linux-pm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Rafael J. Wysocki" <rjw@rjwysocki.net>
To: x86@kernel.org, linux-pm@vger.kernel.org
Cc: Doug Smythies <dsmythies@telus.net>,
	'Len Brown' <lenb@kernel.org>,
	rafael@kernel.org, tglx@linutronix.de,
	srinivas.pandruvada@linux.intel.com, peterz@infradead.org,
	linux-kernel@vger.kernel.org, 'Len Brown' <len.brown@intel.com>
Subject: [PATCH] cpufreq: x86: Make scaling_cur_freq behave more as expected
Date: Fri, 28 Jul 2017 02:13:23 +0200	[thread overview]
Message-ID: <8753755.adRLzWASdR@aspire.rjw.lan> (raw)
In-Reply-To: <006201d30595$e0a23870$a1e6a950$@net>

From: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

After commit f8475cef9008 "x86: use common aperfmperf_khz_on_cpu() to
calculate KHz using APERF/MPERF" the scaling_cur_freq policy attribute
in sysfs only behaves as expected on x86 with APERF/MPERF registers
available when it is read from at least twice in a row.

The value returned by the first read may not be meaningful, because
the computations in there use cached values from the previous
aperfmperf_snapshot_khz() call which may be stale.  However, the
interface is expected to return meaningful values on every read,
including the first one.

To address this problem modify arch_freq_get_on_cpu() to call
aperfmperf_snapshot_khz() twice, with a short delay between
these calls, if the previous invocation of aperfmperf_snapshot_khz()
was too far back in the past (specifically, more that 1s ago) and
adjust aperfmperf_snapshot_khz() for that.

Fixes: f8475cef9008 "x86: use common aperfmperf_khz_on_cpu() to calculate KHz using APERF/MPERF"
Reported-by: Doug Smythies <dsmythies@telus.net>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/x86/kernel/cpu/aperfmperf.c |   36 +++++++++++++++++++++++++++++-------
 1 file changed, 29 insertions(+), 7 deletions(-)

Index: linux-pm/arch/x86/kernel/cpu/aperfmperf.c
===================================================================
--- linux-pm.orig/arch/x86/kernel/cpu/aperfmperf.c
+++ linux-pm/arch/x86/kernel/cpu/aperfmperf.c
@@ -8,20 +8,25 @@
  * This file is licensed under GPLv2.
  */
 
-#include <linux/jiffies.h>
+#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;
-	unsigned long	jiffies;
+	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
@@ -33,9 +38,11 @@ static void aperfmperf_snapshot_khz(void
 	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);
 
-	/* Don't bother re-computing within 10 ms */
-	if (time_before(jiffies, s->jiffies + HZ/100))
+	/* Don't bother re-computing within the cache threshold time. */
+	if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
 		return;
 
 	rdmsrl(MSR_IA32_APERF, aperf);
@@ -51,6 +58,16 @@ static void aperfmperf_snapshot_khz(void
 	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;
+		return;
+	}
+
 	/*
 	 * if (cpu_khz * aperf_delta) fits into ULLONG_MAX, then
 	 *	khz = (cpu_khz * aperf_delta) / mperf_delta
@@ -60,13 +77,12 @@ static void aperfmperf_snapshot_khz(void
 	else	/* khz = aperf_delta / (mperf_delta / cpu_khz) */
 		s->khz = div64_u64(aperf_delta,
 			div64_u64(mperf_delta, cpu_khz));
-	s->jiffies = jiffies;
-	s->aperf = aperf;
-	s->mperf = mperf;
 }
 
 unsigned int arch_freq_get_on_cpu(int cpu)
 {
+	unsigned int khz;
+
 	if (!cpu_khz)
 		return 0;
 
@@ -74,6 +90,12 @@ unsigned int arch_freq_get_on_cpu(int cp
 		return 0;
 
 	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);
 }

  parent reply	other threads:[~2017-07-28  0:21 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-06-24  5:11 [PATCH 0/4 v2] x86,cpufreq: unify APERF/MPERF computation Len Brown
2017-06-24  5:11 ` [PATCH 1/4] x86: do not use cpufreq_quick_get() for /proc/cpuinfo "cpu MHz" Len Brown
2017-06-24  5:11   ` [PATCH 2/4 v2] x86: use common aperfmperf_khz_on_cpu() to calculate KHz using APERF/MPERF Len Brown
2017-06-24  8:56     ` Thomas Gleixner
2017-06-24 12:03       ` Rafael J. Wysocki
2017-06-24  5:11   ` [PATCH 3/4] intel_pstate: delete scheduler hook in HWP mode Len Brown
2017-06-24  5:11   ` [PATCH 4/4] intel_pstate: skip scheduler hook when in "performance" mode Len Brown
2017-07-25 22:32 ` [PATCH 2/4 v2] x86: use common aperfmperf_khz_on_cpu() to calculate KHz using APERF/MPERF Doug Smythies
2017-07-26 17:23   ` Len Brown
2017-07-28  0:13   ` Rafael J. Wysocki [this message]
2017-07-28 12:45     ` [PATCH v2] cpufreq: x86: Make scaling_cur_freq behave more as expected Rafael J. Wysocki
2017-07-31 23:46     ` Doug Smythies
2017-08-01  0:50       ` Rafael J. Wysocki
2017-07-28  6:01   ` [PATCH] " Doug Smythies
2017-07-28 12:26     ` Rafael J. Wysocki

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=8753755.adRLzWASdR@aspire.rjw.lan \
    --to=rjw@rjwysocki.net \
    --cc=dsmythies@telus.net \
    --cc=len.brown@intel.com \
    --cc=lenb@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=peterz@infradead.org \
    --cc=rafael@kernel.org \
    --cc=srinivas.pandruvada@linux.intel.com \
    --cc=tglx@linutronix.de \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).