	const int cpu = smp_processor_id();
-	unsigned long *irqstack_end =
-		(unsigned long *) (cpu_pda(cpu)->irqstackptr);
-	unsigned long *irqstack =
-		(unsigned long *) (cpu_pda(cpu)->irqstackptr - IRQSTACKSIZE);
+	unsigned long *irq_stack_end =
+		(unsigned long *)(per_cpu(irq_stack_ptr, cpu));
+	unsigned long *irq_stack =
+		(unsigned long *)(per_cpu(irq_stack_ptr, cpu) - IRQ_STACK_SIZE);
 
 	/*
 	 * debugging aid: "show_stack(NULL, NULL);" prints the
@@ -218,9 +219,9 @@
 
 	stack = sp;
 	for (i = 0; i < kstack_depth_to_print; i++) {
-		if (stack >= irqstack && stack <= irqstack_end) {
-			if (stack == irqstack_end) {
-				stack = (unsigned long *) (irqstack_end[-1]);
+		if (stack >= irq_stack && stack <= irq_stack_end) {
+			if (stack == irq_stack_end) {
+				stack = (unsigned long *) (irq_stack_end[-1]);
 				printk(" <EOI> ");
 			}
 		} else {
@@ -241,7 +242,7 @@
 	int i;
 	unsigned long sp;
 	const int cpu = smp_processor_id();
-	struct task_struct *cur = cpu_pda(cpu)->pcurrent;
+	struct task_struct *cur = current;
 
 	sp = regs->sp;
 	printk("CPU %d ", cpu);
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 4646902..a0b91aa 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -672,7 +672,7 @@
 ENDPROC(common_interrupt)
 	CFI_ENDPROC
 
-#define BUILD_INTERRUPT(name, nr)	\
+#define BUILD_INTERRUPT3(name, nr, fn)	\
 ENTRY(name)				\
 	RING0_INT_FRAME;		\
 	pushl $~(nr);			\
@@ -680,11 +680,13 @@
 	SAVE_ALL;			\
 	TRACE_IRQS_OFF			\
 	movl %esp,%eax;			\
-	call smp_##name;		\
+	call fn;			\
 	jmp ret_from_intr;		\
 	CFI_ENDPROC;			\
 ENDPROC(name)
 
+#define BUILD_INTERRUPT(name, nr)	BUILD_INTERRUPT3(name, nr, smp_##name)
+
 /* The include is where all of the SMP etc. interrupts come from */
 #include "entry_arch.h"
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index e28c7a9..c52b609 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -52,6 +52,7 @@
 #include <asm/irqflags.h>
 #include <asm/paravirt.h>
 #include <asm/ftrace.h>
+#include <asm/percpu.h>
 
 /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
 #include <linux/elf-em.h>
@@ -209,7 +210,7 @@
 
 	/* %rsp:at FRAMEEND */
 	.macro FIXUP_TOP_OF_STACK tmp offset=0
-	movq %gs:pda_oldrsp,\tmp
+	movq PER_CPU_VAR(old_rsp),\tmp
 	movq \tmp,RSP+\offset(%rsp)
 	movq $__USER_DS,SS+\offset(%rsp)
 	movq $__USER_CS,CS+\offset(%rsp)
@@ -220,7 +221,7 @@
 
 	.macro RESTORE_TOP_OF_STACK tmp offset=0
 	movq RSP+\offset(%rsp),\tmp
-	movq \tmp,%gs:pda_oldrsp
+	movq \tmp,PER_CPU_VAR(old_rsp)
 	movq EFLAGS+\offset(%rsp),\tmp
 	movq \tmp,R11+\offset(%rsp)
 	.endm
@@ -336,15 +337,15 @@
 	je 1f
 	SWAPGS
 	/*
-	 * irqcount is used to check if a CPU is already on an interrupt stack
+	 * irq_count is used to check if a CPU is already on an interrupt stack
 	 * or not. While this is essentially redundant with preempt_count it is
 	 * a little cheaper to use a separate counter in the PDA (short of
 	 * moving irq_enter into assembly, which would be too much work)
 	 */
-1:	incl %gs:pda_irqcount
+1:	incl PER_CPU_VAR(irq_count)
 	jne 2f
 	popq_cfi %rax			/* move return address... */
-	mov %gs:pda_irqstackptr,%rsp
+	mov PER_CPU_VAR(irq_stack_ptr),%rsp
 	EMPTY_FRAME 0
 	pushq_cfi %rax			/* ... to the new stack */
 	/*
@@ -467,7 +468,7 @@
 ENTRY(system_call)
 	CFI_STARTPROC	simple
 	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA	rsp,PDA_STACKOFFSET
+	CFI_DEF_CFA	rsp,KERNEL_STACK_OFFSET
 	CFI_REGISTER	rip,rcx
 	/*CFI_REGISTER	rflags,r11*/
 	SWAPGS_UNSAFE_STACK
@@ -478,8 +479,8 @@
 	 */
 ENTRY(system_call_after_swapgs)
 
-	movq	%rsp,%gs:pda_oldrsp
-	movq	%gs:pda_kernelstack,%rsp
+	movq	%rsp,PER_CPU_VAR(old_rsp)
+	movq	PER_CPU_VAR(kernel_stack),%rsp
 	/*
 	 * No need to follow this irqs off/on section - it's straight
 	 * and short:
@@ -522,7 +523,7 @@
 	CFI_REGISTER	rip,rcx
 	RESTORE_ARGS 0,-ARG_SKIP,1
 	/*CFI_REGISTER	rflags,r11*/
-	movq	%gs:pda_oldrsp, %rsp
+	movq	PER_CPU_VAR(old_rsp), %rsp
 	USERGS_SYSRET64
 
 	CFI_RESTORE_STATE
@@ -832,11 +833,11 @@
 	XCPT_FRAME
 	addq $-0x80,(%rsp)		/* Adjust vector to [-256,-1] range */
 	interrupt do_IRQ
-	/* 0(%rsp): oldrsp-ARGOFFSET */
+	/* 0(%rsp): old_rsp-ARGOFFSET */
 ret_from_intr:
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
-	decl %gs:pda_irqcount
+	decl PER_CPU_VAR(irq_count)
 	leaveq
 	CFI_DEF_CFA_REGISTER	rsp
 	CFI_ADJUST_CFA_OFFSET	-8
@@ -1072,10 +1073,10 @@
 	TRACE_IRQS_OFF
 	movq %rsp,%rdi		/* pt_regs pointer */
 	xorl %esi,%esi		/* no error code */
-	movq %gs:pda_data_offset, %rbp
-	subq $EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp)
+	PER_CPU(init_tss, %rbp)
+	subq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%rbp)
 	call \do_sym
-	addq $EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp)
+	addq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%rbp)
 	jmp paranoid_exit	/* %ebx: no swapgs flag */
 	CFI_ENDPROC
 END(\sym)
@@ -1259,14 +1260,14 @@
 	CFI_REL_OFFSET rbp,0
 	mov  %rsp,%rbp
 	CFI_DEF_CFA_REGISTER rbp
-	incl %gs:pda_irqcount
-	cmove %gs:pda_irqstackptr,%rsp
+	incl PER_CPU_VAR(irq_count)
+	cmove PER_CPU_VAR(irq_stack_ptr),%rsp
 	push  %rbp			# backlink for old unwinder
 	call __do_softirq
 	leaveq
 	CFI_DEF_CFA_REGISTER	rsp
 	CFI_ADJUST_CFA_OFFSET   -8
-	decl %gs:pda_irqcount
+	decl PER_CPU_VAR(irq_count)
 	ret
 	CFI_ENDPROC
 END(call_softirq)
@@ -1296,15 +1297,15 @@
 	movq %rdi, %rsp            # we don't return, adjust the stack frame
 	CFI_ENDPROC
 	DEFAULT_FRAME
-11:	incl %gs:pda_irqcount
+11:	incl PER_CPU_VAR(irq_count)
 	movq %rsp,%rbp
 	CFI_DEF_CFA_REGISTER rbp
-	cmovzq %gs:pda_irqstackptr,%rsp
+	cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
 	pushq %rbp			# backlink for old unwinder
 	call xen_evtchn_do_upcall
 	popq %rsp
 	CFI_DEF_CFA_REGISTER rsp
-	decl %gs:pda_irqcount
+	decl PER_CPU_VAR(irq_count)
 	jmp  error_exit
 	CFI_ENDPROC
 END(do_hypervisor_callback)
diff --git a/arch/x86/kernel/genx2apic_uv_x.c b/arch/x86/kernel/genx2apic_uv_x.c
index b193e08..bfe3624 100644
--- a/arch/x86/kernel/genx2apic_uv_x.c
+++ b/arch/x86/kernel/genx2apic_uv_x.c
@@ -25,6 +25,7 @@
 #include <asm/ipi.h>
 #include <asm/genapic.h>
 #include <asm/pgtable.h>
+#include <asm/uv/uv.h>
 #include <asm/uv/uv_mmrs.h>
 #include <asm/uv/uv_hub.h>
 #include <asm/uv/bios.h>
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index b9a4d8c..f5b2722 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -26,27 +26,6 @@
 #include <asm/bios_ebda.h>
 #include <asm/trampoline.h>
 
-/* boot cpu pda */
-static struct x8664_pda _boot_cpu_pda;
-
-#ifdef CONFIG_SMP
-/*
- * We install an empty cpu_pda pointer table to indicate to early users
- * (numa_set_node) that the cpu_pda pointer table for cpus other than
- * the boot cpu is not yet setup.
- */
-static struct x8664_pda *__cpu_pda[NR_CPUS] __initdata;
-#else
-static struct x8664_pda *__cpu_pda[NR_CPUS] __read_mostly;
-#endif
-
-void __init x86_64_init_pda(void)
-{
-	_cpu_pda = __cpu_pda;
-	cpu_pda(0) = &_boot_cpu_pda;
-	pda_init(0);
-}
-
 static void __init zap_identity_mappings(void)
 {
 	pgd_t *pgd = pgd_offset_k(0UL);
@@ -112,8 +91,6 @@
 	if (console_loglevel == 10)
 		early_printk("Kernel alive\n");
 
-	x86_64_init_pda();
-
 	x86_64_start_reservations(real_mode_data);
 }
 
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index e835b4e..24c0e5c 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -429,12 +429,14 @@
 	ljmp $(__KERNEL_CS),$1f
 1:	movl $(__KERNEL_DS),%eax	# reload all the segment registers
 	movl %eax,%ss			# after changing gdt.
-	movl %eax,%fs			# gets reset once there's real percpu
 
 	movl $(__USER_DS),%eax		# DS/ES contains default USER segment
 	movl %eax,%ds
 	movl %eax,%es
 
+	movl $(__KERNEL_PERCPU), %eax
+	movl %eax,%fs			# set this cpu's percpu
+
 	xorl %eax,%eax			# Clear GS and LDT
 	movl %eax,%gs
 	lldt %ax
@@ -446,8 +448,6 @@
 	movb $1, ready
 	cmpb $0,%cl		# the first CPU calls start_kernel
 	je   1f
-	movl $(__KERNEL_PERCPU), %eax
-	movl %eax,%fs		# set this cpu's percpu
 	movl (stack_start), %esp
 1:
 #endif /* CONFIG_SMP */
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 0e275d4..a0a2b5c 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -19,6 +19,7 @@
 #include <asm/msr.h>
 #include <asm/cache.h>
 #include <asm/processor-flags.h>
+#include <asm/percpu.h>
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/asm-offsets.h>
@@ -204,6 +205,19 @@
 	pushq $0
 	popfq
 
+#ifdef CONFIG_SMP
+	/*
+	 * Fix up static pointers that need __per_cpu_load added.  The assembler
+	 * is unable to do this directly.  This is only needed for the boot cpu.
+	 * These values are set up with the correct base addresses by C code for
+	 * secondary cpus.
+	 */
+	movq	initial_gs(%rip), %rax
+	cmpl	$0, per_cpu__cpu_number(%rax)
+	jne	1f
+	addq	%rax, early_gdt_descr_base(%rip)
+1:
+#endif
 	/*
 	 * We must switch to a new descriptor in kernel space for the GDT
 	 * because soon the kernel won't have access anymore to the userspace
@@ -226,12 +240,15 @@
 	movl %eax,%fs
 	movl %eax,%gs
 
-	/* 
-	 * Setup up a dummy PDA. this is just for some early bootup code
-	 * that does in_interrupt() 
-	 */ 
+	/* Set up %gs.
+	 *
+	 * The base of %gs always points to the bottom of the irqstack
+	 * union.  If the stack protector canary is enabled, it is
+	 * located at %gs:40.  Note that, on SMP, the boot cpu uses
+	 * init data section till per cpu areas are set up.
+	 */
 	movl	$MSR_GS_BASE,%ecx
-	movq	$empty_zero_page,%rax
+	movq	initial_gs(%rip),%rax
 	movq    %rax,%rdx
 	shrq	$32,%rdx
 	wrmsr	
@@ -257,6 +274,12 @@
 	.align	8
 	ENTRY(initial_code)
 	.quad	x86_64_start_kernel
+	ENTRY(initial_gs)
+#ifdef CONFIG_SMP
+	.quad	__per_cpu_load
+#else
+	.quad	PER_CPU_VAR(irq_stack_union)
+#endif
 	__FINITDATA
 
 	ENTRY(stack_start)
@@ -401,7 +424,8 @@
 	.globl early_gdt_descr
 early_gdt_descr:
 	.word	GDT_ENTRIES*8-1
-	.quad   per_cpu__gdt_page
+early_gdt_descr_base:
+	.quad	per_cpu__gdt_page
 
 ENTRY(phys_base)
 	/* This must match the first entry in level2_kernel_pgt */
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index 1c4a130..f796603 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -46,6 +46,7 @@
 #include <asm/idle.h>
 #include <asm/io.h>
 #include <asm/smp.h>
+#include <asm/cpu.h>
 #include <asm/desc.h>
 #include <asm/proto.h>
 #include <asm/acpi.h>
@@ -82,11 +83,11 @@
 int nr_ioapic_registers[MAX_IO_APICS];
 
 /* I/O APIC entries */
-struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
+struct mpc_ioapic mp_ioapics[MAX_IO_APICS];
 int nr_ioapics;
 
 /* MP IRQ source entries */
-struct mp_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
+struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES];
 
 /* # of MP IRQ source entries */
 int mp_irq_entries;
@@ -356,7 +357,7 @@
 
 	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;
 	}
 }
@@ -386,7 +387,7 @@
 static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx)
 {
 	return (void __iomem *) __fix_to_virt(FIX_IO_APIC_BASE_0 + idx)
-		+ (mp_ioapics[idx].mp_apicaddr & ~PAGE_MASK);
+		+ (mp_ioapics[idx].apicaddr & ~PAGE_MASK);
 }
 
 static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
@@ -579,9 +580,9 @@
 	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
@@ -944,10 +945,10 @@
 	int i;
 
 	for (i = 0; i < mp_irq_entries; i++)
-		if (mp_irqs[i].mp_irqtype == type &&
-		    (mp_irqs[i].mp_dstapic == mp_ioapics[apic].mp_apicid ||
-		     mp_irqs[i].mp_dstapic == MP_APIC_ALL) &&
-		    mp_irqs[i].mp_dstirq == pin)
+		if (mp_irqs[i].irqtype == type &&
+		    (mp_irqs[i].dstapic == mp_ioapics[apic].apicid ||
+		     mp_irqs[i].dstapic == MP_APIC_ALL) &&
+		    mp_irqs[i].dstirq == pin)
 			return i;
 
 	return -1;
@@ -961,13 +962,13 @@
 	int i;
 
 	for (i = 0; i < mp_irq_entries; i++) {
-		int lbus = mp_irqs[i].mp_srcbus;
+		int lbus = mp_irqs[i].srcbus;
 
 		if (test_bit(lbus, mp_bus_not_pci) &&
-		    (mp_irqs[i].mp_irqtype == type) &&
-		    (mp_irqs[i].mp_srcbusirq == irq))
+		    (mp_irqs[i].irqtype == type) &&
+		    (mp_irqs[i].srcbusirq == irq))
 
