NFC: Make the copies of the demangler byte-for-byte identical

With this patch, the copies of the files ItaniumDemangle.h,
StringView.h, and Utility.h are kept byte-for-byte in sync between
libcxxabi and llvm. All differences (namespaces, fallthrough, and
unreachable macros) are defined in each copies' DemanglerConfig.h.

This patch also adds a script to copy changes from libcxxabi
(cp-to-llvm.sh), and a README.txt explaining the situation.

Differential revision: https://reviews.llvm.org/D53538

llvm-svn: 351474

include/llvm/Demangle/DemangleConfig.h

@@ -1,14 +1,16 @@
-//===--- Compiler.h ---------------------------------------------*- C++ -*-===//
+//===--- DemangleConfig.h ---------------------------------------*- C++ -*-===//
 //
 //                     The LLVM Compiler Infrastructure
 //
 // This file is distributed under the University of Illinois Open Source
 // License. See LICENSE.TXT for details.
 //
+//===----------------------------------------------------------------------===//
 //
 // This file contains a variety of feature test macros copied from
 // include/llvm/Support/Compiler.h so that LLVMDemangle does not need to take
 // a dependency on LLVMSupport.
+//
 //===----------------------------------------------------------------------===//
 
 #ifndef LLVM_DEMANGLE_COMPILER_H
@@ -37,57 +39,60 @@
 #define __has_builtin(x) 0
 #endif
 
-#ifndef LLVM_GNUC_PREREQ
+#ifndef DEMANGLE_GNUC_PREREQ
 #if defined(__GNUC__) && defined(__GNUC_MINOR__) && defined(__GNUC_PATCHLEVEL__)
-#define LLVM_GNUC_PREREQ(maj, min, patch)                                      \
+#define DEMANGLE_GNUC_PREREQ(maj, min, patch)                           \
   ((__GNUC__ << 20) + (__GNUC_MINOR__ << 10) + __GNUC_PATCHLEVEL__ >=          \
    ((maj) << 20) + ((min) << 10) + (patch))
 #elif defined(__GNUC__) && defined(__GNUC_MINOR__)
-#define LLVM_GNUC_PREREQ(maj, min, patch)                                      \
+#define DEMANGLE_GNUC_PREREQ(maj, min, patch)                           \
   ((__GNUC__ << 20) + (__GNUC_MINOR__ << 10) >= ((maj) << 20) + ((min) << 10))
 #else
-#define LLVM_GNUC_PREREQ(maj, min, patch) 0
+#define DEMANGLE_GNUC_PREREQ(maj, min, patch) 0
 #endif
 #endif
 
-#if __has_attribute(used) || LLVM_GNUC_PREREQ(3, 1, 0)
-#define LLVM_ATTRIBUTE_USED __attribute__((__used__))
+#if __has_attribute(used) || DEMANGLE_GNUC_PREREQ(3, 1, 0)
+#define DEMANGLE_ATTRIBUTE_USED __attribute__((__used__))
 #else
-#define LLVM_ATTRIBUTE_USED
+#define DEMANGLE_ATTRIBUTE_USED
 #endif
 
-#if __has_builtin(__builtin_unreachable) || LLVM_GNUC_PREREQ(4, 5, 0)
-#define LLVM_BUILTIN_UNREACHABLE __builtin_unreachable()
+#if __has_builtin(__builtin_unreachable) || DEMANGLE_GNUC_PREREQ(4, 5, 0)
+#define DEMANGLE_UNREACHABLE __builtin_unreachable()
 #elif defined(_MSC_VER)
-#define LLVM_BUILTIN_UNREACHABLE __assume(false)
+#define DEMANGLE_BUILTIN_UNREACHABLE __assume(false)
 #endif
 
-#if __has_attribute(noinline) || LLVM_GNUC_PREREQ(3, 4, 0)
-#define LLVM_ATTRIBUTE_NOINLINE __attribute__((noinline))
+#if __has_attribute(noinline) || DEMANGLE_GNUC_PREREQ(3, 4, 0)
+#define DEMANGLE_ATTRIBUTE_NOINLINE __attribute__((noinline))
 #elif defined(_MSC_VER)
-#define LLVM_ATTRIBUTE_NOINLINE __declspec(noinline)
+#define DEMANGLE_ATTRIBUTE_NOINLINE __declspec(noinline)
 #else
-#define LLVM_ATTRIBUTE_NOINLINE
+#define DEMANGLE_ATTRIBUTE_NOINLINE
 #endif
 
