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
  ...

drivers/cpufreq/cpufreq.c

@@ -2277,6 +2277,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 		ret = cpufreq_start_governor(policy);
 		if (!ret) {
 			pr_debug("cpufreq: governor change\n");
+			sched_cpufreq_governor_change(policy, old_gov);
 			return 0;
 		}
 		cpufreq_exit_governor(policy);

include/linux/cpufreq.h

@@ -950,6 +950,14 @@ static inline bool policy_has_boost_freq(struct cpufreq_policy *policy)
 }
 #endif
 
+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
+void sched_cpufreq_governor_change(struct cpufreq_policy *policy,
+			struct cpufreq_governor *old_gov);
+#else
+static inline void sched_cpufreq_governor_change(struct cpufreq_policy *policy,
+			struct cpufreq_governor *old_gov) { }
+#endif
+
 extern void arch_freq_prepare_all(void);
 extern unsigned int arch_freq_get_on_cpu(int cpu);
 

include/linux/energy_model.h

@@ -0,0 +1,187 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_ENERGY_MODEL_H
+#define _LINUX_ENERGY_MODEL_H
+#include <linux/cpumask.h>
+#include <linux/jump_label.h>
+#include <linux/kobject.h>
+#include <linux/rcupdate.h>
+#include <linux/sched/cpufreq.h>
+#include <linux/sched/topology.h>
+#include <linux/types.h>
+
+#ifdef CONFIG_ENERGY_MODEL
+/**
+ * em_cap_state - Capacity state of a performance domain
+ * @frequency:	The CPU frequency in KHz, for consistency with CPUFreq
+ * @power:	The power consumed by 1 CPU at this level, in milli-watts
+ * @cost:	The cost coefficient associated with this level, used during
+ *		energy calculation. Equal to: power * max_frequency / frequency
+ */
+struct em_cap_state {
+	unsigned long frequency;
+	unsigned long power;
+	unsigned long cost;
+};
+
+/**
+ * em_perf_domain - Performance domain
+ * @table:		List of capacity states, in ascending order
+ * @nr_cap_states:	Number of capacity states
+ * @cpus:		Cpumask covering the CPUs of the domain
+ *
+ * A "performance domain" represents a group of CPUs whose performance is
+ * scaled together. All CPUs of a performance domain must have the same
+ * micro-architecture. Performance domains often have a 1-to-1 mapping with
+ * CPUFreq policies.
+ */
+struct em_perf_domain {
+	struct em_cap_state *table;
+	int nr_cap_states;
+	unsigned long cpus[0];
+};
+
+#define EM_CPU_MAX_POWER 0xFFFF
+
+struct em_data_callback {
+	/**
+	 * active_power() - Provide power at the next capacity state of a CPU
+	 * @power	: Active power at the capacity state in mW (modified)
+	 * @freq	: Frequency at the capacity state in kHz (modified)
+	 * @cpu		: CPU for which we do this operation
+	 *
+	 * active_power() must find the lowest capacity state of 'cpu' above
+	 * 'freq' and update 'power' and 'freq' to the matching active power
+	 * and frequency.
+	 *
+	 * The power is the one of a single CPU in the domain, expressed in
+	 * milli-watts. It is expected to fit in the [0, EM_CPU_MAX_POWER]
+	 * range.
+	 *
+	 * Return 0 on success.
+	 */
+	int (*active_power)(unsigned long *power, unsigned long *freq, int cpu);
+};
+#define EM_DATA_CB(_active_power_cb) { .active_power = &_active_power_cb }
+
+struct em_perf_domain *em_cpu_get(int cpu);
+int em_register_perf_domain(cpumask_t *span, unsigned int nr_states,
+						struct em_data_callback *cb);
+
+/**
+ * em_pd_energy() - Estimates the energy consumed by the CPUs of a perf. domain
+ * @pd		: performance domain for which energy has to be estimated
+ * @max_util	: highest utilization among CPUs of the domain
+ * @sum_util	: sum of the utilization of all CPUs in the domain
+ *
+ * Return: the sum of the energy consumed by the CPUs of the domain assuming
+ * a capacity state satisfying the max utilization of the domain.
+ */
+static inline unsigned long em_pd_energy(struct em_perf_domain *pd,
+				unsigned long max_util, unsigned long sum_util)
+{
+	unsigned long freq, scale_cpu;
+	struct em_cap_state *cs;
+	int i, cpu;
+
+	/*
+	 * In order to predict the capacity state, map the utilization of the
+	 * most utilized CPU of the performance domain to a requested frequency,
+	 * like schedutil.
+	 */
+	cpu = cpumask_first(to_cpumask(pd->cpus));
+	scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
+	cs = &pd->table[pd->nr_cap_states - 1];
+	freq = map_util_freq(max_util, cs->frequency, scale_cpu);
+
+	/*
+	 * Find the lowest capacity state of the Energy Model above the
+	 * requested frequency.
+	 */
+	for (i = 0; i < pd->nr_cap_states; i++) {
+		cs = &pd->table[i];
+		if (cs->frequency >= freq)
+			break;
+	}
+
+	/*
+	 * The capacity of a CPU in the domain at that capacity state (cs)
+	 * can be computed as:
+	 *
+	 *             cs->freq * scale_cpu
+	 *   cs->cap = --------------------                          (1)
+	 *                 cpu_max_freq
+	 *
+	 * So, ignoring the costs of idle states (which are not available in
+	 * the EM), the energy consumed by this CPU at that capacity state is
+	 * estimated as:
+	 *
+	 *             cs->power * cpu_util
+	 *   cpu_nrg = --------------------                          (2)
+	 *                   cs->cap
+	 *
+	 * since 'cpu_util / cs->cap' represents its percentage of busy time.
+	 *
+	 *   NOTE: Although the result of this computation actually is in
+	 *         units of power, it can be manipulated as an energy value
+	 *         over a scheduling period, since it is assumed to be
+	 *         constant during that interval.
+	 *
+	 * By injecting (1) in (2), 'cpu_nrg' can be re-expressed as a product
+	 * of two terms:
+	 *
+	 *             cs->power * cpu_max_freq   cpu_util
+	 *   cpu_nrg = ------------------------ * ---------          (3)
+	 *                    cs->freq            scale_cpu
+	 *
+	 * The first term is static, and is stored in the em_cap_state struct
+	 * as 'cs->cost'.
+	 *
+	 * Since all CPUs of the domain have the same micro-architecture, they
+	 * share the same 'cs->cost', and the same CPU capacity. Hence, the
+	 * total energy of the domain (which is the simple sum of the energy of
+	 * all of its CPUs) can be factorized as:
+	 *
+	 *            cs->cost * \Sum cpu_util
+	 *   pd_nrg = ------------------------                       (4)
+	 *                  scale_cpu
+	 */
+	return cs->cost * sum_util / scale_cpu;
+}
+
+/**
+ * em_pd_nr_cap_states() - Get the number of capacity states of a perf. domain
+ * @pd		: performance domain for which this must be done
+ *
+ * Return: the number of capacity states in the performance domain table
+ */
+static inline int em_pd_nr_cap_states(struct em_perf_domain *pd)
+{
+	return pd->nr_cap_states;
+}
+
+#else
+struct em_perf_domain {};
+struct em_data_callback {};
+#define EM_DATA_CB(_active_power_cb) { }
+
+static inline int em_register_perf_domain(cpumask_t *span,
+			unsigned int nr_states, struct em_data_callback *cb)
+{
+	return -EINVAL;
+}
+static inline struct em_perf_domain *em_cpu_get(int cpu)
+{
+	return NULL;
+}
+static inline unsigned long em_pd_energy(struct em_perf_domain *pd,
+			unsigned long max_util, unsigned long sum_util)
+{
+	return 0;
+}
+static inline int em_pd_nr_cap_states(struct em_perf_domain *pd)
+{
+	return 0;
+}
+#endif
+
+#endif

