Merge branch 'ppi-irq-core-for-rmk' of git://github.com/mzyngier/arm-platforms into devel-stable

46 files changed, 829 insertions, 307 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index c8d5ec8a939..2686959319a 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1420,6 +1420,31 @@ config SMP_ON_UP
 
 	  If you don't know what to do here, say Y.
 
+config ARM_CPU_TOPOLOGY
+	bool "Support cpu topology definition"
+	depends on SMP && CPU_V7
+	default y
+	help
+	  Support ARM cpu topology definition. The MPIDR register defines
+	  affinity between processors which is then used to describe the cpu
+	  topology of an ARM System.
+
+config SCHED_MC
+	bool "Multi-core scheduler support"
+	depends on ARM_CPU_TOPOLOGY
+	help
+	  Multi-core scheduler support improves the CPU scheduler's decision
+	  making when dealing with multi-core CPU chips at a cost of slightly
+	  increased overhead in some places. If unsure say N here.
+
+config SCHED_SMT
+	bool "SMT scheduler support"
+	depends on ARM_CPU_TOPOLOGY
+	help
+	  Improves the CPU scheduler's decision making when dealing with
+	  MultiThreading at a cost of slightly increased overhead in some
+	  places. If unsure say N here.
+
 config HAVE_ARM_SCU
 	bool
 	help
diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c
index 734db99eaee..016c1aeb847 100644
--- a/arch/arm/common/gic.c
+++ b/arch/arm/common/gic.c
@@ -29,6 +29,9 @@
 #include <linux/cpu_pm.h>
 #include <linux/cpumask.h>
 #include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
 
 #include <asm/irq.h>
 #include <asm/mach/irq.h>
@@ -181,7 +184,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 		return -EINVAL;
 
 	mask = 0xff << shift;
-	bit = 1 << (cpu + shift);
+	bit = 1 << (cpu_logical_map(cpu) + shift);
 
 	spin_lock(&irq_controller_lock);
 	val = readl_relaxed(reg) & ~mask;
@@ -260,9 +263,16 @@ static void __init gic_dist_init(struct gic_chip_data *gic,
 	unsigned int irq_start)
 {
 	unsigned int gic_irqs, irq_limit, i;
+	u32 cpumask;
 	void __iomem *base = gic->dist_base;
-	u32 cpumask = 1 << smp_processor_id();
+	u32 cpu = 0;
+	u32 nrppis = 0, ppi_base = 0;
 
+#ifdef CONFIG_SMP
+	cpu = cpu_logical_map(smp_processor_id());
+#endif
+
+	cpumask = 1 << cpu;
 	cpumask |= cpumask << 8;
 	cpumask |= cpumask << 16;
 
@@ -280,6 +290,23 @@ static void __init gic_dist_init(struct gic_chip_data *gic,
 	gic->gic_irqs = gic_irqs;
 
 	/*
+	 * Nobody would be insane enough to use PPIs on a secondary
+	 * GIC, right?
+	 */
+	if (gic == &gic_data[0]) {
+		nrppis = (32 - irq_start) & 31;
+
+		/* The GIC only supports up to 16 PPIs. */
+		if (nrppis > 16)
+			BUG();
+
+		ppi_base = gic->irq_offset + 32 - nrppis;
+	}
+
+	pr_info("Configuring GIC with %d sources (%d PPIs)\n",
+		gic_irqs, (gic == &gic_data[0]) ? nrppis : 0);
+
+	/*
 	 * Set all global interrupts to be level triggered, active low.
 	 */
 	for (i = 32; i < gic_irqs; i += 16)
@@ -314,7 +341,17 @@ static void __init gic_dist_init(struct gic_chip_data *gic,
 	/*
 	 * Setup the Linux IRQ subsystem.
 	 */
-	for (i = irq_start; i < irq_limit; i++) {
+	for (i = 0; i < nrppis; i++) {
+		int ppi = i + ppi_base;
+
+		irq_set_percpu_devid(ppi);
+		irq_set_chip_and_handler(ppi, &gic_chip,
+					 handle_percpu_devid_irq);
+		irq_set_chip_data(ppi, gic);
+		set_irq_flags(ppi, IRQF_VALID | IRQF_NOAUTOEN);
+	}
+
+	for (i = irq_start + nrppis; i < irq_limit; i++) {
 		irq_set_chip_and_handler(i, &gic_chip, handle_fasteoi_irq);
 		irq_set_chip_data(i, gic);
 		set_irq_flags(i, IRQF_VALID | IRQF_PROBE);
@@ -557,20 +594,15 @@ void __cpuinit gic_secondary_init(unsigned int gic_nr)
 	gic_cpu_init(&gic_data[gic_nr]);
 }
 
-void __cpuinit gic_enable_ppi(unsigned int irq)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	irq_set_status_flags(irq, IRQ_NOPROBE);
-	gic_unmask_irq(irq_get_irq_data(irq));
-	local_irq_restore(flags);
-}
-
 #ifdef CONFIG_SMP
 void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 {
-	unsigned long map = *cpus_addr(*mask);
+	int cpu;
+	unsigned long map = 0;
+
+	/* Convert our logical CPU mask into a physical one. */
+	for_each_cpu(cpu, mask)
+		map |= 1 << cpu_logical_map(cpu);
 
 	/*
 	 * Ensure that stores to Normal memory are visible to the
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index cd4458f6417..cb47d28cbe1 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -8,6 +8,7 @@
 #define CPUID_CACHETYPE	1
 #define CPUID_TCM	2
 #define CPUID_TLBTYPE	3
+#define CPUID_MPIDR	5
 
 #define CPUID_EXT_PFR0	"c1, 0"
 #define CPUID_EXT_PFR1	"c1, 1"
@@ -70,6 +71,11 @@ static inline unsigned int __attribute_const__ read_cpuid_tcmstatus(void)
 	return read_cpuid(CPUID_TCM);
 }
 
+static inline unsigned int __attribute_const__ read_cpuid_mpidr(void)
+{
+	return read_cpuid(CPUID_MPIDR);
+}
+
 /*
  * Intel's XScale3 core supports some v6 features (supersections, L2)
  * but advertises itself as v5 as it does not support the v6 ISA.  For
diff --git a/arch/arm/include/asm/entry-macro-multi.S b/arch/arm/include/asm/entry-macro-multi.S
index 2f1e2098dfe..88d61815f0c 100644
--- a/arch/arm/include/asm/entry-macro-multi.S
+++ b/arch/arm/include/asm/entry-macro-multi.S
@@ -25,13 +25,6 @@
 	movne	r1, sp
 	adrne	lr, BSYM(1b)
 	bne	do_IPI
-
-#ifdef CONFIG_LOCAL_TIMERS
-	test_for_ltirq r0, r2, r6, lr
-	movne	r0, sp
-	adrne	lr, BSYM(1b)
-	bne	do_local_timer
-#endif
 #endif
 9997:
 	.endm
diff --git a/arch/arm/include/asm/exception.h b/arch/arm/include/asm/exception.h
new file mode 100644
index 00000000000..5abaf5bbd98
--- /dev/null
+++ b/arch/arm/include/asm/exception.h
@@ -0,0 +1,19 @@
+/*
+ * Annotations for marking C functions as exception handlers.
+ *
+ * These should only be used for C functions that are called from the low
+ * level exception entry code and not any intervening C code.
+ */
+#ifndef __ASM_ARM_EXCEPTION_H
+#define __ASM_ARM_EXCEPTION_H
+
+#include <linux/ftrace.h>
+
+#define __exception	__attribute__((section(".exception.text")))
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#define __exception_irq_entry	__irq_entry
+#else
+#define __exception_irq_entry	__exception
+#endif
+
+#endif /* __ASM_ARM_EXCEPTION_H */
diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h
index 89ad1805e57..ddf07a92a6c 100644
--- a/arch/arm/include/asm/hardirq.h
+++ b/arch/arm/include/asm/hardirq.h
@@ -9,9 +9,6 @@
 
 typedef struct {
 	unsigned int __softirq_pending;
-#ifdef CONFIG_LOCAL_TIMERS
-	unsigned int local_timer_irqs;
-#endif
 #ifdef CONFIG_SMP
 	unsigned int ipi_irqs[NR_IPI];
 #endif
diff --git a/arch/arm/include/asm/hardware/entry-macro-gic.S b/arch/arm/include/asm/hardware/entry-macro-gic.S
index c115b82fe80..74ebc803904 100644
--- a/arch/arm/include/asm/hardware/entry-macro-gic.S
+++ b/arch/arm/include/asm/hardware/entry-macro-gic.S
@@ -22,15 +22,11 @@
  * interrupt controller spec.  To wit:
  *
  * Interrupts 0-15 are IPI
- * 16-28 are reserved
- * 29-31 are local.  We allow 30 to be used for the watchdog.
+ * 16-31 are local.  We allow 30 to be used for the watchdog.
  * 32-1020 are global
  * 1021-1022 are reserved
  * 1023 is "spurious" (no interrupt)
  *
- * For now, we ignore all local interrupts so only return an interrupt if it's
- * between 30 and 1020.  The test_for_ipi routine below will pick up on IPIs.
- *
  * A simple read from the controller will tell us the number of the highest
  * priority enabled interrupt.  We then just need to check whether it is in the
  * valid range for an IRQ (30-1020 inclusive).
@@ -43,7 +39,7 @@
 
