Merge tag 'sched-core-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler udpates from Ingo Molnar:

 - Changes to core scheduling facilities:

    - Add "Core Scheduling" via CONFIG_SCHED_CORE=y, which enables
      coordinated scheduling across SMT siblings. This is a much
      requested feature for cloud computing platforms, to allow the
      flexible utilization of SMT siblings, without exposing untrusted
      domains to information leaks & side channels, plus to ensure more
      deterministic computing performance on SMT systems used by
      heterogenous workloads.

      There are new prctls to set core scheduling groups, which allows
      more flexible management of workloads that can share siblings.

    - Fix task->state access anti-patterns that may result in missed
      wakeups and rename it to ->__state in the process to catch new
      abuses.

 - Load-balancing changes:

    - Tweak newidle_balance for fair-sched, to improve 'memcache'-like
      workloads.

    - "Age" (decay) average idle time, to better track & improve
      workloads such as 'tbench'.

    - Fix & improve energy-aware (EAS) balancing logic & metrics.

    - Fix & improve the uclamp metrics.

    - Fix task migration (taskset) corner case on !CONFIG_CPUSET.

    - Fix RT and deadline utilization tracking across policy changes

    - Introduce a "burstable" CFS controller via cgroups, which allows
      bursty CPU-bound workloads to borrow a bit against their future
      quota to improve overall latencies & batching. Can be tweaked via
      /sys/fs/cgroup/cpu/<X>/cpu.cfs_burst_us.

    - Rework assymetric topology/capacity detection & handling.

 - Scheduler statistics & tooling:

    - Disable delayacct by default, but add a sysctl to enable it at
      runtime if tooling needs it. Use static keys and other
      optimizations to make it more palatable.

    - Use sched_clock() in delayacct, instead of ktime_get_ns().

 - Misc cleanups and fixes.

* tag 'sched-core-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (72 commits)
  sched/doc: Update the CPU capacity asymmetry bits
  sched/topology: Rework CPU capacity asymmetry detection
  sched/core: Introduce SD_ASYM_CPUCAPACITY_FULL sched_domain flag
  psi: Fix race between psi_trigger_create/destroy
  sched/fair: Introduce the burstable CFS controller
  sched/uclamp: Fix uclamp_tg_restrict()
  sched/rt: Fix Deadline utilization tracking during policy change
  sched/rt: Fix RT utilization tracking during policy change
  sched: Change task_struct::state
  sched,arch: Remove unused TASK_STATE offsets
  sched,timer: Use __set_current_state()
  sched: Add get_current_state()
  sched,perf,kvm: Fix preemption condition
  sched: Introduce task_is_running()
  sched: Unbreak wakeups
  sched/fair: Age the average idle time
  sched/cpufreq: Consider reduced CPU capacity in energy calculation
  sched/fair: Take thermal pressure into account while estimating energy
  thermal/cpufreq_cooling: Update offline CPUs per-cpu thermal_pressure
  sched/fair: Return early from update_tg_cfs_load() if delta == 0
  ...

1 files changed, 1006 insertions, 132 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4ca80df205ce..4a2a448d8dd4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -84,6 +84,272 @@ unsigned int sysctl_sched_rt_period = 1000000;
 
 __read_mostly int scheduler_running;
 
+#ifdef CONFIG_SCHED_CORE
+
+DEFINE_STATIC_KEY_FALSE(__sched_core_enabled);
+
+/* kernel prio, less is more */
+static inline int __task_prio(struct task_struct *p)
+{
+	if (p->sched_class == &stop_sched_class) /* trumps deadline */
+		return -2;
+
+	if (rt_prio(p->prio)) /* includes deadline */
+		return p->prio; /* [-1, 99] */
+
+	if (p->sched_class == &idle_sched_class)
+		return MAX_RT_PRIO + NICE_WIDTH; /* 140 */
+
+	return MAX_RT_PRIO + MAX_NICE; /* 120, squash fair */
+}
+
+/*
+ * l(a,b)
+ * le(a,b) := !l(b,a)
+ * g(a,b)  := l(b,a)
+ * ge(a,b) := !l(a,b)
+ */
+
+/* real prio, less is less */
+static inline bool prio_less(struct task_struct *a, struct task_struct *b, bool in_fi)
+{
+
+	int pa = __task_prio(a), pb = __task_prio(b);
+
+	if (-pa < -pb)
+		return true;
+
+	if (-pb < -pa)
+		return false;
+
+	if (pa == -1) /* dl_prio() doesn't work because of stop_class above */
+		return !dl_time_before(a->dl.deadline, b->dl.deadline);
+
+	if (pa == MAX_RT_PRIO + MAX_NICE)	/* fair */
+		return cfs_prio_less(a, b, in_fi);
+
+	return false;
+}
+
+static inline bool __sched_core_less(struct task_struct *a, struct task_struct *b)
+{
+	if (a->core_cookie < b->core_cookie)
+		return true;
+
+	if (a->core_cookie > b->core_cookie)
+		return false;
+
+	/* flip prio, so high prio is leftmost */
+	if (prio_less(b, a, task_rq(a)->core->core_forceidle))
+		return true;
+
+	return false;
+}
+
+#define __node_2_sc(node) rb_entry((node), struct task_struct, core_node)
+
+static inline bool rb_sched_core_less(struct rb_node *a, const struct rb_node *b)
+{
+	return __sched_core_less(__node_2_sc(a), __node_2_sc(b));
+}
+
+static inline int rb_sched_core_cmp(const void *key, const struct rb_node *node)
+{
+	const struct task_struct *p = __node_2_sc(node);
+	unsigned long cookie = (unsigned long)key;
+
+	if (cookie < p->core_cookie)
+		return -1;
+
+	if (cookie > p->core_cookie)
+		return 1;
+
+	return 0;
+}
+
+void sched_core_enqueue(struct rq *rq, struct task_struct *p)
+{
+	rq->core->core_task_seq++;
+
+	if (!p->core_cookie)
+		return;
+
+	rb_add(&p->core_node, &rq->core_tree, rb_sched_core_less);
+}
+
+void sched_core_dequeue(struct rq *rq, struct task_struct *p)
+{
+	rq->core->core_task_seq++;
+
+	if (!sched_core_enqueued(p))
+		return;
+
+	rb_erase(&p->core_node, &rq->core_tree);
+	RB_CLEAR_NODE(&p->core_node);
+}
+
+/*
+ * Find left-most (aka, highest priority) task matching @cookie.
+ */
+static struct task_struct *sched_core_find(struct rq *rq, unsigned long cookie)
+{
+	struct rb_node *node;
+
+	node = rb_find_first((void *)cookie, &rq->core_tree, rb_sched_core_cmp);
+	/*
+	 * The idle task always matches any cookie!
+	 */
+	if (!node)
+		return idle_sched_class.pick_task(rq);
+
+	return __node_2_sc(node);
+}
+
+static struct task_struct *sched_core_next(struct task_struct *p, unsigned long cookie)
+{
+	struct rb_node *node = &p->core_node;
+
+	node = rb_next(node);
+	if (!node)
+		return NULL;
+
+	p = container_of(node, struct task_struct, core_node);
+	if (p->core_cookie != cookie)
+		return NULL;
+
+	return p;
+}
+
+/*
+ * Magic required such that:
+ *
+ *	raw_spin_rq_lock(rq);
+ *	...
+ *	raw_spin_rq_unlock(rq);
+ *
+ * ends up locking and unlocking the _same_ lock, and all CPUs
+ * always agree on what rq has what lock.
+ *
+ * XXX entirely possible to selectively enable cores, don't bother for now.
+ */
+
+static DEFINE_MUTEX(sched_core_mutex);
+static atomic_t sched_core_count;
+static struct cpumask sched_core_mask;
+
+static void __sched_core_flip(bool enabled)
+{
+	int cpu, t, i;
+
+	cpus_read_lock();
+
+	/*
+	 * Toggle the online cores, one by one.
+	 */
+	cpumask_copy(&sched_core_mask, cpu_online_mask);
+	for_each_cpu(cpu, &sched_core_mask) {
+		const struct cpumask *smt_mask = cpu_smt_mask(cpu);
+
+		i = 0;
+		local_irq_disable();
+		for_each_cpu(t, smt_mask) {
+			/* supports up to SMT8 */
+			raw_spin_lock_nested(&cpu_rq(t)->__lock, i++);
+		}
+
+		for_each_cpu(t, smt_mask)
+			cpu_rq(t)->core_enabled = enabled;
+
+		for_each_cpu(t, smt_mask)
+			raw_spin_unlock(&cpu_rq(t)->__lock);
+		local_irq_enable();
+
+		cpumask_andnot(&sched_core_mask, &sched_core_mask, smt_mask);
+	}
+
+	/*
+	 * Toggle the offline CPUs.
+	 */
+	cpumask_copy(&sched_core_mask, cpu_possible_mask);
+	cpumask_andnot(&sched_core_mask, &sched_core_mask, cpu_online_mask);
+
+	for_each_cpu(cpu, &sched_core_mask)
+		cpu_rq(cpu)->core_enabled = enabled;
+
+	cpus_read_unlock();
+}
+
+static void sched_core_assert_empty(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		WARN_ON_ONCE(!RB_EMPTY_ROOT(&cpu_rq(cpu)->core_tree));
+}
+
+static void __sched_core_enable(void)
+{
+	static_branch_enable(&__sched_core_enabled);
+	/*
+	 * Ensure all previous instances of raw_spin_rq_*lock() have finished
+	 * and future ones will observe !sched_core_disabled().
+	 */
+	synchronize_rcu();
+	__sched_core_flip(true);
+	sched_core_assert_empty();
+}
+
+static void __sched_core_disable(void)
+{
+	sched_core_assert_empty();
+	__sched_core_flip(false);
+	static_branch_disable(&__sched_core_enabled);
+}
+
+void sched_core_get(void)
+{
+	if (atomic_inc_not_zero(&sched_core_count))
+		return;
+
+	mutex_lock(&sched_core_mutex);
+	if (!atomic_read(&sched_core_count))
+		__sched_core_enable();
+
+	smp_mb__before_atomic();
+	atomic_inc(&sched_core_count);
+	mutex_unlock(&sched_core_mutex);
+}
+
+static void __sched_core_put(struct work_struct *work)
+{
+	if (atomic_dec_and_mutex_lock(&sched_core_count, &sched_core_mutex)) {
+		__sched_core_disable();
+		mutex_unlock(&sched_core_mutex);
+	}
+}
+
+void sched_core_put(void)
+{
+	static DECLARE_WORK(_work, __sched_core_put);
+
+	/*
+	 * "There can be only one"
+	 *
+	 * Either this is the last one, or we don't actually need to do any
+	 * 'work'. If it is the last *again*, we rely on
+	 * WORK_STRUCT_PENDING_BIT.
+	 */
+	if (!atomic_add_unless(&sched_core_count, -1, 1))
+		schedule_work(&_work);
+}
+
+#else /* !CONFIG_SCHED_CORE */
+
+static inline void sched_core_enqueue(struct rq *rq, struct task_struct *p) { }
+static inline void sched_core_dequeue(struct rq *rq, struct task_struct *p) { }
+
+#endif /* CONFIG_SCHED_CORE */
+
 /*
  * part of the period that we allow rt tasks to run in us.
  * default: 0.95s
@@ -184,6 +450,79 @@ int sysctl_sched_rt_runtime = 950000;
  *
  */
 
