mm: introduce node_zonelist() for accessing the zonelist for a GFP mask

Introduce a node_zonelist() helper function.  It is used to lookup the
appropriate zonelist given a node and a GFP mask.  The patch on its own is a
cleanup but it helps clarify parts of the two-zonelist-per-node patchset.  If
necessary, it can be merged with the next patch in this set without problems.

Reviewed-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
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>

drivers/char/sysrq.c

@@ -271,8 +271,7 @@ static struct sysrq_key_op sysrq_term_op = {
 
 static void moom_callback(struct work_struct *ignored)
 {
-	out_of_memory(&NODE_DATA(0)->node_zonelists[ZONE_NORMAL],
+	out_of_memory(node_zonelist(0, GFP_KERNEL), GFP_KERNEL, 0);
-			GFP_KERNEL, 0);
 }
 
 static DECLARE_WORK(moom_work, moom_callback);

fs/buffer.c

@@ -361,13 +361,13 @@ void invalidate_bdev(struct block_device *bdev)
 static void free_more_memory(void)
 {
 	struct zonelist *zonelist;
-	pg_data_t *pgdat;
+	int nid;
 
 	wakeup_pdflush(1024);
 	yield();
 
-	for_each_online_pgdat(pgdat) {
+	for_each_online_node(nid) {
-		zonelist = &pgdat->node_zonelists[gfp_zone(GFP_NOFS)];
+		zonelist = node_zonelist(nid, GFP_NOFS);
 		if (zonelist->zones[0])
 			try_to_free_pages(zonelist, 0, GFP_NOFS);
 	}

include/linux/gfp.h

@@ -154,10 +154,15 @@ static inline enum zone_type gfp_zone(gfp_t flags)
 /*
  * 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.
  *
  * 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);
+}
 
 #ifndef HAVE_ARCH_FREE_PAGE
 static inline void arch_free_page(struct page *page, int order) { }
@@ -178,8 +183,7 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
 	if (nid < 0)
 		nid = numa_node_id();
 
-	return __alloc_pages(gfp_mask, order,
+	return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask));
-		NODE_DATA(nid)->node_zonelists + gfp_zone(gfp_mask));
 }
 
 #ifdef CONFIG_NUMA

include/linux/mempolicy.h

@@ -241,7 +241,7 @@ static inline void mpol_fix_fork_child_flag(struct task_struct *p)
 static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma,
  		unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol)
 {
-	return NODE_DATA(0)->node_zonelists + gfp_zone(gfp_flags);
+	return node_zonelist(0, gfp_flags);
 }
 
 static inline int do_migrate_pages(struct mm_struct *mm,

mm/mempolicy.c

@@ -1183,7 +1183,7 @@ static struct zonelist *zonelist_policy(gfp_t gfp, struct mempolicy *policy)
 		nd = 0;
 		BUG();
 	}
-	return NODE_DATA(nd)->node_zonelists + gfp_zone(gfp);
+	return node_zonelist(nd, gfp);
 }
 
 /* Do dynamic interleaving for a process */
@@ -1299,7 +1299,7 @@ struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr,
 		if (unlikely(pol != &default_policy &&
 				pol != current->mempolicy))
 			__mpol_free(pol);	/* finished with pol */
-		return NODE_DATA(nid)->node_zonelists + gfp_zone(gfp_flags);
+		return node_zonelist(nid, gfp_flags);
 	}
 
 	zl = zonelist_policy(GFP_HIGHUSER, pol);
@@ -1321,7 +1321,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
 	struct zonelist *zl;
 	struct page *page;
 
-	zl = NODE_DATA(nid)->node_zonelists + gfp_zone(gfp);
+	zl = node_zonelist(nid, gfp);
 	page = __alloc_pages(gfp, order, zl);
 	if (page && page_zone(page) == zl->zones[0])
 		inc_zone_page_state(page, NUMA_INTERLEAVE_HIT);

mm/page_alloc.c

@@ -1713,10 +1713,9 @@ EXPORT_SYMBOL(free_pages);
 static unsigned int nr_free_zone_pages(int offset)
 {
 	/* Just pick one node, since fallback list is circular */
-	pg_data_t *pgdat = NODE_DATA(numa_node_id());
 	unsigned int sum = 0;
 
-	struct zonelist *zonelist = pgdat->node_zonelists + offset;
+	struct zonelist *zonelist = node_zonelist(numa_node_id(), GFP_KERNEL);
 	struct zone **zonep = zonelist->zones;
 	struct zone *zone;
 

mm/slab.c

@@ -3249,8 +3249,7 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
 	if (flags & __GFP_THISNODE)
 		return NULL;
 
-	zonelist = &NODE_DATA(slab_node(current->mempolicy))
+	zonelist = node_zonelist(slab_node(current->mempolicy), flags);
-			->node_zonelists[gfp_zone(flags)];
 	local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);
 
 retry:

mm/slub.c

@@ -1309,8 +1309,7 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
 			get_cycles() % 1024 > s->remote_node_defrag_ratio)
 		return NULL;
 
-	zonelist = &NODE_DATA(
+	zonelist = node_zonelist(slab_node(current->mempolicy), flags);
-		slab_node(current->mempolicy))->node_zonelists[gfp_zone(flags)];
 	for (z = zonelist->zones; *z; z++) {
 		struct kmem_cache_node *n;