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 <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Doug Smythies <dsmythies@telus.net>
Tested-by: Doug Smythies <dsmythies@telus.net>

1 files changed, 17 insertions, 19 deletions

diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 44ae39f2b47a..bf9b030cd7e1 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -75,24 +75,24 @@ 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];
 
 		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;
@@ -124,7 +124,7 @@ void cpuidle_use_deepest_state(bool enable)
 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
@@ -180,7 +180,7 @@ 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 +209,7 @@ 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 +247,7 @@ 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;
 
 		/*
@@ -255,15 +255,13 @@ 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 (dev->states_usage[i].disable)
 					continue;
@@ -281,14 +279,14 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 				 * 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;
@@ -381,7 +379,7 @@ u64 cpuidle_poll_time(struct cpuidle_driver *drv,
 		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;
@@ -552,7 +550,7 @@ 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;
 }