Merge branch 'sched/core' into core/mm

Pull the migrate disable mechanics which is a prerequisite for preemptible
kmap_local().

13 files changed, 1401 insertions, 388 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d2003a7d5ab5..c962922784d1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -97,7 +97,7 @@ int sysctl_sched_rt_runtime = 950000;
  *
  * 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
+ * always looks at the local rq data structures to find the most eligible task
  * to run next.
  *
  * Task enqueue is also under rq->lock, possibly taken from another CPU.
@@ -518,7 +518,7 @@ static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task)
 
 	/*
 	 * Atomically grab the task, if ->wake_q is !nil already it means
-	 * its already queued (either by us or someone else) and will get the
+	 * it's already queued (either by us or someone else) and will get the
 	 * wakeup due to that.
 	 *
 	 * In order to ensure that a pending wakeup will observe our pending
@@ -769,7 +769,7 @@ bool sched_can_stop_tick(struct rq *rq)
 		return false;
 
 	/*
-	 * If there are more than one RR tasks, we need the tick to effect the
+	 * If there are more than one RR tasks, we need the tick to affect the
 	 * actual RR behaviour.
 	 */
 	if (rq->rt.rr_nr_running) {
@@ -1187,14 +1187,14 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
 	 * accounting was performed at enqueue time and we can just return
 	 * here.
 	 *
-	 * Need to be careful of the following enqeueue/dequeue ordering
+	 * Need to be careful of the following enqueue/dequeue ordering
 	 * problem too
 	 *
 	 *	enqueue(taskA)
 	 *	// sched_uclamp_used gets enabled
 	 *	enqueue(taskB)
 	 *	dequeue(taskA)
-	 *	// Must not decrement bukcet->tasks here
+	 *	// Must not decrement bucket->tasks here
 	 *	dequeue(taskB)
 	 *
 	 * where we could end up with stale data in uc_se and
@@ -1413,17 +1413,24 @@ done:
 static int uclamp_validate(struct task_struct *p,
 			   const struct sched_attr *attr)
 {
-	unsigned int lower_bound = p->uclamp_req[UCLAMP_MIN].value;
-	unsigned int upper_bound = p->uclamp_req[UCLAMP_MAX].value;
+	int util_min = p->uclamp_req[UCLAMP_MIN].value;
+	int util_max = p->uclamp_req[UCLAMP_MAX].value;
 
-	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN)
-		lower_bound = attr->sched_util_min;
-	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX)
-		upper_bound = attr->sched_util_max;
+	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) {
+		util_min = attr->sched_util_min;
 
-	if (lower_bound > upper_bound)
-		return -EINVAL;
-	if (upper_bound > SCHED_CAPACITY_SCALE)
+		if (util_min + 1 > SCHED_CAPACITY_SCALE + 1)
+			return -EINVAL;
+	}
+
+	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) {
+		util_max = attr->sched_util_max;
+
+		if (util_max + 1 > SCHED_CAPACITY_SCALE + 1)
+			return -EINVAL;
+	}
+
+	if (util_min != -1 && util_max != -1 && util_min > util_max)
 		return -EINVAL;
 
 	/*
@@ -1438,20 +1445,41 @@ static int uclamp_validate(struct task_struct *p,
 	return 0;
 }
 
+static bool uclamp_reset(const struct sched_attr *attr,
+			 enum uclamp_id clamp_id,
+			 struct uclamp_se *uc_se)
+{
+	/* Reset on sched class change for a non user-defined clamp value. */
+	if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)) &&
+	    !uc_se->user_defined)
+		return true;
+
+	/* Reset on sched_util_{min,max} == -1. */
+	if (clamp_id == UCLAMP_MIN &&
+	    attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN &&
+	    attr->sched_util_min == -1) {
+		return true;
+	}
+
+	if (clamp_id == UCLAMP_MAX &&
+	    attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX &&
+	    attr->sched_util_max == -1) {
+		return true;
+	}
+
+	return false;
+}
+
 static void __setscheduler_uclamp(struct task_struct *p,
 				  const struct sched_attr *attr)
 {
 	enum uclamp_id clamp_id;
 
-	/*
-	 * On scheduling class change, reset to default clamps for tasks
-	 * without a task-specific value.
-	 */
 	for_each_clamp_id(clamp_id) {
 		struct uclamp_se *uc_se = &p->uclamp_req[clamp_id];
+		unsigned int value;
 
-		/* Keep using defined clamps across class changes */
-		if (uc_se->user_defined)
+		if (!uclamp_reset(attr, clamp_id, uc_se))
 			continue;
 
 		/*
@@ -1459,21 +1487,25 @@ static void __setscheduler_uclamp(struct task_struct *p,
 		 * at runtime.
 		 */
 		if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN))
-			__uclamp_update_util_min_rt_default(p);
+			value = sysctl_sched_uclamp_util_min_rt_default;
 		else
-			uclamp_se_set(uc_se, uclamp_none(clamp_id), false);
+			value = uclamp_none(clamp_id);
+
+		uclamp_se_set(uc_se, value, false);
 
 	}
 
 	if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)))
 		return;
 
-	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) {
+	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN &&
+	    attr->sched_util_min != -1) {
 		uclamp_se_set(&p->uclamp_req[UCLAMP_MIN],
 			      attr->sched_util_min, true);
 	}
 
-	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) {
+	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX &&
+	    attr->sched_util_max != -1) {
 		uclamp_se_set(&p->uclamp_req[UCLAMP_MAX],
 			      attr->sched_util_max, true);
 	}
@@ -1696,6 +1728,76 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 
 #ifdef CONFIG_SMP
 
+static void
+__do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32 flags);
+
+static int __set_cpus_allowed_ptr(struct task_struct *p,
+				  const struct cpumask *new_mask,
+				  u32 flags);
+
+static void migrate_disable_switch(struct rq *rq, struct task_struct *p)
+{
+	if (likely(!p->migration_disabled))
+		return;
+
+	if (p->cpus_ptr != &p->cpus_mask)
+		return;
+
+	/*
+	 * Violates locking rules! see comment in __do_set_cpus_allowed().
+	 */
+	__do_set_cpus_allowed(p, cpumask_of(rq->cpu), SCA_MIGRATE_DISABLE);
+}
+
+void migrate_disable(void)
+{
+	struct task_struct *p = current;
+
+	if (p->migration_disabled) {
+		p->migration_disabled++;
+		return;
+	}
+
+	preempt_disable();
+	this_rq()->nr_pinned++;
+	p->migration_disabled = 1;
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(migrate_disable);
+
+void migrate_enable(void)
+{
+	struct task_struct *p = current;
+
+	if (p->migration_disabled > 1) {
+		p->migration_disabled--;
+		return;
+	}
+
+	/*
+	 * Ensure stop_task runs either before or after this, and that
+	 * __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule().
+	 */
+	preempt_disable();
+	if (p->cpus_ptr != &p->cpus_mask)
+		__set_cpus_allowed_ptr(p, &p->cpus_mask, SCA_MIGRATE_ENABLE);
+	/*
+	 * Mustn't clear migration_disabled() until cpus_ptr points back at the
+	 * regular cpus_mask, otherwise things that race (eg.
+	 * select_fallback_rq) get confused.
+	 */
+	barrier();
+	p->migration_disabled = 0;
+	this_rq()->nr_pinned--;
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(migrate_enable);
+
+static inline bool rq_has_pinned_tasks(struct rq *rq)
+{
+	return rq->nr_pinned;
+}
+
 /*
  * Per-CPU kthreads are allowed to run on !active && online CPUs, see
  * __set_cpus_allowed_ptr() and select_fallback_rq().
@@ -1705,7 +1807,7 @@ static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
 	if (!cpumask_test_cpu(cpu, p->cpus_ptr))
 		return false;
 
-	if (is_per_cpu_kthread(p))
+	if (is_per_cpu_kthread(p) || is_migration_disabled(p))
 		return cpu_online(cpu);
 
 	return cpu_active(cpu);
@@ -1750,8 +1852,16 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
 }
 
 struct migration_arg {
-	struct task_struct *task;
-	int dest_cpu;
+	struct task_struct		*task;
+	int				dest_cpu;
+	struct set_affinity_pending	*pending;
+};
+
+struct set_affinity_pending {
+	refcount_t		refs;
+	struct completion	done;
+	struct cpu_stop_work	stop_work;
+	struct migration_arg	arg;
 };
 
 /*
@@ -1783,16 +1893,19 @@ static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf,
  */
 static int migration_cpu_stop(void *data)
 {
+	struct set_affinity_pending *pending;
 	struct migration_arg *arg = data;
 	struct task_struct *p = arg->task;
+	int dest_cpu = arg->dest_cpu;
 	struct rq *rq = this_rq();
+	bool complete = false;
 	struct rq_flags rf;
 
 	/*
 	 * The original target CPU might have gone down and we might
 	 * be on another CPU but it doesn't matter.
 	 */
-	local_irq_disable();
+	local_irq_save(rf.flags);
 	/*
 	 * We need to explicitly wake pending tasks before running
 	 * __migrate_task() such that we will not miss enforcing cpus_ptr
@@ -1802,21 +1915,137 @@ static int migration_cpu_stop(void *data)
 
 	raw_spin_lock(&p->pi_lock);
 	rq_lock(rq, &rf);
+
+	pending = p->migration_pending;
 	/*
 	 * If task_rq(p) != rq, it cannot be migrated here, because we're
 	 * holding rq->lock, if p->on_rq == 0 it cannot get enqueued because
 	 * we're holding p->pi_lock.
 	 */
 	if (task_rq(p) == rq) {
+		if (is_migration_disabled(p))
+			goto out;
+
+		if (pending) {
+			p->migration_pending = NULL;
+			complete = true;
+		}
+
+		/* migrate_enable() --  we must not race against SCA */
+		if (dest_cpu < 0) {
+			/*
+			 * When this was migrate_enable() but we no longer
+			 * have a @pending, a concurrent SCA 'fixed' things
+			 * and we should be valid again. Nothing to do.
+			 */
+			if (!pending) {
+				WARN_ON_ONCE(!cpumask_test_cpu(task_cpu(p), &p->cpus_mask));
+				goto out;
+			}
+
+			dest_cpu = cpumask_any_distribute(&p->cpus_mask);
+		}
+
 		if (task_on_rq_queued(p))
-			rq = __migrate_task(rq, &rf, p, arg->dest_cpu);
+			rq = __migrate_task(rq, &rf, p, dest_cpu);
 		else
-			p->wake_cpu = arg->dest_cpu;
+			p->wake_cpu = dest_cpu;
+
+	} else if (dest_cpu < 0 || pending) {
+		/*
+		 * This happens when we get migrated between migrate_enable()'s
+		 * preempt_enable() and scheduling the stopper task. At that
+		 * point we're a regular task again and not current anymore.
+		 *
+		 * A !PREEMPT kernel has a giant hole here, which makes it far
+		 * more likely.
+		 */
+
+		/*
+		 * The task moved before the stopper got to run. We're holding
+		 * ->pi_lock, so the allowed mask is stable - if it got
+		 * somewhere allowed, we're done.
+		 */
+		if (pending && cpumask_test_cpu(task_cpu(p), p->cpus_ptr)) {
+			p->migration_pending = NULL;
+			complete = true;
+			goto out;
+		}
+
+		/*
+		 * When this was migrate_enable() but we no longer have an
+		 * @pending, a concurrent SCA 'fixed' things and we should be
+		 * valid again. Nothing to do.
+		 */
+		if (!pending) {
+			WARN_ON_ONCE(!cpumask_test_cpu(task_cpu(p), &p->cpus_mask));
+			goto out;
+		}
+
+		/*
+		 * When migrate_enable() hits a rq mis-match we can't reliably
+		 * determine is_migration_disabled() and so have to chase after
+		 * it.
+		 */
+		task_rq_unlock(rq, p, &rf);
+		stop_one_cpu_nowait(task_cpu(p), migration_cpu_stop,
+				    &pending->arg, &pending->stop_work);
+		return 0;
 	}
-	rq_unlock(rq, &rf);
-	raw_spin_unlock(&p->pi_lock);
+out:
+	task_rq_unlock(rq, p, &rf);
+
+	if (complete)
+		complete_all(&pending->done);
+
+	/* For pending->{arg,stop_work} */
+	pending = arg->pending;
+	if (pending && refcount_dec_and_test(&pending->refs))
+		wake_up_var(&pending->refs);
 
