Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 21fb5a5..5fc9c9b 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -7,6 +7,12 @@
 # that is not a function of syscall inputs. E.g. involuntary context switches.
 KCOV_INSTRUMENT := n
 
+# There are numerous data races here, however, most of them are due to plain accesses.
+# This would make it even harder for syzbot to find reproducers, because these
+# bugs trigger without specific input. Disable by default, but should re-enable
+# eventually.
+KCSAN_SANITIZE := n
+
 ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
 # needed for x86 only.  Why this used to be enabled for all architectures is beyond
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index 1152259..12bca64 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -370,7 +370,7 @@
 	if (sched_clock_stable())
 		return sched_clock() + __sched_clock_offset;
 
-	if (!static_branch_unlikely(&sched_clock_running))
+	if (!static_branch_likely(&sched_clock_running))
 		return sched_clock();
 
 	preempt_disable_notrace();
@@ -393,7 +393,7 @@
 	if (sched_clock_stable())
 		return;
 
-	if (!static_branch_unlikely(&sched_clock_running))
+	if (!static_branch_likely(&sched_clock_running))
 		return;
 
 	lockdep_assert_irqs_disabled();
@@ -460,7 +460,7 @@
 
 u64 sched_clock_cpu(int cpu)
 {
-	if (!static_branch_unlikely(&sched_clock_running))
+	if (!static_branch_likely(&sched_clock_running))
 		return 0;
 
 	return sched_clock();
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index a1ad5b7..a778554 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -29,12 +29,12 @@
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&x->wait.lock, flags);
+	raw_spin_lock_irqsave(&x->wait.lock, flags);
 
 	if (x->done != UINT_MAX)
 		x->done++;
-	__wake_up_locked(&x->wait, TASK_NORMAL, 1);
-	spin_unlock_irqrestore(&x->wait.lock, flags);
+	swake_up_locked(&x->wait);
+	raw_spin_unlock_irqrestore(&x->wait.lock, flags);
 }
 EXPORT_SYMBOL(complete);
 
@@ -58,10 +58,12 @@
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&x->wait.lock, flags);
+	lockdep_assert_RT_in_threaded_ctx();
+
+	raw_spin_lock_irqsave(&x->wait.lock, flags);
 	x->done = UINT_MAX;
-	__wake_up_locked(&x->wait, TASK_NORMAL, 0);
-	spin_unlock_irqrestore(&x->wait.lock, flags);
+	swake_up_all_locked(&x->wait);
+	raw_spin_unlock_irqrestore(&x->wait.lock, flags);
 }
 EXPORT_SYMBOL(complete_all);
 
@@ -70,20 +72,20 @@
 		   long (*action)(long), long timeout, int state)
 {
 	if (!x->done) {
-		DECLARE_WAITQUEUE(wait, current);
+		DECLARE_SWAITQUEUE(wait);
 
-		__add_wait_queue_entry_tail_exclusive(&x->wait, &wait);
 		do {
 			if (signal_pending_state(state, current)) {
 				timeout = -ERESTARTSYS;
 				break;
 			}
+			__prepare_to_swait(&x->wait, &wait);
 			__set_current_state(state);
-			spin_unlock_irq(&x->wait.lock);
+			raw_spin_unlock_irq(&x->wait.lock);
 			timeout = action(timeout);
-			spin_lock_irq(&x->wait.lock);
+			raw_spin_lock_irq(&x->wait.lock);
 		} while (!x->done && timeout);
-		__remove_wait_queue(&x->wait, &wait);
+		__finish_swait(&x->wait, &wait);
 		if (!x->done)
 			return timeout;
 	}
@@ -100,9 +102,9 @@
 
 	complete_acquire(x);
 
-	spin_lock_irq(&x->wait.lock);
+	raw_spin_lock_irq(&x->wait.lock);
 	timeout = do_wait_for_common(x, action, timeout, state);
-	spin_unlock_irq(&x->wait.lock);
+	raw_spin_unlock_irq(&x->wait.lock);
 
 	complete_release(x);
 
@@ -291,12 +293,12 @@
 	if (!READ_ONCE(x->done))
 		return false;
 
-	spin_lock_irqsave(&x->wait.lock, flags);
+	raw_spin_lock_irqsave(&x->wait.lock, flags);
 	if (!x->done)
 		ret = false;
 	else if (x->done != UINT_MAX)
 		x->done--;
-	spin_unlock_irqrestore(&x->wait.lock, flags);
+	raw_spin_unlock_irqrestore(&x->wait.lock, flags);
 	return ret;
 }
 EXPORT_SYMBOL(try_wait_for_completion);
@@ -322,8 +324,8 @@
 	 * otherwise we can end up freeing the completion before complete()
 	 * is done referencing it.
 	 */
-	spin_lock_irqsave(&x->wait.lock, flags);
-	spin_unlock_irqrestore(&x->wait.lock, flags);
+	raw_spin_lock_irqsave(&x->wait.lock, flags);
+	raw_spin_unlock_irqrestore(&x->wait.lock, flags);
 	return true;
 }
 EXPORT_SYMBOL(completion_done);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5dc43d3..0a5f9fa 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6,22 +6,26 @@
  *
  *  Copyright (C) 1991-2002  Linus Torvalds
  */
+#define CREATE_TRACE_POINTS
+#include <trace/events/sched.h>
+#undef CREATE_TRACE_POINTS
+
 #include "sched.h"
 
 #include <linux/nospec.h>
 
 #include <linux/kcov.h>
+#include <linux/scs.h>
 
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
 
 #include "../workqueue_internal.h"
+#include "../../fs/io-wq.h"
 #include "../smpboot.h"
 
 #include "pelt.h"
-
-#define CREATE_TRACE_POINTS
-#include <trace/events/sched.h>
+#include "smp.h"
 
 /*
  * Export tracepoints that act as a bare tracehook (ie: have no trace event
@@ -32,7 +36,11 @@
 EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_dl_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_cpu_capacity_tp);
 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);
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
@@ -72,6 +80,100 @@
  */
 int sysctl_sched_rt_runtime = 950000;
 
+
+/*
+ * Serialization rules:
+ *
+ * Lock order:
+ *
+ *   p->pi_lock
+ *     rq->lock
+ *       hrtimer_cpu_base->lock (hrtimer_start() for bandwidth controls)
+ *
+ *  rq1->lock
+ *    rq2->lock  where: rq1 < rq2
+ *
+ * Regular state:
+ *
+ * Normal scheduling state is serialized by rq->lock. __schedule() takes the
+ * local CPU's rq->lock, it optionally removes the task from the runqueue and
+ * always looks at the local rq data structures to find the most elegible task
+ * to run next.
+ *
+ * Task enqueue is also under rq->lock, possibly taken from another CPU.
+ * Wakeups from another LLC domain might use an IPI to transfer the enqueue to
+ * the local CPU to avoid bouncing the runqueue state around [ see
+ * ttwu_queue_wakelist() ]
+ *
+ * Task wakeup, specifically wakeups that involve migration, are horribly
+ * complicated to avoid having to take two rq->locks.
+ *
+ * Special state:
+ *
+ * System-calls and anything external will use task_rq_lock() which acquires
+ * both p->pi_lock and rq->lock. As a consequence the state they change is
+ * stable while holding either lock:
+ *
+ *  - sched_setaffinity()/
+ *    set_cpus_allowed_ptr():	p->cpus_ptr, p->nr_cpus_allowed
+ *  - set_user_nice():		p->se.load, p->*prio
+ *  - __sched_setscheduler():	p->sched_class, p->policy, p->*prio,
+ *				p->se.load, p->rt_priority,
+ *				p->dl.dl_{runtime, deadline, period, flags, bw, density}
+ *  - sched_setnuma():		p->numa_preferred_nid
+ *  - sched_move_task()/
+ *    cpu_cgroup_fork():	p->sched_task_group
+ *  - uclamp_update_active()	p->uclamp*
+ *
+ * p->state <- TASK_*:
+ *
+ *   is changed locklessly using set_current_state(), __set_current_state() or
+ *   set_special_state(), see their respective comments, or by
+ *   try_to_wake_up(). This latter uses p->pi_lock to serialize against
+ *   concurrent self.
+ *
+ * p->on_rq <- { 0, 1 = TASK_ON_RQ_QUEUED, 2 = TASK_ON_RQ_MIGRATING }:
+ *
+ *   is set by activate_task() and cleared by deactivate_task(), under
+ *   rq->lock. Non-zero indicates the task is runnable, the special
+ *   ON_RQ_MIGRATING state is used for migration without holding both
+ *   rq->locks. It indicates task_cpu() is not stable, see task_rq_lock().
+ *
+ * p->on_cpu <- { 0, 1 }:
+ *
+ *   is set by prepare_task() and cleared by finish_task() such that it will be
+ *   set before p is scheduled-in and cleared after p is scheduled-out, both
+ *   under rq->lock. Non-zero indicates the task is running on its CPU.
+ *
+ *   [ The astute reader will observe that it is possible for two tasks on one
+ *     CPU to have ->on_cpu = 1 at the same time. ]
+ *
+ * task_cpu(p): is changed by set_task_cpu(), the rules are:
+ *
+ *  - Don't call set_task_cpu() on a blocked task:
+ *
+ *    We don't care what CPU we're not running on, this simplifies hotplug,
+ *    the CPU assignment of blocked tasks isn't required to be valid.
+ *
+ *  - for try_to_wake_up(), called under p->pi_lock:
+ *
+ *    This allows try_to_wake_up() to only take one rq->lock, see its comment.
+ *
+ *  - for migration called under rq->lock:
+ *    [ see task_on_rq_migrating() in task_rq_lock() ]
+ *
+ *    o move_queued_task()
+ *    o detach_task()
+ *
+ *  - for migration called under double_rq_lock():
+ *
+ *    o __migrate_swap_task()
+ *    o push_rt_task() / pull_rt_task()
+ *    o push_dl_task() / pull_dl_task()
+ *    o dl_task_offline_migration()
+ *
+ */
+
 /*
  * __task_rq_lock - lock the rq @p resides on.
  */
@@ -218,6 +320,13 @@
 	update_rq_clock_task(rq, delta);
 }
 
+static inline void
+rq_csd_init(struct rq *rq, struct __call_single_data *csd, smp_call_func_t func)
+{
+	csd->flags = 0;
+	csd->func = func;
+	csd->info = rq;
+}
 
 #ifdef CONFIG_SCHED_HRTICK
 /*
@@ -269,7 +378,6 @@
 
 	rq_lock(rq, &rf);
 	__hrtick_restart(rq);
-	rq->hrtick_csd_pending = 0;
 	rq_unlock(rq, &rf);
 }
 
@@ -290,12 +398,10 @@
 	delta = max_t(s64, delay, 10000LL);
 	rq->hrtick_time = ktime_add_ns(timer->base->get_time(), delta);
 
-	if (rq == this_rq()) {
+	if (rq == this_rq())
 		__hrtick_restart(rq);
-	} else if (!rq->hrtick_csd_pending) {
+	else
 		smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd);
-		rq->hrtick_csd_pending = 1;
-	}
 }
 
 #else
@@ -314,18 +420,14 @@
 	hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay),
 		      HRTIMER_MODE_REL_PINNED_HARD);
 }
+
 #endif /* CONFIG_SMP */
 
 static void hrtick_rq_init(struct rq *rq)
 {
 #ifdef CONFIG_SMP
-	rq->hrtick_csd_pending = 0;
-
-	rq->hrtick_csd.flags = 0;
-	rq->hrtick_csd.func = __hrtick_start;
-	rq->hrtick_csd.info = rq;
+	rq_csd_init(rq, &rq->hrtick_csd, __hrtick_start);
 #endif
-
 	hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 	rq->hrtick_timer.function = hrtick;
 }
@@ -549,27 +651,32 @@
  */
 int get_nohz_timer_target(void)
 {
-	int i, cpu = smp_processor_id();
+	int i, cpu = smp_processor_id(), default_cpu = -1;
 	struct sched_domain *sd;
 
-	if (!idle_cpu(cpu) && housekeeping_cpu(cpu, HK_FLAG_TIMER))
-		return cpu;
+	if (housekeeping_cpu(cpu, HK_FLAG_TIMER)) {
+		if (!idle_cpu(cpu))
+			return cpu;
+		default_cpu = cpu;
+	}
 
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
-		for_each_cpu(i, sched_domain_span(sd)) {
+		for_each_cpu_and(i, sched_domain_span(sd),
+			housekeeping_cpumask(HK_FLAG_TIMER)) {
 			if (cpu == i)
 				continue;
 
-			if (!idle_cpu(i) && housekeeping_cpu(i, HK_FLAG_TIMER)) {
+			if (!idle_cpu(i)) {
 				cpu = i;
 				goto unlock;
 			}
 		}
 	}
 
-	if (!housekeeping_cpu(cpu, HK_FLAG_TIMER))
-		cpu = housekeeping_any_cpu(HK_FLAG_TIMER);
+	if (default_cpu == -1)
+		default_cpu = housekeeping_any_cpu(HK_FLAG_TIMER);
+	cpu = default_cpu;
 unlock:
 	rcu_read_unlock();
 	return cpu;
@@ -629,29 +736,23 @@
 		wake_up_idle_cpu(cpu);
 }
 
-static inline bool got_nohz_idle_kick(void)
+static void nohz_csd_func(void *info)
 {
-	int cpu = smp_processor_id();
-
-	if (!(atomic_read(nohz_flags(cpu)) & NOHZ_KICK_MASK))
-		return false;
-
-	if (idle_cpu(cpu) && !need_resched())
-		return true;
+	struct rq *rq = info;
+	int cpu = cpu_of(rq);
+	unsigned int flags;
 
 	/*
-	 * We can't run Idle Load Balance on this CPU for this time so we
-	 * cancel it and clear NOHZ_BALANCE_KICK
+	 * Release the rq::nohz_csd.
 	 */
-	atomic_andnot(NOHZ_KICK_MASK, nohz_flags(cpu));
-	return false;
-}
+	flags = atomic_fetch_andnot(NOHZ_KICK_MASK, nohz_flags(cpu));
+	WARN_ON(!(flags & NOHZ_KICK_MASK));
 
-#else /* CONFIG_NO_HZ_COMMON */
-
-static inline bool got_nohz_idle_kick(void)
-{
-	return false;
+	rq->idle_balance = idle_cpu(cpu);
+	if (rq->idle_balance && !need_resched()) {
+		rq->nohz_idle_balance = flags;
+		raise_softirq_irqoff(SCHED_SOFTIRQ);
+	}
 }
 
 #endif /* CONFIG_NO_HZ_COMMON */
@@ -753,7 +854,6 @@
 	if (task_has_idle_policy(p)) {
 		load->weight = scale_load(WEIGHT_IDLEPRIO);
 		load->inv_weight = WMULT_IDLEPRIO;
-		p->se.runnable_weight = load->weight;
 		return;
 	}
 
@@ -766,7 +866,6 @@
 	} else {
 		load->weight = scale_load(sched_prio_to_weight[prio]);
 		load->inv_weight = sched_prio_to_wmult[prio];
-		p->se.runnable_weight = load->weight;
 	}
 }
 
@@ -789,6 +888,23 @@
 /* Max allowed maximum utilization */
 unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;
 
+/*
+ * By default RT tasks run at the maximum performance point/capacity of the
+ * system. Uclamp enforces this by always setting UCLAMP_MIN of RT tasks to
+ * SCHED_CAPACITY_SCALE.
+ *
+ * This knob allows admins to change the default behavior when uclamp is being
+ * used. In battery powered devices, particularly, running at the maximum
+ * capacity and frequency will increase energy consumption and shorten the
+ * battery life.
+ *
+ * This knob only affects RT tasks that their uclamp_se->user_defined == false.
+ *
+ * This knob will not override the system default sched_util_clamp_min defined
+ * above.
+ */
+unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE;
+
 /* All clamps are required to be less or equal than these values */
 static struct uclamp_se uclamp_default[UCLAMP_CNT];
 
@@ -823,11 +939,6 @@
 	return min_t(unsigned int, clamp_value / UCLAMP_BUCKET_DELTA, UCLAMP_BUCKETS - 1);
 }
 
-static inline unsigned int uclamp_bucket_base_value(unsigned int clamp_value)
-{
-	return UCLAMP_BUCKET_DELTA * uclamp_bucket_id(clamp_value);
-}
-
 static inline unsigned int uclamp_none(enum uclamp_id clamp_id)
 {
 	if (clamp_id == UCLAMP_MIN)
@@ -891,6 +1002,64 @@
 	return uclamp_idle_value(rq, clamp_id, clamp_value);
 }
 
+static void __uclamp_update_util_min_rt_default(struct task_struct *p)
+{
+	unsigned int default_util_min;
+	struct uclamp_se *uc_se;
+
+	lockdep_assert_held(&p->pi_lock);
+
+	uc_se = &p->uclamp_req[UCLAMP_MIN];
+
+	/* Only sync if user didn't override the default */
+	if (uc_se->user_defined)
+		return;
+
+	default_util_min = sysctl_sched_uclamp_util_min_rt_default;
+	uclamp_se_set(uc_se, default_util_min, false);
+}
+
+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);
+	__uclamp_update_util_min_rt_default(p);
+	task_rq_unlock(rq, p, &rf);
+}
+
+static void uclamp_sync_util_min_rt_default(void)
+{
+	struct task_struct *g, *p;
+
+	/*
+	 * copy_process()			sysctl_uclamp
+	 *					  uclamp_min_rt = X;
+	 *   write_lock(&tasklist_lock)		  read_lock(&tasklist_lock)
+	 *   // link thread			  smp_mb__after_spinlock()
+	 *   write_unlock(&tasklist_lock)	  read_unlock(&tasklist_lock);
+	 *   sched_post_fork()			  for_each_process_thread()
+	 *     __uclamp_sync_rt()		    __uclamp_sync_rt()
+	 *
+	 * Ensures that either sched_post_fork() will observe the new
+	 * uclamp_min_rt or for_each_process_thread() will observe the new
+	 * task.
+	 */
+	read_lock(&tasklist_lock);
+	smp_mb__after_spinlock();
+	read_unlock(&tasklist_lock);
+
+	rcu_read_lock();
+	for_each_process_thread(g, p)
+		uclamp_update_util_min_rt_default(p);
+	rcu_read_unlock();
+}
+
 static inline struct uclamp_se
 uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id)
 {
@@ -939,17 +1108,17 @@
 	return uc_req;
 }
 
-unsigned int uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id)
+unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id)
 {
 	struct uclamp_se uc_eff;
 
 	/* Task currently refcounted: use back-annotated (effective) value */
 	if (p->uclamp[clamp_id].active)
-		return p->uclamp[clamp_id].value;
+		return (unsigned long)p->uclamp[clamp_id].value;
 
 	uc_eff = uclamp_eff_get(p, clamp_id);
 
-	return uc_eff.value;
+	return (unsigned long)uc_eff.value;
 }
 
 /*
@@ -1188,16 +1357,16 @@
 #endif
 
 int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
-				void __user *buffer, size_t *lenp,
-				loff_t *ppos)
+				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	bool update_root_tg = false;
-	int old_min, old_max;
+	int old_min, old_max, old_min_rt;
 	int result;
 
 	mutex_lock(&uclamp_mutex);
 	old_min = sysctl_sched_uclamp_util_min;
 	old_max = sysctl_sched_uclamp_util_max;
+	old_min_rt = sysctl_sched_uclamp_util_min_rt_default;
 
 	result = proc_dointvec(table, write, buffer, lenp, ppos);
 	if (result)
@@ -1206,7 +1375,9 @@
 		goto done;
 
 	if (sysctl_sched_uclamp_util_min > sysctl_sched_uclamp_util_max ||
-	    sysctl_sched_uclamp_util_max > SCHED_CAPACITY_SCALE) {
+	    sysctl_sched_uclamp_util_max > SCHED_CAPACITY_SCALE	||
+	    sysctl_sched_uclamp_util_min_rt_default > SCHED_CAPACITY_SCALE) {
+
 		result = -EINVAL;
 		goto undo;
 	}
@@ -1227,6 +1398,11 @@
 		uclamp_update_root_tg();
 	}
 
+	if (old_min_rt != sysctl_sched_uclamp_util_min_rt_default) {
+		static_branch_enable(&sched_uclamp_used);
+		uclamp_sync_util_min_rt_default();
+	}
+
 	/*
 	 * We update all RUNNABLE tasks only when task groups are in use.
 	 * Otherwise, keep it simple and do just a lazy update at each next
@@ -1238,6 +1414,7 @@
 undo:
 	sysctl_sched_uclamp_util_min = old_min;
 	sysctl_sched_uclamp_util_max = old_max;
+	sysctl_sched_uclamp_util_min_rt_default = old_min_rt;
 done:
 	mutex_unlock(&uclamp_mutex);
 
@@ -1283,17 +1460,20 @@
 	 */
 	for_each_clamp_id(clamp_id) {
 		struct uclamp_se *uc_se = &p->uclamp_req[clamp_id];
-		unsigned int clamp_value = uclamp_none(clamp_id);
 
 		/* Keep using defined clamps across class changes */
 		if (uc_se->user_defined)
 			continue;
 
-		/* By default, RT tasks always get 100% boost */
+		/*
+		 * RT by default have a 100% boost value that could be modified
+		 * at runtime.
+		 */
 		if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN))
-			clamp_value = uclamp_none(UCLAMP_MAX);
+			__uclamp_update_util_min_rt_default(p);
+		else
+			uclamp_se_set(uc_se, uclamp_none(clamp_id), false);
 
-		uclamp_se_set(uc_se, clamp_value, false);
 	}
 
 	if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)))
@@ -1314,6 +1494,10 @@
 {
 	enum uclamp_id clamp_id;
 
+	/*
+	 * We don't need to hold task_rq_lock() when updating p->uclamp_* here
+	 * as the task is still at its early fork stages.
+	 */
 	for_each_clamp_id(clamp_id)
 		p->uclamp[clamp_id].active = false;
 
@@ -1326,6 +1510,11 @@
 	}
 }
 
+static void uclamp_post_fork(struct task_struct *p)
+{
+	uclamp_update_util_min_rt_default(p);
+}
+
 static void __init init_uclamp_rq(struct rq *rq)
 {
 	enum uclamp_id clamp_id;
@@ -1337,7 +1526,7 @@
 		};
 	}
 
-	rq->uclamp_flags = 0;
+	rq->uclamp_flags = UCLAMP_FLAG_IDLE;
 }
 
 static void __init init_uclamp(void)
@@ -1346,8 +1535,6 @@
 	enum uclamp_id clamp_id;
 	int cpu;
 
-	mutex_init(&uclamp_mutex);
-
 	for_each_possible_cpu(cpu)
 		init_uclamp_rq(cpu_rq(cpu));
 
@@ -1378,6 +1565,7 @@
 static void __setscheduler_uclamp(struct task_struct *p,
 				  const struct sched_attr *attr) { }
 static inline void uclamp_fork(struct task_struct *p) { }
+static inline void uclamp_post_fork(struct task_struct *p) { }
 static inline void init_uclamp(void) { }
 #endif /* CONFIG_UCLAMP_TASK */
 
@@ -1411,9 +1599,6 @@
 
 void activate_task(struct rq *rq, struct task_struct *p, int flags)
 {
-	if (task_contributes_to_load(p))
-		rq->nr_uninterruptible--;
-
 	enqueue_task(rq, p, flags);
 
 	p->on_rq = TASK_ON_RQ_QUEUED;
@@ -1423,18 +1608,21 @@
 {
 	p->on_rq = (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING;
 
-	if (task_contributes_to_load(p))
-		rq->nr_uninterruptible++;
-
 	dequeue_task(rq, p, flags);
 }
 
-/*
- * __normal_prio - return the priority that is based on the static prio
- */
-static inline int __normal_prio(struct task_struct *p)
+static inline int __normal_prio(int policy, int rt_prio, int nice)
 {
-	return p->static_prio;
+	int prio;
+
+	if (dl_policy(policy))
+		prio = MAX_DL_PRIO - 1;
+	else if (rt_policy(policy))
+		prio = MAX_RT_PRIO - 1 - rt_prio;
+	else
+		prio = NICE_TO_PRIO(nice);
+
+	return prio;
 }
 
 /*
@@ -1446,15 +1634,7 @@
  */
 static inline int normal_prio(struct task_struct *p)
 {
-	int prio;
-
-	if (task_has_dl_policy(p))
-		prio = MAX_DL_PRIO-1;
-	else if (task_has_rt_policy(p))
-		prio = MAX_RT_PRIO-1 - p->rt_priority;
-	else
-		prio = __normal_prio(p);
-	return prio;
+	return __normal_prio(p->policy, p->rt_priority, PRIO_TO_NICE(p->static_prio));
 }
 
 /*
@@ -1510,20 +1690,10 @@
 
 void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 {
-	const struct sched_class *class;
-
-	if (p->sched_class == rq->curr->sched_class) {
+	if (p->sched_class == rq->curr->sched_class)
 		rq->curr->sched_class->check_preempt_curr(rq, p, flags);
-	} else {
-		for_each_class(class) {
-			if (class == rq->curr->sched_class)
-				break;
-			if (class == p->sched_class) {
-				resched_curr(rq);
-				break;
-			}
-		}
-	}
+	else if (p->sched_class > rq->curr->sched_class)
+		resched_curr(rq);
 
 	/*
 	 * A queue event has occurred, and we're going to schedule.  In
@@ -1535,17 +1705,6 @@
 
 #ifdef CONFIG_SMP
 
-static inline bool is_per_cpu_kthread(struct task_struct *p)
-{
-	if (!(p->flags & PF_KTHREAD))
-		return false;
-
-	if (p->nr_cpus_allowed != 1)
-		return false;
-
-	return true;
-}
-
 /*
  * Per-CPU kthreads are allowed to run on !active && online CPUs, see
  * __set_cpus_allowed_ptr() and select_fallback_rq().
@@ -1585,8 +1744,7 @@
 {
 	lockdep_assert_held(&rq->lock);
 
-	WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING);
-	dequeue_task(rq, p, DEQUEUE_NOCLOCK);
+	deactivate_task(rq, p, DEQUEUE_NOCLOCK);
 	set_task_cpu(p, new_cpu);
 	rq_unlock(rq, rf);
 
@@ -1594,8 +1752,7 @@
 
 	rq_lock(rq, rf);
 	BUG_ON(task_cpu(p) != new_cpu);
-	enqueue_task(rq, p, 0);
-	p->on_rq = TASK_ON_RQ_QUEUED;
+	activate_task(rq, p, 0);
 	check_preempt_curr(rq, p, 0);
 
 	return rq;
@@ -1650,7 +1807,7 @@
 	 * __migrate_task() such that we will not miss enforcing cpus_ptr
 	 * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test.
 	 */
-	sched_ttwu_pending();
+	flush_smp_call_function_from_idle();
 
 	raw_spin_lock(&p->pi_lock);
 	rq_lock(rq, &rf);
@@ -1751,7 +1908,12 @@
 	if (cpumask_equal(&p->cpus_mask, new_mask))
 		goto out;
 
-	dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask);
+	/*
+	 * Picking a ~random cpu helps in cases where we are changing affinity
+	 * for groups of tasks (ie. cpuset), so that load balancing is not
+	 * immediately required to distribute the tasks within their new mask.
+	 */
+	dest_cpu = cpumask_any_and_distribute(cpu_valid_mask, new_mask);
 	if (dest_cpu >= nr_cpu_ids) {
 		ret = -EINVAL;
 		goto out;
@@ -2163,7 +2325,7 @@
 				state = possible;
 				break;
 			}
-			/* Fall-through */
+			fallthrough;
 		case possible:
 			do_set_cpus_allowed(p, cpu_possible_mask);
 			state = fail;
@@ -2220,12 +2382,6 @@
 	return cpu;
 }
 
-static void update_avg(u64 *avg, u64 sample)
-{
-	s64 diff = sample - *avg;
-	*avg += diff >> 3;
-}
-
 void sched_set_stop_task(int cpu, struct task_struct *stop)
 {
 	struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
@@ -2348,25 +2504,49 @@
 
 	lockdep_assert_held(&rq->lock);
 
-#ifdef CONFIG_SMP
 	if (p->sched_contributes_to_load)
 		rq->nr_uninterruptible--;
 
+#ifdef CONFIG_SMP
 	if (wake_flags & WF_MIGRATED)
 		en_flags |= ENQUEUE_MIGRATED;
+	else
 #endif
+	if (p->in_iowait) {
+		delayacct_blkio_end(p);
+		atomic_dec(&task_rq(p)->nr_iowait);
+	}
 
 	activate_task(rq, p, en_flags);
 	ttwu_do_wakeup(rq, p, wake_flags, rf);
 }
 
 /*
- * Called in case the task @p isn't fully descheduled from its runqueue,
- * in this case we must do a remote wakeup. Its a 'light' wakeup though,
- * since all we need to do is flip p->state to TASK_RUNNING, since
- * the task is still ->on_rq.
+ * Consider @p being inside a wait loop:
+ *
+ *   for (;;) {
+ *      set_current_state(TASK_UNINTERRUPTIBLE);
+ *
+ *      if (CONDITION)
+ *         break;
+ *
+ *      schedule();
+ *   }
+ *   __set_current_state(TASK_RUNNING);
+ *
+ * between set_current_state() and schedule(). In this case @p is still
+ * runnable, so all that needs doing is change p->state back to TASK_RUNNING in
+ * an atomic manner.
+ *
+ * By taking task_rq(p)->lock we serialize against schedule(), if @p->on_rq
+ * then schedule() must still happen and p->state can be changed to
+ * TASK_RUNNING. Otherwise we lost the race, schedule() has happened, and we
+ * need to do a full wakeup with enqueue.
+ *
+ * Returns: %true when the wakeup is done,
+ *          %false otherwise.
  */
-static int ttwu_remote(struct task_struct *p, int wake_flags)
+static int ttwu_runnable(struct task_struct *p, int wake_flags)
 {
 	struct rq_flags rf;
 	struct rq *rq;
@@ -2385,75 +2565,63 @@
 }
 
 #ifdef CONFIG_SMP
-void sched_ttwu_pending(void)
+void sched_ttwu_pending(void *arg)
 {
+	struct llist_node *llist = arg;
 	struct rq *rq = this_rq();
-	struct llist_node *llist = llist_del_all(&rq->wake_list);
 	struct task_struct *p, *t;
 	struct rq_flags rf;
 
 	if (!llist)
 		return;
 
+	/*
+	 * rq::ttwu_pending racy indication of out-standing wakeups.
+	 * Races such that false-negatives are possible, since they
+	 * are shorter lived that false-positives would be.
+	 */
+	WRITE_ONCE(rq->ttwu_pending, 0);
+
 	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 
-	llist_for_each_entry_safe(p, t, llist, wake_entry)
+	llist_for_each_entry_safe(p, t, llist, wake_entry.llist) {
+		if (WARN_ON_ONCE(p->on_cpu))
+			smp_cond_load_acquire(&p->on_cpu, !VAL);
+
+		if (WARN_ON_ONCE(task_cpu(p) != cpu_of(rq)))
+			set_task_cpu(p, cpu_of(rq));
+
 		ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0, &rf);
+	}
 
 	rq_unlock_irqrestore(rq, &rf);
 }
 
-void scheduler_ipi(void)
+void send_call_function_single_ipi(int cpu)
 {
-	/*
-	 * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting
-	 * TIF_NEED_RESCHED remotely (for the first time) will also send
-	 * this IPI.
-	 */
-	preempt_fold_need_resched();
+	struct rq *rq = cpu_rq(cpu);
 
-	if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick())
-		return;
-
-	/*
-	 * Not all reschedule IPI handlers call irq_enter/irq_exit, since
-	 * traditionally all their work was done from the interrupt return
-	 * path. Now that we actually do some work, we need to make sure
-	 * we do call them.
-	 *
-	 * Some archs already do call them, luckily irq_enter/exit nest
-	 * properly.
-	 *
-	 * Arguably we should visit all archs and update all handlers,
-	 * however a fair share of IPIs are still resched only so this would
-	 * somewhat pessimize the simple resched case.
-	 */
-	irq_enter();
-	sched_ttwu_pending();
-
-	/*
-	 * Check if someone kicked us for doing the nohz idle load balance.
-	 */
-	if (unlikely(got_nohz_idle_kick())) {
-		this_rq()->idle_balance = 1;
-		raise_softirq_irqoff(SCHED_SOFTIRQ);
-	}
-	irq_exit();
+	if (!set_nr_if_polling(rq->idle))
+		arch_send_call_function_single_ipi(cpu);
+	else
+		trace_sched_wake_idle_without_ipi(cpu);
 }
 
-static void ttwu_queue_remote(struct task_struct *p, int cpu, int wake_flags)
+/*
+ * Queue a task on the target CPUs wake_list and wake the CPU via IPI if
+ * necessary. The wakee CPU on receipt of the IPI will queue the task
+ * via sched_ttwu_wakeup() for activation so the wakee incurs the cost
+ * of the wakeup instead of the waker.
+ */
+static void __ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
 {
 	struct rq *rq = cpu_rq(cpu);
 
 	p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);
 
-	if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list)) {
-		if (!set_nr_if_polling(rq->idle))
-			smp_send_reschedule(cpu);
-		else
-			trace_sched_wake_idle_without_ipi(cpu);
-	}
+	WRITE_ONCE(rq->ttwu_pending, 1);
+	__smp_call_single_queue(cpu, &p->wake_entry.llist);
 }
 
 void wake_up_if_idle(int cpu)
@@ -2482,8 +2650,54 @@
 
 bool cpus_share_cache(int this_cpu, int that_cpu)
 {
+	if (this_cpu == that_cpu)
+		return true;
+
 	return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
 }
+
+static inline bool ttwu_queue_cond(int cpu, int wake_flags)
+{
+	/*
+	 * If the CPU does not share cache, then queue the task on the
+	 * remote rqs wakelist to avoid accessing remote data.
+	 */
+	if (!cpus_share_cache(smp_processor_id(), cpu))
+		return true;
+
+	/*
+	 * If the task is descheduling and the only running task on the
+	 * CPU then use the wakelist to offload the task activation to
+	 * the soon-to-be-idle CPU as the current CPU is likely busy.
+	 * nr_running is checked to avoid unnecessary task stacking.
+	 */
+	if ((wake_flags & WF_ON_CPU) && cpu_rq(cpu)->nr_running <= 1)
+		return true;
+
+	return false;
+}
+
+static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
+{
+	if (sched_feat(TTWU_QUEUE) && ttwu_queue_cond(cpu, wake_flags)) {
+		if (WARN_ON_ONCE(cpu == smp_processor_id()))
+			return false;
+
+		sched_clock_cpu(cpu); /* Sync clocks across CPUs */
+		__ttwu_queue_wakelist(p, cpu, wake_flags);
+		return true;
+	}
+
+	return false;
+}
+
+#else /* !CONFIG_SMP */
+
+static inline bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
+{
+	return false;
+}
+
 #endif /* CONFIG_SMP */
 
 static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
@@ -2491,13 +2705,8 @@
 	struct rq *rq = cpu_rq(cpu);
 	struct rq_flags rf;
 
-#if defined(CONFIG_SMP)
-	if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) {
-		sched_clock_cpu(cpu); /* Sync clocks across CPUs */
-		ttwu_queue_remote(p, cpu, wake_flags);
+	if (ttwu_queue_wakelist(p, cpu, wake_flags))
 		return;
-	}
-#endif
 
 	rq_lock(rq, &rf);
 	update_rq_clock(rq);
@@ -2553,8 +2762,8 @@
  * migration. However the means are completely different as there is no lock
  * chain to provide order. Instead we do:
  *
- *   1) smp_store_release(X->on_cpu, 0)
- *   2) smp_cond_load_acquire(!X->on_cpu)
+ *   1) smp_store_release(X->on_cpu, 0)   -- finish_task()
+ *   2) smp_cond_load_acquire(!X->on_cpu) -- try_to_wake_up()
  *
  * Example:
  *
@@ -2594,15 +2803,33 @@
  * @state: the mask of task states that can be woken
  * @wake_flags: wake modifier flags (WF_*)
  *
- * If (@state & @p->state) @p->state = TASK_RUNNING.
+ * Conceptually does:
+ *
+ *   If (@state & @p->state) @p->state = TASK_RUNNING.
  *
  * If the task was not queued/runnable, also place it back on a runqueue.
  *
- * Atomic against schedule() which would dequeue a task, also see
- * set_current_state().
+ * This function is atomic against schedule() which would dequeue the task.
  *
- * This function executes a full memory barrier before accessing the task
- * state; see set_current_state().
+ * It issues a full memory barrier before accessing @p->state, see the comment
+ * with set_current_state().
+ *
+ * Uses p->pi_lock to serialize against concurrent wake-ups.
+ *
+ * Relies on p->pi_lock stabilizing:
+ *  - p->sched_class
+ *  - p->cpus_ptr
+ *  - p->sched_task_group
+ * in order to do migration, see its use of select_task_rq()/set_task_cpu().
+ *
+ * Tries really hard to only take one task_rq(p)->lock for performance.
+ * Takes rq->lock in:
+ *  - ttwu_runnable()    -- old rq, unavoidable, see comment there;
+ *  - ttwu_queue()       -- new rq, for enqueue of the task;
+ *  - psi_ttwu_dequeue() -- much sadness :-( accounting will kill us.
+ *
+ * As a consequence we race really badly with just about everything. See the
+ * many memory barriers and their comments for details.
  *
  * Return: %true if @p->state changes (an actual wakeup was done),
  *	   %false otherwise.
@@ -2618,7 +2845,7 @@
 		/*
 		 * We're waking current, this means 'p->on_rq' and 'task_cpu(p)
 		 * == smp_processor_id()'. Together this means we can special
-		 * case the whole 'p->on_rq && ttwu_remote()' case below
+		 * case the whole 'p->on_rq && ttwu_runnable()' case below
 		 * without taking any locks.
 		 *
 		 * In particular:
@@ -2630,7 +2857,6 @@
 			goto out;
 
 		success = 1;
-		cpu = task_cpu(p);
 		trace_sched_waking(p);
 		p->state = TASK_RUNNING;
 		trace_sched_wakeup(p);
@@ -2640,8 +2866,8 @@
 	/*
 	 * If we are going to wake up a thread waiting for CONDITION we
 	 * need to ensure that CONDITION=1 done by the caller can not be
-	 * reordered with p->state check below. This pairs with mb() in
-	 * set_current_state() the waiting thread does.
+	 * reordered with p->state check below. This pairs with smp_store_mb()
+	 * in set_current_state() that the waiting thread does.
 	 */
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
 	smp_mb__after_spinlock();
@@ -2652,7 +2878,6 @@
 
 	/* We're going to change ->state: */
 	success = 1;
-	cpu = task_cpu(p);
 
 	/*
 	 * Ensure we load p->on_rq _after_ p->state, otherwise it would
@@ -2673,9 +2898,11 @@
 	 *
 	 * 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().
 	 */
 	smp_rmb();
-	if (p->on_rq && ttwu_remote(p, wake_flags))
+	if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags))
 		goto unlock;
 
 #ifdef CONFIG_SMP
@@ -2697,8 +2924,43 @@
 	 *
 	 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
 	 * __schedule().  See the comment for smp_mb__after_spinlock().
+	 *
+	 * Form a control-dep-acquire with p->on_rq == 0 above, to ensure
+	 * schedule()'s deactivate_task() has 'happened' and p will no longer
+	 * care about it's own p->state. See the comment in __schedule().
 	 */
-	smp_rmb();
+	smp_acquire__after_ctrl_dep();
+
+	/*
+	 * We're doing the wakeup (@success == 1), they did a dequeue (p->on_rq
+	 * == 0), which means we need to do an enqueue, change p->state to
+	 * TASK_WAKING such that we can unlock p->pi_lock before doing the
+	 * enqueue, such as ttwu_queue_wakelist().
+	 */
+	p->state = TASK_WAKING;
+
+	/*
+	 * If the owning (remote) CPU is still in the middle of schedule() with
+	 * this task as prev, considering queueing p on the remote CPUs wake_list
+	 * which potentially sends an IPI instead of spinning on p->on_cpu to
+	 * let the waker make forward progress. This is safe because IRQs are
+	 * disabled and the IPI will deliver after on_cpu is cleared.
+	 *
+	 * Ensure we load task_cpu(p) after p->on_cpu:
+	 *
+	 * set_task_cpu(p, cpu);
+	 *   STORE p->cpu = @cpu
+	 * __schedule() (switch to task 'p')
+	 *   LOCK rq->lock
+	 *   smp_mb__after_spin_lock()		smp_cond_load_acquire(&p->on_cpu)
+	 *   STORE p->on_cpu = 1		LOAD p->cpu
+	 *
+	 * to ensure we observe the correct CPU on which the task is currently
+	 * scheduling.
+	 */
+	if (smp_load_acquire(&p->on_cpu) &&
+	    ttwu_queue_wakelist(p, task_cpu(p), wake_flags | WF_ON_CPU))
+		goto unlock;
 
 	/*
 	 * If the owning (remote) CPU is still in the middle of schedule() with
@@ -2711,28 +2973,19 @@
 	 */
 	smp_cond_load_acquire(&p->on_cpu, !VAL);
 
-	p->sched_contributes_to_load = !!task_contributes_to_load(p);
-	p->state = TASK_WAKING;
-
-	if (p->in_iowait) {
-		delayacct_blkio_end(p);
-		atomic_dec(&task_rq(p)->nr_iowait);
-	}
-
 	cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
 	if (task_cpu(p) != cpu) {
+		if (p->in_iowait) {
+			delayacct_blkio_end(p);
+			atomic_dec(&task_rq(p)->nr_iowait);
+		}
+
 		wake_flags |= WF_MIGRATED;
 		psi_ttwu_dequeue(p);
 		set_task_cpu(p, cpu);
 	}
-
-#else /* CONFIG_SMP */
-
-	if (p->in_iowait) {
-		delayacct_blkio_end(p);
-		atomic_dec(&task_rq(p)->nr_iowait);
-	}
-
+#else
+	cpu = task_cpu(p);
 #endif /* CONFIG_SMP */
 
 	ttwu_queue(p, cpu, wake_flags);
@@ -2740,13 +2993,58 @@
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 out:
 	if (success)
-		ttwu_stat(p, cpu, wake_flags);
+		ttwu_stat(p, task_cpu(p), wake_flags);
 	preempt_enable();
 
 	return success;
 }
 
 /**
+ * try_invoke_on_locked_down_task - Invoke a function on task in fixed state
+ * @p: Process for which the function is to be invoked, can be @current.
+ * @func: Function to invoke.
+ * @arg: Argument to function.
+ *
+ * If the specified task can be quickly locked into a definite state
+ * (either sleeping or on a given runqueue), arrange to keep it in that
+ * state while invoking @func(@arg).  This function can use ->on_rq and
+ * task_curr() to work out what the state is, if required.  Given that
+ * @func can be invoked with a runqueue lock held, it had better be quite
+ * lightweight.
+ *
+ * Returns:
+ *	@false if the task slipped out from under the locks.
+ *	@true if the task was locked onto a runqueue or is sleeping.
+ *		However, @func can override this by returning @false.
+ */
+bool try_invoke_on_locked_down_task(struct task_struct *p, bool (*func)(struct task_struct *t, void *arg), void *arg)
+{
+	struct rq_flags rf;
+	bool ret = false;
+	struct rq *rq;
+
+	raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
+	if (p->on_rq) {
+		rq = __task_rq_lock(p, &rf);
+		if (task_rq(p) == rq)
+			ret = func(p, arg);
+		rq_unlock(rq, &rf);
+	} else {
+		switch (p->state) {
+		case TASK_RUNNING:
+		case TASK_WAKING:
+			break;
+		default:
+			smp_rmb(); // See smp_rmb() comment in try_to_wake_up().
+			if (!p->on_rq)
+				ret = func(p, arg);
+		}
+	}
+	raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
+	return ret;
+}
+
+/**
  * wake_up_process - Wake up a specific process
  * @p: The process to be woken up.
  *
@@ -2814,6 +3112,9 @@
 	p->capture_control = NULL;
 #endif
 	init_numa_balancing(clone_flags, p);
+#ifdef CONFIG_SMP
+	p->wake_entry.u_flags = CSD_TYPE_TTWU;
+#endif
 }
 
 DEFINE_STATIC_KEY_FALSE(sched_numa_balancing);
@@ -2830,7 +3131,7 @@
 
 #ifdef CONFIG_PROC_SYSCTL
 int sysctl_numa_balancing(struct ctl_table *table, int write,
-			 void __user *buffer, size_t *lenp, loff_t *ppos)
+			  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table t;
 	int err;
@@ -2904,8 +3205,8 @@
 }
 
 #ifdef CONFIG_PROC_SYSCTL
-int sysctl_schedstats(struct ctl_table *table, int write,
-			 void __user *buffer, size_t *lenp, loff_t *ppos)
+int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table t;
 	int err;
@@ -2933,8 +3234,6 @@
  */
 int sched_fork(unsigned long clone_flags, struct task_struct *p)
 {
-	unsigned long flags;
-
 	__sched_fork(clone_flags, p);
 	/*
 	 * We mark the process as NEW here. This guarantees that
@@ -2961,7 +3260,7 @@
 		} else if (PRIO_TO_NICE(p->static_prio) < 0)
 			p->static_prio = NICE_TO_PRIO(0);
 
-		p->prio = p->normal_prio = __normal_prio(p);
+		p->prio = p->normal_prio = p->static_prio;
 		set_load_weight(p, false);
 
 		/*
@@ -2980,24 +3279,6 @@
 
 	init_entity_runnable_average(&p->se);
 
-	/*
-	 * The child is not yet in the pid-hash so no cgroup attach races,
-	 * and the cgroup is pinned to this child due to cgroup_fork()
-	 * is ran before sched_fork().
-	 *
-	 * Silence PROVE_RCU.
-	 */
-	raw_spin_lock_irqsave(&p->pi_lock, flags);
-	rseq_migrate(p);
-	/*
-	 * We're setting the CPU for the first time, we don't migrate,
-	 * so use __set_task_cpu().
-	 */
-	__set_task_cpu(p, smp_processor_id());
-	if (p->sched_class->task_fork)
-		p->sched_class->task_fork(p);
-	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-
 #ifdef CONFIG_SCHED_INFO
 	if (likely(sched_info_on()))
 		memset(&p->sched_info, 0, sizeof(p->sched_info));
@@ -3013,6 +3294,32 @@
 	return 0;
 }
 
+void sched_post_fork(struct task_struct *p, struct kernel_clone_args *kargs)
+{
+	unsigned long flags;
+#ifdef CONFIG_CGROUP_SCHED
+	struct task_group *tg;
+#endif
+
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
+#ifdef CONFIG_CGROUP_SCHED
+	tg = container_of(kargs->cset->subsys[cpu_cgrp_id],
+			  struct task_group, css);
+	p->sched_task_group = autogroup_task_group(p, tg);
+#endif
+	rseq_migrate(p);
+	/*
+	 * We're setting the CPU for the first time, we don't migrate,
+	 * so use __set_task_cpu().
+	 */
+	__set_task_cpu(p, smp_processor_id());
+	if (p->sched_class->task_fork)
+		p->sched_class->task_fork(p);
+	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+
+	uclamp_post_fork(p);
+}
+
 unsigned long to_ratio(u64 period, u64 runtime)
 {
 	if (runtime == RUNTIME_INF)
@@ -3170,8 +3477,10 @@
 	/*
 	 * Claim the task as running, we do this before switching to it
 	 * such that any running task will have this set.
+	 *
+	 * See the ttwu() WF_ON_CPU case and its ordering comment.
 	 */
-	next->on_cpu = 1;
+	WRITE_ONCE(next->on_cpu, 1);
 #endif
 }
 
@@ -3179,8 +3488,9 @@
 {
 #ifdef CONFIG_SMP
 	/*
-	 * After ->on_cpu is cleared, the task can be moved to a different CPU.
-	 * We must ensure this doesn't happen until the switch is completely
+	 * This must be the very last reference to @prev from this CPU. After
+	 * p->on_cpu is cleared, the task can be moved to a different CPU. We
+	 * must ensure this doesn't happen until the switch is completely
 	 * finished.
 	 *
 	 * In particular, the load of prev->state in finish_task_switch() must
@@ -3202,7 +3512,7 @@
 	 * do an early lockdep release here:
 	 */
 	rq_unpin_lock(rq, rf);
-	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
+	spin_release(&rq->lock.dep_map, _THIS_IP_);
 #ifdef CONFIG_DEBUG_SPINLOCK
 	/* this is a valid case when another task releases the spinlock */
 	rq->lock.owner = next;
@@ -3689,12 +3999,16 @@
 	struct rq *rq = cpu_rq(cpu);
 	struct task_struct *curr = rq->curr;
 	struct rq_flags rf;
+	unsigned long thermal_pressure;
 
