linux-kernel - [RFC PATCH 15/19] sched/fair: Introduce sched_asym_prefer

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: <20250904041516.3046-16-kprateek.nayak@amd.com>
Date: Thu, 4 Sep 2025 04:15:11 +0000
From: K Prateek Nayak <kprateek.nayak@....com>
To: Ingo Molnar <mingo@...hat.com>, Peter Zijlstra <peterz@...radead.org>,
	Juri Lelli <juri.lelli@...hat.com>, Vincent Guittot
	<vincent.guittot@...aro.org>, Anna-Maria Behnsen <anna-maria@...utronix.de>,
	Frederic Weisbecker <frederic@...nel.org>, Thomas Gleixner
	<tglx@...utronix.de>, <linux-kernel@...r.kernel.org>
CC: Dietmar Eggemann <dietmar.eggemann@....com>, Steven Rostedt
	<rostedt@...dmis.org>, Ben Segall <bsegall@...gle.com>, Mel Gorman
	<mgorman@...e.de>, Valentin Schneider <vschneid@...hat.com>, K Prateek Nayak
	<kprateek.nayak@....com>, "Gautham R. Shenoy" <gautham.shenoy@....com>,
	Swapnil Sapkal <swapnil.sapkal@....com>
Subject: [RFC PATCH 15/19] sched/fair: Introduce sched_asym_prefer_idle() for ILB kick

nohz_balancer_kick() currently depends on "nohz.idle_cpus_maks" to kick
off an idle balance if it finds a more preferred CPU in nohz idle state.

Move the detection logic into sched_asym_prefer_idle() and use the
distributed "sd->shared" based nohz tracking to kick ILB if a more
preferred CPU is found idle.

Signed-off-by: K Prateek Nayak <kprateek.nayak@....com>
---
 kernel/sched/fair.c | 70 ++++++++++++++++++++++++++++++++++-----------
 1 file changed, 54 insertions(+), 16 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5e7198078d19..d309cb73d428 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -12289,6 +12289,56 @@ static inline int find_new_ilb(void)
 	return -1;
 }
 
+static inline int
+__asym_prefer_idle(int cpu, struct sched_domain *sd_asym, struct cpumask *idle_mask)
+{
+	int i;
+
+	for_each_cpu_and(i, idle_mask, sched_domain_span(sd_asym)) {
+		if (sched_asym(sd_asym, i, cpu))
+			return 1;
+	}
+
+	return 0;
+}
+
+static int sched_asym_prefer_idle(int cpu, struct sched_domain *sd_asym)
+{
+	struct sched_domain *sd = rcu_dereference(per_cpu(sd_nohz, cpu));
+	struct sched_domain_shared *sds;
+
+	if (!sd)
+		return 0;
+
+	/*
+	 * If sd_asym_packing is a subset of sd_llc, don't traverse
+	 * the nohz_shared_list and directly use the mask from
+	 * sd_nohz->shared to find it a preferred CPU is idling.
+	 */
+	if (sd_asym->flags & SD_SHARE_LLC) {
+		sds = sd->shared;
+
+		if (sds &&
+		    atomic_read(&sds->nr_idle_cpus) &&
+		    __asym_prefer_idle(cpu, sd_asym, sds->idle_cpus_mask))
+			return 1;
+
+		return 0;
+	}
+
+	/* Try the entire list id sd_asym_packing is larger than sd_nohz. */
+	list_for_each_entry_rcu(sds, &nohz_shared_list, nohz_list_node) {
+		/* No idle CPUs in this domain */
+		if (!atomic_read(&sds->nr_idle_cpus))
+			continue;
+
+		if (__asym_prefer_idle(cpu, sd_asym, sds->idle_cpus_mask))
+			return 1;
+	}
+
+	return 0;
+}
+
 /*
  * Kick a CPU to do the NOHZ balancing, if it is time for it, via a cross-CPU
  * SMP function call (IPI).
@@ -12343,7 +12393,7 @@ static void nohz_balancer_kick(struct rq *rq)
 	unsigned long now = jiffies;
 	struct sched_domain_shared *sds;
 	struct sched_domain *sd;
-	int nr_busy, i, cpu = rq->cpu;
+	int nr_busy, cpu = rq->cpu;
 	unsigned int flags = 0;
 
 	if (unlikely(rq->idle_balance))
@@ -12389,21 +12439,9 @@ static void nohz_balancer_kick(struct rq *rq)
 	}
 
 	sd = rcu_dereference(per_cpu(sd_asym_packing, cpu));
-	if (sd) {
-		/*
-		 * When ASYM_PACKING; see if there's a more preferred CPU
-		 * currently idle; in which case, kick the ILB to move tasks
-		 * around.
-		 *
-		 * When balancing between cores, all the SMT siblings of the
-		 * preferred CPU must be idle.
-		 */
-		for_each_cpu_and(i, sched_domain_span(sd), nohz.idle_cpus_mask) {
-			if (sched_asym(sd, i, cpu)) {
-				flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
-				goto unlock;
-			}
-		}
+	if (sd && sched_asym_prefer_idle(cpu, sd)) {
+		flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
+		goto unlock;
 	}
 
 	sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, cpu));
-- 
2.34.1