diff --git a/py/nlrx64.c b/py/nlrx64.c
index 6f006e755..6b7d0262f 100644
--- a/py/nlrx64.c
+++ b/py/nlrx64.c
@@ -35,8 +35,27 @@
 
 __attribute__((used)) unsigned int nlr_push_tail(nlr_buf_t *nlr);
 
+#if !MICROPY_NLR_OS_WINDOWS
+#if defined(__clang__) || (defined(__GNUC__) && __GNUC__ >= 8)
+#define USE_NAKED 1
+#else
+// On older gcc the equivalent here is to force omit-frame-pointer
+__attribute__((optimize("omit-frame-pointer")))
+#endif
+#endif
+
+#if !defined(USE_NAKED)
+#define USE_NAKED 0
+#endif
+
+#if USE_NAKED
+// nlr_push prelude should never push frame pointer register ebp onto the stack
+__attribute__((naked))
+#endif
 unsigned int nlr_push(nlr_buf_t *nlr) {
+    #if !USE_NAKED
     (void)nlr;
+    #endif
 
     #if MICROPY_NLR_OS_WINDOWS
 
@@ -58,9 +77,6 @@ unsigned int nlr_push(nlr_buf_t *nlr) {
     #else
 
     __asm volatile (
-        #if defined(__APPLE__) && defined(__MACH__)
-        "pop    %rbp                \n" // undo function's prelude
-        #endif
         "movq   (%rsp), %rax        \n" // load return %rip
         "movq   %rax, 16(%rdi)      \n" // store %rip into nlr_buf
         "movq   %rbp, 24(%rdi)      \n" // store %rbp into nlr_buf
@@ -79,7 +95,9 @@ unsigned int nlr_push(nlr_buf_t *nlr) {
 
     #endif
 
+    #if !USE_NAKED
     return 0; // needed to silence compiler warning
+    #endif
 }
 
 NORETURN void nlr_jump(void *val) {