path: root/lib/CodeGen/MachOWriter.h

//=== MachOWriter.h - Target-independent Mach-O writer support --*- C++ -*-===//
//
//                     The LLVM Compiler Infrastructure
//
// This file was developed by Nate Begeman and is distributed under the
// University of Illinois Open Source License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file defines the MachOWriter class.
//
//===----------------------------------------------------------------------===//

#ifndef MACHOWRITER_H
#define MACHOWRITER_H

#include "llvm/Constants.h"
#include "llvm/DerivedTypes.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
#include "llvm/CodeGen/MachineRelocation.h"
#include "llvm/Target/TargetData.h"
#include "llvm/Target/TargetMachine.h"
#include "llvm/Target/TargetMachOWriterInfo.h"

namespace llvm {
  class GlobalVariable;
  class Mangler;
  class MachineCodeEmitter;
  class MachOCodeEmitter;
  class OutputBuffer;

  /// MachOSym - This struct contains information about each symbol that is
  /// added to logical symbol table for the module.  This is eventually
  /// turned into a real symbol table in the file.
  struct MachOSym {
    const GlobalValue *GV;    // The global value this corresponds to.
    std::string GVName;       // The mangled name of the global value.
    uint32_t    n_strx;       // index into the string table
    uint8_t     n_type;       // type flag
    uint8_t     n_sect;       // section number or NO_SECT
    int16_t     n_desc;       // see <mach-o/stab.h>
    uint64_t    n_value;      // value for this symbol (or stab offset)
    
    // Constants for the n_sect field
    // see <mach-o/nlist.h>
    enum { NO_SECT = 0 };   // symbol is not in any section

    // Constants for the n_type field
    // see <mach-o/nlist.h>
    enum { N_UNDF  = 0x0,  // undefined, n_sect == NO_SECT
           N_ABS   = 0x2,  // absolute, n_sect == NO_SECT
           N_SECT  = 0xe,  // defined in section number n_sect
           N_PBUD  = 0xc,  // prebound undefined (defined in a dylib)
           N_INDR  = 0xa   // indirect
    };
    // The following bits are OR'd into the types above. For example, a type
    // of 0x0f would be an external N_SECT symbol (0x0e | 0x01).
    enum { N_EXT  = 0x01,   // external symbol bit
           N_PEXT = 0x10    // private external symbol bit
    };
    
    // Constants for the n_desc field
    // see <mach-o/loader.h>
    enum { REFERENCE_FLAG_UNDEFINED_NON_LAZY          = 0,
           REFERENCE_FLAG_UNDEFINED_LAZY              = 1,
           REFERENCE_FLAG_DEFINED                     = 2,
           REFERENCE_FLAG_PRIVATE_DEFINED             = 3,
           REFERENCE_FLAG_PRIVATE_UNDEFINED_NON_LAZY  = 4,
           REFERENCE_FLAG_PRIVATE_UNDEFINED_LAZY      = 5
    };
    enum { N_NO_DEAD_STRIP = 0x0020, // symbol is not to be dead stripped
           N_WEAK_REF      = 0x0040, // symbol is weak referenced
           N_WEAK_DEF      = 0x0080  // coalesced symbol is a weak definition
    };
    
    MachOSym(const GlobalValue *gv, std::string name, uint8_t sect,
             TargetMachine &TM);
  };
      
  /// MachOWriter - This class implements the common target-independent code for
  /// writing Mach-O files.  Targets should derive a class from this to
  /// parameterize the output format.
  ///
  class MachOWriter : public MachineFunctionPass {
    friend class MachOCodeEmitter;
  public:
    static char ID;
    MachineCodeEmitter &getMachineCodeEmitter() const {
      return *(MachineCodeEmitter*)MCE;
    }

    MachOWriter(std::ostream &O, TargetMachine &TM);
    virtual ~MachOWriter();

    virtual const char *getPassName() const {
      return "Mach-O Writer";
    }

    typedef std::vector<unsigned char> DataBuffer;
  protected:
    /// Output stream to send the resultant object file to.
    ///
    std::ostream &O;

    /// Target machine description.
    ///
    TargetMachine &TM;

    /// Mang - The object used to perform name mangling for this module.
    ///
    Mangler *Mang;
    
    /// MCE - The MachineCodeEmitter object that we are exposing to emit machine
    /// code for functions to the .o file.
    MachOCodeEmitter *MCE;

    /// is64Bit/isLittleEndian - This information is inferred from the target
    /// machine directly, indicating what header values and flags to set.
    bool is64Bit, isLittleEndian;

