diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 5240cde..b69e0b4 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -54,26 +54,22 @@
  * save some instructions and make the code more elegant. There really isn't
  * much between them in performance though, especially as locks are out of line.
  */
-#if (NR_CPUS < 256)
 static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock)
 {
-	register union {
-		struct __raw_tickets tickets;
-		unsigned short slock;
-	} inc = { .slock = 1 << TICKET_SHIFT };
+	register struct __raw_tickets inc = { .tail = 1 };
 
-	asm volatile (LOCK_PREFIX "xaddw %w0, %1\n"
-		      : "+Q" (inc), "+m" (lock->slock) : : "memory", "cc");
+	inc = xadd(&lock->tickets, inc);
 
 	for (;;) {
-		if (inc.tickets.head == inc.tickets.tail)
+		if (inc.head == inc.tail)
 			break;
 		cpu_relax();
-		inc.tickets.head = ACCESS_ONCE(lock->tickets.head);
+		inc.head = ACCESS_ONCE(lock->tickets.head);
 	}
 	barrier();		/* make sure nothing creeps before the lock is taken */
 }
 
+#if (NR_CPUS < 256)
 static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
 {
 	unsigned int tmp, new;
@@ -101,27 +97,6 @@
 		     : "memory", "cc");
 }
 #else
-static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock)
-{
-	unsigned inc = 1 << TICKET_SHIFT;
-	__ticket_t tmp;
-
-	asm volatile(LOCK_PREFIX "xaddl %0, %1\n\t"
-		     : "+r" (inc), "+m" (lock->slock)
-		     : : "memory", "cc");
-
-	tmp = inc;
-	inc >>= TICKET_SHIFT;
-
-	for (;;) {
-		if ((__ticket_t)inc == tmp)
-			break;
-		cpu_relax();
-		tmp = ACCESS_ONCE(lock->tickets.head);
-	}
-	barrier();		/* make sure nothing creeps before the lock is taken */
-}
-
 static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
 {
 	unsigned tmp;