Merge branches 'cross-platform/debug_ll' and 'cross-platform/cpu-mapping' into next/cross-platform

arch/arm/Kconfig

@@ -1393,6 +1393,31 @@ 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

@@ -180,7 +180,7 @@ 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;
@@ -259,9 +259,15 @@ 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;
 
+#ifdef CONFIG_SMP
+	cpu = cpu_logical_map(smp_processor_id());
+#endif
+
+	cpumask = 1 << cpu;
 	cpumask |= cpumask << 8;
 	cpumask |= cpumask << 16;
 
@@ -382,7 +388,12 @@ void __cpuinit gic_enable_ppi(unsigned int irq)
 #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/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 */

arch/arm/include/asm/localtimer.h

@@ -22,6 +22,10 @@ void percpu_timer_setup(void);
  */
 asmlinkage void do_local_timer(struct pt_regs *);
 
+/*
+ * Called from C code
+ */
+void handle_local_timer(struct pt_regs *);
 
 #ifdef CONFIG_LOCAL_TIMERS
 

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.
  */

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

@@ -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 */

arch/arm/kernel/Makefile

@@ -66,6 +66,7 @@ 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>

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());
 
 	/*
@@ -459,6 +479,11 @@ static void ipi_timer(void)
 
 #ifdef CONFIG_LOCAL_TIMERS
 asmlinkage void __exception_irq_entry do_local_timer(struct pt_regs *regs)
+{
+	handle_local_timer(regs);
+}
+
+void handle_local_timer(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	int cpu = smp_processor_id();
@@ -566,6 +591,11 @@ 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/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();
+}

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>

arch/arm/mach-exynos4/hotplug.c

@@ -75,7 +75,7 @@ static inline void platform_do_lowpower(unsigned int cpu, int *spurious)
 		    :
 		    : "memory", "cc");
 
-		if (pen_release == cpu) {
+		if (pen_release == cpu_logical_map(cpu)) {
 			/*
 			 * OK, proper wakeup, we're done
 			 */

arch/arm/mach-exynos4/platsmp.c

@@ -126,7 +126,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 * Note that "pen_release" is the hardware CPU ID, whereas
 	 * "cpu" is Linux's internal ID.
 	 */
-	write_pen_release(cpu);
+	write_pen_release(cpu_logical_map(cpu));
 
 	if (!(__raw_readl(S5P_ARM_CORE1_STATUS) & S5P_CORE_LOCAL_PWR_EN)) {
 		__raw_writel(S5P_CORE_LOCAL_PWR_EN,

arch/arm/mach-msm/hotplug.c

@@ -37,7 +37,7 @@ static inline void platform_do_lowpower(unsigned int cpu)
 		    :
 		    : "memory", "cc");
 
-		if (pen_release == cpu) {
+		if (pen_release == cpu_logical_map(cpu)) {
 			/*
 			 * OK, proper wakeup, we're done
 			 */

arch/arm/mach-msm/platsmp.c

@@ -117,7 +117,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 * Note that "pen_release" is the hardware CPU ID, whereas
 	 * "cpu" is Linux's internal ID.
 	 */
-	pen_release = cpu;
+	pen_release = cpu_logical_map(cpu);
 	__cpuc_flush_dcache_area((void *)&pen_release, sizeof(pen_release));
 	outer_clean_range(__pa(&pen_release), __pa(&pen_release + 1));
 

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>

arch/arm/mach-realview/hotplug.c

@@ -69,7 +69,7 @@ static inline void platform_do_lowpower(unsigned int cpu, int *spurious)
 		    :
 		    : "memory", "cc");
 
-		if (pen_release == cpu) {
+		if (pen_release == cpu_logical_map(cpu)) {
 			/*
 			 * OK, proper wakeup, we're done
 			 */

arch/arm/mach-shmobile/smp-sh73a0.c

@@ -74,6 +74,8 @@ void __cpuinit sh73a0_secondary_init(unsigned int cpu)
 
 int __cpuinit sh73a0_boot_secondary(unsigned int cpu)
 {
+	cpu = cpu_logical_map(cpu);
+
 	/* enable cache coherency */
 	modify_scu_cpu_psr(0, 3 << (cpu * 8));
 
@@ -87,6 +89,8 @@ int __cpuinit sh73a0_boot_secondary(unsigned int cpu)
 
 void __init sh73a0_smp_prepare_cpus(void)
 {
+	int cpu = cpu_logical_map(0);
+
 	scu_enable(scu_base_addr());
 
 	/* Map the reset vector (in headsmp.S) */
@@ -94,5 +98,5 @@ void __init sh73a0_smp_prepare_cpus(void)
 	__raw_writel(__pa(shmobile_secondary_vector), __io(SBAR));
 
 	/* enable cache coherency on CPU0 */
-	modify_scu_cpu_psr(0, 3 << (0 * 8));
+	modify_scu_cpu_psr(0, 3 << (cpu * 8));
 }

arch/arm/mach-ux500/hotplug.c

@@ -24,7 +24,7 @@ static inline void platform_do_lowpower(unsigned int cpu)
 	for (;;) {
 		__asm__ __volatile__("dsb\n\t" "wfi\n\t"
 				: : : "memory");
-		if (pen_release == cpu) {
+		if (pen_release == cpu_logical_map(cpu)) {
 			/*
 			 * OK, proper wakeup, we're done
 			 */

arch/arm/mach-ux500/platsmp.c

@@ -96,7 +96,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 * the holding pen - release it, then wait for it to flag
 	 * that it has been released by resetting pen_release.
 	 */
-	write_pen_release(cpu);
+	write_pen_release(cpu_logical_map(cpu));
 
 	gic_raise_softirq(cpumask_of(cpu), 1);
 

arch/arm/mach-vexpress/hotplug.c

@@ -70,7 +70,7 @@ static inline void platform_do_lowpower(unsigned int cpu, int *spurious)
 		    :
 		    : "memory", "cc");
 
-		if (pen_release == cpu) {
+		if (pen_release == cpu_logical_map(cpu)) {
 			/*
 			 * OK, proper wakeup, we're done
 			 */

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>

arch/arm/plat-versatile/platsmp.c

@@ -77,7 +77,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 * since we haven't sent them a soft interrupt, they shouldn't
 	 * be there.
 	 */
-	write_pen_release(cpu);
+	write_pen_release(cpu_logical_map(cpu));
 
 	/*
 	 * Send the secondary CPU a soft interrupt, thereby causing