diff mbox

[RFC/PATCH] PM / Sleep: Timer quiesce in freeze state

Message ID 5446787E.60202@linux.intel.com (mailing list archive)
State Superseded, archived
Headers show

Commit Message

Aubrey Li Oct. 21, 2014, 3:15 p.m. UTC 
The patch is based on v3.17, merged with Rafael's pm+acpi-3.18-rc1 tag from
linux-pm.git tree.

The patch is based on the patch PeterZ initially wrote.
---
Freeze is a general power saving state that processes are frozen, devices
are suspended and CPUs are in idle state. However, when the system enters
freeze state, there are a few timers keep ticking and hence consumes more
power unnecessarily. The observed timer events in freeze state are:
- tick_sched_timer
- watchdog lockup detector
- realtime scheduler period timer

The system power consumption in freeze state will be reduced significantly
if we quiesce these timers.

On Baytrail-T(ASUS_T100) platform, when the system is freezed to low power
idle state(S0ix), quiescing these timers saves 29.8% power(94.48mw -> 66.32mw).

The patch is also tested on:
- Sandybrdige-EP system, both RTC alarm and power button are able to wake
  the system up from freeze state.
- HP laptop EliteBook 8460p, both RTC alarm and power button are able to
  wake the system up from freeze state.

Signed-off-by: Aubrey Li <aubrey.li@linux.intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Alan Cox <alan@linux.intel.com>
---
 arch/x86/kernel/apic/apic.c        |   8 ++
 drivers/cpuidle/cpuidle.c          |  12 +++
 kernel/power/suspend.c             | 175 +++++++++++++++++++++++++++++++++++--
 kernel/time/timekeeping.c          |   4 +-
 kernel/time/timekeeping_internal.h |   3 +
 5 files changed, 193 insertions(+), 9 deletions(-)

Comments

Peter Zijlstra Oct. 24, 2014, 3:36 p.m. UTC | #1 
On Tue, Oct 21, 2014 at 11:15:10PM +0800, Li, Aubrey wrote:
> +++ b/arch/x86/kernel/apic/apic.c
> @@ -917,6 +917,14 @@ static void local_apic_timer_interrupt(void)
>  	 */
>  	inc_irq_stat(apic_timer_irqs);
>  
> +	/*
> +	 * if timekeeping is suspended, the clock event device will be
> +	 * suspended as well, so we are not supposed to invoke the event
> +	 * handler of clock event device.
> +	 */
> +	if (unlikely(timekeeping_suspended))
> +		return;
> +
>  	evt->event_handler(evt);
>  }
>  

How would this even happen? Didn't we just suspend the lapic?

> diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
> index 4ca9a33..e58d880 100644
> --- a/kernel/power/suspend.c
> +++ b/kernel/power/suspend.c
> @@ -28,16 +28,20 @@
>  #include <linux/ftrace.h>
>  #include <trace/events/power.h>
>  #include <linux/compiler.h>
> +#include <linux/stop_machine.h>
> +#include <linux/clockchips.h>
> +#include <linux/hrtimer.h>
>  
>  #include "power.h"
> +#include "../time/tick-internal.h"
> +#include "../time/timekeeping_internal.h"
>  
>  const char *pm_labels[] = { "mem", "standby", "freeze", NULL };
>  const char *pm_states[PM_SUSPEND_MAX];
>  
>  static const struct platform_suspend_ops *suspend_ops;
>  static const struct platform_freeze_ops *freeze_ops;
> -static DECLARE_WAIT_QUEUE_HEAD(suspend_freeze_wait_head);
> -static bool suspend_freeze_wake;
> +static int suspend_freeze_wake;
>  
>  void freeze_set_ops(const struct platform_freeze_ops *ops)
>  {
> @@ -48,22 +52,179 @@ void freeze_set_ops(const struct platform_freeze_ops *ops)
>  
>  static void freeze_begin(void)
>  {
> -	suspend_freeze_wake = false;
> +	suspend_freeze_wake = -1;
>  }
>  
> -static void freeze_enter(void)
> +enum freezer_state {
> +	FREEZER_NONE,
> +	FREEZER_PICK_TK,
> +	FREEZER_SUSPEND_CLKEVT,
> +	FREEZER_SUSPEND_TK,
> +	FREEZER_IDLE,
> +	FREEZER_RESUME_TK,
> +	FREEZER_RESUME_CLKEVT,
> +	FREEZER_EXIT,
> +};
> +
> +struct freezer_data {
> +	int			thread_num;
> +	atomic_t		thread_ack;
> +	enum freezer_state	state;
> +};
> +
> +static void set_state(struct freezer_data *fd, enum freezer_state state)
> +{
> +	/* set ack counter */
> +	atomic_set(&fd->thread_ack, fd->thread_num);
> +	/* guarantee the write ordering between ack counter and state */
> +	smp_wmb();
> +	fd->state = state;
> +}
> +
> +static void ack_state(struct freezer_data *fd)
> +{
> +	if (atomic_dec_and_test(&fd->thread_ack))
> +		set_state(fd, fd->state + 1);
> +}
> +
> +static void freezer_pick_tk(int cpu)
> +{
> +	if (tick_do_timer_cpu == TICK_DO_TIMER_NONE) {
> +		static DEFINE_SPINLOCK(lock);
> +
> +		spin_lock(&lock);
> +		if (tick_do_timer_cpu == TICK_DO_TIMER_NONE)
> +			tick_do_timer_cpu = cpu;
> +		spin_unlock(&lock);
> +	}
> +}
> +
> +static void freezer_suspend_clkevt(int cpu)
> +{
> +	if (tick_do_timer_cpu == cpu)
> +		return;
> +
> +	clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
> +}
> +
> +static void freezer_suspend_tk(int cpu)
>  {
> +	if (tick_do_timer_cpu != cpu)
> +		return;
> +

I had a note here that this might be broken for clocksource drivers that
have suspend/resume methods. You seem to have 'lost' that note, is that
because you found it isn't a problem?

