Merge branch 'sched-fixes-for-linus' of...

Merge branch 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/peterz/linux-2.6-sched

* 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/peterz/linux-2.6-sched:
  sched: Fix bug in SCHED_IDLE interaction with group scheduling
  sched: Fix rt_rq->pushable_tasks initialization in init_rt_rq()
  sched: Reset sched stats on fork()
  sched_rt: Fix overload bug on rt group scheduling
  sched: Documentation/sched-rt-group: Fix style issues & bump version

Documentation/scheduler/sched-rt-group.txt

@@ -73,7 +73,7 @@ The remaining CPU time will be used for user input and other tasks. Because
 realtime tasks have explicitly allocated the CPU time they need to perform
 their tasks, buffer underruns in the graphics or audio can be eliminated.
 
-NOTE: the above example is not fully implemented as of yet (2.6.25). We still
+NOTE: the above example is not fully implemented yet. We still
 lack an EDF scheduler to make non-uniform periods usable.
 
 
@@ -140,14 +140,15 @@ The other option is:
 
 .o CONFIG_CGROUP_SCHED (aka "Basis for grouping tasks" = "Control groups")
 
-This uses the /cgroup virtual file system and "/cgroup/<cgroup>/cpu.rt_runtime_us"
-to control the CPU time reserved for each control group instead.
+This uses the /cgroup virtual file system and
+"/cgroup/<cgroup>/cpu.rt_runtime_us" to control the CPU time reserved for each
+control group instead.
 
 For more information on working with control groups, you should read
 Documentation/cgroups/cgroups.txt as well.
 
-Group settings are checked against the following limits in order to keep the configuration
-schedulable:
+Group settings are checked against the following limits in order to keep the
+configuration schedulable:
 
    \Sum_{i} runtime_{i} / global_period <= global_runtime / global_period
 
@@ -189,7 +190,7 @@ Implementing SCHED_EDF might take a while to complete. Priority Inheritance is
 the biggest challenge as the current linux PI infrastructure is geared towards
 the limited static priority levels 0-99. With deadline scheduling you need to
 do deadline inheritance (since priority is inversely proportional to the
-deadline delta (deadline - now).
+deadline delta (deadline - now)).
 
 This means the whole PI machinery will have to be reworked - and that is one of
 the most complex pieces of code we have.

kernel/sched.c

@@ -493,6 +493,7 @@ struct rt_rq {
 #endif
 #ifdef CONFIG_SMP
 	unsigned long rt_nr_migratory;
+	unsigned long rt_nr_total;
 	int overloaded;
 	struct plist_head pushable_tasks;
 #endif
@@ -2571,15 +2572,37 @@ static void __sched_fork(struct task_struct *p)
 	p->se.avg_wakeup		= sysctl_sched_wakeup_granularity;
 
 #ifdef CONFIG_SCHEDSTATS
-	p->se.wait_start		= 0;
-	p->se.sum_sleep_runtime		= 0;
-	p->se.sleep_start		= 0;
-	p->se.block_start		= 0;
-	p->se.sleep_max			= 0;
-	p->se.block_max			= 0;
-	p->se.exec_max			= 0;
-	p->se.slice_max			= 0;
-	p->se.wait_max			= 0;
+	p->se.wait_start			= 0;
+	p->se.wait_max				= 0;
+	p->se.wait_count			= 0;
+	p->se.wait_sum				= 0;
+
+	p->se.sleep_start			= 0;
+	p->se.sleep_max				= 0;
+	p->se.sum_sleep_runtime			= 0;
+
+	p->se.block_start			= 0;
+	p->se.block_max				= 0;
+	p->se.exec_max				= 0;
+	p->se.slice_max				= 0;
+
+	p->se.nr_migrations_cold		= 0;
+	p->se.nr_failed_migrations_affine	= 0;
+	p->se.nr_failed_migrations_running	= 0;
+	p->se.nr_failed_migrations_hot		= 0;
+	p->se.nr_forced_migrations		= 0;
+	p->se.nr_forced2_migrations		= 0;
+
+	p->se.nr_wakeups			= 0;
+	p->se.nr_wakeups_sync			= 0;
+	p->se.nr_wakeups_migrate		= 0;
+	p->se.nr_wakeups_local			= 0;
+	p->se.nr_wakeups_remote			= 0;
+	p->se.nr_wakeups_affine			= 0;
+	p->se.nr_wakeups_affine_attempts	= 0;
+	p->se.nr_wakeups_passive		= 0;
+	p->se.nr_wakeups_idle			= 0;
+
 #endif
 
 	INIT_LIST_HEAD(&p->rt.run_list);
@@ -9074,7 +9097,7 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
 #ifdef CONFIG_SMP
 	rt_rq->rt_nr_migratory = 0;
 	rt_rq->overloaded = 0;
-	plist_head_init(&rq->rt.pushable_tasks, &rq->lock);
+	plist_head_init(&rt_rq->pushable_tasks, &rq->lock);
 #endif
 
 	rt_rq->rt_time = 0;

kernel/sched_fair.c

@@ -687,7 +687,8 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 			 * all of which have the same weight.
 			 */
 			if (sched_feat(NORMALIZED_SLEEPER) &&
-					task_of(se)->policy != SCHED_IDLE)
+					(!entity_is_task(se) ||
+					 task_of(se)->policy != SCHED_IDLE))
 				thresh = calc_delta_fair(thresh, se);
 
 			vruntime -= thresh;

kernel/sched_rt.c

@@ -10,6 +10,8 @@ static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
 
 #ifdef CONFIG_RT_GROUP_SCHED
 
+#define rt_entity_is_task(rt_se) (!(rt_se)->my_q)
+
 static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
 {
 	return rt_rq->rq;
@@ -22,6 +24,8 @@ static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
 
 #else /* CONFIG_RT_GROUP_SCHED */
 
+#define rt_entity_is_task(rt_se) (1)
+
 static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
 {
 	return container_of(rt_rq, struct rq, rt);
@@ -73,7 +77,7 @@ static inline void rt_clear_overload(struct rq *rq)
 
 static void update_rt_migration(struct rt_rq *rt_rq)
 {
-	if (rt_rq->rt_nr_migratory && (rt_rq->rt_nr_running > 1)) {
+	if (rt_rq->rt_nr_migratory && rt_rq->rt_nr_total > 1) {
 		if (!rt_rq->overloaded) {
 			rt_set_overload(rq_of_rt_rq(rt_rq));
 			rt_rq->overloaded = 1;
@@ -86,6 +90,12 @@ static void update_rt_migration(struct rt_rq *rt_rq)
 
 static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
+	if (!rt_entity_is_task(rt_se))
+		return;
+
+	rt_rq = &rq_of_rt_rq(rt_rq)->rt;
+
+	rt_rq->rt_nr_total++;
 	if (rt_se->nr_cpus_allowed > 1)
 		rt_rq->rt_nr_migratory++;
 
@@ -94,6 +104,12 @@ static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 
 static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
+	if (!rt_entity_is_task(rt_se))
+		return;
+
+	rt_rq = &rq_of_rt_rq(rt_rq)->rt;
+
+	rt_rq->rt_nr_total--;
 	if (rt_se->nr_cpus_allowed > 1)
 		rt_rq->rt_nr_migratory--;