1.. SPDX-License-Identifier: GPL-2.0 2 3======================= 4Energy Model of devices 5======================= 6 71. Overview 8----------- 9 10The Energy Model (EM) framework serves as an interface between drivers knowing 11the power consumed by devices at various performance levels, and the kernel 12subsystems willing to use that information to make energy-aware decisions. 13 14The source of the information about the power consumed by devices can vary greatly 15from one platform to another. These power costs can be estimated using 16devicetree data in some cases. In others, the firmware will know better. 17Alternatively, userspace might be best positioned. And so on. In order to avoid 18each and every client subsystem to re-implement support for each and every 19possible source of information on its own, the EM framework intervenes as an 20abstraction layer which standardizes the format of power cost tables in the 21kernel, hence enabling to avoid redundant work. 22 23The power values might be expressed in milli-Watts or in an 'abstract scale'. 24Multiple subsystems might use the EM and it is up to the system integrator to 25check that the requirements for the power value scale types are met. An example 26can be found in the Energy-Aware Scheduler documentation 27Documentation/scheduler/sched-energy.rst. For some subsystems like thermal or 28powercap power values expressed in an 'abstract scale' might cause issues. 29These subsystems are more interested in estimation of power used in the past, 30thus the real milli-Watts might be needed. An example of these requirements can 31be found in the Intelligent Power Allocation in 32Documentation/driver-api/thermal/power_allocator.rst. 33Kernel subsystems might implement automatic detection to check whether EM 34registered devices have inconsistent scale (based on EM internal flag). 35Important thing to keep in mind is that when the power values are expressed in 36an 'abstract scale' deriving real energy in milli-Joules would not be possible. 37 38The figure below depicts an example of drivers (Arm-specific here, but the 39approach is applicable to any architecture) providing power costs to the EM 40framework, and interested clients reading the data from it:: 41 42 +---------------+ +-----------------+ +---------------+ 43 | Thermal (IPA) | | Scheduler (EAS) | | Other | 44 +---------------+ +-----------------+ +---------------+ 45 | | em_cpu_energy() | 46 | | em_cpu_get() | 47 +---------+ | +---------+ 48 | | | 49 v v v 50 +---------------------+ 51 | Energy Model | 52 | Framework | 53 +---------------------+ 54 ^ ^ ^ 55 | | | em_dev_register_perf_domain() 56 +----------+ | +---------+ 57 | | | 58 +---------------+ +---------------+ +--------------+ 59 | cpufreq-dt | | arm_scmi | | Other | 60 +---------------+ +---------------+ +--------------+ 61 ^ ^ ^ 62 | | | 63 +--------------+ +---------------+ +--------------+ 64 | Device Tree | | Firmware | | ? | 65 +--------------+ +---------------+ +--------------+ 66 67In case of CPU devices the EM framework manages power cost tables per 68'performance domain' in the system. A performance domain is a group of CPUs 69whose performance is scaled together. Performance domains generally have a 701-to-1 mapping with CPUFreq policies. All CPUs in a performance domain are 71required to have the same micro-architecture. CPUs in different performance 72domains can have different micro-architectures. 73 74 752. Core APIs 76------------ 77 782.1 Config options 79^^^^^^^^^^^^^^^^^^ 80 81CONFIG_ENERGY_MODEL must be enabled to use the EM framework. 82 83 842.2 Registration of performance domains 85^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 86 87Registration of 'advanced' EM 88~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 89 90The 'advanced' EM gets it's name due to the fact that the driver is allowed 91to provide more precised power model. It's not limited to some implemented math 92formula in the framework (like it's in 'simple' EM case). It can better reflect 93the real power measurements performed for each performance state. Thus, this 94registration method should be preferred in case considering EM static power 95(leakage) is important. 96 97Drivers are expected to register performance domains into the EM framework by 98calling the following API:: 99 100 int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, 101 struct em_data_callback *cb, cpumask_t *cpus, bool milliwatts); 102 103Drivers must provide a callback function returning <frequency, power> tuples 104for each performance state. The callback function provided by the driver is free 105to fetch data from any relevant location (DT, firmware, ...), and by any mean 106deemed necessary. Only for CPU devices, drivers must specify the CPUs of the 107performance domains using cpumask. For other devices than CPUs the last 108argument must be set to NULL. 109The last argument 'milliwatts' is important to set with correct value. Kernel 110subsystems which use EM might rely on this flag to check if all EM devices use 111the same scale. If there are different scales, these subsystems might decide 112to: return warning/error, stop working or panic. 