1 .. SPDX-License-Identifier: GPL-2.0 1 .. SPDX-License-Identifier: GPL-2.0
2 2
3 ======================= 3 =======================
4 Energy Model of devices 4 Energy Model of devices
5 ======================= 5 =======================
6 6
7 1. Overview 7 1. Overview
8 ----------- 8 -----------
9 9
10 The Energy Model (EM) framework serves as an i 10 The Energy Model (EM) framework serves as an interface between drivers knowing
11 the power consumed by devices at various perfo 11 the power consumed by devices at various performance levels, and the kernel
12 subsystems willing to use that information to 12 subsystems willing to use that information to make energy-aware decisions.
13 13
14 The source of the information about the power 14 The source of the information about the power consumed by devices can vary greatly
15 from one platform to another. These power cost 15 from one platform to another. These power costs can be estimated using
16 devicetree data in some cases. In others, the 16 devicetree data in some cases. In others, the firmware will know better.
17 Alternatively, userspace might be best positio 17 Alternatively, userspace might be best positioned. And so on. In order to avoid
18 each and every client subsystem to re-implemen 18 each and every client subsystem to re-implement support for each and every
19 possible source of information on its own, the 19 possible source of information on its own, the EM framework intervenes as an
20 abstraction layer which standardizes the forma 20 abstraction layer which standardizes the format of power cost tables in the
21 kernel, hence enabling to avoid redundant work 21 kernel, hence enabling to avoid redundant work.
22 22
23 The power values might be expressed in micro-W 23 The power values might be expressed in micro-Watts or in an 'abstract scale'.
24 Multiple subsystems might use the EM and it is 24 Multiple subsystems might use the EM and it is up to the system integrator to
25 check that the requirements for the power valu 25 check that the requirements for the power value scale types are met. An example
26 can be found in the Energy-Aware Scheduler doc 26 can be found in the Energy-Aware Scheduler documentation
27 Documentation/scheduler/sched-energy.rst. For 27 Documentation/scheduler/sched-energy.rst. For some subsystems like thermal or
28 powercap power values expressed in an 'abstrac 28 powercap power values expressed in an 'abstract scale' might cause issues.
29 These subsystems are more interested in estima 29 These subsystems are more interested in estimation of power used in the past,
30 thus the real micro-Watts might be needed. An 30 thus the real micro-Watts might be needed. An example of these requirements can
31 be found in the Intelligent Power Allocation i 31 be found in the Intelligent Power Allocation in
32 Documentation/driver-api/thermal/power_allocat 32 Documentation/driver-api/thermal/power_allocator.rst.
33 Kernel subsystems might implement automatic de 33 Kernel subsystems might implement automatic detection to check whether EM
34 registered devices have inconsistent scale (ba 34 registered devices have inconsistent scale (based on EM internal flag).
35 Important thing to keep in mind is that when t 35 Important thing to keep in mind is that when the power values are expressed in
36 an 'abstract scale' deriving real energy in mi 36 an 'abstract scale' deriving real energy in micro-Joules would not be possible.
