diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 01727dbc294a..7fb336210e1b 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -12,11 +12,11 @@
  */
 
 #ifdef CONFIG_X86_32
-#define mb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "mfence", \
+#define mb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "mfence", \
 				      X86_FEATURE_XMM2) ::: "memory", "cc")
-#define rmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "lfence", \
+#define rmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "lfence", \
 				       X86_FEATURE_XMM2) ::: "memory", "cc")
-#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "sfence", \
+#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "sfence", \
 				       X86_FEATURE_XMM2) ::: "memory", "cc")
 #else
 #define mb() 	asm volatile("mfence":::"memory")
@@ -31,7 +31,11 @@
 #endif
 #define dma_wmb()	barrier()
 
-#define __smp_mb()	mb()
+#ifdef CONFIG_X86_32
+#define __smp_mb()	asm volatile("lock; addl $0,-4(%%esp)" ::: "memory", "cc")
+#else
+#define __smp_mb()	asm volatile("lock; addl $0,-4(%%rsp)" ::: "memory", "cc")
+#endif
 #define __smp_rmb()	dma_rmb()
 #define __smp_wmb()	barrier()
 #define __smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0)
diff --git a/tools/virtio/ringtest/main.h b/tools/virtio/ringtest/main.h
index 90b0133004e1..5706e075adf2 100644
--- a/tools/virtio/ringtest/main.h
+++ b/tools/virtio/ringtest/main.h
@@ -110,11 +110,15 @@ static inline void busy_wait(void)
 		barrier();
 } 
 
+#if defined(__x86_64__) || defined(__i386__)
+#define smp_mb()     asm volatile("lock; addl $0,-128(%%rsp)" ::: "memory", "cc")
+#else
 /*
  * Not using __ATOMIC_SEQ_CST since gcc docs say they are only synchronized
  * with other __ATOMIC_SEQ_CST calls.
  */
 #define smp_mb() __sync_synchronize()
+#endif
 
 /*
  * This abuses the atomic builtins for thread fences, and