mm: filter based on a nodemask as well as a gfp_mask

The MPOL_BIND policy creates a zonelist that is used for allocations
controlled by that mempolicy.  As the per-node zonelist is already being
filtered based on a zone id, this patch adds a version of __alloc_pages() that
takes a nodemask for further filtering.  This eliminates the need for
MPOL_BIND to create a custom zonelist.

A positive benefit of this is that allocations using MPOL_BIND now use the
local node's distance-ordered zonelist instead of a custom node-id-ordered
zonelist.  I.e., pages will be allocated from the closest allowed node with
available memory.

[Lee.Schermerhorn@hp.com: Mempolicy: update stale documentation and comments]
[Lee.Schermerhorn@hp.com: Mempolicy: make dequeue_huge_page_vma() obey MPOL_BIND nodemask]
[Lee.Schermerhorn@hp.com: Mempolicy: make dequeue_huge_page_vma() obey MPOL_BIND nodemask rework]
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: 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>

Documentation/vm/numa_memory_policy.txt

@@ -182,14 +182,9 @@ Components of Memory Policies
 	    The Default mode does not use the optional set of nodes.
 
 	MPOL_BIND:  This mode specifies that memory must come from the
-	set of nodes specified by the policy.
-
-	    The memory policy APIs do not specify an order in which the nodes
-	    will be searched.  However, unlike "local allocation", the Bind
-	    policy does not consider the distance between the nodes.  Rather,
-	    allocations will fallback to the nodes specified by the policy in
-	    order of numeric node id.  Like everything in Linux, this is subject
-	    to change.
+	set of nodes specified by the policy.  Memory will be allocated from
+	the node in the set with sufficient free memory that is closest to
+	the node where the allocation takes place.
 
 	MPOL_PREFERRED:  This mode specifies that the allocation should be
 	attempted from the single node specified in the policy.  If that

fs/buffer.c

@@ -360,16 +360,17 @@ void invalidate_bdev(struct block_device *bdev)
  */
 static void free_more_memory(void)
 {
-	struct zoneref *zrefs;
+	struct zone *zone;
 	int nid;
 
 	wakeup_pdflush(1024);
 	yield();
 
 	for_each_online_node(nid) {
-		zrefs = first_zones_zonelist(node_zonelist(nid, GFP_NOFS),
-						gfp_zone(GFP_NOFS));
-		if (zrefs->zone)
+		(void)first_zones_zonelist(node_zonelist(nid, GFP_NOFS),
+						gfp_zone(GFP_NOFS), NULL,
+						&zone);
+		if (zone)
 			try_to_free_pages(node_zonelist(nid, GFP_NOFS), 0,
 						GFP_NOFS);
 	}

include/linux/cpuset.h

@@ -26,7 +26,7 @@ extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
 #define cpuset_current_mems_allowed (current->mems_allowed)
 void cpuset_init_current_mems_allowed(void);
 void cpuset_update_task_memory_state(void);
-int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl);
+int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask);
 
 extern int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask);
 extern int __cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask);
@@ -103,7 +103,7 @@ static inline nodemask_t cpuset_mems_allowed(struct task_struct *p)
 static inline void cpuset_init_current_mems_allowed(void) {}
 static inline void cpuset_update_task_memory_state(void) {}
 
-static inline int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl)
+static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask)
 {
 	return 1;
 }

include/linux/gfp.h

@@ -182,6 +182,10 @@ static inline void arch_alloc_page(struct page *page, int order) { }
 
 extern struct page *__alloc_pages(gfp_t, unsigned int, struct zonelist *);
 