include/linux/sched.h

@@ -176,7 +176,7 @@ struct task_group;
  * TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING).
  *
  * However, with slightly different timing the wakeup TASK_RUNNING store can
- * also collide with the TASK_UNINTERRUPTIBLE store. Loosing that store is not
+ * also collide with the TASK_UNINTERRUPTIBLE store. Losing that store is not
  * a problem either because that will result in one extra go around the loop
  * and our @cond test will save the day.
  *
@@ -515,7 +515,7 @@ struct sched_dl_entity {
 
 	/*
 	 * Actual scheduling parameters. Initialized with the values above,
-	 * they are continously updated during task execution. Note that
+	 * they are continuously updated during task execution. Note that
 	 * the remaining runtime could be < 0 in case we are in overrun.
 	 */
 	s64				runtime;	/* Remaining runtime for this instance	*/

include/linux/sched/cpufreq.h

@@ -20,6 +20,12 @@ void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data,
                        void (*func)(struct update_util_data *data, u64 time,
 				    unsigned int flags));
 void cpufreq_remove_update_util_hook(int cpu);
+
+static inline unsigned long map_util_freq(unsigned long util,
+					unsigned long freq, unsigned long cap)
+{
+	return (freq + (freq >> 2)) * util / cap;
+}
 #endif /* CONFIG_CPU_FREQ */
 
 #endif /* _LINUX_SCHED_CPUFREQ_H */

include/linux/sched/isolation.h

@@ -16,7 +16,7 @@ enum hk_flags {
 };
 
 #ifdef CONFIG_CPU_ISOLATION
-DECLARE_STATIC_KEY_FALSE(housekeeping_overriden);
+DECLARE_STATIC_KEY_FALSE(housekeeping_overridden);
 extern int housekeeping_any_cpu(enum hk_flags flags);
 extern const struct cpumask *housekeeping_cpumask(enum hk_flags flags);
 extern void housekeeping_affine(struct task_struct *t, enum hk_flags flags);
@@ -43,7 +43,7 @@ static inline void housekeeping_init(void) { }
 static inline bool housekeeping_cpu(int cpu, enum hk_flags flags)
 {
 #ifdef CONFIG_CPU_ISOLATION
-	if (static_branch_unlikely(&housekeeping_overriden))
+	if (static_branch_unlikely(&housekeeping_overridden))
 		return housekeeping_test_cpu(cpu, flags);
 #endif
 	return true;

include/linux/sched/mm.h

@@ -153,7 +153,7 @@ static inline gfp_t current_gfp_context(gfp_t flags)
 {
 	/*
 	 * NOIO implies both NOIO and NOFS and it is a weaker context
-	 * so always make sure it makes precendence
+	 * so always make sure it makes precedence
 	 */
 	if (unlikely(current->flags & PF_MEMALLOC_NOIO))
 		flags &= ~(__GFP_IO | __GFP_FS);

include/linux/sched/stat.h

@@ -8,7 +8,7 @@
  * Various counters maintained by the scheduler and fork(),
  * exposed via /proc, sys.c or used by drivers via these APIs.
  *
- * ( Note that all these values are aquired without locking,
+ * ( Note that all these values are acquired without locking,
  *   so they can only be relied on in narrow circumstances. )
  */
 

include/linux/sched/topology.h

@@ -89,7 +89,6 @@ struct sched_domain {
 	unsigned int newidle_idx;
 	unsigned int wake_idx;
 	unsigned int forkexec_idx;
-	unsigned int smt_gain;
 
 	int nohz_idle;			/* NOHZ IDLE status */
 	int flags;			/* See SD_* */
@@ -202,6 +201,14 @@ extern void set_sched_topology(struct sched_domain_topology_level *tl);
 # define SD_INIT_NAME(type)
 #endif
 
+#ifndef arch_scale_cpu_capacity
+static __always_inline
+unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
+{
+	return SCHED_CAPACITY_SCALE;
+}
+#endif
+
 #else /* CONFIG_SMP */
 
 struct sched_domain_attr;
@@ -217,6 +224,14 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu)
 	return true;
 }
 
+#ifndef arch_scale_cpu_capacity
+static __always_inline
+unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu)
+{
+	return SCHED_CAPACITY_SCALE;
+}
+#endif
+
 #endif	/* !CONFIG_SMP */
 
 static inline int task_node(const struct task_struct *p)

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.

