Update Linux to v5.4.148

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz

Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 44123b4..5dc43d3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -36,7 +36,7 @@
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
-#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_JUMP_LABEL)
+#ifdef CONFIG_SCHED_DEBUG
 /*
  * Debugging: various feature bits
  *
@@ -254,8 +254,9 @@
 static void __hrtick_restart(struct rq *rq)
 {
 	struct hrtimer *timer = &rq->hrtick_timer;
+	ktime_t time = rq->hrtick_time;
 
-	hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED_HARD);
+	hrtimer_start(timer, time, HRTIMER_MODE_ABS_PINNED_HARD);
 }
 
 /*
@@ -280,7 +281,6 @@
 void hrtick_start(struct rq *rq, u64 delay)
 {
 	struct hrtimer *timer = &rq->hrtick_timer;
-	ktime_t time;
 	s64 delta;
 
 	/*
@@ -288,9 +288,7 @@
 	 * doesn't make sense and can cause timer DoS.
 	 */
 	delta = max_t(s64, delay, 10000LL);
-	time = ktime_add_ns(timer->base->get_time(), delta);
-
-	hrtimer_set_expires(timer, time);
+	rq->hrtick_time = ktime_add_ns(timer->base->get_time(), delta);
 
 	if (rq == this_rq()) {
 		__hrtick_restart(rq);
@@ -794,6 +792,26 @@
 /* All clamps are required to be less or equal than these values */
 static struct uclamp_se uclamp_default[UCLAMP_CNT];
 
+/*
+ * This static key is used to reduce the uclamp overhead in the fast path. It
+ * primarily disables the call to uclamp_rq_{inc, dec}() in
+ * enqueue/dequeue_task().
+ *
+ * This allows users to continue to enable uclamp in their kernel config with
+ * minimum uclamp overhead in the fast path.
+ *
+ * As soon as userspace modifies any of the uclamp knobs, the static key is
+ * enabled, since we have an actual users that make use of uclamp
+ * functionality.
+ *
+ * The knobs that would enable this static key are:
+ *
+ *   * A task modifying its uclamp value with sched_setattr().
+ *   * An admin modifying the sysctl_sched_uclamp_{min, max} via procfs.
+ *   * An admin modifying the cgroup cpu.uclamp.{min, max}
+ */
+DEFINE_STATIC_KEY_FALSE(sched_uclamp_used);
+
 /* Integer rounded range for each bucket */
 #define UCLAMP_BUCKET_DELTA DIV_ROUND_CLOSEST(SCHED_CAPACITY_SCALE, UCLAMP_BUCKETS)
 
@@ -802,7 +820,7 @@
 
 static inline unsigned int uclamp_bucket_id(unsigned int clamp_value)
 {
-	return clamp_value / UCLAMP_BUCKET_DELTA;
+	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)
@@ -810,7 +828,7 @@
 	return UCLAMP_BUCKET_DELTA * uclamp_bucket_id(clamp_value);
 }
 
-static inline enum uclamp_id uclamp_none(enum uclamp_id clamp_id)
+static inline unsigned int uclamp_none(enum uclamp_id clamp_id)
 {
 	if (clamp_id == UCLAMP_MIN)
 		return 0;
@@ -853,7 +871,7 @@
 }
 
 static inline
-enum uclamp_id uclamp_rq_max_value(struct rq *rq, enum uclamp_id clamp_id,
+unsigned int uclamp_rq_max_value(struct rq *rq, enum uclamp_id clamp_id,
 				   unsigned int clamp_value)
 {
 	struct uclamp_bucket *bucket = rq->uclamp[clamp_id].bucket;
@@ -876,9 +894,10 @@
 static inline struct uclamp_se
 uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id)
 {
+	/* Copy by value as we could modify it */
 	struct uclamp_se uc_req = p->uclamp_req[clamp_id];
 #ifdef CONFIG_UCLAMP_TASK_GROUP
-	struct uclamp_se uc_max;
+	unsigned int tg_min, tg_max, value;
 
 	/*
 	 * Tasks in autogroups or root task group will be
@@ -889,9 +908,11 @@
 	if (task_group(p) == &root_task_group)
 		return uc_req;
 
-	uc_max = task_group(p)->uclamp[clamp_id];
-	if (uc_req.value > uc_max.value || !uc_req.user_defined)
-		return uc_max;
+	tg_min = task_group(p)->uclamp[UCLAMP_MIN].value;
+	tg_max = task_group(p)->uclamp[UCLAMP_MAX].value;
+	value = uc_req.value;
+	value = clamp(value, tg_min, tg_max);
+	uclamp_se_set(&uc_req, value, false);
 #endif
 
 	return uc_req;
@@ -918,7 +939,7 @@
 	return uc_req;
 }
 
-enum uclamp_id uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id)
+unsigned int uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id)
 {
 	struct uclamp_se uc_eff;
 
@@ -990,10 +1011,38 @@
 
 	lockdep_assert_held(&rq->lock);
 
+	/*
+	 * If sched_uclamp_used was enabled after task @p was enqueued,
+	 * we could end up with unbalanced call to uclamp_rq_dec_id().
+	 *
+	 * In this case the uc_se->active flag should be false since no uclamp
+	 * accounting was performed at enqueue time and we can just return
+	 * here.
+	 *
+	 * Need to be careful of the following enqeueue/dequeue ordering
+	 * problem too
+	 *
+	 *	enqueue(taskA)
+	 *	// sched_uclamp_used gets enabled
+	 *	enqueue(taskB)
+	 *	dequeue(taskA)
+	 *	// Must not decrement bukcet->tasks here
+	 *	dequeue(taskB)
+	 *
+	 * where we could end up with stale data in uc_se and
+	 * bucket[uc_se->bucket_id].
+	 *
+	 * The following check here eliminates the possibility of such race.
+	 */
+	if (unlikely(!uc_se->active))
+		return;
+
 	bucket = &uc_rq->bucket[uc_se->bucket_id];
+
 	SCHED_WARN_ON(!bucket->tasks);
 	if (likely(bucket->tasks))
 		bucket->tasks--;
+
 	uc_se->active = false;
 
 	/*
@@ -1021,6 +1070,15 @@
 {
 	enum uclamp_id clamp_id;
 
+	/*
+	 * Avoid any overhead until uclamp is actually used by the userspace.
+	 *
+	 * The condition is constructed such that a NOP is generated when
+	 * sched_uclamp_used is disabled.
+	 */
+	if (!static_branch_unlikely(&sched_uclamp_used))
+		return;
+
 	if (unlikely(!p->sched_class->uclamp_enabled))
 		return;
 
@@ -1036,6 +1094,15 @@
 {
 	enum uclamp_id clamp_id;
 
+	/*
+	 * Avoid any overhead until uclamp is actually used by the userspace.
+	 *
+	 * The condition is constructed such that a NOP is generated when
+	 * sched_uclamp_used is disabled.
+	 */
+	if (!static_branch_unlikely(&sched_uclamp_used))
+		return;
+
 	if (unlikely(!p->sched_class->uclamp_enabled))
 		return;
 
@@ -1043,9 +1110,27 @@
 		uclamp_rq_dec_id(rq, p, clamp_id);
 }
 
-static inline void
-uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id)
+static inline void uclamp_rq_reinc_id(struct rq *rq, struct task_struct *p,
+				      enum uclamp_id clamp_id)
 {
+	if (!p->uclamp[clamp_id].active)
+		return;
+
+	uclamp_rq_dec_id(rq, p, clamp_id);
+	uclamp_rq_inc_id(rq, p, clamp_id);
+
+	/*
+	 * Make sure to clear the idle flag if we've transiently reached 0
+	 * active tasks on rq.
+	 */
+	if (clamp_id == UCLAMP_MAX && (rq->uclamp_flags & UCLAMP_FLAG_IDLE))
+		rq->uclamp_flags &= ~UCLAMP_FLAG_IDLE;
+}
+
+static inline void
+uclamp_update_active(struct task_struct *p)
+{
+	enum uclamp_id clamp_id;
 	struct rq_flags rf;
 	struct rq *rq;
 
@@ -1065,30 +1150,22 @@
 	 * affecting a valid clamp bucket, the next time it's enqueued,
 	 * it will already see the updated clamp bucket value.
 	 */
-	if (p->uclamp[clamp_id].active) {
-		uclamp_rq_dec_id(rq, p, clamp_id);
-		uclamp_rq_inc_id(rq, p, clamp_id);
-	}
+	for_each_clamp_id(clamp_id)
+		uclamp_rq_reinc_id(rq, p, clamp_id);
 
 	task_rq_unlock(rq, p, &rf);
 }
 
 #ifdef CONFIG_UCLAMP_TASK_GROUP
 static inline void
-uclamp_update_active_tasks(struct cgroup_subsys_state *css,
-			   unsigned int clamps)
+uclamp_update_active_tasks(struct cgroup_subsys_state *css)
 {
-	enum uclamp_id clamp_id;
 	struct css_task_iter it;
 	struct task_struct *p;
 
 	css_task_iter_start(css, 0, &it);
-	while ((p = css_task_iter_next(&it))) {
-		for_each_clamp_id(clamp_id) {
-			if ((0x1 << clamp_id) & clamps)
-				uclamp_update_active(p, clamp_id);
-		}
-	}
+	while ((p = css_task_iter_next(&it)))
+		uclamp_update_active(p);
 	css_task_iter_end(&it);
 }
 
