This is a note to let you know that I've just added the patch titled
cpufreq: amd-pstate: cpufreq: amd-pstate: reset MSR_AMD_PERF_CTL register at init
to the 6.0-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
cpufreq-amd-pstate-cpufreq-amd-pstate-reset-msr_amd_perf_ctl-register-at-init.patch
and it can be found in the queue-6.0 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From 919f4557696939625085435ebde09a539de2349c Mon Sep 17 00:00:00 2001
From: Wyes Karny <wyes.karny@xxxxxxx>
Date: Thu, 17 Nov 2022 15:35:37 +0800
Subject: cpufreq: amd-pstate: cpufreq: amd-pstate: reset MSR_AMD_PERF_CTL register at init
From: Wyes Karny <wyes.karny@xxxxxxx>
commit 919f4557696939625085435ebde09a539de2349c upstream.
MSR_AMD_PERF_CTL is guaranteed to be 0 on a cold boot. However, on a
kexec boot, for instance, it may have a non-zero value (if the cpu was
in a non-P0 Pstate). In such cases, the cores with non-P0 Pstates at
boot will never be pushed to P0, let alone boost frequencies.
Kexec is a common workflow for reboot on Linux and this creates a
regression in performance. Fix it by explicitly setting the
MSR_AMD_PERF_CTL to 0 during amd_pstate driver init.
Cc: All applicable <stable@xxxxxxxxxxxxxxx>
Acked-by: Huang Rui <ray.huang@xxxxxxx>
Reviewed-by: Gautham R. Shenoy <gautham.shenoy@xxxxxxx>
Tested-by: Wyes Karny <wyes.karny@xxxxxxx>
Signed-off-by: Wyes Karny <wyes.karny@xxxxxxx>
Signed-off-by: Perry Yuan <Perry.Yuan@xxxxxxx>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/cpufreq/amd-pstate.c | 10 ++++++++++
1 file changed, 10 insertions(+)
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -483,12 +483,22 @@ static void amd_pstate_boost_init(struct
amd_pstate_driver.boost_enabled = true;
}
+static void amd_perf_ctl_reset(unsigned int cpu)
+{
+ wrmsrl_on_cpu(cpu, MSR_AMD_PERF_CTL, 0);
+}
+
static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
{
int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret;
struct device *dev;
struct amd_cpudata *cpudata;
+ /*
+ * Resetting PERF_CTL_MSR will put the CPU in P0 frequency,
+ * which is ideal for initialization process.
+ */
+ amd_perf_ctl_reset(policy->cpu);
dev = get_cpu_device(policy->cpu);
if (!dev)
return -ENODEV;
Patches currently in stable-queue which might be from wyes.karny@xxxxxxx are
queue-6.0/cpufreq-amd-pstate-cpufreq-amd-pstate-reset-msr_amd_perf_ctl-register-at-init.patch
queue-6.0/cpufreq-amd-pstate-change-amd-pstate-driver-to-be-bu.patch
