Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "The main changes in this cycle were:

   - Introduce "Energy Aware Scheduling" - by Quentin Perret.

     This is a coherent topology description of CPUs in cooperation with
     the PM subsystem, with the goal to schedule more energy-efficiently
     on asymetric SMP platform - such as waking up tasks to the more
     energy-efficient CPUs first, as long as the system isn't
     oversubscribed.

     For details of the design, see:

        https://lore.kernel.org/lkml/20180724122521.22109-1-quentin.perret@arm.com/

   - Misc cleanups and smaller enhancements"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  sched/fair: Select an energy-efficient CPU on task wake-up
  sched/fair: Introduce an energy estimation helper function
  sched/fair: Add over-utilization/tipping point indicator
  sched/fair: Clean-up update_sg_lb_stats parameters
  sched/toplogy: Introduce the 'sched_energy_present' static key
  sched/topology: Make Energy Aware Scheduling depend on schedutil
  sched/topology: Disable EAS on inappropriate platforms
  sched/topology: Add lowest CPU asymmetry sched_domain level pointer
  sched/topology: Reference the Energy Model of CPUs when available
  PM: Introduce an Energy Model management framework
  sched/cpufreq: Prepare schedutil for Energy Aware Scheduling
  sched/topology: Relocate arch_scale_cpu_capacity() to the internal header
  sched/core: Remove unnecessary unlikely() in push_*_task()
  sched/topology: Remove the ::smt_gain field from 'struct sched_domain'
  sched: Fix various typos in comments
  sched/core: Clean up the #ifdef block in add_nr_running()
  sched/fair: Make some variables static
  sched/core: Create task_has_idle_policy() helper
  sched/fair: Add lsub_positive() and use it consistently
  sched/fair: Mask UTIL_AVG_UNCHANGED usages
  ...

13 files changed, 955 insertions, 143 deletions

diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 3a6c2f87699e..f8fe57d1022e 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -298,3 +298,18 @@ config PM_GENERIC_DOMAINS_OF
 
 config CPU_PM
 	bool
+
+config ENERGY_MODEL
+	bool "Energy Model for CPUs"
+	depends on SMP
+	depends on CPU_FREQ
+	default n
+	help
+	  Several subsystems (thermal and/or the task scheduler for example)
+	  can leverage information about the energy consumed by CPUs to make
+	  smarter decisions. This config option enables the framework from
+	  which subsystems can access the energy models.
+
+	  The exact usage of the energy model is subsystem-dependent.
+
+	  If in doubt, say N.
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index a3f79f0eef36..e7e47d9be1e5 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -15,3 +15,5 @@ obj-$(CONFIG_PM_AUTOSLEEP)	+= autosleep.o
 obj-$(CONFIG_PM_WAKELOCKS)	+= wakelock.o
 
