On 26/02/2021 17:40, Srikar Dronamraju wrote:
[...]
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 8a8bd7b13634..d49bfcdc4a19 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -5869,6 +5869,36 @@ wake_affine_weight(struct sched_domain *sd, struct
> task_struct *p,
> return this_eff_load < prev_eff_load ? this_cpu : nr_cpumask_bits;
> }
>
> +static int prefer_idler_llc(int this_cpu, int prev_cpu, int sync)
> +{
> + struct sched_domain_shared *tsds, *psds;
> + int pnr_busy, pllc_size, tnr_busy, tllc_size, diff;
> +
> + tsds = rcu_dereference(per_cpu(sd_llc_shared, this_cpu));
> + tnr_busy = atomic_read(&tsds->nr_busy_cpus);
> + tllc_size = per_cpu(sd_llc_size, this_cpu);
> +
> + psds = rcu_dereference(per_cpu(sd_llc_shared, prev_cpu));
> + pnr_busy = atomic_read(&psds->nr_busy_cpus);
> + pllc_size = per_cpu(sd_llc_size, prev_cpu);
> +
> + /* No need to compare, if both LLCs are fully loaded */
> + if (pnr_busy == pllc_size && tnr_busy == pllc_size)
^
shouldn't this be tllc_size ?
> + return nr_cpumask_bits;
> +
> + if (sched_feat(WA_WAKER) && tnr_busy < tllc_size)
> + return this_cpu;
> +
> + /* For better wakeup latency, prefer idler LLC to cache affinity */
> + diff = tnr_busy * pllc_size - sync - pnr_busy * tllc_size;
> + if (!diff)
> + return nr_cpumask_bits;
> + if (diff < 0)
> + return this_cpu;
> +
> + return prev_cpu;
> +}
> +
