[PATCH] linearly index zone->node_zonelists[]

I wonder why we need this bitmask indexing into zone->node_zonelists[]?

We always start with the highest zone and then include all lower zones
if we build zonelists.

Are there really cases where we need allocation from ZONE_DMA or
ZONE_HIGHMEM but not ZONE_NORMAL? It seems that the current implementation
of highest_zone() makes that already impossible.

If we go linear on the index then gfp_zone() == highest_zone() and a lot
of definitions fall by the wayside.

We can now revert back to the use of gfp_zone() in mempolicy.c ;-)

Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

4 files changed, 18 insertions, 75 deletions

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index a0992d392d79..63ab88a36f39 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -12,9 +12,6 @@ struct vm_area_struct;
  *
  * Zone modifiers (see linux/mmzone.h - low three bits)
  *
- * These may be masked by GFP_ZONEMASK to make allocations with this bit
- * set fall back to ZONE_NORMAL.
- *
  * Do not put any conditional on these. If necessary modify the definitions
  * without the underscores and use the consistently. The definitions here may
  * be used in bit comparisons.
@@ -78,14 +75,7 @@ struct vm_area_struct;
 #define GFP_DMA32       __GFP_DMA32
 
 
-static inline int gfp_zone(gfp_t gfp)
-{
-        int zone = GFP_ZONEMASK & (__force int) gfp;
-        BUG_ON(zone >= GFP_ZONETYPES);
-        return zone;
-}
-
-static inline enum zone_type highest_zone(gfp_t flags)
+static inline enum zone_type gfp_zone(gfp_t flags)
 {
         if (flags & __GFP_DMA)
                 return ZONE_DMA;
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 76d33e688593..7fe317164b73 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -137,60 +137,18 @@ enum zone_type {
         MAX_NR_ZONES
 };
 
-
 /*
  * When a memory allocation must conform to specific limitations (such
  * as being suitable for DMA) the caller will pass in hints to the
  * allocator in the gfp_mask, in the zone modifier bits.  These bits
  * are used to select a priority ordered list of memory zones which
- * match the requested limits.  GFP_ZONEMASK defines which bits within
- * the gfp_mask should be considered as zone modifiers.  Each valid
- * combination of the zone modifier bits has a corresponding list
- * of zones (in node_zonelists).  Thus for two zone modifiers there
- * will be a maximum of 4 (2 ** 2) zonelists, for 3 modifiers there will
- * be 8 (2 ** 3) zonelists.  GFP_ZONETYPES defines the number of possible
- * combinations of zone modifiers in "zone modifier space".
- *
- * As an optimisation any zone modifier bits which are only valid when
- * no other zone modifier bits are set (loners) should be placed in
- * the highest order bits of this field.  This allows us to reduce the
- * extent of the zonelists thus saving space.  For example in the case
- * of three zone modifier bits, we could require up to eight zonelists.
- * If the left most zone modifier is a "loner" then the highest valid
- * zonelist would be four allowing us to allocate only five zonelists.
- * Use the first form for GFP_ZONETYPES when the left most bit is not
- * a "loner", otherwise use the second.
- *
- * NOTE! Make sure this matches the zones in <linux/gfp.h>
+ * match the requested limits. See gfp_zone() in include/linux/gfp.h
  */
 
-#ifdef CONFIG_ZONE_DMA32
-
-#ifdef CONFIG_HIGHMEM
-#define GFP_ZONETYPES           ((GFP_ZONEMASK + 1) / 2 + 1)    /* Loner */
-#define GFP_ZONEMASK            0x07
-#define ZONES_SHIFT             2       /* ceil(log2(MAX_NR_ZONES)) */
-#else
-#define GFP_ZONETYPES           ((0x07 + 1) / 2 + 1)    /* Loner */
-/* Mask __GFP_HIGHMEM */
-#define GFP_ZONEMASK            0x05
-#define ZONES_SHIFT             2
-#endif
-
-#else
-#ifdef CONFIG_HIGHMEM
-
-#define GFP_ZONEMASK            0x03
-#define ZONES_SHIFT             2
-#define GFP_ZONETYPES           3
-
+#if !defined(CONFIG_ZONE_DMA32) && !defined(CONFIG_HIGHMEM)
+#define ZONES_SHIFT 1
 #else
-
-#define GFP_ZONEMASK            0x01
-#define ZONES_SHIFT             1
-#define GFP_ZONETYPES           2
-
-#endif
+#define ZONES_SHIFT 2
 #endif
 
