On Sun, 10 Jun 2012, Gavin Shan wrote:
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 7892f84..dda83c5 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -2474,6 +2474,7 @@ struct page *
> __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
> struct zonelist *zonelist, nodemask_t *nodemask)
> {
> + nodemask_t *preferred_nodemask = nodemask ? : &cpuset_current_mems_allowed;
> enum zone_type high_zoneidx = gfp_zone(gfp_mask);
> struct zone *preferred_zone;
> struct page *page = NULL;
> @@ -2501,19 +2502,18 @@ retry_cpuset:
> cpuset_mems_cookie = get_mems_allowed();
>
> /* The preferred zone is used for statistics later */
> - first_zones_zonelist(zonelist, high_zoneidx,
> - nodemask ? : &cpuset_current_mems_allowed,
> + first_zones_zonelist(zonelist, high_zoneidx, preferred_nodemask,
> &preferred_zone);
> if (!preferred_zone)
> goto out;
>
> /* First allocation attempt */
> - page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
> - zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET,
> + page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, preferred_nodemask,
> + order, zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET,
> preferred_zone, migratetype);
> if (unlikely(!page))
> - page = __alloc_pages_slowpath(gfp_mask, order,
> - zonelist, high_zoneidx, nodemask,
> + page = __alloc_pages_slowpath(gfp_mask, order, zonelist,
> + high_zoneidx, preferred_nodemask,
> preferred_zone, migratetype);
>
> trace_mm_page_alloc(page, order, gfp_mask, migratetype);
Nack, this is wrong. The nodemask passed to first_zones_zonelist() is
only for statistics and is correct as written. The nodemask passed to
get_page_from_freelist() constrains the iteration to only those nodes
which would be done over cpuset_current_mems_allowed with your patch if a
NULL nodemask is passed into the page allocator (meaning it has a default
mempolicy). Allocations on non-cpuset nodes are allowed in some
contexts, see cpuset_zone_allowed_softwall(), so this would cause a
regression.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>