Merging upstream version 6.7.7.

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

17 files changed, 873 insertions, 942 deletions

diff --git a/kernel/sched/build_utility.c b/kernel/sched/build_utility.c
index 99bdd96f45..80a3df49ab 100644
--- a/kernel/sched/build_utility.c
+++ b/kernel/sched/build_utility.c
@@ -34,7 +34,6 @@
 #include <linux/nospec.h>
 #include <linux/proc_fs.h>
 #include <linux/psi.h>
-#include <linux/psi.h>
 #include <linux/ptrace_api.h>
 #include <linux/sched_clock.h>
 #include <linux/security.h>
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a854b71836..a708d225c2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -85,7 +85,6 @@
 
 #include "sched.h"
 #include "stats.h"
-#include "autogroup.h"
 
 #include "autogroup.h"
 #include "pelt.h"
@@ -114,6 +113,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_compute_energy_tp);
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
@@ -919,14 +919,13 @@ static bool set_nr_if_polling(struct task_struct *p)
 	struct thread_info *ti = task_thread_info(p);
 	typeof(ti->flags) val = READ_ONCE(ti->flags);
 
-	for (;;) {
+	do {
 		if (!(val & _TIF_POLLING_NRFLAG))
 			return false;
 		if (val & _TIF_NEED_RESCHED)
 			return true;
-		if (try_cmpxchg(&ti->flags, &val, val | _TIF_NEED_RESCHED))
-			break;
-	}
+	} while (!try_cmpxchg(&ti->flags, &val, val | _TIF_NEED_RESCHED));
+
 	return true;
 }
 
@@ -1480,16 +1479,12 @@ static void __uclamp_update_util_min_rt_default(struct task_struct *p)
 
 static void uclamp_update_util_min_rt_default(struct task_struct *p)
 {
-	struct rq_flags rf;
-	struct rq *rq;
-
 	if (!rt_task(p))
 		return;
 
 	/* Protect updates to p->uclamp_* */
-	rq = task_rq_lock(p, &rf);
+	guard(task_rq_lock)(p);
 	__uclamp_update_util_min_rt_default(p);
-	task_rq_unlock(rq, p, &rf);
 }
 
 static inline struct uclamp_se
@@ -1785,9 +1780,8 @@ static void uclamp_update_root_tg(void)
 	uclamp_se_set(&tg->uclamp_req[UCLAMP_MAX],
 		      sysctl_sched_uclamp_util_max, false);
 
-	rcu_read_lock();
+	guard(rcu)();
 	cpu_util_update_eff(&root_task_group.css);
-	rcu_read_unlock();
 }
 #else
 static void uclamp_update_root_tg(void) { }
@@ -1814,10 +1808,9 @@ static void uclamp_sync_util_min_rt_default(void)
 	smp_mb__after_spinlock();
 	read_unlock(&tasklist_lock);
 
-	rcu_read_lock();
+	guard(rcu)();
 	for_each_process_thread(g, p)
 		uclamp_update_util_min_rt_default(p);
-	rcu_read_unlock();
 }
 
 static int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
@@ -2218,10 +2211,10 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 		p->sched_class->prio_changed(rq, p, oldprio);
 }
 
-void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
+void wakeup_preempt(struct rq *rq, struct task_struct *p, int flags)
 {
 	if (p->sched_class == rq->curr->sched_class)
-		rq->curr->sched_class->check_preempt_curr(rq, p, flags);
+		rq->curr->sched_class->wakeup_preempt(rq, p, flags);
 	else if (sched_class_above(p->sched_class, rq->curr->sched_class))
 		resched_curr(rq);
 
@@ -2239,31 +2232,21 @@ int __task_state_match(struct task_struct *p, unsigned int state)
 	if (READ_ONCE(p->__state) & state)
 		return 1;
 
-#ifdef CONFIG_PREEMPT_RT
 	if (READ_ONCE(p->saved_state) & state)
 		return -1;
-#endif
+
 	return 0;
 }
 
 static __always_inline
 int task_state_match(struct task_struct *p, unsigned int state)
 {
-#ifdef CONFIG_PREEMPT_RT
-	int match;
-
 	/*
-	 * Serialize against current_save_and_set_rtlock_wait_state() and
-	 * current_restore_rtlock_saved_state().
+	 * Serialize against current_save_and_set_rtlock_wait_state(),
+	 * current_restore_rtlock_saved_state(), and __refrigerator().
 	 */
-	raw_spin_lock_irq(&p->pi_lock);
-	match = __task_state_match(p, state);
-	raw_spin_unlock_irq(&p->pi_lock);
-
-	return match;
-#else
+	guard(raw_spinlock_irq)(&p->pi_lock);
 	return __task_state_match(p, state);
-#endif
 }
 
 /*
@@ -2417,10 +2400,9 @@ void migrate_disable(void)
 		return;
 	}
 
-	preempt_disable();
+	guard(preempt)();
 	this_rq()->nr_pinned++;
 	p->migration_disabled = 1;
-	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(migrate_disable);
 
@@ -2444,7 +2426,7 @@ void migrate_enable(void)
 	 * Ensure stop_task runs either before or after this, and that
 	 * __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule().
 	 */
-	preempt_disable();
+	guard(preempt)();
 	if (p->cpus_ptr != &p->cpus_mask)
 		__set_cpus_allowed_ptr(p, &ac);
 	/*
@@ -2455,7 +2437,6 @@ void migrate_enable(void)
 	barrier();
 	p->migration_disabled = 0;
 	this_rq()->nr_pinned--;
-	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(migrate_enable);
 
@@ -2527,7 +2508,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
 	rq_lock(rq, rf);
 	WARN_ON_ONCE(task_cpu(p) != new_cpu);
 	activate_task(rq, p, 0);
-	check_preempt_curr(rq, p, 0);
+	wakeup_preempt(rq, p, 0);
 
 	return rq;
 }
@@ -3413,7 +3394,7 @@ static void __migrate_swap_task(struct task_struct *p, int cpu)
 		deactivate_task(src_rq, p, 0);
 		set_task_cpu(p, cpu);
 		activate_task(dst_rq, p, 0);
-		check_preempt_curr(dst_rq, p, 0);
+		wakeup_preempt(dst_rq, p, 0);
 
 		rq_unpin_lock(dst_rq, &drf);
 		rq_unpin_lock(src_rq, &srf);
@@ -3520,13 +3501,11 @@ out:
  */
 void kick_process(struct task_struct *p)
 {
-	int cpu;
+	guard(preempt)();
+	int cpu = task_cpu(p);
 
-	preempt_disable();
-	cpu = task_cpu(p);
 	if ((cpu != smp_processor_id()) && task_curr(p))
 		smp_send_reschedule(cpu);
-	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(kick_process);
 
@@ -3789,7 +3768,7 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 	}
 
 	activate_task(rq, p, en_flags);
-	check_preempt_curr(rq, p, wake_flags);
+	wakeup_preempt(rq, p, wake_flags);
 
 	ttwu_do_wakeup(p);
 
@@ -3813,9 +3792,6 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 		if (rq->avg_idle > max)
 			rq->avg_idle = max;
 
-		rq->wake_stamp = jiffies;
-		rq->wake_avg_idle = rq->avg_idle / 2;
-
 		rq->idle_stamp = 0;
 	}
 #endif
@@ -3860,7 +3836,7 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags)
 			 * it should preempt the task that is current now.
 			 */
 			update_rq_clock(rq);
-			check_preempt_curr(rq, p, wake_flags);
+			wakeup_preempt(rq, p, wake_flags);
 		}
 		ttwu_do_wakeup(p);
 		ret = 1;
@@ -3960,6 +3936,18 @@ bool cpus_share_cache(int this_cpu, int that_cpu)
 	return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
 }
 
+/*
+ * Whether CPUs are share cache resources, which means LLC on non-cluster
+ * machines and LLC tag or L2 on machines with clusters.
+ */
+bool cpus_share_resources(int this_cpu, int that_cpu)
+{
+	if (this_cpu == that_cpu)
+		return true;
+
+	return per_cpu(sd_share_id, this_cpu) == per_cpu(sd_share_id, that_cpu);
+}
+
 static inline bool ttwu_queue_cond(struct task_struct *p, int cpu)
 {
 	/*
@@ -4040,13 +4028,17 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  * The caller holds p::pi_lock if p != current or has preemption
  * disabled when p == current.
  *
- * The rules of PREEMPT_RT saved_state:
+ * The rules of saved_state:
  *
  *   The related locking code always holds p::pi_lock when updating
  *   p::saved_state, which means the code is fully serialized in both cases.
  *
- *   The lock wait and lock wakeups happen via TASK_RTLOCK_WAIT. No other
- *   bits set. This allows to distinguish all wakeup scenarios.
+ *   For PREEMPT_RT, the lock wait and lock wakeups happen via TASK_RTLOCK_WAIT.
+ *   No other bits set. This allows to distinguish all wakeup scenarios.
+ *
+ *   For FREEZER, the wakeup happens via TASK_FROZEN. No other bits set. This
+ *   allows us to prevent early wakeup of tasks before they can be run on
+ *   asymmetric ISA architectures (eg ARMv9).
  */
 static __always_inline
 bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
@@ -4060,13 +4052,13 @@ bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
 
 	*success = !!(match = __task_state_match(p, state));
 
-#ifdef CONFIG_PREEMPT_RT
 	/*
 	 * Saved state preserves the task state across blocking on
-	 * an RT lock.  If the state matches, set p::saved_state to
-	 * TASK_RUNNING, but do not wake the task because it waits
-	 * for a lock wakeup. Also indicate success because from
-	 * the regular waker's point of view this has succeeded.
+	 * an RT lock or TASK_FREEZABLE tasks.  If the state matches,
+	 * set p::saved_state to TASK_RUNNING, but do not wake the task
+	 * because it waits for a lock wakeup or __thaw_task(). Also
+	 * indicate success because from the regular waker's point of
+	 * view this has succeeded.
 	 *
 	 * After acquiring the lock the task will restore p::__state
 	 * from p::saved_state which ensures that the regular
@@ -4076,7 +4068,7 @@ bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
 	 */
 	if (match < 0)
 		p->saved_state = TASK_RUNNING;
-#endif
+
 	return match > 0;
 }
 
@@ -4258,7 +4250,7 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
 		 * __schedule().  See the comment for smp_mb__after_spinlock().
 		 *
-		 * A similar smb_rmb() lives in try_invoke_on_locked_down_task().
+		 * A similar smp_rmb() lives in __task_needs_rq_lock().
 		 */
 		smp_rmb();
 		if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags))
@@ -4875,7 +4867,7 @@ void wake_up_new_task(struct task_struct *p)
 
 	activate_task(rq, p, ENQUEUE_NOCLOCK);
 	trace_sched_wakeup_new(p);
-	check_preempt_curr(rq, p, WF_FORK);
+	wakeup_preempt(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_woken) {
 		/*
@@ -5918,8 +5910,7 @@ static noinline void __schedule_bug(struct task_struct *prev)
 	print_modules();
 	if (irqs_disabled())
 		print_irqtrace_events(prev);
-	if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)
-	    && in_atomic_preempt_off()) {
+	if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) {
 		pr_err("Preemption disabled at:");
 		print_ip_sym(KERN_ERR, preempt_disable_ip);
 	}
@@ -6370,8 +6361,9 @@ static void sched_core_balance(struct rq *rq)
 	struct sched_domain *sd;
 	int cpu = cpu_of(rq);
 
-	preempt_disable();
-	rcu_read_lock();
+	guard(preempt)();
+	guard(rcu)();
+
 	raw_spin_rq_unlock_irq(rq);
 	for_each_domain(cpu, sd) {
 		if (need_resched())
@@ -6381,8 +6373,6 @@ static void sched_core_balance(struct rq *rq)
 			break;
 	}
 	raw_spin_rq_lock_irq(rq);
-	rcu_read_unlock();
-	preempt_enable();
 }
 
 static DEFINE_PER_CPU(struct balance_callback, core_balance_head);
@@ -6721,22 +6711,24 @@ void __noreturn do_task_dead(void)
 
 static inline void sched_submit_work(struct task_struct *tsk)
 {
+	static DEFINE_WAIT_OVERRIDE_MAP(sched_map, LD_WAIT_CONFIG);
 	unsigned int task_flags;
 
-	if (task_is_running(tsk))
-		return;
+	/*
+	 * Establish LD_WAIT_CONFIG context to ensure none of the code called
+	 * will use a blocking primitive -- which would lead to recursion.
+	 */
+	lock_map_acquire_try(&sched_map);
 
 	task_flags = tsk->flags;
 	/*
 	 * If a worker goes to sleep, notify and ask workqueue whether it
 	 * wants to wake up a task to maintain concurrency.
 	 */
-	if (task_flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
-		if (task_flags & PF_WQ_WORKER)
-			wq_worker_sleeping(tsk);
-		else
-			io_wq_worker_sleeping(tsk);
-	}
+	if (task_flags & PF_WQ_WORKER)
+		wq_worker_sleeping(tsk);
+	else if (task_flags & PF_IO_WORKER)
+		io_wq_worker_sleeping(tsk);
 
 	/*
 	 * spinlock and rwlock must not flush block requests.  This will
@@ -6750,6 +6742,8 @@ static inline void sched_submit_work(struct task_struct *tsk)
 	 * make sure to submit it to avoid deadlocks.
 	 */
 	blk_flush_plug(tsk->plug, true);
+
+	lock_map_release(&sched_map);
 }
 
 static void sched_update_worker(struct task_struct *tsk)
@@ -6762,16 +6756,26 @@ static void sched_update_worker(struct task_struct *tsk)
 	}
 }
 
-asmlinkage __visible void __sched schedule(void)
+static __always_inline void __schedule_loop(unsigned int sched_mode)
 {
-	struct task_struct *tsk = current;
-
-	sched_submit_work(tsk);
 	do {
 		preempt_disable();
-		__schedule(SM_NONE);
+		__schedule(sched_mode);
 		sched_preempt_enable_no_resched();
 	} while (need_resched());
+}
+
+asmlinkage __visible void __sched schedule(void)
+{
+	struct task_struct *tsk = current;
+
+#ifdef CONFIG_RT_MUTEXES
+	lockdep_assert(!tsk->sched_rt_mutex);
+#endif
+
+	if (!task_is_running(tsk))
+		sched_submit_work(tsk);
+	__schedule_loop(SM_NONE);
 	sched_update_worker(tsk);
 }
 EXPORT_SYMBOL(schedule);
@@ -6835,11 +6839,7 @@ void __sched schedule_preempt_disabled(void)
 #ifdef CONFIG_PREEMPT_RT
 void __sched notrace schedule_rtlock(void)
 {
-	do {
-		preempt_disable();
-		__schedule(SM_RTLOCK_WAIT);
-		sched_preempt_enable_no_resched();
-	} while (need_resched());
+	__schedule_loop(SM_RTLOCK_WAIT);
 }
 NOKPROBE_SYMBOL(schedule_rtlock);
 #endif
@@ -7035,6 +7035,32 @@ static void __setscheduler_prio(struct task_struct *p, int prio)
 
 #ifdef CONFIG_RT_MUTEXES
 
+/*
+ * Would be more useful with typeof()/auto_type but they don't mix with
+ * bit-fields. Since it's a local thing, use int. Keep the generic sounding
+ * name such that if someone were to implement this function we get to compare
+ * notes.
+ */
+#define fetch_and_set(x, v) ({ int _x = (x); (x) = (v); _x; })
+
+void rt_mutex_pre_schedule(void)
+{
+	lockdep_assert(!fetch_and_set(current->sched_rt_mutex, 1));
+	sched_submit_work(current);
+}
+
+void rt_mutex_schedule(void)
+{
+	lockdep_assert(current->sched_rt_mutex);
+	__schedule_loop(SM_NONE);
+}
+
+void rt_mutex_post_schedule(void)
+{
+	sched_update_worker(current);
+	lockdep_assert(fetch_and_set(current->sched_rt_mutex, 0));
+}
+
 static inline int __rt_effective_prio(struct task_struct *pi_task, int prio)
 {
 	if (pi_task)
@@ -7188,9 +7214,8 @@ static inline int rt_effective_prio(struct task_struct *p, int prio)
 void set_user_nice(struct task_struct *p, long nice)
 {
 	bool queued, running;
-	int old_prio;
-	struct rq_flags rf;
 	struct rq *rq;
+	int old_prio;
 
 	if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE)
 		return;
@@ -7198,7 +7223,9 @@ void set_user_nice(struct task_struct *p, long nice)
 	 * We have to be careful, if called from sys_setpriority(),
 	 * the task might be in the middle of scheduling on another CPU.
 	 */
-	rq = task_rq_lock(p, &rf);
+	CLASS(task_rq_lock, rq_guard)(p);
+	rq = rq_guard.rq;
+
 	update_rq_clock(rq);
 
 	/*
@@ -7209,8 +7236,9 @@ void set_user_nice(struct task_struct *p, long nice)
 	 */
 	if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
 		p->static_prio = NICE_TO_PRIO(nice);
-		goto out_unlock;
+		return;
 	}
+
 	queued = task_on_rq_queued(p);
 	running = task_current(rq, p);
 	if (queued)
@@ -7233,9 +7261,6 @@ void set_user_nice(struct task_struct *p, long nice)
 	 * lowered its priority, then reschedule its CPU:
 	 */
 	p->sched_class->prio_changed(rq, p, old_prio);
-
-out_unlock:
-	task_rq_unlock(rq, p, &rf);
 }
 EXPORT_SYMBOL(set_user_nice);
 
