Re: [PATCH 08/11] x86/mm: enable broadcast TLB invalidation for multi-threaded processes

[Nadav Amit <nadav.amit@gmail.com>]

On 23 Dec 2024, at 4:55, Rik van Riel <riel@surriel.com> wrote:

> +static int mm_active_cpus(struct mm_struct *mm)
> +{
> +	int count = 0;
> +	int cpu;
> +
> +	for_each_cpu(cpu, mm_cpumask(mm)) {
> +		/* Skip the CPUs that aren't really running this process. */
> +		if (per_cpu(cpu_tlbstate.loaded_mm, cpu) != mm)
> +			continue;
> +
> +		if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu))
> +			continue;
> +
> +		count++;
> +	}
> +	return count;
> +}

Since you are only interested in checking whether the number of “mm active
CPUs" is greater than a certain threshold, don’t you want to add some
checks for early termination? This can allow to avoid cachelines of
cpu_tlbstate traversing back and forth.

For instance, by running cpumask_weight() first, if the weight is lower than
the threshold, no need to loop. Similarly, if inside the loop the threshold
has already been crossed, no need for more iterations.