path: root/src/common/mac/macho_id.cc

// Copyright (c) 2006, Google Inc.
// All rights reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
//
//     * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
//     * Redistributions in binary form must reproduce the above
// copyright notice, this list of conditions and the following disclaimer
// in the documentation and/or other materials provided with the
// distribution.
//     * Neither the name of Google Inc. nor the names of its
// contributors may be used to endorse or promote products derived from
// this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// macho_id.cc: Functions to gather identifying information from a macho file
//
// See macho_id.h for documentation
//
// Author: Dan Waylonis

#include <fcntl.h>
#include <mach-o/loader.h>
#include <mach-o/swap.h>
#include <openssl/md5.h>
#include <openssl/sha.h>
#include <stdio.h>
#include <string.h>
#include <sys/time.h>
#include <sys/types.h>
#include <unistd.h>

#include "common/mac/macho_id.h"
#include "common/mac/macho_walker.h"

namespace MacFileUtilities {

MachoID::MachoID(const char *path) {
  strlcpy(path_, path, sizeof(path_));
  file_ = open(path, O_RDONLY);
}

MachoID::~MachoID() {
  if (file_ != -1)
    close(file_);
}

// The CRC info is from http://en.wikipedia.org/wiki/Adler-32
// With optimizations from http://www.zlib.net/

// The largest prime smaller than 65536
#define MOD_ADLER 65521
// MAX_BLOCK is the largest n such that 255n(n+1)/2 + (n+1)(MAX_BLOCK-1) <= 2^32-1
#define MAX_BLOCK 5552

void MachoID::UpdateCRC(unsigned char *bytes, size_t size) {
// Unrolled loops for summing
#define DO1(buf,i)  {sum1 += (buf)[i]; sum2 += sum1;}
#define DO2(buf,i)  DO1(buf,i); DO1(buf,i+1);
#define DO4(buf,i)  DO2(buf,i); DO2(buf,i+2);
#define DO8(buf,i)  DO4(buf,i); DO4(buf,i+4);
#define DO16(buf)   DO8(buf,0); DO8(buf,8);
  // Split up the crc
  uint32_t sum1 = crc_ & 0xFFFF;
  uint32_t sum2 = (crc_ >> 16) & 0xFFFF;

  // Do large blocks
  while (size >= MAX_BLOCK) {
    size -= MAX_BLOCK;
    int block_count = MAX_BLOCK / 16;
    do {
      DO16(bytes);
      bytes += 16;
    } while (--block_count);
    sum1 %= MOD_ADLER;
    sum2 %= MOD_ADLER;
  }

  // Do remaining bytes
  if (size) {
    while (size >= 16) {
      size -= 16;
      DO16(bytes);
      bytes += 16;
    }
    while (size--) {
      sum1 += *bytes++;
      sum2 += sum1;
    }
    sum1 %= MOD_ADLER;
    sum2 %= MOD_ADLER;
    crc_ = (sum2 << 16) | sum1;
  }
}

void MachoID::UpdateMD5(unsigned char *bytes, size_t size) {
  MD5_Update(&md5_context_, bytes, size);
}

void MachoID::UpdateSHA1(unsigned char *bytes, size_t size) {
  SHA_Update(&sha1_context_, bytes, size);
}

void MachoID::Update(unsigned char *bytes, size_t size) {
  if (update_function_)
    (this->*update_function_)(bytes, size);
}

bool MachoID::UUIDCommand(int cpu_type, unsigned char bytes[16]) {
  struct uuid_command uuid_cmd;
  MachoWalker walker(path_, UUIDWalkerCB, &uuid_cmd);

  uuid_cmd.cmd = 0;
  if (!walker.WalkHeader(cpu_type))
    return false;

  // If we found the command, we'll have initialized the uuid_command
  // structure
  if (uuid_cmd.cmd == LC_UUID) {
    memcpy(bytes, uuid_cmd.uuid, sizeof(uuid_cmd.uuid));
    return true;
  }

  return false;
}

bool MachoID::IDCommand(int cpu_type, unsigned char identifier[16]) {
  struct dylib_command dylib_cmd;
  MachoWalker walker(path_, IDWalkerCB, &dylib_cmd);

  dylib_cmd.cmd = 0;
  if (!walker.WalkHeader(cpu_type))
    return false;

