Re: [PATCH v2 07/12] mm/hugetlb: do not modify user provided gfp_mask

[Michal Hocko <mhocko@kernel.org>]

On Wed 27-05-20 15:44:58, Joonsoo Kim wrote:
> From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
> 
> It's not good practice to modify user input. Instead of using it to
> build correct gfp_mask for APIs, this patch introduces another gfp_mask
> field, __gfp_mask, for internal usage.

Ugh, this is really ugly. It is just hugetlb to add __GFP_THISNODE as a
special case. This is an ugly hack but I do not think we want to work
around it by yet another hack. Moreover it seems that the __GFP_THISNODE
might be not needed anymore as pointed out in a reply to earlier patch.

> Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
> ---
>  mm/hugetlb.c  | 19 ++++++++++---------
>  mm/internal.h |  2 ++
>  2 files changed, 12 insertions(+), 9 deletions(-)
> 
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index e465582..4757e72 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -1068,15 +1068,15 @@ static struct page *dequeue_huge_page_nodemask(struct hstate *h,
>  	struct zoneref *z;
>  	int node = NUMA_NO_NODE;
>  
> -	zonelist = node_zonelist(ac->nid, ac->gfp_mask);
> +	zonelist = node_zonelist(ac->nid, ac->__gfp_mask);
>  
>  retry_cpuset:
>  	cpuset_mems_cookie = read_mems_allowed_begin();
>  	for_each_zone_zonelist_nodemask(zone, z, zonelist,
> -			gfp_zone(ac->gfp_mask), ac->nmask) {
> +			gfp_zone(ac->__gfp_mask), ac->nmask) {
>  		struct page *page;
>  
> -		if (!cpuset_zone_allowed(zone, ac->gfp_mask))
> +		if (!cpuset_zone_allowed(zone, ac->__gfp_mask))
>  			continue;
>  		/*
>  		 * no need to ask again on the same node. Pool is node rather than
> @@ -1127,8 +1127,8 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
>  	if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0)
>  		goto err;
>  
> -	ac.gfp_mask = htlb_alloc_mask(h);
> -	ac.nid = huge_node(vma, address, ac.gfp_mask, &mpol, &ac.nmask);
> +	ac.__gfp_mask = htlb_alloc_mask(h);
> +	ac.nid = huge_node(vma, address, ac.__gfp_mask, &mpol, &ac.nmask);
>  
>  	page = dequeue_huge_page_nodemask(h, &ac);
>  	if (page && !avoid_reserve && vma_has_reserves(vma, chg)) {
> @@ -1951,7 +1951,7 @@ static struct page *alloc_migrate_huge_page(struct hstate *h,
>  	if (hstate_is_gigantic(h))
>  		return NULL;
>  
> -	page = alloc_fresh_huge_page(h, ac->gfp_mask,
> +	page = alloc_fresh_huge_page(h, ac->__gfp_mask,
>  				ac->nid, ac->nmask, NULL);
>  	if (!page)
>  		return NULL;
> @@ -1989,9 +1989,10 @@ struct page *alloc_buddy_huge_page_with_mpol(struct hstate *h,
>  struct page *alloc_huge_page_nodemask(struct hstate *h,
>  				struct alloc_control *ac)
>  {
> -	ac->gfp_mask |= htlb_alloc_mask(h);
> +	ac->__gfp_mask = htlb_alloc_mask(h);
> +	ac->__gfp_mask |= ac->gfp_mask;
>  	if (ac->nid == NUMA_NO_NODE)
> -		ac->gfp_mask &= ~__GFP_THISNODE;
> +		ac->__gfp_mask &= ~__GFP_THISNODE;
>  
>  	spin_lock(&hugetlb_lock);
>  	if (h->free_huge_pages - h->resv_huge_pages > 0) {
> @@ -2010,7 +2011,7 @@ struct page *alloc_huge_page_nodemask(struct hstate *h,
>  	 * will not come from CMA area
>  	 */
>  	if (ac->skip_cma)
> -		ac->gfp_mask &= ~__GFP_MOVABLE;
> +		ac->__gfp_mask &= ~__GFP_MOVABLE;
>  
>  	return alloc_migrate_huge_page(h, ac);
>  }
> diff --git a/mm/internal.h b/mm/internal.h
> index 159cfd6..2dc0268 100644
> --- a/mm/internal.h
> +++ b/mm/internal.h
> @@ -619,6 +619,8 @@ struct alloc_control {
>  	nodemask_t *nmask;
>  	gfp_t gfp_mask;
>  	bool skip_cma;
> +
> +	gfp_t __gfp_mask;	/* Used internally in API implementation */
>  };
>  
>  #endif	/* __MM_INTERNAL_H */
> -- 
> 2.7.4

-- 
Michal Hocko
SUSE Labs