@@ -7508,6 +7533,21 @@ static struct task_struct *find_process_by_pid(pid_t pid)
 	return pid ? find_task_by_vpid(pid) : current;
 }
 
+static struct task_struct *find_get_task(pid_t pid)
+{
+	struct task_struct *p;
+	guard(rcu)();
+
+	p = find_process_by_pid(pid);
+	if (likely(p))
+		get_task_struct(p);
+
+	return p;
+}
+
+DEFINE_CLASS(find_get_task, struct task_struct *, if (_T) put_task_struct(_T),
+	     find_get_task(pid), pid_t pid)
+
 /*
  * sched_setparam() passes in -1 for its policy, to let the functions
  * it calls know not to change it.
@@ -7545,14 +7585,11 @@ static void __setscheduler_params(struct task_struct *p,
 static bool check_same_owner(struct task_struct *p)
 {
 	const struct cred *cred = current_cred(), *pcred;
-	bool match;
+	guard(rcu)();
 
-	rcu_read_lock();
 	pcred = __task_cred(p);
-	match = (uid_eq(cred->euid, pcred->euid) ||
-		 uid_eq(cred->euid, pcred->uid));
-	rcu_read_unlock();
-	return match;
+	return (uid_eq(cred->euid, pcred->euid) ||
+		uid_eq(cred->euid, pcred->uid));
 }
 
 /*
@@ -7964,27 +8001,17 @@ static int
 do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
 {
 	struct sched_param lparam;
-	struct task_struct *p;
-	int retval;
 
 	if (!param || pid < 0)
 		return -EINVAL;
 	if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
 		return -EFAULT;
 
-	rcu_read_lock();
-	retval = -ESRCH;
-	p = find_process_by_pid(pid);
-	if (likely(p))
-		get_task_struct(p);
-	rcu_read_unlock();
-
-	if (likely(p)) {
-		retval = sched_setscheduler(p, policy, &lparam);
-		put_task_struct(p);
-	}
+	CLASS(find_get_task, p)(pid);
+	if (!p)
+		return -ESRCH;
 
-	return retval;
+	return sched_setscheduler(p, policy, &lparam);
 }
 
 /*
@@ -8080,7 +8107,6 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
 			       unsigned int, flags)
 {
 	struct sched_attr attr;
-	struct task_struct *p;
 	int retval;
 
 	if (!uattr || pid < 0 || flags)
@@ -8095,21 +8121,14 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
 	if (attr.sched_flags & SCHED_FLAG_KEEP_POLICY)
 		attr.sched_policy = SETPARAM_POLICY;
 
-	rcu_read_lock();
-	retval = -ESRCH;
-	p = find_process_by_pid(pid);
-	if (likely(p))
-		get_task_struct(p);
-	rcu_read_unlock();
+	CLASS(find_get_task, p)(pid);
+	if (!p)
+		return -ESRCH;
 
-	if (likely(p)) {
-		if (attr.sched_flags & SCHED_FLAG_KEEP_PARAMS)
-			get_params(p, &attr);
-		retval = sched_setattr(p, &attr);
-		put_task_struct(p);
-	}
+	if (attr.sched_flags & SCHED_FLAG_KEEP_PARAMS)
+		get_params(p, &attr);
 
-	return retval;
+	return sched_setattr(p, &attr);
 }
 
 /**
@@ -8127,16 +8146,17 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
 	if (pid < 0)
 		return -EINVAL;
 
-	retval = -ESRCH;
-	rcu_read_lock();
+	guard(rcu)();
 	p = find_process_by_pid(pid);
-	if (p) {
-		retval = security_task_getscheduler(p);
-		if (!retval)
-			retval = p->policy
-				| (p->sched_reset_on_fork ? SCHED_RESET_ON_FORK : 0);
+	if (!p)
+		return -ESRCH;
+
+	retval = security_task_getscheduler(p);
+	if (!retval) {
+		retval = p->policy;
+		if (p->sched_reset_on_fork)
+			retval |= SCHED_RESET_ON_FORK;
 	}
-	rcu_read_unlock();
 	return retval;
 }
 
@@ -8157,30 +8177,23 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
 	if (!param || pid < 0)
 		return -EINVAL;
 
-	rcu_read_lock();
-	p = find_process_by_pid(pid);
-	retval = -ESRCH;
-	if (!p)
-		goto out_unlock;
+	scoped_guard (rcu) {
+		p = find_process_by_pid(pid);
+		if (!p)
+			return -ESRCH;
 
-	retval = security_task_getscheduler(p);
-	if (retval)
-		goto out_unlock;
+		retval = security_task_getscheduler(p);
+		if (retval)
+			return retval;
 
-	if (task_has_rt_policy(p))
-		lp.sched_priority = p->rt_priority;
-	rcu_read_unlock();
+		if (task_has_rt_policy(p))
+			lp.sched_priority = p->rt_priority;
+	}
 
 	/*
 	 * This one might sleep, we cannot do it with a spinlock held ...
 	 */
-	retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
-
-	return retval;
-
-out_unlock:
-	rcu_read_unlock();
-	return retval;
+	return copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
 }
 
 /*
@@ -8240,46 +8253,38 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 	    usize < SCHED_ATTR_SIZE_VER0 || flags)
 		return -EINVAL;
 
-	rcu_read_lock();
-	p = find_process_by_pid(pid);
-	retval = -ESRCH;
-	if (!p)
-		goto out_unlock;
+	scoped_guard (rcu) {
+		p = find_process_by_pid(pid);
+		if (!p)
+			return -ESRCH;
 
-	retval = security_task_getscheduler(p);
-	if (retval)
-		goto out_unlock;
+		retval = security_task_getscheduler(p);
+		if (retval)
+			return retval;
 
-	kattr.sched_policy = p->policy;
-	if (p->sched_reset_on_fork)
-		kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
-	get_params(p, &kattr);
-	kattr.sched_flags &= SCHED_FLAG_ALL;
+		kattr.sched_policy = p->policy;
+		if (p->sched_reset_on_fork)
+			kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
+		get_params(p, &kattr);
+		kattr.sched_flags &= SCHED_FLAG_ALL;
 
 #ifdef CONFIG_UCLAMP_TASK
-	/*
-	 * This could race with another potential updater, but this is fine
-	 * because it'll correctly read the old or the new value. We don't need
-	 * to guarantee who wins the race as long as it doesn't return garbage.
-	 */
-	kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
-	kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
+		/*
+		 * This could race with another potential updater, but this is fine
+		 * because it'll correctly read the old or the new value. We don't need
+		 * to guarantee who wins the race as long as it doesn't return garbage.
+		 */
+		kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
+		kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
 #endif
-
-	rcu_read_unlock();
+	}
 
 	return sched_attr_copy_to_user(uattr, &kattr, usize);
-
-out_unlock:
-	rcu_read_unlock();
-	return retval;
 }
 
 #ifdef CONFIG_SMP
 int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
 {
-	int ret = 0;
-
 	/*
 	 * If the task isn't a deadline task or admission control is
 	 * disabled then we don't care about affinity changes.
@@ -8293,11 +8298,11 @@ int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
 	 * tasks allowed to run on all the CPUs in the task's
 	 * root_domain.
 	 */
-	rcu_read_lock();
+	guard(rcu)();
 	if (!cpumask_subset(task_rq(p)->rd->span, mask))
-		ret = -EBUSY;
-	rcu_read_unlock();
-	return ret;
+		return -EBUSY;
+
+	return 0;
 }
 #endif
 
@@ -8367,39 +8372,24 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 {
 	struct affinity_context ac;
 	struct cpumask *user_mask;
-	struct task_struct *p;
 	int retval;
 
-	rcu_read_lock();
-
-	p = find_process_by_pid(pid);
-	if (!p) {
-		rcu_read_unlock();
+	CLASS(find_get_task, p)(pid);
+	if (!p)
 		return -ESRCH;
-	}
-
-	/* Prevent p going away */
-	get_task_struct(p);
-	rcu_read_unlock();
 
-	if (p->flags & PF_NO_SETAFFINITY) {
-		retval = -EINVAL;
-		goto out_put_task;
-	}
+	if (p->flags & PF_NO_SETAFFINITY)
+		return -EINVAL;
 
 	if (!check_same_owner(p)) {
-		rcu_read_lock();
-		if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) {
-			rcu_read_unlock();
-			retval = -EPERM;
-			goto out_put_task;
-		}
-		rcu_read_unlock();
+		guard(rcu)();
+		if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE))
+			return -EPERM;
 	}
 
 	retval = security_task_setscheduler(p);
 	if (retval)
-		goto out_put_task;
+		return retval;
 
 	/*
 	 * With non-SMP configs, user_cpus_ptr/user_mask isn't used and
@@ -8409,8 +8399,7 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	if (user_mask) {
 		cpumask_copy(user_mask, in_mask);
 	} else if (IS_ENABLED(CONFIG_SMP)) {
-		retval = -ENOMEM;
-		goto out_put_task;
+		return -ENOMEM;
 	}
 
 	ac = (struct affinity_context){
@@ -8422,8 +8411,6 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	retval = __sched_setaffinity(p, &ac);
 	kfree(ac.user_mask);
 
-out_put_task:
-	put_task_struct(p);
 	return retval;
 }
 
@@ -8465,28 +8452,21 @@ SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
 long sched_getaffinity(pid_t pid, struct cpumask *mask)
 {
 	struct task_struct *p;
-	unsigned long flags;
 	int retval;
 
-	rcu_read_lock();
-
-	retval = -ESRCH;
+	guard(rcu)();
 	p = find_process_by_pid(pid);
 	if (!p)
-		goto out_unlock;
+		return -ESRCH;
 
 	retval = security_task_getscheduler(p);
 	if (retval)
-		goto out_unlock;
+		return retval;
 
-	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	guard(raw_spinlock_irqsave)(&p->pi_lock);
 	cpumask_and(mask, &p->cpus_mask, cpu_active_mask);
-	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-
-out_unlock:
-	rcu_read_unlock();
 
-	return retval;
+	return 0;
 }
 
 /**
@@ -8933,55 +8913,46 @@ int __sched yield_to(struct task_struct *p, bool preempt)
 {
 	struct task_struct *curr = current;
 	struct rq *rq, *p_rq;
-	unsigned long flags;
 	int yielded = 0;
 
-	local_irq_save(flags);
-	rq = this_rq();
+	scoped_guard (irqsave) {
+		rq = this_rq();
 
 again:
-	p_rq = task_rq(p);
-	/*
-	 * If we're the only runnable task on the rq and target rq also
-	 * has only one task, there's absolutely no point in yielding.
-	 */
-	if (rq->nr_running == 1 && p_rq->nr_running == 1) {
-		yielded = -ESRCH;
-		goto out_irq;
-	}
+		p_rq = task_rq(p);
+		/*
+		 * If we're the only runnable task on the rq and target rq also
+		 * has only one task, there's absolutely no point in yielding.
+		 */
+		if (rq->nr_running == 1 && p_rq->nr_running == 1)
+			return -ESRCH;
 
-	double_rq_lock(rq, p_rq);
-	if (task_rq(p) != p_rq) {
-		double_rq_unlock(rq, p_rq);
-		goto again;
-	}
+		guard(double_rq_lock)(rq, p_rq);
+		if (task_rq(p) != p_rq)
+			goto again;
 
-	if (!curr->sched_class->yield_to_task)
-		goto out_unlock;
+		if (!curr->sched_class->yield_to_task)
+			return 0;
 
-	if (curr->sched_class != p->sched_class)
-		goto out_unlock;
+		if (curr->sched_class != p->sched_class)
+			return 0;
 
-	if (task_on_cpu(p_rq, p) || !task_is_running(p))
-		goto out_unlock;
+		if (task_on_cpu(p_rq, p) || !task_is_running(p))
+			return 0;
 
-	yielded = curr->sched_class->yield_to_task(rq, p);
-	if (yielded) {
-		schedstat_inc(rq->yld_count);
-		/*
-		 * Make p's CPU reschedule; pick_next_entity takes care of
-		 * fairness.
-		 */
-		if (preempt && rq != p_rq)
-			resched_curr(p_rq);
+		yielded = curr->sched_class->yield_to_task(rq, p);
+		if (yielded) {
+			schedstat_inc(rq->yld_count);
+			/*
+			 * Make p's CPU reschedule; pick_next_entity
+			 * takes care of fairness.
+			 */
+			if (preempt && rq != p_rq)
+				resched_curr(p_rq);
+		}
 	}
 
-out_unlock:
-	double_rq_unlock(rq, p_rq);
-out_irq:
-	local_irq_restore(flags);
-
-	if (yielded > 0)
+	if (yielded)
 		schedule();
 
 	return yielded;
@@ -9084,38 +9055,30 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
 
 static int sched_rr_get_interval(pid_t pid, struct timespec64 *t)
 {
-	struct task_struct *p;
-	unsigned int time_slice;
-	struct rq_flags rf;
-	struct rq *rq;
+	unsigned int time_slice = 0;
 	int retval;
 
 	if (pid < 0)
 		return -EINVAL;
 
-	retval = -ESRCH;
-	rcu_read_lock();
-	p = find_process_by_pid(pid);
-	if (!p)
-		goto out_unlock;
+	scoped_guard (rcu) {
+		struct task_struct *p = find_process_by_pid(pid);
+		if (!p)
+			return -ESRCH;
 
-	retval = security_task_getscheduler(p);
-	if (retval)
-		goto out_unlock;
+		retval = security_task_getscheduler(p);
+		if (retval)
+			return retval;
 
-	rq = task_rq_lock(p, &rf);
-	time_slice = 0;
-	if (p->sched_class->get_rr_interval)
-		time_slice = p->sched_class->get_rr_interval(rq, p);
-	task_rq_unlock(rq, p, &rf);
+		scoped_guard (task_rq_lock, p) {
+			struct rq *rq = scope.rq;
+			if (p->sched_class->get_rr_interval)
+				time_slice = p->sched_class->get_rr_interval(rq, p);
+		}
+	}
 
-	rcu_read_unlock();
 	jiffies_to_timespec64(time_slice, t);
 	return 0;
-
-out_unlock:
-	rcu_read_unlock();
-	return retval;
 }
 
 /**
@@ -9174,9 +9137,9 @@ void sched_show_task(struct task_struct *p)
 	if (pid_alive(p))
 		ppid = task_pid_nr(rcu_dereference(p->real_parent));
 	rcu_read_unlock();
-	pr_cont(" stack:%-5lu pid:%-5d ppid:%-6d flags:0x%08lx\n",
-		free, task_pid_nr(p), ppid,
-		read_task_thread_flags(p));
+	pr_cont(" stack:%-5lu pid:%-5d tgid:%-5d ppid:%-6d flags:0x%08lx\n",
+		free, task_pid_nr(p), task_tgid_nr(p),
+		ppid, read_task_thread_flags(p));
 
 	print_worker_info(KERN_INFO, p);
 	print_stop_info(KERN_INFO, p);
@@ -9906,7 +9869,7 @@ struct task_group root_task_group;
 LIST_HEAD(task_groups);
 
 /* Cacheline aligned slab cache for task_group */
-static struct kmem_cache *task_group_cache __read_mostly;
+static struct kmem_cache *task_group_cache __ro_after_init;
 #endif
 
 void __init sched_init(void)
@@ -10016,7 +9979,7 @@ void __init sched_init(void)
 #ifdef CONFIG_SMP
 		rq->sd = NULL;
 		rq->rd = NULL;
-		rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE;
+		rq->cpu_capacity = SCHED_CAPACITY_SCALE;
 		rq->balance_callback = &balance_push_callback;
 		rq->active_balance = 0;
 		rq->next_balance = jiffies;
@@ -10025,8 +9988,6 @@ void __init sched_init(void)
 		rq->online = 0;
 		rq->idle_stamp = 0;
 		rq->avg_idle = 2*sysctl_sched_migration_cost;
-		rq->wake_stamp = jiffies;
-		rq->wake_avg_idle = rq->avg_idle;
 		rq->max_idle_balance_cost = sysctl_sched_migration_cost;
 
 		INIT_LIST_HEAD(&rq->cfs_tasks);
@@ -10292,9 +10253,9 @@ void normalize_rt_tasks(void)
 
 #endif /* CONFIG_MAGIC_SYSRQ */
 
-#if defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB)
+#if defined(CONFIG_KGDB_KDB)
 /*
- * These functions are only useful for the IA64 MCA handling, or kdb.
+ * These functions are only useful for kdb.
  *
  * They can only be called when the whole system has been
  * stopped - every CPU needs to be quiescent, and no scheduling
@@ -10316,30 +10277,7 @@ struct task_struct *curr_task(int cpu)
 	return cpu_curr(cpu);
 }
 
-#endif /* defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) */
-
-#ifdef CONFIG_IA64
-/**
- * ia64_set_curr_task - set the current task for a given CPU.
- * @cpu: the processor in question.
- * @p: the task pointer to set.
- *
- * Description: This function must only be used when non-maskable interrupts
- * are serviced on a separate stack. It allows the architecture to switch the
- * notion of the current task on a CPU in a non-blocking manner. This function
- * must be called with all CPU's synchronized, and interrupts disabled, the
- * and caller must save the original value of the current task (see
- * curr_task() above) and restore that value before reenabling interrupts and
- * re-starting the system.
- *
- * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
- */
-void ia64_set_curr_task(int cpu, struct task_struct *p)
-{
-	cpu_curr(cpu) = p;
-}
-
-#endif
+#endif /* defined(CONFIG_KGDB_KDB) */
 
