[Clang][CodeGen] Emit !alloc_token for new expressions (#162099)

[ Reland after 7815df1 ("[Clang] Fix brittle print-header-json.c test") ]

For new expressions, the allocated type is syntactically known and we
can trivially emit the !alloc_token metadata. A subsequent change will
wire up the AllocToken pass and introduce appropriate tests.

---

This change is part of the following series:
  1. llvm/llvm-project#160131
  2. llvm/llvm-project#156838
  3. llvm/llvm-project#162098
  4. llvm/llvm-project#162099
  5. llvm/llvm-project#156839
  6. llvm/llvm-project#156840
  7. llvm/llvm-project#156841
  8. llvm/llvm-project#156842

Author: melver

clang/lib/CodeGen/CGExpr.cpp

@@ -1272,6 +1272,23 @@ void CodeGenFunction::EmitBoundsCheckImpl(const Expr *E, llvm::Value *Bound,
   EmitCheck(std::make_pair(Check, CheckKind), CheckHandler, StaticData, Index);
 }
 
+void CodeGenFunction::EmitAllocToken(llvm::CallBase *CB, QualType AllocType) {
+  assert(SanOpts.has(SanitizerKind::AllocToken) &&
+         "Only needed with -fsanitize=alloc-token");
+
+  PrintingPolicy Policy(CGM.getContext().getLangOpts());
+  Policy.SuppressTagKeyword = true;
+  Policy.FullyQualifiedName = true;
+  SmallString<64> TypeName;
+  llvm::raw_svector_ostream TypeNameOS(TypeName);
+  AllocType.getCanonicalType().print(TypeNameOS, Policy);
+  auto *TypeMDS = llvm::MDString::get(CGM.getLLVMContext(), TypeNameOS.str());
+
+  // Format: !{<type-name>}
+  auto *MDN = llvm::MDNode::get(CGM.getLLVMContext(), {TypeMDS});
+  CB->setMetadata(llvm::LLVMContext::MD_alloc_token, MDN);
+}
+
 CodeGenFunction::ComplexPairTy CodeGenFunction::
 EmitComplexPrePostIncDec(const UnaryOperator *E, LValue LV,
                          bool isInc, bool isPre) {

clang/lib/CodeGen/CGExprCXX.cpp

@@ -1655,11 +1655,16 @@ llvm::Value *CodeGenFunction::EmitCXXNewExpr(const CXXNewExpr *E) {
     RValue RV =
       EmitNewDeleteCall(*this, allocator, allocatorType, allocatorArgs);
 
-    // Set !heapallocsite metadata on the call to operator new.
-    if (getDebugInfo())
-      if (auto *newCall = dyn_cast<llvm::CallBase>(RV.getScalarVal()))
-        getDebugInfo()->addHeapAllocSiteMetadata(newCall, allocType,
-                                                 E->getExprLoc());
+    if (auto *newCall = dyn_cast<llvm::CallBase>(RV.getScalarVal())) {
+      if (auto *CGDI = getDebugInfo()) {
+        // Set !heapallocsite metadata on the call to operator new.
+        CGDI->addHeapAllocSiteMetadata(newCall, allocType, E->getExprLoc());
+      }
+      if (SanOpts.has(SanitizerKind::AllocToken)) {
+        // Set !alloc_token metadata.
+        EmitAllocToken(newCall, allocType);
+      }
+    }
 
     // If this was a call to a global replaceable allocation function that does
     // not take an alignment argument, the allocator is known to produce

clang/lib/CodeGen/CodeGenFunction.h

@@ -3348,6 +3348,9 @@ class CodeGenFunction : public CodeGenTypeCache {
   SanitizerAnnotateDebugInfo(ArrayRef<SanitizerKind::SanitizerOrdinal> Ordinals,
                              SanitizerHandler Handler);
 
+  /// Emit additional metadata used by the AllocToken instrumentation.
+  void EmitAllocToken(llvm::CallBase *CB, QualType AllocType);
+
   llvm::Value *GetCountedByFieldExprGEP(const Expr *Base, const FieldDecl *FD,
                                         const FieldDecl *CountDecl);