![Rafael J. Wysocki](/assets/img/avatar_default.png)
The efficiency of suspend-to-idle depends on being able to keep CPUs in the deepest available idle states for as much time as possible. Ideally, they should only be brought out of idle by system wakeup interrupts. However, timer interrupts occurring periodically prevent that from happening and it is not practical to chase all of the "misbehaving" timers in a whack-a-mole fashion. A much more effective approach is to suspend the local ticks for all CPUs and the entire timekeeping along the lines of what is done during full suspend, which also helps to keep suspend-to-idle and full suspend reasonably similar. The idea is to suspend the local tick on each CPU executing cpuidle_enter_freeze() and to make the last of them suspend the entire timekeeping. That should prevent timer interrupts from triggering until an IO interrupt wakes up one of the CPUs. It needs to be done with interrupts disabled on all of the CPUs, though, because otherwise the suspended clocksource might be accessed by an interrupt handler which might lead to fatal consequences. Unfortunately, the existing ->enter callbacks provided by cpuidle drivers generally cannot be used for implementing that, because some of them re-enable interrupts temporarily and some idle entry methods cause interrupts to be re-enabled automatically on exit. Also some of these callbacks manipulate local clock event devices of the CPUs which really shouldn't be done after suspending their ticks. To overcome that difficulty, introduce a new cpuidle state callback, ->enter_freeze, that will be guaranteed (1) to keep interrupts disabled all the time (and return with interrupts disabled) and (2) not to touch the CPU timer devices. Modify cpuidle_enter_freeze() to look for the deepest available idle state with ->enter_freeze present and to make the CPU execute that callback with suspended tick (and the last of the online CPUs to execute it with suspended timekeeping). Suggested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
455 lines
11 KiB
C
455 lines
11 KiB
C
/*
|
|
* linux/kernel/time/tick-common.c
|
|
*
|
|
* This file contains the base functions to manage periodic tick
|
|
* related events.
|
|
*
|
|
* Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
|
|
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
|
|
* Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
|
|
*
|
|
* This code is licenced under the GPL version 2. For details see
|
|
* kernel-base/COPYING.
|
|
*/
|
|
#include <linux/cpu.h>
|
|
#include <linux/err.h>
|
|
#include <linux/hrtimer.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/profile.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/module.h>
|
|
|
|
#include <asm/irq_regs.h>
|
|
|
|
#include "tick-internal.h"
|
|
|
|
/*
|
|
* Tick devices
|
|
*/
|
|
DEFINE_PER_CPU(struct tick_device, tick_cpu_device);
|
|
/*
|
|
* Tick next event: keeps track of the tick time
|
|
*/
|
|
ktime_t tick_next_period;
|
|
ktime_t tick_period;
|
|
|
|
/*
|
|
* tick_do_timer_cpu is a timer core internal variable which holds the CPU NR
|
|
* which is responsible for calling do_timer(), i.e. the timekeeping stuff. This
|
|
* variable has two functions:
|
|
*
|
|
* 1) Prevent a thundering herd issue of a gazillion of CPUs trying to grab the
|
|
* timekeeping lock all at once. Only the CPU which is assigned to do the
|
|
* update is handling it.
|
|
*
|
|
* 2) Hand off the duty in the NOHZ idle case by setting the value to
|
|
* TICK_DO_TIMER_NONE, i.e. a non existing CPU. So the next cpu which looks
|
|
* at it will take over and keep the time keeping alive. The handover
|
|
* procedure also covers cpu hotplug.
