[PATCH] Create nodemask_t

The idea behind this patch is to create a nodemask_t as a node analog of
cpumask_t.  As NUMA machines become more common, the need for a standard,
cross-platform bitmap of both online & possible nodes becomes more
apparent.  We believe we've worked out most of the kinks of the variable
length bitmap types with the recent cpumask_t patches.  Nodemasks are also
currently far less widespread than cpumasks.  Further, inclusion at this
point in the kernel would mean consistency in node handling between 2.6 and
2.7.

Future goals would be to get rid of the 'numnodes' variable used to count
the number of online nodes, and replace with node_online_map.  This would
allow arbitrary node numbering and facilitate node hotplugging.

(Nothing actually uses this yet, but several projects need it, and it does
model a well-defined physical grouping).
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

arch/i386/kernel/numaq.c

@@ -28,6 +28,7 @@
 #include <linux/bootmem.h>
 #include <linux/mmzone.h>
 #include <linux/module.h>
+#include <linux/nodemask.h>
 #include <asm/numaq.h>
 
 /* These are needed before the pgdat's are created */

arch/i386/kernel/srat.c

@@ -28,6 +28,7 @@
 #include <linux/bootmem.h>
 #include <linux/mmzone.h>
 #include <linux/acpi.h>
+#include <linux/nodemask.h>
 #include <asm/srat.h>
 
 /*

arch/i386/mach-default/topology.c

@@ -27,6 +27,7 @@
  */
 #include <linux/init.h>
 #include <linux/smp.h>
+#include <linux/nodemask.h>
 #include <asm/cpu.h>
 
 struct i386_cpu cpu_devices[NR_CPUS];

arch/i386/mm/discontig.c

@@ -28,6 +28,7 @@
 #include <linux/mmzone.h>
 #include <linux/highmem.h>
 #include <linux/initrd.h>
+#include <linux/nodemask.h>
 #include <asm/e820.h>
 #include <asm/setup.h>
 #include <asm/mmzone.h>

arch/ia64/kernel/acpi.c

@@ -43,6 +43,7 @@
 #include <linux/acpi.h>
 #include <linux/efi.h>
 #include <linux/mmzone.h>
+#include <linux/nodemask.h>
 #include <asm/io.h>
 #include <asm/iosapic.h>
 #include <asm/machvec.h>

arch/ia64/mm/discontig.c

@@ -16,6 +16,7 @@
 #include <linux/bootmem.h>
 #include <linux/acpi.h>
 #include <linux/efi.h>
+#include <linux/nodemask.h>
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
 #include <asm/meminit.h>

arch/ppc64/kernel/sysfs.c

@@ -6,6 +6,8 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/module.h>
+#include <linux/nodemask.h>
+
 #include <asm/current.h>
 #include <asm/processor.h>
 #include <asm/cputable.h>

arch/ppc64/mm/numa.c

@@ -14,6 +14,7 @@
 #include <linux/mm.h>
 #include <linux/mmzone.h>
 #include <linux/module.h>
+#include <linux/nodemask.h>
 #include <asm/lmb.h>
 #include <asm/machdep.h>
 #include <asm/abs_addr.h>

arch/x86_64/mm/k8topology.c

@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/module.h>
+#include <linux/nodemask.h>
 #include <asm/io.h>
 #include <linux/pci_ids.h>
 #include <asm/types.h>

arch/x86_64/mm/numa.c

@@ -10,6 +10,8 @@
 #include <linux/mmzone.h>
 #include <linux/ctype.h>
 #include <linux/module.h>
+#include <linux/nodemask.h>
+
 #include <asm/e820.h>
 #include <asm/proto.h>
 #include <asm/dma.h>
@@ -151,9 +153,9 @@ void __init numa_init_array(void)
 	for (i = 0; i < MAXNODE; i++) {
 		if (node_online(i))
 			continue;
-		rr = find_next_bit(node_online_map, MAX_NUMNODES, rr);
+		rr = next_node(rr, node_online_map);
 		if (rr == MAX_NUMNODES)
-			rr = find_first_bit(node_online_map, MAX_NUMNODES);
+			rr = first_node(node_online_map);
 		node_data[i] = node_data[rr];
 		cpu_to_node[i] = rr;
 		rr++; 

include/asm-i386/cpu.h

@@ -4,6 +4,7 @@
 #include <linux/device.h>
 #include <linux/cpu.h>
 #include <linux/topology.h>
+#include <linux/nodemask.h>
 