+void raw_spin_rq_lock_nested(struct rq *rq, int subclass)
+{
+	raw_spinlock_t *lock;
+
+	/* Matches synchronize_rcu() in __sched_core_enable() */
+	preempt_disable();
+	if (sched_core_disabled()) {
+		raw_spin_lock_nested(&rq->__lock, subclass);
+		/* preempt_count *MUST* be > 1 */
+		preempt_enable_no_resched();
+		return;
+	}
+
+	for (;;) {
+		lock = __rq_lockp(rq);
+		raw_spin_lock_nested(lock, subclass);
+		if (likely(lock == __rq_lockp(rq))) {
+			/* preempt_count *MUST* be > 1 */
+			preempt_enable_no_resched();
+			return;
+		}
+		raw_spin_unlock(lock);
+	}
+}
+
+bool raw_spin_rq_trylock(struct rq *rq)
+{
+	raw_spinlock_t *lock;
+	bool ret;
+
+	/* Matches synchronize_rcu() in __sched_core_enable() */
+	preempt_disable();
+	if (sched_core_disabled()) {
+		ret = raw_spin_trylock(&rq->__lock);
+		preempt_enable();
+		return ret;
+	}
+
+	for (;;) {
+		lock = __rq_lockp(rq);
+		ret = raw_spin_trylock(lock);
+		if (!ret || (likely(lock == __rq_lockp(rq)))) {
+			preempt_enable();
+			return ret;
+		}
+		raw_spin_unlock(lock);
+	}
+}
+
+void raw_spin_rq_unlock(struct rq *rq)
+{
+	raw_spin_unlock(rq_lockp(rq));
+}
+
+#ifdef CONFIG_SMP
+/*
+ * double_rq_lock - safely lock two runqueues
+ */
+void double_rq_lock(struct rq *rq1, struct rq *rq2)
+{
+	lockdep_assert_irqs_disabled();
+
+	if (rq_order_less(rq2, rq1))
+		swap(rq1, rq2);
+
+	raw_spin_rq_lock(rq1);
+	if (__rq_lockp(rq1) == __rq_lockp(rq2))
+		return;
+
+	raw_spin_rq_lock_nested(rq2, SINGLE_DEPTH_NESTING);
+}
+#endif
+
 /*
  * __task_rq_lock - lock the rq @p resides on.
  */
@@ -196,12 +535,12 @@ struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 
 	for (;;) {
 		rq = task_rq(p);
-		raw_spin_lock(&rq->lock);
+		raw_spin_rq_lock(rq);
 		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
 			rq_pin_lock(rq, rf);
 			return rq;
 		}
-		raw_spin_unlock(&rq->lock);
+		raw_spin_rq_unlock(rq);
 
 		while (unlikely(task_on_rq_migrating(p)))
 			cpu_relax();
@@ -220,7 +559,7 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 	for (;;) {
 		raw_spin_lock_irqsave(&p->pi_lock, rf->flags);
 		rq = task_rq(p);
-		raw_spin_lock(&rq->lock);
+		raw_spin_rq_lock(rq);
 		/*
 		 *	move_queued_task()		task_rq_lock()
 		 *
@@ -242,7 +581,7 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 			rq_pin_lock(rq, rf);
 			return rq;
 		}
-		raw_spin_unlock(&rq->lock);
+		raw_spin_rq_unlock(rq);
 		raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
 
 		while (unlikely(task_on_rq_migrating(p)))
@@ -312,7 +651,7 @@ void update_rq_clock(struct rq *rq)
 {
 	s64 delta;
 
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 
 	if (rq->clock_update_flags & RQCF_ACT_SKIP)
 		return;
@@ -585,7 +924,6 @@ void wake_up_q(struct wake_q_head *head)
 		struct task_struct *task;
 
 		task = container_of(node, struct task_struct, wake_q);
-		BUG_ON(!task);
 		/* Task can safely be re-inserted now: */
 		node = node->next;
 		task->wake_q.next = NULL;
@@ -611,7 +949,7 @@ void resched_curr(struct rq *rq)
 	struct task_struct *curr = rq->curr;
 	int cpu;
 
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 
 	if (test_tsk_need_resched(curr))
 		return;
@@ -635,10 +973,10 @@ void resched_cpu(int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&rq->lock, flags);
+	raw_spin_rq_lock_irqsave(rq, flags);
 	if (cpu_online(cpu) || cpu == smp_processor_id())
 		resched_curr(rq);
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	raw_spin_rq_unlock_irqrestore(rq, flags);
 }
 
 #ifdef CONFIG_SMP
@@ -1065,9 +1403,10 @@ static void uclamp_sync_util_min_rt_default(void)
 static inline struct uclamp_se
 uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id)
 {
+	/* Copy by value as we could modify it */
 	struct uclamp_se uc_req = p->uclamp_req[clamp_id];
 #ifdef CONFIG_UCLAMP_TASK_GROUP
-	struct uclamp_se uc_max;
+	unsigned int tg_min, tg_max, value;
 
 	/*
 	 * Tasks in autogroups or root task group will be
@@ -1078,9 +1417,11 @@ uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id)
 	if (task_group(p) == &root_task_group)
 		return uc_req;
 
