Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "The main changes in this cycle were:

   - Make nohz housekeeping processing more permissive and less
     intrusive to isolated CPUs

   - Decouple CPU-bound workqueue acconting from the scheduler and move
     it into the workqueue code.

   - Optimize topology building

   - Better handle quota and period overflows

   - Add more RCU annotations

   - Comment updates, misc cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (25 commits)
  nohz_full: Allow the boot CPU to be nohz_full
  sched/isolation: Require a present CPU in housekeeping mask
  kernel/cpu: Allow non-zero CPU to be primary for suspend / kexec freeze
  power/suspend: Add function to disable secondaries for suspend
  sched/core: Allow the remote scheduler tick to be started on CPU0
  sched/nohz: Run NOHZ idle load balancer on HK_FLAG_MISC CPUs
  sched/debug: Fix spelling mistake "logaritmic" -> "logarithmic"
  sched/topology: Update init_sched_domains() comment
  cgroup/cpuset: Update stale generate_sched_domains() comments
  sched/core: Check quota and period overflow at usec to nsec conversion
  sched/core: Handle overflow in cpu_shares_write_u64
  sched/rt: Check integer overflow at usec to nsec conversion
  sched/core: Fix typo in comment
  sched/core: Make some functions static
  sched/core: Unify p->on_rq updates
  sched/core: Remove ttwu_activate()
  sched/core, workqueues: Distangle worker accounting from rq lock
  sched/fair: Remove unneeded prototype of capacity_of()
  sched/topology: Skip duplicate group rewrites in build_sched_groups()
  sched/topology: Fix build_sched_groups() comment
  ...

1 files changed, 41 insertions, 86 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ade3f2287d1f..102dfcf0a29a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -792,10 +792,14 @@ void activate_task(struct rq *rq, struct task_struct *p, int flags)
 		rq->nr_uninterruptible--;
 
 	enqueue_task(rq, p, flags);
+
+	p->on_rq = TASK_ON_RQ_QUEUED;
 }
 
 void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 {
+	p->on_rq = (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING;
+
 	if (task_contributes_to_load(p))
 		rq->nr_uninterruptible++;
 
@@ -920,7 +924,7 @@ static inline bool is_per_cpu_kthread(struct task_struct *p)
 }
 
 /*
- * Per-CPU kthreads are allowed to run on !actie && online CPUs, see
+ * Per-CPU kthreads are allowed to run on !active && online CPUs, see
  * __set_cpus_allowed_ptr() and select_fallback_rq().
  */
 static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
@@ -1236,11 +1240,9 @@ static void __migrate_swap_task(struct task_struct *p, int cpu)
 		rq_pin_lock(src_rq, &srf);
 		rq_pin_lock(dst_rq, &drf);
 
-		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);
 
 		rq_unpin_lock(dst_rq, &drf);
@@ -1680,16 +1682,6 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 		__schedstat_inc(p->se.statistics.nr_wakeups_sync);
 }
 
-static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
-{
-	activate_task(rq, p, en_flags);
-	p->on_rq = TASK_ON_RQ_QUEUED;
-
-	/* If a worker is waking up, notify the workqueue: */
-	if (p->flags & PF_WQ_WORKER)
-		wq_worker_waking_up(p, cpu_of(rq));
-}
-
 /*
  * Mark the task runnable and perform wakeup-preemption.
  */
@@ -1741,7 +1733,7 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 		en_flags |= ENQUEUE_MIGRATED;
 #endif
 
-	ttwu_activate(rq, p, en_flags);
+	activate_task(rq, p, en_flags);
 	ttwu_do_wakeup(rq, p, wake_flags, rf);
 }
 
@@ -2106,56 +2098,6 @@ out:
 }
 
 /**
- * try_to_wake_up_local - try to wake up a local task with rq lock held
- * @p: the thread to be awakened
- * @rf: request-queue flags for pinning
- *
- * Put @p on the run-queue if it's not already there. The caller must
- * ensure that this_rq() is locked, @p is bound to this_rq() and not
- * the current task.
- */
-static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf)
-{
-	struct rq *rq = task_rq(p);
-
-	if (WARN_ON_ONCE(rq != this_rq()) ||
-	    WARN_ON_ONCE(p == current))
-		return;
-
-	lockdep_assert_held(&rq->lock);
-
-	if (!raw_spin_trylock(&p->pi_lock)) {
-		/*
-		 * This is OK, because current is on_cpu, which avoids it being
-		 * picked for load-balance and preemption/IRQs are still
-		 * disabled avoiding further scheduler activity on it and we've
-		 * not yet picked a replacement task.
-		 */
-		rq_unlock(rq, rf);
-		raw_spin_lock(&p->pi_lock);
-		rq_relock(rq, rf);
-	}
-
-	if (!(p->state & TASK_NORMAL))
-		goto out;
-
-	trace_sched_waking(p);
-
-	if (!task_on_rq_queued(p)) {
-		if (p->in_iowait) {
-			delayacct_blkio_end(p);
-			atomic_dec(&rq->nr_iowait);
-		}
-		ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK);
-	}
-
-	ttwu_do_wakeup(rq, p, 0, rf);
-	ttwu_stat(p, smp_processor_id(), 0);
-out:
-	raw_spin_unlock(&p->pi_lock);
-}
-
-/**
  * wake_up_process - Wake up a specific process
  * @p: The process to be woken up.
  *
@@ -2466,7 +2408,6 @@ void wake_up_new_task(struct task_struct *p)
 	post_init_entity_util_avg(p);
 