 #ifdef CONFIG_CGROUP_SCHED
 /* task_group_lock serializes the addition/removal of task groups */
@@ -10501,17 +10439,18 @@ void sched_move_task(struct task_struct *tsk)
 	int queued, running, queue_flags =
 		DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
 	struct task_group *group;
-	struct rq_flags rf;
 	struct rq *rq;
 
-	rq = task_rq_lock(tsk, &rf);
+	CLASS(task_rq_lock, rq_guard)(tsk);
+	rq = rq_guard.rq;
+
 	/*
 	 * Esp. with SCHED_AUTOGROUP enabled it is possible to get superfluous
 	 * group changes.
 	 */
 	group = sched_get_task_group(tsk);
 	if (group == tsk->sched_task_group)
-		goto unlock;
+		return;
 
 	update_rq_clock(rq);
 
@@ -10536,9 +10475,6 @@ void sched_move_task(struct task_struct *tsk)
 		 */
 		resched_curr(rq);
 	}
-
-unlock:
-	task_rq_unlock(rq, tsk, &rf);
 }
 
 static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
@@ -10575,11 +10511,9 @@ static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
 
 #ifdef CONFIG_UCLAMP_TASK_GROUP
 	/* Propagate the effective uclamp value for the new group */
-	mutex_lock(&uclamp_mutex);
-	rcu_read_lock();
+	guard(mutex)(&uclamp_mutex);
+	guard(rcu)();
 	cpu_util_update_eff(css);
-	rcu_read_unlock();
-	mutex_unlock(&uclamp_mutex);
 #endif
 
 	return 0;
@@ -10730,8 +10664,8 @@ static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf,
 
 	static_branch_enable(&sched_uclamp_used);
 
-	mutex_lock(&uclamp_mutex);
-	rcu_read_lock();
+	guard(mutex)(&uclamp_mutex);
+	guard(rcu)();
 
 	tg = css_tg(of_css(of));
 	if (tg->uclamp_req[clamp_id].value != req.util)
@@ -10746,9 +10680,6 @@ static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf,
 	/* Update effective clamps to track the most restrictive value */
 	cpu_util_update_eff(of_css(of));
 
-	rcu_read_unlock();
-	mutex_unlock(&uclamp_mutex);
-
 	return nbytes;
 }
 
@@ -10774,10 +10705,10 @@ static inline void cpu_uclamp_print(struct seq_file *sf,
 	u64 percent;
 	u32 rem;
 
-	rcu_read_lock();
-	tg = css_tg(seq_css(sf));
-	util_clamp = tg->uclamp_req[clamp_id].value;
-	rcu_read_unlock();
+	scoped_guard (rcu) {
+		tg = css_tg(seq_css(sf));
+		util_clamp = tg->uclamp_req[clamp_id].value;
+	}
 
 	if (util_clamp == SCHED_CAPACITY_SCALE) {
 		seq_puts(sf, "max\n");
@@ -10868,11 +10799,12 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota,
 	 * Prevent race between setting of cfs_rq->runtime_enabled and
 	 * unthrottle_offline_cfs_rqs().
 	 */
-	cpus_read_lock();
-	mutex_lock(&cfs_constraints_mutex);
+	guard(cpus_read_lock)();
+	guard(mutex)(&cfs_constraints_mutex);
+
 	ret = __cfs_schedulable(tg, period, quota);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
 	runtime_enabled = quota != RUNTIME_INF;
 	runtime_was_enabled = cfs_b->quota != RUNTIME_INF;
@@ -10882,39 +10814,38 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota,
 	 */
 	if (runtime_enabled && !runtime_was_enabled)
 		cfs_bandwidth_usage_inc();
-	raw_spin_lock_irq(&cfs_b->lock);
-	cfs_b->period = ns_to_ktime(period);
-	cfs_b->quota = quota;
-	cfs_b->burst = burst;
 
-	__refill_cfs_bandwidth_runtime(cfs_b);
+	scoped_guard (raw_spinlock_irq, &cfs_b->lock) {
+		cfs_b->period = ns_to_ktime(period);
+		cfs_b->quota = quota;
+		cfs_b->burst = burst;
 
-	/* Restart the period timer (if active) to handle new period expiry: */
-	if (runtime_enabled)
-		start_cfs_bandwidth(cfs_b);
+		__refill_cfs_bandwidth_runtime(cfs_b);
 
-	raw_spin_unlock_irq(&cfs_b->lock);
+		/*
+		 * Restart the period timer (if active) to handle new
+		 * period expiry:
+		 */
+		if (runtime_enabled)
+			start_cfs_bandwidth(cfs_b);
+	}
 
 	for_each_online_cpu(i) {
 		struct cfs_rq *cfs_rq = tg->cfs_rq[i];
 		struct rq *rq = cfs_rq->rq;
-		struct rq_flags rf;
 
-		rq_lock_irq(rq, &rf);
+		guard(rq_lock_irq)(rq);
 		cfs_rq->runtime_enabled = runtime_enabled;
 		cfs_rq->runtime_remaining = 0;
 
 		if (cfs_rq->throttled)
 			unthrottle_cfs_rq(cfs_rq);
-		rq_unlock_irq(rq, &rf);
 	}
+
 	if (runtime_was_enabled && !runtime_enabled)
 		cfs_bandwidth_usage_dec();
-out_unlock:
-	mutex_unlock(&cfs_constraints_mutex);
-	cpus_read_unlock();
 
-	return ret;
+	return 0;
 }
 
 static int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
@@ -11099,7 +11030,6 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
 
 static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota)
 {
-	int ret;
 	struct cfs_schedulable_data data = {
 		.tg = tg,
 		.period = period,
@@ -11111,11 +11041,8 @@ static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota)
 		do_div(data.quota, NSEC_PER_USEC);
 	}
 
-	rcu_read_lock();
-	ret = walk_tg_tree(tg_cfs_schedulable_down, tg_nop, &data);
-	rcu_read_unlock();
-
-	return ret;
+	guard(rcu)();
+	return walk_tg_tree(tg_cfs_schedulable_down, tg_nop, &data);
 }
 
 static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
@@ -11720,14 +11647,12 @@ int __sched_mm_cid_migrate_from_fetch_cid(struct rq *src_rq,
 	 * are not the last task to be migrated from this cpu for this mm, so
 	 * there is no need to move src_cid to the destination cpu.
 	 */
-	rcu_read_lock();
+	guard(rcu)();
 	src_task = rcu_dereference(src_rq->curr);
 	if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) {
-		rcu_read_unlock();
 		t->last_mm_cid = -1;
 		return -1;
 	}
-	rcu_read_unlock();
 
 	return src_cid;
 }
@@ -11771,18 +11696,17 @@ int __sched_mm_cid_migrate_from_try_steal_cid(struct rq *src_rq,
 	 * the lazy-put flag, this task will be responsible for transitioning
 	 * from lazy-put flag set to MM_CID_UNSET.
 	 */
-	rcu_read_lock();
-	src_task = rcu_dereference(src_rq->curr);
-	if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) {
-		rcu_read_unlock();
-		/*
-		 * We observed an active task for this mm, there is therefore
-		 * no point in moving this cid to the destination cpu.
-		 */
-		t->last_mm_cid = -1;
-		return -1;
+	scoped_guard (rcu) {
+		src_task = rcu_dereference(src_rq->curr);
+		if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) {
+			/*
+			 * We observed an active task for this mm, there is therefore
+			 * no point in moving this cid to the destination cpu.
+			 */
+			t->last_mm_cid = -1;
+			return -1;
+		}
 	}
-	rcu_read_unlock();
 
 	/*
 	 * The src_cid is unused, so it can be unset.
@@ -11855,7 +11779,6 @@ static void sched_mm_cid_remote_clear(struct mm_struct *mm, struct mm_cid *pcpu_
 {
 	struct rq *rq = cpu_rq(cpu);
 	struct task_struct *t;
-	unsigned long flags;
 	int cid, lazy_cid;
 
 	cid = READ_ONCE(pcpu_cid->cid);
@@ -11890,23 +11813,21 @@ static void sched_mm_cid_remote_clear(struct mm_struct *mm, struct mm_cid *pcpu_
 	 * the lazy-put flag, that task will be responsible for transitioning
 	 * from lazy-put flag set to MM_CID_UNSET.
 	 */
-	rcu_read_lock();
-	t = rcu_dereference(rq->curr);
-	if (READ_ONCE(t->mm_cid_active) && t->mm == mm) {
-		rcu_read_unlock();
-		return;
+	scoped_guard (rcu) {
+		t = rcu_dereference(rq->curr);
+		if (READ_ONCE(t->mm_cid_active) && t->mm == mm)
+			return;
 	}
-	rcu_read_unlock();
 
 	/*
 	 * The cid is unused, so it can be unset.
 	 * Disable interrupts to keep the window of cid ownership without rq
 	 * lock small.
 	 */
-	local_irq_save(flags);
-	if (try_cmpxchg(&pcpu_cid->cid, &lazy_cid, MM_CID_UNSET))
-		__mm_cid_put(mm, cid);
-	local_irq_restore(flags);
+	scoped_guard (irqsave) {
+		if (try_cmpxchg(&pcpu_cid->cid, &lazy_cid, MM_CID_UNSET))
+			__mm_cid_put(mm, cid);
+	}
 }
 
 static void sched_mm_cid_remote_clear_old(struct mm_struct *mm, int cpu)
@@ -11928,14 +11849,13 @@ static void sched_mm_cid_remote_clear_old(struct mm_struct *mm, int cpu)
 	 * snapshot associated with this cid if an active task using the mm is
 	 * observed on this rq.
 	 */
-	rcu_read_lock();
-	curr = rcu_dereference(rq->curr);
-	if (READ_ONCE(curr->mm_cid_active) && curr->mm == mm) {
-		WRITE_ONCE(pcpu_cid->time, rq_clock);
-		rcu_read_unlock();
-		return;
+	scoped_guard (rcu) {
+		curr = rcu_dereference(rq->curr);
+		if (READ_ONCE(curr->mm_cid_active) && curr->mm == mm) {
+			WRITE_ONCE(pcpu_cid->time, rq_clock);
+			return;
+		}
 	}
-	rcu_read_unlock();
 
 	if (rq_clock < pcpu_cid->time + SCHED_MM_CID_PERIOD_NS)
 		return;
@@ -12029,7 +11949,6 @@ void task_tick_mm_cid(struct rq *rq, struct task_struct *curr)
 void sched_mm_cid_exit_signals(struct task_struct *t)
 {
 	struct mm_struct *mm = t->mm;
-	struct rq_flags rf;
 	struct rq *rq;
 
 	if (!mm)
@@ -12037,7 +11956,7 @@ void sched_mm_cid_exit_signals(struct task_struct *t)
 
 	preempt_disable();
 	rq = this_rq();
-	rq_lock_irqsave(rq, &rf);
+	guard(rq_lock_irqsave)(rq);
 	preempt_enable_no_resched();	/* holding spinlock */
 	WRITE_ONCE(t->mm_cid_active, 0);
 	/*
@@ -12047,13 +11966,11 @@ void sched_mm_cid_exit_signals(struct task_struct *t)
 	smp_mb();
 	mm_cid_put(mm);
 	t->last_mm_cid = t->mm_cid = -1;
-	rq_unlock_irqrestore(rq, &rf);
 }
 
 void sched_mm_cid_before_execve(struct task_struct *t)
 {
 	struct mm_struct *mm = t->mm;
-	struct rq_flags rf;
 	struct rq *rq;
 
 	if (!mm)
@@ -12061,7 +11978,7 @@ void sched_mm_cid_before_execve(struct task_struct *t)
 
 	preempt_disable();
 	rq = this_rq();
-	rq_lock_irqsave(rq, &rf);
+	guard(rq_lock_irqsave)(rq);
 	preempt_enable_no_resched();	/* holding spinlock */
 	WRITE_ONCE(t->mm_cid_active, 0);
 	/*
@@ -12071,13 +11988,11 @@ void sched_mm_cid_before_execve(struct task_struct *t)
 	smp_mb();
 	mm_cid_put(mm);
 	t->last_mm_cid = t->mm_cid = -1;
-	rq_unlock_irqrestore(rq, &rf);
 }
 
 void sched_mm_cid_after_execve(struct task_struct *t)
 {
 	struct mm_struct *mm = t->mm;
-	struct rq_flags rf;
 	struct rq *rq;
 
 	if (!mm)
@@ -12085,16 +12000,16 @@ void sched_mm_cid_after_execve(struct task_struct *t)
 
 	preempt_disable();
 	rq = this_rq();
-	rq_lock_irqsave(rq, &rf);
-	preempt_enable_no_resched();	/* holding spinlock */
-	WRITE_ONCE(t->mm_cid_active, 1);
-	/*
-	 * Store t->mm_cid_active before loading per-mm/cpu cid.
-	 * Matches barrier in sched_mm_cid_remote_clear_old().
-	 */
-	smp_mb();
-	t->last_mm_cid = t->mm_cid = mm_cid_get(rq, mm);
-	rq_unlock_irqrestore(rq, &rf);
+	scoped_guard (rq_lock_irqsave, rq) {
+		preempt_enable_no_resched();	/* holding spinlock */
+		WRITE_ONCE(t->mm_cid_active, 1);
+		/*
+		 * Store t->mm_cid_active before loading per-mm/cpu cid.
+		 * Matches barrier in sched_mm_cid_remote_clear_old().
+		 */
+		smp_mb();
+		t->last_mm_cid = t->mm_cid = mm_cid_get(rq, mm);
+	}
 	rseq_set_notify_resume(t);
 }
 
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 57c92d751b..95baa12a10 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -131,7 +131,7 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
 			if (!dl_task_fits_capacity(p, cpu)) {
 				cpumask_clear_cpu(cpu, later_mask);
 
-				cap = capacity_orig_of(cpu);
+				cap = arch_scale_cpu_capacity(cpu);
 
 				if (cap > max_cap ||
 				    (cpu == task_cpu(p) && cap == max_cap)) {
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 458d359f59..5888176354 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -556,6 +556,31 @@ static const struct kobj_type sugov_tunables_ktype = {
 
 /********************** cpufreq governor interface *********************/
 
+#ifdef CONFIG_ENERGY_MODEL
+static void rebuild_sd_workfn(struct work_struct *work)
+{
+	rebuild_sched_domains_energy();
+}
+
+static DECLARE_WORK(rebuild_sd_work, rebuild_sd_workfn);
+
+/*
+ * EAS shouldn't be attempted without sugov, so rebuild the sched_domains
+ * on governor changes to make sure the scheduler knows about it.
+ */
+static void sugov_eas_rebuild_sd(void)
+{
+	/*
+	 * When called from the cpufreq_register_driver() path, the
+	 * cpu_hotplug_lock is already held, so use a work item to
+	 * avoid nested locking in rebuild_sched_domains().
+	 */
+	schedule_work(&rebuild_sd_work);
+}
+#else
+static inline void sugov_eas_rebuild_sd(void) { };
+#endif
+
 struct cpufreq_governor schedutil_gov;
 
 static struct sugov_policy *sugov_policy_alloc(struct cpufreq_policy *policy)
@@ -710,6 +735,8 @@ static int sugov_init(struct cpufreq_policy *policy)
 	if (ret)
 		goto fail;
 
+	sugov_eas_rebuild_sd();
+
 out:
 	mutex_unlock(&global_tunables_lock);
 	return 0;
@@ -751,6 +778,8 @@ static void sugov_exit(struct cpufreq_policy *policy)
 	sugov_kthread_stop(sg_policy);
 	sugov_policy_free(sg_policy);
 	cpufreq_disable_fast_switch(policy);
+
+	sugov_eas_rebuild_sd();
 }
 
 static int sugov_start(struct cpufreq_policy *policy)
@@ -768,14 +797,6 @@ static int sugov_start(struct cpufreq_policy *policy)
 
 	sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
 
-	for_each_cpu(cpu, policy->cpus) {
-		struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);
-
-		memset(sg_cpu, 0, sizeof(*sg_cpu));
-		sg_cpu->cpu			= cpu;
-		sg_cpu->sg_policy		= sg_policy;
-	}
-
 	if (policy_is_shared(policy))
 		uu = sugov_update_shared;
 	else if (policy->fast_switch_enabled && cpufreq_driver_has_adjust_perf())
@@ -786,6 +807,9 @@ static int sugov_start(struct cpufreq_policy *policy)
 	for_each_cpu(cpu, policy->cpus) {
 		struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);
 
