Merging upstream version 6.10.3.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

15 files changed, 416 insertions, 365 deletions

diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c
index 991fc90025..db68a964e3 100644
--- a/kernel/sched/autogroup.c
+++ b/kernel/sched/autogroup.c
@@ -19,7 +19,6 @@ static struct ctl_table sched_autogroup_sysctls[] = {
 		.extra1         = SYSCTL_ZERO,
 		.extra2         = SYSCTL_ONE,
 	},
-	{}
 };
 
 static void __init sched_autogroup_sysctl_init(void)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d211d40a2e..ebf21373f6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -108,7 +108,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_rt_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_dl_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp);
-EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_thermal_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_hw_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_cpu_capacity_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp);
@@ -723,7 +723,6 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 
 	rq->prev_irq_time += irq_delta;
 	delta -= irq_delta;
-	psi_account_irqtime(rq->curr, irq_delta);
 	delayacct_irq(rq->curr, irq_delta);
 #endif
 #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
@@ -1327,27 +1326,24 @@ int tg_nop(struct task_group *tg, void *data)
 static void set_load_weight(struct task_struct *p, bool update_load)
 {
 	int prio = p->static_prio - MAX_RT_PRIO;
-	struct load_weight *load = &p->se.load;
+	struct load_weight lw;
 
-	/*
-	 * SCHED_IDLE tasks get minimal weight:
-	 */
 	if (task_has_idle_policy(p)) {
-		load->weight = scale_load(WEIGHT_IDLEPRIO);
-		load->inv_weight = WMULT_IDLEPRIO;
-		return;
+		lw.weight = scale_load(WEIGHT_IDLEPRIO);
+		lw.inv_weight = WMULT_IDLEPRIO;
+	} else {
+		lw.weight = scale_load(sched_prio_to_weight[prio]);
+		lw.inv_weight = sched_prio_to_wmult[prio];
 	}
 
 	/*
 	 * SCHED_OTHER tasks have to update their load when changing their
 	 * weight
 	 */
-	if (update_load && p->sched_class == &fair_sched_class) {
-		reweight_task(p, prio);
-	} else {
-		load->weight = scale_load(sched_prio_to_weight[prio]);
-		load->inv_weight = sched_prio_to_wmult[prio];
-	}
+	if (update_load && p->sched_class == &fair_sched_class)
+		reweight_task(p, &lw);
+	else
+		p->se.load = lw;
 }
 
 #ifdef CONFIG_UCLAMP_TASK
@@ -4467,12 +4463,7 @@ int task_call_func(struct task_struct *p, task_call_f func, void *arg)
  * @cpu: The CPU on which to snapshot the task.
  *
  * Returns the task_struct pointer of the task "currently" running on
- * the specified CPU.  If the same task is running on that CPU throughout,
- * the return value will be a pointer to that task's task_struct structure.
- * If the CPU did any context switches even vaguely concurrently with the
- * execution of this function, the return value will be a pointer to the
- * task_struct structure of a randomly chosen task that was running on
- * that CPU somewhere around the time that this function was executing.
+ * the specified CPU.
  *
  * If the specified CPU was offline, the return value is whatever it
  * is, perhaps a pointer to the task_struct structure of that CPU's idle
@@ -4486,11 +4477,16 @@ int task_call_func(struct task_struct *p, task_call_f func, void *arg)
  */
 struct task_struct *cpu_curr_snapshot(int cpu)
 {
+	struct rq *rq = cpu_rq(cpu);
 	struct task_struct *t;
+	struct rq_flags rf;
 
-	smp_mb(); /* Pairing determined by caller's synchronization design. */
+	rq_lock_irqsave(rq, &rf);
+	smp_mb__after_spinlock(); /* Pairing determined by caller's synchronization design. */
 	t = rcu_dereference(cpu_curr(cpu));
+	rq_unlock_irqrestore(rq, &rf);
 	smp_mb(); /* Pairing determined by caller's synchronization design. */
+
 	return t;
 }
 
@@ -4741,7 +4737,6 @@ static struct ctl_table sched_core_sysctls[] = {
 		.extra2		= SYSCTL_FOUR,
 	},
 #endif /* CONFIG_NUMA_BALANCING */
-	{}
 };
 static int __init sched_core_sysctl_init(void)
 {
@@ -5662,13 +5657,13 @@ static inline u64 cpu_resched_latency(struct rq *rq) { return 0; }
  * This function gets called by the timer code, with HZ frequency.
  * We call it with interrupts disabled.
  */
-void scheduler_tick(void)
+void sched_tick(void)
 {
 	int cpu = smp_processor_id();
 	struct rq *rq = cpu_rq(cpu);
-	struct task_struct *curr = rq->curr;
+	struct task_struct *curr;
 	struct rq_flags rf;
-	unsigned long thermal_pressure;
+	unsigned long hw_pressure;
 	u64 resched_latency;
 
 	if (housekeeping_cpu(cpu, HK_TYPE_TICK))
@@ -5678,9 +5673,12 @@ void scheduler_tick(void)
 
 	rq_lock(rq, &rf);
 
+	curr = rq->curr;
+	psi_account_irqtime(rq, curr, NULL);
+
 	update_rq_clock(rq);
-	thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq));
-	update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure);
+	hw_pressure = arch_scale_hw_pressure(cpu_of(rq));
+	update_hw_load_avg(rq_clock_task(rq), rq, hw_pressure);
 	curr->sched_class->task_tick(rq, curr, 0);
 	if (sched_feat(LATENCY_WARN))
 		resched_latency = cpu_resched_latency(rq);
@@ -5700,7 +5698,7 @@ void scheduler_tick(void)
 
 #ifdef CONFIG_SMP
 	rq->idle_balance = idle_cpu(cpu);
-	trigger_load_balance(rq);
+	sched_balance_trigger(rq);
 #endif
 }
 
@@ -6585,7 +6583,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
  *      paths. For example, see arch/x86/entry_64.S.
  *
  *      To drive preemption between tasks, the scheduler sets the flag in timer
- *      interrupt handler scheduler_tick().
+ *      interrupt handler sched_tick().
  *
  *   3. Wakeups don't really cause entry into schedule(). They add a
  *      task to the run-queue and that's it.
@@ -6738,6 +6736,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 		++*switch_count;
 
 		migrate_disable_switch(rq, prev);
+		psi_account_irqtime(rq, prev, next);
 		psi_sched_switch(prev, next, !task_on_rq_queued(prev));
 
 		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next, prev_state);
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index af7952f12e..aa48b2ec87 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -424,19 +424,6 @@ static inline void irqtime_account_process_tick(struct task_struct *p, int user_
  */
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 
-# ifndef __ARCH_HAS_VTIME_TASK_SWITCH
-void vtime_task_switch(struct task_struct *prev)
-{
-	if (is_idle_task(prev))
-		vtime_account_idle(prev);
-	else
-		vtime_account_kernel(prev);
-
-	vtime_flush(prev);
-	arch_vtime_task_switch(prev);
-}
-# endif
-
 void vtime_account_irq(struct task_struct *tsk, unsigned int offset)
 {
 	unsigned int pc = irq_count() - offset;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index dce51bf2d3..9bedd148f0 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -43,7 +43,6 @@ static struct ctl_table sched_dl_sysctls[] = {
 		.proc_handler   = proc_douintvec_minmax,
 		.extra2         = (void *)&sysctl_sched_dl_period_max,
 	},
-	{}
 };
 
 static int __init sched_dl_sysctl_init(void)
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 8d5d98a583..c1eb9a1afd 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -425,6 +425,7 @@ static void register_sd(struct sched_domain *sd, struct dentry *parent)
 
 	debugfs_create_file("flags", 0444, parent, &sd->flags, &sd_flags_fops);
 	debugfs_create_file("groups_flags", 0444, parent, &sd->groups->flags, &sd_flags_fops);
+	debugfs_create_u32("level", 0444, parent, (u32 *)&sd->level);
 }
 
 void update_sched_domain_debugfs(void)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 98d03b34a8..483c137b9d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -78,15 +78,9 @@ static unsigned int normalized_sysctl_sched_base_slice	= 750000ULL;
 
 const_debug unsigned int sysctl_sched_migration_cost	= 500000UL;
 
-int sched_thermal_decay_shift;
 static int __init setup_sched_thermal_decay_shift(char *str)
 {
-	int _shift = 0;
-
-	if (kstrtoint(str, 0, &_shift))
-		pr_warn("Unable to set scheduler thermal pressure decay shift parameter\n");
-
-	sched_thermal_decay_shift = clamp(_shift, 0, 10);
+	pr_warn("Ignoring the deprecated sched_thermal_decay_shift= option\n");
 	return 1;
 }
 __setup("sched_thermal_decay_shift=", setup_sched_thermal_decay_shift);
@@ -157,7 +151,6 @@ static struct ctl_table sched_fair_sysctls[] = {
 		.extra1		= SYSCTL_ZERO,
 	},
 #endif /* CONFIG_NUMA_BALANCING */
-	{}
 };
 
 static int __init sched_fair_sysctl_init(void)
@@ -388,8 +381,8 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 
 		/*
 		 * With cfs_rq being unthrottled/throttled during an enqueue,
-		 * it can happen the tmp_alone_branch points the a leaf that
-		 * we finally want to del. In this case, tmp_alone_branch moves
+		 * it can happen the tmp_alone_branch points to the leaf that
+		 * we finally want to delete. In this case, tmp_alone_branch moves
 		 * to the prev element but it will point to rq->leaf_cfs_rq_list
 		 * at the end of the enqueue.
 		 */
@@ -406,7 +399,7 @@ static inline void assert_list_leaf_cfs_rq(struct rq *rq)
 	SCHED_WARN_ON(rq->tmp_alone_branch != &rq->leaf_cfs_rq_list);
 }
 
-/* Iterate thr' all leaf cfs_rq's on a runqueue */
+/* Iterate through all leaf cfs_rq's on a runqueue */
 #define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos)			\
 	list_for_each_entry_safe(cfs_rq, pos, &rq->leaf_cfs_rq_list,	\
 				 leaf_cfs_rq_list)
@@ -595,13 +588,13 @@ static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
  *
  * [[ NOTE: this is only equal to the ideal scheduler under the condition
  *          that join/leave operations happen at lag_i = 0, otherwise the
- *          virtual time has non-continguous motion equivalent to:
+ *          virtual time has non-contiguous motion equivalent to:
  *
  *	      V +-= lag_i / W
  *
  *	    Also see the comment in place_entity() that deals with this. ]]
  *
- * However, since v_i is u64, and the multiplcation could easily overflow
+ * However, since v_i is u64, and the multiplication could easily overflow
  * transform it into a relative form that uses smaller quantities:
  *
  * Substitute: v_i == (v_i - v0) + v0
@@ -671,7 +664,7 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq)
 	}
 
 	if (load) {
-		/* sign flips effective floor / ceil */
+		/* sign flips effective floor / ceiling */
 		if (avg < 0)
 			avg -= (load - 1);
 		avg = div_s64(avg, load);
@@ -727,7 +720,7 @@ static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
  *
  * lag_i >= 0 -> \Sum (v_i - v)*w_i >= (v_i - v)*(\Sum w_i)
  *
- * Note: using 'avg_vruntime() > se->vruntime' is inacurate due
+ * Note: using 'avg_vruntime() > se->vruntime' is inaccurate due
  *       to the loss in precision caused by the division.
  */
 static int vruntime_eligible(struct cfs_rq *cfs_rq, u64 vruntime)
@@ -1030,14 +1023,15 @@ void init_entity_runnable_average(struct sched_entity *se)
 	if (entity_is_task(se))
 		sa->load_avg = scale_load_down(se->load.weight);
 
