1 files changed, 120 insertions, 62 deletions

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;
 }