-	local_irq_enable();
+	return 0;
+}
+
+int push_cpu_stop(void *arg)
+{
+	struct rq *lowest_rq = NULL, *rq = this_rq();
+	struct task_struct *p = arg;
+
+	raw_spin_lock_irq(&p->pi_lock);
+	raw_spin_lock(&rq->lock);
+
+	if (task_rq(p) != rq)
+		goto out_unlock;
+
+	if (is_migration_disabled(p)) {
+		p->migration_flags |= MDF_PUSH;
+		goto out_unlock;
+	}
+
+	p->migration_flags &= ~MDF_PUSH;
+
+	if (p->sched_class->find_lock_rq)
+		lowest_rq = p->sched_class->find_lock_rq(p, rq);
+
+	if (!lowest_rq)
+		goto out_unlock;
+
+	// XXX validate p is still the highest prio task
+	if (task_rq(p) == rq) {
+		deactivate_task(rq, p, 0);
+		set_task_cpu(p, lowest_rq->cpu);
+		activate_task(lowest_rq, p, 0);
+		resched_curr(lowest_rq);
+	}
+
+	double_unlock_balance(rq, lowest_rq);
+
+out_unlock:
+	rq->push_busy = false;
+	raw_spin_unlock(&rq->lock);
+	raw_spin_unlock_irq(&p->pi_lock);
+
+	put_task_struct(p);
 	return 0;
 }
 
@@ -1824,18 +2053,39 @@ static int migration_cpu_stop(void *data)
  * sched_class::set_cpus_allowed must do the below, but is not required to
  * actually call this function.
  */
-void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask)
+void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask, u32 flags)
 {
+	if (flags & (SCA_MIGRATE_ENABLE | SCA_MIGRATE_DISABLE)) {
+		p->cpus_ptr = new_mask;
+		return;
+	}
+
 	cpumask_copy(&p->cpus_mask, new_mask);
 	p->nr_cpus_allowed = cpumask_weight(new_mask);
 }
 
-void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
+static void
+__do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32 flags)
 {
 	struct rq *rq = task_rq(p);
 	bool queued, running;
 
-	lockdep_assert_held(&p->pi_lock);
+	/*
+	 * This here violates the locking rules for affinity, since we're only
+	 * supposed to change these variables while holding both rq->lock and
+	 * p->pi_lock.
+	 *
+	 * HOWEVER, it magically works, because ttwu() is the only code that
+	 * accesses these variables under p->pi_lock and only does so after
+	 * smp_cond_load_acquire(&p->on_cpu, !VAL), and we're in __schedule()
+	 * before finish_task().
+	 *
+	 * XXX do further audits, this smells like something putrid.
+	 */
+	if (flags & SCA_MIGRATE_DISABLE)
+		SCHED_WARN_ON(!p->on_cpu);
+	else
+		lockdep_assert_held(&p->pi_lock);
 
 	queued = task_on_rq_queued(p);
 	running = task_current(rq, p);
@@ -1851,7 +2101,7 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 	if (running)
 		put_prev_task(rq, p);
 
-	p->sched_class->set_cpus_allowed(p, new_mask);
+	p->sched_class->set_cpus_allowed(p, new_mask, flags);
 
 	if (queued)
 		enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
@@ -1859,6 +2109,208 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 		set_next_task(rq, p);
 }
 
+void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
+{
+	__do_set_cpus_allowed(p, new_mask, 0);
+}
+
+/*
+ * This function is wildly self concurrent; here be dragons.
+ *
+ *
+ * When given a valid mask, __set_cpus_allowed_ptr() must block until the
+ * designated task is enqueued on an allowed CPU. If that task is currently
+ * running, we have to kick it out using the CPU stopper.
+ *
+ * Migrate-Disable comes along and tramples all over our nice sandcastle.
+ * Consider:
+ *
+ *     Initial conditions: P0->cpus_mask = [0, 1]
+ *
+ *     P0@CPU0                  P1
+ *
+ *     migrate_disable();
+ *     <preempted>
+ *                              set_cpus_allowed_ptr(P0, [1]);
+ *
+ * P1 *cannot* return from this set_cpus_allowed_ptr() call until P0 executes
+ * its outermost migrate_enable() (i.e. it exits its Migrate-Disable region).
+ * This means we need the following scheme:
+ *
+ *     P0@CPU0                  P1
+ *
+ *     migrate_disable();
+ *     <preempted>
+ *                              set_cpus_allowed_ptr(P0, [1]);
+ *                                <blocks>
+ *     <resumes>
+ *     migrate_enable();
+ *       __set_cpus_allowed_ptr();
+ *       <wakes local stopper>
+ *                         `--> <woken on migration completion>
+ *
+ * Now the fun stuff: there may be several P1-like tasks, i.e. multiple
+ * concurrent set_cpus_allowed_ptr(P0, [*]) calls. CPU affinity changes of any
+ * task p are serialized by p->pi_lock, which we can leverage: the one that
+ * should come into effect at the end of the Migrate-Disable region is the last
+ * one. This means we only need to track a single cpumask (i.e. p->cpus_mask),
+ * but we still need to properly signal those waiting tasks at the appropriate
+ * moment.
+ *
+ * This is implemented using struct set_affinity_pending. The first
+ * __set_cpus_allowed_ptr() caller within a given Migrate-Disable region will
+ * setup an instance of that struct and install it on the targeted task_struct.
+ * Any and all further callers will reuse that instance. Those then wait for
+ * a completion signaled at the tail of the CPU stopper callback (1), triggered
+ * on the end of the Migrate-Disable region (i.e. outermost migrate_enable()).
+ *
+ *
+ * (1) In the cases covered above. There is one more where the completion is
+ * signaled within affine_move_task() itself: when a subsequent affinity request
+ * cancels the need for an active migration. Consider:
+ *
+ *     Initial conditions: P0->cpus_mask = [0, 1]
+ *
+ *     P0@CPU0            P1                             P2
+ *
+ *     migrate_disable();
+ *     <preempted>
+ *                        set_cpus_allowed_ptr(P0, [1]);
+ *                          <blocks>
+ *                                                       set_cpus_allowed_ptr(P0, [0, 1]);
+ *                                                         <signal completion>
+ *                          <awakes>
+ *
+ * Note that the above is safe vs a concurrent migrate_enable(), as any
+ * pending affinity completion is preceded by an uninstallation of
+ * p->migration_pending done with p->pi_lock held.
+ */
+static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flags *rf,
+			    int dest_cpu, unsigned int flags)
+{
+	struct set_affinity_pending my_pending = { }, *pending = NULL;
+	struct migration_arg arg = {
+		.task = p,
+		.dest_cpu = dest_cpu,
+	};
+	bool complete = false;
+
+	/* Can the task run on the task's current CPU? If so, we're done */
+	if (cpumask_test_cpu(task_cpu(p), &p->cpus_mask)) {
+		struct task_struct *push_task = NULL;
+
+		if ((flags & SCA_MIGRATE_ENABLE) &&
+		    (p->migration_flags & MDF_PUSH) && !rq->push_busy) {
+			rq->push_busy = true;
+			push_task = get_task_struct(p);
+		}
+
+		pending = p->migration_pending;
+		if (pending) {
+			refcount_inc(&pending->refs);
+			p->migration_pending = NULL;
+			complete = true;
+		}
+		task_rq_unlock(rq, p, rf);
+
+		if (push_task) {
+			stop_one_cpu_nowait(rq->cpu, push_cpu_stop,
+					    p, &rq->push_work);
+		}
+
+		if (complete)
+			goto do_complete;
+
+		return 0;
+	}
+
+	if (!(flags & SCA_MIGRATE_ENABLE)) {
+		/* serialized by p->pi_lock */
+		if (!p->migration_pending) {
+			/* Install the request */
+			refcount_set(&my_pending.refs, 1);
+			init_completion(&my_pending.done);
+			p->migration_pending = &my_pending;
+		} else {
+			pending = p->migration_pending;
+			refcount_inc(&pending->refs);
+		}
+	}
+	pending = p->migration_pending;
+	/*
+	 * - !MIGRATE_ENABLE:
+	 *   we'll have installed a pending if there wasn't one already.
+	 *
+	 * - MIGRATE_ENABLE:
+	 *   we're here because the current CPU isn't matching anymore,
+	 *   the only way that can happen is because of a concurrent
+	 *   set_cpus_allowed_ptr() call, which should then still be
+	 *   pending completion.
+	 *
+	 * Either way, we really should have a @pending here.
+	 */
+	if (WARN_ON_ONCE(!pending)) {
+		task_rq_unlock(rq, p, rf);
+		return -EINVAL;
+	}
+
+	if (flags & SCA_MIGRATE_ENABLE) {
+
+		refcount_inc(&pending->refs); /* pending->{arg,stop_work} */
+		p->migration_flags &= ~MDF_PUSH;
+		task_rq_unlock(rq, p, rf);
+
+		pending->arg = (struct migration_arg) {
+			.task = p,
+			.dest_cpu = -1,
+			.pending = pending,
+		};
+
+		stop_one_cpu_nowait(cpu_of(rq), migration_cpu_stop,
+				    &pending->arg, &pending->stop_work);
+
+		return 0;
+	}
+
+	if (task_running(rq, p) || p->state == TASK_WAKING) {
+		/*
+		 * Lessen races (and headaches) by delegating
+		 * is_migration_disabled(p) checks to the stopper, which will
+		 * run on the same CPU as said p.
+		 */
+		task_rq_unlock(rq, p, rf);
+		stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
+
+	} else {
+
+		if (!is_migration_disabled(p)) {
+			if (task_on_rq_queued(p))
+				rq = move_queued_task(rq, rf, p, dest_cpu);
+
+			p->migration_pending = NULL;
+			complete = true;
+		}
+		task_rq_unlock(rq, p, rf);
+
+do_complete:
+		if (complete)
+			complete_all(&pending->done);
+	}
+
+	wait_for_completion(&pending->done);
+
+	if (refcount_dec_and_test(&pending->refs))
+		wake_up_var(&pending->refs);
+
+	/*
+	 * Block the original owner of &pending until all subsequent callers
+	 * have seen the completion and decremented the refcount
+	 */
+	wait_var_event(&my_pending.refs, !refcount_read(&my_pending.refs));
+
+	return 0;
+}
+
 /*
  * Change a given task's CPU affinity. Migrate the thread to a
  * proper CPU and schedule it away if the CPU it's executing on
@@ -1869,7 +2321,8 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
  * call is not atomic; no spinlocks may be held.
  */
 static int __set_cpus_allowed_ptr(struct task_struct *p,
-				  const struct cpumask *new_mask, bool check)
+				  const struct cpumask *new_mask,
+				  u32 flags)
 {
 	const struct cpumask *cpu_valid_mask = cpu_active_mask;
 	unsigned int dest_cpu;
@@ -1880,9 +2333,14 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 	rq = task_rq_lock(p, &rf);
 	update_rq_clock(rq);
 
-	if (p->flags & PF_KTHREAD) {
+	if (p->flags & PF_KTHREAD || is_migration_disabled(p)) {
 		/*
-		 * Kernel threads are allowed on online && !active CPUs
+		 * Kernel threads are allowed on online && !active CPUs.
+		 *
+		 * Specifically, migration_disabled() tasks must not fail the
+		 * cpumask_any_and_distribute() pick below, esp. so on
+		 * SCA_MIGRATE_ENABLE, otherwise we'll not call
+		 * set_cpus_allowed_common() and actually reset p->cpus_ptr.
 		 */
 		cpu_valid_mask = cpu_online_mask;
 	}
@@ -1891,13 +2349,22 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 	 * Must re-check here, to close a race against __kthread_bind(),
 	 * sched_setaffinity() is not guaranteed to observe the flag.
 	 */
-	if (check && (p->flags & PF_NO_SETAFFINITY)) {
+	if ((flags & SCA_CHECK) && (p->flags & PF_NO_SETAFFINITY)) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	if (cpumask_equal(&p->cpus_mask, new_mask))
-		goto out;
+	if (!(flags & SCA_MIGRATE_ENABLE)) {
+		if (cpumask_equal(&p->cpus_mask, new_mask))
+			goto out;
+
+		if (WARN_ON_ONCE(p == current &&
+				 is_migration_disabled(p) &&
+				 !cpumask_test_cpu(task_cpu(p), new_mask))) {
+			ret = -EBUSY;
+			goto out;
+		}
+	}
 
 	/*
 	 * Picking a ~random cpu helps in cases where we are changing affinity
@@ -1910,7 +2377,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 		goto out;
 	}
 
-	do_set_cpus_allowed(p, new_mask);
+	__do_set_cpus_allowed(p, new_mask, flags);
 
 	if (p->flags & PF_KTHREAD) {
 		/*
@@ -1922,23 +2389,8 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 			p->nr_cpus_allowed != 1);
 	}
 
-	/* Can the task run on the task's current CPU? If so, we're done */
-	if (cpumask_test_cpu(task_cpu(p), new_mask))
-		goto out;
+	return affine_move_task(rq, p, &rf, dest_cpu, flags);
 
-	if (task_running(rq, p) || p->state == TASK_WAKING) {
-		struct migration_arg arg = { p, dest_cpu };
-		/* Need help from migration thread: drop lock and wait. */
-		task_rq_unlock(rq, p, &rf);
-		stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
-		return 0;
-	} else if (task_on_rq_queued(p)) {
-		/*
-		 * OK, since we're going to drop the lock immediately
-		 * afterwards anyway.
-		 */
-		rq = move_queued_task(rq, &rf, p, dest_cpu);
-	}
 out:
 	task_rq_unlock(rq, p, &rf);
 
