/*
 * arch/arm64/kernel/topology.c
 *
 * Copyright (C) 2011,2013,2014 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/of.h>
#include <linux/sched.h>
#include <linux/slab.h>

#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;
}

static int __init get_cpu_for_node(struct device_node *node)
{
	struct device_node *cpu_node;
	int cpu;

	cpu_node = of_parse_phandle(node, "cpu", 0);
	if (!cpu_node)
		return -1;

	for_each_possible_cpu(cpu) {
		if (of_get_cpu_node(cpu, NULL) == cpu_node) {
			of_node_put(cpu_node);
			return cpu;
		}
	}

	pr_crit("Unable to find CPU node for %s\n", cpu_node->full_name);

	of_node_put(cpu_node);
	return -1;
}

static int __init parse_core(struct device_node *core, int cluster_id,
			     int core_id)
{
	char name[10];
	bool leaf = true;
	int i = 0;
	int cpu;
	struct device_node *t;

	do {
		snprintf(name, sizeof(name), "thread%d", i);
		t = of_get_child_by_name(core, name);
		if (t) {
			leaf = false;
			cpu = get_cpu_for_node(t);
			if (cpu >= 0) {
				cpu_topology[cpu].cluster_id = cluster_id;
				cpu_topology[cpu].core_id = core_id;
				cpu_topology[cpu].thread_id = i;
			} else {
				pr_err("%s: Can't get CPU for thread\n",
				       t->full_name);
				of_node_put(t);
				return -EINVAL;
			}
			of_node_put(t);
		}
		i++;
	} while (t);

	cpu = get_cpu_for_node(core);
	if (cpu >= 0) {
		if (!leaf) {
			pr_err("%s: Core has both threads and CPU\n",
			       core->full_name);
			return -EINVAL;
		}

		cpu_topology[cpu].cluster_id = cluster_id;
		cpu_topology[cpu].core_id = core_id;
	} else if (leaf) {
		pr_err("%s: Can't get CPU for leaf core\n", core->full_name);
		return -EINVAL;
	}

	return 0;
}

static int __init parse_cluster(struct device_node *cluster, int depth)
{
	char name[10];
	bool leaf = true;
	bool has_cores = false;
	struct device_node *c;
	static int cluster_id __initdata;
	int core_id = 0;
	int i, ret;

	/*
	 * First check for child clusters; we currently ignore any
	 * information about the nesting of clusters and present the
	 * scheduler with a flat list of them.
	 */
	i = 0;
	do {
		snprintf(name, sizeof(name), "cluster%d", i);
		c = of_get_child_by_name(cluster, name);
		if (c) {
			leaf = false;
			ret = parse_cluster(c, depth + 1);
			of_node_put(c);
			if (ret != 0)
				return ret;
		}
		i++;
	} while (c);

	/* Now check for cores */
	i = 0;
	do {
		snprintf(name, sizeof(name), "core%d", i);
		c = of_get_child_by_name(cluster, name);
		if (c) {
			has_cores = true;

			if (depth == 0) {
				pr_err("%s: cpu-map children should be clusters\n",
				       c->full_name);
				of_node_put(c);
				return -EINVAL;
			}

			if (leaf) {
				ret = parse_core(c, cluster_id, core_id++);
			} else {
				pr_err("%s: Non-leaf cluster with core %s\n",
				       cluster->full_name, name);
				ret = -EINVAL;
			}

			of_node_put(c);
			if (ret != 0)
				return ret;
		}
		i++;
	} while (c);

	if (leaf && !has_cores)
		pr_warn("%s: empty cluster\n", cluster->full_name);

	if (leaf)
		cluster_id++;

	return 0;
}

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[] = {
	{ "arm,cortex-a57", 3891 },
	{ "arm,cortex-a53", 2048 },
	{ 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 int __init parse_dt_topology(void)
{
	struct device_node *cn, *map;
	int ret = 0;
	int cpu;

	cn = of_find_node_by_path("/cpus");
	if (!cn) {
		pr_err("No CPU information found in DT\n");
		return 0;
	}

	/*
	 * When topology is provided cpu-map is essentially a root
	 * cluster with restricted subnodes.
	 */
	map = of_get_child_by_name(cn, "cpu-map");
	if (!map)
		goto out;

	ret = parse_cluster(map, 0);
	if (ret != 0)
		goto out_map;

	/*
	 * Check that all cores are in the topology; the SMP code will
	 * only mark cores described in the DT as possible.
	 */
	for_each_possible_cpu(cpu) {
		if (cpu_topology[cpu].cluster_id == -1) {
			pr_err("CPU%d: No topology information specified\n",
			       cpu);
			ret = -EINVAL;
		}
	}

out_map:
	of_node_put(map);
out:
	of_node_put(cn);
	return ret;
}

static void __init parse_dt_cpu_power(void)
{
	const struct cpu_efficiency *cpu_eff;
	struct device_node *cn;
	unsigned long min_capacity = ULONG_MAX;
	unsigned long max_capacity = 0;
	unsigned long capacity = 0;
	int cpu;

	__cpu_capacity = kcalloc(nr_cpu_ids, sizeof(*__cpu_capacity),
				 GFP_NOWAIT);

	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;
		}

		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));
}

/*
 * cpu topology table
 */
struct cpu_topology 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 cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
	int cpu;

	if (cpuid_topo->cluster_id == -1) {
		/*
		 * DT does not contain topology information for this cpu.
		 */
		pr_debug("CPU%u: No topology information configured\n", cpuid);
		return;
	}