+	arch_scale_freq_tick();
 	sched_clock_tick();
 
 	rq_lock(rq, &rf);
 
 	update_rq_clock(rq);
+	thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq));
+	update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure);
 	curr->sched_class->task_tick(rq, curr, 0);
 	calc_global_load_tick(rq);
 	psi_task_tick(rq);
@@ -3958,8 +4272,7 @@
 	if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)
 	    && in_atomic_preempt_off()) {
 		pr_err("Preemption disabled at:");
-		print_ip_sym(preempt_disable_ip);
-		pr_cont("\n");
+		print_ip_sym(KERN_ERR, preempt_disable_ip);
 	}
 	if (panic_on_warn)
 		panic("scheduling while atomic\n");
@@ -3976,6 +4289,9 @@
 #ifdef CONFIG_SCHED_STACK_END_CHECK
 	if (task_stack_end_corrupted(prev))
 		panic("corrupted stack end detected inside scheduler\n");
+
+	if (task_scs_end_corrupted(prev))
+		panic("corrupted shadow stack detected inside scheduler\n");
 #endif
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
@@ -3998,6 +4314,28 @@
 	schedstat_inc(this_rq()->sched_count);
 }
 
+static void put_prev_task_balance(struct rq *rq, struct task_struct *prev,
+				  struct rq_flags *rf)
+{
+#ifdef CONFIG_SMP
+	const struct sched_class *class;
+	/*
+	 * We must do the balancing pass before put_prev_task(), such
+	 * that when we release the rq->lock the task is in the same
+	 * state as before we took rq->lock.
+	 *
+	 * We can terminate the balance pass as soon as we know there is
+	 * a runnable task of @class priority or higher.
+	 */
+	for_class_range(class, prev->sched_class, &idle_sched_class) {
+		if (class->balance(rq, prev, rf))
+			break;
+	}
+#endif
+
+	put_prev_task(rq, prev);
+}
+
 /*
  * Pick up the highest-prio task:
  */
@@ -4013,41 +4351,27 @@
 	 * higher scheduling class, because otherwise those loose the
 	 * opportunity to pull in more work from other CPUs.
 	 */
-	if (likely((prev->sched_class == &idle_sched_class ||
-		    prev->sched_class == &fair_sched_class) &&
+	if (likely(prev->sched_class <= &fair_sched_class &&
 		   rq->nr_running == rq->cfs.h_nr_running)) {
 
-		p = fair_sched_class.pick_next_task(rq, prev, rf);
+		p = pick_next_task_fair(rq, prev, rf);
 		if (unlikely(p == RETRY_TASK))
 			goto restart;
 
 		/* Assumes fair_sched_class->next == idle_sched_class */
-		if (unlikely(!p))
-			p = idle_sched_class.pick_next_task(rq, prev, rf);
+		if (!p) {
+			put_prev_task(rq, prev);
+			p = pick_next_task_idle(rq);
+		}
 
 		return p;
 	}
 
 restart:
-#ifdef CONFIG_SMP
-	/*
-	 * We must do the balancing pass before put_next_task(), such
-	 * that when we release the rq->lock the task is in the same
-	 * state as before we took rq->lock.
-	 *
-	 * We can terminate the balance pass as soon as we know there is
-	 * a runnable task of @class priority or higher.
-	 */
-	for_class_range(class, prev->sched_class, &idle_sched_class) {
-		if (class->balance(rq, prev, rf))
-			break;
-	}
-#endif
-
-	put_prev_task(rq, prev);
+	put_prev_task_balance(rq, prev, rf);
 
 	for_each_class(class) {
-		p = class->pick_next_task(rq, NULL, NULL);
+		p = class->pick_next_task(rq);
 		if (p)
 			return p;
 	}
@@ -4099,6 +4423,7 @@
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
+	unsigned long prev_state;
 	struct rq_flags rf;
 	struct rq *rq;
 	int cpu;
@@ -4118,9 +4443,16 @@
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below
 	 * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
-	 * done by the caller to avoid the race with signal_wake_up().
+	 * done by the caller to avoid the race with signal_wake_up():
 	 *
-	 * The membarrier system call requires a full memory barrier
+	 * __set_current_state(@state)		signal_wake_up()
+	 * schedule()				  set_tsk_thread_flag(p, TIF_SIGPENDING)
+	 *					  wake_up_state(p, state)
+	 *   LOCK rq->lock			    LOCK p->pi_state
+	 *   smp_mb__after_spinlock()		    smp_mb__after_spinlock()
+	 *     if (signal_pending_state())	    if (p->state & @state)
+	 *
+	 * Also, the membarrier system call requires a full memory barrier
 	 * after coming from user-space, before storing to rq->curr.
 	 */
 	rq_lock(rq, &rf);
@@ -4131,10 +4463,38 @@
 	update_rq_clock(rq);
 
 	switch_count = &prev->nivcsw;
-	if (!preempt && prev->state) {
-		if (signal_pending_state(prev->state, prev)) {
+
+	/*
+	 * We must load prev->state once (task_struct::state is volatile), such
+	 * that:
+	 *
+	 *  - we form a control dependency vs deactivate_task() below.
+	 *  - ptrace_{,un}freeze_traced() can change ->state underneath us.
+	 */
+	prev_state = prev->state;
+	if (!preempt && prev_state) {
+		if (signal_pending_state(prev_state, prev)) {
 			prev->state = TASK_RUNNING;
 		} else {
+			prev->sched_contributes_to_load =
+				(prev_state & TASK_UNINTERRUPTIBLE) &&
+				!(prev_state & TASK_NOLOAD) &&
+				!(prev->flags & PF_FROZEN);
+
+			if (prev->sched_contributes_to_load)
+				rq->nr_uninterruptible++;
+
+			/*
+			 * __schedule()			ttwu()
+			 *   prev_state = prev->state;    if (p->on_rq && ...)
+			 *   if (prev_state)		    goto out;
+			 *     p->on_rq = 0;		  smp_acquire__after_ctrl_dep();
+			 *				  p->state = TASK_WAKING
+			 *
+			 * Where __schedule() and ttwu() have matching control dependencies.
+			 *
+			 * After this, schedule() must not care about p->state any more.
+			 */
 			deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
 
 			if (prev->in_iowait) {
@@ -4172,6 +4532,8 @@
 		 */
 		++*switch_count;
 
+		psi_sched_switch(prev, next, !task_on_rq_queued(prev));
+
 		trace_sched_switch(preempt, prev, next);
 
 		/* Also unlocks the rq: */
@@ -4202,9 +4564,12 @@
 
 static inline void sched_submit_work(struct task_struct *tsk)
 {
+	unsigned int task_flags;
+
 	if (!tsk->state)
 		return;
 
+	task_flags = tsk->flags;
 	/*
 	 * If a worker went to sleep, notify and ask workqueue whether
 	 * it wants to wake up a task to maintain concurrency.
@@ -4213,9 +4578,12 @@
 	 * in the possible wakeup of a kworker and because wq_worker_sleeping()
 	 * requires it.
 	 */
-	if (tsk->flags & PF_WQ_WORKER) {
+	if (task_flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
 		preempt_disable();
-		wq_worker_sleeping(tsk);
+		if (task_flags & PF_WQ_WORKER)
+			wq_worker_sleeping(tsk);
+		else
+			io_wq_worker_sleeping(tsk);
 		preempt_enable_no_resched();
 	}
 
@@ -4232,8 +4600,12 @@
 
 static void sched_update_worker(struct task_struct *tsk)
 {
-	if (tsk->flags & PF_WQ_WORKER)
-		wq_worker_running(tsk);
+	if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
+		if (tsk->flags & PF_WQ_WORKER)
+			wq_worker_running(tsk);
+		else
+			io_wq_worker_running(tsk);
+	}
 }
 
 asmlinkage __visible void __sched schedule(void)
@@ -4437,10 +4809,23 @@
 int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags,
 			  void *key)
 {
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_SCHED_DEBUG) && wake_flags & ~WF_SYNC);
 	return try_to_wake_up(curr->private, mode, wake_flags);
 }
 EXPORT_SYMBOL(default_wake_function);
 
+static void __setscheduler_prio(struct task_struct *p, int prio)
+{
+	if (dl_prio(prio))
+		p->sched_class = &dl_sched_class;
+	else if (rt_prio(prio))
+		p->sched_class = &rt_sched_class;
+	else
+		p->sched_class = &fair_sched_class;
+
+	p->prio = prio;
+}
+
 #ifdef CONFIG_RT_MUTEXES
 
 static inline int __rt_effective_prio(struct task_struct *pi_task, int prio)
@@ -4551,26 +4936,24 @@
 		if (!dl_prio(p->normal_prio) ||
 		    (pi_task && dl_prio(pi_task->prio) &&
 		     dl_entity_preempt(&pi_task->dl, &p->dl))) {
-			p->dl.dl_boosted = 1;
+			p->dl.pi_se = pi_task->dl.pi_se;
 			queue_flag |= ENQUEUE_REPLENISH;
-		} else
-			p->dl.dl_boosted = 0;
-		p->sched_class = &dl_sched_class;
+		} else {
+			p->dl.pi_se = &p->dl;
+		}
 	} else if (rt_prio(prio)) {
 		if (dl_prio(oldprio))
-			p->dl.dl_boosted = 0;
+			p->dl.pi_se = &p->dl;
 		if (oldprio < prio)
 			queue_flag |= ENQUEUE_HEAD;
-		p->sched_class = &rt_sched_class;
 	} else {
 		if (dl_prio(oldprio))
-			p->dl.dl_boosted = 0;
+			p->dl.pi_se = &p->dl;
 		if (rt_prio(oldprio))
 			p->rt.timeout = 0;
-		p->sched_class = &fair_sched_class;
 	}
 
-	p->prio = prio;
+	__setscheduler_prio(p, prio);
 
 	if (queued)
 		enqueue_task(rq, p, queue_flag);
@@ -4596,7 +4979,7 @@
 void set_user_nice(struct task_struct *p, long nice)
 {
 	bool queued, running;
-	int old_prio, delta;
+	int old_prio;
 	struct rq_flags rf;
 	struct rq *rq;
 
@@ -4630,19 +5013,18 @@
 	set_load_weight(p, true);
 	old_prio = p->prio;
 	p->prio = effective_prio(p);
-	delta = p->prio - old_prio;
 
-	if (queued) {
+	if (queued)
 		enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
-		/*
-		 * If the task increased its priority or is running and
-		 * lowered its priority, then reschedule its CPU:
-		 */
-		if (delta < 0 || (delta > 0 && task_running(rq, p)))
-			resched_curr(rq);
-	}
 	if (running)
 		set_next_task(rq, p);
+
+	/*
+	 * If the task increased its priority or is running and
+	 * lowered its priority, then reschedule its CPU:
+	 */
+	p->sched_class->prio_changed(rq, p, old_prio);
+
 out_unlock:
 	task_rq_unlock(rq, p, &rf);
 }
@@ -4727,7 +5109,7 @@
 		return 0;
 
 #ifdef CONFIG_SMP
-	if (!llist_empty(&rq->wake_list))
+	if (rq->ttwu_pending)
 		return 0;
 #endif
 
@@ -4804,35 +5186,6 @@
 	set_load_weight(p, true);
 }
 
-/* Actually do priority change: must hold pi & rq lock. */
-static void __setscheduler(struct rq *rq, struct task_struct *p,
-			   const struct sched_attr *attr, bool keep_boost)
-{
-	/*
-	 * If params can't change scheduling class changes aren't allowed
-	 * either.
-	 */
-	if (attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)
-		return;
-
-	__setscheduler_params(p, attr);
-
-	/*
-	 * Keep a potential priority boosting if called from
-	 * sched_setscheduler().
-	 */
-	p->prio = normal_prio(p);
-	if (keep_boost)
-		p->prio = rt_effective_prio(p, p->prio);
-
-	if (dl_prio(p->prio))
-		p->sched_class = &dl_sched_class;
-	else if (rt_prio(p->prio))
-		p->sched_class = &rt_sched_class;
-	else
-		p->sched_class = &fair_sched_class;
-}
-
 /*
  * Check the target process has a UID that matches the current process's:
  */
@@ -4853,10 +5206,8 @@
 				const struct sched_attr *attr,
 				bool user, bool pi)
 {
-	int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 :
-		      MAX_RT_PRIO - 1 - attr->sched_priority;
-	int retval, oldprio, oldpolicy = -1, queued, running;
-	int new_effective_prio, policy = attr->sched_policy;
+	int oldpolicy = -1, policy = attr->sched_policy;
+	int retval, oldprio, newprio, queued, running;
 	const struct sched_class *prev_class;
 	struct rq_flags rf;
 	int reset_on_fork;
@@ -5054,6 +5405,7 @@
 	p->sched_reset_on_fork = reset_on_fork;
 	oldprio = p->prio;
 
+	newprio = __normal_prio(policy, attr->sched_priority, attr->sched_nice);
 	if (pi) {
 		/*
 		 * Take priority boosted tasks into account. If the new
@@ -5062,8 +5414,8 @@
 		 * the runqueue. This will be done when the task deboost
 		 * itself.
 		 */
-		new_effective_prio = rt_effective_prio(p, newprio);
-		if (new_effective_prio == oldprio)
+		newprio = rt_effective_prio(p, newprio);
+		if (newprio == oldprio)
 			queue_flags &= ~DEQUEUE_MOVE;
 	}
 
@@ -5076,7 +5428,10 @@
 
 	prev_class = p->sched_class;
 
-	__setscheduler(rq, p, attr, pi);
+	if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) {
+		__setscheduler_params(p, attr);
+		__setscheduler_prio(p, newprio);
+	}
 	__setscheduler_uclamp(p, attr);
 
 	if (queued) {
@@ -5140,6 +5495,8 @@
  * @policy: new policy.
  * @param: structure containing the new RT priority.
  *
+ * Use sched_set_fifo(), read its comment.
+ *
  * Return: 0 on success. An error code otherwise.
  *
  * NOTE that the task may be already dead.
@@ -5149,13 +5506,11 @@
 {
 	return _sched_setscheduler(p, policy, param, true);
 }
-EXPORT_SYMBOL_GPL(sched_setscheduler);
 
 int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
 {
 	return __sched_setscheduler(p, attr, true, true);
 }
-EXPORT_SYMBOL_GPL(sched_setattr);
 
 int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr)
 {
@@ -5180,7 +5535,51 @@
 {
 	return _sched_setscheduler(p, policy, param, false);
 }
-EXPORT_SYMBOL_GPL(sched_setscheduler_nocheck);
+
+/*
+ * SCHED_FIFO is a broken scheduler model; that is, it is fundamentally
+ * incapable of resource management, which is the one thing an OS really should
+ * be doing.
+ *
+ * This is of course the reason it is limited to privileged users only.
+ *
+ * Worse still; it is fundamentally impossible to compose static priority
+ * workloads. You cannot take two correctly working static prio workloads
+ * and smash them together and still expect them to work.
+ *
+ * For this reason 'all' FIFO tasks the kernel creates are basically at:
+ *
+ *   MAX_RT_PRIO / 2
+ *
+ * The administrator _MUST_ configure the system, the kernel simply doesn't
+ * know enough information to make a sensible choice.
+ */
+void sched_set_fifo(struct task_struct *p)
+{
+	struct sched_param sp = { .sched_priority = MAX_RT_PRIO / 2 };
+	WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
+}
+EXPORT_SYMBOL_GPL(sched_set_fifo);
+
+/*
+ * For when you don't much care about FIFO, but want to be above SCHED_NORMAL.
+ */
+void sched_set_fifo_low(struct task_struct *p)
+{
+	struct sched_param sp = { .sched_priority = 1 };
+	WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
+}
+EXPORT_SYMBOL_GPL(sched_set_fifo_low);
+
+void sched_set_normal(struct task_struct *p, int nice)
+{
+	struct sched_attr attr = {
+		.sched_policy = SCHED_NORMAL,
+		.sched_nice = nice,
+	};
+	WARN_ON_ONCE(sched_setattr_nocheck(p, &attr) != 0);
+}
+EXPORT_SYMBOL_GPL(sched_set_normal);
 
 static int
 do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
@@ -5471,6 +5870,11 @@
 		kattr.sched_nice = task_nice(p);
 
 #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;
 #endif
@@ -5824,7 +6228,7 @@
 	if (task_running(p_rq, p) || p->state)
 		goto out_unlock;
 
-	yielded = curr->sched_class->yield_to_task(rq, p, preempt);
+	yielded = curr->sched_class->yield_to_task(rq, p);
 	if (yielded) {
 		schedstat_inc(rq->yld_count);
 		/*
@@ -6022,10 +6426,10 @@
 	if (!try_get_task_stack(p))
 		return;
 
-	printk(KERN_INFO "%-15.15s %c", p->comm, task_state_to_char(p));
+	pr_info("task:%-15.15s state:%c", p->comm, task_state_to_char(p));
 
 	if (p->state == TASK_RUNNING)
-		printk(KERN_CONT "  running task    ");
+		pr_cont("  running task    ");
 #ifdef CONFIG_DEBUG_STACK_USAGE
 	free = stack_not_used(p);
 #endif
@@ -6034,12 +6438,12 @@
 	if (pid_alive(p))
 		ppid = task_pid_nr(rcu_dereference(p->real_parent));
 	rcu_read_unlock();
-	printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free,
-		task_pid_nr(p), ppid,
+	pr_cont(" stack:%5lu pid:%5d ppid:%6d flags:0x%08lx\n",
+		free, task_pid_nr(p), ppid,
 		(unsigned long)task_thread_info(p)->flags);
 
 	print_worker_info(KERN_INFO, p);
-	show_stack(p, NULL);
+	show_stack(p, NULL, KERN_INFO);
 	put_task_stack(p);
 }
 EXPORT_SYMBOL_GPL(sched_show_task);
@@ -6070,13 +6474,6 @@
 {
 	struct task_struct *g, *p;
 
-#if BITS_PER_LONG == 32
-	printk(KERN_INFO
-		"  task                PC stack   pid father\n");
-#else
-	printk(KERN_INFO
-		"  task                        PC stack   pid father\n");
-#endif
 	rcu_read_lock();
 	for_each_process_thread(g, p) {
 		/*
@@ -6112,7 +6509,7 @@
  * NOTE: this function does not set the idle thread's NEED_RESCHED
  * flag, to make booting more robust.
  */
-void init_idle(struct task_struct *idle, int cpu)
+void __init init_idle(struct task_struct *idle, int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long flags;
@@ -6126,8 +6523,6 @@
 	idle->se.exec_start = sched_clock();
 	idle->flags |= PF_IDLE;
 
-	kasan_unpoison_task_stack(idle);
-
 #ifdef CONFIG_SMP
 	/*
 	 * Its possible that init_idle() gets called multiple times on a task,
@@ -6308,7 +6703,7 @@
 	struct task_struct *next;
 
 	for_each_class(class) {
-		next = class->pick_next_task(rq, NULL, NULL);
+		next = class->pick_next_task(rq);
 		if (next) {
 			next->sched_class->put_prev_task(rq, next);
 			return next;
@@ -6573,7 +6968,6 @@
 	struct rq_flags rf;
 
 	/* Handle pending wakeups and then migrate everything off */
-	sched_ttwu_pending();
 	sched_tick_stop(cpu);
 
 	rq_lock_irqsave(rq, &rf);
@@ -6658,6 +7052,14 @@
 	unsigned long ptr = 0;
 	int i;
 
+	/* Make sure the linker didn't screw up */
+	BUG_ON(&idle_sched_class + 1 != &fair_sched_class ||
+	       &fair_sched_class + 1 != &rt_sched_class ||
+	       &rt_sched_class + 1   != &dl_sched_class);
+#ifdef CONFIG_SMP
+	BUG_ON(&dl_sched_class + 1 != &stop_sched_class);
+#endif
+
 	wait_bit_init();
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -6676,6 +7078,8 @@
 		root_task_group.cfs_rq = (struct cfs_rq **)ptr;
 		ptr += nr_cpu_ids * sizeof(void **);
 
+		root_task_group.shares = ROOT_TASK_GROUP_LOAD;
+		init_cfs_bandwidth(&root_task_group.cfs_bandwidth);
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 #ifdef CONFIG_RT_GROUP_SCHED
 		root_task_group.rt_se = (struct sched_rt_entity **)ptr;
@@ -6728,7 +7132,6 @@
 		init_rt_rq(&rq->rt);
 		init_dl_rq(&rq->dl);
 #ifdef CONFIG_FAIR_GROUP_SCHED
-		root_task_group.shares = ROOT_TASK_GROUP_LOAD;
 		INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
 		rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
 		/*
@@ -6750,7 +7153,6 @@
 		 * We achieve this by letting root_task_group's tasks sit
 		 * directly in rq->cfs (i.e root_task_group->se[] = NULL).
 		 */
-		init_cfs_bandwidth(&root_task_group.cfs_bandwidth);
 		init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, NULL);
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
@@ -6776,9 +7178,10 @@
 
 		rq_attach_root(rq, &def_root_domain);
 #ifdef CONFIG_NO_HZ_COMMON
-		rq->last_load_update_tick = jiffies;
 		rq->last_blocked_load_update_tick = jiffies;
 		atomic_set(&rq->nohz_flags, 0);
+
+		rq_csd_init(rq, &rq->nohz_csd, nohz_csd_func);
 #endif
 #endif /* CONFIG_SMP */
 		hrtick_rq_init(rq);
@@ -6883,8 +7286,7 @@
 	if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)
 	    && !preempt_count_equals(preempt_offset)) {
 		pr_err("Preemption disabled at:");
-		print_ip_sym(preempt_disable_ip);
-		pr_cont("\n");
+		print_ip_sym(KERN_ERR, preempt_disable_ip);
 	}
 	dump_stack();
 	add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
@@ -8075,4 +8477,7 @@
  /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
 };
 
-#undef CREATE_TRACE_POINTS
+void call_trace_sched_update_nr_running(struct rq *rq, int count)
+{
+        trace_sched_update_nr_running_tp(rq, count);
+}
diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index 9fbb103..941c28c 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -5,6 +5,7 @@
  * Based on the work by Paul Menage (menage@google.com) and Balbir Singh
  * (balbir@in.ibm.com).
  */
+#include <asm/irq_regs.h>
 #include "sched.h"
 
 /* Time spent by the tasks of the CPU accounting group executing in ... */
@@ -339,7 +340,7 @@
 {
 	struct cpuacct *ca;
 	int index = CPUACCT_STAT_SYSTEM;
-	struct pt_regs *regs = task_pt_regs(tsk);
+	struct pt_regs *regs = get_irq_regs() ? : task_pt_regs(tsk);
 
 	if (regs && user_mode(regs))
 		index = CPUACCT_STAT_USER;
@@ -347,7 +348,7 @@
 	rcu_read_lock();
 
 	for (ca = task_ca(tsk); ca; ca = parent_ca(ca))
-		this_cpu_ptr(ca->cpuusage)->usages[index] += cputime;
+		__this_cpu_add(ca->cpuusage->usages[index], cputime);
 
 	rcu_read_unlock();
 }
@@ -363,7 +364,7 @@
 
 	rcu_read_lock();
 	for (ca = task_ca(tsk); ca != &root_cpuacct; ca = parent_ca(ca))
-		this_cpu_ptr(ca->cpustat)->cpustat[index] += val;
+		__this_cpu_add(ca->cpustat->cpustat[index], val);
 	rcu_read_unlock();
 }
 
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 5cc4012..8cb06c8 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -121,6 +121,30 @@
 
 	if (later_mask &&
 	    cpumask_and(later_mask, cp->free_cpus, p->cpus_ptr)) {
+		unsigned long cap, max_cap = 0;
+		int cpu, max_cpu = -1;
+
+		if (!static_branch_unlikely(&sched_asym_cpucapacity))
+			return 1;
+
+		/* Ensure the capacity of the CPUs fits the task. */
+		for_each_cpu(cpu, later_mask) {
+			if (!dl_task_fits_capacity(p, cpu)) {
+				cpumask_clear_cpu(cpu, later_mask);
+
+				cap = capacity_orig_of(cpu);
+
+				if (cap > max_cap ||
+				    (cpu == task_cpu(p) && cap == max_cap)) {
+					max_cap = cap;
+					max_cpu = cpu;
+				}
+			}
+		}
+
+		if (cpumask_empty(later_mask))
+			cpumask_set_cpu(max_cpu, later_mask);
+
 		return 1;
 	} else {
 		int best_cpu = cpudl_maximum(cp);
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 4cb80e6..5e39da0 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -102,8 +102,12 @@
 static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time,
 				   unsigned int next_freq)
 {
-	if (sg_policy->next_freq == next_freq)
-		return false;
+	if (!sg_policy->need_freq_update) {
+		if (sg_policy->next_freq == next_freq)
+			return false;
+	} else {
+		sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
+	}
 
 	sg_policy->next_freq = next_freq;
 	sg_policy->last_freq_update_time = time;
@@ -114,22 +118,8 @@
 static void sugov_fast_switch(struct sugov_policy *sg_policy, u64 time,
 			      unsigned int next_freq)
 {
-	struct cpufreq_policy *policy = sg_policy->policy;
-	int cpu;
-
-	if (!sugov_update_next_freq(sg_policy, time, next_freq))
-		return;
-
-	next_freq = cpufreq_driver_fast_switch(policy, next_freq);
-	if (!next_freq)
-		return;
-
-	policy->cur = next_freq;
-
-	if (trace_cpu_frequency_enabled()) {
-		for_each_cpu(cpu, policy->cpus)
-			trace_cpu_frequency(next_freq, cpu);
-	}
+	if (sugov_update_next_freq(sg_policy, time, next_freq))
+		cpufreq_driver_fast_switch(sg_policy->policy, next_freq);
 }
 
 static void sugov_deferred_update(struct sugov_policy *sg_policy, u64 time,
@@ -178,7 +168,6 @@
 	if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update)
 		return sg_policy->next_freq;
 
-	sg_policy->need_freq_update = false;
 	sg_policy->cached_raw_freq = freq;
 	return cpufreq_driver_resolve_freq(policy, freq);
 }
@@ -238,7 +227,7 @@
 	 */
 	util = util_cfs + cpu_util_rt(rq);
 	if (type == FREQUENCY_UTIL)
-		util = uclamp_util_with(rq, util, p);
+		util = uclamp_rq_util_with(rq, util, p);
 
 	dl_util = cpu_util_dl(rq);
 
@@ -454,7 +443,7 @@
 	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	unsigned long util, max;
 	unsigned int next_f;
-	bool busy;
+	unsigned int cached_freq = sg_policy->cached_raw_freq;
 
 	sugov_iowait_boost(sg_cpu, time, flags);
 	sg_cpu->last_update = time;
@@ -464,9 +453,6 @@
 	if (!sugov_should_update_freq(sg_policy, time))
 		return;
 
-	/* Limits may have changed, don't skip frequency update */
-	busy = !sg_policy->need_freq_update && sugov_cpu_is_busy(sg_cpu);
-
 	util = sugov_get_util(sg_cpu);
 	max = sg_cpu->max;
 	util = sugov_iowait_apply(sg_cpu, time, util, max);
@@ -475,11 +461,11 @@
 	 * Do not reduce the frequency if the CPU has not been idle
 	 * recently, as the reduction is likely to be premature then.
 	 */
-	if (busy && next_f < sg_policy->next_freq) {
+	if (sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
 		next_f = sg_policy->next_freq;
 
-		/* Reset cached freq as next_freq has changed */
-		sg_policy->cached_raw_freq = 0;
+		/* Restore cached freq as next_freq has changed */
+		sg_policy->cached_raw_freq = cached_freq;
 	}
 
 	/*
@@ -624,9 +610,17 @@
 };
 ATTRIBUTE_GROUPS(sugov);
 
+static void sugov_tunables_free(struct kobject *kobj)
+{
+	struct gov_attr_set *attr_set = container_of(kobj, struct gov_attr_set, kobj);
+
+	kfree(to_sugov_tunables(attr_set));
+}
+
 static struct kobj_type sugov_tunables_ktype = {
 	.default_groups = sugov_groups,
 	.sysfs_ops = &governor_sysfs_ops,
+	.release = &sugov_tunables_free,
 };
 
 /********************** cpufreq governor interface *********************/
@@ -726,12 +720,10 @@
 	return tunables;
 }
 
-static void sugov_tunables_free(struct sugov_tunables *tunables)
+static void sugov_clear_global_tunables(void)
 {
 	if (!have_governor_per_policy())
 		global_tunables = NULL;
-
-	kfree(tunables);
 }
 
 static int sugov_init(struct cpufreq_policy *policy)
@@ -794,7 +786,7 @@
 fail:
 	kobject_put(&tunables->attr_set.kobj);
 	policy->governor_data = NULL;
-	sugov_tunables_free(tunables);
+	sugov_clear_global_tunables();
 
 stop_kthread:
 	sugov_kthread_stop(sg_policy);
@@ -821,7 +813,7 @@
 	count = gov_attr_set_put(&tunables->attr_set, &sg_policy->tunables_hook);
 	policy->governor_data = NULL;
 	if (!count)
-		sugov_tunables_free(tunables);
+		sugov_clear_global_tunables();
 
 	mutex_unlock(&global_tunables_lock);
 
@@ -840,9 +832,10 @@
 	sg_policy->next_freq			= 0;
 	sg_policy->work_in_progress		= false;
 	sg_policy->limits_changed		= false;
-	sg_policy->need_freq_update		= false;
 	sg_policy->cached_raw_freq		= 0;
 
+	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);
 
@@ -894,7 +887,7 @@
 struct cpufreq_governor schedutil_gov = {
 	.name			= "schedutil",
 	.owner			= THIS_MODULE,
-	.dynamic_switching	= true,
+	.flags			= CPUFREQ_GOV_DYNAMIC_SWITCHING,
 	.init			= sugov_init,
 	.exit			= sugov_exit,
 	.start			= sugov_start,
@@ -909,11 +902,7 @@
 }
 #endif
 
-static int __init sugov_register(void)
-{
-	return cpufreq_register_governor(&schedutil_gov);
-}
-fs_initcall(sugov_register);
+cpufreq_governor_init(schedutil_gov);
 
 #ifdef CONFIG_ENERGY_MODEL
 extern bool sched_energy_update;
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index b7abca9..0033731 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -41,11 +41,72 @@
 	return cpupri;
 }
 
+static inline int __cpupri_find(struct cpupri *cp, struct task_struct *p,
+				struct cpumask *lowest_mask, int idx)
+{
+	struct cpupri_vec *vec  = &cp->pri_to_cpu[idx];
+	int skip = 0;
+
+	if (!atomic_read(&(vec)->count))
+		skip = 1;
+	/*
+	 * When looking at the vector, we need to read the counter,
+	 * do a memory barrier, then read the mask.
+	 *
+	 * Note: This is still all racey, but we can deal with it.
+	 *  Ideally, we only want to look at masks that are set.
+	 *
+	 *  If a mask is not set, then the only thing wrong is that we
+	 *  did a little more work than necessary.
+	 *
+	 *  If we read a zero count but the mask is set, because of the
+	 *  memory barriers, that can only happen when the highest prio
+	 *  task for a run queue has left the run queue, in which case,
+	 *  it will be followed by a pull. If the task we are processing
+	 *  fails to find a proper place to go, that pull request will
+	 *  pull this task if the run queue is running at a lower
+	 *  priority.
+	 */
+	smp_rmb();
+
+	/* Need to do the rmb for every iteration */
+	if (skip)
+		return 0;
+
+	if (cpumask_any_and(p->cpus_ptr, vec->mask) >= nr_cpu_ids)
+		return 0;
+
+	if (lowest_mask) {
+		cpumask_and(lowest_mask, p->cpus_ptr, vec->mask);
+
+		/*
+		 * We have to ensure that we have at least one bit
+		 * still set in the array, since the map could have
+		 * been concurrently emptied between the first and
+		 * second reads of vec->mask.  If we hit this
+		 * condition, simply act as though we never hit this
+		 * priority level and continue on.
+		 */
+		if (cpumask_empty(lowest_mask))
+			return 0;
+	}
+
+	return 1;
+}
+
+int cpupri_find(struct cpupri *cp, struct task_struct *p,
+		struct cpumask *lowest_mask)
+{
+	return cpupri_find_fitness(cp, p, lowest_mask, NULL);
+}
+
 /**
- * cpupri_find - find the best (lowest-pri) CPU in the system
+ * cpupri_find_fitness - find the best (lowest-pri) CPU in the system
  * @cp: The cpupri context
  * @p: The task
  * @lowest_mask: A mask to fill in with selected CPUs (or NULL)
+ * @fitness_fn: A pointer to a function to do custom checks whether the CPU
+ *              fits a specific criteria so that we only return those CPUs.
  *
  * Note: This function returns the recommended CPUs as calculated during the
  * current invocation.  By the time the call returns, the CPUs may have in
@@ -56,65 +117,59 @@
  *
  * Return: (int)bool - CPUs were found
  */
-int cpupri_find(struct cpupri *cp, struct task_struct *p,
-		struct cpumask *lowest_mask)
+int cpupri_find_fitness(struct cpupri *cp, struct task_struct *p,
+		struct cpumask *lowest_mask,
+		bool (*fitness_fn)(struct task_struct *p, int cpu))
 {
-	int idx = 0;
 	int task_pri = convert_prio(p->prio);
+	int idx, cpu;
 
 	BUG_ON(task_pri >= CPUPRI_NR_PRIORITIES);
 
 	for (idx = 0; idx < task_pri; idx++) {
-		struct cpupri_vec *vec  = &cp->pri_to_cpu[idx];
-		int skip = 0;
 
-		if (!atomic_read(&(vec)->count))
-			skip = 1;
-		/*
-		 * When looking at the vector, we need to read the counter,
-		 * do a memory barrier, then read the mask.
-		 *
-		 * Note: This is still all racey, but we can deal with it.
-		 *  Ideally, we only want to look at masks that are set.
-		 *
-		 *  If a mask is not set, then the only thing wrong is that we
-		 *  did a little more work than necessary.
-		 *
-		 *  If we read a zero count but the mask is set, because of the
-		 *  memory barriers, that can only happen when the highest prio
-		 *  task for a run queue has left the run queue, in which case,
-		 *  it will be followed by a pull. If the task we are processing
-		 *  fails to find a proper place to go, that pull request will
-		 *  pull this task if the run queue is running at a lower
-		 *  priority.
-		 */
-		smp_rmb();
-
-		/* Need to do the rmb for every iteration */
-		if (skip)
+		if (!__cpupri_find(cp, p, lowest_mask, idx))
 			continue;
 
-		if (cpumask_any_and(p->cpus_ptr, vec->mask) >= nr_cpu_ids)
-			continue;
+		if (!lowest_mask || !fitness_fn)
+			return 1;
 
-		if (lowest_mask) {
-			cpumask_and(lowest_mask, p->cpus_ptr, vec->mask);
-
-			/*
-			 * We have to ensure that we have at least one bit
-			 * still set in the array, since the map could have
-			 * been concurrently emptied between the first and
-			 * second reads of vec->mask.  If we hit this
-			 * condition, simply act as though we never hit this
-			 * priority level and continue on.
-			 */
-			if (cpumask_any(lowest_mask) >= nr_cpu_ids)
-				continue;
+		/* Ensure the capacity of the CPUs fit the task */
+		for_each_cpu(cpu, lowest_mask) {
+			if (!fitness_fn(p, cpu))
+				cpumask_clear_cpu(cpu, lowest_mask);
 		}
 
+		/*
+		 * If no CPU at the current priority can fit the task
+		 * continue looking
+		 */
+		if (cpumask_empty(lowest_mask))
+			continue;
+
 		return 1;
 	}
 
+	/*
+	 * If we failed to find a fitting lowest_mask, kick off a new search
+	 * but without taking into account any fitness criteria this time.
+	 *
+	 * This rule favours honouring priority over fitting the task in the
+	 * correct CPU (Capacity Awareness being the only user now).
+	 * The idea is that if a higher priority task can run, then it should
+	 * run even if this ends up being on unfitting CPU.
+	 *
+	 * The cost of this trade-off is not entirely clear and will probably
+	 * be good for some workloads and bad for others.
+	 *
+	 * The main idea here is that if some CPUs were overcommitted, we try
+	 * to spread which is what the scheduler traditionally did. Sys admins
+	 * must do proper RT planning to avoid overloading the system if they
+	 * really care.
+	 */
+	if (fitness_fn)
+		return cpupri_find(cp, p, lowest_mask);
+
 	return 0;
 }
 
diff --git a/kernel/sched/cpupri.h b/kernel/sched/cpupri.h
index 7dc20a3..efbb492 100644
--- a/kernel/sched/cpupri.h
+++ b/kernel/sched/cpupri.h
@@ -18,7 +18,11 @@
 };
 
 #ifdef CONFIG_SMP
-int  cpupri_find(struct cpupri *cp, struct task_struct *p, struct cpumask *lowest_mask);
+int  cpupri_find(struct cpupri *cp, struct task_struct *p,
+		 struct cpumask *lowest_mask);
+int  cpupri_find_fitness(struct cpupri *cp, struct task_struct *p,
+			 struct cpumask *lowest_mask,
+			 bool (*fitness_fn)(struct task_struct *p, int cpu));
 void cpupri_set(struct cpupri *cp, int cpu, int pri);
 int  cpupri_init(struct cpupri *cp);
 void cpupri_cleanup(struct cpupri *cp);
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 46ed4e1..ca0eef7 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -147,10 +147,10 @@
 
 	/* Add guest time to cpustat. */
 	if (task_nice(p) > 0) {
-		cpustat[CPUTIME_NICE] += cputime;
+		task_group_account_field(p, CPUTIME_NICE, cputime);
 		cpustat[CPUTIME_GUEST_NICE] += cputime;
 	} else {
-		cpustat[CPUTIME_USER] += cputime;
+		task_group_account_field(p, CPUTIME_USER, cputime);
 		cpustat[CPUTIME_GUEST] += cputime;
 	}
 }
@@ -355,7 +355,7 @@
  * softirq as those do not count in task exec_runtime any more.
  */
 static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
-					 struct rq *rq, int ticks)
+					 int ticks)
 {
 	u64 other, cputime = TICK_NSEC * ticks;
 
@@ -381,7 +381,7 @@
 		account_system_index_time(p, cputime, CPUTIME_SOFTIRQ);
 	} else if (user_tick) {
 		account_user_time(p, cputime);
-	} else if (p == rq->idle) {
+	} else if (p == this_rq()->idle) {
 		account_idle_time(cputime);
 	} else if (p->flags & PF_VCPU) { /* System time or guest time */
 		account_guest_time(p, cputime);
@@ -392,40 +392,36 @@
 
 static void irqtime_account_idle_ticks(int ticks)
 {
-	struct rq *rq = this_rq();
-
-	irqtime_account_process_tick(current, 0, rq, ticks);
+	irqtime_account_process_tick(current, 0, ticks);
 }
 #else /* CONFIG_IRQ_TIME_ACCOUNTING */
 static inline void irqtime_account_idle_ticks(int ticks) { }
 static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick,
-						struct rq *rq, int nr_ticks) { }
+						int nr_ticks) { }
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
 
 /*
  * Use precise platform statistics if available:
  */
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+
 # ifndef __ARCH_HAS_VTIME_TASK_SWITCH
-void vtime_common_task_switch(struct task_struct *prev)
+void vtime_task_switch(struct task_struct *prev)
 {
 	if (is_idle_task(prev))
 		vtime_account_idle(prev);
 	else
-		vtime_account_system(prev);
+		vtime_account_kernel(prev);
 
 	vtime_flush(prev);
 	arch_vtime_task_switch(prev);
 }
 # endif
-#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
 
-
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 /*
  * Archs that account the whole time spent in the idle task
  * (outside irq) as idle time can rely on this and just implement
- * vtime_account_system() and vtime_account_idle(). Archs that
+ * vtime_account_kernel() and vtime_account_idle(). Archs that
  * have other meaning of the idle time (s390 only includes the
  * time spent by the CPU when it's in low power mode) must override
  * vtime_account().
@@ -436,7 +432,7 @@
 	if (!in_interrupt() && is_idle_task(tsk))
 		vtime_account_idle(tsk);
 	else
-		vtime_account_system(tsk);
+		vtime_account_kernel(tsk);
 }
 EXPORT_SYMBOL_GPL(vtime_account_irq_enter);
 #endif /* __ARCH_HAS_VTIME_ACCOUNT */
@@ -475,13 +471,12 @@
 void account_process_tick(struct task_struct *p, int user_tick)
 {
 	u64 cputime, steal;
-	struct rq *rq = this_rq();
 
-	if (vtime_accounting_cpu_enabled())
+	if (vtime_accounting_enabled_this_cpu())
 		return;
 
 	if (sched_clock_irqtime) {
-		irqtime_account_process_tick(p, user_tick, rq, 1);
+		irqtime_account_process_tick(p, user_tick, 1);
 		return;
 	}
 
@@ -495,7 +490,7 @@
 
 	if (user_tick)
 		account_user_time(p, cputime);
-	else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
+	else if ((p != this_rq()->idle) || (irq_count() != HARDIRQ_OFFSET))
 		account_system_time(p, HARDIRQ_OFFSET, cputime);
 	else
 		account_idle_time(cputime);
@@ -525,50 +520,6 @@
 }
 
 /*
- * Perform (stime * rtime) / total, but avoid multiplication overflow by
- * losing precision when the numbers are big.
- */
-static u64 scale_stime(u64 stime, u64 rtime, u64 total)
-{
-	u64 scaled;
-
-	for (;;) {
-		/* Make sure "rtime" is the bigger of stime/rtime */
-		if (stime > rtime)
-			swap(rtime, stime);
-
-		/* Make sure 'total' fits in 32 bits */
-		if (total >> 32)
-			goto drop_precision;
-
-		/* Does rtime (and thus stime) fit in 32 bits? */
-		if (!(rtime >> 32))
-			break;
-
-		/* Can we just balance rtime/stime rather than dropping bits? */
-		if (stime >> 31)
-			goto drop_precision;
-
-		/* We can grow stime and shrink rtime and try to make them both fit */
-		stime <<= 1;
-		rtime >>= 1;
-		continue;
-
-drop_precision:
-		/* We drop from rtime, it has more bits than stime */
-		rtime >>= 1;
-		total >>= 1;
-	}
-
-	/*
-	 * Make sure gcc understands that this is a 32x32->64 multiply,
-	 * followed by a 64/32->64 divide.
-	 */
-	scaled = div_u64((u64) (u32) stime * (u64) (u32) rtime, (u32)total);
-	return scaled;
-}
-
-/*
  * Adjust tick based cputime random precision against scheduler runtime
  * accounting.
  *
@@ -627,7 +578,7 @@
 		goto update;
 	}
 
-	stime = scale_stime(stime, rtime, stime + utime);
+	stime = mul_u64_u64_div_u64(stime, rtime, stime + utime);
 
 update:
 	/*
@@ -711,8 +662,8 @@
 	return delta - other;
 }
 
-static void __vtime_account_system(struct task_struct *tsk,
-				   struct vtime *vtime)
+static void vtime_account_system(struct task_struct *tsk,
+				 struct vtime *vtime)
 {
 	vtime->stime += get_vtime_delta(vtime);
 	if (vtime->stime >= TICK_NSEC) {
@@ -731,7 +682,17 @@
 	}
 }
 
-void vtime_account_system(struct task_struct *tsk)
+static void __vtime_account_kernel(struct task_struct *tsk,
+				   struct vtime *vtime)
+{
+	/* We might have scheduled out from guest path */
+	if (vtime->state == VTIME_GUEST)
+		vtime_account_guest(tsk, vtime);
+	else
+		vtime_account_system(tsk, vtime);
+}
+
+void vtime_account_kernel(struct task_struct *tsk)
 {
 	struct vtime *vtime = &tsk->vtime;
 
@@ -739,11 +700,7 @@
 		return;
 
 	write_seqcount_begin(&vtime->seqcount);
-	/* We might have scheduled out from guest path */
-	if (tsk->flags & PF_VCPU)
-		vtime_account_guest(tsk, vtime);
-	else
-		__vtime_account_system(tsk, vtime);
+	__vtime_account_kernel(tsk, vtime);
 	write_seqcount_end(&vtime->seqcount);
 }
 
@@ -752,7 +709,7 @@
 	struct vtime *vtime = &tsk->vtime;
 
 	write_seqcount_begin(&vtime->seqcount);
-	__vtime_account_system(tsk, vtime);
+	vtime_account_system(tsk, vtime);
 	vtime->state = VTIME_USER;
 	write_seqcount_end(&vtime->seqcount);
 }
@@ -782,8 +739,9 @@
 	 * that can thus safely catch up with a tickless delta.
 	 */
 	write_seqcount_begin(&vtime->seqcount);
-	__vtime_account_system(tsk, vtime);
+	vtime_account_system(tsk, vtime);
 	tsk->flags |= PF_VCPU;
+	vtime->state = VTIME_GUEST;
 	write_seqcount_end(&vtime->seqcount);
 }
 EXPORT_SYMBOL_GPL(vtime_guest_enter);
@@ -795,6 +753,7 @@
 	write_seqcount_begin(&vtime->seqcount);
 	vtime_account_guest(tsk, vtime);
 	tsk->flags &= ~PF_VCPU;
+	vtime->state = VTIME_SYS;
 	write_seqcount_end(&vtime->seqcount);
 }
 EXPORT_SYMBOL_GPL(vtime_guest_exit);
@@ -804,19 +763,30 @@
 	account_idle_time(get_vtime_delta(&tsk->vtime));
 }
 
-void arch_vtime_task_switch(struct task_struct *prev)
+void vtime_task_switch_generic(struct task_struct *prev)
 {
 	struct vtime *vtime = &prev->vtime;
 
 	write_seqcount_begin(&vtime->seqcount);
+	if (vtime->state == VTIME_IDLE)
+		vtime_account_idle(prev);
+	else
+		__vtime_account_kernel(prev, vtime);
 	vtime->state = VTIME_INACTIVE;
+	vtime->cpu = -1;
 	write_seqcount_end(&vtime->seqcount);
 
 	vtime = &current->vtime;
 
 	write_seqcount_begin(&vtime->seqcount);
-	vtime->state = VTIME_SYS;
+	if (is_idle_task(current))
+		vtime->state = VTIME_IDLE;
+	else if (current->flags & PF_VCPU)
+		vtime->state = VTIME_GUEST;
+	else
+		vtime->state = VTIME_SYS;
 	vtime->starttime = sched_clock();
+	vtime->cpu = smp_processor_id();
 	write_seqcount_end(&vtime->seqcount);
 }
 
@@ -827,8 +797,9 @@
 
 	local_irq_save(flags);
 	write_seqcount_begin(&vtime->seqcount);
-	vtime->state = VTIME_SYS;
+	vtime->state = VTIME_IDLE;
 	vtime->starttime = sched_clock();
+	vtime->cpu = cpu;
 	write_seqcount_end(&vtime->seqcount);
 	local_irq_restore(flags);
 }
@@ -846,7 +817,7 @@
 		seq = read_seqcount_begin(&vtime->seqcount);
 
 		gtime = t->gtime;
-		if (vtime->state == VTIME_SYS && t->flags & PF_VCPU)
+		if (vtime->state == VTIME_GUEST)
 			gtime += vtime->gtime + vtime_delta(vtime);
 
 	} while (read_seqcount_retry(&vtime->seqcount, seq));
@@ -877,20 +848,233 @@
 		*utime = t->utime;
 		*stime = t->stime;
 
-		/* Task is sleeping, nothing to add */
-		if (vtime->state == VTIME_INACTIVE || is_idle_task(t))
+		/* Task is sleeping or idle, nothing to add */
+		if (vtime->state < VTIME_SYS)
 			continue;
 
 		delta = vtime_delta(vtime);
 
