ae98207309
- ACPICA update to upstream revision 20150818 including method tracing extensions to allow more in-depth AML debugging in the kernel and a number of assorted fixes and cleanups (Bob Moore, Lv Zheng, Markus Elfring). - ACPI sysfs code updates and a documentation update related to AML method tracing (Lv Zheng). - ACPI EC driver fix related to serialized evaluations of _Qxx methods and ACPI tools updates allowing the EC userspace tool to be built from the kernel source (Lv Zheng). - ACPI processor driver updates preparing it for future introduction of CPPC support and ACPI PCC mailbox driver updates (Ashwin Chaugule). - ACPI interrupts enumeration fix for a regression related to the handling of IRQ attribute conflicts between MADT and the ACPI namespace (Jiang Liu). - Fixes related to ACPI device PM (Mika Westerberg, Srinidhi Kasagar). - ACPI device registration code reorganization to separate the sysfs-related code and bus type operations from the rest (Rafael J Wysocki). - Assorted cleanups in the ACPI core (Jarkko Nikula, Mathias Krause, Andy Shevchenko, Rafael J Wysocki, Nicolas Iooss). - ACPI cpufreq driver and ia64 cpufreq driver fixes and cleanups (Pan Xinhui, Rafael J Wysocki). - cpufreq core cleanups on top of the previous changes allowing it to preseve its sysfs directories over system suspend/resume (Viresh Kumar, Rafael J Wysocki, Sebastian Andrzej Siewior). - cpufreq fixes and cleanups related to governors (Viresh Kumar). - cpufreq updates (core and the cpufreq-dt driver) related to the turbo/boost mode support (Viresh Kumar, Bartlomiej Zolnierkiewicz). - New DT bindings for Operating Performance Points (OPP), support for them in the OPP framework and in the cpufreq-dt driver plus related OPP framework fixes and cleanups (Viresh Kumar). - cpufreq powernv driver updates (Shilpasri G Bhat). - New cpufreq driver for Mediatek MT8173 (Pi-Cheng Chen). - Assorted cpufreq driver (speedstep-lib, sfi, integrator) cleanups and fixes (Abhilash Jindal, Andrzej Hajda, Cristian Ardelean). - intel_pstate driver updates including Skylake-S support, support for enabling HW P-states per CPU and an additional vendor bypass list entry (Kristen Carlson Accardi, Chen Yu, Ethan Zhao). - cpuidle core fixes related to the handling of coupled idle states (Xunlei Pang). - intel_idle driver updates including Skylake Client support and support for freeze-mode-specific idle states (Len Brown). - Driver core updates related to power management (Andy Shevchenko, Rafael J Wysocki). - Generic power domains framework fixes and cleanups (Jon Hunter, Geert Uytterhoeven, Rajendra Nayak, Ulf Hansson). - Device PM QoS framework update to allow the latency tolerance setting to be exposed to user space via sysfs (Mika Westerberg). - devfreq support for PPMUv2 in Exynos5433 and a fix for an incorrect exynos-ppmu DT binding (Chanwoo Choi, Javier Martinez Canillas). - System sleep support updates (Alan Stern, Len Brown, SungEun Kim). - rockchip-io AVS support updates (Heiko Stuebner). - PM core clocks support fixup (Colin Ian King). - Power capping RAPL driver update including support for Skylake H/S and Broadwell-H (Radivoje Jovanovic, Seiichi Ikarashi). - Generic device properties framework fixes related to the handling of static (driver-provided) property sets (Andy Shevchenko). - turbostat and cpupower updates (Len Brown, Shilpasri G Bhat, Shreyas