 	ldr	\tmp, =1021
 	bic     \irqnr, \irqstat, #0x1c00
-	cmp     \irqnr, #29
+	cmp     \irqnr, #15
 	cmpcc	\irqnr, \irqnr
 	cmpne	\irqnr, \tmp
 	cmpcs	\irqnr, \irqnr
@@ -62,14 +58,3 @@
 	strcc	\irqstat, [\base, #GIC_CPU_EOI]
 	cmpcs	\irqnr, \irqnr
 	.endm
-
-/* As above, this assumes that irqstat and base are preserved.. */
-
-	.macro test_for_ltirq, irqnr, irqstat, base, tmp
-	bic	\irqnr, \irqstat, #0x1c00
-	mov 	\tmp, #0
-	cmp	\irqnr, #29
-	moveq	\tmp, #1
-	streq	\irqstat, [\base, #GIC_CPU_EOI]
-	cmp	\tmp, #0
-	.endm
diff --git a/arch/arm/include/asm/hardware/gic.h b/arch/arm/include/asm/hardware/gic.h
index c5627057b1c..14867e12f20 100644
--- a/arch/arm/include/asm/hardware/gic.h
+++ b/arch/arm/include/asm/hardware/gic.h
@@ -40,7 +40,6 @@ void gic_init(unsigned int, unsigned int, void __iomem *, void __iomem *);
 void gic_secondary_init(unsigned int);
 void gic_cascade_irq(unsigned int gic_nr, unsigned int irq);
 void gic_raise_softirq(const struct cpumask *mask, unsigned int irq);
-void gic_enable_ppi(unsigned int);
 
 struct gic_chip_data {
 	unsigned int irq_offset;
diff --git a/arch/arm/include/asm/localtimer.h b/arch/arm/include/asm/localtimer.h
index 080d74f8128..f5e1cec7e35 100644
--- a/arch/arm/include/asm/localtimer.h
+++ b/arch/arm/include/asm/localtimer.h
@@ -10,6 +10,8 @@
 #ifndef __ASM_ARM_LOCALTIMER_H
 #define __ASM_ARM_LOCALTIMER_H
 
+#include <linux/interrupt.h>
+
 struct clock_event_device;
 
 /*
@@ -17,27 +19,20 @@ struct clock_event_device;
  */
 void percpu_timer_setup(void);
 
-/*
- * Called from assembly, this is the local timer IRQ handler
- */
-asmlinkage void do_local_timer(struct pt_regs *);
-
-
 #ifdef CONFIG_LOCAL_TIMERS
 
 #ifdef CONFIG_HAVE_ARM_TWD
 
 #include "smp_twd.h"
 
-#define local_timer_ack()	twd_timer_ack()
+#define local_timer_stop(c)	twd_timer_stop((c))
 
 #else
 
 /*
- * Platform provides this to acknowledge a local timer IRQ.
- * Returns true if the local timer IRQ is to be processed.
+ * Stop the local timer
  */
-int local_timer_ack(void);
+void local_timer_stop(struct clock_event_device *);
 
 #endif
 
@@ -52,6 +47,10 @@ static inline int local_timer_setup(struct clock_event_device *evt)
 {
 	return -ENXIO;
 }
+
+static inline void local_timer_stop(struct clock_event_device *evt)
+{
+}
 #endif
 
 #endif
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index e42d96a45d3..1e5717afc4a 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -33,6 +33,11 @@ extern void show_ipi_list(struct seq_file *, int);
 asmlinkage void do_IPI(int ipinr, struct pt_regs *regs);
 
 /*
+ * Called from C code, this handles an IPI.
+ */
+void handle_IPI(int ipinr, struct pt_regs *regs);
+
+/*
  * Setup the set of possible CPUs (via set_cpu_possible)
  */
 extern void smp_init_cpus(void);
@@ -66,6 +71,12 @@ extern void platform_secondary_init(unsigned int cpu);
 extern void platform_smp_prepare_cpus(unsigned int);
 
 /*
+ * Logical CPU mapping.
+ */
+extern int __cpu_logical_map[NR_CPUS];
+#define cpu_logical_map(cpu)	__cpu_logical_map[cpu]
+
+/*
  * Initial data for bringing up a secondary CPU.
  */
 struct secondary_data {
@@ -88,9 +99,4 @@ extern void platform_cpu_enable(unsigned int cpu);
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
-/*
- * show local interrupt info
- */
-extern void show_local_irqs(struct seq_file *, int);
-
 #endif /* ifndef __ASM_ARM_SMP_H */
diff --git a/arch/arm/include/asm/smp_twd.h b/arch/arm/include/asm/smp_twd.h
index fed9981fba0..ef9ffba97ad 100644
--- a/arch/arm/include/asm/smp_twd.h
+++ b/arch/arm/include/asm/smp_twd.h
@@ -22,7 +22,7 @@ struct clock_event_device;
 
 extern void __iomem *twd_base;
 
-int twd_timer_ack(void);
 void twd_timer_setup(struct clock_event_device *);
+void twd_timer_stop(struct clock_event_device *);
 
 #endif
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index 832888d0c20..ed6b0499a10 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -62,13 +62,6 @@
 
 #include <asm/outercache.h>
 
-#define __exception	__attribute__((section(".exception.text")))
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-#define __exception_irq_entry	__irq_entry
-#else
-#define __exception_irq_entry	__exception
-#endif
-
 struct thread_info;
 struct task_struct;
 
diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index accbd7cad9b..a7e457ed27c 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -1,6 +1,39 @@
 #ifndef _ASM_ARM_TOPOLOGY_H
 #define _ASM_ARM_TOPOLOGY_H
 
+#ifdef CONFIG_ARM_CPU_TOPOLOGY
+
+#include <linux/cpumask.h>
+
+struct cputopo_arm {
+	int thread_id;
+	int core_id;
+	int socket_id;
+	cpumask_t thread_sibling;
+	cpumask_t core_sibling;
+};
+
+extern struct cputopo_arm cpu_topology[NR_CPUS];
+
+#define topology_physical_package_id(cpu)	(cpu_topology[cpu].socket_id)
+#define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
+#define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
+#define topology_thread_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
+
+#define mc_capable()	(cpu_topology[0].socket_id != -1)
+#define smt_capable()	(cpu_topology[0].thread_id != -1)
+
+void init_cpu_topology(void);
+void store_cpu_topology(unsigned int cpuid);
+const struct cpumask *cpu_coregroup_mask(unsigned int cpu);
+
+#else
+
+static inline void init_cpu_topology(void) { }
+static inline void store_cpu_topology(unsigned int cpuid) { }
+
+#endif
+
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_ARM_TOPOLOGY_H */
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 8fa83f54c96..7cac26c5f50 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -73,6 +73,7 @@ obj-$(CONFIG_IWMMXT)		+= iwmmxt.o
 obj-$(CONFIG_CPU_HAS_PMU)	+= pmu.o
 obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o
 AFLAGS_iwmmxt.o			:= -Wa,-mcpu=iwmmxt
+obj-$(CONFIG_ARM_CPU_TOPOLOGY)  += topology.o
 
 ifneq ($(CONFIG_ARCH_EBSA110),y)
   obj-y		+= io.o
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index de3dcab8610..7cb29261249 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -35,8 +35,8 @@
 #include <linux/list.h>
 #include <linux/kallsyms.h>
 #include <linux/proc_fs.h>
-#include <linux/ftrace.h>
 
+#include <asm/exception.h>
 #include <asm/system.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
@@ -59,9 +59,6 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 #ifdef CONFIG_SMP
 	show_ipi_list(p, prec);
 #endif
-#ifdef CONFIG_LOCAL_TIMERS
-	show_local_irqs(p, prec);
-#endif
 	seq_printf(p, "%*s: %10lu\n", prec, "Err", irq_err_count);
 	return 0;
 }
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index d88ff0230e8..a96c08cd612 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -16,7 +16,6 @@
 #include <linux/cache.h>
 #include <linux/profile.h>
 #include <linux/errno.h>
-#include <linux/ftrace.h>
 #include <linux/mm.h>
 #include <linux/err.h>
 #include <linux/cpu.h>
@@ -31,6 +30,8 @@
 #include <asm/cacheflush.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
+#include <asm/exception.h>
+#include <asm/topology.h>
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -39,6 +40,7 @@
 #include <asm/tlbflush.h>
 #include <asm/ptrace.h>
 #include <asm/localtimer.h>
+#include <asm/smp_plat.h>
 
 /*
  * as from 2.5, kernels no longer have an init_tasks structure
@@ -259,6 +261,20 @@ void __ref cpu_die(void)
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
+int __cpu_logical_map[NR_CPUS];
+
+void __init smp_setup_processor_id(void)
+{
+	int i;
+	u32 cpu = is_smp() ? read_cpuid_mpidr() & 0xff : 0;
+
+	cpu_logical_map(0) = cpu;
+	for (i = 1; i < NR_CPUS; ++i)
+		cpu_logical_map(i) = i == cpu ? 0 : i;
+
+	printk(KERN_INFO "Booting Linux on physical CPU %d\n", cpu);
+}
+
 /*
  * Called by both boot and secondaries to move global data into
  * per-processor storage.
@@ -268,6 +284,8 @@ static void __cpuinit smp_store_cpu_info(unsigned int cpuid)
 	struct cpuinfo_arm *cpu_info = &per_cpu(cpu_data, cpuid);
 
 	cpu_info->loops_per_jiffy = loops_per_jiffy;
+
+	store_cpu_topology(cpuid);
 }
 
 /*
@@ -358,6 +376,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	unsigned int ncores = num_possible_cpus();
 
+	init_cpu_topology();
+
 	smp_store_cpu_info(smp_processor_id());
 
 	/*
@@ -437,10 +457,6 @@ u64 smp_irq_stat_cpu(unsigned int cpu)
 	for (i = 0; i < NR_IPI; i++)
 		sum += __get_irq_stat(cpu, ipi_irqs[i]);
 
-#ifdef CONFIG_LOCAL_TIMERS
-	sum += __get_irq_stat(cpu, local_timer_irqs);
-#endif
-
 	return sum;
 }
 
