Merge branch 'pm-cpuidle'

* pm-cpuidle:
  cpuidle: Pass exit latency limit to cpuidle_use_deepest_state()
  cpuidle: Allow idle injection to apply exit latency limit
  cpuidle: Introduce cpuidle_driver_state_disabled() for driver quirks
  cpuidle: teo: Avoid code duplication in conditionals
  cpuidle: teo: Avoid using "early hits" incorrectly
  cpuidle: teo: Exclude cpuidle overhead from computations
  cpuidle: Use nanoseconds as the unit of time
  cpuidle: Consolidate disabled state checks
  ACPI: processor_idle: Skip dummy wait if kernel is in guest
  cpuidle: Do not unset the driver if it is there already
  cpuidle: teo: Fix "early hits" handling for disabled idle states
  cpuidle: teo: Consider hits and misses metrics of disabled states
  cpuidle: teo: Rename local variable in teo_select()
  cpuidle: teo: Ignore disabled idle states that are too deep

11 files changed, 358 insertions, 243 deletions

diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index ed56c6d20b08..2ae95df2e74f 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -642,6 +642,19 @@ static int acpi_idle_bm_check(void)
 	return bm_status;
 }
 
+static void wait_for_freeze(void)
+{
+#ifdef	CONFIG_X86
+	/* No delay is needed if we are in guest */
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		return;
+#endif
+	/* Dummy wait op - must do something useless after P_LVL2 read
+	   because chipsets cannot guarantee that STPCLK# signal
+	   gets asserted in time to freeze execution properly. */
+	inl(acpi_gbl_FADT.xpm_timer_block.address);
+}
+
 /**
  * acpi_idle_do_entry - enter idle state using the appropriate method
  * @cx: cstate data
@@ -658,10 +671,7 @@ static void __cpuidle acpi_idle_do_entry(struct acpi_processor_cx *cx)
 	} else {
 		/* IO port based C-state */
 		inb(cx->address);
-		/* Dummy wait op - must do something useless after P_LVL2 read
-		   because chipsets cannot guarantee that STPCLK# signal
-		   gets asserted in time to freeze execution properly. */
-		inl(acpi_gbl_FADT.xpm_timer_block.address);
+		wait_for_freeze();
 	}
 }
 
@@ -682,8 +692,7 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index)
 			safe_halt();
 		else if (cx->entry_method == ACPI_CSTATE_SYSTEMIO) {
 			inb(cx->address);
-			/* See comment in acpi_idle_do_entry() */
-			inl(acpi_gbl_FADT.xpm_timer_block.address);
+			wait_for_freeze();
 		} else
 			return -ENODEV;
 	}
diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index 84b1ebe212b3..1b299e801f74 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -56,13 +56,10 @@ static u64 get_snooze_timeout(struct cpuidle_device *dev,
 		return default_snooze_timeout;
 
 	for (i = index + 1; i < drv->state_count; i++) {
-		struct cpuidle_state *s = &drv->states[i];
-		struct cpuidle_state_usage *su = &dev->states_usage[i];
-
-		if (s->disabled || su->disable)
+		if (dev->states_usage[i].disable)
 			continue;
 
-		return s->target_residency * tb_ticks_per_usec;
+		return drv->states[i].target_residency * tb_ticks_per_usec;
 	}
 
 	return default_snooze_timeout;
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 0895b988fa92..569dbac443bd 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -75,44 +75,45 @@ int cpuidle_play_dead(void)
 
 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];
-		struct cpuidle_state_usage *su = &dev->states_usage[i];
 
-		if (s->disabled || su->disable || s->exit_latency <= latency_req
-		    || s->exit_latency > max_latency
-		    || (s->flags & forbidden_flags)
-		    || (s2idle && !s->enter_s2idle))
+		if (dev->states_usage[i].disable ||
+		    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;
 }
 