+		memset(sg_cpu, 0, sizeof(*sg_cpu));
+		sg_cpu->cpu = cpu;
+		sg_cpu->sg_policy = sg_policy;
 		cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, uu);
 	}
 	return 0;
@@ -839,29 +863,3 @@ struct cpufreq_governor *cpufreq_default_governor(void)
 #endif
 
 cpufreq_governor_init(schedutil_gov);
-
-#ifdef CONFIG_ENERGY_MODEL
-static void rebuild_sd_workfn(struct work_struct *work)
-{
-	rebuild_sched_domains_energy();
-}
-static DECLARE_WORK(rebuild_sd_work, rebuild_sd_workfn);
-
-/*
- * EAS shouldn't be attempted without sugov, so rebuild the sched_domains
- * on governor changes to make sure the scheduler knows about it.
- */
-void sched_cpufreq_governor_change(struct cpufreq_policy *policy,
-				  struct cpufreq_governor *old_gov)
-{
-	if (old_gov == &schedutil_gov || policy->governor == &schedutil_gov) {
-		/*
-		 * When called from the cpufreq_register_driver() path, the
-		 * cpu_hotplug_lock is already held, so use a work item to
-		 * avoid nested locking in rebuild_sched_domains().
-		 */
-		schedule_work(&rebuild_sd_work);
-	}
-
-}
-#endif
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index d78f2e8769..b28114478b 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -132,7 +132,7 @@ static inline unsigned long __dl_bw_capacity(const struct cpumask *mask)
 	int i;
 
 	for_each_cpu_and(i, mask, cpu_active_mask)
-		cap += capacity_orig_of(i);
+		cap += arch_scale_cpu_capacity(i);
 
 	return cap;
 }
@@ -144,7 +144,7 @@ static inline unsigned long __dl_bw_capacity(const struct cpumask *mask)
 static inline unsigned long dl_bw_capacity(int i)
 {
 	if (!sched_asym_cpucap_active() &&
-	    capacity_orig_of(i) == SCHED_CAPACITY_SCALE) {
+	    arch_scale_cpu_capacity(i) == SCHED_CAPACITY_SCALE) {
 		return dl_bw_cpus(i) << SCHED_CAPACITY_SHIFT;
 	} else {
 		RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
@@ -509,7 +509,6 @@ void init_dl_rq(struct dl_rq *dl_rq)
 	/* zero means no -deadline tasks */
 	dl_rq->earliest_dl.curr = dl_rq->earliest_dl.next = 0;
 
-	dl_rq->dl_nr_migratory = 0;
 	dl_rq->overloaded = 0;
 	dl_rq->pushable_dl_tasks_root = RB_ROOT_CACHED;
 #else
@@ -553,39 +552,6 @@ static inline void dl_clear_overload(struct rq *rq)
 	cpumask_clear_cpu(rq->cpu, rq->rd->dlo_mask);
 }
 
-static void update_dl_migration(struct dl_rq *dl_rq)
-{
-	if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_running > 1) {
-		if (!dl_rq->overloaded) {
-			dl_set_overload(rq_of_dl_rq(dl_rq));
-			dl_rq->overloaded = 1;
-		}
-	} else if (dl_rq->overloaded) {
-		dl_clear_overload(rq_of_dl_rq(dl_rq));
-		dl_rq->overloaded = 0;
-	}
-}
-
-static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
-{
-	struct task_struct *p = dl_task_of(dl_se);
-
-	if (p->nr_cpus_allowed > 1)
-		dl_rq->dl_nr_migratory++;
-
-	update_dl_migration(dl_rq);
-}
-
-static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
-{
-	struct task_struct *p = dl_task_of(dl_se);
-
-	if (p->nr_cpus_allowed > 1)
-		dl_rq->dl_nr_migratory--;
-
-	update_dl_migration(dl_rq);
-}
-
 #define __node_2_pdl(node) \
 	rb_entry((node), struct task_struct, pushable_dl_tasks)
 
@@ -594,6 +560,11 @@ static inline bool __pushable_less(struct rb_node *a, const struct rb_node *b)
 	return dl_entity_preempt(&__node_2_pdl(a)->dl, &__node_2_pdl(b)->dl);
 }
 
+static inline int has_pushable_dl_tasks(struct rq *rq)
+{
+	return !RB_EMPTY_ROOT(&rq->dl.pushable_dl_tasks_root.rb_root);
+}
+
 /*
  * The list of pushable -deadline task is not a plist, like in
  * sched_rt.c, it is an rb-tree with tasks ordered by deadline.
@@ -609,6 +580,11 @@ static void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
 				 __pushable_less);
 	if (leftmost)
 		rq->dl.earliest_dl.next = p->dl.deadline;
+
+	if (!rq->dl.overloaded) {
+		dl_set_overload(rq);
+		rq->dl.overloaded = 1;
+	}
 }
 
 static void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
@@ -625,11 +601,11 @@ static void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
 		dl_rq->earliest_dl.next = __node_2_pdl(leftmost)->dl.deadline;
 
 	RB_CLEAR_NODE(&p->pushable_dl_tasks);
-}
 
-static inline int has_pushable_dl_tasks(struct rq *rq)
-{
-	return !RB_EMPTY_ROOT(&rq->dl.pushable_dl_tasks_root.rb_root);
+	if (!has_pushable_dl_tasks(rq) && rq->dl.overloaded) {
+		dl_clear_overload(rq);
+		rq->dl.overloaded = 0;
+	}
 }
 
 static int push_dl_task(struct rq *rq);
@@ -763,7 +739,7 @@ static inline void deadline_queue_pull_task(struct rq *rq)
 
 static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags);
 static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags);
-static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p, int flags);
+static void wakeup_preempt_dl(struct rq *rq, struct task_struct *p, int flags);
 
 static inline void replenish_dl_new_period(struct sched_dl_entity *dl_se,
 					    struct rq *rq)
@@ -1175,7 +1151,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 
 	enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
 	if (dl_task(rq->curr))
-		check_preempt_curr_dl(rq, p, 0);
+		wakeup_preempt_dl(rq, p, 0);
 	else
 		resched_curr(rq);
 
@@ -1504,7 +1480,6 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 	add_nr_running(rq_of_dl_rq(dl_rq), 1);
 
 	inc_dl_deadline(dl_rq, deadline);
-	inc_dl_migration(dl_se, dl_rq);
 }
 
 static inline
@@ -1518,7 +1493,6 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 	sub_nr_running(rq_of_dl_rq(dl_rq), 1);
 
 	dec_dl_deadline(dl_rq, dl_se->deadline);
-	dec_dl_migration(dl_se, dl_rq);
 }
 
 static inline bool __dl_less(struct rb_node *a, const struct rb_node *b)
@@ -1939,7 +1913,7 @@ static int balance_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
  * Only called when both the current and waking task are -deadline
  * tasks.
  */
-static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
+static void wakeup_preempt_dl(struct rq *rq, struct task_struct *p,
 				  int flags)
 {
 	if (dl_entity_preempt(&p->dl, &rq->curr->dl)) {
@@ -2291,9 +2265,6 @@ static int push_dl_task(struct rq *rq)
 	struct rq *later_rq;
 	int ret = 0;
 
-	if (!rq->dl.overloaded)
-		return 0;
-
 	next_task = pick_next_pushable_dl_task(rq);
 	if (!next_task)
 		return 0;
@@ -2654,7 +2625,7 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
 			deadline_queue_push_tasks(rq);
 #endif
 		if (dl_task(rq->curr))
-			check_preempt_curr_dl(rq, p, 0);
+			wakeup_preempt_dl(rq, p, 0);
 		else
 			resched_curr(rq);
 	} else {
@@ -2723,7 +2694,7 @@ DEFINE_SCHED_CLASS(dl) = {
 	.dequeue_task		= dequeue_task_dl,
 	.yield_task		= yield_task_dl,
 
-	.check_preempt_curr	= check_preempt_curr_dl,
+	.wakeup_preempt		= wakeup_preempt_dl,
 
 	.pick_next_task		= pick_next_task_dl,
 	.put_prev_task		= put_prev_task_dl,
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 4c3d0d9f3d..4580a45070 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -8,7 +8,7 @@
  */
 
 /*
- * This allows printing both to /proc/sched_debug and
+ * This allows printing both to /sys/kernel/debug/sched/debug and
  * to the console
  */
 #define SEQ_printf(m, x...)			\
@@ -724,9 +724,6 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rt_rq->x))
 
 	PU(rt_nr_running);
-#ifdef CONFIG_SMP
-	PU(rt_nr_migratory);
-#endif
 	P(rt_throttled);
 	PN(rt_time);
 	PN(rt_runtime);
@@ -748,7 +745,6 @@ void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq)
 
 	PU(dl_nr_running);
 #ifdef CONFIG_SMP
-	PU(dl_nr_migratory);
 	dl_bw = &cpu_rq(cpu)->rd->dl_bw;
 #else
 	dl_bw = &dl_rq->dl_bw;
@@ -864,7 +860,6 @@ static void sched_debug_header(struct seq_file *m)
 #define PN(x) \
 	SEQ_printf(m, "  .%-40s: %Ld.%06ld\n", #x, SPLIT_NS(x))
 	PN(sysctl_sched_base_slice);
-	P(sysctl_sched_child_runs_first);
 	P(sysctl_sched_features);
 #undef PN
 #undef P
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d336af9cba..7ac9f4b1d9 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -51,8 +51,6 @@
 
 #include <asm/switch_to.h>
 
-#include <linux/sched/cond_resched.h>
-
 #include "sched.h"
 #include "stats.h"
 #include "autogroup.h"
@@ -78,12 +76,6 @@ unsigned int sysctl_sched_tunable_scaling = SCHED_TUNABLESCALING_LOG;
 unsigned int sysctl_sched_base_slice			= 750000ULL;
 static unsigned int normalized_sysctl_sched_base_slice	= 750000ULL;
 
-/*
- * After fork, child runs first. If set to 0 (default) then
- * parent will (try to) run first.
- */
-unsigned int sysctl_sched_child_runs_first __read_mostly;
-
 const_debug unsigned int sysctl_sched_migration_cost	= 500000UL;
 
 int sched_thermal_decay_shift;
@@ -145,13 +137,6 @@ static unsigned int sysctl_numa_balancing_promote_rate_limit = 65536;
 
 #ifdef CONFIG_SYSCTL
 static struct ctl_table sched_fair_sysctls[] = {
-	{
-		.procname       = "sched_child_runs_first",
-		.data           = &sysctl_sched_child_runs_first,
-		.maxlen         = sizeof(unsigned int),
-		.mode           = 0644,
-		.proc_handler   = proc_dointvec,
-	},
 #ifdef CONFIG_CFS_BANDWIDTH
 	{
 		.procname       = "sched_cfs_bandwidth_slice_us",
@@ -1774,12 +1759,12 @@ static bool pgdat_free_space_enough(struct pglist_data *pgdat)
  * The smaller the hint page fault latency, the higher the possibility
  * for the page to be hot.
  */
-static int numa_hint_fault_latency(struct page *page)
+static int numa_hint_fault_latency(struct folio *folio)
 {
 	int last_time, time;
 
 	time = jiffies_to_msecs(jiffies);
-	last_time = xchg_page_access_time(page, time);
+	last_time = folio_xchg_access_time(folio, time);
 
 	return (time - last_time) & PAGE_ACCESS_TIME_MASK;
 }
@@ -1836,7 +1821,7 @@ static void numa_promotion_adjust_threshold(struct pglist_data *pgdat,
 	}
 }
 
-bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
+bool should_numa_migrate_memory(struct task_struct *p, struct folio *folio,
 				int src_nid, int dst_cpu)
 {
 	struct numa_group *ng = deref_curr_numa_group(p);
@@ -1866,16 +1851,16 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
 		numa_promotion_adjust_threshold(pgdat, rate_limit, def_th);
 
 		th = pgdat->nbp_threshold ? : def_th;
-		latency = numa_hint_fault_latency(page);
+		latency = numa_hint_fault_latency(folio);
 		if (latency >= th)
 			return false;
 
 		return !numa_promotion_rate_limit(pgdat, rate_limit,
-						  thp_nr_pages(page));
+						  folio_nr_pages(folio));
 	}
 
 	this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid);
-	last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
+	last_cpupid = folio_xchg_last_cpupid(folio, this_cpupid);
 
 	if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) &&
 	    !node_is_toptier(src_nid) && !cpupid_valid(last_cpupid))
@@ -2899,19 +2884,7 @@ static void task_numa_placement(struct task_struct *p)
 	}
 
 	/* Cannot migrate task to CPU-less node */
-	if (max_nid != NUMA_NO_NODE && !node_state(max_nid, N_CPU)) {
-		int near_nid = max_nid;
-		int distance, near_distance = INT_MAX;
-
-		for_each_node_state(nid, N_CPU) {
-			distance = node_distance(max_nid, nid);
-			if (distance < near_distance) {
-				near_nid = nid;
-				near_distance = distance;
-			}
-		}
-		max_nid = near_nid;
-	}
+	max_nid = numa_nearest_node(max_nid, N_CPU);
 
 	if (ng) {
 		numa_group_count_active_nodes(ng);
@@ -3182,7 +3155,7 @@ static void reset_ptenuma_scan(struct task_struct *p)
 	p->mm->numa_scan_offset = 0;
 }
 
-static bool vma_is_accessed(struct vm_area_struct *vma)
+static bool vma_is_accessed(struct mm_struct *mm, struct vm_area_struct *vma)
 {
 	unsigned long pids;
 	/*
@@ -3191,11 +3164,23 @@ static bool vma_is_accessed(struct vm_area_struct *vma)
 	 * This is also done to avoid any side effect of task scanning
 	 * amplifying the unfairness of disjoint set of VMAs' access.
 	 */
-	if (READ_ONCE(current->mm->numa_scan_seq) < 2)
+	if ((READ_ONCE(current->mm->numa_scan_seq) - vma->numab_state->start_scan_seq) < 2)
+		return true;
+
+	pids = vma->numab_state->pids_active[0] | vma->numab_state->pids_active[1];
+	if (test_bit(hash_32(current->pid, ilog2(BITS_PER_LONG)), &pids))
+		return true;
+
+	/*
+	 * Complete a scan that has already started regardless of PID access, or
+	 * some VMAs may never be scanned in multi-threaded applications:
+	 */
+	if (mm->numa_scan_offset > vma->vm_start) {
+		trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_IGNORE_PID);
 		return true;
+	}
 
-	pids = vma->numab_state->access_pids[0] | vma->numab_state->access_pids[1];
-	return test_bit(hash_32(current->pid, ilog2(BITS_PER_LONG)), &pids);
+	return false;
 }
 
 #define VMA_PID_RESET_PERIOD (4 * sysctl_numa_balancing_scan_delay)
@@ -3215,6 +3200,8 @@ static void task_numa_work(struct callback_head *work)
 	unsigned long nr_pte_updates = 0;
 	long pages, virtpages;
 	struct vma_iterator vmi;
+	bool vma_pids_skipped;
+	bool vma_pids_forced = false;
 
 	SCHED_WARN_ON(p != container_of(work, struct task_struct, numa_work));
 
@@ -3257,7 +3244,6 @@ static void task_numa_work(struct callback_head *work)
 	 */
 	p->node_stamp += 2 * TICK_NSEC;
 
-	start = mm->numa_scan_offset;
 	pages = sysctl_numa_balancing_scan_size;
 	pages <<= 20 - PAGE_SHIFT; /* MB in pages */
 	virtpages = pages * 8;	   /* Scan up to this much virtual space */
@@ -3267,6 +3253,16 @@ static void task_numa_work(struct callback_head *work)
 
 	if (!mmap_read_trylock(mm))
 		return;
+
+	/*
+	 * VMAs are skipped if the current PID has not trapped a fault within
+	 * the VMA recently. Allow scanning to be forced if there is no
+	 * suitable VMA remaining.
+	 */
+	vma_pids_skipped = false;
+
+retry_pids:
+	start = mm->numa_scan_offset;
 	vma_iter_init(&vmi, mm, start);
 	vma = vma_next(&vmi);
 	if (!vma) {
@@ -3279,6 +3275,7 @@ static void task_numa_work(struct callback_head *work)
 	do {
 		if (!vma_migratable(vma) || !vma_policy_mof(vma) ||
 			is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) {
+			trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_UNSUITABLE);
 			continue;
 		}
 
@@ -3289,15 +3286,19 @@ static void task_numa_work(struct callback_head *work)
 		 * as migrating the pages will be of marginal benefit.
 		 */
 		if (!vma->vm_mm ||
-		    (vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) == (VM_READ)))
+		    (vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) == (VM_READ))) {
+			trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_SHARED_RO);
 			continue;
+		}
 
 		/*
 		 * Skip inaccessible VMAs to avoid any confusion between
 		 * PROT_NONE and NUMA hinting ptes
 		 */
-		if (!vma_is_accessible(vma))
+		if (!vma_is_accessible(vma)) {
+			trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_INACCESSIBLE);
 			continue;
+		}
 
 		/* Initialise new per-VMA NUMAB state. */
 		if (!vma->numab_state) {
@@ -3306,12 +3307,21 @@ static void task_numa_work(struct callback_head *work)
 			if (!vma->numab_state)
 				continue;
 
+			vma->numab_state->start_scan_seq = mm->numa_scan_seq;
+
 			vma->numab_state->next_scan = now +
 				msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
 
 			/* Reset happens after 4 times scan delay of scan start */
-			vma->numab_state->next_pid_reset =  vma->numab_state->next_scan +
+			vma->numab_state->pids_active_reset =  vma->numab_state->next_scan +
 				msecs_to_jiffies(VMA_PID_RESET_PERIOD);
+
+			/*
+			 * Ensure prev_scan_seq does not match numa_scan_seq,
+			 * to prevent VMAs being skipped prematurely on the
+			 * first scan:
+			 */
+			 vma->numab_state->prev_scan_seq = mm->numa_scan_seq - 1;
 		}
 
