Re: [PATCH] xen/arm: minor improvement in smp_send_call_function_mask()

[Julien Grall <julien.grall@linaro.org>]

Hi Anup,

On 18/08/14 23:48, Anup Patel wrote:
>   xen/arch/arm/smp.c |   14 +++++++++++++-
>   1 file changed, 13 insertions(+), 1 deletion(-)
>
> diff --git a/xen/arch/arm/smp.c b/xen/arch/arm/smp.c
> index 30203b8..c80c068 100644
> --- a/xen/arch/arm/smp.c
> +++ b/xen/arch/arm/smp.c
> @@ -19,7 +19,19 @@ void smp_send_event_check_mask(const cpumask_t *mask)
>
>   void smp_send_call_function_mask(const cpumask_t *mask)
>   {
> -    send_SGI_mask(mask, GIC_SGI_CALL_FUNCTION);
> +    cpumask_t target_mask;
> +
> +    cpumask_andnot(&target_mask, mask, cpumask_of(smp_processor_id()));
> +
> +    if ( cpumask_weight(&target_mask) )

Is it necessary? What happen if Xen tries to send an SGI with an empty mask?

AFAIU, the function cpumask_weight is complex so if we can avoid it, it 
would be better.

-- 
Julien Grall