Related
I am getting a segmentation fault from this simple starting program.
I am using Ubuntu 16.10 and kdbg for debugging. Affter reaching starting __int 80h__, it stops moving to the next line.
section .bss ; section containing uninitialized data
BUFFLEN equ 1024 ; length of buffer
Buff: resb BUFFLEN ; text buffer itself
section .data ; section containing initialzed data
section .text ; secttion containing code
global _start ; linker needs to find the entry point!
_start:
nop ; this no-op keeps gdb happy
; read buffer full of text form stdin:
read:
mov eax, 3 ; specify sys_read call
mov ebx, 0 ; specify file descriptor 0 : standard input
mov ecx, Buff ; pass offset of the buffer to read to
mov edx, BUFFLEN ; pass number of bytes to be read at one pass
int 80h ; call sys_read to fill the buffer
mov esi,eax ; copy sys_read return value for safekeeping
cmp eax, 0 ; if eax = 0 , sys_read reached EOF on stdin
je Done ; jump if Equal ( to o, form compare)
; set up the register for the process buffer step:
mov ecx, esi ; place the number of bytes read into ecx
mov ebp, Buff ; pace address of buffer into ebp
dec ebp ; adjust the count to offset
; go through the buffer and cnvert lowercase to uppercase characters:
Scan:
cmp byte [ebp+ecx], 61h ; test input char agaisnst lowercase 'a'
jb Next ; if Below 'a' in ASCII, not lowercase
cmp byte [ebp+ecx], 7Ah ; test against lowercase 'z'
ja Next
sub byte [ebx+ecx], 20h ; subtract 20h to give uppercase..
Next:
dec ecx ; Decrement counter
jnz Scan ; if characters reamin, loop back
; Write the buffer full of processed text to stdout:
Write:
mov eax,4 ; Specify sys_write call
mov ebx, 1 ; Specify file descriptor 1 : stdout
mov ecx, Buff ; pass the offset of the buffer
mov edx, esi ; pass the # of bytes of data in the buffer
int 80h ; make sys_write kernel call
jmp read ; loop back and load another buffer full
Done:
mov eax, 1 ; Code for Exit sys_call
mov ebx, 0 ; return code of Zero
int 80h
I used these commands:
nasm -f elf -g -F stabs uppercaser1.asm
ld -m elf_i386 -o uppercaser1 uppercaser1.o
./uppercaser < inputflie
I think this code is generally public so I am posting with that in mind.
You should use the code as a guide to understanding what may be wrong in your code; however, it does not conform to any coding standard so it is pointless just to copy and paste and turn it in as an assignment; assuming that is the case.
You will never increase your assembly programming skills by merely doing a copy/paste.
lsb_release -a
...
Description: Ubuntu 16.04.3 LTS
nasm -f elf32 -g uppercase1.s -o uppercase1.o && ld -m elf_i386 uppercase1.o -o uppercase1
section .bss
Buff resb 1
section .data
section .text
global _start
_start:
nop
Read:
mov eax, 3 ; read syscall
mov ebx, 0 ; stdin
mov ecx, Buff ; pass address of the buffer to read to
mov edx, 1 ; read one char or one byte
int 0x80 ;
cmp eax, 0 ; if syscall returns returns 0
je Exit ;
cmp byte [Buff], 0x61 ; lower case a
jb Write ; jump if byte is below a in ASCII chart
cmp byte [Buff], 0x7a ; lower case z
ja Write ; jump if byte is above z in ASCII chart
sub byte [Buff], 0x20 ; changes the value in the buffer to an uppercase char
Write:
mov eax, 4 ; write syscall
mov ebx, 1 ; stdout
mov ecx, Buff ; what to print
mov edx, 1 ; length is one byte - each char is a byte
int 0x80
jmp Read ; go back to Read
Exit:
mov eax, 1
mov ebx, 0
int 0x80
Sample output:
david#ubuntuserver00A:~/asm$ ./uppercase1 < uppercase1.s
SECTION .BSS
BUFF RESB 1
SECTION .DATA
SECTION .TEXT
GLOBAL _START
_START:
