Magic-Mirror/radare2
1
0
Fork 0
mirror of https://github.com/radareorg/radare2.git synced 2024-12-12 23:46:36 +00:00
Code Issues Actions 7 Packages Projects Releases Wiki Activity
14b3479658
radare2/libr/bin/format/mach0/mach0_specs.h
Nibble 89a63b5c3a * Fix segfault parsing imports in mach-o 
* Simplify the output of the command 'S'
* Update TODO
2010-07-11 13:15:18 +02:00

1728 lines
70 KiB
C
Raw Blame History

/* radare - LGPL - Copyright 2010 nibble at develsec.org */
#undef MACH0_
#undef MH_MAGIC
#undef MH_CIGAM
#if R_BIN_MACH064
#define MACH0_(name) name##_64
#define MH_MAGIC 0xfeedfacf
#define MH_CIGAM 0xcffaedfe
#define FAT_CIGAM 0xbabefeca /* XXX */
#else
#define MACH0_(name) name
#define MH_MAGIC 0xfeedface
#define MH_CIGAM 0xcefaedfe
#define FAT_CIGAM 0xcafebabe
#endif
#ifndef _INCLUDE_MACHO_SPECS_H_
#define _INCLUDE_MACHO_SPECS_H_
typedef unsigned long long uint64_t;
typedef unsigned int uint32_t;
typedef unsigned short uint16_t;
typedef unsigned char uint8_t;
typedef int cpu_type_t;
typedef int cpu_subtype_t;
typedef int vm_prot_t;
/*
* This file describes the format of mach object files.
#include <stdint.h>
*/
/*
* <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>
*/
/*
* <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 32-bit mach header appears at the very beginning of the object file for
* 32-bit architectures.
*/
struct mach_header {
uint32_t magic; /* mach magic number identifier */
cpu_type_t cputype; /* cpu specifier */
cpu_subtype_t cpusubtype; /* machine specifier */
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 */
};
/*
* The 64-bit mach header appears at the very beginning of object files for
* 64-bit architectures.
*/
struct mach_header_64 {
uint32_t magic; /* mach magic number identifier */
cpu_type_t cputype; /* cpu specifier */
cpu_subtype_t cpusubtype; /* machine specifier */
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; /* reserved */
};
/*
* 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 */
#define MH_DSYM 0xa /* companion file with only debug */
/* sections */
/* 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_SUBSECTIONS_VIA_SYMBOLS 0x2000/* safe to divide up the sections into
sub-sections via symbols for dead
code stripping */
#define MH_CANONICAL 0x4000 /* the binary has been canonicalized
via the unprebind operation */
#define MH_WEAK_DEFINES 0x8000 /* the final linked image contains
external weak symbols */
#define MH_BINDS_TO_WEAK 0x10000 /* the final linked image uses
weak symbols */
#define MH_ALLOW_STACK_EXECUTION 0x20000/* When this bit is set, all stacks
in the task will be given stack
execution privilege. Only used in
MH_EXECUTE filetypes. */
/*
* Capability bits used in the definition of cpu_type.
*/
#define CPU_ARCH_MASK 0xff000000 /* mask for architecture bits */
#define CPU_ARCH_ABI64 0x01000000 /* 64 bit ABI */
/*
* Machine types known by all.
*/
#define CPU_TYPE_ANY ((cpu_type_t) -1)
#define CPU_TYPE_VAX ((cpu_type_t) 1)
#define CPU_TYPE_MC680x0 ((cpu_type_t) 6)
#define CPU_TYPE_X86 ((cpu_type_t) 7)
#define CPU_TYPE_MIPS ((cpu_type_t) 8)
#define CPU_TYPE_I386 CPU_TYPE_X86 /* compatibility */
#define CPU_TYPE_X86_64 (CPU_TYPE_X86 | CPU_ARCH_ABI64)
#define CPU_TYPE_MC98000 ((cpu_type_t) 10)
#define CPU_TYPE_HPPA ((cpu_type_t) 11)
#define CPU_TYPE_ARM ((cpu_type_t) 12)
#define CPU_TYPE_MC88000 ((cpu_type_t) 13)
#define CPU_TYPE_SPARC ((cpu_type_t) 14)
#define CPU_TYPE_I860 ((cpu_type_t) 15)
#define CPU_TYPE_POWERPC ((cpu_type_t) 18)
#define CPU_TYPE_POWERPC64 (CPU_TYPE_POWERPC | CPU_ARCH_ABI64)
/*
* Machine subtypes (these are defined here, instead of in a machine
* dependent directory, so that any program can get all definitions
* regardless of where is it compiled).
*/
/*
* Object files that are hand-crafted to run on any
* implementation of an architecture are tagged with
* CPU_SUBTYPE_MULTIPLE. This functions essentially the same as
* the "ALL" subtype of an architecture except that it allows us
* to easily find object files that may need to be modified
* whenever a new implementation of an architecture comes out.
*
* It is the responsibility of the implementor to make sure the
* software handles unsupported implementations elegantly.
*/
#define CPU_SUBTYPE_MULTIPLE ((cpu_subtype_t) -1)
#define CPU_SUBTYPE_LITTLE_ENDIAN ((cpu_subtype_t) 0)
#define CPU_SUBTYPE_BIG_ENDIAN ((cpu_subtype_t) 1)
/*
* Machine threadtypes.
* This is none - not defined - for most machine types/subtypes.
