Merge branches 'gemini' and 'misc' into devel

6 files changed, 93 insertions, 21 deletions

diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 12fdd3987a36..dbefe15bd582 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -95,7 +95,7 @@ static void cpuidle_idle_call(void)
 	/* give the governor an opportunity to reflect on the outcome */
 	if (cpuidle_curr_governor->reflect)
 		cpuidle_curr_governor->reflect(dev);
-	trace_power_end(0);
+	trace_power_end(smp_processor_id());
 }
 
 /**
@@ -156,7 +156,7 @@ int cpuidle_enable_device(struct cpuidle_device *dev)
 
 	if (dev->enabled)
 		return 0;
-	if (!cpuidle_curr_driver || !cpuidle_curr_governor)
+	if (!cpuidle_get_driver() || !cpuidle_curr_governor)
 		return -EIO;
 	if (!dev->state_count)
 		return -EINVAL;
@@ -207,7 +207,7 @@ void cpuidle_disable_device(struct cpuidle_device *dev)
 {
 	if (!dev->enabled)
 		return;
-	if (!cpuidle_curr_driver || !cpuidle_curr_governor)
+	if (!cpuidle_get_driver() || !cpuidle_curr_governor)
 		return;
 
 	dev->enabled = 0;
@@ -271,10 +271,11 @@ static int __cpuidle_register_device(struct cpuidle_device *dev)
 {
 	int ret;
 	struct sys_device *sys_dev = get_cpu_sysdev((unsigned long)dev->cpu);
+	struct cpuidle_driver *cpuidle_driver = cpuidle_get_driver();
 
 	if (!sys_dev)
 		return -EINVAL;
-	if (!try_module_get(cpuidle_curr_driver->owner))
+	if (!try_module_get(cpuidle_driver->owner))
 		return -EINVAL;
 
 	init_completion(&dev->kobj_unregister);
@@ -284,7 +285,7 @@ static int __cpuidle_register_device(struct cpuidle_device *dev)
 	per_cpu(cpuidle_devices, dev->cpu) = dev;
 	list_add(&dev->device_list, &cpuidle_detected_devices);
 	if ((ret = cpuidle_add_sysfs(sys_dev))) {
-		module_put(cpuidle_curr_driver->owner);
+		module_put(cpuidle_driver->owner);
 		return ret;
 	}
 
@@ -325,6 +326,7 @@ EXPORT_SYMBOL_GPL(cpuidle_register_device);
 void cpuidle_unregister_device(struct cpuidle_device *dev)
 {
 	struct sys_device *sys_dev = get_cpu_sysdev((unsigned long)dev->cpu);
+	struct cpuidle_driver *cpuidle_driver = cpuidle_get_driver();
 
 	if (dev->registered == 0)
 		return;
@@ -340,7 +342,7 @@ void cpuidle_unregister_device(struct cpuidle_device *dev)
 
 	cpuidle_resume_and_unlock();
 
-	module_put(cpuidle_curr_driver->owner);
+	module_put(cpuidle_driver->owner);
 }
 
 EXPORT_SYMBOL_GPL(cpuidle_unregister_device);
diff --git a/drivers/cpuidle/cpuidle.h b/drivers/cpuidle/cpuidle.h
index 9476ba33ee2c..33e50d556f17 100644
--- a/drivers/cpuidle/cpuidle.h
+++ b/drivers/cpuidle/cpuidle.h
@@ -9,7 +9,6 @@
 
 /* For internal use only */
 extern struct cpuidle_governor *cpuidle_curr_governor;
-extern struct cpuidle_driver *cpuidle_curr_driver;
 extern struct list_head cpuidle_governors;
 extern struct list_head cpuidle_detected_devices;
 extern struct mutex cpuidle_lock;
diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c
index 2257004fe33d..fd1601e3d125 100644
--- a/drivers/cpuidle/driver.c
+++ b/drivers/cpuidle/driver.c
@@ -14,7 +14,7 @@
 
 #include "cpuidle.h"
 