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

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);

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 @@ static int __sched_setscheduler(struct task_struct *p,
 		 * 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;
 		}

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 dl_util, util, irq;
-	unsigned long util, irq, max;
+	struct rq *rq = cpu_rq(cpu);
 
-	sg_cpu->max = max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
+	if (type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt))
-	sg_cpu->bw_dl = cpu_bw_dl(rq);
-
-	if (rt_rq_is_runnable(&rq->rt))
 		return max;
 
 	/*
@@ -220,21 +219,30 @@ 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
+	 * For frequency selection we do not make cpu_util_dl() a permanent part
-	 * want to use cpu_bw_dl() later on, but we need to check if the
+	 * of this sum because we want to use cpu_bw_dl() later on, but we need
-	 * CFS+RT+DL sum is saturated (ie. no idle time) such that we select
+	 * to check if the CFS+RT+DL sum is saturated (ie. no idle time) such
-	 * f_max when there is no idle time.
+	 * 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
@@ -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

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)
 {

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. */
+	set_next_task(rq, p);
-       dequeue_pushable_dl_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;
+	set_next_task(rq, rq->curr);
-
-	p->se.exec_start = rq_clock_task(rq);
-
-	/* You can't push away the running task */
-	dequeue_pushable_dl_task(rq, p);
 }
 
 #ifdef CONFIG_SMP
@@ -2041,10 +2042,8 @@ static int push_dl_task(struct rq *rq)
 		return 0;
 
 retry:
-	if (unlikely(next_task == rq->curr)) {
+	if (WARN_ON(next_task == rq->curr))
-		WARN_ON(1);
 		return 0;
-	}
 
 	/*
 	 * If next_task preempts rq->curr, and rq->curr

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);
 	}

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
@@ -59,7 +59,7 @@ 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;
+static unsigned int normalized_sysctl_sched_min_granularity	= 750000ULL;
 
 /*
  * This value is kept at sysctl_sched_latency/sysctl_sched_min_granularity
@@ -82,7 +82,7 @@ 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;
+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,
+	ue.enqueued -= min_t(unsigned int, ue.enqueued, _task_util_est(p));
-			     (_task_util_est(p) | UTIL_AVG_UNCHANGED));
 	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.
+	 *   - Subtract its load from the cfs_rq->runnable_avg.
-	 *   - Substract its previous weight from cfs_rq->load.weight.
+	 *   - 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)) {
+		if (unlikely(task_on_rq_queued(p) || current == p))
-			estimated -= min_t(unsigned int, estimated,
+			lsub_positive(&estimated, _task_util_est(p));
-					   (_task_util_est(p) | UTIL_AVG_UNCHANGED));
+
-		}
 		util = max(util, estimated);
 	}
 
@@ -6332,6 +6377,213 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
 	return !task_fits_capacity(p, min_cap);
 }
 
+/*
+ * 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. */
+		if (max_spare_cap_cpu >= 0) {
+			cur_energy = compute_energy(p, max_spare_cap_cpu, head);
+			if (cur_energy < best_energy) {
+				best_energy = cur_energy;
+				best_energy_cpu = max_spare_cap_cpu;
+			}
+		}
+	}
+unlock:
+	rcu_read_unlock();
+
+	/*
+	 * Pick the best CPU if prev_cpu cannot be used, or if it saves at
+	 * least 6% of the energy used by prev_cpu.
+	 */
+	if (prev_energy == ULONG_MAX)
+		return best_energy_cpu;
+
+	if ((prev_energy - best_energy) > (prev_energy >> 4))
+		return best_energy_cpu;
+
+	return prev_cpu;
+
+fail:
+	rcu_read_unlock();
+
+	return -1;
+}
+
 /*
  * select_task_rq_fair: Select target runqueue for the waking task in domains
  * that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
@@ -6355,8 +6607,16 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 
 	if (sd_flag & SD_BALANCE_WAKE) {
 		record_wakee(p);
-		want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu)
+
-			      && cpumask_test_cpu(cpu, &p->cpus_allowed);
+		if (static_branch_unlikely(&sched_energy_present)) {
+			new_cpu = find_energy_efficient_cpu(p, prev_cpu);
+			if (new_cpu >= 0)
+				return new_cpu;
+			new_cpu = prev_cpu;
+		}
+
+		want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) &&
+			      cpumask_test_cpu(cpu, &p->cpus_allowed);
 	}
 
 	rcu_read_lock();
@@ -6520,7 +6780,7 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
 
 static void set_last_buddy(struct sched_entity *se)
 {
-	if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
+	if (entity_is_task(se) && unlikely(task_has_idle_policy(task_of(se))))
 		return;
 
 	for_each_sched_entity(se) {
@@ -6532,7 +6792,7 @@ static void set_last_buddy(struct sched_entity *se)
 
 static void set_next_buddy(struct sched_entity *se)
 {
-	if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
+	if (entity_is_task(se) && unlikely(task_has_idle_policy(task_of(se))))
 		return;
 
 	for_each_sched_entity(se) {
@@ -6590,8 +6850,8 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 		return;
 
