1 files changed, 137 insertions, 123 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f9123a82cbb6..c86935a7f1f8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -90,26 +90,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
 
-void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period)
-{
-	unsigned long delta;
-	ktime_t soft, hard, now;
-
-	for (;;) {
-		if (hrtimer_active(period_timer))
-			break;
-
-		now = hrtimer_cb_get_time(period_timer);
-		hrtimer_forward(period_timer, now, period);
-
-		soft = hrtimer_get_softexpires(period_timer);
-		hard = hrtimer_get_expires(period_timer);
-		delta = ktime_to_ns(ktime_sub(hard, soft));
-		__hrtimer_start_range_ns(period_timer, soft, delta,
-					 HRTIMER_MODE_ABS_PINNED, 0);
-	}
-}
-
 DEFINE_MUTEX(sched_domains_mutex);
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
@@ -355,12 +335,11 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer)
 
 #ifdef CONFIG_SMP
 
-static int __hrtick_restart(struct rq *rq)
+static void __hrtick_restart(struct rq *rq)
 {
 	struct hrtimer *timer = &rq->hrtick_timer;
-	ktime_t time = hrtimer_get_softexpires(timer);
 
-	return __hrtimer_start_range_ns(timer, time, 0, HRTIMER_MODE_ABS_PINNED, 0);
+	hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);
 }
 
 /*
@@ -440,8 +419,8 @@ void hrtick_start(struct rq *rq, u64 delay)
 	 * doesn't make sense. Rely on vruntime for fairness.
 	 */
 	delay = max_t(u64, delay, 10000LL);
-	__hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0,
-			HRTIMER_MODE_REL_PINNED, 0);
+	hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay),
+		      HRTIMER_MODE_REL_PINNED);
 }
 
 static inline void init_hrtick(void)
@@ -511,7 +490,7 @@ static bool set_nr_and_not_polling(struct task_struct *p)
 static bool set_nr_if_polling(struct task_struct *p)
 {
 	struct thread_info *ti = task_thread_info(p);
-	typeof(ti->flags) old, val = ACCESS_ONCE(ti->flags);
+	typeof(ti->flags) old, val = READ_ONCE(ti->flags);
 
 	for (;;) {
 		if (!(val & _TIF_POLLING_NRFLAG))
@@ -541,6 +520,52 @@ static bool set_nr_if_polling(struct task_struct *p)
 #endif
 #endif
 
+void wake_q_add(struct wake_q_head *head, struct task_struct *task)
+{
+	struct wake_q_node *node = &task->wake_q;
+
+	/*
+	 * Atomically grab the task, if ->wake_q is !nil already it means
+	 * its already queued (either by us or someone else) and will get the
+	 * wakeup due to that.
+	 *
+	 * This cmpxchg() implies a full barrier, which pairs with the write
+	 * barrier implied by the wakeup in wake_up_list().
+	 */
+	if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
+		return;
+
+	get_task_struct(task);
+
+	/*
+	 * The head is context local, there can be no concurrency.
+	 */
+	*head->lastp = node;
+	head->lastp = &node->next;
+}
+
+void wake_up_q(struct wake_q_head *head)
+{
+	struct wake_q_node *node = head->first;
+
+	while (node != WAKE_Q_TAIL) {
+		struct task_struct *task;
+
+		task = container_of(node, struct task_struct, wake_q);
+		BUG_ON(!task);
+		/* task can safely be re-inserted now */
+		node = node->next;
+		task->wake_q.next = NULL;
+
+		/*
+		 * wake_up_process() implies a wmb() to pair with the queueing
+		 * in wake_q_add() so as not to miss wakeups.
+		 */
+		wake_up_process(task);
+		put_task_struct(task);
+	}
+}
+
 /*
  * resched_curr - mark rq's current task 'to be rescheduled now'.
  *
@@ -593,13 +618,12 @@ void resched_cpu(int cpu)
  * selecting an idle cpu will add more delays to the timers than intended
  * (as that cpu's timer base may not be uptodate wrt jiffies etc).
  */
-int get_nohz_timer_target(int pinned)
+int get_nohz_timer_target(void)
 {
-	int cpu = smp_processor_id();
-	int i;
+	int i, cpu = smp_processor_id();
 	struct sched_domain *sd;
 