*/
#define CPU_THREADTYPE_NONE ((cpu_threadtype_t) 0)
/*
* VAX subtypes (these do *not* necessary conform to the actual cpu
* ID assigned by DEC available via the SID register).
*/
#define CPU_SUBTYPE_VAX_ALL ((cpu_subtype_t) 0)
#define CPU_SUBTYPE_VAX780 ((cpu_subtype_t) 1)
#define CPU_SUBTYPE_VAX785 ((cpu_subtype_t) 2)
#define CPU_SUBTYPE_VAX750 ((cpu_subtype_t) 3)
#define CPU_SUBTYPE_VAX730 ((cpu_subtype_t) 4)
#define CPU_SUBTYPE_UVAXI ((cpu_subtype_t) 5)
#define CPU_SUBTYPE_UVAXII ((cpu_subtype_t) 6)
#define CPU_SUBTYPE_VAX8200 ((cpu_subtype_t) 7)
#define CPU_SUBTYPE_VAX8500 ((cpu_subtype_t) 8)
#define CPU_SUBTYPE_VAX8600 ((cpu_subtype_t) 9)
#define CPU_SUBTYPE_VAX8650 ((cpu_subtype_t) 10)
#define CPU_SUBTYPE_VAX8800 ((cpu_subtype_t) 11)
#define CPU_SUBTYPE_UVAXIII ((cpu_subtype_t) 12)
/*
* 680x0 subtypes
*
* The subtype definitions here are unusual for historical reasons.
* NeXT used to consider 68030 code as generic 68000 code. For
* backwards compatability:
*
* CPU_SUBTYPE_MC68030 symbol has been preserved for source code
* compatability.
*
* CPU_SUBTYPE_MC680x0_ALL has been defined to be the same
* subtype as CPU_SUBTYPE_MC68030 for binary comatability.
*
* CPU_SUBTYPE_MC68030_ONLY has been added to allow new object
* files to be tagged as containing 68030-specific instructions.
*/
#define CPU_SUBTYPE_MC680x0_ALL ((cpu_subtype_t) 1)
#define CPU_SUBTYPE_MC68030 ((cpu_subtype_t) 1) /* compat */
#define CPU_SUBTYPE_MC68040 ((cpu_subtype_t) 2)
#define CPU_SUBTYPE_MC68030_ONLY ((cpu_subtype_t) 3)
/*
* I386 subtypes
*/
#define CPU_SUBTYPE_INTEL(f, m) ((cpu_subtype_t) (f) + ((m) << 4))
#define CPU_SUBTYPE_I386_ALL CPU_SUBTYPE_INTEL(3, 0)
#define CPU_SUBTYPE_386 CPU_SUBTYPE_INTEL(3, 0)
#define CPU_SUBTYPE_486 CPU_SUBTYPE_INTEL(4, 0)
#define CPU_SUBTYPE_486SX CPU_SUBTYPE_INTEL(4, 8) // 8 << 4 = 128
#define CPU_SUBTYPE_586 CPU_SUBTYPE_INTEL(5, 0)
#define CPU_SUBTYPE_PENT CPU_SUBTYPE_INTEL(5, 0)
#define CPU_SUBTYPE_PENTPRO CPU_SUBTYPE_INTEL(6, 1)
#define CPU_SUBTYPE_PENTII_M3 CPU_SUBTYPE_INTEL(6, 3)
#define CPU_SUBTYPE_PENTII_M5 CPU_SUBTYPE_INTEL(6, 5)
#define CPU_SUBTYPE_CELERON CPU_SUBTYPE_INTEL(7, 6)
#define CPU_SUBTYPE_CELERON_MOBILE CPU_SUBTYPE_INTEL(7, 7)
#define CPU_SUBTYPE_PENTIUM_3 CPU_SUBTYPE_INTEL(8, 0)
#define CPU_SUBTYPE_PENTIUM_3_M CPU_SUBTYPE_INTEL(8, 1)
#define CPU_SUBTYPE_PENTIUM_3_XEON CPU_SUBTYPE_INTEL(8, 2)
#define CPU_SUBTYPE_PENTIUM_M CPU_SUBTYPE_INTEL(9, 0)
#define CPU_SUBTYPE_PENTIUM_4 CPU_SUBTYPE_INTEL(10, 0)
#define CPU_SUBTYPE_PENTIUM_4_M CPU_SUBTYPE_INTEL(10, 1)
#define CPU_SUBTYPE_ITANIUM CPU_SUBTYPE_INTEL(11, 0)
#define CPU_SUBTYPE_ITANIUM_2 CPU_SUBTYPE_INTEL(11, 1)
#define CPU_SUBTYPE_XEON CPU_SUBTYPE_INTEL(12, 0)
#define CPU_SUBTYPE_XEON_MP CPU_SUBTYPE_INTEL(12, 1)
#define CPU_SUBTYPE_INTEL_FAMILY(x) ((x) & 15)
#define CPU_SUBTYPE_INTEL_FAMILY_MAX 15
#define CPU_SUBTYPE_INTEL_MODEL(x) ((x) >> 4)
#define CPU_SUBTYPE_INTEL_MODEL_ALL 0
/*
* X86 subtypes.
*/
#define CPU_SUBTYPE_X86_ALL ((cpu_subtype_t)3)
#define CPU_SUBTYPE_X86_64_ALL ((cpu_subtype_t)3)
#define CPU_SUBTYPE_X86_ARCH1 ((cpu_subtype_t)4)
#define CPU_THREADTYPE_INTEL_HTT ((cpu_threadtype_t) 1)
/*
* Mips subtypes.