-#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
-#define LLVM_DUMP_METHOD LLVM_ATTRIBUTE_NOINLINE LLVM_ATTRIBUTE_USED
+#if !defined(NDEBUG)
+#define DEMANGLE_DUMP_METHOD DEMANGLE_ATTRIBUTE_NOINLINE DEMANGLE_ATTRIBUTE_USED
 #else
-#define LLVM_DUMP_METHOD LLVM_ATTRIBUTE_NOINLINE
+#define DEMANGLE_DUMP_METHOD DEMANGLE_ATTRIBUTE_NOINLINE
 #endif
 
 #if __cplusplus > 201402L && __has_cpp_attribute(fallthrough)
-#define LLVM_FALLTHROUGH [[fallthrough]]
+#define DEMANGLE_FALLTHROUGH [[fallthrough]]
 #elif __has_cpp_attribute(gnu::fallthrough)
-#define LLVM_FALLTHROUGH [[gnu::fallthrough]]
+#define DEMANGLE_FALLTHROUGH [[gnu::fallthrough]]
 #elif !__cplusplus
 // Workaround for llvm.org/PR23435, since clang 3.6 and below emit a spurious
 // error when __has_cpp_attribute is given a scoped attribute in C mode.
-#define LLVM_FALLTHROUGH
+#define DEMANGLE_FALLTHROUGH
 #elif __has_cpp_attribute(clang::fallthrough)
-#define LLVM_FALLTHROUGH [[clang::fallthrough]]
+#define DEMANGLE_FALLTHROUGH [[clang::fallthrough]]
 #else
-#define LLVM_FALLTHROUGH
+#define DEMANGLE_FALLTHROUGH
 #endif
 
+#define DEMANGLE_NAMESPACE_BEGIN namespace llvm { namespace itanium_demangle {
+#define DEMANGLE_NAMESPACE_END } }
+
 #endif

include/llvm/Demangle/ItaniumDemangle.h

@@ -6,18 +6,22 @@
 // Source Licenses. See LICENSE.TXT for details.
 //
 //===----------------------------------------------------------------------===//
+//
+// Generic itanium demangler library. This file has two byte-per-byte identical
+// copies in the source tree, one in libcxxabi, and the other in llvm.
+//
+//===----------------------------------------------------------------------===//
 
-#ifndef LLVM_DEMANGLE_ITANIUMDEMANGLE_H
-#define LLVM_DEMANGLE_ITANIUMDEMANGLE_H
+#ifndef DEMANGLE_ITANIUMDEMANGLE_H
+#define DEMANGLE_ITANIUMDEMANGLE_H
 
 // FIXME: (possibly) incomplete list of features that clang mangles that this
 // file does not yet support:
 //   - C++ modules TS
 
-#include "llvm/Demangle/Compiler.h"
-#include "llvm/Demangle/StringView.h"
-#include "llvm/Demangle/Utility.h"
-
+#include "DemangleConfig.h"
+#include "StringView.h"
+#include "Utility.h"
 #include <cassert>
 #include <cctype>
 #include <cstdio>
@@ -95,8 +99,8 @@
     X(BracedExpr) \
     X(BracedRangeExpr)
 
-namespace llvm {
-namespace itanium_demangle {
+DEMANGLE_NAMESPACE_BEGIN
+
 // Base class of all AST nodes. The AST is built by the parser, then is
 // traversed by the printLeft/Right functions to produce a demangled string.
 class Node {
@@ -194,7 +198,7 @@ public:
   virtual ~Node() = default;
 
 #ifndef NDEBUG
-  LLVM_DUMP_METHOD void dump() const;
+  DEMANGLE_DUMP_METHOD void dump() const;
 #endif
 };
 