@@ -1145,8 +1222,10 @@
 		update_root_tg = true;
 	}
 
-	if (update_root_tg)
+	if (update_root_tg) {
+		static_branch_enable(&sched_uclamp_used);
 		uclamp_update_root_tg();
+	}
 
 	/*
 	 * We update all RUNNABLE tasks only when task groups are in use.
@@ -1181,6 +1260,15 @@
 	if (upper_bound > SCHED_CAPACITY_SCALE)
 		return -EINVAL;
 
+	/*
+	 * We have valid uclamp attributes; make sure uclamp is enabled.
+	 *
+	 * We need to do that here, because enabling static branches is a
+	 * blocking operation which obviously cannot be done while holding
+	 * scheduler locks.
+	 */
+	static_branch_enable(&sched_uclamp_used);
+
 	return 0;
 }
 
@@ -1233,16 +1321,25 @@
 		return;
 
 	for_each_clamp_id(clamp_id) {
-		unsigned int clamp_value = uclamp_none(clamp_id);
-
-		/* By default, RT tasks always get 100% boost */
-		if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN))
-			clamp_value = uclamp_none(UCLAMP_MAX);
-
-		uclamp_se_set(&p->uclamp_req[clamp_id], clamp_value, false);
+		uclamp_se_set(&p->uclamp_req[clamp_id],
+			      uclamp_none(clamp_id), false);
 	}
 }
 
+static void __init init_uclamp_rq(struct rq *rq)
+{
+	enum uclamp_id clamp_id;
+	struct uclamp_rq *uc_rq = rq->uclamp;
+
+	for_each_clamp_id(clamp_id) {
+		uc_rq[clamp_id] = (struct uclamp_rq) {
+			.value = uclamp_none(clamp_id)
+		};
+	}
+
+	rq->uclamp_flags = 0;
+}
+
 static void __init init_uclamp(void)
 {
 	struct uclamp_se uc_max = {};
@@ -1251,10 +1348,8 @@
 
 	mutex_init(&uclamp_mutex);
 
-	for_each_possible_cpu(cpu) {
-		memset(&cpu_rq(cpu)->uclamp, 0, sizeof(struct uclamp_rq));
-		cpu_rq(cpu)->uclamp_flags = 0;
-	}
+	for_each_possible_cpu(cpu)
+		init_uclamp_rq(cpu_rq(cpu));
 
 	for_each_clamp_id(clamp_id) {
 		uclamp_se_set(&init_task.uclamp_req[clamp_id],
@@ -1653,7 +1748,7 @@
 		goto out;
 	}
 
-	if (cpumask_equal(p->cpus_ptr, new_mask))
+	if (cpumask_equal(&p->cpus_mask, new_mask))
 		goto out;
 
 	dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask);
@@ -2893,6 +2988,7 @@
 	 * 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().
@@ -2957,6 +3053,7 @@
 	 * as we're not fully set-up yet.
 	 */
 	p->recent_used_cpu = task_cpu(p);
+	rseq_migrate(p);
 	__set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
 	rq = __task_rq_lock(p, &rf);
@@ -3667,28 +3764,31 @@
 	 * statistics and checks timeslices in a time-independent way, regardless
 	 * of when exactly it is running.
 	 */
-	if (idle_cpu(cpu) || !tick_nohz_tick_stopped_cpu(cpu))
+	if (!tick_nohz_tick_stopped_cpu(cpu))
 		goto out_requeue;
 
 	rq_lock_irq(rq, &rf);
 	curr = rq->curr;
-	if (is_idle_task(curr) || cpu_is_offline(cpu))
+	if (cpu_is_offline(cpu))
 		goto out_unlock;
 
 	update_rq_clock(rq);
-	delta = rq_clock_task(rq) - curr->se.exec_start;
 
-	/*
-	 * Make sure the next tick runs within a reasonable
-	 * amount of time.
-	 */
-	WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
+	if (!is_idle_task(curr)) {
+		/*
+		 * Make sure the next tick runs within a reasonable
+		 * amount of time.
+		 */
+		delta = rq_clock_task(rq) - curr->se.exec_start;
+		WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
+	}
 	curr->sched_class->task_tick(rq, curr, 0);
 
+	calc_load_nohz_remote(rq);
 out_unlock:
 	rq_unlock_irq(rq, &rf);
-
 out_requeue:
+
 	/*
 	 * Run the remote tick once per second (1Hz). This arbitrary
 	 * frequency is large enough to avoid overload but short enough
@@ -4110,7 +4210,8 @@
 	 * it wants to wake up a task to maintain concurrency.
 	 * As this function is called inside the schedule() context,
 	 * we disable preemption to avoid it calling schedule() again
-	 * in the possible wakeup of a kworker.
+	 * in the possible wakeup of a kworker and because wq_worker_sleeping()
+	 * requires it.
 	 */
 	if (tsk->flags & PF_WQ_WORKER) {
 		preempt_disable();
@@ -4448,7 +4549,8 @@
 	 */
 	if (dl_prio(prio)) {
 		if (!dl_prio(p->normal_prio) ||
-		    (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
+		    (pi_task && dl_prio(pi_task->prio) &&
+		     dl_entity_preempt(&pi_task->dl, &p->dl))) {
 			p->dl.dl_boosted = 1;
 			queue_flag |= ENQUEUE_REPLENISH;
 		} else
@@ -5588,12 +5690,8 @@
 	schedstat_inc(rq->yld_count);
 	current->sched_class->yield_task(rq);
 
-	/*
-	 * Since we are going to call schedule() anyway, there's
-	 * no need to preempt or enable interrupts:
-	 */
 	preempt_disable();
-	rq_unlock(rq, &rf);
+	rq_unlock_irq(rq, &rf);
 	sched_preempt_enable_no_resched();
 
 	schedule();
@@ -6178,13 +6276,14 @@
 	struct mm_struct *mm = current->active_mm;
 
 	BUG_ON(cpu_online(smp_processor_id()));
+	BUG_ON(current != this_rq()->idle);
 
 	if (mm != &init_mm) {
 		switch_mm(mm, &init_mm, current);
-		current->active_mm = &init_mm;
 		finish_arch_post_lock_switch();
 	}
-	mmdrop(mm);
+
+	/* finish_cpu(), as ran on the BP, will clean up the active_mm state */
 }
 
 /*
@@ -7053,8 +7152,15 @@
 
 	if (queued)
 		enqueue_task(rq, tsk, queue_flags);
-	if (running)
+	if (running) {
 		set_next_task(rq, tsk);
+		/*
+		 * After changing group, the running task may have joined a
+		 * throttled one but it's still the running task. Trigger a
+		 * resched to make sure that task can still run.
+		 */
+		resched_curr(rq);
+	}
 
 	task_rq_unlock(rq, tsk, &rf);
 }
@@ -7090,6 +7196,16 @@
 
 	if (parent)
 		sched_online_group(tg, parent);
+
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+	/* Propagate the effective uclamp value for the new group */
+	mutex_lock(&uclamp_mutex);
+	rcu_read_lock();
+	cpu_util_update_eff(css);
+	rcu_read_unlock();
+	mutex_unlock(&uclamp_mutex);
+#endif
+
 	return 0;
 }
 
@@ -7177,6 +7293,9 @@
 	enum uclamp_id clamp_id;
 	unsigned int clamps;
 
+	lockdep_assert_held(&uclamp_mutex);
+	SCHED_WARN_ON(!rcu_read_lock_held());
+
 	css_for_each_descendant_pre(css, top_css) {
 		uc_parent = css_tg(css)->parent
 			? css_tg(css)->parent->uclamp : NULL;
@@ -7209,7 +7328,7 @@
 		}
 
 		/* Immediately update descendants RUNNABLE tasks */
-		uclamp_update_active_tasks(css, clamps);
+		uclamp_update_active_tasks(css);
 	}
 }
 
@@ -7244,7 +7363,7 @@
 					     &req.percent);
 		if (req.ret)
 			return req;
-		if (req.percent > UCLAMP_PERCENT_SCALE) {
+		if ((u64)req.percent > UCLAMP_PERCENT_SCALE) {
 			req.ret = -ERANGE;
 			return req;
 		}
@@ -7267,6 +7386,8 @@
 	if (req.ret)
 		return req.ret;
 
+	static_branch_enable(&sched_uclamp_used);
+
 	mutex_lock(&uclamp_mutex);
 	rcu_read_lock();
 
@@ -7361,6 +7482,8 @@
 
 const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */
 static const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
+/* More than 203 days if BW_SHIFT equals 20. */
+static const u64 max_cfs_runtime = MAX_BW * NSEC_PER_USEC;
 
 static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime);
 
@@ -7389,6 +7512,12 @@
 		return -EINVAL;
 
 	/*
+	 * Bound quota to defend quota against overflow during bandwidth shift.
+	 */
+	if (quota != RUNTIME_INF && quota > max_cfs_runtime)
+		return -EINVAL;
+
+	/*
 	 * Prevent race between setting of cfs_rq->runtime_enabled and
 	 * unthrottle_offline_cfs_rqs().
 	 */
diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c
index b5dcd1d..7c2fe50 100644
--- a/kernel/sched/cpufreq.c
+++ b/kernel/sched/cpufreq.c
@@ -5,6 +5,8 @@
  * Copyright (C) 2016, Intel Corporation
  * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
  */
+#include <linux/cpufreq.h>
+
 #include "sched.h"
 
