[PATCH] Replace 'numnodes' with 'node_online_map' - arch-independent

From: William Lee Irwin III <wli@holomorphy.com>

Without passing this parameter by reference, the changes to used_node_mask
are meaningless and do not affect the caller's copy.

This leads to boot-time failure. This proposed fix passes it by reference.
Signed-off-by: William Irwin <wli@holomorphy.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

Documentation/vm/numa

@@ -29,7 +29,7 @@ Each node's page allocation data structures have also been encapsulated
 into a pg_data_t. The bootmem_data_t is just one part of this. To 
 make the code look uniform between NUMA and regular UMA platforms, 
 UMA platforms have a statically allocated pg_data_t too (contig_page_data).
-For the sake of uniformity, the variable "numnodes" is also defined
+For the sake of uniformity, the function num_online_nodes() is also defined
 for all platforms. As we run benchmarks, we might decide to NUMAize 
 more variables like low_on_memory, nr_free_pages etc into the pg_data_t.
 

drivers/base/node.c

@@ -10,6 +10,7 @@
 #include <linux/hugetlb.h>
 #include <linux/cpumask.h>
 #include <linux/topology.h>
+#include <linux/nodemask.h>
 
 static struct sysdev_class node_class = {
 	set_kset_name("node"),
@@ -120,7 +121,7 @@ static ssize_t node_read_distance(struct sys_device * dev, char * buf)
 	/* buf currently PAGE_SIZE, need ~4 chars per node */
 	BUILD_BUG_ON(MAX_NUMNODES*4 > PAGE_SIZE/2);
 
-	for (i = 0; i < numnodes; i++)
+	for_each_online_node(i)
 		len += sprintf(buf + len, "%s%d", i ? " " : "", node_distance(nid, i));
 
 	len += sprintf(buf + len, "\n");

include/linux/mmzone.h

@@ -272,7 +272,6 @@ typedef struct pglist_data {
 #define node_present_pages(nid)	(NODE_DATA(nid)->node_present_pages)
 #define node_spanned_pages(nid)	(NODE_DATA(nid)->node_spanned_pages)
 
-extern int numnodes;
 extern struct pglist_data *pgdat_list;
 
 void __get_zone_counts(unsigned long *active, unsigned long *inactive,

include/linux/topology.h

@@ -43,16 +43,9 @@
 	})
 #endif
 
-static inline int __next_node_with_cpus(int node)
-{
-	do
-		++node;
-	while (node < numnodes && !nr_cpus_node(node));
-	return node;
-}
-
-#define for_each_node_with_cpus(node) \
-	for (node = 0; node < numnodes; node = __next_node_with_cpus(node))
+#define for_each_node_with_cpus(node)						\
+	for_each_online_node(node)						\
+		if (nr_cpus_node(node))
 
 #ifndef node_distance
 /* Conform to ACPI 2.0 SLIT distance definitions */

mm/hugetlb.c

@@ -10,6 +10,7 @@
 #include <linux/hugetlb.h>
 #include <linux/sysctl.h>
 #include <linux/highmem.h>
+#include <linux/nodemask.h>
 
 const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL;
 static unsigned long nr_huge_pages, free_huge_pages;
@@ -54,10 +55,10 @@ static struct page *alloc_fresh_huge_page(void)
 	struct page *page;
 	page = alloc_pages_node(nid, GFP_HIGHUSER|__GFP_COMP|__GFP_NOWARN,
 					HUGETLB_PAGE_ORDER);
-	nid = (nid + 1) % numnodes;
+	nid = (nid + 1) % num_online_nodes();
 	if (page) {
 		nr_huge_pages++;
-		nr_huge_pages_node[page_zone(page)->zone_pgdat->node_id]++;
+		nr_huge_pages_node[page_to_nid(page)]++;
 	}
 	return page;
 }

mm/mempolicy.c

@@ -489,7 +489,7 @@ asmlinkage long sys_get_mempolicy(int __user *policy,
 
 	if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR))
 		return -EINVAL;
-	if (nmask != NULL && maxnode < numnodes)
+	if (nmask != NULL && maxnode < MAX_NUMNODES)
 		return -EINVAL;
 	if (flags & MPOL_F_ADDR) {
 		down_read(&mm->mmap_sem);

mm/page_alloc.c

@@ -37,13 +37,13 @@
 #include <asm/tlbflush.h>
 #include "internal.h"
 
-nodemask_t node_online_map = NODE_MASK_NONE;
+/* MCD - HACK: Find somewhere to initialize this EARLY, or make this initializer cleaner */
+nodemask_t node_online_map = { { [0] = 1UL } };
 nodemask_t node_possible_map = NODE_MASK_ALL;
 struct pglist_data *pgdat_list;
 unsigned long totalram_pages;
 unsigned long totalhigh_pages;
 long nr_swap_pages;
-int numnodes = 1;
 int sysctl_lower_zone_protection = 0;
 
