static_call/x86: Add __static_call_return0()

Provide a stub function that return 0 and wire up the static call site
patching to replace the CALL with a single 5 byte instruction that
clears %RAX, the return value register.

The function can be cast to any function pointer type that has a
single %RAX return (including pointers). Also provide a version that
returns an int for convenience. We are clearing the entire %RAX register
in any case, whether the return value is 32 or 64 bits, since %RAX is
always a scratch register anyway.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20210118141223.123667-2-frederic@kernel.org

arch/x86/kernel/static_call.c

@@ -11,14 +11,26 @@ enum insn_type {
 	RET = 3,  /* tramp / site cond-tail-call */
 };
 
+/*
+ * data16 data16 xorq %rax, %rax - a single 5 byte instruction that clears %rax
+ * The REX.W cancels the effect of any data16.
+ */
+static const u8 xor5rax[] = { 0x66, 0x66, 0x48, 0x31, 0xc0 };
+
 static void __ref __static_call_transform(void *insn, enum insn_type type, void *func)
 {
+	const void *emulate = NULL;
 	int size = CALL_INSN_SIZE;
 	const void *code;
 
 	switch (type) {
 	case CALL:
 		code = text_gen_insn(CALL_INSN_OPCODE, insn, func);
+		if (func == &__static_call_return0) {
+			emulate = code;
+			code = &xor5rax;
+		}
+
 		break;
 
 	case NOP:
@@ -41,7 +53,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, void
 	if (unlikely(system_state == SYSTEM_BOOTING))
 		return text_poke_early(insn, code, size);
 
-	text_poke_bp(insn, code, size, NULL);
+	text_poke_bp(insn, code, size, emulate);
 }
 
 static void __static_call_validate(void *insn, bool tail)
@@ -54,7 +66,8 @@ static void __static_call_validate(void *insn, bool tail)
 			return;
 	} else {
 		if (opcode == CALL_INSN_OPCODE ||
-		    !memcmp(insn, ideal_nops[NOP_ATOMIC5], 5))
+		    !memcmp(insn, ideal_nops[NOP_ATOMIC5], 5) ||
+		    !memcmp(insn, xor5rax, 5))
 			return;
 	}
 

include/linux/static_call.h

@@ -142,6 +142,8 @@ extern void __static_call_update(struct static_call_key *key, void *tramp, void
 extern int static_call_mod_init(struct module *mod);
 extern int static_call_text_reserved(void *start, void *end);
 
+extern long __static_call_return0(void);
+
 #define DEFINE_STATIC_CALL(name, _func)					\
 	DECLARE_STATIC_CALL(name, _func);				\
 	struct static_call_key STATIC_CALL_KEY(name) = {		\
@@ -206,6 +208,11 @@ static inline int static_call_text_reserved(void *start, void *end)
 	return 0;
 }
 
+static inline long __static_call_return0(void)
+{
+	return 0;
+}
+
 #define EXPORT_STATIC_CALL(name)					\
 	EXPORT_SYMBOL(STATIC_CALL_KEY(name));				\
 	EXPORT_SYMBOL(STATIC_CALL_TRAMP(name))
@@ -222,6 +229,11 @@ struct static_call_key {
 	void *func;
 };
 
+static inline long __static_call_return0(void)
+{
+	return 0;
+}
+
 #define DEFINE_STATIC_CALL(name, _func)					\
 	DECLARE_STATIC_CALL(name, _func);				\
 	struct static_call_key STATIC_CALL_KEY(name) = {		\

kernel/static_call.c

@@ -438,6 +438,11 @@ int __init static_call_init(void)
 }
 early_initcall(static_call_init);
 
+long __static_call_return0(void)
+{
+	return 0;
+}
+
 #ifdef CONFIG_STATIC_CALL_SELFTEST
 
 static int func_a(int x)