  // If we found the command, we'll have initialized the dylib_command
  // structure
  if (dylib_cmd.cmd == LC_ID_DYLIB) {
    // Take the timestamp, version, and compatability version bytes to form
    // the first 12 bytes, pad the rest with zeros
    identifier[0] = (dylib_cmd.dylib.timestamp >> 24) & 0xFF;
    identifier[1] = (dylib_cmd.dylib.timestamp >> 16) & 0xFF;
    identifier[2] = (dylib_cmd.dylib.timestamp >> 8) & 0xFF;
    identifier[3] = dylib_cmd.dylib.timestamp & 0xFF;
    identifier[4] = (dylib_cmd.dylib.current_version >> 24) & 0xFF;
    identifier[5] = (dylib_cmd.dylib.current_version >> 16) & 0xFF;
    identifier[6] = (dylib_cmd.dylib.current_version >> 8) & 0xFF;
    identifier[7] = dylib_cmd.dylib.current_version & 0xFF;
    identifier[8] = (dylib_cmd.dylib.compatibility_version >> 24) & 0xFF;
    identifier[9] = (dylib_cmd.dylib.compatibility_version >> 16) & 0xFF;
    identifier[10] = (dylib_cmd.dylib.compatibility_version >> 8) & 0xFF;
    identifier[11] = dylib_cmd.dylib.compatibility_version & 0xFF;
    identifier[12] = identifier[13] = identifier[14] = identifier[15] = 0;

    return true;
  }

  return false;
}

uint32_t MachoID::Adler32(int cpu_type) {
  MachoWalker walker(path_, WalkerCB, this);
  update_function_ = &MachoID::UpdateCRC;
  crc_ = 0;

  if (!walker.WalkHeader(cpu_type))
    return 0;

  return crc_;
}

bool MachoID::MD5(int cpu_type, unsigned char identifier[16]) {
  MachoWalker walker(path_, WalkerCB, this);
  update_function_ = &MachoID::UpdateMD5;

  if (MD5_Init(&md5_context_)) {
    if (!walker.WalkHeader(cpu_type))
      return false;

    MD5_Final(identifier, &md5_context_);
    return true;
  }

  return false;
}

bool MachoID::SHA1(int cpu_type, unsigned char identifier[16]) {
  MachoWalker walker(path_, WalkerCB, this);
  update_function_ = &MachoID::UpdateSHA1;

  if (SHA_Init(&sha1_context_)) {
    if (!walker.WalkHeader(cpu_type))
      return false;

    SHA_Final(identifier, &sha1_context_);
    return true;
  }

  return false;
}

// static
bool MachoID::WalkerCB(MachoWalker *walker, load_command *cmd, off_t offset,
                       bool swap, void *context) {
  MachoID *macho_id = (MachoID *)context;
  off_t seg_offset = 0;
  size_t seg_size = 0;

  if (cmd->cmd == LC_SEGMENT) {
    struct segment_command seg;

    if (!walker->ReadBytes(&seg, sizeof(seg), offset))
      return false;

    if (swap)
      swap_segment_command(&seg, NXHostByteOrder());

    seg_offset = seg.fileoff;
    seg_size = seg.filesize;
  } else if (cmd->cmd == LC_SEGMENT_64) {
    struct segment_command_64 seg64;

    if (!walker->ReadBytes(&seg64, sizeof(seg64), offset))
      return false;

    if (swap)
      swap_segment_command_64(&seg64, NXHostByteOrder());

    seg_offset = seg64.fileoff;
    seg_size = seg64.filesize;
  }

  // If this was a non-zero segment, read the bytes, update the hash
  if (seg_size) {
    // Read 4k x 2 bytes at a time.  This is faster than just 4k bytes, but
    // doesn't seem to be an unreasonable size for the stack.
    unsigned char buffer[4096 * 2];
    size_t buffer_size;
    off_t file_offset = seg_offset;
    while (seg_size > 0) {
      if (seg_size > sizeof(buffer)) {
        buffer_size = sizeof(buffer);
        seg_size -= buffer_size;
      } else {
        buffer_size = seg_size;
        seg_size = 0;
      }

      if (!walker->ReadBytes(buffer, buffer_size, file_offset))
        return false;

      macho_id->Update(buffer, buffer_size);
      file_offset += buffer_size;
    }
  }

  // Continue processing
  return true;
}

// static
bool MachoID::UUIDWalkerCB(MachoWalker *walker, load_command *cmd, off_t offset,
                           bool swap, void *context) {
  if (cmd->cmd == LC_UUID) {
    struct uuid_command *uuid_cmd = (struct uuid_command *)context;

    if (!walker->ReadBytes(uuid_cmd, sizeof(struct uuid_command), offset))
      return false;

    if (swap)
      swap_uuid_command(uuid_cmd, NXHostByteOrder());

    return false;
  }

  // Continue processing
  return true;
}

// static
bool MachoID::IDWalkerCB(MachoWalker *walker, load_command *cmd, off_t offset,
                         bool swap, void *context) {
  if (cmd->cmd == LC_ID_DYLIB) {
    struct dylib_command *dylib_cmd = (struct dylib_command *)context;

    if (!walker->ReadBytes(dylib_cmd, sizeof(struct dylib_command), offset))
      return false;

    if (swap)
      swap_dylib_command(dylib_cmd, NXHostByteOrder());

    return false;
  }

  // Continue processing
  return true;
}

}  // namespace MacFileUtilities