    /// doInitialization - Emit the file header and all of the global variables
    /// for the module to the Mach-O file.
    bool doInitialization(Module &M);

    bool runOnMachineFunction(MachineFunction &MF);

    /// doFinalization - Now that the module has been completely processed, emit
    /// the Mach-O file to 'O'.
    bool doFinalization(Module &M);

    /// MachOHeader - This struct contains the header information about a
    /// specific architecture type/subtype pair that is emitted to the file.
    struct MachOHeader {
      uint32_t  magic;      // mach magic number identifier
      uint32_t  filetype;   // type of file
      uint32_t  ncmds;      // number of load commands
      uint32_t  sizeofcmds; // the size of all the load commands
      uint32_t  flags;      // flags
      uint32_t  reserved;   // 64-bit only
      
      /// HeaderData - The actual data for the header which we are building
      /// up for emission to the file.
      DataBuffer HeaderData;

      // Constants for the filetype field
      // see <mach-o/loader.h> for additional info on the various types
      enum { MH_OBJECT     = 1, // relocatable object file
             MH_EXECUTE    = 2, // demand paged executable file
             MH_FVMLIB     = 3, // fixed VM shared library file
             MH_CORE       = 4, // core file
             MH_PRELOAD    = 5, // preloaded executable file
             MH_DYLIB      = 6, // dynamically bound shared library
             MH_DYLINKER   = 7, // dynamic link editor
             MH_BUNDLE     = 8, // dynamically bound bundle file
             MH_DYLIB_STUB = 9, // shared library stub for static linking only
             MH_DSYM       = 10 // companion file wiht only debug sections
      };
      
      // Constants for the flags field
      enum { MH_NOUNDEFS                = 1 << 0,
                // the object file has no undefined references
             MH_INCRLINK                = 1 << 1,
                // the object file is the output of an incremental link against
                // a base file and cannot be link edited again
             MH_DYLDLINK                = 1 << 2,
                // the object file is input for the dynamic linker and cannot be
                // statically link edited again.
             MH_BINDATLOAD              = 1 << 3,
                // the object file's undefined references are bound by the
                // dynamic linker when loaded.
             MH_PREBOUND                = 1 << 4,
                // the file has its dynamic undefined references prebound
             MH_SPLIT_SEGS              = 1 << 5,
                // the file has its read-only and read-write segments split
                // see <mach/shared_memory_server.h>
             MH_LAZY_INIT               = 1 << 6,
                // the shared library init routine is to be run lazily via
                // catching memory faults to its writable segments (obsolete)
             MH_TWOLEVEL                = 1 << 7,
                // the image is using two-level namespace bindings
             MH_FORCE_FLAT              = 1 << 8,
                // the executable is forcing all images to use flat namespace
                // bindings.
             MH_NOMULTIDEFS             = 1 << 8,
                // this umbrella guarantees no multiple definitions of symbols
                // in its sub-images so the two-level namespace hints can
                // always be used.
             MH_NOFIXPREBINDING         = 1 << 10,
                // do not have dyld notify the prebidning agent about this
                // executable.
             MH_PREBINDABLE             = 1 << 11,
                // the binary is not prebound but can have its prebinding
                // redone.  only used when MH_PREBOUND is not set.
             MH_ALLMODSBOUND            = 1 << 12,
                // indicates that this binary binds to all two-level namespace
                // modules of its dependent libraries.  Only used when
                // MH_PREBINDABLE and MH_TWOLEVEL are both set.
             MH_SUBSECTIONS_VIA_SYMBOLS = 1 << 13,
                // safe to divide up the sections into sub-sections via symbols
                // for dead code stripping.
             MH_CANONICAL               = 1 << 14,
                // the binary has been canonicalized via the unprebind operation
             MH_WEAK_DEFINES            = 1 << 15,
                // the final linked image contains external weak symbols
             MH_BINDS_TO_WEAK           = 1 << 16,
                // the final linked image uses weak symbols
             MH_ALLOW_STACK_EXECUTION   = 1 << 17
                // When this bit is set, all stacks in the task will be given
                // stack execution privilege.  Only used in MH_EXECUTE filetype
      };

      MachOHeader() : magic(0), filetype(0), ncmds(0), sizeofcmds(0), flags(0),
                      reserved(0) { }
      
      /// cmdSize - This routine returns the size of the MachOSection as written
      /// to disk, depending on whether the destination is a 64 bit Mach-O file.
      unsigned cmdSize(bool is64Bit) const {
        if (is64Bit)