@@ -457,33 +473,6 @@ static void ipi_timer(void)
 	irq_exit();
 }
 
-#ifdef CONFIG_LOCAL_TIMERS
-asmlinkage void __exception_irq_entry do_local_timer(struct pt_regs *regs)
-{
-	struct pt_regs *old_regs = set_irq_regs(regs);
-	int cpu = smp_processor_id();
-
-	if (local_timer_ack()) {
-		__inc_irq_stat(cpu, local_timer_irqs);
-		ipi_timer();
-	}
-
-	set_irq_regs(old_regs);
-}
-
-void show_local_irqs(struct seq_file *p, int prec)
-{
-	unsigned int cpu;
-
-	seq_printf(p, "%*s: ", prec, "LOC");
-
-	for_each_present_cpu(cpu)
-		seq_printf(p, "%10u ", __get_irq_stat(cpu, local_timer_irqs));
-
-	seq_printf(p, " Local timer interrupts\n");
-}
-#endif
-
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 static void smp_timer_broadcast(const struct cpumask *mask)
 {
@@ -534,7 +523,7 @@ static void percpu_timer_stop(void)
 	unsigned int cpu = smp_processor_id();
 	struct clock_event_device *evt = &per_cpu(percpu_clockevent, cpu);
 
-	evt->set_mode(CLOCK_EVT_MODE_UNUSED, evt);
+	local_timer_stop(evt);
 }
 #endif
 
@@ -567,6 +556,11 @@ static void ipi_cpu_stop(unsigned int cpu)
  */
 asmlinkage void __exception_irq_entry do_IPI(int ipinr, struct pt_regs *regs)
 {
+	handle_IPI(ipinr, regs);
+}
+
+void handle_IPI(int ipinr, struct pt_regs *regs)
+{
 	unsigned int cpu = smp_processor_id();
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c
index 79ed5e7f204..5b6d536cbfe 100644
--- a/arch/arm/kernel/smp_scu.c
+++ b/arch/arm/kernel/smp_scu.c
@@ -33,7 +33,7 @@ unsigned int __init scu_get_core_count(void __iomem *scu_base)
 /*
  * Enable the SCU
  */
-void __init scu_enable(void __iomem *scu_base)
+void scu_enable(void __iomem *scu_base)
 {
 	u32 scu_ctrl;
 
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index 01c186222f3..a8a6682d6b5 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -19,6 +19,7 @@
 #include <linux/io.h>
 
 #include <asm/smp_twd.h>
+#include <asm/localtimer.h>
 #include <asm/hardware/gic.h>
 
 /* set up by the platform code */
@@ -26,6 +27,8 @@ void __iomem *twd_base;
 
 static unsigned long twd_timer_rate;
 
+static struct clock_event_device __percpu **twd_evt;
+
 static void twd_set_mode(enum clock_event_mode mode,
 			struct clock_event_device *clk)
 {
@@ -80,6 +83,12 @@ int twd_timer_ack(void)
 	return 0;
 }
 
+void twd_timer_stop(struct clock_event_device *clk)
+{
+	twd_set_mode(CLOCK_EVT_MODE_UNUSED, clk);
+	disable_percpu_irq(clk->irq);
+}
+
 static void __cpuinit twd_calibrate_rate(void)
 {
 	unsigned long count;
@@ -119,11 +128,43 @@ static void __cpuinit twd_calibrate_rate(void)
 	}
 }
 
+static irqreturn_t twd_handler(int irq, void *dev_id)
+{
+	struct clock_event_device *evt = *(struct clock_event_device **)dev_id;
+
+	if (twd_timer_ack()) {
+		evt->event_handler(evt);
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
+}
+
 /*
  * Setup the local clock events for a CPU.
  */
 void __cpuinit twd_timer_setup(struct clock_event_device *clk)
 {
+	struct clock_event_device **this_cpu_clk;
+
+	if (!twd_evt) {
+		int err;
+
+		twd_evt = alloc_percpu(struct clock_event_device *);
+		if (!twd_evt) {
+			pr_err("twd: can't allocate memory\n");
+			return;
+		}
+
+		err = request_percpu_irq(clk->irq, twd_handler,
+					 "twd", twd_evt);
+		if (err) {
+			pr_err("twd: can't register interrupt %d (%d)\n",
+			       clk->irq, err);
+			return;
+		}
+	}
+
 	twd_calibrate_rate();
 
 	clk->name = "local_timer";
@@ -137,8 +178,10 @@ void __cpuinit twd_timer_setup(struct clock_event_device *clk)
 	clk->max_delta_ns = clockevent_delta2ns(0xffffffff, clk);
 	clk->min_delta_ns = clockevent_delta2ns(0xf, clk);
 
+	this_cpu_clk = __this_cpu_ptr(twd_evt);
+	*this_cpu_clk = clk;
+
 	clockevents_register_device(clk);
 
-	/* Make sure our local interrupt controller has this enabled */
-	gic_enable_ppi(clk->irq);
+	enable_percpu_irq(clk->irq, 0);
 }
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
new file mode 100644
index 00000000000..1040c00405d
--- /dev/null
+++ b/arch/arm/kernel/topology.c
@@ -0,0 +1,148 @@
+/*
+ * arch/arm/kernel/topology.c
+ *
+ * Copyright (C) 2011 Linaro Limited.
+ * Written by: Vincent Guittot
+ *
+ * based on arch/sh/kernel/topology.c
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/node.h>
+#include <linux/nodemask.h>
+#include <linux/sched.h>
+
+#include <asm/cputype.h>
+#include <asm/topology.h>
+
+#define MPIDR_SMP_BITMASK (0x3 << 30)
+#define MPIDR_SMP_VALUE (0x2 << 30)
+
+#define MPIDR_MT_BITMASK (0x1 << 24)
+
+/*
+ * These masks reflect the current use of the affinity levels.
+ * The affinity level can be up to 16 bits according to ARM ARM
+ */
+
+#define MPIDR_LEVEL0_MASK 0x3
+#define MPIDR_LEVEL0_SHIFT 0
+
+#define MPIDR_LEVEL1_MASK 0xF
+#define MPIDR_LEVEL1_SHIFT 8
+
+#define MPIDR_LEVEL2_MASK 0xFF
+#define MPIDR_LEVEL2_SHIFT 16
+
+struct cputopo_arm cpu_topology[NR_CPUS];
+
+const struct cpumask *cpu_coregroup_mask(unsigned int cpu)
+{
+	return &cpu_topology[cpu].core_sibling;
+}
+
+/*
+ * store_cpu_topology is called at boot when only one cpu is running
+ * and with the mutex cpu_hotplug.lock locked, when several cpus have booted,
+ * which prevents simultaneous write access to cpu_topology array
+ */
+void store_cpu_topology(unsigned int cpuid)
+{
+	struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid];
+	unsigned int mpidr;
+	unsigned int cpu;
+
+	/* If the cpu topology has been already set, just return */
+	if (cpuid_topo->core_id != -1)
+		return;
+
+	mpidr = read_cpuid_mpidr();
+
+	/* create cpu topology mapping */
+	if ((mpidr & MPIDR_SMP_BITMASK) == MPIDR_SMP_VALUE) {
+		/*
+		 * This is a multiprocessor system
+		 * multiprocessor format & multiprocessor mode field are set
+		 */
+
+		if (mpidr & MPIDR_MT_BITMASK) {
+			/* core performance interdependency */
+			cpuid_topo->thread_id = (mpidr >> MPIDR_LEVEL0_SHIFT)
+				& MPIDR_LEVEL0_MASK;
+			cpuid_topo->core_id = (mpidr >> MPIDR_LEVEL1_SHIFT)
+				& MPIDR_LEVEL1_MASK;
+			cpuid_topo->socket_id = (mpidr >> MPIDR_LEVEL2_SHIFT)
+				& MPIDR_LEVEL2_MASK;
+		} else {
+			/* largely independent cores */
+			cpuid_topo->thread_id = -1;
+			cpuid_topo->core_id = (mpidr >> MPIDR_LEVEL0_SHIFT)
+				& MPIDR_LEVEL0_MASK;
+			cpuid_topo->socket_id = (mpidr >> MPIDR_LEVEL1_SHIFT)
+				& MPIDR_LEVEL1_MASK;
+		}
+	} else {
+		/*
+		 * This is an uniprocessor system
+		 * we are in multiprocessor format but uniprocessor system
+		 * or in the old uniprocessor format
+		 */
+		cpuid_topo->thread_id = -1;
+		cpuid_topo->core_id = 0;
+		cpuid_topo->socket_id = -1;
+	}
+
+	/* update core and thread sibling masks */
+	for_each_possible_cpu(cpu) {
+		struct cputopo_arm *cpu_topo = &cpu_topology[cpu];
+
+		if (cpuid_topo->socket_id == cpu_topo->socket_id) {
+			cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
+			if (cpu != cpuid)
+				cpumask_set_cpu(cpu,
+					&cpuid_topo->core_sibling);
+
+			if (cpuid_topo->core_id == cpu_topo->core_id) {
+				cpumask_set_cpu(cpuid,
+					&cpu_topo->thread_sibling);
+				if (cpu != cpuid)
+					cpumask_set_cpu(cpu,
+						&cpuid_topo->thread_sibling);
+			}
+		}
+	}
+	smp_wmb();
+
+	printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n",
+		cpuid, cpu_topology[cpuid].thread_id,
+		cpu_topology[cpuid].core_id,
+		cpu_topology[cpuid].socket_id, mpidr);
+}
+
+/*
+ * init_cpu_topology is called at boot when only one cpu is running
+ * which prevent simultaneous write access to cpu_topology array
+ */
+void init_cpu_topology(void)
+{
+	unsigned int cpu;
+
+	/* init core mask */
+	for_each_possible_cpu(cpu) {
+		struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]);
+
+		cpu_topo->thread_id = -1;
+		cpu_topo->core_id =  -1;
+		cpu_topo->socket_id = -1;
+		cpumask_clear(&cpu_topo->core_sibling);
+		cpumask_clear(&cpu_topo->thread_sibling);
+	}
+	smp_wmb();
+}
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index bc9f9da782c..210382555af 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -27,6 +27,7 @@
 