 		/*
-		 * Task runs either in user or kernel space, add pending nohz time to
-		 * the right place.
+		 * Task runs either in user (including guest) or kernel space,
+		 * add pending nohz time to the right place.
 		 */
-		if (vtime->state == VTIME_USER || t->flags & PF_VCPU)
-			*utime += vtime->utime + delta;
-		else if (vtime->state == VTIME_SYS)
+		if (vtime->state == VTIME_SYS)
 			*stime += vtime->stime + delta;
+		else
+			*utime += vtime->utime + delta;
 	} while (read_seqcount_retry(&vtime->seqcount, seq));
 }
+
+static int vtime_state_fetch(struct vtime *vtime, int cpu)
+{
+	int state = READ_ONCE(vtime->state);
+
+	/*
+	 * We raced against a context switch, fetch the
+	 * kcpustat task again.
+	 */
+	if (vtime->cpu != cpu && vtime->cpu != -1)
+		return -EAGAIN;
+
+	/*
+	 * Two possible things here:
+	 * 1) We are seeing the scheduling out task (prev) or any past one.
+	 * 2) We are seeing the scheduling in task (next) but it hasn't
+	 *    passed though vtime_task_switch() yet so the pending
+	 *    cputime of the prev task may not be flushed yet.
+	 *
+	 * Case 1) is ok but 2) is not. So wait for a safe VTIME state.
+	 */
+	if (state == VTIME_INACTIVE)
+		return -EAGAIN;
+
+	return state;
+}
+
+static u64 kcpustat_user_vtime(struct vtime *vtime)
+{
+	if (vtime->state == VTIME_USER)
+		return vtime->utime + vtime_delta(vtime);
+	else if (vtime->state == VTIME_GUEST)
+		return vtime->gtime + vtime_delta(vtime);
+	return 0;
+}
+
+static int kcpustat_field_vtime(u64 *cpustat,
+				struct task_struct *tsk,
+				enum cpu_usage_stat usage,
+				int cpu, u64 *val)
+{
+	struct vtime *vtime = &tsk->vtime;
+	unsigned int seq;
+
+	do {
+		int state;
+
+		seq = read_seqcount_begin(&vtime->seqcount);
+
+		state = vtime_state_fetch(vtime, cpu);
+		if (state < 0)
+			return state;
+
+		*val = cpustat[usage];
+
+		/*
+		 * Nice VS unnice cputime accounting may be inaccurate if
+		 * the nice value has changed since the last vtime update.
+		 * But proper fix would involve interrupting target on nice
+		 * updates which is a no go on nohz_full (although the scheduler
+		 * may still interrupt the target if rescheduling is needed...)
+		 */
+		switch (usage) {
+		case CPUTIME_SYSTEM:
+			if (state == VTIME_SYS)
+				*val += vtime->stime + vtime_delta(vtime);
+			break;
+		case CPUTIME_USER:
+			if (task_nice(tsk) <= 0)
+				*val += kcpustat_user_vtime(vtime);
+			break;
+		case CPUTIME_NICE:
+			if (task_nice(tsk) > 0)
+				*val += kcpustat_user_vtime(vtime);
+			break;
+		case CPUTIME_GUEST:
+			if (state == VTIME_GUEST && task_nice(tsk) <= 0)
+				*val += vtime->gtime + vtime_delta(vtime);
+			break;
+		case CPUTIME_GUEST_NICE:
+			if (state == VTIME_GUEST && task_nice(tsk) > 0)
+				*val += vtime->gtime + vtime_delta(vtime);
+			break;
+		default:
+			break;
+		}
+	} while (read_seqcount_retry(&vtime->seqcount, seq));
+
+	return 0;
+}
+
+u64 kcpustat_field(struct kernel_cpustat *kcpustat,
+		   enum cpu_usage_stat usage, int cpu)
+{
+	u64 *cpustat = kcpustat->cpustat;
+	u64 val = cpustat[usage];
+	struct rq *rq;
+	int err;
+
+	if (!vtime_accounting_enabled_cpu(cpu))
+		return val;
+
+	rq = cpu_rq(cpu);
+
+	for (;;) {
+		struct task_struct *curr;
+
+		rcu_read_lock();
+		curr = rcu_dereference(rq->curr);
+		if (WARN_ON_ONCE(!curr)) {
+			rcu_read_unlock();
+			return cpustat[usage];
+		}
+
+		err = kcpustat_field_vtime(cpustat, curr, usage, cpu, &val);
+		rcu_read_unlock();
+
+		if (!err)
+			return val;
+
+		cpu_relax();
+	}
+}
+EXPORT_SYMBOL_GPL(kcpustat_field);
+
+static int kcpustat_cpu_fetch_vtime(struct kernel_cpustat *dst,
+				    const struct kernel_cpustat *src,
+				    struct task_struct *tsk, int cpu)
+{
+	struct vtime *vtime = &tsk->vtime;
+	unsigned int seq;
+
+	do {
+		u64 *cpustat;
+		u64 delta;
+		int state;
+
+		seq = read_seqcount_begin(&vtime->seqcount);
+
+		state = vtime_state_fetch(vtime, cpu);
+		if (state < 0)
+			return state;
+
+		*dst = *src;
+		cpustat = dst->cpustat;
+
+		/* Task is sleeping, dead or idle, nothing to add */
+		if (state < VTIME_SYS)
+			continue;
+
+		delta = vtime_delta(vtime);
+
+		/*
+		 * Task runs either in user (including guest) or kernel space,
+		 * add pending nohz time to the right place.
+		 */
+		if (state == VTIME_SYS) {
+			cpustat[CPUTIME_SYSTEM] += vtime->stime + delta;
+		} else if (state == VTIME_USER) {
+			if (task_nice(tsk) > 0)
+				cpustat[CPUTIME_NICE] += vtime->utime + delta;
+			else
+				cpustat[CPUTIME_USER] += vtime->utime + delta;
+		} else {
+			WARN_ON_ONCE(state != VTIME_GUEST);
+			if (task_nice(tsk) > 0) {
+				cpustat[CPUTIME_GUEST_NICE] += vtime->gtime + delta;
+				cpustat[CPUTIME_NICE] += vtime->gtime + delta;
+			} else {
+				cpustat[CPUTIME_GUEST] += vtime->gtime + delta;
+				cpustat[CPUTIME_USER] += vtime->gtime + delta;
+			}
+		}
+	} while (read_seqcount_retry(&vtime->seqcount, seq));
+
+	return 0;
+}
+
+void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu)
+{
+	const struct kernel_cpustat *src = &kcpustat_cpu(cpu);
+	struct rq *rq;
+	int err;
+
+	if (!vtime_accounting_enabled_cpu(cpu)) {
+		*dst = *src;
+		return;
+	}
+
+	rq = cpu_rq(cpu);
+
+	for (;;) {
+		struct task_struct *curr;
+
+		rcu_read_lock();
+		curr = rcu_dereference(rq->curr);
+		if (WARN_ON_ONCE(!curr)) {
+			rcu_read_unlock();
+			*dst = *src;
+			return;
+		}
+
+		err = kcpustat_cpu_fetch_vtime(dst, src, curr, cpu);
+		rcu_read_unlock();
+
+		if (!err)
+			return;
+
+		cpu_relax();
+	}
+}
+EXPORT_SYMBOL_GPL(kcpustat_cpu_fetch);
+
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 2bda9fd..a3ae00c 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -43,6 +43,28 @@
 	return !RB_EMPTY_NODE(&dl_se->rb_node);
 }
 
+#ifdef CONFIG_RT_MUTEXES
+static inline struct sched_dl_entity *pi_of(struct sched_dl_entity *dl_se)
+{
+	return dl_se->pi_se;
+}
+
+static inline bool is_dl_boosted(struct sched_dl_entity *dl_se)
+{
+	return pi_of(dl_se) != dl_se;
+}
+#else
+static inline struct sched_dl_entity *pi_of(struct sched_dl_entity *dl_se)
+{
+	return dl_se;
+}
+
+static inline bool is_dl_boosted(struct sched_dl_entity *dl_se)
+{
+	return false;
+}
+#endif
+
 #ifdef CONFIG_SMP
 static inline struct dl_bw *dl_bw_of(int i)
 {
@@ -54,15 +76,49 @@
 static inline int dl_bw_cpus(int i)
 {
 	struct root_domain *rd = cpu_rq(i)->rd;
-	int cpus = 0;
+	int cpus;
 
 	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
 			 "sched RCU must be held");
+
+	if (cpumask_subset(rd->span, cpu_active_mask))
+		return cpumask_weight(rd->span);
+
+	cpus = 0;
+
 	for_each_cpu_and(i, rd->span, cpu_active_mask)
 		cpus++;
 
 	return cpus;
 }
+
+static inline unsigned long __dl_bw_capacity(int i)
+{
+	struct root_domain *rd = cpu_rq(i)->rd;
+	unsigned long cap = 0;
+
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
+			 "sched RCU must be held");
+
+	for_each_cpu_and(i, rd->span, cpu_active_mask)
+		cap += capacity_orig_of(i);
+
+	return cap;
+}
+
+/*
+ * XXX Fix: If 'rq->rd == def_root_domain' perform AC against capacity
+ * of the CPU the task is running on rather rd's \Sum CPU capacity.
+ */
+static inline unsigned long dl_bw_capacity(int i)
+{
+	if (!static_branch_unlikely(&sched_asym_cpucapacity) &&
+	    capacity_orig_of(i) == SCHED_CAPACITY_SCALE) {
+		return dl_bw_cpus(i) << SCHED_CAPACITY_SHIFT;
+	} else {
+		return __dl_bw_capacity(i);
+	}
+}
 #else
 static inline struct dl_bw *dl_bw_of(int i)
 {
@@ -73,6 +129,11 @@
 {
 	return 1;
 }
+
+static inline unsigned long dl_bw_capacity(int i)
+{
+	return SCHED_CAPACITY_SCALE;
+}
 #endif
 
 static inline
@@ -153,7 +214,7 @@
 		__sub_running_bw(dl_se->dl_bw, dl_rq);
 }
 
-void dl_change_utilization(struct task_struct *p, u64 new_bw)
+static void dl_change_utilization(struct task_struct *p, u64 new_bw)
 {
 	struct rq *rq;
 
@@ -334,6 +395,8 @@
 	return dl_rq->root.rb_leftmost == &dl_se->rb_node;
 }
 
+static void init_dl_rq_bw_ratio(struct dl_rq *dl_rq);
+
 void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime)
 {
 	raw_spin_lock_init(&dl_b->dl_runtime_lock);
@@ -657,7 +720,7 @@
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 
-	WARN_ON(dl_se->dl_boosted);
+	WARN_ON(is_dl_boosted(dl_se));
 	WARN_ON(dl_time_before(rq_clock(rq), dl_se->deadline));
 
 	/*
@@ -695,21 +758,20 @@
  * could happen are, typically, a entity voluntarily trying to overcome its
  * runtime, or it just underestimated it during sched_setattr().
  */
-static void replenish_dl_entity(struct sched_dl_entity *dl_se,
-				struct sched_dl_entity *pi_se)
+static void replenish_dl_entity(struct sched_dl_entity *dl_se)
 {
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 
-	BUG_ON(pi_se->dl_runtime <= 0);
+	BUG_ON(pi_of(dl_se)->dl_runtime <= 0);
 
 	/*
 	 * This could be the case for a !-dl task that is boosted.
 	 * Just go with full inherited parameters.
 	 */
 	if (dl_se->dl_deadline == 0) {
-		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
-		dl_se->runtime = pi_se->dl_runtime;
+		dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
+		dl_se->runtime = pi_of(dl_se)->dl_runtime;
 	}
 
 	if (dl_se->dl_yielded && dl_se->runtime > 0)
@@ -722,8 +784,8 @@
 	 * arbitrary large.
 	 */
 	while (dl_se->runtime <= 0) {
-		dl_se->deadline += pi_se->dl_period;
-		dl_se->runtime += pi_se->dl_runtime;
+		dl_se->deadline += pi_of(dl_se)->dl_period;
+		dl_se->runtime += pi_of(dl_se)->dl_runtime;
 	}
 
 	/*
@@ -737,8 +799,8 @@
 	 */
 	if (dl_time_before(dl_se->deadline, rq_clock(rq))) {
 		printk_deferred_once("sched: DL replenish lagged too much\n");
-		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
-		dl_se->runtime = pi_se->dl_runtime;
+		dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
+		dl_se->runtime = pi_of(dl_se)->dl_runtime;
 	}
 
 	if (dl_se->dl_yielded)
@@ -771,8 +833,7 @@
  * task with deadline equal to period this is the same of using
  * dl_period instead of dl_deadline in the equation above.
  */
-static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
-			       struct sched_dl_entity *pi_se, u64 t)
+static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t)
 {
 	u64 left, right;
 
@@ -794,9 +855,9 @@
 	 * of anything below microseconds resolution is actually fiction
 	 * (but still we want to give the user that illusion >;).
 	 */
-	left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
+	left = (pi_of(dl_se)->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
 	right = ((dl_se->deadline - t) >> DL_SCALE) *
-		(pi_se->dl_runtime >> DL_SCALE);
+		(pi_of(dl_se)->dl_runtime >> DL_SCALE);
 
 	return dl_time_before(right, left);
 }
@@ -881,24 +942,23 @@
  * Please refer to the comments update_dl_revised_wakeup() function to find
  * more about the Revised CBS rule.
  */
-static void update_dl_entity(struct sched_dl_entity *dl_se,
-			     struct sched_dl_entity *pi_se)
+static void update_dl_entity(struct sched_dl_entity *dl_se)
 {
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 
 	if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
-	    dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) {
+	    dl_entity_overflow(dl_se, rq_clock(rq))) {
 
 		if (unlikely(!dl_is_implicit(dl_se) &&
 			     !dl_time_before(dl_se->deadline, rq_clock(rq)) &&
-			     !dl_se->dl_boosted)){
+			     !is_dl_boosted(dl_se))) {
 			update_dl_revised_wakeup(dl_se, rq);
 			return;
 		}
 
-		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
-		dl_se->runtime = pi_se->dl_runtime;
+		dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
+		dl_se->runtime = pi_of(dl_se)->dl_runtime;
 	}
 }
 
@@ -997,7 +1057,7 @@
 	 * The task might have been boosted by someone else and might be in the
 	 * boosting/deboosting path, its not throttled.
 	 */
-	if (dl_se->dl_boosted)
+	if (is_dl_boosted(dl_se))
 		goto unlock;
 
 	/*
@@ -1025,7 +1085,7 @@
 	 * but do not enqueue -- wait for our wakeup to do that.
 	 */
 	if (!task_on_rq_queued(p)) {
-		replenish_dl_entity(dl_se, dl_se);
+		replenish_dl_entity(dl_se);
 		goto unlock;
 	}
 
@@ -1096,7 +1156,7 @@
  * cannot use the runtime, and so it replenishes the task. This rule
  * works fine for implicit deadline tasks (deadline == period), and the
  * CBS was designed for implicit deadline tasks. However, a task with
- * constrained deadline (deadine < period) might be awakened after the
+ * constrained deadline (deadline < period) might be awakened after the
  * deadline, but before the next period. In this case, replenishing the
  * task would allow it to run for runtime / deadline. As in this case
  * deadline < period, CBS enables a task to run for more than the
@@ -1115,7 +1175,7 @@
 
 	if (dl_time_before(dl_se->deadline, rq_clock(rq)) &&
 	    dl_time_before(rq_clock(rq), dl_next_period(dl_se))) {
-		if (unlikely(dl_se->dl_boosted || !start_dl_timer(p)))
+		if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(p)))
 			return;
 		dl_se->dl_throttled = 1;
 		if (dl_se->runtime > 0)
@@ -1246,7 +1306,7 @@
 			dl_se->dl_overrun = 1;
 
 		__dequeue_task_dl(rq, curr, 0);
-		if (unlikely(dl_se->dl_boosted || !start_dl_timer(curr)))
+		if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(curr)))
 			enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH);
 
 		if (!is_leftmost(curr, &rq->dl))
@@ -1440,8 +1500,7 @@
 }
 
 static void
-enqueue_dl_entity(struct sched_dl_entity *dl_se,
-		  struct sched_dl_entity *pi_se, int flags)
+enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
 {
 	BUG_ON(on_dl_rq(dl_se));
 
@@ -1452,9 +1511,9 @@
 	 */
 	if (flags & ENQUEUE_WAKEUP) {
 		task_contending(dl_se, flags);
-		update_dl_entity(dl_se, pi_se);
+		update_dl_entity(dl_se);
 	} else if (flags & ENQUEUE_REPLENISH) {
-		replenish_dl_entity(dl_se, pi_se);
+		replenish_dl_entity(dl_se);
 	} else if ((flags & ENQUEUE_RESTORE) &&
 		  dl_time_before(dl_se->deadline,
 				 rq_clock(rq_of_dl_rq(dl_rq_of_se(dl_se))))) {
@@ -1471,28 +1530,40 @@
 
 static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 {
-	struct task_struct *pi_task = rt_mutex_get_top_task(p);
-	struct sched_dl_entity *pi_se = &p->dl;
-
-	/*
-	 * Use the scheduling parameters of the top pi-waiter task if:
-	 * - we have a top pi-waiter which is a SCHED_DEADLINE task AND
-	 * - our dl_boosted is set (i.e. the pi-waiter's (absolute) deadline is
-	 *   smaller than our deadline OR we are a !SCHED_DEADLINE task getting
-	 *   boosted due to a SCHED_DEADLINE pi-waiter).
-	 * Otherwise we keep our runtime and deadline.
-	 */
-	if (pi_task && dl_prio(pi_task->normal_prio) && p->dl.dl_boosted) {
-		pi_se = &pi_task->dl;
+	if (is_dl_boosted(&p->dl)) {
+		/*
+		 * Because of delays in the detection of the overrun of a
+		 * thread's runtime, it might be the case that a thread
+		 * goes to sleep in a rt mutex with negative runtime. As
+		 * a consequence, the thread will be throttled.
+		 *
+		 * While waiting for the mutex, this thread can also be
+		 * boosted via PI, resulting in a thread that is throttled
+		 * and boosted at the same time.
+		 *
+		 * In this case, the boost overrides the throttle.
+		 */
+		if (p->dl.dl_throttled) {
+			/*
+			 * The replenish timer needs to be canceled. No
+			 * problem if it fires concurrently: boosted threads
+			 * are ignored in dl_task_timer().
+			 */
+			hrtimer_try_to_cancel(&p->dl.dl_timer);
+			p->dl.dl_throttled = 0;
+		}
 	} else if (!dl_prio(p->normal_prio)) {
 		/*
-		 * Special case in which we have a !SCHED_DEADLINE task
-		 * that is going to be deboosted, but exceeds its
-		 * runtime while doing so. No point in replenishing
-		 * it, as it's going to return back to its original
-		 * scheduling class after this.
+		 * Special case in which we have a !SCHED_DEADLINE task that is going
+		 * to be deboosted, but exceeds its runtime while doing so. No point in
+		 * replenishing it, as it's going to return back to its original
+		 * scheduling class after this. If it has been throttled, we need to
+		 * clear the flag, otherwise the task may wake up as throttled after
+		 * being boosted again with no means to replenish the runtime and clear
+		 * the throttle.
 		 */
-		BUG_ON(!p->dl.dl_boosted || flags != ENQUEUE_REPLENISH);
+		p->dl.dl_throttled = 0;
+		BUG_ON(!is_dl_boosted(&p->dl) || flags != ENQUEUE_REPLENISH);
 		return;
 	}
 
@@ -1529,7 +1600,7 @@
 		return;
 	}
 
-	enqueue_dl_entity(&p->dl, pi_se, flags);
+	enqueue_dl_entity(&p->dl, flags);
 
 	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_dl_task(rq, p);
@@ -1602,6 +1673,7 @@
 select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
 {
 	struct task_struct *curr;
+	bool select_rq;
 	struct rq *rq;
 
 	if (sd_flag != SD_BALANCE_WAKE)
@@ -1621,10 +1693,19 @@
 	 * other hand, if it has a shorter deadline, we
 	 * try to make it stay here, it might be important.
 	 */
-	if (unlikely(dl_task(curr)) &&
-	    (curr->nr_cpus_allowed < 2 ||
-	     !dl_entity_preempt(&p->dl, &curr->dl)) &&
-	    (p->nr_cpus_allowed > 1)) {
+	select_rq = unlikely(dl_task(curr)) &&
+		    (curr->nr_cpus_allowed < 2 ||
+		     !dl_entity_preempt(&p->dl, &curr->dl)) &&
+		    p->nr_cpus_allowed > 1;
+
+	/*
+	 * Take the capacity of the CPU into account to
+	 * ensure it fits the requirement of the task.
+	 */
+	if (static_branch_unlikely(&sched_asym_cpucapacity))
+		select_rq |= !dl_task_fits_capacity(p, cpu);
+
+	if (select_rq) {
 		int target = find_later_rq(p);
 
 		if (target != -1 &&
@@ -1774,15 +1855,12 @@
 	return rb_entry(left, struct sched_dl_entity, rb_node);
 }
 
-static struct task_struct *
-pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+static struct task_struct *pick_next_task_dl(struct rq *rq)
 {
 	struct sched_dl_entity *dl_se;
 	struct dl_rq *dl_rq = &rq->dl;
 	struct task_struct *p;
 
-	WARN_ON_ONCE(prev || rf);
-
 	if (!sched_dl_runnable(rq))
 		return NULL;
 
@@ -2434,8 +2512,8 @@
 	}
 }
 
-const struct sched_class dl_sched_class = {
-	.next			= &rt_sched_class,
+const struct sched_class dl_sched_class
+	__section("__dl_sched_class") = {
 	.enqueue_task		= enqueue_task_dl,
 	.dequeue_task		= dequeue_task_dl,
 	.yield_task		= yield_task_dl,
@@ -2503,7 +2581,7 @@
 	return ret;
 }
 
-void init_dl_rq_bw_ratio(struct dl_rq *dl_rq)
+static void init_dl_rq_bw_ratio(struct dl_rq *dl_rq)
 {
 	if (global_rt_runtime() == RUNTIME_INF) {
 		dl_rq->bw_ratio = 1 << RATIO_SHIFT;
@@ -2556,11 +2634,12 @@
 int sched_dl_overflow(struct task_struct *p, int policy,
 		      const struct sched_attr *attr)
 {
-	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
 	u64 period = attr->sched_period ?: attr->sched_deadline;
 	u64 runtime = attr->sched_runtime;
 	u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
-	int cpus, err = -1;
+	int cpus, err = -1, cpu = task_cpu(p);
+	struct dl_bw *dl_b = dl_bw_of(cpu);
+	unsigned long cap;
 
 	if (attr->sched_flags & SCHED_FLAG_SUGOV)
 		return 0;
@@ -2575,15 +2654,17 @@
 	 * allocated bandwidth of the container.
 	 */
 	raw_spin_lock(&dl_b->lock);
-	cpus = dl_bw_cpus(task_cpu(p));
+	cpus = dl_bw_cpus(cpu);
+	cap = dl_bw_capacity(cpu);
+
 	if (dl_policy(policy) && !task_has_dl_policy(p) &&
-	    !__dl_overflow(dl_b, cpus, 0, new_bw)) {
+	    !__dl_overflow(dl_b, cap, 0, new_bw)) {
 		if (hrtimer_active(&p->dl.inactive_timer))
 			__dl_sub(dl_b, p->dl.dl_bw, cpus);
 		__dl_add(dl_b, new_bw, cpus);
 		err = 0;
 	} else if (dl_policy(policy) && task_has_dl_policy(p) &&
-		   !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) {
+		   !__dl_overflow(dl_b, cap, p->dl.dl_bw, new_bw)) {
 		/*
 		 * XXX this is slightly incorrect: when the task
 		 * utilization decreases, we should delay the total
@@ -2641,6 +2722,14 @@
 }
 
 /*
+ * Default limits for DL period; on the top end we guard against small util
+ * tasks still getting rediculous long effective runtimes, on the bottom end we
+ * guard against timer DoS.
+ */
+unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */
+unsigned int sysctl_sched_dl_period_min = 100;     /* 100 us */
+
+/*
  * This function validates the new parameters of a -deadline task.
  * We ask for the deadline not being zero, and greater or equal
  * than the runtime, as well as the period of being zero or
@@ -2652,6 +2741,8 @@
  */
 bool __checkparam_dl(const struct sched_attr *attr)
 {
+	u64 period, max, min;
+
 	/* special dl tasks don't actually use any parameter */
 	if (attr->sched_flags & SCHED_FLAG_SUGOV)
 		return true;
@@ -2675,12 +2766,21 @@
 	    attr->sched_period & (1ULL << 63))
 		return false;
 
+	period = attr->sched_period;
+	if (!period)
+		period = attr->sched_deadline;
+
 	/* runtime <= deadline <= period (if period != 0) */
-	if ((attr->sched_period != 0 &&
-	     attr->sched_period < attr->sched_deadline) ||
+	if (period < attr->sched_deadline ||
 	    attr->sched_deadline < attr->sched_runtime)
 		return false;
 
+	max = (u64)READ_ONCE(sysctl_sched_dl_period_max) * NSEC_PER_USEC;
+	min = (u64)READ_ONCE(sysctl_sched_dl_period_min) * NSEC_PER_USEC;
+
+	if (period < min || period > max)
+		return false;
+
 	return true;
 }
 
@@ -2698,11 +2798,14 @@
 	dl_se->dl_bw			= 0;
 	dl_se->dl_density		= 0;
 
-	dl_se->dl_boosted		= 0;
 	dl_se->dl_throttled		= 0;
 	dl_se->dl_yielded		= 0;
 	dl_se->dl_non_contending	= 0;
 	dl_se->dl_overrun		= 0;
+
+#ifdef CONFIG_RT_MUTEXES
+	dl_se->pi_se			= dl_se;
+#endif
 }
 
 bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
@@ -2721,19 +2824,19 @@
 #ifdef CONFIG_SMP
 int dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed)
 {
+	unsigned long flags, cap;
 	unsigned int dest_cpu;
 	struct dl_bw *dl_b;
 	bool overflow;
-	int cpus, ret;
-	unsigned long flags;
+	int ret;
 
 	dest_cpu = cpumask_any_and(cpu_active_mask, cs_cpus_allowed);
 
 	rcu_read_lock_sched();
 	dl_b = dl_bw_of(dest_cpu);
 	raw_spin_lock_irqsave(&dl_b->lock, flags);
-	cpus = dl_bw_cpus(dest_cpu);
-	overflow = __dl_overflow(dl_b, cpus, 0, p->dl.dl_bw);
+	cap = dl_bw_capacity(dest_cpu);
+	overflow = __dl_overflow(dl_b, cap, 0, p->dl.dl_bw);
 	if (overflow) {
 		ret = -EBUSY;
 	} else {
@@ -2743,6 +2846,8 @@
 		 * We will free resources in the source root_domain
 		 * later on (see set_cpus_allowed_dl()).
 		 */
+		int cpus = dl_bw_cpus(dest_cpu);
+
 		__dl_add(dl_b, p->dl.dl_bw, cpus);
 		ret = 0;
 	}
@@ -2775,16 +2880,15 @@
 
 bool dl_cpu_busy(unsigned int cpu)
 {
-	unsigned long flags;
+	unsigned long flags, cap;
 	struct dl_bw *dl_b;
 	bool overflow;
-	int cpus;
 
 	rcu_read_lock_sched();
 	dl_b = dl_bw_of(cpu);
 	raw_spin_lock_irqsave(&dl_b->lock, flags);
-	cpus = dl_bw_cpus(cpu);
-	overflow = __dl_overflow(dl_b, cpus, 0, 0);
+	cap = dl_bw_capacity(cpu);
+	overflow = __dl_overflow(dl_b, cap, 0, 0);
 	raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 	rcu_read_unlock_sched();
 
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index faada71..70a5782 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -243,6 +243,60 @@
 	entry->proc_handler = proc_handler;
 }
 
+static int sd_ctl_doflags(struct ctl_table *table, int write,
+			  void *buffer, size_t *lenp, loff_t *ppos)
+{
+	unsigned long flags = *(unsigned long *)table->data;
+	size_t data_size = 0;
+	size_t len = 0;
+	char *tmp, *buf;
+	int idx;
+
+	if (write)
+		return 0;
+
+	for_each_set_bit(idx, &flags, __SD_FLAG_CNT) {
+		char *name = sd_flag_debug[idx].name;
+
+		/* Name plus whitespace */
+		data_size += strlen(name) + 1;
+	}
+
+	if (*ppos > data_size) {
+		*lenp = 0;
+		return 0;
+	}
+
+	buf = kcalloc(data_size + 1, sizeof(*buf), GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	for_each_set_bit(idx, &flags, __SD_FLAG_CNT) {
+		char *name = sd_flag_debug[idx].name;
+
+		len += snprintf(buf + len, strlen(name) + 2, "%s ", name);
+	}
+
+	tmp = buf + *ppos;
+	len -= *ppos;
+
+	if (len > *lenp)
+		len = *lenp;
+	if (len)
+		memcpy(buffer, tmp, len);
+	if (len < *lenp) {
+		((char *)buffer)[len] = '\n';
+		len++;
+	}
+
+	*lenp = len;
+	*ppos += len;
+
+	kfree(buf);
+
+	return 0;
+}
+
 static struct ctl_table *
 sd_alloc_ctl_domain_table(struct sched_domain *sd)
 {
@@ -256,7 +310,7 @@
 	set_table_entry(&table[2], "busy_factor",	  &sd->busy_factor,	    sizeof(int),  0644, proc_dointvec_minmax);
 	set_table_entry(&table[3], "imbalance_pct",	  &sd->imbalance_pct,	    sizeof(int),  0644, proc_dointvec_minmax);
 	set_table_entry(&table[4], "cache_nice_tries",	  &sd->cache_nice_tries,    sizeof(int),  0644, proc_dointvec_minmax);
-	set_table_entry(&table[5], "flags",		  &sd->flags,		    sizeof(int),  0444, proc_dointvec_minmax);
+	set_table_entry(&table[5], "flags",		  &sd->flags,		    sizeof(int),  0444, sd_ctl_doflags);
 	set_table_entry(&table[6], "max_newidle_lb_cost", &sd->max_newidle_lb_cost, sizeof(long), 0644, proc_doulongvec_minmax);
 	set_table_entry(&table[7], "name",		  sd->name,	       CORENAME_MAX_SIZE, 0444, proc_dostring);
 	/* &table[8] is terminator */
@@ -400,11 +454,10 @@
 	}
 
 	P(se->load.weight);
-	P(se->runnable_weight);
 #ifdef CONFIG_SMP
 	P(se->avg.load_avg);
 	P(se->avg.util_avg);
-	P(se->avg.runnable_load_avg);
+	P(se->avg.runnable_avg);
 #endif
 
 #undef PN_SCHEDSTAT
@@ -457,7 +510,7 @@
 	else
 		SEQ_printf(m, " %c", task_state_to_char(p));
 
-	SEQ_printf(m, "%15s %5d %9Ld.%06ld %9Ld %5d ",
+	SEQ_printf(m, " %15s %5d %9Ld.%06ld %9Ld %5d ",
 		p->comm, task_pid_nr(p),
 		SPLIT_NS(p->se.vruntime),
 		(long long)(p->nvcsw + p->nivcsw),
@@ -484,10 +537,10 @@
 
 	SEQ_printf(m, "\n");
 	SEQ_printf(m, "runnable tasks:\n");
-	SEQ_printf(m, " S           task   PID         tree-key  switches  prio"
+	SEQ_printf(m, " S            task   PID         tree-key  switches  prio"
 		   "     wait-time             sum-exec        sum-sleep\n");
 	SEQ_printf(m, "-------------------------------------------------------"
-		   "----------------------------------------------------\n");
+		   "------------------------------------------------------\n");
 
 	rcu_read_lock();
 	for_each_process_thread(g, p) {
@@ -543,11 +596,10 @@
 	SEQ_printf(m, "  .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
 	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
 #ifdef CONFIG_SMP
-	SEQ_printf(m, "  .%-30s: %ld\n", "runnable_weight", cfs_rq->runnable_weight);
 	SEQ_printf(m, "  .%-30s: %lu\n", "load_avg",
 			cfs_rq->avg.load_avg);
-	SEQ_printf(m, "  .%-30s: %lu\n", "runnable_load_avg",
-			cfs_rq->avg.runnable_load_avg);
+	SEQ_printf(m, "  .%-30s: %lu\n", "runnable_avg",
+			cfs_rq->avg.runnable_avg);
 	SEQ_printf(m, "  .%-30s: %lu\n", "util_avg",
 			cfs_rq->avg.util_avg);
 	SEQ_printf(m, "  .%-30s: %u\n", "util_est_enqueued",
@@ -556,8 +608,8 @@
 			cfs_rq->removed.load_avg);
 	SEQ_printf(m, "  .%-30s: %ld\n", "removed.util_avg",
 			cfs_rq->removed.util_avg);
-	SEQ_printf(m, "  .%-30s: %ld\n", "removed.runnable_sum",
-			cfs_rq->removed.runnable_sum);
+	SEQ_printf(m, "  .%-30s: %ld\n", "removed.runnable_avg",
+			cfs_rq->removed.runnable_avg);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	SEQ_printf(m, "  .%-30s: %lu\n", "tg_load_avg_contrib",
 			cfs_rq->tg_load_avg_contrib);
@@ -658,7 +710,6 @@
 
 	P(nr_running);
 	P(nr_switches);
-	P(nr_load_updates);
 	P(nr_uninterruptible);
 	PN(next_balance);
 	SEQ_printf(m, "  .%-30s: %ld\n", "curr->pid", (long)(task_pid_nr(rq->curr)));
@@ -767,9 +818,16 @@
 	int cpu;
 
 	sched_debug_header(NULL);
-	for_each_online_cpu(cpu)
+	for_each_online_cpu(cpu) {
+		/*
+		 * Need to reset softlockup watchdogs on all CPUs, because
+		 * another CPU might be blocked waiting for us to process
+		 * an IPI or stop_machine.
+		 */
+		touch_nmi_watchdog();
+		touch_all_softlockup_watchdogs();
 		print_cpu(NULL, cpu);
-
+	}
 }
 
 /*
@@ -827,10 +885,13 @@
 
 __initcall(init_sched_debug_procfs);
 
-#define __P(F)	SEQ_printf(m, "%-45s:%21Ld\n",	     #F, (long long)F)
-#define   P(F)	SEQ_printf(m, "%-45s:%21Ld\n",	     #F, (long long)p->F)
-#define __PN(F)	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F))
-#define   PN(F)	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
+#define __PS(S, F) SEQ_printf(m, "%-45s:%21Ld\n", S, (long long)(F))
+#define __P(F) __PS(#F, F)
+#define   P(F) __PS(#F, p->F)
+#define   PM(F, M) __PS(#F, p->F & (M))
+#define __PSN(S, F) SEQ_printf(m, "%-45s:%14Ld.%06ld\n", S, SPLIT_NS((long long)(F)))
+#define __PN(F) __PSN(#F, F)
+#define   PN(F) __PSN(#F, p->F)
 
 
 #ifdef CONFIG_NUMA_BALANCING
@@ -879,18 +940,9 @@
 	SEQ_printf(m,
 		"---------------------------------------------------------"
 		"----------\n");
-#define __P(F) \
-	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F)
-#define P(F) \
-	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F)
-#define P_SCHEDSTAT(F) \
-	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)schedstat_val(p->F))
-#define __PN(F) \
-	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F))
-#define PN(F) \
-	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
-#define PN_SCHEDSTAT(F) \
-	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)schedstat_val(p->F)))
+
+#define P_SCHEDSTAT(F)  __PS(#F, schedstat_val(p->F))
+#define PN_SCHEDSTAT(F) __PSN(#F, schedstat_val(p->F))
 
 	PN(se.exec_start);
 	PN(se.vruntime);
@@ -950,23 +1002,26 @@
 	}
 
 	__P(nr_switches);
-	SEQ_printf(m, "%-45s:%21Ld\n",
-		   "nr_voluntary_switches", (long long)p->nvcsw);
-	SEQ_printf(m, "%-45s:%21Ld\n",
-		   "nr_involuntary_switches", (long long)p->nivcsw);
+	__PS("nr_voluntary_switches", p->nvcsw);
+	__PS("nr_involuntary_switches", p->nivcsw);
 
 	P(se.load.weight);
-	P(se.runnable_weight);
 #ifdef CONFIG_SMP
 	P(se.avg.load_sum);
-	P(se.avg.runnable_load_sum);
+	P(se.avg.runnable_sum);
 	P(se.avg.util_sum);
 	P(se.avg.load_avg);
-	P(se.avg.runnable_load_avg);
+	P(se.avg.runnable_avg);
 	P(se.avg.util_avg);
 	P(se.avg.last_update_time);
 	P(se.avg.util_est.ewma);
-	P(se.avg.util_est.enqueued);
+	PM(se.avg.util_est.enqueued, ~UTIL_AVG_UNCHANGED);
+#endif
+#ifdef CONFIG_UCLAMP_TASK
+	__PS("uclamp.min", p->uclamp_req[UCLAMP_MIN].value);
+	__PS("uclamp.max", p->uclamp_req[UCLAMP_MAX].value);
+	__PS("effective uclamp.min", uclamp_eff_value(p, UCLAMP_MIN));
+	__PS("effective uclamp.max", uclamp_eff_value(p, UCLAMP_MAX));
 #endif
 	P(policy);
 	P(prio);
@@ -975,11 +1030,7 @@
 		P(dl.deadline);
 	}
 #undef PN_SCHEDSTAT
-#undef PN
-#undef __PN
 #undef P_SCHEDSTAT
-#undef P
-#undef __P
 
 	{
 		unsigned int this_cpu = raw_smp_processor_id();
@@ -987,8 +1038,7 @@
 
 		t0 = cpu_clock(this_cpu);
 		t1 = cpu_clock(this_cpu);
-		SEQ_printf(m, "%-45s:%21Ld\n",
-			   "clock-delta", (long long)(t1-t0));
+		__PS("clock-delta", t1-t0);
 	}
 
 	sched_show_numa(p, m);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 87d9fad..acd9833 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -22,8 +22,6 @@
  */
 #include "sched.h"
 
-#include <trace/events/sched.h>
-
 /*
  * Targeted preemption latency for CPU-bound tasks:
  *
@@ -86,6 +84,19 @@
 
 const_debug unsigned int sysctl_sched_migration_cost	= 500000UL;
 
+int sched_thermal_decay_shift;
+static int __init setup_sched_thermal_decay_shift(char *str)
+{
+	int _shift = 0;
+
+	if (kstrtoint(str, 0, &_shift))
+		pr_warn("Unable to set scheduler thermal pressure decay shift parameter\n");
+
+	sched_thermal_decay_shift = clamp(_shift, 0, 10);
+	return 1;
+}
+__setup("sched_thermal_decay_shift=", setup_sched_thermal_decay_shift);
+
 #ifdef CONFIG_SMP
 /*
  * For asym packing, by default the lower numbered CPU has higher priority.
@@ -178,7 +189,7 @@
 #undef SET_SYSCTL
 }
 
-void sched_init_granularity(void)
+void __init sched_init_granularity(void)
 {
 	update_sysctl();
 }
@@ -229,8 +240,7 @@
 		}
 	}
 
-	/* hint to use a 32x32->64 mul */
-	fact = (u64)(u32)fact * lw->inv_weight;
+	fact = mul_u32_u32(fact, lw->inv_weight);
 
 	while (fact >> 32) {
 		fact >>= 1;
@@ -633,8 +643,7 @@
  */
 
 int sched_proc_update_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos)
+		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	unsigned int factor = get_update_sysctl_factor();
@@ -691,7 +700,13 @@
  */
 static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	u64 slice = __sched_period(cfs_rq->nr_running + !se->on_rq);
+	unsigned int nr_running = cfs_rq->nr_running;
+	u64 slice;
+
+	if (sched_feat(ALT_PERIOD))
+		nr_running = rq_of(cfs_rq)->cfs.h_nr_running;
+
+	slice = __sched_period(nr_running + !se->on_rq);
 
 	for_each_sched_entity(se) {
 		struct load_weight *load;
@@ -708,6 +723,10 @@
 		}
 		slice = __calc_delta(slice, se->load.weight, load);
 	}
+
+	if (sched_feat(BASE_SLICE))
+		slice = max(slice, (u64)sysctl_sched_min_granularity);
+
 	return slice;
 }
 
@@ -742,9 +761,7 @@
 	 * nothing has been attached to the task group yet.
 	 */
 	if (entity_is_task(se))
-		sa->runnable_load_avg = sa->load_avg = scale_load_down(se->load.weight);
-
-	se->runnable_weight = se->load.weight;
+		sa->load_avg = scale_load_down(se->load.weight);
 
 	/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
 }
@@ -797,12 +814,14 @@
 		}
 	}
 
+	sa->runnable_avg = sa->util_avg;
+
 	if (p->sched_class != &fair_sched_class) {
 		/*
 		 * For !fair tasks do:
 		 *
 		update_cfs_rq_load_avg(now, cfs_rq);
-		attach_entity_load_avg(cfs_rq, se, 0);
+		attach_entity_load_avg(cfs_rq, se);
 		switched_from_fair(rq, p);
 		 *
 		 * such that the next switched_to_fair() has the
@@ -822,7 +841,7 @@
 void post_init_entity_util_avg(struct task_struct *p)
 {
 }
-static void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
+static void update_tg_load_avg(struct cfs_rq *cfs_rq)
 {
 }
 #endif /* CONFIG_SMP */
@@ -1082,7 +1101,7 @@
 	 * more by CPU use than by memory faults.
 	 */
 	unsigned long *faults_cpu;
-	unsigned long faults[0];
+	unsigned long faults[];
 };
 
 /*
@@ -1474,31 +1493,52 @@
 	       group_faults_cpu(ng, src_nid) * group_faults(p, dst_nid) * 4;
 }
 
-static unsigned long cpu_runnable_load(struct rq *rq);
+/*
+ * 'numa_type' describes the node at the moment of load balancing.
+ */
+enum numa_type {
+	/* The node has spare capacity that can be used to run more tasks.  */
+	node_has_spare = 0,
+	/*
+	 * The node is fully used and the tasks don't compete for more CPU
+	 * cycles. Nevertheless, some tasks might wait before running.
+	 */
+	node_fully_busy,
+	/*
+	 * The node is overloaded and can't provide expected CPU cycles to all
+	 * tasks.
+	 */
+	node_overloaded
+};
 
 /* Cached statistics for all CPUs within a node */
 struct numa_stats {
 	unsigned long load;
-
+	unsigned long runnable;
+	unsigned long util;
 	/* Total compute capacity of CPUs on a node */
 	unsigned long compute_capacity;
+	unsigned int nr_running;
+	unsigned int weight;
+	enum numa_type node_type;
+	int idle_cpu;
 };
 
-/*
- * XXX borrowed from update_sg_lb_stats
- */
-static void update_numa_stats(struct numa_stats *ns, int nid)
+static inline bool is_core_idle(int cpu)
 {
-	int cpu;
+#ifdef CONFIG_SCHED_SMT
+	int sibling;
 
-	memset(ns, 0, sizeof(*ns));
-	for_each_cpu(cpu, cpumask_of_node(nid)) {
-		struct rq *rq = cpu_rq(cpu);
+	for_each_cpu(sibling, cpu_smt_mask(cpu)) {
+		if (cpu == sibling)
+			continue;
 
-		ns->load += cpu_runnable_load(rq);
-		ns->compute_capacity += capacity_of(cpu);
+		if (!idle_cpu(sibling))
+			return false;
 	}
+#endif
 
+	return true;
 }
 
 struct task_numa_env {
@@ -1517,20 +1557,132 @@
 	int best_cpu;
 };
 
+static unsigned long cpu_load(struct rq *rq);
+static unsigned long cpu_runnable(struct rq *rq);
+static unsigned long cpu_util(int cpu);
+static inline long adjust_numa_imbalance(int imbalance, int nr_running);
+
+static inline enum
+numa_type numa_classify(unsigned int imbalance_pct,
+			 struct numa_stats *ns)
+{
+	if ((ns->nr_running > ns->weight) &&
+	    (((ns->compute_capacity * 100) < (ns->util * imbalance_pct)) ||
+	     ((ns->compute_capacity * imbalance_pct) < (ns->runnable * 100))))
+		return node_overloaded;
+
+	if ((ns->nr_running < ns->weight) ||
+	    (((ns->compute_capacity * 100) > (ns->util * imbalance_pct)) &&
+	     ((ns->compute_capacity * imbalance_pct) > (ns->runnable * 100))))
+		return node_has_spare;
+
+	return node_fully_busy;
+}
+
+#ifdef CONFIG_SCHED_SMT
+/* Forward declarations of select_idle_sibling helpers */
+static inline bool test_idle_cores(int cpu, bool def);
+static inline int numa_idle_core(int idle_core, int cpu)
+{
+	if (!static_branch_likely(&sched_smt_present) ||
+	    idle_core >= 0 || !test_idle_cores(cpu, false))
+		return idle_core;
+
+	/*
+	 * Prefer cores instead of packing HT siblings
+	 * and triggering future load balancing.
+	 */
+	if (is_core_idle(cpu))
+		idle_core = cpu;
+
+	return idle_core;
+}
+#else
+static inline int numa_idle_core(int idle_core, int cpu)
+{
+	return idle_core;
+}
+#endif
+
+/*
+ * Gather all necessary information to make NUMA balancing placement
+ * decisions that are compatible with standard load balancer. This
+ * borrows code and logic from update_sg_lb_stats but sharing a
+ * common implementation is impractical.
+ */
+static void update_numa_stats(struct task_numa_env *env,
+			      struct numa_stats *ns, int nid,
+			      bool find_idle)
+{
+	int cpu, idle_core = -1;
+
+	memset(ns, 0, sizeof(*ns));
+	ns->idle_cpu = -1;
+
+	rcu_read_lock();
+	for_each_cpu(cpu, cpumask_of_node(nid)) {
+		struct rq *rq = cpu_rq(cpu);
+
+		ns->load += cpu_load(rq);
+		ns->runnable += cpu_runnable(rq);
+		ns->util += cpu_util(cpu);
+		ns->nr_running += rq->cfs.h_nr_running;
+		ns->compute_capacity += capacity_of(cpu);
+
+		if (find_idle && !rq->nr_running && idle_cpu(cpu)) {
+			if (READ_ONCE(rq->numa_migrate_on) ||
+			    !cpumask_test_cpu(cpu, env->p->cpus_ptr))
+				continue;
+
+			if (ns->idle_cpu == -1)
+				ns->idle_cpu = cpu;
+
+			idle_core = numa_idle_core(idle_core, cpu);
+		}
+	}
+	rcu_read_unlock();
+
+	ns->weight = cpumask_weight(cpumask_of_node(nid));
+
+	ns->node_type = numa_classify(env->imbalance_pct, ns);
+
+	if (idle_core >= 0)
+		ns->idle_cpu = idle_core;
+}
+
 static void task_numa_assign(struct task_numa_env *env,
 			     struct task_struct *p, long imp)
 {
 	struct rq *rq = cpu_rq(env->dst_cpu);
 
-	/* Bail out if run-queue part of active NUMA balance. */
-	if (xchg(&rq->numa_migrate_on, 1))
-		return;
+	/* Check if run-queue part of active NUMA balance. */
+	if (env->best_cpu != env->dst_cpu && xchg(&rq->numa_migrate_on, 1)) {
+		int cpu;
+		int start = env->dst_cpu;
 
+		/* Find alternative idle CPU. */
+		for_each_cpu_wrap(cpu, cpumask_of_node(env->dst_nid), start) {
+			if (cpu == env->best_cpu || !idle_cpu(cpu) ||
+			    !cpumask_test_cpu(cpu, env->p->cpus_ptr)) {
+				continue;
+			}
+
+			env->dst_cpu = cpu;
+			rq = cpu_rq(env->dst_cpu);
+			if (!xchg(&rq->numa_migrate_on, 1))
+				goto assign;
+		}
+
+		/* Failed to find an alternative idle CPU */
+		return;
+	}
+
+assign:
 	/*
 	 * Clear previous best_cpu/rq numa-migrate flag, since task now
 	 * found a better CPU to move/swap.
 	 */
-	if (env->best_cpu != -1) {
+	if (env->best_cpu != -1 && env->best_cpu != env->dst_cpu) {
 		rq = cpu_rq(env->best_cpu);
 		WRITE_ONCE(rq->numa_migrate_on, 0);
 	}
@@ -1586,7 +1738,7 @@
  * into account that it might be best if task running on the dst_cpu should
  * be exchanged with the source task
  */
-static void task_numa_compare(struct task_numa_env *env,
+static bool task_numa_compare(struct task_numa_env *env,
 			      long taskimp, long groupimp, bool maymove)
 {
 	struct numa_group *cur_ng, *p_ng = deref_curr_numa_group(env->p);
@@ -1597,9 +1749,10 @@
 	int dist = env->dist;
 	long moveimp = imp;
 	long load;
+	bool stopsearch = false;
 
 	if (READ_ONCE(dst_rq->numa_migrate_on))
-		return;
+		return false;
 
 	rcu_read_lock();
 	cur = rcu_dereference(dst_rq->curr);
@@ -1610,8 +1763,10 @@
 	 * Because we have preemption enabled we can get migrated around and
 	 * end try selecting ourselves (current == env->p) as a swap candidate.
 	 */
-	if (cur == env->p)
+	if (cur == env->p) {
+		stopsearch = true;
 		goto unlock;
+	}
 
 	if (!cur) {
 		if (maymove && moveimp >= env->best_imp)
@@ -1620,18 +1775,27 @@
 			goto unlock;
 	}
 