 		/*
@@ -3319,23 +3329,35 @@ static void task_numa_work(struct callback_head *work)
 		 * delay the scan for new VMAs.
 		 */
 		if (mm->numa_scan_seq && time_before(jiffies,
-						vma->numab_state->next_scan))
+						vma->numab_state->next_scan)) {
+			trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_SCAN_DELAY);
 			continue;
+		}
 
-		/* Do not scan the VMA if task has not accessed */
-		if (!vma_is_accessed(vma))
+		/* RESET access PIDs regularly for old VMAs. */
+		if (mm->numa_scan_seq &&
+				time_after(jiffies, vma->numab_state->pids_active_reset)) {
+			vma->numab_state->pids_active_reset = vma->numab_state->pids_active_reset +
+				msecs_to_jiffies(VMA_PID_RESET_PERIOD);
+			vma->numab_state->pids_active[0] = READ_ONCE(vma->numab_state->pids_active[1]);
+			vma->numab_state->pids_active[1] = 0;
+		}
+
+		/* Do not rescan VMAs twice within the same sequence. */
+		if (vma->numab_state->prev_scan_seq == mm->numa_scan_seq) {
+			mm->numa_scan_offset = vma->vm_end;
+			trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_SEQ_COMPLETED);
 			continue;
+		}
 
 		/*
-		 * RESET access PIDs regularly for old VMAs. Resetting after checking
-		 * vma for recent access to avoid clearing PID info before access..
+		 * Do not scan the VMA if task has not accessed it, unless no other
+		 * VMA candidate exists.
 		 */
-		if (mm->numa_scan_seq &&
-				time_after(jiffies, vma->numab_state->next_pid_reset)) {
-			vma->numab_state->next_pid_reset = vma->numab_state->next_pid_reset +
-				msecs_to_jiffies(VMA_PID_RESET_PERIOD);
-			vma->numab_state->access_pids[0] = READ_ONCE(vma->numab_state->access_pids[1]);
-			vma->numab_state->access_pids[1] = 0;
+		if (!vma_pids_forced && !vma_is_accessed(mm, vma)) {
+			vma_pids_skipped = true;
+			trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_PID_INACTIVE);
+			continue;
 		}
 
 		do {
@@ -3362,8 +3384,28 @@ static void task_numa_work(struct callback_head *work)
 
 			cond_resched();
 		} while (end != vma->vm_end);
+
+		/* VMA scan is complete, do not scan until next sequence. */
+		vma->numab_state->prev_scan_seq = mm->numa_scan_seq;
+
+		/*
+		 * Only force scan within one VMA at a time, to limit the
+		 * cost of scanning a potentially uninteresting VMA.
+		 */
+		if (vma_pids_forced)
+			break;
 	} for_each_vma(vmi, vma);
 
+	/*
+	 * If no VMAs are remaining and VMAs were skipped due to the PID
+	 * not accessing the VMA previously, then force a scan to ensure
+	 * forward progress:
+	 */
+	if (!vma && !vma_pids_forced && vma_pids_skipped) {
+		vma_pids_forced = true;
+		goto retry_pids;
+	}
+
 out:
 	/*
 	 * It is possible to reach the end of the VMA list but the last few
@@ -4047,7 +4089,8 @@ static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
  */
 static inline void update_tg_load_avg(struct cfs_rq *cfs_rq)
 {
-	long delta = cfs_rq->avg.load_avg - cfs_rq->tg_load_avg_contrib;
+	long delta;
+	u64 now;
 
 	/*
 	 * No need to update load_avg for root_task_group as it is not used.
@@ -4055,10 +4098,67 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq)
 	if (cfs_rq->tg == &root_task_group)
 		return;
 
+	/* rq has been offline and doesn't contribute to the share anymore: */
+	if (!cpu_active(cpu_of(rq_of(cfs_rq))))
+		return;
+
+	/*
+	 * For migration heavy workloads, access to tg->load_avg can be
+	 * unbound. Limit the update rate to at most once per ms.
+	 */
+	now = sched_clock_cpu(cpu_of(rq_of(cfs_rq)));
+	if (now - cfs_rq->last_update_tg_load_avg < NSEC_PER_MSEC)
+		return;
+
+	delta = cfs_rq->avg.load_avg - cfs_rq->tg_load_avg_contrib;
 	if (abs(delta) > cfs_rq->tg_load_avg_contrib / 64) {
 		atomic_long_add(delta, &cfs_rq->tg->load_avg);
 		cfs_rq->tg_load_avg_contrib = cfs_rq->avg.load_avg;
+		cfs_rq->last_update_tg_load_avg = now;
+	}
+}
+
+static inline void clear_tg_load_avg(struct cfs_rq *cfs_rq)
+{
+	long delta;
+	u64 now;
+
+	/*
+	 * No need to update load_avg for root_task_group, as it is not used.
+	 */
+	if (cfs_rq->tg == &root_task_group)
+		return;
+
+	now = sched_clock_cpu(cpu_of(rq_of(cfs_rq)));
+	delta = 0 - cfs_rq->tg_load_avg_contrib;
+	atomic_long_add(delta, &cfs_rq->tg->load_avg);
+	cfs_rq->tg_load_avg_contrib = 0;
+	cfs_rq->last_update_tg_load_avg = now;
+}
+
+/* CPU offline callback: */
+static void __maybe_unused clear_tg_offline_cfs_rqs(struct rq *rq)
+{
+	struct task_group *tg;
+
+	lockdep_assert_rq_held(rq);
+
+	/*
+	 * The rq clock has already been updated in
+	 * set_rq_offline(), so we should skip updating
+	 * the rq clock again in unthrottle_cfs_rq().
+	 */
+	rq_clock_start_loop_update(rq);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(tg, &task_groups, list) {
+		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
+
+		clear_tg_load_avg(cfs_rq);
 	}
+	rcu_read_unlock();
+
+	rq_clock_stop_loop_update(rq);
 }
 
 /*
@@ -4357,6 +4457,8 @@ static inline bool skip_blocked_update(struct sched_entity *se)
 
 static inline void update_tg_load_avg(struct cfs_rq *cfs_rq) {}
 
+static inline void clear_tg_offline_cfs_rqs(struct rq *rq) {}
+
 static inline int propagate_entity_load_avg(struct sched_entity *se)
 {
 	return 0;
@@ -4834,7 +4936,7 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
 	 * To avoid overestimation of actual task utilization, skip updates if
 	 * we cannot grant there is idle time in this CPU.
 	 */
-	if (task_util(p) > capacity_orig_of(cpu_of(rq_of(cfs_rq))))
+	if (task_util(p) > arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq))))
 		return;
 
 	/*
@@ -4882,14 +4984,14 @@ static inline int util_fits_cpu(unsigned long util,
 		return fits;
 
 	/*
-	 * We must use capacity_orig_of() for comparing against uclamp_min and
+	 * We must use arch_scale_cpu_capacity() for comparing against uclamp_min and
 	 * uclamp_max. We only care about capacity pressure (by using
 	 * capacity_of()) for comparing against the real util.
 	 *
 	 * If a task is boosted to 1024 for example, we don't want a tiny
 	 * pressure to skew the check whether it fits a CPU or not.
 	 *
-	 * Similarly if a task is capped to capacity_orig_of(little_cpu), it
+	 * 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
@@ -4901,7 +5003,7 @@ static inline int util_fits_cpu(unsigned long util,
 	 * For uclamp_max, we can tolerate a drop in performance level as the
 	 * goal is to cap the task. So it's okay if it's getting less.
 	 */
-	capacity_orig = capacity_orig_of(cpu);
+	capacity_orig = arch_scale_cpu_capacity(cpu);
 	capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu);
 
 	/*
@@ -5356,7 +5458,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
  * 4) do not run the "skip" process, if something else is available
  */
 static struct sched_entity *
-pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr)
+pick_next_entity(struct cfs_rq *cfs_rq)
 {
 	/*
 	 * Enabling NEXT_BUDDY will affect latency but not fairness.
@@ -5900,13 +6002,13 @@ static void unthrottle_cfs_rq_async(struct cfs_rq *cfs_rq)
 
 static bool distribute_cfs_runtime(struct cfs_bandwidth *cfs_b)
 {
-	struct cfs_rq *local_unthrottle = NULL;
 	int this_cpu = smp_processor_id();
 	u64 runtime, remaining = 1;
 	bool throttled = false;
-	struct cfs_rq *cfs_rq;
+	struct cfs_rq *cfs_rq, *tmp;
 	struct rq_flags rf;
 	struct rq *rq;
+	LIST_HEAD(local_unthrottle);
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq,
@@ -5922,11 +6024,9 @@ static bool distribute_cfs_runtime(struct cfs_bandwidth *cfs_b)
 		if (!cfs_rq_throttled(cfs_rq))
 			goto next;
 
-#ifdef CONFIG_SMP
 		/* Already queued for async unthrottle */
 		if (!list_empty(&cfs_rq->throttled_csd_list))
 			goto next;
-#endif
 
 		/* By the above checks, this should never be true */
 		SCHED_WARN_ON(cfs_rq->runtime_remaining > 0);
@@ -5943,11 +6043,17 @@ static bool distribute_cfs_runtime(struct cfs_bandwidth *cfs_b)
 
 		/* we check whether we're throttled above */
 		if (cfs_rq->runtime_remaining > 0) {
-			if (cpu_of(rq) != this_cpu ||
-			    SCHED_WARN_ON(local_unthrottle))
+			if (cpu_of(rq) != this_cpu) {
 				unthrottle_cfs_rq_async(cfs_rq);
-			else
-				local_unthrottle = cfs_rq;
+			} else {
+				/*
+				 * We currently only expect to be unthrottling
+				 * a single cfs_rq locally.
+				 */
+				SCHED_WARN_ON(!list_empty(&local_unthrottle));
+				list_add_tail(&cfs_rq->throttled_csd_list,
+					      &local_unthrottle);
+			}
 		} else {
 			throttled = true;
 		}
@@ -5955,15 +6061,23 @@ static bool distribute_cfs_runtime(struct cfs_bandwidth *cfs_b)
 next:
 		rq_unlock_irqrestore(rq, &rf);
 	}
-	rcu_read_unlock();
 
-	if (local_unthrottle) {
-		rq = cpu_rq(this_cpu);
+	list_for_each_entry_safe(cfs_rq, tmp, &local_unthrottle,
+				 throttled_csd_list) {
+		struct rq *rq = rq_of(cfs_rq);
+
 		rq_lock_irqsave(rq, &rf);
-		if (cfs_rq_throttled(local_unthrottle))
-			unthrottle_cfs_rq(local_unthrottle);
+
+		list_del_init(&cfs_rq->throttled_csd_list);
+
+		if (cfs_rq_throttled(cfs_rq))
+			unthrottle_cfs_rq(cfs_rq);
+
 		rq_unlock_irqrestore(rq, &rf);
 	}
+	SCHED_WARN_ON(!list_empty(&local_unthrottle));
+
+	rcu_read_unlock();
 
 	return throttled;
 }
@@ -6293,9 +6407,7 @@ static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 {
 	cfs_rq->runtime_enabled = 0;
 	INIT_LIST_HEAD(&cfs_rq->throttled_list);
-#ifdef CONFIG_SMP
 	INIT_LIST_HEAD(&cfs_rq->throttled_csd_list);
-#endif
 }
 
 void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
@@ -7253,45 +7365,9 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_rq_mask);
 	int i, cpu, idle_cpu = -1, nr = INT_MAX;
 	struct sched_domain_shared *sd_share;
-	struct rq *this_rq = this_rq();
-	int this = smp_processor_id();
-	struct sched_domain *this_sd = NULL;
-	u64 time = 0;
 
 	cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
 
-	if (sched_feat(SIS_PROP) && !has_idle_core) {
-		u64 avg_cost, avg_idle, span_avg;
-		unsigned long now = jiffies;
-
-		this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
-		if (!this_sd)
-			return -1;
-
-		/*
-		 * If we're busy, the assumption that the last idle period
-		 * predicts the future is flawed; age away the remaining
-		 * predicted idle time.
-		 */
-		if (unlikely(this_rq->wake_stamp < now)) {
-			while (this_rq->wake_stamp < now && this_rq->wake_avg_idle) {
-				this_rq->wake_stamp++;
-				this_rq->wake_avg_idle >>= 1;
-			}
-		}
-
-		avg_idle = this_rq->wake_avg_idle;
-		avg_cost = this_sd->avg_scan_cost + 1;
-
-		span_avg = sd->span_weight * avg_idle;
-		if (span_avg > 4*avg_cost)
-			nr = div_u64(span_avg, avg_cost);
-		else
-			nr = 4;
-
-		time = cpu_clock(this);
-	}
-
 	if (sched_feat(SIS_UTIL)) {
 		sd_share = rcu_dereference(per_cpu(sd_llc_shared, target));
 		if (sd_share) {
@@ -7303,6 +7379,30 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 		}
 	}
 
+	if (static_branch_unlikely(&sched_cluster_active)) {
+		struct sched_group *sg = sd->groups;
+
+		if (sg->flags & SD_CLUSTER) {
+			for_each_cpu_wrap(cpu, sched_group_span(sg), target + 1) {
+				if (!cpumask_test_cpu(cpu, cpus))
+					continue;
+
+				if (has_idle_core) {
+					i = select_idle_core(p, cpu, cpus, &idle_cpu);
+					if ((unsigned int)i < nr_cpumask_bits)
+						return i;
+				} else {
+					if (--nr <= 0)
+						return -1;
+					idle_cpu = __select_idle_cpu(cpu, p);
+					if ((unsigned int)idle_cpu < nr_cpumask_bits)
+						return idle_cpu;
+				}
+			}
+			cpumask_andnot(cpus, cpus, sched_group_span(sg));
+		}
+	}
+
 	for_each_cpu_wrap(cpu, cpus, target + 1) {
 		if (has_idle_core) {
 			i = select_idle_core(p, cpu, cpus, &idle_cpu);
@@ -7310,7 +7410,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 				return i;
 
 		} else {
-			if (!--nr)
+			if (--nr <= 0)
 				return -1;
 			idle_cpu = __select_idle_cpu(cpu, p);
 			if ((unsigned int)idle_cpu < nr_cpumask_bits)
@@ -7321,18 +7421,6 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 	if (has_idle_core)
 		set_idle_cores(target, false);
 
-	if (sched_feat(SIS_PROP) && this_sd && !has_idle_core) {
-		time = cpu_clock(this) - time;
-
-		/*
-		 * Account for the scan cost of wakeups against the average
-		 * idle time.
-		 */
-		this_rq->wake_avg_idle -= min(this_rq->wake_avg_idle, time);
-
-		update_avg(&this_sd->avg_scan_cost, time);
-	}
-
 	return idle_cpu;
 }
 
@@ -7372,7 +7460,7 @@ 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 = capacity_orig_of(cpu) - thermal_load_avg(cpu_rq(cpu));
+			cpu_cap = arch_scale_cpu_capacity(cpu) - thermal_load_avg(cpu_rq(cpu));
 
 		/*
 		 * First, select CPU which fits better (-1 being better than 0).
@@ -7412,7 +7500,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	bool has_idle_core = false;
 	struct sched_domain *sd;
 	unsigned long task_util, util_min, util_max;
-	int i, recent_used_cpu;
+	int i, recent_used_cpu, prev_aff = -1;
 
 	/*
 	 * On asymmetric system, update task utilization because we will check
@@ -7439,8 +7527,14 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	 */
 	if (prev != target && cpus_share_cache(prev, target) &&
 	    (available_idle_cpu(prev) || sched_idle_cpu(prev)) &&
-	    asym_fits_cpu(task_util, util_min, util_max, prev))
-		return prev;
+	    asym_fits_cpu(task_util, util_min, util_max, prev)) {
+
+		if (!static_branch_unlikely(&sched_cluster_active) ||
+		    cpus_share_resources(prev, target))
+			return prev;
+
+		prev_aff = prev;
+	}
 
 	/*
 	 * Allow a per-cpu kthread to stack with the wakee if the
@@ -7467,7 +7561,13 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	    (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
 	    cpumask_test_cpu(recent_used_cpu, p->cpus_ptr) &&
 	    asym_fits_cpu(task_util, util_min, util_max, recent_used_cpu)) {
-		return recent_used_cpu;
+
+		if (!static_branch_unlikely(&sched_cluster_active) ||
+		    cpus_share_resources(recent_used_cpu, target))
+			return recent_used_cpu;
+
+	} else {
+		recent_used_cpu = -1;
 	}
 
 	/*
@@ -7508,6 +7608,17 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	if ((unsigned)i < nr_cpumask_bits)
 		return i;
 
+	/*
+	 * For cluster machines which have lower sharing cache like L2 or
+	 * LLC Tag, we tend to find an idle CPU in the target's cluster
+	 * first. But prev_cpu or recent_used_cpu may also be a good candidate,
+	 * use them if possible when no idle CPU found in select_idle_cpu().
+	 */
+	if ((unsigned int)prev_aff < nr_cpumask_bits)
+		return prev_aff;
+	if ((unsigned int)recent_used_cpu < nr_cpumask_bits)
+		return recent_used_cpu;
+
 	return target;
 }
 
