mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
cc9e303c91
Since commit 7d5905dc14 ("x86 / CPU: Always show current CPU frequency
in /proc/cpuinfo") open and read of /proc/cpuinfo sends IPI to all CPUs.
Many applications read /proc/cpuinfo at the start for trivial reasons like
counting cores or detecting cpu features. While sensitive workloads like
DPDK network polling don't like any interrupts.
Integrates this feature with cpu isolation and do not send IPIs to CPUs
without housekeeping flag HK_FLAG_MISC (set by nohz_full).
Code that requests cpu frequency like show_cpuinfo() falls back to the last
frequency set by the cpufreq driver if this method returns 0.
Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Len Brown <len.brown@intel.com>
Cc: Frederic Weisbecker <frederic@kernel.org>
Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Link: https://lkml.kernel.org/r/155790354043.1104.15333317408370209.stgit@buzz
138 lines
2.9 KiB
C
138 lines
2.9 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* x86 APERF/MPERF KHz calculation for
|
|
* /sys/.../cpufreq/scaling_cur_freq
|
|
*
|
|
* Copyright (C) 2017 Intel Corp.
|
|
* Author: Len Brown <len.brown@intel.com>
|
|
*/
|
|
|
|
#include <linux/delay.h>
|
|
#include <linux/ktime.h>
|
|
#include <linux/math64.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/cpufreq.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/sched/isolation.h>
|
|
|
|
#include "cpu.h"
|
|
|
|
struct aperfmperf_sample {
|
|
unsigned int khz;
|
|
ktime_t time;
|
|
u64 aperf;
|
|
u64 mperf;
|
|
};
|
|
|
|
static DEFINE_PER_CPU(struct aperfmperf_sample, samples);
|
|
|
|
#define APERFMPERF_CACHE_THRESHOLD_MS 10
|
|
#define APERFMPERF_REFRESH_DELAY_MS 10
|
|
#define APERFMPERF_STALE_THRESHOLD_MS 1000
|
|
|
|
/*
|
|
* aperfmperf_snapshot_khz()
|
|
* On the current CPU, snapshot APERF, MPERF, and jiffies
|
|
* unless we already did it within 10ms
|
|
* calculate kHz, save snapshot
|
|
*/
|
|
static void aperfmperf_snapshot_khz(void *dummy)
|
|
{
|
|
u64 aperf, aperf_delta;
|
|
u64 mperf, mperf_delta;
|
|
struct aperfmperf_sample *s = this_cpu_ptr(&samples);
|
|
unsigned long flags;
|
|
|
|
local_irq_save(flags);
|
|
rdmsrl(MSR_IA32_APERF, aperf);
|
|
rdmsrl(MSR_IA32_MPERF, mperf);
|
|
local_irq_restore(flags);
|
|
|
|
aperf_delta = aperf - s->aperf;
|
|
mperf_delta = mperf - s->mperf;
|
|
|
|
/*
|
|
* There is no architectural guarantee that MPERF
|
|
* increments faster than we can read it.
|
|
*/
|
|
if (mperf_delta == 0)
|
|
return;
|
|
|
|
s->time = ktime_get();
|
|
s->aperf = aperf;
|
|
s->mperf = mperf;
|
|
s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta);
|
|
}
|
|
|
|
static bool aperfmperf_snapshot_cpu(int cpu, ktime_t now, bool wait)
|
|
{
|
|
s64 time_delta = ktime_ms_delta(now, per_cpu(samples.time, cpu));
|
|
|
|
/* Don't bother re-computing within the cache threshold time. */
|
|
if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
|
|
return true;
|
|
|
|
smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, wait);
|
|
|
|
/* Return false if the previous iteration was too long ago. */
|
|
return time_delta <= APERFMPERF_STALE_THRESHOLD_MS;
|
|
}
|
|
|
|
unsigned int aperfmperf_get_khz(int cpu)
|
|
{
|
|
if (!cpu_khz)
|
|
return 0;
|
|
|
|
if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
|
|
return 0;
|
|
|
|
if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
|
|
return 0;
|
|
|
|
aperfmperf_snapshot_cpu(cpu, ktime_get(), true);
|
|
return per_cpu(samples.khz, cpu);
|
|
}
|
|
|
|
void arch_freq_prepare_all(void)
|
|
{
|
|
ktime_t now = ktime_get();
|
|
bool wait = false;
|
|
int cpu;
|
|
|
|
if (!cpu_khz)
|
|
return;
|
|
|
|
if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
|
|
return;
|
|
|
|
for_each_online_cpu(cpu) {
|
|
if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
|
|
continue;
|
|
if (!aperfmperf_snapshot_cpu(cpu, now, false))
|
|
wait = true;
|
|
}
|
|
|
|
if (wait)
|
|
msleep(APERFMPERF_REFRESH_DELAY_MS);
|
|
}
|
|
|
|
unsigned int arch_freq_get_on_cpu(int cpu)
|
|
{
|
|
if (!cpu_khz)
|
|
return 0;
|
|
|
|
if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
|
|
return 0;
|
|
|
|
if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
|
|
return 0;
|
|
|
|
if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true))
|
|
return per_cpu(samples.khz, cpu);
|
|
|
|
msleep(APERFMPERF_REFRESH_DELAY_MS);
|
|
smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1);
|
|
|
|
return per_cpu(samples.khz, cpu);
|
|
}
|