[PATCH 10/12] s390/percpu: Use percpu code section for this_cpu_cmpxchg()

[Heiko Carstens]

Convert this_cpu_cmpxchg() to make use of percpu code section
functionality in order to get rid of preempt_disable() and
preempt_enable() calls.

Consider only four and eight byte usages, since there are no compare
and swap instructions for one and two bytes available. For one and
two bytes use the previous simple implementation.

Signed-off-by: Heiko Carstens <hca@xxxxxxxxxxxxx>
---
 arch/s390/include/asm/percpu.h | 32 +++++++++++++++++++++++++++-----
 1 file changed, 27 insertions(+), 5 deletions(-)

diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h
index 237bf8c80843..46368131b932 100644
--- a/arch/s390/include/asm/percpu.h
+++ b/arch/s390/include/asm/percpu.h
@@ -290,7 +290,7 @@ do {									\
 #define this_cpu_write_4(pcp, val) arch_this_cpu_write(pcp, val, "st")
 #define this_cpu_write_8(pcp, val) arch_this_cpu_write(pcp, val, "stg")
 
-#define arch_this_cpu_cmpxchg(pcp, oval, nval)				\
+#define arch_this_cpu_cmpxchg_simple(pcp, oval, nval)			\
 ({									\
 	typedef typeof(pcp) pcp_op_T__;					\
 	pcp_op_T__ ret__;						\
@@ -302,10 +302,32 @@ do {									\
 	ret__;								\
 })
 
-#define this_cpu_cmpxchg_1(pcp, oval, nval) arch_this_cpu_cmpxchg(pcp, oval, nval)
-#define this_cpu_cmpxchg_2(pcp, oval, nval) arch_this_cpu_cmpxchg(pcp, oval, nval)
-#define this_cpu_cmpxchg_4(pcp, oval, nval) arch_this_cpu_cmpxchg(pcp, oval, nval)
-#define this_cpu_cmpxchg_8(pcp, oval, nval) arch_this_cpu_cmpxchg(pcp, oval, nval)
+#define arch_this_cpu_cmpxchg(pcp, oval, nval, op)			\
+({									\
+	typedef typeof(pcp) pcp_op_T__;					\
+	pcp_op_T__ old__ = (oval), new__ = (nval);			\
+	pcp_op_T__ *ptr__;						\
+									\
+	ptr__ = PERCPU_PTR(&(pcp));					\
+	asm_inline volatile(						\
+		__PCPU_BEGIN("%[lcreg]","%[lcoff]","%[ptr__]")		\
+		op "	%[old__],%[new__],0(%[ptr__])\n"		\
+		__PCPU_END("%[lcreg]")					\
+		: [old__] "+&d" (old__),				\
+		  [ptr__] "+&a" (ptr__), "+m" (*ptr__),			\
+		  "=m" (((struct lowcore *)0)->percpu_register)		\
+		: [new__] "d" (new__),					\
+		  [lcreg] "i" (LC_PERCPU_REGISTER),			\
+		  [lcoff] "i" (LC_PERCPU_OFFSET),			\
+		  "m" (((struct lowcore *)0)->percpu_offset)		\
+		: "memory", "cc");					\
+	old__;								\
+})
+
+#define this_cpu_cmpxchg_1(pcp, oval, nval) arch_this_cpu_cmpxchg_simple(pcp, oval, nval)
+#define this_cpu_cmpxchg_2(pcp, oval, nval) arch_this_cpu_cmpxchg_simple(pcp, oval, nval)
+#define this_cpu_cmpxchg_4(pcp, oval, nval) arch_this_cpu_cmpxchg(pcp, oval, nval, "cs")
+#define this_cpu_cmpxchg_8(pcp, oval, nval) arch_this_cpu_cmpxchg(pcp, oval, nval, "csg")
 
 #define this_cpu_cmpxchg64(pcp, o, n)	this_cpu_cmpxchg_8(pcp, o, n)
 
-- 
2.53.0