linux/linux-5.18.11/arch/arm/kernel/topology.c

246 lines
6.8 KiB
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/arch_topology.h>
#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.
*/
#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;
/*
* 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);
for_each_possible_cpu(cpu) {
const __be32 *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 (topology_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("%pOF missing clock-frequency property\n", cn);
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)
topology_normalize_cpu_scale();
}
/*
* 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;
topology_set_cpu_scale(cpu, cpu_capacity(cpu) / middle_capacity);
pr_info("CPU%u: update cpu_capacity %lu\n",
cpu, topology_get_cpu_scale(cpu));
}
#else
static inline void parse_dt_topology(void) {}
static inline void update_cpu_capacity(unsigned int cpuid) {}
#endif
/*
* 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 cpu_topology *cpuid_topo = &cpu_topology[cpuid];
unsigned int mpidr;
if (cpuid_topo->package_id != -1)
goto topology_populated;
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->package_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->package_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->package_id = -1;
}
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].package_id, mpidr);
topology_populated:
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)
{
reset_cpu_topology();
smp_wmb();
parse_dt_topology();
}