-	uc_max = task_group(p)->uclamp[clamp_id];
-	if (uc_req.value > uc_max.value || !uc_req.user_defined)
-		return uc_max;
+	tg_min = task_group(p)->uclamp[UCLAMP_MIN].value;
+	tg_max = task_group(p)->uclamp[UCLAMP_MAX].value;
+	value = uc_req.value;
+	value = clamp(value, tg_min, tg_max);
+	uclamp_se_set(&uc_req, value, false);
 #endif
 
 	return uc_req;
@@ -1137,7 +1478,7 @@ static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p,
 	struct uclamp_se *uc_se = &p->uclamp[clamp_id];
 	struct uclamp_bucket *bucket;
 
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 
 	/* Update task effective clamp */
 	p->uclamp[clamp_id] = uclamp_eff_get(p, clamp_id);
@@ -1177,7 +1518,7 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
 	unsigned int bkt_clamp;
 	unsigned int rq_clamp;
 
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 
 	/*
 	 * If sched_uclamp_used was enabled after task @p was enqueued,
@@ -1279,8 +1620,9 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
 }
 
 static inline void
-uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id)
+uclamp_update_active(struct task_struct *p)
 {
+	enum uclamp_id clamp_id;
 	struct rq_flags rf;
 	struct rq *rq;
 
@@ -1300,9 +1642,11 @@ uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id)
 	 * affecting a valid clamp bucket, the next time it's enqueued,
 	 * it will already see the updated clamp bucket value.
 	 */
-	if (p->uclamp[clamp_id].active) {
-		uclamp_rq_dec_id(rq, p, clamp_id);
-		uclamp_rq_inc_id(rq, p, clamp_id);
+	for_each_clamp_id(clamp_id) {
+		if (p->uclamp[clamp_id].active) {
+			uclamp_rq_dec_id(rq, p, clamp_id);
+			uclamp_rq_inc_id(rq, p, clamp_id);
+		}
 	}
 
 	task_rq_unlock(rq, p, &rf);
@@ -1310,20 +1654,14 @@ uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id)
 
 #ifdef CONFIG_UCLAMP_TASK_GROUP
 static inline void
-uclamp_update_active_tasks(struct cgroup_subsys_state *css,
-			   unsigned int clamps)
+uclamp_update_active_tasks(struct cgroup_subsys_state *css)
 {
-	enum uclamp_id clamp_id;
 	struct css_task_iter it;
 	struct task_struct *p;
 
 	css_task_iter_start(css, 0, &it);
-	while ((p = css_task_iter_next(&it))) {
-		for_each_clamp_id(clamp_id) {
-			if ((0x1 << clamp_id) & clamps)
-				uclamp_update_active(p, clamp_id);
-		}
-	}
+	while ((p = css_task_iter_next(&it)))
+		uclamp_update_active(p);
 	css_task_iter_end(&it);
 }
 
@@ -1596,21 +1934,27 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 		update_rq_clock(rq);
 
 	if (!(flags & ENQUEUE_RESTORE)) {
-		sched_info_queued(rq, p);
+		sched_info_enqueue(rq, p);
 		psi_enqueue(p, flags & ENQUEUE_WAKEUP);
 	}
 
 	uclamp_rq_inc(rq, p);
 	p->sched_class->enqueue_task(rq, p, flags);
+
+	if (sched_core_enabled(rq))
+		sched_core_enqueue(rq, p);
 }
 
 static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 {
+	if (sched_core_enabled(rq))
+		sched_core_dequeue(rq, p);
+
 	if (!(flags & DEQUEUE_NOCLOCK))
 		update_rq_clock(rq);
 
 	if (!(flags & DEQUEUE_SAVE)) {
-		sched_info_dequeued(rq, p);
+		sched_info_dequeue(rq, p);
 		psi_dequeue(p, flags & DEQUEUE_SLEEP);
 	}
 
@@ -1850,7 +2194,7 @@ static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
 static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
 				   struct task_struct *p, int new_cpu)
 {
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 
 	deactivate_task(rq, p, DEQUEUE_NOCLOCK);
 	set_task_cpu(p, new_cpu);
@@ -1916,7 +2260,6 @@ static int migration_cpu_stop(void *data)
 	struct migration_arg *arg = data;
 	struct set_affinity_pending *pending = arg->pending;
 	struct task_struct *p = arg->task;
-	int dest_cpu = arg->dest_cpu;
 	struct rq *rq = this_rq();
 	bool complete = false;
 	struct rq_flags rf;
@@ -1954,19 +2297,15 @@ static int migration_cpu_stop(void *data)
 		if (pending) {
 			p->migration_pending = NULL;
 			complete = true;
-		}
 
-		if (dest_cpu < 0) {
 			if (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, dest_cpu);
+			rq = __migrate_task(rq, &rf, p, arg->dest_cpu);
 		else
-			p->wake_cpu = dest_cpu;
+			p->wake_cpu = arg->dest_cpu;
 
 		/*
 		 * XXX __migrate_task() can fail, at which point we might end
@@ -2024,7 +2363,7 @@ int push_cpu_stop(void *arg)
 	struct task_struct *p = arg;
 
 	raw_spin_lock_irq(&p->pi_lock);
-	raw_spin_lock(&rq->lock);
+	raw_spin_rq_lock(rq);
 
 	if (task_rq(p) != rq)
 		goto out_unlock;
@@ -2054,7 +2393,7 @@ int push_cpu_stop(void *arg)
 
 out_unlock:
 	rq->push_busy = false;
-	raw_spin_unlock(&rq->lock);
+	raw_spin_rq_unlock(rq);
 	raw_spin_unlock_irq(&p->pi_lock);
 
 	put_task_struct(p);
@@ -2107,7 +2446,7 @@ __do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32
 		 * Because __kthread_bind() calls this on blocked tasks without
 		 * holding rq->lock.
 		 */
-		lockdep_assert_held(&rq->lock);
+		lockdep_assert_rq_held(rq);
 		dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK);
 	}
 	if (running)
@@ -2249,7 +2588,7 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
 			init_completion(&my_pending.done);
 			my_pending.arg = (struct migration_arg) {
 				.task = p,
-				.dest_cpu = -1,		/* any */
+				.dest_cpu = dest_cpu,
 				.pending = &my_pending,
 			};
 
@@ -2257,6 +2596,15 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
 		} else {
 			pending = p->migration_pending;
 			refcount_inc(&pending->refs);
+			/*
+			 * Affinity has changed, but we've already installed a
+			 * pending. migration_cpu_stop() *must* see this, else
+			 * we risk a completion of the pending despite having a
+			 * task on a disallowed CPU.
+			 *
+			 * Serialized by p->pi_lock, so this is safe.
+			 */
+			pending->arg.dest_cpu = dest_cpu;
 		}
 	}
 	pending = p->migration_pending;
@@ -2277,7 +2625,7 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
 		return -EINVAL;
 	}
 
-	if (task_running(rq, p) || p->state == TASK_WAKING) {
+	if (task_running(rq, p) || READ_ONCE(p->__state) == TASK_WAKING) {
 		/*
 		 * MIGRATE_ENABLE gets here because 'p == current', but for
 		 * anything else we cannot do is_migration_disabled(), punt
@@ -2420,19 +2768,20 @@ EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
 void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 {
 #ifdef CONFIG_SCHED_DEBUG
+	unsigned int state = READ_ONCE(p->__state);
+
 	/*
 	 * We should never call set_task_cpu() on a blocked task,
 	 * ttwu() will sort out the placement.
 	 */
-	WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING &&
-			!p->on_rq);
+	WARN_ON_ONCE(state != TASK_RUNNING && state != TASK_WAKING && !p->on_rq);
 
 	/*
 	 * Migrating fair class task must have p->on_rq = TASK_ON_RQ_MIGRATING,
 	 * because schedstat_wait_{start,end} rebase migrating task's wait_start
 	 * time relying on p->on_rq.
 	 */
-	WARN_ON_ONCE(p->state == TASK_RUNNING &&
+	WARN_ON_ONCE(state == TASK_RUNNING &&
 		     p->sched_class == &fair_sched_class &&
 		     (p->on_rq && !task_on_rq_migrating(p)));
 
