Linux-libre 4.5-gnu

14 files changed, 1410 insertions, 848 deletions

diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 67687973c..7d4cba227 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -13,7 +13,7 @@ endif
 
 obj-y += core.o loadavg.o clock.o cputime.o
 obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
-obj-y += wait.o completion.o idle.o
+obj-y += wait.o swait.o completion.o idle.o
 obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index 750ed601d..a5d966cb8 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -212,7 +212,7 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice)
 	ag = autogroup_task_get(p);
 
 	down_write(&ag->lock);
-	err = sched_group_set_shares(ag->tg, prio_to_weight[nice + 20]);
+	err = sched_group_set_shares(ag->tg, sched_prio_to_weight[nice + 20]);
 	if (!err)
 		ag->nice = nice;
 	up_write(&ag->lock);
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index caf4041f5..bc54e8467 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -354,7 +354,7 @@ void sched_clock_idle_wakeup_event(u64 delta_ns)
 		return;
 
 	sched_clock_tick();
-	touch_softlockup_watchdog();
+	touch_softlockup_watchdog_sched();
 }
 EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index eb70592f0..05114b15b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -26,6 +26,7 @@
  *              Thomas Gleixner, Mike Kravetz
  */
 
+#include <linux/kasan.h>
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/nmi.h>
@@ -66,12 +67,10 @@
 #include <linux/pagemap.h>
 #include <linux/hrtimer.h>
 #include <linux/tick.h>
-#include <linux/debugfs.h>
 #include <linux/ctype.h>
 #include <linux/ftrace.h>
 #include <linux/slab.h>
 #include <linux/init_task.h>
-#include <linux/binfmts.h>
 #include <linux/context_tracking.h>
 #include <linux/compiler.h>
 
@@ -124,138 +123,6 @@ const_debug unsigned int sysctl_sched_features =
 
 #undef SCHED_FEAT
 
-#ifdef CONFIG_SCHED_DEBUG
-#define SCHED_FEAT(name, enabled)	\
-	#name ,
-
-static const char * const sched_feat_names[] = {
-#include "features.h"
-};
-
-#undef SCHED_FEAT
-
-static int sched_feat_show(struct seq_file *m, void *v)
-{
-	int i;
-
-	for (i = 0; i < __SCHED_FEAT_NR; i++) {
-		if (!(sysctl_sched_features & (1UL << i)))
-			seq_puts(m, "NO_");
-		seq_printf(m, "%s ", sched_feat_names[i]);
-	}
-	seq_puts(m, "\n");
-
-	return 0;
-}
-
-#ifdef HAVE_JUMP_LABEL
-
-#define jump_label_key__true  STATIC_KEY_INIT_TRUE
-#define jump_label_key__false STATIC_KEY_INIT_FALSE
-
-#define SCHED_FEAT(name, enabled)	\
-	jump_label_key__##enabled ,
-
-struct static_key sched_feat_keys[__SCHED_FEAT_NR] = {
-#include "features.h"
-};
-
-#undef SCHED_FEAT
-
-static void sched_feat_disable(int i)
-{
-	static_key_disable(&sched_feat_keys[i]);
-}
-
-static void sched_feat_enable(int i)
-{
-	static_key_enable(&sched_feat_keys[i]);
-}
-#else
-static void sched_feat_disable(int i) { };
-static void sched_feat_enable(int i) { };
-#endif /* HAVE_JUMP_LABEL */
-
-static int sched_feat_set(char *cmp)
-{
-	int i;
-	int neg = 0;
-
-	if (strncmp(cmp, "NO_", 3) == 0) {
-		neg = 1;
-		cmp += 3;
-	}
-
-	for (i = 0; i < __SCHED_FEAT_NR; i++) {
-		if (strcmp(cmp, sched_feat_names[i]) == 0) {
-			if (neg) {
-				sysctl_sched_features &= ~(1UL << i);
-				sched_feat_disable(i);
-			} else {
-				sysctl_sched_features |= (1UL << i);
-				sched_feat_enable(i);
-			}
-			break;
-		}
-	}
-
-	return i;
-}
-
-static ssize_t
-sched_feat_write(struct file *filp, const char __user *ubuf,
-		size_t cnt, loff_t *ppos)
-{
-	char buf[64];
-	char *cmp;
-	int i;
-	struct inode *inode;
-
-	if (cnt > 63)
-		cnt = 63;
-
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-
-	buf[cnt] = 0;
-	cmp = strstrip(buf);
-
-	/* Ensure the static_key remains in a consistent state */
-	inode = file_inode(filp);
-	mutex_lock(&inode->i_mutex);
-	i = sched_feat_set(cmp);
-	mutex_unlock(&inode->i_mutex);
-	if (i == __SCHED_FEAT_NR)
-		return -EINVAL;
-
-	*ppos += cnt;
-
-	return cnt;
-}
-
-static int sched_feat_open(struct inode *inode, struct file *filp)
-{
-	return single_open(filp, sched_feat_show, NULL);
-}
-
-static const struct file_operations sched_feat_fops = {
-	.open		= sched_feat_open,
-	.write		= sched_feat_write,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static __init int sched_init_debug(void)
-{
-	debugfs_create_file("sched_features", 0644, NULL, NULL,
-			&sched_feat_fops);
-
-	return 0;
-}
-late_initcall(sched_init_debug);
-#endif /* CONFIG_SCHED_DEBUG */
-
 /*
  * Number of tasks to iterate in a single balance run.
  * Limited because this is done with IRQs disabled.
@@ -731,7 +598,7 @@ bool sched_can_stop_tick(void)
 	if (current->policy == SCHED_RR) {
 		struct sched_rt_entity *rt_se = &current->rt;
 
-		return rt_se->run_list.prev == rt_se->run_list.next;
+		return list_is_singular(&rt_se->run_list);
 	}
 
 	/*
@@ -823,8 +690,8 @@ static void set_load_weight(struct task_struct *p)
 		return;
 	}
 
-	load->weight = scale_load(prio_to_weight[prio]);
-	load->inv_weight = prio_to_wmult[prio];
+	load->weight = scale_load(sched_prio_to_weight[prio]);
+	load->inv_weight = sched_prio_to_wmult[prio];
 }
 
 static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
@@ -1071,8 +938,8 @@ static struct rq *move_queued_task(struct rq *rq, struct task_struct *p, int new
 {
 	lockdep_assert_held(&rq->lock);
 
-	dequeue_task(rq, p, 0);
 	p->on_rq = TASK_ON_RQ_MIGRATING;
+	dequeue_task(rq, p, 0);
 	set_task_cpu(p, new_cpu);
 	raw_spin_unlock(&rq->lock);
 
@@ -1080,8 +947,8 @@ static struct rq *move_queued_task(struct rq *rq, struct task_struct *p, int new
 
 	raw_spin_lock(&rq->lock);
 	BUG_ON(task_cpu(p) != new_cpu);
-	p->on_rq = TASK_ON_RQ_QUEUED;
 	enqueue_task(rq, p, 0);
+	p->on_rq = TASK_ON_RQ_QUEUED;
 	check_preempt_curr(rq, p, 0);
 
 	return rq;
@@ -1274,6 +1141,15 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	WARN_ON_ONCE(p->state != TASK_RUNNING && p->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 &&
+		     p->sched_class == &fair_sched_class &&
+		     (p->on_rq && !task_on_rq_migrating(p)));
+
 #ifdef CONFIG_LOCKDEP
 	/*
 	 * The caller should hold either p->pi_lock or rq->lock, when changing
@@ -1310,9 +1186,11 @@ static void __migrate_swap_task(struct task_struct *p, int cpu)
 		src_rq = task_rq(p);
 		dst_rq = cpu_rq(cpu);
 
+		p->on_rq = TASK_ON_RQ_MIGRATING;
 		deactivate_task(src_rq, p, 0);
 		set_task_cpu(p, cpu);
 		activate_task(dst_rq, p, 0);
+		p->on_rq = TASK_ON_RQ_QUEUED;
 		check_preempt_curr(dst_rq, p, 0);
 	} else {
 		/*
@@ -1905,6 +1783,97 @@ static void ttwu_queue(struct task_struct *p, int cpu)
 	raw_spin_unlock(&rq->lock);
 }
 
+/*
+ * Notes on Program-Order guarantees on SMP systems.
+ *
+ *  MIGRATION
+ *
+ * The basic program-order guarantee on SMP systems is that when a task [t]
+ * migrates, all its activity on its old cpu [c0] happens-before any subsequent
+ * execution on its new cpu [c1].
+ *
+ * For migration (of runnable tasks) this is provided by the following means:
+ *
+ *  A) UNLOCK of the rq(c0)->lock scheduling out task t
+ *  B) migration for t is required to synchronize *both* rq(c0)->lock and
+ *     rq(c1)->lock (if not at the same time, then in that order).
+ *  C) LOCK of the rq(c1)->lock scheduling in task
+ *
+ * Transitivity guarantees that B happens after A and C after B.
+ * Note: we only require RCpc transitivity.
+ * Note: the cpu doing B need not be c0 or c1
+ *
+ * Example:
+ *
+ *   CPU0            CPU1            CPU2
+ *
+ *   LOCK rq(0)->lock
+ *   sched-out X
+ *   sched-in Y
+ *   UNLOCK rq(0)->lock
+ *
+ *                                   LOCK rq(0)->lock // orders against CPU0
+ *                                   dequeue X
+ *                                   UNLOCK rq(0)->lock
+ *
+ *                                   LOCK rq(1)->lock
+ *                                   enqueue X
+ *                                   UNLOCK rq(1)->lock
+ *
+ *                   LOCK rq(1)->lock // orders against CPU2
+ *                   sched-out Z
+ *                   sched-in X
+ *                   UNLOCK rq(1)->lock
+ *
+ *
+ *  BLOCKING -- aka. SLEEP + WAKEUP
+ *
+ * For blocking we (obviously) need to provide the same guarantee as for
+ * migration. However the means are completely different as there is no lock
+ * chain to provide order. Instead we do:
+ *
+ *   1) smp_store_release(X->on_cpu, 0)
+ *   2) smp_cond_acquire(!X->on_cpu)
+ *
+ * Example:
+ *
+ *   CPU0 (schedule)  CPU1 (try_to_wake_up) CPU2 (schedule)
+ *
+ *   LOCK rq(0)->lock LOCK X->pi_lock
+ *   dequeue X
+ *   sched-out X
+ *   smp_store_release(X->on_cpu, 0);
+ *
+ *                    smp_cond_acquire(!X->on_cpu);
+ *                    X->state = WAKING
+ *                    set_task_cpu(X,2)
+ *
+ *                    LOCK rq(2)->lock
+ *                    enqueue X
+ *                    X->state = RUNNING
+ *                    UNLOCK rq(2)->lock
+ *
+ *                                          LOCK rq(2)->lock // orders against CPU1
+ *                                          sched-out Z
+ *                                          sched-in X
+ *                                          UNLOCK rq(2)->lock
+ *
+ *                    UNLOCK X->pi_lock
+ *   UNLOCK rq(0)->lock
+ *
+ *
+ * However; for wakeups there is a second guarantee we must provide, namely we
+ * must observe the state that lead to our wakeup. That is, not only must our
+ * task observe its own prior state, it must also observe the stores prior to
+ * its wakeup.
+ *
+ * This means that any means of doing remote wakeups must order the CPU doing
+ * the wakeup against the CPU the task is going to end up running on. This,
+ * however, is already required for the regular Program-Order guarantee above,
+ * since the waking CPU is the one issueing the ACQUIRE (smp_cond_acquire).
+ *
+ */
+
 /**
  * try_to_wake_up - wake up a thread
  * @p: the thread to be awakened
@@ -1968,19 +1937,13 @@ 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.
-	 */
-	while (p->on_cpu)
-		cpu_relax();
-	/*
-	 * Combined with the control dependency above, we have an effective
-	 * smp_load_acquire() without the need for full barriers.
 	 *
 	 * Pairs with the smp_store_release() in finish_lock_switch().
 	 *
 	 * This ensures that tasks getting woken will be fully ordered against
 	 * their previous state and preserve Program Order.
 	 */
-	smp_rmb();
+	smp_cond_acquire(!p->on_cpu);
 
 	p->sched_contributes_to_load = !!task_contributes_to_load(p);
 	p->state = TASK_WAKING;
@@ -1997,7 +1960,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 
 	ttwu_queue(p, cpu);
 stat:
-	ttwu_stat(p, cpu, wake_flags);
+	if (schedstat_enabled())
+		ttwu_stat(p, cpu, wake_flags);
 out:
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
@@ -2045,7 +2009,8 @@ static void try_to_wake_up_local(struct task_struct *p)
 		ttwu_activate(rq, p, ENQUEUE_WAKEUP);
 
 	ttwu_do_wakeup(rq, p, 0);
-	ttwu_stat(p, smp_processor_id(), 0);
+	if (schedstat_enabled())
+		ttwu_stat(p, smp_processor_id(), 0);
 out:
 	raw_spin_unlock(&p->pi_lock);
 }
@@ -2087,7 +2052,6 @@ void __dl_clear_params(struct task_struct *p)
 	dl_se->dl_bw = 0;
 
 	dl_se->dl_throttled = 0;
-	dl_se->dl_new = 1;
 	dl_se->dl_yielded = 0;
 }
 
@@ -2109,7 +2073,12 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->se.vruntime			= 0;
 	INIT_LIST_HEAD(&p->se.group_node);
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	p->se.cfs_rq			= NULL;
+#endif
+
 #ifdef CONFIG_SCHEDSTATS
+	/* Even if schedstat is disabled, there should not be garbage */
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
 
@@ -2118,6 +2087,10 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	__dl_clear_params(p);
 
 	INIT_LIST_HEAD(&p->rt.run_list);
+	p->rt.timeout		= 0;
+	p->rt.time_slice	= sched_rr_timeslice;
+	p->rt.on_rq		= 0;
+	p->rt.on_list		= 0;
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 	INIT_HLIST_HEAD(&p->preempt_notifiers);
@@ -2181,6 +2154,69 @@ int sysctl_numa_balancing(struct ctl_table *table, int write,
 #endif
 #endif
 
+DEFINE_STATIC_KEY_FALSE(sched_schedstats);
+
+#ifdef CONFIG_SCHEDSTATS
+static void set_schedstats(bool enabled)
+{
+	if (enabled)
+		static_branch_enable(&sched_schedstats);
+	else
+		static_branch_disable(&sched_schedstats);
+}
+
+void force_schedstat_enabled(void)
+{
+	if (!schedstat_enabled()) {
+		pr_info("kernel profiling enabled schedstats, disable via kernel.sched_schedstats.\n");
+		static_branch_enable(&sched_schedstats);
+	}
+}
+
+static int __init setup_schedstats(char *str)
+{
+	int ret = 0;
+	if (!str)
+		goto out;
+
+	if (!strcmp(str, "enable")) {
+		set_schedstats(true);
+		ret = 1;
+	} else if (!strcmp(str, "disable")) {
+		set_schedstats(false);
+		ret = 1;
+	}
+out:
+	if (!ret)
+		pr_warn("Unable to parse schedstats=\n");
+
+	return ret;
+}
+__setup("schedstats=", setup_schedstats);
+
+#ifdef CONFIG_PROC_SYSCTL
+int sysctl_schedstats(struct ctl_table *table, int write,
+			 void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table t;
+	int err;
+	int state = static_branch_likely(&sched_schedstats);
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	t = *table;
+	t.data = &state;
+	err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
+	if (err < 0)
+		return err;
+	if (write)
+		set_schedstats(state);
+	return err;
+}
+#endif
+#endif
+
 /*
  * fork()/clone()-time setup:
  */
@@ -2910,16 +2946,6 @@ u64 scheduler_tick_max_deferment(void)
 }
 #endif
 
-notrace unsigned long get_parent_ip(unsigned long addr)
-{
-	if (in_lock_functions(addr)) {
-		addr = CALLER_ADDR2;
-		if (in_lock_functions(addr))
-			addr = CALLER_ADDR3;
-	}
-	return addr;
-}
-
 #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
 				defined(CONFIG_PREEMPT_TRACER))
 