 	/* Idle tasks are by definition preempted by non-idle tasks. */
-	if (unlikely(curr->policy == SCHED_IDLE) &&
+	if (unlikely(task_has_idle_policy(curr)) &&
-	    likely(p->policy != SCHED_IDLE))
+	    likely(!task_has_idle_policy(p)))
 		goto preempt;
 
 	/*
@@ -7012,7 +7272,7 @@ static int task_hot(struct task_struct *p, struct lb_env *env)
 	if (p->sched_class != &fair_sched_class)
 		return 0;
 
-	if (unlikely(p->policy == SCHED_IDLE))
+	if (unlikely(task_has_idle_policy(p)))
 		return 0;
 
 	/*
@@ -7896,16 +8156,16 @@ static bool update_nohz_stats(struct rq *rq, bool force)
  * update_sg_lb_stats - Update sched_group's statistics for load balancing.
  * @env: The load balancing environment.
  * @group: sched_group whose statistics are to be updated.
- * @load_idx: Load index of sched_domain of this_cpu for load calc.
- * @local_group: Does group contain this_cpu.
  * @sgs: variable to hold the statistics for this group.
- * @overload: Indicate pullable load (e.g. >1 runnable task).
+ * @sg_status: Holds flag indicating the status of the sched_group
  */
 static inline void update_sg_lb_stats(struct lb_env *env,
-			struct sched_group *group, int load_idx,
+				      struct sched_group *group,
-			int local_group, struct sg_lb_stats *sgs,
+				      struct sg_lb_stats *sgs,
-			bool *overload)
+				      int *sg_status)
 {
+	int local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(group));
+	int load_idx = get_sd_load_idx(env->sd, env->idle);
 	unsigned long load;
 	int i, nr_running;
 
@@ -7929,7 +8189,10 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 
 		nr_running = rq->nr_running;
 		if (nr_running > 1)
-			*overload = true;
+			*sg_status |= SG_OVERLOAD;
+
+		if (cpu_overutilized(i))
+			*sg_status |= SG_OVERUTILIZED;
 
 #ifdef CONFIG_NUMA_BALANCING
 		sgs->nr_numa_running += rq->nr_numa_running;
@@ -7945,7 +8208,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		if (env->sd->flags & SD_ASYM_CPUCAPACITY &&
 		    sgs->group_misfit_task_load < rq->misfit_task_load) {
 			sgs->group_misfit_task_load = rq->misfit_task_load;
-			*overload = 1;
+			*sg_status |= SG_OVERLOAD;
 		}
 	}
 
@@ -8090,17 +8353,14 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 	struct sched_group *sg = env->sd->groups;
 	struct sg_lb_stats *local = &sds->local_stat;
 	struct sg_lb_stats tmp_sgs;
-	int load_idx;
-	bool overload = false;
 	bool prefer_sibling = child && child->flags & SD_PREFER_SIBLING;
+	int sg_status = 0;
 
 #ifdef CONFIG_NO_HZ_COMMON
 	if (env->idle == CPU_NEWLY_IDLE && READ_ONCE(nohz.has_blocked))
 		env->flags |= LBF_NOHZ_STATS;
 #endif
 
-	load_idx = get_sd_load_idx(env->sd, env->idle);
-
 	do {
 		struct sg_lb_stats *sgs = &tmp_sgs;
 		int local_group;
@@ -8115,8 +8375,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 				update_group_capacity(env->sd, env->dst_cpu);
 		}
 
-		update_sg_lb_stats(env, sg, load_idx, local_group, sgs,
+		update_sg_lb_stats(env, sg, sgs, &sg_status);
-						&overload);
 
 		if (local_group)
 			goto next_group;
@@ -8165,9 +8424,15 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 		env->fbq_type = fbq_classify_group(&sds->busiest_stat);
 
 	if (!env->sd->parent) {
+		struct root_domain *rd = env->dst_rq->rd;
+
 		/* update overload indicator if we are at root domain */
-		if (READ_ONCE(env->dst_rq->rd->overload) != overload)
+		WRITE_ONCE(rd->overload, sg_status & SG_OVERLOAD);
-			WRITE_ONCE(env->dst_rq->rd->overload, overload);
+
+		/* Update over-utilization (tipping point, U >= 0) indicator */
+		WRITE_ONCE(rd->overutilized, sg_status & SG_OVERUTILIZED);
+	} else if (sg_status & SG_OVERUTILIZED) {
+		WRITE_ONCE(env->dst_rq->rd->overutilized, SG_OVERUTILIZED);
 	}
 }
 
@@ -8394,6 +8659,14 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 	 * this level.
 	 */
 	update_sd_lb_stats(env, &sds);
+
+	if (static_branch_unlikely(&sched_energy_present)) {
+		struct root_domain *rd = env->dst_rq->rd;
+
+		if (rcu_dereference(rd->pd) && !READ_ONCE(rd->overutilized))
+			goto out_balanced;
+	}
+
 	local = &sds.local_stat;
 	busiest = &sds.busiest_stat;
 
@@ -8910,13 +9183,22 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 	sd->nr_balance_failed = 0;
 
 out_one_pinned:
-	/* tune up the balancing interval */
-	if (((env.flags & LBF_ALL_PINNED) &&
-			sd->balance_interval < MAX_PINNED_INTERVAL) ||
-			(sd->balance_interval < sd->max_interval))
-		sd->balance_interval *= 2;
-
 	ld_moved = 0;
+
+	/*
+	 * idle_balance() disregards balance intervals, so we could repeatedly
+	 * reach this code, which would lead to balance_interval skyrocketting
+	 * in a short amount of time. Skip the balance_interval increase logic
+	 * to avoid that.
+	 */
+	if (env.idle == CPU_NEWLY_IDLE)
+		goto out;
+
+	/* tune up the balancing interval */
+	if ((env.flags & LBF_ALL_PINNED &&
+	     sd->balance_interval < MAX_PINNED_INTERVAL) ||
+	    sd->balance_interval < sd->max_interval)
+		sd->balance_interval *= 2;
 out:
 	return ld_moved;
 }
@@ -9281,7 +9563,7 @@ static void nohz_balancer_kick(struct rq *rq)
 		}
 	}
 
