macho-apple.h

Go to the documentation of this file.

/*
 * Copyright (c) 1999 Apple Computer, Inc. All rights reserved.
 *
 * @APPLE_LICENSE_HEADER_START@
 * 
 * This file contains Original Code and/or Modifications of Original Code
 * as defined in and that are subject to the Apple Public Source License
 * Version 2.0 (the 'License'). You may not use this file except in
 * compliance with the License. Please obtain a copy of the License at
 * http://www.opensource.apple.com/apsl/ and read it before using this
 * file.
 * 
 * The Original Code and all software distributed under the License are
 * distributed on an 'AS IS' basis, WITHOUT WARRANTY OF ANY KIND, EITHER
 * EXPRESS OR IMPLIED, AND APPLE HEREBY DISCLAIMS ALL SUCH WARRANTIES,
 * INCLUDING WITHOUT LIMITATION, ANY WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE, QUIET ENJOYMENT OR NON-INFRINGEMENT.
 * Please see the License for the specific language governing rights and
 * limitations under the License.
 * 
 * @APPLE_LICENSE_HEADER_END@
 */
#ifndef _MACHO_LOADER_H_
#define _MACHO_LOADER_H_

/*
 * This file describes the format of mach object files.
 */

/*
 * <mach/machine.h> is needed here for the cpu_type_t and cpu_subtype_t types
 * and contains the constants for the possible values of these types.
 */
//#include <mach/machine.h>

/*
 * <mach/vm_prot.h> is needed here for the vm_prot_t type and contains the 
 * constants that are or'ed together for the possible values of this type.
 */
//#include <mach/vm_prot.h>
#define VM_PROT_NONE    ((vm_prot_t) 0x00)
#define VM_PROT_READ    ((vm_prot_t) 0x01)  /* read permission */
#define VM_PROT_WRITE   ((vm_prot_t) 0x02)  /* write permission */
#define VM_PROT_EXECUTE ((vm_prot_t) 0x04)  /* execute permission */

/*
 * <machine/thread_status.h> is expected to define the flavors of the thread
 * states and the structures of those flavors for each machine.
 */
//#include <mach/machine/thread_status.h>
//#include <architecture/byte_order.h>

/*
 * The mach header appears at the very beginning of the object file.
 */
struct mach_header {
    unsigned long   magic;      /* mach magic number identifier */
    cpu_type_t  cputype;    /* cpu specifier */
    cpu_subtype_t   cpusubtype; /* machine specifier */
    unsigned long   filetype;   /* type of file */
    unsigned long   ncmds;      /* number of load commands */
    unsigned long   sizeofcmds; /* the size of all the load commands */
    unsigned long   flags;      /* flags */
};

/* Constant for the magic field of the mach_header */
#define MH_MAGIC    0xfeedface  /* the mach magic number */
#define MH_CIGAM    NXSwapInt(MH_MAGIC)

/*
 * The layout of the file depends on the filetype.  For all but the MH_OBJECT
 * file type the segments are padded out and aligned on a segment alignment
 * boundary for efficient demand pageing.  The MH_EXECUTE, MH_FVMLIB, MH_DYLIB,
 * MH_DYLINKER and MH_BUNDLE file types also have the headers included as part
 * of their first segment.
 * 
 * The file type MH_OBJECT is a compact format intended as output of the
 * assembler and input (and possibly output) of the link editor (the .o
 * format).  All sections are in one unnamed segment with no segment padding. 
 * This format is used as an executable format when the file is so small the
 * segment padding greatly increases its size.
 *
 * The file type MH_PRELOAD is an executable format intended for things that
 * are not executed under the kernel (proms, stand alones, kernels, etc).  The
 * format can be executed under the kernel but may demand paged it and not
 * preload it before execution.
 *
 * A core file is in MH_CORE format and can be any in an arbritray legal
 * Mach-O file.
 *
 * Constants for the filetype field of the mach_header
 */
#define MH_OBJECT   0x1     /* relocatable object file */
#define MH_EXECUTE  0x2     /* demand paged executable file */
#define MH_FVMLIB   0x3     /* fixed VM shared library file */
#define MH_CORE     0x4     /* core file */
#define MH_PRELOAD  0x5     /* preloaded executable file */
#define MH_DYLIB    0x6     /* dynamically bound shared library */
#define MH_DYLINKER 0x7     /* dynamic link editor */
#define MH_BUNDLE   0x8     /* dynamically bound bundle file */
#define MH_DYLIB_STUB   0x9     /* shared library stub for static */
                    /*  linking only, no section contents */