-	/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
+	/* when this task is enqueued, it will contribute to its cfs_rq's load_avg */
 }
 
 /*
  * With new tasks being created, their initial util_avgs are extrapolated
  * based on the cfs_rq's current util_avg:
  *
- *   util_avg = cfs_rq->util_avg / (cfs_rq->load_avg + 1) * se.load.weight
+ *   util_avg = cfs_rq->avg.util_avg / (cfs_rq->avg.load_avg + 1)
+ *		* se_weight(se)
  *
  * However, in many cases, the above util_avg does not give a desired
  * value. Moreover, the sum of the util_avgs may be divergent, such
@@ -1084,7 +1078,7 @@ void post_init_entity_util_avg(struct task_struct *p)
 
 	if (cap > 0) {
 		if (cfs_rq->avg.util_avg != 0) {
-			sa->util_avg  = cfs_rq->avg.util_avg * se->load.weight;
+			sa->util_avg  = cfs_rq->avg.util_avg * se_weight(se);
 			sa->util_avg /= (cfs_rq->avg.load_avg + 1);
 
 			if (sa->util_avg > cap)
@@ -1622,7 +1616,7 @@ static unsigned long score_nearby_nodes(struct task_struct *p, int nid,
 	max_dist = READ_ONCE(sched_max_numa_distance);
 	/*
 	 * This code is called for each node, introducing N^2 complexity,
-	 * which should be ok given the number of nodes rarely exceeds 8.
+	 * which should be OK given the number of nodes rarely exceeds 8.
 	 */
 	for_each_online_node(node) {
 		unsigned long faults;
@@ -3296,7 +3290,7 @@ retry_pids:
 		/*
 		 * Shared library pages mapped by multiple processes are not
 		 * migrated as it is expected they are cache replicated. Avoid
-		 * hinting faults in read-only file-backed mappings or the vdso
+		 * hinting faults in read-only file-backed mappings or the vDSO
 		 * as migrating the pages will be of marginal benefit.
 		 */
 		if (!vma->vm_mm ||
@@ -3307,7 +3301,7 @@ retry_pids:
 
 		/*
 		 * Skip inaccessible VMAs to avoid any confusion between
-		 * PROT_NONE and NUMA hinting ptes
+		 * PROT_NONE and NUMA hinting PTEs
 		 */
 		if (!vma_is_accessible(vma)) {
 			trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_INACCESSIBLE);
@@ -3339,7 +3333,7 @@ retry_pids:
 		}
 
 		/*
-		 * Scanning the VMA's of short lived tasks add more overhead. So
+		 * Scanning the VMAs of short lived tasks add more overhead. So
 		 * delay the scan for new VMAs.
 		 */
 		if (mm->numa_scan_seq && time_before(jiffies,
@@ -3383,7 +3377,7 @@ retry_pids:
 			/*
 			 * Try to scan sysctl_numa_balancing_size worth of
 			 * hpages that have at least one present PTE that
-			 * is not already pte-numa. If the VMA contains
+			 * is not already PTE-numa. If the VMA contains
 			 * areas that are unused or already full of prot_numa
 			 * PTEs, scan up to virtpages, to skip through those
 			 * areas faster.
@@ -3690,7 +3684,7 @@ static void reweight_eevdf(struct sched_entity *se, u64 avruntime,
 
 	/*
 	 * VRUNTIME
-	 * ========
+	 * --------
 	 *
 	 * COROLLARY #1: The virtual runtime of the entity needs to be
 	 * adjusted if re-weight at !0-lag point.
@@ -3773,7 +3767,7 @@ static void reweight_eevdf(struct sched_entity *se, u64 avruntime,
 
 	/*
 	 * DEADLINE
-	 * ========
+	 * --------
 	 *
 	 * When the weight changes, the virtual time slope changes and
 	 * we should adjust the relative virtual deadline accordingly.
@@ -3841,15 +3835,14 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 	}
 }
 
-void reweight_task(struct task_struct *p, int prio)
+void reweight_task(struct task_struct *p, const struct load_weight *lw)
 {
 	struct sched_entity *se = &p->se;
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 	struct load_weight *load = &se->load;
-	unsigned long weight = scale_load(sched_prio_to_weight[prio]);
 
-	reweight_entity(cfs_rq, se, weight);
-	load->inv_weight = sched_prio_to_wmult[prio];
+	reweight_entity(cfs_rq, se, lw->weight);
+	load->inv_weight = lw->inv_weight;
 }
 
 static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
@@ -4745,7 +4738,7 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 
 	/*
 	 * Track task load average for carrying it to new CPU after migrated, and
-	 * track group sched_entity load average for task_h_load calc in migration
+	 * track group sched_entity load average for task_h_load calculation in migration
 	 */
 	if (se->avg.last_update_time && !(flags & SKIP_AGE_LOAD))
 		__update_load_avg_se(now, cfs_rq, se);
@@ -4828,7 +4821,7 @@ static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq)
 	return cfs_rq->avg.load_avg;
 }
 
-static int newidle_balance(struct rq *this_rq, struct rq_flags *rf);
+static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf);
 
 static inline unsigned long task_util(struct task_struct *p)
 {
@@ -4971,13 +4964,22 @@ done:
 	trace_sched_util_est_se_tp(&p->se);
 }
 
+static inline unsigned long get_actual_cpu_capacity(int cpu)
+{
+	unsigned long capacity = arch_scale_cpu_capacity(cpu);
+
+	capacity -= max(hw_load_avg(cpu_rq(cpu)), cpufreq_get_pressure(cpu));
+
+	return capacity;
+}
+
 static inline int util_fits_cpu(unsigned long util,
 				unsigned long uclamp_min,
 				unsigned long uclamp_max,
 				int cpu)
 {
-	unsigned long capacity_orig, capacity_orig_thermal;
 	unsigned long capacity = capacity_of(cpu);
+	unsigned long capacity_orig;
 	bool fits, uclamp_max_fits;
 
 	/*
@@ -4999,7 +5001,7 @@ static inline int util_fits_cpu(unsigned long util,
 	 * Similarly if a task is capped to arch_scale_cpu_capacity(little_cpu), it
 	 * should fit a little cpu even if there's some pressure.
 	 *
-	 * Only exception is for thermal pressure since it has a direct impact
+	 * Only exception is for HW or cpufreq pressure since it has a direct impact
 	 * on available OPP of the system.
 	 *
 	 * We honour it for uclamp_min only as a drop in performance level
@@ -5009,7 +5011,6 @@ static inline int util_fits_cpu(unsigned long util,
 	 * goal is to cap the task. So it's okay if it's getting less.
 	 */
 	capacity_orig = arch_scale_cpu_capacity(cpu);
-	capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu);
 
 	/*
 	 * We want to force a task to fit a cpu as implied by uclamp_max.
@@ -5026,14 +5027,14 @@ static inline int util_fits_cpu(unsigned long util,
 	 *   |     |   |       |   |      |   |
 	 *   |     |   |       |   |      |   |
 	 *   +----------------------------------------
-	 *         cpu0        cpu1       cpu2
+	 *         CPU0        CPU1       CPU2
 	 *
 	 *   In the above example if a task is capped to a specific performance
 	 *   point, y, then when:
 	 *
-	 *   * util = 80% of x then it does not fit on cpu0 and should migrate
-	 *     to cpu1
-	 *   * util = 80% of y then it is forced to fit on cpu1 to honour
+	 *   * util = 80% of x then it does not fit on CPU0 and should migrate
+	 *     to CPU1
+	 *   * util = 80% of y then it is forced to fit on CPU1 to honour
 	 *     uclamp_max request.
 	 *
 	 *   which is what we're enforcing here. A task always fits if
@@ -5064,7 +5065,7 @@ static inline int util_fits_cpu(unsigned long util,
 	 *   |     |   |       |   |      |   |
 	 *   |     |   |       |   |      |   |      (region c, boosted, util < uclamp_min)
 	 *   +----------------------------------------
-	 *         cpu0        cpu1       cpu2
+	 *         CPU0        CPU1       CPU2
 	 *
 	 * a) If util > uclamp_max, then we're capped, we don't care about
 	 *    actual fitness value here. We only care if uclamp_max fits
@@ -5084,7 +5085,8 @@ static inline int util_fits_cpu(unsigned long util,
 	 * handle the case uclamp_min > uclamp_max.
 	 */
 	uclamp_min = min(uclamp_min, uclamp_max);
-	if (fits && (util < uclamp_min) && (uclamp_min > capacity_orig_thermal))
+	if (fits && (util < uclamp_min) &&
+	    (uclamp_min > get_actual_cpu_capacity(cpu)))
 		return -1;
 
 	return fits;
@@ -5104,15 +5106,19 @@ static inline int task_fits_cpu(struct task_struct *p, int cpu)
 
 static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
 {
+	int cpu = cpu_of(rq);
+
 	if (!sched_asym_cpucap_active())
 		return;
 
-	if (!p || p->nr_cpus_allowed == 1) {
-		rq->misfit_task_load = 0;
-		return;
-	}
+	/*
+	 * Affinity allows us to go somewhere higher?  Or are we on biggest
+	 * available CPU already? Or do we fit into this CPU ?
+	 */
+	if (!p || (p->nr_cpus_allowed == 1) ||
+	    (arch_scale_cpu_capacity(cpu) == p->max_allowed_capacity) ||
+	    task_fits_cpu(p, cpu)) {
 
-	if (task_fits_cpu(p, cpu_of(rq))) {
 		rq->misfit_task_load = 0;
 		return;
 	}
@@ -5148,7 +5154,7 @@ attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
 static inline void
 detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
 
-static inline int newidle_balance(struct rq *rq, struct rq_flags *rf)
+static inline int sched_balance_newidle(struct rq *rq, struct rq_flags *rf)
 {
 	return 0;
 }
@@ -5254,7 +5260,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	se->vruntime = vruntime - lag;
 
