On Wed, Oct 22, 2025 at 02:55:29PM +0200, Thomas Gleixner wrote:
> Use cpumask_or_and_calc_weight() instead of cpumask_or() and
> cpumask_weight() on the result, which walks the same bitmap twice.
On the previous round you've reported 10-20% performance improvement.
Can you post the numbers in the commit message?
> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
> ---
> kernel/sched/core.c | 5 +++--
> 1 file changed, 3 insertions(+), 2 deletions(-)
>
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -10375,6 +10375,7 @@ void call_trace_sched_update_nr_running(
> 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;
> @@ -10385,8 +10386,8 @@ static inline void mm_update_cpus_allowe
> */
> 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_or_and_calc_weight(mm_allowed, mm_allowed, affmsk);
> + WRITE_ONCE(mm->mm_cid.nr_cpus_allowed, weight);
> }
>
> void sched_mm_cid_exit_signals(struct task_struct *t)