 #include <linux/atomic.h>
 #include <asm/cacheflush.h>
+#include <asm/exception.h>
 #include <asm/system.h>
 #include <asm/unistd.h>
 #include <asm/traps.h>
diff --git a/arch/arm/mach-exynos4/include/mach/entry-macro.S b/arch/arm/mach-exynos4/include/mach/entry-macro.S
index d7a1e281ce7..006a4f4c65c 100644
--- a/arch/arm/mach-exynos4/include/mach/entry-macro.S
+++ b/arch/arm/mach-exynos4/include/mach/entry-macro.S
@@ -55,7 +55,7 @@
 
 		bic     \irqnr, \irqstat, #0x1c00
 
-		cmp     \irqnr, #29
+		cmp     \irqnr, #15
 		cmpcc	\irqnr, \irqnr
 		cmpne	\irqnr, \tmp
 		cmpcs	\irqnr, \irqnr
@@ -76,8 +76,3 @@
 		strcc	\irqstat, [\base, #GIC_CPU_EOI]
 		cmpcs	\irqnr, \irqnr
 		.endm
-
-		/* As above, this assumes that irqstat and base are preserved.. */
-
-		.macro test_for_ltirq, irqnr, irqstat, base, tmp
-		.endm
diff --git a/arch/arm/mach-exynos4/mct.c b/arch/arm/mach-exynos4/mct.c
index 1ae059b7ad7..85a1bb79f11 100644
--- a/arch/arm/mach-exynos4/mct.c
+++ b/arch/arm/mach-exynos4/mct.c
@@ -380,9 +380,11 @@ static void exynos4_mct_tick_init(struct clock_event_device *evt)
 
 	if (cpu == 0) {
 		mct_tick0_event_irq.dev_id = &mct_tick[cpu];
+		evt->irq = IRQ_MCT_L0;
 		setup_irq(IRQ_MCT_L0, &mct_tick0_event_irq);
 	} else {
 		mct_tick1_event_irq.dev_id = &mct_tick[cpu];
+		evt->irq = IRQ_MCT_L1;
 		setup_irq(IRQ_MCT_L1, &mct_tick1_event_irq);
 		irq_set_affinity(IRQ_MCT_L1, cpumask_of(1));
 	}
@@ -394,9 +396,10 @@ void __cpuinit local_timer_setup(struct clock_event_device *evt)
 	exynos4_mct_tick_init(evt);
 }
 
-int local_timer_ack(void)
+void local_timer_stop(struct clock_event_device *evt)
 {
-	return 0;
+	evt->set_mode(CLOCK_EVT_MODE_UNUSED, evt);
+	disable_irq(evt->irq);
 }
 
 #endif /* CONFIG_LOCAL_TIMERS */
diff --git a/arch/arm/mach-exynos4/platsmp.c b/arch/arm/mach-exynos4/platsmp.c
index 7c2282c6ba8..a08c536923f 100644
--- a/arch/arm/mach-exynos4/platsmp.c
+++ b/arch/arm/mach-exynos4/platsmp.c
@@ -191,12 +191,10 @@ void __init smp_init_cpus(void)
 	ncores = scu_base ? scu_get_core_count(scu_base) : 1;
 
 	/* sanity check */
-	if (ncores > NR_CPUS) {
-		printk(KERN_WARNING
-		       "EXYNOS4: no. of cores (%d) greater than configured "
-		       "maximum of %d - clipping\n",
-		       ncores, NR_CPUS);
-		ncores = NR_CPUS;
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
 	}
 
 	for (i = 0; i < ncores; i++)
diff --git a/arch/arm/mach-msm/board-msm8x60.c b/arch/arm/mach-msm/board-msm8x60.c
index 9221f54778b..106170fb184 100644
--- a/arch/arm/mach-msm/board-msm8x60.c
+++ b/arch/arm/mach-msm/board-msm8x60.c
@@ -53,8 +53,6 @@ static void __init msm8x60_map_io(void)
 
 static void __init msm8x60_init_irq(void)
 {
-	unsigned int i;
-
 	gic_init(0, GIC_PPI_START, MSM_QGIC_DIST_BASE,
 		 (void *)MSM_QGIC_CPU_BASE);
 
@@ -66,15 +64,6 @@ static void __init msm8x60_init_irq(void)
 	 */
 	if (!machine_is_msm8x60_sim())
 		writel(0x0000FFFF, MSM_QGIC_DIST_BASE + GIC_DIST_ENABLE_SET);
-
-	/* FIXME: Not installing AVS_SVICINT and AVS_SVICINTSWDONE yet
-	 * as they are configured as level, which does not play nice with
-	 * handle_percpu_irq.
-	 */
-	for (i = GIC_PPI_START; i < GIC_SPI_START; i++) {
-		if (i != AVS_SVICINT && i != AVS_SVICINTSWDONE)
-			irq_set_handler(i, handle_percpu_irq);
-	}
 }
 
 static void __init msm8x60_init(void)
diff --git a/arch/arm/mach-msm/include/mach/entry-macro-qgic.S b/arch/arm/mach-msm/include/mach/entry-macro-qgic.S
index 12467157afb..717076f3ca7 100644
--- a/arch/arm/mach-msm/include/mach/entry-macro-qgic.S
+++ b/arch/arm/mach-msm/include/mach/entry-macro-qgic.S
@@ -8,81 +8,10 @@
  * warranty of any kind, whether express or implied.
  */
 
-#include <mach/hardware.h>
-#include <asm/hardware/gic.h>
+#include <asm/hardware/entry-macro-gic.S>
 
 	.macro	disable_fiq
 	.endm
 
-	.macro  get_irqnr_preamble, base, tmp
-	ldr	\base, =gic_cpu_base_addr
-	ldr	\base, [\base]
-	.endm
-
 	.macro  arch_ret_to_user, tmp1, tmp2
 	.endm
-
-	/*
-	 * The interrupt numbering scheme is defined in the
-	 * interrupt controller spec.  To wit:
-	 *
-	 * Migrated the code from ARM MP port to be more consistent
-	 * with interrupt processing , the following still holds true
-	 * however, all interrupts are treated the same regardless of
-	 * if they are local IPI or PPI
-	 *
-	 * Interrupts 0-15 are IPI
-	 * 16-31 are PPI
-	 *   (16-18 are the timers)
-	 * 32-1020 are global
-	 * 1021-1022 are reserved
-	 * 1023 is "spurious" (no interrupt)
-	 *
-	 * A simple read from the controller will tell us the number of the
-	 * highest priority enabled interrupt.  We then just need to check
-	 * whether it is in the valid range for an IRQ (0-1020 inclusive).
-	 *
-	 * Base ARM code assumes that the local (private) peripheral interrupts
-	 * are not valid, we treat them differently, in that the privates are
-	 * handled like normal shared interrupts with the exception that only
-	 * one processor can register the interrupt and the handler must be
-	 * the same for all processors.
-	 */
-
-	.macro  get_irqnr_and_base, irqnr, irqstat, base, tmp
-
-	ldr  \irqstat, [\base, #GIC_CPU_INTACK] /* bits 12-10 =srcCPU,
-						   9-0 =int # */
-
-	bic     \irqnr, \irqstat, #0x1c00	@mask src
-	cmp     \irqnr, #15
-	ldr		\tmp, =1021
-	cmpcc	\irqnr, \irqnr
-	cmpne	\irqnr, \tmp
-	cmpcs	\irqnr, \irqnr
-
-	.endm
-
-	/* We assume that irqstat (the raw value of the IRQ acknowledge
-	 * register) is preserved from the macro above.
-	 * If there is an IPI, we immediately signal end of interrupt on the
-	 * controller, since this requires the original irqstat value which
-	 * we won't easily be able to recreate later.
-	 */
-	.macro test_for_ipi, irqnr, irqstat, base, tmp
-    bic \irqnr, \irqstat, #0x1c00
-    cmp \irqnr, #16
-    strcc   \irqstat, [\base, #GIC_CPU_EOI]
-    cmpcs   \irqnr, \irqnr
-	.endm
-
-	/* As above, this assumes that irqstat and base are preserved.. */
-
-	.macro test_for_ltirq, irqnr, irqstat, base, tmp
-    bic \irqnr, \irqstat, #0x1c00
-    mov     \tmp, #0
-    cmp \irqnr, #16
-    moveq   \tmp, #1
-    streq   \irqstat, [\base, #GIC_CPU_EOI]
-    cmp \tmp, #0
-	.endm
diff --git a/arch/arm/mach-msm/platsmp.c b/arch/arm/mach-msm/platsmp.c
index 1a1af9e5625..72765952091 100644
--- a/arch/arm/mach-msm/platsmp.c
+++ b/arch/arm/mach-msm/platsmp.c
@@ -156,6 +156,12 @@ void __init smp_init_cpus(void)
 {
 	unsigned int i, ncores = get_core_count();
 
