Re: [PATCH v3 17/20] sched/core: Introduce default arch handling code for inc/dec preferred CPUs

[Ilya Leoshkevich]

On 5/14/26 17:22, Shrikanth Hegde wrote:
> Define default handlers for high/low steal time. If arch has better
> decision logic, may override the default implementation.
>
> - If the steal time higher than threshold, reduce the number of preferred
>    CPUs by 1 core. The last core in the intersection of online and
>    preferred CPUs will be marked as non-preferred.
>    Ensure at least one core is left as preferred always.
>
> - If the steal time lower than threshold, increase the number of preferred
>    CPUs by 1 core. First online core which is not in cpu_preferred_mask will
>    be marked as preferred.
>    If all cores are already set to preferred, bail out.
>
> Increase/Decrease may need to modify the splicing across NUMA nodes. It is
> being kept simple for now.
>
> Signed-off-by: Shrikanth Hegde <sshegde@xxxxxxxxxxxxx>
> ---
>   include/linux/sched.h |  2 ++
>   kernel/sched/core.c   | 58 +++++++++++++++++++++++++++++++++++++++++++
>   2 files changed, 60 insertions(+)

[...]

> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index a3f65e9c7d30..195e3648b1b5 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -11368,6 +11368,64 @@ void sched_init_steal_monitor(void)
>   	steal_mon.sampling_period_ms  = 1000;		/* once per second */
>   }
>   
> +/*
> + * Default implementation of decrementing the preferred CPUs based on steal
> + * time. This is simple logic and decrease the preferred CPUs by 1 core.
> + * It takes out the last core in the online & preferred.
> + *
> + * Ensure at least one housekeeping core is always kept as preferred
> + *
> + * Could be overwritten by arch specific handling.
> + */
> +#ifndef arch_dec_preferred_cpus
> +void arch_dec_preferred_cpus(struct steal_monitor_t *sm, u64 steal_ratio)
> +{
> +	int last_cpu, tmp_cpu;
> +	int this_cpu = raw_smp_processor_id();
> +
> +	cpumask_and(sm->tmp_mask, cpu_online_mask, cpu_preferred_mask);

Since preferred is always a subset of online, do we even need this?
Dropping tmp_mask will also make the error handling concern I posted
earlier go away.

[...]