+	/* Skip this swap candidate if cannot move to the source cpu. */
+	if (!cpumask_test_cpu(env->src_cpu, cur->cpus_ptr))
+		goto unlock;
+
+	/*
+	 * Skip this swap candidate if it is not moving to its preferred
+	 * node and the best task is.
+	 */
+	if (env->best_task &&
+	    env->best_task->numa_preferred_nid == env->src_nid &&
+	    cur->numa_preferred_nid != env->src_nid) {
+		goto unlock;
+	}
+
 	/*
 	 * "imp" is the fault differential for the source task between the
 	 * source and destination node. Calculate the total differential for
 	 * the source task and potential destination task. The more negative
 	 * the value is, the more remote accesses that would be expected to
 	 * be incurred if the tasks were swapped.
-	 */
-	/* Skip this swap candidate if cannot move to the source cpu */
-	if (!cpumask_test_cpu(env->src_cpu, cur->cpus_ptr))
-		goto unlock;
-
-	/*
+	 *
 	 * If dst and source tasks are in the same NUMA group, or not
 	 * in any group then look only at task weights.
 	 */
@@ -1658,6 +1822,19 @@
 			       task_weight(cur, env->dst_nid, dist);
 	}
 
+	/* Discourage picking a task already on its preferred node */
+	if (cur->numa_preferred_nid == env->dst_nid)
+		imp -= imp / 16;
+
+	/*
+	 * Encourage picking a task that moves to its preferred node.
+	 * This potentially makes imp larger than it's maximum of
+	 * 1998 (see SMALLIMP and task_weight for why) but in this
+	 * case, it does not matter.
+	 */
+	if (cur->numa_preferred_nid == env->src_nid)
+		imp += imp / 8;
+
 	if (maymove && moveimp > imp && moveimp > env->best_imp) {
 		imp = moveimp;
 		cur = NULL;
@@ -1665,6 +1842,15 @@
 	}
 
 	/*
+	 * Prefer swapping with a task moving to its preferred node over a
+	 * task that is not.
+	 */
+	if (env->best_task && cur->numa_preferred_nid == env->src_nid &&
+	    env->best_task->numa_preferred_nid != env->src_nid) {
+		goto assign;
+	}
+
+	/*
 	 * If the NUMA importance is less than SMALLIMP,
 	 * task migration might only result in ping pong
 	 * of tasks and also hurt performance due to cache
@@ -1687,42 +1873,95 @@
 		goto unlock;
 
 assign:
-	/*
-	 * One idle CPU per node is evaluated for a task numa move.
-	 * Call select_idle_sibling to maybe find a better one.
-	 */
+	/* Evaluate an idle CPU for a task numa move. */
 	if (!cur) {
+		int cpu = env->dst_stats.idle_cpu;
+
+		/* Nothing cached so current CPU went idle since the search. */
+		if (cpu < 0)
+			cpu = env->dst_cpu;
+
 		/*
-		 * select_idle_siblings() uses an per-CPU cpumask that
-		 * can be used from IRQ context.
+		 * If the CPU is no longer truly idle and the previous best CPU
+		 * is, keep using it.
 		 */
-		local_irq_disable();
-		env->dst_cpu = select_idle_sibling(env->p, env->src_cpu,
-						   env->dst_cpu);
-		local_irq_enable();
+		if (!idle_cpu(cpu) && env->best_cpu >= 0 &&
+		    idle_cpu(env->best_cpu)) {
+			cpu = env->best_cpu;
+		}
+
+		env->dst_cpu = cpu;
 	}
 
 	task_numa_assign(env, cur, imp);
+
+	/*
+	 * If a move to idle is allowed because there is capacity or load
+	 * balance improves then stop the search. While a better swap
+	 * candidate may exist, a search is not free.
+	 */
+	if (maymove && !cur && env->best_cpu >= 0 && idle_cpu(env->best_cpu))
+		stopsearch = true;
+
+	/*
+	 * If a swap candidate must be identified and the current best task
+	 * moves its preferred node then stop the search.
+	 */
+	if (!maymove && env->best_task &&
+	    env->best_task->numa_preferred_nid == env->src_nid) {
+		stopsearch = true;
+	}
 unlock:
 	rcu_read_unlock();
+
+	return stopsearch;
 }
 
 static void task_numa_find_cpu(struct task_numa_env *env,
 				long taskimp, long groupimp)
 {
-	long src_load, dst_load, load;
 	bool maymove = false;
 	int cpu;
 
-	load = task_h_load(env->p);
-	dst_load = env->dst_stats.load + load;
-	src_load = env->src_stats.load - load;
-
 	/*
-	 * If the improvement from just moving env->p direction is better
-	 * than swapping tasks around, check if a move is possible.
+	 * If dst node has spare capacity, then check if there is an
+	 * imbalance that would be overruled by the load balancer.
 	 */
-	maymove = !load_too_imbalanced(src_load, dst_load, env);
+	if (env->dst_stats.node_type == node_has_spare) {
+		unsigned int imbalance;
+		int src_running, dst_running;
+
+		/*
+		 * Would movement cause an imbalance? Note that if src has
+		 * more running tasks that the imbalance is ignored as the
+		 * move improves the imbalance from the perspective of the
+		 * CPU load balancer.
+		 * */
+		src_running = env->src_stats.nr_running - 1;
+		dst_running = env->dst_stats.nr_running + 1;
+		imbalance = max(0, dst_running - src_running);
+		imbalance = adjust_numa_imbalance(imbalance, dst_running);
+
+		/* Use idle CPU if there is no imbalance */
+		if (!imbalance) {
+			maymove = true;
+			if (env->dst_stats.idle_cpu >= 0) {
+				env->dst_cpu = env->dst_stats.idle_cpu;
+				task_numa_assign(env, NULL, 0);
+				return;
+			}
+		}
+	} else {
+		long src_load, dst_load, load;
+		/*
+		 * If the improvement from just moving env->p direction is better
+		 * than swapping tasks around, check if a move is possible.
+		 */
+		load = task_h_load(env->p);
+		dst_load = env->dst_stats.load + load;
+		src_load = env->src_stats.load - load;
+		maymove = !load_too_imbalanced(src_load, dst_load, env);
+	}
 
 	for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) {
 		/* Skip this CPU if the source task cannot migrate */
@@ -1730,7 +1969,8 @@
 			continue;
 
 		env->dst_cpu = cpu;
-		task_numa_compare(env, taskimp, groupimp, maymove);
+		if (task_numa_compare(env, taskimp, groupimp, maymove))
+			break;
 	}
 }
 
@@ -1784,10 +2024,10 @@
 	dist = env.dist = node_distance(env.src_nid, env.dst_nid);
 	taskweight = task_weight(p, env.src_nid, dist);
 	groupweight = group_weight(p, env.src_nid, dist);
-	update_numa_stats(&env.src_stats, env.src_nid);
+	update_numa_stats(&env, &env.src_stats, env.src_nid, false);
 	taskimp = task_weight(p, env.dst_nid, dist) - taskweight;
 	groupimp = group_weight(p, env.dst_nid, dist) - groupweight;
-	update_numa_stats(&env.dst_stats, env.dst_nid);
+	update_numa_stats(&env, &env.dst_stats, env.dst_nid, true);
 
 	/* Try to find a spot on the preferred nid. */
 	task_numa_find_cpu(&env, taskimp, groupimp);
@@ -1820,7 +2060,7 @@
 
 			env.dist = dist;
 			env.dst_nid = nid;
-			update_numa_stats(&env.dst_stats, env.dst_nid);
+			update_numa_stats(&env, &env.dst_stats, env.dst_nid, true);
 			task_numa_find_cpu(&env, taskimp, groupimp);
 		}
 	}
@@ -1844,15 +2084,17 @@
 	}
 
 	/* No better CPU than the current one was found. */
-	if (env.best_cpu == -1)
+	if (env.best_cpu == -1) {
+		trace_sched_stick_numa(p, env.src_cpu, NULL, -1);
 		return -EAGAIN;
+	}
 
 	best_rq = cpu_rq(env.best_cpu);
 	if (env.best_task == NULL) {
 		ret = migrate_task_to(p, env.best_cpu);
 		WRITE_ONCE(best_rq->numa_migrate_on, 0);
 		if (ret != 0)
-			trace_sched_stick_numa(p, env.src_cpu, env.best_cpu);
+			trace_sched_stick_numa(p, env.src_cpu, NULL, env.best_cpu);
 		return ret;
 	}
 
@@ -1860,7 +2102,7 @@
 	WRITE_ONCE(best_rq->numa_migrate_on, 0);
 
 	if (ret != 0)
-		trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task));
+		trace_sched_stick_numa(p, env.src_cpu, env.best_task, env.best_cpu);
 	put_task_struct(env.best_task);
 	return ret;
 }
@@ -2541,7 +2783,7 @@
 		return;
 
 
-	if (!down_read_trylock(&mm->mmap_sem))
+	if (!mmap_read_trylock(mm))
 		return;
 	vma = find_vma(mm, start);
 	if (!vma) {
@@ -2569,7 +2811,7 @@
 		 * Skip inaccessible VMAs to avoid any confusion between
 		 * PROT_NONE and NUMA hinting ptes
 		 */
-		if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
+		if (!vma_is_accessible(vma))
 			continue;
 
 		do {
@@ -2609,7 +2851,7 @@
 		mm->numa_scan_offset = start;
 	else
 		reset_ptenuma_scan(p);
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 
 	/*
 	 * Make sure tasks use at least 32x as much time to run other code
@@ -2696,7 +2938,7 @@
 		curr->node_stamp += period;
 
 		if (!time_before(jiffies, curr->mm->numa_next_scan))
-			task_work_add(curr, work, true);
+			task_work_add(curr, work, TWA_RESUME);
 	}
 }
 
@@ -2831,25 +3073,6 @@
 
 #ifdef CONFIG_SMP
 static inline void
-enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-	cfs_rq->runnable_weight += se->runnable_weight;
-
-	cfs_rq->avg.runnable_load_avg += se->avg.runnable_load_avg;
-	cfs_rq->avg.runnable_load_sum += se_runnable(se) * se->avg.runnable_load_sum;
-}
-
-static inline void
-dequeue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-	cfs_rq->runnable_weight -= se->runnable_weight;
-
-	sub_positive(&cfs_rq->avg.runnable_load_avg, se->avg.runnable_load_avg);
-	sub_positive(&cfs_rq->avg.runnable_load_sum,
-		     se_runnable(se) * se->avg.runnable_load_sum);
-}
-
-static inline void
 enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	cfs_rq->avg.load_avg += se->avg.load_avg;
@@ -2864,45 +3087,36 @@
 }
 #else
 static inline void
-enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
-static inline void
-dequeue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
-static inline void
 enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
 static inline void
 dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
 #endif
 
 static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
-			    unsigned long weight, unsigned long runnable)
+			    unsigned long weight)
 {
 	if (se->on_rq) {
 		/* commit outstanding execution time */
 		if (cfs_rq->curr == se)
 			update_curr(cfs_rq);
-		account_entity_dequeue(cfs_rq, se);
-		dequeue_runnable_load_avg(cfs_rq, se);
+		update_load_sub(&cfs_rq->load, se->load.weight);
 	}
 	dequeue_load_avg(cfs_rq, se);
 
-	se->runnable_weight = runnable;
 	update_load_set(&se->load, weight);
 
 #ifdef CONFIG_SMP
 	do {
-		u32 divider = LOAD_AVG_MAX - 1024 + se->avg.period_contrib;
+		u32 divider = get_pelt_divider(&se->avg);
 
 		se->avg.load_avg = div_u64(se_weight(se) * se->avg.load_sum, divider);
-		se->avg.runnable_load_avg =
-			div_u64(se_runnable(se) * se->avg.runnable_load_sum, divider);
 	} while (0);
 #endif
 
 	enqueue_load_avg(cfs_rq, se);
-	if (se->on_rq) {
-		account_entity_enqueue(cfs_rq, se);
-		enqueue_runnable_load_avg(cfs_rq, se);
-	}
+	if (se->on_rq)
+		update_load_add(&cfs_rq->load, se->load.weight);
+
 }
 
 void reweight_task(struct task_struct *p, int prio)
@@ -2912,7 +3126,7 @@
 	struct load_weight *load = &se->load;
 	unsigned long weight = scale_load(sched_prio_to_weight[prio]);
 
-	reweight_entity(cfs_rq, se, weight, weight);
+	reweight_entity(cfs_rq, se, weight);
 	load->inv_weight = sched_prio_to_wmult[prio];
 }
 
@@ -3024,50 +3238,6 @@
 	 */
 	return clamp_t(long, shares, MIN_SHARES, tg_shares);
 }
-
-/*
- * This calculates the effective runnable weight for a group entity based on
- * the group entity weight calculated above.
- *
- * Because of the above approximation (2), our group entity weight is
- * an load_avg based ratio (3). This means that it includes blocked load and
- * does not represent the runnable weight.
- *
- * Approximate the group entity's runnable weight per ratio from the group
- * runqueue:
- *
- *					     grq->avg.runnable_load_avg
- *   ge->runnable_weight = ge->load.weight * -------------------------- (7)
- *						 grq->avg.load_avg
- *
- * However, analogous to above, since the avg numbers are slow, this leads to
- * transients in the from-idle case. Instead we use:
- *
- *   ge->runnable_weight = ge->load.weight *
- *
- *		max(grq->avg.runnable_load_avg, grq->runnable_weight)
- *		-----------------------------------------------------	(8)
- *		      max(grq->avg.load_avg, grq->load.weight)
- *
- * Where these max() serve both to use the 'instant' values to fix the slow
- * from-idle and avoid the /0 on to-idle, similar to (6).
- */
-static long calc_group_runnable(struct cfs_rq *cfs_rq, long shares)
-{
-	long runnable, load_avg;
-
-	load_avg = max(cfs_rq->avg.load_avg,
-		       scale_load_down(cfs_rq->load.weight));
-
-	runnable = max(cfs_rq->avg.runnable_load_avg,
-		       scale_load_down(cfs_rq->runnable_weight));
-
-	runnable *= shares;
-	if (load_avg)
-		runnable /= load_avg;
-
-	return clamp_t(long, runnable, MIN_SHARES, shares);
-}
 #endif /* CONFIG_SMP */
 
 static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
@@ -3079,7 +3249,7 @@
 static void update_cfs_group(struct sched_entity *se)
 {
 	struct cfs_rq *gcfs_rq = group_cfs_rq(se);
-	long shares, runnable;
+	long shares;
 
 	if (!gcfs_rq)
 		return;
@@ -3088,16 +3258,15 @@
 		return;
 
 #ifndef CONFIG_SMP
-	runnable = shares = READ_ONCE(gcfs_rq->tg->shares);
+	shares = READ_ONCE(gcfs_rq->tg->shares);
 
 	if (likely(se->load.weight == shares))
 		return;
 #else
 	shares   = calc_group_shares(gcfs_rq);
-	runnable = calc_group_runnable(gcfs_rq, shares);
 #endif
 
-	reweight_entity(cfs_rq_of(se), se, shares, runnable);
+	reweight_entity(cfs_rq_of(se), se, shares);
 }
 
 #else /* CONFIG_FAIR_GROUP_SCHED */
@@ -3110,7 +3279,7 @@
 {
 	struct rq *rq = rq_of(cfs_rq);
 
-	if (&rq->cfs == cfs_rq || (flags & SCHED_CPUFREQ_MIGRATION)) {
+	if (&rq->cfs == cfs_rq) {
 		/*
 		 * There are a few boundary cases this might miss but it should
 		 * get called often enough that that should (hopefully) not be
@@ -3134,7 +3303,6 @@
 /**
  * update_tg_load_avg - update the tg's load avg
  * @cfs_rq: the cfs_rq whose avg changed
- * @force: update regardless of how small the difference
  *
  * This function 'ensures': tg->load_avg := \Sum tg->cfs_rq[]->avg.load.
  * However, because tg->load_avg is a global value there are performance
@@ -3146,7 +3314,7 @@
  *
  * Updating tg's load_avg is necessary before update_cfs_share().
  */
-static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
+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;
 
@@ -3156,7 +3324,7 @@
 	if (cfs_rq->tg == &root_task_group)
 		return;
 
-	if (force || abs(delta) > cfs_rq->tg_load_avg_contrib / 64) {
+	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;
 	}
@@ -3211,7 +3379,6 @@
 	se->avg.last_update_time = n_last_update_time;
 }
 
-
 /*
  * When on migration a sched_entity joins/leaves the PELT hierarchy, we need to
  * propagate its contribution. The key to this propagation is the invariant
@@ -3222,11 +3389,11 @@
  * _IFF_ we look at the pure running and runnable sums. Because they
  * represent the very same entity, just at different points in the hierarchy.
  *
- * Per the above update_tg_cfs_util() is trivial and simply copies the running
- * sum over (but still wrong, because the group entity and group rq do not have
- * their PELT windows aligned).
+ * Per the above update_tg_cfs_util() and update_tg_cfs_runnable() are trivial
+ * and simply copies the running/runnable sum over (but still wrong, because
+ * the group entity and group rq do not have their PELT windows aligned).
  *
- * However, update_tg_cfs_runnable() is more complex. So we have:
+ * However, update_tg_cfs_load() is more complex. So we have:
  *
  *   ge->avg.load_avg = ge->load.weight * ge->avg.runnable_avg		(2)
  *
@@ -3279,53 +3446,82 @@
  * XXX: only do this for the part of runnable > running ?
  *
  */
-
 static inline void
 update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq)
 {
 	long delta = gcfs_rq->avg.util_avg - se->avg.util_avg;
+	u32 divider;
 
 	/* Nothing to update */
 	if (!delta)
 		return;
 
 	/*
-	 * The relation between sum and avg is:
-	 *
-	 *   LOAD_AVG_MAX - 1024 + sa->period_contrib
-	 *
-	 * however, the PELT windows are not aligned between grq and gse.
+	 * cfs_rq->avg.period_contrib can be used for both cfs_rq and se.
+	 * See ___update_load_avg() for details.
 	 */
+	divider = get_pelt_divider(&cfs_rq->avg);
 
 	/* Set new sched_entity's utilization */
 	se->avg.util_avg = gcfs_rq->avg.util_avg;
-	se->avg.util_sum = se->avg.util_avg * LOAD_AVG_MAX;
+	se->avg.util_sum = se->avg.util_avg * divider;
 
 	/* Update parent cfs_rq utilization */
 	add_positive(&cfs_rq->avg.util_avg, delta);
-	cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * LOAD_AVG_MAX;
+	cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * divider;
 }
 
 static inline void
 update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq)
 {
-	long delta_avg, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum;
-	unsigned long runnable_load_avg, load_avg;
-	u64 runnable_load_sum, load_sum = 0;
-	s64 delta_sum;
+	long delta = gcfs_rq->avg.runnable_avg - se->avg.runnable_avg;
+	u32 divider;
+
+	/* Nothing to update */
+	if (!delta)
+		return;
+
+	/*
+	 * cfs_rq->avg.period_contrib can be used for both cfs_rq and se.
+	 * See ___update_load_avg() for details.
+	 */
+	divider = get_pelt_divider(&cfs_rq->avg);
+
+	/* Set new sched_entity's runnable */
+	se->avg.runnable_avg = gcfs_rq->avg.runnable_avg;
+	se->avg.runnable_sum = se->avg.runnable_avg * divider;
+
+	/* Update parent cfs_rq runnable */
+	add_positive(&cfs_rq->avg.runnable_avg, delta);
+	cfs_rq->avg.runnable_sum = cfs_rq->avg.runnable_avg * divider;
+}
+
+static inline void
+update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq)
+{
+	long delta, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum;
+	unsigned long load_avg;
+	u64 load_sum = 0;
+	u32 divider;
 
 	if (!runnable_sum)
 		return;
 
 	gcfs_rq->prop_runnable_sum = 0;
 
+	/*
+	 * cfs_rq->avg.period_contrib can be used for both cfs_rq and se.
+	 * See ___update_load_avg() for details.
+	 */
+	divider = get_pelt_divider(&cfs_rq->avg);
+
 	if (runnable_sum >= 0) {
 		/*
 		 * Add runnable; clip at LOAD_AVG_MAX. Reflects that until
 		 * the CPU is saturated running == runnable.
 		 */
 		runnable_sum += se->avg.load_sum;
-		runnable_sum = min(runnable_sum, (long)LOAD_AVG_MAX);
+		runnable_sum = min_t(long, runnable_sum, divider);
 	} else {
 		/*
 		 * Estimate the new unweighted runnable_sum of the gcfs_rq by
@@ -3350,28 +3546,15 @@
 	runnable_sum = max(runnable_sum, running_sum);
 
 	load_sum = (s64)se_weight(se) * runnable_sum;
-	load_avg = div_s64(load_sum, LOAD_AVG_MAX);
+	load_avg = div_s64(load_sum, divider);
 
-	delta_sum = load_sum - (s64)se_weight(se) * se->avg.load_sum;
-	delta_avg = load_avg - se->avg.load_avg;
+	delta = load_avg - se->avg.load_avg;
 
 	se->avg.load_sum = runnable_sum;
 	se->avg.load_avg = load_avg;
-	add_positive(&cfs_rq->avg.load_avg, delta_avg);
-	add_positive(&cfs_rq->avg.load_sum, delta_sum);
 
-	runnable_load_sum = (s64)se_runnable(se) * runnable_sum;
-	runnable_load_avg = div_s64(runnable_load_sum, LOAD_AVG_MAX);
-	delta_sum = runnable_load_sum - se_weight(se) * se->avg.runnable_load_sum;
-	delta_avg = runnable_load_avg - se->avg.runnable_load_avg;
-
-	se->avg.runnable_load_sum = runnable_sum;
-	se->avg.runnable_load_avg = runnable_load_avg;
-
-	if (se->on_rq) {
-		add_positive(&cfs_rq->avg.runnable_load_avg, delta_avg);
-		add_positive(&cfs_rq->avg.runnable_load_sum, delta_sum);
-	}
+	add_positive(&cfs_rq->avg.load_avg, delta);
+	cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * divider;
 }
 
 static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum)
@@ -3400,6 +3583,7 @@
 
 	update_tg_cfs_util(cfs_rq, se, gcfs_rq);
 	update_tg_cfs_runnable(cfs_rq, se, gcfs_rq);
+	update_tg_cfs_load(cfs_rq, se, gcfs_rq);
 
 	trace_pelt_cfs_tp(cfs_rq);
 	trace_pelt_se_tp(se);
@@ -3439,7 +3623,7 @@
 
 #else /* CONFIG_FAIR_GROUP_SCHED */
 
-static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
+static inline void update_tg_load_avg(struct cfs_rq *cfs_rq) {}
 
 static inline int propagate_entity_load_avg(struct sched_entity *se)
 {
@@ -3469,30 +3653,51 @@
 static inline int
 update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 {
-	unsigned long removed_load = 0, removed_util = 0, removed_runnable_sum = 0;
+	unsigned long removed_load = 0, removed_util = 0, removed_runnable = 0;
 	struct sched_avg *sa = &cfs_rq->avg;
 	int decayed = 0;
 
 	if (cfs_rq->removed.nr) {
 		unsigned long r;
-		u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib;
+		u32 divider = get_pelt_divider(&cfs_rq->avg);
 
 		raw_spin_lock(&cfs_rq->removed.lock);
 		swap(cfs_rq->removed.util_avg, removed_util);
 		swap(cfs_rq->removed.load_avg, removed_load);
-		swap(cfs_rq->removed.runnable_sum, removed_runnable_sum);
+		swap(cfs_rq->removed.runnable_avg, removed_runnable);
 		cfs_rq->removed.nr = 0;
 		raw_spin_unlock(&cfs_rq->removed.lock);
 
 		r = removed_load;
 		sub_positive(&sa->load_avg, r);
-		sub_positive(&sa->load_sum, r * divider);
+		sa->load_sum = sa->load_avg * divider;
 
 		r = removed_util;
 		sub_positive(&sa->util_avg, r);
 		sub_positive(&sa->util_sum, r * divider);
+		/*
+		 * Because of rounding, se->util_sum might ends up being +1 more than
+		 * cfs->util_sum. Although this is not a problem by itself, detaching
+		 * a lot of tasks with the rounding problem between 2 updates of
+		 * util_avg (~1ms) can make cfs->util_sum becoming null whereas
+		 * cfs_util_avg is not.
+		 * Check that util_sum is still above its lower bound for the new
+		 * util_avg. Given that period_contrib might have moved since the last
+		 * sync, we are only sure that util_sum must be above or equal to
+		 *    util_avg * minimum possible divider
+		 */
+		sa->util_sum = max_t(u32, sa->util_sum, sa->util_avg * PELT_MIN_DIVIDER);
 
-		add_tg_cfs_propagate(cfs_rq, -(long)removed_runnable_sum);
+		r = removed_runnable;
+		sub_positive(&sa->runnable_avg, r);
+		sa->runnable_sum = sa->runnable_avg * divider;
+
+		/*
+		 * removed_runnable is the unweighted version of removed_load so we
+		 * can use it to estimate removed_load_sum.
+		 */
+		add_tg_cfs_propagate(cfs_rq,
+			-(long)(removed_runnable * divider) >> SCHED_CAPACITY_SHIFT);
 
 		decayed = 1;
 	}
@@ -3511,14 +3716,17 @@
  * attach_entity_load_avg - attach this entity to its cfs_rq load avg
  * @cfs_rq: cfs_rq to attach to
  * @se: sched_entity to attach
- * @flags: migration hints
  *
  * Must call update_cfs_rq_load_avg() before this, since we rely on
  * cfs_rq->avg.last_update_time being current.
  */
-static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
+static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	u32 divider = LOAD_AVG_MAX - 1024 + cfs_rq->avg.period_contrib;
+	/*
+	 * cfs_rq->avg.period_contrib can be used for both cfs_rq and se.
+	 * See ___update_load_avg() for details.
+	 */
+	u32 divider = get_pelt_divider(&cfs_rq->avg);
 
 	/*
 	 * When we attach the @se to the @cfs_rq, we must align the decay
@@ -3538,21 +3746,23 @@
 	 */
 	se->avg.util_sum = se->avg.util_avg * divider;
 
+	se->avg.runnable_sum = se->avg.runnable_avg * divider;
+
 	se->avg.load_sum = divider;
 	if (se_weight(se)) {
 		se->avg.load_sum =
 			div_u64(se->avg.load_avg * se->avg.load_sum, se_weight(se));
 	}
 
-	se->avg.runnable_load_sum = se->avg.load_sum;
-
 	enqueue_load_avg(cfs_rq, se);
 	cfs_rq->avg.util_avg += se->avg.util_avg;
 	cfs_rq->avg.util_sum += se->avg.util_sum;
+	cfs_rq->avg.runnable_avg += se->avg.runnable_avg;
+	cfs_rq->avg.runnable_sum += se->avg.runnable_sum;
 
 	add_tg_cfs_propagate(cfs_rq, se->avg.load_sum);
 
-	cfs_rq_util_change(cfs_rq, flags);
+	cfs_rq_util_change(cfs_rq, 0);
 
 	trace_pelt_cfs_tp(cfs_rq);
 }
@@ -3567,9 +3777,17 @@
  */
 static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
+	/*
+	 * cfs_rq->avg.period_contrib can be used for both cfs_rq and se.
+	 * See ___update_load_avg() for details.
+	 */
+	u32 divider = get_pelt_divider(&cfs_rq->avg);
+
 	dequeue_load_avg(cfs_rq, se);
 	sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
-	sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
+	cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * divider;
+	sub_positive(&cfs_rq->avg.runnable_avg, se->avg.runnable_avg);
+	cfs_rq->avg.runnable_sum = cfs_rq->avg.runnable_avg * divider;
 
 	add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum);
 
@@ -3610,14 +3828,14 @@
 		 *
 		 * IOW we're enqueueing a task on a new CPU.
 		 */
-		attach_entity_load_avg(cfs_rq, se, SCHED_CPUFREQ_MIGRATION);
-		update_tg_load_avg(cfs_rq, 0);
+		attach_entity_load_avg(cfs_rq, se);
+		update_tg_load_avg(cfs_rq);
 
 	} else if (decayed) {
 		cfs_rq_util_change(cfs_rq, 0);
 
 		if (flags & UPDATE_TG)
-			update_tg_load_avg(cfs_rq, 0);
+			update_tg_load_avg(cfs_rq);
 	}
 }
 
@@ -3676,13 +3894,13 @@
 	++cfs_rq->removed.nr;
 	cfs_rq->removed.util_avg	+= se->avg.util_avg;
 	cfs_rq->removed.load_avg	+= se->avg.load_avg;
-	cfs_rq->removed.runnable_sum	+= se->avg.load_sum; /* == runnable_sum */
+	cfs_rq->removed.runnable_avg	+= se->avg.runnable_avg;
 	raw_spin_unlock_irqrestore(&cfs_rq->removed.lock, flags);
 }
 
-static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq)
+static inline unsigned long cfs_rq_runnable_avg(struct cfs_rq *cfs_rq)
 {
-	return cfs_rq->avg.runnable_load_avg;
+	return cfs_rq->avg.runnable_avg;
 }
 
 static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq)
@@ -3690,6 +3908,8 @@
 	return cfs_rq->avg.load_avg;
 }
 
+static int newidle_balance(struct rq *this_rq, struct rq_flags *rf);
+
 static inline unsigned long task_util(struct task_struct *p)
 {
 	return READ_ONCE(p->se.avg.util_avg);
@@ -3699,7 +3919,7 @@
 {
 	struct util_est ue = READ_ONCE(p->se.avg.util_est);
 
-	return (max(ue.ewma, ue.enqueued) | UTIL_AVG_UNCHANGED);
+	return max(ue.ewma, (ue.enqueued & ~UTIL_AVG_UNCHANGED));
 }
 
 static inline unsigned long task_util_est(struct task_struct *p)
@@ -3707,6 +3927,20 @@
 	return max(task_util(p), _task_util_est(p));
 }
 
+#ifdef CONFIG_UCLAMP_TASK
+static inline unsigned long uclamp_task_util(struct task_struct *p)
+{
+	return clamp(task_util_est(p),
+		     uclamp_eff_value(p, UCLAMP_MIN),
+		     uclamp_eff_value(p, UCLAMP_MAX));
+}
+#else
+static inline unsigned long uclamp_task_util(struct task_struct *p)
+{
+	return task_util_est(p);
+}
+#endif
+
 static inline void util_est_enqueue(struct cfs_rq *cfs_rq,
 				    struct task_struct *p)
 {
@@ -3719,8 +3953,28 @@
 	enqueued  = cfs_rq->avg.util_est.enqueued;
 	enqueued += _task_util_est(p);
 	WRITE_ONCE(cfs_rq->avg.util_est.enqueued, enqueued);
+
+	trace_sched_util_est_cfs_tp(cfs_rq);
 }
 
+static inline void util_est_dequeue(struct cfs_rq *cfs_rq,
+				    struct task_struct *p)
+{
+	unsigned int enqueued;
+
+	if (!sched_feat(UTIL_EST))
+		return;
+
+	/* Update root cfs_rq's estimated utilization */
+	enqueued  = cfs_rq->avg.util_est.enqueued;
+	enqueued -= min_t(unsigned int, enqueued, _task_util_est(p));
+	WRITE_ONCE(cfs_rq->avg.util_est.enqueued, enqueued);
+
+	trace_sched_util_est_cfs_tp(cfs_rq);
+}
+
+#define UTIL_EST_MARGIN (SCHED_CAPACITY_SCALE / 100)
+
 /*
  * Check if a (signed) value is within a specified (unsigned) margin,
  * based on the observation that:
@@ -3734,21 +3988,16 @@
 	return ((unsigned int)(value + margin - 1) < (2 * margin - 1));
 }
 
-static void
-util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
+static inline void util_est_update(struct cfs_rq *cfs_rq,
+				   struct task_struct *p,
+				   bool task_sleep)
 {
-	long last_ewma_diff;
+	long last_ewma_diff, last_enqueued_diff;
 	struct util_est ue;
-	int cpu;
 
 	if (!sched_feat(UTIL_EST))
 		return;
 
-	/* Update root cfs_rq's estimated utilization */
-	ue.enqueued  = cfs_rq->avg.util_est.enqueued;
-	ue.enqueued -= min_t(unsigned int, ue.enqueued, _task_util_est(p));
-	WRITE_ONCE(cfs_rq->avg.util_est.enqueued, ue.enqueued);
-
 	/*
 	 * Skip update of task's estimated utilization when the task has not
 	 * yet completed an activation, e.g. being migrated.
@@ -3764,21 +4013,38 @@
 	if (ue.enqueued & UTIL_AVG_UNCHANGED)
 		return;
 
+	last_enqueued_diff = ue.enqueued;
+
 	/*
-	 * Skip update of task's estimated utilization when its EWMA is
+	 * Reset EWMA on utilization increases, the moving average is used only
+	 * to smooth utilization decreases.
+	 */
+	ue.enqueued = task_util(p);
+	if (sched_feat(UTIL_EST_FASTUP)) {
+		if (ue.ewma < ue.enqueued) {
+			ue.ewma = ue.enqueued;
+			goto done;
+		}
+	}
+
+	/*
+	 * Skip update of task's estimated utilization when its members are
 	 * already ~1% close to its last activation value.
 	 */
-	ue.enqueued = (task_util(p) | UTIL_AVG_UNCHANGED);
 	last_ewma_diff = ue.enqueued - ue.ewma;
-	if (within_margin(last_ewma_diff, (SCHED_CAPACITY_SCALE / 100)))
+	last_enqueued_diff -= ue.enqueued;
+	if (within_margin(last_ewma_diff, UTIL_EST_MARGIN)) {
+		if (!within_margin(last_enqueued_diff, UTIL_EST_MARGIN))
+			goto done;
+
 		return;
+	}
 
 	/*
 	 * To avoid overestimation of actual task utilization, skip updates if
 	 * we cannot grant there is idle time in this CPU.
 	 */
-	cpu = cpu_of(rq_of(cfs_rq));
-	if (task_util(p) > capacity_orig_of(cpu))
+	if (task_util(p) > capacity_orig_of(cpu_of(rq_of(cfs_rq))))
 		return;
 
 	/*
@@ -3801,12 +4067,16 @@
 	ue.ewma <<= UTIL_EST_WEIGHT_SHIFT;
 	ue.ewma  += last_ewma_diff;
 	ue.ewma >>= UTIL_EST_WEIGHT_SHIFT;
+done:
+	ue.enqueued |= UTIL_AVG_UNCHANGED;
 	WRITE_ONCE(p->se.avg.util_est, ue);
+
+	trace_sched_util_est_se_tp(&p->se);
 }
 
 static inline int task_fits_capacity(struct task_struct *p, long capacity)
 {
-	return fits_capacity(task_util_est(p), capacity);
+	return fits_capacity(uclamp_task_util(p), capacity);
 }
 
 static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
@@ -3845,11 +4115,11 @@
 static inline void remove_entity_load_avg(struct sched_entity *se) {}
 
 static inline void
-attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) {}
+attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
 static inline void
 detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
 
-static inline int idle_balance(struct rq *rq, struct rq_flags *rf)
+static inline int newidle_balance(struct rq *rq, struct rq_flags *rf)
 {
 	return 0;
 }
@@ -3858,8 +4128,11 @@
 util_est_enqueue(struct cfs_rq *cfs_rq, struct task_struct *p) {}
 
 static inline void
-util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p,
-		 bool task_sleep) {}
+util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p) {}
+
+static inline void
+util_est_update(struct cfs_rq *cfs_rq, struct task_struct *p,
+		bool task_sleep) {}
 static inline void update_misfit_status(struct task_struct *p, struct rq *rq) {}
 
 #endif /* CONFIG_SMP */
@@ -3996,8 +4269,8 @@
 	 *   - Add its new weight to cfs_rq->load.weight
 	 */
 	update_load_avg(cfs_rq, se, UPDATE_TG | DO_ATTACH);
+	se_update_runnable(se);
 	update_cfs_group(se);
-	enqueue_runnable_load_avg(cfs_rq, se);
 	account_entity_enqueue(cfs_rq, se);
 
 	if (flags & ENQUEUE_WAKEUP)
@@ -4086,7 +4359,7 @@
 	 *     of its group cfs_rq.
 	 */
 	update_load_avg(cfs_rq, se, UPDATE_TG);
-	dequeue_runnable_load_avg(cfs_rq, se);
+	se_update_runnable(se);
 
 	update_stats_dequeue(cfs_rq, se, flags);
 
@@ -4238,17 +4511,17 @@
 			se = second;
 	}
 
-	/*
-	 * Prefer last buddy, try to return the CPU to a preempted task.
-	 */
-	if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
-		se = cfs_rq->last;
-
-	/*
-	 * Someone really wants this to run. If it's not unfair, run it.
-	 */
-	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
+	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1) {
+		/*
+		 * Someone really wants this to run. If it's not unfair, run it.
+		 */
 		se = cfs_rq->next;
+	} else if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1) {
+		/*
+		 * Prefer last buddy, try to return the CPU to a preempted task.
+		 */
+		se = cfs_rq->last;
+	}
 
 	clear_buddies(cfs_rq, se);
 
@@ -4554,8 +4827,13 @@
 		if (!se->on_rq)
 			break;
 
-		if (dequeue)
+		if (dequeue) {
 			dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP);
+		} else {
+			update_load_avg(qcfs_rq, se, 0);
+			se_update_runnable(se);
+		}
+
 		qcfs_rq->h_nr_running -= task_delta;
 		qcfs_rq->idle_h_nr_running -= idle_task_delta;
 
@@ -4618,6 +4896,9 @@
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
 
+		update_load_avg(cfs_rq, se, UPDATE_TG);
+		se_update_runnable(se);
+
 		cfs_rq->h_nr_running += task_delta;
 		cfs_rq->idle_h_nr_running += idle_task_delta;
 
@@ -4657,11 +4938,10 @@
 		resched_curr(rq);
 }
 
-static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining)
+static void distribute_cfs_runtime(struct cfs_bandwidth *cfs_b)
 {
 	struct cfs_rq *cfs_rq;
-	u64 runtime;
-	u64 starting_runtime = remaining;
+	u64 runtime, remaining = 1;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq,
@@ -4676,10 +4956,13 @@
 		/* By the above check, this should never be true */
 		SCHED_WARN_ON(cfs_rq->runtime_remaining > 0);
 
+		raw_spin_lock(&cfs_b->lock);
 		runtime = -cfs_rq->runtime_remaining + 1;
-		if (runtime > remaining)
-			runtime = remaining;
-		remaining -= runtime;
+		if (runtime > cfs_b->runtime)
+			runtime = cfs_b->runtime;
+		cfs_b->runtime -= runtime;
+		remaining = cfs_b->runtime;
+		raw_spin_unlock(&cfs_b->lock);
 
 		cfs_rq->runtime_remaining += runtime;
 
@@ -4694,8 +4977,6 @@
 			break;
 	}
 	rcu_read_unlock();
-
-	return starting_runtime - remaining;
 }
 
 /*
@@ -4706,7 +4987,6 @@
  */
 static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, unsigned long flags)
 {
-	u64 runtime;
 	int throttled;
 
 	/* no need to continue the timer with no bandwidth constraint */
@@ -4735,24 +5015,15 @@
 	cfs_b->nr_throttled += overrun;
 
 	/*
-	 * This check is repeated as we are holding onto the new bandwidth while
-	 * we unthrottle. This can potentially race with an unthrottled group
-	 * trying to acquire new bandwidth from the global pool. This can result
-	 * in us over-using our runtime if it is all used during this loop, but
-	 * only by limited amounts in that extreme case.
+	 * This check is repeated as we release cfs_b->lock while we unthrottle.
 	 */
-	while (throttled && cfs_b->runtime > 0 && !cfs_b->distribute_running) {
-		runtime = cfs_b->runtime;
-		cfs_b->distribute_running = 1;
+	while (throttled && cfs_b->runtime > 0) {
 		raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
 		/* we can't nest cfs_b->lock while distributing bandwidth */
-		runtime = distribute_cfs_runtime(cfs_b, runtime);
+		distribute_cfs_runtime(cfs_b);
 		raw_spin_lock_irqsave(&cfs_b->lock, flags);
 
-		cfs_b->distribute_running = 0;
 		throttled = !list_empty(&cfs_b->throttled_cfs_rq);
-
-		lsub_positive(&cfs_b->runtime, runtime);
 	}
 
 	/*
@@ -4865,10 +5136,6 @@
 	/* confirm we're still not at a refresh boundary */
 	raw_spin_lock_irqsave(&cfs_b->lock, flags);
 	cfs_b->slack_started = false;
-	if (cfs_b->distribute_running) {
-		raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
-		return;
-	}
 
 	if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) {
 		raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
@@ -4878,26 +5145,21 @@
 	if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice)
 		runtime = cfs_b->runtime;
 
-	if (runtime)
-		cfs_b->distribute_running = 1;
-
 	raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
 
 	if (!runtime)
 		return;
 
-	runtime = distribute_cfs_runtime(cfs_b, runtime);
+	distribute_cfs_runtime(cfs_b);
 
 	raw_spin_lock_irqsave(&cfs_b->lock, flags);
-	lsub_positive(&cfs_b->runtime, runtime);
-	cfs_b->distribute_running = 0;
 	raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
 }
 
 /*
  * When a group wakes up we want to make sure that its quota is not already
  * expired/exceeded, otherwise it may be allowed to steal additional ticks of
- * runtime as update_curr() throttling can not not trigger until it's on-rq.
+ * runtime as update_curr() throttling can not trigger until it's on-rq.
  */
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq)
 {
@@ -5032,7 +5294,6 @@
 	cfs_b->period_timer.function = sched_cfs_period_timer;
 	hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	cfs_b->slack_timer.function = sched_cfs_slack_timer;
-	cfs_b->distribute_running = 0;
 	cfs_b->slack_started = false;
 }
 
@@ -5237,6 +5498,20 @@
 static inline void update_overutilized_status(struct rq *rq) { }
 #endif
 
+/* Runqueue only has SCHED_IDLE tasks enqueued */
+static int sched_idle_rq(struct rq *rq)
+{
+	return unlikely(rq->nr_running == rq->cfs.idle_h_nr_running &&
+			rq->nr_running);
+}
+
+#ifdef CONFIG_SMP
+static int sched_idle_cpu(int cpu)
+{
+	return sched_idle_rq(cpu_rq(cpu));
+}
+#endif
+
 /*
  * The enqueue_task method is called before nr_running is
  * increased. Here we update the fair scheduling stats and
@@ -5286,6 +5561,7 @@
 		cfs_rq = cfs_rq_of(se);
 
 		update_load_avg(cfs_rq, se, UPDATE_TG);
+		se_update_runnable(se);
 		update_cfs_group(se);
 
 		cfs_rq->h_nr_running++;
@@ -5303,28 +5579,27 @@
                        list_add_leaf_cfs_rq(cfs_rq);
 	}
 
+	/* At this point se is NULL and we are at root level*/
+	add_nr_running(rq, 1);
+
+	/*
+	 * Since new tasks are assigned an initial util_avg equal to
+	 * half of the spare capacity of their CPU, tiny tasks have the
+	 * ability to cross the overutilized threshold, which will
+	 * result in the load balancer ruining all the task placement
+	 * done by EAS. As a way to mitigate that effect, do not account
+	 * for the first enqueue operation of new tasks during the
+	 * overutilized flag detection.
+	 *
+	 * A better way of solving this problem would be to wait for
+	 * the PELT signals of tasks to converge before taking them
+	 * into account, but that is not straightforward to implement,
+	 * and the following generally works well enough in practice.
+	 */
+	if (!task_new)
+		update_overutilized_status(rq);
+
 enqueue_throttle:
-	if (!se) {
-		add_nr_running(rq, 1);
-		/*
-		 * Since new tasks are assigned an initial util_avg equal to
-		 * half of the spare capacity of their CPU, tiny tasks have the
-		 * ability to cross the overutilized threshold, which will
-		 * result in the load balancer ruining all the task placement
-		 * done by EAS. As a way to mitigate that effect, do not account
-		 * for the first enqueue operation of new tasks during the
-		 * overutilized flag detection.
-		 *
-		 * A better way of solving this problem would be to wait for
-		 * the PELT signals of tasks to converge before taking them
-		 * into account, but that is not straightforward to implement,
-		 * and the following generally works well enough in practice.
-		 */
-		if (!task_new)
-			update_overutilized_status(rq);
-
-	}
-
 	if (cfs_bandwidth_used()) {
 		/*
 		 * When bandwidth control is enabled; the cfs_rq_throttled()
@@ -5358,6 +5633,9 @@
 	struct sched_entity *se = &p->se;
 	int task_sleep = flags & DEQUEUE_SLEEP;
 	int idle_h_nr_running = task_has_idle_policy(p);
+	bool was_sched_idle = sched_idle_rq(rq);
+
+	util_est_dequeue(&rq->cfs, p);
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
@@ -5389,6 +5667,7 @@
 		cfs_rq = cfs_rq_of(se);
 
 		update_load_avg(cfs_rq, se, UPDATE_TG);
+		se_update_runnable(se);
 		update_cfs_group(se);
 
 		cfs_rq->h_nr_running--;
@@ -5400,11 +5679,15 @@
 
 	}
 
-dequeue_throttle:
-	if (!se)
-		sub_nr_running(rq, 1);
+	/* At this point se is NULL and we are at root level*/
+	sub_nr_running(rq, 1);
 
-	util_est_dequeue(&rq->cfs, p, task_sleep);
+	/* balance early to pull high priority tasks */
+	if (unlikely(!was_sched_idle && sched_idle_rq(rq)))
+		rq->next_balance = jiffies;
+
+dequeue_throttle:
+	util_est_update(&rq->cfs, p, task_sleep);
 	hrtick_update(rq);
 }
 
@@ -5426,18 +5709,63 @@
 
 #endif /* CONFIG_NO_HZ_COMMON */
 
-/* CPU only has SCHED_IDLE tasks enqueued */
-static int sched_idle_cpu(int cpu)
+static unsigned long cpu_load(struct rq *rq)
 {
-	struct rq *rq = cpu_rq(cpu);
-
-	return unlikely(rq->nr_running == rq->cfs.idle_h_nr_running &&
-			rq->nr_running);
+	return cfs_rq_load_avg(&rq->cfs);
 }
 
-static unsigned long cpu_runnable_load(struct rq *rq)
+/*
+ * cpu_load_without - compute CPU load without any contributions from *p
+ * @cpu: the CPU which load is requested
+ * @p: the task which load should be discounted
+ *
+ * The load of a CPU is defined by the load of tasks currently enqueued on that
+ * CPU as well as tasks which are currently sleeping after an execution on that
+ * CPU.
+ *
+ * This method returns the load of the specified CPU by discounting the load of
+ * the specified task, whenever the task is currently contributing to the CPU
+ * load.
+ */
+static unsigned long cpu_load_without(struct rq *rq, struct task_struct *p)
 {
-	return cfs_rq_runnable_load_avg(&rq->cfs);
+	struct cfs_rq *cfs_rq;
+	unsigned int load;
+
+	/* Task has no contribution or is new */
+	if (cpu_of(rq) != task_cpu(p) || !READ_ONCE(p->se.avg.last_update_time))
+		return cpu_load(rq);
+
+	cfs_rq = &rq->cfs;
+	load = READ_ONCE(cfs_rq->avg.load_avg);
+
+	/* Discount task's util from CPU's util */
+	lsub_positive(&load, task_h_load(p));
+
+	return load;
+}
+
+static unsigned long cpu_runnable(struct rq *rq)
+{
+	return cfs_rq_runnable_avg(&rq->cfs);
+}
+
+static unsigned long cpu_runnable_without(struct rq *rq, struct task_struct *p)
+{
+	struct cfs_rq *cfs_rq;
+	unsigned int runnable;
+
+	/* Task has no contribution or is new */
+	if (cpu_of(rq) != task_cpu(p) || !READ_ONCE(p->se.avg.last_update_time))
+		return cpu_runnable(rq);
+
+	cfs_rq = &rq->cfs;
+	runnable = READ_ONCE(cfs_rq->avg.runnable_avg);
+
+	/* Discount task's runnable from CPU's runnable */
+	lsub_positive(&runnable, p->se.avg.runnable_avg);
+
+	return runnable;
 }
 
 static unsigned long capacity_of(int cpu)
@@ -5445,18 +5773,6 @@
 	return cpu_rq(cpu)->cpu_capacity;
 }
 
