[PATCH] node enumeration fixes

From: Matthew Dobson <colpatch@us.ibm.com>

Here's a small update to the numnodes fix that went into -mm3.  The biggest
changes are:

1) move the actual NODES_SHIFT and MAX_NUMNODES definitions into
   linux/numa.h and include this in linux/mmzone.h, instead of being
   directly in linux/mmzone.h.  This allows other files to include *just*
   the NUMNODES stuff w/out grabbing all of mmzone.h.

2) pull NODE_SHIFT out of linux/mm.h.  This isn't used anywhere in the
   kernel, and it will only get confused with NODES_SHIFT.

3) Fix the IA64 patch.  The original patch I had sent out hadn't been
   tested on IA64.  It was mostly right, but there were circular
   dependencies.  All better now, and acked by Jesse.

4) In linux/mmzone.h, insert code to define MAX_NODES_SHIFT based on the
   size of unsigned long.  For 64-bit arches, we can have a much larger
   value.  This allows IA64 to have 100's or 1000's of nodes.
   MAX_NODES_SHIFT is defined as 10 (ie: 1024 nodes) for 64-bit for now,
   although it could likely be much larger.  For 32-bit it is 6 (ie: 64
   nodes).

5) Small cleanup in include/asm-arm/memory.h.  Mostly the result of the
   new linux/numa.h file.  Much cleaner and more readable now.

include/asm-arm/memory.h

@@ -84,27 +84,24 @@ static inline void *phys_to_virt(unsigned long x)
 
 #define PHYS_TO_NID(addr)	(0)
 
-#else
+#else /* CONFIG_DISCONTIGMEM */
+
 /*
  * This is more complex.  We have a set of mem_map arrays spread
  * around in memory.
  */
-#include <asm/numnodes.h>
-#define NUM_NODES	(1 << NODES_SHIFT)
+#include <linux/numa.h>
 
 #define page_to_pfn(page)					\
 	(( (page) - page_zone(page)->zone_mem_map)		\
 	  + page_zone(page)->zone_start_pfn)
-
 #define pfn_to_page(pfn)					\
 	(PFN_TO_MAPBASE(pfn) + LOCAL_MAP_NR((pfn) << PAGE_SHIFT))
-
-#define pfn_valid(pfn)		(PFN_TO_NID(pfn) < NUM_NODES)
+#define pfn_valid(pfn)		(PFN_TO_NID(pfn) < MAX_NUMNODES)
 
 #define virt_to_page(kaddr)					\
 	(ADDR_TO_MAPBASE(kaddr) + LOCAL_MAP_NR(kaddr))
-
-#define virt_addr_valid(kaddr)	(KVADDR_TO_NID(kaddr) < NUM_NODES)
+#define virt_addr_valid(kaddr)	(KVADDR_TO_NID(kaddr) < MAX_NUMNODES)
 
 /*
  * Common discontigmem stuff.
@@ -112,9 +109,7 @@ static inline void *phys_to_virt(unsigned long x)
  */
 #define PHYS_TO_NID(addr)	PFN_TO_NID((addr) >> PAGE_SHIFT)
 
-#undef NUM_NODES
-
-#endif
+#endif /* !CONFIG_DISCONTIGMEM */
 
 /*
  * For BIO.  "will die".  Kill me when bio_to_phys() and bvec_to_phys() die.

include/asm-ia64/nodedata.h

@@ -8,13 +8,11 @@
  * Copyright (c) 2002 Erich Focht <efocht@ess.nec.de>
  * Copyright (c) 2002 Kimio Suganuma <k-suganuma@da.jp.nec.com>
  */
-
-
 #ifndef _ASM_IA64_NODEDATA_H
 #define _ASM_IA64_NODEDATA_H
 
-
-#include <linux/mmzone.h>
+#include <linux/numa.h>
+#include <asm/mmzone.h>
 
 /*
  * Node Data. One of these structures is located on each node of a NUMA system.
@@ -24,7 +22,7 @@ struct pglist_data;
 struct ia64_node_data {
 	short			active_cpu_count;
 	short			node;
-        struct pglist_data	*pg_data_ptrs[MAX_NUMNODES];
+	struct pglist_data	*pg_data_ptrs[MAX_NUMNODES];
 	struct page		*bank_mem_map_base[NR_BANKS];
 	struct ia64_node_data	*node_data_ptrs[MAX_NUMNODES];
 	short			node_id_map[NR_BANKS];

include/asm-ia64/numa.h

@@ -16,9 +16,9 @@
 
 #ifdef CONFIG_NUMA
 
-# include <asm/mmzone.h>
-
+#include <linux/numa.h>
 #include <linux/cache.h>
+
 extern volatile char cpu_to_node_map[NR_CPUS] __cacheline_aligned;
 extern volatile cpumask_t node_to_cpu_mask[MAX_NUMNODES] __cacheline_aligned;
 

include/asm-ia64/sn/pda.h

@@ -10,7 +10,7 @@
 
 #include <linux/config.h>
 #include <linux/cache.h>
-#include <linux/mmzone.h>
+#include <linux/numa.h>
 #include <asm/percpu.h>
 #include <asm/system.h>
 #include <asm/processor.h>

include/linux/mm.h

@@ -323,7 +323,6 @@ static inline void put_page(struct page *page)
  * The zone field is never updated after free_area_init_core()
  * sets it, so none of the operations on it need to be atomic.
  */
-#define NODE_SHIFT 4
 #define ZONE_SHIFT (BITS_PER_LONG - 8)
 
 struct zone;

include/linux/mmzone.h

@@ -10,14 +10,8 @@
 #include <linux/wait.h>
 #include <linux/cache.h>
 #include <linux/threads.h>
+#include <linux/numa.h>
 #include <asm/atomic.h>
-#ifdef CONFIG_DISCONTIGMEM
-#include <asm/numnodes.h>
-#endif
-#ifndef NODES_SHIFT
-#define NODES_SHIFT	0
-#endif
-#define MAX_NUMNODES	(1 << NODES_SHIFT)
 
 /* Free memory management - zoned buddy allocator.  */
 #ifndef CONFIG_FORCE_MAX_ZONEORDER
@@ -313,12 +307,19 @@ extern struct pglist_data contig_page_data;
 #else /* CONFIG_DISCONTIGMEM */
 
 #include <asm/mmzone.h>
+
+#if BITS_PER_LONG == 32
 /*
- * page->zone is currently 8 bits
- * there are 3 zones (2 bits)
- * this leaves 8-2=6 bits for nodes
+ * with 32 bit flags field, page->zone is currently 8 bits.
+ * there are 3 zones (2 bits) and this leaves 8-2=6 bits for nodes.
  */
 #define MAX_NODES_SHIFT		6
+#elif BITS_PER_LONG == 64
+/*
+ * with 64 bit flags field, there's plenty of room.
+ */
+#define MAX_NODES_SHIFT		10
+#endif
 
 #endif /* !CONFIG_DISCONTIGMEM */
 

include/linux/numa.h

+#ifndef _LINUX_NUMA_H
+#define _LINUX_NUMA_H
+
+#include <linux/config.h>
+
+#ifdef CONFIG_DISCONTIGMEM
+#include <asm/numnodes.h>
+#endif
+
+#ifndef NODES_SHIFT
+#define NODES_SHIFT     0
+#endif
+
+#define MAX_NUMNODES    (1 << NODES_SHIFT)
+
+#endif /* _LINUX_NUMA_H */