 DEFINE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
@@ -57,3 +59,19 @@
 	rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), NULL);
 }
 EXPORT_SYMBOL_GPL(cpufreq_remove_update_util_hook);
+
+/**
+ * cpufreq_this_cpu_can_update - Check if cpufreq policy can be updated.
+ * @policy: cpufreq policy to check.
+ *
+ * Return 'true' if:
+ * - the local and remote CPUs share @policy,
+ * - dvfs_possible_from_any_cpu is set in @policy and the local CPU is not going
+ *   offline (in which case it is not expected to run cpufreq updates any more).
+ */
+bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy)
+{
+	return cpumask_test_cpu(smp_processor_id(), policy->cpus) ||
+		(policy->dvfs_possible_from_any_cpu &&
+		 rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data)));
+}
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 86800b4..4cb80e6 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -82,12 +82,10 @@
 	 * by the hardware, as calculating the frequency is pointless if
 	 * we cannot in fact act on it.
 	 *
-	 * For the slow switching platforms, the kthread is always scheduled on
-	 * the right set of CPUs and any CPU can find the next frequency and
-	 * schedule the kthread.
+	 * This is needed on the slow switching platforms too to prevent CPUs
+	 * going offline from leaving stale IRQ work items behind.
 	 */
-	if (sg_policy->policy->fast_switch_enabled &&
-	    !cpufreq_this_cpu_can_update(sg_policy->policy))
+	if (!cpufreq_this_cpu_can_update(sg_policy->policy))
 		return false;
 
 	if (unlikely(sg_policy->limits_changed)) {
@@ -212,7 +210,7 @@
 	unsigned long dl_util, util, irq;
 	struct rq *rq = cpu_rq(cpu);
 
-	if (!IS_BUILTIN(CONFIG_UCLAMP_TASK) &&
+	if (!uclamp_is_used() &&
 	    type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) {
 		return max;
 	}
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index a8a0803..2bda9fd 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1654,6 +1654,7 @@
 	 */
 	raw_spin_lock(&rq->lock);
 	if (p->dl.dl_non_contending) {
+		update_rq_clock(rq);
 		sub_running_bw(&p->dl, &rq->dl);
 		p->dl.dl_non_contending = 0;
 		/*
@@ -1743,13 +1744,16 @@
 }
 #endif
 
-static void set_next_task_dl(struct rq *rq, struct task_struct *p)
+static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first)
 {
 	p->se.exec_start = rq_clock_task(rq);
 
 	/* You can't push away the running task */
 	dequeue_pushable_dl_task(rq, p);
 
+	if (!first)
+		return;
+
 	if (hrtick_enabled(rq))
 		start_hrtick_dl(rq, p);
 
@@ -1785,7 +1789,7 @@
 	dl_se = pick_next_dl_entity(rq, dl_rq);
 	BUG_ON(!dl_se);
 	p = dl_task_of(dl_se);
-	set_next_task_dl(rq, p);
+	set_next_task_dl(rq, p, true);
 	return p;
 }
 
@@ -2389,6 +2393,8 @@
 			check_preempt_curr_dl(rq, p, 0);
 		else
 			resched_curr(rq);
+	} else {
+		update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0);
 	}
 }
 
@@ -2466,7 +2472,7 @@
 	u64 period = global_rt_period();
 	u64 new_bw = to_ratio(period, runtime);
 	struct dl_bw *dl_b;
-	int cpu, ret = 0;
+	int cpu, cpus, ret = 0;
 	unsigned long flags;
 
 	/*
@@ -2481,9 +2487,10 @@
 	for_each_possible_cpu(cpu) {
 		rcu_read_lock_sched();
 		dl_b = dl_bw_of(cpu);
+		cpus = dl_bw_cpus(cpu);
 
 		raw_spin_lock_irqsave(&dl_b->lock, flags);
-		if (new_bw < dl_b->total_bw)
+		if (new_bw * cpus < dl_b->total_bw)
 			ret = -EBUSY;
 		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 
@@ -2616,7 +2623,7 @@
 	dl_se->dl_runtime = attr->sched_runtime;
 	dl_se->dl_deadline = attr->sched_deadline;
 	dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
-	dl_se->flags = attr->sched_flags;
+	dl_se->flags = attr->sched_flags & SCHED_DL_FLAGS;
 	dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
 	dl_se->dl_density = to_ratio(dl_se->dl_deadline, dl_se->dl_runtime);
 }
@@ -2629,7 +2636,8 @@
 	attr->sched_runtime = dl_se->dl_runtime;
 	attr->sched_deadline = dl_se->dl_deadline;
 	attr->sched_period = dl_se->dl_period;
-	attr->sched_flags = dl_se->flags;
+	attr->sched_flags &= ~SCHED_DL_FLAGS;
+	attr->sched_flags |= dl_se->flags;
 }
 
 /*
@@ -2690,6 +2698,7 @@
 	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;
@@ -2703,7 +2712,7 @@
 	if (dl_se->dl_runtime != attr->sched_runtime ||
 	    dl_se->dl_deadline != attr->sched_deadline ||
 	    dl_se->dl_period != attr->sched_period ||
-	    dl_se->flags != attr->sched_flags)
+	    dl_se->flags != (attr->sched_flags & SCHED_DL_FLAGS))
 		return true;
 
 	return false;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index f7e4579..faada71 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -8,8 +8,6 @@
  */
 #include "sched.h"
 
-static DEFINE_SPINLOCK(sched_debug_lock);
-
 /*
  * This allows printing both to /proc/sched_debug and
  * to the console
@@ -258,7 +256,7 @@
 	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),  0644, proc_dointvec_minmax);
+	set_table_entry(&table[5], "flags",		  &sd->flags,		    sizeof(int),  0444, proc_dointvec_minmax);
 	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 */
@@ -417,16 +415,37 @@
 #endif
 
 #ifdef CONFIG_CGROUP_SCHED
+static DEFINE_SPINLOCK(sched_debug_lock);
 static char group_path[PATH_MAX];
 
-static char *task_group_path(struct task_group *tg)
+static void task_group_path(struct task_group *tg, char *path, int plen)
 {
-	if (autogroup_path(tg, group_path, PATH_MAX))
-		return group_path;
+	if (autogroup_path(tg, path, plen))
+		return;
 
-	cgroup_path(tg->css.cgroup, group_path, PATH_MAX);
+	cgroup_path(tg->css.cgroup, path, plen);
+}
 
-	return group_path;
+/*
+ * Only 1 SEQ_printf_task_group_path() caller can use the full length
+ * group_path[] for cgroup path. Other simultaneous callers will have
+ * to use a shorter stack buffer. A "..." suffix is appended at the end
+ * of the stack buffer so that it will show up in case the output length
+ * matches the given buffer size to indicate possible path name truncation.
+ */
+#define SEQ_printf_task_group_path(m, tg, fmt...)			\
+{									\
+	if (spin_trylock(&sched_debug_lock)) {				\
+		task_group_path(tg, group_path, sizeof(group_path));	\
+		SEQ_printf(m, fmt, group_path);				\
+		spin_unlock(&sched_debug_lock);				\
+	} else {							\
+		char buf[128];						\
+		char *bufend = buf + sizeof(buf) - 3;			\
+		task_group_path(tg, buf, bufend - buf);			\
+		strcpy(bufend - 1, "...");				\
+		SEQ_printf(m, fmt, buf);				\
+	}								\
 }
 #endif
 
@@ -453,7 +472,7 @@
 	SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p));
 #endif
 #ifdef CONFIG_CGROUP_SCHED
-	SEQ_printf(m, " %s", task_group_path(task_group(p)));
+	SEQ_printf_task_group_path(m, task_group(p), " %s")
 #endif
 
 	SEQ_printf(m, "\n");
@@ -490,7 +509,7 @@
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	SEQ_printf(m, "\n");
-	SEQ_printf(m, "cfs_rq[%d]:%s\n", cpu, task_group_path(cfs_rq->tg));
+	SEQ_printf_task_group_path(m, cfs_rq->tg, "cfs_rq[%d]:%s\n", cpu);
 #else
 	SEQ_printf(m, "\n");
 	SEQ_printf(m, "cfs_rq[%d]:\n", cpu);
@@ -562,7 +581,7 @@
 {
 #ifdef CONFIG_RT_GROUP_SCHED
 	SEQ_printf(m, "\n");
-	SEQ_printf(m, "rt_rq[%d]:%s\n", cpu, task_group_path(rt_rq->tg));
+	SEQ_printf_task_group_path(m, rt_rq->tg, "rt_rq[%d]:%s\n", cpu);
 #else
 	SEQ_printf(m, "\n");
 	SEQ_printf(m, "rt_rq[%d]:\n", cpu);
@@ -614,7 +633,6 @@
 static void print_cpu(struct seq_file *m, int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	unsigned long flags;
 
