[LLVMSymbolize] Move ModuleInfo into a separate class (SymbolizableModule).

Summary:
This is mostly NFC. It is a first step in cleaning up LLVMSymbolize
library. It removes "ModuleInfo" class which bundles together ObjectFile
and its debug info context in favor of:
  * abstract SymbolizableModule in public headers;
  * SymbolizableObjectFile subclass in implementation.

Additionally, SymbolizableObjectFile is now created via factory, so we
can properly detect object parsing error at this stage instead of keeping
the broken half-parsed object. As a next step, we would be able to
propagate the error all the way back to the library user.

Further improvements might include:
  * factoring out the logic of finding appropriate file with debug info
    for a given object file, and caching all parsed object files into a
    separate class [A].
  * factoring out DILineInfo rendering [B].
This would make what is now a heavyweight "LLVMSymbolizer" a relatively
straightforward class, that calls into [A] to turn filepath into a
SymbolizableModule, delegates actual symbolization to concrete SymbolizableModule
implementation, and lets [C] render the result.

Reviewers: dblaikie, echristo, rafael

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D14099

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@251662 91177308-0d34-0410-b5e6-96231b3b80d8

Author: vonosmas

include/llvm/DebugInfo/Symbolize/SymbolizableModule.h

@@ -0,0 +1,54 @@
+//===-- SymbolizableModule.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 declares the SymbolizableModule interface.
+//
+//===----------------------------------------------------------------------===//
+#ifndef LLVM_DEBUGINFO_SYMBOLIZE_SYMBOLIZABLEMODULE_H
+#define LLVM_DEBUGINFO_SYMBOLIZE_SYMBOLIZABLEMODULE_H
+
+#include "llvm/DebugInfo/DIContext.h"
+#include <memory>
+#include <string>
+
+namespace llvm {
+namespace object {
+class ObjectFile;
+}
+}
+
+namespace llvm {
+namespace symbolize {
+
+using FunctionNameKind = DILineInfoSpecifier::FunctionNameKind;
+
+class SymbolizableModule {
+public:
+  virtual ~SymbolizableModule() {}
+  virtual DILineInfo symbolizeCode(uint64_t ModuleOffset,
+                                   FunctionNameKind FNKind,
+                                   bool UseSymbolTable) const = 0;
+  virtual DIInliningInfo symbolizeInlinedCode(uint64_t ModuleOffset,
+                                              FunctionNameKind FNKind,
+                                              bool UseSymbolTable) const = 0;
+  virtual bool symbolizeData(uint64_t ModuleOffset, std::string &Name,
+                             uint64_t &Start, uint64_t &Size) const = 0;
+
+  // Return true if this is a 32-bit x86 PE COFF module.
+  virtual bool isWin32Module() const = 0;
+
+  // Returns the preferred base of the module, i.e. where the loader would place
+  // it in memory assuming there were no conflicts.
+  virtual uint64_t getModulePreferredBase() const = 0;
+};
+
+}  // namespace symbolize
+}  // namespace llvm
+
+#endif  // LLVM_DEBUGINFO_SYMBOLIZE_SYMBOLIZABLEMODULE_H

include/llvm/DebugInfo/Symbolize/Symbolize.h

@@ -15,9 +15,9 @@
 
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/DebugInfo/DIContext.h"
+#include "llvm/DebugInfo/Symbolize/SymbolizableModule.h"
 #include "llvm/Object/MachOUniversal.h"
 #include "llvm/Object/ObjectFile.h"
-#include "llvm/Support/DataExtractor.h"
 #include "llvm/Support/MemoryBuffer.h"
 #include <map>
 #include <memory>
@@ -28,7 +28,6 @@ namespace symbolize {
 
 using namespace object;
 using FunctionNameKind = DILineInfoSpecifier::FunctionNameKind;
-class ModuleInfo;
 
 class LLVMSymbolizer {
 public:
@@ -61,13 +60,15 @@ class LLVMSymbolizer {
   std::string
   symbolizeData(const std::string &ModuleName, uint64_t ModuleOffset);
   void flush();
-  static std::string DemangleName(const std::string &Name, ModuleInfo *ModInfo);
+  static std::string DemangleName(const std::string &Name,
+                                  const SymbolizableModule *ModInfo);
 
 private:
   typedef std::pair<ObjectFile*, ObjectFile*> ObjectPair;
 