NOP
READ:
MOV EAX, 3 ; READ SYSCALL
MOV EBX, 0 ; STDIN
MOV ECX, BUFF ; PASS ADDRESS OF THE BUFFER TO READ TO
MOV EDX, 1 ; READ ONE CHAR OR ONE BYTE
INT 0X80 ;
CMP EAX, 0 ; IF SYSCALL RETURNS RETURNS 0
JE EXIT ;
CMP BYTE [BUFF], 0X61 ; LOWER CASE A
JB WRITE ; JUMP IF BYTE IS BELOW A IN ASCII CHART
CMP BYTE [BUFF], 0X7A ; LOWER CASE Z
JA WRITE ; JUMP IF BYTE IS ABOVE Z IN ASCII CHART
SUB BYTE [BUFF], 0X20 ; CHANGES THE VALUE IN THE BUFFER TO AN UPPERCASE CHAR
WRITE:
MOV EAX, 4 ; WRITE SYSCALL
MOV EBX, 1 ; STDOUT
MOV ECX, BUFF ; WHAT TO PRINT
MOV EDX, 1 ; LENGTH IS ONE BYTE - EACH CHAR IS A BYTE
INT 0X80
JMP READ ; GO BACK TO READ
EXIT:
MOV EAX, 1
MOV EBX, 0
INT 0X80
i am using nasm and this is my code :
org 0x7c00
bits 16
section .data
zeichen dw 'hello2'
section .text
mov ax,0x7c00
mov es,ax
mov bh,0
mov bp,zeichen
mov ah,13h
mov bl,00h
mov al,1
mov cx,6
mov dh,010h
mov dl,01h
int 10h
jmp $
times 510 - ($-$$) hlt
dw 0xaa55
it does put the cursor on the right position but it prints nothing.
i load this file with qemu-system-i386.
The int10 ah=13h is a string output and in register es:bp has to be the address of the string
For future reference, since i have been trying to get this working for a long time now, here is a working version!
org 0x7c00
bits 16
xor ax, ax
mov es, ax
xor bh, bh
mov bp, msg
mov ah, 0x13
mov bl, [foreground]
mov al, 1
mov cx, [msg_length]
mov dh, [msg_y]
mov dl, [msg_x]
int 0x10
hlt
foreground dw 0xa
msg db 'Beep Boop Meow'
msg_length dw $-msg
msg_x dw 5
msg_y dw 2
times 510 - ($-$$) db 0
dw 0xaa55
here is a version closest to original.
org 0x7c00
bits 16
; video page number.
mov bh, 0
; ES:BP is the pointer to string.
mov ax, 0x0
mov es, ax
mov bp, msg
; attribute(7 is light gray).
mov bl, 0x7
; write mode: character only, cursor moved.
mov al, 1
; string length, hardcoded.
mov cx, 6
; y coordinate
mov dh, 16
; x coordinate
mov dl, 1
; int 10, 13
mov ah, 0x13
int 0x10
; keep jumping until shutdown.
jmp $
msg dw 'hello2'
times 510 - ($-$$) db 0
dw 0xaa55
i'm trying to create a small nasm program which do this operation in floating point
while(input <= 10^5) do
begin
input = input * 10
i = i - 1
end
the equivilant program in nasm is as following
section .data
input: resd 1
n10: dd 0x41200000 ; 10
_start:
mov eax, 0x43480000 ; eax = 200
mov dword [input], eax ; input = eax = 200
mov edx, 0x49742400 ; 10^5
; %begin
mov ecx, 0 ; i = 0
jmp alpha
alpha:
cmp [input], edx ; input <= 10^5
jle _while
jmp log2
_while:
fld dword [input] ; input
fmul dword [n10] ; input * 10
fst dword [input] ; input = input
dec ecx ; i = i - 1
jmp alpha
the _while loop is iterating infinitely
ecx / i gards always the same value = 0 (it is sepposed to be 0) and doesn't decrement
This works for me (tested in DosBox):
org 0x100
bits 16
_start:
mov dword [input], __float32__(99.0)
mov edx, __float32__(10000.0)
mov ecx, 0 ; i = 0
jmp alpha
alpha:
cmp [input],edx ; input <= 10^5
jle _while
jmp log2
_while:
fld dword [input] ; input
fmul dword [n10] ; input * 10
fstp dword [input] ; input = input
inc ecx ; i = i - 1
jmp alpha
log2:
; print the value of cl
mov dl,cl
add dl,'0'
mov ah,2
int 21h
; Exit to DOS
mov ah,0x4c
int 21h
n10: dd 10.0
input: resd 1
Note the bits 16 which tells nasm that 16-bit operands are the default and that instructions using 32-bit operands should be prefixed. Without this your code would be seen as gibberish if you try to execute it in a real-mode environment.It's possible that you'll need to use bits 32 instead, depending on your target environment.
