1 files changed, 16 insertions, 7 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 62d1ea3f2f5a..6903b695ebae 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3604,6 +3604,17 @@ retry:
          */
         alloc_flags = gfp_to_alloc_flags(gfp_mask);
 
+        /*
+         * Reset the zonelist iterators if memory policies can be ignored.
+         * These allocations are high priority and system rather than user
+         * orientated.
+         */
+        if ((alloc_flags & ALLOC_NO_WATERMARKS) || !(alloc_flags & ALLOC_CPUSET)) {
+                ac->zonelist = node_zonelist(numa_node_id(), gfp_mask);
+                ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
+                                        ac->high_zoneidx, ac->nodemask);
+        }
+
         /* This is the last chance, in general, before the goto nopage. */
         page = get_page_from_freelist(gfp_mask, order,
                                 alloc_flags & ~ALLOC_NO_WATERMARKS, ac);
@@ -3612,12 +3623,6 @@ retry:
 
         /* Allocate without watermarks if the context allows */
         if (alloc_flags & ALLOC_NO_WATERMARKS) {
-                /*
-                 * Ignore mempolicies if ALLOC_NO_WATERMARKS on the grounds
-                 * the allocation is high priority and these type of
-                 * allocations are system rather than user orientated
-                 */
-                ac->zonelist = node_zonelist(numa_node_id(), gfp_mask);
                 page = get_page_from_freelist(gfp_mask, order,
                                                 ALLOC_NO_WATERMARKS, ac);
                 if (page)
@@ -3816,7 +3821,11 @@ retry_cpuset:
         /* Dirty zone balancing only done in the fast path */
         ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE);
 
-        /* The preferred zone is used for statistics later */
+        /*
+         * The preferred zone is used for statistics but crucially it is
+         * also used as the starting point for the zonelist iterator. It
+         * may get reset for allocations that ignore memory policies.
+         */
         ac.preferred_zoneref = first_zones_zonelist(ac.zonelist,
                                         ac.high_zoneidx, ac.nodemask);
         if (!ac.preferred_zoneref) {