-static unsigned long cpu_avg_load_per_task(int cpu)
-{
-	struct rq *rq = cpu_rq(cpu);
-	unsigned long nr_running = READ_ONCE(rq->cfs.h_nr_running);
-	unsigned long load_avg = cpu_runnable_load(rq);
-
-	if (nr_running)
-		return load_avg / nr_running;
-
-	return 0;
-}
-
 static void record_wakee(struct task_struct *p)
 {
 	/*
@@ -5495,7 +5811,7 @@
 {
 	unsigned int master = current->wakee_flips;
 	unsigned int slave = p->wakee_flips;
-	int factor = this_cpu_read(sd_llc_size);
+	int factor = __this_cpu_read(sd_llc_size);
 
 	if (master < slave)
 		swap(master, slave);
@@ -5547,7 +5863,7 @@
 	s64 this_eff_load, prev_eff_load;
 	unsigned long task_load;
 
-	this_eff_load = cpu_runnable_load(cpu_rq(this_cpu));
+	this_eff_load = cpu_load(cpu_rq(this_cpu));
 
 	if (sync) {
 		unsigned long current_load = task_h_load(current);
@@ -5565,7 +5881,7 @@
 		this_eff_load *= 100;
 	this_eff_load *= capacity_of(prev_cpu);
 
-	prev_eff_load = cpu_runnable_load(cpu_rq(prev_cpu));
+	prev_eff_load = cpu_load(cpu_rq(prev_cpu));
 	prev_eff_load -= task_load;
 	if (sched_feat(WA_BIAS))
 		prev_eff_load *= 100 + (sd->imbalance_pct - 100) / 2;
@@ -5603,149 +5919,8 @@
 	return target;
 }
 
-static unsigned long cpu_util_without(int cpu, struct task_struct *p);
-
-static unsigned long capacity_spare_without(int cpu, struct task_struct *p)
-{
-	return max_t(long, capacity_of(cpu) - cpu_util_without(cpu, p), 0);
-}
-
-/*
- * find_idlest_group finds and returns the least busy CPU group within the
- * domain.
- *
- * Assumes p is allowed on at least one CPU in sd.
- */
 static struct sched_group *
-find_idlest_group(struct sched_domain *sd, struct task_struct *p,
-		  int this_cpu, int sd_flag)
-{
-	struct sched_group *idlest = NULL, *group = sd->groups;
-	struct sched_group *most_spare_sg = NULL;
-	unsigned long min_runnable_load = ULONG_MAX;
-	unsigned long this_runnable_load = ULONG_MAX;
-	unsigned long min_avg_load = ULONG_MAX, this_avg_load = ULONG_MAX;
-	unsigned long most_spare = 0, this_spare = 0;
-	int imbalance_scale = 100 + (sd->imbalance_pct-100)/2;
-	unsigned long imbalance = scale_load_down(NICE_0_LOAD) *
-				(sd->imbalance_pct-100) / 100;
-
-	do {
-		unsigned long load, avg_load, runnable_load;
-		unsigned long spare_cap, max_spare_cap;
-		int local_group;
-		int i;
-
-		/* Skip over this group if it has no CPUs allowed */
-		if (!cpumask_intersects(sched_group_span(group),
-					p->cpus_ptr))
-			continue;
-
-		local_group = cpumask_test_cpu(this_cpu,
-					       sched_group_span(group));
-
-		/*
-		 * Tally up the load of all CPUs in the group and find
-		 * the group containing the CPU with most spare capacity.
-		 */
-		avg_load = 0;
-		runnable_load = 0;
-		max_spare_cap = 0;
-
-		for_each_cpu(i, sched_group_span(group)) {
-			load = cpu_runnable_load(cpu_rq(i));
-			runnable_load += load;
-
-			avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs);
-
-			spare_cap = capacity_spare_without(i, p);
-
-			if (spare_cap > max_spare_cap)
-				max_spare_cap = spare_cap;
-		}
-
-		/* Adjust by relative CPU capacity of the group */
-		avg_load = (avg_load * SCHED_CAPACITY_SCALE) /
-					group->sgc->capacity;
-		runnable_load = (runnable_load * SCHED_CAPACITY_SCALE) /
-					group->sgc->capacity;
-
-		if (local_group) {
-			this_runnable_load = runnable_load;
-			this_avg_load = avg_load;
-			this_spare = max_spare_cap;
-		} else {
-			if (min_runnable_load > (runnable_load + imbalance)) {
-				/*
-				 * The runnable load is significantly smaller
-				 * so we can pick this new CPU:
-				 */
-				min_runnable_load = runnable_load;
-				min_avg_load = avg_load;
-				idlest = group;
-			} else if ((runnable_load < (min_runnable_load + imbalance)) &&
-				   (100*min_avg_load > imbalance_scale*avg_load)) {
-				/*
-				 * The runnable loads are close so take the
-				 * blocked load into account through avg_load:
-				 */
-				min_avg_load = avg_load;
-				idlest = group;
-			}
-
-			if (most_spare < max_spare_cap) {
-				most_spare = max_spare_cap;
-				most_spare_sg = group;
-			}
-		}
-	} while (group = group->next, group != sd->groups);
-
-	/*
-	 * The cross-over point between using spare capacity or least load
-	 * is too conservative for high utilization tasks on partially
-	 * utilized systems if we require spare_capacity > task_util(p),
-	 * so we allow for some task stuffing by using
-	 * spare_capacity > task_util(p)/2.
-	 *
-	 * Spare capacity can't be used for fork because the utilization has
-	 * not been set yet, we must first select a rq to compute the initial
-	 * utilization.
-	 */
-	if (sd_flag & SD_BALANCE_FORK)
-		goto skip_spare;
-
-	if (this_spare > task_util(p) / 2 &&
-	    imbalance_scale*this_spare > 100*most_spare)
-		return NULL;
-
-	if (most_spare > task_util(p) / 2)
-		return most_spare_sg;
-
-skip_spare:
-	if (!idlest)
-		return NULL;
-
-	/*
-	 * When comparing groups across NUMA domains, it's possible for the
-	 * local domain to be very lightly loaded relative to the remote
-	 * domains but "imbalance" skews the comparison making remote CPUs
-	 * look much more favourable. When considering cross-domain, add
-	 * imbalance to the runnable load on the remote node and consider
-	 * staying local.
-	 */
-	if ((sd->flags & SD_NUMA) &&
-	    min_runnable_load + imbalance >= this_runnable_load)
-		return NULL;
-
-	if (min_runnable_load > (this_runnable_load + imbalance))
-		return NULL;
-
-	if ((this_runnable_load < (min_runnable_load + imbalance)) &&
-	     (100*this_avg_load < imbalance_scale*min_avg_load))
-		return NULL;
-
-	return idlest;
-}
+find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu);
 
 /*
  * find_idlest_group_cpu - find the idlest CPU among the CPUs in the group.
@@ -5757,7 +5932,7 @@
 	unsigned int min_exit_latency = UINT_MAX;
 	u64 latest_idle_timestamp = 0;
 	int least_loaded_cpu = this_cpu;
-	int shallowest_idle_cpu = -1, si_cpu = -1;
+	int shallowest_idle_cpu = -1;
 	int i;
 
 	/* Check if we have any choice: */
@@ -5766,6 +5941,9 @@
 
 	/* Traverse only the allowed CPUs */
 	for_each_cpu_and(i, sched_group_span(group), p->cpus_ptr) {
+		if (sched_idle_cpu(i))
+			return i;
+
 		if (available_idle_cpu(i)) {
 			struct rq *rq = cpu_rq(i);
 			struct cpuidle_state *idle = idle_get_state(rq);
@@ -5788,13 +5966,8 @@
 				latest_idle_timestamp = rq->idle_stamp;
 				shallowest_idle_cpu = i;
 			}
-		} else if (shallowest_idle_cpu == -1 && si_cpu == -1) {
-			if (sched_idle_cpu(i)) {
-				si_cpu = i;
-				continue;
-			}
-
-			load = cpu_runnable_load(cpu_rq(i));
+		} else if (shallowest_idle_cpu == -1) {
+			load = cpu_load(cpu_rq(i));
 			if (load < min_load) {
 				min_load = load;
 				least_loaded_cpu = i;
@@ -5802,11 +5975,7 @@
 		}
 	}
 
-	if (shallowest_idle_cpu != -1)
-		return shallowest_idle_cpu;
-	if (si_cpu != -1)
-		return si_cpu;
-	return least_loaded_cpu;
+	return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu;
 }
 
 static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p,
@@ -5818,7 +5987,7 @@
 		return prev_cpu;
 
 	/*
-	 * We need task's util for capacity_spare_without, sync it up to
+	 * We need task's util for cpu_util_without, sync it up to
 	 * prev_cpu's last_update_time.
 	 */
 	if (!(sd_flag & SD_BALANCE_FORK))
@@ -5834,7 +6003,7 @@
 			continue;
 		}
 
-		group = find_idlest_group(sd, p, cpu, sd_flag);
+		group = find_idlest_group(sd, p, cpu);
 		if (!group) {
 			sd = sd->child;
 			continue;
@@ -5937,10 +6106,12 @@
 		bool idle = true;
 
 		for_each_cpu(cpu, cpu_smt_mask(core)) {
-			__cpumask_clear_cpu(cpu, cpus);
-			if (!available_idle_cpu(cpu))
+			if (!available_idle_cpu(cpu)) {
 				idle = false;
+				break;
+			}
 		}
+		cpumask_andnot(cpus, cpus, cpu_smt_mask(core));
 
 		if (idle)
 			return core;
@@ -5959,7 +6130,7 @@
  */
 static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
 {
-	int cpu, si_cpu = -1;
+	int cpu;
 
 	if (!static_branch_likely(&sched_smt_present))
 		return -1;
@@ -5968,13 +6139,11 @@
 		if (!cpumask_test_cpu(cpu, p->cpus_ptr) ||
 		    !cpumask_test_cpu(cpu, sched_domain_span(sd)))
 			continue;
-		if (available_idle_cpu(cpu))
+		if (available_idle_cpu(cpu) || sched_idle_cpu(cpu))
 			return cpu;
-		if (si_cpu == -1 && sched_idle_cpu(cpu))
-			si_cpu = cpu;
 	}
 
-	return si_cpu;
+	return -1;
 }
 
 #else /* CONFIG_SCHED_SMT */
@@ -6001,10 +6170,9 @@
 	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
 	struct sched_domain *this_sd;
 	u64 avg_cost, avg_idle;
-	u64 time, cost;
-	s64 delta;
+	u64 time;
 	int this = smp_processor_id();
-	int cpu, nr = INT_MAX, si_cpu = -1;
+	int cpu, nr = INT_MAX;
 
 	this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
 	if (!this_sd)
@@ -6034,46 +6202,113 @@
 
 	for_each_cpu_wrap(cpu, cpus, target) {
 		if (!--nr)
-			return si_cpu;
-		if (available_idle_cpu(cpu))
+			return -1;
+		if (available_idle_cpu(cpu) || sched_idle_cpu(cpu))
 			break;
-		if (si_cpu == -1 && sched_idle_cpu(cpu))
-			si_cpu = cpu;
 	}
 
 	time = cpu_clock(this) - time;
-	cost = this_sd->avg_scan_cost;
-	delta = (s64)(time - cost) / 8;
-	this_sd->avg_scan_cost += delta;
+	update_avg(&this_sd->avg_scan_cost, time);
 
 	return cpu;
 }
 
 /*
+ * Scan the asym_capacity domain for idle CPUs; pick the first idle one on which
+ * the task fits. If no CPU is big enough, but there are idle ones, try to
+ * maximize capacity.
+ */
+static int
+select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
+{
+	unsigned long task_util, best_cap = 0;
+	int cpu, best_cpu = -1;
+	struct cpumask *cpus;
+
+	cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
+	cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
+
+	task_util = uclamp_task_util(p);
+
+	for_each_cpu_wrap(cpu, cpus, target) {
+		unsigned long cpu_cap = capacity_of(cpu);
+
+		if (!available_idle_cpu(cpu) && !sched_idle_cpu(cpu))
+			continue;
+		if (fits_capacity(task_util, cpu_cap))
+			return cpu;
+
+		if (cpu_cap > best_cap) {
+			best_cap = cpu_cap;
+			best_cpu = cpu;
+		}
+	}
+
+	return best_cpu;
+}
+
+static inline bool asym_fits_capacity(int task_util, int cpu)
+{
+	if (static_branch_unlikely(&sched_asym_cpucapacity))
+		return fits_capacity(task_util, capacity_of(cpu));
+
+	return true;
+}
+
+/*
  * Try and locate an idle core/thread in the LLC cache domain.
  */
 static int select_idle_sibling(struct task_struct *p, int prev, int target)
 {
 	struct sched_domain *sd;
+	unsigned long task_util;
 	int i, recent_used_cpu;
 
-	if (available_idle_cpu(target) || sched_idle_cpu(target))
+	/*
+	 * On asymmetric system, update task utilization because we will check
+	 * that the task fits with cpu's capacity.
+	 */
+	if (static_branch_unlikely(&sched_asym_cpucapacity)) {
+		sync_entity_load_avg(&p->se);
+		task_util = uclamp_task_util(p);
+	}
+
+	if ((available_idle_cpu(target) || sched_idle_cpu(target)) &&
+	    asym_fits_capacity(task_util, target))
 		return target;
 
 	/*
 	 * If the previous CPU is cache affine and idle, don't be stupid:
 	 */
 	if (prev != target && cpus_share_cache(prev, target) &&
-	    (available_idle_cpu(prev) || sched_idle_cpu(prev)))
+	    (available_idle_cpu(prev) || sched_idle_cpu(prev)) &&
+	    asym_fits_capacity(task_util, prev))
 		return prev;
 
+	/*
+	 * Allow a per-cpu kthread to stack with the wakee if the
+	 * kworker thread and the tasks previous CPUs are the same.
+	 * The assumption is that the wakee queued work for the
+	 * per-cpu kthread that is now complete and the wakeup is
+	 * essentially a sync wakeup. An obvious example of this
+	 * pattern is IO completions.
+	 */
+	if (is_per_cpu_kthread(current) &&
+	    in_task() &&
+	    prev == smp_processor_id() &&
+	    this_rq()->nr_running <= 1 &&
+	    asym_fits_capacity(task_util, prev)) {
+		return prev;
+	}
+
 	/* Check a recently used CPU as a potential idle candidate: */
 	recent_used_cpu = p->recent_used_cpu;
 	if (recent_used_cpu != prev &&
 	    recent_used_cpu != target &&
 	    cpus_share_cache(recent_used_cpu, target) &&
 	    (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
-	    cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) {
+	    cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) &&
+	    asym_fits_capacity(task_util, recent_used_cpu)) {
 		/*
 		 * Replace recent_used_cpu with prev as it is a potential
 		 * candidate for the next wake:
@@ -6082,6 +6317,26 @@
 		return recent_used_cpu;
 	}
 
+	/*
+	 * For asymmetric CPU capacity systems, our domain of interest is
+	 * sd_asym_cpucapacity rather than sd_llc.
+	 */
+	if (static_branch_unlikely(&sched_asym_cpucapacity)) {
+		sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target));
+		/*
+		 * On an asymmetric CPU capacity system where an exclusive
+		 * cpuset defines a symmetric island (i.e. one unique
+		 * capacity_orig value through the cpuset), the key will be set
+		 * but the CPUs within that cpuset will not have a domain with
+		 * SD_ASYM_CPUCAPACITY. These should follow the usual symmetric
+		 * capacity path.
+		 */
+		if (sd) {
+			i = select_idle_capacity(p, sd, target);
+			return ((unsigned)i < nr_cpumask_bits) ? i : target;
+		}
+	}
+
 	sd = rcu_dereference(per_cpu(sd_llc, target));
 	if (!sd)
 		return target;
@@ -6243,33 +6498,6 @@
 }
 
 /*
- * Disable WAKE_AFFINE in the case where task @p doesn't fit in the
- * capacity of either the waking CPU @cpu or the previous CPU @prev_cpu.
- *
- * In that case WAKE_AFFINE doesn't make sense and we'll let
- * BALANCE_WAKE sort things out.
- */
-static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
-{
-	long min_cap, max_cap;
-
-	if (!static_branch_unlikely(&sched_asym_cpucapacity))
-		return 0;
-
-	min_cap = min(capacity_orig_of(prev_cpu), capacity_orig_of(cpu));
-	max_cap = cpu_rq(cpu)->rd->max_cpu_capacity;
-
-	/* Minimum capacity is close to max, no need to abort wake_affine */
-	if (max_cap - min_cap < max_cap >> 3)
-		return 0;
-
-	/* Bring task utilization in sync with prev_cpu */
-	sync_entity_load_avg(&p->se);
-
-	return !task_fits_capacity(p, min_cap);
-}
-
-/*
  * Predicts what cpu_util(@cpu) would return if @p was migrated (and enqueued)
  * to @dst_cpu.
  */
@@ -6356,7 +6584,7 @@
 		max_util = max(max_util, cpu_util);
 	}
 
-	return em_pd_energy(pd->em_pd, max_util, sum_util);
+	return em_cpu_energy(pd->em_pd, max_util, sum_util);
 }
 
 /*
@@ -6439,9 +6667,19 @@
 			if (!cpumask_test_cpu(cpu, p->cpus_ptr))
 				continue;
 
-			/* Skip CPUs that will be overutilized. */
 			util = cpu_util_next(cpu, p, cpu);
 			cpu_cap = capacity_of(cpu);
+			spare_cap = cpu_cap;
+			lsub_positive(&spare_cap, util);
+
+			/*
+			 * Skip CPUs that cannot satisfy the capacity request.
+			 * IOW, placing the task there would make the CPU
+			 * overutilized. Take uclamp into account to see how
+			 * much capacity we can get out of the CPU; this is
+			 * aligned with schedutil_cpu_util().
+			 */
+			util = uclamp_rq_util_with(cpu_rq(cpu), util, p);
 			if (!fits_capacity(util, cpu_cap))
 				continue;
 
@@ -6456,7 +6694,6 @@
 			 * Find the CPU with the maximum spare capacity in
 			 * the performance domain
 			 */
-			spare_cap = cpu_cap - util;
 			if (spare_cap > max_spare_cap) {
 				max_spare_cap = spare_cap;
 				max_spare_cap_cpu = cpu;
@@ -6525,15 +6762,11 @@
 			new_cpu = prev_cpu;
 		}
 
-		want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) &&
-			      cpumask_test_cpu(cpu, p->cpus_ptr);
+		want_affine = !wake_wide(p) && cpumask_test_cpu(cpu, p->cpus_ptr);
 	}
 
 	rcu_read_lock();
 	for_each_domain(cpu, tmp) {
-		if (!(tmp->flags & SD_LOAD_BALANCE))
-			break;
-
 		/*
 		 * If both 'cpu' and 'prev_cpu' are part of this domain,
 		 * cpu is a valid SD_WAKE_AFFINE target.
@@ -6813,7 +7046,7 @@
 		set_last_buddy(se);
 }
 
-static struct task_struct *
+struct task_struct *
 pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
 	struct cfs_rq *cfs_rq = &rq->cfs;
@@ -6957,6 +7190,11 @@
 	return NULL;
 }
 
+static struct task_struct *__pick_next_task_fair(struct rq *rq)
+{
+	return pick_next_task_fair(rq, NULL, NULL);
+}
+
 /*
  * Account for a descheduled task:
  */
@@ -7007,7 +7245,7 @@
 	set_skip_buddy(se);
 }
 
-static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preempt)
+static bool yield_to_task_fair(struct rq *rq, struct task_struct *p)
 {
 	struct sched_entity *se = &p->se;
 
@@ -7146,11 +7384,49 @@
 
 enum fbq_type { regular, remote, all };
 
+/*
+ * 'group_type' describes the group of CPUs at the moment of load balancing.
+ *
+ * The enum is ordered by pulling priority, with the group with lowest priority
+ * first so the group_type can simply be compared when selecting the busiest
+ * group. See update_sd_pick_busiest().
+ */
 enum group_type {
-	group_other = 0,
+	/* The group has spare capacity that can be used to run more tasks.  */
+	group_has_spare = 0,
+	/*
+	 * The group is fully used and the tasks don't compete for more CPU
+	 * cycles. Nevertheless, some tasks might wait before running.
+	 */
+	group_fully_busy,
+	/*
+	 * SD_ASYM_CPUCAPACITY only: One task doesn't fit with CPU's capacity
+	 * and must be migrated to a more powerful CPU.
+	 */
 	group_misfit_task,
+	/*
+	 * SD_ASYM_PACKING only: One local CPU with higher capacity is available,
+	 * and the task should be migrated to it instead of running on the
+	 * current CPU.
+	 */
+	group_asym_packing,
+	/*
+	 * The tasks' affinity constraints previously prevented the scheduler
+	 * from balancing the load across the system.
+	 */
 	group_imbalanced,
-	group_overloaded,
+	/*
+	 * The CPU is overloaded and can't provide expected CPU cycles to all
+	 * tasks.
+	 */
+	group_overloaded
+};
+
+enum migration_type {
+	migrate_load = 0,
+	migrate_util,
+	migrate_task,
+	migrate_misfit
 };
 
 #define LBF_ALL_PINNED	0x01
@@ -7183,7 +7459,7 @@
 	unsigned int		loop_max;
 
 	enum fbq_type		fbq_type;
-	enum group_type		src_grp_type;
+	enum migration_type	migration_type;
 	struct list_head	tasks;
 };
 
@@ -7202,6 +7478,10 @@
 	if (unlikely(task_has_idle_policy(p)))
 		return 0;
 
+	/* SMT siblings share cache */
+	if (env->sd->flags & SD_SHARE_CPUCAPACITY)
+		return 0;
+
 	/*
 	 * Buddy candidates are cache hot:
 	 */
@@ -7410,7 +7690,7 @@
 static const unsigned int sched_nr_migrate_break = 32;
 
 /*
- * detach_tasks() -- tries to detach up to imbalance runnable load from
+ * detach_tasks() -- tries to detach up to imbalance load/util/tasks from
  * busiest_rq, as part of a balancing operation within domain "sd".
  *
  * Returns number of detached tasks if successful and 0 otherwise.
@@ -7418,8 +7698,8 @@
 static int detach_tasks(struct lb_env *env)
 {
 	struct list_head *tasks = &env->src_rq->cfs_tasks;
+	unsigned long util, load;
 	struct task_struct *p;
-	unsigned long load;
 	int detached = 0;
 
 	lockdep_assert_held(&env->src_rq->lock);
@@ -7452,27 +7732,59 @@
 		if (!can_migrate_task(p, env))
 			goto next;
 
-		/*
-		 * Depending of the number of CPUs and tasks and the
-		 * cgroup hierarchy, task_h_load() can return a null
-		 * value. Make sure that env->imbalance decreases
-		 * otherwise detach_tasks() will stop only after
-		 * detaching up to loop_max tasks.
-		 */
-		load = max_t(unsigned long, task_h_load(p), 1);
+		switch (env->migration_type) {
+		case migrate_load:
+			/*
+			 * Depending of the number of CPUs and tasks and the
+			 * cgroup hierarchy, task_h_load() can return a null
+			 * value. Make sure that env->imbalance decreases
+			 * otherwise detach_tasks() will stop only after
+			 * detaching up to loop_max tasks.
+			 */
+			load = max_t(unsigned long, task_h_load(p), 1);
 
+			if (sched_feat(LB_MIN) &&
+			    load < 16 && !env->sd->nr_balance_failed)
+				goto next;
 
-		if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed)
-			goto next;
+			/*
+			 * Make sure that we don't migrate too much load.
+			 * Nevertheless, let relax the constraint if
+			 * scheduler fails to find a good waiting task to
+			 * migrate.
+			 */
+			if (shr_bound(load, env->sd->nr_balance_failed) > env->imbalance)
+				goto next;
 
-		if ((load / 2) > env->imbalance)
-			goto next;
+			env->imbalance -= load;
+			break;
+
+		case migrate_util:
+			util = task_util_est(p);
+
+			if (util > env->imbalance)
+				goto next;
+
+			env->imbalance -= util;
+			break;
+
+		case migrate_task:
+			env->imbalance--;
+			break;
+
+		case migrate_misfit:
+			/* This is not a misfit task */
+			if (task_fits_capacity(p, capacity_of(env->src_cpu)))
+				goto next;
+
+			env->imbalance = 0;
+			break;
+		}
 
 		detach_task(p, env);
 		list_add(&p->se.group_node, &env->tasks);
 
 		detached++;
-		env->imbalance -= load;
 
 #ifdef CONFIG_PREEMPTION
 		/*
@@ -7486,7 +7798,7 @@
 
 		/*
 		 * We only want to steal up to the prescribed amount of
-		 * runnable load.
+		 * load/util/tasks.
 		 */
 		if (env->imbalance <= 0)
 			break;
@@ -7575,6 +7887,9 @@
 	if (READ_ONCE(rq->avg_dl.util_avg))
 		return true;
 
+	if (thermal_load_avg(rq))
+		return true;
+
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 	if (READ_ONCE(rq->avg_irq.util_avg))
 		return true;
@@ -7600,6 +7915,7 @@
 {
 	const struct sched_class *curr_class;
 	u64 now = rq_clock_pelt(rq);
+	unsigned long thermal_pressure;
 	bool decayed;
 
 	/*
@@ -7608,8 +7924,11 @@
 	 */
 	curr_class = rq->curr->sched_class;
 
+	thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq));
+
 	decayed = update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) |
 		  update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) |
+		  update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure) |
 		  update_irq_load_avg(rq, 0);
 
 	if (others_have_blocked(rq))
@@ -7631,7 +7950,7 @@
 	if (cfs_rq->avg.util_sum)
 		return false;
 
-	if (cfs_rq->avg.runnable_load_sum)
+	if (cfs_rq->avg.runnable_sum)
 		return false;
 
 	return true;
@@ -7651,7 +7970,7 @@
 		struct sched_entity *se;
 
 		if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq)) {
-			update_tg_load_avg(cfs_rq, 0);
+			update_tg_load_avg(cfs_rq);
 
 			if (cfs_rq == &rq->cfs)
 				decayed = true;
@@ -7768,14 +8087,15 @@
 struct sg_lb_stats {
 	unsigned long avg_load; /*Avg load across the CPUs of the group */
 	unsigned long group_load; /* Total load over the CPUs of the group */
-	unsigned long load_per_task;
 	unsigned long group_capacity;
-	unsigned long group_util; /* Total utilization of the group */
-	unsigned int sum_nr_running; /* Nr tasks running in the group */
+	unsigned long group_util; /* Total utilization over the CPUs of the group */
+	unsigned long group_runnable; /* Total runnable time over the CPUs of the group */
+	unsigned int sum_nr_running; /* Nr of tasks running in the group */
+	unsigned int sum_h_nr_running; /* Nr of CFS tasks running in the group */
 	unsigned int idle_cpus;
 	unsigned int group_weight;
 	enum group_type group_type;
-	int group_no_capacity;
+	unsigned int group_asym_packing; /* Tasks should be moved to preferred CPU */
 	unsigned long group_misfit_task_load; /* A CPU has a task too big for its capacity */
 #ifdef CONFIG_NUMA_BALANCING
 	unsigned int nr_numa_running;
@@ -7790,10 +8110,10 @@
 struct sd_lb_stats {
 	struct sched_group *busiest;	/* Busiest group in this sd */
 	struct sched_group *local;	/* Local group in this sd */
-	unsigned long total_running;
 	unsigned long total_load;	/* Total load of all groups in sd */
 	unsigned long total_capacity;	/* Total capacity of all groups in sd */
 	unsigned long avg_load;	/* Average load across all groups in sd */
+	unsigned int prefer_sibling; /* tasks should go to sibling first */
 
 	struct sg_lb_stats busiest_stat;/* Statistics of the busiest group */
 	struct sg_lb_stats local_stat;	/* Statistics of the local group */
@@ -7804,24 +8124,23 @@
 	/*
 	 * Skimp on the clearing to avoid duplicate work. We can avoid clearing
 	 * local_stat because update_sg_lb_stats() does a full clear/assignment.
-	 * We must however clear busiest_stat::avg_load because
-	 * update_sd_pick_busiest() reads this before assignment.
+	 * We must however set busiest_stat::group_type and
+	 * busiest_stat::idle_cpus to the worst busiest group because
+	 * update_sd_pick_busiest() reads these before assignment.
 	 */
 	*sds = (struct sd_lb_stats){
 		.busiest = NULL,
 		.local = NULL,
-		.total_running = 0UL,
 		.total_load = 0UL,
 		.total_capacity = 0UL,
 		.busiest_stat = {
-			.avg_load = 0UL,
-			.sum_nr_running = 0,
-			.group_type = group_other,
+			.idle_cpus = UINT_MAX,
+			.group_type = group_has_spare,
 		},
 	};
 }
 
-static unsigned long scale_rt_capacity(struct sched_domain *sd, int cpu)
+static unsigned long scale_rt_capacity(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long max = arch_scale_cpu_capacity(cpu);
@@ -7833,8 +8152,15 @@
 	if (unlikely(irq >= max))
 		return 1;
 
+	/*
+	 * avg_rt.util_avg and avg_dl.util_avg track binary signals
+	 * (running and not running) with weights 0 and 1024 respectively.
+	 * avg_thermal.load_avg tracks thermal pressure and the weighted
+	 * average uses the actual delta max capacity(load).
+	 */
 	used = READ_ONCE(rq->avg_rt.util_avg);
 	used += READ_ONCE(rq->avg_dl.util_avg);
+	used += thermal_load_avg(rq);
 
 	if (unlikely(used >= max))
 		return 1;
@@ -7846,7 +8172,7 @@
 
 static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 {
-	unsigned long capacity = scale_rt_capacity(sd, 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);
@@ -7855,6 +8181,8 @@
 		capacity = 1;
 
 	cpu_rq(cpu)->cpu_capacity = capacity;
+	trace_sched_cpu_capacity_tp(cpu_rq(cpu));
+
 	sdg->sgc->capacity = capacity;
 	sdg->sgc->min_capacity = capacity;
 	sdg->sgc->max_capacity = capacity;
@@ -7887,29 +8215,11 @@
 		 */
 
 		for_each_cpu(cpu, sched_group_span(sdg)) {
-			struct sched_group_capacity *sgc;
-			struct rq *rq = cpu_rq(cpu);
+			unsigned long cpu_cap = capacity_of(cpu);
 
-			/*
-			 * build_sched_domains() -> init_sched_groups_capacity()
-			 * gets here before we've attached the domains to the
-			 * runqueues.
-			 *
-			 * Use capacity_of(), which is set irrespective of domains
-			 * in update_cpu_capacity().
-			 *
-			 * This avoids capacity from being 0 and
-			 * causing divide-by-zero issues on boot.
-			 */
-			if (unlikely(!rq->sd)) {
-				capacity += capacity_of(cpu);
-			} else {
-				sgc = rq->sd->groups->sgc;
-				capacity += sgc->capacity;
-			}
-
-			min_capacity = min(capacity, min_capacity);
-			max_capacity = max(capacity, max_capacity);
+			capacity += cpu_cap;
+			min_capacity = min(cpu_cap, min_capacity);
+			max_capacity = max(cpu_cap, max_capacity);
 		}
 	} else  {
 		/*
@@ -8004,13 +8314,17 @@
  * any benefit for the load balance.
  */
 static inline bool
-group_has_capacity(struct lb_env *env, struct sg_lb_stats *sgs)
+group_has_capacity(unsigned int imbalance_pct, struct sg_lb_stats *sgs)
 {
 	if (sgs->sum_nr_running < sgs->group_weight)
 		return true;
 
+	if ((sgs->group_capacity * imbalance_pct) <
+			(sgs->group_runnable * 100))
+		return false;
+
 	if ((sgs->group_capacity * 100) >
-			(sgs->group_util * env->sd->imbalance_pct))
+			(sgs->group_util * imbalance_pct))
 		return true;
 
 	return false;
@@ -8025,13 +8339,17 @@
  *  false.
  */
 static inline bool
-group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs)
+group_is_overloaded(unsigned int imbalance_pct, struct sg_lb_stats *sgs)
 {
 	if (sgs->sum_nr_running <= sgs->group_weight)
 		return false;
 
 	if ((sgs->group_capacity * 100) <
-			(sgs->group_util * env->sd->imbalance_pct))
+			(sgs->group_util * imbalance_pct))
+		return true;
+
+	if ((sgs->group_capacity * imbalance_pct) <
+			(sgs->group_runnable * 100))
 		return true;
 
 	return false;
@@ -8058,19 +8376,26 @@
 }
 
 static inline enum
-group_type group_classify(struct sched_group *group,
+group_type group_classify(unsigned int imbalance_pct,
+			  struct sched_group *group,
 			  struct sg_lb_stats *sgs)
 {
-	if (sgs->group_no_capacity)
+	if (group_is_overloaded(imbalance_pct, sgs))
 		return group_overloaded;
 
 	if (sg_imbalanced(group))
 		return group_imbalanced;
 
+	if (sgs->group_asym_packing)
+		return group_asym_packing;
+
 	if (sgs->group_misfit_task_load)
 		return group_misfit_task;
 
-	return group_other;
+	if (!group_has_capacity(imbalance_pct, sgs))
+		return group_fully_busy;
+
+	return group_has_spare;
 }
 
 static bool update_nohz_stats(struct rq *rq, bool force)
@@ -8107,21 +8432,26 @@
 				      struct sg_lb_stats *sgs,
 				      int *sg_status)
 {
-	int i, nr_running;
+	int i, nr_running, local_group;
 
 	memset(sgs, 0, sizeof(*sgs));
 
+	local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(group));
+
 	for_each_cpu_and(i, sched_group_span(group), env->cpus) {
 		struct rq *rq = cpu_rq(i);
 
 		if ((env->flags & LBF_NOHZ_STATS) && update_nohz_stats(rq, false))
 			env->flags |= LBF_NOHZ_AGAIN;
 
-		sgs->group_load += cpu_runnable_load(rq);
+		sgs->group_load += cpu_load(rq);
 		sgs->group_util += cpu_util(i);
-		sgs->sum_nr_running += rq->cfs.h_nr_running;
+		sgs->group_runnable += cpu_runnable(rq);
+		sgs->sum_h_nr_running += rq->cfs.h_nr_running;
 
 		nr_running = rq->nr_running;
+		sgs->sum_nr_running += nr_running;
+
 		if (nr_running > 1)
 			*sg_status |= SG_OVERLOAD;
 
@@ -8135,9 +8465,16 @@
 		/*
 		 * No need to call idle_cpu() if nr_running is not 0
 		 */
-		if (!nr_running && idle_cpu(i))
+		if (!nr_running && idle_cpu(i)) {
 			sgs->idle_cpus++;
+			/* Idle cpu can't have misfit task */
+			continue;
+		}
 
+		if (local_group)
+			continue;
+
+		/* Check for a misfit task on the cpu */
 		if (env->sd->flags & SD_ASYM_CPUCAPACITY &&
 		    sgs->group_misfit_task_load < rq->misfit_task_load) {
 			sgs->group_misfit_task_load = rq->misfit_task_load;
@@ -8145,17 +8482,24 @@
 		}
 	}
 
-	/* Adjust by relative CPU capacity of the group */
-	sgs->group_capacity = group->sgc->capacity;
-	sgs->avg_load = (sgs->group_load*SCHED_CAPACITY_SCALE) / sgs->group_capacity;
+	/* Check if dst CPU is idle and preferred to this group */
+	if (env->sd->flags & SD_ASYM_PACKING &&
+	    env->idle != CPU_NOT_IDLE &&
+	    sgs->sum_h_nr_running &&
+	    sched_asym_prefer(env->dst_cpu, group->asym_prefer_cpu)) {
+		sgs->group_asym_packing = 1;
+	}
 
-	if (sgs->sum_nr_running)
-		sgs->load_per_task = sgs->group_load / sgs->sum_nr_running;
+	sgs->group_capacity = group->sgc->capacity;
 
 	sgs->group_weight = group->group_weight;
 
-	sgs->group_no_capacity = group_is_overloaded(env, sgs);
-	sgs->group_type = group_classify(group, sgs);
+	sgs->group_type = group_classify(env->sd->imbalance_pct, group, sgs);
+
+	/* Computing avg_load makes sense only when group is overloaded */
+	if (sgs->group_type == group_overloaded)
+		sgs->avg_load = (sgs->group_load * SCHED_CAPACITY_SCALE) /
+				sgs->group_capacity;
 }
 
 /**
@@ -8178,6 +8522,10 @@
 {
 	struct sg_lb_stats *busiest = &sds->busiest_stat;
 
+	/* Make sure that there is at least one task to pull */
+	if (!sgs->sum_h_nr_running)
+		return false;
+
 	/*
 	 * Don't try to pull misfit tasks we can't help.
 	 * We can use max_capacity here as reduction in capacity on some
@@ -8186,7 +8534,7 @@
 	 */
 	if (sgs->group_type == group_misfit_task &&
 	    (!group_smaller_max_cpu_capacity(sg, sds->local) ||
-	     !group_has_capacity(env, &sds->local_stat)))
+	     sds->local_stat.group_type != group_has_spare))
 		return false;
 
 	if (sgs->group_type > busiest->group_type)
@@ -8195,62 +8543,92 @@
 	if (sgs->group_type < busiest->group_type)
 		return false;
 
-	if (sgs->avg_load <= busiest->avg_load)
+	/*
+	 * The candidate and the current busiest group are the same type of
+	 * group. Let check which one is the busiest according to the type.
+	 */
+
+	switch (sgs->group_type) {
+	case group_overloaded:
+		/* Select the overloaded group with highest avg_load. */
+		if (sgs->avg_load <= busiest->avg_load)
+			return false;
+		break;
+
+	case group_imbalanced:
+		/*
+		 * Select the 1st imbalanced group as we don't have any way to
+		 * choose one more than another.
+		 */
 		return false;
 
-	if (!(env->sd->flags & SD_ASYM_CPUCAPACITY))
-		goto asym_packing;
-
-	/*
-	 * Candidate sg has no more than one task per CPU and
-	 * has higher per-CPU capacity. Migrating tasks to less
-	 * capable CPUs may harm throughput. Maximize throughput,
-	 * power/energy consequences are not considered.
-	 */
-	if (sgs->sum_nr_running <= sgs->group_weight &&
-	    group_smaller_min_cpu_capacity(sds->local, sg))
-		return false;
-
-	/*
-	 * If we have more than one misfit sg go with the biggest misfit.
-	 */
-	if (sgs->group_type == group_misfit_task &&
-	    sgs->group_misfit_task_load < busiest->group_misfit_task_load)
-		return false;
-
-asym_packing:
-	/* This is the busiest node in its class. */
-	if (!(env->sd->flags & SD_ASYM_PACKING))
-		return true;
-
-	/* No ASYM_PACKING if target CPU is already busy */
-	if (env->idle == CPU_NOT_IDLE)
-		return true;
-	/*
-	 * ASYM_PACKING needs to move all the work to the highest
-	 * prority CPUs in the group, therefore mark all groups
-	 * of lower priority than ourself as busy.
-	 */
-	if (sgs->sum_nr_running &&
-	    sched_asym_prefer(env->dst_cpu, sg->asym_prefer_cpu)) {
-		if (!sds->busiest)
-			return true;
-
+	case group_asym_packing:
 		/* Prefer to move from lowest priority CPU's work */
-		if (sched_asym_prefer(sds->busiest->asym_prefer_cpu,
-				      sg->asym_prefer_cpu))
-			return true;
+		if (sched_asym_prefer(sg->asym_prefer_cpu, sds->busiest->asym_prefer_cpu))
+			return false;
+		break;
+
+	case group_misfit_task:
+		/*
+		 * If we have more than one misfit sg go with the biggest
+		 * misfit.
+		 */
+		if (sgs->group_misfit_task_load < busiest->group_misfit_task_load)
+			return false;
+		break;
+
+	case group_fully_busy:
+		/*
+		 * Select the fully busy group with highest avg_load. In
+		 * theory, there is no need to pull task from such kind of
+		 * group because tasks have all compute capacity that they need
+		 * but we can still improve the overall throughput by reducing
+		 * contention when accessing shared HW resources.
+		 *
+		 * XXX for now avg_load is not computed and always 0 so we
+		 * select the 1st one.
+		 */
+		if (sgs->avg_load <= busiest->avg_load)
+			return false;
+		break;
+
+	case group_has_spare:
+		/*
+		 * Select not overloaded group with lowest number of idle cpus
+		 * and highest number of running tasks. We could also compare
+		 * the spare capacity which is more stable but it can end up
+		 * that the group has less spare capacity but finally more idle
+		 * CPUs which means less opportunity to pull tasks.
+		 */
+		if (sgs->idle_cpus > busiest->idle_cpus)
+			return false;
+		else if ((sgs->idle_cpus == busiest->idle_cpus) &&
+			 (sgs->sum_nr_running <= busiest->sum_nr_running))
+			return false;
+
+		break;
 	}
 
-	return false;
+	/*
+	 * Candidate sg has no more than one task per CPU and has higher
+	 * per-CPU capacity. Migrating tasks to less capable CPUs may harm
+	 * throughput. Maximize throughput, power/energy consequences are not
+	 * considered.
+	 */
+	if ((env->sd->flags & SD_ASYM_CPUCAPACITY) &&
+	    (sgs->group_type <= group_fully_busy) &&
+	    (group_smaller_min_cpu_capacity(sds->local, sg)))
+		return false;
+
+	return true;
 }
 
 #ifdef CONFIG_NUMA_BALANCING
 static inline enum fbq_type fbq_classify_group(struct sg_lb_stats *sgs)
 {
-	if (sgs->sum_nr_running > sgs->nr_numa_running)
+	if (sgs->sum_h_nr_running > sgs->nr_numa_running)
 		return regular;
-	if (sgs->sum_nr_running > sgs->nr_preferred_running)
+	if (sgs->sum_h_nr_running > sgs->nr_preferred_running)
 		return remote;
 	return all;
 }
@@ -8275,18 +8653,323 @@
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
+
+struct sg_lb_stats;
+
+/*
+ * task_running_on_cpu - return 1 if @p is running on @cpu.
+ */
+
+static unsigned int task_running_on_cpu(int cpu, struct task_struct *p)
+{
+	/* Task has no contribution or is new */
+	if (cpu != task_cpu(p) || !READ_ONCE(p->se.avg.last_update_time))
+		return 0;
+
+	if (task_on_rq_queued(p))
+		return 1;
+
+	return 0;
+}
+
+/**
+ * idle_cpu_without - would a given CPU be idle without p ?
+ * @cpu: the processor on which idleness is tested.
+ * @p: task which should be ignored.
+ *
+ * Return: 1 if the CPU would be idle. 0 otherwise.
+ */
+static int idle_cpu_without(int cpu, struct task_struct *p)
+{
+	struct rq *rq = cpu_rq(cpu);
+
+	if (rq->curr != rq->idle && rq->curr != p)
+		return 0;
+
+	/*
+	 * rq->nr_running can't be used but an updated version without the
+	 * impact of p on cpu must be used instead. The updated nr_running
+	 * be computed and tested before calling idle_cpu_without().
+	 */
+
+#ifdef CONFIG_SMP
+	if (rq->ttwu_pending)
+		return 0;
+#endif
+
+	return 1;
+}
+
+/*
+ * update_sg_wakeup_stats - Update sched_group's statistics for wakeup.
+ * @sd: The sched_domain level to look for idlest group.
+ * @group: sched_group whose statistics are to be updated.
+ * @sgs: variable to hold the statistics for this group.
+ * @p: The task for which we look for the idlest group/CPU.
+ */
+static inline void update_sg_wakeup_stats(struct sched_domain *sd,
+					  struct sched_group *group,
+					  struct sg_lb_stats *sgs,
+					  struct task_struct *p)
+{
+	int i, nr_running;
+
+	memset(sgs, 0, sizeof(*sgs));
+
+	for_each_cpu(i, sched_group_span(group)) {
+		struct rq *rq = cpu_rq(i);
+		unsigned int local;
+
+		sgs->group_load += cpu_load_without(rq, p);
+		sgs->group_util += cpu_util_without(i, p);
+		sgs->group_runnable += cpu_runnable_without(rq, p);
+		local = task_running_on_cpu(i, p);
+		sgs->sum_h_nr_running += rq->cfs.h_nr_running - local;
+
+		nr_running = rq->nr_running - local;
+		sgs->sum_nr_running += nr_running;
+
+		/*
+		 * No need to call idle_cpu_without() if nr_running is not 0
+		 */
+		if (!nr_running && idle_cpu_without(i, p))
+			sgs->idle_cpus++;
+
+	}
+
+	/* Check if task fits in the group */
+	if (sd->flags & SD_ASYM_CPUCAPACITY &&
+	    !task_fits_capacity(p, group->sgc->max_capacity)) {
+		sgs->group_misfit_task_load = 1;
+	}
+
+	sgs->group_capacity = group->sgc->capacity;
+
+	sgs->group_weight = group->group_weight;
+
+	sgs->group_type = group_classify(sd->imbalance_pct, group, sgs);
+
+	/*
+	 * Computing avg_load makes sense only when group is fully busy or
+	 * overloaded
+	 */
+	if (sgs->group_type == group_fully_busy ||
+		sgs->group_type == group_overloaded)
+		sgs->avg_load = (sgs->group_load * SCHED_CAPACITY_SCALE) /
+				sgs->group_capacity;
+}
+
+static bool update_pick_idlest(struct sched_group *idlest,
+			       struct sg_lb_stats *idlest_sgs,
+			       struct sched_group *group,
+			       struct sg_lb_stats *sgs)
+{
+	if (sgs->group_type < idlest_sgs->group_type)
+		return true;
+
+	if (sgs->group_type > idlest_sgs->group_type)
+		return false;
+
+	/*
+	 * The candidate and the current idlest group are the same type of
+	 * group. Let check which one is the idlest according to the type.
+	 */
+
+	switch (sgs->group_type) {
+	case group_overloaded:
+	case group_fully_busy:
+		/* Select the group with lowest avg_load. */
+		if (idlest_sgs->avg_load <= sgs->avg_load)
+			return false;
+		break;
+
+	case group_imbalanced:
+	case group_asym_packing:
+		/* Those types are not used in the slow wakeup path */
+		return false;
+
+	case group_misfit_task:
+		/* Select group with the highest max capacity */
+		if (idlest->sgc->max_capacity >= group->sgc->max_capacity)
+			return false;
+		break;
+
+	case group_has_spare:
+		/* Select group with most idle CPUs */
+		if (idlest_sgs->idle_cpus > sgs->idle_cpus)
+			return false;
+
+		/* Select group with lowest group_util */
+		if (idlest_sgs->idle_cpus == sgs->idle_cpus &&
+			idlest_sgs->group_util <= sgs->group_util)
+			return false;
+
+		break;
+	}
+
+	return true;
+}
+
+/*
+ * find_idlest_group() finds and returns the least busy CPU group within the
+ * domain.
+ *
+ * Assumes p is allowed on at least one CPU in sd.
+ */
+static struct sched_group *
+find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
+{
+	struct sched_group *idlest = NULL, *local = NULL, *group = sd->groups;
+	struct sg_lb_stats local_sgs, tmp_sgs;
+	struct sg_lb_stats *sgs;
+	unsigned long imbalance;
+	struct sg_lb_stats idlest_sgs = {
+			.avg_load = UINT_MAX,
+			.group_type = group_overloaded,
+	};
+
+	imbalance = scale_load_down(NICE_0_LOAD) *
+				(sd->imbalance_pct-100) / 100;
+
+	do {
+		int local_group;
+
+		/* Skip over this group if it has no CPUs allowed */
+		if (!cpumask_intersects(sched_group_span(group),
+					p->cpus_ptr))
+			continue;
+
+		local_group = cpumask_test_cpu(this_cpu,
+					       sched_group_span(group));
+
+		if (local_group) {
+			sgs = &local_sgs;
+			local = group;
+		} else {
+			sgs = &tmp_sgs;
+		}
+
+		update_sg_wakeup_stats(sd, group, sgs, p);
+
+		if (!local_group && update_pick_idlest(idlest, &idlest_sgs, group, sgs)) {
+			idlest = group;
+			idlest_sgs = *sgs;
+		}
+
+	} while (group = group->next, group != sd->groups);
+
+
+	/* There is no idlest group to push tasks to */
+	if (!idlest)
+		return NULL;
+
+	/* The local group has been skipped because of CPU affinity */
+	if (!local)
+		return idlest;
+
+	/*
+	 * If the local group is idler than the selected idlest group
+	 * don't try and push the task.
+	 */
+	if (local_sgs.group_type < idlest_sgs.group_type)
+		return NULL;
+
+	/*
+	 * If the local group is busier than the selected idlest group
+	 * try and push the task.
+	 */
+	if (local_sgs.group_type > idlest_sgs.group_type)
+		return idlest;
+
+	switch (local_sgs.group_type) {
+	case group_overloaded:
+	case group_fully_busy:
+		/*
+		 * When comparing groups across NUMA domains, it's possible for
+		 * the local domain to be very lightly loaded relative to the
+		 * remote domains but "imbalance" skews the comparison making
+		 * remote CPUs look much more favourable. When considering
+		 * cross-domain, add imbalance to the load on the remote node
+		 * and consider staying local.
+		 */
+
+		if ((sd->flags & SD_NUMA) &&
+		    ((idlest_sgs.avg_load + imbalance) >= local_sgs.avg_load))
+			return NULL;
+
+		/*
+		 * If the local group is less loaded than the selected
+		 * idlest group don't try and push any tasks.
+		 */
+		if (idlest_sgs.avg_load >= (local_sgs.avg_load + imbalance))
+			return NULL;
+
+		if (100 * local_sgs.avg_load <= sd->imbalance_pct * idlest_sgs.avg_load)
+			return NULL;
+		break;
+
+	case group_imbalanced:
+	case group_asym_packing:
+		/* Those type are not used in the slow wakeup path */
+		return NULL;
+
+	case group_misfit_task:
+		/* Select group with the highest max capacity */
+		if (local->sgc->max_capacity >= idlest->sgc->max_capacity)
+			return NULL;
+		break;
+
+	case group_has_spare:
+		if (sd->flags & SD_NUMA) {
+#ifdef CONFIG_NUMA_BALANCING
+			int idlest_cpu;
+			/*
+			 * If there is spare capacity at NUMA, try to select
+			 * the preferred node
+			 */
+			if (cpu_to_node(this_cpu) == p->numa_preferred_nid)
+				return NULL;
+
+			idlest_cpu = cpumask_first(sched_group_span(idlest));
+			if (cpu_to_node(idlest_cpu) == p->numa_preferred_nid)
+				return idlest;
+#endif
+			/*
+			 * Otherwise, keep the task on this node to stay close
+			 * its wakeup source and improve locality. If there is
+			 * a real need of migration, periodic load balance will
+			 * take care of it.
+			 */
+			if (local_sgs.idle_cpus)
+				return NULL;
+		}
+
+		/*
+		 * Select group with highest number of idle CPUs. We could also
+		 * compare the utilization which is more stable but it can end
+		 * up that the group has less spare capacity but finally more
+		 * idle CPUs which means more opportunity to run task.
+		 */
+		if (local_sgs.idle_cpus >= idlest_sgs.idle_cpus)
+			return NULL;
+		break;
+	}
+
+	return idlest;
+}
+
 /**
  * update_sd_lb_stats - Update sched_domain's statistics for load balancing.
  * @env: The load balancing environment.
  * @sds: variable to hold the statistics for this sched_domain.
  */
+
 static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sds)
 {
 	struct sched_domain *child = env->sd->child;
 	struct sched_group *sg = env->sd->groups;
 	struct sg_lb_stats *local = &sds->local_stat;
 	struct sg_lb_stats tmp_sgs;
-	bool prefer_sibling = child && child->flags & SD_PREFER_SIBLING;
 	int sg_status = 0;
 
