@@ -2,7 +2,7 @@
# Makefile for cpuidle.
#
-obj-y += cpuidle.o driver.o governor.o sysfs.o governors/
+obj-y += cpuidle.o driver.o governor.o sysfs.o
obj-$(CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED) += coupled.o
obj-$(CONFIG_DT_IDLE_STATES) += dt_idle_states.o
@@ -27,3 +27,8 @@ obj-$(CONFIG_MIPS_CPS_CPUIDLE) += cpuidle-cps.o
# POWERPC drivers
obj-$(CONFIG_PSERIES_CPUIDLE) += cpuidle-pseries.o
obj-$(CONFIG_POWERNV_CPUIDLE) += cpuidle-powernv.o
+
+###############################################################################
+# Governors
+obj-$(CONFIG_CPU_IDLE_GOV_LADDER) += governor-ladder.o
+obj-$(CONFIG_CPU_IDLE_GOV_MENU) += governor-menu.o
new file mode 100644
@@ -0,0 +1,197 @@
+/*
+ * 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/jiffies.h>
+#include <linux/tick.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 = this_cpu_ptr(&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];
+
+ last_residency = cpuidle_get_last_residency(dev) - drv->states[last_idx].exit_latency;
+
+ /* consider promotion */
+ if (last_idx < drv->state_count - 1 &&
+ !drv->states[last_idx + 1].disabled &&
+ !dev->states_usage[last_idx + 1].disable &&
+ 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].disabled ||
+ dev->states_usage[last_idx].disable ||
+ 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 = CPUIDLE_DRIVER_STATE_START; 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 > CPUIDLE_DRIVER_STATE_START)
+ 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 = this_cpu_ptr(&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,
+};
+
+/**
+ * init_ladder - initializes the governor
+ */
+static int __init init_ladder(void)
+{
+ /*
+ * When NO_HZ is disabled, or when booting with nohz=off, the ladder
+ * governor is better so give it a higher rating than the menu
+ * governor.
+ */
+ if (!tick_nohz_enabled)
+ ladder_governor.rating = 25;
+
+ return cpuidle_register_governor(&ladder_governor);
+}
+
+postcore_initcall(init_ladder);
new file mode 100644
@@ -0,0 +1,496 @@
+/*
+ * 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>
+
+/*
+ * Please note when changing the tuning values:
+ * If (MAX_INTERESTING-1) * RESOLUTION > UINT_MAX, the result of
+ * a scaling operation multiplication may overflow on 32 bit platforms.
+ * In that case, #define RESOLUTION as ULL to get 64 bit result:
+ * #define RESOLUTION 1024ULL
+ *
+ * The default values do not overflow.
+ */
+#define BUCKETS 12
+#define INTERVAL_SHIFT 3
+#define INTERVALS (1UL << INTERVAL_SHIFT)
+#define RESOLUTION 1024
+#define DECAY 8
+#define MAX_INTERESTING 50000
+
+
+/*
+ * 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 next_timer_us;
+ unsigned int predicted_us;
+ unsigned int bucket;
+ unsigned int correction_factor[BUCKETS];
+ unsigned int intervals[INTERVALS];
+ int interval_ptr;
+};
+
+
+#define LOAD_INT(x) ((x) >> FSHIFT)
+#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
+
+static inline int get_loadavg(unsigned long load)
+{
+ return LOAD_INT(load) * 10 + LOAD_FRAC(load) / 10;
+}
+
+static inline int which_bucket(unsigned int duration, unsigned long nr_iowaiters)
+{
+ 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_iowaiters)
+ 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(unsigned long nr_iowaiters, unsigned long load)
+{
+ int mult = 1;
+
+ /* for higher loadavg, we are more reluctant */
+
+ mult += 2 * get_loadavg(load);
+
+ /* for IO wait tasks (per cpu!) we add 5x each */
+ mult += 10 * nr_iowaiters;
+
+ return mult;
+}
+
+static DEFINE_PER_CPU(struct menu_device, menu_devices);
+
+static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev);
+
+/*
+ * 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 unsigned int get_typical_interval(struct menu_device *data)
