From 1543e317f1da31b75942316931e8f491a8920811 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Thu, 04 Jan 2024 10:08:02 +0000
Subject: [PATCH] disable FB
---
kernel/drivers/cpuidle/governors/menu.c | 245 +++++++++++++++++++++---------------------------
1 files changed, 107 insertions(+), 138 deletions(-)
diff --git a/kernel/drivers/cpuidle/governors/menu.c b/kernel/drivers/cpuidle/governors/menu.c
index 2ee86c9..b0a7ad5 100644
--- a/kernel/drivers/cpuidle/governors/menu.c
+++ b/kernel/drivers/cpuidle/governors/menu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* menu.c - the menu idle governor
*
@@ -5,9 +6,6 @@
* 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>
@@ -21,22 +19,12 @@
#include <linux/sched/stat.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
-
+#define MAX_INTERESTING (50000 * NSEC_PER_USEC)
/*
* Concepts and ideas behind the menu governor
@@ -119,24 +107,17 @@
*/
struct menu_device {
- int last_state_idx;
int needs_update;
int tick_wakeup;
- unsigned int next_timer_us;
- unsigned int predicted_us;
+ u64 next_timer_ns;
unsigned int bucket;
unsigned int correction_factor[BUCKETS];
unsigned int intervals[INTERVALS];
int interval_ptr;
};
-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)
+static inline int which_bucket(u64 duration_ns, unsigned long nr_iowaiters)
{
int bucket = 0;
@@ -149,15 +130,15 @@
if (nr_iowaiters)
bucket = BUCKETS/2;
- if (duration < 10)
+ if (duration_ns < 10ULL * NSEC_PER_USEC)
return bucket;
- if (duration < 100)
+ if (duration_ns < 100ULL * NSEC_PER_USEC)
return bucket + 1;
- if (duration < 1000)
+ if (duration_ns < 1000ULL * NSEC_PER_USEC)
return bucket + 2;
- if (duration < 10000)
+ if (duration_ns < 10000ULL * NSEC_PER_USEC)
return bucket + 3;
- if (duration < 100000)
+ if (duration_ns < 100000ULL * NSEC_PER_USEC)
return bucket + 4;
return bucket + 5;
}
@@ -169,18 +150,10 @@
* 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)
+static inline int performance_multiplier(unsigned long nr_iowaiters)
{
- 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;
+ /* for IO wait tasks (per cpu!) we add 10x each */
+ return 1 + 10 * nr_iowaiters;
}
static DEFINE_PER_CPU(struct menu_device, menu_devices);
@@ -193,17 +166,19 @@
* 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)
+static unsigned int get_typical_interval(struct menu_device *data,
+ unsigned int predicted_us)
{
int i, divisor;
- unsigned int max, thresh, avg;
+ unsigned int min, max, thresh, avg;
uint64_t sum, variance;
- thresh = UINT_MAX; /* Discard outliers above this value */
+ thresh = INT_MAX; /* Discard outliers above this value */
again:
/* First calculate the average of past intervals */
+ min = UINT_MAX;
max = 0;
sum = 0;
divisor = 0;
@@ -214,8 +189,19 @@
divisor++;
if (value > max)
max = value;
+
+ if (value < min)
+ min = value;
}
}
+
+ /*
+ * If the result of the computation is going to be discarded anyway,
+ * avoid the computation altogether.
+ */
+ if (min >= predicted_us)
+ return UINT_MAX;
+
if (divisor == INTERVALS)
avg = sum >> INTERVAL_SHIFT;
else
@@ -280,64 +266,47 @@
bool *stop_tick)
{
struct menu_device *data = this_cpu_ptr(&menu_devices);
- int latency_req = cpuidle_governor_latency_req(dev->cpu);
- int i;
- int first_idx;
- int idx;
- unsigned int interactivity_req;
- unsigned int expected_interval;
- unsigned long nr_iowaiters, cpu_load;
+ s64 latency_req = cpuidle_governor_latency_req(dev->cpu);
+ unsigned int predicted_us;
+ u64 predicted_ns;
+ u64 interactivity_req;
+ unsigned long nr_iowaiters;
ktime_t delta_next;
+ int i, idx;
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)) {
- *stop_tick = false;
+ /* determine the expected residency time, round up */
+ data->next_timer_ns = tick_nohz_get_sleep_length(&delta_next);
+
+ nr_iowaiters = nr_iowait_cpu(dev->cpu);
+ data->bucket = which_bucket(data->next_timer_ns, nr_iowaiters);
+
+ if (unlikely(drv->state_count <= 1 || latency_req == 0) ||
+ ((data->next_timer_ns < drv->states[1].target_residency_ns ||
+ latency_req < drv->states[1].exit_latency_ns) &&
+ !dev->states_usage[0].disable)) {
+ /*
+ * In this case state[0] will be used no matter what, so return
+ * it right away and keep the tick running if state[0] is a
+ * polling one.
