Merge tag 'sched-core-2024-05-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Add cpufreq pressure feedback for the scheduler

 - Rework misfit load-balancing wrt affinity restrictions

 - Clean up and simplify the code around ::overutilized and
   ::overload access.

 - Simplify sched_balance_newidle()

 - Bump SCHEDSTAT_VERSION to 16 due to a cleanup of CPU_MAX_IDLE_TYPES
   handling that changed the output.

 - Rework & clean up <asm/vtime.h> interactions wrt arch_vtime_task_switch()

 - Reorganize, clean up and unify most of the higher level
   scheduler balancing function names around the sched_balance_*()
   prefix

 - Simplify the balancing flag code (sched_balance_running)

 - Miscellaneous cleanups & fixes

* tag 'sched-core-2024-05-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (50 commits)
  sched/pelt: Remove shift of thermal clock
  sched/cpufreq: Rename arch_update_thermal_pressure() => arch_update_hw_pressure()
  thermal/cpufreq: Remove arch_update_thermal_pressure()
  sched/cpufreq: Take cpufreq feedback into account
  cpufreq: Add a cpufreq pressure feedback for the scheduler
  sched/fair: Fix update of rd->sg_overutilized
  sched/vtime: Do not include <asm/vtime.h> header
  s390/irq,nmi: Include <asm/vtime.h> header directly
  s390/vtime: Remove unused __ARCH_HAS_VTIME_TASK_SWITCH leftover
  sched/vtime: Get rid of generic vtime_task_switch() implementation
  sched/vtime: Remove confusing arch_vtime_task_switch() declaration
  sched/balancing: Simplify the sg_status bitmask and use separate ->overloaded and ->overutilized flags
  sched/fair: Rename set_rd_overutilized_status() to set_rd_overutilized()
  sched/fair: Rename SG_OVERLOAD to SG_OVERLOADED
  sched/fair: Rename {set|get}_rd_overload() to {set|get}_rd_overloaded()
  sched/fair: Rename root_domain::overload to ::overloaded
  sched/fair: Use helper functions to access root_domain::overload
  sched/fair: Check root_domain::overload value before update
  sched/fair: Combine EAS check with root_domain::overutilized access
  sched/fair: Simplify the continue_balancing logic in sched_balance_newidle()
  ...

11 files changed, 381 insertions, 325 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7019a40457a6..1a914388144a 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);
@@ -5662,13 +5662,13 @@ 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 rq_flags rf;
-	unsigned long thermal_pressure;
+	unsigned long hw_pressure;
 	u64 resched_latency;
 
 	if (housekeeping_cpu(cpu, HK_TYPE_TICK))
@@ -5679,8 +5679,8 @@ void scheduler_tick(void)
 	rq_lock(rq, &rf);
 
 	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 +5700,7 @@ void scheduler_tick(void)
 
 #ifdef CONFIG_SMP
 	rq->idle_balance = idle_cpu(cpu);
-	trigger_load_balance(rq);
+	sched_balance_trigger(rq);
 #endif
 }
 
@@ -6585,7 +6585,7 @@ 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.
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index af7952f12e6c..aa48b2ec879d 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/fair.c b/kernel/sched/fair.c
index c62805dbd608..146ecf9cc3af 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);
@@ -388,8 +382,8 @@ 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 +400,7 @@ 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 +589,13 @@ 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 +665,7 @@ 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 +721,7 @@ 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)
@@ -1030,7 +1024,7 @@ 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 */
 }
 
 /*
@@ -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.
@@ -4745,7 +4739,7 @@ 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 +4822,7 @@ 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 +4965,22 @@ 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 +5002,7 @@ 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 +5012,6 @@ 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 +5028,14 @@ 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 +5066,7 @@ 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 +5086,8 @@ 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 +5107,19 @@ 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 +5155,7 @@ 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 +5261,7 @@ 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 +5410,7 @@ 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 +5446,7 @@ 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() &&
@@ -6675,22 +6682,47 @@ static inline void hrtick_update(struct rq *rq)
 #ifdef CONFIG_SMP
 static inline bool cpu_overutilized(int cpu)
 {
-	unsigned long rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN);
-	unsigned long rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX);
+	unsigned long  rq_util_min, rq_util_max;
+
+	if (!sched_energy_enabled())
+		return false;
+
+	rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN);
+	rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX);
 
 	/* Return true only if the utilization doesn't fit CPU's capacity */
 	return !util_fits_cpu(cpu_util_cfs(cpu), rq_util_min, rq_util_max, cpu);
 }
 
-static inline void update_overutilized_status(struct rq *rq)
+/*
+ * 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 (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu)) {
-		WRITE_ONCE(rq->rd->overutilized, SG_OVERUTILIZED);
-		trace_sched_overutilized_tp(rq->rd, SG_OVERUTILIZED);
-	}
+	if (!sched_energy_enabled())
+		return;
+
+	WRITE_ONCE(rd->overutilized, flag);
+	trace_sched_overutilized_tp(rd, flag);
+}
+
+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 (!is_rd_overutilized(rq->rd) && cpu_overutilized(rq->cpu))
+		set_rd_overutilized(rq->rd, 1);
 }
 #else
-static inline void update_overutilized_status(struct rq *rq) { }
+static inline void check_update_overutilized_status(struct rq *rq) { }
 #endif
 
 /* Runqueue only has SCHED_IDLE tasks enqueued */
@@ -6791,7 +6823,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	 * and the following generally works well enough in practice.
 	 */
 	if (!task_new)
-		update_overutilized_status(rq);
+		check_update_overutilized_status(rq);
 
 enqueue_throttle:
 	assert_list_leaf_cfs_rq(rq);
@@ -6878,7 +6910,7 @@ 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);
@@ -7110,13 +7142,13 @@ 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;
@@ -7172,7 +7204,7 @@ 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;
@@ -7197,13 +7229,13 @@ 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;
@@ -7471,7 +7503,7 @@ 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).
@@ -7515,7 +7547,7 @@ 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);
@@ -7948,7 +7980,7 @@ 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
@@ -7964,15 +7996,15 @@ 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;
 
 	/*
@@ -7995,7 +8027,7 @@ 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;
@@ -8007,18 +8039,17 @@ 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;
@@ -8039,7 +8070,7 @@ 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}.
@@ -8089,7 +8120,7 @@ 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);
 		}
 
@@ -8104,7 +8135,7 @@ 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,
@@ -8125,14 +8156,14 @@ 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;
@@ -8175,7 +8206,7 @@ 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;
@@ -8213,7 +8244,7 @@ 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);
@@ -8259,14 +8290,46 @@ 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)
@@ -8517,10 +8580,10 @@ 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.
 	 */
@@ -8598,7 +8661,7 @@ 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);
@@ -8936,7 +8999,7 @@ 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;
 
@@ -9082,7 +9145,7 @@ 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++;
@@ -9261,7 +9324,7 @@ 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))
@@ -9291,7 +9354,7 @@ 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;
 
 	/*
@@ -9300,11 +9363,11 @@ 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))
@@ -9423,7 +9486,7 @@ 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);
@@ -9442,25 +9505,25 @@ 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;
@@ -9468,19 +9531,18 @@ 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;		/* T