B Prabhu). / -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (GNU/Linux) iQIcBAABCAAGBQJV5hhGAAoJEILEb/54YlRxs+EQAK51iFk48+IbpHYaZZ50Yo4m ZZc2zBcbwRcBlU9vKERrhG+jieSl8J/JJNxT8vBjKqyvNw038mCjewQh02ol0HuC R7nlDiVJkmZ50sLO4xwE/1UBZr/XqbddwCUnYzvFMkMTA0ePzFtf8BrJ1FXpT8S/ fkwSXQty6hvJDwxkfrbMSaA730wMju9lahx8D6MlmUAedWYZOJDMQKB4WKa/St5X 9uckBPHUBB2KiKlXxdbFPwKLNxHvLROq5SpDLc6cM/7XZB+QfNFy85CUjCUtYo1O 1W8k0qnztvZ6UEv27qz5dejGyAGOarMWGGNsmL9evoeGeHRpQL+dom7HcTnbAfUZ walyhYSm/zKkdy7Vl3xWUUQkMG48+PviMI6K0YhHXb3Rm5wlR/yBNZTwNIty9SX/ fKCHEa8QynWwLxgm53c3xRkiitJxMsHNK03moLD9zQMjshTyTNvpNbZoahyKQzk6 H+9M1DBRHhkkREDWSwGutukxfEMtWe2vcZcyERrFiY7l5k1j58DwDBMPqjPhRv6q P/1NlCzr0XYf83Y86J18LbDuPGDhTjjIEn6CqbtI2mmWqTg3+rF7zvS2ux+FzMnA gisv8l6GT9JiWhxKFqqL/rrVpwtyHebWLYE/RpNUW6fEzLziRNj1qyYO9dqI/GGi I3rfxlXoc/5xJWCgNB8f =fTgI -----END PGP SIGNATURE----- Merge tag 'pm+acpi-4.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm Pull power management and ACPI updates from Rafael Wysocki: "From the number of commits perspective, the biggest items are ACPICA and cpufreq changes with the latter taking the lead (over 50 commits). On the cpufreq front, there are many cleanups and minor fixes in the core and governors, driver updates etc. We also have a new cpufreq driver for Mediatek MT8173 chips. ACPICA mostly updates its debug infrastructure and adds a number of fixes and cleanups for a good measure. The Operating Performance Points (OPP) framework is updated with new DT bindings and support for them among other things. We have a few updates of the generic power domains framework and a reorganization of the ACPI device enumeration code and bus type operations. And a lot of fixes and cleanups all over. Included is one branch from the MFD tree as it contains some PM-related driver core and ACPI PM changes a few other commits are based on. Specifics: - ACPICA update to upstream revision 20150818 including method tracing extensions to allow more in-depth AML debugging in the kernel and a number of assorted fixes and cleanups (Bob Moore, Lv Zheng, Markus Elfring). - ACPI sysfs code updates and a documentation update related to AML method tracing (Lv Zheng). - ACPI EC driver fix related to serialized evaluations of _Qxx methods and ACPI tools updates allowing the EC userspace tool to be built from the kernel source (Lv Zheng). - ACPI processor driver updates preparing it for future introduction of CPPC support and ACPI PCC mailbox driver updates (Ashwin Chaugule). - ACPI interrupts enumeration fix for a regression related to the handling of IRQ attribute conflicts between MADT and the ACPI namespace (Jiang Liu). - Fixes related to ACPI device PM (Mika Westerberg, Srinidhi Kasagar). - ACPI device registration code reorganization to separate the sysfs-related code and bus type operations from the rest (Rafael J Wysocki). - Assorted cleanups in the ACPI core (Jarkko Nikula, Mathias Krause, Andy Shevchenko, Rafael J Wysocki, Nicolas Iooss). - ACPI cpufreq driver and ia64 cpufreq driver fixes and cleanups (Pan Xinhui, Rafael J Wysocki). - cpufreq core cleanups on top of the previous changes allowing it to preseve its sysfs directories over system suspend/resume (Viresh Kumar, Rafael J Wysocki, Sebastian Andrzej Siewior). - cpufreq fixes and cleanups related to governors (Viresh Kumar). - cpufreq updates (core and the cpufreq-dt driver) related to