[RFC][PATCH 6/7] sched: Add rq::ttwu_pending

From: Peter Zijlstra <peterz@infradead.org>
To: tglx@linutronix.de, frederic@kernel.org
Cc: linux-kernel@vger.kernel.org, x86@kernel.org, cai@lca.pw,
	mgorman@techsingularity.net, peterz@infradead.org
Subject: [RFC][PATCH 6/7] sched: Add rq::ttwu_pending
Date: Tue, 26 May 2020 18:11:03 +0200	[thread overview]
Message-ID: <20200526161908.070399698@infradead.org> (raw)
In-Reply-To: 20200526161057.531933155@infradead.org

In preparation of removing rq->wake_list, replace the
!list_empty(rq->wake_list) with rq->ttwu_pending. This is not fully
equivalent as this new variable is racy.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/sched/core.c  |   13 +++++++++++--
 kernel/sched/debug.c |    1 -
 kernel/sched/fair.c  |    2 +-
 kernel/sched/sched.h |    4 +++-
 4 files changed, 15 insertions(+), 5 deletions(-)

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2275,13 +2275,21 @@ static int ttwu_remote(struct task_struc
 void sched_ttwu_pending(void)
 {
 	struct rq *rq = this_rq();
-	struct llist_node *llist = llist_del_all(&rq->wake_list);
+	struct llist_node *llist;
 	struct task_struct *p, *t;
 	struct rq_flags rf;
 
+	llist = llist_del_all(&rq->wake_list);
 	if (!llist)
 		return;
 
+	/*
+	 * rq::ttwu_pending racy indication of out-standing wakeups.
+	 * Races such that false-negatives are possible, since they
+	 * are shorter lived that false-positives would be.
+	 */
+	WRITE_ONCE(rq->ttwu_pending, 0);
+
 	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 
@@ -2312,6 +2320,7 @@ static void ttwu_queue_remote(struct tas
 
 	p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);
 
+	WRITE_ONCE(rq->ttwu_pending, 1);
 	if (llist_add(&p->wake_entry, &rq->wake_list)) {
 		if (!set_nr_if_polling(rq->idle))
 			smp_call_function_single_async(cpu, &rq->wake_csd);
@@ -4668,7 +4677,7 @@ int idle_cpu(int cpu)
 		return 0;
 
 #ifdef CONFIG_SMP
-	if (!llist_empty(&rq->wake_list))
+	if (rq->ttwu_pending)
 		return 0;
 #endif
 
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -638,7 +638,6 @@ do {									\
 
 	P(nr_running);
 	P(nr_switches);
-	P(nr_load_updates);
 	P(nr_uninterruptible);
 	PN(next_balance);
 	SEQ_printf(m, "  .%-30s: %ld\n", "curr->pid", (long)(task_pid_nr(rq->curr)));
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8590,7 +8590,7 @@ static int idle_cpu_without(int cpu, str
 	 */
 
 #ifdef CONFIG_SMP
-	if (!llist_empty(&rq->wake_list))
+	if (rq->ttwu_pending)
 		return 0;
 #endif
 
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -895,7 +895,9 @@ struct rq {
 	atomic_t		nohz_flags;
 #endif /* CONFIG_NO_HZ_COMMON */
 
-	unsigned long		nr_load_updates;
+#ifdef CONFIG_SMP
+	unsigned int		ttwu_pending;
+#endif
 	u64			nr_switches;
 
 #ifdef CONFIG_UCLAMP_TASK