*/
#define CPU_SUBTYPE_MIPS_ALL ((cpu_subtype_t) 0)
#define CPU_SUBTYPE_MIPS_R2300 ((cpu_subtype_t) 1)
#define CPU_SUBTYPE_MIPS_R2600 ((cpu_subtype_t) 2)
#define CPU_SUBTYPE_MIPS_R2800 ((cpu_subtype_t) 3)
#define CPU_SUBTYPE_MIPS_R2000a ((cpu_subtype_t) 4) /* pmax */
#define CPU_SUBTYPE_MIPS_R2000 ((cpu_subtype_t) 5)
#define CPU_SUBTYPE_MIPS_R3000a ((cpu_subtype_t) 6) /* 3max */
#define CPU_SUBTYPE_MIPS_R3000 ((cpu_subtype_t) 7)
/*
* MC98000 (PowerPC) subtypes
*/
#define CPU_SUBTYPE_MC98000_ALL ((cpu_subtype_t) 0)
#define CPU_SUBTYPE_MC98601 ((cpu_subtype_t) 1)
/*
* HPPA subtypes for Hewlett-Packard HP-PA family of
* risc processors. Port by NeXT to 700 series.
*/
#define CPU_SUBTYPE_HPPA_ALL ((cpu_subtype_t) 0)
#define CPU_SUBTYPE_HPPA_7100 ((cpu_subtype_t) 0) /* compat */
#define CPU_SUBTYPE_HPPA_7100LC ((cpu_subtype_t) 1)
/*
* MC88000 subtypes.
*/
#define CPU_SUBTYPE_MC88000_ALL ((cpu_subtype_t) 0)
#define CPU_SUBTYPE_MC88100 ((cpu_subtype_t) 1)
#define CPU_SUBTYPE_MC88110 ((cpu_subtype_t) 2)
/*
* SPARC subtypes
*/
#define CPU_SUBTYPE_SPARC_ALL ((cpu_subtype_t) 0)
/*
* I860 subtypes
*/
#define CPU_SUBTYPE_I860_ALL ((cpu_subtype_t) 0)
#define CPU_SUBTYPE_I860_860 ((cpu_subtype_t) 1)
/*
* PowerPC subtypes
*/
#define CPU_SUBTYPE_POWERPC_ALL ((cpu_subtype_t) 0)
#define CPU_SUBTYPE_POWERPC_601 ((cpu_subtype_t) 1)
#define CPU_SUBTYPE_POWERPC_602 ((cpu_subtype_t) 2)
#define CPU_SUBTYPE_POWERPC_603 ((cpu_subtype_t) 3)
#define CPU_SUBTYPE_POWERPC_603e ((cpu_subtype_t) 4)
#define CPU_SUBTYPE_POWERPC_603ev ((cpu_subtype_t) 5)
#define CPU_SUBTYPE_POWERPC_604 ((cpu_subtype_t) 6)
#define CPU_SUBTYPE_POWERPC_604e ((cpu_subtype_t) 7)
#define CPU_SUBTYPE_POWERPC_620 ((cpu_subtype_t) 8)
#define CPU_SUBTYPE_POWERPC_750 ((cpu_subtype_t) 9)
#define CPU_SUBTYPE_POWERPC_7400 ((cpu_subtype_t) 10)
#define CPU_SUBTYPE_POWERPC_7450 ((cpu_subtype_t) 11)
#define CPU_SUBTYPE_POWERPC_970 ((cpu_subtype_t) 100)
/*
* 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 for 32-bit architectures
* MUST be a multiple of 4 bytes and for 64-bit architectures MUST be a multiple
* of 8 bytes (these are 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 {
uint32_t cmd; /* type of load command */
uint32_t 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)
#define LC_SEGMENT_64 0x19 /* 64-bit segment of this file to be
mapped */
#define LC_ROUTINES_64 0x1a /* 64-bit image routines */
#define LC_UUID 0x1b /* the uuid */
#define LC_CODE_SIGNATURE 0x1d /* local of code signature */
/*
* 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 {
uint32_t offset; /* offset to the string */
#ifndef __LP64__
char *ptr; /* pointer to the string */
#endif
};
/*
* 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 { /* for 32-bit architectures */
uint32_t cmd; /* LC_SEGMENT */
uint32_t cmdsize; /* includes sizeof section structs */
char segname[16]; /* segment name */
uint32_t vmaddr; /* memory address of this segment */
uint32_t vmsize; /* memory size of this segment */
uint32_t fileoff; /* file offset of this segment */
uint32_t filesize; /* amount to map from the file */
vm_prot_t maxprot; /* maximum VM protection */
vm_prot_t initprot; /* initial VM protection */
uint32_t nsects; /* number of sections in segment */
uint32_t flags; /* flags */
};
/*
* The 64-bit segment load command indicates that a part of this file is to be
* mapped into a 64-bit task's address space. If the 64-bit segment has
* sections then section_64 structures directly follow the 64-bit segment
* command and their size is reflected in cmdsize.