/* Constants for the flags field of the mach_header */
#define MH_NOUNDEFS 0x1     /* the object file has no undefined
                       references */
#define MH_INCRLINK 0x2     /* the object file is the output of an
                       incremental link against a base file
                       and can't be link edited again */
#define MH_DYLDLINK 0x4     /* the object file is input for the
                       dynamic linker and can't be staticly
                       link edited again */
#define MH_BINDATLOAD   0x8     /* the object file's undefined
                       references are bound by the dynamic
                       linker when loaded. */
#define MH_PREBOUND 0x10        /* the file has its dynamic undefined
                       references prebound. */
#define MH_SPLIT_SEGS   0x20        /* the file has its read-only and
                       read-write segments split */
#define MH_LAZY_INIT    0x40        /* the shared library init routine is
                       to be run lazily via catching memory
                       faults to its writeable segments
                       (obsolete) */
#define MH_TWOLEVEL 0x80        /* the image is using two-level name
                       space bindings */
#define MH_FORCE_FLAT   0x100       /* the executable is forcing all images
                       to use flat name space bindings */
#define MH_NOMULTIDEFS  0x200       /* this umbrella guarantees no multiple
                       defintions of symbols in its
                       sub-images so the two-level namespace
                       hints can always be used. */
#define MH_NOFIXPREBINDING 0x400    /* do not have dyld notify the
                       prebinding agent about this
                       executable */
#define MH_PREBINDABLE  0x800           /* the binary is not prebound but can
                       have its prebinding redone. only used
                                           when MH_PREBOUND is not set. */
#define MH_ALLMODSBOUND 0x1000      /* 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. */ 
#define MH_CANONICAL    0x4000      /* the binary has been canonicalized
                       via the unprebind operation */
/*
 * The load commands directly follow the mach_header.  The total size of all
 * of the commands is given by the sizeofcmds field in the mach_header.  All
 * load commands must have as their first two fields cmd and cmdsize.  The cmd
 * field is filled in with a constant for that command type.  Each command type
 * has a structure specifically for it.  The cmdsize field is the size in bytes
 * of the particular load command structure plus anything that follows it that
 * is a part of the load command (i.e. section structures, strings, etc.).  To
 * advance to the next load command the cmdsize can be added to the offset or
 * pointer of the current load command.  The cmdsize MUST be a multiple of
 * 4 bytes (this is forever the maximum alignment of any load commands).
 * The padded bytes must be zero.  All tables in the object file must also
 * follow these rules so the file can be memory mapped.  Otherwise the pointers
 * to these tables will not work well or at all on some machines.  With all
 * padding zeroed like objects will compare byte for byte.
 */
struct load_command {
    unsigned long cmd;      /* type of load command */
    unsigned long cmdsize;      /* total size of command in bytes */
};

/*
 * After MacOS X 10.1 when a new load command is added that is required to be
 * understood by the dynamic linker for the image to execute properly the
 * LC_REQ_DYLD bit will be or'ed into the load command constant.  If the dynamic
 * linker sees such a load command it it does not understand will issue a
 * "unknown load command required for execution" error and refuse to use the
 * image.  Other load commands without this bit that are not understood will
 * simply be ignored.
 */
#define LC_REQ_DYLD 0x80000000

/* Constants for the cmd field of all load commands, the type */
#define LC_SEGMENT  0x1 /* segment of this file to be mapped */
#define LC_SYMTAB   0x2 /* link-edit stab symbol table info */
#define LC_SYMSEG   0x3 /* link-edit gdb symbol table info (obsolete) */
#define LC_THREAD   0x4 /* thread */
#define LC_UNIXTHREAD   0x5 /* unix thread (includes a stack) */
#define LC_LOADFVMLIB   0x6 /* load a specified fixed VM shared library */
#define LC_IDFVMLIB 0x7 /* fixed VM shared library identification */
#define LC_IDENT    0x8 /* object identification info (obsolete) */
#define LC_FVMFILE  0x9 /* fixed VM file inclusion (internal use) */
#define LC_PREPAGE      0xa     /* prepage command (internal use) */
#define LC_DYSYMTAB 0xb /* dynamic link-edit symbol table info */
#define LC_LOAD_DYLIB   0xc /* load a dynamically linked shared library */
#define LC_ID_DYLIB 0xd /* dynamically linked shared lib ident */
#define LC_LOAD_DYLINKER 0xe    /* load a dynamic linker */
#define LC_ID_DYLINKER  0xf /* dynamic linker identification */
#define LC_PREBOUND_DYLIB 0x10  /* modules prebound for a dynamically */
                /*  linked shared library */
#define LC_ROUTINES 0x11    /* image routines */
#define LC_SUB_FRAMEWORK 0x12   /* sub framework */
#define LC_SUB_UMBRELLA 0x13    /* sub umbrella */
#define LC_SUB_CLIENT   0x14    /* sub client */
#define LC_SUB_LIBRARY  0x15    /* sub library */
#define LC_TWOLEVEL_HINTS 0x16  /* two-level namespace lookup hints */
#define LC_PREBIND_CKSUM  0x17  /* prebind checksum */
/*
 * load a dynamically linked shared library that is allowed to be missing
 * (all symbols are weak imported).
 */
#define LC_LOAD_WEAK_DYLIB (0x18 | LC_REQ_DYLD)

/*
 * A variable length string in a load command is represented by an lc_str
 * union.  The strings are stored just after the load command structure and
 * the offset is from the start of the load command structure.  The size
 * of the string is reflected in the cmdsize field of the load command.
 * Once again any padded bytes to bring the cmdsize field to a multiple
 * of 4 bytes must be zero.
 */
union lc_str {
    unsigned long   offset; /* offset to the string */
    char        *ptr;   /* pointer to the string */
};

