[PATCH 4/4] s390/percpu: Implement this_cpu_try_cmpxchg()

[Heiko Carstens]

Provide an s390 specific implementation of this_cpu_try_cmpxchg() for
the four and eight byte cases, if the compiler supports flag output
operands.

This variant uses the condition code set by cs/csg, which avoids a
compare instruction required by the generic variant and generates
slightly better code.

Signed-off-by: Heiko Carstens <hca@xxxxxxxxxxxxx>
---
 arch/s390/include/asm/percpu.h | 39 ++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h
index 7d87e0a262c3..7b7a8cb51daa 100644
--- a/arch/s390/include/asm/percpu.h
+++ b/arch/s390/include/asm/percpu.h
@@ -5,6 +5,7 @@
 #include <linux/preempt.h>
 #include <asm/cmpxchg.h>
 #include <asm/march.h>
+#include <asm/asm.h>
 
 /*
  * s390 uses its own implementation for per cpu data, the offset of
@@ -404,6 +405,44 @@ do {									\
 	old__;								\
 })
 
+#ifdef __HAVE_ASM_FLAG_OUTPUTS__
+
+#define arch_this_cpu_try_cmpxchg(pcp, ovalp, nval, op)			\
+({									\
+	typedef typeof(pcp) pcp_op_T__;					\
+	typeof(ovalp) ovalp__ = (ovalp);				\
+	pcp_op_T__ old__ = *ovalp__;					\
+	pcp_op_T__ new__ = (nval);					\
+	union register_pair rp__;					\
+	pcp_op_T__ *ptr__;						\
+	int cc__;							\
+									\
+	ptr__ = PERCPU_PTR(&(pcp));					\
+	asm_inline volatile(						\
+		__PCPU_BEGIN("%[lcreg]","%[lcoff]","%[ptr__]",		\
+			     "%[pair__]","%N[pair__]")			\
+		op "	%[old__],%[new__],0(%N[pair__])\n"		\
+		__PCPU_END("%[lcreg]")					\
+		: [old__] "+&d" (old__), [pair__] "=&a" (rp__.pair),	\
+		  "+m" (*ptr__), "=@cc" (cc__),				\
+		  "=m" (((struct lowcore *)0)->percpu_register)		\
+		: [new__] "d" (new__), [ptr__] "a" (ptr__),		\
+		  [lcreg] "i" (LC_PERCPU_REGISTER),			\
+		  [lcoff] "i" (LC_PERCPU_OFFSET),			\
+		  "m" (((struct lowcore *)0)->percpu_offset)		\
+		: "memory");						\
+	if (unlikely(cc__))						\
+		*ovalp__ = old__;					\
+	likely(cc__ == 0);						\
+})
+
+#define this_cpu_try_cmpxchg_4(pcp, ovalp, nval) arch_this_cpu_try_cmpxchg(pcp, ovalp, nval, "cs")
+#define this_cpu_try_cmpxchg_8(pcp, ovalp, nval) arch_this_cpu_try_cmpxchg(pcp, ovalp, nval, "csg")
+
+#define this_cpu_try_cmpxchg64(pcp, ovalp, nval) this_cpu_try_cmpxchg_8(pcp, ovalp, nval)
+
+#endif /* __HAVE_ASM_FLAG_OUTPUTS__ */
+
 #define arch_this_cpu_xchg_simple(pcp, nval)				\
 ({									\
 	typeof(pcp) *ptr__;						\
-- 
2.53.0