From: Mark Brown broonie@linaro.org

Add basic CPU topology support to arm64, based on the existing pre-v8 code and some work done by Mark Hambleton. This patch does not implement any topology discovery support since that should be based on information from firmware, it merely implements the scaffolding for integration of topology support in the architecture.

The goal is to separate the architecture hookup for providing topology information from the DT parsing in order to ease review and avoid blocking the architecture code (which will be built on by other work) with the DT code review by providing something something simple and basic.

A following patch will implement support for parsing the DT topology bindings for ARM, similar patches will be needed for ACPI.

Signed-off-by: Mark Brown broonie@linaro.org --- arch/arm64/Kconfig | 24 ++++++++++ arch/arm64/include/asm/topology.h | 39 +++++++++++++++++ arch/arm64/kernel/Makefile | 1 + arch/arm64/kernel/smp.c | 12 +++++ arch/arm64/kernel/topology.c | 92 +++++++++++++++++++++++++++++++++++++++ 5 files changed, 168 insertions(+) create mode 100644 arch/arm64/include/asm/topology.h create mode 100644 arch/arm64/kernel/topology.c

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 6d4dd22ee4b7..00fcd490b3be 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -154,6 +154,30 @@ config SMP

If you don't know what to do here, say N.

+config ARM_CPU_TOPOLOGY + bool "Support CPU topology definition" + depends on SMP + default y + help + Support CPU topology definition, based on configuration + provided by the firmware. + +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 NR_CPUS int "Maximum number of CPUs (2-32)" range 2 32 diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h new file mode 100644 index 000000000000..58b8b84adcd2 --- /dev/null +++ b/arch/arm64/include/asm/topology.h @@ -0,0 +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(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/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 5ba2fd43a75b..2d145e38ad49 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -18,6 +18,7 @@ arm64-obj-$(CONFIG_SMP) += smp.o smp_spin_table.o arm64-obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)+= hw_breakpoint.o arm64-obj-$(CONFIG_EARLY_PRINTK) += early_printk.o +arm64-obj-$(CONFIG_ARM_CPU_TOPOLOGY) += topology.o

obj-y += $(arm64-obj-y) vdso/ obj-m += $(arm64-obj-m) diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index a0c2ca602cf8..0271fbde5363 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -113,6 +113,11 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) return ret; }

+static void __cpuinit smp_store_cpu_info(unsigned int cpuid) +{ + store_cpu_topology(cpuid); +} + /* * This is the secondary CPU boot entry. We're using this CPUs * idle thread stack, but a set of temporary page tables. @@ -150,6 +155,8 @@ asmlinkage void secondary_start_kernel(void) */ notify_cpu_starting(cpu);

+ smp_store_cpu_info(cpu); + /* * OK, now it's safe to let the boot CPU continue. Wait for * the CPU migration code to notice that the CPU is online @@ -388,6 +395,11 @@ void __init smp_prepare_cpus(unsigned int max_cpus) int err; unsigned int cpu, ncores = num_possible_cpus();

+ init_cpu_topology(); + + smp_store_cpu_info(smp_processor_id()); + + /* * are we trying to boot more cores than exist? */ diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c new file mode 100644 index 000000000000..853544f30a8b --- /dev/null +++ b/arch/arm64/kernel/topology.c @@ -0,0 +1,92 @@ +/* + * arch/arm64/kernel/topology.c + * + * Copyright (C) 2011,2013 Linaro Limited. + * + * Based on the arm32 version written by Vincent Guittot in turn 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 <linux/slab.h> + +#include <asm/topology.h> + +/* + * cpu topology table + */ +struct cputopo_arm cpu_topology[NR_CPUS]; +EXPORT_SYMBOL_GPL(cpu_topology); + +const struct cpumask *cpu_coregroup_mask(int cpu) +{ + return &cpu_topology[cpu].core_sibling; +} + +static void update_siblings_masks(unsigned int cpuid) +{ + struct cputopo_arm *cpu_topo, *cpuid_topo = &cpu_topology[cpuid]; + int cpu; + + /* update core and thread sibling masks */ + for_each_possible_cpu(cpu) { + cpu_topo = &cpu_topology[cpu]; + + if (cpuid_topo->socket_id != cpu_topo->socket_id) + continue; + + 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) + continue; + + cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling); + if (cpu != cpuid) + cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling); + } + smp_wmb(); +} + +void store_cpu_topology(unsigned int cpuid) +{ + struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid]; + + /* DT should have been parsed by the time we get here */ + if (cpuid_topo->core_id == -1) + pr_info("CPU%u: No topology information configured\n", cpuid); + else + update_siblings_masks(cpuid); +} + +/* + * init_cpu_topology is called at boot when only one cpu is running + * which prevent simultaneous write access to cpu_topology array + */ +void __init init_cpu_topology(void) +{ + unsigned int cpu; + + /* init core mask and power*/ + 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(); +}

From: Mark Brown broonie@linaro.org

In non-heterogeneous systems like big.LITTLE systems the scheduler will be able to make better use of the available cores if we provide power numbers to it indicating their relative performance. Do this by parsing the CPU nodes in the DT.

This code currently has no effect as no information on the relative performance of the cores is provided.