37 37
38 The figure below depicts an example of drivers 38 The figure below depicts an example of drivers (Arm-specific here, but the
39 approach is applicable to any architecture) pr 39 approach is applicable to any architecture) providing power costs to the EM
40 framework, and interested clients reading the 40 framework, and interested clients reading the data from it::
41 41
42 +---------------+ +-----------------+ 42 +---------------+ +-----------------+ +---------------+
43 | Thermal (IPA) | | Scheduler (EAS) | 43 | Thermal (IPA) | | Scheduler (EAS) | | Other |
44 +---------------+ +-----------------+ 44 +---------------+ +-----------------+ +---------------+
45 | | em_cpu_en 45 | | em_cpu_energy() |
46 | | em_cpu_ge 46 | | em_cpu_get() |
47 +---------+ | + 47 +---------+ | +---------+
48 | | | 48 | | |
49 v v v 49 v v v
50 +--------------------- 50 +---------------------+
51 | Energy Model 51 | Energy Model |
52 | Framework 52 | Framework |
53 +--------------------- 53 +---------------------+
54 ^ ^ ^ 54 ^ ^ ^
55 | | | e 55 | | | em_dev_register_perf_domain()
56 +----------+ | +-- 56 +----------+ | +---------+
57 | | 57 | | |
58 +---------------+ +---------------+ 58 +---------------+ +---------------+ +--------------+
59 | cpufreq-dt | | arm_scmi | 59 | cpufreq-dt | | arm_scmi | | Other |
60 +---------------+ +---------------+ 60 +---------------+ +---------------+ +--------------+
61 ^ ^ 61 ^ ^ ^
62 | | 62 | | |
63 +--------------+ +---------------+ 63 +--------------+ +---------------+ +--------------+
64 | Device Tree | | Firmware | 64 | Device Tree | | Firmware | | ? |
65 +--------------+ +---------------+ 65 +--------------+ +---------------+ +--------------+
66 66
67 In case of CPU devices the EM framework manage 67 In case of CPU devices the EM framework manages power cost tables per
68 'performance domain' in the system. A performa 68 'performance domain' in the system. A performance domain is a group of CPUs
69 whose performance is scaled together. Performa 69 whose performance is scaled together. Performance domains generally have a
70 1-to-1 mapping with CPUFreq policies. All CPUs 70 1-to-1 mapping with CPUFreq policies. All CPUs in a performance domain are
71 required to have the same micro-architecture. 71 required to have the same micro-architecture. CPUs in different performance
72 domains can have different micro-architectures 72 domains can have different micro-architectures.
73 73
74 To better reflect power variation due to stati 74 To better reflect power variation due to static power (leakage) the EM
75 supports runtime modifications of the power va 75 supports runtime modifications of the power values. The mechanism relies on
76 RCU to free the modifiable EM perf_state table 76 RCU to free the modifiable EM perf_state table memory. Its user, the task
77 scheduler, also uses RCU to access this memory 77 scheduler, also uses RCU to access this memory. The EM framework provides
78 API for allocating/freeing the new memory for 78 API for allocating/freeing the new memory for the modifiable EM table.
79 The old memory is freed automatically using RC 79 The old memory is freed automatically using RCU callback mechanism when there
80 are no owners anymore for the given EM runtime 80 are no owners anymore for the given EM runtime table instance. This is tracked
81 using kref mechanism. The device driver which 81 using kref mechanism. The device driver which provided the new EM at runtime,
82 should call EM API to free it safely when it's 82 should call EM API to free it safely when it's no longer needed. The EM
83 framework will handle the clean-up when it's p 83 framework will handle the clean-up when it's possible.
84 84
85 The kernel code which want to modify the EM va 85 The kernel code which want to modify the EM values is protected from concurrent
86 access using a mutex. Therefore, the device dr 86 access using a mutex. Therefore, the device driver code must run in sleeping
87 context when it tries to modify the EM. 87 context when it tries to modify the EM.
88 88
89 With the runtime modifiable EM we switch from 89 With the runtime modifiable EM we switch from a 'single and during the entire
90 runtime static EM' (system property) design to 90 runtime static EM' (system property) design to a 'single EM which can be
91 changed during runtime according e.g. to the w 91 changed during runtime according e.g. to the workload' (system and workload
92 property) design. 92 property) design.
93 93
94 It is possible also to modify the CPU performa 94 It is possible also to modify the CPU performance values for each EM's
95 performance state. Thus, the full power and pe 95 performance state. Thus, the full power and performance profile (which
96 is an exponential curve) can be changed accord 96 is an exponential curve) can be changed according e.g. to the workload
97 or system property. 97 or system property.
98 98
99 99
100 2. Core APIs 100 2. Core APIs
101 ------------ 101 ------------
102 102
103 2.1 Config options 103 2.1 Config options
104 ^^^^^^^^^^^^^^^^^^ 104 ^^^^^^^^^^^^^^^^^^
105 105
106 CONFIG_ENERGY_MODEL must be enabled to use the 106 CONFIG_ENERGY_MODEL must be enabled to use the EM framework.
107 107
108 108
109 2.2 Registration of performance domains 109 2.2 Registration of performance domains
110 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 110 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
111 111
112 Registration of 'advanced' EM 112 Registration of 'advanced' EM
113 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 113 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
114 114
115 The 'advanced' EM gets its name due to the fac 115 The 'advanced' EM gets its name due to the fact that the driver is allowed
116 to provide more precised power model. It's not 116 to provide more precised power model. It's not limited to some implemented math
117 formula in the framework (like it is in 'simpl 117 formula in the framework (like it is in 'simple' EM case). It can better reflect
118 the real power measurements performed for each 118 the real power measurements performed for each performance state. Thus, this
119 registration method should be preferred in cas 119 registration method should be preferred in case considering EM static power
120 (leakage) is important. 120 (leakage) is important.