 /**
- * cpuidle_use_deepest_state - Set/clear governor override flag.
- * @enable: New value of the flag.
+ * cpuidle_use_deepest_state - Set/unset governor override mode.
+ * @latency_limit_ns: Idle state exit latency limit (or no override if 0).
  *
- * Set/unset the current CPU to use the deepest idle state (override governors
- * going forward if set).
+ * If @latency_limit_ns is nonzero, set the current CPU to use the deepest idle
+ * state with exit latency within @latency_limit_ns (override governors going
+ * forward), or do not override governors if it is zero.
  */
-void cpuidle_use_deepest_state(bool enable)
+void cpuidle_use_deepest_state(u64 latency_limit_ns)
 {
 	struct cpuidle_device *dev;
 
 	preempt_disable();
 	dev = cpuidle_get_device();
 	if (dev)
-		dev->use_deepest_state = enable;
+		dev->forced_idle_latency_limit_ns = latency_limit_ns;
 	preempt_enable();
 }
 
@@ -122,9 +123,10 @@ void cpuidle_use_deepest_state(bool enable)
  * @dev: cpuidle device for the given CPU.
  */
 int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
-			       struct cpuidle_device *dev)
+			       struct cpuidle_device *dev,
+			       u64 latency_limit_ns)
 {
-	return find_deepest_state(drv, dev, UINT_MAX, 0, false);
+	return find_deepest_state(drv, dev, latency_limit_ns, 0, false);
 }
 
 #ifdef CONFIG_SUSPEND
@@ -180,7 +182,7 @@ int cpuidle_enter_s2idle(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	 * 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);
 
@@ -209,7 +211,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	 * 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();
@@ -247,7 +249,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 		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;
 
 		/*
@@ -255,18 +257,15 @@ 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.
 		 */
-		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 (drv->states[i].disabled ||
-				    dev->states_usage[i].disable)
+				if (dev->states_usage[i].disable)
 					continue;
 
 				/* Shallower states are enabled, so update. */
@@ -275,22 +274,21 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 			}
 		} else if (diff > delay) {
 			for (i = entered_state + 1; i < drv->state_count; i++) {
-				if (drv->states[i].disabled ||
-				    dev->states_usage[i].disable)
+				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;
@@ -380,10 +378,10 @@ u64 cpuidle_poll_time(struct cpuidle_driver *drv,
 
 	limit_ns = TICK_NSEC;
 	for (i = 1; i < drv->state_count; i++) {
-		if (drv->states[i].disabled || dev->states_usage[i].disable)
+		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;
@@ -554,7 +552,7 @@ static void __cpuidle_unregister_device(struct cpuidle_device *dev)
 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;
 }
 
@@ -567,12 +565,16 @@ static void __cpuidle_device_init(struct cpuidle_device *dev)
  */
 static int __cpuidle_register_device(struct cpuidle_device *dev)
 {
-	int ret;
 	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
+	int i, ret;
 
 	if (!try_module_get(drv->owner))
 		return -EINVAL;
 
+	for (i = 0; i < drv->state_count; i++)
+		if (drv->states[i].disabled)
+			dev->states_usage[i].disable |= CPUIDLE_STATE_DISABLED_BY_DRIVER;
+
 	per_cpu(cpuidle_devices, dev->cpu) = dev;
 	list_add(&dev->device_list, &cpuidle_detected_devices);
 
diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c
index 80c1a830d991..c76423aaef4d 100644
--- a/drivers/cpuidle/driver.c
+++ b/drivers/cpuidle/driver.c
@@ -62,24 +62,23 @@ static inline void __cpuidle_unset_driver(struct cpuidle_driver *drv)
  * __cpuidle_set_driver - set per CPU driver variables for the given driver.
  * @drv: a valid pointer to a struct cpuidle_driver
  *
- * For each CPU in the driver's cpumask, unset the registered driver per CPU
- * to @drv.
- *
- * Returns 0 on success, -EBUSY if the CPUs have driver(s) already.
+ * Returns 0 on success, -EBUSY if any CPU in the cpumask have a driver
+ * different from drv already.
  */
 static inline int __cpuidle_set_driver(struct cpuidle_driver *drv)
 {
 	int cpu;
 
 	for_each_cpu(cpu, drv->cpumask) {
+		struct cpuidle_driver *old_drv;
 