|
|
*/
|
|
int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
|
|
|
|
/*
|
|
* Debugging: see timer_list.c
|
|
*/
|
|
struct tick_device *tick_get_device(int cpu)
|
|
{
|
|
return &per_cpu(tick_cpu_device, cpu);
|
|
}
|
|
|
|
/**
|
|
* tick_is_oneshot_available - check for a oneshot capable event device
|
|
*/
|
|
int tick_is_oneshot_available(void)
|
|
{
|
|
struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
|
|
|
|
if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT))
|
|
return 0;
|
|
if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
|
|
return 1;
|
|
return tick_broadcast_oneshot_available();
|
|
}
|
|
|
|
/*
|
|
* Periodic tick
|
|
*/
|
|
static void tick_periodic(int cpu)
|
|
{
|
|
if (tick_do_timer_cpu == cpu) {
|
|
write_seqlock(&jiffies_lock);
|
|
|
|
/* Keep track of the next tick event */
|
|
tick_next_period = ktime_add(tick_next_period, tick_period);
|
|
|
|
do_timer(1);
|
|
write_sequnlock(&jiffies_lock);
|
|
update_wall_time();
|
|
}
|
|
|
|
update_process_times(user_mode(get_irq_regs()));
|
|
profile_tick(CPU_PROFILING);
|
|
}
|
|
|
|
/*
|
|
* Event handler for periodic ticks
|
|
*/
|
|
void tick_handle_periodic(struct clock_event_device *dev)
|
|
{
|
|
int cpu = smp_processor_id();
|
|
ktime_t next = dev->next_event;
|
|
|
|
tick_periodic(cpu);
|
|
|
|
if (dev->mode != CLOCK_EVT_MODE_ONESHOT)
|
|
return;
|
|
for (;;) {
|
|
/*
|
|
* Setup the next period for devices, which do not have
|
|
* periodic mode:
|
|
*/
|
|
next = ktime_add(next, tick_period);
|
|
|
|
if (!clockevents_program_event(dev, next, false))
|
|
return;
|
|
/*
|
|
* Have to be careful here. If we're in oneshot mode,
|
|
* before we call tick_periodic() in a loop, we need
|
|
* to be sure we're using a real hardware clocksource.
|
|
* Otherwise we could get trapped in an infinite
|
|
* loop, as the tick_periodic() increments jiffies,
|
|
* which then will increment time, possibly causing
|
|
* the loop to trigger again and again.
|
|
*/
|
|
if (timekeeping_valid_for_hres())
|
|
tick_periodic(cpu);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Setup the device for a periodic tick
|
|
*/
|
|
void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
|
|
{
|
|
tick_set_periodic_handler(dev, broadcast);
|
|
|
|
/* Broadcast setup ? */
|
|
if (!tick_device_is_functional(dev))
|
|
return;
|
|
|
|
if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) &&
|
|
!tick_broadcast_oneshot_active()) {
|
|
clockevents_set_mode(dev, CLOCK_EVT_MODE_PERIODIC);
|
|
} else {
|
|
unsigned long seq;
|
|
ktime_t next;
|
|
|
|
do {
|
|
seq = read_seqbegin(&jiffies_lock);
|
|
next = tick_next_period;
|
|
} while (read_seqretry(&jiffies_lock, seq));
|
|
|
|
clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
|
|
|
|
for (;;) {
|
|
if (!clockevents_program_event(dev, next, false))
|
|
return;
|
|
next = ktime_add(next, tick_period);
|
|
}
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Setup the tick device
|
|
*/
|
|
static void tick_setup_device(struct tick_device *td,
|
|
struct clock_event_device *newdev, int cpu,
|
|
const struct cpumask *cpumask)
|
|
{
|
|
ktime_t next_event;
|
|
void (*handler)(struct clock_event_device *) = NULL;
|
|
|
|
/*
|
|
* First device setup ?
|
|
*/
|
|
if (!td->evtdev) {
|
|
/*
|
|
* If no cpu took the do_timer update, assign it to
|
|
* this cpu:
|
|
*/
|
|
if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) {
|
|
if (!tick_nohz_full_cpu(cpu))
|
|
tick_do_timer_cpu = cpu;
|
|
else
|
|
tick_do_timer_cpu = TICK_DO_TIMER_NONE;
|
|
tick_next_period = ktime_get();
|
|
tick_period = ktime_set(0, NSEC_PER_SEC / HZ);
|
|
}
|
|
|
|
/*
|
|
* Startup in periodic mode first.
|
|
*/
|
|
td->mode = TICKDEV_MODE_PERIODIC;
|
|
} else {
|
|
handler = td->evtdev->event_handler;
|
|
next_event = td->evtdev->next_event;
|
|
td->evtdev->event_handler = clockevents_handle_noop;
|
|
}
|
|
|
|
td->evtdev = newdev;
|
|
|
|
/*
|
|
* When the device is not per cpu, pin the interrupt to the
|
|
* current cpu:
|
|
*/
|
|
if (!cpumask_equal(newdev->cpumask, cpumask))
|
|
irq_set_affinity(newdev->irq, cpumask);
|
|
|
|
/*
|
|
* When global broadcasting is active, check if the current
|
|
* device is registered as a placeholder for broadcast mode.
