cpuidle: Use nanoseconds as the unit of time

Currently, the cpuidle subsystem uses microseconds as the unit of
time which (among other things) causes the idle loop to incur some
integer division overhead for no clear benefit.

In order to allow cpuidle to measure time in nanoseconds, add two
new fields, exit_latency_ns and target_residency_ns, to represent the
exit latency and target residency of an idle state in nanoseconds,
respectively, to struct cpuidle_state and initialize them with the
help of the corresponding values in microseconds provided by drivers.
Additionally, change cpuidle_governor_latency_req() to return the
idle state exit latency constraint in nanoseconds.

Also meeasure idle state residency (last_residency_ns in struct
cpuidle_device and time_ns in struct cpuidle_driver) in nanoseconds
and update the cpuidle core and governors accordingly.

However, the menu governor still computes typical intervals in
microseconds to avoid integer overflows.

Signed-off-by: Rafael J. Wysocki <[e-mail]>
Acked-by: Peter Zijlstra (Intel) <[e-mail]>
Acked-by: Doug Smythies <[e-mail]>
Tested-by: Doug Smythies <[e-mail]>

drivers/cpuidle/cpuidle.c

···
 
 static int find_deepest_state(struct cpuidle_driver *drv,
 			      struct cpuidle_device *dev,
-			      unsigned int max_latency,
+			      u64 max_latency_ns,
 			      unsigned int forbidden_flags,
 			      bool s2idle)
 {
-	unsigned int latency_req = 0;
+	u64 latency_req = 0;
 	int i, ret = 0;
 
 	for (i = 1; i < drv->state_count; i++) {
 		struct cpuidle_state *s = &drv->states[i];
 
 		if (dev->states_usage[i].disable ||
-		    s->exit_latency <= latency_req ||
-		    s->exit_latency > max_latency ||
+		    s->exit_latency_ns <= latency_req ||
+		    s->exit_latency_ns > max_latency_ns ||
 		    (s->flags & forbidden_flags) ||
 		    (s2idle && !s->enter_s2idle))
 			continue;
 
-		latency_req = s->exit_latency;
+		latency_req = s->exit_latency_ns;
 		ret = i;
 	}
 	return ret;
···
 int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
 			       struct cpuidle_device *dev)
 {
-	return find_deepest_state(drv, dev, UINT_MAX, 0, false);
+	return find_deepest_state(drv, dev, U64_MAX, 0, false);
 }
 
 #ifdef CONFIG_SUSPEND
···
 	 * that interrupts won't be enabled when it exits and allows the tick to
 	 * be frozen safely.
 	 */
-	index = find_deepest_state(drv, dev, UINT_MAX, 0, true);
+	index = find_deepest_state(drv, dev, U64_MAX, 0, true);
 	if (index > 0)
 		enter_s2idle_proper(drv, dev, index);
 
···
 	 * CPU as a broadcast timer, this call may fail if it is not available.
 	 */
 	if (broadcast && tick_broadcast_enter()) {
-		index = find_deepest_state(drv, dev, target_state->exit_latency,
+		index = find_deepest_state(drv, dev, target_state->exit_latency_ns,
 					   CPUIDLE_FLAG_TIMER_STOP, false);
 		if (index < 0) {
 			default_idle_call();
···
 		local_irq_enable();
 
 	if (entered_state >= 0) {
-		s64 diff, delay = drv->states[entered_state].exit_latency;
+		s64 diff, delay = drv->states[entered_state].exit_latency_ns;
 		int i;
 
 		/*
···
 		 * This can be moved to within driver enter routine,
 		 * but that results in multiple copies of same code.
 		 */
-		diff = ktime_us_delta(time_end, time_start);
-		if (diff > INT_MAX)
-			diff = INT_MAX;
+		diff = ktime_sub(time_end, time_start);
 
-		dev->last_residency = (int)diff;
-		dev->states_usage[entered_state].time += dev->last_residency;
+		dev->last_residency_ns = diff;
+		dev->states_usage[entered_state].time_ns += diff;
 		dev->states_usage[entered_state].usage++;
 