> +	timekeeping_suspend();
> +
>  	cpuidle_use_deepest_state(true);
>  	cpuidle_resume();
> -	wait_event(suspend_freeze_wait_head, suspend_freeze_wake);
> +}
> +
> +static void freezer_idle(int cpu)
> +{
> +	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
> +	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
> +
> +	stop_critical_timings();
> +
> +	while (suspend_freeze_wake == -1) {
> +		int next_state;
> +
> +		/*
> +		 * interrupt must be disabled before cpu enters idle
> +		 */
> +		local_irq_disable();
> +
> +		next_state = cpuidle_select(drv, dev);
> +		if (next_state < 0) {
> +			arch_cpu_idle();
> +			continue;
> +		}
> +		/*
> +		 * cpuidle_enter will return with interrupt enabled
> +		 */
> +		cpuidle_enter(drv, dev, next_state);
> +	}
> +
> +	if (suspend_freeze_wake == cpu)
> +		kick_all_cpus_sync();
> +

So I disabled IRQs here

> +	start_critical_timings();
> +}
> +
> +static void freezer_resume_tk(int cpu)
> +{
> +	if (tick_do_timer_cpu != cpu)
> +		return;
> +
>  	cpuidle_pause();
>  	cpuidle_use_deepest_state(false);
> +

Such that they would still be disabled here

> +	local_irq_disable();
> +	timekeeping_resume();
> +	local_irq_enable();
> +}
> +
> +static void freezer_resume_clkevt(int cpu)
> +{
> +	if (tick_do_timer_cpu == cpu)
> +		return;
> +
> +	touch_softlockup_watchdog();
> +	clockevents_notify(CLOCK_EVT_NOTIFY_RESUME, NULL);

And here.

> +	local_irq_disable();
> +	hrtimers_resume();
> +	local_irq_enable();
> +}
> +
> +typedef void (*freezer_fn)(int);
> +
> +static freezer_fn freezer_func[FREEZER_EXIT] = {
> +	NULL,
> +	freezer_pick_tk,
> +	freezer_suspend_clkevt,
> +	freezer_suspend_tk,
> +	freezer_idle,
> +	freezer_resume_tk,
> +	freezer_resume_clkevt,
> +};

Because this is a stop_machine callback, which are nominally run with
IRQs disabled.

> +static int freezer_stopper_fn(void *arg)
> +{
> +	struct freezer_data *fd = arg;
> +	enum freezer_state state = FREEZER_NONE;
> +	int cpu = smp_processor_id();
> +
> +	do {
> +		cpu_relax();
> +		if (fd->state != state) {
> +			state = fd->state;
> +			if (freezer_func[state])
> +				(*freezer_func[state])(cpu);
> +			ack_state(fd);
> +		}
> +	} while (fd->state != FREEZER_EXIT);
> +	return 0;
> +}

Now I suppose the problem is with cpu_pause() which needs IPIs to
complete? Do we really need cpuidle_pause() there?
cpuidle_uninstall_handlers() seems like a daft thing to call just about
there.
--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Aubrey Li Oct. 27, 2014, 6:27 a.m. UTC | #2 
On 2014/10/24 23:36, Peter Zijlstra wrote:
> On Tue, Oct 21, 2014 at 11:15:10PM +0800, Li, Aubrey wrote:
>> +++ b/arch/x86/kernel/apic/apic.c
>> @@ -917,6 +917,14 @@ static void local_apic_timer_interrupt(void)
>>  	 */
>>  	inc_irq_stat(apic_timer_irqs);
>>  
>> +	/*
>> +	 * if timekeeping is suspended, the clock event device will be
>> +	 * suspended as well, so we are not supposed to invoke the event
>> +	 * handler of clock event device.
>> +	 */
>> +	if (unlikely(timekeeping_suspended))
>> +		return;
>> +
>>  	evt->event_handler(evt);
>>  }
>>  
> 
> How would this even happen? Didn't we just suspend the lapic?

There are two race conditions in my mind.

The first one occurs after the interrupt is disabled and before we
suspend lapic. In this time slot, if apic timer interrupt occurs, the
interrupt is pending there because the interrupt is disabled. Then we
suspend timekeeping, and then we enter idle and exit idle with interrupt
re-enabled, the timer interrupt is handled with timekeeping is
suspended. So we at least will hit WARN_ON(timekeeping_suspended) in
ktime_get().

The other occurs after timekeeping_suspended = 1 and before we suspend
lapic. In this time slot, if apic timer interrupt occurs, we will hit
the WARN in ktime_get() as above.