-	sd = rcu_dereference(per_cpu(sd_asym, cpu));
+	sd = rcu_dereference(per_cpu(sd_asym_packing, cpu));
 	if (sd) {
 		for_each_cpu(i, sched_domain_span(sd)) {
 			if (i == cpu ||
@@ -9783,6 +10065,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
 		task_tick_numa(rq, curr);
 
 	update_misfit_status(curr, rq);
+	update_overutilized_status(task_rq(curr));
 }
 
 /*

kernel/sched/isolation.c

@@ -8,14 +8,14 @@
  */
 #include "sched.h"
 
-DEFINE_STATIC_KEY_FALSE(housekeeping_overriden);
+DEFINE_STATIC_KEY_FALSE(housekeeping_overridden);
-EXPORT_SYMBOL_GPL(housekeeping_overriden);
+EXPORT_SYMBOL_GPL(housekeeping_overridden);
 static cpumask_var_t housekeeping_mask;
 static unsigned int housekeeping_flags;
 
 int housekeeping_any_cpu(enum hk_flags flags)
 {
-	if (static_branch_unlikely(&housekeeping_overriden))
+	if (static_branch_unlikely(&housekeeping_overridden))
 		if (housekeeping_flags & flags)
 			return cpumask_any_and(housekeeping_mask, cpu_online_mask);
 	return smp_processor_id();
@@ -24,7 +24,7 @@ EXPORT_SYMBOL_GPL(housekeeping_any_cpu);
 
 const struct cpumask *housekeeping_cpumask(enum hk_flags flags)
 {
-	if (static_branch_unlikely(&housekeeping_overriden))
+	if (static_branch_unlikely(&housekeeping_overridden))
 		if (housekeeping_flags & flags)
 			return housekeeping_mask;
 	return cpu_possible_mask;
@@ -33,7 +33,7 @@ EXPORT_SYMBOL_GPL(housekeeping_cpumask);
 
 void housekeeping_affine(struct task_struct *t, enum hk_flags flags)
 {
-	if (static_branch_unlikely(&housekeeping_overriden))
+	if (static_branch_unlikely(&housekeeping_overridden))
 		if (housekeeping_flags & flags)
 			set_cpus_allowed_ptr(t, housekeeping_mask);
 }
@@ -41,7 +41,7 @@ EXPORT_SYMBOL_GPL(housekeeping_affine);
 
 bool housekeeping_test_cpu(int cpu, enum hk_flags flags)
 {
-	if (static_branch_unlikely(&housekeeping_overriden))
+	if (static_branch_unlikely(&housekeeping_overridden))
 		if (housekeeping_flags & flags)
 			return cpumask_test_cpu(cpu, housekeeping_mask);
 	return true;
@@ -53,7 +53,7 @@ void __init housekeeping_init(void)
 	if (!housekeeping_flags)
 		return;
 
-	static_branch_enable(&housekeeping_overriden);
+	static_branch_enable(&housekeeping_overridden);
 
 	if (housekeeping_flags & HK_FLAG_TICK)
 		sched_tick_offload_init();

kernel/sched/rt.c

@@ -1498,6 +1498,14 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag
 #endif
 }
 
+static inline void set_next_task(struct rq *rq, struct task_struct *p)
+{
+	p->se.exec_start = rq_clock_task(rq);
+
+	/* The running task is never eligible for pushing */
+	dequeue_pushable_task(rq, p);
+}
+
 static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
 						   struct rt_rq *rt_rq)
 {
@@ -1518,7 +1526,6 @@ static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
 static struct task_struct *_pick_next_task_rt(struct rq *rq)
 {
 	struct sched_rt_entity *rt_se;
-	struct task_struct *p;
 	struct rt_rq *rt_rq  = &rq->rt;
 
 	do {
@@ -1527,10 +1534,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
 		rt_rq = group_rt_rq(rt_se);
 	} while (rt_rq);
 
-	p = rt_task_of(rt_se);
+	return rt_task_of(rt_se);
-	p->se.exec_start = rq_clock_task(rq);
-
-	return p;
 }
 
 static struct task_struct *
@@ -1573,8 +1577,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 	p = _pick_next_task_rt(rq);
 
-	/* The running task is never eligible for pushing */
+	set_next_task(rq, p);
-	dequeue_pushable_task(rq, p);
 
 	rt_queue_push_tasks(rq);
 
@@ -1810,10 +1813,8 @@ static int push_rt_task(struct rq *rq)
 		return 0;
 
 retry:
-	if (unlikely(next_task == rq->curr)) {
+	if (WARN_ON(next_task == rq->curr))
-		WARN_ON(1);
 		return 0;
-	}
 
 	/*
 	 * It's possible that the next_task slipped in of
@@ -2355,12 +2356,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
 
 static void set_curr_task_rt(struct rq *rq)
 {
-	struct task_struct *p = rq->curr;
+	set_next_task(rq, rq->curr);
-
-	p->se.exec_start = rq_clock_task(rq);
-
-	/* The running task is never eligible for pushing */
-	dequeue_pushable_task(rq, p);
 }
 
 static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)

kernel/sched/sched.h

@@ -45,6 +45,7 @@
 #include <linux/ctype.h>
 #include <linux/debugfs.h>
 #include <linux/delayacct.h>
+#include <linux/energy_model.h>
 #include <linux/init_task.h>
 #include <linux/kprobes.h>
 #include <linux/kthread.h>
@@ -177,6 +178,11 @@ static inline bool valid_policy(int policy)
 		rt_policy(policy) || dl_policy(policy);
 }
 