@@ -2941,7 +2967,7 @@ void preempt_count_add(int val)
 				PREEMPT_MASK - 10);
 #endif
 	if (preempt_count() == val) {
-		unsigned long ip = get_parent_ip(CALLER_ADDR1);
+		unsigned long ip = get_lock_parent_ip();
 #ifdef CONFIG_DEBUG_PREEMPT
 		current->preempt_disable_ip = ip;
 #endif
@@ -2968,7 +2994,7 @@ void preempt_count_sub(int val)
 #endif
 
 	if (preempt_count() == val)
-		trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
+		trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip());
 	__preempt_count_sub(val);
 }
 EXPORT_SYMBOL(preempt_count_sub);
@@ -3109,7 +3135,6 @@ static void __sched notrace __schedule(bool preempt)
 
 	cpu = smp_processor_id();
 	rq = cpu_rq(cpu);
-	rcu_note_context_switch();
 	prev = rq->curr;
 
 	/*
@@ -3128,13 +3153,16 @@ static void __sched notrace __schedule(bool preempt)
 	if (sched_feat(HRTICK))
 		hrtick_clear(rq);
 
+	local_irq_disable();
+	rcu_note_context_switch();
+
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below
 	 * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
 	 * done by the caller to avoid the race with signal_wake_up().
 	 */
 	smp_mb__before_spinlock();
-	raw_spin_lock_irq(&rq->lock);
+	raw_spin_lock(&rq->lock);
 	lockdep_pin_lock(&rq->lock);
 
 	rq->clock_skip_update <<= 1; /* promote REQ to ACT */
@@ -3178,7 +3206,6 @@ static void __sched notrace __schedule(bool preempt)
 
 		trace_sched_switch(preempt, prev, next);
 		rq = context_switch(rq, prev, next); /* unlocks the rq */
-		cpu = cpu_of(rq);
 	} else {
 		lockdep_unpin_lock(&rq->lock);
 		raw_spin_unlock_irq(&rq->lock);
@@ -3364,7 +3391,7 @@ EXPORT_SYMBOL(default_wake_function);
  */
 void rt_mutex_setprio(struct task_struct *p, int prio)
 {
-	int oldprio, queued, running, enqueue_flag = ENQUEUE_RESTORE;
+	int oldprio, queued, running, queue_flag = DEQUEUE_SAVE | DEQUEUE_MOVE;
 	struct rq *rq;
 	const struct sched_class *prev_class;
 
@@ -3392,11 +3419,15 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
 	trace_sched_pi_setprio(p, prio);
 	oldprio = p->prio;
+
+	if (oldprio == prio)
+		queue_flag &= ~DEQUEUE_MOVE;
+
 	prev_class = p->sched_class;
 	queued = task_on_rq_queued(p);
 	running = task_current(rq, p);
 	if (queued)
-		dequeue_task(rq, p, DEQUEUE_SAVE);
+		dequeue_task(rq, p, queue_flag);
 	if (running)
 		put_prev_task(rq, p);
 
@@ -3414,7 +3445,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 		if (!dl_prio(p->normal_prio) ||
 		    (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
 			p->dl.dl_boosted = 1;
-			enqueue_flag |= ENQUEUE_REPLENISH;
+			queue_flag |= ENQUEUE_REPLENISH;
 		} else
 			p->dl.dl_boosted = 0;
 		p->sched_class = &dl_sched_class;
@@ -3422,7 +3453,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 		if (dl_prio(oldprio))
 			p->dl.dl_boosted = 0;
 		if (oldprio < prio)
-			enqueue_flag |= ENQUEUE_HEAD;
+			queue_flag |= ENQUEUE_HEAD;
 		p->sched_class = &rt_sched_class;
 	} else {
 		if (dl_prio(oldprio))
@@ -3437,7 +3468,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	if (running)
 		p->sched_class->set_curr_task(rq);
 	if (queued)
-		enqueue_task(rq, p, enqueue_flag);
+		enqueue_task(rq, p, queue_flag);
 
 	check_class_changed(rq, p, prev_class, oldprio);
 out_unlock:
@@ -3793,6 +3824,7 @@ static int __sched_setscheduler(struct task_struct *p,
 	const struct sched_class *prev_class;
 	struct rq *rq;
 	int reset_on_fork;
+	int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE;
 
 	/* may grab non-irq protected spin_locks */
 	BUG_ON(in_interrupt());
@@ -3975,17 +4007,14 @@ change:
 		 * itself.
 		 */
 		new_effective_prio = rt_mutex_get_effective_prio(p, newprio);
-		if (new_effective_prio == oldprio) {
-			__setscheduler_params(p, attr);
-			task_rq_unlock(rq, p, &flags);
-			return 0;
-		}
+		if (new_effective_prio == oldprio)
+			queue_flags &= ~DEQUEUE_MOVE;
 	}
 
 	queued = task_on_rq_queued(p);
 	running = task_current(rq, p);
 	if (queued)
-		dequeue_task(rq, p, DEQUEUE_SAVE);
+		dequeue_task(rq, p, queue_flags);
 	if (running)
 		put_prev_task(rq, p);
 
@@ -3995,15 +4024,14 @@ change:
 	if (running)
 		p->sched_class->set_curr_task(rq);
 	if (queued) {
-		int enqueue_flags = ENQUEUE_RESTORE;
 		/*
 		 * We enqueue to tail when the priority of a task is
 		 * increased (user space view).
 		 */
-		if (oldprio <= p->prio)
-			enqueue_flags |= ENQUEUE_HEAD;
+		if (oldprio < p->prio)
+			queue_flags |= ENQUEUE_HEAD;
 
-		enqueue_task(rq, p, enqueue_flags);
+		enqueue_task(rq, p, queue_flags);
 	}
 
 	check_class_changed(rq, p, prev_class, oldprio);
@@ -4994,6 +5022,8 @@ void init_idle(struct task_struct *idle, int cpu)
 	idle->state = TASK_RUNNING;
 	idle->se.exec_start = sched_clock();
 
+	kasan_unpoison_task_stack(idle);
+
 #ifdef CONFIG_SMP
 	/*
 	 * Its possible that init_idle() gets called multiple times on a task,
@@ -5303,183 +5333,6 @@ static void migrate_tasks(struct rq *dead_rq)
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
-#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
-
-static struct ctl_table sd_ctl_dir[] = {
-	{
-		.procname	= "sched_domain",
-		.mode		= 0555,
-	},
-	{}
-};
-
-static struct ctl_table sd_ctl_root[] = {
-	{
-		.procname	= "kernel",
-		.mode		= 0555,
-		.child		= sd_ctl_dir,
-	},
-	{}
-};
-
-static struct ctl_table *sd_alloc_ctl_entry(int n)
-{
-	struct ctl_table *entry =
-		kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL);
-
-	return entry;
-}
-
-static void sd_free_ctl_entry(struct ctl_table **tablep)
-{
-	struct ctl_table *entry;
-
-	/*
-	 * In the intermediate directories, both the child directory and
-	 * procname are dynamically allocated and could fail but the mode
-	 * will always be set. In the lowest directory the names are
-	 * static strings and all have proc handlers.
-	 */
-	for (entry = *tablep; entry->mode; entry++) {
-		if (entry->child)
-			sd_free_ctl_entry(&entry->child);
-		if (entry->proc_handler == NULL)
-			kfree(entry->procname);
-	}
-
-	kfree(*tablep);
-	*tablep = NULL;
-}
-
-static int min_load_idx = 0;
-static int max_load_idx = CPU_LOAD_IDX_MAX-1;
-
-static void
-set_table_entry(struct ctl_table *entry,
-		const char *procname, void *data, int maxlen,
-		umode_t mode, proc_handler *proc_handler,
-		bool load_idx)
-{
-	entry->procname = procname;
-	entry->data = data;
-	entry->maxlen = maxlen;
-	entry->mode = mode;
-	entry->proc_handler = proc_handler;
-
-	if (load_idx) {
-		entry->extra1 = &min_load_idx;
-		entry->extra2 = &max_load_idx;
-	}
-}
-
-static struct ctl_table *
-sd_alloc_ctl_domain_table(struct sched_domain *sd)
-{
-	struct ctl_table *table = sd_alloc_ctl_entry(14);
-
-	if (table == NULL)
-		return NULL;
-
-	set_table_entry(&table[0], "min_interval", &sd->min_interval,
-		sizeof(long), 0644, proc_doulongvec_minmax, false);
-	set_table_entry(&table[1], "max_interval", &sd->max_interval,
-		sizeof(long), 0644, proc_doulongvec_minmax, false);
-	set_table_entry(&table[2], "busy_idx", &sd->busy_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
-	set_table_entry(&table[3], "idle_idx", &sd->idle_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
-	set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
-	set_table_entry(&table[5], "wake_idx", &sd->wake_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
-	set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
-	set_table_entry(&table[7], "busy_factor", &sd->busy_factor,
-		sizeof(int), 0644, proc_dointvec_minmax, false);
-	set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
-		sizeof(int), 0644, proc_dointvec_minmax, false);
-	set_table_entry(&table[9], "cache_nice_tries",
-		&sd->cache_nice_tries,
-		sizeof(int), 0644, proc_dointvec_minmax, false);
-	set_table_entry(&table[10], "flags", &sd->flags,
-		sizeof(int), 0644, proc_dointvec_minmax, false);
-	set_table_entry(&table[11], "max_newidle_lb_cost",
-		&sd->max_newidle_lb_cost,
-		sizeof(long), 0644, proc_doulongvec_minmax, false);
-	set_table_entry(&table[12], "name", sd->name,
-		CORENAME_MAX_SIZE, 0444, proc_dostring, false);
-	/* &table[13] is terminator */
-
-	return table;
-}
-
-static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu)
-{
-	struct ctl_table *entry, *table;
-	struct sched_domain *sd;
-	int domain_num = 0, i;
-	char buf[32];
-
-	for_each_domain(cpu, sd)
-		domain_num++;
-	entry = table = sd_alloc_ctl_entry(domain_num + 1);
-	if (table == NULL)
-		return NULL;
-
-	i = 0;
-	for_each_domain(cpu, sd) {
-		snprintf(buf, 32, "domain%d", i);
-		entry->procname = kstrdup(buf, GFP_KERNEL);
-		entry->mode = 0555;
-		entry->child = sd_alloc_ctl_domain_table(sd);
-		entry++;
-		i++;
-	}
-	return table;
-}
-
-static struct ctl_table_header *sd_sysctl_header;
-static void register_sched_domain_sysctl(void)
-{
-	int i, cpu_num = num_possible_cpus();
-	struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
-	char buf[32];
-
-	WARN_ON(sd_ctl_dir[0].child);
-	sd_ctl_dir[0].child = entry;
-
-	if (entry == NULL)
-		return;
-
-	for_each_possible_cpu(i) {
-		snprintf(buf, 32, "cpu%d", i);
-		entry->procname = kstrdup(buf, GFP_KERNEL);
-		entry->mode = 0555;
-		entry->child = sd_alloc_ctl_cpu_table(i);
-		entry++;
-	}
-
-	WARN_ON(sd_sysctl_header);
-	sd_sysctl_header = register_sysctl_table(sd_ctl_root);
-}
-
-/* may be called multiple times per register */
-static void unregister_sched_domain_sysctl(void)
-{
-	unregister_sysctl_table(sd_sysctl_header);
-	sd_sysctl_header = NULL;
-	if (sd_ctl_dir[0].child)
-		sd_free_ctl_entry(&sd_ctl_dir[0].child);
-}
-#else
-static void register_sched_domain_sysctl(void)
-{
-}
-static void unregister_sched_domain_sysctl(void)
-{
-}
-#endif /* CONFIG_SCHED_DEBUG && CONFIG_SYSCTL */
-
 static void set_rq_online(struct rq *rq)
 {
 	if (!rq->online) {
@@ -6071,11 +5924,16 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 /* Setup the mask of cpus configured for isolated domains */
 static int __init isolated_cpu_setup(char *str)
 {
+	int ret;
+
 	alloc_bootmem_cpumask_var(&cpu_isolated_map);
-	cpulist_parse(str, cpu_isolated_map);
+	ret = cpulist_parse(str, cpu_isolated_map);
+	if (ret) {
+		pr_err("sched: Error, all isolcpus= values must be between 0 and %d\n", nr_cpu_ids);
+		return 0;
+	}
 	return 1;
 }
-
 __setup("isolcpus=", isolated_cpu_setup);
 
 struct s_data {
@@ -7355,6 +7213,9 @@ int in_sched_functions(unsigned long addr)
  */
 struct task_group root_task_group;
 LIST_HEAD(task_groups);
+
+/* Cacheline aligned slab cache for task_group */
+static struct kmem_cache *task_group_cache __read_mostly;
 #endif
 
 DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
@@ -7412,11 +7273,12 @@ void __init sched_init(void)
 #endif /* CONFIG_RT_GROUP_SCHED */
 
 #ifdef CONFIG_CGROUP_SCHED
+	task_group_cache = KMEM_CACHE(task_group, 0);
+
 	list_add(&root_task_group.list, &task_groups);
 	INIT_LIST_HEAD(&root_task_group.children);
 	INIT_LIST_HEAD(&root_task_group.siblings);
 	autogroup_init(&init_task);
-
 #endif /* CONFIG_CGROUP_SCHED */
 
 	for_each_possible_cpu(i) {
@@ -7697,7 +7559,7 @@ static void free_sched_group(struct task_group *tg)
 	free_fair_sched_group(tg);
 	free_rt_sched_group(tg);
 	autogroup_free(tg);
-	kfree(tg);
+	kmem_cache_free(task_group_cache, tg);
 }
 
 /* allocate runqueue etc for a new task group */
@@ -7705,7 +7567,7 @@ struct task_group *sched_create_group(struct task_group *parent)
 {
 	struct task_group *tg;
 
-	tg = kzalloc(sizeof(*tg), GFP_KERNEL);
+	tg = kmem_cache_alloc(task_group_cache, GFP_KERNEL | __GFP_ZERO);
 	if (!tg)
 		return ERR_PTR(-ENOMEM);
 
@@ -7754,11 +7616,9 @@ void sched_destroy_group(struct task_group *tg)
 void sched_offline_group(struct task_group *tg)
 {
 	unsigned long flags;
-	int i;
 
 	/* end participation in shares distribution */
-	for_each_possible_cpu(i)
-		unregister_fair_sched_group(tg, i);
+	unregister_fair_sched_group(tg);
 
 	spin_lock_irqsave(&task_group_lock, flags);
 	list_del_rcu(&tg->list);
@@ -7784,7 +7644,7 @@ void sched_move_task(struct task_struct *tsk)
 	queued = task_on_rq_queued(tsk);
 
 	if (queued)
-		dequeue_task(rq, tsk, DEQUEUE_SAVE);
+		dequeue_task(rq, tsk, DEQUEUE_SAVE | DEQUEUE_MOVE);
 	if (unlikely(running))
 		put_prev_task(rq, tsk);
 
@@ -7808,7 +7668,7 @@ void sched_move_task(struct task_struct *tsk)
 	if (unlikely(running))
 		tsk->sched_class->set_curr_task(rq);
 	if (queued)
-		enqueue_task(rq, tsk, ENQUEUE_RESTORE);
+		enqueue_task(rq, tsk, ENQUEUE_RESTORE | ENQUEUE_MOVE);
 
 	task_rq_unlock(rq, tsk, &flags);
 }
@@ -8236,7 +8096,7 @@ static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css)
 	sched_offline_group(tg);
 }
 
