sched: tidy up and simplify the bonus balance

make the bonus balance more consistent: do not hand out a bonus if
there's too much in flight already, and only deduct as much from a
runner as it has the capacity. This makes the bonus engine a zero-sum
game (as intended).

this also simplifies the code:

   text    data     bss     dec     hex filename
  34770    2998      24   37792    93a0 sched.o.before
  34749    2998      24   37771    938b sched.o.after

and it also avoids overscheduling in sleep-happy workloads like
hackbench.c.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 10 insertions, 4 deletions

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 6b0974c3fb67..c578370cd693 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -306,6 +306,8 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr)
                 delta = min(cfs_rq->sleeper_bonus, (u64)delta_exec);
                 delta = calc_delta_mine(delta, curr->load.weight, lw);
                 delta = min((u64)delta, cfs_rq->sleeper_bonus);
+                delta = min(delta, (unsigned long)(
+                        (long)sysctl_sched_runtime_limit - curr->wait_runtime));
                 cfs_rq->sleeper_bonus -= delta;
                 delta_mine -= delta;
         }
@@ -493,6 +495,13 @@ static void __enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
         unsigned long load = cfs_rq->load.weight, delta_fair;
         long prev_runtime;
 
+        /*
+         * Do not boost sleepers if there's too much bonus 'in flight'
+         * already:
+         */
+        if (unlikely(cfs_rq->sleeper_bonus > sysctl_sched_runtime_limit))
+                return;
+
         if (sysctl_sched_features & SCHED_FEAT_SLEEPER_LOAD_AVG)
                 load = rq_of(cfs_rq)->cpu_load[2];
 
@@ -512,16 +521,13 @@ static void __enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
         prev_runtime = se->wait_runtime;
         __add_wait_runtime(cfs_rq, se, delta_fair);
+        schedstat_add(cfs_rq, wait_runtime, se->wait_runtime);
         delta_fair = se->wait_runtime - prev_runtime;
 
         /*
          * Track the amount of bonus we've given to sleepers:
          */
         cfs_rq->sleeper_bonus += delta_fair;
-        if (unlikely(cfs_rq->sleeper_bonus > sysctl_sched_runtime_limit))
-                cfs_rq->sleeper_bonus = sysctl_sched_runtime_limit;
-
-        schedstat_add(cfs_rq, wait_runtime, se->wait_runtime);
 }
 
 static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)