Blame view
Documentation/power/pm_qos_interface.rst
9.53 KB
151f4e2bd docs: power: conv... |
1 2 3 |
=============================== PM Quality Of Service Interface =============================== |
d82b35186 pm qos infrastruc... |
4 5 6 7 |
This interface provides a kernel and user mode interface for registering performance expectations by drivers, subsystems and user space applications on one of the parameters. |
e3cba3243 PM / QoS: Update ... |
8 |
Two different PM QoS frameworks are available: |
3c8740277 Documentation: po... |
9 10 |
* CPU latency QoS. * The per-device PM QoS framework provides the API to manage the |
1992b66d2 PM: Wrap document... |
11 |
per-device latency constraints and PM QoS flags. |
d82b35186 pm qos infrastruc... |
12 |
|
b8e6e27c6 Documentation: PM... |
13 |
The latency unit used in the PM QoS framework is the microsecond (usec). |
bf1db69fb pm_qos: spelling ... |
14 |
|
e3cba3243 PM / QoS: Update ... |
15 16 |
1. PM QoS framework |
151f4e2bd docs: power: conv... |
17 |
=================== |
e3cba3243 PM / QoS: Update ... |
18 |
|
b8e6e27c6 Documentation: PM... |
19 20 21 22 23 |
A global list of CPU latency QoS requests is maintained along with an aggregated (effective) target value. The aggregated target value is updated with changes to the request list or elements of the list. For CPU latency QoS, the aggregated target value is simply the min of the request values held in the list elements. |
e3cba3243 PM / QoS: Update ... |
24 25 |
Note: the aggregated target value is implemented as an atomic variable so that reading the aggregated value does not require any locking mechanism. |
b8e6e27c6 Documentation: PM... |
26 |
From kernel space the use of this interface is simple: |
d82b35186 pm qos infrastruc... |
27 |
|
b8e6e27c6 Documentation: PM... |
28 29 30 31 32 33 |
void cpu_latency_qos_add_request(handle, target_value): Will insert an element into the CPU latency QoS list with the target value. Upon change to this list the new target is recomputed and any registered notifiers are called only if the target value is now different. Clients of PM QoS need to save the returned handle for future use in other PM QoS API functions. |
d82b35186 pm qos infrastruc... |
34 |
|
b8e6e27c6 Documentation: PM... |
35 |
void cpu_latency_qos_update_request(handle, new_target_value): |
1992b66d2 PM: Wrap document... |
36 37 38 |
Will update the list element pointed to by the handle with the new target value and recompute the new aggregated target, calling the notification tree if the target is changed. |
ed77134bf PM QOS update |
39 |
|
b8e6e27c6 Documentation: PM... |
40 |
void cpu_latency_qos_remove_request(handle): |
1992b66d2 PM: Wrap document... |
41 42 43 |
Will remove the element. After removal it will update the aggregate target and call the notification tree if the target was changed as a result of removing the request. |
d82b35186 pm qos infrastruc... |
44 |
|
b8e6e27c6 Documentation: PM... |
45 46 47 48 49 50 |
int cpu_latency_qos_limit(): Returns the aggregated value for the CPU latency QoS. int cpu_latency_qos_request_active(handle): Returns if the request is still active, i.e. it has not been removed from the CPU latency QoS list. |
e3cba3243 PM / QoS: Update ... |
51 |
|
b8e6e27c6 Documentation: PM... |
52 53 54 |
int cpu_latency_qos_add_notifier(notifier): Adds a notification callback function to the CPU latency QoS. The callback is called when the aggregated value for the CPU latency QoS is changed. |
e3cba3243 PM / QoS: Update ... |
55 |
|
b8e6e27c6 Documentation: PM... |
56 57 |
int cpu_latency_qos_remove_notifier(notifier): Removes the notification callback function from the CPU latency QoS. |
e3cba3243 PM / QoS: Update ... |
58 |
|
e3cba3243 PM / QoS: Update ... |
59 |
|
b8e6e27c6 Documentation: PM... |
60 |
From user space: |
d82b35186 pm qos infrastruc... |
61 |
|
b8e6e27c6 Documentation: PM... |
62 63 |
The infrastructure exposes one device node, /dev/cpu_dma_latency, for the CPU latency QoS. |
151f4e2bd docs: power: conv... |
64 |
|
b8e6e27c6 Documentation: PM... |
65 |
Only processes can register a PM QoS request. To provide for automatic |
ed77134bf PM QOS update |
66 |
cleanup of a process, the interface requires the process to register its |
b8e6e27c6 Documentation: PM... |
67 |
parameter requests as follows. |
d82b35186 pm qos infrastruc... |
68 |
|
b8e6e27c6 Documentation: PM... |
69 70 |
To register the default PM QoS target for the CPU latency QoS, the process must open /dev/cpu_dma_latency. |
d82b35186 pm qos infrastruc... |
71 72 |