121 121
122 Drivers are expected to register performance d 122 Drivers are expected to register performance domains into the EM framework by
123 calling the following API:: 123 calling the following API::
124 124
125 int em_dev_register_perf_domain(struct devic 125 int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
126 struct em_data_callback *cb, c 126 struct em_data_callback *cb, cpumask_t *cpus, bool microwatts);
127 127
128 Drivers must provide a callback function retur 128 Drivers must provide a callback function returning <frequency, power> tuples
129 for each performance state. The callback funct 129 for each performance state. The callback function provided by the driver is free
130 to fetch data from any relevant location (DT, 130 to fetch data from any relevant location (DT, firmware, ...), and by any mean
131 deemed necessary. Only for CPU devices, driver 131 deemed necessary. Only for CPU devices, drivers must specify the CPUs of the
132 performance domains using cpumask. For other d 132 performance domains using cpumask. For other devices than CPUs the last
133 argument must be set to NULL. 133 argument must be set to NULL.
134 The last argument 'microwatts' is important to 134 The last argument 'microwatts' is important to set with correct value. Kernel
135 subsystems which use EM might rely on this fla 135 subsystems which use EM might rely on this flag to check if all EM devices use
136 the same scale. If there are different scales, 136 the same scale. If there are different scales, these subsystems might decide
137 to return warning/error, stop working or panic 137 to return warning/error, stop working or panic.
138 See Section 3. for an example of driver implem 138 See Section 3. for an example of driver implementing this
139 callback, or Section 2.4 for further documenta 139 callback, or Section 2.4 for further documentation on this API
140 140
141 Registration of EM using DT 141 Registration of EM using DT
142 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 142 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
143 143
144 The EM can also be registered using OPP frame 144 The EM can also be registered using OPP framework and information in DT
145 "operating-points-v2". Each OPP entry in DT ca 145 "operating-points-v2". Each OPP entry in DT can be extended with a property
146 "opp-microwatt" containing micro-Watts power v 146 "opp-microwatt" containing micro-Watts power value. This OPP DT property
147 allows a platform to register EM power values 147 allows a platform to register EM power values which are reflecting total power
148 (static + dynamic). These power values might b 148 (static + dynamic). These power values might be coming directly from
149 experiments and measurements. 149 experiments and measurements.
150 150
151 Registration of 'artificial' EM 151 Registration of 'artificial' EM
152 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 152 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
153 153
154 There is an option to provide a custom callbac 154 There is an option to provide a custom callback for drivers missing detailed
155 knowledge about power value for each performan 155 knowledge about power value for each performance state. The callback
156 .get_cost() is optional and provides the 'cost 156 .get_cost() is optional and provides the 'cost' values used by the EAS.
157 This is useful for platforms that only provide 157 This is useful for platforms that only provide information on relative
158 efficiency between CPU types, where one could 158 efficiency between CPU types, where one could use the information to
159 create an abstract power model. But even an ab 159 create an abstract power model. But even an abstract power model can
160 sometimes be hard to fit in, given the input p 160 sometimes be hard to fit in, given the input power value size restrictions.
161 The .get_cost() allows to provide the 'cost' v 161 The .get_cost() allows to provide the 'cost' values which reflect the
162 efficiency of the CPUs. This would allow to pr 162 efficiency of the CPUs. This would allow to provide EAS information which
163 has different relation than what would be forc 163 has different relation than what would be forced by the EM internal
164 formulas calculating 'cost' values. To registe 164 formulas calculating 'cost' values. To register an EM for such platform, the
165 driver must set the flag 'microwatts' to 0, pr 165 driver must set the flag 'microwatts' to 0, provide .get_power() callback
166 and provide .get_cost() callback. The EM frame 166 and provide .get_cost() callback. The EM framework would handle such platform
167 properly during registration. A flag EM_PERF_D 167 properly during registration. A flag EM_PERF_DOMAIN_ARTIFICIAL is set for such
168 platform. Special care should be taken by othe 168 platform. Special care should be taken by other frameworks which are using EM
169 to test and treat this flag properly. 169 to test and treat this flag properly.
