Merge commit 'v2.6.27-rc6' into timers/hpet

3 files changed, 65 insertions, 32 deletions

diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c
index ba7b9a6b17a1..a4bec3f919aa 100644
--- a/drivers/cpuidle/governors/ladder.c
+++ b/drivers/cpuidle/governors/ladder.c
@@ -67,10 +67,17 @@ static int ladder_select_state(struct cpuidle_device *dev)
 	struct ladder_device *ldev = &__get_cpu_var(ladder_devices);
 	struct ladder_device_state *last_state;
 	int last_residency, last_idx = ldev->last_state_idx;
+	int latency_req = pm_qos_requirement(PM_QOS_CPU_DMA_LATENCY);
 
 	if (unlikely(!ldev))
 		return 0;
 
+	/* Special case when user has set very strict latency requirement */
+	if (unlikely(latency_req == 0)) {
+		ladder_do_selection(ldev, last_idx, 0);
+		return 0;
+	}
+
 	last_state = &ldev->states[last_idx];
 
 	if (dev->states[last_idx].flags & CPUIDLE_FLAG_TIME_VALID)
@@ -81,8 +88,7 @@ static int ladder_select_state(struct cpuidle_device *dev)
 	/* consider promotion */
 	if (last_idx < dev->state_count - 1 &&
 	    last_residency > last_state->threshold.promotion_time &&
-	    dev->states[last_idx + 1].exit_latency <=
-			pm_qos_requirement(PM_QOS_CPU_DMA_LATENCY)) {
+	    dev->states[last_idx + 1].exit_latency <= latency_req) {
 		last_state->stats.promotion_count++;
 		last_state->stats.demotion_count = 0;
 		if (last_state->stats.promotion_count >= last_state->threshold.promotion_count) {
@@ -92,7 +98,19 @@ static int ladder_select_state(struct cpuidle_device *dev)
 	}
 
 	/* consider demotion */
-	if (last_idx > 0 &&
+	if (last_idx > CPUIDLE_DRIVER_STATE_START &&
+	    dev->states[last_idx].exit_latency > latency_req) {
+		int i;
+
+		for (i = last_idx - 1; i > CPUIDLE_DRIVER_STATE_START; i--) {
+			if (dev->states[i].exit_latency <= latency_req)
+				break;
+		}
+		ladder_do_selection(ldev, last_idx, i);
+		return i;
+	}
+
+	if (last_idx > CPUIDLE_DRIVER_STATE_START &&
 	    last_residency < last_state->threshold.demotion_time) {
 		last_state->stats.demotion_count++;
 		last_state->stats.promotion_count = 0;
@@ -117,7 +135,7 @@ static int ladder_enable_device(struct cpuidle_device *dev)
 	struct ladder_device_state *lstate;
 	struct cpuidle_state *state;
 
-	ldev->last_state_idx = 0;
+	ldev->last_state_idx = CPUIDLE_DRIVER_STATE_START;
 
 	for (i = 0; i < dev->state_count; i++) {
 		state = &dev->states[i];
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 78d77c5dc35c..8d7cf3f31450 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -34,21 +34,28 @@ static DEFINE_PER_CPU(struct menu_device, menu_devices);
 static int menu_select(struct cpuidle_device *dev)
 {
 	struct menu_device *data = &__get_cpu_var(menu_devices);
+	int latency_req = pm_qos_requirement(PM_QOS_CPU_DMA_LATENCY);
 	int i;
 
+	/* Special case when user has set very strict latency requirement */
+	if (unlikely(latency_req == 0)) {
+		data->last_state_idx = 0;
+		return 0;
+	}
+
 	/* determine the expected residency time */
 	data->expected_us =
 		(u32) ktime_to_ns(tick_nohz_get_sleep_length()) / 1000;
 
 	/* find the deepest idle state that satisfies our constraints */
-	for (i = 1; i < dev->state_count; i++) {
+	for (i = CPUIDLE_DRIVER_STATE_START + 1; i < dev->state_count; i++) {
 		struct cpuidle_state *s = &dev->states[i];
 
 		if (s->target_residency > data->expected_us)
 			break;
 		if (s->target_residency > data->predicted_us)
 			break;
-		if (s->exit_latency > pm_qos_requirement(PM_QOS_CPU_DMA_LATENCY))
+		if (s->exit_latency > latency_req)
 			break;
 	}
 
@@ -67,9 +74,9 @@ static void menu_reflect(struct cpuidle_device *dev)
 {
 	struct menu_device *data = &__get_cpu_var(menu_devices);
 	int last_idx = data->last_state_idx;
-	unsigned int measured_us =
-		cpuidle_get_last_residency(dev) + data->elapsed_us;
+	unsigned int last_idle_us = cpuidle_get_last_residency(dev);
 	struct cpuidle_state *target = &dev->states[last_idx];
+	unsigned int measured_us;
 