 #ifdef CONFIG_NO_HZ_COMMON
@@ -8313,22 +8996,6 @@
 		if (local_group)
 			goto next_group;
 
-		/*
-		 * In case the child domain prefers tasks go to siblings
-		 * first, lower the sg capacity so that we'll try
-		 * and move all the excess tasks away. We lower the capacity
-		 * of a group only if the local group has the capacity to fit
-		 * these excess tasks. The extra check prevents the case where
-		 * you always pull from the heaviest group when it is already
-		 * under-utilized (possible with a large weight task outweighs
-		 * the tasks on the system).
-		 */
-		if (prefer_sibling && sds->local &&
-		    group_has_capacity(env, local) &&
-		    (sgs->sum_nr_running > local->sum_nr_running + 1)) {
-			sgs->group_no_capacity = 1;
-			sgs->group_type = group_classify(sg, sgs);
-		}
 
 		if (update_sd_pick_busiest(env, sds, sg, sgs)) {
 			sds->busiest = sg;
@@ -8337,13 +9004,15 @@
 
 next_group:
 		/* Now, start updating sd_lb_stats */
-		sds->total_running += sgs->sum_nr_running;
 		sds->total_load += sgs->group_load;
 		sds->total_capacity += sgs->group_capacity;
 
 		sg = sg->next;
 	} while (sg != env->sd->groups);
 
+	/* Tag domain that child domain prefers tasks go to siblings first */
+	sds->prefer_sibling = child && child->flags & SD_PREFER_SIBLING;
+
 #ifdef CONFIG_NO_HZ_COMMON
 	if ((env->flags & LBF_NOHZ_AGAIN) &&
 	    cpumask_subset(nohz.idle_cpus_mask, sched_domain_span(env->sd))) {
@@ -8373,119 +9042,19 @@
 	}
 }
 
-/**
- * check_asym_packing - Check to see if the group is packed into the
- *			sched domain.
- *
- * This is primarily intended to used at the sibling level.  Some
- * cores like POWER7 prefer to use lower numbered SMT threads.  In the
- * case of POWER7, it can move to lower SMT modes only when higher
- * threads are idle.  When in lower SMT modes, the threads will
- * perform better since they share less core resources.  Hence when we
- * have idle threads, we want them to be the higher ones.
- *
- * This packing function is run on idle threads.  It checks to see if
- * the busiest CPU in this domain (core in the P7 case) has a higher
- * CPU number than the packing function is being run on.  Here we are
- * assuming lower CPU number will be equivalent to lower a SMT thread
- * number.
- *
- * Return: 1 when packing is required and a task should be moved to
- * this CPU.  The amount of the imbalance is returned in env->imbalance.
- *
- * @env: The load balancing environment.
- * @sds: Statistics of the sched_domain which is to be packed
- */
-static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds)
+static inline long adjust_numa_imbalance(int imbalance, int nr_running)
 {
-	int busiest_cpu;
-
-	if (!(env->sd->flags & SD_ASYM_PACKING))
-		return 0;
-
-	if (env->idle == CPU_NOT_IDLE)
-		return 0;
-
-	if (!sds->busiest)
-		return 0;
-
-	busiest_cpu = sds->busiest->asym_prefer_cpu;
-	if (sched_asym_prefer(busiest_cpu, env->dst_cpu))
-		return 0;
-
-	env->imbalance = sds->busiest_stat.group_load;
-
-	return 1;
-}
-
-/**
- * fix_small_imbalance - Calculate the minor imbalance that exists
- *			amongst the groups of a sched_domain, during
- *			load balancing.
- * @env: The load balancing environment.
- * @sds: Statistics of the sched_domain whose imbalance is to be calculated.
- */
-static inline
-void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
-{
-	unsigned long tmp, capa_now = 0, capa_move = 0;
-	unsigned int imbn = 2;
-	unsigned long scaled_busy_load_per_task;
-	struct sg_lb_stats *local, *busiest;
-
-	local = &sds->local_stat;
-	busiest = &sds->busiest_stat;
-
-	if (!local->sum_nr_running)
-		local->load_per_task = cpu_avg_load_per_task(env->dst_cpu);
-	else if (busiest->load_per_task > local->load_per_task)
-		imbn = 1;
-
-	scaled_busy_load_per_task =
-		(busiest->load_per_task * SCHED_CAPACITY_SCALE) /
-		busiest->group_capacity;
-
-	if (busiest->avg_load + scaled_busy_load_per_task >=
-	    local->avg_load + (scaled_busy_load_per_task * imbn)) {
-		env->imbalance = busiest->load_per_task;
-		return;
-	}
+	unsigned int imbalance_min;
 
 	/*
-	 * OK, we don't have enough imbalance to justify moving tasks,
-	 * however we may be able to increase total CPU capacity used by
-	 * moving them.
+	 * Allow a small imbalance based on a simple pair of communicating
+	 * tasks that remain local when the source domain is almost idle.
 	 */
+	imbalance_min = 2;
+	if (nr_running <= imbalance_min)
+		return 0;
 
-	capa_now += busiest->group_capacity *
-			min(busiest->load_per_task, busiest->avg_load);
-	capa_now += local->group_capacity *
-			min(local->load_per_task, local->avg_load);
-	capa_now /= SCHED_CAPACITY_SCALE;
-
-	/* Amount of load we'd subtract */
-	if (busiest->avg_load > scaled_busy_load_per_task) {
-		capa_move += busiest->group_capacity *
-			    min(busiest->load_per_task,
-				busiest->avg_load - scaled_busy_load_per_task);
-	}
-
-	/* Amount of load we'd add */
-	if (busiest->avg_load * busiest->group_capacity <
-	    busiest->load_per_task * SCHED_CAPACITY_SCALE) {
-		tmp = (busiest->avg_load * busiest->group_capacity) /
-		      local->group_capacity;
-	} else {
-		tmp = (busiest->load_per_task * SCHED_CAPACITY_SCALE) /
-		      local->group_capacity;
-	}
-	capa_move += local->group_capacity *
-		    min(local->load_per_task, local->avg_load + tmp);
-	capa_move /= SCHED_CAPACITY_SCALE;
-
-	/* Move if we gain throughput */
-	if (capa_move > capa_now)
-		env->imbalance = busiest->load_per_task;
+	return imbalance;
 }
 
 /**
@@ -8496,81 +9065,164 @@
  */
 static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
 {
-	unsigned long max_pull, load_above_capacity = ~0UL;
 	struct sg_lb_stats *local, *busiest;
 
 	local = &sds->local_stat;
 	busiest = &sds->busiest_stat;
 
+	if (busiest->group_type == group_misfit_task) {
+		/* Set imbalance to allow misfit tasks to be balanced. */
+		env->migration_type = migrate_misfit;
+		env->imbalance = 1;
+		return;
+	}
+
+	if (busiest->group_type == group_asym_packing) {
+		/*
+		 * In case of asym capacity, we will try to migrate all load to
+		 * the preferred CPU.
+		 */
+		env->migration_type = migrate_task;
+		env->imbalance = busiest->sum_h_nr_running;
+		return;
+	}
+
 	if (busiest->group_type == group_imbalanced) {
 		/*
 		 * In the group_imb case we cannot rely on group-wide averages
-		 * to ensure CPU-load equilibrium, look at wider averages. XXX
+		 * to ensure CPU-load equilibrium, try to move any task to fix
+		 * the imbalance. The next load balance will take care of
+		 * balancing back the system.
 		 */
-		busiest->load_per_task =
-			min(busiest->load_per_task, sds->avg_load);
+		env->migration_type = migrate_task;
+		env->imbalance = 1;
+		return;
 	}
 
 	/*
-	 * Avg load of busiest sg can be less and avg load of local sg can
-	 * be greater than avg load across all sgs of sd because avg load
-	 * factors in sg capacity and sgs with smaller group_type are
-	 * skipped when updating the busiest sg:
+	 * Try to use spare capacity of local group without overloading it or
+	 * emptying busiest.
 	 */
-	if (busiest->group_type != group_misfit_task &&
-	    (busiest->avg_load <= sds->avg_load ||
-	     local->avg_load >= sds->avg_load)) {
-		env->imbalance = 0;
-		return fix_small_imbalance(env, sds);
+	if (local->group_type == group_has_spare) {
+		if ((busiest->group_type > group_fully_busy) &&
+		    !(env->sd->flags & SD_SHARE_PKG_RESOURCES)) {
+			/*
+			 * If busiest is overloaded, try to fill spare
+			 * capacity. This might end up creating spare capacity
+			 * in busiest or busiest still being overloaded but
+			 * there is no simple way to directly compute the
+			 * amount of load to migrate in order to balance the
+			 * system.
+			 */
+			env->migration_type = migrate_util;
+			env->imbalance = max(local->group_capacity, local->group_util) -
+					 local->group_util;
+
+			/*
+			 * In some cases, the group's utilization is max or even
+			 * higher than capacity because of migrations but the
+			 * local CPU is (newly) idle. There is at least one
+			 * waiting task in this overloaded busiest group. Let's
+			 * try to pull it.
+			 */
+			if (env->idle != CPU_NOT_IDLE && env->imbalance == 0) {
+				env->migration_type = migrate_task;
+				env->imbalance = 1;
+			}
+
+			return;
+		}
+
+		if (busiest->group_weight == 1 || sds->prefer_sibling) {
+			unsigned int nr_diff = busiest->sum_nr_running;
+			/*
+			 * When prefer sibling, evenly spread running tasks on
+			 * groups.
+			 */
+			env->migration_type = migrate_task;
+			lsub_positive(&nr_diff, local->sum_nr_running);
+			env->imbalance = nr_diff >> 1;
+		} else {
+
+			/*
+			 * If there is no overload, we just want to even the number of
+			 * idle cpus.
+			 */
+			env->migration_type = migrate_task;
+			env->imbalance = max_t(long, 0, (local->idle_cpus -
+						 busiest->idle_cpus) >> 1);
+		}
+
+		/* Consider allowing a small imbalance between NUMA groups */
+		if (env->sd->flags & SD_NUMA)
+			env->imbalance = adjust_numa_imbalance(env->imbalance,
+						busiest->sum_nr_running);
+
+		return;
 	}
 
 	/*
-	 * If there aren't any idle CPUs, avoid creating some.
+	 * Local is fully busy but has to take more load to relieve the
+	 * busiest group
 	 */
-	if (busiest->group_type == group_overloaded &&
-	    local->group_type   == group_overloaded) {
-		load_above_capacity = busiest->sum_nr_running * SCHED_CAPACITY_SCALE;
-		if (load_above_capacity > busiest->group_capacity) {
-			load_above_capacity -= busiest->group_capacity;
-			load_above_capacity *= scale_load_down(NICE_0_LOAD);
-			load_above_capacity /= busiest->group_capacity;
-		} else
-			load_above_capacity = ~0UL;
+	if (local->group_type < group_overloaded) {
+		/*
+		 * Local will become overloaded so the avg_load metrics are
+		 * finally needed.
+		 */
+
+		local->avg_load = (local->group_load * SCHED_CAPACITY_SCALE) /
+				  local->group_capacity;
+
+		sds->avg_load = (sds->total_load * SCHED_CAPACITY_SCALE) /
+				sds->total_capacity;
+		/*
+		 * If the local group is more loaded than the selected
+		 * busiest group don't try to pull any tasks.
+		 */
+		if (local->avg_load >= busiest->avg_load) {
+			env->imbalance = 0;
+			return;
+		}
 	}
 
 	/*
-	 * We're trying to get all the CPUs to the average_load, so we don't
-	 * want to push ourselves above the average load, nor do we wish to
-	 * reduce the max loaded CPU below the average load. At the same time,
-	 * we also don't want to reduce the group load below the group
-	 * capacity. Thus we look for the minimum possible imbalance.
+	 * Both group are or will become overloaded and we're trying to get all
+	 * the CPUs to the average_load, so we don't want to push ourselves
+	 * above the average load, nor do we wish to reduce the max loaded CPU
+	 * below the average load. At the same time, we also don't want to
+	 * reduce the group load below the group capacity. Thus we look for
+	 * the minimum possible imbalance.
 	 */
-	max_pull = min(busiest->avg_load - sds->avg_load, load_above_capacity);
-
-	/* How much load to actually move to equalise the imbalance */
+	env->migration_type = migrate_load;
 	env->imbalance = min(
-		max_pull * busiest->group_capacity,
+		(busiest->avg_load - sds->avg_load) * busiest->group_capacity,
 		(sds->avg_load - local->avg_load) * local->group_capacity
 	) / SCHED_CAPACITY_SCALE;
-
-	/* Boost imbalance to allow misfit task to be balanced. */
-	if (busiest->group_type == group_misfit_task) {
-		env->imbalance = max_t(long, env->imbalance,
-				       busiest->group_misfit_task_load);
-	}
-
-	/*
-	 * if *imbalance is less than the average load per runnable task
-	 * there is no guarantee that any tasks will be moved so we'll have
-	 * a think about bumping its value to force at least one task to be
-	 * moved
-	 */
-	if (env->imbalance < busiest->load_per_task)
-		return fix_small_imbalance(env, sds);
 }
 
 /******* find_busiest_group() helpers end here *********************/
 
+/*
+ * Decision matrix according to the local and busiest group type:
+ *
+ * busiest \ local has_spare fully_busy misfit asym imbalanced overloaded
+ * has_spare        nr_idle   balanced   N/A    N/A  balanced   balanced
+ * fully_busy       nr_idle   nr_idle    N/A    N/A  balanced   balanced
+ * misfit_task      force     N/A        N/A    N/A  force      force
+ * asym_packing     force     force      N/A    N/A  force      force
+ * imbalanced       force     force      N/A    N/A  force      force
+ * overloaded       force     force      N/A    N/A  force      avg_load
+ *
+ * N/A :      Not Applicable because already filtered while updating
+ *            statistics.
+ * balanced : The system is balanced for these 2 groups.
+ * force :    Calculate the imbalance as load migration is probably needed.
+ * avg_load : Only if imbalance is significant enough.
+ * nr_idle :  dst_cpu is not busy and the number of idle CPUs is quite
+ *            different in groups.
+ */
+
 /**
  * find_busiest_group - Returns the busiest group within the sched_domain
  * if there is an imbalance.
@@ -8590,7 +9242,7 @@
 	init_sd_lb_stats(&sds);
 
 	/*
-	 * Compute the various statistics relavent for load balancing at
+	 * Compute the various statistics relevant for load balancing at
 	 * this level.
 	 */
 	update_sd_lb_stats(env, &sds);
@@ -8605,17 +9257,17 @@
 	local = &sds.local_stat;
 	busiest = &sds.busiest_stat;
 
-	/* ASYM feature bypasses nice load balance check */
-	if (check_asym_packing(env, &sds))
-		return sds.busiest;
-
 	/* There is no busy sibling group to pull tasks from */
-	if (!sds.busiest || busiest->sum_nr_running == 0)
+	if (!sds.busiest)
 		goto out_balanced;
 
-	/* XXX broken for overlapping NUMA groups */
-	sds.avg_load = (SCHED_CAPACITY_SCALE * sds.total_load)
-						/ sds.total_capacity;
+	/* Misfit tasks should be dealt with regardless of the avg load */
+	if (busiest->group_type == group_misfit_task)
+		goto force_balance;
+
+	/* ASYM feature bypasses nice load balance check */
+	if (busiest->group_type == group_asym_packing)
+		goto force_balance;
 
 	/*
 	 * If the busiest group is imbalanced the below checks don't
@@ -8626,55 +9278,80 @@
 		goto force_balance;
 
 	/*
-	 * When dst_cpu is idle, prevent SMP nice and/or asymmetric group
-	 * capacities from resulting in underutilization due to avg_load.
-	 */
-	if (env->idle != CPU_NOT_IDLE && group_has_capacity(env, local) &&
-	    busiest->group_no_capacity)
-		goto force_balance;
-
-	/* Misfit tasks should be dealt with regardless of the avg load */
-	if (busiest->group_type == group_misfit_task)
-		goto force_balance;
-
-	/*
 	 * If the local group is busier than the selected busiest group
 	 * don't try and pull any tasks.
 	 */
-	if (local->avg_load >= busiest->avg_load)
+	if (local->group_type > busiest->group_type)
 		goto out_balanced;
 
 	/*
-	 * Don't pull any tasks if this group is already above the domain
-	 * average load.
+	 * When groups are overloaded, use the avg_load to ensure fairness
+	 * between tasks.
 	 */
-	if (local->avg_load >= sds.avg_load)
-		goto out_balanced;
-
-	if (env->idle == CPU_IDLE) {
+	if (local->group_type == group_overloaded) {
 		/*
-		 * This CPU is idle. If the busiest group is not overloaded
-		 * and there is no imbalance between this and busiest group
-		 * wrt idle CPUs, it is balanced. The imbalance becomes
-		 * significant if the diff is greater than 1 otherwise we
-		 * might end up to just move the imbalance on another group
+		 * If the local group is more loaded than the selected
+		 * busiest group don't try to pull any tasks.
 		 */
-		if ((busiest->group_type != group_overloaded) &&
-				(local->idle_cpus <= (busiest->idle_cpus + 1)))
+		if (local->avg_load >= busiest->avg_load)
 			goto out_balanced;
-	} else {
+
+		/* XXX broken for overlapping NUMA groups */
+		sds.avg_load = (sds.total_load * SCHED_CAPACITY_SCALE) /
+				sds.total_capacity;
+
 		/*
-		 * In the CPU_NEWLY_IDLE, CPU_NOT_IDLE cases, use
-		 * imbalance_pct to be conservative.
+		 * Don't pull any tasks if this group is already above the
+		 * domain average load.
+		 */
+		if (local->avg_load >= sds.avg_load)
+			goto out_balanced;
+
+		/*
+		 * If the busiest group is more loaded, use imbalance_pct to be
+		 * conservative.
 		 */
 		if (100 * busiest->avg_load <=
 				env->sd->imbalance_pct * local->avg_load)
 			goto out_balanced;
 	}
 
+	/* Try to move all excess tasks to child's sibling domain */
+	if (sds.prefer_sibling && local->group_type == group_has_spare &&
+	    busiest->sum_nr_running > local->sum_nr_running + 1)
+		goto force_balance;
+
+	if (busiest->group_type != group_overloaded) {
+		if (env->idle == CPU_NOT_IDLE)
+			/*
+			 * If the busiest group is not overloaded (and as a
+			 * result the local one too) but this CPU is already
+			 * busy, let another idle CPU try to pull task.
+			 */
+			goto out_balanced;
+
+		if (busiest->group_weight > 1 &&
+		    local->idle_cpus <= (busiest->idle_cpus + 1))
+			/*
+			 * If the busiest group is not overloaded
+			 * and there is no imbalance between this and busiest
+			 * group wrt idle CPUs, it is balanced. The imbalance
+			 * becomes significant if the diff is greater than 1
+			 * otherwise we might end up to just move the imbalance
+			 * on another group. Of course this applies only if
+			 * there is more than 1 CPU per group.
+			 */
+			goto out_balanced;
+
+		if (busiest->sum_h_nr_running == 1)
+			/*
+			 * busiest doesn't have any tasks waiting to run
+			 */
+			goto out_balanced;
+	}
+
 force_balance:
 	/* Looks like there is an imbalance. Compute it */
-	env->src_grp_type = busiest->group_type;
 	calculate_imbalance(env, &sds);
 	return env->imbalance ? sds.busiest : NULL;
 
@@ -8690,11 +9367,13 @@
 				     struct sched_group *group)
 {
 	struct rq *busiest = NULL, *rq;
-	unsigned long busiest_load = 0, busiest_capacity = 1;
+	unsigned long busiest_util = 0, busiest_load = 0, busiest_capacity = 1;
+	unsigned int busiest_nr = 0;
 	int i;
 
 	for_each_cpu_and(i, sched_group_span(group), env->cpus) {
-		unsigned long capacity, load;
+		unsigned long capacity, load, util;
+		unsigned int nr_running;
 		enum fbq_type rt;
 
 		rq = cpu_rq(i);
@@ -8722,20 +9401,8 @@
 		if (rt > env->fbq_type)
 			continue;
 
-		/*
-		 * For ASYM_CPUCAPACITY domains with misfit tasks we simply
-		 * seek the "biggest" misfit task.
-		 */
-		if (env->src_grp_type == group_misfit_task) {
-			if (rq->misfit_task_load > busiest_load) {
-				busiest_load = rq->misfit_task_load;
-				busiest = rq;
-			}
-
-			continue;
-		}
-
 		capacity = capacity_of(i);
+		nr_running = rq->cfs.h_nr_running;
 
 		/*
 		 * For ASYM_CPUCAPACITY domains, don't pick a CPU that could
@@ -8745,35 +9412,77 @@
 		 */
 		if (env->sd->flags & SD_ASYM_CPUCAPACITY &&
 		    capacity_of(env->dst_cpu) < capacity &&
-		    rq->nr_running == 1)
+		    nr_running == 1)
 			continue;
 
-		load = cpu_runnable_load(rq);
+		switch (env->migration_type) {
+		case migrate_load:
+			/*
+			 * When comparing with load imbalance, use cpu_load()
+			 * which is not scaled with the CPU capacity.
+			 */
+			load = cpu_load(rq);
 
-		/*
-		 * When comparing with imbalance, use cpu_runnable_load()
-		 * which is not scaled with the CPU capacity.
-		 */
+			if (nr_running == 1 && load > env->imbalance &&
+			    !check_cpu_capacity(rq, env->sd))
+				break;
 
-		if (rq->nr_running == 1 && load > env->imbalance &&
-		    !check_cpu_capacity(rq, env->sd))
-			continue;
+			/*
+			 * For the load comparisons with the other CPUs,
+			 * consider the cpu_load() scaled with the CPU
+			 * capacity, so that the load can be moved away
+			 * from the CPU that is potentially running at a
+			 * lower capacity.
+			 *
+			 * Thus we're looking for max(load_i / capacity_i),
+			 * crosswise multiplication to rid ourselves of the
+			 * division works out to:
+			 * load_i * capacity_j > load_j * capacity_i;
+			 * where j is our previous maximum.
+			 */
+			if (load * busiest_capacity > busiest_load * capacity) {
+				busiest_load = load;
+				busiest_capacity = capacity;
+				busiest = rq;
+			}
+			break;
 
-		/*
-		 * For the load comparisons with the other CPU's, consider
-		 * the cpu_runnable_load() scaled with the CPU capacity, so
-		 * that the load can be moved away from the CPU that is
-		 * potentially running at a lower capacity.
-		 *
-		 * Thus we're looking for max(load_i / capacity_i), crosswise
-		 * multiplication to rid ourselves of the division works out
-		 * to: load_i * capacity_j > load_j * capacity_i;  where j is
-		 * our previous maximum.
-		 */
-		if (load * busiest_capacity > busiest_load * capacity) {
-			busiest_load = load;
-			busiest_capacity = capacity;
-			busiest = rq;
+		case migrate_util:
+			util = cpu_util(cpu_of(rq));
+
+			/*
+			 * Don't try to pull utilization from a CPU with one
+			 * running task. Whatever its utilization, we will fail
+			 * detach the task.
+			 */
+			if (nr_running <= 1)
+				continue;
+
+			if (busiest_util < util) {
+				busiest_util = util;
+				busiest = rq;
+			}
+			break;
+
+		case migrate_task:
+			if (busiest_nr < nr_running) {
+				busiest_nr = nr_running;
+				busiest = rq;
+			}
+			break;
+
+		case migrate_misfit:
+			/*
+			 * For ASYM_CPUCAPACITY domains with misfit tasks we
+			 * simply seek the "biggest" misfit task.
+			 */
+			if (rq->misfit_task_load > busiest_load) {
+				busiest_load = rq->misfit_task_load;
+				busiest = rq;
+			}
+
+			break;
+
 		}
 	}
 
@@ -8819,7 +9528,7 @@
 			return 1;
 	}
 
-	if (env->src_grp_type == group_misfit_task)
+	if (env->migration_type == migrate_misfit)
 		return 1;
 
 	return 0;
@@ -8840,7 +9549,7 @@
 static int should_we_balance(struct lb_env *env)
 {
 	struct sched_group *sg = env->sd->groups;
-	int cpu, balance_cpu = -1;
+	int cpu;
 
 	/*
 	 * Ensure the balancing environment is consistent; can happen
@@ -8861,18 +9570,12 @@
 		if (!idle_cpu(cpu))
 			continue;
 
-		balance_cpu = cpu;
-		break;
+		/* Are we the first idle CPU? */
+		return cpu == env->dst_cpu;
 	}
 
-	if (balance_cpu == -1)
-		balance_cpu = group_balance_cpu(sg);
-
-	/*
-	 * First idle CPU or the first CPU(busiest) in this sched group
-	 * is eligible for doing load balancing at this and above domains.
-	 */
-	return balance_cpu == env->dst_cpu;
+	/* Are we the first CPU of this group ? */
+	return group_balance_cpu(sg) == env->dst_cpu;
 }
 
 /*
@@ -9163,6 +9866,15 @@
 
 	/* scale ms to jiffies */
 	interval = msecs_to_jiffies(interval);
+
+	/*
+	 * Reduce likelihood of busy balancing at higher domains racing with
+	 * balancing at lower domains by preventing their balancing periods
+	 * from being multiples of each other.
+	 */
+	if (cpu_busy)
+		interval -= 1;
+
 	interval = clamp(interval, 1UL, max_load_balance_interval);
 
 	return interval;
@@ -9225,9 +9937,8 @@
 	/* Search for an sd spanning us and the target CPU. */
 	rcu_read_lock();
 	for_each_domain(target_cpu, sd) {
-		if ((sd->flags & SD_LOAD_BALANCE) &&
-		    cpumask_test_cpu(busiest_cpu, sched_domain_span(sd)))
-				break;
+		if (cpumask_test_cpu(busiest_cpu, sched_domain_span(sd)))
+			break;
 	}
 
 	if (likely(sd)) {
@@ -9293,6 +10004,7 @@
 {
 	int continue_balancing = 1;
 	int cpu = rq->cpu;
+	int busy = idle != CPU_IDLE && !sched_idle_cpu(cpu);
 	unsigned long interval;
 	struct sched_domain *sd;
 	/* Earliest time when we have to do rebalance again */
@@ -9315,9 +10027,6 @@
 		}
 		max_cost += sd->max_newidle_lb_cost;
 
-		if (!(sd->flags & SD_LOAD_BALANCE))
-			continue;
-
 		/*
 		 * Stop the load balance at this level. There is another
 		 * CPU in our sched group which is doing load balancing more
@@ -9329,7 +10038,7 @@
 			break;
 		}
 
-		interval = get_sd_balance_interval(sd, idle != CPU_IDLE);
+		interval = get_sd_balance_interval(sd, busy);
 
 		need_serialize = sd->flags & SD_SERIALIZE;
 		if (need_serialize) {
@@ -9345,9 +10054,10 @@
 				 * state even if we migrated tasks. Update it.
 				 */
 				idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE;
+				busy = idle != CPU_IDLE && !sched_idle_cpu(cpu);
 			}
 			sd->last_balance = jiffies;
-			interval = get_sd_balance_interval(sd, idle != CPU_IDLE);
+			interval = get_sd_balance_interval(sd, busy);
 		}
 		if (need_serialize)
 			spin_unlock(&balancing);
@@ -9438,17 +10148,20 @@
 	if (ilb_cpu >= nr_cpu_ids)
 		return;
 
+	/*
+	 * Access to rq::nohz_csd is serialized by NOHZ_KICK_MASK; he who sets
+	 * the first flag owns it; cleared by nohz_csd_func().
+	 */
 	flags = atomic_fetch_or(flags, nohz_flags(ilb_cpu));
 	if (flags & NOHZ_KICK_MASK)
 		return;
 
 	/*
-	 * Use smp_send_reschedule() instead of resched_cpu().
-	 * This way we generate a sched IPI on the target CPU which
+	 * This way we generate an IPI on the target CPU which
 	 * is idle. And the softirq performing nohz idle load balance
 	 * will be run before returning from the IPI.
 	 */
-	smp_send_reschedule(ilb_cpu);
+	smp_call_function_single_async(ilb_cpu, &cpu_rq(ilb_cpu)->nohz_csd);
 }
 
 /*
@@ -9786,20 +10499,14 @@
  */
 static bool nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
 {
-	int this_cpu = this_rq->cpu;
-	unsigned int flags;
+	unsigned int flags = this_rq->nohz_idle_balance;
 
-	if (!(atomic_read(nohz_flags(this_cpu)) & NOHZ_KICK_MASK))
+	if (!flags)
 		return false;
 
-	if (idle != CPU_IDLE) {
-		atomic_andnot(NOHZ_KICK_MASK, nohz_flags(this_cpu));
-		return false;
-	}
+	this_rq->nohz_idle_balance = 0;
 
-	/* could be _relaxed() */
-	flags = atomic_fetch_andnot(NOHZ_KICK_MASK, nohz_flags(this_cpu));
-	if (!(flags & NOHZ_KICK_MASK))
+	if (idle != CPU_IDLE)
 		return false;
 
 	_nohz_idle_balance(this_rq, flags, idle);
@@ -9853,8 +10560,13 @@
 /*
  * idle_balance is called by schedule() if this_cpu is about to become
  * idle. Attempts to pull tasks from other CPUs.
+ *
+ * Returns:
+ *   < 0 - we released the lock and there are !fair tasks present
+ *     0 - failed, no new tasks
+ *   > 0 - success, new (fair) tasks present
  */
-int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
+static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 {
 	unsigned long next_balance = jiffies + HZ;
 	int this_cpu = this_rq->cpu;
@@ -9905,9 +10617,6 @@
 		int continue_balancing = 1;
 		u64 t0, domain_cost;
 
-		if (!(sd->flags & SD_LOAD_BALANCE))
-			continue;
-
 		if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) {
 			update_next_balance(sd, &next_balance);
 			break;
@@ -10097,6 +10806,9 @@
 	if (!task_on_rq_queued(p))
 		return;
 
+	if (rq->cfs.nr_running == 1)
+		return;
+
 	/*
 	 * Reschedule if we are currently running on this runqueue and
 	 * our priority decreased, or if we are not currently running on
@@ -10175,7 +10887,7 @@
 	/* Catch up with the cfs_rq and remove our load when we leave */
 	update_load_avg(cfs_rq, se, 0);
 	detach_entity_load_avg(cfs_rq, se);
-	update_tg_load_avg(cfs_rq, false);
+	update_tg_load_avg(cfs_rq);
 	propagate_entity_cfs_rq(se);
 }
 
@@ -10193,8 +10905,8 @@
 
 	/* Synchronize entity with its cfs_rq */
 	update_load_avg(cfs_rq, se, sched_feat(ATTACH_AGE_LOAD) ? 0 : SKIP_AGE_LOAD);
-	attach_entity_load_avg(cfs_rq, se, 0);
-	update_tg_load_avg(cfs_rq, false);
+	attach_entity_load_avg(cfs_rq, se);
+	update_tg_load_avg(cfs_rq);
 	propagate_entity_cfs_rq(se);
 }
 
@@ -10526,8 +11238,8 @@
 /*
  * All the scheduling class methods:
  */
-const struct sched_class fair_sched_class = {
-	.next			= &idle_sched_class,
+const struct sched_class fair_sched_class
+	__section("__fair_sched_class") = {
 	.enqueue_task		= enqueue_task_fair,
 	.dequeue_task		= dequeue_task_fair,
 	.yield_task		= yield_task_fair,
@@ -10535,7 +11247,7 @@
 
 	.check_preempt_curr	= check_preempt_wakeup,
 
-	.pick_next_task		= pick_next_task_fair,
+	.pick_next_task		= __pick_next_task_fair,
 	.put_prev_task		= put_prev_task_fair,
 	.set_next_task          = set_next_task_fair,
 
@@ -10691,6 +11403,18 @@
 }
 EXPORT_SYMBOL_GPL(sched_trace_rq_cpu);
 
+int sched_trace_rq_cpu_capacity(struct rq *rq)
+{
+	return rq ?
+#ifdef CONFIG_SMP
+		rq->cpu_capacity
+#else
+		SCHED_CAPACITY_SCALE
+#endif
+		: -1;
+}
+EXPORT_SYMBOL_GPL(sched_trace_rq_cpu_capacity);
+
 const struct cpumask *sched_trace_rd_span(struct root_domain *rd)
 {
 #ifdef CONFIG_SMP
@@ -10700,3 +11424,9 @@
 #endif
 }
 EXPORT_SYMBOL_GPL(sched_trace_rd_span);
+
+int sched_trace_rq_nr_running(struct rq *rq)
+{
+        return rq ? rq->nr_running : -1;
+}
+EXPORT_SYMBOL_GPL(sched_trace_rq_nr_running);
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 2410db5..f1bf5e1 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -77,7 +77,7 @@
 SCHED_FEAT(RT_PUSH_IPI, true)
 #endif
 
-SCHED_FEAT(RT_RUNTIME_SHARE, true)
+SCHED_FEAT(RT_RUNTIME_SHARE, false)
 SCHED_FEAT(LB_MIN, false)
 SCHED_FEAT(ATTACH_AGE_LOAD, true)
 
@@ -89,3 +89,7 @@
  * UtilEstimation. Use estimated CPU utilization.
  */
 SCHED_FEAT(UTIL_EST, true)
+SCHED_FEAT(UTIL_EST_FASTUP, true)
+
+SCHED_FEAT(ALT_PERIOD, true)
+SCHED_FEAT(BASE_SLICE, true)
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 3f8c786..2593a73 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -54,17 +54,18 @@
 
 static noinline int __cpuidle cpu_idle_poll(void)
 {
-	rcu_idle_enter();
-	trace_cpu_idle_rcuidle(0, smp_processor_id());
-	local_irq_enable();
+	trace_cpu_idle(0, smp_processor_id());
 	stop_critical_timings();
+	rcu_idle_enter();
+	local_irq_enable();
 
 	while (!tif_need_resched() &&
-		(cpu_idle_force_poll || tick_check_broadcast_expired()))
+	       (cpu_idle_force_poll || tick_check_broadcast_expired()))
 		cpu_relax();
-	start_critical_timings();
-	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
+
 	rcu_idle_exit();
+	start_critical_timings();
+	trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
 
 	return 1;
 }
@@ -77,7 +78,7 @@
 void __weak arch_cpu_idle(void)
 {
 	cpu_idle_force_poll = 1;
-	local_irq_enable();
+	raw_local_irq_enable();
 }
 
 /**
@@ -90,12 +91,52 @@
 	if (current_clr_polling_and_test()) {
 		local_irq_enable();
 	} else {
+
+		trace_cpu_idle(1, smp_processor_id());
 		stop_critical_timings();
+
+		/*
+		 * arch_cpu_idle() is supposed to enable IRQs, however
+		 * we can't do that because of RCU and tracing.
+		 *
+		 * Trace IRQs enable here, then switch off RCU, and have
+		 * arch_cpu_idle() use raw_local_irq_enable(). Note that
+		 * rcu_idle_enter() relies on lockdep IRQ state, so switch that
+		 * last -- this is very similar to the entry code.
+		 */
+		trace_hardirqs_on_prepare();
+		lockdep_hardirqs_on_prepare(_THIS_IP_);
+		rcu_idle_enter();
+		lockdep_hardirqs_on(_THIS_IP_);
+
 		arch_cpu_idle();
+
+		/*
+		 * OK, so IRQs are enabled here, but RCU needs them disabled to
+		 * turn itself back on.. funny thing is that disabling IRQs
+		 * will cause tracing, which needs RCU. Jump through hoops to
+		 * make it 'work'.
+		 */
+		raw_local_irq_disable();
+		lockdep_hardirqs_off(_THIS_IP_);
+		rcu_idle_exit();
+		lockdep_hardirqs_on(_THIS_IP_);
+		raw_local_irq_enable();
+
 		start_critical_timings();
+		trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
 	}
 }
 
+static int call_cpuidle_s2idle(struct cpuidle_driver *drv,
+			       struct cpuidle_device *dev)
+{
+	if (current_clr_polling_and_test())
+		return -EBUSY;
+
+	return cpuidle_enter_s2idle(drv, dev);
+}
+
 static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		      int next_state)
 {
@@ -104,7 +145,7 @@
 	 * update no idle residency and return.
 	 */
 	if (current_clr_polling_and_test()) {
-		dev->last_residency = 0;
+		dev->last_residency_ns = 0;
 		local_irq_enable();
 		return -EBUSY;
 	}
@@ -149,7 +190,6 @@
 
 	if (cpuidle_not_available(drv, dev)) {
 		tick_nohz_idle_stop_tick();
-		rcu_idle_enter();
 
 		default_idle_call();
 		goto exit_idle;
@@ -158,30 +198,30 @@
 	/*
 	 * Suspend-to-idle ("s2idle") is a system state in which all user space
 	 * has been frozen, all I/O devices have been suspended and the only
-	 * activity happens here and in iterrupts (if any).  In that case bypass
+	 * activity happens here and in interrupts (if any). In that case bypass
 	 * the cpuidle governor and go stratight for the deepest idle state
 	 * available.  Possibly also suspend the local tick and the entire
 	 * timekeeping to prevent timer interrupts from kicking us out of idle
 	 * until a proper wakeup interrupt happens.
 	 */
 
-	if (idle_should_enter_s2idle() || dev->use_deepest_state) {
+	if (idle_should_enter_s2idle() || dev->forced_idle_latency_limit_ns) {
+		u64 max_latency_ns;
+
 		if (idle_should_enter_s2idle()) {
-			rcu_idle_enter();
 
-			entered_state = cpuidle_enter_s2idle(drv, dev);
-			if (entered_state > 0) {
-				local_irq_enable();
+			entered_state = call_cpuidle_s2idle(drv, dev);
+			if (entered_state > 0)
 				goto exit_idle;
-			}
 
-			rcu_idle_exit();
+			max_latency_ns = U64_MAX;
+		} else {
+			max_latency_ns = dev->forced_idle_latency_limit_ns;
 		}
 
 		tick_nohz_idle_stop_tick();
-		rcu_idle_enter();
 
-		next_state = cpuidle_find_deepest_state(drv, dev);
+		next_state = cpuidle_find_deepest_state(drv, dev, max_latency_ns);
 		call_cpuidle(drv, dev, next_state);
 	} else {
 		bool stop_tick = true;
@@ -196,8 +236,6 @@
 		else
 			tick_nohz_idle_retain_tick();
 
-		rcu_idle_enter();
-
 		entered_state = call_cpuidle(drv, dev, next_state);
 		/*
 		 * Give the governor an opportunity to reflect on the outcome
@@ -213,8 +251,6 @@
 	 */
 	if (WARN_ON_ONCE(irqs_disabled()))
 		local_irq_enable();
-
-	rcu_idle_exit();
 }
 
 /*
@@ -284,7 +320,11 @@
 	 */
 	smp_mb__after_atomic();
 
-	sched_ttwu_pending();
+	/*
+	 * RCU relies on this call to be done outside of an RCU read-side
+	 * critical section.
+	 */
+	flush_smp_call_function_from_idle();
 	schedule_idle();
 
 	if (unlikely(klp_patch_pending(current)))
@@ -312,7 +352,7 @@
 	return HRTIMER_NORESTART;
 }
 
-void play_idle(unsigned long duration_us)
+void play_idle_precise(u64 duration_ns, u64 latency_ns)
 {
 	struct idle_timer it;
 
@@ -324,29 +364,29 @@
 	WARN_ON_ONCE(current->nr_cpus_allowed != 1);
 	WARN_ON_ONCE(!(current->flags & PF_KTHREAD));
 	WARN_ON_ONCE(!(current->flags & PF_NO_SETAFFINITY));
-	WARN_ON_ONCE(!duration_us);
+	WARN_ON_ONCE(!duration_ns);
 
 	rcu_sleep_check();
 	preempt_disable();
 	current->flags |= PF_IDLE;
-	cpuidle_use_deepest_state(true);
+	cpuidle_use_deepest_state(latency_ns);
 
 	it.done = 0;
-	hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 	it.timer.function = idle_inject_timer_fn;
-	hrtimer_start(&it.timer, ns_to_ktime(duration_us * NSEC_PER_USEC),
-		      HRTIMER_MODE_REL_PINNED);
+	hrtimer_start(&it.timer, ns_to_ktime(duration_ns),
+		      HRTIMER_MODE_REL_PINNED_HARD);
 
 	while (!READ_ONCE(it.done))
 		do_idle();
 
-	cpuidle_use_deepest_state(false);
+	cpuidle_use_deepest_state(0);
 	current->flags &= ~PF_IDLE;
 
 	preempt_fold_need_resched();
 	preempt_enable();
 }
-EXPORT_SYMBOL_GPL(play_idle);
+EXPORT_SYMBOL_GPL(play_idle_precise);
 
 void cpu_startup_entry(enum cpuhp_state state)
 {
@@ -392,14 +432,10 @@
 	schedstat_inc(rq->sched_goidle);
 }
 
-static struct task_struct *
-pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+struct task_struct *pick_next_task_idle(struct rq *rq)
 {
 	struct task_struct *next = rq->idle;
 
-	if (prev)
-		put_prev_task(rq, prev);
-
 	set_next_task_idle(rq, next, true);
 
 	return next;
@@ -441,11 +477,6 @@
 	BUG();
 }
 
-static unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task)
-{
-	return 0;
-}
-
 static void update_curr_idle(struct rq *rq)
 {
 }
@@ -453,8 +484,8 @@
 /*
  * Simple, special scheduling class for the per-CPU idle tasks:
  */
-const struct sched_class idle_sched_class = {
-	/* .next is NULL */
+const struct sched_class idle_sched_class
+	__section("__idle_sched_class") = {
 	/* no enqueue/yield_task for idle tasks */
 
 	/* dequeue is not valid, we print a debug message there: */
@@ -474,8 +505,6 @@
 
 	.task_tick		= task_tick_idle,
 
-	.get_rr_interval	= get_rr_interval_idle,
-
 	.prio_changed		= prio_changed_idle,
 	.switched_to		= switched_to_idle,
 	.update_curr		= update_curr_idle,
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 9fcb2a6..5a6ea03 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -140,7 +140,8 @@
 {
 	unsigned int flags;
 
-	flags = HK_FLAG_TICK | HK_FLAG_WQ | HK_FLAG_TIMER | HK_FLAG_RCU | HK_FLAG_MISC;
+	flags = HK_FLAG_TICK | HK_FLAG_WQ | HK_FLAG_TIMER | HK_FLAG_RCU |
+		HK_FLAG_MISC | HK_FLAG_KTHREAD;
 
 	return housekeeping_setup(str, flags);
 }
@@ -149,6 +150,9 @@
 static int __init housekeeping_isolcpus_setup(char *str)
 {
 	unsigned int flags = 0;
+	bool illegal = false;
+	char *par;
+	int len;
 
 	while (isalpha(*str)) {
 		if (!strncmp(str, "nohz,", 5)) {
@@ -163,8 +167,28 @@
 			continue;
 		}
 
-		pr_warn("isolcpus: Error, unknown flag\n");
-		return 0;
+		if (!strncmp(str, "managed_irq,", 12)) {
+			str += 12;
+			flags |= HK_FLAG_MANAGED_IRQ;
+			continue;
+		}
+
+		/*
+		 * Skip unknown sub-parameter and validate that it is not
+		 * containing an invalid character.
+		 */
+		for (par = str, len = 0; *str && *str != ','; str++, len++) {
+			if (!isalpha(*str) && *str != '_')
+				illegal = true;
+		}
+
+		if (illegal) {
+			pr_warn("isolcpus: Invalid flag %.*s\n", len, par);
+			return 0;
+		}
+
+		pr_info("isolcpus: Skipped unknown flag %.*s\n", len, par);
+		str++;
 	}
 
 	/* Default behaviour for isolcpus without flags */
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index de22da6..d2a6556 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -347,7 +347,7 @@
  *
  * Called from the global timer code.
  */
-void calc_global_load(unsigned long ticks)
+void calc_global_load(void)
 {
 	unsigned long sample_window;
 	long active, delta;
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index 46c142b..cc7cd51 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -18,12 +18,21 @@
 #define MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK	0
 #endif
 