 #ifdef CONFIG_X86
 	{
@@ -666,13 +684,11 @@
 	}
 #undef P
 
-	spin_lock_irqsave(&sched_debug_lock, flags);
 	print_cfs_stats(m, cpu);
 	print_rt_stats(m, cpu);
 	print_dl_stats(m, cpu);
 
 	print_rq(m, rq, cpu);
-	spin_unlock_irqrestore(&sched_debug_lock, flags);
 	SEQ_printf(m, "\n");
 }
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 69a81a5..87d9fad 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2678,7 +2678,7 @@
 	/*
 	 * We don't care about NUMA placement if we don't have memory.
 	 */
-	if (!curr->mm || (curr->flags & PF_EXITING) || work->next != work)
+	if ((curr->flags & (PF_EXITING | PF_KTHREAD)) || work->next != work)
 		return;
 
 	/*
@@ -2927,7 +2927,7 @@
  *
  *                     tg->weight * grq->load.weight
  *   ge->load.weight = -----------------------------               (1)
- *			  \Sum grq->load.weight
+ *                       \Sum grq->load.weight
  *
  * Now, because computing that sum is prohibitively expensive to compute (been
  * there, done that) we approximate it with this average stuff. The average
@@ -2941,7 +2941,7 @@
  *
  *                     tg->weight * grq->avg.load_avg
  *   ge->load.weight = ------------------------------              (3)
- *				tg->load_avg
+ *                             tg->load_avg
  *
  * Where: tg->load_avg ~= \Sum grq->avg.load_avg
  *
@@ -2957,7 +2957,7 @@
  *
  *                     tg->weight * grq->load.weight
  *   ge->load.weight = ----------------------------- = tg->weight   (4)
- *			    grp->load.weight
+ *                         grp->load.weight
  *
  * That is, the sum collapses because all other CPUs are idle; the UP scenario.
  *
@@ -2976,7 +2976,7 @@
  *
  *                     tg->weight * grq->load.weight
  *   ge->load.weight = -----------------------------		   (6)
- *				tg_load_avg'
+ *                             tg_load_avg'
  *
  * Where:
  *
@@ -3504,9 +3504,6 @@
 	cfs_rq->load_last_update_time_copy = sa->last_update_time;
 #endif
 
-	if (decayed)
-		cfs_rq_util_change(cfs_rq, 0);
-
 	return decayed;
 }
 
@@ -3616,8 +3613,12 @@
 		attach_entity_load_avg(cfs_rq, se, SCHED_CPUFREQ_MIGRATION);
 		update_tg_load_avg(cfs_rq, 0);
 
-	} else if (decayed && (flags & UPDATE_TG))
-		update_tg_load_avg(cfs_rq, 0);
+	} else if (decayed) {
+		cfs_rq_util_change(cfs_rq, 0);
+
+		if (flags & UPDATE_TG)
+			update_tg_load_avg(cfs_rq, 0);
+	}
 }
 
 #ifndef CONFIG_64BIT
@@ -3813,7 +3814,7 @@
 	if (!static_branch_unlikely(&sched_asym_cpucapacity))
 		return;
 
-	if (!p) {
+	if (!p || p->nr_cpus_allowed == 1) {
 		rq->misfit_task_load = 0;
 		return;
 	}
@@ -3823,7 +3824,11 @@
 		return;
 	}
 
-	rq->misfit_task_load = task_h_load(p);
+	/*
+	 * Make sure that misfit_task_load will not be null even if
+	 * task_h_load() returns 0.
+	 */
+	rq->misfit_task_load = max_t(unsigned long, task_h_load(p), 1);
 }
 
 #else /* CONFIG_SMP */
@@ -3926,6 +3931,7 @@
 #endif
 }
 
+static inline bool cfs_bandwidth_used(void);
 
 /*
  * MIGRATION
@@ -4004,10 +4010,16 @@
 		__enqueue_entity(cfs_rq, se);
 	se->on_rq = 1;
 
-	if (cfs_rq->nr_running == 1) {
+	/*
+	 * When bandwidth control is enabled, cfs might have been removed
+	 * because of a parent been throttled but cfs->nr_running > 1. Try to
+	 * add it unconditionnally.
+	 */
+	if (cfs_rq->nr_running == 1 || cfs_bandwidth_used())
 		list_add_leaf_cfs_rq(cfs_rq);
+
+	if (cfs_rq->nr_running == 1)
 		check_enqueue_throttle(cfs_rq);
-	}
 }
 
 static void __clear_buddies_last(struct sched_entity *se)
@@ -4371,16 +4383,16 @@
 }
 
 /* returns 0 on failure to allocate runtime */
-static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
+static int __assign_cfs_rq_runtime(struct cfs_bandwidth *cfs_b,
+				   struct cfs_rq *cfs_rq, u64 target_runtime)
 {
-	struct task_group *tg = cfs_rq->tg;
-	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
-	u64 amount = 0, min_amount;
+	u64 min_amount, amount = 0;
+
+	lockdep_assert_held(&cfs_b->lock);
 
 	/* note: this is a positive sum as runtime_remaining <= 0 */
-	min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining;
+	min_amount = target_runtime - cfs_rq->runtime_remaining;
 
-	raw_spin_lock(&cfs_b->lock);
 	if (cfs_b->quota == RUNTIME_INF)
 		amount = min_amount;
 	else {
@@ -4392,13 +4404,25 @@
 			cfs_b->idle = 0;
 		}
 	}
-	raw_spin_unlock(&cfs_b->lock);
 
 	cfs_rq->runtime_remaining += amount;
 
 	return cfs_rq->runtime_remaining > 0;
 }
 
+/* returns 0 on failure to allocate runtime */
+static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
+{
+	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
+	int ret;
+
+	raw_spin_lock(&cfs_b->lock);
+	ret = __assign_cfs_rq_runtime(cfs_b, cfs_rq, sched_cfs_bandwidth_slice());
+	raw_spin_unlock(&cfs_b->lock);
+
+	return ret;
+}
+
 static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
 {
 	/* dock delta_exec before expiring quota (as it could span periods) */
@@ -4487,13 +4511,33 @@
 	return 0;
 }
 
-static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
+static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 {
 	struct rq *rq = rq_of(cfs_rq);
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 	struct sched_entity *se;
 	long task_delta, idle_task_delta, dequeue = 1;
-	bool empty;
+
+	raw_spin_lock(&cfs_b->lock);
+	/* This will start the period timer if necessary */
+	if (__assign_cfs_rq_runtime(cfs_b, cfs_rq, 1)) {
+		/*
+		 * We have raced with bandwidth becoming available, and if we
+		 * actually throttled the timer might not unthrottle us for an
+		 * entire period. We additionally needed to make sure that any
+		 * subsequent check_cfs_rq_runtime calls agree not to throttle
+		 * us, as we may commit to do cfs put_prev+pick_next, so we ask
+		 * for 1ns of runtime rather than just check cfs_b.
+		 */
+		dequeue = 0;
+	} else {
+		list_add_tail_rcu(&cfs_rq->throttled_list,
+				  &cfs_b->throttled_cfs_rq);
+	}
+	raw_spin_unlock(&cfs_b->lock);
+
+	if (!dequeue)
+		return false;  /* Throttle no longer required. */
 
 	se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))];
 
@@ -4522,29 +4566,13 @@
 	if (!se)
 		sub_nr_running(rq, task_delta);
 
+	/*
+	 * Note: distribution will already see us throttled via the
+	 * throttled-list.  rq->lock protects completion.
+	 */
 	cfs_rq->throttled = 1;
 	cfs_rq->throttled_clock = rq_clock(rq);
-	raw_spin_lock(&cfs_b->lock);
-	empty = list_empty(&cfs_b->throttled_cfs_rq);
-
-	/*
-	 * Add to the _head_ of the list, so that an already-started
-	 * distribute_cfs_runtime will not see us. If disribute_cfs_runtime is
-	 * not running add to the tail so that later runqueues don't get starved.
-	 */
-	if (cfs_b->distribute_running)
-		list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
-	else
-		list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
-
-	/*
-	 * If we're the first throttled task, make sure the bandwidth
-	 * timer is running.
-	 */
-	if (empty)
-		start_cfs_bandwidth(cfs_b);
-
-	raw_spin_unlock(&cfs_b->lock);
+	return true;
 }
 
 void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
@@ -4552,7 +4580,6 @@
 	struct rq *rq = rq_of(cfs_rq);
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 	struct sched_entity *se;
-	int enqueue = 1;
 	long task_delta, idle_task_delta;
 
 	se = cfs_rq->tg->se[cpu_of(rq)];
@@ -4576,23 +4603,55 @@
 	idle_task_delta = cfs_rq->idle_h_nr_running;
 	for_each_sched_entity(se) {
 		if (se->on_rq)
-			enqueue = 0;
-
+			break;
 		cfs_rq = cfs_rq_of(se);
-		if (enqueue)
-			enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
+		enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
+
 		cfs_rq->h_nr_running += task_delta;
 		cfs_rq->idle_h_nr_running += idle_task_delta;
 
