[3.11.y.z extended stable] Patch "intel_pstate: Take core C0 time into account for core busy" has been added to staging queue

[Luis Henriques]

This is a note to let you know that I have just added a patch titled

    intel_pstate: Take core C0 time into account for core busy

to the linux-3.11.y-queue branch of the 3.11.y.z extended stable tree 
which can be found at:

 http://kernel.ubuntu.com/git?p=ubuntu/linux.git;a=shortlog;h=refs/heads/linux-3.11.y-queue

If you, or anyone else, feels it should not be added to this tree, please 
reply to this email.

For more information about the 3.11.y.z tree, see
https://wiki.ubuntu.com/Kernel/Dev/ExtendedStable

Thanks.
-Luis

------

>From 52f7f05e009b77337a2d48e4227968ababa1a4ab Mon Sep 17 00:00:00 2001
From: Dirk Brandewie <dirk.j.brandewie at intel.com>
Date: Mon, 3 Feb 2014 08:55:31 -0800
Subject: intel_pstate: Take core C0 time into account for core busy
 calculation

commit fcb6a15c2e7e76d493e6f91ea889ab40e1c643a4 upstream.

Take non-idle time into account when calculating core busy time.
This ensures that intel_pstate will notice a decrease in load.

References: https://bugzilla.kernel.org/show_bug.cgi?id=66581
Signed-off-by: Dirk Brandewie <dirk.j.brandewie at intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki at intel.com>
Signed-off-by: Luis Henriques <luis.henriques at canonical.com>
---
 drivers/cpufreq/intel_pstate.c | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index e52e542..1220359 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -51,6 +51,7 @@ struct sample {
 	int32_t core_pct_busy;
 	u64 aperf;
 	u64 mperf;
+	unsigned long long tsc;
 	int freq;
 };

@@ -86,6 +87,7 @@ struct cpudata {

 	u64	prev_aperf;
 	u64	prev_mperf;
+	unsigned long long prev_tsc;
 	int	sample_ptr;
 	struct sample samples[SAMPLE_COUNT];
 };
@@ -436,29 +438,41 @@ static inline void intel_pstate_calc_busy(struct cpudata *cpu,
 					struct sample *sample)
 {
 	u64 core_pct;
-	core_pct = div64_u64(int_tofp(sample->aperf * 100),
-			     sample->mperf);
-	sample->freq = fp_toint(cpu->pstate.max_pstate * core_pct * 1000);
+	u64 c0_pct;

-	sample->core_pct_busy = core_pct;
+	core_pct = div64_u64(sample->aperf * 100, sample->mperf);
+
+	c0_pct = div64_u64(sample->mperf * 100, sample->tsc);
+	sample->freq = fp_toint(
+		mul_fp(int_tofp(cpu->pstate.max_pstate),
+			int_tofp(core_pct * 1000)));
+
+	sample->core_pct_busy = mul_fp(int_tofp(core_pct),
+				div_fp(int_tofp(c0_pct + 1), int_tofp(100)));
 }

 static inline void intel_pstate_sample(struct cpudata *cpu)
 {
 	u64 aperf, mperf;
+	unsigned long long tsc;

 	rdmsrl(MSR_IA32_APERF, aperf);
 	rdmsrl(MSR_IA32_MPERF, mperf);
+	tsc = native_read_tsc();
+
 	cpu->sample_ptr = (cpu->sample_ptr + 1) % SAMPLE_COUNT;
 	cpu->samples[cpu->sample_ptr].aperf = aperf;
 	cpu->samples[cpu->sample_ptr].mperf = mperf;
+	cpu->samples[cpu->sample_ptr].tsc = tsc;
 	cpu->samples[cpu->sample_ptr].aperf -= cpu->prev_aperf;
 	cpu->samples[cpu->sample_ptr].mperf -= cpu->prev_mperf;
+	cpu->samples[cpu->sample_ptr].tsc -= cpu->prev_tsc;

 	intel_pstate_calc_busy(cpu, &cpu->samples[cpu->sample_ptr]);

 	cpu->prev_aperf = aperf;
 	cpu->prev_mperf = mperf;
+	cpu->prev_tsc = tsc;
 }

 static inline void intel_pstate_set_sample_time(struct cpudata *cpu)
--
1.8.3.2