sched: Account number of SCHED_IDLE entities on each cfs_rq

Adds cfs_rq->idle_nr_running, which accounts the number of idle entities
directly enqueued on the cfs_rq.
Signed-off-by: Josh Don <joshdon@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20210820010403.946838-3-joshdon@google.com

kernel/sched/debug.c

@@ -614,6 +614,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			cfs_rq->nr_spread_over);
 	SEQ_printf(m, "  .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
 	SEQ_printf(m, "  .%-30s: %d\n", "h_nr_running", cfs_rq->h_nr_running);
+	SEQ_printf(m, "  .%-30s: %d\n", "idle_nr_running",
+			cfs_rq->idle_nr_running);
 	SEQ_printf(m, "  .%-30s: %d\n", "idle_h_nr_running",
 			cfs_rq->idle_h_nr_running);
 	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);

kernel/sched/fair.c

@@ -2995,6 +2995,8 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	}
 #endif
 	cfs_rq->nr_running++;
+	if (se_is_idle(se))
+		cfs_rq->idle_nr_running++;
 }
 
 static void
@@ -3008,6 +3010,8 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	}
 #endif
 	cfs_rq->nr_running--;
+	if (se_is_idle(se))
+		cfs_rq->idle_nr_running--;
 }
 
 /*
@@ -5577,6 +5581,17 @@ static int sched_idle_rq(struct rq *rq)
 			rq->nr_running);
 }
 
+/*
+ * Returns true if cfs_rq only has SCHED_IDLE entities enqueued. Note the use
+ * of idle_nr_running, which does not consider idle descendants of normal
+ * entities.
+ */
+static bool sched_idle_cfs_rq(struct cfs_rq *cfs_rq)
+{
+	return cfs_rq->nr_running &&
+		cfs_rq->nr_running == cfs_rq->idle_nr_running;
+}
+
 #ifdef CONFIG_SMP
 static int sched_idle_cpu(int cpu)
 {
@@ -11575,7 +11590,7 @@ int sched_group_set_idle(struct task_group *tg, long idle)
 	for_each_possible_cpu(i) {
 		struct rq *rq = cpu_rq(i);
 		struct sched_entity *se = tg->se[i];
-		struct cfs_rq *grp_cfs_rq = tg->cfs_rq[i];
+		struct cfs_rq *parent_cfs_rq, *grp_cfs_rq = tg->cfs_rq[i];
 		bool was_idle = cfs_rq_is_idle(grp_cfs_rq);
 		long idle_task_delta;
 		struct rq_flags rf;
@@ -11586,6 +11601,14 @@ int sched_group_set_idle(struct task_group *tg, long idle)
 		if (WARN_ON_ONCE(was_idle == cfs_rq_is_idle(grp_cfs_rq)))
 			goto next_cpu;
 
+		if (se->on_rq) {
+			parent_cfs_rq = cfs_rq_of(se);
+			if (cfs_rq_is_idle(grp_cfs_rq))
+				parent_cfs_rq->idle_nr_running++;
+			else
+				parent_cfs_rq->idle_nr_running--;
+		}
+
 		idle_task_delta = grp_cfs_rq->h_nr_running -
 				  grp_cfs_rq->idle_h_nr_running;
 		if (!cfs_rq_is_idle(grp_cfs_rq))

kernel/sched/sched.h

@@ -530,6 +530,7 @@ struct cfs_rq {
 	struct load_weight	load;
 	unsigned int		nr_running;
 	unsigned int		h_nr_running;      /* SCHED_{NORMAL,BATCH,IDLE} */
+	unsigned int		idle_nr_running;   /* SCHED_IDLE */
 	unsigned int		idle_h_nr_running; /* SCHED_IDLE */
 
 	u64			exec_clock;