linux-arm-kernel.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
To: Marc Gonzalez <marc.w.gonzalez@free.fr>
Cc: PM <linux-pm@vger.kernel.org>,
	Jeffrey Hugo <jhugo@codeaurora.org>,
	MSM <linux-arm-msm@vger.kernel.org>,
	Daniel Lezcano <daniel.lezcano@linaro.org>,
	Rafael Wysocki <rjw@rjwysocki.net>,
	Amit Kucheria <amit.kucheria@linaro.org>,
	Bjorn Andersson <bjorn.andersson@linaro.org>,
	Andy Gross <agross@kernel.org>,
	Sibi Sankar <sibis@codeaurora.org>,
	Sudeep Holla <sudeep.holla@arm.com>,
	Niklas Cassel <niklas.cassel@linaro.org>,
	Linux ARM <linux-arm-kernel@lists.infradead.org>
Subject: Re: [PATCH v4] arm64: dts: qcom: msm8998: Add PSCI cpuidle low power states
Date: Wed, 29 May 2019 18:25:41 +0100	[thread overview]
Message-ID: <20190529172541.GB25642@redmoon> (raw)
In-Reply-To: <c41508c7-35b2-aa40-c468-384e51d3d7b6@free.fr>

On Wed, May 29, 2019 at 01:08:44PM +0200, Marc Gonzalez wrote:
> + linux-pm
> 
> On 24/05/2019 14:32, Marc Gonzalez wrote:
> 
> > From: Amit Kucheria <amit.kucheria@linaro.org>
> > 
> > Add device bindings for cpuidle states for cpu devices.
> > 
> > [marc: rebase, fix arm,psci-suspend-param, fix entry-latency-us]
> > Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
> > Signed-off-by: Amit Kucheria <amit.kucheria@linaro.org>
> > Signed-off-by: Marc Gonzalez <marc.w.gonzalez@free.fr>
> > ---
> > Changes from v3:
> > - Fixup all 4 entry-latency-us (Niklas)
> > Changes from v2:
> > - Rebase
> > - Fixup arm,psci-suspend-param for power-collapse states (otherwise: reboot)
> > ---
> >  arch/arm64/boot/dts/qcom/msm8998.dtsi | 50 +++++++++++++++++++++++++++
> >  1 file changed, 50 insertions(+)
> > 
> > diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi
> > index 412195b9794c..ac6bd32c0e7d 100644
> > --- a/arch/arm64/boot/dts/qcom/msm8998.dtsi
> > +++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi
> > @@ -78,6 +78,7 @@
> >  			compatible = "arm,armv8";
> >  			reg = <0x0 0x0>;
> >  			enable-method = "psci";
> > +			cpu-idle-states = <&LITTLE_CPU_SLEEP_0 &LITTLE_CPU_SLEEP_1>;
> >  			next-level-cache = <&L2_0>;
> >  			L2_0: l2-cache {
> >  				compatible = "arm,arch-cache";
> > @@ -96,6 +97,7 @@
> >  			compatible = "arm,armv8";
> >  			reg = <0x0 0x1>;
> >  			enable-method = "psci";
> > +			cpu-idle-states = <&LITTLE_CPU_SLEEP_0 &LITTLE_CPU_SLEEP_1>;
> >  			next-level-cache = <&L2_0>;
> >  			L1_I_1: l1-icache {
> >  				compatible = "arm,arch-cache";
> > @@ -110,6 +112,7 @@
> >  			compatible = "arm,armv8";
> >  			reg = <0x0 0x2>;
> >  			enable-method = "psci";
> > +			cpu-idle-states = <&LITTLE_CPU_SLEEP_0 &LITTLE_CPU_SLEEP_1>;
> >  			next-level-cache = <&L2_0>;
> >  			L1_I_2: l1-icache {
> >  				compatible = "arm,arch-cache";
> > @@ -124,6 +127,7 @@
> >  			compatible = "arm,armv8";
> >  			reg = <0x0 0x3>;
> >  			enable-method = "psci";
> > +			cpu-idle-states = <&LITTLE_CPU_SLEEP_0 &LITTLE_CPU_SLEEP_1>;
> >  			next-level-cache = <&L2_0>;
> >  			L1_I_3: l1-icache {
> >  				compatible = "arm,arch-cache";
> > @@ -138,6 +142,7 @@
> >  			compatible = "arm,armv8";
> >  			reg = <0x0 0x100>;
> >  			enable-method = "psci";
> > +			cpu-idle-states = <&BIG_CPU_SLEEP_0 &BIG_CPU_SLEEP_1>;
> >  			next-level-cache = <&L2_1>;
> >  			L2_1: l2-cache {
> >  				compatible = "arm,arch-cache";
> > @@ -156,6 +161,7 @@
> >  			compatible = "arm,armv8";
> >  			reg = <0x0 0x101>;
> >  			enable-method = "psci";
> > +			cpu-idle-states = <&BIG_CPU_SLEEP_0 &BIG_CPU_SLEEP_1>;
> >  			next-level-cache = <&L2_1>;
> >  			L1_I_101: l1-icache {
> >  				compatible = "arm,arch-cache";
> > @@ -170,6 +176,7 @@
> >  			compatible = "arm,armv8";
> >  			reg = <0x0 0x102>;
> >  			enable-method = "psci";
> > +			cpu-idle-states = <&BIG_CPU_SLEEP_0 &BIG_CPU_SLEEP_1>;
> >  			next-level-cache = <&L2_1>;
> >  			L1_I_102: l1-icache {
> >  				compatible = "arm,arch-cache";
> > @@ -184,6 +191,7 @@
> >  			compatible = "arm,armv8";
> >  			reg = <0x0 0x103>;
> >  			enable-method = "psci";
> > +			cpu-idle-states = <&BIG_CPU_SLEEP_0 &BIG_CPU_SLEEP_1>;
> >  			next-level-cache = <&L2_1>;
> >  			L1_I_103: l1-icache {
> >  				compatible = "arm,arch-cache";
> > @@ -230,6 +238,48 @@
> >  				};
> >  			};
> >  		};
> > +
> > +		idle-states {
> > +			entry-method = "psci";
> > +
> > +			LITTLE_CPU_SLEEP_0: cpu-sleep-0-0 {
> > +				compatible = "arm,idle-state";
> > +				idle-state-name = "little-retention";
> > +				arm,psci-suspend-param = <0x00000002>;
> > +				entry-latency-us = <81>;
> > +				exit-latency-us = <86>;
> > +				min-residency-us = <200>;
> > +			};
> > +
> > +			LITTLE_CPU_SLEEP_1: cpu-sleep-0-1 {
> > +				compatible = "arm,idle-state";
> > +				idle-state-name = "little-power-collapse";
> > +				arm,psci-suspend-param = <0x40000003>;
> > +				entry-latency-us = <273>;
> > +				exit-latency-us = <612>;
> > +				min-residency-us = <1000>;
> > +				local-timer-stop;
> > +			};
> > +
> > +			BIG_CPU_SLEEP_0: cpu-sleep-1-0 {
> > +				compatible = "arm,idle-state";
> > +				idle-state-name = "big-retention";
> > +				arm,psci-suspend-param = <0x00000002>;
> > +				entry-latency-us = <79>;
> > +				exit-latency-us = <82>;
> > +				min-residency-us = <200>;
> > +			};
> > +
> > +			BIG_CPU_SLEEP_1: cpu-sleep-1-1 {
> > +				compatible = "arm,idle-state";
> > +				idle-state-name = "big-power-collapse";
> > +				arm,psci-suspend-param = <0x40000003>;
> > +				entry-latency-us = <336>;
> > +				exit-latency-us = <525>;
> > +				min-residency-us = <1000>;
> > +				local-timer-stop;
> > +			};
> > +		};
> 
> Niklas and I have been discussing the min-residency-us prop.
> 
> https://elixir.bootlin.com/linux/latest/source/Documentation/devicetree/bindings/arm/idle-states.txt
> 
> I thought a requirement would be
> 
> 	min-residency > entry-latency + exit-latency
> 
> but it doesn't seem to be the case.
> 
> Do the values proposed here look kosher?