 	/*
-	 * When joining the competition; the exisiting tasks will be,
+	 * When joining the competition; the existing tasks will be,
 	 * on average, halfway through their slice, as such start tasks
 	 * off with half a slice to ease into the competition.
 	 */
@@ -5403,7 +5409,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * Now advance min_vruntime if @se was the entity holding it back,
 	 * except when: DEQUEUE_SAVE && !DEQUEUE_MOVE, in this case we'll be
 	 * put back on, and if we advance min_vruntime, we'll be placed back
-	 * further than we started -- ie. we'll be penalized.
+	 * further than we started -- i.e. we'll be penalized.
 	 */
 	if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) != DEQUEUE_SAVE)
 		update_min_vruntime(cfs_rq);
@@ -5439,7 +5445,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 	/*
 	 * Track our maximum slice length, if the CPU's load is at
-	 * least twice that of our own weight (i.e. dont track it
+	 * least twice that of our own weight (i.e. don't track it
 	 * when there are only lesser-weight tasks around):
 	 */
 	if (schedstat_enabled() &&
@@ -6687,14 +6693,21 @@ static inline bool cpu_overutilized(int cpu)
 	return !util_fits_cpu(cpu_util_cfs(cpu), rq_util_min, rq_util_max, cpu);
 }
 
-static inline void set_rd_overutilized_status(struct root_domain *rd,
-					      unsigned int status)
+/*
+ * overutilized value make sense only if EAS is enabled
+ */
+static inline bool is_rd_overutilized(struct root_domain *rd)
+{
+	return !sched_energy_enabled() || READ_ONCE(rd->overutilized);
+}
+
+static inline void set_rd_overutilized(struct root_domain *rd, bool flag)
 {
 	if (!sched_energy_enabled())
 		return;
 
-	WRITE_ONCE(rd->overutilized, status);
-	trace_sched_overutilized_tp(rd, !!status);
+	WRITE_ONCE(rd->overutilized, flag);
+	trace_sched_overutilized_tp(rd, flag);
 }
 
 static inline void check_update_overutilized_status(struct rq *rq)
@@ -6703,11 +6716,9 @@ static inline void check_update_overutilized_status(struct rq *rq)
 	 * overutilized field is used for load balancing decisions only
 	 * if energy aware scheduler is being used
 	 */
-	if (!sched_energy_enabled())
-		return;
 
-	if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu))
-		set_rd_overutilized_status(rq->rd, SG_OVERUTILIZED);
+	if (!is_rd_overutilized(rq->rd) && cpu_overutilized(rq->cpu))
+		set_rd_overutilized(rq->rd, 1);
 }
 #else
 static inline void check_update_overutilized_status(struct rq *rq) { }
@@ -6898,7 +6909,7 @@ dequeue_throttle:
 
 #ifdef CONFIG_SMP
 
-/* Working cpumask for: load_balance, load_balance_newidle. */
+/* Working cpumask for: sched_balance_rq(), sched_balance_newidle(). */
 static DEFINE_PER_CPU(cpumask_var_t, load_balance_mask);
 static DEFINE_PER_CPU(cpumask_var_t, select_rq_mask);
 static DEFINE_PER_CPU(cpumask_var_t, should_we_balance_tmpmask);
@@ -7130,13 +7141,13 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 }
 
 static struct sched_group *
-find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu);
+sched_balance_find_dst_group(struct sched_domain *sd, struct task_struct *p, int this_cpu);
 
 /*
- * find_idlest_group_cpu - find the idlest CPU among the CPUs in the group.
+ * sched_balance_find_dst_group_cpu - find the idlest CPU among the CPUs in the group.
  */
 static int
-find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
+sched_balance_find_dst_group_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 {
 	unsigned long load, min_load = ULONG_MAX;
 	unsigned int min_exit_latency = UINT_MAX;
@@ -7192,7 +7203,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this
 	return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu;
 }
 
-static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p,
+static inline int sched_balance_find_dst_cpu(struct sched_domain *sd, struct task_struct *p,
 				  int cpu, int prev_cpu, int sd_flag)
 {
 	int new_cpu = cpu;
@@ -7217,13 +7228,13 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p
 			continue;
 		}
 
-		group = find_idlest_group(sd, p, cpu);
+		group = sched_balance_find_dst_group(sd, p, cpu);
 		if (!group) {
 			sd = sd->child;
 			continue;
 		}
 
-		new_cpu = find_idlest_group_cpu(group, p, cpu);
+		new_cpu = sched_balance_find_dst_group_cpu(group, p, cpu);
 		if (new_cpu == cpu) {
 			/* Now try balancing at a lower domain level of 'cpu': */
 			sd = sd->child;
@@ -7491,7 +7502,7 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
 		 * Look for the CPU with best capacity.
 		 */
 		else if (fits < 0)
-			cpu_cap = arch_scale_cpu_capacity(cpu) - thermal_load_avg(cpu_rq(cpu));
+			cpu_cap = get_actual_cpu_capacity(cpu);
 
 		/*
 		 * First, select CPU which fits better (-1 being better than 0).
@@ -7535,7 +7546,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 
 	/*
 	 * On asymmetric system, update task utilization because we will check
-	 * that the task fits with cpu's capacity.
+	 * that the task fits with CPU's capacity.
 	 */
 	if (sched_asym_cpucap_active()) {
 		sync_entity_load_avg(&p->se);
@@ -7887,8 +7898,8 @@ eenv_pd_max_util(struct energy_env *eenv, struct cpumask *pd_cpus,
 		 * Performance domain frequency: utilization clamping
 		 * must be considered since it affects the selection
 		 * of the performance domain frequency.
-		 * NOTE: in case RT tasks are running, by default the
-		 * FREQUENCY_UTIL's utilization can be max OPP.
+		 * NOTE: in case RT tasks are running, by default the min
+		 * utilization can be max OPP.
 		 */
 		eff_util = effective_cpu_util(cpu, util, &min, &max);
 
@@ -7968,7 +7979,7 @@ compute_energy(struct energy_env *eenv, struct perf_domain *pd,
  * 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
+ * placed by sched_balance_find_dst_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
@@ -7984,15 +7995,15 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 	struct root_domain *rd = this_rq()->rd;
 	int cpu, best_energy_cpu, target = -1;
 	int prev_fits = -1, best_fits = -1;
-	unsigned long best_thermal_cap = 0;
-	unsigned long prev_thermal_cap = 0;
+	unsigned long best_actual_cap = 0;
+	unsigned long prev_actual_cap = 0;
 	struct sched_domain *sd;
 	struct perf_domain *pd;
 	struct energy_env eenv;
 
 	rcu_read_lock();
 	pd = rcu_dereference(rd->pd);
-	if (!pd || READ_ONCE(rd->overutilized))
+	if (!pd)
 		goto unlock;
 
 	/*
@@ -8015,7 +8026,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 
 	for (; pd; pd = pd->next) {
 		unsigned long util_min = p_util_min, util_max = p_util_max;
-		unsigned long cpu_cap, cpu_thermal_cap, util;
+		unsigned long cpu_cap, cpu_actual_cap, util;
 		long prev_spare_cap = -1, max_spare_cap = -1;
 		unsigned long rq_util_min, rq_util_max;
 		unsigned long cur_delta, base_energy;
@@ -8027,18 +8038,17 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 		if (cpumask_empty(cpus))
 			continue;
 
-		/* Account thermal pressure for the energy estimation */
+		/* Account external pressure for the energy estimation */
 		cpu = cpumask_first(cpus);
-		cpu_thermal_cap = arch_scale_cpu_capacity(cpu);
-		cpu_thermal_cap -= arch_scale_thermal_pressure(cpu);
+		cpu_actual_cap = get_actual_cpu_capacity(cpu);
 
-		eenv.cpu_cap = cpu_thermal_cap;
+		eenv.cpu_cap = cpu_actual_cap;
 		eenv.pd_cap = 0;
 
 		for_each_cpu(cpu, cpus) {
 			struct rq *rq = cpu_rq(cpu);
 
-			eenv.pd_cap += cpu_thermal_cap;
+			eenv.pd_cap += cpu_actual_cap;
 
 			if (!cpumask_test_cpu(cpu, sched_domain_span(sd)))
 				continue;
@@ -8059,7 +8069,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 			if (uclamp_is_used() && !uclamp_rq_is_idle(rq)) {
 				/*
 				 * Open code uclamp_rq_util_with() except for
-				 * the clamp() part. Ie: apply max aggregation
+				 * the clamp() part. I.e.: apply max aggregation
 				 * only. util_fits_cpu() logic requires to
 				 * operate on non clamped util but must use the
 				 * max-aggregated uclamp_{min, max}.
@@ -8109,7 +8119,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 			if (prev_delta < base_energy)
 				goto unlock;
 			prev_delta -= base_energy;
-			prev_thermal_cap = cpu_thermal_cap;
+			prev_actual_cap = cpu_actual_cap;
 			best_delta = min(best_delta, prev_delta);
 		}
 
@@ -8124,7 +8134,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 			 * but best energy cpu has better capacity.
 			 */
 			if ((max_fits < 0) &&
-			    (cpu_thermal_cap <= best_thermal_cap))
+			    (cpu_actual_cap <= best_actual_cap))
 				continue;
 
 			cur_delta = compute_energy(&eenv, pd, cpus, p,
@@ -8145,14 +8155,14 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 			best_delta = cur_delta;
 			best_energy_cpu = max_spare_cap_cpu;
 			best_fits = max_fits;
-			best_thermal_cap = cpu_thermal_cap;
+			best_actual_cap = cpu_actual_cap;
 		}
 	}
 	rcu_read_unlock();
 
 	if ((best_fits > prev_fits) ||
 	    ((best_fits > 0) && (best_delta < prev_delta)) ||
-	    ((best_fits < 0) && (best_thermal_cap > prev_thermal_cap)))
+	    ((best_fits < 0) && (best_actual_cap > prev_actual_cap)))
 		target = best_energy_cpu;
 
 	return target;
@@ -8195,7 +8205,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags)
 		    cpumask_test_cpu(cpu, p->cpus_ptr))
 			return cpu;
 
-		if (sched_energy_enabled()) {
+		if (!is_rd_overutilized(this_rq()->rd)) {
 			new_cpu = find_energy_efficient_cpu(p, prev_cpu);
 			if (new_cpu >= 0)
 				return new_cpu;
@@ -8233,7 +8243,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags)
 
 	if (unlikely(sd)) {
 		/* Slow path */
-		new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag);
+		new_cpu = sched_balance_find_dst_cpu(sd, p, cpu, prev_cpu, sd_flag);
 	} else if (wake_flags & WF_TTWU) { /* XXX always ? */
 		/* Fast path */
 		new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
@@ -8279,14 +8289,46 @@ static void task_dead_fair(struct task_struct *p)
 	remove_entity_load_avg(&p->se);
 }
 