*/
struct segment_command_64 { /* for 64-bit architectures */
uint32_t cmd; /* LC_SEGMENT_64 */
uint32_t cmdsize; /* includes sizeof section_64 structs */
char segname[16]; /* segment name */
uint64_t vmaddr; /* memory address of this segment */
uint64_t vmsize; /* memory size of this segment */
uint64_t fileoff; /* file offset of this segment */
uint64_t filesize; /* amount to map from the file */
vm_prot_t maxprot; /* maximum VM protection */
vm_prot_t initprot; /* initial VM protection */
uint32_t nsects; /* number of sections in segment */
uint32_t 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*/
#define SG_PROTECTED_VERSION_1 0x8 /* This segment is protected. If the
segment starts at file offset 0, the
first page of the segment is not
protected. All other pages of the
segment are protected. */
/*
* 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 gigabyte zero fill sections, those with the section
* type S_GB_ZEROFILL, can only be in a segment with sections of this type.
* These segments are then placed after all other segments.
*
* 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 { /* for 32-bit architectures */
char sectname[16]; /* name of this section */
char segname[16]; /* segment this section goes in */
uint32_t addr; /* memory address of this section */
uint32_t size; /* size in bytes of this section */
uint32_t offset; /* file offset of this section */
uint32_t align; /* section alignment (power of 2) */
uint32_t reloff; /* file offset of relocation entries */
uint32_t nreloc; /* number of relocation entries */
uint32_t flags; /* flags (section type and attributes)*/
uint32_t reserved1; /* reserved (for offset or index) */
uint32_t reserved2; /* reserved (for count or sizeof) */
};
struct section_64 { /* for 64-bit architectures */
char sectname[16]; /* name of this section */
char segname[16]; /* segment this section goes in */
uint64_t addr; /* memory address of this section */
uint64_t size; /* size in bytes of this section */
uint32_t offset; /* file offset of this section */
uint32_t align; /* section alignment (power of 2) */
uint32_t reloff; /* file offset of relocation entries */
uint32_t nreloc; /* number of relocation entries */
uint32_t flags; /* flags (section type and attributes)*/
uint32_t reserved1; /* reserved (for offset or index) */
uint32_t reserved2; /* reserved (for count or sizeof) */
uint32_t reserved3; /* 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 */
#define S_GB_ZEROFILL 0xc /* zero fill on demand section
(that can be larger than 4
gigabytes) */
#define S_INTERPOSING 0xd /* section with only pairs of
function pointers for
interposing */
#define S_16BYTE_LITERALS 0xe /* section with only 16 byte literals */
/*
* 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 S_ATTR_NO_DEAD_STRIP 0x10000000 /* no dead stripping */
#define S_ATTR_LIVE_SUPPORT 0x08000000 /* blocks are live if they
reference live blocks */
#define S_ATTR_SELF_MODIFYING_CODE 0x04000000 /* Used with i386 code stubs
written on by dyld */
/*
* If a segment contains any sections marked with S_ATTR_DEBUG then all
* sections in that segment must have this attribute. No section other than
* a section marked with this attribute may reference the contents of this
* section. A section with this attribute may contain no symbols and must have
* a section type S_REGULAR. The static linker will not copy section contents
* from sections with this attribute into its output file. These sections
* generally contain DWARF debugging info.
*/
#define S_ATTR_DEBUG 0x02000000 /* a debug section */
#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 */
#define SEG_IMPORT "__IMPORT" /* the segment for the self (dyld) */
/* modifing code stubs that has read, */
/* write and execute permissions */
/*
* 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. (THIS IS OBSOLETE and no longer supported).
*/
struct fvmlib {
union lc_str name; /* library's target pathname */
uint32_t minor_version; /* library's minor version number */
uint32_t 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.
* (THIS IS OBSOLETE and no longer supported).
*/
struct fvmlib_command {
uint32_t cmd; /* LC_IDFVMLIB or LC_LOADFVMLIB */
uint32_t 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 */
uint32_t timestamp; /* library's build time stamp */
uint32_t current_version; /* library's current version number */
uint32_t 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 {
uint32_t cmd; /* LC_ID_DYLIB, LC_LOAD_{,WEAK_}DYLIB */
uint32_t 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 {
uint32_t cmd; /* LC_SUB_FRAMEWORK */
uint32_t 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 {
uint32_t cmd; /* LC_SUB_CLIENT */
uint32_t 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 {
uint32_t cmd; /* LC_SUB_UMBRELLA */
uint32_t 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 {
uint32_t cmd; /* LC_SUB_LIBRARY */
uint32_t 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 {
uint32_t cmd; /* LC_PREBOUND_DYLIB */
uint32_t cmdsize; /* includes strings */
union lc_str name; /* library's path name */
uint32_t 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 {
