Move parsing of identifiers in MS-style inline assembly into

the actual parser and support arbitrary id-expressions.

We're actually basically set up to do arbitrary expressions here
if we wanted to.

Assembly operands permit things like A::x to be written regardless
of language mode, which forces us to embellish the evaluation
context logic somewhat.  The logic here under template instantiation
is incorrect;  we need to preserve the fact that an expression was
unevaluated.  Of course, template instantiation in general is fishy
here because we have no way of delaying semantic analysis in the
MC parser.  It's all just fishy.

I've also fixed the serialization of MS asm statements.

This commit depends on an LLVM commit.

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@180976 91177308-0d34-0410-b5e6-96231b3b80d8

7 files changed, 105 insertions, 40 deletions

diff --git a/include/clang/AST/Stmt.h b/include/clang/AST/Stmt.h
index 1e5892fcf7..6e5fae4f3c 100644
--- a/include/clang/AST/Stmt.h
+++ b/include/clang/AST/Stmt.h
@@ -1387,7 +1387,6 @@ protected:
   unsigned NumInputs;
   unsigned NumClobbers;
 
-  IdentifierInfo **Names;
   Stmt **Exprs;
 
   AsmStmt(StmtClass SC, SourceLocation asmloc, bool issimple, bool isvolatile,
@@ -1395,10 +1394,12 @@ protected:
     Stmt (SC), AsmLoc(asmloc), IsSimple(issimple), IsVolatile(isvolatile),
     NumOutputs(numoutputs), NumInputs(numinputs), NumClobbers(numclobbers) { }
 
+  friend class ASTStmtReader;
+
 public:
   /// \brief Build an empty inline-assembly statement.
   explicit AsmStmt(StmtClass SC, EmptyShell Empty) :
-    Stmt(SC, Empty), Names(0), Exprs(0) { }
+    Stmt(SC, Empty), Exprs(0) { }
 
   SourceLocation getAsmLoc() const { return AsmLoc; }
   void setAsmLoc(SourceLocation L) { AsmLoc = L; }
@@ -1421,17 +1422,6 @@ public:
 
   unsigned getNumOutputs() const { return NumOutputs; }
 
-  IdentifierInfo *getOutputIdentifier(unsigned i) const {
-    return Names[i];
-  }
-
-  StringRef getOutputName(unsigned i) const {
-    if (IdentifierInfo *II = getOutputIdentifier(i))
-      return II->getName();
-
-    return StringRef();
-  }
-
   /// getOutputConstraint - Return the constraint string for the specified
   /// output operand.  All output constraints are known to be non-empty (either
   /// '=' or '+').
@@ -1454,17 +1444,6 @@ public:
 
   unsigned getNumInputs() const { return NumInputs; }
 
-  IdentifierInfo *getInputIdentifier(unsigned i) const {
-    return Names[i + NumOutputs];
-  }
-
-  StringRef getInputName(unsigned i) const {
-    if (IdentifierInfo *II = getInputIdentifier(i))
-      return II->getName();
-
-    return StringRef();
-  }
-
   /// getInputConstraint - Return the specified input constraint.  Unlike output
   /// constraints, these can be empty.
   StringRef getInputConstraint(unsigned i) const;
@@ -1535,6 +1514,9 @@ class GCCAsmStmt : public AsmStmt {
   // FIXME: If we wanted to, we could allocate all of these in one big array.
   StringLiteral **Constraints;
   StringLiteral **Clobbers;
+  IdentifierInfo **Names;
+
+  friend class ASTStmtReader;
 
 public:
   GCCAsmStmt(ASTContext &C, SourceLocation asmloc, bool issimple,
@@ -1545,7 +1527,7 @@ public:
 
   /// \brief Build an empty inline-assembly statement.
   explicit GCCAsmStmt(EmptyShell Empty) : AsmStmt(GCCAsmStmtClass, Empty),
-    Constraints(0), Clobbers(0) { }
+    Constraints(0), Clobbers(0), Names(0) { }
 
   SourceLocation getRParenLoc() const { return RParenLoc; }
   void setRParenLoc(SourceLocation L) { RParenLoc = L; }
@@ -1610,6 +1592,17 @@ public:
 
