linux-kernel - [RFC PATCH 13/22] sched/fair: Correct the throttle status supplied to pick

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20250220093257.9380-14-kprateek.nayak@amd.com>
Date: Thu, 20 Feb 2025 09:32:48 +0000
From: K Prateek Nayak <kprateek.nayak@....com>
To: Peter Zijlstra <peterz@...radead.org>, Ingo Molnar <mingo@...hat.com>,
	Juri Lelli <juri.lelli@...hat.com>, Vincent Guittot
	<vincent.guittot@...aro.org>, Valentin Schneider <vschneid@...hat.com>, "Ben
 Segall" <bsegall@...gle.com>, Thomas Gleixner <tglx@...utronix.de>, "Andy
 Lutomirski" <luto@...nel.org>, <linux-kernel@...r.kernel.org>
CC: Dietmar Eggemann <dietmar.eggemann@....com>, Steven Rostedt
	<rostedt@...dmis.org>, Mel Gorman <mgorman@...e.de>, "Sebastian Andrzej
 Siewior" <bigeasy@...utronix.de>, Clark Williams <clrkwllms@...nel.org>,
	<linux-rt-devel@...ts.linux.dev>, Tejun Heo <tj@...nel.org>, "Frederic
 Weisbecker" <frederic@...nel.org>, Barret Rhoden <brho@...gle.com>, "Petr
 Mladek" <pmladek@...e.com>, Josh Don <joshdon@...gle.com>, Qais Yousef
	<qyousef@...alina.io>, "Paul E. McKenney" <paulmck@...nel.org>, David Vernet
	<dvernet@...a.com>, K Prateek Nayak <kprateek.nayak@....com>, "Gautham R.
 Shenoy" <gautham.shenoy@....com>, Swapnil Sapkal <swapnil.sapkal@....com>
Subject: [RFC PATCH 13/22] sched/fair: Correct the throttle status supplied to pick_eevdf()

A partially throttled hierarchy does not set the hierarchical indicator.
Find the throttled status of the hierarchy when traversing down the tree
in pick_task_fair() and pass the correct throttle status to
pick_eevdf().

Signed-off-by: K Prateek Nayak <kprateek.nayak@....com>
---
 kernel/sched/fair.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8824e89a3ede..1d871509b246 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5618,7 +5618,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags);
  * 4) do not run the "skip" process, if something else is available
  */
 static struct sched_entity *
-pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq)
+pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq, bool h_throttled)
 {
 	struct sched_entity *se;
 
@@ -5626,13 +5626,13 @@ pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq)
 	 * Picking the ->next buddy will affect latency but not fairness.
 	 */
 	if (sched_feat(PICK_BUDDY) && cfs_rq->next &&
-	    pick_entity(cfs_rq, cfs_rq->next, throttled_hierarchy(cfs_rq))) {
+	    pick_entity(cfs_rq, cfs_rq->next, h_throttled)) {
 		/* ->next will never be delayed */
 		SCHED_WARN_ON(cfs_rq->next->sched_delayed);
 		return cfs_rq->next;
 	}
 
-	se = pick_eevdf(cfs_rq, throttled_hierarchy(cfs_rq));
+	se = pick_eevdf(cfs_rq, h_throttled);
 	if (se->sched_delayed) {
 		dequeue_entities(rq, se, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
 		/*
@@ -9187,6 +9187,7 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
 	struct sched_entity *se = &donor->se, *pse = &p->se;
 	struct cfs_rq *cfs_rq = task_cfs_rq(donor);
 	int cse_is_idle, pse_is_idle;
+	bool h_throttled = false;
 
 	if (unlikely(se == pse))
 		return;
@@ -9260,10 +9261,16 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
 	if (do_preempt_short(cfs_rq, pse, se))
 		cancel_protect_slice(se);
 
+	for_each_sched_entity(se) {
+		h_throttled = h_throttled || cfs_rq_throttled(cfs_rq_of(se));
+		if (h_throttled)
+			break;
+	}
+
 	/*
 	 * If @p has become the most eligible task, force preemption.
 	 */
-	if (pick_eevdf(cfs_rq, throttled_hierarchy(cfs_rq)) == pse)
+	if (pick_eevdf(cfs_rq, h_throttled) == pse)
 		goto preempt;
 
 	return;
@@ -9276,12 +9283,15 @@ static struct task_struct *pick_task_fair(struct rq *rq)
 {
 	struct sched_entity *se;
 	struct cfs_rq *cfs_rq;
+	bool h_throttled;
 
 again:
 	cfs_rq = &rq->cfs;
 	if (!cfs_rq->nr_queued)
 		return NULL;
 
+	h_throttled = false;
+
 	do {
 		/* Might not have done put_prev_entity() */
 		if (cfs_rq->curr && cfs_rq->curr->on_rq)
@@ -9290,7 +9300,8 @@ static struct task_struct *pick_task_fair(struct rq *rq)
 		if (unlikely(check_cfs_rq_runtime(cfs_rq)))
 			goto again;
 
-		se = pick_next_entity(rq, cfs_rq);
+		h_throttled = h_throttled || cfs_rq_throttled(cfs_rq);
+		se = pick_next_entity(rq, cfs_rq, h_throttled);
 		if (!se)
 			goto again;
 		cfs_rq = group_cfs_rq(se);
-- 
2.43.0