+ */
+ *stop_tick = !(drv->states[0].flags & CPUIDLE_FLAG_POLLING);
return 0;
}
- /* determine the expected residency time, round up */
- data->next_timer_us = ktime_to_us(tick_nohz_get_sleep_length(&delta_next));
-
- 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);
-
- first_idx = 0;
- if (drv->states[0].flags & CPUIDLE_FLAG_POLLING) {
- struct cpuidle_state *s = &drv->states[1];
- unsigned int polling_threshold;
-
- /*
- * Default to a physical idle state, not to busy polling, unless
- * a timer is going to trigger really really soon.
- */
- 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[1].disable)
- first_idx = 1;
- }
-
- /*
- * Use the lowest expected idle interval to pick the idle state.
- */
- data->predicted_us = min(data->predicted_us, expected_interval);
+ /* Round up the result for half microseconds. */
+ predicted_us = div_u64(data->next_timer_ns *
+ data->correction_factor[data->bucket] +
+ (RESOLUTION * DECAY * NSEC_PER_USEC) / 2,
+ RESOLUTION * DECAY * NSEC_PER_USEC);
+ /* Use the lowest expected idle interval to pick the idle state. */
+ predicted_ns = (u64)min(predicted_us,
+ get_typical_interval(data, predicted_us)) *
+ NSEC_PER_USEC;
if (tick_nohz_tick_stopped()) {
/*
@@ -348,34 +317,46 @@
* the known time till the closest timer event for the idle
* state selection.
*/
- if (data->predicted_us < TICK_USEC)
- data->predicted_us = ktime_to_us(delta_next);
+ if (predicted_ns < TICK_NSEC)
+ predicted_ns = delta_next;
} else {
/*
* 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);
+ interactivity_req = div64_u64(predicted_ns,
+ performance_multiplier(nr_iowaiters));
if (latency_req > interactivity_req)
latency_req = interactivity_req;
}
- expected_interval = data->predicted_us;
/*
* Find the idle state with the lowest power while satisfying
* our constraints.
*/
idx = -1;
- for (i = first_idx; i < drv->state_count; i++) {
+ for (i = 0; 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)
+ if (dev->states_usage[i].disable)
continue;
+
if (idx == -1)
idx = i; /* first enabled state */
- if (s->target_residency > data->predicted_us) {
- if (data->predicted_us < TICK_USEC)
+
+ if (s->target_residency_ns > predicted_ns) {
+ /*
+ * Use a physical idle state, not busy polling, unless
+ * a timer is going to trigger soon enough.
+ */
+ if ((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) &&
+ s->exit_latency_ns <= latency_req &&
+ s->target_residency_ns <= data->next_timer_ns) {
+ predicted_ns = s->target_residency_ns;
+ idx = i;
+ break;
+ }
+ if (predicted_ns < TICK_NSEC)
break;
if (!tick_nohz_tick_stopped()) {
@@ -385,7 +366,7 @@
* tick in that case and let the governor run
* again in the next iteration of the loop.
*/
- expected_interval = drv->states[idx].target_residency;
+ predicted_ns = drv->states[idx].target_residency_ns;
break;
}
@@ -395,22 +376,15 @@
* closest timer event, select this one to avoid getting
* stuck in the shallow one for too long.
*/
- if (drv->states[idx].target_residency < TICK_USEC &&
- s->target_residency <= ktime_to_us(delta_next))
+ if (drv->states[idx].target_residency_ns < TICK_NSEC &&
+ s->target_residency_ns <= delta_next)
idx = i;
- goto out;
+ return idx;
}
- if (s->exit_latency > latency_req) {
- /*
- * If we break out of the loop for latency reasons, use
- * the target residency of the selected state as the
- * expected idle duration so that the tick is retained
- * as long as that target residency is low enough.
