diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index 93626e699679..731d211a1b20 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -54,6 +54,8 @@ static inline phys_addr_t get_max_mapped(void)
 extern unsigned long init_memory_mapping(unsigned long start,
 					 unsigned long end);
 
+void init_memory_mapping_high(void);
+
 extern void initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 				int acpi, int k8);
 extern void free_initmem(void);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 3def8c9a5dc9..fc0fe743f3a1 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -931,14 +931,6 @@ void __init setup_arch(char **cmdline_p)
 	max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT);
 	max_pfn_mapped = max_low_pfn_mapped;
 
-#ifdef CONFIG_X86_64
-	if (max_pfn > max_low_pfn) {
-		max_pfn_mapped = init_memory_mapping(1UL<<32,
-						     max_pfn<<PAGE_SHIFT);
-		/* can we preseve max_low_pfn ?*/
-		max_low_pfn = max_pfn;
-	}
-#endif
 	memblock.current_limit = get_max_mapped();
 
 	/*
diff --git a/arch/x86/mm/amdtopology_64.c b/arch/x86/mm/amdtopology_64.c
index 51fae9cfdecb..ae6ad691a14a 100644
--- a/arch/x86/mm/amdtopology_64.c
+++ b/arch/x86/mm/amdtopology_64.c
@@ -221,12 +221,14 @@ int __init amd_scan_nodes(void)
 		apicid_base = boot_cpu_physical_apicid;
 	}
 
-	for_each_node_mask(i, node_possible_map) {
-		int j;
-
+	for_each_node_mask(i, node_possible_map)
 		memblock_x86_register_active_regions(i,
 				nodes[i].start >> PAGE_SHIFT,
 				nodes[i].end >> PAGE_SHIFT);
+	init_memory_mapping_high();
+	for_each_node_mask(i, node_possible_map) {
+		int j;
+
 		for (j = apicid_base; j < cores + apicid_base; j++)
 			apicid_to_node[(i << bits) + j] = i;
 		setup_node_bootmem(i, nodes[i].start, nodes[i].end);
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 5863950ebe0c..fa6fe756d912 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -65,16 +65,10 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
 #ifdef CONFIG_X86_32
 	/* for fixmap */
 	tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE);
-#endif
 
-	/*
-	 * RED-PEN putting page tables only on node 0 could
-	 * cause a hotspot and fill up ZONE_DMA. The page tables
-	 * need roughly 0.5KB per GB.
-	 */
-#ifdef CONFIG_X86_32
 	good_end = max_pfn_mapped << PAGE_SHIFT;
 #endif
+
 	base = memblock_find_in_range(start, good_end, tables, PAGE_SIZE);
 	if (base == MEMBLOCK_ERROR)
 		panic("Cannot find space for the kernel page tables");
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 024847dc81ab..194f2732ab77 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -607,9 +607,63 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 				int acpi, int k8)
 {
 	memblock_x86_register_active_regions(0, start_pfn, end_pfn);
+	init_memory_mapping_high();
 }
 #endif
 
+struct mapping_work_data {
+	unsigned long start;
+	unsigned long end;
+	unsigned long pfn_mapped;
+};
+
+static int __init_refok
+mapping_work_fn(unsigned long start_pfn, unsigned long end_pfn, void *datax)
+{
+	struct mapping_work_data *data = datax;
+	unsigned long pfn_mapped;
+	unsigned long final_start, final_end;
+
+	final_start = max_t(unsigned long, start_pfn<<PAGE_SHIFT, data->start);
+	final_end = min_t(unsigned long, end_pfn<<PAGE_SHIFT, data->end);
+
+	if (final_end <= final_start)
+		return 0;
+
+	pfn_mapped = init_memory_mapping(final_start, final_end);
+
+	if (pfn_mapped > data->pfn_mapped)
+		data->pfn_mapped = pfn_mapped;
+
+	return 0;
+}
+
+static unsigned long __init_refok
+init_memory_mapping_active_regions(unsigned long start, unsigned long end)
+{
+	struct mapping_work_data data;
+
+	data.start = start;
+	data.end = end;
+	data.pfn_mapped = 0;
+
+	work_with_active_regions(MAX_NUMNODES, mapping_work_fn, &data);
+
+	return data.pfn_mapped;
+}
+
+void __init_refok init_memory_mapping_high(void)
+{
+	if (max_pfn > max_low_pfn) {
+		max_pfn_mapped = init_memory_mapping_active_regions(1UL<<32,
+							 max_pfn<<PAGE_SHIFT);
+		/* can we preserve max_low_pfn ? */
+		max_low_pfn = max_pfn;
+
+		memblock.current_limit = get_max_mapped();
+	}
+}
+
 void __init paging_init(void)
 {
 	unsigned long max_zone_pfns[MAX_NR_ZONES];
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 02d36ff85ebd..7cc26ae0a15d 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -590,11 +590,12 @@ static int __init numa_emulation(unsigned long start_pfn,
 	 * the e820 memory map.
 	 */
 	remove_all_active_ranges();
-	for_each_node_mask(i, node_possible_map) {
+	for_each_node_mask(i, node_possible_map)
 		memblock_x86_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
 						nodes[i].end >> PAGE_SHIFT);
+	init_memory_mapping_high();
+	for_each_node_mask(i, node_possible_map)
 		setup_node_bootmem(i, nodes[i].start, nodes[i].end);
-	}
 	acpi_fake_nodes(nodes, num_nodes);
 	numa_init_array();
 	return 0;
@@ -645,6 +646,7 @@ void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn,
 	for (i = 0; i < nr_cpu_ids; i++)
 		numa_set_node(i, 0);
 	memblock_x86_register_active_regions(0, start_pfn, last_pfn);
+	init_memory_mapping_high();
 	setup_node_bootmem(0, start_pfn << PAGE_SHIFT, last_pfn << PAGE_SHIFT);
 }
 
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index a35cb9d8b060..0b961c8bffb4 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -433,6 +433,8 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
 		return -1;
 	}
 
+	init_memory_mapping_high();
+
 	/* Account for nodes with cpus and no memory */
 	nodes_or(node_possible_map, nodes_parsed, cpu_nodes_parsed);