@@ -1947,7 +2399,7 @@ out:
 
 int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 {
-	return __set_cpus_allowed_ptr(p, new_mask, false);
+	return __set_cpus_allowed_ptr(p, new_mask, 0);
 }
 EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
 
@@ -1988,6 +2440,8 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	 * Clearly, migrating tasks to offline CPUs is a fairly daft thing.
 	 */
 	WARN_ON_ONCE(!cpu_online(new_cpu));
+
+	WARN_ON_ONCE(is_migration_disabled(p));
 #endif
 
 	trace_sched_migrate_task(p, new_cpu);
@@ -2318,6 +2772,12 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 			}
 			fallthrough;
 		case possible:
+			/*
+			 * XXX When called from select_task_rq() we only
+			 * hold p->pi_lock and again violate locking order.
+			 *
+			 * More yuck to audit.
+			 */
 			do_set_cpus_allowed(p, cpu_possible_mask);
 			state = fail;
 			break;
@@ -2348,12 +2808,12 @@ out:
  * The caller (fork, wakeup) owns p->pi_lock, ->cpus_ptr is stable.
  */
 static inline
-int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
+int select_task_rq(struct task_struct *p, int cpu, int wake_flags)
 {
 	lockdep_assert_held(&p->pi_lock);
 
-	if (p->nr_cpus_allowed > 1)
-		cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags);
+	if (p->nr_cpus_allowed > 1 && !is_migration_disabled(p))
+		cpu = p->sched_class->select_task_rq(p, cpu, wake_flags);
 	else
 		cpu = cpumask_any(p->cpus_ptr);
 
@@ -2375,6 +2835,7 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
 
 void sched_set_stop_task(int cpu, struct task_struct *stop)
 {
+	static struct lock_class_key stop_pi_lock;
 	struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
 	struct task_struct *old_stop = cpu_rq(cpu)->stop;
 
@@ -2390,6 +2851,20 @@ void sched_set_stop_task(int cpu, struct task_struct *stop)
 		sched_setscheduler_nocheck(stop, SCHED_FIFO, &param);
 
 		stop->sched_class = &stop_sched_class;
+
+		/*
+		 * The PI code calls rt_mutex_setprio() with ->pi_lock held to
+		 * adjust the effective priority of a task. As a result,
+		 * rt_mutex_setprio() can trigger (RT) balancing operations,
+		 * which can then trigger wakeups of the stop thread to push
+		 * around the current task.
+		 *
+		 * The stop task itself will never be part of the PI-chain, it
+		 * never blocks, therefore that ->pi_lock recursion is safe.
+		 * Tell lockdep about this by placing the stop->pi_lock in its
+		 * own class.
+		 */
+		lockdep_set_class(&stop->pi_lock, &stop_pi_lock);
 	}
 
 	cpu_rq(cpu)->stop = stop;
@@ -2403,15 +2878,23 @@ void sched_set_stop_task(int cpu, struct task_struct *stop)
 	}
 }
 
-#else
+#else /* CONFIG_SMP */
 
 static inline int __set_cpus_allowed_ptr(struct task_struct *p,
-					 const struct cpumask *new_mask, bool check)
+					 const struct cpumask *new_mask,
+					 u32 flags)
 {
 	return set_cpus_allowed_ptr(p, new_mask);
 }
 
-#endif /* CONFIG_SMP */
+static inline void migrate_disable_switch(struct rq *rq, struct task_struct *p) { }
+
+static inline bool rq_has_pinned_tasks(struct rq *rq)
+{
+	return false;
+}
+
+#endif /* !CONFIG_SMP */
 
 static void
 ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
@@ -2465,7 +2948,7 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_woken) {
 		/*
-		 * Our task @p is fully woken up and running; so its safe to
+		 * Our task @p is fully woken up and running; so it's safe to
 		 * drop the rq->lock, hereafter rq is only used for statistics.
 		 */
 		rq_unpin_lock(rq, rf);
@@ -2952,7 +3435,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 
 	/*
 	 * If the owning (remote) CPU is still in the middle of schedule() with
-	 * this task as prev, wait until its done referencing the task.
+	 * this task as prev, wait until it's done referencing the task.
 	 *
 	 * Pairs with the smp_store_release() in finish_task().
 	 *
@@ -2961,7 +3444,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 */
 	smp_cond_load_acquire(&p->on_cpu, !VAL);
 
-	cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
+	cpu = select_task_rq(p, p->wake_cpu, wake_flags | WF_TTWU);
 	if (task_cpu(p) != cpu) {
 		wake_flags |= WF_MIGRATED;
 		psi_ttwu_dequeue(p);
@@ -3098,6 +3581,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	init_numa_balancing(clone_flags, p);
 #ifdef CONFIG_SMP
 	p->wake_entry.u_flags = CSD_TYPE_TTWU;
+	p->migration_pending = NULL;
 #endif
 }
 
@@ -3344,7 +3828,7 @@ void wake_up_new_task(struct task_struct *p)
 	 */
 	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));
+	__set_task_cpu(p, select_task_rq(p, task_cpu(p), WF_FORK));
 #endif
 	rq = __task_rq_lock(p, &rf);
 	update_rq_clock(rq);
@@ -3356,7 +3840,7 @@ void wake_up_new_task(struct task_struct *p)
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_woken) {
 		/*
-		 * Nothing relies on rq->lock after this, so its fine to
+		 * Nothing relies on rq->lock after this, so it's fine to
 		 * drop it.
 		 */
 		rq_unpin_lock(rq, &rf);
@@ -3485,6 +3969,90 @@ static inline void finish_task(struct task_struct *prev)
 #endif
 }
 
+#ifdef CONFIG_SMP
+
+static void do_balance_callbacks(struct rq *rq, struct callback_head *head)
+{
+	void (*func)(struct rq *rq);
+	struct callback_head *next;
+
+	lockdep_assert_held(&rq->lock);
+
+	while (head) {
+		func = (void (*)(struct rq *))head->func;
+		next = head->next;
+		head->next = NULL;
+		head = next;
+
+		func(rq);
+	}
+}
+
+static inline struct callback_head *splice_balance_callbacks(struct rq *rq)
+{
+	struct callback_head *head = rq->balance_callback;
+
+	lockdep_assert_held(&rq->lock);
+	if (head) {
+		rq->balance_callback = NULL;
+		rq->balance_flags &= ~BALANCE_WORK;
+	}
+
+	return head;
+}
+
+static void __balance_callbacks(struct rq *rq)
+{
+	do_balance_callbacks(rq, splice_balance_callbacks(rq));
+}
+
+static inline void balance_callbacks(struct rq *rq, struct callback_head *head)
+{
+	unsigned long flags;
+
+	if (unlikely(head)) {
+		raw_spin_lock_irqsave(&rq->lock, flags);
+		do_balance_callbacks(rq, head);
+		raw_spin_unlock_irqrestore(&rq->lock, flags);
+	}
+}
+
+static void balance_push(struct rq *rq);
+
+static inline void balance_switch(struct rq *rq)
+{
+	if (likely(!rq->balance_flags))
+		return;
+
+	if (rq->balance_flags & BALANCE_PUSH) {
+		balance_push(rq);
+		return;
+	}
+
+	__balance_callbacks(rq);
+}
+
+#else
+
+static inline void __balance_callbacks(struct rq *rq)
+{
+}
+
+static inline struct callback_head *splice_balance_callbacks(struct rq *rq)
+{
+	return NULL;
+}
+
+static inline void balance_callbacks(struct rq *rq, struct callback_head *head)
+{
+}
+
+static inline void balance_switch(struct rq *rq)
+{
+}
+
+#endif
+
 static inline void
 prepare_lock_switch(struct rq *rq, struct task_struct *next, struct rq_flags *rf)
 {
@@ -3510,6 +4078,7 @@ static inline void finish_lock_switch(struct rq *rq)
 	 * prev into current:
 	 */
 	spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
+	balance_switch(rq);
 	raw_spin_unlock_irq(&rq->lock);
 }
 
@@ -3651,43 +4220,6 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	return rq;
 }
 
-#ifdef CONFIG_SMP
-
-/* rq->lock is NOT held, but preemption is disabled */
-static void __balance_callback(struct rq *rq)
-{
-	struct callback_head *head, *next;
-	void (*func)(struct rq *rq);
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&rq->lock, flags);
-	head = rq->balance_callback;
-	rq->balance_callback = NULL;
-	while (head) {
-		func = (void (*)(struct rq *))head->func;
-		next = head->next;
-		head->next = NULL;
-		head = next;
-
-		func(rq);
-	}
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
-}
-
-static inline void balance_callback(struct rq *rq)
-{
-	if (unlikely(rq->balance_callback))
-		__balance_callback(rq);
-}
-
-#else
-
-static inline void balance_callback(struct rq *rq)
-{
-}
-
-#endif
-
 /**
  * schedule_tail - first thing a freshly forked thread must call.
  * @prev: the thread we just switched away from.
@@ -3707,7 +4239,6 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
 	 */
 
 	rq = finish_task_switch(prev);
-	balance_callback(rq);
 	preempt_enable();
 
 	if (current->set_child_tid)
@@ -3836,7 +4367,7 @@ unsigned long nr_iowait_cpu(int cpu)
 }
 
 /*
- * IO-wait accounting, and how its mostly bollocks (on SMP).
+ * IO-wait accounting, and how it's mostly bollocks (on SMP).
  *
  * The idea behind IO-wait account is to account the idle time that we could
  * have spend running if it were not for IO. That is, if we were to improve the
@@ -3888,7 +4419,7 @@ void sched_exec(void)
 	int dest_cpu;
 
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
-	dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), SD_BALANCE_EXEC, 0);
+	dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), WF_EXEC);
 	if (dest_cpu == smp_processor_id())
 		goto unlock;
 
@@ -4331,7 +4862,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	/*
 	 * Optimization: we know that if all tasks are in the fair class we can
 	 * call that function directly, but only if the @prev task wasn't of a
-	 * higher scheduling class, because otherwise those loose the
+	 * higher scheduling class, because otherwise those lose the
 	 * opportunity to pull in more work from other CPUs.
 	 */
 	if (likely(prev->sched_class <= &fair_sched_class &&
@@ -4515,6 +5046,7 @@ static void __sched notrace __schedule(bool preempt)
 		 */
 		++*switch_count;
 
+		migrate_disable_switch(rq, prev);
 		psi_sched_switch(prev, next, !task_on_rq_queued(prev));
 
 		trace_sched_switch(preempt, prev, next);
@@ -4523,10 +5055,11 @@ static void __sched notrace __schedule(bool preempt)
 		rq = context_switch(rq, prev, next, &rf);
 	} else {
 		rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
-		rq_unlock_irq(rq, &rf);
-	}
 
-	balance_callback(rq);
+		rq_unpin_lock(rq, &rf);
+		__balance_callbacks(rq);
+		raw_spin_unlock_irq(&rq->lock);
+	}
 }
 
 void __noreturn do_task_dead(void)
@@ -4852,7 +5385,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 	 * right. rt_mutex_slowunlock()+rt_mutex_postunlock() work together to
 	 * ensure a task is de-boosted (pi_task is set to NULL) before the
 	 * task is allowed to run again (and can exit). This ensures the pointer
-	 * points to a blocked task -- which guaratees the task is present.
+	 * points to a blocked task -- which guarantees the task is present.
 	 */
 	p->pi_top_task = pi_task;
 
@@ -4937,9 +5470,11 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 out_unlock:
 	/* Avoid rq from going away on us: */
 	preempt_disable();
-	__task_rq_unlock(rq, &rf);
 
-	balance_callback(rq);
+	rq_unpin_lock(rq, &rf);
+	__balance_callbacks(rq);
+	raw_spin_unlock(&rq->lock);
+
 	preempt_enable();
 }
 #else
@@ -4968,7 +5503,7 @@ void set_user_nice(struct task_struct *p, long nice)
 	/*
 	 * The RT priorities are set via sched_setscheduler(), but we still
 	 * allow the 'normal' nice value to be set - but as expected
-	 * it wont have any effect on scheduling until the task is
+	 * it won't have any effect on scheduling until the task is
 	 * SCHED_DEADLINE, SCHED_FIFO or SCHED_RR:
 	 */
 	if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
@@ -5213,6 +5748,7 @@ static int __sched_setscheduler(struct task_struct *p,
 	int retval, oldprio, oldpolicy = -1, queued, running;
 	int new_effective_prio, policy = attr->sched_policy;
 	const struct sched_class *prev_class;
+	struct callback_head *head;
 	struct rq_flags rf;
 	int reset_on_fork;
 	int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
@@ -5451,6 +5987,7 @@ change:
 
