1 Generic OPP (Operating Performance Points) Bindings
2 ----------------------------------------------------
4 Devices work at voltage-current-frequency combinations and some implementations
5 have the liberty of choosing these. These combinations are called Operating
6 Performance Points aka OPPs. This document defines bindings for these OPPs
7 applicable across wide range of devices. For illustration purpose, this document
10 This document contain multiple versions of OPP binding and only one of them
11 should be used per device.
13 Binding 1: operating-points
14 ============================
16 This binding only supports voltage-frequency pairs.
19 - operating-points: An array of 2-tuples items, and each item consists
20 of frequency and voltage like <freq-kHz vol-uV>.
21 freq: clock frequency in kHz
22 vol: voltage in microvolt
27 compatible = "arm,cortex-a9";
29 next-level-cache = <&L2>;
39 Binding 2: operating-points-v2
40 ============================
42 * Property: operating-points-v2
44 Devices supporting OPPs must set their "operating-points-v2" property with
45 phandle to a OPP table in their DT node. The OPP core will use this phandle to
46 find the operating points for the device.
48 This can contain more than one phandle for power domain providers that provide
49 multiple power domains. That is, one phandle for each power domain. If only one
50 phandle is available, then the same OPP table will be used for all power domains
51 provided by the power domain provider.
53 If required, this can be extended for SoC vendor specific bindings. Such bindings
54 should be documented as Documentation/devicetree/bindings/power/<vendor>-opp.txt
55 and should have a compatible description like: "operating-points-v2-<vendor>".
59 This describes the OPPs belonging to a device. This node can have following
63 - compatible: Allow OPPs to express their compatibility. It should be:
64 "operating-points-v2".
66 - OPP nodes: One or more OPP nodes describing voltage-current-frequency
67 combinations. Their name isn't significant but their phandle can be used to
71 - opp-shared: Indicates that device nodes using this OPP Table Node's phandle
72 switch their DVFS state together, i.e. they share clock/voltage/current lines.
73 Missing property means devices have independent clock/voltage/current lines,
74 but they share OPP tables.
76 - status: Marks the OPP table enabled/disabled.
81 This defines voltage-current-frequency combinations along with other related
85 - opp-hz: Frequency in Hz, expressed as a 64-bit big-endian integer. This is a
86 required property for all device nodes, unless another "required" property to
87 uniquely identify the OPP nodes exists. Devices like power domains must have
88 another (implementation dependent) property.
90 - opp-peak-kBps: Peak bandwidth in kilobytes per second, expressed as an array
91 of 32-bit big-endian integers. Each element of the array represents the
92 peak bandwidth value of each interconnect path. The number of elements should
93 match the number of interconnect paths.
96 - opp-microvolt: voltage in micro Volts.
98 A single regulator's voltage is specified with an array of size one or three.
99 Single entry is for target voltage and three entries are for <target min max>
102 Entries for multiple regulators shall be provided in the same field separated
103 by angular brackets <>. The OPP binding doesn't provide any provisions to
104 relate the values to their power supplies or the order in which the supplies
105 need to be configured and that is left for the implementation specific
108 Entries for all regulators shall be of the same size, i.e. either all use a
109 single value or triplets.
111 - opp-microvolt-<name>: Named opp-microvolt property. This is exactly similar to
112 the above opp-microvolt property, but allows multiple voltage ranges to be
113 provided for the same OPP. At runtime, the platform can pick a <name> and
114 matching opp-microvolt-<name> property will be enabled for all OPPs. If the
115 platform doesn't pick a specific <name> or the <name> doesn't match with any
116 opp-microvolt-<name> properties, then opp-microvolt property shall be used, if
119 - opp-microamp: The maximum current drawn by the device in microamperes
120 considering system specific parameters (such as transients, process, aging,
121 maximum operating temperature range etc.) as necessary. This may be used to
122 set the most efficient regulator operating mode.