/*
 * The segment load command indicates that a part of this file is to be
 * mapped into the task's address space.  The size of this segment in memory,
 * vmsize, maybe equal to or larger than the amount to map from this file,
 * filesize.  The file is mapped starting at fileoff to the beginning of
 * the segment in memory, vmaddr.  The rest of the memory of the segment,
 * if any, is allocated zero fill on demand.  The segment's maximum virtual
 * memory protection and initial virtual memory protection are specified
 * by the maxprot and initprot fields.  If the segment has sections then the
 * section structures directly follow the segment command and their size is
 * reflected in cmdsize.
 */
struct segment_command {
    unsigned long   cmd;        /* LC_SEGMENT */
    unsigned long   cmdsize;    /* includes sizeof section structs */
    char        segname[16];    /* segment name */
    unsigned long   vmaddr;     /* memory address of this segment */
    unsigned long   vmsize;     /* memory size of this segment */
    unsigned long   fileoff;    /* file offset of this segment */
    unsigned long   filesize;   /* amount to map from the file */
    vm_prot_t   maxprot;    /* maximum VM protection */
    vm_prot_t   initprot;   /* initial VM protection */
    unsigned long   nsects;     /* number of sections in segment */
    unsigned long   flags;      /* flags */
};

/* Constants for the flags field of the segment_command */
#define SG_HIGHVM   0x1 /* the file contents for this segment is for
                   the high part of the VM space, the low part
                   is zero filled (for stacks in core files) */
#define SG_FVMLIB   0x2 /* this segment is the VM that is allocated by
                   a fixed VM library, for overlap checking in
                   the link editor */
#define SG_NORELOC  0x4 /* this segment has nothing that was relocated
                   in it and nothing relocated to it, that is
                   it maybe safely replaced without relocation*/

/*
 * A segment is made up of zero or more sections.  Non-MH_OBJECT files have
 * all of their segments with the proper sections in each, and padded to the
 * specified segment alignment when produced by the link editor.  The first
 * segment of a MH_EXECUTE and MH_FVMLIB format file contains the mach_header
 * and load commands of the object file before its first section.  The zero
 * fill sections are always last in their segment (in all formats).  This
 * allows the zeroed segment padding to be mapped into memory where zero fill
 * sections might be.
 *
 * The MH_OBJECT format has all of its sections in one segment for
 * compactness.  There is no padding to a specified segment boundary and the
 * mach_header and load commands are not part of the segment.
 *
 * Sections with the same section name, sectname, going into the same segment,
 * segname, are combined by the link editor.  The resulting section is aligned
 * to the maximum alignment of the combined sections and is the new section's
 * alignment.  The combined sections are aligned to their original alignment in
 * the combined section.  Any padded bytes to get the specified alignment are
 * zeroed.
 *
 * The format of the relocation entries referenced by the reloff and nreloc
 * fields of the section structure for mach object files is described in the
 * header file <reloc.h>.
 */
struct section {
    char        sectname[16];   /* name of this section */
    char        segname[16];    /* segment this section goes in */
    unsigned long   addr;       /* memory address of this section */
    unsigned long   size;       /* size in bytes of this section */
    unsigned long   offset;     /* file offset of this section */
    unsigned long   align;      /* section alignment (power of 2) */
    unsigned long   reloff;     /* file offset of relocation entries */
    unsigned long   nreloc;     /* number of relocation entries */
    unsigned long   flags;      /* flags (section type and attributes)*/
    unsigned long   reserved1;  /* reserved */
    unsigned long   reserved2;  /* reserved */
};

/*
 * The flags field of a section structure is separated into two parts a section
 * type and section attributes.  The section types are mutually exclusive (it
 * can only have one type) but the section attributes are not (it may have more
 * than one attribute).
 */
#define SECTION_TYPE         0x000000ff /* 256 section types */
#define SECTION_ATTRIBUTES   0xffffff00 /*  24 section attributes */

/* Constants for the type of a section */
#define S_REGULAR       0x0 /* regular section */
#define S_ZEROFILL      0x1 /* zero fill on demand section */
#define S_CSTRING_LITERALS  0x2 /* section with only literal C strings*/
#define S_4BYTE_LITERALS    0x3 /* section with only 4 byte literals */
#define S_8BYTE_LITERALS    0x4 /* section with only 8 byte literals */
#define S_LITERAL_POINTERS  0x5 /* section with only pointers to */
                    /*  literals */
/*
 * For the two types of symbol pointers sections and the symbol stubs section
 * they have indirect symbol table entries.  For each of the entries in the
 * section the indirect symbol table entries, in corresponding order in the
 * indirect symbol table, start at the index stored in the reserved1 field
 * of the section structure.  Since the indirect symbol table entries
 * correspond to the entries in the section the number of indirect symbol table
 * entries is inferred from the size of the section divided by the size of the
 * entries in the section.  For symbol pointers sections the size of the entries
 * in the section is 4 bytes and for symbol stubs sections the byte size of the
 * stubs is stored in the reserved2 field of the section structure.
 */
#define S_NON_LAZY_SYMBOL_POINTERS  0x6 /* section with only non-lazy
                           symbol pointers */
#define S_LAZY_SYMBOL_POINTERS      0x7 /* section with only lazy symbol
                           pointers */
#define S_SYMBOL_STUBS          0x8 /* section with only symbol
                           stubs, byte size of stub in
                           the reserved2 field */
#define S_MOD_INIT_FUNC_POINTERS    0x9 /* section with only function
                           pointers for initialization*/
#define S_MOD_TERM_FUNC_POINTERS    0xa /* section with only function
                           pointers for termination */
#define S_COALESCED         0xb /* section contains symbols that
                           are to be coalesced */
/*
 * Constants for the section attributes part of the flags field of a section
 * structure.
 */
#define SECTION_ATTRIBUTES_USR   0xff000000 /* User setable attributes */
#define S_ATTR_PURE_INSTRUCTIONS 0x80000000 /* section contains only true
                           machine instructions */
#define S_ATTR_NO_TOC        0x40000000 /* section contains coalesced
                           symbols that are not to be
                           in a ranlib table of
                           contents */
#define S_ATTR_STRIP_STATIC_SYMS 0x20000000 /* ok to strip static symbols
                           in this section in files
                           with the MH_DYLDLINK flag */
#define SECTION_ATTRIBUTES_SYS   0x00ffff00 /* system setable attributes */
#define S_ATTR_SOME_INSTRUCTIONS 0x00000400 /* section contains some
                           machine instructions */
#define S_ATTR_EXT_RELOC     0x00000200 /* section has external
                           relocation entries */
#define S_ATTR_LOC_RELOC     0x00000100 /* section has local
                           relocation entries */