-	if (pinned || !get_sysctl_timer_migration() || !idle_cpu(cpu))
+	if (!idle_cpu(cpu))
 		return cpu;
 
 	rcu_read_lock();
@@ -1016,13 +1040,6 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 		rq_clock_skip_update(rq, true);
 }
 
-static ATOMIC_NOTIFIER_HEAD(task_migration_notifier);
-
-void register_task_migration_notifier(struct notifier_block *n)
-{
-	atomic_notifier_chain_register(&task_migration_notifier, n);
-}
-
 #ifdef CONFIG_SMP
 void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 {
@@ -1053,18 +1070,10 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	trace_sched_migrate_task(p, new_cpu);
 
 	if (task_cpu(p) != new_cpu) {
-		struct task_migration_notifier tmn;
-
 		if (p->sched_class->migrate_task_rq)
 			p->sched_class->migrate_task_rq(p, new_cpu);
 		p->se.nr_migrations++;
-		perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0);
-
-		tmn.task = p;
-		tmn.from_cpu = task_cpu(p);
-		tmn.to_cpu = new_cpu;
-
-		atomic_notifier_call_chain(&task_migration_notifier, 0, &tmn);
+		perf_event_task_migrate(p);
 	}
 
 	__set_task_cpu(p, new_cpu);
@@ -2120,12 +2129,15 @@ void wake_up_new_task(struct task_struct *p)
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 
+static struct static_key preempt_notifier_key = STATIC_KEY_INIT_FALSE;
+
 /**
  * preempt_notifier_register - tell me when current is being preempted & rescheduled
  * @notifier: notifier struct to register
  */
 void preempt_notifier_register(struct preempt_notifier *notifier)
 {
+	static_key_slow_inc(&preempt_notifier_key);
 	hlist_add_head(&notifier->link, &current->preempt_notifiers);
 }
 EXPORT_SYMBOL_GPL(preempt_notifier_register);
@@ -2134,15 +2146,16 @@ EXPORT_SYMBOL_GPL(preempt_notifier_register);
  * preempt_notifier_unregister - no longer interested in preemption notifications
  * @notifier: notifier struct to unregister
  *
- * This is safe to call from within a preemption notifier.
+ * This is *not* safe to call from within a preemption notifier.
  */
 void preempt_notifier_unregister(struct preempt_notifier *notifier)
 {
 	hlist_del(&notifier->link);
+	static_key_slow_dec(&preempt_notifier_key);
 }
 EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
 
-static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
+static void __fire_sched_in_preempt_notifiers(struct task_struct *curr)
 {
 	struct preempt_notifier *notifier;
 
@@ -2150,9 +2163,15 @@ static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
 		notifier->ops->sched_in(notifier, raw_smp_processor_id());
 }
 
+static __always_inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
+{
+	if (static_key_false(&preempt_notifier_key))
+		__fire_sched_in_preempt_notifiers(curr);
+}
+
 static void
-fire_sched_out_preempt_notifiers(struct task_struct *curr,
-				 struct task_struct *next)
+__fire_sched_out_preempt_notifiers(struct task_struct *curr,
+				   struct task_struct *next)
 {
 	struct preempt_notifier *notifier;
 
@@ -2160,13 +2179,21 @@ fire_sched_out_preempt_notifiers(struct task_struct *curr,
 		notifier->ops->sched_out(notifier, next);
 }
 
+static __always_inline void
+fire_sched_out_preempt_notifiers(struct task_struct *curr,
+				 struct task_struct *next)
+{
+	if (static_key_false(&preempt_notifier_key))
+		__fire_sched_out_preempt_notifiers(curr, next);
+}
+
 #else /* !CONFIG_PREEMPT_NOTIFIERS */
 
-static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
+static inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
 {
 }
 
-static void
+static inline void
 fire_sched_out_preempt_notifiers(struct task_struct *curr,
 				 struct task_struct *next)
 {
@@ -2347,7 +2374,6 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	 */
 	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
 
