Provide an s390 specific implementation of arch_this_cpu_read() instead
of the generic variant. The generic variant uses preempt_disable() /
preempt_enable() pair and READ_ONCE().

Get rid of the preempt_disable() / preempt_enable() pairs by providing an
own variant which makes use of the new percpu code section infrastructure.

With this the text size of the kernel image is reduced by ~1k
(defconfig). Also 87 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 | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h
index f26f03b0889c..35e48d193d99 100644
--- a/arch/s390/include/asm/percpu.h
+++ b/arch/s390/include/asm/percpu.h
@@ -240,6 +240,37 @@
 
 #endif /* MARCH_HAS_Z196_FEATURES */
 
+#define arch_this_cpu_read(pcp, op)					\
+({									\
+	unsigned long lc_pcpr, lc_pcpo;					\
+	typedef typeof(pcp) pcp_op_T__;					\
+	pcp_op_T__ val__, *ptr__;					\
+									\
+	lc_pcpr = offsetof(struct lowcore, percpu_register);		\
+	lc_pcpo = offsetof(struct lowcore, percpu_offset);		\
+	ptr__ = &(pcp);							\
+	asm_inline volatile(						\
+		MVIY_PERCPU("%[disppcpr]", "%[dispaltpcpr]", "%[ptr__]")\
+		AG_ALT("%[disppcpo]", "%[dispaltpcpo]", "%[ptr__]")	\
+		op "	%[val__],0(%[ptr__])\n"				\
+		MVIY_ALT("%[disppcpr]", "%[dispaltpcpr]", "%%r0")	\
+		: [val__] "=&d" (val__), [ptr__] "+&a" (ptr__),		\
+		  "=m" (((struct lowcore *)0)->percpu_register)		\
+		: [disppcpr] "i" (lc_pcpr),				\
+		  [disppcpo] "i" (lc_pcpo),				\
+		  [dispaltpcpr] "i" (lc_pcpr + LOWCORE_ALT_ADDRESS),	\
+		  [dispaltpcpo] "i" (lc_pcpo + LOWCORE_ALT_ADDRESS),	\
+		  "m" (*ptr__),						\
+		  "m" (((struct lowcore *)0)->percpu_offset)		\
+		: "cc");						\
+	val__;								\
+})
+
+#define this_cpu_read_1(pcp) arch_this_cpu_read(pcp, "ic")
+#define this_cpu_read_2(pcp) arch_this_cpu_read(pcp, "lh")
+#define this_cpu_read_4(pcp) arch_this_cpu_read(pcp, "l")
+#define this_cpu_read_8(pcp) arch_this_cpu_read(pcp, "lg")
+
 #define arch_this_cpu_cmpxchg(pcp, oval, nval)				\
 ({									\
 	typedef typeof(pcp) pcp_op_T__;					\
-- 
2.51.0