+static inline int task_has_idle_policy(struct task_struct *p)
+{
+	return idle_policy(p->policy);
+}
+
 static inline int task_has_rt_policy(struct task_struct *p)
 {
 	return rt_policy(p->policy);
@@ -632,7 +638,7 @@ struct dl_rq {
 	/*
 	 * Deadline values of the currently executing and the
 	 * earliest ready task on this rq. Caching these facilitates
-	 * the decision wether or not a ready but not running task
+	 * the decision whether or not a ready but not running task
 	 * should migrate somewhere else.
 	 */
 	struct {
@@ -704,6 +710,16 @@ static inline bool sched_asym_prefer(int a, int b)
 	return arch_asym_cpu_priority(a) > arch_asym_cpu_priority(b);
 }
 
+struct perf_domain {
+	struct em_perf_domain *em_pd;
+	struct perf_domain *next;
+	struct rcu_head rcu;
+};
+
+/* Scheduling group status flags */
+#define SG_OVERLOAD		0x1 /* More than one runnable task on a CPU. */
+#define SG_OVERUTILIZED		0x2 /* One or more CPUs are over-utilized. */
+
 /*
  * We add the notion of a root-domain which will be used to define per-domain
  * variables. Each exclusive cpuset essentially defines an island domain by
@@ -726,6 +742,9 @@ struct root_domain {
 	 */
 	int			overload;
 
+	/* Indicate one or more cpus over-utilized (tipping point) */
+	int			overutilized;
+
 	/*
 	 * The bit corresponding to a CPU gets set here if such CPU has more
 	 * than one runnable -deadline task (as it is below for RT tasks).
@@ -756,6 +775,12 @@ struct root_domain {
 	struct cpupri		cpupri;
 
 	unsigned long		max_cpu_capacity;
+
+	/*
+	 * NULL-terminated list of performance domains intersecting with the
+	 * CPUs of the rd. Protected by RCU.
+	 */
+	struct perf_domain	*pd;
 };
 
 extern struct root_domain def_root_domain;
@@ -1285,7 +1310,8 @@ DECLARE_PER_CPU(int, sd_llc_size);
 DECLARE_PER_CPU(int, sd_llc_id);
 DECLARE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
 DECLARE_PER_CPU(struct sched_domain *, sd_numa);
-DECLARE_PER_CPU(struct sched_domain *, sd_asym);
+DECLARE_PER_CPU(struct sched_domain *, sd_asym_packing);
+DECLARE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity);
 extern struct static_key_false sched_asym_cpucapacity;
 
 struct sched_group_capacity {
@@ -1429,7 +1455,7 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
 #ifdef CONFIG_SMP
 	/*
 	 * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be
-	 * successfuly executed on another CPU. We must ensure that updates of
+	 * successfully executed on another CPU. We must ensure that updates of
 	 * per-task data have been completed by this moment.
 	 */
 	smp_wmb();
@@ -1794,12 +1820,12 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
 
 	rq->nr_running = prev_nr + count;
 
-	if (prev_nr < 2 && rq->nr_running >= 2) {
 #ifdef CONFIG_SMP
+	if (prev_nr < 2 && rq->nr_running >= 2) {
 		if (!READ_ONCE(rq->rd->overload))
 			WRITE_ONCE(rq->rd->overload, 1);
-#endif
 	}
+#endif
 
 	sched_update_tick_dependency(rq);
 }
@@ -1854,27 +1880,6 @@ unsigned long arch_scale_freq_capacity(int cpu)
 }
 #endif
 
-#ifdef CONFIG_SMP
-#ifndef arch_scale_cpu_capacity
-static __always_inline
-unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
-{
-	if (sd && (sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1))
-		return sd->smt_gain / sd->span_weight;
-
-	return SCHED_CAPACITY_SCALE;
-}
-#endif
-#else
-#ifndef arch_scale_cpu_capacity
-static __always_inline
-unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu)
-{
-	return SCHED_CAPACITY_SCALE;
-}
-#endif
-#endif
-
 #ifdef CONFIG_SMP
 #ifdef CONFIG_PREEMPT
 
@@ -2207,6 +2212,31 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #endif
 
 #ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
+/**
+ * enum schedutil_type - CPU utilization type
+ * @FREQUENCY_UTIL:	Utilization used to select frequency
+ * @ENERGY_UTIL:	Utilization used during energy calculation
+ *
+ * The utilization signals of all scheduling classes (CFS/RT/DL) and IRQ time
+ * need to be aggregated differently depending on the usage made of them. This
+ * enum is used within schedutil_freq_util() to differentiate the types of
+ * utilization expected by the callers, and adjust the aggregation accordingly.
+ */
+enum schedutil_type {
+	FREQUENCY_UTIL,
+	ENERGY_UTIL,
+};
+
+unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs,
+				  unsigned long max, enum schedutil_type type);
+
+static inline unsigned long schedutil_energy_util(int cpu, unsigned long cfs)
+{
+	unsigned long max = arch_scale_cpu_capacity(NULL, cpu);
+
+	return schedutil_freq_util(cpu, cfs, max, ENERGY_UTIL);
+}
+
 static inline unsigned long cpu_bw_dl(struct rq *rq)
 {
 	return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT;
@@ -2233,6 +2263,11 @@ static inline unsigned long cpu_util_rt(struct rq *rq)
 {
 	return READ_ONCE(rq->avg_rt.util_avg);
 }
+#else /* CONFIG_CPU_FREQ_GOV_SCHEDUTIL */
+static inline unsigned long schedutil_energy_util(int cpu, unsigned long cfs)
+{
+	return cfs;
+}
 #endif
 