-			return mp_irqs[i].mp_dstirq;
+			return mp_irqs[i].dstirq;
 	}
 	return -1;
 }
@@ -977,17 +978,17 @@
 	int i;
 
 	for (i = 0; i < mp_irq_entries; i++) {
-		int lbus = mp_irqs[i].mp_srcbus;
+		int lbus = mp_irqs[i].srcbus;
 
 		if (test_bit(lbus, mp_bus_not_pci) &&
-		    (mp_irqs[i].mp_irqtype == type) &&
-		    (mp_irqs[i].mp_srcbusirq == irq))
+		    (mp_irqs[i].irqtype == type) &&
+		    (mp_irqs[i].srcbusirq == irq))
 			break;
 	}
 	if (i < mp_irq_entries) {
 		int apic;
 		for(apic = 0; apic < nr_ioapics; apic++) {
-			if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic)
+			if (mp_ioapics[apic].apicid == mp_irqs[i].dstapic)
 				return apic;
 		}
 	}
@@ -1012,23 +1013,23 @@
 		return -1;
 	}
 	for (i = 0; i < mp_irq_entries; i++) {
-		int lbus = mp_irqs[i].mp_srcbus;
+		int lbus = mp_irqs[i].srcbus;
 
 		for (apic = 0; apic < nr_ioapics; apic++)
-			if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic ||
-			    mp_irqs[i].mp_dstapic == MP_APIC_ALL)
+			if (mp_ioapics[apic].apicid == mp_irqs[i].dstapic ||
+			    mp_irqs[i].dstapic == MP_APIC_ALL)
 				break;
 
 		if (!test_bit(lbus, mp_bus_not_pci) &&
-		    !mp_irqs[i].mp_irqtype &&
+		    !mp_irqs[i].irqtype &&
 		    (bus == lbus) &&
-		    (slot == ((mp_irqs[i].mp_srcbusirq >> 2) & 0x1f))) {
-			int irq = pin_2_irq(i,apic,mp_irqs[i].mp_dstirq);
+		    (slot == ((mp_irqs[i].srcbusirq >> 2) & 0x1f))) {
+			int irq = pin_2_irq(i, apic, mp_irqs[i].dstirq);
 
 			if (!(apic || IO_APIC_IRQ(irq)))
 				continue;
 
-			if (pin == (mp_irqs[i].mp_srcbusirq & 3))
+			if (pin == (mp_irqs[i].srcbusirq & 3))
 				return irq;
 			/*
 			 * Use the first all-but-pin matching entry as a
@@ -1071,7 +1072,7 @@
  * EISA conforming in the MP table, that means its trigger type must
  * be read in from the ELCR */
 
-#define default_EISA_trigger(idx)	(EISA_ELCR(mp_irqs[idx].mp_srcbusirq))
+#define default_EISA_trigger(idx)	(EISA_ELCR(mp_irqs[idx].srcbusirq))
 #define default_EISA_polarity(idx)	default_ISA_polarity(idx)
 
 /* PCI interrupts are always polarity one level triggered,
@@ -1088,13 +1089,13 @@
 
 static int MPBIOS_polarity(int idx)
 {
-	int bus = mp_irqs[idx].mp_srcbus;
+	int bus = mp_irqs[idx].srcbus;
 	int polarity;
 
 	/*
 	 * Determine IRQ line polarity (high active or low active):
 	 */
-	switch (mp_irqs[idx].mp_irqflag & 3)
+	switch (mp_irqs[idx].irqflag & 3)
 	{
 		case 0: /* conforms, ie. bus-type dependent polarity */
 			if (test_bit(bus, mp_bus_not_pci))
@@ -1130,13 +1131,13 @@
 
 static int MPBIOS_trigger(int idx)
 {
-	int bus = mp_irqs[idx].mp_srcbus;
+	int bus = mp_irqs[idx].srcbus;
 	int trigger;
 
 	/*
 	 * Determine IRQ trigger mode (edge or level sensitive):
 	 */
-	switch ((mp_irqs[idx].mp_irqflag>>2) & 3)
+	switch ((mp_irqs[idx].irqflag>>2) & 3)
 	{
 		case 0: /* conforms, ie. bus-type dependent */
 			if (test_bit(bus, mp_bus_not_pci))
@@ -1214,16 +1215,16 @@
 static int pin_2_irq(int idx, int apic, int pin)
 {
 	int irq, i;
-	int bus = mp_irqs[idx].mp_srcbus;
+	int bus = mp_irqs[idx].srcbus;
 
 	/*
 	 * Debugging check, we are in big trouble if this message pops up!
 	 */
-	if (mp_irqs[idx].mp_dstirq != pin)
+	if (mp_irqs[idx].dstirq != pin)
 		printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n");
 
 	if (test_bit(bus, mp_bus_not_pci)) {
-		irq = mp_irqs[idx].mp_srcbusirq;
+		irq = mp_irqs[idx].srcbusirq;
 	} else {
 		/*
 		 * PCI IRQs are mapped in order
@@ -1566,14 +1567,14 @@
 	apic_printk(APIC_VERBOSE,KERN_DEBUG
 		    "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> "
 		    "IRQ %d Mode:%i Active:%i)\n",
-		    apic, mp_ioapics[apic].mp_apicid, pin, cfg->vector,
+		    apic, mp_ioapics[apic].apicid, pin, cfg->vector,
 		    irq, trigger, polarity);
 
 
-	if (setup_ioapic_entry(mp_ioapics[apic].mp_apicid, irq, &entry,
+	if (setup_ioapic_entry(mp_ioapics[apic].apicid, irq, &entry,
 			       dest, trigger, polarity, cfg->vector)) {
 		printk("Failed to setup ioapic entry for ioapic  %d, pin %d\n",
-		       mp_ioapics[apic].mp_apicid, pin);
+		       mp_ioapics[apic].apicid, pin);
 		__clear_irq_vector(irq, cfg);
 		return;
 	}
@@ -1604,12 +1605,10 @@
 					notcon = 1;
 					apic_printk(APIC_VERBOSE,
 						KERN_DEBUG " %d-%d",
-						mp_ioapics[apic].mp_apicid,
-						pin);
+						mp_ioapics[apic].apicid, pin);
 				} else
 					apic_printk(APIC_VERBOSE, " %d-%d",
-						mp_ioapics[apic].mp_apicid,
-						pin);
+						mp_ioapics[apic].apicid, pin);
 				continue;
 			}
 			if (notcon) {
@@ -1699,7 +1698,7 @@
 	printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
 	for (i = 0; i < nr_ioapics; i++)
 		printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n",
-		       mp_ioapics[i].mp_apicid, nr_ioapic_registers[i]);
+		       mp_ioapics[i].apicid, nr_ioapic_registers[i]);
 
 	/*
 	 * We are a bit conservative about what we expect.  We have to
@@ -1719,7 +1718,7 @@
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 
 	printk("\n");
-	printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mp_apicid);
+	printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].apicid);
 	printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw);
 	printk(KERN_DEBUG ".......    : physical APIC id: %02X\n", reg_00.bits.ID);
 	printk(KERN_DEBUG ".......    : Delivery Type: %X\n", reg_00.bits.delivery_type);
@@ -2121,14 +2120,14 @@
 		reg_00.raw = io_apic_read(apic, 0);
 		spin_unlock_irqrestore(&ioapic_lock, flags);
 
-		old_id = mp_ioapics[apic].mp_apicid;
+		old_id = mp_ioapics[apic].apicid;
 
-		if (mp_ioapics[apic].mp_apicid >= get_physical_broadcast()) {
+		if (mp_ioapics[apic].apicid >= get_physical_broadcast()) {
 			printk(KERN_ERR "BIOS bug, IO-APIC#%d ID is %d in the MPC table!...\n",
-				apic, mp_ioapics[apic].mp_apicid);
+				apic, mp_ioapics[apic].apicid);
 			printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n",
 				reg_00.bits.ID);
-			mp_ioapics[apic].mp_apicid = reg_00.bits.ID;
+			mp_ioapics[apic].apicid = reg_00.bits.ID;
 		}
 
 		/*
@@ -2137,9 +2136,9 @@
 		 * 'stuck on smp_invalidate_needed IPI wait' messages.
 		 */
 		if (check_apicid_used(phys_id_present_map,
-					mp_ioapics[apic].mp_apicid)) {
+					mp_ioapics[apic].apicid)) {
 			printk(KERN_ERR "BIOS bug, IO-APIC#%d ID %d is already used!...\n",
-				apic, mp_ioapics[apic].mp_apicid);
+				apic, mp_ioapics[apic].apicid);
 			for (i = 0; i < get_physical_broadcast(); i++)
 				if (!physid_isset(i, phys_id_present_map))
 					break;
@@ -2148,13 +2147,13 @@
 			printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n",
 				i);
 			physid_set(i, phys_id_present_map);
-			mp_ioapics[apic].mp_apicid = i;
+			mp_ioapics[apic].apicid = i;
 		} else {
 			physid_mask_t tmp;
-			tmp = apicid_to_cpu_present(mp_ioapics[apic].mp_apicid);
+			tmp = apicid_to_cpu_present(mp_ioapics[apic].apicid);
 			apic_printk(APIC_VERBOSE, "Setting %d in the "
 					"phys_id_present_map\n",
-					mp_ioapics[apic].mp_apicid);
+					mp_ioapics[apic].apicid);
 			physids_or(phys_id_present_map, phys_id_present_map, tmp);
 		}
 
@@ -2163,11 +2162,11 @@
 		 * We need to adjust the IRQ routing table
 		 * if the ID changed.
 		 */
-		if (old_id != mp_ioapics[apic].mp_apicid)
+		if (old_id != mp_ioapics[apic].apicid)
 			for (i = 0; i < mp_irq_entries; i++)
-				if (mp_irqs[i].mp_dstapic == old_id)
-					mp_irqs[i].mp_dstapic
-						= mp_ioapics[apic].mp_apicid;
+				if (mp_irqs[i].dstapic == old_id)
+					mp_irqs[i].dstapic
+						= mp_ioapics[apic].apicid;
 
 		/*
 		 * Read the right value from the MPC table and
@@ -2175,9 +2174,9 @@
 		 */
 		apic_printk(APIC_VERBOSE, KERN_INFO
 			"...changing IO-APIC physical APIC ID to %d ...",
-			mp_ioapics[apic].mp_apicid);
+			mp_ioapics[apic].apicid);
 
-		reg_00.bits.ID = mp_ioapics[apic].mp_apicid;
+		reg_00.bits.ID = mp_ioapics[apic].apicid;
 		spin_lock_irqsave(&ioapic_lock, flags);
 		io_apic_write(apic, 0, reg_00.raw);
 		spin_unlock_irqrestore(&ioapic_lock, flags);
@@ -2188,7 +2187,7 @@
 		spin_lock_irqsave(&ioapic_lock, flags);
 		reg_00.raw = io_apic_read(apic, 0);
 		spin_unlock_irqrestore(&ioapic_lock, flags);
-		if (reg_00.bits.ID != mp_ioapics[apic].mp_apicid)
+		if (reg_00.bits.ID != mp_ioapics[apic].apicid)
 			printk("could not set ID!\n");
 		else
 			apic_printk(APIC_VERBOSE, " ok.\n");
@@ -2383,7 +2382,7 @@
 	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 +2404,11 @@
 	}
 
 	/* 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 +2433,7 @@
 				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 +2447,7 @@
 {
 	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 +2515,7 @@
 
 		/* 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;
@@ -3117,8 +3116,8 @@
 
 	spin_lock_irqsave(&ioapic_lock, flags);
 	reg_00.raw = io_apic_read(dev->id, 0);
-	if (reg_00.bits.ID != mp_ioapics[dev->id].mp_apicid) {
-		reg_00.bits.ID = mp_ioapics[dev->id].mp_apicid;
+	if (reg_00.bits.ID != mp_ioapics[dev->id].apicid) {
+		reg_00.bits.ID = mp_ioapics[dev->id].apicid;
 		io_apic_write(dev->id, 0, reg_00.raw);
 	}
 	spin_unlock_irqrestore(&ioapic_lock, flags);
@@ -3183,7 +3182,7 @@
 
 	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;
 
@@ -3258,6 +3257,9 @@
 	int err;
 	unsigned dest;
 
+	if (disable_apic)
+		return -ENXIO;
+
 	cfg = irq_cfg(irq);
 	err = assign_irq_vector(irq, cfg, TARGET_CPUS);
 	if (err)
@@ -3726,6 +3728,9 @@
 	struct irq_cfg *cfg;
 	int err;
 
+	if (disable_apic)
+		return -ENXIO;
+
 	cfg = irq_cfg(irq);
 	err = assign_irq_vector(irq, cfg, TARGET_CPUS);
 	if (!err) {
@@ -3850,6 +3855,22 @@
 		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
    -------------------------------------------------------------------------- */
@@ -3984,8 +4005,8 @@
 		return -1;
 
 	for (i = 0; i < mp_irq_entries; i++)
-		if (mp_irqs[i].mp_irqtype == mp_INT &&
-		    mp_irqs[i].mp_srcbusirq == bus_irq)
+		if (mp_irqs[i].irqtype == mp_INT &&
+		    mp_irqs[i].srcbusirq == bus_irq)
 			break;
 	if (i >= mp_irq_entries)
 		return -1;
@@ -4039,7 +4060,7 @@
 			 */
 			if (desc->status &
 			    (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
-				mask = &desc->affinity;
+				mask = desc->affinity;
 			else
 				mask = TARGET_CPUS;
 
@@ -4100,7 +4121,7 @@
 	ioapic_res = ioapic_setup_resources();
 	for (i = 0; i < nr_ioapics; i++) {
 		if (smp_found_config) {
-			ioapic_phys = mp_ioapics[i].mp_apicaddr;
+			ioapic_phys = mp_ioapics[i].apicaddr;
 #ifdef CONFIG_X86_32
 			if (!ioapic_phys) {
 				printk(KERN_ERR
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 3973e2d..8b30d0c 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -36,11 +36,7 @@
 #endif
 }
 
-#ifdef CONFIG_X86_32
-# define irq_stats(x)		(&per_cpu(irq_stat, x))
-#else
-# define irq_stats(x)		cpu_pda(x)
-#endif
+#define irq_stats(x)		(&per_cpu(irq_stat, x))
 /*
  * /proc/interrupts printing:
  */
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 74b9ff7..e0f29be 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -248,7 +248,7 @@
 		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
index 63c88e6..0b254de 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -19,6 +19,12 @@
 #include <asm/io_apic.h>
 #include <asm/idle.h>
 
+DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
+EXPORT_PER_CPU_SYMBOL(irq_stat);
+
+DEFINE_PER_CPU(struct pt_regs *, irq_regs);
+EXPORT_PER_CPU_SYMBOL(irq_regs);
+
 /*
  * Probabilistic stack overflow check:
  *
@@ -100,7 +106,7 @@
 		/* 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/irqinit_32.c b/arch/x86/kernel/irqinit_32.c
index 1507ad4e..bf629ca 100644
--- a/arch/x86/kernel/irqinit_32.c
+++ b/arch/x86/kernel/irqinit_32.c
@@ -149,8 +149,15 @@
 	 */
 	alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
 
-	/* IPI for invalidation */
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR, invalidate_interrupt);
+	/* IPIs for invalidation */
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7);
 
 	/* IPI for generic function call */
 	alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index b7f4c92..5e9f4fc 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -87,9 +87,9 @@
 #include <linux/cpu.h>
 #include <linux/firmware.h>
 #include <linux/platform_device.h>
+#include <linux/uaccess.h>
 
 #include <asm/msr.h>
-#include <asm/uaccess.h>
 #include <asm/processor.h>
 #include <asm/microcode.h>
 
@@ -196,7 +196,7 @@
 	return (!sigmatch(sig, csig->sig, pf, csig->pf)) ? 0 : 1;
 }
 
-static inline int 
+static inline int
 update_match_revision(struct microcode_header_intel *mc_header,	int rev)
 {
 	return (mc_header->rev <= rev) ? 0 : 1;
@@ -442,8 +442,8 @@
 		return ret;
 	}
 
-	ret = generic_load_microcode(cpu, (void*)firmware->data, firmware->size,
-			&get_ucode_fw);
+	ret = generic_load_microcode(cpu, (void *)firmware->data,
+				     firmware->size, &get_ucode_fw);
 
 	release_firmware(firmware);
 
@@ -460,7 +460,7 @@
 	/* We should bind the task to the CPU */
 	BUG_ON(cpu != raw_smp_processor_id());
 
-	return generic_load_microcode(cpu, (void*)buf, size, &get_ucode_user);
+	return generic_load_microcode(cpu, (void *)buf, size, &get_ucode_user);
 }
 
 static void microcode_fini_cpu(int cpu)
diff --git a/arch/x86/kernel/module_32.c b/arch/x86/kernel/module_32.c
index 3db0a544..0edd819 100644
--- a/arch/x86/kernel/module_32.c
+++ b/arch/x86/kernel/module_32.c
@@ -42,7 +42,7 @@
 {
 	vfree(module_region);
 	/* FIXME: If module_region == mod->init_region, trim exception
-           table entries. */
+	   table entries. */
 }
 
 /* We don't need anything special. */
@@ -113,13 +113,13 @@
 		*para = NULL;
 	char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
 
-	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) { 
+	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
 		if (!strcmp(".text", secstrings + s->sh_name))
 			text = s;
 		if (!strcmp(".altinstructions", secstrings + s->sh_name))
 			alt = s;
 		if (!strcmp(".smp_locks", secstrings + s->sh_name))
-			locks= s;
+			locks = s;
 		if (!strcmp(".parainstructions", secstrings + s->sh_name))
 			para = s;
 	}
diff --git a/arch/x86/kernel/module_64.c b/arch/x86/kernel/module_64.c
index 6ba8783..c23880b 100644
--- a/arch/x86/kernel/module_64.c
+++ b/arch/x86/kernel/module_64.c
@@ -30,14 +30,14 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 
-#define DEBUGP(fmt...) 
+#define DEBUGP(fmt...)
 
