mirror of
https://github.com/netwide-assembler/nasm.git
synced 2024-12-15 09:09:58 +08:00
44d3552ab9
Add a reference to the %+ operator from the section on macro parameter concatenation. Signed-off-by: H. Peter Anvin <hpa@zytor.com>
7697 lines
298 KiB
Plaintext
7697 lines
298 KiB
Plaintext
\#
|
|
\# Source code to NASM documentation
|
|
\#
|
|
\M{category}{Programming}
|
|
\M{title}{NASM - The Netwide Assembler}
|
|
\M{year}{2008}
|
|
\M{author}{The NASM Development Team}
|
|
\M{license}{All rights reserved. This document is redistributable under the license given in the file "COPYING" distributed in the NASM archive.}
|
|
\M{summary}{This file documents NASM, the Netwide Assembler: an assembler targetting the Intel x86 series of processors, with portable source.}
|
|
\M{infoname}{NASM}
|
|
\M{infofile}{nasm}
|
|
\M{infotitle}{The Netwide Assembler for x86}
|
|
\M{epslogo}{nasmlogo.eps}
|
|
\IR{-D} \c{-D} option
|
|
\IR{-E} \c{-E} option
|
|
\IR{-F} \c{-F} option
|
|
\IR{-I} \c{-I} option
|
|
\IR{-M} \c{-M} option
|
|
\IR{-MD} \c{-MD} option
|
|
\IR{-MF} \c{-MF} option
|
|
\IR{-MG} \c{-MG} option
|
|
\IR{-MP} \c{-MP} option
|
|
\IR{-MQ} \c{-MQ} option
|
|
\IR{-MT} \c{-MT} option
|
|
\IR{-O} \c{-O} option
|
|
\IR{-P} \c{-P} option
|
|
\IR{-U} \c{-U} option
|
|
\IR{-X} \c{-X} option
|
|
\IR{-a} \c{-a} option
|
|
\IR{-d} \c{-d} option
|
|
\IR{-e} \c{-e} option
|
|
\IR{-f} \c{-f} option
|
|
\IR{-g} \c{-g} option
|
|
\IR{-i} \c{-i} option
|
|
\IR{-l} \c{-l} option
|
|
\IR{-o} \c{-o} option
|
|
\IR{-p} \c{-p} option
|
|
\IR{-s} \c{-s} option
|
|
\IR{-u} \c{-u} option
|
|
\IR{-v} \c{-v} option
|
|
\IR{-w} \c{-w} option
|
|
\IR{-y} \c{-y} option
|
|
\IR{-Z} \c{-Z} option
|
|
\IR{!=} \c{!=} operator
|
|
\IR{$, here} \c{$}, Here token
|
|
\IR{$, prefix} \c{$}, prefix
|
|
\IR{$$} \c{$$} token
|
|
\IR{%} \c{%} operator
|
|
\IR{%%} \c{%%} operator
|
|
\IR{%+1} \c{%+1} and \c{%-1} syntax
|
|
\IA{%-1}{%+1}
|
|
\IR{%0} \c{%0} parameter count
|
|
\IR{&} \c{&} operator
|
|
\IR{&&} \c{&&} operator
|
|
\IR{*} \c{*} operator
|
|
\IR{..@} \c{..@} symbol prefix
|
|
\IR{/} \c{/} operator
|
|
\IR{//} \c{//} operator
|
|
\IR{<} \c{<} operator
|
|
\IR{<<} \c{<<} operator
|
|
\IR{<=} \c{<=} operator
|
|
\IR{<>} \c{<>} operator
|
|
\IR{=} \c{=} operator
|
|
\IR{==} \c{==} operator
|
|
\IR{>} \c{>} operator
|
|
\IR{>=} \c{>=} operator
|
|
\IR{>>} \c{>>} operator
|
|
\IR{?} \c{?} MASM syntax
|
|
\IR{^} \c{^} operator
|
|
\IR{^^} \c{^^} operator
|
|
\IR{|} \c{|} operator
|
|
\IR{||} \c{||} operator
|
|
\IR{~} \c{~} operator
|
|
\IR{%$} \c{%$} and \c{%$$} prefixes
|
|
\IA{%$$}{%$}
|
|
\IR{+ opaddition} \c{+} operator, binary
|
|
\IR{+ opunary} \c{+} operator, unary
|
|
\IR{+ modifier} \c{+} modifier
|
|
\IR{- opsubtraction} \c{-} operator, binary
|
|
\IR{- opunary} \c{-} operator, unary
|
|
\IR{! opunary} \c{!} operator, unary
|
|
\IR{alignment, in bin sections} alignment, in \c{bin} sections
|
|
\IR{alignment, in elf sections} alignment, in \c{elf} sections
|
|
\IR{alignment, in win32 sections} alignment, in \c{win32} sections
|
|
\IR{alignment, of elf common variables} alignment, of \c{elf} common
|
|
variables
|
|
\IR{alignment, in obj sections} alignment, in \c{obj} sections
|
|
\IR{a.out, bsd version} \c{a.out}, BSD version
|
|
\IR{a.out, linux version} \c{a.out}, Linux version
|
|
\IR{autoconf} Autoconf
|
|
\IR{bin} bin
|
|
\IR{bitwise and} bitwise AND
|
|
\IR{bitwise or} bitwise OR
|
|
\IR{bitwise xor} bitwise XOR
|
|
\IR{block ifs} block IFs
|
|
\IR{borland pascal} Borland, Pascal
|
|
\IR{borland's win32 compilers} Borland, Win32 compilers
|
|
\IR{braces, after % sign} braces, after \c{%} sign
|
|
\IR{bsd} BSD
|
|
\IR{c calling convention} C calling convention
|
|
\IR{c symbol names} C symbol names
|
|
\IA{critical expressions}{critical expression}
|
|
\IA{command line}{command-line}
|
|
\IA{case sensitivity}{case sensitive}
|
|
\IA{case-sensitive}{case sensitive}
|
|
\IA{case-insensitive}{case sensitive}
|
|
\IA{character constants}{character constant}
|
|
\IR{common object file format} Common Object File Format
|
|
\IR{common variables, alignment in elf} common variables, alignment
|
|
in \c{elf}
|
|
\IR{common, elf extensions to} \c{COMMON}, \c{elf} extensions to
|
|
\IR{common, obj extensions to} \c{COMMON}, \c{obj} extensions to
|
|
\IR{declaring structure} declaring structures
|
|
\IR{default-wrt mechanism} default-\c{WRT} mechanism
|
|
\IR{devpac} DevPac
|
|
\IR{djgpp} DJGPP
|
|
\IR{dll symbols, exporting} DLL symbols, exporting
|
|
\IR{dll symbols, importing} DLL symbols, importing
|
|
\IR{dos} DOS
|
|
\IR{dos archive} DOS archive
|
|
\IR{dos source archive} DOS source archive
|
|
\IA{effective address}{effective addresses}
|
|
\IA{effective-address}{effective addresses}
|
|
\IR{elf} ELF
|
|
\IR{elf, 16-bit code and} ELF, 16-bit code and
|
|
\IR{elf shared libraries} ELF, shared libraries
|
|
\IR{executable and linkable format} Executable and Linkable Format
|
|
\IR{extern, obj extensions to} \c{EXTERN}, \c{obj} extensions to
|
|
\IR{extern, rdf extensions to} \c{EXTERN}, \c{rdf} extensions to
|
|
\IR{floating-point, constants} floating-point, constants
|
|
\IR{floating-point, packed bcd constants} floating-point, packed BCD constants
|
|
\IR{freebsd} FreeBSD
|
|
\IR{freelink} FreeLink
|
|
\IR{functions, c calling convention} functions, C calling convention
|
|
\IR{functions, pascal calling convention} functions, Pascal calling
|
|
convention
|
|
\IR{global, aoutb extensions to} \c{GLOBAL}, \c{aoutb} extensions to
|
|
\IR{global, elf extensions to} \c{GLOBAL}, \c{elf} extensions to
|
|
\IR{global, rdf extensions to} \c{GLOBAL}, \c{rdf} extensions to
|
|
\IR{got} GOT
|
|
\IR{got relocations} \c{GOT} relocations
|
|
\IR{gotoff relocation} \c{GOTOFF} relocations
|
|
\IR{gotpc relocation} \c{GOTPC} relocations
|
|
\IR{intel number formats} Intel number formats
|
|
\IR{linux, elf} Linux, ELF
|
|
\IR{linux, a.out} Linux, \c{a.out}
|
|
\IR{linux, as86} Linux, \c{as86}
|
|
\IR{logical and} logical AND
|
|
\IR{logical or} logical OR
|
|
\IR{logical xor} logical XOR
|
|
\IR{masm} MASM
|
|
\IA{memory reference}{memory references}
|
|
\IR{minix} Minix
|
|
\IA{misc directory}{misc subdirectory}
|
|
\IR{misc subdirectory} \c{misc} subdirectory
|
|
\IR{microsoft omf} Microsoft OMF
|
|
\IR{mmx registers} MMX registers
|
|
\IA{modr/m}{modr/m byte}
|
|
\IR{modr/m byte} ModR/M byte
|
|
\IR{ms-dos} MS-DOS
|
|
\IR{ms-dos device drivers} MS-DOS device drivers
|
|
\IR{multipush} \c{multipush} macro
|
|
\IR{nan} NaN
|
|
\IR{nasm version} NASM version
|
|
\IR{netbsd} NetBSD
|
|
\IR{omf} OMF
|
|
\IR{openbsd} OpenBSD
|
|
\IR{operating system} operating system
|
|
\IR{os/2} OS/2
|
|
\IR{pascal calling convention}Pascal calling convention
|
|
\IR{passes} passes, assembly
|
|
\IR{perl} Perl
|
|
\IR{pic} PIC
|
|
\IR{pharlap} PharLap
|
|
\IR{plt} PLT
|
|
\IR{plt} \c{PLT} relocations
|
|
\IA{pre-defining macros}{pre-define}
|
|
\IA{preprocessor expressions}{preprocessor, expressions}
|
|
\IA{preprocessor loops}{preprocessor, loops}
|
|
\IA{preprocessor variables}{preprocessor, variables}
|
|
\IA{rdoff subdirectory}{rdoff}
|
|
\IR{rdoff} \c{rdoff} subdirectory
|
|
\IR{relocatable dynamic object file format} Relocatable Dynamic
|
|
Object File Format
|
|
\IR{relocations, pic-specific} relocations, PIC-specific
|
|
\IA{repeating}{repeating code}
|
|
\IR{section alignment, in elf} section alignment, in \c{elf}
|
|
\IR{section alignment, in bin} section alignment, in \c{bin}
|
|
\IR{section alignment, in obj} section alignment, in \c{obj}
|
|
\IR{section alignment, in win32} section alignment, in \c{win32}
|
|
\IR{section, elf extensions to} \c{SECTION}, \c{elf} extensions to
|
|
\IR{section, win32 extensions to} \c{SECTION}, \c{win32} extensions to
|
|
\IR{segment alignment, in bin} segment alignment, in \c{bin}
|
|
\IR{segment alignment, in obj} segment alignment, in \c{obj}
|
|
\IR{segment, obj extensions to} \c{SEGMENT}, \c{elf} extensions to
|
|
\IR{segment names, borland pascal} segment names, Borland Pascal
|
|
\IR{shift command} \c{shift} command
|
|
\IA{sib}{sib byte}
|
|
\IR{sib byte} SIB byte
|
|
\IR{align, smart} \c{ALIGN}, smart
|
|
\IR{solaris x86} Solaris x86
|
|
\IA{standard section names}{standardized section names}
|
|
\IR{symbols, exporting from dlls} symbols, exporting from DLLs
|
|
\IR{symbols, importing from dlls} symbols, importing from DLLs
|
|
\IR{test subdirectory} \c{test} subdirectory
|
|
\IR{tlink} \c{TLINK}
|
|
\IR{underscore, in c symbols} underscore, in C symbols
|
|
\IR{unicode} Unicode
|
|
\IR{unix} Unix
|
|
\IR{utf-8} UTF-8
|
|
\IR{utf-16} UTF-16
|
|
\IR{utf-32} UTF-32
|
|
\IA{sco unix}{unix, sco}
|
|
\IR{unix, sco} Unix, SCO
|
|
\IA{unix source archive}{unix, source archive}
|
|
\IR{unix, source archive} Unix, source archive
|
|
\IA{unix system v}{unix, system v}
|
|
\IR{unix, system v} Unix, System V
|
|
\IR{unixware} UnixWare
|
|
\IR{val} VAL
|
|
\IR{version number of nasm} version number of NASM
|
|
\IR{visual c++} Visual C++
|
|
\IR{www page} WWW page
|
|
\IR{win32} Win32
|
|
\IR{win32} Win64
|
|
\IR{windows} Windows
|
|
\IR{windows 95} Windows 95
|
|
\IR{windows nt} Windows NT
|
|
\# \IC{program entry point}{entry point, program}
|
|
\# \IC{program entry point}{start point, program}
|
|
\# \IC{MS-DOS device drivers}{device drivers, MS-DOS}
|
|
\# \IC{16-bit mode, versus 32-bit mode}{32-bit mode, versus 16-bit mode}
|
|
\# \IC{c symbol names}{symbol names, in C}
|
|
|
|
|
|
\C{intro} Introduction
|
|
|
|
\H{whatsnasm} What Is NASM?
|
|
|
|
The Netwide Assembler, NASM, is an 80x86 and x86-64 assembler designed
|
|
for portability and modularity. It supports a range of object file
|
|
formats, including Linux and \c{*BSD} \c{a.out}, \c{ELF}, \c{COFF},
|
|
\c{Mach-O}, Microsoft 16-bit \c{OBJ}, \c{Win32} and \c{Win64}. It will
|
|
also output plain binary files. Its syntax is designed to be simple
|
|
and easy to understand, similar to Intel's but less complex. It
|
|
supports all currently known x86 architectural extensions, and has
|
|
strong support for macros.
|
|
|
|
|
|
\S{yaasm} Why Yet Another Assembler?
|
|
|
|
The Netwide Assembler grew out of an idea on \i\c{comp.lang.asm.x86}
|
|
(or possibly \i\c{alt.lang.asm} - I forget which), which was
|
|
essentially that there didn't seem to be a good \e{free} x86-series
|
|
assembler around, and that maybe someone ought to write one.
|
|
|
|
\b \i\c{a86} is good, but not free, and in particular you don't get any
|
|
32-bit capability until you pay. It's DOS only, too.
|
|
|
|
\b \i\c{gas} is free, and ports over to DOS and Unix, but it's not
|
|
very good, since it's designed to be a back end to \i\c{gcc}, which
|
|
always feeds it correct code. So its error checking is minimal. Also,
|
|
its syntax is horrible, from the point of view of anyone trying to
|
|
actually \e{write} anything in it. Plus you can't write 16-bit code in
|
|
it (properly.)
|
|
|
|
\b \i\c{as86} is specific to Minix and Linux, and (my version at least)
|
|
doesn't seem to have much (or any) documentation.
|
|
|
|
\b \i\c{MASM} isn't very good, and it's (was) expensive, and it runs only under
|
|
DOS.
|
|
|
|
\b \i\c{TASM} is better, but still strives for MASM compatibility,
|
|
which means millions of directives and tons of red tape. And its syntax
|
|
is essentially MASM's, with the contradictions and quirks that
|
|
entails (although it sorts out some of those by means of Ideal mode.)
|
|
It's expensive too. And it's DOS-only.
|
|
|
|
So here, for your coding pleasure, is NASM. At present it's
|
|
still in prototype stage - we don't promise that it can outperform
|
|
any of these assemblers. But please, \e{please} send us bug reports,
|
|
fixes, helpful information, and anything else you can get your hands
|
|
on (and thanks to the many people who've done this already! You all
|
|
know who you are), and we'll improve it out of all recognition.
|
|
Again.
|
|
|
|
|
|
\S{legal} License Conditions
|
|
|
|
Please see the file \c{COPYING}, supplied as part of any NASM
|
|
distribution archive, for the \i{license} conditions under which you
|
|
may use NASM. NASM is now under the so-called GNU Lesser General
|
|
Public License, LGPL.
|
|
|
|
|
|
\H{contact} Contact Information
|
|
|
|
The current version of NASM (since about 0.98.08) is maintained by a
|
|
team of developers, accessible through the \c{nasm-devel} mailing list
|
|
(see below for the link).
|
|
If you want to report a bug, please read \k{bugs} first.
|
|
|
|
NASM has a \i{WWW page} at
|
|
\W{http://nasm.sourceforge.net}\c{http://nasm.sourceforge.net}. If it's
|
|
not there, google for us!
|
|
|
|
|
|
The original authors are \i{e\-mail}able as
|
|
\W{mailto:jules@dsf.org.uk}\c{jules@dsf.org.uk} and
|
|
\W{mailto:anakin@pobox.com}\c{anakin@pobox.com}.
|
|
The latter is no longer involved in the development team.
|
|
|
|
\i{New releases} of NASM are uploaded to the official sites
|
|
\W{http://nasm.sourceforge.net}\c{http://nasm.sourceforge.net}
|
|
and to
|
|
\W{ftp://ftp.kernel.org/pub/software/devel/nasm/}\i\c{ftp.kernel.org}
|
|
and
|
|
\W{ftp://ibiblio.org/pub/Linux/devel/lang/assemblers/}\i\c{ibiblio.org}.
|
|
|
|
Announcements are posted to
|
|
\W{news:comp.lang.asm.x86}\i\c{comp.lang.asm.x86},
|
|
\W{news:alt.lang.asm}\i\c{alt.lang.asm} and
|
|
\W{news:comp.os.linux.announce}\i\c{comp.os.linux.announce}
|
|
|
|
If you want information about NASM beta releases, and the current
|
|
development status, please subscribe to the \i\c{nasm-devel} email list
|
|
by registering at
|
|
\W{http://sourceforge.net/projects/nasm}\c{http://sourceforge.net/projects/nasm}.
|
|
|
|
|
|
\H{install} Installation
|
|
|
|
\S{instdos} \i{Installing} NASM under MS-\i{DOS} or Windows
|
|
|
|
Once you've obtained the appropriate archive for NASM,
|
|
\i\c{nasm-XXX-dos.zip} or \i\c{nasm-XXX-win32.zip} (where \c{XXX}
|
|
denotes the version number of NASM contained in the archive), unpack
|
|
it into its own directory (for example \c{c:\\nasm}).
|
|
|
|
The archive will contain a set of executable files: the NASM
|
|
executable file \i\c{nasm.exe}, the NDISASM executable file
|
|
\i\c{ndisasm.exe}, and possibly additional utilities to handle the
|
|
RDOFF file format.
|
|
|
|
The only file NASM needs to run is its own executable, so copy
|
|
\c{nasm.exe} to a directory on your PATH, or alternatively edit
|
|
\i\c{autoexec.bat} to add the \c{nasm} directory to your
|
|
\i\c{PATH} (to do that under Windows XP, go to Start > Control Panel >
|
|
System > Advanced > Environment Variables; these instructions may work
|
|
under other versions of Windows as well.)
|
|
|
|
That's it - NASM is installed. You don't need the nasm directory
|
|
to be present to run NASM (unless you've added it to your \c{PATH}),
|
|
so you can delete it if you need to save space; however, you may
|
|
want to keep the documentation or test programs.
|
|
|
|
If you've downloaded the \i{DOS source archive}, \i\c{nasm-XXX.zip},
|
|
the \c{nasm} directory will also contain the full NASM \i{source
|
|
code}, and a selection of \i{Makefiles} you can (hopefully) use to
|
|
rebuild your copy of NASM from scratch. See the file \c{INSTALL} in
|
|
the source archive.
|
|
|
|
Note that a number of files are generated from other files by Perl
|
|
scripts. Although the NASM source distribution includes these
|
|
generated files, you will need to rebuild them (and hence, will need a
|
|
Perl interpreter) if you change insns.dat, standard.mac or the
|
|
documentation. It is possible future source distributions may not
|
|
include these files at all. Ports of \i{Perl} for a variety of
|
|
platforms, including DOS and Windows, are available from
|
|
\W{http://www.cpan.org/ports/}\i{www.cpan.org}.
|
|
|
|
|
|
\S{instdos} Installing NASM under \i{Unix}
|
|
|
|
Once you've obtained the \i{Unix source archive} for NASM,
|
|
\i\c{nasm-XXX.tar.gz} (where \c{XXX} denotes the version number of
|
|
NASM contained in the archive), unpack it into a directory such
|
|
as \c{/usr/local/src}. The archive, when unpacked, will create its
|
|
own subdirectory \c{nasm-XXX}.
|
|
|
|
NASM is an \I{Autoconf}\I\c{configure}auto-configuring package: once
|
|
you've unpacked it, \c{cd} to the directory it's been unpacked into
|
|
and type \c{./configure}. This shell script will find the best C
|
|
compiler to use for building NASM and set up \i{Makefiles}
|
|
accordingly.
|
|
|
|
Once NASM has auto-configured, you can type \i\c{make} to build the
|
|
\c{nasm} and \c{ndisasm} binaries, and then \c{make install} to
|
|
install them in \c{/usr/local/bin} and install the \i{man pages}
|
|
\i\c{nasm.1} and \i\c{ndisasm.1} in \c{/usr/local/man/man1}.
|
|
Alternatively, you can give options such as \c{--prefix} to the
|
|
configure script (see the file \i\c{INSTALL} for more details), or
|
|
install the programs yourself.
|
|
|
|
NASM also comes with a set of utilities for handling the \c{RDOFF}
|
|
custom object-file format, which are in the \i\c{rdoff} subdirectory
|
|
of the NASM archive. You can build these with \c{make rdf} and
|
|
install them with \c{make rdf_install}, if you want them.
|
|
|
|
|
|
\C{running} Running NASM
|
|
|
|
\H{syntax} NASM \i{Command-Line} Syntax
|
|
|
|
To assemble a file, you issue a command of the form
|
|
|
|
\c nasm -f <format> <filename> [-o <output>]
|
|
|
|
For example,
|
|
|
|
\c nasm -f elf myfile.asm
|
|
|
|
will assemble \c{myfile.asm} into an \c{ELF} object file \c{myfile.o}. And
|
|
|
|
\c nasm -f bin myfile.asm -o myfile.com
|
|
|
|
will assemble \c{myfile.asm} into a raw binary file \c{myfile.com}.
|
|
|
|
To produce a listing file, with the hex codes output from NASM
|
|
displayed on the left of the original sources, use the \c{-l} option
|
|
to give a listing file name, for example:
|
|
|
|
\c nasm -f coff myfile.asm -l myfile.lst
|
|
|
|
To get further usage instructions from NASM, try typing
|
|
|
|
\c nasm -h
|
|
|
|
As \c{-hf}, this will also list the available output file formats, and what they
|
|
are.
|
|
|
|
If you use Linux but aren't sure whether your system is \c{a.out}
|
|
or \c{ELF}, type
|
|
|
|
\c file nasm
|
|
|
|
(in the directory in which you put the NASM binary when you
|
|
installed it). If it says something like
|
|
|
|
\c nasm: ELF 32-bit LSB executable i386 (386 and up) Version 1
|
|
|
|
then your system is \c{ELF}, and you should use the option \c{-f elf}
|
|
when you want NASM to produce Linux object files. If it says
|
|
|
|
\c nasm: Linux/i386 demand-paged executable (QMAGIC)
|
|
|
|
or something similar, your system is \c{a.out}, and you should use
|
|
\c{-f aout} instead (Linux \c{a.out} systems have long been obsolete,
|
|
and are rare these days.)
|
|
|
|
Like Unix compilers and assemblers, NASM is silent unless it
|
|
goes wrong: you won't see any output at all, unless it gives error
|
|
messages.
|
|
|
|
|
|
\S{opt-o} The \i\c{-o} Option: Specifying the Output File Name
|
|
|
|
NASM will normally choose the name of your output file for you;
|
|
precisely how it does this is dependent on the object file format.
|
|
For Microsoft object file formats (\i\c{obj} and \i\c{win32}), it
|
|
will remove the \c{.asm} \i{extension} (or whatever extension you
|
|
like to use - NASM doesn't care) from your source file name and
|
|
substitute \c{.obj}. For Unix object file formats (\i\c{aout},
|
|
\i\c{coff}, \i\c{elf}, \i\c{macho} and \i\c{as86}) it will substitute \c{.o}. For
|
|
\i\c{rdf}, it will use \c{.rdf}, and for the \i\c{bin} format it
|
|
will simply remove the extension, so that \c{myfile.asm} produces
|
|
the output file \c{myfile}.
|
|
|
|
If the output file already exists, NASM will overwrite it, unless it
|
|
has the same name as the input file, in which case it will give a
|
|
warning and use \i\c{nasm.out} as the output file name instead.
|
|
|
|
For situations in which this behaviour is unacceptable, NASM
|
|
provides the \c{-o} command-line option, which allows you to specify
|
|
your desired output file name. You invoke \c{-o} by following it
|
|
with the name you wish for the output file, either with or without
|
|
an intervening space. For example:
|
|
|
|
\c nasm -f bin program.asm -o program.com
|
|
\c nasm -f bin driver.asm -odriver.sys
|
|
|
|
Note that this is a small o, and is different from a capital O , which
|
|
is used to specify the number of optimisation passes required. See \k{opt-O}.
|
|
|
|
|
|
\S{opt-f} The \i\c{-f} Option: Specifying the \i{Output File Format}
|
|
|
|
If you do not supply the \c{-f} option to NASM, it will choose an
|
|
output file format for you itself. In the distribution versions of
|
|
NASM, the default is always \i\c{bin}; if you've compiled your own
|
|
copy of NASM, you can redefine \i\c{OF_DEFAULT} at compile time and
|
|
choose what you want the default to be.
|
|
|
|
Like \c{-o}, the intervening space between \c{-f} and the output
|
|
file format is optional; so \c{-f elf} and \c{-felf} are both valid.
|
|
|
|
A complete list of the available output file formats can be given by
|
|
issuing the command \i\c{nasm -hf}.
|
|
|
|
|
|
\S{opt-l} The \i\c{-l} Option: Generating a \i{Listing File}
|
|
|
|
If you supply the \c{-l} option to NASM, followed (with the usual
|
|
optional space) by a file name, NASM will generate a
|
|
\i{source-listing file} for you, in which addresses and generated
|
|
code are listed on the left, and the actual source code, with
|
|
expansions of multi-line macros (except those which specifically
|
|
request no expansion in source listings: see \k{nolist}) on the
|
|
right. For example:
|
|
|
|
\c nasm -f elf myfile.asm -l myfile.lst
|
|
|
|
If a list file is selected, you may turn off listing for a
|
|
section of your source with \c{[list -]}, and turn it back on
|
|
with \c{[list +]}, (the default, obviously). There is no "user
|
|
form" (without the brackets). This can be used to list only
|
|
sections of interest, avoiding excessively long listings.
|
|
|
|
|
|
\S{opt-M} The \i\c{-M} Option: Generate \i{Makefile Dependencies}
|
|
|
|
This option can be used to generate makefile dependencies on stdout.
|
|
This can be redirected to a file for further processing. For example:
|
|
|
|
\c nasm -M myfile.asm > myfile.dep
|
|
|
|
|
|
\S{opt-MG} The \i\c{-MG} Option: Generate \i{Makefile Dependencies}
|
|
|
|
This option can be used to generate makefile dependencies on stdout.
|
|
This differs from the \c{-M} option in that if a nonexisting file is
|
|
encountered, it is assumed to be a generated file and is added to the
|
|
dependency list without a prefix.
|
|
|
|
|
|
\S{opt-MF} The \i\c\{-MF} Option: Set Makefile Dependency File
|
|
|
|
This option can be used with the \c{-M} or \c{-MG} options to send the
|
|
output to a file, rather than to stdout. For example:
|
|
|
|
\c nasm -M -MF myfile.dep myfile.asm
|
|
|
|
|
|
\S{opt-MD} The \i\c{-MD} Option: Assemble and Generate Dependencies
|
|
|
|
The \c{-MD} option acts as the combination of the \c{-M} and \c{-MF}
|
|
options (i.e. a filename has to be specified.) However, unlike the
|
|
\c{-M} or \c{-MG} options, \c{-MD} does \e{not} inhibit the normal
|
|
operation of the assembler. Use this to automatically generate
|
|
updated dependencies with every assembly session. For example:
|
|
|
|
\c nasm -f elf -o myfile.o -MD myfile.dep myfile.asm
|
|
|
|
|
|
\S{opt-MT} The \i\c{-MT} Option: Dependency Target Name
|
|
|
|
The \c{-MT} option can be used to override the default name of the
|
|
dependency target. This is normally the same as the output filename,
|
|
specified by the \c{-o} option.
|
|
|
|
|
|
\S{opt-MQ} The \i\c{-MQ} Option: Dependency Target Name (Quoted)
|
|
|
|
The \c{-MQ} option acts as the \c{-MT} option, except it tries to
|
|
quote characters that have special meaning in Makefile syntax. This
|
|
is not foolproof, as not all characters with special meaning are
|
|
quotable in Make.
|
|
|
|
|
|
\S{opt-MP} The \i\c{-MP} Option: Emit phony targets
|
|
|
|
When used with any of the dependency generation options, the \c{-MP}
|
|
option causes NASM to emit a phony target without dependencies for
|
|
each header file. This prevents Make from complaining if a header
|
|
file has been removed.
|
|
|
|
|
|
\S{opt-F} The \i\c{-F} Option: Selecting a \i{Debug Information Format}
|
|
|
|
This option is used to select the format of the debug information
|
|
emitted into the output file, to be used by a debugger (or \e{will}
|
|
be). Prior to version 2.03.01, the use of this switch did \e{not} enable
|
|
output of the selected debug info format. Use \c{-g}, see \k{opt-g},
|
|
to enable output. Versions 2.03.01 and later automatically enable \c{-g}
|
|
if \c{-F} is specified.
|
|
|
|
A complete list of the available debug file formats for an output
|
|
format can be seen by issuing the command \c{nasm -f <format> -y}. Not
|
|
all output formats currently support debugging output. See \k{opt-y}.
|
|
|
|
This should not be confused with the \c{-f dbg} output format option which
|
|
is not built into NASM by default. For information on how
|
|
to enable it when building from the sources, see \k{dbgfmt}.
|
|
|
|
|
|
\S{opt-g} The \i\c{-g} Option: Enabling \i{Debug Information}.
|
|
|
|
This option can be used to generate debugging information in the specified
|
|
format. See \k{opt-F}. Using \c{-g} without \c{-F} results in emitting
|
|
debug info in the default format, if any, for the selected output format.
|
|
If no debug information is currently implemented in the selected output
|
|
format, \c{-g} is \e{silently ignored}.
|
|
|
|
|
|
\S{opt-X} The \i\c{-X} Option: Selecting an \i{Error Reporting Format}
|
|
|
|
This option can be used to select an error reporting format for any
|
|
error messages that might be produced by NASM.
|
|
|
|
Currently, two error reporting formats may be selected. They are
|
|
the \c{-Xvc} option and the \c{-Xgnu} option. The GNU format is
|
|
the default and looks like this:
|
|
|
|
\c filename.asm:65: error: specific error message
|
|
|
|
where \c{filename.asm} is the name of the source file in which the
|
|
error was detected, \c{65} is the source file line number on which
|
|
the error was detected, \c{error} is the severity of the error (this
|
|
could be \c{warning}), and \c{specific error message} is a more
|
|
detailed text message which should help pinpoint the exact problem.
|
|
|
|
The other format, specified by \c{-Xvc} is the style used by Microsoft
|
|
Visual C++ and some other programs. It looks like this:
|
|
|
|
\c filename.asm(65) : error: specific error message
|
|
|
|
where the only difference is that the line number is in parentheses
|
|
instead of being delimited by colons.
|
|
|
|
See also the \c{Visual C++} output format, \k{win32fmt}.
|
|
|
|
\S{opt-Z} The \i\c{-Z} Option: Send Errors to a File
|
|
|
|
Under \I{DOS}\c{MS-DOS} it can be difficult (though there are ways) to
|
|
redirect the standard-error output of a program to a file. Since
|
|
NASM usually produces its warning and \i{error messages} on
|
|
\i\c{stderr}, this can make it hard to capture the errors if (for
|
|
example) you want to load them into an editor.
|
|
|
|
NASM therefore provides the \c{-Z} option, taking a filename argument
|
|
which causes errors to be sent to the specified files rather than
|
|
standard error. Therefore you can \I{redirecting errors}redirect
|
|
the errors into a file by typing
|
|
|
|
\c nasm -Z myfile.err -f obj myfile.asm
|
|
|
|
In earlier versions of NASM, this option was called \c{-E}, but it was
|
|
changed since \c{-E} is an option conventionally used for
|
|
preprocessing only, with disastrous results. See \k{opt-E}.
|
|
|
|
\S{opt-s} The \i\c{-s} Option: Send Errors to \i\c{stdout}
|
|
|
|
The \c{-s} option redirects \i{error messages} to \c{stdout} rather
|
|
than \c{stderr}, so it can be redirected under \I{DOS}\c{MS-DOS}. To
|
|
assemble the file \c{myfile.asm} and pipe its output to the \c{more}
|
|
program, you can type:
|
|
|
|
\c nasm -s -f obj myfile.asm | more
|
|
|
|
See also the \c{-Z} option, \k{opt-Z}.
|
|
|
|
|
|
\S{opt-i} The \i\c{-i}\I\c{-I} Option: Include File Search Directories
|
|
|
|
When NASM sees the \i\c{%include} or \i\c{%pathsearch} directive in a
|
|
source file (see \k{include}, \k{pathsearch} or \k{incbin}), it will
|
|
search for the given file not only in the current directory, but also
|
|
in any directories specified on the command line by the use of the
|
|
\c{-i} option. Therefore you can include files from a \i{macro
|
|
library}, for example, by typing
|
|
|
|
\c nasm -ic:\macrolib\ -f obj myfile.asm
|
|
|
|
(As usual, a space between \c{-i} and the path name is allowed, and
|
|
optional).
|
|
|
|
NASM, in the interests of complete source-code portability, does not
|
|
understand the file naming conventions of the OS it is running on;
|
|
the string you provide as an argument to the \c{-i} option will be
|
|
prepended exactly as written to the name of the include file.
|
|
Therefore the trailing backslash in the above example is necessary.
|
|
Under Unix, a trailing forward slash is similarly necessary.
|
|
|
|
(You can use this to your advantage, if you're really \i{perverse},
|
|
by noting that the option \c{-ifoo} will cause \c{%include "bar.i"}
|
|
to search for the file \c{foobar.i}...)
|
|
|
|
If you want to define a \e{standard} \i{include search path},
|
|
similar to \c{/usr/include} on Unix systems, you should place one or
|
|
more \c{-i} directives in the \c{NASMENV} environment variable (see
|
|
\k{nasmenv}).
|
|
|
|
For Makefile compatibility with many C compilers, this option can also
|
|
be specified as \c{-I}.
|
|
|
|
|
|
\S{opt-p} The \i\c{-p}\I\c{-P} Option: \I{pre-including files}Pre-Include a File
|
|
|
|
\I\c{%include}NASM allows you to specify files to be
|
|
\e{pre-included} into your source file, by the use of the \c{-p}
|
|
option. So running
|
|
|
|
\c nasm myfile.asm -p myinc.inc
|
|
|
|
is equivalent to running \c{nasm myfile.asm} and placing the
|
|
directive \c{%include "myinc.inc"} at the start of the file.
|
|
|
|
For consistency with the \c{-I}, \c{-D} and \c{-U} options, this
|
|
option can also be specified as \c{-P}.
|
|
|
|
|
|
\S{opt-d} The \i\c{-d}\I\c{-D} Option: \I{pre-defining macros}Pre-Define a Macro
|
|
|
|
\I\c{%define}Just as the \c{-p} option gives an alternative to placing
|
|
\c{%include} directives at the start of a source file, the \c{-d}
|
|
option gives an alternative to placing a \c{%define} directive. You
|
|
could code
|
|
|
|
\c nasm myfile.asm -dFOO=100
|
|
|
|
as an alternative to placing the directive
|
|
|
|
\c %define FOO 100
|
|
|
|
at the start of the file. You can miss off the macro value, as well:
|
|
the option \c{-dFOO} is equivalent to coding \c{%define FOO}. This
|
|
form of the directive may be useful for selecting \i{assembly-time
|
|
options} which are then tested using \c{%ifdef}, for example
|
|
\c{-dDEBUG}.
|
|
|
|
For Makefile compatibility with many C compilers, this option can also
|
|
be specified as \c{-D}.
|
|
|
|
|
|
\S{opt-u} The \i\c{-u}\I\c{-U} Option: \I{Undefining macros}Undefine a Macro
|
|
|
|
\I\c{%undef}The \c{-u} option undefines a macro that would otherwise
|
|
have been pre-defined, either automatically or by a \c{-p} or \c{-d}
|
|
option specified earlier on the command lines.
|
|
|
|
For example, the following command line:
|
|
|
|
\c nasm myfile.asm -dFOO=100 -uFOO
|
|
|
|
would result in \c{FOO} \e{not} being a predefined macro in the
|
|
program. This is useful to override options specified at a different
|
|
point in a Makefile.
|
|
|
|
For Makefile compatibility with many C compilers, this option can also
|
|
be specified as \c{-U}.
|
|
|
|
|
|
\S{opt-E} The \i\c{-E}\I{-e} Option: Preprocess Only
|
|
|
|
NASM allows the \i{preprocessor} to be run on its own, up to a
|
|
point. Using the \c{-E} option (which requires no arguments) will
|
|
cause NASM to preprocess its input file, expand all the macro
|
|
references, remove all the comments and preprocessor directives, and
|
|
print the resulting file on standard output (or save it to a file,
|
|
if the \c{-o} option is also used).
|
|
|
|
This option cannot be applied to programs which require the
|
|
preprocessor to evaluate \I{preprocessor expressions}\i{expressions}
|
|
which depend on the values of symbols: so code such as
|
|
|
|
\c %assign tablesize ($-tablestart)
|
|
|
|
will cause an error in \i{preprocess-only mode}.
|
|
|
|
For compatiblity with older version of NASM, this option can also be
|
|
written \c{-e}. \c{-E} in older versions of NASM was the equivalent
|
|
of the current \c{-Z} option, \k{opt-Z}.
|
|
|
|
\S{opt-a} The \i\c{-a} Option: Don't Preprocess At All
|
|
|
|
If NASM is being used as the back end to a compiler, it might be
|
|
desirable to \I{suppressing preprocessing}suppress preprocessing
|
|
completely and assume the compiler has already done it, to save time
|
|
and increase compilation speeds. The \c{-a} option, requiring no
|
|
argument, instructs NASM to replace its powerful \i{preprocessor}
|
|
with a \i{stub preprocessor} which does nothing.
|
|
|
|
|
|
\S{opt-O} The \i\c{-O} Option: Specifying \i{Multipass Optimization}
|
|
|
|
NASM defaults to not optimizing operands which can fit into a signed byte.
|
|
This means that if you want the shortest possible object code,
|
|
you have to enable optimization.
|
|
|
|
Using the \c{-O} option, you can tell NASM to carry out different
|
|
levels of optimization. The syntax is:
|
|
|
|
\b \c{-O0}: No optimization. All operands take their long forms,
|
|
if a short form is not specified, except conditional jumps.
|
|
This is intended to match NASM 0.98 behavior.
|
|
|
|
\b \c{-O1}: Minimal optimization. As above, but immediate operands
|
|
which will fit in a signed byte are optimized,
|
|
unless the long form is specified. Conditional jumps default
|
|
to the long form unless otherwise specified.
|
|
|
|
\b \c{-Ox} (where \c{x} is the actual letter \c{x}): Multipass optimization.
|
|
Minimize branch offsets and signed immediate bytes,
|
|
overriding size specification unless the \c{strict} keyword
|
|
has been used (see \k{strict}). For compatability with earlier
|
|
releases, the letter \c{x} may also be any number greater than
|
|
one. This number has no effect on the actual number of passes.
|
|
|
|
The \c{-Ox} mode is recommended for most uses.
|
|
|
|
Note that this is a capital \c{O}, and is different from a small \c{o}, which
|
|
is used to specify the output file name. See \k{opt-o}.
|
|
|
|
|
|
\S{opt-t} The \i\c{-t} option: Enable TASM Compatibility Mode
|
|
|
|
NASM includes a limited form of compatibility with Borland's \i\c{TASM}.
|
|
When NASM's \c{-t} option is used, the following changes are made:
|
|
|
|
\b local labels may be prefixed with \c{@@} instead of \c{.}
|
|
|
|
\b size override is supported within brackets. In TASM compatible mode,
|
|
a size override inside square brackets changes the size of the operand,
|
|
and not the address type of the operand as it does in NASM syntax. E.g.
|
|
\c{mov eax,[DWORD val]} is valid syntax in TASM compatibility mode.
|
|
Note that you lose the ability to override the default address type for
|
|
the instruction.
|
|
|
|
\b unprefixed forms of some directives supported (\c{arg}, \c{elif},
|
|
\c{else}, \c{endif}, \c{if}, \c{ifdef}, \c{ifdifi}, \c{ifndef},
|
|
\c{include}, \c{local})
|
|
|
|
\S{opt-w} The \i\c{-w} Option: Enable or Disable Assembly \i{Warnings}
|
|
|
|
NASM can observe many conditions during the course of assembly which
|
|
are worth mentioning to the user, but not a sufficiently severe
|
|
error to justify NASM refusing to generate an output file. These
|
|
conditions are reported like errors, but come up with the word
|
|
`warning' before the message. Warnings do not prevent NASM from
|
|
generating an output file and returning a success status to the
|
|
operating system.
|
|
|
|
Some conditions are even less severe than that: they are only
|
|
sometimes worth mentioning to the user. Therefore NASM supports the
|
|
\c{-w} command-line option, which enables or disables certain
|
|
classes of assembly warning. Such warning classes are described by a
|
|
name, for example \c{orphan-labels}; you can enable warnings of
|
|
this class by the command-line option \c{-w+orphan-labels} and
|
|
disable it by \c{-w-orphan-labels}.
|
|
|
|
The \i{suppressible warning} classes are:
|
|
|
|
\b \i\c{error} decides if warnings should be treated as errors.
|
|
It is disabled by default.
|
|
|
|
\b \i\c{macro-params} covers warnings about \i{multi-line macros}
|
|
being invoked with the wrong number of parameters. This warning
|
|
class is enabled by default; see \k{mlmacover} for an example of why
|
|
you might want to disable it.
|
|
|
|
\b \i\c{macro-selfref} warns if a macro references itself. This
|
|
warning class is disabled by default.
|
|
|
|
\b\i\c{macro-defaults} warns when a macro has more default
|
|
parameters than optional parameters. This warning class
|
|
is enabled by default; see \k{mlmacdef} for why you might want to disable it.
|
|
|
|
\b \i\c{orphan-labels} covers warnings about source lines which
|
|
contain no instruction but define a label without a trailing colon.
|
|
NASM warns about this somewhat obscure condition by default;
|
|
see \k{syntax} for more information.
|
|
|
|
\b \i\c{number-overflow} covers warnings about numeric constants which
|
|
don't fit in 64 bits. This warning class is enabled by default.
|
|
|
|
\b \i\c{gnu-elf-extensions} warns if 8-bit or 16-bit relocations
|
|
are used in \c{-f elf} format. The GNU extensions allow this.
|
|
This warning class is disabled by default.
|
|
|
|
\b \i\c{float-overflow} warns about floating point overflow.
|
|
Enabled by default.
|
|
|
|
\b \i\c{float-denorm} warns about floating point denormals.
|
|
Disabled by default.
|
|
|
|
\b \i\c{float-underflow} warns about floating point underflow.
|
|
Disabled by default.
|
|
|
|
\b \i\c{float-toolong} warns about too many digits in floating-point numbers.
|
|
Enabled by default.
|
|
|
|
\b \i\c{user} controls \c{%warning} directives (see \k{pperror}).
|
|
Enabled by default.
|
|
|
|
In addition, you can set warning classes across sections.
|
|
Warning classes may be enabled with \i\c{[warning +warning-name]},
|
|
disabled with \i\c{[warning -warning-name]} or reset to their
|
|
original value with \i\c{[warning *warning-name]}. No "user form"
|
|
(without the brackets) exists.
|
|
|
|
|
|
\S{opt-v} The \i\c{-v} Option: Display \i{Version} Info
|
|
|
|
Typing \c{NASM -v} will display the version of NASM which you are using,
|
|
and the date on which it was compiled.