+		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
+			goto unthrottle_throttle;
+	}
+
+	for_each_sched_entity(se) {
+		cfs_rq = cfs_rq_of(se);
+
+		cfs_rq->h_nr_running += task_delta;
+		cfs_rq->idle_h_nr_running += idle_task_delta;
+
+
+		/* end evaluation on encountering a throttled cfs_rq */
+		if (cfs_rq_throttled(cfs_rq))
+			goto unthrottle_throttle;
+
+		/*
+		 * One parent has been throttled and cfs_rq removed from the
+		 * list. Add it back to not break the leaf list.
+		 */
+		if (throttled_hierarchy(cfs_rq))
+			list_add_leaf_cfs_rq(cfs_rq);
+	}
+
+	/* At this point se is NULL and we are at root level*/
+	add_nr_running(rq, task_delta);
+
+unthrottle_throttle:
+	/*
+	 * The cfs_rq_throttled() breaks in the above iteration can result in
+	 * incomplete leaf list maintenance, resulting in triggering the
+	 * assertion below.
+	 */
+	for_each_sched_entity(se) {
+		cfs_rq = cfs_rq_of(se);
+
+		if (list_add_leaf_cfs_rq(cfs_rq))
 			break;
 	}
 
 	assert_list_leaf_cfs_rq(rq);
 
-	if (!se)
-		add_nr_running(rq, task_delta);
-
 	/* Determine whether we need to wake up potentially idle CPU: */
 	if (rq->curr == rq->idle && rq->cfs.nr_running)
 		resched_curr(rq);
@@ -4727,7 +4786,7 @@
 static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire)
 {
 	struct hrtimer *refresh_timer = &cfs_b->period_timer;
-	u64 remaining;
+	s64 remaining;
 
 	/* if the call-back is running a quota refresh is already occurring */
 	if (hrtimer_callback_running(refresh_timer))
@@ -4735,7 +4794,7 @@
 
 	/* is a quota refresh about to occur? */
 	remaining = ktime_to_ns(hrtimer_expires_remaining(refresh_timer));
-	if (remaining < min_expire)
+	if (remaining < (s64)min_expire)
 		return 1;
 
 	return 0;
@@ -4892,8 +4951,7 @@
 	if (cfs_rq_throttled(cfs_rq))
 		return true;
 
-	throttle_cfs_rq(cfs_rq);
-	return true;
+	return throttle_cfs_rq(cfs_rq);
 }
 
 static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
@@ -4923,6 +4981,8 @@
 		if (!overrun)
 			break;
 
+		idle = do_sched_cfs_period_timer(cfs_b, overrun, flags);
+
 		if (++count > 3) {
 			u64 new, old = ktime_to_ns(cfs_b->period);
 
@@ -4952,8 +5012,6 @@
 			/* reset count so we don't come right back in here */
 			count = 0;
 		}
-
-		idle = do_sched_cfs_period_timer(cfs_b, overrun, flags);
 	}
 	if (idle)
 		cfs_b->period_active = 0;
@@ -5190,6 +5248,7 @@
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
 	int idle_h_nr_running = task_has_idle_policy(p);
+	int task_new = !(flags & ENQUEUE_WAKEUP);
 
 	/*
 	 * The code below (indirectly) updates schedutil which looks at
@@ -5213,32 +5272,38 @@
 		cfs_rq = cfs_rq_of(se);
 		enqueue_entity(cfs_rq, se, flags);
 
-		/*
-		 * end evaluation on encountering a throttled cfs_rq
-		 *
-		 * note: in the case of encountering a throttled cfs_rq we will
-		 * post the final h_nr_running increment below.
-		 */
-		if (cfs_rq_throttled(cfs_rq))
-			break;
 		cfs_rq->h_nr_running++;
 		cfs_rq->idle_h_nr_running += idle_h_nr_running;
 
+		/* end evaluation on encountering a throttled cfs_rq */
+		if (cfs_rq_throttled(cfs_rq))
+			goto enqueue_throttle;
+
 		flags = ENQUEUE_WAKEUP;
 	}
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
-		cfs_rq->h_nr_running++;
-		cfs_rq->idle_h_nr_running += idle_h_nr_running;
-
-		if (cfs_rq_throttled(cfs_rq))
-			break;
 
 		update_load_avg(cfs_rq, se, UPDATE_TG);
 		update_cfs_group(se);
+
+		cfs_rq->h_nr_running++;
+		cfs_rq->idle_h_nr_running += idle_h_nr_running;
+
+		/* end evaluation on encountering a throttled cfs_rq */
+		if (cfs_rq_throttled(cfs_rq))
+			goto enqueue_throttle;
+
+               /*
+                * One parent has been throttled and cfs_rq removed from the
+                * list. Add it back to not break the leaf list.
+                */
+               if (throttled_hierarchy(cfs_rq))
+                       list_add_leaf_cfs_rq(cfs_rq);
 	}
 
+enqueue_throttle:
 	if (!se) {
 		add_nr_running(rq, 1);
 		/*
@@ -5255,7 +5320,7 @@
 		 * into account, but that is not straightforward to implement,
 		 * and the following generally works well enough in practice.
 		 */
-		if (flags & ENQUEUE_WAKEUP)
+		if (!task_new)
 			update_overutilized_status(rq);
 
 	}
@@ -5298,17 +5363,13 @@
 		cfs_rq = cfs_rq_of(se);
 		dequeue_entity(cfs_rq, se, flags);
 
-		/*
-		 * end evaluation on encountering a throttled cfs_rq
-		 *
-		 * note: in the case of encountering a throttled cfs_rq we will
-		 * post the final h_nr_running decrement below.
-		*/
-		if (cfs_rq_throttled(cfs_rq))
-			break;
 		cfs_rq->h_nr_running--;
 		cfs_rq->idle_h_nr_running -= idle_h_nr_running;
 
+		/* end evaluation on encountering a throttled cfs_rq */
+		if (cfs_rq_throttled(cfs_rq))
+			goto dequeue_throttle;
+
 		/* Don't dequeue parent if it has other entities besides us */
 		if (cfs_rq->load.weight) {
 			/* Avoid re-evaluating load for this entity: */
@@ -5326,16 +5387,20 @@
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
-		cfs_rq->h_nr_running--;
-		cfs_rq->idle_h_nr_running -= idle_h_nr_running;
-
-		if (cfs_rq_throttled(cfs_rq))
-			break;
 
 		update_load_avg(cfs_rq, se, UPDATE_TG);
 		update_cfs_group(se);
+
+		cfs_rq->h_nr_running--;
+		cfs_rq->idle_h_nr_running -= idle_h_nr_running;
+
+		/* end evaluation on encountering a throttled cfs_rq */
+		if (cfs_rq_throttled(cfs_rq))
+			goto dequeue_throttle;
+
 	}
 
+dequeue_throttle:
 	if (!se)
 		sub_nr_running(rq, 1);
 
@@ -5892,7 +5957,7 @@
 /*
  * Scan the local SMT mask for idle CPUs.
  */
-static int select_idle_smt(struct task_struct *p, int target)
+static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	int cpu, si_cpu = -1;
 
@@ -5900,7 +5965,8 @@
 		return -1;
 
 	for_each_cpu(cpu, cpu_smt_mask(target)) {
-		if (!cpumask_test_cpu(cpu, p->cpus_ptr))
+		if (!cpumask_test_cpu(cpu, p->cpus_ptr) ||
+		    !cpumask_test_cpu(cpu, sched_domain_span(sd)))
 			continue;
 		if (available_idle_cpu(cpu))
 			return cpu;
@@ -5918,7 +5984,7 @@
 	return -1;
 }
 
-static inline int select_idle_smt(struct task_struct *p, int target)
+static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	return -1;
 }
@@ -5932,6 +5998,7 @@
  */
 static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target)
 {
+	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
 	struct sched_domain *this_sd;
 	u64 avg_cost, avg_idle;
 	u64 time, cost;
@@ -5963,11 +6030,11 @@
 
 	time = cpu_clock(this);
 
-	for_each_cpu_wrap(cpu, sched_domain_span(sd), target) {
+	cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
+
+	for_each_cpu_wrap(cpu, cpus, target) {
 		if (!--nr)
 			return si_cpu;
-		if (!cpumask_test_cpu(cpu, p->cpus_ptr))
-			continue;
 		if (available_idle_cpu(cpu))
 			break;
 		if (si_cpu == -1 && sched_idle_cpu(cpu))
@@ -6027,7 +6094,7 @@
 	if ((unsigned)i < nr_cpumask_bits)
 		return i;
 
-	i = select_idle_smt(p, target);
+	i = select_idle_smt(p, sd, target);
 	if ((unsigned)i < nr_cpumask_bits)
 		return i;
 
@@ -7233,6 +7300,10 @@
 	if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu))
 		return 0;
 
+	/* Disregard pcpu kthreads; they are where they need to be. */
+	if (kthread_is_per_cpu(p))
+		return 0;
+
 	if (!cpumask_test_cpu(env->dst_cpu, p->cpus_ptr)) {
 		int cpu;
 
@@ -7381,7 +7452,15 @@
 		if (!can_migrate_task(p, env))
 			goto next;
 
-		load = task_h_load(p);
+		/*
+		 * 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;
@@ -7517,6 +7596,28 @@
 static inline void update_blocked_load_status(struct rq *rq, bool has_blocked) {}
 #endif
 
