Update Linux to v5.4.2

Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 3fffad3..86800b4 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -1,20 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * CPUFreq governor based on scheduler-provided CPU utilization data.
  *
  * Copyright (C) 2016, Intel Corporation
  * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include "sched.h"
 
+#include <linux/sched/cpufreq.h>
 #include <trace/events/power.h>
 
+#define IOWAIT_BOOST_MIN	(SCHED_CAPACITY_SCALE / 8)
+
 struct sugov_tunables {
 	struct gov_attr_set	attr_set;
 	unsigned int		rate_limit_us;
@@ -40,6 +40,7 @@
 	struct task_struct	*thread;
 	bool			work_in_progress;
 
+	bool			limits_changed;
 	bool			need_freq_update;
 };
 
@@ -50,7 +51,6 @@
 
 	bool			iowait_boost_pending;
 	unsigned int		iowait_boost;
-	unsigned int		iowait_boost_max;
 	u64			last_update;
 
 	unsigned long		bw_dl;
@@ -90,8 +90,11 @@
 	    !cpufreq_this_cpu_can_update(sg_policy->policy))
 		return false;
 
-	if (unlikely(sg_policy->need_freq_update))
+	if (unlikely(sg_policy->limits_changed)) {
+		sg_policy->limits_changed = false;
+		sg_policy->need_freq_update = true;
 		return true;
+	}
 
 	delta_ns = time - sg_policy->last_freq_update_time;
 
@@ -114,6 +117,7 @@
 			      unsigned int next_freq)
 {
 	struct cpufreq_policy *policy = sg_policy->policy;
+	int cpu;
 
 	if (!sugov_update_next_freq(sg_policy, time, next_freq))
 		return;
@@ -123,7 +127,11 @@
 		return;
 
 	policy->cur = next_freq;
-	trace_cpu_frequency(next_freq, smp_processor_id());
+
+	if (trace_cpu_frequency_enabled()) {
+		for_each_cpu(cpu, policy->cpus)
+			trace_cpu_frequency(next_freq, cpu);
+	}
 }
 
 static void sugov_deferred_update(struct sugov_policy *sg_policy, u64 time,
@@ -167,7 +175,7 @@
 	unsigned int freq = arch_scale_freq_invariant() ?
 				policy->cpuinfo.max_freq : policy->cur;
 
-	freq = (freq + (freq >> 2)) * util / max;
+	freq = map_util_freq(util, freq, max);
 
 	if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update)
 		return sg_policy->next_freq;
@@ -197,16 +205,17 @@
  * based on the task model parameters and gives the minimal utilization
  * required to meet deadlines.
  */
-static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
+unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs,
+				 unsigned long max, enum schedutil_type type,
+				 struct task_struct *p)
 {
-	struct rq *rq = cpu_rq(sg_cpu->cpu);
-	unsigned long util, irq, max;
+	unsigned long dl_util, util, irq;
+	struct rq *rq = cpu_rq(cpu);
 
-	sg_cpu->max = max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
-	sg_cpu->bw_dl = cpu_bw_dl(rq);
-
-	if (rt_rq_is_runnable(&rq->rt))
+	if (!IS_BUILTIN(CONFIG_UCLAMP_TASK) &&
+	    type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) {
 		return max;
+	}
 
 	/*
 	 * Early check to see if IRQ/steal time saturates the CPU, can be
@@ -222,30 +231,46 @@
 	 * CFS tasks and we use the same metric to track the effective
 	 * utilization (PELT windows are synchronized) we can directly add them
 	 * to obtain the CPU's actual utilization.
+	 *
+	 * CFS and RT utilization can be boosted or capped, depending on
+	 * utilization clamp constraints requested by currently RUNNABLE
+	 * tasks.
+	 * When there are no CFS RUNNABLE tasks, clamps are released and
+	 * frequency will be gracefully reduced with the utilization decay.
 	 */
-	util = cpu_util_cfs(rq);
-	util += cpu_util_rt(rq);
+	util = util_cfs + cpu_util_rt(rq);
+	if (type == FREQUENCY_UTIL)
+		util = uclamp_util_with(rq, util, p);
+
+	dl_util = cpu_util_dl(rq);
 