 	/* Avoid rq from going away on us: */
 	preempt_disable();
+	head = splice_balance_callbacks(rq);
 	task_rq_unlock(rq, p, &rf);
 
 	if (pi) {
@@ -5459,7 +5996,7 @@ change:
 	}
 
 	/* Run balance callbacks after we've adjusted the PI chain: */
-	balance_callback(rq);
+	balance_callbacks(rq, head);
 	preempt_enable();
 
 	return 0;
@@ -5954,7 +6491,7 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	}
 #endif
 again:
-	retval = __set_cpus_allowed_ptr(p, new_mask, true);
+	retval = __set_cpus_allowed_ptr(p, new_mask, SCA_CHECK);
 
 	if (!retval) {
 		cpuset_cpus_allowed(p, cpus_allowed);
@@ -6094,12 +6631,8 @@ static void do_sched_yield(void)
 	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();
@@ -6159,7 +6692,7 @@ EXPORT_SYMBOL(__cond_resched_lock);
  *
  * The scheduler is at all times free to pick the calling task as the most
  * eligible task to run, if removing the yield() call from your code breaks
- * it, its already broken.
+ * it, it's already broken.
  *
  * Typical broken usage is:
  *
@@ -6447,6 +6980,7 @@ void sched_show_task(struct task_struct *p)
 		(unsigned long)task_thread_info(p)->flags);
 
 	print_worker_info(KERN_INFO, p);
+	print_stop_info(KERN_INFO, p);
 	show_stack(p, NULL, KERN_INFO);
 	put_task_stack(p);
 }
@@ -6532,12 +7066,12 @@ void init_idle(struct task_struct *idle, int cpu)
 
 #ifdef CONFIG_SMP
 	/*
-	 * Its possible that init_idle() gets called multiple times on a task,
+	 * It's possible that init_idle() gets called multiple times on a task,
 	 * in that case do_set_cpus_allowed() will not do the right thing.
 	 *
 	 * And since this is boot we can forgo the serialization.
 	 */
-	set_cpus_allowed_common(idle, cpumask_of(cpu));
+	set_cpus_allowed_common(idle, cpumask_of(cpu), 0);
 #endif
 	/*
 	 * We're having a chicken and egg problem, even though we are
@@ -6688,119 +7222,126 @@ void idle_task_exit(void)
 	/* finish_cpu(), as ran on the BP, will clean up the active_mm state */
 }
 
-/*
- * Since this CPU is going 'away' for a while, fold any nr_active delta
- * we might have. Assumes we're called after migrate_tasks() so that the
- * nr_active count is stable. We need to take the teardown thread which
- * is calling this into account, so we hand in adjust = 1 to the load
- * calculation.
- *
- * Also see the comment "Global load-average calculations".
- */
-static void calc_load_migrate(struct rq *rq)
+static int __balance_push_cpu_stop(void *arg)
 {
-	long delta = calc_load_fold_active(rq, 1);
-	if (delta)
-		atomic_long_add(delta, &calc_load_tasks);
-}
+	struct task_struct *p = arg;
+	struct rq *rq = this_rq();
+	struct rq_flags rf;
+	int cpu;
 
-static struct task_struct *__pick_migrate_task(struct rq *rq)
-{
-	const struct sched_class *class;
-	struct task_struct *next;
+	raw_spin_lock_irq(&p->pi_lock);
+	rq_lock(rq, &rf);
 
-	for_each_class(class) {
-		next = class->pick_next_task(rq);
-		if (next) {
-			next->sched_class->put_prev_task(rq, next);
-			return next;
-		}
+	update_rq_clock(rq);
+
+	if (task_rq(p) == rq && task_on_rq_queued(p)) {
+		cpu = select_fallback_rq(rq->cpu, p);
+		rq = __migrate_task(rq, &rf, p, cpu);
 	}
 
-	/* The idle class should always have a runnable task */
-	BUG();
+	rq_unlock(rq, &rf);
+	raw_spin_unlock_irq(&p->pi_lock);
+
+	put_task_struct(p);
+
+	return 0;
 }
 
+static DEFINE_PER_CPU(struct cpu_stop_work, push_work);
+
 /*
- * Migrate all tasks from the rq, sleeping tasks will be migrated by
- * try_to_wake_up()->select_task_rq().
- *
- * Called with rq->lock held even though we'er in stop_machine() and
- * there's no concurrency possible, we hold the required locks anyway
- * because of lock validation efforts.
+ * Ensure we only run per-cpu kthreads once the CPU goes !active.
  */
-static void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf)
+static void balance_push(struct rq *rq)
 {
-	struct rq *rq = dead_rq;
-	struct task_struct *next, *stop = rq->stop;
-	struct rq_flags orf = *rf;
-	int dest_cpu;
+	struct task_struct *push_task = rq->curr;
+
+	lockdep_assert_held(&rq->lock);
+	SCHED_WARN_ON(rq->cpu != smp_processor_id());
 
 	/*
-	 * Fudge the rq selection such that the below task selection loop
-	 * doesn't get stuck on the currently eligible stop task.
-	 *
-	 * We're currently inside stop_machine() and the rq is either stuck
-	 * in the stop_machine_cpu_stop() loop, or we're executing this code,
-	 * either way we should never end up calling schedule() until we're
-	 * done here.
+	 * Both the cpu-hotplug and stop task are in this case and are
+	 * required to complete the hotplug process.
 	 */
-	rq->stop = NULL;
+	if (is_per_cpu_kthread(push_task) || is_migration_disabled(push_task)) {
+		/*
+		 * If this is the idle task on the outgoing CPU try to wake
+		 * up the hotplug control thread which might wait for the
+		 * last task to vanish. The rcuwait_active() check is
+		 * accurate here because the waiter is pinned on this CPU
+		 * and can't obviously be running in parallel.
+		 *
+		 * On RT kernels this also has to check whether there are
+		 * pinned and scheduled out tasks on the runqueue. They
+		 * need to leave the migrate disabled section first.
+		 */
+		if (!rq->nr_running && !rq_has_pinned_tasks(rq) &&
+		    rcuwait_active(&rq->hotplug_wait)) {
+			raw_spin_unlock(&rq->lock);
+			rcuwait_wake_up(&rq->hotplug_wait);
+			raw_spin_lock(&rq->lock);
+		}
+		return;
+	}
 
+	get_task_struct(push_task);
 	/*
-	 * put_prev_task() and pick_next_task() sched
-	 * class method both need to have an up-to-date
-	 * value of rq->clock[_task]
+	 * Temporarily drop rq->lock such that we can wake-up the stop task.
+	 * Both preemption and IRQs are still disabled.
 	 */
-	update_rq_clock(rq);
+	raw_spin_unlock(&rq->lock);
+	stop_one_cpu_nowait(rq->cpu, __balance_push_cpu_stop, push_task,
+			    this_cpu_ptr(&push_work));
+	/*
+	 * At this point need_resched() is true and we'll take the loop in
+	 * schedule(). The next pick is obviously going to be the stop task
+	 * which is_per_cpu_kthread() and will push this task away.
+	 */
+	raw_spin_lock(&rq->lock);
+}
 
-	for (;;) {
-		/*
-		 * There's this thread running, bail when that's the only
-		 * remaining thread:
-		 */
-		if (rq->nr_running == 1)
-			break;
+static void balance_push_set(int cpu, bool on)
+{
+	struct rq *rq = cpu_rq(cpu);
+	struct rq_flags rf;
 
-		next = __pick_migrate_task(rq);
+	rq_lock_irqsave(rq, &rf);
+	if (on)
+		rq->balance_flags |= BALANCE_PUSH;
+	else
+		rq->balance_flags &= ~BALANCE_PUSH;
+	rq_unlock_irqrestore(rq, &rf);
+}
 
-		/*
-		 * Rules for changing task_struct::cpus_mask are holding
-		 * both pi_lock and rq->lock, such that holding either
-		 * stabilizes the mask.
-		 *
-		 * Drop rq->lock is not quite as disastrous as it usually is
-		 * because !cpu_active at this point, which means load-balance
-		 * will not interfere. Also, stop-machine.
-		 */
-		rq_unlock(rq, rf);
-		raw_spin_lock(&next->pi_lock);
-		rq_relock(rq, rf);
+/*
+ * Invoked from a CPUs hotplug control thread after the CPU has been marked
+ * inactive. All tasks which are not per CPU kernel threads are either
+ * pushed off this CPU now via balance_push() or placed on a different CPU
+ * during wakeup. Wait until the CPU is quiescent.
+ */
+static void balance_hotplug_wait(void)
+{
+	struct rq *rq = this_rq();
 
-		/*
-		 * Since we're inside stop-machine, _nothing_ should have
-		 * changed the task, WARN if weird stuff happened, because in
-		 * that case the above rq->lock drop is a fail too.
-		 */
-		if (WARN_ON(task_rq(next) != rq || !task_on_rq_queued(next))) {
-			raw_spin_unlock(&next->pi_lock);
-			continue;
-		}
+	rcuwait_wait_event(&rq->hotplug_wait,
+			   rq->nr_running == 1 && !rq_has_pinned_tasks(rq),
+			   TASK_UNINTERRUPTIBLE);
+}
 
-		/* Find suitable destination for @next, with force if needed. */
-		dest_cpu = select_fallback_rq(dead_rq->cpu, next);
-		rq = __migrate_task(rq, rf, next, dest_cpu);
-		if (rq != dead_rq) {
-			rq_unlock(rq, rf);
-			rq = dead_rq;
-			*rf = orf;
-			rq_relock(rq, rf);
-		}
-		raw_spin_unlock(&next->pi_lock);
-	}
+#else
 
-	rq->stop = stop;
+static inline void balance_push(struct rq *rq)
+{
 }
+
+static inline void balance_push_set(int cpu, bool on)
+{
+}
+
+static inline void balance_hotplug_wait(void)
+{
+}
+
 #endif /* CONFIG_HOTPLUG_CPU */
 
 void set_rq_online(struct rq *rq)
@@ -6886,6 +7427,8 @@ int sched_cpu_activate(unsigned int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	struct rq_flags rf;
 
+	balance_push_set(cpu, false);
+
 #ifdef CONFIG_SCHED_SMT
 	/*
 	 * When going up, increment the number of cores with SMT present.
@@ -6921,6 +7464,8 @@ int sched_cpu_activate(unsigned int cpu)
 
 int sched_cpu_deactivate(unsigned int cpu)
 {
+	struct rq *rq = cpu_rq(cpu);
+	struct rq_flags rf;
 	int ret;
 
 	set_cpu_active(cpu, false);
@@ -6933,6 +7478,16 @@ int sched_cpu_deactivate(unsigned int cpu)
 	 */
 	synchronize_rcu();
 
+	balance_push_set(cpu, true);
+
+	rq_lock_irqsave(rq, &rf);
+	if (rq->rd) {
+		update_rq_clock(rq);
+		BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
+		set_rq_offline(rq);
+	}
+	rq_unlock_irqrestore(rq, &rf);
+
 #ifdef CONFIG_SCHED_SMT
 	/*
 	 * When going down, decrement the number of cores with SMT present.
@@ -6946,6 +7501,7 @@ int sched_cpu_deactivate(unsigned int cpu)
 
 	ret = cpuset_cpu_inactive(cpu);
 	if (ret) {
+		balance_push_set(cpu, false);
 		set_cpu_active(cpu, true);
 		return ret;
 	}
@@ -6969,6 +7525,41 @@ int sched_cpu_starting(unsigned int cpu)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Invoked immediately before the stopper thread is invoked to bring the
+ * CPU down completely. At this point all per CPU kthreads except the
+ * hotplug thread (current) and the stopper thread (inactive) have been
+ * either parked or have been unbound from the outgoing CPU. Ensure that
+ * any of those which might be on the way out are gone.
+ *
+ * If after this point a bound task is being woken on this CPU then the
+ * responsible hotplug callback has failed to do it's job.
+ * sched_cpu_dying() will catch it with the appropriate fireworks.
+ */
+int sched_cpu_wait_empty(unsigned int cpu)
+{
+	balance_hotplug_wait();
+	return 0;
+}
+
+/*
+ * Since this CPU is going 'away' for a while, fold any nr_active delta we
+ * might have. Called from the CPU stopper task after ensuring that the
+ * stopper is the last running task on the CPU, so nr_active count is
+ * stable. We need to take the teardown thread which is calling this into
+ * account, so we hand in adjust = 1 to the load calculation.
+ *
+ * Also see the comment "Global load-average calculations".
+ */
+static void calc_load_migrate(struct rq *rq)
+{
+	long delta = calc_load_fold_active(rq, 1);
+
+	if (delta)
+		atomic_long_add(delta, &calc_load_tasks);
+}
+
 int sched_cpu_dying(unsigned int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
@@ -6978,12 +7569,7 @@ int sched_cpu_dying(unsigned int cpu)
 	sched_tick_stop(cpu);
 
 	rq_lock_irqsave(rq, &rf);
-	if (rq->rd) {
-		BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
-		set_rq_offline(rq);
-	}
-	migrate_tasks(rq, &rf);
-	BUG_ON(rq->nr_running != 1);
+	BUG_ON(rq->nr_running != 1 || rq_has_pinned_tasks(rq));
 	rq_unlock_irqrestore(rq, &rf);
 
 	calc_load_migrate(rq);
@@ -7190,6 +7776,9 @@ void __init sched_init(void)
 
 		rq_csd_init(rq, &rq->nohz_csd, nohz_csd_func);
 #endif
+#ifdef CONFIG_HOTPLUG_CPU
+		rcuwait_init(&rq->hotplug_wait);
+#endif
 #endif /* CONFIG_SMP */
 		hrtick_rq_init(rq);
 		atomic_set(&rq->nr_iowait, 0);
@@ -7327,6 +7916,39 @@ void __cant_sleep(const char *file, int line, int preempt_offset)
 	add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
 }
 EXPORT_SYMBOL_GPL(__cant_sleep);
+
+#ifdef CONFIG_SMP
+void __cant_migrate(const char *file, int line)
+{
+	static unsigned long prev_jiffy;
+
+	if (irqs_disabled())
+		return;
+
+	if (is_migration_disabled(current))
+		return;
+
+	if (!IS_ENABLED(CONFIG_PREEMPT_COUNT))
+		return;
+
+	if (preempt_count() > 0)
+		return;
+
+	if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
+		return;
+	prev_jiffy = jiffies;
+
+	pr_err("BUG: assuming non migratable context at %s:%d\n", file, line);
+	pr_err("in_atomic(): %d, irqs_disabled(): %d, migration_disabled() %u pid: %d, name: %s\n",
+	       in_atomic(), irqs_disabled(), is_migration_disabled(current),
+	       current->pid, current->comm);
+
+	debug_show_held_locks(current);
+	dump_stack();
+	add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
+}
+EXPORT_SYMBOL_GPL(__cant_migrate);
+#endif
 #endif
 