> 
>> diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
>> index 4ca9a33..e58d880 100644
>> --- a/kernel/power/suspend.c
>> +++ b/kernel/power/suspend.c
>> @@ -28,16 +28,20 @@
>>  #include <linux/ftrace.h>
>>  #include <trace/events/power.h>
>>  #include <linux/compiler.h>
>> +#include <linux/stop_machine.h>
>> +#include <linux/clockchips.h>
>> +#include <linux/hrtimer.h>
>>  
>>  #include "power.h"
>> +#include "../time/tick-internal.h"
>> +#include "../time/timekeeping_internal.h"
>>  
>>  const char *pm_labels[] = { "mem", "standby", "freeze", NULL };
>>  const char *pm_states[PM_SUSPEND_MAX];
>>  
>>  static const struct platform_suspend_ops *suspend_ops;
>>  static const struct platform_freeze_ops *freeze_ops;
>> -static DECLARE_WAIT_QUEUE_HEAD(suspend_freeze_wait_head);
>> -static bool suspend_freeze_wake;
>> +static int suspend_freeze_wake;
>>  
>>  void freeze_set_ops(const struct platform_freeze_ops *ops)
>>  {
>> @@ -48,22 +52,179 @@ void freeze_set_ops(const struct platform_freeze_ops *ops)
>>  
>>  static void freeze_begin(void)
>>  {
>> -	suspend_freeze_wake = false;
>> +	suspend_freeze_wake = -1;
>>  }
>>  
>> -static void freeze_enter(void)
>> +enum freezer_state {
>> +	FREEZER_NONE,
>> +	FREEZER_PICK_TK,
>> +	FREEZER_SUSPEND_CLKEVT,
>> +	FREEZER_SUSPEND_TK,
>> +	FREEZER_IDLE,
>> +	FREEZER_RESUME_TK,
>> +	FREEZER_RESUME_CLKEVT,
>> +	FREEZER_EXIT,
>> +};
>> +
>> +struct freezer_data {
>> +	int			thread_num;
>> +	atomic_t		thread_ack;
>> +	enum freezer_state	state;
>> +};
>> +
>> +static void set_state(struct freezer_data *fd, enum freezer_state state)
>> +{
>> +	/* set ack counter */
>> +	atomic_set(&fd->thread_ack, fd->thread_num);
>> +	/* guarantee the write ordering between ack counter and state */
>> +	smp_wmb();
>> +	fd->state = state;
>> +}
>> +
>> +static void ack_state(struct freezer_data *fd)
>> +{
>> +	if (atomic_dec_and_test(&fd->thread_ack))
>> +		set_state(fd, fd->state + 1);
>> +}
>> +
>> +static void freezer_pick_tk(int cpu)
>> +{
>> +	if (tick_do_timer_cpu == TICK_DO_TIMER_NONE) {
>> +		static DEFINE_SPINLOCK(lock);
>> +
>> +		spin_lock(&lock);
>> +		if (tick_do_timer_cpu == TICK_DO_TIMER_NONE)
>> +			tick_do_timer_cpu = cpu;
>> +		spin_unlock(&lock);
>> +	}
>> +}
>> +
>> +static void freezer_suspend_clkevt(int cpu)
>> +{
>> +	if (tick_do_timer_cpu == cpu)
>> +		return;
>> +
>> +	clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
>> +}
>> +
>> +static void freezer_suspend_tk(int cpu)
>>  {
>> +	if (tick_do_timer_cpu != cpu)
>> +		return;
>> +
> 
> I had a note here that this might be broken for clocksource drivers that
> have suspend/resume methods. You seem to have 'lost' that note, is that
> because you found it isn't a problem?
> 
I don't see it's a problem as long as we do not refer the clock source
before it resumes. But I think my testing didn't cover that case that
clock source drivers have suspend/resume methods. Can you please give
more details what do you worry about?

>> +	timekeeping_suspend();
>> +
>>  	cpuidle_use_deepest_state(true);
>>  	cpuidle_resume();
>> -	wait_event(suspend_freeze_wait_head, suspend_freeze_wake);
>> +}
>> +
>> +static void freezer_idle(int cpu)
>> +{
>> +	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
>> +	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
>> +
>> +	stop_critical_timings();
>> +
>> +	while (suspend_freeze_wake == -1) {
>> +		int next_state;
>> +
>> +		/*
>> +		 * interrupt must be disabled before cpu enters idle
>> +		 */
>> +		local_irq_disable();
>> +
>> +		next_state = cpuidle_select(drv, dev);
>> +		if (next_state < 0) {
>> +			arch_cpu_idle();
>> +			continue;
>> +		}
>> +		/*
>> +		 * cpuidle_enter will return with interrupt enabled
>> +		 */
>> +		cpuidle_enter(drv, dev, next_state);
>> +	}
>> +
>> +	if (suspend_freeze_wake == cpu)
>> +		kick_all_cpus_sync();
>> +
> 
> So I disabled IRQs here
> 
>> +	start_critical_timings();
>> +}
>> +
>> +static void freezer_resume_tk(int cpu)
>> +{
>> +	if (tick_do_timer_cpu != cpu)
>> +		return;
>> +
>>  	cpuidle_pause();
>>  	cpuidle_use_deepest_state(false);
>> +
> 
> Such that they would still be disabled here
> 
>> +	local_irq_disable();
>> +	timekeeping_resume();
>> +	local_irq_enable();
>> +}
>> +
>> +static void freezer_resume_clkevt(int cpu)
>> +{
>> +	if (tick_do_timer_cpu == cpu)
>> +		return;
>> +
>> +	touch_softlockup_watchdog();
>> +	clockevents_notify(CLOCK_EVT_NOTIFY_RESUME, NULL);
> 
> And here.
> 
>> +	local_irq_disable();
>> +	hrtimers_resume();
>> +	local_irq_enable();
>> +}
>> +
>> +typedef void (*freezer_fn)(int);
>> +
>> +static freezer_fn freezer_func[FREEZER_EXIT] = {
>> +	NULL,
>> +	freezer_pick_tk,
>> +	freezer_suspend_clkevt,
>> +	freezer_suspend_tk,
>> +	freezer_idle,
>> +	freezer_resume_tk,
>> +	freezer_resume_clkevt,
>> +};
> 
> Because this is a stop_machine callback, which are nominally run with
> IRQs disabled.

Let me double confirm and address this concern in a later mail.
> 
>> +static int freezer_stopper_fn(void *arg)
>> +{
>> +	struct freezer_data *fd = arg;
>> +	enum freezer_state state = FREEZER_NONE;
>> +	int cpu = smp_processor_id();
>> +
>> +	do {
>> +		cpu_relax();
>> +		if (fd->state != state) {
>> +			state = fd->state;
>> +			if (freezer_func[state])
>> +				(*freezer_func[state])(cpu);
>> +			ack_state(fd);
>> +		}
>> +	} while (fd->state != FREEZER_EXIT);
>> +	return 0;
>> +}
> 
> Now I suppose the problem is with cpu_pause() which needs IPIs to
> complete? Do we really need cpuidle_pause() there?
> cpuidle_uninstall_handlers() seems like a daft thing to call just about
> there.

