This is a note to let you know that I've just added the patch titled
cpufreq/amd-pstate: Fix prefcore rankings
to the 6.13-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-fix-prefcore-rankings.patch
and it can be found in the queue-6.13 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 9503fe26f632af6f9e0bd77ab09eae9855ae48c7
Author: Mario Limonciello <mario.limonciello@xxxxxxx>
Date: Thu Jan 2 08:12:04 2025 -0600
cpufreq/amd-pstate: Fix prefcore rankings
[ Upstream commit fd604ae6c261c5a56bb977ae99f875bbd7264a3f ]
commit 50a062a76200 ("cpufreq/amd-pstate: Store the boost numerator as
highest perf again") updated the value stored for highest perf to no longer
store the highest perf value but instead the boost numerator.
This is a fixed value for systems with preferred cores and not appropriate
for use ITMT rankings. Update the value used for ITMT rankings to be the
preferred core ranking.
Reported-and-tested-by: Sebastian <sobrus@xxxxxxxxx>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219640
Fixes: 50a062a76200 ("cpufreq/amd-pstate: Store the boost numerator as highest perf again")
Reviewed-by: Dhananjay Ugwekar <dhananjay.ugwekar@xxxxxxx>
Link: https://lore.kernel.org/r/20250102141204.3413202-1-superm1@xxxxxxxxxx
Signed-off-by: Mario Limonciello <mario.limonciello@xxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 66e5dfc711c0c..f6d04eb40af94 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -802,7 +802,7 @@ static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata)
* sched_set_itmt_support(true) has been called and it is valid to
* update them at any time after it has been called.
*/
- sched_set_itmt_core_prio((int)READ_ONCE(cpudata->highest_perf), cpudata->cpu);
+ sched_set_itmt_core_prio((int)READ_ONCE(cpudata->prefcore_ranking), cpudata->cpu);
schedule_work(&sched_prefcore_work);
}
