diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/arch/i386/Kconfig linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/i386/Kconfig
--- linux-2.6.17-rc4-mm3-clean/arch/i386/Kconfig	2006-05-22 11:25:40.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/i386/Kconfig	2006-05-22 11:28:22.000000000 +0100
@@ -580,12 +580,10 @@ config ARCH_SELECT_MEMORY_MODEL
 	def_bool y
 	depends on ARCH_SPARSEMEM_ENABLE
 
-source "mm/Kconfig"
+config ARCH_POPULATES_NODE_MAP
+	def_bool y
 
-config HAVE_ARCH_EARLY_PFN_TO_NID
-	bool
-	default y
-	depends on NUMA
+source "mm/Kconfig"
 
 config HIGHPTE
 	bool "Allocate 3rd-level pagetables from highmem"
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/arch/i386/kernel/setup.c linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/i386/kernel/setup.c
--- linux-2.6.17-rc4-mm3-clean/arch/i386/kernel/setup.c	2006-05-22 11:25:40.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/i386/kernel/setup.c	2006-05-22 11:28:22.000000000 +0100
@@ -1206,22 +1206,15 @@ static unsigned long __init setup_memory
 
 void __init zone_sizes_init(void)
 {
-	unsigned long zones_size[MAX_NR_ZONES] = {0, 0, 0};
-	unsigned int max_dma, low;
+	unsigned int max_dma;
+#ifndef CONFIG_HIGHMEM
+	unsigned long highend_pfn = max_low_pfn;
+#endif
 
 	max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
-	low = max_low_pfn;
 
-	if (low < max_dma)
-		zones_size[ZONE_DMA] = low;
-	else {
-		zones_size[ZONE_DMA] = max_dma;
-		zones_size[ZONE_NORMAL] = low - max_dma;
-#ifdef CONFIG_HIGHMEM
-		zones_size[ZONE_HIGHMEM] = highend_pfn - low;
-#endif
-	}
-	free_area_init(zones_size);
+	add_active_range(0, 0, highend_pfn);
+	free_area_init_nodes(max_dma, max_dma, max_low_pfn, highend_pfn);
 }
 #else
 extern unsigned long __init setup_memory(void);
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/arch/i386/kernel/srat.c linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/i386/kernel/srat.c
--- linux-2.6.17-rc4-mm3-clean/arch/i386/kernel/srat.c	2006-05-22 11:25:40.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/i386/kernel/srat.c	2006-05-22 11:28:22.000000000 +0100
@@ -55,8 +55,6 @@ struct node_memory_chunk_s {
 static struct node_memory_chunk_s node_memory_chunk[MAXCHUNKS];
 
 static int num_memory_chunks;		/* total number of memory chunks */
-static int zholes_size_init;
-static unsigned long zholes_size[MAX_NUMNODES * MAX_NR_ZONES];
 
 extern void * boot_ioremap(unsigned long, unsigned long);
 
@@ -136,50 +134,6 @@ static void __init parse_memory_affinity
 		 "enabled and removable" : "enabled" ) );
 }
 
-#if MAX_NR_ZONES != 4
-#error "MAX_NR_ZONES != 4, chunk_to_zone requires review"
-#endif
-/* Take a chunk of pages from page frame cstart to cend and count the number
- * of pages in each zone, returned via zones[].
- */
-static __init void chunk_to_zones(unsigned long cstart, unsigned long cend, 
-		unsigned long *zones)
-{
-	unsigned long max_dma;
-	extern unsigned long max_low_pfn;
-
-	int z;
-	unsigned long rend;
-
-	/* FIXME: MAX_DMA_ADDRESS and max_low_pfn are trying to provide
-	 * similarly scoped information and should be handled in a consistant
-	 * manner.
-	 */
-	max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
-
-	/* Split the hole into the zones in which it falls.  Repeatedly
-	 * take the segment in which the remaining hole starts, round it
-	 * to the end of that zone.
-	 */
-	memset(zones, 0, MAX_NR_ZONES * sizeof(long));
-	while (cstart < cend) {
-		if (cstart < max_dma) {
-			z = ZONE_DMA;
-			rend = (cend < max_dma)? cend : max_dma;
-
-		} else if (cstart < max_low_pfn) {
-			z = ZONE_NORMAL;
-			rend = (cend < max_low_pfn)? cend : max_low_pfn;
-
-		} else {
-			z = ZONE_HIGHMEM;
-			rend = cend;
-		}
-		zones[z] += rend - cstart;
-		cstart = rend;
-	}
-}
-
 /*
  * The SRAT table always lists ascending addresses, so can always
  * assume that the first "start" address that you see is the real
@@ -224,7 +178,6 @@ static int __init acpi20_parse_srat(stru
 
 	memset(pxm_bitmap, 0, sizeof(pxm_bitmap));	/* init proximity domain bitmap */
 	memset(node_memory_chunk, 0, sizeof(node_memory_chunk));
-	memset(zholes_size, 0, sizeof(zholes_size));
 
 	num_memory_chunks = 0;
 	while (p < end) {
@@ -288,6 +241,7 @@ static int __init acpi20_parse_srat(stru
 		printk("chunk %d nid %d start_pfn %08lx end_pfn %08lx\n",
 		       j, chunk->nid, chunk->start_pfn, chunk->end_pfn);
 		node_read_chunk(chunk->nid, chunk);
+		add_active_range(chunk->nid, chunk->start_pfn, chunk->end_pfn);
 	}
  
 	for_each_online_node(nid) {
@@ -405,57 +359,7 @@ int __init get_memcfg_from_srat(void)
 		return acpi20_parse_srat((struct acpi_table_srat *)header);
 	}
 out_err:
+	remove_all_active_ranges();
 	printk("failed to get NUMA memory information from SRAT table\n");
 	return 0;
 }
-
-/* For each node run the memory list to determine whether there are
- * any memory holes.  For each hole determine which ZONE they fall
- * into.
- *
- * NOTE#1: this requires knowledge of the zone boundries and so
- * _cannot_ be performed before those are calculated in setup_memory.
- * 
- * NOTE#2: we rely on the fact that the memory chunks are ordered by
- * start pfn number during setup.
- */
-static void __init get_zholes_init(void)
-{
-	int nid;
-	int c;
-	int first;
-	unsigned long end = 0;
-
-	for_each_online_node(nid) {
-		first = 1;
-		for (c = 0; c < num_memory_chunks; c++){
-			if (node_memory_chunk[c].nid == nid) {
-				if (first) {
-					end = node_memory_chunk[c].end_pfn;
-					first = 0;
-
-				} else {
-					/* Record any gap between this chunk
-					 * and the previous chunk on this node
-					 * against the zones it spans.
-					 */
-					chunk_to_zones(end,
-						node_memory_chunk[c].start_pfn,
-						&zholes_size[nid * MAX_NR_ZONES]);
-				}
-			}
-		}
-	}
-}
-
-unsigned long * __init get_zholes_size(int nid)
-{
-	if (!zholes_size_init) {
-		zholes_size_init++;
-		get_zholes_init();
-	}
-	if (nid >= MAX_NUMNODES || !node_online(nid))
-		printk("%s: nid = %d is invalid/offline. num_online_nodes = %d",
-		       __FUNCTION__, nid, num_online_nodes());
-	return &zholes_size[nid * MAX_NR_ZONES];
-}
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/arch/i386/mm/discontig.c linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/i386/mm/discontig.c
--- linux-2.6.17-rc4-mm3-clean/arch/i386/mm/discontig.c	2006-05-22 11:25:40.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/i386/mm/discontig.c	2006-05-22 11:28:22.000000000 +0100
@@ -157,21 +157,6 @@ static void __init find_max_pfn_node(int
 		BUG();
 }
 
-/* Find the owning node for a pfn. */
-int early_pfn_to_nid(unsigned long pfn)
-{
-	int nid;
-
-	for_each_node(nid) {
-		if (node_end_pfn[nid] == 0)
-			break;
-		if (node_start_pfn[nid] <= pfn && node_end_pfn[nid] >= pfn)
-			return nid;
-	}
-
-	return 0;
-}
-
 /* 
  * Allocate memory for the pg_data_t for this node via a crude pre-bootmem
  * method.  For node zero take this from the bottom of memory, for
@@ -227,6 +212,8 @@ static unsigned long calculate_numa_rema
 	unsigned long pfn;
 
 	for_each_online_node(nid) {
+		unsigned old_end_pfn = node_end_pfn[nid];
+
 		/*
 		 * The acpi/srat node info can show hot-add memroy zones
 		 * where memory could be added but not currently present.
@@ -276,6 +263,7 @@ static unsigned long calculate_numa_rema
 
 		node_end_pfn[nid] -= size;
 		node_remap_start_pfn[nid] = node_end_pfn[nid];
+		shrink_active_range(nid, old_end_pfn, node_end_pfn[nid]);
 	}
 	printk("Reserving total of %ld pages for numa KVA remap\n",
 			reserve_pages);
@@ -355,45 +343,20 @@ unsigned long __init setup_memory(void)
 void __init zone_sizes_init(void)
 {
 	int nid;
+	unsigned long max_dma_pfn;
 
-
-	for_each_online_node(nid) {
-		unsigned long zones_size[MAX_NR_ZONES] = {0, 0, 0};
-		unsigned long *zholes_size;
-		unsigned int max_dma;
-
-		unsigned long low = max_low_pfn;
-		unsigned long start = node_start_pfn[nid];
-		unsigned long high = node_end_pfn[nid];
-
-		max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
-
-		if (node_has_online_mem(nid)){
-			if (start > low) {
-#ifdef CONFIG_HIGHMEM
-				BUG_ON(start > high);
-				zones_size[ZONE_HIGHMEM] = high - start;
-#endif
-			} else {
-				if (low < max_dma)
-					zones_size[ZONE_DMA] = low;
-				else {
-					BUG_ON(max_dma > low);
-					BUG_ON(low > high);
-					zones_size[ZONE_DMA] = max_dma;
-					zones_size[ZONE_NORMAL] = low - max_dma;
-#ifdef CONFIG_HIGHMEM
-					zones_size[ZONE_HIGHMEM] = high - low;
-#endif
-				}
-			}
+	/* If SRAT has not registered memory, register it now */
+	if (find_max_pfn_with_active_regions() == 0) {
+		for_each_online_node(nid) {
+			if (node_has_online_mem(nid))
+				add_active_range(nid, node_start_pfn[nid],
+							node_end_pfn[nid]);
 		}
-
-		zholes_size = get_zholes_size(nid);
-
-		free_area_init_node(nid, NODE_DATA(nid), zones_size, start,
-				zholes_size);
 	}
+
+	max_dma_pfn = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
+	free_area_init_nodes(max_dma_pfn, max_dma_pfn,
+						max_low_pfn, highend_pfn);
 	return;
 }
 
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/arch/ia64/Kconfig linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/ia64/Kconfig
--- linux-2.6.17-rc4-mm3-clean/arch/ia64/Kconfig	2006-05-22 11:25:40.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/ia64/Kconfig	2006-05-22 11:30:19.000000000 +0100
@@ -353,6 +353,9 @@ config NODES_SHIFT
 	  MAX_NUMNODES will be 2^(This value).
 	  If in doubt, use the default.
 
