diff options
| -rw-r--r-- | arch/arm/Kconfig | 25 | ||||
| -rw-r--r-- | arch/arm/include/asm/cputype.h | 6 | ||||
| -rw-r--r-- | arch/arm/include/asm/topology.h | 33 | ||||
| -rw-r--r-- | arch/arm/kernel/Makefile | 1 | ||||
| -rw-r--r-- | arch/arm/kernel/smp.c | 5 | ||||
| -rw-r--r-- | arch/arm/kernel/topology.c | 148 |
6 files changed, 218 insertions, 0 deletions
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 4edfdae4e62..ca2e1b40e0b 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1408,6 +1408,31 @@ 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/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/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/smp.c b/arch/arm/kernel/smp.c index d88ff0230e8..62775c5c5ba 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -31,6 +31,7 @@ #include <asm/cacheflush.h> #include <asm/cpu.h> #include <asm/cputype.h> +#include <asm/topology.h> #include <asm/mmu_context.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -268,6 +269,8 @@ 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 +361,8 @@ 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()); /* 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(); +} |