uint32_t cmd; /* LC_ID_DYLINKER or LC_LOAD_DYLINKER */
uint32_t 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 uint32_t
* 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 {
uint32_t cmd; /* LC_THREAD or LC_UNIXTHREAD */
uint32_t cmdsize; /* total size of this command */
uint32_t flavor;
uint32_t count;
/* uint32_t flavor flavor of thread state */
/* uint32_t count count of longs in thread state */
/* struct XXX_thread_state state thread state for this flavor */
/* ... */
};
struct x86_thread_state32 {
uint32_t eax;
uint32_t ebx;
uint32_t ecx;
uint32_t edx;
uint32_t edi;
uint32_t esi;
uint32_t ebp;
uint32_t esp;
uint32_t ss;
uint32_t eflags;
uint32_t eip;
uint32_t cs;
uint32_t ds;
uint32_t es;
uint32_t fs;
uint32_t gs;
} ;
struct x86_thread_state64 {
uint64_t rax;
uint64_t rbx;
uint64_t rcx;
uint64_t rdx;
uint64_t rdi;
uint64_t rsi;
uint64_t rbp;
uint64_t rsp;
uint64_t r8;
uint64_t r9;
uint64_t r10;
uint64_t r11;
uint64_t r12;
uint64_t r13;
uint64_t r14;
uint64_t r15;
uint64_t rip;
uint64_t rflags;
uint64_t cs;
uint64_t fs;
uint64_t gs;
};
#define X86_THREAD_STATE32 1
#define X86_THREAD_STATE64 4
struct ppc_thread_state32 {
uint32_t srr0; /* Instruction address register (PC) */
uint32_t srr1; /* Machine state register (supervisor) */
uint32_t r0;
uint32_t r1;
uint32_t r2;
uint32_t r3;
uint32_t r4;
uint32_t r5;
uint32_t r6;
uint32_t r7;
uint32_t r8;
uint32_t r9;
uint32_t r10;
uint32_t r11;
uint32_t r12;
uint32_t r13;
uint32_t r14;
uint32_t r15;
uint32_t r16;
uint32_t r17;
uint32_t r18;
uint32_t r19;
uint32_t r20;
uint32_t r21;
uint32_t r22;
uint32_t r23;
uint32_t r24;
uint32_t r25;
uint32_t r26;
uint32_t r27;
uint32_t r28;
uint32_t r29;
uint32_t r30;
uint32_t r31;
uint32_t cr; /* Condition register */
uint32_t xer; /* User's integer exception register */
uint32_t lr; /* Link register */
uint32_t ctr; /* Count register */
uint32_t mq; /* MQ register (601 only) */
uint32_t vrsave; /* Vector Save Register */
};
struct ppc_thread_state64 {
uint64_t srr0; /* Instruction address register (PC) */
uint64_t srr1; /* Machine state register (supervisor) */
uint64_t r0;
uint64_t r1;
uint64_t r2;
uint64_t r3;
uint64_t r4;
uint64_t r5;
uint64_t r6;
uint64_t r7;
uint64_t r8;
uint64_t r9;
uint64_t r10;
uint64_t r11;
uint64_t r12;
uint64_t r13;
uint64_t r14;
uint64_t r15;
uint64_t r16;
uint64_t r17;
uint64_t r18;
uint64_t r19;
uint64_t r20;
uint64_t r21;
uint64_t r22;
uint64_t r23;
uint64_t r24;
uint64_t r25;
uint64_t r26;
uint64_t r27;
uint64_t r28;
uint64_t r29;
uint64_t r30;
uint64_t r31;
uint32_t cr; /* Condition register */
uint64_t xer; /* User's integer exception register */
uint64_t lr; /* Link register */
uint64_t ctr; /* Count register */
uint32_t vrsave; /* Vector Save Register */
};
struct arm_thread_state {
uint32_t r0;
uint32_t r1;
uint32_t r2;
uint32_t r3;
uint32_t r4;
uint32_t r5;
uint32_t r6;
uint32_t r7;
uint32_t r8;
uint32_t r9;
uint32_t r10;
uint32_t r11;
uint32_t r12;
uint32_t r13;
uint32_t r14;
uint32_t r15;
uint32_t r16; /* Apple's thread_state has this 17th reg, bug?? */
};
/*
* 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 { /* for 32-bit architectures */
uint32_t cmd; /* LC_ROUTINES */
uint32_t cmdsize; /* total size of this command */
uint32_t init_address; /* address of initialization routine */
uint32_t init_module; /* index into the module table that */
/* the init routine is defined in */
uint32_t reserved1;
uint32_t reserved2;
uint32_t reserved3;
uint32_t reserved4;
uint32_t reserved5;
uint32_t reserved6;
};
/*
* The 64-bit routines command. Same use as above.
*/
struct routines_command_64 { /* for 64-bit architectures */
uint32_t cmd; /* LC_ROUTINES_64 */
uint32_t cmdsize; /* total size of this command */
uint64_t init_address; /* address of initialization routine */
uint64_t init_module; /* index into the module table that */
/* the init routine is defined in */
uint64_t reserved1;
uint64_t reserved2;
uint64_t reserved3;
uint64_t reserved4;
uint64_t reserved5;
uint64_t 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 {
uint32_t cmd; /* LC_SYMTAB */
uint32_t cmdsize; /* sizeof(struct symtab_command) */
uint32_t symoff; /* symbol table offset */
uint32_t nsyms; /* number of symbol table entries */
uint32_t stroff; /* string table offset */
uint32_t 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 {
uint32_t cmd; /* LC_DYSYMTAB */
uint32_t 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).
*/
uint32_t ilocalsym; /* index to local symbols */
uint32_t nlocalsym; /* number of local symbols */
uint32_t iextdefsym;/* index to externally defined symbols */
uint32_t nextdefsym;/* number of externally defined symbols */
uint32_t iundefsym; /* index to undefined symbols */
uint32_t 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.
*/
uint32_t tocoff; /* file offset to table of contents */
uint32_t 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.
*/
uint32_t modtaboff; /* file offset to module table */
uint32_t 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.
*/
uint32_t extrefsymoff; /* offset to referenced symbol table */
uint32_t 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.
