[PATCH 08/17] sched/core: Implement CPU soft offline/online

[Peter Zijlstra]

On Thu, Dec 04, 2025 at 11:23:56PM +0530, Srikar Dronamraju wrote:

> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 89efff1e1ead..f66fd1e925b0 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -8177,13 +8177,16 @@ static void balance_push(struct rq *rq)
>  	 * Only active while going offline and when invoked on the outgoing
>  	 * CPU.
>  	 */
> -	if (!cpu_dying(rq->cpu) || rq != this_rq())
> +	if (cpu_active(rq->cpu) || rq != this_rq())
>  		return;
>  
>  	/*
> -	 * Ensure the thing is persistent until balance_push_set(.on = false);
> +	 * Unless soft-offline, Ensure the thing is persistent until
> +	 * balance_push_set(.on = false); In case of soft-offline, just
> +	 * enough to push current non-pinned tasks out.
>  	 */
> -	rq->balance_callback = &balance_push_callback;
> +	if (cpu_dying(rq->cpu) || rq->nr_running)
> +		rq->balance_callback = &balance_push_callback;
>  
>  	/*
>  	 * Both the cpu-hotplug and stop task are in this case and are
> @@ -8392,6 +8395,8 @@ static inline void sched_smt_present_dec(int cpu)
>  #endif
>  }
>  
> +static struct cpumask cpu_softoffline_mask;
> +
>  int sched_cpu_activate(unsigned int cpu)
>  {
>  	struct rq *rq = cpu_rq(cpu);
> @@ -8411,7 +8416,10 @@ int sched_cpu_activate(unsigned int cpu)
>  	if (sched_smp_initialized) {
>  		sched_update_numa(cpu, true);
>  		sched_domains_numa_masks_set(cpu);
> -		cpuset_cpu_active();
> +
> +		/* For CPU soft-offline, dont need to rebuild sched-domains */
> +		if (!cpumask_test_cpu(cpu, &cpu_softoffline_mask))
> +			cpuset_cpu_active();
>  	}
>  
>  	scx_rq_activate(rq);
> @@ -8485,7 +8493,11 @@ int sched_cpu_deactivate(unsigned int cpu)
>  		return 0;
>  
>  	sched_update_numa(cpu, false);
> -	cpuset_cpu_inactive(cpu);
> +
> +	/* For CPU soft-offline, dont need to rebuild sched-domains */
> +	if (!cpumask_test_cpu(cpu, &cpu_softoffline_mask))
> +		cpuset_cpu_inactive(cpu);
> +
>  	sched_domains_numa_masks_clear(cpu);
>  	return 0;
>  }
> @@ -10928,3 +10940,25 @@ void sched_enq_and_set_task(struct sched_enq_and_set_ctx *ctx)
>  		set_next_task(rq, ctx->p);
>  }
>  #endif /* CONFIG_SCHED_CLASS_EXT */
> +
> +void set_cpu_softoffline(int cpu, bool soft_offline)
> +{
> +	struct sched_domain *sd;
> +
> +	if (!cpu_online(cpu))
> +		return;
> +
> +	cpumask_set_cpu(cpu, &cpu_softoffline_mask);
> +
> +	rcu_read_lock();
> +	for_each_domain(cpu, sd)
> +		update_group_capacity(sd, cpu);
> +	rcu_read_unlock();
> +
> +	if (soft_offline)
> +		sched_cpu_deactivate(cpu);
> +	else
> +		sched_cpu_activate(cpu);
> +
> +	cpumask_clear_cpu(cpu, &cpu_softoffline_mask);
> +}

What happens if you then offline one of these softoffline CPUs? Doesn't
that do sched_cpu_deactivate() again?

Also, the way this seems to use softoffline_mask is as a hidden argument
to sched_cpu_{de,}activate() instead of as an actual mask.

Moreover, there does not seem to be any sort of serialization vs
concurrent set_cpu_softoffline() callers. At the very least
update_group_capacity() would end up with indeterminate results.

This all doesn't look 'robust'.