percpu: Omit segment prefix in the UP case for cmpxchg_double

Omit the segment prefix in the UP case. GS is not used then
and we will generate segfaults if cmpxchg16b is used otherwise.

Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/x86/include/asm/percpu.h

@@ -45,7 +45,7 @@
 #include <linux/stringify.h>
 
 #ifdef CONFIG_SMP
-#define __percpu_arg(x)		"%%"__stringify(__percpu_seg)":%P" #x
+#define __percpu_prefix		"%%"__stringify(__percpu_seg)":"
 #define __my_cpu_offset		percpu_read(this_cpu_off)
 
 /*
@@ -62,9 +62,11 @@
 	(typeof(*(ptr)) __kernel __force *)tcp_ptr__;	\
 })
 #else
-#define __percpu_arg(x)		"%P" #x
+#define __percpu_prefix		""
 #endif
 
+#define __percpu_arg(x)		__percpu_prefix "%P" #x
+
 /*
  * Initialized pointers to per-cpu variables needed for the boot
  * processor need to use these macros to get the proper address
@@ -516,11 +518,11 @@ do {									\
 	typeof(o2) __n2 = n2;						\
 	typeof(o2) __dummy;						\
 	alternative_io("call this_cpu_cmpxchg16b_emu\n\t" P6_NOP4,	\
-		       "cmpxchg16b %%gs:(%%rsi)\n\tsetz %0\n\t",	\
+		       "cmpxchg16b " __percpu_prefix "(%%rsi)\n\tsetz %0\n\t",	\
 		       X86_FEATURE_CX16,				\
 		       ASM_OUTPUT2("=a"(__ret), "=d"(__dummy)),		\
 		       "S" (&pcp1), "b"(__n1), "c"(__n2),		\
-		       "a"(__o1), "d"(__o2));				\
+		       "a"(__o1), "d"(__o2) : "memory");		\
 	__ret;								\
 })
 

arch/x86/lib/cmpxchg16b_emu.S

@@ -10,6 +10,12 @@
 #include <asm/frame.h>
 #include <asm/dwarf2.h>
 
+#ifdef CONFIG_SMP
+#define SEG_PREFIX %gs:
+#else
+#define SEG_PREFIX
+#endif
+
 .text
 
 /*
@@ -37,13 +43,13 @@ this_cpu_cmpxchg16b_emu:
 	pushf
 	cli
 
-	cmpq %gs:(%rsi), %rax
+	cmpq SEG_PREFIX(%rsi), %rax
 	jne not_same
-	cmpq %gs:8(%rsi), %rdx
+	cmpq SEG_PREFIX 8(%rsi), %rdx
 	jne not_same
 
-	movq %rbx, %gs:(%rsi)
-	movq %rcx, %gs:8(%rsi)
+	movq %rbx, SEG_PREFIX(%rsi)
+	movq %rcx, SEG_PREFIX 8(%rsi)
 
 	popf
 	mov $1, %al