+static bool __update_blocked_others(struct rq *rq, bool *done)
+{
+	const struct sched_class *curr_class;
+	u64 now = rq_clock_pelt(rq);
+	bool decayed;
+
+	/*
+	 * update_load_avg() can call cpufreq_update_util(). Make sure that RT,
+	 * DL and IRQ signals have been updated before updating CFS.
+	 */
+	curr_class = rq->curr->sched_class;
+
+	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_irq_load_avg(rq, 0);
+
+	if (others_have_blocked(rq))
+		*done = false;
+
+	return decayed;
+}
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
 static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
@@ -7536,29 +7637,11 @@
 	return true;
 }
 
-static void update_blocked_averages(int cpu)
+static bool __update_blocked_fair(struct rq *rq, bool *done)
 {
-	struct rq *rq = cpu_rq(cpu);
 	struct cfs_rq *cfs_rq, *pos;
-	const struct sched_class *curr_class;
-	struct rq_flags rf;
-	bool done = true;
-
-	rq_lock_irqsave(rq, &rf);
-	update_rq_clock(rq);
-
-	/*
-	 * update_cfs_rq_load_avg() can call cpufreq_update_util(). Make sure
-	 * that RT, DL and IRQ signals have been updated before updating CFS.
-	 */
-	curr_class = rq->curr->sched_class;
-	update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
-	update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
-	update_irq_load_avg(rq, 0);
-
-	/* Don't need periodic decay once load/util_avg are null */
-	if (others_have_blocked(rq))
-		done = false;
+	bool decayed = false;
+	int cpu = cpu_of(rq);
 
 	/*
 	 * Iterates the task_group tree in a bottom up fashion, see
@@ -7567,13 +7650,17 @@
 	for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) {
 		struct sched_entity *se;
 
-		if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq))
+		if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq)) {
 			update_tg_load_avg(cfs_rq, 0);
 
+			if (cfs_rq == &rq->cfs)
+				decayed = true;
+		}
+
 		/* Propagate pending load changes to the parent, if any: */
 		se = cfs_rq->tg->se[cpu];
 		if (se && !skip_blocked_update(se))
-			update_load_avg(cfs_rq_of(se), se, 0);
+			update_load_avg(cfs_rq_of(se), se, UPDATE_TG);
 
 		/*
 		 * There can be a lot of idle CPU cgroups.  Don't let fully
@@ -7584,11 +7671,10 @@
 
 		/* Don't need periodic decay once load/util_avg are null */
 		if (cfs_rq_has_blocked(cfs_rq))
-			done = false;
+			*done = false;
 	}
 
-	update_blocked_load_status(rq, !done);
-	rq_unlock_irqrestore(rq, &rf);
+	return decayed;
 }
 
 /*
@@ -7638,29 +7724,16 @@
 			cfs_rq_load_avg(cfs_rq) + 1);
 }
 #else
-static inline void update_blocked_averages(int cpu)
+static bool __update_blocked_fair(struct rq *rq, bool *done)
 {
-	struct rq *rq = cpu_rq(cpu);
 	struct cfs_rq *cfs_rq = &rq->cfs;
-	const struct sched_class *curr_class;
-	struct rq_flags rf;
+	bool decayed;
 
-	rq_lock_irqsave(rq, &rf);
-	update_rq_clock(rq);
+	decayed = update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq);
+	if (cfs_rq_has_blocked(cfs_rq))
+		*done = false;
 
-	/*
-	 * update_cfs_rq_load_avg() can call cpufreq_update_util(). Make sure
-	 * that RT, DL and IRQ signals have been updated before updating CFS.
-	 */
-	curr_class = rq->curr->sched_class;
-	update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
-	update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
-	update_irq_load_avg(rq, 0);
-
-	update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq);
-
-	update_blocked_load_status(rq, cfs_rq_has_blocked(cfs_rq) || others_have_blocked(rq));
-	rq_unlock_irqrestore(rq, &rf);
+	return decayed;
 }
 
 static unsigned long task_h_load(struct task_struct *p)
@@ -7669,6 +7742,24 @@
 }
 #endif
 
+static void update_blocked_averages(int cpu)
+{
+	bool decayed = false, done = true;
+	struct rq *rq = cpu_rq(cpu);
+	struct rq_flags rf;
+
+	rq_lock_irqsave(rq, &rf);
+	update_rq_clock(rq);
+
+	decayed |= __update_blocked_others(rq, &done);
+	decayed |= __update_blocked_fair(rq, &done);
+
+	update_blocked_load_status(rq, !done);
+	if (decayed)
+		cpufreq_update_util(rq, 0);
+	rq_unlock_irqrestore(rq, &rf);
+}
+
 /********** Helpers for find_busiest_group ************************/
 
 /*
@@ -9335,7 +9426,12 @@
 {
 	int ilb_cpu;
 
-	nohz.next_balance++;
+	/*
+	 * Increase nohz.next_balance only when if full ilb is triggered but
+	 * not if we only update stats.
+	 */
+	if (flags & NOHZ_BALANCE_KICK)
+		nohz.next_balance = jiffies+1;
 
 	ilb_cpu = find_new_ilb();
 
@@ -9653,6 +9749,14 @@
 		}
 	}
 
+	/*
+	 * next_balance will be updated only when there is a need.
+	 * When the CPU is attached to null domain for ex, it will not be
+	 * updated.
+	 */
+	if (likely(update_next_balance))
+		nohz.next_balance = next_balance;
+
 	/* Newly idle CPU doesn't need an update */
 	if (idle != CPU_NEWLY_IDLE) {
 		update_blocked_averages(this_cpu);
@@ -9673,14 +9777,6 @@
 	if (has_blocked_load)
 		WRITE_ONCE(nohz.has_blocked, 1);
 
-	/*
-	 * next_balance will be updated only when there is a need.
-	 * When the CPU is attached to null domain for ex, it will not be
-	 * updated.
-	 */
-	if (likely(update_next_balance))
-		nohz.next_balance = next_balance;
-
 	return ret;
 }
 
@@ -10050,16 +10146,22 @@
 {
 	struct cfs_rq *cfs_rq;
 
+	list_add_leaf_cfs_rq(cfs_rq_of(se));
+
 	/* Start to propagate at parent */
 	se = se->parent;
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
 
-		if (cfs_rq_throttled(cfs_rq))
-			break;
+		if (!cfs_rq_throttled(cfs_rq)){
+			update_load_avg(cfs_rq, se, UPDATE_TG);
+			list_add_leaf_cfs_rq(cfs_rq);
+			continue;
+		}
 
-		update_load_avg(cfs_rq, se, UPDATE_TG);
+		if (list_add_leaf_cfs_rq(cfs_rq))
+			break;
 	}
 }
 #else
@@ -10151,7 +10253,7 @@
  * This routine is mostly called to set cfs_rq->curr field when a task
  * migrates between groups/classes.
  */
-static void set_next_task_fair(struct rq *rq, struct task_struct *p)
+static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first)
 {
 	struct sched_entity *se = &p->se;
 
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index f65ef1e..3f8c786 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -249,6 +249,7 @@
 		}
 
 		arch_cpu_idle_enter();
+		rcu_nocb_flush_deferred_wakeup();
 
 		/*
 		 * In poll mode we reenable interrupts and spin. Also if we
@@ -385,7 +386,7 @@
 {
 }
 
-static void set_next_task_idle(struct rq *rq, struct task_struct *next)
+static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first)
 {
 	update_idle_core(rq);
 	schedstat_inc(rq->sched_goidle);
@@ -399,7 +400,7 @@
 	if (prev)
 		put_prev_task(rq, prev);
 
-	set_next_task_idle(rq, next);
+	set_next_task_idle(rq, next, true);
 
 	return next;
 }
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index 28a5165..de22da6 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -231,16 +231,11 @@
 	return calc_load_idx & 1;
 }
 
-void calc_load_nohz_start(void)
+static void calc_load_nohz_fold(struct rq *rq)
 {
-	struct rq *this_rq = this_rq();
 	long delta;
 
-	/*
-	 * We're going into NO_HZ mode, if there's any pending delta, fold it
-	 * into the pending NO_HZ delta.
-	 */
-	delta = calc_load_fold_active(this_rq, 0);
+	delta = calc_load_fold_active(rq, 0);
 	if (delta) {
 		int idx = calc_load_write_idx();
 
@@ -248,6 +243,24 @@
 	}
 }
 
+void calc_load_nohz_start(void)
+{
+	/*
+	 * We're going into NO_HZ mode, if there's any pending delta, fold it
+	 * into the pending NO_HZ delta.
+	 */
+	calc_load_nohz_fold(this_rq());
+}
+
+/*
+ * Keep track of the load for NOHZ_FULL, must be called between
+ * calc_load_nohz_{start,stop}().
+ */
+void calc_load_nohz_remote(struct rq *rq)
+{
+	calc_load_nohz_fold(rq);
+}
+
 void calc_load_nohz_stop(void)
 {
 	struct rq *this_rq = this_rq();
@@ -268,7 +281,7 @@
 		this_rq->calc_load_update += LOAD_FREQ;
 }
 
-static long calc_load_nohz_fold(void)
+static long calc_load_nohz_read(void)
 {
 	int idx = calc_load_read_idx();
 	long delta = 0;
@@ -323,7 +336,7 @@
 }
 #else /* !CONFIG_NO_HZ_COMMON */
 