|
|
|
|
You will need the version number if you report a bug.
|
|
|
|
\S{opt-y} The \i\c{-y} Option: Display Available Debug Info Formats
|
|
|
|
Typing \c{nasm -f <option> -y} will display a list of the available
|
|
debug info formats for the given output format. The default format
|
|
is indicated by an asterisk. For example:
|
|
|
|
\c nasm -f elf -y
|
|
|
|
\c valid debug formats for 'elf32' output format are
|
|
\c ('*' denotes default):
|
|
\c * stabs ELF32 (i386) stabs debug format for Linux
|
|
\c dwarf elf32 (i386) dwarf debug format for Linux
|
|
|
|
|
|
\S{opt-pfix} The \i\c{--prefix} and \i\c{--postfix} Options.
|
|
|
|
The \c{--prefix} and \c{--postfix} options prepend or append
|
|
(respectively) the given argument to all \c{global} or
|
|
\c{extern} variables. E.g. \c{--prefix _} will prepend the
|
|
underscore to all global and external variables, as C sometimes
|
|
(but not always) likes it.
|
|
|
|
|
|
\S{nasmenv} The \i\c{NASMENV} \i{Environment} Variable
|
|
|
|
If you define an environment variable called \c{NASMENV}, the program
|
|
will interpret it as a list of extra command-line options, which are
|
|
processed before the real command line. You can use this to define
|
|
standard search directories for include files, by putting \c{-i}
|
|
options in the \c{NASMENV} variable.
|
|
|
|
The value of the variable is split up at white space, so that the
|
|
value \c{-s -ic:\\nasmlib} will be treated as two separate options.
|
|
However, that means that the value \c{-dNAME="my name"} won't do
|
|
what you might want, because it will be split at the space and the
|
|
NASM command-line processing will get confused by the two
|
|
nonsensical words \c{-dNAME="my} and \c{name"}.
|
|
|
|
To get round this, NASM provides a feature whereby, if you begin the
|
|
\c{NASMENV} environment variable with some character that isn't a minus
|
|
sign, then NASM will treat this character as the \i{separator
|
|
character} for options. So setting the \c{NASMENV} variable to the
|
|
value \c{!-s!-ic:\\nasmlib} is equivalent to setting it to \c{-s
|
|
-ic:\\nasmlib}, but \c{!-dNAME="my name"} will work.
|
|
|
|
This environment variable was previously called \c{NASM}. This was
|
|
changed with version 0.98.31.
|
|
|
|
|
|
\H{qstart} \i{Quick Start} for \i{MASM} Users
|
|
|
|
If you're used to writing programs with MASM, or with \i{TASM} in
|
|
MASM-compatible (non-Ideal) mode, or with \i\c{a86}, this section
|
|
attempts to outline the major differences between MASM's syntax and
|
|
NASM's. If you're not already used to MASM, it's probably worth
|
|
skipping this section.
|
|
|
|
|
|
\S{qscs} NASM Is \I{case sensitivity}Case-Sensitive
|
|
|
|
One simple difference is that NASM is case-sensitive. It makes a
|
|
difference whether you call your label \c{foo}, \c{Foo} or \c{FOO}.
|
|
If you're assembling to \c{DOS} or \c{OS/2} \c{.OBJ} files, you can
|
|
invoke the \i\c{UPPERCASE} directive (documented in \k{objfmt}) to
|
|
ensure that all symbols exported to other code modules are forced
|
|
to be upper case; but even then, \e{within} a single module, NASM
|
|
will distinguish between labels differing only in case.
|
|
|
|
|
|
\S{qsbrackets} NASM Requires \i{Square Brackets} For \i{Memory References}
|
|
|
|
NASM was designed with simplicity of syntax in mind. One of the
|
|
\i{design goals} of NASM is that it should be possible, as far as is
|
|
practical, for the user to look at a single line of NASM code
|
|
and tell what opcode is generated by it. You can't do this in MASM:
|
|
if you declare, for example,
|
|
|
|
\c foo equ 1
|
|
\c bar dw 2
|
|
|
|
then the two lines of code
|
|
|
|
\c mov ax,foo
|
|
\c mov ax,bar
|
|
|
|
generate completely different opcodes, despite having
|
|
identical-looking syntaxes.
|
|
|
|
NASM avoids this undesirable situation by having a much simpler
|
|
syntax for memory references. The rule is simply that any access to
|
|
the \e{contents} of a memory location requires square brackets
|
|
around the address, and any access to the \e{address} of a variable
|
|
doesn't. So an instruction of the form \c{mov ax,foo} will
|
|
\e{always} refer to a compile-time constant, whether it's an \c{EQU}
|
|
or the address of a variable; and to access the \e{contents} of the
|
|
variable \c{bar}, you must code \c{mov ax,[bar]}.
|
|
|
|
This also means that NASM has no need for MASM's \i\c{OFFSET}
|
|
keyword, since the MASM code \c{mov ax,offset bar} means exactly the
|
|
same thing as NASM's \c{mov ax,bar}. If you're trying to get
|
|
large amounts of MASM code to assemble sensibly under NASM, you
|
|
can always code \c{%idefine offset} to make the preprocessor treat
|
|
the \c{OFFSET} keyword as a no-op.
|
|
|
|
This issue is even more confusing in \i\c{a86}, where declaring a
|
|
label with a trailing colon defines it to be a `label' as opposed to
|
|
a `variable' and causes \c{a86} to adopt NASM-style semantics; so in
|
|
\c{a86}, \c{mov ax,var} has different behaviour depending on whether
|
|
\c{var} was declared as \c{var: dw 0} (a label) or \c{var dw 0} (a
|
|
word-size variable). NASM is very simple by comparison:
|
|
\e{everything} is a label.
|
|
|
|
NASM, in the interests of simplicity, also does not support the
|
|
\i{hybrid syntaxes} supported by MASM and its clones, such as
|
|
\c{mov ax,table[bx]}, where a memory reference is denoted by one
|
|
portion outside square brackets and another portion inside. The
|
|
correct syntax for the above is \c{mov ax,[table+bx]}. Likewise,
|
|
\c{mov ax,es:[di]} is wrong and \c{mov ax,[es:di]} is right.
|
|
|
|
|
|
\S{qstypes} NASM Doesn't Store \i{Variable Types}
|
|
|
|
NASM, by design, chooses not to remember the types of variables you
|
|
declare. Whereas MASM will remember, on seeing \c{var dw 0}, that
|
|
you declared \c{var} as a word-size variable, and will then be able
|
|
to fill in the \i{ambiguity} in the size of the instruction \c{mov
|
|
var,2}, NASM will deliberately remember nothing about the symbol
|
|
\c{var} except where it begins, and so you must explicitly code
|
|
\c{mov word [var],2}.
|
|
|
|
For this reason, NASM doesn't support the \c{LODS}, \c{MOVS},
|
|
\c{STOS}, \c{SCAS}, \c{CMPS}, \c{INS}, or \c{OUTS} instructions,
|
|
but only supports the forms such as \c{LODSB}, \c{MOVSW}, and
|
|
\c{SCASD}, which explicitly specify the size of the components of
|
|
the strings being manipulated.
|
|
|
|
|
|
\S{qsassume} NASM Doesn't \i\c{ASSUME}
|
|
|
|
As part of NASM's drive for simplicity, it also does not support the
|
|
\c{ASSUME} directive. NASM will not keep track of what values you
|
|
choose to put in your segment registers, and will never
|
|
\e{automatically} generate a \i{segment override} prefix.
|
|
|
|
|
|
\S{qsmodel} NASM Doesn't Support \i{Memory Models}
|
|
|
|
NASM also does not have any directives to support different 16-bit
|
|
memory models. The programmer has to keep track of which functions
|
|
are supposed to be called with a \i{far call} and which with a
|
|
\i{near call}, and is responsible for putting the correct form of
|
|
\c{RET} instruction (\c{RETN} or \c{RETF}; NASM accepts \c{RET}
|
|
itself as an alternate form for \c{RETN}); in addition, the
|
|
programmer is responsible for coding CALL FAR instructions where
|
|
necessary when calling \e{external} functions, and must also keep
|
|
track of which external variable definitions are far and which are
|
|
near.
|
|
|
|
|
|
\S{qsfpu} \i{Floating-Point} Differences
|
|
|
|
NASM uses different names to refer to floating-point registers from
|
|
MASM: where MASM would call them \c{ST(0)}, \c{ST(1)} and so on, and
|
|
\i\c{a86} would call them simply \c{0}, \c{1} and so on, NASM
|
|
chooses to call them \c{st0}, \c{st1} etc.
|
|
|
|
As of version 0.96, NASM now treats the instructions with
|
|
\i{`nowait'} forms in the same way as MASM-compatible assemblers.
|
|
The idiosyncratic treatment employed by 0.95 and earlier was based
|
|
on a misunderstanding by the authors.
|
|
|
|
|
|
\S{qsother} Other Differences
|
|
|
|
For historical reasons, NASM uses the keyword \i\c{TWORD} where MASM
|
|
and compatible assemblers use \i\c{TBYTE}.
|
|
|
|
NASM does not declare \i{uninitialized storage} in the same way as
|
|
MASM: where a MASM programmer might use \c{stack db 64 dup (?)},
|
|
NASM requires \c{stack resb 64}, intended to be read as `reserve 64
|
|
bytes'. For a limited amount of compatibility, since NASM treats
|
|
\c{?} as a valid character in symbol names, you can code \c{? equ 0}
|
|
and then writing \c{dw ?} will at least do something vaguely useful.
|
|
\I\c{RESB}\i\c{DUP} is still not a supported syntax, however.
|
|
|
|
In addition to all of this, macros and directives work completely
|
|
differently to MASM. See \k{preproc} and \k{directive} for further
|
|
details.
|
|
|
|
|
|
\C{lang} The NASM Language
|
|
|
|
\H{syntax} Layout of a NASM Source Line
|
|
|
|
Like most assemblers, each NASM source line contains (unless it
|
|
is a macro, a preprocessor directive or an assembler directive: see
|
|
\k{preproc} and \k{directive}) some combination of the four fields
|
|
|
|
\c label: instruction operands ; comment
|
|
|
|
As usual, most of these fields are optional; the presence or absence
|
|
of any combination of a label, an instruction and a comment is allowed.
|
|
Of course, the operand field is either required or forbidden by the
|
|
presence and nature of the instruction field.
|
|
|
|
NASM uses backslash (\\) as the line continuation character; if a line
|
|
ends with backslash, the next line is considered to be a part of the
|
|
backslash-ended line.
|
|
|
|
NASM places no restrictions on white space within a line: labels may
|
|
have white space before them, or instructions may have no space
|
|
before them, or anything. The \i{colon} after a label is also
|
|
optional. (Note that this means that if you intend to code \c{lodsb}
|
|
alone on a line, and type \c{lodab} by accident, then that's still a
|
|
valid source line which does nothing but define a label. Running
|
|
NASM with the command-line option
|
|
\I{orphan-labels}\c{-w+orphan-labels} will cause it to warn you if
|
|
you define a label alone on a line without a \i{trailing colon}.)
|
|
|
|
\i{Valid characters} in labels are letters, numbers, \c{_}, \c{$},
|
|
\c{#}, \c{@}, \c{~}, \c{.}, and \c{?}. The only characters which may
|
|
be used as the \e{first} character of an identifier are letters,
|
|
\c{.} (with special meaning: see \k{locallab}), \c{_} and \c{?}.
|
|
An identifier may also be prefixed with a \I{$, prefix}\c{$} to
|
|
indicate that it is intended to be read as an identifier and not a
|
|
reserved word; thus, if some other module you are linking with
|
|
defines a symbol called \c{eax}, you can refer to \c{$eax} in NASM
|
|
code to distinguish the symbol from the register. Maximum length of
|
|
an identifier is 4095 characters.
|
|
|
|
The instruction field may contain any machine instruction: Pentium
|
|
and P6 instructions, FPU instructions, MMX instructions and even
|
|
undocumented instructions are all supported. The instruction may be
|
|
prefixed by \c{LOCK}, \c{REP}, \c{REPE}/\c{REPZ} or
|
|
\c{REPNE}/\c{REPNZ}, in the usual way. Explicit \I{address-size
|
|
prefixes}address-size and \i{operand-size prefixes} \i\c{A16},
|
|
\i\c{A32}, \i\c{A64}, \i\c{O16} and \i\c{O32}, \i\c{O64} are provided - one example of their use
|
|
is given in \k{mixsize}. You can also use the name of a \I{segment
|
|
override}segment register as an instruction prefix: coding
|
|
\c{es mov [bx],ax} is equivalent to coding \c{mov [es:bx],ax}. We
|
|
recommend the latter syntax, since it is consistent with other
|
|
syntactic features of the language, but for instructions such as
|
|
\c{LODSB}, which has no operands and yet can require a segment
|
|
override, there is no clean syntactic way to proceed apart from
|
|
\c{es lodsb}.
|
|
|
|
An instruction is not required to use a prefix: prefixes such as
|
|
\c{CS}, \c{A32}, \c{LOCK} or \c{REPE} can appear on a line by
|
|
themselves, and NASM will just generate the prefix bytes.
|
|
|
|
In addition to actual machine instructions, NASM also supports a
|
|
number of pseudo-instructions, described in \k{pseudop}.
|
|
|
|
Instruction \i{operands} may take a number of forms: they can be
|
|
registers, described simply by the register name (e.g. \c{ax},
|
|
\c{bp}, \c{ebx}, \c{cr0}: NASM does not use the \c{gas}-style
|
|
syntax in which register names must be prefixed by a \c{%} sign), or
|
|
they can be \i{effective addresses} (see \k{effaddr}), constants
|
|
(\k{const}) or expressions (\k{expr}).
|
|
|
|
For x87 \i{floating-point} instructions, NASM accepts a wide range of
|
|
syntaxes: you can use two-operand forms like MASM supports, or you
|
|
can use NASM's native single-operand forms in most cases.
|
|
\# Details of
|
|
\# all forms of each supported instruction are given in
|
|
\# \k{iref}.
|
|
For example, you can code:
|
|
|
|
\c fadd st1 ; this sets st0 := st0 + st1
|
|
\c fadd st0,st1 ; so does this
|
|
\c
|
|
\c fadd st1,st0 ; this sets st1 := st1 + st0
|
|
\c fadd to st1 ; so does this
|
|
|
|
Almost any x87 floating-point instruction that references memory must
|
|
use one of the prefixes \i\c{DWORD}, \i\c{QWORD} or \i\c{TWORD} to
|
|
indicate what size of \i{memory operand} it refers to.
|
|
|
|
|
|
\H{pseudop} \i{Pseudo-Instructions}
|
|
|
|
Pseudo-instructions are things which, though not real x86 machine
|
|
instructions, are used in the instruction field anyway because that's
|
|
the most convenient place to put them. The current pseudo-instructions
|
|
are \i\c{DB}, \i\c{DW}, \i\c{DD}, \i\c{DQ}, \i\c{DT}, \i\c{DO} and
|
|
\i\c{DY}; their \i{uninitialized} counterparts \i\c{RESB}, \i\c{RESW},
|
|
\i\c{RESD}, \i\c{RESQ}, \i\c{REST}, \i\c{RESO} and \i\c{RESY}; the
|
|
\i\c{INCBIN} command, the \i\c{EQU} command, and the \i\c{TIMES}
|
|
prefix.
|
|
|
|
|
|
\S{db} \c{DB} and Friends: Declaring Initialized Data
|
|
|
|
\i\c{DB}, \i\c{DW}, \i\c{DD}, \i\c{DQ}, \i\c{DT}, \i\c{DO} and
|
|
\i\c{DY} are used, much as in MASM, to declare initialized data in the
|
|
output file. They can be invoked in a wide range of ways:
|
|
\I{floating-point}\I{character constant}\I{string constant}
|
|
|
|
\c db 0x55 ; just the byte 0x55
|
|
\c db 0x55,0x56,0x57 ; three bytes in succession
|
|
\c db 'a',0x55 ; character constants are OK
|
|
\c db 'hello',13,10,'$' ; so are string constants
|
|
\c dw 0x1234 ; 0x34 0x12
|
|
\c dw 'a' ; 0x61 0x00 (it's just a number)
|
|
\c dw 'ab' ; 0x61 0x62 (character constant)
|
|
\c dw 'abc' ; 0x61 0x62 0x63 0x00 (string)
|
|
\c dd 0x12345678 ; 0x78 0x56 0x34 0x12
|
|
\c dd 1.234567e20 ; floating-point constant
|
|
\c dq 0x123456789abcdef0 ; eight byte constant
|
|
\c dq 1.234567e20 ; double-precision float
|
|
\c dt 1.234567e20 ; extended-precision float
|
|
|
|
\c{DT}, \c{DO} and \c{DY} do not accept \i{numeric constants} as operands.
|
|
|
|
|
|
\S{resb} \c{RESB} and Friends: Declaring \i{Uninitialized} Data
|
|
|
|
\i\c{RESB}, \i\c{RESW}, \i\c{RESD}, \i\c{RESQ}, \i\c{REST}, \i\c{RESO}
|
|
and \i\c{RESY} are designed to be used in the BSS section of a module:
|
|
they declare \e{uninitialized} storage space. Each takes a single
|
|
operand, which is the number of bytes, words, doublewords or whatever
|
|
to reserve. As stated in \k{qsother}, NASM does not support the
|
|
MASM/TASM syntax of reserving uninitialized space by writing
|
|
\I\c{?}\c{DW ?} or similar things: this is what it does instead. The
|
|
operand to a \c{RESB}-type pseudo-instruction is a \i\e{critical
|
|
expression}: see \k{crit}.
|
|
|
|
For example:
|
|
|
|
\c buffer: resb 64 ; reserve 64 bytes
|
|
\c wordvar: resw 1 ; reserve a word
|
|
\c realarray resq 10 ; array of ten reals
|
|
\c ymmval: resy 1 ; one YMM register
|
|
|
|
\S{incbin} \i\c{INCBIN}: Including External \i{Binary Files}
|
|
|
|
\c{INCBIN} is borrowed from the old Amiga assembler \i{DevPac}: it
|
|
includes a binary file verbatim into the output file. This can be
|
|
handy for (for example) including \i{graphics} and \i{sound} data
|
|
directly into a game executable file. It can be called in one of
|
|
these three ways:
|
|
|
|
\c incbin "file.dat" ; include the whole file
|
|
\c incbin "file.dat",1024 ; skip the first 1024 bytes
|
|
\c incbin "file.dat",1024,512 ; skip the first 1024, and
|
|
\c ; actually include at most 512
|
|
|
|
\c{INCBIN} is both a directive and a standard macro; the standard
|
|
macro version searches for the file in the include file search path
|
|
and adds the file to the dependency lists. This macro can be
|
|
overridden if desired.
|
|
|
|
|
|
\S{equ} \i\c{EQU}: Defining Constants
|
|
|
|
\c{EQU} defines a symbol to a given constant value: when \c{EQU} is
|
|
used, the source line must contain a label. The action of \c{EQU} is
|
|
to define the given label name to the value of its (only) operand.
|
|
This definition is absolute, and cannot change later. So, for
|
|
example,
|
|
|
|
\c message db 'hello, world'
|
|
\c msglen equ $-message
|
|
|
|
defines \c{msglen} to be the constant 12. \c{msglen} may not then be
|
|
redefined later. This is not a \i{preprocessor} definition either:
|
|
the value of \c{msglen} is evaluated \e{once}, using the value of
|
|
\c{$} (see \k{expr} for an explanation of \c{$}) at the point of
|
|
definition, rather than being evaluated wherever it is referenced
|
|
and using the value of \c{$} at the point of reference.
|
|
|
|
|
|
\S{times} \i\c{TIMES}: \i{Repeating} Instructions or Data
|
|
|
|
The \c{TIMES} prefix causes the instruction to be assembled multiple
|
|
times. This is partly present as NASM's equivalent of the \i\c{DUP}
|
|
syntax supported by \i{MASM}-compatible assemblers, in that you can
|
|
code
|
|
|
|
\c zerobuf: times 64 db 0
|
|
|
|
or similar things; but \c{TIMES} is more versatile than that. The
|
|
argument to \c{TIMES} is not just a numeric constant, but a numeric
|
|
\e{expression}, so you can do things like
|
|
|
|
\c buffer: db 'hello, world'
|
|
\c times 64-$+buffer db ' '
|
|
|
|
which will store exactly enough spaces to make the total length of
|
|
\c{buffer} up to 64. Finally, \c{TIMES} can be applied to ordinary
|
|
instructions, so you can code trivial \i{unrolled loops} in it:
|
|
|
|
\c times 100 movsb
|
|
|
|
Note that there is no effective difference between \c{times 100 resb
|
|
1} and \c{resb 100}, except that the latter will be assembled about
|
|
100 times faster due to the internal structure of the assembler.
|
|
|
|
The operand to \c{TIMES} is a critical expression (\k{crit}).
|
|
|
|
Note also that \c{TIMES} can't be applied to \i{macros}: the reason
|
|
for this is that \c{TIMES} is processed after the macro phase, which
|
|
allows the argument to \c{TIMES} to contain expressions such as
|
|
\c{64-$+buffer} as above. To repeat more than one line of code, or a
|
|
complex macro, use the preprocessor \i\c{%rep} directive.
|
|
|
|
|
|
\H{effaddr} Effective Addresses
|
|
|
|
An \i{effective address} is any operand to an instruction which
|
|
\I{memory reference}references memory. Effective addresses, in NASM,
|
|
have a very simple syntax: they consist of an expression evaluating
|
|
to the desired address, enclosed in \i{square brackets}. For
|
|
example:
|
|
|
|
\c wordvar dw 123
|
|
\c mov ax,[wordvar]
|
|
\c mov ax,[wordvar+1]
|
|
\c mov ax,[es:wordvar+bx]
|
|
|
|
Anything not conforming to this simple system is not a valid memory
|
|
reference in NASM, for example \c{es:wordvar[bx]}.
|
|
|
|
More complicated effective addresses, such as those involving more
|
|
than one register, work in exactly the same way:
|
|
|
|
\c mov eax,[ebx*2+ecx+offset]
|
|
\c mov ax,[bp+di+8]
|
|
|
|
NASM is capable of doing \i{algebra} on these effective addresses,
|
|
so that things which don't necessarily \e{look} legal are perfectly
|
|
all right:
|
|
|
|
\c mov eax,[ebx*5] ; assembles as [ebx*4+ebx]
|
|
\c mov eax,[label1*2-label2] ; ie [label1+(label1-label2)]
|
|
|
|
Some forms of effective address have more than one assembled form;
|
|
in most such cases NASM will generate the smallest form it can. For
|
|
example, there are distinct assembled forms for the 32-bit effective
|
|
addresses \c{[eax*2+0]} and \c{[eax+eax]}, and NASM will generally
|
|
generate the latter on the grounds that the former requires four
|
|
bytes to store a zero offset.
|
|
|
|
NASM has a hinting mechanism which will cause \c{[eax+ebx]} and
|
|
\c{[ebx+eax]} to generate different opcodes; this is occasionally
|
|
useful because \c{[esi+ebp]} and \c{[ebp+esi]} have different
|
|
default segment registers.
|
|
|
|
However, you can force NASM to generate an effective address in a
|
|
particular form by the use of the keywords \c{BYTE}, \c{WORD},
|
|
\c{DWORD} and \c{NOSPLIT}. If you need \c{[eax+3]} to be assembled
|
|
using a double-word offset field instead of the one byte NASM will
|
|
normally generate, you can code \c{[dword eax+3]}. Similarly, you
|
|
can force NASM to use a byte offset for a small value which it
|
|
hasn't seen on the first pass (see \k{crit} for an example of such a
|
|
code fragment) by using \c{[byte eax+offset]}. As special cases,
|
|
\c{[byte eax]} will code \c{[eax+0]} with a byte offset of zero, and
|
|
\c{[dword eax]} will code it with a double-word offset of zero. The
|
|
normal form, \c{[eax]}, will be coded with no offset field.
|
|
|
|
The form described in the previous paragraph is also useful if you
|
|
are trying to access data in a 32-bit segment from within 16 bit code.
|
|
For more information on this see the section on mixed-size addressing
|
|
(\k{mixaddr}). In particular, if you need to access data with a known
|
|
offset that is larger than will fit in a 16-bit value, if you don't
|
|
specify that it is a dword offset, nasm will cause the high word of
|
|
the offset to be lost.
|
|
|
|
Similarly, NASM will split \c{[eax*2]} into \c{[eax+eax]} because
|
|
that allows the offset field to be absent and space to be saved; in
|
|
fact, it will also split \c{[eax*2+offset]} into
|
|
\c{[eax+eax+offset]}. You can combat this behaviour by the use of
|
|
the \c{NOSPLIT} keyword: \c{[nosplit eax*2]} will force
|
|
\c{[eax*2+0]} to be generated literally.
|
|
|
|
In 64-bit mode, NASM will by default generate absolute addresses. The
|
|
\i\c{REL} keyword makes it produce \c{RIP}-relative addresses. Since
|
|
this is frequently the normally desired behaviour, see the \c{DEFAULT}
|
|
directive (\k{default}). The keyword \i\c{ABS} overrides \i\c{REL}.
|
|
|
|
|
|
\H{const} \i{Constants}
|
|
|
|
NASM understands four different types of constant: numeric,
|
|
character, string and floating-point.
|
|
|
|
|
|
\S{numconst} \i{Numeric Constants}
|
|
|
|
A numeric constant is simply a number. NASM allows you to specify
|
|
numbers in a variety of number bases, in a variety of ways: you can
|
|
suffix \c{H}, \c{Q} or \c{O}, and \c{B} for \i{hex}, \i{octal} and \i{binary},
|
|
or you can prefix \c{0x} for hex in the style of C, or you can
|
|
prefix \c{$} for hex in the style of Borland Pascal. Note, though,
|
|
that the \I{$, prefix}\c{$} prefix does double duty as a prefix on
|
|
identifiers (see \k{syntax}), so a hex number prefixed with a \c{$}
|
|
sign must have a digit after the \c{$} rather than a letter.
|
|
|
|
Numeric constants can have underscores (\c{_}) interspersed to break
|
|
up long strings.
|
|
|
|
Some examples:
|
|
|
|
\c mov ax,100 ; decimal
|
|
\c mov ax,0a2h ; hex
|
|
\c mov ax,$0a2 ; hex again: the 0 is required
|
|
\c mov ax,0xa2 ; hex yet again
|
|
\c mov ax,777q ; octal
|
|
\c mov ax,777o ; octal again
|
|
\c mov ax,10010011b ; binary
|
|
\c mov ax,1001_0011b ; same binary constant
|
|
|
|
|
|
\S{strings} \I{Strings}\i{Character Strings}
|
|
|
|
A character string consists of up to eight characters enclosed in
|
|
either single quotes (\c{'...'}), double quotes (\c{"..."}) or
|
|
backquotes (\c{`...`}). Single or double quotes are equivalent to
|
|
NASM (except of course that surrounding the constant with single
|
|
quotes allows double quotes to appear within it and vice versa); the
|
|
contents of those are represented verbatim. Strings enclosed in
|
|
backquotes support C-style \c{\\}-escapes for special characters.
|
|
|
|
|
|
The following \i{escape sequences} are recognized by backquoted strings:
|
|
|
|
\c \' single quote (')
|
|
\c \" double quote (")
|
|
\c \` backquote (`)
|
|
\c \\\ backslash (\)
|
|
\c \? question mark (?)
|
|
\c \a BEL (ASCII 7)
|
|
\c \b BS (ASCII 8)
|
|
\c \t TAB (ASCII 9)
|
|
\c \n LF (ASCII 10)
|
|
\c \v VT (ASCII 11)
|
|
\c \f FF (ASCII 12)
|
|
\c \r CR (ASCII 13)
|
|
\c \e ESC (ASCII 27)
|
|
\c \377 Up to 3 octal digits - literal byte
|
|
\c \xFF Up to 2 hexadecimal digits - literal byte
|
|
\c \u1234 4 hexadecimal digits - Unicode character
|
|
\c \U12345678 8 hexadecimal digits - Unicode character
|
|
|
|
All other escape sequences are reserved. Note that \c{\\0}, meaning a
|
|
\c{NUL} character (ASCII 0), is a special case of the octal escape
|
|
sequence.
|
|
|
|
\i{Unicode} characters specified with \c{\\u} or \c{\\U} are converted to
|
|
\i{UTF-8}. For example, the following lines are all equivalent:
|
|
|
|
\c db `\u263a` ; UTF-8 smiley face
|
|
\c db `\xe2\x98\xba` ; UTF-8 smiley face
|
|
\c db 0E2h, 098h, 0BAh ; UTF-8 smiley face
|
|
|
|
|
|
\S{chrconst} \i{Character Constants}
|
|
|
|
A character constant consists of a string up to eight bytes long, used
|
|
in an expression context. It is treated as if it was an integer.
|
|
|
|
A character constant with more than one byte will be arranged
|
|
with \i{little-endian} order in mind: if you code
|
|
|
|
\c mov eax,'abcd'
|
|
|
|
then the constant generated is not \c{0x61626364}, but
|
|
\c{0x64636261}, so that if you were then to store the value into
|
|
memory, it would read \c{abcd} rather than \c{dcba}. This is also
|
|
the sense of character constants understood by the Pentium's
|
|
\i\c{CPUID} instruction.
|
|
|
|
|
|
\S{strconst} \i{String Constants}
|
|
|
|
String constants are character strings used in the context of some
|
|
pseudo-instructions, namely the
|
|
\I\c{DW}\I\c{DD}\I\c{DQ}\I\c{DT}\I\c{DO}\I\c{DY}\i\c{DB} family and
|
|
\i\c{INCBIN} (where it represents a filename.) They are also used in
|
|
certain preprocessor directives.
|
|
|
|
A string constant looks like a character constant, only longer. It
|
|
is treated as a concatenation of maximum-size character constants
|
|
for the conditions. So the following are equivalent:
|
|
|
|
\c db 'hello' ; string constant
|
|
\c db 'h','e','l','l','o' ; equivalent character constants
|
|
|
|
And the following are also equivalent:
|
|
|
|
\c dd 'ninechars' ; doubleword string constant
|
|
\c dd 'nine','char','s' ; becomes three doublewords
|
|
\c db 'ninechars',0,0,0 ; and really looks like this
|
|
|
|
Note that when used in a string-supporting context, quoted strings are
|
|
treated as a string constants even if they are short enough to be a
|
|
character constant, because otherwise \c{db 'ab'} would have the same
|
|
effect as \c{db 'a'}, which would be silly. Similarly, three-character
|
|
or four-character constants are treated as strings when they are
|
|
operands to \c{DW}, and so forth.
|
|
|
|
\S{unicode} \I{UTF-16}\I{UTF-32}\i{Unicode} Strings
|
|
|
|
The special operators \i\c{__utf16__} and \i\c{__utf32__} allows
|
|
definition of Unicode strings. They take a string in UTF-8 format and
|
|
converts it to (littleendian) UTF-16 or UTF-32, respectively.
|
|
|
|
For example:
|
|
|
|
\c %define u(x) __utf16__(x)
|
|
\c %define w(x) __utf32__(x)
|
|
\c
|
|
\c dw u('C:\WINDOWS'), 0 ; Pathname in UTF-16
|
|
\c dd w(`A + B = \u206a`), 0 ; String in UTF-32
|
|
|
|
\c{__utf16__} and \c{__utf32__} can be applied either to strings
|
|
passed to the \c{DB} family instructions, or to character constants in
|
|
an expression context.
|
|
|
|
\S{fltconst} \I{floating-point, constants}Floating-Point Constants
|
|
|
|
\i{Floating-point} constants are acceptable only as arguments to
|
|
\i\c{DB}, \i\c{DW}, \i\c{DD}, \i\c{DQ}, \i\c{DT}, and \i\c{DO}, or as
|
|
arguments to the special operators \i\c{__float8__},
|
|
\i\c{__float16__}, \i\c{__float32__}, \i\c{__float64__},
|
|
\i\c{__float80m__}, \i\c{__float80e__}, \i\c{__float128l__}, and
|
|
\i\c{__float128h__}.
|
|
|
|
Floating-point constants are expressed in the traditional form:
|
|
digits, then a period, then optionally more digits, then optionally an
|
|
\c{E} followed by an exponent. The period is mandatory, so that NASM
|
|
can distinguish between \c{dd 1}, which declares an integer constant,
|
|
and \c{dd 1.0} which declares a floating-point constant. NASM also
|
|
support C99-style hexadecimal floating-point: \c{0x}, hexadecimal
|
|
digits, period, optionally more hexadeximal digits, then optionally a
|
|
\c{P} followed by a \e{binary} (not hexadecimal) exponent in decimal
|
|
notation.
|
|
|
|
Underscores to break up groups of digits are permitted in
|
|
floating-point constants as well.
|
|
|
|
Some examples:
|
|
|
|
\c db -0.2 ; "Quarter precision"
|
|
\c dw -0.5 ; IEEE 754r/SSE5 half precision
|
|
\c dd 1.2 ; an easy one
|
|
\c dd 1.222_222_222 ; underscores are permitted
|
|
\c dd 0x1p+2 ; 1.0x2^2 = 4.0
|
|
\c dq 0x1p+32 ; 1.0x2^32 = 4 294 967 296.0
|
|
\c dq 1.e10 ; 10 000 000 000.0
|
|
\c dq 1.e+10 ; synonymous with 1.e10
|
|
\c dq 1.e-10 ; 0.000 000 000 1
|
|
\c dt 3.141592653589793238462 ; pi
|
|
\c do 1.e+4000 ; IEEE 754r quad precision
|
|
|
|
The 8-bit "quarter-precision" floating-point format is
|
|
sign:exponent:mantissa = 1:4:3 with an exponent bias of 7. This
|
|
appears to be the most frequently used 8-bit floating-point format,
|
|
although it is not covered by any formal standard. This is sometimes
|
|
called a "\i{minifloat}."
|
|
|
|
The special operators are used to produce floating-point numbers in
|
|
other contexts. They produce the binary representation of a specific
|
|
floating-point number as an integer, and can use anywhere integer
|
|
constants are used in an expression. \c{__float80m__} and
|
|
\c{__float80e__} produce the 64-bit mantissa and 16-bit exponent of an
|
|
80-bit floating-point number, and \c{__float128l__} and
|
|
\c{__float128h__} produce the lower and upper 64-bit halves of a 128-bit
|
|
floating-point number, respectively.
|
|
|
|
For example:
|
|
|
|
\c mov rax,__float64__(3.141592653589793238462)
|
|
|
|
... would assign the binary representation of pi as a 64-bit floating
|
|
point number into \c{RAX}. This is exactly equivalent to:
|
|
|
|
\c mov rax,0x400921fb54442d18
|
|
|
|
NASM cannot do compile-time arithmetic on floating-point constants.
|
|
This is because NASM is designed to be portable - although it always
|
|
generates code to run on x86 processors, the assembler itself can
|
|
run on any system with an ANSI C compiler. Therefore, the assembler
|
|
cannot guarantee the presence of a floating-point unit capable of
|
|
handling the \i{Intel number formats}, and so for NASM to be able to
|
|
do floating arithmetic it would have to include its own complete set
|
|
of floating-point routines, which would significantly increase the
|
|
size of the assembler for very little benefit.
|
|
|
|
The special tokens \i\c{__Infinity__}, \i\c{__QNaN__} (or
|
|
\i\c{__NaN__}) and \i\c{__SNaN__} can be used to generate
|
|
\I{infinity}infinities, quiet \i{NaN}s, and signalling NaNs,
|
|
respectively. These are normally used as macros:
|
|
|
|
\c %define Inf __Infinity__
|
|
\c %define NaN __QNaN__
|
|
\c
|
|
\c dq +1.5, -Inf, NaN ; Double-precision constants
|
|
|
|
\S{bcdconst} \I{floating-point, packed BCD constants}Packed BCD Constants
|
|
|
|
x87-style packed BCD constants can be used in the same contexts as
|
|
80-bit floating-point numbers. They are suffixed with \c{p} or
|
|
prefixed with \c{0p}, and can include up to 18 decimal digits.
|
|
|
|
As with other numeric constants, underscores can be used to separate
|
|
digits.
|
|
|
|
For example:
|
|
|
|
\c dt 12_345_678_901_245_678p
|
|
\c dt -12_345_678_901_245_678p
|
|
\c dt +0p33
|
|
\c dt 33p
|
|
|
|
|
|
\H{expr} \i{Expressions}
|
|
|
|
Expressions in NASM are similar in syntax to those in C. Expressions
|
|
are evaluated as 64-bit integers which are then adjusted to the
|
|
appropriate size.
|
|
|
|
NASM supports two special tokens in expressions, allowing
|
|
calculations to involve the current assembly position: the
|
|
\I{$, here}\c{$} and \i\c{$$} tokens. \c{$} evaluates to the assembly
|
|
position at the beginning of the line containing the expression; so
|
|
you can code an \i{infinite loop} using \c{JMP $}. \c{$$} evaluates
|
|
to the beginning of the current section; so you can tell how far
|
|
into the section you are by using \c{($-$$)}.
|
|
|
|
The arithmetic \i{operators} provided by NASM are listed here, in
|
|
increasing order of \i{precedence}.
|
|
|
|
|
|
\S{expor} \i\c{|}: \i{Bitwise OR} Operator
|
|
|
|
The \c{|} operator gives a bitwise OR, exactly as performed by the
|
|
\c{OR} machine instruction. Bitwise OR is the lowest-priority
|
|
arithmetic operator supported by NASM.
|
|
|
|
|
|
\S{expxor} \i\c{^}: \i{Bitwise XOR} Operator
|
|
|
|
\c{^} provides the bitwise XOR operation.
|
|
|
|
|
|
\S{expand} \i\c{&}: \i{Bitwise AND} Operator
|
|
|
|
\c{&} provides the bitwise AND operation.
|
|
|
|
|
|
\S{expshift} \i\c{<<} and \i\c{>>}: \i{Bit Shift} Operators
|
|
|
|
\c{<<} gives a bit-shift to the left, just as it does in C. So \c{5<<3}
|
|
evaluates to 5 times 8, or 40. \c{>>} gives a bit-shift to the
|
|
right; in NASM, such a shift is \e{always} unsigned, so that
|
|
the bits shifted in from the left-hand end are filled with zero
|
|
rather than a sign-extension of the previous highest bit.
|
|
|
|
|
|
\S{expplmi} \I{+ opaddition}\c{+} and \I{- opsubtraction}\c{-}:
|
|
\i{Addition} and \i{Subtraction} Operators
|
|
|
|
The \c{+} and \c{-} operators do perfectly ordinary addition and
|
|
subtraction.
|
|
|
|
|
|
\S{expmul} \i\c{*}, \i\c{/}, \i\c{//}, \i\c{%} and \i\c{%%}:
|
|
\i{Multiplication} and \i{Division}
|
|
|
|
\c{*} is the multiplication operator. \c{/} and \c{//} are both
|
|
division operators: \c{/} is \i{unsigned division} and \c{//} is
|
|
\i{signed division}. Similarly, \c{%} and \c{%%} provide \I{unsigned
|
|
modulo}\I{modulo operators}unsigned and
|
|
\i{signed modulo} operators respectively.
|
|
|
|
NASM, like ANSI C, provides no guarantees about the sensible
|
|
operation of the signed modulo operator.
|
|
|
|
Since the \c{%} character is used extensively by the macro
|
|
\i{preprocessor}, you should ensure that both the signed and unsigned
|
|
modulo operators are followed by white space wherever they appear.
|
|
|
|
|
|
\S{expmul} \i{Unary Operators}: \I{+ opunary}\c{+}, \I{- opunary}\c{-},
|
|
\i\c{~}, \I{! opunary}\c{!} and \i\c{SEG}
|
|
|
|
The highest-priority operators in NASM's expression grammar are
|
|
those which only apply to one argument. \c{-} negates its operand,
|
|
\c{+} does nothing (it's provided for symmetry with \c{-}), \c{~}
|
|
computes the \i{one's complement} of its operand, \c{!} is the
|
|
\i{logical negation} operator, and \c{SEG} provides the \i{segment address}
|
|
of its operand (explained in more detail in \k{segwrt}).
|
|
|
|
|
|
\H{segwrt} \i\c{SEG} and \i\c{WRT}
|
|
|
|
When writing large 16-bit programs, which must be split into
|
|
multiple \i{segments}, it is often necessary to be able to refer to
|
|
the \I{segment address}segment part of the address of a symbol. NASM
|
|
supports the \c{SEG} operator to perform this function.
|
|
|
|
The \c{SEG} operator returns the \i\e{preferred} segment base of a
|
|
symbol, defined as the segment base relative to which the offset of
|
|
the symbol makes sense. So the code
|
|
|
|
\c mov ax,seg symbol
|
|
\c mov es,ax
|
|
\c mov bx,symbol
|
|
|
|
will load \c{ES:BX} with a valid pointer to the symbol \c{symbol}.
|
|
|
|
Things can be more complex than this: since 16-bit segments and
|
|
\i{groups} may \I{overlapping segments}overlap, you might occasionally
|
|
want to refer to some symbol using a different segment base from the
|
|
preferred one. NASM lets you do this, by the use of the \c{WRT}
|
|
(With Reference To) keyword. So you can do things like
|
|
|
|
\c mov ax,weird_seg ; weird_seg is a segment base
|
|
\c mov es,ax
|
|
\c mov bx,symbol wrt weird_seg
|
|
|
|
to load \c{ES:BX} with a different, but functionally equivalent,
|
|
pointer to the symbol \c{symbol}.
|
|
|
|
NASM supports far (inter-segment) calls and jumps by means of the
|
|
syntax \c{call segment:offset}, where \c{segment} and \c{offset}
|
|
both represent immediate values. So to call a far procedure, you
|
|
could code either of
|
|
|
|
\c call (seg procedure):procedure
|
|
\c call weird_seg:(procedure wrt weird_seg)
|
|
|
|
(The parentheses are included for clarity, to show the intended
|
|
parsing of the above instructions. They are not necessary in
|
|
practice.)
|
|
|
|
NASM supports the syntax \I\c{CALL FAR}\c{call far procedure} as a
|
|
synonym for the first of the above usages. \c{JMP} works identically
|
|
to \c{CALL} in these examples.
|
|
|
|
To declare a \i{far pointer} to a data item in a data segment, you
|
|
must code
|
|
|
|
\c dw symbol, seg symbol
|
|
|
|
NASM supports no convenient synonym for this, though you can always
|
|
invent one using the macro processor.
|
|
|
|
|
|
\H{strict} \i\c{STRICT}: Inhibiting Optimization
|
|
|
|
When assembling with the optimizer set to level 2 or higher (see
|
|
\k{opt-O}), NASM will use size specifiers (\c{BYTE}, \c{WORD},
|
|
\c{DWORD}, \c{QWORD}, \c{TWORD}, \c{OWORD} or \c{YWORD}), but will
|
|
give them the smallest possible size. The keyword \c{STRICT} can be
|
|
used to inhibit optimization and force a particular operand to be
|
|
emitted in the specified size. For example, with the optimizer on, and
|
|
in \c{BITS 16} mode,
|
|
|
|
\c push dword 33
|
|
|
|
is encoded in three bytes \c{66 6A 21}, whereas
|
|
|
|
\c push strict dword 33
|
|
|
|
is encoded in six bytes, with a full dword immediate operand \c{66 68
|
|
21 00 00 00}.
|
|
|
|
With the optimizer off, the same code (six bytes) is generated whether
|
|
the \c{STRICT} keyword was used or not.
|
|
|
|
|
|
\H{crit} \i{Critical Expressions}
|
|
|
|
Although NASM has an optional multi-pass optimizer, there are some
|
|
expressions which must be resolvable on the first pass. These are
|
|
called \e{Critical Expressions}.
|
|
|
|
The first pass is used to determine the size of all the assembled
|
|
code and data, so that the second pass, when generating all the
|
|
code, knows all the symbol addresses the code refers to. So one
|
|
thing NASM can't handle is code whose size depends on the value of a
|
|
symbol declared after the code in question. For example,
|
|
|
|
\c times (label-$) db 0
|
|
\c label: db 'Where am I?'
|
|
|
|
The argument to \i\c{TIMES} in this case could equally legally
|
|
evaluate to anything at all; NASM will reject this example because
|
|
it cannot tell the size of the \c{TIMES} line when it first sees it.
|
|
It will just as firmly reject the slightly \I{paradox}paradoxical
|
|
code
|
|
|
|
\c times (label-$+1) db 0
|
|
\c label: db 'NOW where am I?'