 	/*
-	 * We do not make cpu_util_dl() a permanent part of this sum because we
-	 * want to use cpu_bw_dl() later on, but we need to check if the
-	 * CFS+RT+DL sum is saturated (ie. no idle time) such that we select
-	 * f_max when there is no idle time.
+	 * For frequency selection we do not make cpu_util_dl() a permanent part
+	 * of this sum because we want to use cpu_bw_dl() later on, but we need
+	 * to check if the CFS+RT+DL sum is saturated (ie. no idle time) such
+	 * that we select f_max when there is no idle time.
 	 *
 	 * NOTE: numerical errors or stop class might cause us to not quite hit
 	 * saturation when we should -- something for later.
 	 */
-	if ((util + cpu_util_dl(rq)) >= max)
+	if (util + dl_util >= max)
 		return max;
 
 	/*
+	 * OTOH, for energy computation we need the estimated running time, so
+	 * include util_dl and ignore dl_bw.
+	 */
+	if (type == ENERGY_UTIL)
+		util += dl_util;
+
+	/*
 	 * There is still idle time; further improve the number by using the
 	 * irq metric. Because IRQ/steal time is hidden from the task clock we
 	 * need to scale the task numbers:
 	 *
-	 *              1 - irq
-	 *   U' = irq + ------- * U
-	 *                max
+	 *              max - irq
+	 *   U' = irq + --------- * U
+	 *                 max
 	 */
 	util = scale_irq_capacity(util, irq, max);
 	util += irq;
@@ -260,7 +285,22 @@
 	 * bw_dl as requested freq. However, cpufreq is not yet ready for such
 	 * an interface. So, we only do the latter for now.
 	 */
-	return min(max, util + sg_cpu->bw_dl);
+	if (type == FREQUENCY_UTIL)
+		util += cpu_bw_dl(rq);
+
+	return min(max, util);
+}
+
+static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
+{
+	struct rq *rq = cpu_rq(sg_cpu->cpu);
+	unsigned long util = cpu_util_cfs(rq);
+	unsigned long max = arch_scale_cpu_capacity(sg_cpu->cpu);
+
+	sg_cpu->max = max;
+	sg_cpu->bw_dl = cpu_bw_dl(rq);
+
+	return schedutil_cpu_util(sg_cpu->cpu, util, max, FREQUENCY_UTIL, NULL);
 }
 
 /**
@@ -271,8 +311,8 @@
  *
  * The IO wait boost of a task is disabled after a tick since the last update
  * of a CPU. If a new IO wait boost is requested after more then a tick, then
- * we enable the boost starting from the minimum frequency, which improves
- * energy efficiency by ignoring sporadic wakeups from IO.
+ * we enable the boost starting from IOWAIT_BOOST_MIN, which improves energy
+ * efficiency by ignoring sporadic wakeups from IO.
  */
 static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time,
 			       bool set_iowait_boost)
@@ -283,8 +323,7 @@
 	if (delta_ns <= TICK_NSEC)
 		return false;
 
-	sg_cpu->iowait_boost = set_iowait_boost
-		? sg_cpu->sg_policy->policy->min : 0;
+	sg_cpu->iowait_boost = set_iowait_boost ? IOWAIT_BOOST_MIN : 0;
 	sg_cpu->iowait_boost_pending = set_iowait_boost;
 
 	return true;
@@ -298,8 +337,9 @@
  *
  * Each time a task wakes up after an IO operation, the CPU utilization can be
  * boosted to a certain utilization which doubles at each "frequent and
- * successive" wakeup from IO, ranging from the utilization of the minimum
- * OPP to the utilization of the maximum OPP.
+ * successive" wakeup from IO, ranging from IOWAIT_BOOST_MIN to the utilization
+ * of the maximum OPP.
+ *
  * To keep doubling, an IO boost has to be requested at least once per tick,
  * otherwise we restart from the utilization of the minimum OPP.
  */
@@ -324,14 +364,13 @@
 