Please check the log of 8651f97bd951d0bb1c10fa24e3fa3455193f3548.
Rafael should know more this question than me.

Thanks,
-Aubrey
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/
> 
> 
--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Peter Zijlstra Oct. 27, 2014, 7:28 a.m. UTC | #3 
On Mon, Oct 27, 2014 at 02:27:27PM +0800, Li, Aubrey wrote:
> > Now I suppose the problem is with cpu_pause() which needs IPIs to
> > complete? Do we really need cpuidle_pause() there?
> > cpuidle_uninstall_handlers() seems like a daft thing to call just about
> > there.
> 
> Please check the log of 8651f97bd951d0bb1c10fa24e3fa3455193f3548.
> Rafael should know more this question than me.

That changelog explains its complete bollocks to do it here. We _want_
to enter and/or remain in deep idle states.
--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Peter Zijlstra Oct. 27, 2014, 7:44 a.m. UTC | #4 
On Mon, Oct 27, 2014 at 02:27:27PM +0800, Li, Aubrey wrote:
> >> +static void freezer_suspend_tk(int cpu)
> >>  {
> >> +	if (tick_do_timer_cpu != cpu)
> >> +		return;
> >> +
> > 
> > I had a note here that this might be broken for clocksource drivers that
> > have suspend/resume methods. You seem to have 'lost' that note, is that
> > because you found it isn't a problem?
> > 
> I don't see it's a problem as long as we do not refer the clock source
> before it resumes. But I think my testing didn't cover that case that
> clock source drivers have suspend/resume methods. Can you please give
> more details what do you worry about?

I can't seem to recall :/ Maybe I conflated clocksource and clockevents
and figured we'd need to run the clocksource suspend callback on each
cpu.
--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Aubrey Li Oct. 28, 2014, 4:32 a.m. UTC | #5 
On 2014/10/27 15:28, Peter Zijlstra wrote:
> On Mon, Oct 27, 2014 at 02:27:27PM +0800, Li, Aubrey wrote:
>>> Now I suppose the problem is with cpu_pause() which needs IPIs to
>>> complete? Do we really need cpuidle_pause() there?
>>> cpuidle_uninstall_handlers() seems like a daft thing to call just about
>>> there.
>>
>> Please check the log of 8651f97bd951d0bb1c10fa24e3fa3455193f3548.
>> Rafael should know more this question than me.
> 
> That changelog explains its complete bollocks to do it here. We _want_
> to enter and/or remain in deep idle states.

cpuidle_resume() will be called at the end of dpm_resume_noirq(). So we
still are able to enter deep idle states after resume.

Thanks,
-Aubrey

> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/
> 
> 

--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Aubrey Li Oct. 28, 2014, 4:39 a.m. UTC | #6 
On 2014/10/24 23:36, Peter Zijlstra wrote:
>> +
>> +static void freezer_idle(int cpu)
>> +{
>> +	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
>> +	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
>> +
>> +	stop_critical_timings();
>> +
>> +	while (suspend_freeze_wake == -1) {
>> +		int next_state;
>> +
>> +		/*
>> +		 * interrupt must be disabled before cpu enters idle
>> +		 */
>> +		local_irq_disable();
>> +
>> +		next_state = cpuidle_select(drv, dev);
>> +		if (next_state < 0) {
>> +			arch_cpu_idle();
>> +			continue;
>> +		}
>> +		/*
>> +		 * cpuidle_enter will return with interrupt enabled
>> +		 */
>> +		cpuidle_enter(drv, dev, next_state);
>> +	}
>> +
>> +	if (suspend_freeze_wake == cpu)
>> +		kick_all_cpus_sync();
>> +
> 
> So I disabled IRQs here
> 
>> +	start_critical_timings();
>> +}
>> +
>> +static void freezer_resume_tk(int cpu)
>> +{
>> +	if (tick_do_timer_cpu != cpu)
>> +		return;
>> +
>>  	cpuidle_pause();
>>  	cpuidle_use_deepest_state(false);
>> +
> 
> Such that they would still be disabled here
> 
>> +	local_irq_disable();
>> +	timekeeping_resume();
>> +	local_irq_enable();
>> +}
>> +
>> +static void freezer_resume_clkevt(int cpu)
>> +{
>> +	if (tick_do_timer_cpu == cpu)
>> +		return;
>> +
>> +	touch_softlockup_watchdog();
>> +	clockevents_notify(CLOCK_EVT_NOTIFY_RESUME, NULL);
> 
> And here.
> 
>> +	local_irq_disable();
>> +	hrtimers_resume();
>> +	local_irq_enable();
>> +}
>> +
>> +typedef void (*freezer_fn)(int);
>> +
>> +static freezer_fn freezer_func[FREEZER_EXIT] = {
>> +	NULL,
>> +	freezer_pick_tk,
>> +	freezer_suspend_clkevt,
>> +	freezer_suspend_tk,
>> +	freezer_idle,
>> +	freezer_resume_tk,
>> +	freezer_resume_clkevt,
>> +};
> 
> Because this is a stop_machine callback, which are nominally run with
> IRQs disabled.
> 
>> +static int freezer_stopper_fn(void *arg)
>> +{
>> +	struct freezer_data *fd = arg;
>> +	enum freezer_state state = FREEZER_NONE;
>> +	int cpu = smp_processor_id();
>> +
>> +	do {
>> +		cpu_relax();
>> +		if (fd->state != state) {
>> +			state = fd->state;
>> +			if (freezer_func[state])
>> +				(*freezer_func[state])(cpu);
>> +			ack_state(fd);
>> +		}
>> +	} while (fd->state != FREEZER_EXIT);
>> +	return 0;
>> +}
> 
> Now I suppose the problem is with cpu_pause() which needs IPIs to
> complete? 