Signed-off-by: Mark Brown broonie@linaro.org --- arch/arm64/kernel/topology.c | 145 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 145 insertions(+)

diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 5a2724b3d4b7..68ccf4f4f258 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -23,6 +23,29 @@

#include <asm/topology.h>

+/* + * cpu power table + * This per cpu data structure describes the relative capacity of each core. + * On a heteregenous system, cores don't have the same computation capacity + * and we reflect that difference in the cpu_power field so the scheduler can + * take this difference into account during load balance. A per cpu structure + * is preferred because each CPU updates its own cpu_power field during the + * load balance except for idle cores. One idle core is selected to run the + * rebalance_domains for all idle cores and the cpu_power can be updated + * during this sequence. + */ +static DEFINE_PER_CPU(unsigned long, cpu_scale); + +unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu) +{ + return per_cpu(cpu_scale, cpu); +} + +static void set_power_scale(unsigned int cpu, unsigned long power) +{ + per_cpu(cpu_scale, cpu) = power; +} + #ifdef CONFIG_OF static int cluster_id;

@@ -140,9 +163,49 @@ static void __init parse_cluster(struct device_node *cluster) cluster_id++; }

+struct cpu_efficiency { + const char *compatible; + unsigned long efficiency; +}; + +/* + * Table of relative efficiency of each processors + * The efficiency value must fit in 20bit and the final + * cpu_scale value must be in the range + * 0 < cpu_scale < 3*SCHED_POWER_SCALE/2 + * in order to return at most 1 when DIV_ROUND_CLOSEST + * is used to compute the capacity of a CPU. + * Processors that are not defined in the table, + * use the default SCHED_POWER_SCALE value for cpu_scale. + */ +static const struct cpu_efficiency table_efficiency[] = { + { NULL, }, +}; + +static unsigned long *__cpu_capacity; +#define cpu_capacity(cpu) __cpu_capacity[cpu] + +static unsigned long middle_capacity = 1; + +/* + * Iterate all CPUs' descriptor in DT and compute the efficiency + * (as per table_efficiency). Also calculate a middle efficiency + * as close as possible to (max{eff_i} - min{eff_i}) / 2 + * This is later used to scale the cpu_power field such that an + * 'average' CPU is of middle power. Also see the comments near + * table_efficiency[] and update_cpu_power(). + */ static void __init parse_dt_topology(void) { + const struct cpu_efficiency *cpu_eff; struct device_node *cn; + unsigned long min_capacity = (unsigned long)(-1); + unsigned long max_capacity = 0; + unsigned long capacity = 0; + int alloc_size, cpu; + + alloc_size = nr_cpu_ids * sizeof(*__cpu_capacity); + __cpu_capacity = kzalloc(alloc_size, GFP_NOWAIT);

cn = of_find_node_by_path("/cpus"); if (!cn) { @@ -158,10 +221,88 @@ static void __init parse_dt_topology(void) if (!cn) return; parse_cluster(cn); + + for_each_possible_cpu(cpu) { + const u32 *rate; + int len; + + /* Too early to use cpu->of_node */ + cn = of_get_cpu_node(cpu, NULL); + if (!cn) { + pr_err("Missing device node for CPU %d\n", cpu); + continue; + } + + /* check if the cpu is marked as "disabled", if so ignore */ + if (!of_device_is_available(cn)) + continue; + + for (cpu_eff = table_efficiency; cpu_eff->compatible; cpu_eff++) + if (of_device_is_compatible(cn, cpu_eff->compatible)) + break; + + if (cpu_eff->compatible == NULL) { + pr_warn("%s: Unknown CPU type\n", cn->full_name); + continue; + } + + rate = of_get_property(cn, "clock-frequency", &len); + if (!rate || len != 4) { + pr_err("%s: Missing clock-frequency property\n", + cn->full_name); + continue; + } + + capacity = ((be32_to_cpup(rate)) >> 20) * cpu_eff->efficiency; + + /* Save min capacity of the system */ + if (capacity < min_capacity) + min_capacity = capacity; + + /* Save max capacity of the system */ + if (capacity > max_capacity) + max_capacity = capacity; + + cpu_capacity(cpu) = capacity; + } + + /* If min and max capacities are equal we bypass the update of the + * cpu_scale because all CPUs have the same capacity. Otherwise, we + * compute a middle_capacity factor that will ensure that the capacity + * of an 'average' CPU of the system will be as close as possible to + * SCHED_POWER_SCALE, which is the default value, but with the + * constraint explained near table_efficiency[]. + */ + if (min_capacity == max_capacity) + return; + else if (4 * max_capacity < (3 * (max_capacity + min_capacity))) + middle_capacity = (min_capacity + max_capacity) + >> (SCHED_POWER_SHIFT+1); + else + middle_capacity = ((max_capacity / 3) + >> (SCHED_POWER_SHIFT-1)) + 1; + +} + +/* + * Look for a customed capacity of a CPU in the cpu_topo_data table during the + * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the + * function returns directly for SMP system. + */ +static void update_cpu_power(unsigned int cpu) +{ + if (!cpu_capacity(cpu)) + return; + + set_power_scale(cpu, cpu_capacity(cpu) / middle_capacity); + + pr_info("CPU%u: update cpu_power %lu\n", + cpu, arch_scale_freq_power(NULL, cpu)); }

#else static inline void parse_dt_topology(void) {} +static inline void update_cpu_power(unsigned int cpuid) {} #endif

/* @@ -210,6 +351,8 @@ void store_cpu_topology(unsigned int cpuid) pr_info("CPU%u: No topology information configured\n", cpuid); else update_siblings_masks(cpuid); + + update_cpu_power(cpuid); }

/* @@ -229,6 +372,8 @@ void __init init_cpu_topology(void) cpu_topo->socket_id = -1; cpumask_clear(&cpu_topo->core_sibling); cpumask_clear(&cpu_topo->thread_sibling); + + set_power_scale(cpu, SCHED_POWER_SCALE); }

parse_dt_topology();