 obj-$(CONFIG_MAGIC_SYSRQ)	+= poweroff.o
+
+obj-$(CONFIG_ENERGY_MODEL)	+= energy_model.o
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
new file mode 100644
index 000000000000..d9dc2c38764a
--- /dev/null
+++ b/kernel/power/energy_model.c
@@ -0,0 +1,201 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Energy Model of CPUs
+ *
+ * Copyright (c) 2018, Arm ltd.
+ * Written by: Quentin Perret, Arm ltd.
+ */
+
+#define pr_fmt(fmt) "energy_model: " fmt
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/energy_model.h>
+#include <linux/sched/topology.h>
+#include <linux/slab.h>
+
+/* Mapping of each CPU to the performance domain to which it belongs. */
+static DEFINE_PER_CPU(struct em_perf_domain *, em_data);
+
+/*
+ * Mutex serializing the registrations of performance domains and letting
+ * callbacks defined by drivers sleep.
+ */
+static DEFINE_MUTEX(em_pd_mutex);
+
+static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states,
+						struct em_data_callback *cb)
+{
+	unsigned long opp_eff, prev_opp_eff = ULONG_MAX;
+	unsigned long power, freq, prev_freq = 0;
+	int i, ret, cpu = cpumask_first(span);
+	struct em_cap_state *table;
+	struct em_perf_domain *pd;
+	u64 fmax;
+
+	if (!cb->active_power)
+		return NULL;
+
+	pd = kzalloc(sizeof(*pd) + cpumask_size(), GFP_KERNEL);
+	if (!pd)
+		return NULL;
+
+	table = kcalloc(nr_states, sizeof(*table), GFP_KERNEL);
+	if (!table)
+		goto free_pd;
+
+	/* Build the list of capacity states for this performance domain */
+	for (i = 0, freq = 0; i < nr_states; i++, freq++) {
+		/*
+		 * active_power() is a driver callback which ceils 'freq' to
+		 * lowest capacity state of 'cpu' above 'freq' and updates
+		 * 'power' and 'freq' accordingly.
+		 */
+		ret = cb->active_power(&power, &freq, cpu);
+		if (ret) {
+			pr_err("pd%d: invalid cap. state: %d\n", cpu, ret);
+			goto free_cs_table;
+		}
+
+		/*
+		 * We expect the driver callback to increase the frequency for
+		 * higher capacity states.
+		 */
+		if (freq <= prev_freq) {
+			pr_err("pd%d: non-increasing freq: %lu\n", cpu, freq);
+			goto free_cs_table;
+		}
+
+		/*
+		 * The power returned by active_state() is expected to be
+		 * positive, in milli-watts and to fit into 16 bits.
+		 */
+		if (!power || power > EM_CPU_MAX_POWER) {
+			pr_err("pd%d: invalid power: %lu\n", cpu, power);
+			goto free_cs_table;
+		}
+
+		table[i].power = power;
+		table[i].frequency = prev_freq = freq;
+
+		/*
+		 * The hertz/watts efficiency ratio should decrease as the
+		 * frequency grows on sane platforms. But this isn't always
+		 * true in practice so warn the user if a higher OPP is more
+		 * power efficient than a lower one.
+		 */
+		opp_eff = freq / power;
+		if (opp_eff >= prev_opp_eff)
+			pr_warn("pd%d: hertz/watts ratio non-monotonically decreasing: em_cap_state %d >= em_cap_state%d\n",
+					cpu, i, i - 1);
+		prev_opp_eff = opp_eff;
+	}
+
+	/* Compute the cost of each capacity_state. */
+	fmax = (u64) table[nr_states - 1].frequency;
+	for (i = 0; i < nr_states; i++) {
+		table[i].cost = div64_u64(fmax * table[i].power,
+					  table[i].frequency);
+	}
+
+	pd->table = table;
+	pd->nr_cap_states = nr_states;
+	cpumask_copy(to_cpumask(pd->cpus), span);
+
+	return pd;
+
+free_cs_table:
+	kfree(table);
+free_pd:
+	kfree(pd);
+
+	return NULL;
+}
+
+/**
+ * em_cpu_get() - Return the performance domain for a CPU
+ * @cpu : CPU to find the performance domain for
+ *
+ * Return: the performance domain to which 'cpu' belongs, or NULL if it doesn't
+ * exist.
+ */