the turbo/boost mode support (Viresh Kumar, Bartlomiej Zolnierkiewicz). - New DT bindings for Operating Performance Points (OPP), support for them in the OPP framework and in the cpufreq-dt driver plus related OPP framework fixes and cleanups (Viresh Kumar). - cpufreq powernv driver updates (Shilpasri G Bhat). - New cpufreq driver for Mediatek MT8173 (Pi-Cheng Chen). - Assorted cpufreq driver (speedstep-lib, sfi, integrator) cleanups and fixes (Abhilash Jindal, Andrzej Hajda, Cristian Ardelean). - intel_pstate driver updates including Skylake-S support, support for enabling HW P-states per CPU and an additional vendor bypass list entry (Kristen Carlson Accardi, Chen Yu, Ethan Zhao). - cpuidle core fixes related to the handling of coupled idle states (Xunlei Pang). - intel_idle driver updates including Skylake Client support and support for freeze-mode-specific idle states (Len Brown). - Driver core updates related to power management (Andy Shevchenko, Rafael J Wysocki). - Generic power domains framework fixes and cleanups (Jon Hunter, Geert Uytterhoeven, Rajendra Nayak, Ulf Hansson). - Device PM QoS framework update to allow the latency tolerance setting to be exposed to user space via sysfs (Mika Westerberg). - devfreq support for PPMUv2 in Exynos5433 and a fix for an incorrect exynos-ppmu DT binding (Chanwoo Choi, Javier Martinez Canillas). - System sleep support updates (Alan Stern, Len Brown, SungEun Kim). - rockchip-io AVS support updates (Heiko Stuebner). - PM core clocks support fixup (Colin Ian King). - Power capping RAPL driver update including support for Skylake H/S and Broadwell-H (Radivoje Jovanovic, Seiichi Ikarashi). - Generic device properties framework fixes related to the handling of static (driver-provided) property sets (Andy Shevchenko). - turbostat and cpupower updates (Len Brown, Shilpasri G Bhat, Shreyas B Prabhu)" * tag 'pm+acpi-4.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (180 commits) cpufreq: speedstep-lib: Use monotonic clock cpufreq: powernv: Increase the verbosity of OCC console messages cpufreq: sfi: use kmemdup rather than duplicating its implementation cpufreq: drop !cpufreq_driver check from cpufreq_parse_governor() cpufreq: rename cpufreq_real_policy as cpufreq_user_policy cpufreq: remove redundant 'policy' field from user_policy cpufreq: remove redundant 'governor' field from user_policy cpufreq: update user_policy.* on success cpufreq: use memcpy() to copy policy cpufreq: remove redundant CPUFREQ_INCOMPATIBLE notifier event cpufreq: mediatek: Add MT8173 cpufreq driver dt-bindings: mediatek: Add MT8173 CPU DVFS clock bindings PM / Domains: Fix typo in description of genpd_dev_pm_detach() PM / Domains: Remove unusable governor dummies PM / Domains: Make pm_genpd_init() available to modules PM / domains: Align column headers and data in pm_genpd_summary output powercap / RAPL: disable the 2nd power limit properly tools: cpupower: Fix error when running cpupower monitor PM / OPP: Drop unlikely before IS_ERR(_OR_NULL) PM / OPP: Fix static checker warning (broken 64bit big endian systems) ...
662 lines
15 KiB
C
662 lines
15 KiB
C
/*
|
|
* cpuidle.c - core cpuidle infrastructure
|
|
*
|
|
* (C) 2006-2007 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
|
|
* Shaohua Li <shaohua.li@intel.com>
|
|
* Adam Belay <abelay@novell.com>
|
|
*
|
|
* This code is licenced under the GPL.