+/*
+ * Set the max capacity the task is allowed to run at for misfit detection.
+ */
+static void set_task_max_allowed_capacity(struct task_struct *p)
+{
+	struct asym_cap_data *entry;
+
+	if (!sched_asym_cpucap_active())
+		return;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(entry, &asym_cap_list, link) {
+		cpumask_t *cpumask;
+
+		cpumask = cpu_capacity_span(entry);
+		if (!cpumask_intersects(p->cpus_ptr, cpumask))
+			continue;
+
+		p->max_allowed_capacity = entry->capacity;
+		break;
+	}
+	rcu_read_unlock();
+}
+
+static void set_cpus_allowed_fair(struct task_struct *p, struct affinity_context *ctx)
+{
+	set_cpus_allowed_common(p, ctx);
+	set_task_max_allowed_capacity(p);
+}
+
 static int
 balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
 	if (rq->nr_running)
 		return 1;
 
-	return newidle_balance(rq, rf) != 0;
+	return sched_balance_newidle(rq, rf) != 0;
 }
+#else
+static inline void set_task_max_allowed_capacity(struct task_struct *p) {}
 #endif /* CONFIG_SMP */
 
 static void set_next_buddy(struct sched_entity *se)
@@ -8537,10 +8579,10 @@ idle:
 	if (!rf)
 		return NULL;
 
-	new_tasks = newidle_balance(rq, rf);
+	new_tasks = sched_balance_newidle(rq, rf);
 
 	/*
-	 * Because newidle_balance() releases (and re-acquires) rq->lock, it is
+	 * Because sched_balance_newidle() releases (and re-acquires) rq->lock, it is
 	 * possible for any higher priority task to appear. In that case we
 	 * must re-start the pick_next_entity() loop.
 	 */
@@ -8618,7 +8660,7 @@ static bool yield_to_task_fair(struct rq *rq, struct task_struct *p)
 	if (!se->on_rq || throttled_hierarchy(cfs_rq_of(se)))
 		return false;
 
-	/* Tell the scheduler that we'd really like pse to run next. */
+	/* Tell the scheduler that we'd really like se to run next. */
 	set_next_buddy(se);
 
 	yield_task_fair(rq);
@@ -8956,7 +8998,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu))
 		return 0;
 
-	/* Disregard pcpu kthreads; they are where they need to be. */
+	/* Disregard percpu kthreads; they are where they need to be. */
 	if (kthread_is_per_cpu(p))
 		return 0;
 
@@ -9102,7 +9144,7 @@ static int detach_tasks(struct lb_env *env)
 		 * We don't want to steal all, otherwise we may be treated likewise,
 		 * which could at worst lead to a livelock crash.
 		 */
-		if (env->idle != CPU_NOT_IDLE && env->src_rq->nr_running <= 1)
+		if (env->idle && env->src_rq->nr_running <= 1)
 			break;
 
 		env->loop++;
@@ -9277,7 +9319,7 @@ static inline bool others_have_blocked(struct rq *rq)
 	if (cpu_util_dl(rq))
 		return true;
 
-	if (thermal_load_avg(rq))
+	if (hw_load_avg(rq))
 		return true;
 
 	if (cpu_util_irq(rq))
@@ -9307,7 +9349,7 @@ static bool __update_blocked_others(struct rq *rq, bool *done)
 {
 	const struct sched_class *curr_class;
 	u64 now = rq_clock_pelt(rq);
-	unsigned long thermal_pressure;
+	unsigned long hw_pressure;
 	bool decayed;
 
 	/*
@@ -9316,11 +9358,11 @@ static bool __update_blocked_others(struct rq *rq, bool *done)
 	 */
 	curr_class = rq->curr->sched_class;
 
-	thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq));
+	hw_pressure = arch_scale_hw_pressure(cpu_of(rq));
 
 	decayed = update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) |
 		  update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) |
-		  update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure) |
+		  update_hw_load_avg(now, rq, hw_pressure) |
 		  update_irq_load_avg(rq, 0);
 
 	if (others_have_blocked(rq))
@@ -9439,7 +9481,7 @@ static unsigned long task_h_load(struct task_struct *p)
 }
 #endif
 
-static void update_blocked_averages(int cpu)
+static void sched_balance_update_blocked_averages(int cpu)
 {
 	bool decayed = false, done = true;
 	struct rq *rq = cpu_rq(cpu);
@@ -9458,25 +9500,25 @@ static void update_blocked_averages(int cpu)
 	rq_unlock_irqrestore(rq, &rf);
 }
 
-/********** Helpers for find_busiest_group ************************/
+/********** Helpers for sched_balance_find_src_group ************************/
 
 /*
- * sg_lb_stats - stats of a sched_group required for load_balancing
+ * sg_lb_stats - stats of a sched_group required for load-balancing:
  */
 struct sg_lb_stats {
-	unsigned long avg_load; /*Avg load across the CPUs of the group */
-	unsigned long group_load; /* Total load over the CPUs of the group */
-	unsigned long group_capacity;
-	unsigned long group_util; /* Total utilization over the CPUs of the group */
-	unsigned long group_runnable; /* Total runnable time over the CPUs of the group */
-	unsigned int sum_nr_running; /* Nr of tasks running in the group */
-	unsigned int sum_h_nr_running; /* Nr of CFS tasks running in the group */
-	unsigned int idle_cpus;
+	unsigned long avg_load;			/* Avg load            over the CPUs of the group */
+	unsigned long group_load;		/* Total load          over the CPUs of the group */
+	unsigned long group_capacity;		/* Capacity            over the CPUs of the group */
+	unsigned long group_util;		/* Total utilization   over the CPUs of the group */
+	unsigned long group_runnable;		/* Total runnable time over the CPUs of the group */
+	unsigned int sum_nr_running;		/* Nr of all tasks running in the group */
+	unsigned int sum_h_nr_running;		/* Nr of CFS tasks running in the group */
+	unsigned int idle_cpus;                 /* Nr of idle CPUs         in the group */
 	unsigned int group_weight;
 	enum group_type group_type;
-	unsigned int group_asym_packing; /* Tasks should be moved to preferred CPU */
-	unsigned int group_smt_balance;  /* Task on busy SMT be moved */
-	unsigned long group_misfit_task_load; /* A CPU has a task too big for its capacity */
+	unsigned int group_asym_packing;	/* Tasks should be moved to preferred CPU */
+	unsigned int group_smt_balance;		/* Task on busy SMT be moved */
+	unsigned long group_misfit_task_load;	/* A CPU has a task too big for its capacity */
 #ifdef CONFIG_NUMA_BALANCING
 	unsigned int nr_numa_running;
 	unsigned int nr_preferred_running;
@@ -9484,19 +9526,18 @@ struct sg_lb_stats {
 };
 
 /*
- * sd_lb_stats - Structure to store the statistics of a sched_domain
- *		 during load balancing.
+ * sd_lb_stats - stats of a sched_domain required for load-balancing:
  */
 struct sd_lb_stats {
-	struct sched_group *busiest;	/* Busiest group in this sd */
-	struct sched_group *local;	/* Local group in this sd */
-	unsigned long total_load;	/* Total load of all groups in sd */
-	unsigned long total_capacity;	/* Total capacity of all groups in sd */
-	unsigned long avg_load;	/* Average load across all groups in sd */
-	unsigned int prefer_sibling; /* tasks should go to sibling first */
-
-	struct sg_lb_stats busiest_stat;/* Statistics of the busiest group */
-	struct sg_lb_stats local_stat;	/* Statistics of the local group */
+	struct sched_group *busiest;		/* Busiest group in this sd */
+	struct sched_group *local;		/* Local group in this sd */
+	unsigned long total_load;		/* Total load of all groups in sd */
+	unsigned long total_capacity;		/* Total capacity of all groups in sd */
+	unsigned long avg_load;			/* Average load across all groups in sd */
+	unsigned int prefer_sibling;		/* Tasks should go to sibling first */
+
+	struct sg_lb_stats busiest_stat;	/* Statistics of the busiest group */
+	struct sg_lb_stats local_stat;		/* Statistics of the local group */
 };
 
 static inline void init_sd_lb_stats(struct sd_lb_stats *sds)
@@ -9522,8 +9563,8 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds)
 
 static unsigned long scale_rt_capacity(int cpu)
 {
+	unsigned long max = get_actual_cpu_capacity(cpu);
 	struct rq *rq = cpu_rq(cpu);
-	unsigned long max = arch_scale_cpu_capacity(cpu);
 	unsigned long used, free;
 	unsigned long irq;
 
@@ -9535,12 +9576,9 @@ static unsigned long scale_rt_capacity(int cpu)
 	/*
 	 * avg_rt.util_avg and avg_dl.util_avg track binary signals
 	 * (running and not running) with weights 0 and 1024 respectively.
-	 * avg_thermal.load_avg tracks thermal pressure and the weighted
-	 * average uses the actual delta max capacity(load).
 	 */
 	used = cpu_util_rt(rq);
 	used += cpu_util_dl(rq);
-	used += thermal_load_avg(rq);
 
 	if (unlikely(used >= max))
 		return 1;
@@ -9633,16 +9671,10 @@ check_cpu_capacity(struct rq *rq, struct sched_domain *sd)
 				(arch_scale_cpu_capacity(cpu_of(rq)) * 100));
 }
 
-/*
- * Check whether a rq has a misfit task and if it looks like we can actually
- * help that task: we can migrate the task to a CPU of higher capacity, or
- * the task's current CPU is heavily pressured.
- */
-static inline int check_misfit_status(struct rq *rq, struct sched_domain *sd)
+/* Check if the rq has a misfit task */
+static inline bool check_misfit_status(struct rq *rq)
 {
-	return rq->misfit_task_load &&
-		(arch_scale_cpu_capacity(rq->cpu) < rq->rd->max_cpu_capacity ||
-		 check_cpu_capacity(rq, sd));
+	return rq->misfit_task_load;
 }
 
 /*
@@ -9666,7 +9698,7 @@ static inline int check_misfit_status(struct rq *rq, struct sched_domain *sd)
  *
  * When this is so detected; this group becomes a candidate for busiest; see
  * update_sd_pick_busiest(). And calculate_imbalance() and
- * find_busiest_group() avoid some of the usual balance conditions to allow it
+ * sched_balance_find_src_group() avoid some of the usual balance conditions to allow it
  * to create an effective group imbalance.
  *
  * This is a somewhat tricky proposition since the next run might not find the
@@ -9831,7 +9863,7 @@ static inline bool smt_vs_nonsmt_groups(struct sched_group *sg1,
 static inline bool smt_balance(struct lb_env *env, struct sg_lb_stats *sgs,
 			       struct sched_group *group)
 {
-	if (env->idle == CPU_NOT_IDLE)
+	if (!env->idle)
 		return false;
 
 	/*
@@ -9855,7 +9887,7 @@ static inline long sibling_imbalance(struct lb_env *env,
 	int ncores_busiest, ncores_local;
 	long imbalance;
 
