x86/returnthunk: Allow different return thunks

In preparation for call depth tracking on Intel SKL CPUs, make it possible
to patch in a SKL specific return thunk.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220915111147.680469665@infradead.org

arch/x86/include/asm/nospec-branch.h

@@ -208,6 +208,12 @@ extern void __x86_return_thunk(void);
 extern void zen_untrain_ret(void);
 extern void entry_ibpb(void);
 
+#ifdef CONFIG_CALL_THUNKS
+extern void (*x86_return_thunk)(void);
+#else
+#define x86_return_thunk	(&__x86_return_thunk)
+#endif
+
 #ifdef CONFIG_RETPOLINE
 
 #define GEN(reg) \

arch/x86/kernel/alternative.c

@@ -518,6 +518,11 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
 }
 
 #ifdef CONFIG_RETHUNK
+
+#ifdef CONFIG_CALL_THUNKS
+void (*x86_return_thunk)(void) __ro_after_init = &__x86_return_thunk;
+#endif
+
 /*
  * Rewrite the compiler generated return thunk tail-calls.
  *
@@ -533,14 +538,18 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes)
 {
 	int i = 0;
 
-	if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
-		return -1;
+	if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) {
+		if (x86_return_thunk == __x86_return_thunk)
+			return -1;
 
-	bytes[i++] = RET_INSN_OPCODE;
+		i = JMP32_INSN_SIZE;
+		__text_gen_insn(bytes, JMP32_INSN_OPCODE, addr, x86_return_thunk, i);
+	} else {
+		bytes[i++] = RET_INSN_OPCODE;
+	}
 
 	for (; i < insn->length;)
 		bytes[i++] = INT3_INSN_OPCODE;
-
 	return i;
 }
 

arch/x86/kernel/ftrace.c

@@ -359,7 +359,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 
 	ip = trampoline + size;
 	if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
-		__text_gen_insn(ip, JMP32_INSN_OPCODE, ip, &__x86_return_thunk, JMP32_INSN_SIZE);
+		__text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE);
 	else
 		memcpy(ip, retq, sizeof(retq));
 

arch/x86/kernel/static_call.c

@@ -52,7 +52,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type,
 
 	case RET:
 		if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
-			code = text_gen_insn(JMP32_INSN_OPCODE, insn, &__x86_return_thunk);
+			code = text_gen_insn(JMP32_INSN_OPCODE, insn, x86_return_thunk);
 		else
 			code = &retinsn;
 		break;

arch/x86/net/bpf_jit_comp.c

@@ -432,7 +432,7 @@ static void emit_return(u8 **pprog, u8 *ip)
 	u8 *prog = *pprog;
 
 	if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) {
-		emit_jump(&prog, &__x86_return_thunk, ip);
+		emit_jump(&prog, x86_return_thunk, ip);
 	} else {
 		EMIT1(0xC3);		/* ret */
 		if (IS_ENABLED(CONFIG_SLS))