|
|
|
|
in which \e{any} value for the \c{TIMES} argument is by definition
|
|
wrong!
|
|
|
|
NASM rejects these examples by means of a concept called a
|
|
\e{critical expression}, which is defined to be an expression whose
|
|
value is required to be computable in the first pass, and which must
|
|
therefore depend only on symbols defined before it. The argument to
|
|
the \c{TIMES} prefix is a critical expression.
|
|
|
|
\H{locallab} \i{Local Labels}
|
|
|
|
NASM gives special treatment to symbols beginning with a \i{period}.
|
|
A label beginning with a single period is treated as a \e{local}
|
|
label, which means that it is associated with the previous non-local
|
|
label. So, for example:
|
|
|
|
\c label1 ; some code
|
|
\c
|
|
\c .loop
|
|
\c ; some more code
|
|
\c
|
|
\c jne .loop
|
|
\c ret
|
|
\c
|
|
\c label2 ; some code
|
|
\c
|
|
\c .loop
|
|
\c ; some more code
|
|
\c
|
|
\c jne .loop
|
|
\c ret
|
|
|
|
In the above code fragment, each \c{JNE} instruction jumps to the
|
|
line immediately before it, because the two definitions of \c{.loop}
|
|
are kept separate by virtue of each being associated with the
|
|
previous non-local label.
|
|
|
|
This form of local label handling is borrowed from the old Amiga
|
|
assembler \i{DevPac}; however, NASM goes one step further, in
|
|
allowing access to local labels from other parts of the code. This
|
|
is achieved by means of \e{defining} a local label in terms of the
|
|
previous non-local label: the first definition of \c{.loop} above is
|
|
really defining a symbol called \c{label1.loop}, and the second
|
|
defines a symbol called \c{label2.loop}. So, if you really needed
|
|
to, you could write
|
|
|
|
\c label3 ; some more code
|
|
\c ; and some more
|
|
\c
|
|
\c jmp label1.loop
|
|
|
|
Sometimes it is useful - in a macro, for instance - to be able to
|
|
define a label which can be referenced from anywhere but which
|
|
doesn't interfere with the normal local-label mechanism. Such a
|
|
label can't be non-local because it would interfere with subsequent
|
|
definitions of, and references to, local labels; and it can't be
|
|
local because the macro that defined it wouldn't know the label's
|
|
full name. NASM therefore introduces a third type of label, which is
|
|
probably only useful in macro definitions: if a label begins with
|
|
the \I{label prefix}special prefix \i\c{..@}, then it does nothing
|
|
to the local label mechanism. So you could code
|
|
|
|
\c label1: ; a non-local label
|
|
\c .local: ; this is really label1.local
|
|
\c ..@foo: ; this is a special symbol
|
|
\c label2: ; another non-local label
|
|
\c .local: ; this is really label2.local
|
|
\c
|
|
\c jmp ..@foo ; this will jump three lines up
|
|
|
|
NASM has the capacity to define other special symbols beginning with
|
|
a double period: for example, \c{..start} is used to specify the
|
|
entry point in the \c{obj} output format (see \k{dotdotstart}).
|
|
|
|
|
|
\C{preproc} The NASM \i{Preprocessor}
|
|
|
|
NASM contains a powerful \i{macro processor}, which supports
|
|
conditional assembly, multi-level file inclusion, two forms of macro
|
|
(single-line and multi-line), and a `context stack' mechanism for
|
|
extra macro power. Preprocessor directives all begin with a \c{%}
|
|
sign.
|
|
|
|
The preprocessor collapses all lines which end with a backslash (\\)
|
|
character into a single line. Thus:
|
|
|
|
\c %define THIS_VERY_LONG_MACRO_NAME_IS_DEFINED_TO \\
|
|
\c THIS_VALUE
|
|
|
|
will work like a single-line macro without the backslash-newline
|
|
sequence.
|
|
|
|
\H{slmacro} \i{Single-Line Macros}
|
|
|
|
\S{define} The Normal Way: \I\c{%idefine}\i\c{%define}
|
|
|
|
Single-line macros are defined using the \c{%define} preprocessor
|
|
directive. The definitions work in a similar way to C; so you can do
|
|
things like
|
|
|
|
\c %define ctrl 0x1F &
|
|
\c %define param(a,b) ((a)+(a)*(b))
|
|
\c
|
|
\c mov byte [param(2,ebx)], ctrl 'D'
|
|
|
|
which will expand to
|
|
|
|
\c mov byte [(2)+(2)*(ebx)], 0x1F & 'D'
|
|
|
|
When the expansion of a single-line macro contains tokens which
|
|
invoke another macro, the expansion is performed at invocation time,
|
|
not at definition time. Thus the code
|
|
|
|
\c %define a(x) 1+b(x)
|
|
\c %define b(x) 2*x
|
|
\c
|
|
\c mov ax,a(8)
|
|
|
|
will evaluate in the expected way to \c{mov ax,1+2*8}, even though
|
|
the macro \c{b} wasn't defined at the time of definition of \c{a}.
|
|
|
|
Macros defined with \c{%define} are \i{case sensitive}: after
|
|
\c{%define foo bar}, only \c{foo} will expand to \c{bar}: \c{Foo} or
|
|
\c{FOO} will not. By using \c{%idefine} instead of \c{%define} (the
|
|
`i' stands for `insensitive') you can define all the case variants
|
|
of a macro at once, so that \c{%idefine foo bar} would cause
|
|
\c{foo}, \c{Foo}, \c{FOO}, \c{fOO} and so on all to expand to
|
|
\c{bar}.
|
|
|
|
There is a mechanism which detects when a macro call has occurred as
|
|
a result of a previous expansion of the same macro, to guard against
|
|
\i{circular references} and infinite loops. If this happens, the
|
|
preprocessor will only expand the first occurrence of the macro.
|
|
Hence, if you code
|
|
|
|
\c %define a(x) 1+a(x)
|
|
\c
|
|
\c mov ax,a(3)
|
|
|
|
the macro \c{a(3)} will expand once, becoming \c{1+a(3)}, and will
|
|
then expand no further. This behaviour can be useful: see \k{32c}
|
|
for an example of its use.
|
|
|
|
You can \I{overloading, single-line macros}overload single-line
|
|
macros: if you write
|
|
|
|
\c %define foo(x) 1+x
|
|
\c %define foo(x,y) 1+x*y
|
|
|
|
the preprocessor will be able to handle both types of macro call,
|
|
by counting the parameters you pass; so \c{foo(3)} will become
|
|
\c{1+3} whereas \c{foo(ebx,2)} will become \c{1+ebx*2}. However, if
|
|
you define
|
|
|
|
\c %define foo bar
|
|
|
|
then no other definition of \c{foo} will be accepted: a macro with
|
|
no parameters prohibits the definition of the same name as a macro
|
|
\e{with} parameters, and vice versa.
|
|
|
|
This doesn't prevent single-line macros being \e{redefined}: you can
|
|
perfectly well define a macro with
|
|
|
|
\c %define foo bar
|
|
|
|
and then re-define it later in the same source file with
|
|
|
|
\c %define foo baz
|
|
|
|
Then everywhere the macro \c{foo} is invoked, it will be expanded
|
|
according to the most recent definition. This is particularly useful
|
|
when defining single-line macros with \c{%assign} (see \k{assign}).
|
|
|
|
You can \i{pre-define} single-line macros using the `-d' option on
|
|
the NASM command line: see \k{opt-d}.
|
|
|
|
|
|
\S{xdefine} Resolving \c{%define}: \I\c{%ixdefine}\i\c{%xdefine}
|
|
|
|
To have a reference to an embedded single-line macro resolved at the
|
|
time that the embedding macro is \e{defined}, as opposed to when the
|
|
embedding macro is \e{expanded}, you need a different mechanism to the
|
|
one offered by \c{%define}. The solution is to use \c{%xdefine}, or
|
|
it's \I{case sensitive}case-insensitive counterpart \c{%ixdefine}.
|
|
|
|
Suppose you have the following code:
|
|
|
|
\c %define isTrue 1
|
|
\c %define isFalse isTrue
|
|
\c %define isTrue 0
|
|
\c
|
|
\c val1: db isFalse
|
|
\c
|
|
\c %define isTrue 1
|
|
\c
|
|
\c val2: db isFalse
|
|
|
|
In this case, \c{val1} is equal to 0, and \c{val2} is equal to 1.
|
|
This is because, when a single-line macro is defined using
|
|
\c{%define}, it is expanded only when it is called. As \c{isFalse}
|
|
expands to \c{isTrue}, the expansion will be the current value of
|
|
\c{isTrue}. The first time it is called that is 0, and the second
|
|
time it is 1.
|
|
|
|
If you wanted \c{isFalse} to expand to the value assigned to the
|
|
embedded macro \c{isTrue} at the time that \c{isFalse} was defined,
|
|
you need to change the above code to use \c{%xdefine}.
|
|
|
|
\c %xdefine isTrue 1
|
|
\c %xdefine isFalse isTrue
|
|
\c %xdefine isTrue 0
|
|
\c
|
|
\c val1: db isFalse
|
|
\c
|
|
\c %xdefine isTrue 1
|
|
\c
|
|
\c val2: db isFalse
|
|
|
|
Now, each time that \c{isFalse} is called, it expands to 1,
|
|
as that is what the embedded macro \c{isTrue} expanded to at
|
|
the time that \c{isFalse} was defined.
|
|
|
|
|
|
\S{concat%+} Concatenating Single Line Macro Tokens: \i\c{%+}
|
|
|
|
Individual tokens in single line macros can be concatenated, to produce
|
|
longer tokens for later processing. This can be useful if there are
|
|
several similar macros that perform similar functions.
|
|
|
|
Please note that a space is required after \c{%+}, in order to
|
|
disambiguate it from the syntax \c{%+1} used in multiline macros.
|
|
|
|
As an example, consider the following:
|
|
|
|
\c %define BDASTART 400h ; Start of BIOS data area
|
|
|
|
\c struc tBIOSDA ; its structure
|
|
\c .COM1addr RESW 1
|
|
\c .COM2addr RESW 1
|
|
\c ; ..and so on
|
|
\c endstruc
|
|
|
|
Now, if we need to access the elements of tBIOSDA in different places,
|
|
we can end up with:
|
|
|
|
\c mov ax,BDASTART + tBIOSDA.COM1addr
|
|
\c mov bx,BDASTART + tBIOSDA.COM2addr
|
|
|
|
This will become pretty ugly (and tedious) if used in many places, and
|
|
can be reduced in size significantly by using the following macro:
|
|
|
|
\c ; Macro to access BIOS variables by their names (from tBDA):
|
|
|
|
\c %define BDA(x) BDASTART + tBIOSDA. %+ x
|
|
|
|
Now the above code can be written as:
|
|
|
|
\c mov ax,BDA(COM1addr)
|
|
\c mov bx,BDA(COM2addr)
|
|
|
|
Using this feature, we can simplify references to a lot of macros (and,
|
|
in turn, reduce typing errors).
|
|
|
|
|
|
\S{selfref%?} The Macro Name Itself: \i\c{%?} and \i\c{%??}
|
|
|
|
The special symbols \c{%?} and \c{%??} can be used to reference the
|
|
macro name itself inside a macro expansion, this is supported for both
|
|
single-and multi-line macros. \c{%?} refers to the macro name as
|
|
\e{invoked}, whereas \c{%??} refers to the macro name as
|
|
\e{declared}. The two are always the same for case-sensitive
|
|
macros, but for case-insensitive macros, they can differ.
|
|
|
|
For example:
|
|
|
|
\c %idefine Foo mov %?,%??
|
|
\c
|
|
\c foo
|
|
\c FOO
|
|
|
|
will expand to:
|
|
|
|
\c mov foo,Foo
|
|
\c mov FOO,Foo
|
|
|
|
The sequence:
|
|
|
|
\c %idefine keyword $%?
|
|
|
|
can be used to make a keyword "disappear", for example in case a new
|
|
instruction has been used as a label in older code. For example:
|
|
|
|
\c %idefine pause $%? ; Hide the PAUSE instruction
|
|
|
|
\S{undef} Undefining Single-Line Macros: \i\c{%undef}
|
|
|
|
Single-line macros can be removed with the \c{%undef} directive. For
|
|
example, the following sequence:
|
|
|
|
\c %define foo bar
|
|
\c %undef foo
|
|
\c
|
|
\c mov eax, foo
|
|
|
|
will expand to the instruction \c{mov eax, foo}, since after
|
|
\c{%undef} the macro \c{foo} is no longer defined.
|
|
|
|
Macros that would otherwise be pre-defined can be undefined on the
|
|
command-line using the `-u' option on the NASM command line: see
|
|
\k{opt-u}.
|
|
|
|
|
|
\S{assign} \i{Preprocessor Variables}: \i\c{%assign}
|
|
|
|
An alternative way to define single-line macros is by means of the
|
|
\c{%assign} command (and its \I{case sensitive}case-insensitive
|
|
counterpart \i\c{%iassign}, which differs from \c{%assign} in
|
|
exactly the same way that \c{%idefine} differs from \c{%define}).
|
|
|
|
\c{%assign} is used to define single-line macros which take no
|
|
parameters and have a numeric value. This value can be specified in
|
|
the form of an expression, and it will be evaluated once, when the
|
|
\c{%assign} directive is processed.
|
|
|
|
Like \c{%define}, macros defined using \c{%assign} can be re-defined
|
|
later, so you can do things like
|
|
|
|
\c %assign i i+1
|
|
|
|
to increment the numeric value of a macro.
|
|
|
|
\c{%assign} is useful for controlling the termination of \c{%rep}
|
|
preprocessor loops: see \k{rep} for an example of this. Another
|
|
use for \c{%assign} is given in \k{16c} and \k{32c}.
|
|
|
|
The expression passed to \c{%assign} is a \i{critical expression}
|
|
(see \k{crit}), and must also evaluate to a pure number (rather than
|
|
a relocatable reference such as a code or data address, or anything
|
|
involving a register).
|
|
|
|
|
|
\S{defstr} Defining Strings: \I\c{%idefstr}\i\c{%defstr}
|
|
|
|
\c{%defstr}, and its case-insensitive counterpart \c{%idefstr}, define
|
|
or redefine a single-line macro without parameters but converts the
|
|
entire right-hand side, after macro expansion, to a quoted string
|
|
before definition.
|
|
|
|
For example:
|
|
|
|
\c %defstr test TEST
|
|
|
|
is equivalent to
|
|
|
|
\c %define test 'TEST'
|
|
|
|
This can be used, for example, with the \c{%!} construct (see
|
|
\k{getenv}):
|
|
|
|
\c %defstr PATH %!PATH ; The operating system PATH variable
|
|
|
|
|
|
\H{strlen} \i{String Manipulation in Macros}
|
|
|
|
It's often useful to be able to handle strings in macros. NASM
|
|
supports two simple string handling macro operators from which
|
|
more complex operations can be constructed.
|
|
|
|
All the string operators define or redefine a value (either a string
|
|
or a numeric value) to a single-line macro.
|
|
|
|
\S{strcat} \i{Concatenating Strings}: \i\c{%strcat}
|
|
|
|
The \c{%strcat} operator concatenates quoted strings and assign them to
|
|
a single-line macro. In doing so, it may change the type of quotes
|
|
and possibly use \c{\\}-escapes inside \c{`}-quoted strings in order to
|
|
make sure the string is still a valid quoted string.
|
|
|
|
For example:
|
|
|
|
\c %strcat alpha "Alpha: ", '12" screen'
|
|
|
|
... would assign the value \c{'Alpha: 12" screen'} to \c{alpha}.
|
|
Similarly:
|
|
|
|
\c %strcat beta '"', "'"
|
|
|
|
... would assign the value \c{`"'`} to \c{beta}.
|
|
|
|
The use of commas to separate strings is permitted but optional.
|
|
|
|
|
|
\S{strlen} \i{String Length}: \i\c{%strlen}
|
|
|
|
The \c{%strlen} operator assigns the length of a string to a macro.
|
|
For example:
|
|
|
|
\c %strlen charcnt 'my string'
|
|
|
|
In this example, \c{charcnt} would receive the value 9, just as
|
|
if an \c{%assign} had been used. In this example, \c{'my string'}
|
|
was a literal string but it could also have been a single-line
|
|
macro that expands to a string, as in the following example:
|
|
|
|
\c %define sometext 'my string'
|
|
\c %strlen charcnt sometext
|
|
|
|
As in the first case, this would result in \c{charcnt} being
|
|
assigned the value of 9.
|
|
|
|
|
|
\S{substr} \i{Extracting Substrings}: \i\c{%substr}
|
|
|
|
Individual letters or substrings in strings can be extracted using the
|
|
\c{%substr} operator. An example of its use is probably more useful
|
|
than the description:
|
|
|
|
\c %substr mychar 'xyzw' 1 ; equivalent to %define mychar 'x'
|
|
\c %substr mychar 'xyzw' 2 ; equivalent to %define mychar 'y'
|
|
\c %substr mychar 'xyzw' 3 ; equivalent to %define mychar 'z'
|
|
\c %substr mychar 'xyzw' 2,2 ; equivalent to %define mychar 'yz'
|
|
\c %substr mychar 'xyzw' 2,-1 ; equivalent to %define mychar 'yzw'
|
|
\c %substr mychar 'xyzw' 2,-2 ; equivalent to %define mychar 'yz'
|
|
|
|
As with \c{%strlen} (see \k{strlen}), the first parameter is the
|
|
single-line macro to be created and the second is the string. The
|
|
third parameter specifies the first character to be selected, and the
|
|
optional fourth parameter preceeded by comma) is the length. Note
|
|
that the first index is 1, not 0 and the last index is equal to the
|
|
value that \c{%strlen} would assign given the same string. Index
|
|
values out of range result in an empty string. A negative length
|
|
means "until N-1 characters before the end of string", i.e. \c{-1}
|
|
means until end of string, \c{-2} until one character before, etc.
|
|
|
|
|
|
\H{mlmacro} \i{Multi-Line Macros}: \I\c{%imacro}\i\c{%macro}
|
|
|
|
Multi-line macros are much more like the type of macro seen in MASM
|
|
and TASM: a multi-line macro definition in NASM looks something like
|
|
this.
|
|
|
|
\c %macro prologue 1
|
|
\c
|
|
\c push ebp
|
|
\c mov ebp,esp
|
|
\c sub esp,%1
|
|
\c
|
|
\c %endmacro
|
|
|
|
This defines a C-like function prologue as a macro: so you would
|
|
invoke the macro with a call such as
|
|
|
|
\c myfunc: prologue 12
|
|
|
|
which would expand to the three lines of code
|
|
|
|
\c myfunc: push ebp
|
|
\c mov ebp,esp
|
|
\c sub esp,12
|
|
|
|
The number \c{1} after the macro name in the \c{%macro} line defines
|
|
the number of parameters the macro \c{prologue} expects to receive.
|
|
The use of \c{%1} inside the macro definition refers to the first
|
|
parameter to the macro call. With a macro taking more than one
|
|
parameter, subsequent parameters would be referred to as \c{%2},
|
|
\c{%3} and so on.
|
|
|
|
Multi-line macros, like single-line macros, are \i{case-sensitive},
|
|
unless you define them using the alternative directive \c{%imacro}.
|
|
|
|
If you need to pass a comma as \e{part} of a parameter to a
|
|
multi-line macro, you can do that by enclosing the entire parameter
|
|
in \I{braces, around macro parameters}braces. So you could code
|
|
things like
|
|
|
|
\c %macro silly 2
|
|
\c
|
|
\c %2: db %1
|
|
\c
|
|
\c %endmacro
|
|
\c
|
|
\c silly 'a', letter_a ; letter_a: db 'a'
|
|
\c silly 'ab', string_ab ; string_ab: db 'ab'
|
|
\c silly {13,10}, crlf ; crlf: db 13,10
|
|
|
|
|
|
\S{mlmacover} Overloading Multi-Line Macros\I{overloading, multi-line macros}
|
|
|
|
As with single-line macros, multi-line macros can be overloaded by
|
|
defining the same macro name several times with different numbers of
|
|
parameters. This time, no exception is made for macros with no
|
|
parameters at all. So you could define
|
|
|
|
\c %macro prologue 0
|
|
\c
|
|
\c push ebp
|
|
\c mov ebp,esp
|
|
\c
|
|
\c %endmacro
|
|
|
|
to define an alternative form of the function prologue which
|
|
allocates no local stack space.
|
|
|
|
Sometimes, however, you might want to `overload' a machine
|
|
instruction; for example, you might want to define
|
|
|
|
\c %macro push 2
|
|
\c
|
|
\c push %1
|
|
\c push %2
|
|
\c
|
|
\c %endmacro
|
|
|
|
so that you could code
|
|
|
|
\c push ebx ; this line is not a macro call
|
|
\c push eax,ecx ; but this one is
|
|
|
|
Ordinarily, NASM will give a warning for the first of the above two
|
|
lines, since \c{push} is now defined to be a macro, and is being
|
|
invoked with a number of parameters for which no definition has been
|
|
given. The correct code will still be generated, but the assembler
|
|
will give a warning. This warning can be disabled by the use of the
|
|
\c{-w-macro-params} command-line option (see \k{opt-w}).
|
|
|
|
|
|
\S{maclocal} \i{Macro-Local Labels}
|
|
|
|
NASM allows you to define labels within a multi-line macro
|
|
definition in such a way as to make them local to the macro call: so
|
|
calling the same macro multiple times will use a different label
|
|
each time. You do this by prefixing \i\c{%%} to the label name. So
|
|
you can invent an instruction which executes a \c{RET} if the \c{Z}
|
|
flag is set by doing this:
|
|
|
|
\c %macro retz 0
|
|
\c
|
|
\c jnz %%skip
|
|
\c ret
|
|
\c %%skip:
|
|
\c
|
|
\c %endmacro
|
|
|
|
You can call this macro as many times as you want, and every time
|
|
you call it NASM will make up a different `real' name to substitute
|
|
for the label \c{%%skip}. The names NASM invents are of the form
|
|
\c{..@2345.skip}, where the number 2345 changes with every macro
|
|
call. The \i\c{..@} prefix prevents macro-local labels from
|
|
interfering with the local label mechanism, as described in
|
|
\k{locallab}. You should avoid defining your own labels in this form
|
|
(the \c{..@} prefix, then a number, then another period) in case
|
|
they interfere with macro-local labels.
|
|
|
|
|
|
\S{mlmacgre} \i{Greedy Macro Parameters}
|
|
|
|
Occasionally it is useful to define a macro which lumps its entire
|
|
command line into one parameter definition, possibly after
|
|
extracting one or two smaller parameters from the front. An example
|
|
might be a macro to write a text string to a file in MS-DOS, where
|
|
you might want to be able to write
|
|
|
|
\c writefile [filehandle],"hello, world",13,10
|
|
|
|
NASM allows you to define the last parameter of a macro to be
|
|
\e{greedy}, meaning that if you invoke the macro with more
|
|
parameters than it expects, all the spare parameters get lumped into
|
|
the last defined one along with the separating commas. So if you
|
|
code:
|
|
|
|
\c %macro writefile 2+
|
|
\c
|
|
\c jmp %%endstr
|
|
\c %%str: db %2
|
|
\c %%endstr:
|
|
\c mov dx,%%str
|
|
\c mov cx,%%endstr-%%str
|
|
\c mov bx,%1
|
|
\c mov ah,0x40
|
|
\c int 0x21
|
|
\c
|
|
\c %endmacro
|
|
|
|
then the example call to \c{writefile} above will work as expected:
|
|
the text before the first comma, \c{[filehandle]}, is used as the
|
|
first macro parameter and expanded when \c{%1} is referred to, and
|
|
all the subsequent text is lumped into \c{%2} and placed after the
|
|
\c{db}.
|
|
|
|
The greedy nature of the macro is indicated to NASM by the use of
|
|
the \I{+ modifier}\c{+} sign after the parameter count on the
|
|
\c{%macro} line.
|
|
|
|
If you define a greedy macro, you are effectively telling NASM how
|
|
it should expand the macro given \e{any} number of parameters from
|
|
the actual number specified up to infinity; in this case, for
|
|
example, NASM now knows what to do when it sees a call to
|
|
\c{writefile} with 2, 3, 4 or more parameters. NASM will take this
|
|
into account when overloading macros, and will not allow you to
|
|
define another form of \c{writefile} taking 4 parameters (for
|
|
example).
|
|
|
|
Of course, the above macro could have been implemented as a
|
|
non-greedy macro, in which case the call to it would have had to
|
|
look like
|
|
|
|
\c writefile [filehandle], {"hello, world",13,10}
|
|
|
|
NASM provides both mechanisms for putting \i{commas in macro
|
|
parameters}, and you choose which one you prefer for each macro
|
|
definition.
|
|
|
|
See \k{sectmac} for a better way to write the above macro.
|
|
|
|
|
|
\S{mlmacdef} \i{Default Macro Parameters}
|
|
|
|
NASM also allows you to define a multi-line macro with a \e{range}
|
|
of allowable parameter counts. If you do this, you can specify
|
|
defaults for \i{omitted parameters}. So, for example:
|
|
|
|
\c %macro die 0-1 "Painful program death has occurred."
|
|
\c
|
|
\c writefile 2,%1
|
|
\c mov ax,0x4c01
|
|
\c int 0x21
|
|
\c
|
|
\c %endmacro
|
|
|
|
This macro (which makes use of the \c{writefile} macro defined in
|
|
\k{mlmacgre}) can be called with an explicit error message, which it
|
|
will display on the error output stream before exiting, or it can be
|
|
called with no parameters, in which case it will use the default
|
|
error message supplied in the macro definition.
|
|
|
|
In general, you supply a minimum and maximum number of parameters
|
|
for a macro of this type; the minimum number of parameters are then
|
|
required in the macro call, and then you provide defaults for the
|
|
optional ones. So if a macro definition began with the line
|
|
|
|
\c %macro foobar 1-3 eax,[ebx+2]
|
|
|
|
then it could be called with between one and three parameters, and
|
|
\c{%1} would always be taken from the macro call. \c{%2}, if not
|
|
specified by the macro call, would default to \c{eax}, and \c{%3} if
|
|
not specified would default to \c{[ebx+2]}.
|
|
|
|
You can provide extra information to a macro by providing
|
|
too many default parameters:
|
|
|
|
\c %macro quux 1 something
|
|
|
|
This will trigger a warning by default; see \k{opt-w} for
|
|
more information.
|
|
When \c{quux} is invoked, it receives not one but two parameters.
|
|
\c{something} can be referred to as \c{%2}. The difference
|
|
between passing \c{something} this way and writing \c{something}
|
|
in the macro body is that with this way \c{something} is evaluated
|
|
when the macro is defined, not when it is expanded.
|
|
|
|
You may omit parameter defaults from the macro definition, in which
|
|
case the parameter default is taken to be blank. This can be useful
|
|
for macros which can take a variable number of parameters, since the
|
|
\i\c{%0} token (see \k{percent0}) allows you to determine how many
|
|
parameters were really passed to the macro call.
|
|
|
|
This defaulting mechanism can be combined with the greedy-parameter
|
|
mechanism; so the \c{die} macro above could be made more powerful,
|
|
and more useful, by changing the first line of the definition to
|
|
|
|
\c %macro die 0-1+ "Painful program death has occurred.",13,10
|
|
|
|
The maximum parameter count can be infinite, denoted by \c{*}. In
|
|
this case, of course, it is impossible to provide a \e{full} set of
|
|
default parameters. Examples of this usage are shown in \k{rotate}.
|
|
|
|
|
|
\S{percent0} \i\c{%0}: \I{counting macro parameters}Macro Parameter Counter
|
|
|
|
The parameter reference \c{%0} will return a numeric constant giving the
|
|
number of parameters received, that is, if \c{%0} is n then \c{%}n is the
|
|
last parameter. \c{%0} is mostly useful for macros that can take a variable
|
|
number of parameters. It can be used as an argument to \c{%rep}
|
|
(see \k{rep}) in order to iterate through all the parameters of a macro.
|
|
Examples are given in \k{rotate}.
|
|
|
|
|
|
\S{rotate} \i\c{%rotate}: \i{Rotating Macro Parameters}
|
|
|
|
Unix shell programmers will be familiar with the \I{shift
|
|
command}\c{shift} shell command, which allows the arguments passed
|
|
to a shell script (referenced as \c{$1}, \c{$2} and so on) to be
|
|
moved left by one place, so that the argument previously referenced
|
|
as \c{$2} becomes available as \c{$1}, and the argument previously
|
|
referenced as \c{$1} is no longer available at all.
|
|
|
|
NASM provides a similar mechanism, in the form of \c{%rotate}. As
|
|
its name suggests, it differs from the Unix \c{shift} in that no
|
|
parameters are lost: parameters rotated off the left end of the
|
|
argument list reappear on the right, and vice versa.
|
|
|
|
\c{%rotate} is invoked with a single numeric argument (which may be
|
|
an expression). The macro parameters are rotated to the left by that
|
|
many places. If the argument to \c{%rotate} is negative, the macro
|
|
parameters are rotated to the right.
|
|
|
|
\I{iterating over macro parameters}So a pair of macros to save and
|
|
restore a set of registers might work as follows:
|
|
|
|
\c %macro multipush 1-*
|
|
\c
|
|
\c %rep %0
|
|
\c push %1
|
|
\c %rotate 1
|
|
\c %endrep
|
|
\c
|
|
\c %endmacro
|
|
|
|
This macro invokes the \c{PUSH} instruction on each of its arguments
|
|
in turn, from left to right. It begins by pushing its first
|
|
argument, \c{%1}, then invokes \c{%rotate} to move all the arguments
|
|
one place to the left, so that the original second argument is now
|
|
available as \c{%1}. Repeating this procedure as many times as there
|
|
were arguments (achieved by supplying \c{%0} as the argument to
|
|
\c{%rep}) causes each argument in turn to be pushed.
|
|
|
|
Note also the use of \c{*} as the maximum parameter count,
|
|
indicating that there is no upper limit on the number of parameters
|
|
you may supply to the \i\c{multipush} macro.
|
|
|
|
It would be convenient, when using this macro, to have a \c{POP}
|
|
equivalent, which \e{didn't} require the arguments to be given in
|
|
reverse order. Ideally, you would write the \c{multipush} macro
|
|
call, then cut-and-paste the line to where the pop needed to be
|
|
done, and change the name of the called macro to \c{multipop}, and
|
|
the macro would take care of popping the registers in the opposite
|
|
order from the one in which they were pushed.
|
|
|
|
This can be done by the following definition:
|
|
|
|
\c %macro multipop 1-*
|
|
\c
|
|
\c %rep %0
|
|
\c %rotate -1
|
|
\c pop %1
|
|
\c %endrep
|
|
\c
|
|
\c %endmacro
|
|
|
|
This macro begins by rotating its arguments one place to the
|
|
\e{right}, so that the original \e{last} argument appears as \c{%1}.
|
|
This is then popped, and the arguments are rotated right again, so
|
|
the second-to-last argument becomes \c{%1}. Thus the arguments are
|
|
iterated through in reverse order.
|
|
|
|
|
|
\S{concat} \i{Concatenating Macro Parameters}
|
|
|
|
NASM can concatenate macro parameters on to other text surrounding
|
|
them. This allows you to declare a family of symbols, for example,
|
|
in a macro definition. If, for example, you wanted to generate a
|
|
table of key codes along with offsets into the table, you could code
|
|
something like
|
|
|
|
\c %macro keytab_entry 2
|
|
\c
|
|
\c keypos%1 equ $-keytab
|
|
\c db %2
|
|
\c
|
|
\c %endmacro
|
|
\c
|
|
\c keytab:
|
|
\c keytab_entry F1,128+1
|
|
\c keytab_entry F2,128+2
|
|
\c keytab_entry Return,13
|
|
|
|
which would expand to
|
|
|
|
\c keytab:
|
|
\c keyposF1 equ $-keytab
|
|
\c db 128+1
|
|
\c keyposF2 equ $-keytab
|
|
\c db 128+2
|
|
\c keyposReturn equ $-keytab
|
|
\c db 13
|
|
|
|
You can just as easily concatenate text on to the other end of a
|
|
macro parameter, by writing \c{%1foo}.
|
|
|
|
If you need to append a \e{digit} to a macro parameter, for example
|
|
defining labels \c{foo1} and \c{foo2} when passed the parameter
|
|
\c{foo}, you can't code \c{%11} because that would be taken as the
|
|
eleventh macro parameter. Instead, you must code
|
|
\I{braces, after % sign}\c{%\{1\}1}, which will separate the first
|
|
\c{1} (giving the number of the macro parameter) from the second
|
|
(literal text to be concatenated to the parameter).
|
|
|
|
This concatenation can also be applied to other preprocessor in-line
|
|
objects, such as macro-local labels (\k{maclocal}) and context-local
|
|
labels (\k{ctxlocal}). In all cases, ambiguities in syntax can be
|
|
resolved by enclosing everything after the \c{%} sign and before the
|
|
literal text in braces: so \c{%\{%foo\}bar} concatenates the text
|
|
\c{bar} to the end of the real name of the macro-local label
|
|
\c{%%foo}. (This is unnecessary, since the form NASM uses for the
|
|
real names of macro-local labels means that the two usages
|
|
\c{%\{%foo\}bar} and \c{%%foobar} would both expand to the same
|
|
thing anyway; nevertheless, the capability is there.)
|
|
|
|
See also the \c{%+} operator, \k{concat%+}.
|
|
|
|
|
|
\S{mlmaccc} \i{Condition Codes as Macro Parameters}
|
|
|
|
NASM can give special treatment to a macro parameter which contains
|
|
a condition code. For a start, you can refer to the macro parameter
|
|
\c{%1} by means of the alternative syntax \i\c{%+1}, which informs
|
|
NASM that this macro parameter is supposed to contain a condition
|
|
code, and will cause the preprocessor to report an error message if
|
|
the macro is called with a parameter which is \e{not} a valid
|
|
condition code.
|
|
|
|
Far more usefully, though, you can refer to the macro parameter by
|
|
means of \i\c{%-1}, which NASM will expand as the \e{inverse}
|
|
condition code. So the \c{retz} macro defined in \k{maclocal} can be
|
|
replaced by a general \i{conditional-return macro} like this:
|
|
|
|
\c %macro retc 1
|
|
\c
|
|
\c j%-1 %%skip
|
|
\c ret
|
|
\c %%skip:
|
|
\c
|
|
\c %endmacro
|
|
|
|
This macro can now be invoked using calls like \c{retc ne}, which
|
|
will cause the conditional-jump instruction in the macro expansion
|
|
to come out as \c{JE}, or \c{retc po} which will make the jump a
|
|
\c{JPE}.
|
|
|
|
The \c{%+1} macro-parameter reference is quite happy to interpret
|
|
the arguments \c{CXZ} and \c{ECXZ} as valid condition codes;
|
|
however, \c{%-1} will report an error if passed either of these,
|
|
because no inverse condition code exists.
|
|
|
|
|
|
\S{nolist} \i{Disabling Listing Expansion}\I\c{.nolist}
|
|
|
|
When NASM is generating a listing file from your program, it will
|
|
generally expand multi-line macros by means of writing the macro
|
|
call and then listing each line of the expansion. This allows you to
|
|
see which instructions in the macro expansion are generating what
|
|
code; however, for some macros this clutters the listing up
|
|
unnecessarily.
|
|
|
|
NASM therefore provides the \c{.nolist} qualifier, which you can
|
|
include in a macro definition to inhibit the expansion of the macro
|
|
in the listing file. The \c{.nolist} qualifier comes directly after
|
|
the number of parameters, like this:
|
|
|
|
\c %macro foo 1.nolist
|
|
|
|
Or like this:
|
|
|
|
\c %macro bar 1-5+.nolist a,b,c,d,e,f,g,h
|
|
|
|
\S{unmacro} Undefining Multi-Line Macros: \i\c{%unmacro}
|
|
|
|
Multi-line macros can be removed with the \c{%unmacro} directive.
|
|
Unlike the \c{%undef} directive, however, \c{%unmacro} takes an
|
|
argument specification, and will only remove \i{exact matches} with
|
|
that argument specification.
|
|
|
|
For example:
|
|
|
|
\c %macro foo 1-3
|
|
\c ; Do something
|
|
\c %endmacro
|
|
\c %unmacro foo 1-3
|
|
|
|
removes the previously defined macro \c{foo}, but
|
|
|
|
\c %unmacro bar 1-3
|
|
\c ; Do something
|
|
\c %endmacro
|
|
\c %unmacro bar 1
|
|
|
|
does \e{not} remove the macro \c{bar}, since the argument
|
|
specification does not match exactly.
|
|
|
|
\H{condasm} \i{Conditional Assembly}\I\c{%if}
|
|
|
|
Similarly to the C preprocessor, NASM allows sections of a source
|
|
file to be assembled only if certain conditions are met. The general
|
|
syntax of this feature looks like this:
|
|
|
|
\c %if<condition>
|
|
\c ; some code which only appears if <condition> is met
|
|
\c %elif<condition2>
|
|
\c ; only appears if <condition> is not met but <condition2> is
|
|
\c %else
|
|
\c ; this appears if neither <condition> nor <condition2> was met
|
|
\c %endif
|
|
|
|
The inverse forms \i\c{%ifn} and \i\c{%elifn} are also supported.
|
|
|
|
The \i\c{%else} clause is optional, as is the \i\c{%elif} clause.
|
|
You can have more than one \c{%elif} clause as well.
|
|
|
|
There are a number of variants of the \c{%if} directive. Each has its
|
|
corresponding \c{%elif}, \c{%ifn}, and \c{%elifn} directives; for
|
|
example, the equivalents to the \c{%ifdef} directive are \c{%elifdef},
|
|
\c{%ifndef}, and \c{%elifndef}.
|
|
|
|
\S{ifdef} \i\c{%ifdef}: Testing Single-Line Macro Existence\I{testing,
|
|
single-line macro existence}
|
|
|
|
Beginning a conditional-assembly block with the line \c{%ifdef
|
|
MACRO} will assemble the subsequent code if, and only if, a
|
|
single-line macro called \c{MACRO} is defined. If not, then the
|
|
\c{%elif} and \c{%else} blocks (if any) will be processed instead.
|
|
|
|
For example, when debugging a program, you might want to write code
|
|
such as
|
|
|
|
\c ; perform some function
|
|
\c %ifdef DEBUG
|
|
\c writefile 2,"Function performed successfully",13,10
|
|
\c %endif
|
|
\c ; go and do something else
|
|
|
|
Then you could use the command-line option \c{-dDEBUG} to create a
|
|
version of the program which produced debugging messages, and remove
|
|
the option to generate the final release version of the program.
|
|
|
|
You can test for a macro \e{not} being defined by using
|
|
\i\c{%ifndef} instead of \c{%ifdef}. You can also test for macro
|
|
definitions in \c{%elif} blocks by using \i\c{%elifdef} and
|
|
\i\c{%elifndef}.
|
|
|
|
|
|
\S{ifmacro} \i\c{%ifmacro}: Testing Multi-Line Macro
|
|
Existence\I{testing, multi-line macro existence}
|
|
|
|
The \c{%ifmacro} directive operates in the same way as the \c{%ifdef}
|
|
directive, except that it checks for the existence of a multi-line macro.
|
|
|
|
For example, you may be working with a large project and not have control
|
|
over the macros in a library. You may want to create a macro with one
|
|
name if it doesn't already exist, and another name if one with that name
|
|
does exist.
|
|
|
|
The \c{%ifmacro} is considered true if defining a macro with the given name
|
|
and number of arguments would cause a definitions conflict. For example:
|
|
|
|
\c %ifmacro MyMacro 1-3
|
|
\c
|
|
\c %error "MyMacro 1-3" causes a conflict with an existing macro.
|
|
\c
|
|
\c %else
|
|
\c
|
|
\c %macro MyMacro 1-3
|
|
\c
|
|
\c ; insert code to define the macro
|
|
\c
|
|
\c %endmacro
|
|
\c
|
|
\c %endif
|
|
|
|
This will create the macro "MyMacro 1-3" if no macro already exists which
|
|
would conflict with it, and emits a warning if there would be a definition
|
|
conflict.
|
|
|
|
You can test for the macro not existing by using the \i\c{%ifnmacro} instead
|
|
of \c{%ifmacro}. Additional tests can be performed in \c{%elif} blocks by using
|
|
\i\c{%elifmacro} and \i\c{%elifnmacro}.
|
|
|
|
|
|
\S{ifctx} \i\c{%ifctx}: Testing the Context Stack\I{testing, context
|
|
stack}
|
|
|
|
The conditional-assembly construct \c{%ifctx} will cause the
|
|
subsequent code to be assembled if and only if the top context on
|
|
the preprocessor's context stack has the same name as one of the arguments.
|
|
As with \c{%ifdef}, the inverse and \c{%elif} forms \i\c{%ifnctx},
|
|
\i\c{%elifctx} and \i\c{%elifnctx} are also supported.
|
|
|
|
For more details of the context stack, see \k{ctxstack}. For a
|
|
sample use of \c{%ifctx}, see \k{blockif}.
|
|
|
|
|
|
\S{if} \i\c{%if}: Testing Arbitrary Numeric Expressions\I{testing,
|
|
arbitrary numeric expressions}
|
|
|
|
The conditional-assembly construct \c{%if expr} will cause the
|
|
subsequent code to be assembled if and only if the value of the
|
|
numeric expression \c{expr} is non-zero. An example of the use of
|
|
this feature is in deciding when to break out of a \c{%rep}
|
|
preprocessor loop: see \k{rep} for a detailed example.
|
|
|
|
The expression given to \c{%if}, and its counterpart \i\c{%elif}, is
|
|
a critical expression (see \k{crit}).
|
|
|
|
\c{%if} extends the normal NASM expression syntax, by providing a
|
|
set of \i{relational operators} which are not normally available in
|
|
expressions. The operators \i\c{=}, \i\c{<}, \i\c{>}, \i\c{<=},
|
|
\i\c{>=} and \i\c{<>} test equality, less-than, greater-than,
|
|
less-or-equal, greater-or-equal and not-equal respectively. The
|
|
C-like forms \i\c{==} and \i\c{!=} are supported as alternative
|
|
forms of \c{=} and \c{<>}. In addition, low-priority logical
|
|
operators \i\c{&&}, \i\c{^^} and \i\c{||} are provided, supplying
|
|
\i{logical AND}, \i{logical XOR} and \i{logical OR}. These work like
|
|
the C logical operators (although C has no logical XOR), in that
|
|
they always return either 0 or 1, and treat any non-zero input as 1
|
|
(so that \c{^^}, for example, returns 1 if exactly one of its inputs
|
|
is zero, and 0 otherwise). The relational operators also return 1
|
|
for true and 0 for false.
|
|
|
|
Like other \c{%if} constructs, \c{%if} has a counterpart
|
|
\i\c{%elif}, and negative forms \i\c{%ifn} and \i\c{%elifn}.
|
|
|
|
\S{ifidn} \i\c{%ifidn} and \i\c{%ifidni}: Testing Exact Text
|
|
Identity\I{testing, exact text identity}
|
|
|
|
The construct \c{%ifidn text1,text2} will cause the subsequent code
|
|
to be assembled if and only if \c{text1} and \c{text2}, after
|
|
expanding single-line macros, are identical pieces of text.
|
|
Differences in white space are not counted.
|
|
|
|
\c{%ifidni} is similar to \c{%ifidn}, but is \i{case-insensitive}.
|
|
|
|
For example, the following macro pushes a register or number on the
|
|
stack, and allows you to treat \c{IP} as a real register:
|
|
|
|
\c %macro pushparam 1
|
|
\c
|
|
\c %ifidni %1,ip
|
|
\c call %%label
|
|
\c %%label:
|
|
\c %else
|
|
\c push %1
|
|
\c %endif
|
|
\c
|
|
\c %endmacro
|
|
|
|
Like other \c{%if} constructs, \c{%ifidn} has a counterpart
|
|
\i\c{%elifidn}, and negative forms \i\c{%ifnidn} and \i\c{%elifnidn}.
|
|
Similarly, \c{%ifidni} has counterparts \i\c{%elifidni},
|
|
\i\c{%ifnidni} and \i\c{%elifnidni}.
|
|
|
|
\S{iftyp} \i\c{%ifid}, \i\c{%ifnum}, \i\c{%ifstr}: Testing Token
|
|
Types\I{testing, token types}
|
|
|
|
Some macros will want to perform different tasks depending on
|
|
whether they are passed a number, a string, or an identifier. For
|
|
example, a string output macro might want to be able to cope with
|
|
being passed either a string constant or a pointer to an existing
|
|
string.