As long as the device node is held open that process has a registered |
ed77134bf PM QOS update |
73 |
request on the parameter. |
d82b35186 pm qos infrastruc... |
74 |
|
b8e6e27c6 Documentation: PM... |
75 76 77 78 |
To change the requested target value, the process needs to write an s32 value to the open device node. Alternatively, it can write a hex string for the value using the 10 char long format e.g. "0x12345678". This translates to a cpu_latency_qos_update_request() call. |
d82b35186 pm qos infrastruc... |
79 80 81 |
To remove the user mode request for a target value simply close the device node. |
d30b82a46 PM / QoS: Update ... |
82 |
2. PM QoS per-device latency and flags framework |
151f4e2bd docs: power: conv... |
83 |
================================================ |
d30b82a46 PM / QoS: Update ... |
84 |
|
2d984ad13 PM / QoS: Introcu... |
85 86 87 88 |
For each device, there are three lists of PM QoS requests. Two of them are maintained along with the aggregated targets of resume latency and active state latency tolerance (in microseconds) and the third one is for PM QoS flags. Values are updated in response to changes of the request list. |
d30b82a46 PM / QoS: Update ... |
89 |
|
2d984ad13 PM / QoS: Introcu... |
90 91 92 |
The target values of resume latency and active state latency tolerance are simply the minimum of the request values held in the parameter list elements. The PM QoS flags aggregate value is a gather (bitwise OR) of all list elements' |
20f97caf1 PM / QoS: Drop PM... |
93 |
values. One device PM QoS flag is defined currently: PM_QOS_FLAG_NO_POWER_OFF. |
e3cba3243 PM / QoS: Update ... |
94 |
|
2d984ad13 PM / QoS: Introcu... |
95 96 |
Note: The aggregated target values are implemented in such a way that reading the aggregated value does not require any locking mechanism. |
e3cba3243 PM / QoS: Update ... |
97 98 99 |
From kernel mode the use of this interface is the following: |
ae0fb4b72 PM / QoS: Introdu... |
100 |
int dev_pm_qos_add_request(device, handle, type, value): |
151f4e2bd docs: power: conv... |
101 102 103 104 105 |
Will insert an element into the list for that identified device with the target value. Upon change to this list the new target is recomputed and any registered notifiers are called only if the target value is now different. Clients of dev_pm_qos need to save the handle for future use in other dev_pm_qos API functions. |
e3cba3243 PM / QoS: Update ... |
106 107 |
int dev_pm_qos_update_request(handle, new_value): |
151f4e2bd docs: power: conv... |
108 109 110 |
Will update the list element pointed to by the handle with the new target value and recompute the new aggregated target, calling the notification trees if the target is changed. |
e3cba3243 PM / QoS: Update ... |
111 112 |
int dev_pm_qos_remove_request(handle): |
151f4e2bd docs: power: conv... |
113 114 115 |
Will remove the element. After removal it will update the aggregate target and call the notification trees if the target was changed as a result of removing the request. |
e3cba3243 PM / QoS: Update ... |
116 |
|
2a79ea5ec PM / QOS: Pass re... |
117 |
s32 dev_pm_qos_read_value(device, type): |
151f4e2bd docs: power: conv... |
118 |
Returns the aggregated value for a given device's constraints list. |
e3cba3243 PM / QoS: Update ... |
119 |
|
d30b82a46 PM / QoS: Update ... |
120 |
enum pm_qos_flags_status dev_pm_qos_flags(device, mask) |
151f4e2bd docs: power: conv... |
121 122 123 124 125 126 127 128 129 130 131 132 |
Check PM QoS flags of the given device against the given mask of flags. The meaning of the return values is as follows: PM_QOS_FLAGS_ALL: All flags from the mask are set PM_QOS_FLAGS_SOME: Some flags from the mask are set PM_QOS_FLAGS_NONE: No flags from the mask are set PM_QOS_FLAGS_UNDEFINED: The device's PM QoS structure has not been initialized or the list of requests is empty. |
d30b82a46 PM / QoS: Update ... |
133 |
|
71d821fda PM / QoS: Add typ... |
134 |
int dev_pm_qos_add_ancestor_request(dev, handle, type, value) |
151f4e2bd docs: power: conv... |
135 136 137 138 |
Add a PM QoS request for the first direct ancestor of the given device whose power.ignore_children flag is unset (for DEV_PM_QOS_RESUME_LATENCY requests) or whose power.set_latency_tolerance callback pointer is not NULL (for DEV_PM_QOS_LATENCY_TOLERANCE requests). |
d30b82a46 PM / QoS: Update ... |
139 140 |
int dev_pm_qos_expose_latency_limit(device, value) |
151f4e2bd docs: power: conv... |
141 142 143 |