-  ModuleInfo *getOrCreateModuleInfo(const std::string &ModuleName);
-  ObjectFile *lookUpDsymFile(const std::string &Path, const MachOObjectFile *ExeObj,
+  SymbolizableModule *getOrCreateModuleInfo(const std::string &ModuleName);
+  ObjectFile *lookUpDsymFile(const std::string &Path,
+                             const MachOObjectFile *ExeObj,
                              const std::string &ArchName);
 
   /// \brief Returns pair of pointers to object and debug object.
@@ -77,7 +78,8 @@ class LLVMSymbolizer {
   /// universal binary (or the binary itself if it is an object file).
   ObjectFile *getObjectFileFromBinary(Binary *Bin, const std::string &ArchName);
 
-  std::string printDILineInfo(DILineInfo LineInfo, ModuleInfo *ModInfo) const;
+  std::string printDILineInfo(DILineInfo LineInfo,
+                              const SymbolizableModule *ModInfo) const;
 
   // Owns all the parsed binaries and object files.
   SmallVector<std::unique_ptr<Binary>, 4> ParsedBinariesAndObjects;
@@ -90,7 +92,7 @@ class LLVMSymbolizer {
     MemoryBuffers.push_back(std::move(MemBuf));
   }
 
-  std::map<std::string, std::unique_ptr<ModuleInfo>> Modules;
+  std::map<std::string, std::unique_ptr<SymbolizableModule>> Modules;
   std::map<std::pair<MachOUniversalBinary *, std::string>, ObjectFile *>
       ObjectFileForArch;
   std::map<std::pair<std::string, std::string>, ObjectPair>
@@ -100,51 +102,6 @@ class LLVMSymbolizer {
   static const char kBadString[];
 };
 
-class ModuleInfo {
-public:
-  ModuleInfo(ObjectFile *Obj, std::unique_ptr<DIContext> DICtx);
-
-  DILineInfo symbolizeCode(uint64_t ModuleOffset, FunctionNameKind FNKind,
-                           bool UseSymbolTable) const;
-  DIInliningInfo symbolizeInlinedCode(uint64_t ModuleOffset,
-                                      FunctionNameKind FNKind,
-                                      bool UseSymbolTable) const;
-  bool symbolizeData(uint64_t ModuleOffset, std::string &Name, uint64_t &Start,
-                     uint64_t &Size) const;
-
-  // Return true if this is a 32-bit x86 PE COFF module.
-  bool isWin32Module() const;
-
-  // Returns the preferred base of the module, i.e. where the loader would place
-  // it in memory assuming there were no conflicts.
-  uint64_t getModulePreferredBase() const;
-
-private:
-  bool getNameFromSymbolTable(SymbolRef::Type Type, uint64_t Address,
-                              std::string &Name, uint64_t &Addr,
-                              uint64_t &Size) const;
-  // For big-endian PowerPC64 ELF, OpdAddress is the address of the .opd
-  // (function descriptor) section and OpdExtractor refers to its contents.
-  void addSymbol(const SymbolRef &Symbol, uint64_t SymbolSize,
-                 DataExtractor *OpdExtractor = nullptr,
-                 uint64_t OpdAddress = 0);
-  void addCoffExportSymbols(const COFFObjectFile *CoffObj);
-  ObjectFile *Module;
-  std::unique_ptr<DIContext> DebugInfoContext;
-
-  struct SymbolDesc {
-    uint64_t Addr;
-    // If size is 0, assume that symbol occupies the whole memory range up to
-    // the following symbol.
-    uint64_t Size;
-    friend bool operator<(const SymbolDesc &s1, const SymbolDesc &s2) {
-      return s1.Addr < s2.Addr;
-    }
-  };
-  std::map<SymbolDesc, StringRef> Functions;
-  std::map<SymbolDesc, StringRef> Objects;
-};
-
 } // namespace symbolize
 } // namespace llvm
 

lib/DebugInfo/Symbolize/CMakeLists.txt

@@ -1,4 +1,5 @@
 add_llvm_library(LLVMSymbolize
+  SymbolizableObjectFile.cpp
   Symbolize.cpp
 
   ADDITIONAL_HEADER_DIRS