/*
 * 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/acpi.h>
#include <linux/arch_topology.h>
#include <linux/cacheinfo.h>
#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/sched/topology.h>
#include <linux/slab.h>
#include <linux/smp.h>
#include <linux/string.h>

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

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;

	cpu = of_cpu_node_to_id(cpu_node);
	if (cpu >= 0)
		topology_parse_cpu_capacity(cpu_node, cpu);
	else
		pr_crit("Unable to find CPU node for %pOF\n", cpu_node);

	of_node_put(cpu_node);
	return cpu;
}

static int __init parse_core(struct device_node *core, int package_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].package_id = package_id;
				cpu_topology[cpu].core_id = core_id;
				cpu_topology[cpu].thread_id = i;
			} else {
				pr_err("%pOF: Can't get CPU for thread\n",
				       t);
				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("%pOF: Core has both threads and CPU\n",
			       core);
			return -EINVAL;
		}

		cpu_topology[cpu].package_id = package_id;
		cpu_topology[cpu].core_id = core_id;
	} else if (leaf) {
		pr_err("%pOF: Can't get CPU for leaf core\n", core);
		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 package_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("%pOF: cpu-map children should be clusters\n",
				       c);
				of_node_put(c);
				return -EINVAL;
			}

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

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

	if (leaf && !has_cores)
		pr_warn("%pOF: empty cluster\n", cluster);

	if (leaf)
		package_id++;

	return 0;
}

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;

	topology_normalize_cpu_scale();

	/*
	 * 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].package_id == -1)
			ret = -EINVAL;

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

/*
 * cpu topology table
 */
struct cpu_topology cpu_topology[NR_CPUS];
EXPORT_SYMBOL_GPL(cpu_topology);

const struct cpumask *cpu_coregroup_mask(int cpu)
{
	const cpumask_t *core_mask = cpumask_of_node(cpu_to_node(cpu));

	/* Find the smaller of NUMA, core or LLC siblings */
	if (cpumask_subset(&cpu_topology[cpu].core_sibling, core_mask)) {
		/* not numa in package, lets use the package siblings */
		core_mask = &cpu_topology[cpu].core_sibling;
	}
	if (cpu_topology[cpu].llc_id != -1) {
		if (cpumask_subset(&cpu_topology[cpu].llc_sibling, core_mask))
			core_mask = &cpu_topology[cpu].llc_sibling;
	}

	return core_mask;
}

static void update_siblings_masks(unsigned int cpuid)
{
	struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
	int cpu;

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

		if (cpuid_topo->llc_id == cpu_topo->llc_id) {
			cpumask_set_cpu(cpu, &cpuid_topo->llc_sibling);
			cpumask_set_cpu(cpuid, &cpu_topo->llc_sibling);
		}

		if (cpuid_topo->package_id != cpu_topo->package_id)
			continue;

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

void store_cpu_topology(unsigned int cpuid)
{
	struct cpu_topology *cpuid_topo = &cpu_topology[cpuid];
	u64 mpidr;

	if (cpuid_topo->package_id != -1)
		goto topology_populated;

	mpidr = read_cpuid_mpidr();

	/* Uniprocessor systems can rely on default topology values */
	if (mpidr & MPIDR_UP_BITMASK)
		return;

	/*
	 * This would be the place to create cpu topology based on MPIDR.
	 *
	 * However, it cannot be trusted to depict the actual topology; some
	 * pieces of the architecture enforce an artificial cap on Aff0 values
	 * (e.g. GICv3's ICC_SGI1R_EL1 limits it to 15), leading to an
	 * artificial cycling of Aff1, Aff2 and Aff3 values. IOW, these end up
	 * having absolutely no relationship to the actual underlying system
	 * topology, and cannot be reasonably used as core / package ID.
	 *
	 * If the MT bit is set, Aff0 *could* be used to define a thread ID, but
	 * we still wouldn't be able to obtain a sane core ID. This means we
	 * need to entirely ignore MPIDR for any topology deduction.
	 */
	cpuid_topo->thread_id  = -1;
	cpuid_topo->core_id    = cpuid;
	cpuid_topo->package_id = cpu_to_node(cpuid);

	pr_debug("CPU%u: cluster %d core %d thread %d mpidr %#016llx\n",
		 cpuid, cpuid_topo->package_id, cpuid_topo->core_id,
		 cpuid_topo->thread_id, mpidr);

topology_populated:
	update_siblings_masks(cpuid);
}

static void clear_cpu_topology(int cpu)
{
	struct cpu_topology *cpu_topo = &cpu_topology[cpu];

	cpumask_clear(&cpu_topo->llc_sibling);
	cpumask_set_cpu(cpu, &cpu_topo->llc_sibling);

	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_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->package_id = -1;
		cpu_topo->llc_id = -1;

		clear_cpu_topology(cpu);
	}
}

void remove_cpu_topology(unsigned int cpu)
{
	int sibling;

	for_each_cpu(sibling, topology_core_cpumask(cpu))
		cpumask_clear_cpu(cpu, topology_core_cpumask(sibling));
	for_each_cpu(sibling, topology_sibling_cpumask(cpu))
		cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling));
	for_each_cpu(sibling, topology_llc_cpumask(cpu))
		cpumask_clear_cpu(cpu, topology_llc_cpumask(sibling));

	clear_cpu_topology(cpu);
}

#ifdef CONFIG_ACPI
static bool __init acpi_cpu_is_threaded(int cpu)
{
	int is_threaded = acpi_pptt_cpu_is_thread(cpu);

	/*
	 * if the PPTT doesn't have thread information, assume a homogeneous
	 * machine and return the current CPU's thread state.
	 */
	if (is_threaded < 0)
		is_threaded = read_cpuid_mpidr() & MPIDR_MT_BITMASK;

	return !!is_threaded;
}

/*
 * Propagate the topology information of the processor_topology_node tree to the
 * cpu_topology array.
 */
static int __init parse_acpi_topology(void)
{
	int cpu, topology_id;

	for_each_possible_cpu(cpu) {
		int i, cache_id;

		topology_id = find_acpi_cpu_topology(cpu, 0);
		if (topology_id < 0)
			return topology_id;

		if (acpi_cpu_is_threaded(cpu)) {
			cpu_topology[cpu].thread_id = topology_id;
			topology_id = find_acpi_cpu_topology(cpu, 1);
			cpu_topology[cpu].core_id   = topology_id;
		} else {
			cpu_topology[cpu].thread_id  = -1;
			cpu_topology[cpu].core_id    = topology_id;
		}
		topology_id = find_acpi_cpu_topology_package(cpu);
		cpu_topology[cpu].package_id = topology_id;

		i = acpi_find_last_cache_level(cpu);

		if (i > 0) {
			/*
			 * this is the only part of cpu_topology that has
			 * a direct relationship with the cache topology
			 */
			cache_id = find_acpi_cpu_cache_topology(cpu, i);
			if (cache_id > 0)
				cpu_topology[cpu].llc_id = cache_id;
		}
	}

	return 0;
}

#else
static inline int __init parse_acpi_topology(void)
{
	return -EINVAL;
}
#endif

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 (!acpi_disabled && parse_acpi_topology())
		reset_cpu_topology();
	else if (of_have_populated_dt() && parse_dt_topology())
		reset_cpu_topology();
}