-		if (diff < drv->states[entered_state].target_residency) {
+		if (diff < drv->states[entered_state].target_residency_ns) {
 			for (i = entered_state - 1; i >= 0; i--) {
 				if (dev->states_usage[i].disable)
 					continue;
···
 				 * Update if a deeper state would have been a
 				 * better match for the observed idle duration.
 				 */
-				if (diff - delay >= drv->states[i].target_residency)
+				if (diff - delay >= drv->states[i].target_residency_ns)
 					dev->states_usage[entered_state].below++;
 
 				break;
 			}
 		}
 	} else {
-		dev->last_residency = 0;
+		dev->last_residency_ns = 0;
 	}
 
 	return entered_state;
···
 		if (dev->states_usage[i].disable)
 			continue;
 
-		limit_ns = (u64)drv->states[i].target_residency * NSEC_PER_USEC;
+		limit_ns = (u64)drv->states[i].target_residency_ns;
 	}
 
 	dev->poll_limit_ns = limit_ns;
···
 static void __cpuidle_device_init(struct cpuidle_device *dev)
 {
 	memset(dev->states_usage, 0, sizeof(dev->states_usage));
-	dev->last_residency = 0;
+	dev->last_residency_ns = 0;
 	dev->next_hrtimer = 0;
 }
 

drivers/cpuidle/driver.c

···
 	if (!drv->cpumask)
 		drv->cpumask = (struct cpumask *)cpu_possible_mask;
 
-	/*
-	 * Look for the timer stop flag in the different states, so that we know
-	 * if the broadcast timer has to be set up.  The loop is in the reverse
-	 * order, because usually one of the deeper states have this flag set.
-	 */
-	for (i = drv->state_count - 1; i >= 0 ; i--) {
-		if (drv->states[i].flags & CPUIDLE_FLAG_TIMER_STOP) {
+	for (i = 0; i < drv->state_count; i++) {
+		struct cpuidle_state *s = &drv->states[i];
+
+		/*
+		 * Look for the timer stop flag in the different states and if
+		 * it is found, indicate that the broadcast timer has to be set
+		 * up.
+		 */
+		if (s->flags & CPUIDLE_FLAG_TIMER_STOP)
 			drv->bctimer = 1;
-			break;
-		}
+
+		/*
+		 * The core will use the target residency and exit latency
+		 * values in nanoseconds, but allow drivers to provide them in
+		 * microseconds too.
+		 */
+		if (s->target_residency > 0)
+			s->target_residency_ns = s->target_residency * NSEC_PER_USEC;
+
+		if (s->exit_latency > 0)
+			s->exit_latency_ns = s->exit_latency * NSEC_PER_USEC;
 	}
 }
 

drivers/cpuidle/governor.c

···
  * cpuidle_governor_latency_req - Compute a latency constraint for CPU
  * @cpu: Target CPU
  */
-int cpuidle_governor_latency_req(unsigned int cpu)
+s64 cpuidle_governor_latency_req(unsigned int cpu)
 {
 	int global_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
 	struct device *device = get_cpu_device(cpu);
 	int device_req = dev_pm_qos_raw_resume_latency(device);
 
-	return device_req < global_req ? device_req : global_req;
+	if (device_req > global_req)
+		device_req = global_req;
+
+	return (s64)device_req * NSEC_PER_USEC;
 }

drivers/cpuidle/governors/haltpoll.c

···
 			   struct cpuidle_device *dev,
 			   bool *stop_tick)
 {
-	int latency_req = cpuidle_governor_latency_req(dev->cpu);
+	s64 latency_req = cpuidle_governor_latency_req(dev->cpu);
 
 	if (!drv->state_count || latency_req == 0) {
 		*stop_tick = false;
···
 	return 0;
 }
 
-static void adjust_poll_limit(struct cpuidle_device *dev, unsigned int block_us)
+static void adjust_poll_limit(struct cpuidle_device *dev, u64 block_ns)
 {
 	unsigned int val;
-	u64 block_ns = block_us*NSEC_PER_USEC;
 
 	/* Grow cpu_halt_poll_us if
 	 * cpu_halt_poll_us < block_ns < guest_halt_poll_us
···
 	dev->last_state_idx = index;
 
 	if (index != 0)
-		adjust_poll_limit(dev, dev->last_residency);
+		adjust_poll_limit(dev, dev->last_residency_ns);
 }
 