/*
 * The names of segments and sections in them are mostly meaningless to the
 * link-editor.  But there are few things to support traditional UNIX
 * executables that require the link-editor and assembler to use some names
 * agreed upon by convention.
 *
 * The initial protection of the "__TEXT" segment has write protection turned
 * off (not writeable).
 *
 * The link-editor will allocate common symbols at the end of the "__common"
 * section in the "__DATA" segment.  It will create the section and segment
 * if needed.
 */

/* The currently known segment names and the section names in those segments */

#define SEG_PAGEZERO    "__PAGEZERO"    /* the pagezero segment which has no */
                    /* protections and catches NULL */
                    /* references for MH_EXECUTE files */


#define SEG_TEXT    "__TEXT"    /* the tradition UNIX text segment */
#define SECT_TEXT   "__text"    /* the real text part of the text */
                    /* section no headers, and no padding */
#define SECT_FVMLIB_INIT0 "__fvmlib_init0"  /* the fvmlib initialization */
                        /*  section */
#define SECT_FVMLIB_INIT1 "__fvmlib_init1"  /* the section following the */
                            /*  fvmlib initialization */
                        /*  section */

#define SEG_DATA    "__DATA"    /* the tradition UNIX data segment */
#define SECT_DATA   "__data"    /* the real initialized data section */
                    /* no padding, no bss overlap */
#define SECT_BSS    "__bss"     /* the real uninitialized data section*/
                    /* no padding */
#define SECT_COMMON "__common"  /* the section common symbols are */
                    /* allocated in by the link editor */

#define SEG_OBJC    "__OBJC"    /* objective-C runtime segment */
#define SECT_OBJC_SYMBOLS "__symbol_table"  /* symbol table */
#define SECT_OBJC_MODULES "__module_info"   /* module information */
#define SECT_OBJC_STRINGS "__selector_strs" /* string table */
#define SECT_OBJC_REFS "__selector_refs"    /* string table */

#define SEG_ICON     "__ICON"   /* the icon segment */
#define SECT_ICON_HEADER "__header" /* the icon headers */
#define SECT_ICON_TIFF   "__tiff"   /* the icons in tiff format */

#define SEG_LINKEDIT    "__LINKEDIT"    /* the segment containing all structs */
                    /* created and maintained by the link */
                    /* editor.  Created with -seglinkedit */
                    /* option to ld(1) for MH_EXECUTE and */
                    /* FVMLIB file types only */

#define SEG_UNIXSTACK   "__UNIXSTACK"   /* the unix stack segment */

/*
 * Fixed virtual memory shared libraries are identified by two things.  The
 * target pathname (the name of the library as found for execution), and the
 * minor version number.  The address of where the headers are loaded is in
 * header_addr.
 */
struct fvmlib {
    union lc_str    name;       /* library's target pathname */
    unsigned long   minor_version;  /* library's minor version number */
    unsigned long   header_addr;    /* library's header address */
};

/*
 * A fixed virtual shared library (filetype == MH_FVMLIB in the mach header)
 * contains a fvmlib_command (cmd == LC_IDFVMLIB) to identify the library.
 * An object that uses a fixed virtual shared library also contains a
 * fvmlib_command (cmd == LC_LOADFVMLIB) for each library it uses.
 */
struct fvmlib_command {
    unsigned long   cmd;        /* LC_IDFVMLIB or LC_LOADFVMLIB */
    unsigned long   cmdsize;    /* includes pathname string */
    struct fvmlib   fvmlib;     /* the library identification */
};

/*
 * Dynamicly linked shared libraries are identified by two things.  The
 * pathname (the name of the library as found for execution), and the
 * compatibility version number.  The pathname must match and the compatibility
 * number in the user of the library must be greater than or equal to the
 * library being used.  The time stamp is used to record the time a library was
 * built and copied into user so it can be use to determined if the library used
 * at runtime is exactly the same as used to built the program.
 */
struct dylib {
    union lc_str  name;         /* library's path name */
    unsigned long timestamp;        /* library's build time stamp */
    unsigned long current_version;  /* library's current version number */
    unsigned long compatibility_version;/* library's compatibility vers number*/
};

