[PATCH 1/2] sched: Feature to decide if steal should update CPU capacity

[Shrikanth Hegde]

On 10/28/25 4:12 PM, Srikar Dronamraju wrote:
> At present, scheduler scales CPU capacity for fair tasks based on time
> spent on irq and steal time. If a CPU sees irq or steal time, its
> capacity for fair tasks decreases causing tasks to migrate to other CPU
> that are not affected by irq and steal time. All of this is gated by
> NONTASK_CAPACITY.
> 
> In virtualized setups, a CPU that reports steal time (time taken by the
> hypervisor) can cause tasks to migrate unnecessarily to sibling CPUs that
> appear to be less busy, only for the situation to reverse shortly.
> 
> To mitigate this ping-pong behaviour, this change introduces a new
> scheduler feature flag: ACCT_STEAL which will control whether steal time
> contributes to non-task capacity adjustments (used for fair scheduling).
> 
> Signed-off-by: Srikar Dronamraju <srikar at linux.ibm.com>
> ---
>   include/linux/sched.h   | 1 +
>   kernel/sched/core.c     | 7 +++++--
>   kernel/sched/debug.c    | 8 ++++++++
>   kernel/sched/features.h | 1 +
>   4 files changed, 15 insertions(+), 2 deletions(-)
> 
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index aa9c5be7a632..451931cce5bf 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -2272,5 +2272,6 @@ static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct allo
>   #define alloc_tag_save(_tag)			NULL
>   #define alloc_tag_restore(_tag, _old)		do {} while (0)
>   #endif
> +extern void steal_updates_cpu_capacity(bool enable);
>   
>   #endif
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 81c6df746df1..3a7c4e307371 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -792,8 +792,11 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
>   	rq->clock_task += delta;
>   
>   #ifdef CONFIG_HAVE_SCHED_AVG_IRQ

Curious to know if there are users/distro which have CONFIG_HAVE_SCHED_AVG_IRQ=n

> -	if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
> -		update_irq_load_avg(rq, irq_delta + steal);
> +	if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY)) {
> +		if (steal && sched_feat(ACCT_STEAL))
> +			irq_delta += steal;
> +		update_irq_load_avg(rq, irq_delta);
> +	}
>   #endif
>   	update_rq_clock_pelt(rq, delta);
>   }
> diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
> index 557246880a7e..a0393dd43bb2 100644
> --- a/kernel/sched/debug.c
> +++ b/kernel/sched/debug.c
> @@ -1307,3 +1307,11 @@ void resched_latency_warn(int cpu, u64 latency)
>   	       cpu, latency, cpu_rq(cpu)->ticks_without_resched);
>   	dump_stack();
>   }
> +
> +void steal_updates_cpu_capacity(bool enable)
> +{
> +	if (enable)
> +		sched_feat_set("ACCT_STEAL");
> +	else
> +		sched_feat_set("NO_ACCT_STEAL");
> +}
> diff --git a/kernel/sched/features.h b/kernel/sched/features.h
> index 3c12d9f93331..82d7806ea515 100644
> --- a/kernel/sched/features.h
> +++ b/kernel/sched/features.h
> @@ -121,3 +121,4 @@ SCHED_FEAT(WA_BIAS, true)
>   SCHED_FEAT(UTIL_EST, true)
>   
>   SCHED_FEAT(LATENCY_WARN, false)
> +SCHED_FEAT(ACCT_STEAL, true)