Also note the use of floating-point literals rather than hex values (you had a typo in your code where you compared against 10^6 instead of 10^5).
Suppose that I have an integer number in a register, how can I print it? Can you show a simple example code?
I already know how to print a string such as "hello, world".
I'm developing on Linux.
If you're already on Linux, there's no need to do the conversion yourself. Just use printf instead:
;
; assemble and link with:
; nasm -f elf printf-test.asm && gcc -m32 -o printf-test printf-test.o
;
section .text
global main
extern printf
main:
mov eax, 0xDEADBEEF
push eax
push message
call printf
add esp, 8
ret
message db "Register = %08X", 10, 0
Note that printf uses the cdecl calling convention so we need to restore the stack pointer afterwards, i.e. add 4 bytes per parameter passed to the function.
You have to convert it in a string; if you're talking about hex numbers it's pretty easy. Any number can be represented this way:
0xa31f = 0xf * 16^0 + 0x1 * 16^1 + 3 * 16^2 + 0xa * 16^3
So when you have this number you have to split it like I've shown then convert every "section" to its ASCII equivalent.
Getting the four parts is easily done with some bit magic, in particular with a right shift to move the part we're interested in in the first four bits then AND the result with 0xf to isolate it from the rest. Here's what I mean (soppose we want to take the 3):
0xa31f -> shift right by 8 = 0x00a3 -> AND with 0xf = 0x0003
Now that we have a single number we have to convert it into its ASCII value. If the number is smaller or equal than 9 we can just add 0's ASCII value (0x30), if it's greater than 9 we have to use a's ASCII value (0x61).
Here it is, now we just have to code it:
mov si, ??? ; si points to the target buffer
mov ax, 0a31fh ; ax contains the number we want to convert
mov bx, ax ; store a copy in bx
xor dx, dx ; dx will contain the result
mov cx, 3 ; cx's our counter
convert_loop:
mov ax, bx ; load the number into ax
and ax, 0fh ; we want the first 4 bits
cmp ax, 9h ; check what we should add
ja greater_than_9
add ax, 30h ; 0x30 ('0')
jmp converted
greater_than_9:
add ax, 61h ; or 0x61 ('a')
converted:
xchg al, ah ; put a null terminator after it
mov [si], ax ; (will be overwritten unless this
inc si ; is the last one)
shr bx, 4 ; get the next part
dec cx ; one less to do
jnz convert_loop
sub di, 4 ; di still points to the target buffer
PS: I know this is 16 bit code but I still use the old TASM :P
PPS: this is Intel syntax, converting to AT&T syntax isn't difficult though, look here.
Linux x86-64 with printf
main.asm
default rel ; make [rel format] the default, you always want this.
extern printf, exit ; NASM requires declarations of external symbols, unlike GAS
section .rodata
format db "%#x", 10, 0 ; C 0-terminated string: "%#x\n"
section .text
global main
main:
sub rsp, 8 ; re-align the stack to 16 before calling another function
; Call printf.
mov esi, 0x12345678 ; "%x" takes a 32-bit unsigned int
lea rdi, [rel format]
xor eax, eax ; AL=0 no FP args in XMM regs
call printf
; Return from main.
xor eax, eax
add rsp, 8
ret
GitHub upstream.
Then:
nasm -f elf64 -o main.o main.asm
gcc -no-pie -o main.out main.o
./main.out
Output:
0x12345678
Notes:
sub rsp, 8: How to write assembly language hello world program for 64 bit Mac OS X using printf?
xor eax, eax: Why is %eax zeroed before a call to printf?
-no-pie: plain call printf doesn't work in a PIE executable (-pie), the linker only automatically generates a PLT stub for old-style executables. Your options are:
call printf wrt ..plt to call through the PLT like traditional call printf
call [rel printf wrt ..got] to not use a PLT at all, like gcc -fno-plt.
Like GAS syntax call *printf#GOTPCREL(%rip).
Either of these are fine in a non-PIE executable as well, and don't cause any inefficiency unless you're statically linking libc. In which case call printf can resolve to a call rel32 directly to libc, because the offset from your code to the libc function would be known at static linking time.
See also: Can't call C standard library function on 64-bit Linux from assembly (yasm) code
If you want hex without the C library: Printing Hexadecimal Digits with Assembly
Tested on Ubuntu 18.10, NASM 2.13.03.