 /**

drivers/cpuidle/governors/ladder.c

···
 	struct {
 		u32 promotion_count;
 		u32 demotion_count;
-		u32 promotion_time;
-		u32 demotion_time;
+		u64 promotion_time_ns;
+		u64 demotion_time_ns;
 	} threshold;
 	struct {
 		int promotion_count;
···
 {
 	struct ladder_device *ldev = this_cpu_ptr(&ladder_devices);
 	struct ladder_device_state *last_state;
-	int last_residency, last_idx = dev->last_state_idx;
+	int last_idx = dev->last_state_idx;
 	int first_idx = drv->states[0].flags & CPUIDLE_FLAG_POLLING ? 1 : 0;
-	int latency_req = cpuidle_governor_latency_req(dev->cpu);
+	s64 latency_req = cpuidle_governor_latency_req(dev->cpu);
+	s64 last_residency;
 
 	/* Special case when user has set very strict latency requirement */
 	if (unlikely(latency_req == 0)) {
···
 
 	last_state = &ldev->states[last_idx];
 
-	last_residency = dev->last_residency - drv->states[last_idx].exit_latency;
+	last_residency = dev->last_residency_ns - drv->states[last_idx].exit_latency_ns;
 
 	/* consider promotion */
 	if (last_idx < drv->state_count - 1 &&
 	    !dev->states_usage[last_idx + 1].disable &&
-	    last_residency > last_state->threshold.promotion_time &&
-	    drv->states[last_idx + 1].exit_latency <= latency_req) {
+	    last_residency > last_state->threshold.promotion_time_ns &&
+	    drv->states[last_idx + 1].exit_latency_ns <= latency_req) {
 		last_state->stats.promotion_count++;
 		last_state->stats.demotion_count = 0;
 		if (last_state->stats.promotion_count >= last_state->threshold.promotion_count) {
···
 	/* consider demotion */
 	if (last_idx > first_idx &&
 	    (dev->states_usage[last_idx].disable ||
-	    drv->states[last_idx].exit_latency > latency_req)) {
+	    drv->states[last_idx].exit_latency_ns > latency_req)) {
 		int i;
 
 		for (i = last_idx - 1; i > first_idx; i--) {
-			if (drv->states[i].exit_latency <= latency_req)
+			if (drv->states[i].exit_latency_ns <= latency_req)
 				break;
 		}
 		ladder_do_selection(dev, ldev, last_idx, i);
···
 	}
 
 	if (last_idx > first_idx &&
-	    last_residency < last_state->threshold.demotion_time) {
+	    last_residency < last_state->threshold.demotion_time_ns) {
 		last_state->stats.demotion_count++;
 		last_state->stats.promotion_count = 0;
 		if (last_state->stats.demotion_count >= last_state->threshold.demotion_count) {
···
 		lstate->threshold.demotion_count = DEMOTION_COUNT;
 
 		if (i < drv->state_count - 1)
-			lstate->threshold.promotion_time = state->exit_latency;
+			lstate->threshold.promotion_time_ns = state->exit_latency_ns;
 		if (i > first_idx)
-			lstate->threshold.demotion_time = state->exit_latency;
+			lstate->threshold.demotion_time_ns = state->exit_latency_ns;
 	}
 
 	return 0;

drivers/cpuidle/governors/menu.c

···
 #include <linux/sched/stat.h>
 #include <linux/math64.h>
 
-/*
- * Please note when changing the tuning values:
- * If (MAX_INTERESTING-1) * RESOLUTION > UINT_MAX, the result of
- * a scaling operation multiplication may overflow on 32 bit platforms.
- * In that case, #define RESOLUTION as ULL to get 64 bit result:
- * #define RESOLUTION 1024ULL
- *
- * The default values do not overflow.
- */
 #define BUCKETS 12
 #define INTERVAL_SHIFT 3
 #define INTERVALS (1UL << INTERVAL_SHIFT)
 #define RESOLUTION 1024
 #define DECAY 8
-#define MAX_INTERESTING 50000
-
+#define MAX_INTERESTING (50000 * NSEC_PER_USEC)
 
 /*
  * Concepts and ideas behind the menu governor
···
 	int             needs_update;
 	int             tick_wakeup;
 
-	unsigned int	next_timer_us;
+	u64		next_timer_ns;
 	unsigned int	bucket;
 	unsigned int	correction_factor[BUCKETS];
 	unsigned int	intervals[INTERVALS];
 	int		interval_ptr;
 };
 
