s390: fine-tune stack switch helper

The CALL_ON_STACK helper currently does not work with clang and for
calls without arguments. It does not initialize r2 although the constraint
is "+&d". Rework the CALL_FMT_x and the CALL_ON_STACK macros to work
with clang and produce optimal code in all cases.

Reported-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

arch/s390/include/asm/processor.h

@@ -261,12 +261,12 @@ static __no_kasan_or_inline unsigned short stap(void)
 	CALL_ARGS_4(arg1, arg2, arg3, arg4);				\
 	register unsigned long r4 asm("6") = (unsigned long)(arg5)
 
-#define CALL_FMT_0
-#define CALL_FMT_1 CALL_FMT_0, "0" (r2)
-#define CALL_FMT_2 CALL_FMT_1, "d" (r3)
-#define CALL_FMT_3 CALL_FMT_2, "d" (r4)
-#define CALL_FMT_4 CALL_FMT_3, "d" (r5)
-#define CALL_FMT_5 CALL_FMT_4, "d" (r6)
+#define CALL_FMT_0 "=&d" (r2) :
+#define CALL_FMT_1 "+&d" (r2) :
+#define CALL_FMT_2 CALL_FMT_1 "d" (r3),
+#define CALL_FMT_3 CALL_FMT_2 "d" (r4),
+#define CALL_FMT_4 CALL_FMT_3 "d" (r5),
+#define CALL_FMT_5 CALL_FMT_4 "d" (r6),
 
 #define CALL_CLOBBER_5 "0", "1", "14", "cc", "memory"
 #define CALL_CLOBBER_4 CALL_CLOBBER_5
@@ -286,10 +286,10 @@ static __no_kasan_or_inline unsigned short stap(void)
 		"	stg	%[_prev],%[_bc](15)\n"			\
 		"	brasl	14,%[_fn]\n"				\
 		"	la	15,0(%[_prev])\n"			\
-		: "+&d" (r2), [_prev] "=&a" (prev)			\
-		: [_stack] "a" (stack),					\
+		: [_prev] "=&a" (prev), CALL_FMT_##nr			\
+		  [_stack] "a" (stack),					\
 		  [_bc] "i" (offsetof(struct stack_frame, back_chain)),	\
-		  [_fn] "X" (fn) CALL_FMT_##nr : CALL_CLOBBER_##nr);	\
+		  [_fn] "X" (fn) : CALL_CLOBBER_##nr);			\
 	r2;								\
 })