-		if (__cpuidle_get_cpu_driver(cpu)) {
-			__cpuidle_unset_driver(drv);
+		old_drv = __cpuidle_get_cpu_driver(cpu);
+		if (old_drv && old_drv != drv)
 			return -EBUSY;
-		}
+	}
 
+	for_each_cpu(cpu, drv->cpumask)
 		per_cpu(cpuidle_drivers, cpu) = drv;
-	}
 
 	return 0;
 }
@@ -166,16 +165,27 @@ static void __cpuidle_driver_init(struct cpuidle_driver *drv)
 	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;
 	}
 }
 
@@ -379,3 +389,31 @@ void cpuidle_driver_unref(void)
 
 	spin_unlock(&cpuidle_driver_lock);
 }
+
+/**
+ * cpuidle_driver_state_disabled - Disable or enable an idle state
+ * @drv: cpuidle driver owning the state
+ * @idx: State index
+ * @disable: Whether or not to disable the state
+ */
+void cpuidle_driver_state_disabled(struct cpuidle_driver *drv, int idx,
+				 bool disable)
+{
+	unsigned int cpu;
+
+	mutex_lock(&cpuidle_lock);
+
+	for_each_cpu(cpu, drv->cpumask) {
+		struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu);
+
+		if (!dev)
+			continue;
+
+		if (disable)
+			dev->states_usage[idx].disable |= CPUIDLE_STATE_DISABLED_BY_DRIVER;
+		else
+			dev->states_usage[idx].disable &= ~CPUIDLE_STATE_DISABLED_BY_DRIVER;
+	}
+
+	mutex_unlock(&cpuidle_lock);
+}
diff --git a/drivers/cpuidle/governor.c b/drivers/cpuidle/governor.c
index e9801f26c732..e48271e117a3 100644
--- a/drivers/cpuidle/governor.c
+++ b/drivers/cpuidle/governor.c
@@ -107,11 +107,14 @@ int cpuidle_register_governor(struct cpuidle_governor *gov)
  * 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;
 }
diff --git a/drivers/cpuidle/governors/haltpoll.c b/drivers/cpuidle/governors/haltpoll.c
index 7a703d2e0064..cb2a96eafc02 100644
--- a/drivers/cpuidle/governors/haltpoll.c
+++ b/drivers/cpuidle/governors/haltpoll.c
@@ -49,7 +49,7 @@ static int haltpoll_select(struct cpuidle_driver *drv,
 			   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;
@@ -75,10 +75,9 @@ static int haltpoll_select(struct cpuidle_driver *drv,
 	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
@@ -115,7 +114,7 @@ static void haltpoll_reflect(struct cpuidle_device *dev, int index)
 	dev->last_state_idx = index;
 
 	if (index != 0)
-		adjust_poll_limit(dev, dev->last_residency);
+		adjust_poll_limit(dev, dev->last_residency_ns);
 }
 
 /**
diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c
index 428eeb832fe7..8e9058c4ea63 100644
--- a/drivers/cpuidle/governors/ladder.c
+++ b/drivers/cpuidle/governors/ladder.c
@@ -27,8 +27,8 @@ struct ladder_device_state {
 	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;
@@ -68,9 +68,10 @@ static int ladder_select_state(struct cpuidle_driver *drv,
 {
 	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)) {
@@ -80,14 +81,13 @@ static int ladder_select_state(struct cpuidle_driver *drv,
 
 	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 &&
-	    !drv->states[last_idx + 1].disabled &&
 	    !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) {
@@ -98,13 +98,12 @@ static int ladder_select_state(struct cpuidle_driver *drv,
 