170 170
171 Registration of 'simple' EM 171 Registration of 'simple' EM
172 ~~~~~~~~~~~~~~~~~~~~~~~~~~~ 172 ~~~~~~~~~~~~~~~~~~~~~~~~~~~
173 173
174 The 'simple' EM is registered using the framew 174 The 'simple' EM is registered using the framework helper function
175 cpufreq_register_em_with_opp(). It implements 175 cpufreq_register_em_with_opp(). It implements a power model which is tight to
176 math formula:: 176 math formula::
177 177
178 Power = C * V^2 * f 178 Power = C * V^2 * f
179 179
180 The EM which is registered using this method m 180 The EM which is registered using this method might not reflect correctly the
181 physics of a real device, e.g. when static pow 181 physics of a real device, e.g. when static power (leakage) is important.
182 182
183 183
184 2.3 Accessing performance domains 184 2.3 Accessing performance domains
185 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 185 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
186 186
187 There are two API functions which provide the 187 There are two API functions which provide the access to the energy model:
188 em_cpu_get() which takes CPU id as an argument 188 em_cpu_get() which takes CPU id as an argument and em_pd_get() with device
189 pointer as an argument. It depends on the subs 189 pointer as an argument. It depends on the subsystem which interface it is
190 going to use, but in case of CPU devices both 190 going to use, but in case of CPU devices both functions return the same
191 performance domain. 191 performance domain.
192 192
193 Subsystems interested in the energy model of a 193 Subsystems interested in the energy model of a CPU can retrieve it using the
194 em_cpu_get() API. The energy model tables are 194 em_cpu_get() API. The energy model tables are allocated once upon creation of
195 the performance domains, and kept in memory un 195 the performance domains, and kept in memory untouched.
196 196
197 The energy consumed by a performance domain ca 197 The energy consumed by a performance domain can be estimated using the
198 em_cpu_energy() API. The estimation is perform 198 em_cpu_energy() API. The estimation is performed assuming that the schedutil
199 CPUfreq governor is in use in case of CPU devi 199 CPUfreq governor is in use in case of CPU device. Currently this calculation is
200 not provided for other type of devices. 200 not provided for other type of devices.
201 201
202 More details about the above APIs can be found 202 More details about the above APIs can be found in ``<linux/energy_model.h>``
203 or in Section 2.5 203 or in Section 2.5
204 204
205 205
206 2.4 Runtime modifications 206 2.4 Runtime modifications
207 ^^^^^^^^^^^^^^^^^^^^^^^^^ 207 ^^^^^^^^^^^^^^^^^^^^^^^^^
208 208
209 Drivers willing to update the EM at runtime sh 209 Drivers willing to update the EM at runtime should use the following dedicated
210 function to allocate a new instance of the mod 210 function to allocate a new instance of the modified EM. The API is listed
211 below:: 211 below::
212 212
213 struct em_perf_table __rcu *em_table_alloc(s 213 struct em_perf_table __rcu *em_table_alloc(struct em_perf_domain *pd);
214 214
215 This allows to allocate a structure which cont 215 This allows to allocate a structure which contains the new EM table with
216 also RCU and kref needed by the EM framework. 216 also RCU and kref needed by the EM framework. The 'struct em_perf_table'
217 contains array 'struct em_perf_state state[]' 217 contains array 'struct em_perf_state state[]' which is a list of performance
218 states in ascending order. That list must be p 218 states in ascending order. That list must be populated by the device driver
219 which wants to update the EM. The list of freq 219 which wants to update the EM. The list of frequencies can be taken from
220 existing EM (created during boot). The content 220 existing EM (created during boot). The content in the 'struct em_perf_state'
221 must be populated by the driver as well. 221 must be populated by the driver as well.
222 222
223 This is the API which does the EM update, usin 223 This is the API which does the EM update, using RCU pointers swap::
224 224
225 int em_dev_update_perf_domain(struct device 225 int em_dev_update_perf_domain(struct device *dev,
226 struct em_perf_table _ 226 struct em_perf_table __rcu *new_table);
227 227
228 Drivers must provide a pointer to the allocate 228 Drivers must provide a pointer to the allocated and initialized new EM
229 'struct em_perf_table'. That new EM will be sa 229 'struct em_perf_table'. That new EM will be safely used inside the EM framework
230 and will be visible to other sub-systems in th 230 and will be visible to other sub-systems in the kernel (thermal, powercap).