 #include <asm/node.h>
 

include/asm-i386/node.h

@@ -5,6 +5,7 @@
 #include <linux/mmzone.h>
 #include <linux/node.h>
 #include <linux/topology.h>
+#include <linux/nodemask.h>
 
 struct i386_node {
 	struct node node;

include/asm-x86_64/numa.h

 #ifndef _ASM_X8664_NUMA_H 
 #define _ASM_X8664_NUMA_H 1
 
+#include <linux/nodemask.h>
+
 #define MAXNODE 8 
 #define NODEMASK 0xff
 

include/linux/mmzone.h

@@ -410,35 +410,6 @@ extern struct pglist_data contig_page_data;
 #error ZONES_SHIFT > MAX_ZONES_SHIFT
 #endif
 
-extern DECLARE_BITMAP(node_online_map, MAX_NUMNODES);
-
-#if defined(CONFIG_DISCONTIGMEM) || defined(CONFIG_NUMA)
-
-#define node_online(node)	test_bit(node, node_online_map)
-#define node_set_online(node)	set_bit(node, node_online_map)
-#define node_set_offline(node)	clear_bit(node, node_online_map)
-static inline unsigned int num_online_nodes(void)
-{
-	int i, num = 0;
-
-	for(i = 0; i < MAX_NUMNODES; i++){
-		if (node_online(i))
-			num++;
-	}
-	return num;
-}
-
-#else /* !CONFIG_DISCONTIGMEM && !CONFIG_NUMA */
-
-#define node_online(node) \
-	({ BUG_ON((node) != 0); test_bit(node, node_online_map); })
-#define node_set_online(node) \
-	({ BUG_ON((node) != 0); set_bit(node, node_online_map); })
-#define node_set_offline(node) \
-	({ BUG_ON((node) != 0); clear_bit(node, node_online_map); })
-#define num_online_nodes()	1
-
-#endif /* CONFIG_DISCONTIGMEM || CONFIG_NUMA */
 #endif /* !__ASSEMBLY__ */
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MMZONE_H */

mm/mempolicy.c

@@ -66,6 +66,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
+#include <linux/nodemask.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
 #include <linux/string.h>
@@ -95,7 +96,7 @@ static int nodes_online(unsigned long *nodes)
 {
 	DECLARE_BITMAP(online2, MAX_NUMNODES);
 
-	bitmap_copy(online2, node_online_map, MAX_NUMNODES);
+	bitmap_copy(online2, nodes_addr(node_online_map), MAX_NUMNODES);
 	if (bitmap_empty(online2, MAX_NUMNODES))
 		set_bit(0, online2);
 	if (!bitmap_subset(nodes, online2, MAX_NUMNODES))
@@ -424,7 +425,7 @@ static void get_zonemask(struct mempolicy *p, unsigned long *nodes)
 	case MPOL_PREFERRED:
 		/* or use current node instead of online map? */
 		if (p->v.preferred_node < 0)
-			bitmap_copy(nodes, node_online_map, MAX_NUMNODES);
+			bitmap_copy(nodes, nodes_addr(node_online_map), MAX_NUMNODES);
 		else
 			__set_bit(p->v.preferred_node, nodes);
 		break;
@@ -692,7 +693,7 @@ static struct page *alloc_page_interleave(unsigned gfp, unsigned order, unsigned
 	struct zonelist *zl;
 	struct page *page;
 
-	BUG_ON(!test_bit(nid, node_online_map));
+	BUG_ON(!node_online(nid));
 	zl = NODE_DATA(nid)->node_zonelists + (gfp & GFP_ZONEMASK);
 	page = __alloc_pages(gfp, order, zl);
 	if (page && page_zone(page) == zl->zones[0]) {
@@ -1081,7 +1082,8 @@ void __init numa_policy_init(void)
 	/* Set interleaving policy for system init. This way not all
 	   the data structures allocated at system boot end up in node zero. */
 
-	if (sys_set_mempolicy(MPOL_INTERLEAVE, node_online_map, MAX_NUMNODES) < 0)
+	if (sys_set_mempolicy(MPOL_INTERLEAVE, nodes_addr(node_online_map),
+							MAX_NUMNODES) < 0)
 		printk("numa_policy_init: interleaving failed\n");
 }
 

mm/page_alloc.c

@@ -31,10 +31,12 @@
 #include <linux/topology.h>
 #include <linux/sysctl.h>
 #include <linux/cpu.h>
+#include <linux/nodemask.h>
 
 #include <asm/tlbflush.h>
 
-DECLARE_BITMAP(node_online_map, MAX_NUMNODES);
+nodemask_t node_online_map = NODE_MASK_NONE;
+nodemask_t node_possible_map = NODE_MASK_ALL;
 struct pglist_data *pgdat_list;
 unsigned long totalram_pages;
 unsigned long totalhigh_pages;