-	if (env->idle == CPU_NOT_IDLE || !busiest->sum_nr_running)
+	if (!env->idle || !busiest->sum_nr_running)
 		return 0;
 
 	ncores_busiest = sds->busiest->cores;
@@ -9901,13 +9933,15 @@ sched_reduced_capacity(struct rq *rq, struct sched_domain *sd)
  * @sds: Load-balancing data with statistics of the local group.
  * @group: sched_group whose statistics are to be updated.
  * @sgs: variable to hold the statistics for this group.
- * @sg_status: Holds flag indicating the status of the sched_group
+ * @sg_overloaded: sched_group is overloaded
+ * @sg_overutilized: sched_group is overutilized
  */
 static inline void update_sg_lb_stats(struct lb_env *env,
 				      struct sd_lb_stats *sds,
 				      struct sched_group *group,
 				      struct sg_lb_stats *sgs,
-				      int *sg_status)
+				      bool *sg_overloaded,
+				      bool *sg_overutilized)
 {
 	int i, nr_running, local_group;
 
@@ -9928,10 +9962,10 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		sgs->sum_nr_running += nr_running;
 
 		if (nr_running > 1)
-			*sg_status |= SG_OVERLOAD;
+			*sg_overloaded = 1;
 
 		if (cpu_overutilized(i))
-			*sg_status |= SG_OVERUTILIZED;
+			*sg_overutilized = 1;
 
 #ifdef CONFIG_NUMA_BALANCING
 		sgs->nr_numa_running += rq->nr_numa_running;
@@ -9953,10 +9987,9 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 			/* Check for a misfit task on the cpu */
 			if (sgs->group_misfit_task_load < rq->misfit_task_load) {
 				sgs->group_misfit_task_load = rq->misfit_task_load;
-				*sg_status |= SG_OVERLOAD;
+				*sg_overloaded = 1;
 			}
-		} else if ((env->idle != CPU_NOT_IDLE) &&
-			   sched_reduced_capacity(rq, env->sd)) {
+		} else if (env->idle && sched_reduced_capacity(rq, env->sd)) {
 			/* Check for a task running on a CPU with reduced capacity */
 			if (sgs->group_misfit_task_load < load)
 				sgs->group_misfit_task_load = load;
@@ -9968,7 +10001,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 	sgs->group_weight = group->group_weight;
 
 	/* Check if dst CPU is idle and preferred to this group */
-	if (!local_group && env->idle != CPU_NOT_IDLE && sgs->sum_h_nr_running &&
+	if (!local_group && env->idle && sgs->sum_h_nr_running &&
 	    sched_group_asym(env, sgs, group))
 		sgs->group_asym_packing = 1;
 
@@ -10106,7 +10139,7 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 has_spare:
 
 		/*
-		 * Select not overloaded group with lowest number of idle cpus
+		 * Select not overloaded group with lowest number of idle CPUs
 		 * and highest number of running tasks. We could also compare
 		 * the spare capacity which is more stable but it can end up
 		 * that the group has less spare capacity but finally more idle
@@ -10326,13 +10359,13 @@ static bool update_pick_idlest(struct sched_group *idlest,
 }
 
 /*
- * find_idlest_group() finds and returns the least busy CPU group within the
+ * sched_balance_find_dst_group() finds and returns the least busy CPU group within the
  * domain.
  *
  * Assumes p is allowed on at least one CPU in sd.
  */
 static struct sched_group *
-find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
+sched_balance_find_dst_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
 {
 	struct sched_group *idlest = NULL, *local = NULL, *group = sd->groups;
 	struct sg_lb_stats local_sgs, tmp_sgs;
@@ -10580,7 +10613,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 	struct sg_lb_stats *local = &sds->local_stat;
 	struct sg_lb_stats tmp_sgs;
 	unsigned long sum_util = 0;
-	int sg_status = 0;
+	bool sg_overloaded = 0, sg_overutilized = 0;
 
 	do {
 		struct sg_lb_stats *sgs = &tmp_sgs;
@@ -10596,7 +10629,7 @@ 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, sds, sg, sgs, &sg_status);
+		update_sg_lb_stats(env, sds, sg, sgs, &sg_overloaded, &sg_overutilized);
 
 		if (!local_group && update_sd_pick_busiest(env, sds, sg, sgs)) {
 			sds->busiest = sg;
@@ -10625,13 +10658,12 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 
 	if (!env->sd->parent) {
 		/* update overload indicator if we are at root domain */
-		WRITE_ONCE(env->dst_rq->rd->overload, sg_status & SG_OVERLOAD);
+		set_rd_overloaded(env->dst_rq->rd, sg_overloaded);
 
 		/* Update over-utilization (tipping point, U >= 0) indicator */
-		set_rd_overutilized_status(env->dst_rq->rd,
-					   sg_status & SG_OVERUTILIZED);
-	} else if (sg_status & SG_OVERUTILIZED) {
-		set_rd_overutilized_status(env->dst_rq->rd, SG_OVERUTILIZED);
+		set_rd_overutilized(env->dst_rq->rd, sg_overutilized);
+	} else if (sg_overutilized) {
+		set_rd_overutilized(env->dst_rq->rd, sg_overutilized);
 	}
 
 	update_idle_cpu_scan(env, sum_util);
@@ -10721,7 +10753,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 			 * waiting task in this overloaded busiest group. Let's
 			 * try to pull it.
 			 */
-			if (env->idle != CPU_NOT_IDLE && env->imbalance == 0) {
+			if (env->idle && env->imbalance == 0) {
 				env->migration_type = migrate_task;
 				env->imbalance = 1;
 			}
@@ -10740,7 +10772,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 
 			/*
 			 * If there is no overload, we just want to even the number of
-			 * idle cpus.
+			 * idle CPUs.
 			 */
 			env->migration_type = migrate_task;
 			env->imbalance = max_t(long, 0,
@@ -10813,7 +10845,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 	) / SCHED_CAPACITY_SCALE;
 }
 
-/******* find_busiest_group() helpers end here *********************/
+/******* sched_balance_find_src_group() helpers end here *********************/
 
 /*
  * Decision matrix according to the local and busiest group type:
@@ -10836,7 +10868,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
  */
 
 /**
- * find_busiest_group - Returns the busiest group within the sched_domain
+ * sched_balance_find_src_group - Returns the busiest group within the sched_domain
  * if there is an imbalance.
  * @env: The load balancing environment.
  *
@@ -10845,7 +10877,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
  *
  * Return:	- The busiest group if imbalance exists.
  */
-static struct sched_group *find_busiest_group(struct lb_env *env)
+static struct sched_group *sched_balance_find_src_group(struct lb_env *env)
 {
 	struct sg_lb_stats *local, *busiest;
 	struct sd_lb_stats sds;
@@ -10868,12 +10900,9 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 	if (busiest->group_type == group_misfit_task)
 		goto force_balance;
 
-	if (sched_energy_enabled()) {
-		struct root_domain *rd = env->dst_rq->rd;
-
-		if (rcu_dereference(rd->pd) && !READ_ONCE(rd->overutilized))
-			goto out_balanced;
-	}
+	if (!is_rd_overutilized(env->dst_rq->rd) &&
+	    rcu_dereference(env->dst_rq->rd->pd))
+		goto out_balanced;
 
 	/* ASYM feature bypasses nice load balance check */
 	if (busiest->group_type == group_asym_packing)
@@ -10936,7 +10965,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 		goto force_balance;
 
 	if (busiest->group_type != group_overloaded) {
-		if (env->idle == CPU_NOT_IDLE) {
+		if (!env->idle) {
 			/*
 			 * If the busiest group is not overloaded (and as a
 			 * result the local one too) but this CPU is already
@@ -10984,9 +11013,9 @@ out_balanced:
 }
 
 /*
- * find_busiest_queue - find the busiest runqueue among the CPUs in the group.
+ * sched_balance_find_src_rq - find the busiest runqueue among the CPUs in the group.
  */
-static struct rq *find_busiest_queue(struct lb_env *env,
+static struct rq *sched_balance_find_src_rq(struct lb_env *env,
 				     struct sched_group *group)
 {
 	struct rq *busiest = NULL, *rq;
@@ -11144,7 +11173,7 @@ asym_active_balance(struct lb_env *env)
 	 * the lower priority @env::dst_cpu help it. Do not follow
 	 * CPU priority.
 	 */
-	return env->idle != CPU_NOT_IDLE && sched_use_asym_prio(env->sd, env->dst_cpu) &&
+	return env->idle && sched_use_asym_prio(env->sd, env->dst_cpu) &&
 	       (sched_asym_prefer(env->dst_cpu, env->src_cpu) ||
 		!sched_use_asym_prio(env->sd, env->src_cpu));
 }
@@ -11182,7 +11211,7 @@ static int need_active_balance(struct lb_env *env)
 	 * because of other sched_class or IRQs if more capacity stays
 	 * available on dst_cpu.
 	 */
-	if ((env->idle != CPU_NOT_IDLE) &&
+	if (env->idle &&
 	    (env->src_rq->cfs.h_nr_running == 1)) {
 		if ((check_cpu_capacity(env->src_rq, sd)) &&
 		    (capacity_of(env->src_cpu)*sd->imbalance_pct < capacity_of(env->dst_cpu)*100))
@@ -11267,7 +11296,7 @@ static int should_we_balance(struct lb_env *env)
  * Check this_cpu to ensure it is balanced within domain. Attempt to move
  * tasks if there is an imbalance.
  */
-static int load_balance(int this_cpu, struct rq *this_rq,
+static int sched_balance_rq(int this_cpu, struct rq *this_rq,
 			struct sched_domain *sd, enum cpu_idle_type idle,
 			int *continue_balancing)
 {
@@ -11299,13 +11328,13 @@ redo:
 		goto out_balanced;
 	}
 
-	group = find_busiest_group(&env);
+	group = sched_balance_find_src_group(&env);
 	if (!group) {
 		schedstat_inc(sd->lb_nobusyg[idle]);
 		goto out_balanced;
 	}
 
-	busiest = find_busiest_queue(&env, group);
+	busiest = sched_balance_find_src_rq(&env, group);
 	if (!busiest) {
 		schedstat_inc(sd->lb_nobusyq[idle]);
 		goto out_balanced;
@@ -11323,7 +11352,7 @@ redo:
 	env.flags |= LBF_ALL_PINNED;
 	if (busiest->nr_running > 1) {
 		/*
-		 * Attempt to move tasks. If find_busiest_group has found
+		 * Attempt to move tasks. If sched_balance_find_src_group has found
 		 * an imbalance but busiest->nr_running <= 1, the group is
 		 * still unbalanced. ld_moved simply stays zero, so it is
 		 * correctly treated as an imbalance.
@@ -11436,8 +11465,12 @@ more_balance:
 		 * We do not want newidle balance, which can be very
 		 * frequent, pollute the failure counter causing
 		 * excessive cache_hot migrations and active balances.
+		 *
+		 * Similarly for migration_misfit which is not related to
+		 * load/util migration, don't pollute nr_balance_failed.
 		 */
-		if (idle != CPU_NEWLY_IDLE)
+		if (idle != CPU_NEWLY_IDLE &&
+		    env.migration_type != migrate_misfit)
 			sd->nr_balance_failed++;
 
 		if (need_active_balance(&env)) {
@@ -11516,12 +11549,17 @@ out_one_pinned:
 	ld_moved = 0;
 
