lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Sun, 17 Oct 2021 21:51:53 +0200
From:   Daniel Lezcano <daniel.lezcano@...aro.org>
To:     Heiko Stuebner <heiko@...ech.de>
Cc:     robh+dt@...nel.org, devicetree@...r.kernel.org,
        linux-rockchip@...ts.infradead.org,
        linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH] arm64: dts: rockchip: Add idle cooling devices


Hi Heiko,


On 17/10/2021 12:13, Heiko Stuebner wrote:
> Hi Daniel,
> 
> Am Freitag, 1. Oktober 2021, 18:17:28 CEST schrieb Daniel Lezcano:
>> The thermal framework accepts now the cpu idle cooling device as an
>> alternative when the cpufreq cooling device fails.
>>
>> Add the node in the DT so the cooling devices will be present and the
>> platforms can extend the thermal zone definition to add them.
>>
>> Signed-off-by: Daniel Lezcano <daniel.lezcano@...aro.org>
>> ---
>>  arch/arm64/boot/dts/rockchip/rk3399.dtsi | 10 ++++++++++
>>  1 file changed, 10 insertions(+)
>>
>> diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
>> index 3871c7fd83b0..9ac232ffd284 100644
>> --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
>> +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
>> @@ -124,6 +124,11 @@ cpu_b0: cpu@100 {
>>  			#cooling-cells = <2>; /* min followed by max */
>>  			dynamic-power-coefficient = <436>;
>>  			cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP>;
>> +			thermal-idle {
>> +				#cooling-cells = <2>;
>> +				duration-us = <10000>;
>> +				exit-latency-us = <500>;
>> +			};
> 
> I guess the basic question would be where do the duration
> and exit-latency values come from. And also what happened
> to cpu_l0-l3 (aka the little cores)?

The duration is an arbitrary value, I've done some testing [1] to cool
down the CPU.

The exit-latency is a value to ignore idle states with greater exit
latency. In our case, it discards the cluster power down state.

My experiments on this platform showed the little cluster does not
contribute significantly to the heat, so having idle injection is not
really useful.

Just to clarify that idle injection is not better than dvfs, it can be
used in addition or as a backup solution if the dvfs fails. That is the
reason why there is no setup for the thermal zones.

[1] https://www.linaro.org/blog/force-idle-when-a-cpu-is-overheating/

>>  		};
>>  
>>  		cpu_b1: cpu@101 {
>> @@ -136,6 +141,11 @@ cpu_b1: cpu@101 {
>>  			#cooling-cells = <2>; /* min followed by max */
>>  			dynamic-power-coefficient = <436>;
>>  			cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP>;
>> +			thermal-idle {
>> +				#cooling-cells = <2>;
>> +				duration-us = <10000>;
>> +				exit-latency-us = <500>;
>> +			};
>>  		};
>>  
>>  		idle-states {
>>
> 
> 
> 
> 


-- 
<http://www.linaro.org/> Linaro.org │ Open source software for ARM SoCs

Follow Linaro:  <http://www.facebook.com/pages/Linaro> Facebook |
<http://twitter.com/#!/linaroorg> Twitter |
<http://www.linaro.org/linaro-blog/> Blog

Powered by blists - more mailing lists