|
|
|
|
The conditional assembly construct \c{%ifid}, taking one parameter
|
|
(which may be blank), assembles the subsequent code if and only if
|
|
the first token in the parameter exists and is an identifier.
|
|
\c{%ifnum} works similarly, but tests for the token being a numeric
|
|
constant; \c{%ifstr} tests for it being a string.
|
|
|
|
For example, the \c{writefile} macro defined in \k{mlmacgre} can be
|
|
extended to take advantage of \c{%ifstr} in the following fashion:
|
|
|
|
\c %macro writefile 2-3+
|
|
\c
|
|
\c %ifstr %2
|
|
\c jmp %%endstr
|
|
\c %if %0 = 3
|
|
\c %%str: db %2,%3
|
|
\c %else
|
|
\c %%str: db %2
|
|
\c %endif
|
|
\c %%endstr: mov dx,%%str
|
|
\c mov cx,%%endstr-%%str
|
|
\c %else
|
|
\c mov dx,%2
|
|
\c mov cx,%3
|
|
\c %endif
|
|
\c mov bx,%1
|
|
\c mov ah,0x40
|
|
\c int 0x21
|
|
\c
|
|
\c %endmacro
|
|
|
|
Then the \c{writefile} macro can cope with being called in either of
|
|
the following two ways:
|
|
|
|
\c writefile [file], strpointer, length
|
|
\c writefile [file], "hello", 13, 10
|
|
|
|
In the first, \c{strpointer} is used as the address of an
|
|
already-declared string, and \c{length} is used as its length; in
|
|
the second, a string is given to the macro, which therefore declares
|
|
it itself and works out the address and length for itself.
|
|
|
|
Note the use of \c{%if} inside the \c{%ifstr}: this is to detect
|
|
whether the macro was passed two arguments (so the string would be a
|
|
single string constant, and \c{db %2} would be adequate) or more (in
|
|
which case, all but the first two would be lumped together into
|
|
\c{%3}, and \c{db %2,%3} would be required).
|
|
|
|
The usual \I\c{%elifid}\I\c{%elifnum}\I\c{%elifstr}\c{%elif}...,
|
|
\I\c{%ifnid}\I\c{%ifnnum}\I\c{%ifnstr}\c{%ifn}..., and
|
|
\I\c{%elifnid}\I\c{%elifnnum}\I\c{%elifnstr}\c{%elifn}... versions
|
|
exist for each of \c{%ifid}, \c{%ifnum} and \c{%ifstr}.
|
|
|
|
\S{iftoken} \i\c{%iftoken}: Test for a Single Token
|
|
|
|
Some macros will want to do different things depending on if it is
|
|
passed a single token (e.g. paste it to something else using \c{%+})
|
|
versus a multi-token sequence.
|
|
|
|
The conditional assembly construct \c{%iftoken} assembles the
|
|
subsequent code if and only if the expanded parameters consist of
|
|
exactly one token, possibly surrounded by whitespace.
|
|
|
|
For example:
|
|
|
|
\c %iftoken 1
|
|
|
|
will assemble the subsequent code, but
|
|
|
|
\c %iftoken -1
|
|
|
|
will not, since \c{-1} contains two tokens: the unary minus operator
|
|
\c{-}, and the number \c{1}.
|
|
|
|
The usual \i\c{%eliftoken}, \i\c\{%ifntoken}, and \i\c{%elifntoken}
|
|
variants are also provided.
|
|
|
|
\S{ifempty} \i\c{%ifempty}: Test for Empty Expansion
|
|
|
|
The conditional assembly construct \c{%ifempty} assembles the
|
|
subsequent code if and only if the expanded parameters do not contain
|
|
any tokens at all, whitespace excepted.
|
|
|
|
The usual \i\c{%elifempty}, \i\c\{%ifnempty}, and \i\c{%elifnempty}
|
|
variants are also provided.
|
|
|
|
\H{rep} \i{Preprocessor Loops}\I{repeating code}: \i\c{%rep}
|
|
|
|
NASM's \c{TIMES} prefix, though useful, cannot be used to invoke a
|
|
multi-line macro multiple times, because it is processed by NASM
|
|
after macros have already been expanded. Therefore NASM provides
|
|
another form of loop, this time at the preprocessor level: \c{%rep}.
|
|
|
|
The directives \c{%rep} and \i\c{%endrep} (\c{%rep} takes a numeric
|
|
argument, which can be an expression; \c{%endrep} takes no
|
|
arguments) can be used to enclose a chunk of code, which is then
|
|
replicated as many times as specified by the preprocessor:
|
|
|
|
\c %assign i 0
|
|
\c %rep 64
|
|
\c inc word [table+2*i]
|
|
\c %assign i i+1
|
|
\c %endrep
|
|
|
|
This will generate a sequence of 64 \c{INC} instructions,
|
|
incrementing every word of memory from \c{[table]} to
|
|
\c{[table+126]}.
|
|
|
|
For more complex termination conditions, or to break out of a repeat
|
|
loop part way along, you can use the \i\c{%exitrep} directive to
|
|
terminate the loop, like this:
|
|
|
|
\c fibonacci:
|
|
\c %assign i 0
|
|
\c %assign j 1
|
|
\c %rep 100
|
|
\c %if j > 65535
|
|
\c %exitrep
|
|
\c %endif
|
|
\c dw j
|
|
\c %assign k j+i
|
|
\c %assign i j
|
|
\c %assign j k
|
|
\c %endrep
|
|
\c
|
|
\c fib_number equ ($-fibonacci)/2
|
|
|
|
This produces a list of all the Fibonacci numbers that will fit in
|
|
16 bits. Note that a maximum repeat count must still be given to
|
|
\c{%rep}. This is to prevent the possibility of NASM getting into an
|
|
infinite loop in the preprocessor, which (on multitasking or
|
|
multi-user systems) would typically cause all the system memory to
|
|
be gradually used up and other applications to start crashing.
|
|
|
|
|
|
\H{files} Source Files and Dependencies
|
|
|
|
These commands allow you to split your sources into multiple files.
|
|
|
|
\S{include} \i\c{%include}: \i{Including Other Files}
|
|
|
|
Using, once again, a very similar syntax to the C preprocessor,
|
|
NASM's preprocessor lets you include other source files into your
|
|
code. This is done by the use of the \i\c{%include} directive:
|
|
|
|
\c %include "macros.mac"
|
|
|
|
will include the contents of the file \c{macros.mac} into the source
|
|
file containing the \c{%include} directive.
|
|
|
|
Include files are \I{searching for include files}searched for in the
|
|
current directory (the directory you're in when you run NASM, as
|
|
opposed to the location of the NASM executable or the location of
|
|
the source file), plus any directories specified on the NASM command
|
|
line using the \c{-i} option.
|
|
|
|
The standard C idiom for preventing a file being included more than
|
|
once is just as applicable in NASM: if the file \c{macros.mac} has
|
|
the form
|
|
|
|
\c %ifndef MACROS_MAC
|
|
\c %define MACROS_MAC
|
|
\c ; now define some macros
|
|
\c %endif
|
|
|
|
then including the file more than once will not cause errors,
|
|
because the second time the file is included nothing will happen
|
|
because the macro \c{MACROS_MAC} will already be defined.
|
|
|
|
You can force a file to be included even if there is no \c{%include}
|
|
directive that explicitly includes it, by using the \i\c{-p} option
|
|
on the NASM command line (see \k{opt-p}).
|
|
|
|
|
|
\S{pathsearch} \i\c{%pathsearch}: Search the Include Path
|
|
|
|
The \c{%pathsearch} directive takes a single-line macro name and a
|
|
filename, and declare or redefines the specified single-line macro to
|
|
be the include-path-resolved verson of the filename, if the file
|
|
exists (otherwise, it is passed unchanged.)
|
|
|
|
For example,
|
|
|
|
\c %pathsearch MyFoo "foo.bin"
|
|
|
|
... with \c{-Ibins/} in the include path may end up defining the macro
|
|
\c{MyFoo} to be \c{"bins/foo.bin"}.
|
|
|
|
|
|
\S{depend} \i\c{%depend}: Add Dependent Files
|
|
|
|
The \c{%depend} directive takes a filename and adds it to the list of
|
|
files to be emitted as dependency generation when the \c{-M} options
|
|
and its relatives (see \k{opt-M}) are used. It produces no output.
|
|
|
|
This is generally used in conjunction with \c{%pathsearch}. For
|
|
example, a simplified version of the standard macro wrapper for the
|
|
\c{INCBIN} directive looks like:
|
|
|
|
\c %imacro incbin 1-2+ 0
|
|
\c %pathsearch dep %1
|
|
\c %depend dep
|
|
\c incbin dep,%2
|
|
\c %endmacro
|
|
|
|
This first resolves the location of the file into the macro \c{dep},
|
|
then adds it to the dependency lists, and finally issues the
|
|
assembler-level \c{INCBIN} directive.
|
|
|
|
|
|
\S{use} \i\c{%use}: Include Standard Macro Package
|
|
|
|
The \c{%use} directive is similar to \c{%include}, but rather than
|
|
including the contents of a file, it includes a named standard macro
|
|
package. The standard macro packages are part of NASM, and are
|
|
described in \k{macropkg}.
|
|
|
|
Unlike the \c{%include} directive, package names for the \c{%use}
|
|
directive do not require quotes, but quotes are permitted; using
|
|
quotes will prevent unwanted macro expansion. Thus, the following
|
|
lines are equivalent, unless \c{altreg} is defined as a macro:
|
|
|
|
\c %use altreg
|
|
\c %use 'altreg'
|
|
|
|
Standard macro packages are protected from multiple inclusion. When a
|
|
standard macro package is used, a testable single-line macro of the
|
|
form \c{__USE_}\e{package}\c{__} is also defined, see \k{use_def}.
|
|
|
|
\H{ctxstack} The \i{Context Stack}
|
|
|
|
Having labels that are local to a macro definition is sometimes not
|
|
quite powerful enough: sometimes you want to be able to share labels
|
|
between several macro calls. An example might be a \c{REPEAT} ...
|
|
\c{UNTIL} loop, in which the expansion of the \c{REPEAT} macro
|
|
would need to be able to refer to a label which the \c{UNTIL} macro
|
|
had defined. However, for such a macro you would also want to be
|
|
able to nest these loops.
|
|
|
|
NASM provides this level of power by means of a \e{context stack}.
|
|
The preprocessor maintains a stack of \e{contexts}, each of which is
|
|
characterized by a name. You add a new context to the stack using
|
|
the \i\c{%push} directive, and remove one using \i\c{%pop}. You can
|
|
define labels that are local to a particular context on the stack.
|
|
|
|
|
|
\S{pushpop} \i\c{%push} and \i\c{%pop}: \I{creating
|
|
contexts}\I{removing contexts}Creating and Removing Contexts
|
|
|
|
The \c{%push} directive is used to create a new context and place it
|
|
on the top of the context stack. \c{%push} requires one argument,
|
|
which is the name of the context. For example:
|
|
|
|
\c %push foobar
|
|
|
|
This pushes a new context called \c{foobar} on the stack. You can
|
|
have several contexts on the stack with the same name: they can
|
|
still be distinguished.
|
|
|
|
The directive \c{%pop}, requiring no arguments, removes the top
|
|
context from the context stack and destroys it, along with any
|
|
labels associated with it.
|
|
|
|
|
|
\S{ctxlocal} \i{Context-Local Labels}
|
|
|
|
Just as the usage \c{%%foo} defines a label which is local to the
|
|
particular macro call in which it is used, the usage \I{%$}\c{%$foo}
|
|
is used to define a label which is local to the context on the top
|
|
of the context stack. So the \c{REPEAT} and \c{UNTIL} example given
|
|
above could be implemented by means of:
|
|
|
|
\c %macro repeat 0
|
|
\c
|
|
\c %push repeat
|
|
\c %$begin:
|
|
\c
|
|
\c %endmacro
|
|
\c
|
|
\c %macro until 1
|
|
\c
|
|
\c j%-1 %$begin
|
|
\c %pop
|
|
\c
|
|
\c %endmacro
|
|
|
|
and invoked by means of, for example,
|
|
|
|
\c mov cx,string
|
|
\c repeat
|
|
\c add cx,3
|
|
\c scasb
|
|
\c until e
|
|
|
|
which would scan every fourth byte of a string in search of the byte
|
|
in \c{AL}.
|
|
|
|
If you need to define, or access, labels local to the context
|
|
\e{below} the top one on the stack, you can use \I{%$$}\c{%$$foo}, or
|
|
\c{%$$$foo} for the context below that, and so on.
|
|
|
|
|
|
\S{ctxdefine} \i{Context-Local Single-Line Macros}
|
|
|
|
NASM also allows you to define single-line macros which are local to
|
|
a particular context, in just the same way:
|
|
|
|
\c %define %$localmac 3
|
|
|
|
will define the single-line macro \c{%$localmac} to be local to the
|
|
top context on the stack. Of course, after a subsequent \c{%push},
|
|
it can then still be accessed by the name \c{%$$localmac}.
|
|
|
|
|
|
\S{ctxrepl} \i\c{%repl}: \I{renaming contexts}Renaming a Context
|
|
|
|
If you need to change the name of the top context on the stack (in
|
|
order, for example, to have it respond differently to \c{%ifctx}),
|
|
you can execute a \c{%pop} followed by a \c{%push}; but this will
|
|
have the side effect of destroying all context-local labels and
|
|
macros associated with the context that was just popped.
|
|
|
|
NASM provides the directive \c{%repl}, which \e{replaces} a context
|
|
with a different name, without touching the associated macros and
|
|
labels. So you could replace the destructive code
|
|
|
|
\c %pop
|
|
\c %push newname
|
|
|
|
with the non-destructive version \c{%repl newname}.
|
|
|
|
|
|
\S{blockif} Example Use of the \i{Context Stack}: \i{Block IFs}
|
|
|
|
This example makes use of almost all the context-stack features,
|
|
including the conditional-assembly construct \i\c{%ifctx}, to
|
|
implement a block IF statement as a set of macros.
|
|
|
|
\c %macro if 1
|
|
\c
|
|
\c %push if
|
|
\c j%-1 %$ifnot
|
|
\c
|
|
\c %endmacro
|
|
\c
|
|
\c %macro else 0
|
|
\c
|
|
\c %ifctx if
|
|
\c %repl else
|
|
\c jmp %$ifend
|
|
\c %$ifnot:
|
|
\c %else
|
|
\c %error "expected `if' before `else'"
|
|
\c %endif
|
|
\c
|
|
\c %endmacro
|
|
\c
|
|
\c %macro endif 0
|
|
\c
|
|
\c %ifctx if
|
|
\c %$ifnot:
|
|
\c %pop
|
|
\c %elifctx else
|
|
\c %$ifend:
|
|
\c %pop
|
|
\c %else
|
|
\c %error "expected `if' or `else' before `endif'"
|
|
\c %endif
|
|
\c
|
|
\c %endmacro
|
|
|
|
This code is more robust than the \c{REPEAT} and \c{UNTIL} macros
|
|
given in \k{ctxlocal}, because it uses conditional assembly to check
|
|
that the macros are issued in the right order (for example, not
|
|
calling \c{endif} before \c{if}) and issues a \c{%error} if they're
|
|
not.
|
|
|
|
In addition, the \c{endif} macro has to be able to cope with the two
|
|
distinct cases of either directly following an \c{if}, or following
|
|
an \c{else}. It achieves this, again, by using conditional assembly
|
|
to do different things depending on whether the context on top of
|
|
the stack is \c{if} or \c{else}.
|
|
|
|
The \c{else} macro has to preserve the context on the stack, in
|
|
order to have the \c{%$ifnot} referred to by the \c{if} macro be the
|
|
same as the one defined by the \c{endif} macro, but has to change
|
|
the context's name so that \c{endif} will know there was an
|
|
intervening \c{else}. It does this by the use of \c{%repl}.
|
|
|
|
A sample usage of these macros might look like:
|
|
|
|
\c cmp ax,bx
|
|
\c
|
|
\c if ae
|
|
\c cmp bx,cx
|
|
\c
|
|
\c if ae
|
|
\c mov ax,cx
|
|
\c else
|
|
\c mov ax,bx
|
|
\c endif
|
|
\c
|
|
\c else
|
|
\c cmp ax,cx
|
|
\c
|
|
\c if ae
|
|
\c mov ax,cx
|
|
\c endif
|
|
\c
|
|
\c endif
|
|
|
|
The block-\c{IF} macros handle nesting quite happily, by means of
|
|
pushing another context, describing the inner \c{if}, on top of the
|
|
one describing the outer \c{if}; thus \c{else} and \c{endif} always
|
|
refer to the last unmatched \c{if} or \c{else}.
|
|
|
|
|
|
\H{stackrel} \i{Stack Relative Preprocessor Directives}
|
|
|
|
The following preprocessor directives provide a way to use
|
|
labels to refer to local variables allocated on the stack.
|
|
|
|
\b\c{%arg} (see \k{arg})
|
|
|
|
\b\c{%stacksize} (see \k{stacksize})
|
|
|
|
\b\c{%local} (see \k{local})
|
|
|
|
|
|
\S{arg} \i\c{%arg} Directive
|
|
|
|
The \c{%arg} directive is used to simplify the handling of
|
|
parameters passed on the stack. Stack based parameter passing
|
|
is used by many high level languages, including C, C++ and Pascal.
|
|
|
|
While NASM has macros which attempt to duplicate this
|
|
functionality (see \k{16cmacro}), the syntax is not particularly
|
|
convenient to use. and is not TASM compatible. Here is an example
|
|
which shows the use of \c{%arg} without any external macros:
|
|
|
|
\c some_function:
|
|
\c
|
|
\c %push mycontext ; save the current context
|
|
\c %stacksize large ; tell NASM to use bp
|
|
\c %arg i:word, j_ptr:word
|
|
\c
|
|
\c mov ax,[i]
|
|
\c mov bx,[j_ptr]
|
|
\c add ax,[bx]
|
|
\c ret
|
|
\c
|
|
\c %pop ; restore original context
|
|
|
|
This is similar to the procedure defined in \k{16cmacro} and adds
|
|
the value in i to the value pointed to by j_ptr and returns the
|
|
sum in the ax register. See \k{pushpop} for an explanation of
|
|
\c{push} and \c{pop} and the use of context stacks.
|
|
|
|
|
|
\S{stacksize} \i\c{%stacksize} Directive
|
|
|
|
The \c{%stacksize} directive is used in conjunction with the
|
|
\c{%arg} (see \k{arg}) and the \c{%local} (see \k{local}) directives.
|
|
It tells NASM the default size to use for subsequent \c{%arg} and
|
|
\c{%local} directives. The \c{%stacksize} directive takes one
|
|
required argument which is one of \c{flat}, \c{flat64}, \c{large} or \c{small}.
|
|
|
|
\c %stacksize flat
|
|
|
|
This form causes NASM to use stack-based parameter addressing
|
|
relative to \c{ebp} and it assumes that a near form of call was used
|
|
to get to this label (i.e. that \c{eip} is on the stack).
|
|
|
|
\c %stacksize flat64
|
|
|
|
This form causes NASM to use stack-based parameter addressing
|
|
relative to \c{rbp} and it assumes that a near form of call was used
|
|
to get to this label (i.e. that \c{rip} is on the stack).
|
|
|
|
\c %stacksize large
|
|
|
|
This form uses \c{bp} to do stack-based parameter addressing and
|
|
assumes that a far form of call was used to get to this address
|
|
(i.e. that \c{ip} and \c{cs} are on the stack).
|
|
|
|
\c %stacksize small
|
|
|
|
This form also uses \c{bp} to address stack parameters, but it is
|
|
different from \c{large} because it also assumes that the old value
|
|
of bp is pushed onto the stack (i.e. it expects an \c{ENTER}
|
|
instruction). In other words, it expects that \c{bp}, \c{ip} and
|
|
\c{cs} are on the top of the stack, underneath any local space which
|
|
may have been allocated by \c{ENTER}. This form is probably most
|
|
useful when used in combination with the \c{%local} directive
|
|
(see \k{local}).
|
|
|
|
|
|
\S{local} \i\c{%local} Directive
|
|
|
|
The \c{%local} directive is used to simplify the use of local
|
|
temporary stack variables allocated in a stack frame. Automatic
|
|
local variables in C are an example of this kind of variable. The
|
|
\c{%local} directive is most useful when used with the \c{%stacksize}
|
|
(see \k{stacksize} and is also compatible with the \c{%arg} directive
|
|
(see \k{arg}). It allows simplified reference to variables on the
|
|
stack which have been allocated typically by using the \c{ENTER}
|
|
instruction.
|
|
\# (see \k{insENTER} for a description of that instruction).
|
|
An example of its use is the following:
|
|
|
|
\c silly_swap:
|
|
\c
|
|
\c %push mycontext ; save the current context
|
|
\c %stacksize small ; tell NASM to use bp
|
|
\c %assign %$localsize 0 ; see text for explanation
|
|
\c %local old_ax:word, old_dx:word
|
|
\c
|
|
\c enter %$localsize,0 ; see text for explanation
|
|
\c mov [old_ax],ax ; swap ax & bx
|
|
\c mov [old_dx],dx ; and swap dx & cx
|
|
\c mov ax,bx
|
|
\c mov dx,cx
|
|
\c mov bx,[old_ax]
|
|
\c mov cx,[old_dx]
|
|
\c leave ; restore old bp
|
|
\c ret ;
|
|
\c
|
|
\c %pop ; restore original context
|
|
|
|
The \c{%$localsize} variable is used internally by the
|
|
\c{%local} directive and \e{must} be defined within the
|
|
current context before the \c{%local} directive may be used.
|
|
Failure to do so will result in one expression syntax error for
|
|
each \c{%local} variable declared. It then may be used in
|
|
the construction of an appropriately sized ENTER instruction
|
|
as shown in the example.
|
|
|
|
|
|
\H{pperror} Reporting \i{User-Defined Errors}: \i\c{%error}, \i\c{%warning}, \i\c{%fatal}
|
|
|
|
The preprocessor directive \c{%error} will cause NASM to report an
|
|
error if it occurs in assembled code. So if other users are going to
|
|
try to assemble your source files, you can ensure that they define the
|
|
right macros by means of code like this:
|
|
|
|
\c %ifdef F1
|
|
\c ; do some setup
|
|
\c %elifdef F2
|
|
\c ; do some different setup
|
|
\c %else
|
|
\c %error "Neither F1 nor F2 was defined."
|
|
\c %endif
|
|
|
|
Then any user who fails to understand the way your code is supposed
|
|
to be assembled will be quickly warned of their mistake, rather than
|
|
having to wait until the program crashes on being run and then not
|
|
knowing what went wrong.
|
|
|
|
Similarly, \c{%warning} issues a warning, but allows assembly to continue:
|
|
|
|
\c %ifdef F1
|
|
\c ; do some setup
|
|
\c %elifdef F2
|
|
\c ; do some different setup
|
|
\c %else
|
|
\c %warning "Neither F1 nor F2 was defined, assuming F1."
|
|
\c %define F1
|
|
\c %endif
|
|
|
|
\c{%error} and \c{%warning} are issued only on the final assembly
|
|
pass. This makes them safe to use in conjunction with tests that
|
|
depend on symbol values.
|
|
|
|
\c{%fatal} terminates assembly immediately, regardless of pass. This
|
|
is useful when there is no point in continuing the assembly further,
|
|
and doing so is likely just going to cause a spew of confusing error
|
|
messages.
|
|
|
|
It is optional for the message string after \c{%error}, \c{%warning}
|
|
or \c{%fatal} to be quoted. If it is \e{not}, then single-line macros
|
|
are expanded in it, which can be used to display more information to
|
|
the user. For example:
|
|
|
|
\c %if foo > 64
|
|
\c %assign foo_over foo-64
|
|
\c %error foo is foo_over bytes too large
|
|
\c %endif
|
|
|
|
|
|
\H{otherpreproc} \i{Other Preprocessor Directives}
|
|
|
|
NASM also has preprocessor directives which allow access to
|
|
information from external sources. Currently they include:
|
|
|
|
The following preprocessor directive is supported to allow NASM to
|
|
correctly handle output of the cpp C language preprocessor.
|
|
|
|
\b\c{%line} enables NASM to correctly handle the output of the cpp
|
|
C language preprocessor (see \k{line}).
|
|
|
|
\b\c{%!} enables NASM to read in the value of an environment variable,
|
|
which can then be used in your program (see \k{getenv}).
|
|
|
|
\S{line} \i\c{%line} Directive
|
|
|
|
The \c{%line} directive is used to notify NASM that the input line
|
|
corresponds to a specific line number in another file. Typically
|
|
this other file would be an original source file, with the current
|
|
NASM input being the output of a pre-processor. The \c{%line}
|
|
directive allows NASM to output messages which indicate the line
|
|
number of the original source file, instead of the file that is being
|
|
read by NASM.
|
|
|
|
This preprocessor directive is not generally of use to programmers,
|
|
by may be of interest to preprocessor authors. The usage of the
|
|
\c{%line} preprocessor directive is as follows:
|
|
|
|
\c %line nnn[+mmm] [filename]
|
|
|
|
In this directive, \c{nnn} identifies the line of the original source
|
|
file which this line corresponds to. \c{mmm} is an optional parameter
|
|
which specifies a line increment value; each line of the input file
|
|
read in is considered to correspond to \c{mmm} lines of the original
|
|
source file. Finally, \c{filename} is an optional parameter which
|
|
specifies the file name of the original source file.
|
|
|
|
After reading a \c{%line} preprocessor directive, NASM will report
|
|
all file name and line numbers relative to the values specified
|
|
therein.
|
|
|
|
|
|
\S{getenv} \i\c{%!}\c{<env>}: Read an environment variable.
|
|
|
|
The \c{%!<env>} directive makes it possible to read the value of an
|
|
environment variable at assembly time. This could, for example, be used
|
|
to store the contents of an environment variable into a string, which
|
|
could be used at some other point in your code.
|
|
|
|
For example, suppose that you have an environment variable \c{FOO}, and
|
|
you want the contents of \c{FOO} to be embedded in your program. You
|
|
could do that as follows:
|
|
|
|
\c %defstr FOO %!FOO
|
|
|
|
See \k{defstr} for notes on the \c{%defstr} directive.
|
|
|
|
|
|
\H{stdmac} \i{Standard Macros}
|
|
|
|
NASM defines a set of standard macros, which are already defined
|
|
when it starts to process any source file. If you really need a
|
|
program to be assembled with no pre-defined macros, you can use the
|
|
\i\c{%clear} directive to empty the preprocessor of everything but
|
|
context-local preprocessor variables and single-line macros.
|
|
|
|
Most \i{user-level assembler directives} (see \k{directive}) are
|
|
implemented as macros which invoke primitive directives; these are
|
|
described in \k{directive}. The rest of the standard macro set is
|
|
described here.
|
|
|
|
|
|
\S{stdmacver} \i{NASM Version} Macros
|
|
|
|
The single-line macros \i\c{__NASM_MAJOR__}, \i\c{__NASM_MINOR__},
|
|
\i\c{__NASM_SUBMINOR__} and \i\c{___NASM_PATCHLEVEL__} expand to the
|
|
major, minor, subminor and patch level parts of the \i{version
|
|
number of NASM} being used. So, under NASM 0.98.32p1 for
|
|
example, \c{__NASM_MAJOR__} would be defined to be 0, \c{__NASM_MINOR__}
|
|
would be defined as 98, \c{__NASM_SUBMINOR__} would be defined to 32,
|
|
and \c{___NASM_PATCHLEVEL__} would be defined as 1.
|
|
|
|
Additionally, the macro \i\c{__NASM_SNAPSHOT__} is defined for
|
|
automatically generated snapshot releases \e{only}.
|
|
|
|
|
|
\S{stdmacverid} \i\c{__NASM_VERSION_ID__}: \i{NASM Version ID}
|
|
|
|
The single-line macro \c{__NASM_VERSION_ID__} expands to a dword integer
|
|
representing the full version number of the version of nasm being used.
|
|
The value is the equivalent to \c{__NASM_MAJOR__}, \c{__NASM_MINOR__},
|
|
\c{__NASM_SUBMINOR__} and \c{___NASM_PATCHLEVEL__} concatenated to
|
|
produce a single doubleword. Hence, for 0.98.32p1, the returned number
|
|
would be equivalent to:
|
|
|
|
\c dd 0x00622001
|
|
|
|
or
|
|
|
|
\c db 1,32,98,0
|
|
|
|
Note that the above lines are generate exactly the same code, the second
|
|
line is used just to give an indication of the order that the separate
|
|
values will be present in memory.
|
|
|
|
|
|
\S{stdmacverstr} \i\c{__NASM_VER__}: \i{NASM Version string}
|
|
|
|
The single-line macro \c{__NASM_VER__} expands to a string which defines
|
|
the version number of nasm being used. So, under NASM 0.98.32 for example,
|
|
|
|
\c db __NASM_VER__
|
|
|
|
would expand to
|
|
|
|
\c db "0.98.32"
|
|
|
|
|
|
\S{fileline} \i\c{__FILE__} and \i\c{__LINE__}: File Name and Line Number
|
|
|
|
Like the C preprocessor, NASM allows the user to find out the file
|
|
name and line number containing the current instruction. The macro
|
|
\c{__FILE__} expands to a string constant giving the name of the
|
|
current input file (which may change through the course of assembly
|
|
if \c{%include} directives are used), and \c{__LINE__} expands to a
|
|
numeric constant giving the current line number in the input file.
|
|
|
|
These macros could be used, for example, to communicate debugging
|
|
information to a macro, since invoking \c{__LINE__} inside a macro
|
|
definition (either single-line or multi-line) will return the line
|
|
number of the macro \e{call}, rather than \e{definition}. So to
|
|
determine where in a piece of code a crash is occurring, for
|
|
example, one could write a routine \c{stillhere}, which is passed a
|
|
line number in \c{EAX} and outputs something like `line 155: still
|
|
here'. You could then write a macro
|
|
|
|
\c %macro notdeadyet 0
|
|
\c
|
|
\c push eax
|
|
\c mov eax,__LINE__
|
|
\c call stillhere
|
|
\c pop eax
|
|
\c
|
|
\c %endmacro
|
|
|
|
and then pepper your code with calls to \c{notdeadyet} until you
|
|
find the crash point.
|
|
|
|
|
|
\S{bitsm} \i\c{__BITS__}: Current BITS Mode
|
|
|
|
The \c{__BITS__} standard macro is updated every time that the BITS mode is
|
|
set using the \c{BITS XX} or \c{[BITS XX]} directive, where XX is a valid mode
|
|
number of 16, 32 or 64. \c{__BITS__} receives the specified mode number and
|
|
makes it globally available. This can be very useful for those who utilize
|
|
mode-dependent macros.
|
|
|
|
\S{ofmtm} \i\c{__OUTPUT_FORMAT__}: Current Output Format
|
|
|
|
The \c{__OUTPUT_FORMAT__} standard macro holds the current Output Format,
|
|
as given by the \c{-f} option or NASM's default. Type \c{nasm -hf} for a
|
|
list.
|
|
|
|
\c %ifidn __OUTPUT_FORMAT__, win32
|
|
\c %define NEWLINE 13, 10
|
|
\c %elifidn __OUTPUT_FORMAT__, elf32
|
|
\c %define NEWLINE 10
|
|
\c %endif
|
|
|
|
|
|
\S{datetime} Assembly Date and Time Macros
|
|
|
|
NASM provides a variety of macros that represent the timestamp of the
|
|
assembly session.
|
|
|
|
\b The \i\c{__DATE__} and \i\c{__TIME__} macros give the assembly date and
|
|
time as strings, in ISO 8601 format (\c{"YYYY-MM-DD"} and \c{"HH:MM:SS"},
|
|
respectively.)
|
|
|
|
\b The \i\c{__DATE_NUM__} and \i\c{__TIME_NUM__} macros give the assembly
|
|
date and time in numeric form; in the format \c{YYYYMMDD} and
|
|
\c{HHMMSS} respectively.
|
|
|
|
\b The \i\c{__UTC_DATE__} and \i\c{__UTC_TIME__} macros give the assembly
|
|
date and time in universal time (UTC) as strings, in ISO 8601 format
|
|
(\c{"YYYY-MM-DD"} and \c{"HH:MM:SS"}, respectively.) If the host
|
|
platform doesn't provide UTC time, these macros are undefined.
|
|
|
|
\b The \i\c{__UTC_DATE_NUM__} and \i\c{__UTC_TIME_NUM__} macros give the
|
|
assembly date and time universal time (UTC) in numeric form; in the
|
|
format \c{YYYYMMDD} and \c{HHMMSS} respectively. If the
|
|
host platform doesn't provide UTC time, these macros are
|
|
undefined.
|
|
|
|
\b The \c{__POSIX_TIME__} macro is defined as a number containing the
|
|
number of seconds since the POSIX epoch, 1 January 1970 00:00:00 UTC;
|
|
excluding any leap seconds. This is computed using UTC time if
|
|
available on the host platform, otherwise it is computed using the
|
|
local time as if it was UTC.
|
|
|
|
All instances of time and date macros in the same assembly session
|
|
produce consistent output. For example, in an assembly session
|
|
started at 42 seconds after midnight on January 1, 2010 in Moscow
|
|
(timezone UTC+3) these macros would have the following values,
|
|
assuming, of course, a properly configured environment with a correct
|
|
clock:
|
|
|
|
\c __DATE__ "2010-01-01"
|
|
\c __TIME__ "00:00:42"
|
|
\c __DATE_NUM__ 20100101
|
|
\c __TIME_NUM__ 000042
|
|
\c __UTC_DATE__ "2009-12-31"
|
|
\c __UTC_TIME__ "21:00:42"
|
|
\c __UTC_DATE_NUM__ 20091231
|
|
\c __UTC_TIME_NUM__ 210042
|
|
\c __POSIX_TIME__ 1262293242
|
|
|
|
|
|
\S{use_def} \I\c{__USE_*__}\c{__USE_}\e{package}\c{__}: Package
|
|
Include Test
|
|
|
|
When a standard macro package (see \k{macropkg}) is included with the
|
|
\c{%use} directive (see \k{use}), a single-line macro of the form
|
|
\c{__USE_}\e{package}\c{__} is automatically defined. This allows
|
|
testing if a particular package is invoked or not.
|
|
|
|
For example, if the \c{altreg} package is included (see
|
|
\k{pkg_altreg}), then the macro \c{__USE_ALTREG__} is defined.
|
|
|
|
|
|
\S{pass_macro} \i\c{__PASS__}: Assembly Pass
|
|
|
|
The macro \c{__PASS__} is defined to be \c{1} on preparatory passes,
|
|
and \c{2} on the final pass. In preprocess-only mode, it is set to
|
|
\c{3}, and when running only to generate dependencies (due to the
|
|
\c{-M} or \c{-MG} option, see \k{opt-M}) it is set to \c{0}.
|
|
|
|
\e{Avoid using this macro if at all possible. It is tremendously easy
|
|
to generate very strange errors by misusing it, and the semantics may
|
|
change in future versions of NASM.}
|
|
|
|
|
|
\S{struc} \i\c{STRUC} and \i\c{ENDSTRUC}: \i{Declaring Structure} Data Types
|
|
|
|
The core of NASM contains no intrinsic means of defining data
|
|
structures; instead, the preprocessor is sufficiently powerful that
|
|
data structures can be implemented as a set of macros. The macros
|
|
\c{STRUC} and \c{ENDSTRUC} are used to define a structure data type.
|
|
|
|
\c{STRUC} takes one parameter, which is the name of the data type.
|
|
This name is defined as a symbol with the value zero, and also has
|
|
the suffix \c{_size} appended to it and is then defined as an
|
|
\c{EQU} giving the size of the structure. Once \c{STRUC} has been
|
|
issued, you are defining the structure, and should define fields
|
|
using the \c{RESB} family of pseudo-instructions, and then invoke
|
|
\c{ENDSTRUC} to finish the definition.
|
|
|
|
For example, to define a structure called \c{mytype} containing a
|
|
longword, a word, a byte and a string of bytes, you might code
|
|
|
|
\c struc mytype
|
|
\c
|
|
\c mt_long: resd 1
|
|
\c mt_word: resw 1
|
|
\c mt_byte: resb 1
|
|
\c mt_str: resb 32
|
|
\c
|
|
\c endstruc
|
|
|
|
The above code defines six symbols: \c{mt_long} as 0 (the offset
|
|
from the beginning of a \c{mytype} structure to the longword field),
|
|
\c{mt_word} as 4, \c{mt_byte} as 6, \c{mt_str} as 7, \c{mytype_size}
|
|
as 39, and \c{mytype} itself as zero.
|
|
|
|
The reason why the structure type name is defined at zero is a side
|
|
effect of allowing structures to work with the local label
|
|
mechanism: if your structure members tend to have the same names in
|
|
more than one structure, you can define the above structure like this:
|
|
|
|
\c struc mytype
|
|
\c
|
|
\c .long: resd 1
|
|
\c .word: resw 1
|
|
\c .byte: resb 1
|
|
\c .str: resb 32
|
|
\c
|
|
\c endstruc
|
|
|
|
This defines the offsets to the structure fields as \c{mytype.long},
|
|
\c{mytype.word}, \c{mytype.byte} and \c{mytype.str}.
|
|
|
|
NASM, since it has no \e{intrinsic} structure support, does not
|
|
support any form of period notation to refer to the elements of a
|
|
structure once you have one (except the above local-label notation),
|
|
so code such as \c{mov ax,[mystruc.mt_word]} is not valid.
|
|
\c{mt_word} is a constant just like any other constant, so the
|
|
correct syntax is \c{mov ax,[mystruc+mt_word]} or \c{mov
|
|
ax,[mystruc+mytype.word]}.
|
|
|
|
|
|
\S{istruc} \i\c{ISTRUC}, \i\c{AT} and \i\c{IEND}: Declaring
|
|
\i{Instances of Structures}
|
|
|
|
Having defined a structure type, the next thing you typically want
|
|
to do is to declare instances of that structure in your data
|
|
segment. NASM provides an easy way to do this in the \c{ISTRUC}
|
|
mechanism. To declare a structure of type \c{mytype} in a program,
|
|
you code something like this:
|
|
|
|
\c mystruc:
|
|
\c istruc mytype
|
|
\c
|
|
\c at mt_long, dd 123456
|
|
\c at mt_word, dw 1024
|
|
\c at mt_byte, db 'x'
|
|
\c at mt_str, db 'hello, world', 13, 10, 0
|
|
\c
|
|
\c iend
|
|
|
|
The function of the \c{AT} macro is to make use of the \c{TIMES}
|
|
prefix to advance the assembly position to the correct point for the
|
|
specified structure field, and then to declare the specified data.
|
|
Therefore the structure fields must be declared in the same order as
|
|
they were specified in the structure definition.
|
|
|
|
If the data to go in a structure field requires more than one source
|
|
line to specify, the remaining source lines can easily come after
|
|
the \c{AT} line. For example:
|
|
|
|
\c at mt_str, db 123,134,145,156,167,178,189
|
|
\c db 190,100,0
|
|
|
|
Depending on personal taste, you can also omit the code part of the
|
|
\c{AT} line completely, and start the structure field on the next
|
|
line:
|
|
|
|
\c at mt_str
|
|
\c db 'hello, world'
|
|
\c db 13,10,0
|
|
|
|
|
|
\S{align} \i\c{ALIGN} and \i\c{ALIGNB}: Data Alignment
|
|
|
|
The \c{ALIGN} and \c{ALIGNB} macros provides a convenient way to
|
|
align code or data on a word, longword, paragraph or other boundary.
|
|
(Some assemblers call this directive \i\c{EVEN}.) The syntax of the
|
|
\c{ALIGN} and \c{ALIGNB} macros is
|
|
|
|
\c align 4 ; align on 4-byte boundary
|
|
\c align 16 ; align on 16-byte boundary
|
|
\c align 8,db 0 ; pad with 0s rather than NOPs
|
|
\c align 4,resb 1 ; align to 4 in the BSS
|
|
\c alignb 4 ; equivalent to previous line
|
|
|
|
Both macros require their first argument to be a power of two; they
|
|
both compute the number of additional bytes required to bring the
|
|
length of the current section up to a multiple of that power of two,
|
|
and then apply the \c{TIMES} prefix to their second argument to
|
|
perform the alignment.
|
|
|
|
If the second argument is not specified, the default for \c{ALIGN}
|
|
is \c{NOP}, and the default for \c{ALIGNB} is \c{RESB 1}. So if the
|
|
second argument is specified, the two macros are equivalent.
|
|
Normally, you can just use \c{ALIGN} in code and data sections and
|
|
\c{ALIGNB} in BSS sections, and never need the second argument
|
|
except for special purposes.
|
|
|
|
\c{ALIGN} and \c{ALIGNB}, being simple macros, perform no error
|
|
checking: they cannot warn you if their first argument fails to be a
|
|
power of two, or if their second argument generates more than one
|
|
byte of code. In each of these cases they will silently do the wrong
|
|
thing.
|
|
|
|
\c{ALIGNB} (or \c{ALIGN} with a second argument of \c{RESB 1}) can
|
|
be used within structure definitions:
|
|
|
|
\c struc mytype2
|
|
\c
|
|
\c mt_byte:
|
|
\c resb 1
|
|
\c alignb 2
|
|
\c mt_word:
|
|
\c resw 1
|
|
\c alignb 4
|
|
\c mt_long:
|
|
\c resd 1
|
|
\c mt_str:
|
|
\c resb 32
|
|
\c
|
|
\c endstruc
|
|
|
|
This will ensure that the structure members are sensibly aligned
|
|
relative to the base of the structure.
|
|
|
|
A final caveat: \c{ALIGN} and \c{ALIGNB} work relative to the
|
|
beginning of the \e{section}, not the beginning of the address space
|
|
in the final executable. Aligning to a 16-byte boundary when the
|
|
section you're in is only guaranteed to be aligned to a 4-byte
|
|
boundary, for example, is a waste of effort. Again, NASM does not
|
|
check that the section's alignment characteristics are sensible for
|
|
the use of \c{ALIGN} or \c{ALIGNB}.
|
|
|
|
See also the \c{smartalign} standard macro package, \k{pkg_smartalign}.
|
|
|
|
|
|
\C{macropkg} \i{Standard Macro Packages}
|
|
|
|
The \i\c{%use} directive (see \k{use}) includes one of the standard
|
|
macro packages included with the NASM distribution and compiled into
|
|
the NASM binary. It operates like the \c{%include} directive (see
|
|
\k{include}), but the included contents is provided by NASM itself.
|
|
|
|
The names of standard macro packages are case insensitive, and can be
|
|
quoted or not.
|
|
|
|
|
|
\H{pkg_altreg} \i\c{altreg}: \i{Alternate Register Names}
|
|
|
|
The \c{altreg} standard macro package provides alternate register
|
|
names. It provides numeric register names for all registers (not just
|
|
\c{R8}-\c{R15}), the Intel-defined aliases \c{R8L}-\c{R15L} for the
|
|
low bytes of register (as opposed to the NASM/AMD standard names
|
|
\c{R8B}-\c{R15B}), and the names \c{R0H}-\c{R3H} (by analogy with
|
|
\c{R0L}-\c{R3L}) for \c{AH}, \c{CH}, \c{DH}, and \c{BH}.
|
|
|
|
Example use:
|
|
|
|
\c %use altreg
|
|
\c
|
|
\c proc:
|
|
\c mov r0l,r3h ; mov al,bh
|
|
\c ret
|
|
|
|
See also \k{reg64}.
|
|
|
|
|
|
\H{pkg_smartalign} \i\c{smartalign}\I{align, smart}: Smart \c{ALIGN} Macro
|
|
|
|
The \c{smartalign} standard macro package provides for an \i\c{ALIGN}
|
|
macro which is more powerful than the default (and
|
|
backwards-compatible) one (see \k{align}). When the \c{smartalign}
|
|
package is enabled, when \c{ALIGN} is used without a second argument,
|
|
NASM will generate a sequence of instructions more efficient than a
|
|
series of \c{NOP}. Furthermore, if the padding exceeds a specific
|
|
threshold, then NASM will generate a jump over the entire padding
|
|
sequence.
|
|
|
|
The specific instructions generated can be controlled with the
|
|
new \i\c{ALIGNMODE} macro. This macro takes two parameters: one mode,
|
|
and an optional jump threshold override. The modes are as
|
|
follows:
|
|
|
|
\b \c{generic}: Works on all x86 CPUs and should have reasonable
|
|
performance. The default jump threshold is 8. This is the
|
|
default.
