5 files changed, 37 insertions, 19 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 615953141951..f7402f7eb448 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2366,8 +2366,15 @@ void wake_up_new_task(struct task_struct *p)
 	trace_sched_wakeup_new(p);
 	check_preempt_curr(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
-	if (p->sched_class->task_woken)
+	if (p->sched_class->task_woken) {
+		/*
+		 * Nothing relies on rq->lock after this, so its fine to
+		 * drop it.
+		 */
+		lockdep_unpin_lock(&rq->lock);
 		p->sched_class->task_woken(rq, p);
+		lockdep_pin_lock(&rq->lock);
+	}
 #endif
 	task_rq_unlock(rq, p, &flags);
 }
@@ -2517,11 +2524,11 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	 * If a task dies, then it sets TASK_DEAD in tsk->state and calls
 	 * schedule one last time. The schedule call will never return, and
 	 * the scheduled task must drop that reference.
-	 * The test for TASK_DEAD must occur while the runqueue locks are
-	 * still held, otherwise prev could be scheduled on another cpu, die
-	 * there before we look at prev->state, and then the reference would
-	 * be dropped twice.
-	 *		Manfred Spraul <manfred@colorfullife.com>
+	 *
+	 * We must observe prev->state before clearing prev->on_cpu (in
+	 * finish_lock_switch), otherwise a concurrent wakeup can get prev
+	 * running on another CPU and we could rave with its RUNNING -> DEAD
+	 * transition, resulting in a double drop.
 	 */
 	prev_state = prev->state;
 	vtime_task_switch(prev);
@@ -4022,6 +4029,7 @@ int sched_setscheduler_nocheck(struct task_struct *p, int policy,
 {
 	return _sched_setscheduler(p, policy, param, false);
 }
+EXPORT_SYMBOL_GPL(sched_setscheduler_nocheck);
 
 static int
 do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
@@ -7238,9 +7246,6 @@ 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();
 
 	/*
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index fc8f01083527..8b0a15e285f9 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -668,8 +668,15 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	 * Queueing this task back might have overloaded rq, check if we need
 	 * to kick someone away.
 	 */
-	if (has_pushable_dl_tasks(rq))
+	if (has_pushable_dl_tasks(rq)) {
+		/*
+		 * Nothing relies on rq->lock after this, so its safe to drop
+		 * rq->lock.
+		 */
+		lockdep_unpin_lock(&rq->lock);
 		push_dl_task(rq);
+		lockdep_pin_lock(&rq->lock);
+	}
 #endif
 
 unlock:
@@ -1066,8 +1073,9 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
 		int target = find_later_rq(p);
 
 		if (target != -1 &&
-				dl_time_before(p->dl.deadline,
-					cpu_rq(target)->dl.earliest_dl.curr))
+				(dl_time_before(p->dl.deadline,
+					cpu_rq(target)->dl.earliest_dl.curr) ||
+				(cpu_rq(target)->dl.dl_nr_running == 0)))
 			cpu = target;
 	}
 	rcu_read_unlock();
@@ -1417,7 +1425,8 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
 
 		later_rq = cpu_rq(cpu);
 
-		if (!dl_time_before(task->dl.deadline,
+		if (later_rq->dl.dl_nr_running &&
+		    !dl_time_before(task->dl.deadline,
 					later_rq->dl.earliest_dl.curr)) {
 			/*
 			 * Target rq has tasks of equal or earlier deadline,
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6e2e3483b1ec..9a5e60fe721a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2363,7 +2363,7 @@ static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
 	 */
 	tg_weight = atomic_long_read(&tg->load_avg);
 	tg_weight -= cfs_rq->tg_load_avg_contrib;
-	tg_weight += cfs_rq_load_avg(cfs_rq);
+	tg_weight += cfs_rq->load.weight;
 
 	return tg_weight;
 }
@@ -2373,7 +2373,7 @@ static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
 	long tg_weight, load, shares;
 
 	tg_weight = calc_tg_weight(tg, cfs_rq);
-	load = cfs_rq_load_avg(cfs_rq);
+	load = cfs_rq->load.weight;
 
 	shares = (tg->shares * load);
 	if (tg_weight)
@@ -2664,13 +2664,14 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
 /* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */
 static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 {
-	int decayed;
 	struct sched_avg *sa = &cfs_rq->avg;
+	int decayed, removed = 0;
 
 	if (atomic_long_read(&cfs_rq->removed_load_avg)) {
 		long r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
 		sa->load_avg = max_t(long, sa->load_avg - r, 0);
 		sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0);
+		removed = 1;
 	}
 
 	if (atomic_long_read(&cfs_rq->removed_util_avg)) {
@@ -2688,7 +2689,7 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 	cfs_rq->load_last_update_time_copy = sa->last_update_time;
 #endif
 
-	return decayed;
+	return decayed || removed;
 }
 
 /* Update task and its cfs_rq load average */
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 8f177c73ae19..4a2ef5a02fd3 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -57,9 +57,11 @@ static inline int cpu_idle_poll(void)
 	rcu_idle_enter();
 	trace_cpu_idle_rcuidle(0, smp_processor_id());
 	local_irq_enable();
+	stop_critical_timings();
 	while (!tif_need_resched() &&
 		(cpu_idle_force_poll || tick_check_broadcast_expired()))
 		cpu_relax();
+	start_critical_timings();
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 	rcu_idle_exit();
 	return 1;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 68cda117574c..6d2a119c7ad9 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1078,9 +1078,10 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 	 * After ->on_cpu is cleared, the task can be moved to a different CPU.
 	 * We must ensure this doesn't happen until the switch is completely
 	 * finished.
+	 *
+	 * Pairs with the control dependency and rmb in try_to_wake_up().
 	 */
-	smp_wmb();
-	prev->on_cpu = 0;
+	smp_store_release(&prev->on_cpu, 0);
 #endif
 #ifdef CONFIG_DEBUG_SPINLOCK
 	/* this is a valid case when another task releases the spinlock */