s390: don't trace preemption in percpu macros

Since commit a21ee6055c30 ("lockdep: Change hardirq{s_enabled,_context}
to per-cpu variables") the lockdep code itself uses percpu variables. This
leads to recursions because the percpu macros are calling preempt_enable()
which might call trace_preempt_on().

Signed-off-by: Sven Schnelle <[e-mail]>
Reviewed-by: Vasily Gorbik <[e-mail]>
Signed-off-by: Vasily Gorbik <[e-mail]>

arch/s390/include/asm/percpu.h

···
 	typedef typeof(pcp) pcp_op_T__;					\
 	pcp_op_T__ old__, new__, prev__;				\
 	pcp_op_T__ *ptr__;						\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));					\
 	prev__ = *ptr__;						\
 	do {								\
···
 		new__ = old__ op (val);					\
 		prev__ = cmpxchg(ptr__, old__, new__);			\
 	} while (prev__ != old__);					\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	new__;								\
 })
 
···
 	typedef typeof(pcp) pcp_op_T__; 				\
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp)); 				\
 	if (__builtin_constant_p(val__) &&				\
 	    ((szcast)val__ > -129) && ((szcast)val__ < 128)) {		\
···
 			: [val__] "d" (val__)				\
 			: "cc");					\
 	}								\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 }
 
 #define this_cpu_add_4(pcp, val) arch_this_cpu_add(pcp, val, "laa", "asi", int)
···
 	typedef typeof(pcp) pcp_op_T__; 				\
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));	 				\
 	asm volatile(							\
 		op "    %[old__],%[val__],%[ptr__]\n"			\
 		: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__)		\
 		: [val__] "d" (val__)					\
 		: "cc");						\
-	preempt_enable();						\
+	preempt_enable_notrace();						\
 	old__ + val__;							\
 })
 
···
 	typedef typeof(pcp) pcp_op_T__; 				\
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));	 				\
 	asm volatile(							\
 		op "    %[old__],%[val__],%[ptr__]\n"			\
 		: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__)		\
 		: [val__] "d" (val__)					\
 		: "cc");						\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 }
 
 #define this_cpu_and_4(pcp, val)	arch_this_cpu_to_op(pcp, val, "lan")
···
 	typedef typeof(pcp) pcp_op_T__;					\
 	pcp_op_T__ ret__;						\
 	pcp_op_T__ *ptr__;						\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));					\
 	ret__ = cmpxchg(ptr__, oval, nval);				\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	ret__;								\
 })
 
···
 ({									\
 	typeof(pcp) *ptr__;						\
 	typeof(pcp) ret__;						\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));					\
 	ret__ = xchg(ptr__, nval);					\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	ret__;								\
 })
 
···
 	typeof(pcp1) *p1__;						\
 	typeof(pcp2) *p2__;						\
 	int ret__;							\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	p1__ = raw_cpu_ptr(&(pcp1));					\
 	p2__ = raw_cpu_ptr(&(pcp2));					\
 	ret__ = __cmpxchg_double(p1__, p2__, o1__, o2__, n1__, n2__);	\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	ret__;								\
 })