-struct cpuidle_driver *cpuidle_curr_driver;
+static struct cpuidle_driver *cpuidle_curr_driver;
 DEFINE_SPINLOCK(cpuidle_driver_lock);
 
 /**
@@ -40,13 +40,25 @@ int cpuidle_register_driver(struct cpuidle_driver *drv)
 EXPORT_SYMBOL_GPL(cpuidle_register_driver);
 
 /**
+ * cpuidle_get_driver - return the current driver
+ */
+struct cpuidle_driver *cpuidle_get_driver(void)
+{
+	return cpuidle_curr_driver;
+}
+EXPORT_SYMBOL_GPL(cpuidle_get_driver);
+
+/**
  * cpuidle_unregister_driver - unregisters a driver
  * @drv: the driver
  */
 void cpuidle_unregister_driver(struct cpuidle_driver *drv)
 {
-	if (!drv)
+	if (drv != cpuidle_curr_driver) {
+		WARN(1, "invalid cpuidle_unregister_driver(%s)\n",
+			drv->name);
 		return;
+	}
 
 	spin_lock(&cpuidle_driver_lock);
 	cpuidle_curr_driver = NULL;
diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c
index 1c1ceb4f218f..12c98900dcf8 100644
--- a/drivers/cpuidle/governors/ladder.c
+++ b/drivers/cpuidle/governors/ladder.c
@@ -67,7 +67,7 @@ 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);
+	int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
 
 	/* Special case when user has set very strict latency requirement */
 	if (unlikely(latency_req == 0)) {
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 1aea7157d8ff..1b128702d300 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -21,9 +21,12 @@
 #include <linux/math64.h>
 
 #define BUCKETS 12
+#define INTERVALS 8
 #define RESOLUTION 1024
-#define DECAY 4
+#define DECAY 8
 #define MAX_INTERESTING 50000
+#define STDDEV_THRESH 400
+
 
 /*
  * Concepts and ideas behind the menu governor
@@ -64,6 +67,16 @@
  * indexed based on the magnitude of the expected duration as well as the
  * "is IO outstanding" property.
  *
+ * Repeatable-interval-detector
+ * ----------------------------
+ * There are some cases where "next timer" is a completely unusable predictor:
+ * Those cases where the interval is fixed, for example due to hardware
+ * interrupt mitigation, but also due to fixed transfer rate devices such as
+ * mice.
+ * For this, we use a different predictor: We track the duration of the last 8
+ * intervals and if the stand deviation of these 8 intervals is below a
+ * threshold value, we use the average of these intervals as prediction.
+ *
  * Limiting Performance Impact
  * ---------------------------
  * C states, especially those with large exit latencies, can have a real
@@ -100,11 +113,12 @@ struct menu_device {
 	int             needs_update;
 
 	unsigned int	expected_us;
-	unsigned int	measured_us;
 	u64		predicted_us;
 	unsigned int	exit_us;
 	unsigned int	bucket;
 	u64		correction_factor[BUCKETS];
+	u32		intervals[INTERVALS];
+	int		interval_ptr;
 };
 
 
@@ -129,7 +143,7 @@ static inline int which_bucket(unsigned int duration)
 	 * This allows us to calculate
 	 * E(duration)|iowait
 	 */
-	if (nr_iowait_cpu())
+	if (nr_iowait_cpu(smp_processor_id()))
 		bucket = BUCKETS/2;
 
 	if (duration < 10)
@@ -161,7 +175,7 @@ static inline int performance_multiplier(void)
 	mult += 2 * get_loadavg();
 
 	/* for IO wait tasks (per cpu!) we add 5x each */
-	mult += 10 * nr_iowait_cpu();
+	mult += 10 * nr_iowait_cpu(smp_processor_id());
 
 	return mult;
 }
@@ -176,6 +190,42 @@ static u64 div_round64(u64 dividend, u32 divisor)
 	return div_u64(dividend + (divisor / 2), divisor);
 }
 
