Split reinterpret_casts of member pointers out from CK_BitCast; this

is general goodness because representations of member pointers are
not always equivalent across member pointer types on all ABIs
(even though this isn't really standard-endorsed).

Take advantage of the new information to teach IR-generation how
to do these reinterprets in constant initializers.  Make sure this
works when intermingled with hierarchy conversions (although
this is not part of our motivating use case).  Doing this in the
constant-evaluator would probably have been better, but that would
require a *lot* of extra structure in the representation of
constant member pointers:  you'd really have to track an arbitrary
chain of hierarchy conversions and reinterpretations in order to
get this right.  Ultimately, this seems less complex.  I also
wasn't quite sure how to extend the constant evaluator to handle
foldings that we don't actually want to treat as extended
constant expressions.

llvm-svn: 150551

clang/include/clang/AST/OperationKinds.h

@@ -117,6 +117,15 @@ enum CastKind {
   /// against the null member pointer.
   CK_MemberPointerToBoolean,
 
+  /// CK_ReinterpretMemberPointer - Reinterpret a member pointer as a
+  /// different kind of member pointer.  C++ forbids this from
+  /// crossing between function and object types, but otherwise does
+  /// not restrict it.  However, the only operation that is permitted
+  /// on a "punned" member pointer is casting it back to the original
+  /// type, which is required to be a lossless operation (although
+  /// many ABIs do not guarantee this on all possible intermediate types).
+  CK_ReinterpretMemberPointer,
+
   /// CK_UserDefinedConversion - Conversion using a user defined type
   /// conversion function.
   ///    struct A { operator int(); }; int i = int(A());

clang/lib/AST/Expr.cpp

@@ -1053,6 +1053,11 @@ void CastExpr::CheckCastConsistency() const {
     assert(getSubExpr()->getType()->isBlockPointerType());
     goto CheckNoBasePath;
 
+  case CK_ReinterpretMemberPointer:
+    assert(getType()->isMemberPointerType());
+    assert(getSubExpr()->getType()->isMemberPointerType());
+    goto CheckNoBasePath;
+
   case CK_BitCast:
     // Arbitrary casts to C pointer types count as bitcasts.
     // Otherwise, we should only have block and ObjC pointer casts
@@ -1156,6 +1161,8 @@ const char *CastExpr::getCastKindName() const {
     return "BaseToDerivedMemberPointer";
   case CK_DerivedToBaseMemberPointer:
     return "DerivedToBaseMemberPointer";
+  case CK_ReinterpretMemberPointer:
+    return "ReinterpretMemberPointer";
   case CK_UserDefinedConversion:
     return "UserDefinedConversion";
   case CK_ConstructorConversion:

clang/lib/AST/ExprConstant.cpp

@@ -4974,6 +4974,7 @@ bool IntExprEvaluator::VisitCastExpr(const CastExpr *E) {
   case CK_NullToMemberPointer:
   case CK_BaseToDerivedMemberPointer:
   case CK_DerivedToBaseMemberPointer:
+  case CK_ReinterpretMemberPointer:
   case CK_ConstructorConversion:
   case CK_IntegralToPointer:
   case CK_ToVoid:
@@ -5450,6 +5451,7 @@ bool ComplexExprEvaluator::VisitCastExpr(const CastExpr *E) {
   case CK_BaseToDerivedMemberPointer:
   case CK_DerivedToBaseMemberPointer:
   case CK_MemberPointerToBoolean:
+  case CK_ReinterpretMemberPointer:
   case CK_ConstructorConversion:
   case CK_IntegralToPointer:
   case CK_PointerToIntegral:

clang/lib/CodeGen/CGCXXABI.cpp

@@ -71,6 +71,11 @@ llvm::Value *CGCXXABI::EmitMemberPointerConversion(CodeGenFunction &CGF,
   return GetBogusMemberPointer(CGM, E->getType());
 }
 