+#ifdef CONFIG_RSEQ
+#define MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK		\
+	(MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ			\
+	| MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ)
+#else
+#define MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK	0
+#endif
+
 #define MEMBARRIER_CMD_BITMASK						\
 	(MEMBARRIER_CMD_GLOBAL | MEMBARRIER_CMD_GLOBAL_EXPEDITED	\
 	| MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED			\
 	| MEMBARRIER_CMD_PRIVATE_EXPEDITED				\
 	| MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED			\
-	| MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK)
+	| MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK		\
+	| MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK)
 
 static void ipi_mb(void *info)
 {
@@ -47,6 +56,19 @@
 	sync_core_before_usermode();
 }
 
+static void ipi_rseq(void *info)
+{
+	/*
+	 * Ensure that all stores done by the calling thread are visible
+	 * to the current task before the current task resumes.  We could
+	 * probably optimize this away on most architectures, but by the
+	 * time we've already sent an IPI, the cost of the extra smp_mb()
+	 * is negligible.
+	 */
+	smp_mb();
+	rseq_preempt(current);
+}
+
 static void ipi_sync_rq_state(void *info)
 {
 	struct mm_struct *mm = (struct mm_struct *) info;
@@ -146,27 +168,35 @@
 	return 0;
 }
 
-static int membarrier_private_expedited(int flags)
+static int membarrier_private_expedited(int flags, int cpu_id)
 {
-	int cpu;
 	cpumask_var_t tmpmask;
 	struct mm_struct *mm = current->mm;
 	smp_call_func_t ipi_func = ipi_mb;
 
-	if (flags & MEMBARRIER_FLAG_SYNC_CORE) {
+	if (flags == MEMBARRIER_FLAG_SYNC_CORE) {
 		if (!IS_ENABLED(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE))
 			return -EINVAL;
 		if (!(atomic_read(&mm->membarrier_state) &
 		      MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY))
 			return -EPERM;
 		ipi_func = ipi_sync_core;
+	} else if (flags == MEMBARRIER_FLAG_RSEQ) {
+		if (!IS_ENABLED(CONFIG_RSEQ))
+			return -EINVAL;
+		if (!(atomic_read(&mm->membarrier_state) &
+		      MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY))
+			return -EPERM;
+		ipi_func = ipi_rseq;
 	} else {
+		WARN_ON_ONCE(flags);
 		if (!(atomic_read(&mm->membarrier_state) &
 		      MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY))
 			return -EPERM;
 	}
 
-	if (atomic_read(&mm->mm_users) == 1 || num_online_cpus() == 1)
+	if (flags != MEMBARRIER_FLAG_SYNC_CORE &&
+	    (atomic_read(&mm->mm_users) == 1 || num_online_cpus() == 1))
 		return 0;
 
 	/*
@@ -175,35 +205,73 @@
 	 */
 	smp_mb();	/* system call entry is not a mb. */
 
-	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
+	if (cpu_id < 0 && !zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
 		return -ENOMEM;
 
 	cpus_read_lock();
-	rcu_read_lock();
-	for_each_online_cpu(cpu) {
+
+	if (cpu_id >= 0) {
 		struct task_struct *p;
 
-		/*
-		 * Skipping the current CPU is OK even through we can be
-		 * migrated at any point. The current CPU, at the point
-		 * where we read raw_smp_processor_id(), is ensured to
-		 * be in program order with respect to the caller
-		 * thread. Therefore, we can skip this CPU from the
-		 * iteration.
-		 */
-		if (cpu == raw_smp_processor_id())
-			continue;
-		p = rcu_dereference(cpu_rq(cpu)->curr);
-		if (p && p->mm == mm)
-			__cpumask_set_cpu(cpu, tmpmask);
+		if (cpu_id >= nr_cpu_ids || !cpu_online(cpu_id))
+			goto out;
+		rcu_read_lock();
+		p = rcu_dereference(cpu_rq(cpu_id)->curr);
+		if (!p || p->mm != mm) {
+			rcu_read_unlock();
+			goto out;
+		}
+		rcu_read_unlock();
+	} else {
+		int cpu;
+
+		rcu_read_lock();
+		for_each_online_cpu(cpu) {
+			struct task_struct *p;
+
+			p = rcu_dereference(cpu_rq(cpu)->curr);
+			if (p && p->mm == mm)
+				__cpumask_set_cpu(cpu, tmpmask);
+		}
+		rcu_read_unlock();
 	}
-	rcu_read_unlock();
 
-	preempt_disable();
-	smp_call_function_many(tmpmask, ipi_func, NULL, 1);
-	preempt_enable();
+	if (cpu_id >= 0) {
+		/*
+		 * smp_call_function_single() will call ipi_func() if cpu_id
+		 * is the calling CPU.
+		 */
+		smp_call_function_single(cpu_id, ipi_func, NULL, 1);
+	} else {
+		/*
+		 * For regular membarrier, we can save a few cycles by
+		 * skipping the current cpu -- we're about to do smp_mb()
+		 * below, and if we migrate to a different cpu, this cpu
+		 * and the new cpu will execute a full barrier in the
+		 * scheduler.
+		 *
+		 * For SYNC_CORE, we do need a barrier on the current cpu --
+		 * otherwise, if we are migrated and replaced by a different
+		 * task in the same mm just before, during, or after
+		 * membarrier, we will end up with some thread in the mm
+		 * running without a core sync.
+		 *
+		 * For RSEQ, don't rseq_preempt() the caller.  User code
+		 * is not supposed to issue syscalls at all from inside an
+		 * rseq critical section.
+		 */
+		if (flags != MEMBARRIER_FLAG_SYNC_CORE) {
+			preempt_disable();
+			smp_call_function_many(tmpmask, ipi_func, NULL, true);
+			preempt_enable();
+		} else {
+			on_each_cpu_mask(tmpmask, ipi_func, NULL, true);
+		}
+	}
 
-	free_cpumask_var(tmpmask);
+out:
+	if (cpu_id < 0)
+		free_cpumask_var(tmpmask);
 	cpus_read_unlock();
 
 	/*
@@ -248,7 +316,7 @@
 
 	/*
 	 * For each cpu runqueue, if the task's mm match @mm, ensure that all
-	 * @mm's membarrier state set bits are also set in in the runqueue's
+	 * @mm's membarrier state set bits are also set in the runqueue's
 	 * membarrier state. This ensures that a runqueue scheduling
 	 * between threads which are users of @mm has its membarrier state
 	 * updated.
@@ -300,11 +368,18 @@
 	    set_state = MEMBARRIER_STATE_PRIVATE_EXPEDITED,
 	    ret;
 
-	if (flags & MEMBARRIER_FLAG_SYNC_CORE) {
+	if (flags == MEMBARRIER_FLAG_SYNC_CORE) {
 		if (!IS_ENABLED(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE))
 			return -EINVAL;
 		ready_state =
 			MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY;
+	} else if (flags == MEMBARRIER_FLAG_RSEQ) {
+		if (!IS_ENABLED(CONFIG_RSEQ))
+			return -EINVAL;
+		ready_state =
+			MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY;
+	} else {
+		WARN_ON_ONCE(flags);
 	}
 
 	/*
@@ -316,6 +391,8 @@
 		return 0;
 	if (flags & MEMBARRIER_FLAG_SYNC_CORE)
 		set_state |= MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE;
+	if (flags & MEMBARRIER_FLAG_RSEQ)
+		set_state |= MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ;
 	atomic_or(set_state, &mm->membarrier_state);
 	ret = sync_runqueues_membarrier_state(mm);
 	if (ret)
@@ -327,8 +404,15 @@
 
 /**
  * sys_membarrier - issue memory barriers on a set of threads
- * @cmd:   Takes command values defined in enum membarrier_cmd.
- * @flags: Currently needs to be 0. For future extensions.
+ * @cmd:    Takes command values defined in enum membarrier_cmd.
+ * @flags:  Currently needs to be 0 for all commands other than
+ *          MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ: in the latter
+ *          case it can be MEMBARRIER_CMD_FLAG_CPU, indicating that @cpu_id
+ *          contains the CPU on which to interrupt (= restart)
+ *          the RSEQ critical section.
+ * @cpu_id: if @flags == MEMBARRIER_CMD_FLAG_CPU, indicates the cpu on which
+ *          RSEQ CS should be interrupted (@cmd must be
+ *          MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ).
  *
  * If this system call is not implemented, -ENOSYS is returned. If the
  * command specified does not exist, not available on the running
@@ -354,10 +438,21 @@
  *        smp_mb()           X           O            O
  *        sys_membarrier()   O           O            O
  */
-SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
+SYSCALL_DEFINE3(membarrier, int, cmd, unsigned int, flags, int, cpu_id)
 {
-	if (unlikely(flags))
-		return -EINVAL;
+	switch (cmd) {
+	case MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+		if (unlikely(flags && flags != MEMBARRIER_CMD_FLAG_CPU))
+			return -EINVAL;
+		break;
+	default:
+		if (unlikely(flags))
+			return -EINVAL;
+	}
+
+	if (!(flags & MEMBARRIER_CMD_FLAG_CPU))
+		cpu_id = -1;
+
 	switch (cmd) {
 	case MEMBARRIER_CMD_QUERY:
 	{
@@ -379,13 +474,17 @@
 	case MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED:
 		return membarrier_register_global_expedited();
 	case MEMBARRIER_CMD_PRIVATE_EXPEDITED:
-		return membarrier_private_expedited(0);
+		return membarrier_private_expedited(0, cpu_id);
 	case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED:
 		return membarrier_register_private_expedited(0);
 	case MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE:
-		return membarrier_private_expedited(MEMBARRIER_FLAG_SYNC_CORE);
+		return membarrier_private_expedited(MEMBARRIER_FLAG_SYNC_CORE, cpu_id);
 	case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE:
 		return membarrier_register_private_expedited(MEMBARRIER_FLAG_SYNC_CORE);
+	case MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+		return membarrier_private_expedited(MEMBARRIER_FLAG_RSEQ, cpu_id);
+	case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ:
+		return membarrier_register_private_expedited(MEMBARRIER_FLAG_RSEQ);
 	default:
 		return -EINVAL;
 	}
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index a96db50..2c613e1 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -28,8 +28,6 @@
 #include "sched.h"
 #include "pelt.h"
 
-#include <trace/events/sched.h>
-
 /*
  * Approximate:
  *   val * y^n,    where y^32 ~= 0.5 (~1 scheduling period)
@@ -83,8 +81,6 @@
 	return c1 + c2 + c3;
 }
 
-#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
-
 /*
  * Accumulate the three separate parts of the sum; d1 the remainder
  * of the last (incomplete) period, d2 the span of full periods and d3
@@ -121,23 +117,35 @@
 	 */
 	if (periods) {
 		sa->load_sum = decay_load(sa->load_sum, periods);
-		sa->runnable_load_sum =
-			decay_load(sa->runnable_load_sum, periods);
+		sa->runnable_sum =
+			decay_load(sa->runnable_sum, periods);
 		sa->util_sum = decay_load((u64)(sa->util_sum), periods);
 
 		/*
 		 * Step 2
 		 */
 		delta %= 1024;
-		contrib = __accumulate_pelt_segments(periods,
-				1024 - sa->period_contrib, delta);
+		if (load) {
+			/*
+			 * This relies on the:
+			 *
+			 * if (!load)
+			 *	runnable = running = 0;
+			 *
+			 * clause from ___update_load_sum(); this results in
+			 * the below usage of @contrib to dissapear entirely,
+			 * so no point in calculating it.
+			 */
+			contrib = __accumulate_pelt_segments(periods,
+					1024 - sa->period_contrib, delta);
+		}
 	}
 	sa->period_contrib = delta;
 
 	if (load)
 		sa->load_sum += load * contrib;
 	if (runnable)
-		sa->runnable_load_sum += runnable * contrib;
+		sa->runnable_sum += runnable * contrib << SCHED_CAPACITY_SHIFT;
 	if (running)
 		sa->util_sum += contrib << SCHED_CAPACITY_SHIFT;
 
@@ -205,7 +213,9 @@
 	 * This means that weight will be 0 but not running for a sched_entity
 	 * but also for a cfs_rq if the latter becomes idle. As an example,
 	 * this happens during idle_balance() which calls
-	 * update_blocked_averages()
+	 * update_blocked_averages().
+	 *
+	 * Also see the comment in accumulate_sum().
 	 */
 	if (!load)
 		runnable = running = 0;
@@ -223,16 +233,40 @@
 	return 1;
 }
 
+/*
+ * When syncing *_avg with *_sum, we must take into account the current
+ * position in the PELT segment otherwise the remaining part of the segment
+ * will be considered as idle time whereas it's not yet elapsed and this will
+ * generate unwanted oscillation in the range [1002..1024[.
+ *
+ * The max value of *_sum varies with the position in the time segment and is
+ * equals to :
+ *
+ *   LOAD_AVG_MAX*y + sa->period_contrib
+ *
+ * which can be simplified into:
+ *
+ *   LOAD_AVG_MAX - 1024 + sa->period_contrib
+ *
+ * because LOAD_AVG_MAX*y == LOAD_AVG_MAX-1024
+ *
+ * The same care must be taken when a sched entity is added, updated or
+ * removed from a cfs_rq and we need to update sched_avg. Scheduler entities
+ * and the cfs rq, to which they are attached, have the same position in the
+ * time segment because they use the same clock. This means that we can use
+ * the period_contrib of cfs_rq when updating the sched_avg of a sched_entity
+ * if it's more convenient.
+ */
 static __always_inline void
-___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runnable)
+___update_load_avg(struct sched_avg *sa, unsigned long load)
 {
-	u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib;
+	u32 divider = get_pelt_divider(sa);
 
 	/*
 	 * Step 2: update *_avg.
 	 */
 	sa->load_avg = div_u64(load * sa->load_sum, divider);
-	sa->runnable_load_avg =	div_u64(runnable * sa->runnable_load_sum, divider);
+	sa->runnable_avg = div_u64(sa->runnable_sum, divider);
 	WRITE_ONCE(sa->util_avg, sa->util_sum / divider);
 }
 
@@ -240,33 +274,32 @@
  * sched_entity:
  *
  *   task:
- *     se_runnable() == se_weight()
+ *     se_weight()   = se->load.weight
+ *     se_runnable() = !!on_rq
  *
  *   group: [ see update_cfs_group() ]
  *     se_weight()   = tg->weight * grq->load_avg / tg->load_avg
- *     se_runnable() = se_weight(se) * grq->runnable_load_avg / grq->load_avg
+ *     se_runnable() = grq->h_nr_running
  *
- *   load_sum := runnable_sum
- *   load_avg = se_weight(se) * runnable_avg
+ *   runnable_sum = se_runnable() * runnable = grq->runnable_sum
+ *   runnable_avg = runnable_sum
  *
- *   runnable_load_sum := runnable_sum
- *   runnable_load_avg = se_runnable(se) * runnable_avg
- *
- * XXX collapse load_sum and runnable_load_sum
+ *   load_sum := runnable
+ *   load_avg = se_weight(se) * load_sum
  *
  * cfq_rq:
  *
+ *   runnable_sum = \Sum se->avg.runnable_sum
+ *   runnable_avg = \Sum se->avg.runnable_avg
+ *
  *   load_sum = \Sum se_weight(se) * se->avg.load_sum
  *   load_avg = \Sum se->avg.load_avg
- *
- *   runnable_load_sum = \Sum se_runnable(se) * se->avg.runnable_load_sum
- *   runnable_load_avg = \Sum se->avg.runable_load_avg
  */
 
 int __update_load_avg_blocked_se(u64 now, struct sched_entity *se)
 {
 	if (___update_load_sum(now, &se->avg, 0, 0, 0)) {
-		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
+		___update_load_avg(&se->avg, se_weight(se));
 		trace_pelt_se_tp(se);
 		return 1;
 	}
@@ -276,10 +309,10 @@
 
 int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	if (___update_load_sum(now, &se->avg, !!se->on_rq, !!se->on_rq,
+	if (___update_load_sum(now, &se->avg, !!se->on_rq, se_runnable(se),
 				cfs_rq->curr == se)) {
 
-		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
+		___update_load_avg(&se->avg, se_weight(se));
 		cfs_se_util_change(&se->avg);
 		trace_pelt_se_tp(se);
 		return 1;
@@ -292,10 +325,10 @@
 {
 	if (___update_load_sum(now, &cfs_rq->avg,
 				scale_load_down(cfs_rq->load.weight),
-				scale_load_down(cfs_rq->runnable_weight),
+				cfs_rq->h_nr_running,
 				cfs_rq->curr != NULL)) {
 
-		___update_load_avg(&cfs_rq->avg, 1, 1);
+		___update_load_avg(&cfs_rq->avg, 1);
 		trace_pelt_cfs_tp(cfs_rq);
 		return 1;
 	}
@@ -308,9 +341,9 @@
  *
  *   util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked
  *   util_sum = cpu_scale * load_sum
- *   runnable_load_sum = load_sum
+ *   runnable_sum = util_sum
  *
- *   load_avg and runnable_load_avg are not supported and meaningless.
+ *   load_avg and runnable_avg are not supported and meaningless.
  *
  */
 
@@ -321,7 +354,7 @@
 				running,
 				running)) {
 
-		___update_load_avg(&rq->avg_rt, 1, 1);
+		___update_load_avg(&rq->avg_rt, 1);
 		trace_pelt_rt_tp(rq);
 		return 1;
 	}
@@ -334,7 +367,9 @@
  *
  *   util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked
  *   util_sum = cpu_scale * load_sum
- *   runnable_load_sum = load_sum
+ *   runnable_sum = util_sum
+ *
+ *   load_avg and runnable_avg are not supported and meaningless.
  *
  */
 
@@ -345,7 +380,7 @@
 				running,
 				running)) {
 
-		___update_load_avg(&rq->avg_dl, 1, 1);
+		___update_load_avg(&rq->avg_dl, 1);
 		trace_pelt_dl_tp(rq);
 		return 1;
 	}
@@ -353,13 +388,46 @@
 	return 0;
 }
 
+#ifdef CONFIG_SCHED_THERMAL_PRESSURE
+/*
+ * thermal:
+ *
+ *   load_sum = \Sum se->avg.load_sum but se->avg.load_sum is not tracked
+ *
+ *   util_avg and runnable_load_avg are not supported and meaningless.
+ *
+ * Unlike rt/dl utilization tracking that track time spent by a cpu
+ * running a rt/dl task through util_avg, the average thermal pressure is
+ * tracked through load_avg. This is because thermal pressure signal is
+ * time weighted "delta" capacity unlike util_avg which is binary.
+ * "delta capacity" =  actual capacity  -
+ *			capped capacity a cpu due to a thermal event.
+ */
+
+int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity)
+{
+	if (___update_load_sum(now, &rq->avg_thermal,
+			       capacity,
+			       capacity,
+			       capacity)) {
+		___update_load_avg(&rq->avg_thermal, 1);
+		trace_pelt_thermal_tp(rq);
+		return 1;
+	}
+
+	return 0;
+}
+#endif
+
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 /*
  * irq:
  *
  *   util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked
  *   util_sum = cpu_scale * load_sum
- *   runnable_load_sum = load_sum
+ *   runnable_sum = util_sum
+ *
+ *   load_avg and runnable_avg are not supported and meaningless.
  *
  */
 
@@ -396,7 +464,7 @@
 				1);
 
 	if (ret) {
-		___update_load_avg(&rq->avg_irq, 1, 1);
+		___update_load_avg(&rq->avg_irq, 1);
 		trace_pelt_irq_tp(rq);
 	}
 
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
index afff644..45bf08e 100644
--- a/kernel/sched/pelt.h
+++ b/kernel/sched/pelt.h
@@ -7,6 +7,26 @@
 int update_rt_rq_load_avg(u64 now, struct rq *rq, int running);
 int update_dl_rq_load_avg(u64 now, struct rq *rq, int running);
 
+#ifdef CONFIG_SCHED_THERMAL_PRESSURE
+int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity);
+
+static inline u64 thermal_load_avg(struct rq *rq)
+{
+	return READ_ONCE(rq->avg_thermal.load_avg);
+}
+#else
+static inline int
+update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity)
+{
+	return 0;
+}
+
+static inline u64 thermal_load_avg(struct rq *rq)
+{
+	return 0;
+}
+#endif
+
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 int update_irq_load_avg(struct rq *rq, u64 running);
 #else
@@ -17,14 +37,12 @@
 }
 #endif
 
-/*
- * When a task is dequeued, its estimated utilization should not be update if
- * its util_avg has not been updated at least once.
- * This flag is used to synchronize util_avg updates with util_est updates.
- * We map this information into the LSB bit of the utilization saved at
- * dequeue time (i.e. util_est.dequeued).
- */
-#define UTIL_AVG_UNCHANGED 0x1
+#define PELT_MIN_DIVIDER	(LOAD_AVG_MAX - 1024)
+
+static inline u32 get_pelt_divider(struct sched_avg *avg)
+{
+	return PELT_MIN_DIVIDER + avg->period_contrib;
+}
 
 static inline void cfs_se_util_change(struct sched_avg *avg)
 {
@@ -33,7 +51,7 @@
 	if (!sched_feat(UTIL_EST))
 		return;
 
-	/* Avoid store if the flag has been already set */
+	/* Avoid store if the flag has been already reset */
 	enqueued = avg->util_est.enqueued;
 	if (!(enqueued & UTIL_AVG_UNCHANGED))
 		return;
@@ -159,6 +177,17 @@
 }
 
 static inline int
+update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity)
+{
+	return 0;
+}
+
+static inline u64 thermal_load_avg(struct rq *rq)
+{
+	return 0;
+}
+
+static inline int
 update_irq_load_avg(struct rq *rq, u64 running)
 {
 	return 0;
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 9154e74..b7f38f3 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -179,6 +179,8 @@
 
 static void psi_avgs_work(struct work_struct *work);
 
+static void poll_timer_fn(struct timer_list *t);
+
 static void group_init(struct psi_group *group)
 {
 	int cpu;
@@ -190,7 +192,6 @@
 	INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work);
 	mutex_init(&group->avgs_lock);
 	/* Init trigger-related members */
-	atomic_set(&group->poll_scheduled, 0);
 	mutex_init(&group->trigger_lock);
 	INIT_LIST_HEAD(&group->triggers);
 	memset(group->nr_triggers, 0, sizeof(group->nr_triggers));
@@ -199,7 +200,9 @@
 	memset(group->polling_total, 0, sizeof(group->polling_total));
 	group->polling_next_update = ULLONG_MAX;
 	group->polling_until = 0;
-	rcu_assign_pointer(group->poll_kworker, NULL);
+	init_waitqueue_head(&group->poll_wait);
+	timer_setup(&group->poll_timer, poll_timer_fn, 0);
+	rcu_assign_pointer(group->poll_task, NULL);
 }
 
 void __init psi_init(void)
@@ -225,7 +228,7 @@
 	case PSI_MEM_FULL:
 		return tasks[NR_MEMSTALL] && !tasks[NR_RUNNING];
 	case PSI_CPU_SOME:
-		return tasks[NR_RUNNING] > 1;
+		return tasks[NR_RUNNING] > tasks[NR_ONCPU];
 	case PSI_NONIDLE:
 		return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] ||
 			tasks[NR_RUNNING];
@@ -547,47 +550,38 @@
 	return now + group->poll_min_period;
 }
 
-/*
- * Schedule polling if it's not already scheduled. It's safe to call even from
- * hotpath because even though kthread_queue_delayed_work takes worker->lock
- * spinlock that spinlock is never contended due to poll_scheduled atomic
- * preventing such competition.
- */
+/* Schedule polling if it's not already scheduled. */
 static void psi_schedule_poll_work(struct psi_group *group, unsigned long delay)
 {
-	struct kthread_worker *kworker;
+	struct task_struct *task;
 
-	/* Do not reschedule if already scheduled */
-	if (atomic_cmpxchg(&group->poll_scheduled, 0, 1) != 0)
+	/*
+	 * Do not reschedule if already scheduled.
+	 * Possible race with a timer scheduled after this check but before
+	 * mod_timer below can be tolerated because group->polling_next_update
+	 * will keep updates on schedule.
+	 */
+	if (timer_pending(&group->poll_timer))
 		return;
 
 	rcu_read_lock();
 
-	kworker = rcu_dereference(group->poll_kworker);
+	task = rcu_dereference(group->poll_task);
 	/*
 	 * kworker might be NULL in case psi_trigger_destroy races with
 	 * psi_task_change (hotpath) which can't use locks
 	 */
-	if (likely(kworker))
-		kthread_queue_delayed_work(kworker, &group->poll_work, delay);
-	else
-		atomic_set(&group->poll_scheduled, 0);
+	if (likely(task))
+		mod_timer(&group->poll_timer, jiffies + delay);
 
 	rcu_read_unlock();
 }
 
-static void psi_poll_work(struct kthread_work *work)
+static void psi_poll_work(struct psi_group *group)
 {
-	struct kthread_delayed_work *dwork;
-	struct psi_group *group;
 	u32 changed_states;
 	u64 now;
 
-	dwork = container_of(work, struct kthread_delayed_work, work);
-	group = container_of(dwork, struct psi_group, poll_work);
-
-	atomic_set(&group->poll_scheduled, 0);
-
 	mutex_lock(&group->trigger_lock);
 
 	now = sched_clock();
@@ -623,6 +617,32 @@
 	mutex_unlock(&group->trigger_lock);
 }
 
+static int psi_poll_worker(void *data)
+{
+	struct psi_group *group = (struct psi_group *)data;
+
+	sched_set_fifo_low(current);
+
+	while (true) {
+		wait_event_interruptible(group->poll_wait,
+				atomic_cmpxchg(&group->poll_wakeup, 1, 0) ||
+				kthread_should_stop());
+		if (kthread_should_stop())
+			break;
+
+		psi_poll_work(group);
+	}
+	return 0;
+}
+
+static void poll_timer_fn(struct timer_list *t)
+{
+	struct psi_group *group = from_timer(group, t, poll_timer);
+
+	atomic_set(&group->poll_wakeup, 1);
+	wake_up_interruptible(&group->poll_wait);
+}
+
 static void record_times(struct psi_group_cpu *groupc, int cpu,
 			 bool memstall_tick)
 {
@@ -669,13 +689,14 @@
 		groupc->times[PSI_NONIDLE] += delta;
 }
 
-static u32 psi_group_change(struct psi_group *group, int cpu,
-			    unsigned int clear, unsigned int set)
+static void psi_group_change(struct psi_group *group, int cpu,
+			     unsigned int clear, unsigned int set,
+			     bool wake_clock)
 {
 	struct psi_group_cpu *groupc;
+	u32 state_mask = 0;
 	unsigned int t, m;
 	enum psi_states s;
-	u32 state_mask = 0;
 
 	groupc = per_cpu_ptr(group->pcpu, cpu);
 
@@ -694,14 +715,15 @@
 	for (t = 0, m = clear; m; m &= ~(1 << t), t++) {
 		if (!(m & (1 << t)))
 			continue;
-		if (groupc->tasks[t] == 0 && !psi_bug) {
-			printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u] clear=%x set=%x\n",
+		if (groupc->tasks[t]) {
+			groupc->tasks[t]--;
+		} else if (!psi_bug) {
+			printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u %u] clear=%x set=%x\n",
 					cpu, t, groupc->tasks[0],
 					groupc->tasks[1], groupc->tasks[2],
-					clear, set);
+					groupc->tasks[3], clear, set);
 			psi_bug = 1;
 		}
-		groupc->tasks[t]--;
 	}
 
 	for (t = 0; set; set &= ~(1 << t), t++)
@@ -717,7 +739,11 @@
 
 	write_seqcount_end(&groupc->seq);
 
-	return state_mask;
+	if (state_mask & group->poll_states)
+		psi_schedule_poll_work(group, 1);
+
+	if (wake_clock && !delayed_work_pending(&group->avgs_work))
+		schedule_delayed_work(&group->avgs_work, PSI_FREQ);
 }
 
 static struct psi_group *iterate_groups(struct task_struct *task, void **iter)
@@ -744,6 +770,21 @@
 	return &psi_system;
 }
 
+static void psi_flags_change(struct task_struct *task, int clear, int set)
+{
+	if (((task->psi_flags & set) ||
+	     (task->psi_flags & clear) != clear) &&
+	    !psi_bug) {
+		printk_deferred(KERN_ERR "psi: inconsistent task state! task=%d:%s cpu=%d psi_flags=%x clear=%x set=%x\n",
+				task->pid, task->comm, task_cpu(task),
+				task->psi_flags, clear, set);
+		psi_bug = 1;
+	}
+
+	task->psi_flags &= ~clear;
+	task->psi_flags |= set;
+}
+
 void psi_task_change(struct task_struct *task, int clear, int set)
 {
 	int cpu = task_cpu(task);
@@ -754,17 +795,7 @@
 	if (!task->pid)
 		return;
 
-	if (((task->psi_flags & set) ||
-	     (task->psi_flags & clear) != clear) &&
-	    !psi_bug) {
-		printk_deferred(KERN_ERR "psi: inconsistent task state! task=%d:%s cpu=%d psi_flags=%x clear=%x set=%x\n",
-				task->pid, task->comm, cpu,
-				task->psi_flags, clear, set);
-		psi_bug = 1;
-	}
-
-	task->psi_flags &= ~clear;
-	task->psi_flags |= set;
+	psi_flags_change(task, clear, set);
 
 	/*
 	 * Periodic aggregation shuts off if there is a period of no
@@ -777,14 +808,51 @@
 		     wq_worker_last_func(task) == psi_avgs_work))
 		wake_clock = false;
 
-	while ((group = iterate_groups(task, &iter))) {
-		u32 state_mask = psi_group_change(group, cpu, clear, set);
+	while ((group = iterate_groups(task, &iter)))
+		psi_group_change(group, cpu, clear, set, wake_clock);
+}
 
-		if (state_mask & group->poll_states)
-			psi_schedule_poll_work(group, 1);
+void psi_task_switch(struct task_struct *prev, struct task_struct *next,
+		     bool sleep)
+{
+	struct psi_group *group, *common = NULL;
+	int cpu = task_cpu(prev);
+	void *iter;
 
-		if (wake_clock && !delayed_work_pending(&group->avgs_work))
-			schedule_delayed_work(&group->avgs_work, PSI_FREQ);
+	if (next->pid) {
+		psi_flags_change(next, 0, TSK_ONCPU);
+		/*
+		 * When moving state between tasks, the group that
+		 * contains them both does not change: we can stop
+		 * updating the tree once we reach the first common
+		 * ancestor. Iterate @next's ancestors until we
+		 * encounter @prev's state.
+		 */
+		iter = NULL;
+		while ((group = iterate_groups(next, &iter))) {
+			if (per_cpu_ptr(group->pcpu, cpu)->tasks[NR_ONCPU]) {
+				common = group;
+				break;
+			}
+
+			psi_group_change(group, cpu, 0, TSK_ONCPU, true);
+		}
+	}
+
+	/*
+	 * If this is a voluntary sleep, dequeue will have taken care
+	 * of the outgoing TSK_ONCPU alongside TSK_RUNNING already. We
+	 * only need to deal with it during preemption.
+	 */
+	if (sleep)
+		return;
+
+	if (prev->pid) {
+		psi_flags_change(prev, TSK_ONCPU, 0);
+
+		iter = NULL;
+		while ((group = iterate_groups(prev, &iter)) && group != common)
+			psi_group_change(group, cpu, TSK_ONCPU, 0, true);
 	}
 }
 
@@ -818,17 +886,17 @@
 	if (static_branch_likely(&psi_disabled))
 		return;
 
-	*flags = current->flags & PF_MEMSTALL;
+	*flags = current->in_memstall;
 	if (*flags)
 		return;
 	/*
-	 * PF_MEMSTALL setting & accounting needs to be atomic wrt
+	 * in_memstall setting & accounting needs to be atomic wrt
 	 * changes to the task's scheduling state, otherwise we can
 	 * race with CPU migration.
 	 */
 	rq = this_rq_lock_irq(&rf);
 
-	current->flags |= PF_MEMSTALL;
+	current->in_memstall = 1;
 	psi_task_change(current, 0, TSK_MEMSTALL);
 
 	rq_unlock_irq(rq, &rf);
@@ -851,13 +919,13 @@
 	if (*flags)
 		return;
 	/*
-	 * PF_MEMSTALL clearing & accounting needs to be atomic wrt
+	 * in_memstall clearing & accounting needs to be atomic wrt
 	 * changes to the task's scheduling state, otherwise we could
 	 * race with CPU migration.
 	 */
 	rq = this_rq_lock_irq(&rf);
 
-	current->flags &= ~PF_MEMSTALL;
+	current->in_memstall = 0;
 	psi_task_change(current, TSK_MEMSTALL, 0);
 
 	rq_unlock_irq(rq, &rf);
@@ -916,12 +984,14 @@
 
 	rq = task_rq_lock(task, &rf);
 
-	if (task_on_rq_queued(task))
+	if (task_on_rq_queued(task)) {
 		task_flags = TSK_RUNNING;
-	else if (task->in_iowait)
+		if (task_current(rq, task))
+			task_flags |= TSK_ONCPU;
+	} else if (task->in_iowait)
 		task_flags = TSK_IOWAIT;
 
-	if (task->flags & PF_MEMSTALL)
+	if (task->in_memstall)
 		task_flags |= TSK_MEMSTALL;
 
 	if (task_flags)
@@ -1046,26 +1116,21 @@
 	t->event = 0;
 	t->last_event_time = 0;
 	init_waitqueue_head(&t->event_wait);
-	kref_init(&t->refcount);
 
 	mutex_lock(&group->trigger_lock);
 
-	if (!rcu_access_pointer(group->poll_kworker)) {
-		struct sched_param param = {
-			.sched_priority = 1,
-		};
-		struct kthread_worker *kworker;
+	if (!rcu_access_pointer(group->poll_task)) {
+		struct task_struct *task;
 
-		kworker = kthread_create_worker(0, "psimon");
-		if (IS_ERR(kworker)) {
+		task = kthread_create(psi_poll_worker, group, "psimon");
+		if (IS_ERR(task)) {
 			kfree(t);
 			mutex_unlock(&group->trigger_lock);
-			return ERR_CAST(kworker);
+			return ERR_CAST(task);
 		}
-		sched_setscheduler_nocheck(kworker->task, SCHED_FIFO, &param);
-		kthread_init_delayed_work(&group->poll_work,
-				psi_poll_work);
-		rcu_assign_pointer(group->poll_kworker, kworker);
+		atomic_set(&group->poll_wakeup, 0);
+		wake_up_process(task);
+		rcu_assign_pointer(group->poll_task, task);
 	}
 
 	list_add(&t->node, &group->triggers);
@@ -1079,15 +1144,19 @@
 	return t;
 }
 
-static void psi_trigger_destroy(struct kref *ref)
+void psi_trigger_destroy(struct psi_trigger *t)
 {
-	struct psi_trigger *t = container_of(ref, struct psi_trigger, refcount);
-	struct psi_group *group = t->group;
-	struct kthread_worker *kworker_to_destroy = NULL;
+	struct psi_group *group;
+	struct task_struct *task_to_destroy = NULL;
 
-	if (static_branch_likely(&psi_disabled))
+	/*
+	 * We do not check psi_disabled since it might have been disabled after
+	 * the trigger got created.
+	 */
+	if (!t)
 		return;
 
+	group = t->group;
 	/*
 	 * Wakeup waiters to stop polling. Can happen if cgroup is deleted
 	 * from under a polling process.
@@ -1109,55 +1178,39 @@
 			period = min(period, div_u64(tmp->win.size,
 					UPDATES_PER_WINDOW));
 		group->poll_min_period = period;
-		/* Destroy poll_kworker when the last trigger is destroyed */
+		/* Destroy poll_task when the last trigger is destroyed */
 		if (group->poll_states == 0) {
 			group->polling_until = 0;
-			kworker_to_destroy = rcu_dereference_protected(
-					group->poll_kworker,
+			task_to_destroy = rcu_dereference_protected(
+					group->poll_task,
 					lockdep_is_held(&group->trigger_lock));
-			rcu_assign_pointer(group->poll_kworker, NULL);
+			rcu_assign_pointer(group->poll_task, NULL);
+			del_timer(&group->poll_timer);
 		}
 	}
 
 	mutex_unlock(&group->trigger_lock);
 
 	/*
-	 * Wait for both *trigger_ptr from psi_trigger_replace and
-	 * poll_kworker RCUs to complete their read-side critical sections
-	 * before destroying the trigger and optionally the poll_kworker
+	 * Wait for psi_schedule_poll_work RCU to complete its read-side
+	 * critical section before destroying the trigger and optionally the
+	 * poll_task.
 	 */
 	synchronize_rcu();
 	/*
-	 * Destroy the kworker after releasing trigger_lock to prevent a
+	 * Stop kthread 'psimon' after releasing trigger_lock to prevent a
 	 * deadlock while waiting for psi_poll_work to acquire trigger_lock
 	 */
-	if (kworker_to_destroy) {
+	if (task_to_destroy) {
 		/*
 		 * After the RCU grace period has expired, the worker
-		 * can no longer be found through group->poll_kworker.
-		 * But it might have been already scheduled before
-		 * that - deschedule it cleanly before destroying it.
+		 * can no longer be found through group->poll_task.
 		 */
-		kthread_cancel_delayed_work_sync(&group->poll_work);
-		atomic_set(&group->poll_scheduled, 0);
-
-		kthread_destroy_worker(kworker_to_destroy);
+		kthread_stop(task_to_destroy);
 	}
 	kfree(t);
 }
 
-void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *new)
-{
-	struct psi_trigger *old = *trigger_ptr;
-
-	if (static_branch_likely(&psi_disabled))
-		return;
-
-	rcu_assign_pointer(*trigger_ptr, new);
-	if (old)
-		kref_put(&old->refcount, psi_trigger_destroy);
-}
-
 __poll_t psi_trigger_poll(void **trigger_ptr,
 				struct file *file, poll_table *wait)
 {
@@ -1167,24 +1220,15 @@
 	if (static_branch_likely(&psi_disabled))
 		return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI;
 
-	rcu_read_lock();
-
-	t = rcu_dereference(*(void __rcu __force **)trigger_ptr);
-	if (!t) {
-		rcu_read_unlock();
+	t = smp_load_acquire(trigger_ptr);
+	if (!t)
 		return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI;
-	}
-	kref_get(&t->refcount);
-
-	rcu_read_unlock();
 
 	poll_wait(file, &t->event_wait, wait);
 
 	if (cmpxchg(&t->event, 1, 0) == 1)
 		ret |= EPOLLPRI;
 
-	kref_put(&t->refcount, psi_trigger_destroy);
-
 	return ret;
 }
 
@@ -1208,14 +1252,24 @@
 
 	buf[buf_size - 1] = '\0';
 
-	new = psi_trigger_create(&psi_system, buf, nbytes, res);
-	if (IS_ERR(new))
-		return PTR_ERR(new);
-
 	seq = file->private_data;
+
 	/* Take seq->lock to protect seq->private from concurrent writes */
 	mutex_lock(&seq->lock);
-	psi_trigger_replace(&seq->private, new);
+
+	/* Allow only one trigger per file descriptor */
+	if (seq->private) {
+		mutex_unlock(&seq->lock);
+		return -EBUSY;
+	}
+
+	new = psi_trigger_create(&psi_system, buf, nbytes, res);
+	if (IS_ERR(new)) {
+		mutex_unlock(&seq->lock);
+		return PTR_ERR(new);
+	}
+
+	smp_store_release(&seq->private, new);
 	mutex_unlock(&seq->lock);
 
 	return nbytes;
@@ -1250,43 +1304,45 @@
 {
 	struct seq_file *seq = file->private_data;
 
-	psi_trigger_replace(&seq->private, NULL);
+	psi_trigger_destroy(seq->private);
 	return single_release(inode, file);
 }
 
-static const struct file_operations psi_io_fops = {
-	.open           = psi_io_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.write          = psi_io_write,
-	.poll           = psi_fop_poll,
-	.release        = psi_fop_release,
+static const struct proc_ops psi_io_proc_ops = {
+	.proc_open	= psi_io_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_write	= psi_io_write,
+	.proc_poll	= psi_fop_poll,
+	.proc_release	= psi_fop_release,
 };
 
-static const struct file_operations psi_memory_fops = {
-	.open           = psi_memory_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.write          = psi_memory_write,
-	.poll           = psi_fop_poll,
-	.release        = psi_fop_release,
+static const struct proc_ops psi_memory_proc_ops = {
+	.proc_open	= psi_memory_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_write	= psi_memory_write,
+	.proc_poll	= psi_fop_poll,
+	.proc_release	= psi_fop_release,
 };
 
-static const struct file_operations psi_cpu_fops = {
-	.open           = psi_cpu_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.write          = psi_cpu_write,
-	.poll           = psi_fop_poll,
-	.release        = psi_fop_release,
+static const struct proc_ops psi_cpu_proc_ops = {
+	.proc_open	= psi_cpu_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_write	= psi_cpu_write,
+	.proc_poll	= psi_fop_poll,
+	.proc_release	= psi_fop_release,
 };
 
 static int __init psi_proc_init(void)
 {
-	proc_mkdir("pressure", NULL);
-	proc_create("pressure/io", 0, NULL, &psi_io_fops);
-	proc_create("pressure/memory", 0, NULL, &psi_memory_fops);
-	proc_create("pressure/cpu", 0, NULL, &psi_cpu_fops);
+	if (psi_enable) {
+		proc_mkdir("pressure", NULL);
+		proc_create("pressure/io", 0, NULL, &psi_io_proc_ops);
+		proc_create("pressure/memory", 0, NULL, &psi_memory_proc_ops);
+		proc_create("pressure/cpu", 0, NULL, &psi_cpu_proc_ops);
+	}
 	return 0;
 }
 module_init(psi_proc_init);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 2dffb87..41b14d9 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -52,11 +52,8 @@
 	rt_b->rt_period_timer.function = sched_rt_period_timer;
 }
 
-static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
+static inline void do_start_rt_bandwidth(struct rt_bandwidth *rt_b)
 {
-	if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
-		return;
-
 	raw_spin_lock(&rt_b->rt_runtime_lock);
 	if (!rt_b->rt_period_active) {
 		rt_b->rt_period_active = 1;
@@ -75,6 +72,14 @@
 	raw_spin_unlock(&rt_b->rt_runtime_lock);
 }
 
+static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
+{
+	if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
+		return;
+
+	do_start_rt_bandwidth(rt_b);
+}
+
 void init_rt_rq(struct rt_rq *rt_rq)
 {
 	struct rt_prio_array *array;
@@ -439,6 +444,45 @@
 	return rt_se->on_rq;
 }
 
+#ifdef CONFIG_UCLAMP_TASK
+/*
+ * Verify the fitness of task @p to run on @cpu taking into account the uclamp
+ * settings.
+ *
+ * This check is only important for heterogeneous systems where uclamp_min value
+ * is higher than the capacity of a @cpu. For non-heterogeneous system this
+ * function will always return true.
+ *
+ * The function will return true if the capacity of the @cpu is >= the
+ * uclamp_min and false otherwise.
+ *
+ * Note that uclamp_min will be clamped to uclamp_max if uclamp_min
+ * > uclamp_max.
+ */
+static inline bool rt_task_fits_capacity(struct task_struct *p, int cpu)
+{
+	unsigned int min_cap;
+	unsigned int max_cap;
+	unsigned int cpu_cap;
+
+	/* Only heterogeneous systems can benefit from this check */
+	if (!static_branch_unlikely(&sched_asym_cpucapacity))
+		return true;
+
+	min_cap = uclamp_eff_value(p, UCLAMP_MIN);
+	max_cap = uclamp_eff_value(p, UCLAMP_MAX);
+
+	cpu_cap = capacity_orig_of(cpu);
+
+	return cpu_cap >= min(min_cap, max_cap);
+}
+#else
+static inline bool rt_task_fits_capacity(struct task_struct *p, int cpu)
+{
+	return true;
+}
+#endif
+
 #ifdef CONFIG_RT_GROUP_SCHED
 
 static inline u64 sched_rt_runtime(struct rt_rq *rt_rq)
@@ -983,13 +1027,17 @@
 
 	for_each_sched_rt_entity(rt_se) {
 		struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
+		int exceeded;
 
 		if (sched_rt_runtime(rt_rq) != RUNTIME_INF) {
 			raw_spin_lock(&rt_rq->rt_runtime_lock);
 			rt_rq->rt_time += delta_exec;
-			if (sched_rt_runtime_exceeded(rt_rq))
+			exceeded = sched_rt_runtime_exceeded(rt_rq);
+			if (exceeded)
 				resched_curr(rq);
 			raw_spin_unlock(&rt_rq->rt_runtime_lock);
+			if (exceeded)
+				do_start_rt_bandwidth(sched_rt_bandwidth(rt_rq));
 		}
 	}
 }
@@ -1393,6 +1441,7 @@
 {
 	struct task_struct *curr;
 	struct rq *rq;
+	bool test;
 
 	/* For anything but wake ups, just return the task_cpu */
 	if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK)
@@ -1424,13 +1473,26 @@
 	 *
 	 * This test is optimistic, if we get it wrong the load-balancer
 	 * will have to sort it out.
+	 *
+	 * We take into account the capacity of the CPU to ensure it fits the
+	 * requirement of the task - which is only important on heterogeneous
+	 * systems like big.LITTLE.
 	 */
-	if (curr && unlikely(rt_task(curr)) &&
-	    (curr->nr_cpus_allowed < 2 ||
-	     curr->prio <= p->prio)) {
+	test = curr &&
+	       unlikely(rt_task(curr)) &&
+	       (curr->nr_cpus_allowed < 2 || curr->prio <= p->prio);
+
+	if (test || !rt_task_fits_capacity(p, cpu)) {
 		int target = find_lowest_rq(p);
 
 		/*
+		 * Bail out if we were forcing a migration to find a better
+		 * fitting CPU but our search failed.
+		 */
+		if (!test && target != -1 && !rt_task_fits_capacity(p, target))
+			goto out_unlock;
+
+		/*
 		 * Don't bother moving it if the destination CPU is
 		 * not running a lower priority task.
 		 */
@@ -1438,6 +1500,8 @@
 		    p->prio < cpu_rq(target)->rt.highest_prio.curr)
 			cpu = target;
 	}
+
+out_unlock:
 	rcu_read_unlock();
 
 out:
@@ -1458,8 +1522,8 @@
 	 * p is migratable, so let's not schedule it and
 	 * see if it is pushed or pulled somewhere else.
 	 */
-	if (p->nr_cpus_allowed != 1
-	    && cpupri_find(&rq->rd->cpupri, p, NULL))
+	if (p->nr_cpus_allowed != 1 &&
+	    cpupri_find(&rq->rd->cpupri, p, NULL))
 		return;
 
 	/*
@@ -1569,13 +1633,10 @@
 	return rt_task_of(rt_se);
 }
 
-static struct task_struct *
-pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+static struct task_struct *pick_next_task_rt(struct rq *rq)
 {
 	struct task_struct *p;
 
-	WARN_ON_ONCE(prev || rf);
-
 	if (!sched_rt_runnable(rq))
 		return NULL;
 
@@ -1640,6 +1701,7 @@
 	struct cpumask *lowest_mask = this_cpu_cpumask_var_ptr(local_cpu_mask);
 	int this_cpu = smp_processor_id();
 	int cpu      = task_cpu(task);
+	int ret;
 
 	/* Make sure the mask is initialized first */
 	if (unlikely(!lowest_mask))
@@ -1648,7 +1710,22 @@
 	if (task->nr_cpus_allowed == 1)
 		return -1; /* No other targets possible */
 
-	if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask))
+	/*
+	 * If we're on asym system ensure we consider the different capacities
+	 * of the CPUs when searching for the lowest_mask.
+	 */
+	if (static_branch_unlikely(&sched_asym_cpucapacity)) {
+
+		ret = cpupri_find_fitness(&task_rq(task)->rd->cpupri,
+					  task, lowest_mask,
+					  rt_task_fits_capacity);
+	} else {
+
+		ret = cpupri_find(&task_rq(task)->rd->cpupri,
+				  task, lowest_mask);
+	}
+
+	if (!ret)
 		return -1; /* No targets found */
 
 	/*
@@ -2152,12 +2229,14 @@
  */
 static void task_woken_rt(struct rq *rq, struct task_struct *p)
 {
-	if (!task_running(rq, p) &&
-	    !test_tsk_need_resched(rq->curr) &&
-	    p->nr_cpus_allowed > 1 &&
-	    (dl_task(rq->curr) || rt_task(rq->curr)) &&
-	    (rq->curr->nr_cpus_allowed < 2 ||
-	     rq->curr->prio <= p->prio))
+	bool need_to_push = !task_running(rq, p) &&
+			    !test_tsk_need_resched(rq->curr) &&
+			    p->nr_cpus_allowed > 1 &&
+			    (dl_task(rq->curr) || rt_task(rq->curr)) &&
+			    (rq->curr->nr_cpus_allowed < 2 ||
+			     rq->curr->prio <= p->prio);
+
+	if (need_to_push)
 		push_rt_tasks(rq);
 }
 