*/
uint32_t indirectsymoff; /* file offset to the indirect symbol table */
uint32_t 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).
*/
uint32_t extreloff; /* offset to external relocation entries */
uint32_t 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).
*/
uint32_t locreloff; /* offset to local relocation entries */
uint32_t 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 {
uint32_t symbol_index; /* the defined external symbol
(index into the symbol table) */
uint32_t module_index; /* index into the module table this symbol
is defined in */
};
/* a module table entry */
struct dylib_module {
uint32_t module_name; /* the module name (index into string table) */
uint32_t iextdefsym; /* index into externally defined symbols */
uint32_t nextdefsym; /* number of externally defined symbols */
uint32_t irefsym; /* index into reference symbol table */
uint32_t nrefsym; /* number of reference symbol table entries */
uint32_t ilocalsym; /* index into symbols for local symbols */
uint32_t nlocalsym; /* number of local symbols */
uint32_t iextrel; /* index into external relocation entries */
uint32_t nextrel; /* number of external relocation entries */
uint32_t iinit_iterm; /* low 16 bits are the index into the init
section, high 16 bits are the index into
the term section */
uint32_t ninit_nterm; /* low 16 bits are the number of init section
entries, high 16 bits are the number of
term section entries */
uint32_t /* for this module address of the start of */
objc_module_info_addr; /* the (__OBJC,__module_info) section */
uint32_t /* for this module size of */
objc_module_info_size; /* the (__OBJC,__module_info) section */
};
/* a 64-bit module table entry */
struct dylib_module_64 {
uint32_t module_name; /* the module name (index into string table) */
uint32_t iextdefsym; /* index into externally defined symbols */
uint32_t nextdefsym; /* number of externally defined symbols */
uint32_t irefsym; /* index into reference symbol table */
uint32_t nrefsym; /* number of reference symbol table entries */
uint32_t ilocalsym; /* index into symbols for local symbols */
uint32_t nlocalsym; /* number of local symbols */
uint32_t iextrel; /* index into external relocation entries */
uint32_t nextrel; /* number of external relocation entries */
uint32_t iinit_iterm; /* low 16 bits are the index into the init
section, high 16 bits are the index into
the term section */
uint32_t ninit_nterm; /* low 16 bits are the number of init section
entries, high 16 bits are the number of
term section entries */
uint32_t /* for this module size of */
objc_module_info_size; /* the (__OBJC,__module_info) section */
uint64_t /* for this module address of the start of */
objc_module_info_addr; /* 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 {
uint32_t 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 {
uint32_t cmd; /* LC_TWOLEVEL_HINTS */
uint32_t cmdsize; /* sizeof(struct twolevel_hints_command) */
uint32_t offset; /* offset to the hint table */
uint32_t 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 {
uint32_t
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 {
uint32_t cmd; /* LC_PREBIND_CKSUM */
uint32_t cmdsize; /* sizeof(struct prebind_cksum_command) */
uint32_t cksum; /* the check sum or zero */
};
/*
* The uuid load command contains a single 128-bit unique random number that
* identifies an object produced by the static link editor.
*/
struct uuid_command {
uint32_t cmd; /* LC_UUID */
uint32_t cmdsize; /* sizeof(struct uuid_command) */
uint8_t uuid[16]; /* the 128-bit uuid */
};
/*
* 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 {
uint32_t cmd; /* LC_SYMSEG */
uint32_t cmdsize; /* sizeof(struct symseg_command) */
uint32_t offset; /* symbol segment offset */
uint32_t 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 {
uint32_t cmd; /* LC_IDENT */
uint32_t 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 {
uint32_t cmd; /* LC_FVMFILE */
uint32_t cmdsize; /* includes pathname string */
union lc_str name; /* files pathname */
uint32_t header_addr; /* files virtual address */
};
/*
* Format of a symbol table entry of a Mach-O file for 32-bit architectures.
* Modified from the BSD format. The modifications from the original format
* were changing n_other (an unused field) to n_sect and the addition of the
* N_SECT type. These modifications are required to support symbols in a larger
* number of sections not just the three sections (text, data and bss) in a BSD
* file.
*/
struct nlist {
union {
#ifndef __LP64__
char *n_name; /* for use when in-core */
#endif
int32_t n_strx; /* index into the string table */
} n_un;
uint8_t n_type; /* type flag, see below */
uint8_t n_sect; /* section number or NO_SECT */
int16_t n_desc; /* see <mach-o/stab.h> */
uint32_t n_value; /* value of this symbol (or stab offset) */
};
/*
* This is the symbol table entry structure for 64-bit architectures.
*/
struct nlist_64 {
union {
uint32_t n_strx; /* index into the string table */
} n_un;
uint8_t n_type; /* type flag, see below */
uint8_t n_sect; /* section number or NO_SECT */
uint16_t n_desc; /* see <mach-o/stab.h> */
uint64_t n_value; /* value of this symbol (or stab offset) */
};
/*
* Symbols with a index into the string table of zero (n_un.n_strx == 0) are
* defined to have a null, "", name. Therefore all string indexes to non null
* names must not have a zero string index. This is bit historical information
* that has never been well documented.
*/
/*
* The n_type field really contains four fields:
* unsigned char N_STAB:3,
* N_PEXT:1,
* N_TYPE:3,
* N_EXT:1;
* which are used via the following masks.
