user/clang: Use upstream fix for 32-bit BE

This fixes the problem more generally, using a union so that 64-bit
values can still be stored for offsets; this is required for C++20
module support.

Ref: #1255
Fixes: fabdb20dca ("user/clang: Fixes for PPC32, and more generally")

2 files changed, 156 insertions, 25 deletions

diff --git a/user/clang/APKBUILD b/user/clang/APKBUILD
index 433d79ca3..7d8f46369 100644
--- a/user/clang/APKBUILD
+++ b/user/clang/APKBUILD
@@ -163,7 +163,7 @@ analyzer() {
 
 sha512sums="25eeee9984c8b4d0fbc240df90f33cbb000d3b0414baff5c8982beafcc5e59e7ef18f6f85d95b3a5f60cb3d4cd4f877c80487b5768bc21bc833f107698ad93db  llvm-project-18.1.8.src.tar.xz
 d37d2339a76c21666aa4405b2a620100e6967eb933535b5cea05f5de25a4d75510479443500715529cea38014028741d71553c7b247d5f349a05660133d66bc6  0001-Add-support-for-Ad-lie-Linux.patch
-8928e5f4c5c7160ff1c8bf94b49b54198a6472dfbcb125db45fa0f1f0944b956a33af6004a34636d2ce15022a7ef5a8b77158d8093fb2adde889e0e8085067b3  big-endian-32.patch
+241a087888b7b5373b54653c4675c77c70d82b61a1b79359cba7d5fe0187851e790cb4e7e278a0a59c660b9a980cf087b393dc43a19a975fc9b97717bca12bc4  big-endian-32.patch
 8272ec0eeb93287c9cc961099139f7cb0f94561befc31a4521387fa5f7216dc4b3d99750c4560a0b71ec4acde5bd776abef733cfafe81058ef054b62f72fc209  cfe-005-ppc64-dynamic-linker-path.patch
 0032fdd3864870d345caff9c4ff44f58bebc802bddf06c4b3bf30276c89e237167e6dea03456d322d3f6e2ee5e3a2ecf9f649ed033f0ab078b80bda44371b3ce  ppc-dirwatcher.patch
 a2d90bcfc7cee261d6c8ac3b5dd011f55eab94deff456b63c5ef3598397e358b271e7ae86dec9e56c09c874736645ffbecccde4d31826d9b20908a4a16c61387  ppc-interp.patch
diff --git a/user/clang/big-endian-32.patch b/user/clang/big-endian-32.patch
index 298137257..9235d2f5e 100644
--- a/user/clang/big-endian-32.patch
+++ b/user/clang/big-endian-32.patch
@@ -1,52 +1,183 @@
-We need to use uintptr_t, not uint64_t.
+From 4f37ed5ff6c18c8cf0de244bb064d5f4f60065a4 Mon Sep 17 00:00:00 2001
+From: Jessica Clarke <jrtc27@jrtc27.com>
+Date: Fri, 18 Oct 2024 16:50:22 +0100
+Subject: [PATCH 1/2] [clang] Make LazyOffsetPtr more portable
 
-getAddressOfPointer returns a pointer to the Ptr field.  When dereferenced on
-a 32-bit big endian platform, this will be the first (invalid) 32 bits, not the
-actual 32 bits containing the pointer value.  This leads to bad things.
+LazyOffsetPtr currently relies on uint64_t being able to store a pointer
+and, unless sizeof(uint64_t) == sizeof(void *), little endianness, since
+getAddressOfPointer reinterprets the memory as a pointer. This also
+doesn't properly respect the C++ object model.
 