+llvm::Constant *CGCXXABI::EmitMemberPointerConversion(const CastExpr *E,
+                                                      llvm::Constant *Src) {
+  return GetBogusMemberPointer(CGM, E->getType());
+}
+
 llvm::Value *
 CGCXXABI::EmitMemberPointerComparison(CodeGenFunction &CGF,
                                       llvm::Value *L,
@@ -172,3 +177,24 @@ void CGCXXABI::EmitGuardedInit(CodeGenFunction &CGF,
                                bool PerformInit) {
   ErrorUnsupportedABI(CGF, "static local variable initialization");
 }
+
+/// Returns the adjustment, in bytes, required for the given
+/// member-pointer operation.  Returns null if no adjustment is
+/// required.
+llvm::Constant *CGCXXABI::getMemberPointerAdjustment(const CastExpr *E) {
+  assert(E->getCastKind() == CK_DerivedToBaseMemberPointer ||
+         E->getCastKind() == CK_BaseToDerivedMemberPointer);
+
+  QualType derivedType;
+  if (E->getCastKind() == CK_DerivedToBaseMemberPointer)
+    derivedType = E->getSubExpr()->getType();
+  else
+    derivedType = E->getType();
+
+  const CXXRecordDecl *derivedClass =
+    derivedType->castAs<MemberPointerType>()->getClass()->getAsCXXRecordDecl();
+
+  return CGM.GetNonVirtualBaseClassOffset(derivedClass,
+                                          E->path_begin(),
+                                          E->path_end());
+}

clang/lib/CodeGen/CGCXXABI.h

@@ -100,12 +100,17 @@ public:
                                                     llvm::Value *MemPtr,
                                             const MemberPointerType *MPT);
 
-  /// Perform a derived-to-base or base-to-derived member pointer
-  /// conversion.
+  /// Perform a derived-to-base, base-to-derived, or bitcast member
+  /// pointer conversion.
   virtual llvm::Value *EmitMemberPointerConversion(CodeGenFunction &CGF,
                                                    const CastExpr *E,
                                                    llvm::Value *Src);
 
+  /// Perform a derived-to-base, base-to-derived, or bitcast member
+  /// pointer conversion on a constant value.
+  virtual llvm::Constant *EmitMemberPointerConversion(const CastExpr *E,
+                                                      llvm::Constant *Src);
+
   /// Return true if the given member pointer can be zero-initialized
   /// (in the C++ sense) with an LLVM zeroinitializer.
   virtual bool isZeroInitializable(const MemberPointerType *MPT);
@@ -137,6 +142,15 @@ public:
                              llvm::Value *MemPtr,
                              const MemberPointerType *MPT);
 
+protected:
+  /// A utility method for computing the offset required for the given
+  /// base-to-derived or derived-to-base member-pointer conversion.
+  /// Does not handle virtual conversions (in case we ever fully
+  /// support an ABI that allows this).  Returns null if no adjustment
+  /// is required.
+  llvm::Constant *getMemberPointerAdjustment(const CastExpr *E);
+
+public:
   /// Build the signature of the given constructor variant by adding
   /// any required parameters.  For convenience, ResTy has been
   /// initialized to 'void', and ArgTys has been initialized with the

clang/lib/CodeGen/CGExpr.cpp

@@ -2090,6 +2090,7 @@ LValue CodeGenFunction::EmitCastLValue(const CastExpr *E) {
   case CK_DerivedToBaseMemberPointer:
   case CK_BaseToDerivedMemberPointer:
   case CK_MemberPointerToBoolean:
+  case CK_ReinterpretMemberPointer:
   case CK_AnyPointerToBlockPointerCast:
   case CK_ARCProduceObject:
   case CK_ARCConsumeObject:

clang/lib/CodeGen/CGExprAgg.cpp

@@ -360,6 +360,7 @@ void AggExprEmitter::VisitCastExpr(CastExpr *E) {
   case CK_BaseToDerivedMemberPointer:
   case CK_DerivedToBaseMemberPointer:
   case CK_MemberPointerToBoolean:
+  case CK_ReinterpretMemberPointer:
   case CK_IntegralToPointer:
   case CK_PointerToIntegral:
   case CK_PointerToBoolean:

