Re: [PATCH v7 2/5] mm/memplicy: add page allocation function for MPOL_PREFERRED_MANY policy

[Michal Hocko]

On Tue 03-08-21 13:59:19, Feng Tang wrote:
> The semantics of MPOL_PREFERRED_MANY is similar to MPOL_PREFERRED,
> that it will first try to allocate memory from the preferred node(s),
> and fallback to all nodes in system when first try fails.
> 
> Add a dedicated function alloc_pages_preferred_many() for it just
> like for 'interleave' policy, which will be used by 2 general
> memoory allocation APIs: alloc_pages() and alloc_pages_vma()
> 
> Link: https://lore.kernel.org/r/20200630212517.308045-9-ben.widawsky@xxxxxxxxx
> Suggested-by: Michal Hocko <mhocko@xxxxxxxx>
> Originally-by: Ben Widawsky <ben.widawsky@xxxxxxxxx>
> Co-developed-by: Ben Widawsky <ben.widawsky@xxxxxxxxx>
> Signed-off-by: Ben Widawsky <ben.widawsky@xxxxxxxxx>
> Signed-off-by: Feng Tang <feng.tang@xxxxxxxxx>

Acked-by: Michal Hocko <mhocko@xxxxxxxx>
Thanks!

> ---
>  mm/mempolicy.c | 30 ++++++++++++++++++++++++++++++
>  1 file changed, 30 insertions(+)
> 
> diff --git a/mm/mempolicy.c b/mm/mempolicy.c
> index 72f7ff760989..a00bb1c48a15 100644
> --- a/mm/mempolicy.c
> +++ b/mm/mempolicy.c
> @@ -2166,6 +2166,27 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
>  	return page;
>  }
>  
> +static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order,
> +						int nid, struct mempolicy *pol)
> +{
> +	struct page *page;
> +	gfp_t preferred_gfp;
> +
> +	/*
> +	 * This is a two pass approach. The first pass will only try the
> +	 * preferred nodes but skip the direct reclaim and allow the
> +	 * allocation to fail, while the second pass will try all the
> +	 * nodes in system.
> +	 */
> +	preferred_gfp = gfp | __GFP_NOWARN;
> +	preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL);
> +	page = __alloc_pages(preferred_gfp, order, nid, &pol->nodes);
> +	if (!page)
> +		page = __alloc_pages(gfp, order, numa_node_id(), NULL);
> +
> +	return page;
> +}
> +
>  /**
>   * alloc_pages_vma - Allocate a page for a VMA.
>   * @gfp: GFP flags.
> @@ -2201,6 +2222,12 @@ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
>  		goto out;
>  	}
>  
> +	if (pol->mode == MPOL_PREFERRED_MANY) {
> +		page = alloc_pages_preferred_many(gfp, order, node, pol);
> +		mpol_cond_put(pol);
> +		goto out;
> +	}
> +
>  	if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) {
>  		int hpage_node = node;
>  
> @@ -2278,6 +2305,9 @@ struct page *alloc_pages(gfp_t gfp, unsigned order)
>  	 */
>  	if (pol->mode == MPOL_INTERLEAVE)
>  		page = alloc_page_interleave(gfp, order, interleave_nodes(pol));
> +	else if (pol->mode == MPOL_PREFERRED_MANY)
> +		page = alloc_pages_preferred_many(gfp, order,
> +				numa_node_id(), pol);
>  	else
>  		page = __alloc_pages(gfp, order,
>  				policy_node(gfp, pol, numa_node_id()),
> -- 
> 2.14.1

-- 
Michal Hocko
SUSE Labs