---
 arch/x86/kernel/setup64.c |   34 ++++++++++++++--------------------
 init/main.c               |   18 ++++++++++--------
 2 files changed, 24 insertions(+), 28 deletions(-)

Index: linux-2.6/init/main.c
===================================================================
--- linux-2.6.orig/init/main.c	2007-11-14 12:00:29.977593497 -0800
+++ linux-2.6/init/main.c	2007-11-15 21:33:32.001129814 -0800
@@ -370,18 +370,20 @@ EXPORT_SYMBOL(__per_cpu_offset);
 
 static void __init setup_per_cpu_areas(void)
 {
-	unsigned long size, i;
 	char *ptr;
-	unsigned long nr_possible_cpus = num_possible_cpus();
 
-	/* Copy section for each CPU (we discard the original) */
-	size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
-	ptr = alloc_bootmem_pages(size * nr_possible_cpus);
+	ptr = boot_cpu_alloc(ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE));
+
+	if (!ptr)
+		printk("Cannot allocate per cpu areas\n");
 
 	for_each_possible_cpu(i) {
-		__per_cpu_offset[i] = ptr - __per_cpu_start;
-		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
-		ptr += size;
+		void *p = CPU_PTR(ptr, cpu);
+
+		__per_cpu_offset[cpu] = p - __per_cpu_start;
+
+		memcpy(p, __per_cpu_start,
+				__per_cpu_end - __per_cpu_start);
 	}
 }
 #endif /* !__GENERIC_PER_CPU */
Index: linux-2.6/arch/x86/kernel/setup64.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/setup64.c	2007-11-14 12:00:29.986843710 -0800
+++ linux-2.6/arch/x86/kernel/setup64.c	2007-11-15 21:36:58.727534438 -0800
@@ -80,42 +81,35 @@ static int __init nonx32_setup(char *str
 __setup("noexec32=", nonx32_setup);
 
 /*
- * Great future plan:
- * Declare PDA itself and support (irqstack,tss,pgd) as per cpu data.
- * Always point %gs to its beginning
+ * Per cpu areas are placed directly after the pda. The
+ * gs segment register can be used to access pda data as well
+ * as per cpu data and cpu_alloc data.
  */
 void __init setup_per_cpu_areas(void)
 { 
 	int i;
-	unsigned long size;
+	char *base;
 
 #ifdef CONFIG_HOTPLUG_CPU
 	prefill_possible_map();
 #endif
 
 	/* Copy section for each CPU (we discard the original) */
-	size = PERCPU_ENOUGH_ROOM;
+	base = boot_cpu_alloc(PERCPU_ENOUGH_ROOM);
+	if (!base)
+		panic("Cannot allocate cpu data\n");
 
-	printk(KERN_INFO "PERCPU: Allocating %lu bytes of per cpu data\n", size);
+	printk(KERN_INFO "PERCPU: Allocating %lu bytes of per cpu data\n",
+					PERCPU_ENOUGH_ROOM);
 	for_each_cpu_mask (i, cpu_possible_map) {
-		char *ptr;
+		cpu_pda(i)->data_offset = CPU_PTR(base, i) - __per_cpu_start;
 
-		if (!NODE_DATA(cpu_to_node(i))) {
-			printk("cpu with no node %d, num_online_nodes %d\n",
-			       i, num_online_nodes());
-			ptr = alloc_bootmem_pages(size);
-		} else { 
-			ptr = alloc_bootmem_pages_node(NODE_DATA(cpu_to_node(i)), size);
-		}
-		if (!ptr)
-			panic("Cannot allocate cpu data for CPU %d\n", i);
-		cpu_pda(i)->data_offset = ptr - __per_cpu_start;
-		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
+		memcpy(CPU_PTR(base, i), __per_cpu_start, __per_cpu_end - __per_cpu_start);
 	}
-} 
+}
 
 void pda_init(int cpu)
-{ 
+{
 	struct x8664_pda *pda = cpu_pda(cpu);
 
 	/* Setup up data that may be needed in __get_free_pages early */