clang/lib/CodeGen/CGExprComplex.cpp

@@ -388,6 +388,7 @@ ComplexPairTy ComplexExprEmitter::EmitCast(CastExpr::CastKind CK, Expr *Op,
   case CK_BaseToDerivedMemberPointer:
   case CK_DerivedToBaseMemberPointer:
   case CK_MemberPointerToBoolean:
+  case CK_ReinterpretMemberPointer:
   case CK_ConstructorConversion:
   case CK_IntegralToPointer:
   case CK_PointerToIntegral:

clang/lib/CodeGen/CGExprConstant.cpp

@@ -620,6 +620,11 @@ public:
 
     case CK_Dependent: llvm_unreachable("saw dependent cast!");
 
+    case CK_ReinterpretMemberPointer:
+    case CK_DerivedToBaseMemberPointer:
+    case CK_BaseToDerivedMemberPointer:
+      return CGM.getCXXABI().EmitMemberPointerConversion(E, C);
+
     // These will never be supported.
     case CK_ObjCObjectLValueCast:
     case CK_ARCProduceObject:
@@ -630,18 +635,16 @@ public:
 
     // These don't need to be handled here because Evaluate knows how to
     // evaluate them in the cases where they can be folded.
+    case CK_BitCast:
     case CK_ToVoid:
     case CK_Dynamic:
     case CK_LValueBitCast:
     case CK_NullToMemberPointer:
-    case CK_DerivedToBaseMemberPointer:
-    case CK_BaseToDerivedMemberPointer:
     case CK_UserDefinedConversion:
     case CK_ConstructorConversion:
     case CK_CPointerToObjCPointerCast:
     case CK_BlockPointerToObjCPointerCast:
     case CK_AnyPointerToBlockPointerCast:
-    case CK_BitCast:
     case CK_ArrayToPointerDecay:
     case CK_FunctionToPointerDecay:
     case CK_BaseToDerived:

clang/lib/CodeGen/CGExprScalar.cpp

@@ -1122,6 +1122,7 @@ Value *ScalarExprEmitter::VisitCastExpr(CastExpr *CE) {
     return CGF.CGM.getCXXABI().EmitNullMemberPointer(MPT);
   }
 
+  case CK_ReinterpretMemberPointer:
   case CK_BaseToDerivedMemberPointer:
   case CK_DerivedToBaseMemberPointer: {
     Value *Src = Visit(E);

clang/lib/CodeGen/ItaniumCXXABI.cpp

@@ -73,6 +73,8 @@ public:
   llvm::Value *EmitMemberPointerConversion(CodeGenFunction &CGF,
                                            const CastExpr *E,
                                            llvm::Value *Src);
+  llvm::Constant *EmitMemberPointerConversion(const CastExpr *E,
+                                              llvm::Constant *Src);
 
   llvm::Constant *EmitNullMemberPointer(const MemberPointerType *MPT);
 
@@ -312,7 +314,10 @@ llvm::Value *ItaniumCXXABI::EmitMemberDataPointerAddress(CodeGenFunction &CGF,
   return Builder.CreateBitCast(Addr, PType);
 }
 