@@ -2448,7 +2797,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	 * task_rq_lock().
 	 */
 	WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) ||
-				      lockdep_is_held(&task_rq(p)->lock)));
+				      lockdep_is_held(__rq_lockp(task_rq(p)))));
 #endif
 	/*
 	 * Clearly, migrating tasks to offline CPUs is a fairly daft thing.
@@ -2604,7 +2953,7 @@ out:
  * smp_call_function() if an IPI is sent by the same process we are
  * waiting to become inactive.
  */
-unsigned long wait_task_inactive(struct task_struct *p, long match_state)
+unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state)
 {
 	int running, queued;
 	struct rq_flags rf;
@@ -2632,7 +2981,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		 * is actually now running somewhere else!
 		 */
 		while (task_running(rq, p)) {
-			if (match_state && unlikely(p->state != match_state))
+			if (match_state && unlikely(READ_ONCE(p->__state) != match_state))
 				return 0;
 			cpu_relax();
 		}
@@ -2647,7 +2996,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		running = task_running(rq, p);
 		queued = task_on_rq_queued(p);
 		ncsw = 0;
-		if (!match_state || p->state == match_state)
+		if (!match_state || READ_ONCE(p->__state) == match_state)
 			ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
 		task_rq_unlock(rq, p, &rf);
 
@@ -2956,7 +3305,7 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
 			   struct rq_flags *rf)
 {
 	check_preempt_curr(rq, p, wake_flags);
-	p->state = TASK_RUNNING;
+	WRITE_ONCE(p->__state, TASK_RUNNING);
 	trace_sched_wakeup(p);
 
 #ifdef CONFIG_SMP
@@ -2979,6 +3328,9 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
 		if (rq->avg_idle > max)
 			rq->avg_idle = max;
 
+		rq->wake_stamp = jiffies;
+		rq->wake_avg_idle = rq->avg_idle / 2;
+
 		rq->idle_stamp = 0;
 	}
 #endif
@@ -2990,7 +3342,7 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 {
 	int en_flags = ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK;
 
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 
 	if (p->sched_contributes_to_load)
 		rq->nr_uninterruptible--;
@@ -3345,12 +3697,12 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		 *  - we're serialized against set_special_state() by virtue of
 		 *    it disabling IRQs (this allows not taking ->pi_lock).
 		 */
-		if (!(p->state & state))
+		if (!(READ_ONCE(p->__state) & state))
 			goto out;
 
 		success = 1;
 		trace_sched_waking(p);
-		p->state = TASK_RUNNING;
+		WRITE_ONCE(p->__state, TASK_RUNNING);
 		trace_sched_wakeup(p);
 		goto out;
 	}
@@ -3363,7 +3715,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 */
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
 	smp_mb__after_spinlock();
-	if (!(p->state & state))
+	if (!(READ_ONCE(p->__state) & state))
 		goto unlock;
 
 	trace_sched_waking(p);
@@ -3429,7 +3781,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * TASK_WAKING such that we can unlock p->pi_lock before doing the
 	 * enqueue, such as ttwu_queue_wakelist().
 	 */
-	p->state = TASK_WAKING;
+	WRITE_ONCE(p->__state, TASK_WAKING);
 
 	/*
 	 * If the owning (remote) CPU is still in the middle of schedule() with
@@ -3522,7 +3874,7 @@ bool try_invoke_on_locked_down_task(struct task_struct *p, bool (*func)(struct t
 			ret = func(p, arg);
 		rq_unlock(rq, &rf);
 	} else {
-		switch (p->state) {
+		switch (READ_ONCE(p->__state)) {
 		case TASK_RUNNING:
 		case TASK_WAKING:
 			break;
@@ -3648,7 +4000,6 @@ int sysctl_numa_balancing(struct ctl_table *table, int write,
 #ifdef CONFIG_SCHEDSTATS
 
 DEFINE_STATIC_KEY_FALSE(sched_schedstats);
-static bool __initdata __sched_schedstats = false;
 
 static void set_schedstats(bool enabled)
 {
@@ -3672,16 +4023,11 @@ static int __init setup_schedstats(char *str)
 	if (!str)
 		goto out;
 
-	/*
-	 * This code is called before jump labels have been set up, so we can't
-	 * change the static branch directly just yet.  Instead set a temporary
-	 * variable so init_schedstats() can do it later.
-	 */
 	if (!strcmp(str, "enable")) {
-		__sched_schedstats = true;
+		set_schedstats(true);
 		ret = 1;
 	} else if (!strcmp(str, "disable")) {
-		__sched_schedstats = false;
+		set_schedstats(false);
 		ret = 1;
 	}
 out:
@@ -3692,11 +4038,6 @@ out:
 }
 __setup("schedstats=", setup_schedstats);
 
-static void __init init_schedstats(void)
-{
-	set_schedstats(__sched_schedstats);
-}
-
 #ifdef CONFIG_PROC_SYSCTL
 int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
@@ -3718,8 +4059,6 @@ int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
 	return err;
 }
 #endif /* CONFIG_PROC_SYSCTL */
-#else  /* !CONFIG_SCHEDSTATS */
-static inline void init_schedstats(void) {}
 #endif /* CONFIG_SCHEDSTATS */
 
 /*
@@ -3735,7 +4074,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	 * nobody will actually run it, and a signal or other external
 	 * event cannot wake it up and insert it on the runqueue either.
 	 */
-	p->state = TASK_NEW;
+	p->__state = TASK_NEW;
 
 	/*
 	 * Make sure we do not leak PI boosting priority to the child.
@@ -3841,7 +4180,7 @@ void wake_up_new_task(struct task_struct *p)
 	struct rq *rq;
 
 	raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
-	p->state = TASK_RUNNING;
+	WRITE_ONCE(p->__state, TASK_RUNNING);
 #ifdef CONFIG_SMP
 	/*
 	 * Fork balancing, do it here and not earlier because:
@@ -4001,7 +4340,7 @@ 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);
+	lockdep_assert_rq_held(rq);
 
 	while (head) {
 		func = (void (*)(struct rq *))head->func;
@@ -4024,7 +4363,7 @@ static inline struct callback_head *splice_balance_callbacks(struct rq *rq)
 {
 	struct callback_head *head = rq->balance_callback;
 
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 	if (head)
 		rq->balance_callback = NULL;
 
@@ -4041,9 +4380,9 @@ 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);
+		raw_spin_rq_lock_irqsave(rq, flags);
 		do_balance_callbacks(rq, head);
-		raw_spin_unlock_irqrestore(&rq->lock, flags);
+		raw_spin_rq_unlock_irqrestore(rq, flags);
 	}
 }
 
@@ -4074,10 +4413,10 @@ prepare_lock_switch(struct rq *rq, struct task_struct *next, struct rq_flags *rf
 	 * do an early lockdep release here:
 	 */
 	rq_unpin_lock(rq, rf);
-	spin_release(&rq->lock.dep_map, _THIS_IP_);
+	spin_release(&__rq_lockp(rq)->dep_map, _THIS_IP_);
 #ifdef CONFIG_DEBUG_SPINLOCK
 	/* this is a valid case when another task releases the spinlock */
-	rq->lock.owner = next;
+	rq_lockp(rq)->owner = next;
 #endif
 }
 
@@ -4088,9 +4427,9 @@ static inline void finish_lock_switch(struct rq *rq)
 	 * fix up the runqueue lock - which gets 'carried over' from
 	 * prev into current:
 	 */
-	spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
+	spin_acquire(&__rq_lockp(rq)->dep_map, 0, 0, _THIS_IP_);
 	__balance_callbacks(rq);
-	raw_spin_unlock_irq(&rq->lock);
+	raw_spin_rq_unlock_irq(rq);
 }
 
 /*
@@ -4203,7 +4542,7 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	 * running on another CPU and we could rave with its RUNNING -> DEAD
 	 * transition, resulting in a double drop.
 	 */
-	prev_state = prev->state;
+	prev_state = READ_ONCE(prev->__state);
 	vtime_task_switch(prev);
 	perf_event_task_sched_in(prev, current);
 	finish_task(prev);
@@ -4348,9 +4687,9 @@ context_switch(struct rq *rq, struct task_struct *prev,
  * externally visible scheduler statistics: current number of runnable
  * threads, total number of context switches performed since bootup.
  */
-unsigned long nr_running(void)
+unsigned int nr_running(void)
 {
-	unsigned long i, sum = 0;
+	unsigned int i, sum = 0;
 
 	for_each_online_cpu(i)
 		sum += cpu_rq(i)->nr_running;
@@ -4395,7 +4734,7 @@ unsigned long long nr_context_switches(void)
  * it does become runnable.
  */
 
