On 10/27/21 7:43 PM, Bjorn Andersson wrote:

On Fri 15 Oct 07:45 PDT 2021, Lukasz Luba wrote:

quoted

diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h

[..]

quoted

+/**
+ * topology_thermal_pressure_update() - Update thermal pressure for CPUs
+ * @cpus	: The related CPUs for which capacity has been reduced
+ * @capped_freq	: The maximum allowed frequency that CPUs can run at

I know this matches what I see in e.g. the Qualcomm cpufreq hw driver,
but in what cases will @capped_freq differ from
cpufreq_get_hw_max_freq(cpumask_first(cpus))?

The @capped_freq is the maximum allowed frequency value due to
thermal reasons, which will always be lower or equal to the value
returned by cpufreq_get_hw_max_freq()
(effectively: 'policy->cpuinfo.max_freq').

We limit the frequency (and voltage) of CPU to reduce power (and heat)
in the passive cooling system. That information is important to us,
because scheduler needs to know how fast the CPU can go. It cannot
assume that the speed is always 'policy->cpuinfo.max_freq'. Often
it's less then that at heavy load or GPU heavy load (the same SoC).

Regards,
Lukasz