|
|
*/
|
|
|
|
#include <linux/clockchips.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/mutex.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/pm_qos.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/cpuidle.h>
|
|
#include <linux/ktime.h>
|
|
#include <linux/hrtimer.h>
|
|
#include <linux/module.h>
|
|
#include <linux/suspend.h>
|
|
#include <linux/tick.h>
|
|
#include <trace/events/power.h>
|
|
|
|
#include "cpuidle.h"
|
|
|
|
DEFINE_PER_CPU(struct cpuidle_device *, cpuidle_devices);
|
|
DEFINE_PER_CPU(struct cpuidle_device, cpuidle_dev);
|
|
|
|
DEFINE_MUTEX(cpuidle_lock);
|
|
LIST_HEAD(cpuidle_detected_devices);
|
|
|
|
static int enabled_devices;
|
|
static int off __read_mostly;
|
|
static int initialized __read_mostly;
|
|
|
|
int cpuidle_disabled(void)
|
|
{
|
|
return off;
|
|
}
|
|
void disable_cpuidle(void)
|
|
{
|
|
off = 1;
|
|
}
|
|
|
|
bool cpuidle_not_available(struct cpuidle_driver *drv,
|
|
struct cpuidle_device *dev)
|
|
{
|
|
return off || !initialized || !drv || !dev || !dev->enabled;
|
|
}
|
|
|
|
/**
|
|
* cpuidle_play_dead - cpu off-lining
|
|
*
|
|
* Returns in case of an error or no driver
|
|
*/
|
|
int cpuidle_play_dead(void)
|
|
{
|
|
struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
|
|
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
|
|
int i;
|
|
|
|
if (!drv)
|
|
return -ENODEV;
|
|
|
|
/* Find lowest-power state that supports long-term idle */
|
|
for (i = drv->state_count - 1; i >= 0; i--)
|
|
if (drv->states[i].enter_dead)
|
|
return drv->states[i].enter_dead(dev, i);
|
|
|
|
return -ENODEV;
|
|
}
|
|
|
|
static int find_deepest_state(struct cpuidle_driver *drv,
|
|
struct cpuidle_device *dev,
|
|
unsigned int max_latency,
|
|
unsigned int forbidden_flags,
|
|
bool freeze)
|
|
{
|
|
unsigned int latency_req = 0;
|
|
int i, ret = -ENXIO;
|
|
|
|
for (i = 0; i < drv->state_count; i++) {
|
|
struct cpuidle_state *s = &drv->states[i];
|
|
struct cpuidle_state_usage *su = &dev->states_usage[i];
|
|
|
|
if (s->disabled || su->disable || s->exit_latency <= latency_req
|
|
|| s->exit_latency > max_latency
|
|
|| (s->flags & forbidden_flags)
|
|
|| (freeze && !s->enter_freeze))
|
|
continue;
|
|
|
|
latency_req = s->exit_latency;
|
|
ret = i;
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
#ifdef CONFIG_SUSPEND
|
|
/**
|
|
* cpuidle_find_deepest_state - Find the deepest available idle state.
|
|
* @drv: cpuidle driver for the given CPU.
|
|
* @dev: cpuidle device for the given CPU.
|
|
*/
|
|
int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
|
|
struct cpuidle_device *dev)
|
|
{
|
|
return find_deepest_state(drv, dev, UINT_MAX, 0, false);
|
|
}
|
|
|
|
static void enter_freeze_proper(struct cpuidle_driver *drv,
|
|
struct cpuidle_device *dev, int index)
|
|
{
|
|
/*
|
|
* trace_suspend_resume() called by tick_freeze() for the last CPU
|
|
* executing it contains RCU usage regarded as invalid in the idle
|
|
* context, so tell RCU about that.
|
|
*/
|
|
RCU_NONIDLE(tick_freeze());
|
|
/*
|
|
* The state used here cannot be a "coupled" one, because the "coupled"
|
|
* cpuidle mechanism enables interrupts and doing that with timekeeping
|
|
* suspended is generally unsafe.
|
|
*/
|
|
stop_critical_timings();
|
|
drv->states[index].enter_freeze(dev, drv, index);
|
|
WARN_ON(!irqs_disabled());
|
|
/*
|
|
* timekeeping_resume() that will be called by tick_unfreeze() for the
|
|
* first CPU executing it calls functions containing RCU read-side
|
|
* critical sections, so tell RCU about that.
|
|
*/
|
|
RCU_NONIDLE(tick_unfreeze());
|
|
start_critical_timings();
|
|
}
|
|
|
|
/**
|
|
* cpuidle_enter_freeze - Enter an idle state suitable for suspend-to-idle.
|
|
* @drv: cpuidle driver for the given CPU.
|
|
* @dev: cpuidle device for the given CPU.
|
|
*
|
|
* If there are states with the ->enter_freeze callback, find the deepest of
|
|
* them and enter it with frozen tick.
|
|
*/
|
|
int cpuidle_enter_freeze(struct cpuidle_driver *drv, struct cpuidle_device *dev)
|
|
{
|
|
int index;
|
|
|
|
/*
|
|
* Find the deepest state with ->enter_freeze present, which guarantees
|
|
* that interrupts won't be enabled when it exits and allows the tick to
|
|
* be frozen safely.
