llvm/tools/llvm-size/llvm-size.cpp

//===-- llvm-size.cpp - Print the size of each object section -------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This program is a utility that works like traditional Unix "size",
// that is, it prints out the size of each section, and the total size of all
// sections.
//
//===----------------------------------------------------------------------===//

#include "llvm/ADT/APInt.h"
#include "llvm/Object/Archive.h"
#include "llvm/Object/ObjectFile.h"
#include "llvm/Object/MachO.h"
#include "llvm/Object/MachOUniversal.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/FileSystem.h"
#include "llvm/Support/Format.h"
#include "llvm/Support/ManagedStatic.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/Support/PrettyStackTrace.h"
#include "llvm/Support/Signals.h"
#include "llvm/Support/raw_ostream.h"
#include <algorithm>
#include <string>
#include <system_error>
using namespace llvm;
using namespace object;

enum OutputFormatTy {berkeley, sysv, darwin};
static cl::opt<OutputFormatTy>
       OutputFormat("format",
         cl::desc("Specify output format"),
         cl::values(clEnumVal(sysv, "System V format"),
                    clEnumVal(berkeley, "Berkeley format"),
                    clEnumVal(darwin, "Darwin -m format"), clEnumValEnd),
         cl::init(berkeley));

static cl::opt<OutputFormatTy>
       OutputFormatShort(cl::desc("Specify output format"),
         cl::values(clEnumValN(sysv, "A", "System V format"),
                    clEnumValN(berkeley, "B", "Berkeley format"),
                    clEnumValN(darwin, "m", "Darwin -m format"),
                    clEnumValEnd),
         cl::init(berkeley));

static bool berkeleyHeaderPrinted = false;
static bool moreThanOneFile = false;

cl::opt<bool> DarwinLongFormat("l",
         cl::desc("When format is darwin, use long format "
                  "to include addresses and offsets."));

enum RadixTy {octal = 8, decimal = 10, hexadecimal = 16};
static cl::opt<unsigned int>
       Radix("-radix",
         cl::desc("Print size in radix. Only 8, 10, and 16 are valid"),
         cl::init(decimal));

static cl::opt<RadixTy>
       RadixShort(cl::desc("Print size in radix:"),
         cl::values(clEnumValN(octal, "o", "Print size in octal"),
                    clEnumValN(decimal, "d", "Print size in decimal"),
                    clEnumValN(hexadecimal, "x", "Print size in hexadecimal"),
                    clEnumValEnd),
         cl::init(decimal));

static cl::list<std::string>
       InputFilenames(cl::Positional, cl::desc("<input files>"),
                      cl::ZeroOrMore);

static std::string ToolName;

///  @brief If ec is not success, print the error and return true.
static bool error(std::error_code ec) {
  if (!ec) return false;

  outs() << ToolName << ": error reading file: " << ec.message() << ".\n";
  outs().flush();
  return true;
}

/// @brief Get the length of the string that represents @p num in Radix
///        including the leading 0x or 0 for hexadecimal and octal respectively.
static size_t getNumLengthAsString(uint64_t num) {
  APInt conv(64, num);
  SmallString<32> result;
  conv.toString(result, Radix, false, true);
  return result.size();
}

/// @brief Return the the printing format for the Radix.
static const char * getRadixFmt(void) {
  switch (Radix) {
  case octal:
    return PRIo64;
  case decimal:
    return PRIu64;
  case hexadecimal:
    return PRIx64;
  }
  return nullptr;
}

/// @brief Print the size of each Mach-O segment and section in @p MachO.
///
/// This is when used when @c OutputFormat is darwin and produces the same
/// output as darwin's size(1) -m output.
static void PrintDarwinSectionSizes(MachOObjectFile *MachO) {
  std::string fmtbuf;
  raw_string_ostream fmt(fmtbuf);
  const char *radix_fmt = getRadixFmt();
  if (Radix == hexadecimal)
    fmt << "0x";
  fmt << "%" << radix_fmt;

  uint32_t LoadCommandCount = MachO->getHeader().ncmds;
  uint32_t Filetype = MachO->getHeader().filetype;
  MachOObjectFile::LoadCommandInfo Load = MachO->getFirstLoadCommandInfo();