-static void cpu_cgroup_fork(struct task_struct *task, void *private)
+static void cpu_cgroup_fork(struct task_struct *task)
 {
 	sched_move_task(task);
 }
@@ -8610,3 +8470,44 @@ void dump_cpu_task(int cpu)
 	pr_info("Task dump for CPU %d:\n", cpu);
 	sched_show_task(cpu_curr(cpu));
 }
+
+/*
+ * Nice levels are multiplicative, with a gentle 10% change for every
+ * nice level changed. I.e. when a CPU-bound task goes from nice 0 to
+ * nice 1, it will get ~10% less CPU time than another CPU-bound task
+ * that remained on nice 0.
+ *
+ * The "10% effect" is relative and cumulative: from _any_ nice level,
+ * if you go up 1 level, it's -10% CPU usage, if you go down 1 level
+ * it's +10% CPU usage. (to achieve that we use a multiplier of 1.25.
+ * If a task goes up by ~10% and another task goes down by ~10% then
+ * the relative distance between them is ~25%.)
+ */
+const int sched_prio_to_weight[40] = {
+ /* -20 */     88761,     71755,     56483,     46273,     36291,
+ /* -15 */     29154,     23254,     18705,     14949,     11916,
+ /* -10 */      9548,      7620,      6100,      4904,      3906,
+ /*  -5 */      3121,      2501,      1991,      1586,      1277,
+ /*   0 */      1024,       820,       655,       526,       423,
+ /*   5 */       335,       272,       215,       172,       137,
+ /*  10 */       110,        87,        70,        56,        45,
+ /*  15 */        36,        29,        23,        18,        15,
+};
+
+/*
+ * Inverse (2^32/x) values of the sched_prio_to_weight[] array, precalculated.
+ *
+ * In cases where the weight does not change often, we can use the
+ * precalculated inverse to speed up arithmetics by turning divisions
+ * into multiplications:
+ */
+const u32 sched_prio_to_wmult[40] = {
+ /* -20 */     48388,     59856,     76040,     92818,    118348,
+ /* -15 */    147320,    184698,    229616,    287308,    360437,
+ /* -10 */    449829,    563644,    704093,    875809,   1099582,
+ /*  -5 */   1376151,   1717300,   2157191,   2708050,   3363326,
+ /*   0 */   4194304,   5237765,   6557202,   8165337,  10153587,
+ /*   5 */  12820798,  15790321,  19976592,  24970740,  31350126,
+ /*  10 */  39045157,  49367440,  61356676,  76695844,  95443717,
+ /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
+};
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 05de80b48..75f98c549 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -5,6 +5,9 @@
 #include <linux/static_key.h>
 #include <linux/context_tracking.h>
 #include "sched.h"
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#endif
 
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
@@ -259,21 +262,21 @@ static __always_inline bool steal_account_process_tick(void)
 #ifdef CONFIG_PARAVIRT
 	if (static_key_false(&paravirt_steal_enabled)) {
 		u64 steal;
-		cputime_t steal_ct;
+		unsigned long steal_jiffies;
 
 		steal = paravirt_steal_clock(smp_processor_id());
 		steal -= this_rq()->prev_steal_time;
 
 		/*
-		 * cputime_t may be less precise than nsecs (eg: if it's
-		 * based on jiffies). Lets cast the result to cputime
+		 * steal is in nsecs but our caller is expecting steal
+		 * time in jiffies. Lets cast the result to jiffies
 		 * granularity and account the rest on the next rounds.
 		 */
-		steal_ct = nsecs_to_cputime(steal);
-		this_rq()->prev_steal_time += cputime_to_nsecs(steal_ct);
+		steal_jiffies = nsecs_to_jiffies(steal);
+		this_rq()->prev_steal_time += jiffies_to_nsecs(steal_jiffies);
 
-		account_steal_time(steal_ct);
-		return steal_ct;
+		account_steal_time(jiffies_to_cputime(steal_jiffies));
+		return steal_jiffies;
 	}
 #endif
 	return false;
@@ -466,7 +469,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
 	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
 	struct rq *rq = this_rq();
 
-	if (vtime_accounting_enabled())
+	if (vtime_accounting_cpu_enabled())
 		return;
 
 	if (sched_clock_irqtime) {
@@ -665,26 +668,25 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime
 #endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-static unsigned long long vtime_delta(struct task_struct *tsk)
+static cputime_t vtime_delta(struct task_struct *tsk)
 {
-	unsigned long long clock;
+	unsigned long now = READ_ONCE(jiffies);
 
-	clock = local_clock();
-	if (clock < tsk->vtime_snap)
+	if (time_before(now, (unsigned long)tsk->vtime_snap))
 		return 0;
 
-	return clock - tsk->vtime_snap;
+	return jiffies_to_cputime(now - tsk->vtime_snap);
 }
 
 static cputime_t get_vtime_delta(struct task_struct *tsk)
 {
-	unsigned long long delta = vtime_delta(tsk);
+	unsigned long now = READ_ONCE(jiffies);
+	unsigned long delta = now - tsk->vtime_snap;
 
-	WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_SLEEPING);
-	tsk->vtime_snap += delta;
+	WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE);
+	tsk->vtime_snap = now;
 
-	/* CHECKME: always safe to convert nsecs to cputime? */
-	return nsecs_to_cputime(delta);
+	return jiffies_to_cputime(delta);
 }
 
 static void __vtime_account_system(struct task_struct *tsk)
@@ -696,37 +698,44 @@ static void __vtime_account_system(struct task_struct *tsk)
 
 void vtime_account_system(struct task_struct *tsk)
 {
-	write_seqlock(&tsk->vtime_seqlock);
+	if (!vtime_delta(tsk))
+		return;
+
+	write_seqcount_begin(&tsk->vtime_seqcount);
 	__vtime_account_system(tsk);
-	write_sequnlock(&tsk->vtime_seqlock);
+	write_seqcount_end(&tsk->vtime_seqcount);
 }
 
 void vtime_gen_account_irq_exit(struct task_struct *tsk)
 {
-	write_seqlock(&tsk->vtime_seqlock);
-	__vtime_account_system(tsk);
+	write_seqcount_begin(&tsk->vtime_seqcount);
+	if (vtime_delta(tsk))
+		__vtime_account_system(tsk);
 	if (context_tracking_in_user())
 		tsk->vtime_snap_whence = VTIME_USER;
-	write_sequnlock(&tsk->vtime_seqlock);
+	write_seqcount_end(&tsk->vtime_seqcount);
 }
 
 void vtime_account_user(struct task_struct *tsk)
 {
 	cputime_t delta_cpu;
 
-	write_seqlock(&tsk->vtime_seqlock);
-	delta_cpu = get_vtime_delta(tsk);
+	write_seqcount_begin(&tsk->vtime_seqcount);
 	tsk->vtime_snap_whence = VTIME_SYS;
-	account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu));
-	write_sequnlock(&tsk->vtime_seqlock);
+	if (vtime_delta(tsk)) {
+		delta_cpu = get_vtime_delta(tsk);
+		account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu));
+	}
+	write_seqcount_end(&tsk->vtime_seqcount);
 }
 
 void vtime_user_enter(struct task_struct *tsk)
 {
-	write_seqlock(&tsk->vtime_seqlock);
-	__vtime_account_system(tsk);
+	write_seqcount_begin(&tsk->vtime_seqcount);
+	if (vtime_delta(tsk))
+		__vtime_account_system(tsk);
 	tsk->vtime_snap_whence = VTIME_USER;
-	write_sequnlock(&tsk->vtime_seqlock);
+	write_seqcount_end(&tsk->vtime_seqcount);
 }
 
 void vtime_guest_enter(struct task_struct *tsk)
@@ -738,19 +747,20 @@ void vtime_guest_enter(struct task_struct *tsk)
 	 * synchronization against the reader (task_gtime())
 	 * that can thus safely catch up with a tickless delta.
 	 */
-	write_seqlock(&tsk->vtime_seqlock);
-	__vtime_account_system(tsk);
+	write_seqcount_begin(&tsk->vtime_seqcount);
+	if (vtime_delta(tsk))
+		__vtime_account_system(tsk);
 	current->flags |= PF_VCPU;
-	write_sequnlock(&tsk->vtime_seqlock);
+	write_seqcount_end(&tsk->vtime_seqcount);
 }
 EXPORT_SYMBOL_GPL(vtime_guest_enter);
 
 void vtime_guest_exit(struct task_struct *tsk)
 {
-	write_seqlock(&tsk->vtime_seqlock);
+	write_seqcount_begin(&tsk->vtime_seqcount);
 	__vtime_account_system(tsk);
 	current->flags &= ~PF_VCPU;
-	write_sequnlock(&tsk->vtime_seqlock);
+	write_seqcount_end(&tsk->vtime_seqcount);
 }
 EXPORT_SYMBOL_GPL(vtime_guest_exit);
 
@@ -763,24 +773,26 @@ void vtime_account_idle(struct task_struct *tsk)
 
 void arch_vtime_task_switch(struct task_struct *prev)
 {
-	write_seqlock(&prev->vtime_seqlock);
-	prev->vtime_snap_whence = VTIME_SLEEPING;
-	write_sequnlock(&prev->vtime_seqlock);
+	write_seqcount_begin(&prev->vtime_seqcount);
+	prev->vtime_snap_whence = VTIME_INACTIVE;
+	write_seqcount_end(&prev->vtime_seqcount);
 
-	write_seqlock(&current->vtime_seqlock);
+	write_seqcount_begin(&current->vtime_seqcount);
 	current->vtime_snap_whence = VTIME_SYS;
-	current->vtime_snap = sched_clock_cpu(smp_processor_id());
-	write_sequnlock(&current->vtime_seqlock);
+	current->vtime_snap = jiffies;
+	write_seqcount_end(&current->vtime_seqcount);
 }
 
 void vtime_init_idle(struct task_struct *t, int cpu)
 {
 	unsigned long flags;
 
-	write_seqlock_irqsave(&t->vtime_seqlock, flags);
+	local_irq_save(flags);
+	write_seqcount_begin(&t->vtime_seqcount);
 	t->vtime_snap_whence = VTIME_SYS;
-	t->vtime_snap = sched_clock_cpu(cpu);
-	write_sequnlock_irqrestore(&t->vtime_seqlock, flags);
+	t->vtime_snap = jiffies;
+	write_seqcount_end(&t->vtime_seqcount);
+	local_irq_restore(flags);
 }
 
 cputime_t task_gtime(struct task_struct *t)
@@ -788,17 +800,17 @@ cputime_t task_gtime(struct task_struct *t)
 	unsigned int seq;
 	cputime_t gtime;
 
-	if (!context_tracking_is_enabled())
+	if (!vtime_accounting_enabled())
 		return t->gtime;
 
 	do {
-		seq = read_seqbegin(&t->vtime_seqlock);
+		seq = read_seqcount_begin(&t->vtime_seqcount);
 
 		gtime = t->gtime;
-		if (t->flags & PF_VCPU)
+		if (t->vtime_snap_whence == VTIME_SYS && t->flags & PF_VCPU)
 			gtime += vtime_delta(t);
 
-	} while (read_seqretry(&t->vtime_seqlock, seq));
+	} while (read_seqcount_retry(&t->vtime_seqcount, seq));
 
 	return gtime;
 }
@@ -821,7 +833,7 @@ fetch_task_cputime(struct task_struct *t,
 		*udelta = 0;
 		*sdelta = 0;
 
-		seq = read_seqbegin(&t->vtime_seqlock);
+		seq = read_seqcount_begin(&t->vtime_seqcount);
 
 		if (u_dst)
 			*u_dst = *u_src;
@@ -829,7 +841,7 @@ fetch_task_cputime(struct task_struct *t,
 			*s_dst = *s_src;
 
 		/* Task is sleeping, nothing to add */
-		if (t->vtime_snap_whence == VTIME_SLEEPING ||
+		if (t->vtime_snap_whence == VTIME_INACTIVE ||
 		    is_idle_task(t))
 			continue;
 
@@ -845,7 +857,7 @@ fetch_task_cputime(struct task_struct *t,
 			if (t->vtime_snap_whence == VTIME_SYS)
 				*sdelta = delta;
 		}
-	} while (read_seqretry(&t->vtime_seqlock, seq));
+	} while (read_seqcount_retry(&t->vtime_seqcount, seq));
 }
 
 
@@ -853,6 +865,14 @@ void task_cputime(struct task_struct *t, cputime_t *utime, cputime_t *stime)
 {
 	cputime_t udelta, sdelta;
 
+	if (!vtime_accounting_enabled()) {
+		if (utime)
+			*utime = t->utime;
+		if (stime)
+			*stime = t->stime;
+		return;
+	}
+
 	fetch_task_cputime(t, utime, stime, &t->utime,
 			   &t->stime, &udelta, &sdelta);
 	if (utime)
@@ -866,6 +886,14 @@ void task_cputime_scaled(struct task_struct *t,
 {
 	cputime_t udelta, sdelta;
 
+	if (!vtime_accounting_enabled()) {
+		if (utimescaled)
+			*utimescaled = t->utimescaled;
+		if (stimescaled)
+			*stimescaled = t->stimescaled;
+		return;
+	}
+
 	fetch_task_cputime(t, utimescaled, stimescaled,
 			   &t->utimescaled, &t->stimescaled, &udelta, &sdelta);
 	if (utimescaled)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 8b0a15e28..c7a036fac 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -176,8 +176,10 @@ static void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
 		}
 	}
 
-	if (leftmost)
+	if (leftmost) {
 		dl_rq->pushable_dl_tasks_leftmost = &p->pushable_dl_tasks;
+		dl_rq->earliest_dl.next = p->dl.deadline;
+	}
 
 	rb_link_node(&p->pushable_dl_tasks, parent, link);
 	rb_insert_color(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
@@ -195,6 +197,10 @@ static void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
 
 		next_node = rb_next(&p->pushable_dl_tasks);
 		dl_rq->pushable_dl_tasks_leftmost = next_node;
+		if (next_node) {
+			dl_rq->earliest_dl.next = rb_entry(next_node,
+				struct task_struct, pushable_dl_tasks)->dl.deadline;
+		}
 	}
 
 	rb_erase(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
@@ -346,7 +352,15 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se,
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 
-	WARN_ON(!dl_se->dl_new || dl_se->dl_throttled);
+	WARN_ON(dl_time_before(rq_clock(rq), dl_se->deadline));
+
+	/*
+	 * We are racing with the deadline timer. So, do nothing because
+	 * the deadline timer handler will take care of properly recharging
+	 * the runtime and postponing the deadline
+	 */
+	if (dl_se->dl_throttled)
+		return;
 
 	/*
 	 * We use the regular wall clock time to set deadlines in the
@@ -355,7 +369,6 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se,
 	 */
 	dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
 	dl_se->runtime = pi_se->dl_runtime;
-	dl_se->dl_new = 0;
 }
 
 /*
@@ -393,6 +406,9 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
 		dl_se->runtime = pi_se->dl_runtime;
 	}
 
+	if (dl_se->dl_yielded && dl_se->runtime > 0)
+		dl_se->runtime = 0;
+
 	/*
 	 * We keep moving the deadline away until we get some
 	 * available runtime for the entity. This ensures correct
@@ -414,7 +430,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
 	 * entity.
 	 */
 	if (dl_time_before(dl_se->deadline, rq_clock(rq))) {
-		printk_deferred_once("sched: DL replenish lagged to much\n");
+		printk_deferred_once("sched: DL replenish lagged too much\n");
 		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
 		dl_se->runtime = pi_se->dl_runtime;
 	}
@@ -494,15 +510,6 @@ static void update_dl_entity(struct sched_dl_entity *dl_se,
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 
-	/*
-	 * The arrival of a new instance needs special treatment, i.e.,
-	 * the actual scheduling parameters have to be "renewed".
-	 */
-	if (dl_se->dl_new) {
-		setup_new_dl_entity(dl_se, pi_se);
-		return;
-	}
-
 	if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
 	    dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) {
 		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
@@ -599,16 +606,6 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	}
 
 	/*
-	 * This is possible if switched_from_dl() raced against a running
-	 * callback that took the above !dl_task() path and we've since then
-	 * switched back into SCHED_DEADLINE.
-	 *
-	 * There's nothing to do except drop our task reference.
-	 */
-	if (dl_se->dl_new)
-		goto unlock;
-
-	/*
 	 * The task might have been boosted by someone else and might be in the
 	 * boosting/deboosting path, its not throttled.
 	 */
@@ -729,8 +726,11 @@ static void update_curr_dl(struct rq *rq)
 	 * approach need further study.
 	 */
 	delta_exec = rq_clock_task(rq) - curr->se.exec_start;
-	if (unlikely((s64)delta_exec <= 0))
+	if (unlikely((s64)delta_exec <= 0)) {
+		if (unlikely(dl_se->dl_yielded))
+			goto throttle;
 		return;
+	}
 
 	schedstat_set(curr->se.statistics.exec_max,
 		      max(curr->se.statistics.exec_max, delta_exec));
@@ -743,8 +743,10 @@ static void update_curr_dl(struct rq *rq)
 
 	sched_rt_avg_update(rq, delta_exec);
 