@@ -7614,7 +7725,7 @@ cpu_util(int cpu, struct task_struct *p, int dst_cpu, int boost)
 		util = max(util, util_est);
 	}
 
-	return min(util, capacity_orig_of(cpu));
+	return min(util, arch_scale_cpu_capacity(cpu));
 }
 
 unsigned long cpu_util_cfs(int cpu)
@@ -7766,11 +7877,16 @@ compute_energy(struct energy_env *eenv, struct perf_domain *pd,
 {
 	unsigned long max_util = eenv_pd_max_util(eenv, pd_cpus, p, dst_cpu);
 	unsigned long busy_time = eenv->pd_busy_time;
+	unsigned long energy;
 
 	if (dst_cpu >= 0)
 		busy_time = min(eenv->pd_cap, busy_time + eenv->task_busy_time);
 
-	return em_cpu_energy(pd->em_pd, max_util, busy_time, eenv->cpu_cap);
+	energy = em_cpu_energy(pd->em_pd, max_util, busy_time, eenv->cpu_cap);
+
+	trace_sched_compute_energy_tp(p, dst_cpu, energy, max_util, busy_time);
+
+	return energy;
 }
 
 /*
@@ -8140,7 +8256,7 @@ static void set_next_buddy(struct sched_entity *se)
 /*
  * Preempt the current task with a newly woken task if needed:
  */
-static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
+static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int wake_flags)
 {
 	struct task_struct *curr = rq->curr;
 	struct sched_entity *se = &curr->se, *pse = &p->se;
@@ -8153,7 +8269,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 
 	/*
 	 * This is possible from callers such as attach_tasks(), in which we
-	 * unconditionally check_preempt_curr() after an enqueue (which may have
+	 * unconditionally wakeup_preempt() after an enqueue (which may have
 	 * lead to a throttle).  This both saves work and prevents false
 	 * next-buddy nomination below.
 	 */
@@ -8245,7 +8361,7 @@ again:
 				goto again;
 		}
 
-		se = pick_next_entity(cfs_rq, curr);
+		se = pick_next_entity(cfs_rq);
 		cfs_rq = group_cfs_rq(se);
 	} while (cfs_rq);
 
@@ -8308,7 +8424,7 @@ again:
 			}
 		}
 
-		se = pick_next_entity(cfs_rq, curr);
+		se = pick_next_entity(cfs_rq);
 		cfs_rq = group_cfs_rq(se);
 	} while (cfs_rq);
 
@@ -8347,7 +8463,7 @@ simple:
 		put_prev_task(rq, prev);
 
 	do {
-		se = pick_next_entity(cfs_rq, NULL);
+		se = pick_next_entity(cfs_rq);
 		set_next_entity(cfs_rq, se);
 		cfs_rq = group_cfs_rq(se);
 	} while (cfs_rq);
@@ -9060,7 +9176,7 @@ static void attach_task(struct rq *rq, struct task_struct *p)
 
 	WARN_ON_ONCE(task_rq(p) != rq);
 	activate_task(rq, p, ENQUEUE_NOCLOCK);
-	check_preempt_curr(rq, p, 0);
+	wakeup_preempt(rq, p, 0);
 }
 
 /*
@@ -9400,8 +9516,6 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 	unsigned long capacity = scale_rt_capacity(cpu);
 	struct sched_group *sdg = sd->groups;
 
-	cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(cpu);
-
 	if (!capacity)
 		capacity = 1;
 
@@ -9477,7 +9591,7 @@ static inline int
 check_cpu_capacity(struct rq *rq, struct sched_domain *sd)
 {
 	return ((rq->cpu_capacity * sd->imbalance_pct) <
-				(rq->cpu_capacity_orig * 100));
+				(arch_scale_cpu_capacity(cpu_of(rq)) * 100));
 }
 
 /*
@@ -9488,7 +9602,7 @@ check_cpu_capacity(struct rq *rq, struct sched_domain *sd)
 static inline int check_misfit_status(struct rq *rq, struct sched_domain *sd)
 {
 	return rq->misfit_task_load &&
-		(rq->cpu_capacity_orig < rq->rd->max_cpu_capacity ||
+		(arch_scale_cpu_capacity(rq->cpu) < rq->rd->max_cpu_capacity ||
 		 check_cpu_capacity(rq, sd));
 }
 
@@ -9640,7 +9754,7 @@ static bool sched_use_asym_prio(struct sched_domain *sd, int cpu)
  * can only do it if @group is an SMT group and has exactly on busy CPU. Larger
  * imbalances in the number of CPUS are dealt with in find_busiest_group().
  *
- * If we are balancing load within an SMT core, or at DIE domain level, always
+ * If we are balancing load within an SMT core, or at PKG domain level, always
  * proceed.
  *
  * Return: true if @env::dst_cpu can do with asym_packing load balance. False
@@ -11659,36 +11773,39 @@ static inline int on_null_domain(struct rq *rq)
 
 #ifdef CONFIG_NO_HZ_COMMON
 /*
- * idle load balancing details
- * - When one of the busy CPUs notice that there may be an idle rebalancing
+ * NOHZ idle load balancing (ILB) details:
+ *
+ * - When one of the busy CPUs notices that there may be an idle rebalancing
  *   needed, they will kick the idle load balancer, which then does idle
  *   load balancing for all the idle CPUs.
- * - HK_TYPE_MISC CPUs are used for this task, because HK_TYPE_SCHED not set
+ *
+ * - HK_TYPE_MISC CPUs are used for this task, because HK_TYPE_SCHED is not set
  *   anywhere yet.
  */
-
 static inline int find_new_ilb(void)
 {
-	int ilb;
 	const struct cpumask *hk_mask;
+	int ilb_cpu;
 
 	hk_mask = housekeeping_cpumask(HK_TYPE_MISC);
 
-	for_each_cpu_and(ilb, nohz.idle_cpus_mask, hk_mask) {
+	for_each_cpu_and(ilb_cpu, nohz.idle_cpus_mask, hk_mask) {
 
-		if (ilb == smp_processor_id())
+		if (ilb_cpu == smp_processor_id())
 			continue;
 
-		if (idle_cpu(ilb))
-			return ilb;
+		if (idle_cpu(ilb_cpu))
+			return ilb_cpu;
 	}
 
-	return nr_cpu_ids;
+	return -1;
 }
 
 /*
- * Kick a CPU to do the nohz balancing, if it is time for it. We pick any
- * idle CPU in the HK_TYPE_MISC housekeeping set (if there is one).
+ * Kick a CPU to do the NOHZ balancing, if it is time for it, via a cross-CPU
+ * SMP function call (IPI).
+ *
+ * We pick the first idle CPU in the HK_TYPE_MISC housekeeping set (if there is one).
  */
 static void kick_ilb(unsigned int flags)
 {
@@ -11702,8 +11819,7 @@ static void kick_ilb(unsigned int flags)
 		nohz.next_balance = jiffies+1;
 
 	ilb_cpu = find_new_ilb();
-
-	if (ilb_cpu >= nr_cpu_ids)
+	if (ilb_cpu < 0)
 		return;
 
 	/*
@@ -11716,7 +11832,7 @@ static void kick_ilb(unsigned int flags)
 
 	/*
 	 * This way we generate an IPI on the target CPU which
-	 * is idle. And the softirq performing nohz idle load balance
+	 * is idle, and the softirq performing NOHZ idle load balancing
 	 * will be run before returning from the IPI.
 	 */
 	smp_call_function_single_async(ilb_cpu, &cpu_rq(ilb_cpu)->nohz_csd);
@@ -11745,7 +11861,7 @@ static void nohz_balancer_kick(struct rq *rq)
 
 	/*
 	 * None are in tickless mode and hence no need for NOHZ idle load
-	 * balancing.
+	 * balancing:
 	 */
 	if (likely(!atomic_read(&nohz.nr_cpus)))
 		return;
@@ -11767,9 +11883,8 @@ static void nohz_balancer_kick(struct rq *rq)
 	sd = rcu_dereference(rq->sd);
 	if (sd) {
 		/*
-		 * If there's a CFS task and the current CPU has reduced
-		 * capacity; kick the ILB to see if there's a better CPU to run
-		 * on.
+		 * If there's a runnable CFS task and the current CPU has reduced
+		 * capacity, kick the ILB to see if there's a better CPU to run on:
 		 */
 		if (rq->cfs.h_nr_running >= 1 && check_cpu_capacity(rq, sd)) {
 			flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
@@ -11821,11 +11936,11 @@ static void nohz_balancer_kick(struct rq *rq)
 	if (sds) {
 		/*
 		 * If there is an imbalance between LLC domains (IOW we could
-		 * increase the overall cache use), we need some less-loaded LLC
-		 * domain to pull some load. Likewise, we may need to spread
+		 * increase the overall cache utilization), we need a less-loaded LLC
+		 * domain to pull some load from. Likewise, we may need to spread
 		 * load within the current LLC domain (e.g. packed SMT cores but
 		 * other CPUs are idle). We can't really know from here how busy
-		 * the others are - so just get a nohz balance going if it looks
+		 * the others are - so just get a NOHZ balance going if it looks
 		 * like this LLC domain has tasks we could move.
 		 */
 		nr_busy = atomic_read(&sds->nr_busy_cpus);
@@ -12095,8 +12210,19 @@ static bool nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
 }
 
 /*
- * Check if we need to run the ILB for updating blocked load before entering
- * idle state.
+ * Check if we need to directly run the ILB for updating blocked load before
+ * entering idle state. Here we run ILB directly without issuing IPIs.
+ *
+ * Note that when this function is called, the tick may not yet be stopped on
+ * this CPU yet. nohz.idle_cpus_mask is updated only when tick is stopped and
+ * cleared on the next busy tick. In other words, nohz.idle_cpus_mask updates
+ * don't align with CPUs enter/exit idle to avoid bottlenecks due to high idle
+ * entry/exit rate (usec). So it is possible that _nohz_idle_balance() is
+ * 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
+ * cpu about to enter idle, because it can take a long time.
  */
 void nohz_run_idle_balance(int cpu)
 {
@@ -12338,6 +12464,9 @@ static void rq_offline_fair(struct rq *rq)
 
 	/* Ensure any throttled groups are reachable by pick_next_task */
 	unthrottle_offline_cfs_rqs(rq);
+
+	/* Ensure that we remove rq contribution to group share: */
+	clear_tg_offline_cfs_rqs(rq);
 }
 
 #endif /* CONFIG_SMP */
@@ -12541,7 +12670,7 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
 		if (p->prio > oldprio)
 			resched_curr(rq);
 	} else
-		check_preempt_curr(rq, p, 0);
+		wakeup_preempt(rq, p, 0);
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -12643,7 +12772,7 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p)
 		if (task_current(rq, p))
 			resched_curr(rq);
 		else
-			check_preempt_curr(rq, p, 0);
+			wakeup_preempt(rq, p, 0);
 	}
 }
 
@@ -13002,7 +13131,7 @@ DEFINE_SCHED_CLASS(fair) = {
 	.yield_task		= yield_task_fair,
 	.yield_to_task		= yield_to_task_fair,
 
-	.check_preempt_curr	= check_preempt_wakeup,
+	.wakeup_preempt		= check_preempt_wakeup_fair,
 
 	.pick_next_task		= __pick_next_task_fair,
 	.put_prev_task		= put_prev_task_fair,
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index f770168230..a3ddf84de4 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -49,7 +49,6 @@ SCHED_FEAT(TTWU_QUEUE, true)
 /*
  * When doing wakeups, attempt to limit superfluous scans of the LLC domain.
  */
-SCHED_FEAT(SIS_PROP, false)
 SCHED_FEAT(SIS_UTIL, true)
 
 /*
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 5007b25c5b..565f8374dd 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -401,7 +401,7 @@ balance_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 /*
  * Idle tasks are unconditionally rescheduled:
  */
-static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int flags)
+static void wakeup_preempt_idle(struct rq *rq, struct task_struct *p, int flags)
 {
 	resched_curr(rq);
 }
@@ -482,7 +482,7 @@ DEFINE_SCHED_CLASS(idle) = {
 	/* dequeue is not valid, we print a debug message there: */
 	.dequeue_task		= dequeue_task_idle,
 
-	.check_preempt_curr	= check_preempt_curr_idle,
+	.wakeup_preempt		= wakeup_preempt_idle,
 
 	.pick_next_task		= pick_next_task_idle,
 	.put_prev_task		= put_prev_task_idle,
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index 2ad881d077..4e715b9b27 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -162,6 +162,9 @@
 	| MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK			\
 	| MEMBARRIER_CMD_GET_REGISTRATIONS)
 
+static DEFINE_MUTEX(membarrier_ipi_mutex);
+#define SERIALIZE_IPI() guard(mutex)(&membarrier_ipi_mutex)
+
 static void ipi_mb(void *info)
 {
 	smp_mb();	/* IPIs should be serializing but paranoid. */
@@ -259,6 +262,7 @@ static int membarrier_global_expedited(void)
 	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
 		return -ENOMEM;
 
+	SERIALIZE_IPI();
 	cpus_read_lock();
 	rcu_read_lock();
 	for_each_online_cpu(cpu) {
@@ -347,6 +351,7 @@ static int membarrier_private_expedited(int flags, int cpu_id)
 	if (cpu_id < 0 && !zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
 		return -ENOMEM;
 
+	SERIALIZE_IPI();
 	cpus_read_lock();
 
 	if (cpu_id >= 0) {
@@ -460,6 +465,7 @@ static int sync_runqueues_membarrier_state(struct mm_struct *mm)
 	 * between threads which are users of @mm has its membarrier state
 	 * updated.
 	 */
+	SERIALIZE_IPI();
 	cpus_read_lock();
 	rcu_read_lock();
 	for_each_online_cpu(cpu) {
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index 0f31076826..63b6cf8982 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Per Entity Load Tracking
+ * Per Entity Load Tracking (PELT)
  *
  *  Copyright (C) 2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
  *
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 1d0f634725..7b4aa5809c 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -434,14 +434,13 @@ static u64 window_update(struct psi_window *win, u64 now, u64 value)
 	return growth;
 }
 
-static u64 update_triggers(struct psi_group *group, u64 now, bool *update_total,
+static void update_triggers(struct psi_group *group, u64 now,
 						   enum psi_aggregators aggregator)
 {
 	struct psi_trigger *t;
 	u64 *total = group->total[aggregator];
 	struct list_head *triggers;
 	u64 *aggregator_total;
-	*update_total = false;
 
 	if (aggregator == PSI_AVGS) {
 		triggers = &group->avg_triggers;
@@ -471,14 +470,6 @@ static u64 update_triggers(struct psi_group *group, u64 now, bool *update_total,
 		 * events without dropping any).
 		 */
 		if (new_stall) {
-			/*
-			 * Multiple triggers might be looking at the same state,
-			 * remember to update group->polling_total[] once we've
-			 * been through all of them. Also remember to extend the
-			 * polling time if we see new stall activity.
-			 */
-			*update_total = true;
-
 			/* Calculate growth since last update */
 			growth = window_update(&t->win, now, total[t->state]);
 			if (!t->pending_event) {
@@ -503,8 +494,6 @@ static u64 update_triggers(struct psi_group *group, u64 now, bool *update_total,
 		/* Reset threshold breach flag once event got generated */
 		t->pending_event = false;
 	}
-
-	return now + group->rtpoll_min_period;
 }
 
 static u64 update_averages(struct psi_group *group, u64 now)
@@ -565,7 +554,6 @@ static void psi_avgs_work(struct work_struct *work)
 	struct delayed_work *dwork;
 	struct psi_group *group;
 	u32 changed_states;
-	bool update_total;
 	u64 now;
 
 	dwork = to_delayed_work(work);
@@ -584,7 +572,7 @@ static void psi_avgs_work(struct work_struct *work)
 	 * go - see calc_avgs() and missed_periods.
 	 */
 	if (now >= group->avg_next_update) {
-		update_triggers(group, now, &update_total, PSI_AVGS);
+		update_triggers(group, now, PSI_AVGS);
 		group->avg_next_update = update_averages(group, now);
 	}
 
@@ -608,7 +596,7 @@ static void init_rtpoll_triggers(struct psi_group *group, u64 now)
 	group->rtpoll_next_update = now + group->rtpoll_min_period;
 }
 