-static inline int which_bucket(unsigned int duration, unsigned long nr_iowaiters)
+static inline int which_bucket(u64 duration_ns, unsigned long nr_iowaiters)
 {
 	int bucket = 0;
 
···
 	if (nr_iowaiters)
 		bucket = BUCKETS/2;
 
-	if (duration < 10)
+	if (duration_ns < 10ULL * NSEC_PER_USEC)
 		return bucket;
-	if (duration < 100)
+	if (duration_ns < 100ULL * NSEC_PER_USEC)
 		return bucket + 1;
-	if (duration < 1000)
+	if (duration_ns < 1000ULL * NSEC_PER_USEC)
 		return bucket + 2;
-	if (duration < 10000)
+	if (duration_ns < 10000ULL * NSEC_PER_USEC)
 		return bucket + 3;
-	if (duration < 100000)
+	if (duration_ns < 100000ULL * NSEC_PER_USEC)
 		return bucket + 4;
 	return bucket + 5;
 }
···
 		       bool *stop_tick)
 {
 	struct menu_device *data = this_cpu_ptr(&menu_devices);
-	int latency_req = cpuidle_governor_latency_req(dev->cpu);
-	int i;
-	int idx;
-	unsigned int interactivity_req;
+	s64 latency_req = cpuidle_governor_latency_req(dev->cpu);
 	unsigned int predicted_us;
+	u64 predicted_ns;
+	u64 interactivity_req;
 	unsigned long nr_iowaiters;
 	ktime_t delta_next;
+	int i, idx;
 
 	if (data->needs_update) {
 		menu_update(drv, dev);
···
 	}
 
 	/* determine the expected residency time, round up */
-	data->next_timer_us = ktime_to_us(tick_nohz_get_sleep_length(&delta_next));
+	data->next_timer_ns = tick_nohz_get_sleep_length(&delta_next);
 
 	nr_iowaiters = nr_iowait_cpu(dev->cpu);
-	data->bucket = which_bucket(data->next_timer_us, nr_iowaiters);
+	data->bucket = which_bucket(data->next_timer_ns, nr_iowaiters);
 
 	if (unlikely(drv->state_count <= 1 || latency_req == 0) ||
-	    ((data->next_timer_us < drv->states[1].target_residency ||
-	      latency_req < drv->states[1].exit_latency) &&
+	    ((data->next_timer_ns < drv->states[1].target_residency_ns ||
+	      latency_req < drv->states[1].exit_latency_ns) &&
 	     !dev->states_usage[0].disable)) {
 		/*
 		 * In this case state[0] will be used no matter what, so return
···
 		return 0;
 	}
 
-	/*
-	 * Force the result of multiplication to be 64 bits even if both
-	 * operands are 32 bits.
-	 * Make sure to round up for half microseconds.
-	 */
-	predicted_us = DIV_ROUND_CLOSEST_ULL((uint64_t)data->next_timer_us *
-					 data->correction_factor[data->bucket],
-					 RESOLUTION * DECAY);
-	/*
-	 * Use the lowest expected idle interval to pick the idle state.
-	 */
-	predicted_us = min(predicted_us, get_typical_interval(data, predicted_us));
+	/* Round up the result for half microseconds. */
+	predicted_us = div_u64(data->next_timer_ns *
+			       data->correction_factor[data->bucket] +
+			       (RESOLUTION * DECAY * NSEC_PER_USEC) / 2,
+			       RESOLUTION * DECAY * NSEC_PER_USEC);
+	/* Use the lowest expected idle interval to pick the idle state. */
+	predicted_ns = (u64)min(predicted_us,
+				get_typical_interval(data, predicted_us)) *
+				NSEC_PER_USEC;
 
 	if (tick_nohz_tick_stopped()) {
 		/*
···
 		 * the known time till the closest timer event for the idle
 		 * state selection.
 		 */
-		if (predicted_us < TICK_USEC)
-			predicted_us = ktime_to_us(delta_next);
+		if (predicted_ns < TICK_NSEC)
+			predicted_ns = delta_next;
 	} else {
 		/*
 		 * Use the performance multiplier and the user-configurable
 		 * latency_req to determine the maximum exit latency.
 		 */
-		interactivity_req = predicted_us / performance_multiplier(nr_iowaiters);
+		interactivity_req = div64_u64(predicted_ns,
+					      performance_multiplier(nr_iowaiters));
 		if (latency_req > interactivity_req)
 			latency_req = interactivity_req;
 	}
···
 		if (idx == -1)
 			idx = i; /* first enabled state */
 
