Add more ODR checking.

Add the basics for the ODRHash class, which will only process Decl's from
a whitelist, which currently only has AccessSpecDecl.  Different access
specifiers in merged classes can now be detected.

Differential Revision: https://reviews.llvm.org/D21675

llvm-svn: 295800

clang/include/clang/AST/ODRHash.h

@@ -0,0 +1,84 @@
+//===-- ODRHash.h - Hashing to diagnose ODR failures ------------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+///
+/// \file
+/// This file contains the declaration of the ODRHash class, which calculates
+/// a hash based on AST nodes, which is stable across different runs.
+///
+//===----------------------------------------------------------------------===//
+
+#include "clang/AST/DeclarationName.h"
+#include "clang/AST/Type.h"
+#include "clang/AST/TemplateBase.h"
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/FoldingSet.h"
+#include "llvm/ADT/PointerUnion.h"
+#include "llvm/ADT/SmallVector.h"
+
+namespace clang {
+
+class Decl;
+class IdentifierInfo;
+class NestedNameSpecifer;
+class Stmt;
+class TemplateParameterList;
+
+// ODRHash is used to calculate a hash based on AST node contents that
+// does not rely on pointer addresses.  This allows the hash to not vary
+// between runs and is usable to detect ODR problems in modules.  To use,
+// construct an ODRHash object, then call Add* methods over the nodes that
+// need to be hashed.  Then call CalculateHash to get the hash value.
+// Typically, only one Add* call is needed.  clear can be called to reuse the
+// object.
+class ODRHash {
+  // Use DenseMaps to convert between Decl and Type pointers and an index value.
+  llvm::DenseMap<const Decl*, unsigned> DeclMap;
+  llvm::DenseMap<const Type*, unsigned> TypeMap;
+
+  // Save space by processing bools at the end.
+  llvm::SmallVector<bool, 128> Bools;
+
+  llvm::FoldingSetNodeID ID;
+
+public:
+  ODRHash() {}
+
+  // Use this for ODR checking classes between modules.  This method compares
+  // more information than the AddDecl class.
+  void AddCXXRecordDecl(const CXXRecordDecl *Record);
+
+  // Process SubDecls of the main Decl.  This method calls the DeclVisitor
+  // while AddDecl does not.
+  void AddSubDecl(const Decl *D);
+
+  // Reset the object for reuse.
+  void clear();
+
+  // Add booleans to ID and uses it to calculate the hash.
+  unsigned CalculateHash();
+
+  // Add AST nodes that need to be processed.
+  void AddDecl(const Decl *D);
+  void AddType(const Type *T);
+  void AddQualType(QualType T);
+  void AddStmt(const Stmt *S);
+  void AddIdentifierInfo(const IdentifierInfo *II);
+  void AddNestedNameSpecifier(const NestedNameSpecifier *NNS);
+  void AddTemplateName(TemplateName Name);
+  void AddDeclarationName(DeclarationName Name);
+  void AddTemplateArgument(TemplateArgument TA);
+  void AddTemplateParameterList(const TemplateParameterList *TPL);
+
+  // Save booleans until the end to lower the size of data to process.
+  void AddBoolean(bool value);
+
+  static bool isWhitelistedDecl(const Decl* D, const CXXRecordDecl *Record);
+};
+
+}  // end namespace clang

clang/include/clang/Basic/DiagnosticSerializationKinds.td

@@ -117,6 +117,15 @@ def note_module_odr_violation_different_definitions : Note<
 def err_module_odr_violation_different_instantiations : Error<
   "instantiation of %q0 is different in different modules">;
 
+def err_module_odr_violation_mismatch_decl : Error<
+  "%q0 has different definitions in different modules; first difference is "
+  "%select{definition in module '%2'|defined here}1 found "
+  "%select{end of class|public access specifier|private access specifier|"
+  "protected access specifier}3">;
+def note_module_odr_violation_mismatch_decl : Note<"but in '%0' found "
+  "%select{end of class|public access specifier|private access specifier|"
+  "protected access specifier}1">;
+
 def warn_module_uses_date_time : Warning<
   "%select{precompiled header|module}0 uses __DATE__ or __TIME__">,
   InGroup<DiagGroup<"pch-date-time">>;

clang/lib/AST/CMakeLists.txt

@@ -40,6 +40,7 @@ add_clang_library(clangAST
   MicrosoftMangle.cpp
   NestedNameSpecifier.cpp
   NSAPI.cpp
+  ODRHash.cpp
   OpenMPClause.cpp
   ParentMap.cpp
   RawCommentList.cpp

clang/lib/AST/DeclCXX.cpp

@@ -18,6 +18,7 @@
 #include "clang/AST/DeclTemplate.h"
 #include "clang/AST/Expr.h"
 #include "clang/AST/ExprCXX.h"
+#include "clang/AST/ODRHash.h"
 #include "clang/AST/TypeLoc.h"
 #include "clang/Basic/IdentifierTable.h"
 #include "llvm/ADT/STLExtras.h"
@@ -371,7 +372,15 @@ CXXRecordDecl::setBases(CXXBaseSpecifier const * const *Bases,
   data().IsParsingBaseSpecifiers = false;
 }
 