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
+	}
+
 	for (i = 0; i < ncores; i++)
 		set_cpu_possible(i, true);
 
diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c
index 63621f152c9..afeeca52fc6 100644
--- a/arch/arm/mach-msm/timer.c
+++ b/arch/arm/mach-msm/timer.c
@@ -71,12 +71,16 @@ enum timer_location {
 struct msm_clock {
 	struct clock_event_device   clockevent;
 	struct clocksource          clocksource;
-	struct irqaction            irq;
+	unsigned int		    irq;
 	void __iomem                *regbase;
 	uint32_t                    freq;
 	uint32_t                    shift;
 	void __iomem                *global_counter;
 	void __iomem                *local_counter;
+	union {
+		struct clock_event_device		*evt;
+		struct clock_event_device __percpu	**percpu_evt;
+	};		
 };
 
 enum {
@@ -87,13 +91,10 @@ enum {
 
 
 static struct msm_clock msm_clocks[];
-static struct clock_event_device *local_clock_event;
 
 static irqreturn_t msm_timer_interrupt(int irq, void *dev_id)
 {
-	struct clock_event_device *evt = dev_id;
-	if (smp_processor_id() != 0)
-		evt = local_clock_event;
+	struct clock_event_device *evt = *(struct clock_event_device **)dev_id;
 	if (evt->event_handler == NULL)
 		return IRQ_HANDLED;
 	evt->event_handler(evt);
@@ -171,13 +172,7 @@ static struct msm_clock msm_clocks[] = {
 			.mask           = CLOCKSOURCE_MASK(32),
 			.flags          = CLOCK_SOURCE_IS_CONTINUOUS,
 		},
-		.irq = {
-			.name    = "gp_timer",
-			.flags   = IRQF_DISABLED | IRQF_TIMER | IRQF_TRIGGER_RISING,
-			.handler = msm_timer_interrupt,
-			.dev_id  = &msm_clocks[0].clockevent,
-			.irq     = INT_GP_TIMER_EXP
-		},
+		.irq = INT_GP_TIMER_EXP,
 		.freq = GPT_HZ,
 	},
 	[MSM_CLOCK_DGT] = {
@@ -196,13 +191,7 @@ static struct msm_clock msm_clocks[] = {
 			.mask           = CLOCKSOURCE_MASK((32 - MSM_DGT_SHIFT)),
 			.flags          = CLOCK_SOURCE_IS_CONTINUOUS,
 		},
-		.irq = {
-			.name    = "dg_timer",
-			.flags   = IRQF_DISABLED | IRQF_TIMER | IRQF_TRIGGER_RISING,
-			.handler = msm_timer_interrupt,
-			.dev_id  = &msm_clocks[1].clockevent,
-			.irq     = INT_DEBUG_TIMER_EXP
-		},
+		.irq = INT_DEBUG_TIMER_EXP,
 		.freq = DGT_HZ >> MSM_DGT_SHIFT,
 		.shift = MSM_DGT_SHIFT,
 	}
@@ -261,10 +250,30 @@ static void __init msm_timer_init(void)
 			printk(KERN_ERR "msm_timer_init: clocksource_register "
 			       "failed for %s\n", cs->name);
 
-		res = setup_irq(clock->irq.irq, &clock->irq);
+		ce->irq = clock->irq;
+		if (cpu_is_msm8x60() || cpu_is_msm8960()) {
+			clock->percpu_evt = alloc_percpu(struct clock_event_device *);
+			if (!clock->percpu_evt) {
+				pr_err("msm_timer_init: memory allocation "
+				       "failed for %s\n", ce->name);
+				continue;
+			}
+
+			*__this_cpu_ptr(clock->percpu_evt) = ce;
+			res = request_percpu_irq(ce->irq, msm_timer_interrupt,
+						 ce->name, clock->percpu_evt);
+			if (!res)
+				enable_percpu_irq(ce->irq, 0);
+		} else {
+			clock->evt = ce;
+			res = request_irq(ce->irq, msm_timer_interrupt,
+					  IRQF_TIMER | IRQF_NOBALANCING | IRQF_TRIGGER_RISING,
+					  ce->name, &clock->evt);
+		}
+
 		if (res)
-			printk(KERN_ERR "msm_timer_init: setup_irq "
-			       "failed for %s\n", cs->name);
+			pr_err("msm_timer_init: request_irq failed for %s\n",
+			       ce->name);
 
 		clockevents_register_device(ce);
 	}
@@ -273,6 +282,7 @@ static void __init msm_timer_init(void)
 #ifdef CONFIG_SMP
 int __cpuinit local_timer_setup(struct clock_event_device *evt)
 {
+	static bool local_timer_inited;
 	struct msm_clock *clock = &msm_clocks[MSM_GLOBAL_TIMER];
 
 	/* Use existing clock_event for cpu 0 */
@@ -281,12 +291,13 @@ int __cpuinit local_timer_setup(struct clock_event_device *evt)
 
 	writel(DGT_CLK_CTL_DIV_4, MSM_TMR_BASE + DGT_CLK_CTL);
 
-	if (!local_clock_event) {
+	if (!local_timer_inited) {
 		writel(0, clock->regbase  + TIMER_ENABLE);
 		writel(0, clock->regbase + TIMER_CLEAR);
 		writel(~0, clock->regbase + TIMER_MATCH_VAL);
+		local_timer_inited = true;
 	}
-	evt->irq = clock->irq.irq;
+	evt->irq = clock->irq;
 	evt->name = "local_timer";
 	evt->features = CLOCK_EVT_FEAT_ONESHOT;
 	evt->rating = clock->clockevent.rating;
@@ -298,17 +309,17 @@ int __cpuinit local_timer_setup(struct clock_event_device *evt)
 		clockevent_delta2ns(0xf0000000 >> clock->shift, evt);
 	evt->min_delta_ns = clockevent_delta2ns(4, evt);
 
-	local_clock_event = evt;
-
-	gic_enable_ppi(clock->irq.irq);
+	*__this_cpu_ptr(clock->percpu_evt) = evt;
+	enable_percpu_irq(evt->irq, 0);
 
 	clockevents_register_device(evt);
 	return 0;
 }
 
-inline int local_timer_ack(void)
+void local_timer_stop(struct clock_event_device *evt)
 {
-	return 1;
+	evt->set_mode(CLOCK_EVT_MODE_UNUSED, evt);
+	disable_percpu_irq(evt->irq);
 }
 
 #endif
diff --git a/arch/arm/mach-omap2/include/mach/entry-macro.S b/arch/arm/mach-omap2/include/mach/entry-macro.S
index ceb8b7e593d..feb90a10945 100644
--- a/arch/arm/mach-omap2/include/mach/entry-macro.S
+++ b/arch/arm/mach-omap2/include/mach/entry-macro.S
@@ -78,7 +78,7 @@
 4401:		ldr     \irqstat, [\base, #GIC_CPU_INTACK]
 		ldr     \tmp, =1021
 		bic     \irqnr, \irqstat, #0x1c00
-		cmp     \irqnr, #29
+		cmp     \irqnr, #15
 		cmpcc   \irqnr, \irqnr
 		cmpne   \irqnr, \tmp
 		cmpcs   \irqnr, \irqnr
@@ -101,18 +101,6 @@
 		it	cs
 		cmpcs	\irqnr, \irqnr
 		.endm
-
-		/* As above, this assumes that irqstat and base are preserved */
-
-		.macro test_for_ltirq, irqnr, irqstat, base, tmp
-		bic	\irqnr, \irqstat, #0x1c00
-		mov 	\tmp, #0
-		cmp	\irqnr, #29
-		itt	eq
-		moveq	\tmp, #1
-		streq	\irqstat, [\base, #GIC_CPU_EOI]
-		cmp	\tmp, #0
-		.endm
 #endif	/* CONFIG_SMP */
 
 #else	/* MULTI_OMAP2 */
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index ce65e9329c7..889464dc7b2 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -109,12 +109,10 @@ void __init smp_init_cpus(void)
 	ncores = scu_get_core_count(scu_base);
 
 	/* sanity check */
-	if (ncores > NR_CPUS) {
-		printk(KERN_WARNING
-		       "OMAP4: no. of cores (%d) greater than configured "
-		       "maximum of %d - clipping\n",
-		       ncores, NR_CPUS);
-		ncores = NR_CPUS;
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
 	}
 
 	for (i = 0; i < ncores; i++)
diff --git a/arch/arm/mach-pxa/irq.c b/arch/arm/mach-pxa/irq.c
index b09e848eb6c..ca607571782 100644
--- a/arch/arm/mach-pxa/irq.c
+++ b/arch/arm/mach-pxa/irq.c
@@ -19,6 +19,8 @@
 #include <linux/io.h>
 #include <linux/irq.h>
 
+#include <asm/exception.h>
+
 #include <mach/hardware.h>
 #include <mach/irqs.h>
 #include <mach/gpio.h>
diff --git a/arch/arm/mach-realview/platsmp.c b/arch/arm/mach-realview/platsmp.c
index 4ae943bafa9..e83c654a58d 100644
--- a/arch/arm/mach-realview/platsmp.c
+++ b/arch/arm/mach-realview/platsmp.c
@@ -52,12 +52,10 @@ void __init smp_init_cpus(void)
 	ncores = scu_base ? scu_get_core_count(scu_base) : 1;
 
 	/* sanity check */
-	if (ncores > NR_CPUS) {
-		printk(KERN_WARNING
-		       "Realview: no. of cores (%d) greater than configured "
-		       "maximum of %d - clipping\n",
-		       ncores, NR_CPUS);
-		ncores = NR_CPUS;
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
 	}
 
 	for (i = 0; i < ncores; i++)
diff --git a/arch/arm/mach-shmobile/entry-intc.S b/arch/arm/mach-shmobile/entry-intc.S
index cac0a7ae208..1a1c00ca39a 100644
--- a/arch/arm/mach-shmobile/entry-intc.S
+++ b/arch/arm/mach-shmobile/entry-intc.S
@@ -51,7 +51,4 @@
 	.macro  test_for_ipi, irqnr, irqstat, base, tmp
 	.endm
 