 	/* Double the boost at each request */
 	if (sg_cpu->iowait_boost) {
-		sg_cpu->iowait_boost <<= 1;
-		if (sg_cpu->iowait_boost > sg_cpu->iowait_boost_max)
-			sg_cpu->iowait_boost = sg_cpu->iowait_boost_max;
+		sg_cpu->iowait_boost =
+			min_t(unsigned int, sg_cpu->iowait_boost << 1, SCHED_CAPACITY_SCALE);
 		return;
 	}
 
 	/* First wakeup after IO: start with minimum boost */
-	sg_cpu->iowait_boost = sg_cpu->sg_policy->policy->min;
+	sg_cpu->iowait_boost = IOWAIT_BOOST_MIN;
 }
 
 /**
@@ -353,47 +392,38 @@
  * This mechanism is designed to boost high frequently IO waiting tasks, while
  * being more conservative on tasks which does sporadic IO operations.
  */
-static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
-			       unsigned long *util, unsigned long *max)
+static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
+					unsigned long util, unsigned long max)
 {
-	unsigned int boost_util, boost_max;
+	unsigned long boost;
 
 	/* No boost currently required */
 	if (!sg_cpu->iowait_boost)
-		return;
+		return util;
 
 	/* Reset boost if the CPU appears to have been idle enough */
 	if (sugov_iowait_reset(sg_cpu, time, false))
-		return;
+		return util;
 
-	/*
-	 * An IO waiting task has just woken up:
-	 * allow to further double the boost value
-	 */
-	if (sg_cpu->iowait_boost_pending) {
-		sg_cpu->iowait_boost_pending = false;
-	} else {
+	if (!sg_cpu->iowait_boost_pending) {
 		/*
-		 * Otherwise: reduce the boost value and disable it when we
-		 * reach the minimum.
+		 * No boost pending; reduce the boost value.
 		 */
 		sg_cpu->iowait_boost >>= 1;
-		if (sg_cpu->iowait_boost < sg_cpu->sg_policy->policy->min) {
+		if (sg_cpu->iowait_boost < IOWAIT_BOOST_MIN) {
 			sg_cpu->iowait_boost = 0;
-			return;
+			return util;
 		}
 	}
 
+	sg_cpu->iowait_boost_pending = false;
+
 	/*
-	 * Apply the current boost value: a CPU is boosted only if its current
-	 * utilization is smaller then the current IO boost level.
+	 * @util is already in capacity scale; convert iowait_boost
+	 * into the same scale so we can compare.
 	 */
-	boost_util = sg_cpu->iowait_boost;
-	boost_max = sg_cpu->iowait_boost_max;
-	if (*util * boost_max < *max * boost_util) {
-		*util = boost_util;
-		*max = boost_max;
-	}
+	boost = (sg_cpu->iowait_boost * max) >> SCHED_CAPACITY_SHIFT;
+	return max(boost, util);
 }
 
 #ifdef CONFIG_NO_HZ_COMMON
@@ -416,7 +446,7 @@
 static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_policy *sg_policy)
 {
 	if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl)
-		sg_policy->need_freq_update = true;
+		sg_policy->limits_changed = true;
 }
 
 static void sugov_update_single(struct update_util_data *hook, u64 time,
@@ -436,11 +466,12 @@
 	if (!sugov_should_update_freq(sg_policy, time))
 		return;
 
-	busy = sugov_cpu_is_busy(sg_cpu);
+	/* Limits may have changed, don't skip frequency update */
+	busy = !sg_policy->need_freq_update && sugov_cpu_is_busy(sg_cpu);
 
 	util = sugov_get_util(sg_cpu);
 	max = sg_cpu->max;
-	sugov_iowait_apply(sg_cpu, time, &util, &max);
+	util = sugov_iowait_apply(sg_cpu, time, util, max);
 	next_f = get_next_freq(sg_policy, util, max);
 	/*
 	 * Do not reduce the frequency if the CPU has not been idle
@@ -480,7 +511,7 @@
 
 		j_util = sugov_get_util(j_sg_cpu);
 		j_max = j_sg_cpu->max;
-		sugov_iowait_apply(j_sg_cpu, time, &j_util, &j_max);
+		j_util = sugov_iowait_apply(j_sg_cpu, time, j_util, j_max);
 
 		if (j_util * max > j_max * util) {
 			util = j_util;
@@ -589,19 +620,20 @@
 
 static struct governor_attr rate_limit_us = __ATTR_RW(rate_limit_us);
 