-Ref: #1255
-Upstream-URL: https://github.com/llvm/llvm-project/issues/111993
---- clang/include/clang/AST/ExternalASTSource.h.old	2024-06-15 17:21:32.000000000 +0000
-+++ clang/include/clang/AST/ExternalASTSource.h	2024-10-10 16:54:58.013411406 +0000
-@@ -326,25 +326,25 @@
+As removing getAddressOfPointer would have wide-reaching implications,
+improve the implementation to account for these problems by using
+placement new and a suitably sized-and-aligned buffer, "right"-aligning
+the objects on big-endian platforms so the LSBs are in the same place
+for use as the discriminator.
+
+Fixes: bc73ef0031b50f7443615fef614fb4ecaaa4bd11
+Fixes: https://github.com/llvm/llvm-project/issues/111993
+---
+ clang/include/clang/AST/ExternalASTSource.h | 48 +++++++++++++++------
+ 1 file changed, 35 insertions(+), 13 deletions(-)
+
+diff --git clang/include/clang/AST/ExternalASTSource.h clang/include/clang/AST/ExternalASTSource.h
+index 385c32edbae0fd..caf37144d5eb73 100644
+--- clang/include/clang/AST/ExternalASTSource.h
++++ clang/include/clang/AST/ExternalASTSource.h
+@@ -25,10 +25,12 @@
+ #include "llvm/ADT/SmallVector.h"
+ #include "llvm/ADT/iterator.h"
+ #include "llvm/Support/PointerLikeTypeTraits.h"
++#include <algorithm>
+ #include <cassert>
+ #include <cstddef>
+ #include <cstdint>
+ #include <iterator>
++#include <new>
+ #include <optional>
+ #include <utility>
+ 
+@@ -326,29 +328,49 @@ struct LazyOffsetPtr {
    ///
    /// If the low bit is clear, a pointer to the AST node. If the low
    /// bit is set, the upper 63 bits are the offset.
 -  mutable uint64_t Ptr = 0;
-+  mutable uintptr_t Ptr = 0;
++  static constexpr size_t DataSize = std::max(sizeof(uint64_t), sizeof(T *));
++  alignas(uint64_t) alignas(T *) mutable unsigned char Data[DataSize] = {};
++
++  unsigned char GetLSB() const {
++    return Data[llvm::sys::IsBigEndianHost ? DataSize - 1 : 0];
++  }
++
++  template <typename U> U &As(bool New) const {
++    unsigned char *Obj =
++        Data + (llvm::sys::IsBigEndianHost ? DataSize - sizeof(U) : 0);
++    if (New)
++      return *new (Obj) U;
++    return *std::launder(reinterpret_cast<U *>(Obj));
++  }
++
++  T *&GetPtr() const { return As<T *>(false); }
++  uint64_t &GetU64() const { return As<uint64_t>(false); }
++  void SetPtr(T *Ptr) const { As<T *>(true) = Ptr; }
++  void SetU64(uint64_t U64) const { As<uint64_t>(true) = U64; }
  
  public:
    LazyOffsetPtr() = default;
 -  explicit LazyOffsetPtr(T *Ptr) : Ptr(reinterpret_cast<uint64_t>(Ptr)) {}
-+  explicit LazyOffsetPtr(T *Ptr) : Ptr(reinterpret_cast<uintptr_t>(Ptr)) {}
++  explicit LazyOffsetPtr(T *Ptr) : Data() { SetPtr(Ptr); }
  
 -  explicit LazyOffsetPtr(uint64_t Offset) : Ptr((Offset << 1) | 0x01) {
--    assert((Offset << 1 >> 1) == Offset && "Offsets must require < 63 bits");
-+  explicit LazyOffsetPtr(uintptr_t Offset) : Ptr((Offset << 1) | 0x01) {
-+    assert((Offset << 1 >> 1) == Offset && "Offsets must fit in addressable bits");
++  explicit LazyOffsetPtr(uint64_t Offset) : Data() {
+     assert((Offset << 1 >> 1) == Offset && "Offsets must require < 63 bits");
      if (Offset == 0)
-       Ptr = 0;
+-      Ptr = 0;
++      SetPtr(NULL);
++    else
++      SetU64((Offset << 1) | 0x01);
    }
  
    LazyOffsetPtr &operator=(T *Ptr) {
 -    this->Ptr = reinterpret_cast<uint64_t>(Ptr);
-+    this->Ptr = reinterpret_cast<uintptr_t>(Ptr);
++    SetPtr(Ptr);
      return *this;
    }
  
