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>

2 files changed, 54 insertions, 24 deletions

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index e865d51f1c74..e1c6064cb6c7 100644
--- a/include/linux/gfp.h
+++ b/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
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 451eaa13bc28..d5c33a0b89e9 100644
--- a/include/linux/mmzone.h
+++ b/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