 	/*
-	 * newidle_balance() disregards balance intervals, so we could
+	 * sched_balance_newidle() disregards balance intervals, so we could
 	 * repeatedly reach this code, which would lead to balance_interval
 	 * skyrocketing in a short amount of time. Skip the balance_interval
 	 * increase logic to avoid that.
+	 *
+	 * Similarly misfit migration which is not necessarily an indication of
+	 * the system being busy and requires lb to backoff to let it settle
+	 * down.
 	 */
-	if (env.idle == CPU_NEWLY_IDLE)
+	if (env.idle == CPU_NEWLY_IDLE ||
+	    env.migration_type == migrate_misfit)
 		goto out;
 
 	/* tune up the balancing interval */
@@ -11654,10 +11692,23 @@ out_unlock:
 	return 0;
 }
 
-static DEFINE_SPINLOCK(balancing);
+/*
+ * This flag serializes load-balancing passes over large domains
+ * (above the NODE topology level) - only one load-balancing instance
+ * may run at a time, to reduce overhead on very large systems with
+ * lots of CPUs and large NUMA distances.
+ *
+ * - Note that load-balancing passes triggered while another one
+ *   is executing are skipped and not re-tried.
+ *
+ * - Also note that this does not serialize rebalance_domains()
+ *   execution, as non-SD_SERIALIZE domains will still be
+ *   load-balanced in parallel.
+ */
+static atomic_t sched_balance_running = ATOMIC_INIT(0);
 
 /*
- * Scale the max load_balance interval with the number of CPUs in the system.
+ * Scale the max sched_balance_rq interval with the number of CPUs in the system.
  * This trades load-balance latency on larger machines for less cross talk.
  */
 void update_max_interval(void)
@@ -11695,7 +11746,7 @@ static inline bool update_newidle_cost(struct sched_domain *sd, u64 cost)
  *
  * Balancing parameters are set up in init_sched_domains.
  */
-static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
+static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle)
 {
 	int continue_balancing = 1;
 	int cpu = rq->cpu;
@@ -11732,25 +11783,25 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
 
 		need_serialize = sd->flags & SD_SERIALIZE;
 		if (need_serialize) {
-			if (!spin_trylock(&balancing))
+			if (atomic_cmpxchg_acquire(&sched_balance_running, 0, 1))
 				goto out;
 		}
 
 		if (time_after_eq(jiffies, sd->last_balance + interval)) {
-			if (load_balance(cpu, rq, sd, idle, &continue_balancing)) {
+			if (sched_balance_rq(cpu, rq, sd, idle, &continue_balancing)) {
 				/*
 				 * The LBF_DST_PINNED logic could have changed
 				 * env->dst_cpu, so we can't know our idle
 				 * state even if we migrated tasks. Update it.
 				 */
-				idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE;
-				busy = idle != CPU_IDLE && !sched_idle_cpu(cpu);
+				idle = idle_cpu(cpu);
+				busy = !idle && !sched_idle_cpu(cpu);
 			}
 			sd->last_balance = jiffies;
 			interval = get_sd_balance_interval(sd, busy);
 		}
 		if (need_serialize)
-			spin_unlock(&balancing);
+			atomic_set_release(&sched_balance_running, 0);
 out:
 		if (time_after(next_balance, sd->last_balance + interval)) {
 			next_balance = sd->last_balance + interval;
@@ -11910,7 +11961,7 @@ static void nohz_balancer_kick(struct rq *rq)
 		 * currently idle; in which case, kick the ILB to move tasks
 		 * around.
 		 *
-		 * When balancing betwen cores, all the SMT siblings of the
+		 * When balancing between cores, all the SMT siblings of the
 		 * preferred CPU must be idle.
 		 */
 		for_each_cpu_and(i, sched_domain_span(sd), nohz.idle_cpus_mask) {
@@ -11927,7 +11978,7 @@ static void nohz_balancer_kick(struct rq *rq)
 		 * When ASYM_CPUCAPACITY; see if there's a higher capacity CPU
 		 * to run the misfit task on.
 		 */
-		if (check_misfit_status(rq, sd)) {
+		if (check_misfit_status(rq)) {
 			flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
 			goto unlock;
 		}
@@ -12071,7 +12122,7 @@ void nohz_balance_enter_idle(int cpu)
 out:
 	/*
 	 * Each time a cpu enter idle, we assume that it has blocked load and
-	 * enable the periodic update of the load of idle cpus
+	 * enable the periodic update of the load of idle CPUs
 	 */
 	WRITE_ONCE(nohz.has_blocked, 1);
 }
@@ -12089,13 +12140,13 @@ static bool update_nohz_stats(struct rq *rq)
 	if (!time_after(jiffies, READ_ONCE(rq->last_blocked_load_update_tick)))
 		return true;
 
-	update_blocked_averages(cpu);
+	sched_balance_update_blocked_averages(cpu);
 
 	return rq->has_blocked_load;
 }
 
 /*
- * Internal function that runs load balance for all idle cpus. The load balance
+ * Internal function that runs load balance for all idle CPUs. The load balance
  * can be a simple update of blocked load or a complete load balance with
  * tasks movement depending of flags.
  */
@@ -12171,7 +12222,7 @@ static void _nohz_idle_balance(struct rq *this_rq, unsigned int flags)
 			rq_unlock_irqrestore(rq, &rf);
 
 			if (flags & NOHZ_BALANCE_KICK)
-				rebalance_domains(rq, CPU_IDLE);
+				sched_balance_domains(rq, CPU_IDLE);
 		}
 
 		if (time_after(next_balance, rq->next_balance)) {
@@ -12200,7 +12251,7 @@ abort:
 
 /*
  * In CONFIG_NO_HZ_COMMON case, the idle balance kickee will do the
- * rebalancing for all the cpus for whom scheduler ticks are stopped.
+ * rebalancing for all the CPUs for whom scheduler ticks are stopped.
  */
 static bool nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
 {
@@ -12231,7 +12282,7 @@ static bool nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
  * called from this function on (this) CPU that's not yet in the mask. That's
  * OK because the goal of nohz_run_idle_balance() is to run ILB only for
  * updating the blocked load of already idle CPUs without waking up one of
- * those idle CPUs and outside the preempt disable / irq off phase of the local
+ * those idle CPUs and outside the preempt disable / IRQ off phase of the local
  * cpu about to enter idle, because it can take a long time.
  */
 void nohz_run_idle_balance(int cpu)
@@ -12242,7 +12293,7 @@ void nohz_run_idle_balance(int cpu)
 
 	/*
 	 * Update the blocked load only if no SCHED_SOFTIRQ is about to happen
-	 * (ie NOHZ_STATS_KICK set) and will do the same.
+	 * (i.e. NOHZ_STATS_KICK set) and will do the same.
 	 */
 	if ((flags == NOHZ_NEWILB_KICK) && !need_resched())
 		_nohz_idle_balance(cpu_rq(cpu), NOHZ_STATS_KICK);
@@ -12287,7 +12338,7 @@ static inline void nohz_newidle_balance(struct rq *this_rq) { }
 #endif /* CONFIG_NO_HZ_COMMON */
 
 /*
- * newidle_balance is called by schedule() if this_cpu is about to become
+ * sched_balance_newidle is called by schedule() if this_cpu is about to become
  * idle. Attempts to pull tasks from other CPUs.
  *
  * Returns:
@@ -12295,10 +12346,11 @@ static inline void nohz_newidle_balance(struct rq *this_rq) { }
  *     0 - failed, no new tasks
  *   > 0 - success, new (fair) tasks present
  */
-static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
+static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 {
 	unsigned long next_balance = jiffies + HZ;
 	int this_cpu = this_rq->cpu;
+	int continue_balancing = 1;
 	u64 t0, t1, curr_cost = 0;
 	struct sched_domain *sd;
 	int pulled_task = 0;
@@ -12313,8 +12365,9 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 		return 0;
 
 	/*
-	 * We must set idle_stamp _before_ calling idle_balance(), such that we
-	 * measure the duration of idle_balance() as idle time.
+	 * We must set idle_stamp _before_ calling sched_balance_rq()
+	 * for CPU_NEWLY_IDLE, such that we measure the this duration
+	 * as idle time.
 	 */
 	this_rq->idle_stamp = rq_clock(this_rq);
 
@@ -12335,7 +12388,7 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 	rcu_read_lock();
 	sd = rcu_dereference_check_sched_domain(this_rq->sd);
 
-	if (!READ_ONCE(this_rq->rd->overload) ||
+	if (!get_rd_overloaded(this_rq->rd) ||
 	    (sd && this_rq->avg_idle < sd->max_newidle_lb_cost)) {
 
 		if (sd)
@@ -12349,11 +12402,10 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 	raw_spin_rq_unlock(this_rq);
 
 	t0 = sched_clock_cpu(this_cpu);
-	update_blocked_averages(this_cpu);
+	sched_balance_update_blocked_averages(this_cpu);
 
 	rcu_read_lock();
 	for_each_domain(this_cpu, sd) {
-		int continue_balancing = 1;
 		u64 domain_cost;
 
 		update_next_balance(sd, &next_balance);
@@ -12363,7 +12415,7 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 
 		if (sd->flags & SD_BALANCE_NEWIDLE) {
 
-			pulled_task = load_balance(this_cpu, this_rq,
+			pulled_task = sched_balance_rq(this_cpu, this_rq,
 						   sd, CPU_NEWLY_IDLE,
 						   &continue_balancing);
 
@@ -12379,8 +12431,7 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 		 * Stop searching for tasks to pull if there are
 		 * now runnable tasks on this rq.
 		 */
-		if (pulled_task || this_rq->nr_running > 0 ||
-		    this_rq->ttwu_pending)
+		if (pulled_task || !continue_balancing)
 			break;
 	}
 	rcu_read_unlock();
@@ -12418,19 +12469,21 @@ out:
 }
 
 /*
- * run_rebalance_domains is triggered when needed from the scheduler tick.
- * Also triggered for nohz idle balancing (with nohz_balancing_kick set).
+ * This softirq handler is triggered via SCHED_SOFTIRQ from two places:
+ *
+ * - directly from the local scheduler_tick() for periodic load balancing
+ *
+ * - indirectly from a remote scheduler_tick() for NOHZ idle balancing
+ *   through the SMP cross-call nohz_csd_func()
  */
-static __latent_entropy void run_rebalance_domains(struct softirq_action *h)
+static __latent_entropy void sched_balance_softirq(struct softirq_action *h)
 {
 	struct rq *this_rq = this_rq();
-	enum cpu_idle_type idle = this_rq->idle_balance ?
-						CPU_IDLE : CPU_NOT_IDLE;
-
+	enum cpu_idle_type idle = this_rq->idle_balance;
 	/*
-	 * If this CPU has a pending nohz_balance_kick, then do the
+	 * If this CPU has a pending NOHZ_BALANCE_KICK, then do the
 	 * balancing on behalf of the other idle CPUs whose ticks are
-	 * stopped. Do nohz_idle_balance *before* rebalance_domains to
+	 * stopped. Do nohz_idle_balance *before* sched_balance_domains to
 	 * give the idle CPUs a chance to load balance. Else we may
 	 * load balance only within the local sched_domain hierarchy
 	 * and abort nohz_idle_balance altogether if we pull some load.
@@ -12439,14 +12492,14 @@ static __latent_entropy void run_rebalance_domains(struct softirq_action *h)
 		return;
 