-		if (s->target_residency > predicted_us) {
+		if (s->target_residency_ns > predicted_ns) {
 			/*
 			 * Use a physical idle state, not busy polling, unless
 			 * a timer is going to trigger soon enough.
 			 */
 			if ((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) &&
-			    s->exit_latency <= latency_req &&
-			    s->target_residency <= data->next_timer_us) {
-				predicted_us = s->target_residency;
+			    s->exit_latency_ns <= latency_req &&
+			    s->target_residency_ns <= data->next_timer_ns) {
+				predicted_ns = s->target_residency_ns;
 				idx = i;
 				break;
 			}
-			if (predicted_us < TICK_USEC)
+			if (predicted_ns < TICK_NSEC)
 				break;
 
 			if (!tick_nohz_tick_stopped()) {
···
 				 * tick in that case and let the governor run
 				 * again in the next iteration of the loop.
 				 */
-				predicted_us = drv->states[idx].target_residency;
+				predicted_ns = drv->states[idx].target_residency_ns;
 				break;
 			}
 
···
 			 * closest timer event, select this one to avoid getting
 			 * stuck in the shallow one for too long.
 			 */
-			if (drv->states[idx].target_residency < TICK_USEC &&
-			    s->target_residency <= ktime_to_us(delta_next))
+			if (drv->states[idx].target_residency_ns < TICK_NSEC &&
+			    s->target_residency_ns <= delta_next)
 				idx = i;
 
 			return idx;
 		}
-		if (s->exit_latency > latency_req)
+		if (s->exit_latency_ns > latency_req)
 			break;
 
 		idx = i;
···
 	 * expected idle duration is shorter than the tick period length.
 	 */
 	if (((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) ||
-	     predicted_us < TICK_USEC) && !tick_nohz_tick_stopped()) {
-		unsigned int delta_next_us = ktime_to_us(delta_next);
-
+	     predicted_ns < TICK_NSEC) && !tick_nohz_tick_stopped()) {
 		*stop_tick = false;
 
-		if (idx > 0 && drv->states[idx].target_residency > delta_next_us) {
+		if (idx > 0 && drv->states[idx].target_residency_ns > delta_next) {
 			/*
 			 * The tick is not going to be stopped and the target
 			 * residency of the state to be returned is not within
···
 					continue;
 
 				idx = i;
-				if (drv->states[i].target_residency <= delta_next_us)
+				if (drv->states[i].target_residency_ns <= delta_next)
 					break;
 			}
 		}
···
 	struct menu_device *data = this_cpu_ptr(&menu_devices);
 	int last_idx = dev->last_state_idx;
 	struct cpuidle_state *target = &drv->states[last_idx];
-	unsigned int measured_us;
+	u64 measured_ns;
 	unsigned int new_factor;
 
 	/*
···
 	 * assume the state was never reached and the exit latency is 0.
 	 */
 
-	if (data->tick_wakeup && data->next_timer_us > TICK_USEC) {
+	if (data->tick_wakeup && data->next_timer_ns > TICK_NSEC) {
 		/*
 		 * The nohz code said that there wouldn't be any events within
 		 * the tick boundary (if the tick was stopped), but the idle
···
 		 * have been idle long (but not forever) to help the idle
 		 * duration predictor do a better job next time.
 		 */
-		measured_us = 9 * MAX_INTERESTING / 10;
+		measured_ns = 9 * MAX_INTERESTING / 10;
 	} else if ((drv->states[last_idx].flags & CPUIDLE_FLAG_POLLING) &&
 		   dev->poll_time_limit) {
 		/*
···
 		 * the CPU might have been woken up from idle by the next timer.
 		 * Assume that to be the case.
 		 */
-		measured_us = data->next_timer_us;
+		measured_ns = data->next_timer_ns;
 	} else {
 		/* measured value */
-		measured_us = dev->last_residency;
+		measured_ns = dev->last_residency_ns;
 