-	dl_se->runtime -= dl_se->dl_yielded ? 0 : delta_exec;
-	if (dl_runtime_exceeded(dl_se)) {
+	dl_se->runtime -= delta_exec;
+
+throttle:
+	if (dl_runtime_exceeded(dl_se) || dl_se->dl_yielded) {
 		dl_se->dl_throttled = 1;
 		__dequeue_task_dl(rq, curr, 0);
 		if (unlikely(dl_se->dl_boosted || !start_dl_timer(curr)))
@@ -782,42 +784,14 @@ static void update_curr_dl(struct rq *rq)
 
 #ifdef CONFIG_SMP
 
-static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu);
-
-static inline u64 next_deadline(struct rq *rq)
-{
-	struct task_struct *next = pick_next_earliest_dl_task(rq, rq->cpu);
-
-	if (next && dl_prio(next->prio))
-		return next->dl.deadline;
-	else
-		return 0;
-}
-
 static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
 {
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 
 	if (dl_rq->earliest_dl.curr == 0 ||
 	    dl_time_before(deadline, dl_rq->earliest_dl.curr)) {
-		/*
-		 * If the dl_rq had no -deadline tasks, or if the new task
-		 * has shorter deadline than the current one on dl_rq, we
-		 * know that the previous earliest becomes our next earliest,
-		 * as the new task becomes the earliest itself.
-		 */
-		dl_rq->earliest_dl.next = dl_rq->earliest_dl.curr;
 		dl_rq->earliest_dl.curr = deadline;
 		cpudl_set(&rq->rd->cpudl, rq->cpu, deadline, 1);
-	} else if (dl_rq->earliest_dl.next == 0 ||
-		   dl_time_before(deadline, dl_rq->earliest_dl.next)) {
-		/*
-		 * On the other hand, if the new -deadline task has a
-		 * a later deadline than the earliest one on dl_rq, but
-		 * it is earlier than the next (if any), we must
-		 * recompute the next-earliest.
-		 */
-		dl_rq->earliest_dl.next = next_deadline(rq);
 	}
 }
 
@@ -839,7 +813,6 @@ static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
 
 		entry = rb_entry(leftmost, struct sched_dl_entity, rb_node);
 		dl_rq->earliest_dl.curr = entry->deadline;
-		dl_rq->earliest_dl.next = next_deadline(rq);
 		cpudl_set(&rq->rd->cpudl, rq->cpu, entry->deadline, 1);
 	}
 }
@@ -940,7 +913,7 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se,
 	 * parameters of the task might need updating. Otherwise,
 	 * we want a replenishment of its runtime.
 	 */
-	if (dl_se->dl_new || flags & ENQUEUE_WAKEUP)
+	if (flags & ENQUEUE_WAKEUP)
 		update_dl_entity(dl_se, pi_se);
 	else if (flags & ENQUEUE_REPLENISH)
 		replenish_dl_entity(dl_se, pi_se);
@@ -1017,18 +990,14 @@ static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
  */
 static void yield_task_dl(struct rq *rq)
 {
-	struct task_struct *p = rq->curr;
-
 	/*
 	 * We make the task go to sleep until its current deadline by
 	 * forcing its runtime to zero. This way, update_curr_dl() stops
 	 * it and the bandwidth timer will wake it up and will give it
 	 * new scheduling parameters (thanks to dl_yielded=1).
 	 */
-	if (p->dl.runtime > 0) {
-		rq->curr->dl.dl_yielded = 1;
-		p->dl.runtime = 0;
-	}
+	rq->curr->dl.dl_yielded = 1;
+
 	update_rq_clock(rq);
 	update_curr_dl(rq);
 	/*
@@ -1274,28 +1243,6 @@ static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
 	return 0;
 }
 
-/* Returns the second earliest -deadline task, NULL otherwise */
-static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu)
-{
-	struct rb_node *next_node = rq->dl.rb_leftmost;
-	struct sched_dl_entity *dl_se;
-	struct task_struct *p = NULL;
-
-next_node:
-	next_node = rb_next(next_node);
-	if (next_node) {
-		dl_se = rb_entry(next_node, struct sched_dl_entity, rb_node);
-		p = dl_task_of(dl_se);
-
-		if (pick_dl_task(rq, p, cpu))
-			return p;
-
-		goto next_node;
-	}
-
-	return NULL;
-}
-
 /*
  * Return the earliest pushable rq's task, which is suitable to be executed
  * on the CPU, NULL otherwise:
@@ -1767,6 +1714,9 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p)
  */
 static void switched_to_dl(struct rq *rq, struct task_struct *p)
 {
+	if (dl_time_before(p->dl.deadline, rq_clock(rq)))
+		setup_new_dl_entity(&p->dl, &p->dl);
+
 	if (task_on_rq_queued(p) && rq->curr != p) {
 #ifdef CONFIG_SMP
 		if (p->nr_cpus_allowed > 1 && rq->dl.overloaded)
@@ -1813,8 +1763,7 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p,
 		 */
 		resched_curr(rq);
 #endif /* CONFIG_SMP */
-	} else
-		switched_to_dl(rq, p);
+	}
 }
 
 const struct sched_class dl_sched_class = {
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 641511771..4fbc3bd5f 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -16,6 +16,7 @@
 #include <linux/kallsyms.h>
 #include <linux/utsname.h>
 #include <linux/mempolicy.h>
+#include <linux/debugfs.h>
 
 #include "sched.h"
 
@@ -58,6 +59,309 @@ static unsigned long nsec_low(unsigned long long nsec)
 
 #define SPLIT_NS(x) nsec_high(x), nsec_low(x)
 
+#define SCHED_FEAT(name, enabled)	\
+	#name ,
+
+static const char * const sched_feat_names[] = {
+#include "features.h"
+};
+
+#undef SCHED_FEAT
+
+static int sched_feat_show(struct seq_file *m, void *v)
+{
+	int i;
+
+	for (i = 0; i < __SCHED_FEAT_NR; i++) {
+		if (!(sysctl_sched_features & (1UL << i)))
+			seq_puts(m, "NO_");
+		seq_printf(m, "%s ", sched_feat_names[i]);
+	}
+	seq_puts(m, "\n");
+
+	return 0;
+}
+
+#ifdef HAVE_JUMP_LABEL
+
+#define jump_label_key__true  STATIC_KEY_INIT_TRUE
+#define jump_label_key__false STATIC_KEY_INIT_FALSE
+
+#define SCHED_FEAT(name, enabled)	\
+	jump_label_key__##enabled ,
+
+struct static_key sched_feat_keys[__SCHED_FEAT_NR] = {
+#include "features.h"
+};
+
+#undef SCHED_FEAT
+
+static void sched_feat_disable(int i)
+{
+	static_key_disable(&sched_feat_keys[i]);
+}
+
+static void sched_feat_enable(int i)
+{
+	static_key_enable(&sched_feat_keys[i]);
+}
+#else
+static void sched_feat_disable(int i) { };
+static void sched_feat_enable(int i) { };
+#endif /* HAVE_JUMP_LABEL */
+
+static int sched_feat_set(char *cmp)
+{
+	int i;
+	int neg = 0;
+
+	if (strncmp(cmp, "NO_", 3) == 0) {
+		neg = 1;
+		cmp += 3;
+	}
+
+	for (i = 0; i < __SCHED_FEAT_NR; i++) {
+		if (strcmp(cmp, sched_feat_names[i]) == 0) {
+			if (neg) {
+				sysctl_sched_features &= ~(1UL << i);
+				sched_feat_disable(i);
+			} else {
+				sysctl_sched_features |= (1UL << i);
+				sched_feat_enable(i);
+			}
+			break;
+		}
+	}
+
+	return i;
+}
+
+static ssize_t
+sched_feat_write(struct file *filp, const char __user *ubuf,
+		size_t cnt, loff_t *ppos)
+{
+	char buf[64];
+	char *cmp;
+	int i;
+	struct inode *inode;
+
+	if (cnt > 63)
+		cnt = 63;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+	cmp = strstrip(buf);
+
+	/* Ensure the static_key remains in a consistent state */
+	inode = file_inode(filp);
+	inode_lock(inode);
+	i = sched_feat_set(cmp);
+	inode_unlock(inode);
+	if (i == __SCHED_FEAT_NR)
+		return -EINVAL;
+
+	*ppos += cnt;
+
+	return cnt;
+}
+
+static int sched_feat_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, sched_feat_show, NULL);
+}
+
+static const struct file_operations sched_feat_fops = {
+	.open		= sched_feat_open,
+	.write		= sched_feat_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static __init int sched_init_debug(void)
+{
+	debugfs_create_file("sched_features", 0644, NULL, NULL,
+			&sched_feat_fops);
+
+	return 0;
+}
+late_initcall(sched_init_debug);
+
+#ifdef CONFIG_SMP
+
+#ifdef CONFIG_SYSCTL
+
+static struct ctl_table sd_ctl_dir[] = {
+	{
+		.procname	= "sched_domain",
+		.mode		= 0555,
+	},
+	{}
+};
+
+static struct ctl_table sd_ctl_root[] = {
+	{
+		.procname	= "kernel",
+		.mode		= 0555,
+		.child		= sd_ctl_dir,
+	},
+	{}
+};
+
+static struct ctl_table *sd_alloc_ctl_entry(int n)
+{
+	struct ctl_table *entry =
+		kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL);
+
+	return entry;
+}
+
+static void sd_free_ctl_entry(struct ctl_table **tablep)
+{
+	struct ctl_table *entry;
+
+	/*
+	 * In the intermediate directories, both the child directory and
+	 * procname are dynamically allocated and could fail but the mode
+	 * will always be set. In the lowest directory the names are
+	 * static strings and all have proc handlers.
+	 */
+	for (entry = *tablep; entry->mode; entry++) {
+		if (entry->child)
+			sd_free_ctl_entry(&entry->child);
+		if (entry->proc_handler == NULL)
+			kfree(entry->procname);
+	}
+
+	kfree(*tablep);
+	*tablep = NULL;
+}
+
+static int min_load_idx = 0;
+static int max_load_idx = CPU_LOAD_IDX_MAX-1;
+
+static void
+set_table_entry(struct ctl_table *entry,
+		const char *procname, void *data, int maxlen,
+		umode_t mode, proc_handler *proc_handler,
+		bool load_idx)
+{
+	entry->procname = procname;
+	entry->data = data;
+	entry->maxlen = maxlen;
+	entry->mode = mode;
+	entry->proc_handler = proc_handler;
+
+	if (load_idx) {
+		entry->extra1 = &min_load_idx;
+		entry->extra2 = &max_load_idx;
+	}
+}
+
+static struct ctl_table *
+sd_alloc_ctl_domain_table(struct sched_domain *sd)
+{
+	struct ctl_table *table = sd_alloc_ctl_entry(14);
+
+	if (table == NULL)
+		return NULL;
+
+	set_table_entry(&table[0], "min_interval", &sd->min_interval,
+		sizeof(long), 0644, proc_doulongvec_minmax, false);
+	set_table_entry(&table[1], "max_interval", &sd->max_interval,
+		sizeof(long), 0644, proc_doulongvec_minmax, false);
+	set_table_entry(&table[2], "busy_idx", &sd->busy_idx,
+		sizeof(int), 0644, proc_dointvec_minmax, true);
+	set_table_entry(&table[3], "idle_idx", &sd->idle_idx,
+		sizeof(int), 0644, proc_dointvec_minmax, true);
+	set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx,
+		sizeof(int), 0644, proc_dointvec_minmax, true);
+	set_table_entry(&table[5], "wake_idx", &sd->wake_idx,
+		sizeof(int), 0644, proc_dointvec_minmax, true);
+	set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx,
+		sizeof(int), 0644, proc_dointvec_minmax, true);
+	set_table_entry(&table[7], "busy_factor", &sd->busy_factor,
+		sizeof(int), 0644, proc_dointvec_minmax, false);
+	set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
+		sizeof(int), 0644, proc_dointvec_minmax, false);
+	set_table_entry(&table[9], "cache_nice_tries",
+		&sd->cache_nice_tries,
+		sizeof(int), 0644, proc_dointvec_minmax, false);
+	set_table_entry(&table[10], "flags", &sd->flags,
+		sizeof(int), 0644, proc_dointvec_minmax, false);
+	set_table_entry(&table[11], "max_newidle_lb_cost",
+		&sd->max_newidle_lb_cost,
+		sizeof(long), 0644, proc_doulongvec_minmax, false);
+	set_table_entry(&table[12], "name", sd->name,
+		CORENAME_MAX_SIZE, 0444, proc_dostring, false);
+	/* &table[13] is terminator */
+
+	return table;
+}
+
+static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu)
+{
+	struct ctl_table *entry, *table;
+	struct sched_domain *sd;
+	int domain_num = 0, i;
+	char buf[32];
+
+	for_each_domain(cpu, sd)
+		domain_num++;
+	entry = table = sd_alloc_ctl_entry(domain_num + 1);
+	if (table == NULL)
+		return NULL;
+
+	i = 0;
+	for_each_domain(cpu, sd) {
+		snprintf(buf, 32, "domain%d", i);
+		entry->procname = kstrdup(buf, GFP_KERNEL);
+		entry->mode = 0555;
+		entry->child = sd_alloc_ctl_domain_table(sd);
+		entry++;
+		i++;
+	}
+	return table;
+}
+
+static struct ctl_table_header *sd_sysctl_header;
+void register_sched_domain_sysctl(void)
+{
+	int i, cpu_num = num_possible_cpus();
+	struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
+	char buf[32];
+
+	WARN_ON(sd_ctl_dir[0].child);
+	sd_ctl_dir[0].child = entry;
+
+	if (entry == NULL)
+		return;
+
+	for_each_possible_cpu(i) {
+		snprintf(buf, 32, "cpu%d", i);
+		entry->procname = kstrdup(buf, GFP_KERNEL);
+		entry->mode = 0555;
+		entry->child = sd_alloc_ctl_cpu_table(i);
+		entry++;
+	}
+
+	WARN_ON(sd_sysctl_header);
+	sd_sysctl_header = register_sysctl_table(sd_ctl_root);
+}
+
+/* may be called multiple times per register */
+void unregister_sched_domain_sysctl(void)
+{
+	unregister_sysctl_table(sd_sysctl_header);
+	sd_sysctl_header = NULL;
+	if (sd_ctl_dir[0].child)
+		sd_free_ctl_entry(&sd_ctl_dir[0].child);
+}
+#endif /* CONFIG_SYSCTL */
+#endif /* CONFIG_SMP */
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg)
 {
@@ -75,16 +379,18 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 	PN(se->vruntime);
 	PN(se->sum_exec_runtime);
 #ifdef CONFIG_SCHEDSTATS
-	PN(se->statistics.wait_start);
-	PN(se->statistics.sleep_start);
-	PN(se->statistics.block_start);
-	PN(se->statistics.sleep_max);
-	PN(se->statistics.block_max);
-	PN(se->statistics.exec_max);
-	PN(se->statistics.slice_max);
-	PN(se->statistics.wait_max);
-	PN(se->statistics.wait_sum);
-	P(se->statistics.wait_count);
+	if (schedstat_enabled()) {
+		PN(se->statistics.wait_start);
+		PN(se->statistics.sleep_start);
+		PN(se->statistics.block_start);
+		PN(se->statistics.sleep_max);
+		PN(se->statistics.block_max);
+		PN(se->statistics.exec_max);
+		PN(se->statistics.slice_max);
+		PN(se->statistics.wait_max);
+		PN(se->statistics.wait_sum);
+		P(se->statistics.wait_count);
+	}
 #endif
 	P(se->load.weight);
 #ifdef CONFIG_SMP
@@ -122,10 +428,12 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 		(long long)(p->nvcsw + p->nivcsw),
 		p->prio);
 #ifdef CONFIG_SCHEDSTATS
-	SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
-		SPLIT_NS(p->se.statistics.wait_sum),
-		SPLIT_NS(p->se.sum_exec_runtime),
-		SPLIT_NS(p->se.statistics.sum_sleep_runtime));
+	if (schedstat_enabled()) {
+		SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
+			SPLIT_NS(p->se.statistics.wait_sum),
+			SPLIT_NS(p->se.sum_exec_runtime),
+			SPLIT_NS(p->se.statistics.sum_sleep_runtime));
+	}
 #else
 	SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
 		0LL, 0L,
@@ -258,8 +566,17 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
 
 void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq)
 {
+	struct dl_bw *dl_bw;
+
 	SEQ_printf(m, "\ndl_rq[%d]:\n", cpu);
 	SEQ_printf(m, "  .%-30s: %ld\n", "dl_nr_running", dl_rq->dl_nr_running);
+#ifdef CONFIG_SMP
+	dl_bw = &cpu_rq(cpu)->rd->dl_bw;
+#else
+	dl_bw = &dl_rq->dl_bw;
+#endif
+	SEQ_printf(m, "  .%-30s: %lld\n", "dl_bw->bw", dl_bw->bw);
+	SEQ_printf(m, "  .%-30s: %lld\n", "dl_bw->total_bw", dl_bw->total_bw);
 }
 
 extern __read_mostly int sched_clock_running;
@@ -313,17 +630,18 @@ do {									\
 #define P(n) SEQ_printf(m, "  .%-30s: %d\n", #n, rq->n);
 #define P64(n) SEQ_printf(m, "  .%-30s: %Ld\n", #n, rq->n);
 