-unsigned long nr_iowait_cpu(int cpu)
+unsigned int nr_iowait_cpu(int cpu)
 {
 	return atomic_read(&cpu_rq(cpu)->nr_iowait);
 }
@@ -4430,9 +4769,9 @@ unsigned long nr_iowait_cpu(int cpu)
  * Task CPU affinities can make all that even more 'interesting'.
  */
 
-unsigned long nr_iowait(void)
+unsigned int nr_iowait(void)
 {
-	unsigned long i, sum = 0;
+	unsigned int i, sum = 0;
 
 	for_each_possible_cpu(i)
 		sum += nr_iowait_cpu(i);
@@ -4897,7 +5236,7 @@ static inline void schedule_debug(struct task_struct *prev, bool preempt)
 #endif
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
-	if (!preempt && prev->state && prev->non_block_count) {
+	if (!preempt && READ_ONCE(prev->__state) && prev->non_block_count) {
 		printk(KERN_ERR "BUG: scheduling in a non-blocking section: %s/%d/%i\n",
 			prev->comm, prev->pid, prev->non_block_count);
 		dump_stack();
@@ -4943,7 +5282,7 @@ static void put_prev_task_balance(struct rq *rq, struct task_struct *prev,
  * Pick up the highest-prio task:
  */
 static inline struct task_struct *
-pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+__pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
 	const struct sched_class *class;
 	struct task_struct *p;
@@ -4961,7 +5300,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		if (unlikely(p == RETRY_TASK))
 			goto restart;
 
-		/* Assumes fair_sched_class->next == idle_sched_class */
+		/* Assume the next prioritized class is idle_sched_class */
 		if (!p) {
 			put_prev_task(rq, prev);
 			p = pick_next_task_idle(rq);
@@ -4983,6 +5322,455 @@ restart:
 	BUG();
 }
 
