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 <[email protected]>
Acked-by: Christoph Lameter <[email protected]>
Signed-off-by: Lee Schermerhorn <[email protected]>
Cc: KAMEZAWA Hiroyuki <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Christoph Lameter <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Nick Piggin <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

arch/parisc/mm/init.c

@@ -603,15 +603,18 @@ void show_mem(void)
 #ifdef CONFIG_DISCONTIGMEM
 	{
 		struct zonelist *zl;
-		int i, j, k;
+		int i, j;
 
 		for (i = 0; i < npmem_ranges; i++) {
+			zl = node_zonelist(i);
 			for (j = 0; j < MAX_NR_ZONES; j++) {
-				zl = NODE_DATA(i)->node_zonelists + j;
+				struct zone **z;
+				struct zone *zone;
 
 				printk("Zone list for zone %d on node %d: ", j, i);
-				for (k = 0; zl->zones[k] != NULL; k++) 
-					printk("[%d/%s] ", zone_to_nid(zl->zones[k]), zl->zones[k]->name);
+				for_each_zone_zonelist(zone, z, zl, j)
+					printk("[%d/%s] ", zone_to_nid(zone),
+								zone->name);
 				printk("\n");
 			}
 		}

fs/buffer.c

@@ -360,16 +360,18 @@ void invalidate_bdev(struct block_device *bdev)
  */
 static void free_more_memory(void)
 {
-	struct zonelist *zonelist;
+	struct zone **zones;
 	int nid;
 
 	wakeup_pdflush(1024);
 	yield();
 
 	for_each_online_node(nid) {
-		zonelist = node_zonelist(nid, GFP_NOFS);
-		if (zonelist->zones[0])
-			try_to_free_pages(zonelist, 0, GFP_NOFS);
+		zones = first_zones_zonelist(node_zonelist(nid, GFP_NOFS),
+						gfp_zone(GFP_NOFS));
+		if (*zones)
+			try_to_free_pages(node_zonelist(nid, GFP_NOFS), 0,
+						GFP_NOFS);
 	}
 }
 

include/linux/gfp.h

@@ -151,17 +151,26 @@ static inline enum zone_type gfp_zone(gfp_t flags)
  * virtual kernel addresses to the allocated page(s).
  */
 
+static inline int gfp_zonelist(gfp_t flags)
+{
+	if (NUMA_BUILD && unlikely(flags & __GFP_THISNODE))
+		return 1;
+
+	return 0;
+}
+
 /*
  * We get the zone list from the current node and the gfp_mask.
  * This zone list contains a maximum of MAXNODES*MAX_NR_ZONES zones.
- * There are many zonelists per node, two for each active zone.
+ * There are two zonelists per node, one for all zones with memory and
+ * one containing just zones from the node the zonelist belongs to.
  *
  * For the normal case of non-DISCONTIGMEM systems the NODE_DATA() gets
  * optimized to &contig_page_data at compile-time.
  */
 static inline struct zonelist *node_zonelist(int nid, gfp_t flags)
 {
-	return NODE_DATA(nid)->node_zonelists + gfp_zone(flags);
+	return NODE_DATA(nid)->node_zonelists + gfp_zonelist(flags);
 }
 
 #ifndef HAVE_ARCH_FREE_PAGE

include/linux/mmzone.h

@@ -393,10 +393,10 @@ static inline int zone_is_oom_locked(const struct zone *zone)
  * The NUMA zonelists are doubled becausse we need zonelists that restrict the
  * allocations to a single node for GFP_THISNODE.
  *
- * [0 .. MAX_NR_ZONES -1] 		: Zonelists with fallback
- * [MAZ_NR_ZONES ... MAZ_ZONELISTS -1]  : No fallback (GFP_THISNODE)
+ * [0]	: Zonelist with fallback
+ * [1]	: No fallback (GFP_THISNODE)
  */
-#define MAX_ZONELISTS (2 * MAX_NR_ZONES)
+#define MAX_ZONELISTS 2
 
 
 /*
@@ -464,7 +464,7 @@ struct zonelist_cache {
 	unsigned long last_full_zap;		/* when last zap'd (jiffies) */
 };
 #else
-#define MAX_ZONELISTS MAX_NR_ZONES
+#define MAX_ZONELISTS 1
 struct zonelist_cache;
 #endif
 