+extern struct page *
+__alloc_pages_nodemask(gfp_t, unsigned int,
+				struct zonelist *, nodemask_t *nodemask);
+
 static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
 						unsigned int order)
 {

include/linux/mempolicy.h

@@ -54,19 +54,20 @@ struct mm_struct;
  * mmap_sem.
  *
  * Freeing policy:
- * When policy is MPOL_BIND v.zonelist is kmalloc'ed and must be kfree'd.
- * All other policies don't have any external state. mpol_free() handles this.
+ * Mempolicy objects are reference counted.  A mempolicy will be freed when
+ * mpol_free() decrements the reference count to zero.
  *
  * Copying policy objects:
- * For MPOL_BIND the zonelist must be always duplicated. mpol_clone() does this.
+ * mpol_copy() allocates a new mempolicy and copies the specified mempolicy
+ * to the new storage.  The reference count of the new object is initialized
+ * to 1, representing the caller of mpol_copy().
  */
 struct mempolicy {
 	atomic_t refcnt;
 	short policy; 	/* See MPOL_* above */
 	union {
-		struct zonelist  *zonelist;	/* bind */
 		short 		 preferred_node; /* preferred */
-		nodemask_t	 nodes;		/* interleave */
+		nodemask_t	 nodes;		/* interleave/bind */
 		/* undefined for default */
 	} v;
 	nodemask_t cpuset_mems_allowed;	/* mempolicy relative to these nodes */
@@ -151,7 +152,8 @@ extern void mpol_fix_fork_child_flag(struct task_struct *p);
 
 extern struct mempolicy default_policy;
 extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
-		unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol);
+				unsigned long addr, gfp_t gfp_flags,
+				struct mempolicy **mpol, nodemask_t **nodemask);
 extern unsigned slab_node(struct mempolicy *policy);
 
 extern enum zone_type policy_zone;
@@ -239,8 +241,11 @@ 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)
+				unsigned long addr, gfp_t gfp_flags,
+				struct mempolicy **mpol, nodemask_t **nodemask)
 {
+	*mpol = NULL;
+	*nodemask = NULL;
 	return node_zonelist(0, gfp_flags);
 }
 

include/linux/mmzone.h

@@ -749,36 +749,60 @@ static inline int zonelist_node_idx(struct zoneref *zoneref)
 #endif /* CONFIG_NUMA */
 }
 
-static inline void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
-{
-	zoneref->zone = zone;
-	zoneref->zone_idx = zone_idx(zone);
-}
+/**
+ * next_zones_zonelist - Returns the next zone at or below highest_zoneidx within the allowed nodemask using a cursor within a zonelist as a starting point
+ * @z - The cursor used as a starting point for the search
+ * @highest_zoneidx - The zone index of the highest zone to return
+ * @nodes - An optional nodemask to filter the zonelist with
+ * @zone - The first suitable zone found is returned via this parameter
+ *
+ * This function returns the next zone at or below a given zone index that is
+ * within the allowed nodemask using a cursor as the starting point for the
+ * search. The zoneref returned is a cursor that is used as the next starting
+ * point for future calls to next_zones_zonelist().
+ */
+struct zoneref *next_zones_zonelist(struct zoneref *z,
+					enum zone_type highest_zoneidx,
+					nodemask_t *nodes,
+					struct zone **zone);
 
-/* Returns the first zone at or below highest_zoneidx in a zonelist */
+/**
+ * first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist
+ * @zonelist - The zonelist to search for a suitable zone
+ * @highest_zoneidx - The zone index of the highest zone to return
+ * @nodes - An optional nodemask to filter the zonelist with
+ * @zone - The first suitable zone found is returned via this parameter
+ *
+ * This function returns the first zone at or below a given zone index that is
+ * within the allowed nodemask. The zoneref returned is a cursor that can be
+ * used to iterate the zonelist with next_zones_zonelist. The cursor should
+ * not be used by the caller as it does not match the value of the zone
+ * returned.
+ */
 static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
-					enum zone_type highest_zoneidx)
+					enum zone_type highest_zoneidx,
+					nodemask_t *nodes,
+					struct zone **zone)
 {
-	struct zoneref *z;
-
-	/* Find the first suitable zone to use for the allocation */
-	z = zonelist->_zonerefs;
-	while (zonelist_zone_idx(z) > highest_zoneidx)
-		z++;
-
-	return z;
+	return next_zones_zonelist(zonelist->_zonerefs, highest_zoneidx, nodes,
+								zone);
 }
 
