Memoryless nodes: Fix GFP_THISNODE behavior

[safe/jmp/linux-2.6] / mm / page_alloc.c

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d06f6e0..2f547f4 100644 (file)
--- 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 */