diff options
Diffstat (limited to 'arch/arm/kernel/topology.c')
| -rw-r--r-- | arch/arm/kernel/topology.c | 220 |
1 files changed, 219 insertions, 1 deletions
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c index ec279d161b32..ebf47d91b804 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -12,6 +12,7 @@ */ #include <linux/cpu.h> +#include <linux/cpufreq.h> #include <linux/cpumask.h> #include <linux/export.h> #include <linux/init.h> @@ -21,7 +22,9 @@ #include <linux/of.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/string.h> +#include <asm/cpu.h> #include <asm/cputype.h> #include <asm/topology.h> @@ -41,6 +44,7 @@ * updated during this sequence. */ static DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE; +static DEFINE_MUTEX(cpu_scale_mutex); unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) { @@ -52,6 +56,65 @@ static void set_capacity_scale(unsigned int cpu, unsigned long capacity) per_cpu(cpu_scale, cpu) = capacity; } +#ifdef CONFIG_PROC_SYSCTL +static ssize_t cpu_capacity_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct cpu *cpu = container_of(dev, struct cpu, dev); + + return sprintf(buf, "%lu\n", + arch_scale_cpu_capacity(NULL, cpu->dev.id)); +} + +static ssize_t cpu_capacity_store(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t count) +{ + struct cpu *cpu = container_of(dev, struct cpu, dev); + int this_cpu = cpu->dev.id, i; + unsigned long new_capacity; + ssize_t ret; + + if (count) { + ret = kstrtoul(buf, 0, &new_capacity); + if (ret) + return ret; + if (new_capacity > SCHED_CAPACITY_SCALE) + return -EINVAL; + + mutex_lock(&cpu_scale_mutex); + for_each_cpu(i, &cpu_topology[this_cpu].core_sibling) + set_capacity_scale(i, new_capacity); + mutex_unlock(&cpu_scale_mutex); + } + + return count; +} + +static DEVICE_ATTR_RW(cpu_capacity); + +static int register_cpu_capacity_sysctl(void) +{ + int i; + struct device *cpu; + + for_each_possible_cpu(i) { + cpu = get_cpu_device(i); + if (!cpu) { + pr_err("%s: too early to get CPU%d device!\n", + __func__, i); + continue; + } + device_create_file(cpu, &dev_attr_cpu_capacity); + } + + return 0; +} +subsys_initcall(register_cpu_capacity_sysctl); +#endif + #ifdef CONFIG_OF struct cpu_efficiency { const char *compatible; @@ -78,6 +141,146 @@ static unsigned long *__cpu_capacity; #define cpu_capacity(cpu) __cpu_capacity[cpu] static unsigned long middle_capacity = 1; +static bool cap_from_dt = true; +static u32 *raw_capacity; +static bool cap_parsing_failed; +static u32 capacity_scale; + +static int __init parse_cpu_capacity(struct device_node *cpu_node, int cpu) +{ + int ret = 1; + u32 cpu_capacity; + + if (cap_parsing_failed) + return !ret; + + ret = of_property_read_u32(cpu_node, + "capacity-dmips-mhz", + &cpu_capacity); + if (!ret) { + if (!raw_capacity) { + raw_capacity = kcalloc(num_possible_cpus(), + sizeof(*raw_capacity), + GFP_KERNEL); + if (!raw_capacity) { + pr_err("cpu_capacity: failed to allocate memory for raw capacities\n"); + cap_parsing_failed = true; + return !ret; + } + } + capacity_scale = max(cpu_capacity, capacity_scale); + raw_capacity[cpu] = cpu_capacity; + pr_debug("cpu_capacity: %s cpu_capacity=%u (raw)\n", + cpu_node->full_name, raw_capacity[cpu]); + } else { + if (raw_capacity) { + pr_err("cpu_capacity: missing %s raw capacity\n", + cpu_node->full_name); + pr_err("cpu_capacity: partial information: fallback to 1024 for all CPUs\n"); + } + cap_parsing_failed = true; + kfree(raw_capacity); + } + + return !ret; +} + +static void normalize_cpu_capacity(void) +{ + u64 capacity; + int