From: Andrea Righi <arighi@nvidia.com>
Date: Sat, 9 May 2026 18:07:25 +0000 (+0200)
Subject: sched/fair: Drop redundant RCU read lock in NOHZ kick path
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=c9d93a73ce871ca32caf9308562501290b64b955;p=thirdparty%2Fkernel%2Flinux.git

sched/fair: Drop redundant RCU read lock in NOHZ kick path

nohz_balancer_kick() is reached from sched_balance_trigger(), which is
called from sched_tick(). sched_tick() runs with IRQs disabled, so the
additional rcu_read_lock/unlock() used around sched_domain accesses in
this path is redundant. Rely on the existing IRQ-disabled context (and
the rcu_dereference_all() checking) instead.

The same applies to set_cpu_sd_state_idle(), called from the idle entry
path with IRQs disabled, and to set_cpu_sd_state_busy(), reachable via
nohz_balance_exit_idle() from two contexts: nohz_balancer_kick() (IRQs
disabled, as above) and sched_cpu_deactivate() (the CPUHP_AP_ACTIVE
teardown, which runs under cpus_write_lock(), so it cannot race with
sched-domain rebuilds). In both cases the rcu_dereference_all()
validation is sufficient.

No functional change intended.

Suggested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: K Prateek Nayak <kprateek.nayak@amd.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://patch.msgid.link/20260509180955.1840064-2-arighi@nvidia.com
---

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index bcaadddf86240..03f63b094ff98 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -12715,8 +12715,6 @@ static void nohz_balancer_kick(struct rq *rq)
 		goto out;
 	}
 
-	rcu_read_lock();
-
 	sd = rcu_dereference_all(rq->sd);
 	if (sd) {
 		/*
@@ -12724,8 +12722,8 @@ static void nohz_balancer_kick(struct rq *rq)
 		 * capacity, kick the ILB to see if there's a better CPU to run on:
 		 */
 		if (rq->cfs.h_nr_runnable >= 1 && check_cpu_capacity(rq, sd)) {
-			flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
-			goto unlock;
+			flags |= NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
+			goto out;
 		}
 	}
 
@@ -12741,8 +12739,8 @@ static void nohz_balancer_kick(struct rq *rq)
 		 */
 		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;
+				flags |= NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
+				goto out;
 			}
 		}
 	}
@@ -12753,10 +12751,8 @@ static void nohz_balancer_kick(struct rq *rq)
 		 * When ASYM_CPUCAPACITY; see if there's a higher capacity CPU
 		 * to run the misfit task on.
 		 */
-		if (check_misfit_status(rq)) {
-			flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
-			goto unlock;
-		}
+		if (check_misfit_status(rq))
+			flags |= NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
 
 		/*
 		 * For asymmetric systems, we do not want to nicely balance
@@ -12765,7 +12761,7 @@ static void nohz_balancer_kick(struct rq *rq)
 		 *
 		 * Skip the LLC logic because it's not relevant in that case.
 		 */
-		goto unlock;
+		goto out;
 	}
 
 	sds = rcu_dereference_all(per_cpu(sd_llc_shared, cpu));
@@ -12780,13 +12776,9 @@ static void nohz_balancer_kick(struct rq *rq)
 		 * like this LLC domain has tasks we could move.
 		 */
 		nr_busy = atomic_read(&sds->nr_busy_cpus);
-		if (nr_busy > 1) {
-			flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
-			goto unlock;
-		}
+		if (nr_busy > 1)
+			flags |= NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
 	}
-unlock:
-	rcu_read_unlock();
 out:
 	if (READ_ONCE(nohz.needs_update))
 		flags |= NOHZ_NEXT_KICK;
@@ -12798,17 +12790,13 @@ out:
 static void set_cpu_sd_state_busy(int cpu)
 {
 	struct sched_domain *sd;
-
-	rcu_read_lock();
 	sd = rcu_dereference_all(per_cpu(sd_llc, cpu));
 
 	if (!sd || !sd->nohz_idle)
-		goto unlock;
+		return;
 	sd->nohz_idle = 0;
 
 	atomic_inc(&sd->shared->nr_busy_cpus);
-unlock:
-	rcu_read_unlock();
 }
 
 void nohz_balance_exit_idle(struct rq *rq)
@@ -12827,17 +12815,13 @@ void nohz_balance_exit_idle(struct rq *rq)
 static void set_cpu_sd_state_idle(int cpu)
 {
 	struct sched_domain *sd;
-
-	rcu_read_lock();
 	sd = rcu_dereference_all(per_cpu(sd_llc, cpu));
 
 	if (!sd || sd->nohz_idle)
-		goto unlock;
+		return;
 	sd->nohz_idle = 1;
 
 	atomic_dec(&sd->shared->nr_busy_cpus);
-unlock:
-	rcu_read_unlock();
 }
 
 /*