diff --git a/arch/i386/atomic.h b/arch/i386/atomic.h
index 95fecbdc..25441df2 100644
--- a/arch/i386/atomic.h
+++ b/arch/i386/atomic.h
@@ -88,7 +88,7 @@ static inline void a_dec(volatile int *x)
 
 static inline void a_store(volatile int *p, int x)
 {
-	__asm__( "movl %1, %0" : "=m"(*p) : "r"(x) : "memory" );
+	__asm__( "movl %1, %0 ; lock ; orl $0,(%%esp)" : "=m"(*p) : "r"(x) : "memory" );
 }
 
 static inline void a_spin()
diff --git a/arch/x32/atomic.h b/arch/x32/atomic.h
index b2014cc0..2ab1f7a2 100644
--- a/arch/x32/atomic.h
+++ b/arch/x32/atomic.h
@@ -83,7 +83,7 @@ static inline void a_dec(volatile int *x)
 
 static inline void a_store(volatile int *p, int x)
 {
-	__asm__( "mov %1, %0" : "=m"(*p) : "r"(x) : "memory" );
+	__asm__( "mov %1, %0 ; mfence" : "=m"(*p) : "r"(x) : "memory" );
 }
 
 static inline void a_spin()
diff --git a/arch/x86_64/atomic.h b/arch/x86_64/atomic.h
index b2014cc0..2ab1f7a2 100644
--- a/arch/x86_64/atomic.h
+++ b/arch/x86_64/atomic.h
@@ -83,7 +83,7 @@ static inline void a_dec(volatile int *x)
 
 static inline void a_store(volatile int *p, int x)
 {
-	__asm__( "mov %1, %0" : "=m"(*p) : "r"(x) : "memory" );
+	__asm__( "mov %1, %0 ; mfence" : "=m"(*p) : "r"(x) : "memory" );
 }
 
 static inline void a_spin()