|
|
|
|
\b \c{nop}: Pad out with \c{NOP} instructions. The only difference
|
|
compared to the standard \c{ALIGN} macro is that NASM can still jump
|
|
over a large padding area. The default jump threshold is 16.
|
|
|
|
\b \c{k7}: Optimize for the AMD K7 (Athlon/Althon XP). These
|
|
instructions should still work on all x86 CPUs. The default jump
|
|
threshold is 16.
|
|
|
|
\b \c{k8}: Optimize for the AMD K8 (Opteron/Althon 64). These
|
|
instructions should still work on all x86 CPUs. The default jump
|
|
threshold is 16.
|
|
|
|
\b \c{p6}: Optimize for Intel CPUs. This uses the long \c{NOP}
|
|
instructions first introduced in Pentium Pro. This is incompatible
|
|
with all CPUs of family 5 or lower, as well as some VIA CPUs and
|
|
several virtualization solutions. The default jump threshold is 16.
|
|
|
|
The macro \i\c{__ALIGNMODE__} is defined to contain the current
|
|
alignment mode. A number of other macros beginning with \c{__ALIGN_}
|
|
are used internally by this macro package.
|
|
|
|
|
|
\C{directive} \i{Assembler Directives}
|
|
|
|
NASM, though it attempts to avoid the bureaucracy of assemblers like
|
|
MASM and TASM, is nevertheless forced to support a \e{few}
|
|
directives. These are described in this chapter.
|
|
|
|
NASM's directives come in two types: \I{user-level
|
|
directives}\e{user-level} directives and \I{primitive
|
|
directives}\e{primitive} directives. Typically, each directive has a
|
|
user-level form and a primitive form. In almost all cases, we
|
|
recommend that users use the user-level forms of the directives,
|
|
which are implemented as macros which call the primitive forms.
|
|
|
|
Primitive directives are enclosed in square brackets; user-level
|
|
directives are not.
|
|
|
|
In addition to the universal directives described in this chapter,
|
|
each object file format can optionally supply extra directives in
|
|
order to control particular features of that file format. These
|
|
\I{format-specific directives}\e{format-specific} directives are
|
|
documented along with the formats that implement them, in \k{outfmt}.
|
|
|
|
|
|
\H{bits} \i\c{BITS}: Specifying Target \i{Processor Mode}
|
|
|
|
The \c{BITS} directive specifies whether NASM should generate code
|
|
\I{16-bit mode, versus 32-bit mode}designed to run on a processor
|
|
operating in 16-bit mode, 32-bit mode or 64-bit mode. The syntax is
|
|
\c{BITS XX}, where XX is 16, 32 or 64.
|
|
|
|
In most cases, you should not need to use \c{BITS} explicitly. The
|
|
\c{aout}, \c{coff}, \c{elf}, \c{macho}, \c{win32} and \c{win64}
|
|
object formats, which are designed for use in 32-bit or 64-bit
|
|
operating systems, all cause NASM to select 32-bit or 64-bit mode,
|
|
respectively, by default. The \c{obj} object format allows you
|
|
to specify each segment you define as either \c{USE16} or \c{USE32},
|
|
and NASM will set its operating mode accordingly, so the use of the
|
|
\c{BITS} directive is once again unnecessary.
|
|
|
|
The most likely reason for using the \c{BITS} directive is to write
|
|
32-bit or 64-bit code in a flat binary file; this is because the \c{bin}
|
|
output format defaults to 16-bit mode in anticipation of it being
|
|
used most frequently to write DOS \c{.COM} programs, DOS \c{.SYS}
|
|
device drivers and boot loader software.
|
|
|
|
You do \e{not} need to specify \c{BITS 32} merely in order to use
|
|
32-bit instructions in a 16-bit DOS program; if you do, the
|
|
assembler will generate incorrect code because it will be writing
|
|
code targeted at a 32-bit platform, to be run on a 16-bit one.
|
|
|
|
When NASM is in \c{BITS 16} mode, instructions which use 32-bit
|
|
data are prefixed with an 0x66 byte, and those referring to 32-bit
|
|
addresses have an 0x67 prefix. In \c{BITS 32} mode, the reverse is
|
|
true: 32-bit instructions require no prefixes, whereas instructions
|
|
using 16-bit data need an 0x66 and those working on 16-bit addresses
|
|
need an 0x67.
|
|
|
|
When NASM is in \c{BITS 64} mode, most instructions operate the same
|
|
as they do for \c{BITS 32} mode. However, there are 8 more general and
|
|
SSE registers, and 16-bit addressing is no longer supported.
|
|
|
|
The default address size is 64 bits; 32-bit addressing can be selected
|
|
with the 0x67 prefix. The default operand size is still 32 bits,
|
|
however, and the 0x66 prefix selects 16-bit operand size. The \c{REX}
|
|
prefix is used both to select 64-bit operand size, and to access the
|
|
new registers. NASM automatically inserts REX prefixes when
|
|
necessary.
|
|
|
|
When the \c{REX} prefix is used, the processor does not know how to
|
|
address the AH, BH, CH or DH (high 8-bit legacy) registers. Instead,
|
|
it is possible to access the the low 8-bits of the SP, BP SI and DI
|
|
registers as SPL, BPL, SIL and DIL, respectively; but only when the
|
|
REX prefix is used.
|
|
|
|
The \c{BITS} directive has an exactly equivalent primitive form,
|
|
\c{[BITS 16]}, \c{[BITS 32]} and \c{[BITS 64]}. The user-level form is
|
|
a macro which has no function other than to call the primitive form.
|
|
|
|
Note that the space is neccessary, e.g. \c{BITS32} will \e{not} work!
|
|
|
|
\S{USE16 & USE32} \i\c{USE16} & \i\c{USE32}: Aliases for BITS
|
|
|
|
The `\c{USE16}' and `\c{USE32}' directives can be used in place of
|
|
`\c{BITS 16}' and `\c{BITS 32}', for compatibility with other assemblers.
|
|
|
|
|
|
\H{default} \i\c{DEFAULT}: Change the assembler defaults
|
|
|
|
The \c{DEFAULT} directive changes the assembler defaults. Normally,
|
|
NASM defaults to a mode where the programmer is expected to explicitly
|
|
specify most features directly. However, this is occationally
|
|
obnoxious, as the explicit form is pretty much the only one one wishes
|
|
to use.
|
|
|
|
Currently, the only \c{DEFAULT} that is settable is whether or not
|
|
registerless instructions in 64-bit mode are \c{RIP}-relative or not.
|
|
By default, they are absolute unless overridden with the \i\c{REL}
|
|
specifier (see \k{effaddr}). However, if \c{DEFAULT REL} is
|
|
specified, \c{REL} is default, unless overridden with the \c{ABS}
|
|
specifier, \e{except when used with an FS or GS segment override}.
|
|
|
|
The special handling of \c{FS} and \c{GS} overrides are due to the
|
|
fact that these registers are generally used as thread pointers or
|
|
other special functions in 64-bit mode, and generating
|
|
\c{RIP}-relative addresses would be extremely confusing.
|
|
|
|
\c{DEFAULT REL} is disabled with \c{DEFAULT ABS}.
|
|
|
|
\H{section} \i\c{SECTION} or \i\c{SEGMENT}: Changing and \i{Defining
|
|
Sections}
|
|
|
|
\I{changing sections}\I{switching between sections}The \c{SECTION}
|
|
directive (\c{SEGMENT} is an exactly equivalent synonym) changes
|
|
which section of the output file the code you write will be
|
|
assembled into. In some object file formats, the number and names of
|
|
sections are fixed; in others, the user may make up as many as they
|
|
wish. Hence \c{SECTION} may sometimes give an error message, or may
|
|
define a new section, if you try to switch to a section that does
|
|
not (yet) exist.
|
|
|
|
The Unix object formats, and the \c{bin} object format (but see
|
|
\k{multisec}, all support
|
|
the \i{standardized section names} \c{.text}, \c{.data} and \c{.bss}
|
|
for the code, data and uninitialized-data sections. The \c{obj}
|
|
format, by contrast, does not recognize these section names as being
|
|
special, and indeed will strip off the leading period of any section
|
|
name that has one.
|
|
|
|
|
|
\S{sectmac} The \i\c{__SECT__} Macro
|
|
|
|
The \c{SECTION} directive is unusual in that its user-level form
|
|
functions differently from its primitive form. The primitive form,
|
|
\c{[SECTION xyz]}, simply switches the current target section to the
|
|
one given. The user-level form, \c{SECTION xyz}, however, first
|
|
defines the single-line macro \c{__SECT__} to be the primitive
|
|
\c{[SECTION]} directive which it is about to issue, and then issues
|
|
it. So the user-level directive
|
|
|
|
\c SECTION .text
|
|
|
|
expands to the two lines
|
|
|
|
\c %define __SECT__ [SECTION .text]
|
|
\c [SECTION .text]
|
|
|
|
Users may find it useful to make use of this in their own macros.
|
|
For example, the \c{writefile} macro defined in \k{mlmacgre} can be
|
|
usefully rewritten in the following more sophisticated form:
|
|
|
|
\c %macro writefile 2+
|
|
\c
|
|
\c [section .data]
|
|
\c
|
|
\c %%str: db %2
|
|
\c %%endstr:
|
|
\c
|
|
\c __SECT__
|
|
\c
|
|
\c mov dx,%%str
|
|
\c mov cx,%%endstr-%%str
|
|
\c mov bx,%1
|
|
\c mov ah,0x40
|
|
\c int 0x21
|
|
\c
|
|
\c %endmacro
|
|
|
|
This form of the macro, once passed a string to output, first
|
|
switches temporarily to the data section of the file, using the
|
|
primitive form of the \c{SECTION} directive so as not to modify
|
|
\c{__SECT__}. It then declares its string in the data section, and
|
|
then invokes \c{__SECT__} to switch back to \e{whichever} section
|
|
the user was previously working in. It thus avoids the need, in the
|
|
previous version of the macro, to include a \c{JMP} instruction to
|
|
jump over the data, and also does not fail if, in a complicated
|
|
\c{OBJ} format module, the user could potentially be assembling the
|
|
code in any of several separate code sections.
|
|
|
|
|
|
\H{absolute} \i\c{ABSOLUTE}: Defining Absolute Labels
|
|
|
|
The \c{ABSOLUTE} directive can be thought of as an alternative form
|
|
of \c{SECTION}: it causes the subsequent code to be directed at no
|
|
physical section, but at the hypothetical section starting at the
|
|
given absolute address. The only instructions you can use in this
|
|
mode are the \c{RESB} family.
|
|
|
|
\c{ABSOLUTE} is used as follows:
|
|
|
|
\c absolute 0x1A
|
|
\c
|
|
\c kbuf_chr resw 1
|
|
\c kbuf_free resw 1
|
|
\c kbuf resw 16
|
|
|
|
This example describes a section of the PC BIOS data area, at
|
|
segment address 0x40: the above code defines \c{kbuf_chr} to be
|
|
0x1A, \c{kbuf_free} to be 0x1C, and \c{kbuf} to be 0x1E.
|
|
|
|
The user-level form of \c{ABSOLUTE}, like that of \c{SECTION},
|
|
redefines the \i\c{__SECT__} macro when it is invoked.
|
|
|
|
\i\c{STRUC} and \i\c{ENDSTRUC} are defined as macros which use
|
|
\c{ABSOLUTE} (and also \c{__SECT__}).
|
|
|
|
\c{ABSOLUTE} doesn't have to take an absolute constant as an
|
|
argument: it can take an expression (actually, a \i{critical
|
|
expression}: see \k{crit}) and it can be a value in a segment. For
|
|
example, a TSR can re-use its setup code as run-time BSS like this:
|
|
|
|
\c org 100h ; it's a .COM program
|
|
\c
|
|
\c jmp setup ; setup code comes last
|
|
\c
|
|
\c ; the resident part of the TSR goes here
|
|
\c setup:
|
|
\c ; now write the code that installs the TSR here
|
|
\c
|
|
\c absolute setup
|
|
\c
|
|
\c runtimevar1 resw 1
|
|
\c runtimevar2 resd 20
|
|
\c
|
|
\c tsr_end:
|
|
|
|
This defines some variables `on top of' the setup code, so that
|
|
after the setup has finished running, the space it took up can be
|
|
re-used as data storage for the running TSR. The symbol `tsr_end'
|
|
can be used to calculate the total size of the part of the TSR that
|
|
needs to be made resident.
|
|
|
|
|
|
\H{extern} \i\c{EXTERN}: \i{Importing Symbols} from Other Modules
|
|
|
|
\c{EXTERN} is similar to the MASM directive \c{EXTRN} and the C
|
|
keyword \c{extern}: it is used to declare a symbol which is not
|
|
defined anywhere in the module being assembled, but is assumed to be
|
|
defined in some other module and needs to be referred to by this
|
|
one. Not every object-file format can support external variables:
|
|
the \c{bin} format cannot.
|
|
|
|
The \c{EXTERN} directive takes as many arguments as you like. Each
|
|
argument is the name of a symbol:
|
|
|
|
\c extern _printf
|
|
\c extern _sscanf,_fscanf
|
|
|
|
Some object-file formats provide extra features to the \c{EXTERN}
|
|
directive. In all cases, the extra features are used by suffixing a
|
|
colon to the symbol name followed by object-format specific text.
|
|
For example, the \c{obj} format allows you to declare that the
|
|
default segment base of an external should be the group \c{dgroup}
|
|
by means of the directive
|
|
|
|
\c extern _variable:wrt dgroup
|
|
|
|
The primitive form of \c{EXTERN} differs from the user-level form
|
|
only in that it can take only one argument at a time: the support
|
|
for multiple arguments is implemented at the preprocessor level.
|
|
|
|
You can declare the same variable as \c{EXTERN} more than once: NASM
|
|
will quietly ignore the second and later redeclarations. You can't
|
|
declare a variable as \c{EXTERN} as well as something else, though.
|
|
|
|
|
|
\H{global} \i\c{GLOBAL}: \i{Exporting Symbols} to Other Modules
|
|
|
|
\c{GLOBAL} is the other end of \c{EXTERN}: if one module declares a
|
|
symbol as \c{EXTERN} and refers to it, then in order to prevent
|
|
linker errors, some other module must actually \e{define} the
|
|
symbol and declare it as \c{GLOBAL}. Some assemblers use the name
|
|
\i\c{PUBLIC} for this purpose.
|
|
|
|
The \c{GLOBAL} directive applying to a symbol must appear \e{before}
|
|
the definition of the symbol.
|
|
|
|
\c{GLOBAL} uses the same syntax as \c{EXTERN}, except that it must
|
|
refer to symbols which \e{are} defined in the same module as the
|
|
\c{GLOBAL} directive. For example:
|
|
|
|
\c global _main
|
|
\c _main:
|
|
\c ; some code
|
|
|
|
\c{GLOBAL}, like \c{EXTERN}, allows object formats to define private
|
|
extensions by means of a colon. The \c{elf} object format, for
|
|
example, lets you specify whether global data items are functions or
|
|
data:
|
|
|
|
\c global hashlookup:function, hashtable:data
|
|
|
|
Like \c{EXTERN}, the primitive form of \c{GLOBAL} differs from the
|
|
user-level form only in that it can take only one argument at a
|
|
time.
|
|
|
|
|
|
\H{common} \i\c{COMMON}: Defining Common Data Areas
|
|
|
|
The \c{COMMON} directive is used to declare \i\e{common variables}.
|
|
A common variable is much like a global variable declared in the
|
|
uninitialized data section, so that
|
|
|
|
\c common intvar 4
|
|
|
|
is similar in function to
|
|
|
|
\c global intvar
|
|
\c section .bss
|
|
\c
|
|
\c intvar resd 1
|
|
|
|
The difference is that if more than one module defines the same
|
|
common variable, then at link time those variables will be
|
|
\e{merged}, and references to \c{intvar} in all modules will point
|
|
at the same piece of memory.
|
|
|
|
Like \c{GLOBAL} and \c{EXTERN}, \c{COMMON} supports object-format
|
|
specific extensions. For example, the \c{obj} format allows common
|
|
variables to be NEAR or FAR, and the \c{elf} format allows you to
|
|
specify the alignment requirements of a common variable:
|
|
|
|
\c common commvar 4:near ; works in OBJ
|
|
\c common intarray 100:4 ; works in ELF: 4 byte aligned
|
|
|
|
Once again, like \c{EXTERN} and \c{GLOBAL}, the primitive form of
|
|
\c{COMMON} differs from the user-level form only in that it can take
|
|
only one argument at a time.
|
|
|
|
|
|
\H{CPU} \i\c{CPU}: Defining CPU Dependencies
|
|
|
|
The \i\c{CPU} directive restricts assembly to those instructions which
|
|
are available on the specified CPU.
|
|
|
|
Options are:
|
|
|
|
\b\c{CPU 8086} Assemble only 8086 instruction set
|
|
|
|
\b\c{CPU 186} Assemble instructions up to the 80186 instruction set
|
|
|
|
\b\c{CPU 286} Assemble instructions up to the 286 instruction set
|
|
|
|
\b\c{CPU 386} Assemble instructions up to the 386 instruction set
|
|
|
|
\b\c{CPU 486} 486 instruction set
|
|
|
|
\b\c{CPU 586} Pentium instruction set
|
|
|
|
\b\c{CPU PENTIUM} Same as 586
|
|
|
|
\b\c{CPU 686} P6 instruction set
|
|
|
|
\b\c{CPU PPRO} Same as 686
|
|
|
|
\b\c{CPU P2} Same as 686
|
|
|
|
\b\c{CPU P3} Pentium III (Katmai) instruction sets
|
|
|
|
\b\c{CPU KATMAI} Same as P3
|
|
|
|
\b\c{CPU P4} Pentium 4 (Willamette) instruction set
|
|
|
|
\b\c{CPU WILLAMETTE} Same as P4
|
|
|
|
\b\c{CPU PRESCOTT} Prescott instruction set
|
|
|
|
\b\c{CPU X64} x86-64 (x64/AMD64/Intel 64) instruction set
|
|
|
|
\b\c{CPU IA64} IA64 CPU (in x86 mode) instruction set
|
|
|
|
All options are case insensitive. All instructions will be selected
|
|
only if they apply to the selected CPU or lower. By default, all
|
|
instructions are available.
|
|
|
|
|
|
\H{FLOAT} \i\c{FLOAT}: Handling of \I{floating-point, constants}floating-point constants
|
|
|
|
By default, floating-point constants are rounded to nearest, and IEEE
|
|
denormals are supported. The following options can be set to alter
|
|
this behaviour:
|
|
|
|
\b\c{FLOAT DAZ} Flush denormals to zero
|
|
|
|
\b\c{FLOAT NODAZ} Do not flush denormals to zero (default)
|
|
|
|
\b\c{FLOAT NEAR} Round to nearest (default)
|
|
|
|
\b\c{FLOAT UP} Round up (toward +Infinity)
|
|
|
|
\b\c{FLOAT DOWN} Round down (toward -Infinity)
|
|
|
|
\b\c{FLOAT ZERO} Round toward zero
|
|
|
|
\b\c{FLOAT DEFAULT} Restore default settings
|
|
|
|
The standard macros \i\c{__FLOAT_DAZ__}, \i\c{__FLOAT_ROUND__}, and
|
|
\i\c{__FLOAT__} contain the current state, as long as the programmer
|
|
has avoided the use of the brackeded primitive form, (\c{[FLOAT]}).
|
|
|
|
\c{__FLOAT__} contains the full set of floating-point settings; this
|
|
value can be saved away and invoked later to restore the setting.
|
|
|
|
|
|
\C{outfmt} \i{Output Formats}
|
|
|
|
NASM is a portable assembler, designed to be able to compile on any
|
|
ANSI C-supporting platform and produce output to run on a variety of
|
|
Intel x86 operating systems. For this reason, it has a large number
|
|
of available output formats, selected using the \i\c{-f} option on
|
|
the NASM \i{command line}. Each of these formats, along with its
|
|
extensions to the base NASM syntax, is detailed in this chapter.
|
|
|
|
As stated in \k{opt-o}, NASM chooses a \i{default name} for your
|
|
output file based on the input file name and the chosen output
|
|
format. This will be generated by removing the \i{extension}
|
|
(\c{.asm}, \c{.s}, or whatever you like to use) from the input file
|
|
name, and substituting an extension defined by the output format.
|
|
The extensions are given with each format below.
|
|
|
|
|
|
\H{binfmt} \i\c{bin}: \i{Flat-Form Binary}\I{pure binary} Output
|
|
|
|
The \c{bin} format does not produce object files: it generates
|
|
nothing in the output file except the code you wrote. Such `pure
|
|
binary' files are used by \i{MS-DOS}: \i\c{.COM} executables and
|
|
\i\c{.SYS} device drivers are pure binary files. Pure binary output
|
|
is also useful for \i{operating system} and \i{boot loader}
|
|
development.
|
|
|
|
The \c{bin} format supports \i{multiple section names}. For details of
|
|
how nasm handles sections in the \c{bin} format, see \k{multisec}.
|
|
|
|
Using the \c{bin} format puts NASM by default into 16-bit mode (see
|
|
\k{bits}). In order to use \c{bin} to write 32-bit or 64-bit code,
|
|
such as an OS kernel, you need to explicitly issue the \I\c{BITS}\c{BITS 32}
|
|
or \I\c{BITS}\c{BITS 64} directive.
|
|
|
|
\c{bin} has no default output file name extension: instead, it
|
|
leaves your file name as it is once the original extension has been
|
|
removed. Thus, the default is for NASM to assemble \c{binprog.asm}
|
|
into a binary file called \c{binprog}.
|
|
|
|
|
|
\S{org} \i\c{ORG}: Binary File \i{Program Origin}
|
|
|
|
The \c{bin} format provides an additional directive to the list
|
|
given in \k{directive}: \c{ORG}. The function of the \c{ORG}
|
|
directive is to specify the origin address which NASM will assume
|
|
the program begins at when it is loaded into memory.
|
|
|
|
For example, the following code will generate the longword
|
|
\c{0x00000104}:
|
|
|
|
\c org 0x100
|
|
\c dd label
|
|
\c label:
|
|
|
|
Unlike the \c{ORG} directive provided by MASM-compatible assemblers,
|
|
which allows you to jump around in the object file and overwrite
|
|
code you have already generated, NASM's \c{ORG} does exactly what
|
|
the directive says: \e{origin}. Its sole function is to specify one
|
|
offset which is added to all internal address references within the
|
|
section; it does not permit any of the trickery that MASM's version
|
|
does. See \k{proborg} for further comments.
|
|
|
|
|
|
\S{binseg} \c{bin} Extensions to the \c{SECTION}
|
|
Directive\I{SECTION, bin extensions to}
|
|
|
|
The \c{bin} output format extends the \c{SECTION} (or \c{SEGMENT})
|
|
directive to allow you to specify the alignment requirements of
|
|
segments. This is done by appending the \i\c{ALIGN} qualifier to the
|
|
end of the section-definition line. For example,
|
|
|
|
\c section .data align=16
|
|
|
|
switches to the section \c{.data} and also specifies that it must be
|
|
aligned on a 16-byte boundary.
|
|
|
|
The parameter to \c{ALIGN} specifies how many low bits of the
|
|
section start address must be forced to zero. The alignment value
|
|
given may be any power of two.\I{section alignment, in
|
|
bin}\I{segment alignment, in bin}\I{alignment, in bin sections}
|
|
|
|
|
|
\S{multisec} \i\c{Multisection}\I{bin, multisection} support for the BIN format.
|
|
|
|
The \c{bin} format allows the use of multiple sections, of arbitrary names,
|
|
besides the "known" \c{.text}, \c{.data}, and \c{.bss} names.
|
|
|
|
\b Sections may be designated \i\c{progbits} or \i\c{nobits}. Default
|
|
is \c{progbits} (except \c{.bss}, which defaults to \c{nobits},
|
|
of course).
|
|
|
|
\b Sections can be aligned at a specified boundary following the previous
|
|
section with \c{align=}, or at an arbitrary byte-granular position with
|
|
\i\c{start=}.
|
|
|
|
\b Sections can be given a virtual start address, which will be used
|
|
for the calculation of all memory references within that section
|
|
with \i\c{vstart=}.
|
|
|
|
\b Sections can be ordered using \i\c{follows=}\c{<section>} or
|
|
\i\c{vfollows=}\c{<section>} as an alternative to specifying an explicit
|
|
start address.
|
|
|
|
\b Arguments to \c{org}, \c{start}, \c{vstart}, and \c{align=} are
|
|
critical expressions. See \k{crit}. E.g. \c{align=(1 << ALIGN_SHIFT)}
|
|
- \c{ALIGN_SHIFT} must be defined before it is used here.
|
|
|
|
\b Any code which comes before an explicit \c{SECTION} directive
|
|
is directed by default into the \c{.text} section.
|
|
|
|
\b If an \c{ORG} statement is not given, \c{ORG 0} is used
|
|
by default.
|
|
|
|
\b The \c{.bss} section will be placed after the last \c{progbits}
|
|
section, unless \c{start=}, \c{vstart=}, \c{follows=}, or \c{vfollows=}
|
|
has been specified.
|
|
|
|
\b All sections are aligned on dword boundaries, unless a different
|
|
alignment has been specified.
|
|
|
|
\b Sections may not overlap.
|
|
|
|
\b NASM creates the \c{section.<secname>.start} for each section,
|
|
which may be used in your code.
|
|
|
|
\S{map}\i{Map files}
|
|
|
|
Map files can be generated in \c{-f bin} format by means of the \c{[map]}
|
|
option. Map types of \c{all} (default), \c{brief}, \c{sections}, \c{segments},
|
|
or \c{symbols} may be specified. Output may be directed to \c{stdout}
|
|
(default), \c{stderr}, or a specified file. E.g.
|
|
\c{[map symbols myfile.map]}. No "user form" exists, the square
|
|
brackets must be used.
|
|
|
|
|
|
\H{objfmt} \i\c{obj}: \i{Microsoft OMF}\I{OMF} Object Files
|
|
|
|
The \c{obj} file format (NASM calls it \c{obj} rather than \c{omf}
|
|
for historical reasons) is the one produced by \i{MASM} and
|
|
\i{TASM}, which is typically fed to 16-bit DOS linkers to produce
|
|
\i\c{.EXE} files. It is also the format used by \i{OS/2}.
|
|
|
|
\c{obj} provides a default output file-name extension of \c{.obj}.
|
|
|
|
\c{obj} is not exclusively a 16-bit format, though: NASM has full
|
|
support for the 32-bit extensions to the format. In particular,
|
|
32-bit \c{obj} format files are used by \i{Borland's Win32
|
|
compilers}, instead of using Microsoft's newer \i\c{win32} object
|
|
file format.
|
|
|
|
The \c{obj} format does not define any special segment names: you
|
|
can call your segments anything you like. Typical names for segments
|
|
in \c{obj} format files are \c{CODE}, \c{DATA} and \c{BSS}.
|
|
|
|
If your source file contains code before specifying an explicit
|
|
\c{SEGMENT} directive, then NASM will invent its own segment called
|
|
\i\c{__NASMDEFSEG} for you.
|
|
|
|
When you define a segment in an \c{obj} file, NASM defines the
|
|
segment name as a symbol as well, so that you can access the segment
|
|
address of the segment. So, for example:
|
|
|
|
\c segment data
|
|
\c
|
|
\c dvar: dw 1234
|
|
\c
|
|
\c segment code
|
|
\c
|
|
\c function:
|
|
\c mov ax,data ; get segment address of data
|
|
\c mov ds,ax ; and move it into DS
|
|
\c inc word [dvar] ; now this reference will work
|
|
\c ret
|
|
|
|
The \c{obj} format also enables the use of the \i\c{SEG} and
|
|
\i\c{WRT} operators, so that you can write code which does things
|
|
like
|
|
|
|
\c extern foo
|
|
\c
|
|
\c mov ax,seg foo ; get preferred segment of foo
|
|
\c mov ds,ax
|
|
\c mov ax,data ; a different segment
|
|
\c mov es,ax
|
|
\c mov ax,[ds:foo] ; this accesses `foo'
|
|
\c mov [es:foo wrt data],bx ; so does this
|
|
|
|
|
|
\S{objseg} \c{obj} Extensions to the \c{SEGMENT}
|
|
Directive\I{SEGMENT, obj extensions to}
|
|
|
|
The \c{obj} output format extends the \c{SEGMENT} (or \c{SECTION})
|
|
directive to allow you to specify various properties of the segment
|
|
you are defining. This is done by appending extra qualifiers to the
|
|
end of the segment-definition line. For example,
|
|
|
|
\c segment code private align=16
|
|
|
|
defines the segment \c{code}, but also declares it to be a private
|
|
segment, and requires that the portion of it described in this code
|
|
module must be aligned on a 16-byte boundary.
|
|
|
|
The available qualifiers are:
|
|
|
|
\b \i\c{PRIVATE}, \i\c{PUBLIC}, \i\c{COMMON} and \i\c{STACK} specify
|
|
the combination characteristics of the segment. \c{PRIVATE} segments
|
|
do not get combined with any others by the linker; \c{PUBLIC} and
|
|
\c{STACK} segments get concatenated together at link time; and
|
|
\c{COMMON} segments all get overlaid on top of each other rather
|
|
than stuck end-to-end.
|
|
|
|
\b \i\c{ALIGN} is used, as shown above, to specify how many low bits
|
|
of the segment start address must be forced to zero. The alignment
|
|
value given may be any power of two from 1 to 4096; in reality, the
|
|
only values supported are 1, 2, 4, 16, 256 and 4096, so if 8 is
|
|
specified it will be rounded up to 16, and 32, 64 and 128 will all
|
|
be rounded up to 256, and so on. Note that alignment to 4096-byte
|
|
boundaries is a \i{PharLap} extension to the format and may not be
|
|
supported by all linkers.\I{section alignment, in OBJ}\I{segment
|
|
alignment, in OBJ}\I{alignment, in OBJ sections}
|
|
|
|
\b \i\c{CLASS} can be used to specify the segment class; this feature
|
|
indicates to the linker that segments of the same class should be
|
|
placed near each other in the output file. The class name can be any
|
|
word, e.g. \c{CLASS=CODE}.
|
|
|
|
\b \i\c{OVERLAY}, like \c{CLASS}, is specified with an arbitrary word
|
|
as an argument, and provides overlay information to an
|
|
overlay-capable linker.
|
|
|
|
\b Segments can be declared as \i\c{USE16} or \i\c{USE32}, which has
|
|
the effect of recording the choice in the object file and also
|
|
ensuring that NASM's default assembly mode when assembling in that
|
|
segment is 16-bit or 32-bit respectively.
|
|
|
|
\b When writing \i{OS/2} object files, you should declare 32-bit
|
|
segments as \i\c{FLAT}, which causes the default segment base for
|
|
anything in the segment to be the special group \c{FLAT}, and also
|
|
defines the group if it is not already defined.
|
|
|
|
\b The \c{obj} file format also allows segments to be declared as
|
|
having a pre-defined absolute segment address, although no linkers
|
|
are currently known to make sensible use of this feature;
|
|
nevertheless, NASM allows you to declare a segment such as
|
|
\c{SEGMENT SCREEN ABSOLUTE=0xB800} if you need to. The \i\c{ABSOLUTE}
|
|
and \c{ALIGN} keywords are mutually exclusive.
|
|
|
|
NASM's default segment attributes are \c{PUBLIC}, \c{ALIGN=1}, no
|
|
class, no overlay, and \c{USE16}.
|
|
|
|
|
|
\S{group} \i\c{GROUP}: Defining Groups of Segments\I{segments, groups of}
|
|
|
|
The \c{obj} format also allows segments to be grouped, so that a
|
|
single segment register can be used to refer to all the segments in
|
|
a group. NASM therefore supplies the \c{GROUP} directive, whereby
|
|
you can code
|
|
|
|
\c segment data
|
|
\c
|
|
\c ; some data
|
|
\c
|
|
\c segment bss
|
|
\c
|
|
\c ; some uninitialized data
|
|
\c
|
|
\c group dgroup data bss
|
|
|
|
which will define a group called \c{dgroup} to contain the segments
|
|
\c{data} and \c{bss}. Like \c{SEGMENT}, \c{GROUP} causes the group
|
|
name to be defined as a symbol, so that you can refer to a variable
|
|
\c{var} in the \c{data} segment as \c{var wrt data} or as \c{var wrt
|
|
dgroup}, depending on which segment value is currently in your
|
|
segment register.
|
|
|
|
If you just refer to \c{var}, however, and \c{var} is declared in a
|
|
segment which is part of a group, then NASM will default to giving
|
|
you the offset of \c{var} from the beginning of the \e{group}, not
|
|
the \e{segment}. Therefore \c{SEG var}, also, will return the group
|
|
base rather than the segment base.
|
|
|
|
NASM will allow a segment to be part of more than one group, but
|
|
will generate a warning if you do this. Variables declared in a
|
|
segment which is part of more than one group will default to being
|
|
relative to the first group that was defined to contain the segment.
|
|
|
|
A group does not have to contain any segments; you can still make
|
|
\c{WRT} references to a group which does not contain the variable
|
|
you are referring to. OS/2, for example, defines the special group
|
|
\c{FLAT} with no segments in it.
|
|
|
|
|
|
\S{uppercase} \i\c{UPPERCASE}: Disabling Case Sensitivity in Output
|
|
|
|
Although NASM itself is \i{case sensitive}, some OMF linkers are
|
|
not; therefore it can be useful for NASM to output single-case
|
|
object files. The \c{UPPERCASE} format-specific directive causes all
|
|
segment, group and symbol names that are written to the object file
|
|
to be forced to upper case just before being written. Within a
|
|
source file, NASM is still case-sensitive; but the object file can
|
|
be written entirely in upper case if desired.
|
|
|
|
\c{UPPERCASE} is used alone on a line; it requires no parameters.
|
|
|
|
|
|
\S{import} \i\c{IMPORT}: Importing DLL Symbols\I{DLL symbols,
|
|
importing}\I{symbols, importing from DLLs}
|
|
|
|
The \c{IMPORT} format-specific directive defines a symbol to be
|
|
imported from a DLL, for use if you are writing a DLL's \i{import
|
|
library} in NASM. You still need to declare the symbol as \c{EXTERN}
|
|
as well as using the \c{IMPORT} directive.
|
|
|
|
The \c{IMPORT} directive takes two required parameters, separated by
|
|
white space, which are (respectively) the name of the symbol you
|
|
wish to import and the name of the library you wish to import it
|
|
from. For example:
|
|
|
|
\c import WSAStartup wsock32.dll
|
|
|
|
A third optional parameter gives the name by which the symbol is
|
|
known in the library you are importing it from, in case this is not
|
|
the same as the name you wish the symbol to be known by to your code
|
|
once you have imported it. For example:
|
|
|
|
\c import asyncsel wsock32.dll WSAAsyncSelect
|
|
|
|
|
|
\S{export} \i\c{EXPORT}: Exporting DLL Symbols\I{DLL symbols,
|
|
exporting}\I{symbols, exporting from DLLs}
|
|
|
|
The \c{EXPORT} format-specific directive defines a global symbol to
|
|
be exported as a DLL symbol, for use if you are writing a DLL in
|
|
NASM. You still need to declare the symbol as \c{GLOBAL} as well as
|
|
using the \c{EXPORT} directive.
|
|
|
|
\c{EXPORT} takes one required parameter, which is the name of the
|
|
symbol you wish to export, as it was defined in your source file. An
|
|
optional second parameter (separated by white space from the first)
|
|
gives the \e{external} name of the symbol: the name by which you
|
|
wish the symbol to be known to programs using the DLL. If this name
|
|
is the same as the internal name, you may leave the second parameter
|
|
off.
|
|
|
|
Further parameters can be given to define attributes of the exported
|
|
symbol. These parameters, like the second, are separated by white
|
|
space. If further parameters are given, the external name must also
|
|
be specified, even if it is the same as the internal name. The
|
|
available attributes are:
|
|
|
|
\b \c{resident} indicates that the exported name is to be kept
|
|
resident by the system loader. This is an optimisation for
|
|
frequently used symbols imported by name.
|
|
|
|
\b \c{nodata} indicates that the exported symbol is a function which
|
|
does not make use of any initialized data.
|
|
|
|
\b \c{parm=NNN}, where \c{NNN} is an integer, sets the number of
|
|
parameter words for the case in which the symbol is a call gate
|
|
between 32-bit and 16-bit segments.
|
|
|
|
\b An attribute which is just a number indicates that the symbol
|
|
should be exported with an identifying number (ordinal), and gives
|
|
the desired number.
|
|
|
|
For example:
|
|
|
|
\c export myfunc
|
|
\c export myfunc TheRealMoreFormalLookingFunctionName
|
|
\c export myfunc myfunc 1234 ; export by ordinal
|
|
\c export myfunc myfunc resident parm=23 nodata
|
|
|
|
|
|
\S{dotdotstart} \i\c{..start}: Defining the \i{Program Entry
|
|
Point}
|
|
|
|
\c{OMF} linkers require exactly one of the object files being linked to
|
|
define the program entry point, where execution will begin when the
|
|
program is run. If the object file that defines the entry point is
|
|
assembled using NASM, you specify the entry point by declaring the
|
|
special symbol \c{..start} at the point where you wish execution to
|
|
begin.
|
|
|
|
|
|
\S{objextern} \c{obj} Extensions to the \c{EXTERN}
|
|
Directive\I{EXTERN, obj extensions to}
|
|
|
|
If you declare an external symbol with the directive
|
|
|
|
\c extern foo
|
|
|
|
then references such as \c{mov ax,foo} will give you the offset of
|
|
\c{foo} from its preferred segment base (as specified in whichever
|
|
module \c{foo} is actually defined in). So to access the contents of
|
|
\c{foo} you will usually need to do something like
|
|
|
|
\c mov ax,seg foo ; get preferred segment base
|
|
\c mov es,ax ; move it into ES
|
|
\c mov ax,[es:foo] ; and use offset `foo' from it
|
|
|
|
This is a little unwieldy, particularly if you know that an external
|
|
is going to be accessible from a given segment or group, say
|
|
\c{dgroup}. So if \c{DS} already contained \c{dgroup}, you could
|
|
simply code
|
|
|
|
\c mov ax,[foo wrt dgroup]
|
|
|
|
However, having to type this every time you want to access \c{foo}
|
|
can be a pain; so NASM allows you to declare \c{foo} in the
|
|
alternative form
|
|
|
|
\c extern foo:wrt dgroup
|
|
|
|
This form causes NASM to pretend that the preferred segment base of
|
|
\c{foo} is in fact \c{dgroup}; so the expression \c{seg foo} will
|
|
now return \c{dgroup}, and the expression \c{foo} is equivalent to
|
|
\c{foo wrt dgroup}.
|
|
|
|
This \I{default-WRT mechanism}default-\c{WRT} mechanism can be used
|
|
to make externals appear to be relative to any group or segment in
|
|
your program. It can also be applied to common variables: see
|
|
\k{objcommon}.
|
|
|
|
|
|
\S{objcommon} \c{obj} Extensions to the \c{COMMON}
|
|
Directive\I{COMMON, obj extensions to}
|
|
|
|
The \c{obj} format allows common variables to be either near\I{near
|
|
common variables} or far\I{far common variables}; NASM allows you to
|
|
specify which your variables should be by the use of the syntax
|
|
|
|
\c common nearvar 2:near ; `nearvar' is a near common
|
|
\c common farvar 10:far ; and `farvar' is far
|
|
|
|
Far common variables may be greater in size than 64Kb, and so the
|
|
OMF specification says that they are declared as a number of
|
|
\e{elements} of a given size. So a 10-byte far common variable could
|
|
be declared as ten one-byte elements, five two-byte elements, two
|
|
five-byte elements or one ten-byte element.
|
|
|
|
Some \c{OMF} linkers require the \I{element size, in common
|
|
variables}\I{common variables, element size}element size, as well as
|
|
the variable size, to match when resolving common variables declared
|
|
in more than one module. Therefore NASM must allow you to specify
|
|
the element size on your far common variables. This is done by the
|
|
following syntax:
|
|
|
|
\c common c_5by2 10:far 5 ; two five-byte elements
|
|
\c common c_2by5 10:far 2 ; five two-byte elements
|
|
|
|
If no element size is specified, the default is 1. Also, the \c{FAR}
|
|
keyword is not required when an element size is specified, since
|
|
only far commons may have element sizes at all. So the above
|
|
declarations could equivalently be
|
|
|
|
\c common c_5by2 10:5 ; two five-byte elements
|
|
\c common c_2by5 10:2 ; five two-byte elements
|
|
|
|
In addition to these extensions, the \c{COMMON} directive in \c{obj}
|
|
also supports default-\c{WRT} specification like \c{EXTERN} does
|
|
(explained in \k{objextern}). So you can also declare things like
|
|
|
|
\c common foo 10:wrt dgroup
|
|
\c common bar 16:far 2:wrt data
|
|
\c common baz 24:wrt data:6
|
|
|
|
|
|
\H{win32fmt} \i\c{win32}: Microsoft Win32 Object Files
|
|
|
|
The \c{win32} output format generates Microsoft Win32 object files,
|
|
suitable for passing to Microsoft linkers such as \i{Visual C++}.
|
|
Note that Borland Win32 compilers do not use this format, but use
|
|
\c{obj} instead (see \k{objfmt}).
|
|
|
|
\c{win32} provides a default output file-name extension of \c{.obj}.
|
|
|
|
Note that although Microsoft say that Win32 object files follow the
|
|
\c{COFF} (Common Object File Format) standard, the object files produced
|
|
by Microsoft Win32 compilers are not compatible with COFF linkers
|
|
such as DJGPP's, and vice versa. This is due to a difference of
|
|
opinion over the precise semantics of PC-relative relocations. To
|
|
produce COFF files suitable for DJGPP, use NASM's \c{coff} output
|
|
format; conversely, the \c{coff} format does not produce object
|
|
files that Win32 linkers can generate correct output from.
|
|
|
|
|
|
\S{win32sect} \c{win32} Extensions to the \c{SECTION}
|
|
Directive\I{SECTION, win32 extensions to}
|
|
|
|
Like the \c{obj} format, \c{win32} allows you to specify additional
|
|
information on the \c{SECTION} directive line, to control the type
|
|
and properties of sections you declare. Section types and properties
|
|
are generated automatically by NASM for the \i{standard section names}
|
|
\c{.text}, \c{.data} and \c{.bss}, but may still be overridden by
|
|
these qualifiers.
|
|
|
|
The available qualifiers are:
|
|
|
|
\b \c{code}, or equivalently \c{text}, defines the section to be a
|
|
code section. This marks the section as readable and executable, but
|
|
not writable, and also indicates to the linker that the type of the
|
|
section is code.
|
|
|
|
\b \c{data} and \c{bss} define the section to be a data section,
|
|
analogously to \c{code}. Data sections are marked as readable and
|
|
writable, but not executable. \c{data} declares an initialized data
|
|
section, whereas \c{bss} declares an uninitialized data section.
|
|
|
|
\b \c{rdata} declares an initialized data section that is readable
|
|
but not writable. Microsoft compilers use this section to place
|
|
constants in it.
|
|
|
|
\b \c{info} defines the section to be an \i{informational section},
|
|
which is not included in the executable file by the linker, but may
|
|
(for example) pass information \e{to} the linker. For example,
|
|
declaring an \c{info}-type section called \i\c{.drectve} causes the
|
|
linker to interpret the contents of the section as command-line
|
|
options.
|
|
|
|
\b \c{align=}, used with a trailing number as in \c{obj}, gives the
|
|
\I{section alignment, in win32}\I{alignment, in win32
|
|
sections}alignment requirements of the section. The maximum you may
|
|
specify is 64: the Win32 object file format contains no means to
|
|
request a greater section alignment than this. If alignment is not
|
|
explicitly specified, the defaults are 16-byte alignment for code
|
|
sections, 8-byte alignment for rdata sections and 4-byte alignment
|
|
for data (and BSS) sections.
|
|
Informational sections get a default alignment of 1 byte (no
|
|
alignment), though the value does not matter.
|
|
|
|
The defaults assumed by NASM if you do not specify the above
|
|
qualifiers are:
|
|
|
|
\c section .text code align=16
|
|
\c section .data data align=4
|
|
\c section .rdata rdata align=8
|
|
\c section .bss bss align=4
|
|
|
|
Any other section name is treated by default like \c{.text}.
