brintos

brintos / linux-shallow public Read only

0
0
Text · 6.4 KiB · f28e1ad Raw
239 lines · plain
1==========================================2CPU capacity bindings3==========================================4 5==========================================61 - Introduction7==========================================8 9Some systems may be configured to have cpus with different power/performance10characteristics within the same chip. In this case, additional information has11to be made available to the kernel for it to be aware of such differences and12take decisions accordingly.13 14==========================================152 - CPU capacity definition16==========================================17 18CPU capacity is a number that provides the scheduler information about CPUs19heterogeneity. Such heterogeneity can come from micro-architectural differences20(e.g., ARM big.LITTLE systems) or maximum frequency at which CPUs can run21(e.g., SMP systems with multiple frequency domains). Heterogeneity in this22context is about differing performance characteristics; this binding tries to23capture a first-order approximation of the relative performance of CPUs.24 25CPU capacities are obtained by running a suitable benchmark. This binding makes26no guarantees on the validity or suitability of any particular benchmark, the27final capacity should, however, be:28 29* A "single-threaded" or CPU affine benchmark30* Divided by the running frequency of the CPU executing the benchmark31* Not subject to dynamic frequency scaling of the CPU32 33For the time being we however advise usage of the Dhrystone benchmark. What34above thus becomes:35 36CPU capacities are obtained by running the Dhrystone benchmark on each CPU at37max frequency (with caches enabled). The obtained DMIPS score is then divided38by the frequency (in MHz) at which the benchmark has been run, so that39DMIPS/MHz are obtained.  Such values are then normalized w.r.t. the highest40score obtained in the system.41 42==========================================433 - capacity-dmips-mhz44==========================================45 46capacity-dmips-mhz is an optional cpu node [1] property: u32 value47representing CPU capacity expressed in normalized DMIPS/MHz. At boot time, the48maximum frequency available to the cpu is then used to calculate the capacity49value internally used by the kernel.50 51capacity-dmips-mhz property is all-or-nothing: if it is specified for a cpu52node, it has to be specified for every other cpu nodes, or the system will53fall back to the default capacity value for every CPU. If cpufreq is not54available, final capacities are calculated by directly using capacity-dmips-55mhz values (normalized w.r.t. the highest value found while parsing the DT).56 57===========================================584 - Examples59===========================================60 61Example 1 (ARM 64-bit, 6-cpu system, two clusters):62The capacities-dmips-mhz or DMIPS/MHz values (scaled to 1024)63are 1024 and 578 for cluster0 and cluster1. Further normalization64is done by the operating system based on cluster0@max-freq=1100 and65cluster1@max-freq=850, final capacities are 1024 for cluster0 and66446 for cluster1 (578*850/1100).67 68cpus {69	#address-cells = <2>;70	#size-cells = <0>;71 72	cpu-map {73		cluster0 {74			core0 {75				cpu = <&A57_0>;76			};77			core1 {78				cpu = <&A57_1>;79			};80		};81 82		cluster1 {83			core0 {84				cpu = <&A53_0>;85			};86			core1 {87				cpu = <&A53_1>;88			};89			core2 {90				cpu = <&A53_2>;91			};92			core3 {93				cpu = <&A53_3>;94			};95		};96	};97 98	idle-states {99		entry-method = "psci";100 101		CPU_SLEEP_0: cpu-sleep-0 {102			compatible = "arm,idle-state";103			arm,psci-suspend-param = <0x0010000>;104			local-timer-stop;105			entry-latency-us = <100>;106			exit-latency-us = <250>;107			min-residency-us = <150>;108		};109 110		CLUSTER_SLEEP_0: cluster-sleep-0 {111			compatible = "arm,idle-state";112			arm,psci-suspend-param = <0x1010000>;113			local-timer-stop;114			entry-latency-us = <800>;115			exit-latency-us = <700>;116			min-residency-us = <2500>;117		};118	};119 120	A57_0: cpu@0 {121		compatible = "arm,cortex-a57";122		reg = <0x0 0x0>;123		device_type = "cpu";124		enable-method = "psci";125		next-level-cache = <&A57_L2>;126		clocks = <&scpi_dvfs 0>;127		cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;128		capacity-dmips-mhz = <1024>;129	};130 131	A57_1: cpu@1 {132		compatible = "arm,cortex-a57";133		reg = <0x0 0x1>;134		device_type = "cpu";135		enable-method = "psci";136		next-level-cache = <&A57_L2>;137		clocks = <&scpi_dvfs 0>;138		cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;139		capacity-dmips-mhz = <1024>;140	};141 142	A53_0: cpu@100 {143		compatible = "arm,cortex-a53";144		reg = <0x0 0x100>;145		device_type = "cpu";146		enable-method = "psci";147		next-level-cache = <&A53_L2>;148		clocks = <&scpi_dvfs 1>;149		cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;150		capacity-dmips-mhz = <578>;151	};152 153	A53_1: cpu@101 {154		compatible = "arm,cortex-a53";155		reg = <0x0 0x101>;156		device_type = "cpu";157		enable-method = "psci";158		next-level-cache = <&A53_L2>;159		clocks = <&scpi_dvfs 1>;160		cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;161		capacity-dmips-mhz = <578>;162	};163 164	A53_2: cpu@102 {165		compatible = "arm,cortex-a53";166		reg = <0x0 0x102>;167		device_type = "cpu";168		enable-method = "psci";169		next-level-cache = <&A53_L2>;170		clocks = <&scpi_dvfs 1>;171		cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;172		capacity-dmips-mhz = <578>;173	};174 175	A53_3: cpu@103 {176		compatible = "arm,cortex-a53";177		reg = <0x0 0x103>;178		device_type = "cpu";179		enable-method = "psci";180		next-level-cache = <&A53_L2>;181		clocks = <&scpi_dvfs 1>;182		cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;183		capacity-dmips-mhz = <578>;184	};185 186	A57_L2: l2-cache0 {187		compatible = "cache";188	};189 190	A53_L2: l2-cache1 {191		compatible = "cache";192	};193};194 195Example 2 (ARM 32-bit, 4-cpu system, two clusters,196	   cpus 0,1@1GHz, cpus 2,3@500MHz):197capacities-dmips-mhz are scaled w.r.t. 2 (cpu@0 and cpu@1), this means that first198cpu@0 and cpu@1 are twice fast than cpu@2 and cpu@3 (at the same frequency)199 200cpus {201	#address-cells = <1>;202	#size-cells = <0>;203 204	cpu0: cpu@0 {205		device_type = "cpu";206		compatible = "arm,cortex-a15";207		reg = <0>;208		capacity-dmips-mhz = <2>;209	};210 211	cpu1: cpu@1 {212		device_type = "cpu";213		compatible = "arm,cortex-a15";214		reg = <1>;215		capacity-dmips-mhz = <2>;216	};217 218	cpu2: cpu@2 {219		device_type = "cpu";220		compatible = "arm,cortex-a15";221		reg = <0x100>;222		capacity-dmips-mhz = <1>;223	};224 225	cpu3: cpu@3 {226		device_type = "cpu";227		compatible = "arm,cortex-a15";228		reg = <0x101>;229		capacity-dmips-mhz = <1>;230	};231};232 233===========================================2345 - References235===========================================236 237[1] ARM Linux Kernel documentation - CPUs bindings238    Documentation/devicetree/bindings/arm/cpus.yaml239