It depends on the architecture/environment you are using.
For instance, if I want to display a number on linux, the ASM code will be different from the one I would use on windows.
Edit:
You can refer to THIS for an example of conversion.
I'm relatively new to assembly, and this obviously is not the best solution,
but it's working. The main function is _iprint, it first checks whether the
number in eax is negative, and prints a minus sign if so, than it proceeds
by printing the individual numbers by calling the function _dprint for
every digit. The idea is the following, if we have 512 than it is equal to: 512 = (5 * 10 + 1) * 10 + 2 = Q * 10 + R, so we can found the last digit of a number by dividing it by 10, and
getting the reminder R, but if we do it in a loop than digits will be in a
reverse order, so we use the stack for pushing them, and after that when
writing them to stdout they are popped out in right order.
; Build : nasm -f elf -o baz.o baz.asm
; ld -m elf_i386 -o baz baz.o
section .bss
c: resb 1 ; character buffer
section .data
section .text
; writes an ascii character from eax to stdout
_cprint:
pushad ; push registers
mov [c], eax ; store ascii value at c
mov eax, 0x04 ; sys_write
mov ebx, 1 ; stdout
mov ecx, c ; copy c to ecx
mov edx, 1 ; one character
int 0x80 ; syscall
popad ; pop registers
ret ; bye
; writes a digit stored in eax to stdout
_dprint:
pushad ; push registers
add eax, '0' ; get digit's ascii code
mov [c], eax ; store it at c
mov eax, 0x04 ; sys_write
mov ebx, 1 ; stdout
mov ecx, c ; pass the address of c to ecx
mov edx, 1 ; one character
int 0x80 ; syscall
popad ; pop registers
ret ; bye
; now lets try to write a function which will write an integer
; number stored in eax in decimal at stdout
_iprint:
pushad ; push registers
cmp eax, 0 ; check if eax is negative
jge Pos ; if not proceed in the usual manner
push eax ; store eax
mov eax, '-' ; print minus sign
call _cprint ; call character printing function
pop eax ; restore eax
neg eax ; make eax positive
Pos:
mov ebx, 10 ; base
mov ecx, 1 ; number of digits counter
Cycle1:
mov edx, 0 ; set edx to zero before dividing otherwise the
; program gives an error: SIGFPE arithmetic exception
div ebx ; divide eax with ebx now eax holds the
; quotent and edx the reminder
push edx ; digits we have to write are in reverse order
cmp eax, 0 ; exit loop condition
jz EndLoop1 ; we are done
inc ecx ; increment number of digits counter
jmp Cycle1 ; loop back
EndLoop1:
; write the integer digits by poping them out from the stack
Cycle2:
pop eax ; pop up the digits we have stored
call _dprint ; and print them to stdout
dec ecx ; decrement number of digits counter
jz EndLoop2 ; if it's zero we are done
jmp Cycle2 ; loop back
EndLoop2:
popad ; pop registers
ret ; bye
global _start
_start:
nop ; gdb break point
mov eax, -345 ;
call _iprint ;
mov eax, 0x01 ; sys_exit
mov ebx, 0 ; error code
int 0x80 ; край
Because you didn't say about number representation I wrote the following code for unsigned number with any base(of course not too big), so you could use it:
BITS 32
global _start
section .text
_start:
mov eax, 762002099 ; unsigned number to print
mov ebx, 36 ; base to represent the number, do not set it too big
call print
;exit
mov eax, 1
xor ebx, ebx
int 0x80
print:
mov ecx, esp
sub esp, 36 ; reserve space for the number string, for base-2 it takes 33 bytes with new line, aligned by 4 bytes it takes 36 bytes.
mov edi, 1
dec ecx
mov [ecx], byte 10
print_loop:
xor edx, edx
div ebx
cmp dl, 9 ; if reminder>9 go to use_letter
jg use_letter
add dl, '0'
jmp after_use_letter
use_letter:
add dl, 'W' ; letters from 'a' to ... in ascii code
after_use_letter:
dec ecx
inc edi
mov [ecx],dl
test eax, eax
jnz print_loop
; system call to print, ecx is a pointer on the string
mov eax, 4 ; system call number (sys_write)
mov ebx, 1 ; file descriptor (stdout)
mov edx, edi ; length of the string
int 0x80
add esp, 36 ; release space for the number string
ret
It's not optimised for numbers with base of power of two and doesn't use printf from libc.