@@ -1278,7 +1282,7 @@ public:
     case SpecialSubKind::iostream:
       return StringView("basic_iostream");
     }
-    LLVM_BUILTIN_UNREACHABLE;
+    DEMANGLE_UNREACHABLE;
   }
 
   void printLeft(OutputStream &S) const override {
@@ -1330,7 +1334,7 @@ public:
     case SpecialSubKind::iostream:
       return StringView("iostream");
     }
-    LLVM_BUILTIN_UNREACHABLE;
+    DEMANGLE_UNREACHABLE;
   }
 
   void printLeft(OutputStream &S) const override {
@@ -3467,7 +3471,7 @@ Node *AbstractManglingParser<Derived, Alloc>::parseType() {
       Result = getDerived().parseFunctionType();
       break;
     }
-    LLVM_FALLTHROUGH;
+    DEMANGLE_FALLTHROUGH;
   }
   case 'U': {
     Result = getDerived().parseQualifiedType();
@@ -3754,7 +3758,7 @@ Node *AbstractManglingParser<Derived, Alloc>::parseType() {
       // substitution table.
       return Sub;
     }
-    LLVM_FALLTHROUGH;
+    DEMANGLE_FALLTHROUGH;
   }
   //        ::= <class-enum-type>
   default: {
@@ -5178,7 +5182,6 @@ struct ManglingParser : AbstractManglingParser<ManglingParser<Alloc>, Alloc> {
                                Alloc>::AbstractManglingParser;
 };
 
-}  // namespace itanium_demangle
-}  // namespace llvm
+DEMANGLE_NAMESPACE_END
 
-#endif // LLVM_DEMANGLE_ITANIUMDEMANGLE_H
+#endif // DEMANGLE_ITANIUMDEMANGLE_H

include/llvm/Demangle/MicrosoftDemangle.h

@@ -10,7 +10,7 @@
 #ifndef LLVM_DEMANGLE_MICROSOFT_DEMANGLE_H
 #define LLVM_DEMANGLE_MICROSOFT_DEMANGLE_H
 
-#include "llvm/Demangle/Compiler.h"
+#include "llvm/Demangle/DemangleConfig.h"
 #include "llvm/Demangle/MicrosoftDemangleNodes.h"
 #include "llvm/Demangle/StringView.h"
 #include "llvm/Demangle/Utility.h"

include/llvm/Demangle/MicrosoftDemangleNodes.h

@@ -1,11 +1,31 @@
+//===- MicrosoftDemangleNodes.h ---------------------------------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file defines the AST nodes used in the MSVC demangler.
+//
+//===----------------------------------------------------------------------===//
+
 #ifndef LLVM_SUPPORT_MICROSOFTDEMANGLENODES_H
 #define LLVM_SUPPORT_MICROSOFTDEMANGLENODES_H
 
-#include "llvm/Demangle/Compiler.h"
+#include "llvm/Demangle/DemangleConfig.h"
 #include "llvm/Demangle/StringView.h"
 #include <array>
 
+namespace llvm {
+namespace itanium_demangle {
 class OutputStream;
+}
+}
+
+using llvm::itanium_demangle::OutputStream;
+using llvm::itanium_demangle::StringView;
 
 namespace llvm {
 namespace ms_demangle {
@@ -602,4 +622,4 @@ struct FunctionSymbolNode : public SymbolNode {
 } // namespace ms_demangle
 } // namespace llvm
 
