From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
To: rafael@kernel.org, viresh.kumar@linaro.org
Cc: linux-pm@vger.kernel.org, linux-kernel@vger.kernel.org,
Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>,
stable@vger.kernel.org
Subject: [UPDATE][PATCH] cpufreq: intel_pstate: Fix EPP restore after offline/online
Date: Mon, 15 Nov 2021 05:40:17 -0800 [thread overview]
Message-ID: <20211115134017.1257932-1-srinivas.pandruvada@linux.intel.com> (raw)
When using performance policy, EPP value is restored to non "performance"
mode EPP after offline and online.
For example:
cat /sys/devices/system/cpu/cpu1/cpufreq/energy_performance_preference
performance
echo 0 > /sys/devices/system/cpu/cpu1/online
echo 1 > /sys/devices/system/cpu/cpu1/online
cat /sys/devices/system/cpu/cpu1/cpufreq/energy_performance_preference
balance_performance
The commit 4adcf2e5829f ("cpufreq: intel_pstate: Add ->offline and ->online callbacks")
optimized save restore path of the HWP request MSR, when there is no
change in the policy. Also added special processing for performance mode
EPP. If EPP has been set to "performance" by the active mode "performance"
scaling algorithm, replace that value with the cached EPP. This ends up
replacing with cached EPP during offline, which is restored during online
again.
So add a change which will set cpu_data->epp_policy to zero, when in
performance policy and has non zero epp. In this way EPP is set to zero
again.
Fixes: 4adcf2e5829f ("cpufreq: intel_pstate: Add ->offline and ->online callbacks")
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Cc: stable@vger.kernel.org # v5.9+
---
Update: Minor optimization to skip non performance policy code path
drivers/cpufreq/intel_pstate.c | 12 +++++++++---
1 file changed, 9 insertions(+), 3 deletions(-)
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 815df3daae9d..6d7d73a0c66b 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -936,11 +936,17 @@ static void intel_pstate_hwp_set(unsigned int cpu)
max = cpu_data->max_perf_ratio;
min = cpu_data->min_perf_ratio;
- if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE)
- min = max;
-
rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value);
+ if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE) {
+ min = max;
+ epp = 0;
+ if (boot_cpu_has(X86_FEATURE_HWP_EPP))
+ epp = (value >> 24) & 0xff;
+ if (epp)
+ cpu_data->epp_policy = 0;
+ }
+
value &= ~HWP_MIN_PERF(~0L);
value |= HWP_MIN_PERF(min);
--
2.17.1
next reply other threads:[~2021-11-15 13:43 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-11-15 13:40 Srinivas Pandruvada [this message]
2021-11-16 17:47 ` Rafael J. Wysocki
2021-11-17 2:09 ` Srinivas Pandruvada
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=20211115134017.1257932-1-srinivas.pandruvada@linux.intel.com \
--to=srinivas.pandruvada@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=rafael@kernel.org \
--cc=stable@vger.kernel.org \
--cc=viresh.kumar@linaro.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
all inboxes | Powered by JetHome®