 #ifdef CONFIG_MAGIC_SYSRQ
@@ -7660,7 +8282,7 @@ static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
 			return -EINVAL;
 #endif
 		/*
-		 * Serialize against wake_up_new_task() such that if its
+		 * Serialize against wake_up_new_task() such that if it's
 		 * running, we're sure to observe its full state.
 		 */
 		raw_spin_lock_irq(&task->pi_lock);
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 8cb06c8c7eb1..ceb03d76c0cc 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -120,7 +120,7 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
 	const struct sched_dl_entity *dl_se = &p->dl;
 
 	if (later_mask &&
-	    cpumask_and(later_mask, cp->free_cpus, p->cpus_ptr)) {
+	    cpumask_and(later_mask, cp->free_cpus, &p->cpus_mask)) {
 		unsigned long cap, max_cap = 0;
 		int cpu, max_cpu = -1;
 
@@ -151,7 +151,7 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
 
 		WARN_ON(best_cpu != -1 && !cpu_present(best_cpu));
 
-		if (cpumask_test_cpu(best_cpu, p->cpus_ptr) &&
+		if (cpumask_test_cpu(best_cpu, &p->cpus_mask) &&
 		    dl_time_before(dl_se->deadline, cp->elements[0].dl)) {
 			if (later_mask)
 				cpumask_set_cpu(best_cpu, later_mask);
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index c03a5775d019..8a5f5cf8521a 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -901,16 +901,9 @@ struct cpufreq_governor *cpufreq_default_governor(void)
 cpufreq_governor_init(schedutil_gov);
 
 #ifdef CONFIG_ENERGY_MODEL
-extern bool sched_energy_update;
-extern struct mutex sched_energy_mutex;
-
 static void rebuild_sd_workfn(struct work_struct *work)
 {
-	mutex_lock(&sched_energy_mutex);
-	sched_energy_update = true;
-	rebuild_sched_domains();
-	sched_energy_update = false;
-	mutex_unlock(&sched_energy_mutex);
+	rebuild_sched_domains_energy();
 }
 static DECLARE_WORK(rebuild_sd_work, rebuild_sd_workfn);
 
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index 0033731a0797..ec9be789c7e2 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -11,7 +11,7 @@
  *  This code tracks the priority of each CPU so that global migration
  *  decisions are easy to calculate.  Each CPU can be in a state as follows:
  *
- *                 (INVALID), IDLE, NORMAL, RT1, ... RT99
+ *                 (INVALID), NORMAL, RT1, ... RT99, HIGHER
  *
  *  going from the lowest priority to the highest.  CPUs in the INVALID state
  *  are not eligible for routing.  The system maintains this state with
@@ -19,24 +19,48 @@
  *  in that class).  Therefore a typical application without affinity
  *  restrictions can find a suitable CPU with O(1) complexity (e.g. two bit
  *  searches).  For tasks with affinity restrictions, the algorithm has a
- *  worst case complexity of O(min(102, nr_domcpus)), though the scenario that
+ *  worst case complexity of O(min(101, nr_domcpus)), though the scenario that
  *  yields the worst case search is fairly contrived.
  */
 #include "sched.h"
 
-/* Convert between a 140 based task->prio, and our 102 based cpupri */
+/*
+ * p->rt_priority   p->prio   newpri   cpupri
+ *
+ *				  -1       -1 (CPUPRI_INVALID)
+ *
+ *				  99        0 (CPUPRI_NORMAL)
+ *
+ *		1        98       98        1
+ *	      ...
+ *	       49        50       50       49
+ *	       50        49       49       50
+ *	      ...
+ *	       99         0        0       99
+ *
+ *				 100	  100 (CPUPRI_HIGHER)
+ */
 static int convert_prio(int prio)
 {
 	int cpupri;
 
-	if (prio == CPUPRI_INVALID)
-		cpupri = CPUPRI_INVALID;
-	else if (prio == MAX_PRIO)
-		cpupri = CPUPRI_IDLE;
-	else if (prio >= MAX_RT_PRIO)
-		cpupri = CPUPRI_NORMAL;
-	else
-		cpupri = MAX_RT_PRIO - prio + 1;
+	switch (prio) {
+	case CPUPRI_INVALID:
+		cpupri = CPUPRI_INVALID;	/* -1 */
+		break;
+
+	case 0 ... 98:
+		cpupri = MAX_RT_PRIO-1 - prio;	/* 1 ... 99 */
+		break;
+
+	case MAX_RT_PRIO-1:
+		cpupri = CPUPRI_NORMAL;		/*  0 */
+		break;
+
+	case MAX_RT_PRIO:
+		cpupri = CPUPRI_HIGHER;		/* 100 */
+		break;
+	}
 
 	return cpupri;
 }
@@ -73,11 +97,11 @@ static inline int __cpupri_find(struct cpupri *cp, struct task_struct *p,
 	if (skip)
 		return 0;
 
-	if (cpumask_any_and(p->cpus_ptr, vec->mask) >= nr_cpu_ids)
+	if (cpumask_any_and(&p->cpus_mask, vec->mask) >= nr_cpu_ids)
 		return 0;
 
 	if (lowest_mask) {
-		cpumask_and(lowest_mask, p->cpus_ptr, vec->mask);
+		cpumask_and(lowest_mask, &p->cpus_mask, vec->mask);
 
 		/*
 		 * We have to ensure that we have at least one bit
@@ -177,7 +201,7 @@ int cpupri_find_fitness(struct cpupri *cp, struct task_struct *p,
  * cpupri_set - update the CPU priority setting
  * @cp: The cpupri context
  * @cpu: The target CPU
- * @newpri: The priority (INVALID-RT99) to assign to this CPU
+ * @newpri: The priority (INVALID,NORMAL,RT1-RT99,HIGHER) to assign to this CPU
  *
  * Note: Assumes cpu_rq(cpu)->lock is locked
  *
diff --git a/kernel/sched/cpupri.h b/kernel/sched/cpupri.h
index efbb492bb94c..d6cba0020064 100644
--- a/kernel/sched/cpupri.h
+++ b/kernel/sched/cpupri.h
@@ -1,11 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 
-#define CPUPRI_NR_PRIORITIES	(MAX_RT_PRIO + 2)
+#define CPUPRI_NR_PRIORITIES	(MAX_RT_PRIO+1)
 
 #define CPUPRI_INVALID		-1
-#define CPUPRI_IDLE		 0
-#define CPUPRI_NORMAL		 1
-/* values 2-101 are RT priorities 0-99 */
+#define CPUPRI_NORMAL		 0
+/* values 1-99 are for RT1-RT99 priorities */
+#define CPUPRI_HIGHER		100
 
 struct cpupri_vec {
 	atomic_t		count;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index f232305dcefe..2a5836f440e0 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -97,6 +97,17 @@ static inline unsigned long dl_bw_capacity(int i)
 		return __dl_bw_capacity(i);
 	}
 }
+
+static inline bool dl_bw_visited(int cpu, u64 gen)
+{
+	struct root_domain *rd = cpu_rq(cpu)->rd;
+
+	if (rd->visit_gen == gen)
+		return true;
+
+	rd->visit_gen = gen;
+	return false;
+}
 #else
 static inline struct dl_bw *dl_bw_of(int i)
 {
@@ -112,6 +123,11 @@ static inline unsigned long dl_bw_capacity(int i)
 {
 	return SCHED_CAPACITY_SCALE;
 }
+
+static inline bool dl_bw_visited(int cpu, u64 gen)
+{
+	return false;
+}
 #endif
 
 static inline
@@ -543,7 +559,7 @@ static int push_dl_task(struct rq *rq);
 
 static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev)
 {
-	return dl_task(prev);
+	return rq->online && dl_task(prev);
 }
 
 static DEFINE_PER_CPU(struct callback_head, dl_push_head);
@@ -1378,6 +1394,8 @@ static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
 
 	if (dl_rq->earliest_dl.curr == 0 ||
 	    dl_time_before(deadline, dl_rq->earliest_dl.curr)) {
+		if (dl_rq->earliest_dl.curr == 0)
+			cpupri_set(&rq->rd->cpupri, rq->cpu, CPUPRI_HIGHER);
 		dl_rq->earliest_dl.curr = deadline;
 		cpudl_set(&rq->rd->cpudl, rq->cpu, deadline);
 	}
@@ -1395,6 +1413,7 @@ static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
 		dl_rq->earliest_dl.curr = 0;
 		dl_rq->earliest_dl.next = 0;
 		cpudl_clear(&rq->rd->cpudl, rq->cpu);
+		cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio.curr);
 	} else {
 		struct rb_node *leftmost = dl_rq->root.rb_leftmost;
 		struct sched_dl_entity *entry;
@@ -1664,13 +1683,13 @@ static void yield_task_dl(struct rq *rq)
 static int find_later_rq(struct task_struct *task);
 
 static int
-select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
+select_task_rq_dl(struct task_struct *p, int cpu, int flags)
 {
 	struct task_struct *curr;
 	bool select_rq;
 	struct rq *rq;
 
-	if (sd_flag != SD_BALANCE_WAKE)
+	if (!(flags & WF_TTWU))
 		goto out;
 
 	rq = cpu_rq(cpu);
@@ -1912,7 +1931,7 @@ static void task_fork_dl(struct task_struct *p)
 static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
 {
 	if (!task_running(rq, p) &&
-	    cpumask_test_cpu(cpu, p->cpus_ptr))
+	    cpumask_test_cpu(cpu, &p->cpus_mask))
 		return 1;
 	return 0;
 }
@@ -2002,8 +2021,8 @@ static int find_later_rq(struct task_struct *task)
 				return this_cpu;
 			}
 
-			best_cpu = cpumask_first_and(later_mask,
-							sched_domain_span(sd));
+			best_cpu = cpumask_any_and_distribute(later_mask,
+							      sched_domain_span(sd));
 			/*
 			 * Last chance: if a CPU being in both later_mask
 			 * and current sd span is valid, that becomes our
@@ -2025,7 +2044,7 @@ static int find_later_rq(struct task_struct *task)
 	if (this_cpu != -1)
 		return this_cpu;
 
-	cpu = cpumask_any(later_mask);
+	cpu = cpumask_any_distribute(later_mask);
 	if (cpu < nr_cpu_ids)
 		return cpu;
 
@@ -2062,7 +2081,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
 		/* Retry if something changed. */
 		if (double_lock_balance(rq, later_rq)) {
 			if (unlikely(task_rq(task) != rq ||
-				     !cpumask_test_cpu(later_rq->cpu, task->cpus_ptr) ||
+				     !cpumask_test_cpu(later_rq->cpu, &task->cpus_mask) ||
 				     task_running(rq, task) ||
 				     !dl_task(task) ||
 				     !task_on_rq_queued(task))) {
@@ -2129,6 +2148,9 @@ static int push_dl_task(struct rq *rq)
 		return 0;
 
 retry:
+	if (is_migration_disabled(next_task))
+		return 0;
+
 	if (WARN_ON(next_task == rq->curr))
 		return 0;
 
@@ -2206,7 +2228,7 @@ static void push_dl_tasks(struct rq *rq)
 static void pull_dl_task(struct rq *this_rq)
 {
 	int this_cpu = this_rq->cpu, cpu;
-	struct task_struct *p;
+	struct task_struct *p, *push_task;
 	bool resched = false;
 	struct rq *src_rq;
 	u64 dmin = LONG_MAX;
@@ -2236,6 +2258,7 @@ static void pull_dl_task(struct rq *this_rq)
 			continue;
 
 		/* Might drop this_rq->lock */
+		push_task = NULL;
 		double_lock_balance(this_rq, src_rq);
 
