mm, page_alloc: simplify zonelist initialization

build_zonelists gradually builds zonelists from the nearest to the most
distant node.  As we do not know how many populated zones we will have
in each node we rely on the _zoneref to terminate initialized part of
the zonelist by a NULL zone.  While this is functionally correct it is
quite suboptimal because we cannot allow updaters to race with zonelists
users because they could see an empty zonelist and fail the allocation
or hit the OOM killer in the worst case.

We can do much better, though.  We can store the node ordering into an
already existing node_order array and then give this array to
build_zonelists_in_node_order and do the whole initialization at once.
zonelists consumers still might see halfway initialized state but that
should be much more tolerateable because the list will not be empty and
they would either see some zone twice or skip over some zone(s) in the
worst case which shouldn't lead to immediate failures.

While at it let's simplify build_zonelists_node which is rather
confusing now.  It gets an index into the zoneref array and returns the
updated index for the next iteration.  Let's rename the function to
build_zonerefs_node to better reflect its purpose and give it zoneref
array to update.  The function doesn't the index anymore.  It just
returns the number of added zones so that the caller can advance the
zonered array start for the next update.

This patch alone doesn't introduce any functional change yet, though, it
is merely a preparatory work for later changes.

Link: http://lkml.kernel.org/r/20170721143915.14161-7-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <js1304@gmail.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Shaohua Li <shaohua.li@intel.com>
Cc: Toshi Kani <toshi.kani@hpe.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2523d5b3b22f61c49465d0a65288479e2d99ab9e..36a2f18c5e0a9fe557ac51fe5fb44e7d284e83e1 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4839,18 +4839,17 @@ static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
  *
  * Add all populated zones of a node to the zonelist.
  */
-static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist,
-                               int nr_zones)
+static int build_zonerefs_node(pg_data_t *pgdat, struct zoneref *zonerefs)
 {
        struct zone *zone;
        enum zone_type zone_type = MAX_NR_ZONES;
+       int nr_zones = 0;
 
        do {
                zone_type--;
                zone = pgdat->node_zones + zone_type;
                if (managed_zone(zone)) {
-                       zoneref_set_zone(zone,
-                               &zonelist->_zonerefs[nr_zones++]);
+                       zoneref_set_zone(zone, &zonerefs[nr_zones++]);
                        check_highest_zone(zone_type);
                }
        } while (zone_type);
@@ -4977,17 +4976,24 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask)
  * This results in maximum locality--normal zone overflows into local
  * DMA zone, if any--but risks exhausting DMA zone.
  */
-static void build_zonelists_in_node_order(pg_data_t *pgdat, int node)
+static void build_zonelists_in_node_order(pg_data_t *pgdat, int *node_order,
+               unsigned nr_nodes)
 {
-       int j;
-       struct zonelist *zonelist;
+       struct zoneref *zonerefs;
+       int i;
+
+       zonerefs = pgdat->node_zonelists[ZONELIST_FALLBACK]._zonerefs;
+
+       for (i = 0; i < nr_nodes; i++) {
+               int nr_zones;
 
-       zonelist = &pgdat->node_zonelists[ZONELIST_FALLBACK];
-       for (j = 0; zonelist->_zonerefs[j].zone != NULL; j++)
-               ;
-       j = build_zonelists_node(NODE_DATA(node), zonelist, j);
-       zonelist->_zonerefs[j].zone = NULL;
-       zonelist->_zonerefs[j].zone_idx = 0;
+               pg_data_t *node = NODE_DATA(node_order[i]);
+
+               nr_zones = build_zonerefs_node(node, zonerefs);
+               zonerefs += nr_zones;
+       }
+       zonerefs->zone = NULL;
+       zonerefs->zone_idx = 0;
 }
 
 /*
@@ -4995,13 +5001,14 @@ static void build_zonelists_in_node_order(pg_data_t *pgdat, int node)
  */
 static void build_thisnode_zonelists(pg_data_t *pgdat)
 {
-       int j;
-       struct zonelist *zonelist;
+       struct zoneref *zonerefs;
+       int nr_zones;
 