|
|
*/
|
|
index = find_deepest_state(drv, dev, UINT_MAX, 0, true);
|
|
if (index >= 0)
|
|
enter_freeze_proper(drv, dev, index);
|
|
|
|
return index;
|
|
}
|
|
#endif /* CONFIG_SUSPEND */
|
|
|
|
/**
|
|
* cpuidle_enter_state - enter the state and update stats
|
|
* @dev: cpuidle device for this cpu
|
|
* @drv: cpuidle driver for this cpu
|
|
* @index: index into the states table in @drv of the state to enter
|
|
*/
|
|
int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
|
|
int index)
|
|
{
|
|
int entered_state;
|
|
|
|
struct cpuidle_state *target_state = &drv->states[index];
|
|
bool broadcast = !!(target_state->flags & CPUIDLE_FLAG_TIMER_STOP);
|
|
ktime_t time_start, time_end;
|
|
s64 diff;
|
|
|
|
/*
|
|
* Tell the time framework to switch to a broadcast timer because our
|
|
* local timer will be shut down. If a local timer is used from another
|
|
* CPU as a broadcast timer, this call may fail if it is not available.
|
|
*/
|
|
if (broadcast && tick_broadcast_enter()) {
|
|
index = find_deepest_state(drv, dev, target_state->exit_latency,
|
|
CPUIDLE_FLAG_TIMER_STOP, false);
|
|
if (index < 0) {
|
|
default_idle_call();
|
|
return -EBUSY;
|
|
}
|
|
target_state = &drv->states[index];
|
|
}
|
|
|
|
/* Take note of the planned idle state. */
|
|
sched_idle_set_state(target_state);
|
|
|
|
trace_cpu_idle_rcuidle(index, dev->cpu);
|
|
time_start = ktime_get();
|
|
|
|
stop_critical_timings();
|
|
entered_state = target_state->enter(dev, drv, index);
|
|
start_critical_timings();
|
|
|
|
time_end = ktime_get();
|
|
trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
|
|
|
|
/* The cpu is no longer idle or about to enter idle. */
|
|
sched_idle_set_state(NULL);
|
|
|
|
if (broadcast) {
|
|
if (WARN_ON_ONCE(!irqs_disabled()))
|
|
local_irq_disable();
|
|
|
|
tick_broadcast_exit();
|
|
}
|
|
|
|
if (!cpuidle_state_is_coupled(drv, entered_state))
|
|
local_irq_enable();
|
|
|
|
diff = ktime_to_us(ktime_sub(time_end, time_start));
|
|
if (diff > INT_MAX)
|
|
diff = INT_MAX;
|
|
|
|
dev->last_residency = (int) diff;
|
|
|
|
if (entered_state >= 0) {
|
|
/* Update cpuidle counters */
|
|
/* This can be moved to within driver enter routine
|
|
* but that results in multiple copies of same code.
|
|
*/
|
|
dev->states_usage[entered_state].time += dev->last_residency;
|
|
dev->states_usage[entered_state].usage++;
|
|
} else {
|
|
dev->last_residency = 0;
|
|
}
|
|
|
|
return entered_state;
|
|
}
|
|
|
|
/**
|
|
* cpuidle_select - ask the cpuidle framework to choose an idle state
|
|
*
|
|
* @drv: the cpuidle driver
|
|
* @dev: the cpuidle device
|
|
*
|
|
* Returns the index of the idle state.
|
|
*/
|
|
int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
|
|
{
|
|
return cpuidle_curr_governor->select(drv, dev);
|
|
}
|
|
|
|
/**
|
|
* cpuidle_enter - enter into the specified idle state
|
|
*
|
|
* @drv: the cpuidle driver tied with the cpu
|
|
* @dev: the cpuidle device
|
|
* @index: the index in the idle state table
|
|
*
|
|
* Returns the index in the idle state, < 0 in case of error.