+#ifdef CONFIG_SCHED_CORE
+static inline bool is_task_rq_idle(struct task_struct *t)
+{
+	return (task_rq(t)->idle == t);
+}
+
+static inline bool cookie_equals(struct task_struct *a, unsigned long cookie)
+{
+	return is_task_rq_idle(a) || (a->core_cookie == cookie);
+}
+
+static inline bool cookie_match(struct task_struct *a, struct task_struct *b)
+{
+	if (is_task_rq_idle(a) || is_task_rq_idle(b))
+		return true;
+
+	return a->core_cookie == b->core_cookie;
+}
+
+// XXX fairness/fwd progress conditions
+/*
+ * Returns
+ * - NULL if there is no runnable task for this class.
+ * - the highest priority task for this runqueue if it matches
+ *   rq->core->core_cookie or its priority is greater than max.
+ * - Else returns idle_task.
+ */
+static struct task_struct *
+pick_task(struct rq *rq, const struct sched_class *class, struct task_struct *max, bool in_fi)
+{
+	struct task_struct *class_pick, *cookie_pick;
+	unsigned long cookie = rq->core->core_cookie;
+
+	class_pick = class->pick_task(rq);
+	if (!class_pick)
+		return NULL;
+
+	if (!cookie) {
+		/*
+		 * If class_pick is tagged, return it only if it has
+		 * higher priority than max.
+		 */
+		if (max && class_pick->core_cookie &&
+		    prio_less(class_pick, max, in_fi))
+			return idle_sched_class.pick_task(rq);
+
+		return class_pick;
+	}
+
+	/*
+	 * If class_pick is idle or matches cookie, return early.
+	 */
+	if (cookie_equals(class_pick, cookie))
+		return class_pick;
+
+	cookie_pick = sched_core_find(rq, cookie);
+
+	/*
+	 * If class > max && class > cookie, it is the highest priority task on
+	 * the core (so far) and it must be selected, otherwise we must go with
+	 * the cookie pick in order to satisfy the constraint.
+	 */
+	if (prio_less(cookie_pick, class_pick, in_fi) &&
+	    (!max || prio_less(max, class_pick, in_fi)))
+		return class_pick;
+
+	return cookie_pick;
+}
+
+extern void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi);
+
+static struct task_struct *
+pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+{
+	struct task_struct *next, *max = NULL;
+	const struct sched_class *class;
+	const struct cpumask *smt_mask;
+	bool fi_before = false;
+	int i, j, cpu, occ = 0;
+	bool need_sync;
+
+	if (!sched_core_enabled(rq))
+		return __pick_next_task(rq, prev, rf);
+
+	cpu = cpu_of(rq);
+
+	/* Stopper task is switching into idle, no need core-wide selection. */
+	if (cpu_is_offline(cpu)) {
+		/*
+		 * Reset core_pick so that we don't enter the fastpath when
+		 * coming online. core_pick would already be migrated to
+		 * another cpu during offline.
+		 */
+		rq->core_pick = NULL;
+		return __pick_next_task(rq, prev, rf);
+	}
+
+	/*
+	 * If there were no {en,de}queues since we picked (IOW, the task
+	 * pointers are all still valid), and we haven't scheduled the last
+	 * pick yet, do so now.
+	 *
+	 * rq->core_pick can be NULL if no selection was made for a CPU because
+	 * it was either offline or went offline during a sibling's core-wide
+	 * selection. In this case, do a core-wide selection.
+	 */
+	if (rq->core->core_pick_seq == rq->core->core_task_seq &&
+	    rq->core->core_pick_seq != rq->core_sched_seq &&
+	    rq->core_pick) {
+		WRITE_ONCE(rq->core_sched_seq, rq->core->core_pick_seq);
+
+		next = rq->core_pick;
+		if (next != prev) {
+			put_prev_task(rq, prev);
+			set_next_task(rq, next);
+		}
+
+		rq->core_pick = NULL;
+		return next;
+	}
+
+	put_prev_task_balance(rq, prev, rf);
+
+	smt_mask = cpu_smt_mask(cpu);
+	need_sync = !!rq->core->core_cookie;
+
+	/* reset state */
+	rq->core->core_cookie = 0UL;
+	if (rq->core->core_forceidle) {
+		need_sync = true;
+		fi_before = true;
+		rq->core->core_forceidle = false;
+	}
+
+	/*
+	 * core->core_task_seq, core->core_pick_seq, rq->core_sched_seq
+	 *
+	 * @task_seq guards the task state ({en,de}queues)
+	 * @pick_seq is the @task_seq we did a selection on
+	 * @sched_seq is the @pick_seq we scheduled
+	 *
+	 * However, preemptions can cause multiple picks on the same task set.
+	 * 'Fix' this by also increasing @task_seq for every pick.
+	 */
+	rq->core->core_task_seq++;
+
+	/*
+	 * Optimize for common case where this CPU has no cookies
+	 * and there are no cookied tasks running on siblings.
+	 */
+	if (!need_sync) {
+		for_each_class(class) {
+			next = class->pick_task(rq);
+			if (next)
+				break;
+		}
+
+		if (!next->core_cookie) {
+			rq->core_pick = NULL;
+			/*
+			 * For robustness, update the min_vruntime_fi for
+			 * unconstrained picks as well.
+			 */
+			WARN_ON_ONCE(fi_before);
+			task_vruntime_update(rq, next, false);
+			goto done;
+		}
+	}
+
+	for_each_cpu(i, smt_mask) {
+		struct rq *rq_i = cpu_rq(i);
+
+		rq_i->core_pick = NULL;
+
+		if (i != cpu)
+			update_rq_clock(rq_i);
+	}
+
+	/*
+	 * Try and select tasks for each sibling in descending sched_class
+	 * order.
+	 */
+	for_each_class(class) {
+again:
+		for_each_cpu_wrap(i, smt_mask, cpu) {
+			struct rq *rq_i = cpu_rq(i);
+			struct task_struct *p;
+
+			if (rq_i->core_pick)
+				continue;
+
+			/*
+			 * If this sibling doesn't yet have a suitable task to
+			 * run; ask for the most eligible task, given the
+			 * highest priority task already selected for this
+			 * core.
+			 */
+			p = pick_task(rq_i, class, max, fi_before);
+			if (!p)
+				continue;
+
+			if (!is_task_rq_idle(p))
+				occ++;
+
+			rq_i->core_pick = p;
+			if (rq_i->idle == p && rq_i->nr_running) {
+				rq->core->core_forceidle = true;
+				if (!fi_before)
+					rq->core->core_forceidle_seq++;
+			}
+
+			/*
+			 * If this new candidate is of higher priority than the
+			 * previous; and they're incompatible; we need to wipe
+			 * the slate and start over. pick_task makes sure that
+			 * p's priority is more than max if it doesn't match
+			 * max's cookie.
+			 *
+			 * NOTE: this is a linear max-filter and is thus bounded
+			 * in execution time.
+			 */
+			if (!max || !cookie_match(max, p)) {
+				struct task_struct *old_max = max;
+
+				rq->core->core_cookie = p->core_cookie;
+				max = p;
+
+				if (old_max) {
+					rq->core->core_forceidle = false;
+					for_each_cpu(j, smt_mask) {
+						if (j == i)
+							continue;
+
+						cpu_rq(j)->core_pick = NULL;
+					}
+					occ = 1;
+					goto again;
+				}
+			}
+		}
+	}
+
+	rq->core->core_pick_seq = rq->core->core_task_seq;
+	next = rq->core_pick;
+	rq->core_sched_seq = rq->core->core_pick_seq;
+
+	/* Something should have been selected for current CPU */
+	WARN_ON_ONCE(!next);
+
+	/*
+	 * Reschedule siblings
+	 *
+	 * NOTE: L1TF -- at this point we're no longer running the old task and
+	 * sending an IPI (below) ensures the sibling will no longer be running
+	 * their task. This ensures there is no inter-sibling overlap between
+	 * non-matching user state.
+	 */
+	for_each_cpu(i, smt_mask) {
+		struct rq *rq_i = cpu_rq(i);
+
+		/*
+		 * An online sibling might have gone offline before a task
+		 * could be picked for it, or it might be offline but later
+		 * happen to come online, but its too late and nothing was
+		 * picked for it.  That's Ok - it will pick tasks for itself,
+		 * so ignore it.
+		 */
+		if (!rq_i->core_pick)
+			continue;
+
+		/*
+		 * Update for new !FI->FI transitions, or if continuing to be in !FI:
+		 * fi_before     fi      update?
+		 *  0            0       1
+		 *  0            1       1
+		 *  1            0       1
+		 *  1            1       0
+		 */
+		if (!(fi_before && rq->core->core_forceidle))
+			task_vruntime_update(rq_i, rq_i->core_pick, rq->core->core_forceidle);
+
+		rq_i->core_pick->core_occupation = occ;
+
+		if (i == cpu) {
+			rq_i->core_pick = NULL;
+			continue;
+		}
+
+		/* Did we break L1TF mitigation requirements? */
+		WARN_ON_ONCE(!cookie_match(next, rq_i->core_pick));
+
+		if (rq_i->curr == rq_i->core_pick) {
+			rq_i->core_pick = NULL;
+			continue;
+		}
+
+		resched_curr(rq_i);
+	}
+
+done:
+	set_next_task(rq, next);
+	return next;
+}
+
+static bool try_steal_cookie(int this, int that)
+{
+	struct rq *dst = cpu_rq(this), *src = cpu_rq(that);
+	struct task_struct *p;
+	unsigned long cookie;
+	bool success = false;
+
+	local_irq_disable();
+	double_rq_lock(dst, src);
+
+	cookie = dst->core->core_cookie;
+	if (!cookie)
+		goto unlock;
+
+	if (dst->curr != dst->idle)
+		goto unlock;
+
+	p = sched_core_find(src, cookie);
+	if (p == src->idle)
+		goto unlock;
+
+	do {
+		if (p == src->core_pick || p == src->curr)
+			goto next;
+
+		if (!cpumask_test_cpu(this, &p->cpus_mask))
+			goto next;
+
+		if (p->core_occupation > dst->idle->core_occupation)
+			goto next;
+
+		p->on_rq = TASK_ON_RQ_MIGRATING;
+		deactivate_task(src, p, 0);
+		set_task_cpu(p, this);
+		activate_task(dst, p, 0);
+		p->on_rq = TASK_ON_RQ_QUEUED;
+
+		resched_curr(dst);
+
+		success = true;
+		break;
+
+next:
+		p = sched_core_next(p, cookie);
+	} while (p);
+
+unlock:
+	double_rq_unlock(dst, src);
+	local_irq_enable();
+
+	return success;
+}
+
+static bool steal_cookie_task(int cpu, struct sched_domain *sd)
+{
+	int i;
+
+	for_each_cpu_wrap(i, sched_domain_span(sd), cpu) {
+		if (i == cpu)
+			continue;
+
+		if (need_resched())
+			break;
+
+		if (try_steal_cookie(cpu, i))
+			return true;
+	}
+
+	return false;
+}
+
+static void sched_core_balance(struct rq *rq)
+{
+	struct sched_domain *sd;
+	int cpu = cpu_of(rq);
+
+	preempt_disable();
+	rcu_read_lock();
+	raw_spin_rq_unlock_irq(rq);
+	for_each_domain(cpu, sd) {
+		if (need_resched())
+			break;
+
+		if (steal_cookie_task(cpu, sd))
+			break;
+	}
+	raw_spin_rq_lock_irq(rq);
+	rcu_read_unlock();
+	preempt_enable();
+}
+
+static DEFINE_PER_CPU(struct callback_head, core_balance_head);
+
+void queue_core_balance(struct rq *rq)
+{
+	if (!sched_core_enabled(rq))
+		return;
+
+	if (!rq->core->core_cookie)
+		return;
+
+	if (!rq->nr_running) /* not forced idle */
+		return;
+
+	queue_balance_callback(rq, &per_cpu(core_balance_head, rq->cpu), sched_core_balance);
+}
+
+static inline void sched_core_cpu_starting(unsigned int cpu)
+{
+	const struct cpumask *smt_mask = cpu_smt_mask(cpu);
+	struct rq *rq, *core_rq = NULL;
+	int i;
+
+	core_rq = cpu_rq(cpu)->core;
+
+	if (!core_rq) {
+		for_each_cpu(i, smt_mask) {
+			rq = cpu_rq(i);
+			if (rq->core && rq->core == rq)
+				core_rq = rq;
+		}
+
+		if (!core_rq)
+			core_rq = cpu_rq(cpu);
+
+		for_each_cpu(i, smt_mask) {
+			rq = cpu_rq(i);
+
+			WARN_ON_ONCE(rq->core && rq->core != core_rq);
+			rq->core = core_rq;
+		}
+	}
+}
+#else /* !CONFIG_SCHED_CORE */
+
+static inline void sched_core_cpu_starting(unsigned int cpu) {}
+
+static struct task_struct *
+pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+{
+	return __pick_next_task(rq, prev, rf);
+}
+
+#endif /* CONFIG_SCHED_CORE */
+
 /*
  * __schedule() is the main scheduler function.
  *
@@ -5074,10 +5862,10 @@ static void __sched notrace __schedule(bool preempt)
 	 *  - we form a control dependency vs deactivate_task() below.
 	 *  - ptrace_{,un}freeze_traced() can change ->state underneath us.
 	 */
-	prev_state = prev->state;
+	prev_state = READ_ONCE(prev->__state);
 	if (!preempt && prev_state) {
 		if (signal_pending_state(prev_state, prev)) {
-			prev->state = TASK_RUNNING;
+			WRITE_ONCE(prev->__state, TASK_RUNNING);
 		} else {
 			prev->sched_contributes_to_load =
 				(prev_state & TASK_UNINTERRUPTIBLE) &&
@@ -5150,7 +5938,7 @@ static void __sched notrace __schedule(bool preempt)
 
 		rq_unpin_lock(rq, &rf);
 		__balance_callbacks(rq);
-		raw_spin_unlock_irq(&rq->lock);
+		raw_spin_rq_unlock_irq(rq);
 	}
 }
 
@@ -5174,7 +5962,7 @@ static inline void sched_submit_work(struct task_struct *tsk)
 {
 	unsigned int task_flags;
 
-	if (!tsk->state)
+	if (task_is_running(tsk))
 		return;
 
 	task_flags = tsk->flags;
@@ -5249,7 +6037,7 @@ void __sched schedule_idle(void)
 	 * current task can be in any other state. Note, idle is always in the
 	 * TASK_RUNNING state.
 	 */
-	WARN_ON_ONCE(current->state);
+	WARN_ON_ONCE(current->__state);
 	do {
 		__schedule(false);
 	} while (need_resched());
@@ -5692,7 +6480,7 @@ out_unlock:
 
 	rq_unpin_lock(rq, &rf);
 	__balance_callbacks(rq);
-	raw_spin_unlock(&rq->lock);
+	raw_spin_rq_unlock(rq);
 
 	preempt_enable();
 }
@@ -7148,7 +7936,7 @@ again:
 	if (curr->sched_class != p->sched_class)
 		goto out_unlock;
 