+struct em_perf_domain *em_cpu_get(int cpu)
+{
+	return READ_ONCE(per_cpu(em_data, cpu));
+}
+EXPORT_SYMBOL_GPL(em_cpu_get);
+
+/**
+ * em_register_perf_domain() - Register the Energy Model of a performance domain
+ * @span	: Mask of CPUs in the performance domain
+ * @nr_states	: Number of capacity states to register
+ * @cb		: Callback functions providing the data of the Energy Model
+ *
+ * Create Energy Model tables for a performance domain using the callbacks
+ * defined in cb.
+ *
+ * If multiple clients register the same performance domain, all but the first
+ * registration will be ignored.
+ *
+ * Return 0 on success
+ */
+int em_register_perf_domain(cpumask_t *span, unsigned int nr_states,
+						struct em_data_callback *cb)
+{
+	unsigned long cap, prev_cap = 0;
+	struct em_perf_domain *pd;
+	int cpu, ret = 0;
+
+	if (!span || !nr_states || !cb)
+		return -EINVAL;
+
+	/*
+	 * Use a mutex to serialize the registration of performance domains and
+	 * let the driver-defined callback functions sleep.
+	 */
+	mutex_lock(&em_pd_mutex);
+
+	for_each_cpu(cpu, span) {
+		/* Make sure we don't register again an existing domain. */
+		if (READ_ONCE(per_cpu(em_data, cpu))) {
+			ret = -EEXIST;
+			goto unlock;
+		}
+
+		/*
+		 * All CPUs of a domain must have the same micro-architecture
+		 * since they all share the same table.
+		 */
+		cap = arch_scale_cpu_capacity(NULL, cpu);
+		if (prev_cap && prev_cap != cap) {
+			pr_err("CPUs of %*pbl must have the same capacity\n",
+							cpumask_pr_args(span));
+			ret = -EINVAL;
+			goto unlock;
+		}
+		prev_cap = cap;
+	}
+
+	/* Create the performance domain and add it to the Energy Model. */
+	pd = em_create_pd(span, nr_states, cb);
+	if (!pd) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	for_each_cpu(cpu, span) {
+		/*
+		 * The per-cpu array can be read concurrently from em_cpu_get().
+		 * The barrier enforces the ordering needed to make sure readers
+		 * can only access well formed em_perf_domain structs.
+		 */
+		smp_store_release(per_cpu_ptr(&em_data, cpu), pd);
+	}
+
+	pr_debug("Created perf domain %*pbl\n", cpumask_pr_args(span));
+unlock:
+	mutex_unlock(&em_pd_mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(em_register_perf_domain);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a5b7f1c9f24f..f66920173370 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -697,7 +697,7 @@ static void set_load_weight(struct task_struct *p, bool update_load)
 	/*
 	 * SCHED_IDLE tasks get minimal weight:
 	 */
-	if (idle_policy(p->policy)) {
+	if (task_has_idle_policy(p)) {
 		load->weight = scale_load(WEIGHT_IDLEPRIO);
 		load->inv_weight = WMULT_IDLEPRIO;
 		p->se.runnable_weight = load->weight;
@@ -2857,7 +2857,7 @@ unsigned long nr_running(void)
  * preemption, thus the result might have a time-of-check-to-time-of-use
  * race.  The caller is responsible to use it correctly, for example:
  *
- * - from a non-preemptable section (of course)
+ * - from a non-preemptible section (of course)
  *
  * - from a thread that is bound to a single CPU
  *
@@ -4191,7 +4191,7 @@ recheck:
 		 * Treat SCHED_IDLE as nice 20. Only allow a switch to
 		 * SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
 		 */
-		if (idle_policy(p->policy) && !idle_policy(policy)) {
+		if (task_has_idle_policy(p) && !idle_policy(policy)) {
 			if (!can_nice(p, task_nice(p)))
 				return -EPERM;
 		}
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 626ddd4ffa43..033ec7c45f13 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -10,6 +10,7 @@
 
