Convert arch_this_cpu_add_return() to make use of the new percpu code
section infrastructure.

With this the text size of the kernel image is reduced by ~4k
(defconfig). Also 66 generated preempt_schedule_notrace() function
calls within the kernel image (modules not counted) are removed.

Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/include/asm/percpu.h | 26 +++++++++++++++++++-------
 1 file changed, 19 insertions(+), 7 deletions(-)

diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h
index 3c5364475e3e..2479b4748510 100644
--- a/arch/s390/include/asm/percpu.h
+++ b/arch/s390/include/asm/percpu.h
@@ -177,17 +177,29 @@
 
 #define arch_this_cpu_add_return(pcp, val, op)				\
 ({									\
+	unsigned long lc_pcpr, lc_pcpo;					\
 	typedef typeof(pcp) pcp_op_T__; 				\
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
-	preempt_disable_notrace();					\
-	ptr__ = raw_cpu_ptr(&(pcp));	 				\
-	asm volatile(							\
-		op "    %[old__],%[val__],%[ptr__]"			\
-		: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__)		\
-		: [val__] "d" (val__)					\
+									\
+	lc_pcpr = offsetof(struct lowcore, percpu_register);		\
+	lc_pcpo = offsetof(struct lowcore, percpu_offset);		\
+	ptr__ = PERCPU_PTR(&(pcp));					\
+	asm_inline volatile(						\
+		MVIY_PERCPU("%[disppcpr]", "%[dispaltpcpr]", "%[ptr__]")\
+		AG_ALT("%[disppcpo]", "%[dispaltpcpo]", "%[ptr__]")	\
+		op "	%[old__],%[val__],0(%[ptr__])\n"		\
+		MVIY_ALT("%[disppcpr]", "%[dispaltpcpr]", "%%r0")	\
+		: [old__] "=&d" (old__),				\
+		  [ptr__] "+&a" (ptr__), "+m" (*ptr__),			\
+		  "=m" (((struct lowcore *)0)->percpu_register)		\
+		: [val__] "d" (val__),					\
+		  [disppcpr] "i" (lc_pcpr),				\
+		  [disppcpo] "i" (lc_pcpo),				\
+		  [dispaltpcpr] "i" (lc_pcpr + LOWCORE_ALT_ADDRESS),	\
+		  [dispaltpcpo] "i" (lc_pcpo + LOWCORE_ALT_ADDRESS),	\
+		  "m" (((struct lowcore *)0)->percpu_offset)		\
 		: "cc");						\
-	preempt_enable_notrace();						\
 	old__ + val__;							\
 })
 
-- 
2.51.0