+config ARCH_POPULATES_NODE_MAP
+	def_bool y
+
 # VIRTUAL_MEM_MAP and FLAT_NODE_MEM_MAP are functionally equivalent.
 # VIRTUAL_MEM_MAP has been retained for historical reasons.
 config VIRTUAL_MEM_MAP
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/arch/ia64/mm/contig.c linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/ia64/mm/contig.c
--- linux-2.6.17-rc4-mm3-clean/arch/ia64/mm/contig.c	2006-05-12 00:31:53.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/ia64/mm/contig.c	2006-05-22 11:30:19.000000000 +0100
@@ -26,10 +26,6 @@
 #include <asm/sections.h>
 #include <asm/mca.h>
 
-#ifdef CONFIG_VIRTUAL_MEM_MAP
-static unsigned long num_dma_physpages;
-#endif
-
 /**
  * show_mem - display a memory statistics summary
  *
@@ -212,18 +208,6 @@ count_pages (u64 start, u64 end, void *a
 	return 0;
 }
 
-#ifdef CONFIG_VIRTUAL_MEM_MAP
-static int
-count_dma_pages (u64 start, u64 end, void *arg)
-{
-	unsigned long *count = arg;
-
-	if (start < MAX_DMA_ADDRESS)
-		*count += (min(end, MAX_DMA_ADDRESS) - start) >> PAGE_SHIFT;
-	return 0;
-}
-#endif
-
 /*
  * Set up the page tables.
  */
@@ -232,47 +216,24 @@ void __init
 paging_init (void)
 {
 	unsigned long max_dma;
-	unsigned long zones_size[MAX_NR_ZONES];
 #ifdef CONFIG_VIRTUAL_MEM_MAP
-	unsigned long zholes_size[MAX_NR_ZONES];
+	unsigned long nid = 0;
 	unsigned long max_gap;
 #endif
 
-	/* initialize mem_map[] */
-
-	memset(zones_size, 0, sizeof(zones_size));
-
 	num_physpages = 0;
 	efi_memmap_walk(count_pages, &num_physpages);
 
 	max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT;
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
-	memset(zholes_size, 0, sizeof(zholes_size));
-
-	num_dma_physpages = 0;
-	efi_memmap_walk(count_dma_pages, &num_dma_physpages);
-
-	if (max_low_pfn < max_dma) {
-		zones_size[ZONE_DMA] = max_low_pfn;
-		zholes_size[ZONE_DMA] = max_low_pfn - num_dma_physpages;
-	} else {
-		zones_size[ZONE_DMA] = max_dma;
-		zholes_size[ZONE_DMA] = max_dma - num_dma_physpages;
-		if (num_physpages > num_dma_physpages) {
-			zones_size[ZONE_NORMAL] = max_low_pfn - max_dma;
-			zholes_size[ZONE_NORMAL] =
-				((max_low_pfn - max_dma) -
-				 (num_physpages - num_dma_physpages));
-		}
-	}
-
 	max_gap = 0;
+	efi_memmap_walk(register_active_ranges, &nid);
 	efi_memmap_walk(find_largest_hole, (u64 *)&max_gap);
 	if (max_gap < LARGE_GAP) {
 		vmem_map = (struct page *) 0;
-		free_area_init_node(0, NODE_DATA(0), zones_size, 0,
-				    zholes_size);
+		free_area_init_nodes(max_dma, max_dma,
+				max_low_pfn, max_low_pfn);
 	} else {
 		unsigned long map_size;
 
@@ -284,19 +245,14 @@ paging_init (void)
 		efi_memmap_walk(create_mem_map_page_table, NULL);
 
 		NODE_DATA(0)->node_mem_map = vmem_map;
-		free_area_init_node(0, NODE_DATA(0), zones_size,
-				    0, zholes_size);
+		free_area_init_nodes(max_dma, max_dma,
+				max_low_pfn, max_low_pfn);
 
 		printk("Virtual mem_map starts at 0x%p\n", mem_map);
 	}
 #else /* !CONFIG_VIRTUAL_MEM_MAP */
-	if (max_low_pfn < max_dma)
-		zones_size[ZONE_DMA] = max_low_pfn;
-	else {
-		zones_size[ZONE_DMA] = max_dma;
-		zones_size[ZONE_NORMAL] = max_low_pfn - max_dma;
-	}
-	free_area_init(zones_size);
+	add_active_range(0, 0, max_low_pfn);
+	free_area_init_nodes(max_dma, max_dma, max_low_pfn, max_low_pfn);
 #endif /* !CONFIG_VIRTUAL_MEM_MAP */
 	zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page));
 }
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/arch/ia64/mm/discontig.c linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/ia64/mm/discontig.c
--- linux-2.6.17-rc4-mm3-clean/arch/ia64/mm/discontig.c	2006-05-22 11:25:40.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/ia64/mm/discontig.c	2006-05-22 11:30:19.000000000 +0100
@@ -705,6 +705,7 @@ static __init int count_node_pages(unsig
 {
 	unsigned long end = start + len;
 
+	add_active_range(node, start >> PAGE_SHIFT, end >> PAGE_SHIFT);
 	mem_data[node].num_physpages += len >> PAGE_SHIFT;
 	if (start <= __pa(MAX_DMA_ADDRESS))
 		mem_data[node].num_dma_physpages +=
@@ -729,9 +730,8 @@ static __init int count_node_pages(unsig
 void __init paging_init(void)
 {
 	unsigned long max_dma;
-	unsigned long zones_size[MAX_NR_ZONES];
-	unsigned long zholes_size[MAX_NR_ZONES];
 	unsigned long pfn_offset = 0;
+	unsigned long max_pfn = 0;
 	int node;
 
 	max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT;
@@ -748,47 +748,18 @@ void __init paging_init(void)
 #endif
 
 	for_each_online_node(node) {
-		memset(zones_size, 0, sizeof(zones_size));
-		memset(zholes_size, 0, sizeof(zholes_size));
-
 		num_physpages += mem_data[node].num_physpages;
-
-		if (mem_data[node].min_pfn >= max_dma) {
-			/* All of this node's memory is above ZONE_DMA */
-			zones_size[ZONE_NORMAL] = mem_data[node].max_pfn -
-				mem_data[node].min_pfn;
-			zholes_size[ZONE_NORMAL] = mem_data[node].max_pfn -
-				mem_data[node].min_pfn -
-				mem_data[node].num_physpages;
-		} else if (mem_data[node].max_pfn < max_dma) {
-			/* All of this node's memory is in ZONE_DMA */
-			zones_size[ZONE_DMA] = mem_data[node].max_pfn -
-				mem_data[node].min_pfn;
-			zholes_size[ZONE_DMA] = mem_data[node].max_pfn -
-				mem_data[node].min_pfn -
-				mem_data[node].num_dma_physpages;
-		} else {
-			/* This node has memory in both zones */
-			zones_size[ZONE_DMA] = max_dma -
-				mem_data[node].min_pfn;
-			zholes_size[ZONE_DMA] = zones_size[ZONE_DMA] -
-				mem_data[node].num_dma_physpages;
-			zones_size[ZONE_NORMAL] = mem_data[node].max_pfn -
-				max_dma;
-			zholes_size[ZONE_NORMAL] = zones_size[ZONE_NORMAL] -
-				(mem_data[node].num_physpages -
-				 mem_data[node].num_dma_physpages);
-		}
-
 		pfn_offset = mem_data[node].min_pfn;
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
 		NODE_DATA(node)->node_mem_map = vmem_map + pfn_offset;
 #endif
-		free_area_init_node(node, NODE_DATA(node), zones_size,
-				    pfn_offset, zholes_size);
+		if (mem_data[node].max_pfn > max_pfn)
+			max_pfn = mem_data[node].max_pfn;
 	}
 
+	free_area_init_nodes(max_dma, max_dma, max_pfn, max_pfn);
+
 	zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page));
 }
 
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/arch/ia64/mm/init.c linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/ia64/mm/init.c
--- linux-2.6.17-rc4-mm3-clean/arch/ia64/mm/init.c	2006-05-22 11:25:40.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/ia64/mm/init.c	2006-05-22 11:30:19.000000000 +0100
@@ -539,6 +539,18 @@ find_largest_hole (u64 start, u64 end, v
 	last_end = end;
 	return 0;
 }
+
+int __init
+register_active_ranges(u64 start, u64 end, void *nid)
+{
+	BUG_ON(nid == NULL);
+	BUG_ON(*(unsigned long *)nid >= MAX_NUMNODES);
+
+	add_active_range(*(unsigned long *)nid,
+				__pa(start) >> PAGE_SHIFT,
+				__pa(end) >> PAGE_SHIFT);
+	return 0;
+}
 #endif /* CONFIG_VIRTUAL_MEM_MAP */
 
 static int __init
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/arch/powerpc/Kconfig linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/powerpc/Kconfig
--- linux-2.6.17-rc4-mm3-clean/arch/powerpc/Kconfig	2006-05-22 11:25:40.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/powerpc/Kconfig	2006-05-22 15:42:36.000000000 +0100
@@ -684,11 +684,10 @@ config ARCH_SPARSEMEM_DEFAULT
 	def_bool y
 	depends on SMP && PPC_PSERIES
 