   //===--- Output operands ---===//
 
+  IdentifierInfo *getOutputIdentifier(unsigned i) const {
+    return Names[i];
+  }
+
+  StringRef getOutputName(unsigned i) const {
+    if (IdentifierInfo *II = getOutputIdentifier(i))
+      return II->getName();
+
+    return StringRef();
+  }
+
   StringRef getOutputConstraint(unsigned i) const;
 
   const StringLiteral *getOutputConstraintLiteral(unsigned i) const {
@@ -1627,6 +1620,17 @@ public:
 
   //===--- Input operands ---===//
 
+  IdentifierInfo *getInputIdentifier(unsigned i) const {
+    return Names[i + NumOutputs];
+  }
+
+  StringRef getInputName(unsigned i) const {
+    if (IdentifierInfo *II = getInputIdentifier(i))
+      return II->getName();
+
+    return StringRef();
+  }
+
   StringRef getInputConstraint(unsigned i) const;
 
   const StringLiteral *getInputConstraintLiteral(unsigned i) const {
@@ -1643,6 +1647,7 @@ public:
     return const_cast<GCCAsmStmt*>(this)->getInputExpr(i);
   }
 
+private:
   void setOutputsAndInputsAndClobbers(ASTContext &C,
                                       IdentifierInfo **Names,
                                       StringLiteral **Constraints,
@@ -1651,6 +1656,7 @@ public:
                                       unsigned NumInputs,
                                       StringLiteral **Clobbers,
                                       unsigned NumClobbers);
+public:
 
   //===--- Other ---===//
 
@@ -1677,7 +1683,7 @@ public:
 ///
 class MSAsmStmt : public AsmStmt {
   SourceLocation LBraceLoc, EndLoc;
-  std::string AsmStr;
+  StringRef AsmStr;
 
   unsigned NumAsmToks;
 
@@ -1685,11 +1691,13 @@ class MSAsmStmt : public AsmStmt {
   StringRef *Constraints;
   StringRef *Clobbers;
 
+  friend class ASTStmtReader;
+
 public:
   MSAsmStmt(ASTContext &C, SourceLocation asmloc, SourceLocation lbraceloc,
             bool issimple, bool isvolatile, ArrayRef<Token> asmtoks,
             unsigned numoutputs, unsigned numinputs,
-            ArrayRef<IdentifierInfo*> names, ArrayRef<StringRef> constraints,
+            ArrayRef<StringRef> constraints,
             ArrayRef<Expr*> exprs, StringRef asmstr,
             ArrayRef<StringRef> clobbers, SourceLocation endloc);
 
@@ -1708,10 +1716,7 @@ public:
   Token *getAsmToks() { return AsmToks; }
 
   //===--- Asm String Analysis ---===//
-
-  const std::string *getAsmString() const { return &AsmStr; }
-  std::string *getAsmString() { return &AsmStr; }
-  void setAsmString(StringRef &E) { AsmStr = E.str(); }
+  StringRef getAsmString() const { return AsmStr; }
 
   /// Assemble final IR asm string.
   std::string generateAsmString(ASTContext &C) const;
@@ -1719,6 +1724,7 @@ public:
   //===--- Output operands ---===//
 
   StringRef getOutputConstraint(unsigned i) const {
+    assert(i < NumOutputs);
     return Constraints[i];
   }
 
@@ -1731,6 +1737,7 @@ public:
   //===--- Input operands ---===//
 
   StringRef getInputConstraint(unsigned i) const {
+    assert(i < NumInputs);
     return Constraints[i + NumOutputs];
   }
 
@@ -1743,7 +1750,27 @@ public:
 
   //===--- Other ---===//
 
-  StringRef getClobber(unsigned i) const { return Clobbers[i]; }
+  ArrayRef<StringRef> getAllConstraints() const {
+    return ArrayRef<StringRef>(Constraints, NumInputs + NumOutputs);
+  }
+  ArrayRef<StringRef> getClobbers() const {
+    return ArrayRef<StringRef>(Clobbers, NumClobbers);
+  }
+  ArrayRef<Expr*> getAllExprs() const {
+    return ArrayRef<Expr*>(reinterpret_cast<Expr**>(Exprs),
+                           NumInputs + NumOutputs);
+  }
+
+  StringRef getClobber(unsigned i) const { return getClobbers()[i]; }
+
+private:
+  void initialize(ASTContext &C,
+                  StringRef AsmString,
+                  ArrayRef<Token> AsmToks,
+                  ArrayRef<StringRef> Constraints,
+                  ArrayRef<Expr*> Exprs,
+                  ArrayRef<StringRef> Clobbers);
+public:
 