 	/* normal load balance */
-	update_blocked_averages(this_rq->cpu);
-	rebalance_domains(this_rq, idle);
+	sched_balance_update_blocked_averages(this_rq->cpu);
+	sched_balance_domains(this_rq, idle);
 }
 
 /*
  * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
  */
-void trigger_load_balance(struct rq *rq)
+void sched_balance_trigger(struct rq *rq)
 {
 	/*
 	 * Don't need to rebalance while attached to NULL domain or
@@ -12650,6 +12703,8 @@ static void task_fork_fair(struct task_struct *p)
 	rq_lock(rq, &rf);
 	update_rq_clock(rq);
 
+	set_task_max_allowed_capacity(p);
+
 	cfs_rq = task_cfs_rq(current);
 	curr = cfs_rq->curr;
 	if (curr)
@@ -12773,6 +12828,8 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p)
 {
 	attach_task_cfs_rq(p);
 
+	set_task_max_allowed_capacity(p);
+
 	if (task_on_rq_queued(p)) {
 		/*
 		 * We were most likely switched from sched_rt, so
@@ -13144,7 +13201,7 @@ DEFINE_SCHED_CLASS(fair) = {
 	.rq_offline		= rq_offline_fair,
 
 	.task_dead		= task_dead_fair,
-	.set_cpus_allowed	= set_cpus_allowed_common,
+	.set_cpus_allowed	= set_cpus_allowed_fair,
 #endif
 
 	.task_tick		= task_tick_fair,
@@ -13224,7 +13281,7 @@ __init void init_sched_fair_class(void)
 #endif
 	}
 
-	open_softirq(SCHED_SOFTIRQ, run_rebalance_domains);
+	open_softirq(SCHED_SOFTIRQ, sched_balance_softirq);
 
 #ifdef CONFIG_NO_HZ_COMMON
 	nohz.next_balance = jiffies;
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index 52c8f8226b..ca9da66cc8 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -379,7 +379,7 @@ void calc_global_load(void)
 }
 
 /*
- * Called from scheduler_tick() to periodically update this CPU's
+ * Called from sched_tick() to periodically update this CPU's
  * active count.
  */
 void calc_global_load_tick(struct rq *this_rq)
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index 63b6cf8982..ef00382de5 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -208,8 +208,8 @@ ___update_load_sum(u64 now, struct sched_avg *sa,
 	 * se has been already dequeued but cfs_rq->curr still points to it.
 	 * This means that weight will be 0 but not running for a sched_entity
 	 * but also for a cfs_rq if the latter becomes idle. As an example,
-	 * this happens during idle_balance() which calls
-	 * update_blocked_averages().
+	 * this happens during sched_balance_newidle() which calls
+	 * sched_balance_update_blocked_averages().
 	 *
 	 * Also see the comment in accumulate_sum().
 	 */
@@ -384,30 +384,30 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
 	return 0;
 }
 
-#ifdef CONFIG_SCHED_THERMAL_PRESSURE
+#ifdef CONFIG_SCHED_HW_PRESSURE
 /*
- * thermal:
+ * hardware:
  *
  *   load_sum = \Sum se->avg.load_sum but se->avg.load_sum is not tracked
  *
  *   util_avg and runnable_load_avg are not supported and meaningless.
  *
  * Unlike rt/dl utilization tracking that track time spent by a cpu
- * running a rt/dl task through util_avg, the average thermal pressure is
- * tracked through load_avg. This is because thermal pressure signal is
+ * running a rt/dl task through util_avg, the average HW pressure is
+ * tracked through load_avg. This is because HW pressure signal is
  * time weighted "delta" capacity unlike util_avg which is binary.
  * "delta capacity" =  actual capacity  -
- *			capped capacity a cpu due to a thermal event.
+ *			capped capacity a cpu due to a HW event.
  */
 
-int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity)
+int update_hw_load_avg(u64 now, struct rq *rq, u64 capacity)
 {
-	if (___update_load_sum(now, &rq->avg_thermal,
+	if (___update_load_sum(now, &rq->avg_hw,
 			       capacity,
 			       capacity,
 			       capacity)) {
-		___update_load_avg(&rq->avg_thermal, 1);
-		trace_pelt_thermal_tp(rq);
+		___update_load_avg(&rq->avg_hw, 1);
+		trace_pelt_hw_tp(rq);
 		return 1;
 	}
 
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
index 9e1083465f..2150062949 100644
--- a/kernel/sched/pelt.h
+++ b/kernel/sched/pelt.h
@@ -7,21 +7,21 @@ int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq);
 int update_rt_rq_load_avg(u64 now, struct rq *rq, int running);
 int update_dl_rq_load_avg(u64 now, struct rq *rq, int running);
 
-#ifdef CONFIG_SCHED_THERMAL_PRESSURE
-int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity);
+#ifdef CONFIG_SCHED_HW_PRESSURE
+int update_hw_load_avg(u64 now, struct rq *rq, u64 capacity);
 
-static inline u64 thermal_load_avg(struct rq *rq)
+static inline u64 hw_load_avg(struct rq *rq)
 {
-	return READ_ONCE(rq->avg_thermal.load_avg);
+	return READ_ONCE(rq->avg_hw.load_avg);
 }
 #else
 static inline int
-update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity)
+update_hw_load_avg(u64 now, struct rq *rq, u64 capacity)
 {
 	return 0;
 }
 
-static inline u64 thermal_load_avg(struct rq *rq)
+static inline u64 hw_load_avg(struct rq *rq)
 {
 	return 0;
 }
@@ -202,12 +202,12 @@ update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
 }
 
 static inline int
-update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity)
+update_hw_load_avg(u64 now, struct rq *rq, u64 capacity)
 {
 	return 0;
 }
 
-static inline u64 thermal_load_avg(struct rq *rq)
+static inline u64 hw_load_avg(struct rq *rq)
 {
 	return 0;
 }
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 7b4aa5809c..507d7b8d79 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -773,6 +773,7 @@ static void psi_group_change(struct psi_group *group, int cpu,
 	enum psi_states s;
 	u32 state_mask;
 
+	lockdep_assert_rq_held(cpu_rq(cpu));
 	groupc = per_cpu_ptr(group->pcpu, cpu);
 
 	/*
@@ -991,22 +992,32 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 }
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
-void psi_account_irqtime(struct task_struct *task, u32 delta)
+void psi_account_irqtime(struct rq *rq, struct task_struct *curr, struct task_struct *prev)
 {
-	int cpu = task_cpu(task);
+	int cpu = task_cpu(curr);
 	struct psi_group *group;
 	struct psi_group_cpu *groupc;
-	u64 now;
+	u64 now, irq;
+	s64 delta;
 
 	if (static_branch_likely(&psi_disabled))
 		return;
 
-	if (!task->pid)
+	if (!curr->pid)
+		return;
+
+	lockdep_assert_rq_held(rq);
+	group = task_psi_group(curr);
+	if (prev && task_psi_group(prev) == group)
 		return;
 
 	now = cpu_clock(cpu);
+	irq = irq_time_read(cpu);
+	delta = (s64)(irq - rq->psi_irq_time);
+	if (delta < 0)
+		return;
+	rq->psi_irq_time = irq;
 
-	group = task_psi_group(task);
 	do {
 		if (!group->enabled)
 			continue;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 3261b067b6..aa4c1c874f 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -56,7 +56,6 @@ static struct ctl_table sched_rt_sysctls[] = {
 		.mode           = 0644,
 		.proc_handler   = sched_rr_handler,
 	},
-	{}
 };
 
 static int __init sched_rt_sysctl_init(void)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ae50f21277..38aeedd8a6 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -112,6 +112,20 @@ extern int sysctl_sched_rt_runtime;
 extern int sched_rr_timeslice;
 
 /*
+ * Asymmetric CPU capacity bits
+ */
+struct asym_cap_data {
+	struct list_head link;
+	struct rcu_head rcu;
+	unsigned long capacity;
+	unsigned long cpus[];
+};
+
+extern struct list_head asym_cap_list;
+
+#define cpu_capacity_span(asym_data) to_cpumask((asym_data)->cpus)
+
+/*
  * Helpers for converting nanosecond timing to jiffy resolution
  */
 #define NS_TO_JIFFIES(TIME)	((unsigned long)(TIME) / (NSEC_PER_SEC / HZ))
@@ -701,7 +715,7 @@ struct rt_rq {
 	} highest_prio;
 #endif
 #ifdef CONFIG_SMP
-	int			overloaded;
+	bool			overloaded;
 	struct plist_head	pushable_tasks;
 
 #endif /* CONFIG_SMP */
@@ -745,7 +759,7 @@ struct dl_rq {
 		u64		next;
 	} earliest_dl;
 
-	int			overloaded;
+	bool			overloaded;
 
 	/*
 	 * Tasks on this rq that can be pushed away. They are kept in
@@ -838,10 +852,6 @@ struct perf_domain {
 	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
@@ -862,10 +872,10 @@ struct root_domain {
 	 * - More than one runnable task
 	 * - Running task is misfit
 	 */
-	int			overload;
+	bool			overloaded;
 
 	/* Indicate one or more cpus over-utilized (tipping point) */
-	int			overutilized;
+	bool			overutilized;
 
 	/*
 	 * The bit corresponding to a CPU gets set here if such CPU has more
@@ -905,8 +915,6 @@ struct root_domain {
 	cpumask_var_t		rto_mask;
 	struct cpupri		cpupri;
 
-	unsigned long		max_cpu_capacity;
-
 	/*
 	 * NULL-terminated list of performance domains intersecting with the
 	 * CPUs of the rd. Protected by RCU.
@@ -920,6 +928,17 @@ extern void rq_attach_root(struct rq *rq, struct root_domain *rd);
 extern void sched_get_rd(struct root_domain *rd);
 extern void sched_put_rd(struct root_domain *rd);
 