-static struct attribute *sugov_attributes[] = {
+static struct attribute *sugov_attrs[] = {
 	&rate_limit_us.attr,
 	NULL
 };
+ATTRIBUTE_GROUPS(sugov);
 
 static struct kobj_type sugov_tunables_ktype = {
-	.default_attrs = sugov_attributes,
+	.default_groups = sugov_groups,
 	.sysfs_ops = &governor_sysfs_ops,
 };
 
 /********************** cpufreq governor interface *********************/
 
-static struct cpufreq_governor schedutil_gov;
+struct cpufreq_governor schedutil_gov;
 
 static struct sugov_policy *sugov_policy_alloc(struct cpufreq_policy *policy)
 {
@@ -762,6 +794,7 @@
 	return 0;
 
 fail:
+	kobject_put(&tunables->attr_set.kobj);
 	policy->governor_data = NULL;
 	sugov_tunables_free(tunables);
 
@@ -808,6 +841,7 @@
 	sg_policy->last_freq_update_time	= 0;
 	sg_policy->next_freq			= 0;
 	sg_policy->work_in_progress		= false;
+	sg_policy->limits_changed		= false;
 	sg_policy->need_freq_update		= false;
 	sg_policy->cached_raw_freq		= 0;
 
@@ -817,7 +851,6 @@
 		memset(sg_cpu, 0, sizeof(*sg_cpu));
 		sg_cpu->cpu			= cpu;
 		sg_cpu->sg_policy		= sg_policy;
-		sg_cpu->iowait_boost_max	= policy->cpuinfo.max_freq;
 	}
 
 	for_each_cpu(cpu, policy->cpus) {
@@ -839,7 +872,7 @@
 	for_each_cpu(cpu, policy->cpus)
 		cpufreq_remove_update_util_hook(cpu);
 
-	synchronize_sched();
+	synchronize_rcu();
 
 	if (!policy->fast_switch_enabled) {
 		irq_work_sync(&sg_policy->irq_work);
@@ -857,10 +890,10 @@
 		mutex_unlock(&sg_policy->work_lock);
 	}
 
-	sg_policy->need_freq_update = true;
+	sg_policy->limits_changed = true;
 }
 
-static struct cpufreq_governor schedutil_gov = {
+struct cpufreq_governor schedutil_gov = {
 	.name			= "schedutil",
 	.owner			= THIS_MODULE,
 	.dynamic_switching	= true,
@@ -883,3 +916,36 @@
 	return cpufreq_register_governor(&schedutil_gov);
 }
 fs_initcall(sugov_register);
+
+#ifdef CONFIG_ENERGY_MODEL
+extern bool sched_energy_update;
+extern struct mutex sched_energy_mutex;
+
+static void rebuild_sd_workfn(struct work_struct *work)
+{
+	mutex_lock(&sched_energy_mutex);
+	sched_energy_update = true;
+	rebuild_sched_domains();
+	sched_energy_update = false;
+	mutex_unlock(&sched_energy_mutex);
+}
+static DECLARE_WORK(rebuild_sd_work, rebuild_sd_workfn);
+
+/*
+ * EAS shouldn't be attempted without sugov, so rebuild the sched_domains
+ * on governor changes to make sure the scheduler knows about it.
+ */
+void sched_cpufreq_governor_change(struct cpufreq_policy *policy,
+				  struct cpufreq_governor *old_gov)
+{
+	if (old_gov == &schedutil_gov || policy->governor == &schedutil_gov) {
+		/*
+		 * When called from the cpufreq_register_driver() path, the
+		 * cpu_hotplug_lock is already held, so use a work item to
+		 * avoid nested locking in rebuild_sched_domains().
+		 */
+		schedule_work(&rebuild_sd_work);
+	}
+
+}
+#endif