 #ifndef CONFIG_UML
 void module_free(struct module *mod, void *module_region)
 {
 	vfree(module_region);
 	/* FIXME: If module_region == mod->init_region, trim exception
-           table entries. */
+	   table entries. */
 }
 
 void *module_alloc(unsigned long size)
@@ -77,7 +77,7 @@
 	Elf64_Rela *rel = (void *)sechdrs[relsec].sh_addr;
 	Elf64_Sym *sym;
 	void *loc;
-	u64 val; 
+	u64 val;
 
 	DEBUGP("Applying relocate section %u to %u\n", relsec,
 	       sechdrs[relsec].sh_info);
@@ -91,11 +91,11 @@
 		sym = (Elf64_Sym *)sechdrs[symindex].sh_addr
 			+ ELF64_R_SYM(rel[i].r_info);
 
-	        DEBUGP("type %d st_value %Lx r_addend %Lx loc %Lx\n",
-		       (int)ELF64_R_TYPE(rel[i].r_info), 
-		       sym->st_value, rel[i].r_addend, (u64)loc);
+		DEBUGP("type %d st_value %Lx r_addend %Lx loc %Lx\n",
+			(int)ELF64_R_TYPE(rel[i].r_info),
+			sym->st_value, rel[i].r_addend, (u64)loc);
 
-		val = sym->st_value + rel[i].r_addend; 
+		val = sym->st_value + rel[i].r_addend;
 
 		switch (ELF64_R_TYPE(rel[i].r_info)) {
 		case R_X86_64_NONE:
@@ -113,16 +113,16 @@
 			if ((s64)val != *(s32 *)loc)
 				goto overflow;
 			break;
-		case R_X86_64_PC32: 
+		case R_X86_64_PC32:
 			val -= (u64)loc;
 			*(u32 *)loc = val;
 #if 0
 			if ((s64)val != *(s32 *)loc)
-				goto overflow; 
+				goto overflow;
 #endif
 			break;
 		default:
-			printk(KERN_ERR "module %s: Unknown rela relocation: %Lu\n",
+			printk(KERN_ERR "module %s: Unknown rela relocation: %llu\n",
 			       me->name, ELF64_R_TYPE(rel[i].r_info));
 			return -ENOEXEC;
 		}
@@ -130,7 +130,7 @@
 	return 0;
 
 overflow:
-	printk(KERN_ERR "overflow in relocation type %d val %Lx\n", 
+	printk(KERN_ERR "overflow in relocation type %d val %Lx\n",
 	       (int)ELF64_R_TYPE(rel[i].r_info), val);
 	printk(KERN_ERR "`%s' likely not compiled with -mcmodel=kernel\n",
 	       me->name);
@@ -143,13 +143,13 @@
 		   unsigned int relsec,
 		   struct module *me)
 {
-	printk("non add relocation not supported\n");
+	printk(KERN_ERR "non add relocation not supported\n");
 	return -ENOSYS;
-} 
+}
 
 int module_finalize(const Elf_Ehdr *hdr,
-                    const Elf_Shdr *sechdrs,
-                    struct module *me)
+		    const Elf_Shdr *sechdrs,
+		    struct module *me)
 {
 	const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL,
 		*para = NULL;
@@ -161,7 +161,7 @@
 		if (!strcmp(".altinstructions", secstrings + s->sh_name))
 			alt = s;
 		if (!strcmp(".smp_locks", secstrings + s->sh_name))
-			locks= s;
+			locks = s;
 		if (!strcmp(".parainstructions", secstrings + s->sh_name))
 			para = s;
 	}
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index a649a4c..fa6bb26 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -144,11 +144,11 @@
 	if (bad_ioapic(m->apicaddr))
 		return;
 
-	mp_ioapics[nr_ioapics].mp_apicaddr = m->apicaddr;
-	mp_ioapics[nr_ioapics].mp_apicid = m->apicid;
-	mp_ioapics[nr_ioapics].mp_type = m->type;
-	mp_ioapics[nr_ioapics].mp_apicver = m->apicver;
-	mp_ioapics[nr_ioapics].mp_flags = m->flags;
+	mp_ioapics[nr_ioapics].apicaddr = m->apicaddr;
+	mp_ioapics[nr_ioapics].apicid = m->apicid;
+	mp_ioapics[nr_ioapics].type = m->type;
+	mp_ioapics[nr_ioapics].apicver = m->apicver;
+	mp_ioapics[nr_ioapics].flags = m->flags;
 	nr_ioapics++;
 }
 
@@ -160,55 +160,55 @@
 		m->srcbusirq, m->dstapic, m->dstirq);
 }
 
-static void __init print_mp_irq_info(struct mp_config_intsrc *mp_irq)
+static void __init print_mp_irq_info(struct mpc_intsrc *mp_irq)
 {
 	apic_printk(APIC_VERBOSE, "Int: type %d, pol %d, trig %d, bus %02x,"
 		" IRQ %02x, APIC ID %x, APIC INT %02x\n",
-		mp_irq->mp_irqtype, mp_irq->mp_irqflag & 3,
-		(mp_irq->mp_irqflag >> 2) & 3, mp_irq->mp_srcbus,
-		mp_irq->mp_srcbusirq, mp_irq->mp_dstapic, mp_irq->mp_dstirq);
+		mp_irq->irqtype, mp_irq->irqflag & 3,
+		(mp_irq->irqflag >> 2) & 3, mp_irq->srcbus,
+		mp_irq->srcbusirq, mp_irq->dstapic, mp_irq->dstirq);
 }
 
 static void __init assign_to_mp_irq(struct mpc_intsrc *m,
-				    struct mp_config_intsrc *mp_irq)
+				    struct mpc_intsrc *mp_irq)
 {
-	mp_irq->mp_dstapic = m->dstapic;
-	mp_irq->mp_type = m->type;
-	mp_irq->mp_irqtype = m->irqtype;
-	mp_irq->mp_irqflag = m->irqflag;
-	mp_irq->mp_srcbus = m->srcbus;
-	mp_irq->mp_srcbusirq = m->srcbusirq;
-	mp_irq->mp_dstirq = m->dstirq;
+	mp_irq->dstapic = m->dstapic;
+	mp_irq->type = m->type;
+	mp_irq->irqtype = m->irqtype;
+	mp_irq->irqflag = m->irqflag;
+	mp_irq->srcbus = m->srcbus;
+	mp_irq->srcbusirq = m->srcbusirq;
+	mp_irq->dstirq = m->dstirq;
 }
 
-static void __init assign_to_mpc_intsrc(struct mp_config_intsrc *mp_irq,
+static void __init assign_to_mpc_intsrc(struct mpc_intsrc *mp_irq,
 					struct mpc_intsrc *m)
 {
-	m->dstapic = mp_irq->mp_dstapic;
-	m->type = mp_irq->mp_type;
-	m->irqtype = mp_irq->mp_irqtype;
-	m->irqflag = mp_irq->mp_irqflag;
-	m->srcbus = mp_irq->mp_srcbus;
-	m->srcbusirq = mp_irq->mp_srcbusirq;
-	m->dstirq = mp_irq->mp_dstirq;
+	m->dstapic = mp_irq->dstapic;
+	m->type = mp_irq->type;
+	m->irqtype = mp_irq->irqtype;
+	m->irqflag = mp_irq->irqflag;
+	m->srcbus = mp_irq->srcbus;
+	m->srcbusirq = mp_irq->srcbusirq;
+	m->dstirq = mp_irq->dstirq;
 }
 
-static int __init mp_irq_mpc_intsrc_cmp(struct mp_config_intsrc *mp_irq,
+static int __init mp_irq_mpc_intsrc_cmp(struct mpc_intsrc *mp_irq,
 					struct mpc_intsrc *m)
 {
-	if (mp_irq->mp_dstapic != m->dstapic)
+	if (mp_irq->dstapic != m->dstapic)
 		return 1;
-	if (mp_irq->mp_type != m->type)
+	if (mp_irq->type != m->type)
 		return 2;
-	if (mp_irq->mp_irqtype != m->irqtype)
+	if (mp_irq->irqtype != m->irqtype)
 		return 3;
-	if (mp_irq->mp_irqflag != m->irqflag)
+	if (mp_irq->irqflag != m->irqflag)
 		return 4;
-	if (mp_irq->mp_srcbus != m->srcbus)
+	if (mp_irq->srcbus != m->srcbus)
 		return 5;
-	if (mp_irq->mp_srcbusirq != m->srcbusirq)
+	if (mp_irq->srcbusirq != m->srcbusirq)
 		return 6;
-	if (mp_irq->mp_dstirq != m->dstirq)
+	if (mp_irq->dstirq != m->dstirq)
 		return 7;
 
 	return 0;
@@ -417,7 +417,7 @@
 	intsrc.type = MP_INTSRC;
 	intsrc.irqflag = 0;	/* conforming */
 	intsrc.srcbus = 0;
-	intsrc.dstapic = mp_ioapics[0].mp_apicid;
+	intsrc.dstapic = mp_ioapics[0].apicid;
 
 	intsrc.irqtype = mp_INT;
 
@@ -570,14 +570,14 @@
 	}
 }
 
-static struct intel_mp_floating *mpf_found;
+static struct mpf_intel *mpf_found;
 
 /*
  * Scan the memory blocks for an SMP configuration block.
  */
 static void __init __get_smp_config(unsigned int early)
 {
-	struct intel_mp_floating *mpf = mpf_found;
+	struct mpf_intel *mpf = mpf_found;
 
 	if (!mpf)
 		return;
@@ -598,9 +598,9 @@
 	}
 
 	printk(KERN_INFO "Intel MultiProcessor Specification v1.%d\n",
-	       mpf->mpf_specification);
+	       mpf->specification);
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32)
-	if (mpf->mpf_feature2 & (1 << 7)) {
+	if (mpf->feature2 & (1 << 7)) {
 		printk(KERN_INFO "    IMCR and PIC compatibility mode.\n");
 		pic_mode = 1;
 	} else {
@@ -611,7 +611,7 @@
 	/*
 	 * Now see if we need to read further.
 	 */
-	if (mpf->mpf_feature1 != 0) {
+	if (mpf->feature1 != 0) {
 		if (early) {
 			/*
 			 * local APIC has default address
@@ -621,16 +621,16 @@
 		}
 
 		printk(KERN_INFO "Default MP configuration #%d\n",
-		       mpf->mpf_feature1);
-		construct_default_ISA_mptable(mpf->mpf_feature1);
+		       mpf->feature1);
+		construct_default_ISA_mptable(mpf->feature1);
 
-	} else if (mpf->mpf_physptr) {
+	} else if (mpf->physptr) {
 
 		/*
 		 * Read the physical hardware table.  Anything here will
 		 * override the defaults.
 		 */
-		if (!smp_read_mpc(phys_to_virt(mpf->mpf_physptr), early)) {
+		if (!smp_read_mpc(phys_to_virt(mpf->physptr), early)) {
 #ifdef CONFIG_X86_LOCAL_APIC
 			smp_found_config = 0;
 #endif
@@ -688,19 +688,19 @@
 				  unsigned reserve)
 {
 	unsigned int *bp = phys_to_virt(base);
-	struct intel_mp_floating *mpf;
+	struct mpf_intel *mpf;
 
 	apic_printk(APIC_VERBOSE, "Scan SMP from %p for %ld bytes.\n",
 			bp, length);
 	BUILD_BUG_ON(sizeof(*mpf) != 16);
 
 	while (length > 0) {
-		mpf = (struct intel_mp_floating *)bp;
+		mpf = (struct mpf_intel *)bp;
 		if ((*bp == SMP_MAGIC_IDENT) &&
-		    (mpf->mpf_length == 1) &&
+		    (mpf->length == 1) &&
 		    !mpf_checksum((unsigned char *)bp, 16) &&
-		    ((mpf->mpf_specification == 1)
-		     || (mpf->mpf_specification == 4))) {
+		    ((mpf->specification == 1)
+		     || (mpf->specification == 4))) {
 #ifdef CONFIG_X86_LOCAL_APIC
 			smp_found_config = 1;
 #endif
@@ -713,7 +713,7 @@
 				return 1;
 			reserve_bootmem_generic(virt_to_phys(mpf), PAGE_SIZE,
 					BOOTMEM_DEFAULT);
-			if (mpf->mpf_physptr) {
+			if (mpf->physptr) {
 				unsigned long size = PAGE_SIZE;
 #ifdef CONFIG_X86_32
 				/*
@@ -722,14 +722,14 @@
 				 * the bottom is mapped now.
 				 * PC-9800's MPC table places on the very last
 				 * of physical memory; so that simply reserving
-				 * PAGE_SIZE from mpg->mpf_physptr yields BUG()
+				 * PAGE_SIZE from mpf->physptr yields BUG()
 				 * in reserve_bootmem.
 				 */
 				unsigned long end = max_low_pfn * PAGE_SIZE;
-				if (mpf->mpf_physptr + size > end)
-					size = end - mpf->mpf_physptr;
+				if (mpf->physptr + size > end)
+					size = end - mpf->physptr;
 #endif
-				reserve_bootmem_generic(mpf->mpf_physptr, size,
+				reserve_bootmem_generic(mpf->physptr, size,
 						BOOTMEM_DEFAULT);
 			}
 
@@ -809,15 +809,15 @@
 	/* not legacy */
 
 	for (i = 0; i < mp_irq_entries; i++) {
-		if (mp_irqs[i].mp_irqtype != mp_INT)
+		if (mp_irqs[i].irqtype != mp_INT)
 			continue;
 
-		if (mp_irqs[i].mp_irqflag != 0x0f)
+		if (mp_irqs[i].irqflag != 0x0f)
 			continue;
 
-		if (mp_irqs[i].mp_srcbus != m->srcbus)
+		if (mp_irqs[i].srcbus != m->srcbus)
 			continue;
-		if (mp_irqs[i].mp_srcbusirq != m->srcbusirq)
+		if (mp_irqs[i].srcbusirq != m->srcbusirq)
 			continue;
 		if (irq_used[i]) {
 			/* already claimed */
@@ -922,10 +922,10 @@
 		if (irq_used[i])
 			continue;
 
-		if (mp_irqs[i].mp_irqtype != mp_INT)
+		if (mp_irqs[i].irqtype != mp_INT)
 			continue;
 
-		if (mp_irqs[i].mp_irqflag != 0x0f)
+		if (mp_irqs[i].irqflag != 0x0f)
 			continue;
 
 		if (nr_m_spare > 0) {
@@ -1001,7 +1001,7 @@
 {
 	char str[16];
 	char oem[10];
-	struct intel_mp_floating *mpf;
+	struct mpf_intel *mpf;
 	struct mpc_table *mpc, *mpc_new;
 
 	if (!enable_update_mptable)
@@ -1014,19 +1014,19 @@
 	/*
 	 * Now see if we need to go further.
 	 */
-	if (mpf->mpf_feature1 != 0)
+	if (mpf->feature1 != 0)
 		return 0;
 
-	if (!mpf->mpf_physptr)
+	if (!mpf->physptr)
 		return 0;
 
-	mpc = phys_to_virt(mpf->mpf_physptr);
+	mpc = phys_to_virt(mpf->physptr);
 
 	if (!smp_check_mpc(mpc, oem, str))
 		return 0;
 
 	printk(KERN_INFO "mpf: %lx\n", virt_to_phys(mpf));
-	printk(KERN_INFO "mpf_physptr: %x\n", mpf->mpf_physptr);
+	printk(KERN_INFO "physptr: %x\n", mpf->physptr);
 
 	if (mpc_new_phys && mpc->length > mpc_new_length) {
 		mpc_new_phys = 0;
@@ -1047,23 +1047,23 @@
 		}
 		printk(KERN_INFO "use in-positon replacing\n");
 	} else {
-		mpf->mpf_physptr = mpc_new_phys;
+		mpf->physptr = mpc_new_phys;
 		mpc_new = phys_to_virt(mpc_new_phys);
 		memcpy(mpc_new, mpc, mpc->length);
 		mpc = mpc_new;
 		/* check if we can modify that */
-		if (mpc_new_phys - mpf->mpf_physptr) {
-			struct intel_mp_floating *mpf_new;
+		if (mpc_new_phys - mpf->physptr) {
+			struct mpf_intel *mpf_new;
 			/* steal 16 bytes from [0, 1k) */
 			printk(KERN_INFO "mpf new: %x\n", 0x400 - 16);
 			mpf_new = phys_to_virt(0x400 - 16);
 			memcpy(mpf_new, mpf, 16);
 			mpf = mpf_new;
-			mpf->mpf_physptr = mpc_new_phys;
+			mpf->physptr = mpc_new_phys;
 		}
-		mpf->mpf_checksum = 0;
-		mpf->mpf_checksum -= mpf_checksum((unsigned char *)mpf, 16);
-		printk(KERN_INFO "mpf_physptr new: %x\n", mpf->mpf_physptr);
+		mpf->checksum = 0;
+		mpf->checksum -= mpf_checksum((unsigned char *)mpf, 16);
+		printk(KERN_INFO "physptr new: %x\n", mpf->physptr);
 	}
 
