[PATCH v8 10/12] blk-mq: use hk cpus only when isolcpus=io_queue is enabled

[Daniel Wagner]

On Fri, Sep 05, 2025 at 04:59:56PM +0200, Daniel Wagner wrote:
>  void blk_mq_map_queues(struct blk_mq_queue_map *qmap)
>  {
> -	const struct cpumask *masks;
> +	struct cpumask *masks __free(kfree) = NULL;
> +	const struct cpumask *constraint;
>  	unsigned int queue, cpu, nr_masks;
> +	cpumask_var_t active_hctx;
>  
> +	if (!zalloc_cpumask_var(&active_hctx, GFP_KERNEL))
> +		goto fallback;
> +

> +	free_cpumask_var(active_hctx);
> +
> +	return;
> +
> +free_fallback:
> +	free_cpumask_var(active_hctx);
> +
> +fallback:
> +	blk_mq_map_fallback(qmap);

I am not so happy that the cpumask_var_t and __free doesn't work to
together at this point due to the 'evil way' how cpumask_var_t is defined:

	ifdef CONFIG_CPUMASK_OFFSTACK
	typedef struct cpumask *cpumask_var_t;
	#else
	typedef struct cpumask cpumask_var_t[1];
	#endif /* CONFIG_CPUMASK_OFFSTACK */

In the previous version I used

	cpumask_var_t active_hctx __free(free_cpumask_var) = NULL;

which resulted in a way cleaner code. Though the kernel test robot
complained with

      >> block/blk-mq-cpumap.c:155:16: error: array initializer must be an initializer list
           155 |         cpumask_var_t active_hctx __free(free_cpumask_var) = NULL;

I try to figure out if it's possible to get this somehow working with
some witchcraft (aka pre compiler magic).