static_call: Properly initialise DEFINE_STATIC_CALL_RET0()

When a static call is updated with __static_call_return0() as target,
arch_static_call_transform() set it to use an optimised set of
instructions which are meant to lay in the same cacheline.

But when initialising a static call with DEFINE_STATIC_CALL_RET0(),
we get a branch to the real __static_call_return0() function instead
of getting the optimised setup:

	c00d8120 <__SCT__perf_snapshot_branch_stack>:
	c00d8120:	4b ff ff f4 	b       c00d8114 <__static_call_return0>
	c00d8124:	3d 80 c0 0e 	lis     r12,-16370
	c00d8128:	81 8c 81 3c 	lwz     r12,-32452(r12)
	c00d812c:	7d 89 03 a6 	mtctr   r12
	c00d8130:	4e 80 04 20 	bctr
	c00d8134:	38 60 00 00 	li      r3,0
	c00d8138:	4e 80 00 20 	blr
	c00d813c:	00 00 00 00 	.long 0x0

Add ARCH_DEFINE_STATIC_CALL_RET0_TRAMP() defined by each architecture
to setup the optimised configuration, and rework
DEFINE_STATIC_CALL_RET0() to call it:

	c00d8120 <__SCT__perf_snapshot_branch_stack>:
	c00d8120:	48 00 00 14 	b       c00d8134 <__SCT__perf_snapshot_branch_stack+0x14>
	c00d8124:	3d 80 c0 0e 	lis     r12,-16370
	c00d8128:	81 8c 81 3c 	lwz     r12,-32452(r12)
	c00d812c:	7d 89 03 a6 	mtctr   r12
	c00d8130:	4e 80 04 20 	bctr
	c00d8134:	38 60 00 00 	li      r3,0
	c00d8138:	4e 80 00 20 	blr
	c00d813c:	00 00 00 00 	.long 0x0

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lore.kernel.org/r/1e0a61a88f52a460f62a58ffc2a5f847d1f7d9d8.1647253456.git.christophe.leroy@csgroup.eu

Author: chleroy

arch/powerpc/include/asm/static_call.h

@@ -24,5 +24,6 @@
 
 #define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func)	__PPC_SCT(name, "b " #func)
 #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)	__PPC_SCT(name, "blr")
+#define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name)	__PPC_SCT(name, "b .+20")
 
 #endif /* _ASM_POWERPC_STATIC_CALL_H */

arch/x86/include/asm/static_call.h

@@ -38,6 +38,8 @@
 #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)			\
 	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; int3; nop; nop; nop")
 
+#define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name)			\
+	ARCH_DEFINE_STATIC_CALL_TRAMP(name, __static_call_return0)
 
 #define ARCH_ADD_TRAMP_KEY(name)					\
 	asm(".pushsection .static_call_tramp_key, \"a\"		\n"	\

include/linux/static_call.h

@@ -196,6 +196,14 @@ extern long __static_call_return0(void);
 	};								\
 	ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)
 
+#define DEFINE_STATIC_CALL_RET0(name, _func)				\
+	DECLARE_STATIC_CALL(name, _func);				\
+	struct static_call_key STATIC_CALL_KEY(name) = {		\
+		.func = __static_call_return0,				\
+		.type = 1,						\
+	};								\
+	ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name)
+
 #define static_call_cond(name)	(void)__static_call(name)
 
 #define EXPORT_STATIC_CALL(name)					\
@@ -231,6 +239,12 @@ static inline int static_call_init(void) { return 0; }
 	};								\
 	ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)
 
+#define DEFINE_STATIC_CALL_RET0(name, _func)				\
+	DECLARE_STATIC_CALL(name, _func);				\
+	struct static_call_key STATIC_CALL_KEY(name) = {		\
+		.func = __static_call_return0,				\
+	};								\
+	ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name)
 
 #define static_call_cond(name)	(void)__static_call(name)
 
@@ -284,6 +298,9 @@ static inline long __static_call_return0(void)
 		.func = NULL,						\
 	}
 
+#define DEFINE_STATIC_CALL_RET0(name, _func)				\
+	__DEFINE_STATIC_CALL(name, _func, __static_call_return0)
+
 static inline void __static_call_nop(void) { }
 
 /*
@@ -327,7 +344,4 @@ static inline int static_call_text_reserved(void *start, void *end)
 #define DEFINE_STATIC_CALL(name, _func)					\
 	__DEFINE_STATIC_CALL(name, _func, _func)
 
-#define DEFINE_STATIC_CALL_RET0(name, _func)				\
-	__DEFINE_STATIC_CALL(name, _func, __static_call_return0)
-
 #endif /* _LINUX_STATIC_CALL_H */