124 Should only be set if opp-microvolt is set for the OPP.
126 Entries for multiple regulators shall be provided in the same field separated
127 by angular brackets <>. If current values aren't required for a regulator,
128 then it shall be filled with 0. If current values aren't required for any of
129 the regulators, then this field is not required. The OPP binding doesn't
130 provide any provisions to relate the values to their power supplies or the
131 order in which the supplies need to be configured and that is left for the
132 implementation specific binding.
134 - opp-microamp-<name>: Named opp-microamp property. Similar to
135 opp-microvolt-<name> property, but for microamp instead.
137 - opp-level: A value representing the performance level of the device,
138 expressed as a 32-bit integer.
140 - opp-avg-kBps: Average bandwidth in kilobytes per second, expressed as an array
141 of 32-bit big-endian integers. Each element of the array represents the
142 average bandwidth value of each interconnect path. The number of elements
143 should match the number of interconnect paths. This property is only
144 meaningful in OPP tables where opp-peak-kBps is present.
146 - clock-latency-ns: Specifies the maximum possible transition latency (in
147 nanoseconds) for switching to this OPP from any other OPP.
149 - turbo-mode: Marks the OPP to be used only for turbo modes. Turbo mode is
150 available on some platforms, where the device can run over its operating
151 frequency for a short duration of time limited by the device's power, current
154 - opp-suspend: Marks the OPP to be used during device suspend. If multiple OPPs
155 in the table have this, the OPP with highest opp-hz will be used.
157 - opp-supported-hw: This property allows a platform to enable only a subset of
158 the OPPs from the larger set present in the OPP table, based on the current
159 version of the hardware (already known to the operating system).
161 Each block present in the array of blocks in this property, represents a
162 sub-group of hardware versions supported by the OPP. i.e. <sub-group A>,
163 <sub-group B>, etc. The OPP will be enabled if _any_ of these sub-groups match
164 the hardware's version.
166 Each sub-group is a platform defined array representing the hierarchy of
167 hardware versions supported by the platform. For a platform with three
168 hierarchical levels of version (X.Y.Z), this field shall look like
170 opp-supported-hw = <X1 Y1 Z1>, <X2 Y2 Z2>, <X3 Y3 Z3>.
172 Each level (eg. X1) in version hierarchy is represented by a 32 bit value, one
173 bit per version and so there can be maximum 32 versions per level. Logical AND
174 (&) operation is performed for each level with the hardware's level version
175 and a non-zero output for _all_ the levels in a sub-group means the OPP is
176 supported by hardware. A value of 0xFFFFFFFF for each level in the sub-group
177 will enable the OPP for all versions for the hardware.
179 - status: Marks the node enabled/disabled.
181 - required-opps: This contains phandle to an OPP node in another device's OPP