 	/*
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 7262666..3cf3413 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -35,10 +35,10 @@
 #include <linux/device.h>
 #include <linux/cpu.h>
 #include <linux/notifier.h>
+#include <linux/uaccess.h>
 
 #include <asm/processor.h>
 #include <asm/msr.h>
-#include <asm/uaccess.h>
 #include <asm/system.h>
 
 static struct class *msr_class;
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 7228979..23b6d9e 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -61,11 +61,7 @@
 
 static inline unsigned int get_nmi_count(int cpu)
 {
-#ifdef CONFIG_X86_64
-	return cpu_pda(cpu)->__nmi_count;
-#else
-	return nmi_count(cpu);
-#endif
+	return per_cpu(irq_stat, cpu).__nmi_count;
 }
 
 static inline int mce_in_progress(void)
@@ -82,12 +78,8 @@
  */
 static inline unsigned int get_timer_irqs(int cpu)
 {
-#ifdef CONFIG_X86_64
-	return read_pda(apic_timer_irqs) + read_pda(irq0_irqs);
-#else
 	return per_cpu(irq_stat, cpu).apic_timer_irqs +
 		per_cpu(irq_stat, cpu).irq0_irqs;
-#endif
 }
 
 #ifdef CONFIG_SMP
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index a546f55..2c00a57 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -66,9 +66,6 @@
 DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
 EXPORT_PER_CPU_SYMBOL(current_task);
 
-DEFINE_PER_CPU(int, cpu_number);
-EXPORT_PER_CPU_SYMBOL(cpu_number);
-
 /*
  * Return saved PC of a blocked thread.
  */
@@ -591,7 +588,7 @@
 	if (prev->gs | next->gs)
 		loadsegment(gs, next->gs);
 
-	x86_write_percpu(current_task, next_p);
+	percpu_write(current_task, next_p);
 
 	return prev_p;
 }
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 416fb92..c422eeb 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -16,6 +16,7 @@
 
 #include <stdarg.h>
 
+#include <linux/stackprotector.h>
 #include <linux/cpu.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
@@ -46,7 +47,6 @@
 #include <asm/processor.h>
 #include <asm/i387.h>
 #include <asm/mmu_context.h>
-#include <asm/pda.h>
 #include <asm/prctl.h>
 #include <asm/desc.h>
 #include <asm/proto.h>
@@ -57,6 +57,12 @@
 
 asmlinkage extern void ret_from_fork(void);
 
+DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
+EXPORT_PER_CPU_SYMBOL(current_task);
+
+DEFINE_PER_CPU(unsigned long, old_rsp);
+static DEFINE_PER_CPU(unsigned char, is_idle);
+
 unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED;
 
 static ATOMIC_NOTIFIER_HEAD(idle_notifier);
@@ -75,13 +81,13 @@
 
 void enter_idle(void)
 {
-	write_pda(isidle, 1);
+	percpu_write(is_idle, 1);
 	atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
 }
 
 static void __exit_idle(void)
 {
-	if (test_and_clear_bit_pda(0, isidle) == 0)
+	if (x86_test_and_clear_bit_percpu(0, is_idle) == 0)
 		return;
 	atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
 }
@@ -111,6 +117,17 @@
 void cpu_idle(void)
 {
 	current_thread_info()->status |= TS_POLLING;
+
+	/*
+	 * If we're the non-boot CPU, nothing set the PDA stack
+	 * canary up for us - and if we are the boot CPU we have
+	 * a 0 stack canary. This is a good place for updating
+	 * it, as we wont ever return from this function (so the
+	 * invalid canaries already on the stack wont ever
+	 * trigger):
+	 */
+	boot_init_stack_canary();
+
 	/* endless idle loop with no priority at all */
 	while (1) {
 		tick_nohz_stop_sched_tick(1);
@@ -392,7 +409,7 @@
 	load_gs_index(0);
 	regs->ip		= new_ip;
 	regs->sp		= new_sp;
-	write_pda(oldrsp, new_sp);
+	percpu_write(old_rsp, new_sp);
 	regs->cs		= __USER_CS;
 	regs->ss		= __USER_DS;
 	regs->flags		= 0x200;
@@ -613,21 +630,13 @@
 	/*
 	 * Switch the PDA and FPU contexts.
 	 */
-	prev->usersp = read_pda(oldrsp);
-	write_pda(oldrsp, next->usersp);
-	write_pda(pcurrent, next_p);
+	prev->usersp = percpu_read(old_rsp);
+	percpu_write(old_rsp, next->usersp);
+	percpu_write(current_task, next_p);
 
-	write_pda(kernelstack,
+	percpu_write(kernel_stack,
 		  (unsigned long)task_stack_page(next_p) +
-		  THREAD_SIZE - PDA_STACKOFFSET);
-#ifdef CONFIG_CC_STACKPROTECTOR
-	write_pda(stack_canary, next_p->stack_canary);
-	/*
-	 * Build time only check to make sure the stack_canary is at
-	 * offset 40 in the pda; this is a gcc ABI requirement
-	 */
-	BUILD_BUG_ON(offsetof(struct x8664_pda, stack_canary) != 40);
-#endif
+		  THREAD_SIZE - KERNEL_STACK_OFFSET);
 
 	/*
 	 * Now maybe reload the debug registers and handle I/O bitmaps
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 2b46eb4..f8536fe 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -14,6 +14,7 @@
 #include <asm/reboot.h>
 #include <asm/pci_x86.h>
 #include <asm/virtext.h>
+#include <asm/cpu.h>
 
 #ifdef CONFIG_X86_32
 # include <linux/dmi.h>
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index ae0d804..f41c448 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -89,7 +89,7 @@
 
 #include <asm/system.h>
 #include <asm/vsyscall.h>
-#include <asm/smp.h>
+#include <asm/cpu.h>
 #include <asm/desc.h>
 #include <asm/dma.h>
 #include <asm/iommu.h>
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 55c4607..90b8e15 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -13,6 +13,23 @@
 #include <asm/mpspec.h>
 #include <asm/apicdef.h>
 #include <asm/highmem.h>
+#include <asm/proto.h>
+#include <asm/cpumask.h>
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+# define DBG(x...) printk(KERN_DEBUG x)
+#else
+# define DBG(x...)
+#endif
+
+/*
+ * Could be inside CONFIG_HAVE_SETUP_PER_CPU_AREA with other stuff but
+ * voyager wants cpu_number too.
+ */
+#ifdef CONFIG_SMP
+DEFINE_PER_CPU(int, cpu_number);
+EXPORT_PER_CPU_SYMBOL(cpu_number);
+#endif
 
 #ifdef CONFIG_X86_LOCAL_APIC
 unsigned int num_processors;
@@ -26,31 +43,60 @@
 physid_mask_t phys_cpu_present_map;
 #endif
 
-/* map cpu index to physical APIC ID */
+/*
+ * Map cpu index to physical APIC ID
+ */
 DEFINE_EARLY_PER_CPU(u16, x86_cpu_to_apicid, BAD_APICID);
 DEFINE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid, BAD_APICID);
 EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
 EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
-#define	X86_64_NUMA	1
+#define	X86_64_NUMA	1	/* (used later) */
+DEFINE_PER_CPU(int, node_number) = 0;
+EXPORT_PER_CPU_SYMBOL(node_number);
 
-/* map cpu index to node index */
+/*
+ * Map cpu index to node index
+ */
 DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE);
 EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map);
 
-/* which logical CPUs are on which nodes */
+/*
+ * Which logical CPUs are on which nodes
+ */
 cpumask_t *node_to_cpumask_map;
 EXPORT_SYMBOL(node_to_cpumask_map);
 
-/* setup node_to_cpumask_map */
+/*
+ * Setup node_to_cpumask_map
+ */
 static void __init setup_node_to_cpumask_map(void);
 
 #else
 static inline void setup_node_to_cpumask_map(void) { }
 #endif
 
-#if defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) && defined(CONFIG_X86_SMP)
+#ifdef CONFIG_X86_64
+
+/* correctly size the local cpu masks */
+static void setup_cpu_local_masks(void)
+{
+	alloc_bootmem_cpumask_var(&cpu_initialized_mask);
+	alloc_bootmem_cpumask_var(&cpu_callin_mask);
+	alloc_bootmem_cpumask_var(&cpu_callout_mask);
+	alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask);
+}
+
+#else /* CONFIG_X86_32 */
+
+static inline void setup_cpu_local_masks(void)
+{
+}
+
+#endif /* CONFIG_X86_32 */
+
+#ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
 /*
  * Copy data used in early init routines from the initial arrays to the
  * per cpu data areas.  These arrays then become expendable and the
@@ -79,78 +125,14 @@
 #endif
 }
 
-#ifdef CONFIG_X86_32
-/*
- * Great future not-so-futuristic plan: make i386 and x86_64 do it
- * the same way
- */
-unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
-EXPORT_SYMBOL(__per_cpu_offset);
-static inline void setup_cpu_pda_map(void) { }
-
-#elif !defined(CONFIG_SMP)
-static inline void setup_cpu_pda_map(void) { }
-
-#else /* CONFIG_SMP && CONFIG_X86_64 */
-
-/*
- * Allocate cpu_pda pointer table and array via alloc_bootmem.
- */
-static void __init setup_cpu_pda_map(void)
-{
-	char *pda;
-	struct x8664_pda **new_cpu_pda;
-	unsigned long size;
-	int cpu;
-
-	size = roundup(sizeof(struct x8664_pda), cache_line_size());
-
-	/* allocate cpu_pda array and pointer table */
-	{
-		unsigned long tsize = nr_cpu_ids * sizeof(void *);
-		unsigned long asize = size * (nr_cpu_ids - 1);
-
-		tsize = roundup(tsize, cache_line_size());
-		new_cpu_pda = alloc_bootmem(tsize + asize);
-		pda = (char *)new_cpu_pda + tsize;
-	}
-
-	/* initialize pointer table to static pda's */
-	for_each_possible_cpu(cpu) {
-		if (cpu == 0) {
-			/* leave boot cpu pda in place */
-			new_cpu_pda[0] = cpu_pda(0);
-			continue;
-		}
-		new_cpu_pda[cpu] = (struct x8664_pda *)pda;
-		new_cpu_pda[cpu]->in_bootmem = 1;
-		pda += size;
-	}
-
-	/* point to new pointer table */
-	_cpu_pda = new_cpu_pda;
-}
-
-#endif /* CONFIG_SMP && CONFIG_X86_64 */
-
 #ifdef CONFIG_X86_64
-
-/* correctly size the local cpu masks */
-static void setup_cpu_local_masks(void)
-{
-	alloc_bootmem_cpumask_var(&cpu_initialized_mask);
-	alloc_bootmem_cpumask_var(&cpu_callin_mask);
-	alloc_bootmem_cpumask_var(&cpu_callout_mask);
-	alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask);
-}
-
-#else /* CONFIG_X86_32 */
-
-static inline void setup_cpu_local_masks(void)
-{
-}
-
-#endif /* CONFIG_X86_32 */
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = {
+	[0] = (unsigned long)__per_cpu_load,
+};
+#else
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
+#endif
+EXPORT_SYMBOL(__per_cpu_offset);
 
 /*
  * Great future plan:
@@ -164,9 +146,6 @@
 	int cpu;
 	unsigned long align = 1;
 
-	/* Setup cpu_pda map */
-	setup_cpu_pda_map();
-
 	/* Copy section for each CPU (we discard the original) */
 	old_size = PERCPU_ENOUGH_ROOM;
 	align = max_t(unsigned long, PAGE_SIZE, align);
@@ -197,8 +176,23 @@
 				cpu, node, __pa(ptr));
 		}
 #endif
+
+		memcpy(ptr, __per_cpu_load, __per_cpu_end - __per_cpu_start);
 		per_cpu_offset(cpu) = ptr - __per_cpu_start;
-		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
+		per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu);
+		per_cpu(cpu_number, cpu) = cpu;
+#ifdef CONFIG_X86_64
+		per_cpu(irq_stack_ptr, cpu) =
+			per_cpu(irq_stack_union.irq_stack, cpu) + IRQ_STACK_SIZE - 64;
+		/*
+		 * Up to this point, CPU0 has been using .data.init
+		 * area.  Reload %gs offset for CPU0.
+		 */
+		if (cpu == 0)
+			load_gs_base(cpu);
+#endif
+
+		DBG("PERCPU: cpu %4d %p\n", cpu, ptr);
 	}
 
 	/* Setup percpu data maps */
@@ -220,6 +214,7 @@
  * Requires node_possible_map to be valid.
  *
  * Note: node_to_cpumask() is not valid until after this is done.
+ * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.)
  */
 static void __init setup_node_to_cpumask_map(void)
 {
@@ -235,6 +230,7 @@
 
 	/* allocate the map */
 	map = alloc_bootmem_low(nr_node_ids * sizeof(cpumask_t));
+	DBG("node_to_cpumask_map at %p for %d nodes\n", map, nr_node_ids);
 
 	pr_debug("Node to cpumask map at %p for %d nodes\n",
 		 map, nr_node_ids);
@@ -247,17 +243,23 @@
 {
 	int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);
 
-	if (cpu_pda(cpu) && node != NUMA_NO_NODE)
-		cpu_pda(cpu)->nodenumber = node;
-
-	if (cpu_to_node_map)
+	/* early setting, no percpu area yet */
+	if (cpu_to_node_map) {
 		cpu_to_node_map[cpu] = node;
+		return;
+	}
 
-	else if (per_cpu_offset(cpu))
-		per_cpu(x86_cpu_to_node_map, cpu) = node;
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+	if (cpu >= nr_cpu_ids || !per_cpu_offset(cpu)) {
+		printk(KERN_ERR "numa_set_node: invalid cpu# (%d)\n", cpu);
+		dump_stack();
+		return;
+	}
+#endif
+	per_cpu(x86_cpu_to_node_map, cpu) = node;
 
-	else
-		pr_debug("Setting node for non-present cpu %d\n", cpu);
+	if (node != NUMA_NO_NODE)
+		per_cpu(node_number, cpu) = node;
 }
 
 void __cpuinit numa_clear_node(int cpu)
@@ -274,7 +276,7 @@
 
 void __cpuinit numa_remove_cpu(int cpu)
 {
-	cpu_clear(cpu, node_to_cpumask_map[cpu_to_node(cpu)]);
+	cpu_clear(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
 }
 
 #else /* CONFIG_DEBUG_PER_CPU_MAPS */
@@ -284,7 +286,7 @@
  */
 static void __cpuinit numa_set_cpumask(int cpu, int enable)
 {
-	int node = cpu_to_node(cpu);
+	int node = early_cpu_to_node(cpu);
 	cpumask_t *mask;
 	char buf[64];
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index bb1a3b1..def770b 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -53,7 +53,6 @@
 #include <asm/nmi.h>
 #include <asm/irq.h>
 #include <asm/idle.h>
-#include <asm/smp.h>
 #include <asm/trampoline.h>
 #include <asm/cpu.h>
 #include <asm/numa.h>
@@ -63,6 +62,7 @@
 #include <asm/vmi.h>
 #include <asm/genapic.h>
 #include <asm/setup.h>
+#include <asm/uv/uv.h>
 #include <linux/mc146818rtc.h>
 
 #include <mach_apic.h>
@@ -745,52 +745,6 @@
 	complete(&c_idle->done);
 }
 
-#ifdef CONFIG_X86_64
-
-/* __ref because it's safe to call free_bootmem when after_bootmem == 0. */
-static void __ref free_bootmem_pda(struct x8664_pda *oldpda)
-{
-	if (!after_bootmem)
-		free_bootmem((unsigned long)oldpda, sizeof(*oldpda));
-}
-
-/*
- * Allocate node local memory for the AP pda.
- *
- * Must be called after the _cpu_pda pointer table is initialized.
- */
-int __cpuinit get_local_pda(int cpu)
-{
-	struct x8664_pda *oldpda, *newpda;
-	unsigned long size = sizeof(struct x8664_pda);
-	int node = cpu_to_node(cpu);
-
-	if (cpu_pda(cpu) && !cpu_pda(cpu)->in_bootmem)
-		return 0;
-
-	oldpda = cpu_pda(cpu);
-	newpda = kmalloc_node(size, GFP_ATOMIC, node);
-	if (!newpda) {
-		printk(KERN_ERR "Could not allocate node local PDA "
-			"for CPU %d on node %d\n", cpu, node);
-
-		if (oldpda)
-			return 0;	/* have a usable pda */
-		else
-			return -1;
-	}
-
-	if (oldpda) {
-		memcpy(newpda, oldpda, size);
-		free_bootmem_pda(oldpda);
-	}
-
-	newpda->in_bootmem = 0;
-	cpu_pda(cpu) = newpda;
-	return 0;
-}
-#endif /* CONFIG_X86_64 */
-
 static int __cpuinit do_boot_cpu(int apicid, int cpu)
 /*
  * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad
@@ -808,16 +762,6 @@
 	};
 	INIT_WORK(&c_idle.work, do_fork_idle);
 