|
|
|
|
\S{win32safeseh} \c{win32}: Safe Structured Exception Handling
|
|
|
|
Among other improvements in Windows XP SP2 and Windows Server 2003
|
|
Microsoft has introduced concept of "safe structured exception
|
|
handling." General idea is to collect handlers' entry points in
|
|
designated read-only table and have alleged entry point verified
|
|
against this table prior exception control is passed to the handler. In
|
|
order for an executable module to be equipped with such "safe exception
|
|
handler table," all object modules on linker command line has to comply
|
|
with certain criteria. If one single module among them does not, then
|
|
the table in question is omitted and above mentioned run-time checks
|
|
will not be performed for application in question. Table omission is by
|
|
default silent and therefore can be easily overlooked. One can instruct
|
|
linker to refuse to produce binary without such table by passing
|
|
\c{/safeseh} command line option.
|
|
|
|
Without regard to this run-time check merits it's natural to expect
|
|
NASM to be capable of generating modules suitable for \c{/safeseh}
|
|
linking. From developer's viewpoint the problem is two-fold:
|
|
|
|
\b how to adapt modules not deploying exception handlers of their own;
|
|
|
|
\b how to adapt/develop modules utilizing custom exception handling;
|
|
|
|
Former can be easily achieved with any NASM version by adding following
|
|
line to source code:
|
|
|
|
\c $@feat.00 equ 1
|
|
|
|
As of version 2.03 NASM adds this absolute symbol automatically. If
|
|
it's not already present to be precise. I.e. if for whatever reason
|
|
developer would choose to assign another value in source file, it would
|
|
still be perfectly possible.
|
|
|
|
Registering custom exception handler on the other hand requires certain
|
|
"magic." As of version 2.03 additional directive is implemented,
|
|
\c{safeseh}, which instructs the assembler to produce appropriately
|
|
formatted input data for above mentioned "safe exception handler
|
|
table." Its typical use would be:
|
|
|
|
\c section .text
|
|
\c extern _MessageBoxA@16
|
|
\c %if __NASM_VERSION_ID__ >= 0x02030000
|
|
\c safeseh handler ; register handler as "safe handler"
|
|
\c %endif
|
|
\c handler:
|
|
\c push DWORD 1 ; MB_OKCANCEL
|
|
\c push DWORD caption
|
|
\c push DWORD text
|
|
\c push DWORD 0
|
|
\c call _MessageBoxA@16
|
|
\c sub eax,1 ; incidentally suits as return value
|
|
\c ; for exception handler
|
|
\c ret
|
|
\c global _main
|
|
\c _main:
|
|
\c push DWORD handler
|
|
\c push DWORD [fs:0]
|
|
\c mov DWORD [fs:0],esp ; engage exception handler
|
|
\c xor eax,eax
|
|
\c mov eax,DWORD[eax] ; cause exception
|
|
\c pop DWORD [fs:0] ; disengage exception handler
|
|
\c add esp,4
|
|
\c ret
|
|
\c text: db 'OK to rethrow, CANCEL to generate core dump',0
|
|
\c caption:db 'SEGV',0
|
|
\c
|
|
\c section .drectve info
|
|
\c db '/defaultlib:user32.lib /defaultlib:msvcrt.lib '
|
|
|
|
As you might imagine, it's perfectly possible to produce .exe binary
|
|
with "safe exception handler table" and yet engage unregistered
|
|
exception handler. Indeed, handler is engaged by simply manipulating
|
|
\c{[fs:0]} location at run-time, something linker has no power over,
|
|
run-time that is. It should be explicitly mentioned that such failure
|
|
to register handler's entry point with \c{safeseh} directive has
|
|
undesired side effect at run-time. If exception is raised and
|
|
unregistered handler is to be executed, the application is abruptly
|
|
terminated without any notification whatsoever. One can argue that
|
|
system could at least have logged some kind "non-safe exception
|
|
handler in x.exe at address n" message in event log, but no, literally
|
|
no notification is provided and user is left with no clue on what
|
|
caused application failure.
|
|
|
|
Finally, all mentions of linker in this paragraph refer to Microsoft
|
|
linker version 7.x and later. Presence of \c{@feat.00} symbol and input
|
|
data for "safe exception handler table" causes no backward
|
|
incompatibilities and "safeseh" modules generated by NASM 2.03 and
|
|
later can still be linked by earlier versions or non-Microsoft linkers.
|
|
|
|
|
|
\H{win64fmt} \i\c{win64}: Microsoft Win64 Object Files
|
|
|
|
The \c{win64} output format generates Microsoft Win64 object files,
|
|
which is nearly 100% identical to the \c{win32} object format (\k{win32fmt})
|
|
with the exception that it is meant to target 64-bit code and the x86-64
|
|
platform altogether. This object file is used exactly the same as the \c{win32}
|
|
object format (\k{win32fmt}), in NASM, with regard to this exception.
|
|
|
|
\S{win64pic} \c{win64}: Writing Position-Independent Code
|
|
|
|
While \c{REL} takes good care of RIP-relative addressing, there is one
|
|
aspect that is easy to overlook for a Win64 programmer: indirect
|
|
references. Consider a switch dispatch table:
|
|
|
|
\c jmp QWORD[dsptch+rax*8]
|
|
\c ...
|
|
\c dsptch: dq case0
|
|
\c dq case1
|
|
\c ...
|
|
|
|
Even novice Win64 assembler programmer will soon realize that the code
|
|
is not 64-bit savvy. Most notably linker will refuse to link it with
|
|
"\c{'ADDR32' relocation to '.text' invalid without
|
|
/LARGEADDRESSAWARE:NO}". So [s]he will have to split jmp instruction as
|
|
following:
|
|
|
|
\c lea rbx,[rel dsptch]
|
|
\c jmp QWORD[rbx+rax*8]
|
|
|
|
What happens behind the scene is that effective address in \c{lea} is
|
|
encoded relative to instruction pointer, or in perfectly
|
|
position-independent manner. But this is only part of the problem!
|
|
Trouble is that in .dll context \c{caseN} relocations will make their
|
|
way to the final module and might have to be adjusted at .dll load
|
|
time. To be specific when it can't be loaded at preferred address. And
|
|
when this occurs, pages with such relocations will be rendered private
|
|
to current process, which kind of undermines the idea of sharing .dll.
|
|
But no worry, it's trivial to fix:
|
|
|
|
\c lea rbx,[rel dsptch]
|
|
\c add rbx,QWORD[rbx+rax*8]
|
|
\c jmp rbx
|
|
\c ...
|
|
\c dsptch: dq case0-dsptch
|
|
\c dq case1-dsptch
|
|
\c ...
|
|
|
|
NASM version 2.03 and later provides another alternative, \c{wrt
|
|
..imagebase} operator, which returns offset from base address of the
|
|
current image, be it .exe or .dll module, therefore the name. For those
|
|
acquainted with PE-COFF format base address denotes start of
|
|
\c{IMAGE_DOS_HEADER} structure. Here is how to implement switch with
|
|
these image-relative references:
|
|
|
|
\c lea rbx,[rel dsptch]
|
|
\c mov eax,DWORD[rbx+rax*4]
|
|
\c sub rbx,dsptch wrt ..imagebase
|
|
\c add rbx,rax
|
|
\c jmp rbx
|
|
\c ...
|
|
\c dsptch: dd case0 wrt ..imagebase
|
|
\c dd case1 wrt ..imagebase
|
|
|
|
One can argue that the operator is redundant. Indeed, snippet before
|
|
last works just fine with any NASM version and is not even Windows
|
|
specific... The real reason for implementing \c{wrt ..imagebase} will
|
|
become apparent in next paragraph.
|
|
|
|
It should be noted that \c{wrt ..imagebase} is defined as 32-bit
|
|
operand only:
|
|
|
|
\c dd label wrt ..imagebase ; ok
|
|
\c dq label wrt ..imagebase ; bad
|
|
\c mov eax,label wrt ..imagebase ; ok
|
|
\c mov rax,label wrt ..imagebase ; bad
|
|
|
|
\S{win64seh} \c{win64}: Structured Exception Handling
|
|
|
|
Structured exception handing in Win64 is completely different matter
|
|
from Win32. Upon exception program counter value is noted, and
|
|
linker-generated table comprising start and end addresses of all the
|
|
functions [in given executable module] is traversed and compared to the
|
|
saved program counter. Thus so called \c{UNWIND_INFO} structure is
|
|
identified. If it's not found, then offending subroutine is assumed to
|
|
be "leaf" and just mentioned lookup procedure is attempted for its
|
|
caller. In Win64 leaf function is such function that does not call any
|
|
other function \e{nor} modifies any Win64 non-volatile registers,
|
|
including stack pointer. The latter ensures that it's possible to
|
|
identify leaf function's caller by simply pulling the value from the
|
|
top of the stack.
|
|
|
|
While majority of subroutines written in assembler are not calling any
|
|
other function, requirement for non-volatile registers' immutability
|
|
leaves developer with not more than 7 registers and no stack frame,
|
|
which is not necessarily what [s]he counted with. Customarily one would
|
|
meet the requirement by saving non-volatile registers on stack and
|
|
restoring them upon return, so what can go wrong? If [and only if] an
|
|
exception is raised at run-time and no \c{UNWIND_INFO} structure is
|
|
associated with such "leaf" function, the stack unwind procedure will
|
|
expect to find caller's return address on the top of stack immediately
|
|
followed by its frame. Given that developer pushed caller's
|
|
non-volatile registers on stack, would the value on top point at some
|
|
code segment or even addressable space? Well, developer can attempt
|
|
copying caller's return address to the top of stack and this would
|
|
actually work in some very specific circumstances. But unless developer
|
|
can guarantee that these circumstances are always met, it's more
|
|
appropriate to assume worst case scenario, i.e. stack unwind procedure
|
|
going berserk. Relevant question is what happens then? Application is
|
|
abruptly terminated without any notification whatsoever. Just like in
|
|
Win32 case, one can argue that system could at least have logged
|
|
"unwind procedure went berserk in x.exe at address n" in event log, but
|
|
no, no trace of failure is left.
|
|
|
|
Now, when we understand significance of the \c{UNWIND_INFO} structure,
|
|
let's discuss what's in it and/or how it's processed. First of all it
|
|
is checked for presence of reference to custom language-specific
|
|
exception handler. If there is one, then it's invoked. Depending on the
|
|
return value, execution flow is resumed (exception is said to be
|
|
"handled"), \e{or} rest of \c{UNWIND_INFO} structure is processed as
|
|
following. Beside optional reference to custom handler, it carries
|
|
information about current callee's stack frame and where non-volatile
|
|
registers are saved. Information is detailed enough to be able to
|
|
reconstruct contents of caller's non-volatile registers upon call to
|
|
current callee. And so caller's context is reconstructed, and then
|
|
unwind procedure is repeated, i.e. another \c{UNWIND_INFO} structure is
|
|
associated, this time, with caller's instruction pointer, which is then
|
|
checked for presence of reference to language-specific handler, etc.
|
|
The procedure is recursively repeated till exception is handled. As
|
|
last resort system "handles" it by generating memory core dump and
|
|
terminating the application.
|
|
|
|
As for the moment of this writing NASM unfortunately does not
|
|
facilitate generation of above mentioned detailed information about
|
|
stack frame layout. But as of version 2.03 it implements building
|
|
blocks for generating structures involved in stack unwinding. As
|
|
simplest example, here is how to deploy custom exception handler for
|
|
leaf function:
|
|
|
|
\c default rel
|
|
\c section .text
|
|
\c extern MessageBoxA
|
|
\c handler:
|
|
\c sub rsp,40
|
|
\c mov rcx,0
|
|
\c lea rdx,[text]
|
|
\c lea r8,[caption]
|
|
\c mov r9,1 ; MB_OKCANCEL
|
|
\c call MessageBoxA
|
|
\c sub eax,1 ; incidentally suits as return value
|
|
\c ; for exception handler
|
|
\c add rsp,40
|
|
\c ret
|
|
\c global main
|
|
\c main:
|
|
\c xor rax,rax
|
|
\c mov rax,QWORD[rax] ; cause exception
|
|
\c ret
|
|
\c main_end:
|
|
\c text: db 'OK to rethrow, CANCEL to generate core dump',0
|
|
\c caption:db 'SEGV',0
|
|
\c
|
|
\c section .pdata rdata align=4
|
|
\c dd main wrt ..imagebase
|
|
\c dd main_end wrt ..imagebase
|
|
\c dd xmain wrt ..imagebase
|
|
\c section .xdata rdata align=8
|
|
\c xmain: db 9,0,0,0
|
|
\c dd handler wrt ..imagebase
|
|
\c section .drectve info
|
|
\c db '/defaultlib:user32.lib /defaultlib:msvcrt.lib '
|
|
|
|
What you see in \c{.pdata} section is element of the "table comprising
|
|
start and end addresses of function" along with reference to associated
|
|
\c{UNWIND_INFO} structure. And what you see in \c{.xdata} section is
|
|
\c{UNWIND_INFO} structure describing function with no frame, but with
|
|
designated exception handler. References are \e{required} to be
|
|
image-relative (which is the real reason for implementing \c{wrt
|
|
..imagebase} operator). It should be noted that \c{rdata align=n}, as
|
|
well as \c{wrt ..imagebase}, are optional in these two segments'
|
|
contexts, i.e. can be omitted. Latter means that \e{all} 32-bit
|
|
references, not only above listed required ones, placed into these two
|
|
segments turn out image-relative. Why is it important to understand?
|
|
Developer is allowed to append handler-specific data to \c{UNWIND_INFO}
|
|
structure, and if [s]he adds a 32-bit reference, then [s]he will have
|
|
to remember to adjust its value to obtain the real pointer.
|
|
|
|
As already mentioned, in Win64 terms leaf function is one that does not
|
|
call any other function \e{nor} modifies any non-volatile register,
|
|
including stack pointer. But it's not uncommon that assembler
|
|
programmer plans to utilize every single register and sometimes even
|
|
have variable stack frame. Is there anything one can do with bare
|
|
building blocks? I.e. besides manually composing fully-fledged
|
|
\c{UNWIND_INFO} structure, which would surely be considered
|
|
error-prone? Yes, there is. Recall that exception handler is called
|
|
first, before stack layout is analyzed. As it turned out, it's
|
|
perfectly possible to manipulate current callee's context in custom
|
|
handler in manner that permits further stack unwinding. General idea is
|
|
that handler would not actually "handle" the exception, but instead
|
|
restore callee's context, as it was at its entry point and thus mimic
|
|
leaf function. In other words, handler would simply undertake part of
|
|
unwinding procedure. Consider following example:
|
|
|
|
\c function:
|
|
\c mov rax,rsp ; copy rsp to volatile register
|
|
\c push r15 ; save non-volatile registers
|
|
\c push rbx
|
|
\c push rbp
|
|
\c mov r11,rsp ; prepare variable stack frame
|
|
\c sub r11,rcx
|
|
\c and r11,-64
|
|
\c mov QWORD[r11],rax ; check for exceptions
|
|
\c mov rsp,r11 ; allocate stack frame
|
|
\c mov QWORD[rsp],rax ; save original rsp value
|
|
\c magic_point:
|
|
\c ...
|
|
\c mov r11,QWORD[rsp] ; pull original rsp value
|
|
\c mov rbp,QWORD[r11-24]
|
|
\c mov rbx,QWORD[r11-16]
|
|
\c mov r15,QWORD[r11-8]
|
|
\c mov rsp,r11 ; destroy frame
|
|
\c ret
|
|
|
|
The keyword is that up to \c{magic_point} original \c{rsp} value
|
|
remains in chosen volatile register and no non-volatile register,
|
|
except for \c{rsp}, is modified. While past \c{magic_point} \c{rsp}
|
|
remains constant till the very end of the \c{function}. In this case
|
|
custom language-specific exception handler would look like this:
|
|
|
|
\c EXCEPTION_DISPOSITION handler (EXCEPTION_RECORD *rec,ULONG64 frame,
|
|
\c CONTEXT *context,DISPATCHER_CONTEXT *disp)
|
|
\c { ULONG64 *rsp;
|
|
\c if (context->Rip<(ULONG64)magic_point)
|
|
\c rsp = (ULONG64 *)context->Rax;
|
|
\c else
|
|
\c { rsp = ((ULONG64 **)context->Rsp)[0];
|
|
\c context->Rbp = rsp[-3];
|
|
\c context->Rbx = rsp[-2];
|
|
\c context->R15 = rsp[-1];
|
|
\c }
|
|
\c context->Rsp = (ULONG64)rsp;
|
|
\c
|
|
\c memcpy (disp->ContextRecord,context,sizeof(CONTEXT));
|
|
\c RtlVirtualUnwind(UNW_FLAG_NHANDLER,disp->ImageBase,
|
|
\c dips->ControlPc,disp->FunctionEntry,disp->ContextRecord,
|
|
\c &disp->HandlerData,&disp->EstablisherFrame,NULL);
|
|
\c return ExceptionContinueSearch;
|
|
\c }
|
|
|
|
As custom handler mimics leaf function, corresponding \c{UNWIND_INFO}
|
|
structure does not have to contain any information about stack frame
|
|
and its layout.
|
|
|
|
\H{cofffmt} \i\c{coff}: \i{Common Object File Format}
|
|
|
|
The \c{coff} output type produces \c{COFF} object files suitable for
|
|
linking with the \i{DJGPP} linker.
|
|
|
|
\c{coff} provides a default output file-name extension of \c{.o}.
|
|
|
|
The \c{coff} format supports the same extensions to the \c{SECTION}
|
|
directive as \c{win32} does, except that the \c{align} qualifier and
|
|
the \c{info} section type are not supported.
|
|
|
|
\H{machofmt} \i\c{macho}: \i{Mach Object File Format}
|
|
|
|
The \c{macho} output type produces \c{Mach-O} object files suitable for
|
|
linking with the \i{Mac OSX} linker.
|
|
|
|
\c{macho} provides a default output file-name extension of \c{.o}.
|
|
|
|
\H{elffmt} \i\c{elf, elf32, and elf64}: \I{ELF}\I{linux, elf}\i{Executable and Linkable
|
|
Format} Object Files
|
|
|
|
The \c{elf32} and \c{elf64} output formats generate \c{ELF32 and ELF64} (Executable and Linkable Format) object files, as used by Linux as well as \i{Unix System V},
|
|
including \i{Solaris x86}, \i{UnixWare} and \i{SCO Unix}. \c{elf}
|
|
provides a default output file-name extension of \c{.o}.
|
|
\c{elf} is a synonym for \c{elf32}.
|
|
|
|
\S{abisect} ELF specific directive \i\c{osabi}
|
|
|
|
The ELF header specifies the application binary interface for the target operating system (OSABI).
|
|
This field can be set by using the \c{osabi} directive with the numeric value (0-255) of the target
|
|
system. If this directive is not used, the default value will be "UNIX System V ABI" (0) which will work on
|
|
most systems which support ELF.
|
|
|
|
\S{elfsect} \c{elf} Extensions to the \c{SECTION}
|
|
Directive\I{SECTION, elf extensions to}
|
|
|
|
Like the \c{obj} format, \c{elf} allows you to specify additional
|
|
information on the \c{SECTION} directive line, to control the type
|
|
and properties of sections you declare. Section types and properties
|
|
are generated automatically by NASM for the \i{standard section
|
|
names} \i\c{.text}, \i\c{.data} and \i\c{.bss}, but may still be
|
|
overridden by these qualifiers.
|
|
|
|
The available qualifiers are:
|
|
|
|
\b \i\c{alloc} defines the section to be one which is loaded into
|
|
memory when the program is run. \i\c{noalloc} defines it to be one
|
|
which is not, such as an informational or comment section.
|
|
|
|
\b \i\c{exec} defines the section to be one which should have execute
|
|
permission when the program is run. \i\c{noexec} defines it as one
|
|
which should not.
|
|
|
|
\b \i\c{write} defines the section to be one which should be writable
|
|
when the program is run. \i\c{nowrite} defines it as one which should
|
|
not.
|
|
|
|
\b \i\c{progbits} defines the section to be one with explicit contents
|
|
stored in the object file: an ordinary code or data section, for
|
|
example, \i\c{nobits} defines the section to be one with no explicit
|
|
contents given, such as a BSS section.
|
|
|
|
\b \c{align=}, used with a trailing number as in \c{obj}, gives the
|
|
\I{section alignment, in elf}\I{alignment, in elf sections}alignment
|
|
requirements of the section.
|
|
|
|
The defaults assumed by NASM if you do not specify the above
|
|
qualifiers are:
|
|
|
|
\c section .text progbits alloc exec nowrite align=16
|
|
\c section .rodata progbits alloc noexec nowrite align=4
|
|
\c section .data progbits alloc noexec write align=4
|
|
\c section .bss nobits alloc noexec write align=4
|
|
\c section other progbits alloc noexec nowrite align=1
|
|
|
|
(Any section name other than \c{.text}, \c{.rodata}, \c{.data} and
|
|
\c{.bss} is treated by default like \c{other} in the above code.)
|
|
|
|
|
|
\S{elfwrt} \i{Position-Independent Code}\I{PIC}: \c{elf} Special
|
|
Symbols and \i\c{WRT}
|
|
|
|
The \c{ELF} specification contains enough features to allow
|
|
position-independent code (PIC) to be written, which makes \i{ELF
|
|
shared libraries} very flexible. However, it also means NASM has to
|
|
be able to generate a variety of strange relocation types in ELF
|
|
object files, if it is to be an assembler which can write PIC.
|
|
|
|
Since \c{ELF} does not support segment-base references, the \c{WRT}
|
|
operator is not used for its normal purpose; therefore NASM's
|
|
\c{elf} output format makes use of \c{WRT} for a different purpose,
|
|
namely the PIC-specific \I{relocations, PIC-specific}relocation
|
|
types.
|
|
|
|
\c{elf} defines five special symbols which you can use as the
|
|
right-hand side of the \c{WRT} operator to obtain PIC relocation
|
|
types. They are \i\c{..gotpc}, \i\c{..gotoff}, \i\c{..got},
|
|
\i\c{..plt} and \i\c{..sym}. Their functions are summarized here:
|
|
|
|
\b Referring to the symbol marking the global offset table base
|
|
using \c{wrt ..gotpc} will end up giving the distance from the
|
|
beginning of the current section to the global offset table.
|
|
(\i\c{_GLOBAL_OFFSET_TABLE_} is the standard symbol name used to
|
|
refer to the \i{GOT}.) So you would then need to add \i\c{$$} to the
|
|
result to get the real address of the GOT.
|
|
|
|
\b Referring to a location in one of your own sections using \c{wrt
|
|
..gotoff} will give the distance from the beginning of the GOT to
|
|
the specified location, so that adding on the address of the GOT
|
|
would give the real address of the location you wanted.
|
|
|
|
\b Referring to an external or global symbol using \c{wrt ..got}
|
|
causes the linker to build an entry \e{in} the GOT containing the
|
|
address of the symbol, and the reference gives the distance from the
|
|
beginning of the GOT to the entry; so you can add on the address of
|
|
the GOT, load from the resulting address, and end up with the
|
|
address of the symbol.
|
|
|
|
\b Referring to a procedure name using \c{wrt ..plt} causes the
|
|
linker to build a \i{procedure linkage table} entry for the symbol,
|
|
and the reference gives the address of the \i{PLT} entry. You can
|
|
only use this in contexts which would generate a PC-relative
|
|
relocation normally (i.e. as the destination for \c{CALL} or
|
|
\c{JMP}), since ELF contains no relocation type to refer to PLT
|
|
entries absolutely.
|
|
|
|
\b Referring to a symbol name using \c{wrt ..sym} causes NASM to
|
|
write an ordinary relocation, but instead of making the relocation
|
|
relative to the start of the section and then adding on the offset
|
|
to the symbol, it will write a relocation record aimed directly at
|
|
the symbol in question. The distinction is a necessary one due to a
|
|
peculiarity of the dynamic linker.
|
|
|
|
A fuller explanation of how to use these relocation types to write
|
|
shared libraries entirely in NASM is given in \k{picdll}.
|
|
|
|
|
|
\S{elfglob} \c{elf} Extensions to the \c{GLOBAL} Directive\I{GLOBAL,
|
|
elf extensions to}\I{GLOBAL, aoutb extensions to}
|
|
|
|
\c{ELF} object files can contain more information about a global symbol
|
|
than just its address: they can contain the \I{symbol sizes,
|
|
specifying}\I{size, of symbols}size of the symbol and its \I{symbol
|
|
types, specifying}\I{type, of symbols}type as well. These are not
|
|
merely debugger conveniences, but are actually necessary when the
|
|
program being written is a \i{shared library}. NASM therefore
|
|
supports some extensions to the \c{GLOBAL} directive, allowing you
|
|
to specify these features.
|
|
|
|
You can specify whether a global variable is a function or a data
|
|
object by suffixing the name with a colon and the word
|
|
\i\c{function} or \i\c{data}. (\i\c{object} is a synonym for
|
|
\c{data}.) For example:
|
|
|
|
\c global hashlookup:function, hashtable:data
|
|
|
|
exports the global symbol \c{hashlookup} as a function and
|
|
\c{hashtable} as a data object.
|
|
|
|
Optionally, you can control the ELF visibility of the symbol. Just
|
|
add one of the visibility keywords: \i\c{default}, \i\c{internal},
|
|
\i\c{hidden}, or \i\c{protected}. The default is \i\c{default} of
|
|
course. For example, to make \c{hashlookup} hidden:
|
|
|
|
\c global hashlookup:function hidden
|
|
|
|
You can also specify the size of the data associated with the
|
|
symbol, as a numeric expression (which may involve labels, and even
|
|
forward references) after the type specifier. Like this:
|
|
|
|
\c global hashtable:data (hashtable.end - hashtable)
|
|
\c
|
|
\c hashtable:
|
|
\c db this,that,theother ; some data here
|
|
\c .end:
|
|
|
|
This makes NASM automatically calculate the length of the table and
|
|
place that information into the \c{ELF} symbol table.
|
|
|
|
Declaring the type and size of global symbols is necessary when
|
|
writing shared library code. For more information, see
|
|
\k{picglobal}.
|
|
|
|
|
|
\S{elfcomm} \c{elf} Extensions to the \c{COMMON} Directive
|
|
\I{COMMON, elf extensions to}
|
|
|
|
\c{ELF} also allows you to specify alignment requirements \I{common
|
|
variables, alignment in elf}\I{alignment, of elf common variables}on
|
|
common variables. This is done by putting a number (which must be a
|
|
power of two) after the name and size of the common variable,
|
|
separated (as usual) by a colon. For example, an array of
|
|
doublewords would benefit from 4-byte alignment:
|
|
|
|
\c common dwordarray 128:4
|
|
|
|
This declares the total size of the array to be 128 bytes, and
|
|
requires that it be aligned on a 4-byte boundary.
|
|
|
|
|
|
\S{elf16} 16-bit code and ELF
|
|
\I{ELF, 16-bit code and}
|
|
|
|
The \c{ELF32} specification doesn't provide relocations for 8- and
|
|
16-bit values, but the GNU \c{ld} linker adds these as an extension.
|
|
NASM can generate GNU-compatible relocations, to allow 16-bit code to
|
|
be linked as ELF using GNU \c{ld}. If NASM is used with the
|
|
\c{-w+gnu-elf-extensions} option, a warning is issued when one of
|
|
these relocations is generated.
|
|
|
|
\S{elfdbg} Debug formats and ELF
|
|
\I{ELF, Debug formats and}
|
|
|
|
\c{ELF32} and \c{ELF64} provide debug information in \c{STABS} and \c{DWARF} formats.
|
|
Line number information is generated for all executable sections, but please
|
|
note that only the ".text" section is executable by default.
|
|
|
|
\H{aoutfmt} \i\c{aout}: Linux \I{a.out, Linux version}\I{linux, a.out}\c{a.out} Object Files
|
|
|
|
The \c{aout} format generates \c{a.out} object files, in the form used
|
|
by early Linux systems (current Linux systems use ELF, see
|
|
\k{elffmt}.) These differ from other \c{a.out} object files in that
|
|
the magic number in the first four bytes of the file is
|
|
different; also, some implementations of \c{a.out}, for example
|
|
NetBSD's, support position-independent code, which Linux's
|
|
implementation does not.
|
|
|
|
\c{a.out} provides a default output file-name extension of \c{.o}.
|
|
|
|
\c{a.out} is a very simple object format. It supports no special
|
|
directives, no special symbols, no use of \c{SEG} or \c{WRT}, and no
|
|
extensions to any standard directives. It supports only the three
|
|
\i{standard section names} \i\c{.text}, \i\c{.data} and \i\c{.bss}.
|
|
|
|
|
|
\H{aoutfmt} \i\c{aoutb}: \i{NetBSD}/\i{FreeBSD}/\i{OpenBSD}
|
|
\I{a.out, BSD version}\c{a.out} Object Files
|
|
|
|
The \c{aoutb} format generates \c{a.out} object files, in the form
|
|
used by the various free \c{BSD Unix} clones, \c{NetBSD}, \c{FreeBSD}
|
|
and \c{OpenBSD}. For simple object files, this object format is exactly
|
|
the same as \c{aout} except for the magic number in the first four bytes
|
|
of the file. However, the \c{aoutb} format supports
|
|
\I{PIC}\i{position-independent code} in the same way as the \c{elf}
|
|
format, so you can use it to write \c{BSD} \i{shared libraries}.
|
|
|
|
\c{aoutb} provides a default output file-name extension of \c{.o}.
|
|
|
|
\c{aoutb} supports no special directives, no special symbols, and
|
|
only the three \i{standard section names} \i\c{.text}, \i\c{.data}
|
|
and \i\c{.bss}. However, it also supports the same use of \i\c{WRT} as
|
|
\c{elf} does, to provide position-independent code relocation types.
|
|
See \k{elfwrt} for full documentation of this feature.
|
|
|
|
\c{aoutb} also supports the same extensions to the \c{GLOBAL}
|
|
directive as \c{elf} does: see \k{elfglob} for documentation of
|
|
this.
|
|
|
|
|
|
\H{as86fmt} \c{as86}: \i{Minix}/Linux\I{linux, as86} \i\c{as86} Object Files
|
|
|
|
The Minix/Linux 16-bit assembler \c{as86} has its own non-standard
|
|
object file format. Although its companion linker \i\c{ld86} produces
|
|
something close to ordinary \c{a.out} binaries as output, the object
|
|
file format used to communicate between \c{as86} and \c{ld86} is not
|
|
itself \c{a.out}.
|
|
|
|
NASM supports this format, just in case it is useful, as \c{as86}.
|
|
\c{as86} provides a default output file-name extension of \c{.o}.
|
|
|
|
\c{as86} is a very simple object format (from the NASM user's point
|
|
of view). It supports no special directives, no special symbols, no
|
|
use of \c{SEG} or \c{WRT}, and no extensions to any standard
|
|
directives. It supports only the three \i{standard section names}
|
|
\i\c{.text}, \i\c{.data} and \i\c{.bss}.
|
|
|
|
|
|
\H{rdffmt} \I{RDOFF}\i\c{rdf}: \i{Relocatable Dynamic Object File
|
|
Format}
|
|
|
|
The \c{rdf} output format produces \c{RDOFF} object files. \c{RDOFF}
|
|
(Relocatable Dynamic Object File Format) is a home-grown object-file
|
|
format, designed alongside NASM itself and reflecting in its file
|
|
format the internal structure of the assembler.
|
|
|
|
\c{RDOFF} is not used by any well-known operating systems. Those
|
|
writing their own systems, however, may well wish to use \c{RDOFF}
|
|
as their object format, on the grounds that it is designed primarily
|
|
for simplicity and contains very little file-header bureaucracy.
|
|
|
|
The Unix NASM archive, and the DOS archive which includes sources,
|
|
both contain an \I{rdoff subdirectory}\c{rdoff} subdirectory holding
|
|
a set of RDOFF utilities: an RDF linker, an \c{RDF} static-library
|
|
manager, an RDF file dump utility, and a program which will load and
|
|
execute an RDF executable under Linux.
|
|
|
|
\c{rdf} supports only the \i{standard section names} \i\c{.text},
|
|
\i\c{.data} and \i\c{.bss}.
|
|
|
|
|
|
\S{rdflib} Requiring a Library: The \i\c{LIBRARY} Directive
|
|
|
|
\c{RDOFF} contains a mechanism for an object file to demand a given
|
|
library to be linked to the module, either at load time or run time.
|
|
This is done by the \c{LIBRARY} directive, which takes one argument
|
|
which is the name of the module:
|
|
|
|
\c library mylib.rdl
|
|
|
|
|
|
\S{rdfmod} Specifying a Module Name: The \i\c{MODULE} Directive
|
|
|
|
Special \c{RDOFF} header record is used to store the name of the module.
|
|
It can be used, for example, by run-time loader to perform dynamic
|
|
linking. \c{MODULE} directive takes one argument which is the name
|
|
of current module:
|
|
|
|
\c module mymodname
|
|
|
|
Note that when you statically link modules and tell linker to strip
|
|
the symbols from output file, all module names will be stripped too.
|
|
To avoid it, you should start module names with \I{$, prefix}\c{$}, like:
|
|
|
|
\c module $kernel.core
|
|
|
|
|
|
\S{rdfglob} \c{rdf} Extensions to the \c{GLOBAL} directive\I{GLOBAL,
|
|
rdf extensions to}
|
|
|
|
\c{RDOFF} global symbols can contain additional information needed by
|
|
the static linker. You can mark a global symbol as exported, thus
|
|
telling the linker do not strip it from target executable or library
|
|
file. Like in \c{ELF}, you can also specify whether an exported symbol
|
|
is a procedure (function) or data object.
|
|
|
|
Suffixing the name with a colon and the word \i\c{export} you make the
|
|
symbol exported:
|
|
|
|
\c global sys_open:export
|
|
|
|
To specify that exported symbol is a procedure (function), you add the
|
|
word \i\c{proc} or \i\c{function} after declaration:
|
|
|
|
\c global sys_open:export proc
|
|
|
|
Similarly, to specify exported data object, add the word \i\c{data}
|
|
or \i\c{object} to the directive:
|
|
|
|
\c global kernel_ticks:export data
|
|
|
|
|
|
\S{rdfimpt} \c{rdf} Extensions to the \c{EXTERN} directive\I{EXTERN,
|
|
rdf extensions to}
|
|
|
|
By default the \c{EXTERN} directive in \c{RDOFF} declares a "pure external"
|
|
symbol (i.e. the static linker will complain if such a symbol is not resolved).
|
|
To declare an "imported" symbol, which must be resolved later during a dynamic
|
|
linking phase, \c{RDOFF} offers an additional \c{import} modifier. As in
|
|
\c{GLOBAL}, you can also specify whether an imported symbol is a procedure
|
|
(function) or data object. For example:
|
|
|
|
\c library $libc
|
|
\c extern _open:import
|
|
\c extern _printf:import proc
|
|
\c extern _errno:import data
|
|
|
|
Here the directive \c{LIBRARY} is also included, which gives the dynamic linker
|
|
a hint as to where to find requested symbols.
|
|
|
|
|
|
\H{dbgfmt} \i\c{dbg}: Debugging Format
|
|
|
|
The \c{dbg} output format is not built into NASM in the default
|
|
configuration. If you are building your own NASM executable from the
|
|
sources, you can define \i\c{OF_DBG} in \c{outform.h} or on the
|
|
compiler command line, and obtain the \c{dbg} output format.
|
|
|
|
The \c{dbg} format does not output an object file as such; instead,
|
|
it outputs a text file which contains a complete list of all the
|
|
transactions between the main body of NASM and the output-format
|
|
back end module. It is primarily intended to aid people who want to
|
|
write their own output drivers, so that they can get a clearer idea
|
|
of the various requests the main program makes of the output driver,
|
|
and in what order they happen.
|
|
|
|
For simple files, one can easily use the \c{dbg} format like this:
|
|
|
|
\c nasm -f dbg filename.asm
|
|
|
|
which will generate a diagnostic file called \c{filename.dbg}.
|
|
However, this will not work well on files which were designed for a
|
|
different object format, because each object format defines its own
|
|
macros (usually user-level forms of directives), and those macros
|
|
will not be defined in the \c{dbg} format. Therefore it can be
|
|
useful to run NASM twice, in order to do the preprocessing with the
|
|
native object format selected:
|
|
|
|
\c nasm -e -f rdf -o rdfprog.i rdfprog.asm
|
|
\c nasm -a -f dbg rdfprog.i
|
|
|
|
This preprocesses \c{rdfprog.asm} into \c{rdfprog.i}, keeping the
|
|
\c{rdf} object format selected in order to make sure RDF special
|
|
directives are converted into primitive form correctly. Then the
|
|
preprocessed source is fed through the \c{dbg} format to generate
|
|
the final diagnostic output.
|
|
|
|
This workaround will still typically not work for programs intended
|
|
for \c{obj} format, because the \c{obj} \c{SEGMENT} and \c{GROUP}
|
|
directives have side effects of defining the segment and group names
|
|
as symbols; \c{dbg} will not do this, so the program will not
|
|
assemble. You will have to work around that by defining the symbols
|
|
yourself (using \c{EXTERN}, for example) if you really need to get a
|
|
\c{dbg} trace of an \c{obj}-specific source file.
|
|
|
|
\c{dbg} accepts any section name and any directives at all, and logs
|
|
them all to its output file.
|
|
|
|
|
|
\C{16bit} Writing 16-bit Code (DOS, Windows 3/3.1)
|
|
|
|
This chapter attempts to cover some of the common issues encountered
|
|
when writing 16-bit code to run under \c{MS-DOS} or \c{Windows 3.x}. It
|
|
covers how to link programs to produce \c{.EXE} or \c{.COM} files,
|
|
how to write \c{.SYS} device drivers, and how to interface assembly
|
|
language code with 16-bit C compilers and with Borland Pascal.
|
|
|
|
|
|
\H{exefiles} Producing \i\c{.EXE} Files
|
|
|
|
Any large program written under DOS needs to be built as a \c{.EXE}
|
|
file: only \c{.EXE} files have the necessary internal structure
|
|
required to span more than one 64K segment. \i{Windows} programs,
|
|
also, have to be built as \c{.EXE} files, since Windows does not
|
|
support the \c{.COM} format.
|
|
|
|
In general, you generate \c{.EXE} files by using the \c{obj} output
|
|
format to produce one or more \i\c{.OBJ} files, and then linking
|
|
them together using a linker. However, NASM also supports the direct
|
|
generation of simple DOS \c{.EXE} files using the \c{bin} output
|
|
format (by using \c{DB} and \c{DW} to construct the \c{.EXE} file
|
|
header), and a macro package is supplied to do this. Thanks to
|
|
Yann Guidon for contributing the code for this.
|
|
|
|
NASM may also support \c{.EXE} natively as another output format in
|
|
future releases.
|
|
|
|
|
|
\S{objexe} Using the \c{obj} Format To Generate \c{.EXE} Files
|
|
|
|
This section describes the usual method of generating \c{.EXE} files
|
|
by linking \c{.OBJ} files together.
|
|
|
|
Most 16-bit programming language packages come with a suitable
|
|
linker; if you have none of these, there is a free linker called
|
|
\i{VAL}\I{linker, free}, available in \c{LZH} archive format from
|
|
\W{ftp://x2ftp.oulu.fi/pub/msdos/programming/lang/}\i\c{x2ftp.oulu.fi}.
|
|
An LZH archiver can be found at
|
|
\W{ftp://ftp.simtel.net/pub/simtelnet/msdos/arcers}\i\c{ftp.simtel.net}.
|
|
There is another `free' linker (though this one doesn't come with
|
|
sources) called \i{FREELINK}, available from
|
|
\W{http://www.pcorner.com/tpc/old/3-101.html}\i\c{www.pcorner.com}.
|
|
A third, \i\c{djlink}, written by DJ Delorie, is available at
|
|
\W{http://www.delorie.com/djgpp/16bit/djlink/}\i\c{www.delorie.com}.
|
|
A fourth linker, \i\c{ALINK}, written by Anthony A.J. Williams, is
|
|
available at \W{http://alink.sourceforge.net}\i\c{alink.sourceforge.net}.
|
|
|
|
When linking several \c{.OBJ} files into a \c{.EXE} file, you should
|
|
ensure that exactly one of them has a start point defined (using the
|
|
\I{program entry point}\i\c{..start} special symbol defined by the
|
|
\c{obj} format: see \k{dotdotstart}). If no module defines a start
|
|
point, the linker will not know what value to give the entry-point
|
|
field in the output file header; if more than one defines a start
|
|
point, the linker will not know \e{which} value to use.
|
|
|
|
An example of a NASM source file which can be assembled to a
|
|
\c{.OBJ} file and linked on its own to a \c{.EXE} is given here. It
|
|
demonstrates the basic principles of defining a stack, initialising
|
|
the segment registers, and declaring a start point. This file is
|
|
also provided in the \I{test subdirectory}\c{test} subdirectory of
|
|
the NASM archives, under the name \c{objexe.asm}.
|
|
|
|
\c segment code
|
|
\c
|
|
\c ..start:
|
|
\c mov ax,data
|
|
\c mov ds,ax
|
|
\c mov ax,stack
|
|
\c mov ss,ax
|
|
\c mov sp,stacktop
|
|
|
|
This initial piece of code sets up \c{DS} to point to the data
|
|
segment, and initializes \c{SS} and \c{SP} to point to the top of
|
|
the provided stack. Notice that interrupts are implicitly disabled
|
|
for one instruction after a move into \c{SS}, precisely for this
|
|
situation, so that there's no chance of an interrupt occurring
|
|
between the loads of \c{SS} and \c{SP} and not having a stack to
|
|
execute on.
|
|
|
|
Note also that the special symbol \c{..start} is defined at the
|
|
beginning of this code, which means that will be the entry point
|
|
into the resulting executable file.
|
|
|
|
\c mov dx,hello
|
|
\c mov ah,9
|
|
\c int 0x21
|
|
|
|
The above is the main program: load \c{DS:DX} with a pointer to the
|
|
greeting message (\c{hello} is implicitly relative to the segment
|
|
\c{data}, which was loaded into \c{DS} in the setup code, so the
|
|
full pointer is valid), and call the DOS print-string function.
|
|
|
|
\c mov ax,0x4c00
|
|
\c int 0x21
|
|
|
|
This terminates the program using another DOS system call.
|
|
|
|
\c segment data
|
|
\c
|
|
\c hello: db 'hello, world', 13, 10, '$'
|
|
|
|
The data segment contains the string we want to display.
|
|
|
|
\c segment stack stack
|
|
\c resb 64
|
|
\c stacktop:
|
|
|
|
The above code declares a stack segment containing 64 bytes of
|
|
uninitialized stack space, and points \c{stacktop} at the top of it.
|
|
The directive \c{segment stack stack} defines a segment \e{called}
|
|
\c{stack}, and also of \e{type} \c{STACK}. The latter is not
|
|
necessary to the correct running of the program, but linkers are
|
|
likely to issue warnings or errors if your program has no segment of
|
|
type \c{STACK}.
|
|
|
|
The above file, when assembled into a \c{.OBJ} file, will link on
|
|
its own to a valid \c{.EXE} file, which when run will print `hello,
|
|
world' and then exit.
|
|
|
|
|
|
\S{binexe} Using the \c{bin} Format To Generate \c{.EXE} Files
|
|
|
|
The \c{.EXE} file format is simple enough that it's possible to
|
|
build a \c{.EXE} file by writing a pure-binary program and sticking
|
|
a 32-byte header on the front. This header is simple enough that it
|
|
can be generated using \c{DB} and \c{DW} commands by NASM itself, so
|
|
that you can use the \c{bin} output format to directly generate
|
|
\c{.EXE} files.
|
|
|
|
Included in the NASM archives, in the \I{misc subdirectory}\c{misc}
|
|
subdirectory, is a file \i\c{exebin.mac} of macros. It defines three
|
|
macros: \i\c{EXE_begin}, \i\c{EXE_stack} and \i\c{EXE_end}.
|
|
|
|
To produce a \c{.EXE} file using this method, you should start by
|
|
using \c{%include} to load the \c{exebin.mac} macro package into
|
|
your source file. You should then issue the \c{EXE_begin} macro call
|
|
(which takes no arguments) to generate the file header data. Then
|
|
write code as normal for the \c{bin} format - you can use all three
|
|
standard sections \c{.text}, \c{.data} and \c{.bss}. At the end of
|
|
the file you should call the \c{EXE_end} macro (again, no arguments),
|
|
which defines some symbols to mark section sizes, and these symbols
|
|
are referred to in the header code generated by \c{EXE_begin}.