-/// Perform a derived-to-base or base-to-derived member pointer conversion.
+/// Perform a bitcast, derived-to-base, or base-to-derived member pointer
+/// conversion.
+///
+/// Bitcast conversions are always a no-op under Itanium.
 ///
 /// Obligatory offset/adjustment diagram:
 ///         <-- offset -->          <-- adjustment -->
@@ -335,64 +340,105 @@ llvm::Value *ItaniumCXXABI::EmitMemberDataPointerAddress(CodeGenFunction &CGF,
 llvm::Value *
 ItaniumCXXABI::EmitMemberPointerConversion(CodeGenFunction &CGF,
                                            const CastExpr *E,
-                                           llvm::Value *Src) {
+                                           llvm::Value *src) {
   assert(E->getCastKind() == CK_DerivedToBaseMemberPointer ||
-         E->getCastKind() == CK_BaseToDerivedMemberPointer);
+         E->getCastKind() == CK_BaseToDerivedMemberPointer ||
+         E->getCastKind() == CK_ReinterpretMemberPointer);
+
+  // Under Itanium, reinterprets don't require any additional processing.
+  if (E->getCastKind() == CK_ReinterpretMemberPointer) return src;
+
+  // Use constant emission if we can.
+  if (isa<llvm::Constant>(src))
+    return EmitMemberPointerConversion(E, cast<llvm::Constant>(src));
+
+  llvm::Constant *adj = getMemberPointerAdjustment(E);
+  if (!adj) return src;
 
   CGBuilderTy &Builder = CGF.Builder;
+  bool isDerivedToBase = (E->getCastKind() == CK_DerivedToBaseMemberPointer);
 
-  const MemberPointerType *SrcTy =
-    E->getSubExpr()->getType()->getAs<MemberPointerType>();
-  const MemberPointerType *DestTy = E->getType()->getAs<MemberPointerType>();
-
-  const CXXRecordDecl *SrcDecl = SrcTy->getClass()->getAsCXXRecordDecl();
-  const CXXRecordDecl *DestDecl = DestTy->getClass()->getAsCXXRecordDecl();
-
-  bool DerivedToBase =
-    E->getCastKind() == CK_DerivedToBaseMemberPointer;
-
-  const CXXRecordDecl *DerivedDecl;
-  if (DerivedToBase)
-    DerivedDecl = SrcDecl;
-  else
-    DerivedDecl = DestDecl;
-
-  llvm::Constant *Adj = 
-    CGF.CGM.GetNonVirtualBaseClassOffset(DerivedDecl,
-                                         E->path_begin(),
-                                         E->path_end());
-  if (!Adj) return Src;
+  const MemberPointerType *destTy =
+    E->getType()->castAs<MemberPointerType>();
 
   // For member data pointers, this is just a matter of adding the
   // offset if the source is non-null.
-  if (SrcTy->isMemberDataPointer()) {
-    llvm::Value *Dst;
-    if (DerivedToBase)
-      Dst = Builder.CreateNSWSub(Src, Adj, "adj");
+  if (destTy->isMemberDataPointer()) {
+    llvm::Value *dst;
+    if (isDerivedToBase)
+      dst = Builder.CreateNSWSub(src, adj, "adj");
     else
-      Dst = Builder.CreateNSWAdd(Src, Adj, "adj");
+      dst = Builder.CreateNSWAdd(src, adj, "adj");
 
     // Null check.
-    llvm::Value *Null = llvm::Constant::getAllOnesValue(Src->getType());
-    llvm::Value *IsNull = Builder.CreateICmpEQ(Src, Null, "memptr.isnull");
-    return Builder.CreateSelect(IsNull, Src, Dst);
+    llvm::Value *null = llvm::Constant::getAllOnesValue(src->getType());
+    llvm::Value *isNull = Builder.CreateICmpEQ(src, null, "memptr.isnull");
+    return Builder.CreateSelect(isNull, src, dst);
   }
 
   // The this-adjustment is left-shifted by 1 on ARM.
   if (IsARM) {
-    uint64_t Offset = cast<llvm::ConstantInt>(Adj)->getZExtValue();
-    Offset <<= 1;
-    Adj = llvm::ConstantInt::get(Adj->getType(), Offset);
+    uint64_t offset = cast<llvm::ConstantInt>(adj)->getZExtValue();
+    offset <<= 1;
+    adj = llvm::ConstantInt::get(adj->getType(), offset);
   }
 