@@ -2366,8 +2445,8 @@
 		return 0;
 }
 
-const struct sched_class rt_sched_class = {
-	.next			= &fair_sched_class,
+const struct sched_class rt_sched_class
+	__section("__rt_sched_class") = {
 	.enqueue_task		= enqueue_task_rt,
 	.dequeue_task		= dequeue_task_rt,
 	.yield_task		= yield_task_rt,
@@ -2408,10 +2487,11 @@
  */
 static DEFINE_MUTEX(rt_constraints_mutex);
 
-/* Must be called with tasklist_lock held */
 static inline int tg_has_rt_tasks(struct task_group *tg)
 {
-	struct task_struct *g, *p;
+	struct task_struct *task;
+	struct css_task_iter it;
+	int ret = 0;
 
 	/*
 	 * Autogroups do not have RT tasks; see autogroup_create().
@@ -2419,12 +2499,12 @@
 	if (task_group_is_autogroup(tg))
 		return 0;
 
-	for_each_process_thread(g, p) {
-		if (rt_task(p) && task_group(p) == tg)
-			return 1;
-	}
+	css_task_iter_start(&tg->css, 0, &it);
+	while (!ret && (task = css_task_iter_next(&it)))
+		ret |= rt_task(task);
+	css_task_iter_end(&it);
 
-	return 0;
+	return ret;
 }
 
 struct rt_schedulable_data {
@@ -2455,9 +2535,10 @@
 		return -EINVAL;
 
 	/*
-	 * Ensure we don't starve existing RT tasks.
+	 * Ensure we don't starve existing RT tasks if runtime turns zero.
 	 */
-	if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg))
+	if (rt_bandwidth_enabled() && !runtime &&
+	    tg->rt_bandwidth.rt_runtime && tg_has_rt_tasks(tg))
 		return -EBUSY;
 
 	total = to_ratio(period, runtime);
@@ -2529,7 +2610,6 @@
 		return -EINVAL;
 
 	mutex_lock(&rt_constraints_mutex);
-	read_lock(&tasklist_lock);
 	err = __rt_schedulable(tg, rt_period, rt_runtime);
 	if (err)
 		goto unlock;
@@ -2547,7 +2627,6 @@
 	}
 	raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
 unlock:
-	read_unlock(&tasklist_lock);
 	mutex_unlock(&rt_constraints_mutex);
 
 	return err;
@@ -2606,9 +2685,7 @@
 	int ret = 0;
 
 	mutex_lock(&rt_constraints_mutex);
-	read_lock(&tasklist_lock);
 	ret = __rt_schedulable(NULL, 0, 0);
-	read_unlock(&tasklist_lock);
 	mutex_unlock(&rt_constraints_mutex);
 
 	return ret;
@@ -2659,13 +2736,16 @@
 
 static void sched_rt_do_global(void)
 {
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
 	def_rt_bandwidth.rt_runtime = global_rt_runtime();
 	def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period());
+	raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
 }
 
-int sched_rt_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos)
+int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos)
 {
 	int old_period, old_runtime;
 	static DEFINE_MUTEX(mutex);
@@ -2703,9 +2783,8 @@
 	return ret;
 }
 
-int sched_rr_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos)
+int sched_rr_handler(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos)
 {
 	int ret;
 	static DEFINE_MUTEX(mutex);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index fe755c1..08db8e0 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -67,6 +67,7 @@
 #include <linux/tsacct_kern.h>
 
 #include <asm/tlb.h>
+#include <asm-generic/vmlinux.lds.h>
 
 #ifdef CONFIG_PARAVIRT
 # include <asm/paravirt.h>
@@ -75,6 +76,8 @@
 #include "cpupri.h"
 #include "cpudeadline.h"
 
+#include <trace/events/sched.h>
+
 #ifdef CONFIG_SCHED_DEBUG
 # define SCHED_WARN_ON(x)	WARN_ONCE(x, #x)
 #else
@@ -96,6 +99,7 @@
 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);
 /*
  * Helpers for converting nanosecond timing to jiffy resolution
  */
@@ -195,6 +199,19 @@
 
 #define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
 
+static inline void update_avg(u64 *avg, u64 sample)
+{
+	s64 diff = sample - *avg;
+	*avg += diff / 8;
+}
+
+/*
+ * Shifting a value by an exponent greater *or equal* to the size of said value
+ * is UB; cap at size-1.
+ */
+#define shr_bound(val, shift)							\
+	(val >> min_t(typeof(shift), shift, BITS_PER_TYPE(typeof(val)) - 1))
+
 /*
  * !! For sched_setattr_nocheck() (kernel) only !!
  *
@@ -300,14 +317,28 @@
 	__dl_update(dl_b, -((s32)tsk_bw / cpus));
 }
 
-static inline
-bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
+static inline bool __dl_overflow(struct dl_bw *dl_b, unsigned long cap,
+				 u64 old_bw, u64 new_bw)
 {
 	return dl_b->bw != -1 &&
-	       dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
+	       cap_scale(dl_b->bw, cap) < dl_b->total_bw - old_bw + new_bw;
 }
 
-extern void dl_change_utilization(struct task_struct *p, u64 new_bw);
+/*
+ * Verify the fitness of task @p to run on @cpu taking into account the
+ * CPU original capacity and the runtime/deadline ratio of the task.
+ *
+ * The function will return true if the CPU original capacity of the
+ * @cpu scaled by SCHED_CAPACITY_SCALE >= runtime/deadline ratio of the
+ * task and false otherwise.
+ */
+static inline bool dl_task_fits_capacity(struct task_struct *p, int cpu)
+{
+	unsigned long cap = arch_scale_cpu_capacity(cpu);
+
+	return cap_scale(p->dl.dl_deadline, cap) >= p->dl.dl_runtime;
+}
+
 extern void init_dl_bw(struct dl_bw *dl_b);
 extern int  sched_dl_global_validate(void);
 extern void sched_dl_do_global(void);
@@ -340,7 +371,6 @@
 
 	u8			idle;
 	u8			period_active;
-	u8			distribute_running;
 	u8			slack_started;
 	struct hrtimer		period_timer;
 	struct hrtimer		slack_timer;
@@ -491,7 +521,6 @@
 /* CFS-related fields in a runqueue */
 struct cfs_rq {
 	struct load_weight	load;
-	unsigned long		runnable_weight;
 	unsigned int		nr_running;
 	unsigned int		h_nr_running;      /* SCHED_{NORMAL,BATCH,IDLE} */
 	unsigned int		idle_h_nr_running; /* SCHED_IDLE */
@@ -530,7 +559,7 @@
 		int		nr;
 		unsigned long	load_avg;
 		unsigned long	util_avg;
-		unsigned long	runnable_sum;
+		unsigned long	runnable_avg;
 	} removed;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -690,8 +719,30 @@
 #ifdef CONFIG_FAIR_GROUP_SCHED
 /* An entity is a task if it doesn't "own" a runqueue */
 #define entity_is_task(se)	(!se->my_q)
+
+static inline void se_update_runnable(struct sched_entity *se)
+{
+	if (!entity_is_task(se))
+		se->runnable_weight = se->my_q->h_nr_running;
+}
+
+static inline long se_runnable(struct sched_entity *se)
+{
+	if (entity_is_task(se))
+		return !!se->on_rq;
+	else
+		return se->runnable_weight;
+}
+
 #else
 #define entity_is_task(se)	1
+
+static inline void se_update_runnable(struct sched_entity *se) {}
+
+static inline long se_runnable(struct sched_entity *se)
+{
+	return !!se->on_rq;
+}
 #endif
 
 #ifdef CONFIG_SMP
@@ -703,10 +754,6 @@
 	return scale_load_down(se->load.weight);
 }
 
-static inline long se_runnable(struct sched_entity *se)
-{
-	return scale_load_down(se->runnable_weight);
-}
 
 static inline bool sched_asym_prefer(int a, int b)
 {
@@ -864,15 +911,17 @@
 #endif
 #ifdef CONFIG_NO_HZ_COMMON
 #ifdef CONFIG_SMP
-	unsigned long		last_load_update_tick;
 	unsigned long		last_blocked_load_update_tick;
 	unsigned int		has_blocked_load;
+	call_single_data_t	nohz_csd;
 #endif /* CONFIG_SMP */
 	unsigned int		nohz_tick_stopped;
-	atomic_t nohz_flags;
+	atomic_t		nohz_flags;
 #endif /* CONFIG_NO_HZ_COMMON */
 
-	unsigned long		nr_load_updates;
+#ifdef CONFIG_SMP
+	unsigned int		ttwu_pending;
+#endif
 	u64			nr_switches;
 
 #ifdef CONFIG_UCLAMP_TASK
@@ -900,7 +949,7 @@
 	 */
 	unsigned long		nr_uninterruptible;
 
-	struct task_struct	*curr;
+	struct task_struct __rcu	*curr;
 	struct task_struct	*idle;
 	struct task_struct	*stop;
 	unsigned long		next_balance;
@@ -928,6 +977,7 @@
 
 	struct callback_head	*balance_callback;
 
+	unsigned char		nohz_idle_balance;
 	unsigned char		idle_balance;
 
 	unsigned long		misfit_task_load;
@@ -948,12 +998,15 @@
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 	struct sched_avg	avg_irq;
 #endif
+#ifdef CONFIG_SCHED_THERMAL_PRESSURE
+	struct sched_avg	avg_thermal;
+#endif
 	u64			idle_stamp;
 	u64			avg_idle;
 
 	/* This is used to determine avg_idle's max value */
 	u64			max_idle_balance_cost;
-#endif
+#endif /* CONFIG_SMP */
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 	u64			prev_irq_time;
@@ -971,7 +1024,6 @@
 
 #ifdef CONFIG_SCHED_HRTICK
 #ifdef CONFIG_SMP
-	int			hrtick_csd_pending;
 	call_single_data_t	hrtick_csd;
 #endif
 	struct hrtimer		hrtick_timer;
@@ -996,10 +1048,6 @@
 	unsigned int		ttwu_local;
 #endif
 
-#ifdef CONFIG_SMP
-	struct llist_head	wake_list;
-#endif
-
 #ifdef CONFIG_CPU_IDLE
 	/* Must be inspected within a rcu lock section */
 	struct cpuidle_state	*idle_state;
@@ -1112,6 +1160,24 @@
 	return rq->clock_task;
 }
 
+/**
+ * By default the decay is the default pelt decay period.
+ * The decay shift can change the decay period in
+ * multiples of 32.
+ *  Decay shift		Decay period(ms)
+ *	0			32
+ *	1			64
+ *	2			128
+ *	3			256
+ *	4			512
+ */
+extern int sched_thermal_decay_shift;
+
+static inline u64 rq_clock_thermal(struct rq *rq)
+{
+	return rq_clock_task(rq) >> sched_thermal_decay_shift;
+}
+
 static inline void rq_clock_skip_update(struct rq *rq)
 {
 	lockdep_assert_held(&rq->lock);
@@ -1141,6 +1207,16 @@
 #endif
 };
 
+/*
+ * Lockdep annotation that avoids accidental unlocks; it's like a
+ * sticky/continuous lockdep_assert_held().
+ *
+ * This avoids code that has access to 'struct rq *rq' (basically everything in
+ * the scheduler) from accidentally unlocking the rq if they do not also have a
+ * copy of the (on-stack) 'struct rq_flags rf'.
+ *
+ * Also see Documentation/locking/lockdep-design.rst.
+ */
 static inline void rq_pin_lock(struct rq *rq, struct rq_flags *rf)
 {
 	rf->cookie = lockdep_pin_lock(&rq->lock);
@@ -1325,8 +1401,6 @@
 	rq->balance_callback = head;
 }
 
-extern void sched_ttwu_pending(void);
-
 #define rcu_dereference_check_sched_domain(p) \
 	rcu_dereference_check((p), \
 			      lockdep_is_held(&sched_domains_mutex))
@@ -1342,8 +1416,6 @@
 	for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); \
 			__sd; __sd = __sd->parent)
 
-#define for_each_lower_domain(sd) for (; sd; sd = sd->child)
-
 /**
  * highest_flag_domain - Return highest sched_domain containing flag.
  * @cpu:	The CPU whose highest level of sched domain is to
@@ -1403,7 +1475,7 @@
 	int			id;
 #endif
 
-	unsigned long		cpumask[0];		/* Balance mask */
+	unsigned long		cpumask[];		/* Balance mask */
 };
 
 struct sched_group {
@@ -1421,7 +1493,7 @@
 	 * by attaching extra space to the end of the structure,
 	 * depending on how many CPUs the kernel has booted up with)
 	 */
-	unsigned long		cpumask[0];
+	unsigned long		cpumask[];
 };
 
 static inline struct cpumask *sched_group_span(struct sched_group *sg)
@@ -1464,15 +1536,11 @@
 }
 #endif
 
-extern int newidle_balance(struct rq *this_rq, struct rq_flags *rf);
+extern void flush_smp_call_function_from_idle(void);
 
-#else
-
-static inline void sched_ttwu_pending(void) { }
-
-static inline int newidle_balance(struct rq *this_rq, struct rq_flags *rf) { return 0; }
-
-#endif /* CONFIG_SMP */
+#else /* !CONFIG_SMP: */
+static inline void flush_smp_call_function_from_idle(void) { }
+#endif
 
 #include "stats.h"
 #include "autogroup.h"
@@ -1655,7 +1723,8 @@
  */
 #define WF_SYNC			0x01		/* Waker goes to sleep after wakeup */
 #define WF_FORK			0x02		/* Child wakeup after fork */
-#define WF_MIGRATED		0x4		/* Internal use, task got migrated */
+#define WF_MIGRATED		0x04		/* Internal use, task got migrated */
+#define WF_ON_CPU		0x08		/* Wakee is on_cpu */
 
 /*
  * To aid in avoiding the subversion of "niceness" due to uneven distribution
@@ -1712,7 +1781,6 @@
 #define RETRY_TASK		((void *)-1UL)
 
 struct sched_class {
-	const struct sched_class *next;
 
 #ifdef CONFIG_UCLAMP_TASK
 	int uclamp_enabled;
@@ -1721,24 +1789,12 @@
 	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
 	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
 	void (*yield_task)   (struct rq *rq);
-	bool (*yield_to_task)(struct rq *rq, struct task_struct *p, bool preempt);
+	bool (*yield_to_task)(struct rq *rq, struct task_struct *p);
 
 	void (*check_preempt_curr)(struct rq *rq, struct task_struct *p, int flags);
 
-	/*
-	 * Both @prev and @rf are optional and may be NULL, in which case the
-	 * caller must already have invoked put_prev_task(rq, prev, rf).
-	 *
-	 * Otherwise it is the responsibility of the pick_next_task() to call
-	 * put_prev_task() on the @prev task or something equivalent, IFF it
-	 * returns a next task.
-	 *
-	 * In that case (@rf != NULL) it may return RETRY_TASK when it finds a
-	 * higher prio class has runnable tasks.
-	 */
-	struct task_struct * (*pick_next_task)(struct rq *rq,
-					       struct task_struct *prev,
-					       struct rq_flags *rf);
+	struct task_struct *(*pick_next_task)(struct rq *rq);
+
 	void (*put_prev_task)(struct rq *rq, struct task_struct *p);
 	void (*set_next_task)(struct rq *rq, struct task_struct *p, bool first);
 
@@ -1781,7 +1837,7 @@
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	void (*task_change_group)(struct task_struct *p, int type);
 #endif
-};
+} __aligned(STRUCT_ALIGNMENT); /* STRUCT_ALIGN(), vmlinux.lds.h */
 
 static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
@@ -1795,17 +1851,18 @@
 	next->sched_class->set_next_task(rq, next, false);
 }
 
-#ifdef CONFIG_SMP
-#define sched_class_highest (&stop_sched_class)
-#else
-#define sched_class_highest (&dl_sched_class)
-#endif
+/* Defined in include/asm-generic/vmlinux.lds.h */
+extern struct sched_class __begin_sched_classes[];
+extern struct sched_class __end_sched_classes[];
+
+#define sched_class_highest (__end_sched_classes - 1)
+#define sched_class_lowest  (__begin_sched_classes - 1)
 
 #define for_class_range(class, _from, _to) \
-	for (class = (_from); class != (_to); class = class->next)
+	for (class = (_from); class != (_to); class--)
 
 #define for_each_class(class) \
-	for_class_range(class, sched_class_highest, NULL)
+	for_class_range(class, sched_class_highest, sched_class_lowest)
 
 extern const struct sched_class stop_sched_class;
 extern const struct sched_class dl_sched_class;
@@ -1833,6 +1890,9 @@
 	return rq->cfs.nr_running > 0;
 }
 
+extern struct task_struct *pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
+extern struct task_struct *pick_next_task_idle(struct rq *rq);
+
 #ifdef CONFIG_SMP
 
 extern void update_group_capacity(struct sched_domain *sd, int cpu);
@@ -1890,7 +1950,6 @@
 extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
 extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
 extern void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se);
-extern void init_dl_rq_bw_ratio(struct dl_rq *dl_rq);
 
 #define BW_SHIFT		20
 #define BW_UNIT			(1 << BW_SHIFT)
@@ -1913,12 +1972,7 @@
  */
 static inline void sched_update_tick_dependency(struct rq *rq)
 {
-	int cpu;
-
-	if (!tick_nohz_full_enabled())
-		return;
-
-	cpu = cpu_of(rq);
+	int cpu = cpu_of(rq);
 
 	if (!tick_nohz_full_cpu(cpu))
 		return;
@@ -1938,6 +1992,9 @@
 	unsigned prev_nr = rq->nr_running;
 
 	rq->nr_running = prev_nr + count;
+	if (trace_sched_update_nr_running_tp_enabled()) {
+		call_trace_sched_update_nr_running(rq, count);
+	}
 
 #ifdef CONFIG_SMP
 	if (prev_nr < 2 && rq->nr_running >= 2) {
@@ -1952,6 +2009,10 @@
 static inline void sub_nr_running(struct rq *rq, unsigned count)
 {
 	rq->nr_running -= count;
+	if (trace_sched_update_nr_running_tp_enabled()) {
+		call_trace_sched_update_nr_running(rq, -count);
+	}
+
 	/* Check if we still need preemption */
 	sched_update_tick_dependency(rq);
 }
@@ -1991,7 +2052,24 @@
 
 #endif /* CONFIG_SCHED_HRTICK */
 
+#ifndef arch_scale_freq_tick
+static __always_inline
+void arch_scale_freq_tick(void)
+{
+}
+#endif
+
 #ifndef arch_scale_freq_capacity
+/**
+ * arch_scale_freq_capacity - get the frequency scale factor of a given CPU.
+ * @cpu: the CPU in question.
+ *
+ * Return: the frequency scale factor normalized against SCHED_CAPACITY_SCALE, i.e.
+ *
+ *     f_curr
+ *     ------ * SCHED_CAPACITY_SCALE
+ *     f_max
+ */
 static __always_inline
 unsigned long arch_scale_freq_capacity(int cpu)
 {
@@ -2323,10 +2401,10 @@
 #endif /* CONFIG_CPU_FREQ */
 
 #ifdef CONFIG_UCLAMP_TASK
-unsigned int uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
+unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
 
 /**
- * uclamp_util_with - clamp @util with @rq and @p effective uclamp values.
+ * uclamp_rq_util_with - clamp @util with @rq and @p effective uclamp values.
  * @rq:		The rq to clamp against. Must not be NULL.
  * @util:	The util value to clamp.
  * @p:		The task to clamp against. Can be NULL if you want to clamp
@@ -2343,23 +2421,30 @@
  * static key is disabled.
  */
 static __always_inline
-unsigned int uclamp_util_with(struct rq *rq, unsigned int util,
-			      struct task_struct *p)
+unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
+				  struct task_struct *p)
 {
-	unsigned int min_util;
-	unsigned int max_util;
+	unsigned long min_util = 0;
+	unsigned long max_util = 0;
 
 	if (!static_branch_likely(&sched_uclamp_used))
 		return util;
 
-	min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value);
-	max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value);
-
 	if (p) {
-		min_util = max(min_util, uclamp_eff_value(p, UCLAMP_MIN));
-		max_util = max(max_util, uclamp_eff_value(p, UCLAMP_MAX));
+		min_util = uclamp_eff_value(p, UCLAMP_MIN);
+		max_util = uclamp_eff_value(p, UCLAMP_MAX);
+
+		/*
+		 * Ignore last runnable task's max clamp, as this task will
+		 * reset it. Similarly, no need to read the rq's min clamp.
+		 */
+		if (rq->uclamp_flags & UCLAMP_FLAG_IDLE)
+			goto out;
 	}
 
+	min_util = max_t(unsigned long, min_util, READ_ONCE(rq->uclamp[UCLAMP_MIN].value));
+	max_util = max_t(unsigned long, max_util, READ_ONCE(rq->uclamp[UCLAMP_MAX].value));
+out:
 	/*
 	 * Since CPU's {min,max}_util clamps are MAX aggregated considering
 	 * RUNNABLE tasks with _different_ clamps, we can end up with an
@@ -2371,11 +2456,6 @@
 	return clamp(util, min_util, max_util);
 }
 
-static inline unsigned int uclamp_util(struct rq *rq, unsigned int util)
-{
-	return uclamp_util_with(rq, util, NULL);
-}
-
 /*
  * When uclamp is compiled in, the aggregation at rq level is 'turned off'
  * by default in the fast path and only gets turned on once userspace performs
@@ -2389,12 +2469,9 @@
 	return static_branch_likely(&sched_uclamp_used);
 }
 #else /* CONFIG_UCLAMP_TASK */
-static inline unsigned int uclamp_util_with(struct rq *rq, unsigned int util,
-					    struct task_struct *p)
-{
-	return util;
-}
-static inline unsigned int uclamp_util(struct rq *rq, unsigned int util)
+static inline
+unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
+				  struct task_struct *p)
 {
 	return util;
 }
@@ -2551,3 +2628,19 @@
 {
 }
 #endif
+
+#ifdef CONFIG_SMP
+static inline bool is_per_cpu_kthread(struct task_struct *p)
+{
+	if (!(p->flags & PF_KTHREAD))
+		return false;
+
+	if (p->nr_cpus_allowed != 1)
+		return false;
+
+	return true;
+}
+#endif
+
+void swake_up_all_locked(struct swait_queue_head *q);
+void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
diff --git a/kernel/sched/smp.h b/kernel/sched/smp.h
new file mode 100644
index 0000000..9620e32
--- /dev/null
+++ b/kernel/sched/smp.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Scheduler internal SMP callback types and methods between the scheduler
+ * and other internal parts of the core kernel:
+ */
+
+extern void sched_ttwu_pending(void *arg);
+
+extern void send_call_function_single_ipi(int cpu);
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index ba683fe..33d0daf 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -70,7 +70,7 @@
 		return;
 
 	if (!wakeup || p->sched_psi_wake_requeue) {
-		if (p->flags & PF_MEMSTALL)
+		if (p->in_memstall)
 			set |= TSK_MEMSTALL;
 		if (p->sched_psi_wake_requeue)
 			p->sched_psi_wake_requeue = 0;
@@ -90,9 +90,17 @@
 		return;
 
 	if (!sleep) {
-		if (p->flags & PF_MEMSTALL)
+		if (p->in_memstall)
 			clear |= TSK_MEMSTALL;
 	} else {
+		/*
+		 * When a task sleeps, schedule() dequeues it before
+		 * switching to the next one. Merge the clearing of
+		 * TSK_RUNNING and TSK_ONCPU to save an unnecessary
+		 * psi_task_change() call in psi_sched_switch().
+		 */
+		clear |= TSK_ONCPU;
+
 		if (p->in_iowait)
 			set |= TSK_IOWAIT;
 	}
@@ -109,14 +117,14 @@
 	 * deregister its sleep-persistent psi states from the old
 	 * queue, and let psi_enqueue() know it has to requeue.
 	 */
-	if (unlikely(p->in_iowait || (p->flags & PF_MEMSTALL))) {
+	if (unlikely(p->in_iowait || p->in_memstall)) {
 		struct rq_flags rf;
 		struct rq *rq;
 		int clear = 0;
 
 		if (p->in_iowait)
 			clear |= TSK_IOWAIT;
-		if (p->flags & PF_MEMSTALL)
+		if (p->in_memstall)
 			clear |= TSK_MEMSTALL;
 
 		rq = __task_rq_lock(p, &rf);
@@ -126,18 +134,31 @@
 	}
 }
 
+static inline void psi_sched_switch(struct task_struct *prev,
+				    struct task_struct *next,
+				    bool sleep)
+{
+	if (static_branch_likely(&psi_disabled))
+		return;
+
+	psi_task_switch(prev, next, sleep);
+}
+
 static inline void psi_task_tick(struct rq *rq)
 {
 	if (static_branch_likely(&psi_disabled))
 		return;
 
-	if (unlikely(rq->curr->flags & PF_MEMSTALL))
+	if (unlikely(rq->curr->in_memstall))
 		psi_memstall_tick(rq->curr, cpu_of(rq));
 }
 #else /* CONFIG_PSI */
 static inline void psi_enqueue(struct task_struct *p, bool wakeup) {}
 static inline void psi_dequeue(struct task_struct *p, bool sleep) {}
 static inline void psi_ttwu_dequeue(struct task_struct *p) {}
+static inline void psi_sched_switch(struct task_struct *prev,
+				    struct task_struct *next,
+				    bool sleep) {}
 static inline void psi_task_tick(struct rq *rq) {}
 #endif /* CONFIG_PSI */
 
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 02dc0a8..ceb5b6b 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -34,11 +34,8 @@
 	stop->se.exec_start = rq_clock_task(rq);
 }
 
-static struct task_struct *
-pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+static struct task_struct *pick_next_task_stop(struct rq *rq)
 {
-	WARN_ON_ONCE(prev || rf);
-
 	if (!sched_stop_runnable(rq))
 		return NULL;
 
@@ -105,12 +102,6 @@
 	BUG(); /* how!?, what priority? */
 }
 
-static unsigned int
-get_rr_interval_stop(struct rq *rq, struct task_struct *task)
-{
-	return 0;
-}
-
 static void update_curr_stop(struct rq *rq)
 {
 }
@@ -118,8 +109,8 @@
 /*
  * Simple, special scheduling class for the per-CPU stop tasks:
  */
-const struct sched_class stop_sched_class = {
-	.next			= &dl_sched_class,
+const struct sched_class stop_sched_class
+	__section("__stop_sched_class") = {
 
 	.enqueue_task		= enqueue_task_stop,
 	.dequeue_task		= dequeue_task_stop,
@@ -139,8 +130,6 @@
 
 	.task_tick		= task_tick_stop,
 
-	.get_rr_interval	= get_rr_interval_stop,
-
 	.prio_changed		= prio_changed_stop,
 	.switched_to		= switched_to_stop,
 	.update_curr		= update_curr_stop,
diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c
index e83a3f8..e1c655f 100644
--- a/kernel/sched/swait.c
+++ b/kernel/sched/swait.c
@@ -32,6 +32,19 @@
 }
 EXPORT_SYMBOL(swake_up_locked);
 
+/*
+ * Wake up all waiters. This is an interface which is solely exposed for
+ * completions and not for general usage.
+ *
+ * It is intentionally different from swake_up_all() to allow usage from
+ * hard interrupt context and interrupt disabled regions.
+ */
+void swake_up_all_locked(struct swait_queue_head *q)
+{
+	while (!list_empty(&q->task_list))
+		swake_up_locked(q);
+}
+
 void swake_up_one(struct swait_queue_head *q)
 {
 	unsigned long flags;
@@ -69,7 +82,7 @@
 }
 EXPORT_SYMBOL(swake_up_all);
 
-static void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
+void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
 {
 	wait->task = current;
 	if (list_empty(&wait->task_list))
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index ffaa97a..ff2c6d3 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -25,22 +25,22 @@
 	return sched_debug_enabled;
 }
 
+#define SD_FLAG(_name, mflags) [__##_name] = { .meta_flags = mflags, .name = #_name },
+const struct sd_flag_debug sd_flag_debug[] = {
+#include <linux/sched/sd_flags.h>
+};
+#undef SD_FLAG
+
 static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 				  struct cpumask *groupmask)
 {
 	struct sched_group *group = sd->groups;
+	unsigned long flags = sd->flags;
+	unsigned int idx;
 
 	cpumask_clear(groupmask);
 
 	printk(KERN_DEBUG "%*s domain-%d: ", level, "", level);
-
-	if (!(sd->flags & SD_LOAD_BALANCE)) {
-		printk("does not load-balance\n");
-		if (sd->parent)
-			printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain has parent");
-		return -1;
-	}
-
 	printk(KERN_CONT "span=%*pbl level=%s\n",
 	       cpumask_pr_args(sched_domain_span(sd)), sd->name);
 
@@ -51,6 +51,21 @@
 		printk(KERN_ERR "ERROR: domain->groups does not contain CPU%d\n", cpu);
 	}
 
+	for_each_set_bit(idx, &flags, __SD_FLAG_CNT) {
+		unsigned int flag = BIT(idx);
+		unsigned int meta_flags = sd_flag_debug[idx].meta_flags;
+
+		if ((meta_flags & SDF_SHARED_CHILD) && sd->child &&
+		    !(sd->child->flags & flag))
+			printk(KERN_ERR "ERROR: flag %s set here but not in child\n",
+			       sd_flag_debug[idx].name);
+
+		if ((meta_flags & SDF_SHARED_PARENT) && sd->parent &&
+		    !(sd->parent->flags & flag))
+			printk(KERN_ERR "ERROR: flag %s set here but not in parent\n",
+			       sd_flag_debug[idx].name);
+	}
+
 	printk(KERN_DEBUG "%*s groups:", level + 1, "");
 	do {
 		if (!group) {
@@ -145,23 +160,22 @@
 }
 #endif /* CONFIG_SCHED_DEBUG */
 
+/* Generate a mask of SD flags with the SDF_NEEDS_GROUPS metaflag */
+#define SD_FLAG(name, mflags) (name * !!((mflags) & SDF_NEEDS_GROUPS)) |
+static const unsigned int SD_DEGENERATE_GROUPS_MASK =
+#include <linux/sched/sd_flags.h>
+0;
+#undef SD_FLAG
+
 static int sd_degenerate(struct sched_domain *sd)
 {
 	if (cpumask_weight(sched_domain_span(sd)) == 1)
 		return 1;
 
 	/* Following flags need at least 2 groups */
-	if (sd->flags & (SD_LOAD_BALANCE |
-			 SD_BALANCE_NEWIDLE |
-			 SD_BALANCE_FORK |
-			 SD_BALANCE_EXEC |
-			 SD_SHARE_CPUCAPACITY |
-			 SD_ASYM_CPUCAPACITY |
-			 SD_SHARE_PKG_RESOURCES |
-			 SD_SHARE_POWERDOMAIN)) {
-		if (sd->groups != sd->groups->next)
-			return 0;
-	}
+	if ((sd->flags & SD_DEGENERATE_GROUPS_MASK) &&
+	    (sd->groups != sd->groups->next))
+		return 0;
 
 	/* Following flags don't use groups */
 	if (sd->flags & (SD_WAKE_AFFINE))
@@ -182,19 +196,9 @@
 		return 0;
 
 	/* Flags needing groups don't count if only 1 group in parent */
-	if (parent->groups == parent->groups->next) {
-		pflags &= ~(SD_LOAD_BALANCE |
-				SD_BALANCE_NEWIDLE |
-				SD_BALANCE_FORK |
-				SD_BALANCE_EXEC |
-				SD_ASYM_CPUCAPACITY |
-				SD_SHARE_CPUCAPACITY |
-				SD_SHARE_PKG_RESOURCES |
-				SD_PREFER_SIBLING |
-				SD_SHARE_POWERDOMAIN);
-		if (nr_node_ids == 1)
-			pflags &= ~SD_SERIALIZE;
-	}
+	if (parent->groups == parent->groups->next)
+		pflags &= ~SD_DEGENERATE_GROUPS_MASK;
+
 	if (~cflags & pflags)
 		return 0;
 
@@ -209,7 +213,7 @@
 
 #ifdef CONFIG_PROC_SYSCTL
 int sched_energy_aware_handler(struct ctl_table *table, int write,
-			 void __user *buffer, size_t *lenp, loff_t *ppos)
+		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret, state;
 
@@ -282,10 +286,10 @@
 	printk(KERN_DEBUG "root_domain %*pbl:", cpumask_pr_args(cpu_map));
 
 	while (pd) {
-		printk(KERN_CONT " pd%d:{ cpus=%*pbl nr_cstate=%d }",
+		printk(KERN_CONT " pd%d:{ cpus=%*pbl nr_pstate=%d }",
 				cpumask_first(perf_domain_span(pd)),
 				cpumask_pr_args(perf_domain_span(pd)),
-				em_pd_nr_cap_states(pd->em_pd));
+				em_pd_nr_perf_states(pd->em_pd));
 		pd = pd->next;
 	}
 
@@ -317,31 +321,32 @@
  * EAS can be used on a root domain if it meets all the following conditions:
  *    1. an Energy Model (EM) is available;
  *    2. the SD_ASYM_CPUCAPACITY flag is set in the sched_domain hierarchy.
- *    3. the EM complexity is low enough to keep scheduling overheads low;
- *    4. schedutil is driving the frequency of all CPUs of the rd;
+ *    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;
  *
  * The complexity of the Energy Model is defined as:
  *
- *              C = nr_pd * (nr_cpus + nr_cs)
+ *              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_cs:    the sum of the number of capacity states of all performance
+ *  - 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 capacity states each, nr_cs = 2 * 10 = 20).
+ *              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 capacity states each, for example.
+ * with per-CPU DVFS and less than 8 performance states each, for example.
  */
 #define EM_MAX_COMPLEXITY 2048
 
 extern struct cpufreq_governor schedutil_gov;
 static bool build_perf_domains(const struct cpumask *cpu_map)
 {
-	int i, nr_pd = 0, nr_cs = 0, nr_cpus = cpumask_weight(cpu_map);
+	int i, nr_pd = 0, nr_ps = 0, nr_cpus = cpumask_weight(cpu_map);
 	struct perf_domain *pd = NULL, *tmp;
 	int cpu = cpumask_first(cpu_map);
 	struct root_domain *rd = cpu_rq(cpu)->rd;
@@ -360,6 +365,13 @@
 		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;
+	}
+
 	for_each_cpu(i, cpu_map) {
 		/* Skip already covered CPUs. */
 		if (find_pd(pd, i))
@@ -386,15 +398,15 @@
 		pd = tmp;
 
 		/*
-		 * Count performance domains and capacity states for the
+		 * Count performance domains and performance states for the
 		 * complexity check.
 		 */
 		nr_pd++;
-		nr_cs += em_pd_nr_cap_states(pd->em_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_cs + nr_cpus) > EM_MAX_COMPLEXITY) {
+	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;
@@ -1201,16 +1213,13 @@
 	if (!attr || attr->relax_domain_level < 0) {
 		if (default_relax_domain_level < 0)
 			return;
-		else
-			request = default_relax_domain_level;
+		request = default_relax_domain_level;
 	} else
 		request = attr->relax_domain_level;
-	if (request < sd->level) {
+
+	if (sd->level > request) {
 		/* Turn off idle balance on this domain: */
 		sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
-	} else {
-		/* Turn on idle balance on this domain: */
-		sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
 	}
 }
 
@@ -1224,13 +1233,13 @@
 	case sa_rootdomain:
 		if (!atomic_read(&d->rd->refcount))
 			free_rootdomain(&d->rd->rcu);
-		/* Fall through */
+		fallthrough;
 	case sa_sd:
 		free_percpu(d->sd);
-		/* Fall through */
+		fallthrough;
 	case sa_sd_storage:
 		__sdt_free(cpu_map);
-		/* Fall through */
+		fallthrough;
 	case sa_none:
 		break;
 	}
@@ -1297,7 +1306,6 @@
  *   SD_SHARE_CPUCAPACITY   - describes SMT topologies
  *   SD_SHARE_PKG_RESOURCES - describes shared caches
  *   SD_NUMA                - describes NUMA topologies
- *   SD_SHARE_POWERDOMAIN   - describes shared power domain
  *
  * Odd one out, which beside describing the topology has a quirk also
  * prescribes the desired behaviour that goes along with it:
@@ -1308,8 +1316,7 @@
 	(SD_SHARE_CPUCAPACITY	|	\
 	 SD_SHARE_PKG_RESOURCES |	\
 	 SD_NUMA		|	\
-	 SD_ASYM_PACKING	|	\
-	 SD_SHARE_POWERDOMAIN)
+	 SD_ASYM_PACKING)
 
 static struct sched_domain *
 sd_init(struct sched_domain_topology_level *tl,
@@ -1341,13 +1348,12 @@
 	*sd = (struct sched_domain){
 		.min_interval		= sd_weight,
 		.max_interval		= 2*sd_weight,
-		.busy_factor		= 32,
-		.imbalance_pct		= 125,
+		.busy_factor		= 16,
+		.imbalance_pct		= 117,
 
 		.cache_nice_tries	= 0,
 
-		.flags			= 1*SD_LOAD_BALANCE
-					| 1*SD_BALANCE_NEWIDLE
+		.flags			= 1*SD_BALANCE_NEWIDLE
 					| 1*SD_BALANCE_EXEC
 					| 1*SD_BALANCE_FORK
 					| 0*SD_BALANCE_WAKE
@@ -1377,18 +1383,9 @@
 	 * Convert topological properties into behaviour.
 	 */
 
-	if (sd->flags & SD_ASYM_CPUCAPACITY) {
-		struct sched_domain *t = sd;
-
-		/*
-		 * Don't attempt to spread across CPUs of different capacities.
-		 */
-		if (sd->child)
-			sd->child->flags &= ~SD_PREFER_SIBLING;
-
-		for_each_lower_domain(t)
-			t->flags |= SD_BALANCE_WAKE;
-	}
+	/* Don't attempt to spread across CPUs of different capacities. */
+	if ((sd->flags & SD_ASYM_CPUCAPACITY) && sd->child)
+		sd->child->flags &= ~SD_PREFER_SIBLING;
 
 	if (sd->flags & SD_SHARE_CPUCAPACITY) {
 		sd->imbalance_pct = 110;
@@ -1552,66 +1549,58 @@
 	}
 }
 
+
+#define NR_DISTANCE_VALUES (1 << DISTANCE_BITS)
+
 void sched_init_numa(void)
 {
-	int next_distance, curr_distance = node_distance(0, 0);
 	struct sched_domain_topology_level *tl;
-	int level = 0;
-	int i, j, k;
-
-	sched_domains_numa_distance = kzalloc(sizeof(int) * (nr_node_ids + 1), GFP_KERNEL);
-	if (!sched_domains_numa_distance)
-		return;
-
-	/* Includes NUMA identity node at level 0. */
-	sched_domains_numa_distance[level++] = curr_distance;
-	sched_domains_numa_levels = level;
+	unsigned long *distance_map;
+	int nr_levels = 0;
+	int i, j;
 
 	/*
 	 * O(nr_nodes^2) deduplicating selection sort -- in order to find the
 	 * unique distances in the node_distance() table.
-	 *
-	 * Assumes node_distance(0,j) includes all distances in
-	 * node_distance(i,j) in order to avoid cubic time.
 	 */
-	next_distance = curr_distance;
+	distance_map = bitmap_alloc(NR_DISTANCE_VALUES, GFP_KERNEL);
+	if (!distance_map)
+		return;
+
+	bitmap_zero(distance_map, NR_DISTANCE_VALUES);
 	for (i = 0; i < nr_node_ids; i++) {
 		for (j = 0; j < nr_node_ids; j++) {
-			for (k = 0; k < nr_node_ids; k++) {
-				int distance = node_distance(i, k);
+			int distance = node_distance(i, j);
 
-				if (distance > curr_distance &&
-				    (distance < next_distance ||
-				     next_distance == curr_distance))
-					next_distance = distance;
-
-				/*
-				 * While not a strong assumption it would be nice to know
-				 * about cases where if node A is connected to B, B is not
-				 * equally connected to A.
-				 */
-				if (sched_debug() && node_distance(k, i) != distance)
-					sched_numa_warn("Node-distance not symmetric");
-
-				if (sched_debug() && i && !find_numa_distance(distance))
-					sched_numa_warn("Node-0 not representative");
+			if (distance < LOCAL_DISTANCE || distance >= NR_DISTANCE_VALUES) {
+				sched_numa_warn("Invalid distance value range");
+				return;
 			}
-			if (next_distance != curr_distance) {
-				sched_domains_numa_distance[level++] = next_distance;
-				sched_domains_numa_levels = level;
-				curr_distance = next_distance;
-			} else break;
-		}
 
-		/*
-		 * In case of sched_debug() we verify the above assumption.
-		 */
-		if (!sched_debug())
-			break;
+			bitmap_set(distance_map, distance, 1);
+		}
+	}
+	/*
+	 * We can now figure out how many unique distance values there are and
+	 * allocate memory accordingly.
+	 */
+	nr_levels = bitmap_weight(distance_map, NR_DISTANCE_VALUES);
+
+	sched_domains_numa_distance = kcalloc(nr_levels, sizeof(int), GFP_KERNEL);
+	if (!sched_domains_numa_distance) {
+		bitmap_free(distance_map);
+		return;
 	}
 
+	for (i = 0, j = 0; i < nr_levels; i++, j++) {
+		j = find_next_bit(distance_map, NR_DISTANCE_VALUES, j);
+		sched_domains_numa_distance[i] = j;
+	}
+
+	bitmap_free(distance_map);
+
 	/*
-	 * 'level' contains the number of unique distances
+	 * 'nr_levels' contains the number of unique distances
 	 *
 	 * The sched_domains_numa_distance[] array includes the actual distance
 	 * numbers.
@@ -1620,15 +1609,15 @@
 	/*
 	 * Here, we should temporarily reset sched_domains_numa_levels to 0.
 	 * If it fails to allocate memory for array sched_domains_numa_masks[][],
-	 * the array will contain less then 'level' members. This could be
+	 * the array will contain less then 'nr_levels' members. This could be
 	 * dangerous when we use it to iterate array sched_domains_numa_masks[][]
 	 * in other functions.
 	 *
-	 * We reset it to 'level' at the end of this function.
+	 * We reset it to 'nr_levels' at the end of this function.
 	 */
 	sched_domains_numa_levels = 0;
 
-	sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL);
+	sched_domains_numa_masks = kzalloc(sizeof(void *) * nr_levels, GFP_KERNEL);
 	if (!sched_domains_numa_masks)
 		return;
 
@@ -1636,7 +1625,7 @@
 	 * Now for each level, construct a mask per node which contains all
 	 * CPUs of nodes that are that many hops away from us.
 	 */
-	for (i = 0; i < level; i++) {
+	for (i = 0; i < nr_levels; i++) {
 		sched_domains_numa_masks[i] =
 			kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL);
 		if (!sched_domains_numa_masks[i])
@@ -1644,12 +1633,17 @@
 
 		for (j = 0; j < nr_node_ids; j++) {
 			struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL);
+			int k;
+
 			if (!mask)
 				return;
 
 			sched_domains_numa_masks[i][j] = mask;
 
 			for_each_node(k) {
+				if (sched_debug() && (node_distance(j, k) != node_distance(k, j)))
+					sched_numa_warn("Node-distance not symmetric");
+
 				if (node_distance(j, k) > sched_domains_numa_distance[i])
 					continue;
 
@@ -1661,7 +1655,7 @@
 	/* Compute default topology size */
 	for (i = 0; sched_domain_topology[i].mask; i++);
 
-	tl = kzalloc((i + level + 1) *
+	tl = kzalloc((i + nr_levels + 1) *
 			sizeof(struct sched_domain_topology_level), GFP_KERNEL);
 	if (!tl)
 		return;
@@ -1684,7 +1678,7 @@
 	/*
 	 * .. and append 'j' levels of NUMA goodness.
 	 */
-	for (j = 1; j < level; i++, j++) {
+	for (j = 1; j < nr_levels; i++, j++) {
 		tl[i] = (struct sched_domain_topology_level){
 			.mask = sd_numa_mask,
 			.sd_flags = cpu_numa_flags,
@@ -1696,8 +1690,8 @@
 
 	sched_domain_topology = tl;
 
-	sched_domains_numa_levels = level;
-	sched_max_numa_distance = sched_domains_numa_distance[level - 1];
+	sched_domains_numa_levels = nr_levels;
+	sched_max_numa_distance = sched_domains_numa_distance[nr_levels - 1];
 
 	init_numa_topology_type();
 }
@@ -2004,11 +1998,10 @@
 	/* Set up domains for CPUs specified by the cpu_map: */
 	for_each_cpu(i, cpu_map) {
 		struct sched_domain_topology_level *tl;
+		int dflags = 0;
 
 		sd = NULL;
 		for_each_sd_topology(tl) {
-			int dflags = 0;
-
 			if (tl == tl_asym) {
 				dflags |= SD_ASYM_CPUCAPACITY;
 				has_asym = true;
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 84bd051..a55642a 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -169,7 +169,6 @@
  * __wake_up_sync_key - wake up threads blocked on a waitqueue.
  * @wq_head: the waitqueue
  * @mode: which threads
- * @nr_exclusive: how many wake-one or wake-many threads to wake up
  * @key: opaque value to be passed to wakeup targets
  *
  * The sync wakeup differs that the waker knows that it will schedule
@@ -183,29 +182,54 @@
  * accessing the task state.
  */
 void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode,
-			int nr_exclusive, void *key)
+			void *key)
 {
-	int wake_flags = 1; /* XXX WF_SYNC */
-
 	if (unlikely(!wq_head))
 		return;
 
-	if (unlikely(nr_exclusive != 1))
-		wake_flags = 0;
-
-	__wake_up_common_lock(wq_head, mode, nr_exclusive, wake_flags, key);
+	__wake_up_common_lock(wq_head, mode, 1, WF_SYNC, key);
 }
 EXPORT_SYMBOL_GPL(__wake_up_sync_key);
 
+/**
+ * __wake_up_locked_sync_key - wake up a thread blocked on a locked waitqueue.
+ * @wq_head: the waitqueue
+ * @mode: which threads
+ * @key: opaque value to be passed to wakeup targets
+ *
+ * The sync wakeup differs in that the waker knows that it will schedule
+ * away soon, so while the target thread will be woken up, it will not
+ * be migrated to another CPU - ie. the two threads are 'synchronized'
+ * with each other. This can prevent needless bouncing between CPUs.
+ *
+ * On UP it can prevent extra preemption.
+ *
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
+ */
+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);
+}
+EXPORT_SYMBOL_GPL(__wake_up_locked_sync_key);
+
 /*
  * __wake_up_sync - see __wake_up_sync_key()
  */
-void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive)
+void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode)
 {
-	__wake_up_sync_key(wq_head, mode, nr_exclusive, NULL);
+	__wake_up_sync_key(wq_head, mode, NULL);
 }
 EXPORT_SYMBOL_GPL(__wake_up_sync);	/* For internal use only */
 
+void __wake_up_pollfree(struct wait_queue_head *wq_head)
+{
+	__wake_up(wq_head, TASK_NORMAL, 0, poll_to_key(EPOLLHUP | POLLFREE));
+	/* POLLFREE must have cleared the queue. */
+	WARN_ON_ONCE(waitqueue_active(wq_head));
+}
+
 /*
  * Note: we use "set_current_state()" _after_ the wait-queue add,
  * because we need a memory barrier there on SMP, so that any
@@ -377,7 +401,7 @@
 	int ret = default_wake_function(wq_entry, mode, sync, key);
 
 	if (ret)
-		list_del_init(&wq_entry->entry);
+		list_del_init_careful(&wq_entry->entry);
 
 	return ret;
 }
diff --git a/kernel/sched/wait_bit.c b/kernel/sched/wait_bit.c
index 45eba18..02ce292 100644
--- a/kernel/sched/wait_bit.c
+++ b/kernel/sched/wait_bit.c
@@ -179,6 +179,7 @@
 			.bit_nr = -1,
 		},
 		.wq_entry = {
+			.flags	 = flags,
 			.private = current,
 			.func	 = var_wake_function,
 			.entry	 = LIST_HEAD_INIT(wbq_entry->wq_entry.entry),