arm64: hikey960: update idle-states

Update entry/exit latency and residency time of hikey960 to use more
realistic figures based on unitary tests done on the platform.

The complete results (in us) :
                  big cluster
                  cluster  CPU
max entry latency     800  400
max exit latency     2900  550
residency  903Mhz    5000 1500
residency 2363Mhz       0 1500

                  little cluster
                  cluster  CPU
max entry latency     500  400
max exit latency     1600  650
residency  533Mhz    8000 4500
residency 1844Mhz       0 1500

We can see that the residency time depends of the running OPP which is not
handled for now. Then we also have to take into account the constraint of
a residency time shorter than the tick to get full advantage of idle loop
reordering(tick is stopped if idle duration is higher than tick period).
Finally the selected residency value are :
                 big cluster
                  cluster  CPU
residency            3700 1500

                  little cluster
                  cluster  CPU
residency            3500 1500

A simple test with a task waking up every 11,111ms shows improvement:
- 5% a lowest OPP
- 22% at highest OPP

The period has been chosen:
- to be shorter than old cluster residency time and longer than new
residency time od cluster off C-state
- to prevent any sync with tick (4ms) when running tests that can add
some variances between tests

Change-Id: I9f8d5e4d1920268b720d340047cc7ec7305cf413
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>

1 files changed, 35 insertions, 18 deletions

diff --git a/arch/arm64/boot/dts/hisilicon/hi3660.dtsi b/arch/arm64/boot/dts/hisilicon/hi3660.dtsi
index c98aade39b14..9110f977d712 100644
--- a/arch/arm64/boot/dts/hisilicon/hi3660.dtsi
+++ b/arch/arm64/boot/dts/hisilicon/hi3660.dtsi
@@ -60,7 +60,8 @@
 			reg = <0x0 0x0>;
 			enable-method = "psci";
 			next-level-cache = <&A53_L2>;
-			cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP_0>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+			capacity-dmips-mhz = <592>;
 			clocks = <&stub_clock HI3660_CLK_STUB_CLUSTER0>;
 			operating-points-v2 = <&cluster0_opp>;
 			cooling-min-level = <4>;
@@ -76,7 +77,8 @@
 			reg = <0x0 0x1>;
 			enable-method = "psci";
 			next-level-cache = <&A53_L2>;
-			cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP_0>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+			capacity-dmips-mhz = <592>;
 			clocks = <&stub_clock HI3660_CLK_STUB_CLUSTER0>;
 			operating-points-v2 = <&cluster0_opp>;
 			sched-energy-costs = <&CPU_COST_A53 &CLUSTER_COST_A53>;
@@ -88,7 +90,8 @@
 			reg = <0x0 0x2>;
 			enable-method = "psci";
 			next-level-cache = <&A53_L2>;
-			cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP_0>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+			capacity-dmips-mhz = <592>;
 			clocks = <&stub_clock HI3660_CLK_STUB_CLUSTER0>;
 			operating-points-v2 = <&cluster0_opp>;
 			sched-energy-costs = <&CPU_COST_A53 &CLUSTER_COST_A53>;
@@ -100,7 +103,8 @@
 			reg = <0x0 0x3>;
 			enable-method = "psci";
 			next-level-cache = <&A53_L2>;
-			cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP_0>;
+			cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+			capacity-dmips-mhz = <592>;
 			clocks = <&stub_clock HI3660_CLK_STUB_CLUSTER0>;
 			operating-points-v2 = <&cluster0_opp>;
 			sched-energy-costs = <&CPU_COST_A53 &CLUSTER_COST_A53>;
@@ -112,7 +116,8 @@
 			reg = <0x0 0x100>;
 			enable-method = "psci";
 			next-level-cache = <&A73_L2>;
-			cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP_1>;
+			cpu-idle-states = <&CPU_SLEEP_1 &CLUSTER_SLEEP_1>;
+			capacity-dmips-mhz = <1024>;
 			clocks = <&stub_clock HI3660_CLK_STUB_CLUSTER1>;
 			operating-points-v2 = <&cluster1_opp>;
 			cooling-min-level = <4>;
@@ -128,7 +133,8 @@
 			reg = <0x0 0x101>;
 			enable-method = "psci";
 			next-level-cache = <&A73_L2>;
-			cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP_1>;
+			cpu-idle-states = <&CPU_SLEEP_1 &CLUSTER_SLEEP_1>;
+			capacity-dmips-mhz = <1024>;
 			clocks = <&stub_clock HI3660_CLK_STUB_CLUSTER1>;
 			operating-points-v2 = <&cluster1_opp>;
 			sched-energy-costs = <&CPU_COST_A72 &CLUSTER_COST_A72>;
@@ -140,7 +146,8 @@
 			reg = <0x0 0x102>;
 			enable-method = "psci";
 			next-level-cache = <&A73_L2>;
-			cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP_1>;
+			cpu-idle-states = <&CPU_SLEEP_1 &CLUSTER_SLEEP_1>;
+			capacity-dmips-mhz = <1024>;
 			clocks = <&stub_clock HI3660_CLK_STUB_CLUSTER1>;
 			operating-points-v2 = <&cluster1_opp>;
 			sched-energy-costs = <&CPU_COST_A72 &CLUSTER_COST_A72>;
@@ -152,7 +159,8 @@
 			reg = <0x0 0x103>;
 			enable-method = "psci";
 			next-level-cache = <&A73_L2>;
-			cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP_1>;
+			cpu-idle-states = <&CPU_SLEEP_1 &CLUSTER_SLEEP_1>;
+			capacity-dmips-mhz = <1024>;
 			clocks = <&stub_clock HI3660_CLK_STUB_CLUSTER1>;
 			operating-points-v2 = <&cluster1_opp>;
 			sched-energy-costs = <&CPU_COST_A72 &CLUSTER_COST_A72>;
@@ -161,31 +169,40 @@
 		idle-states {
 			entry-method = "psci";
 
-			CPU_SLEEP: cpu-sleep {
+			CPU_SLEEP_0: cpu-sleep-0 {
 				compatible = "arm,idle-state";
 				local-timer-stop;
 				arm,psci-suspend-param = <0x0010000>;
-				entry-latency-us = <40>;
-				exit-latency-us = <70>;
-				min-residency-us = <3000>;
+				entry-latency-us = <400>;
+				exit-latency-us = <650>;
+				min-residency-us = <1500>;
 			};
-
 			CLUSTER_SLEEP_0: cluster-sleep-0 {
 				compatible = "arm,idle-state";
 				local-timer-stop;
 				arm,psci-suspend-param = <0x1010000>;
 				entry-latency-us = <500>;
-				exit-latency-us = <5000>;
-				min-residency-us = <20000>;
+				exit-latency-us = <1600>;
+				min-residency-us = <3500>;
+			};
+
+
+			CPU_SLEEP_1: cpu-sleep-1 {
+				compatible = "arm,idle-state";
+				local-timer-stop;
+				arm,psci-suspend-param = <0x0010000>;
+				entry-latency-us = <400>;
+				exit-latency-us = <550>;
+				min-residency-us = <1500>;
 			};
 
 			CLUSTER_SLEEP_1: cluster-sleep-1 {
 				compatible = "arm,idle-state";
 				local-timer-stop;
 				arm,psci-suspend-param = <0x1010000>;
-				entry-latency-us = <1000>;
-				exit-latency-us = <5000>;
-				min-residency-us = <20000>;
+				entry-latency-us = <800>;
+				exit-latency-us = <2900>;
+				min-residency-us = <3500>;
 			};
 		};