user/clang: Fixes for PPC32, and more generally

* Fix upstream issue on all 32-bit BE platforms where pointers are
  cast in an invalid way, causing crashes when building C++ code.

* Improve ppc-interp.patch to ensure *all* executable repl tests will
  be skipped when run on ppc32.

* Disable known-flaky test (found on ppc, but also Gentoo/arm).

Closes: #1255

3 files changed, 90 insertions, 11 deletions

diff --git a/user/clang/APKBUILD b/user/clang/APKBUILD
index bdc1cdad7..433d79ca3 100644
--- a/user/clang/APKBUILD
+++ b/user/clang/APKBUILD
@@ -18,6 +18,7 @@ subpackages="$pkgname-static $pkgname-dev $pkgname-doc $pkgname-libs
 	$pkgname-analyzer::noarch"
 source="https://github.com/llvm/llvm-project/releases/download/llvmorg-$pkgver/llvm-project-$pkgver.src.tar.xz
 	0001-Add-support-for-Ad-lie-Linux.patch
+	big-endian-32.patch
 	cfe-005-ppc64-dynamic-linker-path.patch
 	ppc-dirwatcher.patch
 	ppc-interp.patch
@@ -63,6 +64,18 @@ prepare() {
 		;
 
 	rm -f test/Driver/ppc-float-abi-warning.cpp
+	# known broken on 32-bit platforms
+	rm -f test/CodeGenCUDA/static-device-var-rdc.cu
+
+	case $CARCH in
+	ppc)
+		for _interp_test in code-undo.cpp const.cpp execute-stmts.cpp \
+			execute-weak.cpp execute.cpp fail.cpp global-dtor.cpp \
+			inline-virtual.cpp lambda.cpp multiline.cpp \
+			simple-exception.cpp; do
+			rm test/Interpreter/$_interp_test
+		done;;
+	esac
 }
 
 build() {
@@ -150,7 +163,8 @@ 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
 8272ec0eeb93287c9cc961099139f7cb0f94561befc31a4521387fa5f7216dc4b3d99750c4560a0b71ec4acde5bd776abef733cfafe81058ef054b62f72fc209  cfe-005-ppc64-dynamic-linker-path.patch
 0032fdd3864870d345caff9c4ff44f58bebc802bddf06c4b3bf30276c89e237167e6dea03456d322d3f6e2ee5e3a2ecf9f649ed033f0ab078b80bda44371b3ce  ppc-dirwatcher.patch
-d6de2ed213e2c2a95e6ee68c7c6abe72cad0b97341b221f1c3eed13fc3fbeb95b0a4b07bff9504461d64a659b7f4ea6d61be4ec9ff5c63722b0f41ab135e29a0  ppc-interp.patch
+a2d90bcfc7cee261d6c8ac3b5dd011f55eab94deff456b63c5ef3598397e358b271e7ae86dec9e56c09c874736645ffbecccde4d31826d9b20908a4a16c61387  ppc-interp.patch
 6c6b4fc49539ecf02e4eec9c2bbd89cc37fe01383e7884aa52c90ab0a4aa23cd9a86716bc645af6949f787d2fe3b9a3ad177baef1edbec928437872d14db536d  use-llvm-lit.patch"
diff --git a/user/clang/big-endian-32.patch b/user/clang/big-endian-32.patch
new file mode 100644
index 000000000..298137257
--- /dev/null
+++ b/user/clang/big-endian-32.patch
@@ -0,0 +1,52 @@
+We need to use uintptr_t, not uint64_t.
+
+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.
+
+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 @@
+   ///
+   /// 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;
+ 
+ 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(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");
+     if (Offset == 0)
+       Ptr = 0;
+   }
+ 
+   LazyOffsetPtr &operator=(T *Ptr) {
+-    this->Ptr = reinterpret_cast<uint64_t>(Ptr);
++    this->Ptr = reinterpret_cast<uintptr_t>(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");
+     if (Offset == 0)
+       Ptr = 0;
+     else
+@@ -375,7 +375,7 @@
+     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));
+     }
+     return reinterpret_cast<T*>(Ptr);
+   }
diff --git a/user/clang/ppc-interp.patch b/user/clang/ppc-interp.patch
index bc2905f42..fae58aa3d 100644
--- a/user/clang/ppc-interp.patch
+++ b/user/clang/ppc-interp.patch
@@ -9,14 +9,27 @@ implemented in RuntimeDyld.
  
  // clang-format off
  // RUN: clang-repl "int i = 10;" 'extern "C" int printf(const char*,...);' \
---- clang-14.0.6.src/unittests/Interpreter/InterpreterTest.cpp.old	2022-06-22 16:46:24.000000000 +0000
-+++ clang-14.0.6.src/unittests/Interpreter/InterpreterTest.cpp	2022-12-05 01:53:47.058187317 +0000
-@@ -270,7 +270,7 @@
-   return R.getFoundDecl();
- }
+--- clang/unittests/Interpreter/InterpreterTest.cpp.old	2024-10-10 18:11:05.390017076 +0000
++++ clang/unittests/Interpreter/InterpreterTest.cpp	2024-10-10 22:34:07.176019197 +0000
+@@ -30,7 +30,7 @@
  
--#ifdef CLANG_INTERPRETER_NO_SUPPORT_EXEC
-+#if defined(CLANG_INTERPRETER_NO_SUPPORT_EXEC) || (!defined(__powerpc64__) && defined(__powerpc__))
- TEST(IncrementalProcessing, DISABLED_InstantiateTemplate) {
- #else
- TEST(IncrementalProcessing, InstantiateTemplate) {
+ using namespace clang;
+ 
+-#if defined(_AIX)
++#if defined(_AIX) || (!defined(__powerpc64__) && defined(__powerpc__))
+ #define CLANG_INTERPRETER_NO_SUPPORT_EXEC
+ #endif
+ 
+--- clang/unittests/Interpreter/ExceptionTests/InterpreterExceptionTest.cpp.old	2024-06-15 17:21:32.000000000 +0000
++++ clang/unittests/Interpreter/ExceptionTests/InterpreterExceptionTest.cpp	2024-10-10 22:36:53.358466534 +0000
+@@ -113,8 +113,8 @@
+   if (Triple.isOSAIX())
+     GTEST_SKIP();
+ 
+-  // FIXME: ARM fails due to `Not implemented relocation type!`
+-  if (Triple.isARM())
++  // FIXME: ARM and PPC32 fail due to `Not implemented relocation type!`
++  if (Triple.isARM() || Triple.isPPC32())
+     GTEST_SKIP();
+ 
+   // FIXME: libunwind on darwin is broken, see PR49692.