Yes, cpu_pause() will invoke smp IPI functions which need interrupt is
enabled. So I changed irq ops like above. Actually, I have an early
version to move cpuidle_pause()/cpuidle_resume() out of stop_machine(),
that might be a better solution?

Thanks,
-Aubrey

--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Aubrey Li Oct. 28, 2014, 7:52 a.m. UTC | #7 
On 2014/10/27 15:44, Peter Zijlstra wrote:
> On Mon, Oct 27, 2014 at 02:27:27PM +0800, Li, Aubrey wrote:
>>>> +static void freezer_suspend_tk(int cpu)
>>>>  {
>>>> +	if (tick_do_timer_cpu != cpu)
>>>> +		return;
>>>> +
>>>
>>> I had a note here that this might be broken for clocksource drivers that
>>> have suspend/resume methods. You seem to have 'lost' that note, is that
>>> because you found it isn't a problem?
>>>
>> I don't see it's a problem as long as we do not refer the clock source
>> before it resumes. But I think my testing didn't cover that case that
>> clock source drivers have suspend/resume methods. Can you please give
>> more details what do you worry about?
> 
> I can't seem to recall :/ Maybe I conflated clocksource and clockevents
> and figured we'd need to run the clocksource suspend callback on each
> cpu.

Both clocksource and clockevents are not per-cpu device, why do we need
to run their suspend callback on *each* cpu?

Thanks,
-Aubrey

> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/
> 
> 

--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Peter Zijlstra Oct. 28, 2014, 8:25 a.m. UTC | #8 
On Tue, Oct 28, 2014 at 03:52:17PM +0800, Li, Aubrey wrote:

> Both clocksource and clockevents are not per-cpu device, why do we need
> to run their suspend callback on *each* cpu?

Uhm, you mean to say we don't use per-cpu timer lists and per-cpu timer
hardware for clockevents then?
--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Peter Zijlstra Oct. 28, 2014, 8:25 a.m. UTC | #9 
On Tue, Oct 28, 2014 at 12:39:53PM +0800, Li, Aubrey wrote:

> > Now I suppose the problem is with cpu_pause() which needs IPIs to
> > complete? 
> 
> Yes, cpu_pause() will invoke smp IPI functions which need interrupt is
> enabled. So I changed irq ops like above. Actually, I have an early
> version to move cpuidle_pause()/cpuidle_resume() out of stop_machine(),
> that might be a better solution?

I think you can simply remove them altogether, they're nonsense.
--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Peter Zijlstra Oct. 28, 2014, 8:29 a.m. UTC | #10 
On Tue, Oct 28, 2014 at 12:32:16PM +0800, Li, Aubrey wrote:
> On 2014/10/27 15:28, Peter Zijlstra wrote:
> > On Mon, Oct 27, 2014 at 02:27:27PM +0800, Li, Aubrey wrote:
> >>> Now I suppose the problem is with cpu_pause() which needs IPIs to
> >>> complete? Do we really need cpuidle_pause() there?
> >>> cpuidle_uninstall_handlers() seems like a daft thing to call just about
> >>> there.
> >>
> >> Please check the log of 8651f97bd951d0bb1c10fa24e3fa3455193f3548.
> >> Rafael should know more this question than me.
> > 
> > That changelog explains its complete bollocks to do it here. We _want_
> > to enter and/or remain in deep idle states.
> 
> cpuidle_resume() will be called at the end of dpm_resume_noirq(). So we
> still are able to enter deep idle states after resume.

cpuidle_resume is absolute crap, as is cpuidle_suspend for that matter
-- in this case.

The only reason we needed cpuidle_suspend is because some BIOS shat its
pants when some CPUs were in higher C states while trying to do the S3
thing. We're not going to use S states or BIOS calls _at_all_, so no
point in kicking CPUs out of their deep C states.

Read that changelog you referred me to again.
--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Aubrey Li Oct. 28, 2014, 10:46 p.m. UTC | #11 
On 2014/10/28 16:29, Peter Zijlstra wrote:
> On Tue, Oct 28, 2014 at 12:32:16PM +0800, Li, Aubrey wrote:
>> On 2014/10/27 15:28, Peter Zijlstra wrote:
>>> On Mon, Oct 27, 2014 at 02:27:27PM +0800, Li, Aubrey wrote:
>>>>> Now I suppose the problem is with cpu_pause() which needs IPIs to
>>>>> complete? Do we really need cpuidle_pause() there?
>>>>> cpuidle_uninstall_handlers() seems like a daft thing to call just about
>>>>> there.
>>>>
>>>> Please check the log of 8651f97bd951d0bb1c10fa24e3fa3455193f3548.
>>>> Rafael should know more this question than me.
>>>
>>> That changelog explains its complete bollocks to do it here. We _want_
>>> to enter and/or remain in deep idle states.
>>
>> cpuidle_resume() will be called at the end of dpm_resume_noirq(). So we
>> still are able to enter deep idle states after resume.
> 
> cpuidle_resume is absolute crap, as is cpuidle_suspend for that matter
> -- in this case.
> 
> The only reason we needed cpuidle_suspend is because some BIOS shat its
> pants when some CPUs were in higher C states while trying to do the S3
> thing. We're not going to use S states or BIOS calls _at_all_, so no
> point in kicking CPUs out of their deep C states.

We already kicked CPUs out of their deep C states in dpm_suspend_noirq().

We pause cpuidle in dpm_suspend_noirq() and resume cpuidle in
dpm_resume_noirq(), so currently we can't enter deep c-state during S
states. That's an intention for some buggy BIOS.

