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

* 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  sched: disable the hrtick for now
  sched: revert back to per-rq vruntime
  sched: fair scheduler should not resched rt tasks
  sched: optimize group load balancer
  sched: minor fast-path overhead reduction
  sched: fix the wrong mask_len, cleanup
  sched: kill unused scheduler decl.
  sched: fix the wrong mask_len
  sched: only update rq->clock while holding rq->lock

1 files changed, 40 insertions, 22 deletions

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index f604dae71316..9573c33688b8 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -73,6 +73,8 @@ unsigned int sysctl_sched_wakeup_granularity = 5000000UL;
 
 const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
 
+static const struct sched_class fair_sched_class;
+
 /**************************************************************
  * CFS operations on generic schedulable entities:
  */
@@ -334,7 +336,7 @@ int sched_nr_latency_handler(struct ctl_table *table, int write,
 #endif
 
 /*
- * delta *= w / rw
+ * delta *= P[w / rw]
  */
 static inline unsigned long
 calc_delta_weight(unsigned long delta, struct sched_entity *se)
@@ -348,15 +350,13 @@ calc_delta_weight(unsigned long delta, struct sched_entity *se)
 }
 
 /*
- * delta *= rw / w
+ * delta /= w
  */
 static inline unsigned long
 calc_delta_fair(unsigned long delta, struct sched_entity *se)
 {
-        for_each_sched_entity(se) {
-                delta = calc_delta_mine(delta,
-                                cfs_rq_of(se)->load.weight, &se->load);
-        }
+        if (unlikely(se->load.weight != NICE_0_LOAD))
+                delta = calc_delta_mine(delta, NICE_0_LOAD, &se->load);
 
         return delta;
 }
@@ -386,26 +386,26 @@ static u64 __sched_period(unsigned long nr_running)
  * We calculate the wall-time slice from the period by taking a part
  * proportional to the weight.
  *
- * s = p*w/rw
+ * s = p*P[w/rw]
  */
 static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-        return calc_delta_weight(__sched_period(cfs_rq->nr_running), se);
+        unsigned long nr_running = cfs_rq->nr_running;
+
+        if (unlikely(!se->on_rq))
+                nr_running++;
+
+        return calc_delta_weight(__sched_period(nr_running), se);
 }
 
 /*
  * We calculate the vruntime slice of a to be inserted task
  *
- * vs = s*rw/w = p
+ * vs = s/w
  */
-static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-        unsigned long nr_running = cfs_rq->nr_running;
-
-        if (!se->on_rq)
-                nr_running++;
-
-        return __sched_period(nr_running);
+        return calc_delta_fair(sched_slice(cfs_rq, se), se);
 }
 
 /*
@@ -628,7 +628,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
          * stays open at the end.
          */
         if (initial && sched_feat(START_DEBIT))
-                vruntime += sched_vslice_add(cfs_rq, se);
+                vruntime += sched_vslice(cfs_rq, se);
 
         if (!initial) {
                 /* sleeps upto a single latency don't count. */
@@ -748,7 +748,7 @@ pick_next(struct cfs_rq *cfs_rq, struct sched_entity *se)
         struct rq *rq = rq_of(cfs_rq);
         u64 pair_slice = rq->clock - cfs_rq->pair_start;
 
-        if (!cfs_rq->next || pair_slice > sched_slice(cfs_rq, cfs_rq->next)) {
+        if (!cfs_rq->next || pair_slice > sysctl_sched_min_granularity) {
                 cfs_rq->pair_start = rq->clock;
                 return se;
         }
@@ -849,11 +849,31 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
                 hrtick_start(rq, delta);
         }
 }
+
+/*
+ * called from enqueue/dequeue and updates the hrtick when the
+ * current task is from our class and nr_running is low enough
+ * to matter.
+ */
+static void hrtick_update(struct rq *rq)
+{
+        struct task_struct *curr = rq->curr;
+
+        if (curr->sched_class != &fair_sched_class)
+                return;
+
+        if (cfs_rq_of(&curr->se)->nr_running < sched_nr_latency)
+                hrtick_start_fair(rq, curr);
+}
 #else /* !CONFIG_SCHED_HRTICK */
 static inline void
 hrtick_start_fair(struct rq *rq, struct task_struct *p)
 {
 }
+
+static inline void hrtick_update(struct rq *rq)
+{
+}
 #endif
 
 /*
@@ -874,7 +894,7 @@ static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup)
                 wakeup = 1;
         }
 
-        hrtick_start_fair(rq, rq->curr);
+        hrtick_update(rq);
 }
 
 /*
@@ -896,7 +916,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
                 sleep = 1;
         }
 
-        hrtick_start_fair(rq, rq->curr);
+        hrtick_update(rq);
 }
 
 /*
@@ -1002,8 +1022,6 @@ static inline int wake_idle(int cpu, struct task_struct *p)
 
 #ifdef CONFIG_SMP
 
-static const struct sched_class fair_sched_class;
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
 /*
  * effective_load() calculates the load change as seen from the root_task_group