231 The main design goal for this API is to be fas 231 The main design goal for this API is to be fast and avoid extra calculations
232 or memory allocations at runtime. When pre-com 232 or memory allocations at runtime. When pre-computed EMs are available in the
233 device driver, than it should be possible to s 233 device driver, than it should be possible to simply re-use them with low
234 performance overhead. 234 performance overhead.
235 235
236 In order to free the EM, provided earlier by t 236 In order to free the EM, provided earlier by the driver (e.g. when the module
237 is unloaded), there is a need to call the API: 237 is unloaded), there is a need to call the API::
238 238
239 void em_table_free(struct em_perf_table __rc 239 void em_table_free(struct em_perf_table __rcu *table);
240 240
241 It will allow the EM framework to safely remov 241 It will allow the EM framework to safely remove the memory, when there is
242 no other sub-system using it, e.g. EAS. 242 no other sub-system using it, e.g. EAS.
243 243
244 To use the power values in other sub-systems ( 244 To use the power values in other sub-systems (like thermal, powercap) there is
245 a need to call API which protects the reader a 245 a need to call API which protects the reader and provide consistency of the EM
246 table data:: 246 table data::
247 247
248 struct em_perf_state *em_perf_state_from_pd( 248 struct em_perf_state *em_perf_state_from_pd(struct em_perf_domain *pd);
249 249
250 It returns the 'struct em_perf_state' pointer 250 It returns the 'struct em_perf_state' pointer which is an array of performance
251 states in ascending order. 251 states in ascending order.
252 This function must be called in the RCU read l 252 This function must be called in the RCU read lock section (after the
253 rcu_read_lock()). When the EM table is not nee 253 rcu_read_lock()). When the EM table is not needed anymore there is a need to
254 call rcu_real_unlock(). In this way the EM saf 254 call rcu_real_unlock(). In this way the EM safely uses the RCU read section
255 and protects the users. It also allows the EM 255 and protects the users. It also allows the EM framework to manage the memory
256 and free it. More details how to use it can be 256 and free it. More details how to use it can be found in Section 3.2 in the
257 example driver. 257 example driver.
258 258
259 There is dedicated API for device drivers to c 259 There is dedicated API for device drivers to calculate em_perf_state::cost
260 values:: 260 values::
261 261
262 int em_dev_compute_costs(struct device *dev, 262 int em_dev_compute_costs(struct device *dev, struct em_perf_state *table,
263 int nr_states); 263 int nr_states);
264 264
265 These 'cost' values from EM are used in EAS. T 265 These 'cost' values from EM are used in EAS. The new EM table should be passed
266 together with the number of entries and device 266 together with the number of entries and device pointer. When the computation
267 of the cost values is done properly the return 267 of the cost values is done properly the return value from the function is 0.
268 The function takes care for right setting of i 268 The function takes care for right setting of inefficiency for each performance
269 state as well. It updates em_perf_state::flags 269 state as well. It updates em_perf_state::flags accordingly.
270 Then such prepared new EM can be passed to the 270 Then such prepared new EM can be passed to the em_dev_update_perf_domain()
271 function, which will allow to use it. 271 function, which will allow to use it.
272 272
273 More details about the above APIs can be found 273 More details about the above APIs can be found in ``<linux/energy_model.h>``
274 or in Section 3.2 with an example code showing 274 or in Section 3.2 with an example code showing simple implementation of the
275 updating mechanism in a device driver. 275 updating mechanism in a device driver.
276 276
277 277
278 2.5 Description details of this API 278 2.5 Description details of this API
279 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 279 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
280 .. kernel-doc:: include/linux/energy_model.h 280 .. kernel-doc:: include/linux/energy_model.h
281 :internal: 281 :internal:
282 282
283 .. kernel-doc:: kernel/power/energy_model.c 283 .. kernel-doc:: kernel/power/energy_model.c
284 :export: 284 :export:
285 285
286 286
287 3. Examples 287 3. Examples
288 ----------- 288 -----------
289 289
290 3.1 Example driver with EM registration 290 3.1 Example driver with EM registration
291 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 291 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
292 292
293 The CPUFreq framework supports dedicated callb 293 The CPUFreq framework supports dedicated callback for registering
294 the EM for a given CPU(s) 'policy' object: cpu 294 the EM for a given CPU(s) 'policy' object: cpufreq_driver::register_em().