The function print outputs the number with a new line. The number string is formed on stack. Compile by nasm.
Output:
clockz
https://github.com/tigertv/stackoverflow-answers/tree/master/8194141-how-to-print-a-number-in-assembly-nasm
I have writen this little experiement bootstrap that has a getline and print_string "functions". The boot stuff is taken from MikeOS tutorial but the rest I have writen myself. I compile this with NASM and run it in QEMU.
So the actual question: I've declared this variable curInpLn on line 6. What ever the user types is saved on that variable and then after enter is hit it is displayed to the user with some additional messages. What I'd like to do is to clear the contents of curInpLn each time the getline function is called but for some reason I can't manage to do that. I'm quite the beginner with Assmebly at the moment.
You can compile the code to bin format and then create a floppy image of it with: "dd status=noxfer conv=notrunc if=FILENAME.bin of=FILENAME.flp" and run it in qemu with: "qemu -fda FILENAME.flp"
BITS 16
jmp start
welcomeSTR: db 'Welcome!',0
promptSTR: db 'Please prompt something: ',0
responseSTR: db 'You prompted: ',0
curInpLn: times 80 db 0 ;this is a variable to hold the input 'command'
curCharCnt: dw 0
curLnNum: dw 1
start:
mov ax, 07C0h ; Set up 4K stack space after this bootloader
add ax, 288 ; (4096 + 512) / 16 bytes per paragraph
mov ss, ax
mov sp, 4096
mov ax, 07C0h ; Set data segment to where we're loaded
mov ds, ax
call clear_screen
lea bx, [welcomeSTR] ; Put string position into SI
call print_string
call new_line
.waitCMD:
lea bx, [promptSTR]
call print_string
call getLine ; Call our string-printing routine
jmp .waitCMD
getLine:
cld
mov cx, 80 ;number of loops for loopne
mov di, 0 ;offset to bx
lea bx, [curInpLn] ;the address of our string
.gtlLoop:
mov ah, 00h ;This is an bios interrupt to
int 16h ;wait for a keypress and save it to al
cmp al, 08h ;see if backspace was pressed
je .gtlRemChar ;if so, jump
mov [bx+di], al ;effective address of our curInpLn string
inc di ;is saved in bx, di is an offset where we will
;insert our char in al
cmp al, 0Dh ;see if character typed is car-return (enter)
je .gtlDone ;if so, jump
mov ah, 0Eh ;bios interrupt to show the char in al
int 10h
.gtlCont:
loopne .gtlLoop ;loopne loops until cx is zero
jmp .gtlDone
.gtlRemChar:
;mov [bx][di-1], 0 ;this needs to be solved. NASM gives error on this.
dec di
jmp .gtlCont
.gtlDone:
call new_line
lea bx, [responseSTR]
call print_string
mov [curCharCnt], di ;save the amount of chars entered to a var
lea bx, [curInpLn]
call print_string
call new_line
ret
print_string: ; Routine: output string in SI to screen
mov si, bx
mov ah, 0Eh ; int 10h 'print char' function
.repeat:
lodsb ; Get character from string
cmp al, 0
je .done ; If char is zero, end of string
int 10h ; Otherwise, print it
jmp .repeat
.done:
ret
new_line:
mov ax, [curLnNum]
inc ax
mov [curLnNum], ax
mov ah, 02h
mov dl, 0
mov dh, [curLnNum]
int 10h
ret
clear_screen:
push ax
mov ax, 3
int 10h
pop ax
ret
times 510-($-$$) db 0 ; Pad remainder of boot sector with 0s
dw 0xAA55 ; The standard PC boot signature
I haven't written code in Assembly for 20 years (!), but it looks like you need to use the 'stosw' instruction (or 'stosb'). STOSB loads the value held in AL to the byte pointed to by ES:DI, whereas STOSSW loads the value held in AX to the word pointed to by ES:DI. The instruction automatically advances the pointer. As your variable curInpLn is 80 bytes long, you can clear it with 40 iterations of STOSW. Something like
xor ax, ax ; ax = 0
mov es, ds ; point es to our data segment
mov di, offset curInpLn ; point di at the variable
mov cx, 40 ; how many repetitions
rep stosw ; zap the variable
This method is probably the quickest method of clearing the variable as it doesn't require the CPU to retrieve any instructions from the pre-fetch queue. In fact, it allows the pre-fetch queue to fill up, thus allowing any following instructions to execute as quickly as possible.