sched: re-instate vruntime based wakeup preemption

The advantage is that vruntime based wakeup preemption has a better
conceptual model. Here wakeup_gran = 0 means: preempt when 'fair'.
Therefore wakeup_gran is the granularity of unfairness we allow in order
to make progress.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index b71ee2c62297b46713230a753f6beb7417fc07ec..7af17e04a6db86cc6b753e0d5db68b13e4acc240 100644 (file)
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -143,6 +143,49 @@ static inline struct sched_entity *parent_entity(struct sched_entity *se)
        return se->parent;
 }
 
+/* return depth at which a sched entity is present in the hierarchy */
+static inline int depth_se(struct sched_entity *se)
+{
+       int depth = 0;
+
+       for_each_sched_entity(se)
+               depth++;
+
+       return depth;
+}
+
+static void
+find_matching_se(struct sched_entity **se, struct sched_entity **pse)
+{
+       int se_depth, pse_depth;
+
+       /*
+        * preemption test can be made between sibling entities who are in the
+        * same cfs_rq i.e who have a common parent. Walk up the hierarchy of
+        * both tasks until we find their ancestors who are siblings of common
+        * parent.
+        */
+
+       /* First walk up until both entities are at same depth */
+       se_depth = depth_se(*se);
+       pse_depth = depth_se(*pse);
+
+       while (se_depth > pse_depth) {
+               se_depth--;
+               *se = parent_entity(*se);
+       }
+
+       while (pse_depth > se_depth) {
+               pse_depth--;
+               *pse = parent_entity(*pse);
+       }
+
+       while (!is_same_group(*se, *pse)) {
+               *se = parent_entity(*se);
+               *pse = parent_entity(*pse);
+       }
+}
+
 #else  /* CONFIG_FAIR_GROUP_SCHED */
 
 static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
@@ -193,6 +236,11 @@ static inline struct sched_entity *parent_entity(struct sched_entity *se)
        return NULL;
 }
 
+static inline void
+find_matching_se(struct sched_entity **se, struct sched_entity **pse)
+{
+}
+
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
 
@@ -1244,12 +1292,41 @@ static unsigned long wakeup_gran(struct sched_entity *se)
         * More easily preempt - nice tasks, while not making it harder for
         * + nice tasks.
         */
-       if (sched_feat(ASYM_GRAN))
-               gran = calc_delta_mine(gran, NICE_0_LOAD, &se->load);
+       if (!sched_feat(ASYM_GRAN) || se->load.weight > NICE_0_LOAD)
+               gran = calc_delta_fair(sysctl_sched_wakeup_granularity, se);
 
        return gran;
 }
 
+/*
+ * Should 'se' preempt 'curr'.
+ *
+ *             |s1
+ *        |s2
+ *   |s3
+ *         g
+ *      |<--->|c
+ *
+ *  w(c, s1) = -1
+ *  w(c, s2) =  0
+ *  w(c, s3) =  1
+ *
+ */
+static int
+wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
+{
+       s64 gran, vdiff = curr->vruntime - se->vruntime;
+
+       if (vdiff <= 0)
+               return -1;
+
+       gran = wakeup_gran(curr);
+       if (vdiff > gran)
+               return 1;
+
+       return 0;
+}
+
 /*
  * Preempt the current task with a newly woken task if needed:
  */
@@ -1258,7 +1335,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
        struct task_struct *curr = rq->curr;
        struct cfs_rq *cfs_rq = task_cfs_rq(curr);
        struct sched_entity *se = &curr->se, *pse = &p->se;
-       s64 delta_exec;
 
        if (unlikely(rt_prio(p->prio))) {
                update_rq_clock(rq);
@@ -1296,9 +1372,19 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
                return;
        }
 
-       delta_exec = se->sum_exec_runtime - se->prev_sum_exec_runtime;
-       if (delta_exec > wakeup_gran(pse))
-               resched_task(curr);
+       find_matching_se(&se, &pse);
+
+       while (se) {
+               BUG_ON(!pse);
+
+               if (wakeup_preempt_entity(se, pse) == 1) {
+                       resched_task(curr);
+                       break;
+               }
+
+               se = parent_entity(se);
+               pse = parent_entity(pse);
+       }
 }
 
 static struct task_struct *pick_next_task_fair(struct rq *rq)