 EXPORT_SYMBOL(totalram_pages);
@@ -1220,13 +1220,13 @@ static int __init build_zonelists_node(pg_data_t *pgdat, struct zonelist *zoneli
 }
 
 #ifdef CONFIG_NUMA
-#define MAX_NODE_LOAD (numnodes)
+#define MAX_NODE_LOAD (num_online_nodes())
 static int __initdata node_load[MAX_NUMNODES];
 /**
  * find_next_best_node - find the next node that should appear in a given
  *    node's fallback list
  * @node: node whose fallback list we're appending
- * @used_node_mask: pointer to the bitmap of already used nodes
+ * @used_node_mask: nodemask_t of already used nodes
  *
  * We use a number of factors to determine which is the next node that should
  * appear on a given node's fallback list.  The node should not have appeared
@@ -1237,24 +1237,24 @@ static int __initdata node_load[MAX_NUMNODES];
  * on them otherwise.
  * It returns -1 if no node is found.
  */
-static int __init find_next_best_node(int node, void *used_node_mask)
+static int __init find_next_best_node(int node, nodemask_t *used_node_mask)
 {
 	int i, n, val;
 	int min_val = INT_MAX;
 	int best_node = -1;
 
-	for (i = 0; i < numnodes; i++) {
+	for_each_online_node(i) {
 		cpumask_t tmp;
 
 		/* Start from local node */
-		n = (node+i)%numnodes;
+		n = (node+i) % num_online_nodes();
 
 		/* Don't want a node to appear more than once */
-		if (test_bit(n, used_node_mask))
+		if (node_isset(n, *used_node_mask))
 			continue;
 
 		/* Use the local node if we haven't already */
-		if (!test_bit(node, used_node_mask)) {
+		if (!node_isset(node, *used_node_mask)) {
 			best_node = node;
 			break;
 		}
@@ -1278,7 +1278,7 @@ static int __init find_next_best_node(int node, void *used_node_mask)
 	}
 
 	if (best_node >= 0)
-		set_bit(best_node, used_node_mask);
+		node_set(best_node, *used_node_mask);
 
 	return best_node;
 }
@@ -1288,7 +1288,7 @@ static void __init build_zonelists(pg_data_t *pgdat)
 	int i, j, k, node, local_node;
 	int prev_node, load;
 	struct zonelist *zonelist;
-	DECLARE_BITMAP(used_mask, MAX_NUMNODES);
+	nodemask_t used_mask;
 
 	/* initialize zonelists */
 	for (i = 0; i < GFP_ZONETYPES; i++) {
@@ -1299,10 +1299,10 @@ static void __init build_zonelists(pg_data_t *pgdat)
 
 	/* NUMA-aware ordering of nodes */
 	local_node = pgdat->node_id;
-	load = numnodes;
+	load = num_online_nodes();
 	prev_node = local_node;
-	bitmap_zero(used_mask, MAX_NUMNODES);
-	while ((node = find_next_best_node(local_node, used_mask)) >= 0) {
+	nodes_clear(used_mask);
+	while ((node = find_next_best_node(local_node, &used_mask)) >= 0) {
 		/*
 		 * We don't want to pressure a particular node.
 		 * So adding penalty to the first node in same
@@ -1358,11 +1358,17 @@ static void __init build_zonelists(pg_data_t *pgdat)
  		 * zones coming right after the local ones are those from
  		 * node N+1 (modulo N)
  		 */
- 		for (node = local_node + 1; node < numnodes; node++)
- 			j = build_zonelists_node(NODE_DATA(node), zonelist, j, k);
- 		for (node = 0; node < local_node; node++)
- 			j = build_zonelists_node(NODE_DATA(node), zonelist, j, k);
- 
+		for (node = local_node + 1; node < MAX_NUMNODES; node++) {
+			if (!node_online(node))
+				continue;
+			j = build_zonelists_node(NODE_DATA(node), zonelist, j, k);
+		}
+		for (node = 0; node < local_node; node++) {
+			if (!node_online(node))
+				continue;
+			j = build_zonelists_node(NODE_DATA(node), zonelist, j, k);
+		}
+
 		zonelist->zones[j] = NULL;
 	}
 }
@@ -1373,9 +1379,9 @@ void __init build_all_zonelists(void)
 {
 	int i;
 
-	for(i = 0 ; i < numnodes ; i++)
+	for_each_online_node(i)
 		build_zonelists(NODE_DATA(i));
-	printk("Built %i zonelists\n", numnodes);
+	printk("Built %i zonelists\n", num_online_nodes());
 }
 
 /*