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: sched_slice() fixlet
  sched: fix update_min_vruntime
  sched: SCHED_OTHER vs SCHED_IDLE isolation
  sched: SCHED_IDLE weight change
  sched: fix bandwidth validation for UID grouping
  Revert "sched: improve preempt debugging"

2 files changed, 37 insertions, 13 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index eb1931eef587..52bbf1c842a8 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1323,8 +1323,8 @@ static inline void update_load_sub(struct load_weight *lw, unsigned long dec)
  * slice expiry etc.
  */
 
-#define WEIGHT_IDLEPRIO         2
-#define WMULT_IDLEPRIO          (1 << 31)
+#define WEIGHT_IDLEPRIO                3
+#define WMULT_IDLEPRIO         1431655765
 
 /*
  * Nice levels are multiplicative, with a gentle 10% change for every
@@ -4440,7 +4440,7 @@ void __kprobes sub_preempt_count(int val)
         /*
          * Underflow?
          */
-       if (DEBUG_LOCKS_WARN_ON(val > preempt_count() - (!!kernel_locked())))
+        if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
                 return;
         /*
          * Is the spinlock portion underflowing?
@@ -9050,6 +9050,13 @@ static int tg_schedulable(struct task_group *tg, void *data)
                 runtime = d->rt_runtime;
         }
 
+#ifdef CONFIG_USER_SCHED
+        if (tg == &root_task_group) {
+                period = global_rt_period();
+                runtime = global_rt_runtime();
+        }
+#endif
+
         /*
          * Cannot have more runtime than the period.
          */
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 8e1352c75557..5cc1c162044f 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -283,7 +283,7 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
                                                    struct sched_entity,
                                                    run_node);
 
-                if (vruntime == cfs_rq->min_vruntime)
+                if (!cfs_rq->curr)
                         vruntime = se->vruntime;
                 else
                         vruntime = min_vruntime(vruntime, se->vruntime);
@@ -429,7 +429,10 @@ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
         u64 slice = __sched_period(cfs_rq->nr_running + !se->on_rq);
 
         for_each_sched_entity(se) {
-                struct load_weight *load = &cfs_rq->load;
+                struct load_weight *load;
+
+                cfs_rq = cfs_rq_of(se);
+                load = &cfs_rq->load;
 
                 if (unlikely(!se->on_rq)) {
                         struct load_weight lw = cfs_rq->load;
@@ -677,9 +680,13 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
                         unsigned long thresh = sysctl_sched_latency;
 
                         /*
-                         * convert the sleeper threshold into virtual time
+                         * Convert the sleeper threshold into virtual time.
+                         * SCHED_IDLE is a special sub-class.  We care about
+                         * fairness only relative to other SCHED_IDLE tasks,
+                         * all of which have the same weight.
                          */
-                        if (sched_feat(NORMALIZED_SLEEPER))
+                        if (sched_feat(NORMALIZED_SLEEPER) &&
+                                        task_of(se)->policy != SCHED_IDLE)
                                 thresh = calc_delta_fair(thresh, se);
 
                         vruntime -= thresh;
@@ -1340,14 +1347,18 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
 
 static void set_last_buddy(struct sched_entity *se)
 {
-        for_each_sched_entity(se)
-                cfs_rq_of(se)->last = se;
+        if (likely(task_of(se)->policy != SCHED_IDLE)) {
+                for_each_sched_entity(se)
+                        cfs_rq_of(se)->last = se;
+        }
 }
 
 static void set_next_buddy(struct sched_entity *se)
 {
-        for_each_sched_entity(se)
-                cfs_rq_of(se)->next = se;
+        if (likely(task_of(se)->policy != SCHED_IDLE)) {
+                for_each_sched_entity(se)
+                        cfs_rq_of(se)->next = se;
+        }
 }
 
 /*
@@ -1393,12 +1404,18 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
                 return;
 
         /*
-         * Batch tasks do not preempt (their preemption is driven by
+         * Batch and idle tasks do not preempt (their preemption is driven by
          * the tick):
          */
-        if (unlikely(p->policy == SCHED_BATCH))
+        if (unlikely(p->policy != SCHED_NORMAL))
                 return;
 
+        /* Idle tasks are by definition preempted by everybody. */
+        if (unlikely(curr->policy == SCHED_IDLE)) {
+                resched_task(curr);
+                return;
+        }
+
         if (!sched_feat(WAKEUP_PREEMPT))
                 return;