Re: [RFC v2 29/34] mm: slub: Move flush_cpu_slab() invocations __free_slab() invocations out of IRQ context

[Cyrill Gorcunov]

On Wed, Jun 09, 2021 at 01:38:58PM +0200, Vlastimil Babka wrote:
> +static DEFINE_MUTEX(flush_lock);
> +static DEFINE_PER_CPU(struct slub_flush_work, slub_flush);
> +
>  static void flush_all(struct kmem_cache *s)
>  {
> -	on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1);
> +	struct slub_flush_work *sfw;
> +	unsigned int cpu;
> +
> +	cpus_read_lock();
> +	mutex_lock(&flush_lock);
> +

Hi, Vlastimil! Could you please point why do you lock cpus first and
mutex only after? Why not mutex_lock + cpus_read_lock instead?