   SourceLocation getLocStart() const LLVM_READONLY { return AsmLoc; }
   SourceLocation getLocEnd() const LLVM_READONLY { return EndLoc; }
diff --git a/include/clang/Basic/DiagnosticParseKinds.td b/include/clang/Basic/DiagnosticParseKinds.td
index 08abef120a..f50dceca57 100644
--- a/include/clang/Basic/DiagnosticParseKinds.td
+++ b/include/clang/Basic/DiagnosticParseKinds.td
@@ -18,6 +18,13 @@ def w_asm_qualifier_ignored : Warning<"ignored %0 qualifier on asm">,
 def warn_file_asm_volatile : Warning<
   "meaningless 'volatile' on asm outside function">, CatInlineAsm;
 
+let CategoryName = "Inline Assembly Issue" in {
+def err_asm_empty : Error<"__asm used with no assembly instructions">;
+def err_inline_ms_asm_parsing : Error<"%0">;
+def err_msasm_unsupported_arch : Error<
+  "Unsupported architecture '%0' for MS-style inline assembly">;
+}
+
 let CategoryName = "Parse Issue" in {
 
 def ext_empty_translation_unit : Extension<
diff --git a/include/clang/Basic/DiagnosticSemaKinds.td b/include/clang/Basic/DiagnosticSemaKinds.td
index fb2ffe8872..bfbbb91be9 100644
--- a/include/clang/Basic/DiagnosticSemaKinds.td
+++ b/include/clang/Basic/DiagnosticSemaKinds.td
@@ -5408,16 +5408,13 @@ let CategoryName = "Inline Assembly Issue" in {
   def err_asm_tying_incompatible_types : Error<
     "unsupported inline asm: input with type "
     "%diff{$ matching output with type $|}0,1">;
+  def err_asm_incomplete_type : Error<"asm operand has incomplete type %0">;
   def err_asm_unknown_register_name : Error<"unknown register name '%0' in asm">;
-  def err_asm_empty : Error<"__asm used with no assembly instructions">;
   def err_asm_invalid_input_size : Error<
     "invalid input size for constraint '%0'">;
   def err_invalid_asm_cast_lvalue : Error<
     "invalid use of a cast in a inline asm context requiring an l-value: "
     "remove the cast or build with -fheinous-gnu-extensions">;
-  def err_inline_ms_asm_parsing : Error<"%0">;
-  def err_msasm_unsupported_arch : Error<
-    "Unsupported architecture '%0' for MS-style inline assembly">;
 
   def warn_asm_label_on_auto_decl : Warning<
     "ignored asm label '%0' on automatic variable">;
diff --git a/include/clang/Parse/Parser.h b/include/clang/Parse/Parser.h
index 44c213c5ef..a33d01d27b 100644
--- a/include/clang/Parse/Parser.h
+++ b/include/clang/Parse/Parser.h
@@ -1221,6 +1221,11 @@ public:
   // Expr that doesn't include commas.
   ExprResult ParseAssignmentExpression(TypeCastState isTypeCast = NotTypeCast);
 
+  ExprResult ParseMSAsmIdentifier(llvm::SmallVectorImpl<Token> &LineToks,
+                                  unsigned &NumLineToksConsumed,
+                                  void *Info,
+                                  bool IsUnevaluated);
+
 private:
   ExprResult ParseExpressionWithLeadingAt(SourceLocation AtLoc);
 
diff --git a/include/clang/Sema/Sema.h b/include/clang/Sema/Sema.h
index e5f2d448fd..9aee774d1f 100644
--- a/include/clang/Sema/Sema.h
+++ b/include/clang/Sema/Sema.h
@@ -600,6 +600,10 @@ public:
   /// have been declared.
   bool GlobalNewDeleteDeclared;
 
+  /// A flag to indicate that we're in a context that permits abstract
+  /// references to fields.  This is really a 
+  bool AllowAbstractFieldReference;
+
   /// \brief Describes how the expressions currently being parsed are
   /// evaluated at run-time, if at all.
   enum ExpressionEvaluationContext {
@@ -610,6 +614,11 @@ public:
     /// run time.
     Unevaluated,
 