-	.macro  test_for_ltirq, irqnr, irqstat, base, tmp
-	.endm
-
 	arch_irq_handler shmobile_handle_irq_intc
diff --git a/arch/arm/mach-shmobile/include/mach/entry-macro.S b/arch/arm/mach-shmobile/include/mach/entry-macro.S
index d791f10eeac..8d4a416d428 100644
--- a/arch/arm/mach-shmobile/include/mach/entry-macro.S
+++ b/arch/arm/mach-shmobile/include/mach/entry-macro.S
@@ -27,8 +27,5 @@
 	.macro  test_for_ipi, irqnr, irqstat, base, tmp
 	.endm
 
-	.macro  test_for_ltirq, irqnr, irqstat, base, tmp
-	.endm
-
 	.macro  arch_ret_to_user, tmp1, tmp2
 	.endm
diff --git a/arch/arm/mach-shmobile/platsmp.c b/arch/arm/mach-shmobile/platsmp.c
index 66f980625a3..e4e485fa253 100644
--- a/arch/arm/mach-shmobile/platsmp.c
+++ b/arch/arm/mach-shmobile/platsmp.c
@@ -56,6 +56,12 @@ void __init smp_init_cpus(void)
 	unsigned int ncores = shmobile_smp_get_core_count();
 	unsigned int i;
 
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
+	}
+
 	for (i = 0; i < ncores; i++)
 		set_cpu_possible(i, true);
 
diff --git a/arch/arm/mach-tegra/platsmp.c b/arch/arm/mach-tegra/platsmp.c
index 0886cbccdde..7d2b5d03c1d 100644
--- a/arch/arm/mach-tegra/platsmp.c
+++ b/arch/arm/mach-tegra/platsmp.c
@@ -114,10 +114,10 @@ void __init smp_init_cpus(void)
 {
 	unsigned int i, ncores = scu_get_core_count(scu_base);
 
-	if (ncores > NR_CPUS) {
-		printk(KERN_ERR "Tegra: no. of cores (%u) greater than configured (%u), clipping\n",
-			ncores, NR_CPUS);
-		ncores = NR_CPUS;
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
 	}
 
 	for (i = 0; i < ncores; i++)
diff --git a/arch/arm/mach-ux500/platsmp.c b/arch/arm/mach-ux500/platsmp.c
index a33df5f4c27..eb5199102cf 100644
--- a/arch/arm/mach-ux500/platsmp.c
+++ b/arch/arm/mach-ux500/platsmp.c
@@ -156,12 +156,10 @@ void __init smp_init_cpus(void)
 	ncores = scu_base ? scu_get_core_count(scu_base) : 1;
 
 	/* sanity check */
-	if (ncores > NR_CPUS) {
-		printk(KERN_WARNING
-		       "U8500: no. of cores (%d) greater than configured "
-		       "maximum of %d - clipping\n",
-		       ncores, NR_CPUS);
-		ncores = NR_CPUS;
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
 	}
 
 	for (i = 0; i < ncores; i++)
diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c
index bfd32f52c2d..2b1e836a76e 100644
--- a/arch/arm/mach-vexpress/ct-ca9x4.c
+++ b/arch/arm/mach-vexpress/ct-ca9x4.c
@@ -221,6 +221,12 @@ static void ct_ca9x4_init_cpu_map(void)
 {
 	int i, ncores = scu_get_core_count(MMIO_P2V(A9_MPCORE_SCU));
 
+	if (ncores > nr_cpu_ids) {
+		pr_warn("SMP: %u cores greater than maximum (%u), clipping\n",
+			ncores, nr_cpu_ids);
+		ncores = nr_cpu_ids;
+	}
+
 	for (i = 0; i < ncores; ++i)
 		set_cpu_possible(i, true);
 
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 3b5ea68acbb..aa33949fef6 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -20,6 +20,7 @@
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
 
+#include <asm/exception.h>
 #include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index a103732b758..664544ff77d 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -95,6 +95,7 @@ typedef irqreturn_t (*irq_handler_t)(int, void *);
  * @flags:	flags (see IRQF_* above)
  * @name:	name of the device
  * @dev_id:	cookie to identify the device
+ * @percpu_dev_id:	cookie to identify the device
  * @next:	pointer to the next irqaction for shared interrupts
  * @irq:	interrupt number
  * @dir:	pointer to the proc/irq/NN/name entry
@@ -104,17 +105,18 @@ typedef irqreturn_t (*irq_handler_t)(int, void *);
  * @thread_mask:	bitmask for keeping track of @thread activity
  */
 struct irqaction {
-	irq_handler_t handler;
-	unsigned long flags;
-	void *dev_id;
-	struct irqaction *next;
-	int irq;
-	irq_handler_t thread_fn;
-	struct task_struct *thread;
-	unsigned long thread_flags;
-	unsigned long thread_mask;
-	const char *name;
-	struct proc_dir_entry *dir;
+	irq_handler_t		handler;
+	unsigned long		flags;
+	void			*dev_id;
+	void __percpu		*percpu_dev_id;
+	struct irqaction	*next;
+	int			irq;
+	irq_handler_t		thread_fn;
+	struct task_struct	*thread;
+	unsigned long		thread_flags;
+	unsigned long		thread_mask;
+	const char		*name;
+	struct proc_dir_entry	*dir;
 } ____cacheline_internodealigned_in_smp;
 
 extern irqreturn_t no_action(int cpl, void *dev_id);
@@ -136,6 +138,10 @@ extern int __must_check
 request_any_context_irq(unsigned int irq, irq_handler_t handler,
 			unsigned long flags, const char *name, void *dev_id);
 
+extern int __must_check
+request_percpu_irq(unsigned int irq, irq_handler_t handler,
+		   const char *devname, void __percpu *percpu_dev_id);
+
 extern void exit_irq_thread(void);
 #else
 
@@ -164,10 +170,18 @@ request_any_context_irq(unsigned int irq, irq_handler_t handler,
 	return request_irq(irq, handler, flags, name, dev_id);
 }
 
+static inline int __must_check
+request_percpu_irq(unsigned int irq, irq_handler_t handler,
+		   const char *devname, void __percpu *percpu_dev_id)
+{
+	return request_irq(irq, handler, 0, devname, percpu_dev_id);
+}
+
 static inline void exit_irq_thread(void) { }
 #endif
 
 extern void free_irq(unsigned int, void *);
+extern void free_percpu_irq(unsigned int, void __percpu *);
 
 struct device;
 
@@ -207,7 +221,9 @@ extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id);
 
 extern void disable_irq_nosync(unsigned int irq);
 extern void disable_irq(unsigned int irq);
+extern void disable_percpu_irq(unsigned int irq);
 extern void enable_irq(unsigned int irq);
+extern void enable_percpu_irq(unsigned int irq, unsigned int type);
 
 /* The following three functions are for the core kernel use only. */
 #ifdef CONFIG_GENERIC_HARDIRQS
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 59517300a31..59e49c80cc2 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -66,6 +66,7 @@ typedef	void (*irq_preflow_handler_t)(struct irq_data *data);
  * IRQ_NO_BALANCING		- Interrupt cannot be balanced (affinity set)
  * IRQ_MOVE_PCNTXT		- Interrupt can be migrated from process context
  * IRQ_NESTED_TRHEAD		- Interrupt nests into another thread
+ * IRQ_PER_CPU_DEVID		- Dev_id is a per-cpu variable
  */
 enum {
 	IRQ_TYPE_NONE		= 0x00000000,
@@ -88,12 +89,13 @@ enum {
 	IRQ_MOVE_PCNTXT		= (1 << 14),
 	IRQ_NESTED_THREAD	= (1 << 15),
 	IRQ_NOTHREAD		= (1 << 16),
+	IRQ_PER_CPU_DEVID	= (1 << 17),
 };
 
 #define IRQF_MODIFY_MASK	\
 	(IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \
 	 IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \
-	 IRQ_PER_CPU | IRQ_NESTED_THREAD)
+	 IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID)
 
 #define IRQ_NO_BALANCING_MASK	(IRQ_PER_CPU | IRQ_NO_BALANCING)
 
@@ -336,12 +338,14 @@ struct irq_chip {
  * IRQCHIP_MASK_ON_SUSPEND:	Mask non wake irqs in the suspend path
  * IRQCHIP_ONOFFLINE_ENABLED:	Only call irq_on/off_line callbacks
  *				when irq enabled
+ * IRQCHIP_SKIP_SET_WAKE:	Skip chip.irq_set_wake(), for this irq chip
  */
 enum {
 	IRQCHIP_SET_TYPE_MASKED		= (1 <<  0),
 	IRQCHIP_EOI_IF_HANDLED		= (1 <<  1),
 	IRQCHIP_MASK_ON_SUSPEND		= (1 <<  2),
 	IRQCHIP_ONOFFLINE_ENABLED	= (1 <<  3),
+	IRQCHIP_SKIP_SET_WAKE		= (1 <<  4),
 };
 
 /* This include will go away once we isolated irq_desc usage to core code */
@@ -365,6 +369,8 @@ enum {
 struct irqaction;
 extern int setup_irq(unsigned int irq, struct irqaction *new);
 extern void remove_irq(unsigned int irq, struct irqaction *act);
+extern int setup_percpu_irq(unsigned int irq, struct irqaction *new);
+extern void remove_percpu_irq(unsigned int irq, struct irqaction *act);
 
 extern void irq_cpu_online(void);
 extern void irq_cpu_offline(void);
@@ -392,6 +398,7 @@ extern void handle_edge_irq(unsigned int irq, struct irq_desc *desc);
 extern void handle_edge_eoi_irq(unsigned int irq, struct irq_desc *desc);
 extern void handle_simple_irq(unsigned int irq, struct irq_desc *desc);
 extern void handle_percpu_irq(unsigned int irq, struct irq_desc *desc);
+extern void handle_percpu_devid_irq(unsigned int irq, struct irq_desc *desc);
 extern void handle_bad_irq(unsigned int irq, struct irq_desc *desc);
 extern void handle_nested_irq(unsigned int irq);
 