-source "mm/Kconfig"
-
-config HAVE_ARCH_EARLY_PFN_TO_NID
+config ARCH_POPULATES_NODE_MAP
 	def_bool y
-	depends on NEED_MULTIPLE_NODES
+
+source "mm/Kconfig"
 
 config ARCH_MEMORY_PROBE
 	def_bool y
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/arch/powerpc/mm/mem.c linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/powerpc/mm/mem.c
--- linux-2.6.17-rc4-mm3-clean/arch/powerpc/mm/mem.c	2006-05-22 11:25:40.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/powerpc/mm/mem.c	2006-05-22 11:27:19.000000000 +0100
@@ -257,20 +257,22 @@ void __init do_init_bootmem(void)
 
 	boot_mapsize = init_bootmem(start >> PAGE_SHIFT, total_pages);
 
+	/* Add active regions with valid PFNs */
+	for (i = 0; i < lmb.memory.cnt; i++) {
+		unsigned long start_pfn, end_pfn;
+		start_pfn = lmb.memory.region[i].base >> PAGE_SHIFT;
+		end_pfn = start_pfn + lmb_size_pages(&lmb.memory, i);
+		add_active_range(0, start_pfn, end_pfn);
+	}
+
 	/* Add all physical memory to the bootmem map, mark each area
 	 * present.
 	 */
-	for (i = 0; i < lmb.memory.cnt; i++) {
-		unsigned long base = lmb.memory.region[i].base;
-		unsigned long size = lmb_size_bytes(&lmb.memory, i);
 #ifdef CONFIG_HIGHMEM
-		if (base >= total_lowmem)
-			continue;
-		if (base + size > total_lowmem)
-			size = total_lowmem - base;
+	free_bootmem_with_active_regions(0, total_lowmem >> PAGE_SHIFT);
+#else
+	free_bootmem_with_active_regions(0, max_pfn);
 #endif
-		free_bootmem(base, size);
-	}
 
 	/* reserve the sections we're already using */
 	for (i = 0; i < lmb.reserved.cnt; i++)
@@ -278,9 +280,8 @@ void __init do_init_bootmem(void)
 				lmb_size_bytes(&lmb.reserved, i));
 
 	/* XXX need to clip this if using highmem? */
-	for (i = 0; i < lmb.memory.cnt; i++)
-		memory_present(0, lmb_start_pfn(&lmb.memory, i),
-			       lmb_end_pfn(&lmb.memory, i));
+	sparse_memory_present_with_active_regions(0);
+
 	init_bootmem_done = 1;
 }
 
@@ -289,8 +290,6 @@ void __init do_init_bootmem(void)
  */
 void __init paging_init(void)
 {
-	unsigned long zones_size[MAX_NR_ZONES];
-	unsigned long zholes_size[MAX_NR_ZONES];
 	unsigned long total_ram = lmb_phys_mem_size();
 	unsigned long top_of_ram = lmb_end_of_DRAM();
 
@@ -308,26 +307,18 @@ void __init paging_init(void)
 	       top_of_ram, total_ram);
 	printk(KERN_DEBUG "Memory hole size: %ldMB\n",
 	       (top_of_ram - total_ram) >> 20);
-	/*
-	 * All pages are DMA-able so we put them all in the DMA zone.
-	 */
-	memset(zones_size, 0, sizeof(zones_size));
-	memset(zholes_size, 0, sizeof(zholes_size));
-
-	zones_size[ZONE_DMA] = top_of_ram >> PAGE_SHIFT;
-	zholes_size[ZONE_DMA] = (top_of_ram - total_ram) >> PAGE_SHIFT;
-
 #ifdef CONFIG_HIGHMEM
-	zones_size[ZONE_DMA] = total_lowmem >> PAGE_SHIFT;
-	zones_size[ZONE_HIGHMEM] = (total_memory - total_lowmem) >> PAGE_SHIFT;
-	zholes_size[ZONE_HIGHMEM] = (top_of_ram - total_ram) >> PAGE_SHIFT;
+	free_area_init_nodes(total_lowmem >> PAGE_SHIFT,
+				total_lowmem >> PAGE_SHIFT,
+				total_lowmem >> PAGE_SHIFT,
+				top_of_ram >> PAGE_SHIFT);
 #else
-	zones_size[ZONE_DMA] = top_of_ram >> PAGE_SHIFT;
-	zholes_size[ZONE_DMA] = (top_of_ram - total_ram) >> PAGE_SHIFT;
-#endif /* CONFIG_HIGHMEM */
+	free_area_init_nodes(top_of_ram >> PAGE_SHIFT,
+				top_of_ram >> PAGE_SHIFT,
+				top_of_ram >> PAGE_SHIFT,
+				top_of_ram >> PAGE_SHIFT);
+#endif
 
-	free_area_init_node(0, NODE_DATA(0), zones_size,
-			    __pa(PAGE_OFFSET) >> PAGE_SHIFT, zholes_size);
 }
 #endif /* ! CONFIG_NEED_MULTIPLE_NODES */
 
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/arch/powerpc/mm/numa.c linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/powerpc/mm/numa.c
--- linux-2.6.17-rc4-mm3-clean/arch/powerpc/mm/numa.c	2006-05-22 11:25:40.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/powerpc/mm/numa.c	2006-05-22 11:27:19.000000000 +0100
@@ -39,96 +39,6 @@ static bootmem_data_t __initdata plat_no
 static int min_common_depth;
 static int n_mem_addr_cells, n_mem_size_cells;
 
-/*
- * We need somewhere to store start/end/node for each region until we have
- * allocated the real node_data structures.
- */
-#define MAX_REGIONS	(MAX_LMB_REGIONS*2)
-static struct {
-	unsigned long start_pfn;
-	unsigned long end_pfn;
-	int nid;
-} init_node_data[MAX_REGIONS] __initdata;
-
-int __init early_pfn_to_nid(unsigned long pfn)
-{
-	unsigned int i;
-
-	for (i = 0; init_node_data[i].end_pfn; i++) {
-		unsigned long start_pfn = init_node_data[i].start_pfn;
-		unsigned long end_pfn = init_node_data[i].end_pfn;
-
-		if ((start_pfn <= pfn) && (pfn < end_pfn))
-			return init_node_data[i].nid;
-	}
-
-	return -1;
-}
-
-void __init add_region(unsigned int nid, unsigned long start_pfn,
-		       unsigned long pages)
-{
-	unsigned int i;
-
-	dbg("add_region nid %d start_pfn 0x%lx pages 0x%lx\n",
-		nid, start_pfn, pages);
-
-	for (i = 0; init_node_data[i].end_pfn; i++) {
-		if (init_node_data[i].nid != nid)
-			continue;
-		if (init_node_data[i].end_pfn == start_pfn) {
-			init_node_data[i].end_pfn += pages;
-			return;
-		}
-		if (init_node_data[i].start_pfn == (start_pfn + pages)) {
-			init_node_data[i].start_pfn -= pages;
-			return;
-		}
-	}
-
-	/*
-	 * Leave last entry NULL so we dont iterate off the end (we use
-	 * entry.end_pfn to terminate the walk).
-	 */
-	if (i >= (MAX_REGIONS - 1)) {
-		printk(KERN_ERR "WARNING: too many memory regions in "
-				"numa code, truncating\n");
-		return;
-	}
-
-	init_node_data[i].start_pfn = start_pfn;
-	init_node_data[i].end_pfn = start_pfn + pages;
-	init_node_data[i].nid = nid;
-}
-
-/* We assume init_node_data has no overlapping regions */
-void __init get_region(unsigned int nid, unsigned long *start_pfn,
-		       unsigned long *end_pfn, unsigned long *pages_present)
-{
-	unsigned int i;
-
-	*start_pfn = -1UL;
-	*end_pfn = *pages_present = 0;
-
-	for (i = 0; init_node_data[i].end_pfn; i++) {
-		if (init_node_data[i].nid != nid)
-			continue;
-
-		*pages_present += init_node_data[i].end_pfn -
-			init_node_data[i].start_pfn;
-
-		if (init_node_data[i].start_pfn < *start_pfn)
-			*start_pfn = init_node_data[i].start_pfn;
-
-		if (init_node_data[i].end_pfn > *end_pfn)
-			*end_pfn = init_node_data[i].end_pfn;
-	}
-
-	/* We didnt find a matching region, return start/end as 0 */
-	if (*start_pfn == -1UL)
-		*start_pfn = 0;
-}
-
 static void __cpuinit map_cpu_to_node(int cpu, int node)
 {
 	numa_cpu_lookup_table[cpu] = node;
@@ -471,8 +381,8 @@ new_range:
 				continue;
 		}
 
-		add_region(nid, start >> PAGE_SHIFT,
-			   size >> PAGE_SHIFT);
+		add_active_range(nid, start >> PAGE_SHIFT,
+				(start >> PAGE_SHIFT) + (size >> PAGE_SHIFT));
 
 		if (--ranges)
 			goto new_range;
@@ -485,6 +395,7 @@ static void __init setup_nonnuma(void)
 {
 	unsigned long top_of_ram = lmb_end_of_DRAM();
 	unsigned long total_ram = lmb_phys_mem_size();
+	unsigned long start_pfn, end_pfn;
 	unsigned int i;
 
 	printk(KERN_DEBUG "Top of RAM: 0x%lx, Total RAM: 0x%lx\n",
@@ -492,9 +403,11 @@ static void __init setup_nonnuma(void)
 	printk(KERN_DEBUG "Memory hole size: %ldMB\n",
 	       (top_of_ram - total_ram) >> 20);
 
-	for (i = 0; i < lmb.memory.cnt; ++i)
-		add_region(0, lmb.memory.region[i].base >> PAGE_SHIFT,
-			   lmb_size_pages(&lmb.memory, i));
+	for (i = 0; i < lmb.memory.cnt; ++i) {
+		start_pfn = lmb.memory.region[i].base >> PAGE_SHIFT;
+		end_pfn = start_pfn + lmb_size_pages(&lmb.memory, i);
+		add_active_range(0, start_pfn, end_pfn);
+	}
 	node_set_online(0);
 }
 
@@ -632,11 +545,11 @@ void __init do_init_bootmem(void)
 			  (void *)(unsigned long)boot_cpuid);
 
 	for_each_online_node(nid) {
-		unsigned long start_pfn, end_pfn, pages_present;
+		unsigned long start_pfn, end_pfn;
 		unsigned long bootmem_paddr;
 		unsigned long bootmap_pages;
 
-		get_region(nid, &start_pfn, &end_pfn, &pages_present);
+		get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
 
 		/* Allocate the node structure node local if possible */
 		NODE_DATA(nid) = careful_allocation(nid,
@@ -669,19 +582,7 @@ void __init do_init_bootmem(void)
 		init_bootmem_node(NODE_DATA(nid), bootmem_paddr >> PAGE_SHIFT,
 				  start_pfn, end_pfn);
 