 #include "sched.h"
 
+#include <linux/sched/cpufreq.h>
 #include <trace/events/power.h>
 
 struct sugov_tunables {
@@ -164,7 +165,7 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
 	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;
@@ -194,15 +195,13 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
  * 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_freq_util(int cpu, unsigned long util_cfs,
+				  unsigned long max, enum schedutil_type type)
 {
-	struct rq *rq = cpu_rq(sg_cpu->cpu);
-	unsigned long util, irq, max;
-
-	sg_cpu->max = max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
-	sg_cpu->bw_dl = cpu_bw_dl(rq);
+	unsigned long dl_util, util, irq;
+	struct rq *rq = cpu_rq(cpu);
 
-	if (rt_rq_is_runnable(&rq->rt))
+	if (type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt))
 		return max;
 
 	/*
@@ -220,22 +219,31 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
 	 * utilization (PELT windows are synchronized) we can directly add them
 	 * to obtain the CPU's actual utilization.
 	 */
-	util = cpu_util_cfs(rq);
+	util = util_cfs;
 	util += cpu_util_rt(rq);
 
+	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:
@@ -257,7 +265,22 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
 	 * 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(NULL, sg_cpu->cpu);
+
+	sg_cpu->max = max;
+	sg_cpu->bw_dl = cpu_bw_dl(rq);
+
+	return schedutil_freq_util(sg_cpu->cpu, util, max, FREQUENCY_UTIL);
 }
 
 /**
@@ -598,7 +621,7 @@ static struct kobj_type sugov_tunables_ktype = {
 
 /********************** 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)
 {
@@ -857,7 +880,7 @@ static void sugov_limits(struct cpufreq_policy *policy)
 	sg_policy->need_freq_update = true;
 }
 
-static struct cpufreq_governor schedutil_gov = {
+struct cpufreq_governor schedutil_gov = {
 	.name			= "schedutil",
 	.owner			= THIS_MODULE,
 	.dynamic_switching	= true,
@@ -880,3 +903,36 @@ static int __init sugov_register(void)
 	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
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 0796f938c4f0..ba4a143bdcf3 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -525,7 +525,7 @@ void account_idle_ticks(unsigned long ticks)
 
 /*
  * Perform (stime * rtime) / total, but avoid multiplication overflow by
- * loosing precision when the numbers are big.
+ * losing precision when the numbers are big.
  */
 static u64 scale_stime(u64 stime, u64 rtime, u64 total)
 {
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 91e4202b0634..fb8b7b5d745d 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -727,7 +727,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
  * refill the runtime and set the deadline a period in the future,
  * because keeping the current (absolute) deadline of the task would
  * result in breaking guarantees promised to other tasks (refer to
- * Documentation/scheduler/sched-deadline.txt for more informations).
+ * Documentation/scheduler/sched-deadline.txt for more information).
  *
  * This function returns true if:
  *
@@ -1695,6 +1695,14 @@ static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
 }
 #endif
 
+static inline void set_next_task(struct rq *rq, struct task_struct *p)
+{
+	p->se.exec_start = rq_clock_task(rq);
+
+	/* You can't push away the running task */
+	dequeue_pushable_dl_task(rq, p);
+}
+
 static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
 						   struct dl_rq *dl_rq)
 {
@@ -1750,10 +1758,8 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	BUG_ON(!dl_se);
 
 	p = dl_task_of(dl_se);
-	p->se.exec_start = rq_clock_task(rq);
 
-	/* Running task will never be pushed. */
-       dequeue_pushable_dl_task(rq, p);
+	set_next_task(rq, p);
 
 	if (hrtick_enabled(rq))
 		start_hrtick_dl(rq, p);
@@ -1808,12 +1814,7 @@ static void task_fork_dl(struct task_struct *p)
 
 static void set_curr_task_dl(struct rq *rq)
 {
-	struct task_struct *p = rq->curr;
-
-	p->se.exec_start = rq_clock_task(rq);
-
-	/* You can't push away the running task */
-	dequeue_pushable_dl_task(rq, p);
+	set_next_task(rq, rq->curr);
 }
 
 #ifdef CONFIG_SMP
@@ -2041,10 +2042,8 @@ static int push_dl_task(struct rq *rq)
 		return 0;
 
 retry:
-	if (unlikely(next_task == rq->curr)) {
-		WARN_ON(1);
+	if (WARN_ON(next_task == rq->curr))
 		return 0;
-	}
 
 	/*
 	 * If next_task preempts rq->curr, and rq->curr
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 6383aa6a60ca..02bd5f969b21 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -974,7 +974,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 #endif
 	P(policy);
 	P(prio);
-	if (p->policy == SCHED_DEADLINE) {
+	if (task_has_dl_policy(p)) {
 		P(dl.runtime);
 		P(dl.deadline);
 	}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index db514993565b..1c1cfbf6ba0c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -38,7 +38,7 @@
  * (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds)
  */
 unsigned int sysctl_sched_latency			= 6000000ULL;
-unsigned int normalized_sysctl_sched_latency		= 6000000ULL;
+static unsigned int normalized_sysctl_sched_latency	= 6000000ULL;
 