/*
 * A dynamically linked shared library (filetype == MH_DYLIB in the mach header)
 * contains a dylib_command (cmd == LC_ID_DYLIB) to identify the library.
 * An object that uses a dynamically linked shared library also contains a
 * dylib_command (cmd == LC_LOAD_DYLIB or cmd == LC_LOAD_WEAK_DYLIB) for each
 * library it uses.
 */
struct dylib_command {
    unsigned long   cmd;        /* LC_ID_DYLIB, LC_LOAD_{,WEAK_}DYLIB */
    unsigned long   cmdsize;    /* includes pathname string */
    struct dylib    dylib;      /* the library identification */
};

/*
 * A dynamically linked shared library may be a subframework of an umbrella
 * framework.  If so it will be linked with "-umbrella umbrella_name" where
 * Where "umbrella_name" is the name of the umbrella framework. A subframework
 * can only be linked against by its umbrella framework or other subframeworks
 * that are part of the same umbrella framework.  Otherwise the static link
 * editor produces an error and states to link against the umbrella framework.
 * The name of the umbrella framework for subframeworks is recorded in the
 * following structure.
 */
struct sub_framework_command {
    unsigned long   cmd;        /* LC_SUB_FRAMEWORK */
    unsigned long   cmdsize;    /* includes umbrella string */
    union lc_str    umbrella;   /* the umbrella framework name */
};

/*
 * For dynamically linked shared libraries that are subframework of an umbrella
 * framework they can allow clients other than the umbrella framework or other
 * subframeworks in the same umbrella framework.  To do this the subframework
 * is built with "-allowable_client client_name" and an LC_SUB_CLIENT load
 * command is created for each -allowable_client flag.  The client_name is
 * usually a framework name.  It can also be a name used for bundles clients
 * where the bundle is built with "-client_name client_name".
 */
struct sub_client_command {
    unsigned long   cmd;        /* LC_SUB_CLIENT */
    unsigned long   cmdsize;    /* includes client string */
    union lc_str    client;     /* the client name */
};

/*
 * A dynamically linked shared library may be a sub_umbrella of an umbrella
 * framework.  If so it will be linked with "-sub_umbrella umbrella_name" where
 * Where "umbrella_name" is the name of the sub_umbrella framework.  When
 * staticly linking when -twolevel_namespace is in effect a twolevel namespace 
 * umbrella framework will only cause its subframeworks and those frameworks
 * listed as sub_umbrella frameworks to be implicited linked in.  Any other
 * dependent dynamic libraries will not be linked it when -twolevel_namespace
 * is in effect.  The primary library recorded by the static linker when
 * resolving a symbol in these libraries will be the umbrella framework.
 * Zero or more sub_umbrella frameworks may be use by an umbrella framework.
 * The name of a sub_umbrella framework is recorded in the following structure.
 */
struct sub_umbrella_command {
    unsigned long   cmd;        /* LC_SUB_UMBRELLA */
    unsigned long   cmdsize;    /* includes sub_umbrella string */
    union lc_str    sub_umbrella;   /* the sub_umbrella framework name */
};

/*
 * A dynamically linked shared library may be a sub_library of another shared
 * library.  If so it will be linked with "-sub_library library_name" where
 * Where "library_name" is the name of the sub_library shared library.  When
 * staticly linking when -twolevel_namespace is in effect a twolevel namespace 
 * shared library will only cause its subframeworks and those frameworks
 * listed as sub_umbrella frameworks and libraries listed as sub_libraries to
 * be implicited linked in.  Any other dependent dynamic libraries will not be
 * linked it when -twolevel_namespace is in effect.  The primary library
 * recorded by the static linker when resolving a symbol in these libraries
 * will be the umbrella framework (or dynamic library). Zero or more sub_library
 * shared libraries may be use by an umbrella framework or (or dynamic library).
 * The name of a sub_library framework is recorded in the following structure.
 * For example /usr/lib/libobjc_profile.A.dylib would be recorded as "libobjc".
 */
struct sub_library_command {
    unsigned long   cmd;        /* LC_SUB_LIBRARY */
    unsigned long   cmdsize;    /* includes sub_library string */
    union lc_str    sub_library;    /* the sub_library name */
};

/*
 * A program (filetype == MH_EXECUTE) that is
 * prebound to its dynamic libraries has one of these for each library that
 * the static linker used in prebinding.  It contains a bit vector for the
 * modules in the library.  The bits indicate which modules are bound (1) and
 * which are not (0) from the library.  The bit for module 0 is the low bit
 * of the first byte.  So the bit for the Nth module is:
 * (linked_modules[N/8] >> N%8) & 1
 */
struct prebound_dylib_command {
    unsigned long   cmd;        /* LC_PREBOUND_DYLIB */
    unsigned long   cmdsize;    /* includes strings */
    union lc_str    name;       /* library's path name */
    unsigned long   nmodules;   /* number of modules in library */
    union lc_str    linked_modules; /* bit vector of linked modules */
};

