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

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

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;
 
@@ -279,6 +289,23 @@ 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.
 	 */
@@ -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

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

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

arch/arm/include/asm/exception.h

+/*
+ * 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 */

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

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

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;

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

arch/arm/include/asm/smp.h

@@ -32,6 +32,11 @@ 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)
  */
@@ -65,6 +70,12 @@ 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.
  */
@@ -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 */

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

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;
 

arch/arm/include/asm/topology.h

 #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 */

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

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>
@@ -58,9 +58,6 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 #endif
 #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;

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
 
@@ -566,6 +555,11 @@ static void ipi_cpu_stop(unsigned int cpu)
  * Main handler for inter-processor interrupts
  */
 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);

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;
 

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);
 }

arch/arm/kernel/topology.c

+/*
+ * 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();
+}

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>