-	P(yld_count);
-
-	P(sched_count);
-	P(sched_goidle);
 #ifdef CONFIG_SMP
 	P64(avg_idle);
 	P64(max_idle_balance_cost);
 #endif
 
-	P(ttwu_count);
-	P(ttwu_local);
+	if (schedstat_enabled()) {
+		P(yld_count);
+		P(sched_count);
+		P(sched_goidle);
+		P(ttwu_count);
+		P(ttwu_local);
+	}
 
 #undef P
 #undef P64
@@ -569,38 +887,39 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 	nr_switches = p->nvcsw + p->nivcsw;
 
 #ifdef CONFIG_SCHEDSTATS
-	PN(se.statistics.sum_sleep_runtime);
-	PN(se.statistics.wait_start);
-	PN(se.statistics.sleep_start);
-	PN(se.statistics.block_start);
-	PN(se.statistics.sleep_max);
-	PN(se.statistics.block_max);
-	PN(se.statistics.exec_max);
-	PN(se.statistics.slice_max);
-	PN(se.statistics.wait_max);
-	PN(se.statistics.wait_sum);
-	P(se.statistics.wait_count);
-	PN(se.statistics.iowait_sum);
-	P(se.statistics.iowait_count);
 	P(se.nr_migrations);
-	P(se.statistics.nr_migrations_cold);
-	P(se.statistics.nr_failed_migrations_affine);
-	P(se.statistics.nr_failed_migrations_running);
-	P(se.statistics.nr_failed_migrations_hot);
-	P(se.statistics.nr_forced_migrations);
-	P(se.statistics.nr_wakeups);
-	P(se.statistics.nr_wakeups_sync);
-	P(se.statistics.nr_wakeups_migrate);
-	P(se.statistics.nr_wakeups_local);
-	P(se.statistics.nr_wakeups_remote);
-	P(se.statistics.nr_wakeups_affine);
-	P(se.statistics.nr_wakeups_affine_attempts);
-	P(se.statistics.nr_wakeups_passive);
-	P(se.statistics.nr_wakeups_idle);
 
-	{
+	if (schedstat_enabled()) {
 		u64 avg_atom, avg_per_cpu;
 
+		PN(se.statistics.sum_sleep_runtime);
+		PN(se.statistics.wait_start);
+		PN(se.statistics.sleep_start);
+		PN(se.statistics.block_start);
+		PN(se.statistics.sleep_max);
+		PN(se.statistics.block_max);
+		PN(se.statistics.exec_max);
+		PN(se.statistics.slice_max);
+		PN(se.statistics.wait_max);
+		PN(se.statistics.wait_sum);
+		P(se.statistics.wait_count);
+		PN(se.statistics.iowait_sum);
+		P(se.statistics.iowait_count);
+		P(se.statistics.nr_migrations_cold);
+		P(se.statistics.nr_failed_migrations_affine);
+		P(se.statistics.nr_failed_migrations_running);
+		P(se.statistics.nr_failed_migrations_hot);
+		P(se.statistics.nr_forced_migrations);
+		P(se.statistics.nr_wakeups);
+		P(se.statistics.nr_wakeups_sync);
+		P(se.statistics.nr_wakeups_migrate);
+		P(se.statistics.nr_wakeups_local);
+		P(se.statistics.nr_wakeups_remote);
+		P(se.statistics.nr_wakeups_affine);
+		P(se.statistics.nr_wakeups_affine_attempts);
+		P(se.statistics.nr_wakeups_passive);
+		P(se.statistics.nr_wakeups_idle);
+
 		avg_atom = p->se.sum_exec_runtime;
 		if (nr_switches)
 			avg_atom = div64_ul(avg_atom, nr_switches);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 82e905862..ac7fb39c3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -20,8 +20,8 @@
  *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  */
 
-#include <linux/latencytop.h>
 #include <linux/sched.h>
+#include <linux/latencytop.h>
 #include <linux/cpumask.h>
 #include <linux/cpuidle.h>
 #include <linux/slab.h>
@@ -763,16 +763,52 @@ static void update_curr_fair(struct rq *rq)
 	update_curr(cfs_rq_of(&rq->curr->se));
 }
 
+#ifdef CONFIG_SCHEDSTATS
 static inline void
 update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	schedstat_set(se->statistics.wait_start, rq_clock(rq_of(cfs_rq)));
+	u64 wait_start = rq_clock(rq_of(cfs_rq));
+
+	if (entity_is_task(se) && task_on_rq_migrating(task_of(se)) &&
+	    likely(wait_start > se->statistics.wait_start))
+		wait_start -= se->statistics.wait_start;
+
+	se->statistics.wait_start = wait_start;
+}
+
+static void
+update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	struct task_struct *p;
+	u64 delta;
+
+	delta = rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start;
+
+	if (entity_is_task(se)) {
+		p = task_of(se);
+		if (task_on_rq_migrating(p)) {
+			/*
+			 * Preserve migrating task's wait time so wait_start
+			 * time stamp can be adjusted to accumulate wait time
+			 * prior to migration.
+			 */
+			se->statistics.wait_start = delta;
+			return;
+		}
+		trace_sched_stat_wait(p, delta);
+	}
+
+	se->statistics.wait_max = max(se->statistics.wait_max, delta);
+	se->statistics.wait_count++;
+	se->statistics.wait_sum += delta;
+	se->statistics.wait_start = 0;
 }
 
 /*
  * Task is being enqueued - update stats:
  */
-static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static inline void
+update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	/*
 	 * Are we enqueueing a waiting task? (for current tasks
@@ -782,25 +818,8 @@ static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		update_stats_wait_start(cfs_rq, se);
 }
 
-static void
-update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-	schedstat_set(se->statistics.wait_max, max(se->statistics.wait_max,
-			rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start));
-	schedstat_set(se->statistics.wait_count, se->statistics.wait_count + 1);
-	schedstat_set(se->statistics.wait_sum, se->statistics.wait_sum +
-			rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start);
-#ifdef CONFIG_SCHEDSTATS
-	if (entity_is_task(se)) {
-		trace_sched_stat_wait(task_of(se),
-			rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start);
-	}
-#endif
-	schedstat_set(se->statistics.wait_start, 0);
-}
-
 static inline void
-update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
+update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
 	/*
 	 * Mark the end of the wait period if dequeueing a
@@ -808,8 +827,41 @@ update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	 */
 	if (se != cfs_rq->curr)
 		update_stats_wait_end(cfs_rq, se);
+
+	if (flags & DEQUEUE_SLEEP) {
+		if (entity_is_task(se)) {
+			struct task_struct *tsk = task_of(se);
+
+			if (tsk->state & TASK_INTERRUPTIBLE)
+				se->statistics.sleep_start = rq_clock(rq_of(cfs_rq));
+			if (tsk->state & TASK_UNINTERRUPTIBLE)
+				se->statistics.block_start = rq_clock(rq_of(cfs_rq));
+		}
+	}
+
+}
+#else
+static inline void
+update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+}
+
+static inline void
+update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
 }
 
+static inline void
+update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+}
+
+static inline void
+update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
+{
+}
+#endif
+
 /*
  * We are picking a new current task - update its stats:
  */
@@ -905,10 +957,11 @@ struct numa_group {
 	spinlock_t lock; /* nr_tasks, tasks */
 	int nr_tasks;
 	pid_t gid;
+	int active_nodes;
 
 	struct rcu_head rcu;
-	nodemask_t active_nodes;
 	unsigned long total_faults;
+	unsigned long max_faults_cpu;
 	/*
 	 * Faults_cpu is used to decide whether memory should move
 	 * towards the CPU. As a consequence, these stats are weighted
@@ -967,6 +1020,18 @@ static inline unsigned long group_faults_cpu(struct numa_group *group, int nid)
 		group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 1)];
 }
 
+/*
+ * A node triggering more than 1/3 as many NUMA faults as the maximum is
+ * considered part of a numa group's pseudo-interleaving set. Migrations
+ * between these nodes are slowed down, to allow things to settle down.
+ */
+#define ACTIVE_NODE_FRACTION 3
+
+static bool numa_is_active_node(int nid, struct numa_group *ng)
+{
+	return group_faults_cpu(ng, nid) * ACTIVE_NODE_FRACTION > ng->max_faults_cpu;
+}
+
 /* Handle placement on systems where not all nodes are directly connected. */
 static unsigned long score_nearby_nodes(struct task_struct *p, int nid,
 					int maxdist, bool task)
@@ -1116,27 +1181,23 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
 		return true;
 
 	/*
-	 * Do not migrate if the destination is not a node that
-	 * is actively used by this numa group.
+	 * Destination node is much more heavily used than the source
+	 * node? Allow migration.
 	 */
-	if (!node_isset(dst_nid, ng->active_nodes))
-		return false;
-
-	/*
-	 * Source is a node that is not actively used by this
-	 * numa group, while the destination is. Migrate.
-	 */
-	if (!node_isset(src_nid, ng->active_nodes))
+	if (group_faults_cpu(ng, dst_nid) > group_faults_cpu(ng, src_nid) *
+					ACTIVE_NODE_FRACTION)
 		return true;
 
 	/*
-	 * Both source and destination are nodes in active
-	 * use by this numa group. Maximize memory bandwidth
-	 * by migrating from more heavily used groups, to less
-	 * heavily used ones, spreading the load around.
-	 * Use a 1/4 hysteresis to avoid spurious page movement.
+	 * Distribute memory according to CPU & memory use on each node,
+	 * with 3/4 hysteresis to avoid unnecessary memory migrations:
+	 *
+	 * faults_cpu(dst)   3   faults_cpu(src)
+	 * --------------- * - > ---------------
+	 * faults_mem(dst)   4   faults_mem(src)
 	 */
-	return group_faults(p, dst_nid) < (group_faults(p, src_nid) * 3 / 4);
+	return group_faults_cpu(ng, dst_nid) * group_faults(p, src_nid) * 3 >
+	       group_faults_cpu(ng, src_nid) * group_faults(p, dst_nid) * 4;
 }
 
 static unsigned long weighted_cpuload(const int cpu);
@@ -1218,8 +1279,6 @@ static void task_numa_assign(struct task_numa_env *env,
 {
 	if (env->best_task)
 		put_task_struct(env->best_task);
-	if (p)
-		get_task_struct(p);
 
 	env->best_task = p;
 	env->best_imp = imp;
@@ -1287,20 +1346,30 @@ static void task_numa_compare(struct task_numa_env *env,
 	long imp = env->p->numa_group ? groupimp : taskimp;
 	long moveimp = imp;
 	int dist = env->dist;
+	bool assigned = false;
 
 	rcu_read_lock();
 
 	raw_spin_lock_irq(&dst_rq->lock);
 	cur = dst_rq->curr;
 	/*
-	 * No need to move the exiting task, and this ensures that ->curr
-	 * wasn't reaped and thus get_task_struct() in task_numa_assign()
-	 * is safe under RCU read lock.
-	 * Note that rcu_read_lock() itself can't protect from the final
-	 * put_task_struct() after the last schedule().
+	 * No need to move the exiting task or idle task.
 	 */
 	if ((cur->flags & PF_EXITING) || is_idle_task(cur))
 		cur = NULL;
+	else {
+		/*
+		 * The task_struct must be protected here to protect the
+		 * p->numa_faults access in the task_weight since the
+		 * numa_faults could already be freed in the following path:
+		 * finish_task_switch()
+		 *     --> put_task_struct()
+		 *         --> __put_task_struct()
+		 *             --> task_numa_free()
+		 */
+		get_task_struct(cur);
+	}
+
 	raw_spin_unlock_irq(&dst_rq->lock);
 
 	/*
@@ -1384,6 +1453,7 @@ balance:
 		 */
 		if (!load_too_imbalanced(src_load, dst_load, env)) {
 			imp = moveimp - 1;
+			put_task_struct(cur);
 			cur = NULL;
 			goto assign;
 		}
@@ -1409,9 +1479,16 @@ balance:
 		env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu);
 
 assign:
+	assigned = true;
 	task_numa_assign(env, cur, imp);
 unlock:
 	rcu_read_unlock();
+	/*
+	 * The dst_rq->curr isn't assigned. The protection for task_struct is
+	 * finished.
+	 */
+	if (cur && !assigned)
+		put_task_struct(cur);
 }
 
 static void task_numa_find_cpu(struct task_numa_env *env,
@@ -1466,7 +1543,7 @@ static int task_numa_migrate(struct task_struct *p)
 
 		.best_task = NULL,
 		.best_imp = 0,
-		.best_cpu = -1
+		.best_cpu = -1,
 	};
 	struct sched_domain *sd;
 	unsigned long taskweight, groupweight;
@@ -1518,8 +1595,7 @@ static int task_numa_migrate(struct task_struct *p)
 	 *   multiple NUMA nodes; in order to better consolidate the group,
 	 *   we need to check other locations.
 	 */
-	if (env.best_cpu == -1 || (p->numa_group &&
-			nodes_weight(p->numa_group->active_nodes) > 1)) {
+	if (env.best_cpu == -1 || (p->numa_group && p->numa_group->active_nodes > 1)) {
 		for_each_online_node(nid) {
 			if (nid == env.src_nid || nid == p->numa_preferred_nid)
 				continue;
@@ -1554,12 +1630,14 @@ static int task_numa_migrate(struct task_struct *p)
 	 * trying for a better one later. Do not set the preferred node here.
 	 */
 	if (p->numa_group) {
+		struct numa_group *ng = p->numa_group;
+
 		if (env.best_cpu == -1)
 			nid = env.src_nid;
 		else
 			nid = env.dst_nid;
 
-		if (node_isset(nid, p->numa_group->active_nodes))
+		if (ng->active_nodes > 1 && numa_is_active_node(env.dst_nid, ng))
 			sched_setnuma(p, env.dst_nid);
 	}
 
@@ -1609,20 +1687,15 @@ static void numa_migrate_preferred(struct task_struct *p)
 }
 