-#ifdef CONFIG_X86_64
-	/* Allocate node local memory for AP pdas */
-	if (cpu > 0) {
-		boot_error = get_local_pda(cpu);
-		if (boot_error)
-			goto restore_state;
-			/* if can't get pda memory, can't start cpu */
-	}
-#endif
-
 	alternatives_smp_switch(1);
 
 	c_idle.idle = get_idle_for_cpu(cpu);
@@ -847,14 +791,17 @@
 
 	set_idle_for_cpu(cpu, c_idle.idle);
 do_rest:
-#ifdef CONFIG_X86_32
 	per_cpu(current_task, cpu) = c_idle.idle;
+#ifdef CONFIG_X86_32
 	init_gdt(cpu);
 	/* Stack for startup_32 can be just as for start_secondary onwards */
 	irq_ctx_init(cpu);
 #else
-	cpu_pda(cpu)->pcurrent = c_idle.idle;
 	clear_tsk_thread_flag(c_idle.idle, TIF_FORK);
+	initial_gs = per_cpu_offset(cpu);
+	per_cpu(kernel_stack, cpu) =
+		(unsigned long)task_stack_page(c_idle.idle) -
+		KERNEL_STACK_OFFSET + THREAD_SIZE;
 #endif
 	early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
 	initial_code = (unsigned long)start_secondary;
@@ -931,9 +878,7 @@
 				inquire_remote_apic(apicid);
 		}
 	}
-#ifdef CONFIG_X86_64
-restore_state:
-#endif
+
 	if (boot_error) {
 		/* Try to put things back the way they were before ... */
 		numa_remove_cpu(cpu); /* was set by numa_add_cpu */
@@ -1125,6 +1070,7 @@
 		printk(KERN_ERR "... forcing use of dummy APIC emulation."
 				"(tell your hw vendor)\n");
 		smpboot_clear_io_apic();
+		disable_ioapic_setup();
 		return -1;
 	}
 
diff --git a/arch/x86/kernel/smpcommon.c b/arch/x86/kernel/smpcommon.c
index 397e309..add36b4 100644
--- a/arch/x86/kernel/smpcommon.c
+++ b/arch/x86/kernel/smpcommon.c
@@ -3,11 +3,16 @@
  */
 #include <linux/module.h>
 #include <asm/smp.h>
+#include <asm/sections.h>
 
-#ifdef CONFIG_X86_32
+#ifdef CONFIG_X86_64
+DEFINE_PER_CPU(unsigned long, this_cpu_off) = (unsigned long)__per_cpu_load;
+#else
 DEFINE_PER_CPU(unsigned long, this_cpu_off);
+#endif
 EXPORT_PER_CPU_SYMBOL(this_cpu_off);
 
+#ifdef CONFIG_X86_32
 /*
  * Initialize the CPU's GDT.  This is either the boot CPU doing itself
  * (still using the master per-cpu area), or a CPU doing it for a
@@ -23,8 +28,5 @@
 
 	write_gdt_entry(get_cpu_gdt_table(cpu),
 			GDT_ENTRY_PERCPU, &gdt, DESCTYPE_S);
-
-	per_cpu(this_cpu_off, cpu) = __per_cpu_offset[cpu];
-	per_cpu(cpu_number, cpu) = cpu;
 }
 #endif
diff --git a/arch/x86/kernel/tlb_32.c b/arch/x86/kernel/tlb_32.c
deleted file mode 100644
index ce50546..0000000
--- a/arch/x86/kernel/tlb_32.c
+++ /dev/null
@@ -1,256 +0,0 @@
-#include <linux/spinlock.h>
-#include <linux/cpu.h>
-#include <linux/interrupt.h>
-
-#include <asm/tlbflush.h>
-
-DEFINE_PER_CPU(struct tlb_state, cpu_tlbstate)
-			____cacheline_aligned = { &init_mm, 0, };
-
-/* must come after the send_IPI functions above for inlining */
-#include <mach_ipi.h>
-
-/*
- *	Smarter SMP flushing macros.
- *		c/o Linus Torvalds.
- *
- *	These mean you can really definitely utterly forget about
- *	writing to user space from interrupts. (Its not allowed anyway).
- *
- *	Optimizations Manfred Spraul <manfred@colorfullife.com>
- */
-
-static cpumask_t flush_cpumask;
-static struct mm_struct *flush_mm;
-static unsigned long flush_va;
-static DEFINE_SPINLOCK(tlbstate_lock);
-
-/*
- * We cannot call mmdrop() because we are in interrupt context,
- * instead update mm->cpu_vm_mask.
- *
- * We need to reload %cr3 since the page tables may be going
- * away from under us..
- */
-void leave_mm(int cpu)
-{
-	BUG_ON(x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_OK);
-	cpu_clear(cpu, x86_read_percpu(cpu_tlbstate.active_mm)->cpu_vm_mask);
-	load_cr3(swapper_pg_dir);
-}
-EXPORT_SYMBOL_GPL(leave_mm);
-
-/*
- *
- * The flush IPI assumes that a thread switch happens in this order:
- * [cpu0: the cpu that switches]
- * 1) switch_mm() either 1a) or 1b)
- * 1a) thread switch to a different mm
- * 1a1) cpu_clear(cpu, old_mm->cpu_vm_mask);
- * 	Stop ipi delivery for the old mm. This is not synchronized with
- * 	the other cpus, but smp_invalidate_interrupt ignore flush ipis
- * 	for the wrong mm, and in the worst case we perform a superfluous
- * 	tlb flush.
- * 1a2) set cpu_tlbstate to TLBSTATE_OK
- * 	Now the smp_invalidate_interrupt won't call leave_mm if cpu0
- *	was in lazy tlb mode.
- * 1a3) update cpu_tlbstate[].active_mm
- * 	Now cpu0 accepts tlb flushes for the new mm.
- * 1a4) cpu_set(cpu, new_mm->cpu_vm_mask);
- * 	Now the other cpus will send tlb flush ipis.
- * 1a4) change cr3.
- * 1b) thread switch without mm change
- *	cpu_tlbstate[].active_mm is correct, cpu0 already handles
- *	flush ipis.
- * 1b1) set cpu_tlbstate to TLBSTATE_OK
- * 1b2) test_and_set the cpu bit in cpu_vm_mask.
- * 	Atomically set the bit [other cpus will start sending flush ipis],
- * 	and test the bit.
- * 1b3) if the bit was 0: leave_mm was called, flush the tlb.
- * 2) switch %%esp, ie current
- *
- * The interrupt must handle 2 special cases:
- * - cr3 is changed before %%esp, ie. it cannot use current->{active_,}mm.
- * - the cpu performs speculative tlb reads, i.e. even if the cpu only
- *   runs in kernel space, the cpu could load tlb entries for user space
- *   pages.
- *
- * The good news is that cpu_tlbstate is local to each cpu, no
- * write/read ordering problems.
- */
-
-/*
- * TLB flush IPI:
- *
- * 1) Flush the tlb entries if the cpu uses the mm that's being flushed.
- * 2) Leave the mm if we are in the lazy tlb mode.
- */
-
-void smp_invalidate_interrupt(struct pt_regs *regs)
-{
-	unsigned long cpu;
-
-	cpu = get_cpu();
-
-	if (!cpu_isset(cpu, flush_cpumask))
-		goto out;
-		/*
-		 * This was a BUG() but until someone can quote me the
-		 * line from the intel manual that guarantees an IPI to
-		 * multiple CPUs is retried _only_ on the erroring CPUs
-		 * its staying as a return
-		 *
-		 * BUG();
-		 */
-
-	if (flush_mm == x86_read_percpu(cpu_tlbstate.active_mm)) {
-		if (x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_OK) {
-			if (flush_va == TLB_FLUSH_ALL)
-				local_flush_tlb();
-			else
-				__flush_tlb_one(flush_va);
-		} else
-			leave_mm(cpu);
-	}
-	ack_APIC_irq();
-	smp_mb__before_clear_bit();
-	cpu_clear(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)
-{
-	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(!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
-	 * MM hot path, but we'll see how contended it is.
-	 * AK: x86-64 has a faster method that could be ported.
-	 */
-	spin_lock(&tlbstate_lock);
-
-	flush_mm = mm;
-	flush_va = va;
-	cpus_or(flush_cpumask, cpumask, flush_cpumask);
-
-	/*
-	 * Make the above memory operations globally visible before
-	 * sending the IPI.
-	 */
-	smp_mb();
-	/*
-	 * We have to send the IPI only to
-	 * CPUs affected.
-	 */
-	send_IPI_mask(&cpumask, INVALIDATE_TLB_VECTOR);
-
-	while (!cpus_empty(flush_cpumask))
-		/* nothing. lockup detection does not belong here */
-		cpu_relax();
-
-	flush_mm = NULL;
-	flush_va = 0;
-	spin_unlock(&tlbstate_lock);
-}
-
-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);
-	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)
-			local_flush_tlb();
-		else
-			leave_mm(smp_processor_id());
-	}
-	if (!cpus_empty(cpu_mask))
-		flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL);
-
-	preempt_enable();
-}
-
-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)
-			__flush_tlb_one(va);
-		 else
-			leave_mm(smp_processor_id());
-	}
-
-	if (!cpus_empty(cpu_mask))
-		flush_tlb_others(cpu_mask, mm, va);
-
-	preempt_enable();
-}
-EXPORT_SYMBOL(flush_tlb_page);
-
-static void do_flush_tlb_all(void *info)
-{
-	unsigned long cpu = smp_processor_id();
-
-	__flush_tlb_all();
-	if (x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_LAZY)
-		leave_mm(cpu);
-}
-
-void flush_tlb_all(void)
-{
-	on_each_cpu(do_flush_tlb_all, NULL, 1);
-}
-
-void reset_lazy_tlbstate(void)
-{
-	int cpu = raw_smp_processor_id();
-
-	per_cpu(cpu_tlbstate, cpu).state = 0;
-	per_cpu(cpu_tlbstate, cpu).active_mm = &init_mm;
-}
-
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index f885023..aae15dd 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 
 #include <asm/mmu_context.h>
+#include <asm/uv/uv.h>
 #include <asm/uv/uv_mmrs.h>
 #include <asm/uv/uv_hub.h>
 #include <asm/uv/uv_bau.h>
@@ -209,14 +210,15 @@
  *
  * Send a broadcast and wait for a broadcast message to complete.
  *
- * The cpumaskp mask contains the cpus the broadcast was sent to.
+ * The flush_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 NULL if all remote flushing was done. The mask is zeroed.
+ * Returns @flush_mask 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)
+const struct cpumask *uv_flush_send_and_wait(int cpu, int this_blade,
+					     struct bau_desc *bau_desc,
+					     struct cpumask *flush_mask)
 {
 	int completion_status = 0;
 	int right_shift;
@@ -263,59 +265,69 @@
 	 * 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, flush_mask) {
 		blade = uv_cpu_to_blade_id(bit);
 		if (blade == this_blade)
 			continue;
-		cpu_clear(bit, *cpumaskp);
+		cpumask_clear_cpu(bit, flush_mask);
 	}
-	if (!cpus_empty(*cpumaskp))
-		return 0;
-	return 1;
+	if (!cpumask_empty(flush_mask))
+		return flush_mask;
+	return NULL;
 }
 
 /**
  * uv_flush_tlb_others - globally purge translation cache of a virtual
  * address or all TLB's
- * @cpumaskp: mask of all cpu's in which the address is to be removed
+ * @cpumask: mask of all cpu's in which the address is to be removed
  * @mm: mm_struct containing virtual address range
  * @va: virtual address to be removed (or TLB_FLUSH_ALL for all TLB's on cpu)
+ * @cpu: the current cpu
  *
  * This is the entry point for initiating any UV global TLB shootdown.
  *
  * Purges the translation caches of all specified processors of the given
  * virtual address, or purges all TLB's on specified processors.
  *
- * The caller has derived the cpumaskp from the mm_struct and has subtracted
- * the local cpu from the mask.  This function is called only if there
- * are bits set in the mask. (e.g. flush_tlb_page())
+ * The caller has derived the cpumask from the mm_struct.  This function
+ * is called only if there are bits set in the mask. (e.g. flush_tlb_page())
  *
- * The cpumaskp is converted into a nodemask of the nodes containing
+ * The cpumask is converted into a nodemask of the nodes containing
  * the cpus.
  *
- * Returns 1 if all remote flushing was done.
- * Returns 0 if some remote flushing remains to be done.
+ * Note that this function should be called with preemption disabled.
+ *
+ * Returns NULL if all remote flushing was done.
+ * Returns pointer to cpumask if some remote flushing remains to be
+ * done.  The returned pointer is valid till preemption is re-enabled.
  */
-int uv_flush_tlb_others(cpumask_t *cpumaskp, struct mm_struct *mm,
-			unsigned long va)
+const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
+					  struct mm_struct *mm,
+					  unsigned long va, unsigned int cpu)
 {
+	static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask);
+	struct cpumask *flush_mask = &__get_cpu_var(flush_tlb_mask);
 	int i;
 	int bit;
 	int blade;
-	int cpu;
+	int uv_cpu;
 	int this_blade;
 	int locals = 0;
 	struct bau_desc *bau_desc;
 
-	cpu = uv_blade_processor_id();
+	WARN_ON(!in_atomic());
+
+	cpumask_andnot(flush_mask, cpumask, cpumask_of(cpu));
+
+	uv_cpu = uv_blade_processor_id();
 	this_blade = uv_numa_blade_id();
 	bau_desc = __get_cpu_var(bau_control).descriptor_base;
-	bau_desc += UV_ITEMS_PER_DESCRIPTOR * cpu;
+	bau_desc += UV_ITEMS_PER_DESCRIPTOR * uv_cpu;
 
 	bau_nodes_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE);
 
 	i = 0;
-	for_each_cpu_mask(bit, *cpumaskp) {
+	for_each_cpu(bit, flush_mask) {
 		blade = uv_cpu_to_blade_id(bit);
 		BUG_ON(blade > (UV_DISTRIBUTION_SIZE - 1));
 		if (blade == this_blade) {
@@ -330,17 +342,17 @@
 		 * no off_node flushing; return status for local node
 		 */
 		if (locals)
-			return 0;
+			return flush_mask;
 		else
-			return 1;
+			return NULL;
 	}
 	__get_cpu_var(ptcstats).requestor++;
 	__get_cpu_var(ptcstats).ntargeted += i;
 
 	bau_desc->payload.address = va;
-	bau_desc->payload.sending_cpu = smp_processor_id();
+	bau_desc->payload.sending_cpu = cpu;
 
-	return uv_flush_send_and_wait(cpu, this_blade, bau_desc, cpumaskp);
+	return uv_flush_send_and_wait(uv_cpu, this_blade, bau_desc, flush_mask);
 }
 
 /*
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 98c2d055..ed5aee5 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -59,7 +59,6 @@
 #ifdef CONFIG_X86_64
 #include <asm/pgalloc.h>
 #include <asm/proto.h>
-#include <asm/pda.h>
 #else
 #include <asm/processor-flags.h>
 #include <asm/arch_hooks.h>
diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S
index 82c6755..3eba7f7 100644
--- a/arch/x86/kernel/vmlinux_32.lds.S
+++ b/arch/x86/kernel/vmlinux_32.lds.S
@@ -178,14 +178,7 @@
 	__initramfs_end = .;
   }
 #endif
-  . = ALIGN(PAGE_SIZE);
-  .data.percpu  : AT(ADDR(.data.percpu) - LOAD_OFFSET) {
-	__per_cpu_start = .;
-	*(.data.percpu.page_aligned)
-	*(.data.percpu)
-	*(.data.percpu.shared_aligned)
-	__per_cpu_end = .;
-  }
+  PERCPU(PAGE_SIZE)
   . = ALIGN(PAGE_SIZE);
   /* freed after init ends here */
 
diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S
index 1a614c0..c974099 100644
--- a/arch/x86/kernel/vmlinux_64.lds.S
+++ b/arch/x86/kernel/vmlinux_64.lds.S
@@ -5,6 +5,7 @@
 #define LOAD_OFFSET __START_KERNEL_map
 
