1    :  // Copyright 2015 Google Inc. All Rights Reserved.
   2    :  //
   3    :  // Licensed under the Apache License, Version 2.0 (the "License");
   4    :  // you may not use this file except in compliance with the License.
   5    :  // You may obtain a copy of the License at
   6    :  //
   7    :  //     http://www.apache.org/licenses/LICENSE-2.0
   8    :  //
   9    :  // Unless required by applicable law or agreed to in writing, software
  10    :  // distributed under the License is distributed on an "AS IS" BASIS,
  11    :  // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  12    :  // See the License for the specific language governing permissions and
  13    :  // limitations under the License.
  14    :  
  15    :  #ifndef SYZYGY_REFINERY_TYPES_PDB_CRAWLER_H_
  16    :  #define SYZYGY_REFINERY_TYPES_PDB_CRAWLER_H_
  17    :  
  18    :  #include <windows.h>  // NOLINT
  19    :  #include <dbghelp.h>
  20    :  #include <memory>
  21    :  #include <vector>
  22    :  
  23    :  #include "base/containers/hash_tables.h"
  24    :  #include "base/files/file_path.h"
  25    :  #include "syzygy/common/binary_stream.h"
  26    :  #include "syzygy/pdb/pdb_dbi_stream.h"
  27    :  #include "syzygy/pdb/pdb_stream.h"
  28    :  #include "syzygy/refinery/core/address.h"
  29    :  
  30  m :  namespace refinery {
  31    :  // Forward declaration.
  32  m :  class TypeRepository;
  33    :  
  34    :  // A worker class to scrape types from PDB symbols using type info enumerator.
  35    :  // TODO(manzagop): ensure duplicate types are properly dealt with. The current
  36    :  // implementation generates equivalent types due to:
  37    :  // - basic types that are mapped to the same type (eg T_LONG and T_INT4)
  38    :  // - UDTs that are identical up to extra LF_NESTTYPE (which do not make it to
  39    :  //   our type representation)
  40    :  // - pointers: Foo* and Foo*const will lead to the creation of 2 Foo* types.
  41  m :  class PdbCrawler {
  42  m :   public:
  43  m :    PdbCrawler();
  44  m :    ~PdbCrawler();
  45    :  
  46    :    // Initializes this crawler for the file at @p path.
  47    :    // @param path the image file whose symbols to crawl for types.
  48  m :    bool InitializeForFile(const base::FilePath& path);
  49    :  
  50    :    // Retrieves all @p types associated with the file this instance
  51    :    // is initialized to.
  52    :    // @param types on success contains zero or more types.
  53    :    // @returns true on success, false on failure.
  54  m :    bool GetTypes(TypeRepository* types);
  55    :  
  56    :    // Retrieves the relative virtual addresses of all virtual function tables.
  57    :    // @param vftable_rvas on success contains zero or more relative addresses.
  58    :    // @returns true on success, false on failure.
  59  m :    bool GetVFTableRVAs(base::hash_set<RelativeAddress>* vftable_rvas);
  60    :  
  61  m :   private:
  62  m :    bool GetVFTableRVAForSymbol(base::hash_set<RelativeAddress>* vftable_rvas,
  63  m :                                uint16_t symbol_length,
  64  m :                                uint16_t symbol_type,
  65  m :                                common::BinaryStreamReader* symbol_reader);
  66    :  
  67    :    // Pointers to the PDB type and symbol streams.
  68  m :    scoped_refptr<pdb::PdbStream> tpi_stream_;
  69  m :    scoped_refptr<pdb::PdbStream> sym_stream_;
  70    :  
  71    :    // The PE section headers extracted from the pdb.
  72    :    // Note: we use these as it seems the DbiStream's section map does not contain
  73    :    // information about section offsets (rva_offset is 0).
  74  m :    std::vector<IMAGE_SECTION_HEADER> section_headers_;
  75    :  
  76    :    // OMAP data to map from original space to transformed space. Empty if there
  77    :    // is no OMAP data.
  78  m :    std::vector<OMAP> omap_from_;
  79  m :  };
  80    :  
  81  m :  }  // namespace refinery
  82    :  
  83    :  #endif  // SYZYGY_REFINERY_TYPES_PDB_CRAWLER_H_