From: Thomas Gleixner Date: Wed, 19 Nov 2025 17:26:59 +0000 (+0100) Subject: sched/mmcid: Use cpumask_weighted_or() X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=79c11fb3da8581a2f222b290ce62a153ab1108fc;p=thirdparty%2Fkernel%2Flinux.git sched/mmcid: Use cpumask_weighted_or() Use cpumask_weighted_or() instead of cpumask_or() and cpumask_weight() on the result, which walks the same bitmap twice. Results in 10-20% less cycles, which reduces the runqueue lock hold time. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Mathieu Desnoyers Acked-by: Yury Norov (NVIDIA) Link: https://patch.msgid.link/20251119172549.511736272@linutronix.de --- diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2ea77e72f7c67..f6bbfa1f5c15a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -10377,6 +10377,7 @@ void call_trace_sched_update_nr_running(struct rq *rq, int count) static inline void mm_update_cpus_allowed(struct mm_struct *mm, const struct cpumask *affmsk) { struct cpumask *mm_allowed; + unsigned int weight; if (!mm) return; @@ -10387,8 +10388,8 @@ static inline void mm_update_cpus_allowed(struct mm_struct *mm, const struct cpu */ guard(raw_spinlock)(&mm->mm_cid.lock); mm_allowed = mm_cpus_allowed(mm); - cpumask_or(mm_allowed, mm_allowed, affmsk); - WRITE_ONCE(mm->mm_cid.nr_cpus_allowed, cpumask_weight(mm_allowed)); + weight = cpumask_weighted_or(mm_allowed, mm_allowed, affmsk); + WRITE_ONCE(mm->mm_cid.nr_cpus_allowed, weight); } void sched_mm_cid_exit_signals(struct task_struct *t)