However, for freeze state, there is another intention that we want
always to enter the *deepest* c-state every time we enter freeze.
So we need cpuidle_resume() to make sure we have deep cstate  in freeze.

So back to your question in another email,

> I think you can simply remove them altogether, they're nonsense.

We need them to resume cpuidle in freeze.

Thanks,
-Aubrey

> 
> Read that changelog you referred me to again.
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/
> 
> 

--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Aubrey Li Oct. 28, 2014, 11:22 p.m. UTC | #12 
On 2014/10/28 16:25, Peter Zijlstra wrote:
> On Tue, Oct 28, 2014 at 03:52:17PM +0800, Li, Aubrey wrote:
> 
>> Both clocksource and clockevents are not per-cpu device, why do we need
>> to run their suspend callback on *each* cpu?
> 
> Uhm, you mean to say we don't use per-cpu timer lists and per-cpu timer
> hardware for clockevents then?
> 

From OS level, currently tick device is per-cpu implementation while
clocksource and clockevent devices are global device.

We already stop tick by clockevents_notify(suspend) on each cpu, that
addresses per-cpu timer list.

And, we already call clocksource_suspend() and clockevents_suspend() in
timekeeping_suspend() on the tick timer CPU. Yes, we didn't suspend
per-cpu timer hardware on x86 because x86 does not have lapic timer
suspend implementation. If we need to implement this, I think we can do
the cross-CPU calls in clocksource/clockevents suspend(), but I didn't
see any necessary we need to do this now.

so, I think we are okay now, :)

Thanks,
-Aubrey
--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Peter Zijlstra Oct. 29, 2014, 8:21 a.m. UTC | #13 
On Wed, Oct 29, 2014 at 06:46:03AM +0800, Li, Aubrey wrote:
> On 2014/10/28 16:29, Peter Zijlstra wrote:
> > On Tue, Oct 28, 2014 at 12:32:16PM +0800, Li, Aubrey wrote:
> >> On 2014/10/27 15:28, Peter Zijlstra wrote:
> >>> On Mon, Oct 27, 2014 at 02:27:27PM +0800, Li, Aubrey wrote:
> >>>>> Now I suppose the problem is with cpu_pause() which needs IPIs to
> >>>>> complete? Do we really need cpuidle_pause() there?
> >>>>> cpuidle_uninstall_handlers() seems like a daft thing to call just about
> >>>>> there.
> >>>>
> >>>> Please check the log of 8651f97bd951d0bb1c10fa24e3fa3455193f3548.
> >>>> Rafael should know more this question than me.
> >>>
> >>> That changelog explains its complete bollocks to do it here. We _want_
> >>> to enter and/or remain in deep idle states.
> >>
> >> cpuidle_resume() will be called at the end of dpm_resume_noirq(). So we
> >> still are able to enter deep idle states after resume.
> > 
> > cpuidle_resume is absolute crap, as is cpuidle_suspend for that matter
> > -- in this case.
> > 
> > The only reason we needed cpuidle_suspend is because some BIOS shat its
> > pants when some CPUs were in higher C states while trying to do the S3
> > thing. We're not going to use S states or BIOS calls _at_all_, so no
> > point in kicking CPUs out of their deep C states.
> 
> We already kicked CPUs out of their deep C states in dpm_suspend_noirq().
> 
> We pause cpuidle in dpm_suspend_noirq() and resume cpuidle in
> dpm_resume_noirq(), so currently we can't enter deep c-state during S
> states. That's an intention for some buggy BIOS.

And work arounds for buggy crap hardware should not be in generic code.
They should be in the platform drivers associated with said crap bugs.

But I think I see what you're saying, we're going through this dpm_ crap
even for suspend to idle, which is wrong too.

> However, for freeze state, there is another intention that we want
> always to enter the *deepest* c-state every time we enter freeze.
> So we need cpuidle_resume() to make sure we have deep cstate  in freeze.
> 
> So back to your question in another email,
> 
> > I think you can simply remove them altogether, they're nonsense.
> 
> We need them to resume cpuidle in freeze.

So you can do cpuidle_resume() before we do the stop machine dance, but
ideally it'd all be ripped out from generic code and stuffed into
the platform drivers where it belongs. But at the very least it should
be isolated to the S3 path, I bet suspend to disk doesn't care either.

--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Peter Zijlstra Oct. 29, 2014, 8:24 a.m. UTC | #14 
On Wed, Oct 29, 2014 at 07:22:35AM +0800, Li, Aubrey wrote:
> On 2014/10/28 16:25, Peter Zijlstra wrote:
> > On Tue, Oct 28, 2014 at 03:52:17PM +0800, Li, Aubrey wrote:
> > 
> >> Both clocksource and clockevents are not per-cpu device, why do we need
> >> to run their suspend callback on *each* cpu?
> > 
> > Uhm, you mean to say we don't use per-cpu timer lists and per-cpu timer
> > hardware for clockevents then?
> > 
> 
> From OS level, currently tick device is per-cpu implementation while
> clocksource and clockevent devices are global device.
> 
> We already stop tick by clockevents_notify(suspend) on each cpu, that
> addresses per-cpu timer list.

Right, I know. But I was saying I might have confused myself between
events and sources while going through that call chain, thereby
(mistakenly) thinking the source suspend code needed more than the 1
cpu.