--  LazyOffsetPtr &operator=(uint64_t Offset) {
--    assert((Offset << 1 >> 1) == Offset && "Offsets must require < 63 bits");
-+  LazyOffsetPtr &operator=(uintptr_t Offset) {
-+    assert((Offset << 1 >> 1) == Offset && "Offsets must fit in addressable bits");
+   LazyOffsetPtr &operator=(uint64_t Offset) {
+     assert((Offset << 1 >> 1) == Offset && "Offsets must require < 63 bits");
      if (Offset == 0)
-       Ptr = 0;
+-      Ptr = 0;
++      SetPtr(NULL);
      else
-@@ -375,7 +375,7 @@
+-      Ptr = (Offset << 1) | 0x01;
++      SetU64((Offset << 1) | 0x01);
+ 
+     return *this;
+   }
+@@ -356,15 +378,15 @@ struct LazyOffsetPtr {
+   /// Whether this pointer is non-NULL.
+   ///
+   /// This operation does not require the AST node to be deserialized.
+-  explicit operator bool() const { return Ptr != 0; }
++  explicit operator bool() const { return isOffset() || GetPtr() != NULL; }
+ 
+   /// Whether this pointer is non-NULL.
+   ///
+   /// This operation does not require the AST node to be deserialized.
+-  bool isValid() const { return Ptr != 0; }
++  bool isValid() const { return isOffset() || GetPtr() != NULL; }
+ 
+   /// Whether this pointer is currently stored as an offset.
+-  bool isOffset() const { return Ptr & 0x01; }
++  bool isOffset() const { return GetLSB() & 0x01; }
+ 
+   /// Retrieve the pointer to the AST node that this lazy pointer points to.
+   ///
+@@ -375,9 +397,9 @@ struct LazyOffsetPtr {
      if (isOffset()) {
        assert(Source &&
               "Cannot deserialize a lazy pointer without an AST source");
 -      Ptr = reinterpret_cast<uint64_t>((Source->*Get)(Ptr >> 1));
-+      Ptr = reinterpret_cast<uintptr_t>((Source->*Get)(Ptr >> 1));
++      SetPtr((Source->*Get)(GetU64() >> 1));
      }
-     return reinterpret_cast<T*>(Ptr);
+-    return reinterpret_cast<T*>(Ptr);
++    return GetPtr();
+   }
+ 
+   /// Retrieve the address of the AST node pointer. Deserializes the pointee if
+@@ -385,7 +407,7 @@ struct LazyOffsetPtr {
+   T **getAddressOfPointer(ExternalASTSource *Source) const {
+     // Ensure the integer is in pointer form.
+     (void)get(Source);
+-    return reinterpret_cast<T**>(&Ptr);
++    return &GetPtr();
    }
+ };
+ 
+
+From 35eed5f3f5e09c4275cabac09e277a167a98f742 Mon Sep 17 00:00:00 2001
+From: Jessica Clarke <jrtc27@jrtc27.com>
+Date: Fri, 18 Oct 2024 17:45:28 +0100
+Subject: [PATCH 2/2] NULL -> nullptr
+
+---
+ clang/include/clang/AST/ExternalASTSource.h | 8 ++++----
+ 1 file changed, 4 insertions(+), 4 deletions(-)
+
+diff --git clang/include/clang/AST/ExternalASTSource.h clang/include/clang/AST/ExternalASTSource.h
+index caf37144d5eb73..582ed7c65f58ca 100644
+--- clang/include/clang/AST/ExternalASTSource.h
++++ clang/include/clang/AST/ExternalASTSource.h
+@@ -355,7 +355,7 @@ struct LazyOffsetPtr {
+   explicit LazyOffsetPtr(uint64_t Offset) : Data() {
+     assert((Offset << 1 >> 1) == Offset && "Offsets must require < 63 bits");
+     if (Offset == 0)
+-      SetPtr(NULL);
++      SetPtr(nullptr);
+     else
+       SetU64((Offset << 1) | 0x01);
+   }
+@@ -368,7 +368,7 @@ struct LazyOffsetPtr {
+   LazyOffsetPtr &operator=(uint64_t Offset) {
+     assert((Offset << 1 >> 1) == Offset && "Offsets must require < 63 bits");
+     if (Offset == 0)
+-      SetPtr(NULL);
++      SetPtr(nullptr);
+     else
+       SetU64((Offset << 1) | 0x01);
+ 
+@@ -378,12 +378,12 @@ struct LazyOffsetPtr {
+   /// Whether this pointer is non-NULL.
+   ///
+   /// This operation does not require the AST node to be deserialized.
+-  explicit operator bool() const { return isOffset() || GetPtr() != NULL; }
++  explicit operator bool() const { return isOffset() || GetPtr() != nullptr; }
+ 
+   /// Whether this pointer is non-NULL.
+   ///
+   /// This operation does not require the AST node to be deserialized.
+-  bool isValid() const { return isOffset() || GetPtr() != NULL; }
++  bool isValid() const { return isOffset() || GetPtr() != nullptr; }
+ 
+   /// Whether this pointer is currently stored as an offset.
+   bool isOffset() const { return GetLSB() & 0x01; }