Add a request to the device's PM QoS list of resume latency constraints and create a sysfs attribute pm_qos_resume_latency_us under the device's power directory allowing user space to manipulate that request. |
d30b82a46 PM / QoS: Update ... |
144 145 |
void dev_pm_qos_hide_latency_limit(device) |
151f4e2bd docs: power: conv... |
146 147 148 |
Drop the request added by dev_pm_qos_expose_latency_limit() from the device's PM QoS list of resume latency constraints and remove sysfs attribute pm_qos_resume_latency_us from the device's power directory. |
d30b82a46 PM / QoS: Update ... |
149 150 |
int dev_pm_qos_expose_flags(device, value) |
151f4e2bd docs: power: conv... |
151 152 153 |
Add a request to the device's PM QoS list of flags and create sysfs attribute pm_qos_no_power_off under the device's power directory allowing user space to change the value of the PM_QOS_FLAG_NO_POWER_OFF flag. |
d30b82a46 PM / QoS: Update ... |
154 155 |
void dev_pm_qos_hide_flags(device) |
1992b66d2 PM: Wrap document... |
156 157 158 |
Drop the request added by dev_pm_qos_expose_flags() from the device's PM QoS list of flags and remove sysfs attribute pm_qos_no_power_off from the device's power directory. |
e3cba3243 PM / QoS: Update ... |
159 160 |
Notification mechanisms: |
151f4e2bd docs: power: conv... |
161 |
|
d08d1b27f PM / QoS: Remove ... |
162 |
The per-device PM QoS framework has a per-device notification tree. |
e3cba3243 PM / QoS: Update ... |
163 |
|
0b07ee944 PM / QOS: Pass re... |
164 |
int dev_pm_qos_add_notifier(device, notifier, type): |
d0411ec8c Merge tag 'pm-5.3... |
165 166 |
Adds a notification callback function for the device for a particular request type. |
0b07ee944 PM / QOS: Pass re... |
167 |
|
1992b66d2 PM: Wrap document... |
168 169 |
The callback is called when the aggregated value of the device constraints list is changed. |
e3cba3243 PM / QoS: Update ... |
170 |
|
0b07ee944 PM / QOS: Pass re... |
171 |
int dev_pm_qos_remove_notifier(device, notifier, type): |
151f4e2bd docs: power: conv... |
172 |
Removes the notification callback function for the device. |
e3cba3243 PM / QoS: Update ... |
173 |
|
2d984ad13 PM / QoS: Introcu... |
174 175 |
Active state latency tolerance |
151f4e2bd docs: power: conv... |
176 |
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ |
2d984ad13 PM / QoS: Introcu... |
177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 |
This device PM QoS type is used to support systems in which hardware may switch to energy-saving operation modes on the fly. In those systems, if the operation mode chosen by the hardware attempts to save energy in an overly aggressive way, it may cause excess latencies to be visible to software, causing it to miss certain protocol requirements or target frame or sample rates etc. If there is a latency tolerance control mechanism for a given device available to software, the .set_latency_tolerance callback in that device's dev_pm_info structure should be populated. The routine pointed to by it is should implement whatever is necessary to transfer the effective requirement value to the hardware. Whenever the effective latency tolerance changes for the device, its .set_latency_tolerance() callback will be executed and the effective value will be passed to it. If that value is negative, which means that the list of latency tolerance requirements for the device is empty, the callback is expected to switch the underlying hardware latency tolerance control mechanism to an autonomous mode if available. If that value is PM_QOS_LATENCY_ANY, in turn, and the hardware supports a special "no requirement" setting, the callback is expected to use it. That allows software to prevent the hardware from automatically updating the device's latency tolerance in response to its power state changes (e.g. during transitions from D3cold to D0), which generally may be done in the autonomous latency tolerance control mode. If .set_latency_tolerance() is present for the device, sysfs attribute pm_qos_latency_tolerance_us will be present in the devivce's power directory. Then, user space can use that attribute to specify its latency tolerance requirement for the device, if any. Writing "any" to it means "no requirement, but do not let the hardware control latency tolerance" and writing "auto" to it allows the hardware to be switched to the autonomous mode if there are no other requirements from the kernel side in the device's list. Kernel code can use the functions described above along with the DEV_PM_QOS_LATENCY_TOLERANCE device PM QoS type to add, remove and update latency tolerance requirements for devices. |