113See Section 3. for an example of driver implementing this 114callback, or Section 2.4 for further documentation on this API 115 116Registration of EM using DT 117~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 118 119The EM can also be registered using OPP framework and information in DT 120"operating-points-v2". Each OPP entry in DT can be extended with a property 121"opp-microwatt" containing micro-Watts power value. This OPP DT property 122allows a platform to register EM power values which are reflecting total power 123(static + dynamic). These power values might be coming directly from 124experiments and measurements. 125 126Registration of 'simple' EM 127~~~~~~~~~~~~~~~~~~~~~~~~~~~ 128 129The 'simple' EM is registered using the framework helper function 130cpufreq_register_em_with_opp(). It implements a power model which is tight to 131math formula:: 132 133 Power = C * V^2 * f 134 135The EM which is registered using this method might not reflect correctly the 136physics of a real device, e.g. when static power (leakage) is important. 137 138 1392.3 Accessing performance domains 140^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 141 142There are two API functions which provide the access to the energy model: 143em_cpu_get() which takes CPU id as an argument and em_pd_get() with device 144pointer as an argument. It depends on the subsystem which interface it is 145going to use, but in case of CPU devices both functions return the same 146performance domain. 147 148Subsystems interested in the energy model of a CPU can retrieve it using the 149em_cpu_get() API. The energy model tables are allocated once upon creation of 150the performance domains, and kept in memory untouched. 151 152The energy consumed by a performance domain can be estimated using the 153em_cpu_energy() API. The estimation is performed assuming that the schedutil 154CPUfreq governor is in use in case of CPU device. Currently this calculation is 155not provided for other type of devices. 156 157More details about the above APIs can be found in ``<linux/energy_model.h>`` 158or in Section 2.4 159 160 1612.4 Description details of this API 162^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 163.. kernel-doc:: include/linux/energy_model.h 164 :internal: 165 166.. kernel-doc:: kernel/power/energy_model.c 167 :export: 168 169 1703. Example driver 171----------------- 172 173The CPUFreq framework supports dedicated callback for registering 174the EM for a given CPU(s) 'policy' object: cpufreq_driver::register_em(). 175That callback has to be implemented properly for a given driver, 176because the framework would call it at the right time during setup. 177This section provides a simple example of a CPUFreq driver registering a 178performance domain in the Energy Model framework using the (fake) 'foo' 179protocol. The driver implements an est_power() function to be provided to the 180EM framework:: 181 182 -> drivers/cpufreq/foo_cpufreq.c 183 184 01 static int est_power(unsigned long *mW, unsigned long *KHz, 185 02 struct device *dev) 186 03 { 187 04 long freq, power; 188 05 189 06 /* Use the 'foo' protocol to ceil the frequency */ 190 07 freq = foo_get_freq_ceil(dev, *KHz); 191 08 if (freq < 0); 192 09 return freq; 193 10 194 11 /* Estimate the power cost for the dev at the relevant freq. */ 195 12 power = foo_estimate_power(dev, freq); 196 13 if (power < 0); 197 14 return power; 198 15 199 16 /* Return the values to the EM framework */ 200 17 *mW = power; 201 18 *KHz = freq; 202 19 203 20 return 0; 204 21 } 205 22 206 23 static void foo_cpufreq_register_em(struct cpufreq_policy *policy) 207 24 { 208 25 struct em_data_callback em_cb = EM_DATA_CB(est_power); 209 26 struct device *cpu_dev; 210 27 int nr_opp; 211 28 212 29 cpu_dev = get_cpu_device(cpumask_first(policy->cpus)); 213 30 214 31 /* Find the number of OPPs for this policy */ 215 32 nr_opp = foo_get_nr_opp(policy); 216 33 217 34 /* And register the new performance domain */ 218 35 em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb, policy->cpus, 219 36 true); 220 37 } 221 38 222 39 static struct cpufreq_driver foo_cpufreq_driver = { 223 40 .register_em = foo_cpufreq_register_em, 224 41 }; 225