 		/*
@@ -2267,17 +2290,27 @@ static void pull_dl_task(struct rq *this_rq)
 					   src_rq->curr->dl.deadline))
 				goto skip;
 
-			resched = true;
-
-			deactivate_task(src_rq, p, 0);
-			set_task_cpu(p, this_cpu);
-			activate_task(this_rq, p, 0);
-			dmin = p->dl.deadline;
+			if (is_migration_disabled(p)) {
+				push_task = get_push_task(src_rq);
+			} else {
+				deactivate_task(src_rq, p, 0);
+				set_task_cpu(p, this_cpu);
+				activate_task(this_rq, p, 0);
+				dmin = p->dl.deadline;
+				resched = true;
+			}
 
 			/* Is there any other task even earlier? */
 		}
 skip:
 		double_unlock_balance(this_rq, src_rq);
+
+		if (push_task) {
+			raw_spin_unlock(&this_rq->lock);
+			stop_one_cpu_nowait(src_rq->cpu, push_cpu_stop,
+					    push_task, &src_rq->push_work);
+			raw_spin_lock(&this_rq->lock);
+		}
 	}
 
 	if (resched)
@@ -2301,7 +2334,8 @@ static void task_woken_dl(struct rq *rq, struct task_struct *p)
 }
 
 static void set_cpus_allowed_dl(struct task_struct *p,
-				const struct cpumask *new_mask)
+				const struct cpumask *new_mask,
+				u32 flags)
 {
 	struct root_domain *src_rd;
 	struct rq *rq;
@@ -2330,7 +2364,7 @@ static void set_cpus_allowed_dl(struct task_struct *p,
 		raw_spin_unlock(&src_dl_b->lock);
 	}
 
-	set_cpus_allowed_common(p, new_mask);
+	set_cpus_allowed_common(p, new_mask, flags);
 }
 
 /* Assumes rq->lock is held */
@@ -2503,8 +2537,8 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p,
 	}
 }
 
-const struct sched_class dl_sched_class
-	__section("__dl_sched_class") = {
+DEFINE_SCHED_CLASS(dl) = {
+
 	.enqueue_task		= enqueue_task_dl,
 	.dequeue_task		= dequeue_task_dl,
 	.yield_task		= yield_task_dl,
@@ -2523,6 +2557,7 @@ const struct sched_class dl_sched_class
 	.rq_online              = rq_online_dl,
 	.rq_offline             = rq_offline_dl,
 	.task_woken		= task_woken_dl,
+	.find_lock_rq		= find_lock_later_rq,
 #endif
 
 	.task_tick		= task_tick_dl,
@@ -2535,33 +2570,39 @@ const struct sched_class dl_sched_class
 	.update_curr		= update_curr_dl,
 };
 
+/* Used for dl_bw check and update, used under sched_rt_handler()::mutex */
+static u64 dl_generation;
+
 int sched_dl_global_validate(void)
 {
 	u64 runtime = global_rt_runtime();
 	u64 period = global_rt_period();
 	u64 new_bw = to_ratio(period, runtime);
+	u64 gen = ++dl_generation;
 	struct dl_bw *dl_b;
-	int cpu, ret = 0;
+	int cpu, cpus, ret = 0;
 	unsigned long flags;
 
 	/*
 	 * Here we want to check the bandwidth not being set to some
 	 * value smaller than the currently allocated bandwidth in
 	 * any of the root_domains.
-	 *
-	 * FIXME: Cycling on all the CPUs is overdoing, but simpler than
-	 * cycling on root_domains... Discussion on different/better
-	 * solutions is welcome!
 	 */
 	for_each_possible_cpu(cpu) {
 		rcu_read_lock_sched();
+
+		if (dl_bw_visited(cpu, gen))
+			goto next;
+
 		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);
 
+next:
 		rcu_read_unlock_sched();
 
 		if (ret)
@@ -2587,6 +2628,7 @@ static void init_dl_rq_bw_ratio(struct dl_rq *dl_rq)
 void sched_dl_do_global(void)
 {
 	u64 new_bw = -1;
+	u64 gen = ++dl_generation;
 	struct dl_bw *dl_b;
 	int cpu;
 	unsigned long flags;
@@ -2597,11 +2639,14 @@ void sched_dl_do_global(void)
 	if (global_rt_runtime() != RUNTIME_INF)
 		new_bw = to_ratio(global_rt_period(), global_rt_runtime());
 
-	/*
-	 * FIXME: As above...
-	 */
 	for_each_possible_cpu(cpu) {
 		rcu_read_lock_sched();
+
+		if (dl_bw_visited(cpu, gen)) {
+			rcu_read_unlock_sched();
+			continue;
+		}
+
 		dl_b = dl_bw_of(cpu);
 
 		raw_spin_lock_irqsave(&dl_b->lock, flags);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 290f9e38378c..6691e28fa3da 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -906,6 +906,15 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	if (!schedstat_enabled())
 		return;
 
+	/*
+	 * When the sched_schedstat changes from 0 to 1, some sched se
+	 * maybe already in the runqueue, the se->statistics.wait_start
+	 * will be 0.So it will let the delta wrong. We need to avoid this
+	 * scenario.
+	 */
+	if (unlikely(!schedstat_val(se->statistics.wait_start)))
+		return;
+
 	delta = rq_clock(rq_of(cfs_rq)) - schedstat_val(se->statistics.wait_start);
 
 	if (entity_is_task(se)) {
@@ -4779,25 +4788,37 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 		struct cfs_rq *qcfs_rq = cfs_rq_of(se);
 		/* throttled entity or throttle-on-deactivate */
 		if (!se->on_rq)
-			break;
+			goto done;
 
-		if (dequeue) {
-			dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP);
-		} else {
-			update_load_avg(qcfs_rq, se, 0);
-			se_update_runnable(se);
-		}
+		dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP);
 
 		qcfs_rq->h_nr_running -= task_delta;
 		qcfs_rq->idle_h_nr_running -= idle_task_delta;
 
-		if (qcfs_rq->load.weight)
-			dequeue = 0;
+		if (qcfs_rq->load.weight) {
+			/* Avoid re-evaluating load for this entity: */
+			se = parent_entity(se);
+			break;
+		}
 	}
 
-	if (!se)
-		sub_nr_running(rq, task_delta);
+	for_each_sched_entity(se) {
+		struct cfs_rq *qcfs_rq = cfs_rq_of(se);
+		/* throttled entity or throttle-on-deactivate */
+		if (!se->on_rq)
+			goto done;
+
+		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;
+	}
+
+	/* At this point se is NULL and we are at root level*/
+	sub_nr_running(rq, task_delta);
+
+done:
 	/*
 	 * Note: distribution will already see us throttled via the
 	 * throttled-list.  rq->lock protects completion.
@@ -5105,9 +5126,6 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 		return;
 
 	distribute_cfs_runtime(cfs_b);
-
-	raw_spin_lock_irqsave(&cfs_b->lock, flags);
-	raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
 }
 
 /*
@@ -5804,6 +5822,9 @@ wake_affine_idle(int this_cpu, int prev_cpu, int sync)
 	if (sync && cpu_rq(this_cpu)->nr_running == 1)
 		return this_cpu;
 
+	if (available_idle_cpu(prev_cpu))
+		return prev_cpu;
+
 	return nr_cpumask_bits;
 }
 
@@ -6663,7 +6684,7 @@ fail:
 
 /*
  * select_task_rq_fair: Select target runqueue for the waking task in domains
- * that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
+ * that have the relevant SD flag set. In practice, this is SD_BALANCE_WAKE,
  * SD_BALANCE_FORK, or SD_BALANCE_EXEC.
  *
  * Balances load by selecting the idlest CPU in the idlest group, or under
@@ -6674,15 +6695,17 @@ fail:
  * preempt must be disabled.
  */
 static int
-select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags)
+select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags)
 {
+	int sync = (wake_flags & WF_SYNC) && !(current->flags & PF_EXITING);
 	struct sched_domain *tmp, *sd = NULL;
 	int cpu = smp_processor_id();
 	int new_cpu = prev_cpu;
 	int want_affine = 0;
-	int sync = (wake_flags & WF_SYNC) && !(current->flags & PF_EXITING);
+	/* SD_flags and WF_flags share the first nibble */
+	int sd_flag = wake_flags & 0xF;
 
-	if (sd_flag & SD_BALANCE_WAKE) {
+	if (wake_flags & WF_TTWU) {
 		record_wakee(p);
 
 		if (sched_energy_enabled()) {
@@ -6719,9 +6742,8 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 	if (unlikely(sd)) {
 		/* Slow path */
 		new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag);
-	} else if (sd_flag & SD_BALANCE_WAKE) { /* XXX always ? */
+	} else if (wake_flags & WF_TTWU) { /* XXX always ? */
 		/* Fast path */
-
 		new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
 
 		if (want_affine)
@@ -10047,6 +10069,10 @@ static inline int find_new_ilb(void)
 
 	for_each_cpu_and(ilb, nohz.idle_cpus_mask,
 			      housekeeping_cpumask(HK_FLAG_MISC)) {
+
+		if (ilb == smp_processor_id())
+			continue;
+
 		if (idle_cpu(ilb))
 			return ilb;
 	}
@@ -11158,8 +11184,8 @@ static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task
 /*
  * All the scheduling class methods:
  */
-const struct sched_class fair_sched_class
-	__section("__fair_sched_class") = {
+DEFINE_SCHED_CLASS(fair) = {
+
 	.enqueue_task		= enqueue_task_fair,
 	.dequeue_task		= dequeue_task_fair,
 	.yield_task		= yield_task_fair,
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 24d0ee26377d..df91b198a74c 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -338,6 +338,7 @@ void play_idle_precise(u64 duration_ns, u64 latency_ns)
 	WARN_ON_ONCE(!(current->flags & PF_KTHREAD));
 	WARN_ON_ONCE(!(current->flags & PF_NO_SETAFFINITY));
 	WARN_ON_ONCE(!duration_ns);
+	WARN_ON_ONCE(current->mm);
 
 	rcu_sleep_check();
 	preempt_disable();
@@ -375,7 +376,7 @@ void cpu_startup_entry(enum cpuhp_state state)
 
 #ifdef CONFIG_SMP
 static int
-select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags)
+select_task_rq_idle(struct task_struct *p, int cpu, int flags)
 {
 	return task_cpu(p); /* IDLE tasks as never migrated */
 }
@@ -457,8 +458,8 @@ static void update_curr_idle(struct rq *rq)
 /*
  * Simple, special scheduling class for the per-CPU idle tasks:
  */
-const struct sched_class idle_sched_class
-	__section("__idle_sched_class") = {
+DEFINE_SCHED_CLASS(idle) = {
+
 	/* no enqueue/yield_task for idle tasks */
 
 	/* dequeue is not valid, we print a debug message there: */
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index e23e74d52db5..5a40b3828ff2 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -7,6 +7,134 @@
 #include "sched.h"
 