 /*
  * The initial- and re-scaling of tunables is configurable
@@ -58,8 +58,8 @@ enum sched_tunable_scaling sysctl_sched_tunable_scaling = SCHED_TUNABLESCALING_L
  *
  * (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
-unsigned int sysctl_sched_min_granularity		= 750000ULL;
-unsigned int normalized_sysctl_sched_min_granularity	= 750000ULL;
+unsigned int sysctl_sched_min_granularity			= 750000ULL;
+static unsigned int normalized_sysctl_sched_min_granularity	= 750000ULL;
 
 /*
  * This value is kept at sysctl_sched_latency/sysctl_sched_min_granularity
@@ -81,8 +81,8 @@ unsigned int sysctl_sched_child_runs_first __read_mostly;
  *
  * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
-unsigned int sysctl_sched_wakeup_granularity		= 1000000UL;
-unsigned int normalized_sysctl_sched_wakeup_granularity	= 1000000UL;
+unsigned int sysctl_sched_wakeup_granularity			= 1000000UL;
+static unsigned int normalized_sysctl_sched_wakeup_granularity	= 1000000UL;
 
 const_debug unsigned int sysctl_sched_migration_cost	= 500000UL;
 
@@ -116,7 +116,7 @@ unsigned int sysctl_sched_cfs_bandwidth_slice		= 5000UL;
  *
  * (default: ~20%)
  */
-unsigned int capacity_margin				= 1280;
+static unsigned int capacity_margin			= 1280;
 
 static inline void update_load_add(struct load_weight *lw, unsigned long inc)
 {
@@ -703,9 +703,9 @@ void init_entity_runnable_average(struct sched_entity *se)
 	memset(sa, 0, sizeof(*sa));
 
 	/*
-	 * Tasks are intialized with full load to be seen as heavy tasks until
+	 * Tasks are initialized with full load to be seen as heavy tasks until
 	 * they get a chance to stabilize to their real load level.
-	 * Group entities are intialized with zero load to reflect the fact that
+	 * Group entities are initialized with zero load to reflect the fact that
 	 * nothing has been attached to the task group yet.
 	 */
 	if (entity_is_task(se))
@@ -2734,6 +2734,17 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	WRITE_ONCE(*ptr, res);					\
 } while (0)
 
+/*
+ * Remove and clamp on negative, from a local variable.
+ *
+ * A variant of sub_positive(), which does not use explicit load-store
+ * and is thus optimized for local variable updates.
+ */
+#define lsub_positive(_ptr, _val) do {				\
+	typeof(_ptr) ptr = (_ptr);				\
+	*ptr -= min_t(typeof(*ptr), *ptr, _val);		\
+} while (0)
+
 #ifdef CONFIG_SMP
 static inline void
 enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -3604,7 +3615,7 @@ static inline unsigned long _task_util_est(struct task_struct *p)
 {
 	struct util_est ue = READ_ONCE(p->se.avg.util_est);
 
-	return max(ue.ewma, ue.enqueued);
+	return (max(ue.ewma, ue.enqueued) | UTIL_AVG_UNCHANGED);
 }
 
 static inline unsigned long task_util_est(struct task_struct *p)
@@ -3622,7 +3633,7 @@ static inline void util_est_enqueue(struct cfs_rq *cfs_rq,
 
 	/* Update root cfs_rq's estimated utilization */
 	enqueued  = cfs_rq->avg.util_est.enqueued;
-	enqueued += (_task_util_est(p) | UTIL_AVG_UNCHANGED);
+	enqueued += _task_util_est(p);
 	WRITE_ONCE(cfs_rq->avg.util_est.enqueued, enqueued);
 }
 