-/* Schedule polling if it's not already scheduled or forced. */
+/* Schedule rtpolling if it's not already scheduled or forced. */
 static void psi_schedule_rtpoll_work(struct psi_group *group, unsigned long delay,
 				   bool force)
 {
@@ -640,7 +628,6 @@ static void psi_rtpoll_work(struct psi_group *group)
 {
 	bool force_reschedule = false;
 	u32 changed_states;
-	bool update_total;
 	u64 now;
 
 	mutex_lock(&group->rtpoll_trigger_lock);
@@ -649,37 +636,37 @@ static void psi_rtpoll_work(struct psi_group *group)
 
 	if (now > group->rtpoll_until) {
 		/*
-		 * We are either about to start or might stop polling if no
-		 * state change was recorded. Resetting poll_scheduled leaves
+		 * We are either about to start or might stop rtpolling if no
+		 * state change was recorded. Resetting rtpoll_scheduled leaves
 		 * a small window for psi_group_change to sneak in and schedule
-		 * an immediate poll_work before we get to rescheduling. One
-		 * potential extra wakeup at the end of the polling window
-		 * should be negligible and polling_next_update still keeps
+		 * an immediate rtpoll_work before we get to rescheduling. One
+		 * potential extra wakeup at the end of the rtpolling window
+		 * should be negligible and rtpoll_next_update still keeps
 		 * updates correctly on schedule.
 		 */
 		atomic_set(&group->rtpoll_scheduled, 0);
 		/*
-		 * A task change can race with the poll worker that is supposed to
+		 * A task change can race with the rtpoll worker that is supposed to
 		 * report on it. To avoid missing events, ensure ordering between
-		 * poll_scheduled and the task state accesses, such that if the poll
-		 * worker misses the state update, the task change is guaranteed to
-		 * reschedule the poll worker:
+		 * rtpoll_scheduled and the task state accesses, such that if the
+		 * rtpoll worker misses the state update, the task change is
+		 * guaranteed to reschedule the rtpoll worker:
 		 *
-		 * poll worker:
-		 *   atomic_set(poll_scheduled, 0)
+		 * rtpoll worker:
+		 *   atomic_set(rtpoll_scheduled, 0)
 		 *   smp_mb()
 		 *   LOAD states
 		 *
 		 * task change:
 		 *   STORE states
-		 *   if atomic_xchg(poll_scheduled, 1) == 0:
-		 *     schedule poll worker
+		 *   if atomic_xchg(rtpoll_scheduled, 1) == 0:
+		 *     schedule rtpoll worker
 		 *
 		 * The atomic_xchg() implies a full barrier.
 		 */
 		smp_mb();
 	} else {
-		/* Polling window is not over, keep rescheduling */
+		/* The rtpolling window is not over, keep rescheduling */
 		force_reschedule = true;
 	}
 
@@ -687,7 +674,7 @@ static void psi_rtpoll_work(struct psi_group *group)
 	collect_percpu_times(group, PSI_POLL, &changed_states);
 
 	if (changed_states & group->rtpoll_states) {
-		/* Initialize trigger windows when entering polling mode */
+		/* Initialize trigger windows when entering rtpolling mode */
 		if (now > group->rtpoll_until)
 			init_rtpoll_triggers(group, now);
 
@@ -706,10 +693,12 @@ static void psi_rtpoll_work(struct psi_group *group)
 	}
 
 	if (now >= group->rtpoll_next_update) {
-		group->rtpoll_next_update = update_triggers(group, now, &update_total, PSI_POLL);
-		if (update_total)
+		if (changed_states & group->rtpoll_states) {
+			update_triggers(group, now, PSI_POLL);
 			memcpy(group->rtpoll_total, group->total[PSI_POLL],
 				   sizeof(group->rtpoll_total));
+		}
+		group->rtpoll_next_update = now + group->rtpoll_min_period;
 	}
 
 	psi_schedule_rtpoll_work(group,
@@ -1009,6 +998,9 @@ void psi_account_irqtime(struct task_struct *task, u32 delta)
 	struct psi_group_cpu *groupc;
 	u64 now;
 
+	if (static_branch_likely(&psi_disabled))
+		return;
+
 	if (!task->pid)
 		return;
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 904dd85345..6aaf0a3d60 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -16,7 +16,7 @@ struct rt_bandwidth def_rt_bandwidth;
  * period over which we measure -rt task CPU usage in us.
  * default: 1s
  */
-unsigned int sysctl_sched_rt_period = 1000000;
+int sysctl_sched_rt_period = 1000000;
 
 /*
  * part of the period that we allow rt tasks to run in us.
@@ -34,9 +34,11 @@ static struct ctl_table sched_rt_sysctls[] = {
 	{
 		.procname       = "sched_rt_period_us",
 		.data           = &sysctl_sched_rt_period,
-		.maxlen         = sizeof(unsigned int),
+		.maxlen         = sizeof(int),
 		.mode           = 0644,
 		.proc_handler   = sched_rt_handler,
+		.extra1         = SYSCTL_ONE,
+		.extra2         = SYSCTL_INT_MAX,
 	},
 	{
 		.procname       = "sched_rt_runtime_us",
@@ -44,6 +46,8 @@ static struct ctl_table sched_rt_sysctls[] = {
 		.maxlen         = sizeof(int),
 		.mode           = 0644,
 		.proc_handler   = sched_rt_handler,
+		.extra1         = SYSCTL_NEG_ONE,
+		.extra2         = (void *)&sysctl_sched_rt_period,
 	},
 	{
 		.procname       = "sched_rr_timeslice_ms",
@@ -143,7 +147,6 @@ void init_rt_rq(struct rt_rq *rt_rq)
 #if defined CONFIG_SMP
 	rt_rq->highest_prio.curr = MAX_RT_PRIO-1;
 	rt_rq->highest_prio.next = MAX_RT_PRIO-1;
-	rt_rq->rt_nr_migratory = 0;
 	rt_rq->overloaded = 0;
 	plist_head_init(&rt_rq->pushable_tasks);
 #endif /* CONFIG_SMP */
@@ -358,53 +361,6 @@ static inline void rt_clear_overload(struct rq *rq)
 	cpumask_clear_cpu(rq->cpu, rq->rd->rto_mask);
 }
 
-static void update_rt_migration(struct rt_rq *rt_rq)
-{
-	if (rt_rq->rt_nr_migratory && rt_rq->rt_nr_total > 1) {
-		if (!rt_rq->overloaded) {
-			rt_set_overload(rq_of_rt_rq(rt_rq));
-			rt_rq->overloaded = 1;
-		}
-	} else if (rt_rq->overloaded) {
-		rt_clear_overload(rq_of_rt_rq(rt_rq));
-		rt_rq->overloaded = 0;
-	}
-}
-
-static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
-{
-	struct task_struct *p;
-
-	if (!rt_entity_is_task(rt_se))
-		return;
-
-	p = rt_task_of(rt_se);
-	rt_rq = &rq_of_rt_rq(rt_rq)->rt;
-
-	rt_rq->rt_nr_total++;
-	if (p->nr_cpus_allowed > 1)
-		rt_rq->rt_nr_migratory++;
-
-	update_rt_migration(rt_rq);
-}
-
-static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
-{
-	struct task_struct *p;
-
-	if (!rt_entity_is_task(rt_se))
-		return;
-
-	p = rt_task_of(rt_se);
-	rt_rq = &rq_of_rt_rq(rt_rq)->rt;
-
-	rt_rq->rt_nr_total--;
-	if (p->nr_cpus_allowed > 1)
-		rt_rq->rt_nr_migratory--;
-
-	update_rt_migration(rt_rq);
-}
-
 static inline int has_pushable_tasks(struct rq *rq)
 {
 	return !plist_head_empty(&rq->rt.pushable_tasks);
@@ -438,6 +394,11 @@ static void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
 	/* Update the highest prio pushable task */
 	if (p->prio < rq->rt.highest_prio.next)
 		rq->rt.highest_prio.next = p->prio;
+
+	if (!rq->rt.overloaded) {
+		rt_set_overload(rq);
+		rq->rt.overloaded = 1;
+	}
 }
 
 static void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
@@ -451,6 +412,11 @@ static void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
 		rq->rt.highest_prio.next = p->prio;
 	} else {
 		rq->rt.highest_prio.next = MAX_RT_PRIO-1;
+
+		if (rq->rt.overloaded) {
+			rt_clear_overload(rq);
+			rq->rt.overloaded = 0;
+		}
 	}
 }
 
@@ -464,16 +430,6 @@ static inline void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
 {
 }
 
-static inline
-void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
-{
-}
-
-static inline
-void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
-{
-}
-
 static inline void rt_queue_push_tasks(struct rq *rq)
 {
 }
@@ -515,7 +471,7 @@ static inline bool rt_task_fits_capacity(struct task_struct *p, int cpu)
 	min_cap = uclamp_eff_value(p, UCLAMP_MIN);
 	max_cap = uclamp_eff_value(p, UCLAMP_MAX);
 
-	cpu_cap = capacity_orig_of(cpu);
+	cpu_cap = arch_scale_cpu_capacity(cpu);
 
 	return cpu_cap >= min(min_cap, max_cap);
 }
@@ -953,7 +909,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 
 				/*
 				 * When we're idle and a woken (rt) task is
-				 * throttled check_preempt_curr() will set
+				 * throttled wakeup_preempt() will set
 				 * skip_update and the time between the wakeup
 				 * and this unthrottle will get accounted as
 				 * 'runtime'.
@@ -1281,7 +1237,6 @@ void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 	rt_rq->rr_nr_running += rt_se_rr_nr_running(rt_se);
 
 	inc_rt_prio(rt_rq, prio);
-	inc_rt_migration(rt_se, rt_rq);
 	inc_rt_group(rt_se, rt_rq);
 }
 
@@ -1294,7 +1249,6 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 	rt_rq->rr_nr_running -= rt_se_rr_nr_running(rt_se);
 
 	dec_rt_prio(rt_rq, rt_se_prio(rt_se));
-	dec_rt_migration(rt_se, rt_rq);
 	dec_rt_group(rt_se, rt_rq);
 }
 
@@ -1715,7 +1669,7 @@ static int balance_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
 /*
  * Preempt the current task with a newly woken task if needed:
  */
-static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flags)
+static void wakeup_preempt_rt(struct rq *rq, struct task_struct *p, int flags)
 {
 	if (p->prio < rq->curr->prio) {
 		resched_curr(rq);
@@ -2706,7 +2660,7 @@ DEFINE_SCHED_CLASS(rt) = {
 	.dequeue_task		= dequeue_task_rt,
 	.yield_task		= yield_task_rt,
 
-	.check_preempt_curr	= check_preempt_curr_rt,
+	.wakeup_preempt		= wakeup_preempt_rt,
 
 	.pick_next_task		= pick_next_task_rt,
 	.put_prev_task		= put_prev_task_rt,
@@ -2989,9 +2943,6 @@ static int sched_rt_global_constraints(void)
 #ifdef CONFIG_SYSCTL
 static int sched_rt_global_validate(void)
 {
-	if (sysctl_sched_rt_period <= 0)
-		return -EINVAL;
-
 	if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
 		((sysctl_sched_rt_runtime > sysctl_sched_rt_period) ||
 		 ((u64)sysctl_sched_rt_runtime *
@@ -3022,7 +2973,7 @@ static int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
 	old_period = sysctl_sched_rt_period;
 	old_runtime = sysctl_sched_rt_runtime;
 
-	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 
 	if (!ret && write) {
 		ret = sched_rt_global_validate();
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0484627240..2e5a95486a 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -74,15 +74,6 @@
 
 #include "../workqueue_internal.h"
 
-#ifdef CONFIG_CGROUP_SCHED
-#include <linux/cgroup.h>
-#include <linux/psi.h>
-#endif
-
-#ifdef CONFIG_SCHED_DEBUG
-# include <linux/static_key.h>
-#endif
-
 #ifdef CONFIG_PARAVIRT
 # include <asm/paravirt.h>
 # include <asm/paravirt_api_clock.h>
@@ -109,14 +100,12 @@ extern __read_mostly int scheduler_running;
 extern unsigned long calc_load_update;
 extern atomic_long_t calc_load_tasks;
 
-extern unsigned int sysctl_sched_child_runs_first;
-
 extern void calc_global_load_tick(struct rq *this_rq);
 extern long calc_load_fold_active(struct rq *this_rq, long adjust);
 
 extern void call_trace_sched_update_nr_running(struct rq *rq, int count);
 
-extern unsigned int sysctl_sched_rt_period;
+extern int sysctl_sched_rt_period;
 extern int sysctl_sched_rt_runtime;
 extern int sched_rr_timeslice;
 
@@ -594,6 +583,7 @@ struct cfs_rq {
 	} removed;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+	u64			last_update_tg_load_avg;
 	unsigned long		tg_load_avg_contrib;
 	long			propagate;
 	long			prop_runnable_sum;
@@ -644,9 +634,7 @@ struct cfs_rq {
 	int			throttled;
 	int			throttle_count;
 	struct list_head	throttled_list;
-#ifdef CONFIG_SMP
 	struct list_head	throttled_csd_list;
-#endif
 #endif /* CONFIG_CFS_BANDWIDTH */
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 };
@@ -675,8 +663,6 @@ struct rt_rq {
 	} highest_prio;
 #endif
 #ifdef CONFIG_SMP
-	unsigned int		rt_nr_migratory;
-	unsigned int		rt_nr_total;
 	int			overloaded;
 	struct plist_head	pushable_tasks;
 
@@ -721,7 +707,6 @@ struct dl_rq {
 		u64		next;
 	} earliest_dl;
 
-	unsigned int		dl_nr_migratory;
 	int			overloaded;
 
 	/*
@@ -963,10 +948,6 @@ struct rq {
 	/* runqueue lock: */
 	raw_spinlock_t		__lock;
 
-	/*
-	 * nr_running and cpu_load should be in the same cacheline because
-	 * remote CPUs use both these fields when doing load calculation.
-	 */
 	unsigned int		nr_running;
 #ifdef CONFIG_NUMA_BALANCING
 	unsigned int		nr_numa_running;
@@ -1048,7 +1029,6 @@ struct rq {
 	struct sched_domain __rcu	*sd;
 
 	unsigned long		cpu_capacity;
-	unsigned long		cpu_capacity_orig;
 
 	struct balance_callback *balance_callback;
 
@@ -1079,9 +1059,6 @@ struct rq {
 	u64			idle_stamp;
 	u64			avg_idle;
 
-	unsigned long		wake_stamp;
-	u64			wake_avg_idle;
-
 	/* This is used to determine avg_idle's max value */
 	u64			max_idle_balance_cost;
 
@@ -1658,6 +1635,11 @@ task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
 	raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
 }
 
+DEFINE_LOCK_GUARD_1(task_rq_lock, struct task_struct,
+		    _T->rq = task_rq_lock(_T->lock, &_T->rf),
+		    task_rq_unlock(_T->rq, _T->lock, &_T->rf),
+		    struct rq *rq; struct rq_flags rf)
+
 static inline void
 rq_lock_irqsave(struct rq *rq, struct rq_flags *rf)
 	__acquires(rq->lock)
@@ -1868,11 +1850,13 @@ static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
 DECLARE_PER_CPU(struct sched_domain __rcu *, sd_llc);
 DECLARE_PER_CPU(int, sd_llc_size);
 DECLARE_PER_CPU(int, sd_llc_id);
+DECLARE_PER_CPU(int, sd_share_id);
 DECLARE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
 DECLARE_PER_CPU(struct sched_domain __rcu *, sd_numa);
 DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
 DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
 extern struct static_key_false sched_asym_cpucapacity;
+extern struct static_key_false sched_cluster_active;
 
 static __always_inline bool sched_asym_cpucap_active(void)
 {
@@ -2239,7 +2223,7 @@ struct sched_class {
 	void (*yield_task)   (struct rq *rq);
 	bool (*yield_to_task)(struct rq *rq, struct task_struct *p);
 
-	void (*check_preempt_curr)(struct rq *rq, struct task_struct *p, int flags);
+	void (*wakeup_preempt)(struct rq *rq, struct task_struct *p, int flags);
 
 	struct task_struct *(*pick_next_task)(struct rq *rq);
 
@@ -2513,7 +2497,7 @@ static inline void sub_nr_running(struct rq *rq, unsigned count)
 extern void activate_task(struct rq *rq, struct task_struct *p, int flags);
 extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);
 
-extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
+extern void wakeup_preempt(struct rq *rq, struct task_struct *p, int flags);
 
 #ifdef CONFIG_PREEMPT_RT
 #define SCHED_NR_MIGRATE_BREAK 8
@@ -2977,11 +2961,6 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #endif
 
 #ifdef CONFIG_SMP
-static inline unsigned long capacity_orig_of(int cpu)
-{
-	return cpu_rq(cpu)->cpu_capacity_orig;
-}
-
 /**
  * enum cpu_util_type - CPU utilization type
  * @FREQUENCY_UTIL:	Utilization used to select frequency
@@ -3219,6 +3198,8 @@ static inline bool sched_energy_enabled(void)
 	return static_branch_unlikely(&sched_energy_present);
 }
 
+extern struct cpufreq_governor schedutil_gov;
+
 #else /* ! (CONFIG_ENERGY_MODEL && CONFIG_CPU_FREQ_GOV_SCHEDUTIL) */
 
 #define perf_domain_span(pd) NULL
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 85590599b4..6cf7304e64 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -23,7 +23,7 @@ balance_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 #endif /* CONFIG_SMP */
 
 static void
-check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
+wakeup_preempt_stop(struct rq *rq, struct task_struct *p, int flags)
 {
 	/* we're never preempted */
 }
@@ -120,7 +120,7 @@ DEFINE_SCHED_CLASS(stop) = {
 	.dequeue_task		= dequeue_task_stop,
 	.yield_task		= yield_task_stop,
 
-	.check_preempt_curr	= check_preempt_curr_stop,
+	.wakeup_preempt		= wakeup_preempt_stop,
 
 	.pick_next_task		= pick_next_task_stop,
 	.put_prev_task		= put_prev_task_stop,
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 423d089479..10d1391e74 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -212,6 +212,69 @@ static unsigned int sysctl_sched_energy_aware = 1;
 static DEFINE_MUTEX(sched_energy_mutex);
 static bool sched_energy_update;
 