182 table. It may contain an array of phandles, where each phandle points to an
183 OPP of a different device. It should not contain multiple phandles to the OPP
184 nodes in the same OPP table. This specifies the minimum required OPP of the
185 device(s), whose OPP's phandle is present in this property, for the
186 functioning of the current device at the current OPP (where this property is
189 Example 1: Single cluster Dual-core ARM cortex A9, switch DVFS states together.
193 #address-cells = <1>;
197 compatible = "arm,cortex-a9";
199 next-level-cache = <&L2>;
200 clocks = <&clk_controller 0>;
202 cpu-supply = <&cpu_supply0>;
203 operating-points-v2 = <&cpu0_opp_table>;
207 compatible = "arm,cortex-a9";
209 next-level-cache = <&L2>;
210 clocks = <&clk_controller 0>;
212 cpu-supply = <&cpu_supply0>;
213 operating-points-v2 = <&cpu0_opp_table>;
217 cpu0_opp_table: opp_table0 {
218 compatible = "operating-points-v2";
222 opp-hz = /bits/ 64 <1000000000>;
223 opp-microvolt = <975000 970000 985000>;
224 opp-microamp = <70000>;
225 clock-latency-ns = <300000>;
229 opp-hz = /bits/ 64 <1100000000>;
230 opp-microvolt = <1000000 980000 1010000>;
231 opp-microamp = <80000>;
232 clock-latency-ns = <310000>;
235 opp-hz = /bits/ 64 <1200000000>;
236 opp-microvolt = <1025000>;
237 clock-latency-ns = <290000>;
243 Example 2: Single cluster, Quad-core Qualcom-krait, switches DVFS states
248 #address-cells = <1>;
252 compatible = "qcom,krait";
254 next-level-cache = <&L2>;
255 clocks = <&clk_controller 0>;
257 cpu-supply = <&cpu_supply0>;
258 operating-points-v2 = <&cpu_opp_table>;
262 compatible = "qcom,krait";
264 next-level-cache = <&L2>;
265 clocks = <&clk_controller 1>;
267 cpu-supply = <&cpu_supply1>;
268 operating-points-v2 = <&cpu_opp_table>;
272 compatible = "qcom,krait";
274 next-level-cache = <&L2>;
275 clocks = <&clk_controller 2>;
277 cpu-supply = <&cpu_supply2>;
278 operating-points-v2 = <&cpu_opp_table>;
282 compatible = "qcom,krait";
284 next-level-cache = <&L2>;
285 clocks = <&clk_controller 3>;
287 cpu-supply = <&cpu_supply3>;
288 operating-points-v2 = <&cpu_opp_table>;
292 cpu_opp_table: opp_table {
293 compatible = "operating-points-v2";
296 * Missing opp-shared property means CPUs switch DVFS states
301 opp-hz = /bits/ 64 <1000000000>;
302 opp-microvolt = <975000 970000 985000>;
303 opp-microamp = <70000>;
304 clock-latency-ns = <300000>;
308 opp-hz = /bits/ 64 <1100000000>;
309 opp-microvolt = <1000000 980000 1010000>;
310 opp-microamp = <80000>;
311 clock-latency-ns = <310000>;
314 opp-hz = /bits/ 64 <1200000000>;
315 opp-microvolt = <1025000>;
316 opp-microamp = <90000;
317 lock-latency-ns = <290000>;
323 Example 3: Dual-cluster, Dual-core per cluster. CPUs within a cluster switch
328 #address-cells = <1>;
332 compatible = "arm,cortex-a7";
334 next-level-cache = <&L2>;
335 clocks = <&clk_controller 0>;
337 cpu-supply = <&cpu_supply0>;
338 operating-points-v2 = <&cluster0_opp>;
342 compatible = "arm,cortex-a7";
344 next-level-cache = <&L2>;
345 clocks = <&clk_controller 0>;
347 cpu-supply = <&cpu_supply0>;
348 operating-points-v2 = <&cluster0_opp>;
352 compatible = "arm,cortex-a15";
354 next-level-cache = <&L2>;
355 clocks = <&clk_controller 1>;
357 cpu-supply = <&cpu_supply1>;
358 operating-points-v2 = <&cluster1_opp>;
362 compatible = "arm,cortex-a15";
364 next-level-cache = <&L2>;
365 clocks = <&clk_controller 1>;
367 cpu-supply = <&cpu_supply1>;
368 operating-points-v2 = <&cluster1_opp>;
372 cluster0_opp: opp_table0 {
373 compatible = "operating-points-v2";
377 opp-hz = /bits/ 64 <1000000000>;
378 opp-microvolt = <975000 970000 985000>;
379 opp-microamp = <70000>;
380 clock-latency-ns = <300000>;
384 opp-hz = /bits/ 64 <1100000000>;
