linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
* [PATCH] cpuidle: Measure idle state durations with monotonic clock
@ 2012-11-13 21:52 Julius Werner
  2012-11-14  9:06 ` Deepthi Dharwar
  2012-11-14 11:05 ` Daniel Lezcano
  0 siblings, 2 replies; 12+ messages in thread
From: Julius Werner @ 2012-11-13 21:52 UTC (permalink / raw)
  To: linux-kernel
  Cc: Kevin Hilman, Deepthi Dharwar, Trinabh Gupta, linux-pm,
	Daniel Lezcano, Rafael J. Wysocki, linux-acpi, Srivatsa S. Bhat,
	Julius Werner, Andrew Morton, linuxppc-dev, Sameer Nanda,
	Len Brown

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 use the monotonic
clock for their measurements instead. 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>
---
 arch/powerpc/platforms/pseries/processor_idle.c |    4 ++--
 drivers/acpi/processor_idle.c                   |   12 ++++++------
 drivers/cpuidle/cpuidle.c                       |    3 +--
 drivers/idle/intel_idle.c                       |   13 ++++---------
 4 files changed, 13 insertions(+), 19 deletions(-)

diff --git a/arch/powerpc/platforms/pseries/processor_idle.c b/arch/powerpc/platforms/pseries/processor_idle.c
index 45d00e5..4d806b4 100644
--- a/arch/powerpc/platforms/pseries/processor_idle.c
+++ b/arch/powerpc/platforms/pseries/processor_idle.c
@@ -36,7 +36,7 @@ static struct cpuidle_state *cpuidle_state_table;
 static inline void idle_loop_prolog(unsigned long *in_purr, ktime_t *kt_before)
 {
 
-	*kt_before = ktime_get_real();
+	*kt_before = ktime_get();
 	*in_purr = mfspr(SPRN_PURR);
 	/*
 	 * Indicate to the HV that we are idle. Now would be
@@ -50,7 +50,7 @@ static inline  s64 idle_loop_epilog(unsigned long in_purr, ktime_t kt_before)
 	get_lppaca()->wait_state_cycles += mfspr(SPRN_PURR) - in_purr;
 	get_lppaca()->idle = 0;
 
-	return ktime_to_us(ktime_sub(ktime_get_real(), kt_before));
+	return ktime_to_us(ktime_sub(ktime_get(), kt_before));
 }
 
 static int snooze_loop(struct cpuidle_device *dev,
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index e8086c7..8c98d73 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -751,9 +751,9 @@ static int acpi_idle_enter_c1(struct cpuidle_device *dev,
 
 
 	lapic_timer_state_broadcast(pr, cx, 1);
-	kt1 = ktime_get_real();
+	kt1 = ktime_get();
 	acpi_idle_do_entry(cx);
-	kt2 = ktime_get_real();
+	kt2 = ktime_get();
 	idle_time =  ktime_to_us(ktime_sub(kt2, kt1));
 
 	/* Update device last_residency*/
@@ -843,11 +843,11 @@ static int acpi_idle_enter_simple(struct cpuidle_device *dev,
 	if (cx->type == ACPI_STATE_C3)
 		ACPI_FLUSH_CPU_CACHE();
 
-	kt1 = ktime_get_real();
+	kt1 = ktime_get();
 	/* Tell the scheduler that we are going deep-idle: */
 	sched_clock_idle_sleep_event();
 	acpi_idle_do_entry(cx);
-	kt2 = ktime_get_real();
+	kt2 = ktime_get();
 	idle_time_ns = ktime_to_ns(ktime_sub(kt2, kt1));
 	idle_time = idle_time_ns;
 	do_div(idle_time, NSEC_PER_USEC);
@@ -934,7 +934,7 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev,
 	 */
 	lapic_timer_state_broadcast(pr, cx, 1);
 
-	kt1 = ktime_get_real();
+	kt1 = ktime_get();
 	/*
 	 * disable bus master
 	 * bm_check implies we need ARB_DIS
@@ -965,7 +965,7 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev,
 		c3_cpu_count--;
 		raw_spin_unlock(&c3_lock);
 	}
-	kt2 = ktime_get_real();
+	kt2 = ktime_get();
 	idle_time_ns = ktime_to_ns(ktime_sub(kt2, kt1));
 	idle_time = idle_time_ns;
 	do_div(idle_time, NSEC_PER_USEC);
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 7f15b85..1536edd 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -109,8 +109,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 		/* This can be moved to within driver enter routine
 		 * but that results in multiple copies of same code.
 		 */
-		dev->states_usage[entered_state].time +=
-				(unsigned long long)dev->last_residency;
+		dev->states_usage[entered_state].time += dev->last_residency;
 		dev->states_usage[entered_state].usage++;
 	} else {
 		dev->last_residency = 0;
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index b0f6b4c..6329a97 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -56,7 +56,7 @@
 #include <linux/kernel.h>
 #include <linux/cpuidle.h>
 #include <linux/clockchips.h>
-#include <linux/hrtimer.h>	/* ktime_get_real() */
+#include <linux/hrtimer.h>	/* ktime_get() */
 #include <trace/events/power.h>
 #include <linux/sched.h>
 #include <linux/notifier.h>
@@ -281,8 +281,7 @@ static int intel_idle(struct cpuidle_device *dev,
 	struct cpuidle_state_usage *state_usage = &dev->states_usage[index];
 	unsigned long eax = (unsigned long)cpuidle_get_statedata(state_usage);
 	unsigned int cstate;
-	ktime_t kt_before, kt_after;
-	s64 usec_delta;
+	ktime_t kt_before;
 	int cpu = smp_processor_id();
 
 	cstate = (((eax) >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK) + 1;
@@ -297,7 +296,7 @@ static int intel_idle(struct cpuidle_device *dev,
 	if (!(lapic_timer_reliable_states & (1 << (cstate))))
 		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
 
-	kt_before = ktime_get_real();
+	kt_before = ktime_get();
 
 	stop_critical_timings();
 	if (!need_resched()) {
@@ -310,17 +309,13 @@ static int intel_idle(struct cpuidle_device *dev,
 
 	start_critical_timings();
 
-	kt_after = ktime_get_real();
-	usec_delta = ktime_to_us(ktime_sub(kt_after, kt_before));
+	dev->last_residency = ktime_to_us(ktime_sub(ktime_get(), kt_before));
 
 	local_irq_enable();
 
 	if (!(lapic_timer_reliable_states & (1 << (cstate))))
 		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
 
-	/* Update cpuidle counters */
-	dev->last_residency = (int)usec_delta;
-
 	return index;
 }
 
-- 
1.7.8.6

^ permalink raw reply related	[flat|nested] 12+ messages in thread

end of thread, other threads:[~2012-11-27 19:14 UTC | newest]

Thread overview: 12+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2012-11-13 21:52 [PATCH] cpuidle: Measure idle state durations with monotonic clock Julius Werner
2012-11-14  9:06 ` Deepthi Dharwar
2012-11-14 10:57   ` Daniel Lezcano
2012-11-14 11:05 ` Daniel Lezcano
2012-11-14 17:15   ` Julius Werner
2012-11-15  1:56     ` Julius Werner
2012-11-15  9:04       ` Preeti Murthy
2012-11-27  6:14         ` Len Brown
2012-11-15 10:52       ` Daniel Lezcano
2012-11-21  0:17       ` Rafael J. Wysocki
2012-11-27  6:15         ` Len Brown
2012-11-27 19:12       ` Rafael J. Wysocki

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).