summaryrefslogtreecommitdiffstats
path: root/include/linux/mmzone.h
diff options
context:
space:
mode:
authorMel Gorman <mel@csn.ul.ie>2008-04-28 02:12:18 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2008-04-28 08:58:19 -0700
commit19770b32609b6bf97a3dece2529089494cbfc549 (patch)
tree3b5922d1b20aabdf929bde9309f323841717747a /include/linux/mmzone.h
parentdd1a239f6f2d4d3eedd318583ec319aa145b324c (diff)
downloadop-kernel-dev-19770b32609b6bf97a3dece2529089494cbfc549.zip
op-kernel-dev-19770b32609b6bf97a3dece2529089494cbfc549.tar.gz
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>
Diffstat (limited to 'include/linux/mmzone.h')
-rw-r--r--include/linux/mmzone.h80
1 files changed, 50 insertions, 30 deletions
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index d34b4c2..498d6ce 100644
--- a/include/linux/mmzone.h
+++ b/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>
OpenPOWER on IntegriCloud