-#endif
+#endif

include/llvm/Demangle/README.txt

@@ -0,0 +1,52 @@
+Itanium Name Demangler Library
+==============================
+
+Introduction
+------------
+
+This directory contains the generic itanium name demangler library. The main
+purpose of the library is to demangle C++ symbols, i.e. convert the string
+"_Z1fv" into "f()". You can also use the CRTP base ManglingParser to perform
+some simple analysis on the mangled name, or (in LLVM) use the opaque
+ItaniumPartialDemangler to query the demangled AST.
+
+Why are there multiple copies of the this library in the source tree?
+---------------------------------------------------------------------
+
+This directory is mirrored between libcxxabi/demangle and
+llvm/include/llvm/Demangle. The simple reason for this is that both projects
+need to demangle symbols, but neither can depend on each other. libcxxabi needs
+the demangler to implement __cxa_demangle, which is part of the itanium ABI
+spec. LLVM needs a copy for a bunch of places, but doesn't want to use the
+system's __cxa_demangle because it a) might not be available (i.e., on Windows),
+and b) probably isn't that up-to-date on the latest language features.
+
+The copy of the demangler in LLVM has some extra stuff that aren't needed in
+libcxxabi (ie, the MSVC demangler, ItaniumPartialDemangler), which depend on the
+shared generic components. Despite these differences, we want to keep the "core"
+generic demangling library identical between both copies to simplify development
+and testing.
+
+If you're working on the generic library, then do the work first in libcxxabi,
+then run the cp-to-llvm.sh script in src/demangle. This script takes as an
+argument the path to llvm, and re-copies the changes you made to libcxxabi over.
+Note that this script just blindly overwrites all changes to the generic library
+in llvm, so be careful.
+
+Because the core demangler needs to work in libcxxabi, everything needs to be
+declared in an anonymous namespace (see DEMANGLE_NAMESPACE_BEGIN), and you can't
+introduce any code that depends on the libcxx dylib.
+
+Hopefully, when LLVM becomes a monorepo, we can de-duplicate this code, and have
+both LLVM and libcxxabi depend on a shared demangler library.
+
+Testing
+-------
+
+The tests are split up between libcxxabi/test/{unit,}test_demangle.cpp, and
+llvm/unittest/Demangle. The llvm directory should only get tests for stuff not
+included in the core library. In the future though, we should probably move all
+the tests to LLVM.
+
+It is also a really good idea to run libFuzzer after non-trivial changes, see
+libcxxabi/fuzz/cxa_demangle_fuzzer.cpp and https://llvm.org/docs/LibFuzzer.html.

include/llvm/Demangle/StringView.h

@@ -5,18 +5,22 @@
 // This file is distributed under the University of Illinois Open Source
 // License. See LICENSE.TXT for details.
 //
+//===----------------------------------------------------------------------===//
+//
+// FIXME: Use std::string_view instead when we support C++17.
 //
-// This file contains a limited version of LLVM's StringView class.  It is
-// copied here so that LLVMDemangle need not take a dependency on LLVMSupport.
 //===----------------------------------------------------------------------===//
 
-#ifndef LLVM_DEMANGLE_STRINGVIEW_H
-#define LLVM_DEMANGLE_STRINGVIEW_H
+#ifndef DEMANGLE_STRINGVIEW_H
+#define DEMANGLE_STRINGVIEW_H
 
+#include "DemangleConfig.h"
 #include <algorithm>
 #include <cassert>
 #include <cstring>
 
+DEMANGLE_NAMESPACE_BEGIN
+
 class StringView {
   const char *First;
   const char *Last;
@@ -43,7 +47,7 @@ public:
     if (FindBegin < size()) {
       // Just forward to memchr, which is faster than a hand-rolled loop.
       if (const void *P = ::memchr(First + FindBegin, C, size() - FindBegin))
-        return static_cast<const char *>(P) - First;
+        return size_t(static_cast<const char *>(P) - First);
     }
     return npos;
   }
@@ -118,4 +122,6 @@ inline bool operator==(const StringView &LHS, const StringView &RHS) {
          std::equal(LHS.begin(), LHS.end(), RHS.begin());
 }
 
+DEMANGLE_NAMESPACE_END
+
 #endif

include/llvm/Demangle/Utility.h

@@ -5,21 +5,24 @@
 // This file is distributed under the University of Illinois Open Source
 // License. See LICENSE.TXT for details.
 //
+//===----------------------------------------------------------------------===//
+//
+// Provide some utility classes for use in the demangler(s).
 //
-// This file contains several utility classes used by the demangle library.
 //===----------------------------------------------------------------------===//
 
-#ifndef LLVM_DEMANGLE_UTILITY_H
-#define LLVM_DEMANGLE_UTILITY_H
+#ifndef DEMANGLE_UTILITY_H
+#define DEMANGLE_UTILITY_H
 
 #include "StringView.h"
-
 #include <cstdint>
 #include <cstdlib>
 #include <cstring>
 #include <iterator>
 #include <limits>
 
+DEMANGLE_NAMESPACE_BEGIN
+
 // Stream that AST nodes write their string representation into after the AST
 // has been parsed.
 class OutputStream {
@@ -184,4 +187,6 @@ inline bool initializeOutputStream(char *Buf, size_t *N, OutputStream &S,
   return true;
 }
 
+DEMANGLE_NAMESPACE_END
+
 #endif

lib/Demangle/MicrosoftDemangle.cpp

@@ -18,7 +18,7 @@
 #include "llvm/Demangle/Demangle.h"
 #include "llvm/Demangle/MicrosoftDemangleNodes.h"
 
