sched, autogroup: Fix CONFIG_RT_GROUP_SCHED sched_setscheduler() failure

If CONFIG_RT_GROUP_SCHED is set, __sched_setscheduler() fails due to autogroup
not allocating rt_runtime.  Free unused/unusable rt_se and rt_rq, redirect RT
tasks to the root task group, and tell __sched_setscheduler() that it's ok.

Reported-and-tested-by: Bharata B Rao <bharata@linux.vnet.ibm.com>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1294890890.8089.39.camel@marge.simson.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

kernel/sched.c

@@ -4871,7 +4871,8 @@ recheck:
 		 * assigned.
 		 */
 		if (rt_bandwidth_enabled() && rt_policy(policy) &&
-				task_group(p)->rt_bandwidth.rt_runtime == 0) {
+				task_group(p)->rt_bandwidth.rt_runtime == 0 &&
+				!task_group_is_autogroup(task_group(p))) {
 			__task_rq_unlock(rq);
 			raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 			return -EPERM;

kernel/sched_autogroup.c

@@ -27,6 +27,11 @@ static inline void autogroup_destroy(struct kref *kref)
 {
 	struct autogroup *ag = container_of(kref, struct autogroup, kref);
 
+#ifdef CONFIG_RT_GROUP_SCHED
+	/* We've redirected RT tasks to the root task group... */
+	ag->tg->rt_se = NULL;
+	ag->tg->rt_rq = NULL;
+#endif
 	sched_destroy_group(ag->tg);
 }
 
@@ -55,6 +60,10 @@ static inline struct autogroup *autogroup_task_get(struct task_struct *p)
 	return ag;
 }
 
+#ifdef CONFIG_RT_GROUP_SCHED
+static void free_rt_sched_group(struct task_group *tg);
+#endif
+
 static inline struct autogroup *autogroup_create(void)
 {
 	struct autogroup *ag = kzalloc(sizeof(*ag), GFP_KERNEL);
@@ -72,6 +81,19 @@ static inline struct autogroup *autogroup_create(void)
 	init_rwsem(&ag->lock);
 	ag->id = atomic_inc_return(&autogroup_seq_nr);
 	ag->tg = tg;
+#ifdef CONFIG_RT_GROUP_SCHED
+	/*
+	 * Autogroup RT tasks are redirected to the root task group
+	 * so we don't have to move tasks around upon policy change,
+	 * or flail around trying to allocate bandwidth on the fly.
+	 * A bandwidth exception in __sched_setscheduler() allows
+	 * the policy change to proceed.  Thereafter, task_group()
+	 * returns &root_task_group, so zero bandwidth is required.
+	 */
+	free_rt_sched_group(tg);
+	tg->rt_se = root_task_group.rt_se;
+	tg->rt_rq = root_task_group.rt_rq;
+#endif
 	tg->autogroup = ag;
 
 	return ag;
@@ -106,6 +128,11 @@ task_wants_autogroup(struct task_struct *p, struct task_group *tg)
 	return true;
 }
 
+static inline bool task_group_is_autogroup(struct task_group *tg)
+{
+	return tg != &root_task_group && tg->autogroup;
+}
+
 static inline struct task_group *
 autogroup_task_group(struct task_struct *p, struct task_group *tg)
 {

kernel/sched_autogroup.h

@@ -15,6 +15,10 @@ autogroup_task_group(struct task_struct *p, struct task_group *tg);
 
 static inline void autogroup_init(struct task_struct *init_task) {  }
 static inline void autogroup_free(struct task_group *tg) { }
+static inline bool task_group_is_autogroup(struct task_group *tg)
+{
+	return 0;
+}
 
 static inline struct task_group *
 autogroup_task_group(struct task_struct *p, struct task_group *tg)