-		/* Add free regions on this node */
-		for (i = 0; init_node_data[i].end_pfn; i++) {
-			unsigned long start, end;
-
-			if (init_node_data[i].nid != nid)
-				continue;
-
-			start = init_node_data[i].start_pfn << PAGE_SHIFT;
-			end = init_node_data[i].end_pfn << PAGE_SHIFT;
-
-			dbg("free_bootmem %lx %lx\n", start, end - start);
-  			free_bootmem_node(NODE_DATA(nid), start, end - start);
-		}
+		free_bootmem_with_active_regions(nid, end_pfn);
 
 		/* Mark reserved regions on this node */
 		for (i = 0; i < lmb.reserved.cnt; i++) {
@@ -712,44 +613,14 @@ void __init do_init_bootmem(void)
 			}
 		}
 
-		/* Add regions into sparsemem */
-		for (i = 0; init_node_data[i].end_pfn; i++) {
-			unsigned long start, end;
-
-			if (init_node_data[i].nid != nid)
-				continue;
-
-			start = init_node_data[i].start_pfn;
-			end = init_node_data[i].end_pfn;
-
-			memory_present(nid, start, end);
-		}
+		sparse_memory_present_with_active_regions(nid);
 	}
 }
 
 void __init paging_init(void)
 {
-	unsigned long zones_size[MAX_NR_ZONES];
-	unsigned long zholes_size[MAX_NR_ZONES];
-	int nid;
-
-	memset(zones_size, 0, sizeof(zones_size));
-	memset(zholes_size, 0, sizeof(zholes_size));
-
-	for_each_online_node(nid) {
-		unsigned long start_pfn, end_pfn, pages_present;
-
-		get_region(nid, &start_pfn, &end_pfn, &pages_present);
-
-		zones_size[ZONE_DMA] = end_pfn - start_pfn;
-		zholes_size[ZONE_DMA] = zones_size[ZONE_DMA] - pages_present;
-
-		dbg("free_area_init node %d %lx %lx (hole: %lx)\n", nid,
-		    zones_size[ZONE_DMA], start_pfn, zholes_size[ZONE_DMA]);
-
-		free_area_init_node(nid, NODE_DATA(nid), zones_size, start_pfn,
-				    zholes_size);
-	}
+	unsigned long end_pfn = lmb_end_of_DRAM() >> PAGE_SHIFT;
+	free_area_init_nodes(end_pfn, end_pfn, end_pfn, end_pfn);
 }
 
 static int __init early_numa(char *p)
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/arch/ppc/Kconfig linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/ppc/Kconfig
--- linux-2.6.17-rc4-mm3-clean/arch/ppc/Kconfig	2006-05-22 11:25:40.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/ppc/Kconfig	2006-05-22 11:27:19.000000000 +0100
@@ -949,6 +949,9 @@ config NR_CPUS
 config HIGHMEM
 	bool "High memory support"
 
+config ARCH_POPULATES_NODE_MAP
+	def_bool y
+
 source kernel/Kconfig.hz
 source kernel/Kconfig.preempt
 source "mm/Kconfig"
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/arch/ppc/mm/init.c linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/ppc/mm/init.c
--- linux-2.6.17-rc4-mm3-clean/arch/ppc/mm/init.c	2006-05-12 00:31:53.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/ppc/mm/init.c	2006-05-22 11:27:19.000000000 +0100
@@ -359,8 +359,7 @@ void __init do_init_bootmem(void)
  */
 void __init paging_init(void)
 {
-	unsigned long zones_size[MAX_NR_ZONES], i;
-
+	unsigned long start_pfn, end_pfn;
 #ifdef CONFIG_HIGHMEM
 	map_page(PKMAP_BASE, 0, 0);	/* XXX gross */
 	pkmap_page_table = pte_offset_kernel(pmd_offset(pgd_offset_k
@@ -370,19 +369,22 @@ void __init paging_init(void)
 			(KMAP_FIX_BEGIN), KMAP_FIX_BEGIN), KMAP_FIX_BEGIN);
 	kmap_prot = PAGE_KERNEL;
 #endif /* CONFIG_HIGHMEM */
-
-	/*
-	 * All pages are DMA-able so we put them all in the DMA zone.
-	 */
-	zones_size[ZONE_DMA] = total_lowmem >> PAGE_SHIFT;
-	for (i = 1; i < MAX_NR_ZONES; i++)
-		zones_size[i] = 0;
+	/* All pages are DMA-able so we put them all in the DMA zone. */
+	start_pfn = __pa(PAGE_OFFSET) >> PAGE_SHIFT;
+	end_pfn = start_pfn + (total_memory >> PAGE_SHIFT);
+	add_active_range(0, start_pfn, end_pfn);
 
 #ifdef CONFIG_HIGHMEM
-	zones_size[ZONE_HIGHMEM] = (total_memory - total_lowmem) >> PAGE_SHIFT;
+	free_area_init_nodes(total_lowmem >> PAGE_SHIFT,
+				total_lowmem >> PAGE_SHIFT,
+				total_lowmem >> PAGE_SHIFT,
+				total_memory >> PAGE_SHIFT);
+#else
+	free_area_init_nodes(total_memory >> PAGE_SHIFT,
+				total_memory >> PAGE_SHIFT,
+				total_memory >> PAGE_SHIFT,
+				total_memory >> PAGE_SHIFT);
 #endif /* CONFIG_HIGHMEM */
-
-	free_area_init(zones_size);
 }
 
 void __init mem_init(void)
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/arch/x86_64/Kconfig linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/x86_64/Kconfig
--- linux-2.6.17-rc4-mm3-clean/arch/x86_64/Kconfig	2006-05-22 11:25:40.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/x86_64/Kconfig	2006-05-22 11:29:22.000000000 +0100
@@ -73,6 +73,9 @@ config ARCH_MAY_HAVE_PC_FDC
 	bool
 	default y
 
+config ARCH_POPULATES_NODE_MAP
+	def_bool y
+
 config DMI
 	bool
 	default y
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/arch/x86_64/kernel/e820.c linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/x86_64/kernel/e820.c
--- linux-2.6.17-rc4-mm3-clean/arch/x86_64/kernel/e820.c	2006-05-22 11:25:40.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/x86_64/kernel/e820.c	2006-05-24 12:19:20.000000000 +0100
@@ -17,6 +17,7 @@
 #include <linux/string.h>
 #include <linux/kexec.h>
 #include <linux/module.h>
+#include <linux/mm.h>
 
 #include <asm/page.h>
 #include <asm/e820.h>
@@ -160,58 +161,14 @@ unsigned long __init find_e820_area(unsi
 	return -1UL;		
 } 
 
-/* 
- * Free bootmem based on the e820 table for a node.
- */
-void __init e820_bootmem_free(pg_data_t *pgdat, unsigned long start,unsigned long end)
-{
-	int i;
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i]; 
-		unsigned long last, addr;
-
-		if (ei->type != E820_RAM || 
-		    ei->addr+ei->size <= start || 
-		    ei->addr >= end)
-			continue;
-
-		addr = round_up(ei->addr, PAGE_SIZE);
-		if (addr < start) 
-			addr = start;
-
-		last = round_down(ei->addr + ei->size, PAGE_SIZE); 
-		if (last >= end)
-			last = end; 
-
-		if (last > addr && last-addr >= PAGE_SIZE)
-			free_bootmem_node(pgdat, addr, last-addr);
-	}
-}
-
 /*
  * Find the highest page frame number we have available
  */
 unsigned long __init e820_end_of_ram(void)
 {
-	int i;
 	unsigned long end_pfn = 0;
 	
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i]; 
-		unsigned long start, end;
-
-		start = round_up(ei->addr, PAGE_SIZE); 
-		end = round_down(ei->addr + ei->size, PAGE_SIZE); 
-		if (start >= end)
-			continue;
-		if (ei->type == E820_RAM) { 
-		if (end > end_pfn<<PAGE_SHIFT)
-			end_pfn = end>>PAGE_SHIFT;
-		} else { 
-			if (end > end_pfn_map<<PAGE_SHIFT) 
-				end_pfn_map = end>>PAGE_SHIFT;
-		} 
-	}
+	end_pfn = find_max_pfn_with_active_regions();
 
 	if (end_pfn > end_pfn_map) 
 		end_pfn_map = end_pfn;
@@ -222,43 +179,10 @@ unsigned long __init e820_end_of_ram(voi
 	if (end_pfn > end_pfn_map) 
 		end_pfn = end_pfn_map; 
 
+	printk("end_pfn_map = %lu\n", end_pfn_map);
 	return end_pfn;	
 }
 
-/* 
- * Compute how much memory is missing in a range.
- * Unlike the other functions in this file the arguments are in page numbers.
- */
-unsigned long __init
-e820_hole_size(unsigned long start_pfn, unsigned long end_pfn)
-{
-	unsigned long ram = 0;
-	unsigned long start = start_pfn << PAGE_SHIFT;
-	unsigned long end = end_pfn << PAGE_SHIFT;
-	int i;
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
-		unsigned long last, addr;
-
-		if (ei->type != E820_RAM ||
-		    ei->addr+ei->size <= start ||
-		    ei->addr >= end)
-			continue;
-
-		addr = round_up(ei->addr, PAGE_SIZE);
-		if (addr < start)
-			addr = start;
-
-		last = round_down(ei->addr + ei->size, PAGE_SIZE);
-		if (last >= end)
-			last = end;
-
-		if (last > addr)
-			ram += last - addr;
-	}
-	return ((end - start) - ram) >> PAGE_SHIFT;
-}
-
 /*
  * Mark e820 reserved areas as busy for the resource manager.
  */
@@ -293,6 +217,43 @@ void __init e820_reserve_resources(void)
 	}
 }
 