  uint64_t total = 0;
  for (unsigned I = 0; ; ++I) {
    if (Load.C.cmd == MachO::LC_SEGMENT_64) {
      MachO::segment_command_64 Seg = MachO->getSegment64LoadCommand(Load);
      outs() << "Segment " << Seg.segname << ": "
             << format(fmt.str().c_str(), Seg.vmsize);
      if (DarwinLongFormat)
        outs() << " (vmaddr 0x" << format("%" PRIx64, Seg.vmaddr)
               << " fileoff " << Seg.fileoff << ")";
      outs() << "\n";
      total += Seg.vmsize;
      uint64_t sec_total = 0;
      for (unsigned J = 0; J < Seg.nsects; ++J) {
        MachO::section_64 Sec = MachO->getSection64(Load, J);
        if (Filetype == MachO::MH_OBJECT)
          outs() << "\tSection (" << format("%.16s", &Sec.segname) << ", "
                 << format("%.16s", &Sec.sectname) << "): ";
        else
          outs() << "\tSection " << format("%.16s", &Sec.sectname) << ": ";
        outs() << format(fmt.str().c_str(), Sec.size);
        if (DarwinLongFormat)
          outs() << " (addr 0x" << format("%" PRIx64, Sec.addr)
                 << " offset " << Sec.offset << ")";
        outs() << "\n";
        sec_total += Sec.size;
      }
      if (Seg.nsects != 0)
        outs() << "\ttotal " << format(fmt.str().c_str(), sec_total) << "\n";
    }
    else if (Load.C.cmd == MachO::LC_SEGMENT) {
      MachO::segment_command Seg = MachO->getSegmentLoadCommand(Load);
      outs() << "Segment " << Seg.segname << ": "
             << format(fmt.str().c_str(), Seg.vmsize);
      if (DarwinLongFormat)
        outs() << " (vmaddr 0x" << format("%" PRIx64, Seg.vmaddr)
               << " fileoff " << Seg.fileoff << ")";
      outs() << "\n";
      total += Seg.vmsize;
      uint64_t sec_total = 0;
      for (unsigned J = 0; J < Seg.nsects; ++J) {
        MachO::section Sec = MachO->getSection(Load, J);
        if (Filetype == MachO::MH_OBJECT)
          outs() << "\tSection (" << format("%.16s", &Sec.segname) << ", "
                 << format("%.16s", &Sec.sectname) << "): ";
        else
          outs() << "\tSection " << format("%.16s", &Sec.sectname) << ": ";
        outs() << format(fmt.str().c_str(), Sec.size);
        if (DarwinLongFormat)
          outs() << " (addr 0x" << format("%" PRIx64, Sec.addr)
                 << " offset " << Sec.offset << ")";
        outs() << "\n";
        sec_total += Sec.size;
      }
      if (Seg.nsects != 0)
        outs() << "\ttotal " << format(fmt.str().c_str(), sec_total) << "\n";
    }
    if (I == LoadCommandCount - 1)
      break;
    else
      Load = MachO->getNextLoadCommandInfo(Load);
  }
  outs() << "total " << format(fmt.str().c_str(), total) << "\n";
}

/// @brief Print the summary sizes of the standard Mach-O segments in @p MachO.
///
/// This is when used when @c OutputFormat is berkeley with a Mach-O file and
/// produces the same output as darwin's size(1) default output.
static void PrintDarwinSegmentSizes(MachOObjectFile *MachO) {
  uint32_t LoadCommandCount = MachO->getHeader().ncmds;
  MachOObjectFile::LoadCommandInfo Load = MachO->getFirstLoadCommandInfo();

