d82b35186e
The following patch is a generalization of the latency.c implementation done
by Arjan last year. It provides infrastructure for more than one parameter,
and exposes a user mode interface for processes to register pm_qos
expectations of processes.
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.
Currently we have {cpu_dma_latency, network_latency, network_throughput} as
the initial set of pm_qos parameters.
The infrastructure exposes multiple misc device nodes one per implemented
parameter. The set of parameters implement is defined by pm_qos_power_init()
and pm_qos_params.h. This is done because having the available parameters
being runtime configurable or changeable from a driver was seen as too easy to
abuse.
For each parameter a list of performance requirements is maintained along with
an aggregated target value. The aggregated target value is updated with
changes to the requirement list or elements of the list. Typically the
aggregated target value is simply the max or min of the requirement values
held in the parameter list elements.
>From kernel mode the use of this interface is simple:
pm_qos_add_requirement(param_id, name, target_value):
Will insert a named element in the list for that identified PM_QOS
parameter 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.
pm_qos_update_requirement(param_id, name, new_target_value):
Will search the list identified by the param_id for the named list element
and then update its target value, calling the notification tree if the
aggregated target is changed. with that name is already registered.
pm_qos_remove_requirement(param_id, name):
Will search the identified list for the named element and remove it, after
removal it will update the aggregate target and call the notification tree
if the target was changed as a result of removing the named requirement.
>From user mode:
Only processes can register a pm_qos requirement. To provide for
automatic cleanup for process the interface requires the process to register
its parameter requirements in the following way:
To register the default pm_qos target for the specific parameter, the
process must open one of /dev/[cpu_dma_latency, network_latency,
network_throughput]
As long as the device node is held open that process has a registered
requirement on the parameter. The name of the requirement is
"process_<PID>" derived from the current->pid from within the open system
call.
To change the requested target value the process needs to write a s32
value to the open device node. This translates to a
pm_qos_update_requirement call.
To remove the user mode request for a target value simply close the device
node.
[akpm@linux-foundation.org: fix warnings]
[akpm@linux-foundation.org: fix build]
[akpm@linux-foundation.org: fix build again]
[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: mark gross <mgross@linux.intel.com>
Cc: "John W. Linville" <linville@tuxdriver.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Jaroslav Kysela <perex@suse.cz>
Cc: Takashi Iwai <tiwai@suse.de>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Venki Pallipadi <venkatesh.pallipadi@intel.com>
Cc: Adam Belay <abelay@novell.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
138 lines
3.3 KiB
C
138 lines
3.3 KiB
C
/*
|
|
* menu.c - the menu idle governor
|
|
*
|
|
* Copyright (C) 2006-2007 Adam Belay <abelay@novell.com>
|
|
*
|
|
* This code is licenced under the GPL.
|
|
*/
|
|
|
|
#include <linux/kernel.h>
|
|
#include <linux/cpuidle.h>
|
|
#include <linux/pm_qos_params.h>
|
|
#include <linux/time.h>
|
|
#include <linux/ktime.h>
|
|
#include <linux/hrtimer.h>
|
|
#include <linux/tick.h>
|
|
|
|
#define BREAK_FUZZ 4 /* 4 us */
|
|
|
|
struct menu_device {
|
|
int last_state_idx;
|
|
|
|
unsigned int expected_us;
|
|
unsigned int predicted_us;
|
|
unsigned int last_measured_us;
|
|
unsigned int elapsed_us;
|
|
};
|
|
|
|
static DEFINE_PER_CPU(struct menu_device, menu_devices);
|
|
|
|
/**
|
|
* menu_select - selects the next idle state to enter
|
|
* @dev: the CPU
|
|
*/
|
|
static int menu_select(struct cpuidle_device *dev)
|
|
{
|
|
struct menu_device *data = &__get_cpu_var(menu_devices);
|
|
int i;
|
|
|
|
/* determine the expected residency time */
|
|
data->expected_us =
|
|
(u32) ktime_to_ns(tick_nohz_get_sleep_length()) / 1000;
|
|
|
|
/* find the deepest idle state that satisfies our constraints */
|
|
for (i = 1; i < dev->state_count; i++) {
|
|
struct cpuidle_state *s = &dev->states[i];
|
|
|
|
if (s->target_residency > data->expected_us)
|
|
break;
|
|
if (s->target_residency > data->predicted_us)
|
|
break;
|
|
if (s->exit_latency > pm_qos_requirement(PM_QOS_CPU_DMA_LATENCY))
|
|
break;
|
|
}
|
|
|
|
data->last_state_idx = i - 1;
|
|
return i - 1;
|
|
}
|
|
|
|
/**
|
|
* menu_reflect - attempts to guess what happened after entry
|
|
* @dev: the CPU
|
|
*
|
|
* NOTE: it's important to be fast here because this operation will add to
|
|
* the overall exit latency.
|
|
*/
|
|
static void menu_reflect(struct cpuidle_device *dev)
|
|
{
|
|
struct menu_device *data = &__get_cpu_var(menu_devices);
|
|
int last_idx = data->last_state_idx;
|
|
unsigned int measured_us =
|
|
cpuidle_get_last_residency(dev) + data->elapsed_us;
|
|
struct cpuidle_state *target = &dev->states[last_idx];
|
|
|
|
/*
|
|
* Ugh, this idle state doesn't support residency measurements, so we
|
|
* are basically lost in the dark. As a compromise, assume we slept
|
|
* for one full standard timer tick. However, be aware that this
|
|
* could potentially result in a suboptimal state transition.
|
|
*/
|
|
if (!(target->flags & CPUIDLE_FLAG_TIME_VALID))
|
|
measured_us = USEC_PER_SEC / HZ;
|
|
|
|
/* Predict time remaining until next break event */
|
|
if (measured_us + BREAK_FUZZ < data->expected_us - target->exit_latency) {
|
|
data->predicted_us = max(measured_us, data->last_measured_us);
|
|
data->last_measured_us = measured_us;
|
|
data->elapsed_us = 0;
|
|
} else {
|
|
if (data->elapsed_us < data->elapsed_us + measured_us)
|
|
data->elapsed_us = measured_us;
|
|
else
|
|
data->elapsed_us = -1;
|
|
data->predicted_us = max(measured_us, data->last_measured_us);
|
|
}
|
|
}
|
|
|
|
/**
|
|
* menu_enable_device - scans a CPU's states and does setup
|
|
* @dev: the CPU
|
|
*/
|
|
static int menu_enable_device(struct cpuidle_device *dev)
|
|
{
|
|
struct menu_device *data = &per_cpu(menu_devices, dev->cpu);
|
|
|
|
memset(data, 0, sizeof(struct menu_device));
|
|
|
|
return 0;
|
|
}
|
|
|
|
static struct cpuidle_governor menu_governor = {
|
|
.name = "menu",
|
|
.rating = 20,
|
|
.enable = menu_enable_device,
|
|
.select = menu_select,
|
|
.reflect = menu_reflect,
|
|
.owner = THIS_MODULE,
|
|
};
|
|
|
|
/**
|
|
* init_menu - initializes the governor
|
|
*/
|
|
static int __init init_menu(void)
|
|
{
|
|
return cpuidle_register_governor(&menu_governor);
|
|
}
|
|
|
|
/**
|
|
* exit_menu - exits the governor
|
|
*/
|
|
static void __exit exit_menu(void)
|
|
{
|
|
cpuidle_unregister_governor(&menu_governor);
|
|
}
|
|
|
|
MODULE_LICENSE("GPL");
|
|
module_init(init_menu);
|
|
module_exit(exit_menu);
|