+{
+ int i, divisor;
+ unsigned int max, thresh, avg;
+ uint64_t sum, variance;
+
+ thresh = UINT_MAX; /* Discard outliers above this value */
+
+again:
+
+ /* First calculate the average of past intervals */
+ max = 0;
+ sum = 0;
+ divisor = 0;
+ for (i = 0; i < INTERVALS; i++) {
+ unsigned int value = data->intervals[i];
+ if (value <= thresh) {
+ sum += value;
+ divisor++;
+ if (value > max)
+ max = value;
+ }
+ }
+ if (divisor == INTERVALS)
+ avg = sum >> INTERVAL_SHIFT;
+ else
+ avg = div_u64(sum, divisor);
+
+ /* 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 = (int64_t)value - avg;
+ variance += diff * diff;
+ }
+ }
+ if (divisor == INTERVALS)
+ variance >>= INTERVAL_SHIFT;
+ else
+ do_div(variance, divisor);
+
+ /*
+ * 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(variance <= U64_MAX/36)) {
+ if ((((u64)avg*avg > variance*36) && (divisor * 4 >= INTERVALS * 3))
+ || variance <= 400) {
+ return avg;
+ }
+ }
+
+ /*
+ * If we have outliers to the upside in our distribution, discard
+ * those by setting the threshold to exclude these outliers, then
+ * calculate the average and standard deviation again. Once we get
+ * down to the bottom 3/4 of our samples, stop excluding samples.
+ *
+ * This can deal with workloads that have long pauses interspersed
+ * with sporadic activity with a bunch of short pauses.
+ */
+ if ((divisor * 4) <= INTERVALS * 3)
+ return UINT_MAX;
+
+ thresh = max - 1;
+ goto again;
+}
+
+/**
+ * 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 = this_cpu_ptr(&menu_devices);
+ 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) {
+ menu_update(drv, dev);
+ data->needs_update = 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 */
+ data->next_timer_us = ktime_to_us(tick_nohz_get_sleep_length());
+
+ get_iowait_load(&nr_iowaiters, &cpu_load);
+ data->bucket = which_bucket(data->next_timer_us, nr_iowaiters);
+
+ /*
+ * Force the result of multiplication to be 64 bits even if both
+ * operands are 32 bits.
+ * Make sure to round up for half microseconds.
+ */
+ data->predicted_us = DIV_ROUND_CLOSEST_ULL((uint64_t)data->next_timer_us *
+ data->correction_factor[data->bucket],
+ RESOLUTION * DECAY);
+
+ expected_interval = get_typical_interval(data);
+ expected_interval = min(expected_interval, data->next_timer_us);
+
+ if (CPUIDLE_DRIVER_STATE_START > 0) {
+ 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, or
+ * C1's exit latency exceeds the user configured limit.
+ */
+ 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.
+ */
+ for (i = data->last_state_idx + 1; 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)
+ continue;
+ if (s->target_residency > data->predicted_us)
+ continue;
+ if (s->exit_latency > latency_req)
+ continue;
+
+ data->last_state_idx = i;
+ }
+
+ 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 = this_cpu_ptr(&menu_devices);
+
+ data->last_state_idx = index;
+ 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 = this_cpu_ptr(&menu_devices);
+ int last_idx = data->last_state_idx;
+ struct cpuidle_state *target = &drv->states[last_idx];
+ unsigned int measured_us;
+ unsigned int new_factor;
+
+ /*
+ * Try to figure out how much time passed between entry to low
+ * power state and occurrence of the wakeup event.
+ *
+ * If the entered idle state didn't support residency measurements,
+ * we use them anyway if they are short, and if long,
+ * truncate to the whole expected time.
+ *
+ * Any measured amount of time will include the exit latency.
+ * Since we are interested in when the wakeup begun, not when it
+ * was completed, we must subtract the exit latency. However, if
+ * the measured amount of time is less than the exit latency,
+ * assume the state was never reached and the exit latency is 0.