  uint64_t total_text = 0;
  uint64_t total_data = 0;
  uint64_t total_objc = 0;
  uint64_t total_others = 0;
  for (unsigned I = 0; ; ++I) {
    if (Load.C.cmd == MachO::LC_SEGMENT_64) {
      MachO::segment_command_64 Seg = MachO->getSegment64LoadCommand(Load);
      if (MachO->getHeader().filetype == MachO::MH_OBJECT) {
        for (unsigned J = 0; J < Seg.nsects; ++J) {
          MachO::section_64 Sec = MachO->getSection64(Load, J);
          StringRef SegmentName = StringRef(Sec.segname);
          if (SegmentName == "__TEXT")
            total_text += Sec.size;
          else if (SegmentName == "__DATA")
            total_data += Sec.size;
          else if (SegmentName == "__OBJC")
            total_objc += Sec.size;
          else
            total_others += Sec.size;
	}
      } else {
        StringRef SegmentName = StringRef(Seg.segname);
        if (SegmentName == "__TEXT")
          total_text += Seg.vmsize;
        else if (SegmentName == "__DATA")
          total_data += Seg.vmsize;
        else if (SegmentName == "__OBJC")
          total_objc += Seg.vmsize;
        else
          total_others += Seg.vmsize;
      }
    }
    else if (Load.C.cmd == MachO::LC_SEGMENT) {
      MachO::segment_command Seg = MachO->getSegmentLoadCommand(Load);
      if (MachO->getHeader().filetype == MachO::MH_OBJECT) {
        for (unsigned J = 0; J < Seg.nsects; ++J) {
          MachO::section Sec = MachO->getSection(Load, J);
          StringRef SegmentName = StringRef(Sec.segname);
          if (SegmentName == "__TEXT")
            total_text += Sec.size;
          else if (SegmentName == "__DATA")
            total_data += Sec.size;
          else if (SegmentName == "__OBJC")
            total_objc += Sec.size;
          else
            total_others += Sec.size;
	}
      } else {
        StringRef SegmentName = StringRef(Seg.segname);
        if (SegmentName == "__TEXT")
          total_text += Seg.vmsize;
        else if (SegmentName == "__DATA")
          total_data += Seg.vmsize;
        else if (SegmentName == "__OBJC")
          total_objc += Seg.vmsize;
        else
          total_others += Seg.vmsize;
      }
    }
    if (I == LoadCommandCount - 1)
      break;
    else
      Load = MachO->getNextLoadCommandInfo(Load);
  }
  uint64_t total = total_text + total_data + total_objc + total_others;

  if (!berkeleyHeaderPrinted) {
    outs() << "__TEXT\t__DATA\t__OBJC\tothers\tdec\thex\n";
    berkeleyHeaderPrinted = true;
  }
  outs() << total_text << "\t" << total_data << "\t" << total_objc << "\t"
         << total_others << "\t" << total << "\t" << format("%" PRIx64, total)
         << "\t";
}

/// @brief Print the size of each section in @p Obj.
///
/// The format used is determined by @c OutputFormat and @c Radix.
static void PrintObjectSectionSizes(ObjectFile *Obj) {
  uint64_t total = 0;
  std::string fmtbuf;
  raw_string_ostream fmt(fmtbuf);
  const char *radix_fmt = getRadixFmt();

  // If OutputFormat is darwin and we have a MachOObjectFile print as darwin's
  // size(1) -m output, else if OutputFormat is darwin and not a Mach-O object
  // let it fall through to OutputFormat berkeley.
  MachOObjectFile *MachO = dyn_cast<MachOObjectFile>(Obj);
  if (OutputFormat == darwin && MachO)
    PrintDarwinSectionSizes(MachO);
  // If we have a MachOObjectFile and the OutputFormat is berkeley print as
  // darwin's default berkeley format for Mach-O files.
  else if (MachO && OutputFormat == berkeley)
    PrintDarwinSegmentSizes(MachO);
  else if (OutputFormat == sysv) {
    // Run two passes over all sections. The first gets the lengths needed for
    // formatting the output. The second actually does the output.
    std::size_t max_name_len = strlen("section");
    std::size_t max_size_len = strlen("size");
    std::size_t max_addr_len = strlen("addr");
    for (const SectionRef &Section : Obj->sections()) {
      uint64_t size = 0;
      if (error(Section.getSize(size)))
        return;
      total += size;

      StringRef name;
      uint64_t addr = 0;
      if (error(Section.getName(name)))
        return;
      if (error(Section.getAddress(addr)))
        return;
      max_name_len = std::max(max_name_len, name.size());
      max_size_len = std::max(max_size_len, getNumLengthAsString(size));
      max_addr_len = std::max(max_addr_len, getNumLengthAsString(addr));
    }

    // Add extra padding.
    max_name_len += 2;
    max_size_len += 2;
    max_addr_len += 2;

    // Setup header format.
    fmt << "%-" << max_name_len << "s "
        << "%" << max_size_len << "s "
        << "%" << max_addr_len << "s\n";

    // Print header
    outs() << format(fmt.str().c_str(),
                     static_cast<const char*>("section"),
                     static_cast<const char*>("size"),
                     static_cast<const char*>("addr"));
    fmtbuf.clear();

