avoid marking as immutable what is already immutable

this has been demonstrated to help performance

compiler/rustc_const_eval/src/interpret/operand.rs

@@ -93,6 +93,17 @@ impl<Prov: Provenance> Immediate<Prov> {
             Immediate::Uninit => bug!("Got uninit where a scalar pair was expected"),
         }
     }
+
+    /// Returns the scalar from the first component and optionally the 2nd component as metadata.
+    #[inline]
+    #[cfg_attr(debug_assertions, track_caller)] // only in debug builds due to perf (see #98980)
+    pub fn to_scalar_and_meta(self) -> (Scalar<Prov>, MemPlaceMeta<Prov>) {
+        match self {
+            Immediate::ScalarPair(val1, val2) => (val1, MemPlaceMeta::Meta(val2)),
+            Immediate::Scalar(val) => (val, MemPlaceMeta::None),
+            Immediate::Uninit => bug!("Got uninit where a scalar or scalar pair was expected"),
+        }
+    }
 }
 
 // ScalarPair needs a type to interpret, so we often have an immediate and a type together

compiler/rustc_const_eval/src/interpret/place.rs

@@ -406,11 +406,7 @@ where
         let pointee_type =
             val.layout.ty.builtin_deref(true).expect("`ref_to_mplace` called on non-ptr type").ty;
         let layout = self.layout_of(pointee_type)?;
-        let (ptr, meta) = match **val {
-            Immediate::Scalar(ptr) => (ptr, MemPlaceMeta::None),
-            Immediate::ScalarPair(ptr, meta) => (ptr, MemPlaceMeta::Meta(meta)),
-            Immediate::Uninit => throw_ub!(InvalidUninitBytes(None)),
-        };
+        let (ptr, meta) = val.to_scalar_and_meta();
 
         // `ref_to_mplace` is called on raw pointers even if they don't actually get dereferenced;
         // we hence can't call `size_and_align_of` since that asserts more validity than we want.