From 1221af99281c87d35c65110a75f87893ff0fc947 Mon Sep 17 00:00:00 2001
From: =?utf8?q?Timm=20B=C3=A4der?= <tbaeder@redhat.com>
Date: Fri, 2 Dec 2022 08:19:14 +0100
Subject: [PATCH] [clang][Interp] Use placement new to construct opcode args
 into vector

Differential Revision: https://reviews.llvm.org/D139185
---
 clang/lib/AST/Interp/ByteCodeEmitter.cpp | 19 +++++++++++++------
 clang/lib/AST/Interp/PrimType.h          |  7 +++++++
 clang/lib/AST/Interp/Source.h            |  4 +++-
 3 files changed, 23 insertions(+), 7 deletions(-)

diff --git a/clang/lib/AST/Interp/ByteCodeEmitter.cpp b/clang/lib/AST/Interp/ByteCodeEmitter.cpp
index ff2136d..4633d1e 100644
--- a/clang/lib/AST/Interp/ByteCodeEmitter.cpp
+++ b/clang/lib/AST/Interp/ByteCodeEmitter.cpp
@@ -116,7 +116,8 @@ void ByteCodeEmitter::emitLabel(LabelTy Label) {
       using namespace llvm::support;
 
       /// Rewrite the operand of all jumps to this label.
-      void *Location = Code.data() + Reloc - sizeof(int32_t);
+      void *Location = Code.data() + Reloc - align(sizeof(int32_t));
+      assert(aligned(Location));
       const int32_t Offset = Target - static_cast<int64_t>(Reloc);
       endian::write<int32_t, endianness::native, 1>(Location, Offset);
     }
@@ -126,7 +127,9 @@ void ByteCodeEmitter::emitLabel(LabelTy Label) {
 
 int32_t ByteCodeEmitter::getOffset(LabelTy Label) {
   // Compute the PC offset which the jump is relative to.
-  const int64_t Position = Code.size() + sizeof(Opcode) + sizeof(int32_t);
+  const int64_t Position =
+      Code.size() + align(sizeof(Opcode)) + align(sizeof(int32_t));
+  assert(aligned(Position));
 
   // If target is known, compute jump offset.
   auto It = LabelOffsets.find(Label);
@@ -162,13 +165,17 @@ static void emit(Program &P, std::vector<char> &Code, const T &Val,
     return;
   }
 
+  // Access must be aligned!
+  size_t ValPos = align(Code.size());
+  Size = align(Size);
+  assert(aligned(ValPos + Size));
+  Code.resize(ValPos + Size);
+
   if constexpr (!std::is_pointer_v<T>) {
-    const char *Data = reinterpret_cast<const char *>(&Val);
-    Code.insert(Code.end(), Data, Data + Size);
+    new (Code.data() + ValPos) T(Val);
   } else {
     uint32_t ID = P.getOrCreateNativePointer(Val);
-    const char *Data = reinterpret_cast<const char *>(&ID);
-    Code.insert(Code.end(), Data, Data + Size);
+    new (Code.data() + ValPos) uint32_t(ID);
   }
 }
 
diff --git a/clang/lib/AST/Interp/PrimType.h b/clang/lib/AST/Interp/PrimType.h
index 8490c1f..3a77c66 100644
--- a/clang/lib/AST/Interp/PrimType.h
+++ b/clang/lib/AST/Interp/PrimType.h
@@ -59,6 +59,13 @@ constexpr size_t align(size_t Size) {
   return ((Size + alignof(void *) - 1) / alignof(void *)) * alignof(void *);
 }
 
+constexpr bool aligned(uintptr_t Value) { return Value == align(Value); }
+static_assert(aligned(sizeof(void *)));
+
+static inline bool aligned(const void *P) {
+  return aligned(reinterpret_cast<uintptr_t>(P));
+}
+
 inline bool isPrimitiveIntegral(PrimType Type) {
   switch (Type) {
   case PT_Bool:
diff --git a/clang/lib/AST/Interp/Source.h b/clang/lib/AST/Interp/Source.h
index de4ae55..99ffce3 100644
--- a/clang/lib/AST/Interp/Source.h
+++ b/clang/lib/AST/Interp/Source.h
@@ -13,6 +13,7 @@
 #ifndef LLVM_CLANG_AST_INTERP_SOURCE_H
 #define LLVM_CLANG_AST_INTERP_SOURCE_H
 
+#include "PrimType.h"
 #include "clang/AST/Decl.h"
 #include "clang/AST/Stmt.h"
 #include "llvm/Support/Endian.h"
@@ -47,9 +48,10 @@ public:
 
   /// Reads data and advances the pointer.
   template <typename T> std::enable_if_t<!std::is_pointer<T>::value, T> read() {
+    assert(aligned(Ptr));
     using namespace llvm::support;
     T Value = endian::read<T, endianness::native, 1>(Ptr);
-    Ptr += sizeof(T);
+    Ptr += align(sizeof(T));
     return Value;
   }
 
-- 
2.7.4