-       zonelist = &pgdat->node_zonelists[ZONELIST_NOFALLBACK];
-       j = build_zonelists_node(pgdat, zonelist, 0);
-       zonelist->_zonerefs[j].zone = NULL;
-       zonelist->_zonerefs[j].zone_idx = 0;
+       zonerefs = pgdat->node_zonelists[ZONELIST_NOFALLBACK]._zonerefs;
+       nr_zones = build_zonerefs_node(pgdat, zonerefs);
+       zonerefs += nr_zones;
+       zonerefs->zone = NULL;
+       zonerefs->zone_idx = 0;
 }
 
 /*
@@ -5010,21 +5017,13 @@ static void build_thisnode_zonelists(pg_data_t *pgdat)
  * exhausted, but results in overflowing to remote node while memory
  * may still exist in local DMA zone.
  */
-static int node_order[MAX_NUMNODES];
 
 static void build_zonelists(pg_data_t *pgdat)
 {
-       int i, node, load;
+       static int node_order[MAX_NUMNODES];
+       int node, load, nr_nodes = 0;
        nodemask_t used_mask;
        int local_node, prev_node;
-       struct zonelist *zonelist;
-
-       /* initialize zonelists */
-       for (i = 0; i < MAX_ZONELISTS; i++) {
-               zonelist = pgdat->node_zonelists + i;
-               zonelist->_zonerefs[0].zone = NULL;
-               zonelist->_zonerefs[0].zone_idx = 0;
-       }
 
        /* NUMA-aware ordering of nodes */
        local_node = pgdat->node_id;
@@ -5033,8 +5032,6 @@ static void build_zonelists(pg_data_t *pgdat)
        nodes_clear(used_mask);
 
        memset(node_order, 0, sizeof(node_order));
-       i = 0;
-
        while ((node = find_next_best_node(local_node, &used_mask)) >= 0) {
                /*
                 * We don't want to pressure a particular node.
@@ -5045,11 +5042,12 @@ static void build_zonelists(pg_data_t *pgdat)
                    node_distance(local_node, prev_node))
                        node_load[node] = load;
 
+               node_order[nr_nodes++] = node;
                prev_node = node;
                load--;
-               build_zonelists_in_node_order(pgdat, node);
        }
 
+       build_zonelists_in_node_order(pgdat, node_order, nr_nodes);
        build_thisnode_zonelists(pgdat);
 }
 
@@ -5078,13 +5076,14 @@ static void setup_min_slab_ratio(void);
 static void build_zonelists(pg_data_t *pgdat)
 {
        int node, local_node;
-       enum zone_type j;
-       struct zonelist *zonelist;
+       struct zoneref *zonerefs;
+       int nr_zones;
 
        local_node = pgdat->node_id;
 
-       zonelist = &pgdat->node_zonelists[ZONELIST_FALLBACK];
-       j = build_zonelists_node(pgdat, zonelist, 0);
+       zonerefs = pgdat->node_zonelists[ZONELIST_FALLBACK]._zonerefs;
+       nr_zones = build_zonerefs_node(pgdat, zonerefs);
+       zonerefs += nr_zones;
 
        /*
         * Now we build the zonelist so that it contains the zones
@@ -5097,16 +5096,18 @@ static void build_zonelists(pg_data_t *pgdat)
        for (node = local_node + 1; node < MAX_NUMNODES; node++) {
                if (!node_online(node))
                        continue;
-               j = build_zonelists_node(NODE_DATA(node), zonelist, j);
+               nr_zones = build_zonerefs_node(NODE_DATA(node), zonerefs);
+               zonerefs += nr_zones;
        }
        for (node = 0; node < local_node; node++) {
                if (!node_online(node))
                        continue;
-               j = build_zonelists_node(NODE_DATA(node), zonelist, j);
+               nr_zones = build_zonerefs_node(NODE_DATA(node), zonerefs);
+               zonerefs += nr_zones;
        }
 
-       zonelist->_zonerefs[j].zone = NULL;
-       zonelist->_zonerefs[j].zone_idx = 0;
+       zonerefs->zone = NULL;
+       zonerefs->zone_idx = 0;
 }
 
 #endif /* CONFIG_NUMA */