-static inline long calc_load_nohz_fold(void) { return 0; }
+static inline long calc_load_nohz_read(void) { return 0; }
 static inline void calc_global_nohz(void) { }
 
 #endif /* CONFIG_NO_HZ_COMMON */
@@ -346,7 +359,7 @@
 	/*
 	 * Fold the 'old' NO_HZ-delta to include all NO_HZ CPUs.
 	 */
-	delta = calc_load_nohz_fold();
+	delta = calc_load_nohz_read();
 	if (delta)
 		atomic_long_add(delta, &calc_load_tasks);
 
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index 168479a..46c142b 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -30,6 +30,23 @@
 	smp_mb();	/* IPIs should be serializing but paranoid. */
 }
 
+static void ipi_sync_core(void *info)
+{
+	/*
+	 * The smp_mb() in membarrier after all the IPIs is supposed to
+	 * ensure that memory on remote CPUs that occur before the IPI
+	 * become visible to membarrier()'s caller -- see scenario B in
+	 * the big comment at the top of this file.
+	 *
+	 * A sync_core() would provide this guarantee, but
+	 * sync_core_before_usermode() might end up being deferred until
+	 * after membarrier()'s smp_mb().
+	 */
+	smp_mb();	/* IPIs should be serializing but paranoid. */
+
+	sync_core_before_usermode();
+}
+
 static void ipi_sync_rq_state(void *info)
 {
 	struct mm_struct *mm = (struct mm_struct *) info;
@@ -134,6 +151,7 @@
 	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 (!IS_ENABLED(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE))
@@ -141,6 +159,7 @@
 		if (!(atomic_read(&mm->membarrier_state) &
 		      MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY))
 			return -EPERM;
+		ipi_func = ipi_sync_core;
 	} else {
 		if (!(atomic_read(&mm->membarrier_state) &
 		      MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY))
@@ -181,7 +200,7 @@
 	rcu_read_unlock();
 
 	preempt_disable();
-	smp_call_function_many(tmpmask, ipi_mb, NULL, 1);
+	smp_call_function_many(tmpmask, ipi_func, NULL, 1);
 	preempt_enable();
 
 	free_cpumask_var(tmpmask);
@@ -246,9 +265,7 @@
 	}
 	rcu_read_unlock();
 
-	preempt_disable();
-	smp_call_function_many(tmpmask, ipi_sync_rq_state, mm, 1);
-	preempt_enable();
+	on_each_cpu_mask(tmpmask, ipi_sync_rq_state, mm, true);
 
 	free_cpumask_var(tmpmask);
 	cpus_read_unlock();
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 517e371..9154e74 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -185,7 +185,8 @@
 
 	for_each_possible_cpu(cpu)
 		seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq);
-	group->avg_next_update = sched_clock() + psi_period;
+	group->avg_last_update = sched_clock();
+	group->avg_next_update = group->avg_last_update + psi_period;
 	INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work);
 	mutex_init(&group->avgs_lock);
 	/* Init trigger-related members */
@@ -481,7 +482,7 @@
 		u32 remaining;
 
 		remaining = win->size - elapsed;
-		growth += div_u64(win->prev_growth * remaining, win->size);
+		growth += div64_u64(win->prev_growth * remaining, win->size);
 	}
 
 	return growth;
@@ -1198,6 +1199,9 @@
 	if (static_branch_likely(&psi_disabled))
 		return -EOPNOTSUPP;
 
+	if (!nbytes)
+		return -EINVAL;
+
 	buf_size = min(nbytes, sizeof(buf));
 	if (copy_from_user(buf, user_buf, buf_size))
 		return -EFAULT;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 9b8adc0..2dffb87 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -9,6 +9,8 @@
 
 int sched_rr_timeslice = RR_TIMESLICE;
 int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
+/* More than 4 hours if BW_SHIFT equals 20. */
+static const u64 max_rt_runtime = MAX_BW;
 
 static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);
 
@@ -1515,13 +1517,16 @@
 #endif
 }
 
-static inline void set_next_task_rt(struct rq *rq, struct task_struct *p)
+static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, bool first)
 {
 	p->se.exec_start = rq_clock_task(rq);
 
 	/* The running task is never eligible for pushing */
 	dequeue_pushable_task(rq, p);
 
+	if (!first)
+		return;
+
 	/*
 	 * If prev task was rt, put_prev_task() has already updated the
 	 * utilization. We only care of the case where we start to schedule a
@@ -1575,7 +1580,7 @@
 		return NULL;
 
 	p = _pick_next_task_rt(rq);
-	set_next_task_rt(rq, p);
+	set_next_task_rt(rq, p, true);
 	return p;
 }
 
@@ -2216,13 +2221,20 @@
 static void switched_to_rt(struct rq *rq, struct task_struct *p)
 {
 	/*
-	 * If we are already running, then there's nothing
-	 * that needs to be done. But if we are not running
-	 * we may need to preempt the current running task.
-	 * If that current running task is also an RT task
+	 * If we are running, update the avg_rt tracking, as the running time
+	 * will now on be accounted into the latter.
+	 */
+	if (task_current(rq, p)) {
+		update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0);
+		return;
+	}
+
+	/*
+	 * If we are not running we may need to preempt the current
+	 * running task. If that current running task is also an RT task
 	 * then see if we can move to another run queue.
 	 */
-	if (task_on_rq_queued(p) && rq->curr != p) {
+	if (task_on_rq_queued(p)) {
 #ifdef CONFIG_SMP
 		if (p->nr_cpus_allowed > 1 && rq->rt.overloaded)
 			rt_queue_push_tasks(rq);
@@ -2510,6 +2522,12 @@
 	if (rt_period == 0)
 		return -EINVAL;
 
+	/*
+	 * Bound quota to defend quota against overflow during bandwidth shift.
+	 */
+	if (rt_runtime != RUNTIME_INF && rt_runtime > max_rt_runtime)
+		return -EINVAL;
+
 	mutex_lock(&rt_constraints_mutex);
 	read_lock(&tasklist_lock);
 	err = __rt_schedulable(tg, rt_period, rt_runtime);
@@ -2631,7 +2649,9 @@
 		return -EINVAL;
 
 	if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
-		(sysctl_sched_rt_runtime > sysctl_sched_rt_period))
+		((sysctl_sched_rt_runtime > sysctl_sched_rt_period) ||
+		 ((u64)sysctl_sched_rt_runtime *
+			NSEC_PER_USEC > max_rt_runtime)))
 		return -EINVAL;
 
 	return 0;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c8870c5..fe755c1 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -118,7 +118,13 @@
 #ifdef CONFIG_64BIT
 # define NICE_0_LOAD_SHIFT	(SCHED_FIXEDPOINT_SHIFT + SCHED_FIXEDPOINT_SHIFT)
 # define scale_load(w)		((w) << SCHED_FIXEDPOINT_SHIFT)
-# define scale_load_down(w)	((w) >> SCHED_FIXEDPOINT_SHIFT)
+# define scale_load_down(w) \
+({ \
+	unsigned long __w = (w); \
+	if (__w) \
+		__w = max(2UL, __w >> SCHED_FIXEDPOINT_SHIFT); \
+	__w; \
+})
 #else
 # define NICE_0_LOAD_SHIFT	(SCHED_FIXEDPOINT_SHIFT)
 # define scale_load(w)		(w)
@@ -203,6 +209,8 @@
  */
 #define SCHED_FLAG_SUGOV	0x10000000
 
+#define SCHED_DL_FLAGS (SCHED_FLAG_RECLAIM | SCHED_FLAG_DL_OVERRUN | SCHED_FLAG_SUGOV)
+
 static inline bool dl_entity_is_special(struct sched_dl_entity *dl_se)
 {
 #ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
@@ -241,30 +249,6 @@
 
 void __dl_clear_params(struct task_struct *p);
 
-/*
- * To keep the bandwidth of -deadline tasks and groups under control
- * we need some place where:
- *  - store the maximum -deadline bandwidth of the system (the group);
- *  - cache the fraction of that bandwidth that is currently allocated.
- *
- * This is all done in the data structure below. It is similar to the
- * one used for RT-throttling (rt_bandwidth), with the main difference
- * that, since here we are only interested in admission control, we
- * do not decrease any runtime while the group "executes", neither we
- * need a timer to replenish it.
- *
- * With respect to SMP, the bandwidth is given on a per-CPU basis,
- * meaning that:
- *  - dl_bw (< 100%) is the bandwidth of the system (group) on each CPU;
- *  - dl_total_bw array contains, in the i-eth element, the currently
- *    allocated bandwidth on the i-eth CPU.
- * Moreover, groups consume bandwidth on each CPU, while tasks only
- * consume bandwidth on the CPU they're running on.
- * Finally, dl_total_bw_cpu is used to cache the index of dl_total_bw
- * that will be shown the next time the proc or cgroup controls will
- * be red. It on its turn can be changed by writing on its own
- * control.
- */
 struct dl_bandwidth {
 	raw_spinlock_t		dl_runtime_lock;
 	u64			dl_runtime;
@@ -276,6 +260,24 @@
 	return sysctl_sched_rt_runtime >= 0;
 }
 
