[libcxx-commits] [libcxx] [libc++] Properly implement array cookies in the ARM ABI (PR #160182)

[Louis Dionne via libcxx-commits]

================
@@ -26,28 +26,94 @@ _LIBCPP_BEGIN_NAMESPACE_STD
 // Trait representing whether a type requires an array cookie at the start of its allocation when
 // allocated as `new T[n]` and deallocated as `delete[] array`.
 //
-// Under the Itanium C++ ABI [1], we know that an array cookie is available unless `T` is trivially
-// destructible and the call to `operator delete[]` is not a sized operator delete. Under ABIs other
-// than the Itanium ABI, we assume there are no array cookies.
+// Under the Itanium C++ ABI [1] and the ARM ABI which derives from it, we know that an array cookie is available
+// unless `T` is trivially destructible and the call to `operator delete[]` is not a sized operator delete. Under
+// other ABIs, we assume there are no array cookies.
 //
 // [1]: https://itanium-cxx-abi.github.io/cxx-abi/abi.html#array-cookies
-#ifdef _LIBCPP_ABI_ITANIUM
+#if defined(_LIBCPP_ABI_ITANIUM) || defined(_LIBCPP_ABI_ITANIUM_WITH_ARM_DIFFERENCES)
 // TODO: Use a builtin instead
-// TODO: We should factor in the choice of the usual deallocation function in this determination.
+// TODO: We should factor in the choice of the usual deallocation function in this determination:
+//       a cookie may be available in more cases but we ignore those for now.
 template <class _Tp>
 struct __has_array_cookie : _Not<is_trivially_destructible<_Tp> > {};
 #else
 template <class _Tp>
 struct __has_array_cookie : false_type {};
 #endif
 
+// Return the array cookie located before the given pointer.
+//
+// In the Itanium ABI [1]
+// ----------------------
+// The array cookie is stored immediately before the first element of the array. If the preferred alignment
+// of array elements (which is different from the ABI alignment) is more than that of size_t, additional
+// padding bytes exist before the array cookie. Assuming array elements of size and alignment 16 bytes, that
+// gives us the following layout:
+//
+// |ooooooooxxxxxxxxaaaaaaaaaaaaaaaabbbbbbbbbbbbbbbbccccccccccccccccdddddddddddddddd|
+//  ^^^^^^^^        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+//     |    ^^^^^^^^                               |
+//     |       |                              array elements
+//  padding    |
+//        array cookie
+//
+// In practice, it is sufficient to read the bytes immediately before the first array element.
+//
+//
+// In the ARM ABI [2]
+// ------------------
+// The array cookie is stored at the very start of the allocation and it has the following form:
+//
+//    struct array_cookie {
+//      std::size_t element_size; // element_size != 0
+//      std::size_t element_count;
+//    };
+//
+// Assuming elements of size and alignment 32 bytes, this gives us the following layout:
+//
+//  |xxxxxxxxXXXXXXXXooooooooooooooooaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaabbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb|
+//   ^^^^^^^^        ^^^^^^^^^^^^^^^^
+//      |    ^^^^^^^^        |       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+// element size  |        padding                                 |
+//         element count                                     array elements
+//
+// We calculate the starting address of the allocation by taking into account the ABI (not the preferred)
+// alignment of the type.
+//
+// [1]: https://itanium-cxx-abi.github.io/cxx-abi/abi.html#array-cookies
+// [2]: https://developer.apple.com/documentation/xcode/writing-arm64-code-for-apple-platforms#Handle-C++-differences
 template <class _Tp>
 // Avoid failures when -fsanitize-address-poison-custom-array-cookie is enabled
-_LIBCPP_HIDE_FROM_ABI _LIBCPP_NO_SANITIZE("address") size_t __get_array_cookie(_Tp const* __ptr) {
+_LIBCPP_HIDE_FROM_ABI _LIBCPP_NO_SANITIZE("address") size_t __get_array_cookie([[__maybe_unused__]] _Tp const* __ptr) {
   static_assert(
       __has_array_cookie<_Tp>::value, "Trying to access the array cookie of a type that is not guaranteed to have one");
-  size_t const* __cookie = reinterpret_cast<size_t const*>(__ptr) - 1; // TODO: Use a builtin instead
-  return *__cookie;
+
+#if defined(_LIBCPP_ABI_ITANIUM)
+
+  using _ArrayCookie             = size_t;
+  char const* __allocation_start = reinterpret_cast<char const*>(__ptr) - sizeof(_ArrayCookie);
+  char __cookie[sizeof(_ArrayCookie)];
----------------
ldionne wrote:

There's a bit of duplication and complexity, but this code is tricky enough that IMO it's better to be explicit than clever. I think this achieves the best level of clarity.

https://github.com/llvm/llvm-project/pull/160182