 	/* consider demotion */
 	if (last_idx > first_idx &&
-	    (drv->states[last_idx].disabled ||
-	    dev->states_usage[last_idx].disable ||
-	    drv->states[last_idx].exit_latency > latency_req)) {
+	    (dev->states_usage[last_idx].disable ||
+	    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);
@@ -112,7 +111,7 @@ static int ladder_select_state(struct cpuidle_driver *drv,
 	}
 
 	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) {
@@ -152,9 +151,9 @@ static int ladder_enable_device(struct cpuidle_driver *drv,
 		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;
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index e5a5d0c8d66b..b0a7ad566081 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -19,22 +19,12 @@
 #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
@@ -120,14 +110,14 @@ struct menu_device {
 	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;
 
@@ -140,15 +130,15 @@ static inline int which_bucket(unsigned int duration, unsigned long nr_iowaiters
 	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;
 }
@@ -276,13 +266,13 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		       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);
@@ -290,15 +280,15 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *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) &&
-	     !drv->states[0].disabled && !dev->states_usage[0].disable)) {
+	    ((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
 		 * it right away and keep the tick running if state[0] is a
@@ -308,18 +298,15 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		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()) {
 		/*
@@ -330,14 +317,15 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		 * 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;
 	}
@@ -349,27 +337,26 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	idx = -1;
 	for (i = 0; i < drv->state_count; i++) {
 		struct cpuidle_state *s = &drv->states[i];
-		struct cpuidle_state_usage *su = &dev->states_usage[i];
 
-		if (s->disabled || su->disable)
+		if (dev->states_usage[i].disable)
 			continue;
 
 		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()) {
@@ -379,7 +366,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 				 * 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;
 			}
 
@@ -389,13 +376,13 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 			 * 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;
@@ -409,12 +396,10 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	 * 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
@@ -422,12 +407,11 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 			 * tick, so try to correct that.
 			 */
 			for (i = idx - 1; i >= 0; i--) {
-				if (drv->states[i].disabled ||
-				    dev->states_usage[i].disable)
+				if (dev->states_usage[i].disable)
 					continue;
 
 				idx = i;
-				if (drv->states[i].target_residency <= delta_next_us)
+				if (drv->states[i].target_residency_ns <= delta_next)
 					break;
 			}
 		}
@@ -463,7 +447,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	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;
 
 	/*
@@ -481,7 +465,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	 * 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
@@ -491,7 +475,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		 * 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) {
 		/*
@@ -501,28 +485,29 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		 * 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
@@ -542,7 +527,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	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;
 }
diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c
index b5a0e498f798..de7e706efd46 100644
--- a/drivers/cpuidle/governors/teo.c
+++ b/drivers/cpuidle/governors/teo.c
@@ -104,7 +104,7 @@ struct teo_cpu {
 	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);
@@ -117,9 +117,8 @@ 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) {
 		/*
@@ -127,23 +126,28 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		 * 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);
+		/*
+		 * The computations below are to determine whether or not the
+		 * (saved) time till the next timer event and the measured idle
+		 * duration fall into the same "bin", so use last_residency_ns
+		 * for that instead of time_span_ns which includes the cpuidle
+		 * overhead.
+		 */
+		measured_ns = dev->last_residency_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;
 	}
 
 	/*
@@ -155,9 +159,9 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 
 		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;
 		}
 	}
@@ -193,30 +197,35 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	 * 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;
 }
 
+static bool teo_time_ok(u64 interval_ns)
+{
+	return !tick_nohz_tick_stopped() || interval_ns >= TICK_NSEC;
+}
+
 /**
  * teo_find_shallower_state - Find shallower idle state matching given duration.
  * @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;
 
 	for (i = state_idx - 1; i >= 0; i--) {
-		if (drv->states[i].disabled || dev->states_usage[i].disable)
+		if (dev->states_usage[i].disable)
 			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;
@@ -232,9 +241,10 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		      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, count;
-	int max_early_idx, constraint_idx, idx, i;
+	s64 latency_req = cpuidle_governor_latency_req(dev->cpu);
+	u64 duration_ns;
+	unsigned int hits, misses, early_hits;
+	int max_early_idx, prev_max_early_idx, constraint_idx, idx, i;
 	ktime_t delta_tick;
 
 	if (dev->last_state_idx >= 0) {
@@ -244,50 +254,92 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 
 	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;
 
