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 'simple' EM
117~~~~~~~~~~~~~~~~~~~~~~~~~~~
118
119The 'simple' EM is registered using the framework helper function
120cpufreq_register_em_with_opp(). It implements a power model which is tight to
121math formula::
122
123	Power = C * V^2 * f
124
125The EM which is registered using this method might not reflect correctly the
126physics of a real device, e.g. when static power (leakage) is important.
127
128
1292.3 Accessing performance domains
130^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
131
132There are two API functions which provide the access to the energy model:
133em_cpu_get() which takes CPU id as an argument and em_pd_get() with device
134pointer as an argument. It depends on the subsystem which interface it is
135going to use, but in case of CPU devices both functions return the same
136performance domain.
137
138Subsystems interested in the energy model of a CPU can retrieve it using the
139em_cpu_get() API. The energy model tables are allocated once upon creation of
140the performance domains, and kept in memory untouched.
141
142The energy consumed by a performance domain can be estimated using the
143em_cpu_energy() API. The estimation is performed assuming that the schedutil
144CPUfreq governor is in use in case of CPU device. Currently this calculation is
145not provided for other type of devices.
146
147More details about the above APIs can be found in ``<linux/energy_model.h>``
148or in Section 2.4
149
150
1512.4 Description details of this API
152^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
153.. kernel-doc:: include/linux/energy_model.h
154   :internal:
155
156.. kernel-doc:: kernel/power/energy_model.c
157   :export:
158
159
1603. Example driver
161-----------------
162
163The CPUFreq framework supports dedicated callback for registering
164the EM for a given CPU(s) 'policy' object: cpufreq_driver::register_em().
165That callback has to be implemented properly for a given driver,
166because the framework would call it at the right time during setup.
167This section provides a simple example of a CPUFreq driver registering a
168performance domain in the Energy Model framework using the (fake) 'foo'
169protocol. The driver implements an est_power() function to be provided to the
170EM framework::
171
172  -> drivers/cpufreq/foo_cpufreq.c
173
174  01	static int est_power(unsigned long *mW, unsigned long *KHz,
175  02			struct device *dev)
176  03	{
177  04		long freq, power;
178  05
179  06		/* Use the 'foo' protocol to ceil the frequency */
180  07		freq = foo_get_freq_ceil(dev, *KHz);
181  08		if (freq < 0);
182  09			return freq;
183  10
184  11		/* Estimate the power cost for the dev at the relevant freq. */
185  12		power = foo_estimate_power(dev, freq);
186  13		if (power < 0);
187  14			return power;
188  15
189  16		/* Return the values to the EM framework */
190  17		*mW = power;
191  18		*KHz = freq;
192  19
193  20		return 0;
194  21	}
195  22
196  23	static void foo_cpufreq_register_em(struct cpufreq_policy *policy)
197  24	{
198  25		struct em_data_callback em_cb = EM_DATA_CB(est_power);
199  26		struct device *cpu_dev;
200  27		int nr_opp;
201  28
202  29		cpu_dev = get_cpu_device(cpumask_first(policy->cpus));
203  30
204  31     	/* Find the number of OPPs for this policy */
205  32     	nr_opp = foo_get_nr_opp(policy);
206  33
207  34     	/* And register the new performance domain */
208  35     	em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb, policy->cpus,
209  36					    true);
210  37	}
211  38
212  39	static struct cpufreq_driver foo_cpufreq_driver = {
213  40		.register_em = foo_cpufreq_register_em,
214  41	};
215