+static bool sched_is_eas_possible(const struct cpumask *cpu_mask)
+{
+	bool any_asym_capacity = false;
+	struct cpufreq_policy *policy;
+	struct cpufreq_governor *gov;
+	int i;
+
+	/* EAS is enabled for asymmetric CPU capacity topologies. */
+	for_each_cpu(i, cpu_mask) {
+		if (rcu_access_pointer(per_cpu(sd_asym_cpucapacity, i))) {
+			any_asym_capacity = true;
+			break;
+		}
+	}
+	if (!any_asym_capacity) {
+		if (sched_debug()) {
+			pr_info("rd %*pbl: Checking EAS, CPUs do not have asymmetric capacities\n",
+				cpumask_pr_args(cpu_mask));
+		}
+		return false;
+	}
+
+	/* EAS definitely does *not* handle SMT */
+	if (sched_smt_active()) {
+		if (sched_debug()) {
+			pr_info("rd %*pbl: Checking EAS, SMT is not supported\n",
+				cpumask_pr_args(cpu_mask));
+		}
+		return false;
+	}
+
+	if (!arch_scale_freq_invariant()) {
+		if (sched_debug()) {
+			pr_info("rd %*pbl: Checking EAS: frequency-invariant load tracking not yet supported",
+				cpumask_pr_args(cpu_mask));
+		}
+		return false;
+	}
+
+	/* Do not attempt EAS if schedutil is not being used. */
+	for_each_cpu(i, cpu_mask) {
+		policy = cpufreq_cpu_get(i);
+		if (!policy) {
+			if (sched_debug()) {
+				pr_info("rd %*pbl: Checking EAS, cpufreq policy not set for CPU: %d",
+					cpumask_pr_args(cpu_mask), i);
+			}
+			return false;
+		}
+		gov = policy->governor;
+		cpufreq_cpu_put(policy);
+		if (gov != &schedutil_gov) {
+			if (sched_debug()) {
+				pr_info("rd %*pbl: Checking EAS, schedutil is mandatory\n",
+					cpumask_pr_args(cpu_mask));
+			}
+			return false;
+		}
+	}
+
+	return true;
+}
+
 void rebuild_sched_domains_energy(void)
 {
 	mutex_lock(&sched_energy_mutex);
@@ -230,6 +293,15 @@ static int sched_energy_aware_handler(struct ctl_table *table, int write,
 	if (write && !capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
+	if (!sched_is_eas_possible(cpu_active_mask)) {
+		if (write) {
+			return -EOPNOTSUPP;
+		} else {
+			*lenp = 0;
+			return 0;
+		}
+	}
+
 	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (!ret && write) {
 		state = static_branch_unlikely(&sched_energy_present);
@@ -348,103 +420,33 @@ static void sched_energy_set(bool has_eas)
  *    1. an Energy Model (EM) is available;
  *    2. the SD_ASYM_CPUCAPACITY flag is set in the sched_domain hierarchy.
  *    3. no SMT is detected.
- *    4. the EM complexity is low enough to keep scheduling overheads low;
- *    5. schedutil is driving the frequency of all CPUs of the rd;
- *    6. frequency invariance support is present;
- *
- * The complexity of the Energy Model is defined as:
- *
- *              C = nr_pd * (nr_cpus + nr_ps)
- *
- * with parameters defined as:
- *  - nr_pd:    the number of performance domains
- *  - nr_cpus:  the number of CPUs
- *  - nr_ps:    the sum of the number of performance states of all performance
- *              domains (for example, on a system with 2 performance domains,
- *              with 10 performance states each, nr_ps = 2 * 10 = 20).
- *
- * It is generally not a good idea to use such a model in the wake-up path on
- * very complex platforms because of the associated scheduling overheads. The
- * arbitrary constraint below prevents that. It makes EAS usable up to 16 CPUs
- * with per-CPU DVFS and less than 8 performance states each, for example.
+ *    4. schedutil is driving the frequency of all CPUs of the rd;
+ *    5. frequency invariance support is present;
  */
-#define EM_MAX_COMPLEXITY 2048
-
-extern struct cpufreq_governor schedutil_gov;
 static bool build_perf_domains(const struct cpumask *cpu_map)
 {
-	int i, nr_pd = 0, nr_ps = 0, nr_cpus = cpumask_weight(cpu_map);
+	int i;
 	struct perf_domain *pd = NULL, *tmp;
 	int cpu = cpumask_first(cpu_map);
 	struct root_domain *rd = cpu_rq(cpu)->rd;
-	struct cpufreq_policy *policy;
-	struct cpufreq_governor *gov;
 
 	if (!sysctl_sched_energy_aware)
 		goto free;
 
-	/* EAS is enabled for asymmetric CPU capacity topologies. */
-	if (!per_cpu(sd_asym_cpucapacity, cpu)) {
-		if (sched_debug()) {
-			pr_info("rd %*pbl: CPUs do not have asymmetric capacities\n",
-					cpumask_pr_args(cpu_map));
-		}
-		goto free;
-	}
-
-	/* EAS definitely does *not* handle SMT */
-	if (sched_smt_active()) {
-		pr_warn("rd %*pbl: Disabling EAS, SMT is not supported\n",
-			cpumask_pr_args(cpu_map));
-		goto free;
-	}
-
-	if (!arch_scale_freq_invariant()) {
-		if (sched_debug()) {
-			pr_warn("rd %*pbl: Disabling EAS: frequency-invariant load tracking not yet supported",
-				cpumask_pr_args(cpu_map));
-		}
+	if (!sched_is_eas_possible(cpu_map))
 		goto free;
-	}
 
 	for_each_cpu(i, cpu_map) {
 		/* Skip already covered CPUs. */
 		if (find_pd(pd, i))
 			continue;
 
-		/* Do not attempt EAS if schedutil is not being used. */
-		policy = cpufreq_cpu_get(i);
-		if (!policy)
-			goto free;
-		gov = policy->governor;
-		cpufreq_cpu_put(policy);
-		if (gov != &schedutil_gov) {
-			if (rd->pd)
-				pr_warn("rd %*pbl: Disabling EAS, schedutil is mandatory\n",
-						cpumask_pr_args(cpu_map));
-			goto free;
-		}
-
 		/* Create the new pd and add it to the local list. */
 		tmp = pd_init(i);
 		if (!tmp)
 			goto free;
 		tmp->next = pd;
 		pd = tmp;
-
-		/*
-		 * Count performance domains and performance states for the
-		 * complexity check.
-		 */
-		nr_pd++;
-		nr_ps += em_pd_nr_perf_states(pd->em_pd);
-	}
-
-	/* Bail out if the Energy Model complexity is too high. */
-	if (nr_pd * (nr_ps + nr_cpus) > EM_MAX_COMPLEXITY) {
-		WARN(1, "rd %*pbl: Failed to start EAS, EM complexity is too high\n",
-						cpumask_pr_args(cpu_map));
-		goto free;
 	}
 
 	perf_domain_debug(cpu_map, pd);
@@ -666,11 +668,14 @@ static void destroy_sched_domains(struct sched_domain *sd)
 DEFINE_PER_CPU(struct sched_domain __rcu *, sd_llc);
 DEFINE_PER_CPU(int, sd_llc_size);
 DEFINE_PER_CPU(int, sd_llc_id);
+DEFINE_PER_CPU(int, sd_share_id);
 DEFINE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
 DEFINE_PER_CPU(struct sched_domain __rcu *, sd_numa);
 DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
 DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
+
 DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);
+DEFINE_STATIC_KEY_FALSE(sched_cluster_active);
 
 static void update_top_cache_domain(int cpu)
 {
@@ -691,6 +696,17 @@ static void update_top_cache_domain(int cpu)
 	per_cpu(sd_llc_id, cpu) = id;
 	rcu_assign_pointer(per_cpu(sd_llc_shared, cpu), sds);
 
+	sd = lowest_flag_domain(cpu, SD_CLUSTER);
+	if (sd)
+		id = cpumask_first(sched_domain_span(sd));
+
+	/*
+	 * This assignment should be placed after the sd_llc_id as
+	 * we want this id equals to cluster id on cluster machines
+	 * but equals to LLC id on non-Cluster machines.
+	 */
+	per_cpu(sd_share_id, cpu) = id;
+
 	sd = lowest_flag_domain(cpu, SD_NUMA);
 	rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
 
@@ -1117,7 +1133,7 @@ fail:
  *
  *  - Simultaneous multithreading (SMT)
  *  - Multi-Core Cache (MC)
- *  - Package (DIE)
+ *  - Package (PKG)
  *
  * Where the last one more or less denotes everything up to a NUMA node.
  *
@@ -1139,13 +1155,13 @@ fail:
  *
  * CPU   0   1   2   3   4   5   6   7
  *
- * DIE  [                             ]
+ * PKG  [                             ]
  * MC   [             ] [             ]
  * SMT  [     ] [     ] [     ] [     ]
  *
  *  - or -
  *
- * DIE  0-7 0-7 0-7 0-7 0-7 0-7 0-7 0-7
+ * PKG  0-7 0-7 0-7 0-7 0-7 0-7 0-7 0-7
  * MC	0-3 0-3 0-3 0-3 4-7 4-7 4-7 4-7
  * SMT  0-1 0-1 2-3 2-3 4-5 4-5 6-7 6-7
  *
@@ -1548,6 +1564,7 @@ static struct cpumask		***sched_domains_numa_masks;
  */
 #define TOPOLOGY_SD_FLAGS		\
 	(SD_SHARE_CPUCAPACITY	|	\
+	 SD_CLUSTER		|	\
 	 SD_SHARE_PKG_RESOURCES |	\
 	 SD_NUMA		|	\
 	 SD_ASYM_PACKING)
@@ -1679,7 +1696,7 @@ static struct sched_domain_topology_level default_topology[] = {
 #ifdef CONFIG_SCHED_MC
 	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
 #endif
-	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
+	{ cpu_cpu_mask, SD_INIT_NAME(PKG) },
 	{ NULL, },
 };
 
@@ -2112,13 +2129,15 @@ static int hop_cmp(const void *a, const void *b)
 	return -1;
 }
 
-/*
- * sched_numa_find_nth_cpu() - given the NUMA topology, find the Nth next cpu
- *                             closest to @cpu from @cpumask.
- * cpumask: cpumask to find a cpu from
- * cpu: Nth cpu to find
- *
- * returns: cpu, or nr_cpu_ids when nothing found.
+/**
+ * sched_numa_find_nth_cpu() - given the NUMA topology, find the Nth closest CPU
+ *                             from @cpus to @cpu, taking into account distance
+ *                             from a given @node.
+ * @cpus: cpumask to find a cpu from
+ * @cpu: CPU to start searching
+ * @node: NUMA node to order CPUs by distance
+ *
+ * Return: cpu, or nr_cpu_ids when nothing found.
  */
 int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node)
 {
@@ -2126,6 +2145,9 @@ int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node)
 	struct cpumask ***hop_masks;
 	int hop, ret = nr_cpu_ids;
 
+	if (node == NUMA_NO_NODE)
+		return cpumask_nth_and(cpu, cpus, cpu_online_mask);
+
 	rcu_read_lock();
 
 	/* CPU-less node entries are uninitialized in sched_domains_numa_masks */
@@ -2366,6 +2388,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	struct rq *rq = NULL;
 	int i, ret = -ENOMEM;
 	bool has_asym = false;
+	bool has_cluster = false;
 
 	if (WARN_ON(cpumask_empty(cpu_map)))
 		goto error;
@@ -2483,20 +2506,29 @@ 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 (rq->cpu_capacity_orig > READ_ONCE(d.rd->max_cpu_capacity))
-			WRITE_ONCE(d.rd->max_cpu_capacity, rq->cpu_capacity_orig);
+		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))
+			has_cluster = true;
 	}
 	rcu_read_unlock();
 
 	if (has_asym)
 		static_branch_inc_cpuslocked(&sched_asym_cpucapacity);
 
+	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);
@@ -2596,6 +2628,9 @@ static void detach_destroy_domains(const struct cpumask *cpu_map)
 	if (rcu_access_pointer(per_cpu(sd_asym_cpucapacity, cpu)))
 		static_branch_dec_cpuslocked(&sched_asym_cpucapacity);
 
+	if (static_branch_unlikely(&sched_cluster_active))
+		static_branch_dec_cpuslocked(&sched_cluster_active);
+
 	rcu_read_lock();
 	for_each_cpu(i, cpu_map)
 		cpu_attach_domain(NULL, &def_root_domain, i);
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 802d98cf2d..51e38f5f47 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -58,13 +58,6 @@ void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry
 EXPORT_SYMBOL(remove_wait_queue);
 
 /*
- * Scan threshold to break wait queue walk.
- * This allows a waker to take a break from holding the
- * wait queue lock during the wait queue walk.
- */
-#define WAITQUEUE_WALK_BREAK_CNT 64
-
-/*
  * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just
  * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve
  * number) then we wake that number of exclusive tasks, and potentially all
@@ -78,21 +71,13 @@ EXPORT_SYMBOL(remove_wait_queue);
  * zero in this (rare) case, and we handle it by continuing to scan the queue.
  */
 static int __wake_up_common(struct wait_queue_head *wq_head, unsigned int mode,
-			int nr_exclusive, int wake_flags, void *key,
-			wait_queue_entry_t *bookmark)
+			int nr_exclusive, int wake_flags, void *key)
 {
 	wait_queue_entry_t *curr, *next;
-	int cnt = 0;
 
 	lockdep_assert_held(&wq_head->lock);
 
-	if (bookmark && (bookmark->flags & WQ_FLAG_BOOKMARK)) {
-		curr = list_next_entry(bookmark, entry);
-
-		list_del(&bookmark->entry);
-		bookmark->flags = 0;
-	} else
-		curr = list_first_entry(&wq_head->head, wait_queue_entry_t, entry);
+	curr = list_first_entry(&wq_head->head, wait_queue_entry_t, entry);
 
 	if (&curr->entry == &wq_head->head)
 		return nr_exclusive;
@@ -101,21 +86,11 @@ static int __wake_up_common(struct wait_queue_head *wq_head, unsigned int mode,
 		unsigned flags = curr->flags;
 		int ret;
 
-		if (flags & WQ_FLAG_BOOKMARK)
-			continue;
-
 		ret = curr->func(curr, mode, wake_flags, key);
 		if (ret < 0)
 			break;
 		if (ret && (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
 			break;
-
-		if (bookmark && (++cnt > WAITQUEUE_WALK_BREAK_CNT) &&
-				(&next->entry != &wq_head->head)) {
-			bookmark->flags = WQ_FLAG_BOOKMARK;
-			list_add_tail(&bookmark->entry, &next->entry);
-			break;
-		}
 	}
 
 	return nr_exclusive;
@@ -125,20 +100,12 @@ static int __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int m
 			int nr_exclusive, int wake_flags, void *key)
 {
 	unsigned long flags;
-	wait_queue_entry_t bookmark;
-	int remaining = nr_exclusive;
+	int remaining;
 
-	bookmark.flags = 0;
-	bookmark.private = NULL;
-	bookmark.func = NULL;
-	INIT_LIST_HEAD(&bookmark.entry);
-
-	do {
-		spin_lock_irqsave(&wq_head->lock, flags);
-		remaining = __wake_up_common(wq_head, mode, remaining,
-						wake_flags, key, &bookmark);
-		spin_unlock_irqrestore(&wq_head->lock, flags);
-	} while (bookmark.flags & WQ_FLAG_BOOKMARK);
+	spin_lock_irqsave(&wq_head->lock, flags);
+	remaining = __wake_up_common(wq_head, mode, nr_exclusive, wake_flags,
+			key);
+	spin_unlock_irqrestore(&wq_head->lock, flags);
 
 	return nr_exclusive - remaining;
 }
@@ -171,23 +138,16 @@ void __wake_up_on_current_cpu(struct wait_queue_head *wq_head, unsigned int mode
  */
 void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr)
 {
-	__wake_up_common(wq_head, mode, nr, 0, NULL, NULL);
+	__wake_up_common(wq_head, mode, nr, 0, NULL);
 }
 EXPORT_SYMBOL_GPL(__wake_up_locked);
 
 void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key)
 {
-	__wake_up_common(wq_head, mode, 1, 0, key, NULL);
+	__wake_up_common(wq_head, mode, 1, 0, key);
 }
 EXPORT_SYMBOL_GPL(__wake_up_locked_key);
 
-void __wake_up_locked_key_bookmark(struct wait_queue_head *wq_head,
-		unsigned int mode, void *key, wait_queue_entry_t *bookmark)
-{
-	__wake_up_common(wq_head, mode, 1, 0, key, bookmark);
-}
-EXPORT_SYMBOL_GPL(__wake_up_locked_key_bookmark);
-
 /**
  * __wake_up_sync_key - wake up threads blocked on a waitqueue.
  * @wq_head: the waitqueue
@@ -233,7 +193,7 @@ EXPORT_SYMBOL_GPL(__wake_up_sync_key);
 void __wake_up_locked_sync_key(struct wait_queue_head *wq_head,
 			       unsigned int mode, void *key)
 {
-        __wake_up_common(wq_head, mode, 1, WF_SYNC, key, NULL);
+        __wake_up_common(wq_head, mode, 1, WF_SYNC, key);
 }
 EXPORT_SYMBOL_GPL(__wake_up_locked_sync_key);