+/* Walk the e820 map and register active regions within a node */
+void __init
+e820_register_active_regions(int nid, unsigned long start_pfn,
+							unsigned long end_pfn)
+{
+	int i;
+	unsigned long ei_startpfn, ei_endpfn;
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+		ei_startpfn = round_up(ei->addr, PAGE_SIZE) >> PAGE_SHIFT;
+		ei_endpfn = round_down(ei->addr + ei->size, PAGE_SIZE)
+								>> PAGE_SHIFT;
+
+		/* Skip map entries smaller than a page */
+		if (ei_startpfn > ei_endpfn)
+			continue;
+
+		/* Check if end_pfn_map should be updated */
+		if (ei->type != E820_RAM && ei_endpfn > end_pfn_map)
+			end_pfn_map = ei_endpfn;
+
+		/* Skip if map is outside the node */
+		if (ei->type != E820_RAM ||
+				ei_endpfn <= start_pfn ||
+				ei_startpfn >= end_pfn)
+			continue;
+
+		/* Check for overlaps */
+		if (ei_startpfn < start_pfn)
+			ei_startpfn = start_pfn;
+		if (ei_endpfn > end_pfn)
+			ei_endpfn = end_pfn;
+
+		add_active_range(nid, ei_startpfn, ei_endpfn);
+	}
+}
+
 /* 
  * Add a memory region to the kernel e820 map.
  */ 
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/arch/x86_64/kernel/setup.c linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/x86_64/kernel/setup.c
--- linux-2.6.17-rc4-mm3-clean/arch/x86_64/kernel/setup.c	2006-05-22 11:25:40.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/x86_64/kernel/setup.c	2006-05-22 11:29:22.000000000 +0100
@@ -472,7 +472,8 @@ contig_initmem_init(unsigned long start_
 	if (bootmap == -1L)
 		panic("Cannot find bootmem map of size %ld\n",bootmap_size);
 	bootmap_size = init_bootmem(bootmap >> PAGE_SHIFT, end_pfn);
-	e820_bootmem_free(NODE_DATA(0), 0, end_pfn << PAGE_SHIFT);
+	e820_register_active_regions(0, start_pfn, end_pfn);
+	free_bootmem_with_active_regions(0, end_pfn);
 	reserve_bootmem(bootmap, bootmap_size);
 } 
 #endif
@@ -646,6 +647,7 @@ void __init setup_arch(char **cmdline_p)
 
 	early_identify_cpu(&boot_cpu_data);
 
+	e820_register_active_regions(0, 0, -1UL);
 	/*
 	 * partially used pages are not usable - thus
 	 * we are rounding upwards:
@@ -671,6 +673,9 @@ void __init setup_arch(char **cmdline_p)
 	acpi_boot_table_init();
 #endif
 
+	/* Remove active ranges so rediscovery with NUMA-awareness happens */
+	remove_all_active_ranges();
+
 #ifdef CONFIG_ACPI_NUMA
 	/*
 	 * Parse SRAT to discover nodes.
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/arch/x86_64/mm/init.c linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/x86_64/mm/init.c
--- linux-2.6.17-rc4-mm3-clean/arch/x86_64/mm/init.c	2006-05-22 11:25:40.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/x86_64/mm/init.c	2006-05-22 11:29:22.000000000 +0100
@@ -406,69 +406,12 @@ void __cpuinit zap_low_mappings(int cpu)
 	__flush_tlb_all();
 }
 
-/* Compute zone sizes for the DMA and DMA32 zones in a node. */
-__init void
-size_zones(unsigned long *z, unsigned long *h,
-	   unsigned long start_pfn, unsigned long end_pfn)
-{
- 	int i;
- 	unsigned long w;
-
- 	for (i = 0; i < MAX_NR_ZONES; i++)
- 		z[i] = 0;
-
- 	if (start_pfn < MAX_DMA_PFN)
- 		z[ZONE_DMA] = MAX_DMA_PFN - start_pfn;
- 	if (start_pfn < MAX_DMA32_PFN) {
- 		unsigned long dma32_pfn = MAX_DMA32_PFN;
- 		if (dma32_pfn > end_pfn)
- 			dma32_pfn = end_pfn;
- 		z[ZONE_DMA32] = dma32_pfn - start_pfn;
- 	}
- 	z[ZONE_NORMAL] = end_pfn - start_pfn;
-
- 	/* Remove lower zones from higher ones. */
- 	w = 0;
- 	for (i = 0; i < MAX_NR_ZONES; i++) {
- 		if (z[i])
- 			z[i] -= w;
- 	        w += z[i];
-	}
-
-	/* Compute holes */
-	w = start_pfn;
-	for (i = 0; i < MAX_NR_ZONES; i++) {
-		unsigned long s = w;
-		w += z[i];
-		h[i] = e820_hole_size(s, w);
-	}
-
-	/* Add the space pace needed for mem_map to the holes too. */
-	for (i = 0; i < MAX_NR_ZONES; i++)
-		h[i] += (z[i] * sizeof(struct page)) / PAGE_SIZE;
-
-	/* The 16MB DMA zone has the kernel and other misc mappings.
- 	   Account them too */
-	if (h[ZONE_DMA]) {
-		h[ZONE_DMA] += dma_reserve;
-		if (h[ZONE_DMA] >= z[ZONE_DMA]) {
-			printk(KERN_WARNING
-				"Kernel too large and filling up ZONE_DMA?\n");
-			h[ZONE_DMA] = z[ZONE_DMA];
-		}
-	}
-}
-
 #ifndef CONFIG_NUMA
 void __init paging_init(void)
 {
-	unsigned long zones[MAX_NR_ZONES], holes[MAX_NR_ZONES];
-
 	memory_present(0, 0, end_pfn);
 	sparse_init();
-	size_zones(zones, holes, 0, end_pfn);
-	free_area_init_node(0, NODE_DATA(0), zones,
-			    __pa(PAGE_OFFSET) >> PAGE_SHIFT, holes);
+	free_area_init_nodes(MAX_DMA_PFN, MAX_DMA32_PFN, end_pfn, end_pfn);
 }
 #endif
 
@@ -620,7 +563,8 @@ void __init mem_init(void)
 #else
 	totalram_pages = free_all_bootmem();
 #endif
-	reservedpages = end_pfn - totalram_pages - e820_hole_size(0, end_pfn);
+	reservedpages = end_pfn - totalram_pages -
+					absent_pages_in_range(0, end_pfn);
 
 	after_bootmem = 1;
 
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/arch/x86_64/mm/k8topology.c linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/x86_64/mm/k8topology.c
--- linux-2.6.17-rc4-mm3-clean/arch/x86_64/mm/k8topology.c	2006-05-12 00:31:53.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/x86_64/mm/k8topology.c	2006-05-22 11:29:22.000000000 +0100
@@ -146,6 +146,9 @@ int __init k8_scan_nodes(unsigned long s
 		
 		nodes[nodeid].start = base; 
 		nodes[nodeid].end = limit;
+		e820_register_active_regions(nodeid,
+				nodes[nodeid].start >> PAGE_SHIFT,
+				nodes[nodeid].end >> PAGE_SHIFT);
 
 		prevbase = base;
 
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/arch/x86_64/mm/numa.c linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/x86_64/mm/numa.c
--- linux-2.6.17-rc4-mm3-clean/arch/x86_64/mm/numa.c	2006-05-12 00:31:53.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/x86_64/mm/numa.c	2006-05-22 11:29:22.000000000 +0100
@@ -161,7 +161,7 @@ void __init setup_node_bootmem(int nodei
 					 bootmap_start >> PAGE_SHIFT, 
 					 start_pfn, end_pfn); 
 
-	e820_bootmem_free(NODE_DATA(nodeid), start, end);
+	free_bootmem_with_active_regions(nodeid, end);
 
 	reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys, pgdat_size); 
 	reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start, bootmap_pages<<PAGE_SHIFT);
@@ -175,13 +175,11 @@ void __init setup_node_bootmem(int nodei
 void __init setup_node_zones(int nodeid)
 { 
 	unsigned long start_pfn, end_pfn, memmapsize, limit;
-	unsigned long zones[MAX_NR_ZONES];
-	unsigned long holes[MAX_NR_ZONES];
 
  	start_pfn = node_start_pfn(nodeid);
  	end_pfn = node_end_pfn(nodeid);
 
-	Dprintk(KERN_INFO "Setting up node %d %lx-%lx\n",
+	Dprintk(KERN_INFO "Setting up memmap for node %d %lx-%lx\n",
 		nodeid, start_pfn, end_pfn);
 
 	/* Try to allocate mem_map at end to not fill up precious <4GB
@@ -195,10 +193,6 @@ void __init setup_node_zones(int nodeid)
 				round_down(limit - memmapsize, PAGE_SIZE), 
 				limit);
 #endif
-
-	size_zones(zones, holes, start_pfn, end_pfn);
-	free_area_init_node(nodeid, NODE_DATA(nodeid), zones,
-			    start_pfn, holes);
 } 
 
 void __init numa_init_array(void)
@@ -259,8 +253,11 @@ static int numa_emulation(unsigned long 
  		printk(KERN_ERR "No NUMA hash function found. Emulation disabled.\n");
  		return -1;
  	}
- 	for_each_online_node(i)
+ 	for_each_online_node(i) {
+		e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
+						nodes[i].end >> PAGE_SHIFT);
  		setup_node_bootmem(i, nodes[i].start, nodes[i].end);
+	}
  	numa_init_array();
  	return 0;
 }
@@ -299,6 +296,7 @@ void __init numa_initmem_init(unsigned l
 	for (i = 0; i < NR_CPUS; i++)
 		numa_set_node(i, 0);
 	node_to_cpumask[0] = cpumask_of_cpu(0);
+	e820_register_active_regions(0, start_pfn, end_pfn);
 	setup_node_bootmem(0, start_pfn << PAGE_SHIFT, end_pfn << PAGE_SHIFT);
 }
 
@@ -346,6 +344,8 @@ void __init paging_init(void)
 	for_each_online_node(i) {
 		setup_node_zones(i); 
 	}
+
+	free_area_init_nodes(MAX_DMA_PFN, MAX_DMA32_PFN, end_pfn, end_pfn);
 } 
 
 /* [numa=off] */
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/arch/x86_64/mm/srat.c linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/x86_64/mm/srat.c
--- linux-2.6.17-rc4-mm3-clean/arch/x86_64/mm/srat.c	2006-05-22 11:25:40.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/arch/x86_64/mm/srat.c	2006-05-22 11:29:22.000000000 +0100
@@ -91,6 +91,7 @@ static __init void bad_srat(void)
 		apicid_to_node[i] = NUMA_NO_NODE;
 	for (i = 0; i < MAX_NUMNODES; i++)
 		nodes_add[i].start = nodes[i].end = 0;
+	remove_all_active_ranges();
 }
 
 static __init inline int srat_disabled(void)
@@ -173,7 +174,7 @@ static int hotadd_enough_memory(struct b
 
 	if (mem < 0)
 		return 0;
-	allowed = (end_pfn - e820_hole_size(0, end_pfn)) * PAGE_SIZE;
+	allowed = (end_pfn - absent_pages_in_range(0, end_pfn)) * PAGE_SIZE;
 	allowed = (allowed / 100) * hotadd_percent;
 	if (allocated + mem > allowed) {
 		unsigned long range;
@@ -223,7 +224,7 @@ static int reserve_hotadd(int node, unsi
 	}
 