-/* Returns the next zone at or below highest_zoneidx in a zonelist */
-static inline struct zoneref *next_zones_zonelist(struct zoneref *z,
-					enum zone_type highest_zoneidx)
-{
-	/* Find the next suitable zone to use for the allocation */
-	while (zonelist_zone_idx(z) > highest_zoneidx)
-		z++;
-
-	return z;
-}
+/**
+ * for_each_zone_zonelist_nodemask - helper macro to iterate over valid zones in a zonelist at or below a given zone index and within a nodemask
+ * @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
+ * @nodemask - Nodemask allowed by the allocator
+ *
+ * This iterator iterates though all zones at or below a given zone index and
+ * within a given nodemask
+ */
+#define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \
+	for (z = first_zones_zonelist(zlist, highidx, nodemask, &zone);	\
+		zone;							\
+		z = next_zones_zonelist(z, highidx, nodemask, &zone))	\
 
 /**
  * for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index
@@ -790,11 +814,7 @@ static inline struct zoneref *next_zones_zonelist(struct zoneref *z,
  * 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 = zonelist_zone(z++);	\
-		zone;							\
-		z = next_zones_zonelist(z, highidx),			\
-					zone = zonelist_zone(z++))
+	for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, NULL)
 
 #ifdef CONFIG_SPARSEMEM
 #include <asm/sparsemem.h>

kernel/cpuset.c

@@ -1958,22 +1958,14 @@ nodemask_t cpuset_mems_allowed(struct task_struct *tsk)
 }
 
 /**
- * cpuset_zonelist_valid_mems_allowed - check zonelist vs. curremt mems_allowed
- * @zl: the zonelist to be checked
+ * cpuset_nodemask_valid_mems_allowed - check nodemask vs. curremt mems_allowed
+ * @nodemask: the nodemask to be checked
  *
- * Are any of the nodes on zonelist zl allowed in current->mems_allowed?
+ * Are any of the nodes in the nodemask allowed in current->mems_allowed?
  */
-int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl)
+int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask)
 {
-	int i;
-
-	for (i = 0; zl->_zonerefs[i].zone; i++) {
-		int nid = zonelist_node_idx(&zl->_zonerefs[i]);
-
-		if (node_isset(nid, current->mems_allowed))
-			return 1;
-	}
-	return 0;
+	return nodes_intersects(*nodemask, current->mems_allowed);
 }
 
 /*

mm/hugetlb.c

@@ -95,12 +95,14 @@ static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma,
 	int nid;
 	struct page *page = NULL;
 	struct mempolicy *mpol;
+	nodemask_t *nodemask;
 	struct zonelist *zonelist = huge_zonelist(vma, address,
-					htlb_alloc_mask, &mpol);
+					htlb_alloc_mask, &mpol, &nodemask);
 	struct zone *zone;
 	struct zoneref *z;
 
-	for_each_zone_zonelist(zone, z, zonelist, MAX_NR_ZONES - 1) {
+	for_each_zone_zonelist_nodemask(zone, z, zonelist,
+						MAX_NR_ZONES - 1, nodemask) {
 		nid = zone_to_nid(zone);
 		if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask) &&
 		    !list_empty(&hugepage_freelists[nid])) {

mm/mmzone.c

@@ -42,3 +42,33 @@ struct zone *next_zone(struct zone *zone)
 	return zone;
 }
 
+static inline int zref_in_nodemask(struct zoneref *zref, nodemask_t *nodes)
+{
+#ifdef CONFIG_NUMA
+	return node_isset(zonelist_node_idx(zref), *nodes);
+#else
+	return 1;
+#endif /* CONFIG_NUMA */
+}
+
+/* Returns the next zone at or below highest_zoneidx in a zonelist */
+struct zoneref *next_zones_zonelist(struct zoneref *z,
+					enum zone_type highest_zoneidx,
+					nodemask_t *nodes,
+					struct zone **zone)
+{
+	/*
+	 * Find the next suitable zone to use for the allocation.
+	 * Only filter based on nodemask if it's set
+	 */
+	if (likely(nodes == NULL))
+		while (zonelist_zone_idx(z) > highest_zoneidx)
+			z++;
+	else
+		while (zonelist_zone_idx(z) > highest_zoneidx ||
+				(z->zone && !zref_in_nodemask(z, nodes)))
+			z++;
+
+	*zone = zonelist_zone(z++);
+	return z;
+}

mm/page_alloc.c

@@ -1377,7 +1377,7 @@ static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
  * a page.
  */
 static struct page *
-get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
+get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order,
 		struct zonelist *zonelist, int high_zoneidx, int alloc_flags)
 {
 	struct zoneref *z;
@@ -1388,16 +1388,17 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
 	int zlc_active = 0;		/* set if using zonelist_cache */
 	int did_zlc_setup = 0;		/* just call zlc_setup() one time */
 