|
|
* This allows us to handle this x86 misfeature in a generic
|
|
* way. This function also returns !=0 when we keep the
|
|
* current active broadcast state for this CPU.
|
|
*/
|
|
if (tick_device_uses_broadcast(newdev, cpu))
|
|
return;
|
|
|
|
if (td->mode == TICKDEV_MODE_PERIODIC)
|
|
tick_setup_periodic(newdev, 0);
|
|
else
|
|
tick_setup_oneshot(newdev, handler, next_event);
|
|
}
|
|
|
|
void tick_install_replacement(struct clock_event_device *newdev)
|
|
{
|
|
struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
|
|
int cpu = smp_processor_id();
|
|
|
|
clockevents_exchange_device(td->evtdev, newdev);
|
|
tick_setup_device(td, newdev, cpu, cpumask_of(cpu));
|
|
if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
|
|
tick_oneshot_notify();
|
|
}
|
|
|
|
static bool tick_check_percpu(struct clock_event_device *curdev,
|
|
struct clock_event_device *newdev, int cpu)
|
|
{
|
|
if (!cpumask_test_cpu(cpu, newdev->cpumask))
|
|
return false;
|
|
if (cpumask_equal(newdev->cpumask, cpumask_of(cpu)))
|
|
return true;
|
|
/* Check if irq affinity can be set */
|
|
if (newdev->irq >= 0 && !irq_can_set_affinity(newdev->irq))
|
|
return false;
|
|
/* Prefer an existing cpu local device */
|
|
if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu)))
|
|
return false;
|
|
return true;
|
|
}
|
|
|
|
static bool tick_check_preferred(struct clock_event_device *curdev,
|
|
struct clock_event_device *newdev)
|
|
{
|
|
/* Prefer oneshot capable device */
|
|
if (!(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) {
|
|
if (curdev && (curdev->features & CLOCK_EVT_FEAT_ONESHOT))
|
|
return false;
|
|
if (tick_oneshot_mode_active())
|
|
return false;
|
|
}
|
|
|
|
/*
|
|
* Use the higher rated one, but prefer a CPU local device with a lower
|
|
* rating than a non-CPU local device
|
|
*/
|
|
return !curdev ||
|
|
newdev->rating > curdev->rating ||
|
|
!cpumask_equal(curdev->cpumask, newdev->cpumask);
|
|
}
|
|
|
|
/*
|
|
* Check whether the new device is a better fit than curdev. curdev
|
|
* can be NULL !
|
|
*/
|
|
bool tick_check_replacement(struct clock_event_device *curdev,
|
|
struct clock_event_device *newdev)
|
|
{
|
|
if (!tick_check_percpu(curdev, newdev, smp_processor_id()))
|
|
return false;
|
|
|
|
return tick_check_preferred(curdev, newdev);
|
|
}
|
|
|
|
/*
|
|
* Check, if the new registered device should be used. Called with
|
|
* clockevents_lock held and interrupts disabled.
|
|
*/
|
|
void tick_check_new_device(struct clock_event_device *newdev)
|
|
{
|
|
struct clock_event_device *curdev;
|
|
struct tick_device *td;
|
|
int cpu;
|
|
|
|
cpu = smp_processor_id();
|
|
if (!cpumask_test_cpu(cpu, newdev->cpumask))
|
|
goto out_bc;
|
|
|
|
td = &per_cpu(tick_cpu_device, cpu);
|
|
curdev = td->evtdev;
|
|
|
|
/* cpu local device ? */
|
|
if (!tick_check_percpu(curdev, newdev, cpu))
|
|
goto out_bc;
|
|
|
|
/* Preference decision */
|
|
if (!tick_check_preferred(curdev, newdev))
|
|
goto out_bc;
|
|
|
|
if (!try_module_get(newdev->owner))
|
|
return;
|
|
|
|
/*
|
|
* Replace the eventually existing device by the new
|
|
* device. If the current device is the broadcast device, do
|
|
* not give it back to the clockevents layer !
|
|
*/
|
|
if (tick_is_broadcast_device(curdev)) {
|
|
clockevents_shutdown(curdev);
|
|
curdev = NULL;
|
|
}
|
|
clockevents_exchange_device(curdev, newdev);
|
|
tick_setup_device(td, newdev, cpu, cpumask_of(cpu));
|
|
if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
|
|
tick_oneshot_notify();
|
|
return;
|
|
|
|
out_bc:
|
|
/*
|
|
* Can the new device be used as a broadcast device ?
