mm: filter based on a nodemask as well as a gfp_mask

The MPOL_BIND policy creates a zonelist that is used for allocations
controlled by that mempolicy.  As the per-node zonelist is already being
filtered based on a zone id, this patch adds a version of __alloc_pages() that
takes a nodemask for further filtering.  This eliminates the need for
MPOL_BIND to create a custom zonelist.

A positive benefit of this is that allocations using MPOL_BIND now use the
local node's distance-ordered zonelist instead of a custom node-id-ordered
zonelist.  I.e., pages will be allocated from the closest allowed node with
available memory.

[Lee.Schermerhorn@hp.com: Mempolicy: update stale documentation and comments]
[Lee.Schermerhorn@hp.com: Mempolicy: make dequeue_huge_page_vma() obey MPOL_BIND nodemask]
[Lee.Schermerhorn@hp.com: Mempolicy: make dequeue_huge_page_vma() obey MPOL_BIND nodemask rework]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 36 insertions, 14 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6d94d04..b4beb3e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1377,7 +1377,7 @@ static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
  * a page.
  */
 static struct page *
-get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
+get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order,
 		struct zonelist *zonelist, int high_zoneidx, int alloc_flags)
 {
 	struct zoneref *z;
@@ -1388,16 +1388,17 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
 	int zlc_active = 0;		/* set if using zonelist_cache */
 	int did_zlc_setup = 0;		/* just call zlc_setup() one time */
 
-	z = first_zones_zonelist(zonelist, high_zoneidx);
-	classzone_idx = zonelist_zone_idx(z);
-	preferred_zone = zonelist_zone(z);
+	(void)first_zones_zonelist(zonelist, high_zoneidx, nodemask,
+							&preferred_zone);
+	classzone_idx = zone_idx(preferred_zone);
 
 zonelist_scan:
 	/*
 	 * Scan zonelist, looking for a zone with enough free.
 	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
 	 */
-	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
+	for_each_zone_zonelist_nodemask(zone, z, zonelist,
+						high_zoneidx, nodemask) {
 		if (NUMA_BUILD && zlc_active &&
 			!zlc_zone_worth_trying(zonelist, z, allowednodes))
 				continue;
@@ -1447,9 +1448,9 @@ try_next_zone:
 /*
  * This is the 'heart' of the zoned buddy allocator.
  */
-struct page *
-__alloc_pages(gfp_t gfp_mask, unsigned int order,
-		struct zonelist *zonelist)
+static struct page *
+__alloc_pages_internal(gfp_t gfp_mask, unsigned int order,
+			struct zonelist *zonelist, nodemask_t *nodemask)
 {
 	const gfp_t wait = gfp_mask & __GFP_WAIT;
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
@@ -1478,7 +1479,7 @@ restart:
 		return NULL;
 	}
 
-	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
+	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
 			zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET);
 	if (page)
 		goto got_pg;
@@ -1523,7 +1524,7 @@ restart:
 	 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
 	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
 	 */
-	page = get_page_from_freelist(gfp_mask, order, zonelist,
+	page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
 						high_zoneidx, alloc_flags);
 	if (page)
 		goto got_pg;
@@ -1536,7 +1537,7 @@ rebalance:
 		if (!(gfp_mask & __GFP_NOMEMALLOC)) {
 nofail_alloc:
 			/* go through the zonelist yet again, ignoring mins */
-			page = get_page_from_freelist(gfp_mask, order,
+			page = get_page_from_freelist(gfp_mask, nodemask, order,
 				zonelist, high_zoneidx, ALLOC_NO_WATERMARKS);
 			if (page)
 				goto got_pg;
@@ -1571,7 +1572,7 @@ nofail_alloc:
 		drain_all_pages();
 
 	if (likely(did_some_progress)) {
-		page = get_page_from_freelist(gfp_mask, order,
+		page = get_page_from_freelist(gfp_mask, nodemask, order,
 					zonelist, high_zoneidx, alloc_flags);
 		if (page)
 			goto got_pg;
@@ -1587,8 +1588,9 @@ nofail_alloc:
 		 * a parallel oom killing, we must fail if we're still
 		 * under heavy pressure.
 		 */
-		page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
-			zonelist, high_zoneidx, ALLOC_WMARK_HIGH|ALLOC_CPUSET);
+		page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask,
+			order, zonelist, high_zoneidx,
+			ALLOC_WMARK_HIGH|ALLOC_CPUSET);
 		if (page) {
 			clear_zonelist_oom(zonelist, gfp_mask);
 			goto got_pg;
@@ -1637,6 +1639,20 @@ got_pg:
 	return page;
 }
 
+struct page *
+__alloc_pages(gfp_t gfp_mask, unsigned int order,
+		struct zonelist *zonelist)
+{
+	return __alloc_pages_internal(gfp_mask, order, zonelist, NULL);
+}
+
+struct page *
+__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
+		struct zonelist *zonelist, nodemask_t *nodemask)
+{
+	return __alloc_pages_internal(gfp_mask, order, zonelist, nodemask);
+}
+
 EXPORT_SYMBOL(__alloc_pages);
 
 /*
@@ -1880,6 +1896,12 @@ void show_free_areas(void)
 	show_swap_cache_info();
 }
 
+static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
+{
+	zoneref->zone = zone;
+	zoneref->zone_idx = zone_idx(zone);
+}
+
 /*
  * Builds allocation fallback zone lists.
  *