-	context_tracking_task_switch(prev, next);
 	/* Here we just switch the register state and the stack. */
 	switch_to(prev, next, prev);
 	barrier();
@@ -2412,9 +2438,9 @@ unsigned long nr_iowait_cpu(int cpu)
 
 void get_iowait_load(unsigned long *nr_waiters, unsigned long *load)
 {
-	struct rq *this = this_rq();
-	*nr_waiters = atomic_read(&this->nr_iowait);
-	*load = this->cpu_load[0];
+	struct rq *rq = this_rq();
+	*nr_waiters = atomic_read(&rq->nr_iowait);
+	*load = rq->load.weight;
 }
 
 #ifdef CONFIG_SMP
@@ -2512,6 +2538,7 @@ void scheduler_tick(void)
 	update_rq_clock(rq);
 	curr->sched_class->task_tick(rq, curr, 0);
 	update_cpu_load_active(rq);
+	calc_global_load_tick(rq);
 	raw_spin_unlock(&rq->lock);
 
 	perf_event_task_tick();
@@ -2540,7 +2567,7 @@ void scheduler_tick(void)
 u64 scheduler_tick_max_deferment(void)
 {
 	struct rq *rq = this_rq();
-	unsigned long next, now = ACCESS_ONCE(jiffies);
+	unsigned long next, now = READ_ONCE(jiffies);
 
 	next = rq->last_sched_tick + HZ;
 
@@ -2741,9 +2768,7 @@ again:
  *          - return from syscall or exception to user-space
  *          - return from interrupt-handler to user-space
  *
- * WARNING: all callers must re-check need_resched() afterward and reschedule
- * accordingly in case an event triggered the need for rescheduling (such as
- * an interrupt waking up a task) while preemption was disabled in __schedule().
+ * WARNING: must be called with preemption disabled!
  */
 static void __sched __schedule(void)
 {
@@ -2752,7 +2777,6 @@ static void __sched __schedule(void)
 	struct rq *rq;
 	int cpu;
 
-	preempt_disable();
 	cpu = smp_processor_id();
 	rq = cpu_rq(cpu);
 	rcu_note_context_switch();
@@ -2816,8 +2840,6 @@ static void __sched __schedule(void)
 		raw_spin_unlock_irq(&rq->lock);
 
 	post_schedule(rq);
-
-	sched_preempt_enable_no_resched();
 }
 
 static inline void sched_submit_work(struct task_struct *tsk)
@@ -2838,7 +2860,9 @@ asmlinkage __visible void __sched schedule(void)
 
 	sched_submit_work(tsk);
 	do {
+		preempt_disable();
 		__schedule();
+		sched_preempt_enable_no_resched();
 	} while (need_resched());
 }
 EXPORT_SYMBOL(schedule);
@@ -2877,15 +2901,14 @@ void __sched schedule_preempt_disabled(void)
 static void __sched notrace preempt_schedule_common(void)
 {
 	do {
-		__preempt_count_add(PREEMPT_ACTIVE);
+		preempt_active_enter();
 		__schedule();
-		__preempt_count_sub(PREEMPT_ACTIVE);
+		preempt_active_exit();
 
 		/*
 		 * Check again in case we missed a preemption opportunity
 		 * between schedule and now.
 		 */
-		barrier();
 	} while (need_resched());
 }
 
@@ -2909,9 +2932,8 @@ asmlinkage __visible void __sched notrace preempt_schedule(void)
 NOKPROBE_SYMBOL(preempt_schedule);
 EXPORT_SYMBOL(preempt_schedule);
 
-#ifdef CONFIG_CONTEXT_TRACKING
 /**
- * preempt_schedule_context - preempt_schedule called by tracing
+ * preempt_schedule_notrace - preempt_schedule called by tracing
  *
  * The tracing infrastructure uses preempt_enable_notrace to prevent
  * recursion and tracing preempt enabling caused by the tracing
@@ -2924,7 +2946,7 @@ EXPORT_SYMBOL(preempt_schedule);
  * instead of preempt_schedule() to exit user context if needed before
  * calling the scheduler.
  */
-asmlinkage __visible void __sched notrace preempt_schedule_context(void)
+asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
 {
 	enum ctx_state prev_ctx;
 