 /*
+ * For documentation purposes, here are some membarrier ordering
+ * scenarios to keep in mind:
+ *
+ * A) Userspace thread execution after IPI vs membarrier's memory
+ *    barrier before sending the IPI
+ *
+ * Userspace variables:
+ *
+ * int x = 0, y = 0;
+ *
+ * The memory barrier at the start of membarrier() on CPU0 is necessary in
+ * order to enforce the guarantee that any writes occurring on CPU0 before
+ * the membarrier() is executed will be visible to any code executing on
+ * CPU1 after the IPI-induced memory barrier:
+ *
+ *         CPU0                              CPU1
+ *
+ *         x = 1
+ *         membarrier():
+ *           a: smp_mb()
+ *           b: send IPI                       IPI-induced mb
+ *           c: smp_mb()
+ *         r2 = y
+ *                                           y = 1
+ *                                           barrier()
+ *                                           r1 = x
+ *
+ *                     BUG_ON(r1 == 0 && r2 == 0)
+ *
+ * The write to y and load from x by CPU1 are unordered by the hardware,
+ * so it's possible to have "r1 = x" reordered before "y = 1" at any
+ * point after (b).  If the memory barrier at (a) is omitted, then "x = 1"
+ * can be reordered after (a) (although not after (c)), so we get r1 == 0
+ * and r2 == 0.  This violates the guarantee that membarrier() is
+ * supposed by provide.
+ *
+ * The timing of the memory barrier at (a) has to ensure that it executes
+ * before the IPI-induced memory barrier on CPU1.
+ *
+ * B) Userspace thread execution before IPI vs membarrier's memory
+ *    barrier after completing the IPI
+ *
+ * Userspace variables:
+ *
+ * int x = 0, y = 0;
+ *
+ * The memory barrier at the end of membarrier() on CPU0 is necessary in
+ * order to enforce the guarantee that any writes occurring on CPU1 before
+ * the membarrier() is executed will be visible to any code executing on
+ * CPU0 after the membarrier():
+ *
+ *         CPU0                              CPU1
+ *
+ *                                           x = 1
+ *                                           barrier()
+ *                                           y = 1
+ *         r2 = y
+ *         membarrier():
+ *           a: smp_mb()
+ *           b: send IPI                       IPI-induced mb
+ *           c: smp_mb()
+ *         r1 = x
+ *         BUG_ON(r1 == 0 && r2 == 1)
+ *
+ * The writes to x and y are unordered by the hardware, so it's possible to
+ * have "r2 = 1" even though the write to x doesn't execute until (b).  If
+ * the memory barrier at (c) is omitted then "r1 = x" can be reordered
+ * before (b) (although not before (a)), so we get "r1 = 0".  This violates
+ * the guarantee that membarrier() is supposed to provide.
+ *
+ * The timing of the memory barrier at (c) has to ensure that it executes
+ * after the IPI-induced memory barrier on CPU1.
+ *
+ * C) Scheduling userspace thread -> kthread -> userspace thread vs membarrier
+ *
+ *           CPU0                            CPU1
+ *
+ *           membarrier():
+ *           a: smp_mb()
+ *                                           d: switch to kthread (includes mb)
+ *           b: read rq->curr->mm == NULL
+ *                                           e: switch to user (includes mb)
+ *           c: smp_mb()
+ *
+ * Using the scenario from (A), we can show that (a) needs to be paired
+ * with (e). Using the scenario from (B), we can show that (c) needs to
+ * be paired with (d).
+ *
+ * D) exit_mm vs membarrier
+ *
+ * Two thread groups are created, A and B.  Thread group B is created by
+ * issuing clone from group A with flag CLONE_VM set, but not CLONE_THREAD.
+ * Let's assume we have a single thread within each thread group (Thread A
+ * and Thread B).  Thread A runs on CPU0, Thread B runs on CPU1.
+ *
+ *           CPU0                            CPU1
+ *
+ *           membarrier():
+ *             a: smp_mb()
+ *                                           exit_mm():
+ *                                             d: smp_mb()
+ *                                             e: current->mm = NULL
+ *             b: read rq->curr->mm == NULL
+ *             c: smp_mb()
+ *
+ * Using scenario (B), we can show that (c) needs to be paired with (d).
+ *
+ * E) kthread_{use,unuse}_mm vs membarrier
+ *
+ *           CPU0                            CPU1
+ *
+ *           membarrier():
+ *           a: smp_mb()
+ *                                           kthread_unuse_mm()
+ *                                             d: smp_mb()
+ *                                             e: current->mm = NULL
+ *           b: read rq->curr->mm == NULL
+ *                                           kthread_use_mm()
+ *                                             f: current->mm = mm
+ *                                             g: smp_mb()
+ *           c: smp_mb()
+ *
+ * Using the scenario from (A), we can show that (a) needs to be paired
+ * with (g). Using the scenario from (B), we can show that (c) needs to
+ * be paired with (d).
+ */
+
+/*
  * Bitmask made from a "or" of all commands within enum membarrier_cmd,
  * except MEMBARRIER_CMD_QUERY.
  */
@@ -76,6 +204,18 @@ void membarrier_exec_mmap(struct mm_struct *mm)
 	this_cpu_write(runqueues.membarrier_state, 0);
 }
 
+void membarrier_update_current_mm(struct mm_struct *next_mm)
+{
+	struct rq *rq = this_rq();
+	int membarrier_state = 0;
+
+	if (next_mm)
+		membarrier_state = atomic_read(&next_mm->membarrier_state);
+	if (READ_ONCE(rq->membarrier_state) == membarrier_state)
+		return;
+	WRITE_ONCE(rq->membarrier_state, membarrier_state);
+}
+
 static int membarrier_global_expedited(void)
 {
 	int cpu;
@@ -114,12 +254,11 @@ static int membarrier_global_expedited(void)
 			continue;
 
 		/*
-		 * Skip the CPU if it runs a kernel thread. The scheduler
-		 * leaves the prior task mm in place as an optimization when
-		 * scheduling a kthread.
+		 * Skip the CPU if it runs a kernel thread which is not using
+		 * a task mm.
 		 */
 		p = rcu_dereference(cpu_rq(cpu)->curr);
-		if (p->flags & PF_KTHREAD)
+		if (!p->mm)
 			continue;
 
 		__cpumask_set_cpu(cpu, tmpmask);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 49ec096a8aa1..dbe4629cf7ba 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -89,8 +89,8 @@ void init_rt_rq(struct rt_rq *rt_rq)
 	__set_bit(MAX_RT_PRIO, array->bitmap);
 
 #if defined CONFIG_SMP
-	rt_rq->highest_prio.curr = MAX_RT_PRIO;
-	rt_rq->highest_prio.next = MAX_RT_PRIO;
+	rt_rq->highest_prio.curr = MAX_RT_PRIO-1;
+	rt_rq->highest_prio.next = MAX_RT_PRIO-1;
 	rt_rq->rt_nr_migratory = 0;
 	rt_rq->overloaded = 0;
 	plist_head_init(&rt_rq->pushable_tasks);
@@ -161,7 +161,7 @@ void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
 {
 	struct rq *rq = cpu_rq(cpu);
 
-	rt_rq->highest_prio.curr = MAX_RT_PRIO;
+	rt_rq->highest_prio.curr = MAX_RT_PRIO-1;
 	rt_rq->rt_nr_boosted = 0;
 	rt_rq->rq = rq;
 	rt_rq->tg = tg;
@@ -265,7 +265,7 @@ static void pull_rt_task(struct rq *this_rq);
 static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev)
 {
 	/* Try to pull RT tasks here if we lower this rq's prio */
-	return rq->rt.highest_prio.curr > prev->prio;
+	return rq->online && rq->rt.highest_prio.curr > prev->prio;
 }
 
 static inline int rt_overloaded(struct rq *rq)
@@ -393,8 +393,9 @@ static void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
 		p = plist_first_entry(&rq->rt.pushable_tasks,
 				      struct task_struct, pushable_tasks);
 		rq->rt.highest_prio.next = p->prio;
-	} else
-		rq->rt.highest_prio.next = MAX_RT_PRIO;
+	} else {
+		rq->rt.highest_prio.next = MAX_RT_PRIO-1;
+	}
 }
 
 #else
@@ -1147,8 +1148,9 @@ dec_rt_prio(struct rt_rq *rt_rq, int prio)
 				sched_find_first_bit(array->bitmap);
 		}
 
-	} else
-		rt_rq->highest_prio.curr = MAX_RT_PRIO;
+	} else {
+		rt_rq->highest_prio.curr = MAX_RT_PRIO-1;
+	}
 
 	dec_rt_prio_smp(rt_rq, prio, prev_prio);
 }
@@ -1428,14 +1430,14 @@ static void yield_task_rt(struct rq *rq)
 static int find_lowest_rq(struct task_struct *task);
 
 static int
-select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags)
+select_task_rq_rt(struct task_struct *p, int cpu, int flags)
 {
 	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)
+	if (!(flags & (WF_TTWU | WF_FORK)))
 		goto out;
 
 	rq = cpu_rq(cpu);
@@ -1658,7 +1660,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
 {
 	if (!task_running(rq, p) &&
-	    cpumask_test_cpu(cpu, p->cpus_ptr))
+	    cpumask_test_cpu(cpu, &p->cpus_mask))
 		return 1;
 
 	return 0;
@@ -1752,8 +1754,8 @@ static int find_lowest_rq(struct task_struct *task)
 				return this_cpu;
 			}
 
-			best_cpu = cpumask_first_and(lowest_mask,
-						     sched_domain_span(sd));
+			best_cpu = cpumask_any_and_distribute(lowest_mask,
+							      sched_domain_span(sd));
 			if (best_cpu < nr_cpu_ids) {
 				rcu_read_unlock();
 				return best_cpu;
@@ -1770,7 +1772,7 @@ static int find_lowest_rq(struct task_struct *task)
 	if (this_cpu != -1)
 		return this_cpu;
 
-	cpu = cpumask_any(lowest_mask);
+	cpu = cpumask_any_distribute(lowest_mask);
 	if (cpu < nr_cpu_ids)
 		return cpu;
 
@@ -1811,7 +1813,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 			 * Also make sure that it wasn't scheduled on its rq.
 			 */
 			if (unlikely(task_rq(task) != rq ||
-				     !cpumask_test_cpu(lowest_rq->cpu, task->cpus_ptr) ||
+				     !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_mask) ||
 				     task_running(rq, task) ||
 				     !rt_task(task) ||
 				     !task_on_rq_queued(task))) {
@@ -1859,7 +1861,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq)
  * running task can migrate over to a CPU that is running a task
  * of lesser priority.
  */
-static int push_rt_task(struct rq *rq)
+static int push_rt_task(struct rq *rq, bool pull)
 {
 	struct task_struct *next_task;
 	struct rq *lowest_rq;
@@ -1873,6 +1875,34 @@ static int push_rt_task(struct rq *rq)
 		return 0;
 
 retry:
+	if (is_migration_disabled(next_task)) {
+		struct task_struct *push_task = NULL;
+		int cpu;
+
+		if (!pull || rq->push_busy)
+			return 0;
+
+		cpu = find_lowest_rq(rq->curr);
+		if (cpu == -1 || cpu == rq->cpu)
+			return 0;
+
+		/*
+		 * Given we found a CPU with lower priority than @next_task,
+		 * therefore it should be running. However we cannot migrate it
+		 * to this other CPU, instead attempt to push the current
+		 * running task on this CPU away.
+		 */
+		push_task = get_push_task(rq);
+		if (push_task) {
+			raw_spin_unlock(&rq->lock);
+			stop_one_cpu_nowait(rq->cpu, push_cpu_stop,
+					    push_task, &rq->push_work);
+			raw_spin_lock(&rq->lock);
+		}
+
+		return 0;
+	}
+
 	if (WARN_ON(next_task == rq->curr))
 		return 0;
 
@@ -1927,12 +1957,10 @@ retry:
 	deactivate_task(rq, next_task, 0);
 	set_task_cpu(next_task, lowest_rq->cpu);
 	activate_task(lowest_rq, next_task, 0);
-	ret = 1;
-
 	resched_curr(lowest_rq);
+	ret = 1;
 
 	double_unlock_balance(rq, lowest_rq);
-
 out:
 	put_task_struct(next_task);
 
@@ -1942,7 +1970,7 @@ out:
 static void push_rt_tasks(struct rq *rq)
 {
 	/* push_rt_task will return true if it moved an RT */
-	while (push_rt_task(rq))
+	while (push_rt_task(rq, false))
 		;
 }
 
@@ -2095,7 +2123,8 @@ void rto_push_irq_work_func(struct irq_work *work)
 	 */
 	if (has_pushable_tasks(rq)) {
 		raw_spin_lock(&rq->lock);
-		push_rt_tasks(rq);
+		while (push_rt_task(rq, true))
+			;
 		raw_spin_unlock(&rq->lock);
 	}
 
@@ -2120,7 +2149,7 @@ static void pull_rt_task(struct rq *this_rq)
 {
 	int this_cpu = this_rq->cpu, cpu;
 	bool resched = false;
-	struct task_struct *p;
+	struct task_struct *p, *push_task;
 	struct rq *src_rq;
 	int rt_overload_count = rt_overloaded(this_rq);
 
@@ -2167,6 +2196,7 @@ static void pull_rt_task(struct rq *this_rq)
 		 * double_lock_balance, and another CPU could
 		 * alter this_rq
 		 */
+		push_task = NULL;
 		double_lock_balance(this_rq, src_rq);
 
 		/*
@@ -2194,11 +2224,14 @@ static void pull_rt_task(struct rq *this_rq)
 			if (p->prio < src_rq->curr->prio)
 				goto skip;
 
-			resched = true;
-
-			deactivate_task(src_rq, p, 0);
-			set_task_cpu(p, this_cpu);
-			activate_task(this_rq, p, 0);
+			if (is_migration_disabled(p)) {
+				push_task = get_push_task(src_rq);
+			} else {
+				deactivate_task(src_rq, p, 0);
+				set_task_cpu(p, this_cpu);
+				activate_task(this_rq, p, 0);
+				resched = true;
+			}
 			/*
 			 * We continue with the search, just in
 			 * case there's an even higher prio task
@@ -2208,6 +2241,13 @@ static void pull_rt_task(struct rq *this_rq)
 		}
 skip:
 		double_unlock_balance(this_rq, src_rq);
+
+		if (push_task) {
+			raw_spin_unlock(&this_rq->lock);
+			stop_one_cpu_nowait(src_rq->cpu, push_cpu_stop,
+					    push_task, &src_rq->push_work);
+			raw_spin_lock(&this_rq->lock);
+		}
 	}
 
 	if (resched)
@@ -2429,8 +2469,8 @@ static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
 		return 0;
 }
 
-const struct sched_class rt_sched_class
-	__section("__rt_sched_class") = {
+DEFINE_SCHED_CLASS(rt) = {
+
 	.enqueue_task		= enqueue_task_rt,
 	.dequeue_task		= dequeue_task_rt,
 	.yield_task		= yield_task_rt,
@@ -2449,6 +2489,7 @@ const struct sched_class rt_sched_class
 	.rq_offline             = rq_offline_rt,
 	.task_woken		= task_woken_rt,
 	.switched_from		= switched_from_rt,
+	.find_lock_rq		= find_lock_lowest_rq,
 #endif
 
