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/cpufreq.h>
#include <linux/cpumask.h>
#include <linux/export.h>
#include <linux/init.h>
#include <linux/percpu.h>
#include <linux/node.h>
#include <linux/nodemask.h>
#include <linux/of.h>
#include <linux/sched.h>
#include <linux/sched/topology.h>
#include <linux/slab.h>
#include <linux/string.h>

#include <asm/cpu.h>
#include <asm/cputype.h>
#include <asm/topology.h>

/*
 * cpu capacity scale management
 */

/*
 * cpu capacity 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_capacity 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_capacity 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_capacity can be
 * 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)
{
	return per_cpu(cpu_scale, cpu);
}

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;
	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_CAPACITY_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_CAPACITY_SCALE value for cpu_scale.
 */
static const struct cpu_efficiency table_efficiency[] = {
	{"arm,cortex-a15", 3891},
	{"arm,cortex-a7",  2048},
	{NULL, },
};

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
 * (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_capacity field such that an
 * 'average' CPU is of middle capacity. Also see the comments near
 * table_efficiency[] and update_cpu_capacity().
 */
static void __init parse_dt_topology(void)
{
	const struct cpu_efficiency *cpu_eff;
	struct device_node *cn = NULL;
	unsigned long min_capacity = ULONG_MAX;
	unsigned long max_capacity = 0;
	unsigned long capacity = 0;
	int cpu = 0;

	__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;

		/* 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;
		}

		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;

		if (cpu_eff->compatible == NULL)
			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 equals, 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_CAPACITY_SCALE, which is the default value, but with the
	 * constraint explained near table_efficiency[].
	 */
	if (4*max_capacity < (3*(max_capacity + min_capacity)))
		middle_capacity = (min_capacity + max_capacity)
				>> (SCHED_CAPACITY_SHIFT+1);
	else
		middle_capacity = ((max_capacity / 3)
				>> (SCHED_CAPACITY_SHIFT-1)) + 1;

	if (cap_from_dt && !cap_parsing_failed)
		normalize_cpu_capacity();
}

/*
 * Look for a customed capacity of a CPU in the cpu_capacity 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_capacity(unsigned int cpu)
{
	if (!cpu_capacity(cpu) || cap_from_dt)
		return;

	set_capacity_scale(cpu, cpu_capacity(cpu) / middle_capacity);

	pr_info("CPU%u: update cpu_capacity %lu\n",
		cpu, arch_scale_cpu_capacity(NULL, cpu));
}

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

 /*
 * 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;
}

/*
 * The current assumption is that we can power gate each core independently.
 * This will be superseded by DT binding once available.
 */
const struct cpumask *cpu_corepower_mask(int cpu)
{
	return &cpu_topology[cpu].thread_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();
}

/*
 * 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;

	/* 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_AFFINITY_LEVEL(mpidr, 0);
			cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 1);
			cpuid_topo->socket_id = MPIDR_AFFINITY_LEVEL(mpidr, 2);
		} else {
			/* largely independent cores */
			cpuid_topo->thread_id = -1;
			cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
			cpuid_topo->socket_id = MPIDR_AFFINITY_LEVEL(mpidr, 1);
		}
	} 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_siblings_masks(cpuid);

	update_cpu_capacity(cpuid);

	pr_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);
}

static inline int cpu_corepower_flags(void)
{
	return SD_SHARE_PKG_RESOURCES  | SD_SHARE_POWERDOMAIN;
}

static struct sched_domain_topology_level arm_topology[] = {
#ifdef CONFIG_SCHED_MC
	{ cpu_corepower_mask, cpu_corepower_flags, SD_INIT_NAME(GMC) },
	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
#endif
	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
	{ NULL, },
};

/*
 * 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 capacity */
	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();

	parse_dt_topology();

	/* Set scheduler topology descriptor */
	set_sched_topology(arm_topology);
}