Its easy to confuse yourself trying to reverse engineer that opaque
callchain :-)

> And, we already call clocksource_suspend() and clockevents_suspend() in
> timekeeping_suspend() on the tick timer CPU. Yes, we didn't suspend
> per-cpu timer hardware on x86 because x86 does not have lapic timer
> suspend implementation. If we need to implement this, I think we can do
> the cross-CPU calls in clocksource/clockevents suspend(), but I didn't
> see any necessary we need to do this now.
> 
> so, I think we are okay now, :)

Right, I tend to agree, we'll find out quickly enough once those
platforms will try this code anyhow ;-)
--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Aubrey Li Oct. 29, 2014, 3:09 p.m. UTC | #15 
On 2014/10/29 16:21, Peter Zijlstra wrote:
> On Wed, Oct 29, 2014 at 06:46:03AM +0800, Li, Aubrey wrote:
>> On 2014/10/28 16:29, Peter Zijlstra wrote:
>>> On Tue, Oct 28, 2014 at 12:32:16PM +0800, Li, Aubrey wrote:
>>>> On 2014/10/27 15:28, Peter Zijlstra wrote:
>>>>> On Mon, Oct 27, 2014 at 02:27:27PM +0800, Li, Aubrey wrote:
>>>>>>> Now I suppose the problem is with cpu_pause() which needs IPIs to
>>>>>>> complete? Do we really need cpuidle_pause() there?
>>>>>>> cpuidle_uninstall_handlers() seems like a daft thing to call just about
>>>>>>> there.
>>>>>>
>>>>>> Please check the log of 8651f97bd951d0bb1c10fa24e3fa3455193f3548.
>>>>>> Rafael should know more this question than me.
>>>>>
>>>>> That changelog explains its complete bollocks to do it here. We _want_
>>>>> to enter and/or remain in deep idle states.
>>>>
>>>> cpuidle_resume() will be called at the end of dpm_resume_noirq(). So we
>>>> still are able to enter deep idle states after resume.
>>>
>>> cpuidle_resume is absolute crap, as is cpuidle_suspend for that matter
>>> -- in this case.
>>>
>>> The only reason we needed cpuidle_suspend is because some BIOS shat its
>>> pants when some CPUs were in higher C states while trying to do the S3
>>> thing. We're not going to use S states or BIOS calls _at_all_, so no
>>> point in kicking CPUs out of their deep C states.
>>
>> We already kicked CPUs out of their deep C states in dpm_suspend_noirq().
>>
>> We pause cpuidle in dpm_suspend_noirq() and resume cpuidle in
>> dpm_resume_noirq(), so currently we can't enter deep c-state during S
>> states. That's an intention for some buggy BIOS.
> 
> And work arounds for buggy crap hardware should not be in generic code.
> They should be in the platform drivers associated with said crap bugs.
> 
> But I think I see what you're saying, we're going through this dpm_ crap
> even for suspend to idle, which is wrong too.
> 
>> However, for freeze state, there is another intention that we want
>> always to enter the *deepest* c-state every time we enter freeze.
>> So we need cpuidle_resume() to make sure we have deep cstate  in freeze.
>>
>> So back to your question in another email,
>>
>>> I think you can simply remove them altogether, they're nonsense.
>>
>> We need them to resume cpuidle in freeze.
> 
> So you can do cpuidle_resume() before we do the stop machine dance,

I agree, this can leave the current behavior unchanged. I'll send out a
refined version soon.

> but ideally it'd all be ripped out from generic code and stuffed into
> the platform drivers where it belongs. But at the very least it should
> be isolated to the S3 path, I bet suspend to disk doesn't care either.
> 
I think this is a good question to Rafael, which I ever asked before.

Thanks,
-Aubrey
--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 6776027..f2bb645 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -917,6 +917,14 @@  static void local_apic_timer_interrupt(void)
 	 */
 	inc_irq_stat(apic_timer_irqs);
 
+	/*
+	 * if timekeeping is suspended, the clock event device will be
+	 * suspended as well, so we are not supposed to invoke the event
+	 * handler of clock event device.
+	 */
+	if (unlikely(timekeeping_suspended))
+		return;
+
 	evt->event_handler(evt);
 }
 
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index ee9df5e..8f84f40 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -119,6 +119,18 @@  int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	ktime_t time_start, time_end;
 	s64 diff;
 
+	/*
+	 * under the scenario of use deepest idle state, the timekeeping
+	 * could be suspended as well as the clock source device, so we
+	 * bypass the idle counter update for this case
+	 */
+	if (unlikely(use_deepest_state)) {
+		entered_state = target_state->enter(dev, drv, index);
+		if (!cpuidle_state_is_coupled(dev, drv, entered_state))
+			local_irq_enable();
+		return entered_state;
+	}
+
 	trace_cpu_idle_rcuidle(index, dev->cpu);
 	time_start = ktime_get();
 
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 4ca9a33..e58d880 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -28,16 +28,20 @@ 
 #include <linux/ftrace.h>
 #include <trace/events/power.h>
 #include <linux/compiler.h>
+#include <linux/stop_machine.h>
+#include <linux/clockchips.h>
+#include <linux/hrtimer.h>
 
 #include "power.h"
+#include "../time/tick-internal.h"
+#include "../time/timekeeping_internal.h"
 
 const char *pm_labels[] = { "mem", "standby", "freeze", NULL };
 const char *pm_states[PM_SUSPEND_MAX];
 
 static const struct platform_suspend_ops *suspend_ops;
 static const struct platform_freeze_ops *freeze_ops;
-static DECLARE_WAIT_QUEUE_HEAD(suspend_freeze_wait_head);
-static bool suspend_freeze_wake;
+static int suspend_freeze_wake;
 
 void freeze_set_ops(const struct platform_freeze_ops *ops)
 {
@@ -48,22 +52,179 @@  void freeze_set_ops(const struct platform_freeze_ops *ops)
 
 static void freeze_begin(void)
 {
-	suspend_freeze_wake = false;
+	suspend_freeze_wake = -1;
 }
 