-	count = 0;
+	hits = 0;
+	misses = 0;
+	early_hits = 0;
 	max_early_idx = -1;
+	prev_max_early_idx = -1;
 	constraint_idx = drv->state_count;
 	idx = -1;
 
 	for (i = 0; i < drv->state_count; i++) {
 		struct cpuidle_state *s = &drv->states[i];
-		struct cpuidle_state_usage *su = &dev->states_usage[i];
 
-		if (s->disabled || su->disable) {
+		if (dev->states_usage[i].disable) {
+			/*
+			 * Ignore disabled states with target residencies beyond
+			 * the anticipated idle duration.
+			 */
+			if (s->target_residency_ns > duration_ns)
+				continue;
+
+			/*
+			 * This state is disabled, so the range of idle duration
+			 * values corresponding to it is covered by the current
+			 * candidate state, but still the "hits" and "misses"
+			 * metrics of the disabled state need to be used to
+			 * decide whether or not the state covering the range in
+			 * question is good enough.
+			 */
+			hits = cpu_data->states[i].hits;
+			misses = cpu_data->states[i].misses;
+
+			if (early_hits >= cpu_data->states[i].early_hits ||
+			    idx < 0)
+				continue;
+
 			/*
-			 * If the "early hits" metric of a disabled state is
-			 * greater than the current maximum, it should be taken
-			 * into account, because it would be a mistake to select
-			 * a deeper state with lower "early hits" metric.  The
-			 * index cannot be changed to point to it, however, so
-			 * just increase the max count alone and let the index
-			 * still point to a shallower idle state.
+			 * If the current candidate state has been the one with
+			 * the maximum "early hits" metric so far, the "early
+			 * hits" metric of the disabled state replaces the
+			 * current "early hits" count to avoid selecting a
+			 * deeper state with lower "early hits" metric.
 			 */
-			if (max_early_idx >= 0 &&
-			    count < cpu_data->states[i].early_hits)
-				count = cpu_data->states[i].early_hits;
+			if (max_early_idx == idx) {
+				early_hits = cpu_data->states[i].early_hits;
+				continue;
+			}
+
+			/*
+			 * The current candidate state is closer to the disabled
+			 * one than the current maximum "early hits" state, so
+			 * replace the latter with it, but in case the maximum
+			 * "early hits" state index has not been set so far,
+			 * check if the current candidate state is not too
+			 * shallow for that role.
+			 */
+			if (teo_time_ok(drv->states[idx].target_residency_ns)) {
+				prev_max_early_idx = max_early_idx;
+				early_hits = cpu_data->states[i].early_hits;
+				max_early_idx = idx;
+			}
 
 			continue;
 		}
 
-		if (idx < 0)
+		if (idx < 0) {
 			idx = i; /* first enabled state */
+			hits = cpu_data->states[i].hits;
+			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;
+		hits = cpu_data->states[i].hits;
+		misses = cpu_data->states[i].misses;
 
