Post by Paolo AmorosoI'm looking for source code of MS-DOS .COM programs in real-mode 8086
Assembly written in NASM syntax. Any repositories or recommendations?
I'm learning Assembly programming under MS-DOS (and MikeOS). To avoid
the complexity of x86 segmentation, for the time being I prefer to focus
on single-segment programs, as I plan to write small programs anyway.
So I'd like to study examples of how such systems organize and reference
data and code. I searched a bit but found remarkably little .COM code.
But it doesn't make much sense to write .com programs which can't
be run natively on a current computer system. Windows programs also
don't use segmentation and there in no difference in the assembly code
for DOS and Windows (as long as you use also 32 bit instructions in DOS,
which makes things much easier). The big difference is, that there
is no such simple file format as the .com format in DOS so you will have
to use a linker which generates the proper file structure for a Windows
binary.
But if you really want, you can also generate any byte if the .exe
file by your assembler source code so NASM directly generates the
exe file. Here an example for a simple program which reads from
stdin, converts any lowercase letter to upper case and writes it
to stdout (the code itself starts at the label winmain, the rest
is just the data of the exe file format). Because NASM uses an awful
syntax you have to include "mac.inc" to be able to use a readable
instruction format (I post mac.inc in a follow up):
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;; upper.asm: copy stdin to stdout, convert a-z to A-Z ;;
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
; nasm -O99 -f bin -o upper.exe upper.asm
%include "mac.inc"
UseIdatSection equ 0 ; 0 if no idat section is used
UseUdatSection equ 0 ; 0 if no udat section is used
;#==================================================================#
;# Start of Headers #
;#==================================================================#
; +--------------------------------------------+
; | Start of DOS Header |
; +--------------------------------------------+
section .text vstart=0
doshead_start:
; DOS .EXE header
dc.b 'MZ' ; Magic number
dc.w dosfilesize % 512 ; Bytes on last page of file (0->512)
dc.w (dosfilesize-1)/512+1
; Pages in file (Page=512 byte)
dc.w 0 ; Relocations (nr of entries)
dc.w doshead_size/16 ; Size of header size in paragraphs (16 byte)
dc.w 0 ; Minimum extra paragraphs needed
dc.w $0ffff ; Maximum extra paragraphs needed
dc.w 0 ; Initial (relative) SS value (ss=load_adr+nr)
dc.w dosstack ; Initial SP value
dc.w 0 ; Checksum
dc.w dosmain ; Initial IP value
dc.w 0 ; Initial (relative) CS value (cs=load_adr+nr)
dc.w reloc ; File address of relocation table
dc.w 0 ; Overlay number
dc.w 0,0,0,0 ; Reserved words
dc.w 0 ; OEM identifier (for e_oeminfo)
dc.w 0 ; OEM information; e_oemid specific
dc.l 0,0,0,0,0 ; Reserved words
dc.l WinHeader ; File address of new exe header
reloc:
doshead_end:
doshead_size equ doshead_end-doshead_start
@@0 equ $-$$ ; current file position
section .text0 vstart=0
dosstart:
dosmain:move.w s6,-[sp]
move.w [sp]+,s0
move.w .text,r1
move.b $09,m0
trap $21
move.w $4c01,r0
trap $21
text: dc.b 'Nice to meet somebody who is still using DOS,',13,10
dc.b 'but this program requires Win32.',13,10,'$'
align 16, db 0
dosstack equ $+256 ; 256 Byte stack
dosfilesize equ $-dosstart+256
; +--------------------------------------------+
; | End of DOS Header |
; +--------------------------------------------+
; +--------------------------------------------+
; | Start of Windows Header |
; +--------------------------------------------+
ImageBase equ $00400000
SectionAlignment equ 4096
FileAlignment equ 512
@@1 equ @@0 + $-$$ ; current file position
WinHeader equ @@1
section .text1 vstart=ImageBase
ImageBase1 equ $
; ImageBase1 has same value as ImageBase but is nonrelatve
; see WINNT.H for information
dc.b 'PE',0,0 ; magic word
; _IMAGE_FILE_HEADER:
dc.w $014c ; Machine ($014c=Intel x86 processor)
dc.w NumberOfSections ; NumberOfSections
dc.l $36a57950 ; TimeDateStamp (seconds since 31.12.69 16:00)
dc.l 0 ; PointerToSymbolTable
dc.l 0 ; NumberOfSymbols
dc.w SizeOfOptionalHeader ; SizeOfOptionalHeader
dc.w $010f ; Charcteristics
; 0x0001 Relocation info stripped from file.
; 0x0002 File is executable (i.e. no unresolved externel references).