+    /// \brief The current expression occurs within an unevaluated
+    /// operand that unconditionally permits abstract references to
+    /// fields, such as a SIZE operator in MS-style inline assembly.
+    UnevaluatedAbstract,
+
     /// \brief The current context is "potentially evaluated" in C++11 terms,
     /// but the expression is evaluated at compile-time (like the values of
     /// cases in a switch statment).
@@ -689,6 +698,10 @@ public:
         LambdaMangle = new LambdaMangleContext;
       return *LambdaMangle;
     }
+
+    bool isUnevaluated() const {
+      return Context == Unevaluated || Context == UnevaluatedAbstract;
+    }
   };
 
   /// A stack of expression evaluation contexts.
@@ -2801,12 +2814,21 @@ public:
                              Expr *AsmString, MultiExprArg Clobbers,
                              SourceLocation RParenLoc);
 
-  NamedDecl *LookupInlineAsmIdentifier(StringRef &LineBuf, SourceLocation Loc,
-                                       InlineAsmIdentifierInfo &Info);
+  ExprResult LookupInlineAsmIdentifier(CXXScopeSpec &SS,
+                                       SourceLocation TemplateKWLoc,
+                                       UnqualifiedId &Id,
+                                       InlineAsmIdentifierInfo &Info,
+                                       bool IsUnevaluatedContext);
   bool LookupInlineAsmField(StringRef Base, StringRef Member,
                             unsigned &Offset, SourceLocation AsmLoc);
   StmtResult ActOnMSAsmStmt(SourceLocation AsmLoc, SourceLocation LBraceLoc,
-                            ArrayRef<Token> AsmToks, SourceLocation EndLoc);
+                            ArrayRef<Token> AsmToks,
+                            StringRef AsmString,
+                            unsigned NumOutputs, unsigned NumInputs,
+                            ArrayRef<StringRef> Constraints,
+                            ArrayRef<StringRef> Clobbers,
+                            ArrayRef<Expr*> Exprs,
+                            SourceLocation EndLoc);
 
   VarDecl *BuildObjCExceptionDecl(TypeSourceInfo *TInfo, QualType ExceptionType,
                                   SourceLocation StartLoc,
@@ -5998,7 +6020,7 @@ public:
   bool isUnevaluatedContext() const {
     assert(!ExprEvalContexts.empty() &&
            "Must be in an expression evaluation context");
-    return ExprEvalContexts.back().Context == Sema::Unevaluated;
+    return ExprEvalContexts.back().isUnevaluated();
   }
 
   /// \brief RAII class used to determine whether SFINAE has
diff --git a/include/clang/Serialization/ASTReader.h b/include/clang/Serialization/ASTReader.h
index 0aa649a84d..9c19eda1ff 100644
--- a/include/clang/Serialization/ASTReader.h
+++ b/include/clang/Serialization/ASTReader.h
@@ -1802,6 +1802,9 @@ public:
   /// \brief Reads a sub-expression operand during statement reading.
   Expr *ReadSubExpr();
 
+  /// \brief Reads a token out of a record.
+  Token ReadToken(ModuleFile &M, const RecordData &Record, unsigned &Idx);
+
   /// \brief Reads the macro record located at the given offset.
   MacroInfo *ReadMacroRecord(ModuleFile &F, uint64_t Offset);
 
diff --git a/include/clang/Serialization/ASTWriter.h b/include/clang/Serialization/ASTWriter.h
index 2938dc76de..8ac8fde884 100644
--- a/include/clang/Serialization/ASTWriter.h
+++ b/include/clang/Serialization/ASTWriter.h
@@ -63,6 +63,7 @@ class Sema;
 class SourceManager;
 class SwitchCase;
 class TargetInfo;
+class Token;
 class VersionTuple;
 class ASTUnresolvedSet;
 
@@ -498,6 +499,9 @@ public:
                 Module *WritingModule, StringRef isysroot,
                 bool hasErrors = false);
 
+  /// \brief Emit a token.
+  void AddToken(const Token &Tok, RecordDataImpl &Record);
+
   /// \brief Emit a source location.
   void AddSourceLocation(SourceLocation Loc, RecordDataImpl &Record);