 #include <asm-generic/vmlinux.lds.h>
+#include <asm/asm-offsets.h>
 #include <asm/page.h>
 
 #undef i386	/* in case the preprocessor is a 32bit one */
@@ -13,12 +14,14 @@
 OUTPUT_ARCH(i386:x86-64)
 ENTRY(phys_startup_64)
 jiffies_64 = jiffies;
-_proxy_pda = 1;
 PHDRS {
 	text PT_LOAD FLAGS(5);	/* R_E */
 	data PT_LOAD FLAGS(7);	/* RWE */
 	user PT_LOAD FLAGS(7);	/* RWE */
 	data.init PT_LOAD FLAGS(7);	/* RWE */
+#ifdef CONFIG_SMP
+	percpu PT_LOAD FLAGS(7);	/* RWE */
+#endif
 	note PT_NOTE FLAGS(0);	/* ___ */
 }
 SECTIONS
@@ -208,14 +211,28 @@
   __initramfs_end = .;
 #endif
 
+#ifdef CONFIG_SMP
+  /*
+   * percpu offsets are zero-based on SMP.  PERCPU_VADDR() changes the
+   * output PHDR, so the next output section - __data_nosave - should
+   * switch it back to data.init.  Also, pda should be at the head of
+   * percpu area.  Preallocate it and define the percpu offset symbol
+   * so that it can be accessed as a percpu variable.
+   */
+  . = ALIGN(PAGE_SIZE);
+  PERCPU_VADDR(0, :percpu)
+#else
   PERCPU(PAGE_SIZE)
+#endif
 
   . = ALIGN(PAGE_SIZE);
   __init_end = .;
 
   . = ALIGN(PAGE_SIZE);
   __nosave_begin = .;
-  .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) { *(.data.nosave) }
+  .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
+      *(.data.nosave)
+  } :data.init	/* switch back to data.init, see PERCPU_VADDR() above */
   . = ALIGN(PAGE_SIZE);
   __nosave_end = .;
 
@@ -244,3 +261,8 @@
  */
 ASSERT((_end - _text <= KERNEL_IMAGE_SIZE),
 	"kernel image bigger than KERNEL_IMAGE_SIZE")
+
+#ifdef CONFIG_SMP
+ASSERT((per_cpu__irq_stack_union == 0),
+        "irq_stack_union is not at start of per-cpu area");
+#endif
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index 695e426..3909e3b 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -58,5 +58,3 @@
 EXPORT_SYMBOL(empty_zero_page);
 EXPORT_SYMBOL(init_level4_pgt);
 EXPORT_SYMBOL(load_gs_index);
-
-EXPORT_SYMBOL(_proxy_pda);
diff --git a/arch/x86/mach-voyager/setup.c b/arch/x86/mach-voyager/setup.c
index a580b95..0ade625 100644
--- a/arch/x86/mach-voyager/setup.c
+++ b/arch/x86/mach-voyager/setup.c
@@ -9,6 +9,7 @@
 #include <asm/e820.h>
 #include <asm/io.h>
 #include <asm/setup.h>
+#include <asm/cpu.h>
 
 void __init pre_intr_init_hook(void)
 {
diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c
index 9840b7e..96f15b09 100644
--- a/arch/x86/mach-voyager/voyager_smp.c
+++ b/arch/x86/mach-voyager/voyager_smp.c
@@ -402,7 +402,7 @@
 	     VOYAGER_SUS_IN_CONTROL_PORT);
 
 	current_thread_info()->cpu = boot_cpu_id;
-	x86_write_percpu(cpu_number, boot_cpu_id);
+	percpu_write(cpu_number, boot_cpu_id);
 }
 
 /*
@@ -531,6 +531,7 @@
 	stack_start.sp = (void *)idle->thread.sp;
 
 	init_gdt(cpu);
+	per_cpu(this_cpu_off, cpu) = __per_cpu_offset[cpu];
 	per_cpu(current_task, cpu) = idle;
 	early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
 	irq_ctx_init(cpu);
@@ -1748,6 +1749,7 @@
 static void __cpuinit voyager_smp_prepare_boot_cpu(void)
 {
 	init_gdt(smp_processor_id());
+	per_cpu(this_cpu_off, cpu) = __per_cpu_offset[cpu];
 	switch_to_new_gdt();
 
 	cpu_set(smp_processor_id(), cpu_online_map);
@@ -1780,7 +1782,7 @@
 void __init smp_setup_processor_id(void)
 {
 	current_thread_info()->cpu = hard_smp_processor_id();
-	x86_write_percpu(cpu_number, hard_smp_processor_id());
+	percpu_write(cpu_number, hard_smp_processor_id());
 }
 
 static void voyager_send_call_func(cpumask_t callmask)
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index d8cc96a2..9f051572 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,6 +1,8 @@
 obj-y	:=  init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
 	    pat.o pgtable.o gup.o
 
+obj-$(CONFIG_X86_SMP)		+= tlb.o
+
 obj-$(CONFIG_X86_32)		+= pgtable_32.o iomap_32.o
 
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 033292d..65709a6 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -26,6 +26,7 @@
 #include <linux/kprobes.h>
 #include <linux/uaccess.h>
 #include <linux/kdebug.h>
+#include <linux/magic.h>
 
 #include <asm/system.h>
 #include <asm/desc.h>
@@ -433,6 +434,8 @@
 			unsigned long error_code, unsigned long address)
 {
 	struct task_struct *tsk = current;
+	unsigned long *stackend;
+
 #ifdef CONFIG_X86_64
 	unsigned long flags;
 	int sig;
@@ -469,6 +472,10 @@
 
 	show_fault_oops(regs, error_code, address);
 
+ 	stackend = end_of_stack(tsk);
+	if (*stackend != STACK_END_MAGIC)
+		printk(KERN_ALERT "Thread overran stack, or stack corrupted\n");
+
 	tsk->thread.cr2 = address;
 	tsk->thread.trap_no = 14;
 	tsk->thread.error_code = error_code;
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 88f1b10..4a6989e 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -49,7 +49,6 @@
 #include <asm/paravirt.h>
 #include <asm/setup.h>
 #include <asm/cacheflush.h>
-#include <asm/smp.h>
 
 unsigned int __VMALLOC_RESERVE = 128 << 20;
 
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 8b08fb9..c948851 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -333,11 +333,20 @@
 					      req_type & _PAGE_CACHE_MASK);
 	}
 
-	is_range_ram = pagerange_is_ram(start, end);
-	if (is_range_ram == 1)
-		return reserve_ram_pages_type(start, end, req_type, new_type);
-	else if (is_range_ram < 0)
-		return -EINVAL;
+	/*
+	 * For legacy reasons, some parts of the physical address range in the
+	 * legacy 1MB region is treated as non-RAM (even when listed as RAM in
+	 * the e820 tables).  So we will track the memory attributes of this
+	 * legacy 1MB region using the linear memtype_list always.
+	 */
+	if (end >= ISA_END_ADDRESS) {
+		is_range_ram = pagerange_is_ram(start, end);
+		if (is_range_ram == 1)
+			return reserve_ram_pages_type(start, end, req_type,
+						      new_type);
+		else if (is_range_ram < 0)
+			return -EINVAL;
+	}
 
 	new  = kmalloc(sizeof(struct memtype), GFP_KERNEL);
 	if (!new)
@@ -437,11 +446,19 @@
 	if (is_ISA_range(start, end - 1))
 		return 0;
 
-	is_range_ram = pagerange_is_ram(start, end);
-	if (is_range_ram == 1)
-		return free_ram_pages_type(start, end);
-	else if (is_range_ram < 0)
-		return -EINVAL;
+	/*
+	 * For legacy reasons, some parts of the physical address range in the
+	 * legacy 1MB region is treated as non-RAM (even when listed as RAM in
+	 * the e820 tables).  So we will track the memory attributes of this
+	 * legacy 1MB region using the linear memtype_list always.
+	 */
+	if (end >= ISA_END_ADDRESS) {
+		is_range_ram = pagerange_is_ram(start, end);
+		if (is_range_ram == 1)
+			return free_ram_pages_type(start, end);
+		else if (is_range_ram < 0)
+			return -EINVAL;
+	}
 
 	spin_lock(&memtype_lock);
 	list_for_each_entry(entry, &memtype_list, nd) {
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 09737c8..15df1bae 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -21,6 +21,7 @@
 #include <asm/numa.h>
 #include <asm/e820.h>
 #include <asm/genapic.h>
+#include <asm/uv/uv.h>
 
 int acpi_numa __initdata;
 
diff --git a/arch/x86/kernel/tlb_64.c b/arch/x86/mm/tlb.c
similarity index 71%
rename from arch/x86/kernel/tlb_64.c
rename to arch/x86/mm/tlb.c
index 8cfea5d..72a6d4e 100644
--- a/arch/x86/kernel/tlb_64.c
+++ b/arch/x86/mm/tlb.c
@@ -1,22 +1,18 @@
 #include <linux/init.h>
 
 #include <linux/mm.h>
-#include <linux/delay.h>
 #include <linux/spinlock.h>
 #include <linux/smp.h>
-#include <linux/kernel_stat.h>
-#include <linux/mc146818rtc.h>
 #include <linux/interrupt.h>
+#include <linux/module.h>
 
-#include <asm/mtrr.h>
-#include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
-#include <asm/proto.h>
-#include <asm/apicdef.h>
-#include <asm/idle.h>
-#include <asm/uv/uv_hub.h>
-#include <asm/uv/uv_bau.h>
+#include <asm/apic.h>
+#include <asm/uv/uv.h>
+
+DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate)
+			= { &init_mm, 0, };
 
 #include <mach_ipi.h>
 /*
@@ -43,10 +39,10 @@
 
 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[CONFIG_X86_INTERNODE_CACHE_BYTES];
 } ____cacheline_internodealigned_in_smp;
@@ -62,9 +58,9 @@
  */
 void leave_mm(int cpu)
 {
-	if (read_pda(mmu_state) == TLBSTATE_OK)
+	if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
 		BUG();
-	cpu_clear(cpu, read_pda(active_mm)->cpu_vm_mask);
+	cpu_clear(cpu, percpu_read(cpu_tlbstate.active_mm)->cpu_vm_mask);
 	load_cr3(swapper_pg_dir);
 }
 EXPORT_SYMBOL_GPL(leave_mm);
@@ -117,10 +113,20 @@
  * Interrupts are disabled.
  */
 
-asmlinkage void smp_invalidate_interrupt(struct pt_regs *regs)
+/*
+ * FIXME: use of asmlinkage is not consistent.  On x86_64 it's noop
+ * but still used for documentation purpose but the usage is slightly
+ * inconsistent.  On x86_32, asmlinkage is regparm(0) but interrupt
+ * entry calls in with the first parameter in %eax.  Maybe define
+ * intrlinkage?
+ */
+#ifdef CONFIG_X86_64
+asmlinkage
+#endif
+void smp_invalidate_interrupt(struct pt_regs *regs)
 {
-	int cpu;
-	int sender;
+	unsigned int cpu;
+	unsigned int sender;
 	union smp_flush_state *f;
 
 	cpu = smp_processor_id();
@@ -131,7 +137,7 @@
 	sender = ~regs->orig_ax - INVALIDATE_TLB_VECTOR_START;
 	f = &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
@@ -142,8 +148,8 @@
 		 * BUG();
 		 */
 
-	if (f->flush_mm == read_pda(active_mm)) {
-		if (read_pda(mmu_state) == TLBSTATE_OK) {
+	if (f->flush_mm == percpu_read(cpu_tlbstate.active_mm)) {
+		if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
 			if (f->flush_va == TLB_FLUSH_ALL)
 				local_flush_tlb();
 			else
@@ -153,19 +159,17 @@
 	}
 out:
 	ack_APIC_irq();
-	cpu_clear(cpu, f->flush_cpumask);
+	smp_mb__before_clear_bit();
+	cpumask_clear_cpu(cpu, to_cpumask(f->flush_cpumask));
+	smp_mb__after_clear_bit();
 	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;
+	unsigned 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 +184,8 @@
 
 	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
@@ -191,9 +196,10 @@
 	 * 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;
@@ -201,6 +207,22 @@
 	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()) {
+		unsigned int cpu;
+
+		cpu = get_cpu();
+		cpumask = uv_flush_tlb_others(cpumask, mm, va, cpu);
+		if (cpumask)
+			flush_tlb_others_ipi(cpumask, mm, va);
+		put_cpu();
+		return;
+	}
+	flush_tlb_others_ipi(cpumask, mm, va);
+}
+
 static int __cpuinit init_smp_flush(void)
 {
 	int i;
@@ -215,25 +237,18 @@
 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 +256,8 @@
 		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 +265,8 @@
 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 +275,8 @@
 			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();
 }
@@ -274,7 +286,7 @@
 	unsigned long cpu = smp_processor_id();
 
 	__flush_tlb_all();
-	if (read_pda(mmu_state) == TLBSTATE_LAZY)
+	if (percpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY)
 		leave_mm(cpu);
 }
 
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index bea2152..bef941f 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -634,35 +634,27 @@
 	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 @@
 
 	MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF);
 
+issue:
 	xen_mc_issue(PARAVIRT_LAZY_MMU);
 }
 
@@ -702,17 +695,17 @@
 
 static void xen_write_cr2(unsigned long cr2)
 {
-	x86_read_percpu(xen_vcpu)->arch.cr2 = cr2;
+	percpu_read(xen_vcpu)->arch.cr2 = cr2;
 }
 
 static unsigned long xen_read_cr2(void)
 {
-	return x86_read_percpu(xen_vcpu)->arch.cr2;
+	return percpu_read(xen_vcpu)->arch.cr2;
 }
 
 static unsigned long xen_read_cr2_direct(void)
 {
-	return x86_read_percpu(xen_vcpu_info.arch.cr2);
+	return percpu_read(xen_vcpu_info.arch.cr2);
 }
 
 static void xen_write_cr4(unsigned long cr4)
@@ -725,12 +718,12 @@
 
 static unsigned long xen_read_cr3(void)
 {
-	return x86_read_percpu(xen_cr3);
+	return percpu_read(xen_cr3);
 }
 
 static void set_current_cr3(void *v)
 {
-	x86_write_percpu(xen_current_cr3, (unsigned long)v);
+	percpu_write(xen_current_cr3, (unsigned long)v);
 }
 
 static void __xen_write_cr3(bool kernel, unsigned long cr3)
@@ -755,7 +748,7 @@
 	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
 
 	if (kernel) {
-		x86_write_percpu(xen_cr3, cr3);
+		percpu_write(xen_cr3, cr3);
 
 		/* Update xen_current_cr3 once the batch has actually
 		   been submitted. */
@@ -771,7 +764,7 @@
 
 	/* Update while interrupts are disabled, so its atomic with
 	   respect to ipis */
-	x86_write_percpu(xen_cr3, cr3);
+	percpu_write(xen_cr3, cr3);
 
 	__xen_write_cr3(true, cr3);
 
@@ -1652,7 +1645,6 @@
 #ifdef CONFIG_X86_64
 	/* Disable until direct per-cpu data access. */
 	have_vcpu_info_placement = 0;
-	x86_64_init_pda();
 #endif
 
 	xen_smp_init();
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index bb04260..2e82714 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -39,7 +39,7 @@
 	struct vcpu_info *vcpu;
 	unsigned long flags;
 
-	vcpu = x86_read_percpu(xen_vcpu);
+	vcpu = percpu_read(xen_vcpu);
 
 	/* flag has opposite sense of mask */
 	flags = !vcpu->evtchn_upcall_mask;
@@ -62,7 +62,7 @@
 	   make sure we're don't switch CPUs between getting the vcpu
 	   pointer and updating the mask. */
 	preempt_disable();
-	vcpu = x86_read_percpu(xen_vcpu);
+	vcpu = percpu_read(xen_vcpu);
 	vcpu->evtchn_upcall_mask = flags;
 	preempt_enable_no_resched();
 
@@ -83,7 +83,7 @@
 	   make sure we're don't switch CPUs between getting the vcpu
 	   pointer and updating the mask. */
 	preempt_disable();
-	x86_read_percpu(xen_vcpu)->evtchn_upcall_mask = 1;
+	percpu_read(xen_vcpu)->evtchn_upcall_mask = 1;
 	preempt_enable_no_resched();
 }
 
@@ -96,7 +96,7 @@
 	   the caller is confused and is trying to re-enable interrupts
 	   on an indeterminate processor. */
 
-	vcpu = x86_read_percpu(xen_vcpu);
+	vcpu = percpu_read(xen_vcpu);
 	vcpu->evtchn_upcall_mask = 0;
 
 	/* Doesn't matter if we get preempted here, because any
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 503c240..98cb986 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1063,18 +1063,14 @@
 	struct mm_struct *mm = info;
 	struct mm_struct *active_mm;
 