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
@@ -2262,3 +2297,13 @@ unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned
 	return util;
 }
 #endif
+
+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
+#define perf_domain_span(pd) (to_cpumask(((pd)->em_pd->cpus)))
+#else
+#define perf_domain_span(pd) NULL
+#endif
+
+#ifdef CONFIG_SMP
+extern struct static_key_false sched_energy_present;
+#endif

kernel/sched/topology.c

@@ -201,6 +201,199 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 	return 1;
 }
 
+DEFINE_STATIC_KEY_FALSE(sched_energy_present);
+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
+DEFINE_MUTEX(sched_energy_mutex);
+bool sched_energy_update;
+
+static void free_pd(struct perf_domain *pd)
+{
+	struct perf_domain *tmp;
+
+	while (pd) {
+		tmp = pd->next;
+		kfree(pd);
+		pd = tmp;
+	}
+}
+
+static struct perf_domain *find_pd(struct perf_domain *pd, int cpu)
+{
+	while (pd) {
+		if (cpumask_test_cpu(cpu, perf_domain_span(pd)))
+			return pd;
+		pd = pd->next;
+	}
+
+	return NULL;
+}
+
+static struct perf_domain *pd_init(int cpu)
+{
+	struct em_perf_domain *obj = em_cpu_get(cpu);
+	struct perf_domain *pd;
+
+	if (!obj) {
+		if (sched_debug())
+			pr_info("%s: no EM found for CPU%d\n", __func__, cpu);
+		return NULL;
+	}
+
+	pd = kzalloc(sizeof(*pd), GFP_KERNEL);
+	if (!pd)
+		return NULL;
+	pd->em_pd = obj;
+
+	return pd;
+}
+
+static void perf_domain_debug(const struct cpumask *cpu_map,
+						struct perf_domain *pd)
+{
+	if (!sched_debug() || !pd)
+		return;
+
+	printk(KERN_DEBUG "root_domain %*pbl:", cpumask_pr_args(cpu_map));
+
+	while (pd) {
+		printk(KERN_CONT " pd%d:{ cpus=%*pbl nr_cstate=%d }",
+				cpumask_first(perf_domain_span(pd)),
+				cpumask_pr_args(perf_domain_span(pd)),
+				em_pd_nr_cap_states(pd->em_pd));
+		pd = pd->next;
+	}
+
+	printk(KERN_CONT "\n");
+}
+
+static void destroy_perf_domain_rcu(struct rcu_head *rp)
+{
+	struct perf_domain *pd;
+
+	pd = container_of(rp, struct perf_domain, rcu);
+	free_pd(pd);
+}
+
+static void sched_energy_set(bool has_eas)
+{
+	if (!has_eas && static_branch_unlikely(&sched_energy_present)) {
+		if (sched_debug())
+			pr_info("%s: stopping EAS\n", __func__);
+		static_branch_disable_cpuslocked(&sched_energy_present);
+	} else if (has_eas && !static_branch_unlikely(&sched_energy_present)) {
+		if (sched_debug())
+			pr_info("%s: starting EAS\n", __func__);
+		static_branch_enable_cpuslocked(&sched_energy_present);
+	}
+}
+
+/*
+ * EAS can be used on a root domain if it meets all the following conditions:
+ *    1. an Energy Model (EM) is available;
+ *    2. the SD_ASYM_CPUCAPACITY flag is set in the sched_domain hierarchy.
+ *    3. the EM complexity is low enough to keep scheduling overheads low;
+ *    4. schedutil is driving the frequency of all CPUs of the rd;
+ *
+ * The complexity of the Energy Model is defined as:
+ *
+ *              C = nr_pd * (nr_cpus + nr_cs)
+ *
+ * with parameters defined as:
+ *  - nr_pd:    the number of performance domains
+ *  - nr_cpus:  the number of CPUs
+ *  - nr_cs:    the sum of the number of capacity states of all performance
+ *              domains (for example, on a system with 2 performance domains,
+ *              with 10 capacity states each, nr_cs = 2 * 10 = 20).
+ *
+ * It is generally not a good idea to use such a model in the wake-up path on
+ * very complex platforms because of the associated scheduling overheads. The
+ * arbitrary constraint below prevents that. It makes EAS usable up to 16 CPUs
+ * with per-CPU DVFS and less than 8 capacity states each, for example.
+ */
+#define EM_MAX_COMPLEXITY 2048
+
+extern struct cpufreq_governor schedutil_gov;
+static bool build_perf_domains(const struct cpumask *cpu_map)
+{
+	int i, nr_pd = 0, nr_cs = 0, nr_cpus = cpumask_weight(cpu_map);
+	struct perf_domain *pd = NULL, *tmp;
+	int cpu = cpumask_first(cpu_map);
+	struct root_domain *rd = cpu_rq(cpu)->rd;
+	struct cpufreq_policy *policy;
+	struct cpufreq_governor *gov;
+
+	/* EAS is enabled for asymmetric CPU capacity topologies. */
+	if (!per_cpu(sd_asym_cpucapacity, cpu)) {
+		if (sched_debug()) {
+			pr_info("rd %*pbl: CPUs do not have asymmetric capacities\n",
+					cpumask_pr_args(cpu_map));
+		}
+		goto free;
+	}
+
+	for_each_cpu(i, cpu_map) {
+		/* Skip already covered CPUs. */
+		if (find_pd(pd, i))
+			continue;
+
+		/* Do not attempt EAS if schedutil is not being used. */
+		policy = cpufreq_cpu_get(i);
+		if (!policy)
+			goto free;
+		gov = policy->governor;
+		cpufreq_cpu_put(policy);
+		if (gov != &schedutil_gov) {
+			if (rd->pd)
+				pr_warn("rd %*pbl: Disabling EAS, schedutil is mandatory\n",
+						cpumask_pr_args(cpu_map));
+			goto free;
+		}
+
+		/* Create the new pd and add it to the local list. */
+		tmp = pd_init(i);
+		if (!tmp)
+			goto free;
+		tmp->next = pd;
+		pd = tmp;
+
+		/*
+		 * Count performance domains and capacity states for the
+		 * complexity check.
+		 */
+		nr_pd++;
+		nr_cs += em_pd_nr_cap_states(pd->em_pd);
+	}
+
+	/* Bail out if the Energy Model complexity is too high. */
+	if (nr_pd * (nr_cs + nr_cpus) > EM_MAX_COMPLEXITY) {
+		WARN(1, "rd %*pbl: Failed to start EAS, EM complexity is too high\n",
+						cpumask_pr_args(cpu_map));
+		goto free;
+	}
+
+	perf_domain_debug(cpu_map, pd);
+
+	/* Attach the new list of performance domains to the root domain. */
+	tmp = rd->pd;
+	rcu_assign_pointer(rd->pd, pd);
+	if (tmp)
+		call_rcu(&tmp->rcu, destroy_perf_domain_rcu);
+
+	return !!pd;
+
+free:
+	free_pd(pd);
+	tmp = rd->pd;
+	rcu_assign_pointer(rd->pd, NULL);
+	if (tmp)
+		call_rcu(&tmp->rcu, destroy_perf_domain_rcu);
+
+	return false;
+}
+#else
+static void free_pd(struct perf_domain *pd) { }
+#endif /* CONFIG_ENERGY_MODEL && CONFIG_CPU_FREQ_GOV_SCHEDUTIL*/
+
 static void free_rootdomain(struct rcu_head *rcu)
 {
 	struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
@@ -211,6 +404,7 @@ static void free_rootdomain(struct rcu_head *rcu)
 	free_cpumask_var(rd->rto_mask);
 	free_cpumask_var(rd->online);
 	free_cpumask_var(rd->span);
+	free_pd(rd->pd);
 	kfree(rd);
 }
 