 		/* Deduct exit latency */
-		if (measured_us > 2 * target->exit_latency)
-			measured_us -= target->exit_latency;
+		if (measured_ns > 2 * target->exit_latency_ns)
+			measured_ns -= target->exit_latency_ns;
 		else
-			measured_us /= 2;
+			measured_ns /= 2;
 	}
 
 	/* Make sure our coefficients do not exceed unity */
-	if (measured_us > data->next_timer_us)
-		measured_us = data->next_timer_us;
+	if (measured_ns > data->next_timer_ns)
+		measured_ns = data->next_timer_ns;
 
 	/* Update our correction ratio */
 	new_factor = data->correction_factor[data->bucket];
 	new_factor -= new_factor / DECAY;
 
-	if (data->next_timer_us > 0 && measured_us < MAX_INTERESTING)
-		new_factor += RESOLUTION * measured_us / data->next_timer_us;
+	if (data->next_timer_ns > 0 && measured_ns < MAX_INTERESTING)
+		new_factor += div64_u64(RESOLUTION * measured_ns,
+					data->next_timer_ns);
 	else
 		/*
 		 * we were idle so long that we count it as a perfect
···
 	data->correction_factor[data->bucket] = new_factor;
 
 	/* update the repeating-pattern data */
-	data->intervals[data->interval_ptr++] = measured_us;
+	data->intervals[data->interval_ptr++] = ktime_to_us(measured_ns);
 	if (data->interval_ptr >= INTERVALS)
 		data->interval_ptr = 0;
 }

drivers/cpuidle/governors/teo.c

···
 	u64 sleep_length_ns;
 	struct teo_idle_state states[CPUIDLE_STATE_MAX];
 	int interval_idx;
-	unsigned int intervals[INTERVALS];
+	u64 intervals[INTERVALS];
 };
 
 static DEFINE_PER_CPU(struct teo_cpu, teo_cpus);
···
 static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
 	struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu);
-	unsigned int sleep_length_us = ktime_to_us(cpu_data->sleep_length_ns);
 	int i, idx_hit = -1, idx_timer = -1;
-	unsigned int measured_us;
+	u64 measured_ns;
 
 	if (cpu_data->time_span_ns >= cpu_data->sleep_length_ns) {
 		/*
···
 		 * enough to the closest timer event expected at the idle state
 		 * selection time to be discarded.
 		 */
-		measured_us = UINT_MAX;
+		measured_ns = U64_MAX;
 	} else {
-		unsigned int lat;
+		u64 lat_ns = drv->states[dev->last_state_idx].exit_latency_ns;
 
-		lat = drv->states[dev->last_state_idx].exit_latency;
-
-		measured_us = ktime_to_us(cpu_data->time_span_ns);
+		measured_ns = cpu_data->time_span_ns;
 		/*
 		 * The delay between the wakeup and the first instruction
 		 * executed by the CPU is not likely to be worst-case every
 		 * time, so take 1/2 of the exit latency as a very rough
 		 * approximation of the average of it.
 		 */
-		if (measured_us >= lat)
-			measured_us -= lat / 2;
+		if (measured_ns >= lat_ns)
+			measured_ns -= lat_ns / 2;
 		else
-			measured_us /= 2;
+			measured_ns /= 2;
 	}
 
 	/*
···
 
 		cpu_data->states[i].early_hits -= early_hits >> DECAY_SHIFT;
 
-		if (drv->states[i].target_residency <= sleep_length_us) {
+		if (drv->states[i].target_residency_ns <= cpu_data->sleep_length_ns) {
 			idx_timer = i;
-			if (drv->states[i].target_residency <= measured_us)
+			if (drv->states[i].target_residency_ns <= measured_ns)
 				idx_hit = i;
 		}
 	}
···
 	 * Save idle duration values corresponding to non-timer wakeups for
 	 * pattern detection.
 	 */
-	cpu_data->intervals[cpu_data->interval_idx++] = measured_us;
+	cpu_data->intervals[cpu_data->interval_idx++] = measured_ns;
 	if (cpu_data->interval_idx > INTERVALS)
 		cpu_data->interval_idx = 0;
 }
···
  * @drv: cpuidle driver containing state data.
  * @dev: Target CPU.
  * @state_idx: Index of the capping idle state.
- * @duration_us: Idle duration value to match.
+ * @duration_ns: Idle duration value to match.
  */
 static int teo_find_shallower_state(struct cpuidle_driver *drv,
 				    struct cpuidle_device *dev, int state_idx,
-				    unsigned int duration_us)
+				    u64 duration_ns)
 {
 	int i;
 
