Collapse duplicated branch tails and use checked_sub in CALL_KW

youknowone · youknowone · commit 411257750270 · 2026-03-04T05:45:36.000+09:00
- Collapse conditional deopt + unconditional vectorcall pattern in
  CallBuiltinClass, CallNonPyGeneral, CallKwNonPy
- Use checked_sub for nargs_usize - kw_count in execute_call_kw_vectorcall
  to prevent silent underflow in release builds
diff --git a/crates/vm/src/frame.rs b/crates/vm/src/frame.rs
@@ -4117,10 +4117,9 @@ impl ExecutingFrame<'_> {
                 let nargs: u32 = arg.into();
                 let callable = self.nth_value(nargs + 1);
                 let callable_tag = callable as *const PyObject as u32;
-                if cached_tag == callable_tag && callable.downcast_ref::<PyType>().is_some() {
-                    return self.execute_call_vectorcall(nargs, vm);
+                if !(cached_tag == callable_tag && callable.downcast_ref::<PyType>().is_some()) {
+                    self.deoptimize_call();
                 }
-                self.deoptimize_call();
                 self.execute_call_vectorcall(nargs, vm)
             }
             Instruction::CallMethodDescriptorFastWithKeywords => {
@@ -4198,10 +4197,9 @@ impl ExecutingFrame<'_> {
                 let nargs: u32 = arg.into();
                 let callable = self.nth_value(nargs + 1);
                 let callable_tag = callable as *const PyObject as u32;
-                if cached_tag == callable_tag {
-                    return self.execute_call_vectorcall(nargs, vm);
+                if cached_tag != callable_tag {
+                    self.deoptimize_call();
                 }
-                self.deoptimize_call();
                 self.execute_call_vectorcall(nargs, vm)
             }
             Instruction::CallKwPy => {
@@ -4289,10 +4287,9 @@ impl ExecutingFrame<'_> {
                 let nargs: u32 = arg.into();
                 let callable = self.nth_value(nargs + 2);
                 let callable_tag = callable as *const PyObject as u32;
-                if cached_tag == callable_tag {
-                    return self.execute_call_kw_vectorcall(nargs, vm);
+                if cached_tag != callable_tag {
+                    self.deoptimize_call_kw();
                 }
-                self.deoptimize_call_kw();
                 self.execute_call_kw_vectorcall(nargs, vm)
             }
             Instruction::LoadSuperAttrAttr => {
@@ -5738,7 +5735,9 @@ impl ExecutingFrame<'_> {
             .map(|sr| sr.to_pyobj());
         let has_self = self_or_null.is_some();
 
-        let pos_count = nargs_usize - kw_count;
+        let pos_count = nargs_usize
+            .checked_sub(kw_count)
+            .expect("CALL_KW: kw_count exceeds nargs");
         let effective_nargs = if has_self { pos_count + 1 } else { pos_count };
 
         // Build the full args slice: positional (including self) + kwarg values
