On Sat, Jun 08, 2019 at 01:08:52PM +0200, Heiko Carstens wrote:
> --- a/arch/s390/kernel/processor.c
> +++ b/arch/s390/kernel/processor.c
> @@ -31,6 +31,7 @@ struct cpu_info {
> };
>
> static DEFINE_PER_CPU(struct cpu_info, cpu_info);
> +static DEFINE_PER_CPU(int, cpu_relax_retry);
>
> static bool machine_has_cpu_mhz;
>
> @@ -58,13 +59,21 @@ void s390_update_cpu_mhz(void)
> on_each_cpu(update_cpu_mhz, NULL, 0);
> }
>
> +void notrace cpu_relax_yield(const struct cpumask *cpumask)
> {
> + int cpu;
> +
> + if (__this_cpu_inc_return(cpu_relax_retry) >= spin_retry) {
> + __this_cpu_write(cpu_relax_retry, 0);
I don't mind, but do we really need a per-cpu variable for this? Does it
really matter if you spin on a stack variable and occasionally spin a
bit longer due to the missed tail of the previous spin?
> + cpu = cpumask_next(smp_processor_id(), cpumask);
> + if (cpu >= nr_cpu_ids) {
> + cpu = cpumask_first(cpumask);
> + if (cpu == smp_processor_id())
> + return;
If this function is passed an empty cpumask, the above will result in
'cpu == nr_cpu_ids' and the below might be unhappy with that.
(FWIW we do have cpumask_next_wrap(), but I admit it is somewhat awkward
to use)
> + }
> + if (arch_vcpu_is_preempted(cpu))
> + smp_yield_cpu(cpu);
> }
> }
> EXPORT_SYMBOL(cpu_relax_yield);