+ */
+
+ /* measured value */
+ measured_us = cpuidle_get_last_residency(dev);
+
+ /* Deduct exit latency */
+ if (measured_us > 2 * target->exit_latency)
+ measured_us -= target->exit_latency;
+ else
+ measured_us /= 2;
+
+ /* Make sure our coefficients do not exceed unity */
+ if (measured_us > data->next_timer_us)
+ measured_us = data->next_timer_us;
+
+ /* Update our correction ratio */
+ new_factor = data->correction_factor[data->bucket];
+ new_factor -= new_factor / DECAY;
+
+ if (data->next_timer_us > 0 && measured_us < MAX_INTERESTING)
+ new_factor += RESOLUTION * measured_us / data->next_timer_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. Fortunately, due to rounding,
+ * new_factor will stay nonzero regardless of measured_us values
+ * and the compiler can eliminate this test as long as DECAY > 1.
+ */
+ if (DECAY == 1 && unlikely(new_factor == 0))
+ new_factor = 1;
+
+ data->correction_factor[data->bucket] = new_factor;
+
+ /* update the repeating-pattern data */
+ data->intervals[data->interval_ptr++] = measured_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);
+ int i;
+
+ memset(data, 0, sizeof(struct menu_device));
+
+ /*
+ * if the correction factor is 0 (eg first time init or cpu hotplug
+ * etc), we actually want to start out with a unity factor.
+ */
+ for(i = 0; i < BUCKETS; i++)
+ data->correction_factor[i] = RESOLUTION * DECAY;
+
+ return 0;
+}
+
+static struct cpuidle_governor menu_governor = {
+ .name = "menu",
+ .rating = 20,
+ .enable = menu_enable_device,
+ .select = menu_select,
+ .reflect = menu_reflect,
+};
+
+/**
+ * init_menu - initializes the governor
+ */
+static int __init init_menu(void)
+{
+ return cpuidle_register_governor(&menu_governor);
+}
+
+postcore_initcall(init_menu);
deleted file mode 100644
@@ -1,6 +0,0 @@
-#
-# Makefile for cpuidle governors.
-#
-
-obj-$(CONFIG_CPU_IDLE_GOV_LADDER) += ladder.o
-obj-$(CONFIG_CPU_IDLE_GOV_MENU) += menu.o
deleted file mode 100644
@@ -1,197 +0,0 @@
-/*
- * 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/jiffies.h>
-#include <linux/tick.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 = this_cpu_ptr(&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];
-
- last_residency = cpuidle_get_last_residency(dev) - drv->states[last_idx].exit_latency;
-
- /* consider promotion */
- if (last_idx < drv->state_count - 1 &&
- !drv->states[last_idx + 1].disabled &&
- !dev->states_usage[last_idx + 1].disable &&
- 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].disabled ||
- dev->states_usage[last_idx].disable ||
- 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 = CPUIDLE_DRIVER_STATE_START; 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 > CPUIDLE_DRIVER_STATE_START)
- 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 = this_cpu_ptr(&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,
-};
-
-/**
- * init_ladder - initializes the governor
- */
-static int __init init_ladder(void)
-{
- /*
- * When NO_HZ is disabled, or when booting with nohz=off, the ladder
- * governor is better so give it a higher rating than the menu
- * governor.
- */
- if (!tick_nohz_enabled)
- ladder_governor.rating = 25;
-
- return cpuidle_register_governor(&ladder_governor);
-}
-
-postcore_initcall(init_ladder);
deleted file mode 100644
@@ -1,496 +0,0 @@
-/*
- * 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>
-
-/*
- * Please note when changing the tuning values:
- * If (MAX_INTERESTING-1) * RESOLUTION > UINT_MAX, the result of
- * a scaling operation multiplication may overflow on 32 bit platforms.
- * In that case, #define RESOLUTION as ULL to get 64 bit result:
- * #define RESOLUTION 1024ULL
- *
- * The default values do not overflow.