 	/*
 	 * Ugh, this idle state doesn't support residency measurements, so we
@@ -77,20 +84,27 @@ static void menu_reflect(struct cpuidle_device *dev)
 	 * for one full standard timer tick.  However, be aware that this
 	 * could potentially result in a suboptimal state transition.
 	 */
-	if (!(target->flags & CPUIDLE_FLAG_TIME_VALID))
-		measured_us = USEC_PER_SEC / HZ;
+	if (unlikely(!(target->flags & CPUIDLE_FLAG_TIME_VALID)))
+		last_idle_us = USEC_PER_SEC / HZ;
+
+	/*
+	 * measured_us and elapsed_us are the cumulative idle time, since the
+	 * last time we were woken out of idle by an interrupt.
+	 */
+	if (data->elapsed_us <= data->elapsed_us + last_idle_us)
+		measured_us = data->elapsed_us + last_idle_us;
+	else
+		measured_us = -1;
+
+	/* Predict time until next break event */
+	data->predicted_us = max(measured_us, data->last_measured_us);
 
-	/* Predict time remaining until next break event */
-	if (measured_us + BREAK_FUZZ < data->expected_us - target->exit_latency) {
-		data->predicted_us = max(measured_us, data->last_measured_us);
+	if (last_idle_us + BREAK_FUZZ <
+	    data->expected_us - target->exit_latency) {
 		data->last_measured_us = measured_us;
 		data->elapsed_us = 0;
 	} else {
-		if (data->elapsed_us < data->elapsed_us + measured_us)
-			data->elapsed_us = measured_us;
-		else
-			data->elapsed_us = -1;
-		data->predicted_us = max(measured_us, data->last_measured_us);
+		data->elapsed_us = measured_us;
 	}
 }
 
diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c
index 31a0e0b455b6..97b003839fb6 100644
--- a/drivers/cpuidle/sysfs.c
+++ b/drivers/cpuidle/sysfs.c
@@ -21,8 +21,8 @@ static int __init cpuidle_sysfs_setup(char *unused)
 }
 __setup("cpuidle_sysfs_switch", cpuidle_sysfs_setup);
 
-static ssize_t show_available_governors(struct sys_device *dev,
-		struct sysdev_attribute *attr, char *buf)
+static ssize_t show_available_governors(struct sysdev_class *class,
+					char *buf)
 {
 	ssize_t i = 0;
 	struct cpuidle_governor *tmp;
@@ -40,8 +40,8 @@ out:
 	return i;
 }
 
-static ssize_t show_current_driver(struct sys_device *dev,
-		struct sysdev_attribute *attr, char *buf)
+static ssize_t show_current_driver(struct sysdev_class *class,
+				   char *buf)
 {
 	ssize_t ret;
 
@@ -55,8 +55,8 @@ static ssize_t show_current_driver(struct sys_device *dev,
 	return ret;
 }
 
-static ssize_t show_current_governor(struct sys_device *dev,
-			struct sysdev_attribute *attr, char *buf)
+static ssize_t show_current_governor(struct sysdev_class *class,
+				     char *buf)
 {
 	ssize_t ret;
 
@@ -70,9 +70,8 @@ static ssize_t show_current_governor(struct sys_device *dev,
 	return ret;
 }
 
-static ssize_t store_current_governor(struct sys_device *dev,
-	struct sysdev_attribute *attr,
-	const char *buf, size_t count)
+static ssize_t store_current_governor(struct sysdev_class *class,
+				      const char *buf, size_t count)
 {
 	char gov_name[CPUIDLE_NAME_LEN];
 	int ret = -EINVAL;
@@ -104,8 +103,9 @@ static ssize_t store_current_governor(struct sys_device *dev,
 		return count;
 }
 
-static SYSDEV_ATTR(current_driver, 0444, show_current_driver, NULL);
-static SYSDEV_ATTR(current_governor_ro, 0444, show_current_governor, NULL);
+static SYSDEV_CLASS_ATTR(current_driver, 0444, show_current_driver, NULL);
+static SYSDEV_CLASS_ATTR(current_governor_ro, 0444, show_current_governor,
+			 NULL);
 
 static struct attribute *cpuclass_default_attrs[] = {
 	&attr_current_driver.attr,
@@ -113,9 +113,10 @@ static struct attribute *cpuclass_default_attrs[] = {
 	NULL
 };
 
-static SYSDEV_ATTR(available_governors, 0444, show_available_governors, NULL);
-static SYSDEV_ATTR(current_governor, 0644, show_current_governor,
-	store_current_governor);
+static SYSDEV_CLASS_ATTR(available_governors, 0444, show_available_governors,
+			 NULL);
+static SYSDEV_CLASS_ATTR(current_governor, 0644, show_current_governor,
+			 store_current_governor);
 
 static struct attribute *cpuclass_switch_attrs[] = {
 	&attr_available_governors.attr,