···
 			continue;
 
 		state_idx = i;
-		if (drv->states[i].target_residency <= duration_us)
+		if (drv->states[i].target_residency_ns <= duration_ns)
 			break;
 	}
 	return state_idx;
···
 		      bool *stop_tick)
 {
 	struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu);
-	int latency_req = cpuidle_governor_latency_req(dev->cpu);
-	unsigned int duration_us, hits, misses, early_hits;
+	s64 latency_req = cpuidle_governor_latency_req(dev->cpu);
+	u64 duration_ns;
+	unsigned int hits, misses, early_hits;
 	int max_early_idx, constraint_idx, idx, i;
 	ktime_t delta_tick;
 
···
 
 	cpu_data->time_span_ns = local_clock();
 
-	cpu_data->sleep_length_ns = tick_nohz_get_sleep_length(&delta_tick);
-	duration_us = ktime_to_us(cpu_data->sleep_length_ns);
+	duration_ns = tick_nohz_get_sleep_length(&delta_tick);
+	cpu_data->sleep_length_ns = duration_ns;
 
 	hits = 0;
 	misses = 0;
···
 			 * Ignore disabled states with target residencies beyond
 			 * the anticipated idle duration.
 			 */
-			if (s->target_residency > duration_us)
+			if (s->target_residency_ns > duration_ns)
 				continue;
 
 			/*
···
 			 * shallow for that role.
 			 */
 			if (!(tick_nohz_tick_stopped() &&
-			      drv->states[idx].target_residency < TICK_USEC)) {
+			      drv->states[idx].target_residency_ns < TICK_NSEC)) {
 				early_hits = cpu_data->states[i].early_hits;
 				max_early_idx = idx;
 			}
···
 			misses = cpu_data->states[i].misses;
 		}
 
-		if (s->target_residency > duration_us)
+		if (s->target_residency_ns > duration_ns)
 			break;
 
-		if (s->exit_latency > latency_req && constraint_idx > i)
+		if (s->exit_latency_ns > latency_req && constraint_idx > i)
 			constraint_idx = i;
 
 		idx = i;
···
 
 		if (early_hits < cpu_data->states[i].early_hits &&
 		    !(tick_nohz_tick_stopped() &&
-		      drv->states[i].target_residency < TICK_USEC)) {
+		      drv->states[i].target_residency_ns < TICK_NSEC)) {
 			early_hits = cpu_data->states[i].early_hits;
 			max_early_idx = i;
 		}
···
 	 */
 	if (hits <= misses && max_early_idx >= 0) {
 		idx = max_early_idx;
-		duration_us = drv->states[idx].target_residency;
+		duration_ns = drv->states[idx].target_residency_ns;
 	}
 
 	/*
···
 		 * the current expected idle duration value.
 		 */
 		for (i = 0; i < INTERVALS; i++) {
-			unsigned int val = cpu_data->intervals[i];
+			u64 val = cpu_data->intervals[i];
 
-			if (val >= duration_us)
+			if (val >= duration_ns)
 				continue;
 
 			count++;
···
 		 * values are in the interesting range.
 		 */
 		if (count > INTERVALS / 2) {
-			unsigned int avg_us = div64_u64(sum, count);
+			u64 avg_ns = div64_u64(sum, count);
 
 			/*
 			 * Avoid spending too much time in an idle state that
 			 * would be too shallow.
 			 */
-			if (!(tick_nohz_tick_stopped() && avg_us < TICK_USEC)) {
-				duration_us = avg_us;
-				if (drv->states[idx].target_residency > avg_us)
+			if (!(tick_nohz_tick_stopped() && avg_ns < TICK_NSEC)) {
+				duration_ns = avg_ns;
+				if (drv->states[idx].target_residency_ns > avg_ns)
 					idx = teo_find_shallower_state(drv, dev,
-								       idx, avg_us);
+								       idx, avg_ns);
 			}
 		}
 	}
···
 	 * expected idle duration is shorter than the tick period length.
 	 */
 	if (((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) ||
-	    duration_us < TICK_USEC) && !tick_nohz_tick_stopped()) {
-		unsigned int delta_tick_us = ktime_to_us(delta_tick);
-
+	    duration_ns < TICK_NSEC) && !tick_nohz_tick_stopped()) {
 		*stop_tick = false;
 