-void CXXRecordDecl::computeODRHash() {}
+void CXXRecordDecl::computeODRHash() {
+  if (!DefinitionData)
+    return;
+
+  ODRHash Hash;
+  Hash.AddCXXRecordDecl(this);
+
+  DefinitionData->ODRHash = Hash.CalculateHash();
+}
 
 void CXXRecordDecl::addedClassSubobject(CXXRecordDecl *Subobj) {
   // C++11 [class.copy]p11:

clang/lib/AST/ODRHash.cpp

@@ -0,0 +1,152 @@
+//===-- ODRHash.cpp - Hashing to diagnose ODR failures ----------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+///
+/// \file
+/// This file implements the ODRHash class, which calculates a hash based
+/// on AST nodes, which is stable across different runs.
+///
+//===----------------------------------------------------------------------===//
+
+#include "clang/AST/ODRHash.h"
+
+#include "clang/AST/DeclVisitor.h"
+#include "clang/AST/NestedNameSpecifier.h"
+#include "clang/AST/StmtVisitor.h"
+#include "clang/AST/TypeVisitor.h"
+
+using namespace clang;
+
+void ODRHash::AddStmt(const Stmt *S) {}
+void ODRHash::AddIdentifierInfo(const IdentifierInfo *II) {}
+void ODRHash::AddNestedNameSpecifier(const NestedNameSpecifier *NNS) {}
+void ODRHash::AddTemplateName(TemplateName Name) {}
+void ODRHash::AddDeclarationName(DeclarationName Name) {}
+void ODRHash::AddTemplateArgument(TemplateArgument TA) {}
+void ODRHash::AddTemplateParameterList(const TemplateParameterList *TPL) {}
+
+void ODRHash::clear() {
+  DeclMap.clear();
+  TypeMap.clear();
+  Bools.clear();
+  ID.clear();
+}
+
+unsigned ODRHash::CalculateHash() {
+  // Append the bools to the end of the data segment backwards.  This allows
+  // for the bools data to be compressed 32 times smaller compared to using
+  // ID.AddBoolean
+  const unsigned unsigned_bits = sizeof(unsigned) * CHAR_BIT;
+  const unsigned size = Bools.size();
+  const unsigned remainder = size % unsigned_bits;
+  const unsigned loops = size / unsigned_bits;
+  auto I = Bools.rbegin();
+  unsigned value = 0;
+  for (unsigned i = 0; i < remainder; ++i) {
+    value <<= 1;
+    value |= *I;
+    ++I;
+  }
+  ID.AddInteger(value);
+
+  for (unsigned i = 0; i < loops; ++i) {
+    value = 0;
+    for (unsigned j = 0; j < unsigned_bits; ++j) {
+      value <<= 1;
+      value |= *I;
+      ++I;
+    }
+    ID.AddInteger(value);
+  }
+
+  assert(I == Bools.rend());
+  Bools.clear();
+  return ID.ComputeHash();
+}
+
+// Process a Decl pointer.  Add* methods call back into ODRHash while Visit*
+// methods process the relevant parts of the Decl.
+class ODRDeclVisitor : public ConstDeclVisitor<ODRDeclVisitor> {
+  typedef ConstDeclVisitor<ODRDeclVisitor> Inherited;
+  llvm::FoldingSetNodeID &ID;
+  ODRHash &Hash;
+
+public:
+  ODRDeclVisitor(llvm::FoldingSetNodeID &ID, ODRHash &Hash)
+      : ID(ID), Hash(Hash) {}
+
+  void Visit(const Decl *D) {
+    ID.AddInteger(D->getKind());
+    Inherited::Visit(D);
+  }
+
+  void VisitAccessSpecDecl(const AccessSpecDecl *D) {
+    ID.AddInteger(D->getAccess());
+    Inherited::VisitAccessSpecDecl(D);
+  }
+};
+
+// Only allow a small portion of Decl's to be processed.  Remove this once
+// all Decl's can be handled.
+bool ODRHash::isWhitelistedDecl(const Decl *D, const CXXRecordDecl *Parent) {
+  if (D->isImplicit()) return false;
+  if (D->getDeclContext() != Parent) return false;
+
+  switch (D->getKind()) {
+    default:
+      return false;
+    case Decl::AccessSpec:
+      return true;
+  }
+}
+
+void ODRHash::AddSubDecl(const Decl *D) {
+  assert(D && "Expecting non-null pointer.");
+  AddDecl(D);
+
+  ODRDeclVisitor(ID, *this).Visit(D);
+}
+
+void ODRHash::AddCXXRecordDecl(const CXXRecordDecl *Record) {
+  assert(Record && Record->hasDefinition() &&
+         "Expected non-null record to be a definition.");
+  AddDecl(Record);
+
+  // Filter out sub-Decls which will not be processed in order to get an
+  // accurate count of Decl's.
+  llvm::SmallVector<const Decl *, 16> Decls;
+  for (const Decl *SubDecl : Record->decls()) {
+    if (isWhitelistedDecl(SubDecl, Record)) {
+      Decls.push_back(SubDecl);
+    }
+  }
+
+  ID.AddInteger(Decls.size());
+  for (auto SubDecl : Decls) {
+    AddSubDecl(SubDecl);
+  }
+}
+
+void ODRHash::AddDecl(const Decl *D) {
+  assert(D && "Expecting non-null pointer.");
+  auto Result = DeclMap.insert(std::make_pair(D, DeclMap.size()));
+  ID.AddInteger(Result.first->second);
+  // On first encounter of a Decl pointer, process it.  Every time afterwards,
+  // only the index value is needed.
+  if (!Result.second) {
+    return;
+  }
+
+  ID.AddInteger(D->getKind());
+}
+
+void ODRHash::AddType(const Type *T) {}
+void ODRHash::AddQualType(QualType T) {}
+void ODRHash::AddBoolean(bool Value) {
+  Bools.push_back(Value);
+}