+/*
+ * Try detecting repeating patterns by keeping track of the last 8
+ * intervals, and checking if the standard deviation of that set
+ * of points is below a threshold. If it is... then use the
+ * average of these 8 points as the estimated value.
+ */
+static void detect_repeating_patterns(struct menu_device *data)
+{
+	int i;
+	uint64_t avg = 0;
+	uint64_t stddev = 0; /* contains the square of the std deviation */
+
+	/* first calculate average and standard deviation of the past */
+	for (i = 0; i < INTERVALS; i++)
+		avg += data->intervals[i];
+	avg = avg / INTERVALS;
+
+	/* if the avg is beyond the known next tick, it's worthless */
+	if (avg > data->expected_us)
+		return;
+
+	for (i = 0; i < INTERVALS; i++)
+		stddev += (data->intervals[i] - avg) *
+			  (data->intervals[i] - avg);
+
+	stddev = stddev / INTERVALS;
+
+	/*
+	 * now.. if stddev is small.. then assume we have a
+	 * repeating pattern and predict we keep doing this.
+	 */
+
+	if (avg && stddev < STDDEV_THRESH)
+		data->predicted_us = avg;
+}
+
 /**
  * menu_select - selects the next idle state to enter
  * @dev: the CPU
@@ -183,18 +233,18 @@ static u64 div_round64(u64 dividend, u32 divisor)
 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 latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
 	int i;
 	int multiplier;
 
-	data->last_state_idx = 0;
-	data->exit_us = 0;
-
 	if (data->needs_update) {
 		menu_update(dev);
 		data->needs_update = 0;
 	}
 
+	data->last_state_idx = 0;
+	data->exit_us = 0;
+
 	/* Special case when user has set very strict latency requirement */
 	if (unlikely(latency_req == 0))
 		return 0;
@@ -219,6 +269,8 @@ static int menu_select(struct cpuidle_device *dev)
 	data->predicted_us = div_round64(data->expected_us * data->correction_factor[data->bucket],
 					 RESOLUTION * DECAY);
 
+	detect_repeating_patterns(data);
+
 	/*
 	 * We want to default to C1 (hlt), not to busy polling
 	 * unless the timer is happening really really soon.
@@ -294,7 +346,7 @@ static void menu_update(struct cpuidle_device *dev)
 	new_factor = data->correction_factor[data->bucket]
 			* (DECAY - 1) / DECAY;
 
-	if (data->expected_us > 0 && data->measured_us < MAX_INTERESTING)
+	if (data->expected_us > 0 && measured_us < MAX_INTERESTING)
 		new_factor += RESOLUTION * measured_us / data->expected_us;
 	else
 		/*
@@ -311,6 +363,11 @@ static void menu_update(struct cpuidle_device *dev)
 		new_factor = 1;
 
 	data->correction_factor[data->bucket] = new_factor;
+
+	/* update the repeating-pattern data */
+	data->intervals[data->interval_ptr++] = last_idle_us;
+	if (data->interval_ptr >= INTERVALS)
+		data->interval_ptr = 0;
 }
 
 /**
diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c
index 8719b36e1a4d..0310ffaec9df 100644
--- a/drivers/cpuidle/sysfs.c
+++ b/drivers/cpuidle/sysfs.c
@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/cpuidle.h>
 #include <linux/sysfs.h>
+#include <linux/slab.h>
 #include <linux/cpu.h>
 
 #include "cpuidle.h"
@@ -46,10 +47,11 @@ static ssize_t show_current_driver(struct sysdev_class *class,
 				   char *buf)
 {
 	ssize_t ret;
+	struct cpuidle_driver *cpuidle_driver = cpuidle_get_driver();
 
 	spin_lock(&cpuidle_driver_lock);
-	if (cpuidle_curr_driver)
-		ret = sprintf(buf, "%s\n", cpuidle_curr_driver->name);
+	if (cpuidle_driver)
+		ret = sprintf(buf, "%s\n", cpuidle_driver->name);
 	else
 		ret = sprintf(buf, "none\n");
 	spin_unlock(&cpuidle_driver_lock);