-static void freeze_enter(void)
+enum freezer_state {
+	FREEZER_NONE,
+	FREEZER_PICK_TK,
+	FREEZER_SUSPEND_CLKEVT,
+	FREEZER_SUSPEND_TK,
+	FREEZER_IDLE,
+	FREEZER_RESUME_TK,
+	FREEZER_RESUME_CLKEVT,
+	FREEZER_EXIT,
+};
+
+struct freezer_data {
+	int			thread_num;
+	atomic_t		thread_ack;
+	enum freezer_state	state;
+};
+
+static void set_state(struct freezer_data *fd, enum freezer_state state)
+{
+	/* set ack counter */
+	atomic_set(&fd->thread_ack, fd->thread_num);
+	/* guarantee the write ordering between ack counter and state */
+	smp_wmb();
+	fd->state = state;
+}
+
+static void ack_state(struct freezer_data *fd)
+{
+	if (atomic_dec_and_test(&fd->thread_ack))
+		set_state(fd, fd->state + 1);
+}
+
+static void freezer_pick_tk(int cpu)
+{
+	if (tick_do_timer_cpu == TICK_DO_TIMER_NONE) {
+		static DEFINE_SPINLOCK(lock);
+
+		spin_lock(&lock);
+		if (tick_do_timer_cpu == TICK_DO_TIMER_NONE)
+			tick_do_timer_cpu = cpu;
+		spin_unlock(&lock);
+	}
+}
+
+static void freezer_suspend_clkevt(int cpu)
+{
+	if (tick_do_timer_cpu == cpu)
+		return;
+
+	clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
+}
+
+static void freezer_suspend_tk(int cpu)
 {
+	if (tick_do_timer_cpu != cpu)
+		return;
+
+	timekeeping_suspend();
+
 	cpuidle_use_deepest_state(true);
 	cpuidle_resume();
-	wait_event(suspend_freeze_wait_head, suspend_freeze_wake);
+}
+
+static void freezer_idle(int cpu)
+{
+	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
+	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
+
+	stop_critical_timings();
+
+	while (suspend_freeze_wake == -1) {
+		int next_state;
+
+		/*
+		 * interrupt must be disabled before cpu enters idle
+		 */
+		local_irq_disable();
+
+		next_state = cpuidle_select(drv, dev);
+		if (next_state < 0) {
+			arch_cpu_idle();
+			continue;
+		}
+		/*
+		 * cpuidle_enter will return with interrupt enabled
+		 */
+		cpuidle_enter(drv, dev, next_state);
+	}
+
+	if (suspend_freeze_wake == cpu)
+		kick_all_cpus_sync();
+
+	start_critical_timings();
+}
+
+static void freezer_resume_tk(int cpu)
+{
+	if (tick_do_timer_cpu != cpu)
+		return;
+
 	cpuidle_pause();
 	cpuidle_use_deepest_state(false);
+
+	local_irq_disable();
+	timekeeping_resume();
+	local_irq_enable();
+}
+
+static void freezer_resume_clkevt(int cpu)
+{
+	if (tick_do_timer_cpu == cpu)
+		return;
+
+	touch_softlockup_watchdog();
+	clockevents_notify(CLOCK_EVT_NOTIFY_RESUME, NULL);
+	local_irq_disable();
+	hrtimers_resume();
+	local_irq_enable();
+}
+
+typedef void (*freezer_fn)(int);
+
+static freezer_fn freezer_func[FREEZER_EXIT] = {
+	NULL,
+	freezer_pick_tk,
+	freezer_suspend_clkevt,
+	freezer_suspend_tk,
+	freezer_idle,
+	freezer_resume_tk,
+	freezer_resume_clkevt,
+};
+
+static int freezer_stopper_fn(void *arg)
+{
+	struct freezer_data *fd = arg;
+	enum freezer_state state = FREEZER_NONE;
+	int cpu = smp_processor_id();
+
+	do {
+		cpu_relax();
+		if (fd->state != state) {
+			state = fd->state;
+			if (freezer_func[state])
+				(*freezer_func[state])(cpu);
+			ack_state(fd);
+		}
+	} while (fd->state != FREEZER_EXIT);
+
+	return 0;
+}
+
+static void freeze_enter(void)
+{
+	struct freezer_data fd;
+
+	get_online_cpus();
+
+	fd.thread_num = num_online_cpus();
+	set_state(&fd, FREEZER_PICK_TK);
+
+	__stop_machine(freezer_stopper_fn, &fd, cpu_online_mask);
+
+	put_online_cpus();
 }
 
 void freeze_wake(void)
 {
-	suspend_freeze_wake = true;
-	wake_up(&suspend_freeze_wait_head);
+	if (suspend_freeze_wake != -1)
+		return;
+	suspend_freeze_wake = smp_processor_id();
 }
 EXPORT_SYMBOL_GPL(freeze_wake);
 
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index ec1791f..23d8feb 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1114,7 +1114,7 @@  void timekeeping_inject_sleeptime(struct timespec *delta)
  * xtime/wall_to_monotonic/jiffies/etc are
  * still managed by arch specific suspend/resume code.
  */
-static void timekeeping_resume(void)
+void timekeeping_resume(void)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	struct clocksource *clock = tk->tkr.clock;
@@ -1195,7 +1195,7 @@  static void timekeeping_resume(void)
 	hrtimers_resume();
 }
 
-static int timekeeping_suspend(void)
+int timekeeping_suspend(void)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	unsigned long flags;
diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h
index 4ea005a..ed7a574 100644
--- a/kernel/time/timekeeping_internal.h
+++ b/kernel/time/timekeeping_internal.h
@@ -26,4 +26,7 @@  static inline cycle_t clocksource_delta(cycle_t now, cycle_t last, cycle_t mask)
 }
 #endif
 
+extern int timekeeping_suspend(void);
+extern void timekeeping_resume(void);
+
 #endif /* _TIMEKEEPING_INTERNAL_H */