diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c
index b07ba2a..9304c45 100644
--- a/drivers/oprofile/buffer_sync.c
+++ b/drivers/oprofile/buffer_sync.c
@@ -491,7 +491,7 @@
  */
 void sync_buffer(int cpu)
 {
-	struct oprofile_cpu_buffer * cpu_buf = &cpu_buffer[cpu];
+	struct oprofile_cpu_buffer *cpu_buf = &per_cpu(cpu_buffer, cpu);
 	struct mm_struct *mm = NULL;
 	struct task_struct * new;
 	unsigned long cookie = 0;
diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c
index c93d3d2..efcbf4b 100644
--- a/drivers/oprofile/cpu_buffer.c
+++ b/drivers/oprofile/cpu_buffer.c
@@ -27,7 +27,7 @@
 #include "buffer_sync.h"
 #include "oprof.h"
 
-struct oprofile_cpu_buffer cpu_buffer[NR_CPUS] __cacheline_aligned;
+DEFINE_PER_CPU_SHARED_ALIGNED(struct oprofile_cpu_buffer, cpu_buffer);
 
 static void wq_sync_buffer(struct work_struct *work);
 
@@ -39,7 +39,7 @@
 	int i;
  
 	for_each_online_cpu(i)
-		vfree(cpu_buffer[i].buffer);
+		vfree(per_cpu(cpu_buffer, i).buffer);
 }
 
 int alloc_cpu_buffers(void)
@@ -49,7 +49,7 @@
 	unsigned long buffer_size = fs_cpu_buffer_size;
  
 	for_each_online_cpu(i) {
-		struct oprofile_cpu_buffer * b = &cpu_buffer[i];
+		struct oprofile_cpu_buffer *b = &per_cpu(cpu_buffer, i);
  
 		b->buffer = vmalloc_node(sizeof(struct op_sample) * buffer_size,
 			cpu_to_node(i));
@@ -83,7 +83,7 @@
 	work_enabled = 1;
 
 	for_each_online_cpu(i) {
-		struct oprofile_cpu_buffer * b = &cpu_buffer[i];
+		struct oprofile_cpu_buffer *b = &per_cpu(cpu_buffer, i);
 
 		/*
 		 * Spread the work by 1 jiffy per cpu so they dont all
@@ -100,7 +100,7 @@
 	work_enabled = 0;
 
 	for_each_online_cpu(i) {
-		struct oprofile_cpu_buffer * b = &cpu_buffer[i];
+		struct oprofile_cpu_buffer *b = &per_cpu(cpu_buffer, i);
 
 		cancel_delayed_work(&b->work);
 	}
@@ -227,7 +227,7 @@
 void oprofile_add_ext_sample(unsigned long pc, struct pt_regs * const regs,
 				unsigned long event, int is_kernel)
 {
-	struct oprofile_cpu_buffer * cpu_buf = &cpu_buffer[smp_processor_id()];
+	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);
 
 	if (!backtrace_depth) {
 		log_sample(cpu_buf, pc, is_kernel, event);
@@ -254,13 +254,13 @@
 
 void oprofile_add_pc(unsigned long pc, int is_kernel, unsigned long event)
 {
-	struct oprofile_cpu_buffer * cpu_buf = &cpu_buffer[smp_processor_id()];
+	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);
 	log_sample(cpu_buf, pc, is_kernel, event);
 }
 
 void oprofile_add_trace(unsigned long pc)
 {
-	struct oprofile_cpu_buffer * cpu_buf = &cpu_buffer[smp_processor_id()];
+	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);
 
 	if (!cpu_buf->tracing)
 		return;
diff --git a/drivers/oprofile/cpu_buffer.h b/drivers/oprofile/cpu_buffer.h
index c66c025..1358817 100644
--- a/drivers/oprofile/cpu_buffer.h
+++ b/drivers/oprofile/cpu_buffer.h
@@ -14,6 +14,7 @@
 #include <linux/spinlock.h>
 #include <linux/workqueue.h>
 #include <linux/cache.h>
+#include <linux/sched.h>
  
 struct task_struct;
  
@@ -47,7 +48,7 @@
 	struct delayed_work work;
 } ____cacheline_aligned;
 
-extern struct oprofile_cpu_buffer cpu_buffer[];
+DECLARE_PER_CPU(struct oprofile_cpu_buffer, cpu_buffer);
 
 void cpu_buffer_reset(struct oprofile_cpu_buffer * cpu_buf);
 
diff --git a/drivers/oprofile/oprofile_stats.c b/drivers/oprofile/oprofile_stats.c
index d1f6d77..f99b28e 100644
--- a/drivers/oprofile/oprofile_stats.c
+++ b/drivers/oprofile/oprofile_stats.c
@@ -23,7 +23,7 @@
 	int i;
  
 	for_each_possible_cpu(i) {
-		cpu_buf = &cpu_buffer[i]; 
+		cpu_buf = &per_cpu(cpu_buffer, i);
 		cpu_buf->sample_received = 0;
 		cpu_buf->sample_lost_overflow = 0;
 		cpu_buf->backtrace_aborted = 0;
@@ -49,7 +49,7 @@
 		return;
 
 	for_each_possible_cpu(i) {
-		cpu_buf = &cpu_buffer[i]; 
+		cpu_buf = &per_cpu(cpu_buffer, i);
 		snprintf(buf, 10, "cpu%d", i);
 		cpudir = oprofilefs_mkdir(sb, dir, buf);