@@ -397,7 +591,8 @@ DEFINE_PER_CPU(int, sd_llc_size);
 DEFINE_PER_CPU(int, sd_llc_id);
 DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
 DEFINE_PER_CPU(struct sched_domain *, sd_numa);
-DEFINE_PER_CPU(struct sched_domain *, sd_asym);
+DEFINE_PER_CPU(struct sched_domain *, sd_asym_packing);
+DEFINE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity);
 DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);
 
 static void update_top_cache_domain(int cpu)
@@ -423,7 +618,10 @@ static void update_top_cache_domain(int cpu)
 	rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
 
 	sd = highest_flag_domain(cpu, SD_ASYM_PACKING);
-	rcu_assign_pointer(per_cpu(sd_asym, cpu), sd);
+	rcu_assign_pointer(per_cpu(sd_asym_packing, cpu), sd);
+
+	sd = lowest_flag_domain(cpu, SD_ASYM_CPUCAPACITY);
+	rcu_assign_pointer(per_cpu(sd_asym_cpucapacity, cpu), sd);
 }
 
 /*
@@ -1133,7 +1331,6 @@ sd_init(struct sched_domain_topology_level *tl,
 
 		.last_balance		= jiffies,
 		.balance_interval	= sd_weight,
-		.smt_gain		= 0,
 		.max_newidle_lb_cost	= 0,
 		.next_decay_max_lb_cost	= jiffies,
 		.child			= child,
@@ -1164,7 +1361,6 @@ sd_init(struct sched_domain_topology_level *tl,
 
 	if (sd->flags & SD_SHARE_CPUCAPACITY) {
 		sd->imbalance_pct = 110;
-		sd->smt_gain = 1178; /* ~15% */
 
 	} else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
 		sd->imbalance_pct = 117;
@@ -1934,6 +2130,7 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
 void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 			     struct sched_domain_attr *dattr_new)
 {
+	bool __maybe_unused has_eas = false;
 	int i, j, n;
 	int new_topology;
 
@@ -1961,8 +2158,8 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 	/* Destroy deleted domains: */
 	for (i = 0; i < ndoms_cur; i++) {
 		for (j = 0; j < n && !new_topology; j++) {
-			if (cpumask_equal(doms_cur[i], doms_new[j])
+			if (cpumask_equal(doms_cur[i], doms_new[j]) &&
-			    && dattrs_equal(dattr_cur, i, dattr_new, j))
+			    dattrs_equal(dattr_cur, i, dattr_new, j))
 				goto match1;
 		}
 		/* No match - a current sched domain not in new doms_new[] */
@@ -1982,8 +2179,8 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 	/* Build new domains: */
 	for (i = 0; i < ndoms_new; i++) {
 		for (j = 0; j < n && !new_topology; j++) {
-			if (cpumask_equal(doms_new[i], doms_cur[j])
+			if (cpumask_equal(doms_new[i], doms_cur[j]) &&
-			    && dattrs_equal(dattr_new, i, dattr_cur, j))
+			    dattrs_equal(dattr_new, i, dattr_cur, j))
 				goto match2;
 		}
 		/* No match - add a new doms_new */
@@ -1992,6 +2189,24 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 		;
 	}
 
+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
+	/* Build perf. domains: */
+	for (i = 0; i < ndoms_new; i++) {
+		for (j = 0; j < n && !sched_energy_update; j++) {
+			if (cpumask_equal(doms_new[i], doms_cur[j]) &&
+			    cpu_rq(cpumask_first(doms_cur[j]))->rd->pd) {
+				has_eas = true;
+				goto match3;
+			}
+		}
+		/* No match - add perf. domains for a new rd */
+		has_eas |= build_perf_domains(doms_new[i]);
+match3:
+		;
+	}
+	sched_energy_set(has_eas);
+#endif
+
 	/* Remember the new sched domains: */
 	if (doms_cur != &fallback_doms)
 		free_sched_domains(doms_cur, ndoms_cur);