Linux-libre 4.6.2-gnu

2 files changed, 56 insertions, 45 deletions

diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index f996efc56..0db185762 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -214,7 +214,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 		tick_broadcast_exit();
 	}
 
-	if (!cpuidle_state_is_coupled(drv, entered_state))
+	if (!cpuidle_state_is_coupled(drv, index))
 		local_irq_enable();
 
 	diff = ktime_to_us(ktime_sub(time_end, time_start));
@@ -433,6 +433,8 @@ static void __cpuidle_unregister_device(struct cpuidle_device *dev)
 	list_del(&dev->device_list);
 	per_cpu(cpuidle_devices, dev->cpu) = NULL;
 	module_put(drv->owner);
+
+	dev->registered = 0;
 }
 
 static void __cpuidle_device_init(struct cpuidle_device *dev)
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 0742b3296..03d38c291 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -196,11 +196,11 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev);
  * of points is below a threshold. If it is... then use the
  * average of these 8 points as the estimated value.
  */
-static void get_typical_interval(struct menu_device *data)
+static unsigned int get_typical_interval(struct menu_device *data)
 {
 	int i, divisor;
-	unsigned int max, thresh;
-	uint64_t avg, stddev;
+	unsigned int max, thresh, avg;
+	uint64_t sum, variance;
 
 	thresh = UINT_MAX; /* Discard outliers above this value */
 
@@ -208,55 +208,52 @@ again:
 
 	/* First calculate the average of past intervals */
 	max = 0;
-	avg = 0;
+	sum = 0;
 	divisor = 0;
 	for (i = 0; i < INTERVALS; i++) {
 		unsigned int value = data->intervals[i];
 		if (value <= thresh) {
-			avg += value;
+			sum += value;
 			divisor++;
 			if (value > max)
 				max = value;
 		}
 	}
 	if (divisor == INTERVALS)
-		avg >>= INTERVAL_SHIFT;
+		avg = sum >> INTERVAL_SHIFT;
 	else
-		do_div(avg, divisor);
+		avg = div_u64(sum, divisor);
 
-	/* Then try to determine standard deviation */
-	stddev = 0;
+	/* Then try to determine variance */
+	variance = 0;
 	for (i = 0; i < INTERVALS; i++) {
 		unsigned int value = data->intervals[i];
 		if (value <= thresh) {
-			int64_t diff = value - avg;
-			stddev += diff * diff;
+			int64_t diff = (int64_t)value - avg;
+			variance += diff * diff;
 		}
 	}
 	if (divisor == INTERVALS)
-		stddev >>= INTERVAL_SHIFT;
+		variance >>= INTERVAL_SHIFT;
 	else
-		do_div(stddev, divisor);
+		do_div(variance, divisor);
 
 	/*
-	 * The typical interval is obtained when standard deviation is small
-	 * or standard deviation is small compared to the average interval.
-	 *
-	 * int_sqrt() formal parameter type is unsigned long. When the
-	 * greatest difference to an outlier exceeds ~65 ms * sqrt(divisor)
-	 * the resulting squared standard deviation exceeds the input domain
-	 * of int_sqrt on platforms where unsigned long is 32 bits in size.
-	 * In such case reject the candidate average.
+	 * The typical interval is obtained when standard deviation is
+	 * small (stddev <= 20 us, variance <= 400 us^2) or standard
+	 * deviation is small compared to the average interval (avg >
+	 * 6*stddev, avg^2 > 36*variance). The average is smaller than
+	 * UINT_MAX aka U32_MAX, so computing its square does not
+	 * overflow a u64. We simply reject this candidate average if
+	 * the standard deviation is greater than 715 s (which is
+	 * rather unlikely).
 	 *
 	 * Use this result only if there is no timer to wake us up sooner.
 	 */
-	if (likely(stddev <= ULONG_MAX)) {
-		stddev = int_sqrt(stddev);
-		if (((avg > stddev * 6) && (divisor * 4 >= INTERVALS * 3))
-							|| stddev <= 20) {
-			if (data->next_timer_us > avg)
-				data->predicted_us = avg;
-			return;
+	if (likely(variance <= U64_MAX/36)) {
+		if ((((u64)avg*avg > variance*36) && (divisor * 4 >= INTERVALS * 3))
+							|| variance <= 400) {
+			return avg;
 		}
 	}
 
@@ -270,7 +267,7 @@ again:
 	 * with sporadic activity with a bunch of short pauses.
 	 */
 	if ((divisor * 4) <= INTERVALS * 3)
-		return;
+		return UINT_MAX;
 
 	thresh = max - 1;
 	goto again;
@@ -287,6 +284,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
 	int i;
 	unsigned int interactivity_req;
+	unsigned int expected_interval;
 	unsigned long nr_iowaiters, cpu_load;
 
 	if (data->needs_update) {
@@ -313,32 +311,43 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 					 data->correction_factor[data->bucket],
 					 RESOLUTION * DECAY);
 
-	get_typical_interval(data);
-
-	/*
-	 * Performance multiplier defines a minimum predicted idle
-	 * duration / latency ratio. Adjust the latency limit if
-	 * necessary.
-	 */
-	interactivity_req = data->predicted_us / performance_multiplier(nr_iowaiters, cpu_load);
-	if (latency_req > interactivity_req)
-		latency_req = interactivity_req;
+	expected_interval = get_typical_interval(data);
+	expected_interval = min(expected_interval, data->next_timer_us);
 
 	if (CPUIDLE_DRIVER_STATE_START > 0) {
-		data->last_state_idx = CPUIDLE_DRIVER_STATE_START - 1;
+		struct cpuidle_state *s = &drv->states[CPUIDLE_DRIVER_STATE_START];
+		unsigned int polling_threshold;
+
 		/*
 		 * We want to default to C1 (hlt), not to busy polling
-		 * unless the timer is happening really really soon.
+		 * unless the timer is happening really really soon, or
+		 * C1's exit latency exceeds the user configured limit.
 		 */
-		if (interactivity_req > 20 &&
-		    !drv->states[CPUIDLE_DRIVER_STATE_START].disabled &&
-			dev->states_usage[CPUIDLE_DRIVER_STATE_START].disable == 0)
+		polling_threshold = max_t(unsigned int, 20, s->target_residency);
+		if (data->next_timer_us > polling_threshold &&
+		    latency_req > s->exit_latency && !s->disabled &&
+		    !dev->states_usage[CPUIDLE_DRIVER_STATE_START].disable)
 			data->last_state_idx = CPUIDLE_DRIVER_STATE_START;
+		else
+			data->last_state_idx = CPUIDLE_DRIVER_STATE_START - 1;
 	} else {
 		data->last_state_idx = CPUIDLE_DRIVER_STATE_START;
 	}
 
 	/*
+	 * Use the lowest expected idle interval to pick the idle state.
+	 */
+	data->predicted_us = min(data->predicted_us, expected_interval);
+
+	/*
+	 * Use the performance multiplier and the user-configurable
+	 * latency_req to determine the maximum exit latency.
+	 */
+	interactivity_req = data->predicted_us / performance_multiplier(nr_iowaiters, cpu_load);
+	if (latency_req > interactivity_req)
+		latency_req = interactivity_req;
+
+	/*
 	 * Find the idle state with the lowest power while satisfying
 	 * our constraints.
 	 */