diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 54c7f46c453f..e1b0c5ed0b7c 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -2119,10 +2119,15 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
 		restore_regs(m, &prog, nr_args, regs_off);
 
-		/* call original function */
-		if (emit_call(&prog, orig_call, prog)) {
-			ret = -EINVAL;
-			goto cleanup;
+		if (flags & BPF_TRAMP_F_ORIG_STACK) {
+			emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, 8);
+			EMIT2(0xff, 0xd0); /* call *rax */
+		} else {
+			/* call original function */
+			if (emit_call(&prog, orig_call, prog)) {
+				ret = -EINVAL;
+				goto cleanup;
+			}
 		}
 		/* remember return value in a stack for bpf prog to access */
 		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a97751d845c9..1d22df8bf306 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -751,6 +751,11 @@ struct btf_func_model {
 /* Return the return value of fentry prog. Only used by bpf_struct_ops. */
 #define BPF_TRAMP_F_RET_FENTRY_RET	BIT(4)
 
+/* Get original function from stack instead of from provided direct address.
+ * Makes sense for trampolines with fexit or fmod_ret programs.
+ */
+#define BPF_TRAMP_F_ORIG_STACK		BIT(5)
+
 /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
  * bytes on x86.
  */