 /*
- * Find the nodes on which the workload is actively running. We do this by
+ * Find out how many nodes on the workload is actively running on. Do this by
  * tracking the nodes from which NUMA hinting faults are triggered. This can
  * be different from the set of nodes where the workload's memory is currently
  * located.
- *
- * The bitmask is used to make smarter decisions on when to do NUMA page
- * migrations, To prevent flip-flopping, and excessive page migrations, nodes
- * are added when they cause over 6/16 of the maximum number of faults, but
- * only removed when they drop below 3/16.
  */
-static void update_numa_active_node_mask(struct numa_group *numa_group)
+static void numa_group_count_active_nodes(struct numa_group *numa_group)
 {
 	unsigned long faults, max_faults = 0;
-	int nid;
+	int nid, active_nodes = 0;
 
 	for_each_online_node(nid) {
 		faults = group_faults_cpu(numa_group, nid);
@@ -1632,12 +1705,12 @@ static void update_numa_active_node_mask(struct numa_group *numa_group)
 
 	for_each_online_node(nid) {
 		faults = group_faults_cpu(numa_group, nid);
-		if (!node_isset(nid, numa_group->active_nodes)) {
-			if (faults > max_faults * 6 / 16)
-				node_set(nid, numa_group->active_nodes);
-		} else if (faults < max_faults * 3 / 16)
-			node_clear(nid, numa_group->active_nodes);
+		if (faults * ACTIVE_NODE_FRACTION > max_faults)
+			active_nodes++;
 	}
+
+	numa_group->max_faults_cpu = max_faults;
+	numa_group->active_nodes = active_nodes;
 }
 
 /*
@@ -1928,7 +2001,7 @@ static void task_numa_placement(struct task_struct *p)
 	update_task_scan_period(p, fault_types[0], fault_types[1]);
 
 	if (p->numa_group) {
-		update_numa_active_node_mask(p->numa_group);
+		numa_group_count_active_nodes(p->numa_group);
 		spin_unlock_irq(group_lock);
 		max_nid = preferred_group_nid(p, max_group_nid);
 	}
@@ -1972,14 +2045,14 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 			return;
 
 		atomic_set(&grp->refcount, 1);
+		grp->active_nodes = 1;
+		grp->max_faults_cpu = 0;
 		spin_lock_init(&grp->lock);
 		grp->gid = p->pid;
 		/* Second half of the array tracks nids where faults happen */
 		grp->faults_cpu = grp->faults + NR_NUMA_HINT_FAULT_TYPES *
 						nr_node_ids;
 
-		node_set(task_node(current), grp->active_nodes);
-
 		for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
 			grp->faults[i] = p->numa_faults[i];
 
@@ -2093,6 +2166,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 	bool migrated = flags & TNF_MIGRATED;
 	int cpu_node = task_node(current);
 	int local = !!(flags & TNF_FAULT_LOCAL);
+	struct numa_group *ng;
 	int priv;
 
 	if (!static_branch_likely(&sched_numa_balancing))
@@ -2133,9 +2207,10 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 	 * actively using should be counted as local. This allows the
 	 * scan rate to slow down when a workload has settled down.
 	 */
-	if (!priv && !local && p->numa_group &&
-			node_isset(cpu_node, p->numa_group->active_nodes) &&
-			node_isset(mem_node, p->numa_group->active_nodes))
+	ng = p->numa_group;
+	if (!priv && !local && ng && ng->active_nodes > 1 &&
+				numa_is_active_node(cpu_node, ng) &&
+				numa_is_active_node(mem_node, ng))
 		local = 1;
 
 	task_numa_placement(p);
@@ -2180,6 +2255,7 @@ void task_numa_work(struct callback_head *work)
 	unsigned long migrate, next_scan, now = jiffies;
 	struct task_struct *p = current;
 	struct mm_struct *mm = p->mm;
+	u64 runtime = p->se.sum_exec_runtime;
 	struct vm_area_struct *vma;
 	unsigned long start, end;
 	unsigned long nr_pte_updates = 0;
@@ -2302,6 +2378,17 @@ out:
 	else
 		reset_ptenuma_scan(p);
 	up_read(&mm->mmap_sem);
+
+	/*
+	 * Make sure tasks use at least 32x as much time to run other code
+	 * than they used here, to limit NUMA PTE scanning overhead to 3% max.
+	 * Usually update_task_scan_period slows down scanning enough; on an
+	 * overloaded system we need to limit overhead on a per task basis.
+	 */
+	if (unlikely(p->se.sum_exec_runtime != runtime)) {
+		u64 diff = p->se.sum_exec_runtime - runtime;
+		p->node_stamp += 32 * diff;
+	}
 }
 
 /*
@@ -2695,12 +2782,64 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
 {
 	long delta = cfs_rq->avg.load_avg - cfs_rq->tg_load_avg_contrib;
 
+	/*
+	 * No need to update load_avg for root_task_group as it is not used.
+	 */
+	if (cfs_rq->tg == &root_task_group)
+		return;
+
 	if (force || abs(delta) > cfs_rq->tg_load_avg_contrib / 64) {
 		atomic_long_add(delta, &cfs_rq->tg->load_avg);
 		cfs_rq->tg_load_avg_contrib = cfs_rq->avg.load_avg;
 	}
 }
 
+/*
+ * Called within set_task_rq() right before setting a task's cpu. The
+ * caller only guarantees p->pi_lock is held; no other assumptions,
+ * including the state of rq->lock, should be made.
+ */
+void set_task_rq_fair(struct sched_entity *se,
+		      struct cfs_rq *prev, struct cfs_rq *next)
+{
+	if (!sched_feat(ATTACH_AGE_LOAD))
+		return;
+
+	/*
+	 * We are supposed to update the task to "current" time, then its up to
+	 * date and ready to go to new CPU/cfs_rq. But we have difficulty in
+	 * getting what current time is, so simply throw away the out-of-date
+	 * time. This will result in the wakee task is less decayed, but giving
+	 * the wakee more load sounds not bad.
+	 */
+	if (se->avg.last_update_time && prev) {
+		u64 p_last_update_time;
+		u64 n_last_update_time;
+
+#ifndef CONFIG_64BIT
+		u64 p_last_update_time_copy;
+		u64 n_last_update_time_copy;
+
+		do {
+			p_last_update_time_copy = prev->load_last_update_time_copy;
+			n_last_update_time_copy = next->load_last_update_time_copy;
+
+			smp_rmb();
+
+			p_last_update_time = prev->avg.last_update_time;
+			n_last_update_time = next->avg.last_update_time;
+
+		} while (p_last_update_time != p_last_update_time_copy ||
+			 n_last_update_time != n_last_update_time_copy);
+#else
+		p_last_update_time = prev->avg.last_update_time;
+		n_last_update_time = next->avg.last_update_time;
+#endif
+		__update_load_avg(p_last_update_time, cpu_of(rq_of(prev)),
+				  &se->avg, 0, 0, NULL);
+		se->avg.last_update_time = n_last_update_time;
+	}
+}
 #else /* CONFIG_FAIR_GROUP_SCHED */
 static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
 #endif /* CONFIG_FAIR_GROUP_SCHED */
@@ -2834,48 +2973,48 @@ dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		max_t(s64,  cfs_rq->runnable_load_sum - se->avg.load_sum, 0);
 }
 
-/*
- * Task first catches up with cfs_rq, and then subtract
- * itself from the cfs_rq (task must be off the queue now).
- */
-void remove_entity_load_avg(struct sched_entity *se)
-{
-	struct cfs_rq *cfs_rq = cfs_rq_of(se);
-	u64 last_update_time;
-
 #ifndef CONFIG_64BIT
+static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
+{
 	u64 last_update_time_copy;
+	u64 last_update_time;
 
 	do {
 		last_update_time_copy = cfs_rq->load_last_update_time_copy;
 		smp_rmb();
 		last_update_time = cfs_rq->avg.last_update_time;
 	} while (last_update_time != last_update_time_copy);
-#else
-	last_update_time = cfs_rq->avg.last_update_time;
-#endif
 
-	__update_load_avg(last_update_time, cpu_of(rq_of(cfs_rq)), &se->avg, 0, 0, NULL);
-	atomic_long_add(se->avg.load_avg, &cfs_rq->removed_load_avg);
-	atomic_long_add(se->avg.util_avg, &cfs_rq->removed_util_avg);
+	return last_update_time;
 }
-
-/*
- * Update the rq's load with the elapsed running time before entering
- * idle. if the last scheduled task is not a CFS task, idle_enter will
- * be the only way to update the runnable statistic.
- */
-void idle_enter_fair(struct rq *this_rq)
+#else
+static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
 {
+	return cfs_rq->avg.last_update_time;
 }
+#endif
 
 /*
- * Update the rq's load with the elapsed idle time before a task is
- * scheduled. if the newly scheduled task is not a CFS task, idle_exit will
- * be the only way to update the runnable statistic.
+ * Task first catches up with cfs_rq, and then subtract
+ * itself from the cfs_rq (task must be off the queue now).
  */
-void idle_exit_fair(struct rq *this_rq)
+void remove_entity_load_avg(struct sched_entity *se)
 {
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+	u64 last_update_time;
+
+	/*
+	 * Newly created task or never used group entity should not be removed
+	 * from its (source) cfs_rq
+	 */
+	if (se->avg.last_update_time == 0)
+		return;
+
+	last_update_time = cfs_rq_last_update_time(cfs_rq);
+
+	__update_load_avg(last_update_time, cpu_of(rq_of(cfs_rq)), &se->avg, 0, 0, NULL);
+	atomic_long_add(se->avg.load_avg, &cfs_rq->removed_load_avg);
+	atomic_long_add(se->avg.util_avg, &cfs_rq->removed_util_avg);
 }
 
 static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq)
@@ -3020,6 +3159,26 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq);
 
+static inline void check_schedstat_required(void)
+{
+#ifdef CONFIG_SCHEDSTATS
+	if (schedstat_enabled())
+		return;
+
+	/* Force schedstat enabled if a dependent tracepoint is active */
+	if (trace_sched_stat_wait_enabled()    ||
+			trace_sched_stat_sleep_enabled()   ||
+			trace_sched_stat_iowait_enabled()  ||
+			trace_sched_stat_blocked_enabled() ||
+			trace_sched_stat_runtime_enabled())  {
+		pr_warn_once("Scheduler tracepoints stat_sleep, stat_iowait, "
+			     "stat_blocked and stat_runtime require the "
+			     "kernel parameter schedstats=enabled or "
+			     "kernel.sched_schedstats=1\n");
+	}
+#endif
+}
+
 static void
 enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
@@ -3040,11 +3199,15 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	if (flags & ENQUEUE_WAKEUP) {
 		place_entity(cfs_rq, se, 0);
-		enqueue_sleeper(cfs_rq, se);
+		if (schedstat_enabled())
+			enqueue_sleeper(cfs_rq, se);
 	}
 
-	update_stats_enqueue(cfs_rq, se);
-	check_spread(cfs_rq, se);
+	check_schedstat_required();
+	if (schedstat_enabled()) {
+		update_stats_enqueue(cfs_rq, se);
+		check_spread(cfs_rq, se);
+	}
 	if (se != cfs_rq->curr)
 		__enqueue_entity(cfs_rq, se);
 	se->on_rq = 1;
@@ -3111,19 +3274,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	update_curr(cfs_rq);
 	dequeue_entity_load_avg(cfs_rq, se);
 
-	update_stats_dequeue(cfs_rq, se);
-	if (flags & DEQUEUE_SLEEP) {
-#ifdef CONFIG_SCHEDSTATS
-		if (entity_is_task(se)) {
-			struct task_struct *tsk = task_of(se);
-
-			if (tsk->state & TASK_INTERRUPTIBLE)
-				se->statistics.sleep_start = rq_clock(rq_of(cfs_rq));
-			if (tsk->state & TASK_UNINTERRUPTIBLE)
-				se->statistics.block_start = rq_clock(rq_of(cfs_rq));
-		}
-#endif
-	}
+	if (schedstat_enabled())
+		update_stats_dequeue(cfs_rq, se, flags);
 
 	clear_buddies(cfs_rq, se);
 
@@ -3197,7 +3349,8 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		 * a CPU. So account for the time it spent waiting on the
 		 * runqueue.
 		 */
-		update_stats_wait_end(cfs_rq, se);
+		if (schedstat_enabled())
+			update_stats_wait_end(cfs_rq, se);
 		__dequeue_entity(cfs_rq, se);
 		update_load_avg(se, 1);
 	}
@@ -3210,7 +3363,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	 * least twice that of our own weight (i.e. dont track it
 	 * when there are only lesser-weight tasks around):
 	 */
-	if (rq_of(cfs_rq)->load.weight >= 2*se->load.weight) {
+	if (schedstat_enabled() && rq_of(cfs_rq)->load.weight >= 2*se->load.weight) {
 		se->statistics.slice_max = max(se->statistics.slice_max,
 			se->sum_exec_runtime - se->prev_sum_exec_runtime);
 	}
@@ -3293,9 +3446,13 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 	/* throttle cfs_rqs exceeding runtime */
 	check_cfs_rq_runtime(cfs_rq);
 
-	check_spread(cfs_rq, prev);
+	if (schedstat_enabled()) {
+		check_spread(cfs_rq, prev);
+		if (prev->on_rq)
+			update_stats_wait_start(cfs_rq, prev);
+	}
+
 	if (prev->on_rq) {
-		update_stats_wait_start(cfs_rq, prev);
 		/* Put 'current' back into the tree. */
 		__enqueue_entity(cfs_rq, prev);
 		/* in !on_rq case, update occurred at dequeue */
@@ -4265,42 +4422,37 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
  */
 
 /*
- * The exact cpuload at various idx values, calculated at every tick would be
- * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load
+ * The exact cpuload calculated at every tick would be:
+ *
+ *   load' = (1 - 1/2^i) * load + (1/2^i) * cur_load
  *
- * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called
- * on nth tick when cpu may be busy, then we have:
- * load = ((2^idx - 1) / 2^idx)^(n-1) * load
- * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load
+ * If a cpu misses updates for n ticks (as it was idle) and update gets
+ * called on the n+1-th tick when cpu may be busy, then we have:
+ *
+ *   load_n   = (1 - 1/2^i)^n * load_0
+ *   load_n+1 = (1 - 1/2^i)   * load_n + (1/2^i) * cur_load
  *
  * decay_load_missed() below does efficient calculation of
- * load = ((2^idx - 1) / 2^idx)^(n-1) * load
- * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load
+ *
+ *   load' = (1 - 1/2^i)^n * load
+ *
+ * Because x^(n+m) := x^n * x^m we can decompose any x^n in power-of-2 factors.
+ * This allows us to precompute the above in said factors, thereby allowing the
+ * reduction of an arbitrary n in O(log_2 n) steps. (See also
+ * fixed_power_int())
  *
  * The calculation is approximated on a 128 point scale.
- * degrade_zero_ticks is the number of ticks after which load at any
- * particular idx is approximated to be zero.
- * degrade_factor is a precomputed table, a row for each load idx.
- * Each column corresponds to degradation factor for a power of two ticks,
- * based on 128 point scale.
- * Example:
- * row 2, col 3 (=12) says that the degradation at load idx 2 after
- * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8).
- *
- * With this power of 2 load factors, we can degrade the load n times
- * by looking at 1 bits in n and doing as many mult/shift instead of
- * n mult/shifts needed by the exact degradation.
  */
 #define DEGRADE_SHIFT		7
-static const unsigned char
-		degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128};
-static const unsigned char
-		degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = {
-					{0, 0, 0, 0, 0, 0, 0, 0},
-					{64, 32, 8, 0, 0, 0, 0, 0},
-					{96, 72, 40, 12, 1, 0, 0},
-					{112, 98, 75, 43, 15, 1, 0},
-					{120, 112, 98, 76, 45, 16, 2} };
+
+static const u8 degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128};
+static const u8 degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = {
+	{   0,   0,  0,  0,  0,  0, 0, 0 },
+	{  64,  32,  8,  0,  0,  0, 0, 0 },
+	{  96,  72, 40, 12,  1,  0, 0, 0 },
+	{ 112,  98, 75, 43, 15,  1, 0, 0 },
+	{ 120, 112, 98, 76, 45, 16, 2, 0 }
+};
 
 /*
  * Update cpu_load for any missed ticks, due to tickless idle. The backlog
@@ -4331,14 +4483,46 @@ decay_load_missed(unsigned long load, unsigned long missed_updates, int idx)
 	return load;
 }
 