-  llvm::Value *SrcAdj = Builder.CreateExtractValue(Src, 1, "src.adj");
-  llvm::Value *DstAdj;
-  if (DerivedToBase)
-    DstAdj = Builder.CreateNSWSub(SrcAdj, Adj, "adj");
+  llvm::Value *srcAdj = Builder.CreateExtractValue(src, 1, "src.adj");
+  llvm::Value *dstAdj;
+  if (isDerivedToBase)
+    dstAdj = Builder.CreateNSWSub(srcAdj, adj, "adj");
   else
-    DstAdj = Builder.CreateNSWAdd(SrcAdj, Adj, "adj");
+    dstAdj = Builder.CreateNSWAdd(srcAdj, adj, "adj");
 
-  return Builder.CreateInsertValue(Src, DstAdj, 1);
+  return Builder.CreateInsertValue(src, dstAdj, 1);
+}
+
+llvm::Constant *
+ItaniumCXXABI::EmitMemberPointerConversion(const CastExpr *E,
+                                           llvm::Constant *src) {
+  assert(E->getCastKind() == CK_DerivedToBaseMemberPointer ||
+         E->getCastKind() == CK_BaseToDerivedMemberPointer ||
+         E->getCastKind() == CK_ReinterpretMemberPointer);
+
+  // Under Itanium, reinterprets don't require any additional processing.
+  if (E->getCastKind() == CK_ReinterpretMemberPointer) return src;
+
+  // If the adjustment is trivial, we don't need to do anything.
+  llvm::Constant *adj = getMemberPointerAdjustment(E);
+  if (!adj) return src;
+
+  bool isDerivedToBase = (E->getCastKind() == CK_DerivedToBaseMemberPointer);
+
+  const MemberPointerType *destTy =
+    E->getType()->castAs<MemberPointerType>();
+
+  // For member data pointers, this is just a matter of adding the
+  // offset if the source is non-null.
+  if (destTy->isMemberDataPointer()) {
+    // null maps to null.
+    if (src->isAllOnesValue()) return src;
+
+    if (isDerivedToBase)
+      return llvm::ConstantExpr::getNSWSub(src, adj);
+    else
+      return llvm::ConstantExpr::getNSWAdd(src, adj);
+  }
+
+  // The this-adjustment is left-shifted by 1 on ARM.
+  if (IsARM) {
+    uint64_t offset = cast<llvm::ConstantInt>(adj)->getZExtValue();
+    offset <<= 1;
+    adj = llvm::ConstantInt::get(adj->getType(), offset);
+  }
+
+  llvm::Constant *srcAdj = llvm::ConstantExpr::getExtractValue(src, 1);
+  llvm::Constant *dstAdj;
+  if (isDerivedToBase)
+    dstAdj = llvm::ConstantExpr::getNSWSub(srcAdj, adj);
+  else
+    dstAdj = llvm::ConstantExpr::getNSWAdd(srcAdj, adj);
+
+  return llvm::ConstantExpr::getInsertValue(src, dstAdj, 1);
 }
 
 llvm::Constant *

clang/lib/Sema/SemaCast.cpp

@@ -1576,7 +1576,8 @@ static TryCastResult TryReinterpretCast(Sema &Self, ExprResult &SrcExpr,
     }
 
     // A valid member pointer cast.
-    Kind = IsLValueCast? CK_LValueBitCast : CK_BitCast;
+    assert(!IsLValueCast);
+    Kind = CK_ReinterpretMemberPointer;
     return TC_Success;
   }
 

clang/lib/StaticAnalyzer/Core/ExprEngineC.cpp

@@ -289,6 +289,7 @@ void ExprEngine::VisitCast(const CastExpr *CastE, const Expr *Ex,
       case CK_NullToMemberPointer:
       case CK_BaseToDerivedMemberPointer:
       case CK_DerivedToBaseMemberPointer:
+      case CK_ReinterpretMemberPointer:
       case CK_UserDefinedConversion:
       case CK_ConstructorConversion:
       case CK_VectorSplat:

clang/test/CodeGenCXX/member-function-pointers.cpp

@@ -28,6 +28,16 @@ void (C::*pc2)() = &C::f;
 // CHECK: @pc3 = global { i64, i64 } { i64 1, i64 0 }, align 8
 void (A::*pc3)() = &A::vf1;
 