385 opp-microvolt = <1000000 980000 1010000>;
386 opp-microamp = <80000>;
387 clock-latency-ns = <310000>;
390 opp-hz = /bits/ 64 <1200000000>;
391 opp-microvolt = <1025000>;
392 opp-microamp = <90000>;
393 clock-latency-ns = <290000>;
398 cluster1_opp: opp_table1 {
399 compatible = "operating-points-v2";
403 opp-hz = /bits/ 64 <1300000000>;
404 opp-microvolt = <1050000 1045000 1055000>;
405 opp-microamp = <95000>;
406 clock-latency-ns = <400000>;
410 opp-hz = /bits/ 64 <1400000000>;
411 opp-microvolt = <1075000>;
412 opp-microamp = <100000>;
413 clock-latency-ns = <400000>;
416 opp-hz = /bits/ 64 <1500000000>;
417 opp-microvolt = <1100000 1010000 1110000>;
418 opp-microamp = <95000>;
419 clock-latency-ns = <400000>;
425 Example 4: Handling multiple regulators
430 compatible = "vendor,cpu-type";
433 vcc0-supply = <&cpu_supply0>;
434 vcc1-supply = <&cpu_supply1>;
435 vcc2-supply = <&cpu_supply2>;
436 operating-points-v2 = <&cpu0_opp_table>;
440 cpu0_opp_table: opp_table0 {
441 compatible = "operating-points-v2";
445 opp-hz = /bits/ 64 <1000000000>;
446 opp-microvolt = <970000>, /* Supply 0 */
447 <960000>, /* Supply 1 */
448 <960000>; /* Supply 2 */
449 opp-microamp = <70000>, /* Supply 0 */
450 <70000>, /* Supply 1 */
451 <70000>; /* Supply 2 */
452 clock-latency-ns = <300000>;
458 opp-hz = /bits/ 64 <1000000000>;
459 opp-microvolt = <975000 970000 985000>, /* Supply 0 */
460 <965000 960000 975000>, /* Supply 1 */
461 <965000 960000 975000>; /* Supply 2 */
462 opp-microamp = <70000>, /* Supply 0 */
463 <70000>, /* Supply 1 */
464 <70000>; /* Supply 2 */
465 clock-latency-ns = <300000>;
471 opp-hz = /bits/ 64 <1000000000>;
472 opp-microvolt = <975000 970000 985000>, /* Supply 0 */
473 <965000 960000 975000>, /* Supply 1 */
474 <965000 960000 975000>; /* Supply 2 */
475 opp-microamp = <70000>, /* Supply 0 */
476 <0>, /* Supply 1 doesn't need this */
477 <70000>; /* Supply 2 */
478 clock-latency-ns = <300000>;
483 Example 5: opp-supported-hw
484 (example: three level hierarchy of versions: cuts, substrate and process)
489 compatible = "arm,cortex-a7";
492 cpu-supply = <&cpu_supply>
493 operating-points-v2 = <&cpu0_opp_table_slow>;
498 compatible = "operating-points-v2";
503 * Supports all substrate and process versions for 0xF
504 * cuts, i.e. only first four cuts.
506 opp-supported-hw = <0xF 0xFFFFFFFF 0xFFFFFFFF>
507 opp-hz = /bits/ 64 <600000000>;
514 * - cuts: only one, 6th cut (represented by 6th bit).
515 * - substrate: supports 16 different substrate versions
516 * - process: supports 9 different process versions
518 opp-supported-hw = <0x20 0xff0000ff 0x0000f4f0>
519 opp-hz = /bits/ 64 <800000000>;
526 * - All cuts and substrate where process version is 0x2.
527 * - All cuts and process where substrate version is 0x2.
529 opp-supported-hw = <0xFFFFFFFF 0xFFFFFFFF 0x02>, <0xFFFFFFFF 0x01 0xFFFFFFFF>
530 opp-hz = /bits/ 64 <900000000>;
536 Example 6: opp-microvolt-<name>, opp-microamp-<name>:
537 (example: device with two possible microvolt ranges: slow and fast)
542 compatible = "arm,cortex-a7";
545 operating-points-v2 = <&cpu0_opp_table>;
549 cpu0_opp_table: opp_table0 {
550 compatible = "operating-points-v2";
554 opp-hz = /bits/ 64 <1000000000>;
555 opp-microvolt-slow = <915000 900000 925000>;
556 opp-microvolt-fast = <975000 970000 985000>;
557 opp-microamp-slow = <70000>;
558 opp-microamp-fast = <71000>;
562 opp-hz = /bits/ 64 <1200000000>;
563 opp-microvolt-slow = <915000 900000 925000>, /* Supply vcc0 */
564 <925000 910000 935000>; /* Supply vcc1 */
565 opp-microvolt-fast = <975000 970000 985000>, /* Supply vcc0 */
566 <965000 960000 975000>; /* Supply vcc1 */
567 opp-microamp = <70000>; /* Will be used for both slow/fast */