@@ -2932,7 +2954,13 @@ asmlinkage __visible void __sched notrace preempt_schedule_context(void)
 		return;
 
 	do {
-		__preempt_count_add(PREEMPT_ACTIVE);
+		/*
+		 * Use raw __prempt_count() ops that don't call function.
+		 * We can't call functions before disabling preemption which
+		 * disarm preemption tracing recursions.
+		 */
+		__preempt_count_add(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET);
+		barrier();
 		/*
 		 * Needs preempt disabled in case user_exit() is traced
 		 * and the tracer calls preempt_enable_notrace() causing
@@ -2942,12 +2970,11 @@ asmlinkage __visible void __sched notrace preempt_schedule_context(void)
 		__schedule();
 		exception_exit(prev_ctx);
 
-		__preempt_count_sub(PREEMPT_ACTIVE);
 		barrier();
+		__preempt_count_sub(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET);
 	} while (need_resched());
 }
-EXPORT_SYMBOL_GPL(preempt_schedule_context);
-#endif /* CONFIG_CONTEXT_TRACKING */
+EXPORT_SYMBOL_GPL(preempt_schedule_notrace);
 
 #endif /* CONFIG_PREEMPT */
 
@@ -2967,17 +2994,11 @@ asmlinkage __visible void __sched preempt_schedule_irq(void)
 	prev_state = exception_enter();
 
 	do {
-		__preempt_count_add(PREEMPT_ACTIVE);
+		preempt_active_enter();
 		local_irq_enable();
 		__schedule();
 		local_irq_disable();
-		__preempt_count_sub(PREEMPT_ACTIVE);
-
-		/*
-		 * Check again in case we missed a preemption opportunity
-		 * between schedule and now.
-		 */
-		barrier();
+		preempt_active_exit();
 	} while (need_resched());
 
 	exception_exit(prev_state);
@@ -3055,7 +3076,6 @@ 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;
-			p->dl.dl_throttled = 0;
 			enqueue_flag = ENQUEUE_REPLENISH;
 		} else
 			p->dl.dl_boosted = 0;
@@ -3315,15 +3335,18 @@ static void __setscheduler_params(struct task_struct *p,
 
 /* Actually do priority change: must hold pi & rq lock. */
 static void __setscheduler(struct rq *rq, struct task_struct *p,
-			   const struct sched_attr *attr)
+			   const struct sched_attr *attr, bool keep_boost)
 {
 	__setscheduler_params(p, attr);
 
 	/*
-	 * If we get here, there was no pi waiters boosting the
-	 * task. It is safe to use the normal prio.
+	 * Keep a potential priority boosting if called from
+	 * sched_setscheduler().
 	 */
-	p->prio = normal_prio(p);
+	if (keep_boost)
+		p->prio = rt_mutex_get_effective_prio(p, normal_prio(p));
+	else
+		p->prio = normal_prio(p);
 
 	if (dl_prio(p->prio))
 		p->sched_class = &dl_sched_class;
@@ -3423,7 +3446,7 @@ static int __sched_setscheduler(struct task_struct *p,
 	int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 :
 		      MAX_RT_PRIO - 1 - attr->sched_priority;
 	int retval, oldprio, oldpolicy = -1, queued, running;
-	int policy = attr->sched_policy;
+	int new_effective_prio, policy = attr->sched_policy;
 	unsigned long flags;
 	const struct sched_class *prev_class;
 	struct rq *rq;
@@ -3605,15 +3628,14 @@ change:
 	oldprio = p->prio;
 
 	/*
-	 * Special case for priority boosted tasks.
-	 *
-	 * If the new priority is lower or equal (user space view)
-	 * than the current (boosted) priority, we just store the new
+	 * Take priority boosted tasks into account. If the new
+	 * effective priority is unchanged, we just store the new
 	 * normal parameters and do not touch the scheduler class and
 	 * the runqueue. This will be done when the task deboost
 	 * itself.
 	 */
-	if (rt_mutex_check_prio(p, newprio)) {
+	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;
@@ -3627,7 +3649,7 @@ change:
 		put_prev_task(rq, p);
 
 	prev_class = p->sched_class;
-	__setscheduler(rq, p, attr);
+	__setscheduler(rq, p, attr, true);
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
@@ -4402,10 +4424,7 @@ long __sched io_schedule_timeout(long timeout)
 	long ret;
 
 	current->in_iowait = 1;
-	if (old_iowait)
-		blk_schedule_flush_plug(current);
-	else
-		blk_flush_plug(current);
+	blk_schedule_flush_plug(current);
 
 	delayacct_blkio_start();
 	rq = raw_rq();
@@ -5330,7 +5349,7 @@ static struct notifier_block migration_notifier = {
 	.priority = CPU_PRI_MIGRATION,
 };
 
