[RFC PATCH v2 5/6] sched/fair: Add trivial fair server

[Juri Lelli <juri.lelli@redhat.com>]

From: Peter Zijlstra <peterz@infradead.org>

Use deadline servers to service fair tasks.

This patch adds a fair_server deadline entity which acts as a container
for fair entities and can be used to fix starvation when higher priority
(wrt fair) tasks are monopolizing CPU(s).

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/sched/core.c  |  1 +
 kernel/sched/fair.c  | 29 +++++++++++++++++++++++++++++
 kernel/sched/sched.h |  4 ++++
 3 files changed, 34 insertions(+)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7c471961fd0b8..6537637139c63 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7170,6 +7170,7 @@ void __init sched_init(void)
 #endif /* CONFIG_SMP */
 		hrtick_rq_init(rq);
 		atomic_set(&rq->nr_iowait, 0);
+		fair_server_init(rq);
 	}
 
 	set_load_weight(&init_task, false);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5130239c0e1e5..6a97ee2a4e26d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5514,6 +5514,9 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	 */
 	util_est_enqueue(&rq->cfs, p);
 
+	if (!rq->cfs.h_nr_running)
+		dl_server_start(&rq->fair_server);
+
 	/*
 	 * If in_iowait is set, the code below may not trigger any cpufreq
 	 * utilization updates, so do it here explicitly with the IOWAIT flag
@@ -5666,6 +5669,9 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		rq->next_balance = jiffies;
 
 dequeue_throttle:
+	if (!rq->cfs.h_nr_running)
+		dl_server_stop(&rq->fair_server);
+
 	util_est_dequeue(&rq->cfs, p, task_sleep);
 	hrtick_update(rq);
 }
@@ -7151,6 +7157,29 @@ static struct task_struct *__pick_next_task_fair(struct rq *rq)
 	return pick_next_task_fair(rq, NULL, NULL);
 }
 
+static bool fair_server_has_tasks(struct sched_dl_entity *dl_se)
+{
+	return !!dl_se->rq->cfs.nr_running;
+}
+
+static struct task_struct *fair_server_pick(struct sched_dl_entity *dl_se)
+{
+	return pick_next_task_fair(dl_se->rq, NULL, NULL);
+}
+
+void fair_server_init(struct rq *rq)
+{
+	struct sched_dl_entity *dl_se = &rq->fair_server;
+
+	init_dl_entity(dl_se);
+
+	dl_se->dl_runtime = TICK_NSEC;
+	dl_se->dl_deadline = 20 * TICK_NSEC;
+	dl_se->dl_period = 20 * TICK_NSEC;
+
+	dl_server_init(dl_se, rq, fair_server_has_tasks, fair_server_pick);
+}
+
 /*
  * Account for a descheduled task:
  */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index f035cd8ccd224..bf8c9c07705c9 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -375,6 +375,8 @@ extern void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
 		    dl_server_has_tasks_f has_tasks,
 		    dl_server_pick_f pick);
 
+extern void fair_server_init(struct rq *);
+
 #ifdef CONFIG_CGROUP_SCHED
 
 #include <linux/cgroup.h>
@@ -959,6 +961,8 @@ struct rq {
 	struct rt_rq		rt;
 	struct dl_rq		dl;
 
+	struct sched_dl_entity	fair_server;
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* list of leaf cfs_rq on this CPU: */
 	struct list_head	leaf_cfs_rq_list;
-- 
2.26.2