|
|
* The error code depends on the backend driver
|
|
*/
|
|
int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev,
|
|
int index)
|
|
{
|
|
if (cpuidle_state_is_coupled(drv, index))
|
|
return cpuidle_enter_state_coupled(dev, drv, index);
|
|
return cpuidle_enter_state(dev, drv, index);
|
|
}
|
|
|
|
/**
|
|
* cpuidle_reflect - tell the underlying governor what was the state
|
|
* we were in
|
|
*
|
|
* @dev : the cpuidle device
|
|
* @index: the index in the idle state table
|
|
*
|
|
*/
|
|
void cpuidle_reflect(struct cpuidle_device *dev, int index)
|
|
{
|
|
if (cpuidle_curr_governor->reflect && index >= 0)
|
|
cpuidle_curr_governor->reflect(dev, index);
|
|
}
|
|
|
|
/**
|
|
* cpuidle_install_idle_handler - installs the cpuidle idle loop handler
|
|
*/
|
|
void cpuidle_install_idle_handler(void)
|
|
{
|
|
if (enabled_devices) {
|
|
/* Make sure all changes finished before we switch to new idle */
|
|
smp_wmb();
|
|
initialized = 1;
|
|
}
|
|
}
|
|
|
|
/**
|
|
* cpuidle_uninstall_idle_handler - uninstalls the cpuidle idle loop handler
|
|
*/
|
|
void cpuidle_uninstall_idle_handler(void)
|
|
{
|
|
if (enabled_devices) {
|
|
initialized = 0;
|
|
wake_up_all_idle_cpus();
|
|
}
|
|
|
|
/*
|
|
* Make sure external observers (such as the scheduler)
|
|
* are done looking at pointed idle states.
|
|
*/
|
|
synchronize_rcu();
|
|
}
|
|
|
|
/**
|
|
* cpuidle_pause_and_lock - temporarily disables CPUIDLE
|
|
*/
|
|
void cpuidle_pause_and_lock(void)
|
|
{
|
|
mutex_lock(&cpuidle_lock);
|
|
cpuidle_uninstall_idle_handler();
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(cpuidle_pause_and_lock);
|
|
|
|
/**
|
|
* cpuidle_resume_and_unlock - resumes CPUIDLE operation
|
|
*/
|
|
void cpuidle_resume_and_unlock(void)
|
|
{
|
|
cpuidle_install_idle_handler();
|
|
mutex_unlock(&cpuidle_lock);
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(cpuidle_resume_and_unlock);
|
|
|
|
/* Currently used in suspend/resume path to suspend cpuidle */
|
|
void cpuidle_pause(void)
|
|
{
|
|
mutex_lock(&cpuidle_lock);
|
|
cpuidle_uninstall_idle_handler();
|
|
mutex_unlock(&cpuidle_lock);
|
|
}
|
|
|
|
/* Currently used in suspend/resume path to resume cpuidle */
|
|
void cpuidle_resume(void)
|
|
{
|
|
mutex_lock(&cpuidle_lock);
|
|
cpuidle_install_idle_handler();
|
|
mutex_unlock(&cpuidle_lock);
|
|
}
|
|
|
|
/**
|
|
* cpuidle_enable_device - enables idle PM for a CPU
|
|
* @dev: the CPU
|
|
*
|
|
* This function must be called between cpuidle_pause_and_lock and
|
|
* cpuidle_resume_and_unlock when used externally.
|
|
*/
|
|
int cpuidle_enable_device(struct cpuidle_device *dev)
|
|
{
|
|
int ret;
|
|
struct cpuidle_driver *drv;
|
|
|
|
if (!dev)
|
|
return -EINVAL;
|
|
|
|
if (dev->enabled)
|
|
return 0;
|
|
|
|
drv = cpuidle_get_cpu_driver(dev);
|
|
|
|
if (!drv || !cpuidle_curr_governor)
|
|
return -EIO;
|
|
|
|
if (!dev->registered)
|
|
return -EINVAL;
|
|
|
|
ret = cpuidle_add_device_sysfs(dev);
|
|
if (ret)
|
|
return ret;
|
|
|
|
if (cpuidle_curr_governor->enable &&
|
|
(ret = cpuidle_curr_governor->enable(drv, dev)))
|
|
goto fail_sysfs;
|
|
|
|
smp_wmb();
|
|
|
|
dev->enabled = 1;
|
|
|
|
enabled_devices++;
|
|
return 0;
|
|
|
|
fail_sysfs:
|
|
cpuidle_remove_device_sysfs(dev);
|
|
|
|
return ret;
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(cpuidle_enable_device);
|
|
|
|
/**
|
|
* cpuidle_disable_device - disables idle PM for a CPU
|
|
* @dev: the CPU
|
|
*
|
|
* This function must be called between cpuidle_pause_and_lock and
|
|
* cpuidle_resume_and_unlock when used externally.