; 0x0004 Line nunbers stripped from file.
; 0x0008 Local symbols stripped from file.
; 0x0010 Agressively trim working set
; 0x0080 Bytes of machine word are reversed.
; 0x0100 32 bit word machine.
; 0x0200 Debugging info stripped from file in .DBG file
; 0x0400 If Image is on removable media, copy and run from the swap file.
; 0x0800 If Image is on Net, copy and run from the swap file.
; 0x1000 System File.
; 0x2000 File is a DLL.
; 0x4000 File should only be run on a UP machine
; 0x8000 Bytes of machine word are reversed.
@a1 equ $ ; _IMAGE_OPTIONAL_HEADER
dc.w $010b ; Magic
dc.b 5 ; MajorLinkerVersion
dc.b 12 ; MinorLinkerVersion
dc.l SizeOfCode ; SizeOfCode
dc.l SizeOfInitializedData ; SizeOfInitializedData
dc.l SizeOfUninitializedData ; SizeOfUninitializedData
dc.l winmain-ImageBase ; AddressOfEntryPoint
dc.l BaseOfCode ; BaseOfCode
dc.l BaseOfData ; BaseOfData
dc.l ImageBase ; ImageBase
dc.l SectionAlignment ; SectionAlignment
dc.l FileAlignment ; FileAlignment
dc.w 4 ; MajorOperatingSystemVersion
dc.w 0 ; MinorOperatingSystemVersion
dc.w 0 ; MajorImageVersion
dc.w 0 ; MinorImageVersion
dc.w 4 ; MajorSubsystemVersion
dc.w 0 ; MinorSubsystemVersion
dc.l 0 ; Win32VersionValue
dc.l SizeOfImage ; SizeOfImage
dc.l SizeOfHeaders ; SizeOfHeaders
dc.l 0 ; CheckSum
dc.w 3 ; Subsystem
; 0: Unknown subsystem.
; 1: Image doesn't require a subsystem.
; 2: Image runs in the Windows GUI subsystem.
; 3: Image runs in the Windows character subsystem.
; 5: image runs in the OS/2 character subsystem.
; 7: image run in the Posix character subsystem.
; 8: image run in the 8 subsystem.
dc.w $0000 ; DllCharacteristics
dc.l $00100000 ; SizeOfStackReserve
dc.l $00001000 ; SizeOfStackCommit
dc.l $00100000 ; SizeOfHeapReserve
dc.l $00001000 ; SizeOfHeapCommit
dc.l $00000000 ; LoaderFlags
dc.l NumberOfRvaAndSize ; NumberOfRvaAndSize (entries
; in the data dir)
; ..............................................
; : Start of Image Data Directory :
; ..............................................
; virtual address, size
@b equ $
dc.l 0,0 ; Export Directory
dc.l imp_start,imp_size ; Import Directory
dc.l 0,0 ; Resource Directory
dc.l 0,0 ; Exception Directory
dc.l 0,0 ; Security Directory
dc.l 0,0 ; Base Relocation Table
dc.l 0,0 ; Debug Directory
dc.l 0,0 ; Description String
dc.l 0,0 ; Machine Value (MIPS GP)
dc.l 0,0 ; TLS Directory
dc.l 0,0 ; Load Configuration Directory
dc.l 0,0 ; Bound Import Directory in headers
dc.l iat_start,iat_size ; Import Address Table
dc.l 0,0 ; 14
dc.l 0,0 ; 15
dc.l 0,0 ; 16
NumberOfRvaAndSize equ ($-@b)/8
SizeOfOptionalHeader equ $-@a1
; ..............................................
; : End of Image Data Directory :
; ..............................................
; ..............................................
; : Start of Image Sections Header :
; ..............................................
@a2 equ $
dc.b '.text',0,0,0 ; name
dc.l VSizeOf_text ; virtual size
dc.l VBaseOf_text ; virtual address
dc.l FSizeOf_text ; size of raw data
dc.l FBaseOf_text ; pointer to raw data
dc.l 0 ; pointer to relocatins
dc.l 0 ; pointer to line numbers
dc.w 0 ; number of relocations
dc.w 0 ; number of line numbers
dc.l $0e0000020 ; characteristics
%IF UseIdatSection <> 0
dc.b '.idat',0,0,0 ; name
dc.l VSizeOf_idat ; virtual size
dc.l VBaseOf_idat ; virtual address
dc.l FSizeOf_idat ; size of raw data
dc.l FBaseOf_idat ; pointer to raw data
dc.l 0 ; pointer to relocatins
dc.l 0 ; pointer to line numbers
dc.w 0 ; number of relocations
dc.w 0 ; number of line numbers
dc.l $0e0000040 ; characteristics
%ENDIF
%IF UseUdatSection <> 0
dc.b '.udat',0,0,0 ; name
dc.l VSizeOf_udat ; virtual size
dc.l VBaseOf_udat ; virtual address
dc.l FSizeOf_udat ; size of raw data
dc.l FBaseOf_udat ; pointer to raw data
dc.l 0 ; pointer to relocatins
dc.l 0 ; pointer to line numbers
dc.w 0 ; number of relocations
dc.w 0 ; number of line numbers
dc.l $0e0000080 ; characteristics
%ENDIF
NumberOfSections equ ($-@a2)/40
; ..............................................
