[PATCH v3 46/59] x86/returnthunk: Allow different return thunks

[Peter Zijlstra]

From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>

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@xxxxxxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
 arch/x86/include/asm/nospec-branch.h |    6 ++++++
 arch/x86/kernel/alternative.c        |   19 ++++++++++++++-----
 arch/x86/kernel/ftrace.c             |    2 +-
 arch/x86/kernel/static_call.c        |    2 +-
 arch/x86/net/bpf_jit_comp.c          |    2 +-
 5 files changed, 23 insertions(+), 8 deletions(-)

--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -198,6 +198,12 @@ 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) \
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -509,6 +509,11 @@ void __init_or_module noinline apply_ret
 }
 
 #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.
  *
@@ -524,14 +529,18 @@ static int patch_return(void *addr, stru
 {
 	int i = 0;
 
-	if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
-		return -1;
-
-	bytes[i++] = RET_INSN_OPCODE;
+	if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) {
+		if (x86_return_thunk == __x86_return_thunk)
+			return -1;
+
+		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;
 }
 
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -359,7 +359,7 @@ create_trampoline(struct ftrace_ops *ops
 
 	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));
 
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -52,7 +52,7 @@ static void __ref __static_call_transfor
 
 	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;
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -430,7 +430,7 @@ static void emit_return(u8 **pprog, u8 *
 	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))