linux-kernel - [RFC PATCH 10/19] sched/topology: Introduce "idle_cpus

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: <20250904041516.3046-11-kprateek.nayak@amd.com>
Date: Thu, 4 Sep 2025 04:15:06 +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 10/19] sched/topology: Introduce "idle_cpus_mask" in sd->shared

Introduce "idle_cpus_mask" to track idle CPUs within the sd_nohz
domains. This mask will eventually replace the need for the global
"nohz.idle_cpus" mask for nohz idle balancing.

Convert cpu_set_sd_state_*() to set / clear the CPU from the mask when
transitioning to / out of nohz idle state.

Reviewed-by: Gautham R. Shenoy <gautham.shenoy@....com>
Signed-off-by: K Prateek Nayak <kprateek.nayak@....com>
---
 include/linux/sched/topology.h |  1 +
 kernel/sched/fair.c            |  2 ++
 kernel/sched/topology.c        | 48 +++++++++++++++++++++++++++++++---
 3 files changed, 47 insertions(+), 4 deletions(-)

diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 2f0d8ecea427..6db3448e2f00 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -67,6 +67,7 @@ struct sched_domain_shared {
 	atomic_t	ref;
 #ifdef CONFIG_NO_HZ_COMMON
 	atomic_t	nr_idle_cpus;
+	struct cpumask	*idle_cpus_mask;
 #endif
 	int		has_idle_cores;
 	int		nr_idle_scan;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 624b3753c818..c8226520758d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -12458,6 +12458,7 @@ static void set_cpu_sd_state_busy(int cpu)
 	if (!xchg(&sd->nohz_idle, 0))
 		return;
 
+	cpumask_clear_cpu(cpu, sd->shared->idle_cpus_mask);
 	atomic_dec(&sd->shared->nr_idle_cpus);
 }
 
@@ -12488,6 +12489,7 @@ static void set_cpu_sd_state_idle(int cpu)
 	if (xchg(&sd->nohz_idle, 1))
 		return;
 
+	cpumask_set_cpu(cpu, sd->shared->idle_cpus_mask);
 	atomic_inc(&sd->shared->nr_idle_cpus);
 }
 
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index f230892528c7..c2832445c578 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -468,6 +468,24 @@ struct s_data {
 
 DEFINE_PER_CPU(struct sched_domain __rcu *, sd_nohz);
 
+static int __sds_nohz_idle_alloc(struct sched_domain_shared *sds, int node)
+{
+	sds->idle_cpus_mask = kzalloc_node(cpumask_size(), GFP_KERNEL, node);
+
+	if (!sds->idle_cpus_mask)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void __sds_nohz_idle_free(struct sched_domain_shared *sds)
+{
+	if (!sds)
+		return;
+
+	kfree(sds->idle_cpus_mask);
+}
+
 static int __fallback_sds_alloc(struct s_data *d, unsigned long *visited_nodes)
 {
 	int j;
@@ -490,6 +508,9 @@ static int __fallback_sds_alloc(struct s_data *d, unsigned long *visited_nodes)
 			return -ENOMEM;
 
 		d->fallback_nohz_sds[j] = sds;
+
+		if (__sds_nohz_idle_alloc(sds, j))
+			return -ENOMEM;
 	}
 
 	return 0;
@@ -502,8 +523,10 @@ static void __fallback_sds_free(struct s_data *d)
 	if (!d->fallback_nohz_sds)
 		return;
 
-	for (j = 0; j < nr_node_ids; ++j)
+	for (j = 0; j < nr_node_ids; ++j) {
+		__sds_nohz_idle_free(d->fallback_nohz_sds[j]);
 		kfree(d->fallback_nohz_sds[j]);
+	}
 
 	kfree(d->fallback_nohz_sds);
 	d->fallback_nohz_sds = NULL;
@@ -553,6 +576,13 @@ static void update_nohz_domain(int cpu)
 
 #else /* !CONFIG_NO_HZ_COMMON */
 
+static int __sds_nohz_idle_alloc(struct sched_domain_shared *sds, int node)
+{
+	return 0;
+}
+
+static void __sds_nohz_idle_free(struct sched_domain_shared *sds) { }
+
 static inline int __fallback_sds_alloc(struct s_data *d, unsigned long *visited_nodes)
 {
 	return 0;
@@ -740,8 +770,10 @@ static void destroy_sched_domain(struct sched_domain *sd)
 	 */
 	free_sched_groups(sd->groups, 1);
 
-	if (sd->shared && atomic_dec_and_test(&sd->shared->ref))
+	if (sd->shared && atomic_dec_and_test(&sd->shared->ref)) {
+		__sds_nohz_idle_free(sd->shared);
 		kfree(sd->shared);
+	}
 	kfree(sd);
 }
 
@@ -2524,6 +2556,9 @@ static int __sds_alloc(struct s_data *d, const struct cpumask *cpu_map)
 
 		bitmap_set(visited_nodes, cpu_to_node(j), 1);
 		*per_cpu_ptr(d->sds, j) = sds;
+
+		if (__sds_nohz_idle_alloc(sds, cpu_to_node(j)))
+			return -ENOMEM;
 	}
 
 	if (__fallback_sds_alloc(d, visited_nodes))
@@ -2539,8 +2574,13 @@ static void __sds_free(struct s_data *d, const struct cpumask *cpu_map)
 	if (!d->sds)
 		return;
 
-	for_each_cpu(j, cpu_map)
-		kfree(*per_cpu_ptr(d->sds, j));
+	for_each_cpu(j, cpu_map) {
+		struct sched_domain_shared *sds;
+
+		sds = *per_cpu_ptr(d->sds, j);
+		__sds_nohz_idle_free(sds);
+		kfree(sds);
+	}
 
 	__fallback_sds_free(d);
 
-- 
2.34.1