- */
-#define BUCKETS 12
-#define INTERVAL_SHIFT 3
-#define INTERVALS (1UL << INTERVAL_SHIFT)
-#define RESOLUTION 1024
-#define DECAY 8
-#define MAX_INTERESTING 50000
-
-
-/*
- * 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 next_timer_us;
- unsigned int predicted_us;
- unsigned int bucket;
- unsigned int correction_factor[BUCKETS];
- unsigned int intervals[INTERVALS];
- int interval_ptr;
-};
-
-
-#define LOAD_INT(x) ((x) >> FSHIFT)
-#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
-
-static inline int get_loadavg(unsigned long load)
-{
- return LOAD_INT(load) * 10 + LOAD_FRAC(load) / 10;
-}
-
-static inline int which_bucket(unsigned int duration, unsigned long nr_iowaiters)
-{
- 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_iowaiters)
- 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(unsigned long nr_iowaiters, unsigned long load)
-{
- int mult = 1;
-
- /* for higher loadavg, we are more reluctant */
-
- mult += 2 * get_loadavg(load);
-
- /* for IO wait tasks (per cpu!) we add 5x each */
- mult += 10 * nr_iowaiters;
-
- return mult;
-}
-
-static DEFINE_PER_CPU(struct menu_device, menu_devices);
-
-static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev);
-
-/*
- * 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 unsigned int get_typical_interval(struct menu_device *data)
-{
- int i, divisor;
- unsigned int max, thresh, avg;
- uint64_t sum, variance;
-
- thresh = UINT_MAX; /* Discard outliers above this value */
-
-again:
-
- /* First calculate the average of past intervals */
- max = 0;
- sum = 0;
- divisor = 0;
- for (i = 0; i < INTERVALS; i++) {
- unsigned int value = data->intervals[i];
- if (value <= thresh) {
- sum += value;
- divisor++;
- if (value > max)
- max = value;
- }
- }
- if (divisor == INTERVALS)
- avg = sum >> INTERVAL_SHIFT;
- else
- avg = div_u64(sum, divisor);
-
- /* 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 = (int64_t)value - avg;
- variance += diff * diff;
- }
- }
- if (divisor == INTERVALS)
- variance >>= INTERVAL_SHIFT;
- else
- do_div(variance, divisor);
-
- /*
- * 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(variance <= U64_MAX/36)) {
- if ((((u64)avg*avg > variance*36) && (divisor * 4 >= INTERVALS * 3))
- || variance <= 400) {
- return avg;
- }
- }
-
- /*
- * If we have outliers to the upside in our distribution, discard
- * those by setting the threshold to exclude these outliers, then
- * calculate the average and standard deviation again. Once we get
- * down to the bottom 3/4 of our samples, stop excluding samples.
- *
- * This can deal with workloads that have long pauses interspersed
- * with sporadic activity with a bunch of short pauses.
- */
- if ((divisor * 4) <= INTERVALS * 3)
- return UINT_MAX;
-
- thresh = max - 1;
- goto again;
-}
-
-/**
- * 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 = this_cpu_ptr(&menu_devices);
- 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) {
- menu_update(drv, dev);
- data->needs_update = 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 */
- data->next_timer_us = ktime_to_us(tick_nohz_get_sleep_length());
-
- get_iowait_load(&nr_iowaiters, &cpu_load);
- data->bucket = which_bucket(data->next_timer_us, nr_iowaiters);
-
- /*
- * Force the result of multiplication to be 64 bits even if both
- * operands are 32 bits.
- * Make sure to round up for half microseconds.
- */
- data->predicted_us = DIV_ROUND_CLOSEST_ULL((uint64_t)data->next_timer_us *
- data->correction_factor[data->bucket],
- RESOLUTION * DECAY);
-
- expected_interval = get_typical_interval(data);
- expected_interval = min(expected_interval, data->next_timer_us);
-
- if (CPUIDLE_DRIVER_STATE_START > 0) {
- 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, or
- * C1's exit latency exceeds the user configured limit.
- */
- 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.
