diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 34734d730463..8450fe4a2753 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -31,18 +31,32 @@
 #define __percpu_prefix		"%%"__stringify(__percpu_seg)":"
 #define __my_cpu_offset		this_cpu_read(this_cpu_off)
 
-/*
- * Compared to the generic __my_cpu_offset version, the following
- * saves one instruction and avoids clobbering a temp register.
- */
-#define arch_raw_cpu_ptr(ptr)				\
-({							\
-	unsigned long tcp_ptr__;			\
-	asm ("add " __percpu_arg(1) ", %0"		\
-	     : "=r" (tcp_ptr__)				\
-	     : "m" (this_cpu_off), "0" (ptr));		\
-	(typeof(*(ptr)) __kernel __force *)tcp_ptr__;	\
+#ifdef CONFIG_X86_64
+#define arch_raw_cpu_ptr(ptr)					\
+({								\
+	unsigned long tcp_ptr__;				\
+	asm (ALTERNATIVE("movq " __percpu_arg(1) ", %0",	\
+			 "rdgsbase %0",				\
+			 X86_FEATURE_FSGSBASE)			\
+	     : "=r" (tcp_ptr__)					\
+	     : "m" (this_cpu_off));				\
+								\
+	tcp_ptr__ += (unsigned long)(ptr);			\
+	(typeof(*(ptr)) __kernel __force *)tcp_ptr__;		\
 })
+#else /* CONFIG_X86_64 */
+#define arch_raw_cpu_ptr(ptr)					\
+({								\
+	unsigned long tcp_ptr__;				\
+	asm ("movl " __percpu_arg(1) ", %0"			\
+	     : "=r" (tcp_ptr__)					\
+	     : "m" (this_cpu_off));				\
+								\
+	tcp_ptr__ += (unsigned long)(ptr);			\
+	(typeof(*(ptr)) __kernel __force *)tcp_ptr__;		\
+})
+#endif /* CONFIG_X86_64 */
+
 #else
 #define __percpu_prefix		""
 #endif