sched: Separate group-scheduling code more clearly

Clean up cfs/rt runqueue initialization by moving group scheduling
related code into the corresponding functions.

Also, keep group scheduling as an add-on, so that things are only done
additionally, i. e. remove the init_*_rq() calls from init_tg_*_entry().
(This removes a redundant initalization during sched_init()).

In case of group scheduling rt_rq->highest_prio.curr is now initialized
twice, but adding another #ifdef seems not worth it.

Signed-off-by: Jan H. Schönherr <schnhrr@cs.tu-berlin.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1310661163-16606-1-git-send-email-schnhrr@cs.tu-berlin.de
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/sched.c b/kernel/sched.c
index e3f0bac05270691ee2d5c74bba996ad4c9df3854..6fdf7ffbebc64e7a0a7b85f0850107a78a785f35 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -7859,17 +7859,10 @@ int in_sched_functions(unsigned long addr)
                && addr < (unsigned long)__sched_text_end);
 }
 
-static void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq)
+static void init_cfs_rq(struct cfs_rq *cfs_rq)
 {
        cfs_rq->tasks_timeline = RB_ROOT;
        INIT_LIST_HEAD(&cfs_rq->tasks);
-#ifdef CONFIG_FAIR_GROUP_SCHED
-       cfs_rq->rq = rq;
-       /* allow initial update_cfs_load() to truncate */
-#ifdef CONFIG_SMP
-       cfs_rq->load_stamp = 1;
-#endif
-#endif
        cfs_rq->min_vruntime = (u64)(-(1LL << 20));
 #ifndef CONFIG_64BIT
        cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
@@ -7889,13 +7882,9 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
        /* delimiter for bitsearch: */
        __set_bit(MAX_RT_PRIO, array->bitmap);
 
-#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
+#if defined CONFIG_SMP
        rt_rq->highest_prio.curr = MAX_RT_PRIO;
-#ifdef CONFIG_SMP
        rt_rq->highest_prio.next = MAX_RT_PRIO;
-#endif
-#endif
-#ifdef CONFIG_SMP
        rt_rq->rt_nr_migratory = 0;
        rt_rq->overloaded = 0;
        plist_head_init_raw(&rt_rq->pushable_tasks, &rq->lock);
@@ -7905,11 +7894,6 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
        rt_rq->rt_throttled = 0;
        rt_rq->rt_runtime = 0;
        raw_spin_lock_init(&rt_rq->rt_runtime_lock);
-
-#ifdef CONFIG_RT_GROUP_SCHED
-       rt_rq->rt_nr_boosted = 0;
-       rt_rq->rq = rq;
-#endif
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -7918,11 +7902,17 @@ static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
                                struct sched_entity *parent)
 {
        struct rq *rq = cpu_rq(cpu);
-       tg->cfs_rq[cpu] = cfs_rq;
-       init_cfs_rq(cfs_rq, rq);
+
        cfs_rq->tg = tg;
+       cfs_rq->rq = rq;
+#ifdef CONFIG_SMP
+       /* allow initial update_cfs_load() to truncate */
+       cfs_rq->load_stamp = 1;
+#endif
 
+       tg->cfs_rq[cpu] = cfs_rq;
        tg->se[cpu] = se;
+
        /* se could be NULL for root_task_group */
        if (!se)
                return;
@@ -7945,12 +7935,14 @@ static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
 {
        struct rq *rq = cpu_rq(cpu);
 
-       tg->rt_rq[cpu] = rt_rq;
-       init_rt_rq(rt_rq, rq);
+       rt_rq->highest_prio.curr = MAX_RT_PRIO;
+       rt_rq->rt_nr_boosted = 0;
+       rt_rq->rq = rq;
        rt_rq->tg = tg;
-       rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime;
 
+       tg->rt_rq[cpu] = rt_rq;
        tg->rt_se[cpu] = rt_se;
+
        if (!rt_se)
                return;
 
@@ -8032,7 +8024,7 @@ void __init sched_init(void)
                rq->nr_running = 0;
                rq->calc_load_active = 0;
                rq->calc_load_update = jiffies + LOAD_FREQ;
-               init_cfs_rq(&rq->cfs, rq);
+               init_cfs_rq(&rq->cfs);
                init_rt_rq(&rq->rt, rq);
 #ifdef CONFIG_FAIR_GROUP_SCHED
                root_task_group.shares = root_task_group_load;
@@ -8335,6 +8327,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
                if (!se)
                        goto err_free_rq;
 
+               init_cfs_rq(cfs_rq);
                init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
        }
 
@@ -8425,6 +8418,8 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
                if (!rt_se)
                        goto err_free_rq;
 
+               init_rt_rq(rt_rq, cpu_rq(i));
+               rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime;
                init_tg_rt_entry(tg, rt_rq, rt_se, i, parent->rt_se[i]);
        }