 	.task_tick		= task_tick_rt,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index df80bfcea92e..f5acb6c5ce49 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -67,7 +67,6 @@
 #include <linux/tsacct_kern.h>
 
 #include <asm/tlb.h>
-#include <asm-generic/vmlinux.lds.h>
 
 #ifdef CONFIG_PARAVIRT
 # include <asm/paravirt.h>
@@ -257,30 +256,6 @@ struct rt_bandwidth {
 
 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;
@@ -292,6 +267,24 @@ static inline int dl_bandwidth_enabled(void)
 	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;
@@ -801,6 +794,15 @@ struct root_domain {
 	struct dl_bw		dl_bw;
 	struct cpudl		cpudl;
 
+	/*
+	 * Indicate whether a root_domain's dl_bw has been checked or
+	 * updated. It's monotonously increasing value.
+	 *
+	 * Also, some corner cases, like 'wrap around' is dangerous, but given
+	 * that u64 is 'big enough'. So that shouldn't be a concern.
+	 */
+	u64 visit_gen;
+
 #ifdef HAVE_RT_PUSH_IPI
 	/*
 	 * For IPI pull requests, loop across the rto_mask.
@@ -973,6 +975,7 @@ struct rq {
 	unsigned long		cpu_capacity_orig;
 
 	struct callback_head	*balance_callback;
+	unsigned char		balance_flags;
 
 	unsigned char		nohz_idle_balance;
 	unsigned char		idle_balance;
@@ -1003,6 +1006,10 @@ struct rq {
 
 	/* This is used to determine avg_idle's max value */
 	u64			max_idle_balance_cost;
+
+#ifdef CONFIG_HOTPLUG_CPU
+	struct rcuwait		hotplug_wait;
+#endif
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
@@ -1048,6 +1055,12 @@ struct rq {
 	/* Must be inspected within a rcu lock section */
 	struct cpuidle_state	*idle_state;
 #endif
+
+#ifdef CONFIG_SMP
+	unsigned int		nr_pinned;
+#endif
+	unsigned int		push_busy;
+	struct cpu_stop_work	push_work;
 };
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -1075,6 +1088,16 @@ static inline int cpu_of(struct rq *rq)
 #endif
 }
 
+#define MDF_PUSH	0x01
+
+static inline bool is_migration_disabled(struct task_struct *p)
+{
+#ifdef CONFIG_SMP
+	return p->migration_disabled;
+#else
+	return false;
+#endif
+}
 
 #ifdef CONFIG_SCHED_SMT
 extern void __update_idle_core(struct rq *rq);
@@ -1221,6 +1244,9 @@ static inline void rq_pin_lock(struct rq *rq, struct rq_flags *rf)
 	rq->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
 	rf->clock_update_flags = 0;
 #endif
+#ifdef CONFIG_SMP
+	SCHED_WARN_ON(rq->balance_callback);
+#endif
 }
 
 static inline void rq_unpin_lock(struct rq *rq, struct rq_flags *rf)
@@ -1382,6 +1408,9 @@ init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
 
 #ifdef CONFIG_SMP
 
+#define BALANCE_WORK	0x01
+#define BALANCE_PUSH	0x02
+
 static inline void
 queue_balance_callback(struct rq *rq,
 		       struct callback_head *head,
@@ -1389,12 +1418,13 @@ queue_balance_callback(struct rq *rq,
 {
 	lockdep_assert_held(&rq->lock);
 
-	if (unlikely(head->next))
+	if (unlikely(head->next || (rq->balance_flags & BALANCE_PUSH)))
 		return;
 
 	head->func = (void (*)(struct callback_head *))func;
 	head->next = rq->balance_callback;
 	rq->balance_callback = head;
+	rq->balance_flags |= BALANCE_WORK;
 }
 
 #define rcu_dereference_check_sched_domain(p) \
@@ -1714,13 +1744,20 @@ static inline int task_on_rq_migrating(struct task_struct *p)
 	return READ_ONCE(p->on_rq) == TASK_ON_RQ_MIGRATING;
 }
 
-/*
- * wake flags
- */
-#define WF_SYNC			0x01		/* Waker goes to sleep after wakeup */
-#define WF_FORK			0x02		/* Child wakeup after fork */
-#define WF_MIGRATED		0x04		/* Internal use, task got migrated */
-#define WF_ON_CPU		0x08		/* Wakee is on_cpu */
+/* Wake flags. The first three directly map to some SD flag value */
+#define WF_EXEC     0x02 /* Wakeup after exec; maps to SD_BALANCE_EXEC */
+#define WF_FORK     0x04 /* Wakeup after fork; maps to SD_BALANCE_FORK */
+#define WF_TTWU     0x08 /* Wakeup;            maps to SD_BALANCE_WAKE */
+
+#define WF_SYNC     0x10 /* Waker goes to sleep after wakeup */
+#define WF_MIGRATED 0x20 /* Internal use, task got migrated */
+#define WF_ON_CPU   0x40 /* Wakee is on_cpu */
+
+#ifdef CONFIG_SMP
+static_assert(WF_EXEC == SD_BALANCE_EXEC);
+static_assert(WF_FORK == SD_BALANCE_FORK);
+static_assert(WF_TTWU == SD_BALANCE_WAKE);
+#endif
 
 /*
  * To aid in avoiding the subversion of "niceness" due to uneven distribution
@@ -1796,16 +1833,19 @@ struct sched_class {
 
 #ifdef CONFIG_SMP
 	int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
-	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
+	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int flags);
 	void (*migrate_task_rq)(struct task_struct *p, int new_cpu);
 
 	void (*task_woken)(struct rq *this_rq, struct task_struct *task);
 
 	void (*set_cpus_allowed)(struct task_struct *p,
-				 const struct cpumask *newmask);
+				 const struct cpumask *newmask,
+				 u32 flags);
 
 	void (*rq_online)(struct rq *rq);
 	void (*rq_offline)(struct rq *rq);
+
+	struct rq *(*find_lock_rq)(struct task_struct *p, struct rq *rq);
 #endif
 
 	void (*task_tick)(struct rq *rq, struct task_struct *p, int queued);
@@ -1833,7 +1873,7 @@ struct sched_class {
 #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)
 {
@@ -1847,6 +1887,20 @@ static inline void set_next_task(struct rq *rq, struct task_struct *next)
 	next->sched_class->set_next_task(rq, next, false);
 }
 
+
+/*
+ * Helper to define a sched_class instance; each one is placed in a separate
+ * section which is ordered by the linker script:
+ *
+ *   include/asm-generic/vmlinux.lds.h
+ *
+ * Also enforce alignment on the instance, not the type, to guarantee layout.
+ */
+#define DEFINE_SCHED_CLASS(name) \
+const struct sched_class name##_sched_class \
+	__aligned(__alignof__(struct sched_class)) \
+	__section("__" #name "_sched_class")
+
 /* Defined in include/asm-generic/vmlinux.lds.h */
 extern struct sched_class __begin_sched_classes[];
 extern struct sched_class __end_sched_classes[];
@@ -1889,13 +1943,35 @@ static inline bool sched_fair_runnable(struct rq *rq)
 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);
 
+#define SCA_CHECK		0x01
+#define SCA_MIGRATE_DISABLE	0x02
+#define SCA_MIGRATE_ENABLE	0x04
+
 #ifdef CONFIG_SMP
 
 extern void update_group_capacity(struct sched_domain *sd, int cpu);
 
 extern void trigger_load_balance(struct rq *rq);
 
-extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask);
+extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask, u32 flags);
+
+static inline struct task_struct *get_push_task(struct rq *rq)
+{
+	struct task_struct *p = rq->curr;
+
+	lockdep_assert_held(&rq->lock);
+
+	if (rq->push_busy)
+		return NULL;
+
+	if (p->nr_cpus_allowed == 1)
+		return NULL;
+
+	rq->push_busy = true;
+	return get_task_struct(p);
+}
+
+extern int push_cpu_stop(void *arg);
 
 #endif
 
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index ceb5b6b12561..55f39125c0e1 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -11,7 +11,7 @@
 
 #ifdef CONFIG_SMP
 static int
-select_task_rq_stop(struct task_struct *p, int cpu, int sd_flag, int flags)
+select_task_rq_stop(struct task_struct *p, int cpu, int flags)
 {
 	return task_cpu(p); /* stop tasks as never migrate */
 }
@@ -109,8 +109,7 @@ static void update_curr_stop(struct rq *rq)
 /*
  * Simple, special scheduling class for the per-CPU stop tasks:
  */
-const struct sched_class stop_sched_class
-	__section("__stop_sched_class") = {
+DEFINE_SCHED_CLASS(stop) = {
 
 	.enqueue_task		= enqueue_task_stop,
 	.dequeue_task		= dequeue_task_stop,
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index dd7770226086..5d3675c7a76b 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -211,6 +211,15 @@ unsigned int sysctl_sched_energy_aware = 1;
 DEFINE_MUTEX(sched_energy_mutex);
 bool sched_energy_update;
 
+void rebuild_sched_domains_energy(void)
+{
+	mutex_lock(&sched_energy_mutex);
+	sched_energy_update = true;
+	rebuild_sched_domains();
+	sched_energy_update = false;
+	mutex_unlock(&sched_energy_mutex);
+}
+
 #ifdef CONFIG_PROC_SYSCTL
 int sched_energy_aware_handler(struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
@@ -223,13 +232,8 @@ int sched_energy_aware_handler(struct ctl_table *table, int write,
 	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (!ret && write) {
 		state = static_branch_unlikely(&sched_energy_present);
-		if (state != sysctl_sched_energy_aware) {
-			mutex_lock(&sched_energy_mutex);
-			sched_energy_update = 1;
-			rebuild_sched_domains();
-			sched_energy_update = 0;
-			mutex_unlock(&sched_energy_mutex);
-		}
+		if (state != sysctl_sched_energy_aware)
+			rebuild_sched_domains_energy();
 	}
 
 	return ret;
@@ -324,6 +328,7 @@ static void sched_energy_set(bool has_eas)
  *    3. no SMT is detected.
  *    4. the EM complexity is low enough to keep scheduling overheads low;
  *    5. schedutil is driving the frequency of all CPUs of the rd;
+ *    6. frequency invariance support is present;
  *
  * The complexity of the Energy Model is defined as:
  *
@@ -372,6 +377,14 @@ static bool build_perf_domains(const struct cpumask *cpu_map)
 		goto free;
 	}
 
+	if (!arch_scale_freq_invariant()) {
+		if (sched_debug()) {
+			pr_warn("rd %*pbl: Disabling EAS: frequency-invariant load tracking not yet supported",
+				cpumask_pr_args(cpu_map));
+		}
+		goto free;
+	}
+
 	for_each_cpu(i, cpu_map) {
 		/* Skip already covered CPUs. */
 		if (find_pd(pd, i))
@@ -516,6 +529,7 @@ static int init_rootdomain(struct root_domain *rd)
 	init_irq_work(&rd->rto_push_work, rto_push_irq_work_func);
 #endif
 
+	rd->visit_gen = 0;
 	init_dl_bw(&rd->dl_bw);
 	if (cpudl_init(&rd->cpudl) != 0)
 		goto free_rto_mask;
@@ -674,6 +688,7 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	struct sched_domain *tmp;
+	int numa_distance = 0;
 
 	/* Remove the sched domains which do not contribute to scheduling. */
 	for (tmp = sd; tmp; ) {
@@ -705,6 +720,38 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 			sd->child = NULL;
 	}
 
+	for (tmp = sd; tmp; tmp = tmp->parent)
+		numa_distance += !!(tmp->flags & SD_NUMA);
+
+	/*
+	 * FIXME: Diameter >=3 is misrepresented.
+	 *
+	 * Smallest diameter=3 topology is:
+	 *
+	 *   node   0   1   2   3
+	 *     0:  10  20  30  40
+	 *     1:  20  10  20  30
+	 *     2:  30  20  10  20
+	 *     3:  40  30  20  10
+	 *
+	 *   0 --- 1 --- 2 --- 3
+	 *
+	 * NUMA-3	0-3		N/A		N/A		0-3
+	 *  groups:	{0-2},{1-3}					{1-3},{0-2}
+	 *
+	 * NUMA-2	0-2		0-3		0-3		1-3
+	 *  groups:	{0-1},{1-3}	{0-2},{2-3}	{1-3},{0-1}	{2-3},{0-2}
+	 *
+	 * NUMA-1	0-1		0-2		1-3		2-3
+	 *  groups:	{0},{1}		{1},{2},{0}	{2},{3},{1}	{3},{2}
+	 *
+	 * NUMA-0	0		1		2		3
+	 *
+	 * The NUMA-2 groups for nodes 0 and 3 are obviously buggered, as the
+	 * group span isn't a subset of the domain span.
+	 */
+	WARN_ONCE(numa_distance > 2, "Shortest NUMA path spans too many nodes\n");
+
 	sched_domain_debug(sd, cpu);
 
 	rq_attach_root(rq, rd);