mm: use two zonelist that are filtered by GFP mask

Currently a node has two sets of zonelists, one for each zone type in the
system and a second set for GFP_THISNODE allocations.  Based on the zones
allowed by a gfp mask, one of these zonelists is selected.  All of these
zonelists consume memory and occupy cache lines.

This patch replaces the multiple zonelists per-node with two zonelists.  The
first contains all populated zones in the system, ordered by distance, for
fallback allocations when the target/preferred node has no free pages.  The
second contains all populated zones in the node suitable for GFP_THISNODE
allocations.

An iterator macro is introduced called for_each_zone_zonelist() that interates
through each zone allowed by the GFP flags in the selected zonelist.

Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 73 insertions, 97 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 187efd4..4ccb865 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1378,42 +1378,29 @@ static void zlc_mark_zone_full(struct zonelist *zonelist, struct zone **z)
  */
 static struct page *
 get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
-		struct zonelist *zonelist, int alloc_flags)
+		struct zonelist *zonelist, int high_zoneidx, int alloc_flags)
 {
 	struct zone **z;
 	struct page *page = NULL;
-	int classzone_idx = zone_idx(zonelist->zones[0]);
+	int classzone_idx;
 	struct zone *zone, *preferred_zone;
 	nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */
 	int zlc_active = 0;		/* set if using zonelist_cache */
 	int did_zlc_setup = 0;		/* just call zlc_setup() one time */
-	enum zone_type highest_zoneidx = -1; /* Gets set for policy zonelists */
+
+	z = first_zones_zonelist(zonelist, high_zoneidx);
+	classzone_idx = zone_idx(*z);
+	preferred_zone = *z;
 
 zonelist_scan:
 	/*
 	 * Scan zonelist, looking for a zone with enough free.
 	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
 	 */
-	z = zonelist->zones;
-	preferred_zone = *z;
-
-	do {
-		/*
-		 * In NUMA, this could be a policy zonelist which contains
-		 * zones that may not be allowed by the current gfp_mask.
-		 * Check the zone is allowed by the current flags
-		 */
-		if (unlikely(alloc_should_filter_zonelist(zonelist))) {
-			if (highest_zoneidx == -1)
-				highest_zoneidx = gfp_zone(gfp_mask);
-			if (zone_idx(*z) > highest_zoneidx)
-				continue;
-		}
-
+	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
 		if (NUMA_BUILD && zlc_active &&
 			!zlc_zone_worth_trying(zonelist, z, allowednodes))
 				continue;
-		zone = *z;
 		if ((alloc_flags & ALLOC_CPUSET) &&
 			!cpuset_zone_allowed_softwall(zone, gfp_mask))
 				goto try_next_zone;
@@ -1447,7 +1434,7 @@ try_next_zone:
 			zlc_active = 1;
 			did_zlc_setup = 1;
 		}
-	} while (*(++z) != NULL);
+	}
 
 	if (unlikely(NUMA_BUILD && page == NULL && zlc_active)) {
 		/* Disable zlc cache for second zonelist scan */
@@ -1465,6 +1452,7 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 		struct zonelist *zonelist)
 {
 	const gfp_t wait = gfp_mask & __GFP_WAIT;
+	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	struct zone **z;
 	struct page *page;
 	struct reclaim_state reclaim_state;
@@ -1490,7 +1478,7 @@ restart:
 	}
 
 	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
-				zonelist, ALLOC_WMARK_LOW|ALLOC_CPUSET);
+			zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET);
 	if (page)
 		goto got_pg;
 
@@ -1534,7 +1522,8 @@ restart:
 	 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
 	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
 	 */
-	page = get_page_from_freelist(gfp_mask, order, zonelist, alloc_flags);
+	page = get_page_from_freelist(gfp_mask, order, zonelist,
+						high_zoneidx, alloc_flags);
 	if (page)
 		goto got_pg;
 