-	if (task_running(p_rq, p) || p->state)
+	if (task_running(p_rq, p) || !task_is_running(p))
 		goto out_unlock;
 
 	yielded = curr->sched_class->yield_to_task(rq, p);
@@ -7351,7 +8139,7 @@ void sched_show_task(struct task_struct *p)
 
 	pr_info("task:%-15.15s state:%c", p->comm, task_state_to_char(p));
 
-	if (p->state == TASK_RUNNING)
+	if (task_is_running(p))
 		pr_cont("  running task    ");
 #ifdef CONFIG_DEBUG_STACK_USAGE
 	free = stack_not_used(p);
@@ -7375,26 +8163,28 @@ EXPORT_SYMBOL_GPL(sched_show_task);
 static inline bool
 state_filter_match(unsigned long state_filter, struct task_struct *p)
 {
+	unsigned int state = READ_ONCE(p->__state);
+
 	/* no filter, everything matches */
 	if (!state_filter)
 		return true;
 
 	/* filter, but doesn't match */
-	if (!(p->state & state_filter))
+	if (!(state & state_filter))
 		return false;
 
 	/*
 	 * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows
 	 * TASK_KILLABLE).
 	 */
-	if (state_filter == TASK_UNINTERRUPTIBLE && p->state == TASK_IDLE)
+	if (state_filter == TASK_UNINTERRUPTIBLE && state == TASK_IDLE)
 		return false;
 
 	return true;
 }
 
 
-void show_state_filter(unsigned long state_filter)
+void show_state_filter(unsigned int state_filter)
 {
 	struct task_struct *g, *p;
 
@@ -7433,19 +8223,32 @@ void show_state_filter(unsigned long state_filter)
  * NOTE: this function does not set the idle thread's NEED_RESCHED
  * flag, to make booting more robust.
  */
-void init_idle(struct task_struct *idle, int cpu)
+void __init init_idle(struct task_struct *idle, int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long flags;
 
 	__sched_fork(0, idle);
 
+	/*
+	 * The idle task doesn't need the kthread struct to function, but it
+	 * is dressed up as a per-CPU kthread and thus needs to play the part
+	 * if we want to avoid special-casing it in code that deals with per-CPU
+	 * kthreads.
+	 */
+	set_kthread_struct(idle);
+
 	raw_spin_lock_irqsave(&idle->pi_lock, flags);
-	raw_spin_lock(&rq->lock);
+	raw_spin_rq_lock(rq);
 
-	idle->state = TASK_RUNNING;
+	idle->__state = TASK_RUNNING;
 	idle->se.exec_start = sched_clock();
-	idle->flags |= PF_IDLE;
+	/*
+	 * PF_KTHREAD should already be set at this point; regardless, make it
+	 * look like a proper per-CPU kthread.
+	 */
+	idle->flags |= PF_IDLE | PF_KTHREAD | PF_NO_SETAFFINITY;
+	kthread_set_per_cpu(idle, cpu);
 
 	scs_task_reset(idle);
 	kasan_unpoison_task_stack(idle);
@@ -7479,7 +8282,7 @@ void init_idle(struct task_struct *idle, int cpu)
 #ifdef CONFIG_SMP
 	idle->on_cpu = 1;
 #endif
-	raw_spin_unlock(&rq->lock);
+	raw_spin_rq_unlock(rq);
 	raw_spin_unlock_irqrestore(&idle->pi_lock, flags);
 
 	/* Set the preempt count _outside_ the spinlocks! */
@@ -7645,7 +8448,7 @@ static void balance_push(struct rq *rq)
 {
 	struct task_struct *push_task = rq->curr;
 
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 	SCHED_WARN_ON(rq->cpu != smp_processor_id());
 
 	/*
@@ -7662,12 +8465,8 @@ static void balance_push(struct rq *rq)
 	/*
 	 * Both the cpu-hotplug and stop task are in this case and are
 	 * required to complete the hotplug process.
-	 *
-	 * XXX: the idle task does not match kthread_is_per_cpu() due to
-	 * histerical raisins.
 	 */
-	if (rq->idle == push_task ||
-	    kthread_is_per_cpu(push_task) ||
+	if (kthread_is_per_cpu(push_task) ||
 	    is_migration_disabled(push_task)) {
 
 		/*
@@ -7683,9 +8482,9 @@ static void balance_push(struct rq *rq)
 		 */
 		if (!rq->nr_running && !rq_has_pinned_tasks(rq) &&
 		    rcuwait_active(&rq->hotplug_wait)) {
-			raw_spin_unlock(&rq->lock);
+			raw_spin_rq_unlock(rq);
 			rcuwait_wake_up(&rq->hotplug_wait);
-			raw_spin_lock(&rq->lock);
+			raw_spin_rq_lock(rq);
 		}
 		return;
 	}
@@ -7695,7 +8494,7 @@ static void balance_push(struct rq *rq)
 	 * Temporarily drop rq->lock such that we can wake-up the stop task.
 	 * Both preemption and IRQs are still disabled.
 	 */
-	raw_spin_unlock(&rq->lock);
+	raw_spin_rq_unlock(rq);
 	stop_one_cpu_nowait(rq->cpu, __balance_push_cpu_stop, push_task,
 			    this_cpu_ptr(&push_work));
 	/*
@@ -7703,7 +8502,7 @@ static void balance_push(struct rq *rq)
 	 * schedule(). The next pick is obviously going to be the stop task
 	 * which kthread_is_per_cpu() and will push this task away.
 	 */
-	raw_spin_lock(&rq->lock);
+	raw_spin_rq_lock(rq);
 }
 
 static void balance_push_set(int cpu, bool on)
@@ -7947,6 +8746,7 @@ static void sched_rq_cpu_starting(unsigned int cpu)
 
 int sched_cpu_starting(unsigned int cpu)
 {
+	sched_core_cpu_starting(cpu);
 	sched_rq_cpu_starting(cpu);
 	sched_tick_start(cpu);
 	return 0;
@@ -7993,7 +8793,7 @@ static void dump_rq_tasks(struct rq *rq, const char *loglvl)
 	struct task_struct *g, *p;
 	int cpu = cpu_of(rq);
 
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 
 	printk("%sCPU%d enqueued tasks (%u total):\n", loglvl, cpu, rq->nr_running);
 	for_each_process_thread(g, p) {
@@ -8045,6 +8845,7 @@ void __init sched_init_smp(void)
 	/* Move init over to a non-isolated CPU */
 	if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0)
 		BUG();
+	current->flags &= ~PF_NO_SETAFFINITY;
 	sched_init_granularity();
 
 	init_sched_rt_class();
@@ -8166,7 +8967,7 @@ void __init sched_init(void)
 		struct rq *rq;
 
 		rq = cpu_rq(i);
-		raw_spin_lock_init(&rq->lock);
+		raw_spin_lock_init(&rq->__lock);
 		rq->nr_running = 0;
 		rq->calc_load_active = 0;
 		rq->calc_load_update = jiffies + LOAD_FREQ;
@@ -8214,6 +9015,8 @@ void __init sched_init(void)
 		rq->online = 0;
 		rq->idle_stamp = 0;
 		rq->avg_idle = 2*sysctl_sched_migration_cost;
+		rq->wake_stamp = jiffies;
+		rq->wake_avg_idle = rq->avg_idle;
 		rq->max_idle_balance_cost = sysctl_sched_migration_cost;
 
 		INIT_LIST_HEAD(&rq->cfs_tasks);
@@ -8231,6 +9034,16 @@ void __init sched_init(void)
 #endif /* CONFIG_SMP */
 		hrtick_rq_init(rq);
 		atomic_set(&rq->nr_iowait, 0);
+
+#ifdef CONFIG_SCHED_CORE
+		rq->core = NULL;
+		rq->core_pick = NULL;
+		rq->core_enabled = 0;
+		rq->core_tree = RB_ROOT;
+		rq->core_forceidle = false;
+
+		rq->core_cookie = 0UL;
+#endif
 	}
 
 	set_load_weight(&init_task, false);
@@ -8257,8 +9070,6 @@ void __init sched_init(void)
 #endif
 	init_sched_fair_class();
 