/*
 * A program that uses a dynamic linker contains a dylinker_command to identify
 * the name of the dynamic linker (LC_LOAD_DYLINKER).  And a dynamic linker
 * contains a dylinker_command to identify the dynamic linker (LC_ID_DYLINKER).
 * A file can have at most one of these.
 */
struct dylinker_command {
    unsigned long   cmd;        /* LC_ID_DYLINKER or LC_LOAD_DYLINKER */
    unsigned long   cmdsize;    /* includes pathname string */
    union lc_str    name;       /* dynamic linker's path name */
};

/*
 * Thread commands contain machine-specific data structures suitable for
 * use in the thread state primitives.  The machine specific data structures
 * follow the struct thread_command as follows.
 * Each flavor of machine specific data structure is preceded by an unsigned
 * long constant for the flavor of that data structure, an unsigned long
 * that is the count of longs of the size of the state data structure and then
 * the state data structure follows.  This triple may be repeated for many
 * flavors.  The constants for the flavors, counts and state data structure
 * definitions are expected to be in the header file <machine/thread_status.h>.
 * These machine specific data structures sizes must be multiples of
 * 4 bytes  The cmdsize reflects the total size of the thread_command
 * and all of the sizes of the constants for the flavors, counts and state
 * data structures.
 *
 * For executable objects that are unix processes there will be one
 * thread_command (cmd == LC_UNIXTHREAD) created for it by the link-editor.
 * This is the same as a LC_THREAD, except that a stack is automatically
 * created (based on the shell's limit for the stack size).  Command arguments
 * and environment variables are copied onto that stack.
 */
struct thread_command {
    unsigned long   cmd;        /* LC_THREAD or  LC_UNIXTHREAD */
    unsigned long   cmdsize;    /* total size of this command */
    /* unsigned long flavor        flavor of thread state */
    /* unsigned long count         count of longs in thread state */
    /* struct XXX_thread_state state   thread state for this flavor */
    /* ... */
};

/*
 * The routines command contains the address of the dynamic shared library 
 * initialization routine and an index into the module table for the module
 * that defines the routine.  Before any modules are used from the library the
 * dynamic linker fully binds the module that defines the initialization routine
 * and then calls it.  This gets called before any module initialization
 * routines (used for C++ static constructors) in the library.
 */
struct routines_command {
    unsigned long   cmd;        /* LC_ROUTINES */
    unsigned long   cmdsize;    /* total size of this command */
    unsigned long   init_address;   /* address of initialization routine */
    unsigned long   init_module;    /* index into the module table that */
                        /*  the init routine is defined in */
    unsigned long   reserved1;
    unsigned long   reserved2;
    unsigned long   reserved3;
    unsigned long   reserved4;
    unsigned long   reserved5;
    unsigned long   reserved6;
};

/*
 * The symtab_command contains the offsets and sizes of the link-edit 4.3BSD
 * "stab" style symbol table information as described in the header files
 * <nlist.h> and <stab.h>.
 */
struct symtab_command {
    unsigned long   cmd;        /* LC_SYMTAB */
    unsigned long   cmdsize;    /* sizeof(struct symtab_command) */
    unsigned long   symoff;     /* symbol table offset */
    unsigned long   nsyms;      /* number of symbol table entries */
    unsigned long   stroff;     /* string table offset */
    unsigned long   strsize;    /* string table size in bytes */
};

/*
 * This is the second set of the symbolic information which is used to support
 * the data structures for the dynamically link editor.
 *
 * The original set of symbolic information in the symtab_command which contains
 * the symbol and string tables must also be present when this load command is
 * present.  When this load command is present the symbol table is organized
 * into three groups of symbols:
 *  local symbols (static and debugging symbols) - grouped by module
 *  defined external symbols - grouped by module (sorted by name if not lib)
 *  undefined external symbols (sorted by name if MH_BINDATLOAD is not set,
 *                      and in order the were seen by the static
 *                  linker if MH_BINDATLOAD is set)
 * In this load command there are offsets and counts to each of the three groups
 * of symbols.
 *
 * This load command contains a the offsets and sizes of the following new
 * symbolic information tables:
 *  table of contents
 *  module table
 *  reference symbol table
 *  indirect symbol table
 * The first three tables above (the table of contents, module table and
 * reference symbol table) are only present if the file is a dynamically linked
 * shared library.  For executable and object modules, which are files
 * containing only one module, the information that would be in these three
 * tables is determined as follows:
 *  table of contents - the defined external symbols are sorted by name
 *  module table - the file contains only one module so everything in the
 *             file is part of the module.
 *  reference symbol table - is the defined and undefined external symbols
 *
 * For dynamically linked shared library files this load command also contains
 * offsets and sizes to the pool of relocation entries for all sections
 * separated into two groups:
 *  external relocation entries
 *  local relocation entries
 * For executable and object modules the relocation entries continue to hang
 * off the section structures.
 */
struct dysymtab_command {
    unsigned long cmd;      /* LC_DYSYMTAB */
    unsigned long cmdsize;  /* sizeof(struct dysymtab_command) */