@@ -420,6 +427,8 @@ static inline void irq_set_chip_and_handler(unsigned int irq, struct irq_chip *c
 	irq_set_chip_and_handler_name(irq, chip, handle, NULL);
 }
 
+extern int irq_set_percpu_devid(unsigned int irq);
+
 extern void
 __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		  const char *name);
@@ -481,6 +490,13 @@ static inline void irq_set_nested_thread(unsigned int irq, bool nest)
 		irq_clear_status_flags(irq, IRQ_NESTED_THREAD);
 }
 
+static inline void irq_set_percpu_devid_flags(unsigned int irq)
+{
+	irq_set_status_flags(irq,
+			     IRQ_NOAUTOEN | IRQ_PER_CPU | IRQ_NOTHREAD |
+			     IRQ_NOPROBE | IRQ_PER_CPU_DEVID);
+}
+
 /* Handle dynamic irq creation and destruction */
 extern unsigned int create_irq_nr(unsigned int irq_want, int node);
 extern int create_irq(void);
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 150134ac709..6b69c2c9dff 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -53,6 +53,7 @@ struct irq_desc {
 	unsigned long		last_unhandled;	/* Aging timer for unhandled count */
 	unsigned int		irqs_unhandled;
 	raw_spinlock_t		lock;
+	struct cpumask		*percpu_enabled;
 #ifdef CONFIG_SMP
 	const struct cpumask	*affinity_hint;
 	struct irq_affinity_notify *affinity_notify;
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index d5a3009da71..f7c543a801d 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -26,7 +26,7 @@
 int irq_set_chip(unsigned int irq, struct irq_chip *chip)
 {
 	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
 
 	if (!desc)
 		return -EINVAL;
@@ -54,7 +54,7 @@ EXPORT_SYMBOL(irq_set_chip);
 int irq_set_irq_type(unsigned int irq, unsigned int type)
 {
 	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
+	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
 	int ret = 0;
 
 	if (!desc)
@@ -78,7 +78,7 @@ EXPORT_SYMBOL(irq_set_irq_type);
 int irq_set_handler_data(unsigned int irq, void *data)
 {
 	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
 
 	if (!desc)
 		return -EINVAL;
@@ -98,7 +98,7 @@ EXPORT_SYMBOL(irq_set_handler_data);
 int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry)
 {
 	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
 
 	if (!desc)
 		return -EINVAL;
@@ -119,7 +119,7 @@ int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry)
 int irq_set_chip_data(unsigned int irq, void *data)
 {
 	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
 
 	if (!desc)
 		return -EINVAL;
@@ -178,7 +178,7 @@ void irq_shutdown(struct irq_desc *desc)
 	desc->depth = 1;
 	if (desc->irq_data.chip->irq_shutdown)
 		desc->irq_data.chip->irq_shutdown(&desc->irq_data);
-	if (desc->irq_data.chip->irq_disable)
+	else if (desc->irq_data.chip->irq_disable)
 		desc->irq_data.chip->irq_disable(&desc->irq_data);
 	else
 		desc->irq_data.chip->irq_mask(&desc->irq_data);
@@ -204,6 +204,24 @@ void irq_disable(struct irq_desc *desc)
 	}
 }
 
+void irq_percpu_enable(struct irq_desc *desc, unsigned int cpu)
+{
+	if (desc->irq_data.chip->irq_enable)
+		desc->irq_data.chip->irq_enable(&desc->irq_data);
+	else
+		desc->irq_data.chip->irq_unmask(&desc->irq_data);
+	cpumask_set_cpu(cpu, desc->percpu_enabled);
+}
+
+void irq_percpu_disable(struct irq_desc *desc, unsigned int cpu)
+{
+	if (desc->irq_data.chip->irq_disable)
+		desc->irq_data.chip->irq_disable(&desc->irq_data);
+	else
+		desc->irq_data.chip->irq_mask(&desc->irq_data);
+	cpumask_clear_cpu(cpu, desc->percpu_enabled);
+}
+
 static inline void mask_ack_irq(struct irq_desc *desc)
 {
 	if (desc->irq_data.chip->irq_mask_ack)
@@ -544,12 +562,44 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
 		chip->irq_eoi(&desc->irq_data);
 }
 
+/**
+ * handle_percpu_devid_irq - Per CPU local irq handler with per cpu dev ids
+ * @irq:	the interrupt number
+ * @desc:	the interrupt description structure for this irq
+ *
+ * Per CPU interrupts on SMP machines without locking requirements. Same as
+ * handle_percpu_irq() above but with the following extras:
+ *
+ * action->percpu_dev_id is a pointer to percpu variables which
+ * contain the real device id for the cpu on which this handler is
+ * called
+ */
+void handle_percpu_devid_irq(unsigned int irq, struct irq_desc *desc)
+{
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct irqaction *action = desc->action;
+	void *dev_id = __this_cpu_ptr(action->percpu_dev_id);
+	irqreturn_t res;
+
+	kstat_incr_irqs_this_cpu(irq, desc);
+
+	if (chip->irq_ack)
+		chip->irq_ack(&desc->irq_data);
+
+	trace_irq_handler_entry(irq, action);
+	res = action->handler(irq, dev_id);
+	trace_irq_handler_exit(irq, action, res);
+
+	if (chip->irq_eoi)
+		chip->irq_eoi(&desc->irq_data);
+}
+
 void
 __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		  const char *name)
 {
 	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
+	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, 0);
 
 	if (!desc)
 		return;
@@ -593,7 +643,7 @@ irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
 void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set)
 {
 	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
 
 	if (!desc)
 		return;
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 6546431447d..a73dd6c7372 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -71,6 +71,8 @@ extern int irq_startup(struct irq_desc *desc);
 extern void irq_shutdown(struct irq_desc *desc);
 extern void irq_enable(struct irq_desc *desc);
 extern void irq_disable(struct irq_desc *desc);
+extern void irq_percpu_enable(struct irq_desc *desc, unsigned int cpu);
+extern void irq_percpu_disable(struct irq_desc *desc, unsigned int cpu);
 extern void mask_irq(struct irq_desc *desc);
 extern void unmask_irq(struct irq_desc *desc);
 
@@ -114,14 +116,21 @@ static inline void chip_bus_sync_unlock(struct irq_desc *desc)
 		desc->irq_data.chip->irq_bus_sync_unlock(&desc->irq_data);
 }
 
+#define _IRQ_DESC_CHECK		(1 << 0)
+#define _IRQ_DESC_PERCPU	(1 << 1)
+
+#define IRQ_GET_DESC_CHECK_GLOBAL	(_IRQ_DESC_CHECK)
+#define IRQ_GET_DESC_CHECK_PERCPU	(_IRQ_DESC_CHECK | _IRQ_DESC_PERCPU)
+
 struct irq_desc *
-__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus);
+__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus,
+		    unsigned int check);
 void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus);
 
 static inline struct irq_desc *
-irq_get_desc_buslock(unsigned int irq, unsigned long *flags)
+irq_get_desc_buslock(unsigned int irq, unsigned long *flags, unsigned int check)
 {
-	return __irq_get_desc_lock(irq, flags, true);
+	return __irq_get_desc_lock(irq, flags, true, check);
 }
 
 static inline void
@@ -131,9 +140,9 @@ irq_put_desc_busunlock(struct irq_desc *desc, unsigned long flags)
 }
 
 static inline struct irq_desc *
-irq_get_desc_lock(unsigned int irq, unsigned long *flags)
+irq_get_desc_lock(unsigned int irq, unsigned long *flags, unsigned int check)
 {
-	return __irq_get_desc_lock(irq, flags, false);
+	return __irq_get_desc_lock(irq, flags, false, check);
 }
 
 static inline void
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 039b889ea05..1550e8447a1 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -424,11 +424,22 @@ unsigned int irq_get_next_irq(unsigned int offset)
 }
 
 struct irq_desc *
-__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus)
+__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus,
+		    unsigned int check)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 
 	if (desc) {
+		if (check & _IRQ_DESC_CHECK) {
+			if ((check & _IRQ_DESC_PERCPU) &&
+			    !irq_settings_is_per_cpu_devid(desc))
+				return NULL;
+
+			if (!(check & _IRQ_DESC_PERCPU) &&
+			    irq_settings_is_per_cpu_devid(desc))
+				return NULL;
+		}
+
 		if (bus)
 			chip_bus_lock(desc);
 		raw_spin_lock_irqsave(&desc->lock, *flags);
@@ -443,6 +454,25 @@ void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus)
 		chip_bus_sync_unlock(desc);
 }
 
+int irq_set_percpu_devid(unsigned int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	if (!desc)
+		return -EINVAL;
+
+	if (desc->percpu_enabled)
+		return -EINVAL;
+
+	desc->percpu_enabled = kzalloc(sizeof(*desc->percpu_enabled), GFP_KERNEL);
+
+	if (!desc->percpu_enabled)
+		return -ENOMEM;
+
+	irq_set_percpu_devid_flags(irq);
+	return 0;
+}
+
 /**
  * dynamic_irq_cleanup - cleanup a dynamically allocated irq
  * @irq:	irq number to initialize
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 9b956fa2030..67ce837ae52 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -195,7 +195,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *mask)
 int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m)
 {
 	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
 
 	if (!desc)
 		return -EINVAL;
@@ -356,7 +356,7 @@ void __disable_irq(struct irq_desc *desc, unsigned int irq, bool suspend)
 static int __disable_irq_nosync(unsigned int irq)
 {
 	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
+	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
 
 	if (!desc)
 		return -EINVAL;
@@ -448,7 +448,7 @@ void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
 void enable_irq(unsigned int irq)
 {
 	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
+	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
 
 	if (!desc)
 		return;
@@ -467,6 +467,9 @@ static int set_irq_wake_real(unsigned int irq, unsigned int on)
 	struct irq_desc *desc = irq_to_desc(irq);
 	int ret = -ENXIO;
 
