[RFC v3 5/6] Do not reclaim the whole CPU bandwidth

[Luca Abeni]

Original GRUB tends to reclaim 100% of the CPU time... And this allows a
CPU hot to starve non-deadline tasks.
To address this issue, allow the scheduler to reclaim only a specified
fraction of CPU time.

Signed-off-by: Luca Abeni <luca.abeni@xxxxxxxx>
---
 kernel/sched/core.c     | 4 ++++
 kernel/sched/deadline.c | 7 ++++++-
 kernel/sched/sched.h    | 6 ++++++
 3 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 337a5f0..6706b5f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8256,6 +8256,10 @@ static void sched_dl_do_global(void)
 		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 
 		rcu_read_unlock_sched();
+		if (dl_b->bw == -1)
+			cpu_rq(cpu)->dl.non_deadline_bw = 0;
+		else
+			cpu_rq(cpu)->dl.non_deadline_bw = (1 << 20) - new_bw;
 	}
 }
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index fa10fcd..cab76e8 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -147,6 +147,11 @@ void init_dl_rq(struct dl_rq *dl_rq)
 #else
 	init_dl_bw(&dl_rq->dl_bw);
 #endif
+	if (global_rt_runtime() == RUNTIME_INF)
+		dl_rq->non_deadline_bw = 0;
+	else
+		dl_rq->non_deadline_bw = (1 << 20) -
+			to_ratio(global_rt_period(), global_rt_runtime());
 }
 
 #ifdef CONFIG_SMP
@@ -780,7 +785,7 @@ extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
  */
 u64 grub_reclaim(u64 delta, struct rq *rq)
 {
-	return (delta * rq->dl.running_bw) >> 20;
+	return (delta * (rq->dl.non_deadline_bw + rq->dl.running_bw)) >> 20;
 }
 
 /*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e82c419..2748431 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -541,6 +541,12 @@ struct dl_rq {
 	 * task blocks
 	 */
 	s64 running_bw;
+
+	/*
+	 * Fraction of the CPU utilization that cannot be reclaimed
+	 * by the GRUB algorithm.
+	 */
+	s64 non_deadline_bw;
 };
 
 #ifdef CONFIG_SMP
-- 
2.7.4