| Message ID | 20211001161728.1729664-1-daniel.lezcano@linaro.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | arm64: dts: rockchip: Add idle cooling devices | expand |
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@linaro.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)? Heiko > }; > > 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 { >
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@linaro.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 { >> > > > >
On Fri, 1 Oct 2021 18:17:28 +0200, Daniel Lezcano wrote: > 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. Applied, thanks! [1/1] arm64: dts: rockchip: Add idle cooling devices commit: 43f9699b0c12d4e50b66723213cef456c52254f3 Best regards,
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>; + }; }; 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 {
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@linaro.org> --- arch/arm64/boot/dts/rockchip/rk3399.dtsi | 10 ++++++++++ 1 file changed, 10 insertions(+)