1 files changed, 76 insertions, 61 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index f8b8996228d..f52a8801b7a 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -306,52 +306,6 @@ static int init_task_group_load = INIT_TASK_GROUP_LOAD;
  */
 struct task_group init_task_group;
 
-/* return group to which a task belongs */
-static inline struct task_group *task_group(struct task_struct *p)
-{
-	struct task_group *tg;
-
-#ifdef CONFIG_CGROUP_SCHED
-	tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id),
-				struct task_group, css);
-#else
-	tg = &init_task_group;
-#endif
-	return tg;
-}
-
-/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
-static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
-{
-	/*
-	 * Strictly speaking this rcu_read_lock() is not needed since the
-	 * task_group is tied to the cgroup, which in turn can never go away
-	 * as long as there are tasks attached to it.
-	 *
-	 * However since task_group() uses task_subsys_state() which is an
-	 * rcu_dereference() user, this quiets CONFIG_PROVE_RCU.
-	 */
-	rcu_read_lock();
-#ifdef CONFIG_FAIR_GROUP_SCHED
-	p->se.cfs_rq = task_group(p)->cfs_rq[cpu];
-	p->se.parent = task_group(p)->se[cpu];
-#endif
-
-#ifdef CONFIG_RT_GROUP_SCHED
-	p->rt.rt_rq  = task_group(p)->rt_rq[cpu];
-	p->rt.parent = task_group(p)->rt_se[cpu];
-#endif
-	rcu_read_unlock();
-}
-
-#else
-
-static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { }
-static inline struct task_group *task_group(struct task_struct *p)
-{
-	return NULL;
-}
-
 #endif	/* CONFIG_CGROUP_SCHED */
 
 /* CFS-related fields in a runqueue */
@@ -644,6 +598,49 @@ static inline int cpu_of(struct rq *rq)
 #define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
 #define raw_rq()		(&__raw_get_cpu_var(runqueues))
 
+#ifdef CONFIG_CGROUP_SCHED
+
+/*
+ * Return the group to which this tasks belongs.
+ *
+ * We use task_subsys_state_check() and extend the RCU verification
+ * with lockdep_is_held(&task_rq(p)->lock) because cpu_cgroup_attach()
+ * holds that lock for each task it moves into the cgroup. Therefore
+ * by holding that lock, we pin the task to the current cgroup.
+ */
+static inline struct task_group *task_group(struct task_struct *p)
+{
+	struct cgroup_subsys_state *css;
+
+	css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
+			lockdep_is_held(&task_rq(p)->lock));
+	return container_of(css, struct task_group, css);
+}
+
+/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
+static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
+{
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	p->se.cfs_rq = task_group(p)->cfs_rq[cpu];
+	p->se.parent = task_group(p)->se[cpu];
+#endif
+
+#ifdef CONFIG_RT_GROUP_SCHED
+	p->rt.rt_rq  = task_group(p)->rt_rq[cpu];
+	p->rt.parent = task_group(p)->rt_se[cpu];
+#endif
+}
+
+#else /* CONFIG_CGROUP_SCHED */
+
+static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { }
+static inline struct task_group *task_group(struct task_struct *p)
+{
+	return NULL;
+}
+
+#endif /* CONFIG_CGROUP_SCHED */
+
 inline void update_rq_clock(struct rq *rq)
 {
 	if (!rq->skip_clock_update)
@@ -1257,6 +1254,12 @@ static void sched_avg_update(struct rq *rq)
 	s64 period = sched_avg_period();
 
 	while ((s64)(rq->clock - rq->age_stamp) > period) {
+		/*
+		 * Inline assembly required to prevent the compiler
+		 * optimising this loop into a divmod call.
+		 * See __iter_div_u64_rem() for another example of this.
+		 */
+		asm("" : "+rm" (rq->age_stamp));
 		rq->age_stamp += period;
 		rq->rt_avg /= 2;
 	}
@@ -1660,9 +1663,6 @@ static void update_shares(struct sched_domain *sd)
 
 static void update_h_load(long cpu)
 {
-	if (root_task_group_empty())
-		return;
-
 	walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
 }
 
@@ -2494,7 +2494,16 @@ void sched_fork(struct task_struct *p, int clone_flags)
 	if (p->sched_class->task_fork)
 		p->sched_class->task_fork(p);
 
+	/*
+	 * The child is not yet in the pid-hash so no cgroup attach races,
+	 * and the cgroup is pinned to this child due to cgroup_fork()
+	 * is ran before sched_fork().
+	 *
+	 * Silence PROVE_RCU.
+	 */
+	rcu_read_lock();
 	set_task_cpu(p, cpu);
+	rcu_read_unlock();
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
 	if (likely(sched_info_on()))
@@ -2864,9 +2873,9 @@ unsigned long nr_iowait(void)
 	return sum;
 }
 
-unsigned long nr_iowait_cpu(void)
+unsigned long nr_iowait_cpu(int cpu)
 {
-	struct rq *this = this_rq();
+	struct rq *this = cpu_rq(cpu);
 	return atomic_read(&this->nr_iowait);
 }
 
@@ -4465,16 +4474,6 @@ recheck:
 	}
 
 	if (user) {
-#ifdef CONFIG_RT_GROUP_SCHED
-		/*
-		 * Do not allow realtime tasks into groups that have no runtime
-		 * assigned.
-		 */
-		if (rt_bandwidth_enabled() && rt_policy(policy) &&
-				task_group(p)->rt_bandwidth.rt_runtime == 0)
-			return -EPERM;
-#endif
-
 		retval = security_task_setscheduler(p, policy, param);
 		if (retval)
 			return retval;
@@ -4490,6 +4489,22 @@ recheck:
 	 * runqueue lock must be held.
 	 */
 	rq = __task_rq_lock(p);
+
+#ifdef CONFIG_RT_GROUP_SCHED
+	if (user) {
+		/*
+		 * Do not allow realtime tasks into groups that have no runtime
+		 * assigned.
+		 */
+		if (rt_bandwidth_enabled() && rt_policy(policy) &&
+				task_group(p)->rt_bandwidth.rt_runtime == 0) {
+			__task_rq_unlock(rq);
+			raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+			return -EPERM;
+		}
+	}
+#endif
+
 	/* recheck policy now with rq lock held */
 	if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
 		policy = oldpolicy = -1;