-	init_schedstats();
-
 	psi_init();
 
 	init_uclamp();
@@ -8276,15 +9087,15 @@ static inline int preempt_count_equals(int preempt_offset)
 
 void __might_sleep(const char *file, int line, int preempt_offset)
 {
+	unsigned int state = get_current_state();
 	/*
 	 * Blocking primitives will set (and therefore destroy) current->state,
 	 * since we will exit with TASK_RUNNING make sure we enter with it,
 	 * otherwise we will destroy state.
 	 */
-	WARN_ONCE(current->state != TASK_RUNNING && current->task_state_change,
+	WARN_ONCE(state != TASK_RUNNING && current->task_state_change,
 			"do not call blocking ops when !TASK_RUNNING; "
-			"state=%lx set at [<%p>] %pS\n",
-			current->state,
+			"state=%x set at [<%p>] %pS\n", state,
 			(void *)current->task_state_change,
 			(void *)current->task_state_change);
 
@@ -8680,7 +9491,11 @@ static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
 
 #ifdef CONFIG_UCLAMP_TASK_GROUP
 	/* Propagate the effective uclamp value for the new group */
+	mutex_lock(&uclamp_mutex);
+	rcu_read_lock();
 	cpu_util_update_eff(css);
+	rcu_read_unlock();
+	mutex_unlock(&uclamp_mutex);
 #endif
 
 	return 0;
@@ -8741,7 +9556,7 @@ static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
 		 * has happened. This would lead to problems with PELT, due to
 		 * move wanting to detach+attach while we're not attached yet.
 		 */
-		if (task->state == TASK_NEW)
+		if (READ_ONCE(task->__state) == TASK_NEW)
 			ret = -EINVAL;
 		raw_spin_unlock_irq(&task->pi_lock);
 
@@ -8770,6 +9585,9 @@ static void cpu_util_update_eff(struct cgroup_subsys_state *css)
 	enum uclamp_id clamp_id;
 	unsigned int clamps;
 
+	lockdep_assert_held(&uclamp_mutex);
+	SCHED_WARN_ON(!rcu_read_lock_held());
+
 	css_for_each_descendant_pre(css, top_css) {
 		uc_parent = css_tg(css)->parent
 			? css_tg(css)->parent->uclamp : NULL;
@@ -8802,7 +9620,7 @@ static void cpu_util_update_eff(struct cgroup_subsys_state *css)
 		}
 
 		/* Immediately update descendants RUNNABLE tasks */
-		uclamp_update_active_tasks(css, clamps);
+		uclamp_update_active_tasks(css);
 	}
 }
 
@@ -8961,7 +9779,8 @@ static const u64 max_cfs_runtime = MAX_BW * NSEC_PER_USEC;
 
 static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime);
 
-static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
+static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota,
+				u64 burst)
 {
 	int i, ret = 0, runtime_enabled, runtime_was_enabled;
 	struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
@@ -8991,6 +9810,10 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
 	if (quota != RUNTIME_INF && quota > max_cfs_runtime)
 		return -EINVAL;
 
+	if (quota != RUNTIME_INF && (burst > quota ||
+				     burst + quota > max_cfs_runtime))
+		return -EINVAL;
+
 	/*
 	 * Prevent race between setting of cfs_rq->runtime_enabled and
 	 * unthrottle_offline_cfs_rqs().
@@ -9012,6 +9835,7 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
 	raw_spin_lock_irq(&cfs_b->lock);
 	cfs_b->period = ns_to_ktime(period);
 	cfs_b->quota = quota;
+	cfs_b->burst = burst;
 
 	__refill_cfs_bandwidth_runtime(cfs_b);
 
@@ -9045,9 +9869,10 @@ out_unlock:
 
 static int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
 {
-	u64 quota, period;
+	u64 quota, period, burst;
 
 	period = ktime_to_ns(tg->cfs_bandwidth.period);
+	burst = tg->cfs_bandwidth.burst;
 	if (cfs_quota_us < 0)
 		quota = RUNTIME_INF;
 	else if ((u64)cfs_quota_us <= U64_MAX / NSEC_PER_USEC)
@@ -9055,7 +9880,7 @@ static int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
 	else
 		return -EINVAL;
 
-	return tg_set_cfs_bandwidth(tg, period, quota);
+	return tg_set_cfs_bandwidth(tg, period, quota, burst);
 }
 
 static long tg_get_cfs_quota(struct task_group *tg)
@@ -9073,15 +9898,16 @@ static long tg_get_cfs_quota(struct task_group *tg)
 
 static int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
 {
-	u64 quota, period;
+	u64 quota, period, burst;
 
 	if ((u64)cfs_period_us > U64_MAX / NSEC_PER_USEC)
 		return -EINVAL;
 
 	period = (u64)cfs_period_us * NSEC_PER_USEC;
 	quota = tg->cfs_bandwidth.quota;
+	burst = tg->cfs_bandwidth.burst;
 
-	return tg_set_cfs_bandwidth(tg, period, quota);
+	return tg_set_cfs_bandwidth(tg, period, quota, burst);
 }
 
 static long tg_get_cfs_period(struct task_group *tg)
@@ -9094,6 +9920,30 @@ static long tg_get_cfs_period(struct task_group *tg)
 	return cfs_period_us;
 }
 
+static int tg_set_cfs_burst(struct task_group *tg, long cfs_burst_us)
+{
+	u64 quota, period, burst;
+
+	if ((u64)cfs_burst_us > U64_MAX / NSEC_PER_USEC)
+		return -EINVAL;
+
+	burst = (u64)cfs_burst_us * NSEC_PER_USEC;
+	period = ktime_to_ns(tg->cfs_bandwidth.period);
+	quota = tg->cfs_bandwidth.quota;
+
+	return tg_set_cfs_bandwidth(tg, period, quota, burst);
+}
+
+static long tg_get_cfs_burst(struct task_group *tg)
+{
+	u64 burst_us;
+
+	burst_us = tg->cfs_bandwidth.burst;
+	do_div(burst_us, NSEC_PER_USEC);
+
+	return burst_us;
+}
+
 static s64 cpu_cfs_quota_read_s64(struct cgroup_subsys_state *css,
 				  struct cftype *cft)
 {
@@ -9118,6 +9968,18 @@ static int cpu_cfs_period_write_u64(struct cgroup_subsys_state *css,
 	return tg_set_cfs_period(css_tg(css), cfs_period_us);
 }
 
+static u64 cpu_cfs_burst_read_u64(struct cgroup_subsys_state *css,
+				  struct cftype *cft)
+{
+	return tg_get_cfs_burst(css_tg(css));
+}
+
+static int cpu_cfs_burst_write_u64(struct cgroup_subsys_state *css,
+				   struct cftype *cftype, u64 cfs_burst_us)
+{
+	return tg_set_cfs_burst(css_tg(css), cfs_burst_us);
+}
+
 struct cfs_schedulable_data {
 	struct task_group *tg;
 	u64 period, quota;
@@ -9271,6 +10133,11 @@ static struct cftype cpu_legacy_files[] = {
 		.write_u64 = cpu_cfs_period_write_u64,
 	},
 	{
+		.name = "cfs_burst_us",
+		.read_u64 = cpu_cfs_burst_read_u64,
+		.write_u64 = cpu_cfs_burst_write_u64,
+	},
+	{
 		.name = "stat",
 		.seq_show = cpu_cfs_stat_show,
 	},
@@ -9435,12 +10302,13 @@ static ssize_t cpu_max_write(struct kernfs_open_file *of,
 {
 	struct task_group *tg = css_tg(of_css(of));
 	u64 period = tg_get_cfs_period(tg);
+	u64 burst = tg_get_cfs_burst(tg);
 	u64 quota;
 	int ret;
 
 	ret = cpu_period_quota_parse(buf, &period, &quota);
 	if (!ret)
-		ret = tg_set_cfs_bandwidth(tg, period, quota);
+		ret = tg_set_cfs_bandwidth(tg, period, quota, burst);
 	return ret ?: nbytes;
 }
 #endif
@@ -9467,6 +10335,12 @@ static struct cftype cpu_files[] = {
 		.seq_show = cpu_max_show,
 		.write = cpu_max_write,
 	},
+	{
+		.name = "max.burst",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_u64 = cpu_cfs_burst_read_u64,
+		.write_u64 = cpu_cfs_burst_write_u64,
+	},
 #endif
 #ifdef CONFIG_UCLAMP_TASK_GROUP
 	{