cpuidle: Measure idle state durations with monotonic clock
Many cpuidle drivers measure their time spent in an idle state by
reading the wallclock time before and after idling and calculating the
difference. This leads to erroneous results when the wallclock time gets
updated by another processor in the meantime, adding that clock
adjustment to the idle state's time counter.
If the clock adjustment was negative, the result is even worse due to an
erroneous cast from int to unsigned long long of the last_residency
variable. The negative 32 bit integer will zero-extend and result in a
forward time jump of roughly four billion milliseconds or 1.3 hours on
the idle state residency counter.
This patch changes all affected cpuidle drivers to either use the
monotonic clock for their measurements or make use of the generic time
measurement wrapper in cpuidle.c, which was already working correctly.
Some superfluous CLIs/STIs in the ACPI code are removed (interrupts
should always already be disabled before entering the idle function, and
not get reenabled until the generic wrapper has performed its second
measurement). It also removes the erroneous cast, making sure that
negative residency values are applied correctly even though they should
not appear anymore.
Signed-off-by: Julius Werner <jwerner@chromium.org>
Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Tested-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Acked-by: Len Brown <len.brown@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index e8086c7..f1a5da4 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -735,31 +735,18 @@
static int acpi_idle_enter_c1(struct cpuidle_device *dev,
struct cpuidle_driver *drv, int index)
{
- ktime_t kt1, kt2;
- s64 idle_time;
struct acpi_processor *pr;
struct cpuidle_state_usage *state_usage = &dev->states_usage[index];
struct acpi_processor_cx *cx = cpuidle_get_statedata(state_usage);
pr = __this_cpu_read(processors);
- dev->last_residency = 0;
if (unlikely(!pr))
return -EINVAL;
- local_irq_disable();
-
-
lapic_timer_state_broadcast(pr, cx, 1);
- kt1 = ktime_get_real();
acpi_idle_do_entry(cx);
- kt2 = ktime_get_real();
- idle_time = ktime_to_us(ktime_sub(kt2, kt1));
- /* Update device last_residency*/
- dev->last_residency = (int)idle_time;
-
- local_irq_enable();
lapic_timer_state_broadcast(pr, cx, 0);
return index;
@@ -806,19 +793,12 @@
struct acpi_processor *pr;
struct cpuidle_state_usage *state_usage = &dev->states_usage[index];
struct acpi_processor_cx *cx = cpuidle_get_statedata(state_usage);
- ktime_t kt1, kt2;
- s64 idle_time_ns;
- s64 idle_time;
pr = __this_cpu_read(processors);
- dev->last_residency = 0;
if (unlikely(!pr))
return -EINVAL;
- local_irq_disable();
-
-
if (cx->entry_method != ACPI_CSTATE_FFH) {
current_thread_info()->status &= ~TS_POLLING;
/*
@@ -829,7 +809,6 @@
if (unlikely(need_resched())) {
current_thread_info()->status |= TS_POLLING;
- local_irq_enable();
return -EINVAL;
}
}
@@ -843,22 +822,12 @@
if (cx->type == ACPI_STATE_C3)
ACPI_FLUSH_CPU_CACHE();
- kt1 = ktime_get_real();
/* Tell the scheduler that we are going deep-idle: */
sched_clock_idle_sleep_event();
acpi_idle_do_entry(cx);
- kt2 = ktime_get_real();
- idle_time_ns = ktime_to_ns(ktime_sub(kt2, kt1));
- idle_time = idle_time_ns;
- do_div(idle_time, NSEC_PER_USEC);
- /* Update device last_residency*/
- dev->last_residency = (int)idle_time;
+ sched_clock_idle_wakeup_event(0);
- /* Tell the scheduler how much we idled: */
- sched_clock_idle_wakeup_event(idle_time_ns);
-
- local_irq_enable();
if (cx->entry_method != ACPI_CSTATE_FFH)
current_thread_info()->status |= TS_POLLING;
@@ -883,13 +852,8 @@
struct acpi_processor *pr;
struct cpuidle_state_usage *state_usage = &dev->states_usage[index];
struct acpi_processor_cx *cx = cpuidle_get_statedata(state_usage);
- ktime_t kt1, kt2;
- s64 idle_time_ns;
- s64 idle_time;
-
pr = __this_cpu_read(processors);
- dev->last_residency = 0;
if (unlikely(!pr))
return -EINVAL;
@@ -899,16 +863,11 @@
return drv->states[drv->safe_state_index].enter(dev,
drv, drv->safe_state_index);
} else {
- local_irq_disable();
acpi_safe_halt();
- local_irq_enable();
return -EBUSY;
}
}
- local_irq_disable();
-
-
if (cx->entry_method != ACPI_CSTATE_FFH) {
current_thread_info()->status &= ~TS_POLLING;
/*
@@ -919,7 +878,6 @@
if (unlikely(need_resched())) {
current_thread_info()->status |= TS_POLLING;
- local_irq_enable();
return -EINVAL;
}
}
@@ -934,7 +892,6 @@
*/
lapic_timer_state_broadcast(pr, cx, 1);
- kt1 = ktime_get_real();
/*
* disable bus master
* bm_check implies we need ARB_DIS
@@ -965,18 +922,9 @@
c3_cpu_count--;
raw_spin_unlock(&c3_lock);
}
- kt2 = ktime_get_real();
- idle_time_ns = ktime_to_ns(ktime_sub(kt2, kt1));
- idle_time = idle_time_ns;
- do_div(idle_time, NSEC_PER_USEC);
- /* Update device last_residency*/
- dev->last_residency = (int)idle_time;
+ sched_clock_idle_wakeup_event(0);
- /* Tell the scheduler how much we idled: */
- sched_clock_idle_wakeup_event(idle_time_ns);
-
- local_irq_enable();
if (cx->entry_method != ACPI_CSTATE_FFH)
current_thread_info()->status |= TS_POLLING;
@@ -987,6 +935,7 @@
struct cpuidle_driver acpi_idle_driver = {
.name = "acpi_idle",
.owner = THIS_MODULE,
+ .en_core_tk_irqen = 1,
};
/**