From: Lucas Lee Jing Yi <lucasleeeeeeeee@gmail.com>
To: rafael@kernel.org
Cc: Perry.Yuan@amd.com, Xiaojian.Du@amd.com,
alexander.deucher@amd.com, bp@alien8.de, deepak.sharma@amd.com,
li.meng@amd.com, linux-acpi@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org,
linux-pm@vger.kernel.org, mario.limonciello@amd.com,
nathan.fontenot@amd.com, oleksandr@natalenko.name,
rafael.j.wysocki@intel.com, ray.huang@amd.com,
shimmer.huang@amd.com, skhan@linuxfoundation.org,
viresh.kumar@linaro.org, x86@kernel.org,
Lucas Lee Jing Yi <lucasleeeeeeeee@gmail.com>
Subject: [PATCH] [PATCH] amd_pstate: fix erroneous highest_perf value on some CPUs
Date: Mon, 19 Feb 2024 00:10:31 +0800 [thread overview]
Message-ID: <20240218161435.38312-2-lucasleeeeeeeee@gmail.com> (raw)
In-Reply-To: <20240218161435.38312-1-lucasleeeeeeeee@gmail.com>
On a Ryzen 7840HS the highest_perf value is 196, not 166 as AMD assumed.
This leads to the advertised max clock speed to only be 4.35ghz instead of 5.14ghz , leading to a large degradation in performance.
Fix the broken assumption and revert back to the old logic for getting highest_perf.
TEST:
Geekbench 6 Before Patch:
Single Core: 2325 (-22%)!
Multi Core: 11335 (-10%)
Geekbench 6 AFTER Patch:
Single Core: 2635
Multi Core: 12487
Signed-off-by: Lucas Lee Jing Yi <lucasleeeeeeeee@gmail.com>
---
drivers/cpufreq/amd-pstate.c | 22 ++++++++++------------
1 file changed, 10 insertions(+), 12 deletions(-)
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 08e112444c27..54df68773620 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -50,7 +50,6 @@
#define AMD_PSTATE_TRANSITION_LATENCY 20000
#define AMD_PSTATE_TRANSITION_DELAY 1000
-#define AMD_PSTATE_PREFCORE_THRESHOLD 166
/*
* TODO: We need more time to fine tune processors with shared memory solution
@@ -299,15 +298,12 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
&cap1);
if (ret)
return ret;
-
- /* For platforms that do not support the preferred core feature, the
- * highest_pef may be configured with 166 or 255, to avoid max frequency
- * calculated wrongly. we take the AMD_CPPC_HIGHEST_PERF(cap1) value as
- * the default max perf.
+
+ /* Some CPUs have different highest_perf from others, it is safer
+ * to read it than to assume some erroneous value, leading to performance issues.
*/
- if (cpudata->hw_prefcore)
- highest_perf = AMD_PSTATE_PREFCORE_THRESHOLD;
- else
+ highest_perf = amd_get_highest_perf();
+ if(highest_perf > AMD_CPPC_HIGHEST_PERF(cap1))
highest_perf = AMD_CPPC_HIGHEST_PERF(cap1);
WRITE_ONCE(cpudata->highest_perf, highest_perf);
@@ -329,9 +325,11 @@ static int cppc_init_perf(struct amd_cpudata *cpudata)
if (ret)
return ret;
- if (cpudata->hw_prefcore)
- highest_perf = AMD_PSTATE_PREFCORE_THRESHOLD;
- else
+ /* Some CPUs have different highest_perf from others, it is safer
+ * to read it than to assume some erroneous value, leading to performance issues.
+ */
+ highest_perf = amd_get_highest_perf();
+ if(highest_perf > cppc_perf.highest_perf)
highest_perf = cppc_perf.highest_perf;
WRITE_ONCE(cpudata->highest_perf, highest_perf);
--
2.43.2
next prev parent reply other threads:[~2024-02-18 16:15 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-01-19 9:04 [PATCH V14 0/7] amd-pstate preferred core Meng Li
2024-01-19 9:04 ` [PATCH V14 1/7] x86: Drop CPU_SUP_INTEL from SCHED_MC_PRIO for the expansion Meng Li
2024-01-19 9:04 ` [PATCH V14 2/7] ACPI: CPPC: Add get the highest performance cppc control Meng Li
2024-01-19 9:04 ` [PATCH V14 3/7] cpufreq: amd-pstate: Enable amd-pstate preferred core supporting Meng Li
2024-01-19 9:04 ` [PATCH V14 4/7] cpufreq: Add a notification message that the highest perf has changed Meng Li
2024-01-19 9:05 ` [PATCH V14 5/7] cpufreq: amd-pstate: Update amd-pstate preferred core ranking dynamically Meng Li
2024-01-19 9:05 ` [PATCH V14 6/7] Documentation: amd-pstate: introduce amd-pstate preferred core Meng Li
2024-01-19 9:05 ` [PATCH V14 7/7] Documentation: introduce amd-pstate preferrd core mode kernel command line options Meng Li
2024-01-29 15:18 ` [PATCH V14 0/7] amd-pstate preferred core Rafael J. Wysocki
2024-01-29 15:33 ` Borislav Petkov
2024-01-31 13:58 ` Rafael J. Wysocki
2024-02-18 16:10 ` Lucas Lee Jing Yi
2024-02-18 16:10 ` Lucas Lee Jing Yi [this message]
2024-02-20 7:23 ` [PATCH] [PATCH] amd_pstate: fix erroneous highest_perf value on some CPUs Meng, Li (Jassmine)
2024-02-20 9:02 ` Oleksandr Natalenko
2024-02-21 17:19 ` Lucas Lee Jing Yi
2024-02-21 17:19 ` Lucas Lee Jing Yi
2024-02-21 18:47 ` Mario Limonciello
2024-02-19 1:02 ` [PATCH V14 0/7] amd-pstate preferred core Meng, Li (Jassmine)
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=20240218161435.38312-2-lucasleeeeeeeee@gmail.com \
--to=lucasleeeeeeeee@gmail.com \
--cc=Perry.Yuan@amd.com \
--cc=Xiaojian.Du@amd.com \
--cc=alexander.deucher@amd.com \
--cc=bp@alien8.de \
--cc=deepak.sharma@amd.com \
--cc=li.meng@amd.com \
--cc=linux-acpi@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=mario.limonciello@amd.com \
--cc=nathan.fontenot@amd.com \
--cc=oleksandr@natalenko.name \
--cc=rafael.j.wysocki@intel.com \
--cc=rafael@kernel.org \
--cc=ray.huang@amd.com \
--cc=shimmer.huang@amd.com \
--cc=skhan@linuxfoundation.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).