-		if (count < cpu_data->states[i].early_hits &&
-		    !(tick_nohz_tick_stopped() &&
-		      drv->states[i].target_residency < TICK_USEC)) {
-			count = cpu_data->states[i].early_hits;
+		if (early_hits < cpu_data->states[i].early_hits &&
+		    teo_time_ok(drv->states[i].target_residency_ns)) {
+			prev_max_early_idx = max_early_idx;
+			early_hits = cpu_data->states[i].early_hits;
 			max_early_idx = i;
 		}
 	}
@@ -300,10 +352,19 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	 * "early hits" metric, but if that cannot be determined, just use the
 	 * state selected so far.
 	 */
-	if (cpu_data->states[idx].hits <= cpu_data->states[idx].misses &&
-	    max_early_idx >= 0) {
-		idx = max_early_idx;
-		duration_us = drv->states[idx].target_residency;
+	if (hits <= misses) {
+		/*
+		 * The current candidate state is not suitable, so take the one
+		 * whose "early hits" metric is the maximum for the range of
+		 * shallower states.
+		 */
+		if (idx == max_early_idx)
+			max_early_idx = prev_max_early_idx;
+
+		if (max_early_idx >= 0) {
+			idx = max_early_idx;
+			duration_ns = drv->states[idx].target_residency_ns;
+		}
 	}
 
 	/*
@@ -316,18 +377,17 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	if (idx < 0) {
 		idx = 0; /* No states enabled. Must use 0. */
 	} else if (idx > 0) {
+		unsigned int count = 0;
 		u64 sum = 0;
 
-		count = 0;
-
 		/*
 		 * Count and sum the most recent idle duration values less than
 		 * 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++;
@@ -339,17 +399,17 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		 * 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 (teo_time_ok(avg_ns)) {
+				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);
 			}
 		}
 	}
@@ -359,9 +419,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	 * 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;
 
 		/*
@@ -370,8 +428,8 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		 * 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;
@@ -415,7 +473,7 @@ static int teo_enable_device(struct cpuidle_driver *drv,
 	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;
 }
diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c
index c8fa5f41dfc4..9f1ace9c53da 100644
--- a/drivers/cpuidle/poll_state.c
+++ b/drivers/cpuidle/poll_state.c
@@ -49,6 +49,8 @@ void cpuidle_poll_state_init(struct cpuidle_driver *drv)
 	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;
diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c
index 2bb2683b493c..38ef770be90d 100644
--- a/drivers/cpuidle/sysfs.c
+++ b/drivers/cpuidle/sysfs.c
@@ -255,25 +255,6 @@ static ssize_t show_state_##_name(struct cpuidle_state *state, \
 	return sprintf(buf, "%u\n", state->_name);\
 }
 
-#define define_store_state_ull_function(_name) \
-static ssize_t store_state_##_name(struct cpuidle_state *state, \
-				   struct cpuidle_state_usage *state_usage, \
-				   const char *buf, size_t size)	\
-{ \
-	unsigned long long value; \
-	int err; \
-	if (!capable(CAP_SYS_ADMIN)) \
-		return -EPERM; \
-	err = kstrtoull(buf, 0, &value); \
-	if (err) \
-		return err; \
-	if (value) \
-		state_usage->_name = 1; \
-	else \
-		state_usage->_name = 0; \
-	return size; \
-}
-
 #define define_show_state_ull_function(_name) \
 static ssize_t show_state_##_name(struct cpuidle_state *state, \
 				  struct cpuidle_state_usage *state_usage, \
@@ -292,18 +273,60 @@ static ssize_t show_state_##_name(struct cpuidle_state *state, \
 	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(disable)
-define_store_state_ull_function(disable)
 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,
+				  char *buf)
+{
+	return sprintf(buf, "%llu\n",
+		       state_usage->disable & CPUIDLE_STATE_DISABLED_BY_USER);
+}
+
+static ssize_t store_state_disable(struct cpuidle_state *state,
+				   struct cpuidle_state_usage *state_usage,
+				   const char *buf, size_t size)
+{
+	unsigned int value;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	err = kstrtouint(buf, 0, &value);
+	if (err)
+		return err;
+
+	if (value)
+		state_usage->disable |= CPUIDLE_STATE_DISABLED_BY_USER;
+	else
+		state_usage->disable &= ~CPUIDLE_STATE_DISABLED_BY_USER;
+
+	return size;
+}
+
 define_one_state_ro(name, show_state_name);
 define_one_state_ro(desc, show_state_desc);
 define_one_state_ro(latency, show_state_exit_latency);