*/
#define N_STAB 0xe0 /* if any of these bits set, a symbolic debugging entry */
#define N_PEXT 0x10 /* private external symbol bit */
#define N_TYPE 0x0e /* mask for the type bits */
#define N_EXT 0x01 /* external symbol bit, set for external symbols */
/*
* Only symbolic debugging entries have some of the N_STAB bits set and if any
* of these bits are set then it is a symbolic debugging entry (a stab). In
* which case then the values of the n_type field (the entire field) are given
* in <mach-o/stab.h>
*/
/*
* Values for N_TYPE bits of the n_type field.
*/
#define N_UNDF 0x0 /* undefined, n_sect == NO_SECT */
#define N_ABS 0x2 /* absolute, n_sect == NO_SECT */
#define N_SECT 0xe /* defined in section number n_sect */
#define N_PBUD 0xc /* prebound undefined (defined in a dylib) */
#define N_INDR 0xa /* indirect */
/*
* If the type is N_INDR then the symbol is defined to be the same as another
* symbol. In this case the n_value field is an index into the string table
* of the other symbol's name. When the other symbol is defined then they both
* take on the defined type and value.
*/
/*
* If the type is N_SECT then the n_sect field contains an ordinal of the
* section the symbol is defined in. The sections are numbered from 1 and
* refer to sections in order they appear in the load commands for the file
* they are in. This means the same ordinal may very well refer to different
* sections in different files.
*
* The n_value field for all symbol table entries (including N_STAB's) gets
* updated by the link editor based on the value of it's n_sect field and where
* the section n_sect references gets relocated. If the value of the n_sect
* field is NO_SECT then it's n_value field is not changed by the link editor.
*/
#define NO_SECT 0 /* symbol is not in any section */
#define MAX_SECT 255 /* 1 thru 255 inclusive */
/*
* Common symbols are represented by undefined (N_UNDF) external (N_EXT) types
* who's values (n_value) are non-zero. In which case the value of the n_value
* field is the size (in bytes) of the common symbol. The n_sect field is set
* to NO_SECT.
*/
/*
* To support the lazy binding of undefined symbols in the dynamic link-editor,
* the undefined symbols in the symbol table (the nlist structures) are marked
* with the indication if the undefined reference is a lazy reference or
* non-lazy reference. If both a non-lazy reference and a lazy reference is
* made to the same symbol the non-lazy reference takes precedence. A reference
* is lazy only when all references to that symbol are made through a symbol
* pointer in a lazy symbol pointer section.
*
* The implementation of marking nlist structures in the symbol table for
* undefined symbols will be to use some of the bits of the n_desc field as a
* reference type. The mask REFERENCE_TYPE will be applied to the n_desc field
* of an nlist structure for an undefined symbol to determine the type of
* undefined reference (lazy or non-lazy).
*
* The constants for the REFERENCE FLAGS are propagated to the reference table
* in a shared library file. In that case the constant for a defined symbol,
* REFERENCE_FLAG_DEFINED, is also used.
*/
/* Reference type bits of the n_desc field of undefined symbols */
#define REFERENCE_TYPE 0xf
/* types of references */
#define REFERENCE_FLAG_UNDEFINED_NON_LAZY 0
#define REFERENCE_FLAG_UNDEFINED_LAZY 1
#define REFERENCE_FLAG_DEFINED 2
#define REFERENCE_FLAG_PRIVATE_DEFINED 3
#define REFERENCE_FLAG_PRIVATE_UNDEFINED_NON_LAZY 4
#define REFERENCE_FLAG_PRIVATE_UNDEFINED_LAZY 5
/*
* To simplify stripping of objects that use are used with the dynamic link
* editor, the static link editor marks the symbols defined an object that are
* referenced by a dynamicly bound object (dynamic shared libraries, bundles).
* With this marking strip knows not to strip these symbols.
*/
#define REFERENCED_DYNAMICALLY 0x0010
/*
* For images created by the static link editor with the -twolevel_namespace
* option in effect the flags field of the mach header is marked with
* MH_TWOLEVEL. And the binding of the undefined references of the image are
* determined by the static link editor. Which library an undefined symbol is
* bound to is recorded by the static linker in the high 8 bits of the n_desc
* field using the SET_LIBRARY_ORDINAL macro below. The ordinal recorded
* references the libraries listed in the Mach-O's LC_LOAD_DYLIB load commands
* in the order they appear in the headers. The library ordinals start from 1.
* For a dynamic library that is built as a two-level namespace image the
* undefined references from module defined in another use the same nlist struct
* an in that case SELF_LIBRARY_ORDINAL is used as the library ordinal. For
* defined symbols in all images they also must have the library ordinal set to
* SELF_LIBRARY_ORDINAL. The EXECUTABLE_ORDINAL refers to the executable
* image for references from plugins that refer to the executable that loads
* them.
*
* The DYNAMIC_LOOKUP_ORDINAL is for undefined symbols in a two-level namespace
* image that are looked up by the dynamic linker with flat namespace semantics.
* This ordinal was added as a feature in Mac OS X 10.3 by reducing the
* value of MAX_LIBRARY_ORDINAL by one. So it is legal for existing binaries
* or binaries built with older tools to have 0xfe (254) dynamic libraries. In
* this case the ordinal value 0xfe (254) must be treated as a library ordinal
* for compatibility.