@@ -3650,8 +3661,7 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
 
 	/* Update root cfs_rq's estimated utilization */
 	ue.enqueued  = cfs_rq->avg.util_est.enqueued;
-	ue.enqueued -= min_t(unsigned int, ue.enqueued,
-			     (_task_util_est(p) | UTIL_AVG_UNCHANGED));
+	ue.enqueued -= min_t(unsigned int, ue.enqueued, _task_util_est(p));
 	WRITE_ONCE(cfs_rq->avg.util_est.enqueued, ue.enqueued);
 
 	/*
@@ -3966,8 +3976,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	/*
 	 * When dequeuing a sched_entity, we must:
 	 *   - Update loads to have both entity and cfs_rq synced with now.
-	 *   - Substract its load from the cfs_rq->runnable_avg.
-	 *   - Substract its previous weight from cfs_rq->load.weight.
+	 *   - Subtract its load from the cfs_rq->runnable_avg.
+	 *   - Subtract its previous weight from cfs_rq->load.weight.
 	 *   - For group entity, update its weight to reflect the new share
 	 *     of its group cfs_rq.
 	 */
@@ -4640,7 +4650,7 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
 		cfs_b->distribute_running = 0;
 		throttled = !list_empty(&cfs_b->throttled_cfs_rq);
 
-		cfs_b->runtime -= min(runtime, cfs_b->runtime);
+		lsub_positive(&cfs_b->runtime, runtime);
 	}
 
 	/*
@@ -4774,7 +4784,7 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 
 	raw_spin_lock(&cfs_b->lock);
 	if (expires == cfs_b->runtime_expires)
-		cfs_b->runtime -= min(runtime, cfs_b->runtime);
+		lsub_positive(&cfs_b->runtime, runtime);
 	cfs_b->distribute_running = 0;
 	raw_spin_unlock(&cfs_b->lock);
 }
@@ -5072,6 +5082,24 @@ static inline void hrtick_update(struct rq *rq)
 }
 #endif
 
+#ifdef CONFIG_SMP
+static inline unsigned long cpu_util(int cpu);
+static unsigned long capacity_of(int cpu);
+
+static inline bool cpu_overutilized(int cpu)
+{
+	return (capacity_of(cpu) * 1024) < (cpu_util(cpu) * capacity_margin);
+}
+
+static inline void update_overutilized_status(struct rq *rq)
+{
+	if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu))
+		WRITE_ONCE(rq->rd->overutilized, SG_OVERUTILIZED);
+}
+#else
+static inline void update_overutilized_status(struct rq *rq) { }
+#endif
+
 /*
  * The enqueue_task method is called before nr_running is
  * increased. Here we update the fair scheduling stats and
@@ -5129,8 +5157,26 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		update_cfs_group(se);
 	}
 
-	if (!se)
+	if (!se) {
 		add_nr_running(rq, 1);
+		/*
+		 * Since new tasks are assigned an initial util_avg equal to
+		 * half of the spare capacity of their CPU, tiny tasks have the
+		 * ability to cross the overutilized threshold, which will
+		 * result in the load balancer ruining all the task placement
+		 * done by EAS. As a way to mitigate that effect, do not account
+		 * for the first enqueue operation of new tasks during the
+		 * overutilized flag detection.
+		 *
+		 * A better way of solving this problem would be to wait for
+		 * the PELT signals of tasks to converge before taking them
+		 * into account, but that is not straightforward to implement,
+		 * and the following generally works well enough in practice.
+		 */
+		if (flags & ENQUEUE_WAKEUP)
+			update_overutilized_status(rq);
+
+	}
 
 	hrtick_update(rq);
 }
@@ -6241,7 +6287,7 @@ static unsigned long cpu_util_without(int cpu, struct task_struct *p)
 	util = READ_ONCE(cfs_rq->avg.util_avg);
 
 	/* Discount task's util from CPU's util */
-	util -= min_t(unsigned int, util, task_util(p));
+	lsub_positive(&util, task_util(p));
 
