[llvm] [TySan] A Type Sanitizer (LLVM) (PR #76259)

[Florian Mayer via llvm-commits]

================
@@ -0,0 +1,868 @@
+//===----- TypeSanitizer.cpp - type-based-aliasing-violation detector -----===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file is a part of TypeSanitizer, a type-based-aliasing-violation
+// detector.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Transforms/Instrumentation/TypeSanitizer.h"
+#include "llvm/ADT/SetVector.h"
+#include "llvm/ADT/SmallSet.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/ADT/Statistic.h"
+#include "llvm/ADT/StringExtras.h"
+#include "llvm/Analysis/MemoryLocation.h"
+#include "llvm/Analysis/TargetLibraryInfo.h"
+#include "llvm/IR/DataLayout.h"
+#include "llvm/IR/Function.h"
+#include "llvm/IR/IRBuilder.h"
+#include "llvm/IR/Instructions.h"
+#include "llvm/IR/IntrinsicInst.h"
+#include "llvm/IR/Intrinsics.h"
+#include "llvm/IR/LLVMContext.h"
+#include "llvm/IR/MDBuilder.h"
+#include "llvm/IR/Metadata.h"
+#include "llvm/IR/Module.h"
+#include "llvm/IR/Type.h"
+#include "llvm/ProfileData/InstrProf.h"
+#include "llvm/Support/CommandLine.h"
+#include "llvm/Support/Debug.h"
+#include "llvm/Support/MD5.h"
+#include "llvm/Support/MathExtras.h"
+#include "llvm/Support/Regex.h"
+#include "llvm/Support/raw_ostream.h"
+#include "llvm/Transforms/Utils/BasicBlockUtils.h"
+#include "llvm/Transforms/Utils/Local.h"
+#include "llvm/Transforms/Utils/ModuleUtils.h"
+
+#include <cctype>
+
+using namespace llvm;
+
+#define DEBUG_TYPE "tysan"
+
+static const char *const kTysanModuleCtorName = "tysan.module_ctor";
+static const char *const kTysanInitName = "__tysan_init";
+static const char *const kTysanCheckName = "__tysan_check";
+static const char *const kTysanGVNamePrefix = "__tysan_v1_";
+
+static const char *const kTysanShadowMemoryAddress =
+    "__tysan_shadow_memory_address";
+static const char *const kTysanAppMemMask = "__tysan_app_memory_mask";
+
+static cl::opt<bool>
+    ClWritesAlwaysSetType("tysan-writes-always-set-type",
+                          cl::desc("Writes always set the type"), cl::Hidden,
+                          cl::init(false));
+
+STATISTIC(NumInstrumentedAccesses, "Number of instrumented accesses");
+
+static Regex AnonNameRegex("^_ZTS.*N[1-9][0-9]*_GLOBAL__N");
+
+namespace {
+
+/// TypeSanitizer: instrument the code in module to find  type-based aliasing
+/// violations.
+struct TypeSanitizer {
+  TypeSanitizer(Module &M);
+  bool run(Function &F, const TargetLibraryInfo &TLI);
+  void instrumentGlobals();
+
+private:
+  typedef SmallDenseMap<const MDNode *, GlobalVariable *, 8>
+      TypeDescriptorsMapTy;
+  typedef SmallDenseMap<const MDNode *, std::string, 8> TypeNameMapTy;
+
+  void initializeCallbacks(Module &M);
+
+  Value *getShadowBase(Function &F);
+  Value *getAppMemMask(Function &F);
+
+  bool instrumentWithShadowUpdate(IRBuilder<> &IRB, const MDNode *TBAAMD,
+                                  Value *Ptr, uint64_t AccessSize, bool IsRead,
+                                  bool IsWrite, Value *&ShadowBase,
+                                  Value *&AppMemMask, bool ForceSetType,
+                                  bool SanitizeFunction,
+                                  TypeDescriptorsMapTy &TypeDescriptors,
+                                  const DataLayout &DL);
+  bool instrumentMemoryAccess(Instruction *I, MemoryLocation &MLoc,
+                              Value *&ShadowBase, Value *&AppMemMask,
+                              bool SanitizeFunction,
+                              TypeDescriptorsMapTy &TypeDescriptors,
+                              const DataLayout &DL);
+  bool instrumentMemInst(Value *I, Value *&ShadowBase, Value *&AppMemMask,
+                         const DataLayout &DL);
+
+  std::string getAnonymousStructIdentifier(const MDNode *MD,
+                                           TypeNameMapTy &TypeNames);
+  bool generateTypeDescriptor(const MDNode *MD,
+                              TypeDescriptorsMapTy &TypeDescriptors,
+                              TypeNameMapTy &TypeNames, Module &M);
+  bool generateBaseTypeDescriptor(const MDNode *MD,
+                                  TypeDescriptorsMapTy &TypeDescriptors,
+                                  TypeNameMapTy &TypeNames, Module &M);
+
+  const Triple TargetTriple;
+  Regex AnonNameRegex;
+  Type *IntptrTy;
+  uint64_t PtrShift;
+  IntegerType *OrdTy;
+
+  // Callbacks to run-time library are computed in doInitialization.
+  Function *TysanCheck;
+  Function *TysanCtorFunction;
+  Function *TysanGlobalsSetTypeFunction;
+};
+} // namespace
+
+TypeSanitizer::TypeSanitizer(Module &M)
+    : TargetTriple(Triple(M.getTargetTriple())),
+      AnonNameRegex("^_ZTS.*N[1-9][0-9]*_GLOBAL__N") {
+  const DataLayout &DL = M.getDataLayout();
+  IntptrTy = DL.getIntPtrType(M.getContext());
+  PtrShift = countr_zero(IntptrTy->getPrimitiveSizeInBits() / 8);
+
+  TysanGlobalsSetTypeFunction = M.getFunction("__tysan_set_globals_types");
+  initializeCallbacks(M);
+}
+
+void TypeSanitizer::initializeCallbacks(Module &M) {
+  IRBuilder<> IRB(M.getContext());
+  OrdTy = IRB.getInt32Ty();
+
+  AttributeList Attr;
+  Attr = Attr.addFnAttribute(M.getContext(), Attribute::NoUnwind);
+  // Initialize the callbacks.
+  TysanCheck = cast<Function>(
----------------
fmayer wrote:

Why can't you just store the `FunctionCallee`? That's what we do in HWASan e.g.

https://github.com/llvm/llvm-project/pull/76259