*/
#define GET_LIBRARY_ORDINAL(n_desc) (((n_desc) >> 8) & 0xff)
#define SET_LIBRARY_ORDINAL(n_desc,ordinal) \
(n_desc) = (((n_desc) & 0x00ff) | (((ordinal) & 0xff) << 8))
#define SELF_LIBRARY_ORDINAL 0x0
#define MAX_LIBRARY_ORDINAL 0xfd
#define DYNAMIC_LOOKUP_ORDINAL 0xfe
#define EXECUTABLE_ORDINAL 0xff
/*
* The bit 0x0020 of the n_desc field is used for two non-overlapping purposes
* and has two different symbolic names, N_NO_DEAD_STRIP and N_DESC_DISCARDED.
*/
/*
* The N_NO_DEAD_STRIP bit of the n_desc field only ever appears in a
* relocatable .o file (MH_OBJECT filetype). And is used to indicate to the
* static link editor it is never to dead strip the symbol.
*/
#define N_NO_DEAD_STRIP 0x0020 /* symbol is not to be dead stripped */
/*
* The N_DESC_DISCARDED bit of the n_desc field never appears in linked image.
* But is used in very rare cases by the dynamic link editor to mark an in
* memory symbol as discared and longer used for linking.
*/
#define N_DESC_DISCARDED 0x0020 /* symbol is discarded */
/*
* The N_WEAK_REF bit of the n_desc field indicates to the dynamic linker that
* the undefined symbol is allowed to be missing and is to have the address of
* zero when missing.
*/
#define N_WEAK_REF 0x0040 /* symbol is weak referenced */
/*
* The N_WEAK_DEF bit of the n_desc field indicates to the static and dynamic
* linkers that the symbol definition is weak, allowing a non-weak symbol to
* also be used which causes the weak definition to be discared. Currently this
* is only supported for symbols in coalesed sections.
*/
#define N_WEAK_DEF 0x0080 /* coalesed symbol is a weak definition */
/*
* The N_REF_TO_WEAK bit of the n_desc field indicates to the dynamic linker
* that the undefined symbol should be resolved using flat namespace searching.
*/
#define N_REF_TO_WEAK 0x0080 /* reference to a weak symbol */
#ifndef __STRICT_BSD__
/*
* The function nlist(3) from the C library.
*/
extern int nlist (const char *filename, struct nlist *list);
#endif /* __STRICT_BSD__ */
/*
* Symbolic debugger symbols. The comments give the conventional use for
*
* .stabs "n_name", n_type, n_sect, n_desc, n_value
*
* where n_type is the defined constant and not listed in the comment. Other
* fields not listed are zero. n_sect is the section ordinal the entry is
* refering to.
*/
#define N_GSYM 0x20 /* global symbol: name,,NO_SECT,type,0 */
#define N_FNAME 0x22 /* procedure name (f77 kludge): name,,NO_SECT,0,0 */
#define N_FUN 0x24 /* procedure: name,,n_sect,linenumber,address */
#define N_STSYM 0x26 /* static symbol: name,,n_sect,type,address */
#define N_LCSYM 0x28 /* .lcomm symbol: name,,n_sect,type,address */
#define N_BNSYM 0x2e /* begin nsect sym: 0,,n_sect,0,address */
#define N_OPT 0x3c /* emitted with gcc2_compiled and in gcc source */
#define N_RSYM 0x40 /* register sym: name,,NO_SECT,type,register */
#define N_SLINE 0x44 /* src line: 0,,n_sect,linenumber,address */
#define N_ENSYM 0x4e /* end nsect sym: 0,,n_sect,0,address */
#define N_SSYM 0x60 /* structure elt: name,,NO_SECT,type,struct_offset */
#define N_SO 0x64 /* source file name: name,,n_sect,0,address */
#define N_OSO 0x66 /* object file name: name,,0,0,st_mtime */
#define N_LSYM 0x80 /* local sym: name,,NO_SECT,type,offset */
#define N_BINCL 0x82 /* include file beginning: name,,NO_SECT,0,sum */
#define N_SOL 0x84 /* #included file name: name,,n_sect,0,address */
#define N_PARAMS 0x86 /* compiler parameters: name,,NO_SECT,0,0 */
#define N_VERSION 0x88 /* compiler version: name,,NO_SECT,0,0 */
#define N_OLEVEL 0x8A /* compiler -O level: name,,NO_SECT,0,0 */
#define N_PSYM 0xa0 /* parameter: name,,NO_SECT,type,offset */
#define N_EINCL 0xa2 /* include file end: name,,NO_SECT,0,0 */
#define N_ENTRY 0xa4 /* alternate entry: name,,n_sect,linenumber,address */
#define N_LBRAC 0xc0 /* left bracket: 0,,NO_SECT,nesting level,address */
#define N_EXCL 0xc2 /* deleted include file: name,,NO_SECT,0,sum */
#define N_RBRAC 0xe0 /* right bracket: 0,,NO_SECT,nesting level,address */
#define N_BCOMM 0xe2 /* begin common: name,,NO_SECT,0,0 */
#define N_ECOMM 0xe4 /* end common: name,,n_sect,0,0 */
#define N_ECOML 0xe8 /* end common (local name): 0,,n_sect,0,address */
#define N_LENG 0xfe /* second stab entry with length information */
/*
* for the berkeley pascal compiler, pc(1):
*/
#define N_PC 0x30 /* global pascal symbol: name,,NO_SECT,subtype,line */
#endif /* _MACHO_LOADER_H_ */
Reference in New Issue View Git Blame Copy Permalink