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

Pull scheduler fixes from Ingo Molnar:
 "Misc fixes: group scheduling corner case fix, two deadline scheduler
  fixes, effective_load() overflow fix, nested sleep fix, 6144 CPUs
  system fix"

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/fair: Fix RCU stall upon -ENOMEM in sched_create_group()
  sched/deadline: Avoid double-accounting in case of missed deadlines
  sched/deadline: Fix migration of SCHED_DEADLINE tasks
  sched: Fix odd values in effective_load() calculations
  sched, fanotify: Deal with nested sleeps
  sched: Fix KMALLOC_MAX_SIZE overflow during cpumask allocation

fs/notify/fanotify/fanotify_user.c

@@ -259,16 +259,15 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
 	struct fsnotify_event *kevent;
 	char __user *start;
 	int ret;
-	DEFINE_WAIT(wait);
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
 	start = buf;
 	group = file->private_data;
 
 	pr_debug("%s: group=%p\n", __func__, group);
 
+	add_wait_queue(&group->notification_waitq, &wait);
 	while (1) {
-		prepare_to_wait(&group->notification_waitq, &wait, TASK_INTERRUPTIBLE);
-
 		mutex_lock(&group->notification_mutex);
 		kevent = get_one_event(group, count);
 		mutex_unlock(&group->notification_mutex);
@@ -289,7 +288,8 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
 
 			if (start != buf)
 				break;
-			schedule();
+
+			wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
 			continue;
 		}
 
@@ -318,8 +318,8 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
 		buf += ret;
 		count -= ret;
 	}
+	remove_wait_queue(&group->notification_waitq, &wait);
 
-	finish_wait(&group->notification_waitq, &wait);
 	if (start != buf && ret != -EFAULT)
 		ret = buf - start;
 	return ret;

kernel/sched/core.c

@@ -7112,9 +7112,6 @@ void __init sched_init(void)
 #endif
 #ifdef CONFIG_RT_GROUP_SCHED
 	alloc_size += 2 * nr_cpu_ids * sizeof(void **);
-#endif
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	alloc_size += num_possible_cpus() * cpumask_size();
 #endif
 	if (alloc_size) {
 		ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);
@@ -7135,13 +7132,13 @@ void __init sched_init(void)
 		ptr += nr_cpu_ids * sizeof(void **);
 
 #endif /* CONFIG_RT_GROUP_SCHED */
+	}
 #ifdef CONFIG_CPUMASK_OFFSTACK
 	for_each_possible_cpu(i) {
-			per_cpu(load_balance_mask, i) = (void *)ptr;
-			ptr += cpumask_size();
+		per_cpu(load_balance_mask, i) = (cpumask_var_t)kzalloc_node(
+			cpumask_size(), GFP_KERNEL, cpu_to_node(i));
 	}
 #endif /* CONFIG_CPUMASK_OFFSTACK */
-	}
 
 	init_rt_bandwidth(&def_rt_bandwidth,
 			global_rt_period(), global_rt_runtime());

kernel/sched/deadline.c

@@ -570,24 +570,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
 static
 int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se)
 {
-	int dmiss = dl_time_before(dl_se->deadline, rq_clock(rq));
-	int rorun = dl_se->runtime <= 0;
-
-	if (!rorun && !dmiss)
-		return 0;
-
-	/*
-	 * If we are beyond our current deadline and we are still
-	 * executing, then we have already used some of the runtime of
-	 * the next instance. Thus, if we do not account that, we are
-	 * stealing bandwidth from the system at each deadline miss!
-	 */
-	if (dmiss) {
-		dl_se->runtime = rorun ? dl_se->runtime : 0;
-		dl_se->runtime -= rq_clock(rq) - dl_se->deadline;
-	}
-
-	return 1;
+	return (dl_se->runtime <= 0);
 }
 
 extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
@@ -826,10 +809,10 @@ 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_REPLENISH)
-		replenish_dl_entity(dl_se, pi_se);
-	else
+	if (dl_se->dl_new || flags & ENQUEUE_WAKEUP)
 		update_dl_entity(dl_se, pi_se);
+	else if (flags & ENQUEUE_REPLENISH)
+		replenish_dl_entity(dl_se, pi_se);
 
 	__enqueue_dl_entity(dl_se);
 }

kernel/sched/fair.c

@@ -4005,6 +4005,10 @@ void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force)
 
 static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 {
+	/* init_cfs_bandwidth() was not called */
+	if (!cfs_b->throttled_cfs_rq.next)
+		return;
+
 	hrtimer_cancel(&cfs_b->period_timer);
 	hrtimer_cancel(&cfs_b->slack_timer);
 }
@@ -4424,7 +4428,7 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
 		 * wl = S * s'_i; see (2)
 		 */
 		if (W > 0 && w < W)
-			wl = (w * tg->shares) / W;
+			wl = (w * (long)tg->shares) / W;
 		else
 			wl = tg->shares;