|
|
|
|
In this model, the code you end up writing starts at \c{0x100}, just
|
|
like a \c{.COM} file - in fact, if you strip off the 32-byte header
|
|
from the resulting \c{.EXE} file, you will have a valid \c{.COM}
|
|
program. All the segment bases are the same, so you are limited to a
|
|
64K program, again just like a \c{.COM} file. Note that an \c{ORG}
|
|
directive is issued by the \c{EXE_begin} macro, so you should not
|
|
explicitly issue one of your own.
|
|
|
|
You can't directly refer to your segment base value, unfortunately,
|
|
since this would require a relocation in the header, and things
|
|
would get a lot more complicated. So you should get your segment
|
|
base by copying it out of \c{CS} instead.
|
|
|
|
On entry to your \c{.EXE} file, \c{SS:SP} are already set up to
|
|
point to the top of a 2Kb stack. You can adjust the default stack
|
|
size of 2Kb by calling the \c{EXE_stack} macro. For example, to
|
|
change the stack size of your program to 64 bytes, you would call
|
|
\c{EXE_stack 64}.
|
|
|
|
A sample program which generates a \c{.EXE} file in this way is
|
|
given in the \c{test} subdirectory of the NASM archive, as
|
|
\c{binexe.asm}.
|
|
|
|
|
|
\H{comfiles} Producing \i\c{.COM} Files
|
|
|
|
While large DOS programs must be written as \c{.EXE} files, small
|
|
ones are often better written as \c{.COM} files. \c{.COM} files are
|
|
pure binary, and therefore most easily produced using the \c{bin}
|
|
output format.
|
|
|
|
|
|
\S{combinfmt} Using the \c{bin} Format To Generate \c{.COM} Files
|
|
|
|
\c{.COM} files expect to be loaded at offset \c{100h} into their
|
|
segment (though the segment may change). Execution then begins at
|
|
\I\c{ORG}\c{100h}, i.e. right at the start of the program. So to
|
|
write a \c{.COM} program, you would create a source file looking
|
|
like
|
|
|
|
\c org 100h
|
|
\c
|
|
\c section .text
|
|
\c
|
|
\c start:
|
|
\c ; put your code here
|
|
\c
|
|
\c section .data
|
|
\c
|
|
\c ; put data items here
|
|
\c
|
|
\c section .bss
|
|
\c
|
|
\c ; put uninitialized data here
|
|
|
|
The \c{bin} format puts the \c{.text} section first in the file, so
|
|
you can declare data or BSS items before beginning to write code if
|
|
you want to and the code will still end up at the front of the file
|
|
where it belongs.
|
|
|
|
The BSS (uninitialized data) section does not take up space in the
|
|
\c{.COM} file itself: instead, addresses of BSS items are resolved
|
|
to point at space beyond the end of the file, on the grounds that
|
|
this will be free memory when the program is run. Therefore you
|
|
should not rely on your BSS being initialized to all zeros when you
|
|
run.
|
|
|
|
To assemble the above program, you should use a command line like
|
|
|
|
\c nasm myprog.asm -fbin -o myprog.com
|
|
|
|
The \c{bin} format would produce a file called \c{myprog} if no
|
|
explicit output file name were specified, so you have to override it
|
|
and give the desired file name.
|
|
|
|
|
|
\S{comobjfmt} Using the \c{obj} Format To Generate \c{.COM} Files
|
|
|
|
If you are writing a \c{.COM} program as more than one module, you
|
|
may wish to assemble several \c{.OBJ} files and link them together
|
|
into a \c{.COM} program. You can do this, provided you have a linker
|
|
capable of outputting \c{.COM} files directly (\i{TLINK} does this),
|
|
or alternatively a converter program such as \i\c{EXE2BIN} to
|
|
transform the \c{.EXE} file output from the linker into a \c{.COM}
|
|
file.
|
|
|
|
If you do this, you need to take care of several things:
|
|
|
|
\b The first object file containing code should start its code
|
|
segment with a line like \c{RESB 100h}. This is to ensure that the
|
|
code begins at offset \c{100h} relative to the beginning of the code
|
|
segment, so that the linker or converter program does not have to
|
|
adjust address references within the file when generating the
|
|
\c{.COM} file. Other assemblers use an \i\c{ORG} directive for this
|
|
purpose, but \c{ORG} in NASM is a format-specific directive to the
|
|
\c{bin} output format, and does not mean the same thing as it does
|
|
in MASM-compatible assemblers.
|
|
|
|
\b You don't need to define a stack segment.
|
|
|
|
\b All your segments should be in the same group, so that every time
|
|
your code or data references a symbol offset, all offsets are
|
|
relative to the same segment base. This is because, when a \c{.COM}
|
|
file is loaded, all the segment registers contain the same value.
|
|
|
|
|
|
\H{sysfiles} Producing \i\c{.SYS} Files
|
|
|
|
\i{MS-DOS device drivers} - \c{.SYS} files - are pure binary files,
|
|
similar to \c{.COM} files, except that they start at origin zero
|
|
rather than \c{100h}. Therefore, if you are writing a device driver
|
|
using the \c{bin} format, you do not need the \c{ORG} directive,
|
|
since the default origin for \c{bin} is zero. Similarly, if you are
|
|
using \c{obj}, you do not need the \c{RESB 100h} at the start of
|
|
your code segment.
|
|
|
|
\c{.SYS} files start with a header structure, containing pointers to
|
|
the various routines inside the driver which do the work. This
|
|
structure should be defined at the start of the code segment, even
|
|
though it is not actually code.
|
|
|
|
For more information on the format of \c{.SYS} files, and the data
|
|
which has to go in the header structure, a list of books is given in
|
|
the Frequently Asked Questions list for the newsgroup
|
|
\W{news:comp.os.msdos.programmer}\i\c{comp.os.msdos.programmer}.
|
|
|
|
|
|
\H{16c} Interfacing to 16-bit C Programs
|
|
|
|
This section covers the basics of writing assembly routines that
|
|
call, or are called from, C programs. To do this, you would
|
|
typically write an assembly module as a \c{.OBJ} file, and link it
|
|
with your C modules to produce a \i{mixed-language program}.
|
|
|
|
|
|
\S{16cunder} External Symbol Names
|
|
|
|
\I{C symbol names}\I{underscore, in C symbols}C compilers have the
|
|
convention that the names of all global symbols (functions or data)
|
|
they define are formed by prefixing an underscore to the name as it
|
|
appears in the C program. So, for example, the function a C
|
|
programmer thinks of as \c{printf} appears to an assembly language
|
|
programmer as \c{_printf}. This means that in your assembly
|
|
programs, you can define symbols without a leading underscore, and
|
|
not have to worry about name clashes with C symbols.
|
|
|
|
If you find the underscores inconvenient, you can define macros to
|
|
replace the \c{GLOBAL} and \c{EXTERN} directives as follows:
|
|
|
|
\c %macro cglobal 1
|
|
\c
|
|
\c global _%1
|
|
\c %define %1 _%1
|
|
\c
|
|
\c %endmacro
|
|
\c
|
|
\c %macro cextern 1
|
|
\c
|
|
\c extern _%1
|
|
\c %define %1 _%1
|
|
\c
|
|
\c %endmacro
|
|
|
|
(These forms of the macros only take one argument at a time; a
|
|
\c{%rep} construct could solve this.)
|
|
|
|
If you then declare an external like this:
|
|
|
|
\c cextern printf
|
|
|
|
then the macro will expand it as
|
|
|
|
\c extern _printf
|
|
\c %define printf _printf
|
|
|
|
Thereafter, you can reference \c{printf} as if it was a symbol, and
|
|
the preprocessor will put the leading underscore on where necessary.
|
|
|
|
The \c{cglobal} macro works similarly. You must use \c{cglobal}
|
|
before defining the symbol in question, but you would have had to do
|
|
that anyway if you used \c{GLOBAL}.
|
|
|
|
Also see \k{opt-pfix}.
|
|
|
|
\S{16cmodels} \i{Memory Models}
|
|
|
|
NASM contains no mechanism to support the various C memory models
|
|
directly; you have to keep track yourself of which one you are
|
|
writing for. This means you have to keep track of the following
|
|
things:
|
|
|
|
\b In models using a single code segment (tiny, small and compact),
|
|
functions are near. This means that function pointers, when stored
|
|
in data segments or pushed on the stack as function arguments, are
|
|
16 bits long and contain only an offset field (the \c{CS} register
|
|
never changes its value, and always gives the segment part of the
|
|
full function address), and that functions are called using ordinary
|
|
near \c{CALL} instructions and return using \c{RETN} (which, in
|
|
NASM, is synonymous with \c{RET} anyway). This means both that you
|
|
should write your own routines to return with \c{RETN}, and that you
|
|
should call external C routines with near \c{CALL} instructions.
|
|
|
|
\b In models using more than one code segment (medium, large and
|
|
huge), functions are far. This means that function pointers are 32
|
|
bits long (consisting of a 16-bit offset followed by a 16-bit
|
|
segment), and that functions are called using \c{CALL FAR} (or
|
|
\c{CALL seg:offset}) and return using \c{RETF}. Again, you should
|
|
therefore write your own routines to return with \c{RETF} and use
|
|
\c{CALL FAR} to call external routines.
|
|
|
|
\b In models using a single data segment (tiny, small and medium),
|
|
data pointers are 16 bits long, containing only an offset field (the
|
|
\c{DS} register doesn't change its value, and always gives the
|
|
segment part of the full data item address).
|
|
|
|
\b In models using more than one data segment (compact, large and
|
|
huge), data pointers are 32 bits long, consisting of a 16-bit offset
|
|
followed by a 16-bit segment. You should still be careful not to
|
|
modify \c{DS} in your routines without restoring it afterwards, but
|
|
\c{ES} is free for you to use to access the contents of 32-bit data
|
|
pointers you are passed.
|
|
|
|
\b The huge memory model allows single data items to exceed 64K in
|
|
size. In all other memory models, you can access the whole of a data
|
|
item just by doing arithmetic on the offset field of the pointer you
|
|
are given, whether a segment field is present or not; in huge model,
|
|
you have to be more careful of your pointer arithmetic.
|
|
|
|
\b In most memory models, there is a \e{default} data segment, whose
|
|
segment address is kept in \c{DS} throughout the program. This data
|
|
segment is typically the same segment as the stack, kept in \c{SS},
|
|
so that functions' local variables (which are stored on the stack)
|
|
and global data items can both be accessed easily without changing
|
|
\c{DS}. Particularly large data items are typically stored in other
|
|
segments. However, some memory models (though not the standard
|
|
ones, usually) allow the assumption that \c{SS} and \c{DS} hold the
|
|
same value to be removed. Be careful about functions' local
|
|
variables in this latter case.
|
|
|
|
In models with a single code segment, the segment is called
|
|
\i\c{_TEXT}, so your code segment must also go by this name in order
|
|
to be linked into the same place as the main code segment. In models
|
|
with a single data segment, or with a default data segment, it is
|
|
called \i\c{_DATA}.
|
|
|
|
|
|
\S{16cfunc} Function Definitions and Function Calls
|
|
|
|
\I{functions, C calling convention}The \i{C calling convention} in
|
|
16-bit programs is as follows. In the following description, the
|
|
words \e{caller} and \e{callee} are used to denote the function
|
|
doing the calling and the function which gets called.
|
|
|
|
\b The caller pushes the function's parameters on the stack, one
|
|
after another, in reverse order (right to left, so that the first
|
|
argument specified to the function is pushed last).
|
|
|
|
\b The caller then executes a \c{CALL} instruction to pass control
|
|
to the callee. This \c{CALL} is either near or far depending on the
|
|
memory model.
|
|
|
|
\b The callee receives control, and typically (although this is not
|
|
actually necessary, in functions which do not need to access their
|
|
parameters) starts by saving the value of \c{SP} in \c{BP} so as to
|
|
be able to use \c{BP} as a base pointer to find its parameters on
|
|
the stack. However, the caller was probably doing this too, so part
|
|
of the calling convention states that \c{BP} must be preserved by
|
|
any C function. Hence the callee, if it is going to set up \c{BP} as
|
|
a \i\e{frame pointer}, must push the previous value first.
|
|
|
|
\b The callee may then access its parameters relative to \c{BP}.
|
|
The word at \c{[BP]} holds the previous value of \c{BP} as it was
|
|
pushed; the next word, at \c{[BP+2]}, holds the offset part of the
|
|
return address, pushed implicitly by \c{CALL}. In a small-model
|
|
(near) function, the parameters start after that, at \c{[BP+4]}; in
|
|
a large-model (far) function, the segment part of the return address
|
|
lives at \c{[BP+4]}, and the parameters begin at \c{[BP+6]}. The
|
|
leftmost parameter of the function, since it was pushed last, is
|
|
accessible at this offset from \c{BP}; the others follow, at
|
|
successively greater offsets. Thus, in a function such as \c{printf}
|
|
which takes a variable number of parameters, the pushing of the
|
|
parameters in reverse order means that the function knows where to
|
|
find its first parameter, which tells it the number and type of the
|
|
remaining ones.
|
|
|
|
\b The callee may also wish to decrease \c{SP} further, so as to
|
|
allocate space on the stack for local variables, which will then be
|
|
accessible at negative offsets from \c{BP}.
|
|
|
|
\b The callee, if it wishes to return a value to the caller, should
|
|
leave the value in \c{AL}, \c{AX} or \c{DX:AX} depending on the size
|
|
of the value. Floating-point results are sometimes (depending on the
|
|
compiler) returned in \c{ST0}.
|
|
|
|
\b Once the callee has finished processing, it restores \c{SP} from
|
|
\c{BP} if it had allocated local stack space, then pops the previous
|
|
value of \c{BP}, and returns via \c{RETN} or \c{RETF} depending on
|
|
memory model.
|
|
|
|
\b When the caller regains control from the callee, the function
|
|
parameters are still on the stack, so it typically adds an immediate
|
|
constant to \c{SP} to remove them (instead of executing a number of
|
|
slow \c{POP} instructions). Thus, if a function is accidentally
|
|
called with the wrong number of parameters due to a prototype
|
|
mismatch, the stack will still be returned to a sensible state since
|
|
the caller, which \e{knows} how many parameters it pushed, does the
|
|
removing.
|
|
|
|
It is instructive to compare this calling convention with that for
|
|
Pascal programs (described in \k{16bpfunc}). Pascal has a simpler
|
|
convention, since no functions have variable numbers of parameters.
|
|
Therefore the callee knows how many parameters it should have been
|
|
passed, and is able to deallocate them from the stack itself by
|
|
passing an immediate argument to the \c{RET} or \c{RETF}
|
|
instruction, so the caller does not have to do it. Also, the
|
|
parameters are pushed in left-to-right order, not right-to-left,
|
|
which means that a compiler can give better guarantees about
|
|
sequence points without performance suffering.
|
|
|
|
Thus, you would define a function in C style in the following way.
|
|
The following example is for small model:
|
|
|
|
\c global _myfunc
|
|
\c
|
|
\c _myfunc:
|
|
\c push bp
|
|
\c mov bp,sp
|
|
\c sub sp,0x40 ; 64 bytes of local stack space
|
|
\c mov bx,[bp+4] ; first parameter to function
|
|
\c
|
|
\c ; some more code
|
|
\c
|
|
\c mov sp,bp ; undo "sub sp,0x40" above
|
|
\c pop bp
|
|
\c ret
|
|
|
|
For a large-model function, you would replace \c{RET} by \c{RETF},
|
|
and look for the first parameter at \c{[BP+6]} instead of
|
|
\c{[BP+4]}. Of course, if one of the parameters is a pointer, then
|
|
the offsets of \e{subsequent} parameters will change depending on
|
|
the memory model as well: far pointers take up four bytes on the
|
|
stack when passed as a parameter, whereas near pointers take up two.
|
|
|
|
At the other end of the process, to call a C function from your
|
|
assembly code, you would do something like this:
|
|
|
|
\c extern _printf
|
|
\c
|
|
\c ; and then, further down...
|
|
\c
|
|
\c push word [myint] ; one of my integer variables
|
|
\c push word mystring ; pointer into my data segment
|
|
\c call _printf
|
|
\c add sp,byte 4 ; `byte' saves space
|
|
\c
|
|
\c ; then those data items...
|
|
\c
|
|
\c segment _DATA
|
|
\c
|
|
\c myint dw 1234
|
|
\c mystring db 'This number -> %d <- should be 1234',10,0
|
|
|
|
This piece of code is the small-model assembly equivalent of the C
|
|
code
|
|
|
|
\c int myint = 1234;
|
|
\c printf("This number -> %d <- should be 1234\n", myint);
|
|
|
|
In large model, the function-call code might look more like this. In
|
|
this example, it is assumed that \c{DS} already holds the segment
|
|
base of the segment \c{_DATA}. If not, you would have to initialize
|
|
it first.
|
|
|
|
\c push word [myint]
|
|
\c push word seg mystring ; Now push the segment, and...
|
|
\c push word mystring ; ... offset of "mystring"
|
|
\c call far _printf
|
|
\c add sp,byte 6
|
|
|
|
The integer value still takes up one word on the stack, since large
|
|
model does not affect the size of the \c{int} data type. The first
|
|
argument (pushed last) to \c{printf}, however, is a data pointer,
|
|
and therefore has to contain a segment and offset part. The segment
|
|
should be stored second in memory, and therefore must be pushed
|
|
first. (Of course, \c{PUSH DS} would have been a shorter instruction
|
|
than \c{PUSH WORD SEG mystring}, if \c{DS} was set up as the above
|
|
example assumed.) Then the actual call becomes a far call, since
|
|
functions expect far calls in large model; and \c{SP} has to be
|
|
increased by 6 rather than 4 afterwards to make up for the extra
|
|
word of parameters.
|
|
|
|
|
|
\S{16cdata} Accessing Data Items
|
|
|
|
To get at the contents of C variables, or to declare variables which
|
|
C can access, you need only declare the names as \c{GLOBAL} or
|
|
\c{EXTERN}. (Again, the names require leading underscores, as stated
|
|
in \k{16cunder}.) Thus, a C variable declared as \c{int i} can be
|
|
accessed from assembler as
|
|
|
|
\c extern _i
|
|
\c
|
|
\c mov ax,[_i]
|
|
|
|
And to declare your own integer variable which C programs can access
|
|
as \c{extern int j}, you do this (making sure you are assembling in
|
|
the \c{_DATA} segment, if necessary):
|
|
|
|
\c global _j
|
|
\c
|
|
\c _j dw 0
|
|
|
|
To access a C array, you need to know the size of the components of
|
|
the array. For example, \c{int} variables are two bytes long, so if
|
|
a C program declares an array as \c{int a[10]}, you can access
|
|
\c{a[3]} by coding \c{mov ax,[_a+6]}. (The byte offset 6 is obtained
|
|
by multiplying the desired array index, 3, by the size of the array
|
|
element, 2.) The sizes of the C base types in 16-bit compilers are:
|
|
1 for \c{char}, 2 for \c{short} and \c{int}, 4 for \c{long} and
|
|
\c{float}, and 8 for \c{double}.
|
|
|
|
To access a C \i{data structure}, you need to know the offset from
|
|
the base of the structure to the field you are interested in. You
|
|
can either do this by converting the C structure definition into a
|
|
NASM structure definition (using \i\c{STRUC}), or by calculating the
|
|
one offset and using just that.
|
|
|
|
To do either of these, you should read your C compiler's manual to
|
|
find out how it organizes data structures. NASM gives no special
|
|
alignment to structure members in its own \c{STRUC} macro, so you
|
|
have to specify alignment yourself if the C compiler generates it.
|
|
Typically, you might find that a structure like
|
|
|
|
\c struct {
|
|
\c char c;
|
|
\c int i;
|
|
\c } foo;
|
|
|
|
might be four bytes long rather than three, since the \c{int} field
|
|
would be aligned to a two-byte boundary. However, this sort of
|
|
feature tends to be a configurable option in the C compiler, either
|
|
using command-line options or \c{#pragma} lines, so you have to find
|
|
out how your own compiler does it.
|
|
|
|
|
|
\S{16cmacro} \i\c{c16.mac}: Helper Macros for the 16-bit C Interface
|
|
|
|
Included in the NASM archives, in the \I{misc subdirectory}\c{misc}
|
|
directory, is a file \c{c16.mac} of macros. It defines three macros:
|
|
\i\c{proc}, \i\c{arg} and \i\c{endproc}. These are intended to be
|
|
used for C-style procedure definitions, and they automate a lot of
|
|
the work involved in keeping track of the calling convention.
|
|
|
|
(An alternative, TASM compatible form of \c{arg} is also now built
|
|
into NASM's preprocessor. See \k{stackrel} for details.)
|
|
|
|
An example of an assembly function using the macro set is given
|
|
here:
|
|
|
|
\c proc _nearproc
|
|
\c
|
|
\c %$i arg
|
|
\c %$j arg
|
|
\c mov ax,[bp + %$i]
|
|
\c mov bx,[bp + %$j]
|
|
\c add ax,[bx]
|
|
\c
|
|
\c endproc
|
|
|
|
This defines \c{_nearproc} to be a procedure taking two arguments,
|
|
the first (\c{i}) an integer and the second (\c{j}) a pointer to an
|
|
integer. It returns \c{i + *j}.
|
|
|
|
Note that the \c{arg} macro has an \c{EQU} as the first line of its
|
|
expansion, and since the label before the macro call gets prepended
|
|
to the first line of the expanded macro, the \c{EQU} works, defining
|
|
\c{%$i} to be an offset from \c{BP}. A context-local variable is
|
|
used, local to the context pushed by the \c{proc} macro and popped
|
|
by the \c{endproc} macro, so that the same argument name can be used
|
|
in later procedures. Of course, you don't \e{have} to do that.
|
|
|
|
The macro set produces code for near functions (tiny, small and
|
|
compact-model code) by default. You can have it generate far
|
|
functions (medium, large and huge-model code) by means of coding
|
|
\I\c{FARCODE}\c{%define FARCODE}. This changes the kind of return
|
|
instruction generated by \c{endproc}, and also changes the starting
|
|
point for the argument offsets. The macro set contains no intrinsic
|
|
dependency on whether data pointers are far or not.
|
|
|
|
\c{arg} can take an optional parameter, giving the size of the
|
|
argument. If no size is given, 2 is assumed, since it is likely that
|
|
many function parameters will be of type \c{int}.
|
|
|
|
The large-model equivalent of the above function would look like this:
|
|
|
|
\c %define FARCODE
|
|
\c
|
|
\c proc _farproc
|
|
\c
|
|
\c %$i arg
|
|
\c %$j arg 4
|
|
\c mov ax,[bp + %$i]
|
|
\c mov bx,[bp + %$j]
|
|
\c mov es,[bp + %$j + 2]
|
|
\c add ax,[bx]
|
|
\c
|
|
\c endproc
|
|
|
|
This makes use of the argument to the \c{arg} macro to define a
|
|
parameter of size 4, because \c{j} is now a far pointer. When we
|
|
load from \c{j}, we must load a segment and an offset.
|
|
|
|
|
|
\H{16bp} Interfacing to \i{Borland Pascal} Programs
|
|
|
|
Interfacing to Borland Pascal programs is similar in concept to
|
|
interfacing to 16-bit C programs. The differences are:
|
|
|
|
\b The leading underscore required for interfacing to C programs is
|
|
not required for Pascal.
|
|
|
|
\b The memory model is always large: functions are far, data
|
|
pointers are far, and no data item can be more than 64K long.
|
|
(Actually, some functions are near, but only those functions that
|
|
are local to a Pascal unit and never called from outside it. All
|
|
assembly functions that Pascal calls, and all Pascal functions that
|
|
assembly routines are able to call, are far.) However, all static
|
|
data declared in a Pascal program goes into the default data
|
|
segment, which is the one whose segment address will be in \c{DS}
|
|
when control is passed to your assembly code. The only things that
|
|
do not live in the default data segment are local variables (they
|
|
live in the stack segment) and dynamically allocated variables. All
|
|
data \e{pointers}, however, are far.
|
|
|
|
\b The function calling convention is different - described below.
|
|
|
|
\b Some data types, such as strings, are stored differently.
|
|
|
|
\b There are restrictions on the segment names you are allowed to
|
|
use - Borland Pascal will ignore code or data declared in a segment
|
|
it doesn't like the name of. The restrictions are described below.
|
|
|
|
|
|
\S{16bpfunc} The Pascal Calling Convention
|
|
|
|
\I{functions, Pascal calling convention}\I{Pascal calling
|
|
convention}The 16-bit Pascal calling convention is as follows. In
|
|
the following description, the words \e{caller} and \e{callee} are
|
|
used to denote the function doing the calling and the function which
|
|
gets called.
|
|
|
|
\b The caller pushes the function's parameters on the stack, one
|
|
after another, in normal order (left to right, so that the first
|
|
argument specified to the function is pushed first).
|
|
|
|
\b The caller then executes a far \c{CALL} instruction to pass
|
|
control to the callee.
|
|
|
|
\b The callee receives control, and typically (although this is not
|
|
actually necessary, in functions which do not need to access their
|
|
parameters) starts by saving the value of \c{SP} in \c{BP} so as to
|
|
be able to use \c{BP} as a base pointer to find its parameters on
|
|
the stack. However, the caller was probably doing this too, so part
|
|
of the calling convention states that \c{BP} must be preserved by
|
|
any function. Hence the callee, if it is going to set up \c{BP} as a
|
|
\i{frame pointer}, must push the previous value first.
|
|
|
|
\b The callee may then access its parameters relative to \c{BP}.
|
|
The word at \c{[BP]} holds the previous value of \c{BP} as it was
|
|
pushed. The next word, at \c{[BP+2]}, holds the offset part of the
|
|
return address, and the next one at \c{[BP+4]} the segment part. The
|
|
parameters begin at \c{[BP+6]}. The rightmost parameter of the
|
|
function, since it was pushed last, is accessible at this offset
|
|
from \c{BP}; the others follow, at successively greater offsets.
|
|
|
|
\b The callee may also wish to decrease \c{SP} further, so as to
|
|
allocate space on the stack for local variables, which will then be
|
|
accessible at negative offsets from \c{BP}.
|
|
|
|
\b The callee, if it wishes to return a value to the caller, should
|
|
leave the value in \c{AL}, \c{AX} or \c{DX:AX} depending on the size
|
|
of the value. Floating-point results are returned in \c{ST0}.
|
|
Results of type \c{Real} (Borland's own custom floating-point data
|
|
type, not handled directly by the FPU) are returned in \c{DX:BX:AX}.
|
|
To return a result of type \c{String}, the caller pushes a pointer
|
|
to a temporary string before pushing the parameters, and the callee
|
|
places the returned string value at that location. The pointer is
|
|
not a parameter, and should not be removed from the stack by the
|
|
\c{RETF} instruction.
|
|
|
|
\b Once the callee has finished processing, it restores \c{SP} from
|
|
\c{BP} if it had allocated local stack space, then pops the previous
|
|
value of \c{BP}, and returns via \c{RETF}. It uses the form of
|
|
\c{RETF} with an immediate parameter, giving the number of bytes
|
|
taken up by the parameters on the stack. This causes the parameters
|
|
to be removed from the stack as a side effect of the return
|
|
instruction.
|
|
|
|
\b When the caller regains control from the callee, the function
|
|
parameters have already been removed from the stack, so it needs to
|
|
do nothing further.
|
|
|
|
Thus, you would define a function in Pascal style, taking two
|
|
\c{Integer}-type parameters, in the following way:
|
|
|
|
\c global myfunc
|
|
\c
|
|
\c myfunc: push bp
|
|
\c mov bp,sp
|
|
\c sub sp,0x40 ; 64 bytes of local stack space
|
|
\c mov bx,[bp+8] ; first parameter to function
|
|
\c mov bx,[bp+6] ; second parameter to function
|
|
\c
|
|
\c ; some more code
|
|
\c
|
|
\c mov sp,bp ; undo "sub sp,0x40" above
|
|
\c pop bp
|
|
\c retf 4 ; total size of params is 4
|
|
|
|
At the other end of the process, to call a Pascal function from your
|
|
assembly code, you would do something like this:
|
|
|
|
\c extern SomeFunc
|
|
\c
|
|
\c ; and then, further down...
|
|
\c
|
|
\c push word seg mystring ; Now push the segment, and...
|
|
\c push word mystring ; ... offset of "mystring"
|
|
\c push word [myint] ; one of my variables
|
|
\c call far SomeFunc
|
|
|
|
This is equivalent to the Pascal code
|
|
|
|
\c procedure SomeFunc(String: PChar; Int: Integer);
|
|
\c SomeFunc(@mystring, myint);
|
|
|
|
|
|
\S{16bpseg} Borland Pascal \I{segment names, Borland Pascal}Segment
|
|
Name Restrictions
|
|
|
|
Since Borland Pascal's internal unit file format is completely
|
|
different from \c{OBJ}, it only makes a very sketchy job of actually
|
|
reading and understanding the various information contained in a
|
|
real \c{OBJ} file when it links that in. Therefore an object file
|
|
intended to be linked to a Pascal program must obey a number of
|
|
restrictions:
|
|
|
|
\b Procedures and functions must be in a segment whose name is
|
|
either \c{CODE}, \c{CSEG}, or something ending in \c{_TEXT}.
|
|
|
|
\b initialized data must be in a segment whose name is either
|
|
\c{CONST} or something ending in \c{_DATA}.
|
|
|
|
\b Uninitialized data must be in a segment whose name is either
|
|
\c{DATA}, \c{DSEG}, or something ending in \c{_BSS}.
|
|
|
|
\b Any other segments in the object file are completely ignored.
|
|
\c{GROUP} directives and segment attributes are also ignored.
|
|
|
|
|
|
\S{16bpmacro} Using \i\c{c16.mac} With Pascal Programs
|
|
|
|
The \c{c16.mac} macro package, described in \k{16cmacro}, can also
|
|
be used to simplify writing functions to be called from Pascal
|
|
programs, if you code \I\c{PASCAL}\c{%define PASCAL}. This
|
|
definition ensures that functions are far (it implies
|
|
\i\c{FARCODE}), and also causes procedure return instructions to be
|
|
generated with an operand.
|
|
|
|
Defining \c{PASCAL} does not change the code which calculates the
|
|
argument offsets; you must declare your function's arguments in
|
|
reverse order. For example:
|
|
|
|
\c %define PASCAL
|
|
\c
|
|
\c proc _pascalproc
|
|
\c
|
|
\c %$j arg 4
|
|
\c %$i arg
|
|
\c mov ax,[bp + %$i]
|
|
\c mov bx,[bp + %$j]
|
|
\c mov es,[bp + %$j + 2]
|
|
\c add ax,[bx]
|
|
\c
|
|
\c endproc
|
|
|
|
This defines the same routine, conceptually, as the example in
|
|
\k{16cmacro}: it defines a function taking two arguments, an integer
|
|
and a pointer to an integer, which returns the sum of the integer
|
|
and the contents of the pointer. The only difference between this
|
|
code and the large-model C version is that \c{PASCAL} is defined
|
|
instead of \c{FARCODE}, and that the arguments are declared in
|
|
reverse order.
|
|
|
|
|
|
\C{32bit} Writing 32-bit Code (Unix, Win32, DJGPP)
|
|
|
|
This chapter attempts to cover some of the common issues involved
|
|
when writing 32-bit code, to run under \i{Win32} or Unix, or to be
|
|
linked with C code generated by a Unix-style C compiler such as
|
|
\i{DJGPP}. It covers how to write assembly code to interface with
|
|
32-bit C routines, and how to write position-independent code for
|
|
shared libraries.
|
|
|
|
Almost all 32-bit code, and in particular all code running under
|
|
\c{Win32}, \c{DJGPP} or any of the PC Unix variants, runs in \I{flat
|
|
memory model}\e{flat} memory model. This means that the segment registers
|
|
and paging have already been set up to give you the same 32-bit 4Gb
|
|
address space no matter what segment you work relative to, and that
|
|
you should ignore all segment registers completely. When writing
|
|
flat-model application code, you never need to use a segment
|
|
override or modify any segment register, and the code-section
|
|
addresses you pass to \c{CALL} and \c{JMP} live in the same address
|
|
space as the data-section addresses you access your variables by and
|
|
the stack-section addresses you access local variables and procedure
|
|
parameters by. Every address is 32 bits long and contains only an
|
|
offset part.
|
|
|
|
|
|
\H{32c} Interfacing to 32-bit C Programs
|
|
|
|
A lot of the discussion in \k{16c}, about interfacing to 16-bit C
|
|
programs, still applies when working in 32 bits. The absence of
|
|
memory models or segmentation worries simplifies things a lot.
|
|
|
|
|
|
\S{32cunder} External Symbol Names
|
|
|
|
Most 32-bit C compilers share the convention used by 16-bit
|
|
compilers, that the names of all global symbols (functions or data)
|
|
they define are formed by prefixing an underscore to the name as it
|
|
appears in the C program. However, not all of them do: the \c{ELF}
|
|
specification states that C symbols do \e{not} have a leading
|
|
underscore on their assembly-language names.
|
|
|
|
The older Linux \c{a.out} C compiler, all \c{Win32} compilers,
|
|
\c{DJGPP}, and \c{NetBSD} and \c{FreeBSD}, all use the leading
|
|
underscore; for these compilers, the macros \c{cextern} and
|
|
\c{cglobal}, as given in \k{16cunder}, will still work. For \c{ELF},
|
|
though, the leading underscore should not be used.
|
|
|
|
See also \k{opt-pfix}.
|
|
|
|
\S{32cfunc} Function Definitions and Function Calls
|
|
|
|
\I{functions, C calling convention}The \i{C calling convention}
|
|
in 32-bit programs is as follows. In the following description,
|
|
the words \e{caller} and \e{callee} are used to denote
|
|
the function doing the calling and the function which gets called.
|
|
|
|
\b The caller pushes the function's parameters on the stack, one
|
|
after another, in reverse order (right to left, so that the first
|
|
argument specified to the function is pushed last).
|
|
|
|
\b The caller then executes a near \c{CALL} instruction to pass
|
|
control to the callee.
|
|
|
|
\b The callee receives control, and typically (although this is not
|
|
actually necessary, in functions which do not need to access their
|
|
parameters) starts by saving the value of \c{ESP} in \c{EBP} so as
|
|
to be able to use \c{EBP} as a base pointer to find its parameters
|
|
on the stack. However, the caller was probably doing this too, so
|
|
part of the calling convention states that \c{EBP} must be preserved
|
|
by any C function. Hence the callee, if it is going to set up
|
|
\c{EBP} as a \i{frame pointer}, must push the previous value first.
|
|
|
|
\b The callee may then access its parameters relative to \c{EBP}.
|
|
The doubleword at \c{[EBP]} holds the previous value of \c{EBP} as
|
|
it was pushed; the next doubleword, at \c{[EBP+4]}, holds the return
|
|
address, pushed implicitly by \c{CALL}. The parameters start after
|
|
that, at \c{[EBP+8]}. The leftmost parameter of the function, since
|
|
it was pushed last, is accessible at this offset from \c{EBP}; the
|
|
others follow, at successively greater offsets. Thus, in a function
|
|
such as \c{printf} which takes a variable number of parameters, the
|
|
pushing of the parameters in reverse order means that the function
|
|
knows where to find its first parameter, which tells it the number
|
|
and type of the remaining ones.
|
|
|
|
\b The callee may also wish to decrease \c{ESP} further, so as to
|
|
allocate space on the stack for local variables, which will then be
|
|
accessible at negative offsets from \c{EBP}.
|
|
|
|
\b The callee, if it wishes to return a value to the caller, should
|
|
leave the value in \c{AL}, \c{AX} or \c{EAX} depending on the size
|
|
of the value. Floating-point results are typically returned in
|
|
\c{ST0}.
|
|
|
|
\b Once the callee has finished processing, it restores \c{ESP} from
|
|
\c{EBP} if it had allocated local stack space, then pops the previous
|
|
value of \c{EBP}, and returns via \c{RET} (equivalently, \c{RETN}).
|
|
|
|
\b When the caller regains control from the callee, the function
|
|
parameters are still on the stack, so it typically adds an immediate
|
|
constant to \c{ESP} to remove them (instead of executing a number of
|
|
slow \c{POP} instructions). Thus, if a function is accidentally
|
|
called with the wrong number of parameters due to a prototype
|
|
mismatch, the stack will still be returned to a sensible state since
|
|
the caller, which \e{knows} how many parameters it pushed, does the
|
|
removing.
|
|
|
|
There is an alternative calling convention used by Win32 programs
|
|
for Windows API calls, and also for functions called \e{by} the
|
|
Windows API such as window procedures: they follow what Microsoft
|
|
calls the \c{__stdcall} convention. This is slightly closer to the
|
|
Pascal convention, in that the callee clears the stack by passing a
|
|
parameter to the \c{RET} instruction. However, the parameters are
|
|
still pushed in right-to-left order.
|
|
|
|
Thus, you would define a function in C style in the following way:
|
|
|
|
\c global _myfunc
|
|
\c
|
|
\c _myfunc:
|
|
\c push ebp
|
|
\c mov ebp,esp
|
|
\c sub esp,0x40 ; 64 bytes of local stack space
|
|
\c mov ebx,[ebp+8] ; first parameter to function
|
|
\c
|
|
\c ; some more code
|
|
\c
|
|
\c leave ; mov esp,ebp / pop ebp
|
|
\c ret
|
|
|
|
At the other end of the process, to call a C function from your
|
|
assembly code, you would do something like this:
|
|
|
|
\c extern _printf
|
|
\c
|
|
\c ; and then, further down...
|
|
\c
|
|
\c push dword [myint] ; one of my integer variables
|
|
\c push dword mystring ; pointer into my data segment
|
|
\c call _printf
|
|
\c add esp,byte 8 ; `byte' saves space
|
|
\c
|
|
\c ; then those data items...
|
|
\c
|
|
\c segment _DATA
|
|
\c
|
|
\c myint dd 1234
|
|
\c mystring db 'This number -> %d <- should be 1234',10,0
|
|
|
|
This piece of code is the assembly equivalent of the C code
|
|
|
|
\c int myint = 1234;
|
|
\c printf("This number -> %d <- should be 1234\n", myint);
|
|
|
|
|
|
\S{32cdata} Accessing Data Items
|
|
|
|
To get at the contents of C variables, or to declare variables which
|
|
C can access, you need only declare the names as \c{GLOBAL} or
|
|
\c{EXTERN}. (Again, the names require leading underscores, as stated
|
|
in \k{32cunder}.) Thus, a C variable declared as \c{int i} can be
|
|
accessed from assembler as
|
|
|
|
\c extern _i
|
|
\c mov eax,[_i]
|
|
|
|
And to declare your own integer variable which C programs can access
|
|
as \c{extern int j}, you do this (making sure you are assembling in
|
|
the \c{_DATA} segment, if necessary):
|
|
|
|
\c global _j
|
|
\c _j dd 0
|
|
|
|
To access a C array, you need to know the size of the components of
|
|
the array. For example, \c{int} variables are four bytes long, so if
|
|
a C program declares an array as \c{int a[10]}, you can access
|
|
\c{a[3]} by coding \c{mov ax,[_a+12]}. (The byte offset 12 is obtained
|
|
by multiplying the desired array index, 3, by the size of the array
|
|
element, 4.) The sizes of the C base types in 32-bit compilers are:
|
|
1 for \c{char}, 2 for \c{short}, 4 for \c{int}, \c{long} and
|
|
\c{float}, and 8 for \c{double}. Pointers, being 32-bit addresses,
|
|
are also 4 bytes long.
|
|
|
|
To access a C \i{data structure}, you need to know the offset from
|
|
the base of the structure to the field you are interested in. You
|
|
can either do this by converting the C structure definition into a
|
|
NASM structure definition (using \c{STRUC}), or by calculating the
|
|
one offset and using just that.
|
|
|
|
To do either of these, you should read your C compiler's manual to
|
|
find out how it organizes data structures. NASM gives no special
|
|
alignment to structure members in its own \i\c{STRUC} macro, so you
|
|
have to specify alignment yourself if the C compiler generates it.
|
|
Typically, you might find that a structure like
|
|
|
|
\c struct {
|
|
\c char c;
|
|
\c int i;
|
|
\c } foo;
|
|
|
|
might be eight bytes long rather than five, since the \c{int} field
|
|
would be aligned to a four-byte boundary. However, this sort of
|
|
feature is sometimes a configurable option in the C compiler, either
|
|
using command-line options or \c{#pragma} lines, so you have to find
|
|
out how your own compiler does it.
|
|
|
|
|
|
\S{32cmacro} \i\c{c32.mac}: Helper Macros for the 32-bit C Interface
|
|
|
|
Included in the NASM archives, in the \I{misc directory}\c{misc}
|
|
directory, is a file \c{c32.mac} of macros. It defines three macros:
|
|
\i\c{proc}, \i\c{arg} and \i\c{endproc}. These are intended to be
|
|
used for C-style procedure definitions, and they automate a lot of
|
|
the work involved in keeping track of the calling convention.
|
|
|
|
An example of an assembly function using the macro set is given
|
|
here:
|
|
|
|
\c proc _proc32
|
|
\c
|
|
\c %$i arg
|
|
\c %$j arg
|
|
\c mov eax,[ebp + %$i]
|
|
\c mov ebx,[ebp + %$j]
|
|
\c add eax,[ebx]
|
|
\c
|
|
\c endproc
|
|
|
|
This defines \c{_proc32} to be a procedure taking two arguments, the
|
|
first (\c{i}) an integer and the second (\c{j}) a pointer to an
|
|
integer. It returns \c{i + *j}.
|
|
|
|
Note that the \c{arg} macro has an \c{EQU} as the first line of its
|
|
expansion, and since the label before the macro call gets prepended
|
|
to the first line of the expanded macro, the \c{EQU} works, defining
|
|
\c{%$i} to be an offset from \c{BP}. A context-local variable is
|
|
used, local to the context pushed by the \c{proc} macro and popped
|
|
by the \c{endproc} macro, so that the same argument name can be used
|
|
in later procedures. Of course, you don't \e{have} to do that.
|
|
|
|
\c{arg} can take an optional parameter, giving the size of the
|
|
argument. If no size is given, 4 is assumed, since it is likely that
|
|
many function parameters will be of type \c{int} or pointers.
|
|
|
|
|
|
\H{picdll} Writing NetBSD/FreeBSD/OpenBSD and Linux/ELF \i{Shared
|
|
Libraries}
|
|
|
|
\c{ELF} replaced the older \c{a.out} object file format under Linux
|
|
because it contains support for \i{position-independent code}
|
|
(\i{PIC}), which makes writing shared libraries much easier. NASM
|
|
supports the \c{ELF} position-independent code features, so you can
|
|
write Linux \c{ELF} shared libraries in NASM.
|
|
|
|
\i{NetBSD}, and its close cousins \i{FreeBSD} and \i{OpenBSD}, take
|
|
a different approach by hacking PIC support into the \c{a.out}
|
|
format. NASM supports this as the \i\c{aoutb} output format, so you
|
|
can write \i{BSD} shared libraries in NASM too.
|
|
|
|
The operating system loads a PIC shared library by memory-mapping
|
|
the library file at an arbitrarily chosen point in the address space
|
|
of the running process. The contents of the library's code section
|
|
must therefore not depend on where it is loaded in memory.
|
|
|
|
Therefore, you cannot get at your variables by writing code like
|
|
this:
|
|
|
|
\c mov eax,[myvar] ; WRONG
|
|
|
|
Instead, the linker provides an area of memory called the
|
|
\i\e{global offset table}, or \i{GOT}; the GOT is situated at a
|
|
constant distance from your library's code, so if you can find out
|
|
where your library is loaded (which is typically done using a
|
|
\c{CALL} and \c{POP} combination), you can obtain the address of the
|
|
GOT, and you can then load the addresses of your variables out of
|
|
linker-generated entries in the GOT.
|
|
|
|
The \e{data} section of a PIC shared library does not have these
|
|
restrictions: since the data section is writable, it has to be
|
|
copied into memory anyway rather than just paged in from the library
|
|
file, so as long as it's being copied it can be relocated too. So
|
|
you can put ordinary types of relocation in the data section without
|
|
too much worry (but see \k{picglobal} for a caveat).