    // Setup per section format.
    fmt << "%-" << max_name_len << "s "
        << "%#" << max_size_len << radix_fmt << " "
        << "%#" << max_addr_len << radix_fmt << "\n";

    // Print each section.
    for (const SectionRef &Section : Obj->sections()) {
      StringRef name;
      uint64_t size = 0;
      uint64_t addr = 0;
      if (error(Section.getName(name)))
        return;
      if (error(Section.getSize(size)))
        return;
      if (error(Section.getAddress(addr)))
        return;
      std::string namestr = name;

      outs() << format(fmt.str().c_str(), namestr.c_str(), size, addr);
    }

    // Print total.
    fmtbuf.clear();
    fmt << "%-" << max_name_len << "s "
        << "%#" << max_size_len << radix_fmt << "\n";
    outs() << format(fmt.str().c_str(),
                     static_cast<const char*>("Total"),
                     total);
  } else {
    // The Berkeley format does not display individual section sizes. It
    // displays the cumulative size for each section type.
    uint64_t total_text = 0;
    uint64_t total_data = 0;
    uint64_t total_bss = 0;

    // Make one pass over the section table to calculate sizes.
    for (const SectionRef &Section : Obj->sections()) {
      uint64_t size = 0;
      bool isText = false;
      bool isData = false;
      bool isBSS = false;
      if (error(Section.getSize(size)))
        return;
      if (error(Section.isText(isText)))
        return;
      if (error(Section.isData(isData)))
        return;
      if (error(Section.isBSS(isBSS)))
        return;
      if (isText)
        total_text += size;
      else if (isData)
        total_data += size;
      else if (isBSS)
        total_bss += size;
    }

    total = total_text + total_data + total_bss;

    if (!berkeleyHeaderPrinted) {
      outs() << "   text    data     bss     "
             << (Radix == octal ? "oct" : "dec")
             << "     hex filename\n";
      berkeleyHeaderPrinted = true;
    }

    // Print result.
    fmt << "%#7" << radix_fmt << " "
        << "%#7" << radix_fmt << " "
        << "%#7" << radix_fmt << " ";
    outs() << format(fmt.str().c_str(),
                     total_text,
                     total_data,
                     total_bss);
    fmtbuf.clear();
    fmt << "%7" << (Radix == octal ? PRIo64 : PRIu64) << " "
        << "%7" PRIx64 " ";
    outs() << format(fmt.str().c_str(),
                     total,
                     total);
  }
}

/// @brief Print the section sizes for @p file. If @p file is an archive, print
///        the section sizes for each archive member.
static void PrintFileSectionSizes(StringRef file) {
  // If file is not stdin, check that it exists.
  if (file != "-") {
    bool exists;
    if (sys::fs::exists(file, exists) || !exists) {
      errs() << ToolName << ": '" << file << "': " << "No such file\n";
      return;
    }
  }

  // Attempt to open the binary.
  ErrorOr<Binary *> BinaryOrErr = createBinary(file);
  if (std::error_code EC = BinaryOrErr.getError()) {
    errs() << ToolName << ": " << file << ": " << EC.message() << ".\n";
    return;
  }
  std::unique_ptr<Binary> binary(BinaryOrErr.get());

