[RFC PATCH v3 06/16] sched/fair: Export newidle_balance()

[Vineeth Remanan Pillai <vpillai@digitalocean.com>]

From: Peter Zijlstra <peterz@infradead.org>

For pick_next_task_fair() it is the newidle balance that requires
dropping the rq->lock; provided we do put_prev_task() early, we can
also detect the condition for doing newidle early.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/sched/fair.c  | 18 ++++++++----------
 kernel/sched/sched.h |  4 ++++
 2 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 56fc2a1aa261..49707b4797de 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3615,8 +3615,6 @@ static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq)
 	return cfs_rq->avg.load_avg;
 }
 
-static int idle_balance(struct rq *this_rq, struct rq_flags *rf);
-
 static inline unsigned long task_util(struct task_struct *p)
 {
 	return READ_ONCE(p->se.avg.util_avg);
@@ -7087,11 +7085,10 @@ done: __maybe_unused;
 	return p;
 
 idle:
-	update_misfit_status(NULL, rq);
-	new_tasks = idle_balance(rq, rf);
+	new_tasks = newidle_balance(rq, rf);
 
 	/*
-	 * Because idle_balance() releases (and re-acquires) rq->lock, it is
+	 * Because newidle_balance() releases (and re-acquires) rq->lock, it is
 	 * possible for any higher priority task to appear. In that case we
 	 * must re-start the pick_next_entity() loop.
 	 */
@@ -9286,10 +9283,10 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 	ld_moved = 0;
 
 	/*
-	 * idle_balance() disregards balance intervals, so we could repeatedly
-	 * reach this code, which would lead to balance_interval skyrocketting
-	 * in a short amount of time. Skip the balance_interval increase logic
-	 * to avoid that.
+	 * newidle_balance() disregards balance intervals, so we could
+	 * repeatedly reach this code, which would lead to balance_interval
+	 * skyrocketting in a short amount of time. Skip the balance_interval
+	 * increase logic to avoid that.
 	 */
 	if (env.idle == CPU_NEWLY_IDLE)
 		goto out;
@@ -9996,7 +9993,7 @@ static inline void nohz_newidle_balance(struct rq *this_rq) { }
  * idle_balance is called by schedule() if this_cpu is about to become
  * idle. Attempts to pull tasks from other CPUs.
  */
-static int idle_balance(struct rq *this_rq, struct rq_flags *rf)
+int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 {
 	unsigned long next_balance = jiffies + HZ;
 	int this_cpu = this_rq->cpu;
@@ -10004,6 +10001,7 @@ static int idle_balance(struct rq *this_rq, struct rq_flags *rf)
 	int pulled_task = 0;
 	u64 curr_cost = 0;
 
+	update_misfit_status(NULL, this_rq);
 	/*
 	 * We must set idle_stamp _before_ calling idle_balance(), such that we
 	 * measure the duration of idle_balance() as idle time.
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index fb01c77c16ff..bfcbcbb25646 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1414,10 +1414,14 @@ static inline void unregister_sched_domain_sysctl(void)
 }
 #endif
 
+extern int newidle_balance(struct rq *this_rq, struct rq_flags *rf);
+
 #else
 
 static inline void sched_ttwu_pending(void) { }
 
+static inline int newidle_balance(struct rq *this_rq, struct rq_flags *rf) { return 0; }
+
 #endif /* CONFIG_SMP */
 
 #include "stats.h"
-- 
2.17.1