|
|
|
|
|
|
\S{picgot} Obtaining the Address of the GOT
|
|
|
|
Each code module in your shared library should define the GOT as an
|
|
external symbol:
|
|
|
|
\c extern _GLOBAL_OFFSET_TABLE_ ; in ELF
|
|
\c extern __GLOBAL_OFFSET_TABLE_ ; in BSD a.out
|
|
|
|
At the beginning of any function in your shared library which plans
|
|
to access your data or BSS sections, you must first calculate the
|
|
address of the GOT. This is typically done by writing the function
|
|
in this form:
|
|
|
|
\c func: push ebp
|
|
\c mov ebp,esp
|
|
\c push ebx
|
|
\c call .get_GOT
|
|
\c .get_GOT:
|
|
\c pop ebx
|
|
\c add ebx,_GLOBAL_OFFSET_TABLE_+$$-.get_GOT wrt ..gotpc
|
|
\c
|
|
\c ; the function body comes here
|
|
\c
|
|
\c mov ebx,[ebp-4]
|
|
\c mov esp,ebp
|
|
\c pop ebp
|
|
\c ret
|
|
|
|
(For BSD, again, the symbol \c{_GLOBAL_OFFSET_TABLE} requires a
|
|
second leading underscore.)
|
|
|
|
The first two lines of this function are simply the standard C
|
|
prologue to set up a stack frame, and the last three lines are
|
|
standard C function epilogue. The third line, and the fourth to last
|
|
line, save and restore the \c{EBX} register, because PIC shared
|
|
libraries use this register to store the address of the GOT.
|
|
|
|
The interesting bit is the \c{CALL} instruction and the following
|
|
two lines. The \c{CALL} and \c{POP} combination obtains the address
|
|
of the label \c{.get_GOT}, without having to know in advance where
|
|
the program was loaded (since the \c{CALL} instruction is encoded
|
|
relative to the current position). The \c{ADD} instruction makes use
|
|
of one of the special PIC relocation types: \i{GOTPC relocation}.
|
|
With the \i\c{WRT ..gotpc} qualifier specified, the symbol
|
|
referenced (here \c{_GLOBAL_OFFSET_TABLE_}, the special symbol
|
|
assigned to the GOT) is given as an offset from the beginning of the
|
|
section. (Actually, \c{ELF} encodes it as the offset from the operand
|
|
field of the \c{ADD} instruction, but NASM simplifies this
|
|
deliberately, so you do things the same way for both \c{ELF} and
|
|
\c{BSD}.) So the instruction then \e{adds} the beginning of the section,
|
|
to get the real address of the GOT, and subtracts the value of
|
|
\c{.get_GOT} which it knows is in \c{EBX}. Therefore, by the time
|
|
that instruction has finished, \c{EBX} contains the address of the GOT.
|
|
|
|
If you didn't follow that, don't worry: it's never necessary to
|
|
obtain the address of the GOT by any other means, so you can put
|
|
those three instructions into a macro and safely ignore them:
|
|
|
|
\c %macro get_GOT 0
|
|
\c
|
|
\c call %%getgot
|
|
\c %%getgot:
|
|
\c pop ebx
|
|
\c add ebx,_GLOBAL_OFFSET_TABLE_+$$-%%getgot wrt ..gotpc
|
|
\c
|
|
\c %endmacro
|
|
|
|
\S{piclocal} Finding Your Local Data Items
|
|
|
|
Having got the GOT, you can then use it to obtain the addresses of
|
|
your data items. Most variables will reside in the sections you have
|
|
declared; they can be accessed using the \I{GOTOFF
|
|
relocation}\c{..gotoff} special \I\c{WRT ..gotoff}\c{WRT} type. The
|
|
way this works is like this:
|
|
|
|
\c lea eax,[ebx+myvar wrt ..gotoff]
|
|
|
|
The expression \c{myvar wrt ..gotoff} is calculated, when the shared
|
|
library is linked, to be the offset to the local variable \c{myvar}
|
|
from the beginning of the GOT. Therefore, adding it to \c{EBX} as
|
|
above will place the real address of \c{myvar} in \c{EAX}.
|
|
|
|
If you declare variables as \c{GLOBAL} without specifying a size for
|
|
them, they are shared between code modules in the library, but do
|
|
not get exported from the library to the program that loaded it.
|
|
They will still be in your ordinary data and BSS sections, so you
|
|
can access them in the same way as local variables, using the above
|
|
\c{..gotoff} mechanism.
|
|
|
|
Note that due to a peculiarity of the way BSD \c{a.out} format
|
|
handles this relocation type, there must be at least one non-local
|
|
symbol in the same section as the address you're trying to access.
|
|
|
|
|
|
\S{picextern} Finding External and Common Data Items
|
|
|
|
If your library needs to get at an external variable (external to
|
|
the \e{library}, not just to one of the modules within it), you must
|
|
use the \I{GOT relocations}\I\c{WRT ..got}\c{..got} type to get at
|
|
it. The \c{..got} type, instead of giving you the offset from the
|
|
GOT base to the variable, gives you the offset from the GOT base to
|
|
a GOT \e{entry} containing the address of the variable. The linker
|
|
will set up this GOT entry when it builds the library, and the
|
|
dynamic linker will place the correct address in it at load time. So
|
|
to obtain the address of an external variable \c{extvar} in \c{EAX},
|
|
you would code
|
|
|
|
\c mov eax,[ebx+extvar wrt ..got]
|
|
|
|
This loads the address of \c{extvar} out of an entry in the GOT. The
|
|
linker, when it builds the shared library, collects together every
|
|
relocation of type \c{..got}, and builds the GOT so as to ensure it
|
|
has every necessary entry present.
|
|
|
|
Common variables must also be accessed in this way.
|
|
|
|
|
|
\S{picglobal} Exporting Symbols to the Library User
|
|
|
|
If you want to export symbols to the user of the library, you have
|
|
to declare whether they are functions or data, and if they are data,
|
|
you have to give the size of the data item. This is because the
|
|
dynamic linker has to build \I{PLT}\i{procedure linkage table}
|
|
entries for any exported functions, and also moves exported data
|
|
items away from the library's data section in which they were
|
|
declared.
|
|
|
|
So to export a function to users of the library, you must use
|
|
|
|
\c global func:function ; declare it as a function
|
|
\c
|
|
\c func: push ebp
|
|
\c
|
|
\c ; etc.
|
|
|
|
And to export a data item such as an array, you would have to code
|
|
|
|
\c global array:data array.end-array ; give the size too
|
|
\c
|
|
\c array: resd 128
|
|
\c .end:
|
|
|
|
Be careful: If you export a variable to the library user, by
|
|
declaring it as \c{GLOBAL} and supplying a size, the variable will
|
|
end up living in the data section of the main program, rather than
|
|
in your library's data section, where you declared it. So you will
|
|
have to access your own global variable with the \c{..got} mechanism
|
|
rather than \c{..gotoff}, as if it were external (which,
|
|
effectively, it has become).
|
|
|
|
Equally, if you need to store the address of an exported global in
|
|
one of your data sections, you can't do it by means of the standard
|
|
sort of code:
|
|
|
|
\c dataptr: dd global_data_item ; WRONG
|
|
|
|
NASM will interpret this code as an ordinary relocation, in which
|
|
\c{global_data_item} is merely an offset from the beginning of the
|
|
\c{.data} section (or whatever); so this reference will end up
|
|
pointing at your data section instead of at the exported global
|
|
which resides elsewhere.
|
|
|
|
Instead of the above code, then, you must write
|
|
|
|
\c dataptr: dd global_data_item wrt ..sym
|
|
|
|
which makes use of the special \c{WRT} type \I\c{WRT ..sym}\c{..sym}
|
|
to instruct NASM to search the symbol table for a particular symbol
|
|
at that address, rather than just relocating by section base.
|
|
|
|
Either method will work for functions: referring to one of your
|
|
functions by means of
|
|
|
|
\c funcptr: dd my_function
|
|
|
|
will give the user the address of the code you wrote, whereas
|
|
|
|
\c funcptr: dd my_function wrt .sym
|
|
|
|
will give the address of the procedure linkage table for the
|
|
function, which is where the calling program will \e{believe} the
|
|
function lives. Either address is a valid way to call the function.
|
|
|
|
|
|
\S{picproc} Calling Procedures Outside the Library
|
|
|
|
Calling procedures outside your shared library has to be done by
|
|
means of a \i\e{procedure linkage table}, or \i{PLT}. The PLT is
|
|
placed at a known offset from where the library is loaded, so the
|
|
library code can make calls to the PLT in a position-independent
|
|
way. Within the PLT there is code to jump to offsets contained in
|
|
the GOT, so function calls to other shared libraries or to routines
|
|
in the main program can be transparently passed off to their real
|
|
destinations.
|
|
|
|
To call an external routine, you must use another special PIC
|
|
relocation type, \I{PLT relocations}\i\c{WRT ..plt}. This is much
|
|
easier than the GOT-based ones: you simply replace calls such as
|
|
\c{CALL printf} with the PLT-relative version \c{CALL printf WRT
|
|
..plt}.
|
|
|
|
|
|
\S{link} Generating the Library File
|
|
|
|
Having written some code modules and assembled them to \c{.o} files,
|
|
you then generate your shared library with a command such as
|
|
|
|
\c ld -shared -o library.so module1.o module2.o # for ELF
|
|
\c ld -Bshareable -o library.so module1.o module2.o # for BSD
|
|
|
|
For ELF, if your shared library is going to reside in system
|
|
directories such as \c{/usr/lib} or \c{/lib}, it is usually worth
|
|
using the \i\c{-soname} flag to the linker, to store the final
|
|
library file name, with a version number, into the library:
|
|
|
|
\c ld -shared -soname library.so.1 -o library.so.1.2 *.o
|
|
|
|
You would then copy \c{library.so.1.2} into the library directory,
|
|
and create \c{library.so.1} as a symbolic link to it.
|
|
|
|
|
|
\C{mixsize} Mixing 16 and 32 Bit Code
|
|
|
|
This chapter tries to cover some of the issues, largely related to
|
|
unusual forms of addressing and jump instructions, encountered when
|
|
writing operating system code such as protected-mode initialisation
|
|
routines, which require code that operates in mixed segment sizes,
|
|
such as code in a 16-bit segment trying to modify data in a 32-bit
|
|
one, or jumps between different-size segments.
|
|
|
|
|
|
\H{mixjump} Mixed-Size Jumps\I{jumps, mixed-size}
|
|
|
|
\I{operating system, writing}\I{writing operating systems}The most
|
|
common form of \i{mixed-size instruction} is the one used when
|
|
writing a 32-bit OS: having done your setup in 16-bit mode, such as
|
|
loading the kernel, you then have to boot it by switching into
|
|
protected mode and jumping to the 32-bit kernel start address. In a
|
|
fully 32-bit OS, this tends to be the \e{only} mixed-size
|
|
instruction you need, since everything before it can be done in pure
|
|
16-bit code, and everything after it can be pure 32-bit.
|
|
|
|
This jump must specify a 48-bit far address, since the target
|
|
segment is a 32-bit one. However, it must be assembled in a 16-bit
|
|
segment, so just coding, for example,
|
|
|
|
\c jmp 0x1234:0x56789ABC ; wrong!
|
|
|
|
will not work, since the offset part of the address will be
|
|
truncated to \c{0x9ABC} and the jump will be an ordinary 16-bit far
|
|
one.
|
|
|
|
The Linux kernel setup code gets round the inability of \c{as86} to
|
|
generate the required instruction by coding it manually, using
|
|
\c{DB} instructions. NASM can go one better than that, by actually
|
|
generating the right instruction itself. Here's how to do it right:
|
|
|
|
\c jmp dword 0x1234:0x56789ABC ; right
|
|
|
|
\I\c{JMP DWORD}The \c{DWORD} prefix (strictly speaking, it should
|
|
come \e{after} the colon, since it is declaring the \e{offset} field
|
|
to be a doubleword; but NASM will accept either form, since both are
|
|
unambiguous) forces the offset part to be treated as far, in the
|
|
assumption that you are deliberately writing a jump from a 16-bit
|
|
segment to a 32-bit one.
|
|
|
|
You can do the reverse operation, jumping from a 32-bit segment to a
|
|
16-bit one, by means of the \c{WORD} prefix:
|
|
|
|
\c jmp word 0x8765:0x4321 ; 32 to 16 bit
|
|
|
|
If the \c{WORD} prefix is specified in 16-bit mode, or the \c{DWORD}
|
|
prefix in 32-bit mode, they will be ignored, since each is
|
|
explicitly forcing NASM into a mode it was in anyway.
|
|
|
|
|
|
\H{mixaddr} Addressing Between Different-Size Segments\I{addressing,
|
|
mixed-size}\I{mixed-size addressing}
|
|
|
|
If your OS is mixed 16 and 32-bit, or if you are writing a DOS
|
|
extender, you are likely to have to deal with some 16-bit segments
|
|
and some 32-bit ones. At some point, you will probably end up
|
|
writing code in a 16-bit segment which has to access data in a
|
|
32-bit segment, or vice versa.
|
|
|
|
If the data you are trying to access in a 32-bit segment lies within
|
|
the first 64K of the segment, you may be able to get away with using
|
|
an ordinary 16-bit addressing operation for the purpose; but sooner
|
|
or later, you will want to do 32-bit addressing from 16-bit mode.
|
|
|
|
The easiest way to do this is to make sure you use a register for
|
|
the address, since any effective address containing a 32-bit
|
|
register is forced to be a 32-bit address. So you can do
|
|
|
|
\c mov eax,offset_into_32_bit_segment_specified_by_fs
|
|
\c mov dword [fs:eax],0x11223344
|
|
|
|
This is fine, but slightly cumbersome (since it wastes an
|
|
instruction and a register) if you already know the precise offset
|
|
you are aiming at. The x86 architecture does allow 32-bit effective
|
|
addresses to specify nothing but a 4-byte offset, so why shouldn't
|
|
NASM be able to generate the best instruction for the purpose?
|
|
|
|
It can. As in \k{mixjump}, you need only prefix the address with the
|
|
\c{DWORD} keyword, and it will be forced to be a 32-bit address:
|
|
|
|
\c mov dword [fs:dword my_offset],0x11223344
|
|
|
|
Also as in \k{mixjump}, NASM is not fussy about whether the
|
|
\c{DWORD} prefix comes before or after the segment override, so
|
|
arguably a nicer-looking way to code the above instruction is
|
|
|
|
\c mov dword [dword fs:my_offset],0x11223344
|
|
|
|
Don't confuse the \c{DWORD} prefix \e{outside} the square brackets,
|
|
which controls the size of the data stored at the address, with the
|
|
one \c{inside} the square brackets which controls the length of the
|
|
address itself. The two can quite easily be different:
|
|
|
|
\c mov word [dword 0x12345678],0x9ABC
|
|
|
|
This moves 16 bits of data to an address specified by a 32-bit
|
|
offset.
|
|
|
|
You can also specify \c{WORD} or \c{DWORD} prefixes along with the
|
|
\c{FAR} prefix to indirect far jumps or calls. For example:
|
|
|
|
\c call dword far [fs:word 0x4321]
|
|
|
|
This instruction contains an address specified by a 16-bit offset;
|
|
it loads a 48-bit far pointer from that (16-bit segment and 32-bit
|
|
offset), and calls that address.
|
|
|
|
|
|
\H{mixother} Other Mixed-Size Instructions
|
|
|
|
The other way you might want to access data might be using the
|
|
string instructions (\c{LODSx}, \c{STOSx} and so on) or the
|
|
\c{XLATB} instruction. These instructions, since they take no
|
|
parameters, might seem to have no easy way to make them perform
|
|
32-bit addressing when assembled in a 16-bit segment.
|
|
|
|
This is the purpose of NASM's \i\c{a16}, \i\c{a32} and \i\c{a64} prefixes. If
|
|
you are coding \c{LODSB} in a 16-bit segment but it is supposed to
|
|
be accessing a string in a 32-bit segment, you should load the
|
|
desired address into \c{ESI} and then code
|
|
|
|
\c a32 lodsb
|
|
|
|
The prefix forces the addressing size to 32 bits, meaning that
|
|
\c{LODSB} loads from \c{[DS:ESI]} instead of \c{[DS:SI]}. To access
|
|
a string in a 16-bit segment when coding in a 32-bit one, the
|
|
corresponding \c{a16} prefix can be used.
|
|
|
|
The \c{a16}, \c{a32} and \c{a64} prefixes can be applied to any instruction
|
|
in NASM's instruction table, but most of them can generate all the
|
|
useful forms without them. The prefixes are necessary only for
|
|
instructions with implicit addressing:
|
|
\# \c{CMPSx} (\k{insCMPSB}),
|
|
\# \c{SCASx} (\k{insSCASB}), \c{LODSx} (\k{insLODSB}), \c{STOSx}
|
|
\# (\k{insSTOSB}), \c{MOVSx} (\k{insMOVSB}), \c{INSx} (\k{insINSB}),
|
|
\# \c{OUTSx} (\k{insOUTSB}), and \c{XLATB} (\k{insXLATB}).
|
|
\c{CMPSx}, \c{SCASx}, \c{LODSx}, \c{STOSx}, \c{MOVSx}, \c{INSx},
|
|
\c{OUTSx}, and \c{XLATB}.
|
|
Also, the
|
|
various push and pop instructions (\c{PUSHA} and \c{POPF} as well as
|
|
the more usual \c{PUSH} and \c{POP}) can accept \c{a16}, \c{a32} or \c{a64}
|
|
prefixes to force a particular one of \c{SP}, \c{ESP} or \c{RSP} to be used
|
|
as a stack pointer, in case the stack segment in use is a different
|
|
size from the code segment.
|
|
|
|
\c{PUSH} and \c{POP}, when applied to segment registers in 32-bit
|
|
mode, also have the slightly odd behaviour that they push and pop 4
|
|
bytes at a time, of which the top two are ignored and the bottom two
|
|
give the value of the segment register being manipulated. To force
|
|
the 16-bit behaviour of segment-register push and pop instructions,
|
|
you can use the operand-size prefix \i\c{o16}:
|
|
|
|
\c o16 push ss
|
|
\c o16 push ds
|
|
|
|
This code saves a doubleword of stack space by fitting two segment
|
|
registers into the space which would normally be consumed by pushing
|
|
one.
|
|
|
|
(You can also use the \i\c{o32} prefix to force the 32-bit behaviour
|
|
when in 16-bit mode, but this seems less useful.)
|
|
|
|
|
|
\C{64bit} Writing 64-bit Code (Unix, Win64)
|
|
|
|
This chapter attempts to cover some of the common issues involved when
|
|
writing 64-bit code, to run under \i{Win64} or Unix. It covers how to
|
|
write assembly code to interface with 64-bit C routines, and how to
|
|
write position-independent code for shared libraries.
|
|
|
|
All 64-bit code uses a flat memory model, since segmentation is not
|
|
available in 64-bit mode. The one exception is the \c{FS} and \c{GS}
|
|
registers, which still add their bases.
|
|
|
|
Position independence in 64-bit mode is significantly simpler, since
|
|
the processor supports \c{RIP}-relative addressing directly; see the
|
|
\c{REL} keyword (\k{effaddr}). On most 64-bit platforms, it is
|
|
probably desirable to make that the default, using the directive
|
|
\c{DEFAULT REL} (\k{default}).
|
|
|
|
64-bit programming is relatively similar to 32-bit programming, but
|
|
of course pointers are 64 bits long; additionally, all existing
|
|
platforms pass arguments in registers rather than on the stack.
|
|
Furthermore, 64-bit platforms use SSE2 by default for floating point.
|
|
Please see the ABI documentation for your platform.
|
|
|
|
64-bit platforms differ in the sizes of the fundamental datatypes, not
|
|
just from 32-bit platforms but from each other. If a specific size
|
|
data type is desired, it is probably best to use the types defined in
|
|
the Standard C header \c{<inttypes.h>}.
|
|
|
|
In 64-bit mode, the default instruction size is still 32 bits. When
|
|
loading a value into a 32-bit register (but not an 8- or 16-bit
|
|
register), the upper 32 bits of the corresponding 64-bit register are
|
|
set to zero.
|
|
|
|
\H{reg64} Register Names in 64-bit Mode
|
|
|
|
NASM uses the following names for general-purpose registers in 64-bit
|
|
mode, for 8-, 16-, 32- and 64-bit references, respecitively:
|
|
|
|
\c AL/AH, CL/CH, DL/DH, BL/BH, SPL, BPL, SIL, DIL, R8B-R15B
|
|
\c AX, CX, DX, BX, SP, BP, SI, DI, R8W-R15W
|
|
\c EAX, ECX, EDX, EBX, ESP, EBP, ESI, EDI, R8D-R15D
|
|
\c RAX, RCX, RDX, RBX, RSP, RBP, RSI, RDI, R8-R15
|
|
|
|
This is consistent with the AMD documentation and most other
|
|
assemblers. The Intel documentation, however, uses the names
|
|
\c{R8L-R15L} for 8-bit references to the higher registers. It is
|
|
possible to use those names by definiting them as macros; similarly,
|
|
if one wants to use numeric names for the low 8 registers, define them
|
|
as macros. The standard macro package \c{altreg} (see \k{pkg_altreg})
|
|
can be used for this purpose.
|
|
|
|
\H{id64} Immediates and Displacements in 64-bit Mode
|
|
|
|
In 64-bit mode, immediates and displacements are generally only 32
|
|
bits wide. NASM will therefore truncate most displacements and
|
|
immediates to 32 bits.
|
|
|
|
The only instruction which takes a full \i{64-bit immediate} is:
|
|
|
|
\c MOV reg64,imm64
|
|
|
|
NASM will produce this instruction whenever the programmer uses
|
|
\c{MOV} with an immediate into a 64-bit register. If this is not
|
|
desirable, simply specify the equivalent 32-bit register, which will
|
|
be automatically zero-extended by the processor, or specify the
|
|
immediate as \c{DWORD}:
|
|
|
|
\c mov rax,foo ; 64-bit immediate
|
|
\c mov rax,qword foo ; (identical)
|
|
\c mov eax,foo ; 32-bit immediate, zero-extended
|
|
\c mov rax,dword foo ; 32-bit immediate, sign-extended
|
|
|
|
The length of these instructions are 10, 5 and 7 bytes, respectively.
|
|
|
|
The only instructions which take a full \I{64-bit displacement}64-bit
|
|
\e{displacement} is loading or storing, using \c{MOV}, \c{AL}, \c{AX},
|
|
\c{EAX} or \c{RAX} (but no other registers) to an absolute 64-bit address.
|
|
Since this is a relatively rarely used instruction (64-bit code generally uses
|
|
relative addressing), the programmer has to explicitly declare the
|
|
displacement size as \c{QWORD}:
|
|
|
|
\c default abs
|
|
\c
|
|
\c mov eax,[foo] ; 32-bit absolute disp, sign-extended
|
|
\c mov eax,[a32 foo] ; 32-bit absolute disp, zero-extended
|
|
\c mov eax,[qword foo] ; 64-bit absolute disp
|
|
\c
|
|
\c default rel
|
|
\c
|
|
\c mov eax,[foo] ; 32-bit relative disp
|
|
\c mov eax,[a32 foo] ; d:o, address truncated to 32 bits(!)
|
|
\c mov eax,[qword foo] ; error
|
|
\c mov eax,[abs qword foo] ; 64-bit absolute disp
|
|
|
|
A sign-extended absolute displacement can access from -2 GB to +2 GB;
|
|
a zero-extended absolute displacement can access from 0 to 4 GB.
|
|
|
|
\H{unix64} Interfacing to 64-bit C Programs (Unix)
|
|
|
|
On Unix, the 64-bit ABI is defined by the document:
|
|
|
|
\W{http://www.x86-64.org/documentation/abi.pdf}\c{http://www.x86-64.org/documentation/abi.pdf}
|
|
|
|
Although written for AT&T-syntax assembly, the concepts apply equally
|
|
well for NASM-style assembly. What follows is a simplified summary.
|
|
|
|
The first six integer arguments (from the left) are passed in \c{RDI},
|
|
\c{RSI}, \c{RDX}, \c{RCX}, \c{R8}, and \c{R9}, in that order.
|
|
Additional integer arguments are passed on the stack. These
|
|
registers, plus \c{RAX}, \c{R10} and \c{R11} are destroyed by function
|
|
calls, and thus are available for use by the function without saving.
|
|
|
|
Integer return values are passed in \c{RAX} and \c{RDX}, in that order.
|
|
|
|
Floating point is done using SSE registers, except for \c{long
|
|
double}. Floating-point arguments are passed in \c{XMM0} to \c{XMM7};
|
|
return is \c{XMM0} and \c{XMM1}. \c{long double} are passed on the
|
|
stack, and returned in \c{ST(0)} and \c{ST(1)}.
|
|
|
|
All SSE and x87 registers are destroyed by function calls.
|
|
|
|
On 64-bit Unix, \c{long} is 64 bits.
|
|
|
|
Integer and SSE register arguments are counted separately, so for the case of
|
|
|
|
\c void foo(long a, double b, int c)
|
|
|
|
\c{a} is passed in \c{RDI}, \c{b} in \c{XMM0}, and \c{c} in \c{ESI}.
|
|
|
|
\H{win64} Interfacing to 64-bit C Programs (Win64)
|
|
|
|
The Win64 ABI is described at:
|
|
|
|
\W{http://msdn2.microsoft.com/en-gb/library/ms794533.aspx}\c{http://msdn2.microsoft.com/en-gb/library/ms794533.aspx}
|
|
|
|
What follows is a simplified summary.
|
|
|
|
The first four integer arguments are passed in \c{RCX}, \c{RDX},
|
|
\c{R8} and \c{R9}, in that order. Additional integer arguments are
|
|
passed on the stack. These registers, plus \c{RAX}, \c{R10} and
|
|
\c{R11} are destroyed by function calls, and thus are available for
|
|
use by the function without saving.
|
|
|
|
Integer return values are passed in \c{RAX} only.
|
|
|
|
Floating point is done using SSE registers, except for \c{long
|
|
double}. Floating-point arguments are passed in \c{XMM0} to \c{XMM3};
|
|
return is \c{XMM0} only.
|
|
|
|
On Win64, \c{long} is 32 bits; \c{long long} or \c{_int64} is 64 bits.
|
|
|
|
Integer and SSE register arguments are counted together, so for the case of
|
|
|
|
\c void foo(long long a, double b, int c)
|
|
|
|
\c{a} is passed in \c{RCX}, \c{b} in \c{XMM1}, and \c{c} in \c{R8D}.
|
|
|
|
\C{trouble} Troubleshooting
|
|
|
|
This chapter describes some of the common problems that users have
|
|
been known to encounter with NASM, and answers them. It also gives
|
|
instructions for reporting bugs in NASM if you find a difficulty
|
|
that isn't listed here.
|
|
|
|
|
|
\H{problems} Common Problems
|
|
|
|
\S{inefficient} NASM Generates \i{Inefficient Code}
|
|
|
|
We sometimes get `bug' reports about NASM generating inefficient, or
|
|
even `wrong', code on instructions such as \c{ADD ESP,8}. This is a
|
|
deliberate design feature, connected to predictability of output:
|
|
NASM, on seeing \c{ADD ESP,8}, will generate the form of the
|
|
instruction which leaves room for a 32-bit offset. You need to code
|
|
\I\c{BYTE}\c{ADD ESP,BYTE 8} if you want the space-efficient form of
|
|
the instruction. This isn't a bug, it's user error: if you prefer to
|
|
have NASM produce the more efficient code automatically enable
|
|
optimization with the \c{-O} option (see \k{opt-O}).
|
|
|
|
|
|
\S{jmprange} My Jumps are Out of Range\I{out of range, jumps}
|
|
|
|
Similarly, people complain that when they issue \i{conditional
|
|
jumps} (which are \c{SHORT} by default) that try to jump too far,
|
|
NASM reports `short jump out of range' instead of making the jumps
|
|
longer.
|
|
|
|
This, again, is partly a predictability issue, but in fact has a
|
|
more practical reason as well. NASM has no means of being told what
|
|
type of processor the code it is generating will be run on; so it
|
|
cannot decide for itself that it should generate \i\c{Jcc NEAR} type
|
|
instructions, because it doesn't know that it's working for a 386 or
|
|
above. Alternatively, it could replace the out-of-range short
|
|
\c{JNE} instruction with a very short \c{JE} instruction that jumps
|
|
over a \c{JMP NEAR}; this is a sensible solution for processors
|
|
below a 386, but hardly efficient on processors which have good
|
|
branch prediction \e{and} could have used \c{JNE NEAR} instead. So,
|
|
once again, it's up to the user, not the assembler, to decide what
|
|
instructions should be generated. See \k{opt-O}.
|
|
|
|
|
|
\S{proborg} \i\c{ORG} Doesn't Work
|
|
|
|
People writing \i{boot sector} programs in the \c{bin} format often
|
|
complain that \c{ORG} doesn't work the way they'd like: in order to
|
|
place the \c{0xAA55} signature word at the end of a 512-byte boot
|
|
sector, people who are used to MASM tend to code
|
|
|
|
\c ORG 0
|
|
\c
|
|
\c ; some boot sector code
|
|
\c
|
|
\c ORG 510
|
|
\c DW 0xAA55
|
|
|
|
This is not the intended use of the \c{ORG} directive in NASM, and
|
|
will not work. The correct way to solve this problem in NASM is to
|
|
use the \i\c{TIMES} directive, like this:
|
|
|
|
\c ORG 0
|
|
\c
|
|
\c ; some boot sector code
|
|
\c
|
|
\c TIMES 510-($-$$) DB 0
|
|
\c DW 0xAA55
|
|
|
|
The \c{TIMES} directive will insert exactly enough zero bytes into
|
|
the output to move the assembly point up to 510. This method also
|
|
has the advantage that if you accidentally fill your boot sector too
|
|
full, NASM will catch the problem at assembly time and report it, so
|
|
you won't end up with a boot sector that you have to disassemble to
|
|
find out what's wrong with it.
|
|
|
|
|
|
\S{probtimes} \i\c{TIMES} Doesn't Work
|
|
|
|
The other common problem with the above code is people who write the
|
|
\c{TIMES} line as
|
|
|
|
\c TIMES 510-$ DB 0
|
|
|
|
by reasoning that \c{$} should be a pure number, just like 510, so
|
|
the difference between them is also a pure number and can happily be
|
|
fed to \c{TIMES}.
|
|
|
|
NASM is a \e{modular} assembler: the various component parts are
|
|
designed to be easily separable for re-use, so they don't exchange
|
|
information unnecessarily. In consequence, the \c{bin} output
|
|
format, even though it has been told by the \c{ORG} directive that
|
|
the \c{.text} section should start at 0, does not pass that
|
|
information back to the expression evaluator. So from the
|
|
evaluator's point of view, \c{$} isn't a pure number: it's an offset
|
|
from a section base. Therefore the difference between \c{$} and 510
|
|
is also not a pure number, but involves a section base. Values
|
|
involving section bases cannot be passed as arguments to \c{TIMES}.
|
|
|
|
The solution, as in the previous section, is to code the \c{TIMES}
|
|
line in the form
|
|
|
|
\c TIMES 510-($-$$) DB 0
|
|
|
|
in which \c{$} and \c{$$} are offsets from the same section base,
|
|
and so their difference is a pure number. This will solve the
|
|
problem and generate sensible code.
|
|
|
|
|
|
\H{bugs} \i{Bugs}\I{reporting bugs}
|
|
|
|
We have never yet released a version of NASM with any \e{known}
|
|
bugs. That doesn't usually stop there being plenty we didn't know
|
|
about, though. Any that you find should be reported firstly via the
|
|
\i\c{bugtracker} at
|
|
\W{https://sourceforge.net/projects/nasm/}\c{https://sourceforge.net/projects/nasm/}
|
|
(click on "Bugs"), or if that fails then through one of the
|
|
contacts in \k{contact}.
|
|
|
|
Please read \k{qstart} first, and don't report the bug if it's
|
|
listed in there as a deliberate feature. (If you think the feature
|
|
is badly thought out, feel free to send us reasons why you think it
|
|
should be changed, but don't just send us mail saying `This is a
|
|
bug' if the documentation says we did it on purpose.) Then read
|
|
\k{problems}, and don't bother reporting the bug if it's listed
|
|
there.
|
|
|
|
If you do report a bug, \e{please} give us all of the following
|
|
information:
|
|
|
|
\b What operating system you're running NASM under. DOS, Linux,
|
|
NetBSD, Win16, Win32, VMS (I'd be impressed), whatever.
|
|
|
|
\b If you're running NASM under DOS or Win32, tell us whether you've
|
|
compiled your own executable from the DOS source archive, or whether
|
|
you were using the standard distribution binaries out of the
|
|
archive. If you were using a locally built executable, try to
|
|
reproduce the problem using one of the standard binaries, as this
|
|
will make it easier for us to reproduce your problem prior to fixing
|
|
it.
|
|
|
|
\b Which version of NASM you're using, and exactly how you invoked
|
|
it. Give us the precise command line, and the contents of the
|
|
\c{NASMENV} environment variable if any.
|
|
|
|
\b Which versions of any supplementary programs you're using, and
|
|
how you invoked them. If the problem only becomes visible at link
|
|
time, tell us what linker you're using, what version of it you've
|
|
got, and the exact linker command line. If the problem involves
|
|
linking against object files generated by a compiler, tell us what
|
|
compiler, what version, and what command line or options you used.
|
|
(If you're compiling in an IDE, please try to reproduce the problem
|
|
with the command-line version of the compiler.)
|
|
|
|
\b If at all possible, send us a NASM source file which exhibits the
|
|
problem. If this causes copyright problems (e.g. you can only
|
|
reproduce the bug in restricted-distribution code) then bear in mind
|
|
the following two points: firstly, we guarantee that any source code
|
|
sent to us for the purposes of debugging NASM will be used \e{only}
|
|
for the purposes of debugging NASM, and that we will delete all our
|
|
copies of it as soon as we have found and fixed the bug or bugs in
|
|
question; and secondly, we would prefer \e{not} to be mailed large
|
|
chunks of code anyway. The smaller the file, the better. A
|
|
three-line sample file that does nothing useful \e{except}
|
|
demonstrate the problem is much easier to work with than a
|
|
fully fledged ten-thousand-line program. (Of course, some errors
|
|
\e{do} only crop up in large files, so this may not be possible.)
|
|
|
|
\b A description of what the problem actually \e{is}. `It doesn't
|
|
work' is \e{not} a helpful description! Please describe exactly what
|
|
is happening that shouldn't be, or what isn't happening that should.
|
|
Examples might be: `NASM generates an error message saying Line 3
|
|
for an error that's actually on Line 5'; `NASM generates an error
|
|
message that I believe it shouldn't be generating at all'; `NASM
|
|
fails to generate an error message that I believe it \e{should} be
|
|
generating'; `the object file produced from this source code crashes
|
|
my linker'; `the ninth byte of the output file is 66 and I think it
|
|
should be 77 instead'.
|
|
|
|
\b If you believe the output file from NASM to be faulty, send it to
|
|
us. That allows us to determine whether our own copy of NASM
|
|
generates the same file, or whether the problem is related to
|
|
portability issues between our development platforms and yours. We
|
|
can handle binary files mailed to us as MIME attachments, uuencoded,
|
|
and even BinHex. Alternatively, we may be able to provide an FTP
|
|
site you can upload the suspect files to; but mailing them is easier
|
|
for us.
|
|
|
|
\b Any other information or data files that might be helpful. If,
|
|
for example, the problem involves NASM failing to generate an object
|
|
file while TASM can generate an equivalent file without trouble,
|
|
then send us \e{both} object files, so we can see what TASM is doing
|
|
differently from us.
|
|
|
|
|
|
\A{ndisasm} \i{Ndisasm}
|
|
|
|
The Netwide Disassembler, NDISASM
|
|
|
|
\H{ndisintro} Introduction
|
|
|
|
|
|
The Netwide Disassembler is a small companion program to the Netwide
|
|
Assembler, NASM. It seemed a shame to have an x86 assembler,
|
|
complete with a full instruction table, and not make as much use of
|
|
it as possible, so here's a disassembler which shares the
|
|
instruction table (and some other bits of code) with NASM.
|
|
|
|
The Netwide Disassembler does nothing except to produce
|
|
disassemblies of \e{binary} source files. NDISASM does not have any
|
|
understanding of object file formats, like \c{objdump}, and it will
|
|
not understand \c{DOS .EXE} files like \c{debug} will. It just
|
|
disassembles.
|
|
|
|
|
|
\H{ndisstart} Getting Started: Installation
|
|
|
|
See \k{install} for installation instructions. NDISASM, like NASM,
|
|
has a \c{man page} which you may want to put somewhere useful, if you
|
|
are on a Unix system.
|
|
|
|
|
|
\H{ndisrun} Running NDISASM
|
|
|
|
To disassemble a file, you will typically use a command of the form
|
|
|
|
\c ndisasm -b {16|32|64} filename
|
|
|
|
NDISASM can disassemble 16-, 32- or 64-bit code equally easily,
|
|
provided of course that you remember to specify which it is to work
|
|
with. If no \i\c{-b} switch is present, NDISASM works in 16-bit mode
|
|
by default. The \i\c{-u} switch (for USE32) also invokes 32-bit mode.
|
|
|
|
Two more command line options are \i\c{-r} which reports the version
|
|
number of NDISASM you are running, and \i\c{-h} which gives a short
|
|
summary of command line options.
|
|
|
|
|
|
\S{ndiscom} COM Files: Specifying an Origin
|
|
|
|
To disassemble a \c{DOS .COM} file correctly, a disassembler must assume
|
|
that the first instruction in the file is loaded at address \c{0x100},
|
|
rather than at zero. NDISASM, which assumes by default that any file
|
|
you give it is loaded at zero, will therefore need to be informed of
|
|
this.
|
|
|
|
The \i\c{-o} option allows you to declare a different origin for the
|
|
file you are disassembling. Its argument may be expressed in any of
|
|
the NASM numeric formats: decimal by default, if it begins with `\c{$}'
|
|
or `\c{0x}' or ends in `\c{H}' it's \c{hex}, if it ends in `\c{Q}' it's
|
|
\c{octal}, and if it ends in `\c{B}' it's \c{binary}.
|
|
|
|
Hence, to disassemble a \c{.COM} file:
|
|
|
|
\c ndisasm -o100h filename.com
|
|
|
|
will do the trick.
|
|
|
|
|
|
\S{ndissync} Code Following Data: Synchronisation
|
|
|
|
Suppose you are disassembling a file which contains some data which
|
|
isn't machine code, and \e{then} contains some machine code. NDISASM
|
|
will faithfully plough through the data section, producing machine
|
|
instructions wherever it can (although most of them will look
|
|
bizarre, and some may have unusual prefixes, e.g. `\c{FS OR AX,0x240A}'),
|
|
and generating `DB' instructions ever so often if it's totally stumped.
|
|
Then it will reach the code section.
|
|
|
|
Supposing NDISASM has just finished generating a strange machine
|
|
instruction from part of the data section, and its file position is
|
|
now one byte \e{before} the beginning of the code section. It's
|
|
entirely possible that another spurious instruction will get
|
|
generated, starting with the final byte of the data section, and
|
|
then the correct first instruction in the code section will not be
|
|
seen because the starting point skipped over it. This isn't really
|
|
ideal.
|
|
|
|
To avoid this, you can specify a `\i\c{synchronisation}' point, or indeed
|
|
as many synchronisation points as you like (although NDISASM can
|
|
only handle 8192 sync points internally). The definition of a sync
|
|
point is this: NDISASM guarantees to hit sync points exactly during
|
|
disassembly. If it is thinking about generating an instruction which
|
|
would cause it to jump over a sync point, it will discard that
|
|
instruction and output a `\c{db}' instead. So it \e{will} start
|
|
disassembly exactly from the sync point, and so you \e{will} see all
|
|
the instructions in your code section.
|
|
|
|
Sync points are specified using the \i\c{-s} option: they are measured
|
|
in terms of the program origin, not the file position. So if you
|
|
want to synchronize after 32 bytes of a \c{.COM} file, you would have to
|
|
do
|
|
|
|
\c ndisasm -o100h -s120h file.com
|
|
|
|
rather than
|
|
|
|
\c ndisasm -o100h -s20h file.com
|
|
|
|
As stated above, you can specify multiple sync markers if you need
|
|
to, just by repeating the \c{-s} option.
|
|
|
|
|
|
\S{ndisisync} Mixed Code and Data: Automatic (Intelligent) Synchronisation
|
|
\I\c{auto-sync}
|
|
|
|
Suppose you are disassembling the boot sector of a \c{DOS} floppy (maybe
|
|
it has a virus, and you need to understand the virus so that you
|
|
know what kinds of damage it might have done you). Typically, this
|
|
will contain a \c{JMP} instruction, then some data, then the rest of the
|
|
code. So there is a very good chance of NDISASM being \e{misaligned}
|
|
when the data ends and the code begins. Hence a sync point is
|
|
needed.
|
|
|
|
On the other hand, why should you have to specify the sync point
|
|
manually? What you'd do in order to find where the sync point would
|
|
be, surely, would be to read the \c{JMP} instruction, and then to use
|
|
its target address as a sync point. So can NDISASM do that for you?
|
|
|
|
The answer, of course, is yes: using either of the synonymous
|
|
switches \i\c{-a} (for automatic sync) or \i\c{-i} (for intelligent
|
|
sync) will enable \c{auto-sync} mode. Auto-sync mode automatically
|
|
generates a sync point for any forward-referring PC-relative jump or
|
|
call instruction that NDISASM encounters. (Since NDISASM is one-pass,
|
|
if it encounters a PC-relative jump whose target has already been
|
|
processed, there isn't much it can do about it...)
|
|
|
|
Only PC-relative jumps are processed, since an absolute jump is
|
|
either through a register (in which case NDISASM doesn't know what
|
|
the register contains) or involves a segment address (in which case
|
|
the target code isn't in the same segment that NDISASM is working
|
|
in, and so the sync point can't be placed anywhere useful).
|
|
|
|
For some kinds of file, this mechanism will automatically put sync
|
|
points in all the right places, and save you from having to place
|
|
any sync points manually. However, it should be stressed that
|
|
auto-sync mode is \e{not} guaranteed to catch all the sync points, and
|
|
you may still have to place some manually.
|
|
|
|
Auto-sync mode doesn't prevent you from declaring manual sync
|
|
points: it just adds automatically generated ones to the ones you
|
|
provide. It's perfectly feasible to specify \c{-i} \e{and} some \c{-s}
|
|
options.
|
|
|
|
Another caveat with auto-sync mode is that if, by some unpleasant
|
|
fluke, something in your data section should disassemble to a
|
|
PC-relative call or jump instruction, NDISASM may obediently place a
|
|
sync point in a totally random place, for example in the middle of
|
|
one of the instructions in your code section. So you may end up with
|
|
a wrong disassembly even if you use auto-sync. Again, there isn't
|
|
much I can do about this. If you have problems, you'll have to use
|
|
manual sync points, or use the \c{-k} option (documented below) to
|
|
suppress disassembly of the data area.
|
|
|
|
|
|
\S{ndisother} Other Options
|
|
|
|
The \i\c{-e} option skips a header on the file, by ignoring the first N
|
|
bytes. This means that the header is \e{not} counted towards the
|
|
disassembly offset: if you give \c{-e10 -o10}, disassembly will start
|
|
at byte 10 in the file, and this will be given offset 10, not 20.
|
|
|
|
The \i\c{-k} option is provided with two comma-separated numeric
|
|
arguments, the first of which is an assembly offset and the second
|
|
is a number of bytes to skip. This \e{will} count the skipped bytes
|
|
towards the assembly offset: its use is to suppress disassembly of a
|
|
data section which wouldn't contain anything you wanted to see
|
|
anyway.
|
|
|
|
|
|
\H{ndisbugs} Bugs and Improvements
|
|
|
|
There are no known bugs. However, any you find, with patches if
|
|
possible, should be sent to
|
|
\W{mailto:nasm-bugs@lists.sourceforge.net}\c{nasm-bugs@lists.sourceforge.net}, or to the
|
|
developer's site at
|
|
\W{https://sourceforge.net/projects/nasm/}\c{https://sourceforge.net/projects/nasm/}
|
|
and we'll try to fix them. Feel free to send contributions and
|
|
new features as well.
|
|
|
|
\A{inslist} \i{Instruction List}
|
|
|
|
\H{inslistintro} Introduction
|
|
|
|
The following sections show the instructions which NASM currently supports. For each
|
|
instruction, there is a separate entry for each supported addressing mode. The third
|
|
column shows the processor type in which the instruction was introduced and,
|
|
when appropriate, one or more usage flags.
|
|
|
|
\& inslist.src
|
|
|
|
\A{changelog} \i{NASM Version History}
|
|
|
|
\& changes.src
|
|
|