From: Lee Schermerhorn <Lee.Schermerhorn@hp.com>

Against 2.6.23-rc3-mm1

V1 -> V2:
+ moved population of N_HIGH_MEMORY node state mask to
  free_area_init_nodes(), as this is called before we
  build zonelists.  So, we can use this mask in
  find_next_best_node.  Still need to keep the duplicate
  code in early_calculate_totalpages() for zone movable
  setup.

mm/page_alloc.c:find_next_best_node()

	visit only nodes with memory [N_HIGH_MEMORY mask]
	looking for next best node for fallback zonelists.

mm/page_alloc.c:find_zone_movable_pfns_for_nodes()

	spread kernelcore over nodes with memory.

	This required calling early_calculate_totalpages()
	unconditionally, and populating N_HIGH_MEMORY node
	state therein from nodes in the early_node_map[].
	This duplicates the code in free_area_init_nodes(), but
	I don't want to depend on this copy if ZONE_MOVABLE
	might go away, taking early_calculate_totalpages()
	with it.

Signed-off-by:  Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Mel Gorman <mel@skynet.ie>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Jeremy Higdon <jeremy@sgi.com>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/page_alloc.c |   48 +++++++++++++++++++---------------------------
 1 file changed, 20 insertions(+), 28 deletions(-)

diff -puN mm/page_alloc.c~memoryless-nodes-fixup-uses-of-node_online_map-in-generic-code-fix mm/page_alloc.c
--- a/mm/page_alloc.c~memoryless-nodes-fixup-uses-of-node_online_map-in-generic-code-fix
+++ a/mm/page_alloc.c
@@ -1802,18 +1802,10 @@ static int find_next_best_node(int node,
 		return node;
 	}
 
-	for_each_online_node(n) {
+	for_each_node_state(n, N_HIGH_MEMORY) {
 		pg_data_t *pgdat = NODE_DATA(n);
 		cpumask_t tmp;
 
-		/*
-		 * skip nodes w/o memory.
-		 * Note:  N_HIGH_MEMORY state not guaranteed to be
-		 *        populated yet.
-		 */
-		if (pgdat->node_present_pages)
-			continue;
-
 		/* Don't want a node to appear more than once */
 		if (node_isset(n, *used_node_mask))
 			continue;
@@ -2108,20 +2100,6 @@ static void build_zonelist_cache(pg_data
 
 #endif	/* CONFIG_NUMA */
 
-/* Any regular memory on that node ? */
-static void check_for_regular_memory(pg_data_t *pgdat)
-{
-#ifdef CONFIG_HIGHMEM
-	enum zone_type zone_type;
-
-	for (zone_type = 0; zone_type <= ZONE_NORMAL; zone_type++) {
-		struct zone *zone = &pgdat->node_zones[zone_type];
-		if (zone->present_pages)
-			node_set_state(zone_to_nid(zone), N_NORMAL_MEMORY);
-	}
-#endif
-}
-
 /* return values int ....just for stop_machine_run() */
 static int __build_all_zonelists(void *dummy)
 {
@@ -2132,11 +2110,6 @@ static int __build_all_zonelists(void *d
 
 		build_zonelists(pgdat);
 		build_zonelist_cache(pgdat);
-
-		/* Any memory on that node */
-		if (pgdat->node_present_pages)
-			node_set_state(nid, N_HIGH_MEMORY);
-		check_for_regular_memory(pgdat);
 	}
 	return 0;
 }
@@ -3451,6 +3424,20 @@ restart:
 			roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES);
 }
 
+/* Any regular memory on that node ? */
+static void check_for_regular_memory(pg_data_t *pgdat)
+{
+#ifdef CONFIG_HIGHMEM
+	enum zone_type zone_type;
+
+	for (zone_type = 0; zone_type <= ZONE_NORMAL; zone_type++) {
+		struct zone *zone = &pgdat->node_zones[zone_type];
+		if (zone->present_pages)
+			node_set_state(zone_to_nid(zone), N_NORMAL_MEMORY);
+	}
+#endif
+}
+
 /**
  * free_area_init_nodes - Initialise all pg_data_t and zone data
  * @max_zone_pfn: an array of max PFNs for each zone
@@ -3525,6 +3512,11 @@ void __init free_area_init_nodes(unsigne
 		pg_data_t *pgdat = NODE_DATA(nid);
 		free_area_init_node(nid, pgdat, NULL,
 				find_min_pfn_for_node(nid), NULL);
+
+		/* Any memory on that node */
+		if (pgdat->node_present_pages)
+			node_set_state(nid, N_HIGH_MEMORY);
+		check_for_regular_memory(pgdat);
 	}
 }
 
_