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);