-/*
+/**
+ * __update_cpu_load - update the rq->cpu_load[] statistics
+ * @this_rq: The rq to update statistics for
+ * @this_load: The current load
+ * @pending_updates: The number of missed updates
+ * @active: !0 for NOHZ_FULL
+ *
  * Update rq->cpu_load[] statistics. This function is usually called every
- * scheduler tick (TICK_NSEC). With tickless idle this will not be called
- * every tick. We fix it up based on jiffies.
+ * scheduler tick (TICK_NSEC).
+ *
+ * This function computes a decaying average:
+ *
+ *   load[i]' = (1 - 1/2^i) * load[i] + (1/2^i) * load
+ *
+ * Because of NOHZ it might not get called on every tick which gives need for
+ * the @pending_updates argument.
+ *
+ *   load[i]_n = (1 - 1/2^i) * load[i]_n-1 + (1/2^i) * load_n-1
+ *             = A * load[i]_n-1 + B ; A := (1 - 1/2^i), B := (1/2^i) * load
+ *             = A * (A * load[i]_n-2 + B) + B
+ *             = A * (A * (A * load[i]_n-3 + B) + B) + B
+ *             = A^3 * load[i]_n-3 + (A^2 + A + 1) * B
+ *             = A^n * load[i]_0 + (A^(n-1) + A^(n-2) + ... + 1) * B
+ *             = A^n * load[i]_0 + ((1 - A^n) / (1 - A)) * B
+ *             = (1 - 1/2^i)^n * (load[i]_0 - load) + load
+ *
+ * In the above we've assumed load_n := load, which is true for NOHZ_FULL as
+ * any change in load would have resulted in the tick being turned back on.
+ *
+ * For regular NOHZ, this reduces to:
+ *
+ *   load[i]_n = (1 - 1/2^i)^n * load[i]_0
+ *
+ * see decay_load_misses(). For NOHZ_FULL we get to subtract and add the extra
+ * term. See the @active paramter.
  */
 static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
-			      unsigned long pending_updates)
+			      unsigned long pending_updates, int active)
 {
+	unsigned long tickless_load = active ? this_rq->cpu_load[0] : 0;
 	int i, scale;
 
 	this_rq->nr_load_updates++;
@@ -4352,6 +4536,15 @@ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
 
 		old_load = this_rq->cpu_load[i];
 		old_load = decay_load_missed(old_load, pending_updates - 1, i);
+		if (tickless_load) {
+			old_load -= decay_load_missed(tickless_load, pending_updates - 1, i);
+			/*
+			 * old_load can never be a negative value because a
+			 * decayed tickless_load cannot be greater than the
+			 * original tickless_load.
+			 */
+			old_load += tickless_load;
+		}
 		new_load = this_load;
 		/*
 		 * Round up the averaging division if load is increasing. This
@@ -4374,6 +4567,25 @@ static unsigned long weighted_cpuload(const int cpu)
 }
 
 #ifdef CONFIG_NO_HZ_COMMON
+static void __update_cpu_load_nohz(struct rq *this_rq,
+				   unsigned long curr_jiffies,
+				   unsigned long load,
+				   int active)
+{
+	unsigned long pending_updates;
+
+	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+	if (pending_updates) {
+		this_rq->last_load_update_tick = curr_jiffies;
+		/*
+		 * In the regular NOHZ case, we were idle, this means load 0.
+		 * In the NOHZ_FULL case, we were non-idle, we should consider
+		 * its weighted load.
+		 */
+		__update_cpu_load(this_rq, load, pending_updates, active);
+	}
+}
+
 /*
  * There is no sane way to deal with nohz on smp when using jiffies because the
  * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading
@@ -4391,46 +4603,31 @@ static unsigned long weighted_cpuload(const int cpu)
  * Called from nohz_idle_balance() to update the load ratings before doing the
  * idle balance.
  */
-static void update_idle_cpu_load(struct rq *this_rq)
+static void update_cpu_load_idle(struct rq *this_rq)
 {
-	unsigned long curr_jiffies = READ_ONCE(jiffies);
-	unsigned long load = weighted_cpuload(cpu_of(this_rq));
-	unsigned long pending_updates;
-
 	/*
 	 * bail if there's load or we're actually up-to-date.
 	 */
-	if (load || curr_jiffies == this_rq->last_load_update_tick)
+	if (weighted_cpuload(cpu_of(this_rq)))
 		return;
 
-	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
-	this_rq->last_load_update_tick = curr_jiffies;
-
-	__update_cpu_load(this_rq, load, pending_updates);
+	__update_cpu_load_nohz(this_rq, READ_ONCE(jiffies), 0, 0);
 }
 
 /*
  * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed.
  */
-void update_cpu_load_nohz(void)
+void update_cpu_load_nohz(int active)
 {
 	struct rq *this_rq = this_rq();
 	unsigned long curr_jiffies = READ_ONCE(jiffies);
-	unsigned long pending_updates;
+	unsigned long load = active ? weighted_cpuload(cpu_of(this_rq)) : 0;
 
 	if (curr_jiffies == this_rq->last_load_update_tick)
 		return;
 
 	raw_spin_lock(&this_rq->lock);
-	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
-	if (pending_updates) {
-		this_rq->last_load_update_tick = curr_jiffies;
-		/*
-		 * We were idle, this means load 0, the current load might be
-		 * !0 due to remote wakeups and the sort.
-		 */
-		__update_cpu_load(this_rq, 0, pending_updates);
-	}
+	__update_cpu_load_nohz(this_rq, curr_jiffies, load, active);
 	raw_spin_unlock(&this_rq->lock);
 }
 #endif /* CONFIG_NO_HZ */
@@ -4442,10 +4639,10 @@ void update_cpu_load_active(struct rq *this_rq)
 {
 	unsigned long load = weighted_cpuload(cpu_of(this_rq));
 	/*
-	 * See the mess around update_idle_cpu_load() / update_cpu_load_nohz().
+	 * See the mess around update_cpu_load_idle() / update_cpu_load_nohz().
 	 */
 	this_rq->last_load_update_tick = jiffies;
-	__update_cpu_load(this_rq, load, 1);
+	__update_cpu_load(this_rq, load, 1, 1);
 }
 
 /*
@@ -5032,8 +5229,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 /*
  * Called immediately before a task is migrated to a new cpu; task_cpu(p) and
  * cfs_rq_of(p) references at time of call are still valid and identify the
- * previous cpu.  However, the caller only guarantees p->pi_lock is held; no
- * other assumptions, including the state of rq->lock, should be made.
+ * previous cpu. The caller guarantees p->pi_lock or task_rq(p)->lock is held.
  */
 static void migrate_task_rq_fair(struct task_struct *p)
 {
@@ -5746,8 +5942,8 @@ static void detach_task(struct task_struct *p, struct lb_env *env)
 {
 	lockdep_assert_held(&env->src_rq->lock);
 
-	deactivate_task(env->src_rq, p, 0);
 	p->on_rq = TASK_ON_RQ_MIGRATING;
+	deactivate_task(env->src_rq, p, 0);
 	set_task_cpu(p, env->dst_cpu);
 }
 
@@ -5880,8 +6076,8 @@ static void attach_task(struct rq *rq, struct task_struct *p)
 	lockdep_assert_held(&rq->lock);
 
 	BUG_ON(task_rq(p) != rq);
-	p->on_rq = TASK_ON_RQ_QUEUED;
 	activate_task(rq, p, 0);
+	p->on_rq = TASK_ON_RQ_QUEUED;
 	check_preempt_curr(rq, p, 0);
 }
 
@@ -6327,7 +6523,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 			bool *overload)
 {
 	unsigned long load;
-	int i;
+	int i, nr_running;
 
 	memset(sgs, 0, sizeof(*sgs));
 
@@ -6344,7 +6540,8 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		sgs->group_util += cpu_util(i);
 		sgs->sum_nr_running += rq->cfs.h_nr_running;
 
-		if (rq->nr_running > 1)
+		nr_running = rq->nr_running;
+		if (nr_running > 1)
 			*overload = true;
 
 #ifdef CONFIG_NUMA_BALANCING
@@ -6352,7 +6549,10 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		sgs->nr_preferred_running += rq->nr_preferred_running;
 #endif
 		sgs->sum_weighted_load += weighted_cpuload(i);
-		if (idle_cpu(i))
+		/*
+		 * No need to call idle_cpu() if nr_running is not 0
+		 */
+		if (!nr_running && idle_cpu(i))
 			sgs->idle_cpus++;
 	}
 
@@ -7273,8 +7473,6 @@ static int idle_balance(struct rq *this_rq)
 	int pulled_task = 0;
 	u64 curr_cost = 0;
 
-	idle_enter_fair(this_rq);
-
 	/*
 	 * We must set idle_stamp _before_ calling idle_balance(), such that we
 	 * measure the duration of idle_balance() as idle time.
@@ -7355,10 +7553,8 @@ out:
 	if (this_rq->nr_running != this_rq->cfs.h_nr_running)
 		pulled_task = -1;
 
-	if (pulled_task) {
-		idle_exit_fair(this_rq);
+	if (pulled_task)
 		this_rq->idle_stamp = 0;
-	}
 
 	return pulled_task;
 }
@@ -7737,7 +7933,7 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
 		if (time_after_eq(jiffies, rq->next_balance)) {
 			raw_spin_lock_irq(&rq->lock);
 			update_rq_clock(rq);
-			update_idle_cpu_load(rq);
+			update_cpu_load_idle(rq);
 			raw_spin_unlock_irq(&rq->lock);
 			rebalance_domains(rq, CPU_IDLE);
 		}
@@ -8123,11 +8319,8 @@ void free_fair_sched_group(struct task_group *tg)
 	for_each_possible_cpu(i) {
 		if (tg->cfs_rq)
 			kfree(tg->cfs_rq[i]);
-		if (tg->se) {
-			if (tg->se[i])
-				remove_entity_load_avg(tg->se[i]);
+		if (tg->se)
 			kfree(tg->se[i]);
-		}
 	}
 
 	kfree(tg->cfs_rq);
@@ -8175,21 +8368,29 @@ err:
 	return 0;
 }
 
-void unregister_fair_sched_group(struct task_group *tg, int cpu)
+void unregister_fair_sched_group(struct task_group *tg)
 {
-	struct rq *rq = cpu_rq(cpu);
 	unsigned long flags;
+	struct rq *rq;
+	int cpu;
 
-	/*
-	* Only empty task groups can be destroyed; so we can speculatively
-	* check on_list without danger of it being re-added.
-	*/
-	if (!tg->cfs_rq[cpu]->on_list)
-		return;
+	for_each_possible_cpu(cpu) {
+		if (tg->se[cpu])
+			remove_entity_load_avg(tg->se[cpu]);
 
-	raw_spin_lock_irqsave(&rq->lock, flags);
-	list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+		/*
+		 * Only empty task groups can be destroyed; so we can speculatively
+		 * check on_list without danger of it being re-added.
+		 */
+		if (!tg->cfs_rq[cpu]->on_list)
+			continue;
+
+		rq = cpu_rq(cpu);
+
+		raw_spin_lock_irqsave(&rq->lock, flags);
+		list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
+		raw_spin_unlock_irqrestore(&rq->lock, flags);
+	}
 }
 
 void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
@@ -8271,7 +8472,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 	return 1;
 }
 
-void unregister_fair_sched_group(struct task_group *tg, int cpu) { }
+void unregister_fair_sched_group(struct task_group *tg) { }
 
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 4a2ef5a02..544a7133c 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -97,12 +97,6 @@ void default_idle_call(void)
 static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		      int next_state)
 {
-	/* Fall back to the default arch idle method on errors. */
-	if (next_state < 0) {
-		default_idle_call();
-		return next_state;
-	}
-
 	/*
 	 * The idle task must be scheduled, it is pointless to go to idle, just
 	 * update no idle residency and return.
@@ -168,7 +162,7 @@ static void cpuidle_idle_call(void)
 	 */
 	if (idle_should_freeze()) {
 		entered_state = cpuidle_enter_freeze(drv, dev);
-		if (entered_state >= 0) {
+		if (entered_state > 0) {
 			local_irq_enable();
 			goto exit_idle;
 		}
@@ -219,6 +213,7 @@ static void cpu_idle_loop(void)
 		 */
 
 		__current_set_polling();
+		quiet_vmstat();
 		tick_nohz_idle_enter();
 
 		while (!need_resched()) {
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index c4ae0f1fd..47ce94931 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -47,7 +47,6 @@ dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)
 
 static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
 {
-	idle_exit_fair(rq);
 	rq_last_tick_reset(rq);
 }
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 8ec86abe0..a774b4dbf 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -58,7 +58,15 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 	raw_spin_lock(&rt_b->rt_runtime_lock);
 	if (!rt_b->rt_period_active) {
 		rt_b->rt_period_active = 1;
-		hrtimer_forward_now(&rt_b->rt_period_timer, rt_b->rt_period);
+		/*
+		 * SCHED_DEADLINE updates the bandwidth, as a run away
+		 * RT task with a DL task could hog a CPU. But DL does
+		 * not reset the period. If a deadline task was running
+		 * without an RT task running, it can cause RT tasks to
+		 * throttle when they start up. Kick the timer right away
+		 * to update the period.
+		 */
+		hrtimer_forward_now(&rt_b->rt_period_timer, ns_to_ktime(0));
 		hrtimer_start_expires(&rt_b->rt_period_timer, HRTIMER_MODE_ABS_PINNED);
 	}
 	raw_spin_unlock(&rt_b->rt_runtime_lock);
@@ -436,7 +444,7 @@ static void dequeue_top_rt_rq(struct rt_rq *rt_rq);
 
 static inline int on_rt_rq(struct sched_rt_entity *rt_se)
 {
-	return !list_empty(&rt_se->run_list);
+	return rt_se->on_rq;
 }
 
 #ifdef CONFIG_RT_GROUP_SCHED
@@ -482,8 +490,8 @@ static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
 	return rt_se->my_q;
 }
 
-static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head);
-static void dequeue_rt_entity(struct sched_rt_entity *rt_se);
+static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags);
+static void dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags);
 
 static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 {
@@ -499,7 +507,7 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 		if (!rt_se)
 			enqueue_top_rt_rq(rt_rq);
 		else if (!on_rt_rq(rt_se))
-			enqueue_rt_entity(rt_se, false);
+			enqueue_rt_entity(rt_se, 0);
 
 		if (rt_rq->highest_prio.curr < curr->prio)
 			resched_curr(rq);
@@ -516,7 +524,7 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
 	if (!rt_se)
 		dequeue_top_rt_rq(rt_rq);
 	else if (on_rt_rq(rt_se))
-		dequeue_rt_entity(rt_se);
+		dequeue_rt_entity(rt_se, 0);
 }
 
 static inline int rt_rq_throttled(struct rt_rq *rt_rq)
@@ -1166,7 +1174,30 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 	dec_rt_group(rt_se, rt_rq);
 }
 
-static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head)
+/*
+ * Change rt_se->run_list location unless SAVE && !MOVE
+ *
+ * assumes ENQUEUE/DEQUEUE flags match
+ */
+static inline bool move_entity(unsigned int flags)
+{
+	if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) == DEQUEUE_SAVE)
+		return false;
+
+	return true;
+}
+
+static void __delist_rt_entity(struct sched_rt_entity *rt_se, struct rt_prio_array *array)
+{
+	list_del_init(&rt_se->run_list);
+
+	if (list_empty(array->queue + rt_se_prio(rt_se)))
+		__clear_bit(rt_se_prio(rt_se), array->bitmap);
+
+	rt_se->on_list = 0;
+}
+
+static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
 {
 	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
 	struct rt_prio_array *array = &rt_rq->active;
@@ -1179,26 +1210,37 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head)
 	 * get throttled and the current group doesn't have any other
 	 * active members.
 	 */
-	if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running))
+	if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running)) {
+		if (rt_se->on_list)
+			__delist_rt_entity(rt_se, array);
 		return;
+	}
 