cpu; + + if (!raw_capacity || cap_parsing_failed) + return; + + pr_debug("cpu_capacity: capacity_scale=%u\n", capacity_scale); + mutex_lock(&cpu_scale_mutex); + for_each_possible_cpu(cpu) { + capacity = (raw_capacity[cpu] << SCHED_CAPACITY_SHIFT) + / capacity_scale; + set_capacity_scale(cpu, capacity); + pr_debug("cpu_capacity: CPU%d cpu_capacity=%lu\n", + cpu, arch_scale_cpu_capacity(NULL, cpu)); + } + mutex_unlock(&cpu_scale_mutex); +} + +#ifdef CONFIG_CPU_FREQ +static cpumask_var_t cpus_to_visit; +static bool cap_parsing_done; +static void parsing_done_workfn(struct work_struct *work); +static DECLARE_WORK(parsing_done_work, parsing_done_workfn); + +static int +init_cpu_capacity_callback(struct notifier_block *nb, + unsigned long val, + void *data) +{ + struct cpufreq_policy *policy = data; + int cpu; + + if (cap_parsing_failed || cap_parsing_done) + return 0; + + switch (val) { + case CPUFREQ_NOTIFY: + pr_debug("cpu_capacity: init cpu capacity for CPUs [%*pbl] (to_visit=%*pbl)\n", + cpumask_pr_args(policy->related_cpus), + cpumask_pr_args(cpus_to_visit)); + cpumask_andnot(cpus_to_visit, + cpus_to_visit, + policy->related_cpus); + for_each_cpu(cpu, policy->related_cpus) { + raw_capacity[cpu] = arch_scale_cpu_capacity(NULL, cpu) * + policy->cpuinfo.max_freq / 1000UL; + capacity_scale = max(raw_capacity[cpu], capacity_scale); + } + if (cpumask_empty(cpus_to_visit)) { + normalize_cpu_capacity(); + kfree(raw_capacity); + pr_debug("cpu_capacity: parsing done\n"); + cap_parsing_done = true; + schedule_work(&parsing_done_work); + } + } + return 0; +} + +static struct notifier_block init_cpu_capacity_notifier = { + .notifier_call = init_cpu_capacity_callback, +}; + +static int __init register_cpufreq_notifier(void) +{ + if (cap_parsing_failed) + return -EINVAL; + + if (!alloc_cpumask_var(&cpus_to_visit, GFP_KERNEL)) { + pr_err("cpu_capacity: failed to allocate memory for cpus_to_visit\n"); + return -ENOMEM; + } + cpumask_copy(cpus_to_visit, cpu_possible_mask); + + return cpufreq_register_notifier(&init_cpu_capacity_notifier, + CPUFREQ_POLICY_NOTIFIER); +} +core_initcall(register_cpufreq_notifier); + +static void parsing_done_workfn(struct work_struct *work) +{ + cpufreq_unregister_notifier(&init_cpu_capacity_notifier, + CPUFREQ_POLICY_NOTIFIER); +} + +#else +static int __init free_raw_capacity(void) +{ + kfree(raw_capacity); + + return 0; +} +core_initcall(free_raw_capacity); +#endif /* * Iterate all CPUs' descriptor in DT and compute the efficiency @@ -99,6 +302,12 @@ static void __init parse_dt_topology(void) __cpu_capacity = kcalloc(nr_cpu_ids, sizeof(*__cpu_capacity), GFP_NOWAIT); + cn = of_find_node_by_path("/cpus"); + if (!cn) { + pr_err("No CPU information found in DT\n"); + return; + } + for_each_possible_cpu(cpu) { const u32 *rate; int len; @@ -110,6 +319,13 @@ static void __init parse_dt_topology(void) continue; } + if (parse_cpu_capacity(cn, cpu)) { + of_node_put(cn); + continue; + } + + cap_from_dt = false; + for (cpu_eff = table_efficiency; cpu_eff->compatible; cpu_eff++) if (of_device_is_compatible(cn, cpu_eff->compatible)) break; @@ -151,6 +367,8 @@ static void __init parse_dt_topology(void) middle_capacity = ((max_capacity / 3) >> (SCHED_CAPACITY_SHIFT-1)) + 1; + if (cap_from_dt && !cap_parsing_failed) + normalize_cpu_capacity(); } /* @@ -160,7 +378,7 @@ static void __init parse_dt_topology(void) */ static void update_cpu_capacity(unsigned int cpu) { - if (!cpu_capacity(cpu)) + if (!cpu_capacity(cpu) || cap_from_dt) return; set_capacity_scale(cpu, cpu_capacity(cpu) / middle_capacity); |