 	/*
 	 * Covered cases:
@@ -6290,10 +6336,9 @@ static unsigned long cpu_util_without(int cpu, struct task_struct *p)
 		 * properly fix the execl regression and it helps in further
 		 * reducing the chances for the above race.
 		 */
-		if (unlikely(task_on_rq_queued(p) || current == p)) {
-			estimated -= min_t(unsigned int, estimated,
-					   (_task_util_est(p) | UTIL_AVG_UNCHANGED));
-		}
+		if (unlikely(task_on_rq_queued(p) || current == p))
+			lsub_positive(&estimated, _task_util_est(p));
+
 		util = max(util, estimated);
 	}
 
@@ -6333,6 +6378,213 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
 }
 
 /*
+ * Predicts what cpu_util(@cpu) would return if @p was migrated (and enqueued)
+ * to @dst_cpu.
+ */
+static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu)
+{
+	struct cfs_rq *cfs_rq = &cpu_rq(cpu)->cfs;
+	unsigned long util_est, util = READ_ONCE(cfs_rq->avg.util_avg);
+
+	/*
+	 * If @p migrates from @cpu to another, remove its contribution. Or,
+	 * if @p migrates from another CPU to @cpu, add its contribution. In
+	 * the other cases, @cpu is not impacted by the migration, so the
+	 * util_avg should already be correct.
+	 */
+	if (task_cpu(p) == cpu && dst_cpu != cpu)
+		sub_positive(&util, task_util(p));
+	else if (task_cpu(p) != cpu && dst_cpu == cpu)
+		util += task_util(p);
+
+	if (sched_feat(UTIL_EST)) {
+		util_est = READ_ONCE(cfs_rq->avg.util_est.enqueued);
+
+		/*
+		 * During wake-up, the task isn't enqueued yet and doesn't
+		 * appear in the cfs_rq->avg.util_est.enqueued of any rq,
+		 * so just add it (if needed) to "simulate" what will be
+		 * cpu_util() after the task has been enqueued.
+		 */
+		if (dst_cpu == cpu)
+			util_est += _task_util_est(p);
+
+		util = max(util, util_est);
+	}
+
+	return min(util, capacity_orig_of(cpu));
+}
+
+/*
+ * compute_energy(): Estimates the energy that would be consumed if @p was
+ * migrated to @dst_cpu. compute_energy() predicts what will be the utilization
+ * landscape of the * CPUs after the task migration, and uses the Energy Model
+ * to compute what would be the energy if we decided to actually migrate that
+ * task.
+ */
+static long
+compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
+{
+	long util, max_util, sum_util, energy = 0;
+	int cpu;
+
+	for (; pd; pd = pd->next) {
+		max_util = sum_util = 0;
+		/*
+		 * The capacity state of CPUs of the current rd can be driven by
+		 * CPUs of another rd if they belong to the same performance
+		 * domain. So, account for the utilization of these CPUs too
+		 * by masking pd with cpu_online_mask instead of the rd span.
+		 *
+		 * If an entire performance domain is outside of the current rd,
+		 * it will not appear in its pd list and will not be accounted
+		 * by compute_energy().
+		 */
+		for_each_cpu_and(cpu, perf_domain_span(pd), cpu_online_mask) {
+			util = cpu_util_next(cpu, p, dst_cpu);
+			util = schedutil_energy_util(cpu, util);
+			max_util = max(util, max_util);
+			sum_util += util;
+		}
+
+		energy += em_pd_energy(pd->em_pd, max_util, sum_util);
+	}
+
+	return energy;
+}
+
+/*
+ * find_energy_efficient_cpu(): Find most energy-efficient target CPU for the
+ * waking task. find_energy_efficient_cpu() looks for the CPU with maximum
+ * spare capacity in each performance domain and uses it as a potential
+ * candidate to execute the task. Then, it uses the Energy Model to figure
+ * out which of the CPU candidates is the most energy-efficient.
+ *
+ * The rationale for this heuristic is as follows. In a performance domain,
+ * all the most energy efficient CPU candidates (according to the Energy
+ * Model) are those for which we'll request a low frequency. When there are