295 That callback has to be implemented properly f 295 That callback has to be implemented properly for a given driver,
296 because the framework would call it at the rig 296 because the framework would call it at the right time during setup.
297 This section provides a simple example of a CP 297 This section provides a simple example of a CPUFreq driver registering a
298 performance domain in the Energy Model framewo 298 performance domain in the Energy Model framework using the (fake) 'foo'
299 protocol. The driver implements an est_power() 299 protocol. The driver implements an est_power() function to be provided to the
300 EM framework:: 300 EM framework::
301 301
302 -> drivers/cpufreq/foo_cpufreq.c 302 -> drivers/cpufreq/foo_cpufreq.c
303 303
304 01 static int est_power(struct device *de 304 01 static int est_power(struct device *dev, unsigned long *mW,
305 02 unsigned long *KHz) 305 02 unsigned long *KHz)
306 03 { 306 03 {
307 04 long freq, power; 307 04 long freq, power;
308 05 308 05
309 06 /* Use the 'foo' protocol to c 309 06 /* Use the 'foo' protocol to ceil the frequency */
310 07 freq = foo_get_freq_ceil(dev, 310 07 freq = foo_get_freq_ceil(dev, *KHz);
311 08 if (freq < 0); 311 08 if (freq < 0);
312 09 return freq; 312 09 return freq;
313 10 313 10
314 11 /* Estimate the power cost for 314 11 /* Estimate the power cost for the dev at the relevant freq. */
315 12 power = foo_estimate_power(dev 315 12 power = foo_estimate_power(dev, freq);
316 13 if (power < 0); 316 13 if (power < 0);
317 14 return power; 317 14 return power;
318 15 318 15
319 16 /* Return the values to the EM 319 16 /* Return the values to the EM framework */
320 17 *mW = power; 320 17 *mW = power;
321 18 *KHz = freq; 321 18 *KHz = freq;
322 19 322 19
323 20 return 0; 323 20 return 0;
324 21 } 324 21 }
325 22 325 22
326 23 static void foo_cpufreq_register_em(st 326 23 static void foo_cpufreq_register_em(struct cpufreq_policy *policy)
327 24 { 327 24 {
328 25 struct em_data_callback em_cb 328 25 struct em_data_callback em_cb = EM_DATA_CB(est_power);
329 26 struct device *cpu_dev; 329 26 struct device *cpu_dev;
330 27 int nr_opp; 330 27 int nr_opp;
331 28 331 28
332 29 cpu_dev = get_cpu_device(cpuma 332 29 cpu_dev = get_cpu_device(cpumask_first(policy->cpus));
333 30 333 30
334 31 /* Find the number of OPPs for 334 31 /* Find the number of OPPs for this policy */
335 32 nr_opp = foo_get_nr_opp(policy 335 32 nr_opp = foo_get_nr_opp(policy);
336 33 336 33
337 34 /* And register the new perfor 337 34 /* And register the new performance domain */
338 35 em_dev_register_perf_domain(cp 338 35 em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb, policy->cpus,
339 36 tr 339 36 true);
340 37 } 340 37 }
341 38 341 38
342 39 static struct cpufreq_driver foo_cpufr 342 39 static struct cpufreq_driver foo_cpufreq_driver = {
343 40 .register_em = foo_cpufreq_reg 343 40 .register_em = foo_cpufreq_register_em,
344 41 }; 344 41 };
345 345
346 346
347 3.2 Example driver with EM modification 347 3.2 Example driver with EM modification
348 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 348 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
349 349
350 This section provides a simple example of a th 350 This section provides a simple example of a thermal driver modifying the EM.