+static inline int get_rd_overloaded(struct root_domain *rd)
+{
+	return READ_ONCE(rd->overloaded);
+}
+
+static inline void set_rd_overloaded(struct root_domain *rd, int status)
+{
+	if (get_rd_overloaded(rd) != status)
+		WRITE_ONCE(rd->overloaded, status);
+}
+
 #ifdef HAVE_RT_PUSH_IPI
 extern void rto_push_irq_work_func(struct irq_work *work);
 #endif
@@ -1091,8 +1110,8 @@ struct rq {
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 	struct sched_avg	avg_irq;
 #endif
-#ifdef CONFIG_SCHED_THERMAL_PRESSURE
-	struct sched_avg	avg_thermal;
+#ifdef CONFIG_SCHED_HW_PRESSURE
+	struct sched_avg	avg_hw;
 #endif
 	u64			idle_stamp;
 	u64			avg_idle;
@@ -1107,6 +1126,7 @@ struct rq {
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 	u64			prev_irq_time;
+	u64			psi_irq_time;
 #endif
 #ifdef CONFIG_PARAVIRT
 	u64			prev_steal_time;
@@ -1533,24 +1553,6 @@ static inline u64 rq_clock_task(struct rq *rq)
 	return rq->clock_task;
 }
 
-/**
- * By default the decay is the default pelt decay period.
- * The decay shift can change the decay period in
- * multiples of 32.
- *  Decay shift		Decay period(ms)
- *	0			32
- *	1			64
- *	2			128
- *	3			256
- *	4			512
- */
-extern int sched_thermal_decay_shift;
-
-static inline u64 rq_clock_thermal(struct rq *rq)
-{
-	return rq_clock_task(rq) >> sched_thermal_decay_shift;
-}
-
 static inline void rq_clock_skip_update(struct rq *rq)
 {
 	lockdep_assert_rq_held(rq);
@@ -2399,7 +2401,7 @@ extern struct task_struct *pick_next_task_idle(struct rq *rq);
 
 extern void update_group_capacity(struct sched_domain *sd, int cpu);
 
-extern void trigger_load_balance(struct rq *rq);
+extern void sched_balance_trigger(struct rq *rq);
 
 extern void set_cpus_allowed_common(struct task_struct *p, struct affinity_context *ctx);
 
@@ -2462,7 +2464,7 @@ extern void init_sched_dl_class(void);
 extern void init_sched_rt_class(void);
 extern void init_sched_fair_class(void);
 
-extern void reweight_task(struct task_struct *p, int prio);
+extern void reweight_task(struct task_struct *p, const struct load_weight *lw);
 
 extern void resched_curr(struct rq *rq);
 extern void resched_cpu(int cpu);
@@ -2519,10 +2521,8 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
 	}
 
 #ifdef CONFIG_SMP
-	if (prev_nr < 2 && rq->nr_running >= 2) {
-		if (!READ_ONCE(rq->rd->overload))
-			WRITE_ONCE(rq->rd->overload, 1);
-	}
+	if (prev_nr < 2 && rq->nr_running >= 2)
+		set_rd_overloaded(rq->rd, 1);
 #endif
 
 	sched_update_tick_dependency(rq);
@@ -2906,7 +2906,7 @@ extern void cfs_bandwidth_usage_dec(void);
 #define NOHZ_NEWILB_KICK_BIT	2
 #define NOHZ_NEXT_KICK_BIT	3
 
-/* Run rebalance_domains() */
+/* Run sched_balance_domains() */
 #define NOHZ_BALANCE_KICK	BIT(NOHZ_BALANCE_KICK_BIT)
 /* Update blocked load */
 #define NOHZ_STATS_KICK		BIT(NOHZ_STATS_KICK_BIT)
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index 857f837f52..78e48f5426 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -113,7 +113,7 @@ void __update_stats_enqueue_sleeper(struct rq *rq, struct task_struct *p,
  * Bump this up when changing the output format or the meaning of an existing
  * format, so that tools can adapt (or abort)
  */
-#define SCHEDSTAT_VERSION 15
+#define SCHEDSTAT_VERSION 16
 
 static int show_schedstat(struct seq_file *seq, void *v)
 {
@@ -150,8 +150,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
 
 			seq_printf(seq, "domain%d %*pb", dcount++,
 				   cpumask_pr_args(sched_domain_span(sd)));
-			for (itype = CPU_IDLE; itype < CPU_MAX_IDLE_TYPES;
-					itype++) {
+			for (itype = 0; itype < CPU_MAX_IDLE_TYPES; itype++) {
 				seq_printf(seq, " %u %u %u %u %u %u %u %u",
 				    sd->lb_count[itype],
 				    sd->lb_balanced[itype],
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 38f3698f5e..b02dfc3229 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -110,8 +110,12 @@ __schedstats_from_se(struct sched_entity *se)
 void psi_task_change(struct task_struct *task, int clear, int set);
 void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 		     bool sleep);
-void psi_account_irqtime(struct task_struct *task, u32 delta);
-
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+void psi_account_irqtime(struct rq *rq, struct task_struct *curr, struct task_struct *prev);
+#else
+static inline void psi_account_irqtime(struct rq *rq, struct task_struct *curr,
+				       struct task_struct *prev) {}
+#endif /*CONFIG_IRQ_TIME_ACCOUNTING */
 /*
  * PSI tracks state that persists across sleeps, such as iowaits and
  * memory stalls. As a result, it has to distinguish between sleeps,
@@ -192,7 +196,8 @@ static inline void psi_ttwu_dequeue(struct task_struct *p) {}
 static inline void psi_sched_switch(struct task_struct *prev,
 				    struct task_struct *next,
 				    bool sleep) {}
-static inline void psi_account_irqtime(struct task_struct *task, u32 delta) {}
+static inline void psi_account_irqtime(struct rq *rq, struct task_struct *curr,
+				       struct task_struct *prev) {}
 #endif /* CONFIG_PSI */
 
 #ifdef CONFIG_SCHED_INFO
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 3127c9b30a..a6994a1fcc 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -322,7 +322,6 @@ static struct ctl_table sched_energy_aware_sysctls[] = {
 		.extra1         = SYSCTL_ZERO,
 		.extra2         = SYSCTL_ONE,
 	},
-	{}
 };
 
 static int __init sched_energy_aware_sysctl_init(void)
@@ -1330,23 +1329,12 @@ next:
 }
 
 /*
- * Asymmetric CPU capacity bits
- */
-struct asym_cap_data {
-	struct list_head link;
-	unsigned long capacity;
-	unsigned long cpus[];
-};
-
-/*
  * Set of available CPUs grouped by their corresponding capacities
  * Each list entry contains a CPU mask reflecting CPUs that share the same
  * capacity.
  * The lifespan of data is unlimited.
  */
-static LIST_HEAD(asym_cap_list);
-
-#define cpu_capacity_span(asym_data) to_cpumask((asym_data)->cpus)
+LIST_HEAD(asym_cap_list);
 
 /*
  * Verify whether there is any CPU capacity asymmetry in a given sched domain.
@@ -1386,21 +1374,39 @@ asym_cpu_capacity_classify(const struct cpumask *sd_span,
 
 }
 
+static void free_asym_cap_entry(struct rcu_head *head)
+{
+	struct asym_cap_data *entry = container_of(head, struct asym_cap_data, rcu);
+	kfree(entry);
+}
+
 static inline void asym_cpu_capacity_update_data(int cpu)
 {
 	unsigned long capacity = arch_scale_cpu_capacity(cpu);
-	struct asym_cap_data *entry = NULL;
+	struct asym_cap_data *insert_entry = NULL;
+	struct asym_cap_data *entry;
 
+	/*
+	 * Search if capacity already exits. If not, track which the entry
+	 * where we should insert to keep the list ordered descendingly.
+	 */
 	list_for_each_entry(entry, &asym_cap_list, link) {
 		if (capacity == entry->capacity)
 			goto done;
+		else if (!insert_entry && capacity > entry->capacity)
+			insert_entry = list_prev_entry(entry, link);
 	}
 
 	entry = kzalloc(sizeof(*entry) + cpumask_size(), GFP_KERNEL);
 	if (WARN_ONCE(!entry, "Failed to allocate memory for asymmetry data\n"))
 		return;
 	entry->capacity = capacity;
-	list_add(&entry->link, &asym_cap_list);
+
+	/* If NULL then the new capacity is the smallest, add last. */
+	if (!insert_entry)
+		list_add_tail_rcu(&entry->link, &asym_cap_list);
+	else
+		list_add_rcu(&entry->link, &insert_entry->link);
 done:
 	__cpumask_set_cpu(cpu, cpu_capacity_span(entry));
 }
@@ -1423,8 +1429,8 @@ static void asym_cpu_capacity_scan(void)
 
 	list_for_each_entry_safe(entry, next, &asym_cap_list, link) {
 		if (cpumask_empty(cpu_capacity_span(entry))) {
-			list_del(&entry->link);
-			kfree(entry);
+			list_del_rcu(&entry->link);
+			call_rcu(&entry->rcu, free_asym_cap_entry);
 		}
 	}
 
@@ -1434,8 +1440,8 @@ static void asym_cpu_capacity_scan(void)
 	 */
 	if (list_is_singular(&asym_cap_list)) {
 		entry = list_first_entry(&asym_cap_list, typeof(*entry), link);
-		list_del(&entry->link);
-		kfree(entry);
+		list_del_rcu(&entry->link);
+		call_rcu(&entry->rcu, free_asym_cap_entry);
 	}
 }
 
@@ -2347,7 +2353,7 @@ static struct sched_domain *build_sched_domain(struct sched_domain_topology_leve
 static bool topology_span_sane(struct sched_domain_topology_level *tl,
 			      const struct cpumask *cpu_map, int cpu)
 {
-	int i;
+	int i = cpu + 1;
 
 	/* NUMA levels are allowed to overlap */
 	if (tl->flags & SDTL_OVERLAP)
@@ -2359,9 +2365,7 @@ static bool topology_span_sane(struct sched_domain_topology_level *tl,
 	 * breaking the sched_group lists - i.e. a later get_group() pass
 	 * breaks the linking done for an earlier span.
 	 */
-	for_each_cpu(i, cpu_map) {
-		if (i == cpu)
-			continue;
+	for_each_cpu_from(i, cpu_map) {
 		/*
 		 * We should 'and' all those masks with 'cpu_map' to exactly
 		 * match the topology we're about to build, but that can only
@@ -2507,16 +2511,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	/* Attach the domains */
 	rcu_read_lock();
 	for_each_cpu(i, cpu_map) {
-		unsigned long capacity;
-
 		rq = cpu_rq(i);
 		sd = *per_cpu_ptr(d.sd, i);
 
-		capacity = arch_scale_cpu_capacity(i);
-		/* Use READ_ONCE()/WRITE_ONCE() to avoid load/store tearing: */
-		if (capacity > READ_ONCE(d.rd->max_cpu_capacity))
-			WRITE_ONCE(d.rd->max_cpu_capacity, capacity);
-
 		cpu_attach_domain(sd, d.rd, i);
 
 		if (lowest_flag_domain(i, SD_CLUSTER))
@@ -2530,10 +2527,8 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	if (has_cluster)
 		static_branch_inc_cpuslocked(&sched_cluster_active);
 
-	if (rq && sched_debug_verbose) {
-		pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n",
-			cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);
-	}
+	if (rq && sched_debug_verbose)
+		pr_info("root domain span: %*pbl\n", cpumask_pr_args(cpu_map));
 
 	ret = 0;
 error: