Moved, renamed, and deleted files

The original directory structure was scattered and unorganized.
Changes are basically to make it look like kernel structure.

3 files changed, 645 insertions, 0 deletions

diff --git a/drivers/cpuidle/governors/Makefile b/drivers/cpuidle/governors/Makefile
new file mode 100644
index 00000000..1b512722
--- /dev/null
+++ b/drivers/cpuidle/governors/Makefile
@@ -0,0 +1,6 @@
+#
+# Makefile for cpuidle governors.
+#
+
+obj-$(CONFIG_CPU_IDLE_GOV_LADDER) += ladder.o
+obj-$(CONFIG_CPU_IDLE_GOV_MENU) += menu.o
diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c
new file mode 100644
index 00000000..b6a09ea8
--- /dev/null
+++ b/drivers/cpuidle/governors/ladder.c
@@ -0,0 +1,201 @@
+/*
+ * ladder.c - the residency ladder algorithm
+ *
+ *  Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com>
+ *  Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
+ *  Copyright (C) 2004, 2005 Dominik Brodowski <linux@brodo.de>
+ *
+ * (C) 2006-2007 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
+ *               Shaohua Li <shaohua.li@intel.com>
+ *               Adam Belay <abelay@novell.com>
+ *
+ * This code is licenced under the GPL.
+ */
+
+#include <linux/kernel.h>
+#include <linux/cpuidle.h>
+#include <linux/pm_qos.h>
+#include <linux/module.h>
+#include <linux/jiffies.h>
+
+#include <asm/io.h>
+#include <asm/uaccess.h>
+
+#define PROMOTION_COUNT 4
+#define DEMOTION_COUNT 1
+
+struct ladder_device_state {
+	struct {
+		u32 promotion_count;
+		u32 demotion_count;
+		u32 promotion_time;
+		u32 demotion_time;
+	} threshold;
+	struct {
+		int promotion_count;
+		int demotion_count;
+	} stats;
+};
+
+struct ladder_device {
+	struct ladder_device_state states[CPUIDLE_STATE_MAX];
+	int last_state_idx;
+};
+
+static DEFINE_PER_CPU(struct ladder_device, ladder_devices);
+
+/**
+ * ladder_do_selection - prepares private data for a state change
+ * @ldev: the ladder device
+ * @old_idx: the current state index
+ * @new_idx: the new target state index
+ */
+static inline void ladder_do_selection(struct ladder_device *ldev,
+				       int old_idx, int new_idx)
+{
+	ldev->states[old_idx].stats.promotion_count = 0;
+	ldev->states[old_idx].stats.demotion_count = 0;
+	ldev->last_state_idx = new_idx;
+}
+
+/**
+ * ladder_select_state - selects the next state to enter
+ * @drv: cpuidle driver
+ * @dev: the CPU
+ */
+static int ladder_select_state(struct cpuidle_driver *drv,
+				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_request(PM_QOS_CPU_DMA_LATENCY);
+
+	/* 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 (drv->states[last_idx].flags & CPUIDLE_FLAG_TIME_VALID) {
+		last_residency = cpuidle_get_last_residency(dev) - \
+					 drv->states[last_idx].exit_latency;
+	}
+	else
+		last_residency = last_state->threshold.promotion_time + 1;
+
+	/* consider promotion */
+	if (last_idx < drv->state_count - 1 &&
+	    last_residency > last_state->threshold.promotion_time &&
+	    drv->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) {
+			ladder_do_selection(ldev, last_idx, last_idx + 1);
+			return last_idx + 1;
+		}
+	}
+
+	/* consider demotion */
+	if (last_idx > CPUIDLE_DRIVER_STATE_START &&
+	    drv->states[last_idx].exit_latency > latency_req) {
+		int i;
+
+		for (i = last_idx - 1; i > CPUIDLE_DRIVER_STATE_START; i--) {
+			if (drv->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;
+		if (last_state->stats.demotion_count >= last_state->threshold.demotion_count) {
+			ladder_do_selection(ldev, last_idx, last_idx - 1);
+			return last_idx - 1;
+		}
+	}
+
+	/* otherwise remain at the current state */
+	return last_idx;
+}
+
+/**
+ * ladder_enable_device - setup for the governor
+ * @drv: cpuidle driver
+ * @dev: the CPU
+ */
+static int ladder_enable_device(struct cpuidle_driver *drv,
+				struct cpuidle_device *dev)
+{
+	int i;
+	struct ladder_device *ldev = &per_cpu(ladder_devices, dev->cpu);
+	struct ladder_device_state *lstate;
+	struct cpuidle_state *state;
+
+	ldev->last_state_idx = CPUIDLE_DRIVER_STATE_START;
+
+	for (i = 0; i < drv->state_count; i++) {
+		state = &drv->states[i];
+		lstate = &ldev->states[i];
+
+		lstate->stats.promotion_count = 0;
+		lstate->stats.demotion_count = 0;
+
+		lstate->threshold.promotion_count = PROMOTION_COUNT;
+		lstate->threshold.demotion_count = DEMOTION_COUNT;
+
+		if (i < drv->state_count - 1)
+			lstate->threshold.promotion_time = state->exit_latency;
+		if (i > 0)
+			lstate->threshold.demotion_time = state->exit_latency;
+	}
+
+	return 0;
+}
+
+/**
+ * ladder_reflect - update the correct last_state_idx
+ * @dev: the CPU
+ * @index: the index of actual state entered
+ */
+static void ladder_reflect(struct cpuidle_device *dev, int index)
+{
+	struct ladder_device *ldev = &__get_cpu_var(ladder_devices);
+	if (index > 0)
+		ldev->last_state_idx = index;
+}
+
+static struct cpuidle_governor ladder_governor = {
+	.name =		"ladder",
+	.rating =	10,
+	.enable =	ladder_enable_device,
+	.select =	ladder_select_state,
+	.reflect =	ladder_reflect,
+	.owner =	THIS_MODULE,
+};
+
+/**
+ * init_ladder - initializes the governor
+ */
+static int __init init_ladder(void)
+{
+	return cpuidle_register_governor(&ladder_governor);
+}
+
+/**
+ * exit_ladder - exits the governor
+ */
+static void __exit exit_ladder(void)
+{
+	cpuidle_unregister_governor(&ladder_governor);
+}
+
+MODULE_LICENSE("GPL");
+module_init(init_ladder);
+module_exit(exit_ladder);
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
new file mode 100644
index 00000000..746f1e6b
--- /dev/null
+++ b/drivers/cpuidle/governors/menu.c
@@ -0,0 +1,438 @@
+/*
+ * menu.c - the menu idle governor
+ *
+ * Copyright (C) 2006-2007 Adam Belay <abelay@novell.com>
+ * Copyright (C) 2009 Intel Corporation
+ * Author:
+ *        Arjan van de Ven <arjan@linux.intel.com>
+ *
+ * This code is licenced under the GPL version 2 as described
+ * in the COPYING file that acompanies the Linux Kernel.
+ */
+
+#include <linux/kernel.h>
+#include <linux/cpuidle.h>
+#include <linux/pm_qos.h>
+#include <linux/time.h>
+#include <linux/ktime.h>
+#include <linux/hrtimer.h>
+#include <linux/tick.h>
+#include <linux/sched.h>
+#include <linux/math64.h>
+#include <linux/module.h>
+
+#define BUCKETS 12
+#define INTERVALS 8
+#define RESOLUTION 1024
+#define DECAY 8
+#define MAX_INTERESTING 50000
+#define STDDEV_THRESH 400
+
+
+/*
+ * Concepts and ideas behind the menu governor
+ *
+ * For the menu governor, there are 3 decision factors for picking a C
+ * state:
+ * 1) Energy break even point
+ * 2) Performance impact
+ * 3) Latency tolerance (from pmqos infrastructure)
+ * These these three factors are treated independently.
+ *
+ * Energy break even point
+ * -----------------------
+ * C state entry and exit have an energy cost, and a certain amount of time in
+ * the  C state is required to actually break even on this cost. CPUIDLE
+ * provides us this duration in the "target_residency" field. So all that we
+ * need is a good prediction of how long we'll be idle. Like the traditional
+ * menu governor, we start with the actual known "next timer event" time.
+ *
+ * Since there are other source of wakeups (interrupts for example) than
+ * the next timer event, this estimation is rather optimistic. To get a
+ * more realistic estimate, a correction factor is applied to the estimate,
+ * that is based on historic behavior. For example, if in the past the actual
+ * duration always was 50% of the next timer tick, the correction factor will
+ * be 0.5.
+ *
+ * menu uses a running average for this correction factor, however it uses a
+ * set of factors, not just a single factor. This stems from the realization
+ * that the ratio is dependent on the order of magnitude of the expected
+ * duration; if we expect 500 milliseconds of idle time the likelihood of
+ * getting an interrupt very early is much higher than if we expect 50 micro
+ * seconds of idle time. A second independent factor that has big impact on
+ * the actual factor is if there is (disk) IO outstanding or not.
+ * (as a special twist, we consider every sleep longer than 50 milliseconds
+ * as perfect; there are no power gains for sleeping longer than this)
+ *
+ * For these two reasons we keep an array of 12 independent factors, that gets
+ * 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
+ * noticeable impact on workloads, which is not acceptable for most sysadmins,
+ * and in addition, less performance has a power price of its own.
+ *
+ * As a general rule of thumb, menu assumes that the following heuristic
+ * holds:
+ *     The busier the system, the less impact of C states is acceptable
+ *
+ * This rule-of-thumb is implemented using a performance-multiplier:
+ * If the exit latency times the performance multiplier is longer than
+ * the predicted duration, the C state is not considered a candidate
+ * for selection due to a too high performance impact. So the higher
+ * this multiplier is, the longer we need to be idle to pick a deep C
+ * state, and thus the less likely a busy CPU will hit such a deep
+ * C state.
+ *
+ * Two factors are used in determing this multiplier:
+ * a value of 10 is added for each point of "per cpu load average" we have.
+ * a value of 5 points is added for each process that is waiting for
+ * IO on this CPU.
+ * (these values are experimentally determined)
+ *
+ * The load average factor gives a longer term (few seconds) input to the
+ * decision, while the iowait value gives a cpu local instantanious input.
+ * The iowait factor may look low, but realize that this is also already
+ * represented in the system load average.
+ *
+ */
+
+struct menu_device {
+	int		last_state_idx;
+	int             needs_update;
+
+	unsigned int	expected_us;
+	u64		predicted_us;
+	unsigned int	exit_us;
+	unsigned int	bucket;
+	u64		correction_factor[BUCKETS];
+	u32		intervals[INTERVALS];
+	int		interval_ptr;
+};
+
+
+#define LOAD_INT(x) ((x) >> FSHIFT)
+#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
+
+static int get_loadavg(void)
+{
+	unsigned long this = this_cpu_load();
+
+
+	return LOAD_INT(this) * 10 + LOAD_FRAC(this) / 10;
+}
+
+static inline int which_bucket(unsigned int duration)
+{
+	int bucket = 0;
+
+	/*
+	 * We keep two groups of stats; one with no
+	 * IO pending, one without.
+	 * This allows us to calculate
+	 * E(duration)|iowait
+	 */
+	if (nr_iowait_cpu(smp_processor_id()))
+		bucket = BUCKETS/2;
+
+	if (duration < 10)
+		return bucket;
+	if (duration < 100)
+		return bucket + 1;
+	if (duration < 1000)
+		return bucket + 2;
+	if (duration < 10000)
+		return bucket + 3;
+	if (duration < 100000)
+		return bucket + 4;
+	return bucket + 5;
+}
+
+/*
+ * Return a multiplier for the exit latency that is intended
+ * to take performance requirements into account.
+ * The more performance critical we estimate the system
+ * to be, the higher this multiplier, and thus the higher
+ * the barrier to go to an expensive C state.
+ */
+static inline int performance_multiplier(void)
+{
+	int mult = 1;
+
+	/* for higher loadavg, we are more reluctant */
+
+	/*
+	 * this doesn't work as intended - it is almost always 0, but can
+	 * sometimes, depending on workload, spike very high into the hundreds
+	 * even when the average cpu load is under 10%.
+	 */
+	/* mult += 2 * get_loadavg(); */
+
+	/* for IO wait tasks (per cpu!) we add 5x each */
+	mult += 10 * nr_iowait_cpu(smp_processor_id());
+
+	return mult;
+}
+
+static DEFINE_PER_CPU(struct menu_device, menu_devices);
+
+static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev);
+
+/* This implements DIV_ROUND_CLOSEST but avoids 64 bit division */
+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
+ * @drv: cpuidle driver containing state data
+ * @dev: the CPU
+ */
+static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
+{
+	struct menu_device *data = &__get_cpu_var(menu_devices);
+	int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
+	int power_usage = -1;
+	int i;
+	int multiplier;
+	struct timespec t;
+
+	if (data->needs_update) {
+		menu_update(drv, 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;
+
+	/* determine the expected residency time, round up */
+	t = ktime_to_timespec(tick_nohz_get_sleep_length());
+	data->expected_us =
+		t.tv_sec * USEC_PER_SEC + t.tv_nsec / NSEC_PER_USEC;
+
+
+	data->bucket = which_bucket(data->expected_us);
+
+	multiplier = performance_multiplier();
+
+	/*
+	 * if the correction factor is 0 (eg first time init or cpu hotplug
+	 * etc), we actually want to start out with a unity factor.
+	 */
+	if (data->correction_factor[data->bucket] == 0)
+		data->correction_factor[data->bucket] = RESOLUTION * DECAY;
+
+	/* Make sure to round up for half microseconds */
+	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.
+	 */
+	if (data->expected_us > 5 &&
+		drv->states[CPUIDLE_DRIVER_STATE_START].disable == 0)
+		data->last_state_idx = CPUIDLE_DRIVER_STATE_START;
+
+	/*
+	 * Find the idle state with the lowest power while satisfying
+	 * our constraints.
+	 */
+	for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) {
+		struct cpuidle_state *s = &drv->states[i];
+
+		if (s->disable)
+			continue;
+		if (s->target_residency > data->predicted_us)
+			continue;
+		if (s->exit_latency > latency_req)
+			continue;
+		if (s->exit_latency * multiplier > data->predicted_us)
+			continue;
+
+		if (s->power_usage < power_usage) {
+			power_usage = s->power_usage;
+			data->last_state_idx = i;
+			data->exit_us = s->exit_latency;
+		}
+	}
+
+	return data->last_state_idx;
+}
+
+/**
+ * menu_reflect - records that data structures need update
+ * @dev: the CPU
+ * @index: the index of actual entered state
+ *
+ * NOTE: it's important to be fast here because this operation will add to
+ *       the overall exit latency.
+ */
+static void menu_reflect(struct cpuidle_device *dev, int index)
+{
+	struct menu_device *data = &__get_cpu_var(menu_devices);
+	data->last_state_idx = index;
+	if (index >= 0)
+		data->needs_update = 1;
+}
+
+/**
+ * menu_update - attempts to guess what happened after entry
+ * @drv: cpuidle driver containing state data
+ * @dev: the CPU
+ */
+static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
+{
+	struct menu_device *data = &__get_cpu_var(menu_devices);
+	int last_idx = data->last_state_idx;
+	unsigned int last_idle_us = cpuidle_get_last_residency(dev);
+	struct cpuidle_state *target = &drv->states[last_idx];
+	unsigned int measured_us;
+	u64 new_factor;
+
+	/*
+	 * Ugh, this idle state doesn't support residency measurements, so we
+	 * are basically lost in the dark.  As a compromise, assume we slept
+	 * for the whole expected time.
+	 */
+	if (unlikely(!(target->flags & CPUIDLE_FLAG_TIME_VALID)))
+		last_idle_us = data->expected_us;
+
+
+	measured_us = last_idle_us;
+
+	/*
+	 * We correct for the exit latency; we are assuming here that the
+	 * exit latency happens after the event that we're interested in.
+	 */
+	if (measured_us > data->exit_us)
+		measured_us -= data->exit_us;
+
+
+	/* update our correction ratio */
+
+	new_factor = data->correction_factor[data->bucket]
+			* (DECAY - 1) / DECAY;
+
+	if (data->expected_us > 0 && measured_us < MAX_INTERESTING)
+		new_factor += RESOLUTION * measured_us / data->expected_us;
+	else
+		/*
+		 * we were idle so long that we count it as a perfect
+		 * prediction
+		 */
+		new_factor += RESOLUTION;
+
+	/*
+	 * We don't want 0 as factor; we always want at least
+	 * a tiny bit of estimated time.
+	 */
+	if (new_factor == 0)
+		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;
+}
+
+/**
+ * menu_enable_device - scans a CPU's states and does setup
+ * @drv: cpuidle driver
+ * @dev: the CPU
+ */
+static int menu_enable_device(struct cpuidle_driver *drv,
+				struct cpuidle_device *dev)
+{
+	struct menu_device *data = &per_cpu(menu_devices, dev->cpu);
+
+	memset(data, 0, sizeof(struct menu_device));
+
+	return 0;
+}
+
+static struct cpuidle_governor menu_governor = {
+	.name =		"menu",
+	.rating =	20,
+	.enable =	menu_enable_device,
+	.select =	menu_select,
+	.reflect =	menu_reflect,
+	.owner =	THIS_MODULE,
+};
+
+/**
+ * init_menu - initializes the governor
+ */
+static int __init init_menu(void)
+{
+	return cpuidle_register_governor(&menu_governor);
+}
+
+/**
+ * exit_menu - exits the governor
+ */
+static void __exit exit_menu(void)
+{
+	cpuidle_unregister_governor(&menu_governor);
+}
+
+MODULE_LICENSE("GPL");
+module_init(init_menu);
+module_exit(exit_menu);