 		/*
···
 		 * till the closest timer including the tick, try to correct
 		 * that.
 		 */
-		if (idx > 0 && drv->states[idx].target_residency > delta_tick_us)
-			idx = teo_find_shallower_state(drv, dev, idx, delta_tick_us);
+		if (idx > 0 && drv->states[idx].target_residency_ns > delta_tick)
+			idx = teo_find_shallower_state(drv, dev, idx, delta_tick);
 	}
 
 	return idx;
···
 	memset(cpu_data, 0, sizeof(*cpu_data));
 
 	for (i = 0; i < INTERVALS; i++)
-		cpu_data->intervals[i] = UINT_MAX;
+		cpu_data->intervals[i] = U64_MAX;
 
 	return 0;
 }

drivers/cpuidle/poll_state.c

···
 	snprintf(state->desc, CPUIDLE_DESC_LEN, "CPUIDLE CORE POLL IDLE");
 	state->exit_latency = 0;
 	state->target_residency = 0;
+	state->exit_latency_ns = 0;
+	state->target_residency_ns = 0;
 	state->power_usage = -1;
 	state->enter = poll_idle;
 	state->disabled = false;

drivers/cpuidle/sysfs.c

···
 	return sprintf(buf, "%s\n", state->_name);\
 }
 
-define_show_state_function(exit_latency)
-define_show_state_function(target_residency)
+#define define_show_state_time_function(_name) \
+static ssize_t show_state_##_name(struct cpuidle_state *state, \
+				  struct cpuidle_state_usage *state_usage, \
+				  char *buf) \
+{ \
+	return sprintf(buf, "%llu\n", ktime_to_us(state->_name##_ns)); \
+}
+
+define_show_state_time_function(exit_latency)
+define_show_state_time_function(target_residency)
 define_show_state_function(power_usage)
 define_show_state_ull_function(usage)
-define_show_state_ull_function(time)
 define_show_state_str_function(name)
 define_show_state_str_function(desc)
 define_show_state_ull_function(above)
 define_show_state_ull_function(below)
+
+static ssize_t show_state_time(struct cpuidle_state *state,
+			       struct cpuidle_state_usage *state_usage,
+			       char *buf)
+{
+	return sprintf(buf, "%llu\n", ktime_to_us(state_usage->time_ns));
+}
 
 static ssize_t show_state_disable(struct cpuidle_state *state,
 				  struct cpuidle_state_usage *state_usage,

include/linux/cpuidle.h

···
 struct cpuidle_state_usage {
 	unsigned long long	disable;
 	unsigned long long	usage;
-	unsigned long long	time; /* in US */
+	u64			time_ns;
 	unsigned long long	above; /* Number of times it's been too deep */
 	unsigned long long	below; /* Number of times it's been too shallow */
 #ifdef CONFIG_SUSPEND
···
 	char		name[CPUIDLE_NAME_LEN];
 	char		desc[CPUIDLE_DESC_LEN];
 
+	u64		exit_latency_ns;
+	u64		target_residency_ns;
 	unsigned int	flags;
 	unsigned int	exit_latency; /* in US */
 	int		power_usage; /* in mW */
···
 	ktime_t			next_hrtimer;
 
 	int			last_state_idx;
-	int			last_residency;
+	u64			last_residency_ns;
 	u64			poll_limit_ns;
 	struct cpuidle_state_usage	states_usage[CPUIDLE_STATE_MAX];
 	struct cpuidle_state_kobj *kobjs[CPUIDLE_STATE_MAX];
···
 
 #ifdef CONFIG_CPU_IDLE
 extern int cpuidle_register_governor(struct cpuidle_governor *gov);
-extern int cpuidle_governor_latency_req(unsigned int cpu);
+extern s64 cpuidle_governor_latency_req(unsigned int cpu);
 #else
 static inline int cpuidle_register_governor(struct cpuidle_governor *gov)
 {return 0;}

kernel/sched/idle.c

···
 	 * update no idle residency and return.
 	 */
 	if (current_clr_polling_and_test()) {
-		dev->last_residency = 0;
+		dev->last_residency_ns = 0;
 		local_irq_enable();
 		return -EBUSY;
 	}