Memoryless nodes: Fix GFP_THISNODE behavior

GFP_THISNODE checks that the zone selected is within the pgdat (node) of the
first zone of a nodelist.  That only works if the node has memory.  A
memoryless node will have its first node on another pgdat (node).

GFP_THISNODE currently will return simply memory on the first pgdat.  Thus it
is returning memory on other nodes.  GFP_THISNODE should fail if there is no
local memory on a node.

Add a new set of zonelists for each node that only contain the nodes that
belong to the zones itself so that no fallback is possible.

Then modify gfp_type to pickup the right zone based on the presence of
__GFP_THISNODE.

Drop the existing GFP_THISNODE checks from the page_allocators hot path.

Signed-off-by: Christoph Lameter <clameter@sgi.com>
Acked-by: Nishanth Aravamudan <nacc@us.ibm.com>
Tested-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Bob Picco <bob.picco@hp.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@skynet.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 23 insertions, 5 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d06f6e0f75a..2f547f45de1 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1191,9 +1191,6 @@ zonelist_scan:
 			!zlc_zone_worth_trying(zonelist, z, allowednodes))
 				continue;
 		zone = *z;
-		if (unlikely(NUMA_BUILD && (gfp_mask & __GFP_THISNODE) &&
-			zone->zone_pgdat != zonelist->zones[0]->zone_pgdat))
-				break;
 		if ((alloc_flags & ALLOC_CPUSET) &&
 			!cpuset_zone_allowed_softwall(zone, gfp_mask))
 				goto try_next_zone;
@@ -1262,7 +1259,10 @@ restart:
 	z = zonelist->zones;  /* the list of zones suitable for gfp_mask */
 
 	if (unlikely(*z == NULL)) {
-		/* Should this ever happen?? */
+		/*
+		 * Happens if we have an empty zonelist as a result of
+		 * GFP_THISNODE being used on a memoryless node
+		 */
 		return NULL;
 	}
 
@@ -1858,6 +1858,22 @@ static void build_zonelists_in_node_order(pg_data_t *pgdat, int node)
 }
 
 /*
+ * Build gfp_thisnode zonelists
+ */
+static void build_thisnode_zonelists(pg_data_t *pgdat)
+{
+	enum zone_type i;
+	int j;
+	struct zonelist *zonelist;
+
+	for (i = 0; i < MAX_NR_ZONES; i++) {
+		zonelist = pgdat->node_zonelists + MAX_NR_ZONES + i;
+		j = build_zonelists_node(pgdat, zonelist, 0, i);
+		zonelist->zones[j] = NULL;
+	}
+}
+
+/*
  * Build zonelists ordered by zone and nodes within zones.
  * This results in conserving DMA zone[s] until all Normal memory is
  * exhausted, but results in overflowing to remote node while memory
@@ -1961,7 +1977,7 @@ static void build_zonelists(pg_data_t *pgdat)
 	int order = current_zonelist_order;
 
 	/* initialize zonelists */
-	for (i = 0; i < MAX_NR_ZONES; i++) {
+	for (i = 0; i < MAX_ZONELISTS; i++) {
 		zonelist = pgdat->node_zonelists + i;
 		zonelist->zones[0] = NULL;
 	}
@@ -2006,6 +2022,8 @@ static void build_zonelists(pg_data_t *pgdat)
 		/* calculate node order -- i.e., DMA last! */
 		build_zonelists_in_zone_order(pgdat, j);
 	}
+
+	build_thisnode_zonelists(pgdat);
 }
 
 /* Construct the zonelist performance cache - see further mmzone.h */