@@ -1547,7 +1536,7 @@ rebalance:
 nofail_alloc:
 			/* go through the zonelist yet again, ignoring mins */
 			page = get_page_from_freelist(gfp_mask, order,
-				zonelist, ALLOC_NO_WATERMARKS);
+				zonelist, high_zoneidx, ALLOC_NO_WATERMARKS);
 			if (page)
 				goto got_pg;
 			if (gfp_mask & __GFP_NOFAIL) {
@@ -1582,7 +1571,7 @@ nofail_alloc:
 
 	if (likely(did_some_progress)) {
 		page = get_page_from_freelist(gfp_mask, order,
-						zonelist, alloc_flags);
+					zonelist, high_zoneidx, alloc_flags);
 		if (page)
 			goto got_pg;
 	} else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
@@ -1598,7 +1587,7 @@ nofail_alloc:
 		 * under heavy pressure.
 		 */
 		page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
-				zonelist, ALLOC_WMARK_HIGH|ALLOC_CPUSET);
+			zonelist, high_zoneidx, ALLOC_WMARK_HIGH|ALLOC_CPUSET);
 		if (page) {
 			clear_zonelist_oom(zonelist);
 			goto got_pg;
@@ -1713,14 +1702,15 @@ EXPORT_SYMBOL(free_pages);
 
 static unsigned int nr_free_zone_pages(int offset)
 {
+	struct zone **z;
+	struct zone *zone;
+
 	/* Just pick one node, since fallback list is circular */
 	unsigned int sum = 0;
 
 	struct zonelist *zonelist = node_zonelist(numa_node_id(), GFP_KERNEL);
-	struct zone **zonep = zonelist->zones;
-	struct zone *zone;
 
-	for (zone = *zonep++; zone; zone = *zonep++) {
+	for_each_zone_zonelist(zone, z, zonelist, offset) {
 		unsigned long size = zone->present_pages;
 		unsigned long high = zone->pages_high;
 		if (size > high)
@@ -2078,17 +2068,15 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask)
  */
 static void build_zonelists_in_node_order(pg_data_t *pgdat, int node)
 {
-	enum zone_type i;
 	int j;
 	struct zonelist *zonelist;
 
-	for (i = 0; i < MAX_NR_ZONES; i++) {
-		zonelist = pgdat->node_zonelists + i;
-		for (j = 0; zonelist->zones[j] != NULL; j++)
-			;
- 		j = build_zonelists_node(NODE_DATA(node), zonelist, j, i);
-		zonelist->zones[j] = NULL;
-	}
+	zonelist = &pgdat->node_zonelists[0];
+	for (j = 0; zonelist->zones[j] != NULL; j++)
+		;
+	j = build_zonelists_node(NODE_DATA(node), zonelist, j,
+							MAX_NR_ZONES - 1);
+	zonelist->zones[j] = NULL;
 }
 
 /*
@@ -2096,15 +2084,12 @@ static void build_zonelists_in_node_order(pg_data_t *pgdat, int node)
  */
 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;
-	}
+	zonelist = &pgdat->node_zonelists[1];
+	j = build_zonelists_node(pgdat, zonelist, 0, MAX_NR_ZONES - 1);
+	zonelist->zones[j] = NULL;
 }
 
 /*
@@ -2117,27 +2102,24 @@ static int node_order[MAX_NUMNODES];
 
 static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes)
 {
-	enum zone_type i;
 	int pos, j, node;
 	int zone_type;		/* needs to be signed */
 	struct zone *z;
 	struct zonelist *zonelist;
 
-	for (i = 0; i < MAX_NR_ZONES; i++) {
-		zonelist = pgdat->node_zonelists + i;
-		pos = 0;
-		for (zone_type = i; zone_type >= 0; zone_type--) {
-			for (j = 0; j < nr_nodes; j++) {
-				node = node_order[j];
-				z = &NODE_DATA(node)->node_zones[zone_type];
-				if (populated_zone(z)) {
-					zonelist->zones[pos++] = z;
-					check_highest_zone(zone_type);
-				}
+	zonelist = &pgdat->node_zonelists[0];
+	pos = 0;
+	for (zone_type = MAX_NR_ZONES - 1; zone_type >= 0; zone_type--) {
+		for (j = 0; j < nr_nodes; j++) {
+			node = node_order[j];
+			z = &NODE_DATA(node)->node_zones[zone_type];
+			if (populated_zone(z)) {
+				zonelist->zones[pos++] = z;
+				check_highest_zone(zone_type);
 			}
 		}
-		zonelist->zones[pos] = NULL;
 	}
+	zonelist->zones[pos] = NULL;
 }
 