-static void __cpuinit set_cpu_rq_start_time(void)
+static void set_cpu_rq_start_time(void)
 {
 	int cpu = smp_processor_id();
 	struct rq *rq = cpu_rq(cpu);
@@ -7012,27 +7031,23 @@ static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action,
 	unsigned long flags;
 	long cpu = (long)hcpu;
 	struct dl_bw *dl_b;
+	bool overflow;
+	int cpus;
 
-	switch (action & ~CPU_TASKS_FROZEN) {
+	switch (action) {
 	case CPU_DOWN_PREPARE:
-		/* explicitly allow suspend */
-		if (!(action & CPU_TASKS_FROZEN)) {
-			bool overflow;
-			int cpus;
-
-			rcu_read_lock_sched();
-			dl_b = dl_bw_of(cpu);
+		rcu_read_lock_sched();
+		dl_b = dl_bw_of(cpu);
 
-			raw_spin_lock_irqsave(&dl_b->lock, flags);
-			cpus = dl_bw_cpus(cpu);
-			overflow = __dl_overflow(dl_b, cpus, 0, 0);
-			raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+		raw_spin_lock_irqsave(&dl_b->lock, flags);
+		cpus = dl_bw_cpus(cpu);
+		overflow = __dl_overflow(dl_b, cpus, 0, 0);
+		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 
-			rcu_read_unlock_sched();
+		rcu_read_unlock_sched();
 
-			if (overflow)
-				return notifier_from_errno(-EBUSY);
-		}
+		if (overflow)
+			return notifier_from_errno(-EBUSY);
 		cpuset_update_active_cpus(false);
 		break;
 	case CPU_DOWN_PREPARE_FROZEN:
@@ -7052,6 +7067,9 @@ void __init sched_init_smp(void)
 	alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
 	alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
 
+	/* nohz_full won't take effect without isolating the cpus. */
+	tick_nohz_full_add_cpus_to(cpu_isolated_map);
+
 	sched_init_numa();
 
 	/*
@@ -7088,8 +7106,6 @@ void __init sched_init_smp(void)
 }
 #endif /* CONFIG_SMP */
 
-const_debug unsigned int sysctl_timer_migration = 1;
-
 int in_sched_functions(unsigned long addr)
 {
 	return in_lock_functions(addr) ||
@@ -7361,7 +7377,7 @@ static void normalize_task(struct rq *rq, struct task_struct *p)
 	queued = task_on_rq_queued(p);
 	if (queued)
 		dequeue_task(rq, p, 0);
-	__setscheduler(rq, p, &attr);
+	__setscheduler(rq, p, &attr, false);
 	if (queued) {
 		enqueue_task(rq, p, 0);
 		resched_curr(rq);
@@ -7754,11 +7770,11 @@ static long sched_group_rt_runtime(struct task_group *tg)
 	return rt_runtime_us;
 }
 
-static int sched_group_set_rt_period(struct task_group *tg, long rt_period_us)
+static int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us)
 {
 	u64 rt_runtime, rt_period;
 
-	rt_period = (u64)rt_period_us * NSEC_PER_USEC;
+	rt_period = rt_period_us * NSEC_PER_USEC;
 	rt_runtime = tg->rt_bandwidth.rt_runtime;
 
 	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
@@ -8125,10 +8141,8 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
 
 	__refill_cfs_bandwidth_runtime(cfs_b);
 	/* restart the period timer (if active) to handle new period expiry */
-	if (runtime_enabled && cfs_b->timer_active) {
-		/* force a reprogram */
-		__start_cfs_bandwidth(cfs_b, true);
-	}
+	if (runtime_enabled)
+		start_cfs_bandwidth(cfs_b);
 	raw_spin_unlock_irq(&cfs_b->lock);
 
 	for_each_online_cpu(i) {