-#ifdef CONFIG_X86_64
-	active_mm = read_pda(active_mm);
-#else
-	active_mm = __get_cpu_var(cpu_tlbstate).active_mm;
-#endif
+	active_mm = percpu_read(cpu_tlbstate.active_mm);
 
 	if (active_mm == mm)
 		leave_mm(smp_processor_id());
 
 	/* If this cpu still has a stale cr3 reference, then make sure
 	   it has been flushed. */
-	if (x86_read_percpu(xen_current_cr3) == __pa(mm->pgd)) {
+	if (percpu_read(xen_current_cr3) == __pa(mm->pgd)) {
 		load_cr3(swapper_pg_dir);
 		arch_flush_lazy_cpu_mode();
 	}
diff --git a/arch/x86/xen/multicalls.h b/arch/x86/xen/multicalls.h
index 8589382..e786fa7 100644
--- a/arch/x86/xen/multicalls.h
+++ b/arch/x86/xen/multicalls.h
@@ -39,7 +39,7 @@
 		xen_mc_flush();
 
 	/* restore flags saved in xen_mc_batch */
-	local_irq_restore(x86_read_percpu(xen_mc_irq_flags));
+	local_irq_restore(percpu_read(xen_mc_irq_flags));
 }
 
 /* Set up a callback to be called when the current batch is flushed */
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index c44e206..72c2eb9 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -50,11 +50,7 @@
  */
 static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id)
 {
-#ifdef CONFIG_X86_32
-	__get_cpu_var(irq_stat).irq_resched_count++;
-#else
-	add_pda(irq_resched_count, 1);
-#endif
+	inc_irq_stat(irq_resched_count);
 
 	return IRQ_HANDLED;
 }
@@ -78,7 +74,7 @@
 	xen_setup_cpu_clockevents();
 
 	cpu_set(cpu, cpu_online_map);
-	x86_write_percpu(cpu_state, CPU_ONLINE);
+	percpu_write(cpu_state, CPU_ONLINE);
 	wmb();
 
 	/* We can take interrupts now: we're officially "up". */
@@ -283,22 +279,11 @@
 	struct task_struct *idle = idle_task(cpu);
 	int rc;
 
-#ifdef CONFIG_X86_64
-	/* Allocate node local memory for AP pdas */
-	WARN_ON(cpu == 0);
-	if (cpu > 0) {
-		rc = get_local_pda(cpu);
-		if (rc)
-			return rc;
-	}
-#endif
-
+	per_cpu(current_task, cpu) = idle;
 #ifdef CONFIG_X86_32
 	init_gdt(cpu);
-	per_cpu(current_task, cpu) = idle;
 	irq_ctx_init(cpu);
 #else
-	cpu_pda(cpu)->pcurrent = idle;
 	clear_tsk_thread_flag(idle, TIF_FORK);
 #endif
 	xen_setup_timer(cpu);
@@ -445,11 +430,7 @@
 {
 	irq_enter();
 	generic_smp_call_function_interrupt();
-#ifdef CONFIG_X86_32
-	__get_cpu_var(irq_stat).irq_call_count++;
-#else
-	add_pda(irq_call_count, 1);
-#endif
+	inc_irq_stat(irq_call_count);
 	irq_exit();
 
 	return IRQ_HANDLED;
@@ -459,11 +440,7 @@
 {
 	irq_enter();
 	generic_smp_call_function_single_interrupt();
-#ifdef CONFIG_X86_32
-	__get_cpu_var(irq_stat).irq_call_count++;
-#else
-	add_pda(irq_call_count, 1);
-#endif
+	inc_irq_stat(irq_call_count);
 	irq_exit();
 
 	return IRQ_HANDLED;
diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S
index 05794c5..d6fc51f 100644
--- a/arch/x86/xen/xen-asm_64.S
+++ b/arch/x86/xen/xen-asm_64.S
@@ -17,6 +17,7 @@
 #include <asm/processor-flags.h>
 #include <asm/errno.h>
 #include <asm/segment.h>
+#include <asm/percpu.h>
 
 #include <xen/interface/xen.h>
 
@@ -28,12 +29,10 @@
 
 #if 1
 /*
-	x86-64 does not yet support direct access to percpu variables
-	via a segment override, so we just need to make sure this code
-	never gets used
+	FIXME: x86_64 now can support direct access to percpu variables
+	via a segment override.  Update xen accordingly.
  */
 #define BUG			ud2a
-#define PER_CPU_VAR(var, off)	0xdeadbeef
 #endif
 
 /*
@@ -45,14 +44,14 @@
 	BUG
 
 	/* Unmask events */
-	movb $0, PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_mask)
+	movb $0, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
 
 	/* Preempt here doesn't matter because that will deal with
 	   any pending interrupts.  The pending check may end up being
 	   run on the wrong CPU, but that doesn't hurt. */
 
 	/* Test for pending */
-	testb $0xff, PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_pending)
+	testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending
 	jz 1f
 
 2:	call check_events
@@ -69,7 +68,7 @@
 ENTRY(xen_irq_disable_direct)
 	BUG
 
-	movb $1, PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_mask)
+	movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
 ENDPATCH(xen_irq_disable_direct)
 	ret
 	ENDPROC(xen_irq_disable_direct)
@@ -87,7 +86,7 @@
 ENTRY(xen_save_fl_direct)
 	BUG
 
-	testb $0xff, PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_mask)
+	testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
 	setz %ah
 	addb %ah,%ah
 ENDPATCH(xen_save_fl_direct)
@@ -107,13 +106,13 @@
 	BUG
 
 	testb $X86_EFLAGS_IF>>8, %ah
-	setz PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_mask)
+	setz PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
 	/* Preempt here doesn't matter because that will deal with
 	   any pending interrupts.  The pending check may end up being
 	   run on the wrong CPU, but that doesn't hurt. */
 
 	/* check for unmasked and pending */
-	cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_pending)
+	cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending
 	jz 1f
 2:	call check_events
 1:
@@ -195,11 +194,11 @@
 ENTRY(xen_sysret64)
 	/* We're already on the usermode stack at this point, but still
 	   with the kernel gs, so we can easily switch back */
-	movq %rsp, %gs:pda_oldrsp
-	movq %gs:pda_kernelstack,%rsp
+	movq %rsp, PER_CPU_VAR(old_rsp)
+	movq PER_CPU_VAR(kernel_stack),%rsp
 
 	pushq $__USER_DS
-	pushq %gs:pda_oldrsp
+	pushq PER_CPU_VAR(old_rsp)
 	pushq %r11
 	pushq $__USER_CS
 	pushq %rcx
@@ -212,11 +211,11 @@
 ENTRY(xen_sysret32)
 	/* We're already on the usermode stack at this point, but still
 	   with the kernel gs, so we can easily switch back */
-	movq %rsp, %gs:pda_oldrsp
-	movq %gs:pda_kernelstack, %rsp
+	movq %rsp, PER_CPU_VAR(old_rsp)
+	movq PER_CPU_VAR(kernel_stack), %rsp
 
 	pushq $__USER32_DS
-	pushq %gs:pda_oldrsp
+	pushq PER_CPU_VAR(old_rsp)
 	pushq %r11
 	pushq $__USER32_CS
 	pushq %rcx
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 719ee5c..5b257a57 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -107,7 +107,7 @@
 /*
  * 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
index a778fb5..bf6b132 100644
--- 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 @@
 	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 @@
 			   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 @@
 				  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_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 @@
 				  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_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/firmware/dcdbas.c b/drivers/firmware/dcdbas.c
index 777fba4..3009e01 100644
--- a/drivers/firmware/dcdbas.c
+++ b/drivers/firmware/dcdbas.c
@@ -244,7 +244,7 @@
  */
 int dcdbas_smi_request(struct smi_cmd *smi_cmd)
 {
-	cpumask_t old_mask;
+	cpumask_var_t old_mask;
 	int ret = 0;
 
 	if (smi_cmd->magic != SMI_CMD_MAGIC) {
@@ -254,8 +254,11 @@
 	}
 
 	/* SMI requires CPU 0 */
-	old_mask = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, &cpumask_of_cpu(0));
+	if (!alloc_cpumask_var(&old_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	cpumask_copy(old_mask, &current->cpus_allowed);
+	set_cpus_allowed_ptr(current, cpumask_of(0));
 	if (smp_processor_id() != 0) {
 		dev_dbg(&dcdbas_pdev->dev, "%s: failed to get CPU 0\n",
 			__func__);
@@ -275,7 +278,8 @@
 	);
 
 out:
-	set_cpus_allowed_ptr(current, &old_mask);
+	set_cpus_allowed_ptr(current, old_mask);
+	free_cpumask_var(old_mask);
 	return ret;
 }
 
diff --git a/drivers/misc/sgi-xp/xpc_main.c b/drivers/misc/sgi-xp/xpc_main.c
index 89218f7..6576170 100644
--- a/drivers/misc/sgi-xp/xpc_main.c
+++ b/drivers/misc/sgi-xp/xpc_main.c
@@ -318,7 +318,7 @@
 
 	/* 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
index 7673fd9..101c00a 100644
--- a/drivers/net/sfc/efx.c
+++ b/drivers/net/sfc/efx.c
@@ -854,20 +854,27 @@
  * 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
index 9da5a4b..c3ea5fa 100644
--- 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 @@
 {
 	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 @@
 	 */
 	process_task_mortuary();
 
-	cpus_clear(marked_cpus);
+	cpumask_clear(marked_cpus);
 }
 
 
@@ -565,6 +565,20 @@
 	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
index 3110732..0ebf5db 100644
--- a/drivers/oprofile/buffer_sync.h
+++ b/drivers/oprofile/buffer_sync.h
@@ -19,4 +19,8 @@
 /* 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
index 3cffce9..ced39f6 100644
--- a/drivers/oprofile/oprof.c
+++ b/drivers/oprofile/oprof.c
@@ -183,6 +183,10 @@
 {
 	int err;
 
+	err = buffer_sync_init();
+	if (err)
+		return err;
+
 	err = oprofile_arch_init(&oprofile_ops);
 
 	if (err < 0 || timer) {
@@ -191,8 +195,10 @@
 	}
 
 	err = oprofilefs_register();
-	if (err)
+	if (err) {
 		oprofile_arch_exit();
+		buffer_sync_cleanup();
+	}
 
 	return err;
 }
@@ -202,6 +208,7 @@
 {
 	oprofilefs_unregister();
 	oprofile_arch_exit();
+	buffer_sync_cleanup();
 }
 
 
diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c
index f78371b..5a57753 100644
--- a/drivers/pci/intr_remapping.c
+++ b/drivers/pci/intr_remapping.c
@@ -6,6 +6,7 @@
 #include <linux/irq.h>
 #include <asm/io_apic.h>
 #include <asm/smp.h>
+#include <asm/cpu.h>
 #include <linux/intel-iommu.h>
 #include "intr_remapping.h"
 
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index eb0dfde..3141e14 100644
--- 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_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 @@
 					   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 @@
 
 	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 @@
 
 	/* 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)
 {
 	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
index 9b91617..e7e83b6 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -100,7 +100,7 @@
 	/* 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/asm-generic/bitops/__ffs.h b/include/asm-generic/bitops/__ffs.h
index 9a3274a..937d7c4 100644
--- a/include/asm-generic/bitops/__ffs.h
+++ b/include/asm-generic/bitops/__ffs.h
@@ -9,7 +9,7 @@
  *
  * Undefined if no bit exists, so code should check against 0 first.
  */
-static inline unsigned long __ffs(unsigned long word)
+static __always_inline unsigned long __ffs(unsigned long word)
 {
 	int num = 0;
 
diff --git a/include/asm-generic/bitops/__fls.h b/include/asm-generic/bitops/__fls.h
index be24465..a60a7cc 100644
--- a/include/asm-generic/bitops/__fls.h
+++ b/include/asm-generic/bitops/__fls.h
@@ -9,7 +9,7 @@
  *
  * Undefined if no set bit exists, so code should check against 0 first.
  */
-static inline unsigned long __fls(unsigned long word)
+static __always_inline unsigned long __fls(unsigned long word)
 {
 	int num = BITS_PER_LONG - 1;
 
diff --git a/include/asm-generic/bitops/fls.h b/include/asm-generic/bitops/fls.h
index 850859b..0576d1f 100644
--- a/include/asm-generic/bitops/fls.h
+++ b/include/asm-generic/bitops/fls.h
@@ -9,7 +9,7 @@
  * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
  */
 
-static inline int fls(int x)
+static __always_inline int fls(int x)
 {
 	int r = 32;
 
diff --git a/include/asm-generic/bitops/fls64.h b/include/asm-generic/bitops/fls64.h
index 86d403f..b097cf8 100644
--- a/include/asm-generic/bitops/fls64.h
+++ b/include/asm-generic/bitops/fls64.h
@@ -15,7 +15,7 @@
  * at position 64.
  */
 #if BITS_PER_LONG == 32
-static inline int fls64(__u64 x)
+static __always_inline int fls64(__u64 x)
 {
 	__u32 h = x >> 32;
 	if (h)
@@ -23,7 +23,7 @@
 	return fls(x);
 }
 #elif BITS_PER_LONG == 64
-static inline int fls64(__u64 x)
+static __always_inline int fls64(__u64 x)
 {
 	if (x == 0)
 		return 0;
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index b0e63c6..00f45ff 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -80,4 +80,56 @@
 #define DECLARE_PER_CPU(type, name) extern PER_CPU_ATTRIBUTES \
 					__typeof__(type) per_cpu_var(name)
 
+/*
+ * Optional methods for optimized non-lvalue per-cpu variable access.
+ *
+ * @var can be a percpu variable or a field of it and its size should
+ * equal char, int or long.  percpu_read() evaluates to a lvalue and
+ * all others to void.
+ *
+ * These operations are guaranteed to be atomic w.r.t. preemption.
+ * The generic versions use plain get/put_cpu_var().  Archs are
+ * encouraged to implement single-instruction alternatives which don't
+ * require preemption protection.
+ */
+#ifndef percpu_read
+# define percpu_read(var)						\
+  ({									\
+	typeof(per_cpu_var(var)) __tmp_var__;				\
+	__tmp_var__ = get_cpu_var(var);					\
+	put_cpu_var(var);						\
+	__tmp_var__;							\
+  })
+#endif
+
+#define __percpu_generic_to_op(var, val, op)				\
+do {									\
+	get_cpu_var(var) op val;					\
+	put_cpu_var(var);						\
+} while (0)
+
+#ifndef percpu_write
+# define percpu_write(var, val)		__percpu_generic_to_op(var, (val), =)
+#endif
+
+#ifndef percpu_add
+# define percpu_add(var, val)		__percpu_generic_to_op(var, (val), +=)
+#endif
+
+#ifndef percpu_sub
+# define percpu_sub(var, val)		__percpu_generic_to_op(var, (val), -=)
+#endif
+
+#ifndef percpu_and
+# define percpu_and(var, val)		__percpu_generic_to_op(var, (val), &=)
+#endif
+
+#ifndef percpu_or
+# define percpu_or(var, val)		__percpu_generic_to_op(var, (val), |=)
+#endif
+
+#ifndef percpu_xor
+# define percpu_xor(var, val)		__percpu_generic_to_op(var, (val), ^=)
+#endif
+
 #endif /* _ASM_GENERIC_PERCPU_H_ */
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index 79a7ff9..4ce48e8 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -9,7 +9,7 @@
 extern char __init_begin[], __init_end[];
 extern char _sinittext[], _einittext[];
 extern char _end[];
-extern char __per_cpu_start[], __per_cpu_end[];
+extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
 extern char __kprobes_text_start[], __kprobes_text_end[];
 extern char __initdata_begin[], __initdata_end[];
 extern char __start_rodata[], __end_rodata[];
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index c61fab1..53e21f3 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -430,12 +430,47 @@
   	*(.initcall7.init)						\
   	*(.initcall7s.init)
 