+	if (irq_desc_get_chip(desc)->flags &  IRQCHIP_SKIP_SET_WAKE)
+		return 0;
+
 	if (desc->irq_data.chip->irq_set_wake)
 		ret = desc->irq_data.chip->irq_set_wake(&desc->irq_data, on);
 
@@ -488,7 +491,7 @@ static int set_irq_wake_real(unsigned int irq, unsigned int on)
 int irq_set_irq_wake(unsigned int irq, unsigned int on)
 {
 	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
+	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
 	int ret = 0;
 
 	if (!desc)
@@ -529,7 +532,7 @@ EXPORT_SYMBOL(irq_set_irq_wake);
 int can_request_irq(unsigned int irq, unsigned long irqflags)
 {
 	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_lock(irq, &flags);
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
 	int canrequest = 0;
 
 	if (!desc)
@@ -1118,6 +1121,8 @@ int setup_irq(unsigned int irq, struct irqaction *act)
 	int retval;
 	struct irq_desc *desc = irq_to_desc(irq);
 
+	if (WARN_ON(irq_settings_is_per_cpu_devid(desc)))
+		return -EINVAL;
 	chip_bus_lock(desc);
 	retval = __setup_irq(irq, desc, act);
 	chip_bus_sync_unlock(desc);
@@ -1126,7 +1131,7 @@ int setup_irq(unsigned int irq, struct irqaction *act)
 }
 EXPORT_SYMBOL_GPL(setup_irq);
 
- /*
+/*
  * Internal function to unregister an irqaction - used to free
  * regular and special interrupts that are part of the architecture.
  */
@@ -1224,7 +1229,10 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
  */
 void remove_irq(unsigned int irq, struct irqaction *act)
 {
-	__free_irq(irq, act->dev_id);
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	if (desc && !WARN_ON(irq_settings_is_per_cpu_devid(desc)))
+	    __free_irq(irq, act->dev_id);
 }
 EXPORT_SYMBOL_GPL(remove_irq);
 
@@ -1246,7 +1254,7 @@ void free_irq(unsigned int irq, void *dev_id)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 
-	if (!desc)
+	if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc)))
 		return;
 
 #ifdef CONFIG_SMP
@@ -1324,7 +1332,8 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
 	if (!desc)
 		return -EINVAL;
 
-	if (!irq_settings_can_request(desc))
+	if (!irq_settings_can_request(desc) ||
+	    WARN_ON(irq_settings_is_per_cpu_devid(desc)))
 		return -EINVAL;
 
 	if (!handler) {
@@ -1409,3 +1418,194 @@ int request_any_context_irq(unsigned int irq, irq_handler_t handler,
 	return !ret ? IRQC_IS_HARDIRQ : ret;
 }
 EXPORT_SYMBOL_GPL(request_any_context_irq);
+
+void enable_percpu_irq(unsigned int irq, unsigned int type)
+{
+	unsigned int cpu = smp_processor_id();
+	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU);
+
+	if (!desc)
+		return;
+
+	type &= IRQ_TYPE_SENSE_MASK;
+	if (type != IRQ_TYPE_NONE) {
+		int ret;
+
+		ret = __irq_set_trigger(desc, irq, type);
+
+		if (ret) {
+			WARN(1, "failed to set type for IRQ%d\n", irq);
+			goto out;
+		}
+	}
+
+	irq_percpu_enable(desc, cpu);
+out:
+	irq_put_desc_unlock(desc, flags);
+}
+
+void disable_percpu_irq(unsigned int irq)
+{
+	unsigned int cpu = smp_processor_id();
+	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU);
+
+	if (!desc)
+		return;
+
+	irq_percpu_disable(desc, cpu);
+	irq_put_desc_unlock(desc, flags);
+}
+
+/*
+ * Internal function to unregister a percpu irqaction.
+ */
+static struct irqaction *__free_percpu_irq(unsigned int irq, void __percpu *dev_id)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	struct irqaction *action;
+	unsigned long flags;
+
+	WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);
+
+	if (!desc)
+		return NULL;
+
+	raw_spin_lock_irqsave(&desc->lock, flags);
+
+	action = desc->action;
+	if (!action || action->percpu_dev_id != dev_id) {
+		WARN(1, "Trying to free already-free IRQ %d\n", irq);
+		goto bad;
+	}
+
+	if (!cpumask_empty(desc->percpu_enabled)) {
+		WARN(1, "percpu IRQ %d still enabled on CPU%d!\n",
+		     irq, cpumask_first(desc->percpu_enabled));
+		goto bad;
+	}
+
+	/* Found it - now remove it from the list of entries: */
+	desc->action = NULL;
+
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+
+	unregister_handler_proc(irq, action);
+
+	module_put(desc->owner);
+	return action;
+
+bad:
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	return NULL;
+}
+
+/**
+ *	remove_percpu_irq - free a per-cpu interrupt
+ *	@irq: Interrupt line to free
+ *	@act: irqaction for the interrupt
+ *
+ * Used to remove interrupts statically setup by the early boot process.
+ */
+void remove_percpu_irq(unsigned int irq, struct irqaction *act)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	if (desc && irq_settings_is_per_cpu_devid(desc))
+	    __free_percpu_irq(irq, act->percpu_dev_id);
+}
+
+/**
+ *	free_percpu_irq - free an interrupt allocated with request_percpu_irq
+ *	@irq: Interrupt line to free
+ *	@dev_id: Device identity to free
+ *
+ *	Remove a percpu interrupt handler. The handler is removed, but
+ *	the interrupt line is not disabled. This must be done on each
+ *	CPU before calling this function. The function does not return
+ *	until any executing interrupts for this IRQ have completed.
+ *
+ *	This function must not be called from interrupt context.
+ */
+void free_percpu_irq(unsigned int irq, void __percpu *dev_id)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	if (!desc || !irq_settings_is_per_cpu_devid(desc))
+		return;
+
+	chip_bus_lock(desc);
+	kfree(__free_percpu_irq(irq, dev_id));
+	chip_bus_sync_unlock(desc);
+}
+
+/**
+ *	setup_percpu_irq - setup a per-cpu interrupt
+ *	@irq: Interrupt line to setup
+ *	@act: irqaction for the interrupt
+ *
+ * Used to statically setup per-cpu interrupts in the early boot process.
+ */
+int setup_percpu_irq(unsigned int irq, struct irqaction *act)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	int retval;
+
+	if (!desc || !irq_settings_is_per_cpu_devid(desc))
+		return -EINVAL;
+	chip_bus_lock(desc);
+	retval = __setup_irq(irq, desc, act);
+	chip_bus_sync_unlock(desc);
+
+	return retval;
+}
+
+/**
+ *	request_percpu_irq - allocate a percpu interrupt line
+ *	@irq: Interrupt line to allocate
+ *	@handler: Function to be called when the IRQ occurs.
+ *	@devname: An ascii name for the claiming device
+ *	@dev_id: A percpu cookie passed back to the handler function
+ *
+ *	This call allocates interrupt resources, but doesn't
+ *	automatically enable the interrupt. It has to be done on each
+ *	CPU using enable_percpu_irq().
+ *
+ *	Dev_id must be globally unique. It is a per-cpu variable, and
+ *	the handler gets called with the interrupted CPU's instance of
+ *	that variable.
+ */
+int request_percpu_irq(unsigned int irq, irq_handler_t handler,
+		       const char *devname, void __percpu *dev_id)
+{
+	struct irqaction *action;
+	struct irq_desc *desc;
+	int retval;
+
+	if (!dev_id)
+		return -EINVAL;
+
+	desc = irq_to_desc(irq);
+	if (!desc || !irq_settings_can_request(desc) ||
+	    !irq_settings_is_per_cpu_devid(desc))
+		return -EINVAL;
+
+	action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
+	if (!action)
+		return -ENOMEM;
+
+	action->handler = handler;
+	action->flags = IRQF_PERCPU;
+	action->name = devname;
+	action->percpu_dev_id = dev_id;
+
+	chip_bus_lock(desc);
+	retval = __setup_irq(irq, desc, action);
+	chip_bus_sync_unlock(desc);
+
+	if (retval)
+		kfree(action);
+
+	return retval;
+}
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index f1667833d44..1162f1030f1 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -13,6 +13,7 @@ enum {
 	_IRQ_MOVE_PCNTXT	= IRQ_MOVE_PCNTXT,
 	_IRQ_NO_BALANCING	= IRQ_NO_BALANCING,
 	_IRQ_NESTED_THREAD	= IRQ_NESTED_THREAD,
+	_IRQ_PER_CPU_DEVID	= IRQ_PER_CPU_DEVID,
 	_IRQF_MODIFY_MASK	= IRQF_MODIFY_MASK,
 };
 
@@ -24,6 +25,7 @@ enum {
 #define IRQ_NOTHREAD		GOT_YOU_MORON
 #define IRQ_NOAUTOEN		GOT_YOU_MORON
 #define IRQ_NESTED_THREAD	GOT_YOU_MORON
+#define IRQ_PER_CPU_DEVID	GOT_YOU_MORON
 #undef IRQF_MODIFY_MASK
 #define IRQF_MODIFY_MASK	GOT_YOU_MORON
 
@@ -39,6 +41,11 @@ static inline bool irq_settings_is_per_cpu(struct irq_desc *desc)
 	return desc->status_use_accessors & _IRQ_PER_CPU;
 }
 
+static inline bool irq_settings_is_per_cpu_devid(struct irq_desc *desc)
+{
+	return desc->status_use_accessors & _IRQ_PER_CPU_DEVID;
+}
+
 static inline void irq_settings_set_per_cpu(struct irq_desc *desc)
 {
 	desc->status_use_accessors |= _IRQ_PER_CPU;