    /*
     * The symbols indicated by symoff and nsyms of the LC_SYMTAB load command
     * are grouped into the following three groups:
     *    local symbols (further grouped by the module they are from)
     *    defined external symbols (further grouped by the module they are from)
     *    undefined symbols
     *
     * The local symbols are used only for debugging.  The dynamic binding
     * process may have to use them to indicate to the debugger the local
     * symbols for a module that is being bound.
     *
     * The last two groups are used by the dynamic binding process to do the
     * binding (indirectly through the module table and the reference symbol
     * table when this is a dynamically linked shared library file).
     */
    unsigned long ilocalsym;    /* index to local symbols */
    unsigned long nlocalsym;    /* number of local symbols */

    unsigned long iextdefsym;   /* index to externally defined symbols */
    unsigned long nextdefsym;   /* number of externally defined symbols */

    unsigned long iundefsym;    /* index to undefined symbols */
    unsigned long nundefsym;    /* number of undefined symbols */

    /*
     * For the for the dynamic binding process to find which module a symbol
     * is defined in the table of contents is used (analogous to the ranlib
     * structure in an archive) which maps defined external symbols to modules
     * they are defined in.  This exists only in a dynamically linked shared
     * library file.  For executable and object modules the defined external
     * symbols are sorted by name and is use as the table of contents.
     */
    unsigned long tocoff;   /* file offset to table of contents */
    unsigned long ntoc;     /* number of entries in table of contents */

    /*
     * To support dynamic binding of "modules" (whole object files) the symbol
     * table must reflect the modules that the file was created from.  This is
     * done by having a module table that has indexes and counts into the merged
     * tables for each module.  The module structure that these two entries
     * refer to is described below.  This exists only in a dynamically linked
     * shared library file.  For executable and object modules the file only
     * contains one module so everything in the file belongs to the module.
     */
    unsigned long modtaboff;    /* file offset to module table */
    unsigned long nmodtab;  /* number of module table entries */

    /*
     * To support dynamic module binding the module structure for each module
     * indicates the external references (defined and undefined) each module
     * makes.  For each module there is an offset and a count into the
     * reference symbol table for the symbols that the module references.
     * This exists only in a dynamically linked shared library file.  For
     * executable and object modules the defined external symbols and the
     * undefined external symbols indicates the external references.
     */
    unsigned long extrefsymoff;  /* offset to referenced symbol table */
    unsigned long nextrefsyms;   /* number of referenced symbol table entries */

    /*
     * The sections that contain "symbol pointers" and "routine stubs" have
     * indexes and (implied counts based on the size of the section and fixed
     * size of the entry) into the "indirect symbol" table for each pointer
     * and stub.  For every section of these two types the index into the
     * indirect symbol table is stored in the section header in the field
     * reserved1.  An indirect symbol table entry is simply a 32bit index into
     * the symbol table to the symbol that the pointer or stub is referring to.
     * The indirect symbol table is ordered to match the entries in the section.
     */
    unsigned long indirectsymoff; /* file offset to the indirect symbol table */
    unsigned long nindirectsyms;  /* number of indirect symbol table entries */

    /*
     * To support relocating an individual module in a library file quickly the
     * external relocation entries for each module in the library need to be
     * accessed efficiently.  Since the relocation entries can't be accessed
     * through the section headers for a library file they are separated into
     * groups of local and external entries further grouped by module.  In this
     * case the presents of this load command who's extreloff, nextrel,
     * locreloff and nlocrel fields are non-zero indicates that the relocation
     * entries of non-merged sections are not referenced through the section
     * structures (and the reloff and nreloc fields in the section headers are
     * set to zero).
     *
     * Since the relocation entries are not accessed through the section headers
     * this requires the r_address field to be something other than a section
     * offset to identify the item to be relocated.  In this case r_address is
     * set to the offset from the vmaddr of the first LC_SEGMENT command.
     * For MH_SPLIT_SEGS images r_address is set to the the offset from the
     * vmaddr of the first read-write LC_SEGMENT command.
     *
     * The relocation entries are grouped by module and the module table
     * entries have indexes and counts into them for the group of external
     * relocation entries for that the module.
     *
     * For sections that are merged across modules there must not be any
     * remaining external relocation entries for them (for merged sections
     * remaining relocation entries must be local).
     */
    unsigned long extreloff;    /* offset to external relocation entries */
    unsigned long nextrel;  /* number of external relocation entries */

    /*
     * All the local relocation entries are grouped together (they are not
     * grouped by their module since they are only used if the object is moved
     * from it staticly link edited address).
     */
    unsigned long locreloff;    /* offset to local relocation entries */
    unsigned long nlocrel;  /* number of local relocation entries */

};  

/*
 * An indirect symbol table entry is simply a 32bit index into the symbol table 
 * to the symbol that the pointer or stub is refering to.  Unless it is for a
 * non-lazy symbol pointer section for a defined symbol which strip(1) as 
 * removed.  In which case it has the value INDIRECT_SYMBOL_LOCAL.  If the
 * symbol was also absolute INDIRECT_SYMBOL_ABS is or'ed with that.
 */
#define INDIRECT_SYMBOL_LOCAL   0x80000000
#define INDIRECT_SYMBOL_ABS 0x40000000


/* a table of contents entry */
struct dylib_table_of_contents {
    unsigned long symbol_index; /* the defined external symbol
                   (index into the symbol table) */
    unsigned long module_index; /* index into the module table this symbol
                   is defined in */
};  