 	activate_task(rq, p, ENQUEUE_NOCLOCK);
-	p->on_rq = TASK_ON_RQ_QUEUED;
 	trace_sched_wakeup_new(p);
 	check_preempt_curr(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
@@ -3465,25 +3406,11 @@ static void __sched notrace __schedule(bool preempt)
 			prev->state = TASK_RUNNING;
 		} else {
 			deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
-			prev->on_rq = 0;
 
 			if (prev->in_iowait) {
 				atomic_inc(&rq->nr_iowait);
 				delayacct_blkio_start();
 			}
-
-			/*
-			 * If a worker went to sleep, notify and ask workqueue
-			 * whether it wants to wake up a task to maintain
-			 * concurrency.
-			 */
-			if (prev->flags & PF_WQ_WORKER) {
-				struct task_struct *to_wakeup;
-
-				to_wakeup = wq_worker_sleeping(prev);
-				if (to_wakeup)
-					try_to_wake_up_local(to_wakeup, &rf);
-			}
 		}
 		switch_count = &prev->nvcsw;
 	}
@@ -3543,6 +3470,20 @@ static inline void sched_submit_work(struct task_struct *tsk)
 {
 	if (!tsk->state || tsk_is_pi_blocked(tsk))
 		return;
+
+	/*
+	 * If a worker went to sleep, notify and ask workqueue whether
+	 * it wants to wake up a task to maintain concurrency.
+	 * As this function is called inside the schedule() context,
+	 * we disable preemption to avoid it calling schedule() again
+	 * in the possible wakeup of a kworker.
+	 */
+	if (tsk->flags & PF_WQ_WORKER) {
+		preempt_disable();
+		wq_worker_sleeping(tsk);
+		preempt_enable_no_resched();
+	}
+
 	/*
 	 * If we are going to sleep and we have plugged IO queued,
 	 * make sure to submit it to avoid deadlocks.
@@ -3551,6 +3492,12 @@ static inline void sched_submit_work(struct task_struct *tsk)
 		blk_schedule_flush_plug(tsk);
 }
 
+static void sched_update_worker(struct task_struct *tsk)
+{
+	if (tsk->flags & PF_WQ_WORKER)
+		wq_worker_running(tsk);
+}
+
 asmlinkage __visible void __sched schedule(void)
 {
 	struct task_struct *tsk = current;
@@ -3561,6 +3508,7 @@ asmlinkage __visible void __sched schedule(void)
 		__schedule(false);
 		sched_preempt_enable_no_resched();
 	} while (need_resched());
+	sched_update_worker(tsk);
 }
 EXPORT_SYMBOL(schedule);
 
@@ -5917,7 +5865,7 @@ void __init sched_init_smp(void)
 
 static int __init migration_init(void)
 {
-	sched_rq_cpu_starting(smp_processor_id());
+	sched_cpu_starting(smp_processor_id());
 	return 0;
 }
 early_initcall(migration_init);
@@ -6558,6 +6506,8 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset)
 static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
 				struct cftype *cftype, u64 shareval)
 {
+	if (shareval > scale_load_down(ULONG_MAX))
+		shareval = MAX_SHARES;
 	return sched_group_set_shares(css_tg(css), scale_load(shareval));
 }
 
@@ -6573,7 +6523,7 @@ static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css,
 static DEFINE_MUTEX(cfs_constraints_mutex);
 
 const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */
-const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
+static const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
 
 static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime);
 
@@ -6653,20 +6603,22 @@ out_unlock:
 	return ret;
 }
 
-int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
+static int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
 {
 	u64 quota, period;
 
 	period = ktime_to_ns(tg->cfs_bandwidth.period);
 	if (cfs_quota_us < 0)
 		quota = RUNTIME_INF;
-	else
+	else if ((u64)cfs_quota_us <= U64_MAX / NSEC_PER_USEC)
 		quota = (u64)cfs_quota_us * NSEC_PER_USEC;
+	else
+		return -EINVAL;
 
 	return tg_set_cfs_bandwidth(tg, period, quota);
 }
 
-long tg_get_cfs_quota(struct task_group *tg)
+static long tg_get_cfs_quota(struct task_group *tg)
 {
 	u64 quota_us;
 
@@ -6679,17 +6631,20 @@ long tg_get_cfs_quota(struct task_group *tg)
 	return quota_us;
 }
 
-int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
+static int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
 {
 	u64 quota, period;
 
+	if ((u64)cfs_period_us > U64_MAX / NSEC_PER_USEC)
+		return -EINVAL;
+
 	period = (u64)cfs_period_us * NSEC_PER_USEC;
 	quota = tg->cfs_bandwidth.quota;
 
 	return tg_set_cfs_bandwidth(tg, period, quota);
 }
 
-long tg_get_cfs_period(struct task_group *tg)
+static long tg_get_cfs_period(struct task_group *tg)
 {
 	u64 cfs_period_us;