 struct zone {
@@ -360,7 +318,7 @@ struct zonelist {
 struct bootmem_data;
 typedef struct pglist_data {
         struct zone node_zones[MAX_NR_ZONES];
-        struct zonelist node_zonelists[GFP_ZONETYPES];
+        struct zonelist node_zonelists[MAX_NR_ZONES];
         int nr_zones;
 #ifdef CONFIG_FLAT_NODE_MEM_MAP
         struct page *node_mem_map;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 7da4142ce960..c3429a710ab1 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1101,7 +1101,7 @@ static struct zonelist *zonelist_policy(gfp_t gfp, struct mempolicy *policy)
         case MPOL_BIND:
                 /* Lower zones don't get a policy applied */
                 /* Careful: current->mems_allowed might have moved */
-                if (highest_zone(gfp) >= policy_zone)
+                if (gfp_zone(gfp) >= policy_zone)
                         if (cpuset_zonelist_valid_mems_allowed(policy->v.zonelist))
                                 return policy->v.zonelist;
                 /*FALL THROUGH*/
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9c44b9a39d30..208a6b03aa78 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1444,14 +1444,14 @@ static int __meminit find_next_best_node(int node, nodemask_t *used_node_mask)
 
 static void __meminit build_zonelists(pg_data_t *pgdat)
 {
-        int i, j, node, local_node;
+        int j, node, local_node;
+        enum zone_type i;
         int prev_node, load;
         struct zonelist *zonelist;
         nodemask_t used_mask;
-        enum zone_type k;
 
         /* initialize zonelists */
-        for (i = 0; i < GFP_ZONETYPES; i++) {
+        for (i = 0; i < MAX_NR_ZONES; i++) {
                 zonelist = pgdat->node_zonelists + i;
                 zonelist->zones[0] = NULL;
         }
@@ -1481,13 +1481,11 @@ static void __meminit build_zonelists(pg_data_t *pgdat)
                         node_load[node] += load;
                 prev_node = node;
                 load--;
-                for (i = 0; i < GFP_ZONETYPES; i++) {
+                for (i = 0; i < MAX_NR_ZONES; i++) {
                         zonelist = pgdat->node_zonelists + i;
                         for (j = 0; zonelist->zones[j] != NULL; j++);
 
-                        k = highest_zone(i);
-
-                        j = build_zonelists_node(NODE_DATA(node), zonelist, j, k);
+                        j = build_zonelists_node(NODE_DATA(node), zonelist, j, i);
                         zonelist->zones[j] = NULL;
                 }
         }
@@ -1497,19 +1495,16 @@ static void __meminit build_zonelists(pg_data_t *pgdat)
 
 static void __meminit build_zonelists(pg_data_t *pgdat)
 {
-        int i, node, local_node;
-        enum zone_type k;
-        enum zone_type j;
+        int node, local_node;
+        enum zone_type i,j;
 
         local_node = pgdat->node_id;
-        for (i = 0; i < GFP_ZONETYPES; i++) {
+        for (i = 0; i < MAX_NR_ZONES; i++) {
                 struct zonelist *zonelist;
 
                 zonelist = pgdat->node_zonelists + i;
 
-                j = 0;
-                k = highest_zone(i);
-                j = build_zonelists_node(pgdat, zonelist, j, k);
+                j = build_zonelists_node(pgdat, zonelist, 0, i);
                 /*
                  * Now we build the zonelist so that it contains the zones
                  * of all the other nodes.
@@ -1521,12 +1516,12 @@ static void __meminit build_zonelists(pg_data_t *pgdat)
                 for (node = local_node + 1; node < MAX_NUMNODES; node++) {
                         if (!node_online(node))
                                 continue;
-                        j = build_zonelists_node(NODE_DATA(node), zonelist, j, k);
+                        j = build_zonelists_node(NODE_DATA(node), zonelist, j, i);
                 }
                 for (node = 0; node < local_node; node++) {
                         if (!node_online(node))
                                 continue;
-                        j = build_zonelists_node(NODE_DATA(node), zonelist, j, k);
+                        j = build_zonelists_node(NODE_DATA(node), zonelist, j, i);
                 }
 
                 zonelist->zones[j] = NULL;