sched/fair: Fix forced idle sibling starvation corner case

If there is only one long running local task and the sibling is
forced idle, it  might not get a chance to run until a schedule
event happens on any cpu in the core.

So we check for this condition during a tick to see if a sibling
is starved and then give it a chance to schedule.

Signed-off-by: Vineeth Pillai <viremana@linux.microsoft.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Don Hiatt <dhiatt@digitalocean.com>
Tested-by: Hongyu Ning <hongyu.ning@linux.intel.com>
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20210422123308.617407840@infradead.org

3 files changed, 49 insertions, 8 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index db763f42a4b0..f5e1e6f96411 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5459,16 +5459,15 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 	/* reset state */
 	rq->core->core_cookie = 0UL;
+	if (rq->core->core_forceidle) {
+		need_sync = true;
+		rq->core->core_forceidle = false;
+	}
 	for_each_cpu(i, smt_mask) {
 		struct rq *rq_i = cpu_rq(i);
 
 		rq_i->core_pick = NULL;
 
-		if (rq_i->core_forceidle) {
-			need_sync = true;
-			rq_i->core_forceidle = false;
-		}
-
 		if (i != cpu)
 			update_rq_clock(rq_i);
 	}
@@ -5588,8 +5587,10 @@ next_class:;
 		if (!rq_i->core_pick)
 			continue;
 
-		if (is_task_rq_idle(rq_i->core_pick) && rq_i->nr_running)
-			rq_i->core_forceidle = true;
+		if (is_task_rq_idle(rq_i->core_pick) && rq_i->nr_running &&
+		    !rq_i->core->core_forceidle) {
+			rq_i->core->core_forceidle = true;
+		}
 
 		if (i == cpu) {
 			rq_i->core_pick = NULL;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 08be7a2eb05b..4d1ecab41e80 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10767,6 +10767,44 @@ static void rq_offline_fair(struct rq *rq)
 
 #endif /* CONFIG_SMP */
 
+#ifdef CONFIG_SCHED_CORE
+static inline bool
+__entity_slice_used(struct sched_entity *se, int min_nr_tasks)
+{
+	u64 slice = sched_slice(cfs_rq_of(se), se);
+	u64 rtime = se->sum_exec_runtime - se->prev_sum_exec_runtime;
+
+	return (rtime * min_nr_tasks > slice);
+}
+
+#define MIN_NR_TASKS_DURING_FORCEIDLE	2
+static inline void task_tick_core(struct rq *rq, struct task_struct *curr)
+{
+	if (!sched_core_enabled(rq))
+		return;
+
+	/*
+	 * If runqueue has only one task which used up its slice and
+	 * if the sibling is forced idle, then trigger schedule to
+	 * give forced idle task a chance.
+	 *
+	 * sched_slice() considers only this active rq and it gets the
+	 * whole slice. But during force idle, we have siblings acting
+	 * like a single runqueue and hence we need to consider runnable
+	 * tasks on this cpu and the forced idle cpu. Ideally, we should
+	 * go through the forced idle rq, but that would be a perf hit.
+	 * We can assume that the forced idle cpu has atleast
+	 * MIN_NR_TASKS_DURING_FORCEIDLE - 1 tasks and use that to check
+	 * if we need to give up the cpu.
+	 */
+	if (rq->core->core_forceidle && rq->cfs.nr_running == 1 &&
+	    __entity_slice_used(&curr->se, MIN_NR_TASKS_DURING_FORCEIDLE))
+		resched_curr(rq);
+}
+#else
+static inline void task_tick_core(struct rq *rq, struct task_struct *curr) {}
+#endif
+
 /*
  * scheduler tick hitting a task of our scheduling class.
  *
@@ -10790,6 +10828,8 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
 
 	update_misfit_status(curr, rq);
 	update_overutilized_status(task_rq(curr));
+
+	task_tick_core(rq, curr);
 }
 
 /*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index dd44a3127e9c..db555143380d 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1083,12 +1083,12 @@ struct rq {
 	unsigned int		core_enabled;
 	unsigned int		core_sched_seq;
 	struct rb_root		core_tree;
-	unsigned char		core_forceidle;
 
 	/* shared state */
 	unsigned int		core_task_seq;
 	unsigned int		core_pick_seq;
 	unsigned long		core_cookie;
+	unsigned char		core_forceidle;
 #endif
 };