Re: [PATCH v3 2/6] mm: hugetlb: Move mpol interpretation out of alloc_buddy_hugetlb_folio_with_mpol()

[Ackerley Tng]

Ackerley Tng via B4 Relay <devnull+ackerleytng.google.com@xxxxxxxxxx>
writes:

>
> [...snip...]
>
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index 190ab539a97d4..6a5f69b3b1cb4 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -1334,6 +1334,12 @@ static unsigned long available_huge_pages(struct hstate *h)
>  	return h->free_huge_pages - h->resv_huge_pages;
>  }
>
> +struct mempolicy_interpreted {
> +	int nid;
> +	nodemask_t *nodemask;
> +	enum mempolicy_mode mode;
> +};
> +
>
> [...snip...]
>
> @@ -2941,8 +2943,20 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
>  		folio = dequeue_hugetlb_folio_vma(h, vma, addr);
>
>  	if (!folio) {
> +		struct mempolicy_interpreted mpoli;
> +		struct mempolicy *mpol;
> +		nodemask_t *nodemask;
> +		int nid;
> +
>  		spin_unlock_irq(&hugetlb_lock);
> -		folio = alloc_buddy_hugetlb_folio_with_mpol(h, vma, addr);
> +		nid = huge_node(vma, addr, gfp, &mpol, &nodemask);
> +		mpoli = (struct mempolicy_interpreted){
> +			.nid = nid,
> +			.mode = mpol->mode,
> +			.nodemask = nodemask,
> +		};

This needs to take into account CONFIG_NUMA, so the next revision will
look something like this instead:

	mpoli = (struct mempolicy_interpreted){
		.nid = nid,
#ifdef CONFIG_NUMA
		.mode = mpol ? mpol->mode : MPOL_DEFAULT,
#else
		.mode = MPOL_DEFAULT,
#endif
		.nodemask = nodemask,
	};


> +		folio = alloc_buddy_hugetlb_folio(h, gfp, &mpoli);
> +		mpol_cond_put(mpol);
>  		if (!folio)
>  			goto out_uncharge_cgroup;
>  		spin_lock_irq(&hugetlb_lock);
>
> [...snip...]
>