351 The driver implements a foo_thermal_em_update( 351 The driver implements a foo_thermal_em_update() function. The driver is woken
352 up periodically to check the temperature and m 352 up periodically to check the temperature and modify the EM data::
353 353
354 -> drivers/soc/example/example_em_mod.c 354 -> drivers/soc/example/example_em_mod.c
355 355
356 01 static void foo_get_new_em(struct foo_ 356 01 static void foo_get_new_em(struct foo_context *ctx)
357 02 { 357 02 {
358 03 struct em_perf_table __rcu *em 358 03 struct em_perf_table __rcu *em_table;
359 04 struct em_perf_state *table, * 359 04 struct em_perf_state *table, *new_table;
360 05 struct device *dev = ctx->dev; 360 05 struct device *dev = ctx->dev;
361 06 struct em_perf_domain *pd; 361 06 struct em_perf_domain *pd;
362 07 unsigned long freq; 362 07 unsigned long freq;
363 08 int i, ret; 363 08 int i, ret;
364 09 364 09
365 10 pd = em_pd_get(dev); 365 10 pd = em_pd_get(dev);
366 11 if (!pd) 366 11 if (!pd)
367 12 return; 367 12 return;
368 13 368 13
369 14 em_table = em_table_alloc(pd); 369 14 em_table = em_table_alloc(pd);
370 15 if (!em_table) 370 15 if (!em_table)
371 16 return; 371 16 return;
372 17 372 17
373 18 new_table = em_table->state; 373 18 new_table = em_table->state;
374 19 374 19
375 20 rcu_read_lock(); 375 20 rcu_read_lock();
376 21 table = em_perf_state_from_pd( 376 21 table = em_perf_state_from_pd(pd);
377 22 for (i = 0; i < pd->nr_perf_st 377 22 for (i = 0; i < pd->nr_perf_states; i++) {
378 23 freq = table[i].freque 378 23 freq = table[i].frequency;
379 24 foo_get_power_perf_val 379 24 foo_get_power_perf_values(dev, freq, &new_table[i]);
380 25 } 380 25 }
381 26 rcu_read_unlock(); 381 26 rcu_read_unlock();
382 27 382 27
383 28 /* Calculate 'cost' values for 383 28 /* Calculate 'cost' values for EAS */
384 29 ret = em_dev_compute_costs(dev 384 29 ret = em_dev_compute_costs(dev, table, pd->nr_perf_states);
385 30 if (ret) { 385 30 if (ret) {
386 31 dev_warn(dev, "EM: com 386 31 dev_warn(dev, "EM: compute costs failed %d\n", ret);
387 32 em_free_table(em_table 387 32 em_free_table(em_table);
388 33 return; 388 33 return;
389 34 } 389 34 }
390 35 390 35
391 36 ret = em_dev_update_perf_domai 391 36 ret = em_dev_update_perf_domain(dev, em_table);
392 37 if (ret) { 392 37 if (ret) {
393 38 dev_warn(dev, "EM: upd 393 38 dev_warn(dev, "EM: update failed %d\n", ret);
394 39 em_free_table(em_table 394 39 em_free_table(em_table);
395 40 return; 395 40 return;
396 41 } 396 41 }
397 42 397 42
398 43 /* 398 43 /*
399 44 * Since it's one-time-update 399 44 * Since it's one-time-update drop the usage counter.
400 45 * The EM framework will later 400 45 * The EM framework will later free the table when needed.
401 46 */ 401 46 */
402 47 em_table_free(em_table); 402 47 em_table_free(em_table);
403 48 } 403 48 }
404 49 404 49
405 50 /* 405 50 /*
406 51 * Function called periodically to che 406 51 * Function called periodically to check the temperature and
407 52 * update the EM if needed 407 52 * update the EM if needed
408 53 */ 408 53 */
409 54 static void foo_thermal_em_update(stru 409 54 static void foo_thermal_em_update(struct foo_context *ctx)
410 55 { 410 55 {
411 56 struct device *dev = ctx->dev; 411 56 struct device *dev = ctx->dev;
412 57 int cpu; 412 57 int cpu;
413 58 413 58
414 59 ctx->temperature = foo_get_tem 414 59 ctx->temperature = foo_get_temp(dev, ctx);
415 60 if (ctx->temperature < FOO_EM_ 415 60 if (ctx->temperature < FOO_EM_UPDATE_TEMP_THRESHOLD)
416 61 return; 416 61 return;
417 62 417 62
418 63 foo_get_new_em(ctx); 418 63 foo_get_new_em(ctx);
419 64 } 419 64 }
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.