  if (Archive *a = dyn_cast<Archive>(binary.get())) {
    // This is an archive. Iterate over each member and display its sizes.
    for (object::Archive::child_iterator i = a->child_begin(),
                                         e = a->child_end(); i != e; ++i) {
      ErrorOr<std::unique_ptr<Binary>> ChildOrErr = i->getAsBinary();
      if (std::error_code EC = ChildOrErr.getError()) {
        errs() << ToolName << ": " << file << ": " << EC.message() << ".\n";
        continue;
      }
      if (ObjectFile *o = dyn_cast<ObjectFile>(&*ChildOrErr.get())) {
        MachOObjectFile *MachO = dyn_cast<MachOObjectFile>(o);
        if (OutputFormat == sysv)
          outs() << o->getFileName() << "   (ex " << a->getFileName()
                  << "):\n";
        else if(MachO && OutputFormat == darwin)
            outs() << a->getFileName() << "(" << o->getFileName() << "):\n";
        PrintObjectSectionSizes(o);
        if (OutputFormat == berkeley) {
          if (MachO)
            outs() << a->getFileName() << "(" << o->getFileName() << ")\n";
          else
            outs() << o->getFileName() << " (ex " << a->getFileName() << ")\n";
        }
      }
    }
  } else if (MachOUniversalBinary *UB =
             dyn_cast<MachOUniversalBinary>(binary.get())) {
    // This is a Mach-O universal binary. Iterate over each object and
    // display its sizes.
    bool moreThanOneArch = UB->getNumberOfObjects() > 1;
    for (MachOUniversalBinary::object_iterator I = UB->begin_objects(),
                                               E = UB->end_objects();
         I != E; ++I) {
      ErrorOr<std::unique_ptr<ObjectFile>> UO = I->getAsObjectFile();
      std::unique_ptr<Archive> UA;
      if (UO) {
        if (ObjectFile *o = dyn_cast<ObjectFile>(&*UO.get())) {
          MachOObjectFile *MachO = dyn_cast<MachOObjectFile>(o);
          if (OutputFormat == sysv)
            outs() << o->getFileName() << "  :\n";
          else if(MachO && OutputFormat == darwin) {
            if (moreThanOneFile || moreThanOneArch)
              outs() << o->getFileName() << " (for architecture "
                     << I->getArchTypeName() << "):";
            outs() << "\n";
          }
          PrintObjectSectionSizes(o);
          if (OutputFormat == berkeley) {
            if (!MachO || moreThanOneFile || moreThanOneArch)
              outs() << o->getFileName() << " (for architecture "
                     << I->getArchTypeName() << ")";
            outs() << "\n";
          }
        }
      }
      else if (!I->getAsArchive(UA)) {
        // This is an archive. Iterate over each member and display its sizes.
        for (object::Archive::child_iterator i = UA->child_begin(),
                                             e = UA->child_end(); i != e; ++i) {
          ErrorOr<std::unique_ptr<Binary>> ChildOrErr = i->getAsBinary();
          if (std::error_code EC = ChildOrErr.getError()) {
            errs() << ToolName << ": " << file << ": " << EC.message() << ".\n";
            continue;
          }
          if (ObjectFile *o = dyn_cast<ObjectFile>(&*ChildOrErr.get())) {
            MachOObjectFile *MachO = dyn_cast<MachOObjectFile>(o);
            if (OutputFormat == sysv)
              outs() << o->getFileName() << "   (ex " << UA->getFileName()
                     << "):\n";
            else if(MachO && OutputFormat == darwin)
              outs() << UA->getFileName() << "(" << o->getFileName() << ")"
                     << " (for architecture " << I->getArchTypeName()
                     << "):\n";
            PrintObjectSectionSizes(o);
            if (OutputFormat == berkeley) {
              if (MachO)
                outs() << UA->getFileName() << "(" << o->getFileName() << ")"
                       << " (for architecture " << I->getArchTypeName()
                       << ")\n";
              else
                outs() << o->getFileName() << " (ex " << UA->getFileName()
                       << ")\n";
            }
          }
        }
      }
    }
  } else if (ObjectFile *o = dyn_cast<ObjectFile>(binary.get())) {
    if (OutputFormat == sysv)
      outs() << o->getFileName() << "  :\n";
    PrintObjectSectionSizes(o);
    if (OutputFormat == berkeley) {
      MachOObjectFile *MachO = dyn_cast<MachOObjectFile>(o);
      if (!MachO || moreThanOneFile)
        outs() << o->getFileName();
      outs() << "\n";
    }
  } else {
    errs() << ToolName << ": " << file << ": " << "Unrecognized file type.\n";
  }
  // System V adds an extra newline at the end of each file.
  if (OutputFormat == sysv)
    outs() << "\n";
}

int main(int argc, char **argv) {
  // Print a stack trace if we signal out.
  sys::PrintStackTraceOnErrorSignal();
  PrettyStackTraceProgram X(argc, argv);

  llvm_shutdown_obj Y;  // Call llvm_shutdown() on exit.
  cl::ParseCommandLineOptions(argc, argv, "llvm object size dumper\n");

  ToolName = argv[0];
  if (OutputFormatShort.getNumOccurrences())
    OutputFormat = OutputFormatShort;
  if (RadixShort.getNumOccurrences())
    Radix = RadixShort;

  if (InputFilenames.size() == 0)
    InputFilenames.push_back("a.out");

  moreThanOneFile = InputFilenames.size() > 1;
  std::for_each(InputFilenames.begin(), InputFilenames.end(),
                PrintFileSectionSizes);

  return 0;
}