 static int default_zonelist_order(void)
@@ -2264,19 +2246,15 @@ static void build_zonelists(pg_data_t *pgdat)
 /* Construct the zonelist performance cache - see further mmzone.h */
 static void build_zonelist_cache(pg_data_t *pgdat)
 {
-	int i;
-
-	for (i = 0; i < MAX_NR_ZONES; i++) {
-		struct zonelist *zonelist;
-		struct zonelist_cache *zlc;
-		struct zone **z;
+	struct zonelist *zonelist;
+	struct zonelist_cache *zlc;
+	struct zone **z;
 
-		zonelist = pgdat->node_zonelists + i;
-		zonelist->zlcache_ptr = zlc = &zonelist->zlcache;
-		bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
-		for (z = zonelist->zones; *z; z++)
-			zlc->z_to_n[z - zonelist->zones] = zone_to_nid(*z);
-	}
+	zonelist = &pgdat->node_zonelists[0];
+	zonelist->zlcache_ptr = zlc = &zonelist->zlcache;
+	bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
+	for (z = zonelist->zones; *z; z++)
+		zlc->z_to_n[z - zonelist->zones] = zone_to_nid(*z);
 }
 
 
@@ -2290,45 +2268,43 @@ static void set_zonelist_order(void)
 static void build_zonelists(pg_data_t *pgdat)
 {
 	int node, local_node;
-	enum zone_type i,j;
+	enum zone_type j;
+	struct zonelist *zonelist;
 
 	local_node = pgdat->node_id;
-	for (i = 0; i < MAX_NR_ZONES; i++) {
-		struct zonelist *zonelist;
 
-		zonelist = pgdat->node_zonelists + i;
+	zonelist = &pgdat->node_zonelists[0];
+	j = build_zonelists_node(pgdat, zonelist, 0, MAX_NR_ZONES - 1);
 
- 		j = build_zonelists_node(pgdat, zonelist, 0, i);
- 		/*
- 		 * Now we build the zonelist so that it contains the zones
- 		 * of all the other nodes.
- 		 * We don't want to pressure a particular node, so when
- 		 * building the zones for node N, we make sure that the
- 		 * zones coming right after the local ones are those from
- 		 * node N+1 (modulo N)
- 		 */
-		for (node = local_node + 1; node < MAX_NUMNODES; node++) {
-			if (!node_online(node))
-				continue;
-			j = build_zonelists_node(NODE_DATA(node), zonelist, j, i);
-		}
-		for (node = 0; node < local_node; node++) {
-			if (!node_online(node))
-				continue;
-			j = build_zonelists_node(NODE_DATA(node), zonelist, j, i);
-		}
-
-		zonelist->zones[j] = NULL;
+	/*
+	 * Now we build the zonelist so that it contains the zones
+	 * of all the other nodes.
+	 * We don't want to pressure a particular node, so when
+	 * building the zones for node N, we make sure that the
+	 * zones coming right after the local ones are those from
+	 * node N+1 (modulo N)
+	 */
+	for (node = local_node + 1; node < MAX_NUMNODES; node++) {
+		if (!node_online(node))
+			continue;
+		j = build_zonelists_node(NODE_DATA(node), zonelist, j,
+							MAX_NR_ZONES - 1);
 	}
+	for (node = 0; node < local_node; node++) {
+		if (!node_online(node))
+			continue;
+		j = build_zonelists_node(NODE_DATA(node), zonelist, j,
+							MAX_NR_ZONES - 1);
+	}
+
+	zonelist->zones[j] = NULL;
 }
 
 /* non-NUMA variant of zonelist performance cache - just NULL zlcache_ptr */
 static void build_zonelist_cache(pg_data_t *pgdat)
 {
-	int i;
-
-	for (i = 0; i < MAX_NR_ZONES; i++)
-		pgdat->node_zonelists[i].zlcache_ptr = NULL;
+	pgdat->node_zonelists[0].zlcache_ptr = NULL;
+	pgdat->node_zonelists[1].zlcache_ptr = NULL;
 }
 
 #endif	/* CONFIG_NUMA */