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
87Drivers are expected to register performance domains into the EM framework by
88calling the following API::
89
90  int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
91		struct em_data_callback *cb, cpumask_t *cpus, bool milliwatts);
92
93Drivers must provide a callback function returning <frequency, power> tuples
94for each performance state. The callback function provided by the driver is free
95to fetch data from any relevant location (DT, firmware, ...), and by any mean
96deemed necessary. Only for CPU devices, drivers must specify the CPUs of the
97performance domains using cpumask. For other devices than CPUs the last
98argument must be set to NULL.
99The last argument 'milliwatts' is important to set with correct value. Kernel
100subsystems which use EM might rely on this flag to check if all EM devices use
101the same scale. If there are different scales, these subsystems might decide
102to: return warning/error, stop working or panic.
103See Section 3. for an example of driver implementing this
104callback, or Section 2.4 for further documentation on this API
105
106
1072.3 Accessing performance domains
108^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
109
110There are two API functions which provide the access to the energy model:
111em_cpu_get() which takes CPU id as an argument and em_pd_get() with device
112pointer as an argument. It depends on the subsystem which interface it is
113going to use, but in case of CPU devices both functions return the same
114performance domain.
115
116Subsystems interested in the energy model of a CPU can retrieve it using the
117em_cpu_get() API. The energy model tables are allocated once upon creation of
118the performance domains, and kept in memory untouched.
119
120The energy consumed by a performance domain can be estimated using the
121em_cpu_energy() API. The estimation is performed assuming that the schedutil
122CPUfreq governor is in use in case of CPU device. Currently this calculation is
123not provided for other type of devices.
124
125More details about the above APIs can be found in ``<linux/energy_model.h>``
126or in Section 2.4
127
128
1292.4 Description details of this API
130^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
131.. kernel-doc:: include/linux/energy_model.h
132   :internal:
133
134.. kernel-doc:: kernel/power/energy_model.c
135   :export:
136
137
1383. Example driver
139-----------------
140
141This section provides a simple example of a CPUFreq driver registering a
142performance domain in the Energy Model framework using the (fake) 'foo'
143protocol. The driver implements an est_power() function to be provided to the
144EM framework::
145
146  -> drivers/cpufreq/foo_cpufreq.c
147
148  01	static int est_power(unsigned long *mW, unsigned long *KHz,
149  02			struct device *dev)
150  03	{
151  04		long freq, power;
152  05
153  06		/* Use the 'foo' protocol to ceil the frequency */
154  07		freq = foo_get_freq_ceil(dev, *KHz);
155  08		if (freq < 0);
156  09			return freq;
157  10
158  11		/* Estimate the power cost for the dev at the relevant freq. */
159  12		power = foo_estimate_power(dev, freq);
160  13		if (power < 0);
161  14			return power;
162  15
163  16		/* Return the values to the EM framework */
164  17		*mW = power;
165  18		*KHz = freq;
166  19
167  20		return 0;
168  21	}
169  22
170  23	static int foo_cpufreq_init(struct cpufreq_policy *policy)
171  24	{
172  25		struct em_data_callback em_cb = EM_DATA_CB(est_power);
173  26		struct device *cpu_dev;
174  27		int nr_opp, ret;
175  28
176  29		cpu_dev = get_cpu_device(cpumask_first(policy->cpus));
177  30
178  31     	/* Do the actual CPUFreq init work ... */
179  32     	ret = do_foo_cpufreq_init(policy);
180  33     	if (ret)
181  34     		return ret;
182  35
183  36     	/* Find the number of OPPs for this policy */
184  37     	nr_opp = foo_get_nr_opp(policy);
185  38
186  39     	/* And register the new performance domain */
187  40     	em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb, policy->cpus,
188  41					    true);
189  42
190  43	        return 0;
191  44	}
192