|
|
*/
|
|
tick_install_broadcast_device(newdev);
|
|
}
|
|
|
|
/*
|
|
* Transfer the do_timer job away from a dying cpu.
|
|
*
|
|
* Called with interrupts disabled.
|
|
*/
|
|
void tick_handover_do_timer(int *cpup)
|
|
{
|
|
if (*cpup == tick_do_timer_cpu) {
|
|
int cpu = cpumask_first(cpu_online_mask);
|
|
|
|
tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu :
|
|
TICK_DO_TIMER_NONE;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Shutdown an event device on a given cpu:
|
|
*
|
|
* This is called on a life CPU, when a CPU is dead. So we cannot
|
|
* access the hardware device itself.
|
|
* We just set the mode and remove it from the lists.
|
|
*/
|
|
void tick_shutdown(unsigned int *cpup)
|
|
{
|
|
struct tick_device *td = &per_cpu(tick_cpu_device, *cpup);
|
|
struct clock_event_device *dev = td->evtdev;
|
|
|
|
td->mode = TICKDEV_MODE_PERIODIC;
|
|
if (dev) {
|
|
/*
|
|
* Prevent that the clock events layer tries to call
|
|
* the set mode function!
|
|
*/
|
|
dev->mode = CLOCK_EVT_MODE_UNUSED;
|
|
clockevents_exchange_device(dev, NULL);
|
|
dev->event_handler = clockevents_handle_noop;
|
|
td->evtdev = NULL;
|
|
}
|
|
}
|
|
|
|
void tick_suspend(void)
|
|
{
|
|
struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
|
|
|
|
clockevents_shutdown(td->evtdev);
|
|
}
|
|
|
|
void tick_resume(void)
|
|
{
|
|
struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
|
|
int broadcast = tick_resume_broadcast();
|
|
|
|
clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_RESUME);
|
|
|
|
if (!broadcast) {
|
|
if (td->mode == TICKDEV_MODE_PERIODIC)
|
|
tick_setup_periodic(td->evtdev, 0);
|
|
else
|
|
tick_resume_oneshot();
|
|
}
|
|
}
|
|
|
|
static DEFINE_RAW_SPINLOCK(tick_freeze_lock);
|
|
static unsigned int tick_freeze_depth;
|
|
|
|
/**
|
|
* tick_freeze - Suspend the local tick and (possibly) timekeeping.
|
|
*
|
|
* Check if this is the last online CPU executing the function and if so,
|
|
* suspend timekeeping. Otherwise suspend the local tick.
|
|
*
|
|
* Call with interrupts disabled. Must be balanced with %tick_unfreeze().
|
|
* Interrupts must not be enabled before the subsequent %tick_unfreeze().
|
|
*/
|
|
void tick_freeze(void)
|
|
{
|
|
raw_spin_lock(&tick_freeze_lock);
|
|
|
|
tick_freeze_depth++;
|
|
if (tick_freeze_depth == num_online_cpus()) {
|
|
timekeeping_suspend();
|
|
} else {
|
|
tick_suspend();
|
|
tick_suspend_broadcast();
|
|
}
|
|
|
|
raw_spin_unlock(&tick_freeze_lock);
|
|
}
|
|
|
|
/**
|
|
* tick_unfreeze - Resume the local tick and (possibly) timekeeping.
|
|
*
|
|
* Check if this is the first CPU executing the function and if so, resume
|
|
* timekeeping. Otherwise resume the local tick.
|
|
*
|
|
* Call with interrupts disabled. Must be balanced with %tick_freeze().
|
|
* Interrupts must not be enabled after the preceding %tick_freeze().
|
|
*/
|
|
void tick_unfreeze(void)
|
|
{
|
|
raw_spin_lock(&tick_freeze_lock);
|
|
|
|
if (tick_freeze_depth == num_online_cpus())
|
|
timekeeping_resume();
|
|
else
|
|
tick_resume();
|
|
|
|
tick_freeze_depth--;
|
|
|
|
raw_spin_unlock(&tick_freeze_lock);
|
|
}
|
|
|
|
/**
|
|
* tick_init - initialize the tick control
|
|
*/
|
|
void __init tick_init(void)
|
|
{
|
|
tick_broadcast_init();
|
|
tick_nohz_init();
|
|
}
|