b29c6ef7bb
Even though aperfmperf_snapshot_khz() caches the samples.khz value to return if called again in a sufficiently short time, its caller, arch_freq_get_on_cpu(), still uses smp_call_function_single() to run it which may allow user space to trigger an IPI storm by reading from the scaling_cur_freq cpufreq sysfs file in a tight loop. To avoid that, move the decision on whether or not to return the cached samples.khz value to arch_freq_get_on_cpu(). This change was part of commit941f5f0f6e("x86: CPU: Fix up "cpu MHz" in /proc/cpuinfo"), but it was not the reason for the revert and it remains applicable. Fixes:4815d3c56d(cpufreq: x86: Make scaling_cur_freq behave more as expected) Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Reviewed-by: WANG Chao <chao.wang@ucloud.cn> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
98 lines
2.2 KiB
C
98 lines
2.2 KiB
C
/*
|
|
* x86 APERF/MPERF KHz calculation for
|
|
* /sys/.../cpufreq/scaling_cur_freq
|
|
*
|
|
* Copyright (C) 2017 Intel Corp.
|
|
* Author: Len Brown <len.brown@intel.com>
|
|
*
|
|
* This file is licensed under GPLv2.
|
|
*/
|
|
|
|
#include <linux/delay.h>
|
|
#include <linux/ktime.h>
|
|
#include <linux/math64.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/smp.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 20
|
|
#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);
|
|
ktime_t now = ktime_get();
|
|
s64 time_delta = ktime_ms_delta(now, s->time);
|
|
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 = now;
|
|
s->aperf = aperf;
|
|
s->mperf = mperf;
|
|
|
|
/* If the previous iteration was too long ago, discard it. */
|
|
if (time_delta > APERFMPERF_STALE_THRESHOLD_MS)
|
|
s->khz = 0;
|
|
else
|
|
s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta);
|
|
}
|
|
|
|
unsigned int arch_freq_get_on_cpu(int cpu)
|
|
{
|
|
s64 time_delta;
|
|
unsigned int khz;
|
|
|
|
if (!cpu_khz)
|
|
return 0;
|
|
|
|
if (!static_cpu_has(X86_FEATURE_APERFMPERF))
|
|
return 0;
|
|
|
|
/* Don't bother re-computing within the cache threshold time. */
|
|
time_delta = ktime_ms_delta(ktime_get(), per_cpu(samples.time, cpu));
|
|
khz = per_cpu(samples.khz, cpu);
|
|
if (khz && time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
|
|
return khz;
|
|
|
|
smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1);
|
|
khz = per_cpu(samples.khz, cpu);
|
|
if (khz)
|
|
return khz;
|
|
|
|
msleep(APERFMPERF_REFRESH_DELAY_MS);
|
|
smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1);
|
|
|
|
return per_cpu(samples.khz, cpu);
|
|
}
|