 	/* This check might be a bit too strict, but I'm keeping it for now. */
-	if (e820_hole_size(s_pfn, e_pfn) != e_pfn - s_pfn) {
+	if (absent_pages_in_range(s_pfn, e_pfn) != e_pfn - s_pfn) {
 		printk(KERN_ERR "SRAT: Hotplug area has existing memory\n");
 		return -1;
 	}
@@ -317,6 +318,8 @@ acpi_numa_memory_affinity_init(struct ac
 
 	printk(KERN_INFO "SRAT: Node %u PXM %u %Lx-%Lx\n", node, pxm,
 	       nd->start, nd->end);
+	e820_register_active_regions(node, nd->start >> PAGE_SHIFT,
+						nd->end >> PAGE_SHIFT);
 
 #ifdef RESERVE_HOTADD
  	if (ma->flags.hot_pluggable && reserve_hotadd(node, start, end) < 0) {
@@ -341,13 +344,13 @@ static int nodes_cover_memory(void)
 		unsigned long s = nodes[i].start >> PAGE_SHIFT;
 		unsigned long e = nodes[i].end >> PAGE_SHIFT;
 		pxmram += e - s;
-		pxmram -= e820_hole_size(s, e);
+		pxmram -= absent_pages_in_range(s, e);
 		pxmram -= nodes_add[i].end - nodes_add[i].start;
 		if ((long)pxmram < 0)
 			pxmram = 0;
 	}
 
-	e820ram = end_pfn - e820_hole_size(0, end_pfn);
+	e820ram = end_pfn - absent_pages_in_range(0, end_pfn);
 	/* We seem to lose 3 pages somewhere. Allow a bit of slack. */
 	if ((long)(e820ram - pxmram) >= 1*1024*1024) {
 		printk(KERN_ERR
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/include/asm-ia64/meminit.h linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/include/asm-ia64/meminit.h
--- linux-2.6.17-rc4-mm3-clean/include/asm-ia64/meminit.h	2006-05-22 11:25:42.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/include/asm-ia64/meminit.h	2006-05-22 11:30:19.000000000 +0100
@@ -55,6 +55,7 @@ extern void efi_memmap_init(unsigned lon
   extern unsigned long vmalloc_end;
   extern struct page *vmem_map;
   extern int find_largest_hole (u64 start, u64 end, void *arg);
+  extern int register_active_ranges (u64 start, u64 end, void *arg);
   extern int create_mem_map_page_table (u64 start, u64 end, void *arg);
 #endif
 
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/include/asm-x86_64/e820.h linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/include/asm-x86_64/e820.h
--- linux-2.6.17-rc4-mm3-clean/include/asm-x86_64/e820.h	2006-05-12 00:31:53.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/include/asm-x86_64/e820.h	2006-05-22 11:29:22.000000000 +0100
@@ -50,10 +50,9 @@ extern void e820_print_map(char *who);
 extern int e820_any_mapped(unsigned long start, unsigned long end, unsigned type);
 extern int e820_all_mapped(unsigned long start, unsigned long end, unsigned type);
 
-extern void e820_bootmem_free(pg_data_t *pgdat, unsigned long start,unsigned long end);
 extern void e820_setup_gap(void);
-extern unsigned long e820_hole_size(unsigned long start_pfn,
-				    unsigned long end_pfn);
+extern void e820_register_active_regions(int nid,
+				unsigned long start_pfn, unsigned long end_pfn);
 
 extern void __init parse_memopt(char *p, char **end);
 extern void __init parse_memmapopt(char *p, char **end);
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/include/asm-x86_64/proto.h linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/include/asm-x86_64/proto.h
--- linux-2.6.17-rc4-mm3-clean/include/asm-x86_64/proto.h	2006-05-22 11:25:42.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/include/asm-x86_64/proto.h	2006-05-22 11:29:22.000000000 +0100
@@ -24,8 +24,6 @@ extern void mtrr_bp_init(void);
 #define mtrr_bp_init() do {} while (0)
 #endif
 extern void init_memory_mapping(unsigned long start, unsigned long end);
-extern void size_zones(unsigned long *z, unsigned long *h,
-			unsigned long start_pfn, unsigned long end_pfn);
 
 extern void system_call(void); 
 extern int kernel_syscall(void);
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/include/linux/mm.h linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/include/linux/mm.h
--- linux-2.6.17-rc4-mm3-clean/include/linux/mm.h	2006-05-22 11:25:42.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/include/linux/mm.h	2006-05-24 10:43:31.000000000 +0100
@@ -922,6 +922,51 @@ extern void free_area_init(unsigned long
 extern void free_area_init_node(int nid, pg_data_t *pgdat,
 	unsigned long * zones_size, unsigned long zone_start_pfn, 
 	unsigned long *zholes_size);
+#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+/*
+ * With CONFIG_ARCH_POPULATES_NODE_MAP set, an architecture may initialise its
+ * zones, allocate the backing mem_map and account for memory holes in an
+ * architecture independent manner. This is a substitute for creating the
+ * zone_sizes[] and zholes_size[] arrays and passing them to
+ * free_area_init_node()
+ *
+ * An architecture is expected to register range of page frames backed by
+ * physical memory with add_active_range() before calling
+ * free_area_init_nodes() passing in the PFN each zone ends at. At a basic
+ * usage, an architecture is expected to do something like
+ *
+ * for_each_valid_physical_page_range()
+ * 	add_active_range(node_id, start_pfn, end_pfn)
+ * free_area_init_nodes(max_dma, max_dma32, max_normal_pfn, max_highmem_pfn);
+ *
+ * If the architecture guarantees that there are no holes in the ranges
+ * registered with add_active_range(), free_bootmem_active_regions()
+ * will call free_bootmem_node() for each registered physical page range.
+ * Similarly sparse_memory_present_with_active_regions() calls
+ * memory_present() for each range when SPARSEMEM is enabled.
+ *
+ * See mm/page_alloc.c for more information on each function exposed by
+ * CONFIG_ARCH_POPULATES_NODE_MAP
+ */
+extern void free_area_init_nodes(unsigned long max_dma_pfn,
+					unsigned long max_dma32_pfn,
+					unsigned long max_low_pfn,
+					unsigned long max_high_pfn);
+extern void add_active_range(unsigned int nid, unsigned long start_pfn,
+					unsigned long end_pfn);
+extern void shrink_active_range(unsigned int nid, unsigned long old_end_pfn,
+						unsigned long new_end_pfn);
+extern void remove_all_active_ranges(void);
+extern unsigned long absent_pages_in_range(unsigned long start_pfn,
+						unsigned long end_pfn);
+extern void get_pfn_range_for_nid(unsigned int nid,
+			unsigned long *start_pfn, unsigned long *end_pfn);
+extern unsigned long find_min_pfn_with_active_regions(void);
+extern unsigned long find_max_pfn_with_active_regions(void);
+extern void free_bootmem_with_active_regions(int nid,
+						unsigned long max_low_pfn);
+extern void sparse_memory_present_with_active_regions(int nid);
+#endif
 extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long);
 extern void setup_per_zone_pages_min(void);
 extern void mem_init(void);
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/include/linux/mmzone.h linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/include/linux/mmzone.h
--- linux-2.6.17-rc4-mm3-clean/include/linux/mmzone.h	2006-05-22 11:25:42.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/include/linux/mmzone.h	2006-05-22 11:26:26.000000000 +0100
@@ -271,6 +271,13 @@ struct zonelist {
 	struct zone *zones[MAX_NUMNODES * MAX_NR_ZONES + 1]; // NULL delimited
 };
 
+#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+struct node_active_region {
+	unsigned long start_pfn;
+	unsigned long end_pfn;
+	int nid;
+};
+#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
 
 /*
  * The pg_data_t structure is used in machines with CONFIG_DISCONTIGMEM
@@ -477,7 +484,8 @@ extern struct zone *next_zone(struct zon
 
 #endif
 
-#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
+#if !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) && \
+	!defined(CONFIG_ARCH_POPULATES_NODE_MAP)
 #define early_pfn_to_nid(nid)  (0UL)
 #endif
 
diff -rup -X /usr/src/patchset-0.5/bin//dontdiff linux-2.6.17-rc4-mm3-clean/mm/page_alloc.c linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/mm/page_alloc.c
--- linux-2.6.17-rc4-mm3-clean/mm/page_alloc.c	2006-05-22 11:25:42.000000000 +0100
+++ linux-2.6.17-rc4-mm3-105-ia64_use_init_nodes/mm/page_alloc.c	2006-05-24 11:07:09.000000000 +0100
@@ -38,6 +38,8 @@
 #include <linux/vmalloc.h>
 #include <linux/mempolicy.h>
 #include <linux/stop_machine.h>
+#include <linux/sort.h>
+#include <linux/pfn.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -87,6 +89,33 @@ int min_free_kbytes = 1024;
 unsigned long __meminitdata nr_kernel_pages;
 unsigned long __meminitdata nr_all_pages;
 
+#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+  /*
+   * MAX_ACTIVE_REGIONS determines the maxmimum number of distinct
+   * ranges of memory that may be registered with add_active_range().
+   * Ranges passed to add_active_range() will be merged if possible
+   * so the number of times add_active_range() can be called is
+   * related to the number of nodes and the number of holes
+   */
+  #ifdef CONFIG_MAX_ACTIVE_REGIONS
+    /* Allow an architecture to set MAX_ACTIVE_REGIONS to save memory */
+    #define MAX_ACTIVE_REGIONS CONFIG_MAX_ACTIVE_REGIONS
+  #else
+    #if MAX_NUMNODES >= 128
+      /* If there can be many nodes, allow up to 50 holes per node */
+      #define MAX_ACTIVE_REGIONS (MAX_NUMNODES*50)
+    #else
+      /* By default, allow up to 256 distinct regions */
+      #define MAX_ACTIVE_REGIONS 256
+    #endif
+  #endif
+
+  struct node_active_region __initdata early_node_map[MAX_ACTIVE_REGIONS];
+  int __initdata nr_nodemap_entries;
+  unsigned long __initdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES];
+  unsigned long __initdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
+#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
+
 #ifdef CONFIG_DEBUG_VM
 static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
 {
@@ -1872,25 +1901,6 @@ static inline unsigned long wait_table_b
 