-#include "llvm/Demangle/Compiler.h"
+#include "llvm/Demangle/DemangleConfig.h"
 #include "llvm/Demangle/StringView.h"
 #include "llvm/Demangle/Utility.h"
 
@@ -265,7 +265,7 @@ Demangler::demangleSpecialTableSymbolNode(StringView &MangledName,
     NI->Name = "`RTTI Complete Object Locator'";
     break;
   default:
-    LLVM_BUILTIN_UNREACHABLE;
+    DEMANGLE_UNREACHABLE;
   }
   QualifiedNameNode *QN = demangleNameScopeChain(MangledName, NI);
   SpecialTableSymbolNode *STSN = Arena.alloc<SpecialTableSymbolNode>();
@@ -632,7 +632,7 @@ translateIntrinsicFunctionCode(char CH, FunctionIdentifierCodeGroup Group) {
   case FunctionIdentifierCodeGroup::DoubleUnder:
     return DoubleUnder[Index];
   }
-  LLVM_BUILTIN_UNREACHABLE;
+  DEMANGLE_UNREACHABLE;
 }
 
 IdentifierNode *
@@ -1188,7 +1188,7 @@ Demangler::demangleStringLiteral(StringView &MangledName) {
   switch (MangledName.popFront()) {
   case '1':
     IsWcharT = true;
-    LLVM_FALLTHROUGH;
+    DEMANGLE_FALLTHROUGH;
   case '0':
     break;
   default:
@@ -1255,7 +1255,7 @@ Demangler::demangleStringLiteral(StringView &MangledName) {
       Result->Char = CharKind::Char32;
       break;
     default:
-      LLVM_BUILTIN_UNREACHABLE;
+      DEMANGLE_UNREACHABLE;
     }
     const unsigned NumChars = BytesDecoded / CharBytes;
     for (unsigned CharIndex = 0; CharIndex < NumChars; ++CharIndex) {
@@ -2083,15 +2083,15 @@ Demangler::demangleTemplateParameterList(StringView &MangledName) {
       case 'J':
         TPRN->ThunkOffsets[TPRN->ThunkOffsetCount++] =
             demangleSigned(MangledName);
-        LLVM_FALLTHROUGH;
+        DEMANGLE_FALLTHROUGH;
       case 'I':
         TPRN->ThunkOffsets[TPRN->ThunkOffsetCount++] =
             demangleSigned(MangledName);
-        LLVM_FALLTHROUGH;
+        DEMANGLE_FALLTHROUGH;
       case 'H':
         TPRN->ThunkOffsets[TPRN->ThunkOffsetCount++] =
             demangleSigned(MangledName);
-        LLVM_FALLTHROUGH;
+        DEMANGLE_FALLTHROUGH;
       case '1':
         break;
       default:
@@ -2117,13 +2117,13 @@ Demangler::demangleTemplateParameterList(StringView &MangledName) {
       case 'G':
         TPRN->ThunkOffsets[TPRN->ThunkOffsetCount++] =
             demangleSigned(MangledName);
-        LLVM_FALLTHROUGH;
+        DEMANGLE_FALLTHROUGH;
       case 'F':
         TPRN->ThunkOffsets[TPRN->ThunkOffsetCount++] =
             demangleSigned(MangledName);
         TPRN->ThunkOffsets[TPRN->ThunkOffsetCount++] =
             demangleSigned(MangledName);
-        LLVM_FALLTHROUGH;
+        DEMANGLE_FALLTHROUGH;
       case '0':
         break;
       default:

lib/Demangle/MicrosoftDemangleNodes.cpp

@@ -12,7 +12,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "llvm/Demangle/MicrosoftDemangleNodes.h"
-#include "llvm/Demangle/Compiler.h"
+#include "llvm/Demangle/DemangleConfig.h"
 #include "llvm/Demangle/Utility.h"
 #include <cctype>
 #include <string>

lib/Support/ItaniumManglingCanonicalizer.cpp

@@ -22,6 +22,7 @@ using namespace llvm;
 using llvm::itanium_demangle::ForwardTemplateReference;
 using llvm::itanium_demangle::Node;
 using llvm::itanium_demangle::NodeKind;
+using llvm::itanium_demangle::StringView;
 
 namespace {
 struct FoldingSetNodeIDBuilder {