diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h
index 34323456939274d7709cfe13a01c69394d75a3dc..7efce22d635523795e289dd91985a89a739c690c 100644
--- a/arch/x86/include/asm/static_call.h
+++ b/arch/x86/include/asm/static_call.h
@@ -21,6 +21,16 @@
  * relative displacement across sections.
  */
 
+/*
+ * The trampoline is 8 bytes and of the general form:
+ *
+ *   jmp.d32 \func
+ *   ud1 %esp, %ecx
+ *
+ * That trailing #UD provides both a speculation stop and serves as a unique
+ * 3 byte signature identifying static call trampolines. Also see tramp_ud[]
+ * and __static_call_fixup().
+ */
 #define __ARCH_DEFINE_STATIC_CALL_TRAMP(name, insns)			\
 	asm(".pushsection .static_call.text, \"ax\"		\n"	\
 	    ".align 4						\n"	\
@@ -34,8 +44,13 @@
 #define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func)			\
 	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, ".byte 0xe9; .long " #func " - (. + 4)")
 
+#ifdef CONFIG_RETPOLINE
+#define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)			\
+	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, "jmp __x86_return_thunk")
+#else
 #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)			\
 	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; int3; nop; nop; nop")
+#endif
 
 
 #define ARCH_ADD_TRAMP_KEY(name)					\
@@ -44,4 +59,6 @@
 	    ".long " STATIC_CALL_KEY_STR(name) " - .		\n"	\
 	    ".popsection					\n")
 
+extern bool __static_call_fixup(void *tramp, u8 op, void *dest);
+
 #endif /* _ASM_STATIC_CALL_H */
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 75caf244e88b33c18cb5b16ecda28586e09930cb..1ba8f4006a507e4b6331a1bab37c2878a46574d2 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -643,18 +643,22 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end)
 	s32 *s;
 
 	for (s = start; s < end; s++) {
-		void *addr = (void *)s + *s;
+		void *dest = NULL, *addr = (void *)s + *s;
 		struct insn insn;
 		int len, ret;
 		u8 bytes[16];
-		u8 op1;
+		u8 op;
 
 		ret = insn_decode_kernel(&insn, addr);
 		if (WARN_ON_ONCE(ret < 0))
 			continue;
 
-		op1 = insn.opcode.bytes[0];
-		if (WARN_ON_ONCE(op1 != JMP32_INSN_OPCODE))
+		op = insn.opcode.bytes[0];
+		if (op == JMP32_INSN_OPCODE)
+			dest = addr + insn.length + insn.immediate.value;
+
+		if (__static_call_fixup(addr, op, dest) ||
+		    WARN_ON_ONCE(dest != &__x86_return_thunk))
 			continue;
 
 		DPRINTK("return thunk at: %pS (%px) len: %d to: %pS",
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index ae9b858c996a0be1bf1c8525b1ca6cc63c2dd1d9..8d7b1da5d82f680d1a51b5957e702741ba855bb5 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -17,6 +17,13 @@ enum insn_type {
  */
 static const u8 xor5rax[] = { 0x66, 0x66, 0x48, 0x31, 0xc0 };
 
+/*
+ * ud1 %esp, %ecx - a 3 byte #UD that is unique to trampolines, chosen such
+ * that there is no false-positive trampoline identification while also being a
+ * speculation stop.
+ */
+static const u8 tramp_ud[] = { 0x0f, 0xb9, 0xcc };
+
 static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc };
 
 static void __ref __static_call_transform(void *insn, enum insn_type type, void *func)
@@ -44,7 +51,10 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, void
 		break;
 
 	case RET:
-		code = &retinsn;
+		if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+			code = text_gen_insn(JMP32_INSN_OPCODE, insn, &__x86_return_thunk);
+		else
+			code = &retinsn;
 		break;
 	}
 
@@ -110,3 +120,29 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
 	mutex_unlock(&text_mutex);
 }
 EXPORT_SYMBOL_GPL(arch_static_call_transform);
+
+#ifdef CONFIG_RETPOLINE
+/*
+ * This is called by apply_returns() to fix up static call trampolines,
+ * specifically ARCH_DEFINE_STATIC_CALL_NULL_TRAMP which is recorded as
+ * having a return trampoline.
+ *
+ * The problem is that static_call() is available before determining
+ * X86_FEATURE_RETHUNK and, by implication, running alternatives.
+ *
+ * This means that __static_call_transform() above can have overwritten the
+ * return trampoline and we now need to fix things up to be consistent.
+ */
+bool __static_call_fixup(void *tramp, u8 op, void *dest)
+{
+	if (memcmp(tramp+5, tramp_ud, 3)) {
+		/* Not a trampoline site, not our problem. */
+		return false;
+	}
+
+	if (op == RET_INSN_OPCODE || dest == &__x86_return_thunk)
+		__static_call_transform(tramp, RET, NULL);
+
+	return true;
+}
+#endif