From 156cdd5548ced1c9102ecadf07e08bb2d2aabd68 Mon Sep 17 00:00:00 2001
From: Mel Gorman <mel@csn.ul.ie>
Date: Wed, 22 Aug 2007 14:02:05 -0700
Subject: [PATCH] --- yaml --- r: 64271 b: refs/heads/master c:
 b377fd3982ad957c796758a90e2988401a884241 h: refs/heads/master i:   64269:
 6bf20b91584649e75642a50531c452cfa40c280f   64267:
 7f8fba42161f7d469ebb9ab6e8054b13886180ed   64263:
 df7a7792fc4f65845d3a3e650cd21b76aebf0e31   64255:
 4024b621af56498fcaba69dcce0aabcd7ce79757 v: v3

---
 [refs]                          |  2 +-
 trunk/include/linux/mempolicy.h |  2 +-
 trunk/include/linux/mmzone.h    | 18 ++++++++++++++++++
 trunk/mm/mempolicy.c            |  2 +-
 trunk/mm/page_alloc.c           | 13 +++++++++++++
 5 files changed, 34 insertions(+), 3 deletions(-)

diff --git a/[refs] b/[refs]
index fcef18377436..d1d3448d2a0d 100644
--- a/[refs]
+++ b/[refs]
@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 8e92f21ba3ea3f54e4be062b87ef9fc4af2d33e2
+refs/heads/master: b377fd3982ad957c796758a90e2988401a884241
diff --git a/trunk/include/linux/mempolicy.h b/trunk/include/linux/mempolicy.h
index e147cf50529f..5bdd656e88cf 100644
--- a/trunk/include/linux/mempolicy.h
+++ b/trunk/include/linux/mempolicy.h
@@ -166,7 +166,7 @@ extern enum zone_type policy_zone;
 
 static inline void check_highest_zone(enum zone_type k)
 {
-	if (k > policy_zone)
+	if (k > policy_zone && k != ZONE_MOVABLE)
 		policy_zone = k;
 }
 
diff --git a/trunk/include/linux/mmzone.h b/trunk/include/linux/mmzone.h
index 3ea68cd3b61f..4e5627379b09 100644
--- a/trunk/include/linux/mmzone.h
+++ b/trunk/include/linux/mmzone.h
@@ -410,6 +410,24 @@ 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;
diff --git a/trunk/mm/mempolicy.c b/trunk/mm/mempolicy.c
index 71b84b45154a..172abffeb2e3 100644
--- a/trunk/mm/mempolicy.c
+++ b/trunk/mm/mempolicy.c
@@ -149,7 +149,7 @@ static struct zonelist *bind_zonelist(nodemask_t *nodes)
 	   lower zones etc. Avoid empty zones because the memory allocator
 	   doesn't like them. If you implement node hot removal you
 	   have to fix that. */
-	k = policy_zone;
+	k = MAX_NR_ZONES - 1;
 	while (1) {
 		for_each_node_mask(nd, *nodes) { 
 			struct zone *z = &NODE_DATA(nd)->node_zones[k];
diff --git a/trunk/mm/page_alloc.c b/trunk/mm/page_alloc.c
index 3da85b81dabb..6427653023aa 100644
--- a/trunk/mm/page_alloc.c
+++ b/trunk/mm/page_alloc.c
@@ -1157,6 +1157,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
 	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 */
 
 zonelist_scan:
 	/*
@@ -1166,6 +1167,18 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
 	z = zonelist->zones;
 
 	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;
+		}
+
 		if (NUMA_BUILD && zlc_active &&
 			!zlc_zone_worth_trying(zonelist, z, allowednodes))
 				continue;