x86/aperfmperf: erase stale arch_freq_scale values when disabling frequency invariance readings
PATCH 1/1 x86/aperfmperf: erase stale arch_freq_scale values when disabling frequency invariance readings
Once disable_freq_invariance_work is called the scale_freq_tick function will not compute or update the arch_freq_scale values.
However the scheduler will still read these values and use them. The result is that the scheduler might perform unfair decisions based on stale values.
This patch adds the step of setting the arch_freq_scale values for all cpus to the default (max) value SCHED_CAPACITY_SCALE, Once all cpus have the same arch_freq_scale value the scaling is meaningless.
--- arch/x86/kernel/cpu/aperfmperf.c | 9 +++++++++ 1 file changed, 9 insertions(+)
arch/x86/kernel/cpu/aperfmperf.c +9 -0
@@ -330,7 +330,16 @@ static void __init bp_init_freq_invariance(void)static void disable_freq_invariance_workfn (struct work_struct *work) { +int cpu; +static_branch_disable (&arch_scale_freq_key); + +/* +* Set arch_freq_scale to a default value on all cpus +* This negates the effect of scaling +*/ +for_each_possible_cpu (cpu) +per_cpu (arch_freq_scale, cpu) =SCHED_CAPACITY_SCALE ; } static DECLARE_WORK(disable_freq_invariance_work,
Signature · 1 line
2.31.1
[tip: sched/urgent] x86/aperfmperf: Erase stale arch_freq_scale values when disabling frequency invariance readings
The following commit has been merged into the sched/urgent branch of tip:
The following commit has been merged into the sched/urgent branch of tip:
Commit-ID: 5f5cc9ed992cbab6361f198966f0edba5fc52688 Gitweb: https://git.kernel.org/tip/5f5cc9ed992cbab6361f198966f0edba5fc52688 Author: Yair Podemsky <[email protected]> AuthorDate: Tue, 10 Jan 2023 18:02:06 +02:00 Committer: Ingo Molnar <[email protected]> CommitterDate: Mon, 16 Jan 2023 10:19:15 +01:00
x86/aperfmperf: Erase stale arch_freq_scale values when disabling frequency invariance readings
Once disable_freq_invariance_work is called the scale_freq_tick function will not compute or update the arch_freq_scale values.
However the scheduler will still read these values and use them. The result is that the scheduler might perform unfair decisions based on stale values.
This patch adds the step of setting the arch_freq_scale values for all cpus to the default (max) value SCHED_CAPACITY_SCALE, Once all cpus have the same arch_freq_scale value the scaling is meaningless.
--- arch/x86/kernel/cpu/aperfmperf.c | 9 +++++++++ 1 file changed, 9 insertions(+)
arch/x86/kernel/cpu/aperfmperf.c +9 -0
@@ -330,7 +330,16 @@ static void __init bp_init_freq_invariance(void)static void disable_freq_invariance_workfn (struct work_struct *work) { +int cpu; +static_branch_disable (&arch_scale_freq_key); + +/* +* Set arch_freq_scale to a default value on all cpus +* This negates the effect of scaling +*/ +for_each_possible_cpu (cpu) +per_cpu (arch_freq_scale, cpu) =SCHED_CAPACITY_SCALE ; } static DECLARE_WORK(disable_freq_invariance_work,