 #define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1))
 
-static void __init calculate_zone_totalpages(struct pglist_data *pgdat,
-		unsigned long *zones_size, unsigned long *zholes_size)
-{
-	unsigned long realtotalpages, totalpages = 0;
-	int i;
-
-	for (i = 0; i < MAX_NR_ZONES; i++)
-		totalpages += zones_size[i];
-	pgdat->node_spanned_pages = totalpages;
-
-	realtotalpages = totalpages;
-	if (zholes_size)
-		for (i = 0; i < MAX_NR_ZONES; i++)
-			realtotalpages -= zholes_size[i];
-	pgdat->node_present_pages = realtotalpages;
-	printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages);
-}
-
-
 /*
  * Initially all pages are reserved - free ones are freed
  * up by free_all_bootmem() once the early boot process is
@@ -2208,6 +2218,271 @@ __meminit int init_currently_empty_zone(
 	return 0;
 }
 
+#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+/*
+ * Basic iterator support. Return the first range of PFNs for a node
+ * Note: nid == MAX_NUMNODES returns first region regardless of node
+ */
+static int __init first_active_region_index_in_nid(int nid)
+{
+	int i;
+	for (i = 0; i < nr_nodemap_entries; i++) {
+		if (nid == MAX_NUMNODES || early_node_map[i].nid == nid)
+			return i;
+	}
+
+	return -1;
+}
+
+/*
+ * Basic iterator support. Return the next active range of PFNs for a node
+ * Note: nid == MAX_NUMNODES returns next region regardles of node
+ */
+static int __init next_active_region_index_in_nid(int index, int nid)
+{
+	for (index = index + 1; index < nr_nodemap_entries; index++) {
+		if (nid == MAX_NUMNODES || early_node_map[index].nid == nid)
+			return index;
+	}
+
+	return -1;
+}
+
+#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
+/*
+ * Required by SPARSEMEM. Given a PFN, return what node the PFN is on.
+ * Architectures may implement their own version but if add_active_range()
+ * was used and there are no special requirements, this is a convenient
+ * alternative
+ */
+int __init early_pfn_to_nid(unsigned long pfn)
+{
+	int i;
+
+	for (i = 0; i < nr_nodemap_entries; i++) {
+		unsigned long start_pfn = early_node_map[i].start_pfn;
+		unsigned long end_pfn = early_node_map[i].end_pfn;
+
+		if ((start_pfn <= pfn) && (pfn < end_pfn))
+			return early_node_map[i].nid;
+	}
+
+	return 0;
+}
+#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */
+
+/* Basic iterator support to walk early_node_map[] */
+#define for_each_active_range_index_in_nid(i, nid) \
+	for (i = first_active_region_index_in_nid(nid); \
+				i != -1; \
+				i = next_active_region_index_in_nid(i, nid))
+
+/**
+ * free_bootmem_with_active_regions - Call free_bootmem_node for each active range
+ * @nid: The node to free memory on
+ * @max_low_pfn: The highest PFN that till be passed to free_bootmem_node
+ *
+ * If an architecture guarantees that all ranges registered with
+ * add_active_ranges() contain no holes and may be freed, this
+ * this function may be used instead of calling free_bootmem() manually.
+ */
+void __init free_bootmem_with_active_regions(int nid,
+						unsigned long max_low_pfn)
+{
+	int i;
+	for_each_active_range_index_in_nid(i, nid) {
+		unsigned long size_pages = 0;
+		unsigned long end_pfn = early_node_map[i].end_pfn;
+		if (early_node_map[i].start_pfn >= max_low_pfn)
+			continue;
+
+		if (end_pfn > max_low_pfn)
+			end_pfn = max_low_pfn;
+
+		size_pages = end_pfn - early_node_map[i].start_pfn;
+		free_bootmem_node(NODE_DATA(early_node_map[i].nid),
+				PFN_PHYS(early_node_map[i].start_pfn),
+				size_pages << PAGE_SHIFT);
+	}
+}
+
+/**
+ * sparse_memory_present_with_active_regions - Call memory_present for each active range
+ * @nid: The node to call memory_present for
+ *
+ * If an architecture guarantees that all ranges registered with
+ * add_active_ranges() contain no holes and may be freed, this
+ * this function may be used instead of calling memory_present() manually.
+ */
+void __init sparse_memory_present_with_active_regions(int nid)
+{
+	int i;
+	for_each_active_range_index_in_nid(i, nid)
+		memory_present(early_node_map[i].nid,
+				early_node_map[i].start_pfn,
+				early_node_map[i].end_pfn);
+}
+
+/**
+ * get_pfn_range_for_nid - Return the start and end page frames for a node
+ * @nid: The nid to return the range for
+ * @start_pfn: Passed by reference. On return, it will have the node start_pfn
+ * @end_pfn: Passed by reference. On return, it will have the node end_pfn
+ *
+ * It returns the start and end page frame of a node based on information
+ * provided by an arch calling add_active_range(). If called for a node
+ * with no available memory, a warning is printed and the start and end
+ * PFNs will be 0
+ */
+void __init get_pfn_range_for_nid(unsigned int nid,
+			unsigned long *start_pfn, unsigned long *end_pfn)
+{
+	int i;
+	*start_pfn = -1UL;
+	*end_pfn = 0;
+
+	for_each_active_range_index_in_nid(i, nid) {
+		*start_pfn = min(*start_pfn, early_node_map[i].start_pfn);
+		*end_pfn = max(*end_pfn, early_node_map[i].end_pfn);
+	}
+
+	if (*start_pfn == -1UL) {
+		printk(KERN_WARNING "Node %u active with no memory\n", nid);
+		*start_pfn = 0;
+	}
+}
+
+/*
+ * Return the number of pages a zone spans in a node, including holes
+ * present_pages = zone_spanned_pages_in_node() - zone_absent_pages_in_node()
+ */
+unsigned long __init zone_spanned_pages_in_node(int nid,
+					unsigned long zone_type,
+					unsigned long *ignored)
+{
+	unsigned long node_start_pfn, node_end_pfn;
+	unsigned long zone_start_pfn, zone_end_pfn;
+
+	/* Get the start and end of the node and zone */
+	get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn);
+	zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type];
+	zone_end_pfn = arch_zone_highest_possible_pfn[zone_type];
+
+	/* Check that this node has pages within the zone's required range */
+	if (zone_end_pfn < node_start_pfn || zone_start_pfn > node_end_pfn)
+		return 0;
+
+	/* Move the zone boundaries inside the node if necessary */
+	zone_end_pfn = min(zone_end_pfn, node_end_pfn);
+	zone_start_pfn = max(zone_start_pfn, node_start_pfn);
+
+	/* Return the spanned pages */
+	return zone_end_pfn - zone_start_pfn;
+}
+
+/*
+ * Return the number of holes in a range on a node. If nid is MAX_NUMNODES,
+ * then all holes in the requested range will be accounted for
+ */
+unsigned long __init __absent_pages_in_range(int nid,
+				unsigned long range_start_pfn,
+				unsigned long range_end_pfn)
+{
+	int i = 0;
+	unsigned long prev_end_pfn = 0, hole_pages = 0;
+	unsigned long start_pfn;
+
+	/* Find the end_pfn of the first active range of pfns in the node */
+	i = first_active_region_index_in_nid(nid);
+	if (i == -1)
+		return 0;
+	prev_end_pfn = early_node_map[i].start_pfn;
+
+	/* Find all holes for the zone within the node */
+	for (; i != -1; i = next_active_region_index_in_nid(i, nid)) {
+
+		/* No need to continue if prev_end_pfn is outside the zone */
+		if (prev_end_pfn >= range_end_pfn)
+			break;
+
+		/* Make sure the end of the zone is not within the hole */
+		start_pfn = min(early_node_map[i].start_pfn, range_end_pfn);
+		prev_end_pfn = max(prev_end_pfn, range_start_pfn);
+
+		/* Update the hole size cound and move on */
+		if (start_pfn > range_start_pfn) {
+			BUG_ON(prev_end_pfn > start_pfn);
+			hole_pages += start_pfn - prev_end_pfn;
+		}
+		prev_end_pfn = early_node_map[i].end_pfn;
+	}
+
+	return hole_pages;
+}
+
+/**
+ * absent_pages_in_range - Return number of page frames in holes within a range
+ * @start_pfn: The start PFN to start searching for holes
+ * @end_pfn: The end PFN to stop searching for holes
+ *
+ * It returns the number of pages frames in memory holes within a range
+ */
+unsigned long __init absent_pages_in_range(unsigned long start_pfn,
+							unsigned long end_pfn)
+{
+	return __absent_pages_in_range(MAX_NUMNODES, start_pfn, end_pfn);
+}
+
+/* Return the number of page frames in holes in a zone on a node */
+unsigned long __init zone_absent_pages_in_node(int nid,
+					unsigned long zone_type,
+					unsigned long *ignored)
+{
+	return __absent_pages_in_range(nid,
+				arch_zone_lowest_possible_pfn[zone_type],
+				arch_zone_highest_possible_pfn[zone_type]);
+}
+#else
+static inline unsigned long zone_spanned_pages_in_node(int nid,
+					unsigned long zone_type,
+					unsigned long *zones_size)
+{
+	return zones_size[zone_type];
+}
+
+static inline unsigned long zone_absent_pages_in_node(int nid,
+						unsigned long zone_type,
+						unsigned long *zholes_size)
+{
+	if (!zholes_size)
+		return 0;
+
+	return zholes_size[zone_type];
+}
+#endif
+
+static void __init calculate_node_totalpages(struct pglist_data *pgdat,
+		unsigned long *zones_size, unsigned long *zholes_size)
+{
+	unsigned long realtotalpages, totalpages = 0;
+	int i;
+
+	for (i = 0; i < MAX_NR_ZONES; i++) {
+		totalpages += zone_spanned_pages_in_node(pgdat->node_id, i,
+								zones_size);
+	}
+	pgdat->node_spanned_pages = totalpages;
+
+	realtotalpages = totalpages;
+	for (i = 0; i < MAX_NR_ZONES; i++) {
+		realtotalpages -=
+			zone_absent_pages_in_node(pgdat->node_id, i, zholes_size);
+	}
+	pgdat->node_present_pages = realtotalpages;
+	printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id,
+							realtotalpages);
+}
+
 /*
  * Set up the zone data structures:
  *   - mark all pages reserved
@@ -2231,10 +2506,9 @@ static void __meminit free_area_init_cor
 		struct zone *zone = pgdat->node_zones + j;
 		unsigned long size, realsize;
 
