From: Giovanni Gherdovich <ggherdovich@suse.cz>
To: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Borislav Petkov <bp@suse.de>, Len Brown <lenb@kernel.org>,
"Rafael J . Wysocki" <rjw@rjwysocki.net>
Cc: x86@kernel.org, linux-pm@vger.kernel.org,
linux-kernel@vger.kernel.org,
Mel Gorman <mgorman@techsingularity.net>,
Matt Fleming <matt@codeblueprint.co.uk>,
Viresh Kumar <viresh.kumar@linaro.org>,
Juri Lelli <juri.lelli@redhat.com>, Paul Turner <pjt@google.com>,
Vincent Guittot <vincent.guittot@linaro.org>,
Quentin Perret <qperret@qperret.net>,
Dietmar Eggemann <dietmar.eggemann@arm.com>,
Doug Smythies <dsmythies@telus.net>,
Giovanni Gherdovich <ggherdovich@suse.cz>
Subject: [PATCH v4 4/6] x86,sched: Add support for frequency invariance on ATOM_GOLDMONT*
Date: Wed, 13 Nov 2019 13:46:52 +0100 [thread overview]
Message-ID: <20191113124654.18122-5-ggherdovich@suse.cz> (raw)
In-Reply-To: <20191113124654.18122-1-ggherdovich@suse.cz>
The scheduler needs the ratio freq_curr/freq_max for frequency-invariant
accounting. On GOLDMONT (aka Apollo Lake), GOLDMONT_D (aka Denverton) and
GOLDMONT_PLUS CPUs (aka Gemini Lake) set freq_max to the highest frequency
reported by the CPU.
The encoding of turbo ratios for GOLDMONT* is identical to the one for
SKYLAKE_X, but we treat the Atom case apart because we want to set freq_max to
a higher value, thus the ratio freq_curr/freq_max to be lower, leading to more
conservative frequency selections (favoring power efficiency).
Signed-off-by: Giovanni Gherdovich <ggherdovich@suse.cz>
---
arch/x86/kernel/smpboot.c | 32 +++++++++++++++++++++++++++++---
1 file changed, 29 insertions(+), 3 deletions(-)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 0e79dcc03ae4..4d192abf337d 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1795,6 +1795,10 @@ void native_play_dead(void)
* which would ignore the entire turbo range (a conspicuous part, making
* freq_curr/freq_max always maxed out).
*
+ * An exception to the heuristic above is the Atom uarch, where we choose the
+ * highest turbo level for freq_max since Atom's are generally oriented towards
+ * power efficiency.
+ *
* Setting freq_max to anything less than the 1C turbo ratio makes the ratio
* freq_curr / freq_max to eventually grow >1, in which case we clip it to 1.
*/
@@ -1841,6 +1845,27 @@ static const struct x86_cpu_id has_glm_turbo_ratio_limits[] = {
{}
};
+static bool glm_set_cpu_max_freq(u64 *ratio, u64 *turbo_ratio)
+{
+ int err;
+
+ if (!x86_match_cpu(has_glm_turbo_ratio_limits))
+ return false;
+
+ err = rdmsrl_safe(MSR_PLATFORM_INFO, ratio);
+ if (err)
+ return false;
+
+ err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, turbo_ratio);
+ if (err)
+ return false;
+
+ *ratio = (*ratio >> 8) & 0xFF; /* max P state ratio */
+ *turbo_ratio = *turbo_ratio & 0xFF; /* highest turbo ratio */
+
+ return true;
+}
+
static int get_knl_turbo_ratio(u64 *turbo_ratio)
{
u64 msr;
@@ -1962,7 +1987,6 @@ static void intel_set_cpu_max_freq(void)
/*
* TODO: add support for:
*