-	if (head)
-		list_add(&rt_se->run_list, queue);
-	else
-		list_add_tail(&rt_se->run_list, queue);
-	__set_bit(rt_se_prio(rt_se), array->bitmap);
+	if (move_entity(flags)) {
+		WARN_ON_ONCE(rt_se->on_list);
+		if (flags & ENQUEUE_HEAD)
+			list_add(&rt_se->run_list, queue);
+		else
+			list_add_tail(&rt_se->run_list, queue);
+
+		__set_bit(rt_se_prio(rt_se), array->bitmap);
+		rt_se->on_list = 1;
+	}
+	rt_se->on_rq = 1;
 
 	inc_rt_tasks(rt_se, rt_rq);
 }
 
-static void __dequeue_rt_entity(struct sched_rt_entity *rt_se)
+static void __dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
 {
 	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
 	struct rt_prio_array *array = &rt_rq->active;
 
-	list_del_init(&rt_se->run_list);
-	if (list_empty(array->queue + rt_se_prio(rt_se)))
-		__clear_bit(rt_se_prio(rt_se), array->bitmap);
+	if (move_entity(flags)) {
+		WARN_ON_ONCE(!rt_se->on_list);
+		__delist_rt_entity(rt_se, array);
+	}
+	rt_se->on_rq = 0;
 
 	dec_rt_tasks(rt_se, rt_rq);
 }
@@ -1207,7 +1249,7 @@ static void __dequeue_rt_entity(struct sched_rt_entity *rt_se)
  * Because the prio of an upper entry depends on the lower
  * entries, we must remove entries top - down.
  */
-static void dequeue_rt_stack(struct sched_rt_entity *rt_se)
+static void dequeue_rt_stack(struct sched_rt_entity *rt_se, unsigned int flags)
 {
 	struct sched_rt_entity *back = NULL;
 
@@ -1220,31 +1262,31 @@ static void dequeue_rt_stack(struct sched_rt_entity *rt_se)
 
 	for (rt_se = back; rt_se; rt_se = rt_se->back) {
 		if (on_rt_rq(rt_se))
-			__dequeue_rt_entity(rt_se);
+			__dequeue_rt_entity(rt_se, flags);
 	}
 }
 
-static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head)
+static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
 {
 	struct rq *rq = rq_of_rt_se(rt_se);
 
-	dequeue_rt_stack(rt_se);
+	dequeue_rt_stack(rt_se, flags);
 	for_each_sched_rt_entity(rt_se)
-		__enqueue_rt_entity(rt_se, head);
+		__enqueue_rt_entity(rt_se, flags);
 	enqueue_top_rt_rq(&rq->rt);
 }
 
-static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
+static void dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
 {
 	struct rq *rq = rq_of_rt_se(rt_se);
 
-	dequeue_rt_stack(rt_se);
+	dequeue_rt_stack(rt_se, flags);
 
 	for_each_sched_rt_entity(rt_se) {
 		struct rt_rq *rt_rq = group_rt_rq(rt_se);
 
 		if (rt_rq && rt_rq->rt_nr_running)
-			__enqueue_rt_entity(rt_se, false);
+			__enqueue_rt_entity(rt_se, flags);
 	}
 	enqueue_top_rt_rq(&rq->rt);
 }
@@ -1260,7 +1302,7 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 	if (flags & ENQUEUE_WAKEUP)
 		rt_se->timeout = 0;
 
-	enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD);
+	enqueue_rt_entity(rt_se, flags);
 
 	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
@@ -1271,7 +1313,7 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 	struct sched_rt_entity *rt_se = &p->rt;
 
 	update_curr_rt(rq);
-	dequeue_rt_entity(rt_se);
+	dequeue_rt_entity(rt_se, flags);
 
 	dequeue_pushable_task(rq, p);
 }
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b242775bf..ef5875fff 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3,6 +3,7 @@
 #include <linux/sched/sysctl.h>
 #include <linux/sched/rt.h>
 #include <linux/sched/deadline.h>
+#include <linux/binfmts.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <linux/stop_machine.h>
@@ -248,7 +249,12 @@ struct task_group {
 	unsigned long shares;
 
 #ifdef	CONFIG_SMP
-	atomic_long_t load_avg;
+	/*
+	 * load_avg can be heavily contended at clock tick time, so put
+	 * it in its own cacheline separated from the fields above which
+	 * will also be accessed at each tick.
+	 */
+	atomic_long_t load_avg ____cacheline_aligned;
 #endif
 #endif
 
@@ -308,12 +314,11 @@ extern int tg_nop(struct task_group *tg, void *data);
 
 extern void free_fair_sched_group(struct task_group *tg);
 extern int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent);
-extern void unregister_fair_sched_group(struct task_group *tg, int cpu);
+extern void unregister_fair_sched_group(struct task_group *tg);
 extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 			struct sched_entity *se, int cpu,
 			struct sched_entity *parent);
 extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
-extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
 
 extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
 extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
@@ -335,7 +340,15 @@ extern void sched_move_task(struct task_struct *tsk);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
-#endif
+
+#ifdef CONFIG_SMP
+extern void set_task_rq_fair(struct sched_entity *se,
+			     struct cfs_rq *prev, struct cfs_rq *next);
+#else /* !CONFIG_SMP */
+static inline void set_task_rq_fair(struct sched_entity *se,
+			     struct cfs_rq *prev, struct cfs_rq *next) { }
+#endif /* CONFIG_SMP */
+#endif /* CONFIG_FAIR_GROUP_SCHED */
 
 #else /* CONFIG_CGROUP_SCHED */
 
@@ -896,6 +909,18 @@ static inline unsigned int group_first_cpu(struct sched_group *group)
 
 extern int group_balance_cpu(struct sched_group *sg);
 
+#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
+void register_sched_domain_sysctl(void);
+void unregister_sched_domain_sysctl(void);
+#else
+static inline void register_sched_domain_sysctl(void)
+{
+}
+static inline void unregister_sched_domain_sysctl(void)
+{
+}
+#endif
+
 #else
 
 static inline void sched_ttwu_pending(void) { }
@@ -933,6 +958,7 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
 #endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+	set_task_rq_fair(&p->se, p->se.cfs_rq, tg->cfs_rq[cpu]);
 	p->se.cfs_rq = tg->cfs_rq[cpu];
 	p->se.parent = tg->se[cpu];
 #endif
@@ -1008,6 +1034,7 @@ extern struct static_key sched_feat_keys[__SCHED_FEAT_NR];
 #endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */
 
 extern struct static_key_false sched_numa_balancing;
+extern struct static_key_false sched_schedstats;
 
 static inline u64 global_rt_period(void)
 {
@@ -1076,7 +1103,7 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 	 * In particular, the load of prev->state in finish_task_switch() must
 	 * happen before this.
 	 *
-	 * Pairs with the control dependency and rmb in try_to_wake_up().
+	 * Pairs with the smp_cond_acquire() in try_to_wake_up().
 	 */
 	smp_store_release(&prev->on_cpu, 0);
 #endif
@@ -1113,59 +1140,43 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 #define WEIGHT_IDLEPRIO                3
 #define WMULT_IDLEPRIO         1431655765
 
-/*
- * Nice levels are multiplicative, with a gentle 10% change for every
- * nice level changed. I.e. when a CPU-bound task goes from nice 0 to
- * nice 1, it will get ~10% less CPU time than another CPU-bound task
- * that remained on nice 0.
- *
- * The "10% effect" is relative and cumulative: from _any_ nice level,
- * if you go up 1 level, it's -10% CPU usage, if you go down 1 level
- * it's +10% CPU usage. (to achieve that we use a multiplier of 1.25.
- * If a task goes up by ~10% and another task goes down by ~10% then
- * the relative distance between them is ~25%.)
- */
-static const int prio_to_weight[40] = {
- /* -20 */     88761,     71755,     56483,     46273,     36291,
- /* -15 */     29154,     23254,     18705,     14949,     11916,
- /* -10 */      9548,      7620,      6100,      4904,      3906,
- /*  -5 */      3121,      2501,      1991,      1586,      1277,
- /*   0 */      1024,       820,       655,       526,       423,
- /*   5 */       335,       272,       215,       172,       137,
- /*  10 */       110,        87,        70,        56,        45,
- /*  15 */        36,        29,        23,        18,        15,
-};
+extern const int sched_prio_to_weight[40];
+extern const u32 sched_prio_to_wmult[40];
 
 /*
- * Inverse (2^32/x) values of the prio_to_weight[] array, precalculated.
+ * {de,en}queue flags:
+ *
+ * DEQUEUE_SLEEP  - task is no longer runnable
+ * ENQUEUE_WAKEUP - task just became runnable
+ *
+ * SAVE/RESTORE - an otherwise spurious dequeue/enqueue, done to ensure tasks
+ *                are in a known state which allows modification. Such pairs
+ *                should preserve as much state as possible.
+ *
+ * MOVE - paired with SAVE/RESTORE, explicitly does not preserve the location
+ *        in the runqueue.
+ *
+ * ENQUEUE_HEAD      - place at front of runqueue (tail if not specified)
+ * ENQUEUE_REPLENISH - CBS (replenish runtime and postpone deadline)
+ * ENQUEUE_WAKING    - sched_class::task_waking was called
  *
- * In cases where the weight does not change often, we can use the
- * precalculated inverse to speed up arithmetics by turning divisions
- * into multiplications:
  */
-static const u32 prio_to_wmult[40] = {
- /* -20 */     48388,     59856,     76040,     92818,    118348,
- /* -15 */    147320,    184698,    229616,    287308,    360437,
- /* -10 */    449829,    563644,    704093,    875809,   1099582,
- /*  -5 */   1376151,   1717300,   2157191,   2708050,   3363326,
- /*   0 */   4194304,   5237765,   6557202,   8165337,  10153587,
- /*   5 */  12820798,  15790321,  19976592,  24970740,  31350126,
- /*  10 */  39045157,  49367440,  61356676,  76695844,  95443717,
- /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
-};
+
+#define DEQUEUE_SLEEP		0x01
+#define DEQUEUE_SAVE		0x02 /* matches ENQUEUE_RESTORE */
+#define DEQUEUE_MOVE		0x04 /* matches ENQUEUE_MOVE */
 
 #define ENQUEUE_WAKEUP		0x01
-#define ENQUEUE_HEAD		0x02
+#define ENQUEUE_RESTORE		0x02
+#define ENQUEUE_MOVE		0x04
+
+#define ENQUEUE_HEAD		0x08
+#define ENQUEUE_REPLENISH	0x10
 #ifdef CONFIG_SMP
-#define ENQUEUE_WAKING		0x04	/* sched_class::task_waking was called */
+#define ENQUEUE_WAKING		0x20
 #else
 #define ENQUEUE_WAKING		0x00
 #endif
-#define ENQUEUE_REPLENISH	0x08
-#define ENQUEUE_RESTORE	0x10
-
-#define DEQUEUE_SLEEP		0x01
-#define DEQUEUE_SAVE		0x02
 
 #define RETRY_TASK		((void *)-1UL)
 
@@ -1252,16 +1263,8 @@ extern void update_group_capacity(struct sched_domain *sd, int cpu);
 
 extern void trigger_load_balance(struct rq *rq);
 
-extern void idle_enter_fair(struct rq *this_rq);
-extern void idle_exit_fair(struct rq *this_rq);
-
 extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask);
 
-#else
-
-static inline void idle_enter_fair(struct rq *rq) { }
-static inline void idle_exit_fair(struct rq *rq) { }
-
 #endif
 
 #ifdef CONFIG_CPU_IDLE
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index b0fbc7632..70b3b6a20 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -29,9 +29,10 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)
 	if (rq)
 		rq->rq_sched_info.run_delay += delta;
 }
-# define schedstat_inc(rq, field)	do { (rq)->field++; } while (0)
-# define schedstat_add(rq, field, amt)	do { (rq)->field += (amt); } while (0)
-# define schedstat_set(var, val)	do { var = (val); } while (0)
+# define schedstat_enabled()		static_branch_unlikely(&sched_schedstats)
+# define schedstat_inc(rq, field)	do { if (schedstat_enabled()) { (rq)->field++; } } while (0)
+# define schedstat_add(rq, field, amt)	do { if (schedstat_enabled()) { (rq)->field += (amt); } } while (0)
+# define schedstat_set(var, val)	do { if (schedstat_enabled()) { var = (val); } } while (0)
 #else /* !CONFIG_SCHEDSTATS */
 static inline void
 rq_sched_info_arrive(struct rq *rq, unsigned long long delta)
@@ -42,6 +43,7 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)
 static inline void
 rq_sched_info_depart(struct rq *rq, unsigned long long delta)
 {}
+# define schedstat_enabled()		0
 # define schedstat_inc(rq, field)	do { } while (0)
 # define schedstat_add(rq, field, amt)	do { } while (0)
 # define schedstat_set(var, val)	do { } while (0)
diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c
new file mode 100644
index 000000000..82f0dff90
--- /dev/null
+++ b/kernel/sched/swait.c
@@ -0,0 +1,123 @@
+#include <linux/sched.h>
+#include <linux/swait.h>
+
+void __init_swait_queue_head(struct swait_queue_head *q, const char *name,
+			     struct lock_class_key *key)
+{
+	raw_spin_lock_init(&q->lock);
+	lockdep_set_class_and_name(&q->lock, key, name);
+	INIT_LIST_HEAD(&q->task_list);
+}
+EXPORT_SYMBOL(__init_swait_queue_head);
+
+/*
+ * The thing about the wake_up_state() return value; I think we can ignore it.
+ *
+ * If for some reason it would return 0, that means the previously waiting
+ * task is already running, so it will observe condition true (or has already).
+ */
+void swake_up_locked(struct swait_queue_head *q)
+{
+	struct swait_queue *curr;
+
+	if (list_empty(&q->task_list))
+		return;
+
+	curr = list_first_entry(&q->task_list, typeof(*curr), task_list);
+	wake_up_process(curr->task);
+	list_del_init(&curr->task_list);
+}
+EXPORT_SYMBOL(swake_up_locked);
+
+void swake_up(struct swait_queue_head *q)
+{
+	unsigned long flags;
+
+	if (!swait_active(q))
+		return;
+
+	raw_spin_lock_irqsave(&q->lock, flags);
+	swake_up_locked(q);
+	raw_spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(swake_up);
+
+/*
+ * Does not allow usage from IRQ disabled, since we must be able to
+ * release IRQs to guarantee bounded hold time.
+ */
+void swake_up_all(struct swait_queue_head *q)
+{
+	struct swait_queue *curr;
+	LIST_HEAD(tmp);
+
+	if (!swait_active(q))
+		return;
+
+	raw_spin_lock_irq(&q->lock);
+	list_splice_init(&q->task_list, &tmp);
+	while (!list_empty(&tmp)) {
+		curr = list_first_entry(&tmp, typeof(*curr), task_list);
+
+		wake_up_state(curr->task, TASK_NORMAL);
+		list_del_init(&curr->task_list);
+
+		if (list_empty(&tmp))
+			break;
+
+		raw_spin_unlock_irq(&q->lock);
+		raw_spin_lock_irq(&q->lock);
+	}
+	raw_spin_unlock_irq(&q->lock);
+}
+EXPORT_SYMBOL(swake_up_all);
+
+void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
+{
+	wait->task = current;
+	if (list_empty(&wait->task_list))
+		list_add(&wait->task_list, &q->task_list);
+}
+
+void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&q->lock, flags);
+	__prepare_to_swait(q, wait);
+	set_current_state(state);
+	raw_spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(prepare_to_swait);
+
+long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state)
+{
+	if (signal_pending_state(state, current))
+		return -ERESTARTSYS;
+
+	prepare_to_swait(q, wait, state);
+
+	return 0;
+}
+EXPORT_SYMBOL(prepare_to_swait_event);
+
+void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait)
+{
+	__set_current_state(TASK_RUNNING);
+	if (!list_empty(&wait->task_list))
+		list_del_init(&wait->task_list);
+}
+
+void finish_swait(struct swait_queue_head *q, struct swait_queue *wait)
+{
+	unsigned long flags;
+
+	__set_current_state(TASK_RUNNING);
+
+	if (!list_empty_careful(&wait->task_list)) {
+		raw_spin_lock_irqsave(&q->lock, flags);
+		list_del_init(&wait->task_list);
+		raw_spin_unlock_irqrestore(&q->lock, flags);
+	}
+}
+EXPORT_SYMBOL(finish_swait);