- */
- expected_interval = drv->states[idx].target_residency;
+ if (s->exit_latency_ns > latency_req)
break;
- }
+
idx = i;
}
@@ -422,12 +396,10 @@
* expected idle duration is shorter than the tick period length.
*/
if (((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) ||
- expected_interval < TICK_USEC) && !tick_nohz_tick_stopped()) {
- unsigned int delta_next_us = ktime_to_us(delta_next);
-
+ predicted_ns < TICK_NSEC) && !tick_nohz_tick_stopped()) {
*stop_tick = false;
- if (idx > 0 && drv->states[idx].target_residency > delta_next_us) {
+ if (idx > 0 && drv->states[idx].target_residency_ns > delta_next) {
/*
* The tick is not going to be stopped and the target
* residency of the state to be returned is not within
@@ -435,21 +407,17 @@
* tick, so try to correct that.
*/
for (i = idx - 1; i >= 0; i--) {
- if (drv->states[i].disabled ||
- dev->states_usage[i].disable)
+ if (dev->states_usage[i].disable)
continue;
idx = i;
- if (drv->states[i].target_residency <= delta_next_us)
+ if (drv->states[i].target_residency_ns <= delta_next)
break;
}
}
}
-out:
- data->last_state_idx = idx;
-
- return data->last_state_idx;
+ return idx;
}
/**
@@ -464,7 +432,7 @@
{
struct menu_device *data = this_cpu_ptr(&menu_devices);
- data->last_state_idx = index;
+ dev->last_state_idx = index;
data->needs_update = 1;
data->tick_wakeup = tick_nohz_idle_got_tick();
}
@@ -477,9 +445,9 @@
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;
+ int last_idx = dev->last_state_idx;
struct cpuidle_state *target = &drv->states[last_idx];
- unsigned int measured_us;
+ u64 measured_ns;
unsigned int new_factor;
/*
@@ -497,7 +465,7 @@
* assume the state was never reached and the exit latency is 0.
*/
- if (data->tick_wakeup && data->next_timer_us > TICK_USEC) {
+ if (data->tick_wakeup && data->next_timer_ns > TICK_NSEC) {
/*
* The nohz code said that there wouldn't be any events within
* the tick boundary (if the tick was stopped), but the idle
@@ -507,7 +475,7 @@
* have been idle long (but not forever) to help the idle
* duration predictor do a better job next time.
*/
- measured_us = 9 * MAX_INTERESTING / 10;
+ measured_ns = 9 * MAX_INTERESTING / 10;
} else if ((drv->states[last_idx].flags & CPUIDLE_FLAG_POLLING) &&
dev->poll_time_limit) {
/*
@@ -517,28 +485,29 @@
* the CPU might have been woken up from idle by the next timer.
* Assume that to be the case.
*/
- measured_us = data->next_timer_us;
+ measured_ns = data->next_timer_ns;
} else {
/* measured value */
- measured_us = cpuidle_get_last_residency(dev);
+ measured_ns = dev->last_residency_ns;
/* Deduct exit latency */
- if (measured_us > 2 * target->exit_latency)
- measured_us -= target->exit_latency;
+ if (measured_ns > 2 * target->exit_latency_ns)
+ measured_ns -= target->exit_latency_ns;
else
- measured_us /= 2;
+ measured_ns /= 2;
}
/* Make sure our coefficients do not exceed unity */
- if (measured_us > data->next_timer_us)
- measured_us = data->next_timer_us;
+ if (measured_ns > data->next_timer_ns)
+ measured_ns = data->next_timer_ns;
/* 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;
+ if (data->next_timer_ns > 0 && measured_ns < MAX_INTERESTING)
+ new_factor += div64_u64(RESOLUTION * measured_ns,
+ data->next_timer_ns);
else
/*
* we were idle so long that we count it as a perfect
@@ -558,7 +527,7 @@
data->correction_factor[data->bucket] = new_factor;
/* update the repeating-pattern data */
- data->intervals[data->interval_ptr++] = measured_us;
+ data->intervals[data->interval_ptr++] = ktime_to_us(measured_ns);
if (data->interval_ptr >= INTERVALS)
data->interval_ptr = 0;
}
--
Gitblit v1.6.2