; : End of Image Sections Header :
; ..............................................
; characteristics
; 0x00000020 // Section contains code.
; 0x00000040 // Section contains initialized data.
; 0x00000080 // Section contains uninitialized data.
; 0x00000200 // Section contains comments or some other type of information.
; 0x00000800 // Section contents will not become part of image.
; 0x00001000 // Section contents comdat.
; 0x01000000 // Section contains extended relocations.
; 0x02000000 // Section can be discarded.
; 0x04000000 // Section is not cachable.
; 0x08000000 // Section is not pageable.
; 0x10000000 // Section is shareable.
; 0x20000000 // Section is executable.
; 0x40000000 // Section is readable.
; 0x80000000 // Section is writeable.
; +--------------------------------------------+
; | End of Windows Header |
; +--------------------------------------------+
@@2 equ @@1 + ($-$$) ; current file position
times ((@@2+FileAlignment-1)/FileAlignment*FileAlignment)-@@2 db 0
@@3 equ @@1 + ($-$$) ; current file position
SizeOfHeaders equ @@3
;#==================================================================#
;# End of Headers #
;#==================================================================#
;#==================================================================#
;# Start of Sections #
;#==================================================================#
; +--------------------------------------------+
; | Start of .text Section |
; +--------------------------------------------+
FBaseOf_text equ @@3
VBaseOf_text equ ($-ImageBase1+SectionAlignment-1)/SectionAlignment*SectionAlignment
BaseOfCode equ VBaseOf_text
section .text2 vstart=ImageBase+VBaseOf_text
ImageBase2 equ $-VBaseOf_text
; ImageBase2 has same value as ImageBase but is nonrelatve
; ..............................................
; : Start of Thunk Table :
; ..............................................
iat_start equ $-ImageBase
KERNEL32_thunk:
ExitProcess: dc.l KERNEL32_ExitProcess -ImageBase
GetStdHandle: dc.l KERNEL32_GetStdHandle -ImageBase
ReadFile: dc.l KERNEL32_ReadFile -ImageBase
WriteFile: dc.l KERNEL32_WriteFile -ImageBase
dc.l 0
iat_size equ $-ImageBase-iat_start
; ..............................................
; : End of Thunk Table :
; ..............................................
; ..............................................
; : Start of Import Directory :
; ..............................................
imp_start equ $-ImageBase
imp:
dc.l KERNEL32_import -ImageBase
dc.l 0
dc.l 0
dc.l KERNEL32_name -ImageBase
dc.l KERNEL32_thunk -ImageBase
dc.l 0
dc.l 0
dc.l 0
dc.l 0
dc.l 0
imp_size equ $-imp
; ..............................................
; : End of Import Directory :
; ..............................................
KERNEL32_name:
dc.b 'KERNEL32.dll',0
align 2 , db 0
KERNEL32_import:
dc.l KERNEL32_ExitProcess -ImageBase
dc.l KERNEL32_GetStdHandle -ImageBase
dc.l KERNEL32_ReadFile -ImageBase
dc.l KERNEL32_WriteFile -ImageBase
dc.l 0
align 2, db 0
KERNEL32_ExitProcess:
dc.w 0
dc.b 'ExitProcess',0
align 2, db 0
KERNEL32_GetStdHandle:
dc.w 0
dc.b 'GetStdHandle',0
align 2, db 0
KERNEL32_ReadFile:
dc.w 0
dc.b 'ReadFile',0
align 2, db 0
KERNEL32_WriteFile:
dc.w 0
dc.b 'WriteFile',0
align 2, db 0
; ..............................................