+/*
+ * To keep the bandwidth of -deadline tasks under control
+ * we need some place where:
+ *  - store the maximum -deadline bandwidth of each cpu;
+ *  - cache the fraction of bandwidth that is currently allocated in
+ *    each root domain;
+ *
+ * This is all done in the data structure below. It is similar to the
+ * one used for RT-throttling (rt_bandwidth), with the main difference
+ * that, since here we are only interested in admission control, we
+ * do not decrease any runtime while the group "executes", neither we
+ * need a timer to replenish it.
+ *
+ * With respect to SMP, bandwidth is given on a per root domain basis,
+ * meaning that:
+ *  - bw (< 100%) is the deadline bandwidth of each CPU;
+ *  - total_bw is the currently allocated bandwidth in each root domain;
+ */
 struct dl_bw {
 	raw_spinlock_t		lock;
 	u64			bw;
@@ -835,6 +837,8 @@
 	unsigned int value;
 	struct uclamp_bucket bucket[UCLAMP_BUCKETS];
 };
+
+DECLARE_STATIC_KEY_FALSE(sched_uclamp_used);
 #endif /* CONFIG_UCLAMP_TASK */
 
 /*
@@ -971,6 +975,7 @@
 	call_single_data_t	hrtick_csd;
 #endif
 	struct hrtimer		hrtick_timer;
+	ktime_t 		hrtick_time;
 #endif
 
 #ifdef CONFIG_SCHEDSTATS
@@ -1560,7 +1565,7 @@
 
 #undef SCHED_FEAT
 
-#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_JUMP_LABEL)
+#ifdef CONFIG_SCHED_DEBUG
 
 /*
  * To support run-time toggling of sched features, all the translation units
@@ -1568,6 +1573,7 @@
  */
 extern const_debug unsigned int sysctl_sched_features;
 
+#ifdef CONFIG_JUMP_LABEL
 #define SCHED_FEAT(name, enabled)					\
 static __always_inline bool static_branch_##name(struct static_key *key) \
 {									\
@@ -1580,7 +1586,13 @@
 extern struct static_key sched_feat_keys[__SCHED_FEAT_NR];
 #define sched_feat(x) (static_branch_##x(&sched_feat_keys[__SCHED_FEAT_##x]))
 
-#else /* !(SCHED_DEBUG && CONFIG_JUMP_LABEL) */
+#else /* !CONFIG_JUMP_LABEL */
+
+#define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
+
+#endif /* CONFIG_JUMP_LABEL */
+
+#else /* !SCHED_DEBUG */
 
 /*
  * Each translation unit has its own copy of sysctl_sched_features to allow
@@ -1596,7 +1608,7 @@
 
 #define sched_feat(x) !!(sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
 
-#endif /* SCHED_DEBUG && CONFIG_JUMP_LABEL */
+#endif /* SCHED_DEBUG */
 
 extern struct static_key_false sched_numa_balancing;
 extern struct static_key_false sched_schedstats;
@@ -1728,7 +1740,7 @@
 					       struct task_struct *prev,
 					       struct rq_flags *rf);
 	void (*put_prev_task)(struct rq *rq, struct task_struct *p);
-	void (*set_next_task)(struct rq *rq, struct task_struct *p);
+	void (*set_next_task)(struct rq *rq, struct task_struct *p, bool first);
 
 #ifdef CONFIG_SMP
 	int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
@@ -1780,7 +1792,7 @@
 static inline void set_next_task(struct rq *rq, struct task_struct *next)
 {
 	WARN_ON_ONCE(rq->curr != next);
-	next->sched_class->set_next_task(rq, next);
+	next->sched_class->set_next_task(rq, next, false);
 }
 
 #ifdef CONFIG_SMP
@@ -1883,6 +1895,8 @@
 #define BW_SHIFT		20
 #define BW_UNIT			(1 << BW_SHIFT)
 #define RATIO_SHIFT		8
+#define MAX_BW_BITS		(64 - BW_SHIFT)
+#define MAX_BW			((1ULL << MAX_BW_BITS) - 1)
 unsigned long to_ratio(u64 period, u64 runtime);
 
 extern void init_entity_runnable_average(struct sched_entity *se);
@@ -2309,14 +2323,37 @@
 #endif /* CONFIG_CPU_FREQ */
 
 #ifdef CONFIG_UCLAMP_TASK
-enum uclamp_id uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
+unsigned int uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
 
+/**
+ * uclamp_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
+ *		against @rq only.
+ *
+ * Clamps the passed @util to the max(@rq, @p) effective uclamp values.
+ *
+ * If sched_uclamp_used static key is disabled, then just return the util
+ * without any clamping since uclamp aggregation at the rq level in the fast
+ * path is disabled, rendering this operation a NOP.
+ *
+ * Use uclamp_eff_value() if you don't care about uclamp values at rq level. It
+ * will return the correct effective uclamp value of the task even if the
+ * static key is disabled.
+ */
 static __always_inline
 unsigned int uclamp_util_with(struct rq *rq, unsigned int util,
 			      struct task_struct *p)
 {
-	unsigned int min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value);
-	unsigned int max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value);
+	unsigned int min_util;
+	unsigned int max_util;
+
+	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));
@@ -2338,6 +2375,19 @@
 {
 	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
+ * an operation that requires it.
+ *
+ * Returns true if userspace opted-in to use uclamp and aggregation at rq level
+ * hence is active.
+ */
+static inline bool uclamp_is_used(void)
+{
+	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)
@@ -2348,6 +2398,11 @@
 {
 	return util;
 }
+
+static inline bool uclamp_is_used(void)
+{
+	return false;
+}
 #endif /* CONFIG_UCLAMP_TASK */
 
 #ifdef arch_scale_freq_capacity
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index c064073..02dc0a8 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -29,7 +29,7 @@
 	/* we're never preempted */
 }
 
-static void set_next_task_stop(struct rq *rq, struct task_struct *stop)
+static void set_next_task_stop(struct rq *rq, struct task_struct *stop, bool first)
 {
 	stop->se.exec_start = rq_clock_task(rq);
 }
@@ -42,7 +42,7 @@
 	if (!sched_stop_runnable(rq))
 		return NULL;
 
-	set_next_task_stop(rq, rq->stop);
+	set_next_task_stop(rq, rq->stop, true);
 	return rq->stop;
 }
 
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 49b835f..ffaa97a 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1333,7 +1333,7 @@
 		sd_flags = (*tl->sd_flags)();
 	if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS,
 			"wrong sd_flags in topology description\n"))
-		sd_flags &= ~TOPOLOGY_SD_FLAGS;
+		sd_flags &= TOPOLOGY_SD_FLAGS;
 
 	/* Apply detected topology flags */
 	sd_flags |= dflags;
@@ -1883,6 +1883,42 @@
 }
 
 /*
+ * Ensure topology masks are sane, i.e. there are no conflicts (overlaps) for
+ * any two given CPUs at this (non-NUMA) topology level.
+ */
+static bool topology_span_sane(struct sched_domain_topology_level *tl,
+			      const struct cpumask *cpu_map, int cpu)
+{
+	int i;
+
+	/* NUMA levels are allowed to overlap */
+	if (tl->flags & SDTL_OVERLAP)
+		return true;
+
+	/*
+	 * Non-NUMA levels cannot partially overlap - they must be either
+	 * completely equal or completely disjoint. Otherwise we can end up
+	 * breaking the sched_group lists - i.e. a later get_group() pass
+	 * breaks the linking done for an earlier span.
+	 */
+	for_each_cpu(i, cpu_map) {
+		if (i == cpu)
+			continue;
+		/*
+		 * We should 'and' all those masks with 'cpu_map' to exactly
+		 * match the topology we're about to build, but that can only
+		 * remove CPUs, which only lessens our ability to detect
+		 * overlaps
+		 */
+		if (!cpumask_equal(tl->mask(cpu), tl->mask(i)) &&
+		    cpumask_intersects(tl->mask(cpu), tl->mask(i)))
+			return false;
+	}
+
+	return true;
+}
+
+/*
  * Find the sched_domain_topology_level where all CPU capacities are visible
  * for all CPUs.
  */
@@ -1978,6 +2014,9 @@
 				has_asym = true;
 			}
 
+			if (WARN_ON(!topology_span_sane(tl, cpu_map, i)))
+				goto error;
+
 			sd = build_sched_domain(tl, cpu_map, attr, sd, dflags, i);
 
 			if (tl == sched_domain_topology)
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index c1e566a..84bd051 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -232,17 +232,22 @@
 }
 EXPORT_SYMBOL(prepare_to_wait);
 
-void
+/* Returns true if we are the first waiter in the queue, false otherwise. */
+bool
 prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state)
 {
 	unsigned long flags;
+	bool was_empty = false;
 
 	wq_entry->flags |= WQ_FLAG_EXCLUSIVE;
 	spin_lock_irqsave(&wq_head->lock, flags);
-	if (list_empty(&wq_entry->entry))
+	if (list_empty(&wq_entry->entry)) {
+		was_empty = list_empty(&wq_head->head);
 		__add_wait_queue_entry_tail(wq_head, wq_entry);
+	}
 	set_current_state(state);
 	spin_unlock_irqrestore(&wq_head->lock, flags);
+	return was_empty;
 }
 EXPORT_SYMBOL(prepare_to_wait_exclusive);