GFP_ZONEMASK vs. MAX_NR_ZONES

Ok... hot on the heels of the other GFP_ZONEMASK patch:

struct bootmem_data;

typedef struct pglist_data {
	struct zone node_zones[MAX_NR_ZONES];
	struct zonelist node_zonelists[GFP_ZONEMASK+1];
	int nr_zones;
	struct page *node_mem_map;
	unsigned long *valid_addr_bitmap;
	struct bootmem_data *bdata;
	unsigned long node_start_pfn;
	unsigned long node_size;
	int node_id;
	struct pglist_data *pgdat_next;
	wait_queue_head_t       kswapd_wait;
} pg_data_t;

node_zonelists looks like it should really be declared of size MAX_NR_ZONES, not GFP_ZONEMASK. GFP_ZONEMASK is currently 15, making node_zonelists an array of 16 elements. The extra zonelists are all just duplicates of the *real* zonelists, namely the first 3 entries. Again, if anyone can explain to me why I'm wrong in my thinking, I'd love to know. There's certainly no way you could bitwise-and something with any combination of the GFP_DMA and GFP_HIGHMEM flags to refer to the 12th zonelist or some such! Or am I crazy?

Cheers!

-Matt

diff -Nur --exclude-from=/usr/src/.dontdiff linux-2.5.64-vanilla/include/linux/mmzone.h linux-2.5.64-zonelist_fix/include/linux/mmzone.h
@@ -178,7 +178,7 @@
 struct bootmem_data;
 typedef struct pglist_data {
 	struct zone node_zones[MAX_NR_ZONES];
-	struct zonelist node_zonelists[GFP_ZONEMASK+1];
+	struct zonelist node_zonelists[MAX_NR_ZONES];
 	int nr_zones;
 	struct page *node_mem_map;
 	unsigned long *valid_addr_bitmap;

diff -Nur --exclude-from=/usr/src/.dontdiff linux-2.5.64-vanilla/mm/page_alloc.c linux-2.5.64-zonelist_fix/mm/page_alloc.c
@@ -1028,7 +1028,7 @@
 
 	local_node = pgdat->node_id;
 	printk("Building zonelist for node : %d\n", local_node);
-	for (i = 0; i <= GFP_ZONEMASK; i++) {
+	for (i = 0; i < MAX_NR_ZONES; i++) {
 		struct zonelist *zonelist;
 
 		zonelist = pgdat->node_zonelists + i;

No, you're not crazy, you're right:

#define __GFP_DMA 0x01
#define __GFP_HIGHMEM 0x02

/* Action modifiers - doesn't change the zoning */

#define __GFP_WAIT      0x10    /* Can wait and reschedule? */
#define __GFP_HIGH      0x20    /* Should access emergency pools? */
#define __GFP_IO        0x40    /* Can start physical IO? */
#define __GFP_FS        0x80    /* Can call down to low-level FS? */
#define __GFP_COLD      0x100   /* Cache-cold page required */
#define __GFP_NOWARN    0x200   /* Suppress page allocation failure warning */

bits 3-6 of gfp masks are totally unused.

-- wli