-	z = first_zones_zonelist(zonelist, high_zoneidx);
-	classzone_idx = zonelist_zone_idx(z);
-	preferred_zone = zonelist_zone(z);
+	(void)first_zones_zonelist(zonelist, high_zoneidx, nodemask,
+							&preferred_zone);
+	classzone_idx = zone_idx(preferred_zone);
 
 zonelist_scan:
 	/*
 	 * Scan zonelist, looking for a zone with enough free.
 	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
 	 */
-	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
+	for_each_zone_zonelist_nodemask(zone, z, zonelist,
+						high_zoneidx, nodemask) {
 		if (NUMA_BUILD && zlc_active &&
 			!zlc_zone_worth_trying(zonelist, z, allowednodes))
 				continue;
@@ -1447,9 +1448,9 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
 /*
  * This is the 'heart' of the zoned buddy allocator.
  */
-struct page *
-__alloc_pages(gfp_t gfp_mask, unsigned int order,
-		struct zonelist *zonelist)
+static struct page *
+__alloc_pages_internal(gfp_t gfp_mask, unsigned int order,
+			struct zonelist *zonelist, nodemask_t *nodemask)
 {
 	const gfp_t wait = gfp_mask & __GFP_WAIT;
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
@@ -1478,7 +1479,7 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 		return NULL;
 	}
 
-	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
+	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
 			zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET);
 	if (page)
 		goto got_pg;
@@ -1523,7 +1524,7 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 	 * 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,
+	page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
 						high_zoneidx, alloc_flags);
 	if (page)
 		goto got_pg;
@@ -1536,7 +1537,7 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 		if (!(gfp_mask & __GFP_NOMEMALLOC)) {
 nofail_alloc:
 			/* go through the zonelist yet again, ignoring mins */
-			page = get_page_from_freelist(gfp_mask, order,
+			page = get_page_from_freelist(gfp_mask, nodemask, order,
 				zonelist, high_zoneidx, ALLOC_NO_WATERMARKS);
 			if (page)
 				goto got_pg;
@@ -1571,7 +1572,7 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 		drain_all_pages();
 
 	if (likely(did_some_progress)) {
-		page = get_page_from_freelist(gfp_mask, order,
+		page = get_page_from_freelist(gfp_mask, nodemask, order,
 					zonelist, high_zoneidx, alloc_flags);
 		if (page)
 			goto got_pg;
@@ -1587,8 +1588,9 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 		 * a parallel oom killing, we must fail if we're still
 		 * under heavy pressure.
 		 */
-		page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
-			zonelist, high_zoneidx, ALLOC_WMARK_HIGH|ALLOC_CPUSET);
+		page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask,
+			order, zonelist, high_zoneidx,
+			ALLOC_WMARK_HIGH|ALLOC_CPUSET);
 		if (page) {
 			clear_zonelist_oom(zonelist, gfp_mask);
 			goto got_pg;
@@ -1637,6 +1639,20 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 	return page;
 }
 
+struct page *
+__alloc_pages(gfp_t gfp_mask, unsigned int order,
+		struct zonelist *zonelist)
+{
+	return __alloc_pages_internal(gfp_mask, order, zonelist, NULL);
+}
+
+struct page *
+__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
+		struct zonelist *zonelist, nodemask_t *nodemask)
+{
+	return __alloc_pages_internal(gfp_mask, order, zonelist, nodemask);
+}
+
 EXPORT_SYMBOL(__alloc_pages);
 
 /*
@@ -1880,6 +1896,12 @@ void show_free_areas(void)
 	show_swap_cache_info();
 }
 
+static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
+{
+	zoneref->zone = zone;
+	zoneref->zone_idx = zone_idx(zone);
+}
+
 /*
  * Builds allocation fallback zone lists.
  *