[RFC PATCH v3 13/13] sched/fair: Switch nohz.idle_cpus to use sbm
From: K Prateek Nayak
Date: Thu Oct 01 2026 - 15:35:21 EST
From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
With sbm infrastructure in place, convert the global nohz.idle_cpus
cpumask to use sparsebitmap (sbm).
[ prateek: Used sbm_for_each_bit_wrap(), and adapted find_new_ilb() to
the current SMT aware scheme. ]
(Not-yet-)Signed-off-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Signed-off-by: K Prateek Nayak <kprateek.nayak@xxxxxxx>
---
kernel/sched/fair.c | 66 +++++++++++++++++++--------------------------
1 file changed, 27 insertions(+), 39 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a0a659f4c3be..0b1458c4360e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -51,8 +51,9 @@
#include <linux/profile.h>
#include <linux/psi.h>
#include <linux/ratelimit.h>
-#include <linux/task_work.h>
#include <linux/rbtree_augmented.h>
+#include <linux/sbm.h>
+#include <linux/task_work.h>
#include <asm/switch_to.h>
@@ -8210,7 +8211,7 @@ static DEFINE_PER_CPU(cpumask_var_t, should_we_balance_tmpmask);
#ifdef CONFIG_NO_HZ_COMMON
static struct {
- cpumask_var_t idle_cpus_mask;
+ struct sbm *sbm;
int has_blocked_load; /* Idle CPUS has blocked load */
int needs_update; /* Newly idle CPUs need their next_balance collated */
unsigned long next_balance; /* in jiffy units */
@@ -14030,7 +14031,7 @@ static inline int on_null_domain(struct rq *rq)
*/
static inline int find_new_ilb(void)
{
- struct cpumask *ilb_cpus;
+ struct cpumask *skip_cpus;
int ilb_cpu, fallback = -1;
lockdep_assert_irqs_disabled();
@@ -14039,18 +14040,22 @@ static inline int find_new_ilb(void)
* Reuse the per-CPU select_rq_mask, which is protected from concurrent
* use on this CPU by having interrupts disabled.
*/
- ilb_cpus = this_cpu_cpumask_var_ptr(select_rq_mask);
- cpumask_and(ilb_cpus, nohz.idle_cpus_mask,
- housekeeping_cpumask(HK_TYPE_KERNEL_NOISE));
+ skip_cpus = this_cpu_cpumask_var_ptr(select_rq_mask);
+ cpumask_clear(skip_cpus);
+
+ sbm_for_each_set_bit(nohz.sbm, idx) {
+ ilb_cpu = sbm_idx_to_cpu(idx);
+
+ if (cpumask_test_cpu(ilb_cpu, skip_cpus))
+ continue;
- for_each_cpu(ilb_cpu, ilb_cpus) {
if (!idle_cpu(ilb_cpu)) {
/*
* Once an idle fallback exists, a busy CPU proves that
* this core cannot be fully idle. Skip its siblings.
*/
if (sched_smt_active() && fallback >= 0)
- cpumask_andnot(ilb_cpus, ilb_cpus, cpu_smt_mask(ilb_cpu));
+ cpumask_or(skip_cpus, skip_cpus, cpu_smt_mask(ilb_cpu));
continue;
}
@@ -14069,8 +14074,7 @@ static inline int find_new_ilb(void)
* The core is not idle, so there is no need to check
* any of its other SMT siblings.
*/
- cpumask_andnot(ilb_cpus, ilb_cpus,
- cpu_smt_mask(ilb_cpu));
+ cpumask_or(skip_cpus, skip_cpus, cpu_smt_mask(ilb_cpu));
continue;
}
@@ -14134,7 +14138,7 @@ 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))
@@ -14162,11 +14166,7 @@ static void nohz_balancer_kick(struct rq *rq)
if (time_before(now, nohz.next_balance))
goto out;
- /*
- * None are in tickless mode and hence no need for NOHZ idle load
- * balancing
- */
- if (unlikely(cpumask_empty(nohz.idle_cpus_mask)))
+ if (unlikely(sbm_empty(nohz.sbm)))
return;
if (rq->nr_running >= 2) {
@@ -14186,24 +14186,6 @@ static void nohz_balancer_kick(struct rq *rq)
}
}
- sd = rcu_dereference_all(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 out;
- }
- }
- }
-
sd = rcu_dereference_all(per_cpu(sd_asym_cpucapacity, cpu));
if (sd) {
/*
@@ -14270,7 +14252,8 @@ void nohz_balance_exit_idle(struct rq *rq)
return;
rq->nohz_tick_stopped = 0;
- cpumask_clear_cpu(rq->cpu, nohz.idle_cpus_mask);
+ if (cpumask_test_cpu(rq->cpu, housekeeping_cpumask(HK_TYPE_KERNEL_NOISE)))
+ sbm_cpu_clear(nohz.sbm, rq->cpu);
set_cpu_sd_state_busy(rq->cpu);
}
@@ -14324,7 +14307,8 @@ void nohz_balance_enter_idle(int cpu)
rq->nohz_tick_stopped = 1;
- cpumask_set_cpu(cpu, nohz.idle_cpus_mask);
+ if (cpumask_test_cpu(rq->cpu, housekeeping_cpumask(HK_TYPE_KERNEL_NOISE)))
+ sbm_cpu_set(nohz.sbm, rq->cpu);
/*
* Ensures that if nohz_idle_balance() fails to observe our
@@ -14351,7 +14335,7 @@ static bool update_nohz_stats(struct rq *rq)
if (!rq->has_blocked_load)
return false;
- if (!cpumask_test_cpu(cpu, nohz.idle_cpus_mask))
+ if (!sbm_cpu_test(nohz.sbm, cpu))
return false;
if (!time_after(jiffies, READ_ONCE(rq->last_blocked_load_update_tick)))
@@ -14377,6 +14361,7 @@ static void _nohz_idle_balance(struct rq *this_rq, unsigned int flags)
int this_cpu = this_rq->cpu;
int balance_cpu;
struct rq *rq;
+ int start;
WARN_ON_ONCE((flags & NOHZ_KICK_MASK) == NOHZ_BALANCE_KICK);
@@ -14405,7 +14390,10 @@ static void _nohz_idle_balance(struct rq *this_rq, unsigned int flags)
* Start with the next CPU after this_cpu so we will end with this_cpu and let a
* chance for other idle cpu to pull load.
*/
- for_each_cpu_wrap(balance_cpu, nohz.idle_cpus_mask, this_cpu+1) {
+ start = sbm_cpu_to_idx(cpumask_next_wrap(this_cpu, cpu_online_mask));
+ sbm_for_each_set_bit_wrap(nohz.sbm, idx, start) {
+ balance_cpu = sbm_idx_to_cpu(idx);
+
if (!idle_cpu(balance_cpu))
continue;
@@ -15648,7 +15636,7 @@ void show_numa_stats(struct task_struct *p, struct seq_file *m)
__init void init_sched_fair_class_smp(void)
{
#ifdef CONFIG_NO_HZ_COMMON
- zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT);
+ nohz.sbm = sbm_alloc();
#endif
}
--
2.34.1