- */
- for (i = data->last_state_idx + 1; 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)
- continue;
- if (s->target_residency > data->predicted_us)
- continue;
- if (s->exit_latency > latency_req)
- continue;
-
- data->last_state_idx = i;
- }
-
- 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 = this_cpu_ptr(&menu_devices);
-
- data->last_state_idx = index;
- 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 = this_cpu_ptr(&menu_devices);
- int last_idx = data->last_state_idx;
- struct cpuidle_state *target = &drv->states[last_idx];
- unsigned int measured_us;
- unsigned int new_factor;
-
- /*
- * Try to figure out how much time passed between entry to low
- * power state and occurrence of the wakeup event.
- *
- * If the entered idle state didn't support residency measurements,
- * we use them anyway if they are short, and if long,
- * truncate to the whole expected time.
- *
- * Any measured amount of time will include the exit latency.
- * Since we are interested in when the wakeup begun, not when it
- * was completed, we must subtract the exit latency. However, if
- * the measured amount of time is less than the exit latency,
- * assume the state was never reached and the exit latency is 0.
- */
-
- /* measured value */
- measured_us = cpuidle_get_last_residency(dev);
-
- /* Deduct exit latency */
- if (measured_us > 2 * target->exit_latency)
- measured_us -= target->exit_latency;
- else
- measured_us /= 2;
-
- /* Make sure our coefficients do not exceed unity */
- if (measured_us > data->next_timer_us)
- measured_us = data->next_timer_us;
-
- /* Update our correction ratio */
- new_factor = data->correction_factor[data->bucket];
- new_factor -= new_factor / DECAY;
-
- if (data->next_timer_us > 0 && measured_us < MAX_INTERESTING)
- new_factor += RESOLUTION * measured_us / data->next_timer_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. Fortunately, due to rounding,
- * new_factor will stay nonzero regardless of measured_us values
- * and the compiler can eliminate this test as long as DECAY > 1.
- */
- if (DECAY == 1 && unlikely(new_factor == 0))
- new_factor = 1;
-
- data->correction_factor[data->bucket] = new_factor;
-
- /* update the repeating-pattern data */
- data->intervals[data->interval_ptr++] = measured_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);
- int i;
-
- memset(data, 0, sizeof(struct menu_device));
-
- /*
- * if the correction factor is 0 (eg first time init or cpu hotplug
- * etc), we actually want to start out with a unity factor.
- */
- for(i = 0; i < BUCKETS; i++)
- data->correction_factor[i] = RESOLUTION * DECAY;
-
- return 0;
-}
-
-static struct cpuidle_governor menu_governor = {
- .name = "menu",
- .rating = 20,
- .enable = menu_enable_device,
- .select = menu_select,
- .reflect = menu_reflect,
-};
-
-/**
- * init_menu - initializes the governor
- */
-static int __init init_menu(void)
-{
- return cpuidle_register_governor(&menu_governor);
-}
-
-postcore_initcall(init_menu);
Currently the different governors are stored in the subdir 'governors'. That is not a problem. However, that forces to declare some private structure in the include/linux/cpuidle.h header because these governor files don't have access to the private 'cpuidle.h' located in drivers/cpuidle. Instead of having the governors in the separate directory, move them along with the drivers and prefix them with 'governor-', that allows to do a proper cleanup in the cpuidle headers. Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org> --- drivers/cpuidle/Makefile | 7 +- drivers/cpuidle/governor-ladder.c | 197 +++++++++++++++ drivers/cpuidle/governor-menu.c | 496 +++++++++++++++++++++++++++++++++++++ drivers/cpuidle/governors/Makefile | 6 - drivers/cpuidle/governors/ladder.c | 197 --------------- drivers/cpuidle/governors/menu.c | 496 ------------------------------------- 6 files changed, 699 insertions(+), 700 deletions(-) create mode 100644 drivers/cpuidle/governor-ladder.c create mode 100644 drivers/cpuidle/governor-menu.c delete mode 100644 drivers/cpuidle/governors/Makefile delete mode 100644 drivers/cpuidle/governors/ladder.c delete mode 100644 drivers/cpuidle/governors/menu.c -- 1.9.1