|
|
*/
|
|
void cpuidle_disable_device(struct cpuidle_device *dev)
|
|
{
|
|
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
|
|
|
|
if (!dev || !dev->enabled)
|
|
return;
|
|
|
|
if (!drv || !cpuidle_curr_governor)
|
|
return;
|
|
|
|
dev->enabled = 0;
|
|
|
|
if (cpuidle_curr_governor->disable)
|
|
cpuidle_curr_governor->disable(drv, dev);
|
|
|
|
cpuidle_remove_device_sysfs(dev);
|
|
enabled_devices--;
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(cpuidle_disable_device);
|
|
|
|
static void __cpuidle_unregister_device(struct cpuidle_device *dev)
|
|
{
|
|
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
|
|
|
|
list_del(&dev->device_list);
|
|
per_cpu(cpuidle_devices, dev->cpu) = NULL;
|
|
module_put(drv->owner);
|
|
}
|
|
|
|
static void __cpuidle_device_init(struct cpuidle_device *dev)
|
|
{
|
|
memset(dev->states_usage, 0, sizeof(dev->states_usage));
|
|
dev->last_residency = 0;
|
|
}
|
|
|
|
/**
|
|
* __cpuidle_register_device - internal register function called before register
|
|
* and enable routines
|
|
* @dev: the cpu
|
|
*
|
|
* cpuidle_lock mutex must be held before this is called
|
|
*/
|
|
static int __cpuidle_register_device(struct cpuidle_device *dev)
|
|
{
|
|
int ret;
|
|
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
|
|
|
|
if (!try_module_get(drv->owner))
|
|
return -EINVAL;
|
|
|
|
per_cpu(cpuidle_devices, dev->cpu) = dev;
|
|
list_add(&dev->device_list, &cpuidle_detected_devices);
|
|
|
|
ret = cpuidle_coupled_register_device(dev);
|
|
if (ret)
|
|
__cpuidle_unregister_device(dev);
|
|
else
|
|
dev->registered = 1;
|
|
|
|
return ret;
|
|
}
|
|
|
|
/**
|
|
* cpuidle_register_device - registers a CPU's idle PM feature
|
|
* @dev: the cpu
|
|
*/
|
|
int cpuidle_register_device(struct cpuidle_device *dev)
|
|
{
|
|
int ret = -EBUSY;
|
|
|
|
if (!dev)
|
|
return -EINVAL;
|
|
|
|
mutex_lock(&cpuidle_lock);
|
|
|
|
if (dev->registered)
|
|
goto out_unlock;
|
|
|
|
__cpuidle_device_init(dev);
|
|
|
|
ret = __cpuidle_register_device(dev);
|
|
if (ret)
|
|
goto out_unlock;
|
|
|
|
ret = cpuidle_add_sysfs(dev);
|
|
if (ret)
|
|
goto out_unregister;
|
|
|
|
ret = cpuidle_enable_device(dev);
|
|
if (ret)
|
|
goto out_sysfs;
|
|
|
|
cpuidle_install_idle_handler();
|
|
|
|
out_unlock:
|
|
mutex_unlock(&cpuidle_lock);
|
|
|
|
return ret;
|
|
|
|
out_sysfs:
|
|
cpuidle_remove_sysfs(dev);
|
|
out_unregister:
|
|
__cpuidle_unregister_device(dev);
|
|
goto out_unlock;
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(cpuidle_register_device);
|
|
|
|
/**
|
|
* cpuidle_unregister_device - unregisters a CPU's idle PM feature
|
|
* @dev: the cpu
|
|
*/
|
|
void cpuidle_unregister_device(struct cpuidle_device *dev)
|
|
{
|
|
if (!dev || dev->registered == 0)
|
|
return;
|
|
|
|
cpuidle_pause_and_lock();
|
|
|
|
cpuidle_disable_device(dev);
|
|
|
|
cpuidle_remove_sysfs(dev);
|
|
|
|
__cpuidle_unregister_device(dev);
|
|
|
|
cpuidle_coupled_unregister_device(dev);
|
|
|
|
cpuidle_resume_and_unlock();
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(cpuidle_unregister_device);
|
|
|
|
/**
|
|
* cpuidle_unregister: unregister a driver and the devices. This function
|
|
* can be used only if the driver has been previously registered through
|
|
* the cpuidle_register function.
