x86/aperfmperf: Replace arch_freq_get_on_cpu()

Reading the current CPU frequency from /sys/..../scaling_cur_freq involves
in the worst case two IPIs due to the ad hoc sampling.

The frequency invariance infrastructure provides the APERF/MPERF samples
already. Utilize them and consolidate this with the /proc/cpuinfo readout.

The sample is considered valid for 20ms. So for idle or isolated NOHZ full
CPUs the function returns 0, which is matching the previous behaviour.

The resulting text size vs. the original APERF/MPERF plus the separate
frequency invariance code:

  text:		2411	->   723
  init.text:	   0	->   767

Signed-off-by: Thomas Gleixner <[email protected]>
Tested-by: Eric Dumazet <[email protected]>
Reviewed-by: Rafael J. Wysocki <[email protected]>
Acked-by: Peter Zijlstra (Intel) <[email protected]>
Acked-by: Paul E. McKenney <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: KAGA-KOKO

arch/x86/kernel/cpu/aperfmperf.c

@@ -36,98 +36,6 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct aperfmperf, cpu_samples) = {
 	.seq = SEQCNT_ZERO(cpu_samples.seq)
 };
 
-struct aperfmperf_sample {
-	unsigned int	khz;
-	atomic_t	scfpending;
-	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);
-	atomic_set_release(&s->scfpending, 0);
-}
-
-static bool aperfmperf_snapshot_cpu(int cpu, ktime_t now, bool wait)
-{
-	s64 time_delta = ktime_ms_delta(now, per_cpu(samples.time, cpu));
-	struct aperfmperf_sample *s = per_cpu_ptr(&samples, cpu);
-
-	/* Don't bother re-computing within the cache threshold time. */
-	if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
-		return true;
-
-	if (!atomic_xchg(&s->scfpending, 1) || wait)
-		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 arch_freq_get_on_cpu(int cpu)
-{
-	struct aperfmperf_sample *s = per_cpu_ptr(&samples, cpu);
-
-	if (!cpu_khz)
-		return 0;
-
-	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
-		return 0;
-
-	if (!housekeeping_cpu(cpu, HK_TYPE_MISC))
-		return 0;
-
-	if (rcu_is_idle_cpu(cpu))
-		return 0;
-
-	if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true))
-		return per_cpu(samples.khz, cpu);
-
-	msleep(APERFMPERF_REFRESH_DELAY_MS);
-	atomic_set(&s->scfpending, 1);
-	smp_mb(); /* ->scfpending before smp_call_function_single(). */
-	smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1);
-
-	return per_cpu(samples.khz, cpu);
-}
-
 static void init_counter_refs(void)
 {
 	u64 aperf, mperf;
@@ -494,7 +402,7 @@ void arch_scale_freq_tick(void)
  */
 #define MAX_SAMPLE_AGE	((unsigned long)HZ / 50)
 
-unsigned int aperfmperf_get_khz(int cpu)
+unsigned int arch_freq_get_on_cpu(int cpu)
 {
 	struct aperfmperf *s = per_cpu_ptr(&cpu_samples, cpu);
 	unsigned long last;

arch/x86/kernel/cpu/proc.c

@@ -84,7 +84,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		seq_printf(m, "microcode\t: 0x%x\n", c->microcode);
 
 	if (cpu_has(c, X86_FEATURE_TSC)) {
-		unsigned int freq = aperfmperf_get_khz(cpu);
+		unsigned int freq = arch_freq_get_on_cpu(cpu);
 
 		if (!freq)
 			freq = cpufreq_quick_get(cpu);