; : Start of Code :
; ..............................................
seg 32
winmain:
20: bsr.l getc
cmpq.l -1,r0
beq.b exit
cmp.b 'a',r0
blo.b .10
cmp.b 'z',r0
bhi.b .10
add.b 'A'-'a',r0
10: bsr.l putc
br.b .20
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;; OS specific functions: getc, putc, exit ;;
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
exit: move.l r0,-[sp]
jsr.l [ExitProcess] ; exit program
putc: movem.l r0-r7,-[sp]
eor.l r0,r0
add.l [.handle],r0
bne.b .10
moveq.l -11,-[sp]
jsr.l [GetStdHandle]
move.l r0,[.handle]
10: moveq.l 0,-[sp]
lea.l [r7+4*4],r1
move.l r1,-[sp]
moveq.l 1,-[sp]
addq.l 4*4,r1
move.l r1,-[sp]
move.l r0,-[sp]
jsr.l [WriteFile]
or.l r0,r0
bne.b .20
30: moveq.l 0,-[sp]
jsr.l [ExitProcess]
20: cmpq.l 1,[r7+3*4]
bne.b .30
movem.l [sp]+,r0-r7
rts.l
align 4, db 0
handle:dc.l 0
getc: eor.l r0,r0
movem.l r0-r7,-[sp]
add.l [.handle],r0
bne.b .10
moveq.l -10,-[sp]
jsr.l [GetStdHandle]
move.l r0,[.handle]
10: moveq.l 0,-[sp]
lea.l [r7+4*4],r1
move.l r1,-[sp]
moveq.l 1,-[sp]
addq.l 4*4,r1
move.l r1,-[sp]
move.l r0,-[sp]
jsr.l [ReadFile]
or.l r0,r0
bne.b .20
moveq.l 0,-[sp]
jsr.l [ExitProcess]
20: cmpq.l 1,[r7+3*4]
beq.b .30
move.l -1,[r7+7*4]
30: movem.l [sp]+,r0-r7
rts.l
align 4, db 0
handle:dc.l 0
; ..............................................
; : End of Code :
; ..............................................
VSizeOf_text equ $-ImageBase-VBaseOf_text
@a3 equ $-ImageBase2
@@4 equ @@3 + ($-$$) ; current file position
times ((@@4+FileAlignment-1)/FileAlignment*FileAlignment)-@@4 db 0
@@5 equ @@3 + ($-$$) ; current file position
FSizeOf_text equ @@5-FBaseOf_text
SizeOfCode equ FSizeOf_text
; +--------------------------------------------+
; | End of .text Section |
; +--------------------------------------------+
; +--------------------------------------------+
; | Start of .idat Section |
; +--------------------------------------------+
FBaseOf_idat equ @@5
VBaseOf_idat equ (@a3+SectionAlignment-1)/SectionAlignment*SectionAlignment
BaseOfData equ VBaseOf_idat
section .text3 vstart=ImageBase+VBaseOf_idat
ImageBase3 equ $-VBaseOf_idat
; ImageBase3 has same value as ImageBase but is nonrelatve
; Insert initialized variables here (and set UseIdatSection=1
; at the top of this file). Because the code section is set
; r/w-able, you can put initialized variables also into the
; code section.
; var1: dc.l 0
; var2: dc.l $12345678
VSizeOf_idat equ $-ImageBase-VBaseOf_idat
@a4 equ $ - ImageBase3
@@6 equ @@5 + ($-$$) ; current file position
times ((@@6+FileAlignment-1)/FileAlignment*FileAlignment)-@@6 db 0
@@7 equ @@5 + ($-$$) ; current file position
FSizeOf_idat equ @@7-FBaseOf_idat
; +--------------------------------------------+
; | End of .idat Section |
; +--------------------------------------------+
SizeOfInitializedData equ FSizeOf_idat
; +--------------------------------------------+
; | Start of .udat Section |
; +--------------------------------------------+
FBaseOf_udat equ @@7
VBaseOf_udat equ (@a4+SectionAlignment-1)/SectionAlignment*SectionAlignment
section .bss vstart=ImageBase+VBaseOf_udat
ImageBase4 equ $-VBaseOf_udat
; ImageBase4 has same value as ImageBase but is nonrelatve
; Insert uninitialized variables here (and set UseUdatSection=1
; at the top of this file). Because the code section is set
; r/w-able, you can put uninitialized variables also at the END
; of the code section (but NASM doesn't support this).
; buf1: blk.l 10
; buf2: blk.l 200
VSizeOf_udat equ $-ImageBase-VBaseOf_udat
FSizeOf_udat equ 0
; +--------------------------------------------+
; | End of .udat Section |
; +--------------------------------------------+
SizeOfUninitializedData equ VSizeOf_udat
SizeOfImage equ ($-ImageBase4+SectionAlignment-1)/SectionAlignment*SectionAlignment
;#==================================================================#
;# End of Sections #
;#==================================================================#