- * - Atom Goldmont
* - Atom Silvermont
*
* which all now get by default arch_max_freq = SCHED_CAPACITY_SCALE
@@ -1970,10 +1994,12 @@ static void intel_set_cpu_max_freq(void)
u64 ratio = 1, turbo_ratio = 1;
- if (turbo_disabled() ||
- x86_match_cpu(has_glm_turbo_ratio_limits))
+ if (turbo_disabled())
return;
+ if (glm_set_cpu_max_freq(&ratio, &turbo_ratio))
+ goto set_value;
+
if (knl_set_cpu_max_freq(&ratio, &turbo_ratio))
goto set_value;
--
2.16.4
next prev parent reply other threads:[~2019-11-13 12:41 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-11-13 12:46 [PATCH v4 0/6] Add support for frequency invariance for (some) x86 Giovanni Gherdovich
2019-11-13 12:46 ` [PATCH v4 1/6] x86,sched: Add support for frequency invariance Giovanni Gherdovich
2019-11-24 7:49 ` Doug Smythies
2019-11-25 8:16 ` Doug Smythies
2019-11-25 9:16 ` Mel Gorman
2019-11-25 16:06 ` Giovanni Gherdovich
2019-11-26 5:59 ` Doug Smythies
2019-11-26 15:20 ` Giovanni Gherdovich
2019-11-27 7:32 ` Doug Smythies
2019-11-28 22:48 ` Doug Smythies
2019-12-19 10:48 ` Qais Yousef
2019-12-23 7:47 ` Doug Smythies
2019-12-23 14:07 ` Qais Yousef
2019-12-23 14:40 ` Qais Yousef
2019-12-23 16:34 ` Doug Smythies
2019-12-23 19:10 ` Qais Yousef
2019-12-24 1:16 ` Doug Smythies
2019-12-24 11:08 ` Qais Yousef
2019-12-02 16:34 ` Ionela Voinescu
2019-12-06 11:57 ` Giovanni Gherdovich
2019-12-18 19:34 ` Peter Zijlstra
2019-12-19 20:27 ` Giovanni Gherdovich
2019-11-13 12:46 ` [PATCH v4 2/6] x86,sched: Add support for frequency invariance on SKYLAKE_X Giovanni Gherdovich
2019-12-18 20:06 ` Peter Zijlstra
2019-12-19 20:29 ` Giovanni Gherdovich
2019-11-13 12:46 ` [PATCH v4 3/6] x86,sched: Add support for frequency invariance on XEON_PHI_KNL/KNM Giovanni Gherdovich
2019-12-18 20:22 ` Peter Zijlstra
2019-12-19 20:32 ` Giovanni Gherdovich
2019-11-13 12:46 ` Giovanni Gherdovich [this message]
2019-11-13 12:46 ` [PATCH v4 5/6] x86,sched: Add support for frequency invariance on ATOM Giovanni Gherdovich
2019-11-13 16:50 ` Srinivas Pandruvada
2019-11-15 10:34 ` Giovanni Gherdovich
2019-11-13 12:46 ` [PATCH v4 6/6] x86: intel_pstate: handle runtime turbo disablement/enablement in freq. invariance Giovanni Gherdovich
2019-12-18 20:37 ` [PATCH v4 0/6] Add support for frequency invariance for (some) x86 Peter Zijlstra
2019-12-19 20:33 ` Giovanni Gherdovich
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=20191113124654.18122-5-ggherdovich@suse.cz \
--to=ggherdovich@suse.cz \
--cc=bp@suse.de \
--cc=dietmar.eggemann@arm.com \
--cc=dsmythies@telus.net \
--cc=juri.lelli@redhat.com \
--cc=lenb@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=matt@codeblueprint.co.uk \
--cc=mgorman@techsingularity.net \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=pjt@google.com \
--cc=qperret@qperret.net \
--cc=rjw@rjwysocki.net \
--cc=srinivas.pandruvada@linux.intel.com \
--cc=tglx@linutronix.de \
--cc=vincent.guittot@linaro.org \
--cc=viresh.kumar@linaro.org \
--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).