/* a module table entry */
struct dylib_module {
    unsigned long module_name;  /* the module name (index into string table) */

    unsigned long iextdefsym;   /* index into externally defined symbols */
    unsigned long nextdefsym;   /* number of externally defined symbols */
    unsigned long irefsym;  /* index into reference symbol table */
    unsigned long nrefsym;  /* number of reference symbol table entries */
    unsigned long ilocalsym;    /* index into symbols for local symbols */
    unsigned long nlocalsym;    /* number of local symbols */

    unsigned long iextrel;  /* index into external relocation entries */
    unsigned long nextrel;  /* number of external relocation entries */

    unsigned long iinit_iterm;  /* low 16 bits are the index into the init
                   section, high 16 bits are the index into
                       the term section */
    unsigned long ninit_nterm;  /* low 16 bits are the number of init section
                   entries, high 16 bits are the number of
                   term section entries */

    unsigned long       /* for this module address of the start of */
    objc_module_info_addr;  /*  the (__OBJC,__module_info) section */
    unsigned long       /* for this module size of */
    objc_module_info_size;  /*  the (__OBJC,__module_info) section */
};  

/* 
 * The entries in the reference symbol table are used when loading the module
 * (both by the static and dynamic link editors) and if the module is unloaded
 * or replaced.  Therefore all external symbols (defined and undefined) are
 * listed in the module's reference table.  The flags describe the type of
 * reference that is being made.  The constants for the flags are defined in
 * <mach-o/nlist.h> as they are also used for symbol table entries.
 */
struct dylib_reference {
    unsigned long isym:24,  /* index into the symbol table */
              flags:8;  /* flags to indicate the type of reference */
};

/*
 * The twolevel_hints_command contains the offset and number of hints in the
 * two-level namespace lookup hints table.
 */
struct twolevel_hints_command {
    unsigned long cmd;      /* LC_TWOLEVEL_HINTS */
    unsigned long cmdsize;  /* sizeof(struct twolevel_hints_command) */
    unsigned long offset;   /* offset to the hint table */
    unsigned long nhints;   /* number of hints in the hint table */
};

/*
 * The entries in the two-level namespace lookup hints table are twolevel_hint
 * structs.  These provide hints to the dynamic link editor where to start
 * looking for an undefined symbol in a two-level namespace image.  The
 * isub_image field is an index into the sub-images (sub-frameworks and
 * sub-umbrellas list) that made up the two-level image that the undefined
 * symbol was found in when it was built by the static link editor.  If
 * isub-image is 0 the the symbol is expected to be defined in library and not
 * in the sub-images.  If isub-image is non-zero it is an index into the array
 * of sub-images for the umbrella with the first index in the sub-images being
 * 1. The array of sub-images is the ordered list of sub-images of the umbrella
 * that would be searched for a symbol that has the umbrella recorded as its
 * primary library.  The table of contents index is an index into the
 * library's table of contents.  This is used as the starting point of the
 * binary search or a directed linear search.
 */
struct twolevel_hint {
    unsigned long 
    isub_image:8,   /* index into the sub images */
    itoc:24;    /* index into the table of contents */
};

/*
 * The prebind_cksum_command contains the value of the original check sum for
 * prebound files or zero.  When a prebound file is first created or modified
 * for other than updating its prebinding information the value of the check sum
 * is set to zero.  When the file has it prebinding re-done and if the value of
 * the check sum is zero the original check sum is calculated and stored in
 * cksum field of this load command in the output file.  If when the prebinding
 * is re-done and the cksum field is non-zero it is left unchanged from the
 * input file.
 */
struct prebind_cksum_command {
    unsigned long cmd;      /* LC_PREBIND_CKSUM */
    unsigned long cmdsize;  /* sizeof(struct prebind_cksum_command) */
    unsigned long cksum;    /* the check sum or zero */
};

/*
 * The symseg_command contains the offset and size of the GNU style
 * symbol table information as described in the header file <symseg.h>.
 * The symbol roots of the symbol segments must also be aligned properly
 * in the file.  So the requirement of keeping the offsets aligned to a
 * multiple of a 4 bytes translates to the length field of the symbol
 * roots also being a multiple of a long.  Also the padding must again be
 * zeroed. (THIS IS OBSOLETE and no longer supported).
 */
struct symseg_command {
    unsigned long   cmd;        /* LC_SYMSEG */
    unsigned long   cmdsize;    /* sizeof(struct symseg_command) */
    unsigned long   offset;     /* symbol segment offset */
    unsigned long   size;       /* symbol segment size in bytes */
};

/*
 * The ident_command contains a free format string table following the
 * ident_command structure.  The strings are null terminated and the size of
 * the command is padded out with zero bytes to a multiple of 4 bytes/
 * (THIS IS OBSOLETE and no longer supported).
 */
struct ident_command {
    unsigned long cmd;      /* LC_IDENT */
    unsigned long cmdsize;      /* strings that follow this command */
};

/*
 * The fvmfile_command contains a reference to a file to be loaded at the
 * specified virtual address.  (Presently, this command is reserved for
 * internal use.  The kernel ignores this command when loading a program into
 * memory).
 */
struct fvmfile_command {
    unsigned long cmd;      /* LC_FVMFILE */
    unsigned long cmdsize;      /* includes pathname string */
    union lc_str    name;       /* files pathname */
    unsigned long   header_addr;    /* files virtual address */
};

#endif /* _MACHO_LOADER_H_ */

---