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"

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/deadline: Fix deadline parameter modification handling
  sched/wait: Remove might_sleep() from wait_event_cmd()
  sched: Fix crash if cpuset_cpumask_can_shrink() is passed an empty cpumask
  sched/fair: Avoid using uninitialized variable in preferred_group_nid()

include/linux/wait.h

@@ -363,7 +363,6 @@ do {									\
  */
 #define wait_event_cmd(wq, condition, cmd1, cmd2)			\
 do {									\
-	might_sleep();							\
 	if (condition)							\
 		break;							\
 	__wait_event_cmd(wq, condition, cmd1, cmd2);			\

kernel/sched/core.c

@@ -1814,6 +1814,10 @@ void __dl_clear_params(struct task_struct *p)
 	dl_se->dl_period = 0;
 	dl_se->flags = 0;
 	dl_se->dl_bw = 0;
+
+	dl_se->dl_throttled = 0;
+	dl_se->dl_new = 1;
+	dl_se->dl_yielded = 0;
 }
 
 /*
@@ -1839,7 +1843,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 #endif
 
 	RB_CLEAR_NODE(&p->dl.rb_node);
-	hrtimer_init(&p->dl.dl_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	init_dl_task_timer(&p->dl);
 	__dl_clear_params(p);
 
 	INIT_LIST_HEAD(&p->rt.run_list);
@@ -2049,6 +2053,9 @@ static inline int dl_bw_cpus(int i)
  * allocated bandwidth to reflect the new situation.
  *
  * This function is called while holding p's rq->lock.
+ *
+ * XXX we should delay bw change until the task's 0-lag point, see
+ * __setparam_dl().
  */
 static int dl_overflow(struct task_struct *p, int policy,
 		       const struct sched_attr *attr)
@@ -3251,15 +3258,31 @@ __setparam_dl(struct task_struct *p, const struct sched_attr *attr)
 {
 	struct sched_dl_entity *dl_se = &p->dl;
 
-	init_dl_task_timer(dl_se);
 	dl_se->dl_runtime = attr->sched_runtime;
 	dl_se->dl_deadline = attr->sched_deadline;
 	dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
 	dl_se->flags = attr->sched_flags;
 	dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
-	dl_se->dl_throttled = 0;
-	dl_se->dl_new = 1;
-	dl_se->dl_yielded = 0;
+
+	/*
+	 * Changing the parameters of a task is 'tricky' and we're not doing
+	 * the correct thing -- also see task_dead_dl() and switched_from_dl().
+	 *
+	 * What we SHOULD do is delay the bandwidth release until the 0-lag
+	 * point. This would include retaining the task_struct until that time
+	 * and change dl_overflow() to not immediately decrement the current
+	 * amount.
+	 *
+	 * Instead we retain the current runtime/deadline and let the new
+	 * parameters take effect after the current reservation period lapses.
+	 * This is safe (albeit pessimistic) because the 0-lag point is always
+	 * before the current scheduling deadline.
+	 *
+	 * We can still have temporary overloads because we do not delay the
+	 * change in bandwidth until that time; so admission control is
+	 * not on the safe side. It does however guarantee tasks will never
+	 * consume more than promised.
+	 */
 }
 
 /*
@@ -4642,6 +4665,9 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur,
 	struct dl_bw *cur_dl_b;
 	unsigned long flags;
 
+	if (!cpumask_weight(cur))
+		return ret;
+
 	rcu_read_lock_sched();
 	cur_dl_b = dl_bw_of(cpumask_any(cur));
 	trial_cpus = cpumask_weight(trial);

kernel/sched/deadline.c

@@ -1094,6 +1094,7 @@ static void task_dead_dl(struct task_struct *p)
 	 * Since we are TASK_DEAD we won't slip out of the domain!
 	 */
 	raw_spin_lock_irq(&dl_b->lock);
+	/* XXX we should retain the bw until 0-lag */
 	dl_b->total_bw -= p->dl.dl_bw;
 	raw_spin_unlock_irq(&dl_b->lock);
 
@@ -1614,8 +1615,8 @@ static void cancel_dl_timer(struct rq *rq, struct task_struct *p)
 
 static void switched_from_dl(struct rq *rq, struct task_struct *p)
 {
+	/* XXX we should retain the bw until 0-lag */
 	cancel_dl_timer(rq, p);
-
 	__dl_clear_params(p);
 
 	/*

kernel/sched/fair.c

@@ -1730,7 +1730,7 @@ static int preferred_group_nid(struct task_struct *p, int nid)
 	nodes = node_online_map;
 	for (dist = sched_max_numa_distance; dist > LOCAL_DISTANCE; dist--) {
 		unsigned long max_faults = 0;
-		nodemask_t max_group;
+		nodemask_t max_group = NODE_MASK_NONE;
 		int a, b;
 
 		/* Are there nodes at this distance from each other? */