	/* update core and thread sibling masks */
	for_each_possible_cpu(cpu) {
		cpu_topo = &cpu_topology[cpu];

		if (cpuid_topo->cluster_id != cpu_topo->cluster_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);
	}
}

void store_cpu_topology(unsigned int cpuid)
{
	update_siblings_masks(cpuid);
	update_cpu_power(cpuid);
}

#ifdef CONFIG_SCHED_HMP

/*
 * Retrieve logical cpu index corresponding to a given MPIDR[23:0]
 *  - mpidr: MPIDR[23:0] to be used for the look-up
 *
 * Returns the cpu logical index or -EINVAL on look-up error
 */
static inline int get_logical_index(u32 mpidr)
{
	int cpu;
	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
		if (cpu_logical_map(cpu) == mpidr)
			return cpu;
	return -EINVAL;
}

static const char * const little_cores[] = {
	"arm,cortex-a53",
	NULL,
};

static bool is_little_cpu(struct device_node *cn)
{
	const char * const *lc;
	for (lc = little_cores; *lc; lc++)
		if (of_device_is_compatible(cn, *lc))
			return true;
	return false;
}

void __init arch_get_fast_and_slow_cpus(struct cpumask *fast,
					struct cpumask *slow)
{
	struct device_node *cn = NULL;
	int cpu;

	cpumask_clear(fast);
	cpumask_clear(slow);

	/*
	 * Use the config options if they are given. This helps testing
	 * HMP scheduling on systems without a big.LITTLE architecture.
	 */
	if (strlen(CONFIG_HMP_FAST_CPU_MASK) && strlen(CONFIG_HMP_SLOW_CPU_MASK)) {
		if (cpulist_parse(CONFIG_HMP_FAST_CPU_MASK, fast))
			WARN(1, "Failed to parse HMP fast cpu mask!\n");
		if (cpulist_parse(CONFIG_HMP_SLOW_CPU_MASK, slow))
			WARN(1, "Failed to parse HMP slow cpu mask!\n");
		return;
	}

	/*
	 * Else, parse device tree for little cores.
	 */
	while ((cn = of_find_node_by_type(cn, "cpu"))) {

		const u32 *mpidr;
		int len;

		mpidr = of_get_property(cn, "reg", &len);
		if (!mpidr || len != 8) {
			pr_err("%s missing reg property\n", cn->full_name);
			continue;
		}

		cpu = get_logical_index(be32_to_cpup(mpidr+1));
		if (cpu == -EINVAL) {
			pr_err("couldn't get logical index for mpidr %x\n",
							be32_to_cpup(mpidr+1));
			break;
		}

		if (is_little_cpu(cn))
			cpumask_set_cpu(cpu, slow);
		else
			cpumask_set_cpu(cpu, fast);
	}

	if (!cpumask_empty(fast) && !cpumask_empty(slow))
		return;

	/*
	 * We didn't find both big and little cores so let's call all cores
	 * fast as this will keep the system running, with all cores being
	 * treated equal.
	 */
	cpumask_setall(fast);
	cpumask_clear(slow);
}

struct cpumask hmp_slow_cpu_mask;

void __init arch_get_hmp_domains(struct list_head *hmp_domains_list)
{
	struct cpumask hmp_fast_cpu_mask;
	struct hmp_domain *domain;

	arch_get_fast_and_slow_cpus(&hmp_fast_cpu_mask, &hmp_slow_cpu_mask);

	/*
	 * Initialize hmp_domains
	 * Must be ordered with respect to compute capacity.
	 * Fastest domain at head of list.
	 */
	if(!cpumask_empty(&hmp_slow_cpu_mask)) {
		domain = (struct hmp_domain *)
			kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
		cpumask_copy(&domain->possible_cpus, &hmp_slow_cpu_mask);
		cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
		list_add(&domain->hmp_domains, hmp_domains_list);
	}
	domain = (struct hmp_domain *)
		kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
	cpumask_copy(&domain->possible_cpus, &hmp_fast_cpu_mask);
	cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
	list_add(&domain->hmp_domains, hmp_domains_list);
}
#endif /* CONFIG_SCHED_HMP */

static void __init reset_cpu_topology(void)
{
	unsigned int cpu;

	for_each_possible_cpu(cpu) {
		struct cpu_topology *cpu_topo = &cpu_topology[cpu];

		cpu_topo->thread_id = -1;
		cpu_topo->core_id = 0;
		cpu_topo->cluster_id = -1;

		cpumask_clear(&cpu_topo->core_sibling);
		cpumask_set_cpu(cpu, &cpu_topo->core_sibling);
		cpumask_clear(&cpu_topo->thread_sibling);
		cpumask_set_cpu(cpu, &cpu_topo->thread_sibling);
	}
}

static void __init reset_cpu_power(void)
{
	unsigned int cpu;

	for_each_possible_cpu(cpu)
		set_power_scale(cpu, SCHED_POWER_SCALE);
}

void __init init_cpu_topology(void)
{
	reset_cpu_topology();

	/*
	 * Discard anything that was parsed if we hit an error so we
	 * don't use partial information.
	 */
	if (parse_dt_topology())
		reset_cpu_topology();

	reset_cpu_power();
	parse_dt_cpu_power();
}