+ * several CPUs for which the frequency request will be the same, we don't
+ * have enough data to break the tie between them, because the Energy Model
+ * only includes active power costs. With this model, if we assume that
+ * frequency requests follow utilization (e.g. using schedutil), the CPU with
+ * the maximum spare capacity in a performance domain is guaranteed to be among
+ * the best candidates of the performance domain.
+ *
+ * In practice, it could be preferable from an energy standpoint to pack
+ * small tasks on a CPU in order to let other CPUs go in deeper idle states,
+ * but that could also hurt our chances to go cluster idle, and we have no
+ * ways to tell with the current Energy Model if this is actually a good
+ * idea or not. So, find_energy_efficient_cpu() basically favors
+ * cluster-packing, and spreading inside a cluster. That should at least be
+ * a good thing for latency, and this is consistent with the idea that most
+ * of the energy savings of EAS come from the asymmetry of the system, and
+ * not so much from breaking the tie between identical CPUs. That's also the
+ * reason why EAS is enabled in the topology code only for systems where
+ * SD_ASYM_CPUCAPACITY is set.
+ *
+ * NOTE: Forkees are not accepted in the energy-aware wake-up path because
+ * they don't have any useful utilization data yet and it's not possible to
+ * forecast their impact on energy consumption. Consequently, they will be
+ * placed by find_idlest_cpu() on the least loaded CPU, which might turn out
+ * to be energy-inefficient in some use-cases. The alternative would be to
+ * bias new tasks towards specific types of CPUs first, or to try to infer
+ * their util_avg from the parent task, but those heuristics could hurt
+ * other use-cases too. So, until someone finds a better way to solve this,
+ * let's keep things simple by re-using the existing slow path.
+ */
+
+static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
+{
+	unsigned long prev_energy = ULONG_MAX, best_energy = ULONG_MAX;
+	struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
+	int cpu, best_energy_cpu = prev_cpu;
+	struct perf_domain *head, *pd;
+	unsigned long cpu_cap, util;
+	struct sched_domain *sd;
+
+	rcu_read_lock();
+	pd = rcu_dereference(rd->pd);
+	if (!pd || READ_ONCE(rd->overutilized))
+		goto fail;
+	head = pd;
+
+	/*
+	 * Energy-aware wake-up happens on the lowest sched_domain starting
+	 * from sd_asym_cpucapacity spanning over this_cpu and prev_cpu.
+	 */
+	sd = rcu_dereference(*this_cpu_ptr(&sd_asym_cpucapacity));
+	while (sd && !cpumask_test_cpu(prev_cpu, sched_domain_span(sd)))
+		sd = sd->parent;
+	if (!sd)
+		goto fail;
+
+	sync_entity_load_avg(&p->se);
+	if (!task_util_est(p))
+		goto unlock;
+
+	for (; pd; pd = pd->next) {
+		unsigned long cur_energy, spare_cap, max_spare_cap = 0;
+		int max_spare_cap_cpu = -1;
+
+		for_each_cpu_and(cpu, perf_domain_span(pd), sched_domain_span(sd)) {
+			if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+				continue;
+
+			/* Skip CPUs that will be overutilized. */
+			util = cpu_util_next(cpu, p, cpu);
+			cpu_cap = capacity_of(cpu);
+			if (cpu_cap * 1024 < util * capacity_margin)
+				continue;
+
+			/* Always use prev_cpu as a candidate. */
+			if (cpu == prev_cpu) {
+				prev_energy = compute_energy(p, prev_cpu, head);
+				best_energy = min(best_energy, prev_energy);
+				continue;
+			}
+
+			/*
+			 * Find the CPU with the maximum spare capacity in
+			 * the performance domain
+			 */
+			spare_cap = cpu_cap - util;
+			if (spare_cap > max_spare_cap) {
+				max_spare_cap = spare_cap;
+				max_spare_cap_cpu = cpu;
+			}
+		}
+
+		/* Evaluate the energy impact of using this CPU. */