As the document describes the right values should be computed by
plotting energy consumption.

min-residency is a worst case scenario because the energy consumed to
enter an idle state depends on the system state (eg cache state), so the
worst case value should be added there.

Lorenzo

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

      reply	other threads:[~2019-05-29 17:25 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-05-23  8:36 [PATCH v3] arm64: dts: qcom: msm8998: Add PSCI cpuidle low power states Marc Gonzalez
2019-05-23 21:46 ` Niklas Cassel
2019-05-24 11:33   ` Marc Gonzalez
2019-05-24 12:32   ` [PATCH v4] " Marc Gonzalez
2019-05-29 11:08     ` Marc Gonzalez
2019-05-29 17:25       ` Lorenzo Pieralisi [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190529172541.GB25642@redmoon \
    --to=lorenzo.pieralisi@arm.com \
    --cc=agross@kernel.org \
    --cc=amit.kucheria@linaro.org \
    --cc=bjorn.andersson@linaro.org \
    --cc=daniel.lezcano@linaro.org \
    --cc=jhugo@codeaurora.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-arm-msm@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=marc.w.gonzalez@free.fr \
    --cc=niklas.cassel@linaro.org \
    --cc=rjw@rjwysocki.net \
    --cc=sibis@codeaurora.org \
    --cc=sudeep.holla@arm.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).