@@ -486,24 +486,6 @@ struct zonelist {
 #endif
 };
 
-#ifdef CONFIG_NUMA
-/*
- * Only custom zonelists like MPOL_BIND need to be filtered as part of
- * policies. As described in the comment for struct zonelist_cache, these
- * zonelists will not have a zlcache so zlcache_ptr will not be set. Use
- * that to determine if the zonelists needs to be filtered or not.
- */
-static inline int alloc_should_filter_zonelist(struct zonelist *zonelist)
-{
-	return !zonelist->zlcache_ptr;
-}
-#else
-static inline int alloc_should_filter_zonelist(struct zonelist *zonelist)
-{
-	return 0;
-}
-#endif /* CONFIG_NUMA */
-
 #ifdef CONFIG_ARCH_POPULATES_NODE_MAP
 struct node_active_region {
 	unsigned long start_pfn;
@@ -731,6 +713,45 @@ extern struct zone *next_zone(struct zone *zone);
 	     zone;					\
 	     zone = next_zone(zone))
 
+/* Returns the first zone at or below highest_zoneidx in a zonelist */
+static inline struct zone **first_zones_zonelist(struct zonelist *zonelist,
+					enum zone_type highest_zoneidx)
+{
+	struct zone **z;
+
+	/* Find the first suitable zone to use for the allocation */
+	z = zonelist->zones;
+	while (*z && zone_idx(*z) > highest_zoneidx)
+		z++;
+
+	return z;
+}
+
+/* Returns the next zone at or below highest_zoneidx in a zonelist */
+static inline struct zone **next_zones_zonelist(struct zone **z,
+					enum zone_type highest_zoneidx)
+{
+	/* Find the next suitable zone to use for the allocation */
+	while (*z && zone_idx(*z) > highest_zoneidx)
+		z++;
+
+	return z;
+}
+
+/**
+ * for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index
+ * @zone - The current zone in the iterator
+ * @z - The current pointer within zonelist->zones being iterated
+ * @zlist - The zonelist being iterated
+ * @highidx - The zone index of the highest zone to return
+ *
+ * This iterator iterates though all zones at or below a given zone index.
+ */
+#define for_each_zone_zonelist(zone, z, zlist, highidx) \
+	for (z = first_zones_zonelist(zlist, highidx), zone = *z++;	\
+		zone;							\
+		z = next_zones_zonelist(z, highidx), zone = *z++)
+
 #ifdef CONFIG_SPARSEMEM
 #include <asm/sparsemem.h>
 #endif

mm/hugetlb.c

@@ -97,11 +97,11 @@ static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma,
 	struct mempolicy *mpol;
 	struct zonelist *zonelist = huge_zonelist(vma, address,
 					htlb_alloc_mask, &mpol);
-	struct zone **z;
+	struct zone *zone, **z;
 
-	for (z = zonelist->zones; *z; z++) {
-		nid = zone_to_nid(*z);
-		if (cpuset_zone_allowed_softwall(*z, htlb_alloc_mask) &&
+	for_each_zone_zonelist(zone, z, zonelist, MAX_NR_ZONES - 1) {
+		nid = zone_to_nid(zone);
+		if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask) &&
 		    !list_empty(&hugepage_freelists[nid])) {
 			page = list_entry(hugepage_freelists[nid].next,
 					  struct page, lru);

mm/oom_kill.c

@@ -175,12 +175,14 @@ static inline enum oom_constraint constrained_alloc(struct zonelist *zonelist,
 						    gfp_t gfp_mask)
 {
 #ifdef CONFIG_NUMA
+	struct zone *zone;
 	struct zone **z;
+	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	nodemask_t nodes = node_states[N_HIGH_MEMORY];
 
-	for (z = zonelist->zones; *z; z++)
-		if (cpuset_zone_allowed_softwall(*z, gfp_mask))
-			node_clear(zone_to_nid(*z), nodes);
+	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
+		if (cpuset_zone_allowed_softwall(zone, gfp_mask))
+			node_clear(zone_to_nid(zone), nodes);
 		else
 			return CONSTRAINT_CPUSET;