+// Tests for test10.
+// CHECK: @_ZN6test101aE = global { i64, i64 } { i64 ptrtoint (void (%"struct.test10::A"*)* @_ZN6test101A3fooEv to i64), i64 0 }, align 8
+// CHECK: @_ZN6test101bE = global { i64, i64 } { i64 ptrtoint (void (%"struct.test10::A"*)* @_ZN6test101A3fooEv to i64), i64 8 }, align 8
+// CHECK: @_ZN6test101cE = global { i64, i64 } { i64 ptrtoint (void (%"struct.test10::A"*)* @_ZN6test101A3fooEv to i64), i64 8 }, align 8
+// CHECK: @_ZN6test101dE = global { i64, i64 } { i64 ptrtoint (void (%"struct.test10::A"*)* @_ZN6test101A3fooEv to i64), i64 16 }, align 8
+// CHECK-LP32: @_ZN6test101aE = global { i32, i32 } { i32 ptrtoint (void (%"struct.test10::A"*)* @_ZN6test101A3fooEv to i32), i32 0 }, align 4
+// CHECK-LP32: @_ZN6test101bE = global { i32, i32 } { i32 ptrtoint (void (%"struct.test10::A"*)* @_ZN6test101A3fooEv to i32), i32 4 }, align 4
+// CHECK-LP32: @_ZN6test101cE = global { i32, i32 } { i32 ptrtoint (void (%"struct.test10::A"*)* @_ZN6test101A3fooEv to i32), i32 4 }, align 4
+// CHECK-LP32: @_ZN6test101dE = global { i32, i32 } { i32 ptrtoint (void (%"struct.test10::A"*)* @_ZN6test101A3fooEv to i32), i32 8 }, align 4
+
 void f() {
   // CHECK: store { i64, i64 } zeroinitializer, { i64, i64 }* @pa
   pa = 0;
@@ -232,3 +242,33 @@ namespace test9 {
     static S array[] = { (fooptr) &B::foo };
   }
 }
+
+// rdar://problem/10815683 - Verify that we can emit reinterprets of
+// member pointers as constant initializers.  For added trickiness,
+// we also add some non-trivial adjustments.
+namespace test10 {
+  struct A {
+    int nonEmpty;
+    void foo();
+  };
+  struct B : public A {
+    virtual void requireNonZeroAdjustment();
+  };
+  struct C {
+    int nonEmpty;
+  };
+  struct D : public C {
+    virtual void requireNonZeroAdjustment();
+  };
+
+  // Non-ARM tests at top of file.
+  void (A::*a)() = &A::foo;
+  void (B::*b)() = (void (B::*)()) &A::foo;
+  void (C::*c)() = (void (C::*)()) (void (B::*)()) &A::foo;
+  void (D::*d)() = (void (C::*)()) (void (B::*)()) &A::foo;
+}
+// It's not that the offsets are doubled on ARM, it's that they're left-shifted by 1.
+// CHECK-ARM: @_ZN6test101aE = global { i32, i32 } { i32 ptrtoint (void (%"struct.test10::A"*)* @_ZN6test101A3fooEv to i32), i32 0 }, align 4
+// CHECK-ARM: @_ZN6test101bE = global { i32, i32 } { i32 ptrtoint (void (%"struct.test10::A"*)* @_ZN6test101A3fooEv to i32), i32 8 }, align 4
+// CHECK-ARM: @_ZN6test101cE = global { i32, i32 } { i32 ptrtoint (void (%"struct.test10::A"*)* @_ZN6test101A3fooEv to i32), i32 8 }, align 4
+// CHECK-ARM: @_ZN6test101dE = global { i32, i32 } { i32 ptrtoint (void (%"struct.test10::A"*)* @_ZN6test101A3fooEv to i32), i32 16 }, align 4