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>

1 files changed, 1 insertions, 13 deletions

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index b0f6b4c8ee14..c49c04d9c2b0 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -56,7 +56,6 @@
 #include <linux/kernel.h>
 #include <linux/cpuidle.h>
 #include <linux/clockchips.h>
-#include <linux/hrtimer.h>      /* ktime_get_real() */
 #include <trace/events/power.h>
 #include <linux/sched.h>
 #include <linux/notifier.h>
@@ -72,6 +71,7 @@
 static struct cpuidle_driver intel_idle_driver = {
         .name = "intel_idle",
         .owner = THIS_MODULE,
+        .en_core_tk_irqen = 1,
 };
 /* intel_idle.max_cstate=0 disables driver */
 static int max_cstate = MWAIT_MAX_NUM_CSTATES - 1;
@@ -281,8 +281,6 @@ 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;
         int cpu = smp_processor_id();
 
         cstate = (((eax) >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK) + 1;
@@ -297,8 +295,6 @@ 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();
-
         stop_critical_timings();
         if (!need_resched()) {
 
@@ -310,17 +306,9 @@ 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));
-
-        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;
 }