Merge git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi-rc-fixes-2.6

[sfrench/cifs-2.6.git] / kernel / sched_fair.c

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 8e1352c75557308bf1e892bb260b39e9feffd10f..0566f2a03c420717e6604bde5deac33cb71f6ed1 100644 (file)
--- 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;
@@ -712,7 +719,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
                __enqueue_entity(cfs_rq, se);
 }
 
-static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
        if (cfs_rq->last == se)
                cfs_rq->last = NULL;
@@ -721,6 +728,12 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
                cfs_rq->next = NULL;
 }
 
+static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+       for_each_sched_entity(se)
+               __clear_buddies(cfs_rq_of(se), se);
+}
+
 static void
 dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 {
@@ -761,8 +774,14 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 
        ideal_runtime = sched_slice(cfs_rq, curr);
        delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
-       if (delta_exec > ideal_runtime)
+       if (delta_exec > ideal_runtime) {
                resched_task(rq_of(cfs_rq)->curr);
+               /*
+                * The current task ran long enough, ensure it doesn't get
+                * re-elected due to buddy favours.
+                */
+               clear_buddies(cfs_rq, curr);
+       }
 }
 
 static void
@@ -1340,14 +1359,18 @@ 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;
+       }
 }
 
 /*
@@ -1393,11 +1416,17 @@ 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;
@@ -1435,6 +1464,11 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
 
        do {
                se = pick_next_entity(cfs_rq);
+               /*
+                * If se was a buddy, clear it so that it will have to earn
+                * the favour again.
+                */
+               __clear_buddies(cfs_rq, se);
                set_next_entity(cfs_rq, se);
                cfs_rq = group_cfs_rq(se);
        } while (cfs_rq);