|
|
*
|
|
* @drv: a valid pointer to a struct cpuidle_driver
|
|
*/
|
|
void cpuidle_unregister(struct cpuidle_driver *drv)
|
|
{
|
|
int cpu;
|
|
struct cpuidle_device *device;
|
|
|
|
for_each_cpu(cpu, drv->cpumask) {
|
|
device = &per_cpu(cpuidle_dev, cpu);
|
|
cpuidle_unregister_device(device);
|
|
}
|
|
|
|
cpuidle_unregister_driver(drv);
|
|
}
|
|
EXPORT_SYMBOL_GPL(cpuidle_unregister);
|
|
|
|
/**
|
|
* cpuidle_register: registers the driver and the cpu devices with the
|
|
* coupled_cpus passed as parameter. This function is used for all common
|
|
* initialization pattern there are in the arch specific drivers. The
|
|
* devices is globally defined in this file.
|
|
*
|
|
* @drv : a valid pointer to a struct cpuidle_driver
|
|
* @coupled_cpus: a cpumask for the coupled states
|
|
*
|
|
* Returns 0 on success, < 0 otherwise
|
|
*/
|
|
int cpuidle_register(struct cpuidle_driver *drv,
|
|
const struct cpumask *const coupled_cpus)
|
|
{
|
|
int ret, cpu;
|
|
struct cpuidle_device *device;
|
|
|
|
ret = cpuidle_register_driver(drv);
|
|
if (ret) {
|
|
pr_err("failed to register cpuidle driver\n");
|
|
return ret;
|
|
}
|
|
|
|
for_each_cpu(cpu, drv->cpumask) {
|
|
device = &per_cpu(cpuidle_dev, cpu);
|
|
device->cpu = cpu;
|
|
|
|
#ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED
|
|
/*
|
|
* On multiplatform for ARM, the coupled idle states could be
|
|
* enabled in the kernel even if the cpuidle driver does not
|
|
* use it. Note, coupled_cpus is a struct copy.
|
|
*/
|
|
if (coupled_cpus)
|
|
device->coupled_cpus = *coupled_cpus;
|
|
#endif
|
|
ret = cpuidle_register_device(device);
|
|
if (!ret)
|
|
continue;
|
|
|
|
pr_err("Failed to register cpuidle device for cpu%d\n", cpu);
|
|
|
|
cpuidle_unregister(drv);
|
|
break;
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL_GPL(cpuidle_register);
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
/*
|
|
* This function gets called when a part of the kernel has a new latency
|
|
* requirement. This means we need to get all processors out of their C-state,
|
|
* and then recalculate a new suitable C-state. Just do a cross-cpu IPI; that
|
|
* wakes them all right up.
|
|
*/
|
|
static int cpuidle_latency_notify(struct notifier_block *b,
|
|
unsigned long l, void *v)
|
|
{
|
|
wake_up_all_idle_cpus();
|
|
return NOTIFY_OK;
|
|
}
|
|
|
|
static struct notifier_block cpuidle_latency_notifier = {
|
|
.notifier_call = cpuidle_latency_notify,
|
|
};
|
|
|
|
static inline void latency_notifier_init(struct notifier_block *n)
|
|
{
|
|
pm_qos_add_notifier(PM_QOS_CPU_DMA_LATENCY, n);
|
|
}
|
|
|
|
#else /* CONFIG_SMP */
|
|
|
|
#define latency_notifier_init(x) do { } while (0)
|
|
|
|
#endif /* CONFIG_SMP */
|
|
|
|
/**
|
|
* cpuidle_init - core initializer
|
|
*/
|
|
static int __init cpuidle_init(void)
|
|
{
|
|
int ret;
|
|
|
|
if (cpuidle_disabled())
|
|
return -ENODEV;
|
|
|
|
ret = cpuidle_add_interface(cpu_subsys.dev_root);
|
|
if (ret)
|
|
return ret;
|
|
|
|
latency_notifier_init(&cpuidle_latency_notifier);
|
|
|
|
return 0;
|
|
}
|
|
|
|
module_param(off, int, 0444);
|
|
core_initcall(cpuidle_init);
|