Re: [PATCH] powercap/drivers/dtpm_cpu: Fix suspend failure and kernel warning

[Rafael J. Wysocki]

On Mon, Nov 8, 2021 at 7:24 AM Daniel Lezcano <daniel.lezcano@xxxxxxxxxx> wrote:
>
> When the ENERGY_MODEL and DTPM_CPU are enabled but actually without
> any energy model, at cpu hotplug time, the dead cpuhp callback fails
> leading to the warning.
>
> Actually, the check could be simplified and we only do an action if
> the dtpm cpu is enabled, otherwise we bail out without error.
>
> Fixes: 7a89d7eacf8e ("powercap/drivers/dtpm: Simplify the dtpm table")
> Reported-by: Kenneth R. Crudup <kenny@xxxxxxxxx>
> Tested-by: Kenneth R. Crudup <kenny@xxxxxxxxx>
> Reported-by: kernel test robot <oliver.sang@xxxxxxxxx>
> Cc: lkp@xxxxxxxxxxxx
> Cc: lkp@xxxxxxxxx
> Signed-off-by: Daniel Lezcano <daniel.lezcano@xxxxxxxxxx>
> ---
>  drivers/powercap/dtpm_cpu.c | 9 +++------
>  1 file changed, 3 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c
> index 69eb5101b5c7..477042199d90 100644
> --- a/drivers/powercap/dtpm_cpu.c
> +++ b/drivers/powercap/dtpm_cpu.c
> @@ -166,16 +166,13 @@ static struct dtpm_ops dtpm_ops = {
>
>  static int cpuhp_dtpm_cpu_offline(unsigned int cpu)
>  {
> -       struct em_perf_domain *pd;
>         struct dtpm_cpu *dtpm_cpu;
>
> -       pd = em_cpu_get(cpu);
> -       if (!pd)
> -               return -EINVAL;
> -
>         dtpm_cpu = per_cpu(dtpm_per_cpu, cpu);
> +       if (dtpm_cpu)
> +               dtpm_update_power(&dtpm_cpu->dtpm);
>
> -       return dtpm_update_power(&dtpm_cpu->dtpm);
> +       return 0;
>  }
>
>  static int cpuhp_dtpm_cpu_online(unsigned int cpu)
> --

Applied as 5.16-rc material, thanks!