-		realsize = size = zones_size[j];
-		if (zholes_size)
-			realsize -= zholes_size[j];
-
+		size = zone_spanned_pages_in_node(nid, j, zones_size);
+		realsize = size - zone_absent_pages_in_node(nid, j,
+								zholes_size);
 		if (j < ZONE_HIGHMEM)
 			nr_kernel_pages += realsize;
 		nr_all_pages += realsize;
@@ -2325,13 +2599,243 @@ void __meminit free_area_init_node(int n
 {
 	pgdat->node_id = nid;
 	pgdat->node_start_pfn = node_start_pfn;
-	calculate_zone_totalpages(pgdat, zones_size, zholes_size);
+	calculate_node_totalpages(pgdat, zones_size, zholes_size);
 
 	alloc_node_mem_map(pgdat);
 
 	free_area_init_core(pgdat, zones_size, zholes_size);
 }
 
+#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+/**
+ * add_active_range - Register a range of PFNs backed by physical memory
+ * @nid: The node ID the range resides on
+ * @start_pfn: The start PFN of the available physical memory
+ * @end_pfn: The end PFN of the available physical memory
+ *
+ * These ranges are stored in an early_node_map[] and later used by
+ * free_area_init_nodes() to calculate zone sizes and holes. If the
+ * range spans a memory hole, it is up to the architecture to ensure
+ * the memory is not freed by the bootmem allocator. If possible
+ * the range being registered will be merged with existing ranges.
+ */
+void __init add_active_range(unsigned int nid, unsigned long start_pfn,
+						unsigned long end_pfn)
+{
+	int i;
+	printk("Entering add_active_range(%d, %lu, %lu) "
+			  "%d entries of %d used\n",
+			  nid, start_pfn, end_pfn,
+			  nr_nodemap_entries, MAX_ACTIVE_REGIONS);
+
+	/* Merge with existing active regions if possible */
+	for (i = 0; i < nr_nodemap_entries; i++) {
+		if (early_node_map[i].nid != nid)
+			continue;
+
+		/* Skip if an existing region covers this new one */
+		if (start_pfn >= early_node_map[i].start_pfn &&
+				end_pfn <= early_node_map[i].end_pfn) {
+			return;
+		}
+
+		/* Merge forward if suitable */
+		if (start_pfn <= early_node_map[i].end_pfn &&
+				end_pfn > early_node_map[i].end_pfn) {
+			early_node_map[i].end_pfn = end_pfn;
+			return;
+		}
+
+		/* Merge backward if suitable */
+		if (start_pfn < early_node_map[i].end_pfn &&
+				end_pfn >= early_node_map[i].start_pfn) {
+			early_node_map[i].start_pfn = start_pfn;
+			return;
+		}
+	}
+
+	/* Check that early_node_map is large enough */
+	if (i >= MAX_ACTIVE_REGIONS) {
+		printk(KERN_CRIT "More than %d memory regions, truncating\n",
+							MAX_ACTIVE_REGIONS);
+		return;
+	}
+
+	early_node_map[i].nid = nid;
+	early_node_map[i].start_pfn = start_pfn;
+	early_node_map[i].end_pfn = end_pfn;
+	nr_nodemap_entries = i + 1;
+}
+
+/**
+ * shrink_active_range - Shrink an existing registered range of PFNs
+ * @nid: The node id the range is on that should be shrunk
+ * @old_end_pfn: The old end PFN of the range
+ * @new_end_pfn: The new PFN of the range
+ *
+ * i386 with NUMA use alloc_remap() to store a node_mem_map on a local node.
+ * The map is kept at the end physical page range that has already been
+ * registered with add_active_range(). This function allows an arch to shrink
+ * an existing registered range.
+ */
+void __init shrink_active_range(unsigned int nid, unsigned long old_end_pfn,
+						unsigned long new_end_pfn)
+{
+	int i;
+
+	/* Find the old active region end and shrink */
+	for_each_active_range_index_in_nid(i, nid) {
+		if (early_node_map[i].end_pfn == old_end_pfn) {
+			early_node_map[i].end_pfn = new_end_pfn;
+			break;
+		}
+	}
+}
+
+/**
+ * remove_all_active_ranges - Remove all currently registered regions
+ * During discovery, it may be found that a table like SRAT is invalid
+ * and an alternative discovery method must be used. This function removes
+ * all currently registered regions.
+ */
+void __init remove_all_active_ranges()
+{
+	memset(early_node_map, 0, sizeof(early_node_map));
+	nr_nodemap_entries = 0;
+}
+
+/* Compare two active node_active_regions */
+static int __init cmp_node_active_region(const void *a, const void *b)
+{
+	struct node_active_region *arange = (struct node_active_region *)a;
+	struct node_active_region *brange = (struct node_active_region *)b;
+
+	/* Done this way to avoid overflows */
+	if (arange->start_pfn > brange->start_pfn)
+		return 1;
+	if (arange->start_pfn < brange->start_pfn)
+		return -1;
+
+	return 0;
+}
+
+/* sort the node_map by start_pfn */
+static void __init sort_node_map(void)
+{
+	sort(early_node_map, (size_t)nr_nodemap_entries,
+			sizeof(struct node_active_region),
+			cmp_node_active_region, NULL);
+}
+
+/* Find the lowest pfn for a node. This depends on a sorted early_node_map */
+unsigned long __init find_min_pfn_for_node(unsigned long nid)
+{
+	int i;
+
+	/* Assuming a sorted map, the first range found has the starting pfn */
+	for_each_active_range_index_in_nid(i, nid)
+		return early_node_map[i].start_pfn;
+
+	printk(KERN_WARNING "Could not find start_pfn for node %lu\n", nid);
+	return 0;
+}
+
+/**
+ * find_min_pfn_with_active_regions - Find the minimum PFN registered
+ *
+ * It returns the minimum PFN based on information provided via
+ * add_active_range()
+ */
+unsigned long __init find_min_pfn_with_active_regions(void)
+{
+	return find_min_pfn_for_node(MAX_NUMNODES);
+}
+
+/**
+ * find_max_pfn_with_active_regions - Find the maximum PFN registered
+ *
+ * It returns the maximum PFN based on information provided via
+ * add_active_range()
+ */
+unsigned long __init find_max_pfn_with_active_regions(void)
+{
+	int i;
+	unsigned long max_pfn = 0;
+
+	for (i = 0; i < nr_nodemap_entries; i++)
+		max_pfn = max(max_pfn, early_node_map[i].end_pfn);
+
+	return max_pfn;
+}
+
+/**
+ * free_area_init_nodes - Initialise all pg_data_t and zone data
+ * @arch_max_dma_pfn: The maximum PFN usable for ZONE_DMA
+ * @arch_max_dma32_pfn: The maximum PFN usable for ZONE_DMA32
+ * @arch_max_low_pfn: The maximum PFN usable for ZONE_NORMAL
+ * @arch_max_high_pfn: The maximum PFN usable for ZONE_HIGHMEM
+ *
+ * This will call free_area_init_node() for each active node in the system.
+ * Using the page ranges provided by add_active_range(), the size of each
+ * zone in each node and their holes is calculated. If the maximum PFN
+ * between two adjacent zones match, it is assumed that the zone is empty.
+ * For example, if arch_max_dma_pfn == arch_max_dma32_pfn, it is assumed
+ * that arch_max_dma32_pfn has no pages. It is also assumed that a zone
+ * starts where the previous one ended. For example, ZONE_DMA32 starts
+ * at arch_max_dma_pfn.
+ */
+void __init free_area_init_nodes(unsigned long arch_max_dma_pfn,
+				unsigned long arch_max_dma32_pfn,
+				unsigned long arch_max_low_pfn,
+				unsigned long arch_max_high_pfn)
+{
+	unsigned long nid;
+	int i;
+
+	/* Record where the zone boundaries are */
+	memset(arch_zone_lowest_possible_pfn, 0,
+				sizeof(arch_zone_lowest_possible_pfn));
+	memset(arch_zone_highest_possible_pfn, 0,
+				sizeof(arch_zone_highest_possible_pfn));
+	arch_zone_lowest_possible_pfn[ZONE_DMA] =
+					find_min_pfn_with_active_regions();
+	arch_zone_highest_possible_pfn[ZONE_DMA] = arch_max_dma_pfn;
+	arch_zone_highest_possible_pfn[ZONE_DMA32] = arch_max_dma32_pfn;
+	arch_zone_highest_possible_pfn[ZONE_NORMAL] = arch_max_low_pfn;
+	arch_zone_highest_possible_pfn[ZONE_HIGHMEM] = arch_max_high_pfn;
+	for (i = 1; i < MAX_NR_ZONES; i++) {
+		arch_zone_lowest_possible_pfn[i] =
+			arch_zone_highest_possible_pfn[i-1];
+	}
+
+	/* Regions in the early_node_map can be in any order */
+	sort_node_map();
+
+	/* Print out the zone ranges */
+	printk("Zone PFN ranges:\n");
+	for (i = 0; i < MAX_NR_ZONES; i++) {
+		printk("  %-8s %8lu -> %8lu\n",
+				zone_names[i],
+				arch_zone_lowest_possible_pfn[i],
+				arch_zone_highest_possible_pfn[i]);
+	}
+
+	/* Print out the early_node_map[] */
+	printk("early_node_map[%d] active PFN ranges\n", nr_nodemap_entries);
+	for (i = 0; i < nr_nodemap_entries; i++)
+		printk("  %3d: %8lu -> %8lu\n", early_node_map[i].nid,
+						early_node_map[i].start_pfn,
+						early_node_map[i].end_pfn);
+
+	/* Initialise every node */
+	for_each_online_node(nid) {
+		pg_data_t *pgdat = NODE_DATA(nid);
+		free_area_init_node(nid, pgdat, NULL,
+				find_min_pfn_for_node(nid), NULL);
+	}
+}
+#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
+
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 static bootmem_data_t contig_bootmem_data;
 struct pglist_data contig_page_data = { .bdata = &contig_bootmem_data };