-#define PERCPU(align)							\
-	. = ALIGN(align);						\
-	VMLINUX_SYMBOL(__per_cpu_start) = .;				\
-	.data.percpu  : AT(ADDR(.data.percpu) - LOAD_OFFSET) {		\
+/**
+ * PERCPU_VADDR - define output section for percpu area
+ * @vaddr: explicit base address (optional)
+ * @phdr: destination PHDR (optional)
+ *
+ * Macro which expands to output section for percpu area.  If @vaddr
+ * is not blank, it specifies explicit base address and all percpu
+ * symbols will be offset from the given address.  If blank, @vaddr
+ * always equals @laddr + LOAD_OFFSET.
+ *
+ * @phdr defines the output PHDR to use if not blank.  Be warned that
+ * output PHDR is sticky.  If @phdr is specified, the next output
+ * section in the linker script will go there too.  @phdr should have
+ * a leading colon.
+ *
+ * This macro defines three symbols, __per_cpu_load, __per_cpu_start
+ * and __per_cpu_end.  The first one is the vaddr of loaded percpu
+ * init data.  __per_cpu_start equals @vaddr and __per_cpu_end is the
+ * end offset.
+ */
+#define PERCPU_VADDR(vaddr, phdr)					\
+	VMLINUX_SYMBOL(__per_cpu_load) = .;				\
+	.data.percpu vaddr : AT(VMLINUX_SYMBOL(__per_cpu_load)		\
+				- LOAD_OFFSET) {			\
+		VMLINUX_SYMBOL(__per_cpu_start) = .;			\
+		*(.data.percpu.first)					\
 		*(.data.percpu.page_aligned)				\
 		*(.data.percpu)						\
 		*(.data.percpu.shared_aligned)				\
-	}								\
-	VMLINUX_SYMBOL(__per_cpu_end) = .;
+		VMLINUX_SYMBOL(__per_cpu_end) = .;			\
+	} phdr								\
+	. = VMLINUX_SYMBOL(__per_cpu_load) + SIZEOF(.data.percpu);
+
+/**
+ * PERCPU - define output section for percpu area, simple version
+ * @align: required alignment
+ *
+ * Align to @align and outputs output section for percpu area.  This
+ * macro doesn't maniuplate @vaddr or @phdr and __per_cpu_load and
+ * __per_cpu_start will be identical.
+ */
+#define PERCPU(align)							\
+	. = ALIGN(align);						\
+	PERCPU_VADDR( , )
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 9127f6b..472f117 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -467,6 +467,7 @@
 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
index f899b50..27a6753 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -182,11 +182,11 @@
 	unsigned int		irqs_unhandled;
 	spinlock_t		lock;
 #ifdef CONFIG_SMP
-	cpumask_t		affinity;
+	cpumask_var_t		affinity;
 	unsigned int		cpu;
-#endif
 #ifdef CONFIG_GENERIC_PENDING_IRQ
-	cpumask_t		pending_mask;
+	cpumask_var_t		pending_mask;
+#endif
 #endif
 #ifdef CONFIG_PROC_FS
 	struct proc_dir_entry	*dir;
@@ -422,4 +422,84 @@
 
 #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
index 86af92e..887477b 100644
--- 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/magic.h b/include/linux/magic.h
index 0b4df7e..5b4e28b 100644
--- a/include/linux/magic.h
+++ b/include/linux/magic.h
@@ -49,4 +49,5 @@
 #define FUTEXFS_SUPER_MAGIC	0xBAD1DEA
 #define INOTIFYFS_SUPER_MAGIC	0x2BAD1DEA
 
+#define STACK_END_MAGIC		0x57AC6E9D
 #endif /* __LINUX_MAGIC_H__ */
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 9f2a375..0e24202 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -9,34 +9,39 @@
 #include <asm/percpu.h>
 
 #ifdef CONFIG_SMP
-#define DEFINE_PER_CPU(type, name)					\
-	__attribute__((__section__(".data.percpu")))			\
-	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
+#define PER_CPU_BASE_SECTION ".data.percpu"
 
 #ifdef MODULE
-#define SHARED_ALIGNED_SECTION ".data.percpu"
+#define PER_CPU_SHARED_ALIGNED_SECTION ""
 #else
-#define SHARED_ALIGNED_SECTION ".data.percpu.shared_aligned"
+#define PER_CPU_SHARED_ALIGNED_SECTION ".shared_aligned"
 #endif
+#define PER_CPU_FIRST_SECTION ".first"
+
+#else
+
+#define PER_CPU_BASE_SECTION ".data"
+#define PER_CPU_SHARED_ALIGNED_SECTION ""
+#define PER_CPU_FIRST_SECTION ""
+
+#endif
+
+#define DEFINE_PER_CPU_SECTION(type, name, section)			\
+	__attribute__((__section__(PER_CPU_BASE_SECTION section)))	\
+	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
+
+#define DEFINE_PER_CPU(type, name)					\
+	DEFINE_PER_CPU_SECTION(type, name, "")
 
 #define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)			\
-	__attribute__((__section__(SHARED_ALIGNED_SECTION)))		\
-	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name		\
+	DEFINE_PER_CPU_SECTION(type, name, PER_CPU_SHARED_ALIGNED_SECTION) \
 	____cacheline_aligned_in_smp
 
-#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name)			\
-	__attribute__((__section__(".data.percpu.page_aligned")))	\
-	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
-#else
-#define DEFINE_PER_CPU(type, name)					\
-	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
+#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name)				\
+	DEFINE_PER_CPU_SECTION(type, name, ".page_aligned")
 
-#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)		      \
-	DEFINE_PER_CPU(type, name)
-
-#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name)		      \
-	DEFINE_PER_CPU(type, name)
-#endif
+#define DEFINE_PER_CPU_FIRST(type, name)				\
+	DEFINE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
 
 #define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
 #define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4cae9b8..a85b0ce 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1157,10 +1157,9 @@
 	pid_t pid;
 	pid_t tgid;
 
-#ifdef CONFIG_CC_STACKPROTECTOR
 	/* Canary value for the -fstack-protector gcc feature */
 	unsigned long stack_canary;
-#endif
+
 	/* 
 	 * pointers to (original) parent process, youngest child, younger sibling,
 	 * older sibling, respectively.  (p->father can be replaced with 
@@ -2066,6 +2065,19 @@
 
 extern void thread_info_cache_init(void);
 
+#ifdef CONFIG_DEBUG_STACK_USAGE
+static inline unsigned long stack_not_used(struct task_struct *p)
+{
+	unsigned long *n = end_of_stack(p);
+
+	do { 	/* Skip over canary */
+		n++;
+	} while (!*n);
+
+	return (unsigned long)n - (unsigned long)end_of_stack(p);
+}
+#endif
+
 /* set thread flags in other task's structures
  * - see asm/thread_info.h for TIF_xxxx flags available
  */
diff --git a/include/linux/stackprotector.h b/include/linux/stackprotector.h
new file mode 100644
index 0000000..6f3e54c
--- /dev/null
+++ b/include/linux/stackprotector.h
@@ -0,0 +1,16 @@
+#ifndef _LINUX_STACKPROTECTOR_H
+#define _LINUX_STACKPROTECTOR_H 1
+
+#include <linux/compiler.h>
+#include <linux/sched.h>
+#include <linux/random.h>
+
+#ifdef CONFIG_CC_STACKPROTECTOR
+# include <asm/stackprotector.h>
+#else
+static inline void boot_init_stack_canary(void)
+{
+}
+#endif
+
+#endif
diff --git a/include/linux/topology.h b/include/linux/topology.h
index e632d29..a16b9e0 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -193,5 +193,11 @@
 #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/init/main.c b/init/main.c
index 8442094..bfe4fb0 100644
--- a/init/main.c
+++ b/init/main.c
@@ -14,6 +14,7 @@
 #include <linux/proc_fs.h>
 #include <linux/kernel.h>
 #include <linux/syscalls.h>
+#include <linux/stackprotector.h>
 #include <linux/string.h>
 #include <linux/ctype.h>
 #include <linux/delay.h>
@@ -539,6 +540,12 @@
 	 */
 	lockdep_init();
 	debug_objects_early_init();
+
+	/*
+	 * Set up the the initial canary ASAP:
+	 */
+	boot_init_stack_canary();
+
 	cgroup_init_early();
 
 	local_irq_disable();
diff --git a/kernel/exit.c b/kernel/exit.c
index f80dec3..70612c1 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -977,12 +977,9 @@
 {
 	static DEFINE_SPINLOCK(low_water_lock);
 	static int lowest_to_date = THREAD_SIZE;
-	unsigned long *n = end_of_stack(current);
 	unsigned long free;
 
-	while (*n == 0)
-		n++;
-	free = (unsigned long)n - (unsigned long)end_of_stack(current);
+	free = stack_not_used(current);
 
 	if (free >= lowest_to_date)
 		return;
diff --git a/kernel/fork.c b/kernel/fork.c
index bf0cef8..5ba5f5d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -61,6 +61,7 @@
 #include <linux/proc_fs.h>
 #include <linux/blkdev.h>
 #include <trace/sched.h>
+#include <linux/magic.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -212,6 +213,8 @@
 {
 	struct task_struct *tsk;
 	struct thread_info *ti;
+	unsigned long *stackend;
+
 	int err;
 
 	prepare_to_copy(orig);
@@ -237,6 +240,8 @@
 		goto out;
 
 	setup_thread_stack(tsk, orig);
+	stackend = end_of_stack(tsk);
+	*stackend = STACK_END_MAGIC;	/* for overflow detection */
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 	tsk->stack_canary = get_random_int();
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index f63c706..c248eba 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -46,7 +46,10 @@
 	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
index c20db0b..375d68c 100644
--- 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"
 
@@ -57,6 +58,7 @@
 EXPORT_SYMBOL_GPL(nr_irqs);
 
 #ifdef CONFIG_SPARSE_IRQ
+
 static struct irq_desc irq_desc_init = {
 	.irq	    = -1,
 	.status	    = IRQ_DISABLED,
@@ -64,9 +66,6 @@
 	.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)
@@ -101,6 +100,10 @@
 		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);
 }
 
@@ -109,7 +112,7 @@
  */
 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] = {
@@ -119,14 +122,10 @@
 		.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)
 {
@@ -134,18 +133,30 @@
 	int legacy_count;
 	int i;
 
+	 /* 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();
@@ -153,7 +164,10 @@
 
 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)
@@ -162,10 +176,9 @@
 	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;
 	}
 
@@ -207,9 +220,6 @@
 		.handle_irq = handle_bad_irq,
 		.depth = 1,
 		.lock = __SPIN_LOCK_UNLOCKED(irq_desc->lock),
-#ifdef CONFIG_SMP
-		.affinity = CPU_MASK_ALL
-#endif
 	}
 };
 
@@ -219,12 +229,15 @@
 	int count;
 	int i;
 
+	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
index e6d0a43..40416a8 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -16,7 +16,14 @@
 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
index cd0cd8d..b98739a 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -98,14 +98,14 @@
 
 #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;
@@ -127,16 +127,16 @@
 	 * 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
index bd72329..e05ad9b 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -18,7 +18,7 @@
 
 	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 @@
 	 * 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
index ecf765c..666260e 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -38,15 +38,22 @@
 	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 @@
 	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;
 
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index aae3f74..692363d 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -20,11 +20,11 @@
 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/panic.c b/kernel/panic.c
index 2a2ff36..33cab3d 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -74,6 +74,9 @@
 	vsnprintf(buf, sizeof(buf), fmt, args);
 	va_end(args);
 	printk(KERN_EMERG "Kernel panic - not syncing: %s\n",buf);
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+	dump_stack();
+#endif
 	bust_spinlocks(0);
 
 	/*
@@ -355,15 +358,22 @@
 #endif
 
 #ifdef CONFIG_CC_STACKPROTECTOR
+
+#ifndef GCC_HAS_SP
+#warning You have selected the CONFIG_CC_STACKPROTECTOR option, but the gcc used does not support this.
+#endif
+
 /*
  * Called when gcc's -fstack-protector feature is used, and
  * gcc detects corruption of the on-stack canary value
  */
 void __stack_chk_fail(void)
 {
-	panic("stack-protector: Kernel stack is corrupted");
+	panic("stack-protector: Kernel stack is corrupted in: %p\n",
+		__builtin_return_address(0));
 }
 EXPORT_SYMBOL(__stack_chk_fail);
+
 #endif
 
 core_param(panic, panic_timeout, int, 0644);
diff --git a/kernel/sched.c b/kernel/sched.c
index 52bbf1c..c71d7d5 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -5939,12 +5939,7 @@
 		printk(KERN_CONT " %016lx ", thread_saved_pc(p));
 #endif
 #ifdef CONFIG_DEBUG_STACK_USAGE
-	{
-		unsigned long *n = end_of_stack(p);
-		while (!*n)
-			n++;
-		free = (unsigned long)n - (unsigned long)end_of_stack(p);
-	}
+	free = stack_not_used(p);
 #endif
 	printk(KERN_CONT "%5lu %5d %6d\n", free,
 		task_pid_nr(p), task_pid_nr(p->real_parent));
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 954e1a8..da932f4 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -960,16 +960,17 @@
 
 static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);
 
-static inline int pick_optimal_cpu(int this_cpu, cpumask_t *mask)
+static inline int pick_optimal_cpu(int this_cpu,
+				   const struct cpumask *mask)
 {
 	int first;
 
 	/* "this_cpu" is cheaper to preempt than a remote processor */
-	if ((this_cpu != -1) && cpu_isset(this_cpu, *mask))
+	if ((this_cpu != -1) && cpumask_test_cpu(this_cpu, mask))
 		return this_cpu;
 
-	first = first_cpu(*mask);
-	if (first != NR_CPUS)
+	first = cpumask_first(mask);
+	if (first < nr_cpu_ids)
 		return first;
 
 	return -1;
@@ -981,6 +982,7 @@
 	struct cpumask *lowest_mask = __get_cpu_var(local_cpu_mask);
 	int this_cpu = smp_processor_id();
 	int cpu      = task_cpu(task);
+	cpumask_var_t domain_mask;
 
 	if (task->rt.nr_cpus_allowed == 1)
 		return -1; /* No other targets possible */
@@ -1013,19 +1015,25 @@
 	if (this_cpu == cpu)
 		this_cpu = -1; /* Skip this_cpu opt if the same */
 
-	for_each_domain(cpu, sd) {
-		if (sd->flags & SD_WAKE_AFFINE) {
-			cpumask_t domain_mask;
-			int       best_cpu;
+	if (alloc_cpumask_var(&domain_mask, GFP_ATOMIC)) {
+		for_each_domain(cpu, sd) {
+			if (sd->flags & SD_WAKE_AFFINE) {
+				int best_cpu;
 
-			cpumask_and(&domain_mask, sched_domain_span(sd),
-				    lowest_mask);
+				cpumask_and(domain_mask,
+					    sched_domain_span(sd),
+					    lowest_mask);
 
-			best_cpu = pick_optimal_cpu(this_cpu,
-						    &domain_mask);
-			if (best_cpu != -1)
-				return best_cpu;
+				best_cpu = pick_optimal_cpu(this_cpu,
+							    domain_mask);
+
+				if (best_cpu != -1) {
+					free_cpumask_var(domain_mask);
+					return best_cpu;
+				}
+			}
 		}
+		free_cpumask_var(domain_mask);
 	}
 
 	/*
diff --git a/kernel/softirq.c b/kernel/softirq.c
index bdbe9de..0365b48 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -795,6 +795,11 @@
 	return 0;
 }
 
+int __init __weak arch_probe_nr_irqs(void)
+{
+	return 0;
+}
+
 int __init __weak arch_early_irq_init(void)
 {
 	return 0;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 2f44583..1f0c509 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -971,6 +971,8 @@
 }
 
 #ifdef CONFIG_SMP
+static struct workqueue_struct *work_on_cpu_wq __read_mostly;
+
 struct work_for_cpu {
 	struct work_struct work;
 	long (*fn)(void *);
@@ -991,8 +993,8 @@
  * @fn: the function to run
  * @arg: the function arg
  *
- * This will return -EINVAL in the cpu is not online, or the return value
- * of @fn otherwise.
+ * This will return the value @fn returns.
+ * It is up to the caller to ensure that the cpu doesn't go offline.
  */
 long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
 {
@@ -1001,14 +1003,8 @@
 	INIT_WORK(&wfc.work, do_work_for_cpu);
 	wfc.fn = fn;
 	wfc.arg = arg;
-	get_online_cpus();
-	if (unlikely(!cpu_online(cpu)))
-		wfc.ret = -EINVAL;
-	else {
-		schedule_work_on(cpu, &wfc.work);
-		flush_work(&wfc.work);
-	}
-	put_online_cpus();
+	queue_work_on(cpu, work_on_cpu_wq, &wfc.work);
+	flush_work(&wfc.work);
 
 	return wfc.ret;
 }
@@ -1025,4 +1021,8 @@
 	hotcpu_notifier(workqueue_cpu_callback, 0);
 	keventd_wq = create_workqueue("events");
 	BUG_ON(!keventd_wq);
+#ifdef CONFIG_SMP
+	work_on_cpu_wq = create_workqueue("work_on_cpu");
+	BUG_ON(!work_on_cpu_wq);
+#endif
 }
diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c
index 0f8fc22..4689cb0 100644
--- a/lib/smp_processor_id.c
+++ b/lib/smp_processor_id.c
@@ -22,7 +22,7 @@
 	 * Kernel threads bound to a single CPU can safely use
 	 * smp_processor_id():
 	 */
-	if (cpus_equal(current->cpus_allowed, cpumask_of_cpu(this_cpu)))
+	if (cpumask_equal(&current->cpus_allowed, cpumask_of(this_cpu)))
 		goto out;
 
 	/*